[PATCH v2] ath10k: support firmware crash-by-assert

[PATCH v2] ath10k: support firmware crash-by-assert

[Kalle Valo]

From: Ben Greear <greearb@candelatech.com>

10.1 firmware does not have an official way to
cause assert on purpose, but it can be done with
carefully crafted WMI command.  This is a different
kind of crash from the 'hard' crash, which is
a bad memory dereference.

Different crashes decode in different manners, so
this will help the crash-report testing as well as
offer better ways to test firmware failure and
recovery.

kvalo: move the wmi command creation to debug.c, modify
the info print

Signed-off-by: Ben Greear <greearb@candelatech.com>
Signed-off-by: Kalle Valo <kvalo@qca.qualcomm.com>
---
 drivers/net/wireless/ath/ath10k/debug.c |   28 +++++++++++++++++++++++++++-
 1 file changed, 27 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath10k/debug.c b/drivers/net/wireless/ath/ath10k/debug.c
index f948a4d8ee59..c5d01058c2a3 100644
--- a/drivers/net/wireless/ath/ath10k/debug.c
+++ b/drivers/net/wireless/ath/ath10k/debug.c
@@ -565,6 +565,26 @@ static const struct file_operations fops_fw_stats = {
 	.llseek = default_llseek,
 };
 
+/* This is a clean assert crash in firmware. */
+static int ath10k_debug_fw_assert(struct ath10k *ar)
+{
+	struct wmi_vdev_install_key_cmd *cmd;
+	struct sk_buff *skb;
+
+	skb = ath10k_wmi_alloc_skb(ar, sizeof(*cmd) + 16);
+	if (!skb)
+		return -ENOMEM;
+
+	cmd = (struct wmi_vdev_install_key_cmd *)skb->data;
+	memset(cmd, 0, sizeof(*cmd));
+
+	/* big enough number so that firmware asserts */
+	cmd->vdev_id = __cpu_to_le32(0x7ffe);
+
+	return ath10k_wmi_cmd_send(ar, skb,
+				   ar->wmi.cmd->vdev_install_key_cmdid);
+}
+
 static ssize_t ath10k_read_simulate_fw_crash(struct file *file,
 					     char __user *user_buf,
 					     size_t count, loff_t *ppos)
@@ -574,7 +594,10 @@ static ssize_t ath10k_read_simulate_fw_crash(struct file *file,
 			   " WMI_FORCE_FW_HANG_ASSERT to firmware if FW"
 			   " supports that command.\n `hard` - this will send"
 			   " to firmware command with illegal parameters"
-			   " causing firmware crash.\n";
+			   " causing firmware crash.\n"
+			   "`assert` - this will send special illegal parameter"
+			   " to firmware to cause assert failure"
+			   " and crash.\n";
 
 	return simple_read_from_buffer(user_buf, count, ppos, buf, strlen(buf));
 }
@@ -623,6 +646,9 @@ static ssize_t ath10k_write_simulate_fw_crash(struct file *file,
 		 */
 		ret = ath10k_wmi_vdev_set_param(ar, 0x7fff,
 					ar->wmi.vdev_param->rts_threshold, 0);
+	} else if (!strcmp(buf, "assert")) {
+		ath10k_info(ar, "simulating firmware assert crash\n");
+		ret = ath10k_debug_fw_assert(ar);
 	} else {
 		ret = -EINVAL;
 		goto exit;

[PATCH v2] ath10k: support firmware crash-by-assert

[Kalle Valo]

From: Ben Greear <greearb@candelatech.com>

10.1 firmware does not have an official way to
cause assert on purpose, but it can be done with
carefully crafted WMI command.  This is a different
kind of crash from the 'hard' crash, which is
a bad memory dereference.

Different crashes decode in different manners, so
this will help the crash-report testing as well as
offer better ways to test firmware failure and
recovery.

kvalo: move the wmi command creation to debug.c, modify
the info print

Signed-off-by: Ben Greear <greearb@candelatech.com>
Signed-off-by: Kalle Valo <kvalo@qca.qualcomm.com>
---
 drivers/net/wireless/ath/ath10k/debug.c |   28 +++++++++++++++++++++++++++-
 1 file changed, 27 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath10k/debug.c b/drivers/net/wireless/ath/ath10k/debug.c
index f948a4d8ee59..c5d01058c2a3 100644
--- a/drivers/net/wireless/ath/ath10k/debug.c
+++ b/drivers/net/wireless/ath/ath10k/debug.c
@@ -565,6 +565,26 @@ static const struct file_operations fops_fw_stats = {
 	.llseek = default_llseek,
 };
 
