Commit 9a5a908c authored by David S. Miller's avatar David S. Miller
Browse files

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



Daniel Borkmann says:

====================
pull-request: bpf-next 2020-06-02

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

We've added 10 non-merge commits during the last 1 day(s) which contain
a total of 15 files changed, 229 insertions(+), 74 deletions(-).

The main changes are:

1) Several fixes to s390 BPF JIT e.g. fixing kernel panic when BPF stack is
   not 8-byte aligned, from Ilya Leoshkevich.

2) Fix bpf_skb_adjust_room() helper's CHECKSUM_UNNECESSARY handling which
   was wrongly bypassing TCP checksum verification, from Daniel Borkmann.

3) Fix tools/bpf/ build under MAKEFLAGS=rR which causes built-in CXX and
   others vars to be undefined, also from Ilya Leoshkevich.

4) Fix BPF ringbuf's selftest shared sample_cnt variable to avoid compiler
   optimizations on it, from Andrii Nakryiko.

5) Fix up test_verifier selftest due to addition of rx_queue_mapping to
   the bpf_sock structure, from Alexei Starovoitov.
====================

Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parents 9a25c1df e7ad28e6

arch/s390/net/bpf_jit_comp.c

+12 −10
Original line number Diff line number Diff line
@@ -503,7 +503,8 @@ static void bpf_jit_prologue(struct bpf_jit *jit, u32 stack_depth) 
	} else {

		/* j tail_call_start: NOP if no tail calls are used */

		EMIT4_PCREL(0xa7f40000, 6);

		_EMIT2(0);

		/* bcr 0,%0 */

		EMIT2(0x0700, 0, REG_0);

	}

	/* Tail calls have to skip above initialization */

	jit->tail_call_start = jit->prg;
@@ -594,7 +595,7 @@ static void bpf_jit_epilogue(struct bpf_jit *jit, u32 stack_depth) 
 * stack space for the large switch statement.

 */

static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp,

				 int i, bool extra_pass)

				 int i, bool extra_pass, u32 stack_depth)

{

	struct bpf_insn *insn = &fp->insnsi[i];

	u32 dst_reg = insn->dst_reg;
@@ -1207,7 +1208,7 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, 
		 */



		if (jit->seen & SEEN_STACK)

			off = STK_OFF_TCCNT + STK_OFF + fp->aux->stack_depth;

			off = STK_OFF_TCCNT + STK_OFF + stack_depth;

		else

			off = STK_OFF_TCCNT;

		/* lhi %w0,1 */
@@ -1249,7 +1250,7 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, 
		/*

		 * Restore registers before calling function

		 */

		save_restore_regs(jit, REGS_RESTORE, fp->aux->stack_depth);

		save_restore_regs(jit, REGS_RESTORE, stack_depth);



		/*

		 * goto *(prog->bpf_func + tail_call_start);
@@ -1519,7 +1520,7 @@ static int bpf_set_addr(struct bpf_jit *jit, int i) 
 * Compile eBPF program into s390x code

 */

static int bpf_jit_prog(struct bpf_jit *jit, struct bpf_prog *fp,

			bool extra_pass)

			bool extra_pass, u32 stack_depth)

{

	int i, insn_count, lit32_size, lit64_size;
@@ -1527,18 +1528,18 @@ static int bpf_jit_prog(struct bpf_jit *jit, struct bpf_prog *fp, 
	jit->lit64 = jit->lit64_start;

	jit->prg = 0;



	bpf_jit_prologue(jit, fp->aux->stack_depth);

	bpf_jit_prologue(jit, stack_depth);

	if (bpf_set_addr(jit, 0) < 0)

		return -1;

	for (i = 0; i < fp->len; i += insn_count) {

		insn_count = bpf_jit_insn(jit, fp, i, extra_pass);

		insn_count = bpf_jit_insn(jit, fp, i, extra_pass, stack_depth);

		if (insn_count < 0)

			return -1;

		/* Next instruction address */

		if (bpf_set_addr(jit, i + insn_count) < 0)

			return -1;

	}

	bpf_jit_epilogue(jit, fp->aux->stack_depth);

	bpf_jit_epilogue(jit, stack_depth);



	lit32_size = jit->lit32 - jit->lit32_start;

	lit64_size = jit->lit64 - jit->lit64_start;
@@ -1569,6 +1570,7 @@ struct s390_jit_data { 
 */

struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)

{

	u32 stack_depth = round_up(fp->aux->stack_depth, 8);

	struct bpf_prog *tmp, *orig_fp = fp;

	struct bpf_binary_header *header;

	struct s390_jit_data *jit_data;
@@ -1621,7 +1623,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp) 
	 *   - 3:   Calculate program size and addrs arrray

	 */

	for (pass = 1; pass <= 3; pass++) {

		if (bpf_jit_prog(&jit, fp, extra_pass)) {

		if (bpf_jit_prog(&jit, fp, extra_pass, stack_depth)) {

			fp = orig_fp;

			goto free_addrs;

		}
@@ -1635,7 +1637,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp) 
		goto free_addrs;

	}

skip_init_ctx:

	if (bpf_jit_prog(&jit, fp, extra_pass)) {

	if (bpf_jit_prog(&jit, fp, extra_pass, stack_depth)) {

		bpf_jit_binary_free(header);

		fp = orig_fp;

		goto free_addrs;

include/linux/skbuff.h

+8 −0
Original line number Diff line number Diff line
@@ -3919,6 +3919,14 @@ static inline void __skb_incr_checksum_unnecessary(struct sk_buff *skb) 
	}

}



static inline void __skb_reset_checksum_unnecessary(struct sk_buff *skb)

{

	if (skb->ip_summed == CHECKSUM_UNNECESSARY) {

		skb->ip_summed = CHECKSUM_NONE;

		skb->csum_level = 0;

	}

}



/* Check if we need to perform checksum complete validation.

 *

 * Returns true if checksum complete is needed, false otherwise

include/uapi/linux/bpf.h

+50 −1
Original line number Diff line number Diff line
@@ -1635,6 +1635,13 @@ union bpf_attr { 
 * 		Grow or shrink the room for data in the packet associated to

 * 		*skb* by *len_diff*, and according to the selected *mode*.

 *

 * 		By default, the helper will reset any offloaded checksum

 * 		indicator of the skb to CHECKSUM_NONE. This can be avoided

 * 		by the following flag:

 *

 * 		* **BPF_F_ADJ_ROOM_NO_CSUM_RESET**: Do not reset offloaded

 * 		  checksum data of the skb to CHECKSUM_NONE.

 *

 *		There are two supported modes at this time:

 *

 *		* **BPF_ADJ_ROOM_MAC**: Adjust room at the mac layer
@@ -3213,6 +3220,38 @@ union bpf_attr { 
 *		calculation.

 *	Return

 *		Requested value, or 0, if flags are not recognized.

 *

 * int bpf_csum_level(struct sk_buff *skb, u64 level)

 * 	Description

 * 		Change the skbs checksum level by one layer up or down, or

 * 		reset it entirely to none in order to have the stack perform

 * 		checksum validation. The level is applicable to the following

 * 		protocols: TCP, UDP, GRE, SCTP, FCOE. For example, a decap of

 * 		| ETH | IP | UDP | GUE | IP | TCP | into | ETH | IP | TCP |

 * 		through **bpf_skb_adjust_room**\ () helper with passing in

 * 		**BPF_F_ADJ_ROOM_NO_CSUM_RESET** flag would require one	call

 * 		to **bpf_csum_level**\ () with **BPF_CSUM_LEVEL_DEC** since

 * 		the UDP header is removed. Similarly, an encap of the latter

 * 		into the former could be accompanied by a helper call to

 * 		**bpf_csum_level**\ () with **BPF_CSUM_LEVEL_INC** if the

 * 		skb is still intended to be processed in higher layers of the

 * 		stack instead of just egressing at tc.

