From: Andrew Banman <abanman@sgi.com>
To: mingo@redhat.com, akpm@linux-foundation.org
Cc: tglx@linutronix.de, hpa@zytor.com, travis@sgi.com, rja@sgi.com,
sivanich@sgi.com, x86@kernel.org, linux-kernel@vger.kernel.org,
abanman@sgi.com
Subject: [PATCH 08/10] arch/x86/platform/uv: BAU UV4 fix payload queue setup
Date: Tue, 20 Sep 2016 17:21:14 -0500 [thread overview]
Message-ID: <1474410076-178329-9-git-send-email-abanman@sgi.com> (raw)
In-Reply-To: <1474410076-178329-1-git-send-email-abanman@sgi.com>
The BAU on UV4 does not need to maintain the payload queue tail pointer. Do
not initialize the tail pointer MMR on UV4.
Note that write_payload_tail is not an abstracted BAU function since it is
an operation specific to pre-UV4 versions. Then we must switch on the UV
version to control its usage, for which we use uvhub_version rather than
is_uv*_hub because it is quicker/more concise.
Signed-off-by: Andrew Banman <abanman@sgi.com>
Acked-by: Mike Travis <travis@sgi.com>
Acked-by: Dimitri Sivanich <sivanich@sgi.com>
---
arch/x86/platform/uv/tlb_uv.c | 16 ++++++++++++----
1 file changed, 12 insertions(+), 4 deletions(-)
diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c
index bfd03db..56d12eb 100644
--- a/arch/x86/platform/uv/tlb_uv.c
+++ b/arch/x86/platform/uv/tlb_uv.c
@@ -1826,11 +1826,19 @@ static void pq_init(int node, int pnode)
first = ops.bau_gpa_to_offset(uv_gpa(pqp));
last = ops.bau_gpa_to_offset(uv_gpa(pqp + (DEST_Q_SIZE - 1)));
- tail = first;
- gnode = uv_gpa_to_gnode(uv_gpa(pqp));
- first = (gnode << UV_PAYLOADQ_GNODE_SHIFT) | tail;
- write_mmr_payload_tail(pnode, tail);
+ /*
+ * Pre UV4, the gnode is required to locate the payload queue
+ * and the payload queue tail must be maintained by the kernel.
+ */
+ bcp = &per_cpu(bau_control, smp_processor_id());
+ if (bcp->uvhub_version <= 3) {
+ tail = first;
+ gnode = uv_gpa_to_gnode(uv_gpa(pqp));
+ first = (gnode << UV_PAYLOADQ_GNODE_SHIFT) | tail;
+ write_mmr_payload_tail(pnode, tail);
+ }
+
ops.write_payload_first(pnode, first);
ops.write_payload_last(pnode, last);
ops.write_g_sw_ack(pnode, 0xffffUL);
--
1.8.5.6
next prev parent reply other threads:[~2016-09-20 22:22 UTC|newest]
Thread overview: 12+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-09-20 22:21 Andrew Banman
2016-09-20 22:21 ` [PATCH 01/10] arch/x86/platform/uv: BAU cleanup: update printks Andrew Banman
2016-09-20 22:21 ` [PATCH 02/10] arch/x86/platform/uv: BAU cleanup: pq_init Andrew Banman
2016-09-20 22:21 ` [PATCH 03/10] arch/x86/platform/uv: BAU replace uv_physnodeaddr Andrew Banman
2016-09-20 22:21 ` [PATCH 04/10] arch/x86/platform/uv: BAU add generic function pointers Andrew Banman
2016-09-20 22:21 ` [PATCH 05/10] arch/x86/platform/uv: BAU use " Andrew Banman
2016-09-20 22:21 ` [PATCH 06/10] arch/x86/platform/uv: BAU UV4 populate uvhub_version Andrew Banman
2016-09-20 22:21 ` [PATCH 07/10] arch/x86/platform/uv: BAU UV4 disable software timeout Andrew Banman
2016-09-20 22:21 ` Andrew Banman [this message]
2016-09-20 22:21 ` [PATCH 09/10] arch/x86/platform/uv: BAU UV4 add version-specific functions Andrew Banman
2016-09-20 22:21 ` [PATCH 10/10] Apply Mike's UV4 fixup patches Andrew Banman
2016-09-20 22:23 ` your mail andrew banman
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=1474410076-178329-9-git-send-email-abanman@sgi.com \
--to=abanman@sgi.com \
--cc=akpm@linux-foundation.org \
--cc=hpa@zytor.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=rja@sgi.com \
--cc=sivanich@sgi.com \
--cc=tglx@linutronix.de \
--cc=travis@sgi.com \
--cc=x86@kernel.org \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.