Skip to content

RFC KVM: PPC: Book3S HV P9: entry/exit optimisations round 1

Nicholas Piggin kvm-ppc linuxppc-dev 1 version In review

Get series with b4
b4 am [email protected]

Versions newest first

  1. v1 RFC Latest43 patches 23 repliesIn review

Patches in v1 No applies recorded yet

#Subject and filesSizeRepliesApplied
1/43powerpc/64s: Remove WORT SPR from POWER9/10arch/powerpc/kvm/book3s_hv.c arch/powerpc/platforms/powernv/idle.c+0 -51 reply
2/43KMV: PPC: Book3S HV P9: Use set_dec to set decrementer to hostarch/powerpc/kvm/book3s_hv.c+1 -10 replies
3/43KVM: PPC: Book3S HV P9: Use host timer accounting to avoid decrementer readarch/powerpc/include/asm/time.h arch/powerpc/kernel/time.c arch/powerpc/kvm/book3s_hv.c+13 -70 replies
4/43KVM: PPC: Book3S HV P9: Use large decrementer for HDECarch/powerpc/include/asm/time.h arch/powerpc/kernel/time.c arch/powerpc/kvm/book3s_hv_p9_entry.c+5 -10 replies
5/43KVM: PPC: Book3S HV P9: Reduce mftb per guest entry/exitarch/powerpc/kvm/book3s_hv.c arch/powerpc/kvm/book3s_hv_p9_entry.c+5 -40 replies
6/43powerpc/time: add API for KVM to re-arm the host timer/decrementerarch/powerpc/include/asm/time.h arch/powerpc/kernel/time.c arch/powerpc/kvm/book3s_hv.c+49 -260 replies
7/43KVM: PPC: Book3S HV: POWER10 enable HAIL when running radix guestsarch/powerpc/kvm/book3s_hv.c+25 -41 reply
8/43powerpc/64s: Keep AMOR SPR a constant ~0 at runtimearch/powerpc/kernel/cpu_setup_power.c arch/powerpc/kernel/dt_cpu_ftrs.c arch/powerpc/kvm/book3s_hv_p9_entry.c +3 more+13 -241 reply
9/43KVM: PPC: Book3S HV: Don't always save PMU for guest capable of nestingarch/powerpc/kvm/book3s_hv.c+0 -20 replies
10/43powerpc/64s: Always set PMU control registers to frozen/disabled when not in usearch/powerpc/kernel/cpu_setup_power.c arch/powerpc/kernel/dt_cpu_ftrs.c arch/powerpc/kvm/book3s_hv.c +1 more+17 -59 replies
11/43KVM: PPC: Book3S HV P9: Implement PMU save/restore in Carch/powerpc/include/asm/asm-prototypes.h arch/powerpc/kvm/book3s_hv.c arch/powerpc/kvm/book3s_hv_interrupts.S +1 more+200 -663 replies
12/43KVM: PPC: Book3S HV P9: Factor out yield_count incrementarch/powerpc/kvm/book3s_hv.c+12 -121 reply
13/43KVM: PPC: Book3S HV P9: Factor PMU save/load into context switch functionsarch/powerpc/kvm/book3s_hv.c+23 -280 replies
14/43KVM: PPC: Book3S HV P9: Demand fault PMU SPRs when marked not inusearch/powerpc/include/asm/kvm_host.h arch/powerpc/kvm/book3s_hv.c arch/powerpc/kvm/book3s_hv_nested.c+105 -300 replies
15/43KVM: PPC: Book3S HV: CTRL SPR does not require read-modify-writearch/powerpc/kvm/book3s_hv.c arch/powerpc/kvm/book3s_hv_rmhandlers.S+7 -100 replies
16/43KVM: PPC: Book3S HV P9: Move SPRG restore to restore_p9_host_os_sprsarch/powerpc/kvm/book3s_hv.c+2 -20 replies
17/43KVM: PPC: Book3S HV P9: Reduce mtmsrd instructions required to save host SPRsarch/powerpc/kernel/process.c arch/powerpc/kvm/book3s_hv.c arch/powerpc/kvm/book3s_hv_p9_entry.c+64 -180 replies
18/43KVM: PPC: Book3S HV P9: Improve mtmsrd scheduling by delaying MSR[EE] disablearch/powerpc/kvm/book3s_hv.c+18 -50 replies
19/43KVM: PPC: Book3S HV P9: Add kvmppc_stop_thread to match kvmppc_start_threadarch/powerpc/kvm/book3s_hv.c+9 -21 reply
20/43KVM: PPC: Book3S HV: Change dec_expires to be relative to guest timebasearch/powerpc/include/asm/kvm_book3s.h arch/powerpc/include/asm/kvm_host.h arch/powerpc/kvm/book3s_hv.c +3 more+49 -440 replies
