x86: eliminate bogus IRQ restrictions

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@novell.com>

diff --git a/xen/arch/x86/io_apic.c b/xen/arch/x86/io_apic.c
index ac3d5d3bb70f41fcccfffe7c01fc64aefcccf2de..97ccf9e2663f23a64ee89b1551776a3b0b00445d 100644 (file)
--- a/xen/arch/x86/io_apic.c
+++ b/xen/arch/x86/io_apic.c
@@ -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 ( !smp_found_config || skip_ioapic_setup || nr_irqs_gsi < 16 )
-        nr_irqs_gsi = 16;
-    else if ( nr_irqs_gsi > MAX_GSI_IRQS)
+    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 )
     {
-        /* 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 "\"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;
 
-    if (nr_irqs < 2 * nr_irqs_gsi)
-        nr_irqs = 2 * nr_irqs_gsi;
+    /* for PHYSDEVOP_pirq_eoi_gmfn guest assumptions */
+    if ( max_gsi_irqs > PAGE_SIZE * 8 )
+        max_gsi_irqs = PAGE_SIZE * 8;
 
-    if (nr_irqs > MAX_NR_IRQS)
-        nr_irqs = MAX_NR_IRQS;
+    if ( !smp_found_config || skip_ioapic_setup || nr_irqs_gsi < 16 )
+        nr_irqs_gsi = 16;
+    else if ( 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 == 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);
 }

diff --git a/xen/arch/x86/irq.c b/xen/arch/x86/irq.c
index a8368fd4ed23e4a8f85bd1bfa0df2368121a9b4d..e0aa1512f999c082959221941b11b3603b2d1972 100644 (file)
--- a/xen/arch/x86/irq.c
+++ b/xen/arch/x86/irq.c
@@ -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;

diff --git a/xen/common/domain.c b/xen/common/domain.c
index 9a9376763009de0af2d5d78355ed4919ecde3101..20e89ea00868fd2d7d084469a4d5a99030463122 100644 (file)
--- a/xen/common/domain.c
+++ b/xen/common/domain.c
@@ -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(

diff --git a/xen/include/asm-x86/irq.h b/xen/include/asm-x86/irq.h
index 7f596ce5a90e907c8b22db3b9e3002e08e5c700f..efbfb8fa195385f9d4ad25f6c8402699c227401c 100644 (file)
--- a/xen/include/asm-x86/irq.h
+++ b/xen/include/asm-x86/irq.h
@@ -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;