tg3: Fix RSS ring refill race condition

The RSS feature in tg3 hardware has only one rx producer ring for all
RSS rings.  NAPI vector 1 is special and handles the refilling of the
rx producer ring on behalf of all RSS rings.  There is a race condition
between these RSS NAPIs and the NAPI[1].  If NAPI[1] finishes checking
for refill and then another RSS ring empties the rx producer ring
before NAPI[1] exits NAPI, the chip will be completely out of SKBs in
the rx producer ring.

We fix this by adding a flag tp->rx_refill and rely on napi_schedule()/
napi_complete() to help synchronize it to close the race condition.

Update driver version to 3.123.

Signed-off-by: Michael Chan <mchan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index b065746..7b71387 100644 (file)
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -89,10 +89,10 @@ static inline void _tg3_flag_clear(enum TG3_FLAGS flag, unsigned long *bits)
 
 #define DRV_MODULE_NAME                "tg3"
 #define TG3_MAJ_NUM                    3
-#define TG3_MIN_NUM                    122
+#define TG3_MIN_NUM                    123
 #define DRV_MODULE_VERSION     \
        __stringify(TG3_MAJ_NUM) "." __stringify(TG3_MIN_NUM)
-#define DRV_MODULE_RELDATE     "December 7, 2011"
+#define DRV_MODULE_RELDATE     "March 21, 2012"
 
 #define RESET_KIND_SHUTDOWN    0
 #define RESET_KIND_INIT                1
@@ -5953,8 +5953,10 @@ next_pkt_nopost:
                tpr->rx_std_prod_idx = std_prod_idx & tp->rx_std_ring_mask;
                tpr->rx_jmb_prod_idx = jmb_prod_idx & tp->rx_jmb_ring_mask;
 
-               if (tnapi != &tp->napi[1])
+               if (tnapi != &tp->napi[1]) {
+                       tp->rx_refill = true;
                        napi_schedule(&tp->napi[1].napi);
+               }
        }
 
        return received;
@@ -6134,6 +6136,7 @@ static int tg3_poll_work(struct tg3_napi *tnapi, int work_done, int budget)
                u32 std_prod_idx = dpr->rx_std_prod_idx;
                u32 jmb_prod_idx = dpr->rx_jmb_prod_idx;
 
+               tp->rx_refill = false;
                for (i = 1; i < tp->irq_cnt; i++)
                        err |= tg3_rx_prodring_xfer(tp, dpr,
                                                    &tp->napi[i].prodring);
@@ -6197,9 +6200,25 @@ static int tg3_poll_msix(struct napi_struct *napi, int budget)
                /* check for RX/TX work to do */
                if (likely(sblk->idx[0].tx_consumer == tnapi->tx_cons &&
                           *(tnapi->rx_rcb_prod_idx) == tnapi->rx_rcb_ptr)) {
+
+                       /* This test here is not race free, but will reduce
+                        * the number of interrupts by looping again.
+                        */
+                       if (tnapi == &tp->napi[1] && tp->rx_refill)
+                               continue;
+
                        napi_complete(napi);
                        /* Reenable interrupts. */
                        tw32_mailbox(tnapi->int_mbox, tnapi->last_tag << 24);
+
+                       /* This test here is synchronized by napi_schedule()
+                        * and napi_complete() to close the race condition.
+                        */
+                       if (unlikely(tnapi == &tp->napi[1] && tp->rx_refill)) {
+                               tw32(HOSTCC_MODE, tp->coalesce_mode |
+                                                 HOSTCC_MODE_ENABLE |
+                                                 tnapi->coal_now);
+                       }
                        mmiowb();
                        break;
                }

diff --git a/drivers/net/ethernet/broadcom/tg3.h b/drivers/net/ethernet/broadcom/tg3.h
index 66bcfca..93865f8 100644 (file)
--- a/drivers/net/ethernet/broadcom/tg3.h
+++ b/drivers/net/ethernet/broadcom/tg3.h
@@ -3007,6 +3007,7 @@ struct tg3 {
        u32                             rx_std_max_post;
        u32                             rx_offset;
        u32                             rx_pkt_map_sz;
+       bool                            rx_refill;
 
 
        /* begin "everything else" cacheline(s) section */