From: Andrew Cooper <andrew.cooper3@citrix.com>
To: Xen-devel <xen-devel@lists.xen.org>
Cc: Andrew Cooper <andrew.cooper3@citrix.com>
Subject: [PATCH v4 17/26] x86/pv: Provide custom cpumasks for PV domains
Date: Wed, 23 Mar 2016 16:36:20 +0000 [thread overview]
Message-ID: <1458750989-28967-18-git-send-email-andrew.cooper3@citrix.com> (raw)
In-Reply-To: <1458750989-28967-1-git-send-email-andrew.cooper3@citrix.com>
And use them in preference to cpumask_defaults on context switch. HVM domains
must not be masked (to avoid interfering with cpuid calls within the guest),
so always lazily context switch to the host default.
Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
Reviewed-by: Jan Beulich <JBeulich@suse.com>
---
v2:
* s/cpumasks/cpuidmasks/
* Use structure assignment
* Fix error path in arch_domain_create()
v3:
* Indentation fixes.
* Only allocate PV cpuidmasks if the host is has cpumasks to use.
---
xen/arch/x86/cpu/amd.c | 4 +++-
xen/arch/x86/cpu/intel.c | 5 ++++-
xen/arch/x86/domain.c | 14 ++++++++++++++
xen/include/asm-x86/domain.h | 2 ++
4 files changed, 23 insertions(+), 2 deletions(-)
diff --git a/xen/arch/x86/cpu/amd.c b/xen/arch/x86/cpu/amd.c
index 484d4b0..8cb04f0 100644
--- a/xen/arch/x86/cpu/amd.c
+++ b/xen/arch/x86/cpu/amd.c
@@ -206,7 +206,9 @@ static void __init noinline probe_masking_msrs(void)
static void amd_ctxt_switch_levelling(const struct domain *nextd)
{
struct cpuidmasks *these_masks = &this_cpu(cpuidmasks);
- const struct cpuidmasks *masks = &cpuidmask_defaults;
+ const struct cpuidmasks *masks =
+ (nextd && is_pv_domain(nextd) && nextd->arch.pv_domain.cpuidmasks)
+ ? nextd->arch.pv_domain.cpuidmasks : &cpuidmask_defaults;
#define LAZY(cap, msr, field) \
({ \
diff --git a/xen/arch/x86/cpu/intel.c b/xen/arch/x86/cpu/intel.c
index 71b1199..00a9987 100644
--- a/xen/arch/x86/cpu/intel.c
+++ b/xen/arch/x86/cpu/intel.c
@@ -154,13 +154,16 @@ static void __init probe_masking_msrs(void)
static void intel_ctxt_switch_levelling(const struct domain *nextd)
{
struct cpuidmasks *these_masks = &this_cpu(cpuidmasks);
- const struct cpuidmasks *masks = &cpuidmask_defaults;
+ const struct cpuidmasks *masks;
if (cpu_has_cpuid_faulting) {
set_cpuid_faulting(nextd && is_pv_domain(nextd));
return;
}
+ masks = (nextd && is_pv_domain(nextd) && nextd->arch.pv_domain.cpuidmasks)
+ ? nextd->arch.pv_domain.cpuidmasks : &cpuidmask_defaults;
+
#define LAZY(msr, field) \
({ \
if (unlikely(these_masks->field != masks->field) && \
diff --git a/xen/arch/x86/domain.c b/xen/arch/x86/domain.c
index abc7194..d0d9773 100644
--- a/xen/arch/x86/domain.c
+++ b/xen/arch/x86/domain.c
@@ -577,6 +577,14 @@ int arch_domain_create(struct domain *d, unsigned int domcr_flags,
goto fail;
clear_page(d->arch.pv_domain.gdt_ldt_l1tab);
+ if ( levelling_caps & ~LCAP_faulting )
+ {
+ d->arch.pv_domain.cpuidmasks = xmalloc(struct cpuidmasks);
+ if ( !d->arch.pv_domain.cpuidmasks )
+ goto fail;
+ *d->arch.pv_domain.cpuidmasks = cpuidmask_defaults;
