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

Daniel Borkmann says:

====================
pull-request: bpf 2017-11-23

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

The main changes are:

1) Several BPF offloading fixes, from Jakub. Among others:

    - Limit offload to cls_bpf and XDP program types only.
    - Move device validation into the driver and don't make
      any assumptions about the device in the classifier due
      to shared blocks semantics.
    - Don't pass offloaded XDP program into the driver when
      it should be run in native XDP instead. Offloaded ones
      are not JITed for the host in such cases.
    - Don't destroy device offload state when moved to
      another namespace.
    - Revert dumping offload info into user space for now,
      since ifindex alone is not sufficient. This will be
      redone properly for bpf-next tree.

2) Fix test_verifier to avoid using bpf_probe_write_user()
   helper in test cases, since it's dumping a warning into
   kernel log which may confuse users when only running tests.
   Switch to use bpf_trace_printk() instead, from Yonghong.

3) Several fixes for correcting ARG_CONST_SIZE_OR_ZERO semantics
   before it becomes uabi, from Gianluca. More specifically:

    - Add a type ARG_PTR_TO_MEM_OR_NULL that is used only
      by bpf_csum_diff(), where the argument is either a
      valid pointer or NULL. The subsequent ARG_CONST_SIZE_OR_ZERO
      then enforces a valid pointer in case of non-0 size
      or a valid pointer or NULL in case of size 0. Given
      that, the semantics for ARG_PTR_TO_MEM in combination
      with ARG_CONST_SIZE_OR_ZERO are now such that in case
      of size 0, the pointer must always be valid and cannot
      be NULL. This fix in semantics allows for bpf_probe_read()
      to drop the recently added size == 0 check in the helper
      that would become part of uabi otherwise once released.
      At the same time we can then fix bpf_probe_read_str() and
      bpf_perf_event_output() to use ARG_CONST_SIZE_OR_ZERO
      instead of ARG_CONST_SIZE in order to fix recently
      reported issues by Arnaldo et al, where LLVM optimizes
      two boundary checks into a single one for unknown
      variables where the verifier looses track of the variable
      bounds and thus rejects valid programs otherwise.

4) A fix for the verifier for the case when it detects
   comparison of two constants where the branch is guaranteed
   to not be taken at runtime. Verifier will rightfully prune
   the exploration of such paths, but we still pass the program
   to JITs, where they would complain about using reserved
   fields, etc. Track such dead instructions and sanitize
   them with mov r0,r0. Rejection is not possible since LLVM
   may generate them for valid C code and doesn't do as much
   data flow analysis as verifier. For bpf-next we might
   implement removal of such dead code and adjust branches
   instead. Fix from Alexei.
====================

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

4 files changed, 59 insertions, 51 deletions

diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c
index 2816feb38be1..68ec884440b7 100644
--- a/kernel/bpf/offload.c
+++ b/kernel/bpf/offload.c
@@ -14,8 +14,9 @@ int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr)
 	struct net *net = current->nsproxy->net_ns;
 	struct bpf_dev_offload *offload;
 
-	if (!capable(CAP_SYS_ADMIN))
-		return -EPERM;
+	if (attr->prog_type != BPF_PROG_TYPE_SCHED_CLS &&
+	    attr->prog_type != BPF_PROG_TYPE_XDP)
+		return -EINVAL;
 
 	if (attr->prog_flags)
 		return -EINVAL;
@@ -28,7 +29,7 @@ int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr)
 	init_waitqueue_head(&offload->verifier_done);
 
 	rtnl_lock();
-	offload->netdev = __dev_get_by_index(net, attr->prog_target_ifindex);
+	offload->netdev = __dev_get_by_index(net, attr->prog_ifindex);
 	if (!offload->netdev) {
 		rtnl_unlock();
 		kfree(offload);
@@ -85,6 +86,10 @@ static void __bpf_prog_offload_destroy(struct bpf_prog *prog)
 	struct bpf_dev_offload *offload = prog->aux->offload;
 	struct netdev_bpf data = {};
 
+	/* Caution - if netdev is destroyed before the program, this function
+	 * will be called twice.
+	 */
+
 	data.offload.prog = prog;
 
 	if (offload->verifier_running)
@@ -144,18 +149,6 @@ int bpf_prog_offload_compile(struct bpf_prog *prog)
 	return bpf_prog_offload_translate(prog);
 }
 
-u32 bpf_prog_offload_ifindex(struct bpf_prog *prog)
-{
-	struct bpf_dev_offload *offload = prog->aux->offload;
-	u32 ifindex;
-
-	rtnl_lock();
-	ifindex = offload->netdev ? offload->netdev->ifindex : 0;
-	rtnl_unlock();
-
-	return ifindex;
-}
-
 const struct bpf_prog_ops bpf_offload_prog_ops = {
 };
 
@@ -169,6 +162,10 @@ static int bpf_offload_notification(struct notifier_block *notifier,
 
 	switch (event) {
 	case NETDEV_UNREGISTER:
+		/* ignore namespace changes */
+		if (netdev->reg_state != NETREG_UNREGISTERING)
+			break;
+
 		list_for_each_entry_safe(offload, tmp, &bpf_prog_offload_devs,
 					 offloads) {
 			if (offload->netdev == netdev)
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 09badc37e864..2c4cfeaa8d5e 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1057,22 +1057,23 @@ struct bpf_prog *bpf_prog_inc_not_zero(struct bpf_prog *prog)
 }
 EXPORT_SYMBOL_GPL(bpf_prog_inc_not_zero);
 
-static bool bpf_prog_can_attach(struct bpf_prog *prog,
-				enum bpf_prog_type *attach_type,
-				struct net_device *netdev)
+static bool bpf_prog_get_ok(struct bpf_prog *prog,
+			    enum bpf_prog_type *attach_type, bool attach_drv)
 {
-	struct bpf_dev_offload *offload = prog->aux->offload;
+	/* not an attachment, just a refcount inc, always allow */
+	if (!attach_type)
+		return true;
 
 	if (prog->type != *attach_type)
 		return false;
-	if (offload && offload->netdev != netdev)
+	if (bpf_prog_is_dev_bound(prog->aux) && !attach_drv)
 		return false;
 
 	return true;
 }
 
 static struct bpf_prog *__bpf_prog_get(u32 ufd, enum bpf_prog_type *attach_type,
-				       struct net_device *netdev)
+				       bool attach_drv)
 {
 	struct fd f = fdget(ufd);
 	struct bpf_prog *prog;
@@ -1080,7 +1081,7 @@ static struct bpf_prog *__bpf_prog_get(u32 ufd, enum bpf_prog_type *attach_type,
 	prog = ____bpf_prog_get(f);
 	if (IS_ERR(prog))
 		return prog;
-	if (attach_type && !bpf_prog_can_attach(prog, attach_type, netdev)) {
+	if (!bpf_prog_get_ok(prog, attach_type, attach_drv)) {
 		prog = ERR_PTR(-EINVAL);
 		goto out;
 	}
@@ -1093,23 +1094,13 @@ out:
 
 struct bpf_prog *bpf_prog_get(u32 ufd)
 {
-	return __bpf_prog_get(ufd, NULL, NULL);
+	return __bpf_prog_get(ufd, NULL, false);
 }
 