 *

 * 		There are three supported level settings at this time:

 *

 * 		* **BPF_CSUM_LEVEL_INC**: Increases skb->csum_level for skbs

 * 		  with CHECKSUM_UNNECESSARY.

 * 		* **BPF_CSUM_LEVEL_DEC**: Decreases skb->csum_level for skbs

 * 		  with CHECKSUM_UNNECESSARY.

 * 		* **BPF_CSUM_LEVEL_RESET**: Resets skb->csum_level to 0 and

 * 		  sets CHECKSUM_NONE to force checksum validation by the stack.

 * 		* **BPF_CSUM_LEVEL_QUERY**: No-op, returns the current

 * 		  skb->csum_level.

 * 	Return

 * 		0 on success, or a negative error in case of failure. In the

 * 		case of **BPF_CSUM_LEVEL_QUERY**, the current skb->csum_level

 * 		is returned or the error code -EACCES in case the skb is not

 * 		subject to CHECKSUM_UNNECESSARY.

 */

#define __BPF_FUNC_MAPPER(FN)		\

	FN(unspec),			\
@@ -3349,7 +3388,8 @@ union bpf_attr { 
	FN(ringbuf_reserve),		\

	FN(ringbuf_submit),		\

	FN(ringbuf_discard),		\

	FN(ringbuf_query),

	FN(ringbuf_query),		\

	FN(csum_level),



/* integer value in 'imm' field of BPF_CALL instruction selects which helper

 * function eBPF program intends to call
@@ -3426,6 +3466,14 @@ enum { 
	BPF_F_CURRENT_NETNS		= (-1L),

};



/* BPF_FUNC_csum_level level values. */

enum {

	BPF_CSUM_LEVEL_QUERY,

	BPF_CSUM_LEVEL_INC,

	BPF_CSUM_LEVEL_DEC,

	BPF_CSUM_LEVEL_RESET,

};



/* BPF_FUNC_skb_adjust_room flags. */

enum {

	BPF_F_ADJ_ROOM_FIXED_GSO	= (1ULL << 0),
@@ -3433,6 +3481,7 @@ enum { 
	BPF_F_ADJ_ROOM_ENCAP_L3_IPV6	= (1ULL << 2),

	BPF_F_ADJ_ROOM_ENCAP_L4_GRE	= (1ULL << 3),

	BPF_F_ADJ_ROOM_ENCAP_L4_UDP	= (1ULL << 4),

	BPF_F_ADJ_ROOM_NO_CSUM_RESET	= (1ULL << 5),

};



enum {

net/core/filter.c

+44 −2
Original line number Diff line number Diff line
@@ -2015,6 +2015,40 @@ static const struct bpf_func_proto bpf_csum_update_proto = { 
	.arg2_type	= ARG_ANYTHING,

};



BPF_CALL_2(bpf_csum_level, struct sk_buff *, skb, u64, level)

{

	/* The interface is to be used in combination with bpf_skb_adjust_room()

	 * for encap/decap of packet headers when BPF_F_ADJ_ROOM_NO_CSUM_RESET

	 * is passed as flags, for example.

	 */

	switch (level) {

	case BPF_CSUM_LEVEL_INC:

		__skb_incr_checksum_unnecessary(skb);

		break;

	case BPF_CSUM_LEVEL_DEC:

		__skb_decr_checksum_unnecessary(skb);

		break;

	case BPF_CSUM_LEVEL_RESET:

		__skb_reset_checksum_unnecessary(skb);

		break;

	case BPF_CSUM_LEVEL_QUERY:

		return skb->ip_summed == CHECKSUM_UNNECESSARY ?

		       skb->csum_level : -EACCES;

	default:

		return -EINVAL;

	}



	return 0;

}



static const struct bpf_func_proto bpf_csum_level_proto = {

	.func		= bpf_csum_level,

	.gpl_only	= false,

	.ret_type	= RET_INTEGER,

	.arg1_type	= ARG_PTR_TO_CTX,

	.arg2_type	= ARG_ANYTHING,

};



static inline int __bpf_rx_skb(struct net_device *dev, struct sk_buff *skb)

{

	return dev_forward_skb(dev, skb);
@@ -3113,7 +3147,8 @@ static int bpf_skb_net_shrink(struct sk_buff *skb, u32 off, u32 len_diff, 
{

	int ret;



	if (flags & ~BPF_F_ADJ_ROOM_FIXED_GSO)

	if (unlikely(flags & ~(BPF_F_ADJ_ROOM_FIXED_GSO |

			       BPF_F_ADJ_ROOM_NO_CSUM_RESET)))

		return -EINVAL;



	if (skb_is_gso(skb) && !skb_is_gso_tcp(skb)) {
@@ -3163,7 +3198,8 @@ BPF_CALL_4(bpf_skb_adjust_room, struct sk_buff *, skb, s32, len_diff, 
	u32 off;

	int ret;



	if (unlikely(flags & ~BPF_F_ADJ_ROOM_MASK))

	if (unlikely(flags & ~(BPF_F_ADJ_ROOM_MASK |

			       BPF_F_ADJ_ROOM_NO_CSUM_RESET)))

		return -EINVAL;

	if (unlikely(len_diff_abs > 0xfffU))

		return -EFAULT;
@@ -3191,6 +3227,8 @@ BPF_CALL_4(bpf_skb_adjust_room, struct sk_buff *, skb, s32, len_diff, 


	ret = shrink ? bpf_skb_net_shrink(skb, off, len_diff_abs, flags) :

		       bpf_skb_net_grow(skb, off, len_diff_abs, flags);

	if (!ret && !(flags & BPF_F_ADJ_ROOM_NO_CSUM_RESET))

		__skb_reset_checksum_unnecessary(skb);



	bpf_compute_data_pointers(skb);

	return ret;
@@ -6276,6 +6314,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) 
		return &bpf_csum_diff_proto;

	case BPF_FUNC_csum_update:

		return &bpf_csum_update_proto;

	case BPF_FUNC_csum_level:

		return &bpf_csum_level_proto;

	case BPF_FUNC_l3_csum_replace:

		return &bpf_l3_csum_replace_proto;

	case BPF_FUNC_l4_csum_replace:
@@ -6609,6 +6649,8 @@ lwt_xmit_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) 
		return &bpf_skb_store_bytes_proto;

	case BPF_FUNC_csum_update:

		return &bpf_csum_update_proto;

	case BPF_FUNC_csum_level:

		return &bpf_csum_level_proto;

	case BPF_FUNC_l3_csum_replace:

		return &bpf_l3_csum_replace_proto;

	case BPF_FUNC_l4_csum_replace:

tools/bpf/Makefile

+3 −3
Original line number Diff line number Diff line
@@ -64,12 +64,12 @@ $(OUTPUT)%.lex.c: $(srctree)/tools/bpf/%.l 
	$(QUIET_FLEX)$(LEX) -o $@ $<



$(OUTPUT)%.o: $(srctree)/tools/bpf/%.c

	$(QUIET_CC)$(COMPILE.c) -o $@ $<

	$(QUIET_CC)$(CC) $(CFLAGS) -c -o $@ $<



$(OUTPUT)%.yacc.o: $(OUTPUT)%.yacc.c

	$(QUIET_CC)$(COMPILE.c) -o $@ $<

	$(QUIET_CC)$(CC) $(CFLAGS) -c -o $@ $<

$(OUTPUT)%.lex.o: $(OUTPUT)%.lex.c

	$(QUIET_CC)$(COMPILE.c) -o $@ $<

	$(QUIET_CC)$(CC) $(CFLAGS) -c -o $@ $<



PROGS = $(OUTPUT)bpf_jit_disasm $(OUTPUT)bpf_dbg $(OUTPUT)bpf_asm

CRA Git | Maintained and supported by SUSTech CRA and CCSE