| Commit message (Expand) | Author | Age | Files | Lines |
* | This patch adds an M_NOFREE flag which allows one to mark an mbuf as | Kip Macy | 2007-10-06 | 2 | -0/+12 |
* | Allow drivers to free an mbuf without having the mbuf be touched if | Kip Macy | 2007-10-06 | 1 | -2/+5 |
* | Fix sx_try_slock(), so it only fails when there is an exclusive owner. | Pawel Jakub Dawidek | 2007-10-02 | 1 | -9/+12 |
* | - Reassign the thread queue lock to newtd prior to switching. Assigning | Jeff Roberson | 2007-10-02 | 1 | -4/+6 |
* | - Move the rebalancer back into hardclock to prevent potential softclock | Jeff Roberson | 2007-10-02 | 1 | -55/+86 |
* | - Honor the PREEMPTION and FULL_PREEMPTION flags by setting the default | Jeff Roberson | 2007-09-27 | 1 | -2/+10 |
* | Fix the description of the formula used to autosize the number of | Ruslan Ermilov | 2007-09-26 | 1 | -1/+1 |
* | Change the management of cached pages (PQ_CACHE) in two fundamental | Alan Cox | 2007-09-25 | 2 | -11/+5 |
* | - Bound the interactivity score so that it cannot become negative. | Jeff Roberson | 2007-09-24 | 1 | -1/+1 |
* | - Improve grammar. s/it's/its/. | Jeff Roberson | 2007-09-22 | 1 | -5/+13 |
* | Fix some locking cases where we ask for exclusively locked vnode, but we get | Pawel Jakub Dawidek | 2007-09-21 | 2 | -4/+25 |
* | - Redefine p_swtime and td_slptime as p_swtick and td_slptick. This | Jeff Roberson | 2007-09-21 | 4 | -26/+29 |
* | - Call sched_sleep() before we suspend threads. sched_wakeup() is already | Jeff Roberson | 2007-09-21 | 1 | -0/+2 |
* | Fix some entries in the locks static table of witness. | Attilio Rao | 2007-09-20 | 3 | -11/+9 |
* | - Move all of the PS_ flags into either p_flag or td_flags. | Jeff Roberson | 2007-09-17 | 13 | -69/+47 |
* | Remove the definition and implementation of 'CALLOUT_NETGIANT', a now- (and | Robert Watson | 2007-09-15 | 1 | -11/+2 |
* | Currently the LO_NOPROFILE flag (which is masked on upper level code by | Attilio Rao | 2007-09-14 | 1 | -1/+1 |
* | subr_sleepqueue.c presents a thread lock missing which leads to dangerous | Attilio Rao | 2007-09-13 | 1 | -0/+2 |
* | When restoring the mount after umount failed, the MNTK_UNMOUNT flag | Konstantin Belousov | 2007-09-12 | 2 | -5/+10 |
* | This is a follow-up, cleaning-up commit about recent changes involving | Attilio Rao | 2007-09-11 | 1 | -1/+1 |
* | Rename mac_check_vnode_delete() MAC Framework and MAC Policy entry | Robert Watson | 2007-09-10 | 1 | -2/+2 |
* | In userland_sysctl(), call useracc() with the actual newlen value to be | Robert Watson | 2007-09-02 | 1 | -1/+1 |
* | Close a race that snuck in with the recent changes to fix a LOR between | John Baldwin | 2007-08-31 | 1 | -13/+27 |
* | Add missing newline in the log message of the previous commit. | Diomidis Spinellis | 2007-08-31 | 1 | -1/+1 |
* | Don't panic. When encountering a negative value call log(LOG_NOTICE, ...) | Diomidis Spinellis | 2007-08-31 | 1 | -1/+7 |
* | Partially revert the previous change. I failed to notice that where | John Baldwin | 2007-08-29 | 1 | -2/+0 |
* | Rework the routines to convert a 5.x+ statfs structure (with fixed-size | John Baldwin | 2007-08-28 | 1 | -4/+46 |
* | - During shutdown pending, when the last sack came in and | Randall Stewart | 2007-08-27 | 1 | -8/+5 |
* | Destroy the kaio_mtx on the freeing the struct kaioinfo in the | Konstantin Belousov | 2007-08-20 | 1 | -1/+5 |
* | - Improve runq_findbit_from() which is used by ULE's circular queue. Mask | Jeff Roberson | 2007-08-20 | 1 | -32/+22 |
* | - Set steal_thresh to log2(ncpus). This improves idle-time load balancing | Jeff Roberson | 2007-08-20 | 1 | -0/+6 |
* | Always call sched_bind(), even if on the CPU in question. It is wrong to | Nate Lawson | 2007-08-20 | 1 | -25/+15 |
* | Use a different loop variable for the inner loop. This previous reuse could | Nate Lawson | 2007-08-19 | 1 | -4/+4 |
* | Regenerate. | David Xu | 2007-08-16 | 3 | -0/+11 |
* | Add thr_kill2 syscall which sends a signal to a thread in another process. | David Xu | 2007-08-16 | 2 | -0/+56 |
* | On 6.x this works: | John Baldwin | 2007-08-15 | 1 | -11/+56 |
* | Improve vn_printf() by: | Pawel Jakub Dawidek | 2007-08-13 | 1 | -7/+45 |
* | Do not call free() while holding vnode interlock. | Konstantin Belousov | 2007-08-07 | 1 | -27/+44 |
* | Remove the now-unused NET_{LOCK,UNLOCK,ASSERT}_GIANT() macros, which | Robert Watson | 2007-08-06 | 5 | -107/+25 |
* | - Fix one line that erroneously crept in my last commit. | Jeff Roberson | 2007-08-04 | 1 | -1/+0 |
* | - Share scheduler locks between hyper-threaded cores to protect the | Jeff Roberson | 2007-08-03 | 1 | -114/+200 |
* | - Set SW_PREEMPT when we preempt in critical_exit(). | Jeff Roberson | 2007-08-03 | 1 | -1/+1 |
* | First in a series of changes to remove the now-unused Giant compatibility | Robert Watson | 2007-07-27 | 2 | -10/+2 |
* | Actually, upcalls cannot be freed while destroying the thread because we | Attilio Rao | 2007-07-27 | 2 | -0/+20 |
* | When we do open, we should lock the vnode exclusively. This fixes few races: | Pawel Jakub Dawidek | 2007-07-26 | 2 | -3/+3 |
* | The v_mountedhere field is protected by the vnode lock, not vnode's internal | Pawel Jakub Dawidek | 2007-07-26 | 1 | -1/+1 |
* | upcall_free() was only used in kse_GC() which has been removed so it now | Attilio Rao | 2007-07-23 | 1 | -8/+0 |
* | Actually, KSE kernel bits locking is broken and can lead likely to | Attilio Rao | 2007-07-23 | 2 | -82/+71 |
* | If clock_ct_to_ts fails to convert time time from the real time clock, | David Malone | 2007-07-23 | 1 | -1/+1 |
* | ttyfree() frees the cdev(). But if there are pending kevents, | Konstantin Belousov | 2007-07-20 | 1 | -7/+17 |