Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Daniel Borkmann says:

====================
pull-request: bpf-next 2018-12-11

The following pull-request contains BPF updates for your *net-next* tree.

It has three minor merge conflicts, resolutions:

1) tools/testing/selftests/bpf/test_verifier.c

 Take first chunk with alignment_prevented_execution.

2) net/core/filter.c

  [...]
  case bpf_ctx_range_ptr(struct __sk_buff, flow_keys):
  case bpf_ctx_range(struct __sk_buff, wire_len):
        return false;
  [...]

3) include/uapi/linux/bpf.h

  Take the second chunk for the two cases each.

The main changes are:

1) Add support for BPF line info via BTF and extend libbpf as well
   as bpftool's program dump to annotate output with BPF C code to
   facilitate debugging and introspection, from Martin.

2) Add support for BPF_ALU | BPF_ARSH | BPF_{K,X} in interpreter
   and all JIT backends, from Jiong.

3) Improve BPF test coverage on archs with no efficient unaligned
   access by adding an "any alignment" flag to the BPF program load
   to forcefully disable verifier alignment checks, from David.

4) Add a new bpf_prog_test_run_xattr() API to libbpf which allows for
   proper use of BPF_PROG_TEST_RUN with data_out, from Lorenz.

5) Extend tc BPF programs to use a new __sk_buff field called wire_len
   for more accurate accounting of packets going to wire, from Petar.

6) Improve bpftool to allow dumping the trace pipe from it and add
   several improvements in bash completion and map/prog dump,
   from Quentin.

7) Optimize arm64 BPF JIT to always emit movn/movk/movk sequence for
   kernel addresses and add a dedicated BPF JIT backend allocator,
   from Ard.

8) Add a BPF helper function for IR remotes to report mouse movements,
   from Sean.

9) Various cleanups in BPF prog dump e.g. to make UAPI bpf_prog_info
   member naming consistent with existing conventions, from Yonghong
   and Song.

10) Misc cleanups and improvements in allowing to pass interface name
    via cmdline for xdp1 BPF example, from Matteo.

11) Fix a potential segfault in BPF sample loader's kprobes handling,
    from Daniel T.

12) Fix SPDX license in libbpf's README.rst, from Andrey.
====================

Signed-off-by: David S. Miller <[email protected]>

Author: davem330

arch/arm64/include/asm/memory.h

@@ -62,8 +62,11 @@
 #define PAGE_OFFSET		(UL(0xffffffffffffffff) - \
 	(UL(1) << (VA_BITS - 1)) + 1)
 #define KIMAGE_VADDR		(MODULES_END)
+#define BPF_JIT_REGION_START	(VA_START + KASAN_SHADOW_SIZE)
+#define BPF_JIT_REGION_SIZE	(SZ_128M)
+#define BPF_JIT_REGION_END	(BPF_JIT_REGION_START + BPF_JIT_REGION_SIZE)
 #define MODULES_END		(MODULES_VADDR + MODULES_VSIZE)
-#define MODULES_VADDR		(VA_START + KASAN_SHADOW_SIZE)
+#define MODULES_VADDR		(BPF_JIT_REGION_END)
 #define MODULES_VSIZE		(SZ_128M)
 #define VMEMMAP_START		(PAGE_OFFSET - VMEMMAP_SIZE)
 #define PCI_IO_END		(VMEMMAP_START - SZ_2M)

arch/arm64/net/bpf_jit_comp.c

@@ -134,19 +134,18 @@ 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)
 {
 	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);
@@ -634,11 +633,7 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
 					    &func_addr, &func_addr_fixed);
 		if (ret < 0)
 			return ret;
-		if (func_addr_fixed)
-			/* We can use optimized emission here. */
-			emit_a64_mov_i64(tmp, func_addr, ctx);
-		else
-			emit_addr_mov_i64(tmp, func_addr, ctx);
+		emit_addr_mov_i64(tmp, func_addr, ctx);
 		emit(A64_BLR(tmp), ctx);
 		emit(A64_MOV(1, r0, A64_R(0)), ctx);
 		break;
@@ -948,3 +943,16 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 					   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);
+}

arch/mips/include/asm/uasm.h

@@ -157,6 +157,7 @@ Ip_u2u1s3(_slti);
 Ip_u2u1s3(_sltiu);
 Ip_u3u1u2(_sltu);
 Ip_u2u1u3(_sra);
+Ip_u3u2u1(_srav);
 Ip_u2u1u3(_srl);
 Ip_u3u2u1(_srlv);
 Ip_u3u1u2(_subu);

arch/mips/include/uapi/asm/inst.h

@@ -369,8 +369,9 @@ enum mm_32a_minor_op {
 	mm_ext_op = 0x02c,
 	mm_pool32axf_op = 0x03c,
 	mm_srl32_op = 0x040,
+	mm_srlv32_op = 0x050,
 	mm_sra_op = 0x080,
-	mm_srlv32_op = 0x090,
+	mm_srav_op = 0x090,
 	mm_rotr_op = 0x0c0,
 	mm_lwxs_op = 0x118,
 	mm_addu32_op = 0x150,

arch/mips/mm/uasm-micromips.c

@@ -104,6 +104,7 @@ static const struct insn insn_table_MM[insn_invalid] = {
 	[insn_sltiu]	= {M(mm_sltiu32_op, 0, 0, 0, 0, 0), RT | RS | SIMM},
 	[insn_sltu]	= {M(mm_pool32a_op, 0, 0, 0, 0, mm_sltu_op), RT | RS | RD},
 	[insn_sra]	= {M(mm_pool32a_op, 0, 0, 0, 0, mm_sra_op), RT | RS | RD},
+	[insn_srav]	= {M(mm_pool32a_op, 0, 0, 0, 0, mm_srav_op), RT | RS | RD},
 	[insn_srl]	= {M(mm_pool32a_op, 0, 0, 0, 0, mm_srl32_op), RT | RS | RD},
 	[insn_srlv]	= {M(mm_pool32a_op, 0, 0, 0, 0, mm_srlv32_op), RT | RS | RD},
 	[insn_rotr]	= {M(mm_pool32a_op, 0, 0, 0, 0, mm_rotr_op), RT | RS | RD},

arch/mips/mm/uasm-mips.c

@@ -171,6 +171,7 @@ static const struct insn insn_table[insn_invalid] = {
 	[insn_sltiu]	= {M(sltiu_op, 0, 0, 0, 0, 0), RS | RT | SIMM},
 	[insn_sltu]	= {M(spec_op, 0, 0, 0, 0, sltu_op), RS | RT | RD},
 	[insn_sra]	= {M(spec_op, 0, 0, 0, 0, sra_op),  RT | RD | RE},
+	[insn_srav]	= {M(spec_op, 0, 0, 0, 0, srav_op), RS | RT | RD},
 	[insn_srl]	= {M(spec_op, 0, 0, 0, 0, srl_op),  RT | RD | RE},
 	[insn_srlv]	= {M(spec_op, 0, 0, 0, 0, srlv_op),  RS | RT | RD},
 	[insn_subu]	= {M(spec_op, 0, 0, 0, 0, subu_op),	RS | RT | RD},

arch/mips/mm/uasm.c

@@ -61,10 +61,10 @@ enum opcode {
 	insn_mthc0, insn_mthi, insn_mtlo, insn_mul, insn_multu, insn_nor,
 	insn_or, insn_ori, insn_pref, insn_rfe, insn_rotr, insn_sb,
 	insn_sc, insn_scd, insn_sd, insn_sh, insn_sll, insn_sllv,
-	insn_slt, insn_slti, insn_sltiu, insn_sltu, insn_sra, insn_srl,
-	insn_srlv, insn_subu, insn_sw, insn_sync, insn_syscall, insn_tlbp,
-	insn_tlbr, insn_tlbwi, insn_tlbwr, insn_wait, insn_wsbh, insn_xor,
-	insn_xori, insn_yield,
+	insn_slt, insn_slti, insn_sltiu, insn_sltu, insn_sra, insn_srav,
+	insn_srl, insn_srlv, insn_subu, insn_sw, insn_sync, insn_syscall,
+	insn_tlbp, insn_tlbr, insn_tlbwi, insn_tlbwr, insn_wait, insn_wsbh,
+	insn_xor, insn_xori, insn_yield,
 	insn_invalid /* insn_invalid must be last */
 };
 