-struct bpf_prog *bpf_prog_get_type(u32 ufd, enum bpf_prog_type type)
-{
-	struct bpf_prog *prog = __bpf_prog_get(ufd, &type, NULL);
-
-	if (!IS_ERR(prog))
-		trace_bpf_prog_get_type(prog);
-	return prog;
-}
-EXPORT_SYMBOL_GPL(bpf_prog_get_type);
-
 struct bpf_prog *bpf_prog_get_type_dev(u32 ufd, enum bpf_prog_type type,
-				       struct net_device *netdev)
+				       bool attach_drv)
 {
-	struct bpf_prog *prog = __bpf_prog_get(ufd, &type, netdev);
+	struct bpf_prog *prog = __bpf_prog_get(ufd, &type, attach_drv);
 
 	if (!IS_ERR(prog))
 		trace_bpf_prog_get_type(prog);
@@ -1118,7 +1109,7 @@ struct bpf_prog *bpf_prog_get_type_dev(u32 ufd, enum bpf_prog_type type,
 EXPORT_SYMBOL_GPL(bpf_prog_get_type_dev);
 
 /* last field in 'union bpf_attr' used by this command */
-#define	BPF_PROG_LOAD_LAST_FIELD prog_target_ifindex
+#define	BPF_PROG_LOAD_LAST_FIELD prog_ifindex
 
 static int bpf_prog_load(union bpf_attr *attr)
 {
@@ -1181,7 +1172,7 @@ static int bpf_prog_load(union bpf_attr *attr)
 	atomic_set(&prog->aux->refcnt, 1);
 	prog->gpl_compatible = is_gpl ? 1 : 0;
 
-	if (attr->prog_target_ifindex) {
+	if (attr->prog_ifindex) {
 		err = bpf_prog_offload_init(prog, attr);
 		if (err)
 			goto free_prog;
@@ -1625,11 +1616,6 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
 			return -EFAULT;
 	}
 
-	if (bpf_prog_is_dev_bound(prog->aux)) {
-		info.status |= BPF_PROG_STATUS_DEV_BOUND;
-		info.ifindex = bpf_prog_offload_ifindex(prog);
-	}
-
 done:
 	if (copy_to_user(uinfo, &info, info_len) ||
 	    put_user(info_len, &uattr->info.info_len))
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index dd54d20ace2f..d4593571c404 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1384,13 +1384,15 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
 		if (type != expected_type)
 			goto err_type;
 	} else if (arg_type == ARG_PTR_TO_MEM ||
+		   arg_type == ARG_PTR_TO_MEM_OR_NULL ||
 		   arg_type == ARG_PTR_TO_UNINIT_MEM) {
 		expected_type = PTR_TO_STACK;
 		/* One exception here. In case function allows for NULL to be
 		 * passed in as argument, it's a SCALAR_VALUE type. Final test
 		 * happens during stack boundary checking.
 		 */
-		if (register_is_null(*reg))
+		if (register_is_null(*reg) &&
+		    arg_type == ARG_PTR_TO_MEM_OR_NULL)
 			/* final test in check_stack_boundary() */;
 		else if (!type_is_pkt_pointer(type) &&
 			 type != PTR_TO_MAP_VALUE &&
@@ -3825,6 +3827,7 @@ static int do_check(struct bpf_verifier_env *env)
 			return err;
 
 		regs = cur_regs(env);
+		env->insn_aux_data[insn_idx].seen = true;
 		if (class == BPF_ALU || class == BPF_ALU64) {
 			err = check_alu_op(env, insn);
 			if (err)
@@ -4020,6 +4023,7 @@ process_bpf_exit:
 					return err;
 
 				insn_idx++;
+				env->insn_aux_data[insn_idx].seen = true;
 			} else {
 				verbose(env, "invalid BPF_LD mode\n");
 				return -EINVAL;
@@ -4202,6 +4206,7 @@ static int adjust_insn_aux_data(struct bpf_verifier_env *env, u32 prog_len,
 				u32 off, u32 cnt)
 {
 	struct bpf_insn_aux_data *new_data, *old_data = env->insn_aux_data;
+	int i;
 
 	if (cnt == 1)
 		return 0;
@@ -4211,6 +4216,8 @@ static int adjust_insn_aux_data(struct bpf_verifier_env *env, u32 prog_len,
 	memcpy(new_data, old_data, sizeof(struct bpf_insn_aux_data) * off);
 	memcpy(new_data + off + cnt - 1, old_data + off,
 	       sizeof(struct bpf_insn_aux_data) * (prog_len - off - cnt + 1));
+	for (i = off; i < off + cnt - 1; i++)
+		new_data[i].seen = true;
 	env->insn_aux_data = new_data;
 	vfree(old_data);
 	return 0;
@@ -4229,6 +4236,25 @@ static struct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 of
 	return new_prog;
 }
 
+/* The verifier does more data flow analysis than llvm and will not explore
+ * branches that are dead at run time. Malicious programs can have dead code
+ * too. Therefore replace all dead at-run-time code with nops.
+ */
+static void sanitize_dead_code(struct bpf_verifier_env *env)
+{
+	struct bpf_insn_aux_data *aux_data = env->insn_aux_data;
+	struct bpf_insn nop = BPF_MOV64_REG(BPF_REG_0, BPF_REG_0);
+	struct bpf_insn *insn = env->prog->insnsi;
+	const int insn_cnt = env->prog->len;
+	int i;
+
+	for (i = 0; i < insn_cnt; i++) {
+		if (aux_data[i].seen)
+			continue;
+		memcpy(insn + i, &nop, sizeof(nop));
+	}
+}
+
 /* convert load instructions that access fields of 'struct __sk_buff'
  * into sequence of instructions that access fields of 'struct sk_buff'
  */
@@ -4556,6 +4582,9 @@ skip_full_check:
 	free_states(env);
 
 	if (ret == 0)
+		sanitize_dead_code(env);
+
+	if (ret == 0)
 		/* program is valid, convert *(u32*)(ctx + off) accesses */
 		ret = convert_ctx_accesses(env);
 
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index a5580c670866..27d1f4ffa3de 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -78,16 +78,12 @@ EXPORT_SYMBOL_GPL(trace_call_bpf);
 
 BPF_CALL_3(bpf_probe_read, void *, dst, u32, size, const void *, unsafe_ptr)
 {
-	int ret = 0;
-
-	if (unlikely(size == 0))
-		goto out;
+	int ret;
 
 	ret = probe_kernel_read(dst, unsafe_ptr, size);
 	if (unlikely(ret < 0))
 		memset(dst, 0, size);
 
- out:
 	return ret;
 }
 
@@ -407,7 +403,7 @@ static const struct bpf_func_proto bpf_perf_event_output_proto = {
 	.arg2_type	= ARG_CONST_MAP_PTR,
 	.arg3_type	= ARG_ANYTHING,
 	.arg4_type	= ARG_PTR_TO_MEM,
-	.arg5_type	= ARG_CONST_SIZE,
+	.arg5_type	= ARG_CONST_SIZE_OR_ZERO,
 };
 
 static DEFINE_PER_CPU(struct pt_regs, bpf_pt_regs);
@@ -498,7 +494,7 @@ static const struct bpf_func_proto bpf_probe_read_str_proto = {
 	.gpl_only	= true,
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_PTR_TO_UNINIT_MEM,
-	.arg2_type	= ARG_CONST_SIZE,
+	.arg2_type	= ARG_CONST_SIZE_OR_ZERO,
 	.arg3_type	= ARG_ANYTHING,
 };
 
@@ -609,7 +605,7 @@ static const struct bpf_func_proto bpf_perf_event_output_proto_tp = {
 	.arg2_type	= ARG_CONST_MAP_PTR,
 	.arg3_type	= ARG_ANYTHING,
 	.arg4_type	= ARG_PTR_TO_MEM,
-	.arg5_type	= ARG_CONST_SIZE,
+	.arg5_type	= ARG_CONST_SIZE_OR_ZERO,
 };
 
 BPF_CALL_3(bpf_get_stackid_tp, void *, tp_buff, struct bpf_map *, map,