+/* This is a clean assert crash in firmware. */
+static int ath10k_debug_fw_assert(struct ath10k *ar)
+{
+	struct wmi_vdev_install_key_cmd *cmd;
+	struct sk_buff *skb;
+
+	skb = ath10k_wmi_alloc_skb(ar, sizeof(*cmd) + 16);
+	if (!skb)
+		return -ENOMEM;
+
+	cmd = (struct wmi_vdev_install_key_cmd *)skb->data;
+	memset(cmd, 0, sizeof(*cmd));
+
+	/* big enough number so that firmware asserts */
+	cmd->vdev_id = __cpu_to_le32(0x7ffe);
+
+	return ath10k_wmi_cmd_send(ar, skb,
+				   ar->wmi.cmd->vdev_install_key_cmdid);
+}
+
 static ssize_t ath10k_read_simulate_fw_crash(struct file *file,
 					     char __user *user_buf,
 					     size_t count, loff_t *ppos)
@@ -574,7 +594,10 @@ static ssize_t ath10k_read_simulate_fw_crash(struct file *file,
 			   " WMI_FORCE_FW_HANG_ASSERT to firmware if FW"
 			   " supports that command.\n `hard` - this will send"
 			   " to firmware command with illegal parameters"
-			   " causing firmware crash.\n";
+			   " causing firmware crash.\n"
+			   "`assert` - this will send special illegal parameter"
+			   " to firmware to cause assert failure"
+			   " and crash.\n";
 
 	return simple_read_from_buffer(user_buf, count, ppos, buf, strlen(buf));
 }
@@ -623,6 +646,9 @@ static ssize_t ath10k_write_simulate_fw_crash(struct file *file,
 		 */
 		ret = ath10k_wmi_vdev_set_param(ar, 0x7fff,
 					ar->wmi.vdev_param->rts_threshold, 0);
+	} else if (!strcmp(buf, "assert")) {
+		ath10k_info(ar, "simulating firmware assert crash\n");
+		ret = ath10k_debug_fw_assert(ar);
 	} else {
 		ret = -EINVAL;
 		goto exit;


_______________________________________________
ath10k mailing list
ath10k@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/ath10k

Re: [PATCH v2] ath10k: support firmware crash-by-assert

[Ben Greear]

On 09/10/2014 08:59 AM, Kalle Valo wrote:
> From: Ben Greear <greearb@candelatech.com>
>
> 10.1 firmware does not have an official way to
> cause assert on purpose, but it can be done with
> carefully crafted WMI command.  This is a different
> kind of crash from the 'hard' crash, which is
> a bad memory dereference.
>
> Different crashes decode in different manners, so
> this will help the crash-report testing as well as
> offer better ways to test firmware failure and
> recovery.
>
> kvalo: move the wmi command creation to debug.c, modify
> the info print

This looks fine to me.  I have not tested this version.

Thanks,
Ben

>
> Signed-off-by: Ben Greear <greearb@candelatech.com>
> Signed-off-by: Kalle Valo <kvalo@qca.qualcomm.com>
> ---
>   drivers/net/wireless/ath/ath10k/debug.c |   28 +++++++++++++++++++++++++++-
>   1 file changed, 27 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/net/wireless/ath/ath10k/debug.c b/drivers/net/wireless/ath/ath10k/debug.c
> index f948a4d8ee59..c5d01058c2a3 100644
> --- a/drivers/net/wireless/ath/ath10k/debug.c
> +++ b/drivers/net/wireless/ath/ath10k/debug.c
> @@ -565,6 +565,26 @@ static const struct file_operations fops_fw_stats = {
>   	.llseek = default_llseek,
>   };
>
> +/* This is a clean assert crash in firmware. */
> +static int ath10k_debug_fw_assert(struct ath10k *ar)
> +{
> +	struct wmi_vdev_install_key_cmd *cmd;
> +	struct sk_buff *skb;
> +
> +	skb = ath10k_wmi_alloc_skb(ar, sizeof(*cmd) + 16);
> +	if (!skb)
> +		return -ENOMEM;
> +
> +	cmd = (struct wmi_vdev_install_key_cmd *)skb->data;
> +	memset(cmd, 0, sizeof(*cmd));
> +
> +	/* big enough number so that firmware asserts */
> +	cmd->vdev_id = __cpu_to_le32(0x7ffe);
> +
> +	return ath10k_wmi_cmd_send(ar, skb,
> +				   ar->wmi.cmd->vdev_install_key_cmdid);
> +}
> +
>   static ssize_t ath10k_read_simulate_fw_crash(struct file *file,
>   					     char __user *user_buf,
>   					     size_t count, loff_t *ppos)
> @@ -574,7 +594,10 @@ static ssize_t ath10k_read_simulate_fw_crash(struct file *file,
>   			   " WMI_FORCE_FW_HANG_ASSERT to firmware if FW"
>   			   " supports that command.\n `hard` - this will send"
>   			   " to firmware command with illegal parameters"
> -			   " causing firmware crash.\n";
> +			   " causing firmware crash.\n"
> +			   "`assert` - this will send special illegal parameter"
> +			   " to firmware to cause assert failure"
> +			   " and crash.\n";
>
>   	return simple_read_from_buffer(user_buf, count, ppos, buf, strlen(buf));
>   }
> @@ -623,6 +646,9 @@ static ssize_t ath10k_write_simulate_fw_crash(struct file *file,
>   		 */
>   		ret = ath10k_wmi_vdev_set_param(ar, 0x7fff,
>   					ar->wmi.vdev_param->rts_threshold, 0);
> +	} else if (!strcmp(buf, "assert")) {
> +		ath10k_info(ar, "simulating firmware assert crash\n");
> +		ret = ath10k_debug_fw_assert(ar);
>   	} else {
>   		ret = -EINVAL;
>   		goto exit;
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-wireless" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
>


