From: "tip-bot2 for Steve Wahl" <tip-bot2@linutronix.de>
To: linux-tip-commits@vger.kernel.org
Cc: Steve Wahl <steve.wahl@hpe.com>,
"Peter Zijlstra (Intel)" <peterz@infradead.org>,
Kan Liang <kan.liang@linux.intel.com>,
x86@kernel.org, linux-kernel@vger.kernel.org
Subject: [tip: perf/core] perf/x86/intel/uncore: With > 8 nodes, get pci bus die id from NUMA info
Date: Thu, 14 Jan 2021 11:29:03 -0000 [thread overview]
Message-ID: <161062374347.414.10709302386439251120.tip-bot2@tip-bot2> (raw)
In-Reply-To: <20210108153549.108989-3-steve.wahl@hpe.com>
The following commit has been merged into the perf/core branch of tip:
Commit-ID: 9a7832ce3d920426a36cdd78eda4b3568d4d09e3
Gitweb: https://git.kernel.org/tip/9a7832ce3d920426a36cdd78eda4b3568d4d09e3
Author: Steve Wahl <steve.wahl@hpe.com>
AuthorDate: Fri, 08 Jan 2021 09:35:49 -06:00
Committer: Peter Zijlstra <peterz@infradead.org>
CommitterDate: Thu, 14 Jan 2021 11:20:14 +01:00
perf/x86/intel/uncore: With > 8 nodes, get pci bus die id from NUMA info
The registers used to determine which die a pci bus belongs to don't
contain enough information to uniquely specify more than 8 dies, so
when more than 8 dies are present, use NUMA information instead.
Continue to use the previous method for 8 or fewer because it
works there, and covers cases of NUMA being disabled.
Signed-off-by: Steve Wahl <steve.wahl@hpe.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Kan Liang <kan.liang@linux.intel.com>
Link: https://lkml.kernel.org/r/20210108153549.108989-3-steve.wahl@hpe.com
---
arch/x86/events/intel/uncore_snbep.c | 93 ++++++++++++++++++---------
1 file changed, 65 insertions(+), 28 deletions(-)
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 2d7014d..b79951d 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -1370,40 +1370,77 @@ static int snbep_pci2phy_map_init(int devid, int nodeid_loc, int idmap_loc, bool
if (!ubox_dev)
break;
bus = ubox_dev->bus->number;
- /* get the Node ID of the local register */
- err = pci_read_config_dword(ubox_dev, nodeid_loc, &config);
- if (err)
- break;
- nodeid = config & NODE_ID_MASK;
- /* get the Node ID mapping */
- err = pci_read_config_dword(ubox_dev, idmap_loc, &config);
- if (err)
- break;
+ /*
+ * The nodeid and idmap registers only contain enough
+ * information to handle 8 nodes. On systems with more
+ * than 8 nodes, we need to rely on NUMA information,
+ * filled in from BIOS supplied information, to determine
+ * the topology.
+ */
+ if (nr_node_ids <= 8) {
+ /* get the Node ID of the local register */
+ err = pci_read_config_dword(ubox_dev, nodeid_loc, &config);
+ if (err)
+ break;
+ nodeid = config & NODE_ID_MASK;
+ /* get the Node ID mapping */
+ err = pci_read_config_dword(ubox_dev, idmap_loc, &config);
+ if (err)
+ break;
- segment = pci_domain_nr(ubox_dev->bus);
- raw_spin_lock(&pci2phy_map_lock);
- map = __find_pci2phy_map(segment);
- if (!map) {
+ segment = pci_domain_nr(ubox_dev->bus);
+ raw_spin_lock(&pci2phy_map_lock);
+ map = __find_pci2phy_map(segment);
+ if (!map) {
+ raw_spin_unlock(&pci2phy_map_lock);
+ err = -ENOMEM;
+ break;
+ }
+
+ /*
+ * every three bits in the Node ID mapping register maps
+ * to a particular node.
+ */
+ for (i = 0; i < 8; i++) {
+ if (nodeid == ((config >> (3 * i)) & 0x7)) {
+ if (topology_max_die_per_package() > 1)
+ die_id = i;
+ else
+ die_id = topology_phys_to_logical_pkg(i);
+ map->pbus_to_dieid[bus] = die_id;
+ break;
+ }
+ }
raw_spin_unlock(&pci2phy_map_lock);
- err = -ENOMEM;
- break;
- }
+ } else {
+ int node = pcibus_to_node(ubox_dev->bus);
+ int cpu;
+
+ segment = pci_domain_nr(ubox_dev->bus);
+ raw_spin_lock(&pci2phy_map_lock);
+ map = __find_pci2phy_map(segment);
+ if (!map) {
+ raw_spin_unlock(&pci2phy_map_lock);
+ err = -ENOMEM;
+ break;
+ }
- /*
- * every three bits in the Node ID mapping register maps
- * to a particular node.
- */
- for (i = 0; i < 8; i++) {
- if (nodeid == ((config >> (3 * i)) & 0x7)) {
- if (topology_max_die_per_package() > 1)
- die_id = i;
- else
- die_id = topology_phys_to_logical_pkg(i);
- map->pbus_to_dieid[bus] = die_id;
+ die_id = -1;
+ for_each_cpu(cpu, cpumask_of_pcibus(ubox_dev->bus)) {
+ struct cpuinfo_x86 *c = &cpu_data(cpu);
+
+ if (c->initialized && cpu_to_node(cpu) == node) {
+ map->pbus_to_dieid[bus] = die_id = c->logical_die_id;
+ break;
+ }
+ }
+ raw_spin_unlock(&pci2phy_map_lock);
+
+ if (WARN_ON_ONCE(die_id == -1)) {
+ err = -EINVAL;
break;
}
}
- raw_spin_unlock(&pci2phy_map_lock);
}
if (!err) {
next prev parent reply other threads:[~2021-01-14 11:30 UTC|newest]
Thread overview: 10+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-01-08 15:35 [PATCH 0/2] perf/x86/intel/uncore: Derive die id from NUMA info with more than 8 nodes Steve Wahl
2021-01-08 15:35 ` [PATCH 1/2] perf/x86/intel/uncore: Store the logical die id instead of the physical die id Steve Wahl
2021-01-14 11:29 ` [tip: perf/core] " tip-bot2 for Steve Wahl
2021-01-08 15:35 ` [PATCH 2/2] perf/x86/intel/uncore: With > 8 nodes, get pci bus die id from NUMA info Steve Wahl
2021-01-11 13:00 ` Peter Zijlstra
2021-01-11 15:45 ` Steve Wahl
2021-01-12 15:07 ` Peter Zijlstra
2021-01-12 19:42 ` Steve Wahl
2021-01-14 11:29 ` tip-bot2 for Steve Wahl [this message]
2021-01-11 16:39 ` [PATCH 0/2] perf/x86/intel/uncore: Derive die id from NUMA info with more than 8 nodes Liang, Kan
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=161062374347.414.10709302386439251120.tip-bot2@tip-bot2 \
--to=tip-bot2@linutronix.de \
--cc=kan.liang@linux.intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-tip-commits@vger.kernel.org \
--cc=peterz@infradead.org \
--cc=steve.wahl@hpe.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 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).