io_uring: track restrictions separately for IORING_OP and IORING_REGISTER

It's quite likely that only register opcode restrictions exists, in
which case we'd never need to check the normal opcodes. Split
ctx->restricted into two separate fields, one for I/O opcodes, and one
for register opcodes.

Reviewed-by: Gabriel Krisman Bertazi <krisman@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

Author: axboe

include/linux/io_uring_types.h

@@ -224,7 +224,10 @@ struct io_restriction {
 	DECLARE_BITMAP(sqe_op, IORING_OP_LAST);
 	u8 sqe_flags_allowed;
 	u8 sqe_flags_required;
-	bool registered;
+	/* IORING_OP_* restrictions exist */
+	bool op_registered;
+	/* IORING_REGISTER_* restrictions exist */
+	bool reg_registered;
 };
 
 struct io_submit_link {
@@ -259,7 +262,8 @@ struct io_ring_ctx {
 	struct {
 		unsigned int		flags;
 		unsigned int		drain_next: 1;
-		unsigned int		restricted: 1;
+		unsigned int		op_restricted: 1;
+		unsigned int		reg_restricted: 1;
 		unsigned int		off_timeout_used: 1;
 		unsigned int		drain_active: 1;
 		unsigned int		has_evfd: 1;

io_uring/io_uring.c

@@ -2056,7 +2056,7 @@ static inline bool io_check_restriction(struct io_ring_ctx *ctx,
 					struct io_kiocb *req,
 					unsigned int sqe_flags)
 {
-	if (!ctx->restricted)
+	if (!ctx->op_restricted)
 		return true;
 	if (!test_bit(req->opcode, ctx->restrictions.sqe_op))
 		return false;
@@ -2159,7 +2159,7 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
 			io_init_drain(ctx);
 		}
 	}
-	if (unlikely(ctx->restricted || ctx->drain_active || ctx->drain_next)) {
+	if (unlikely(ctx->op_restricted || ctx->drain_active || ctx->drain_next)) {
 		if (!io_check_restriction(ctx, req, sqe_flags))
 			return io_init_fail_req(req, -EACCES);
 		/* knock it to the slow queue path, will be drained there */

io_uring/register.c

@@ -133,24 +133,31 @@ static __cold int io_parse_restrictions(void __user *arg, unsigned int nr_args,
 			if (res[i].register_op >= IORING_REGISTER_LAST)
 				goto err;
 			__set_bit(res[i].register_op, restrictions->register_op);
+			restrictions->reg_registered = true;
 			break;
 		case IORING_RESTRICTION_SQE_OP:
 			if (res[i].sqe_op >= IORING_OP_LAST)
 				goto err;
 			__set_bit(res[i].sqe_op, restrictions->sqe_op);
+			restrictions->op_registered = true;
 			break;
 		case IORING_RESTRICTION_SQE_FLAGS_ALLOWED:
 			restrictions->sqe_flags_allowed = res[i].sqe_flags;
+			restrictions->op_registered = true;
 			break;
 		case IORING_RESTRICTION_SQE_FLAGS_REQUIRED:
 			restrictions->sqe_flags_required = res[i].sqe_flags;
+			restrictions->op_registered = true;
 			break;
 		default:
 			goto err;
 		}
 	}
 	ret = nr_args;
-	restrictions->registered = true;
+	if (!nr_args) {
+		restrictions->op_registered = true;
+		restrictions->reg_registered = true;
+	}
 err:
 	kfree(res);
 	return ret;
@@ -166,7 +173,7 @@ static __cold int io_register_restrictions(struct io_ring_ctx *ctx,
 		return -EBADFD;
 
 	/* We allow only a single restrictions registration */
-	if (ctx->restrictions.registered)
+	if (ctx->restrictions.op_registered || ctx->restrictions.reg_registered)
 		return -EBUSY;
 
 	ret = io_parse_restrictions(arg, nr_args, &ctx->restrictions);
@@ -175,8 +182,10 @@ static __cold int io_register_restrictions(struct io_ring_ctx *ctx,
 		memset(&ctx->restrictions, 0, sizeof(ctx->restrictions));
 		return ret;
 	}
-	if (ctx->restrictions.registered)
-		ctx->restricted = 1;
+	if (ctx->restrictions.op_registered)
+		ctx->op_restricted = 1;
+	if (ctx->restrictions.reg_registered)
+		ctx->reg_restricted = 1;
 	return 0;
 }
 
@@ -626,7 +635,7 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode,
 	if (ctx->submitter_task && ctx->submitter_task != current)
 		return -EEXIST;
 
-	if (ctx->restricted && !(ctx->flags & IORING_SETUP_R_DISABLED)) {
+	if (ctx->reg_restricted && !(ctx->flags & IORING_SETUP_R_DISABLED)) {
 		opcode = array_index_nospec(opcode, IORING_REGISTER_LAST);
 		if (!test_bit(opcode, ctx->restrictions.register_op))
 			return -EACCES;