RFC: Possible napi deadlock work-around?

[Ben Greear]

Does this look like a good idea?


[greearb at ben-dt3 ath10k]$ git diff
diff --git a/drivers/net/wireless/ath/ath10k/core.h b/drivers/net/wireless/ath/ath10k/core.h
index 72b4495..c7ba49f 100644
--- a/drivers/net/wireless/ath/ath10k/core.h
+++ b/drivers/net/wireless/ath/ath10k/core.h
@@ -1205,6 +1205,7 @@ struct ath10k {
         /* NAPI */
         struct net_device napi_dev;
         struct napi_struct napi;
+       bool napi_enabled;

         struct work_struct stop_scan_work;

diff --git a/drivers/net/wireless/ath/ath10k/pci.c b/drivers/net/wireless/ath/ath10k/pci.c
index 398e413..fad4fb9 100644
--- a/drivers/net/wireless/ath/ath10k/pci.c
+++ b/drivers/net/wireless/ath/ath10k/pci.c
@@ -1956,6 +1956,7 @@ static int ath10k_pci_hif_start(struct ath10k *ar)
         ath10k_dbg(ar, ATH10K_DBG_BOOT, "boot hif start\n");

         napi_enable(&ar->napi);
+       ar->napi_enabled = true;

         ath10k_pci_irq_enable(ar);
         ath10k_pci_rx_post(ar);
@@ -2086,8 +2087,23 @@ static void ath10k_pci_hif_stop(struct ath10k *ar)
         ath10k_pci_irq_disable(ar);
         ath10k_pci_irq_sync(ar);
         ath10k_pci_flush(ar);
-       napi_synchronize(&ar->napi);
-       napi_disable(&ar->napi);
+
+       /* Calling napi_disable twice in a row (w/out starting it and/or without
+        * having NAPI active leads to deadlock because napi_disable sets
+        * NAPI_STATE_SCHED and NAPI_STATE_NPSVC when it returns, as far as I
+        * can tell.  So, guard this call to napi_disable.  I believe the
+        * failure case is something like this:
+        * rmmod ath10k_pci ath10k_core
+        *   Firmware crashes before hif_stop is called by the rmmod path
+        *   The crash handling logic calls hif_stop
+         *   Then rmmod gets around to calling hif_stop, but spins endlessly
+        *   in napi_synchronize.
+        */
+       if (ar->napi_enabled) {
+               napi_synchronize(&ar->napi);
+               napi_disable(&ar->napi);
+               ar->napi_enabled = false;
+       }

         spin_lock_irqsave(&ar_pci->ps_lock, flags);
         WARN_ON(ar_pci->ps_wake_refcount > 0);
[greearb at ben-dt3 ath10k]$

-- 
Ben Greear <greearb at candelatech.com>
Candela Technologies Inc  http://www.candelatech.com