7a398c9090
- Resolves: RHEL-184808, Dynamically removing cores from an LPAR is not taking care of NUMA topology - Resolves: RHEL-185098, DLPAR Memory remove/add operations fail
117 lines
3.2 KiB
Diff
117 lines
3.2 KiB
Diff
commit 1c4812fb35510c7e02ff27fc39badbe5eef24611
|
|
Author: Haren Myneni <haren@linux.ibm.com>
|
|
Date: Sat May 16 11:34:20 2026 -0700
|
|
|
|
drmgr: Allocate CPU bitmap for each NUMA node
|
|
|
|
The current code allocates one bitmap and uses it to determine
|
|
number of valid CPUs for each NUMA node and then frees the bitmap.
|
|
The NUMA based CPU removal needs this bitmap per node to determine
|
|
the valid CPU in that node. So this patch retains bitmap per node
|
|
and frees it after DLPAR memory / CPU removal.
|
|
|
|
Signed-off-by: Haren Myneni <haren@linux.ibm.com>
|
|
Reviewed-by: Dave Marquardt <davemarq@linux.ibm.com>
|
|
Signed-off-by: Tyrel Datwyler <tyreld@linux.ibm.com>
|
|
|
|
diff --git a/src/drmgr/common_numa.c b/src/drmgr/common_numa.c
|
|
index 6bc2ea8..eba6c3d 100644
|
|
--- a/src/drmgr/common_numa.c
|
|
+++ b/src/drmgr/common_numa.c
|
|
@@ -84,9 +84,6 @@ static int read_numa_topology(struct ppcnuma_topology *numa)
|
|
|
|
rc = 0;
|
|
|
|
- /* In case of allocation error, the libnuma is calling exit() */
|
|
- cpus = numa_allocate_cpumask();
|
|
-
|
|
for (nid = 0; nid <= max_node; nid++) {
|
|
|
|
if (!numa_bitmask_isbitset(numa_nodes_ptr, nid))
|
|
@@ -98,20 +95,24 @@ static int read_numa_topology(struct ppcnuma_topology *numa)
|
|
break;
|
|
}
|
|
|
|
+ /* In case of allocation error, the libnuma is calling exit() */
|
|
+ cpus = numa_allocate_cpumask();
|
|
+
|
|
rc = numa_node_to_cpus(nid, cpus);
|
|
- if (rc < 0)
|
|
+ if (rc < 0) {
|
|
+ numa_bitmask_free(cpus);
|
|
break;
|
|
+ }
|
|
|
|
/* Count the CPUs in that node */
|
|
for (i = 0; i < cpus->size; i++)
|
|
if (numa_bitmask_isbitset(cpus, i))
|
|
node->n_cpus++;
|
|
|
|
+ node->cpus = cpus;
|
|
numa->cpu_count += node->n_cpus;
|
|
}
|
|
|
|
- numa_bitmask_free(cpus);
|
|
-
|
|
if (rc) {
|
|
ppcnuma_foreach_node(numa, nid, node)
|
|
node->n_cpus = 0;
|
|
@@ -160,6 +161,20 @@ void build_numa_topology(void)
|
|
numa_enabled = 1;
|
|
}
|
|
|
|
+void free_numa_topology(void)
|
|
+{
|
|
+ struct ppcnuma_node *node;
|
|
+ int nid;
|
|
+
|
|
+ ppcnuma_foreach_node(&numa, nid, node) {
|
|
+ if (node) {
|
|
+ if (node->cpus)
|
|
+ numa_bitmask_free(node->cpus);
|
|
+ free(node);
|
|
+ }
|
|
+ }
|
|
+}
|
|
+
|
|
void order_numa_node_ratio_list(void)
|
|
{
|
|
int nid;
|
|
diff --git a/src/drmgr/common_numa.h b/src/drmgr/common_numa.h
|
|
index 2b0901e..7aea026 100644
|
|
--- a/src/drmgr/common_numa.h
|
|
+++ b/src/drmgr/common_numa.h
|
|
@@ -30,6 +30,7 @@ struct ppcnuma_node {
|
|
unsigned int ratio;
|
|
struct dr_node *lmbs; /* linked by lmb_numa_next */
|
|
struct ppcnuma_node *ratio_next;
|
|
+ struct bitmask *cpus;
|
|
};
|
|
|
|
struct ppcnuma_topology {
|
|
@@ -48,6 +49,7 @@ extern int numa_enabled;
|
|
extern struct ppcnuma_topology numa;
|
|
void build_numa_topology(void);
|
|
void order_numa_node_ratio_list(void);
|
|
+void free_numa_topology(void);
|
|
|
|
struct ppcnuma_node *ppcnuma_fetch_node(struct ppcnuma_topology *numa,
|
|
int node_id);
|
|
diff --git a/src/drmgr/drslot_chrp_mem.c b/src/drmgr/drslot_chrp_mem.c
|
|
index 2d22bff..fe04ad1 100644
|
|
--- a/src/drmgr/drslot_chrp_mem.c
|
|
+++ b/src/drmgr/drslot_chrp_mem.c
|
|
@@ -1731,9 +1731,10 @@ int do_mem_kernel_dlpar(void)
|
|
if (usr_action == REMOVE && usr_drc_count && !usr_drc_index) {
|
|
build_numa_topology();
|
|
if (numa_enabled) {
|
|
- if (!numa_based_remove(usr_drc_count))
|
|
+ rc = numa_based_remove(usr_drc_count);
|
|
+ free_numa_topology();
|
|
+ if (!rc)
|
|
return 0;
|
|
-
|
|
/*
|
|
* If the NUMA based removal failed, lets try the legacy
|
|
* way.
|