Hi Stefano,
On 26/06/2019 20:30, Julien Grall wrote:
On 6/26/19 8:01 PM, Stefano Stabellini wrote:
On Mon, 10 Jun 2019, Julien Grall wrote:
At the moment, the fixmap table is only hooked when earlyprintk is used.
This is fine today because in C land, the fixmap is not used by anyone
until the the boot CPU is switching to the runtime page-tables.
In the future, the boot CPU will not switch between page-tables to avoid
TLB conflict. This means the fixmap table will need to be hooked before
any use. For simplicity, setup_fixmap() will now do that job.
Can I ask you to reword this slightly, especially the last sentence? It
took me a while to understand what you meant. I suggest:
In the future, the boot CPU will not switch between page-tables to
avoid any TLB conflicts. Thus, the fixmap table will need to be always
hooked before any use. Let's start doing it now in setup_fixmap().
I will update the commit message.
I realized the commit message I wrote is inaccurate and reflected to your
rewording.
Not all the platforms will generate a TLB conflict abort. Some of them may just
decide to use an amalgamation of two entries (see "TLB matching" page D5-2500 in
ARM DDI 0487D.b).
I will replace "any TLB conflicts" by "TLB incoherency".
Acked-by: Stefano Stabellini <sstabell...@kernel.org> >
Let me know if you are happy with the change suggested.
Cheers,
--
Julien Grall
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel
