[S390] Calibrate delay and bogomips.
Preset the bogomips number to the cpu capacity value reported by
store system information in SYSIB 1.2.2. This value is constant
for a particular machine model and can be used to determine
relative performance differences between machines.
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
diff --git a/arch/s390/lib/qrnnd.S b/arch/s390/lib/qrnnd.S
new file mode 100644
index 0000000..eb1df63
--- /dev/null
+++ b/arch/s390/lib/qrnnd.S
@@ -0,0 +1,77 @@
+# S/390 __udiv_qrnnd
+
+# r2 : &__r
+# r3 : upper half of 64 bit word n
+# r4 : lower half of 64 bit word n
+# r5 : divisor d
+# the reminder r of the division is to be stored to &__r and
+# the quotient q is to be returned
+
+ .text
+ .globl __udiv_qrnnd
+__udiv_qrnnd:
+ st %r2,24(%r15) # store pointer to reminder for later
+ lr %r0,%r3 # reload n
+ lr %r1,%r4
+ ltr %r2,%r5 # reload and test divisor
+ jp 5f
+ # divisor >= 0x80000000
+ srdl %r0,2 # n/4
+ srl %r2,1 # d/2
+ slr %r1,%r2 # special case if last bit of d is set
+ brc 3,0f # (n/4) div (n/2) can overflow by 1
+ ahi %r0,-1 # trick: subtract n/2, then divide
+0: dr %r0,%r2 # signed division
+ ahi %r1,1 # trick part 2: add 1 to the quotient
+ # now (n >> 2) = (d >> 1) * %r1 + %r0
+ lhi %r3,1
+ nr %r3,%r1 # test last bit of q
+ jz 1f
+ alr %r0,%r2 # add (d>>1) to r
+1: srl %r1,1 # q >>= 1
+ # now (n >> 2) = (d&-2) * %r1 + %r0
+ lhi %r3,1
+ nr %r3,%r5 # test last bit of d
+ jz 2f
+ slr %r0,%r1 # r -= q
+ brc 3,2f # borrow ?
+ alr %r0,%r5 # r += d
+ ahi %r1,-1
+2: # now (n >> 2) = d * %r1 + %r0
+ alr %r1,%r1 # q <<= 1
+ alr %r0,%r0 # r <<= 1
+ brc 12,3f # overflow on r ?
+ slr %r0,%r5 # r -= d
+ ahi %r1,1 # q += 1
+3: lhi %r3,2
+ nr %r3,%r4 # test next to last bit of n
+ jz 4f
+ ahi %r0,1 # r += 1
+4: clr %r0,%r5 # r >= d ?
+ jl 6f
+ slr %r0,%r5 # r -= d
+ ahi %r1,1 # q += 1
+ # now (n >> 1) = d * %r1 + %r0
+ j 6f
+5: # divisor < 0x80000000
+ srdl %r0,1
+ dr %r0,%r2 # signed division
+ # now (n >> 1) = d * %r1 + %r0
+6: alr %r1,%r1 # q <<= 1
+ alr %r0,%r0 # r <<= 1
+ brc 12,7f # overflow on r ?
+ slr %r0,%r5 # r -= d
+ ahi %r1,1 # q += 1
+7: lhi %r3,1
+ nr %r3,%r4 # isolate last bit of n
+ alr %r0,%r3 # r += (n & 1)
+ clr %r0,%r5 # r >= d ?
+ jl 8f
+ slr %r0,%r5 # r -= d
+ ahi %r1,1 # q += 1
+8: # now n = d * %r1 + %r0
+ l %r2,24(%r15)
+ st %r0,0(%r2)
+ lr %r2,%r1
+ br %r14
+ .end __udiv_qrnnd