summaryrefslogtreecommitdiffstats
path: root/sys/dev/cxgb
Commit message (Expand)AuthorAgeFilesLines
* Evidently setup_rss needs to happen whenever bind_qsets is done. This fixeskmacy2007-09-111-4/+0
* pull in changes made to RELENG_6 version in the process of doing the MFCkmacy2007-09-105-29/+36
* - Remove filter supportkmacy2007-09-091-298/+0
* Add back in support for normal mbuf chaining on RX under DISABLE_MBUF_IOVECkmacy2007-09-093-30/+174
* Fix last-minute typo in last commit caused by pre-commit scriptskmacy2007-09-091-1/+1
* - fix qset to port binding as a proper fix for the problems encountered on t...kmacy2007-09-0911-540/+678
* Fixes for 4 port and small packet optimizationkmacy2007-08-255-76/+125
* forward port signedness fixes from RELENG_6kmacy2007-08-179-18/+31
* White space cleanupskmacy2007-08-102-9/+6
* - In all structures other than port info port is a pointer to a port info,kmacy2007-08-104-15/+14
* - integrate most recent changes from vendor branch and upgrade to firmware re...kmacy2007-07-1719-690/+1474
* - Increase descriptors per call to startkmacy2007-07-173-13/+10
* MFp4 122896kmacy2007-07-103-42/+78
* - switch adapter and port lock over to using sx so that resourceskmacy2007-06-174-85/+205
* Fix build warningskmacy2007-06-152-2/+5
* - import new common code for the T304kmacy2007-06-1315-759/+1480
* remove pointless recursive acquisition of port lock in cxgb_init_lockedkmacy2007-06-021-2/+0
* Fix case of setting OACTIVE erroneouslykmacy2007-05-291-1/+2
* Fix interrupt setup for the non-MSI-X casekmacy2007-05-291-4/+3
* When building cxgb as a module make include paths relative to the driver's root.kmacy2007-05-2822-129/+137
* Tuning for small packet handlingkmacy2007-05-272-9/+6
* Don't bind queue to cpus if only one queue is in usekmacy2007-05-271-1/+3
* fix compile warning by removing redundant LOG_ERR definekmacy2007-05-271-1/+0
* set IFF_OACTIVE to avoid hangs when the tx ring fills upkmacy2007-05-272-0/+10
* add missed headerkmacy2007-05-251-0/+148
* update license headerskmacy2007-05-252-6/+6
* add toe device header missed by previous commitkmacy2007-05-251-0/+172
* (MFp4)kmacy2007-05-2521-1111/+4903
* Default to using a single queue as this is currently the only way to achievekmacy2007-04-261-1/+6
* Disable mbuf chain collapsing - it is currently causing an mbuf leakkmacy2007-04-261-1/+1
* Free cluster if we fail to create the dmamap.kmacy2007-04-201-3/+1
* Eliminate CID 1842 by comparing against (type != EXT_MBUF) => refcnt != NULLkmacy2007-04-201-1/+2
* Fix memory leak in m_collapse (CID 1843)kmacy2007-04-201-4/+7
* PHYS_TO_VM_PAGE requires explicit vm_page.h include on sparc64kmacy2007-04-151-0/+1
* Use %j and args cast to uintmax_t to print bus_addr_t && length args.mjacob2007-04-151-2/+2
* Add pmap includes needed by i386kmacy2007-04-151-0/+3
* suck in more of busdma to enable more efficient mappingskmacy2007-04-151-58/+164
* Add sysctl for disabling/enabling mbuf chain collapsingkmacy2007-04-152-11/+8
* Implement ZERO_COPY_SOCKETS check in a way that doesn't make LINT unhappykmacy2007-04-151-5/+6
* Add support for mbuf iovec in the TX pathkmacy2007-04-142-40/+87
* add reference count pointer to mbuf ioveckmacy2007-04-142-161/+381
* restore sense to get_imm_packetkmacy2007-04-121-6/+4
* switch over to per-txq dma tag to facilitate parallelism on TXkmacy2007-04-121-12/+12
* explicitly check TSO flagkmacy2007-04-121-12/+8
* Add ETHER_HDR_LEN to hardware accepted mtukmacy2007-04-121-3/+3
* Fix m_freem_vec() to actually traverse the mbuf chain. This avoidsjhb2007-04-111-0/+1
* throw sun4v into the check while we're at itkmacy2007-04-091-1/+1
* busdma tags are opaque on all architectures except sparc64kmacy2007-04-091-1/+2
* Add missing parenkmacy2007-04-081-4/+4
* remove stale variable referencekmacy2007-04-081-2/+2
OpenPOWER on IntegriCloud