WARNING - OLD ARCHIVES

This is an archived copy of the Xen.org mailing list, which we have preserved to ensure that existing links to archives are not broken. The live archive, which contains the latest emails, can be found at http://lists.xen.org/
   
 
 
Xen 
 
Home Products Support Community News
 
   
 

xen-devel

[Xen-devel] [PATCH, RFC, resend] x86: eliminate bogus IRQ restrictions

To: "xen-devel@xxxxxxxxxxxxxxxxxxx" <xen-devel@xxxxxxxxxxxxxxxxxxx>
Subject: [Xen-devel] [PATCH, RFC, resend] x86: eliminate bogus IRQ restrictions
From: "Jan Beulich" <JBeulich@xxxxxxxxxx>
Date: Fri, 13 Aug 2010 14:26:03 +0100
Delivery-date: Fri, 13 Aug 2010 06:26:14 -0700
Envelope-to: www-data@xxxxxxxxxxxxxxxxxxx
List-help: <mailto:xen-devel-request@lists.xensource.com?subject=help>
List-id: Xen developer discussion <xen-devel.lists.xensource.com>
List-post: <mailto:xen-devel@lists.xensource.com>
List-subscribe: <http://lists.xensource.com/mailman/listinfo/xen-devel>, <mailto:xen-devel-request@lists.xensource.com?subject=subscribe>
List-unsubscribe: <http://lists.xensource.com/mailman/listinfo/xen-devel>, <mailto:xen-devel-request@lists.xensource.com?subject=unsubscribe>
Sender: xen-devel-bounces@xxxxxxxxxxxxxxxxxxx
As pointed out in
http://lists.xensource.com/archives/html/xen-devel/2010-07/msg00077.html 
the limits introduced in c/s 20072 are at least questionable. Eliminate
them in favor of a more dynamic approach: There's no real need for an
upper limit on nr_irqs (as anything beyond nr_irqs_gsi isn't visible to
domains anyway), and the split point (and hence ratio) between GSI and
MSI/MSI-X IRQs doesn't need to be hard coded, but can instead be
controlled on the command line in case there are *very* many GSIs.

The default used for nr_irqs will be rather large with this patch, so
it may not be acceptable without also switching to a sparse irq_desc[]
as was done not so lomg ago in Linux.

The added capping of any domain's nr_pirqs is based on the observation
that no domain can possibly have more than the system wide number of
IRQs. The opposite case may in fact also require some adjustment:
Defaulting the number of non-GSI IRQs available (namely to Dom0) to a
fixed value may not be the best choice going forward, since if there
indeed are very many non-GSI interrupt sources, it won't be possible
for the kernel to make use of them without giving "extra_guest_irqs="
on the command line (but the goal should be to allow things to work
right by default even on large systems).

Signed-off-by: Jan Beulich <jbeulich@xxxxxxxxxx>

--- 2010-08-12.orig/xen/arch/x86/io_apic.c      2010-08-06 08:44:33.000000000 
+0200
+++ 2010-08-12/xen/arch/x86/io_apic.c   2010-08-12 17:01:37.000000000 +0200
@@ -2503,6 +2503,9 @@ void dump_ioapic_irq_info(void)
 
 unsigned highest_gsi(void);
 
+static unsigned int __initdata max_gsi_irqs;
+integer_param("max_gsi_irqs", max_gsi_irqs);
+
 void __init init_ioapic_mappings(void)
 {
     unsigned long ioapic_phys;
@@ -2547,19 +2550,37 @@ void __init init_ioapic_mappings(void)
 
     nr_irqs_gsi = max(nr_irqs_gsi, highest_gsi());
 
+    if ( max_gsi_irqs == 0 )
+        max_gsi_irqs = nr_irqs ? nr_irqs / 8 : PAGE_SIZE;
+    else if ( nr_irqs != 0 && max_gsi_irqs > nr_irqs )
+    {
+        printk(XENLOG_WARNING "\"max_gsi_irqs=\" cannot be specified larger"
+                              " than \"nr_irqs=\"\n");
+        max_gsi_irqs = nr_irqs;
+    }
+    if ( max_gsi_irqs < 16 )
+        max_gsi_irqs = 16;
+
+    /* for PHYSDEVOP_pirq_eoi_gmfn guest assumptions */
+    if ( max_gsi_irqs > PAGE_SIZE * 8 )
+        max_gsi_irqs = PAGE_SIZE * 8;
+
     if ( !smp_found_config || skip_ioapic_setup || nr_irqs_gsi < 16 )
         nr_irqs_gsi = 16;
-    else if ( nr_irqs_gsi > MAX_GSI_IRQS)
+    else if ( nr_irqs_gsi > max_gsi_irqs )
     {
-        /* for PHYSDEVOP_pirq_eoi_gmfn guest assumptions */
-        printk(KERN_WARNING "Limiting number of GSI IRQs found (%u) to %lu\n",
-               nr_irqs_gsi, MAX_GSI_IRQS);
-        nr_irqs_gsi = MAX_GSI_IRQS;
+        printk(XENLOG_WARNING "Limiting to %u GSI IRQs (found %u)\n",
+               max_gsi_irqs, nr_irqs_gsi);
+        nr_irqs_gsi = max_gsi_irqs;
     }
 
-    if (nr_irqs < 2 * nr_irqs_gsi)
-        nr_irqs = 2 * nr_irqs_gsi;
-
-    if (nr_irqs > MAX_NR_IRQS)
-        nr_irqs = MAX_NR_IRQS;
+    if ( nr_irqs == 0 )
+        nr_irqs = cpu_has_apic ?
+                  max(16U + num_present_cpus() * NR_DYNAMIC_VECTORS,
+                      8 * nr_irqs_gsi) :
+                  nr_irqs_gsi;
+    else if ( nr_irqs < 16 )
+        nr_irqs = 16;
+    printk(XENLOG_INFO "IRQ limits: %u GSI, %u MSI/MSI-X\n",
+           nr_irqs_gsi, nr_irqs - nr_irqs_gsi);
 }
--- 2010-08-12.orig/xen/arch/x86/irq.c  2010-07-05 08:49:19.000000000 +0200
+++ 2010-08-12/xen/arch/x86/irq.c       2010-08-12 17:01:37.000000000 +0200
@@ -29,7 +29,7 @@ int __read_mostly opt_noirqbalance = 0;
 boolean_param("noirqbalance", opt_noirqbalance);
 
 unsigned int __read_mostly nr_irqs_gsi = 16;
-unsigned int __read_mostly nr_irqs = 1024;
+unsigned int __read_mostly nr_irqs;
 integer_param("nr_irqs", nr_irqs);
 
 u8 __read_mostly *irq_vector;
--- 2010-08-12.orig/xen/common/domain.c 2010-08-06 08:44:34.000000000 +0200
+++ 2010-08-12/xen/common/domain.c      2010-08-12 17:01:37.000000000 +0200
@@ -274,6 +274,8 @@ struct domain *domain_create(
             d->nr_pirqs = nr_irqs_gsi + extra_domU_irqs;
         else
             d->nr_pirqs = nr_irqs_gsi + extra_dom0_irqs;
+        if ( d->nr_pirqs > nr_irqs )
+            d->nr_pirqs = nr_irqs;
 
         d->pirq_to_evtchn = xmalloc_array(u16, d->nr_pirqs);
         d->pirq_mask = xmalloc_array(
--- 2010-08-12.orig/xen/include/asm-x86/irq.h   2010-07-05 13:42:16.000000000 
+0200
+++ 2010-08-12/xen/include/asm-x86/irq.h        2010-08-12 17:01:37.000000000 
+0200
@@ -23,9 +23,6 @@
 #define irq_to_desc(irq)    (&irq_desc[irq])
 #define irq_cfg(irq)        (&irq_cfg[irq])
 
-#define MAX_GSI_IRQS PAGE_SIZE * 8
-#define MAX_NR_IRQS (2 * MAX_GSI_IRQS)
-
 struct irq_cfg {
         int  vector;
         cpumask_t domain;


Attachment: x86-max-irqs-gsi.patch
Description: Text document

_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-devel
<Prev in Thread] Current Thread [Next in Thread>
  • [Xen-devel] [PATCH, RFC, resend] x86: eliminate bogus IRQ restrictions, Jan Beulich <=