* [RFC PATCH] ARM: Allow HIGHPTE with OUTER_CACHE if the processor supports outer PTWs
@ 2010-09-07 12:46 Catalin Marinas
2010-09-29 12:56 ` Catalin Marinas
0 siblings, 1 reply; 2+ messages in thread
From: Catalin Marinas @ 2010-09-07 12:46 UTC (permalink / raw)
To: linux-arm-kernel
This patch introduces CONFIG_CPU_HAS_OUTER_PTW (selected by CPU_V7) to
allow HIGHPTE to be selected even when OUTER_CACHE is enabled.
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
I haven't seen any discussion on the initial patch for HIGHPTE. I'm not
sure why the limitation on !OUTER_CACHE. The set_pte_ext() at least on
ARMv6 and ARMv7 doesn't do any outer cache flushing. Do we even need
something like CPU_HAS_OUTER_PTW?
I tested it on Versatile Express and haven't seen any errors.
arch/arm/Kconfig | 2 +-
arch/arm/mm/Kconfig | 8 ++++++++
2 files changed, 9 insertions(+), 1 deletions(-)
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index a7ed21f..17d00ec 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -1318,7 +1318,7 @@ config HIGHMEM
config HIGHPTE
bool "Allocate 2nd-level pagetables from highmem"
depends on HIGHMEM
- depends on !OUTER_CACHE
+ depends on !OUTER_CACHE || CPU_HAS_OUTER_PTW
config HW_PERF_EVENTS
bool "Enable hardware performance counter support for perf events"
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index 8493ed0..cf0fa87 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -420,6 +420,7 @@ config CPU_V7
select CPU_HAS_ASID if MMU
select CPU_COPY_V6 if MMU
select CPU_TLB_V7 if MMU
+ select CPU_HAS_OUTER_PTW if MMU
# Figure out what processor architecture version we should be using.
# This defines the compiler instruction set which depends on the machine type.
@@ -607,6 +608,13 @@ config CPU_USE_DOMAINS
This option enables or disables the use of domain switching
via the set_fs() function.
+config CPU_HAS_OUTER_PTW
+ bool
+ depends on MMU
+ help
+ This option is enabled if the processors can perform page
+ table walks on the outer cache.
+
#
# CPU supports 36-bit I/O
#
^ permalink raw reply related [flat|nested] 2+ messages in thread
* [RFC PATCH] ARM: Allow HIGHPTE with OUTER_CACHE if the processor supports outer PTWs
2010-09-07 12:46 [RFC PATCH] ARM: Allow HIGHPTE with OUTER_CACHE if the processor supports outer PTWs Catalin Marinas
@ 2010-09-29 12:56 ` Catalin Marinas
0 siblings, 0 replies; 2+ messages in thread
From: Catalin Marinas @ 2010-09-29 12:56 UTC (permalink / raw)
To: linux-arm-kernel
Hi Russell,
On Tue, 2010-09-07 at 13:46 +0100, Catalin Marinas wrote:
> This patch introduces CONFIG_CPU_HAS_OUTER_PTW (selected by CPU_V7) to
> allow HIGHPTE to be selected even when OUTER_CACHE is enabled.
>
> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
> ---
>
> I haven't seen any discussion on the initial patch for HIGHPTE. I'm not
> sure why the limitation on !OUTER_CACHE. The set_pte_ext() at least on
> ARMv6 and ARMv7 doesn't do any outer cache flushing. Do we even need
> something like CPU_HAS_OUTER_PTW?
Any thoughts on this since you pushed the original patch for HIGHPTE? Is
there any architecture that does outer cache maintenance by physical
address in set_pte_ext()?
(keeping the patch below for reference, though I think we should just
drop the restriction on !OUTER_CACHE)
> I tested it on Versatile Express and haven't seen any errors.
>
>
> arch/arm/Kconfig | 2 +-
> arch/arm/mm/Kconfig | 8 ++++++++
> 2 files changed, 9 insertions(+), 1 deletions(-)
>
> diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
> index a7ed21f..17d00ec 100644
> --- a/arch/arm/Kconfig
> +++ b/arch/arm/Kconfig
> @@ -1318,7 +1318,7 @@ config HIGHMEM
> config HIGHPTE
> bool "Allocate 2nd-level pagetables from highmem"
> depends on HIGHMEM
> - depends on !OUTER_CACHE
> + depends on !OUTER_CACHE || CPU_HAS_OUTER_PTW
>
> config HW_PERF_EVENTS
> bool "Enable hardware performance counter support for perf events"
> diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
> index 8493ed0..cf0fa87 100644
> --- a/arch/arm/mm/Kconfig
> +++ b/arch/arm/mm/Kconfig
> @@ -420,6 +420,7 @@ config CPU_V7
> select CPU_HAS_ASID if MMU
> select CPU_COPY_V6 if MMU
> select CPU_TLB_V7 if MMU
> + select CPU_HAS_OUTER_PTW if MMU
>
> # Figure out what processor architecture version we should be using.
> # This defines the compiler instruction set which depends on the machine type.
> @@ -607,6 +608,13 @@ config CPU_USE_DOMAINS
> This option enables or disables the use of domain switching
> via the set_fs() function.
>
> +config CPU_HAS_OUTER_PTW
> + bool
> + depends on MMU
> + help
> + This option is enabled if the processors can perform page
> + table walks on the outer cache.
> +
> #
> # CPU supports 36-bit I/O
> #
--
Catalin
^ permalink raw reply [flat|nested] 2+ messages in thread
end of thread, other threads:[~2010-09-29 12:56 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2010-09-07 12:46 [RFC PATCH] ARM: Allow HIGHPTE with OUTER_CACHE if the processor supports outer PTWs Catalin Marinas
2010-09-29 12:56 ` Catalin Marinas
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).