summaryrefslogtreecommitdiff
path: root/sys/dev/pci/if_em.c
AgeCommit message (Collapse)Author
2006-05-31fix Jumbo frames on strict alignment architectures by allocating a new mbuf andBrad Smith
copying the Ethernet header to the new mbuf. The new mbuf is then prepended into the existing mbuf chain. From FreeBSD ok reyk@ pascoe@ jason@
2006-05-28- force the maximum receivable frame size down to 1518 bytes forBrad Smith
strict alignment architectures for the time being. - remove the m_adj() on non-strict alignment architectures as this seems to resolve the Jumbo crashing issue. tested by a few developers. ok reyk@
2006-05-28always set if_hardmtu.Brad Smith
2006-05-28use if_hardmtu for MTU ioctl handler.Brad Smith
2006-05-28unknown ioctl is ENOTTY not EINVALJason Wright
2006-05-27remove IFCAP_JUMBO_MTU interface capabilities flag and set if_hardmtu in a fewBrad Smith
more drivers. ok reyk@
2006-05-26rename jumbo mtu to if_hardmtu; ok brad reykTheo de Raadt
2006-05-25formattingBrad Smith
2006-05-25formatting; ok bradJason Wright
2006-05-20fix pci resource allocation in em, don't crash!Reyk Floeter
fix by brad@
2006-05-20set if_jumbo_mtu and the IFCAP_JUMBO_MTU capabilities flag whereBrad Smith
appropriate. ok reyk@
2006-05-20simplify MTU ioctl switch case.Brad Smith
2006-05-07fix a typo and some KNF.Brad Smith
2006-05-07- Remove unreachable bus_dmamap_unload() in em_dma_malloc().Brad Smith
- Set the dma_tag to NULL upon failure in em_dma_malloc(). - In em_dma_free(), return if dma_tag is NULL.
2006-05-01replace magic value of 32 with EM_MAX_SCATTER.Brad Smith
2006-04-28when setting the interface address, only call em_init() if the interfaceBrad Smith
is not already running.
2006-04-18add a few more Intel Gig PCI ids.Brad Smith
Some of these are from jason@ and the rest are from the Linux PCI ids page.
2006-04-16remove splnet usage from em_intr().Brad Smith
2006-04-12when the interrupt handler has run out of work to do it shouldnt return 0David Gwynne
from the work loop. instead it should break from it so the spl can be lowered and any work that has been done can be counted. this fixes interrupt counting at least, and possibly issues related to leaving splnet raised.. ok deraadt@
2006-03-28Sync up to Intel's latest FreeBSD em driver (5.1.5). Adds supportBrad Smith
for the 82563 PCI Express chipset and a few fixes. From: Intel's web-site
2006-03-27sync in some of the new PCI ids.Brad Smith
2006-03-25allow bpf(4) to ignore packets based on their direction (inbound orDamien Miller
outbound), using a new BIOCSDIRFILT ioctl; guidance, feedback and ok canacar@
2006-02-24update link status here.Brad Smith
2006-02-22For 82544 and newer chips increase the number of TX descriptors to 512.Brad Smith
2006-02-17If there is no link then set IFM_NONE so ifconfig will show a mediaBrad Smith
status of (none) whether in auto or forced speed/duplex mode.
2006-02-17- simplify link state handling code.Brad Smith
- update interface baud rate properly so userland programs such as a SNMP daemon or bgpctl/ospfctl for example will display the correct interface speed instead of always saying 1 Gbps. From FreeBSD
2006-02-15be gone whitespace.Brad Smith
2006-02-10fix a typo in em_clean_transmit_interrupts() that will cause theBrad Smith
watchdog timer to fire if the TX descriptor ring is emptied for EM_TX_TIMEOUT seconds. The same bug exists in ixgb(4) too. From FreeSBD
2006-02-10remove unnecessary link state check in the watchdog handler.Brad Smith
2006-01-28a little cleaning.Brad Smith
2006-01-14Only update the RX ring consumer pointer after running through the RX loop,Brad Smith
not with each iteration through the loop. From FreeBSD
2005-12-10add a shutdown function and register it with shutdownhook_establish().Brad Smith
2005-12-10remove a bit of unused code.Brad Smith
Pointed out by Andrey Matveev <evol at online dot ptt dot ru> through noticing a missing splx which pointed out the fact that code is unused to me.
2005-12-04On the 82571 and newer chipset the ICR register is meaningful onlyBrad Smith
if the E1000_ICR_INT_ASSERTED bit is set. From FreeBSD
2005-11-28back out last change, caused me panics on jumbo packets, ok deraadt@Peter Stromberg
2005-11-27Since reception of Jumbo frames is enabled by default; ensure properBrad Smith
alignment with m_adj() in em_get_buf() whether the MTU is bumped higher or not.
2005-11-26set Ethernet flow control parameters in em_hardware_init()Brad Smith
after the PBA size has been set.
2005-11-19a whole lot of spaces to tabs, KNF and some other cleaning.Brad Smith
2005-11-18PCIX -> PCI-X in a few commentsBrad Smith
2005-11-18Use bus_addr_t for address in em_fill_descriptors().Brad Smith
2005-11-18fix wrong htole usage in the 82544 PCI-X workaround codepath in em_encap().Brad Smith
From FreeBSD
2005-11-18revert part of rev 1.45 ..Brad Smith
- Modify the caller of em_encap() to detect a NULL m_head and not try to queue the mbuf if that happens. which was in preparation for a software-based workaround for a HW VLAN tagging issue, but due to a HW limitation with tagging, we cannot use HW VLAN tagging at all.
2005-11-15remove braces and fix indenting here so its easier to read.Brad Smith
2005-11-14re-add comment which is still valid for em_print_hw_stats().Brad Smith
2005-11-14remove unused em_print_debug_info() function.Brad Smith
2005-11-14remove unused HW VLAN tagging support which cannot be used due to HW ↵Brad Smith
limitations. ok dlg@
2005-11-13- Introduce two more stat counters, counting number of RXBrad Smith
overruns and number of watchdog timeouts. - Do not increase if->if_oerrors in em_watchdog(), since this leads to counter slipping back, when if->if_oerrors is recalculated in em_update_stats_counters(). Instead increase watchdog counter in em_watchdog() and take it into account in em_update_stats_counters(). From glebius FreeBSD ok dlg@
2005-11-08Sync up to Intel's latest FreeBSD em driver (3.2.18). A few fixesBrad Smith
for the new PCI Express chips. From: Intel's web-site
2005-11-04don't bother setting error in em_attach() since it'sBrad Smith
not being used anyway.
2005-10-26add missing bus_dmamap_sync()'s, much closer to working on hppaBrad Smith
though it still falls over with NFS builds. From: FreeBSD ok deraadt@
generated by cgit v1.2.3 (git 2.25.1) at 2025-01-04 05:16:31 +0000