Hi David,
I believe my recent set of RFC/patches [1] provided good visibility on where
I would like to take eBPF subsystem. These two trivial patches is a first step
in that direction:
patch 1 - mechanical split of eBPF interpreter out of filter.c
patch 2 - nominate myself as a maintainer for eBPF core pieces
In the foreseeable future eBPF patches will be going through net-next,
so put netdev as a primary mailing list
[1] git://git.kernel.org/pub/scm/linux/kernel/git/ast/bpf master
Alexei Starovoitov (2):
net: filter: split filter.c into two files
bpf: update MAINTAINERS entry
MAINTAINERS | 7 +
kernel/Makefile | 1 +
kernel/bpf/Makefile | 1 +
kernel/bpf/core.c | 536 +++++++++++++++++++++++++++++++++++++++++++++++++++
net/core/filter.c | 511 ------------------------------------------------
5 files changed, 545 insertions(+), 511 deletions(-)
create mode 100644 kernel/bpf/Makefile
create mode 100644 kernel/bpf/core.c
--
1.7.9.5
BPF is used in several kernel components. This split creates logical boundary
between generic eBPF core and the rest
kernel/bpf/core.c: eBPF interpreter
net/core/filter.c: classic->eBPF converter, classic verifiers, socket filters
This patch only moves functions.
Signed-off-by: Alexei Starovoitov <[email protected]>
---
kernel/Makefile | 1 +
kernel/bpf/Makefile | 1 +
kernel/bpf/core.c | 536 +++++++++++++++++++++++++++++++++++++++++++++++++++
net/core/filter.c | 511 ------------------------------------------------
4 files changed, 538 insertions(+), 511 deletions(-)
create mode 100644 kernel/bpf/Makefile
create mode 100644 kernel/bpf/core.c
diff --git a/kernel/Makefile b/kernel/Makefile
index f2a8b6246ce9..e7360b7c2c0e 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -87,6 +87,7 @@ obj-$(CONFIG_RING_BUFFER) += trace/
obj-$(CONFIG_TRACEPOINTS) += trace/
obj-$(CONFIG_IRQ_WORK) += irq_work.o
obj-$(CONFIG_CPU_PM) += cpu_pm.o
+obj-$(CONFIG_NET) += bpf/
obj-$(CONFIG_PERF_EVENTS) += events/
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
new file mode 100644
index 000000000000..6a71145e2769
--- /dev/null
+++ b/kernel/bpf/Makefile
@@ -0,0 +1 @@
+obj-y := core.o
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
new file mode 100644
index 000000000000..77a240a1ce11
--- /dev/null
+++ b/kernel/bpf/core.c
@@ -0,0 +1,536 @@
+/*
+ * Linux Socket Filter - Kernel level socket filtering
+ *
+ * Based on the design of the Berkeley Packet Filter. The new
+ * internal format has been designed by PLUMgrid:
+ *
+ * Copyright (c) 2011 - 2014 PLUMgrid, http://plumgrid.com
+ *
+ * Authors:
+ *
+ * Jay Schulist <[email protected]>
+ * Alexei Starovoitov <[email protected]>
+ * Daniel Borkmann <[email protected]>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Andi Kleen - Fix a few bad bugs and races.
+ * Kris Katterjohn - Added many additional checks in sk_chk_filter()
+ */
+#include <linux/filter.h>
+#include <linux/skbuff.h>
+#include <asm/unaligned.h>
+
+/* Registers */
+#define BPF_R0 regs[BPF_REG_0]
+#define BPF_R1 regs[BPF_REG_1]
+#define BPF_R2 regs[BPF_REG_2]
+#define BPF_R3 regs[BPF_REG_3]
+#define BPF_R4 regs[BPF_REG_4]
+#define BPF_R5 regs[BPF_REG_5]
+#define BPF_R6 regs[BPF_REG_6]
+#define BPF_R7 regs[BPF_REG_7]
+#define BPF_R8 regs[BPF_REG_8]
+#define BPF_R9 regs[BPF_REG_9]
+#define BPF_R10 regs[BPF_REG_10]
+
+/* Named registers */
+#define DST regs[insn->dst_reg]
+#define SRC regs[insn->src_reg]
+#define FP regs[BPF_REG_FP]
+#define ARG1 regs[BPF_REG_ARG1]
+#define CTX regs[BPF_REG_CTX]
+#define IMM insn->imm
+
+/* No hurry in this branch
+ *
+ * Exported for the bpf jit load helper.
+ */
+void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb, int k, unsigned int size)
+{
+ u8 *ptr = NULL;
+
+ if (k >= SKF_NET_OFF)
+ ptr = skb_network_header(skb) + k - SKF_NET_OFF;
+ else if (k >= SKF_LL_OFF)
+ ptr = skb_mac_header(skb) + k - SKF_LL_OFF;
+ if (ptr >= skb->head && ptr + size <= skb_tail_pointer(skb))
+ return ptr;
+
+ return NULL;
+}
+
+/* Base function for offset calculation. Needs to go into .text section,
+ * therefore keeping it non-static as well; will also be used by JITs
+ * anyway later on, so do not let the compiler omit it.
+ */
+noinline u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
+{
+ return 0;
+}
+
+/**
+ * __sk_run_filter - run a filter on a given context
+ * @ctx: buffer to run the filter on
+ * @insn: filter to apply
+ *
+ * Decode and apply filter instructions to the skb->data. Return length to
+ * keep, 0 for none. @ctx is the data we are operating on, @insn is the
+ * array of filter instructions.
+ */
+static unsigned int __sk_run_filter(void *ctx, const struct sock_filter_int *insn)
+{
+ u64 stack[MAX_BPF_STACK / sizeof(u64)];
+ u64 regs[MAX_BPF_REG], tmp;
+ static const void *jumptable[256] = {
+ [0 ... 255] = &&default_label,
+ /* Now overwrite non-defaults ... */
+ /* 32 bit ALU operations */
+ [BPF_ALU | BPF_ADD | BPF_X] = &&ALU_ADD_X,
+ [BPF_ALU | BPF_ADD | BPF_K] = &&ALU_ADD_K,
+ [BPF_ALU | BPF_SUB | BPF_X] = &&ALU_SUB_X,
+ [BPF_ALU | BPF_SUB | BPF_K] = &&ALU_SUB_K,
+ [BPF_ALU | BPF_AND | BPF_X] = &&ALU_AND_X,
+ [BPF_ALU | BPF_AND | BPF_K] = &&ALU_AND_K,
+ [BPF_ALU | BPF_OR | BPF_X] = &&ALU_OR_X,
+ [BPF_ALU | BPF_OR | BPF_K] = &&ALU_OR_K,
+ [BPF_ALU | BPF_LSH | BPF_X] = &&ALU_LSH_X,
+ [BPF_ALU | BPF_LSH | BPF_K] = &&ALU_LSH_K,
+ [BPF_ALU | BPF_RSH | BPF_X] = &&ALU_RSH_X,
+ [BPF_ALU | BPF_RSH | BPF_K] = &&ALU_RSH_K,
+ [BPF_ALU | BPF_XOR | BPF_X] = &&ALU_XOR_X,
+ [BPF_ALU | BPF_XOR | BPF_K] = &&ALU_XOR_K,
+ [BPF_ALU | BPF_MUL | BPF_X] = &&ALU_MUL_X,
+ [BPF_ALU | BPF_MUL | BPF_K] = &&ALU_MUL_K,
+ [BPF_ALU | BPF_MOV | BPF_X] = &&ALU_MOV_X,
+ [BPF_ALU | BPF_MOV | BPF_K] = &&ALU_MOV_K,
+ [BPF_ALU | BPF_DIV | BPF_X] = &&ALU_DIV_X,
+ [BPF_ALU | BPF_DIV | BPF_K] = &&ALU_DIV_K,
+ [BPF_ALU | BPF_MOD | BPF_X] = &&ALU_MOD_X,
+ [BPF_ALU | BPF_MOD | BPF_K] = &&ALU_MOD_K,
+ [BPF_ALU | BPF_NEG] = &&ALU_NEG,
+ [BPF_ALU | BPF_END | BPF_TO_BE] = &&ALU_END_TO_BE,
+ [BPF_ALU | BPF_END | BPF_TO_LE] = &&ALU_END_TO_LE,
+ /* 64 bit ALU operations */
+ [BPF_ALU64 | BPF_ADD | BPF_X] = &&ALU64_ADD_X,
+ [BPF_ALU64 | BPF_ADD | BPF_K] = &&ALU64_ADD_K,
+ [BPF_ALU64 | BPF_SUB | BPF_X] = &&ALU64_SUB_X,
+ [BPF_ALU64 | BPF_SUB | BPF_K] = &&ALU64_SUB_K,
+ [BPF_ALU64 | BPF_AND | BPF_X] = &&ALU64_AND_X,
+ [BPF_ALU64 | BPF_AND | BPF_K] = &&ALU64_AND_K,
+ [BPF_ALU64 | BPF_OR | BPF_X] = &&ALU64_OR_X,
+ [BPF_ALU64 | BPF_OR | BPF_K] = &&ALU64_OR_K,
+ [BPF_ALU64 | BPF_LSH | BPF_X] = &&ALU64_LSH_X,
+ [BPF_ALU64 | BPF_LSH | BPF_K] = &&ALU64_LSH_K,
+ [BPF_ALU64 | BPF_RSH | BPF_X] = &&ALU64_RSH_X,
+ [BPF_ALU64 | BPF_RSH | BPF_K] = &&ALU64_RSH_K,
+ [BPF_ALU64 | BPF_XOR | BPF_X] = &&ALU64_XOR_X,
+ [BPF_ALU64 | BPF_XOR | BPF_K] = &&ALU64_XOR_K,
+ [BPF_ALU64 | BPF_MUL | BPF_X] = &&ALU64_MUL_X,
+ [BPF_ALU64 | BPF_MUL | BPF_K] = &&ALU64_MUL_K,
+ [BPF_ALU64 | BPF_MOV | BPF_X] = &&ALU64_MOV_X,
+ [BPF_ALU64 | BPF_MOV | BPF_K] = &&ALU64_MOV_K,
+ [BPF_ALU64 | BPF_ARSH | BPF_X] = &&ALU64_ARSH_X,
+ [BPF_ALU64 | BPF_ARSH | BPF_K] = &&ALU64_ARSH_K,
+ [BPF_ALU64 | BPF_DIV | BPF_X] = &&ALU64_DIV_X,
+ [BPF_ALU64 | BPF_DIV | BPF_K] = &&ALU64_DIV_K,
+ [BPF_ALU64 | BPF_MOD | BPF_X] = &&ALU64_MOD_X,
+ [BPF_ALU64 | BPF_MOD | BPF_K] = &&ALU64_MOD_K,
+ [BPF_ALU64 | BPF_NEG] = &&ALU64_NEG,
+ /* Call instruction */
+ [BPF_JMP | BPF_CALL] = &&JMP_CALL,
+ /* Jumps */
+ [BPF_JMP | BPF_JA] = &&JMP_JA,
+ [BPF_JMP | BPF_JEQ | BPF_X] = &&JMP_JEQ_X,
+ [BPF_JMP | BPF_JEQ | BPF_K] = &&JMP_JEQ_K,
+ [BPF_JMP | BPF_JNE | BPF_X] = &&JMP_JNE_X,
+ [BPF_JMP | BPF_JNE | BPF_K] = &&JMP_JNE_K,
+ [BPF_JMP | BPF_JGT | BPF_X] = &&JMP_JGT_X,
+ [BPF_JMP | BPF_JGT | BPF_K] = &&JMP_JGT_K,
+ [BPF_JMP | BPF_JGE | BPF_X] = &&JMP_JGE_X,
+ [BPF_JMP | BPF_JGE | BPF_K] = &&JMP_JGE_K,
+ [BPF_JMP | BPF_JSGT | BPF_X] = &&JMP_JSGT_X,
+ [BPF_JMP | BPF_JSGT | BPF_K] = &&JMP_JSGT_K,
+ [BPF_JMP | BPF_JSGE | BPF_X] = &&JMP_JSGE_X,
+ [BPF_JMP | BPF_JSGE | BPF_K] = &&JMP_JSGE_K,
+ [BPF_JMP | BPF_JSET | BPF_X] = &&JMP_JSET_X,
+ [BPF_JMP | BPF_JSET | BPF_K] = &&JMP_JSET_K,
+ /* Program return */
+ [BPF_JMP | BPF_EXIT] = &&JMP_EXIT,
+ /* Store instructions */
+ [BPF_STX | BPF_MEM | BPF_B] = &&STX_MEM_B,
+ [BPF_STX | BPF_MEM | BPF_H] = &&STX_MEM_H,
+ [BPF_STX | BPF_MEM | BPF_W] = &&STX_MEM_W,
+ [BPF_STX | BPF_MEM | BPF_DW] = &&STX_MEM_DW,
+ [BPF_STX | BPF_XADD | BPF_W] = &&STX_XADD_W,
+ [BPF_STX | BPF_XADD | BPF_DW] = &&STX_XADD_DW,
+ [BPF_ST | BPF_MEM | BPF_B] = &&ST_MEM_B,
+ [BPF_ST | BPF_MEM | BPF_H] = &&ST_MEM_H,
+ [BPF_ST | BPF_MEM | BPF_W] = &&ST_MEM_W,
+ [BPF_ST | BPF_MEM | BPF_DW] = &&ST_MEM_DW,
+ /* Load instructions */
+ [BPF_LDX | BPF_MEM | BPF_B] = &&LDX_MEM_B,
+ [BPF_LDX | BPF_MEM | BPF_H] = &&LDX_MEM_H,
+ [BPF_LDX | BPF_MEM | BPF_W] = &&LDX_MEM_W,
