kvm.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Andy Lutomirski <luto@kernel.org>
To: x86@kernel.org
Cc: Borislav Petkov <bp@suse.de>,
	Peter Zijlstra <peterz@infradead.org>,
	John Stultz <john.stultz@linaro.org>,
	linux-kernel@vger.kernel.org, Len Brown <lenb@kernel.org>,
	Huang Rui <ray.huang@amd.com>,
	Denys Vlasenko <dvlasenk@redhat.com>,
	kvm@vger.kernel.org, Ralf Baechle <ralf@linux-mips.org>,
	Andy Lutomirski <luto@kernel.org>,
	Paolo Bonzini <pbonzini@redhat.com>,
	Radim Krcmar <rkrcmar@redhat.com>,
	Marcelo Tosatti <mtosatti@redhat.com>
Subject: [PATCH v3 17/18] x86/kvm/tsc: Drop extra barrier and use rdtsc_ordered in kvmclock
Date: Tue, 16 Jun 2015 17:36:05 -0700	[thread overview]
Message-ID: <678981cc4761fb38a793c217c9cac42503cf3719.1434501121.git.luto@kernel.org> (raw)
In-Reply-To: <cover.1434501120.git.luto@kernel.org>
In-Reply-To: <cover.1434501120.git.luto@kernel.org>

__pvclock_read_cycles had an unnecessary barrier.  Get rid of that
barrier and clean up the code by just using rdtsc_ordered().

Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Radim Krcmar <rkrcmar@redhat.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Cc: kvm@vger.kernel.org
Signed-off-by: Andy Lutomirski <luto@kernel.org>
---

I'm hoping to get an ack for this to go in through -tip.  (Arguably
I'm the maintainer of this code given how it's used, but I should
still ask for an ack.)

arch/x86/include/asm/pvclock.h | 21 ++++++++++++---------
 1 file changed, 12 insertions(+), 9 deletions(-)

diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h
index 6084bce345fc..cf2329ca4812 100644
--- a/arch/x86/include/asm/pvclock.h
+++ b/arch/x86/include/asm/pvclock.h
@@ -62,7 +62,18 @@ static inline u64 pvclock_scale_delta(u64 delta, u32 mul_frac, int shift)
 static __always_inline
 u64 pvclock_get_nsec_offset(const struct pvclock_vcpu_time_info *src)
 {
-	u64 delta = rdtsc() - src->tsc_timestamp;
+	/*
+	 * Note: emulated platforms which do not advertise SSE2 support
+	 * break rdtsc_ordered, resulting in kvmclock not using the
+	 * necessary RDTSC barriers.  Without barriers, it is possible
+	 * that RDTSC instruction is executed before prior loads,
+	 * resulting in violation of monotonicity.
+	 *
+	 * On an SMP guest without SSE2, it's unclear how anything is
+	 * supposed to work correctly, though -- memory fences
+	 * (e.g. smp_mb) are important for more than just timing.
+	 */
+	u64 delta = rdtsc_ordered() - src->tsc_timestamp;
 	return pvclock_scale_delta(delta, src->tsc_to_system_mul,
 				   src->tsc_shift);
 }
@@ -76,17 +87,9 @@ unsigned __pvclock_read_cycles(const struct pvclock_vcpu_time_info *src,
 	u8 ret_flags;
 
 	version = src->version;
-	/* Note: emulated platforms which do not advertise SSE2 support
-	 * result in kvmclock not using the necessary RDTSC barriers.
-	 * Without barriers, it is possible that RDTSC instruction reads from
-	 * the time stamp counter outside rdtsc_barrier protected section
-	 * below, resulting in violation of monotonicity.
-	 */
-	rdtsc_barrier();
 	offset = pvclock_get_nsec_offset(src);
 	ret = src->system_time + offset;
 	ret_flags = src->flags;
-	rdtsc_barrier();
 
 	*cycles = ret;
 	*flags = ret_flags;
-- 
2.4.2


  parent reply	other threads:[~2015-06-17  0:37 UTC|newest]

Thread overview: 57+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-06-17  0:35 [PATCH v3 00/18] x86/tsc: Clean up rdtsc helpers Andy Lutomirski
2015-06-17  0:35 ` [PATCH v3 01/18] x86/tsc: Inline native_read_tsc and remove __native_read_tsc Andy Lutomirski
2015-06-17  9:26   ` Borislav Petkov
2015-07-06 15:39   ` [tip:x86/asm] x86/asm/tsc: Inline native_read_tsc() and remove __native_read_tsc() tip-bot for Andy Lutomirski
2015-06-17  0:35 ` [PATCH v3 02/18] x86/msr/kvm: Remove vget_cycles() Andy Lutomirski
2015-06-17  9:42   ` Borislav Petkov
2015-06-17 13:34   ` Paolo Bonzini
2015-07-06 15:40   ` [tip:x86/asm] x86/asm/tsc, kvm: " tip-bot for Andy Lutomirski
2015-06-17  0:35 ` [PATCH v3 03/18] x86/tsc/paravirt: Remove the read_tsc and read_tscp paravirt hooks Andy Lutomirski
2015-06-17  9:56   ` Borislav Petkov
2015-06-19 15:32   ` Borislav Petkov
2015-06-19 16:14     ` Andy Lutomirski
2015-06-19 17:13       ` Borislav Petkov
2015-07-06 15:40   ` [tip:x86/asm] x86/asm/tsc, x86/paravirt: Remove read_tsc() and read_tscp() " tip-bot for Andy Lutomirski
2015-06-17  0:35 ` [PATCH v3 04/18] x86/tsc: Replace rdtscll with native_read_tsc Andy Lutomirski
2015-06-17 10:03   ` Borislav Petkov
2015-07-06 15:40   ` [tip:x86/asm] x86/asm/tsc: Replace rdtscll() with native_read_tsc () tip-bot for Andy Lutomirski
2015-06-17  0:35 ` [PATCH v3 05/18] x86/tsc: Remove the rdtscp and rdtscpll macros Andy Lutomirski
2015-07-06 15:41   ` [tip:x86/asm] x86/asm/tsc: Remove the rdtscp() and rdtscpll() macros tip-bot for Andy Lutomirski
2015-06-17  0:35 ` [PATCH v3 06/18] x86/tsc: Use the full 64-bit tsc in tsc_delay Andy Lutomirski
2015-07-06 15:41   ` [tip:x86/asm] x86/asm/tsc: Use the full 64-bit TSC in delay_tsc() tip-bot for Andy Lutomirski
2015-06-17  0:35 ` [PATCH v3 07/18] x86/cpu/amd: Use the full 64-bit TSC to detect the 2.6.2 bug Andy Lutomirski
2015-07-06 15:41   ` [tip:x86/asm] x86/asm/tsc, " tip-bot for Andy Lutomirski
2015-06-17  0:35 ` [PATCH v3 08/18] baycom_epp: Replace rdtscl() with native_read_tsc() Andy Lutomirski
2015-06-17  0:49   ` Thomas Sailer
2015-06-20 13:54   ` walter harms
2015-06-20 14:14     ` Thomas Gleixner
2015-06-20 14:26       ` Andy Lutomirski
2015-06-20 16:30         ` Thomas Gleixner
2015-07-06 15:42   ` [tip:x86/asm] x86/asm/tsc, drivers/net/hamradio/baycom_epp: " tip-bot for Andy Lutomirski
2015-06-17  0:35 ` [PATCH v3 09/18] staging/lirc_serial: Remove TSC-based timing Andy Lutomirski
2015-07-06 15:42   ` [tip:x86/asm] x86/asm/tsc, " tip-bot for Andy Lutomirski
2015-06-17  0:35 ` [PATCH v3 10/18] input/joystick/analog: Switch from rdtscl() to native_read_tsc() Andy Lutomirski
