| Commit message (Expand) | Author | Age | Files | Lines |
* | Handle overflow in calculating max kmem size. | Konstantin Belousov | 2019-01-14 | 1 | -2/+5 |
* | Fix DDB's "show malloc" after r338899. | Mark Johnston | 2018-12-19 | 1 | -5/+5 |
* | Add malloc_domainset(9) and _domainset variants to other allocator KPIs. | Mark Johnston | 2018-10-30 | 1 | -6/+24 |
* | Eliminate false sharing in malloc due to statistic collection | Mateusz Guzik | 2018-09-23 | 1 | -8/+27 |
* | Eliminate the arena parameter to kmem_free(). Implicitly this corrects an | Alan Cox | 2018-08-25 | 1 | -1/+1 |
* | Eliminate kmem_alloc_contig()'s unused arena parameter. | Alan Cox | 2018-08-20 | 1 | -2/+2 |
* | Make UMA and malloc(9) return non-executable memory in most cases. | Jonathan T. Looney | 2018-06-13 | 1 | -2/+2 |
* | malloc: try to use builtins for zeroing at the callsite | Mateusz Guzik | 2018-06-02 | 1 | -1/+1 |
* | malloc: avoid possibly returning stack garbage if MALLOC_DEBUG is defined | Matt Macy | 2018-05-19 | 1 | -0/+2 |
* | Add simple preempt safe epoch API | Matt Macy | 2018-05-10 | 1 | -1/+4 |
* | dtrace: depessimize dtmalloc when dtrace is active | Mateusz Guzik | 2018-04-24 | 1 | -3/+4 |
* | malloc: stop reading the subzone if MALLOC_DEBUG_MAXZONES == 1 (the default) | Mateusz Guzik | 2018-04-23 | 1 | -19/+36 |
* | Fix boot_pages exhaustion on machines with many domains and cores, where | Gleb Smirnoff | 2018-02-09 | 1 | -4/+0 |
* | Followup on r302393 by cperciva, improving calculation of boot pages required | Gleb Smirnoff | 2018-02-06 | 1 | -0/+2 |
* | Fix build for architectures where size_t is not unsigned long | Li-Wen Hsu | 2018-01-25 | 1 | -1/+1 |
* | malloc(9): Change nominal size to size_t to match standard C | Conrad Meyer | 2018-01-24 | 1 | -4/+4 |
* | Implement NUMA support in uma(9) and malloc(9). Allocations from specific | Jeff Roberson | 2018-01-12 | 1 | -57/+195 |
* | mallocarray(9): panic if the requested allocation would overflow | Conrad Meyer | 2018-01-10 | 1 | -8/+2 |
* | Introduce mallocarray() in the kernel | Kristof Provost | 2018-01-07 | 1 | -0/+17 |
* | Eliminate kmem_arena and kmem_object in preparation for further NUMA commits. | Jeff Roberson | 2017-11-28 | 1 | -20/+11 |
* | sys: further adoption of SPDX licensing ID tags. | Pedro F. Giffuni | 2017-11-20 | 1 | -0/+2 |
* | Renumber license clauses in sys/kern to avoid skipping #3 | Ed Maste | 2016-09-15 | 1 | -1/+1 |
* | Move IPv6 malloc tag definitions into the IPv6 code. | Mark Johnston | 2016-05-20 | 1 | -3/+0 |
* | Include sys/_task.h into uma_int.h, so that taskqueue.h isn't a | Gleb Smirnoff | 2016-02-09 | 1 | -1/+0 |
* | Redo r292484. Embed task(9) into zone, so that uz_maxaction is called | Gleb Smirnoff | 2016-02-03 | 1 | -0/+1 |
* | Don't make assertions about td_critnest when the scheduler is stopped. | Mark Johnston | 2015-12-11 | 1 | -6/+3 |
* | Consistently enforce the restriction against calling malloc/free when in a | Jonathan T. Looney | 2015-11-19 | 1 | -0/+9 |
* | The vmem callback to reclaim kmem arena address space on low or | Konstantin Belousov | 2015-05-09 | 1 | -2/+4 |
* | Set the SBUF_INCLUDENUL flag in sbuf_new_for_sysctl() so that sysctl | Ian Lepore | 2015-03-14 | 1 | -0/+1 |
* | svn revisions r269964 and r269963 seemed to have impaired small memory | Sean Bruno | 2014-09-22 | 1 | -0/+2 |
* | Add a new loader tunable, vm.kmem_zmax which allows a system administrator | Xin LI | 2014-08-14 | 1 | -2/+9 |
* | Re-instate UMA cached backend for 4K - 64K allocations. New consumers | Xin LI | 2014-08-14 | 1 | -12/+1 |
* | Compile fixes: | Hans Petter Selasky | 2014-06-28 | 1 | -1/+1 |
* | Pull in r267961 and r267973 again. Fix for issues reported will follow. | Hans Petter Selasky | 2014-06-28 | 1 | -27/+30 |
* | Revert r267961, r267973: | Glen Barber | 2014-06-27 | 1 | -30/+27 |
* | Extend the meaning of the CTLFLAG_TUN flag to automatically check if | Hans Petter Selasky | 2014-06-27 | 1 | -27/+30 |
* | Rename global cnt to vm_cnt to avoid shadowing. | Bryan Drewery | 2014-03-22 | 1 | -2/+2 |
* | On sparc64, VM_KMEM_SIZE_SCALE is not a constant expression, so it | Dimitry Andric | 2014-02-23 | 1 | -0/+2 |
* | - For kernel compiled only with KDTRACE_HOOKS and not any lock debugging | Attilio Rao | 2013-11-25 | 1 | -1/+0 |
* | As of r257209, all architectures have defined VM_KMEM_SIZE_SCALE. In other | Alan Cox | 2013-11-08 | 1 | -23/+31 |
* | Tidy up kmeminit(): Since r245575, 'nmbclusters' is calculated after | Alan Cox | 2013-10-05 | 1 | -3/+2 |
* | - Disable quantum caches on the kmem_arena. This can make fragmentation | Jeff Roberson | 2013-08-13 | 1 | -1/+1 |
* | Instead of just trying to do it for arm, make sure vm_kmem_size is properly | Olivier Houchard | 2013-08-09 | 1 | -0/+1 |
* | Replace kernel virtual address space allocation with vmem. This provides | Jeff Roberson | 2013-08-07 | 1 | -25/+41 |
* | Remove unused malloc type. | Konstantin Belousov | 2013-08-01 | 1 | -2/+0 |
* | Try to improve r242655 take III: move these SYSCTLs describing the kernel | Marius Strobl | 2013-02-04 | 1 | -11/+0 |
* | Further improve r242655 and supply VM_{MIN,MAX}_KERNEL_ADDRESS as constant | Marius Strobl | 2013-02-03 | 1 | -7/+7 |
* | Make r242655 build on sparc64. While at it, make vm_{max,min}_kernel_address | Marius Strobl | 2012-11-08 | 1 | -2/+4 |
* | export VM_MIN_KERNEL_ADDRESS and VM_MAX_KERNEL_ADDRESS via sysctl. | Alfred Perlstein | 2012-11-06 | 1 | -0/+8 |
* | Fix a bug with memguard(9) on 32-bit architectures without a | Matthew D Fleming | 2012-07-15 | 1 | -1/+1 |