From: Jeremy Fitzhardinge <jeremy@goop.org>
To: Alex Nixon <alex.nixon@citrix.com>
Cc: Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
Ingo Molnar <mingo@elte.hu>
Subject: Re: [PATCH 2/7] x86/paravirt: Add paravirt hook for wbinvd_halt
Date: Thu, 21 Aug 2008 11:16:52 -0700 [thread overview]
Message-ID: <48ADB114.2000304@goop.org> (raw)
In-Reply-To: <1219341888-23191-2-git-send-email-alex.nixon@citrix.com>
Alex Nixon wrote:
> The native case of wb_invd_halt uses inline asm to ensure the compiler doesn't reorder the sequence of instructions, which has the side-effect of skirting around the paravirt hooks for those instructions. Thus, create a new hook for this case.
>
Not necessary. Halting in Xen doesn't require the caches to be flushed
in this way, and I think that would be true for any virtual environment
(and if it were, the invalidate/halt instruction sequence would work
anyway).
The correct fix is to make sure that the native_play_dead calls this,
but the xen_play_dead doesn't (ie, make sure it's not in the common code
path).
J
> Signed-off-by: Alex Nixon <alex.nixon@citrix.com>
> Cc: Jeremy Fitzhardinge <jeremy@goop.org>
> Cc: Ingo Molnar <mingo@elte.hu>
> ---
> arch/x86/kernel/paravirt.c | 1 +
> include/asm-x86/paravirt.h | 6 ++++++
> include/asm-x86/processor.h | 3 ++-
> 3 files changed, 9 insertions(+), 1 deletions(-)
>
> diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
> index 8ffe4d1..66d6d0d 100644
> --- a/arch/x86/kernel/paravirt.c
> +++ b/arch/x86/kernel/paravirt.c
> @@ -299,6 +299,7 @@ struct pv_irq_ops pv_irq_ops = {
> .restore_fl = native_restore_fl,
> .irq_disable = native_irq_disable,
> .irq_enable = native_irq_enable,
> + .wbinvd_halt = native_wbinvd_halt,
> .safe_halt = native_safe_halt,
> .halt = native_halt,
> #ifdef CONFIG_X86_64
> diff --git a/include/asm-x86/paravirt.h b/include/asm-x86/paravirt.h
> index fd922c3..5360f3f 100644
> --- a/include/asm-x86/paravirt.h
> +++ b/include/asm-x86/paravirt.h
> @@ -194,6 +194,7 @@ struct pv_irq_ops {
> void (*restore_fl)(unsigned long);
> void (*irq_disable)(void);
> void (*irq_enable)(void);
> + void (*wbinvd_halt)(void);
> void (*safe_halt)(void);
> void (*halt)(void);
>
> @@ -716,6 +717,11 @@ static inline void raw_safe_halt(void)
> PVOP_VCALL0(pv_irq_ops.safe_halt);
> }
>
> +static inline void wbinvd_halt(void)
> +{
> + PVOP_VCALL0(pv_irq_ops.wbinvd_halt);
> +}
> +
> static inline void halt(void)
> {
> PVOP_VCALL0(pv_irq_ops.safe_halt);
> diff --git a/include/asm-x86/processor.h b/include/asm-x86/processor.h
> index bcfc727..75db315 100644
> --- a/include/asm-x86/processor.h
> +++ b/include/asm-x86/processor.h
> @@ -558,6 +558,7 @@ static inline void load_sp0(struct tss_struct *tss,
> native_load_sp0(tss, thread);
> }
>
> +#define wbinvd_halt native_wbinvd_halt
> #define set_iopl_mask native_set_iopl_mask
> #endif /* CONFIG_PARAVIRT */
>
> @@ -733,7 +734,7 @@ extern unsigned long idle_nomwait;
> *
> * Systems without cache can just go into halt.
> */
> -static inline void wbinvd_halt(void)
> +static inline void native_wbinvd_halt(void)
> {
> mb();
> /* check for clflush to determine if wbinvd is legal */
>
next prev parent reply other threads:[~2008-08-21 18:17 UTC|newest]
Thread overview: 10+ messages / expand[flat|nested] mbox.gz Atom feed top
2008-08-21 18:04 [PATCH 1/7] x86/paravirt: Add hooks for CPU hotplugging Alex Nixon
2008-08-21 18:04 ` [PATCH 2/7] x86/paravirt: Add paravirt hook for wbinvd_halt Alex Nixon
2008-08-21 18:04 ` [PATCH 3/7] Xen: Add Xen implementation of wbinvd_halt Alex Nixon
2008-08-21 18:04 ` [PATCH 4/7] x86_32: Clean up play_dead Alex Nixon
2008-08-21 18:04 ` [PATCH 5/7] x86: Unify x86_32 and x86_64 play_dead into one function Alex Nixon
2008-08-21 18:04 ` [PATCH 6/7] x86: Separate generic cpu disabling code from APIC writes in cpu_disable Alex Nixon
2008-08-21 18:04 ` [PATCH 7/7] Xen: Implement CPU hotplugging Alex Nixon
2008-08-21 18:37 ` Jeremy Fitzhardinge
2008-08-21 18:16 ` Jeremy Fitzhardinge [this message]
2008-08-21 18:19 ` [PATCH 1/7] x86/paravirt: Add hooks for " 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=48ADB114.2000304@goop.org \
--to=jeremy@goop.org \
--cc=alex.nixon@citrix.com \
--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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox