summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorDavid S. Miller <davem@davemloft.net>2014-03-13 14:36:18 -0400
committerDavid S. Miller <davem@davemloft.net>2014-03-13 14:36:18 -0400
commitbc0a9a4b0d6b6695a9b365c9da6ec4b6d4f4b3c2 (patch)
treea1559c68612d6f4d031f5fa3894e4760fd82f339
parent433131ba03c511a84e1fda5669c70cf8b44702e1 (diff)
parentca71de6ba7c18a3a1576e04f7ed8d8508ceba4c9 (diff)
Merge branch 'cxgb4-next'
Hariprasad Shenai says: ==================== Misc. fixes for cxgb4 This patch series provides miscelleneous fixes for Chelsio T4/T5 adapters cxgb4 driver related to SGE and MTU. Also fixes regression in LSO calcuation path. ("cxgb4: Calculate len properly for LSO path") The patches series is created against David Miller's 'net-next' tree. And includes patches on cxgb4 driver. We would like to request this patch series to get merged via David Miller's 'net-next' tree. We have included all the maintainers of respective drivers. Kindly review the change and let us know in case of any review comments. ==================== Signed-off-by: David S. Miller <davem@davemloft.net>
-rw-r--r--drivers/net/ethernet/chelsio/cxgb4/cxgb4.h10
-rw-r--r--drivers/net/ethernet/chelsio/cxgb4/sge.c122
-rw-r--r--drivers/net/ethernet/chelsio/cxgb4/t4_hw.c106
-rw-r--r--drivers/net/ethernet/chelsio/cxgb4/t4_regs.h9
4 files changed, 219 insertions, 28 deletions
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
index 944f2cbc1795..50abe1d61287 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
@@ -556,8 +556,13 @@ struct sge {
u32 pktshift; /* padding between CPL & packet data */
u32 fl_align; /* response queue message alignment */
u32 fl_starve_thres; /* Free List starvation threshold */
- unsigned int starve_thres;
- u8 idma_state[2];
+
+ /* State variables for detecting an SGE Ingress DMA hang */
+ unsigned int idma_1s_thresh;/* SGE same State Counter 1s threshold */
+ unsigned int idma_stalled[2];/* SGE synthesized stalled timers in HZ */
+ unsigned int idma_state[2]; /* SGE IDMA Hang detect state */
+ unsigned int idma_qid[2]; /* SGE IDMA Hung Ingress Queue ID */
+
unsigned int egr_start;
unsigned int ingr_start;
void *egr_map[MAX_EGRQ]; /* qid->queue egress queue map */
@@ -1032,4 +1037,5 @@ void t4_db_dropped(struct adapter *adapter);
int t4_mem_win_read_len(struct adapter *adap, u32 addr, __be32 *data, int len);
int t4_fwaddrspace_write(struct adapter *adap, unsigned int mbox,
u32 addr, u32 val);
+void t4_sge_decode_idma_state(struct adapter *adapter, int state);
#endif /* __CXGB4_H__ */
diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c
index af76b25bb606..46429f9d0592 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c
@@ -93,6 +93,16 @@
*/
#define TX_QCHECK_PERIOD (HZ / 2)
+/* SGE Hung Ingress DMA Threshold Warning time (in Hz) and Warning Repeat Rate
+ * (in RX_QCHECK_PERIOD multiples). If we find one of the SGE Ingress DMA
+ * State Machines in the same state for this amount of time (in HZ) then we'll
+ * issue a warning about a potential hang. We'll repeat the warning as the
+ * SGE Ingress DMA Channel appears to be hung every N RX_QCHECK_PERIODs till
+ * the situation clears. If the situation clears, we'll note that as well.
+ */
+#define SGE_IDMA_WARN_THRESH (1 * HZ)
+#define SGE_IDMA_WARN_REPEAT (20 * RX_QCHECK_PERIOD)
+
/*
* Max number of Tx descriptors to be reclaimed by the Tx timer.
