[PATCH] mwifiex: debugfs: remove redunant check of mwifiex_dfs_dir

debugfs_remove already check mwifiex_dfs_dir, so remove it. Signed-off-by: Shawn Lin --- drivers/net/wireless/marvell/mwifiex/debugfs.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/net/wireless/marvell/mwifiex/debugfs.c b/drivers/net/wireless/marvell/mwifiex/de

Re: Question on flushing and deauth frames

On 06/14/2017 11:18 PM, Emmanuel Grumbach wrote: ath10k is a bit weird about flushing frames, and at least my variant of the wave-2 firmware does not always put the deauth frame on the air when deleting stations. It will likely not be much fun to fix this. I was wondering if the code below f

WPA: EAPOL-Key timeout

I am trying to use hostapd to set up a wifi access point on my Beaglebone Black. With no WPA security everything works fine. When I add WPA security, I can't log into my wifi network anymore. This is my /etc/hostapd/hostapd.conf file interface=wlan2 driver=nl80211 ssid=virtual_serial_port_br3

Re: [V3] brcmfmac: Fix glom_skb leak in brcmf_sdiod_recv_chain

Arend van Spriel writes: > On 6/14/2017 11:21 AM, Kalle Valo wrote: >> Arend van Spriel writes: >> >>> On 13-06-17 09:00, Kalle Valo wrote: Arend Van Spriel wrote: > From: "Peter S. Housel" > > An earlier change to this function (3bdae810721b) fixed a leak in the > ca

Re: [PATCH] wireless: brcmfmac: initialize oob irq data before request_irq()

Michał Mirosław writes: > On Wed, Jun 14, 2017 at 07:58:35AM +0300, Kalle Valo wrote: >> Michał Mirosław writes: >> > This fixes spin-forever in irq handler when IRQ is already asserted >> > at request_irq() time. >> > >> > Signed-off-by: Michał Mirosław >> >> Your name in patchwork is broken:

Re: [PATCH 2/6] rsi: use enum for FSM states

Amitkumar Karwar writes: > On Wed, Jun 14, 2017 at 2:43 PM, Kalle Valo wrote: >> amit karwar writes: >> >>> On Tue, Jun 13, 2017 at 12:17 PM, Kalle Valo wrote: >>> Also your name in patchwork is not capitalised (patchwork is idiotic and takes the name from patchwork user data and not

Re: [PATCH v2 08/11] brcmsmac: make some local variables 'static const' to reduce stack size

Arnd Bergmann writes: > With KASAN and a couple of other patches applied, this driver is one > of the few remaining ones that actually use more than 2048 bytes of > kernel stack: > > broadcom/brcm80211/brcmsmac/phy/phy_n.c: In function > 'wlc_phy_workarounds_nphy_gainctrl': > broadcom/brcm80211/

Re: [PATCH] linux-firmware: wilc1000: Add unified firmware for wilc1000 WLAN

On Sat, Jun 03, 2017 at 02:06:41PM +0530, Aditya Shankar wrote: > This commit adds a new unified firmware for the wilc1000 > staging driver with below items addressed. > > - Single firmware supports STA, AP and P2P modes. > - Support suspend/resume on WILC1000. > - Verify PS stability for WILC1000

Re: pull-request mwifiex-firmware 2017-06-05

On Mon, Jun 05, 2017 at 09:50:20AM +, Xinming Hu wrote: > The following changes since commit 47afd9950fbcadeb7cefc093b21d6123bdc76f79: > > linux-firmware: add Marvell USB8997 firmware image (2017-05-02 12:28:34 > +0530) > > are available in the git repository at: > > git://git.marvell.c

Re: linux-next: build failure after merge of the wireless-drivers-next tree

From: Stephen Rothwell Date: Tue, 13 Jun 2017 12:00:24 +1000 > Hi Dave, > > On Thu, 8 Jun 2017 12:27:59 +1000 Stephen Rothwell > wrote: >> >> After merging the wireless-drivers-next tree, today's linux-next build >> (x86_64 allmodconfig) failed like this: >> >> drivers/net/wireless/quantenna/

Re: [for-4.12, 1/3] brcmfmac: add parameter to pass error code in firmware callback

Arend Van Spriel wrote: > Extend the parameters in the firmware callback so it can be called > upon success and failure. This allows the caller to properly clear > all resources in the failure path. Right now the error code is > always zero, ie. success. > > Cc: sta...@vger.kernel.org # 4.9.x- >

