Bernard Blackham [Sun, 21 Oct 2012 19:45:00 +0000 (06:45 +1100)]
staging: usbip: Don't leak struct file.
usbip takes a reference on a struct file which is passed in via
sysfs. Previously, this reference was never cleaned up, although
the socket it referred to was.
This patch drops the corresponding reference (found with the
socket's ->file backpointer) instead of just closing the socket.
Signed-off-by: Bernard Blackham <b-linuxgit@largestprime.net> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Bart Westgeest [Wed, 10 Oct 2012 17:34:25 +0000 (13:34 -0400)]
staging: usbip: replaced pointer arithmetic, and strongly type function return.
Replaced pointer arithmetic by using array indexing, and changed
function return type for usbip_alloc_iso_desc_pdu from 'void*' to
'struct usbip_iso_packet_descriptor'.
Arve Hjønnevåg [Tue, 16 Oct 2012 22:29:53 +0000 (15:29 -0700)]
Staging: android: binder: Add some tracepoints
Add tracepoints:
- ioctl entry and exit
- Main binder lock: lock, locked and unlock
- Command and return buffer opcodes
- Transaction: create and receive
- Transaction buffer: create and free
- Object and file descriptor transfer
- binder_update_page_range
YAMANE Toshiaki [Tue, 9 Oct 2012 13:07:27 +0000 (22:07 +0900)]
staging/comedi: Use pr_ or dev_ printks in drivers/dt9812.c
fixed below checkpatch warnings.
- WARNING: Prefer netdev_err(netdev, ... then dev_err(dev, ... then pr_err(... to printk(KERN_ERR ...
- WARNING: Prefer netdev_info(netdev, ... then dev_info(dev, ... then pr_info(... to printk(KERN_INFO ...
YAMANE Toshiaki [Mon, 8 Oct 2012 12:26:33 +0000 (21:26 +0900)]
staging/comedi: Use dev_ printks in drivers/ii_pci20kc.c
fixed below checkpatch warnings.
- WARNING: Prefer netdev_warn(netdev, ... then dev_warn(dev, ... then pr_warn(... to printk(KERN_WARNING ...
- WARNING: Prefer netdev_info(netdev, ... then dev_info(dev, ... then pr_info(... to printk(KERN_INFO ...
YAMANE Toshiaki [Sat, 6 Oct 2012 05:52:34 +0000 (14:52 +0900)]
staging/comedi: Use dev_ printks in drivers/quatech_daqp_cs.c
fixed below checkpatch warnings.
- WARNING: Prefer netdev_info(netdev, ... then dev_info(dev, ... then pr_info(... to printk(KERN_INFO ...
- WARNING: Prefer netdev_warn(netdev, ... then dev_warn(dev, ... then pr_warn(... to printk(KERN_WARNING ...
- WARNING: Prefer netdev_err(netdev, ... then dev_err(dev, ... then pr_err(... to printk(KERN_ERR ...
- WARNING: Prefer netdev_info(netdev, ... then dev_info(dev, ... then pr_info(... to printk(KERN_INFO ...
- WARNING: Prefer netdev_notice(netdev, ... then dev_notice(dev, ... then pr_notice(... to printk(KERN_NOTICE ...
Ian Abbott [Mon, 15 Oct 2012 12:07:32 +0000 (13:07 +0100)]
staging: comedi: always set hw_dev during auto-config
Auto-configuration (auto-attachment) of USB and PCI comedi devices all
goes through `comedi_auto_config_helper()`. That is a good place to set
the comedi device's `hw_dev` pointer to the hardware `struct device` via
a call to `comedi_set_hw_dev(comedi_device, hardware_device)` as it may
obviate the need for the low-level comedi driver to make this call.
Signed-off-by: Ian Abbott <abbotti@mev.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
The remaining comedi drivers that still have a devpriv macro
are all pretty straight forward for removing the devpriv
macro.
This macro relies on a local variable having a specific name.
Remove its use by replacing it with a local variable where
used.
The inline function alloc_private(), used to kzalloc the
dev->private memory, returns non-zero if there is an error.
Fix all the alloc_private() calls accordingly and remove any
kernel messages or obvious comments that still exist in the
drivers. Leave a comment in the skel driver.
Signed-off-by: H Hartley Sweeten <hsweeten@visionengravers.com> Cc: Ian Abbott <abbotti@mev.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
The ni_mio_common.c file is #include'd by the ni_atmio, ni_mio_cs,
and ni_pcimio drivers. Those drivers all have a devpriv macro of
this type:
This macro relies on a local variable having a specific name.
Remove its use in all the files by replacing it with a local
variable.
Some of the functions in ni_mio_common.c don't always use the
devpriv variable due to differences in how the low-level i/o
is handled by the driver. Tag the variable in those functions
with __maybe_unused to avoid compile warnings.
Signed-off-by: H Hartley Sweeten <hsweeten@visionengravers.com> Cc: Ian Abbott <abbotti@mev.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
This driver only supports a single "boardtype". Remove the unneeded
boardinfo struct and its use in the driver. Change the "driver_name"
to match what the boardinfo supplied.
Signed-off-by: H Hartley Sweeten <hsweeten@visionengravers.com> Cc: Ian Abbott <abbotti@mev.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Dan Carpenter [Tue, 2 Oct 2012 08:26:04 +0000 (11:26 +0300)]
staging: rtl8192u: fix a macro expansion bug
Clang detected this macro expansion bug:
drivers/staging/rtl8192u/r8192U_core.c:2384:76: warning: operator '?:'
has lower precedence than '+'; '+' will be evaluated first
[-Wparentheses]
The line from the .c file looks like this:
u1bAIFS = qos_parameters->aifs[i] * ((mode&(IEEE_G|IEEE_N_24G)) ?9:20) + aSifsTime;
We need to put parenthesis around the entire macro to fix the bug.
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Andres Salomon [Mon, 1 Oct 2012 21:46:11 +0000 (14:46 -0700)]
staging/olpc_dcon: drop pin frobbing code for xo1.5
This code looks in the PCI config space for pin addresses and sets up some
stuff. However, Openfirmware has already done this for us, so there's no
need to ever do it in Linux. According to Mitch Bradley, this OFW has been
doing this for us since at least B3 builds (pre-mass production).
Signed-off-by: Andres Salomon <dilinger@queued.net> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Andres Salomon [Mon, 1 Oct 2012 21:46:01 +0000 (14:46 -0700)]
staging/olpc_dcon: drop fb_notifier code
Previously we registered a notifier block to inform us of any framebuffer
device changes; if the screen was blanked or unblanked, we'd put the DCON
to sleep or wake it up.
Turns out that the backlight code registers a notifier block as well
and calls the update_status hook, so we can just use that to put the DCON
to sleep. For those status updates where the blanking isn't changed,
dcon_sleep will do nothing.
Signed-off-by: Andres Salomon <dilinger@queued.net> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Andres Salomon [Mon, 1 Oct 2012 21:45:50 +0000 (14:45 -0700)]
staging/olpc_dcon: move wait queue into dcon_priv struct
Another global variable (dcon_wait_queue) moved into the dcon_priv struct.
In the process, replace an instance of a manually implemented
wait_event_timeout. This code came from Jordan's original gxfb_dcon.c
driver waaaay back in 2006; well past time for a replacement.
Signed-off-by: Andres Salomon <dilinger@queued.net> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Andres Salomon [Mon, 1 Oct 2012 21:45:37 +0000 (14:45 -0700)]
staging/olpc_dcon: drop useaa module arg
The 'useaa' module parameter was a workaround for a buggy DCON prototype
not supporting the optional anti-aliasing mode properly. There's no
reason to disable it any more, so drop the option.
Signed-off-by: Andres Salomon <dilinger@queued.net> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Kevin McKinney [Fri, 19 Oct 2012 02:40:15 +0000 (22:40 -0400)]
Staging: bcm: Reverse condition in if statement in Misc.c
This patch reverses the condition in two if
statements in CopyBufferToControlPacket to
place Adapter->bShutStatus and
Adapter->idleMode to the left of the equal
"==" sign, and TRUE to the right of
the equal "==" sign. This was done for
readability purposes.
Signed-off-by: Kevin McKinney <klmckinney1@gmail.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Kevin McKinney [Fri, 19 Oct 2012 02:40:14 +0000 (22:40 -0400)]
Staging: bcm: Clean up function CopyBufferToControlPacket in Misc.c
This patch cleans up the code in function
CopyBufferToControlPacket. Several things are
being done here: (1) remove the null
initialization from variable cntrl_buff, (2)
reverse the if statement to check if cntrl_buff
is null; if so, then write debug statement and
return -ENOMEM error code, and (3) indent the
code properly.
Signed-off-by: Kevin McKinney <klmckinney1@gmail.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Kevin McKinney [Sat, 13 Oct 2012 03:49:36 +0000 (23:49 -0400)]
Staging: bcm: Remove unneeded do while loop in InterfaceWRM.
This patch removes an unneeded do while loop which
sends a control message to bcm usb device. In this case,
the loop executes once because usRetries is
initialized to zero. After the first iteration
this variable will be 1. Therefore, the statement:
"usRetries < MAX_RDM_WRM_RETIRES" will evaluate to
false causing the do while statement to execute
once because MAX_RDM_WRM_RETIRES is equal to 1.
Signed-off-by: Kevin McKinney <klmckinney1@gmail.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Kevin McKinney [Sat, 13 Oct 2012 03:49:35 +0000 (23:49 -0400)]
Staging: bcm: Remove unneeded do while loop in InterfaceRDM.
This patch removes an unneeded do while loop which
sends a control message to bcm usb device. In this case,
the loop executes once because usRetries is
initialized to zero. After the first iteration
this variable will be 1. Therefore, the statement:
"usRetries < MAX_RDM_WRM_RETIRES" will evaluate to
false causing the do while statement to execute
once because MAX_RDM_WRM_RETIRES is equal to 1.
Signed-off-by: Kevin McKinney <klmckinney1@gmail.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Kevin McKinney [Sat, 13 Oct 2012 03:49:33 +0000 (23:49 -0400)]
Staging: bcm: Change the style of comparing structures to null in InterfaceMisc.c.
This patch changes the style of comparing
structures to null. Instead of this:
"if (foo == NULL) {" or "if (foo != NULL) {",
the new logic uses: "if (!foo) {" or
"if (foo) {".
Signed-off-by: Kevin McKinney <klmckinney1@gmail.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Now that we have the infrastructure to use the regular function in place
and all existing users are converted, remove the map and unmap callbacks
from the ipack_bus_device->ops.
Previously the *_phys fields were of type ipack_addr_space, which use
void pointers to refer to memory addresses. Since the *_phys fields
refer to unmapped memory, this is not correct. Introduce a new struct
ipack_region (which uses phys_addr_t to refer to the start of a region)
and use that as a replacement for struct ipack_addr_space.
struct ipack_region is defined in ipack.h because it is planned to later
expose the physical addressed to the IPack Module drivers.
projects / linux-beck.git / log