diff options
author | Martin KaFai Lau <kafai@fb.com> | 2022-03-09 01:05:09 -0800 |
---|---|---|
committer | Daniel Borkmann <daniel@iogearbox.net> | 2022-03-10 22:57:05 +0100 |
commit | 9bb984f28d5bcb917d35d930fcfb89f90f9449fd (patch) | |
tree | d397b169f94ead6433e2608397f2624bfbe417a7 /net/core | |
parent | 9d90db97e4d4537c82a5ee476b1c13553e487f28 (diff) | |
download | linux-9bb984f28d5bcb917d35d930fcfb89f90f9449fd.tar.bz2 |
bpf: Remove BPF_SKB_DELIVERY_TIME_NONE and rename s/delivery_time_/tstamp_/
This patch is to simplify the uapi bpf.h regarding to the tstamp type
and use a similar way as the kernel to describe the value stored
in __sk_buff->tstamp.
My earlier thought was to avoid describing the semantic and
clock base for the rcv timestamp until there is more clarity
on the use case, so the __sk_buff->delivery_time_type naming instead
of __sk_buff->tstamp_type.
With some thoughts, it can reuse the UNSPEC naming. This patch first
removes BPF_SKB_DELIVERY_TIME_NONE and also
rename BPF_SKB_DELIVERY_TIME_UNSPEC to BPF_SKB_TSTAMP_UNSPEC
and BPF_SKB_DELIVERY_TIME_MONO to BPF_SKB_TSTAMP_DELIVERY_MONO.
The semantic of BPF_SKB_TSTAMP_DELIVERY_MONO is the same:
__sk_buff->tstamp has delivery time in mono clock base.
BPF_SKB_TSTAMP_UNSPEC means __sk_buff->tstamp has the (rcv)
tstamp at ingress and the delivery time at egress. At egress,
the clock base could be found from skb->sk->sk_clockid.
__sk_buff->tstamp == 0 naturally means NONE, so NONE is not needed.
With BPF_SKB_TSTAMP_UNSPEC for the rcv tstamp at ingress,
the __sk_buff->delivery_time_type is also renamed to __sk_buff->tstamp_type
which was also suggested in the earlier discussion:
https://lore.kernel.org/bpf/b181acbe-caf8-502d-4b7b-7d96b9fc5d55@iogearbox.net/
The above will then make __sk_buff->tstamp and __sk_buff->tstamp_type
the same as its kernel skb->tstamp and skb->mono_delivery_time
counter part.
The internal kernel function bpf_skb_convert_dtime_type_read() is then
renamed to bpf_skb_convert_tstamp_type_read() and it can be simplified
with the BPF_SKB_DELIVERY_TIME_NONE gone. A BPF_ALU32_IMM(BPF_AND)
insn is also saved by using BPF_JMP32_IMM(BPF_JSET).
The bpf helper bpf_skb_set_delivery_time() is also renamed to
bpf_skb_set_tstamp(). The arg name is changed from dtime
to tstamp also. It only allows setting tstamp 0 for
BPF_SKB_TSTAMP_UNSPEC and it could be relaxed later
if there is use case to change mono delivery time to
non mono.
prog->delivery_time_access is also renamed to prog->tstamp_type_access.
