bpf, arm64: Add BPF exception tables

When a tracing BPF program attempts to read memory without using the
bpf_probe_read() helper, the verifier marks the load instruction with
the BPF_PROBE_MEM flag. Since the arm64 JIT does not currently recognize
this flag it falls back to the interpreter.

Add support for BPF_PROBE_MEM, by appending an exception table to the
BPF program. If the load instruction causes a data abort, the fixup
infrastructure finds the exception table and fixes up the fault, by
clearing the destination register and jumping over the faulting
instruction.

To keep the compact exception table entry format, inspect the pc in
fixup_exception(). A more generic solution would add a "handler" field
to the table entry, like on x86 and s390.

Signed-off-by: Jean-Philippe Brucker <[e-mail]>
Signed-off-by: Daniel Borkmann <[e-mail]>
Acked-by: Song Liu <[e-mail]>
Link: https://lore.kernel.org/bpf/[e-mail]

arch/arm64/include/asm/extable.h

···
 
 #define ARCH_HAS_RELATIVE_EXTABLE
 
+#ifdef CONFIG_BPF_JIT
+int arm64_bpf_fixup_exception(const struct exception_table_entry *ex,
+			      struct pt_regs *regs);
+#else /* !CONFIG_BPF_JIT */
+static inline
+int arm64_bpf_fixup_exception(const struct exception_table_entry *ex,
+			      struct pt_regs *regs)
+{
+	return 0;
+}
+#endif /* !CONFIG_BPF_JIT */
+
 extern int fixup_exception(struct pt_regs *regs);
 #endif

arch/arm64/mm/extable.c

···
 	const struct exception_table_entry *fixup;
 
 	fixup = search_exception_tables(instruction_pointer(regs));
-	if (fixup)
-		regs->pc = (unsigned long)&fixup->fixup + fixup->fixup;
+	if (!fixup)
+		return 0;
 
-	return fixup != NULL;
+	if (IS_ENABLED(CONFIG_BPF_JIT) &&
+	    regs->pc >= BPF_JIT_REGION_START &&
+	    regs->pc < BPF_JIT_REGION_END)
+		return arm64_bpf_fixup_exception(fixup, regs);
+
+	regs->pc = (unsigned long)&fixup->fixup + fixup->fixup;
+	return 1;
 }

arch/arm64/net/bpf_jit_comp.c

···
 
 #define pr_fmt(fmt) "bpf_jit: " fmt
 
+#include <linux/bitfield.h>
 #include <linux/bpf.h>
 #include <linux/filter.h>
 #include <linux/printk.h>
···
 	int idx;
 	int epilogue_offset;
 	int *offset;
+	int exentry_idx;
 	__le32 *image;
 	u32 stack_size;
 };
···
 	emit(A64_RET(A64_LR), ctx);
 }
 
+#define BPF_FIXUP_OFFSET_MASK	GENMASK(26, 0)
+#define BPF_FIXUP_REG_MASK	GENMASK(31, 27)
+
+int arm64_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 dst_reg = FIELD_GET(BPF_FIXUP_REG_MASK, ex->fixup);
+
+	regs->regs[dst_reg] = 0;
+	regs->pc = (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 jit_ctx *ctx,
+				 int dst_reg)
+{
+	off_t offset;
+	unsigned long pc;
+	struct exception_table_entry *ex;
+
+	if (!ctx->image)
+		/* First pass */
+		return 0;
+
+	if (BPF_MODE(insn->code) != BPF_PROBE_MEM)
+		return 0;
+
+	if (!ctx->prog->aux->extable ||
+	    WARN_ON_ONCE(ctx->exentry_idx >= ctx->prog->aux->num_exentries))
+		return -EINVAL;
+
+	ex = &ctx->prog->aux->extable[ctx->exentry_idx];
+	pc = (unsigned long)&ctx->image[ctx->idx - 1];
+
+	offset = pc - (long)&ex->insn;
+	if (WARN_ON_ONCE(offset >= 0 || offset < INT_MIN))
+		return -ERANGE;
+	ex->insn = offset;
+
+	/*
+	 * 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 + AARCH64_INSN_SIZE);
+	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->exentry_idx++;
+	return 0;
+}
+
 /* JITs an eBPF instruction.
  * Returns:
  * 0  - successfully JITed an 8-byte eBPF instruction.
···
 	u8 jmp_cond, reg;
 	s32 jmp_offset;
 	u32 a64_insn;
+	int ret;
 
 #define check_imm(bits, imm) do {				\
 	if ((((imm) > 0) && ((imm) >> (bits))) ||		\
···
 		const u8 r0 = bpf2a64[BPF_REG_0];
 		bool func_addr_fixed;
 		u64 func_addr;
-		int ret;
 
 		ret = bpf_jit_get_func_addr(ctx->prog, insn, extra_pass,
 					    &func_addr, &func_addr_fixed);
···
 	case BPF_LDX | BPF_MEM | BPF_H:
 	case BPF_LDX | BPF_MEM | BPF_B:
 	case BPF_LDX | BPF_MEM | BPF_DW:
+	case BPF_LDX | BPF_PROBE_MEM | BPF_DW:
+	case BPF_LDX | BPF_PROBE_MEM | BPF_W:
+	case BPF_LDX | BPF_PROBE_MEM | BPF_H:
+	case BPF_LDX | BPF_PROBE_MEM | BPF_B:
 		emit_a64_mov_i(1, tmp, off, ctx);
 		switch (BPF_SIZE(code)) {
 		case BPF_W:
···
 			emit(A64_LDR64(dst, src, tmp), ctx);
 			break;
 		}
+
+		ret = add_exception_handler(insn, ctx, dst);
+		if (ret)
+			return ret;
 		break;
 
 	/* ST: *(size *)(dst + off) = imm */
···
 			return -1;
 	}
 
+	if (WARN_ON_ONCE(ctx->exentry_idx != ctx->prog->aux->num_exentries))
+		return -1;
+
 	return 0;
 }
 
···
 
 struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 {
+	int image_size, prog_size, extable_size;
 	struct bpf_prog *tmp, *orig_prog = prog;
 	struct bpf_binary_header *header;
 	struct arm64_jit_data *jit_data;
···
 	bool tmp_blinded = false;
 	bool extra_pass = false;
 	struct jit_ctx ctx;
-	int image_size;
 	u8 *image_ptr;
 
 	if (!prog->jit_requested)
···
 		image_ptr = jit_data->image;
 		header = jit_data->header;
 		extra_pass = true;
-		image_size = sizeof(u32) * ctx.idx;
+		prog_size = sizeof(u32) * ctx.idx;
 		goto skip_init_ctx;
 	}
 	memset(&ctx, 0, sizeof(ctx));
···
 	ctx.epilogue_offset = ctx.idx;
 	build_epilogue(&ctx);
 
+	extable_size = prog->aux->num_exentries *
+		sizeof(struct exception_table_entry);
+
 	/* Now we know the actual image size. */
-	image_size = sizeof(u32) * ctx.idx;
+	prog_size = sizeof(u32) * ctx.idx;
+	image_size = prog_size + extable_size;
 	header = bpf_jit_binary_alloc(image_size, &image_ptr,
 				      sizeof(u32), jit_fill_hole);
 	if (header == NULL) {
···
 	/* 2. Now, the actual pass. */
 
 	ctx.image = (__le32 *)image_ptr;
+	if (extable_size)
+		prog->aux->extable = (void *)image_ptr + prog_size;
 skip_init_ctx:
 	ctx.idx = 0;
+	ctx.exentry_idx = 0;
 
 	build_prologue(&ctx, was_classic);
 
···
 
 	/* And we're done. */
 	if (bpf_jit_enable > 1)
-		bpf_jit_dump(prog->len, image_size, 2, ctx.image);
+		bpf_jit_dump(prog->len, prog_size, 2, ctx.image);
 
 	bpf_flush_icache(header, ctx.image + ctx.idx);
 
···
 	}
 	prog->bpf_func = (void *)ctx.image;
 	prog->jited = 1;
-	prog->jited_len = image_size;
+	prog->jited_len = prog_size;
 
 	if (!prog->is_func || extra_pass) {
 		bpf_prog_fill_jited_linfo(prog, ctx.offset);