x86, SGI UV: TLB shootdown using broadcast assist unit

TLB shootdown for SGI UV.

Depends on patch (in tip/x86/irq):
   x86-update-macros-used-by-uv-platform.patch   Jack Steiner May 29

This patch provides the ability to flush TLB's in cpu's that are not on
the local node.  The hardware mechanism for distributing the flush
messages is the UV's "broadcast assist unit".

The hook to intercept TLB shootdown requests is a 2-line change to
native_flush_tlb_others() (arch/x86/kernel/tlb_64.c).

This code has been tested on a hardware simulator. The real hardware
is not yet available.

The shootdown statistics are provided through /proc/sgi_uv/ptc_statistics.
The use of /sys was considered, but would have required the use of
many /sys files.  The debugfs was also considered, but these statistics
should be available on an ongoing basis, not just for debugging.

Issues to be fixed later:
- The IRQ for the messaging interrupt is currently hardcoded as 200
  (see UV_BAU_MESSAGE).  It should be dynamically assigned in the future.
- The use of appropriate udelay()'s is untested, as they are a problem
  in the simulator.
Signed-off-by: Cliff Wickman <cpw@sgi.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

arch/x86/kernel/Makefile

@@ -94,7 +94,7 @@ obj-$(CONFIG_OLPC)		+= olpc.o
 ###
 # 64 bit specific files
 ifeq ($(CONFIG_X86_64),y)
-        obj-y				+= genapic_64.o genapic_flat_64.o genx2apic_uv_x.o
+        obj-y				+= genapic_64.o genapic_flat_64.o genx2apic_uv_x.o tlb_uv.o
         obj-$(CONFIG_X86_PM_TIMER)	+= pmtimer_64.o
         obj-$(CONFIG_AUDIT)		+= audit_64.o
 

arch/x86/kernel/entry_64.S

@@ -720,6 +720,10 @@ ENTRY(apic_timer_interrupt)
 	apicinterrupt LOCAL_TIMER_VECTOR,smp_apic_timer_interrupt
 END(apic_timer_interrupt)
 
+ENTRY(uv_bau_message_intr1)
+	apicinterrupt 220,uv_bau_message_interrupt
+END(uv_bau_message_intr1)
+
 ENTRY(error_interrupt)
 	apicinterrupt ERROR_APIC_VECTOR,smp_error_interrupt
 END(error_interrupt)

arch/x86/kernel/tlb_64.c

@@ -15,6 +15,8 @@
 #include <asm/proto.h>
 #include <asm/apicdef.h>
 #include <asm/idle.h>
+#include <asm/uv/uv_hub.h>
+#include <asm/uv/uv_bau.h>
 
 #include <mach_ipi.h>
 /*
@@ -162,6 +164,9 @@ void native_flush_tlb_others(const cpumask_t *cpumaskp, struct mm_struct *mm,
 	union smp_flush_state *f;
 	cpumask_t cpumask = *cpumaskp;
 
+	if (is_uv_system() && uv_flush_tlb_others(&cpumask, mm, va))
+			return;
+
 	/* Caller has disabled preemption */
 	sender = smp_processor_id() % NUM_INVALIDATE_TLB_VECTORS;
 	f = &per_cpu(flush_state, sender);