patch 'eal: fix undetected NUMA nodes' has been queued to stable release 22.11.8

[luca.boccassi at gmail.com]

Hi,

FYI, your patch has been queued to stable release 22.11.8

Note it hasn't been pushed to http://dpdk.org/browse/dpdk-stable yet.
It will be pushed if I get no objections before 03/27/25. So please
shout if anyone has objections.

Also note that after the patch there's a diff of the upstream commit vs the
patch applied to the branch. This will indicate if there was any rebasing
needed to apply to the stable branch. If there were code changes for rebasing
(ie: not only metadata diffs), please double check that the rebase was
correctly done.

Queued patches are on a temporary branch at:
https://github.com/bluca/dpdk-stable

This queued commit can be viewed at:
https://github.com/bluca/dpdk-stable/commit/e4081bc8044358481867c5860933aeb5d7aa2d8c

Thanks.

Luca Boccassi

---
>From e4081bc8044358481867c5860933aeb5d7aa2d8c Mon Sep 17 00:00:00 2001
From: Bruce Richardson <bruce.richardson at intel.com>
Date: Wed, 5 Mar 2025 16:24:58 +0000
Subject: [PATCH] eal: fix undetected NUMA nodes

[ upstream commit ef41b96461703c766e4a39ecf4bf7cb731d9617d ]

In cases where the number of cores on a given socket is greater than
RTE_MAX_LCORES, then EAL will be unaware of all the sockets/numa nodes
on a system. Fix this limitation by having the EAL probe the NUMA node
for cores it isn't going to use, and recording that for completeness.

This is necessary as memory is tracked per node, and with the --lcores
parameters our app lcores may be on different sockets than the lcore ids
may imply. For example, lcore 0 is on socket zero, but if app is run
with --lcores=0 at 64, then DPDK lcore 0 may be on socket one, so DPDK
needs to be aware of that socket.

Fixes: 952b20777255 ("eal: provide API for querying valid socket ids")

Signed-off-by: Bruce Richardson <bruce.richardson at intel.com>
---
 lib/eal/common/eal_common_lcore.c | 17 ++++++++++++-----
 1 file changed, 12 insertions(+), 5 deletions(-)

diff --git a/lib/eal/common/eal_common_lcore.c b/lib/eal/common/eal_common_lcore.c
index 06c594b022..787dbaff36 100644
--- a/lib/eal/common/eal_common_lcore.c
+++ b/lib/eal/common/eal_common_lcore.c
@@ -140,7 +140,11 @@ rte_eal_cpu_init(void)
 	unsigned lcore_id;
 	unsigned count = 0;
 	unsigned int socket_id, prev_socket_id;
-	int lcore_to_socket_id[RTE_MAX_LCORE];
+#if CPU_SETSIZE > RTE_MAX_LCORE
+	int lcore_to_socket_id[CPU_SETSIZE] = {0};
+#else
+	int lcore_to_socket_id[RTE_MAX_LCORE] = {0};
+#endif
 
 	/*
 	 * Parse the maximum set of logical cores, detect the subset of running
@@ -179,9 +183,11 @@ rte_eal_cpu_init(void)
 	for (; lcore_id < CPU_SETSIZE; lcore_id++) {
 		if (eal_cpu_detected(lcore_id) == 0)
 			continue;
+		socket_id = eal_cpu_socket_id(lcore_id);
+		lcore_to_socket_id[lcore_id] = socket_id;
 		RTE_LOG(DEBUG, EAL, "Skipped lcore %u as core %u on socket %u\n",
 			lcore_id, eal_cpu_core_id(lcore_id),
-			eal_cpu_socket_id(lcore_id));
+			socket_id);
 	}
 
 	/* Set the count of enabled logical cores of the EAL configuration */
@@ -197,12 +203,13 @@ rte_eal_cpu_init(void)
 
 	prev_socket_id = -1;
 	config->numa_node_count = 0;
-	for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) {
+	for (lcore_id = 0; lcore_id < RTE_DIM(lcore_to_socket_id); lcore_id++) {
 		socket_id = lcore_to_socket_id[lcore_id];
 		if (socket_id != prev_socket_id)
-			config->numa_nodes[config->numa_node_count++] =
-					socket_id;
+			config->numa_nodes[config->numa_node_count++] =	socket_id;
 		prev_socket_id = socket_id;
+		if (config->numa_node_count >= RTE_MAX_NUMA_NODES)
+			break;
 	}
 	RTE_LOG(INFO, EAL, "Detected NUMA nodes: %u\n", config->numa_node_count);
 
-- 
2.47.2

---
  Diff of the applied patch vs upstream commit (please double-check if non-empty:
---
--- -	2025-03-25 11:23:58.243823149 +0000
+++ 0001-eal-fix-undetected-NUMA-nodes.patch	2025-03-25 11:23:58.213308917 +0000
@@ -1 +1 @@
-From ef41b96461703c766e4a39ecf4bf7cb731d9617d Mon Sep 17 00:00:00 2001
+From e4081bc8044358481867c5860933aeb5d7aa2d8c Mon Sep 17 00:00:00 2001
@@ -5,0 +6,2 @@
+[ upstream commit ef41b96461703c766e4a39ecf4bf7cb731d9617d ]
+
@@ -18 +19,0 @@
-Cc: stable at dpdk.org
@@ -26 +27 @@
-index 2ff9252c52..820a6534b1 100644
+index 06c594b022..787dbaff36 100644
@@ -29 +30 @@
-@@ -144,7 +144,11 @@ rte_eal_cpu_init(void)
+@@ -140,7 +140,11 @@ rte_eal_cpu_init(void)
@@ -42 +43 @@
-@@ -183,9 +187,11 @@ rte_eal_cpu_init(void)
+@@ -179,9 +183,11 @@ rte_eal_cpu_init(void)
@@ -48 +49 @@
- 		EAL_LOG(DEBUG, "Skipped lcore %u as core %u on socket %u",
+ 		RTE_LOG(DEBUG, EAL, "Skipped lcore %u as core %u on socket %u\n",
@@ -55 +56 @@
-@@ -201,12 +207,13 @@ rte_eal_cpu_init(void)
+@@ -197,12 +203,13 @@ rte_eal_cpu_init(void)
@@ -70 +71 @@
- 	EAL_LOG(INFO, "Detected NUMA nodes: %u", config->numa_node_count);
+ 	RTE_LOG(INFO, EAL, "Detected NUMA nodes: %u\n", config->numa_node_count);