Currently, the hibmcge netdev acquires the rtnl_lock in
pci_error_handlers.reset_prepare() and releases it in
pci_error_handlers.reset_done().
However, in the PCI framework:
pci_reset_bus - __pci_reset_slot - pci_slot_save_and_disable_locked -
pci_dev_save_and_disable - err_handler->reset_prepare(dev);
In pci_slot_save_and_disable_locked():
list_for_each_entry(dev, &slot->bus->devices, bus_list) {
if (!dev->slot || dev->slot!= slot)
continue;
pci_dev_save_and_disable(dev);
if (dev->subordinate)
pci_bus_save_and_disable_locked(dev->subordinate);
}
This will iterate through all devices under the current bus and execute
err_handler->reset_prepare(), causing two devices of the hibmcge driver
to sequentially request the rtnl_lock, leading to a deadlock.
Since the driver now executes netif_device_detach()
before the reset process, it will not concurrently with
other netdev APIs, so there is no need to hold the rtnl_lock now.
Therefore, this patch removes the rtnl_lock during the reset process and
adjusts the position of HBG_NIC_STATE_RESETTING to ensure
that multiple resets are not executed concurrently.
Fixes: 3f5a61f6d504f ("net: hibmcge: Add reset supported in this module")
Signed-off-by: Jijie Shao <shaojijie@huawei.com>
---
drivers/net/ethernet/hisilicon/hibmcge/hbg_err.c | 13 ++++---------
1 file changed, 4 insertions(+), 9 deletions(-)
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.c
index 503cfbfb4a8a..94bc6f0da912 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.c
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.c
@@ -53,9 +53,11 @@ static int hbg_reset_prepare(struct hbg_priv *priv, enum hbg_reset_type type)
{
int ret;
- ASSERT_RTNL();
+ if (test_and_set_bit(HBG_NIC_STATE_RESETTING, &priv->state))
+ return -EBUSY;
if (netif_running(priv->netdev)) {
+ clear_bit(HBG_NIC_STATE_RESETTING, &priv->state);
dev_warn(&priv->pdev->dev,
"failed to reset because port is up\n");
return -EBUSY;
@@ -64,7 +66,6 @@ static int hbg_reset_prepare(struct hbg_priv *priv, enum hbg_reset_type type)
netif_device_detach(priv->netdev);
priv->reset_type = type;
- set_bit(HBG_NIC_STATE_RESETTING, &priv->state);
clear_bit(HBG_NIC_STATE_RESET_FAIL, &priv->state);
ret = hbg_hw_event_notify(priv, HBG_HW_EVENT_RESET);
if (ret) {
@@ -84,10 +85,8 @@ static int hbg_reset_done(struct hbg_priv *priv, enum hbg_reset_type type)
type != priv->reset_type)
return 0;
- ASSERT_RTNL();
-
- clear_bit(HBG_NIC_STATE_RESETTING, &priv->state);
ret = hbg_rebuild(priv);
+ clear_bit(HBG_NIC_STATE_RESETTING, &priv->state);
if (ret) {
priv->stats.reset_fail_cnt++;
set_bit(HBG_NIC_STATE_RESET_FAIL, &priv->state);
@@ -101,12 +100,10 @@ static int hbg_reset_done(struct hbg_priv *priv, enum hbg_reset_type type)
return ret;
}
-/* must be protected by rtnl lock */
int hbg_reset(struct hbg_priv *priv)
{
int ret;
- ASSERT_RTNL();
ret = hbg_reset_prepare(priv, HBG_RESET_TYPE_FUNCTION);
if (ret)
return ret;
@@ -171,7 +168,6 @@ static void hbg_pci_err_reset_prepare(struct pci_dev *pdev)
struct net_device *netdev = pci_get_drvdata(pdev);
struct hbg_priv *priv = netdev_priv(netdev);
- rtnl_lock();
hbg_reset_prepare(priv, HBG_RESET_TYPE_FLR);
}
@@ -181,7 +177,6 @@ static void hbg_pci_err_reset_done(struct pci_dev *pdev)
struct hbg_priv *priv = netdev_priv(netdev);
hbg_reset_done(priv, HBG_RESET_TYPE_FLR);
- rtnl_unlock();
}
static const struct pci_error_handlers hbg_pci_err_handler = {
--
2.33.0On Thu, Jul 31, 2025 at 09:47:47PM +0800, Jijie Shao wrote:
> Currently, the hibmcge netdev acquires the rtnl_lock in
> pci_error_handlers.reset_prepare() and releases it in
> pci_error_handlers.reset_done().
>
> However, in the PCI framework:
> pci_reset_bus - __pci_reset_slot - pci_slot_save_and_disable_locked -
> pci_dev_save_and_disable - err_handler->reset_prepare(dev);
>
> In pci_slot_save_and_disable_locked():
> list_for_each_entry(dev, &slot->bus->devices, bus_list) {
> if (!dev->slot || dev->slot!= slot)
> continue;
> pci_dev_save_and_disable(dev);
> if (dev->subordinate)
> pci_bus_save_and_disable_locked(dev->subordinate);
> }
>
> This will iterate through all devices under the current bus and execute
> err_handler->reset_prepare(), causing two devices of the hibmcge driver
> to sequentially request the rtnl_lock, leading to a deadlock.
>
> Since the driver now executes netif_device_detach()
> before the reset process, it will not concurrently with
> other netdev APIs, so there is no need to hold the rtnl_lock now.
>
> Therefore, this patch removes the rtnl_lock during the reset process and
> adjusts the position of HBG_NIC_STATE_RESETTING to ensure
> that multiple resets are not executed concurrently.
>
> Fixes: 3f5a61f6d504f ("net: hibmcge: Add reset supported in this module")
> Signed-off-by: Jijie Shao <shaojijie@huawei.com>
> ---
> drivers/net/ethernet/hisilicon/hibmcge/hbg_err.c | 13 ++++---------
> 1 file changed, 4 insertions(+), 9 deletions(-)
>
> diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.c
> index 503cfbfb4a8a..94bc6f0da912 100644
> --- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.c
> +++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.c
> @@ -53,9 +53,11 @@ static int hbg_reset_prepare(struct hbg_priv *priv, enum hbg_reset_type type)
> {
> int ret;
>
> - ASSERT_RTNL();
> + if (test_and_set_bit(HBG_NIC_STATE_RESETTING, &priv->state))
> + return -EBUSY;
>
> if (netif_running(priv->netdev)) {
> + clear_bit(HBG_NIC_STATE_RESETTING, &priv->state);
> dev_warn(&priv->pdev->dev,
> "failed to reset because port is up\n");
> return -EBUSY;
> @@ -64,7 +66,6 @@ static int hbg_reset_prepare(struct hbg_priv *priv, enum hbg_reset_type type)
> netif_device_detach(priv->netdev);
>
> priv->reset_type = type;
> - set_bit(HBG_NIC_STATE_RESETTING, &priv->state);
> clear_bit(HBG_NIC_STATE_RESET_FAIL, &priv->state);
> ret = hbg_hw_event_notify(priv, HBG_HW_EVENT_RESET);
> if (ret) {
> @@ -84,10 +85,8 @@ static int hbg_reset_done(struct hbg_priv *priv, enum hbg_reset_type type)
> type != priv->reset_type)
> return 0;
>
> - ASSERT_RTNL();
> -
> - clear_bit(HBG_NIC_STATE_RESETTING, &priv->state);
> ret = hbg_rebuild(priv);
> + clear_bit(HBG_NIC_STATE_RESETTING, &priv->state);
Hi Jijie,
If I understand things correctly, then with this patch the
HBG_NIC_STATE_RESETTING bit is used to prevent concurrent execution.
Noting that a reset may be triggered via eththool, where hbg_reset() is
used as a callback, I am concerned about concurrency implications for lines
below this one.
> if (ret) {
> priv->stats.reset_fail_cnt++;
> set_bit(HBG_NIC_STATE_RESET_FAIL, &priv->state);
> @@ -101,12 +100,10 @@ static int hbg_reset_done(struct hbg_priv *priv, enum hbg_reset_type type)
> return ret;
> }
>
> -/* must be protected by rtnl lock */
> int hbg_reset(struct hbg_priv *priv)
> {
> int ret;
>
> - ASSERT_RTNL();
> ret = hbg_reset_prepare(priv, HBG_RESET_TYPE_FUNCTION);
> if (ret)
> return ret;
> @@ -171,7 +168,6 @@ static void hbg_pci_err_reset_prepare(struct pci_dev *pdev)
> struct net_device *netdev = pci_get_drvdata(pdev);
> struct hbg_priv *priv = netdev_priv(netdev);
>
> - rtnl_lock();
> hbg_reset_prepare(priv, HBG_RESET_TYPE_FLR);
> }
>
> @@ -181,7 +177,6 @@ static void hbg_pci_err_reset_done(struct pci_dev *pdev)
> struct hbg_priv *priv = netdev_priv(netdev);
>
> hbg_reset_done(priv, HBG_RESET_TYPE_FLR);
> - rtnl_unlock();
> }
>
> static const struct pci_error_handlers hbg_pci_err_handler = {
> --
> 2.33.0
>
on 2025/8/1 18:05, Simon Horman wrote:
> On Thu, Jul 31, 2025 at 09:47:47PM +0800, Jijie Shao wrote:
>> Currently, the hibmcge netdev acquires the rtnl_lock in
>> pci_error_handlers.reset_prepare() and releases it in
>> pci_error_handlers.reset_done().
>>
>> However, in the PCI framework:
>> pci_reset_bus - __pci_reset_slot - pci_slot_save_and_disable_locked -
>> pci_dev_save_and_disable - err_handler->reset_prepare(dev);
>>
>> In pci_slot_save_and_disable_locked():
>> list_for_each_entry(dev, &slot->bus->devices, bus_list) {
>> if (!dev->slot || dev->slot!= slot)
>> continue;
>> pci_dev_save_and_disable(dev);
>> if (dev->subordinate)
>> pci_bus_save_and_disable_locked(dev->subordinate);
>> }
>>
>> This will iterate through all devices under the current bus and execute
>> err_handler->reset_prepare(), causing two devices of the hibmcge driver
>> to sequentially request the rtnl_lock, leading to a deadlock.
>>
>> Since the driver now executes netif_device_detach()
>> before the reset process, it will not concurrently with
>> other netdev APIs, so there is no need to hold the rtnl_lock now.
>>
>> Therefore, this patch removes the rtnl_lock during the reset process and
>> adjusts the position of HBG_NIC_STATE_RESETTING to ensure
>> that multiple resets are not executed concurrently.
>>
>> Fixes: 3f5a61f6d504f ("net: hibmcge: Add reset supported in this module")
>> Signed-off-by: Jijie Shao <shaojijie@huawei.com>
>> ---
>> drivers/net/ethernet/hisilicon/hibmcge/hbg_err.c | 13 ++++---------
>> 1 file changed, 4 insertions(+), 9 deletions(-)
>>
>> diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.c
>> index 503cfbfb4a8a..94bc6f0da912 100644
>> --- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.c
>> +++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.c
>> @@ -53,9 +53,11 @@ static int hbg_reset_prepare(struct hbg_priv *priv, enum hbg_reset_type type)
>> {
>> int ret;
>>
>> - ASSERT_RTNL();
>> + if (test_and_set_bit(HBG_NIC_STATE_RESETTING, &priv->state))
>> + return -EBUSY;
>>
>> if (netif_running(priv->netdev)) {
>> + clear_bit(HBG_NIC_STATE_RESETTING, &priv->state);
>> dev_warn(&priv->pdev->dev,
>> "failed to reset because port is up\n");
>> return -EBUSY;
>> @@ -64,7 +66,6 @@ static int hbg_reset_prepare(struct hbg_priv *priv, enum hbg_reset_type type)
>> netif_device_detach(priv->netdev);
>>
>> priv->reset_type = type;
>> - set_bit(HBG_NIC_STATE_RESETTING, &priv->state);
>> clear_bit(HBG_NIC_STATE_RESET_FAIL, &priv->state);
>> ret = hbg_hw_event_notify(priv, HBG_HW_EVENT_RESET);
>> if (ret) {
>> @@ -84,10 +85,8 @@ static int hbg_reset_done(struct hbg_priv *priv, enum hbg_reset_type type)
>> type != priv->reset_type)
>> return 0;
>>
>> - ASSERT_RTNL();
>> -
>> - clear_bit(HBG_NIC_STATE_RESETTING, &priv->state);
>> ret = hbg_rebuild(priv);
>> + clear_bit(HBG_NIC_STATE_RESETTING, &priv->state);
> Hi Jijie,
>
> If I understand things correctly, then with this patch the
> HBG_NIC_STATE_RESETTING bit is used to prevent concurrent execution.