Re: [for-4.12] brcmfmac: fix brcmf_fws_add_interface() for USB devices

Arend Van Spriel wrote: > USB devices rely on queuing functionality provided by the fwsignal > module regardless the mode fwsignal is operating in. For this some > data structure needs to be reserved which is tied to the interface, > which is done by brcmf_fws_add_interface(). However, it checks

Re: [PATCH for-4.12 1/3] brcmfmac: add parameter to pass error code in firmware callback

Arend van Spriel writes: > Extend the parameters in the firmware callback so it can be called > upon success and failure. This allows the caller to properly clear > all resources in the failure path. Right now the error code is > always zero, ie. success. > > Cc: sta...@vger.kernel.org # 4.9.x- >

Re: Question on flushing and deauth frames

On Thu, Jun 15, 2017 at 4:32 PM, Ben Greear wrote: > > > On 06/14/2017 11:18 PM, Emmanuel Grumbach wrote: >>> >>> ath10k is a bit weird about flushing frames, and at least my variant of >>> the wave-2 >>> firmware does not always put the deauth frame on the air when deleting >>> stations. >>> >>>

Re: Question on flushing and deauth frames

On 06/15/2017 09:34 AM, Emmanuel Grumbach wrote: On Thu, Jun 15, 2017 at 4:32 PM, Ben Greear wrote: On 06/14/2017 11:18 PM, Emmanuel Grumbach wrote: ath10k is a bit weird about flushing frames, and at least my variant of the wave-2 firmware does not always put the deauth frame on the air wh

Re: [PATCH] nfc: nci: remove unnecessary null check

On Tue, Jun 13, 2017 at 11:37:18AM -0500, Gustavo A. R. Silva wrote: > Remove unnecessary NULL check for pointer conn_info. > conn_info is set in list_for_each_entry() using container_of(), > which is never NULL. > > Addresses-Coverity-ID: 1362349 > Cc: Guenter Roeck > Signed-off-by: Gustavo A. R

Re: Question on flushing and deauth frames

>> >> Keep in mind that this code is also called when roaming, any >> additional operations will slow down the roaming process. Not all the > > > This is a reason to not retransmit, but logically the flush(drop=false) is > supposed to wait for the frame to be transmitted anyway, and at that point,

[PATCH 1/3] NFC: digital: NFC-A SEL_RES must be one byte

Section 4.8.2 (SEL_RES Response) of NFC Forum's NFC Digital Protocol Technical Specification dated 2010-11-17 clearly states that the size of a SEL_RES Response is one byte. Enforce this restriction in the code. Signed-off-by: Mark Greer --- net/nfc/digital_technology.c | 3 ++- 1 file changed,

[PATCH 0/3] NFC: Misc. kernel updates and trf7970a erratum handling

Add a couple minor fixups and remove the trf7970a erratum handling in which the last byte in the response to a Type 5 Read Multiple Blocks command is discarded. That handling is moved to the neard daemon where there is enough context to do it properly. Mark Greer (3): NFC: digital: NFC-A SEL_RE

[PATCH 3/3] Revert "NFC: trf7970a: Handle extra byte in response to Type 5 RMB commands"

This reverts commit ab714817d7e891608d31f6996b1e4c43cf2bf342. The original commit was designed to handle a bug in the trf7970a NFC controller where an extra byte was returned in Read Multiple Blocks (RMB) command responses. However, it has become less clear whether it is a bug in the trf7970a or

[PATCH 2/3] NFC: digital: NFC-DEP Target WT(nfcdep,max) is now 14

Version 1.1 of the NFC Forum's NFC Digital Protocol Technical Specification dated 2014-07-14 specifies that the NFC-DEP Protocol's Target WT(nfcdep,max) value is 14. In version 1.0 it was 8 so change the value in the Linux NFC-DEP Protocol code accordingly. Signed-off-by: Mark Greer --- net/nfc

Re: Question on flushing and deauth frames

On 06/15/2017 10:40 AM, Emmanuel Grumbach wrote: Keep in mind that this code is also called when roaming, any additional operations will slow down the roaming process. Not all the This is a reason to not retransmit, but logically the flush(drop=false) is supposed to wait for the frame to be t

[PATCH 14/23] nfctype5: Add space between 'if' and first '('

Add a space between the 'if' and first parenthesis in 'if' statements as no space is both annoying and contrary to neard coding style. Signed-off-by: Mark Greer --- plugins/nfctype5.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/plugins/nfctype5.c b/plugins/nfctype5.

