| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <1355468932.24876.153.camel@yhuang-dev>
Date: Fri, 14 Dec 2012 15:08:52 +0800
From: Huang Ying <ying.huang@...el.com>
To: Greg Kroah-Hartman <gregkh@...uxfoundation.org>
Cc: Ben Hutchings <ben@...adent.org.uk>, linux-kernel@...r.kernel.org,
stable@...r.kernel.org, alan@...rguk.ukuu.org.uk,
Bjorn Helgaas <bhelgaas@...gle.com>,
"Rafael J. Wysocki" <rafael.j.wysocki@...el.com>,
Zhang Yanmin <yanmin.zhang@...el.com>
Subject: Re: [ 02/38] PCI/PM: Fix deadlock when unbinding device if parent
in D3cold
On Tue, 2012-12-11 at 10:08 -0800, Greg Kroah-Hartman wrote:
> On Tue, Dec 11, 2012 at 04:12:52PM +0800, Huang Ying wrote:
[snip]
> > Which tree should I base the patch on?
>
> 3.6.10 would be great.
Here is the patch for 3.6.10.
------------------------------------------------------------------------->
Subject: [PATCH] PCI/PM: Fix deadlock when unbind device if its parent in D3cold
If a PCI device and its parents are put into D3cold, unbinding the
device will trigger deadlock as follow:
- driver_unbind
- device_release_driver
- device_lock(dev) <--- previous lock here
- __device_release_driver
- pm_runtime_get_sync
...
- rpm_resume(dev)
- rpm_resume(dev->parent)
...
- pci_pm_runtime_resume
...
- pci_set_power_state
- __pci_start_power_transition
- pci_wakeup_bus(dev->parent->subordinate)
- pci_walk_bus
- device_lock(dev) <--- dead lock here
If we do not do device_lock in pci_walk_bus, we can avoid dead lock.
Device_lock in pci_walk_bus is introduced in commit:
d71374dafbba7ec3f67371d3b7e9f6310a588808, corresponding email thread
is: https://lkml.org/lkml/2006/5/26/38. The patch author Zhang Yanmin
said device_lock is added to pci_walk_bus because:
Some error handling functions call pci_walk_bus. For example, PCIe
aer. Here we lock the device, so the driver wouldn't detach from the
device, as the cb might call driver's callback function.
So I fixed the dead lock as follow:
- remove device_lock from pci_walk_bus
- add device_lock into callback if callback will call driver's callback
I checked pci_walk_bus users one by one, and found only PCIe aer needs
device lock.
Signed-off-by: Huang Ying <ying.huang@...el.com>
Cc: Zhang Yanmin <yanmin.zhang@...el.com>
---
arch/powerpc/platforms/pseries/eeh_driver.c | 35 ++++++++++++++++++++--------
drivers/pci/bus.c | 3 --
drivers/pci/pcie/aer/aerdrv_core.c | 20 ++++++++++++----
3 files changed, 41 insertions(+), 17 deletions(-)
--- a/drivers/pci/bus.c
+++ b/drivers/pci/bus.c
@@ -316,10 +316,7 @@ void pci_walk_bus(struct pci_bus *top, i
} else
next = dev->bus_list.next;
- /* Run device routines with the device locked */
- device_lock(&dev->dev);
retval = cb(dev, userdata);
- device_unlock(&dev->dev);
if (retval)
break;
}
--- a/drivers/pci/pcie/aer/aerdrv_core.c
+++ b/drivers/pci/pcie/aer/aerdrv_core.c
@@ -244,6 +244,7 @@ static int report_error_detected(struct
struct aer_broadcast_data *result_data;
result_data = (struct aer_broadcast_data *) data;
+ device_lock(&dev->dev);
dev->error_state = result_data->state;
if (!dev->driver ||
@@ -262,12 +263,14 @@ static int report_error_detected(struct
dev->driver ?
"no AER-aware driver" : "no driver");
}
- return 0;
+ goto out;
}
err_handler = dev->driver->err_handler;
vote = err_handler->error_detected(dev, result_data->state);
result_data->result = merge_result(result_data->result, vote);
+out:
+ device_unlock(&dev->dev);
return 0;
}
@@ -278,14 +281,17 @@ static int report_mmio_enabled(struct pc
struct aer_broadcast_data *result_data;
result_data = (struct aer_broadcast_data *) data;
+ device_lock(&dev->dev);
if (!dev->driver ||
!dev->driver->err_handler ||
!dev->driver->err_handler->mmio_enabled)
- return 0;
+ goto out;
err_handler = dev->driver->err_handler;
vote = err_handler->mmio_enabled(dev);
result_data->result = merge_result(result_data->result, vote);
+out:
+ device_unlock(&dev->dev);
return 0;
}
@@ -296,14 +302,17 @@ static int report_slot_reset(struct pci_
struct aer_broadcast_data *result_data;
result_data = (struct aer_broadcast_data *) data;
+ device_lock(&dev->dev);
if (!dev->driver ||
!dev->driver->err_handler ||
!dev->driver->err_handler->slot_reset)
- return 0;
+ goto out;
err_handler = dev->driver->err_handler;
vote = err_handler->slot_reset(dev);
result_data->result = merge_result(result_data->result, vote);
+out:
+ device_unlock(&dev->dev);
return 0;
}
@@ -311,15 +320,18 @@ static int report_resume(struct pci_dev
{
struct pci_error_handlers *err_handler;
+ device_lock(&dev->dev);
dev->error_state = pci_channel_io_normal;
if (!dev->driver ||
!dev->driver->err_handler ||
!dev->driver->err_handler->resume)
- return 0;
+ goto out;
err_handler = dev->driver->err_handler;
err_handler->resume(dev);
+out:
+ device_unlock(&dev->dev);
return 0;
}
--- a/arch/powerpc/platforms/pseries/eeh_driver.c
+++ b/arch/powerpc/platforms/pseries/eeh_driver.c
@@ -164,17 +164,18 @@ static int eeh_report_error(struct pci_d
enum pci_ers_result rc, *res = userdata;
struct pci_driver *driver;
+ device_lock(&dev->dev);
dev->error_state = pci_channel_io_frozen;
driver = eeh_pcid_get(dev);
- if (!driver) return 0;
+ if (!driver) goto out;
eeh_disable_irq(dev);
if (!driver->err_handler ||
!driver->err_handler->error_detected) {
eeh_pcid_put(dev);
- return 0;
+ goto out;
}
rc = driver->err_handler->error_detected(dev, pci_channel_io_frozen);
@@ -184,6 +185,8 @@ static int eeh_report_error(struct pci_d
if (*res == PCI_ERS_RESULT_NONE) *res = rc;
eeh_pcid_put(dev);
+out:
+ device_unlock(&dev->dev);
return 0;
}
@@ -201,13 +204,14 @@ static int eeh_report_mmio_enabled(struc
enum pci_ers_result rc, *res = userdata;
struct pci_driver *driver;
+ device_lock(&dev->dev);
driver = eeh_pcid_get(dev);
- if (!driver) return 0;
+ if (!driver) goto out;
if (!driver->err_handler ||
!driver->err_handler->mmio_enabled) {
eeh_pcid_put(dev);
- return 0;
+ goto out;
}
rc = driver->err_handler->mmio_enabled(dev);
@@ -217,6 +221,8 @@ static int eeh_report_mmio_enabled(struc
if (*res == PCI_ERS_RESULT_NONE) *res = rc;
eeh_pcid_put(dev);
+out:
+ device_unlock(&dev->dev);
return 0;
}
@@ -235,17 +241,18 @@ static int eeh_report_reset(struct pci_d
enum pci_ers_result rc, *res = userdata;
struct pci_driver *driver;
+ device_lock(&dev->dev);
dev->error_state = pci_channel_io_normal;
driver = eeh_pcid_get(dev);
- if (!driver) return 0;
+ if (!driver) goto out;
eeh_enable_irq(dev);
if (!driver->err_handler ||
!driver->err_handler->slot_reset) {
eeh_pcid_put(dev);
- return 0;
+ goto out;
}
rc = driver->err_handler->slot_reset(dev);
@@ -255,6 +262,8 @@ static int eeh_report_reset(struct pci_d
rc == PCI_ERS_RESULT_NEED_RESET) *res = rc;
eeh_pcid_put(dev);
+out:
+ device_unlock(&dev->dev);
return 0;
}
@@ -271,22 +280,25 @@ static int eeh_report_resume(struct pci_
{
struct pci_driver *driver;
+ device_lock(&dev->dev);
dev->error_state = pci_channel_io_normal;
driver = eeh_pcid_get(dev);
- if (!driver) return 0;
+ if (!driver) goto out;
eeh_enable_irq(dev);
if (!driver->err_handler ||
!driver->err_handler->resume) {
eeh_pcid_put(dev);
- return 0;
+ goto out;
}
driver->err_handler->resume(dev);
eeh_pcid_put(dev);
+out:
+ device_unlock(&dev->dev);
return 0;
}
@@ -302,22 +314,25 @@ static int eeh_report_failure(struct pci
{
struct pci_driver *driver;
+ device_lock(&dev->dev);
dev->error_state = pci_channel_io_perm_failure;
driver = eeh_pcid_get(dev);
- if (!driver) return 0;
+ if (!driver) goto out;
eeh_disable_irq(dev);
if (!driver->err_handler ||
!driver->err_handler->error_detected) {
eeh_pcid_put(dev);
- return 0;
+ goto out;
}
driver->err_handler->error_detected(dev, pci_channel_io_perm_failure);
eeh_pcid_put(dev);
+out:
+ device_unlock(&dev->dev);
return 0;
}
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists