SLB miss conversion to C, and SLB optimisations
Get series with b4
b4 am [email protected]Versions newest first
- v1 Latest12 patches 7 repliesIn review
Patches in v1 No applies recorded yet
| # | Subject and files | Size | Replies | Applied |
|---|---|---|---|---|
| 1/12 | powerpc/64s/hash: Fix stab_rr off by one initializationarch/ | +1 | 3 replies | |
| 2/12 | powerpc/64s/hash: avoid the POWER5 < DD2.1 slb invalidate workaround on POWER8/9arch/ arch/ | +7 | 0 replies | |
| 3/12 | powerpc/64s/hash: move POWER5 < DD2.1 slbie workaround where it is neededarch/ | +7 | 2 replies | |
| 4/12 | powerpc/64s/hash: remove the vmalloc segment from the bolted SLBarch/ arch/ | +6 | 0 replies | |
| 5/12 | powerpc/64s/hash: Use POWER6 SLBIA IH=1 variant in switch_slbarch/ | +23 | 2 replies | |
| 6/12 | powerpc/64s/hash: Use POWER9 SLBIA IH=3 variant in switch_slbarch/ arch/ | +57 | 0 replies | |
| 7/12 | powerpc/64s/hash: convert SLB miss handlers to Carch/ arch/ arch/ +3 more | +196 | 0 replies | |
| 8/12 | powerpc/64s/hash: remove user SLB data from the pacaarch/ arch/ arch/ +5 more | +40 | 0 replies | |
| 9/12 | powerpc/64s/hash: SLB allocation status bitmapsarch/ arch/ arch/ +1 more | +58 | 0 replies | |
| 10/12 | powerpc/64s: xmon do not dump hash fields when using radix modearch/ | +21 | 0 replies | |
| 11/12 | powerpc/64s/hash: provide arch_setup_exec hooks for hash slice setuparch/ arch/ arch/ +3 more | +37 | 0 replies | |
| 12/12 | powerpc/64s/hash: Add a SLB preload cachearch/ arch/ arch/ +2 more | +143 | 0 replies |
Reviews trailers per patch
None of the 12 patches has a Reviewed-by or Acked-by.
| Patch | Nicholas Piggin |
|---|---|
| 1/12 | |
| 2/12 | |
| 3/12 | |
| 4/12 | |
| 5/12 | |
| 6/12 | Signed-of-by |
| 7/12 | |
| 8/12 | |
| 9/12 | |
| 10/12 | |
| 11/12 | |
| 12/12 |
Trailers given in replies are filled; those carried in the patches from earlier versions are outlined with dashes.
Cover letter [PATCH 00/12] SLB miss conversion to C, and SLB optimisations
This is a repost of the SLB conversion to C, no real change since last post. But given that slows down the SLB miss handler, I promised some optimisations could be made to mitigate that.
The two main optimisations after the C conversion are the SLB alloation bitmaps, and the preload cache.
Thanks,
Nick
Nicholas Piggin (12):
powerpc/64s/hash: Fix stab_rr off by one initialization powerpc/64s/hash: avoid the POWER5 < DD2.1 slb invalidate workaround
on POWER8/9
powerpc/64s/hash: move POWER5 < DD2.1 slbie workaround where it is
needed
powerpc/64s/hash: remove the vmalloc segment from the bolted SLB powerpc/64s/hash: Use POWER6 SLBIA IH=1 variant in switch_slb powerpc/64s/hash: Use POWER9 SLBIA IH=3 variant in switch_slb powerpc/64s/hash: convert SLB miss handlers to C powerpc/64s/hash: remove user SLB data from the paca powerpc/64s/hash: SLB allocation status bitmaps powerpc/64s: xmon do not dump hash fields when using radix mode powerpc/64s/hash: provide arch_setup_exec hooks for hash slice setup powerpc/64s/hash: Add a SLB preload cache
arch/powerpc/include/asm/asm-prototypes.h | 2 + arch/powerpc/include/asm/book3s/64/mmu-hash.h | 5 +- arch/powerpc/include/asm/exception-64s.h | 8 - arch/powerpc/include/asm/paca.h | 19 +- arch/powerpc/include/asm/processor.h | 1 + arch/powerpc/include/asm/slice.h | 1 + arch/powerpc/include/asm/thread_info.h | 11 + arch/powerpc/kernel/asm-offsets.c | 11 +- arch/powerpc/kernel/entry_64.S | 2 + arch/powerpc/kernel/exceptions-64s.S | 202 ++---- arch/powerpc/kernel/paca.c | 21 - arch/powerpc/kernel/process.c | 16 + arch/powerpc/mm/Makefile | 2 +- arch/powerpc/mm/hash_utils_64.c | 46 +- arch/powerpc/mm/mmu_context.c | 3 +- arch/powerpc/mm/mmu_context_book3s64.c | 9 + arch/powerpc/mm/slb.c | 596 ++++++++++++------ arch/powerpc/mm/slb_low.S | 335 ---------- arch/powerpc/mm/slice.c | 43 +- arch/powerpc/xmon/xmon.c | 37 +- 20 files changed, 540 insertions(+), 830 deletions(-) delete mode 100644 arch/powerpc/mm/slb_low.S
Signature · 1 line
2.18.0