1 files changed, 33 insertions, 16 deletions

diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index a6fdaea07c63..1542df00b23c 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -134,10 +134,9 @@ static inline void emit_a64_mov_i64(const int reg, const u64 val,
 }
 
 /*
- * This is an unoptimized 64 immediate emission used for BPF to BPF call
- * addresses. It will always do a full 64 bit decomposition as otherwise
- * more complexity in the last extra pass is required since we previously
- * reserved 4 instructions for the address.
+ * Kernel addresses in the vmalloc space use at most 48 bits, and the
+ * remaining bits are guaranteed to be 0x1. So we can compose the address
+ * with a fixed length movn/movk/movk sequence.
  */
 static inline void emit_addr_mov_i64(const int reg, const u64 val,
 				     struct jit_ctx *ctx)
@@ -145,8 +144,8 @@ static inline void emit_addr_mov_i64(const int reg, const u64 val,
 	u64 tmp = val;
 	int shift = 0;
 
-	emit(A64_MOVZ(1, reg, tmp & 0xffff, shift), ctx);
-	for (;shift < 48;) {
+	emit(A64_MOVN(1, reg, ~tmp & 0xffff, shift), ctx);
+	while (shift < 32) {
 		tmp >>= 16;
 		shift += 16;
 		emit(A64_MOVK(1, reg, tmp & 0xffff, shift), ctx);
@@ -351,7 +350,8 @@ static void build_epilogue(struct jit_ctx *ctx)
  * >0 - successfully JITed a 16-byte eBPF instruction.
  * <0 - failed to JIT.
  */
-static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
+static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
+		      bool extra_pass)
 {
 	const u8 code = insn->code;
 	const u8 dst = bpf2a64[insn->dst_reg];
@@ -625,12 +625,15 @@ emit_cond_jmp:
 	case BPF_JMP | BPF_CALL:
 	{
 		const u8 r0 = bpf2a64[BPF_REG_0];
-		const u64 func = (u64)__bpf_call_base + imm;
+		bool func_addr_fixed;
+		u64 func_addr;
+		int ret;
 
-		if (ctx->prog->is_func)
-			emit_addr_mov_i64(tmp, func, ctx);
-		else
-			emit_a64_mov_i64(tmp, func, ctx);
+		ret = bpf_jit_get_func_addr(ctx->prog, insn, extra_pass,
+					    &func_addr, &func_addr_fixed);
+		if (ret < 0)
+			return ret;
+		emit_addr_mov_i64(tmp, func_addr, ctx);
 		emit(A64_BLR(tmp), ctx);
 		emit(A64_MOV(1, r0, A64_R(0)), ctx);
 		break;
@@ -753,7 +756,7 @@ emit_cond_jmp:
 	return 0;
 }
 
-static int build_body(struct jit_ctx *ctx)
+static int build_body(struct jit_ctx *ctx, bool extra_pass)
 {
 	const struct bpf_prog *prog = ctx->prog;
 	int i;
@@ -762,7 +765,7 @@ static int build_body(struct jit_ctx *ctx)
 		const struct bpf_insn *insn = &prog->insnsi[i];
 		int ret;
 
-		ret = build_insn(insn, ctx);
+		ret = build_insn(insn, ctx, extra_pass);
 		if (ret > 0) {
 			i++;
 			if (ctx->image == NULL)
@@ -858,7 +861,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	/* 1. Initial fake pass to compute ctx->idx. */
 
 	/* Fake pass to fill in ctx->offset. */
-	if (build_body(&ctx)) {
+	if (build_body(&ctx, extra_pass)) {
 		prog = orig_prog;
 		goto out_off;
 	}
@@ -888,7 +891,7 @@ skip_init_ctx:
 
 	build_prologue(&ctx, was_classic);
 
-	if (build_body(&ctx)) {
+	if (build_body(&ctx, extra_pass)) {
 		bpf_jit_binary_free(header);
 		prog = orig_prog;
 		goto out_off;
@@ -929,6 +932,7 @@ skip_init_ctx:
 	prog->jited_len = image_size;
 
 	if (!prog->is_func || extra_pass) {
+		bpf_prog_fill_jited_linfo(prog, ctx.offset);
 out_off:
 		kfree(ctx.offset);
 		kfree(jit_data);
@@ -940,3 +944,16 @@ out:
 					   tmp : orig_prog);
 	return prog;
 }
+
+void *bpf_jit_alloc_exec(unsigned long size)
+{
+	return __vmalloc_node_range(size, PAGE_SIZE, BPF_JIT_REGION_START,
+				    BPF_JIT_REGION_END, GFP_KERNEL,
+				    PAGE_KERNEL_EXEC, 0, NUMA_NO_NODE,
+				    __builtin_return_address(0));
+}
+
+void bpf_jit_free_exec(void *addr)
+{
+	return vfree(addr);
+}