+ [BPF_LDX | BPF_MEM | BPF_DW] = &&LDX_MEM_DW,
+ [BPF_LD | BPF_ABS | BPF_W] = &&LD_ABS_W,
+ [BPF_LD | BPF_ABS | BPF_H] = &&LD_ABS_H,
+ [BPF_LD | BPF_ABS | BPF_B] = &&LD_ABS_B,
+ [BPF_LD | BPF_IND | BPF_W] = &&LD_IND_W,
+ [BPF_LD | BPF_IND | BPF_H] = &&LD_IND_H,
+ [BPF_LD | BPF_IND | BPF_B] = &&LD_IND_B,
+ };
+ void *ptr;
+ int off;
+
+#define CONT ({ insn++; goto select_insn; })
+#define CONT_JMP ({ insn++; goto select_insn; })
+
+ FP = (u64) (unsigned long) &stack[ARRAY_SIZE(stack)];
+ ARG1 = (u64) (unsigned long) ctx;
+
+ /* Registers used in classic BPF programs need to be reset first. */
+ regs[BPF_REG_A] = 0;
+ regs[BPF_REG_X] = 0;
+
+select_insn:
+ goto *jumptable[insn->code];
+
+ /* ALU */
+#define ALU(OPCODE, OP) \
+ ALU64_##OPCODE##_X: \
+ DST = DST OP SRC; \
+ CONT; \
+ ALU_##OPCODE##_X: \
+ DST = (u32) DST OP (u32) SRC; \
+ CONT; \
+ ALU64_##OPCODE##_K: \
+ DST = DST OP IMM; \
+ CONT; \
+ ALU_##OPCODE##_K: \
+ DST = (u32) DST OP (u32) IMM; \
+ CONT;
+
+ ALU(ADD, +)
+ ALU(SUB, -)
+ ALU(AND, &)
+ ALU(OR, |)
+ ALU(LSH, <<)
+ ALU(RSH, >>)
+ ALU(XOR, ^)
+ ALU(MUL, *)
+#undef ALU
+ ALU_NEG:
+ DST = (u32) -DST;
+ CONT;
+ ALU64_NEG:
+ DST = -DST;
+ CONT;
+ ALU_MOV_X:
+ DST = (u32) SRC;
+ CONT;
+ ALU_MOV_K:
+ DST = (u32) IMM;
+ CONT;
+ ALU64_MOV_X:
+ DST = SRC;
+ CONT;
+ ALU64_MOV_K:
+ DST = IMM;
+ CONT;
+ ALU64_ARSH_X:
+ (*(s64 *) &DST) >>= SRC;
+ CONT;
+ ALU64_ARSH_K:
+ (*(s64 *) &DST) >>= IMM;
+ CONT;
+ ALU64_MOD_X:
+ if (unlikely(SRC == 0))
+ return 0;
+ tmp = DST;
+ DST = do_div(tmp, SRC);
+ CONT;
+ ALU_MOD_X:
+ if (unlikely(SRC == 0))
+ return 0;
+ tmp = (u32) DST;
+ DST = do_div(tmp, (u32) SRC);
+ CONT;
+ ALU64_MOD_K:
+ tmp = DST;
+ DST = do_div(tmp, IMM);
+ CONT;
+ ALU_MOD_K:
+ tmp = (u32) DST;
+ DST = do_div(tmp, (u32) IMM);
+ CONT;
+ ALU64_DIV_X:
+ if (unlikely(SRC == 0))
+ return 0;
+ do_div(DST, SRC);
+ CONT;
+ ALU_DIV_X:
+ if (unlikely(SRC == 0))
+ return 0;
+ tmp = (u32) DST;
+ do_div(tmp, (u32) SRC);
+ DST = (u32) tmp;
+ CONT;
+ ALU64_DIV_K:
+ do_div(DST, IMM);
+ CONT;
+ ALU_DIV_K:
+ tmp = (u32) DST;
+ do_div(tmp, (u32) IMM);
+ DST = (u32) tmp;
+ CONT;
+ ALU_END_TO_BE:
+ switch (IMM) {
+ case 16:
+ DST = (__force u16) cpu_to_be16(DST);
+ break;
+ case 32:
+ DST = (__force u32) cpu_to_be32(DST);
+ break;
+ case 64:
+ DST = (__force u64) cpu_to_be64(DST);
+ break;
+ }
+ CONT;
+ ALU_END_TO_LE:
+ switch (IMM) {
+ case 16:
+ DST = (__force u16) cpu_to_le16(DST);
+ break;
+ case 32:
+ DST = (__force u32) cpu_to_le32(DST);
+ break;
+ case 64:
+ DST = (__force u64) cpu_to_le64(DST);
+ break;
+ }
+ CONT;
+
+ /* CALL */
+ JMP_CALL:
+ /* Function call scratches BPF_R1-BPF_R5 registers,
+ * preserves BPF_R6-BPF_R9, and stores return value
+ * into BPF_R0.
+ */
+ BPF_R0 = (__bpf_call_base + insn->imm)(BPF_R1, BPF_R2, BPF_R3,
+ BPF_R4, BPF_R5);
+ 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_JGE_X:
+ if (DST >= SRC) {
+ insn += insn->off;
+ CONT_JMP;
+ }
+ CONT;
+ JMP_JGE_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_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_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;
+
+ /* STX and ST and LDX*/
+#define LDST(SIZEOP, SIZE) \
+ STX_MEM_##SIZEOP: \
+ *(SIZE *)(unsigned long) (DST + insn->off) = SRC; \
+ CONT; \
+ ST_MEM_##SIZEOP: \
+ *(SIZE *)(unsigned long) (DST + insn->off) = IMM; \
+ CONT; \
+ LDX_MEM_##SIZEOP: \
+ DST = *(SIZE *)(unsigned long) (SRC + insn->off); \
+ CONT;
+
+ LDST(B, u8)
+ LDST(H, u16)
+ LDST(W, u32)
+ LDST(DW, u64)
+#undef LDST
+ STX_XADD_W: /* lock xadd *(u32 *)(dst_reg + off16) += src_reg */
+ atomic_add((u32) SRC, (atomic_t *)(unsigned long)
+ (DST + insn->off));
+ CONT;
+ STX_XADD_DW: /* lock xadd *(u64 *)(dst_reg + off16) += src_reg */
+ atomic64_add((u64) SRC, (atomic64_t *)(unsigned long)
+ (DST + insn->off));
+ CONT;
+ LD_ABS_W: /* BPF_R0 = ntohl(*(u32 *) (skb->data + imm32)) */
+ off = IMM;
+load_word:
+ /* BPF_LD + BPD_ABS and BPF_LD + BPF_IND insns are
+ * only appearing in the programs where ctx ==
+ * skb. All programs keep 'ctx' in regs[BPF_REG_CTX]
+ * == BPF_R6, sk_convert_filter() saves it in BPF_R6,
+ * internal BPF verifier will check that BPF_R6 ==
+ * ctx.
