Commit Graph

166 Commits

Author SHA1 Message Date
Navdeep Parhar
6e22f9f3da Display SGE tunables in the sysctl tree.
dev.t5nex.0.fl_pktshift: payload DMA offset in rx buffer (bytes)
dev.t5nex.0.fl_pad: payload pad boundary (bytes)
dev.t5nex.0.spg_len: status page size (bytes)
dev.t5nex.0.cong_drop: congestion drop setting

Discussed with:	scottl
2013-07-31 05:12:51 +00:00
Navdeep Parhar
2393220538 Display a string instead of a numeric code in the linkdnrc sysctl.
Submitted by:	gnn@
2013-07-27 07:43:43 +00:00
Navdeep Parhar
716c9e1b58 Expand the list of devices claimed by cxgbe(4). 2013-07-27 00:53:07 +00:00
Navdeep Parhar
caf20efcde Add support for packet-sniffing tracers to cxgbe(4). This works with
all T4 and T5 based cards and is useful for analyzing TSO, LRO, TOE, and
for general purpose monitoring without tapping any cxgbe or cxl ifnet
directly.

Tracers on the T4/T5 chips provide access to Ethernet frames exactly as
they were received from or transmitted on the wire.  On transmit, a
tracer will capture a frame after TSO segmentation, hw VLAN tag
insertion, hw L3 & L4 checksum insertion, etc.  It will also capture
frames generated by the TCP offload engine (TOE traffic is normally
invisible to the kernel).  On receive, a tracer will capture a frame
before hw VLAN extraction, runt filtering, other badness filtering,
before the steering/drop/L2-rewrite filters or the TOE have had a go at
it, and of course before sw LRO in the driver.

There are 4 tracers on a chip.  A tracer can trace only in one direction
(tx or rx).  For now cxgbetool will set up tracers to capture the first
128B of every transmitted or received frame on a given port.  This is a
small subset of what the hardware can do.  A pseudo ifnet with the same
name as the nexus driver (t4nex0 or t5nex0) will be created for tracing.
The data delivered to this ifnet is an additional copy made inside the
chip.  Normal delivery to cxgbe<n> or cxl<n> will be made as usual.

/* watch cxl0, which is the first port hanging off t5nex0. */
# cxgbetool t5nex0 tracer 0 tx0  (watch what cxl0 is transmitting)
# cxgbetool t5nex0 tracer 1 rx0  (watch what cxl0 is receiving)
# cxgbetool t5nex0 tracer list
# tcpdump -i t5nex0   <== all that cxl0 sees and puts on the wire

If you were doing TSO, a tcpdump on cxl0 may have shown you ~64K
"frames" with no L3/L4 checksum but this will show you the frames that
were actually transmitted.

/* all done */
# cxgbetool t5nex0 tracer 0 disable
# cxgbetool t5nex0 tracer 1 disable
# cxgbetool t5nex0 tracer list
# ifconfig t5nex0 destroy
2013-07-26 22:04:11 +00:00
Navdeep Parhar
4ff45b8b45 Reserve room for ioctls that aren't in this copy of the driver yet. 2013-07-26 20:54:33 +00:00
Navdeep Parhar
92ad6ac7d4 Specify a timeout for the PL block.
MFC after:	3 days
2013-07-17 02:37:40 +00:00
Navdeep Parhar
2b66d73259 Attach to the 4x10G T540-CR card. 2013-07-11 19:09:31 +00:00
Navdeep Parhar
3a760ee793 - Show the reason why link is down if this information is available.
- Display the temperature and PHY firmware version of the BT PHY.

MFC after:	1 day
2013-07-05 01:53:51 +00:00
Navdeep Parhar
6eb3180fb2 - Make note of interface MTU change if the rx queues exist, and not just
when the interface is up.
- Add a tunable to control the TOE's rx coalesce feature (enabled by
  default as it always has been).  Consider the interface MTU or the
  coalesce size when deciding which cluster zone to use to fill the
  offload rx queue's free list.  The tunable is:
  dev.{t4nex,t5nex}.<N>.toe.rx_coalesce

MFC after:	1 day
2013-07-04 21:19:01 +00:00
Navdeep Parhar
6300655cc1 On-the-fly changes to the interrupt coalescing timer should apply to the
TOE rx queues too.

MFC after:	1 day
2013-07-04 20:17:39 +00:00
Navdeep Parhar
50ce3d40aa Pay attention to TCP_NODELAY when it's set/unset after the connection
is established.

MFC after:	1 day
2013-07-04 19:44:30 +00:00
Navdeep Parhar
7e2fb22f81 Ring the egress queue's doorbell as soon as there are 8 or more
descriptors ready to be processed.

MFC after:	1 day
2013-07-04 19:15:41 +00:00
Navdeep Parhar
054a2dc11c The T5 allows the driver to specify the ISS. Do so; use the ISS picked
by the kernel.

MFC after:	1 day
2013-07-04 18:41:21 +00:00
Navdeep Parhar
c337fa30af - Read all TP parameters in one place.
- Read the filter mode, calculate various shifts, and use them
  properly during active open (in select_ntuple).

MFC after:	1 day
2013-07-04 17:55:52 +00:00
Navdeep Parhar
f72b68a1bf - Include the T5 firmware with the driver.
- Update the T4 firmware to the latest.
- Minor reorganization and updates to the version macros, etc.

Obtained from:	Chelsio
MFC after:	1 day
2013-07-03 23:52:15 +00:00
Navdeep Parhar
87c7afeb55 Add a sysctl to get the number of filters available.
sysctl dev.t4nex.<N>.nfilters
sysctl dev.t5nex.<N>.nfilters

MFC after:	3 days
2013-07-01 17:31:04 +00:00
Navdeep Parhar
9942898697 Update T5 register ranges. This is so that regdump skips over registers
with read side-effects.

MFC after:	3 days
2013-06-27 18:59:07 +00:00
Navdeep Parhar
f81cb396de cxgbe/tom: Allow caller to select the queue (control or data) used to
send the CPL_SET_TCB_FIELD request in t4_set_tcb_field().

MFC after:	1 week
2013-06-11 21:20:23 +00:00
Navdeep Parhar
e0f8a7f4da cxgbe/tom: Fix bad signed/unsigned mixup in the stid allocator. This
fixes a panic when allocating a mixture of IPv6 and IPv4 stids.

MFC after:	1 week
2013-06-08 07:23:26 +00:00
Navdeep Parhar
ad13c6af54 cxgbe(4): Never install a firmware if hw.cxgbe.fw_install is 0.
MFC after:	1 week
2013-06-05 20:57:52 +00:00
Navdeep Parhar
9050afc0a0 cxgbe(4): Provide accurate hit count for filters on T5 cards. The
location within the TCB and the size have both changed.

MFC after:	1 week
2013-06-04 02:25:25 +00:00
Navdeep Parhar
9e4ffff197 cxgbe(4): Some more debug sysctls. These work on both T4 and T5 based
cards.

dev.t5nex.0.misc.cim_ma_la: CIM MA logic analyzer
dev.t5nex.0.misc.cim_pif_la: CIM PIF logic analyzer
dev.t5nex.0.misc.mps_tcam: MPS TCAM entries
dev.t5nex.0.misc.tp_la: TP logic analyzer
dev.t5nex.0.misc.ulprx_la: ULPRX logic analyzer

Obtained from:	Chelsio
MFC after:	1 week
2013-06-01 02:07:37 +00:00
Konstantin Belousov
5ada86640b Add dependencies on the firmware, which allows the loading of the cxgb
and cxgbe modules.

Reviewed and approved by:	np
MFC after:	1 week
2013-05-16 13:07:02 +00:00
Navdeep Parhar
d607c7477c Deal correctly with 40G ports that don't have any transceiver plugged
in.  Do not claim that they have unknown tranceivers.

MFC after:	3 days
2013-05-13 20:00:03 +00:00
Navdeep Parhar
959cbee5b0 cxgbe: Switch to a better way to install firmware.
MFC after:	1 week
2013-05-03 20:09:17 +00:00
Navdeep Parhar
688dba74a5 cxgbe/tom: Do not use M_PROTO1 to mark rx zero-copy mbufs as special.
All the M_PROTOn flags are clobbered when an mbuf is appended to the
socket buffer.

MFC after:	1 week
2013-05-03 18:37:50 +00:00
Navdeep Parhar
88c4ff7bf1 Fix DDP breakage introduced in r248925. Bitwise OR has higher
precedence than ternary conditional.

MFC after:	1 week
2013-04-30 19:57:21 +00:00
Navdeep Parhar
249b2994d4 Attach to the T580 (2 x 40G) card.
MFC after:	1 week.
2013-04-30 06:30:21 +00:00
Navdeep Parhar
8cf31b85b5 - Provide accurate ifmedia information so that 40G ports/transceivers are
displayed properly in ifconfig, etc.

- Use the same number of tx and rx queues for a 40G port as for a 10G port.

MFC after:	1 week
2013-04-30 05:51:52 +00:00
Navdeep Parhar
3cc9b3e283 cxgbe(4): Some updates to shared code.
Obtained from:	Chelsio
MFC after:	1 week
2013-04-30 05:32:07 +00:00
Navdeep Parhar
3cc7ae06fd cxgbe(4): Refuse to install T5 firmwares on a T4 card (and vice versa).
MFC after:	1 week
2013-04-18 22:54:41 +00:00
Navdeep Parhar
dd181b2652 cxgbe/tom: Update the CLIP table on the chip when there are changes
to the list of IPv6 addresses on the system.  The table is used for
TOE+IPv6 only.
2013-04-18 19:52:11 +00:00
Navdeep Parhar
c0bc8af9b7 Add pciids of the T5 based cards. The ones that I haven't tested with
cxgbe(4) are disabled for now.  This will change.

MFC after:	2 weeks
2013-04-11 23:40:05 +00:00
Navdeep Parhar
77ad3c4146 Cosmetic change (s/wrwc/wcwr/;s/WRWC/WCWR/).
MFC after:	3 days.
2013-04-11 22:49:29 +00:00
Navdeep Parhar
cf738022b0 Auto-reduce the holdoff timers that are greater than the maximum value
allowed by the hardware.

MFC after:	3 days
2013-04-11 22:46:39 +00:00
Navdeep Parhar
b7a7c6d0c3 cxgbe/tom: Slight simplification of code that calculates options2.
MFC after:	3 days
2013-04-11 21:36:01 +00:00
Navdeep Parhar
e7fdf38bbb Get rid of a couple of stray \n's.
MFC after:	3 days.
2013-04-11 21:17:49 +00:00
Navdeep Parhar
53e8e49dcf There is no need for elaborate queries and error checking when trying to
set FW4MSG_ENCAP.

MFC after:	3 days
2013-04-11 21:15:35 +00:00
Navdeep Parhar
408b98ef5a - Explain clearly why a different firmware is being installed (if/when
it is being installed).  Improve other error messages while here.

- Select special FPGA specific configuration profile when appropriate.

MFC after:	3 days
2013-04-11 19:39:40 +00:00
Navdeep Parhar
13bf4b0798 cxgbe(4): Ensure that the MOD_LOAD handler runs before either t4nex or
t5nex attach to their devices.

MFC after:	3 days
2013-04-11 17:50:50 +00:00
Navdeep Parhar
d14b0ac129 cxgbe(4): Add support for Chelsio's Terminator 5 (aka T5) ASIC. This
includes support for the NIC and TOE features of the 40G, 10G, and
1G/100M cards based on the T5.

The ASIC is mostly backward compatible with the Terminator 4 so cxgbe(4)
has been updated instead of writing a brand new driver.  T5 cards will
show up as cxl (short for cxlgb) ports attached to the t5nex bus driver.

Sponsored by:	Chelsio
2013-03-30 02:26:20 +00:00
Navdeep Parhar
cc66a2c789 cxgbe(4): Report unusual out of band errors from the firmware.
Obtained from:	Chelsio
MFC after:	5 days
2013-02-26 21:25:17 +00:00
Navdeep Parhar
d78bd33fac cxgbe(4): Consider all the API versions of the interfaces exported by
the firmware (instead of just the main firmware version) when evaluating
firmware compatibility.  Document the new "hw.cxgbe.fw_install" knob
being introduced here.

This should fix kern/173584 too.  Setting hw.cxgbe.fw_install=2 will
mostly do what was requested in the PR but it's a bit more intelligent
in that it won't reinstall the same firmware repeatedly if the knob is
left set.

PR:		kern/173584
MFC after:	5 days
2013-02-26 20:35:54 +00:00
Navdeep Parhar
0abd31e2f7 cxgbe(4): Ask the card's firmware to pad up tiny CPLs by encapsulating
them in a firmware message if it is able to do so.  This works out
better for one of the FIFOs in the chip.

MFC after:	5 days
2013-02-26 00:27:27 +00:00
Navdeep Parhar
d938ff1d15 cxgbe(4): Update firmware to 1.8.4.0.
MFC after:	5 days
2013-02-26 00:10:28 +00:00
Navdeep Parhar
c1508f2bad cxgbe(4): Add sysctls to extract debug information from the chip:
dev.t4nex.X.misc.cim_la         logic analyzer dump
dev.t4nex.X.misc.cim_qcfg       queue configuration
dev.t4nex.X.misc.cim_ibq_xxx    inbound queues
dev.t4nex.X.misc.cim_obq_xxx    outbound queues

Obtained from:	Chelsio
MFC after:	1 week
2013-02-21 20:13:15 +00:00
Navdeep Parhar
b85313804d cxgbe(4): Assume that CSUM_TSO in the transmit path implies CSUM_IP and
CSUM_TCP too.  They are all set explicitly by the kernel usually.

While here, fix an unrelated bug where hardware L4 checksum calculation
was accidentally disabled for some IPv6 packets.

Reported by:	alfred@
MFC after:	3 days
2013-02-20 23:15:40 +00:00
Navdeep Parhar
bf3db9ebd8 Do not hold locks around hardware context reads.
MFC after:	3 days
2013-02-09 00:35:28 +00:00
Navdeep Parhar
0d8158d796 Busy-wait when cold.
Reported by:	gnn, jhb
MFC after:	3 days
2013-02-06 06:44:42 +00:00
Navdeep Parhar
c25f378771 Provide a statistic to track the number of drops in each of the port's
txq's buf_ring.  The aggregate for all the queues of a port is already
provided in ifnet->if_snd.ifq_drops.

MFC after:	3 days.
2013-01-29 20:59:22 +00:00