2013-05-18 02:54:28

by jonghwan Choi

Subject: [PATCH 3.9-stable] NTB: memcpy lockup workaround

From: Jon Mason <[email protected]>

This patch looks like it should be in the 3.9-stable tree, should we apply
it?

------------------

From: "Jon Mason <[email protected]>"

commit c336acd3331dcc191a97dbc66a557d47741657c7 upstream

The system will appear to lockup for long periods of time due to the NTB
driver spending too much time in memcpy. Avoid this by reducing the
number of packets that can be serviced on a given interrupt.

Cc: <[email protected]> # 3.9.x: ad3e2751: ntb: off by one
Cc: <[email protected]> # 3.9.x: cc0f868d: NTB: fix pointer math
Cc: <[email protected]> # 3.9.x: 113fc505: NTB: Handle 64bit BAR
Cc: <[email protected]> # 3.9.x: b77b2637: NTB: Link toggle memory
Cc: <[email protected]> # 3.9.x: 90f9e934: NTB: reset tx_index on
Cc: <[email protected]> # 3.9.x: c9d534c8: NTB: Correctly handle receive
Signed-off-by: Jon Mason <[email protected]>
Signed-off-by: Jonghwan Choi <[email protected]>
---
drivers/ntb/ntb_transport.c | 11 ++++++++---
1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/drivers/ntb/ntb_transport.c b/drivers/ntb/ntb_transport.c
index a288a26..0f66daa 100644
--- a/drivers/ntb/ntb_transport.c
+++ b/drivers/ntb/ntb_transport.c
@@ -1034,11 +1034,16 @@ out:
static void ntb_transport_rx(unsigned long data)
{
struct ntb_transport_qp *qp = (struct ntb_transport_qp *)data;
- int rc;
+ int rc, i;

- do {
+ /* Limit the number of packets processed in a single interrupt to
+ * provide fairness to others
+ */
+ for (i = 0; i < qp->rx_max_entry; i++) {
rc = ntb_process_rxc(qp);
- } while (!rc);
+ if (rc)
+ break;
+ }
}

static void ntb_transport_rxc_db(void *data, int db_num)
--
1.8.1.2

2013-05-18 14:48:51

by Jon Mason

Subject: Re: [PATCH 3.9-stable] NTB: memcpy lockup workaround

On Sat, May 18, 2013 at 11:52:17AM +0900, Jonghwan Choi wrote:
> From: Jon Mason <[email protected]>
>
> This patch looks like it should be in the 3.9-stable tree, should we apply
> it?

Yes, thanks.

>
> ------------------
>
> From: "Jon Mason <[email protected]>"
>
> commit c336acd3331dcc191a97dbc66a557d47741657c7 upstream
>
> The system will appear to lockup for long periods of time due to the NTB
> driver spending too much time in memcpy. Avoid this by reducing the
> number of packets that can be serviced on a given interrupt.
>
> Cc: <[email protected]> # 3.9.x: ad3e2751: ntb: off by one
> Cc: <[email protected]> # 3.9.x: cc0f868d: NTB: fix pointer math
> Cc: <[email protected]> # 3.9.x: 113fc505: NTB: Handle 64bit BAR
> Cc: <[email protected]> # 3.9.x: b77b2637: NTB: Link toggle memory
> Cc: <[email protected]> # 3.9.x: 90f9e934: NTB: reset tx_index on
> Cc: <[email protected]> # 3.9.x: c9d534c8: NTB: Correctly handle receive
> Signed-off-by: Jon Mason <[email protected]>
> Signed-off-by: Jonghwan Choi <[email protected]>
> ---
> drivers/ntb/ntb_transport.c | 11 ++++++++---
> 1 file changed, 8 insertions(+), 3 deletions(-)
>
> diff --git a/drivers/ntb/ntb_transport.c b/drivers/ntb/ntb_transport.c
> index a288a26..0f66daa 100644
> --- a/drivers/ntb/ntb_transport.c
> +++ b/drivers/ntb/ntb_transport.c
> @@ -1034,11 +1034,16 @@ out:
> static void ntb_transport_rx(unsigned long data)
> {
> struct ntb_transport_qp *qp = (struct ntb_transport_qp *)data;
> - int rc;
> + int rc, i;
>
> - do {
> + /* Limit the number of packets processed in a single interrupt to
> + * provide fairness to others
> + */
> + for (i = 0; i < qp->rx_max_entry; i++) {
> rc = ntb_process_rxc(qp);
> - } while (!rc);
> + if (rc)
> + break;
> + }
> }
>
> static void ntb_transport_rxc_db(void *data, int db_num)
> --
> 1.8.1.2
>