>
> Noting that a reset may be triggered via eththool, where hbg_reset() is
> used as a callback, I am concerned about concurrency implications for lines
> below this one.
Yes, just like the following, it can lead to reset and net open concurrency.
===========
reset1 reset2 open
set_bit HBG_NIC_STATE_RESETTING
netif_device_detach()
resetting...
clear_bit HBG_NIC_STATE_RESETTING
set_bit HBG_NIC_STATE_RESETTING
netif_device_detach()
netif_device_attach()
resetting... hbg_net_open()
hbg_txrx_init()
clear_bit HBG_NIC_STATE_RESETTING
netif_device_attach()
============
Thank you for your reminder.
I will fix it in V2
Jijie Shao
>> if (ret) {
>> priv->stats.reset_fail_cnt++;
>> set_bit(HBG_NIC_STATE_RESET_FAIL, &priv->state);
>> @@ -101,12 +100,10 @@ static int hbg_reset_done(struct hbg_priv *priv, enum hbg_reset_type type)
>> return ret;
>> }
>>
>> -/* must be protected by rtnl lock */
>> int hbg_reset(struct hbg_priv *priv)
>> {
>> int ret;
>>
>> - ASSERT_RTNL();
>> ret = hbg_reset_prepare(priv, HBG_RESET_TYPE_FUNCTION);
>> if (ret)
>> return ret;
>> @@ -171,7 +168,6 @@ static void hbg_pci_err_reset_prepare(struct pci_dev *pdev)
>> struct net_device *netdev = pci_get_drvdata(pdev);
>> struct hbg_priv *priv = netdev_priv(netdev);
>>
>> - rtnl_lock();
>> hbg_reset_prepare(priv, HBG_RESET_TYPE_FLR);
>> }
>>
>> @@ -181,7 +177,6 @@ static void hbg_pci_err_reset_done(struct pci_dev *pdev)
>> struct hbg_priv *priv = netdev_priv(netdev);
>>
>> hbg_reset_done(priv, HBG_RESET_TYPE_FLR);
>> - rtnl_unlock();
>> }
>>
>> static const struct pci_error_handlers hbg_pci_err_handler = {
>> --
>> 2.33.0
>>
On Fri, Aug 01, 2025 at 06:44:36PM +0800, Jijie Shao wrote:
>
> on 2025/8/1 18:05, Simon Horman wrote:
> > On Thu, Jul 31, 2025 at 09:47:47PM +0800, Jijie Shao wrote:
> > > Currently, the hibmcge netdev acquires the rtnl_lock in
> > > pci_error_handlers.reset_prepare() and releases it in
> > > pci_error_handlers.reset_done().
