- 20 Sep, 2018 14 commits
-
-
Connor McAdams authored
This patch adds the input selection commands for the Sound BlasterX AE-5. Signed-off-by:
Connor McAdams <conmanx360@gmail.com> Signed-off-by:
Takashi Iwai <tiwai@suse.de>
-
Connor McAdams authored
This patch adds output selection commands for the AE-5. Signed-off-by:
-
Connor McAdams authored
This patch cleans up ca0132_alt_out_select by moving the card specific output commands into a separate function. As more cards are added, the function ca0132_alt_out_select is going to get more bloated with these, so moving into a separate function tries to keep that from happening. Signed-off-by:
-
Connor McAdams authored
This patch adds DSP setup functions for the AE-5. Signed-off-by:
-
Connor McAdams authored
This patch cleans up some of the formatting of the post-dsp load setup functions, and also merges some of the sub functions into individual ones. Signed-off-by:
-
Connor McAdams authored
The Recon3D, AE-5, Z and ZxR all share the same firmware file. Rename this from the specific "ctefx-sbz.bin" to "ctefx-desktop.bin" and set the AE-5 and Recon3D to use it as well. Signed-off-by:
-
Connor McAdams authored
This patch adds AE-5 specific stuff to the ca0132_alt_init function. Signed-off-by:
-
Connor McAdams authored
This patch adds AE-5 pre-init functions that happen before the main ca0132_alt_init, and gives functions related to the ca0113 a ca0113 prefix instead of ca0132. It also adds functions to write to the 8051's SFRs, and to write the special ca0113 commands for the AE-5. Signed-off-by:
-
Connor McAdams authored
This patch adds the unique writes for the AE-5 on startup to ca0132_mmio_init. The other cards share some addresses written to, but use different values. Signed-off-by:
-
Connor McAdams authored
This patch sets the bool values for the AE-5, as well as selects the mixer it will use. Signed-off-by:
-
Connor McAdams authored
This patch adds the pincfg for the Sound BlasterX AE-5, and cleans up the function it's assigned in. Signed-off-by:
-
Connor McAdams authored
This patch adds the PCI subsys ID quirk for the Sound BlasterX AE-5. Signed-off-by:
-
Connor McAdams authored
This patch defines some new verbs found from reverse engineering of the onboard 8051 CPU, and a control param found there as well. This clears up usage of these verbs in other parts of the driver, and removes their usage where they're now known to be unnecessary. Signed-off-by:
-
Nick Simonov authored
snd_pcm_ops are not supposed to change. So mark the non-const structs as const. Also, refine indentation to ncrease readability. Signed-off-by:
Nick Simonov <nicksimonovv@gmail.com> Reviewed-by:
Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com> Signed-off-by:
-
- 14 Sep, 2018 1 commit
-
-
Gustavo A. R. Silva authored
Replace "fallthru" with a proper "fall through" annotation. This fix is part of the ongoing efforts to enabling -Wimplicit-fallthrough Signed-off-by:
Gustavo A. R. Silva <gustavo@embeddedor.com> Signed-off-by:
-
- 13 Sep, 2018 1 commit
-
-
Takashi Iwai authored
The interrupt handler has to be acquired after the other resource initialization when allocated with IRQF_SHARED. Otherwise it's triggered before the resource gets ready, and may lead to unpleasant behavior. Signed-off-by:
