cxgb4/iw_cxgb4: work request logging feature

This commit enhances the iwarp driver to optionally keep a log of rdma
work request timining data for kernel mode QPs.  If iw_cxgb4 module option
c4iw_wr_log is set to non-zero, each work request is tracked and timing
data maintained in a rolling log that is 4096 entries deep by default.
Module option c4iw_wr_log_size_order allows specifing a log2 size to use
instead of the default order of 12 (4096 entries). Both module options
are read-only and must be passed in at module load time to set them. IE:

modprobe iw_cxgb4 c4iw_wr_log=1 c4iw_wr_log_size_order=10

The timing data is viewable via the iw_cxgb4 debugfs file "wr_log".
Writing anything to this file will clear all the timing data.
Data tracked includes:

- The host time when the work request was posted, just before ringing
the doorbell.  The host time when the completion was polled by the
application.  This is also the time the log entry is created.  The delta
of these two times is the amount of time took processing the work request.

- The qid of the EQ used to post the work request.

- The work request opcode.

- The cqe wr_id field.  For sq completions requests this is the swsqe
index.  For recv completions this is the MSN of the ingress SEND.
This value can be used to match log entries from this log with firmware
flowc event entries.

- The sge timestamp value just before ringing the doorbell when
posting,  the sge timestamp value just after polling the completion,
and CQE.timestamp field from the completion itself.  With these three
timestamps we can track the latency from post to poll, and the amount
of time the completion resided in the CQ before being reaped by the
application.  With debug firmware, the sge timestamp is also logged by
firmware in its flowc history so that we can compute the latency from
posting the work request until the firmware sees it.

Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Hariprasad Shenai <hariprasad@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 22 insertions, 0 deletions

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index ba7d13de5e8..9c7e4f0a768 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -3898,6 +3898,19 @@ err:
 }
 EXPORT_SYMBOL(cxgb4_read_tpte);
 
+u64 cxgb4_read_sge_timestamp(struct net_device *dev)
+{
+	u32 hi, lo;
+	struct adapter *adap;
+
+	adap = netdev2adap(dev);
+	lo = t4_read_reg(adap, SGE_TIMESTAMP_LO);
+	hi = GET_TSVAL(t4_read_reg(adap, SGE_TIMESTAMP_HI));
+
+	return ((u64)hi << 32) | (u64)lo;
+}
+EXPORT_SYMBOL(cxgb4_read_sge_timestamp);
+
 static struct pci_driver cxgb4_driver;
 
 static void check_neigh_update(struct neighbour *neigh)
@@ -4161,6 +4174,7 @@ static void uld_attach(struct adapter *adap, unsigned int uld)
 	lli.wr_cred = adap->params.ofldq_wr_cred;
 	lli.adapter_type = adap->params.chip;
 	lli.iscsi_iolen = MAXRXDATA_GET(t4_read_reg(adap, TP_PARA_REG2));
+	lli.cclk_ps = 1000000000 / adap->params.vpd.cclk;
 	lli.udb_density = 1 << QUEUESPERPAGEPF0_GET(
 			t4_read_reg(adap, SGE_EGRESS_QUEUES_PER_PAGE_PF) >>
 			(adap->fn * 4));
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
index c7170d68bf6..79a84de1d20 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
@@ -243,6 +243,7 @@ struct cxgb4_lld_info {
 	unsigned char fw_api_ver;            /* FW API version */
 	unsigned int fw_vers;                /* FW version */
 	unsigned int iscsi_iolen;            /* iSCSI max I/O length */
+	unsigned int cclk_ps;                /* Core clock period in psec */
 	unsigned short udb_density;          /* # of user DB/page */
 	unsigned short ucq_density;          /* # of user CQs/page */
 	unsigned short filt_mode;            /* filter optional components */
@@ -297,5 +298,6 @@ int cxgb4_flush_eq_cache(struct net_device *dev);
 void cxgb4_disable_db_coalescing(struct net_device *dev);
 void cxgb4_enable_db_coalescing(struct net_device *dev);
 int cxgb4_read_tpte(struct net_device *dev, u32 stag, __be32 *tpte);
+u64 cxgb4_read_sge_timestamp(struct net_device *dev);
 
 #endif  /* !__CXGB4_OFLD_H */
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
index ae7776471ce..3b244abbf90 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
@@ -251,6 +251,12 @@
 #define V_NOCOALESCE(x) ((x) << S_NOCOALESCE)
 #define F_NOCOALESCE    V_NOCOALESCE(1U)
 
+#define SGE_TIMESTAMP_LO 0x1098
+#define SGE_TIMESTAMP_HI 0x109c
+#define S_TSVAL    0
+#define M_TSVAL    0xfffffffU
+#define GET_TSVAL(x) (((x) >> S_TSVAL) & M_TSVAL)
+
 #define SGE_TIMER_VALUE_0_AND_1 0x10b8
 #define  TIMERVALUE0_MASK   0xffff0000U
 #define  TIMERVALUE0_SHIFT  16