> > >
> > > However, in the PCI framework:
> > > pci_reset_bus - __pci_reset_slot - pci_slot_save_and_disable_locked -
> > > pci_dev_save_and_disable - err_handler->reset_prepare(dev);
> > >
> > > In pci_slot_save_and_disable_locked():
> > > list_for_each_entry(dev, &slot->bus->devices, bus_list) {
> > > if (!dev->slot || dev->slot!= slot)
> > > continue;
> > > pci_dev_save_and_disable(dev);
> > > if (dev->subordinate)
> > > pci_bus_save_and_disable_locked(dev->subordinate);
> > > }
> > >
> > > This will iterate through all devices under the current bus and execute
> > > err_handler->reset_prepare(), causing two devices of the hibmcge driver
> > > to sequentially request the rtnl_lock, leading to a deadlock.
> > >
> > > Since the driver now executes netif_device_detach()
> > > before the reset process, it will not concurrently with
> > > other netdev APIs, so there is no need to hold the rtnl_lock now.
> > >
> > > Therefore, this patch removes the rtnl_lock during the reset process and
> > > adjusts the position of HBG_NIC_STATE_RESETTING to ensure
> > > that multiple resets are not executed concurrently.
> > >
> > > Fixes: 3f5a61f6d504f ("net: hibmcge: Add reset supported in this module")
> > > Signed-off-by: Jijie Shao <shaojijie@huawei.com>
> > > ---
> > > drivers/net/ethernet/hisilicon/hibmcge/hbg_err.c | 13 ++++---------
> > > 1 file changed, 4 insertions(+), 9 deletions(-)
> > >
> > > diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.c
> > > index 503cfbfb4a8a..94bc6f0da912 100644
> > > --- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.c
> > > +++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.c
> > > @@ -53,9 +53,11 @@ static int hbg_reset_prepare(struct hbg_priv *priv, enum hbg_reset_type type)
> > > {
> > > int ret;
> > > - ASSERT_RTNL();
> > > + if (test_and_set_bit(HBG_NIC_STATE_RESETTING, &priv->state))
> > > + return -EBUSY;
> > > if (netif_running(priv->netdev)) {
> > > + clear_bit(HBG_NIC_STATE_RESETTING, &priv->state);
> > > dev_warn(&priv->pdev->dev,
> > > "failed to reset because port is up\n");
> > > return -EBUSY;
> > > @@ -64,7 +66,6 @@ static int hbg_reset_prepare(struct hbg_priv *priv, enum hbg_reset_type type)
> > > netif_device_detach(priv->netdev);
> > > priv->reset_type = type;
> > > - set_bit(HBG_NIC_STATE_RESETTING, &priv->state);
> > > clear_bit(HBG_NIC_STATE_RESET_FAIL, &priv->state);
> > > ret = hbg_hw_event_notify(priv, HBG_HW_EVENT_RESET);
> > > if (ret) {
> > > @@ -84,10 +85,8 @@ static int hbg_reset_done(struct hbg_priv *priv, enum hbg_reset_type type)
> > > type != priv->reset_type)
> > > return 0;
> > > - ASSERT_RTNL();
> > > -
> > > - clear_bit(HBG_NIC_STATE_RESETTING, &priv->state);
> > > ret = hbg_rebuild(priv);
> > > + clear_bit(HBG_NIC_STATE_RESETTING, &priv->state);
> > Hi Jijie,
> >
> > If I understand things correctly, then with this patch the
> > HBG_NIC_STATE_RESETTING bit is used to prevent concurrent execution.
> >
> > Noting that a reset may be triggered via eththool, where hbg_reset() is
> > used as a callback, I am concerned about concurrency implications for lines
> > below this one.
>
> Yes, just like the following, it can lead to reset and net open concurrency.
> ===========
>
> reset1 reset2 open
>
> set_bit HBG_NIC_STATE_RESETTING
>
> netif_device_detach()
> resetting...
>
> clear_bit HBG_NIC_STATE_RESETTING
> set_bit HBG_NIC_STATE_RESETTING
> netif_device_detach()
>
> netif_device_attach()
> resetting... hbg_net_open()
> hbg_txrx_init()
>
> clear_bit HBG_NIC_STATE_RESETTING
> netif_device_attach()
>
> ============
> Thank you for your reminder.
> I will fix it in V2
Likewise, thanks.
--
pw-bot: cr
© 2016 - 2025 Red Hat, Inc.