In secondary processes, directly accessing 'dev->data->dev_private' can
cause a segmentation fault if the primary process has exited or if the
shared memory is no longer accessible. If a secondary process attempts
to query device information (e.g., via testpmd), a NULL dereference
may occur due to missing shared data.
The secondary process not only crashes on device close but also segfaults
when executing commands like "show device info all" after the primary has
exited.
This patch adds a mechanism in testpmd to monitor the primary process from the
secondary using `rte_eal_primary_proc_alive()`, and exits secondary process
when primary has exited.
Fixes: af75078fece3 ("first public release")
Cc: sta...@dpdk.org
Signed-off-by: Khadem Ullah <14pwcse1...@uetpeshawar.edu.pk>
---
app/test-pmd/testpmd.c | 49 +++++++++++++++++++++++++++++++++++++----
lib/ethdev/rte_ethdev.c | 8 ++++++-
2 files changed, 52 insertions(+), 5 deletions(-)
diff --git a/app/test-pmd/testpmd.c b/app/test-pmd/testpmd.c
index bb88555328..ad780ba754 100644
--- a/app/test-pmd/testpmd.c
+++ b/app/test-pmd/testpmd.c
@@ -101,13 +101,15 @@
uint16_t verbose_level = 0; /**< Silent by default. */
int testpmd_logtype; /**< Log type for testpmd logs */
+/* Maximum delay for exiting after primary process. */
+#define MONITOR_INTERVAL (500 * 1000)
+
/* use main core for command line ? */
uint8_t interactive = 0;
uint8_t auto_start = 0;
uint8_t tx_first;
char cmdline_filename[PATH_MAX] = {0};
bool echo_cmdline_file;
-
/*
* NUMA support configuration.
* When set, the NUMA support attempts to dispatch the allocation of the
@@ -2281,7 +2283,7 @@ run_pkt_fwd_on_lcore(struct fwd_lcore *fc, packet_fwd_t
pkt_fwd)
fc->total_cycles += tsc - prev_tsc;
prev_tsc = tsc;
}
- } while (! fc->stopped);
+ } while (!fc->stopped && !f_quit);
}
static int
@@ -4332,6 +4334,43 @@ signal_handler(int signum __rte_unused)
prompt_exit();
}
+
+/* Alarm signal handler, used to check that primary process */
+static void
+monitor_primary(void *arg __rte_unused)
+{
+ if (rte_eal_primary_proc_alive(NULL)) {
+ rte_eal_alarm_set(MONITOR_INTERVAL, monitor_primary, NULL);
+ } else {
+ fprintf(stderr,
+ "Primary process is no longer active, exiting...\n");
+ f_quit = 1;
+ prompt_exit();
+ }
+}
+
+/* Setup handler to check when primary exits. */
+static void
+enable_primary_monitor(void)
+{
+ int ret;
+
+ /* Once primary exits, so will pdump. */
+ ret = rte_eal_alarm_set(MONITOR_INTERVAL, monitor_primary, NULL);
+ if (ret < 0)
+ fprintf(stderr, "Fail to enable monitor:%d\n", ret);
+}
+
+static void
+disable_primary_monitor(void)
+{
+ int ret;
+
+ ret = rte_eal_alarm_cancel(monitor_primary, NULL);
+ if (ret < 0)
+ fprintf(stderr, "Fail to disable monitor:%d\n", ret);
+}
+
int
main(int argc, char** argv)
{
@@ -4362,7 +4401,8 @@ main(int argc, char** argv)
if (diag < 0)
rte_exit(EXIT_FAILURE, "Cannot init EAL: %s\n",
rte_strerror(rte_errno));
-
+ if (rte_eal_process_type() == RTE_PROC_SECONDARY)
+ enable_primary_monitor();
/* allocate port structures, and init them */
init_port();
@@ -4571,7 +4611,8 @@ main(int argc, char** argv)
if (ret != 0)
rte_exit(EXIT_FAILURE, "Cannot unregister for ethdev events");
-
+ if (rte_eal_process_type() == RTE_PROC_SECONDARY)
+ disable_primary_monitor();
ret = rte_eal_cleanup();
if (ret != 0)
rte_exit(EXIT_FAILURE,
diff --git a/lib/ethdev/rte_ethdev.c b/lib/ethdev/rte_ethdev.c
index dd7c00bc94..5c73397164 100644
--- a/lib/ethdev/rte_ethdev.c
+++ b/lib/ethdev/rte_ethdev.c
@@ -4079,6 +4079,13 @@ rte_eth_dev_info_get(uint16_t port_id, struct
rte_eth_dev_info *dev_info)
if (dev->dev_ops->dev_infos_get == NULL)
return -ENOTSUP;
+ if (rte_eal_process_type() == RTE_PROC_SECONDARY &&
+ unlikely(rte_mem_virt2phy(dev->data->dev_private) ==
RTE_BAD_PHYS_ADDR)) {
+ RTE_ETHDEV_LOG_LINE(ERR,
+ "Secondary: dev_private not accessible (primary
exited?)");
+ rte_errno = ENODEV;
+ return -rte_errno;
+ }
diag = dev->dev_ops->dev_infos_get(dev, dev_info);
if (diag != 0) {
/* Cleanup already filled in device information */
@@ -4307,7 +4314,6 @@ rte_eth_macaddr_get(uint16_t port_id, struct
rte_ether_addr *mac_addr)
port_id);
return -EINVAL;
}
-
rte_ether_addr_copy(&dev->data->mac_addrs[0], mac_addr);
rte_eth_trace_macaddr_get(port_id, mac_addr);
--
2.43.0
