1 files changed, 234 insertions, 52 deletions

diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index ceed77c29fe6..13eac43c632d 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -76,6 +76,7 @@ struct jit_ctx {
 	int *offset;
 	int exentry_idx;
 	__le32 *image;
+	__le32 *ro_image;
 	u32 stack_size;
 	int fpb_offset;
 };
@@ -205,6 +206,14 @@ static void jit_fill_hole(void *area, unsigned int size)
 		*ptr++ = cpu_to_le32(AARCH64_BREAK_FAULT);
 }
 
+int bpf_arch_text_invalidate(void *dst, size_t len)
+{
+	if (!aarch64_insn_set(dst, AARCH64_BREAK_FAULT, len))
+		return -EINVAL;
+
+	return 0;
+}
+
 static inline int epilogue_offset(const struct jit_ctx *ctx)
 {
 	int to = ctx->epilogue_offset;
@@ -285,7 +294,8 @@ static bool is_lsi_offset(int offset, int scale)
 /* Tail call offset to jump into */
 #define PROLOGUE_OFFSET (BTI_INSNS + 2 + PAC_INSNS + 8)
 
-static int build_prologue(struct jit_ctx *ctx, bool ebpf_from_cbpf)
+static int build_prologue(struct jit_ctx *ctx, bool ebpf_from_cbpf,
+			  bool is_exception_cb)
 {
 	const struct bpf_prog *prog = ctx->prog;
 	const bool is_main_prog = !bpf_is_subprog(prog);
@@ -333,19 +343,34 @@ static int build_prologue(struct jit_ctx *ctx, bool ebpf_from_cbpf)
 	emit(A64_MOV(1, A64_R(9), A64_LR), ctx);
 	emit(A64_NOP, ctx);
 
-	/* Sign lr */
-	if (IS_ENABLED(CONFIG_ARM64_PTR_AUTH_KERNEL))
-		emit(A64_PACIASP, ctx);
-
-	/* Save FP and LR registers to stay align with ARM64 AAPCS */
-	emit(A64_PUSH(A64_FP, A64_LR, A64_SP), ctx);
-	emit(A64_MOV(1, A64_FP, A64_SP), ctx);
-
-	/* Save callee-saved registers */
-	emit(A64_PUSH(r6, r7, A64_SP), ctx);
-	emit(A64_PUSH(r8, r9, A64_SP), ctx);
-	emit(A64_PUSH(fp, tcc, A64_SP), ctx);
-	emit(A64_PUSH(fpb, A64_R(28), A64_SP), ctx);
+	if (!is_exception_cb) {
+		/* Sign lr */
+		if (IS_ENABLED(CONFIG_ARM64_PTR_AUTH_KERNEL))
+			emit(A64_PACIASP, ctx);
+		/* Save FP and LR registers to stay align with ARM64 AAPCS */
+		emit(A64_PUSH(A64_FP, A64_LR, A64_SP), ctx);
+		emit(A64_MOV(1, A64_FP, A64_SP), ctx);
+
+		/* Save callee-saved registers */
+		emit(A64_PUSH(r6, r7, A64_SP), ctx);
+		emit(A64_PUSH(r8, r9, A64_SP), ctx);
+		emit(A64_PUSH(fp, tcc, A64_SP), ctx);
+		emit(A64_PUSH(fpb, A64_R(28), A64_SP), ctx);
+	} else {
+		/*
+		 * Exception callback receives FP of Main Program as third
+		 * parameter
+		 */
+		emit(A64_MOV(1, A64_FP, A64_R(2)), ctx);
+		/*
+		 * Main Program already pushed the frame record and the
+		 * callee-saved registers. The exception callback will not push
+		 * anything and re-use the main program's stack.
+		 *
+		 * 10 registers are on the stack
+		 */
+		emit(A64_SUB_I(1, A64_SP, A64_FP, 80), ctx);
+	}
 
 	/* Set up BPF prog stack base register */
 	emit(A64_MOV(1, fp, A64_SP), ctx);
@@ -365,6 +390,20 @@ static int build_prologue(struct jit_ctx *ctx, bool ebpf_from_cbpf)
 		emit_bti(A64_BTI_J, ctx);
 	}
 