2015-07-06 15:42   ` [tip:x86/asm] x86/asm/tsc, " tip-bot for Andy Lutomirski
2015-06-17  0:35 ` [PATCH v3 11/18] drivers/input/gameport: Replace rdtscl() with native_read_tsc() Andy Lutomirski
2015-07-06 15:43   ` [tip:x86/asm] x86/asm/tsc, drivers/input/gameport: Replace rdtscl () " tip-bot for Andy Lutomirski
2015-06-17  0:36 ` [PATCH v3 12/18] x86/tsc: Remove rdtscl() Andy Lutomirski
2015-07-06 15:43   ` [tip:x86/asm] x86/asm/tsc: " tip-bot for Andy Lutomirski
2015-06-17  0:36 ` [PATCH v3 13/18] x86/tsc: Rename native_read_tsc() to rdtsc() Andy Lutomirski
2015-06-24 21:38   ` Borislav Petkov
2015-07-06 15:43   ` [tip:x86/asm] x86/asm/tsc: " tip-bot for Andy Lutomirski
2015-06-17  0:36 ` [PATCH v3 14/18] x86: Add rdtsc_ordered() and use it in trivial call sites Andy Lutomirski
2015-07-06 15:44   ` [tip:x86/asm] x86/asm/tsc: " tip-bot for Andy Lutomirski
2015-08-21  7:45   ` [tip:x86/asm] x86/asm/tsc: Add rdtscll() merge helper tip-bot for Ingo Molnar
2015-06-17  0:36 ` [PATCH v3 15/18] x86/tsc: Use rdtsc_ordered() in check_tsc_warp() and drop extra barriers Andy Lutomirski
2015-07-06 15:44   ` [tip:x86/asm] x86/asm/tsc/sync: " tip-bot for Andy Lutomirski
2015-06-17  0:36 ` [PATCH v3 16/18] x86/tsc: In read_tsc, use rdtsc_ordered() instead of get_cycles() Andy Lutomirski
2015-07-06 15:44   ` [tip:x86/asm] x86/asm/tsc: Use rdtsc_ordered() in read_tsc() " tip-bot for Andy Lutomirski
2015-06-17  0:36 ` Andy Lutomirski [this message]
2015-06-17  7:47   ` [PATCH v3 17/18] x86/kvm/tsc: Drop extra barrier and use rdtsc_ordered in kvmclock Paolo Bonzini
2015-06-17 13:31     ` Paolo Bonzini
2015-06-20 21:50     ` Borislav Petkov
2015-07-06 15:45   ` [tip:x86/asm] x86/asm/tsc, x86/kvm: Drop open-coded barrier and use rdtsc_ordered() " tip-bot for Andy Lutomirski
2015-06-17  0:36 ` [PATCH v3 18/18] x86/tsc: Remove rdtsc_barrier() Andy Lutomirski
2015-07-06 15:45   ` [tip:x86/asm] x86/asm/tsc: " tip-bot for Andy Lutomirski
2015-06-17 11:11 ` [PATCH v3 00/18] x86/tsc: Clean up rdtsc helpers Borislav Petkov
2015-06-17 13:37   ` Paolo Bonzini

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=678981cc4761fb38a793c217c9cac42503cf3719.1434501121.git.luto@kernel.org \
    --to=luto@kernel.org \
    --cc=bp@suse.de \
    --cc=dvlasenk@redhat.com \
    --cc=john.stultz@linaro.org \
    --cc=kvm@vger.kernel.org \
    --cc=lenb@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mtosatti@redhat.com \
    --cc=pbonzini@redhat.com \
    --cc=peterz@infradead.org \
    --cc=ralf@linux-mips.org \
    --cc=ray.huang@amd.com \
    --cc=rkrcmar@redhat.com \
    --cc=x86@kernel.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).