3 files changed, 61 insertions, 4 deletions
diff --git a/arch/ia64/lib/do_csum.S b/arch/ia64/lib/do_csum.S
index 6bec2fc9f5b..1a431a5cf86 100644
--- a/arch/ia64/lib/do_csum.S
+++ b/arch/ia64/lib/do_csum.S
@@ -201,7 +201,7 @@ GLOBAL_ENTRY(do_csum)
 	;;
 (p6)	adds result1[0]=1,result1[0]
 (p9)	br.cond.sptk .do_csum_exit	// if (count == 1) exit
-	// Fall through to caluculate the checksum, feeding result1[0] as
+	// Fall through to calculate the checksum, feeding result1[0] as
 	// the initial value in result1[0].
 	//
 	// Calculate the checksum loading two 8-byte words per loop.
diff --git a/arch/ia64/lib/flush.S b/arch/ia64/lib/flush.S
index 2a0d27f2f21..1d8c8886006 100644
--- a/arch/ia64/lib/flush.S
+++ b/arch/ia64/lib/flush.S
@@ -60,3 +60,58 @@ GLOBAL_ENTRY(flush_icache_range)
 	mov	ar.lc=r3		// restore ar.lc
 	br.ret.sptk.many rp
 END(flush_icache_range)
+
+	/*
+	 * clflush_cache_range(start,size)
+	 *
+	 *	Flush cache lines from start to start+size-1.
+	 *
+	 *	Must deal with range from start to start+size-1 but nothing else
+	 *	(need to be careful not to touch addresses that may be
+	 *	unmapped).
+	 *
+	 *	Note: "in0" and "in1" are preserved for debugging purposes.
+	 */
+	.section .kprobes.text,"ax"
+GLOBAL_ENTRY(clflush_cache_range)
+
+	.prologue
+	alloc	r2=ar.pfs,2,0,0,0
+	movl	r3=ia64_cache_stride_shift
+	mov	r21=1
+	add     r22=in1,in0
+	;;
+	ld8	r20=[r3]		// r20: stride shift
+	sub	r22=r22,r0,1		// last byte address
+	;;
+	shr.u	r23=in0,r20		// start / (stride size)
+	shr.u	r22=r22,r20		// (last byte address) / (stride size)
+	shl	r21=r21,r20		// r21: stride size of the i-cache(s)
+	;;
+	sub	r8=r22,r23		// number of strides - 1
+	shl	r24=r23,r20		// r24: addresses for "fc" =
+					//	"start" rounded down to stride
+					//	boundary
+	.save	ar.lc,r3
+	mov	r3=ar.lc		// save ar.lc
+	;;
+
+	.body
+	mov	ar.lc=r8
+	;;
+	/*
+	 * 32 byte aligned loop, even number of (actually 2) bundles
+	 */
+.Loop_fc:
+	fc	r24		// issuable on M0 only
+	add	r24=r21,r24	// we flush "stride size" bytes per iteration
+	nop.i	0
+	br.cloop.sptk.few .Loop_fc
+	;;
+	sync.i
+	;;
+	srlz.i
+	;;
+	mov	ar.lc=r3		// restore ar.lc
+	br.ret.sptk.many rp
+END(clflush_cache_range)
diff --git a/arch/ia64/lib/ip_fast_csum.S b/arch/ia64/lib/ip_fast_csum.S
index 1f86aeb2c94..620d9dc5220 100644
--- a/arch/ia64/lib/ip_fast_csum.S
+++ b/arch/ia64/lib/ip_fast_csum.S
@@ -96,20 +96,22 @@ END(ip_fast_csum)
 GLOBAL_ENTRY(csum_ipv6_magic)
 	ld4	r20=[in0],4
 	ld4	r21=[in1],4
-	dep	r15=in3,in2,32,16
+	zxt4	in2=in2
 	;;
 	ld4	r22=[in0],4
 	ld4	r23=[in1],4
-	mux1	r15=r15,@rev
+	dep	r15=in3,in2,32,16
 	;;
 	ld4	r24=[in0],4
 	ld4	r25=[in1],4
-	shr.u	r15=r15,16
+	mux1	r15=r15,@rev
 	add	r16=r20,r21
 	add	r17=r22,r23
+	zxt4	in4=in4
 	;;
 	ld4	r26=[in0],4
 	ld4	r27=[in1],4
+	shr.u	r15=r15,16
 	add	r18=r24,r25
 	add	r8=r16,r17
 	;;