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20220309090509.3712315-1-kafai@fb.com
Diffstat (limited to 'net/core')
-rw-r--r-- | net/core/filter.c | 88 |
1 files changed, 34 insertions, 54 deletions
diff --git a/net/core/filter.c b/net/core/filter.c index f914e4b13b18..03655f2074ae 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -7388,36 +7388,36 @@ static const struct bpf_func_proto bpf_sock_ops_reserve_hdr_opt_proto = { .arg3_type = ARG_ANYTHING, }; -BPF_CALL_3(bpf_skb_set_delivery_time, struct sk_buff *, skb, - u64, dtime, u32, dtime_type) +BPF_CALL_3(bpf_skb_set_tstamp, struct sk_buff *, skb, + u64, tstamp, u32, tstamp_type) { /* skb_clear_delivery_time() is done for inet protocol */ if (skb->protocol != htons(ETH_P_IP) && skb->protocol != htons(ETH_P_IPV6)) return -EOPNOTSUPP; - switch (dtime_type) { - case BPF_SKB_DELIVERY_TIME_MONO: - if (!dtime) + switch (tstamp_type) { + case BPF_SKB_TSTAMP_DELIVERY_MONO: + if (!tstamp) return -EINVAL; - skb->tstamp = dtime; + skb->tstamp = tstamp; skb->mono_delivery_time = 1; break; - case BPF_SKB_DELIVERY_TIME_NONE: - if (dtime) + case BPF_SKB_TSTAMP_UNSPEC: + if (tstamp) return -EINVAL; skb->tstamp = 0; skb->mono_delivery_time = 0; break; default: - return -EOPNOTSUPP; + return -EINVAL; } return 0; } -static const struct bpf_func_proto bpf_skb_set_delivery_time_proto = { - .func = bpf_skb_set_delivery_time, +static const struct bpf_func_proto bpf_skb_set_tstamp_proto = { + .func = bpf_skb_set_tstamp, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, @@ -7786,8 +7786,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_tcp_gen_syncookie_proto; case BPF_FUNC_sk_assign: return &bpf_sk_assign_proto; - case BPF_FUNC_skb_set_delivery_time: - return &bpf_skb_set_delivery_time_proto; + case BPF_FUNC_skb_set_tstamp: + return &bpf_skb_set_tstamp_proto; #endif default: return bpf_sk_base_func_proto(func_id); @@ -8127,9 +8127,9 @@ static bool bpf_skb_is_valid_access(int off, int size, enum bpf_access_type type return false; info->reg_type = PTR_TO_SOCK_COMMON_OR_NULL; break; - case offsetof(struct __sk_buff, delivery_time_type): + case offsetof(struct __sk_buff, tstamp_type): return false; - case offsetofend(struct __sk_buff, delivery_time_type) ... offsetof(struct __sk_buff, hwtstamp) - 1: + case offsetofend(struct __sk_buff, tstamp_type) ... offsetof(struct __sk_buff, hwtstamp) - 1: /* Explicitly prohibit access to padding in __sk_buff. */ return false; default: @@ -8484,14 +8484,14 @@ static bool tc_cls_act_is_valid_access(int off, int size, break; case bpf_ctx_range_till(struct __sk_buff, family, local_port): return false; - case offsetof(struct __sk_buff, delivery_time_type): + case offsetof(struct __sk_buff, tstamp_type): /* The convert_ctx_access() on reading and writing * __sk_buff->tstamp depends on whether the bpf prog - * has used __sk_buff->delivery_time_type or not. - * Thus, we need to set prog->delivery_time_access + * has used __sk_buff->tstamp_type or not. + * Thus, we need to set prog->tstamp_type_access * earlier during is_valid_access() here. */ - ((struct bpf_prog *)prog)->delivery_time_access = 1; + ((struct bpf_prog *)prog)->tstamp_type_access = 1; return size == sizeof(__u8); } @@ -8888,42 +8888,22 @@ static u32 flow_dissector_convert_ctx_access(enum