[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20180219194556.6575-4-willy@infradead.org>
Date: Mon, 19 Feb 2018 11:44:58 -0800
From: Matthew Wilcox <willy@...radead.org>
To: Andrew Morton <akpm@...ux-foundation.org>
Cc: Matthew Wilcox <mawilcox@...rosoft.com>,
linux-kernel@...r.kernel.org, linux-mm@...ck.org,
linux-fsdevel@...r.kernel.org
Subject: [PATCH v7 03/61] arm64: Turn flush_dcache_mmap_lock into a no-op
From: Matthew Wilcox <mawilcox@...rosoft.com>
ARM64 doesn't walk the VMA tree in its flush_dcache_page()
implementation, so has no need to take the tree_lock.
Signed-off-by: Matthew Wilcox <mawilcox@...rosoft.com>
Reviewed-by: Will Deacon <will.deacon@....com>
---
arch/arm64/include/asm/cacheflush.h | 6 ++----
1 file changed, 2 insertions(+), 4 deletions(-)
diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h
index bef9f418f089..550b0abea953 100644
--- a/arch/arm64/include/asm/cacheflush.h
+++ b/arch/arm64/include/asm/cacheflush.h
@@ -137,10 +137,8 @@ static inline void __flush_icache_all(void)
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
--
2.16.1
Powered by blists - more mailing lists