@@ -353,6 +353,7 @@ I_u2u1s3(_slti)
 I_u2u1s3(_sltiu)
 I_u3u1u2(_sltu)
 I_u2u1u3(_sra)
+I_u3u2u1(_srav)
 I_u2u1u3(_srl)
 I_u3u2u1(_srlv)
 I_u2u1u3(_rotr)

arch/mips/net/ebpf_jit.c

@@ -854,6 +854,7 @@ static int build_one_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
 	case BPF_ALU | BPF_MOD | BPF_X: /* ALU_REG */
 	case BPF_ALU | BPF_LSH | BPF_X: /* ALU_REG */
 	case BPF_ALU | BPF_RSH | BPF_X: /* ALU_REG */
+	case BPF_ALU | BPF_ARSH | BPF_X: /* ALU_REG */
 		src = ebpf_to_mips_reg(ctx, insn, src_reg_no_fp);
 		dst = ebpf_to_mips_reg(ctx, insn, dst_reg);
 		if (src < 0 || dst < 0)
@@ -913,6 +914,9 @@ static int build_one_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
 		case BPF_RSH:
 			emit_instr(ctx, srlv, dst, dst, src);
 			break;
+		case BPF_ARSH:
+			emit_instr(ctx, srav, dst, dst, src);
+			break;
 		default:
 			pr_err("ALU_REG NOT HANDLED\n");
 			return -EINVAL;

arch/powerpc/include/asm/ppc-opcode.h

@@ -342,6 +342,8 @@
 #define PPC_INST_SLW			0x7c000030
 #define PPC_INST_SLD			0x7c000036
 #define PPC_INST_SRW			0x7c000430
+#define PPC_INST_SRAW			0x7c000630
+#define PPC_INST_SRAWI			0x7c000670
 #define PPC_INST_SRD			0x7c000436
 #define PPC_INST_SRAD			0x7c000634
 #define PPC_INST_SRADI			0x7c000674

arch/powerpc/net/bpf_jit.h

@@ -152,6 +152,10 @@
 				     ___PPC_RS(a) | ___PPC_RB(s))
 #define PPC_SRW(d, a, s)	EMIT(PPC_INST_SRW | ___PPC_RA(d) |	      \
 				     ___PPC_RS(a) | ___PPC_RB(s))
+#define PPC_SRAW(d, a, s)	EMIT(PPC_INST_SRAW | ___PPC_RA(d) |	      \
+				     ___PPC_RS(a) | ___PPC_RB(s))
+#define PPC_SRAWI(d, a, i)	EMIT(PPC_INST_SRAWI | ___PPC_RA(d) |	      \
+				     ___PPC_RS(a) | __PPC_SH(i))
 #define PPC_SRD(d, a, s)	EMIT(PPC_INST_SRD | ___PPC_RA(d) |	      \
 				     ___PPC_RS(a) | ___PPC_RB(s))
 #define PPC_SRAD(d, a, s)	EMIT(PPC_INST_SRAD | ___PPC_RA(d) |	      \

arch/powerpc/net/bpf_jit_comp64.c

@@ -529,9 +529,15 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
 			if (imm != 0)
 				PPC_SRDI(dst_reg, dst_reg, imm);
 			break;
+		case BPF_ALU | BPF_ARSH | BPF_X: /* (s32) dst >>= src */
+			PPC_SRAW(dst_reg, dst_reg, src_reg);
+			goto bpf_alu32_trunc;
 		case BPF_ALU64 | BPF_ARSH | BPF_X: /* (s64) dst >>= src */
 			PPC_SRAD(dst_reg, dst_reg, src_reg);
 			break;
+		case BPF_ALU | BPF_ARSH | BPF_K: /* (s32) dst >>= imm */
+			PPC_SRAWI(dst_reg, dst_reg, imm);
+			goto bpf_alu32_trunc;
 		case BPF_ALU64 | BPF_ARSH | BPF_K: /* (s64) dst >>= imm */
 			if (imm != 0)
 				PPC_SRADI(dst_reg, dst_reg, imm);

