diff options
| author | Mike Frysinger <vapier@gentoo.org> | 2009-04-10 20:52:08 +0000 |
|---|---|---|
| committer | Mike Frysinger <vapier@gentoo.org> | 2009-06-12 06:03:45 -0400 |
| commit | 5d89137a17ca804ee60077f5d4ad8d7ca60f0614 (patch) | |
| tree | e6445551fdb86ffdbb3da14b8ab91d0e05c94612 /arch/blackfin/mach-common | |
| parent | f82e0a0c67621df83458753aef580a3508d5428e (diff) | |
Blackfin: fix data cache flushing when doing icache flushing
Make sure we flush all data caches and their write buffers before flushing
icache, otherwise random edge cases could crop up where stale data is read
into icache from external memory. As fallout, punt the combined icache +
dcache flush function since we cannot safely do them back to back -- the
SSYNC is needed between the dcache flush and the icache flush.
Signed-off-by: Mike Frysinger <vapier@gentoo.org>
Signed-off-by: Bryan Wu <cooloney@kernel.org>
Diffstat (limited to 'arch/blackfin/mach-common')
| -rw-r--r-- | arch/blackfin/mach-common/cache.S | 16 |
1 files changed, 0 insertions, 16 deletions
diff --git a/arch/blackfin/mach-common/cache.S b/arch/blackfin/mach-common/cache.S index aa0648c6a9fe..c295e8f837c0 100644 --- a/arch/blackfin/mach-common/cache.S +++ b/arch/blackfin/mach-common/cache.S @@ -80,22 +80,6 @@ ENTRY(_blackfin_icache_flush_range) do_flush IFLUSH, , nop ENDPROC(_blackfin_icache_flush_range) -/* Flush all cache lines assocoiated with this area of memory. */ -ENTRY(_blackfin_icache_dcache_flush_range) -/* - * Walkaround to avoid loading wrong instruction after invalidating icache - * and following sequence is met. - * - * 1) One instruction address is cached in the instruction cache. - * 2) This instruction in SDRAM is changed. - * 3) IFLASH[P0] is executed only once in blackfin_icache_flush_range(). - * 4) This instruction is executed again, but the old one is loaded. - */ - P0 = R0; - IFLUSH[P0]; - do_flush FLUSH, IFLUSH -ENDPROC(_blackfin_icache_dcache_flush_range) - /* Throw away all D-cached data in specified region without any obligation to * write them back. Since the Blackfin ISA does not have an "invalidate" * instruction, we use flush/invalidate. Perhaps as a speed optimization we |