From: "Jan Beulich" <JBeulich@suse.com>
To: xen-devel <xen-devel@lists.xenproject.org>
Cc: George Dunlap <George.Dunlap@eu.citrix.com>,
Andrew Cooper <andrew.cooper3@citrix.com>,
Wei Liu <wei.liu2@citrix.com>,
Roger Pau Monne <roger.pau@citrix.com>
Subject: [PATCH 1/4] x86: suppress XPTI-related TLB flushes when possible
Date: Wed, 13 Mar 2019 06:38:08 -0600 [thread overview]
Message-ID: <5C88F9B0020000780021E177@prv1-mh.provo.novell.com> (raw)
In-Reply-To: <5C88F524020000780021E12C@prv1-mh.provo.novell.com>
When there's no XPTI-enabled PV domain at all, there's no need to issue
respective TLB flushes. Hardwire opt_xpti_* to false when !PV, and
record the creation of PV domains by bumping opt_xpti_* accordingly.
Signed-off-by: Jan Beulich <jbeulich@suse.com>
---
TBD: The hardwiring to false could be extended to opt_pv_l1tf_* and (for
!HVM) opt_l1d_flush as well.
--- a/xen/arch/x86/flushtlb.c
+++ b/xen/arch/x86/flushtlb.c
@@ -218,7 +218,7 @@ unsigned int flush_area_local(const void
*/
invpcid_flush_one(PCID_PV_PRIV, addr);
invpcid_flush_one(PCID_PV_USER, addr);
- if ( opt_xpti_hwdom || opt_xpti_domu )
+ if ( opt_xpti_hwdom > 1 || opt_xpti_domu > 1 )
{
invpcid_flush_one(PCID_PV_PRIV | PCID_PV_XPTI, addr);
invpcid_flush_one(PCID_PV_USER | PCID_PV_XPTI, addr);
--- a/xen/arch/x86/pv/domain.c
+++ b/xen/arch/x86/pv/domain.c
@@ -270,6 +270,9 @@ void pv_domain_destroy(struct domain *d)
destroy_perdomain_mapping(d, GDT_LDT_VIRT_START,
GDT_LDT_MBYTES << (20 - PAGE_SHIFT));
+ opt_xpti_hwdom -= IS_ENABLED(CONFIG_LATE_HWDOM) &&
+ !d->domain_id && opt_xpti_hwdom;
+
XFREE(d->arch.pv.cpuidmasks);
FREE_XENHEAP_PAGE(d->arch.pv.gdt_ldt_l1tab);
@@ -308,7 +311,16 @@ int pv_domain_initialise(struct domain *
/* 64-bit PV guest by default. */
d->arch.is_32bit_pv = d->arch.has_32bit_shinfo = 0;
- d->arch.pv.xpti = is_hardware_domain(d) ? opt_xpti_hwdom : opt_xpti_domu;
+ if ( is_hardware_domain(d) && opt_xpti_hwdom )
+ {
+ d->arch.pv.xpti = true;
+ ++opt_xpti_hwdom;
+ }
+ if ( !is_hardware_domain(d) && opt_xpti_domu )
+ {
+ d->arch.pv.xpti = true;
+ opt_xpti_domu = 2;
+ }
if ( !is_pv_32bit_domain(d) && use_invpcid && cpu_has_pcid )
switch ( ACCESS_ONCE(opt_pcid) )
--- a/xen/arch/x86/spec_ctrl.c
+++ b/xen/arch/x86/spec_ctrl.c
@@ -78,10 +78,12 @@ static int __init parse_spec_ctrl(const
opt_eager_fpu = 0;
+#ifdef CONFIG_PV
if ( opt_xpti_hwdom < 0 )
opt_xpti_hwdom = 0;
if ( opt_xpti_domu < 0 )
opt_xpti_domu = 0;
+#endif
if ( opt_smt < 0 )
opt_smt = 1;
@@ -607,6 +609,7 @@ static __init void l1tf_calculations(uin
: (3ul << (paddr_bits - 2))));
}
+#ifdef CONFIG_PV
int8_t __read_mostly opt_xpti_hwdom = -1;
int8_t __read_mostly opt_xpti_domu = -1;
@@ -673,6 +676,9 @@ static __init int parse_xpti(const char
return rc;
}
custom_param("xpti", parse_xpti);
+#else /* !CONFIG_PV */
+# define xpti_init_default(caps) ((void)(caps))
+#endif /* CONFIG_PV */
void __init init_speculation_mitigations(void)
{
--- a/xen/include/asm-x86/spec_ctrl.h
+++ b/xen/include/asm-x86/spec_ctrl.h
@@ -42,7 +42,12 @@ extern bool bsp_delay_spec_ctrl;
extern uint8_t default_xen_spec_ctrl;
extern uint8_t default_spec_ctrl_flags;
+#ifdef CONFIG_PV
extern int8_t opt_xpti_hwdom, opt_xpti_domu;
+#else
+# define opt_xpti_hwdom false
+# define opt_xpti_domu false
+#endif
extern int8_t opt_pv_l1tf_hwdom, opt_pv_l1tf_domu;
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel
next prev parent reply other threads:[~2019-03-13 12:38 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-03-13 12:18 [PATCH 0/4] x86: some further follow-up to recent XSAs Jan Beulich
2019-03-13 12:38 ` Jan Beulich [this message]
2019-04-03 18:52 ` [PATCH 1/4] x86: suppress XPTI-related TLB flushes when possible Andrew Cooper
2019-04-04 10:07 ` Jan Beulich
2019-03-13 12:38 ` [PATCH 2/4] x86: relax a few get_gfn() invocations Jan Beulich
2019-04-03 18:16 ` Andrew Cooper
2019-04-05 10:30 ` George Dunlap
2019-04-05 10:30 ` [Xen-devel] " George Dunlap
2019-04-05 10:52 ` Jan Beulich
2019-04-05 10:52 ` [Xen-devel] " Jan Beulich
2019-03-13 12:38 ` [PATCH 3/4] x86/mm: drop redundant local variable from _get_page_type() Jan Beulich
2019-04-03 18:17 ` Andrew Cooper
2019-04-05 10:37 ` George Dunlap
2019-04-05 10:37 ` [Xen-devel] " George Dunlap
2019-03-13 12:39 ` [PATCH 4/4] x86/PV: remove unnecessary toggle_guest_pt() overhead Jan Beulich
2019-04-03 18:32 ` Andrew Cooper
2019-04-04 9:42 ` Jan Beulich
[not found] ` <5C88F9F30200000000104057@prv1-mh.provo.novell.com>
[not found] ` <5C88F9F3020000780023294C@prv1-mh.provo.novell.com>
2019-05-27 9:25 ` Ping: " Jan Beulich
2019-05-27 9:25 ` [Xen-devel] " Jan Beulich
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=5C88F9B0020000780021E177@prv1-mh.provo.novell.com \
--to=jbeulich@suse.com \
--cc=George.Dunlap@eu.citrix.com \
--cc=andrew.cooper3@citrix.com \
--cc=roger.pau@citrix.com \
--cc=wei.liu2@citrix.com \
--cc=xen-devel@lists.xenproject.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.