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

Daniel Borkmann says:

====================
pull-request: bpf-next 2019-01-29

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

The main changes are:

1) Teach verifier dead code removal, this also allows for optimizing /
   removing conditional branches around dead code and to shrink the
   resulting image. Code store constrained architectures like nfp would
   have hard time doing this at JIT level, from Jakub.

2) Add JMP32 instructions to BPF ISA in order to allow for optimizing
   code generation for 32-bit sub-registers. Evaluation shows that this
   can result in code reduction of ~5-20% compared to 64 bit-only code
   generation. Also add implementation for most JITs, from Jiong.

3) Add support for __int128 types in BTF which is also needed for
   vmlinux's BTF conversion to work, from Yonghong.

4) Add a new command to bpftool in order to dump a list of BPF-related
   parameters from the system or for a specific network device e.g. in
   terms of available prog/map types or helper functions, from Quentin.

5) Add AF_XDP sock_diag interface for querying sockets from user
   space which provides information about the RX/TX/fill/completion
   rings, umem, memory usage etc, from Björn.

6) Add skb context access for skb_shared_info->gso_segs field, from Eric.

7) Add support for testing flow dissector BPF programs by extending
   existing BPF_PROG_TEST_RUN infrastructure, from Stanislav.

8) Split BPF kselftest's test_verifier into various subgroups of tests
   in order better deal with merge conflicts in this area, from Jakub.

9) Add support for queue/stack manipulations in bpftool, from Stanislav.

10) Document BTF, from Yonghong.

11) Dump supported ELF section names in libbpf on program load
    failure, from Taeung.

12) Silence a false positive compiler warning in verifier's BTF
    handling, from Peter.

13) Fix help string in bpftool's feature probing, from Prashant.

14) Remove duplicate includes in BPF kselftests, from Yue.
====================

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

5 files changed, 774 insertions, 296 deletions

diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index befe570be5ba..3d661f0606fe 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -157,7 +157,7 @@
  *
  */
 
-#define BITS_PER_U64 (sizeof(u64) * BITS_PER_BYTE)
+#define BITS_PER_U128 (sizeof(u64) * BITS_PER_BYTE * 2)
 #define BITS_PER_BYTE_MASK (BITS_PER_BYTE - 1)
 #define BITS_PER_BYTE_MASKED(bits) ((bits) & BITS_PER_BYTE_MASK)
 #define BITS_ROUNDDOWN_BYTES(bits) ((bits) >> 3)
@@ -525,7 +525,7 @@ const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id)
 
 /*
  * Regular int is not a bit field and it must be either
- * u8/u16/u32/u64.
+ * u8/u16/u32/u64 or __int128.
  */
 static bool btf_type_int_is_regular(const struct btf_type *t)
 {
@@ -538,7 +538,8 @@ static bool btf_type_int_is_regular(const struct btf_type *t)
 	if (BITS_PER_BYTE_MASKED(nr_bits) ||
 	    BTF_INT_OFFSET(int_data) ||
 	    (nr_bytes != sizeof(u8) && nr_bytes != sizeof(u16) &&
-	     nr_bytes != sizeof(u32) && nr_bytes != sizeof(u64))) {
+	     nr_bytes != sizeof(u32) && nr_bytes != sizeof(u64) &&
+	     nr_bytes != (2 * sizeof(u64)))) {
 		return false;
 	}
 
@@ -1063,9 +1064,9 @@ static int btf_int_check_member(struct btf_verifier_env *env,
 	nr_copy_bits = BTF_INT_BITS(int_data) +
 		BITS_PER_BYTE_MASKED(struct_bits_off);
 
-	if (nr_copy_bits > BITS_PER_U64) {
+	if (nr_copy_bits > BITS_PER_U128) {
 		btf_verifier_log_member(env, struct_type, member,
-					"nr_copy_bits exceeds 64");
+					"nr_copy_bits exceeds 128");
 		return -EINVAL;
 	}
 
@@ -1119,9 +1120,9 @@ static int btf_int_check_kflag_member(struct btf_verifier_env *env,
 
 	bytes_offset = BITS_ROUNDDOWN_BYTES(struct_bits_off);
 	nr_copy_bits = nr_bits + BITS_PER_BYTE_MASKED(struct_bits_off);
-	if (nr_copy_bits > BITS_PER_U64) {
+	if (nr_copy_bits > BITS_PER_U128) {
 		btf_verifier_log_member(env, struct_type, member,
-					"nr_copy_bits exceeds 64");
+					"nr_copy_bits exceeds 128");
 		return -EINVAL;
 	}
 
@@ -1168,9 +1169,9 @@ static s32 btf_int_check_meta(struct btf_verifier_env *env,
 
 	nr_bits = BTF_INT_BITS(int_data) + BTF_INT_OFFSET(int_data);
 
-	if (nr_bits > BITS_PER_U64) {
+	if (nr_bits > BITS_PER_U128) {
 		btf_verifier_log_type(env, t, "nr_bits exceeds %zu",
-				      BITS_PER_U64);
+				      BITS_PER_U128);
 		return -EINVAL;
 	}
 
@@ -1211,31 +1212,93 @@ static void btf_int_log(struct btf_verifier_env *env,
 			 btf_int_encoding_str(BTF_INT_ENCODING(int_data)));
 }
 
+static void btf_int128_print(struct seq_file *m, void *data)
+{
+	/* data points to a __int128 number.
+	 * Suppose
+	 *     int128_num = *(__int128 *)data;
+	 * The below formulas shows what upper_num and lower_num represents:
+	 *     upper_num = int128_num >> 64;
+	 *     lower_num = int128_num & 0xffffffffFFFFFFFFULL;
+	 */
+	u64 upper_num, lower_num;
+
+#ifdef __BIG_ENDIAN_BITFIELD
+	upper_num = *(u64 *)data;
+	lower_num = *(u64 *)(data + 8);
+#else
+	upper_num = *(u64 *)(data + 8);
+	lower_num = *(u64 *)data;
+#endif
+	if (upper_num == 0)
+		seq_printf(m, "0x%llx", lower_num);
+	else
+		seq_printf(m, "0x%llx%016llx", upper_num, lower_num);
+}
+
+static void btf_int128_shift(u64 *print_num, u16 left_shift_bits,
+			     u16 right_shift_bits)
+{
+	u64 upper_num, lower_num;
+
+#ifdef __BIG_ENDIAN_BITFIELD
+	upper_num = print_num[0];
+	lower_num = print_num[1];
+#else
+	upper_num = print_num[1];
+	lower_num = print_num[0];
+#endif
+
+	/* shake out un-needed bits by shift/or operations */
+	if (left_shift_bits >= 64) {
+		upper_num = lower_num << (left_shift_bits - 64);
+		lower_num = 0;
+	} else {
+		upper_num = (upper_num << left_shift_bits) |
+			    (lower_num >> (64 - left_shift_bits));
+		lower_num = lower_num << left_shift_bits;
+	}
+
+	if (right_shift_bits >= 64) {
+		lower_num = upper_num >> (right_shift_bits - 64);
+		upper_num = 0;
+	} else {
+		lower_num = (lower_num >> right_shift_bits) |
+			    (upper_num << (64 - right_shift_bits));
+		upper_num = upper_num >> right_shift_bits;
+	}
+
+#ifdef __BIG_ENDIAN_BITFIELD
+	print_num[0] = upper_num;
+	print_num[1] = lower_num;
+#else
+	print_num[0] = lower_num;
+	print_num[1] = upper_num;
+#endif
+}
+
 static void btf_bitfield_seq_show(void *data, u8 bits_offset,
 				  u8 nr_bits, struct seq_file *m)
 {
 	u16 left_shift_bits, right_shift_bits;
 	u8 nr_copy_bytes;
 	u8 nr_copy_bits;
-	u64 print_num;
+	u64 print_num[2] = {};
 
 	nr_copy_bits = nr_bits + bits_offset;
 	nr_copy_bytes = BITS_ROUNDUP_BYTES(nr_copy_bits);
 
-	print_num = 0;
-	memcpy(&print_num, data, nr_copy_bytes);
+	memcpy(print_num, data, nr_copy_bytes);
 
