| Commit message (Expand) | Author | Age | Files | Lines |
* | - Take advantage of bus_dmamap_load_mbuf_sg(9). | Marius Strobl | 2008-03-24 | 2 | -94/+71 |
* | - Const'ify the dc_devs array. | Marius Strobl | 2008-03-24 | 2 | -85/+84 |
* | Split the registers into two halves in preparation for SBus support. | Marius Strobl | 2008-03-24 | 4 | -212/+285 |
* | Diff reduction to Adaptec driver build 15317 (refactoring and code shuffling): | Ed Maste | 2008-03-24 | 1 | -187/+206 |
* | Fix a bug that when getting/dumping the soft lifetime we reported | Bjoern A. Zeeb | 2008-03-24 | 1 | -1/+1 |
* | Import change from KAME, rev. 1.362 kame/kame/sys/netkey/key.c | Bjoern A. Zeeb | 2008-03-24 | 1 | -1/+1 |
* | Bump the FreeBSD version for zerocopy bpf buffers and changes to the | Christian S.J. Peron | 2008-03-24 | 1 | -1/+1 |
* | Introduce support for zero-copy BPF buffering, which reduces the | Christian S.J. Peron | 2008-03-24 | 8 | -122/+1229 |
* | remove unneccessary tcbinfo lock acquisitions - set tp to null affter calling... | Kip Macy | 2008-03-24 | 1 | -4/+2 |
* | - Greatly simplify vget() by removing the guarantee that any new | Jeff Roberson | 2008-03-24 | 1 | -32/+18 |
* | - Don't acquire the vnode interlock in _vn_lock() unless no lock type | Jeff Roberson | 2008-03-24 | 1 | -19/+13 |
* | - Remove an old comment; vnodes have been working without Giant for | Jeff Roberson | 2008-03-24 | 1 | -3/+3 |
* | Label inp as unused in the non-INVARIANTS case | Kip Macy | 2008-03-24 | 1 | -2/+2 |
* | First pass at (possibly futile) microoptimizing of cpu_switch. Results | Peter Wemm | 2008-03-23 | 1 | -75/+116 |
* | Correct an error in pmap_mincore() when applied to a 2MB page mapping: | Alan Cox | 2008-03-23 | 1 | -3/+3 |
* | Export TDP_KTHREAD to asm files. | Peter Wemm | 2008-03-23 | 1 | -0/+1 |
* | Move pcb_flags to make trivially better use of cache lines. | Peter Wemm | 2008-03-23 | 1 | -1/+1 |
* | Protect the setting of the fsbase/gsbase MSR registers and the | Peter Wemm | 2008-03-23 | 1 | -0/+2 |
* | Insulate inpcb consumers outside the stack from the lock type and offset with... | Kip Macy | 2008-03-23 | 4 | -73/+142 |
* | To date, we have assumed that the TLB will only set the PG_M bit in a | Alan Cox | 2008-03-23 | 1 | -38/+17 |
* | Yield the cpu in the kernel while iterating the list of the | Konstantin Belousov | 2008-03-23 | 3 | -0/+9 |
* | Prevent the overflow in the calculation of the next page directory. | Konstantin Belousov | 2008-03-23 | 2 | -0/+24 |
* | MSI handling on some RealTek chips are broken so disable it by | Pyun YongHyeon | 2008-03-23 | 1 | -1/+1 |
* | For MSI capable hardwares, enable MSI enable bit in RL_CFG2 | Pyun YongHyeon | 2008-03-23 | 2 | -0/+14 |
* | Some RealTek chips are known to be buggy on DAC handling, so | Pyun YongHyeon | 2008-03-23 | 1 | -1/+6 |
* | VLAN hardware tag information should be set for all desciptors of a | Pyun YongHyeon | 2008-03-23 | 1 | -11/+13 |
* | Always honor configured VLAN/checksum offload capabilities. | Pyun YongHyeon | 2008-03-23 | 1 | -3/+8 |
* | Remove commented out code, thread suspension is done in thread library. | David Xu | 2008-03-23 | 1 | -2/+1 |
* | - Only return 1 from sync_vnode() in cases where the vnode is still | Jeff Roberson | 2008-03-23 | 1 | -1/+1 |
* | Instead of making a single geom_part.ko module, make a module | Marcel Moolenaar | 2008-03-23 | 6 | -15/+66 |
* | - Pass BO_MTX(bo) to lockmgr in vtruncbuf, we don't own the vnode | Jeff Roberson | 2008-03-23 | 1 | -1/+1 |
* | Redefine G_PART_SCHEME_DECLARE() from populating a private linker set | Marcel Moolenaar | 2008-03-23 | 7 | -27/+128 |
* | Add g_retaste(), which given a class will present all non-open providers | Marcel Moolenaar | 2008-03-23 | 2 | -0/+61 |
* | We need to prototype _start() as well, as we use it to test if we're running | Olivier Houchard | 2008-03-22 | 1 | -0/+1 |
* | Reuse the mbuf that was just retrieved from the receive ring if mbuf | Qing Li | 2008-03-22 | 1 | -8/+17 |
* | add hints to specify how NPE ports are mapped to MAC+PHY; these | Sam Leffler | 2008-03-22 | 1 | -0/+8 |
* | Improve mac+phy configuration so that hints can be used to describe | Sam Leffler | 2008-03-22 | 1 | -16/+80 |
* | In abort2(2): Accept a NULL arg pointer if nargs == 0 | Poul-Henning Kamp | 2008-03-22 | 1 | -6/+8 |
* | (finally) add the hal status to the diagnostic generated after | Sam Leffler | 2008-03-22 | 1 | -3/+4 |
* | - Complete part of the unfinished bufobj work by consistently using | Jeff Roberson | 2008-03-22 | 18 | -253/+243 |
* | Fix a race where timeout/untimeout could cause crashes for Giant locked | Alfred Perlstein | 2008-03-22 | 1 | -4/+19 |
* | Add in a compat. mode so you can either open the card's device | Doug Ambrisko | 2008-03-22 | 1 | -0/+9 |
* | Add ';' missed with the SYSINIT changes. | Bjoern A. Zeeb | 2008-03-21 | 1 | -1/+1 |
* | Add the i915 GME device to DRM. | Remko Lodder | 2008-03-21 | 2 | -1/+3 |
* | Reduce contention on the vnode interlock by not acquiring the BO_LOCK | Konstantin Belousov | 2008-03-21 | 1 | -12/+10 |
* | Reduce the acquisition of the vnode interlock in the ffs_read() and | Konstantin Belousov | 2008-03-21 | 1 | -2/+4 |
* | - Reduce contention on the global bdonelock and bpinlock by using | Jeff Roberson | 2008-03-21 | 1 | -30/+34 |
* | - Add a new td flag TDF_NEEDSUSPCHK that is set whenever a thread needs | Jeff Roberson | 2008-03-21 | 6 | -20/+19 |
* | Explicitly use spinlock_enter/exit rather than locking the icu_lock spin | John Baldwin | 2008-03-20 | 2 | -30/+28 |
* | Implement a BUS_BIND_INTR() method in the bus interface to bind an IRQ | John Baldwin | 2008-03-20 | 5 | -0/+79 |