[PATCH] tg3: driver sleeps indefinitely when EEH errors exceed eeh_max_freezes

From: David Christensen
Date: Mon Jun 15 2020 - 15:01:49 EST


The driver function tg3_io_error_detected() calls napi_disable twice,
without an intervening napi_enable, when the number of EEH errors exceeds
eeh_max_freezes, resulting in an indefinite sleep while holding rtnl_lock.

The function is called once with the PCI state pci_channel_io_frozen and
then called again with the state pci_channel_io_perm_failure when the
number of EEH failures in an hour exceeds eeh_max_freezes.

Protecting the calls to napi_enable/napi_disable with a new state
variable prevents the long sleep.

Signed-off-by: David Christensen <drc@xxxxxxxxxxxxxxxxxx>
---
drivers/net/ethernet/broadcom/tg3.c | 18 +++++++++++++++---
drivers/net/ethernet/broadcom/tg3.h | 1 +
2 files changed, 16 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 7a3b22b35238..953f535e0ceb 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -7373,22 +7373,34 @@ static void tg3_napi_disable(struct tg3 *tp)
{
int i;

+ if (!tp->napi_enabled)
+ return;
+
for (i = tp->irq_cnt - 1; i >= 0; i--)
napi_disable(&tp->napi[i].napi);
+
+ tp->napi_enabled = false;
}

static void tg3_napi_enable(struct tg3 *tp)
{
int i;

+ if (tp->napi_enabled)
+ return;
+
for (i = 0; i < tp->irq_cnt; i++)
napi_enable(&tp->napi[i].napi);
+
+ tp->napi_enabled = true;
}

static void tg3_napi_init(struct tg3 *tp)
{
int i;

+ tp->napi_enabled = false;
+
netif_napi_add(tp->dev, &tp->napi[0].napi, tg3_poll, 64);
for (i = 1; i < tp->irq_cnt; i++)
netif_napi_add(tp->dev, &tp->napi[i].napi, tg3_poll_msix, 64);
@@ -7400,6 +7412,8 @@ static void tg3_napi_fini(struct tg3 *tp)

for (i = 0; i < tp->irq_cnt; i++)
netif_napi_del(&tp->napi[i].napi);
+
+ tp->napi_enabled = false;
}

static inline void tg3_netif_stop(struct tg3 *tp)
@@ -18194,10 +18208,8 @@ static pci_ers_result_t tg3_io_error_detected(struct pci_dev *pdev,

done:
if (state == pci_channel_io_perm_failure) {
- if (netdev) {
- tg3_napi_enable(tp);
+ if (netdev)
dev_close(netdev);
- }
err = PCI_ERS_RESULT_DISCONNECT;
} else {
pci_disable_device(pdev);
diff --git a/drivers/net/ethernet/broadcom/tg3.h b/drivers/net/ethernet/broadcom/tg3.h
index 6953d0546acb..0681f4b9ec79 100644
--- a/drivers/net/ethernet/broadcom/tg3.h
+++ b/drivers/net/ethernet/broadcom/tg3.h
@@ -3430,6 +3430,7 @@ struct tg3 {
u32 ape_hb;
unsigned long ape_hb_interval;
unsigned long ape_hb_jiffies;
+ bool napi_enabled;
};

/* Accessor macros for chip and asic attributes
--
2.18.2