From: Matthew Wilcox <mawilcox@xxxxxxxxxxxxx> Subject: arm64: turn flush_dcache_mmap_lock into a no-op ARM64 doesn't walk the VMA tree in its flush_dcache_page() implementation, so has no need to take the tree_lock. Link: http://lkml.kernel.org/r/20180313132639.17387-4-willy@xxxxxxxxxxxxx Signed-off-by: Matthew Wilcox <mawilcox@xxxxxxxxxxxxx> Reviewed-by: Will Deacon <will.deacon@xxxxxxx> Cc: Darrick J. Wong <darrick.wong@xxxxxxxxxx> Cc: Dave Chinner <david@xxxxxxxxxxxxx> Cc: Jeff Layton <jlayton@xxxxxxxxxx> Cc: Ryusuke Konishi <konishi.ryusuke@xxxxxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- arch/arm64/include/asm/cacheflush.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff -puN arch/arm64/include/asm/cacheflush.h~arm64-turn-flush_dcache_mmap_lock-into-a-no-op arch/arm64/include/asm/cacheflush.h --- a/arch/arm64/include/asm/cacheflush.h~arm64-turn-flush_dcache_mmap_lock-into-a-no-op +++ a/arch/arm64/include/asm/cacheflush.h @@ -140,10 +140,8 @@ static inline void __flush_icache_all(vo dsb(ish); } -#define flush_dcache_mmap_lock(mapping) \ - spin_lock_irq(&(mapping)->tree_lock) -#define flush_dcache_mmap_unlock(mapping) \ - spin_unlock_irq(&(mapping)->tree_lock) +#define flush_dcache_mmap_lock(mapping) do { } while (0) +#define flush_dcache_mmap_unlock(mapping) do { } while (0) /* * We don't appear to need to do anything here. In fact, if we did, we'd _ -- To unsubscribe from this list: send the line "unsubscribe mm-commits" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