-- 
Ben Greear <greearb@candelatech.com>
Candela Technologies Inc  http://www.candelatech.com

Re: [PATCH v2] ath10k: support firmware crash-by-assert

[Ben Greear]

On 09/10/2014 08:59 AM, Kalle Valo wrote:
> From: Ben Greear <greearb@candelatech.com>
>
> 10.1 firmware does not have an official way to
> cause assert on purpose, but it can be done with
> carefully crafted WMI command.  This is a different
> kind of crash from the 'hard' crash, which is
> a bad memory dereference.
>
> Different crashes decode in different manners, so
> this will help the crash-report testing as well as
> offer better ways to test firmware failure and
> recovery.
>
> kvalo: move the wmi command creation to debug.c, modify
> the info print

This looks fine to me.  I have not tested this version.

Thanks,
Ben

>
> Signed-off-by: Ben Greear <greearb@candelatech.com>
> Signed-off-by: Kalle Valo <kvalo@qca.qualcomm.com>
> ---
>   drivers/net/wireless/ath/ath10k/debug.c |   28 +++++++++++++++++++++++++++-
>   1 file changed, 27 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/net/wireless/ath/ath10k/debug.c b/drivers/net/wireless/ath/ath10k/debug.c
> index f948a4d8ee59..c5d01058c2a3 100644
> --- a/drivers/net/wireless/ath/ath10k/debug.c
> +++ b/drivers/net/wireless/ath/ath10k/debug.c
> @@ -565,6 +565,26 @@ static const struct file_operations fops_fw_stats = {
>   	.llseek = default_llseek,
>   };
>
> +/* This is a clean assert crash in firmware. */
> +static int ath10k_debug_fw_assert(struct ath10k *ar)
> +{
> +	struct wmi_vdev_install_key_cmd *cmd;
> +	struct sk_buff *skb;
> +
> +	skb = ath10k_wmi_alloc_skb(ar, sizeof(*cmd) + 16);
> +	if (!skb)
> +		return -ENOMEM;
> +
> +	cmd = (struct wmi_vdev_install_key_cmd *)skb->data;
> +	memset(cmd, 0, sizeof(*cmd));
> +
> +	/* big enough number so that firmware asserts */
> +	cmd->vdev_id = __cpu_to_le32(0x7ffe);
> +
> +	return ath10k_wmi_cmd_send(ar, skb,
> +				   ar->wmi.cmd->vdev_install_key_cmdid);
> +}
> +
>   static ssize_t ath10k_read_simulate_fw_crash(struct file *file,
>   					     char __user *user_buf,
>   					     size_t count, loff_t *ppos)
> @@ -574,7 +594,10 @@ static ssize_t ath10k_read_simulate_fw_crash(struct file *file,
>   			   " WMI_FORCE_FW_HANG_ASSERT to firmware if FW"
>   			   " supports that command.\n `hard` - this will send"
>   			   " to firmware command with illegal parameters"
> -			   " causing firmware crash.\n";
> +			   " causing firmware crash.\n"
> +			   "`assert` - this will send special illegal parameter"
> +			   " to firmware to cause assert failure"
> +			   " and crash.\n";
>
>   	return simple_read_from_buffer(user_buf, count, ppos, buf, strlen(buf));
>   }
> @@ -623,6 +646,9 @@ static ssize_t ath10k_write_simulate_fw_crash(struct file *file,
>   		 */
>   		ret = ath10k_wmi_vdev_set_param(ar, 0x7fff,
>   					ar->wmi.vdev_param->rts_threshold, 0);
> +	} else if (!strcmp(buf, "assert")) {
> +		ath10k_info(ar, "simulating firmware assert crash\n");
> +		ret = ath10k_debug_fw_assert(ar);
>   	} else {
>   		ret = -EINVAL;
>   		goto exit;
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-wireless" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
>


-- 
Ben Greear <greearb@candelatech.com>
Candela Technologies Inc  http://www.candelatech.com


_______________________________________________
ath10k mailing list
ath10k@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/ath10k

Re: [PATCH v2] ath10k: support firmware crash-by-assert

[Kalle Valo]

Ben Greear <greearb@candelatech.com> writes:

> On 09/10/2014 08:59 AM, Kalle Valo wrote:
>> From: Ben Greear <greearb@candelatech.com>
>>
>> 10.1 firmware does not have an official way to
>> cause assert on purpose, but it can be done with
>> carefully crafted WMI command.  This is a different
>> kind of crash from the 'hard' crash, which is
>> a bad memory dereference.
>>
>> Different crashes decode in different manners, so
>> this will help the crash-report testing as well as
>> offer better ways to test firmware failure and
>> recovery.
>>
>> kvalo: move the wmi command creation to debug.c, modify
>> the info print
>
> This looks fine to me.  I have not tested this version.

I did test it and seems to work as it should.

-- 
Kalle Valo

Re: [PATCH v2] ath10k: support firmware crash-by-assert

[Kalle Valo]

Ben Greear <greearb@candelatech.com> writes:

> On 09/10/2014 08:59 AM, Kalle Valo wrote:
>> From: Ben Greear <greearb@candelatech.com>
>>
>> 10.1 firmware does not have an official way to
>> cause assert on purpose, but it can be done with
>> carefully crafted WMI command.  This is a different
>> kind of crash from the 'hard' crash, which is
>> a bad memory dereference.
>>
>> Different crashes decode in different manners, so
>> this will help the crash-report testing as well as
>> offer better ways to test firmware failure and
>> recovery.
>>
>> kvalo: move the wmi command creation to debug.c, modify
>> the info print
>
> This looks fine to me.  I have not tested this version.

I did test it and seems to work as it should.

-- 
Kalle Valo

_______________________________________________
ath10k mailing list
ath10k@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/ath10k

Re: [PATCH v2] ath10k: support firmware crash-by-assert

[Kalle Valo]

Kalle Valo <kvalo@qca.qualcomm.com> writes:

> From: Ben Greear <greearb@candelatech.com>
>
> 10.1 firmware does not have an official way to
> cause assert on purpose, but it can be done with
> carefully crafted WMI command.  This is a different
> kind of crash from the 'hard' crash, which is
> a bad memory dereference.
>
> Different crashes decode in different manners, so
> this will help the crash-report testing as well as
> offer better ways to test firmware failure and
> recovery.
>
> kvalo: move the wmi command creation to debug.c, modify
> the info print
>
> Signed-off-by: Ben Greear <greearb@candelatech.com>
> Signed-off-by: Kalle Valo <kvalo@qca.qualcomm.com>

Thanks Ben, applied.

-- 
Kalle Valo

Re: [PATCH v2] ath10k: support firmware crash-by-assert

[Kalle Valo]

Kalle Valo <kvalo@qca.qualcomm.com> writes:

> From: Ben Greear <greearb@candelatech.com>
>
> 10.1 firmware does not have an official way to
> cause assert on purpose, but it can be done with
> carefully crafted WMI command.  This is a different
> kind of crash from the 'hard' crash, which is
> a bad memory dereference.
>
> Different crashes decode in different manners, so
> this will help the crash-report testing as well as
> offer better ways to test firmware failure and
> recovery.
>
> kvalo: move the wmi command creation to debug.c, modify
> the info print
>
> Signed-off-by: Ben Greear <greearb@candelatech.com>
> Signed-off-by: Kalle Valo <kvalo@qca.qualcomm.com>

Thanks Ben, applied.

-- 
Kalle Valo

_______________________________________________
ath10k mailing list
ath10k@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/ath10k