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

Daniel Borkmann says:

====================
pull-request: bpf-next 2019-07-09

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

The main changes are:

1) Lots of libbpf improvements: i) addition of new APIs to attach BPF
   programs to tracing entities such as {k,u}probes or tracepoints,
   ii) improve specification of BTF-defined maps by eliminating the
   need for data initialization for some of the members, iii) addition
   of a high-level API for setting up and polling perf buffers for
   BPF event output helpers, all from Andrii.

2) Add "prog run" subcommand to bpftool in order to test-run programs
   through the kernel testing infrastructure of BPF, from Quentin.

3) Improve verifier for BPF sockaddr programs to support 8-byte stores
   for user_ip6 and msg_src_ip6 members given clang tends to generate
   such stores, from Stanislav.

4) Enable the new BPF JIT zero-extension optimization for further
   riscv64 ALU ops, from Luke.

5) Fix a bpftool json JIT dump crash on powerpc, from Jiri.

6) Fix an AF_XDP race in generic XDP's receive path, from Ilya.

7) Various smaller fixes from Ilya, Yue and Arnd.
====================

Signed-off-by: David S. Miller <[email protected]>

arch/riscv/net/bpf_jit_comp.c

@@ -757,31 +757,31 @@ static int emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 	case BPF_ALU | BPF_ADD | BPF_X:
 	case BPF_ALU64 | BPF_ADD | BPF_X:
 		emit(is64 ? rv_add(rd, rd, rs) : rv_addw(rd, rd, rs), ctx);
-		if (!is64)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_SUB | BPF_X:
 	case BPF_ALU64 | BPF_SUB | BPF_X:
 		emit(is64 ? rv_sub(rd, rd, rs) : rv_subw(rd, rd, rs), ctx);
-		if (!is64)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_AND | BPF_X:
 	case BPF_ALU64 | BPF_AND | BPF_X:
 		emit(rv_and(rd, rd, rs), ctx);
-		if (!is64)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_OR | BPF_X:
 	case BPF_ALU64 | BPF_OR | BPF_X:
 		emit(rv_or(rd, rd, rs), ctx);
-		if (!is64)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_XOR | BPF_X:
 	case BPF_ALU64 | BPF_XOR | BPF_X:
 		emit(rv_xor(rd, rd, rs), ctx);
-		if (!is64)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_MUL | BPF_X:
@@ -811,13 +811,13 @@ static int emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 	case BPF_ALU | BPF_RSH | BPF_X:
 	case BPF_ALU64 | BPF_RSH | BPF_X:
 		emit(is64 ? rv_srl(rd, rd, rs) : rv_srlw(rd, rd, rs), ctx);
-		if (!is64)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_ARSH | BPF_X:
 	case BPF_ALU64 | BPF_ARSH | BPF_X:
 		emit(is64 ? rv_sra(rd, rd, rs) : rv_sraw(rd, rd, rs), ctx);
-		if (!is64)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 
@@ -826,7 +826,7 @@ static int emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 	case BPF_ALU64 | BPF_NEG:
 		emit(is64 ? rv_sub(rd, RV_REG_ZERO, rd) :
 		     rv_subw(rd, RV_REG_ZERO, rd), ctx);
-		if (!is64)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 

include/linux/filter.h

@@ -747,6 +747,12 @@ bpf_ctx_narrow_access_ok(u32 off, u32 size, u32 size_default)
 	return size <= size_default && (size & (size - 1)) == 0;
 }
 
+#define bpf_ctx_wide_store_ok(off, size, type, field)			\
+	(size == sizeof(__u64) &&					\
+	off >= offsetof(type, field) &&					\
+	off + sizeof(__u64) <= offsetofend(type, field) &&		\
+	off % sizeof(__u64) == 0)
+
 #define bpf_classic_proglen(fprog) (fprog->len * sizeof(fprog->filter[0]))
 
 static inline void bpf_prog_lock_ro(struct bpf_prog *fp)

include/net/tcp.h

@@ -2223,9 +2223,7 @@ static inline bool tcp_bpf_ca_needs_ecn(struct sock *sk)
 
 static inline void tcp_bpf_rtt(struct sock *sk)
 {
-	struct tcp_sock *tp = tcp_sk(sk);
-
-	if (BPF_SOCK_OPS_TEST_FLAG(tp, BPF_SOCK_OPS_RTT_CB_FLAG))
+	if (BPF_SOCK_OPS_TEST_FLAG(tcp_sk(sk), BPF_SOCK_OPS_RTT_CB_FLAG))
 		tcp_call_bpf(sk, BPF_SOCK_OPS_RTT_CB, 0, NULL);
 }
 

include/net/xdp_sock.h

@@ -67,6 +67,8 @@ struct xdp_sock {
 	 * in the SKB destructor callback.
 	 */
 	spinlock_t tx_completion_lock;
+	/* Protects generic receive. */
+	spinlock_t rx_lock;
 	u64 rx_dropped;
 };
 

include/uapi/linux/bpf.h

@@ -3247,7 +3247,7 @@ struct bpf_sock_addr {
 	__u32 user_ip4;		/* Allows 1,2,4-byte read and 4-byte write.
 				 * Stored in network byte order.
 				 */
-	__u32 user_ip6[4];	/* Allows 1,2,4-byte read an 4-byte write.
+	__u32 user_ip6[4];	/* Allows 1,2,4-byte read and 4,8-byte write.
 				 * Stored in network byte order.
 				 */
 	__u32 user_port;	/* Allows 4-byte read and write.
@@ -3256,10 +3256,10 @@ struct bpf_sock_addr {
 	__u32 family;		/* Allows 4-byte read, but no write */
 	__u32 type;		/* Allows 4-byte read, but no write */
 	__u32 protocol;		/* Allows 4-byte read, but no write */
-	__u32 msg_src_ip4;	/* Allows 1,2,4-byte read an 4-byte write.
+	__u32 msg_src_ip4;	/* Allows 1,2,4-byte read and 4-byte write.
 				 * Stored in network byte order.
 				 */
-	__u32 msg_src_ip6[4];	/* Allows 1,2,4-byte read an 4-byte write.
+	__u32 msg_src_ip6[4];	/* Allows 1,2,4-byte read and 4,8-byte write.
 				 * Stored in network byte order.
 				 */
 	__bpf_md_ptr(struct bpf_sock *, sk);

kernel/bpf/cgroup.c

@@ -939,6 +939,7 @@ int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head,
 }
 EXPORT_SYMBOL(__cgroup_bpf_run_filter_sysctl);
 
+#ifdef CONFIG_NET
 static bool __cgroup_bpf_prog_array_is_empty(struct cgroup *cgrp,
 					     enum bpf_attach_type attach_type)
 {
@@ -1120,6 +1121,7 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
 	return ret;
 }
 EXPORT_SYMBOL(__cgroup_bpf_run_filter_getsockopt);
+#endif
 
 static ssize_t sysctl_cpy_dir(const struct ctl_dir *dir, char **bufp,
 			      size_t *lenp)
@@ -1386,10 +1388,12 @@ static const struct bpf_func_proto *
 cg_sockopt_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
 	switch (func_id) {
+#ifdef CONFIG_NET
 	case BPF_FUNC_sk_storage_get:
 		return &bpf_sk_storage_get_proto;
 	case BPF_FUNC_sk_storage_delete:
 		return &bpf_sk_storage_delete_proto;
+#endif
 #ifdef CONFIG_INET
 	case BPF_FUNC_tcp_sock:
 		return &bpf_tcp_sock_proto;

net/core/filter.c

@@ -6890,6 +6890,16 @@ static bool sock_addr_is_valid_access(int off, int size,
 			if (!bpf_ctx_narrow_access_ok(off, size, size_default))
 				return false;
 		} else {
+			if (bpf_ctx_wide_store_ok(off, size,
+						  struct bpf_sock_addr,
+						  user_ip6))
+				return true;
+
+			if (bpf_ctx_wide_store_ok(off, size,
+						  struct bpf_sock_addr,
+						  msg_src_ip6))
+				return true;
+
 			if (size != size_default)
 				return false;
 		}
@@ -7730,17 +7740,14 @@ static u32 xdp_convert_ctx_access(enum bpf_access_type type,
 /* SOCK_ADDR_STORE_NESTED_FIELD_OFF() has semantic similar to
  * SOCK_ADDR_LOAD_NESTED_FIELD_SIZE_OFF() but for store operation.
  *
- * It doesn't support SIZE argument though since narrow stores are not
- * supported for now.
- *
  * In addition it uses Temporary Field TF (member of struct S) as the 3rd
  * "register" since two registers available in convert_ctx_access are not
  * enough: we can't override neither SRC, since it contains value to store, nor
  * DST since it contains pointer to context that may be used by later
  * instructions. But we need a temporary place to save pointer to nested
  * structure whose field we want to store to.
  */
-#define SOCK_ADDR_STORE_NESTED_FIELD_OFF(S, NS, F, NF, OFF, TF)		       \
+#define SOCK_ADDR_STORE_NESTED_FIELD_OFF(S, NS, F, NF, SIZE, OFF, TF)	       \
 	do {								       \
 		int tmp_reg = BPF_REG_9;				       \
 		if (si->src_reg == tmp_reg || si->dst_reg == tmp_reg)	       \
@@ -7751,8 +7758,7 @@ static u32 xdp_convert_ctx_access(enum bpf_access_type type,
 				      offsetof(S, TF));			       \
 		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(S, F), tmp_reg,	       \
 				      si->dst_reg, offsetof(S, F));	       \
-		*insn++ = BPF_STX_MEM(					       \
-			BPF_FIELD_SIZEOF(NS, NF), tmp_reg, si->src_reg,	       \
+		*insn++ = BPF_STX_MEM(SIZE, tmp_reg, si->src_reg,	       \
 			bpf_target_off(NS, NF, FIELD_SIZEOF(NS, NF),	       \
 				       target_size)			       \
 				+ OFF);					       \
@@ -7764,8 +7770,8 @@ static u32 xdp_convert_ctx_access(enum bpf_access_type type,
 						      TF)		       \
 	do {								       \
 		if (type == BPF_WRITE) {				       \
-			SOCK_ADDR_STORE_NESTED_FIELD_OFF(S, NS, F, NF, OFF,    \
-							 TF);		       \
+			SOCK_ADDR_STORE_NESTED_FIELD_OFF(S, NS, F, NF, SIZE,   \
+							 OFF, TF);	       \
 		} else {						       \
 			SOCK_ADDR_LOAD_NESTED_FIELD_SIZE_OFF(		       \
 				S, NS, F, NF, SIZE, OFF);  \

