- 06 2月, 2012 2 次提交
-
-
由 Takashi Iwai 提交于
sparse complains that "spec->multiout.dac_nids" is a pointer. sound/pci/hda/patch_realtek.c:2321:37: error: incompatible types for operation (>) sound/pci/hda/patch_realtek.c:2321:37: left side has type unsigned short const [usertype] *dac_nids sound/pci/hda/patch_realtek.c:2321:37: right side has type int It was meant to be num_dacs instead of dac_nids. Although the current code still works as expected (when num_dacs is zero, dac_nids should be NULL, too), better to fix now, of course. Reported-by: NDan Carpenter <dan.carpenter@oracle.com> Cc: David Henningsson <david.henningsson@canonical.com> Signed-off-by: NTakashi Iwai <tiwai@suse.de>
-
由 Jesper Juhl 提交于
The header 'linux/moduleparam.h' is included twice in 'sound/isa/sb/emu8000_patch.c'. Once is enough. Signed-off-by: NJesper Juhl <jj@chaosbits.net> Signed-off-by: NTakashi Iwai <tiwai@suse.de>
-
- 03 2月, 2012 1 次提交
-
-
由 Takashi Iwai 提交于
The recent changes in Realtek auto-parser added the new "Bass Speaker" and "CLFE" mixer elements which should be tracked as vmaster slaves, too. Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=42720Signed-off-by: NTakashi Iwai <tiwai@suse.de>
-
- 02 2月, 2012 4 次提交
-
-
由 Takashi Iwai 提交于
Since the dynamic pin power-control and the analog low-current mode may lead to pop-noise, it's safer to set it off as default. Bugzilla: https://bugzilla.novell.com/show_bug.cgi?id=741128 Cc: <stable@kernel.org> [v3.1+] Signed-off-by: NTakashi Iwai <tiwai@suse.de>
-
由 Takashi Iwai 提交于
VIA codecs have several different power-saving features, and one of them is the analog low-current mode. But it turned out that the ALC mode causes pop-noises at each on/off time on some machines. As a quick workaround, disable the ALC when another power-saving feature, the dynamic pin power-control, is turned off, too, since the dynamic power-control is already exposed as a mixer enum element so that user can turn it on/off freely. Bugzilla: https://bugzilla.novell.com/show_bug.cgi?id=741128 Cc: <stable@kernel.org> [v3.1+] Signed-off-by: NTakashi Iwai <tiwai@suse.de>
-
由 Takashi Iwai 提交于
The analog low-current mode must be enabled when the no stream is running but the current detection checks it in a wrong way. Bugzilla: https://bugzilla.novell.com/show_bug.cgi?id=741128 Cc: <stable@kernel.org> [v3.1+] Signed-off-by: NTakashi Iwai <tiwai@suse.de>
-
由 Takashi Iwai 提交于
Instead of always writing AC_VERB_SET_POWER_STATE, check the current power-state and don't write again if the value is already set. This may reduce the click noise upon the dynamic power-state change (e.g. in analog-input mixer). Signed-off-by: NTakashi Iwai <tiwai@suse.de>
-
- 01 2月, 2012 2 次提交
-
-
由 David Henningsson 提交于
This typo caused the wrong codec's nid to be checked for wcaps type. As a result, sometimes speakers would duplicate the output sent to HDMI output. Cc: stable@kernel.org BugLink: https://bugs.launchpad.net/bugs/924320Signed-off-by: NDavid Henningsson <david.henningsson@canonical.com> Signed-off-by: NTakashi Iwai <tiwai@suse.de>
-
由 Dylan Reid 提交于
If cs_automic is called twice (like it is during init) while the mic is present, it will over-write the last_input with the new one, causing it to switch back to the automic input when the mic is unplugged. This leaves the driver in a state (cur_input, last_input, and automix_idx the same) where the internal mic can not be selected until it is rebooted without the mic attached. Check that the mic hasn't already been switched to before setting last_input. Signed-off-by: NDylan Reid <dgreid@chromium.org> Cc: <stable@kernel.org> Signed-off-by: NTakashi Iwai <tiwai@suse.de>
-
- 31 1月, 2012 3 次提交
-
-
由 Takashi Iwai 提交于
-
由 David Henningsson 提交于
The user reports that model=auto works better than current handling on a 3.2 based kernel (with jack detection patches backported). Since model=auto is what we prefer these days anyway, the quirk should be removed. Alsa-info for the relevant machine: https://bugs.launchpad.net/ubuntu/+source/linux/+bug/923316/+attachment/2702812/+files/alsa-info.txt.Pbfno2x7bp BugLink: https://bugs.launchpad.net/bugs/923316Signed-off-by: NDavid Henningsson <david.henningsson@canonical.com> Signed-off-by: NTakashi Iwai <tiwai@suse.de>
-
由 David Henningsson 提交于
If a codec has both a front and a rear Line In, two controls both named "Line Jack" will be created, which causes parsing to fail. While a long term solution might be to name the jacks differently, this extra check is consistent with what is already being done in many auto-parsers, and will also protect against other cases when two inputs have the same label. BugLink: https://bugs.launchpad.net/bugs/923409Signed-off-by: NDavid Henningsson <david.henningsson@canonical.com> Signed-off-by: NTakashi Iwai <tiwai@suse.de>
-
- 30 1月, 2012 4 次提交
-
-
由 Takashi Iwai 提交于
It turned out that other ASUS laptops require the similar fix to enable the VREF on the pin 0x0f for the secret output amp, not only ASUS A6Rp. Moreover, it's required even when the pin is being used as the output. Thus, writing a fixed value doesn't work always. This patch applies the VREF-fix for all ASUS laptops with ALC861/660 in a fixup function that checks the current value and turns on only the VREF value no matter whether input or output direction is set. The automute function is modified as well to keep the pin VREF upon muting/unmuting via pin-control; otherwise the pin VREF is reset at plugging/unplugging a jack. Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=42588 Cc: <stable@kernel.org> [v3.2+] Signed-off-by: NTakashi Iwai <tiwai@suse.de>
-
git://git.kernel.org/pub/scm/linux/kernel/git/broonie/sound由 Takashi Iwai 提交于
A bunch of small driver specific fixes - nothing terribly exciting here, all of this will only affect people using particular devices and then usually only in some use cases.
-
由 Denis 'GNUtoo' Carikli 提交于
The Openmoko GTA01 machine has been removed from the machine ID database, so we need to remove references to it as well. Without that fix we have: sound/soc/samsung/neo1973_wm8753.c: In function ‘neo1973_wm8753_init’: sound/soc/samsung/neo1973_wm8753.c:325:2: error: implicit declaration of function ‘machine_is_neo1973_gta01’ Signed-off-by: NDenis 'GNUtoo' Carikli <GNUtoo@no-log.org> Signed-off-by: NMark Brown <broonie@opensource.wolfsonmicro.com>
-
由 Axel Lin 提交于
This fixes below build warning when CONFIG_PCI is not set. CC sound/sound_core.o In file included from sound/sound_core.c:15: include/sound/core.h:454: warning: 'struct pci_dev' declared inside parameter list include/sound/core.h:454: warning: its scope is only this definition or declaration, which is probably not what you want Signed-off-by: NAxel Lin <axel.lin@gmail.com> Signed-off-by: NTakashi Iwai <tiwai@suse.de>
-
- 28 1月, 2012 1 次提交
-
-
由 UK KIM 提交于
Signed-off-by: NUK KIM <w0806.kim@samsung.com> Signed-off-by: NMark Brown <broonie@opensource.wolfsonmicro.com> Cc: stable@vger.kernel.org
-
- 27 1月, 2012 2 次提交
-
-
由 David Henningsson 提交于
The user reports that he needs to add model=auto for audio to work properly. In fact, since node 0x15 is not even a pin node, the existing fixup is definitely wrong. Relevant information can be found in the buglink below. Cc: stable@kernel.org (3.2+) BugLink: https://bugs.launchpad.net/bugs/918254Signed-off-by: NDavid Henningsson <david.henningsson@canonical.com> Signed-off-by: NTakashi Iwai <tiwai@suse.de>
-
由 Mark Brown 提交于
For optimal performance the single ended line outputs require that the line output VMID buffer be enabled. Signed-off-by: NMark Brown <broonie@opensource.wolfsonmicro.com> Cc: stable@vger.kernel.org
-
- 26 1月, 2012 5 次提交
-
-
由 Takashi Iwai 提交于
The very same problem is seen on Haier W18 laptop with ALC861 as seen on ASUS A6Rp, which was fixed by the commit 3b25eb69. Now we just need to add a new SSID entry pointing to the same fixup. Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=42656 Cc: <stable@kernel.org> [v3.2+] Signed-off-by: NTakashi Iwai <tiwai@suse.de>
-
由 Mark Brown 提交于
Otherwise we won't resync later. Signed-off-by: NMark Brown <broonie@opensource.wolfsonmicro.com>
-
由 Mark Brown 提交于
Otherwise we won't resync later. Signed-off-by: NMark Brown <broonie@opensource.wolfsonmicro.com>
-
由 Mark Brown 提交于
Otherwise we won't resync later. Signed-off-by: NMark Brown <broonie@opensource.wolfsonmicro.com>
-
由 Mark Brown 提交于
We need to write the configuration for each microphone to a different register. Signed-off-by: NMark Brown <broonie@opensource.wolfsonmicro.com> Cc: stable@vger.kernel.org
-
- 25 1月, 2012 3 次提交
-
-
由 Mark Brown 提交于
When we have identified an accessory make sure we've flagged that we've done so in order to make sure we always report buttons and don't continue to polarity flip. Signed-off-by: NMark Brown <broonie@opensource.wolfsonmicro.com>
-
HP laptop models with buggy BIOS are apparently frequent, including machines with different codecs. Set the polarity of the mute led based on the SSID and include an entry for the HP Mini 110-3100. Signed-off-by: NGustavo Maciel Dias Vieira <gustavo@sagui.org> Tested-by: NPredrag Ivanovic <predivan@open.telekom.rs> Cc: <stable@kernel.org> [v3.2+] Signed-off-by: NTakashi Iwai <tiwai@suse.de>
-
由 Takashi Iwai 提交于
The refactoring of Realtek codec driver in 3.2 kernel caused a regression for ASUS A6Rp laptop; it doesn't give any output. The reason was that this machine has a secret master mute (or EAPD) control via NID 0x0f VREF. Setting VREF50 on this node makes the sound working again. Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=42588 Cc: <stable@kernel.org> [v3.2+] Signed-off-by: NTakashi Iwai <tiwai@suse.de>
-
- 24 1月, 2012 7 次提交
-
-
由 Jesper Juhl 提交于
If copy_from_user() does not return 0 we'll leak the memory we allocated for 'params' when that variable goes out of scope. Also a small CodingStyle cleanup: Use braces on both branches of if/else when one branch needs it. Signed-off-by: NJesper Juhl <jj@chaosbits.net> Acked-by: NVinod Koul <vinod.koul@linux.intel.com> Signed-off-by: NTakashi Iwai <tiwai@suse.de>
-
由 Raymond Yau 提交于
- check SDAC bit of AC97 primary codec when create "rear" device 3, "4ch" device 2 and "4ch Duplication" switch as the card need a four channels AC97 codec to support surround40. Signed-off-by: NRaymond Yau <superquad.vortex2@gmail.com> Signed-off-by: NTakashi Iwai <tiwai@suse.de>
-
由 Jesper Juhl 提交于
In wm2000_i2c_probe(), if we take the true branch in " ret = snd_soc_register_codec(&i2c->dev, &soc_codec_dev_wm2000, NULL, 0); if (ret != 0) goto err_fw; " then we'll release_firmware(fw) at the 'err_fw' label. But we've already done that just a few lines above. That's a use-after-free bug. This patch restructures the code so that we always call release_firmware(fw) before leaving the function, but only ever call it once. This means that we have to initialize 'fw' to NULL since some paths may now end up calling it without having called request_firmware(), but since request_firmware() deals gracefully with NULL pointers, we are fine if we just NULL initialize it. Signed-off-by: NJesper Juhl <jj@chaosbits.net> Signed-off-by: NMark Brown <broonie@opensource.wolfsonmicro.com>
-
由 Jesper Juhl 提交于
To print a value of type size_t one should use %zd, not %d. Signed-off-by: NJesper Juhl <jj@chaosbits.net> Signed-off-by: NMark Brown <broonie@opensource.wolfsonmicro.com>
-
由 Takashi Iwai 提交于
