raw/ifpga: fix monitor thread

Monitor thread handles graceful shutdown according to the value of
specific sensors in device, two issues are found below.
1. Thread is not created when card is probed.
2. Thread is canceled without checking presence of other cards.
To fix them, thread is created in pci device probe function, a reference
count is checked before canceling the thread.

Fixes: 9c006c45 ("raw/ifpga: scan PCIe BDF device tree")
Cc: stable@dpdk.org
Signed-off-by: Wei Huang <wei.huang@intel.com>
Acked-by: Tianfei Zhang <tianfei.zhang@intel.com>

diff --git a/drivers/raw/ifpga/ifpga_rawdev.c b/drivers/raw/ifpga/ifpga_rawdev.c
index cc569c5e71d592cf45587021c5c1628217a824a2..26c1366a64f5e898519af1bf45c6c878e239af97 100644 (file)
--- a/drivers/raw/ifpga/ifpga_rawdev.c
+++ b/drivers/raw/ifpga/ifpga_rawdev.c
@@ -68,7 +68,7 @@ static const struct rte_pci_id pci_ifpga_map[] = {
 
 static struct ifpga_rawdev ifpga_rawdevices[IFPGA_RAWDEV_NUM];
 
-static int ifpga_monitor_start;
+static int ifpga_monitor_refcnt;
 static pthread_t ifpga_monitor_start_thread;
 
 static struct ifpga_rawdev *
@@ -133,6 +133,7 @@ ifpga_rawdev_allocate(struct rte_rawdev *rawdev)
        dev->dev_id = dev_id;
        for (i = 0; i < IFPGA_MAX_IRQ; i++)
                dev->intr_handle[i] = NULL;
+       dev->poll_enabled = 0;
 
        return dev;
 }
@@ -207,10 +208,11 @@ static int ifpga_get_dev_vendor_id(const char *bdf,
 
        return 0;
 }
-static int ifpga_rawdev_fill_info(struct ifpga_rawdev *ifpga_dev,
-       const char *bdf)
+
+static int ifpga_rawdev_fill_info(struct ifpga_rawdev *ifpga_dev)
 {
-       char path[1024] = "/sys/bus/pci/devices/0000:";
+       struct opae_adapter *adapter = NULL;
+       char path[1024] = "/sys/bus/pci/devices/";
        char link[1024], link1[1024];
        char dir[1024] = "/sys/devices/";
        char *c;
@@ -225,7 +227,11 @@ static int ifpga_rawdev_fill_info(struct ifpga_rawdev *ifpga_dev,
        int func;
        uint32_t dev_id, vendor_id;
 
-       strlcat(path, bdf, sizeof(path));
+       adapter = ifpga_dev ? ifpga_rawdev_get_priv(ifpga_dev->rawdev) : NULL;
+       if (!adapter)
+               return -ENODEV;
+
+       strlcat(path, adapter->name, sizeof(path));
        memset(link, 0, sizeof(link));
        memset(link1, 0, sizeof(link1));
        ret = readlink(path, link, (sizeof(link)-1));
@@ -375,7 +381,7 @@ ifpga_monitor_sensor(struct rte_rawdev *raw_dev,
                /* monitor temperature sensors */
                if (!strcmp(sensor->name, "Board Temperature") ||
                                !strcmp(sensor->name, "FPGA Die Temperature")) {
-                       IFPGA_RAWDEV_PMD_INFO("read sensor %s %d %d %d\n",
+                       IFPGA_RAWDEV_PMD_DEBUG("read sensor %s %d %d %d\n",
                                        sensor->name, value, sensor->high_warn,
                                        sensor->high_fatal);
 
@@ -417,7 +423,7 @@ static int set_surprise_link_check_aer(
        bool enable = 0;
        uint32_t aer_new0, aer_new1;
 
-       if (!ifpga_rdev) {
+       if (!ifpga_rdev || !ifpga_rdev->rawdev) {
                printf("\n device does not exist\n");
                return -EFAULT;
        }
@@ -496,11 +502,11 @@ ifpga_rawdev_gsd_handle(__rte_unused void *param)
        int gsd_enable, ret;
 #define MS 1000
 
-       while (__atomic_load_n(&ifpga_monitor_start, __ATOMIC_RELAXED)) {
+       while (__atomic_load_n(&ifpga_monitor_refcnt, __ATOMIC_RELAXED)) {
                gsd_enable = 0;
                for (i = 0; i < IFPGA_RAWDEV_NUM; i++) {
                        ifpga_rdev = &ifpga_rawdevices[i];
-                       if (ifpga_rdev->rawdev) {
+                       if (ifpga_rdev->poll_enabled) {
                                ret = set_surprise_link_check_aer(ifpga_rdev,
                                        gsd_enable);
                                if (ret == 1 && !gsd_enable) {
@@ -520,32 +526,46 @@ ifpga_rawdev_gsd_handle(__rte_unused void *param)
 }
 
 static int
-ifpga_monitor_start_func(void)
+ifpga_monitor_start_func(struct ifpga_rawdev *dev)
 {
        int ret;
 
-       if (!__atomic_load_n(&ifpga_monitor_start, __ATOMIC_RELAXED)) {
+       if (!dev)
+               return -ENODEV;
+
+       ret = ifpga_rawdev_fill_info(dev);
+       if (ret)
+               return ret;
+
+       dev->poll_enabled = 1;
+
+       if (!__atomic_fetch_add(&ifpga_monitor_refcnt, 1, __ATOMIC_RELAXED)) {
                ret = rte_ctrl_thread_create(&ifpga_monitor_start_thread,
                                             "ifpga-monitor", NULL,
                                             ifpga_rawdev_gsd_handle, NULL);
                if (ret != 0) {
+                       ifpga_monitor_start_thread = 0;
                        IFPGA_RAWDEV_PMD_ERR(
                                "Fail to create ifpga monitor thread");
                        return -1;
                }
-               __atomic_store_n(&ifpga_monitor_start, 1, __ATOMIC_RELAXED);
        }
 
        return 0;
 }
+
 static int
-ifpga_monitor_stop_func(void)
+ifpga_monitor_stop_func(struct ifpga_rawdev *dev)
 {
        int ret;
 
-       if (__atomic_load_n(&ifpga_monitor_start, __ATOMIC_RELAXED)) {
-               __atomic_store_n(&ifpga_monitor_start, 0, __ATOMIC_RELAXED);
+       if (!dev || !dev->poll_enabled)
+               return 0;
+
+       dev->poll_enabled = 0;
 
+       if (!__atomic_sub_fetch(&ifpga_monitor_refcnt, 1, __ATOMIC_RELAXED) &&
+               ifpga_monitor_start_thread) {
                ret = pthread_cancel(ifpga_monitor_start_thread);
                if (ret)
                        IFPGA_RAWDEV_PMD_ERR("Can't cancel the thread");
@@ -718,6 +738,7 @@ ifpga_rawdev_close(struct rte_rawdev *dev)
        struct opae_adapter *adapter;
 
        if (dev) {
+               ifpga_monitor_stop_func(ifpga_rawdev_get(dev));
                adapter = ifpga_rawdev_get_priv(dev);
                if (adapter) {
                        opae_adapter_destroy(adapter);
@@ -1571,6 +1592,10 @@ ifpga_rawdev_create(struct rte_pci_device *pci_dev,
        if (ret)
                goto free_adapter_data;
 
+       ret = ifpga_monitor_start_func(dev);
+       if (ret)
+               goto free_adapter_data;
+
        return ret;
 
 free_adapter_data:
@@ -1646,7 +1671,7 @@ ifpga_rawdev_pci_probe(struct rte_pci_driver *pci_drv __rte_unused,
 static int
 ifpga_rawdev_pci_remove(struct rte_pci_device *pci_dev)
 {
-       ifpga_monitor_stop_func();
+       IFPGA_RAWDEV_PMD_INFO("remove pci_dev %s", pci_dev->device.name);
        return ifpga_rawdev_destroy(pci_dev);
 }
 
@@ -1697,7 +1722,6 @@ ifpga_cfg_probe(struct rte_vdev_device *dev)
        struct ifpga_rawdev *ifpga_dev;
        int port;
        char *name = NULL;
-       const char *bdf;
        char dev_name[RTE_RAWDEV_NAME_MAX_LEN];
        int ret = -1;
 
@@ -1746,10 +1770,6 @@ ifpga_cfg_probe(struct rte_vdev_device *dev)
        ifpga_dev = ifpga_rawdev_get(rawdev);
        if (!ifpga_dev)
                goto end;
-       bdf = name;
-       ifpga_rawdev_fill_info(ifpga_dev, bdf);
-
-       ifpga_monitor_start_func();
 
        memset(dev_name, 0, sizeof(dev_name));
        snprintf(dev_name, RTE_RAWDEV_NAME_MAX_LEN, "%d|%s",

diff --git a/drivers/raw/ifpga/ifpga_rawdev.h b/drivers/raw/ifpga/ifpga_rawdev.h
index 6e09afead31f1f319066905a9f87ed3f77b8c9af..857b73463d374c49398fc318e1f9ae612dde8214 100644 (file)
--- a/drivers/raw/ifpga/ifpga_rawdev.h
+++ b/drivers/raw/ifpga/ifpga_rawdev.h
@@ -62,6 +62,8 @@ struct ifpga_rawdev {
        char parent_bdf[16];
        /* 0 for FME interrupt, others are reserved for AFU irq */
        void *intr_handle[IFPGA_MAX_IRQ];
+       /* enable monitor thread poll device's sensors or not */
+       int poll_enabled;
 };
 
 struct ifpga_rawdev *