4.20-stable review patch. If anyone has any objections, please let me know.
------------------
From: Catalin Marinas <catalin.mari...@arm.com>
commit 132fdc379eb143932d209a20fd581e1ce7630960 upstream.
Commit 3b8c9f1cdfc5 ("arm64: IPI each CPU after invalidating the I-cache
for kernel mappings") was aimed at fixing the I-cache invalidation for
kernel mappings. However, it inadvertently caused all cache maintenance
for user mappings via set_pte_at() -> __sync_icache_dcache() ->
sync_icache_aliases() to call kick_all_cpus_sync().
Reported-by: Shijith Thotton <sthot...@marvell.com>
Tested-by: Shijith Thotton <sthot...@marvell.com>
Reported-by: Wandun Chen <chenwan...@huawei.com>
Fixes: 3b8c9f1cdfc5 ("arm64: IPI each CPU after invalidating the I-cache for
kernel mappings")
Cc: <sta...@vger.kernel.org> # 4.19.x-
Signed-off-by: Catalin Marinas <catalin.mari...@arm.com>
Signed-off-by: Will Deacon <will.dea...@arm.com>
Signed-off-by: Greg Kroah-Hartman <gre...@linuxfoundation.org>
---
arch/arm64/mm/flush.c | 6 +++++-
1 file changed, 5 insertions(+), 1 deletion(-)
--- a/arch/arm64/mm/flush.c
+++ b/arch/arm64/mm/flush.c
@@ -33,7 +33,11 @@ void sync_icache_aliases(void *kaddr, un
__clean_dcache_area_pou(kaddr, len);
__flush_icache_all();
} else {
- flush_icache_range(addr, addr + len);
+ /*
+ * Don't issue kick_all_cpus_sync() after I-cache invalidation
+ * for user mappings.
+ */
+ __flush_icache_range(addr, addr + len);
}
}
