qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Paolo Bonzini <pbonzini@redhat.com>
To: qemu-devel@nongnu.org
Cc: Kashyap Chamarthy <kchamart@redhat.com>
Subject: [PULL 30/61] qemu-cpu-models.rst: Document -noTSX, mds-no, taa-no, and tsx-ctrl
Date: Mon, 16 Mar 2020 22:26:57 +0100	[thread overview]
Message-ID: <1584394048-44994-31-git-send-email-pbonzini@redhat.com> (raw)
In-Reply-To: <1584394048-44994-1-git-send-email-pbonzini@redhat.com>

From: Kashyap Chamarthy <kchamart@redhat.com>

- Add the '-noTSX' variants for CascadeLake and SkyLake.

- Document the three MSR bits: 'mds-no', 'taa-no', and 'tsx-ctrl'

  Two confusing things about 'mds-no' (and the first point applies to
  the other two MSRs too):

  (1) The 'mds-no' bit will _not_ show up in the guest's /proc/cpuinfo.
      Rather it is used to fill in the guest's sysfs:

        /sys/devices/system/cpu/vulnerabilities/mds:Not affected

      Paolo confirmed on IRC as such.

  (2) There are _three_ variants[+] of CascadeLake CPUs, with different
      stepping levels: 5, 6, and 7.  To quote wikichip.org[*]:

        "note that while steppings 6 & 7 are fully mitigated, earlier
        stepping 5 is not protected against MSBDS, MLPDS, nor MDSUM"

      The above is also indicated in the Intel's document[+], as
      indicated by "No" under the three columns of MFBDS, MSBDS, and
      MLPDS.

  I've expressed this in the docs without belabouring the details.

      [+] https://software.intel.com/security-software-guidance/insights/processors-affected-microarchitectural-data-sampling
      [*] https://en.wikichip.org/wiki/intel/microarchitectures/cascade_lake#Key_changes_from_Skylake

Signed-off-by: Kashyap Chamarthy <kchamart@redhat.com>
Message-Id: <20200225165618.6571-3-kchamart@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 docs/system/cpu-models-x86.rst.inc | 57 ++++++++++++++++++++++++++++++++++++--
 1 file changed, 55 insertions(+), 2 deletions(-)

diff --git a/docs/system/cpu-models-x86.rst.inc b/docs/system/cpu-models-x86.rst.inc
index cbad930..9a23278 100644
--- a/docs/system/cpu-models-x86.rst.inc
+++ b/docs/system/cpu-models-x86.rst.inc
@@ -49,10 +49,15 @@ mixture of host CPU models between machines, if live migration
 compatibility is required, use the newest CPU model that is compatible
 across all desired hosts.
 
-``Skylake-Server``, ``Skylake-Server-IBRS``
+``Cascadelake-Server``, ``Cascadelake-Server-noTSX``
+    Intel Xeon Processor (Cascade Lake, 2019), with "stepping" levels 6
+    or 7 only.  (The Cascade Lake Xeon processor with *stepping 5 is
+    vulnerable to MDS variants*.)
+
+``Skylake-Server``, ``Skylake-Server-IBRS``, ``Skylake-Server-IBRS-noTSX``
     Intel Xeon Processor (Skylake, 2016)
 
-``Skylake-Client``, ``Skylake-Client-IBRS``
+``Skylake-Client``, ``Skylake-Client-IBRS``, ``Skylake-Client-noTSX-IBRS}``
     Intel Core Processor (Skylake, 2015)
 
 ``Broadwell``, ``Broadwell-IBRS``, ``Broadwell-noTSX``, ``Broadwell-noTSX-IBRS``
@@ -148,6 +153,54 @@ features are included if using "Host passthrough" or "Host model".
   Requires the host CPU microcode to support this feature before it
   can be used for guest CPUs.
 
