[rt2x00-users] [RFC 1/6] rt2x00: Introduce 3 queue commands in drivers (start, kick, stop).

[Helmut Schaa]

Am Montag 22 November 2010 schrieb Ivo van Doorn:
> As part of the queue refactoring, we now introduce
> 3 queue commands: start, kick, stop.
> 
>  - Start: will enable a queue, for TX this will
>    not mean anything, while for beacons and RX
>    this will update the registers to enable the queue.
>  - Kick: This will kick all pending frames to
>    the hardware. This is needed for the TX queue
>    to push all frames to the HW after the queue
>    has been started
>  - Stop: This will stop the queue in the hardware,
>    and cancel any pending work (So this doesn't
>    mean the queue is empty after a stop!).
> 
> Move all code from the drivers into the appropriate
> functions, and link those calls to the old rt2x00lib
> callback functions (we will fix this later when we
> refactor the queue control inside rt2x00lib).
> 
> Signed-off-by: Ivo van Doorn <IvDoorn at gmail.com>
> ---
>  drivers/net/wireless/rt2x00/rt2400pci.c |  123 +++++++++++++++++---------
>  drivers/net/wireless/rt2x00/rt2500pci.c |  123 +++++++++++++++++---------
>  drivers/net/wireless/rt2x00/rt2500usb.c |   72 +++++++++++-----
>  drivers/net/wireless/rt2x00/rt2800pci.c |  141 +++++++++++++++++++----------
>  drivers/net/wireless/rt2x00/rt2800usb.c |   72 +++++++++++-----
>  drivers/net/wireless/rt2x00/rt2x00usb.c |   12 ++--
>  drivers/net/wireless/rt2x00/rt2x00usb.h |    8 +-
>  drivers/net/wireless/rt2x00/rt61pci.c   |  146 +++++++++++++++++++++----------
>  drivers/net/wireless/rt2x00/rt73usb.c   |   72 +++++++++++-----
>  9 files changed, 522 insertions(+), 247 deletions(-)

[...]

> +static void rt2800pci_stop_queue(struct data_queue *queue)
> +{
> +	struct rt2x00_dev *rt2x00dev = queue->rt2x00dev;
> +	u32 reg;
> +
> +	switch (queue->qid) {
> +	case QID_AC_BE:
> +		rt2800_register_read(rt2x00dev, WPDMA_RST_IDX, &reg);
> +		rt2x00_set_field32(&reg, WPDMA_RST_IDX_DTX_IDX0, 1);
> +		rt2800_register_write(rt2x00dev, WPDMA_RST_IDX, reg);

The function is called stop_queue but this will reset the tx queue index
within the device. and thus drop all tx entries still in there. Is that
what stop_queue is expected to do?

If the tx queue flush before stop_queue fails we would have to clear all
entries that are still in the queue and also reset our own tx queue index?
Otherwise there might be a queue corruption after an ifdown/ifup cycle.

I guess the same applies to the other pci drivers as well.

Helmut