From: Jeff Guo <jia.guo@intel.com>
To: stephen@networkplumber.org, bruce.richardson@intel.com,
ferruh.yigit@intel.com, konstantin.ananyev@intel.com,
gaetan.rivet@6wind.com, jingjing.wu@intel.com,
thomas@monjalon.net, motih@mellanox.com, matan@mellanox.com,
harry.van.haaren@intel.com, qi.z.zhang@intel.com,
shaopeng.he@intel.com, bernard.iremonger@intel.com
Cc: jblunck@infradead.org, shreyansh.jain@nxp.com, dev@dpdk.org,
jia.guo@intel.com, helin.zhang@intel.com
Subject: [dpdk-dev] [PATCH V4 6/9] eal: add failure handle mechanism for hot plug
Date: Fri, 29 Jun 2018 18:24:28 +0800 [thread overview]
Message-ID: <1530267871-7161-7-git-send-email-jia.guo@intel.com> (raw)
In-Reply-To: <1530267871-7161-1-git-send-email-jia.guo@intel.com>
This patch introduces a failure handler mechanism to handle device
hot plug removal event.
First register sigbus handler, once sigbus error be captured, will
check the failure address and accordingly remap the invalid memory
for the corresponding device. Bese on this mechanism, it could
guaranty the application not to be crash when hot unplug devices.
Signed-off-by: Jeff Guo <jia.guo@intel.com>
---
v4->v3:
split patches to be small and clear.
---
lib/librte_eal/linuxapp/eal/eal_dev.c | 88 ++++++++++++++++++++++++++++++++++-
1 file changed, 87 insertions(+), 1 deletion(-)
diff --git a/lib/librte_eal/linuxapp/eal/eal_dev.c b/lib/librte_eal/linuxapp/eal/eal_dev.c
index 1cf6aeb..c9dddab 100644
--- a/lib/librte_eal/linuxapp/eal/eal_dev.c
+++ b/lib/librte_eal/linuxapp/eal/eal_dev.c
@@ -4,6 +4,8 @@
#include <string.h>
#include <unistd.h>
+#include <fcntl.h>
+#include <signal.h>
#include <sys/socket.h>
#include <linux/netlink.h>
@@ -14,15 +16,24 @@
#include <rte_malloc.h>
#include <rte_interrupts.h>
#include <rte_alarm.h>
+#include <rte_bus.h>
+#include <rte_eal.h>
+#include <rte_spinlock.h>
+#include <rte_errno.h>
#include "eal_private.h"
static struct rte_intr_handle intr_handle = {.fd = -1 };
static bool monitor_started;
+extern struct rte_bus_list rte_bus_list;
+
#define EAL_UEV_MSG_LEN 4096
#define EAL_UEV_MSG_ELEM_LEN 128
+/* spinlock for device failure process */
+static rte_spinlock_t dev_failure_lock = RTE_SPINLOCK_INITIALIZER;
+
static void dev_uev_handler(__rte_unused void *param);
/* identify the system layer which reports this event. */
@@ -33,6 +44,34 @@ enum eal_dev_event_subsystem {
EAL_DEV_EVENT_SUBSYSTEM_MAX
};
+static void sigbus_handler(int signum __rte_unused, siginfo_t *info,
+ void *ctx __rte_unused)
+{
+ int ret;
+
+ RTE_LOG(DEBUG, EAL, "Thread[%d] catch SIGBUS, fault address:%p\n",
+ (int)pthread_self(), info->si_addr);
+
+ rte_spinlock_lock(&dev_failure_lock);
+ ret = rte_bus_sigbus_handler(info->si_addr);
+ rte_spinlock_unlock(&dev_failure_lock);
+ if (!ret)
+ RTE_LOG(INFO, EAL,
+ "Success to handle SIGBUS error for hotplug!\n");
+ else
+ rte_exit(EXIT_FAILURE,
+ "A generic SIGBUS error, (rte_errno: %s)!",
+ strerror(rte_errno));
+}
+
+static int cmp_dev_name(const struct rte_device *dev,
+ const void *_name)
+{
+ const char *name = _name;
+
+ return strcmp(dev->name, name);
+}
+
static int
dev_uev_socket_fd_create(void)
{
@@ -147,6 +186,9 @@ dev_uev_handler(__rte_unused void *param)
struct rte_dev_event uevent;
int ret;
char buf[EAL_UEV_MSG_LEN];
+ struct rte_bus *bus;
+ struct rte_device *dev;
+ const char *busname;
memset(&uevent, 0, sizeof(struct rte_dev_event));
memset(buf, 0, EAL_UEV_MSG_LEN);
@@ -171,13 +213,48 @@ dev_uev_handler(__rte_unused void *param)
RTE_LOG(DEBUG, EAL, "receive uevent(name:%s, type:%d, subsystem:%d)\n",
uevent.devname, uevent.type, uevent.subsystem);
- if (uevent.devname)
+ switch (uevent.subsystem) {
+ case EAL_DEV_EVENT_SUBSYSTEM_PCI:
+ case EAL_DEV_EVENT_SUBSYSTEM_UIO:
+ busname = "pci";
+ break;
+ default:
+ break;
+ }
+
+ if (uevent.devname) {
+ if (uevent.type == RTE_DEV_EVENT_REMOVE) {
+ bus = rte_bus_find_by_name(busname);
+ if (bus == NULL) {
+ RTE_LOG(ERR, EAL, "Cannot find bus (%s)\n",
+ busname);
+ return;
+ }
+ dev = bus->find_device(NULL, cmp_dev_name,
+ uevent.devname);
+ if (dev == NULL) {
+ RTE_LOG(ERR, EAL, "Cannot find device (%s) on "
+ "bus (%s)\n", uevent.devname, busname);
+ return;
+ }
+ rte_spinlock_lock(&dev_failure_lock);
+ ret = bus->hotplug_handler(dev);
+ rte_spinlock_unlock(&dev_failure_lock);
+ if (ret) {
+ RTE_LOG(ERR, EAL, "Can not handle hotplug for "
+ "device (%s)\n", dev->name);
+ return;
+ }
+ }
dev_callback_process(uevent.devname, uevent.type);
+ }
}
int __rte_experimental
rte_dev_event_monitor_start(void)
{
+ sigset_t mask;
+ struct sigaction action;
int ret;
if (monitor_started)
@@ -197,6 +274,14 @@ rte_dev_event_monitor_start(void)
return -1;
}
+ /* register sigbus handler */
+ sigemptyset(&mask);
+ sigaddset(&mask, SIGBUS);
+ action.sa_flags = SA_SIGINFO;
+ action.sa_mask = mask;
+ action.sa_sigaction = sigbus_handler;
+ sigaction(SIGBUS, &action, NULL);
+
monitor_started = true;
return 0;
@@ -220,5 +305,6 @@ rte_dev_event_monitor_stop(void)
close(intr_handle.fd);
intr_handle.fd = -1;
monitor_started = false;
+
return 0;
}
--
2.7.4
next prev parent reply other threads:[~2018-06-29 10:27 UTC|newest]
Thread overview: 14+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-06-29 10:24 [dpdk-dev] [PATCH V4 0/9] hot plug failure handle mechanism Jeff Guo
2018-06-29 10:24 ` [dpdk-dev] [PATCH V4 1/9] bus: introduce hotplug failure handler Jeff Guo
2018-06-29 10:24 ` [dpdk-dev] [PATCH V4 2/9] bus/pci: implement hotplug handler operation Jeff Guo
2018-06-29 10:24 ` [dpdk-dev] [PATCH V4 3/9] bus: introduce sigbus handler Jeff Guo
2018-06-29 10:24 ` [dpdk-dev] [PATCH V4 4/9] bus/pci: implement sigbus handler operation Jeff Guo
2018-06-29 10:24 ` [dpdk-dev] [PATCH V4 5/9] bus: add helper to handle sigbus Jeff Guo
2018-06-29 10:24 ` Jeff Guo [this message]
2018-06-29 10:24 ` [dpdk-dev] [PATCH V4 7/9] igb_uio: fix uio release issue when hot unplug Jeff Guo
2018-06-29 10:24 ` [dpdk-dev] [PATCH V4 8/9] app/testpmd: show example to handle " Jeff Guo
2018-06-29 10:24 ` [dpdk-dev] [PATCH V4 9/9] app/testpmd: enable device hotplug monitoring Jeff Guo
-- strict thread matches above, loose matches on Subject: below --
2017-06-29 4:37 [dpdk-dev] [PATCH v3 0/2] add uevent api for hot plug Jeff Guo
2018-06-29 10:30 ` [dpdk-dev] [PATCH V4 0/9] hot plug failure handle mechanism Jeff Guo
2018-06-29 10:30 ` [dpdk-dev] [PATCH V4 6/9] eal: add failure handle mechanism for hot plug Jeff Guo
2018-06-29 10:49 ` Ananyev, Konstantin
2018-06-29 11:15 ` Guo, Jia
2018-06-29 12:06 ` Ananyev, Konstantin
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1530267871-7161-7-git-send-email-jia.guo@intel.com \
--to=jia.guo@intel.com \
--cc=bernard.iremonger@intel.com \
--cc=bruce.richardson@intel.com \
--cc=dev@dpdk.org \
--cc=ferruh.yigit@intel.com \
--cc=gaetan.rivet@6wind.com \
--cc=harry.van.haaren@intel.com \
--cc=helin.zhang@intel.com \
--cc=jblunck@infradead.org \
--cc=jingjing.wu@intel.com \
--cc=konstantin.ananyev@intel.com \
--cc=matan@mellanox.com \
--cc=motih@mellanox.com \
--cc=qi.z.zhang@intel.com \
--cc=shaopeng.he@intel.com \
--cc=shreyansh.jain@nxp.com \
--cc=stephen@networkplumber.org \
--cc=thomas@monjalon.net \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).