All of lore.kernel.org
 help / color / mirror / Atom feed
From: David Vrabel <david.vrabel@citrix.com>
To: David Vrabel <david.vrabel@citrix.com>, Jan Beulich <JBeulich@suse.com>
Cc: xen-devel@lists.xenproject.org, Keir Fraser <keir@xen.org>,
	Ian Campbell <ian.campbell@citrix.com>, Tim Deegan <tim@xen.org>
Subject: Re: [PATCHv9 3/4] gnttab: make the grant table lock a read-write lock
Date: Thu, 21 May 2015 15:20:39 +0100	[thread overview]
Message-ID: <555DE9B7.6040407@citrix.com> (raw)
In-Reply-To: <555DDF4E.7030508@citrix.com>

On 21/05/15 14:36, David Vrabel wrote:
> On 21/05/15 11:32, Jan Beulich wrote:
>>>>> On 20.05.15 at 17:54, <david.vrabel@citrix.com> wrote:
>>> @@ -842,8 +845,6 @@ __gnttab_map_grant_ref(
>>>      mt->ref   = op->ref;
>>>      mt->flags = op->flags;
>>>  
>>> -    double_gt_unlock(lgt, rgt);
>>
>> Don't the mt-> updates above need some kind of protection?
> 
> It depends:
> 
> If not gnttab_need_iommu_mapping() but we only need a write barrier
> before the mt->flags store.
> 
> If gnttab_need_iommu_mapping() then a lock is required to prevent racing
> with concurrent mapcount() calls.  This is not a path I care about so
> its easiest to just keep the double lock around this.

Like so:

@@ -806,12 +806,13 @@ __gnttab_map_grant_ref(
         goto undo_out;
     }

-    double_gt_lock(lgt, rgt);
-
     if ( gnttab_need_iommu_mapping(ld) )
     {
         unsigned int wrc, rdc;
         int err = 0;
+
+        double_gt_lock(lgt, rgt);
+
         /* We're not translated, so we know that gmfns and mfns are
            the same things, so the IOMMU entry is always 1-to-1. */
         mapcount(lgt, rd, frame, &wrc, &rdc);
@@ -837,12 +838,22 @@ __gnttab_map_grant_ref(

     TRACE_1D(TRC_MEM_PAGE_GRANT_MAP, op->dom);

+    /*
+     * All maptrack entry users check mt->flags first before using the
+     * other fields so just ensure the flags field is stored last.
+     *
+     * However, if gnttab_need_iommu_mapping() then this would race
+     * with a concurrent mapcount() call (on an unmap, for example)
+     * and a lock is required.
+     */
     mt = &maptrack_entry(lgt, handle);
     mt->domid = op->dom;
     mt->ref   = op->ref;
-    mt->flags = op->flags;
+    wmb();
+    write_atomic(&mt->flags, op->flags);

-    double_gt_unlock(lgt, rgt);
+    if ( gnttab_need_iommu_mapping(ld) )
+        double_gt_unlock(lgt, rgt);

     op->dev_bus_addr = (u64)frame << PAGE_SHIFT;
     op->handle       = handle;

David

  reply	other threads:[~2015-05-21 14:20 UTC|newest]

Thread overview: 15+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-05-20 15:54 [PATCHv9 0/3] gnttab: Improve scaleability David Vrabel
2015-05-20 15:54 ` [PATCHv9 1/4] gnttab: per-active entry locking David Vrabel
2015-05-21  7:46   ` Jan Beulich
2015-05-21 14:11     ` David Vrabel
2015-05-20 15:54 ` [PATCHv9 2/4] gnttab: introduce maptrack lock David Vrabel
2015-05-20 15:54 ` [PATCHv9 3/4] gnttab: make the grant table lock a read-write lock David Vrabel
2015-05-21 10:32   ` Jan Beulich
2015-05-21 13:36     ` David Vrabel
2015-05-21 14:20       ` David Vrabel [this message]
2015-05-21 14:53       ` Jan Beulich
2015-05-21 15:16         ` David Vrabel
2015-05-22  6:37           ` Jan Beulich
2015-05-22  8:54             ` David Vrabel
2015-05-20 15:54 ` [PATCHv9 4/4] gnttab: use per-VCPU maptrack free lists David Vrabel
2015-05-21 10:42   ` Jan Beulich

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=555DE9B7.6040407@citrix.com \
    --to=david.vrabel@citrix.com \
    --cc=JBeulich@suse.com \
    --cc=ian.campbell@citrix.com \
    --cc=keir@xen.org \
    --cc=tim@xen.org \
    --cc=xen-devel@lists.xenproject.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 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.