#
0cf573e9 |
| 30-Mar-2012 |
David Xu <davidxu@FreeBSD.org> |
Fix COMPAT_FREEBSD32 build.
Submitted by: Andreas Tobler < andreast at fgznet dot ch >
|
#
4ed8858d |
| 30-Mar-2012 |
David Xu <davidxu@FreeBSD.org> |
Remove trailing space.
|
#
e05171d9 |
| 30-Mar-2012 |
David Xu <davidxu@FreeBSD.org> |
Merge umtxq_sleep and umtxq_nanosleep into a single function by using an abs_timeout structure which describes timeout info.
|
#
d31f470d |
| 29-Mar-2012 |
David Xu <davidxu@FreeBSD.org> |
Reduce code size by creating common timed sleeping function.
|
#
c6111de5 |
| 16-Mar-2012 |
Davide Italiano <davide@FreeBSD.org> |
Add rudimentary profiling of the hash table used in the in the umtx code to hold active lock queues.
Reviewed by: attilio Approved by: davidxu, gnn (mentor) MFC after: 3 weeks
|
#
867099fa |
| 08-Mar-2012 |
Gleb Smirnoff <glebius@FreeBSD.org> |
Merge head up to r232685 to projects/pf/head.
|
#
c9b01ed5 |
| 29-Feb-2012 |
David Xu <davidxu@FreeBSD.org> |
initialize clock ID and flags only when copying timespec, a _umtx_time copy already contains these fields.
|
#
24c20949 |
| 27-Feb-2012 |
David Xu <davidxu@FreeBSD.org> |
Follow changes made in revision 232144, pass absolute timeout to kernel, this eliminates a clock_gettime() syscall.
|
#
df1f1bae |
| 25-Feb-2012 |
David Xu <davidxu@FreeBSD.org> |
In revision 231989, we pass a 16-bit clock ID into kernel, however according to POSIX document, the clock ID may be dynamically allocated, it unlikely will be in 64K forever. To make it future compat
In revision 231989, we pass a 16-bit clock ID into kernel, however according to POSIX document, the clock ID may be dynamically allocated, it unlikely will be in 64K forever. To make it future compatible, we pack all timeout information into a new structure called _umtx_time, and use fourth argument as a size indication, a zero means it is old code using timespec as timeout value, but the new structure also includes flags and a clock ID, so the size argument is different than before, and it is non-zero. With this change, it is possible that a thread can sleep on any supported clock, though current kernel code does not have such a POSIX clock driver system.
show more ...
|
#
f911d9fa |
| 22-Feb-2012 |
David Xu <davidxu@FreeBSD.org> |
Fix typo.
|
#
b13a8fa7 |
| 22-Feb-2012 |
David Xu <davidxu@FreeBSD.org> |
Use unused fourth argument of umtx_op to pass flags to kernel for operation UMTX_OP_WAIT. Upper 16bits is enough to hold a clock id, and lower 16bits is used to pass flags. The change saves a clock_g
Use unused fourth argument of umtx_op to pass flags to kernel for operation UMTX_OP_WAIT. Upper 16bits is enough to hold a clock id, and lower 16bits is used to pass flags. The change saves a clock_gettime() syscall from libthr.
show more ...
|
#
8fa0b743 |
| 23-Jan-2012 |
Xin LI <delphij@FreeBSD.org> |
IFC @230489 (pending review).
|
#
29a06690 |
| 16-Jan-2012 |
David Xu <davidxu@FreeBSD.org> |
Eliminate branch and insert an explicit reader memory barrier to ensure that waiter bit is set before reading semaphore count.
|
#
80dbff4e |
| 04-Jan-2012 |
Sean Bruno <sbruno@FreeBSD.org> |
IFC to head to catch up the bhyve branch
Approved by: grehan@
|
Revision tags: release/9.0.0 |
|
#
662ebe9b |
| 03-Dec-2011 |
Peter Holm <pho@FreeBSD.org> |
Add umtx_copyin_timeout() and move parameter checks here.
In collaboration with: kib MFC after: 1 week
|
#
ff77dfb0 |
| 03-Dec-2011 |
Peter Holm <pho@FreeBSD.org> |
Rename copyin_timeout32 to umtx_copyin_timeout32 and move parameter check here. Include check for negative seconds value.
In collaboration with: kib MFC after: 1 week
|
#
3ee1a36e |
| 22-Nov-2011 |
Peter Grehan <grehan@FreeBSD.org> |
IFC @ r227804
Pull in the virtio drivers from head.
|
#
6472ac3d |
| 07-Nov-2011 |
Ed Schouten <ed@FreeBSD.org> |
Mark all SYSCTL_NODEs static that have no corresponding SYSCTL_DECLs.
The SYSCTL_NODE macro defines a list that stores all child-elements of that node. If there's no SYSCTL_DECL macro anywhere else,
Mark all SYSCTL_NODEs static that have no corresponding SYSCTL_DECLs.
The SYSCTL_NODE macro defines a list that stores all child-elements of that node. If there's no SYSCTL_DECL macro anywhere else, there's no reason why it shouldn't be static.
show more ...
|
#
70d8f36a |
| 27-Oct-2011 |
Peter Grehan <grehan@FreeBSD.org> |
IFC @ r226824
|
#
27449604 |
| 01-Oct-2011 |
Alexander Motin <mav@FreeBSD.org> |
MFC
|
#
8451d0dd |
| 16-Sep-2011 |
Kip Macy <kmacy@FreeBSD.org> |
In order to maximize the re-usability of kernel code in user space this patch modifies makesyscalls.sh to prefix all of the non-compatibility calls (e.g. not linux_, freebsd32_) with sys_ and updates
In order to maximize the re-usability of kernel code in user space this patch modifies makesyscalls.sh to prefix all of the non-compatibility calls (e.g. not linux_, freebsd32_) with sys_ and updates the kernel entry points and all places in the code that use them. It also fixes an additional name space collision between the kernel function psignal and the libc function of the same name by renaming the kernel psignal kern_psignal(). By introducing this change now we will ease future MFCs that change syscalls.
Reviewed by: rwatson Approved by: re (bz)
show more ...
|
#
db06a6f4 |
| 12-Mar-2011 |
Marcel Moolenaar <marcel@FreeBSD.org> |
Merge svn+ssh://svn.freebsd.org/base/head@219553
|
#
3379ac59 |
| 23-Feb-2011 |
John Baldwin <jhb@FreeBSD.org> |
Expose the umtx_key structure and API to the rest of the kernel.
MFC after: 3 days
|
#
9b4fcf85 |
| 18-Feb-2011 |
Marcel Moolenaar <marcel@FreeBSD.org> |
Merge svn+ssh://svn.freebsd.org/base/head@218816
|
Revision tags: release/7.4.0_cvs, release/8.2.0_cvs, release/7.4.0, release/8.2.0 |
|
#
c8e368a9 |
| 29-Dec-2010 |
David Xu <davidxu@FreeBSD.org> |
- Follow r216313, the sched_unlend_user_prio is no longer needed, always use sched_lend_user_prio to set lent priority. - Improve pthread priority-inherit mutex, when a contender's priority is lo
- Follow r216313, the sched_unlend_user_prio is no longer needed, always use sched_lend_user_prio to set lent priority. - Improve pthread priority-inherit mutex, when a contender's priority is lowered, repropagete priorities, this may cause mutex owner's priority to be lowerd, in old code, mutex owner's priority is rise-only.
show more ...
|