+	/*
+	 * Program acting as exception boundary should save all ARM64
+	 * Callee-saved registers as the exception callback needs to recover
+	 * all ARM64 Callee-saved registers in its epilogue.
+	 */
+	if (prog->aux->exception_boundary) {
+		/*
+		 * As we are pushing two more registers, BPF_FP should be moved
+		 * 16 bytes
+		 */
+		emit(A64_SUB_I(1, fp, fp, 16), ctx);
+		emit(A64_PUSH(A64_R(23), A64_R(24), A64_SP), ctx);
+	}
+
 	emit(A64_SUB_I(1, fpb, fp, ctx->fpb_offset), ctx);
 
 	/* Stack must be multiples of 16B */
@@ -653,7 +692,7 @@ static void build_plt(struct jit_ctx *ctx)
 		plt->target = (u64)&dummy_tramp;
 }
 
-static void build_epilogue(struct jit_ctx *ctx)
+static void build_epilogue(struct jit_ctx *ctx, bool is_exception_cb)
 {
 	const u8 r0 = bpf2a64[BPF_REG_0];
 	const u8 r6 = bpf2a64[BPF_REG_6];
@@ -666,6 +705,15 @@ static void build_epilogue(struct jit_ctx *ctx)
 	/* We're done with BPF stack */
 	emit(A64_ADD_I(1, A64_SP, A64_SP, ctx->stack_size), ctx);
 
+	/*
+	 * Program acting as exception boundary pushes R23 and R24 in addition
+	 * to BPF callee-saved registers. Exception callback uses the boundary
+	 * program's stack frame, so recover these extra registers in the above
+	 * two cases.
+	 */
+	if (ctx->prog->aux->exception_boundary || is_exception_cb)
+		emit(A64_POP(A64_R(23), A64_R(24), A64_SP), ctx);
+
 	/* Restore x27 and x28 */
 	emit(A64_POP(fpb, A64_R(28), A64_SP), ctx);
 	/* Restore fs (x25) and x26 */
@@ -707,7 +755,8 @@ static int add_exception_handler(const struct bpf_insn *insn,
 				 struct jit_ctx *ctx,
 				 int dst_reg)
 {
-	off_t offset;
+	off_t ins_offset;
+	off_t fixup_offset;
 	unsigned long pc;
 	struct exception_table_entry *ex;
 
@@ -724,12 +773,17 @@ static int add_exception_handler(const struct bpf_insn *insn,
 		return -EINVAL;
 
 	ex = &ctx->prog->aux->extable[ctx->exentry_idx];
-	pc = (unsigned long)&ctx->image[ctx->idx - 1];
+	pc = (unsigned long)&ctx->ro_image[ctx->idx - 1];
 
-	offset = pc - (long)&ex->insn;
-	if (WARN_ON_ONCE(offset >= 0 || offset < INT_MIN))
+	/*
+	 * This is the relative offset of the instruction that may fault from
+	 * the exception table itself. This will be written to the exception
+	 * table and if this instruction faults, the destination register will
+	 * be set to '0' and the execution will jump to the next instruction.
+	 */
+	ins_offset = pc - (long)&ex->insn;
+	if (WARN_ON_ONCE(ins_offset >= 0 || ins_offset < INT_MIN))
 		return -ERANGE;
-	ex->insn = offset;
 
 	/*
 	 * Since the extable follows the program, the fixup offset is always
@@ -738,12 +792,25 @@ static int add_exception_handler(const struct bpf_insn *insn,
 	 * 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.
+	 *
+	 * The fixup_offset is set to the next instruction from the instruction
+	 * that may fault. The execution will jump to this after handling the
+	 * fault.
 	 */
-	offset = (long)&ex->fixup - (pc + AARCH64_INSN_SIZE);
-	if (!FIELD_FIT(BPF_FIXUP_OFFSET_MASK, offset))
+	fixup_offset = (long)&ex->fixup - (pc + AARCH64_INSN_SIZE);
+	if (!FIELD_FIT(BPF_FIXUP_OFFSET_MASK, fixup_offset))
 		return -ERANGE;
 
-	ex->fixup = FIELD_PREP(BPF_FIXUP_OFFSET_MASK, offset) |
+	/*
+	 * The offsets above have been calculated using the RO buffer but we
+	 * need to use the R/W buffer for writes.
+	 * switch ex to rw buffer for writing.
+	 */
+	ex = (void *)ctx->image + ((void *)ex - (void *)ctx->ro_image);
+
+	ex->insn = ins_offset;
+
+	ex->fixup = FIELD_PREP(BPF_FIXUP_OFFSET_MASK, fixup_offset) |
 		    FIELD_PREP(BPF_FIXUP_REG_MASK, dst_reg);
 
 	ex->type = EX_TYPE_BPF;
@@ -1511,7 +1578,8 @@ static inline void bpf_flush_icache(void *start, void *end)
 
 struct arm64_jit_data {
 	struct bpf_binary_header *header;
-	u8 *image;
+	u8 *ro_image;
+	struct bpf_binary_header *ro_header;
 	struct jit_ctx ctx;
 };
 
@@ -1520,12 +1588,14 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	int image_size, prog_size, extable_size, extable_align, extable_offset;
 	struct bpf_prog *tmp, *orig_prog = prog;
 	struct bpf_binary_header *header;
+	struct bpf_binary_header *ro_header;
 	struct arm64_jit_data *jit_data;
 	bool was_classic = bpf_prog_was_classic(prog);
 	bool tmp_blinded = false;
 	bool extra_pass = false;
 	struct jit_ctx ctx;
 	u8 *image_ptr;
+	u8 *ro_image_ptr;
 
 	if (!prog->jit_requested)
 		return orig_prog;
@@ -1552,8 +1622,11 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	}
 	if (jit_data->ctx.offset) {
 		ctx = jit_data->ctx;
-		image_ptr = jit_data->image;
+		ro_image_ptr = jit_data->ro_image;
+		ro_header = jit_data->ro_header;
 		header = jit_data->header;
+		image_ptr = (void *)header + ((void *)ro_image_ptr
+						 - (void *)ro_header);
 		extra_pass = true;
 		prog_size = sizeof(u32) * ctx.idx;
 		goto skip_init_ctx;
@@ -1575,7 +1648,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	 * BPF line info needs ctx->offset[i] to be the offset of
 	 * instruction[i] in jited image, so build prologue first.
 	 */
-	if (build_prologue(&ctx, was_classic)) {
+	if (build_prologue(&ctx, was_classic, prog->aux->exception_cb)) {
 		prog = orig_prog;
 		goto out_off;
 	}
@@ -1586,7 +1659,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	}
 
 	ctx.epilogue_offset = ctx.idx;
-	build_epilogue(&ctx);
+	build_epilogue(&ctx, prog->aux->exception_cb);
 	build_plt(&ctx);
 
 	extable_align = __alignof__(struct exception_table_entry);
@@ -1598,63 +1671,81 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	/* also allocate space for plt target */
 	extable_offset = round_up(prog_size + PLT_TARGET_SIZE, extable_align);
 	image_size = extable_offset + extable_size;
-	header = bpf_jit_binary_alloc(image_size, &image_ptr,
-				      sizeof(u32), jit_fill_hole);
-	if (header == NULL) {
+	ro_header = bpf_jit_binary_pack_alloc(image_size, &ro_image_ptr,
+					      sizeof(u32), &header, &image_ptr,
+					      jit_fill_hole);
+	if (!ro_header) {
 		prog = orig_prog;
 		goto out_off;
 	}
 
 	/* 2. Now, the actual pass. */
 
+	/*
+	 * Use the image(RW) for writing the JITed instructions. But also save
+	 * the ro_image(RX) for calculating the offsets in the image. The RW
+	 * image will be later copied to the RX image from where the program
+	 * will run. The bpf_jit_binary_pack_finalize() will do this copy in the
+	 * final step.
+	 */
 	ctx.image = (__le32 *)image_ptr;
+	ctx.ro_image = (__le32 *)ro_image_ptr;
 	if (extable_size)
-		prog->aux->extable = (void *)image_ptr + extable_offset;
+		prog->aux->extable = (void *)ro_image_ptr + extable_offset;
 skip_init_ctx:
 	ctx.idx = 0;
 	ctx.exentry_idx = 0;
 
