xen-devel.lists.xenproject.org archive mirror
 help / color / mirror / Atom feed
From: Boris Ostrovsky <boris.ostrovsky@oracle.com>
To: xen-devel@lists.xen.org
Cc: jun.nakajima@intel.com, JBeulich@suse.com,
	George.Dunlap@eu.citrix.com, jacob.shin@amd.com,
	eddie.dong@intel.com, dietmar.hahn@ts.fujitsu.com,
	suravee.suthikulpanit@amd.com,
	Boris Ostrovsky <boris.ostrovsky@oracle.com>
Subject: [PATCH v2 03/13] x86/PMU: Stop AMD counters when called from vpmu_save_force()
Date: Fri, 20 Sep 2013 05:42:02 -0400	[thread overview]
Message-ID: <1379670132-1748-4-git-send-email-boris.ostrovsky@oracle.com> (raw)
In-Reply-To: <1379670132-1748-1-git-send-email-boris.ostrovsky@oracle.com>

Change amd_vpmu_save() algorithm to accommodate cases when we need
to stop counters from vpmu_save_force() (needed by subsequent PMU
patches).

Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
---
 xen/arch/x86/hvm/svm/vpmu.c | 14 ++++----------
 xen/arch/x86/hvm/vpmu.c     | 12 ++++++------
 2 files changed, 10 insertions(+), 16 deletions(-)

diff --git a/xen/arch/x86/hvm/svm/vpmu.c b/xen/arch/x86/hvm/svm/vpmu.c
index 4d1fbc8..5d9c3f5 100644
--- a/xen/arch/x86/hvm/svm/vpmu.c
+++ b/xen/arch/x86/hvm/svm/vpmu.c
@@ -223,22 +223,16 @@ static int amd_vpmu_save(struct vcpu *v)
     struct amd_vpmu_context *ctx = vpmu->context;
     unsigned int i;
 
-    /*
-     * Stop the counters. If we came here via vpmu_save_force (i.e.
-     * when VPMU_CONTEXT_SAVE is set) counters are already stopped.
-     */
-    if ( !vpmu_is_set(vpmu, VPMU_CONTEXT_SAVE) )
+    if ( !vpmu_is_set(vpmu, VPMU_FROZEN) )
     {
-        vpmu_set(vpmu, VPMU_FROZEN);
-
         for ( i = 0; i < num_counters; i++ )
             wrmsrl(ctrls[i], 0);
 
-        return 0;
+        vpmu_set(vpmu, VPMU_FROZEN);
     }
 
-    if ( !vpmu_is_set(vpmu, VPMU_CONTEXT_LOADED) )
-        return 0;
+    if ( !vpmu_is_set(vpmu, VPMU_CONTEXT_SAVE) )
+            return 0;
 
     context_save(v);
 
diff --git a/xen/arch/x86/hvm/vpmu.c b/xen/arch/x86/hvm/vpmu.c
index 21fbaba..a4e3664 100644
--- a/xen/arch/x86/hvm/vpmu.c
+++ b/xen/arch/x86/hvm/vpmu.c
@@ -127,13 +127,19 @@ static void vpmu_save_force(void *arg)
     struct vcpu *v = (struct vcpu *)arg;
     struct vpmu_struct *vpmu = vcpu_vpmu(v);
 
+    if ( !vpmu_is_set(vpmu, VPMU_CONTEXT_ALLOCATED) )
+        return;
+
     if ( !vpmu_is_set(vpmu, VPMU_CONTEXT_LOADED) )
         return;
 
+    vpmu_set(vpmu, VPMU_CONTEXT_SAVE);
+
     if ( vpmu->arch_vpmu_ops )
         (void)vpmu->arch_vpmu_ops->arch_vpmu_save(v);
 
     vpmu_reset(vpmu, VPMU_CONTEXT_SAVE);
+    vpmu_reset(vpmu, VPMU_CONTEXT_LOADED);
 
     per_cpu(last_vcpu, smp_processor_id()) = NULL;
 }
@@ -177,12 +183,8 @@ void vpmu_load(struct vcpu *v)
          * before saving the context.
          */
         if ( vpmu_is_set(vpmu, VPMU_CONTEXT_LOADED) )
-        {
-            vpmu_set(vpmu, VPMU_CONTEXT_SAVE);
             on_selected_cpus(cpumask_of(vpmu->last_pcpu),
                              vpmu_save_force, (void *)v, 1);
-            vpmu_reset(vpmu, VPMU_CONTEXT_LOADED);
-        }
     } 
 
     /* Prevent forced context save from remote CPU */
@@ -195,9 +197,7 @@ void vpmu_load(struct vcpu *v)
         vpmu = vcpu_vpmu(prev);
 
         /* Someone ran here before us */
-        vpmu_set(vpmu, VPMU_CONTEXT_SAVE);
         vpmu_save_force(prev);
-        vpmu_reset(vpmu, VPMU_CONTEXT_LOADED);
 
         vpmu = vcpu_vpmu(v);
     }
-- 
1.8.1.4

  parent reply	other threads:[~2013-09-20  9:42 UTC|newest]

Thread overview: 51+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-09-20  9:41 [PATCH v2 00/13] x86/PMU: Xen PMU PV support Boris Ostrovsky
2013-09-20  9:42 ` [PATCH v2 01/13] Export hypervisor symbols Boris Ostrovsky
2013-09-23 19:42   ` Konrad Rzeszutek Wilk
2013-09-23 20:06     ` Boris Ostrovsky
2013-09-24 17:40       ` Konrad Rzeszutek Wilk
2013-09-25 13:15   ` Jan Beulich
2013-09-25 14:03     ` Boris Ostrovsky
2013-09-25 14:53       ` Jan Beulich
2013-09-20  9:42 ` [PATCH v2 02/13] Set VCPU's is_running flag closer to when the VCPU is dispatched Boris Ostrovsky
2013-09-25 13:42   ` Jan Beulich
2013-09-25 14:08     ` Keir Fraser
2013-09-20  9:42 ` Boris Ostrovsky [this message]
2013-09-20  9:42 ` [PATCH v2 04/13] x86/VPMU: Minor VPMU cleanup Boris Ostrovsky
2013-09-20  9:42 ` [PATCH v2 05/13] intel/VPMU: Clean up Intel VPMU code Boris Ostrovsky
2013-09-23 11:42   ` Dietmar Hahn
2013-09-23 19:46   ` Konrad Rzeszutek Wilk
2013-09-25 13:55   ` Jan Beulich
2013-09-25 14:39     ` Boris Ostrovsky
2013-09-25 14:57       ` Jan Beulich
2013-09-25 15:37         ` Boris Ostrovsky
2013-09-20  9:42 ` [PATCH v2 06/13] x86/PMU: Add public xenpmu.h Boris Ostrovsky
2013-09-23 13:04   ` Dietmar Hahn
2013-09-23 13:16     ` Jan Beulich
2013-09-23 14:00       ` Boris Ostrovsky
2013-09-23 13:45     ` Boris Ostrovsky
2013-09-25 14:04   ` Jan Beulich
2013-09-25 15:59     ` Boris Ostrovsky
2013-09-25 16:08       ` Jan Beulich
2013-09-30 13:25     ` Boris Ostrovsky
2013-09-30 13:30       ` Jan Beulich
2013-09-30 13:55         ` Boris Ostrovsky
2013-09-20  9:42 ` [PATCH v2 07/13] x86/PMU: Make vpmu not HVM-specific Boris Ostrovsky
2013-09-25 14:05   ` Jan Beulich
2013-09-25 14:49     ` Boris Ostrovsky
2013-09-25 14:57       ` Jan Beulich
2013-09-20  9:42 ` [PATCH v2 08/13] x86/PMU: Interface for setting PMU mode and flags Boris Ostrovsky
2013-09-25 14:11   ` Jan Beulich
2013-09-25 14:55     ` Boris Ostrovsky
2013-09-20  9:42 ` [PATCH v2 09/13] x86/PMU: Initialize PMU for PV guests Boris Ostrovsky
2013-09-20  9:42 ` [PATCH v2 10/13] x86/PMU: Add support for PMU registes handling on " Boris Ostrovsky
2013-09-23 13:50   ` Dietmar Hahn
2013-09-25 14:23   ` Jan Beulich
2013-09-25 15:03     ` Boris Ostrovsky
2013-09-20  9:42 ` [PATCH v2 11/13] x86/PMU: Handle PMU interrupts for " Boris Ostrovsky
2013-09-25 14:33   ` Jan Beulich
2013-09-25 14:40     ` Andrew Cooper
2013-09-25 15:52       ` Boris Ostrovsky
2013-09-25 15:19     ` Boris Ostrovsky
2013-09-25 15:25       ` Jan Beulich
2013-09-20  9:42 ` [PATCH v2 12/13] x86/PMU: Save VPMU state for PV guests during context switch Boris Ostrovsky
2013-09-20  9:42 ` [PATCH v2 13/13] x86/PMU: Move vpmu files up from hvm directory Boris Ostrovsky

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=1379670132-1748-4-git-send-email-boris.ostrovsky@oracle.com \
    --to=boris.ostrovsky@oracle.com \
    --cc=George.Dunlap@eu.citrix.com \
    --cc=JBeulich@suse.com \
    --cc=dietmar.hahn@ts.fujitsu.com \
    --cc=eddie.dong@intel.com \
    --cc=jacob.shin@amd.com \
    --cc=jun.nakajima@intel.com \
    --cc=suravee.suthikulpanit@amd.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).