From: khilman@ti•com (Kevin Hilman)
To: linux-arm-kernel@lists•infradead.org
Subject: [PATCH 02/25] OMAP4: Redefine mandatory barriers for OMAP to include interconnect barriers.
Date: Thu, 15 Sep 2011 10:17:31 -0700 [thread overview]
Message-ID: <87obyl7mj8.fsf@ti.com> (raw)
In-Reply-To: <4E7080F8.9020302@ti.com> (Santosh's message of "Wed, 14 Sep 2011 15:54:56 +0530")
Santosh <santosh.shilimkar@ti•com> writes:
> On Wednesday 14 September 2011 01:57 AM, Tony Lindgren wrote:
>> * Santosh Shilimkar<santosh.shilimkar@ti•com> [110904 06:22]:
>>> On OMAP4 SOC intecronnects has many write buffers in the async bridges
>>> and they can be drained only with stongly ordered accesses.
>>
>> This is not correct, strongly ordered access does not guarantee
>> anything here. If it fixes issues, it's because it makes the writes
>> to reach the device faster. Strongly ordered does not affect anything
>> outside ARM, so the bus access won't change.
>>
> What I said is the aync bridges WB and what is said is correct
> from MPU accesses point of view.
>
> It's not about faster or slower. With device memory the, writes
> can get stuck into write buffers where as with SO, the write buffers
> will be bypassed.
>
> The behaviours is limited to the MPU side async bridge boundary which
> is the problem. The statement is not for l3 and l4 interconnect which
> probably you mean.
>
> There is always a hardware signal to communicate CPU at async bridges
> to ensure that data is not stuck in these bridges before CPU
> clock/voltage is cut. Unfortunately we have a BUG on OMAP44XX devices
> and the dual channel makes it even worst since both pipes have the
> same BUG. So what we are doing is issuing SO write/read accesses
> on these pipes so that there is nothing stuck there before MPU
> hits low power states and also avoids any race conditions when
> both channels are used together by some initiators. The behaviour
> is validated at RTL level and there is no ambiguity about it.
>
> May be you have mistaken the L3 and L4 as the interconnect levels
> in this case.
Sounds to me like the changelog needs to be a bit more verbose.
Remember, we're all probably going to forget the gory details of this in
a few months and want to be able to go back to the code w/changelog to
refresh our memories.
Thanks,
Kevin
next prev parent reply other threads:[~2011-09-15 17:17 UTC|newest]
Thread overview: 119+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-09-04 13:54 [PATCH 00/25] OMAP4: PM: suspend, CPU-hotplug and CPUilde support Santosh Shilimkar
2011-09-04 13:54 ` [PATCH 01/25] ARM: mm: Add strongly ordered descriptor support Santosh Shilimkar
2011-09-13 20:23 ` Tony Lindgren
2011-09-14 5:36 ` Shilimkar, Santosh
2011-09-04 13:54 ` [PATCH 02/25] OMAP4: Redefine mandatory barriers for OMAP to include interconnect barriers Santosh Shilimkar
2011-09-13 20:27 ` Tony Lindgren
2011-09-14 5:39 ` Shilimkar, Santosh
2011-09-14 10:24 ` Santosh
2011-09-15 17:17 ` Kevin Hilman [this message]
2011-09-15 17:24 ` Shilimkar, Santosh
2011-09-15 17:53 ` Tony Lindgren
2011-09-15 18:22 ` Shilimkar, Santosh
2011-09-15 19:43 ` Tony Lindgren
2011-09-15 20:00 ` Shilimkar, Santosh
2011-09-16 12:01 ` Shilimkar, Santosh
2011-09-04 13:54 ` [PATCH 03/25] OMAP4: PM: Use custom omap_do_wfi() for suspend and default idle Santosh Shilimkar
2011-09-04 13:54 ` [PATCH 04/25] OMAP4: Remove un-used do_wfi() macro Santosh Shilimkar
2011-09-04 13:54 ` [PATCH 05/25] OMAP4: Use WARN_ON() instead of BUG_ON() with graceful exit Santosh Shilimkar
2011-09-05 10:11 ` Sergei Shtylyov
2011-09-05 10:42 ` Santosh
2011-09-05 10:47 ` Russell King - ARM Linux
2011-09-05 10:51 ` Santosh
2011-09-08 18:51 ` Jean Pihet
2011-09-04 13:54 ` [PATCH 06/25] OMAP4: Export omap4_get_base*() rather than global address pointers Santosh Shilimkar
2011-09-04 13:54 ` [PATCH 07/25] OMAP4: PM: Add SAR RAM support Santosh Shilimkar
2011-09-04 13:54 ` [PATCH 08/25] OMAP4: PM: Keep static dep between MPUSS-EMIF and MPUSS-L3 and DUCATI-L3 Santosh Shilimkar
2011-09-08 18:06 ` Kevin Hilman
2011-09-09 4:21 ` Santosh
2011-09-04 13:54 ` [PATCH 09/25] OMAP4: PM: Avoid omap4_pm_init() on OMAP4430 ES1.0 Santosh Shilimkar
2011-09-04 13:54 ` [PATCH 10/25] OMAP4: PM: Initialise all the clockdomains to supported states Santosh Shilimkar
2011-09-04 13:54 ` [PATCH 11/25] OMAP: Add Secure HAL and monitor mode API infrastructure Santosh Shilimkar
2011-09-08 18:58 ` Jean Pihet
2011-09-09 4:22 ` Santosh
2011-09-04 13:54 ` [PATCH 12/25] OMAP: Add support to allocate the memory for secure RAM Santosh Shilimkar
2011-09-08 19:19 ` Jean Pihet
2011-09-09 9:43 ` Santosh
2011-09-09 12:54 ` Jean Pihet
2011-09-09 14:09 ` Shilimkar, Santosh
2011-09-04 13:54 ` [PATCH 13/25] OMAP4: PM: Add WakeupGen module as OMAP gic_arch_extn Santosh Shilimkar
2011-09-08 18:27 ` Kevin Hilman
2011-09-09 4:29 ` Santosh
2011-09-09 7:19 ` Thomas Gleixner
2011-09-09 8:07 ` Santosh
2011-09-09 8:18 ` Thomas Gleixner
2011-09-09 9:05 ` Santosh
2011-09-12 7:56 ` Thomas Gleixner
2011-09-12 8:44 ` Santosh
2011-09-08 19:16 ` Jean Pihet
2011-09-09 4:23 ` Santosh
2011-09-13 20:36 ` Tony Lindgren
2011-09-14 5:34 ` Shilimkar, Santosh
2011-09-14 15:21 ` Tony Lindgren
2011-09-14 16:49 ` Santosh
2011-09-14 17:08 ` Tony Lindgren
2011-09-14 17:13 ` Santosh
2011-09-14 17:18 ` Tony Lindgren
2011-09-14 17:21 ` Santosh
2011-09-14 17:22 ` Santosh
2011-09-14 19:04 ` Tony Lindgren
2011-09-15 2:57 ` Santosh
2011-09-15 9:36 ` Cousson, Benoit
2011-09-15 12:02 ` Shilimkar, Santosh
2011-09-15 13:29 ` Woodruff, Richard
2011-09-04 13:54 ` [PATCH 14/25] OMAP4: PM: Add CPUX OFF mode support Santosh Shilimkar
2011-09-08 19:39 ` Jean Pihet
2011-09-09 9:59 ` Santosh
2011-09-09 8:04 ` Shawn Guo
2011-09-09 8:09 ` Santosh
2011-09-09 14:13 ` Shawn Guo
2011-09-09 14:11 ` Shilimkar, Santosh
2011-09-09 15:27 ` Shawn Guo
2011-09-09 16:59 ` Santosh
2011-09-09 18:34 ` Kevin Hilman
2011-09-10 3:39 ` Shilimkar, Santosh
2011-09-09 23:34 ` Shawn Guo
2011-09-10 3:38 ` Shilimkar, Santosh
2011-09-10 4:54 ` Shawn Guo
2011-09-10 5:51 ` Santosh
2011-09-12 21:06 ` Kevin Hilman
2011-09-13 5:39 ` Santosh
2011-09-13 17:33 ` Kevin Hilman
2011-09-14 5:26 ` Shilimkar, Santosh
2011-09-04 13:54 ` [PATCH 15/25] OMAP4: Remove __INIT from omap_secondary_startup() to re-use it for hotplug Santosh Shilimkar
2011-09-04 13:54 ` [PATCH 16/25] OMAP4: PM: Program CPU1 to hit OFF when off-lined Santosh Shilimkar
2011-09-12 21:12 ` Kevin Hilman
2011-09-13 5:35 ` Santosh
2011-09-04 13:54 ` [PATCH 17/25] OMAP4: PM: CPU1 wakeup workaround from Low power modes Santosh Shilimkar
2011-09-04 13:54 ` [PATCH 18/25] OMAP4: suspend: Add MPUSS power domain RETENTION support Santosh Shilimkar
2011-09-15 0:27 ` Kevin Hilman
2011-09-15 3:19 ` Santosh
2011-09-04 13:54 ` [PATCH 19/25] OMAP4: PM: Add WakeupGen and secure GIC low power support Santosh Shilimkar
2011-09-04 13:54 ` [PATCH 20/25] OMAP4: PM: Add L2X0 cache lowpower support Santosh Shilimkar
2011-09-05 14:01 ` Lorenzo Pieralisi
2011-09-05 14:13 ` Santosh
2011-09-16 17:23 ` Kevin Hilman
2011-09-18 8:46 ` Santosh
2011-09-04 13:54 ` [PATCH 21/25] OMAP4: PM: Add MPUSS power domain OSWR support Santosh Shilimkar
2011-09-12 18:52 ` Kevin Hilman
2011-09-13 5:37 ` Santosh
2011-09-13 7:39 ` Jean Pihet
2011-09-13 8:25 ` Santosh
2011-09-04 13:54 ` [PATCH 22/25] OMAP4: PM: Add power domain statistics support Santosh Shilimkar
2011-09-05 10:08 ` Sergei Shtylyov
2011-09-05 10:43 ` Santosh
2011-09-04 13:54 ` [PATCH 23/25] OMAP4: PM: Add CPUidle support Santosh Shilimkar
2011-09-16 17:45 ` Kevin Hilman
2011-09-18 8:47 ` Santosh
2011-09-04 13:54 ` [PATCH 24/25] OMAP4: cpuidle: Switch to gptimer from twd in deeper C-states Santosh Shilimkar
2011-09-16 17:51 ` Kevin Hilman
2011-09-18 8:48 ` Santosh
2011-09-04 13:54 ` [PATCH 25/25] OMAP3: CPUidle: Make use of CPU PM notifiers Santosh Shilimkar
2011-09-08 17:57 ` Kevin Hilman
2011-09-09 4:20 ` Santosh
2011-09-09 7:17 ` Santosh
2011-09-08 20:15 ` [PATCH 00/25] OMAP4: PM: suspend, CPU-hotplug and CPUilde support Jean Pihet
2011-09-09 4:25 ` Santosh
2011-09-20 11:24 ` Vishwanath Sripathy
2011-09-20 11:37 ` Santosh
2011-09-20 11:57 ` Santosh
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=87obyl7mj8.fsf@ti.com \
--to=khilman@ti$(echo .)com \
--cc=linux-arm-kernel@lists$(echo .)infradead.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
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