 #ifdef __BIG_ENDIAN_BITFIELD
 	left_shift_bits = bits_offset;
 #else
-	left_shift_bits = BITS_PER_U64 - nr_copy_bits;
+	left_shift_bits = BITS_PER_U128 - nr_copy_bits;
 #endif
-	right_shift_bits = BITS_PER_U64 - nr_bits;
-
-	print_num <<= left_shift_bits;
-	print_num >>= right_shift_bits;
+	right_shift_bits = BITS_PER_U128 - nr_bits;
 
-	seq_printf(m, "0x%llx", print_num);
+	btf_int128_shift(print_num, left_shift_bits, right_shift_bits);
+	btf_int128_print(m, print_num);
 }
 
 
@@ -1250,7 +1313,7 @@ static void btf_int_bits_seq_show(const struct btf *btf,
 
 	/*
 	 * bits_offset is at most 7.
-	 * BTF_INT_OFFSET() cannot exceed 64 bits.
+	 * BTF_INT_OFFSET() cannot exceed 128 bits.
 	 */
 	total_bits_offset = bits_offset + BTF_INT_OFFSET(int_data);
 	data += BITS_ROUNDDOWN_BYTES(total_bits_offset);
@@ -1274,6 +1337,9 @@ static void btf_int_seq_show(const struct btf *btf, const struct btf_type *t,
 	}
 
 	switch (nr_bits) {
+	case 128:
+		btf_int128_print(m, data);
+		break;
 	case 64:
 		if (sign)
 			seq_printf(m, "%lld", *(s64 *)data);
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index f908b9356025..a7bcb23bee84 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -307,15 +307,16 @@ int bpf_prog_calc_tag(struct bpf_prog *fp)
 	return 0;
 }
 
-static int bpf_adj_delta_to_imm(struct bpf_insn *insn, u32 pos, u32 delta,
-				u32 curr, const bool probe_pass)
+static int bpf_adj_delta_to_imm(struct bpf_insn *insn, u32 pos, s32 end_old,
+				s32 end_new, u32 curr, const bool probe_pass)
 {
 	const s64 imm_min = S32_MIN, imm_max = S32_MAX;
+	s32 delta = end_new - end_old;
 	s64 imm = insn->imm;
 
-	if (curr < pos && curr + imm + 1 > pos)
+	if (curr < pos && curr + imm + 1 >= end_old)
 		imm += delta;
-	else if (curr > pos + delta && curr + imm + 1 <= pos + delta)
+	else if (curr >= end_new && curr + imm + 1 < end_new)
 		imm -= delta;
 	if (imm < imm_min || imm > imm_max)
 		return -ERANGE;
@@ -324,15 +325,16 @@ static int bpf_adj_delta_to_imm(struct bpf_insn *insn, u32 pos, u32 delta,
 	return 0;
 }
 
-static int bpf_adj_delta_to_off(struct bpf_insn *insn, u32 pos, u32 delta,
-				u32 curr, const bool probe_pass)
+static int bpf_adj_delta_to_off(struct bpf_insn *insn, u32 pos, s32 end_old,
+				s32 end_new, u32 curr, const bool probe_pass)
 {
 	const s32 off_min = S16_MIN, off_max = S16_MAX;
+	s32 delta = end_new - end_old;
 	s32 off = insn->off;
 
-	if (curr < pos && curr + off + 1 > pos)
+	if (curr < pos && curr + off + 1 >= end_old)
 		off += delta;
-	else if (curr > pos + delta && curr + off + 1 <= pos + delta)
+	else if (curr >= end_new && curr + off + 1 < end_new)
 		off -= delta;
 	if (off < off_min || off > off_max)
 		return -ERANGE;
@@ -341,10 +343,10 @@ static int bpf_adj_delta_to_off(struct bpf_insn *insn, u32 pos, u32 delta,
 	return 0;
 }
 
-static int bpf_adj_branches(struct bpf_prog *prog, u32 pos, u32 delta,
-			    const bool probe_pass)
+static int bpf_adj_branches(struct bpf_prog *prog, u32 pos, s32 end_old,
+			    s32 end_new, const bool probe_pass)
 {
-	u32 i, insn_cnt = prog->len + (probe_pass ? delta : 0);
+	u32 i, insn_cnt = prog->len + (probe_pass ? end_new - end_old : 0);
 	struct bpf_insn *insn = prog->insnsi;
 	int ret = 0;
 
@@ -356,22 +358,23 @@ static int bpf_adj_branches(struct bpf_prog *prog, u32 pos, u32 delta,
 		 * do any other adjustments. Therefore skip the patchlet.
 		 */
 		if (probe_pass && i == pos) {
-			i += delta + 1;
-			insn++;
+			i = end_new;
+			insn = prog->insnsi + end_old;
 		}
 		code = insn->code;
-		if (BPF_CLASS(code) != BPF_JMP ||
+		if ((BPF_CLASS(code) != BPF_JMP &&
+		     BPF_CLASS(code) != BPF_JMP32) ||
 		    BPF_OP(code) == BPF_EXIT)
 			continue;
 		/* Adjust offset of jmps if we cross patch boundaries. */
 		if (BPF_OP(code) == BPF_CALL) {
 			if (insn->src_reg != BPF_PSEUDO_CALL)
 				continue;
-			ret = bpf_adj_delta_to_imm(insn, pos, delta, i,
-						   probe_pass);
+			ret = bpf_adj_delta_to_imm(insn, pos, end_old,
+						   end_new, i, probe_pass);
 		} else {
-			ret = bpf_adj_delta_to_off(insn, pos, delta, i,
-						   probe_pass);
+			ret = bpf_adj_delta_to_off(insn, pos, end_old,
+						   end_new, i, probe_pass);
 		}
 		if (ret)
 			break;
@@ -421,7 +424,7 @@ struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off,
 	 * we afterwards may not fail anymore.
 	 */
 	if (insn_adj_cnt > cnt_max &&
-	    bpf_adj_branches(prog, off, insn_delta, true))
+	    bpf_adj_branches(prog, off, off + 1, off + len, true))
 		return NULL;
 
 	/* Several new instructions need to be inserted. Make room
@@ -453,13 +456,25 @@ struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off,
 	 * the ship has sailed to reverse to the original state. An
 	 * overflow cannot happen at this point.
 	 */
-	BUG_ON(bpf_adj_branches(prog_adj, off, insn_delta, false));
+	BUG_ON(bpf_adj_branches(prog_adj, off, off + 1, off + len, false));
 
 	bpf_adj_linfo(prog_adj, off, insn_delta);
 
 	return prog_adj;
 }
 
+int bpf_remove_insns(struct bpf_prog *prog, u32 off, u32 cnt)
+{
+	/* Branch offsets can't overflow when program is shrinking, no need
+	 * to call bpf_adj_branches(..., true) here
+	 */
+	memmove(prog->insnsi + off, prog->insnsi + off + cnt,
+		sizeof(struct bpf_insn) * (prog->len - off - cnt));
+	prog->len -= cnt;
+
+	return WARN_ON_ONCE(bpf_adj_branches(prog, off, off + cnt, off, false));
+}
+
 void bpf_prog_kallsyms_del_subprogs(struct bpf_prog *fp)
 {
 	int i;
@@ -934,6 +949,27 @@ static int bpf_jit_blind_insn(const struct bpf_insn *from,
 		*to++ = BPF_JMP_REG(from->code, from->dst_reg, BPF_REG_AX, off);
 		break;
 
