Subject: [IA64] Kexec: Fix ia64_do_tlb_purge so that it works with XEN
From: Simon Horman <horms@verge.net.au>
Date: Fri, 13 Jul 2007 16:54:49 +0900

Fix ia64_do_tlb_purge, its broken in too many ways

1. Call SET_PER_CPU_DATA before making any calls to GET_THIS_PADDR
   to ensure that per-cpu data is set up correctly.

2. Use the per_cpu variable to derive CURRENT_STACK_OFFSET rather
   than reading it from a kernel register. See 1) for explanation
   of why.

3. In the VHPT pruning code, don't use r25 as ia64_jump_to_sal,
   which branches to ia64_do_tlb_purge expects r25 to be preserved.
   There seems no reason not to use r2 as per the other purges
   done in ia64_do_tlb_purge.  Furthermore use r16 and r18 instead
   of r20 and r24 for consistency reasons.

4. Move __va_ul(vcpu_vhpt_maddr(v)) comment outside of
   #if VHPT_ENABLED as it also applies to code further down that
   is outside the #if

Cc: Tristan Gingold <tgingold@free.fr>,
Cc: Yutaka Ezaki <yutaka.ezaki@jp.fujitsu.com>,
Cc: Masaki Kanno <kanno.masaki@jp.fujitsu.com>,
Cc: Kazuhiro Suzuki <kaz@jp.fujitsu.com>,
Signed-off-by: Simon Horman <horms@verge.net.au>

---
Date: Thu, 13 Sep 2007 15:31:43 +0900
From: Horms <horms@verge.net.au>

Fixes as suggested by SUZUKI Kazuhiro:
- Fix up comment relating to the use of SET_PER_CPU_DATA -
  it was describing a previous version of the fix.
- 2.6.18 does perge the DTR for PERCPU data, so there is
  no need to guard it with #ifdef XEN, although later
  kernels do remove this code
- Dereference what is at offset IA64_DOMAIN_FLAGS_OFFSET

Index: xen-unstable.hg/xen/arch/ia64/linux-xen/mca_asm.S
===================================================================
--- xen-unstable.hg.orig/xen/arch/ia64/linux-xen/mca_asm.S	2007-07-11 12:05:33.000000000 +0900
+++ xen-unstable.hg/xen/arch/ia64/linux-xen/mca_asm.S	2007-07-11 13:13:56.000000000 +0900
@@ -195,6 +195,10 @@
  */
 
 ia64_do_tlb_purge:
+#ifdef XEN
+	// This needs to be called in order for GET_THIS_PADDR to work
+	SET_PER_CPU_DATA();;
+#endif
 #define O(member)	IA64_CPUINFO_##member##_OFFSET
 
 	GET_THIS_PADDR(r2, cpu_info)	// load phys addr of cpu_info into r2
@@ -263,7 +269,16 @@ ia64_do_tlb_purge:
 	srlz.i
 	;;
 	// 4. Purge DTR for stack.
+#ifdef XEN
+	// Kernel registers are saved in a per_cpu cpu_kr_ia64_t
+	// to allow the kernel registers themselves to be used by domains.
+	GET_THIS_PADDR(r2, cpu_kr);;
+	add r2=IA64_KR_CURRENT_STACK_OFFSET,r2
+	;;
+	ld8 r16=[r2]
+#else
 	mov r16=IA64_KR(CURRENT_STACK)
+#endif
 	;;
 	shl r16=r16,IA64_GRANULE_SHIFT
 	movl r19=PAGE_OFFSET
@@ -277,8 +292,8 @@ ia64_do_tlb_purge:
 	;;
 #ifdef XEN
 	// 5. VHPT
+	// r2 = __va_ul(vcpu_vhpt_maddr(v));
 #if VHPT_ENABLED
-	// r25 = __va_ul(vcpu_vhpt_maddr(v));
 	GET_THIS_PADDR(r2,cpu_kr);;
 	add r2=IA64_KR_CURRENT_OFFSET,r2;;
 	ld8 r2=[r2];;
@@ -289,18 +304,18 @@ ia64_do_tlb_purge:
 	add r2=IA64_VCPU_VHPT_MADDR_OFFSET,r2;;
 	dep r2=0,r2,60,4;;			// virtual to physical
 	ld8 r2=[r2];; 
-	dep r25=-1,r2,60,4;;			// physical to virtual
+	dep r2=-1,r2,60,4;;			// physical to virtual
 	br.sptk		.percpu_vhpt_done
 #endif
 .not_pervcpu_vhpt:
 	GET_THIS_PADDR(r2, vhpt_paddr);; 
 	ld8 r2=[r2];; 
-	dep r25=-1,r2,60,4;;			// physical to virtual
+	dep r2=-1,r2,60,4;;			// physical to virtual
 .percpu_vhpt_done:
-	dep r20=0,r25,0,IA64_GRANULE_SHIFT
-	mov r24=IA64_GRANULE_SHIFT<<2
+	dep r16=0,r2,0,IA64_GRANULE_SHIFT
+	mov r18=IA64_GRANULE_SHIFT<<2
 	;;
-	ptr.d r20,r24
+	ptr.d r16,r18
 	;;
 	srlz.d
 	;;