This enables the completion callback to be called from a different
context, preventing a possible deadlock if the callback resulted in the
invocation of a nested call to the currently locked nfc_dev.
This is also more in line with the im_transceive nfc_ops for NFC Core or
NCI drivers which already behave asynchronously.
Signed-off-by: NEric Lapuyade <eric.lapuyade@intel.com>
Signed-off-by: NSamuel Ortiz <sameo@linux.intel.com>

This method initiates execution of an HCI cmd. Result will be delivered
through an asynchronous callback.
Signed-off-by: NEric Lapuyade <eric.lapuyade@intel.com>
Signed-off-by: NSamuel Ortiz <sameo@linux.intel.com>

Make it match the data_exchange_cb_t so that it can be used directly in
the implementation of an asynchronous hci_transceive
Signed-off-by: NEric Lapuyade <eric.lapuyade@intel.com>
Signed-off-by: NSamuel Ortiz <sameo@linux.intel.com>

Driver must handle its data added to the frame, so at this point
removeing control field of shdlc frame is enough.
Signed-off-by: NWaldemar Rymarkiewicz <waldemar.rymarkiewicz@tieto.com>
Acked-by: NEric Lapuyade <eric.lapuyade@intel.com>
Signed-off-by: NSamuel Ortiz <sameo@linux.intel.com>

Checksum is specific for a chip spcification and it varies
(in size and type) between different hardware. It should be
handled in the driver then.

Moreover, shdlc spec doesn't mention crc as a part of the frame.

Update pn544_hci driver as well.
Signed-off-by: NWaldemar Rymarkiewicz <waldemar.rymarkiewicz@tieto.com>
Acked-by: NEric Lapuyade <eric.lapuyade@intel.com>
Signed-off-by: NSamuel Ortiz <sameo@linux.intel.com>

nfc_llcp_build_tlv() malloced the memory and should be free in
nfc_llcp_build_gb() after used, and the same in the error handling
case, otherwise it will cause memory leak.

spatch with a semantic match is used to found this problem.
(http://coccinelle.lip6.fr/)
Signed-off-by: NWei Yongjun <yongjun_wei@trendmicro.com.cn>
Signed-off-by: NSamuel Ortiz <sameo@linux.intel.com>

Signed-off-by: NWei Yongjun <yongjun_wei@trendmicro.com.cn>
Signed-off-by: NSamuel Ortiz <sameo@linux.intel.com>

NFC is using a number of custom ordered workqueues w/ WQ_MEM_RECLAIM.
WQ_MEM_RECLAIM is unnecessary unless NFC is gonna be used as transport
for storage device, and all use cases match one work item to one
ordered workqueue - IOW, there's no actual ordering going on at all
and using system_nrt_wq gives the same behavior.

There's nothing to be gained by using custom workqueues.  Use
system_nrt_wq instead and drop all the custom ones.
Signed-off-by: NTejun Heo <tj@kernel.org>
Signed-off-by: NSamuel Ortiz <sameo@linux.intel.com>

This patch remove the repeated code for checking llcp_sock &
llcp_sock->dev against NULL.
Signed-off-by: NSyam Sidhardhan <s.syam@samsung.com>
Signed-off-by: NSamuel Ortiz <sameo@linux.intel.com>

During NFC-DEP target activation, store the remote
general bytes to be used later in dep_link_up.
When dep_link_up is called, activate the NFC-DEP target,
and forward the remote general bytes.
When dep_link_down is called, deactivate the target.
Signed-off-by: NIlan Elias <ilane@ti.com>
Signed-off-by: NSamuel Ortiz <sameo@linux.intel.com>

Signed-off-by: NIlan Elias <ilane@ti.com>
Signed-off-by: NSamuel Ortiz <sameo@linux.intel.com>

If initiator protocol is NFC-DEP, set the local general bytes
in nci_start_poll.
Signed-off-by: NIlan Elias <ilane@ti.com>
Signed-off-by: NSamuel Ortiz <sameo@linux.intel.com>

Signed-off-by: NDave Jones <davej@redhat.com>
Signed-off-by: NSamuel Ortiz <sameo@linux.intel.com>
Signed-off-by: NJohn W. Linville <linville@tuxdriver.com>

Without the discovered target nfcid1 and its length set properly, type 2
tags detection fails with the pn544 as it checks for them from
pn544_hci_complete_target_discovered().
Signed-off-by: NEric Lapuyade <eric.lapuyade@intel.com>
Reported-by: NMathias Jeppsson <mathias.jeppsson@sonymobile.com>
Signed-off-by: NSamuel Ortiz <sameo@linux.intel.com>
Signed-off-by: NJohn W. Linville <linville@tuxdriver.com>

The HCP message should be added to transmit queue, not the other way around.
Signed-off-by: NMathias Jeppsson <mathias.jeppsson@sonymobile.com>
Signed-off-by: NSamuel Ortiz <sameo@linux.intel.com>
Signed-off-by: NJohn W. Linville <linville@tuxdriver.com>

list_first_entry() will never return NULL. Instead use
list_for_each_entry_safe() to iterate through the list.
Signed-off-by: NMathias Jeppsson <mathias.jeppsson@sonymobile.com>
Signed-off-by: NSamuel Ortiz <sameo@linux.intel.com>
Signed-off-by: NJohn W. Linville <linville@tuxdriver.com>

They both can potentially be NULL.
Signed-off-by: NSamuel Ortiz <sameo@linux.intel.com>

Some devices (e.g. Sony's PaSoRi) can not do type B polling, so we have
to make a distinction between ISO14443 type A and B poll modes.

Cc: Eric Lapuyade <eric.lapuyade@intel.com>
Cc: Ilan Elias <ilane@ti.com>
Signed-off-by: NSamuel Ortiz <sameo@linux.intel.com>

Reported-by: NDan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: NSamuel Ortiz <sameo@linux.intel.com>

We check for the polling flag before checking if the netlink PID caller
match.
Signed-off-by: NSamuel Ortiz <sameo@linux.intel.com>

The socket local pointer can be NULL when a socket is created but never
bound or connected.
Reported-by: NSasha Levin <levinsasha928@gmail.com>
Signed-off-by: NSamuel Ortiz <sameo@linux.intel.com>

When receiving such frame, the sockets waiting for a connection to finish
should be woken up. Connecting to an unbound LLCP service will trigger a
DM as a response.
Signed-off-by: NSamuel Ortiz <sameo@linux.intel.com>

With the LLCP 16 local SAPs we can potentially quickly run out of source
SAPs for non well known services.
With the so called late binding we will reserve an SAP only when we actually
get a client connection for a local service. The SAP will be released once
the last client is gone, leaving it available to other services.
Signed-off-by: NSamuel Ortiz <sameo@linux.intel.com>

With not Well Known Services there is no guarantees as to which
SSAP the server will be listening on, so there is no reason to
support binding to a specific source SAP.
Signed-off-by: NSamuel Ortiz <sameo@linux.intel.com>

This patch fixes a typo and return the correct error when trying to
bind 2 sockets to the same service name.
Signed-off-by: NSamuel Ortiz <sameo@linux.intel.com>

The LLCP SAP should only be freed when the socket owning it is released.
As long as the socket is alive, the SAP should be reserved in order to
e.g. send the right wks array when bringing the MAC up.
Signed-off-by: NSamuel Ortiz <sameo@linux.intel.com>

When the MAC link goes down, we should only keep the bound sockets
alive. They will be closed by sock_release or when the underlying
NFC device is moving away.
Signed-off-by: NSamuel Ortiz <sameo@linux.intel.com>

Drivers will need them before starting a poll or when being activated
as targets. Mostly WKS can have changed between device registration and
then so we need to re-build the whole array.
Signed-off-by: NSamuel Ortiz <sameo@linux.intel.com>

Set the right target index and use a better socket declaration routine.
Signed-off-by: NSamuel Ortiz <sameo@linux.intel.com>

Getting a valid CONNECT means we have a valid target index.
Signed-off-by: NSamuel Ortiz <sameo@linux.intel.com>

Signed-off-by: NSamuel Ortiz <sameo@linux.intel.com>

Signed-off-by: NSamuel Ortiz <sameo@linux.intel.com>

Some NFC chips will statically create and open pipes for both standard
and proprietary gates. The driver can now pass this information to HCI
such that HCI will not attempt to create and open them, but will instead
directly use the passed pipe ids.
Signed-off-by: NEric Lapuyade <eric.lapuyade@intel.com>
Signed-off-by: NSamuel Ortiz <sameo@linux.intel.com>

If the device is polling we sent a 0 target found event.
Signed-off-by: NEric Lapuyade <eric.lapuyade@intel.com>
Signed-off-by: NSamuel Ortiz <sameo@linux.intel.com>

The semantics for a zero target found event is that the polling operation
could not complete.
Signed-off-by: NEric Lapuyade <eric.lapuyade@intel.com>
Signed-off-by: NSamuel Ortiz <sameo@linux.intel.com>

There can ever be only one call to nfc_targets_found() after polling
has been engaged. This could be from a target discovered event from
the driver, or from an error handler to notify poll will never complete.
Signed-off-by: NEric Lapuyade <eric.lapuyade@intel.com>
Signed-off-by: NSamuel Ortiz <sameo@linux.intel.com>

If there is an ongoing HCI command executing, it will be completed,
thereby pushing the error up to the core. Otherwise, HCI will directly
notify the core with the error.
Signed-off-by: NEric Lapuyade <eric.lapuyade@intel.com>
Signed-off-by: NSamuel Ortiz <sameo@linux.intel.com>

HCI cmd can be completed either from an HCI response or from an
internal driver or HCI error. This requires to factorize the
completion code outside of the device lock.
Signed-off-by: NEric Lapuyade <eric.lapuyade@intel.com>
Signed-off-by: NSamuel Ortiz <sameo@linux.intel.com>

This API should be used by drivers, HCI, SHDLC or NCI stacks to report an
unrecoverable error.
Signed-off-by: NEric Lapuyade <eric.lapuyade@intel.com>
Signed-off-by: NSamuel Ortiz <sameo@linux.intel.com>

An HCI command can complete either from an HCI response
(with an HCI result) or as a consequence of any other system
error during processing. The completion therefore needs to take
a standard errno code. The HCI response will convert its result
to a standard errno before calling the completion.
Signed-off-by: NEric Lapuyade <eric.lapuyade@intel.com>
Signed-off-by: NSamuel Ortiz <sameo@linux.intel.com>