user/sven/linux.git/include/linux/dma-mapping.h, branch v4.19.29

dma-mapping: relax warning for per-device areas

2018-07-25T11:32:58Z

The reasons why dma_free_attrs() should not be called from IRQ context are not necessarily obvious and somewhat buried in the development history, so let's start by documenting the warning itself to help anyone who does happen to hit it and wonder what the deal is. However, this check turns out to be slightly over-restrictive for the way that per-device memory has been spliced into the general API, since for that case we know that dma_declare_coherent_memory() has created an appropriate CPU mapping for the entire area and nothing dynamic should be happening. Given that the usage model for per-device memory is often more akin to streaming DMA than 'real' coherent DMA (e.g. allocating and freeing space to copy short-lived packets in and out), it is also somewhat more reasonable for those operations to happen in IRQ handlers for such devices. Therefore, let's move the irqs_disabled() check down past the per-device area hook, so that that gets a chance to resolve the request before we reach definite "you're doing it wrong" territory. Reported-by: Fredrik Noring Tested-by: Fredrik Noring Signed-off-by: Robin Murphy Signed-off-by: Christoph Hellwig

x86/pci-dma: switch the VIA 32-bit DMA quirk to use the struct device flag

2018-05-28T10:48:25Z

Instead of globally disabling > 32bit DMA using the arch_dma_supported hook walk the PCI bus under the actually affected bridge and mark every device with the dma_32bit_limit flag. This also gets rid of the arch_dma_supported hook entirely. Signed-off-by: Christoph Hellwig Reviewed-by: Thomas Gleixner

dma-mapping: remove unused gfp_t parameter to arch_dma_alloc_attrs

2018-05-25T09:23:06Z

Signed-off-by: Huaisheng Ye Signed-off-by: Christoph Hellwig

dma-mapping: provide a generic dma-noncoherent implementation

2018-05-19T06:46:12Z

Add a new dma_map_ops implementation that uses dma-direct for the address mapping of streaming mappings, and which requires arch-specific implemenations of coherent allocate/free. Architectures have to provide flushing helpers to ownership trasnfers to the device and/or CPU, and can provide optional implementations of the coherent mmap functionality, and the cache_flush routines for non-coherent long term allocations. Signed-off-by: Christoph Hellwig Tested-by: Alexey Brodkin Acked-by: Vineet Gupta

dma-mapping: move the NEED_DMA_MAP_STATE config symbol to lib/Kconfig

2018-05-09T04:56:08Z

This way we have one central definition of it, and user can select it as needed. Note that we now also always select it when CONFIG_DMA_API_DEBUG is select, which fixes some incorrect checks in a few network drivers. Signed-off-by: Christoph Hellwig Reviewed-by: Anshuman Khandual

PCI: remove PCI_DMA_BUS_IS_PHYS

2018-05-07T05:15:41Z

This was used by the ide, scsi and networking code in the past to determine if they should bounce payloads. Now that the dma mapping always have to support dma to all physical memory (thanks to swiotlb for non-iommu systems) there is no need to this crude hack any more. Signed-off-by: Christoph Hellwig Acked-by: Palmer Dabbelt (for riscv) Reviewed-by: Jens Axboe

Merge tag 'dma-mapping-4.17' of git://git.infradead.org/users/hch/dma-mapping

2018-04-05T17:23:24Z

Pull dma-mapping updates from Christoph Hellwig: "Very light this round as the interesting dma mapping changes went through the x86 tree. This just provides proper stubs for architectures not supporting dma (Geert Uytterhoeven)" * tag 'dma-mapping-4.17' of git://git.infradead.org/users/hch/dma-mapping: usb: gadget: Add NO_DMA dummies for DMA mapping API scsi: Add NO_DMA dummies for SCSI DMA mapping API mm: Add NO_DMA dummies for DMA pool API dma-coherent: Add NO_DMA dummies for managed DMA API dma-mapping: Convert NO_DMA get_dma_ops() into a real dummy

dma-mapping: Don't clear GFP_ZERO in dma_alloc_attrs

2018-03-28T15:34:23Z

Revert the clearing of __GFP_ZERO in dma_alloc_attrs and move it to dma_direct_alloc for now. While most common architectures always zero dma cohereny allocations (and x86 did so since day one) this is not documented and at least arc and s390 do not zero without the explicit __GFP_ZERO argument. Fixes: 57bf5a8963f8 ("dma-mapping: clear harmful GFP_* flags in common code") Reported-by: Evgeniy Didin Reported-by: Sebastian Ott Signed-off-by: Christoph Hellwig Signed-off-by: Thomas Gleixner Tested-by: Evgeniy Didin Cc: iommu@lists.linux-foundation.org Link: https://lkml.kernel.org/r/20180328133535.17302-2-hch@lst.de

dma-coherent: Add NO_DMA dummies for managed DMA API

2018-03-16T18:58:27Z

Add dummies for dmam_{alloc,free}_coherent(), to allow compile-testing if NO_DMA=y. This prevents the following from showing up later: ERROR: "dmam_alloc_coherent" [drivers/net/ethernet/arc/arc_emac.ko] undefined! ERROR: "dmam_free_coherent" [drivers/net/ethernet/apm/xgene/xgene-enet.ko] undefined! ERROR: "dmam_alloc_coherent" [drivers/net/ethernet/apm/xgene/xgene-enet.ko] undefined! ERROR: "dmam_alloc_coherent" [drivers/mtd/nand/hisi504_nand.ko] undefined! ERROR: "dmam_alloc_coherent" [drivers/mmc/host/dw_mmc.ko] undefined! Signed-off-by: Geert Uytterhoeven Reviewed-by: Mark Brown Acked-by: Robin Murphy Signed-off-by: Christoph Hellwig

dma-mapping: Convert NO_DMA get_dma_ops() into a real dummy

2018-03-16T18:58:27Z

If NO_DMA=y, get_dma_ops() returns a reference to the non-existing symbol bad_dma_ops, thus causing a link failure if it is ever used. Make get_dma_ops() return NULL instead, to avoid the link failure. This allows to improve compile-testing, and limits the need to keep on sprinkling dependencies on HAS_DMA all over the place. Signed-off-by: Geert Uytterhoeven Reviewed-by: Mark Brown Acked-by: Robin Murphy Signed-off-by: Christoph Hellwig