+ *
+ * BPF_ABS and BPF_IND are wrappers of function calls,
+ * so they scratch BPF_R1-BPF_R5 registers, preserve
+ * BPF_R6-BPF_R9, and store return value into BPF_R0.
+ *
+ * Implicit input:
+ * ctx == skb == BPF_R6 == CTX
+ *
+ * Explicit input:
+ * SRC == any register
+ * IMM == 32-bit immediate
+ *
+ * Output:
+ * BPF_R0 - 8/16/32-bit skb data converted to cpu endianness
+ */
+
+ ptr = bpf_load_pointer((struct sk_buff *) (unsigned long) CTX, off, 4, &tmp);
+ if (likely(ptr != NULL)) {
+ BPF_R0 = get_unaligned_be32(ptr);
+ CONT;
+ }
+
+ return 0;
+ LD_ABS_H: /* BPF_R0 = ntohs(*(u16 *) (skb->data + imm32)) */
+ off = IMM;
+load_half:
+ ptr = bpf_load_pointer((struct sk_buff *) (unsigned long) CTX, off, 2, &tmp);
+ if (likely(ptr != NULL)) {
+ BPF_R0 = get_unaligned_be16(ptr);
+ CONT;
+ }
+
+ return 0;
+ LD_ABS_B: /* BPF_R0 = *(u8 *) (skb->data + imm32) */
+ off = IMM;
+load_byte:
+ ptr = bpf_load_pointer((struct sk_buff *) (unsigned long) CTX, off, 1, &tmp);
+ if (likely(ptr != NULL)) {
+ BPF_R0 = *(u8 *)ptr;
+ CONT;
+ }
+
+ return 0;
+ LD_IND_W: /* BPF_R0 = ntohl(*(u32 *) (skb->data + src_reg + imm32)) */
+ off = IMM + SRC;
+ goto load_word;
+ LD_IND_H: /* BPF_R0 = ntohs(*(u16 *) (skb->data + src_reg + imm32)) */
+ off = IMM + SRC;
+ goto load_half;
+ LD_IND_B: /* BPF_R0 = *(u8 *) (skb->data + src_reg + imm32) */
+ off = IMM + SRC;
+ goto load_byte;
+
+ default_label:
+ /* If we ever reach this, we have a bug somewhere. */
+ WARN_RATELIMIT(1, "unknown opcode %02x\n", insn->code);
+ return 0;
+}
+
+void __weak bpf_int_jit_compile(struct sk_filter *prog)
+{
+}
+
+/**
+ * sk_filter_select_runtime - select execution runtime for BPF program
+ * @fp: sk_filter populated with internal BPF program
+ *
+ * try to JIT internal BPF program, if JIT is not available select interpreter
+ * BPF program will be executed via SK_RUN_FILTER() macro
+ */
+void sk_filter_select_runtime(struct sk_filter *fp)
+{
+ fp->bpf_func = (void *) __sk_run_filter;
+
+ /* Probe if internal BPF can be JITed */
+ bpf_int_jit_compile(fp);
+}
+EXPORT_SYMBOL_GPL(sk_filter_select_runtime);
+
+/* free internal BPF program */
+void sk_filter_free(struct sk_filter *fp)
+{
+ bpf_jit_free(fp);
+}
+EXPORT_SYMBOL_GPL(sk_filter_free);
diff --git a/net/core/filter.c b/net/core/filter.c
index b90ae7fb3b89..1d0e9492e4fa 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -45,45 +45,6 @@
#include <linux/seccomp.h>
#include <linux/if_vlan.h>
-/* Registers */
-#define BPF_R0 regs[BPF_REG_0]
-#define BPF_R1 regs[BPF_REG_1]
-#define BPF_R2 regs[BPF_REG_2]
-#define BPF_R3 regs[BPF_REG_3]
-#define BPF_R4 regs[BPF_REG_4]
-#define BPF_R5 regs[BPF_REG_5]
-#define BPF_R6 regs[BPF_REG_6]
-#define BPF_R7 regs[BPF_REG_7]
-#define BPF_R8 regs[BPF_REG_8]
-#define BPF_R9 regs[BPF_REG_9]
-#define BPF_R10 regs[BPF_REG_10]
-
-/* Named registers */
-#define DST regs[insn->dst_reg]
-#define SRC regs[insn->src_reg]
-#define FP regs[BPF_REG_FP]
-#define ARG1 regs[BPF_REG_ARG1]
-#define CTX regs[BPF_REG_CTX]
-#define IMM insn->imm
-
-/* No hurry in this branch
- *
- * Exported for the bpf jit load helper.
- */
-void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb, int k, unsigned int size)
-{
- u8 *ptr = NULL;
-
- if (k >= SKF_NET_OFF)
- ptr = skb_network_header(skb) + k - SKF_NET_OFF;
- else if (k >= SKF_LL_OFF)
- ptr = skb_mac_header(skb) + k - SKF_LL_OFF;
- if (ptr >= skb->head && ptr + size <= skb_tail_pointer(skb))
- return ptr;
-
- return NULL;
-}
-
/**
* sk_filter - run a packet through a socket filter
* @sk: sock associated with &sk_buff
@@ -126,451 +87,6 @@ int sk_filter(struct sock *sk, struct sk_buff *skb)
}
EXPORT_SYMBOL(sk_filter);
-/* Base function for offset calculation. Needs to go into .text section,
- * therefore keeping it non-static as well; will also be used by JITs
- * anyway later on, so do not let the compiler omit it.
- */
-noinline u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
-{
- return 0;
-}
-
-/**
- * __sk_run_filter - run a filter on a given context
- * @ctx: buffer to run the filter on
- * @insn: filter to apply
- *
- * Decode and apply filter instructions to the skb->data. Return length to
- * keep, 0 for none. @ctx is the data we are operating on, @insn is the
- * array of filter instructions.
