[dpdk-dev] [PATCH v7 11/14] eal: do not panic on PCI failures

[Aaron Conole]

Some devices may be inaccessible for a variety of reasons, or the
PCI-bus may be unavailable causing the whole thing to fail.  Still,
better to continue attempts at probes.

Since PCI isn't neccessarily required, it may be possible to simply log
the error and continue on letting the user check the logs and restart
the application when things have failed.

This will usually be an issue because of permissions.  However, it could
also be caused by OOM.  In either case, errno will contain the
underlying cause.

For linux, it is safe to re-init the system here, so allow the
application to take corrective action and reinit.

For BSD, this is not the case, for other reasons, including hugepage
allocation has already happened, and needs to be properly uninitialized.

Signed-off-by: Aaron Conole <aconole at redhat.com>
---
 lib/librte_eal/bsdapp/eal/eal.c        | 15 +++++++++++----
 lib/librte_eal/common/eal_common_pci.c | 12 +++++++++---
 lib/librte_eal/linuxapp/eal/eal.c      | 15 +++++++++++----
 3 files changed, 31 insertions(+), 11 deletions(-)

diff --git a/lib/librte_eal/bsdapp/eal/eal.c b/lib/librte_eal/bsdapp/eal/eal.c
index 7c6dd4e..75ddf31 100644
--- a/lib/librte_eal/bsdapp/eal/eal.c
+++ b/lib/librte_eal/bsdapp/eal/eal.c
@@ -604,8 +604,12 @@ rte_eal_init(int argc, char **argv)
 		return -1;
 	}
 
-	if (rte_eal_pci_init() < 0)
-		rte_panic("Cannot init PCI\n");
+	if (rte_eal_pci_init() < 0) {
+		rte_eal_init_alert("Cannot init PCI\n");
+		rte_errno = EPROTO;
+		rte_atomic32_clear(&run_once);
+		return -1;
+	}
 
 	eal_check_mem_on_local_socket();
 
@@ -660,8 +664,11 @@ rte_eal_init(int argc, char **argv)
 		rte_panic("Cannot probe devices\n");
 
 	/* Probe & Initialize PCI devices */
-	if (rte_eal_pci_probe())
-		rte_panic("Cannot probe PCI\n");
+	if (rte_eal_pci_probe()) {
+		rte_eal_init_alert("Cannot probe PCI\n");
+		rte_errno = ENOTSUP;
+		return -1;
+	}
 
 	if (rte_eal_dev_init() < 0)
 		rte_panic("Cannot init pmd devices\n");
diff --git a/lib/librte_eal/common/eal_common_pci.c b/lib/librte_eal/common/eal_common_pci.c
index 72547bd..d45b7d3 100644
--- a/lib/librte_eal/common/eal_common_pci.c
+++ b/lib/librte_eal/common/eal_common_pci.c
@@ -69,6 +69,7 @@
 #include <sys/queue.h>
 #include <sys/mman.h>
 
+#include <rte_errno.h>
 #include <rte_interrupts.h>
 #include <rte_log.h>
 #include <rte_pci.h>
@@ -414,6 +415,7 @@ int
 rte_eal_pci_probe(void)
 {
 	struct rte_pci_device *dev = NULL;
+	size_t probed = 0, failed = 0;
 	struct rte_devargs *devargs;
 	int probe_all = 0;
 	int ret = 0;
@@ -422,6 +424,7 @@ rte_eal_pci_probe(void)
 		probe_all = 1;
 
 	TAILQ_FOREACH(dev, &pci_device_list, next) {
+		probed++;
 
 		/* set devargs in PCI structure */
 		devargs = pci_devargs_lookup(dev);
@@ -434,13 +437,16 @@ rte_eal_pci_probe(void)
 		else if (devargs != NULL &&
 			devargs->type == RTE_DEVTYPE_WHITELISTED_PCI)
 			ret = pci_probe_all_drivers(dev);
-		if (ret < 0)
-			rte_exit(EXIT_FAILURE, "Requested device " PCI_PRI_FMT
+		if (ret < 0) {
+			RTE_LOG(ERR, EAL, "Requested device " PCI_PRI_FMT
 				 " cannot be used\n", dev->addr.domain, dev->addr.bus,
 				 dev->addr.devid, dev->addr.function);
+			rte_errno = errno;
+			failed++;
+		}
 	}
 
-	return 0;
+	return (probed && probed == failed) ? -1 : 0;
 }
 
 /* dump one device */
diff --git a/lib/librte_eal/linuxapp/eal/eal.c b/lib/librte_eal/linuxapp/eal/eal.c
index b2a9005..354d0d8 100644
--- a/lib/librte_eal/linuxapp/eal/eal.c
+++ b/lib/librte_eal/linuxapp/eal/eal.c
@@ -832,8 +832,12 @@ rte_eal_init(int argc, char **argv)
 		return -1;
 	}
 
-	if (rte_eal_pci_init() < 0)
-		rte_panic("Cannot init PCI\n");
+	if (rte_eal_pci_init() < 0) {
+		rte_eal_init_alert("Cannot init PCI\n");
+		rte_errno = EPROTO;
+		rte_atomic32_clear(&run_once);
+		return -1;
+	}
 
 #ifdef VFIO_PRESENT
 	if (rte_eal_vfio_setup() < 0) {
@@ -939,8 +943,11 @@ rte_eal_init(int argc, char **argv)
 		rte_panic("Cannot probe devices\n");
 
 	/* Probe & Initialize PCI devices */
-	if (rte_eal_pci_probe())
-		rte_panic("Cannot probe PCI\n");
+	if (rte_eal_pci_probe()) {
+		rte_eal_init_alert("Cannot probe PCI\n");
+		rte_errno = ENOTSUP;
+		return -1;
+	}
 
 	if (rte_eal_dev_init() < 0)
 		rte_panic("Cannot init pmd devices\n");
-- 
2.9.3