From: Thiago Jung Bauermann <bauerman@linux.ibm.com>
To: Alexey Kardashevskiy <aik@ozlabs.ru>
Cc: Michael Anderson <andmike@linux.ibm.com>,
Ram Pai <linuxram@us.ibm.com>,
kvm-ppc@vger.kernel.org, linuxppc-dev@lists.ozlabs.org,
David Gibson <david@gibson.dropbear.id.au>
Subject: Re: [PATCH kernel v2 3/4] powerpc/pseries/iommu: Separate FW_FEATURE_MULTITCE to put/stuff features
Date: Mon, 16 Dec 2019 20:19:46 -0300 [thread overview]
Message-ID: <877e2vuact.fsf@morokweng.localdomain> (raw)
In-Reply-To: <20191216041924.42318-4-aik@ozlabs.ru>
Alexey Kardashevskiy <aik@ozlabs.ru> writes:
> H_PUT_TCE_INDIRECT allows packing up to 512 TCE updates into a single
> hypercall; H_STUFF_TCE can clear lots in a single hypercall too.
>
> However, unlike H_STUFF_TCE (which writes the same TCE to all entries),
> H_PUT_TCE_INDIRECT uses a 4K page with new TCEs. In a secure VM
> environment this means sharing a secure VM page with a hypervisor which
> we would rather avoid.
>
> This splits the FW_FEATURE_MULTITCE feature into FW_FEATURE_PUT_TCE_IND
> and FW_FEATURE_STUFF_TCE. "hcall-multi-tce" in
> the "/rtas/ibm,hypertas-functions" device tree property sets both;
> the "multitce=off" kernel command line parameter disables both.
>
> This should not cause behavioural change.
>
> Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: Thiago Jung Bauermann <bauerman@linux.ibm.com>
Tested-by: Thiago Jung Bauermann <bauerman@linux.ibm.com>
--
Thiago Jung Bauermann
IBM Linux Technology Center
next prev parent reply other threads:[~2019-12-16 23:28 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-12-16 4:19 [PATCH kernel v2 0/4] Enable IOMMU support for pseries Secure VMs Alexey Kardashevskiy
2019-12-16 4:19 ` [PATCH kernel v2 1/4] Revert "powerpc/pseries/iommu: Don't use dma_iommu_ops on secure guests" Alexey Kardashevskiy
2019-12-16 22:58 ` Thiago Jung Bauermann
2020-01-06 23:33 ` Michael Ellerman
2019-12-16 4:19 ` [PATCH kernel v2 2/4] powerpc/pseries: Allow not having ibm, hypertas-functions::hcall-multi-tce for DDW Alexey Kardashevskiy
2019-12-16 23:07 ` Thiago Jung Bauermann
2019-12-17 0:09 ` [PATCH kernel v2 2/4] powerpc/pseries: Allow not having ibm,hypertas-functions::hcall-multi-tce " Alexey Kardashevskiy
2019-12-17 2:06 ` [PATCH kernel v2 2/4] powerpc/pseries: Allow not having ibm, hypertas-functions::hcall-multi-tce " Thiago Jung Bauermann
2020-01-02 22:02 ` [PATCH kernel v2 2/4] powerpc/pseries: Allow not having ibm,hypertas-functions::hcall-multi-tce " Ram Pai
2019-12-16 4:19 ` [PATCH kernel v2 3/4] powerpc/pseries/iommu: Separate FW_FEATURE_MULTITCE to put/stuff features Alexey Kardashevskiy
2019-12-16 23:19 ` Thiago Jung Bauermann [this message]
2020-01-02 22:24 ` Ram Pai
2019-12-16 4:19 ` [PATCH kernel v2 4/4] powerpc/pseries/svm: Allow IOMMU to work in SVM Alexey Kardashevskiy
2019-12-16 23:23 ` Thiago Jung Bauermann
2020-01-02 22:21 ` Ram Pai
2020-01-03 0:08 ` David Gibson
2020-01-03 2:06 ` Ram Pai
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=877e2vuact.fsf@morokweng.localdomain \
--to=bauerman@linux.ibm.com \
--cc=aik@ozlabs.ru \
--cc=andmike@linux.ibm.com \
--cc=david@gibson.dropbear.id.au \
--cc=kvm-ppc@vger.kernel.org \
--cc=linuxppc-dev@lists.ozlabs.org \
--cc=linuxram@us.ibm.com \
/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).