rasdaemon: Fix for vendor errors are not recorded in the SQLite database if some...

Fix for vendor errors are not recorded in the SQLite database if some cpus
are offline at the system start.

Issue:

This issue is reproducible by offline some cpus, run
./rasdaemon -f --record & and
inject vendor specific error supported in the rasdaemon.

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_ns_finalize_vendor_tables(), which invokes sqlite3_finalize() on vendor
tables created. Thus the vendor error data does not stored in the SQLite
database when such error is reported next time.

Solution:

In ras_ns_add_vendor_tables() and ras_ns_finalize_vendor_tables() use
reference count and close vendor tables which created in ras_ns_add_vendor_tables()
based on the reference count.

Reported-by: Junhao He <hejunhao3@huawei.com>
Signed-off-by: Shiju Jose <shiju.jose@huawei.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>

diff --git a/ras-non-standard-handler.c b/ras-non-standard-handler.c
index 940fd87ffa5ab19b8f439dcadd094eaaacd6d4bf..e21455aac686159c9b574f3882580b4f42fef913 100644 (file)
--- a/ras-non-standard-handler.c
+++ b/ras-non-standard-handler.c
@@ -66,6 +66,7 @@ int register_ns_ev_decoder(struct ras_ns_ev_decoder *ns_ev_decoder)
 #endif
        if (!ras_ns_ev_dec_list) {
                ras_ns_ev_dec_list = ns_ev_decoder;
+               ras_ns_ev_dec_list->ref_count = 0;
        } else {
                list = ras_ns_ev_dec_list;
                while (list->next)
@@ -86,6 +87,8 @@ int ras_ns_add_vendor_tables(struct ras_events *ras)
                return -1;
 
        ns_ev_decoder = ras_ns_ev_dec_list;
+       if (ras_ns_ev_dec_list)
+               ras_ns_ev_dec_list->ref_count++;
        while (ns_ev_decoder) {
                if (ns_ev_decoder->add_table && !ns_ev_decoder->stmt_dec_record) {
                        error = ns_ev_decoder->add_table(ras, ns_ev_decoder);
@@ -128,6 +131,16 @@ void ras_ns_finalize_vendor_tables(void)
 #ifdef HAVE_SQLITE3
        struct ras_ns_ev_decoder *ns_ev_decoder = ras_ns_ev_dec_list;
 
+       if (!ras_ns_ev_dec_list)
+               return;
+
+       if (ras_ns_ev_dec_list->ref_count > 0)
+               ras_ns_ev_dec_list->ref_count--;
+       else
+               return;
+       if (ras_ns_ev_dec_list->ref_count > 0)
+               return;
+
        while (ns_ev_decoder) {
                if (ns_ev_decoder->stmt_dec_record) {
                        ras_mc_finalize_vendor_table(ns_ev_decoder->stmt_dec_record);
@@ -141,6 +154,9 @@ void ras_ns_finalize_vendor_tables(void)
 static void unregister_ns_ev_decoder(void)
 {
 #ifdef HAVE_SQLITE3
+       if (!ras_ns_ev_dec_list)
+               return;
+       ras_ns_ev_dec_list->ref_count = 1;
        ras_ns_finalize_vendor_tables();
 #endif
        ras_ns_ev_dec_list = NULL;

diff --git a/ras-non-standard-handler.h b/ras-non-standard-handler.h
index d19a5649cd80de5fc94d4aa291a525769d8e1d32..913ce00480b7b4115b2e2ea3a74480289e27ff04 100644 (file)
--- a/ras-non-standard-handler.h
+++ b/ras-non-standard-handler.h
@@ -19,6 +19,7 @@
 
 struct ras_ns_ev_decoder {
        struct ras_ns_ev_decoder *next;
+       uint16_t ref_count;
        const char *sec_type;
        int (*add_table)(struct ras_events *ras, struct ras_ns_ev_decoder *ev_decoder);
        int (*decode)(struct ras_events *ras, struct ras_ns_ev_decoder *ev_decoder,