diff --git a/include/sound/emu10k1.h b/include/sound/emu10k1.h index db32b7de52e0..5ebcc51c0a6a 100644 --- a/include/sound/emu10k1.h +++ b/include/sound/emu10k1.h @@ -1710,6 +1710,7 @@ struct snd_emu10k1 { unsigned int ecard_ctrl; /* ecard control bits */ unsigned int address_mode; /* address mode */ unsigned long dma_mask; /* PCI DMA mask */ + bool iommu_workaround; /* IOMMU workaround needed */ unsigned int delay_pcm_irq; /* in samples */ int max_cache_pages; /* max memory size / PAGE_SIZE */ struct snd_dma_buffer silent_page; /* silent page */ @@ -1877,6 +1878,8 @@ void snd_p16v_resume(struct snd_emu10k1 *emu); /* memory allocation */ struct snd_util_memblk *snd_emu10k1_alloc_pages(struct snd_emu10k1 *emu, struct snd_pcm_substream *substream); int snd_emu10k1_free_pages(struct snd_emu10k1 *emu, struct snd_util_memblk *blk); +int snd_emu10k1_alloc_pages_maybe_wider(struct snd_emu10k1 *emu, size_t size, + struct snd_dma_buffer *dmab); struct snd_util_memblk *snd_emu10k1_synth_alloc(struct snd_emu10k1 *emu, unsigned int size); int snd_emu10k1_synth_free(struct snd_emu10k1 *emu, struct snd_util_memblk *blk); int snd_emu10k1_synth_bzero(struct snd_emu10k1 *emu, struct snd_util_memblk *blk, int offset, int size); diff --git a/sound/pci/emu10k1/emu10k1_main.c b/sound/pci/emu10k1/emu10k1_main.c index 8decd2a7a404..18267de3a269 100644 --- a/sound/pci/emu10k1/emu10k1_main.c +++ b/sound/pci/emu10k1/emu10k1_main.c @@ -36,6 +36,7 @@ #include #include #include +#include #include #include #include @@ -1758,6 +1759,38 @@ static struct snd_emu_chip_details emu_chip_details[] = { { } /* terminator */ }; +/* + * The chip (at least the Audigy 2 CA0102 chip, but most likely others, too) + * has a problem that from time to time it likes to do few DMA reads a bit + * beyond its normal allocation and gets very confused if these reads get + * blocked by a IOMMU. + * + * This behaviour has been observed for the first (reserved) page + * (for which it happens multiple times at every playback), often for various + * synth pages and sometimes for PCM playback buffers and the page table + * memory itself. + * + * As a workaround let's widen these DMA allocations by an extra page if we + * detect that the device is behind a non-passthrough IOMMU. + */ +static void snd_emu10k1_detect_iommu(struct snd_emu10k1 *emu) +{ + struct iommu_domain *domain; + + emu->iommu_workaround = false; + + if (!iommu_present(emu->card->dev->bus)) + return; + + domain = iommu_get_domain_for_dev(emu->card->dev); + if (domain && domain->type == IOMMU_DOMAIN_IDENTITY) + return; + + dev_notice(emu->card->dev, + "non-passthrough IOMMU detected, widening DMA allocations"); + emu->iommu_workaround = true; +} + int snd_emu10k1_create(struct snd_card *card, struct pci_dev *pci, unsigned short extin_mask, @@ -1770,6 +1803,7 @@ int snd_emu10k1_create(struct snd_card *card, struct snd_emu10k1 *emu; int idx, err; int is_audigy; + size_t page_table_size; unsigned int silent_page; const struct snd_emu_chip_details *c; static struct snd_device_ops ops = { @@ -1867,6 +1901,8 @@ int snd_emu10k1_create(struct snd_card *card, is_audigy = emu->audigy = c->emu10k2_chip; + snd_emu10k1_detect_iommu(emu); + /* set addressing mode */ emu->address_mode = is_audigy ? 0 : 1; /* set the DMA transfer mask */ @@ -1893,8 +1929,11 @@ int snd_emu10k1_create(struct snd_card *card, emu->port = pci_resource_start(pci, 0); emu->max_cache_pages = max_cache_bytes >> PAGE_SHIFT; - if (snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, snd_dma_pci_data(pci), - (emu->address_mode ? 