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

Daniel Borkmann says:

====================
pull-request: bpf 2021-11-16

We've added 12 non-merge commits during the last 5 day(s) which contain
a total of 23 files changed, 573 insertions(+), 73 deletions(-).

The main changes are:

1) Fix pruning regression where verifier went overly conservative rejecting
   previsouly accepted programs, from Alexei Starovoitov and Lorenz Bauer.

2) Fix verifier TOCTOU bug when using read-only map's values as constant
   scalars during verification, from Daniel Borkmann.

3) Fix a crash due to a double free in XSK's buffer pool, from Magnus Karlsson.

4) Fix libbpf regression when cross-building runqslower, from Jean-Philippe Brucker.

5) Forbid use of bpf_ktime_get_coarse_ns() and bpf_timer_*() helpers in tracing
   programs due to deadlock possibilities, from Dmitrii Banshchikov.

6) Fix checksum validation in sockmap's udp_read_sock() callback, from Cong Wang.

7) Various BPF sample fixes such as XDP stats in xdp_sample_user, from Alexander Lobakin.

8) Fix libbpf gen_loader error handling wrt fd cleanup, from Kumar Kartikeya Dwivedi.

* https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf:
  udp: Validate checksum in udp_read_sock()
  bpf: Fix toctou on read-only map's constant scalar tracking
  samples/bpf: Fix build error due to -isystem removal
  selftests/bpf: Add tests for restricted helpers
  bpf: Forbid bpf_ktime_get_coarse_ns and bpf_timer_* in tracing progs
  libbpf: Perform map fd cleanup for gen_loader in case of error
  samples/bpf: Fix incorrect use of strlen in xdp_redirect_cpu
  tools/runqslower: Fix cross-build
  samples/bpf: Fix summary per-sec stats in xdp_sample_user
  selftests/bpf: Check map in map pruning
  bpf: Fix inner map state pruning regression.
  xsk: Fix crash on double free in buffer pool
====================

Link: https://lore.kernel.org/r/20211116141134.6490-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

5 files changed, 63 insertions, 27 deletions

diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 2ca643af9a54..43eb3501721b 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -1809,6 +1809,8 @@ sysctl_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_sysctl_get_new_value_proto;
 	case BPF_FUNC_sysctl_set_new_value:
 		return &bpf_sysctl_set_new_value_proto;
+	case BPF_FUNC_ktime_get_coarse_ns:
+		return &bpf_ktime_get_coarse_ns_proto;
 	default:
 		return cgroup_base_func_proto(func_id, prog);
 	}
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 1ffd469c217f..649f07623df6 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -1364,8 +1364,6 @@ bpf_base_func_proto(enum bpf_func_id func_id)
 		return &bpf_ktime_get_ns_proto;
 	case BPF_FUNC_ktime_get_boot_ns:
 		return &bpf_ktime_get_boot_ns_proto;
-	case BPF_FUNC_ktime_get_coarse_ns:
-		return &bpf_ktime_get_coarse_ns_proto;
 	case BPF_FUNC_ringbuf_output:
 		return &bpf_ringbuf_output_proto;
 	case BPF_FUNC_ringbuf_reserve:
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 50f96ea4452a..1033ee8c0caf 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -132,6 +132,21 @@ static struct bpf_map *find_and_alloc_map(union bpf_attr *attr)
 	return map;
 }
 
+static void bpf_map_write_active_inc(struct bpf_map *map)
+{
+	atomic64_inc(&map->writecnt);
+}
+
+static void bpf_map_write_active_dec(struct bpf_map *map)
+{
+	atomic64_dec(&map->writecnt);
+}
+
+bool bpf_map_write_active(const struct bpf_map *map)
+{
+	return atomic64_read(&map->writecnt) != 0;
+}
+
 static u32 bpf_map_value_size(const struct bpf_map *map)
 {
 	if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
@@ -601,11 +616,8 @@ static void bpf_map_mmap_open(struct vm_area_struct *vma)
 {
 	struct bpf_map *map = vma->vm_file->private_data;
 
-	if (vma->vm_flags & VM_MAYWRITE) {
-		mutex_lock(&map->freeze_mutex);
-		map->writecnt++;
-		mutex_unlock(&map->freeze_mutex);
-	}
+	if (vma->vm_flags & VM_MAYWRITE)
+		bpf_map_write_active_inc(map);
 }
 
 /* called for all unmapped memory region (including initial) */
@@ -613,11 +625,8 @@ static void bpf_map_mmap_close(struct vm_area_struct *vma)
 {
 	struct bpf_map *map = vma->vm_file->private_data;
 
-	if (vma->vm_flags & VM_MAYWRITE) {
-		mutex_lock(&map->freeze_mutex);
-		map->writecnt--;
-		mutex_unlock(&map->freeze_mutex);
-	}
+	if (vma->vm_flags & VM_MAYWRITE)
+		bpf_map_write_active_dec(map);
 }
 
 static const struct vm_operations_struct bpf_map_default_vmops = {
@@ -668,7 +677,7 @@ static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma)
 		goto out;
 
 	if (vma->vm_flags & VM_MAYWRITE)
-		map->writecnt++;
+		bpf_map_write_active_inc(map);
 out:
 	mutex_unlock(&map->freeze_mutex);
 	return err;
@@ -1139,6 +1148,7 @@ static int map_update_elem(union bpf_attr *attr, bpfptr_t uattr)
 	map = __bpf_map_get(f);
 	if (IS_ERR(map))
 		return PTR_ERR(map);
+	bpf_map_write_active_inc(map);
 	if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) {
 		err = -EPERM;
 		goto err_put;
@@ -1174,6 +1184,7 @@ free_value:
 free_key:
 	kvfree(key);
 err_put:
+	bpf_map_write_active_dec(map);
 	fdput(f);
 	return err;
 }
@@ -1196,6 +1207,7 @@ static int map_delete_elem(union bpf_attr *attr)
 	map = __bpf_map_get(f);
 	if (IS_ERR(map))
 		return PTR_ERR(map);
+	bpf_map_write_active_inc(map);
 	if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) {
 		err = -EPERM;
 		goto err_put;
@@ -1226,6 +1238,7 @@ static int map_delete_elem(union bpf_attr *attr)
 out:
 	kvfree(key);
 err_put:
+	bpf_map_write_active_dec(map);
 	fdput(f);
 	return err;
 }
@@ -1533,6 +1546,7 @@ static int map_lookup_and_delete_elem(union bpf_attr *attr)
 	map = __bpf_map_get(f);
 	if (IS_ERR(map))
 		return PTR_ERR(map);
+	bpf_map_write_active_inc(map);
 	if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ) ||
 	    !(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) {
 		err = -EPERM;
@@ -1597,6 +1611,7 @@ free_value:
 free_key:
 	kvfree(key);
 err_put:
+	bpf_map_write_active_dec(map);
 	fdput(f);
 	return err;
 }
@@ -1624,8 +1639,7 @@ static int map_freeze(const union bpf_attr *attr)
 	}
 
