bpf: introduce bpf_skb_vlan_push/pop() helpers
Allow eBPF programs attached to TC qdiscs call skb_vlan_push/pop via
helper functions. These functions may change skb->data/hlen which are
cached by some JITs to improve performance of ld_abs/ld_ind instructions.
Therefore JITs need to recognize bpf_skb_vlan_push/pop() calls,
re-compute header len and re-cache skb->data/hlen back into cpu registers.
Note, skb->data/hlen are not directly accessible from the programs,
so any changes to skb->data done either by these helpers or by other
TC actions are safe.
eBPF JIT supported by three architectures:
- arm64 JIT is using bpf_load_pointer() without caching, so it's ok as-is.
- x64 JIT re-caches skb->data/hlen unconditionally after vlan_push/pop calls
(experiments showed that conditional re-caching is slower).
- s390 JIT falls back to interpreter for now when bpf_skb_vlan_push() is present
in the program (re-caching is tbd).
These helpers allow more scalable handling of vlan from the programs.
Instead of creating thousands of vlan netdevs on top of eth0 and attaching
TC+ingress+bpf to all of them, the program can be attached to eth0 directly
and manipulate vlans as necessary.
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 579a8fd..6c335a8 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -315,6 +315,26 @@
*pprog = prog;
}
+
+static void emit_load_skb_data_hlen(u8 **pprog)
+{
+ u8 *prog = *pprog;
+ int cnt = 0;
+
+ /* r9d = skb->len - skb->data_len (headlen)
+ * r10 = skb->data
+ */
+ /* mov %r9d, off32(%rdi) */
+ EMIT3_off32(0x44, 0x8b, 0x8f, offsetof(struct sk_buff, len));
+
+ /* sub %r9d, off32(%rdi) */
+ EMIT3_off32(0x44, 0x2b, 0x8f, offsetof(struct sk_buff, data_len));
+
+ /* mov %r10, off32(%rdi) */
+ EMIT3_off32(0x4c, 0x8b, 0x97, offsetof(struct sk_buff, data));
+ *pprog = prog;
+}
+
static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
int oldproglen, struct jit_context *ctx)
{
@@ -329,36 +349,8 @@
emit_prologue(&prog);
- if (seen_ld_abs) {
- /* r9d : skb->len - skb->data_len (headlen)
- * r10 : skb->data
- */
- if (is_imm8(offsetof(struct sk_buff, len)))
- /* mov %r9d, off8(%rdi) */
- EMIT4(0x44, 0x8b, 0x4f,
- offsetof(struct sk_buff, len));
- else
- /* mov %r9d, off32(%rdi) */
- EMIT3_off32(0x44, 0x8b, 0x8f,
- offsetof(struct sk_buff, len));
-
- if (is_imm8(offsetof(struct sk_buff, data_len)))
- /* sub %r9d, off8(%rdi) */
- EMIT4(0x44, 0x2b, 0x4f,
- offsetof(struct sk_buff, data_len));
- else
- EMIT3_off32(0x44, 0x2b, 0x8f,
- offsetof(struct sk_buff, data_len));
-
- if (is_imm8(offsetof(struct sk_buff, data)))
- /* mov %r10, off8(%rdi) */
- EMIT4(0x4c, 0x8b, 0x57,
- offsetof(struct sk_buff, data));
- else
- /* mov %r10, off32(%rdi) */
- EMIT3_off32(0x4c, 0x8b, 0x97,
- offsetof(struct sk_buff, data));
- }
+ if (seen_ld_abs)
+ emit_load_skb_data_hlen(&prog);
for (i = 0; i < insn_cnt; i++, insn++) {
const s32 imm32 = insn->imm;
@@ -367,6 +359,7 @@
u8 b1 = 0, b2 = 0, b3 = 0;
s64 jmp_offset;
u8 jmp_cond;
+ bool reload_skb_data;
int ilen;
u8 *func;
@@ -818,12 +811,18 @@
func = (u8 *) __bpf_call_base + imm32;
jmp_offset = func - (image + addrs[i]);
if (seen_ld_abs) {
- EMIT2(0x41, 0x52); /* push %r10 */
- EMIT2(0x41, 0x51); /* push %r9 */
- /* need to adjust jmp offset, since
- * pop %r9, pop %r10 take 4 bytes after call insn
- */
- jmp_offset += 4;
+ reload_skb_data = bpf_helper_changes_skb_data(func);
+ if (reload_skb_data) {
+ EMIT1(0x57); /* push %rdi */
+ jmp_offset += 22; /* pop, mov, sub, mov */
+ } else {
+ EMIT2(0x41, 0x52); /* push %r10 */
+ EMIT2(0x41, 0x51); /* push %r9 */
+ /* need to adjust jmp offset, since
+ * pop %r9, pop %r10 take 4 bytes after call insn
+ */
+ jmp_offset += 4;
+ }
}
if (!imm32 || !is_simm32(jmp_offset)) {
pr_err("unsupported bpf func %d addr %p image %p\n",
@@ -832,8 +831,13 @@
}
EMIT1_off32(0xE8, jmp_offset);
if (seen_ld_abs) {
- EMIT2(0x41, 0x59); /* pop %r9 */
- EMIT2(0x41, 0x5A); /* pop %r10 */
+ if (reload_skb_data) {
+ EMIT1(0x5F); /* pop %rdi */
+ emit_load_skb_data_hlen(&prog);
+ } else {
+ EMIT2(0x41, 0x59); /* pop %r9 */
+ EMIT2(0x41, 0x5A); /* pop %r10 */
+ }
}
break;