+``mds-no``
+  Recommended to inform the guest OS that the host is *not* vulnerable
+  to any of the MDS variants ([MFBDS] CVE-2018-12130, [MLPDS]
+  CVE-2018-12127, [MSBDS] CVE-2018-12126).
+
+  This is an MSR (Model-Specific Register) feature rather than a CPUID feature,
+  so it will not appear in the Linux ``/proc/cpuinfo`` in the host or
+  guest.  Instead, the host kernel uses it to populate the MDS
+  vulnerability file in ``sysfs``.
+
+  So it should only be enabled for VMs if the host reports @code{Not
+  affected} in the ``/sys/devices/system/cpu/vulnerabilities/mds`` file.
+
+``taa-no``
+  Recommended to inform that the guest that the host is ``not``
+  vulnerable to CVE-2019-11135, TSX Asynchronous Abort (TAA).
+
+  This too is an MSR feature, so it does not show up in the Linux
+  ``/proc/cpuinfo`` in the host or guest.
+
+  It should only be enabled for VMs if the host reports ``Not affected``
+  in the ``/sys/devices/system/cpu/vulnerabilities/tsx_async_abort``
+  file.
+
+``tsx-ctrl``
+  Recommended to inform the guest that it can disable the Intel TSX
+  (Transactional Synchronization Extensions) feature; or, if the
+  processor is vulnerable, use the Intel VERW instruction (a
+  processor-level instruction that performs checks on memory access) as
+  a mitigation for the TAA vulnerability.  (For details, refer to
+  Intel's `deep dive into MDS
+  <https://software.intel.com/security-software-guidance/insights/deep-dive-intel-analysis-microarchitectural-data-sampling>`_.)
+
+  Expose this to the guest OS if and only if: (a) the host has TSX
+  enabled; *and* (b) the guest has ``rtm`` CPU flag enabled.
+
+  By disabling TSX, KVM-based guests can avoid paying the price of
+  mitigating TSX-based attacks.
+
+  Note that ``tsx-ctrl`` too is an MSR feature, so it does not show
+  up in the Linux ``/proc/cpuinfo`` in the host or guest.
+
+  To validate that Intel TSX is indeed disabled for the guest, there are
+  two ways: (a) check for the *absence* of ``rtm`` in the guest's
+  ``/proc/cpuinfo``; or (b) the
+  ``/sys/devices/system/cpu/vulnerabilities/tsx_async_abort`` file in
+  the guest should report ``Mitigation: TSX disabled``.
+
 
 Preferred CPU models for AMD x86 hosts
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
-- 
1.8.3.1




  parent reply	other threads:[~2020-03-16 21:56 UTC|newest]

Thread overview: 70+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-03-16 21:26 [PULL 00/61] Misc patches for soft freeze Paolo Bonzini
2020-03-16 21:26 ` [PULL 01/61] scsi/qemu-pr-helper: Fix out-of-bounds access to trnptid_list[] Paolo Bonzini
2020-03-16 21:26 ` [PULL 02/61] optionrom/pvh: scan entire RSDP Area Paolo Bonzini
2020-03-16 21:26 ` [PULL 03/61] misc: Replace zero-length arrays with flexible array member (automatic) Paolo Bonzini
2020-03-16 21:26 ` [PULL 04/61] misc: Replace zero-length arrays with flexible array member (manual) Paolo Bonzini
2020-03-16 21:26 ` [PULL 05/61] configure: add configure option avx512f_opt Paolo Bonzini
2020-03-16 21:26 ` [PULL 06/61] util: add util function buffer_zero_avx512() Paolo Bonzini
2020-03-16 22:02   ` Paolo Bonzini
2020-03-16 21:26 ` [PULL 07/61] WHPX: TSC get and set should be dependent on VM state Paolo Bonzini
2020-03-16 21:26 ` [PULL 08/61] WHPX: Use QEMU values for trapped CPUID Paolo Bonzini
2020-03-16 21:26 ` [PULL 09/61] MAINTAINERS: Add entry for Guest X86 HAXM CPUs Paolo Bonzini
2020-03-17  7:46   ` Colin Xu
2020-03-17  8:26     ` Paolo Bonzini
2020-03-17  8:55       ` Colin Xu
2020-03-17 10:27         ` Paolo Bonzini
2020-03-18  0:23           ` Colin Xu
2020-03-16 21:26 ` [PULL 10/61] hw/i386/intel_iommu: Fix out-of-bounds access on guest IRT Paolo Bonzini
2020-03-16 21:26 ` [PULL 11/61] oslib-posix: initialize mutex and condition variable Paolo Bonzini
2020-03-16 21:26 ` [PULL 12/61] build-sys: do not make qemu-ga link with pixman Paolo Bonzini
2020-03-16 21:26 ` [PULL 13/61] modules: load modules from versioned /var/run dir Paolo Bonzini
2020-03-16 21:26 ` [PULL 14/61] configure: Fix building with SASL on Windows Paolo Bonzini
2020-03-16 21:26 ` [PULL 15/61] tests/docker: Install SASL library to extend code coverage on amd64 Paolo Bonzini
2020-03-16 21:26 ` [PULL 16/61] memory: Fix start offset for bitmap log_clear hook Paolo Bonzini
2020-03-16 21:26 ` [PULL 17/61] qom/object: enable setter for uint types Paolo Bonzini
2020-03-16 21:26 ` [PULL 18/61] ich9: fix getter type for sci_int property Paolo Bonzini
2020-03-16 21:26 ` [PULL 19/61] ich9: Simplify ich9_lpc_initfn Paolo Bonzini
2020-03-16 21:26 ` [PULL 20/61] qom/object: Use common get/set uint helpers Paolo Bonzini
2020-03-16 21:26 ` [PULL 21/61] i386: Fix GCC warning with snprintf when HAX is enabled Paolo Bonzini
2020-03-16 21:26 ` [PULL 22/61] WHPX: Use proper synchronization primitives while processing Paolo Bonzini
2020-03-16 21:26 ` [PULL 23/61] Makefile: Align 'help' target output Paolo Bonzini
2020-03-16 21:26 ` [PULL 24/61] Makefile: Let the 'help' target list the tools targets Paolo Bonzini
2020-03-16 21:26 ` [PULL 25/61] hw/audio/fmopl: Move ENV_CURVE to .heap to save 32KiB of .bss Paolo Bonzini
2020-03-16 21:26 ` [PULL 26/61] hw/audio/intel-hda: Use memory region alias to reduce .rodata by 4.34MB Paolo Bonzini
2020-03-16 21:26 ` [PULL 27/61] hw/usb/quirks: Use smaller types to reduce .rodata by 10KiB Paolo Bonzini
2020-03-16 21:26 ` [PULL 28/61] ui/curses: Make control_characters[] array const Paolo Bonzini
2020-03-16 21:26 ` [PULL 29/61] ui/curses: Move arrays to .heap to save 74KiB of .bss Paolo Bonzini
2020-03-16 21:26 ` Paolo Bonzini [this message]
2020-03-16 21:26 ` [PULL 31/61] softmmu/vl.c: Handle '-cpu help' and '-device help' before 'no default machine' Paolo Bonzini
2020-03-16 21:26 ` [PULL 32/61] Use -isystem for linux-headers dir Paolo Bonzini
2020-03-16 21:27 ` [PULL 33/61] exec/rom_reset: Free rom data during inmigrate skip Paolo Bonzini
2020-03-16 21:27 ` [PULL 34/61] cpus: avoid pause_all_vcpus getting stuck due to race Paolo Bonzini
2020-03-16 21:27 ` [PULL 35/61] lockable: add lock guards Paolo Bonzini
2020-03-16 21:27 ` [PULL 36/61] lockable: add QemuRecMutex support Paolo Bonzini
2020-03-16 21:27 ` [PULL 37/61] memory: Correctly return alias region type Paolo Bonzini
2020-03-16 21:27 ` [PULL 38/61] memory: Simplify memory_region_init_rom_nomigrate() to ease review Paolo Bonzini
2020-03-16 21:27 ` [PULL 39/61] scripts/cocci: Rename memory-region-{init-ram -> housekeeping} Paolo Bonzini
2020-03-16 21:27 ` [PULL 40/61] scripts/cocci: Patch to replace memory_region_init_{ram, readonly -> rom} Paolo Bonzini
2020-03-16 21:27 ` [PULL 41/61] hw/arm: Use memory_region_init_rom() with read-only regions Paolo Bonzini
2020-03-16 21:27 ` [PULL 42/61] hw/display: " Paolo Bonzini
2020-03-16 21:27 ` [PULL 43/61] hw/m68k: " Paolo Bonzini
2020-03-16 21:27 ` [PULL 44/61] hw/net: " Paolo Bonzini
2020-03-16 21:27 ` [PULL 45/61] hw/pci-host: " Paolo Bonzini
2020-03-16 21:27 ` [PULL 46/61] hw/ppc: " Paolo Bonzini
2020-03-16 21:27 ` [PULL 47/61] hw/riscv: " Paolo Bonzini
2020-03-16 21:27 ` [PULL 48/61] hw/sh4: " Paolo Bonzini
2020-03-16 21:27 ` [PULL 49/61] hw/sparc: " Paolo Bonzini
2020-03-16 21:27 ` [PULL 50/61] scripts/cocci: Patch to detect potential use of memory_region_init_rom Paolo Bonzini
2020-03-16 21:27 ` [PULL 51/61] scripts/cocci: Patch to remove unnecessary memory_region_set_readonly() Paolo Bonzini
2020-03-16 21:27 ` [PULL 52/61] scripts/cocci: Patch to let devices own their MemoryRegions Paolo Bonzini
2020-03-16 21:27 ` [PULL 53/61] hw/core: Let devices own the MemoryRegion they create Paolo Bonzini
2020-03-16 21:27 ` [PULL 54/61] hw/display: " Paolo Bonzini
2020-03-16 21:27 ` [PULL 55/61] hw/dma: " Paolo Bonzini
2020-03-16 21:27 ` [PULL 56/61] hw/riscv: " Paolo Bonzini
2020-03-16 21:27 ` [PULL 57/61] hw/char: " Paolo Bonzini
2020-03-16 21:27 ` [PULL 58/61] hw/arm/stm32: Use memory_region_init_rom() with read-only regions Paolo Bonzini
2020-03-16 21:27 ` [PULL 59/61] hw/ppc/ppc405: " Paolo Bonzini
2020-03-16 21:27 ` [PULL 60/61] hw/arm: Remove unnecessary memory_region_set_readonly() on ROM alias Paolo Bonzini
2020-03-16 21:27 ` [PULL 61/61] hw/arm: Let devices own the MemoryRegion they create Paolo Bonzini
2020-03-16 23:58 ` [PULL 00/61] Misc patches for soft freeze no-reply
2020-03-17  0:27 ` no-reply

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=1584394048-44994-31-git-send-email-pbonzini@redhat.com \
    --to=pbonzini@redhat.com \
    --cc=kchamart@redhat.com \
    --cc=qemu-devel@nongnu.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;
as well as URLs for NNTP newsgroup(s).