The recent change of the power-widget handling for IDT codecs caused the silent output from the docking-station line-out jack. This was partially fixed by the commit f2cbba76 "ALSA: hda - Fix the lost power-setup of seconary pins after PM resume". But the line-out on the docking-station is still silent when booted with the jack plugged even by this fix. The remainig bug is that the power-widget is set off in stac92xx_init() because the pins in cfg->line_out_pins[] aren't checked there properly but only hp_pins[] are checked in is_nid_hp_pin(). This patch fixes the problem by checking both HP and line-out pins and leaving the power-map correctly. Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=42637 Cc: <stable@kernel.org> Signed-off-by: NTakashi Iwai <tiwai@suse.de>
-
由 David Henningsson 提交于
The user reports that model=auto works fine for him. Using model=auto bring in new features such as jack detection notification to userspace. Alsa info is available at http://paste.ubuntu.com/805351/Signed-off-by: NDavid Henningsson <david.henningsson@canonical.com> Signed-off-by: NTakashi Iwai <tiwai@suse.de>
-
由 Takashi Iwai 提交于
The commit 2ae66c26 ALSA: hda: option to enable arbitrary buffer/period sizes introduced a regression on machines with Intel controller and Nvidia HDMI. The reason is that the driver modifies the global variable align_buffer_size when an Intel controller is found, and the Nvidia HDMI controller is probed after Intel although Nvidia chips require the aligned buffers. This patch fixes the problem by moving the flag into the local struct so that it's not affected by other controllers. Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=42567 Cc: <stable@kernel.org> Signed-off-by: NTakashi Iwai <tiwai@suse.de>
-
- 23 1月, 2012 1 次提交
-
-
由 Mark Brown 提交于
We should be allowing a 5ms delay after the charge pump is started in order to ensure it has finished ramping. Signed-off-by: NMark Brown <broonie@opensource.wolfsonmicro.com> Cc: stable@kernel.org
-
- 21 1月, 2012 1 次提交
-
-
由 Fabio Estevam 提交于
On a mx28evk board the following errors happens on mxs-sgtl5000 probe: [ 0.660000] saif0_clk_set_rate: divider writing timeout [ 0.670000] mxs-sgtl5000: probe of mxs-sgtl5000.0 failed with error -110 [ 0.670000] ALSA device list: [ 0.680000] No soundcards found. This timeout happens because clk_set_rate will result in writing to the DIV bits of register HW_CLKCTRL_SAIF0 with the saif clock gated (CLKGATE bit set to one). MX28 Reference states the following about CLKGATE: "The DIV field can change ONLY when this clock gate bit field is low." So call clk_prepare_enable prior to clk_set_rate to fix this problem. After this change the mxs-saif driver can be correctly probed and audio is functional. Signed-off-by: NFabio Estevam <fabio.estevam@freescale.com> Signed-off-by: NMark Brown <broonie@opensource.wolfsonmicro.com>
-
- 20 1月, 2012 4 次提交
-
-
由 Mark Brown 提交于
With a low frequency SYSCLK and a fast I2C clock register synchronisation may occasionally take too long to take effect, causing I/O issues. Disable synchronisation in order to avoid any issues. Signed-off-by: NMark Brown <broonie@opensource.wolfsonmicro.com> Cc: stable@kernel.org
-
由 Mark Brown 提交于
These are all to either uncached registers or fixes to register defaults, in the former case the cache won't do anything and in the latter case we're fixing things so the cache sync will do the right thing. Signed-off-by: NMark Brown <broonie@opensource.wolfsonmicro.com> Cc: stable@kernel.org
-
由 Mark Brown 提交于
Writing to the registers won't work if we do actually manage to hit a fully powered off state. Signed-off-by: NMark Brown <broonie@opensource.wolfsonmicro.com> Cc: stable@kernel.org
-
由 Wolfram Sang 提交于
Register LDOCTLEN must always be initialized to clear the analog power control bit, otherwise the analog block will stay deactivated. Signed-off-by: NWolfram Sang <w.sang@pengutronix.de> Acked-by: NJavier Martin <javier.martin@vista-silicon.com> Signed-off-by: NMark Brown <broonie@opensource.wolfsonmicro.com>
-