kernel.git/drivers/dma/ioat/init.c, branch linux-4.13.y

dmaengine: ioat: don't use DMA_ERROR_CODE

2017-06-20T09:12:56Z

DMA_ERROR_CODE is not a public API and will go away. Instead properly unwind based on the loop counter. Signed-off-by: Christoph Hellwig Acked-by: Dave Jiang Acked-By: Vinod Koul

dmaengine: ioat: use setup_timer

2017-04-24T04:08:41Z

Use setup_timer() instead of init_timer() to simplify the code. Signed-off-by: Geliang Tang Reviewed-by: Dan Williams Signed-off-by: Vinod Koul

dmaengine: iota: ioat_alloc_chan_resources should not perform sleeping allocations.

2017-01-10T05:11:51Z

On a kernel with DEBUG_LOCKS, ioat_free_chan_resources triggers an in_interrupt() warning. With PROVE_LOCKING, it reports detecting a SOFTIRQ-safe to SOFTIRQ-unsafe lock ordering in the same code path. This is because dma_generic_alloc_coherent() checks if the GFP flags permit blocking. It allocates from different subsystems if blocking is permitted. The free path knows how to return the memory to the correct allocator. If GFP_KERNEL is specified then the alloc and free end up going through cma_alloc(), which uses mutexes. Given that ioat_free_chan_resources() can be called in interrupt context, ioat_alloc_chan_resources() must specify GFP_NOWAIT so that the allocations do not block and instead use an allocator that uses spinlocks. Signed-off-by: Krister Johansen Acked-by: Dave Jiang Signed-off-by: Vinod Koul

dmaengine: ioatdma: workaround SKX ioatdma version

2017-01-02T02:42:59Z

The Skylake ioatdma is technically CBDMA 3.2+ and contains the same hardware bits with some additional 3.3 features, but it's not really 3.3 where the driver is concerned. Signed-off-by: Dave Jiang Signed-off-by: Vinod Koul

dmaengine: ioatdma: Add Skylake PCI Dev ID

2017-01-02T02:42:59Z

Adding Skylake Xeon PCI device ids for ioatdma and related bits. Signed-off-by: Dave Jiang Signed-off-by: Vinod Koul

Merge branch 'topic/ioat' into for-linus

2016-12-14T03:36:23Z

dmaengine: ioat: remove unused ‘is_raid_device’

2016-12-12T16:55:21Z

In ioat3_dma_probe(), variable ‘is_raid_device’ is initialized but never used, which leads to warning with W=1 drivers/dma/ioat/init.c: In function ‘ioat3_dma_probe’: drivers/dma/ioat/init.c:1084:7: warning: variable ‘is_raid_device’ set but not used [-Wunused-but-set-variable] bool is_raid_device = false; So remove it. Cc: Dave Jiang Signed-off-by: Vinod Koul

dmaengine: ioat: set error code on failures

2016-12-06T04:58:18Z

In function ioat_xor_val_self_test(), when the calls to dma_mapping_error() fail, the value of return variable err is 0 (indicates no error). As a result, the return value may be inconsistent with the execution status. This patch fixes the bug by assigning "-ENOMEM" to err on the error path. Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=188601 Signed-off-by: Pan Bian Acked-by: Dave Jiang Signed-off-by: Vinod Koul

dmaengine: ioat: set error code on failures

2016-12-06T04:58:11Z

In function ioat_dma_self_test(), when the calls to dma_mapping_error() fails, the value of return variable err is 0 (indicates no error). As a result, the return value may be inconsistent with the execution status. This patch fixes the bug by assigning -ENOMEM to err on the error path. Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=188591 Signed-off-by: Pan Bian Acked-by: Dave Jiang Signed-off-by: Vinod Koul

dmaengine: ioatdma: fix uninitialized array usage

2016-08-08T02:32:00Z

Static analysis showed that unitialized array is being used for compare. At line 850 when a dma_mapping_error() occurs, it jumps to dma_unmap. At this point, dma_srcs has not been initialized. However, the code after dma_unmap label checks dma_srcs for a comparison and thus is comparing to random garbage in the array. Given that when dest_dma is being mapped this is the first instance of mapping DMA memory and failed, there is really nothing to be cleaned up and thus should jump to free_resources label instead. Signed-off-by: Dave Jiang Signed-off-by: Vinod Koul