bpf_access_type type, return insn - insn_buf; } -static struct bpf_insn *bpf_convert_dtime_type_read(const struct bpf_insn *si, - struct bpf_insn *insn) +static struct bpf_insn *bpf_convert_tstamp_type_read(const struct bpf_insn *si, + struct bpf_insn *insn) { __u8 value_reg = si->dst_reg; __u8 skb_reg = si->src_reg; + /* 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_ALU32_IMM(BPF_AND, tmp_reg, - SKB_MONO_DELIVERY_TIME_MASK); - *insn++ = BPF_JMP32_IMM(BPF_JEQ, tmp_reg, 0, 2); - /* value_reg = BPF_SKB_DELIVERY_TIME_MONO */ - *insn++ = BPF_MOV32_IMM(value_reg, BPF_SKB_DELIVERY_TIME_MONO); - *insn++ = BPF_JMP_A(IS_ENABLED(CONFIG_NET_CLS_ACT) ? 10 : 5); - - *insn++ = BPF_LDX_MEM(BPF_DW, tmp_reg, skb_reg, - offsetof(struct sk_buff, tstamp)); - *insn++ = BPF_JMP_IMM(BPF_JNE, tmp_reg, 0, 2); - /* value_reg = BPF_SKB_DELIVERY_TIME_NONE */ - *insn++ = BPF_MOV32_IMM(value_reg, BPF_SKB_DELIVERY_TIME_NONE); - *insn++ = BPF_JMP_A(IS_ENABLED(CONFIG_NET_CLS_ACT) ? 6 : 1); - -#ifdef CONFIG_NET_CLS_ACT - *insn++ = BPF_LDX_MEM(BPF_B, tmp_reg, skb_reg, PKT_VLAN_PRESENT_OFFSET); - *insn++ = BPF_ALU32_IMM(BPF_AND, tmp_reg, TC_AT_INGRESS_MASK); - *insn++ = BPF_JMP32_IMM(BPF_JEQ, tmp_reg, 0, 2); - /* At ingress, value_reg = 0 */ - *insn++ = BPF_MOV32_IMM(value_reg, 0); + *insn++ = BPF_JMP32_IMM(BPF_JSET, tmp_reg, + SKB_MONO_DELIVERY_TIME_MASK, 2); + *insn++ = BPF_MOV32_IMM(value_reg, BPF_SKB_TSTAMP_UNSPEC); *insn++ = BPF_JMP_A(1); -#endif - - /* value_reg = BPF_SKB_DELIVERYT_TIME_UNSPEC */ - *insn++ = BPF_MOV32_IMM(value_reg, BPF_SKB_DELIVERY_TIME_UNSPEC); + *insn++ = BPF_MOV32_IMM(value_reg, BPF_SKB_TSTAMP_DELIVERY_MONO); - /* 15 insns with CONFIG_NET_CLS_ACT */ return insn; } @@ -8956,11 +8936,11 @@ static struct bpf_insn *bpf_convert_tstamp_read(const struct bpf_prog *prog, __u8 skb_reg = si->src_reg; #ifdef CONFIG_NET_CLS_ACT - /* If the delivery_time_type is read, + /* If the tstamp_type is read, * the bpf prog is aware the tstamp could have delivery time. - * Thus, read skb->tstamp as is if delivery_time_access is true. + * Thus, read skb->tstamp as is if tstamp_type_access is true. */ - if (!prog->delivery_time_access) { + if (!prog->tstamp_type_access) { /* AX is needed because src_reg and dst_reg could be the same */ __u8 tmp_reg = BPF_REG_AX; @@ -8990,13 +8970,13 @@ static struct bpf_insn *bpf_convert_tstamp_write(const struct bpf_prog *prog, __u8 skb_reg = si->dst_reg; #ifdef CONFIG_NET_CLS_ACT - /* If the delivery_time_type is read, + /* If the tstamp_type is read, * the bpf prog is aware the tstamp could have delivery time. - * Thus, write skb->tstamp as is if delivery_time_access is true. + * Thus, write skb->tstamp as is if tstamp_type_access is true. * Otherwise, writing at ingress will have to clear the * mono_delivery_time bit also. */ - if (!prog->delivery_time_access) { + 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); @@ -9329,8 +9309,8 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, insn = bpf_convert_tstamp_read(prog, si, insn); break; - case offsetof(struct __sk_buff, delivery_time_type): - insn = bpf_convert_dtime_type_read(si, insn); + case offsetof(struct __sk_buff, tstamp_type): + insn = bpf_convert_tstamp_type_read(si, insn); break; case offsetof(struct __sk_buff, gso_segs): |