[PATCH 17/23] nfctype5: Add support for TI Standard and Pro Type 5 tag

Standard and Pro Type 5 tags from Texas Instruments do not support the Get System Information command which means they cannot be read with the current neard code. Fortunately, both types of tags have eight, 4-byte blocks so that information can be filled in instead of issuing the Get System Inform

[PATCH 21/23] nfctype5: Fix formatting

Use the output of the Linux kernel's 'Lindent' script to format the code in nfctype5.c. Some of the formatting performed by Lindent was overridden for various reasons. These include: - no space between '__attribute__' and '((packed))' to match other tag files - struct mem

[PATCH 19/23] nfctype5: Don't issue RMB command when formatting

Currently, when neard is formatting a Type 5 tag, it issues the Read Multiple Blocks (RMB) command to see if the tag supports it. If the command succeeds, the appropriate bit in the CC is set so the RMB command can be used in the future. The problem is that when the tag doesn't support the comman

[PATCH 18/23] nfctype5: Remove useless initialization

There is no point in assigning 'local_data' to 'cookie' when 'cookie' is going to be reassigned before it is used. Signed-off-by: Mark Greer --- plugins/nfctype5.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/plugins/nfctype5.c b/plugins/nfctype5.c index f26d8fa..873ac

[PATCH 23/23] nfc_copy: Update nfc_copy.h to match Linux kernel's version

neard's version of Linux's include/uapi/linux/nfc.h file has become stale so update it to match the most current. The update changes a few macro names which are used by neard so update those names in the neard code as well. Signed-off-by: Mark Greer --- include/nfc_copy.h | 51

[PATCH 11/23] adapter: Do not poll when there is an active tag

When there is an active tag and a request to start polling is received by neard, it will discard the currently registered tag and requests that the kernel start another poll. The kernel receives this request and returns EBUSY because there is already an active tag. neard receives this failure and

[PATCH 04/23] ndef: Verify RTD record type name encodings

The NFC Forum's Record Type Definition (RTD) Technical Specification version 1.0, section 3.4 (RTD Type Names Requirements) specifies that RTD type name encodings MUST be done according to the ASCII chart in Appendix A (Character Set for Record Types). Enforce this by checking that all of the RTD

[PATCH 13/23] nfctype5: Reduce noise when tag is moved out of range

The NFC Type 5 tag code prints a message whenever it receives an error. This makes it extra noisy compared to the other tag types whenever a tag is moved out of range. Instead, reduce that noise by turning the error message into a debug message. Signed-off-by: Mark Greer --- plugins/nfctype5.c

[PATCH 15/23] nfctype5: Remove superfluous parentheses

Remove the superfluous parentheses around calls to t5_manufacturer_stmicro(). Signed-off-by: Mark Greer --- plugins/nfctype5.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/plugins/nfctype5.c b/plugins/nfctype5.c index 29e1d0c..9d09bf8 100644 --- a/plugins/nfctype5.c

[PATCH 00/23] neard: Support TI Std & Pro tags, fixups, etc.

This is an assortment of commits that make some fixups, do some general tightening of NDEF data checking, add support for TI Standard and Pro Type 5 tags, and stop issuing the Read Multiple Blocks command when formatting a Type 5 tag. The reasoning for each change is in the individual commit descr

[PATCH 07/23] adapter: Return '-errno' when socket() call fails

near_adapter_connect() incorrectly returns '-1' when the socket() call fails. Instead, it should return '-errno' which is the real error code. Signed-off-by: Mark Greer --- src/adapter.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/adapter.c b/src/adapter.c index bc29

[PATCH 01/23] ndef: Add default language ("en") for Text records

Despite section 3.3 of the NFC Forum RTD-Text 1.0 Technical Specification stating in part, "The language code MAY NOT be omitted", some tags have a 0-length language field. A 0-length language field currently causes neard to exit which isn't ideal so choose a default language (generic English) whi

[PATCH 16/23] nfctype5: Rework code that identifies ST Micro Type 5 tags

Rework the code that identifies ST Micro Type 5 tags to make it conform better to established coding style in the file and to make it easier to add check for tags from other manufacturers. Signed-off-by: Mark Greer --- plugins/nfctype5.c | 51 +++

[PATCH 03/23] ndef: Unrecognized WKTs should return RECORD_TYPE_UNKNOWN

When get_record_type() doesn't recognize the record type in a record with a Well Known Type TNF, it falls through to the next case clause and returns RECORD_TYPE_MIME_TYPE. This is incorrect so add a break statement to the RECORD_TNF_WELLKNOWN case so that RECORD_TYPE_UNKNOWN is returned. Signed-

