public inbox for kvm@vger.kernel.org
 help / color / mirror / Atom feed
From: "Woodhouse, David" <dwmw@amazon.co.uk>
To: "Paolo Bonzini" <pbonzini@redhat.com>,
	"Jim Mattson" <jmattson@google.com>,
	"Radim Krčmář" <rkrcmar@redhat.com>,
	linux-kernel@vger.kernel.org, kvm@vger.kernel.org,
	"KarimAllah Ahmed" <karahmed@amazon.de>,
	gregkh@linuxfoundation.org, stable@vger.kernel.org
Subject: Re: [STABLE 4.9.y PATCH 0/9] Backport of KVM Speculation Control support
Date: Tue, 6 Feb 2018 21:05:46 +0000	[thread overview]
Message-ID: <1517951146.3677.34.camel@amazon.co.uk> (raw)
In-Reply-To: <9ea4d52a-7ae6-a179-2f86-1e7b77255387@redhat.com>

[-- Attachment #1: Type: text/plain, Size: 8131 bytes --]



On Tue, 2018-02-06 at 19:01 +0100, Paolo Bonzini wrote:
> On 06/02/2018 18:29, David Woodhouse wrote:
> > I've put together a linux-4.9.y branch at 
> > http://git.infradead.org/retpoline-stable.git/shortlog/refs/heads/linux-4.9.y
> > 
> > Most of it is fairly straightforward, apart from the IBPB on context 
> > switch for which Tim has already posted a candidate. I wanted some more
> > review on my backports of the KVM bits though, including some extra
> > historical patches I pulled in.
> 
> Looks good!  Thanks for the work,
> 
> Paolo

Thanks. In that case, Greg, the full set is lined up in
http://git.infradead.org/retpoline-stable.git/shortlog/refs/heads/linux-4.9.y
or git://git.infradead.org/retpoline-stable linux-4.9.y

This matches what Linus just pulled in from tip/x86-pti-for-linus,
except that it's missing the IBPB on context switch (qv).

----------------------------------------------------------------
Andi Kleen (1):
      module/retpoline: Warn about missing retpoline in module

Andy Lutomirski (3):
      x86/entry/64: Remove the SYSCALL64 fast path
      x86/entry/64: Push extra regs right away
      x86/asm: Move 'status' from thread_struct to thread_info

Arnd Bergmann (1):
      x86/pti: Mark constant arrays as __initconst

Ashok Raj (1):
      KVM/x86: Add IBPB support

Borislav Petkov (4):
      x86/alternative: Print unadorned pointers
      x86/nospec: Fix header guards names
      x86/bugs: Drop one "mitigation" from dmesg
      x86/retpoline: Simplify vmexit_fill_RSB()

Colin Ian King (1):
      x86/spectre: Fix spelling mistake: "vunerable"-> "vulnerable"

Dan Williams (12):
      array_index_nospec: Sanitize speculative array de-references
      x86: Implement array_index_mask_nospec
      x86: Introduce barrier_nospec
      x86: Introduce __uaccess_begin_nospec() and uaccess_try_nospec
      x86/usercopy: Replace open coded stac/clac with __uaccess_{begin, end}
      x86/uaccess: Use __uaccess_begin_nospec() and uaccess_try_nospec
      x86/get_user: Use pointer masking to limit speculation
      x86/syscall: Sanitize syscall table de-references under speculation
      vfs, fdtable: Prevent bounds-check bypass via speculative execution
      nl80211: Sanitize array index in parse_txq_params
      x86/spectre: Report get_user mitigation for spectre_v1
      x86/kvm: Update spectre-v1 mitigation

Darren Kenny (1):
      x86/speculation: Fix typo IBRS_ATT, which should be IBRS_ALL

David Hildenbrand (1):
      KVM: nVMX: vmx_complete_nested_posted_interrupt() can't fail

David Matlack (1):
      KVM: nVMX: mark vmcs12 pages dirty on L2 exit

David Woodhouse (10):
      x86/cpufeatures: Add CPUID_7_EDX CPUID leaf
      x86/cpufeatures: Add Intel feature bits for Speculation Control
      x86/cpufeatures: Add AMD feature bits for Speculation Control
      x86/msr: Add definitions for new speculation control MSRs
      x86/pti: Do not enable PTI on CPUs which are not vulnerable to Meltdown
      x86/cpufeature: Blacklist SPEC_CTRL/PRED_CMD on early Spectre v2 microcodes
      x86/speculation: Add basic IBPB (Indirect Branch Prediction Barrier) support
      x86/cpufeatures: Clean up Spectre v2 related CPUID flags
      x86/cpuid: Fix up "virtual" IBRS/IBPB/STIBP feature bits on Intel
      x86/retpoline: Avoid retpolines for built-in __init functions

Dou Liyang (1):
      x86/spectre: Check CONFIG_RETPOLINE in command line parser

Jim Mattson (1):
      KVM: nVMX: Eliminate vmcs02 pool

Josh Poimboeuf (1):
      x86/paravirt: Remove 'noreplace-paravirt' cmdline option

KarimAllah Ahmed (4):
      x86/spectre: Simplify spectre_v2 command line parsing
      KVM/VMX: Emulate MSR_IA32_ARCH_CAPABILITIES
      KVM/VMX: Allow direct access to MSR_IA32_SPEC_CTRL
      KVM/SVM: Allow direct access to MSR_IA32_SPEC_CTRL

Mark Rutland (1):
      Documentation: Document array_index_nospec

Paolo Bonzini (2):
      KVM: VMX: introduce alloc_loaded_vmcs
      KVM: VMX: make MSR bitmaps per-VCPU

Peter Zijlstra (2):
      KVM: x86: Make indirect calls in emulator speculation safe
      KVM: VMX: Make indirect call speculation safe

Thomas Gleixner (1):
      x86/cpu/bugs: Make retpoline module warning conditional

Waiman Long (1):
      x86/retpoline: Remove the esp/rsp thunk

 Documentation/kernel-parameters.txt      |   2 -
 Documentation/speculation.txt            |  90 +++++++++++++
 arch/x86/entry/common.c                  |   9 +-
 arch/x86/entry/entry_32.S                |   3 +-
 arch/x86/entry/entry_64.S                | 134 ++----------------
 arch/x86/entry/syscall_64.c              |   7 +-
 arch/x86/include/asm/asm-prototypes.h    |   4 +-
 arch/x86/include/asm/barrier.h           |  28 ++++
 arch/x86/include/asm/cpufeature.h        |   7 +-
 arch/x86/include/asm/cpufeatures.h       |  22 ++-
 arch/x86/include/asm/disabled-features.h |   3 +-
 arch/x86/include/asm/intel-family.h      |   7 +-
 arch/x86/include/asm/msr-index.h         |  12 ++
 arch/x86/include/asm/msr.h               |   3 +-
 arch/x86/include/asm/nospec-branch.h     |  91 ++++---------
 arch/x86/include/asm/processor.h         |   2 -
 arch/x86/include/asm/required-features.h |   3 +-
 arch/x86/include/asm/syscall.h           |   6 +-
 arch/x86/include/asm/thread_info.h       |   3 +-
 arch/x86/include/asm/uaccess.h           |  15 ++-
 arch/x86/include/asm/uaccess_32.h        |  12 +-
 arch/x86/include/asm/uaccess_64.h        |  12 +-
 arch/x86/kernel/alternative.c            |  28 +---
 arch/x86/kernel/cpu/bugs.c               | 128 +++++++++++++-----
 arch/x86/kernel/cpu/common.c             |  70 +++++++++-
 arch/x86/kernel/cpu/intel.c              |  66 +++++++++
 arch/x86/kernel/cpu/scattered.c          |   2 -
 arch/x86/kernel/process_64.c             |   4 +-
 arch/x86/kernel/ptrace.c                 |   2 +-
 arch/x86/kernel/signal.c                 |   2 +-
 arch/x86/kvm/cpuid.c                     |  21 ++-
 arch/x86/kvm/cpuid.h                     |  31 +++++
 arch/x86/kvm/emulate.c                   |  10 +-
 arch/x86/kvm/svm.c                       | 116 ++++++++++++++++
 arch/x86/kvm/vmx.c                       | 754 ++++++++++++++++++++++++++++++++++++++++++++++++++++++------------------------------------------------
 arch/x86/kvm/x86.c                       |   1 +
 arch/x86/lib/Makefile                    |   1 +
 arch/x86/lib/getuser.S                   |  10 ++
 arch/x86/lib/retpoline.S                 |  57 +++++++-
 arch/x86/lib/usercopy_32.c               |   8 +-
 include/linux/fdtable.h                  |   5 +-
 include/linux/init.h                     |   9 +-
 include/linux/module.h                   |   9 ++
 include/linux/nospec.h                   |  72 ++++++++++
 kernel/module.c                          |  11 ++
 net/wireless/nl80211.c                   |   9 +-
 scripts/mod/modpost.c                    |   9 ++
 47 files changed, 1230 insertions(+), 680 deletions(-)
 create mode 100644 Documentation/speculation.txt
 create mode 100644 include/linux/nospec.h

[-- Attachment #2: smime.p7s --]
[-- Type: application/x-pkcs7-signature, Size: 5210 bytes --]

  reply	other threads:[~2018-02-06 21:05 UTC|newest]

Thread overview: 26+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-02-06 17:29 [STABLE 4.9.y PATCH 0/9] Backport of KVM Speculation Control support David Woodhouse
2018-02-06 17:29 ` [PATCH 1/9] KVM: nVMX: vmx_complete_nested_posted_interrupt() can't fail David Woodhouse
2018-02-06 17:29 ` [PATCH 2/9] KVM: nVMX: mark vmcs12 pages dirty on L2 exit David Woodhouse
2018-02-06 17:29 ` [PATCH 3/9] KVM: nVMX: Eliminate vmcs02 pool David Woodhouse
2018-02-06 17:29 ` [PATCH 4/9] KVM: VMX: introduce alloc_loaded_vmcs David Woodhouse
2018-02-06 17:29 ` [PATCH 5/9] KVM: VMX: make MSR bitmaps per-VCPU David Woodhouse
2018-02-06 17:29 ` [PATCH 6/9] KVM/x86: Add IBPB support David Woodhouse
2018-02-06 17:29 ` [PATCH 7/9] KVM/VMX: Emulate MSR_IA32_ARCH_CAPABILITIES David Woodhouse
2018-02-16 14:18   ` Paolo Bonzini
2018-02-16 16:29     ` Jim Mattson
2018-02-16 16:33       ` David Woodhouse
2018-02-06 17:29 ` [PATCH 8/9] KVM/VMX: Allow direct access to MSR_IA32_SPEC_CTRL David Woodhouse
2018-02-16  4:02   ` Jim Mattson
2018-02-16  4:16   ` Jim Mattson
2018-02-06 17:29 ` [PATCH 9/9] KVM/SVM: " David Woodhouse
2018-02-06 18:01 ` [STABLE 4.9.y PATCH 0/9] Backport of KVM Speculation Control support Paolo Bonzini
2018-02-06 21:05   ` Woodhouse, David [this message]
2018-02-08  2:49     ` Greg KH
2018-02-08 17:14       ` Greg KH
2018-02-08 17:42         ` Paolo Bonzini
2018-02-08 17:57           ` Greg KH
2018-02-09  7:58             ` Greg KH
2018-02-15 10:15 ` Thomas Voegtle
2018-02-15 10:23   ` Greg KH
2018-02-15 10:49     ` Thomas Voegtle
2018-02-15 13:57       ` Greg KH

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1517951146.3677.34.camel@amazon.co.uk \
    --to=dwmw@amazon.co.uk \
    --cc=gregkh@linuxfoundation.org \
    --cc=jmattson@google.com \
    --cc=karahmed@amazon.de \
    --cc=kvm@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=pbonzini@redhat.com \
    --cc=rkrcmar@redhat.com \
    --cc=stable@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox