Signed-off-by: NDuncan Sands <baldrick@free.fr>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

The receive logic has always assumed that urbs contain an integral
number of ATM cells, which is a bit naughty, though it never caused
any problems with bulk transfers.  Isochronous urbs spank us soundly
for this.  Fixed thanks to this patch, mostly by Stanislaw Gruszka.
Signed-off-by: NDuncan Sands <baldrick@free.fr>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

While the usbatm core has had some support for using isoc urbs
for some time, there was no way for users to turn it on.  While
use of isoc transfer should still be considered experimental, it
now works well enough to let users turn it on.  Minidrivers signal
to the core that they want to use isoc transfer by setting the new
UDSL_USE_ISOC flag.  The speedtch minidriver gets a new module
parameter enable_isoc (defaults to false), plus some logic that
checks for the existence of an isoc receive endpoint (not all
speedtouch modems have one).
Signed-off-by: NDuncan Sands <baldrick@free.fr>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

Change the module parameters rcv_buf_size and snd_buf_size to
specify buffer sizes in bytes rather than ATM cells.  Since
there is some danger that users may not notice this change,
the parameters are renamed to rcv_buf_bytes etc.  The transmit
buffer needs to be a multiple of the ATM cell size in length,
while the receive buffer should be a multiple of the endpoint
maxpacket size (this wasn't enforced before, which causes trouble
with isochronous transfers), so enforce these restrictions.  Now
that the usbatm probe method inspects the endpoint maxpacket size,
minidriver bind routines need to set the correct alternate setting
for the interface in their bind routine.  This is the reason for
the speedtch changes.
Signed-off-by: NDuncan Sands <baldrick@free.fr>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

In one spot (usbatm_cancel_send) we were calling dev_kfree_skb with irqs
disabled.  This mistake is just too easy to make, so systematically use
dev_kfree_skb_any rather than dev_kfree_skb.
Signed-off-by: NDuncan Sands <baldrick@free.fr>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

We weren't always returning -ENOMEM.
Signed-off-by: NDuncan Sands <baldrick@free.fr>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

This patch causes vcc_release_async to be applied to any open
vcc's when the modem is disconnected.  This signals a socket
shutdown, letting the socket user know that the game is up.
I wrote this patch because of reports that pppd would keep
connections open forever when the modem is disconnected.
This patch does not fix that problem, but it's a step in the
right direction.  It doesn't help because the pppoatm module
doesn't yet monitor state changes on the ATM socket, so simply
never realises that the ATM connection has gone down (meaning
it doesn't tell the ppp layer).  But at least there is a socket
state change now.  Unfortunately this patch may create problems
for those rare users like me who use routed IP or some other
non-ppp connection method that goes via the ATM ARP daemon: the
daemon is buggy, and with this patch will crash when the modem
is disconnected.  Users with a buggy atmarpd can simply restart
it after disconnecting the modem.
Signed-off-by: NDuncan Sands <baldrick@free.fr>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

Convert kmalloc + memset to kzalloc.
Signed-off-by: NDuncan Sands <baldrick@free.fr>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

Have minidrivers and the core signal special requirements
using a flags field in struct usbatm_data.  For the moment
this is only used to replace the need_heavy_init bind
parameter, but there'll be new flags in later patches.
Signed-off-by: NDuncan Sands <baldrick@free.fr>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

Formatting, changes to variable names, comments, log level changes,
printk rate limiting.
Signed-off-by: NDuncan Sands <baldrick@free.fr>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

Remove the "inline" keyword from a bunch of big functions in the kernel with
the goal of shrinking it by 30kb to 40kb
Signed-off-by: NArjan van de Ven <arjan@infradead.org>
Signed-off-by: NIngo Molnar <mingo@elte.hu>
Acked-by: NJeff Garzik <jgarzik@pobox.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

This patch contains the following cleanups:
- make needlessly global functions static
- every file should #include the headers containing the prototypes for
  it's global functions
Signed-off-by: NAdrian Bunk <bunk@stusta.de>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

atm_dev_deregister() removes device from atm_dev list immediately to
prevent operations on a phantom device.  Decision to free device based
only on ->refcnt  now. Remove shutdown_atm_dev() use atm_dev_deregister()
instead.  atm_dev_deregister() also asynchronously releases all vccs
related to device.
Signed-off-by: NStanislaw Gruszka <stf_xl@wp.pl>
Signed-off-by: NChas Williams <chas@cmf.nrl.navy.mil>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch converts kcalloc(1, ...) calls to use the new kzalloc() function.
Signed-off-by: NPekka Enberg <penberg@cs.helsinki.fi>
Cc: Greg KH <greg@kroah.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

you seem to have applied the original, not the new improved one with
whiter teeth that uses kcalloc instead of kmalloc + memset.  Here's a
patch that goes on top of the one you applied.
Signed-off-by: NDuncan Sands <baldrick@free.fr>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

Zero the entire instance, not just the struct usbatm_data head.
Make sure the just allocated urb is freed if we fail to allocate
a buffer.  Based on a patch by Stanislaw W. Gruszka.
Signed-off-by: NDuncan Sands <baldrick@free.fr>
Acked-by: NPete Zaitcev <zaitcev@redhat.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

Reduce the number of "unknown vpi/vci" debug messages to (usually) at most
one per-urb, rather than one per-cell.  This is only an issue when (a) many
packets come in but no connection is open; and (b) CONFIG_USB_DEBUG is set.
Signed-off-by: NDuncan Sands <baldrick@free.fr>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

Rework the core usbatm code: minidrivers (i.e. drivers for particular
modems) now register themselves with the usbatm core, supplying methods
for binding/unbinding etc.  The design was inspired by usb-serial and
usbnet.  At the same time, more common code from the speedtch and
cxacru (patch 3/5) drivers was generalized and moved into the core.  The
transmission and reception parts have been unified and simplified.  Since
this is a major change and I don't like underscores in file names,
usb_atm.[ch] has been renamed usbatm.[ch].

Many thanks to Roman Kagan, who did a lot of the coding.
Signed-off-by: NDuncan Sands <baldrick@free.fr>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>