Per cpu atomics in core allocators, cleanup and more this_cpu_ops
Get series with b4
b4 am [email protected]Versions newest first · linked by author and title
- v8 Latest16 patches 21 repliesIn review
- v78 patches 30 repliesSuperseded
- v67 patches 48 repliesSuperseded
Earlier versions · 5
| Version | Posted | Patches | Replies | Status |
|---|---|---|---|---|
| v5 | 18 of 19 patches | 38 replies | Superseded | |
| v3 | 19 patches | 4 replies | Superseded | |
| v4 | 20 patches | 44 replies | Superseded | |
| v2 | 19 patches | 28 replies | Superseded | |
| v1 | 11 patches | 17 replies | Superseded |
Changes in v8 from the cover letter
- Fix issue in slub patch
- Fix issue in modules patch
- Rediff page allocator patch
- Provide new this_cpu ops needed for ringbuffer [RFC state]
Patches in v8 No applies recorded yet
| # | Subject and files | Size | Replies | Applied |
|---|---|---|---|---|
| 1/16 | this_cpu_ops: page allocator conversioninclude/ include/ mm/ +1 more | +92 | 0 replies | |
| 2/16 | this_cpu ops: Remove pageset_notifiermm/ mm/ | +1 | 0 replies | |
| 3/16 | Use this_cpu operations in slubinclude/ mm/ | +49 | 1 reply | |
| 4/16 | SLUB: Get rid of dynamic DMA kmalloc cache allocationinclude/ mm/ | +21 | 0 replies | |
| 5/16 | this_cpu: Remove slub kmem_cache fieldsinclude/ mm/ | +17 | 0 replies | |
| 6/16 | Make slub statistics use this_cpu_incmm/ | +20 | 0 replies | |
| 7/16 | Module handling: Use this_cpu_xx to dynamically allocate countersinclude/ kernel/ kernel/ | +31 | 11 replies | |
| 8/16 | Remove cpu_local_xx macrosarch/ arch/ arch/ +3 more | +0 | 0 replies | |
| 9/16 | Allow arch to provide inc/dec functionality for each size separatelyinclude/ | +90 | 3 replies | |
| 10/16 | Support generating inc/dec for this_cpu_inc/decarch/ | +47 | 0 replies | |
| 11/16 | Generic support for this_cpu_cmpxchginclude/ | +99 | 6 replies | |
| 12/16 | Add percpu cmpxchg operationsarch/ | +12 | 0 replies | |
| 13/16 | Generic support for this_cpu_xchginclude/ | +95 | 0 replies | |
| 14/16 | x86 percpu xchg operationarch/ | +21 | 0 replies | |
| 15/16 | Generic support for this_cpu_add_return()include/ | +90 | 0 replies | |
| 16/16 | x86 support for this_cpu_add_returnarch/ | +35 | 0 replies |
Reviews trailers per patch
1 of 16 patches has a Reviewed-by or Acked-by.
| Patch | Mel Gorman |
|---|---|
| 1/16 | R-b |
| 2/16 | |
| 3/16 | |
| 4/16 | |
| 5/16 | |
| 6/16 | |
| 7/16 | |
| 8/16 | |
| 9/16 | |
| 10/16 | |
| 11/16 | |
| 12/16 | |
| 13/16 | |
| 14/16 | |
| 15/16 | |
| 16/16 |
Trailers given in replies are filled; those carried in the patches from earlier versions are outlined with dashes.
Cover letter [this_cpu_xx V8 00/16] Per cpu atomics in core allocators, cleanup and more this_cpu_ops
Leftovers from the earlier patchset rediffed to 2.6.33-rc1. Mostly applications of per cpu counters to core components.
After this patchset there will be only one user of local_t left: Mathieu's trace ringbuffer.
I added some patches that define additional this_cpu ops in order to help Mathieu with making the trace ringbuffer use this_cpu ops. These have barely been tested (boots fine on 32 and 64 bit but there is no user of these operations). RFC state.
V7->V8
- Fix issue in slub patch
- Fix issue in modules patch
- Rediff page allocator patch
- Provide new this_cpu ops needed for ringbuffer [RFC state]
V6->V7
- Drop patches merged in 2.6.33 merge cycle
- Drop risky slub patches
V5->V6:
- Drop patches merged by Tejun.
- Drop irqless slub fastpath for now.
- Patches against Tejun percpu for-next branch.
V4->V5:
- Avoid setup_per_cpu_area() modifications and fold the remainder of the patch into the page allocator patch.
- Irq disable / per cpu ptr fixes for page allocator patch.
V3->V4:
- Fix various macro definitions.
- Provide experimental percpu based fastpath that does not disable interrupts for SLUB.
V2->V3:
- Available via git tree against latest upstream from
git://git.kernel.org/pub/scm/linux/kernel/git/christoph/percpu.git linus
- Rework SLUB per cpu operations. Get rid of dynamic DMA slab creation for CONFIG_ZONE_DMA
- Create fallback framework so that 64 bit ops on 32 bit platforms can fallback to the use of preempt or interrupt disable. 64 bit platforms can use 64 bit atomic per cpu ops.
V1->V2:
- Various minor fixes
- Add SLUB conversion
- Add Page allocator conversion
- Patch against the git tree of today