[PATCH 09/23] adapter: Clear timeout handle when check presence timer stopped

__near_adapter_stop_check_presence() stops the neard check presence timer but doesn't clear the timer handle. This can cause neard to try to stop the timer when it isn't running. To fix that, clear the handle so neard doesn't try to stop an already stopped timer. Signed-off-by: Mark Greer ---

Re: linux-next: build failure after merge of the wireless-drivers-next tree

Hi Dave, On Thu, 15 Jun 2017 12:08:08 -0400 (EDT) David Miller wrote: > > From: Stephen Rothwell > Date: Tue, 13 Jun 2017 12:00:24 +1000 > > > On Thu, 8 Jun 2017 12:27:59 +1000 Stephen Rothwell > > wrote: > >> > >> After merging the wireless-drivers-next tree, today's linux-next build > >>

[PATCH 05/23] ndef: Discard records containing errors

Currently, near_ndef_parse_msg() adds records even when they contain erroneous record types. This can later cause neard to exit when it tries to signal dbus with incomplete record information. Avoid this by ignoring records that contain bad record types (and all of the records that follow in the

[PATCH 10/23] adapter: Clear timer handle when DEP timer stopped

__near_adapter_set_dep_state() stops the neard DEP timer but doesn't clear the timer handle. This can cause neard to try to stop the timer when it isn't running. To fix that, clear the handle so neard doesn't try to stop an already stopped timer. Signed-off-by: Mark Greer --- src/adapter.c | 4

[PATCH 02/23] ndef: Fix use of uninitialized variable in property_get_type()

The 'type' variable in property_get_type() is never set when the record type is invalid. This means that the check for NULL doesn't work as it should and a bogus string can be appended. Fix this by adding a default case to the switch statement that checks the record type ensuring that 'type' is s

[PATCH 20/23] nfctype5: Discard extra byte in RMB response data

Sometimes there can be an extra byte in the response data for Read Multiple Blocks (RMB) commands so discard it whenever that happens. Signed-off-by: Mark Greer --- plugins/nfctype5.c | 13 ++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/plugins/nfctype5.c b/plugins/

[PATCH 06/23] ndef: Validate text data in WKT Text records

Ensure that the text encodings in WKT Text records are valid. Signed-off-by: Mark Greer --- src/ndef.c | 26 ++ 1 file changed, 22 insertions(+), 4 deletions(-) diff --git a/src/ndef.c b/src/ndef.c index 38dcf72..fb17be9 100644 --- a/src/ndef.c +++ b/src/ndef.c @@ -1149,

[PATCH 22/23] nfctools: Move nciattach macros & enums to nciattach.c

Some header file macros and an enum were copied from Linux and placed in neard's include/nfc_copy.h file. That isn't the proper place as nfc_copy.h is supposed to be a pristine copy of the Linux nfc.h file. Move those header file definitions into tools/nciattach.c since that is the only file that

[PATCH 12/23] nfctype2: Don't read tags with bad magic number

NFC Type 2 tags that have a bad magic number need to be reformatted so do not try to read them. Signed-off-by: Mark Greer --- plugins/nfctype2.c | 1 + 1 file changed, 1 insertion(+) diff --git a/plugins/nfctype2.c b/plugins/nfctype2.c index 559ecb0..f0f1158 100644 --- a/plugins/nfctype2.c +++

[PATCH 08/23] adapter: Return '-errno' when connect() call fails

near_adapter_connect() incorrectly returns '-1' when the connect() call fails. Instead, it should return '-errno' which is the real error code. Signed-off-by: Mark Greer --- src/adapter.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/adapter.c b/src/adapter.c index bfc

[mac80211-next:skb-put-zero 5/5] drivers/net/ppp/ppp_async.c:805:3: error: invalid use of void expression

tree: https://git.kernel.org/pub/scm/linux/kernel/git/jberg/mac80211-next.git skb-put-zero head: f18c9b85b5d68bb029dc1f8c82bae33632d6f485 commit: f18c9b85b5d68bb029dc1f8c82bae33632d6f485 [5/5] networking: make skb_push & __skb_push return void* config: m68k-sun3_defconfig (attached as .config

linux-next: build warning after merge of the wireless-drivers tree

Hi all, After merging the wireless-drivers tree, today's linux-next build (x86_64 allmodconfig) produced this warning: drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c: In function 'brcmf_usb_probe_phase2': drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c:1198:2: warning: 'devinfo'

