From: Andrew Cooper <andrew.cooper3@citrix.com>
To: Xen-devel <xen-devel@lists.xen.org>
Cc: Andrew Cooper <andrew.cooper3@citrix.com>
Subject: [PATCH v8 16/17] x86/cpuid: Offer Indirect Branch Controls to guests
Date: Fri, 12 Jan 2018 18:01:06 +0000 [thread overview]
Message-ID: <1515780067-31735-17-git-send-email-andrew.cooper3@citrix.com> (raw)
In-Reply-To: <1515780067-31735-1-git-send-email-andrew.cooper3@citrix.com>
With all infrastructure in place, it is now safe to let guests see and use
these features. Allow AMD's IBPB to be set even on Intel hardware, so the
toolstack can express "IBPB only" to guests.
This also requires updating the libxc logic to understand the e8b feature
leaf, which has the side effect of also offering CLZERO on applicable
hardware.
Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
Acked-by: Jan Beulich <jbeulich@suse.com>
Acked-by: Wei Liu <wei.liu2@citrix.com>
---
tools/libxc/xc_cpuid_x86.c | 4 +++-
xen/arch/x86/cpuid.c | 8 ++++++++
xen/include/public/arch-x86/cpufeatureset.h | 6 +++---
3 files changed, 14 insertions(+), 4 deletions(-)
diff --git a/tools/libxc/xc_cpuid_x86.c b/tools/libxc/xc_cpuid_x86.c
index 25b922e..9fa2f7c 100644
--- a/tools/libxc/xc_cpuid_x86.c
+++ b/tools/libxc/xc_cpuid_x86.c
@@ -465,7 +465,9 @@ static void xc_cpuid_hvm_policy(xc_interface *xch,
case 0x80000008:
regs[0] &= 0x0000ffffu;
- regs[1] = regs[3] = 0;
+ regs[1] = info->featureset[featureword_of(X86_FEATURE_CLZERO)];
+ /* regs[2] handled in the per-vendor logic. */
+ regs[3] = 0;
break;
case 0x00000002: /* Intel cache info (dumped by AMD policy) */
diff --git a/xen/arch/x86/cpuid.c b/xen/arch/x86/cpuid.c
index 2ef71d2..e1b8c7a 100644
--- a/xen/arch/x86/cpuid.c
+++ b/xen/arch/x86/cpuid.c
@@ -354,6 +354,14 @@ static void __init calculate_host_policy(void)
recalculate_xstate(p);
recalculate_misc(p);
+ /*
+ * AMD's IPBP is a subset of Intel's IBRS/IBPB. For performance reasons,
+ * we may want to offer a guest only IBPB and not IBRS, so allow the AMD
+ * CPUID bit to be used whenever the hardware supports IBPB.
+ */
+ if ( p->feat.ibrsb )
+ p->extd.ibpb = true;
+
if ( p->extd.svm )
{
/* Clamp to implemented features which require hardware support. */
diff --git a/xen/include/public/arch-x86/cpufeatureset.h b/xen/include/public/arch-x86/cpufeatureset.h
index e148755..aaeb149 100644
--- a/xen/include/public/arch-x86/cpufeatureset.h
+++ b/xen/include/public/arch-x86/cpufeatureset.h
@@ -237,13 +237,13 @@ XEN_CPUFEATURE(EFRO, 7*32+10) /* APERF/MPERF Read Only interface */
/* AMD-defined CPU features, CPUID level 0x80000008.ebx, word 8 */
XEN_CPUFEATURE(CLZERO, 8*32+ 0) /*A CLZERO instruction */
-XEN_CPUFEATURE(IBPB, 8*32+12) /* IBPB support only (no IBRS, used by AMD) */
+XEN_CPUFEATURE(IBPB, 8*32+12) /*A IBPB support only (no IBRS, used by AMD) */
/* Intel-defined CPU features, CPUID level 0x00000007:0.edx, word 9 */
XEN_CPUFEATURE(AVX512_4VNNIW, 9*32+ 2) /*A AVX512 Neural Network Instructions */
XEN_CPUFEATURE(AVX512_4FMAPS, 9*32+ 3) /*A AVX512 Multiply Accumulation Single Precision */
-XEN_CPUFEATURE(IBRSB, 9*32+26) /* IBRS and IBPB support (used by Intel) */
-XEN_CPUFEATURE(STIBP, 9*32+27) /* STIBP */
+XEN_CPUFEATURE(IBRSB, 9*32+26) /*A IBRS and IBPB support (used by Intel) */
+XEN_CPUFEATURE(STIBP, 9*32+27) /*A STIBP */
#endif /* XEN_CPUFEATURE */
--
2.1.4
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel
next prev parent reply other threads:[~2018-01-12 18:01 UTC|newest]
Thread overview: 55+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-01-12 18:00 [PATCH v8 00/17] x86: Mitigations for SP2/CVE-2017-5715/Branch Target Injection Andrew Cooper
2018-01-12 18:00 ` [PATCH v8 01/17] x86: Support compiling with indirect branch thunks Andrew Cooper
2018-01-14 19:48 ` David Woodhouse
2018-01-15 0:00 ` Andrew Cooper
2018-01-15 4:11 ` Konrad Rzeszutek Wilk
2018-01-15 10:14 ` Jan Beulich
2018-01-15 10:40 ` Andrew Cooper
2018-01-15 10:48 ` Jan Beulich
2018-01-12 18:00 ` [PATCH v8 02/17] x86: Support indirect thunks from assembly code Andrew Cooper
2018-01-15 10:28 ` Jan Beulich
2018-01-16 13:55 ` Andrew Cooper
2018-01-16 14:00 ` Jan Beulich
2018-02-04 10:57 ` David Woodhouse
2018-02-05 8:56 ` Jan Beulich
2018-01-12 18:00 ` [PATCH v8 03/17] x86/boot: Report details of speculative mitigations Andrew Cooper
2018-01-12 18:00 ` [PATCH v8 04/17] x86/amd: Try to set lfence as being Dispatch Serialising Andrew Cooper
2018-01-12 18:00 ` [PATCH v8 05/17] x86: Introduce alternative indirect thunks Andrew Cooper
2018-01-15 10:53 ` Jan Beulich
2018-01-12 18:00 ` [PATCH v8 06/17] x86/feature: Definitions for Indirect Branch Controls Andrew Cooper
2018-01-12 18:00 ` [PATCH v8 07/17] x86/cmdline: Introduce a command line option to disable IBRS/IBPB, STIBP and IBPB Andrew Cooper
2018-01-12 18:00 ` [PATCH v8 08/17] x86/msr: Emulation of MSR_{SPEC_CTRL, PRED_CMD} for guests Andrew Cooper
2018-01-16 11:10 ` David Woodhouse
2018-01-16 16:58 ` Andrew Cooper
2018-01-17 9:11 ` Jan Beulich
2018-01-17 9:39 ` Andrew Cooper
2018-01-12 18:00 ` [PATCH v8 09/17] x86/migrate: Move MSR_SPEC_CTRL on migrate Andrew Cooper
2018-01-12 18:01 ` [PATCH v8 10/17] x86/hvm: Permit guests direct access to MSR_{SPEC_CTRL, PRED_CMD} Andrew Cooper
2018-01-15 11:11 ` Jan Beulich
2018-01-15 16:02 ` Boris Ostrovsky
2018-01-16 0:39 ` Tian, Kevin
2018-01-12 18:01 ` [PATCH v8 11/17] x86: Protect unaware domains from meddling hyperthreads Andrew Cooper
2018-01-15 11:26 ` Jan Beulich
2018-01-16 21:11 ` Andrew Cooper
2018-01-17 8:40 ` Jan Beulich
2018-01-17 8:43 ` Andrew Cooper
2018-01-12 18:01 ` [PATCH v8 12/17] x86/entry: Organise the use of MSR_SPEC_CTRL at each entry/exit point Andrew Cooper
2018-01-15 12:09 ` Jan Beulich
2018-01-16 21:24 ` Andrew Cooper
2018-01-17 8:47 ` Jan Beulich
2018-01-17 9:25 ` Andrew Cooper
2018-01-12 18:01 ` [PATCH v8 13/17] x86/boot: Calculate the most appropriate BTI mitigation to use Andrew Cooper
2018-01-16 14:10 ` Boris Ostrovsky
2018-01-16 14:13 ` Andrew Cooper
2018-01-16 14:25 ` Boris Ostrovsky
2018-01-16 15:12 ` Andrew Cooper
2018-01-12 18:01 ` [PATCH v8 14/17] x86/entry: Clobber the Return Stack Buffer/Return Address Stack on entry to Xen Andrew Cooper
2018-01-12 18:01 ` [PATCH v8 15/17] x86/ctxt: Issue a speculation barrier between vcpu contexts Andrew Cooper
2018-01-15 12:54 ` David Woodhouse
2018-01-15 13:02 ` Andrew Cooper
2018-01-15 13:23 ` David Woodhouse
2018-01-15 21:39 ` David Woodhouse
2018-01-17 17:26 ` David Woodhouse
2018-01-18 9:12 ` David Woodhouse
2018-01-12 18:01 ` Andrew Cooper [this message]
2018-01-12 18:01 ` [PATCH v8 17/17] x86/idle: Clear SPEC_CTRL while idle Andrew Cooper
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=1515780067-31735-17-git-send-email-andrew.cooper3@citrix.com \
--to=andrew.cooper3@citrix.com \
--cc=xen-devel@lists.xen.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).