- */
-static unsigned int __sk_run_filter(void *ctx, const struct sock_filter_int *insn)
-{
- u64 stack[MAX_BPF_STACK / sizeof(u64)];
- u64 regs[MAX_BPF_REG], tmp;
- static const void *jumptable[256] = {
- [0 ... 255] = &&default_label,
- /* Now overwrite non-defaults ... */
- /* 32 bit ALU operations */
- [BPF_ALU | BPF_ADD | BPF_X] = &&ALU_ADD_X,
- [BPF_ALU | BPF_ADD | BPF_K] = &&ALU_ADD_K,
- [BPF_ALU | BPF_SUB | BPF_X] = &&ALU_SUB_X,
- [BPF_ALU | BPF_SUB | BPF_K] = &&ALU_SUB_K,
- [BPF_ALU | BPF_AND | BPF_X] = &&ALU_AND_X,
- [BPF_ALU | BPF_AND | BPF_K] = &&ALU_AND_K,
- [BPF_ALU | BPF_OR | BPF_X] = &&ALU_OR_X,
- [BPF_ALU | BPF_OR | BPF_K] = &&ALU_OR_K,
- [BPF_ALU | BPF_LSH | BPF_X] = &&ALU_LSH_X,
- [BPF_ALU | BPF_LSH | BPF_K] = &&ALU_LSH_K,
- [BPF_ALU | BPF_RSH | BPF_X] = &&ALU_RSH_X,
- [BPF_ALU | BPF_RSH | BPF_K] = &&ALU_RSH_K,
- [BPF_ALU | BPF_XOR | BPF_X] = &&ALU_XOR_X,
- [BPF_ALU | BPF_XOR | BPF_K] = &&ALU_XOR_K,
- [BPF_ALU | BPF_MUL | BPF_X] = &&ALU_MUL_X,
- [BPF_ALU | BPF_MUL | BPF_K] = &&ALU_MUL_K,
- [BPF_ALU | BPF_MOV | BPF_X] = &&ALU_MOV_X,
- [BPF_ALU | BPF_MOV | BPF_K] = &&ALU_MOV_K,
- [BPF_ALU | BPF_DIV | BPF_X] = &&ALU_DIV_X,
- [BPF_ALU | BPF_DIV | BPF_K] = &&ALU_DIV_K,
- [BPF_ALU | BPF_MOD | BPF_X] = &&ALU_MOD_X,
- [BPF_ALU | BPF_MOD | BPF_K] = &&ALU_MOD_K,
- [BPF_ALU | BPF_NEG] = &&ALU_NEG,
- [BPF_ALU | BPF_END | BPF_TO_BE] = &&ALU_END_TO_BE,
- [BPF_ALU | BPF_END | BPF_TO_LE] = &&ALU_END_TO_LE,
- /* 64 bit ALU operations */
- [BPF_ALU64 | BPF_ADD | BPF_X] = &&ALU64_ADD_X,
- [BPF_ALU64 | BPF_ADD | BPF_K] = &&ALU64_ADD_K,
- [BPF_ALU64 | BPF_SUB | BPF_X] = &&ALU64_SUB_X,
- [BPF_ALU64 | BPF_SUB | BPF_K] = &&ALU64_SUB_K,
- [BPF_ALU64 | BPF_AND | BPF_X] = &&ALU64_AND_X,
- [BPF_ALU64 | BPF_AND | BPF_K] = &&ALU64_AND_K,
- [BPF_ALU64 | BPF_OR | BPF_X] = &&ALU64_OR_X,
- [BPF_ALU64 | BPF_OR | BPF_K] = &&ALU64_OR_K,
- [BPF_ALU64 | BPF_LSH | BPF_X] = &&ALU64_LSH_X,
- [BPF_ALU64 | BPF_LSH | BPF_K] = &&ALU64_LSH_K,
- [BPF_ALU64 | BPF_RSH | BPF_X] = &&ALU64_RSH_X,
- [BPF_ALU64 | BPF_RSH | BPF_K] = &&ALU64_RSH_K,
- [BPF_ALU64 | BPF_XOR | BPF_X] = &&ALU64_XOR_X,
- [BPF_ALU64 | BPF_XOR | BPF_K] = &&ALU64_XOR_K,
- [BPF_ALU64 | BPF_MUL | BPF_X] = &&ALU64_MUL_X,
- [BPF_ALU64 | BPF_MUL | BPF_K] = &&ALU64_MUL_K,
- [BPF_ALU64 | BPF_MOV | BPF_X] = &&ALU64_MOV_X,
- [BPF_ALU64 | BPF_MOV | BPF_K] = &&ALU64_MOV_K,
- [BPF_ALU64 | BPF_ARSH | BPF_X] = &&ALU64_ARSH_X,
- [BPF_ALU64 | BPF_ARSH | BPF_K] = &&ALU64_ARSH_K,
- [BPF_ALU64 | BPF_DIV | BPF_X] = &&ALU64_DIV_X,
- [BPF_ALU64 | BPF_DIV | BPF_K] = &&ALU64_DIV_K,
- [BPF_ALU64 | BPF_MOD | BPF_X] = &&ALU64_MOD_X,
- [BPF_ALU64 | BPF_MOD | BPF_K] = &&ALU64_MOD_K,
- [BPF_ALU64 | BPF_NEG] = &&ALU64_NEG,
- /* Call instruction */
- [BPF_JMP | BPF_CALL] = &&JMP_CALL,
- /* Jumps */
- [BPF_JMP | BPF_JA] = &&JMP_JA,
- [BPF_JMP | BPF_JEQ | BPF_X] = &&JMP_JEQ_X,
- [BPF_JMP | BPF_JEQ | BPF_K] = &&JMP_JEQ_K,
- [BPF_JMP | BPF_JNE | BPF_X] = &&JMP_JNE_X,
- [BPF_JMP | BPF_JNE | BPF_K] = &&JMP_JNE_K,
- [BPF_JMP | BPF_JGT | BPF_X] = &&JMP_JGT_X,
- [BPF_JMP | BPF_JGT | BPF_K] = &&JMP_JGT_K,
- [BPF_JMP | BPF_JGE | BPF_X] = &&JMP_JGE_X,
- [BPF_JMP | BPF_JGE | BPF_K] = &&JMP_JGE_K,
- [BPF_JMP | BPF_JSGT | BPF_X] = &&JMP_JSGT_X,
- [BPF_JMP | BPF_JSGT | BPF_K] = &&JMP_JSGT_K,
- [BPF_JMP | BPF_JSGE | BPF_X] = &&JMP_JSGE_X,
- [BPF_JMP | BPF_JSGE | BPF_K] = &&JMP_JSGE_K,
- [BPF_JMP | BPF_JSET | BPF_X] = &&JMP_JSET_X,
- [BPF_JMP | BPF_JSET | BPF_K] = &&JMP_JSET_K,
- /* Program return */
- [BPF_JMP | BPF_EXIT] = &&JMP_EXIT,
- /* Store instructions */
- [BPF_STX | BPF_MEM | BPF_B] = &&STX_MEM_B,
- [BPF_STX | BPF_MEM | BPF_H] = &&STX_MEM_H,
- [BPF_STX | BPF_MEM | BPF_W] = &&STX_MEM_W,
- [BPF_STX | BPF_MEM | BPF_DW] = &&STX_MEM_DW,
- [BPF_STX | BPF_XADD | BPF_W] = &&STX_XADD_W,
- [BPF_STX | BPF_XADD | BPF_DW] = &&STX_XADD_DW,
- [BPF_ST | BPF_MEM | BPF_B] = &&ST_MEM_B,
- [BPF_ST | BPF_MEM | BPF_H] = &&ST_MEM_H,
- [BPF_ST | BPF_MEM | BPF_W] = &&ST_MEM_W,
- [BPF_ST | BPF_MEM | BPF_DW] = &&ST_MEM_DW,
- /* Load instructions */
- [BPF_LDX | BPF_MEM | BPF_B] = &&LDX_MEM_B,
- [BPF_LDX | BPF_MEM | BPF_H] = &&LDX_MEM_H,
- [BPF_LDX | BPF_MEM | BPF_W] = &&LDX_MEM_W,