Re: ath9k_htc - Division by zero in kernel (as well as firmware panic)

Yeah, this is basically mostly copy-pasted from the sboot code, would need some cleaning up. I've been playing more a little with other bits of the hardware, writing some test fw from scratch, mostly without using the builtin rom (except for interrupts). Oleksij Rempel wrote: > Am 08.06.2017 um 00

[PATCH 1/2] NFC: digital: Abort cmd when deactivating target

When deactivating an active target, the outstanding command should be aborted. Signed-off-by: Mark Greer --- net/nfc/digital_core.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/nfc/digital_core.c b/net/nfc/digital_core.c index 0fd5518bf252..145dd74927c4 100644 --- a/net/nfc/digital_co

[PATCH 2/2] NFC: Add NFC_CMD_DEACTIVATE_TARGET support

Once an NFC target (i.e., a tag) is found, it remains active until there is a failure reading or writing it (often caused by the target moving out of range). While the target is active, the NFC adapter and antenna must remain powered. This wastes power when the target remains in range but the cli

[PATCH 0/2] NFC: Add deactivate target functionality

There is currently no way for userspace to deactivate an active target. Since the target is active, the adapter cannot be powered down which wastes wastes power when the target has been read and isn't needed anymore (but remains within range). To solve this, add a way to deactivate a currently act

[PATCH 0/4] neard: Add support for deactivating tags

This series adds the ability for client apps to deactivate a currently active tag. Once deactivated, the client can either poll again to reactivate the tag or power the adapter off to save power. These changes will not work until the Linux kernel commits submitted under the subject, "NFC: Add dea

[PATCH 3/4] tag: Add Tag deactivate support

Once a tag has been discovered, it remains active until it is moved out of range, or an error occurs while reading or writing it. While the tag is active, the adapter cannot be powered off. This wastes power when the client application no longer cares whether the tag is in range or not. To addre

[PATCH 4/4] test: Add option to deactivate tag

Add the 'deactivate' option to test-tag which deactivates the specified tag. Signed-off-by: Mark Greer --- test/test-tag | 13 + 1 file changed, 13 insertions(+) diff --git a/test/test-tag b/test/test-tag index fd80132..cb2c9e8 100755 --- a/test/test-tag +++ b/test/test-tag @@ -11,6

[PATCH 1/4] adapter: Make adapter_start_poll() global

An upcoming commit will need to call adapter_start_poll() from the tag code so make it global. To be consistent with the names of other global routines in adapter.c, add the '__near_' prefix. Signed-off-by: Mark Greer --- src/adapter.c | 22 +++--- src/near.h| 1 + 2 files

[PATCH 2/4] adapter: Add call indicating whether constant poll is enabled

Add a routine that returns a boolean indicating whether the adapter constant poll option is enabled or not. Signed-off-by: Mark Greer --- src/adapter.c | 5 + src/near.h| 1 + 2 files changed, 6 insertions(+) diff --git a/src/adapter.c b/src/adapter.c index e8c7c61..9c483ca 100644 --- a

Re: linux-next: build warning after merge of the wireless-drivers tree

Stephen Rothwell writes: > After merging the wireless-drivers tree, today's linux-next build > (x86_64 allmodconfig) produced this warning: > > drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c: In function > 'brcmf_usb_probe_phase2': > drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c:

Re: ath6kl: fix spelling mistake: "Indicat" -> "Indicate"

Colin Ian King wrote: > Trivial fix to spelling mistake in ath6kl_dbg debug message > > Signed-off-by: Colin Ian King > Reviewed-by: Steve deRosier > Signed-off-by: Kalle Valo Patch applied to ath-next branch of ath.git, thanks. fe611d047e45 ath6kl: fix spelling mistake: "Indicat" -> "Indic

Re: [v3] ath10k: Define structures for CE ctrl/misc register

Sarada Prasanna Garnayak wrote: > Define structures for the copy engine ctrl/misc registers, > that includes CE CMD halt, watermark source, watermark destination, > host IE ring, source, destination and dmax ring. > > This adds support to avoid the conditional compilation, > code optimization an

Re: [1/1] Add per chain RSSI reporting.

Norik Dzhandzhapanyan wrote: > Report per chain RSSI to mac80211. > > Signed-off-by: Norik Dzhandzhapanyan > [kv...@qca.qualcomm.com: fix conflicts and style] > Signed-off-by: Kalle Valo Patch applied to ath-next branch of ath.git, thanks. 8241253d03fe ath10k: add per chain RSSI reporting -