arch/s390/net/bpf_jit_comp.c

@@ -821,10 +821,22 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i
 	/*
 	 * BPF_ARSH
 	 */
+	case BPF_ALU | BPF_ARSH | BPF_X: /* ((s32) dst) >>= src */
+		/* sra %dst,%dst,0(%src) */
+		EMIT4_DISP(0x8a000000, dst_reg, src_reg, 0);
+		EMIT_ZERO(dst_reg);
+		break;
 	case BPF_ALU64 | BPF_ARSH | BPF_X: /* ((s64) dst) >>= src */
 		/* srag %dst,%dst,0(%src) */
 		EMIT6_DISP_LH(0xeb000000, 0x000a, dst_reg, dst_reg, src_reg, 0);
 		break;
+	case BPF_ALU | BPF_ARSH | BPF_K: /* ((s32) dst >> imm */
+		if (imm == 0)
+			break;
+		/* sra %dst,imm(%r0) */
+		EMIT4_DISP(0x8a000000, dst_reg, REG_0, imm);
+		EMIT_ZERO(dst_reg);
+		break;
 	case BPF_ALU64 | BPF_ARSH | BPF_K: /* ((s64) dst) >>= imm */
 		if (imm == 0)
 			break;

arch/x86/net/bpf_jit_comp.c

@@ -1181,6 +1181,8 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	}
 
 	if (!image || !prog->is_func || extra_pass) {
+		if (image)
+			bpf_prog_fill_jited_linfo(prog, addrs);
 out_addrs:
 		kfree(addrs);
 		kfree(jit_data);

drivers/media/rc/bpf-lirc.c

@@ -59,6 +59,28 @@ static const struct bpf_func_proto rc_keydown_proto = {
 	.arg4_type = ARG_ANYTHING,
 };
 
+BPF_CALL_3(bpf_rc_pointer_rel, u32*, sample, s32, rel_x, s32, rel_y)
+{
+	struct ir_raw_event_ctrl *ctrl;
+
+	ctrl = container_of(sample, struct ir_raw_event_ctrl, bpf_sample);
+
+	input_report_rel(ctrl->dev->input_dev, REL_X, rel_x);
+	input_report_rel(ctrl->dev->input_dev, REL_Y, rel_y);
+	input_sync(ctrl->dev->input_dev);
+
+	return 0;
+}
+
+static const struct bpf_func_proto rc_pointer_rel_proto = {
+	.func	   = bpf_rc_pointer_rel,
+	.gpl_only  = true,
+	.ret_type  = RET_INTEGER,
+	.arg1_type = ARG_PTR_TO_CTX,
+	.arg2_type = ARG_ANYTHING,
+	.arg3_type = ARG_ANYTHING,
+};
+
 static const struct bpf_func_proto *
 lirc_mode2_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
@@ -67,6 +89,8 @@ lirc_mode2_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &rc_repeat_proto;
 	case BPF_FUNC_rc_keydown:
 		return &rc_keydown_proto;
+	case BPF_FUNC_rc_pointer_rel:
+		return &rc_pointer_rel_proto;
 	case BPF_FUNC_map_lookup_elem:
 		return &bpf_map_lookup_elem_proto;
 	case BPF_FUNC_map_update_elem:

drivers/net/ethernet/netronome/nfp/bpf/jit.c

@@ -2382,6 +2382,49 @@ static int neg_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 	return 0;
 }
 
+static int __ashr_imm(struct nfp_prog *nfp_prog, u8 dst, u8 shift_amt)
+{
+	/* Set signedness bit (MSB of result). */
+	emit_alu(nfp_prog, reg_none(), reg_a(dst), ALU_OP_OR, reg_imm(0));
+	emit_shf(nfp_prog, reg_both(dst), reg_none(), SHF_OP_ASHR, reg_b(dst),
+		 SHF_SC_R_SHF, shift_amt);
+	wrp_immed(nfp_prog, reg_both(dst + 1), 0);
+
+	return 0;
+}
+
+static int ashr_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	const struct bpf_insn *insn = &meta->insn;
+	u64 umin, umax;
+	u8 dst, src;
+
+	dst = insn->dst_reg * 2;
+	umin = meta->umin_src;
+	umax = meta->umax_src;
+	if (umin == umax)
+		return __ashr_imm(nfp_prog, dst, umin);
+
+	src = insn->src_reg * 2;
+	/* NOTE: the first insn will set both indirect shift amount (source A)
+	 * and signedness bit (MSB of result).
+	 */
+	emit_alu(nfp_prog, reg_none(), reg_a(src), ALU_OP_OR, reg_b(dst));
+	emit_shf_indir(nfp_prog, reg_both(dst), reg_none(), SHF_OP_ASHR,
+		       reg_b(dst), SHF_SC_R_SHF);
+	wrp_immed(nfp_prog, reg_both(dst + 1), 0);
+
+	return 0;
+}
+
+static int ashr_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	const struct bpf_insn *insn = &meta->insn;
+	u8 dst = insn->dst_reg * 2;
+
+	return __ashr_imm(nfp_prog, dst, insn->imm);
+}
+
 static int shl_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
 	const struct bpf_insn *insn = &meta->insn;
@@ -3286,6 +3329,8 @@ static const instr_cb_t instr_cb[256] = {
 	[BPF_ALU | BPF_DIV | BPF_K] =	div_imm,
 	[BPF_ALU | BPF_NEG] =		neg_reg,
 	[BPF_ALU | BPF_LSH | BPF_K] =	shl_imm,
+	[BPF_ALU | BPF_ARSH | BPF_X] =	ashr_reg,
+	[BPF_ALU | BPF_ARSH | BPF_K] =	ashr_imm,
 	[BPF_ALU | BPF_END | BPF_X] =	end_reg32,
 	[BPF_LD | BPF_IMM | BPF_DW] =	imm_ld8,
 	[BPF_LD | BPF_ABS | BPF_B] =	data_ld1,

include/linux/bpf.h

@@ -319,7 +319,28 @@ struct bpf_prog_aux {
 	struct bpf_prog_offload *offload;
 	struct btf *btf;
 	struct bpf_func_info *func_info;
+	/* bpf_line_info loaded from userspace.  linfo->insn_off
+	 * has the xlated insn offset.
+	 * Both the main and sub prog share the same linfo.
+	 * The subprog can access its first linfo by
+	 * using the linfo_idx.
+	 */
+	struct bpf_line_info *linfo;
+	/* jited_linfo is the jited addr of the linfo.  It has a
+	 * one to one mapping to linfo:
+	 * jited_linfo[i] is the jited addr for the linfo[i]->insn_off.
+	 * Both the main and sub prog share the same jited_linfo.
+	 * The subprog can access its first jited_linfo by
+	 * using the linfo_idx.
+	 */
+	void **jited_linfo;
 	u32 func_info_cnt;
+	u32 nr_linfo;
+	/* subprog can use linfo_idx to access its first linfo and
+	 * jited_linfo.
+	 * main prog always has linfo_idx == 0
+	 */
+	u32 linfo_idx;
 	union {
 		struct work_struct work;
 		struct rcu_head	rcu;

include/linux/bpf_verifier.h

@@ -203,6 +203,7 @@ static inline bool bpf_verifier_log_needed(const struct bpf_verifier_log *log)
 
 struct bpf_subprog_info {
 	u32 start; /* insn idx of function entry point */
+	u32 linfo_idx; /* The idx to the main_prog->aux->linfo */
 	u16 stack_depth; /* max. stack depth used by this function */
 };
 

include/linux/btf.h

@@ -46,6 +46,7 @@ void btf_type_seq_show(const struct btf *btf, u32 type_id, void *obj,
 		       struct seq_file *m);
 int btf_get_fd_by_id(u32 id);
 u32 btf_id(const struct btf *btf);
+bool btf_name_offset_valid(const struct btf *btf, u32 offset);
 
 #ifdef CONFIG_BPF_SYSCALL
 const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id);

include/linux/filter.h

@@ -725,6 +725,13 @@ void bpf_prog_free(struct bpf_prog *fp);
 
 bool bpf_opcode_in_insntable(u8 code);
 
+void bpf_prog_free_linfo(struct bpf_prog *prog);
+void bpf_prog_fill_jited_linfo(struct bpf_prog *prog,
+			       const u32 *insn_to_jit_off);
+int bpf_prog_alloc_jited_linfo(struct bpf_prog *prog);
+void bpf_prog_free_jited_linfo(struct bpf_prog *prog);
+void bpf_prog_free_unused_jited_linfo(struct bpf_prog *prog);
+
 struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags);
 struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size,
 				  gfp_t gfp_extra_flags);