21/43KVM: PPC: Book3S HV P9: Move TB updatesarch/powerpc/kvm/book3s_hv_p9_entry.c+18 -180 replies
22/43KVM: PPC: Book3S HV P9: Optimise timebase readsarch/powerpc/include/asm/kvm_book3s_64.h arch/powerpc/kvm/book3s_hv.c arch/powerpc/kvm/book3s_hv_p9_entry.c+65 -580 replies
23/43KVM: PPC: Book3S HV P9: Avoid SPR scoreboard stallsarch/powerpc/kvm/book3s_hv.c arch/powerpc/kvm/book3s_hv_p9_entry.c+15 -120 replies
24/43KVM: PPC: Book3S HV P9: Only execute mtSPR if the value changedarch/powerpc/kvm/book3s_hv.c+39 -250 replies
25/43KVM: PPC: Book3S HV P9: Juggle SPR switching aroundarch/powerpc/kvm/book3s_hv.c+4 -40 replies
26/43KVM: PPC: Book3S HV P9: Move vcpu register save/restore into functionsarch/powerpc/kvm/book3s_hv.c+33 -220 replies
27/43KVM: PPC: Book3S HV P9: Move host OS save/restore functions to built-inarch/powerpc/kvm/book3s_hv.c arch/powerpc/kvm/book3s_hv.h arch/powerpc/kvm/book3s_hv_p9_entry.c+372 -3502 replies
28/43KVM: PPC: Book3S HV P9: Move nested guest entry into its own functionarch/powerpc/kvm/book3s_hv.c+67 -580 replies
29/43KVM: PPC: Book3S HV P9: Move remaining SPR and MSR access into low level entryarch/powerpc/kvm/book3s_hv.c arch/powerpc/kvm/book3s_hv_p9_entry.c+96 -610 replies
30/43KVM: PPC: Book3S HV P9: Implement TM fastpath for guest entry/exitarch/powerpc/kvm/book3s_hv_p9_entry.c+20 -40 replies
31/43KVM: PPC: Book3S HV P9: Switch PMU to guest as late as possiblearch/powerpc/kvm/book3s_hv.c arch/powerpc/kvm/book3s_hv_p9_entry.c+4 -80 replies
32/43KVM: PPC: Book3S HV P9: Restrict DSISR canary workaround to processors that requirarch/powerpc/kvm/book3s_hv.c arch/powerpc/kvm/book3s_hv_p9_entry.c+6 -30 replies
33/43KVM: PPC: Book3S HV P9: More SPR speed improvementsarch/powerpc/kvm/book3s_hv_p9_entry.c+40 -270 replies
34/43KVM: PPC: Book3S HV P9: Demand fault EBB facility registersarch/powerpc/include/asm/kvm_host.h arch/powerpc/kvm/book3s_hv.c arch/powerpc/kvm/book3s_hv_nested.c +1 more+34 -71 reply
35/43KVM: PPC: Book3S HV P9: Demand fault TM facility registersarch/powerpc/include/asm/kvm_host.h arch/powerpc/kvm/book3s_hv.c arch/powerpc/kvm/book3s_hv_nested.c +1 more+31 -111 reply
36/43KVM: PPC: Book3S HV P9: Use Linux SPR save/restore to manage some host SPRsarch/powerpc/include/asm/switch_to.h arch/powerpc/kernel/process.c arch/powerpc/kvm/book3s_hv.c +2 more+72 -490 replies
37/43KVM: PPC: Book3S HV P9: Comment and fix MMU context switching codearch/powerpc/kvm/book3s_64_mmu_radix.c arch/powerpc/kvm/book3s_hv_p9_entry.c+33 -110 replies
38/43KVM: PPC: Book3S HV P9: Test dawr_enabled() before saving host DAWR SPRsarch/powerpc/kvm/book3s_hv_p9_entry.c+20 -142 replies
39/43KVM: PPC: Book3S HV P9: Don't restore PSSCR if not neededarch/powerpc/kvm/book3s_hv.c arch/powerpc/kvm/book3s_hv_p9_entry.c+24 -90 replies
40/43KVM: PPC: Book3S HV P9: Avoid tlbsync sequence on radix guest exitarch/powerpc/kvm/book3s_hv.c arch/powerpc/kvm/book3s_hv_p9_entry.c+26 -120 replies
41/43KVM: PPC: Book3S HV Nested: Avoid extra mftb() in nested entryarch/powerpc/include/asm/kvm_asm.h arch/powerpc/kvm/book3s_hv.c arch/powerpc/kvm/book3s_hv_nested.c+13 -50 replies
42/43KVM: PPC: Book3S HV P9: Improve mfmsr performance on entryarch/powerpc/include/asm/kvm_book3s_64.h arch/powerpc/kvm/book3s_hv.c arch/powerpc/kvm/book3s_hv_p9_entry.c+47 -390 replies
43/43KVM: PPC: Book3S HV P9: Optimise hash guest SLB savingarch/powerpc/kvm/book3s_hv_p9_entry.c+18 -40 replies

