Commit 6a9f5cdb authored by Martin KaFai Lau's avatar Martin KaFai Lau
Browse files

Merge branch 'net: skbuff: skb bitfield compaction - bpf' 

Jakub Kicinski says:

====================

I'm trying to make more of the sk_buff bits optional.
Move the BPF-accessed bits a little - because they must
be at coding-time-constant offsets they must precede any
optional bit. While at it clean up the naming a bit.

v1: https://lore.kernel.org/all/20230308003159.441580-1-kuba@kernel.org/


====================

Signed-off-by: default avatarMartin KaFai Lau <martin.lau@kernel.org>
parents 01dc26c9 c0ba8611

include/linux/skbuff.h

+18 −18
Original line number Diff line number Diff line
@@ -944,6 +944,19 @@ struct sk_buff { 
	__u8			ip_summed:2;

	__u8			ooo_okay:1;



	/* private: */

	__u8			__mono_tc_offset[0];

	/* public: */

	__u8			mono_delivery_time:1;	/* See SKB_MONO_DELIVERY_TIME_MASK */

#ifdef CONFIG_NET_CLS_ACT

	__u8			tc_at_ingress:1;	/* See TC_AT_INGRESS_MASK */

	__u8			tc_skip_classify:1;

#endif

	__u8			remcsum_offload:1;

	__u8			csum_complete_sw:1;

	__u8			csum_level:2;

	__u8			dst_pending_confirm:1;



	__u8			l4_hash:1;

	__u8			sw_hash:1;

	__u8			wifi_acked_valid:1;
@@ -953,19 +966,6 @@ struct sk_buff { 
	__u8			encapsulation:1;

	__u8			encap_hdr_csum:1;

	__u8			csum_valid:1;



	/* private: */

	__u8			__pkt_vlan_present_offset[0];

	/* public: */

	__u8			remcsum_offload:1;

	__u8			csum_complete_sw:1;

	__u8			csum_level:2;

	__u8			dst_pending_confirm:1;

	__u8			mono_delivery_time:1;	/* See SKB_MONO_DELIVERY_TIME_MASK */

#ifdef CONFIG_NET_CLS_ACT

	__u8			tc_skip_classify:1;

	__u8			tc_at_ingress:1;	/* See TC_AT_INGRESS_MASK */

#endif

#ifdef CONFIG_IPV6_NDISC_NODETYPE

	__u8			ndisc_nodetype:2;

#endif
@@ -1072,13 +1072,13 @@ struct sk_buff { 
 * around, you also must adapt these constants.

 */

#ifdef __BIG_ENDIAN_BITFIELD

#define TC_AT_INGRESS_MASK		(1 << 0)

#define SKB_MONO_DELIVERY_TIME_MASK	(1 << 2)

#define SKB_MONO_DELIVERY_TIME_MASK	(1 << 7)

#define TC_AT_INGRESS_MASK		(1 << 6)

#else

#define TC_AT_INGRESS_MASK		(1 << 7)

#define SKB_MONO_DELIVERY_TIME_MASK	(1 << 5)

#define SKB_MONO_DELIVERY_TIME_MASK	(1 << 0)

#define TC_AT_INGRESS_MASK		(1 << 1)

#endif

#define PKT_VLAN_PRESENT_OFFSET	offsetof(struct sk_buff, __pkt_vlan_present_offset)

#define SKB_BF_MONO_TC_OFFSET		offsetof(struct sk_buff, __mono_tc_offset)



#ifdef __KERNEL__

/*

net/core/filter.c

+4 −4
Original line number Diff line number Diff line
@@ -9185,7 +9185,7 @@ static struct bpf_insn *bpf_convert_tstamp_type_read(const struct bpf_insn *si, 
	__u8 tmp_reg = BPF_REG_AX;



	*insn++ = BPF_LDX_MEM(BPF_B, tmp_reg, skb_reg,

			      PKT_VLAN_PRESENT_OFFSET);

			      SKB_BF_MONO_TC_OFFSET);

	*insn++ = BPF_JMP32_IMM(BPF_JSET, tmp_reg,

				SKB_MONO_DELIVERY_TIME_MASK, 2);

	*insn++ = BPF_MOV32_IMM(value_reg, BPF_SKB_TSTAMP_UNSPEC);
@@ -9232,7 +9232,7 @@ static struct bpf_insn *bpf_convert_tstamp_read(const struct bpf_prog *prog, 
		/* AX is needed because src_reg and dst_reg could be the same */

		__u8 tmp_reg = BPF_REG_AX;



		*insn++ = BPF_LDX_MEM(BPF_B, tmp_reg, skb_reg, PKT_VLAN_PRESENT_OFFSET);

		*insn++ = BPF_LDX_MEM(BPF_B, tmp_reg, skb_reg, SKB_BF_MONO_TC_OFFSET);

		*insn++ = BPF_ALU32_IMM(BPF_AND, tmp_reg,

					TC_AT_INGRESS_MASK | SKB_MONO_DELIVERY_TIME_MASK);

		*insn++ = BPF_JMP32_IMM(BPF_JNE, tmp_reg,
@@ -9267,14 +9267,14 @@ static struct bpf_insn *bpf_convert_tstamp_write(const struct bpf_prog *prog, 
	if (!prog->tstamp_type_access) {

		__u8 tmp_reg = BPF_REG_AX;



		*insn++ = BPF_LDX_MEM(BPF_B, tmp_reg, skb_reg, PKT_VLAN_PRESENT_OFFSET);

		*insn++ = BPF_LDX_MEM(BPF_B, tmp_reg, skb_reg, SKB_BF_MONO_TC_OFFSET);

		/* Writing __sk_buff->tstamp as ingress, goto <clear> */

		*insn++ = BPF_JMP32_IMM(BPF_JSET, tmp_reg, TC_AT_INGRESS_MASK, 1);

		/* goto <store> */

		*insn++ = BPF_JMP_A(2);

		/* <clear>: mono_delivery_time */

		*insn++ = BPF_ALU32_IMM(BPF_AND, tmp_reg, ~SKB_MONO_DELIVERY_TIME_MASK);

		*insn++ = BPF_STX_MEM(BPF_B, skb_reg, tmp_reg, PKT_VLAN_PRESENT_OFFSET);

		*insn++ = BPF_STX_MEM(BPF_B, skb_reg, tmp_reg, SKB_BF_MONO_TC_OFFSET);

	}

#endif

tools/testing/selftests/bpf/prog_tests/ctx_rewrite.c

+7 −7
Original line number Diff line number Diff line
@@ -68,17 +68,17 @@ static struct test_case test_cases[] = { 
#if defined(__x86_64__) || defined(__aarch64__)

	{

		N(SCHED_CLS, struct __sk_buff, tstamp),

		.read  = "r11 = *(u8 *)($ctx + sk_buff::__pkt_vlan_present_offset);"

			 "w11 &= 160;"

			 "if w11 != 0xa0 goto pc+2;"

		.read  = "r11 = *(u8 *)($ctx + sk_buff::__mono_tc_offset);"

			 "w11 &= 3;"

			 "if w11 != 0x3 goto pc+2;"

			 "$dst = 0;"

			 "goto pc+1;"

			 "$dst = *(u64 *)($ctx + sk_buff::tstamp);",

		.write = "r11 = *(u8 *)($ctx + sk_buff::__pkt_vlan_present_offset);"

			 "if w11 & 0x80 goto pc+1;"

		.write = "r11 = *(u8 *)($ctx + sk_buff::__mono_tc_offset);"

			 "if w11 & 0x2 goto pc+1;"

			 "goto pc+2;"

			 "w11 &= -33;"

			 "*(u8 *)($ctx + sk_buff::__pkt_vlan_present_offset) = r11;"

			 "w11 &= -2;"

			 "*(u8 *)($ctx + sk_buff::__mono_tc_offset) = r11;"

			 "*(u64 *)($ctx + sk_buff::tstamp) = $src;",

	},

#endif