Due to race conditions between qca_hw_error and qca_controller_memdump
during SSR timeout,the same pointer is freed twice. Which results to
double free error. Now a lock is acquired while SSR state moved to timeout.
Signed-off-by: Venkata Lakshmi Narayana Gubba <[email protected]>
---
drivers/bluetooth/hci_qca.c | 19 ++++++++++++++-----
1 file changed, 14 insertions(+), 5 deletions(-)
diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c
index 836949d..9110775 100644
--- a/drivers/bluetooth/hci_qca.c
+++ b/drivers/bluetooth/hci_qca.c
@@ -983,8 +983,11 @@ static void qca_controller_memdump(struct work_struct *work)
while ((skb = skb_dequeue(&qca->rx_memdump_q))) {
mutex_lock(&qca->hci_memdump_lock);
- /* Skip processing the received packets if timeout detected. */
- if (qca->memdump_state == QCA_MEMDUMP_TIMEOUT) {
+ /* Skip processing the received packets if timeout detected
+ * or memdump collection completed.
+ */
+ if (qca->memdump_state == QCA_MEMDUMP_TIMEOUT ||
+ qca->memdump_state == QCA_MEMDUMP_COLLECTED) {
mutex_unlock(&qca->hci_memdump_lock);
return;
}
@@ -1485,7 +1488,7 @@ static void qca_hw_error(struct hci_dev *hdev, u8 code)
{
struct hci_uart *hu = hci_get_drvdata(hdev);
struct qca_data *qca = hu->priv;
- struct qca_memdump_data *qca_memdump = qca->qca_memdump;
+ struct qca_memdump_data *qca_memdump = NULL;
char *memdump_buf = NULL;
set_bit(QCA_HW_ERROR_EVENT, &qca->flags);
@@ -1509,9 +1512,10 @@ static void qca_hw_error(struct hci_dev *hdev, u8 code)
qca_wait_for_dump_collection(hdev);
}
+ mutex_lock(&qca->hci_memdump_lock);
if (qca->memdump_state != QCA_MEMDUMP_COLLECTED) {
bt_dev_err(hu->hdev, "clearing allocated memory due to memdump timeout");
- mutex_lock(&qca->hci_memdump_lock);
+ qca_memdump = qca->qca_memdump;
if (qca_memdump)
memdump_buf = qca_memdump->memdump_buf_head;
vfree(memdump_buf);
@@ -1520,8 +1524,13 @@ static void qca_hw_error(struct hci_dev *hdev, u8 code)
qca->memdump_state = QCA_MEMDUMP_TIMEOUT;
cancel_delayed_work(&qca->ctrl_memdump_timeout);
skb_queue_purge(&qca->rx_memdump_q);
- mutex_unlock(&qca->hci_memdump_lock);
+ }
+ mutex_unlock(&qca->hci_memdump_lock);
+
+ if (qca->memdump_state == QCA_MEMDUMP_TIMEOUT ||
+ qca->memdump_state == QCA_MEMDUMP_COLLECTED) {
cancel_work_sync(&qca->ctrl_memdump_evt);
+ skb_queue_purge(&qca->rx_memdump_q);
}
clear_bit(QCA_HW_ERROR_EVENT, &qca->flags);
--
QUALCOMM INDIA, on behalf of Qualcomm Innovation Center, Inc. is a member
of Code Aurora Forum, hosted by The Linux Foundation
On 2020-06-04 19:27, Venkata Lakshmi Narayana Gubba wrote:
> Due to race conditions between qca_hw_error and qca_controller_memdump
> during SSR timeout,the same pointer is freed twice. Which results to
> double free error. Now a lock is acquired while SSR state moved to
> timeout.
>
> Signed-off-by: Venkata Lakshmi Narayana Gubba <[email protected]>
> ---
> drivers/bluetooth/hci_qca.c | 19 ++++++++++++++-----
> 1 file changed, 14 insertions(+), 5 deletions(-)
>
> diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c
> index 836949d..9110775 100644
> --- a/drivers/bluetooth/hci_qca.c
> +++ b/drivers/bluetooth/hci_qca.c
> @@ -983,8 +983,11 @@ static void qca_controller_memdump(struct
> work_struct *work)
> while ((skb = skb_dequeue(&qca->rx_memdump_q))) {
>
> mutex_lock(&qca->hci_memdump_lock);
> - /* Skip processing the received packets if timeout detected. */
> - if (qca->memdump_state == QCA_MEMDUMP_TIMEOUT) {
> + /* Skip processing the received packets if timeout detected
> + * or memdump collection completed.
> + */
> + if (qca->memdump_state == QCA_MEMDUMP_TIMEOUT ||
> + qca->memdump_state == QCA_MEMDUMP_COLLECTED) {
> mutex_unlock(&qca->hci_memdump_lock);
> return;
> }
> @@ -1485,7 +1488,7 @@ static void qca_hw_error(struct hci_dev *hdev, u8
> code)
> {
> struct hci_uart *hu = hci_get_drvdata(hdev);
> struct qca_data *qca = hu->priv;
> - struct qca_memdump_data *qca_memdump = qca->qca_memdump;
> + struct qca_memdump_data *qca_memdump = NULL;
> char *memdump_buf = NULL;
>
> set_bit(QCA_HW_ERROR_EVENT, &qca->flags);
> @@ -1509,9 +1512,10 @@ static void qca_hw_error(struct hci_dev *hdev,
> u8 code)
> qca_wait_for_dump_collection(hdev);
> }
>
> + mutex_lock(&qca->hci_memdump_lock);
> if (qca->memdump_state != QCA_MEMDUMP_COLLECTED) {
> bt_dev_err(hu->hdev, "clearing allocated memory due to memdump
> timeout");
> - mutex_lock(&qca->hci_memdump_lock);
> + qca_memdump = qca->qca_memdump;
> if (qca_memdump)
> memdump_buf = qca_memdump->memdump_buf_head;
> vfree(memdump_buf);
> @@ -1520,8 +1524,13 @@ static void qca_hw_error(struct hci_dev *hdev,
> u8 code)
> qca->memdump_state = QCA_MEMDUMP_TIMEOUT;
> cancel_delayed_work(&qca->ctrl_memdump_timeout);
> skb_queue_purge(&qca->rx_memdump_q);
> - mutex_unlock(&qca->hci_memdump_lock);
> + }
> + mutex_unlock(&qca->hci_memdump_lock);
> +
> + if (qca->memdump_state == QCA_MEMDUMP_TIMEOUT ||
> + qca->memdump_state == QCA_MEMDUMP_COLLECTED) {
> cancel_work_sync(&qca->ctrl_memdump_evt);
> + skb_queue_purge(&qca->rx_memdump_q);
> }
>
> clear_bit(QCA_HW_ERROR_EVENT, &qca->flags);
Reviewed-by: Balakrishna Godavarthi <[email protected]>
Hi,
On Thu, Jun 4, 2020 at 6:59 AM Venkata Lakshmi Narayana Gubba
<[email protected]> wrote:
>
> Due to race conditions between qca_hw_error and qca_controller_memdump
> during SSR timeout,the same pointer is freed twice. Which results to
> double free error. Now a lock is acquired while SSR state moved to timeout.
suggestion: Change "which results to double free error" to "This
results in a double free."
suggestion: Change "while SSR state moved to timeout" to "when SSR
state is changed to timeout"
>
> Signed-off-by: Venkata Lakshmi Narayana Gubba <[email protected]>
> ---
> drivers/bluetooth/hci_qca.c | 19 ++++++++++++++-----
> 1 file changed, 14 insertions(+), 5 deletions(-)
>
> diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c
> index 836949d..9110775 100644
> --- a/drivers/bluetooth/hci_qca.c
> +++ b/drivers/bluetooth/hci_qca.c
> @@ -983,8 +983,11 @@ static void qca_controller_memdump(struct work_struct *work)
> while ((skb = skb_dequeue(&qca->rx_memdump_q))) {
>
> mutex_lock(&qca->hci_memdump_lock);
> - /* Skip processing the received packets if timeout detected. */
> - if (qca->memdump_state == QCA_MEMDUMP_TIMEOUT) {
> + /* Skip processing the received packets if timeout detected
> + * or memdump collection completed.
