[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [Xen-devel] [PATCH v7 07/11] pvqspinlock, x86: Allow unfair queue spinlock in a XEN guest



On 03/19/2014 04:28 PM, Konrad Rzeszutek Wilk wrote:
On Wed, Mar 19, 2014 at 04:14:05PM -0400, Waiman Long wrote:
This patch adds a XEN init function to activate the unfair queue
spinlock in a XEN guest when the PARAVIRT_UNFAIR_LOCKS kernel config
option is selected.

Signed-off-by: Waiman Long<Waiman.Long@xxxxxx>
---
  arch/x86/xen/setup.c |   19 +++++++++++++++++++
  1 files changed, 19 insertions(+), 0 deletions(-)

diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 0982233..66bb6f5 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -625,3 +625,22 @@ void __init xen_arch_setup(void)
        numa_off = 1;
  #endif
  }
+
+#ifdef CONFIG_PARAVIRT_UNFAIR_LOCKS
+/*
+ * Enable unfair lock if running in a Xen guest
+ */
+static __init int xen_unfair_locks_init_jump(void)
+{
+       /*
+        * Disable unfair lock if not running in a PV domain
+        */
+       if (!xen_pv_domain())
+               return 0;
I would just make this 'xen_domain'. Not sure why you need
to have it only for PV while the PVHVM guests can also use it?

The compilation of the setup.c file should have implied xen_domain already (at least HVM). The check is added to make sure that unfair lock won't be enabled on bare metal. As for PVHVM, is there a way to detect it is running as such which is distinct from HVM?

Would it also make sense to use the same printk statement
that the KVM has?


Yes, I can add a printk statement like KVM.

-Longman

_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
http://lists.xen.org/xen-devel


 


Rackspace

Lists.xenproject.org is hosted with RackSpace, monitoring our
servers 24x7x365 and backed by RackSpace's Fanatical Support®.