init_params

pub fn init_params(entries: u16, p: *linux.io_uring_params) !IoUring

File

Code

pub fn init_params(entries: u16, p: *linux.io_uring_params) !IoUring {
    if (entries == 0) return error.EntriesZero;
    if (!std.math.isPowerOfTwo(entries)) return error.EntriesNotPowerOfTwo;

    assert(p.sq_entries == 0);
    assert(p.cq_entries == 0 or p.flags & linux.IORING_SETUP_CQSIZE != 0);
    assert(p.features == 0);
    assert(p.wq_fd == 0 or p.flags & linux.IORING_SETUP_ATTACH_WQ != 0);
    assert(p.resv[0] == 0);
    assert(p.resv[1] == 0);
    assert(p.resv[2] == 0);

    const res = linux.io_uring_setup(entries, p);
    switch (linux.errno(res)) {
        .SUCCESS => {},
        .FAULT => return error.ParamsOutsideAccessibleAddressSpace,
        // The resv array contains non-zero data, p.flags contains an unsupported flag,
        // entries out of bounds, IORING_SETUP_SQ_AFF was specified without IORING_SETUP_SQPOLL,
        // or IORING_SETUP_CQSIZE was specified but linux.io_uring_params.cq_entries was invalid:
        .INVAL => return error.ArgumentsInvalid,
        .MFILE => return error.ProcessFdQuotaExceeded,
        .NFILE => return error.SystemFdQuotaExceeded,
        .NOMEM => return error.SystemResources,
        // IORING_SETUP_SQPOLL was specified but effective user ID lacks sufficient privileges,
        // or a container seccomp policy prohibits io_uring syscalls:
        .PERM => return error.PermissionDenied,
        .NOSYS => return error.SystemOutdated,
        else => |errno| return posix.unexpectedErrno(errno),
    }
    const fd = @as(linux.fd_t, @intCast(res));
    assert(fd >= 0);
    errdefer _ = linux.close(fd);

    // Kernel versions 5.4 and up use only one mmap() for the submission and completion queues.
    // This is not an optional feature for us... if the kernel does it, we have to do it.
    // The thinking on this by the kernel developers was that both the submission and the
    // completion queue rings have sizes just over a power of two, but the submission queue ring
    // is significantly smaller with u32 slots. By bundling both in a single mmap, the kernel
    // gets the submission queue ring for free.
    // See https://patchwork.kernel.org/patch/11115257 for the kernel patch.
    // We do not support the double mmap() done before 5.4, because we want to keep the
    // init/deinit mmap paths simple and because io_uring has had many bug fixes even since 5.4.
    if ((p.features & linux.IORING_FEAT_SINGLE_MMAP) == 0) {
        return error.SystemOutdated;
    }

    // Check that the kernel has actually set params and that "impossible is nothing".
    assert(p.sq_entries != 0);
    assert(p.cq_entries != 0);
    assert(p.cq_entries >= p.sq_entries);

    // From here on, we only need to read from params, so pass `p` by value as immutable.
    // The completion queue shares the mmap with the submission queue, so pass `sq` there too.
    var sq = try SubmissionQueue.init(fd, p.*);
    errdefer sq.deinit();
    var cq = try CompletionQueue.init(fd, p.*, sq);
    errdefer cq.deinit();

    // Check that our starting state is as we expect.
    assert(sq.head.* == 0);
    assert(sq.tail.* == 0);
    assert(sq.mask == p.sq_entries - 1);
    // Allow flags.* to be non-zero, since the kernel may set IORING_SQ_NEED_WAKEUP at any time.
    assert(sq.dropped.* == 0);
    assert(sq.array.len == p.sq_entries);
    assert(sq.sqes.len == p.sq_entries);
    assert(sq.sqe_head == 0);
    assert(sq.sqe_tail == 0);

    assert(cq.head.* == 0);
    assert(cq.tail.* == 0);
    assert(cq.mask == p.cq_entries - 1);
    assert(cq.overflow.* == 0);
    assert(cq.cqes.len == p.cq_entries);

    return IoUring{
        .fd = fd,
        .sq = sq,
        .cq = cq,
        .flags = p.flags,
        .features = p.features,
    };
}