Merge tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf

Daniel Borkmann says:

====================
pull-request: bpf 2023-10-02

We've added 11 non-merge commits during the last 12 day(s) which contain
a total of 12 files changed, 176 insertions(+), 41 deletions(-).

The main changes are:

1) Fix BPF verifier to reset backtrack_state masks on global function
   exit as otherwise subsequent precision tracking would reuse them,
   from Andrii Nakryiko.

2) Several sockmap fixes for available bytes accounting,
   from John Fastabend.

3) Reject sk_msg egress redirects to non-TCP sockets given this
   is only supported for TCP sockets today, from Jakub Sitnicki.

4) Fix a syzkaller splat in bpf_mprog when hitting maximum program
   limits with BPF_F_BEFORE directive, from Daniel Borkmann
   and Nikolay Aleksandrov.

5) Fix BPF memory allocator to use kmalloc_size_roundup() to adjust
   size_index for selecting a bpf_mem_cache, from Hou Tao.

6) Fix arch_prepare_bpf_trampoline return code for s390 JIT,
   from Song Liu.

7) Fix bpf_trampoline_get when CONFIG_BPF_JIT is turned off,
   from Leon Hwang.

* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf:
  bpf: Use kmalloc_size_roundup() to adjust size_index
  selftest/bpf: Add various selftests for program limits
  bpf, mprog: Fix maximum program check on mprog attachment
  bpf, sockmap: Reject sk_msg egress redirects to non-TCP sockets
  bpf, sockmap: Add tests for MSG_F_PEEK
  bpf, sockmap: Do not inc copied_seq when PEEK flag set
  bpf: tcp_read_skb needs to pop skb regardless of seq
  bpf: unconditionally reset backtrack_state masks on global func exit
  bpf: Fix tr dereferencing
  selftests/bpf: Check bpf_cubic_acked() is called via struct_ops
  s390/bpf: Let arch_prepare_bpf_trampoline return program size
====================

Link: https://lore.kernel.org/r/20231002113417.2309-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

3 files changed, 25 insertions, 30 deletions

diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c
index cf1941516643..d93ddac283d4 100644
--- a/kernel/bpf/memalloc.c
+++ b/kernel/bpf/memalloc.c
@@ -965,37 +965,31 @@ void notrace *bpf_mem_cache_alloc_flags(struct bpf_mem_alloc *ma, gfp_t flags)
 	return !ret ? NULL : ret + LLIST_NODE_SZ;
 }
 
-/* Most of the logic is taken from setup_kmalloc_cache_index_table() */
 static __init int bpf_mem_cache_adjust_size(void)
 {
-	unsigned int size, index;
+	unsigned int size;
 
-	/* Normally KMALLOC_MIN_SIZE is 8-bytes, but it can be
-	 * up-to 256-bytes.
+	/* Adjusting the indexes in size_index() according to the object_size
+	 * of underlying slab cache, so bpf_mem_alloc() will select a
+	 * bpf_mem_cache with unit_size equal to the object_size of
+	 * the underlying slab cache.
+	 *
+	 * The maximal value of KMALLOC_MIN_SIZE and __kmalloc_minalign() is
+	 * 256-bytes, so only do adjustment for [8-bytes, 192-bytes].
 	 */
-	size = KMALLOC_MIN_SIZE;
-	if (size <= 192)
-		index = size_index[(size - 1) / 8];
-	else
-		index = fls(size - 1) - 1;
-	for (size = 8; size < KMALLOC_MIN_SIZE && size <= 192; size += 8)
-		size_index[(size - 1) / 8] = index;
+	for (size = 192; size >= 8; size -= 8) {
+		unsigned int kmalloc_size, index;
 
-	/* The minimal alignment is 64-bytes, so disable 96-bytes cache and
-	 * use 128-bytes cache instead.
-	 */
-	if (KMALLOC_MIN_SIZE >= 64) {
-		index = size_index[(128 - 1) / 8];
-		for (size = 64 + 8; size <= 96; size += 8)
-			size_index[(size - 1) / 8] = index;
-	}
+		kmalloc_size = kmalloc_size_roundup(size);
+		if (kmalloc_size == size)
+			continue;
 
-	/* The minimal alignment is 128-bytes, so disable 192-bytes cache and
-	 * use 256-bytes cache instead.
-	 */
-	if (KMALLOC_MIN_SIZE >= 128) {
-		index = fls(256 - 1) - 1;
-		for (size = 128 + 8; size <= 192; size += 8)
+		if (kmalloc_size <= 192)
+			index = size_index[(kmalloc_size - 1) / 8];
+		else
+			index = fls(kmalloc_size - 1) - 1;
+		/* Only overwrite if necessary */
+		if (size_index[(size - 1) / 8] != index)
 			size_index[(size - 1) / 8] = index;
 	}
 
diff --git a/kernel/bpf/mprog.c b/kernel/bpf/mprog.c
index 32d2c4829eb8..007d98c799e2 100644
--- a/kernel/bpf/mprog.c
+++ b/kernel/bpf/mprog.c
@@ -253,6 +253,9 @@ int bpf_mprog_attach(struct bpf_mprog_entry *entry,
 			goto out;
 		}
 		idx = tidx;
+	} else if (bpf_mprog_total(entry) == bpf_mprog_max()) {
+		ret = -ERANGE;
+		goto out;
 	}
 	if (flags & BPF_F_BEFORE) {
 		tidx = bpf_mprog_pos_before(entry, &rtuple);
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index bb78212fa5b2..c0c7d137066a 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -4047,11 +4047,9 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno)
 				bitmap_from_u64(mask, bt_reg_mask(bt));
 				for_each_set_bit(i, mask, 32) {
 					reg = &st->frame[0]->regs[i];
-					if (reg->type != SCALAR_VALUE) {
-						bt_clear_reg(bt, i);
-						continue;
-					}
-					reg->precise = true;
+					bt_clear_reg(bt, i);
+					if (reg->type == SCALAR_VALUE)
+						reg->precise = true;
 				}
 				return 0;
 			}