> + */
> + if (qca->memdump_state == QCA_MEMDUMP_TIMEOUT ||
> + qca->memdump_state == QCA_MEMDUMP_COLLECTED) {
> mutex_unlock(&qca->hci_memdump_lock);
> return;
> }
> @@ -1485,7 +1488,7 @@ static void qca_hw_error(struct hci_dev *hdev, u8 code)
> {
> struct hci_uart *hu = hci_get_drvdata(hdev);
> struct qca_data *qca = hu->priv;
> - struct qca_memdump_data *qca_memdump = qca->qca_memdump;
> + struct qca_memdump_data *qca_memdump = NULL;
> char *memdump_buf = NULL;
>
> set_bit(QCA_HW_ERROR_EVENT, &qca->flags);
> @@ -1509,9 +1512,10 @@ static void qca_hw_error(struct hci_dev *hdev, u8 code)
> qca_wait_for_dump_collection(hdev);
> }
>
> + mutex_lock(&qca->hci_memdump_lock);
> if (qca->memdump_state != QCA_MEMDUMP_COLLECTED) {
> bt_dev_err(hu->hdev, "clearing allocated memory due to memdump timeout");
> - mutex_lock(&qca->hci_memdump_lock);
> + qca_memdump = qca->qca_memdump;
> if (qca_memdump)
> memdump_buf = qca_memdump->memdump_buf_head;
> vfree(memdump_buf);
This section of code looks a bit unclear because it's only partially
in an if statement. Suggestion:
if (qca->qca_memdump) {
vfree(qca->qca_memdump->memdump_buf_head);
kfree(qca->qca_memdump);
qca->qca_memdump = NULL;
}
> @@ -1520,8 +1524,13 @@ static void qca_hw_error(struct hci_dev *hdev, u8 code)
> qca->memdump_state = QCA_MEMDUMP_TIMEOUT;
> cancel_delayed_work(&qca->ctrl_memdump_timeout);
> skb_queue_purge(&qca->rx_memdump_q);
> - mutex_unlock(&qca->hci_memdump_lock);
> + }
> + mutex_unlock(&qca->hci_memdump_lock);
> +
> + if (qca->memdump_state == QCA_MEMDUMP_TIMEOUT ||
> + qca->memdump_state == QCA_MEMDUMP_COLLECTED) {
> cancel_work_sync(&qca->ctrl_memdump_evt);
> + skb_queue_purge(&qca->rx_memdump_q);
> }
Earlier in the function, you call qca_wait_for_dump_collection for
[Idle, Collecting] so the state should be either [Timeout, Collected]
at this branch. So, you can remove the `cancel_delayed_work` and
`skb_queue_purge` from above and just leave it only in the bottom
branch. Currently you're duplicating these calls unnecessarily.
I don't know if we discussed this in an earlier review but I noticed
that `qca_wait_for_dump_collection` doesn't actually pay attention to
the return value of `wait_on_bit_timeout`. I don't have context for
the order of calls anymore but is there a possibility for that timeout
to complete before `qca_memdump_timeout` is called? In that case, you
should probably set the state to timeout in
`qca_wait_for_dump_collection` as well.
>
> clear_bit(QCA_HW_ERROR_EVENT, &qca->flags);
> --
> QUALCOMM INDIA, on behalf of Qualcomm Innovation Center, Inc. is a member
> of Code Aurora Forum, hosted by The Linux Foundation
>
Hi Abhishek,
On 2020-06-05 10:23, Abhishek Pandit-Subedi wrote:
> Hi,
>
> On Thu, Jun 4, 2020 at 6:59 AM Venkata Lakshmi Narayana Gubba
> <[email protected]> wrote:
>>
>> Due to race conditions between qca_hw_error and qca_controller_memdump
>> during SSR timeout,the same pointer is freed twice. Which results to
>> double free error. Now a lock is acquired while SSR state moved to
>> timeout.
> suggestion: Change "which results to double free error" to "This
> results in a double free."
> suggestion: Change "while SSR state moved to timeout" to "when SSR
> state is changed to timeout"
>
[Venkata]:
Sure will update in next patchset.
>>
>> Signed-off-by: Venkata Lakshmi Narayana Gubba
>> <[email protected]>
>> ---
>> drivers/bluetooth/hci_qca.c | 19 ++++++++++++++-----
>> 1 file changed, 14 insertions(+), 5 deletions(-)
>>
>> diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c
>> index 836949d..9110775 100644
>> --- a/drivers/bluetooth/hci_qca.c
>> +++ b/drivers/bluetooth/hci_qca.c
>> @@ -983,8 +983,11 @@ static void qca_controller_memdump(struct
>> work_struct *work)
>> while ((skb = skb_dequeue(&qca->rx_memdump_q))) {
>>
>> mutex_lock(&qca->hci_memdump_lock);
>> - /* Skip processing the received packets if timeout
>> detected. */
>> - if (qca->memdump_state == QCA_MEMDUMP_TIMEOUT) {
>> + /* Skip processing the received packets if timeout
>> detected
>> + * or memdump collection completed.
