Commit Graph

22 Commits

Author SHA1 Message Date
scottl
4aba678223 There seems to be a problem with txcsum and UDP. Turn it off until it is
understood better.  This fixes timeout problems with NFS.
2006-10-21 20:41:08 +00:00
scottl
077b3a2427 Be more like the BGE driver. Ensure that at least 16 TX descriptors are
kept unused in the ring.  This check should probably be moved up to
bce_start_locked at some point, as it'll make the loop up there slightly
more efficient, and will eliminate a costly set of busdma operations when
the ring is full.  But this works for now.

This makes all of my UDP torture tests work.  I'll cautiously say that
it might even work for other users now.  Feedback is appreciated.
2006-10-21 07:54:39 +00:00
scottl
a910ffdb2b I can't find any reason why an 8 byte alignment should be enforced on rx
and tx buffers.  Fix it there, and also don't have it be overridden by the
parent tag.
2006-10-19 08:01:43 +00:00
scottl
ac5b874a80 Remove some spurious debugging, and use more complete error handling for
tx load and fragmentation problems.
2006-10-19 06:58:01 +00:00
scottl
c4037be379 Overhaul the transmit and dma paths:
- Use bus_dmamap_load_mbuf_sg() to eliminate the need for the callback and
all of the extra bookkeeping associated with it.
- Eliminate the bce_dmamap_arg structure and streamline the memory allocation
routines to not need it.  This does change some of the debugging messages.
- Refactor the loop that fills the buffer descriptor so that it can be done
with a single set of logic in a single loop instead of two sets of logic.
- Eliminate the need to cache and pass descriptor indexes between the start
loop and the encap function.
- Change the start loop to always check the ifnet sendq for more work.

This significantly helps the driver withstand large UDP workloads, though
it's still not perfect.  I suspect the remaining work lies with handling
the OACTIVE flag, and also in possibly streamlining the interrupt handler
some.  It is, however, nearly on par with the other popular gigabit drivers
in terms of stability now.
2006-10-15 23:42:56 +00:00
scottl
8bd9cc6205 Simplify the arguments to bce_tx_encap. 2006-10-14 05:30:12 +00:00
scottl
2640fdfe79 More small whitespace cleanups 2006-10-14 04:28:23 +00:00
scottl
5cccc781cc Don't copy the bd_chain head pointers into temporary objects, they are
available globally.
2006-10-14 03:58:59 +00:00
scottl
aad3bc0906 Fix some whitespace 2006-10-13 05:18:03 +00:00
ambrisko
d0248e472f Add a new 'bce_mgmt_init_locked' function to enable the minimal parts
of the chip to let ASF/IPMI firmware to respond to IPMI after attaching
and when the chip is down.  David looked at it but could really say
what they right minimal config. stuff would be.  It's not documented.
I figured this out via trial and error.

Reviewed by:	davidch
2006-09-20 18:55:16 +00:00
andre
2d9e7e4a32 Move ethernet VLAN tags from mtags to its own mbuf packet header field
m_pkthdr.ether_vlan.  The presence of the M_VLANTAG flag on the mbuf
signifies the presence and validity of its content.

Drivers that support hardware VLAN tag stripping fill in the received
VLAN tag (containing both vlan and priority information) into the
ether_vtag mbuf packet header field:

	m->m_pkthdr.ether_vtag = vlan_id;	/* ntohs()? */
	m->m_flags |= M_VLANTAG;

to mark the packet m with the specified VLAN tag.

On output the driver should check the mbuf for the M_VLANTAG flag to
see if a VLAN tag is present and valid:

	if (m->m_flags & M_VLANTAG) {
		... = m->m_pkthdr.ether_vtag;	/* htons()? */
		... pass tag to hardware ...
	}

VLAN tags are stored in host byte order.  Byte swapping may be necessary.

(Note: This driver conversion was mechanic and did not add or remove any
byte swapping in the drivers.)

Remove zone_mtag_vlan UMA zone and MTAG_VLAN definition.  No more tag
memory allocation have to be done.

Reviewed by:	thompsa, yar
Sponsored by:	TCP/IP Optimization Fundraise 2005
2006-09-17 13:33:30 +00:00
julian
2b72eebfd3 Remove extra '*/' comment close. In code not normally compiled but a bug never the less. 2006-08-15 04:56:29 +00:00
jhb
70fe8b7279 Expand locking coverage slightly to cover if_drv_flags in a few places
where it wasn't locked.

MFC after:	3 days
Reviewed by:	davidch
2006-07-20 18:41:00 +00:00
ambrisko
d49c8aec47 Fix ifconfig up when the HW was down. If the driver isn't running
then we need to call init otherwise just start the rx.

Interestingly dhclient seemed to work but ifconfig <IP> didn't
for me.

Reviewed by:	jhb
2006-07-12 23:13:09 +00:00
davidch
003705e187 Log:
- Removed updates to if_ibytes, if_obytes, if_imcasts, and if_omcasts.
  These should not be handled by the driver.
- Add code to handle excessively fragmented mbufs when mapping TX frames.

Reviewed by:	ps
Approved by:	ps (mentor)
MFC after:	1 week
2006-06-08 18:31:21 +00:00
phk
ef310efff8 Since DELAY() was moved, most <machine/clock.h> #includes have been
unnecessary.
2006-05-16 14:37:58 +00:00
mjacob
98b1689816 Gratuitous tag alignment. It bugged me. 2006-05-04 00:34:07 +00:00
ps
4a65e282e5 Only use the low address for stats collection. 2006-04-26 16:33:58 +00:00
jhb
82b42c364a Fix half of the current i386 tinderbox failure. max_bus_addr should be a
bus_addr_t rather than a bus_size_t.
2006-04-25 19:18:48 +00:00
ru
c3bf094702 Fix DEVICE_POLLING support (compile-only tested). 2006-04-13 14:12:26 +00:00
ps
cc2c59e66f Hook bce up to the build 2006-04-10 20:04:22 +00:00
ps
c2fa353e65 Add a driver for the Broadcom NetXtreme II (BCM5706/BCM5708)
PCI/PCIe Gigabit Ethernet adapeter.

Submitted by:	David Christensen
2006-04-10 19:55:23 +00:00