Skip to content

cloud-kernel
cloud-kernel

openanolis / cloud-kernel
大约 1 年 前同步成功

通知 154
Star 36
Fork 7
cloud-kernel
cloud-kernel

体验新版 GitCode，发现更多精彩内容 >>

切换分支/标签
  1. 17 5月, 2013 4 次提交
    • A
      staging/solo6x10: depend on CONFIG_FONTS · 8c090cfb
      由 Arnd Bergmann 提交于 
      The new SOLO6X10 driver needs the built-in console fonts, specifically
the VGA8x16 font and building it without console support results in
a link error error.

drivers/built-in.o: In function `solo_osd_print':
 :(.text+0x7d3424): undefined reference to `find_font'

This adds a dependency on the CONFIG_FONTS symbol and changes the
console code to always build the base driver even if there are
no specific fonts built-in.

Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Hans Verkuil <hans.verkuil@cisco.com>
Cc: Mauro Carvalho Chehab <mchehab@infradead.org>
Signed-off-by: NArnd Bergmann <arnd@arndb.de>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>
      8c090cfb
    • A
      staging/drm: imx: add missing dependencies · fcce7680
      由 Arnd Bergmann 提交于 
      The imx DRM driver needs a couple of extra Kconfig dependencies
to avoid random build failures:

drivers/staging/imx-drm/ipuv3-crtc.c:448:
 undefined reference to `ipu_idmac_put'
 drivers/staging/imx-drm/ipuv3-crtc.c:450: undefined reference to
 `ipu_dmfc_put' drivers/staging/imx-drm/ipuv3-crtc.c:452:
 undefined reference to `ipu_dp_put'
 drivers/staging/imx-drm/ipuv3-crtc.c:454: undefined reference to
 `ipu_di_put'
drivers/built-in.o: In function `ipu_probe':
 :(.text+0x4b4174): undefined reference to `device_reset'
drivers/built-in.o: In function `imx_tve_probe':
 drivers/staging/imx-drm/imx-tve.c:648: undefined reference to
 `devm_regmap_init_mmio_clk'
drivers/built-in.o: In function
 `imx_pd_connector_get_modes':
 drivers/staging/imx-drm/parallel-display.c:78: undefined
 reference to `of_get_drm_display_mode'

Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Shawn Guo <shawn.guo@linaro.org>
Cc: Philipp Zabel <p.zabel@pengutronix.de>
Signed-off-by: NArnd Bergmann <arnd@arndb.de>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>
      fcce7680
    • L
      staging: ste_rmi4: Suppress 'ignoring return value of ‘regulator_enable()' warning · a5017b96
      由 Lee Jones 提交于 
      drivers/staging/ste_rmi4/synaptics_i2c_rmi4.c:
        In function ‘synaptics_rmi4_resume’:
drivers/staging/ste_rmi4/synaptics_i2c_rmi4.c:1090:18:
        warning: ignoring return value of ‘regulator_enable’, declared
        with attribute warn_unused_result [-Wunused-result

Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: devel@driverdev.osuosl.org
Acked-by: NSrinidhi Kasagar <srinidhi.kasagar@stericsson.com>
Signed-off-by: NLee Jones <lee.jones@linaro.org>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>
      a5017b96
    • R
      staging: sep: fix driver build and kconfig · ab2273c6
      由 Randy Dunlap 提交于 
      Fix build errors in staging/sep/ by making DX_SEP depend on
CRYPTO.

drivers/built-in.o: In function `sep_sha1_init':
sep_crypto.c:(.text+0x245ece): undefined reference to `crypto_enqueue_request'
drivers/built-in.o: In function `sep_sha1_update':
sep_crypto.c:(.text+0x245f4f): undefined reference to `crypto_enqueue_request'
drivers/built-in.o: In function `sep_sha1_final':
sep_crypto.c:(.text+0x245fcf): undefined reference to `crypto_enqueue_request'
drivers/built-in.o: In function `sep_sha1_finup':
sep_crypto.c:(.text+0x24604f): undefined reference to `crypto_enqueue_request'
drivers/built-in.o: In function `sep_sha1_digest':
sep_crypto.c:(.text+0x2460de): undefined reference to `crypto_enqueue_request'
drivers/built-in.o:sep_crypto.c:(.text+0x24616e): more undefined references to `crypto_enqueue_request' follow
drivers/built-in.o: In function `sep_crypto_block':
sep_crypto.c:(.text+0x247c81): undefined reference to `ablkcipher_walk_phys'
sep_crypto.c:(.text+0x247e40): undefined reference to `ablkcipher_walk_phys'
drivers/built-in.o: In function `sep_dequeuer':
sep_crypto.c:(.text+0x248ab9): undefined reference to `crypto_dequeue_request'
sep_crypto.c:(.text+0x248afa): undefined reference to `crypto_ahash_type'
sep_crypto.c:(.text+0x248fdf): undefined reference to `crypto_dequeue_request'
drivers/built-in.o: In function `sep_crypto_setup':
(.text+0x24902a): undefined reference to `crypto_init_queue'
drivers/built-in.o: In function `sep_crypto_setup':
(.text+0x24909c): undefined reference to `crypto_register_ahash'
drivers/built-in.o: In function `sep_crypto_setup':
(.text+0x2490c4): undefined reference to `crypto_register_alg'
drivers/built-in.o: In function `sep_crypto_setup':
(.text+0x2490f7): undefined reference to `crypto_unregister_alg'
drivers/built-in.o: In function `sep_crypto_setup':
(.text+0x249118): undefined reference to `crypto_unregister_ahash'
drivers/built-in.o: In function `sep_crypto_takedown':
(.text+0x249176): undefined reference to `crypto_unregister_ahash'
drivers/built-in.o: In function `sep_crypto_takedown':
(.text+0x249197): undefined reference to `crypto_unregister_alg'
Signed-off-by: NRandy Dunlap <rdunlap@infradead.org>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>
      ab2273c6
  3. 14 5月, 2013 9 次提交
    • M
      staging: nvec: cleanup childs on remove · c2b62f60
      由 Marc Dietrich 提交于 
      Disable device functions and unregister notifier if available. The
serio device must not be "kzallocated". Otherwise serio_unregister_port
will fail because the device is already freed.
Signed-off-by: NMarc Dietrich <marvin24@gmx.de>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>
      c2b62f60
    • M
      staging: nvec: implement unregistering of notifiers · 111c1587
      由 Marc Dietrich 提交于 
      This implements the unregistering of notifiers so kernel modules
can be unloaded.
Signed-off-by: NMarc Dietrich <marvin24@gmx.de>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>
      111c1587
    • M
      staging: nvec: add missing module aliases · 99758dec
      由 Marc Dietrich 提交于 
      Keyboard and mouse drivers were missing MODULE_ALIAS
definitions. This fixes auto module loading of these
drivers.
Signed-off-by: NMarc Dietrich <marvin24@gmx.de>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>
      99758dec
    • D
      staging: nvec: remove inline marking of EXPORT_SYMBOL functions · 705a4212
      由 Denis Efremov 提交于 
      EXPORT_SYMBOL and inline directives are contradictory to each other.
The patch fixes this inconsistency.

Found by Linux Driver Verification project (linuxtesting.org).
Signed-off-by: NDenis Efremov <yefremov.denis@gmail.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>
      705a4212
    • I
      staging: comedi: complain if dma buffer allocation not supported · e9166139
      由 Ian Abbott 提交于 
      When allocating a buffer to support asynchronous comedi commands, if a
DMA coherent buffer was requested but `CONFIG_HAS_DMA` is undefined,
bail out of local helper function `__comedi_buf_alloc()` with an error
message.
Signed-off-by: NIan Abbott <abbotti@mev.co.uk>
Reviewed-by: NH Hartley Sweeten <hsweeten@visionengravers.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>
      e9166139
    • I
      staging: comedi: ni_mio_common: only do counter commands for ni_pcimio · bd304a73
      由 Ian Abbott 提交于 
      "ni_mio_common.c" holds common code included by "ni_pcimio.c",
"ni_atmio.c" and "ni_mio_cs.c", including a common initialization
function `ni_E_init()`.  Amongst other things, this initializes some
counter subdevices to support comedi instructions and asynchronous
commands.  However, even though it sets up the handlers to support
asynchronous commands on these subdevices, the handlers will return an
error unless the `PCIDMA` macro is defined (which is defined only in
"ni_pcimio.c").  If the `PCIDMA` macro is not defined, the comedi core
will needlessly allocate buffers to support the asynchronous commands.
Also, `s->async_dma_dir` is set to `DMA_BIDIRECTIONAL`, causing the
physical pages for the buffers to be allocated using
`dma_alloc_coherent()`.

If the comedi core cannot call `dma_alloc_coherent()` because
`CONFIG_HAS_DMA` is not defined, it will fail to allocate the buffers,
which ultimately causes `ni_E_init()` to fail.

Avoid the wastage and prevent the failure by only setting up
asynchronous command support for the counter subdevices if the `PCIDMA`
macro is defined.
Signed-off-by: NIan Abbott <abbotti@mev.co.uk>
Reviewed-by: NH Hartley Sweeten <hsweeten@visionengravers.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>
      bd304a73
    • I
      staging: comedi: work without HAS_DMA · 4efc4bbd
      由 Ian Abbott 提交于 
      The core "comedi" module and the "mite" helper module for NI PCI devices
both have calls to `dma_alloc_coherent()` and `dma_free_coherent()`.
Those functions are only available if `CONFIG_HAS_DMA` is defined.

Apart from the "mite" module, the functions are only called for comedi
drivers that set `s->async_dma_dir` (where `s` is a pointer to a `struct
comedi_subdevice`) to anything other than `DMA_NONE`.

Change local helper functions `__comedi_buf_alloc()` and
`__comedi_buf_free()` to only call `dma_alloc_coherent()` and
`dma_free_coherent()` if `CONFIG_HAS_DMA` is defined.

Change the "Kconfig" to make the following configuration options depend
on `HAS_DMA`:

`COMEDI_MITE` - builds the "mite" module.
`COMEDI_NI_6527` - selects `COMEDI_MITE`.
`COMEDI_NI_65XX` - selects `COMEDI_MITE`.
`COMEDI_NI_670X` - selects `COMEDI_MITE`.
`COMEDI_NI_LABPC_PCI` - selects `COMEDI_MITE`.
`COMEDI_NI_PCIDIO` - selects `COMEDI_MITE`.
`COMEDI_NI_TIOCMD` - selects `COMEDI_MITE`.
`COMEDI_NI_660X` - selects `COMEDI_NI_TIOCMD`,
                   sets `s->async_dma_dir`.
`COMEDI_NI_PCIMIO` - selects `COMEDI_NI_TIOCMD`,
                     sets `s->async_dma_dir`.
Signed-off-by: NIan Abbott <abbotti@mev.co.uk>
Reviewed-by: NH Hartley Sweeten <hsweeten@visionengravers.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>
      4efc4bbd
    • I
      staging: comedi: allow buffer resize if previous resize failed · b3fab427
      由 Ian Abbott 提交于 
      When a comedi device is successfully attached, those subdevices that
support asynchronous commands will have had buffers allocated
successfully.  It is possible to resize the buffers afterwards, but if
the resize fails the subdevice is left with no buffer
(`s->async->prealloc_buf == NULL`).  Currently, this also causes any
subsequent attempts to resize the buffer to fail with an error, which
seems like a bad idea.

Remove the check in `resize_async_buffer()` that causes the resize to
fail if the subdevice currently has no buffer (presumably due to the
failure of a previous resize attempt).  Callers of
`resize_async_buffer()` have already checked that the subdevice is
allowed to have a buffer.
Signed-off-by: NIan Abbott <abbotti@mev.co.uk>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>
      b3fab427
    • H
      staging: comedi: ni_labpc: fix build when VIRT_TO_BUS is not defined · 1581a035
      由 H Hartley Sweeten 提交于 
      After merging the final tree, the next-20130424 build (powerpc
allyesconfig) failed like this:

drivers/staging/comedi/drivers/ni_labpc.c: In function 'labpc_ai_cmd':
drivers/staging/comedi/drivers/ni_labpc.c:980:9: error:
    implicit declaration of function 'virt_to_bus'
   [-Werror=implicit-function-declaration]

The virt_to_bus() is only needed for the ISA DMA support in this driver.

On powerpc, CONFIG_COMEDI_NI_LABPC_ISA cannot be enabled due to the
depends on VIRT_TO_BUS but the PCI driver, ni_labpc_pci, can be enabled.
That driver uses the ni_labpc driver for the common support code shared
by the ISA, PCI, and PCMCIA boards.

The ISA specific support, and the optional ISA DMA support, are currently
still in the common ni_labpc driver. The ISA specific code is protected
by #if IS_ENABLED(CONFIG_COMEDI_NI_LABPC_ISA) and the ISA DMA support
is protected by #ifdef CONFIG_ISA_DMA_API. This allows the ISA support
to be enabled on architectures that support VIRT_TO_BUS and optionally
enables ISA DMA support if ISA_DMA_API is enabled.

Unfortunately, the ISA DMA code uses virt_to_bus(). This results in
the build failure for architectures that enable ISA_DMA_API but do not
have VIRT_TO_BUS.

Add a new member to the private data, dma_addr, to hold the phys_addr_t
returned by virt_to_bus() and initialize it in the ISA specific
labpc_attach().

For architectures that enable ISA_DMA_API but not VIRT_TO_BUS, this
will fix the build error. This is also safe for architectures the
enable both options but don't enable COMEDI_NI_LABPC_ISA because the
dma channel (devpriv->dma_chan) is only initialized in the ISA
specific labpc_attach().
Signed-off-by: NH Hartley Sweeten <hsweeten@visionengravers.com>
Reported-by: NStephen Rothwell <sfr@canb.auug.org.au>
Cc: Ian Abbott <abbotti@mev.co.uk>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>
      1581a035
  5. 13 5月, 2013 1 次提交
  7. 10 5月, 2013 26 次提交