32 : 16) * 1024, &emu->ptb_pages) < 0) { + + page_table_size = sizeof(u32) * (emu->address_mode ? MAXPAGES1 : + MAXPAGES0); + if (snd_emu10k1_alloc_pages_maybe_wider(emu, page_table_size, + &emu->ptb_pages) < 0) { err = -ENOMEM; goto error; } @@ -1910,8 +1949,8 @@ int snd_emu10k1_create(struct snd_card *card, goto error; } - if (snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, snd_dma_pci_data(pci), - EMUPAGESIZE, &emu->silent_page) < 0) { + if (snd_emu10k1_alloc_pages_maybe_wider(emu, EMUPAGESIZE, + &emu->silent_page) < 0) { err = -ENOMEM; goto error; } @@ -1995,7 +2034,7 @@ int snd_emu10k1_create(struct snd_card *card, 0x00000000 | SPCS_EMPHASIS_NONE | SPCS_COPYRIGHT; /* Clear silent pages and set up pointers */ - memset(emu->silent_page.area, 0, PAGE_SIZE); + memset(emu->silent_page.area, 0, emu->silent_page.bytes); silent_page = emu->silent_page.addr << emu->address_mode; for (idx = 0; idx < (emu->address_mode ? MAXPAGES1 : MAXPAGES0); idx++) ((u32 *)emu->ptb_pages.area)[idx] = cpu_to_le32(silent_page | idx); diff --git a/sound/pci/emu10k1/emupcm.c b/sound/pci/emu10k1/emupcm.c index 2683b9717215..cefe613ef7b7 100644 --- a/sound/pci/emu10k1/emupcm.c +++ b/sound/pci/emu10k1/emupcm.c @@ -411,12 +411,20 @@ static int snd_emu10k1_playback_hw_params(struct snd_pcm_substream *substream, struct snd_emu10k1 *emu = snd_pcm_substream_chip(substream); struct snd_pcm_runtime *runtime = substream->runtime; struct snd_emu10k1_pcm *epcm = runtime->private_data; + size_t alloc_size; int err; if ((err = snd_emu10k1_pcm_channel_alloc(epcm, params_channels(hw_params))) < 0) return err; - if ((err = snd_pcm_lib_malloc_pages(substream, params_buffer_bytes(hw_params))) < 0) + + alloc_size = params_buffer_bytes(hw_params); + if (emu->iommu_workaround) + alloc_size += EMUPAGESIZE; + err = snd_pcm_lib_malloc_pages(substream, alloc_size); + if (err < 0) return err; + if (emu->iommu_workaround && runtime->dma_bytes >= EMUPAGESIZE) + runtime->dma_bytes -= EMUPAGESIZE; if (err > 0) { /* change */ int mapped; if (epcm->memblk != NULL) diff --git a/sound/pci/emu10k1/memory.c b/sound/pci/emu10k1/memory.c index 1d0ce7356bbd..5865f3b90b34 100644 --- a/sound/pci/emu10k1/memory.c +++ b/sound/pci/emu10k1/memory.c @@ -377,6 +377,33 @@ int snd_emu10k1_free_pages(struct snd_emu10k1 *emu, struct snd_util_memblk *blk) return snd_emu10k1_synth_free(emu, blk); } +/* + * allocate DMA pages, widening the allocation if necessary + * + * See the comment above snd_emu10k1_detect_iommu() in emu10k1_main.c why + * this might be needed. + * + * If you modify this function check whether __synth_free_pages() also needs + * changes. + */ +int snd_emu10k1_alloc_pages_maybe_wider(struct snd_emu10k1 *emu, size_t size, + struct snd_dma_buffer *dmab) +{ + if (emu->iommu_workaround) { + size_t npages = (size + PAGE_SIZE - 1) / PAGE_SIZE; + size_t size_real = npages * PAGE_SIZE; + + /* + * The device has been observed to accesses up to 256 extra + * bytes, but use 1k to be safe. + */ + if (size_real < size + 1024) + size += PAGE_SIZE; + } + + return snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, + snd_dma_pci_data(emu->pci), size, dmab); +} /* * memory allocation using multiple pages (for synth) @@ -472,7 +499,15 @@ static void __synth_free_pages(struct snd_emu10k1 *emu, int first_page, continue; dmab.area = emu->page_ptr_table[page]; dmab.addr = emu->page_addr_table[page]; + + /* + * please keep me in sync with logic in + * snd_emu10k1_alloc_pages_maybe_wider() + */ dmab.bytes = PAGE_SIZE; + if (emu->iommu_workaround) + dmab.bytes *= 2; + snd_dma_free_pages(&dmab); emu->page_addr_table[page] = 0; emu->page_ptr_table[page] = NULL; @@ -491,9 +526,8 @@ static int synth_alloc_pages(struct snd_emu10k1 *emu, struct snd_emu10k1_memblk get_single_page_range(emu->memhdr, blk, &first_page, &last_page); /* allocate kernel pages */ for (page = first_page; page <= last_page; page++) { - if (snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, - snd_dma_pci_data(emu->pci), - PAGE_SIZE, &dmab) < 0) + if (snd_emu10k1_alloc_pages_maybe_wider(emu, PAGE_SIZE, + &dmab) < 0) goto __fail; if (!is_valid_page(emu, dmab.addr)) { snd_dma_free_pages(&dmab);