-
- 11 Sep, 2018 1 commit
-
-
Anders Roxell authored
When CONFIG_X86=n function azx_snoop doesn't use the variable chip it only returns true. sound/pci/hda/hda_intel.c: In function ‘dma_alloc_pages’: sound/pci/hda/hda_intel.c:2002:14: warning: unused variable ‘chip’ [-Wunused-variable] struct azx *chip = bus_to_azx(bus); ^~~~ Create a inline function of azx_snoop. Fixes: a41d1224 ("ALSA: hda - Embed bus into controller object") Signed-off-by:Anders Roxell <anders.roxell@linaro.org> Signed-off-by:
-
- 10 Sep, 2018 1 commit
-
-
Ricardo Biehl Pasquali authored
This ensures the transfer loop won't waste a run to read the few frames (if any) between start and hw_ptr update. It will wait for the next interrupt with wait_for_avail(). Signed-off-by:
Ricardo Biehl Pasquali <pasqualirb@gmail.com> Signed-off-by:
-
- 04 Sep, 2018 6 commits
-
-
Takashi Iwai authored
Signed-off-by: -
Takashi Iwai authored
We shouldn't set up the indirect PCM parameters at trigger but they should be set at prepare. Also, remove a useless debug message, too. Reviewed-by:
Takashi Sakamoto <o-takashi@sakamocchi.jp> Signed-off-by:
-
Takashi Iwai authored
The recently introduced PCM info flag assures the call of ack ops at each applptr change, and this is mandatory for the indirect PCM helpers. Reviewed-by:
-
Takashi Iwai authored
The recently introduced PCM info flag assures the call of ack ops at each applptr change, and this is mandatory for the indirect PCM helpers. Reviewed-by:
-
Takashi Iwai authored
The recently introduced PCM info flag assures the call of ack ops at each applptr change, and this is mandatory for the indirect PCM helpers. Also, with the proper ack callback, we need no longer prefill at trigger start. The relevant code can be killed. Reviewed-by:
-
Takashi Iwai authored
The recently introduced PCM info flag assures the call of ack ops at each applptr change, and this is mandatory for the indirect PCM helpers. Also, with the proper ack callback, we need no longer prefill at trigger start. The relevant code can be killed. Reviewed-by:
-
- 03 Sep, 2018 3 commits
-
-
Keyon Jie authored
E.g. for snd_hdac_ext_link_clear_stream_id(), we should set (1 << stream) as mask, and 0 as value, here correct it and several similar mismatches. And, here also remove unreadable register_mask usage for those mask value updating. Signed-off-by:
Keyon Jie <yang.jie@linux.intel.com> Signed-off-by:
-
Rob Herring authored
In preparation to remove the node name pointer from struct device_node, convert printf users to use the %pOFn format specifier. Signed-off-by:
Rob Herring <robh@kernel.org> Signed-off-by:
-
Takashi Iwai authored
syzbot reported the uninitialized value exposure in certain situations using virmidi loop. It's likely a very small race at writing and reading, and the influence is almost negligible. But it's safer to paper over this just by replacing the existing kvmalloc() with kvzalloc(). Reported-by: syzbot+194dffdb8b22fc5d207a@syzkaller.appspotmail.com Signed-off-by:
-
- 30 Aug, 2018 4 commits
-
-
Takashi Iwai authored
Merge tag 'hda-codec-h-move' of git://git.kernel.org/pub/scm/linux/kernel/git/broonie/sound into for-next ALSA: Move hda_codec.h to include/sound For easier sharing with ASoC.
-
Pierre-Louis Bossart authored
As suggested by Takashi, move this header file to make it easier to include from e.g. the Intel Skylake driver in follow-up patches Signed-off-by:
Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com> Signed-off-by:
Mark Brown <broonie@kernel.org>
-
Takashi Iwai authored
On AMD/ATI controllers, the HD-audio controller driver allows a bus reset upon the error recovery, and its procedure includes the cancellation of pending jack polling work as found in snd_hda_bus_codec_reset(). This works usually fine, but it becomes a problem when the reset happens from the jack poll work itself; then calling cancel_work_sync() from the work being processed tries to wait the finish endlessly. As a workaround, this patch adds the check of current_work() and applies the cancel_work_sync() only when it's not from the jackpoll_work. This doesn't fix the root cause of the reported error below, but at least, it eases the unexpected stall of the whole system. Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=200937 Cc: <stable@vger.kernel.org> Cc: Lukas Wunner <lukas@wunner.de> Signed-off-by:
-
Takashi Iwai authored
Currently the jackpoll_ms option value is passed indirectly by referring to an array in chip->jackpoll_ms although each card needs to see only the assigned value. Also, the sanity check is done at each time in get_jackpoll_interval() although basically jackpoll_ms option is a read-only, hence we need to evaluate only once at probe time. This patch is the code simplification about the above points: the jack polling interval is directly set to chip->jackpoll_interval so that it can be simply copied to each codec. No functional change but only code reduction. Signed-off-by:
-
- 28 Aug, 2018 9 commits
-
-
Takashi Iwai authored
The HDMI LPE audio driver requires the non-cached page allocations for its buffers. With the recent support of SNDRV_DMA_TYPE_DEV_UC type, we can reduce lots of codes in the driver side and let the memalloc core doing it properly. Signed-off-by: -
Takashi Iwai authored
intel8x0 driver requires the non-cached pages for 440MX workaround, and this can be implemented more easily with the new memalloc type, SNDRV_DMA_TYPE_DEV_UC. This allows us to reduce lots of code. Signed-off-by: -
Takashi Iwai authored
Since we dropped the memory page fiddling in the own allocators in hda_intel.c, the substream allocation and free ops in both hda_intel.c and hda_tegra.c became nothing but the simple calls of the standard snd_pcm_lib helpers. As both are identical, there is no longer need for indirect calls via ops; it's a good opportunity for removing ops and simplifying the codes. Signed-off-by: -
Takashi Iwai authored
Now the ALSA memory allocator helper supports the new non-cached pages, let's use the new type, SNDRV_DMA_TYPE_DEV_UC_SG, for HD-audio driver. This allows us to reduce lots of codes. As another positive side-effect by this patch, the long-standing issue with non-snoop mode playing in the non-mmap mode is fixed. The core memalloc helper does the proper pgprot setup for non-cached pages for vmap(), which was missing in the past. Reported-and-tested-by:
Hans Hu <HansHu@zhaoxin.com> Signed-off-by:
-
Takashi Iwai authored
Introduce a new flag, uc_buffer, to indicate that the controller requires the non-cached pages for stream buffers, either as a chip-specific requirement or specified via snoop=0 option. This improves the code-readability. Also, this patch fixes the incorrect behavior for C-Media chip where the stream buffers were never handled as non-cached due to the check of driver_type even if you pass snoop=0 option. Signed-off-by: -
Takashi Iwai authored
In some cases (mainly for x86), we need the DMA coherent buffer with non-cached pages. Although this has been done in each driver side like HD-audio and intel8x0, it can be done cleaner in the core memory allocator. This patch adds the new types, SNDRV_DMA_TYPE_DEV_UC and SNDRV_DMA_TYPE_DEV_UC_SG, for allocating such non-cached buffer pages. On non-x86 architectures, they work as same as the standard SNDRV_DMA_TYPE_DEV and *_SG. One additional change by this move is that we can assure to pass the non-cached pgprot to the vmapped buffer, too. It eventually fixes the case like non-snoop mode without mmap access on HD-audio. Signed-off-by: -
Takashi Iwai authored
snd_malloc_dev_pages() and snd_free_dev_pages() are local functions and the parameters passed there are all contained in snd_dma_buffer object. As a code-simplification, pass snd_dma_buffer object and assign the address there like other allocators do (except for snd_malloc_pages() which is called from outside, hence we can't change easily). Only code refactoring, no functional changes. Signed-off-by: -
Takashi Iwai authored
The size passed to dma_alloc_coherent() doesn't have to be aligned with power-of-two, rather it should be the raw size. As a minor optimization, remove the size adjustment in the current code. Signed-off-by: -
Takashi Iwai authored
snd_seq_system_client_init() doesn't check the errors returned from its port creations. Let's do it properly and handle the error paths. Signed-off-by:
-
