tg3: prevent ifup/ifdown during PCI error recovery

The patch fixes race conditions between PCI error recovery callbacks and
potential ifup/ifdown.

First, if ifup (tg3_open) is called between tg3_io_error_detected() and
tg3_io_resume() then tp->timer is armed twice before expiry. Once during
tg3_open() and again during tg3_io_resume(). This results in BUG
at kernel/time/timer.c:945.

Second, if ifdown (tg3_close) is called between tg3_io_error_detected()
and tg3_io_resume() then tg3_napi_disable() is called twice without
a tg3_napi_enable between. Once during tg3_io_error_detected() and again
during tg3_close(). The tg3_io_resume() then hangs on rtnl_lock().

v2: Added logging messages per Prashant's request

Cc: Prashant Sreedharan <prashant@broadcom.com>
Cc: Michael Chan <mchan@broadcom.com>

Signed-off-by: Ivan Vecera <ivecera@redhat.com>
Acked-by: Prashant Sreedharan <prashant@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 17 insertions, 0 deletions

diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 3ac5d23454a8..cb77ae93d89a 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -11617,6 +11617,12 @@ static int tg3_open(struct net_device *dev)
         struct tg3 *tp = netdev_priv(dev);
         int err;
 
+        if (tp->pcierr_recovery) {
+                netdev_err(dev, "Failed to open device. PCI error recovery "
+                           "in progress\n");
+                return -EAGAIN;
+        }
+
         if (tp->fw_needed) {
                 err = tg3_request_firmware(tp);
                 if (tg3_asic_rev(tp) == ASIC_REV_57766) {
@@ -11674,6 +11680,12 @@ static int tg3_close(struct net_device *dev)
 {
         struct tg3 *tp = netdev_priv(dev);
 
+        if (tp->pcierr_recovery) {
+                netdev_err(dev, "Failed to close device. PCI error recovery "
+                           "in progress\n");
+                return -EAGAIN;
+        }
+
         tg3_ptp_fini(tp);
 
         tg3_stop(tp);
@@ -17561,6 +17573,7 @@ static int tg3_init_one(struct pci_dev *pdev,
         tp->rx_mode = TG3_DEF_RX_MODE;
         tp->tx_mode = TG3_DEF_TX_MODE;
         tp->irq_sync = 1;
+        tp->pcierr_recovery = false;
 
         if (tg3_debug > 0)
                 tp->msg_enable = tg3_debug;
@@ -18071,6 +18084,8 @@ static pci_ers_result_t tg3_io_error_detected(struct pci_dev *pdev,
 
         rtnl_lock();
 
+        tp->pcierr_recovery = true;
+
         /* We probably don't have netdev yet */
         if (!netdev || !netif_running(netdev))
                 goto done;
@@ -18195,6 +18210,7 @@ static void tg3_io_resume(struct pci_dev *pdev)
         tg3_phy_start(tp);
 
 done:
+        tp->pcierr_recovery = false;
         rtnl_unlock();
 }
 
diff --git a/drivers/net/ethernet/broadcom/tg3.h b/drivers/net/ethernet/broadcom/tg3.h
index 461accaf0aa4..31c9f8295953 100644
--- a/drivers/net/ethernet/broadcom/tg3.h
+++ b/drivers/net/ethernet/broadcom/tg3.h
@@ -3407,6 +3407,7 @@ struct tg3 {
 
         struct device                   *hwmon_dev;
         bool                            link_up;
+        bool                            pcierr_recovery;
 };
 
 /* Accessor macros for chip and asic attributes