Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux

Pull s390 updates from Heiko Carstens:
 "Since Martin is on vacation you get the s390 pull request for the
  v4.15 merge window this time from me.

  Besides a lot of cleanups and bug fixes these are the most important
  changes:

   - a new regset for runtime instrumentation registers

   - hardware accelerated AES-GCM support for the aes_s390 module

   - support for the new CEX6S crypto cards

   - support for FORTIFY_SOURCE

   - addition of missing z13 and new z14 instructions to the in-kernel
     disassembler

   - generate opcode tables for the in-kernel disassembler out of a
     simple text file instead of having to manually maintain those
     tables

   - fast memset16, memset32 and memset64 implementations

   - removal of named saved segment support

   - hardware counter support for z14

   - queued spinlocks and queued rwlocks implementations for s390

   - use the stack_depth tracking feature for s390 BPF JIT

   - a new s390_sthyi system call which emulates the sthyi (store
     hypervisor information) instruction

   - removal of the old KVM virtio transport

   - an s390 specific CPU alternatives implementation which is used in
     the new spinlock code"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux: (88 commits)
  MAINTAINERS: add virtio-ccw.h to virtio/s390 section
  s390/noexec: execute kexec datamover without DAT
  s390: fix transactional execution control register handling
  s390/bpf: take advantage of stack_depth tracking
  s390: simplify transactional execution elf hwcap handling
  s390/zcrypt: Rework struct ap_qact_ap_info.
  s390/virtio: remove unused header file kvm_virtio.h
  s390: avoid undefined behaviour
  s390/disassembler: generate opcode tables from text file
  s390/disassembler: remove insn_to_mnemonic()
  s390/dasd: avoid calling do_gettimeofday()
  s390: vfio-ccw: Do not attempt to free no-op, test and tic cda.
  s390: remove named saved segment support
  s390/archrandom: Reconsider s390 arch random implementation
  s390/pci: do not require AIS facility
  s390/qdio: sanitize put_indicator
  s390/qdio: use atomic_cmpxchg
  s390/nmi: avoid using long-displacement facility
  s390: pass endianness info to sparse
  s390/decompressor: remove informational messages
  ...

1 files changed, 56 insertions, 8 deletions

diff --git a/arch/s390/lib/mem.S b/arch/s390/lib/mem.S
index d6675139..495c9c4 100644
--- a/arch/s390/lib/mem.S
+++ b/arch/s390/lib/mem.S
@@ -79,21 +79,25 @@ ENTRY(memset)
 	ex	%r4,0(%r3)
 	br	%r14
 .Lmemset_fill:
-	stc	%r3,0(%r2)
 	cghi	%r4,1
 	lgr	%r1,%r2
-	ber	%r14
+	je	.Lmemset_fill_exit
 	aghi	%r4,-2
-	srlg	%r3,%r4,8
-	ltgr	%r3,%r3
+	srlg	%r5,%r4,8
+	ltgr	%r5,%r5
 	jz	.Lmemset_fill_remainder
 .Lmemset_fill_loop:
-	mvc	1(256,%r1),0(%r1)
+	stc	%r3,0(%r1)
+	mvc	1(255,%r1),0(%r1)
 	la	%r1,256(%r1)
-	brctg	%r3,.Lmemset_fill_loop
+	brctg	%r5,.Lmemset_fill_loop
 .Lmemset_fill_remainder:
-	larl	%r3,.Lmemset_mvc
-	ex	%r4,0(%r3)
+	stc	%r3,0(%r1)
+	larl	%r5,.Lmemset_mvc
+	ex	%r4,0(%r5)
+	br	%r14
+.Lmemset_fill_exit:
+	stc	%r3,0(%r1)
 	br	%r14
 .Lmemset_xc:
 	xc	0(1,%r1),0(%r1)
@@ -127,3 +131,47 @@ ENTRY(memcpy)
 .Lmemcpy_mvc:
 	mvc	0(1,%r1),0(%r3)
 EXPORT_SYMBOL(memcpy)
+
+/*
+ * __memset16/32/64
+ *
+ * void *__memset16(uint16_t *s, uint16_t v, size_t count)
+ * void *__memset32(uint32_t *s, uint32_t v, size_t count)
+ * void *__memset64(uint64_t *s, uint64_t v, size_t count)
+ */
+.macro __MEMSET bits,bytes,insn
+ENTRY(__memset\bits)
+	ltgr	%r4,%r4
+	bzr	%r14
+	cghi	%r4,\bytes
+	je	.L__memset_exit\bits
+	aghi	%r4,-(\bytes+1)
+	srlg	%r5,%r4,8
+	ltgr	%r5,%r5
+	lgr	%r1,%r2
+	jz	.L__memset_remainder\bits
+.L__memset_loop\bits:
+	\insn	%r3,0(%r1)
+	mvc	\bytes(256-\bytes,%r1),0(%r1)
+	la	%r1,256(%r1)
+	brctg	%r5,.L__memset_loop\bits
+.L__memset_remainder\bits:
+	\insn	%r3,0(%r1)
+	larl	%r5,.L__memset_mvc\bits
+	ex	%r4,0(%r5)
+	br	%r14
+.L__memset_exit\bits:
+	\insn	%r3,0(%r2)
+	br	%r14
+.L__memset_mvc\bits:
+	mvc	\bytes(1,%r1),0(%r1)
+.endm
+
+__MEMSET 16,2,sth
+EXPORT_SYMBOL(__memset16)
+
+__MEMSET 32,4,st
+EXPORT_SYMBOL(__memset32)
+
+__MEMSET 64,8,stg
+EXPORT_SYMBOL(__memset64)