What is bug of OMAP4460 that make oprofile can not run normally
dave.martin at linaro.org
Thu Mar 8 11:09:24 UTC 2012
On Mon, Mar 05, 2012 at 09:49:42PM +0000, Turgis, Frederic wrote:
> There is known bug until r3 ARM version. But it is more like losing 20 to 30% of PMU interrupts, not all.
I understand in any case that the way the PMU overflow interrupt is
routed on omap4 is not supported upstream yet -- see the following
thread for details and patches:
If you are getting no events at all yet, this may help you.
My understanding is that the missed counter overflow issue only applies
to certain situations, and certain events (namely, those that can be
incremented by more than 1 in a cycle).
There are potential workarounds for this which guarantee that no event
is missed, but nothing upstream yet.
> http://lists.linaro.org/pipermail/linaro-dev/2011-September/007598.html (read begin and end)
> OMAP Platform Business Unit - OMAP System Engineering - Platform Enablement - System Multimedia
> Texas Instruments France SA, 821 Avenue Jack Kilby, 06270 Villeneuve Loubet. 036 420 040 R.C.S Antibes. Capital de EUR 753.920
> From: linaro-kernel-bounces at lists.linaro.org [mailto:linaro-kernel-bounces at lists.linaro.org] On Behalf Of Kyler Zhang
> Sent: Monday, March 05, 2012 2:29 PM
> To: linaro-kernel at lists.linaro.org
> Subject: What is bug of OMAP4460 that make oprofile can not run normally
> Hi all,
> We are know that the OMAP4460's PMU is buggy, which loses PMU interrupt always.
> But I do not know what the real bug is, the HW bug or Software bug?
> What the bug is?
> Could some one give a point?
> Kyler Zhang
> linaro-kernel mailing list
> linaro-kernel at lists.linaro.org
More information about the linaro-kernel