* [PATCH 1/2] sh: Flush ITLB too in PTEAEX's flush_tlb_page()
@ 2010-03-21 19:51 Matt Fleming
2010-03-23 4:39 ` Paul Mundt
0 siblings, 1 reply; 2+ messages in thread
From: Matt Fleming @ 2010-03-21 19:51 UTC (permalink / raw)
To: linux-sh
flush_tlb_page() can be used to flush TLB entries that map executable
pages. Therefore, we need to ensure that the ITLB is also flushed in
local_flush_tlb_page().
Signed-off-by: Matt Fleming <matt@console-pimps.org>
---
arch/sh/include/cpu-sh4/cpu/mmu_context.h | 2 ++
arch/sh/mm/tlb-pteaex.c | 2 ++
2 files changed, 4 insertions(+), 0 deletions(-)
diff --git a/arch/sh/include/cpu-sh4/cpu/mmu_context.h b/arch/sh/include/cpu-sh4/cpu/mmu_context.h
index 03ea75c..310ec92 100644
--- a/arch/sh/include/cpu-sh4/cpu/mmu_context.h
+++ b/arch/sh/include/cpu-sh4/cpu/mmu_context.h
@@ -19,6 +19,8 @@
#define MMUCR 0xFF000010 /* MMU Control Register */
+#define MMU_ITLB_ADDRESS_ARRAY 0xF2000000
+#define MMU_ITLB_ADDRESS_ARRAY2 0xF2800000
#define MMU_UTLB_ADDRESS_ARRAY 0xF6000000
#define MMU_UTLB_ADDRESS_ARRAY2 0xF6800000
#define MMU_PAGE_ASSOC_BIT 0x80
diff --git a/arch/sh/mm/tlb-pteaex.c b/arch/sh/mm/tlb-pteaex.c
index 32dc674..bdd0982 100644
--- a/arch/sh/mm/tlb-pteaex.c
+++ b/arch/sh/mm/tlb-pteaex.c
@@ -73,5 +73,7 @@ void local_flush_tlb_one(unsigned long asid, unsigned long page)
jump_to_uncached();
__raw_writel(page, MMU_UTLB_ADDRESS_ARRAY | MMU_PAGE_ASSOC_BIT);
__raw_writel(asid, MMU_UTLB_ADDRESS_ARRAY2 | MMU_PAGE_ASSOC_BIT);
+ __raw_writel(page, MMU_ITLB_ADDRESS_ARRAY | MMU_PAGE_ASSOC_BIT);
+ __raw_writel(asid, MMU_ITLB_ADDRESS_ARRAY2 | MMU_PAGE_ASSOC_BIT);
back_to_cached();
}
--
1.6.4.rc0
^ permalink raw reply related [flat|nested] 2+ messages in thread
* Re: [PATCH 1/2] sh: Flush ITLB too in PTEAEX's flush_tlb_page()
2010-03-21 19:51 [PATCH 1/2] sh: Flush ITLB too in PTEAEX's flush_tlb_page() Matt Fleming
@ 2010-03-23 4:39 ` Paul Mundt
0 siblings, 0 replies; 2+ messages in thread
From: Paul Mundt @ 2010-03-23 4:39 UTC (permalink / raw)
To: linux-sh
On Sun, Mar 21, 2010 at 07:51:43PM +0000, Matt Fleming wrote:
> flush_tlb_page() can be used to flush TLB entries that map executable
> pages. Therefore, we need to ensure that the ITLB is also flushed in
> local_flush_tlb_page().
On Sun, Mar 21, 2010 at 07:51:52PM +0000, Matt Fleming wrote:
> Setting the TI in MMUCR causes all the TLB bits in MMUCR to be
> cleared. Unfortunately, the TLB wired bits are also cleared when setting
> the TI bit, causing any wired TLB entries to become unwired.
>
> Use local_flush_tlb_all() which implements TLB flushing in a safer
> manner by using the memory-mapped TLB registers. As each CPU has its own
> PMB the modifications in pmb_init() only affect the local CPU, so only
> flush the local CPU's TLB.
On Mon, Mar 22, 2010 at 10:09:58PM +0000, Matt Fleming wrote:
> set_pmb_entry() is now only used by a function that is wrapped in #ifdef
> CONFIG_PM, so wrap set_pmb_entry() in CONFIG_PM too.
All applied, thanks.
^ permalink raw reply [flat|nested] 2+ messages in thread
end of thread, other threads:[~2010-03-23 4:39 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2010-03-21 19:51 [PATCH 1/2] sh: Flush ITLB too in PTEAEX's flush_tlb_page() Matt Fleming
2010-03-23 4:39 ` Paul Mundt
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.