Merge tag 'bpf-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf

Pull BPF fixes from Daniel Borkmann:

 - Fix a soft-lockup in BPF arena_map_free on 64k page size kernels
   (Alan Maguire)

 - Fix a missing allocation failure check in BPF verifier's
   acquire_lock_state (Kumar Kartikeya Dwivedi)

 - Fix a NULL-pointer dereference in trace_kfree_skb by adding kfree_skb
   to the raw_tp_null_args set (Kuniyuki Iwashima)

 - Fix a deadlock when freeing BPF cgroup storage (Abel Wu)

 - Fix a syzbot-reported deadlock when holding BPF map's freeze_mutex
   (Andrii Nakryiko)

 - Fix a use-after-free issue in bpf_test_init when eth_skb_pkt_type is
   accessing skb data not containing an Ethernet header (Shigeru
   Yoshida)

 - Fix skipping non-existing keys in generic_map_lookup_batch (Yan Zhai)

 - Several BPF sockmap fixes to address incorrect TCP copied_seq
   calculations, which prevented correct data reads from recv(2) in user
   space (Jiayuan Chen)

 - Two fixes for BPF map lookup nullness elision (Daniel Xu)

 - Fix a NULL-pointer dereference from vmlinux BTF lookup in
   bpf_sk_storage_tracing_allowed (Jared Kangas)

* tag 'bpf-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf:
  selftests: bpf: test batch lookup on array of maps with holes
  bpf: skip non exist keys in generic_map_lookup_batch
  bpf: Handle allocation failure in acquire_lock_state
  bpf: verifier: Disambiguate get_constant_map_key() errors
  bpf: selftests: Test constant key extraction on irrelevant maps
  bpf: verifier: Do not extract constant map keys for irrelevant maps
  bpf: Fix softlockup in arena_map_free on 64k page kernel
  net: Add rx_skb of kfree_skb to raw_tp_null_args[].
  bpf: Fix deadlock when freeing cgroup storage
  selftests/bpf: Add strparser test for bpf
  selftests/bpf: Fix invalid flag of recv()
  bpf: Disable non stream socket for strparser
  bpf: Fix wrong copied_seq calculation
  strparser: Add read_sock callback
  bpf: avoid holding freeze_mutex during mmap operation
  bpf: unify VM_WRITE vs VM_MAYWRITE use in BPF map mmaping logic
  selftests/bpf: Adjust data size to have ETH_HLEN
  bpf, test_run: Fix use-after-free issue in eth_skb_pkt_type()
  bpf: Remove unnecessary BTF lookups in bpf_sk_storage_tracing_allowed

Author: torvalds

Documentation/networking/strparser.rst

@@ -112,7 +112,7 @@ Functions
 Callbacks
 =========
 
-There are six callbacks:
+There are seven callbacks:
 
     ::
 
@@ -182,6 +182,13 @@ There are six callbacks:
     the length of the message. skb->len - offset may be greater
     then full_len since strparser does not trim the skb.
 
+    ::
+
+	int (*read_sock)(struct strparser *strp, read_descriptor_t *desc,
+                     sk_read_actor_t recv_actor);
+
+    The read_sock callback is used by strparser instead of
+    sock->ops->read_sock, if provided.
     ::
 
 	int (*read_sock_done)(struct strparser *strp, int err);

include/linux/skmsg.h

@@ -91,6 +91,8 @@ struct sk_psock {
 	struct sk_psock_progs		progs;
 #if IS_ENABLED(CONFIG_BPF_STREAM_PARSER)
 	struct strparser		strp;
+	u32				copied_seq;
+	u32				ingress_bytes;
 #endif
 	struct sk_buff_head		ingress_skb;
 	struct list_head		ingress_msg;

include/net/strparser.h

@@ -43,6 +43,8 @@ struct strparser;
 struct strp_callbacks {
 	int (*parse_msg)(struct strparser *strp, struct sk_buff *skb);
 	void (*rcv_msg)(struct strparser *strp, struct sk_buff *skb);
+	int (*read_sock)(struct strparser *strp, read_descriptor_t *desc,
+			 sk_read_actor_t recv_actor);
 	int (*read_sock_done)(struct strparser *strp, int err);
 	void (*abort_parser)(struct strparser *strp, int err);
 	void (*lock)(struct strparser *strp);

include/net/tcp.h

@@ -743,6 +743,9 @@ void tcp_get_info(struct sock *, struct tcp_info *);
 /* Read 'sendfile()'-style from a TCP socket */
 int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
 		  sk_read_actor_t recv_actor);
+int tcp_read_sock_noack(struct sock *sk, read_descriptor_t *desc,
+			sk_read_actor_t recv_actor, bool noack,
+			u32 *copied_seq);
 int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor);
 struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off);
 void tcp_read_done(struct sock *sk, size_t len);
@@ -2613,6 +2616,11 @@ struct sk_psock;
 #ifdef CONFIG_BPF_SYSCALL
 int tcp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore);
 void tcp_bpf_clone(const struct sock *sk, struct sock *newsk);
+#ifdef CONFIG_BPF_STREAM_PARSER
+struct strparser;
+int tcp_bpf_strp_read_sock(struct strparser *strp, read_descriptor_t *desc,
+			   sk_read_actor_t recv_actor);
+#endif /* CONFIG_BPF_STREAM_PARSER */
 #endif /* CONFIG_BPF_SYSCALL */
 
 #ifdef CONFIG_INET

kernel/bpf/arena.c

@@ -39,7 +39,7 @@
  */
 
 /* number of bytes addressable by LDX/STX insn with 16-bit 'off' field */
-#define GUARD_SZ (1ull << sizeof_field(struct bpf_insn, off) * 8)
+#define GUARD_SZ round_up(1ull << sizeof_field(struct bpf_insn, off) * 8, PAGE_SIZE << 1)
 #define KERN_VM_SZ (SZ_4G + GUARD_SZ)
 
 struct bpf_arena {

kernel/bpf/bpf_cgrp_storage.c

@@ -153,7 +153,7 @@ static struct bpf_map *cgroup_storage_map_alloc(union bpf_attr *attr)
 
 static void cgroup_storage_map_free(struct bpf_map *map)
 {
-	bpf_local_storage_map_free(map, &cgroup_cache, NULL);
+	bpf_local_storage_map_free(map, &cgroup_cache, &bpf_cgrp_storage_busy);
 }
 
 /* *gfp_flags* is a hidden argument provided by the verifier */

kernel/bpf/btf.c

@@ -6507,6 +6507,8 @@ static const struct bpf_raw_tp_null_args raw_tp_null_args[] = {
 	/* rxrpc */
 	{ "rxrpc_recvdata", 0x1 },
 	{ "rxrpc_resend", 0x10 },
+	/* skb */
+	{"kfree_skb", 0x1000},
 	/* sunrpc */
 	{ "xs_stream_read_data", 0x1 },
 	/* ... from xprt_cong_event event class */

kernel/bpf/ringbuf.c

@@ -268,8 +268,6 @@ static int ringbuf_map_mmap_kern(struct bpf_map *map, struct vm_area_struct *vma
 		/* allow writable mapping for the consumer_pos only */
 		if (vma->vm_pgoff != 0 || vma->vm_end - vma->vm_start != PAGE_SIZE)
 			return -EPERM;
-	} else {
-		vm_flags_clear(vma, VM_MAYWRITE);
 	}
 	/* remap_vmalloc_range() checks size and offset constraints */
 	return remap_vmalloc_range(vma, rb_map->rb,
@@ -289,8 +287,6 @@ static int ringbuf_map_mmap_user(struct bpf_map *map, struct vm_area_struct *vma
 			 * position, and the ring buffer data itself.
 			 */
 			return -EPERM;
-	} else {
-		vm_flags_clear(vma, VM_MAYWRITE);
 	}
 	/* remap_vmalloc_range() checks size and offset constraints */
 	return remap_vmalloc_range(vma, rb_map->rb, vma->vm_pgoff + RINGBUF_PGOFF);

kernel/bpf/syscall.c

@@ -1035,7 +1035,7 @@ static const struct vm_operations_struct bpf_map_default_vmops = {
 static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma)
 {
 	struct bpf_map *map = filp->private_data;
-	int err;
+	int err = 0;
 
 	if (!map->ops->map_mmap || !IS_ERR_OR_NULL(map->record))
 		return -ENOTSUPP;
@@ -1059,24 +1059,33 @@ static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma)
 			err = -EACCES;
 			goto out;
 		}
+		bpf_map_write_active_inc(map);
 	}
+out:
+	mutex_unlock(&map->freeze_mutex);
+	if (err)
+		return err;
 
 	/* set default open/close callbacks */
 	vma->vm_ops = &bpf_map_default_vmops;
 	vma->vm_private_data = map;
 	vm_flags_clear(vma, VM_MAYEXEC);
+	/* If mapping is read-only, then disallow potentially re-mapping with
+	 * PROT_WRITE by dropping VM_MAYWRITE flag. This VM_MAYWRITE clearing
+	 * means that as far as BPF map's memory-mapped VMAs are concerned,
+	 * VM_WRITE and VM_MAYWRITE and equivalent, if one of them is set,
+	 * both should be set, so we can forget about VM_MAYWRITE and always
+	 * check just VM_WRITE
+	 */
 	if (!(vma->vm_flags & VM_WRITE))
-		/* disallow re-mapping with PROT_WRITE */
 		vm_flags_clear(vma, VM_MAYWRITE);
 
 	err = map->ops->map_mmap(map, vma);
-	if (err)
-		goto out;
+	if (err) {
+		if (vma->vm_flags & VM_WRITE)
+			bpf_map_write_active_dec(map);
+	}
 
-	if (vma->vm_flags & VM_MAYWRITE)
-		bpf_map_write_active_inc(map);
-out:
-	mutex_unlock(&map->freeze_mutex);
 	return err;
 }
 
@@ -1968,8 +1977,6 @@ int generic_map_update_batch(struct bpf_map *map, struct file *map_file,
 	return err;
 }
 
-#define MAP_LOOKUP_RETRIES 3
-
 int generic_map_lookup_batch(struct bpf_map *map,
 				    const union bpf_attr *attr,
 				    union bpf_attr __user *uattr)
@@ -1979,8 +1986,8 @@ int generic_map_lookup_batch(struct bpf_map *map,
 	void __user *values = u64_to_user_ptr(attr->batch.values);
 	void __user *keys = u64_to_user_ptr(attr->batch.keys);
 	void *buf, *buf_prevkey, *prev_key, *key, *value;
-	int err, retry = MAP_LOOKUP_RETRIES;
 	u32 value_size, cp, max_count;
+	int err;
 
 	if (attr->batch.elem_flags & ~BPF_F_LOCK)
 		return -EINVAL;
@@ -2026,14 +2033,8 @@ int generic_map_lookup_batch(struct bpf_map *map,
 		err = bpf_map_copy_value(map, key, value,
 					 attr->batch.elem_flags);
 
-		if (err == -ENOENT) {
-			if (retry) {
-				retry--;
-				continue;
-			}
-			err = -EINTR;
-			break;
-		}
+		if (err == -ENOENT)
+			goto next_key;
 
 		if (err)
 			goto free_buf;
@@ -2048,12 +2049,12 @@ int generic_map_lookup_batch(struct bpf_map *map,
 			goto free_buf;
 		}
 
+		cp++;
+next_key:
 		if (!prev_key)
 			prev_key = buf_prevkey;
 
 		swap(prev_key, key);
-		retry = MAP_LOOKUP_RETRIES;
-		cp++;
 		cond_resched();
 	}
 

kernel/bpf/verifier.c

@@ -1501,6 +1501,8 @@ static int acquire_lock_state(struct bpf_verifier_env *env, int insn_idx, enum r
 	struct bpf_reference_state *s;
 
 	s = acquire_reference_state(env, insn_idx);
+	if (!s)
+		return -ENOMEM;
 	s->type = type;
 	s->id = id;
 	s->ptr = ptr;
@@ -9149,10 +9151,11 @@ static int check_reg_const_str(struct bpf_verifier_env *env,
 	return 0;
 }
 
-/* Returns constant key value if possible, else negative error */
-static s64 get_constant_map_key(struct bpf_verifier_env *env,
+/* Returns constant key value in `value` if possible, else negative error */
+static int get_constant_map_key(struct bpf_verifier_env *env,
 				struct bpf_reg_state *key,
-				u32 key_size)
+				u32 key_size,
+				s64 *value)
 {
 	struct bpf_func_state *state = func(env, key);
 	struct bpf_reg_state *reg;
@@ -9179,8 +9182,10 @@ static s64 get_constant_map_key(struct bpf_verifier_env *env,
 	/* First handle precisely tracked STACK_ZERO */
 	for (i = off; i >= 0 && stype[i] == STACK_ZERO; i--)
 		zero_size++;
-	if (zero_size >= key_size)
+	if (zero_size >= key_size) {
+		*value = 0;
 		return 0;
+	}
 
 	/* Check that stack contains a scalar spill of expected size */
 	if (!is_spilled_scalar_reg(&state->stack[spi]))
@@ -9203,9 +9208,12 @@ static s64 get_constant_map_key(struct bpf_verifier_env *env,
 	if (err < 0)
 		return err;
 
-	return reg->var_off.value;
+	*value = reg->var_off.value;
+	return 0;
 }
 
+static bool can_elide_value_nullness(enum bpf_map_type type);
+
 static int check_func_arg(struct bpf_verifier_env *env, u32 arg,
 			  struct bpf_call_arg_meta *meta,
 			  const struct bpf_func_proto *fn,
@@ -9354,9 +9362,16 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg,
 		err = check_helper_mem_access(env, regno, key_size, BPF_READ, false, NULL);
 		if (err)
 			return err;
-		meta->const_map_key = get_constant_map_key(env, reg, key_size);
-		if (meta->const_map_key < 0 && meta->const_map_key != -EOPNOTSUPP)
-			return meta->const_map_key;
+		if (can_elide_value_nullness(meta->map_ptr->map_type)) {
+			err = get_constant_map_key(env, reg, key_size, &meta->const_map_key);
+			if (err < 0) {
+				meta->const_map_key = -1;
+				if (err == -EOPNOTSUPP)
+					err = 0;
+				else
+					return err;
+			}
+		}
 		break;
 	case ARG_PTR_TO_MAP_VALUE:
 		if (type_may_be_null(arg_type) && register_is_null(reg))