xen-devel.lists.xenproject.org archive mirror
 help / color / mirror / Atom feed
From: Andrew Cooper <andrew.cooper3@citrix.com>
To: Xen-devel <xen-devel@lists.xen.org>
Cc: Andrew Cooper <andrew.cooper3@citrix.com>,
	Kevin Tian <kevin.tian@intel.com>,
	Jun Nakajima <jun.nakajima@intel.com>,
	Jan Beulich <JBeulich@suse.com>
Subject: [PATCH 2/3] x86/vmx: Don't self-recurse in vmx_update_guest_cr()
Date: Fri, 29 Sep 2017 19:31:02 +0100	[thread overview]
Message-ID: <1506709863-12291-3-git-send-email-andrew.cooper3@citrix.com> (raw)
In-Reply-To: <1506709863-12291-1-git-send-email-andrew.cooper3@citrix.com>

An update to CR4 following a CR0 update can be done easily by falling
through into the CR4 case.  This avoids unnecessary passes through
vmx_vmcs_{enter,exit}() and unnecessary stack usage (as the compiler
cannot optimise this use to a tailcall).

Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
---
CC: Jan Beulich <JBeulich@suse.com>
CC: Jun Nakajima <jun.nakajima@intel.com>
CC: Kevin Tian <kevin.tian@intel.com>
---
 xen/arch/x86/hvm/vmx/vmx.c | 40 ++++++++++++++++++----------------------
 1 file changed, 18 insertions(+), 22 deletions(-)

diff --git a/xen/arch/x86/hvm/vmx/vmx.c b/xen/arch/x86/hvm/vmx/vmx.c
index 61047e0..5b943d4 100644
--- a/xen/arch/x86/hvm/vmx/vmx.c
+++ b/xen/arch/x86/hvm/vmx/vmx.c
@@ -1627,29 +1627,8 @@ static void vmx_update_guest_cr(struct vcpu *v, unsigned int cr)
         v->arch.hvm_vcpu.hw_cr[0] =
             v->arch.hvm_vcpu.guest_cr[0] | hw_cr0_mask;
         __vmwrite(GUEST_CR0, v->arch.hvm_vcpu.hw_cr[0]);
-
-        /* Changing CR0 can change some bits in real CR4. */
-        vmx_update_guest_cr(v, 4);
-        break;
     }
-
-    case 2:
-        /* CR2 is updated in exit stub. */
-        break;
-
-    case 3:
-        if ( paging_mode_hap(v->domain) )
-        {
-            if ( !hvm_paging_enabled(v) && !vmx_unrestricted_guest(v) )
-                v->arch.hvm_vcpu.hw_cr[3] =
-                    v->domain->arch.hvm_domain.params[HVM_PARAM_IDENT_PT];
-            vmx_load_pdptrs(v);
-        }
-
-        __vmwrite(GUEST_CR3, v->arch.hvm_vcpu.hw_cr[3]);
-        hvm_asid_flush_vcpu(v);
-        break;
-
+        /* Fallthrough: Changing CR0 can change some bits in real CR4. */
     case 4:
         v->arch.hvm_vcpu.hw_cr[4] = HVM_CR4_HOST_MASK;
         if ( paging_mode_hap(v->domain) )
@@ -1681,6 +1660,23 @@ static void vmx_update_guest_cr(struct vcpu *v, unsigned int cr)
         __vmwrite(GUEST_CR4, v->arch.hvm_vcpu.hw_cr[4]);
         break;
 
+    case 2:
+        /* CR2 is updated in exit stub. */
+        break;
+
+    case 3:
+        if ( paging_mode_hap(v->domain) )
+        {
+            if ( !hvm_paging_enabled(v) && !vmx_unrestricted_guest(v) )
+                v->arch.hvm_vcpu.hw_cr[3] =
+                    v->domain->arch.hvm_domain.params[HVM_PARAM_IDENT_PT];
+            vmx_load_pdptrs(v);
+        }
+
+        __vmwrite(GUEST_CR3, v->arch.hvm_vcpu.hw_cr[3]);
+        hvm_asid_flush_vcpu(v);
+        break;
+
     default:
         BUG();
     }
-- 
2.1.4


_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel

  parent reply	other threads:[~2017-09-29 18:31 UTC|newest]

Thread overview: 12+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-09-29 18:31 [PATCH 0/3] x86/vmx: Minor improvements to vmx_update_guest_cr() Andrew Cooper
2017-09-29 18:31 ` [PATCH 1/3] x86/vmx: Misc cleanup " Andrew Cooper
2017-10-03 11:53   ` Roger Pau Monné
2017-10-10  5:25   ` Tian, Kevin
2017-09-29 18:31 ` Andrew Cooper [this message]
2017-10-03 12:01   ` [PATCH 2/3] x86/vmx: Don't self-recurse in vmx_update_guest_cr() Roger Pau Monné
2017-10-10  5:26   ` Tian, Kevin
2017-09-29 18:31 ` [PATCH 3/3] x86/vmx: Better description of CR4 settings outside of paged mode Andrew Cooper
2017-10-03 14:04   ` Roger Pau Monné
2017-10-03 14:12     ` Andrew Cooper
2017-10-03 15:12       ` Roger Pau Monné
2017-10-10  5:31   ` Tian, Kevin

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=1506709863-12291-3-git-send-email-andrew.cooper3@citrix.com \
    --to=andrew.cooper3@citrix.com \
    --cc=JBeulich@suse.com \
    --cc=jun.nakajima@intel.com \
    --cc=kevin.tian@intel.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).