All of lore.kernel.org
 help / color / mirror / Atom feed
From: Jeremy Fitzhardinge <jeremy@goop.org>
To: Ingo Molnar <mingo@elte.hu>
Cc: LKML <linux-kernel@vger.kernel.org>
Subject: [PATCH 1 of 5] xen: use hypercall rather than clts
Date: Fri, 23 May 2008 14:10:54 +0100	[thread overview]
Message-ID: <9fc73591d78e1adfc785.1211548254@localhost> (raw)
In-Reply-To: <patchbomb.1211548253@localhost>

Xen will trap and emulate clts, but its better to use a hypercall.
Also, xenner doesn't handle clts.

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
---
 arch/x86/xen/enlighten.c        |   28 ++++++++++++++++++++++++++--
 include/asm-x86/xen/hypercall.h |    7 +++++++
 2 files changed, 33 insertions(+), 2 deletions(-)

diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -607,6 +607,30 @@
 	xen_mc_issue(PARAVIRT_LAZY_MMU);
 }
 
+static void xen_clts(void)
+{
+	struct multicall_space mcs;
+
+	mcs = xen_mc_entry(0);
+
+	MULTI_fpu_taskswitch(mcs.mc, 0);
+
+	xen_mc_issue(PARAVIRT_LAZY_CPU);
+}
+
+static void xen_write_cr0(unsigned long cr0)
+{
+	struct multicall_space mcs;
+
+	/* Only pay attention to cr0.TS; everything else is
+	   ignored. */
+	mcs = xen_mc_entry(0);
+
+	MULTI_fpu_taskswitch(mcs.mc, (cr0 & X86_CR0_TS) != 0);
+
+	xen_mc_issue(PARAVIRT_LAZY_CPU);
+}
+
 static void xen_write_cr2(unsigned long cr2)
 {
 	x86_read_percpu(xen_vcpu)->arch.cr2 = cr2;
@@ -978,10 +1002,10 @@
 	.set_debugreg = xen_set_debugreg,
 	.get_debugreg = xen_get_debugreg,
 
-	.clts = native_clts,
+	.clts = xen_clts,
 
 	.read_cr0 = native_read_cr0,
-	.write_cr0 = native_write_cr0,
+	.write_cr0 = xen_write_cr0,
 
 	.read_cr4 = native_read_cr4,
 	.read_cr4_safe = native_read_cr4_safe,
diff --git a/include/asm-x86/xen/hypercall.h b/include/asm-x86/xen/hypercall.h
--- a/include/asm-x86/xen/hypercall.h
+++ b/include/asm-x86/xen/hypercall.h
@@ -315,6 +315,13 @@
 }
 
 static inline void
+MULTI_fpu_taskswitch(struct multicall_entry *mcl, int set)
+{
+	mcl->op = __HYPERVISOR_fpu_taskswitch;
+	mcl->args[0] = set;
+}
+
+static inline void
 MULTI_update_va_mapping(struct multicall_entry *mcl, unsigned long va,
 			pte_t new_val, unsigned long flags)
 {



  reply	other threads:[~2008-05-23 13:13 UTC|newest]

Thread overview: 6+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2008-05-23 13:10 [PATCH 0 of 5] xen+x86: misc fixes Jeremy Fitzhardinge
2008-05-23 13:10 ` Jeremy Fitzhardinge [this message]
2008-05-23 13:10 ` [PATCH 2 of 5] xen: use new sched_op Jeremy Fitzhardinge
2008-05-23 13:10 ` [PATCH 3 of 5] x86: use symbolic constant in stts() Jeremy Fitzhardinge
2008-05-23 13:10 ` [PATCH 4 of 5] xen: allow some cr4 updates Jeremy Fitzhardinge
2008-05-23 13:10 ` [PATCH 5 of 5] xen: don't worry about preempt during xen_irq_enable() Jeremy Fitzhardinge

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=9fc73591d78e1adfc785.1211548254@localhost \
    --to=jeremy@goop.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@elte.hu \
    /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.