+ }
+
rc = create_perdomain_mapping(d, GDT_LDT_VIRT_START,
GDT_LDT_MBYTES << (20 - PAGE_SHIFT),
NULL, NULL);
@@ -672,7 +680,10 @@ int arch_domain_create(struct domain *d, unsigned int domcr_flags,
paging_final_teardown(d);
free_perdomain_mappings(d);
if ( is_pv_domain(d) )
+ {
+ xfree(d->arch.pv_domain.cpuidmasks);
free_xenheap_page(d->arch.pv_domain.gdt_ldt_l1tab);
+ }
psr_domain_free(d);
return rc;
}
@@ -692,7 +703,10 @@ void arch_domain_destroy(struct domain *d)
free_perdomain_mappings(d);
if ( is_pv_domain(d) )
+ {
free_xenheap_page(d->arch.pv_domain.gdt_ldt_l1tab);
+ xfree(d->arch.pv_domain.cpuidmasks);
+ }
free_xenheap_page(d->shared_info);
cleanup_domain_irq_mapping(d);
diff --git a/xen/include/asm-x86/domain.h b/xen/include/asm-x86/domain.h
index de60def..90f021f 100644
--- a/xen/include/asm-x86/domain.h
+++ b/xen/include/asm-x86/domain.h
@@ -252,6 +252,8 @@ struct pv_domain
/* map_domain_page() mapping cache. */
struct mapcache_domain mapcache;
+
+ struct cpuidmasks *cpuidmasks;
};
struct monitor_write_data {
--
2.1.4
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
http://lists.xen.org/xen-devel
next prev parent reply other threads:[~2016-03-23 16:36 UTC|newest]
Thread overview: 72+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-03-23 16:36 [PATCH v4 00/26] x86: Improvements to cpuid handling for guests Andrew Cooper
2016-03-23 16:36 ` [PATCH v4 01/26] xen/public: Export cpu featureset information in the public API Andrew Cooper
2016-03-24 14:08 ` Jan Beulich
2016-03-24 14:12 ` Andrew Cooper
2016-03-24 14:16 ` Jan Beulich
2016-03-23 16:36 ` [PATCH v4 02/26] xen/x86: Script to automatically process featureset information Andrew Cooper
2016-03-23 16:36 ` [PATCH v4 03/26] xen/x86: Collect more cpuid feature leaves Andrew Cooper
2016-03-23 16:36 ` [PATCH v4 04/26] xen/x86: Mask out unknown features from Xen's capabilities Andrew Cooper
2016-03-23 16:36 ` [PATCH v4 05/26] xen/x86: Annotate special features Andrew Cooper
2016-03-23 16:36 ` [PATCH v4 06/26] xen/x86: Annotate VM applicability in featureset Andrew Cooper
2016-03-23 16:36 ` [PATCH v4 07/26] xen/x86: Calculate maximum host and guest featuresets Andrew Cooper
2016-03-29 8:57 ` Jan Beulich
2016-03-23 16:36 ` [PATCH v4 08/26] xen/x86: Generate deep dependencies of features Andrew Cooper
2016-03-24 16:16 ` Jan Beulich
2016-03-23 16:36 ` [PATCH v4 09/26] xen/x86: Clear dependent features when clearing a cpu cap Andrew Cooper
2016-03-23 16:36 ` [PATCH v4 10/26] xen/x86: Improve disabling of features which have dependencies Andrew Cooper
2016-03-28 15:18 ` Konrad Rzeszutek Wilk
2016-03-23 16:36 ` [PATCH v4 11/26] xen/x86: Improvements to in-hypervisor cpuid sanity checks Andrew Cooper
2016-03-24 15:38 ` Andrew Cooper
2016-03-24 16:47 ` Jan Beulich
2016-03-24 17:01 ` Andrew Cooper
2016-03-24 17:11 ` Jan Beulich
2016-03-24 17:12 ` Andrew Cooper
2016-03-28 15:29 ` Konrad Rzeszutek Wilk
2016-04-05 15:25 ` Andrew Cooper
