Re: [PATCH 15/21] ARM: dma-mapping: always invalidate WT caches before DMA
Linus Walleij <[email protected]> Fri, 31 Mar 2023 11:01:51 +0200
| Newsgroups | io.groups.linux-oxnas,org.infradead.lists.linux-arm-kernel,org.infradead.lists.linux-riscv,org.infradead.lists.linux-snps-arc,org.kernel.vger.linux-csky,org.kernel.vger.linux-hexagon,org.kernel.vger.linux-kernel,org.kernel.vger.linux-m68k,org.kernel.vger.linux-mips,org.kernel.vger.linux-openrisc,org.kernel.vger.linux-parisc,org.kernel.vger.linux-sh,org.kernel.vger.sparclinux,org.ozlabs.lists.linuxppc-dev |
|---|---|
| Message-ID | <CACRpkdbMry_UUYN1MuXTUpRXV+Tj9RSDvN-iBdvR8hDfkTaX4w@mail.gmail.com> |
On Mon, Mar 27, 2023 at 2:16=E2=80=AFPM Arnd Bergmann <[email protected]> wro= te: > From: Arnd Bergmann <[email protected]> > > Most ARM CPUs can have write-back caches and that require > cache management to be done in the dma_sync_*_for_device() > operation. This is typically done in both writeback and > writethrough mode. > > The cache-v4.S (arm720/740/7tdmi/9tdmi) and cache-v4wt.S > (arm920t, arm940t) implementations are the exception here, > and only do the cache management after the DMA is complete, > in the dma_sync_*_for_cpu() operation. > > Change this for consistency with the other platforms. This > should have no user visible effect. > > Signed-off-by: Arnd Bergmann <[email protected]> Looks good to me. Reviewed-by: Linus Walleij <[email protected]> Yours, Linus Walleij