diff options
authorSebastian Andrzej Siewior <bigeasy@linutronix.de>2016-01-25 10:08:00 -0600
committerGreg Kroah-Hartman <gregkh@linuxfoundation.org>2016-03-03 15:06:24 -0800
commitdcc121e02f773b4b8fc88522810214af39ea8313 (patch)
parent43a349917d77250e1fb7dbcb44e50a80b8cab026 (diff)
PCI/AER: Flush workqueue on device remove to avoid use-after-free
commit 4ae2182b1e3407de369f8c5d799543b7db74221b upstream. A Root Port's AER structure (rpc) contains a queue of events. aer_irq() enqueues AER status information and schedules aer_isr() to dequeue and process it. When we remove a device, aer_remove() waits for the queue to be empty, then frees the rpc struct. But aer_isr() references the rpc struct after dequeueing and possibly emptying the queue, which can cause a use-after-free error as in the following scenario with two threads, aer_isr() on the left and a concurrent aer_remove() on the right: Thread A Thread B -------- -------- aer_irq(): rpc->prod_idx++ aer_remove(): wait_event(rpc->prod_idx == rpc->cons_idx) # now blocked until queue becomes empty aer_isr(): # ... rpc->cons_idx++ # unblocked because queue is now empty ... kfree(rpc) mutex_unlock(&rpc->rpc_mutex) To prevent this problem, use flush_work() to wait until the last scheduled instance of aer_isr() has completed before freeing the rpc struct in aer_remove(). I reproduced this use-after-free by flashing a device FPGA and re-enumerating the bus to find the new device. With SLUB debug, this crashes with 0x6b bytes (POISON_FREE, the use-after-free magic number) in GPR25: pcieport 0000:00:00.0: AER: Multiple Corrected error received: id=0000 Unable to handle kernel paging request for data at address 0x27ef9e3e Workqueue: events aer_isr GPR24: dd6aa000 6b6b6b6b 605f8378 605f8360 d99b12c0 604fc674 606b1704 d99b12c0 NIP [602f5328] pci_walk_bus+0xd4/0x104 [bhelgaas: changelog, stable tag] Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Bjorn Helgaas <bhelgaas@google.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
3 files changed, 1 insertions, 6 deletions
diff --git a/drivers/pci/pcie/aer/aerdrv.c b/drivers/pci/pcie/aer/aerdrv.c
index 76ef634caf6f..b84e713445d0 100644
--- a/drivers/pci/pcie/aer/aerdrv.c
+++ b/drivers/pci/pcie/aer/aerdrv.c
@@ -262,7 +262,6 @@ static struct aer_rpc *aer_alloc_rpc(struct pcie_device *dev)
rpc->rpd = dev;
INIT_WORK(&rpc->dpc_handler, aer_isr);
- init_waitqueue_head(&rpc->wait_release);
/* Use PCIe bus function to store rpc into PCIe device */
set_service_data(dev, rpc);
@@ -285,8 +284,7 @@ static void aer_remove(struct pcie_device *dev)
if (rpc->isr)
free_irq(dev->irq, dev);
- wait_event(rpc->wait_release, rpc->prod_idx == rpc->cons_idx);
+ flush_work(&rpc->dpc_handler);
set_service_data(dev, NULL);
diff --git a/drivers/pci/pcie/aer/aerdrv.h b/drivers/pci/pcie/aer/aerdrv.h
index d12c77cd6991..3b8766e1e51b 100644
--- a/drivers/pci/pcie/aer/aerdrv.h
+++ b/drivers/pci/pcie/aer/aerdrv.h
@@ -76,7 +76,6 @@ struct aer_rpc {
* recovery on the same
* root port hierarchy
- wait_queue_head_t wait_release;
struct aer_broadcast_data {
diff --git a/drivers/pci/pcie/aer/aerdrv_core.c b/drivers/pci/pcie/aer/aerdrv_core.c
index 0f4554e48cc5..a017aac0d7ed 100644
--- a/drivers/pci/pcie/aer/aerdrv_core.c
+++ b/drivers/pci/pcie/aer/aerdrv_core.c
@@ -817,8 +817,6 @@ void aer_isr(struct work_struct *work)
while (get_e_source(rpc, &e_src))
aer_isr_one_error(p_device, &e_src);
- wake_up(&rpc->wait_release);