55 Commits

Author SHA1 Message Date
kmacy
49e613fa45 MFSVN:
- add / remove clients from cxgb_main.c now
 - change ifdef TOE_ENABLED to TCP_OFFLOAD_DISABLE
 - update copyrights
 - fix transmit data mismatch bug caused by not setting SB_NOCOALESCE
   on tx sockbuf on passive connections
 - fix receive sequence mismatch bug caused by not setting SB_NOCOALESCE
   on rx sockbuf on passive connections
 - don't sleep without checking SBS_CANTRCVMORE first
 - various ddp ordering fixes

Supported by: Chelsio Inc.
2008-05-05 01:41:53 +00:00
kmacy
4eae976a6a move cxgb_lt2.[ch] from NIC to TOE
move most offload functionality from NIC to TOE
factor out all socket and inpcb direct access
factor out access to locking in incpb, pcbinfo, and sockbuf
2008-04-19 03:22:43 +00:00
kmacy
db590514fa pay attention to default cluster limits when sizing receive queues 2008-03-20 20:52:37 +00:00
kmacy
2deefa8109 fix link management bug and conditionally allow the PHY to be kept on at all times for allowing non-conformant link state checks 2008-03-19 20:56:51 +00:00
kmacy
8070f0fd71 - Integrate 1.133 vendor driver changes
- update some copyrights
- add improved support for delayed ack
- fix issue with fec
2008-03-18 03:55:12 +00:00
kmacy
a8940df33d move remaining binaries in to blob headers 2008-02-26 23:05:05 +00:00
kmacy
3c2b753612 Move firmware in to separate module that can be compiled statically in to the kernel
Add utility for converting future firmware revs to a C header file
2008-02-26 03:02:20 +00:00
kmacy
48fe676ff5 - update firmware to 5.0
- add support for T3C
- add DDP support (zero-copy receive)
- fix TOE transmit of large requests
- fix shutdown so that sockets don't remain in CLOSING state indefinitely
- register listeners when an interface is brought up after tom is loaded
- fix setting of multicast filter
- enable link at device attach
- exit tick handler if shutdown is in progress
- add helper for logging TCB
- add sysctls for dumping transmit queues

- note that TOE wxill not be MFC'd until after 7.0 has been finalized

MFC after: 3 days
2008-02-23 01:06:17 +00:00
kmacy
6dfbebef02 Fix lock ordering panic by not calling ether_ioctl with port lock held
Reported by: rrs
2008-01-16 21:33:34 +00:00
kmacy
1287cf02b7 - move WR_LEN in to cxgb_adapter.h add PIO_LEN to make intent clearer
- move cxgb_tx_common in to cxgb_multiq.c and rename to cxgb_tx
- move cxgb_tx_common dependencies
- further simplify cxgb_dequeue_packet for the non-multiqueue case
- only launch one service thread per port in the non-multiq case
- remove dead cleaning code from cxgb_sge.c
- simplify PIO case substantially in by returning directly from mbuf collapse
  and just using m_copydata
- remove gratuitous m_gethdr in the rx path
- clarify freeing of mbufs in collapse
2008-01-15 03:27:42 +00:00
kmacy
fdd517afe7 Make back pressure visible more quickly, particularly now that we maintain a queue internally 2008-01-14 05:59:06 +00:00
kmacy
fa806e1d17 Convert over to using the multiqueue infrastructure although all calls going
through cxgb_start still end up using queue 0
2008-01-13 22:38:17 +00:00
kmacy
bc3858933d Be more aggressive about tx cleaning - when multiples streams were running the tx
queue could fill up and stop getting cleaned.
2008-01-11 02:26:54 +00:00
kmacy
7e708f7f6f - make 9k clusters the default unless a tunable is set
- return the error from cxgb_tx_common so that when an error is hit we dont
  spin forever in the taskq thread
- remove unused rxsd_ref
- simplify header_offset calculation for embedded mbuf headers
- fix memory leak by making sure that mbuf header initialization took place
- disable printf's for stalled queue, don't do offload/ctrl queue restart
  when tunnel queue is restarted
- add more diagnostic information about the txq state
- add facility to dump the actual contents of the hardware queue using sysctl
2008-01-10 00:55:42 +00:00
kmacy
9fc024313f only include intr_machdep.h when it is needed for intr_bind
ia64 doesn't have an intr_machdep.h
2007-12-17 23:39:28 +00:00
kmacy
a541ef6e7d Make TCP offload work on HEAD (modulo negative interaction between sbcompress
and t3_push_frames).
 - Import latest changes to cxgb_main.c and cxgb_sge.c from toestack p4 branch
 - make driver local copy of tcp_subr.c and tcp_usrreq.c and override tcp_usrreqs so
   TOE can also functions on versions with unmodified TCP

- add cxgb back to the build
2007-12-17 08:17:51 +00:00
kmacy
9bec876a09 Use the vm include convention of busdma 2007-12-16 18:43:57 +00:00
kmacy
74fb05ec40 need M_IOVEC define 2007-12-16 18:36:57 +00:00
kmacy
62acf9d037 Import updated support code for the TOM (tcp offload module). 2007-12-15 21:54:59 +00:00
kmacy
552004c58f Evidently setup_rss needs to happen whenever bind_qsets is done. This fixes
a problem with jumbo frames when not using msi-x interrupts.

Supported by: Chelsio
Approved by: re (blanket)
2007-09-11 23:49:27 +00:00
kmacy
495285abf0 pull in changes made to RELENG_6 version in the process of doing the MFC
Supported by: Chelsio
Approved by: re (blanket)
2007-09-10 00:59:51 +00:00
kmacy
5e60afe4dd - Remove filter support
Supported by: Chelsio
Approved by: re(blanket)
2007-09-09 20:26:02 +00:00
kmacy
36e50690be - fix qset to port binding as a proper fix for the problems encountered on the 4-port
- fix the use after free seen when sending packets small enough to fit as an immediate
   and bpf peers are present
 - update to firmware rev 4.7 along with various small vendor fixes

Supported by: Chelsio
Approved by: re (blanket)
MFC after: 3 days
2007-09-09 01:28:03 +00:00
kmacy
2e3a8d8016 Fixes for 4 port and small packet optimization
- remove cpl->iff panic - we can't know the port number from the rspq on the 4-port
- pick the ifnet based on the interface in the CPL header
- switch to using qset 0 for egress on the 4-port for now - may change
  when we start using RSS
- move ether_ifdetach to before the port lock gets deinitialized to avoid
  hang in the case where there are BPF peers (cxgb_ioctl is called indirectly
  when BPF peers are present)
- don't call t3_mac_reset if multiport is set, this was causing tx errors
  by misconfiguring the MAC on the 4-port
- change V_TXPKT_INTF to use txpkt_intf as the interfaces are not contiguous
- free the mbuf immediately in the case where the payload is small enough to be copied
  into the rspq
- only update the coalesce timer if for a queue if packets were taken off of it
- add in missed 20ms DELAY in initializaton vsc8211

- prompt MFC as this only applies to the 4-port which is currently completely
  broken - OK'd by kensmith

Supported by: Chelsio
Approved by: re (blanket)
MFC after: 0 days
2007-08-25 21:07:37 +00:00
kmacy
c09acdcd00 forward port signedness fixes from RELENG_6
fix compile error for case where MSI_SUPPORTED not defined

Approved by: re (blanket)
2007-08-17 05:57:04 +00:00
kmacy
3a4b5d55d8 White space cleanups
Approved by: re (blanket)
2007-08-10 23:47:39 +00:00
kmacy
083e8c5c0f - In all structures other than port info port is a pointer to a port info,
make the code less confusing by renaming the port number to port_id

Approved by: re (blanket)
2007-08-10 23:33:34 +00:00
kmacy
184f644f1c - integrate most recent changes from vendor branch and upgrade to firmware revision 4.5.5
- add filter support
	- further improvements for T304
- recover gracefully from spurious immediate packets

Approved by: re(blanket)
Supported by: Chelsio
MFC after: 3 days
2007-07-17 06:50:35 +00:00
kmacy
2d80191535 - Increase descriptors per call to start
- enqueue per-txq task
- fix per-txq task initialization

Approved by: re (blanket)
2007-07-17 06:12:22 +00:00
kmacy
73c1163dd5 MFp4 122896
- reduce cpu usage by as much as 25% (40% -> 30) by doing txq reclaim more efficiently
   - use mtx_trylock when trying to grab the lock to avoid spinning during long encap loop
   - add per-txq reclaim task
   - if mbufs were successfully re-claimed try another pass
- track txq overruns with sysctl

Approved by: re (blanket)
2007-07-10 06:01:45 +00:00
kmacy
ee0c9012ea - switch adapter and port lock over to using sx so that resources
can be allocated atomically
- add debug macros for printing lock initialization / teardown
- add buffers to port_info and adapter to allow each lock to have a
  unique name
- destroy mutexes initialized by cxgb_offload_init
- remove recursive calls to ADAPTER_LOCK
- move callout_drain calls so that they don't occur with the lock held
- ensure that only as many qsets as are needed are initialized and
  destroyed

MFC after: 3 days
Sponsored by: Chelsio Inc.
2007-06-17 04:33:38 +00:00
kmacy
86403b20df Fix build warnings
Submitted by: mjacob@
2007-06-15 20:02:02 +00:00
kmacy
ca1df96c1a - import new common code for the T304
- update to firmware version 4.1.0

- switch over to standard method for initializing cdevs (contributed by scottl@)
- break out timer_reclaim_task to be per-port
- move msix teardown into separate function
- fix bus_setup_intr for msi-x for the multi-port case so that msi-x resources
  are not corrupted on unload
- handle 10/100/1000 base-T media and auto negotiation
- bind qset to cpu even for singleq case
- white space cleanups
- remove recursive PORT_LOCK
- move mtu setting to separate function
- stop and re-init port when changing mtu
- replace all direct references to m_data with calls to mtod
- handle attach failure better by not trying to de-initialize
  taskqueues when they have not been allocated
- no longer default to jumbo frames

Sponsored by: Chelsio
MFC after: 3 days
2007-06-13 05:36:00 +00:00
kmacy
206255ce0b remove pointless recursive acquisition of port lock in cxgb_init_locked 2007-06-02 03:02:36 +00:00
kmacy
052215bb59 Fix case of setting OACTIVE erroneously 2007-05-29 04:18:21 +00:00
kmacy
9cb5d0f6ce Fix interrupt setup for the non-MSI-X case 2007-05-29 03:13:53 +00:00
kmacy
679d42f237 When building cxgb as a module make include paths relative to the driver's root.
This will make it possible to build the module out of tree against an older src tree.

MFC after: 3 days
2007-05-28 22:57:27 +00:00
kmacy
3446e0aa75 Don't bind queue to cpus if only one queue is in use 2007-05-27 22:04:30 +00:00
kmacy
a25cd5af4b set IFF_OACTIVE to avoid hangs when the tx ring fills up 2007-05-27 04:39:07 +00:00
kmacy
ddbd7cde72 (MFp4)
- upgrade to reflect state of 1.0.0.86
        - move from firmware rev 3.2 to 4.0.0
        - import driver bits for offload functionality
	- remove binary distribution clause from top level files as it
	  runs counter to the intent of purely supporting the hardware

MFC after: 3 days
2007-05-25 09:48:20 +00:00
kmacy
2f0b14e001 Default to using a single queue as this is currently the only way to achieve
line rate
2007-04-26 08:38:00 +00:00
kmacy
8d122756a5 Add sysctl for disabling/enabling mbuf chain collapsing
remove map creation before calling bus_dmamap_load_mvec_sg
2007-04-15 05:45:10 +00:00
kmacy
df7c6cd2a9 Add support for mbuf iovec in the TX path 2007-04-14 20:40:22 +00:00
kmacy
560360bd84 Add ETHER_HDR_LEN to hardware accepted mtu
MFC after: 3 days
2007-04-12 03:07:24 +00:00
kmacy
758c270b77 bus_size_t is a bad cross-architectural type with respect to printf, use uint32_t instead 2007-03-24 04:28:33 +00:00
kmacy
eeef57ea74 - Increase coalesce_nsecs
- commit fixes for the following coverity warnings: 1765, 1760, 1758, 1756
2007-03-23 22:03:55 +00:00
kmacy
4bfdd681e7 Check PCI-e link width to avoid foot shooting with 4x links
MFC after: 3 days
2007-03-23 20:18:07 +00:00
kmacy
0fdeee32de move call to t3_prep_adapter earlier in attach before msi-x setup occurs
this works around the fact that pci_config_{save,restore} doesn't adequately
restore state for msi-x

MFC after: 3 days
2007-03-21 16:40:37 +00:00
kmacy
8c807af8fa allocate 9 messages in all cases 2007-03-21 09:16:10 +00:00
kmacy
88ef185ca9 make MSI-X the default and allocate up to mp_ncpus queues per port
MFC after: 3 days
2007-03-21 07:25:40 +00:00