linux-arm-kernel.lists.infradead.org archive mirror
 help / color / mirror / Atom feed
From: dave.martin@linaro.org (Dave Martin)
To: linux-arm-kernel@lists.infradead.org
Subject: [PATCH v4 00/15] multi-cluster power management
Date: Wed, 24 Apr 2013 15:25:47 +0100	[thread overview]
Message-ID: <20130424142547.GB2664@linaro.org> (raw)
In-Reply-To: <alpine.LFD.2.03.1304231657150.17375@syhkavp.arg>

On Tue, Apr 23, 2013 at 05:03:06PM -0400, Nicolas Pitre wrote:
> On Tue, 23 Apr 2013, Russell King - ARM Linux wrote:
> 
> > What I suggest for the time being is to provide new inline function(s)
> > in arch/arm/include/cacheflush.h which are purposed for your application,
> > document them in that file, and call the implementation you're currently
> > using.  That means if we do have to change it in the future (for example,
> > we don't need to do anything in the dcache flushing stuff) we don't have
> > to hunt through all the code to find _your_ different use of that function
> > and fix it - we can just fix it in one place and we have the reference
> > there for what your code expects.
> 
> What about the patch below?  Once you tell me it is fine to you I'll 
> adapt the MCPM series to it.

This looks appropriate for mcpm's needs, and generic enough for other
code to reuse.  Thanks for that.

Acked-by: Dave Martin <dave.martin@linaro.org>

> 
> ----- >8
> From: Nicolas Pitre <nicolas.pitre@linaro.org>
> Date: Tue, 23 Apr 2013 16:45:40 -0400
> Subject: [PATCH] ARM: cacheflush: add synchronization helpers for mixed cache state accesses
> 
> Algorithms used by the MCPM layer rely on state variables which are
> accessed while the cache is either active or inactive, depending
> on the code path and the active state.
> 
> This patch introduces generic cache maintenance helpers to provide the
> necessary cache synchronization for such state variables to always hit
> main memory in a ordered way.
> 
> Signed-off-by: Nicolas Pitre <nico@linaro.org>
> 
> diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h
> index e1489c54cd..bff71388e7 100644
> --- a/arch/arm/include/asm/cacheflush.h
> +++ b/arch/arm/include/asm/cacheflush.h
> @@ -363,4 +363,79 @@ static inline void flush_cache_vunmap(unsigned long start, unsigned long end)
>  		flush_cache_all();
>  }
>  
> +/*
> + * Memory synchronization helpers for mixed cached vs non cached accesses.
> + *
> + * Some synchronization algorithms have to set states in memory with the
> + * cache enabled or disabled depending on the code path.  It is crucial
> + * to always ensure proper cache maintenance to update main memory right
> + * away in that case.
> + *
> + * Any cached write must be followed by a cache clean operation.
> + * Any cached read must be preceded by a cache invalidate operation.
> + * Yet, in the read case, a cache flush i.e. atomic clean+invalidate
> + * operation is needed to avoid discarding possible concurrent writes to the
> + * accessed memory.
> + *
> + * Also, in order to prevent a cached writer from interfering with an
> + * adjacent non-cached writer, each state variable must be located to
> + * a separate cache line.
> + */
> +
> +/*
> + * This needs to be >= the max cache writeback size of all
> + * supported platforms included in the current kernel configuration.
> + * This is used to align state variables to their own cache lines.
> + */
> +#define __CACHE_WRITEBACK_ORDER 6  /* guessed from existing platforms */
> +#define __CACHE_WRITEBACK_GRANULE (1 << __CACHE_WRITEBACK_ORDER)
> +
> +/*
> + * There is no __cpuc_clean_dcache_area but we use it anyway for
> + * code intent clarity, and alias it to __cpuc_flush_dcache_area.
> + */
> +#define __cpuc_clean_dcache_area __cpuc_flush_dcache_area
> +
> +/*
> + * Ensure preceding writes to *p by this CPU are visible to
> + * subsequent reads by other CPUs:
> + */
> +static inline void __sync_cache_range_w(volatile void *p, size_t size)
> +{
> +	char *_p = (char *)p;
> +
> +	__cpuc_clean_dcache_area(_p, size);
> +	outer_clean_range(__pa(_p), __pa(_p + size));
> +}
> +
> +/*
> + * Ensure preceding writes to *p by other CPUs are visible to
> + * subsequent reads by this CPU.  We must be careful not to
> + * discard data simultaneously written by another CPU, hence the
> + * usage of flush rather than invalidate operations.
> + */
> +static inline void __sync_cache_range_r(volatile void *p, size_t size)
> +{
> +	char *_p = (char *)p;
> +
> +#ifdef CONFIG_OUTER_CACHE
> +	if (outer_cache.flush_range) {
> +		/*
> +		 * Ensure dirty data migrated from other CPUs into our cache
> +		 * are cleaned out safely before the outer cache is cleaned:
> +		 */
> +		__cpuc_clean_dcache_area(_p, size);
> +
> +		/* Clean and invalidate stale data for *p from outer ... */
> +		outer_flush_range(__pa(_p), __pa(_p + size));
> +	}
> +#endif
> +
> +	/* ... and inner cache: */
> +	__cpuc_flush_dcache_area(_p, size);
> +}
> +
> +#define sync_cache_w(ptr) __sync_cache_range_w(ptr, sizeof *(ptr))
> +#define sync_cache_r(ptr) __sync_cache_range_r(ptr, sizeof *(ptr))
> +
>  #endif

  parent reply	other threads:[~2013-04-24 14:25 UTC|newest]

Thread overview: 55+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-02-05  5:21 [PATCH v4 00/15] multi-cluster power management Nicolas Pitre
2013-02-05  5:21 ` [PATCH v4 01/15] ARM: multi-cluster PM: secondary kernel entry code Nicolas Pitre
2013-04-23 19:19   ` Russell King - ARM Linux
2013-04-23 19:34     ` Nicolas Pitre
2013-04-23 20:09       ` Russell King - ARM Linux
2013-04-23 20:19         ` Nicolas Pitre
2013-02-05  5:21 ` [PATCH v4 02/15] ARM: mcpm: introduce the CPU/cluster power API Nicolas Pitre
2013-02-05  5:22 ` [PATCH v4 03/15] ARM: mcpm: introduce helpers for platform coherency exit/setup Nicolas Pitre
2013-04-05 23:00   ` Olof Johansson
2013-04-06 13:41     ` Nicolas Pitre
2013-04-24  9:10     ` Dave Martin
2013-02-05  5:22 ` [PATCH v4 04/15] ARM: mcpm: Add baremetal voting mutexes Nicolas Pitre
2013-02-05  5:22 ` [PATCH v4 05/15] ARM: mcpm_head.S: vlock-based first man election Nicolas Pitre
2013-02-05  5:22 ` [PATCH v4 06/15] ARM: mcpm: generic SMP secondary bringup and hotplug support Nicolas Pitre
2013-04-23 19:31   ` Russell King - ARM Linux
2013-04-23 19:36     ` Nicolas Pitre
2013-02-05  5:22 ` [PATCH v4 07/15] ARM: introduce common set_auxcr/get_auxcr functions Nicolas Pitre
2013-02-05  5:22 ` [PATCH v4 08/15] ARM: vexpress: introduce DCSCB support Nicolas Pitre
2013-02-07 18:14   ` Catalin Marinas
2013-02-07 18:56     ` Nicolas Pitre
2013-02-05  5:22 ` [PATCH v4 09/15] ARM: vexpress/dcscb: add CPU use counts to the power up/down API implementation Nicolas Pitre
2013-02-05  5:22 ` [PATCH v4 10/15] ARM: vexpress/dcscb: do not hardcode number of CPUs per cluster Nicolas Pitre
2013-02-05  5:22 ` [PATCH v4 11/15] drivers/bus: add ARM CCI support Nicolas Pitre
2013-04-23 19:38   ` Russell King - ARM Linux
2013-04-23 19:53     ` Nicolas Pitre
2013-02-05  5:22 ` [PATCH v4 12/15] ARM: CCI: ensure powerdown-time data is flushed from cache Nicolas Pitre
2013-04-23 19:40   ` Russell King - ARM Linux
2013-02-05  5:22 ` [PATCH v4 13/15] ARM: vexpress/dcscb: handle platform coherency exit/setup and CCI Nicolas Pitre
2013-02-05  5:22 ` [PATCH v4 14/15] ARM: Enable selection of SMP operations at boot time Nicolas Pitre
2013-04-05 22:43   ` Olof Johansson
2013-04-06 13:43     ` Nicolas Pitre
2013-04-09 16:30   ` Nicolas Pitre
2013-04-09 16:55     ` Jon Medhurst (Tixy)
2013-02-05  5:22 ` [PATCH v4 15/15] ARM: vexpress: Select multi-cluster SMP operation if required Nicolas Pitre
2013-02-06 16:38   ` Pawel Moll
2013-02-06 17:55     ` Nicolas Pitre
2013-04-05 22:48   ` Olof Johansson
2013-04-06 14:02     ` Nicolas Pitre
2013-04-08  9:10       ` Jon Medhurst (Tixy)
2013-04-09  5:41         ` Nicolas Pitre
2013-04-09  6:00           ` Jon Medhurst (Tixy)
2013-04-09 16:34             ` Nicolas Pitre
2013-04-09 17:28               ` Jon Medhurst (Tixy)
2013-04-23 19:42   ` Russell King - ARM Linux
2013-04-23 19:56     ` Nicolas Pitre
2013-04-23 20:04 ` [PATCH v4 00/15] multi-cluster power management Russell King - ARM Linux
2013-04-23 21:03   ` Nicolas Pitre
2013-04-23 21:46     ` Russell King - ARM Linux
2013-04-23 21:56       ` Nicolas Pitre
2013-04-23 22:44         ` Russell King - ARM Linux
2013-04-24  4:11           ` Nicolas Pitre
2013-04-24 20:25             ` Russell King - ARM Linux
2013-04-24 23:31               ` Nicolas Pitre
2013-04-24 14:25     ` Dave Martin [this message]
2013-04-23 21:11   ` Nicolas Pitre

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20130424142547.GB2664@linaro.org \
    --to=dave.martin@linaro.org \
    --cc=linux-arm-kernel@lists.infradead.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
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).