Reviews trailers per patch

9 of 43 patches have a Reviewed-by or Acked-by.

PatchAlexey KardashevskiyFabiano Rosas
1/43R-b
2/43
3/43
4/43R-b
5/43R-b
6/43
7/43R-b
8/43R-b
9/43
10/43
11/43
12/43R-b
13/43
14/43
15/43
16/43
17/43
18/43
19/43R-b
20/43
21/43
22/43
23/43
24/43
25/43
26/43
27/43
28/43
29/43
30/43
31/43
32/43
33/43
34/43R-b
35/43R-b
36/43
37/43
38/43
39/43
40/43
41/43
42/43
43/43

Trailers given in replies are filled; those carried in the patches from earlier versions are outlined with dashes.

Read the v1 thread

Cover letter [RFC PATCH 00/43] KVM: PPC: Book3S HV P9: entry/exit optimisations round 1

This series applies to powerpc topic/ppc-kvm branch (KVM Cify series in particular), plus "KVM: PPC: Book3S HV Nested: Reflect L2 PMU in-use to L0 when L2 SPRs are live" posted to kvm-ppc.

This reduces radix guest full entry/exit latency on POWER9 and POWER10 by almost 2x (hash is similar but it's still significantly slower than the P7/8 real mode handler). Nested HV guests should see speedups with some smaller improvements in the L1, plus the L0 switching sees many of the same speedups as a direct guest.

It does this in several main ways:

- Rearrange code to optimise SPR accesses. Mainly, avoid scoreboard stalls.

- Test SPR values to avoid mtSPRs where possible. mtSPRs are expensive.

- Reduce mftb. mftb is expensive.

- Demand fault certain facilities to avoid saving and/or restoring them (at the cost of fault when they are used, but this is mitigated over a number of entries, like the facilities when context switching processes). PM, TM, and EBB so far.

- Defer some sequences that are made just in case a guest is interrupted in the middle of a critical section to the case where the guest is scheduled on a different CPU, rather than every time (at the cost of an extra IPI in this case). Namely the tlbsync sequence for radix with GTSE, which is very expensive.

Some of the numbers quoted in changelogs may have changed a bit with patches being updated, reordered, etc. They give a bit of a guide, but I might remove them from the final submission because they're too much to maintain.