net/xdp/xsk.c

@@ -129,13 +129,17 @@ int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
 	u64 addr;
 	int err;
 
-	if (xs->dev != xdp->rxq->dev || xs->queue_id != xdp->rxq->queue_index)
-		return -EINVAL;
+	spin_lock_bh(&xs->rx_lock);
+
+	if (xs->dev != xdp->rxq->dev || xs->queue_id != xdp->rxq->queue_index) {
+		err = -EINVAL;
+		goto out_unlock;
+	}
 
 	if (!xskq_peek_addr(xs->umem->fq, &addr) ||
 	    len > xs->umem->chunk_size_nohr - XDP_PACKET_HEADROOM) {
-		xs->rx_dropped++;
-		return -ENOSPC;
+		err = -ENOSPC;
+		goto out_drop;
 	}
 
 	addr += xs->umem->headroom;
@@ -144,13 +148,21 @@ int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
 	memcpy(buffer, xdp->data_meta, len + metalen);
 	addr += metalen;
 	err = xskq_produce_batch_desc(xs->rx, addr, len);
-	if (!err) {
-		xskq_discard_addr(xs->umem->fq);
-		xsk_flush(xs);
-		return 0;
-	}
+	if (err)
+		goto out_drop;
+
+	xskq_discard_addr(xs->umem->fq);
+	xskq_produce_flush_desc(xs->rx);
 
+	spin_unlock_bh(&xs->rx_lock);
+
+	xs->sk.sk_data_ready(&xs->sk);
+	return 0;
+
+out_drop:
 	xs->rx_dropped++;
+out_unlock:
+	spin_unlock_bh(&xs->rx_lock);
 	return err;
 }
 
@@ -787,6 +799,7 @@ static int xsk_create(struct net *net, struct socket *sock, int protocol,
 
 	xs = xdp_sk(sk);
 	mutex_init(&xs->mutex);
+	spin_lock_init(&xs->rx_lock);
 	spin_lock_init(&xs->tx_completion_lock);
 
 	mutex_lock(&net->xdp.lock);

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

@@ -29,6 +29,7 @@ PROG COMMANDS
 |	**bpftool** **prog attach** *PROG* *ATTACH_TYPE* [*MAP*]
 |	**bpftool** **prog detach** *PROG* *ATTACH_TYPE* [*MAP*]
 |	**bpftool** **prog tracelog**
+|	**bpftool** **prog run** *PROG* **data_in** *FILE* [**data_out** *FILE* [**data_size_out** *L*]] [**ctx_in** *FILE* [**ctx_out** *FILE* [**ctx_size_out** *M*]]] [**repeat** *N*]
 |	**bpftool** **prog help**
 |
 |	*MAP* := { **id** *MAP_ID* | **pinned** *FILE* }
@@ -146,6 +147,39 @@ DESCRIPTION
 		  streaming data from BPF programs to user space, one can use
 		  perf events (see also **bpftool-map**\ (8)).
 
