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

Alexei Starovoitov says:

====================
pull-request: bpf-next 2021-11-01

We've added 181 non-merge commits during the last 28 day(s) which contain
a total of 280 files changed, 11791 insertions(+), 5879 deletions(-).

The main changes are:

1) Fix bpf verifier propagation of 64-bit bounds, from Alexei.

2) Parallelize bpf test_progs, from Yucong and Andrii.

3) Deprecate various libbpf apis including af_xdp, from Andrii, Hengqi, Magnus.

4) Improve bpf selftests on s390, from Ilya.

5) bloomfilter bpf map type, from Joanne.

6) Big improvements to JIT tests especially on Mips, from Johan.

7) Support kernel module function calls from bpf, from Kumar.

8) Support typeless and weak ksym in light skeleton, from Kumar.

9) Disallow unprivileged bpf by default, from Pawan.

10) BTF_KIND_DECL_TAG support, from Yonghong.

11) Various bpftool cleanups, from Quentin.

* https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (181 commits)
  libbpf: Deprecate AF_XDP support
  kbuild: Unify options for BTF generation for vmlinux and modules
  selftests/bpf: Add a testcase for 64-bit bounds propagation issue.
  bpf: Fix propagation of signed bounds from 64-bit min/max into 32-bit.
  bpf: Fix propagation of bounds from 64-bit min/max into 32-bit and var_off.
  selftests/bpf: Fix also no-alu32 strobemeta selftest
  bpf: Add missing map_delete_elem method to bloom filter map
  selftests/bpf: Add bloom map success test for userspace calls
  bpf: Add alignment padding for "map_extra" + consolidate holes
  bpf: Bloom filter map naming fixups
  selftests/bpf: Add test cases for struct_ops prog
  bpf: Add dummy BPF STRUCT_OPS for test purpose
  bpf: Factor out helpers for ctx access checking
  bpf: Factor out a helper to prepare trampoline for struct_ops prog
  selftests, bpf: Fix broken riscv build
  riscv, libbpf: Add RISC-V (RV64) support to bpf_tracing.h
  tools, build: Add RISC-V to HOSTARCH parsing
  riscv, bpf: Increase the maximum number of iterations
  selftests, bpf: Add one test for sockmap with strparser
  selftests, bpf: Fix test_txmsg_ingress_parser error
  ...
====================

Link: https://lore.kernel.org/r/20211102013123.9005-1-alexei.starovoitov@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

3 files changed, 164 insertions, 43 deletions

diff --git a/arch/riscv/net/bpf_jit.h b/arch/riscv/net/bpf_jit.h
index 75c1e9996867..f42d9cd3b64d 100644
--- a/arch/riscv/net/bpf_jit.h
+++ b/arch/riscv/net/bpf_jit.h
@@ -71,6 +71,7 @@ struct rv_jit_context {
 	int ninsns;
 	int epilogue_offset;
 	int *offset;		/* BPF to RV */
+	int nexentries;
 	unsigned long flags;
 	int stack_size;
 };
diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c
index 3af4131c22c7..2ca345c7b0bf 100644
--- a/arch/riscv/net/bpf_jit_comp64.c
+++ b/arch/riscv/net/bpf_jit_comp64.c
@@ -5,6 +5,7 @@
  *
  */
 
+#include <linux/bitfield.h>
 #include <linux/bpf.h>
 #include <linux/filter.h>
 #include "bpf_jit.h"
@@ -27,6 +28,21 @@ static const int regmap[] = {
 	[BPF_REG_AX] =	RV_REG_T0,
 };
 
+static const int pt_regmap[] = {
+	[RV_REG_A0] = offsetof(struct pt_regs, a0),
+	[RV_REG_A1] = offsetof(struct pt_regs, a1),
+	[RV_REG_A2] = offsetof(struct pt_regs, a2),
+	[RV_REG_A3] = offsetof(struct pt_regs, a3),
+	[RV_REG_A4] = offsetof(struct pt_regs, a4),
+	[RV_REG_A5] = offsetof(struct pt_regs, a5),
+	[RV_REG_S1] = offsetof(struct pt_regs, s1),
+	[RV_REG_S2] = offsetof(struct pt_regs, s2),
+	[RV_REG_S3] = offsetof(struct pt_regs, s3),
+	[RV_REG_S4] = offsetof(struct pt_regs, s4),
+	[RV_REG_S5] = offsetof(struct pt_regs, s5),
+	[RV_REG_T0] = offsetof(struct pt_regs, t0),
+};
+
 enum {
 	RV_CTX_F_SEEN_TAIL_CALL =	0,
 	RV_CTX_F_SEEN_CALL =		RV_REG_RA,
@@ -440,6 +456,69 @@ static int emit_call(bool fixed, u64 addr, struct rv_jit_context *ctx)
 	return 0;
 }
 
+#define BPF_FIXUP_OFFSET_MASK   GENMASK(26, 0)
+#define BPF_FIXUP_REG_MASK      GENMASK(31, 27)
+
+int rv_bpf_fixup_exception(const struct exception_table_entry *ex,
+				struct pt_regs *regs)
+{
+	off_t offset = FIELD_GET(BPF_FIXUP_OFFSET_MASK, ex->fixup);
+	int regs_offset = FIELD_GET(BPF_FIXUP_REG_MASK, ex->fixup);
+
+	*(unsigned long *)((void *)regs + pt_regmap[regs_offset]) = 0;
+	regs->epc = (unsigned long)&ex->fixup - offset;
+
+	return 1;
+}
+
+/* For accesses to BTF pointers, add an entry to the exception table */
+static int add_exception_handler(const struct bpf_insn *insn,
+				 struct rv_jit_context *ctx,
+				 int dst_reg, int insn_len)
+{
+	struct exception_table_entry *ex;
+	unsigned long pc;
+	off_t offset;
+
+	if (!ctx->insns || !ctx->prog->aux->extable || BPF_MODE(insn->code) != BPF_PROBE_MEM)
+		return 0;
+
+	if (WARN_ON_ONCE(ctx->nexentries >= ctx->prog->aux->num_exentries))
+		return -EINVAL;
+
+	if (WARN_ON_ONCE(insn_len > ctx->ninsns))
+		return -EINVAL;
+
+	if (WARN_ON_ONCE(!rvc_enabled() && insn_len == 1))
+		return -EINVAL;
+
+	ex = &ctx->prog->aux->extable[ctx->nexentries];
+	pc = (unsigned long)&ctx->insns[ctx->ninsns - insn_len];
+
+	offset = pc - (long)&ex->insn;
+	if (WARN_ON_ONCE(offset >= 0 || offset < INT_MIN))
+		return -ERANGE;
+	ex->insn = pc;
+
+	/*
+	 * Since the extable follows the program, the fixup offset is always
+	 * negative and limited to BPF_JIT_REGION_SIZE. Store a positive value
+	 * to keep things simple, and put the destination register in the upper
+	 * bits. We don't need to worry about buildtime or runtime sort
+	 * modifying the upper bits because the table is already sorted, and
+	 * isn't part of the main exception table.
+	 */
+	offset = (long)&ex->fixup - (pc + insn_len * sizeof(u16));
+	if (!FIELD_FIT(BPF_FIXUP_OFFSET_MASK, offset))
+		return -ERANGE;
+
+	ex->fixup = FIELD_PREP(BPF_FIXUP_OFFSET_MASK, offset) |
+		FIELD_PREP(BPF_FIXUP_REG_MASK, dst_reg);
+
+	ctx->nexentries++;
+	return 0;
+}
+
 int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 		      bool extra_pass)
 {
@@ -893,52 +972,86 @@ out_be:
 
 	/* LDX: dst = *(size *)(src + off) */
 	case BPF_LDX | BPF_MEM | BPF_B:
-		if (is_12b_int(off)) {
-			emit(rv_lbu(rd, off, rs), ctx);
+	case BPF_LDX | BPF_MEM | BPF_H:
+	case BPF_LDX | BPF_MEM | BPF_W:
+	case BPF_LDX | BPF_MEM | BPF_DW:
+	case BPF_LDX | BPF_PROBE_MEM | BPF_B:
+	case BPF_LDX | BPF_PROBE_MEM | BPF_H:
+	case BPF_LDX | BPF_PROBE_MEM | BPF_W:
+	case BPF_LDX | BPF_PROBE_MEM | BPF_DW:
+	{
+		int insn_len, insns_start;
+
+		switch (BPF_SIZE(code)) {
+		case BPF_B:
+			if (is_12b_int(off)) {
+				insns_start = ctx->ninsns;
+				emit(rv_lbu(rd, off, rs), ctx);
+				insn_len = ctx->ninsns - insns_start;
+				break;
+			}
+
+			emit_imm(RV_REG_T1, off, ctx);
+			emit_add(RV_REG_T1, RV_REG_T1, rs, ctx);
+			insns_start = ctx->ninsns;
+			emit(rv_lbu(rd, 0, RV_REG_T1), ctx);
+			insn_len = ctx->ninsns - insns_start;
+			if (insn_is_zext(&insn[1]))
+				return 1;
 			break;
-		}
+		case BPF_H:
+			if (is_12b_int(off)) {
+				insns_start = ctx->ninsns;
+				emit(rv_lhu(rd, off, rs), ctx);
+				insn_len = ctx->ninsns - insns_start;
+				break;
+			}
 
-		emit_imm(RV_REG_T1, off, ctx);
-		emit_add(RV_REG_T1, RV_REG_T1, rs, ctx);
-		emit(rv_lbu(rd, 0, RV_REG_T1), ctx);
-		if (insn_is_zext(&insn[1]))
-			return 1;
-		break;
-	case BPF_LDX | BPF_MEM | BPF_H:
-		if (is_12b_int(off)) {
-			emit(rv_lhu(rd, off, rs), ctx);
+			emit_imm(RV_REG_T1, off, ctx);
+			emit_add(RV_REG_T1, RV_REG_T1, rs, ctx);
+			insns_start = ctx->ninsns;
+			emit(rv_lhu(rd, 0, RV_REG_T1), ctx);
+			insn_len = ctx->ninsns - insns_start;
+			if (insn_is_zext(&insn[1]))
+				return 1;
 			break;
-		}
+		case BPF_W:
+			if (is_12b_int(off)) {
+				insns_start = ctx->ninsns;
+				emit(rv_lwu(rd, off, rs), ctx);
+				insn_len = ctx->ninsns - insns_start;
+				break;
+			}
 
-		emit_imm(RV_REG_T1, off, ctx);
-		emit_add(RV_REG_T1, RV_REG_T1, rs, ctx);
-		emit(rv_lhu(rd, 0, RV_REG_T1), ctx);
-		if (insn_is_zext(&insn[1]))
-			return 1;
-		break;
-	case BPF_LDX | BPF_MEM | BPF_W:
-		if (is_12b_int(off)) {
-			emit(rv_lwu(rd, off, rs), ctx);
+			emit_imm(RV_REG_T1, off, ctx);
+			emit_add(RV_REG_T1, RV_REG_T1, rs, ctx);
+			insns_start = ctx->ninsns;
+			emit(rv_lwu(rd, 0, RV_REG_T1), ctx);
+			insn_len = ctx->ninsns - insns_start;
+			if (insn_is_zext(&insn[1]))
+				return 1;
 			break;
-		}
+		case BPF_DW:
+			if (is_12b_int(off)) {
+				insns_start = ctx->ninsns;
+				emit_ld(rd, off, rs, ctx);
+				insn_len = ctx->ninsns - insns_start;
+				break;
+			}
 
-		emit_imm(RV_REG_T1, off, ctx);
-		emit_add(RV_REG_T1, RV_REG_T1, rs, ctx);
-		emit(rv_lwu(rd, 0, RV_REG_T1), ctx);
-		if (insn_is_zext(&insn[1]))
-			return 1;
-		break;
-	case BPF_LDX | BPF_MEM | BPF_DW:
-		if (is_12b_int(off)) {
-			emit_ld(rd, off, rs, ctx);
+			emit_imm(RV_REG_T1, off, ctx);
+			emit_add(RV_REG_T1, RV_REG_T1, rs, ctx);
+			insns_start = ctx->ninsns;
+			emit_ld(rd, 0, RV_REG_T1, ctx);
+			insn_len = ctx->ninsns - insns_start;
 			break;
 		}
 
-		emit_imm(RV_REG_T1, off, ctx);
-		emit_add(RV_REG_T1, RV_REG_T1, rs, ctx);
-		emit_ld(rd, 0, RV_REG_T1, ctx);
+		ret = add_exception_handler(insn, ctx, rd, insn_len);
+		if (ret)
+			return ret;
 		break;
-
+	}
 	/* speculation barrier */
 	case BPF_ST | BPF_NOSPEC:
 		break;
diff --git a/arch/riscv/net/bpf_jit_core.c b/arch/riscv/net/bpf_jit_core.c
index 753d85bdfad0..be743d700aa7 100644
--- a/arch/riscv/net/bpf_jit_core.c
+++ b/arch/riscv/net/bpf_jit_core.c
@@ -11,7 +11,7 @@
 #include "bpf_jit.h"
 
 /* Number of iterations to try until offsets converge. */
-#define NR_JIT_ITERATIONS	16
+#define NR_JIT_ITERATIONS	32
 
 static int build_body(struct rv_jit_context *ctx, bool extra_pass, int *offset)
 {
@@ -41,12 +41,12 @@ bool bpf_jit_needs_zext(void)
 
 struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 {
+	unsigned int prog_size = 0, extable_size = 0;
 	bool tmp_blinded = false, extra_pass = false;
 	struct bpf_prog *tmp, *orig_prog = prog;
 	int pass = 0, prev_ninsns = 0, i;
 	struct rv_jit_data *jit_data;
 	struct rv_jit_context *ctx;
-	unsigned int image_size = 0;
 
 	if (!prog->jit_requested)
 		return orig_prog;
@@ -73,7 +73,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 
 	if (ctx->offset) {
 		extra_pass = true;
-		image_size = sizeof(*ctx->insns) * ctx->ninsns;
+		prog_size = sizeof(*ctx->insns) * ctx->ninsns;
 		goto skip_init_ctx;
 	}
 
@@ -102,10 +102,13 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 		if (ctx->ninsns == prev_ninsns) {
 			if (jit_data->header)
 				break;
+			/* obtain the actual image size */
+			extable_size = prog->aux->num_exentries *
+				sizeof(struct exception_table_entry);
+			prog_size = sizeof(*ctx->insns) * ctx->ninsns;
 
-			image_size = sizeof(*ctx->insns) * ctx->ninsns;
 			jit_data->header =
-				bpf_jit_binary_alloc(image_size,
+				bpf_jit_binary_alloc(prog_size + extable_size,
 						     &jit_data->image,
 						     sizeof(u32),
 						     bpf_fill_ill_insns);
@@ -131,9 +134,13 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 		goto out_offset;
 	}
 
+	if (extable_size)
+		prog->aux->extable = (void *)ctx->insns + prog_size;
+
 skip_init_ctx:
 	pass++;
 	ctx->ninsns = 0;
+	ctx->nexentries = 0;
 
 	bpf_jit_build_prologue(ctx);
 	if (build_body(ctx, extra_pass, NULL)) {
@@ -144,11 +151,11 @@ skip_init_ctx:
 	bpf_jit_build_epilogue(ctx);
 
 	if (bpf_jit_enable > 1)
-		bpf_jit_dump(prog->len, image_size, pass, ctx->insns);
+		bpf_jit_dump(prog->len, prog_size, pass, ctx->insns);
 
 	prog->bpf_func = (void *)ctx->insns;
 	prog->jited = 1;
-	prog->jited_len = image_size;
+	prog->jited_len = prog_size;
 
 	bpf_flush_icache(jit_data->header, ctx->insns + ctx->ninsns);