+	case BPF_JMP32 | BPF_JEQ  | BPF_K:
+	case BPF_JMP32 | BPF_JNE  | BPF_K:
+	case BPF_JMP32 | BPF_JGT  | BPF_K:
+	case BPF_JMP32 | BPF_JLT  | BPF_K:
+	case BPF_JMP32 | BPF_JGE  | BPF_K:
+	case BPF_JMP32 | BPF_JLE  | BPF_K:
+	case BPF_JMP32 | BPF_JSGT | BPF_K:
+	case BPF_JMP32 | BPF_JSLT | BPF_K:
+	case BPF_JMP32 | BPF_JSGE | BPF_K:
+	case BPF_JMP32 | BPF_JSLE | BPF_K:
+	case BPF_JMP32 | BPF_JSET | BPF_K:
+		/* Accommodate for extra offset in case of a backjump. */
+		off = from->off;
+		if (off < 0)
+			off -= 2;
+		*to++ = BPF_ALU32_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm);
+		*to++ = BPF_ALU32_IMM(BPF_XOR, BPF_REG_AX, imm_rnd);
+		*to++ = BPF_JMP32_REG(from->code, from->dst_reg, BPF_REG_AX,
+				      off);
+		break;
+
 	case BPF_LD | BPF_IMM | BPF_DW:
 		*to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ aux[1].imm);
 		*to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd);
@@ -1130,6 +1166,31 @@ EXPORT_SYMBOL_GPL(__bpf_call_base);
 	INSN_2(JMP, CALL),			\
 	/* Exit instruction. */			\
 	INSN_2(JMP, EXIT),			\
+	/* 32-bit Jump instructions. */		\
+	/*   Register based. */			\
+	INSN_3(JMP32, JEQ,  X),			\
+	INSN_3(JMP32, JNE,  X),			\
+	INSN_3(JMP32, JGT,  X),			\
+	INSN_3(JMP32, JLT,  X),			\
+	INSN_3(JMP32, JGE,  X),			\
+	INSN_3(JMP32, JLE,  X),			\
+	INSN_3(JMP32, JSGT, X),			\
+	INSN_3(JMP32, JSLT, X),			\
+	INSN_3(JMP32, JSGE, X),			\
+	INSN_3(JMP32, JSLE, X),			\
+	INSN_3(JMP32, JSET, X),			\
+	/*   Immediate based. */		\
+	INSN_3(JMP32, JEQ,  K),			\
+	INSN_3(JMP32, JNE,  K),			\
+	INSN_3(JMP32, JGT,  K),			\
+	INSN_3(JMP32, JLT,  K),			\
+	INSN_3(JMP32, JGE,  K),			\
+	INSN_3(JMP32, JLE,  K),			\
+	INSN_3(JMP32, JSGT, K),			\
+	INSN_3(JMP32, JSLT, K),			\
+	INSN_3(JMP32, JSGE, K),			\
+	INSN_3(JMP32, JSLE, K),			\
+	INSN_3(JMP32, JSET, K),			\
 	/* Jump instructions. */		\
 	/*   Register based. */			\
 	INSN_3(JMP, JEQ,  X),			\
@@ -1390,145 +1451,49 @@ select_insn:
 out:
 		CONT;
 	}
-	/* JMP */
 	JMP_JA:
 		insn += insn->off;
 		CONT;
-	JMP_JEQ_X:
-		if (DST == SRC) {
-			insn += insn->off;
-			CONT_JMP;
-		}
-		CONT;
-	JMP_JEQ_K:
-		if (DST == IMM) {
-			insn += insn->off;
-			CONT_JMP;
-		}
-		CONT;
-	JMP_JNE_X:
-		if (DST != SRC) {
-			insn += insn->off;
-			CONT_JMP;
-		}
-		CONT;
-	JMP_JNE_K:
-		if (DST != IMM) {
-			insn += insn->off;
-			CONT_JMP;
-		}
-		CONT;
-	JMP_JGT_X:
-		if (DST > SRC) {
-			insn += insn->off;
-			CONT_JMP;
-		}
-		CONT;
-	JMP_JGT_K:
-		if (DST > IMM) {
-			insn += insn->off;
-			CONT_JMP;
-		}
-		CONT;
-	JMP_JLT_X:
-		if (DST < SRC) {
-			insn += insn->off;
-			CONT_JMP;
-		}
-		CONT;
-	JMP_JLT_K:
-		if (DST < IMM) {
-			insn += insn->off;
-			CONT_JMP;
-		}
-		CONT;
-	JMP_JGE_X:
-		if (DST >= SRC) {
-			insn += insn->off;
-			CONT_JMP;
-		}
-		CONT;
-	JMP_JGE_K:
-		if (DST >= IMM) {
-			insn += insn->off;
-			CONT_JMP;
-		}
-		CONT;
-	JMP_JLE_X:
-		if (DST <= SRC) {
-			insn += insn->off;
-			CONT_JMP;
-		}
-		CONT;
-	JMP_JLE_K:
-		if (DST <= IMM) {
-			insn += insn->off;
-			CONT_JMP;
-		}
-		CONT;
-	JMP_JSGT_X:
-		if (((s64) DST) > ((s64) SRC)) {
-			insn += insn->off;
-			CONT_JMP;
-		}
-		CONT;
-	JMP_JSGT_K:
-		if (((s64) DST) > ((s64) IMM)) {
-			insn += insn->off;
-			CONT_JMP;
-		}
-		CONT;
-	JMP_JSLT_X:
-		if (((s64) DST) < ((s64) SRC)) {
-			insn += insn->off;
-			CONT_JMP;
-		}
-		CONT;
-	JMP_JSLT_K:
-		if (((s64) DST) < ((s64) IMM)) {
-			insn += insn->off;
-			CONT_JMP;
-		}
-		CONT;
-	JMP_JSGE_X:
-		if (((s64) DST) >= ((s64) SRC)) {
-			insn += insn->off;
-			CONT_JMP;
-		}
-		CONT;
-	JMP_JSGE_K:
-		if (((s64) DST) >= ((s64) IMM)) {
-			insn += insn->off;
-			CONT_JMP;
-		}
-		CONT;
-	JMP_JSLE_X:
-		if (((s64) DST) <= ((s64) SRC)) {
-			insn += insn->off;
-			CONT_JMP;
-		}
-		CONT;
-	JMP_JSLE_K:
-		if (((s64) DST) <= ((s64) IMM)) {
-			insn += insn->off;
-			CONT_JMP;
-		}
-		CONT;
-	JMP_JSET_X:
-		if (DST & SRC) {
-			insn += insn->off;
-			CONT_JMP;
-		}
-		CONT;
-	JMP_JSET_K:
-		if (DST & IMM) {
-			insn += insn->off;
-			CONT_JMP;
-		}
-		CONT;
 	JMP_EXIT:
 		return BPF_R0;
-
+	/* JMP */
+#define COND_JMP(SIGN, OPCODE, CMP_OP)				\
+	JMP_##OPCODE##_X:					\
+		if ((SIGN##64) DST CMP_OP (SIGN##64) SRC) {	\
+			insn += insn->off;			\
+			CONT_JMP;				\
+		}						\
+		CONT;						\
+	JMP32_##OPCODE##_X:					\
+		if ((SIGN##32) DST CMP_OP (SIGN##32) SRC) {	\
+			insn += insn->off;			\
+			CONT_JMP;				\
+		}						\
+		CONT;						\
+	JMP_##OPCODE##_K:					\
+		if ((SIGN##64) DST CMP_OP (SIGN##64) IMM) {	\
+			insn += insn->off;			\
+			CONT_JMP;				\
+		}						\
+		CONT;						\
+	JMP32_##OPCODE##_K:					\
+		if ((SIGN##32) DST CMP_OP (SIGN##32) IMM) {	\
+			insn += insn->off;			\
+			CONT_JMP;				\
+		}						\
+		CONT;
+	COND_JMP(u, JEQ, ==)
+	COND_JMP(u, JNE, !=)
+	COND_JMP(u, JGT, >)
+	COND_JMP(u, JLT, <)
+	COND_JMP(u, JGE, >=)
+	COND_JMP(u, JLE, <=)
+	COND_JMP(u, JSET, &)
+	COND_JMP(s, JSGT, >)
+	COND_JMP(s, JSLT, <)
+	COND_JMP(s, JSGE, >=)
+	COND_JMP(s, JSLE, <=)
+#undef COND_JMP
 	/* STX and ST and LDX*/
 #define LDST(SIZEOP, SIZE)						\
 	STX_MEM_##SIZEOP:						\
diff --git a/kernel/bpf/disasm.c b/kernel/bpf/disasm.c
index d6b76377cb6e..de73f55e42fd 100644
--- a/kernel/bpf/disasm.c
+++ b/kernel/bpf/disasm.c
@@ -67,7 +67,7 @@ const char *const bpf_class_string[8] = {
 	[BPF_STX]   = "stx",
 	[BPF_ALU]   = "alu",
 	[BPF_JMP]   = "jmp",
-	[BPF_RET]   = "BUG",
+	[BPF_JMP32] = "jmp32",
 	[BPF_ALU64] = "alu64",
 };
 
