kernel.git/sound/core/memalloc.c, branch linux-5.0.y

ALSA: memalloc: Add fall-through annotation

2018-10-12T07:31:23Z

As a preparatory patch for the upcoming -Wimplicit-fallthrough compiler checks, add the "fall through" annotation in snd_dma_alloc_pages(). Note that this seems necessary to be put exactly before the next label, so it's outside the ifdef block. Signed-off-by: Takashi Iwai

ALSA: memalloc: Add non-cached buffer type

2018-08-28T11:56:47Z

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

ALSA: memalloc: Simplify snd_malloc_dev_pages() calls

2018-08-28T11:56:46Z

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

ALSA: memalloc: Don't align the size to power-of-two

2018-08-28T11:56:46Z

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

ALSA: memalloc: Don't exceed over the requested size

2018-07-23T07:06:33Z

snd_dma_alloc_pages_fallback() tries to allocate pages again when the allocation fails with reduced size. But the first try actually *increases* the size to power-of-two, which may give back a larger chunk than the requested size. This confuses the callers, e.g. sgbuf assumes that the size is equal or less, and it may result in a bad loop due to the underflow and eventually lead to Oops. The code of this function seems incorrectly assuming the usage of get_order(). We need to decrease at first, then align to power-of-two. Reported-and-tested-by: he, bo Reported-by: zhang jun Cc: Signed-off-by: Takashi Iwai

ALSA: core: Follow standard EXPORT_SYMBOL() declarations

2017-06-16T14:19:16Z

Just a tidy up to follow the standard EXPORT_SYMBOL*() declarations in order to improve grep-ability. - Move EXPORT_SYMBOL*() to the position right after its definition - Remove superfluous blank line before EXPORT_SYMBOL*() lines Signed-off-by: Takashi Iwai

genalloc: rename of_get_named_gen_pool() to of_gen_pool_get()

2015-07-01T02:45:01Z

To be consistent with other kernel interface namings, rename of_get_named_gen_pool() to of_gen_pool_get(). In the original function name "_named" suffix references to a device tree property, which contains a phandle to a device and the corresponding device driver is assumed to register a gen_pool object. Due to a weak relation and to avoid any confusion (e.g. in future possible scenario if gen_pool objects are named) the suffix is removed. [sfr@canb.auug.org.au: crypto/marvell/cesa - fix up for of_get_named_gen_pool() rename] Signed-off-by: Vladimir Zapolskiy Cc: Nicolas Ferre Cc: Philipp Zabel Cc: Shawn Guo Cc: Sascha Hauer Cc: Alexandre Belloni Cc: Russell King Cc: Mauro Carvalho Chehab Cc: Vinod Koul Cc: Takashi Iwai Cc: Jaroslav Kysela Signed-off-by: Stephen Rothwell Cc: Herbert Xu Cc: Boris BREZILLON Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds

ALSA: core: Use standard printk helpers

2014-02-14T07:14:15Z

Use dev_err() & co as much as possible. If not available (no device assigned at the calling point), use pr_xxx() helpers instead. Signed-off-by: Takashi Iwai

ALSA: Merge memalloc code into snd-pcm module

2014-01-09T07:12:57Z

Instead of keeping a separate snd-page-alloc module, merge into the core snd-pcm module, as we don't need to keep it as an individual module due to the drop of page reservation. Signed-off-by: Takashi Iwai

ALSA: Remove superfluous header inclusions in memalloc.c

2014-01-09T06:44:11Z

After cutting off the proc and page reservation codes, we don't need many headers any longer. Signed-off-by: Takashi Iwai