2016-03-23 16:36 ` [PATCH v4 12/26] x86/cpu: Move set_cpumask() calls into c_early_init() Andrew Cooper
2016-03-28 15:55 ` Konrad Rzeszutek Wilk
2016-04-05 16:19 ` Andrew Cooper
2016-03-23 16:36 ` [PATCH v4 13/26] x86/cpu: Sysctl and common infrastructure for levelling context switching Andrew Cooper
2016-03-24 16:58 ` Jan Beulich
2016-03-28 16:12 ` Konrad Rzeszutek Wilk
2016-04-05 16:33 ` Andrew Cooper
2016-03-28 17:37 ` Konrad Rzeszutek Wilk
2016-03-23 16:36 ` [PATCH v4 14/26] x86/cpu: Rework AMD masking MSR setup Andrew Cooper
2016-03-28 18:55 ` Konrad Rzeszutek Wilk
2016-04-05 16:44 ` Andrew Cooper
2016-03-23 16:36 ` [PATCH v4 15/26] x86/cpu: Rework Intel masking/faulting setup Andrew Cooper
2016-03-28 19:14 ` Konrad Rzeszutek Wilk
2016-04-05 16:45 ` Andrew Cooper
2016-03-23 16:36 ` [PATCH v4 16/26] x86/cpu: Context switch cpuid masks and faulting state in context_switch() Andrew Cooper
2016-03-28 19:27 ` Konrad Rzeszutek Wilk
2016-04-05 18:34 ` Andrew Cooper
2016-03-23 16:36 ` Andrew Cooper [this message]
2016-03-28 19:40 ` [PATCH v4 17/26] x86/pv: Provide custom cpumasks for PV domains Konrad Rzeszutek Wilk
2016-04-05 16:55 ` Andrew Cooper
2016-03-23 16:36 ` [PATCH v4 18/26] x86/domctl: Update PV domain cpumasks when setting cpuid policy Andrew Cooper
2016-03-24 17:04 ` Jan Beulich
2016-03-24 17:05 ` Andrew Cooper
2016-03-28 19:51 ` Konrad Rzeszutek Wilk
2016-03-23 16:36 ` [PATCH v4 19/26] xen+tools: Export maximum host and guest cpu featuresets via SYSCTL Andrew Cooper
2016-03-28 19:59 ` Konrad Rzeszutek Wilk
2016-03-23 16:36 ` [PATCH v4 20/26] tools/libxc: Modify bitmap operations to take void pointers Andrew Cooper
2016-03-28 20:05 ` Konrad Rzeszutek Wilk
2016-03-23 16:36 ` [PATCH v4 21/26] tools/libxc: Use public/featureset.h for cpuid policy generation Andrew Cooper
2016-03-28 20:07 ` Konrad Rzeszutek Wilk
2016-03-23 16:36 ` [PATCH v4 22/26] tools/libxc: Expose the automatically generated cpu featuremask information Andrew Cooper
2016-03-28 20:08 ` Konrad Rzeszutek Wilk
2016-03-23 16:36 ` [PATCH v4 23/26] tools: Utility for dealing with featuresets Andrew Cooper
2016-03-28 20:26 ` Konrad Rzeszutek Wilk
2016-03-23 16:36 ` [PATCH v4 24/26] tools/libxc: Wire a featureset through to cpuid policy logic Andrew Cooper
2016-03-28 20:39 ` Konrad Rzeszutek Wilk
2016-03-23 16:36 ` [PATCH v4 25/26] tools/libxc: Use featuresets rather than guesswork Andrew Cooper
2016-03-23 16:36 ` [PATCH v4 26/26] tools/libxc: Calculate xstate cpuid leaf from guest information Andrew Cooper
2016-03-24 17:20 ` Wei Liu
2016-03-31 7:48 ` Jan Beulich
2016-04-05 17:48 ` Andrew Cooper
2016-04-07 0:16 ` Jan Beulich
2016-04-07 0:40 ` Andrew Cooper
2016-04-07 0:56 ` Jan Beulich
2016-04-07 11:34 ` Andrew Cooper
2016-03-24 10:27 ` [PATCH v4 00/26] x86: Improvements to cpuid handling for guests Jan Beulich
2016-03-24 10:28 ` 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=1458750989-28967-18-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).