- [BPF_LDX | BPF_MEM | BPF_DW] = &&LDX_MEM_DW,
- [BPF_LD | BPF_ABS | BPF_W] = &&LD_ABS_W,
- [BPF_LD | BPF_ABS | BPF_H] = &&LD_ABS_H,
- [BPF_LD | BPF_ABS | BPF_B] = &&LD_ABS_B,
- [BPF_LD | BPF_IND | BPF_W] = &&LD_IND_W,
- [BPF_LD | BPF_IND | BPF_H] = &&LD_IND_H,
- [BPF_LD | BPF_IND | BPF_B] = &&LD_IND_B,
- };
- void *ptr;
- int off;
-
-#define CONT ({ insn++; goto select_insn; })
-#define CONT_JMP ({ insn++; goto select_insn; })
-
- FP = (u64) (unsigned long) &stack[ARRAY_SIZE(stack)];
- ARG1 = (u64) (unsigned long) ctx;
-
- /* Registers used in classic BPF programs need to be reset first. */
- regs[BPF_REG_A] = 0;
- regs[BPF_REG_X] = 0;
-
-select_insn:
- goto *jumptable[insn->code];
-
- /* ALU */
-#define ALU(OPCODE, OP) \
- ALU64_##OPCODE##_X: \
- DST = DST OP SRC; \
- CONT; \
- ALU_##OPCODE##_X: \
- DST = (u32) DST OP (u32) SRC; \
- CONT; \
- ALU64_##OPCODE##_K: \
- DST = DST OP IMM; \
- CONT; \
- ALU_##OPCODE##_K: \
- DST = (u32) DST OP (u32) IMM; \
- CONT;
-
- ALU(ADD, +)
- ALU(SUB, -)
- ALU(AND, &)
- ALU(OR, |)
- ALU(LSH, <<)
- ALU(RSH, >>)
- ALU(XOR, ^)
- ALU(MUL, *)
-#undef ALU
- ALU_NEG:
- DST = (u32) -DST;
- CONT;
- ALU64_NEG:
- DST = -DST;
- CONT;
- ALU_MOV_X:
- DST = (u32) SRC;
- CONT;
- ALU_MOV_K:
- DST = (u32) IMM;
- CONT;
- ALU64_MOV_X:
- DST = SRC;
- CONT;
- ALU64_MOV_K:
- DST = IMM;
- CONT;
- ALU64_ARSH_X:
- (*(s64 *) &DST) >>= SRC;
- CONT;
- ALU64_ARSH_K:
- (*(s64 *) &DST) >>= IMM;
- CONT;
- ALU64_MOD_X:
- if (unlikely(SRC == 0))
- return 0;
- tmp = DST;
- DST = do_div(tmp, SRC);
- CONT;
- ALU_MOD_X:
- if (unlikely(SRC == 0))
- return 0;
- tmp = (u32) DST;
- DST = do_div(tmp, (u32) SRC);
- CONT;
- ALU64_MOD_K:
- tmp = DST;
- DST = do_div(tmp, IMM);
- CONT;
- ALU_MOD_K:
- tmp = (u32) DST;
- DST = do_div(tmp, (u32) IMM);
- CONT;
- ALU64_DIV_X:
- if (unlikely(SRC == 0))
- return 0;
- do_div(DST, SRC);
- CONT;
- ALU_DIV_X:
- if (unlikely(SRC == 0))
- return 0;
- tmp = (u32) DST;
- do_div(tmp, (u32) SRC);
- DST = (u32) tmp;
- CONT;
- ALU64_DIV_K:
- do_div(DST, IMM);
- CONT;
- ALU_DIV_K:
- tmp = (u32) DST;
- do_div(tmp, (u32) IMM);
- DST = (u32) tmp;
- CONT;
- ALU_END_TO_BE:
- switch (IMM) {
- case 16:
- DST = (__force u16) cpu_to_be16(DST);
- break;
- case 32:
- DST = (__force u32) cpu_to_be32(DST);
- break;
- case 64:
- DST = (__force u64) cpu_to_be64(DST);
- break;
- }
- CONT;
- ALU_END_TO_LE:
- switch (IMM) {
- case 16:
- DST = (__force u16) cpu_to_le16(DST);
- break;
- case 32:
- DST = (__force u32) cpu_to_le32(DST);
- break;
- case 64:
- DST = (__force u64) cpu_to_le64(DST);
- break;
- }
- CONT;
-
- /* CALL */
- JMP_CALL:
- /* Function call scratches BPF_R1-BPF_R5 registers,
- * preserves BPF_R6-BPF_R9, and stores return value
- * into BPF_R0.
- */
- BPF_R0 = (__bpf_call_base + insn->imm)(BPF_R1, BPF_R2, BPF_R3,
- BPF_R4, BPF_R5);
- 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_JGE_X:
- if (DST >= SRC) {
- insn += insn->off;
- CONT_JMP;
- }
- CONT;
- JMP_JGE_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_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_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;
-
- /* STX and ST and LDX*/
-#define LDST(SIZEOP, SIZE) \
- STX_MEM_##SIZEOP: \
- *(SIZE *)(unsigned long) (DST + insn->off) = SRC; \
- CONT; \
- ST_MEM_##SIZEOP: \
- *(SIZE *)(unsigned long) (DST + insn->off) = IMM; \
- CONT; \
- LDX_MEM_##SIZEOP: \
- DST = *(SIZE *)(unsigned long) (SRC + insn->off); \
- CONT;
-
- LDST(B, u8)
- LDST(H, u16)
- LDST(W, u32)
- LDST(DW, u64)
-#undef LDST
- STX_XADD_W: /* lock xadd *(u32 *)(dst_reg + off16) += src_reg */
- atomic_add((u32) SRC, (atomic_t *)(unsigned long)
- (DST + insn->off));
- CONT;
- STX_XADD_DW: /* lock xadd *(u64 *)(dst_reg + off16) += src_reg */
- atomic64_add((u64) SRC, (atomic64_t *)(unsigned long)
- (DST + insn->off));
- CONT;
- LD_ABS_W: /* BPF_R0 = ntohl(*(u32 *) (skb->data + imm32)) */
- off = IMM;
-load_word:
- /* BPF_LD + BPD_ABS and BPF_LD + BPF_IND insns are
- * only appearing in the programs where ctx ==
- * skb. All programs keep 'ctx' in regs[BPF_REG_CTX]
- * == BPF_R6, sk_convert_filter() saves it in BPF_R6,
- * internal BPF verifier will check that BPF_R6 ==
- * ctx.
- *
- * BPF_ABS and BPF_IND are wrappers of function calls,
- * so they scratch BPF_R1-BPF_R5 registers, preserve
- * BPF_R6-BPF_R9, and store return value into BPF_R0.
- *
- * Implicit input:
- * ctx == skb == BPF_R6 == CTX
- *
- * Explicit input:
- * SRC == any register
- * IMM == 32-bit immediate
- *
- * Output:
- * BPF_R0 - 8/16/32-bit skb data converted to cpu endianness
- */
-
- ptr = bpf_load_pointer((struct sk_buff *) (unsigned long) CTX, off, 4, &tmp);
- if (likely(ptr != NULL)) {
- BPF_R0 = get_unaligned_be32(ptr);
- CONT;
- }
-
- return 0;
- LD_ABS_H: /* BPF_R0 = ntohs(*(u16 *) (skb->data + imm32)) */
- off = IMM;
-load_half:
- ptr = bpf_load_pointer((struct sk_buff *) (unsigned long) CTX, off, 2, &tmp);
- if (likely(ptr != NULL)) {
- BPF_R0 = get_unaligned_be16(ptr);
- CONT;
- }
-
- return 0;
- LD_ABS_B: /* BPF_R0 = *(u8 *) (skb->data + imm32) */
- off = IMM;
-load_byte:
- ptr = bpf_load_pointer((struct sk_buff *) (unsigned long) CTX, off, 1, &tmp);
- if (likely(ptr != NULL)) {
- BPF_R0 = *(u8 *)ptr;
- CONT;
- }
-
- return 0;
- LD_IND_W: /* BPF_R0 = ntohl(*(u32 *) (skb->data + src_reg + imm32)) */
- off = IMM + SRC;
- goto load_word;
- LD_IND_H: /* BPF_R0 = ntohs(*(u16 *) (skb->data + src_reg + imm32)) */
- off = IMM + SRC;
- goto load_half;
- LD_IND_B: /* BPF_R0 = *(u8 *) (skb->data + src_reg + imm32) */
- off = IMM + SRC;
- goto load_byte;
-
- default_label:
- /* If we ever reach this, we have a bug somewhere. */
- WARN_RATELIMIT(1, "unknown opcode %02x\n", insn->code);
- return 0;
-}
-
/* Helper to find the offset of pkt_type in sk_buff structure. We want
* to make sure its still a 3bit field starting at a byte boundary;
* taken from arch/x86/net/bpf_jit_comp.c.
@@ -1455,33 +971,6 @@ out_err:
return ERR_PTR(err);
}
-void __weak bpf_int_jit_compile(struct sk_filter *prog)
-{
-}
-
-/**
- * sk_filter_select_runtime - select execution runtime for BPF program
- * @fp: sk_filter populated with internal BPF program
- *
- * try to JIT internal BPF program, if JIT is not available select interpreter
- * BPF program will be executed via SK_RUN_FILTER() macro
- */
-void sk_filter_select_runtime(struct sk_filter *fp)
-{
- fp->bpf_func = (void *) __sk_run_filter;
-
- /* Probe if internal BPF can be JITed */
- bpf_int_jit_compile(fp);
-}
-EXPORT_SYMBOL_GPL(sk_filter_select_runtime);
-
-/* free internal BPF program */
-void sk_filter_free(struct sk_filter *fp)
-{
- bpf_jit_free(fp);
-}
-EXPORT_SYMBOL_GPL(sk_filter_free);
-
static struct sk_filter *__sk_prepare_filter(struct sk_filter *fp,
struct sock *sk)
{
--
1.7.9.5
Signed-off-by: Alexei Starovoitov <[email protected]>
---
MAINTAINERS | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/MAINTAINERS b/MAINTAINERS
index 78215a5dea28..62bf15f6954f 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1912,6 +1912,13 @@ S: Supported
F: drivers/net/bonding/
F: include/uapi/linux/if_bonding.h
+BPF (Safe dynamic programs and tools)
+M: Alexei Starovoitov <[email protected]>
+L: [email protected]
+L: [email protected]
+S: Supported
+F: kernel/bpf/
+
BROADCOM B44 10/100 ETHERNET DRIVER
M: Gary Zambrano <[email protected]>
L: [email protected]
--
1.7.9.5
On 07/23/2014 11:31 AM, Alexei Starovoitov wrote:
> BPF is used in several kernel components. This split creates logical boundary
> between generic eBPF core and the rest
>
> kernel/bpf/core.c: eBPF interpreter
>
> net/core/filter.c: classic->eBPF converter, classic verifiers, socket filters
>
> This patch only moves functions.
If we are moving the code also its good to do cleanup.
Run checkpatch.pl on this...
--
Regards,
Varka Bhadram.
From: Varka Bhadram
> On 07/23/2014 11:31 AM, Alexei Starovoitov wrote:
> > BPF is used in several kernel components. This split creates logical boundary
> > between generic eBPF core and the rest
> >
> > kernel/bpf/core.c: eBPF interpreter
> >
> > net/core/filter.c: classic->eBPF converter, classic verifiers, socket filters
> >
> > This patch only moves functions.
>
> If we are moving the code also its good to do cleanup.
Except you need to do it as a separate patch.
David
> Run checkpatch.pl on this...
>
>
> --
> Regards,
> Varka Bhadram.
>
> --
> To unsubscribe from this list: send the line "unsubscribe netdev" in
> the body of a message to [email protected]
> More majordomo info at http://vger.kernel.org/majordomo-info.html
On 07/23/2014 08:11 AM, Varka Bhadram wrote:
> On 07/23/2014 11:31 AM, Alexei Starovoitov wrote:
>> BPF is used in several kernel components. This split creates logical boundary
>> between generic eBPF core and the rest
>>
>> kernel/bpf/core.c: eBPF interpreter
>>
>> net/core/filter.c: classic->eBPF converter, classic verifiers, socket filters
>>
>> This patch only moves functions.
>
> If we are moving the code also its good to do cleanup.
>
> Run checkpatch.pl on this...
Not sure what you understand as a cleanup, but there's nothing
wrong with it and most things reported are either intentional or
false positives as you might have seen already. The only thing
one could do later on perhaps is to rename related functions to
have consistently a 'bpf' prefix instead of 'sk' since they
won't be under net/ anymore.
On Wed, Jul 23, 2014 at 10:54:04AM +0200, Daniel Borkmann wrote:
> On 07/23/2014 08:11 AM, Varka Bhadram wrote:
> >On 07/23/2014 11:31 AM, Alexei Starovoitov wrote:
> >>BPF is used in several kernel components. This split creates logical boundary
> >>between generic eBPF core and the rest
> >>
> >>kernel/bpf/core.c: eBPF interpreter
> >>
> >>net/core/filter.c: classic->eBPF converter, classic verifiers, socket filters
> >>
> >>This patch only moves functions.
> >
> >If we are moving the code also its good to do cleanup.
> >
> >Run checkpatch.pl on this...
>
> Not sure what you understand as a cleanup, but there's nothing
> wrong with it and most things reported are either intentional or
> false positives as you might have seen already. The only thing
+1. interpreter code is quite polished already.
Few lines are longer than 80 char, but wrapping will look ugly.
The rest are false positives, since checkpatch is struggling to
understand jump-threaded code.
> one could do later on perhaps is to rename related functions to
> have consistently a 'bpf' prefix instead of 'sk' since they
> won't be under net/ anymore.
yes. it's on my todo list. The sk_* functions and 'struct sk_filter'
look out of place in kernel/bpf/*
The first renaming patch of sock_filter_int->bpf_insn I've sent as rfc:
http://patchwork.ozlabs.org/patch/371332/
'struct sk_filter' I'm thinking to rename as 'struct bpf_prog'
Speaking of kernel/bpf/* comment style...
I would prefer to keep networking comments to save lines.
From: Alexei Starovoitov <[email protected]>
Date: Tue, 22 Jul 2014 23:01:57 -0700
> I believe my recent set of RFC/patches [1] provided good visibility on where
> I would like to take eBPF subsystem. These two trivial patches is a first step
> in that direction:
> patch 1 - mechanical split of eBPF interpreter out of filter.c
> patch 2 - nominate myself as a maintainer for eBPF core pieces
> In the foreseeable future eBPF patches will be going through net-next,
> so put netdev as a primary mailing list
>
> [1] git://git.kernel.org/pub/scm/linux/kernel/git/ast/bpf master
Series applied to net-next.
On Tue, 22 Jul 2014 23:01:58 -0700, Alexei Starovoitov said:
> BPF is used in several kernel components. This split creates logical boundary
> between generic eBPF core and the rest
>
> kernel/bpf/core.c: eBPF interpreter
>
> net/core/filter.c: classic->eBPF converter, classic verifiers, socket filters
>
> This patch only moves functions.
>
> Signed-off-by: Alexei Starovoitov <[email protected]>
> ---
> kernel/Makefile | 1 +
> kernel/bpf/Makefile | 1 +
> kernel/bpf/core.c | 536 +++++++++++++++++++++++++++++++++++++++++++++++++
++
> net/core/filter.c | 511 ------------------------------------------------
> 4 files changed, 538 insertions(+), 511 deletions(-)
> create mode 100644 kernel/bpf/Makefile
> create mode 100644 kernel/bpf/core.c
>
> diff --git a/kernel/Makefile b/kernel/Makefile
> index f2a8b6246ce9..e7360b7c2c0e 100644
> --- a/kernel/Makefile
> +++ b/kernel/Makefile
> @@ -87,6 +87,7 @@ obj-$(CONFIG_RING_BUFFER) += trace/
> obj-$(CONFIG_TRACEPOINTS) += trace/
> obj-$(CONFIG_IRQ_WORK) += irq_work.o
> obj-$(CONFIG_CPU_PM) += cpu_pm.o
> +obj-$(CONFIG_NET) += bpf/
I was expecting to see CONFIG_NETFILTER here. Is CONFIG_NET intentional?
On Thu, Jul 24, 2014 at 4:45 PM, <[email protected]> wrote:
> On Tue, 22 Jul 2014 23:01:58 -0700, Alexei Starovoitov said:
>> BPF is used in several kernel components. This split creates logical boundary
>> between generic eBPF core and the rest
>>
>> kernel/bpf/core.c: eBPF interpreter
>>
>> net/core/filter.c: classic->eBPF converter, classic verifiers, socket filters
>>
>> This patch only moves functions.
>>
>> Signed-off-by: Alexei Starovoitov <[email protected]>
>> ---
>> kernel/Makefile | 1 +
>> kernel/bpf/Makefile | 1 +
>> kernel/bpf/core.c | 536 +++++++++++++++++++++++++++++++++++++++++++++++++
> ++
>> net/core/filter.c | 511 ------------------------------------------------
>> 4 files changed, 538 insertions(+), 511 deletions(-)
>> create mode 100644 kernel/bpf/Makefile
>> create mode 100644 kernel/bpf/core.c
>>
>> diff --git a/kernel/Makefile b/kernel/Makefile
>> index f2a8b6246ce9..e7360b7c2c0e 100644
>> --- a/kernel/Makefile
>> +++ b/kernel/Makefile
>> @@ -87,6 +87,7 @@ obj-$(CONFIG_RING_BUFFER) += trace/
>> obj-$(CONFIG_TRACEPOINTS) += trace/
>> obj-$(CONFIG_IRQ_WORK) += irq_work.o
>> obj-$(CONFIG_CPU_PM) += cpu_pm.o
>> +obj-$(CONFIG_NET) += bpf/
>
> I was expecting to see CONFIG_NETFILTER here. Is CONFIG_NET intentional?
yes. it is config_net for now, until eBPF is completely separate from net.
Then it will gain its own config_bpf, so it can be used in net-less setups
or disabled in net-full setups by folks who care about last byte of .text size.
Future will tell.
On Thu, 24 Jul 2014 16:58:23 -0700, Alexei Starovoitov said:
> On Thu, Jul 24, 2014 at 4:45 PM, <[email protected]> wrote:
> > On Tue, 22 Jul 2014 23:01:58 -0700, Alexei Starovoitov said:
> >> +obj-$(CONFIG_NET) += bpf/
> >
> > I was expecting to see CONFIG_NETFILTER here. Is CONFIG_NET intentional?
>
> yes. it is config_net for now, until eBPF is completely separate from net.
> Then it will gain its own config_bpf, so it can be used in net-less setups
> or disabled in net-full setups by folks who care about last byte of .text size.
OH, OK. That works for me. :)