summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
Diffstat (limited to 'app-admin/rasdaemon/files/rasdaemon-0.8.0-table-create-offline-cpus.patch')
-rw-r--r--app-admin/rasdaemon/files/rasdaemon-0.8.0-table-create-offline-cpus.patch179
1 files changed, 179 insertions, 0 deletions
diff --git a/app-admin/rasdaemon/files/rasdaemon-0.8.0-table-create-offline-cpus.patch b/app-admin/rasdaemon/files/rasdaemon-0.8.0-table-create-offline-cpus.patch
new file mode 100644
index 000000000000..4eb3977930c6
--- /dev/null
+++ b/app-admin/rasdaemon/files/rasdaemon-0.8.0-table-create-offline-cpus.patch
@@ -0,0 +1,179 @@
+https://bugs.gentoo.org/890286
+https://github.com/mchehab/rasdaemon/issues/77
+https://github.com/mchehab/rasdaemon/commit/6f7851f72d8464c7a20a248d4abf4362de8f0ba9
+
+From 6f7851f72d8464c7a20a248d4abf4362de8f0ba9 Mon Sep 17 00:00:00 2001
+From: Shiju Jose <shiju.jose@huawei.com>
+Date: Sun, 5 Mar 2023 23:14:42 +0000
+Subject: [PATCH] rasdaemon: fix table create if some cpus are offline
+
+Fix for regression in ras_mc_create_table() if some cpus are offline
+at the system start
+
+Issue:
+
+Regression in the ras_mc_create_table() if some of the cpus are offline
+at the system start when run the rasdaemon.
+
+This issue is reproducible in ras_mc_create_table() with decode and
+record non-standard events and reproducible sometimes with
+ras_mc_create_table() for the standard events.
+
+Also in the multi thread way, there is memory leak in ras_mc_event_opendb()
+as struct sqlite3_priv *priv and sqlite3 *db allocated/initialized per
+thread, but stored in the common struct ras_events ras in pthread data,
+which is shared across the threads.
+
+Reason:
+
+when the system starts with some of the cpus offline and then run
+the rasdaemon, read_ras_event_all_cpus() exit with error and switch to
+the multi thread way. However read() in read_ras_event() return error in
+threads for each of the offline CPUs and does clean up including calling
+ras_mc_event_closedb().
+
+Since the 'struct ras_events ras' passed in the pthread_data to each of the
+threads is common, struct sqlite3_priv *priv and sqlite3 *db allocated/
+initialized per thread and stored in the common 'struct ras_events ras',
+are getting overwritten in each ras_mc_event_opendb()(which called from
+pthread per cpu), result memory leak.
+
+Also when ras_mc_event_closedb() is called in the above error case from
+the threads corresponding to the offline cpus, close the sqlite3 *db and
+free sqlite3_priv *priv stored in the common 'struct ras_events ras',
+result regression when accessing priv->db in the ras_mc_create_table()
+from another context later.
+
+Solution:
+
+In ras_mc_event_opendb(), allocate struct sqlite3_priv *priv,
+init sqlite3 *db and create tables common for the threads with shared
+'struct ras_events ras' based on a reference count and free them in the
+same way.
+
+Also protect critical code ras_mc_event_opendb() and ras_mc_event_closedb()
+using mutex in the multi thread case from any regression caused by the
+thread pre-emption.
+
+Reported-by: Lei Feng <fenglei47@h-partners.com>
+Signed-off-by: Shiju Jose <shiju.jose@huawei.com>
+Signed-off-by: Mauro Carvalho Chehab <mchehab@kernel.org>
+---
+ ras-events.c | 16 +++++++++++++++-
+ ras-events.h | 4 +++-
+ ras-record.c | 12 ++++++++++++
+ 3 files changed, 30 insertions(+), 2 deletions(-)
+
+diff --git a/ras-events.c b/ras-events.c
+index 49e4f9a..5fe8e19 100644
+--- a/ras-events.c
++++ b/ras-events.c
+@@ -625,19 +625,25 @@ static void *handle_ras_events_cpu(void *priv)
+
+ log(TERM, LOG_INFO, "Listening to events on cpu %d\n", pdata->cpu);
+ if (pdata->ras->record_events) {
++ pthread_mutex_lock(&pdata->ras->db_lock);
+ if (ras_mc_event_opendb(pdata->cpu, pdata->ras)) {
++ pthread_mutex_unlock(&pdata->ras->db_lock);
+ log(TERM, LOG_ERR, "Can't open database\n");
+ close(fd);
+ kbuffer_free(kbuf);
+ free(page);
+ return 0;
+ }
++ pthread_mutex_unlock(&pdata->ras->db_lock);
+ }
+
+ read_ras_event(fd, pdata, kbuf, page);
+
+- if (pdata->ras->record_events)
++ if (pdata->ras->record_events) {
++ pthread_mutex_lock(&pdata->ras->db_lock);
+ ras_mc_event_closedb(pdata->cpu, pdata->ras);
++ pthread_mutex_unlock(&pdata->ras->db_lock);
++ }
+
+ close(fd);
+ kbuffer_free(kbuf);
+@@ -993,6 +999,11 @@ int handle_ras_events(int record_events)
+
+ /* Poll doesn't work on this kernel. Fallback to pthread way */
+ if (rc == -255) {
++ if (pthread_mutex_init(&ras->db_lock, NULL) != 0) {
++ log(SYSLOG, LOG_INFO, "sqlite db lock init has failed\n");
++ goto err;
++ }
++
+ log(SYSLOG, LOG_INFO,
+ "Opening one thread per cpu (%d threads)\n", cpus);
+ for (i = 0; i < cpus; i++) {
+@@ -1005,6 +1016,8 @@ int handle_ras_events(int record_events)
+ i);
+ while (--i)
+ pthread_cancel(data[i].thread);
++
++ pthread_mutex_destroy(&ras->db_lock);
+ goto err;
+ }
+ }
+@@ -1012,6 +1025,7 @@ int handle_ras_events(int record_events)
+ /* Wait for all threads to complete */
+ for (i = 0; i < cpus; i++)
+ pthread_join(data[i].thread, NULL);
++ pthread_mutex_destroy(&ras->db_lock);
+ }
+
+ log(SYSLOG, LOG_INFO, "Huh! something got wrong. Aborting.\n");
+diff --git a/ras-events.h b/ras-events.h
+index 6c9f507..649b0c0 100644
+--- a/ras-events.h
++++ b/ras-events.h
+@@ -56,7 +56,9 @@ struct ras_events {
+ time_t uptime_diff;
+
+ /* For ras-record */
+- void *db_priv;
++ void *db_priv;
++ int db_ref_count;
++ pthread_mutex_t db_lock;
+
+ /* For the mce handler */
+ struct mce_priv *mce_priv;
+diff --git a/ras-record.c b/ras-record.c
+index a367939..adc97a4 100644
+--- a/ras-record.c
++++ b/ras-record.c
+@@ -763,6 +763,10 @@ int ras_mc_event_opendb(unsigned cpu, struct ras_events *ras)
+
+ printf("Calling %s()\n", __FUNCTION__);
+
++ ras->db_ref_count++;
++ if (ras->db_ref_count > 1)
++ return 0;
++
+ ras->db_priv = NULL;
+
+ priv = calloc(1, sizeof(*priv));
+@@ -912,6 +916,13 @@ int ras_mc_event_closedb(unsigned int cpu, struct ras_events *ras)
+
+ printf("Calling %s()\n", __func__);
+
++ if (ras->db_ref_count > 0)
++ ras->db_ref_count--;
++ else
++ return -1;
++ if (ras->db_ref_count > 0)
++ return 0;
++
+ if (!priv)
+ return -1;
+
+@@ -1018,6 +1029,7 @@ int ras_mc_event_closedb(unsigned int cpu, struct ras_events *ras)
+ log(TERM, LOG_ERR,
+ "cpu %u: Failed to shutdown sqlite: error = %d\n", cpu, rc);
+ free(priv);
++ ras->db_priv = NULL;
+
+ return 0;
+ }
+