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

Daniel Borkmann says:

====================
pull-request: bpf-next 2022-05-23

We've added 113 non-merge commits during the last 26 day(s) which contain
a total of 121 files changed, 7425 insertions(+), 1586 deletions(-).

The main changes are:

1) Speed up symbol resolution for kprobes multi-link attachments, from Jiri Olsa.

2) Add BPF dynamic pointer infrastructure e.g. to allow for dynamically sized ringbuf
   reservations without extra memory copies, from Joanne Koong.

3) Big batch of libbpf improvements towards libbpf 1.0 release, from Andrii Nakryiko.

4) Add BPF link iterator to traverse links via seq_file ops, from Dmitrii Dolgov.

5) Add source IP address to BPF tunnel key infrastructure, from Kaixi Fan.

6) Refine unprivileged BPF to disable only object-creating commands, from Alan Maguire.

7) Fix JIT blinding of ld_imm64 when they point to subprogs, from Alexei Starovoitov.

8) Add BPF access to mptcp_sock structures and their meta data, from Geliang Tang.

9) Add new BPF helper for access to remote CPU's BPF map elements, from Feng Zhou.

10) Allow attaching 64-bit cookie to BPF link of fentry/fexit/fmod_ret, from Kui-Feng Lee.

11) Follow-ups to typed pointer support in BPF maps, from Kumar Kartikeya Dwivedi.

12) Add busy-poll test cases to the XSK selftest suite, from Magnus Karlsson.

13) Improvements in BPF selftest test_progs subtest output, from Mykola Lysenko.

14) Fill bpf_prog_pack allocator areas with illegal instructions, from Song Liu.

15) Add generic batch operations for BPF map-in-map cases, from Takshak Chahande.

16) Make bpf_jit_enable more user friendly when permanently on 1, from Tiezhu Yang.

17) Fix an array overflow in bpf_trampoline_get_progs(), from Yuntao Wang.

====================

Link: https://lore.kernel.org/r/20220523223805.27931-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 53 insertions, 22 deletions

diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index e0aead17dff4..2b69306d3c6e 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2864,19 +2864,12 @@ struct bpf_link *bpf_link_get_from_fd(u32 ufd)
 }
 EXPORT_SYMBOL(bpf_link_get_from_fd);
 
-struct bpf_tracing_link {
-	struct bpf_link link;
-	enum bpf_attach_type attach_type;
-	struct bpf_trampoline *trampoline;
-	struct bpf_prog *tgt_prog;
-};
-
 static void bpf_tracing_link_release(struct bpf_link *link)
 {
 	struct bpf_tracing_link *tr_link =
-		container_of(link, struct bpf_tracing_link, link);
+		container_of(link, struct bpf_tracing_link, link.link);
 
-	WARN_ON_ONCE(bpf_trampoline_unlink_prog(link->prog,
+	WARN_ON_ONCE(bpf_trampoline_unlink_prog(&tr_link->link,
 						tr_link->trampoline));
 
 	bpf_trampoline_put(tr_link->trampoline);
@@ -2889,7 +2882,7 @@ static void bpf_tracing_link_release(struct bpf_link *link)
 static void bpf_tracing_link_dealloc(struct bpf_link *link)
 {
 	struct bpf_tracing_link *tr_link =
-		container_of(link, struct bpf_tracing_link, link);
+		container_of(link, struct bpf_tracing_link, link.link);
 
 	kfree(tr_link);
 }
@@ -2898,7 +2891,7 @@ static void bpf_tracing_link_show_fdinfo(const struct bpf_link *link,
 					 struct seq_file *seq)
 {
 	struct bpf_tracing_link *tr_link =
-		container_of(link, struct bpf_tracing_link, link);
+		container_of(link, struct bpf_tracing_link, link.link);
 
 	seq_printf(seq,
 		   "attach_type:\t%d\n",
@@ -2909,7 +2902,7 @@ static int bpf_tracing_link_fill_link_info(const struct bpf_link *link,
 					   struct bpf_link_info *info)
 {
 	struct bpf_tracing_link *tr_link =
-		container_of(link, struct bpf_tracing_link, link);
+		container_of(link, struct bpf_tracing_link, link.link);
 
 	info->tracing.attach_type = tr_link->attach_type;
 	bpf_trampoline_unpack_key(tr_link->trampoline->key,
@@ -2928,7 +2921,8 @@ static const struct bpf_link_ops bpf_tracing_link_lops = {
 
 static int bpf_tracing_prog_attach(struct bpf_prog *prog,
 				   int tgt_prog_fd,
-				   u32 btf_id)
+				   u32 btf_id,
+				   u64 bpf_cookie)
 {
 	struct bpf_link_primer link_primer;
 	struct bpf_prog *tgt_prog = NULL;
@@ -2990,9 +2984,10 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog,
 		err = -ENOMEM;
 		goto out_put_prog;
 	}
-	bpf_link_init(&link->link, BPF_LINK_TYPE_TRACING,
+	bpf_link_init(&link->link.link, BPF_LINK_TYPE_TRACING,
 		      &bpf_tracing_link_lops, prog);
 	link->attach_type = prog->expected_attach_type;
+	link->link.cookie = bpf_cookie;
 
 	mutex_lock(&prog->aux->dst_mutex);
 
@@ -3060,11 +3055,11 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog,
 		tgt_prog = prog->aux->dst_prog;
 	}
 
-	err = bpf_link_prime(&link->link, &link_primer);
+	err = bpf_link_prime(&link->link.link, &link_primer);
 	if (err)
 		goto out_unlock;
 
-	err = bpf_trampoline_link_prog(prog, tr);
+	err = bpf_trampoline_link_prog(&link->link, tr);
 	if (err) {
 		bpf_link_cleanup(&link_primer);
 		link = NULL;
@@ -3278,7 +3273,7 @@ static int bpf_raw_tp_link_attach(struct bpf_prog *prog,
 			tp_name = prog->aux->attach_func_name;
 			break;
 		}
-		return bpf_tracing_prog_attach(prog, 0, 0);
+		return bpf_tracing_prog_attach(prog, 0, 0, 0);
 	case BPF_PROG_TYPE_RAW_TRACEPOINT:
 	case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE:
 		if (strncpy_from_user(buf, user_tp_name, sizeof(buf) - 1) < 0)
@@ -4531,7 +4526,8 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr)
 	case BPF_PROG_TYPE_EXT:
 		ret = bpf_tracing_prog_attach(prog,
 					      attr->link_create.target_fd,
-					      attr->link_create.target_btf_id);
+					      attr->link_create.target_btf_id,
+					      attr->link_create.tracing.cookie);
 		break;
 	case BPF_PROG_TYPE_LSM:
 	case BPF_PROG_TYPE_TRACING:
@@ -4546,7 +4542,8 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr)
 		else
 			ret = bpf_tracing_prog_attach(prog,
 						      attr->link_create.target_fd,
-						      attr->link_create.target_btf_id);
+						      attr->link_create.target_btf_id,
+						      attr->link_create.tracing.cookie);
 		break;
 	case BPF_PROG_TYPE_FLOW_DISSECTOR:
 	case BPF_PROG_TYPE_SK_LOOKUP:
@@ -4680,6 +4677,25 @@ struct bpf_link *bpf_link_by_id(u32 id)
 	return link;
 }
 
+struct bpf_link *bpf_link_get_curr_or_next(u32 *id)
+{
+	struct bpf_link *link;
+
+	spin_lock_bh(&link_idr_lock);
+again:
+	link = idr_get_next(&link_idr, id);
+	if (link) {
+		link = bpf_link_inc_not_zero(link);
+		if (IS_ERR(link)) {
+			(*id)++;
+			goto again;
+		}
+	}
+	spin_unlock_bh(&link_idr_lock);
+
+	return link;
+}
+
 #define BPF_LINK_GET_FD_BY_ID_LAST_FIELD link_id
 
 static int bpf_link_get_fd_by_id(const union bpf_attr *attr)
@@ -4847,9 +4863,21 @@ out_prog_put:
 static int __sys_bpf(int cmd, bpfptr_t uattr, unsigned int size)
 {
 	union bpf_attr attr;
+	bool capable;
 	int err;
 
-	if (sysctl_unprivileged_bpf_disabled && !bpf_capable())
+	capable = bpf_capable() || !sysctl_unprivileged_bpf_disabled;
+
+	/* Intent here is for unprivileged_bpf_disabled to block key object
+	 * creation commands for unprivileged users; other actions depend
+	 * of fd availability and access to bpffs, so are dependent on
+	 * object creation success.  Capabilities are later verified for
+	 * operations such as load and map create, so even with unprivileged
+	 * BPF disabled, capability checks are still carried out for these
+	 * and other operations.
+	 */
+	if (!capable &&
+	    (cmd == BPF_MAP_CREATE || cmd == BPF_PROG_LOAD))
 		return -EPERM;
 
 	err = bpf_check_uarg_tail_zero(uattr, sizeof(attr), size);
@@ -5008,6 +5036,7 @@ static bool syscall_prog_is_valid_access(int off, int size,
 BPF_CALL_3(bpf_sys_bpf, int, cmd, union bpf_attr *, attr, u32, attr_size)
 {
 	struct bpf_prog * __maybe_unused prog;
+	struct bpf_tramp_run_ctx __maybe_unused run_ctx;
 
 	switch (cmd) {
 	case BPF_MAP_CREATE:
@@ -5035,13 +5064,15 @@ BPF_CALL_3(bpf_sys_bpf, int, cmd, union bpf_attr *, attr, u32, attr_size)
 			return -EINVAL;
 		}
 
-		if (!__bpf_prog_enter_sleepable(prog)) {
+		run_ctx.bpf_cookie = 0;
+		run_ctx.saved_run_ctx = NULL;
+		if (!__bpf_prog_enter_sleepable(prog, &run_ctx)) {
 			/* recursion detected */
 			bpf_prog_put(prog);
 			return -EBUSY;
 		}
 		attr->test.retval = bpf_prog_run(prog, (void *) (long) attr->test.ctx_in);
-		__bpf_prog_exit_sleepable(prog, 0 /* bpf_prog_run does runtime stats */);
+		__bpf_prog_exit_sleepable(prog, 0 /* bpf_prog_run does runtime stats */, &run_ctx);
 		bpf_prog_put(prog);
 		return 0;
 #endif