Thanks,
Nick

Nicholas Piggin (43):
powerpc/64s: Remove WORT SPR from POWER9/10
KMV: PPC: Book3S HV P9: Use set_dec to set decrementer to host
KVM: PPC: Book3S HV P9: Use host timer accounting to avoid decrementer
read
KVM: PPC: Book3S HV P9: Use large decrementer for HDEC
KVM: PPC: Book3S HV P9: Reduce mftb per guest entry/exit powerpc/time: add API for KVM to re-arm the host timer/decrementer
KVM: PPC: Book3S HV: POWER10 enable HAIL when running radix guests powerpc/64s: Keep AMOR SPR a constant ~0 at runtime
KVM: PPC: Book3S HV: Don't always save PMU for guest capable of
nesting
powerpc/64s: Always set PMU control registers to frozen/disabled when
not in use
KVM: PPC: Book3S HV P9: Implement PMU save/restore in C
KVM: PPC: Book3S HV P9: Factor out yield_count increment
KVM: PPC: Book3S HV P9: Factor PMU save/load into context switch
functions
KVM: PPC: Book3S HV P9: Demand fault PMU SPRs when marked not inuse
KVM: PPC: Book3S HV: CTRL SPR does not require read-modify-write
KVM: PPC: Book3S HV P9: Move SPRG restore to restore_p9_host_os_sprs
KVM: PPC: Book3S HV P9: Reduce mtmsrd instructions required to save
host SPRs
KVM: PPC: Book3S HV P9: Improve mtmsrd scheduling by delaying MSR[EE]
disable
KVM: PPC: Book3S HV P9: Add kvmppc_stop_thread to match
kvmppc_start_thread
KVM: PPC: Book3S HV: Change dec_expires to be relative to guest
timebase
KVM: PPC: Book3S HV P9: Move TB updates
KVM: PPC: Book3S HV P9: Optimise timebase reads
KVM: PPC: Book3S HV P9: Avoid SPR scoreboard stalls
KVM: PPC: Book3S HV P9: Only execute mtSPR if the value changed
KVM: PPC: Book3S HV P9: Juggle SPR switching around
KVM: PPC: Book3S HV P9: Move vcpu register save/restore into functions
KVM: PPC: Book3S HV P9: Move host OS save/restore functions to
built-in
KVM: PPC: Book3S HV P9: Move nested guest entry into its own function
KVM: PPC: Book3S HV P9: Move remaining SPR and MSR access into low
level entry
KVM: PPC: Book3S HV P9: Implement TM fastpath for guest entry/exit
KVM: PPC: Book3S HV P9: Switch PMU to guest as late as possible
KVM: PPC: Book3S HV P9: Restrict DSISR canary workaround to processors
that require it
KVM: PPC: Book3S HV P9: More SPR speed improvements
KVM: PPC: Book3S HV P9: Demand fault EBB facility registers
KVM: PPC: Book3S HV P9: Demand fault TM facility registers
KVM: PPC: Book3S HV P9: Use Linux SPR save/restore to manage some host
SPRs
KVM: PPC: Book3S HV P9: Comment and fix MMU context switching code
KVM: PPC: Book3S HV P9: Test dawr_enabled() before saving host DAWR
SPRs
KVM: PPC: Book3S HV P9: Don't restore PSSCR if not needed
KVM: PPC: Book3S HV P9: Avoid tlbsync sequence on radix guest exit
KVM: PPC: Book3S HV Nested: Avoid extra mftb() in nested entry
KVM: PPC: Book3S HV P9: Improve mfmsr performance on entry
KVM: PPC: Book3S HV P9: Optimise hash guest SLB saving

 arch/powerpc/include/asm/asm-prototypes.h |   5 -
 arch/powerpc/include/asm/kvm_asm.h        |   1 +
 arch/powerpc/include/asm/kvm_book3s.h     |   6 +
 arch/powerpc/include/asm/kvm_book3s_64.h  |   4 +-
 arch/powerpc/include/asm/kvm_host.h       |   5 +-
 arch/powerpc/include/asm/switch_to.h      |   2 +
 arch/powerpc/include/asm/time.h           |  19 +-
 arch/powerpc/kernel/cpu_setup_power.c     |  12 +-
 arch/powerpc/kernel/dt_cpu_ftrs.c         |   8 +-
 arch/powerpc/kernel/process.c             |  30 +
 arch/powerpc/kernel/time.c                |  54 +-
 arch/powerpc/kvm/book3s_64_mmu_radix.c    |   4 +
 arch/powerpc/kvm/book3s_hv.c              | 628 +++++++++----------
 arch/powerpc/kvm/book3s_hv.h              |  36 ++
 arch/powerpc/kvm/book3s_hv_interrupts.S   |  13 +-
 arch/powerpc/kvm/book3s_hv_nested.c       |  21 +-
 arch/powerpc/kvm/book3s_hv_p9_entry.c     | 725 +++++++++++++++++++---
 arch/powerpc/kvm/book3s_hv_rmhandlers.S   |  74 +--
 arch/powerpc/mm/book3s64/radix_pgtable.c  |  15 -
 arch/powerpc/perf/core-book3s.c           |   7 +
 arch/powerpc/platforms/powernv/idle.c     |  10 +-
 21 files changed, 1143 insertions(+), 536 deletions(-)
 create mode 100644 arch/powerpc/kvm/book3s_hv.h
Signature · 1 line
2.23.0