-	build_prologue(&ctx, was_classic);
+	build_prologue(&ctx, was_classic, prog->aux->exception_cb);
 
 	if (build_body(&ctx, extra_pass)) {
-		bpf_jit_binary_free(header);
 		prog = orig_prog;
-		goto out_off;
+		goto out_free_hdr;
 	}
 
-	build_epilogue(&ctx);
+	build_epilogue(&ctx, prog->aux->exception_cb);
 	build_plt(&ctx);
 
 	/* 3. Extra pass to validate JITed code. */
 	if (validate_ctx(&ctx)) {
-		bpf_jit_binary_free(header);
 		prog = orig_prog;
-		goto out_off;
+		goto out_free_hdr;
 	}
 
 	/* And we're done. */
 	if (bpf_jit_enable > 1)
 		bpf_jit_dump(prog->len, prog_size, 2, ctx.image);
 
-	bpf_flush_icache(header, ctx.image + ctx.idx);
-
 	if (!prog->is_func || extra_pass) {
 		if (extra_pass && ctx.idx != jit_data->ctx.idx) {
 			pr_err_once("multi-func JIT bug %d != %d\n",
 				    ctx.idx, jit_data->ctx.idx);
-			bpf_jit_binary_free(header);
 			prog->bpf_func = NULL;
 			prog->jited = 0;
 			prog->jited_len = 0;
+			goto out_free_hdr;
+		}
+		if (WARN_ON(bpf_jit_binary_pack_finalize(prog, ro_header,
+							 header))) {
+			/* ro_header has been freed */
+			ro_header = NULL;
+			prog = orig_prog;
 			goto out_off;
 		}
-		bpf_jit_binary_lock_ro(header);
+		/*
+		 * The instructions have now been copied to the ROX region from
+		 * where they will execute. Now the data cache has to be cleaned to
+		 * the PoU and the I-cache has to be invalidated for the VAs.
+		 */
+		bpf_flush_icache(ro_header, ctx.ro_image + ctx.idx);
 	} else {
 		jit_data->ctx = ctx;
-		jit_data->image = image_ptr;
+		jit_data->ro_image = ro_image_ptr;
 		jit_data->header = header;
+		jit_data->ro_header = ro_header;
 	}
-	prog->bpf_func = (void *)ctx.image;
+
+	prog->bpf_func = (void *)ctx.ro_image;
 	prog->jited = 1;
 	prog->jited_len = prog_size;
 
@@ -1675,6 +1766,14 @@ out:
 		bpf_jit_prog_release_other(prog, prog == orig_prog ?
 					   tmp : orig_prog);
 	return prog;
+
+out_free_hdr:
+	if (header) {
+		bpf_arch_text_copy(&ro_header->size, &header->size,
+				   sizeof(header->size));
+		bpf_jit_binary_pack_free(ro_header, header);
+	}
+	goto out_off;
 }
 
 bool bpf_jit_supports_kfunc_call(void)
@@ -1682,6 +1781,13 @@ bool bpf_jit_supports_kfunc_call(void)
 	return true;
 }
 
+void *bpf_arch_text_copy(void *dst, void *src, size_t len)
+{
+	if (!aarch64_insn_copy(dst, src, len))
+		return ERR_PTR(-EINVAL);
+	return dst;
+}
+
 u64 bpf_jit_alloc_exec_limit(void)
 {
 	return VMALLOC_END - VMALLOC_START;
@@ -1970,7 +2076,7 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im,
 		/* store return value */
 		emit(A64_STR64I(A64_R(0), A64_SP, retval_off), ctx);
 		/* reserve a nop for bpf_tramp_image_put */
-		im->ip_after_call = ctx->image + ctx->idx;
+		im->ip_after_call = ctx->ro_image + ctx->idx;
 		emit(A64_NOP, ctx);
 	}
 
@@ -1985,7 +2091,7 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im,
 				run_ctx_off, false);
 
 	if (flags & BPF_TRAMP_F_CALL_ORIG) {
-		im->ip_epilogue = ctx->image + ctx->idx;
+		im->ip_epilogue = ctx->ro_image + ctx->idx;
 		emit_addr_mov_i64(A64_R(0), (const u64)im, ctx);
 		emit_call((const u64)__bpf_tramp_exit, ctx);
 	}
@@ -2018,9 +2124,6 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im,
 		emit(A64_RET(A64_R(10)), ctx);
 	}
 
