Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Skip to content
Commit b75bb236 authored by David Howells's avatar David Howells
Browse files

MN10300: The icache invalidate functions should disable the icache first



The icache invalidate functions should disable the icache on AM33 and wait for
it to quiesce before attempting to invalidate it, and should then wait for it
to quiesce again before reenabling it, but on AM34 they should invalidate
directly.  The same goes for the dcache invalidation, but this isn't used much.

Whilst we're at it, this can be wrapped in assembler macros to remove duplicate
code.

The AM33 manual states that:

	An operation that invalidates the cache, switches the writing mode, or
	changes the way mode must be performed after disabling the cache,
	checking the busy bit, and confirming that the cache is not in
	operation.

for the dcache [sec 2.8.3.2.1].  This is not stated so for the icache [sec
2.8.3.1.1] but the example code there suggests that it is.

Whilst the AM34 manual states that the cache must be disabled for both the
icache [sec 1.8.3.2.1] and the dcache [sec 1.8.3.2.1], the Panasonic hardware
engineers say the manual is wrong and that disabling the caches for
invalidation is wrong.

Furthermore, they say that disabling the caches on the AM34 whilst running an
SMP kernel can lead to incoherency between the various CPU caches and should
thus be avoided.

Signed-off-by: default avatarDavid Howells <dhowells@redhat.com>
parent 9ee21723
Loading
Loading
Loading
Loading
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment