| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <1394188409-9739-4-git-send-email-hariprasad@chelsio.com>
Date: Fri, 7 Mar 2014 16:03:00 +0530
From: Hariprasad Shenai <hariprasad@...lsio.com>
To: netdev@...r.kernel.org, linux-rdma@...r.kernel.org
Cc: davem@...emloft.net, roland@...estorage.com, santosh@...lsio.com,
dm@...lsio.com, kumaras@...lsio.com, swise@...ngridcomputing.com,
leedom@...lsio.com, nirranjan@...lsio.com, hariprasad@...lsio.com
Subject: [PATCHv4 net-next 03/32] cxgb4: Rectify emitting messages about SGE Ingress DMA channels being potentially stuck
From: Kumar Sanghvi <kumaras@...lsio.com>
Based on original work by Casey Leedom <leedom@...lsio.com>
Signed-off-by: Kumar Sanghvi <kumaras@...lsio.com>
---
drivers/net/ethernet/chelsio/cxgb4/cxgb4.h | 9 ++-
drivers/net/ethernet/chelsio/cxgb4/sge.c | 90 ++++++++++++++++++++++++------
2 files changed, 79 insertions(+), 20 deletions(-)
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
index 509c976..50abe1d 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 */
diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c
index 3a2ecd8..054bb03 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.
*/
@@ -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);
}
@@ -2756,8 +2809,9 @@ int t4_sge_init(struct adapter *adap)
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;
--
1.8.4
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists