Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]


Groups > linux.kernel > #1687346

[PATCH v9 00/10] Hyper-V: paravirtualized remote TLB flushing and hypercall improvements

From Vitaly Kuznetsov <vkuznets@redhat.com>
Newsgroups linux.kernel
Subject [PATCH v9 00/10] Hyper-V: paravirtualized remote TLB flushing and hypercall improvements
Date 2017-07-14 14:50 +0200
Message-ID <u38cG-3uL-1@gated-at.bofh.it> (permalink)
Organization linux.* mail to news gateway

Show all headers | View raw


It seems the series missed 4.13 merge window, rebase and resend.

Changes since v8:
- Rebase to the current char-misc tree (mostly to account for the newly
  added struct flush_tlb_info in tlb flush interfaces).
- PATCH07: drop hv_tmpcpumap as we have global infrastructure now.
- PATCH08: make fill_gva_list() return 'gva_n - offset' as we were doing
  too many REPs before (offset is the size of variable header, we don't
  need to include it in REP count when doing hypercall).
- PATCH08/09: add setup_clear_cpu_cap(X86_FEATURE_PCID) to future proof
  the code if PCID feature appears in Hyper-V guests.
- Add Andy's/Stephen's Reviewed-by: to all patches (hopefully they stand
  with the above mentioned changes).

P.S. I'm traveling next two weeks, my responses will probably be delayed.

Original description:

Hyper-V supports hypercalls for doing local and remote TLB flushing and
gives its guests hints when using hypercall is preferred. While doing
hypercalls for local TLB flushes is probably not practical (and is not
being suggested by modern Hyper-V versions) remote TLB flush with a
hypercall brings significant improvement.

To test the series I wrote a special 'TLB trasher': on a 16 vCPU guest I
was creating 32 threads which were doing 100000 mmap/munmaps each on some
big file. Here are the results:

Before:
# time ./pthread_mmap ./randfile 
real	3m33.118s
user	0m3.698s
sys	3m16.624s

After:
# time ./pthread_mmap ./randfile 
real	2m19.920s
user	0m2.662s
sys	2m9.948s

This series brings a number of small improvements along the way: fast
hypercall implementation and using it for event signaling, rep hypercalls
implementation, hyperv tracing subsystem (which only traces the newly added
remote TLB flush for now).

Vitaly Kuznetsov (10):
  x86/hyper-v: include hyperv/ only when CONFIG_HYPERV is set
  x86/hyper-v: stash the max number of virtual/logical processor
  x86/hyper-v: make hv_do_hypercall() inline
  x86/hyper-v: fast hypercall implementation
  hyper-v: use fast hypercall for HVCALL_SIGNAL_EVENT
  x86/hyper-v: implement rep hypercalls
  hyper-v: globalize vp_index
  x86/hyper-v: use hypercall for remote TLB flush
  x86/hyper-v: support extended CPU ranges for TLB flush hypercalls
  tracing/hyper-v: trace hyperv_mmu_flush_tlb_others()

 MAINTAINERS                         |   1 +
 arch/x86/Kbuild                     |   2 +-
 arch/x86/hyperv/Makefile            |   2 +-
 arch/x86/hyperv/hv_init.c           |  90 ++++++------
 arch/x86/hyperv/mmu.c               | 270 ++++++++++++++++++++++++++++++++++++
 arch/x86/include/asm/mshyperv.h     | 148 +++++++++++++++++++-
 arch/x86/include/asm/trace/hyperv.h |  40 ++++++
 arch/x86/include/uapi/asm/hyperv.h  |  17 +++
 arch/x86/kernel/cpu/mshyperv.c      |  13 +-
 drivers/hv/channel_mgmt.c           |  20 +--
 drivers/hv/connection.c             |   7 +-
 drivers/hv/hv.c                     |   9 --
 drivers/hv/hyperv_vmbus.h           |  11 --
 drivers/hv/vmbus_drv.c              |  17 ---
 drivers/pci/host/pci-hyperv.c       |  54 +-------
 include/linux/hyperv.h              |  17 +--
 16 files changed, 541 insertions(+), 177 deletions(-)
 create mode 100644 arch/x86/hyperv/mmu.c
 create mode 100644 arch/x86/include/asm/trace/hyperv.h

-- 
2.13.0

Back to linux.kernel | Previous | Next — Next in thread | Find similar | Unroll thread


Thread

[PATCH v9 00/10] Hyper-V: paravirtualized remote TLB flushing and hypercall improvements Vitaly Kuznetsov <vkuznets@redhat.com> - 2017-07-14 14:50 +0200
  [PATCH v9 06/10] x86/hyper-v: implement rep hypercalls Vitaly Kuznetsov <vkuznets@redhat.com> - 2017-07-14 14:50 +0200
  [PATCH v9 04/10] x86/hyper-v: fast hypercall implementation Vitaly Kuznetsov <vkuznets@redhat.com> - 2017-07-14 14:50 +0200
  [PATCH v9 09/10] x86/hyper-v: support extended CPU ranges for TLB flush hypercalls Vitaly Kuznetsov <vkuznets@redhat.com> - 2017-07-14 14:50 +0200
  [PATCH v9 07/10] hyper-v: globalize vp_index Vitaly Kuznetsov <vkuznets@redhat.com> - 2017-07-14 14:50 +0200
  [PATCH v9 08/10] x86/hyper-v: use hypercall for remote TLB flush Vitaly Kuznetsov <vkuznets@redhat.com> - 2017-07-14 14:50 +0200
    Re: [PATCH v9 08/10] x86/hyper-v: use hypercall for remote TLB flush Andy Shevchenko <andy.shevchenko@gmail.com> - 2017-07-15 00:00 +0200
  [PATCH v9 10/10] tracing/hyper-v: trace hyperv_mmu_flush_tlb_others() Vitaly Kuznetsov <vkuznets@redhat.com> - 2017-07-14 14:50 +0200
  [PATCH v9 03/10] x86/hyper-v: make hv_do_hypercall() inline Vitaly Kuznetsov <vkuznets@redhat.com> - 2017-07-14 14:50 +0200
  [PATCH v9 05/10] hyper-v: use fast hypercall for HVCALL_SIGNAL_EVENT Vitaly Kuznetsov <vkuznets@redhat.com> - 2017-07-14 14:50 +0200
  [PATCH v9 02/10] x86/hyper-v: stash the max number of virtual/logical processor Vitaly Kuznetsov <vkuznets@redhat.com> - 2017-07-14 14:50 +0200
  [PATCH v9 01/10] x86/hyper-v: include hyperv/ only when CONFIG_HYPERV is set Vitaly Kuznetsov <vkuznets@redhat.com> - 2017-07-14 14:50 +0200

csiph-web