-	if (ctx->image)
-		bpf_flush_icache(ctx->image, ctx->image + ctx->idx);
-
 	kfree(branches);
 
 	return ctx->idx;
@@ -2063,14 +2166,43 @@ int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags,
 	return ret < 0 ? ret : ret * AARCH64_INSN_SIZE;
 }
 
-int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image,
-				void *image_end, const struct btf_func_model *m,
+void *arch_alloc_bpf_trampoline(unsigned int size)
+{
+	return bpf_prog_pack_alloc(size, jit_fill_hole);
+}
+
+void arch_free_bpf_trampoline(void *image, unsigned int size)
+{
+	bpf_prog_pack_free(image, size);
+}
+
+void arch_protect_bpf_trampoline(void *image, unsigned int size)
+{
+}
+
+void arch_unprotect_bpf_trampoline(void *image, unsigned int size)
+{
+}
+
+int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *ro_image,
+				void *ro_image_end, const struct btf_func_model *m,
 				u32 flags, struct bpf_tramp_links *tlinks,
 				void *func_addr)
 {
 	int ret, nregs;
+	void *image, *tmp;
+	u32 size = ro_image_end - ro_image;
+
+	/* image doesn't need to be in module memory range, so we can
+	 * use kvmalloc.
+	 */
+	image = kvmalloc(size, GFP_KERNEL);
+	if (!image)
+		return -ENOMEM;
+
 	struct jit_ctx ctx = {
 		.image = image,
+		.ro_image = ro_image,
 		.idx = 0,
 	};
 
@@ -2079,15 +2211,26 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image,
 	if (nregs > 8)
 		return -ENOTSUPP;
 
-	jit_fill_hole(image, (unsigned int)(image_end - image));
+	jit_fill_hole(image, (unsigned int)(ro_image_end - ro_image));
 	ret = prepare_trampoline(&ctx, im, tlinks, func_addr, nregs, flags);
 
-	if (ret > 0 && validate_code(&ctx) < 0)
+	if (ret > 0 && validate_code(&ctx) < 0) {
 		ret = -EINVAL;
+		goto out;
+	}
 
 	if (ret > 0)
 		ret *= AARCH64_INSN_SIZE;
 
+	tmp = bpf_arch_text_copy(ro_image, image, size);
+	if (IS_ERR(tmp)) {
+		ret = PTR_ERR(tmp);
+		goto out;
+	}
+
+	bpf_flush_icache(ro_image, ro_image + size);
+out:
+	kvfree(image);
 	return ret;
 }
 
@@ -2305,3 +2448,42 @@ out:
 
 	return ret;
 }
+
+bool bpf_jit_supports_ptr_xchg(void)
+{
+	return true;
+}
+
+bool bpf_jit_supports_exceptions(void)
+{
+	/* We unwind through both kernel frames starting from within bpf_throw
+	 * call and BPF frames. Therefore we require FP unwinder to be enabled
+	 * to walk kernel frames and reach BPF frames in the stack trace.
+	 * ARM64 kernel is aways compiled with CONFIG_FRAME_POINTER=y
+	 */
+	return true;
+}
+
+void bpf_jit_free(struct bpf_prog *prog)
+{
+	if (prog->jited) {
+		struct arm64_jit_data *jit_data = prog->aux->jit_data;
+		struct bpf_binary_header *hdr;
+
+		/*
+		 * If we fail the final pass of JIT (from jit_subprogs),
+		 * the program may not be finalized yet. Call finalize here
+		 * before freeing it.
+		 */
+		if (jit_data) {
+			bpf_arch_text_copy(&jit_data->ro_header->size, &jit_data->header->size,
+					   sizeof(jit_data->header->size));
+			kfree(jit_data);
+		}
+		hdr = bpf_jit_binary_pack_hdr(prog);
+		bpf_jit_binary_pack_free(hdr, NULL);
+		WARN_ON_ONCE(!bpf_prog_kallsyms_verify_off(prog));
+	}
+
+	bpf_prog_unlock_free(prog);
+}