kernel/linux.git/drivers/crypto/allwinner, branch v6.12.80

crypto: sun8i-ce - remove channel timeout field

2025-11-13T20:34:23+00:00

[ Upstream commit 9a23ea1f7558bdd3f8d2b35b1c2e16a2f9bf671e ] Using the number of bytes in the request as DMA timeout is really inconsistent, as large requests could possibly set a timeout of hundreds of seconds. Remove the per-channel timeout field and use a single, static DMA timeout of 3 seconds for all requests. Signed-off-by: Ovidiu Panait Tested-by: Corentin LABBE Reviewed-by: Corentin LABBE Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin

crypto: sun8i-ce - fix nents passed to dma_unmap_sg()

2025-08-15T10:13:49+00:00

[ Upstream commit b6cd3cfb5afe49952f8f6be947aeeca9ba0faebb ] In sun8i_ce_cipher_unprepare(), dma_unmap_sg() is incorrectly called with the number of entries returned by dma_map_sg(), rather than using the original number of entries passed when mapping the scatterlist. To fix this, stash the original number of entries passed to dma_map_sg() in the request context. Fixes: 0605fa0f7826 ("crypto: sun8i-ce - split into prepare/run/unprepare") Signed-off-by: Ovidiu Panait Acked-by: Corentin LABBE Tested-by: Corentin LABBE Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin

crypto: sun8i-ce - move fallback ahash_request to the end of the struct

2025-06-19T13:31:30+00:00

[ Upstream commit c822831b426307a6ca426621504d3c7f99765a39 ] 'struct ahash_request' has a flexible array at the end, so it must be the last member in a struct, to avoid overwriting other struct members. Therefore, move 'fallback_req' to the end of the 'sun8i_ce_hash_reqctx' struct. Fixes: 56f6d5aee88d ("crypto: sun8i-ce - support hash algorithms") Signed-off-by: Ovidiu Panait Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin

crypto: sun8i-ce - undo runtime PM changes during driver removal

2025-06-19T13:31:28+00:00

[ Upstream commit 9334f427576e6d361a409959b52246b0aa10476f ] The pm_runtime_use_autosuspend() call must be undone with pm_runtime_dont_use_autosuspend() at driver exit, but this is not currently handled in the driver. To fix this issue and at the same time simplify error handling, switch to devm_pm_runtime_enable(). It will call both pm_runtime_disable() and pm_runtime_dont_use_autosuspend() during driver removal. Fixes: 06f751b61329 ("crypto: allwinner - Add sun8i-ce Crypto Engine") Signed-off-by: Ovidiu Panait Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin

crypto: sun8i-ss - do not use sg_dma_len before calling DMA functions

2025-06-19T13:31:27+00:00

[ Upstream commit 2dfc7cd74a5e062a5405560447517e7aab1c7341 ] When testing sun8i-ss with multi_v7_defconfig, all CBC algorithm fail crypto selftests. This is strange since on sunxi_defconfig, everything was ok. The problem was in the IV setup loop which never run because sg_dma_len was 0. Fixes: 359e893e8af4 ("crypto: sun8i-ss - rework handling of IV") Signed-off-by: Corentin Labbe Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin

crypto: sun8i-ce-cipher - fix error handling in sun8i_ce_cipher_prepare()

2025-06-19T13:31:27+00:00

[ Upstream commit f31adc3e356f7350d4a4d68c98d3f60f2f6e26b3 ] Fix two DMA cleanup issues on the error path in sun8i_ce_cipher_prepare(): 1] If dma_map_sg() fails for areq->dst, the device driver would try to free DMA memory it has not allocated in the first place. To fix this, on the "theend_sgs" error path, call dma unmap only if the corresponding dma map was successful. 2] If the dma_map_single() call for the IV fails, the device driver would try to free an invalid DMA memory address on the "theend_iv" path: ------------[ cut here ]------------ DMA-API: sun8i-ce 1904000.crypto: device driver tries to free an invalid DMA memory address WARNING: CPU: 2 PID: 69 at kernel/dma/debug.c:968 check_unmap+0x123c/0x1b90 Modules linked in: skcipher_example(O+) CPU: 2 UID: 0 PID: 69 Comm: 1904000.crypto- Tainted: G O 6.15.0-rc3+ #24 PREEMPT Tainted: [O]=OOT_MODULE Hardware name: OrangePi Zero2 (DT) pc : check_unmap+0x123c/0x1b90 lr : check_unmap+0x123c/0x1b90 ... Call trace: check_unmap+0x123c/0x1b90 (P) debug_dma_unmap_page+0xac/0xc0 dma_unmap_page_attrs+0x1f4/0x5fc sun8i_ce_cipher_do_one+0x1bd4/0x1f40 crypto_pump_work+0x334/0x6e0 kthread_worker_fn+0x21c/0x438 kthread+0x374/0x664 ret_from_fork+0x10/0x20 ---[ end trace 0000000000000000 ]--- To fix this, check for !dma_mapping_error() before calling dma_unmap_single() on the "theend_iv" path. Fixes: 06f751b61329 ("crypto: allwinner - Add sun8i-ce Crypto Engine") Signed-off-by: Ovidiu Panait Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin

crypto: sun8i-ce-hash - fix error handling in sun8i_ce_hash_run()

2025-06-19T13:31:26+00:00

[ Upstream commit ea4dd134ef332bd9e3e734c1ba0a1521f436b678 ] Rework error handling in sun8i_ce_hash_run() to unmap the dma buffers in case of failure. Currently, the dma unmap functions are not called if the function errors out at various points. Fixes: 56f6d5aee88d1 ("crypto: sun8i-ce - support hash algorithms") Signed-off-by: Ovidiu Panait Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin

move asm/unaligned.h to linux/unaligned.h

2024-10-02T21:23:23+00:00

asm/unaligned.h is always an include of asm-generic/unaligned.h; might as well move that thing to linux/unaligned.h and include that - there's nothing arch-specific in that header. auto-generated by the following: for i in `git grep -l -w asm/unaligned.h`; do sed -i -e "s/asm\/unaligned.h/linux\/unaligned.h/" $i done for i in `git grep -l -w asm-generic/unaligned.h`; do sed -i -e "s/asm-generic\/unaligned.h/linux\/unaligned.h/" $i done git mv include/asm-generic/unaligned.h include/linux/unaligned.h git mv tools/include/asm-generic/unaligned.h tools/include/linux/unaligned.h sed -i -e "/unaligned.h/d" include/asm-generic/Kbuild sed -i -e "s/__ASM_GENERIC/__LINUX/" include/linux/unaligned.h tools/include/linux/unaligned.h

crypto: sun8i-ce - add Allwinner H616 support

2024-07-06T00:20:00+00:00

The crypto engine in the Allwinner H616 is very similar to the H6, but needs the base address for the task descriptor and the addresses within it to be expressed in words, not in bytes. Add a new variant struct entry for the H616, and set the new flag to mark the use of 34 bit addresses. Also the internal 32K oscillator is required for TRNG operation, so specify all four clocks. Signed-off-by: Andre Przywara Reviewed-by: Chen-Yu Tsai Tested-by: Ryan Walklin Tested-by: Philippe Simons Signed-off-by: Herbert Xu

crypto: sun8i-ce - wrap accesses to descriptor address fields

2024-07-06T00:19:59+00:00

The Allwinner H616 (and later) SoCs support more than 32 bits worth of physical addresses. To accommodate the larger address space, the CE task descriptor fields holding addresses are now encoded as "word addresses", so take the actual address divided by four. This is true for the fields within the descriptor, but also for the descriptor base address, in the CE_TDA register. Wrap all accesses to those fields in a function, which will do the required division if needed. For now this in unused, so there should be no change in behaviour. Signed-off-by: Andre Przywara Reviewed-by: Chen-Yu Tsai Signed-off-by: Herbert Xu