+	**bpftool prog run** *PROG* **data_in** *FILE* [**data_out** *FILE* [**data_size_out** *L*]] [**ctx_in** *FILE* [**ctx_out** *FILE* [**ctx_size_out** *M*]]] [**repeat** *N*]
+		  Run BPF program *PROG* in the kernel testing infrastructure
+		  for BPF, meaning that the program works on the data and
+		  context provided by the user, and not on actual packets or
+		  monitored functions etc. Return value and duration for the
+		  test run are printed out to the console.
+
+		  Input data is read from the *FILE* passed with **data_in**.
+		  If this *FILE* is "**-**", input data is read from standard
+		  input. Input context, if any, is read from *FILE* passed with
+		  **ctx_in**. Again, "**-**" can be used to read from standard
+		  input, but only if standard input is not already in use for
+		  input data. If a *FILE* is passed with **data_out**, output
+		  data is written to that file. Similarly, output context is
+		  written to the *FILE* passed with **ctx_out**. For both
+		  output flows, "**-**" can be used to print to the standard
+		  output (as plain text, or JSON if relevant option was
+		  passed). If output keywords are omitted, output data and
+		  context are discarded. Keywords **data_size_out** and
+		  **ctx_size_out** are used to pass the size (in bytes) for the
+		  output buffers to the kernel, although the default of 32 kB
+		  should be more than enough for most cases.
+
+		  Keyword **repeat** is used to indicate the number of
+		  consecutive runs to perform. Note that output data and
+		  context printed to files correspond to the last of those
+		  runs. The duration printed out at the end of the runs is an
+		  average over all runs performed by the command.
+
+		  Not all program types support test run. Among those which do,
+		  not all of them can take the **ctx_in**/**ctx_out**
+		  arguments. bpftool does not perform checks on program types.
+
 	**bpftool prog help**
 		  Print short help message.
 

tools/bpf/bpftool/bash-completion/bpftool

@@ -342,6 +342,13 @@ _bpftool()
                 load|loadall)
                     local obj
 
+                    # Propose "load/loadall" to complete "bpftool prog load",
+                    # or bash tries to complete "load" as a filename below.
+                    if [[ ${#words[@]} -eq 3 ]]; then
+                        COMPREPLY=( $( compgen -W "load loadall" -- "$cur" ) )
+                        return 0
+                    fi
+
                     if [[ ${#words[@]} -lt 6 ]]; then
                         _filedir
                         return 0
@@ -408,10 +415,34 @@ _bpftool()
                 tracelog)
                     return 0
                     ;;
+                run)
+                    if [[ ${#words[@]} -lt 5 ]]; then
+                        _filedir
+                        return 0
+                    fi
+                    case $prev in
+                        id)
+                            _bpftool_get_prog_ids
+                            return 0
+                            ;;
+                        data_in|data_out|ctx_in|ctx_out)
+                            _filedir
+                            return 0
+                            ;;
+                        repeat|data_size_out|ctx_size_out)
+                            return 0
+                            ;;
+                        *)
+                            _bpftool_once_attr 'data_in data_out data_size_out \
+                                ctx_in ctx_out ctx_size_out repeat'
+                            return 0
+                            ;;
+                    esac
+                    ;;
                 *)
                     [[ $prev == $object ]] && \
-                        COMPREPLY=( $( compgen -W 'dump help pin attach detach load \
-                            show list tracelog' -- "$cur" ) )
+                        COMPREPLY=( $( compgen -W 'dump help pin attach detach \
+                            load loadall show list tracelog run' -- "$cur" ) )
                     ;;
             esac
             ;;

tools/bpf/bpftool/jit_disasm.c

@@ -11,6 +11,8 @@
  * Licensed under the GNU General Public License, version 2.0 (GPLv2)
  */
 
+#define _GNU_SOURCE
+#include <stdio.h>
 #include <stdarg.h>
 #include <stdint.h>
 #include <stdio.h>
@@ -44,11 +46,13 @@ static int fprintf_json(void *out, const char *fmt, ...)
 	char *s;
 
 	va_start(ap, fmt);
+	if (vasprintf(&s, fmt, ap) < 0)
+		return -1;
+	va_end(ap);
+
 	if (!oper_count) {
 		int i;
 
-		s = va_arg(ap, char *);
-
 		/* Strip trailing spaces */
 		i = strlen(s) - 1;
 		while (s[i] == ' ')
@@ -61,11 +65,10 @@ static int fprintf_json(void *out, const char *fmt, ...)
 	} else if (!strcmp(fmt, ",")) {
 		   /* Skip */
 	} else {
-		s = va_arg(ap, char *);
 		jsonw_string(json_wtr, s);
 		oper_count++;
 	}
-	va_end(ap);
+	free(s);
 	return 0;
 }