mbox series

[v4,00/11] KVM: selftests: Add nested support to dirty_log_perf_test

Message ID 20220520233249.3776001-1-dmatlack@google.com (mailing list archive)
Headers show
Series KVM: selftests: Add nested support to dirty_log_perf_test | expand

Message

David Matlack May 20, 2022, 11:32 p.m. UTC 
This series adds support for taking any perf_test_util-based test and
configuring it to run vCPUs in L2 instead of L1, and adds an option to
dirty_log_perf_test to enable it.

This series was used to collect the performance data for eager page
spliting for nested MMUs [1].

[1] https://lore.kernel.org/kvm/20220422210546.458943-1-dmatlack@google.com/

v4:
 - Add patch 11 to support for hosts with MAXPHYADDR > 48 [Sean]

v3: https://lore.kernel.org/kvm/20220520215723.3270205-1-dmatlack@google.com/
 - Only identity map a subset of the nGPA space [Sean, Peter]
 - Fail if nested_paddr contains more than 48 bits [me]
 - Move patch to delete all rule earlier [Peter]

v2: https://lore.kernel.org/kvm/20220517190524.2202762-1-dmatlack@google.com/
 - Collect R-b tags from Peter.
 - Use level macros instead of raw numbers [Peter]
 - Remove "upper" from function name [Peter]
 - Bring back setting the A/D bits on EPT PTEs [Peter]
 - Drop "all" rule from Makefile [Peter]
 - Reserve memory for EPT pages [Peter]
 - Fix off-by-one error in nested_map_all_1g() [me]

v1: https://lore.kernel.org/kvm/20220429183935.1094599-1-dmatlack@google.com/


David Matlack (11):
  KVM: selftests: Replace x86_page_size with PG_LEVEL_XX
  KVM: selftests: Add option to create 2M and 1G EPT mappings
  KVM: selftests: Drop stale function parameter comment for nested_map()
  KVM: selftests: Refactor nested_map() to specify target level
  KVM: selftests: Move VMX_EPT_VPID_CAP_AD_BITS to vmx.h
  KVM: selftests: Add a helper to check EPT/VPID capabilities
  KVM: selftests: Drop unnecessary rule for STATIC_LIBS
  KVM: selftests: Link selftests directly with lib object files
  KVM: selftests: Clean up LIBKVM files in Makefile
  KVM: selftests: Add option to run dirty_log_perf_test vCPUs in L2
  KVM: selftests: Restrict test region to 48-bit physical addresses when
    using nested

 tools/testing/selftests/kvm/Makefile          |  49 ++++--
 .../selftests/kvm/dirty_log_perf_test.c       |  10 +-
 .../selftests/kvm/include/perf_test_util.h    |   9 ++
 .../selftests/kvm/include/x86_64/processor.h  |  25 +--
 .../selftests/kvm/include/x86_64/vmx.h        |   6 +
 .../selftests/kvm/lib/perf_test_util.c        |  53 ++++++-
 .../selftests/kvm/lib/x86_64/perf_test_util.c | 112 +++++++++++++
 .../selftests/kvm/lib/x86_64/processor.c      |  33 ++--
 tools/testing/selftests/kvm/lib/x86_64/vmx.c  | 149 +++++++++++-------
 .../selftests/kvm/max_guest_memory_test.c     |   2 +-
 .../selftests/kvm/x86_64/mmu_role_test.c      |   2 +-
 11 files changed, 343 insertions(+), 107 deletions(-)
 create mode 100644 tools/testing/selftests/kvm/lib/x86_64/perf_test_util.c


base-commit: a3808d88461270c71d3fece5e51cc486ecdac7d0

Comments

Paolo Bonzini June 8, 2022, 5:18 p.m. UTC | #1 
On 5/21/22 01:32, David Matlack wrote:
> This series adds support for taking any perf_test_util-based test and
> configuring it to run vCPUs in L2 instead of L1, and adds an option to
> dirty_log_perf_test to enable it.
> 
> This series was used to collect the performance data for eager page
> spliting for nested MMUs [1].
> 
> [1] https://lore.kernel.org/kvm/20220422210546.458943-1-dmatlack@google.com/
> 
> v4:
>   - Add patch 11 to support for hosts with MAXPHYADDR > 48 [Sean]
> 
> v3: https://lore.kernel.org/kvm/20220520215723.3270205-1-dmatlack@google.com/
>   - Only identity map a subset of the nGPA space [Sean, Peter]
>   - Fail if nested_paddr contains more than 48 bits [me]
>   - Move patch to delete all rule earlier [Peter]
> 
> v2: https://lore.kernel.org/kvm/20220517190524.2202762-1-dmatlack@google.com/
>   - Collect R-b tags from Peter.
>   - Use level macros instead of raw numbers [Peter]
>   - Remove "upper" from function name [Peter]
>   - Bring back setting the A/D bits on EPT PTEs [Peter]
>   - Drop "all" rule from Makefile [Peter]
>   - Reserve memory for EPT pages [Peter]
>   - Fix off-by-one error in nested_map_all_1g() [me]
> 
> v1: https://lore.kernel.org/kvm/20220429183935.1094599-1-dmatlack@google.com/
> 
> 
> David Matlack (11):
>    KVM: selftests: Replace x86_page_size with PG_LEVEL_XX
>    KVM: selftests: Add option to create 2M and 1G EPT mappings
>    KVM: selftests: Drop stale function parameter comment for nested_map()
>    KVM: selftests: Refactor nested_map() to specify target level
>    KVM: selftests: Move VMX_EPT_VPID_CAP_AD_BITS to vmx.h
>    KVM: selftests: Add a helper to check EPT/VPID capabilities
>    KVM: selftests: Drop unnecessary rule for STATIC_LIBS
>    KVM: selftests: Link selftests directly with lib object files
>    KVM: selftests: Clean up LIBKVM files in Makefile
>    KVM: selftests: Add option to run dirty_log_perf_test vCPUs in L2
>    KVM: selftests: Restrict test region to 48-bit physical addresses when
>      using nested
> 
>   tools/testing/selftests/kvm/Makefile          |  49 ++++--
>   .../selftests/kvm/dirty_log_perf_test.c       |  10 +-
>   .../selftests/kvm/include/perf_test_util.h    |   9 ++
>   .../selftests/kvm/include/x86_64/processor.h  |  25 +--
>   .../selftests/kvm/include/x86_64/vmx.h        |   6 +
>   .../selftests/kvm/lib/perf_test_util.c        |  53 ++++++-
>   .../selftests/kvm/lib/x86_64/perf_test_util.c | 112 +++++++++++++
>   .../selftests/kvm/lib/x86_64/processor.c      |  33 ++--
>   tools/testing/selftests/kvm/lib/x86_64/vmx.c  | 149 +++++++++++-------
>   .../selftests/kvm/max_guest_memory_test.c     |   2 +-
>   .../selftests/kvm/x86_64/mmu_role_test.c      |   2 +-
>   11 files changed, 343 insertions(+), 107 deletions(-)
>   create mode 100644 tools/testing/selftests/kvm/lib/x86_64/perf_test_util.c
> 
> 
> base-commit: a3808d88461270c71d3fece5e51cc486ecdac7d0

Queued, thanks!  (It will be in either -rc2 or -rc3).

Paolo