From: Keir Fraser <keir.fraser@eu.citrix.com>
To: Juergen Gross <juergen.gross@ts.fujitsu.com>
Cc: "xen-devel@lists.xensource.com" <xen-devel@lists.xensource.com>
Subject: Re: [Patch] continue_hypercall_on_cpu rework using tasklets
Date: Wed, 14 Apr 2010 08:35:22 +0100 [thread overview]
Message-ID: <C7EB2ECA.11382%keir.fraser@eu.citrix.com> (raw)
In-Reply-To: <4BC56DE5.6040405@ts.fujitsu.com>
On 14/04/2010 08:25, "Juergen Gross" <juergen.gross@ts.fujitsu.com> wrote:
>> A tasklet also takes an arbitrary ulong parameter, which you can cast to a
>> pointer to your informational structure. The parameter is specified via
>> tasklet_init(). That should suffice.
>
> I'm already using this. The problem is to find the original calling vcpu in
> case of a nested call of continue_hypercall_on_cpu() while not conflicting
> with concurrent calls from other vcpus which happen to address the same pcpu.
There can be only one nested invocation on any given pcpu, since a running
invocation is never preempted. Hence on entry to c_h_o_c() you can check a
per-cpu variable to see whether this invocation is nesting, or not. And if
it is, that variable can be a pointer to an info structure which includes a
pointer to the invoking vcpu.
-- Keir
next prev parent reply other threads:[~2010-04-14 7:35 UTC|newest]
Thread overview: 44+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-04-13 13:19 [Patch] continue_hypercall_on_cpu rework using tasklets Juergen Gross
2010-04-13 13:40 ` Jan Beulich
2010-04-13 13:49 ` Juergen Gross
2010-04-13 15:08 ` Keir Fraser
2010-04-14 6:54 ` Juergen Gross
2010-04-13 14:41 ` Keir Fraser
2010-04-14 4:26 ` Juergen Gross
2010-04-14 6:46 ` Keir Fraser
2010-04-14 6:58 ` Juergen Gross
2010-04-14 7:15 ` Keir Fraser
2010-04-14 7:25 ` Juergen Gross
2010-04-14 7:35 ` Keir Fraser [this message]
2010-04-14 8:04 ` Juergen Gross
2010-04-14 10:30 ` Keir Fraser
2010-04-15 6:31 ` Juergen Gross
2010-04-15 6:39 ` Keir Fraser
2010-04-15 7:57 ` Juergen Gross
2010-04-15 8:13 ` Keir Fraser
2010-04-15 8:22 ` Keir Fraser
2010-04-15 9:59 ` Jiang, Yunhong
2010-04-15 11:06 ` Keir Fraser
2010-04-15 11:22 ` Keir Fraser
2010-04-16 9:20 ` Yu, Ke
2010-04-16 17:51 ` Keir Fraser
2010-04-19 10:50 ` Keir Fraser
2010-04-19 12:04 ` Yu, Ke
2010-04-20 5:35 ` Wei, Gang
2010-04-20 12:51 ` Keir Fraser
2010-04-20 14:10 ` Wei, Gang
2010-04-21 6:47 ` Wei, Gang
2010-04-16 6:42 ` Jiang, Yunhong
2010-04-16 6:55 ` Juergen Gross
2010-04-16 8:30 ` Jiang, Yunhong
2010-04-16 7:13 ` Keir Fraser
2010-04-16 8:16 ` Jiang, Yunhong
2010-04-16 17:57 ` Keir Fraser
2010-04-19 5:53 ` Jiang, Yunhong
2010-04-19 6:48 ` Keir Fraser
2010-04-16 6:45 ` Jiang, Yunhong
2010-04-15 8:29 ` Juergen Gross
2010-04-15 9:08 ` Keir Fraser
-- strict thread matches above, loose matches on Subject: below --
2009-12-30 13:46 Juergen Gross
2009-12-30 13:57 ` Keir Fraser
2009-12-30 13:59 ` Juergen Gross
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=C7EB2ECA.11382%keir.fraser@eu.citrix.com \
--to=keir.fraser@eu.citrix.com \
--cc=juergen.gross@ts.fujitsu.com \
--cc=xen-devel@lists.xensource.com \
/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.