@@ -136,23 +136,22 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs,
 			else
 				print_bpf_end_insn(verbose, cbs->private_data, insn);
 		} else if (BPF_OP(insn->code) == BPF_NEG) {
-			verbose(cbs->private_data, "(%02x) r%d = %s-r%d\n",
-				insn->code, insn->dst_reg,
-				class == BPF_ALU ? "(u32) " : "",
+			verbose(cbs->private_data, "(%02x) %c%d = -%c%d\n",
+				insn->code, class == BPF_ALU ? 'w' : 'r',
+				insn->dst_reg, class == BPF_ALU ? 'w' : 'r',
 				insn->dst_reg);
 		} else if (BPF_SRC(insn->code) == BPF_X) {
-			verbose(cbs->private_data, "(%02x) %sr%d %s %sr%d\n",
-				insn->code, class == BPF_ALU ? "(u32) " : "",
+			verbose(cbs->private_data, "(%02x) %c%d %s %c%d\n",
+				insn->code, class == BPF_ALU ? 'w' : 'r',
 				insn->dst_reg,
 				bpf_alu_string[BPF_OP(insn->code) >> 4],
-				class == BPF_ALU ? "(u32) " : "",
+				class == BPF_ALU ? 'w' : 'r',
 				insn->src_reg);
 		} else {
-			verbose(cbs->private_data, "(%02x) %sr%d %s %s%d\n",
-				insn->code, class == BPF_ALU ? "(u32) " : "",
+			verbose(cbs->private_data, "(%02x) %c%d %s %d\n",
+				insn->code, class == BPF_ALU ? 'w' : 'r',
 				insn->dst_reg,
 				bpf_alu_string[BPF_OP(insn->code) >> 4],
-				class == BPF_ALU ? "(u32) " : "",
 				insn->imm);
 		}
 	} else if (class == BPF_STX) {
@@ -220,7 +219,7 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs,
 			verbose(cbs->private_data, "BUG_ld_%02x\n", insn->code);
 			return;
 		}
-	} else if (class == BPF_JMP) {
+	} else if (class == BPF_JMP32 || class == BPF_JMP) {
 		u8 opcode = BPF_OP(insn->code);
 
 		if (opcode == BPF_CALL) {
@@ -244,13 +243,18 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs,
 		} else if (insn->code == (BPF_JMP | BPF_EXIT)) {
 			verbose(cbs->private_data, "(%02x) exit\n", insn->code);
 		} else if (BPF_SRC(insn->code) == BPF_X) {
-			verbose(cbs->private_data, "(%02x) if r%d %s r%d goto pc%+d\n",
-				insn->code, insn->dst_reg,
+			verbose(cbs->private_data,
+				"(%02x) if %c%d %s %c%d goto pc%+d\n",
+				insn->code, class == BPF_JMP32 ? 'w' : 'r',
+				insn->dst_reg,
 				bpf_jmp_string[BPF_OP(insn->code) >> 4],
+				class == BPF_JMP32 ? 'w' : 'r',
 				insn->src_reg, insn->off);
 		} else {
-			verbose(cbs->private_data, "(%02x) if r%d %s 0x%x goto pc%+d\n",
-				insn->code, insn->dst_reg,
+			verbose(cbs->private_data,
+				"(%02x) if %c%d %s 0x%x goto pc%+d\n",
+				insn->code, class == BPF_JMP32 ? 'w' : 'r',
+				insn->dst_reg,
 				bpf_jmp_string[BPF_OP(insn->code) >> 4],
 				insn->imm, insn->off);
 		}
diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c
index 54cf2b9c44a4..39dba8c90331 100644
--- a/kernel/bpf/offload.c
+++ b/kernel/bpf/offload.c
@@ -173,6 +173,41 @@ int bpf_prog_offload_finalize(struct bpf_verifier_env *env)
 	return ret;
 }
 
+void
+bpf_prog_offload_replace_insn(struct bpf_verifier_env *env, u32 off,
+			      struct bpf_insn *insn)
+{
+	const struct bpf_prog_offload_ops *ops;
+	struct bpf_prog_offload *offload;
+	int ret = -EOPNOTSUPP;
+
+	down_read(&bpf_devs_lock);
+	offload = env->prog->aux->offload;
+	if (offload) {
+		ops = offload->offdev->ops;
+		if (!offload->opt_failed && ops->replace_insn)
+			ret = ops->replace_insn(env, off, insn);
+		offload->opt_failed |= ret;
+	}
+	up_read(&bpf_devs_lock);
+}
+
+void
+bpf_prog_offload_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt)
+{
+	struct bpf_prog_offload *offload;
+	int ret = -EOPNOTSUPP;
+
+	down_read(&bpf_devs_lock);
+	offload = env->prog->aux->offload;
+	if (offload) {
+		if (!offload->opt_failed && offload->offdev->ops->remove_insns)
+			ret = offload->offdev->ops->remove_insns(env, off, cnt);
+		offload->opt_failed |= ret;
+	}
+	up_read(&bpf_devs_lock);
+}
+
 static void __bpf_prog_offload_destroy(struct bpf_prog *prog)
 {
 	struct bpf_prog_offload *offload = prog->aux->offload;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 56674a7c3778..8c1c21cd50b4 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1095,7 +1095,7 @@ static int check_subprogs(struct bpf_verifier_env *env)
 	for (i = 0; i < insn_cnt; i++) {
 		u8 code = insn[i].code;
 
-		if (BPF_CLASS(code) != BPF_JMP)
+		if (BPF_CLASS(code) != BPF_JMP && BPF_CLASS(code) != BPF_JMP32)
 			goto next;
 		if (BPF_OP(code) == BPF_EXIT || BPF_OP(code) == BPF_CALL)
 			goto next;
@@ -4031,11 +4031,50 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *vstate,
  *  0 - branch will not be taken and fall-through to next insn
  * -1 - unknown. Example: "if (reg < 5)" is unknown when register value range [0,10]
  */
-static int is_branch_taken(struct bpf_reg_state *reg, u64 val, u8 opcode)
+static int is_branch_taken(struct bpf_reg_state *reg, u64 val, u8 opcode,
+			   bool is_jmp32)
 {
+	struct bpf_reg_state reg_lo;
+	s64 sval;
+
 	if (__is_pointer_value(false, reg))
 		return -1;
 
+	if (is_jmp32) {
+		reg_lo = *reg;
+		reg = &reg_lo;
+		/* For JMP32, only low 32 bits are compared, coerce_reg_to_size
+		 * could truncate high bits and update umin/umax according to
+		 * information of low bits.
+		 */
+		coerce_reg_to_size(reg, 4);
+		/* smin/smax need special handling. For example, after coerce,
+		 * if smin_value is 0x00000000ffffffffLL, the value is -1 when
+		 * used as operand to JMP32. It is a negative number from s32's
+		 * point of view, while it is a positive number when seen as
+		 * s64. The smin/smax are kept as s64, therefore, when used with
+		 * JMP32, they need to be transformed into s32, then sign
+		 * extended back to s64.
+		 *
+		 * Also, smin/smax were copied from umin/umax. If umin/umax has
+		 * different sign bit, then min/max relationship doesn't
+		 * maintain after casting into s32, for this case, set smin/smax
+		 * to safest range.
+		 */
+		if ((reg->umax_value ^ reg->umin_value) &
+		    (1ULL << 31)) {
+			reg->smin_value = S32_MIN;
+			reg->smax_value = S32_MAX;
+		}
+		reg->smin_value = (s64)(s32)reg->smin_value;
+		reg->smax_value = (s64)(s32)reg->smax_value;
+
+		val = (u32)val;
+		sval = (s64)(s32)val;
+	} else {
+		sval = (s64)val;
+	}
+
 	switch (opcode) {
 	case BPF_JEQ:
 		if (tnum_is_const(reg->var_off))
@@ -4058,9 +4097,9 @@ static int is_branch_taken(struct bpf_reg_state *reg, u64 val, u8 opcode)
 			return 0;
 		break;
 	case BPF_JSGT:
-		if (reg->smin_value > (s64)val)
+		if (reg->smin_value > sval)
 			return 1;
-		else if (reg->smax_value < (s64)val)
+		else if (reg->smax_value < sval)
 			return 0;
 		break;
 	case BPF_JLT:
@@ -4070,9 +4109,9 @@ static int is_branch_taken(struct bpf_reg_state *reg, u64 val, u8 opcode)
 			return 0;
 		break;
 	case BPF_JSLT:
-		if (reg->smax_value < (s64)val)
+		if (reg->smax_value < sval)
 			return 1;
-		else if (reg->smin_value >= (s64)val)
+		else if (reg->smin_value >= sval)
 			return 0;
 		break;
 	case BPF_JGE:
@@ -4082,9 +4121,9 @@ static int is_branch_taken(struct bpf_reg_state *reg, u64 val, u8 opcode)
 			return 0;
 		break;
 	case BPF_JSGE:
-		if (reg->smin_value >= (s64)val)
+		if (reg->smin_value >= sval)
 			return 1;
-		else if (reg->smax_value < (s64)val)
+		else if (reg->smax_value < sval)
 			return 0;
 		break;
 	case BPF_JLE:
@@ -4094,9 +4133,9 @@ static int is_branch_taken(struct bpf_reg_state *reg, u64 val, u8 opcode)
 			return 0;
 		break;
 	case BPF_JSLE:
-		if (reg->smax_value <= (s64)val)
+		if (reg->smax_value <= sval)
 			return 1;
-		else if (reg->smin_value > (s64)val)
+		else if (reg->smin_value > sval)
 			return 0;
 		break;
 	}
@@ -4104,6 +4143,29 @@ static int is_branch_taken(struct bpf_reg_state *reg, u64 val, u8 opcode)
 	return -1;
 }
 
+/* Generate min value of the high 32-bit from TNUM info. */
+static u64 gen_hi_min(struct tnum var)
+{
+	return var.value & ~0xffffffffULL;
+}
+
+/* Generate max value of the high 32-bit from TNUM info. */
+static u64 gen_hi_max(struct tnum var)
+{
+	return (var.value | var.mask) & ~0xffffffffULL;
+}
+
+/* Return true if VAL is compared with a s64 sign extended from s32, and they
+ * are with the same signedness.
+ */
+static bool cmp_val_with_extended_s64(s64 sval, struct bpf_reg_state *reg)
+{
+	return ((s32)sval >= 0 &&
+		reg->smin_value >= 0 && reg->smax_value <= S32_MAX) ||
+	       ((s32)sval < 0 &&
+		reg->smax_value <= 0 && reg->smin_value >= S32_MIN);
+}
+
 /* Adjusts the register min/max values in the case that the dst_reg is the
  * variable register that we are working on, and src_reg is a constant or we're
  * simply doing a BPF_K check.
@@ -4111,8 +4173,10 @@ static int is_branch_taken(struct bpf_reg_state *reg, u64 val, u8 opcode)
  */
 static void reg_set_min_max(struct bpf_reg_state *true_reg,
 			    struct bpf_reg_state *false_reg, u64 val,
-			    u8 opcode)
+			    u8 opcode, bool is_jmp32)
 {
+	s64 sval;
+
 	/* If the dst_reg is a pointer, we can't learn anything about its
 	 * variable offset from the compare (unless src_reg were a pointer into
 	 * the same object, but we don't bother with that.
@@ -4122,19 +4186,31 @@ static void reg_set_min_max(struct bpf_reg_state *true_reg,
 	if (__is_pointer_value(false, false_reg))
 		return;
 
+	val = is_jmp32 ? (u32)val : val;
+	sval = is_jmp32 ? (s64)(s32)val : (s64)val;
+
 	switch (opcode) {
 	case BPF_JEQ:
-		/* If this is false then we know nothing Jon Snow, but if it is
-		 * true then we know for sure.
-		 */
-		__mark_reg_known(true_reg, val);
-		break;
 	case BPF_JNE:
-		/* If this is true we know nothing Jon Snow, but if it is false
-		 * we know the value for sure;
+	{
+		struct bpf_reg_state *reg =
+			opcode == BPF_JEQ ? true_reg : false_reg;
+
+		/* For BPF_JEQ, if this is false we know nothing Jon Snow, but
+		 * if it is true we know the value for sure. Likewise for
+		 * BPF_JNE.
 		 */
-		__mark_reg_known(false_reg, val);
+		if (is_jmp32) {
+			u64 old_v = reg->var_off.value;
+			u64 hi_mask = ~0xffffffffULL;
+
+			reg->var_off.value = (old_v & hi_mask) | val;
+			reg->var_off.mask &= hi_mask;
+		} else {
+			__mark_reg_known(reg, val);
+		}
 		break;
+	}
 	case BPF_JSET:
 		false_reg->var_off = tnum_and(false_reg->var_off,
 					      tnum_const(~val));
@@ -4142,38 +4218,61 @@ static void reg_set_min_max(struct bpf_reg_state *true_reg,
 			true_reg->var_off = tnum_or(true_reg->var_off,
 						    tnum_const(val));
 		break;
-	case BPF_JGT:
-		false_reg->umax_value = min(false_reg->umax_value, val);
-		true_reg->umin_value = max(true_reg->umin_value, val + 1);
-		break;
-	case BPF_JSGT:
-		false_reg->smax_value = min_t(s64, false_reg->smax_value, val);
-		true_reg->smin_value = max_t(s64, true_reg->smin_value, val + 1);
-		break;
-	case BPF_JLT:
-		false_reg->umin_value = max(false_reg->umin_value, val);
-		true_reg->umax_value = min(true_reg->umax_value, val - 1);
-		break;
-	case BPF_JSLT:
-		false_reg->smin_value = max_t(s64, false_reg->smin_value, val);
-		true_reg->smax_value = min_t(s64, true_reg->smax_value, val - 1);
-		break;
 	case BPF_JGE:
-		false_reg->umax_value = min(false_reg->umax_value, val - 1);
-		true_reg->umin_value = max(true_reg->umin_value, val);
+	case BPF_JGT:
+	{
+		u64 false_umax = opcode == BPF_JGT ? val    : val - 1;
+		u64 true_umin = opcode == BPF_JGT ? val + 1 : val;
+
+		if (is_jmp32) {
+			false_umax += gen_hi_max(false_reg->var_off);
+			true_umin += gen_hi_min(true_reg->var_off);
+		}
+		false_reg->umax_value = min(false_reg->umax_value, false_umax);
+		true_reg->umin_value = max(true_reg->umin_value, true_umin);
 		break;
+	}
 	case BPF_JSGE:
-		false_reg->smax_value = min_t(s64, false_reg->smax_value, val - 1);
-		true_reg->smin_value = max_t(s64, true_reg->smin_value, val);
+	case BPF_JSGT:
+	{
+		s64 false_smax = opcode == BPF_JSGT ? sval    : sval - 1;
+		s64 true_smin = opcode == BPF_JSGT ? sval + 1 : sval;
+
+		/* If the full s64 was not sign-extended from s32 then don't
+		 * deduct further info.
+		 */
+		if (is_jmp32 && !cmp_val_with_extended_s64(sval, false_reg))
+			break;
+		false_reg->smax_value = min(false_reg->smax_value, false_smax);
+		true_reg->smin_value = max(true_reg->smin_value, true_smin);
 		break;
+	}
 	case BPF_JLE:
-		false_reg->umin_value = max(false_reg->umin_value, val + 1);
-		true_reg->umax_value = min(true_reg->umax_value, val);
+	case BPF_JLT:
+	{
+		u64 false_umin = opcode == BPF_JLT ? val    : val + 1;
+		u64 true_umax = opcode == BPF_JLT ? val - 1 : val;
+
+		if (is_jmp32) {
+			false_umin += gen_hi_min(false_reg->var_off);
+			true_umax += gen_hi_max(true_reg->var_off);
+		}
+		false_reg->umin_value = max(false_reg->umin_value, false_umin);
+		true_reg->umax_value = min(true_reg->umax_value, true_umax);
 		break;
+	}
 	case BPF_JSLE:
-		false_reg->smin_value = max_t(s64, false_reg->smin_value, val + 1);
-		true_reg->smax_value = min_t(s64, true_reg->smax_value, val);
+	case BPF_JSLT:
+	{
+		s64 false_smin = opcode == BPF_JSLT ? sval    : sval + 1;
+		s64 true_smax = opcode == BPF_JSLT ? sval - 1 : sval;
+
+		if (is_jmp32 && !cmp_val_with_extended_s64(sval, false_reg))
+			break;
+		false_reg->smin_value = max(false_reg->smin_value, false_smin);
+		true_reg->smax_value = min(true_reg->smax_value, true_smax);
 		break;
+	}
 	default:
 		break;
 	}
@@ -4196,24 +4295,34 @@ static void reg_set_min_max(struct bpf_reg_state *true_reg,
  */
 static void reg_set_min_max_inv(struct bpf_reg_state *true_reg,
 				struct bpf_reg_state *false_reg, u64 val,
-				u8 opcode)
+				u8 opcode, bool is_jmp32)
 {
+	s64 sval;
+
 	if (__is_pointer_value(false, false_reg))
 		return;
 
+	val = is_jmp32 ? (u32)val : val;
+	sval = is_jmp32 ? (s64)(s32)val : (s64)val;
+
 	switch (opcode) {
 	case BPF_JEQ:
-		/* If this is false then we know nothing Jon Snow, but if it is
-		 * true then we know for sure.
-		 */
-		__mark_reg_known(true_reg, val);
-		break;
 	case BPF_JNE:
-		/* If this is true we know nothing Jon Snow, but if it is false
-		 * we know the value for sure;
-		 */
-		__mark_reg_known(false_reg, val);
+	{
+		struct bpf_reg_state *reg =
+			opcode == BPF_JEQ ? true_reg : false_reg;
+
+		if (is_jmp32) {
+			u64 old_v = reg->var_off.value;
+			u64 hi_mask = ~0xffffffffULL;
+
+			reg->var_off.value = (old_v & hi_mask) | val;
+			reg->var_off.mask &= hi_mask;
+		} else {
+			__mark_reg_known(reg, val);
+		}
 		break;
+	}
 	case BPF_JSET:
 		false_reg->var_off = tnum_and(false_reg->var_off,
 					      tnum_const(~val));
@@ -4221,38 +4330,58 @@ static void reg_set_min_max_inv(struct bpf_reg_state *true_reg,
 			true_reg->var_off = tnum_or(true_reg->var_off,
 						    tnum_const(val));
 		break;
-	case BPF_JGT:
-		true_reg->umax_value = min(true_reg->umax_value, val - 1);
-		false_reg->umin_value = max(false_reg->umin_value, val);
-		break;
-	case BPF_JSGT:
-		true_reg->smax_value = min_t(s64, true_reg->smax_value, val - 1);
-		false_reg->smin_value = max_t(s64, false_reg->smin_value, val);
-		break;
-	case BPF_JLT:
-		true_reg->umin_value = max(true_reg->umin_value, val + 1);
-		false_reg->umax_value = min(false_reg->umax_value, val);
-		break;
-	case BPF_JSLT:
-		true_reg->smin_value = max_t(s64, true_reg->smin_value, val + 1);
-		false_reg->smax_value = min_t(s64, false_reg->smax_value, val);
-		break;
 	case BPF_JGE:
-		true_reg->umax_value = min(true_reg->umax_value, val);
-		false_reg->umin_value = max(false_reg->umin_value, val + 1);
+	case BPF_JGT:
+	{
+		u64 false_umin = opcode == BPF_JGT ? val    : val + 1;
+		u64 true_umax = opcode == BPF_JGT ? val - 1 : val;
+
+		if (is_jmp32) {
+			false_umin += gen_hi_min(false_reg->var_off);
+			true_umax += gen_hi_max(true_reg->var_off);
+		}
+		false_reg->umin_value = max(false_reg->umin_value, false_umin);
+		true_reg->umax_value = min(true_reg->umax_value, true_umax);
 		break;
+	}
 	case BPF_JSGE:
-		true_reg->smax_value = min_t(s64, true_reg->smax_value, val);
-		false_reg->smin_value = max_t(s64, false_reg->smin_value, val + 1);
+	case BPF_JSGT:
+	{
+		s64 false_smin = opcode == BPF_JSGT ? sval    : sval + 1;
+		s64 true_smax = opcode == BPF_JSGT ? sval - 1 : sval;
+
+		if (is_jmp32 && !cmp_val_with_extended_s64(sval, false_reg))
+			break;
+		false_reg->smin_value = max(false_reg->smin_value, false_smin);
+		true_reg->smax_value = min(true_reg->smax_value, true_smax);
 		break;
+	}
 	case BPF_JLE:
-		true_reg->umin_value = max(true_reg->umin_value, val);
-		false_reg->umax_value = min(false_reg->umax_value, val - 1);
+	case BPF_JLT:
+	{
+		u64 false_umax = opcode == BPF_JLT ? val    : val - 1;
+		u64 true_umin = opcode == BPF_JLT ? val + 1 : val;
+
+		if (is_jmp32) {
+			false_umax += gen_hi_max(false_reg->var_off);
+			true_umin += gen_hi_min(true_reg->var_off);
+		}
+		false_reg->umax_value = min(false_reg->umax_value, false_umax);
+		true_reg->umin_value = max(true_reg->umin_value, true_umin);
 		break;
+	}
 	case BPF_JSLE:
-		true_reg->smin_value = max_t(s64, true_reg->smin_value, val);
-		false_reg->smax_value = min_t(s64, false_reg->smax_value, val - 1);
+	case BPF_JSLT:
+	{
+		s64 false_smax = opcode == BPF_JSLT ? sval    : sval - 1;
+		s64 true_smin = opcode == BPF_JSLT ? sval + 1 : sval;
+
+		if (is_jmp32 && !cmp_val_with_extended_s64(sval, false_reg))
+			break;
+		false_reg->smax_value = min(false_reg->smax_value, false_smax);
+		true_reg->smin_value = max(true_reg->smin_value, true_smin);
 		break;
+	}
 	default:
 		break;
 	}
@@ -4390,6 +4519,10 @@ static bool try_match_pkt_pointers(const struct bpf_insn *insn,
 	if (BPF_SRC(insn->code) != BPF_X)
 		return false;
 
+	/* Pointers are always 64-bit. */
+	if (BPF_CLASS(insn->code) == BPF_JMP32)
+		return false;
+
 	switch (BPF_OP(insn->code)) {
 	case BPF_JGT:
 		if ((dst_reg->type == PTR_TO_PACKET &&
@@ -4482,16 +4615,18 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
 	struct bpf_reg_state *regs = this_branch->frame[this_branch->curframe]->regs;
 	struct bpf_reg_state *dst_reg, *other_branch_regs;
 	u8 opcode = BPF_OP(insn->code);
+	bool is_jmp32;
 	int err;
 
-	if (opcode > BPF_JSLE) {
-		verbose(env, "invalid BPF_JMP opcode %x\n", opcode);
+	/* Only conditional jumps are expected to reach here. */
+	if (opcode == BPF_JA || opcode > BPF_JSLE) {
+		verbose(env, "invalid BPF_JMP/JMP32 opcode %x\n", opcode);
 		return -EINVAL;
 	}
 
 	if (BPF_SRC(insn->code) == BPF_X) {
 		if (insn->imm != 0) {
-			verbose(env, "BPF_JMP uses reserved fields\n");
+			verbose(env, "BPF_JMP/JMP32 uses reserved fields\n");
 			return -EINVAL;
 		}
 
@@ -4507,7 +4642,7 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
 		}
 	} else {
 		if (insn->src_reg != BPF_REG_0) {
-			verbose(env, "BPF_JMP uses reserved fields\n");
+			verbose(env, "BPF_JMP/JMP32 uses reserved fields\n");
 			return -EINVAL;
 		}
 	}
@@ -4518,9 +4653,11 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
 		return err;
 
 	dst_reg = &regs[insn->dst_reg];
+	is_jmp32 = BPF_CLASS(insn->code) == BPF_JMP32;
 
 	if (BPF_SRC(insn->code) == BPF_K) {
-		int pred = is_branch_taken(dst_reg, insn->imm, opcode);
+		int pred = is_branch_taken(dst_reg, insn->imm, opcode,
+					   is_jmp32);
 
 		if (pred == 1) {
 			 /* only follow the goto, ignore fall-through */
@@ -4548,30 +4685,51 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
 	 * comparable.
 	 */
 	if (BPF_SRC(insn->code) == BPF_X) {
+		struct bpf_reg_state *src_reg = &regs[insn->src_reg];
+		struct bpf_reg_state lo_reg0 = *dst_reg;
+		struct bpf_reg_state lo_reg1 = *src_reg;
+		struct bpf_reg_state *src_lo, *dst_lo;
+
+		dst_lo = &lo_reg0;
+		src_lo = &lo_reg1;
+		coerce_reg_to_size(dst_lo, 4);
+		coerce_reg_to_size(src_lo, 4);
+
 		if (dst_reg->type == SCALAR_VALUE &&
-		    regs[insn->src_reg].type == SCALAR_VALUE) {
-			if (tnum_is_const(regs[insn->src_reg].var_off))
+		    src_reg->type == SCALAR_VALUE) {
+			if (tnum_is_const(src_reg->var_off) ||
+			    (is_jmp32 && tnum_is_const(src_lo->var_off)))
 				reg_set_min_max(&other_branch_regs[insn->dst_reg],
-						dst_reg, regs[insn->src_reg].var_off.value,
-						opcode);
-			else if (tnum_is_const(dst_reg->var_off))
+						dst_reg,
+						is_jmp32
+						? src_lo->var_off.value
+						: src_reg->var_off.value,
+						opcode, is_jmp32);
+			else if (tnum_is_const(dst_reg->var_off) ||
+				 (is_jmp32 && tnum_is_const(dst_lo->var_off)))
 				reg_set_min_max_inv(&other_branch_regs[insn->src_reg],
-						    &regs[insn->src_reg],
-						    dst_reg->var_off.value, opcode);
-			else if (opcode == BPF_JEQ || opcode == BPF_JNE)
+						    src_reg,
+						    is_jmp32
+						    ? dst_lo->var_off.value
+						    : dst_reg->var_off.value,
+						    opcode, is_jmp32);
+			else if (!is_jmp32 &&
+				 (opcode == BPF_JEQ || opcode == BPF_JNE))
 				/* Comparing for equality, we can combine knowledge */
 				reg_combine_min_max(&other_branch_regs[insn->src_reg],
 						    &other_branch_regs[insn->dst_reg],
-						    &regs[insn->src_reg],
-						    &regs[insn->dst_reg], opcode);
+						    src_reg, dst_reg, opcode);
 		}
 	} else if (dst_reg->type == SCALAR_VALUE) {
 		reg_set_min_max(&other_branch_regs[insn->dst_reg],
-					dst_reg, insn->imm, opcode);
+					dst_reg, insn->imm, opcode, is_jmp32);
 	}
 
-	/* detect if R == 0 where R is returned from bpf_map_lookup_elem() */
-	if (BPF_SRC(insn->code) == BPF_K &&
+	/* detect if R == 0 where R is returned from bpf_map_lookup_elem().
+	 * NOTE: these optimizations below are related with pointer comparison
+	 *       which will never be JMP32.
+	 */
+	if (!is_jmp32 && BPF_SRC(insn->code) == BPF_K &&
 	    insn->imm == 0 && (opcode == BPF_JEQ || opcode == BPF_JNE) &&
 	    reg_type_may_be_null(dst_reg->type)) {
 		/* Mark all identical registers in each branch as either
@@ -4900,7 +5058,8 @@ peek_stack:
 		goto check_state;
 	t = insn_stack[cur_stack - 1];
 
-	if (BPF_CLASS(insns[t].code) == BPF_JMP) {
+	if (BPF_CLASS(insns[t].code) == BPF_JMP ||
+	    BPF_CLASS(insns[t].code) == BPF_JMP32) {
 		u8 opcode = BPF_OP(insns[t].code);
 
 		if (opcode == BPF_EXIT) {
@@ -4997,13 +5156,14 @@ static int check_btf_func(struct bpf_verifier_env *env,
 			  const union bpf_attr *attr,
 			  union bpf_attr __user *uattr)
 {
-	u32 i, nfuncs, urec_size, min_size, prev_offset;
+	u32 i, nfuncs, urec_size, min_size;
 	u32 krec_size = sizeof(struct bpf_func_info);
 	struct bpf_func_info *krecord;
 	const struct btf_type *type;
 	struct bpf_prog *prog;
 	const struct btf *btf;
 	void __user *urecord;
+	u32 prev_offset = 0;
 	int ret = 0;
 
 	nfuncs = attr->func_info_cnt;
@@ -6055,7 +6215,7 @@ static int do_check(struct bpf_verifier_env *env)
 			if (err)
 				return err;
 
-		} else if (class == BPF_JMP) {
+		} else if (class == BPF_JMP || class == BPF_JMP32) {
 			u8 opcode = BPF_OP(insn->code);
 
 			if (opcode == BPF_CALL) {
@@ -6063,7 +6223,8 @@ static int do_check(struct bpf_verifier_env *env)
 				    insn->off != 0 ||
 				    (insn->src_reg != BPF_REG_0 &&
 				     insn->src_reg != BPF_PSEUDO_CALL) ||
-				    insn->dst_reg != BPF_REG_0) {
+				    insn->dst_reg != BPF_REG_0 ||
+				    class == BPF_JMP32) {
 					verbose(env, "BPF_CALL uses reserved fields\n");
 					return -EINVAL;
 				}
@@ -6079,7 +6240,8 @@ static int do_check(struct bpf_verifier_env *env)
 				if (BPF_SRC(insn->code) != BPF_K ||
 				    insn->imm != 0 ||
 				    insn->src_reg != BPF_REG_0 ||
-				    insn->dst_reg != BPF_REG_0) {
+				    insn->dst_reg != BPF_REG_0 ||
+				    class == BPF_JMP32) {
 					verbose(env, "BPF_JA uses reserved fields\n");
 					return -EINVAL;
 				}
@@ -6091,7 +6253,8 @@ static int do_check(struct bpf_verifier_env *env)
 				if (BPF_SRC(insn->code) != BPF_K ||
 				    insn->imm != 0 ||
 				    insn->src_reg != BPF_REG_0 ||
-				    insn->dst_reg != BPF_REG_0) {
+				    insn->dst_reg != BPF_REG_0 ||
+				    class == BPF_JMP32) {
 					verbose(env, "BPF_EXIT uses reserved fields\n");
 					return -EINVAL;
 				}
@@ -6431,6 +6594,153 @@ static struct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 of
 	return new_prog;
 }
 
+static int adjust_subprog_starts_after_remove(struct bpf_verifier_env *env,
+					      u32 off, u32 cnt)
+{
+	int i, j;
+
+	/* find first prog starting at or after off (first to remove) */
+	for (i = 0; i < env->subprog_cnt; i++)
+		if (env->subprog_info[i].start >= off)
+			break;
+	/* find first prog starting at or after off + cnt (first to stay) */
+	for (j = i; j < env->subprog_cnt; j++)
+		if (env->subprog_info[j].start >= off + cnt)
+			break;
+	/* if j doesn't start exactly at off + cnt, we are just removing
+	 * the front of previous prog
+	 */
+	if (env->subprog_info[j].start != off + cnt)
+		j--;
+
+	if (j > i) {
+		struct bpf_prog_aux *aux = env->prog->aux;
+		int move;
+
+		/* move fake 'exit' subprog as well */
+		move = env->subprog_cnt + 1 - j;
+
+		memmove(env->subprog_info + i,
+			env->subprog_info + j,
+			sizeof(*env->subprog_info) * move);
+		env->subprog_cnt -= j - i;
+
+		/* remove func_info */
+		if (aux->func_info) {
+			move = aux->func_info_cnt - j;
+
+			memmove(aux->func_info + i,
+				aux->func_info + j,
+				sizeof(*aux->func_info) * move);
+			aux->func_info_cnt -= j - i;
+			/* func_info->insn_off is set after all code rewrites,
+			 * in adjust_btf_func() - no need to adjust
+			 */
+		}
+	} else {
+		/* convert i from "first prog to remove" to "first to adjust" */
+		if (env->subprog_info[i].start == off)
+			i++;
+	}
+
+	/* update fake 'exit' subprog as well */
+	for (; i <= env->subprog_cnt; i++)
+		env->subprog_info[i].start -= cnt;
+
+	return 0;
+}
+
+static int bpf_adj_linfo_after_remove(struct bpf_verifier_env *env, u32 off,
+				      u32 cnt)
+{
+	struct bpf_prog *prog = env->prog;
+	u32 i, l_off, l_cnt, nr_linfo;
+	struct bpf_line_info *linfo;
+
+	nr_linfo = prog->aux->nr_linfo;
+	if (!nr_linfo)
+		return 0;
+
+	linfo = prog->aux->linfo;
+
+	/* find first line info to remove, count lines to be removed */
+	for (i = 0; i < nr_linfo; i++)
+		if (linfo[i].insn_off >= off)
+			break;
+
+	l_off = i;
+	l_cnt = 0;
+	for (; i < nr_linfo; i++)
+		if (linfo[i].insn_off < off + cnt)
+			l_cnt++;
+		else
+			break;
+
+	/* First live insn doesn't match first live linfo, it needs to "inherit"
+	 * last removed linfo.  prog is already modified, so prog->len == off
+	 * means no live instructions after (tail of the program was removed).
+	 */
+	if (prog->len != off && l_cnt &&
+	    (i == nr_linfo || linfo[i].insn_off != off + cnt)) {
+		l_cnt--;
+		linfo[--i].insn_off = off + cnt;
+	}
+
+	/* remove the line info which refer to the removed instructions */
+	if (l_cnt) {
+		memmove(linfo + l_off, linfo + i,
+			sizeof(*linfo) * (nr_linfo - i));
+
+		prog->aux->nr_linfo -= l_cnt;
+		nr_linfo = prog->aux->nr_linfo;
+	}
+
+	/* pull all linfo[i].insn_off >= off + cnt in by cnt */
+	for (i = l_off; i < nr_linfo; i++)
+		linfo[i].insn_off -= cnt;
+
+	/* fix up all subprogs (incl. 'exit') which start >= off */
+	for (i = 0; i <= env->subprog_cnt; i++)
+		if (env->subprog_info[i].linfo_idx > l_off) {
+			/* program may have started in the removed region but
+			 * may not be fully removed
+			 */
+			if (env->subprog_info[i].linfo_idx >= l_off + l_cnt)
+				env->subprog_info[i].linfo_idx -= l_cnt;
+			else
+				env->subprog_info[i].linfo_idx = l_off;
+		}
+
+	return 0;
+}
+
+static int verifier_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt)
+{
+	struct bpf_insn_aux_data *aux_data = env->insn_aux_data;
+	unsigned int orig_prog_len = env->prog->len;
+	int err;
+
+	if (bpf_prog_is_dev_bound(env->prog->aux))
+		bpf_prog_offload_remove_insns(env, off, cnt);
+
+	err = bpf_remove_insns(env->prog, off, cnt);
+	if (err)
+		return err;
+
+	err = adjust_subprog_starts_after_remove(env, off, cnt);
+	if (err)
+		return err;
+
+	err = bpf_adj_linfo_after_remove(env, off, cnt);
+	if (err)
+		return err;
+
+	memmove(aux_data + off,	aux_data + off + cnt,
+		sizeof(*aux_data) * (orig_prog_len - off - cnt));
+
+	return 0;
+}
+
 /* 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
@@ -6457,6 +6767,91 @@ static void sanitize_dead_code(struct bpf_verifier_env *env)
 	}
 }
 
+static bool insn_is_cond_jump(u8 code)
+{
+	u8 op;
+
+	if (BPF_CLASS(code) == BPF_JMP32)
+		return true;
+
+	if (BPF_CLASS(code) != BPF_JMP)
+		return false;
+
+	op = BPF_OP(code);
+	return op != BPF_JA && op != BPF_EXIT && op != BPF_CALL;
+}
+
+static void opt_hard_wire_dead_code_branches(struct bpf_verifier_env *env)
+{
+	struct bpf_insn_aux_data *aux_data = env->insn_aux_data;
+	struct bpf_insn ja = BPF_JMP_IMM(BPF_JA, 0, 0, 0);
+	struct bpf_insn *insn = env->prog->insnsi;
+	const int insn_cnt = env->prog->len;
+	int i;
+
+	for (i = 0; i < insn_cnt; i++, insn++) {
+		if (!insn_is_cond_jump(insn->code))
+			continue;
+
+		if (!aux_data[i + 1].seen)
+			ja.off = insn->off;
+		else if (!aux_data[i + 1 + insn->off].seen)
+			ja.off = 0;
+		else
+			continue;
+
+		if (bpf_prog_is_dev_bound(env->prog->aux))
+			bpf_prog_offload_replace_insn(env, i, &ja);
+
+		memcpy(insn, &ja, sizeof(ja));
+	}
+}
+
+static int opt_remove_dead_code(struct bpf_verifier_env *env)
+{
+	struct bpf_insn_aux_data *aux_data = env->insn_aux_data;
+	int insn_cnt = env->prog->len;
+	int i, err;
+
+	for (i = 0; i < insn_cnt; i++) {
+		int j;
+
+		j = 0;
+		while (i + j < insn_cnt && !aux_data[i + j].seen)
+			j++;
+		if (!j)
+			continue;
+
+		err = verifier_remove_insns(env, i, j);
+		if (err)
+			return err;
+		insn_cnt = env->prog->len;
+	}
+
+	return 0;
+}
+
+static int opt_remove_nops(struct bpf_verifier_env *env)
+{
+	const struct bpf_insn ja = BPF_JMP_IMM(BPF_JA, 0, 0, 0);
+	struct bpf_insn *insn = env->prog->insnsi;
+	int insn_cnt = env->prog->len;
+	int i, err;
+
+	for (i = 0; i < insn_cnt; i++) {
+		if (memcmp(&insn[i], &ja, sizeof(ja)))
+			continue;
+
+		err = verifier_remove_insns(env, i, 1);
+		if (err)
+			return err;
+		insn_cnt--;
+		i--;
+	}
+
+	return 0;
+}
+
 /* convert load instructions that access fields of a context type into a
  * sequence of instructions that access fields of the underlying structure:
  *     struct __sk_buff    -> struct sk_buff
@@ -7147,7 +7542,8 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
 {
 	struct bpf_verifier_env *env;
 	struct bpf_verifier_log *log;
-	int ret = -EINVAL;
+	int i, len, ret = -EINVAL;
+	bool is_priv;
 
 	/* no program is valid */
 	if (ARRAY_SIZE(bpf_verifier_ops) == 0)
@@ -7161,12 +7557,14 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
 		return -ENOMEM;
 	log = &env->log;
 
+	len = (*prog)->len;
 	env->insn_aux_data =
-		vzalloc(array_size(sizeof(struct bpf_insn_aux_data),
-				   (*prog)->len));
+		vzalloc(array_size(sizeof(struct bpf_insn_aux_data), len));
 	ret = -ENOMEM;
 	if (!env->insn_aux_data)
 		goto err_free_env;
+	for (i = 0; i < len; i++)
+		env->insn_aux_data[i].orig_idx = i;
 	env->prog = *prog;
 	env->ops = bpf_verifier_ops[env->prog->type];
 
@@ -7194,6 +7592,9 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
 	if (attr->prog_flags & BPF_F_ANY_ALIGNMENT)
 		env->strict_alignment = false;
 
+	is_priv = capable(CAP_SYS_ADMIN);
+	env->allow_ptr_leaks = is_priv;
+
 	ret = replace_map_fd_with_map_ptr(env);
 	if (ret < 0)
 		goto skip_full_check;
@@ -7211,8 +7612,6 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
 	if (!env->explored_states)
 		goto skip_full_check;
 
-	env->allow_ptr_leaks = capable(CAP_SYS_ADMIN);
-
 	ret = check_subprogs(env);
 	if (ret < 0)
 		goto skip_full_check;
@@ -7242,8 +7641,17 @@ skip_full_check:
 		ret = check_max_stack_depth(env);
 
 	/* instruction rewrites happen after this point */
-	if (ret == 0)
-		sanitize_dead_code(env);
+	if (is_priv) {
+		if (ret == 0)
+			opt_hard_wire_dead_code_branches(env);
+		if (ret == 0)
+			ret = opt_remove_dead_code(env);
+		if (ret == 0)
+			ret = opt_remove_nops(env);
+	} else {
+		if (ret == 0)
+			sanitize_dead_code(env);
+	}
 
 	if (ret == 0)
 		/* program is valid, convert *(u32*)(ctx + off) accesses */