 	mutex_lock(&map->freeze_mutex);
-
-	if (map->writecnt) {
+	if (bpf_map_write_active(map)) {
 		err = -EBUSY;
 		goto err_put;
 	}
@@ -4171,6 +4185,9 @@ static int bpf_map_do_batch(const union bpf_attr *attr,
 			    union bpf_attr __user *uattr,
 			    int cmd)
 {
+	bool has_read  = cmd == BPF_MAP_LOOKUP_BATCH ||
+			 cmd == BPF_MAP_LOOKUP_AND_DELETE_BATCH;
+	bool has_write = cmd != BPF_MAP_LOOKUP_BATCH;
 	struct bpf_map *map;
 	int err, ufd;
 	struct fd f;
@@ -4183,16 +4200,13 @@ static int bpf_map_do_batch(const union bpf_attr *attr,
 	map = __bpf_map_get(f);
 	if (IS_ERR(map))
 		return PTR_ERR(map);
-
-	if ((cmd == BPF_MAP_LOOKUP_BATCH ||
-	     cmd == BPF_MAP_LOOKUP_AND_DELETE_BATCH) &&
-	    !(map_get_sys_perms(map, f) & FMODE_CAN_READ)) {
+	if (has_write)
+		bpf_map_write_active_inc(map);
+	if (has_read && !(map_get_sys_perms(map, f) & FMODE_CAN_READ)) {
 		err = -EPERM;
 		goto err_put;
 	}
-
-	if (cmd != BPF_MAP_LOOKUP_BATCH &&
-	    !(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) {
+	if (has_write && !(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) {
 		err = -EPERM;
 		goto err_put;
 	}
@@ -4205,8 +4219,9 @@ static int bpf_map_do_batch(const union bpf_attr *attr,
 		BPF_DO_BATCH(map->ops->map_update_batch);
 	else
 		BPF_DO_BATCH(map->ops->map_delete_batch);
-
 err_put:
+	if (has_write)
+		bpf_map_write_active_dec(map);
 	fdput(f);
 	return err;
 }
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 890b3ec375a3..50efda51515b 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1151,7 +1151,8 @@ static void mark_ptr_not_null_reg(struct bpf_reg_state *reg)
 			/* transfer reg's id which is unique for every map_lookup_elem
 			 * as UID of the inner map.
 			 */
-			reg->map_uid = reg->id;
+			if (map_value_has_timer(map->inner_map_meta))
+				reg->map_uid = reg->id;
 		} else if (map->map_type == BPF_MAP_TYPE_XSKMAP) {
 			reg->type = PTR_TO_XDP_SOCK;
 		} else if (map->map_type == BPF_MAP_TYPE_SOCKMAP ||
@@ -4055,7 +4056,22 @@ static void coerce_reg_to_size(struct bpf_reg_state *reg, int size)
 
 static bool bpf_map_is_rdonly(const struct bpf_map *map)
 {
-	return (map->map_flags & BPF_F_RDONLY_PROG) && map->frozen;
+	/* A map is considered read-only if the following condition are true:
+	 *
+	 * 1) BPF program side cannot change any of the map content. The
+	 *    BPF_F_RDONLY_PROG flag is throughout the lifetime of a map
+	 *    and was set at map creation time.
+	 * 2) The map value(s) have been initialized from user space by a
+	 *    loader and then "frozen", such that no new map update/delete
+	 *    operations from syscall side are possible for the rest of
+	 *    the map's lifetime from that point onwards.
+	 * 3) Any parallel/pending map update/delete operations from syscall
+	 *    side have been completed. Only after that point, it's safe to
+	 *    assume that map value(s) are immutable.
+	 */
+	return (map->map_flags & BPF_F_RDONLY_PROG) &&
+	       READ_ONCE(map->frozen) &&
+	       !bpf_map_write_active(map);
 }
 
 static int bpf_map_direct_read(struct bpf_map *map, int off, int size, u64 *val)
@@ -11631,6 +11647,13 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env,
 		}
 	}
 
+	if (map_value_has_timer(map)) {
+		if (is_tracing_prog_type(prog_type)) {
+			verbose(env, "tracing progs cannot use bpf_timer yet\n");
+			return -EINVAL;
+		}
+	}
+
 	if ((bpf_prog_is_dev_bound(prog->aux) || bpf_map_is_dev_bound(map)) &&
 	    !bpf_offload_prog_map_match(prog, map)) {
 		verbose(env, "offload device mismatch between prog and map\n");
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 7396488793ff..ae9755037b7e 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1111,8 +1111,6 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_ktime_get_ns_proto;
 	case BPF_FUNC_ktime_get_boot_ns:
 		return &bpf_ktime_get_boot_ns_proto;
-	case BPF_FUNC_ktime_get_coarse_ns:
-		return &bpf_ktime_get_coarse_ns_proto;
 	case BPF_FUNC_tail_call:
 		return &bpf_tail_call_proto;
 	case BPF_FUNC_get_current_pid_tgid: