From 1dee26c2a60dd9a5264331cc20143a5590289187 Mon Sep 17 00:00:00 2001
From: Haren Myneni <haren@linux.ibm.com>
Date: Mon, 18 May 2026 22:37:53 -0700
Subject: [PATCH 10/11] drmgr: Add timeout signal handling for NUMA memory
 REMOVE

Upstream: merged, expected in v1.3.15
Git-commit: 1dee26c2a60dd9a5264331cc20143a5590289187

RMC expects drmgr timeout based on value passed with -w option and
drmgr can check fequently for each LMB removal request and exits
once reached the timeout value. But this check happens only in the
user space and does not consider when executes in the kernel to
remove memory. In the case of LMB removal, the kernel expects to
run longer until all pages in LMB are isolated and can return to
the user space for any pending signals.

This patch enables SIGALRM signal based on the user defined
value which generates signal when the timer expires. It allows
the kernel interface returns in case [age isolation is taking
longer and drmgr timeout.

Signed-off-by: Haren Myneni <haren@linux.ibm.com>
Signed-off-by: Tyrel Datwyler <tyreld@linux.ibm.com>
---
 src/drmgr/drslot_chrp_mem.c | 46 ++++++++++++++++++++++++++++++++++++-
 1 file changed, 45 insertions(+), 1 deletion(-)

diff --git a/src/drmgr/drslot_chrp_mem.c b/src/drmgr/drslot_chrp_mem.c
index fe04ad1..5a08839 100644
--- a/src/drmgr/drslot_chrp_mem.c
+++ b/src/drmgr/drslot_chrp_mem.c
@@ -26,6 +26,9 @@
 #include <dirent.h>
 #include <inttypes.h>
 #include <time.h>
+#include <signal.h>
+#include <unistd.h>
+#include <stdbool.h>
 #include <sys/wait.h>
 #include <sys/stat.h>
 #include "dr.h"
@@ -35,6 +38,7 @@
 
 uint64_t block_sz_bytes = 0;
 static char *state_strs[] = {"offline", "online"};
+sig_atomic_t numa_mem_timeout = 0;
 
 static char *usagestr = "-c mem {-a | -r} {-q <quantity> -p {variable_weight | ent_capacity} | {-q <quantity> | -s [<drc_name> | <drc_index>]}}";
 
@@ -50,6 +54,14 @@ mem_usage(char **pusage)
 	*pusage = usagestr;
 }
 
+/*
+ * SIGALRM handler for drmgr timeout
+ */
+void mem_timeout_handler(int sig)
+{
+	numa_mem_timeout = 1;
+}
+
 /**
  * report_resource_count
  * @brief Report the number of LMBs that were added or removed.
@@ -1681,13 +1693,45 @@ static void clear_numa_lmb_links(void)
 		node->lmbs = NULL;
 }
 
+/*
+ * Setup SIGALRM signal based on timeout value passed by the user
+ * (with -w option). In the case of LMB removal, the kernel
+ * interface can run longer until all pages in LMB are isolated
+ * and can return to the user space if any pending signals.
+ * This SIGALRM signal can exit the kernel in case LMB removal
+ * is taking longer than timeout.
+ */
+static int drmem_timer_setup(void)
+{
+	struct sigaction sigact;
+
+	if (!usr_timeout)
+		return 0;
+
+	sigact.sa_handler = mem_timeout_handler;
+	sigemptyset(&sigact.sa_mask);
+	sigact.sa_flags = 0;
+	if (sigaction(SIGALRM, &sigact, NULL))
+		return -1;
+
+	alarm(usr_timeout);
+	return 0;
+}
+
 static int numa_based_remove(uint32_t count)
 {
 	struct lmb_list_head *lmb_list;
 	struct ppcnuma_node *node;
-	int nid;
+	int nid, rc = 0;
 	uint32_t done = 0;
 
+	/*
+	 * Enable alarm signal handler for usr_timeout
+	 */
+	rc = drmem_timer_setup();
+	if (rc)
+		return rc;
+
 	/*
 	 * Read the LMBs
 	 * Link the LMBs to their node
-- 
2.51.0