>> + */
>> + if (qca->memdump_state == QCA_MEMDUMP_TIMEOUT ||
>> + qca->memdump_state == QCA_MEMDUMP_COLLECTED) {
>> mutex_unlock(&qca->hci_memdump_lock);
>> return;
>> }
>> @@ -1485,7 +1488,7 @@ static void qca_hw_error(struct hci_dev *hdev,
>> u8 code)
>> {
>> struct hci_uart *hu = hci_get_drvdata(hdev);
>> struct qca_data *qca = hu->priv;
>> - struct qca_memdump_data *qca_memdump = qca->qca_memdump;
>> + struct qca_memdump_data *qca_memdump = NULL;
>> char *memdump_buf = NULL;
>>
>> set_bit(QCA_HW_ERROR_EVENT, &qca->flags);
>> @@ -1509,9 +1512,10 @@ static void qca_hw_error(struct hci_dev *hdev,
>> u8 code)
>> qca_wait_for_dump_collection(hdev);
>> }
>>
>> + mutex_lock(&qca->hci_memdump_lock);
>> if (qca->memdump_state != QCA_MEMDUMP_COLLECTED) {
>> bt_dev_err(hu->hdev, "clearing allocated memory due to
>> memdump timeout");
>> - mutex_lock(&qca->hci_memdump_lock);
>> + qca_memdump = qca->qca_memdump;
>> if (qca_memdump)
>> memdump_buf = qca_memdump->memdump_buf_head;
>> vfree(memdump_buf);
>
> This section of code looks a bit unclear because it's only partially
> in an if statement. Suggestion:
> if (qca->qca_memdump) {
> vfree(qca->qca_memdump->memdump_buf_head);
> kfree(qca->qca_memdump);
> qca->qca_memdump = NULL;
> }
>
[Venkata]:
Sure will update in next patchset.
>> @@ -1520,8 +1524,13 @@ static void qca_hw_error(struct hci_dev *hdev,
>> u8 code)
>> qca->memdump_state = QCA_MEMDUMP_TIMEOUT;
>> cancel_delayed_work(&qca->ctrl_memdump_timeout);
>> skb_queue_purge(&qca->rx_memdump_q);
>> - mutex_unlock(&qca->hci_memdump_lock);
>> + }
>> + mutex_unlock(&qca->hci_memdump_lock);
>> +
>> + if (qca->memdump_state == QCA_MEMDUMP_TIMEOUT ||
>> + qca->memdump_state == QCA_MEMDUMP_COLLECTED) {
>> cancel_work_sync(&qca->ctrl_memdump_evt);
>> + skb_queue_purge(&qca->rx_memdump_q);
>> }
>
> Earlier in the function, you call qca_wait_for_dump_collection for
> [Idle, Collecting] so the state should be either [Timeout, Collected]
> at this branch. So, you can remove the `cancel_delayed_work` and
> `skb_queue_purge` from above and just leave it only in the bottom
> branch. Currently you're duplicating these calls unnecessarily.
>
> I don't know if we discussed this in an earlier review but I noticed
> that `qca_wait_for_dump_collection` doesn't actually pay attention to
> the return value of `wait_on_bit_timeout`. I don't have context for
> the order of calls anymore but is there a possibility for that timeout
> to complete before `qca_memdump_timeout` is called? In that case, you
> should probably set the state to timeout in
> `qca_wait_for_dump_collection` as well.
>
[Venkata]:
I see only skb_queue_purge is getting duplicated and will update in next
patchset.
But cancel_delayed_work is for qca->ctrl_memdump_timeout and
cancel_work_sync is for
qca->ctrl_memdump_evt.So these calls are not getting duplicated.
If timeout happens in qca_wait_for_dump_collection, we are setting state
to timeout
in subsequent if block which is if (qca->memdump_state !=
QCA_MEMDUMP_COLLECTED).
>>
>> clear_bit(QCA_HW_ERROR_EVENT, &qca->flags);
>> --
>> QUALCOMM INDIA, on behalf of Qualcomm Innovation Center, Inc. is a
>> member
>> of Code Aurora Forum, hosted by The Linux Foundation
>>
Regards,
Lakshmi Narayana.