*/
@@ -1041,7 +1051,6 @@ out_free: dev_kfree_skb(skb);
end = (u64 *)wr + flits;
len = immediate ? skb->len : 0;
- len += sizeof(*cpl);
ssi = skb_shinfo(skb);
if (ssi->gso_size) {
struct cpl_tx_pkt_lso *lso = (void *)wr;
@@ -1069,6 +1078,7 @@ out_free: dev_kfree_skb(skb);
q->tso++;
q->tx_cso += ssi->gso_segs;
} else {
+ len += sizeof(*cpl);
wr->op_immdlen = htonl(FW_WR_OP(FW_ETH_TX_PKT_WR) |
FW_WR_IMMDLEN(len));
cpl = (void *)(wr + 1);
@@ -2008,7 +2018,7 @@ irq_handler_t t4_intr_handler(struct adapter *adap)
static void sge_rx_timer_cb(unsigned long data)
{
unsigned long m;
- unsigned int i, cnt[2];
+ unsigned int i, idma_same_state_cnt[2];
struct adapter *adap = (struct adapter *)data;
struct sge *s = &adap->sge;
@@ -2031,21 +2041,64 @@ static void sge_rx_timer_cb(unsigned long data)
}
t4_write_reg(adap, SGE_DEBUG_INDEX, 13);
- cnt[0] = t4_read_reg(adap, SGE_DEBUG_DATA_HIGH);
- cnt[1] = t4_read_reg(adap, SGE_DEBUG_DATA_LOW);
-
- for (i = 0; i < 2; i++)
- if (cnt[i] >= s->starve_thres) {
- if (s->idma_state[i] || cnt[i] == 0xffffffff)
- continue;
- s->idma_state[i] = 1;
- t4_write_reg(adap, SGE_DEBUG_INDEX, 11);
- m = t4_read_reg(adap, SGE_DEBUG_DATA_LOW) >> (i * 16);
- dev_warn(adap->pdev_dev,
- "SGE idma%u starvation detected for "
- "queue %lu\n", i, m & 0xffff);
- } else if (s->idma_state[i])
- s->idma_state[i] = 0;
+ idma_same_state_cnt[0] = t4_read_reg(adap, SGE_DEBUG_DATA_HIGH);
+ idma_same_state_cnt[1] = t4_read_reg(adap, SGE_DEBUG_DATA_LOW);
+
+ for (i = 0; i < 2; i++) {
+ u32 debug0, debug11;
+
+ /* If the Ingress DMA Same State Counter ("timer") is less
+ * than 1s, then we can reset our synthesized Stall Timer and
+ * continue. If we have previously emitted warnings about a
+ * potential stalled Ingress Queue, issue a note indicating
+ * that the Ingress Queue has resumed forward progress.
+ */
+ if (idma_same_state_cnt[i] < s->idma_1s_thresh) {
+ if (s->idma_stalled[i] >= SGE_IDMA_WARN_THRESH)
+ CH_WARN(adap, "SGE idma%d, queue%u,resumed after %d sec\n",
+ i, s->idma_qid[i],
+ s->idma_stalled[i]/HZ);
+ s->idma_stalled[i] = 0;
+ continue;
+ }
+
+ /* Synthesize an SGE Ingress DMA Same State Timer in the Hz
+ * domain. The first time we get here it'll be because we
+ * passed the 1s Threshold; each additional time it'll be
+ * because the RX Timer Callback is being fired on its regular
+ * schedule.
+ *
+ * If the stall is below our Potential Hung Ingress Queue
+ * Warning Threshold, continue.
+ */
+ if (s->idma_stalled[i] == 0)
+ s->idma_stalled[i] = HZ;
+ else
+ s->idma_stalled[i] += RX_QCHECK_PERIOD;
+
+ if (s->idma_stalled[i] < SGE_IDMA_WARN_THRESH)
+ continue;
+
+ /* We'll issue a warning every SGE_IDMA_WARN_REPEAT Hz */
+ if (((s->idma_stalled[i] - HZ) % SGE_IDMA_WARN_REPEAT) != 0)
+ continue;
+
+ /* Read and save the SGE IDMA State and Queue ID information.
+ * We do this every time in case it changes across time ...
+ */
+ t4_write_reg(adap, SGE_DEBUG_INDEX, 0);
+ debug0 = t4_read_reg(adap, SGE_DEBUG_DATA_LOW);
+ s->idma_state[i] = (debug0 >> (i * 9)) & 0x3f;
+
+ t4_write_reg(adap, SGE_DEBUG_INDEX, 11);
+ debug11 = t4_read_reg(adap, SGE_DEBUG_DATA_LOW);
+ s->idma_qid[i] = (debug11 >> (i * 16)) & 0xffff;
+
+ CH_WARN(adap, "SGE idma%u, queue%u, maybe stuck state%u %dsecs (debug0=%#x, debug11=%#x)\n",
+ i, s->idma_qid[i], s->idma_state[i],
+ s->idma_stalled[i]/HZ, debug0, debug11);
+ t4_sge_decode_idma_state(adap, s->idma_state[i]);
+ }
mod_timer(&s->rx_timer, jiffies + RX_QCHECK_PERIOD);
}
@@ -2596,11 +2649,19 @@ static int t4_sge_init_soft(struct adapter *adap)
fl_small_mtu = READ_FL_BUF(RX_SMALL_MTU_BUF);
fl_large_mtu = READ_FL_BUF(RX_LARGE_MTU_BUF);
+ /* We only bother using the Large Page logic if the Large Page Buffer
+ * is larger than our Page Size Buffer.
+ */
+ if (fl_large_pg <= fl_small_pg)
+ fl_large_pg = 0;
+
#undef READ_FL_BUF
+ /* The Page Size Buffer must be exactly equal to our Page Size and the
+ * Large Page Size Buffer should be 0 (per above) or a power of 2.
+ */
if (fl_small_pg != PAGE_SIZE ||
- (fl_large_pg != 0 && (fl_large_pg < fl_small_pg ||
- (fl_large_pg & (fl_large_pg-1)) != 0))) {
+ (fl_large_pg & (fl_large_pg-1)) != 0) {
dev_err(adap->pdev_dev, "bad SGE FL page buffer sizes [%d, %d]\n",
fl_small_pg, fl_large_pg);
return -EINVAL;
@@ -2715,8 +2776,8 @@ static int t4_sge_init_hard(struct adapter *adap)
int t4_sge_init(struct adapter *adap)
{
struct sge *s = &adap->sge;
- u32 sge_control;
- int ret;
+ u32 sge_control, sge_conm_ctrl;
+ int ret, egress_threshold;
/*
* Ingress Padding Boundary and Egress Status Page Size are set up by
@@ -2741,15 +2802,24 @@ int t4_sge_init(struct adapter *adap)
* SGE's Egress Congestion Threshold. If it isn't, then we can get
* stuck waiting for new packets while the SGE is waiting for us to
* give it more Free List entries. (Note that the SGE's Egress
- * Congestion Threshold is in units of 2 Free List pointers.)
+ * Congestion Threshold is in units of 2 Free List pointers.) For T4,
+ * there was only a single field to control this. For T5 there's the
+ * original field which now only applies to Unpacked Mode Free List
+ * buffers and a new field which only applies to Packed Mode Free List
+ * buffers.
*/
- s->fl_starve_thres
- = EGRTHRESHOLD_GET(t4_read_reg(adap, SGE_CONM_CTRL))*2 + 1;
+ sge_conm_ctrl = t4_read_reg(adap, SGE_CONM_CTRL);
+ if (is_t4(adap->params.chip))
+ egress_threshold = EGRTHRESHOLD_GET(sge_conm_ctrl);
+ else
+ egress_threshold = EGRTHRESHOLDPACKING_GET(sge_conm_ctrl);
+ s->fl_starve_thres = 2*egress_threshold + 1;
setup_timer(&s->rx_timer, sge_rx_timer_cb, (unsigned long)adap);
setup_timer(&s->tx_timer, sge_tx_timer_cb, (unsigned long)adap);
- s->starve_thres = core_ticks_per_usec(adap) * 1000000; /* 1 s */
- s->idma_state[0] = s->idma_state[1] = 0;
+ s->idma_1s_thresh = core_ticks_per_usec(adap) * 1000000; /* 1 s */
+ s->idma_stalled[0] = 0;
+ s->idma_stalled[1] = 0;
spin_lock_init(&s->intrq_lock);
return 0;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
index d3c2a516fa88..fb2fe65903c2 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
@@ -2597,6 +2597,112 @@ int t4_mdio_wr(struct adapter *adap, unsigned int mbox, unsigned int phy_addr,
}
/**
+ * t4_sge_decode_idma_state - decode the idma state
+ * @adap: the adapter
+ * @state: the state idma is stuck in
+ */
+void t4_sge_decode_idma_state(struct adapter *adapter, int state)
+{
+ static const char * const t4_decode[] = {
+ "IDMA_IDLE",
+ "IDMA_PUSH_MORE_CPL_FIFO",
+ "IDMA_PUSH_CPL_MSG_HEADER_TO_FIFO",
+ "Not used",
+ "IDMA_PHYSADDR_SEND_PCIEHDR",
+ "IDMA_PHYSADDR_SEND_PAYLOAD_FIRST",
+ "IDMA_PHYSADDR_SEND_PAYLOAD",
+ "IDMA_SEND_FIFO_TO_IMSG",
+ "IDMA_FL_REQ_DATA_FL_PREP",
+ "IDMA_FL_REQ_DATA_FL",
+ "IDMA_FL_DROP",
+ "IDMA_FL_H_REQ_HEADER_FL",
+ "IDMA_FL_H_SEND_PCIEHDR",
+ "IDMA_FL_H_PUSH_CPL_FIFO",
+ "IDMA_FL_H_SEND_CPL",
+ "IDMA_FL_H_SEND_IP_HDR_FIRST",
+ "IDMA_FL_H_SEND_IP_HDR",
+ "IDMA_FL_H_REQ_NEXT_HEADER_FL",
+ "IDMA_FL_H_SEND_NEXT_PCIEHDR",
+ "IDMA_FL_H_SEND_IP_HDR_PADDING",
+ "IDMA_FL_D_SEND_PCIEHDR",
+ "IDMA_FL_D_SEND_CPL_AND_IP_HDR",
+ "IDMA_FL_D_REQ_NEXT_DATA_FL",
+ "IDMA_FL_SEND_PCIEHDR",
+ "IDMA_FL_PUSH_CPL_FIFO",
+ "IDMA_FL_SEND_CPL",
+ "IDMA_FL_SEND_PAYLOAD_FIRST",
+ "IDMA_FL_SEND_PAYLOAD",
+ "IDMA_FL_REQ_NEXT_DATA_FL",
+ "IDMA_FL_SEND_NEXT_PCIEHDR",
+ "IDMA_FL_SEND_PADDING",
+ "IDMA_FL_SEND_COMPLETION_TO_IMSG",
+ "IDMA_FL_SEND_FIFO_TO_IMSG",
+ "IDMA_FL_REQ_DATAFL_DONE",
+ "IDMA_FL_REQ_HEADERFL_DONE",
+ };
+ static const char * const t5_decode[] = {
+ "IDMA_IDLE",
+ "IDMA_ALMOST_IDLE",
+ "IDMA_PUSH_MORE_CPL_FIFO",
+ "IDMA_PUSH_CPL_MSG_HEADER_TO_FIFO",
+ "IDMA_SGEFLRFLUSH_SEND_PCIEHDR",
+ "IDMA_PHYSADDR_SEND_PCIEHDR",
+ "IDMA_PHYSADDR_SEND_PAYLOAD_FIRST",
+ "IDMA_PHYSADDR_SEND_PAYLOAD",
+ "IDMA_SEND_FIFO_TO_IMSG",
+ "IDMA_FL_REQ_DATA_FL",
+ "IDMA_FL_DROP",
+ "IDMA_FL_DROP_SEND_INC",
+ "IDMA_FL_H_REQ_HEADER_FL",
+ "IDMA_FL_H_SEND_PCIEHDR",
+ "IDMA_FL_H_PUSH_CPL_FIFO",
+ "IDMA_FL_H_SEND_CPL",
+ "IDMA_FL_H_SEND_IP_HDR_FIRST",
+ "IDMA_FL_H_SEND_IP_HDR",
+ "IDMA_FL_H_REQ_NEXT_HEADER_FL",
+ "IDMA_FL_H_SEND_NEXT_PCIEHDR",
+ "IDMA_FL_H_SEND_IP_HDR_PADDING",
+ "IDMA_FL_D_SEND_PCIEHDR",
+ "IDMA_FL_D_SEND_CPL_AND_IP_HDR",
+ "IDMA_FL_D_REQ_NEXT_DATA_FL",
+ "IDMA_FL_SEND_PCIEHDR",
+ "IDMA_FL_PUSH_CPL_FIFO",
+ "IDMA_FL_SEND_CPL",
+ "IDMA_FL_SEND_PAYLOAD_FIRST",
+ "IDMA_FL_SEND_PAYLOAD",
+ "IDMA_FL_REQ_NEXT_DATA_FL",
+ "IDMA_FL_SEND_NEXT_PCIEHDR",
+ "IDMA_FL_SEND_PADDING",
+ "IDMA_FL_SEND_COMPLETION_TO_IMSG",
+ };
+ static const u32 sge_regs[] = {
+ SGE_DEBUG_DATA_LOW_INDEX_2,
+ SGE_DEBUG_DATA_LOW_INDEX_3,
+ SGE_DEBUG_DATA_HIGH_INDEX_10,
+ };
+ const char **sge_idma_decode;
+ int sge_idma_decode_nstates;
+ int i;
+
+ if (is_t4(adapter->params.chip)) {
+ sge_idma_decode = (const char **)t4_decode;
+ sge_idma_decode_nstates = ARRAY_SIZE(t4_decode);
+ } else {
+ sge_idma_decode = (const char **)t5_decode;
+ sge_idma_decode_nstates = ARRAY_SIZE(t5_decode);
+ }
+
+ if (state < sge_idma_decode_nstates)
+ CH_WARN(adapter, "idma state %s\n", sge_idma_decode[state]);
+ else
+ CH_WARN(adapter, "idma state %d unknown\n", state);
+
+ for (i = 0; i < ARRAY_SIZE(sge_regs); i++)
+ CH_WARN(adapter, "SGE register %#x value %#x\n",
+ sge_regs[i], t4_read_reg(adapter, sge_regs[i]));
+}
+
+/**
* t4_fw_hello - establish communication with FW
* @adap: the adapter
* @mbox: mailbox to use for the FW command
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
index 4082522d8140..225ad8a5722d 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
@@ -230,6 +230,12 @@
#define EGRTHRESHOLD(x) ((x) << EGRTHRESHOLDshift)
#define EGRTHRESHOLD_GET(x) (((x) & EGRTHRESHOLD_MASK) >> EGRTHRESHOLDshift)
+#define EGRTHRESHOLDPACKING_MASK 0x3fU
+#define EGRTHRESHOLDPACKING_SHIFT 14
+#define EGRTHRESHOLDPACKING(x) ((x) << EGRTHRESHOLDPACKING_SHIFT)
+#define EGRTHRESHOLDPACKING_GET(x) (((x) >> EGRTHRESHOLDPACKING_SHIFT) & \
+ EGRTHRESHOLDPACKING_MASK)
+
#define SGE_DBFIFO_STATUS 0x10a4
#define HP_INT_THRESH_SHIFT 28
#define HP_INT_THRESH_MASK 0xfU
@@ -278,6 +284,9 @@
#define SGE_DEBUG_INDEX 0x10cc
#define SGE_DEBUG_DATA_HIGH 0x10d0
#define SGE_DEBUG_DATA_LOW 0x10d4
+#define SGE_DEBUG_DATA_LOW_INDEX_2 0x12c8
+#define SGE_DEBUG_DATA_LOW_INDEX_3 0x12cc
+#define SGE_DEBUG_DATA_HIGH_INDEX_10 0x12a8
#define SGE_INGRESS_QUEUES_PER_PAGE_PF 0x10f4
#define S_HP_INT_THRESH 28