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
  ...

Documentation/admin-guide/kernel-parameters.txt

@@ -2548,6 +2548,9 @@
 
 	noalign		[KNL,ARM]
 
+	noaltinstr	[S390] Disables alternative instructions patching
+			(CPU alternatives feature).
+
 	noapic		[SMP,APIC] Tells the kernel to not make use of any
 			IOAPICs that may be present in the system.
 

MAINTAINERS

@@ -14335,6 +14335,7 @@ L:	virtualization@lists.linux-foundation.org
 L:	kvm@vger.kernel.org
 S:	Supported
 F:	drivers/s390/virtio/
+F:	arch/s390/include/uapi/asm/virtio-ccw.h
 
 VIRTIO GPU DRIVER
 M:	David Airlie <airlied@linux.ie>

arch/s390/Kconfig

@@ -68,6 +68,7 @@ config S390
 	select ARCH_BINFMT_ELF_STATE
 	select ARCH_HAS_DEVMEM_IS_ALLOWED
 	select ARCH_HAS_ELF_RANDOMIZE
+	select ARCH_HAS_FORTIFY_SOURCE
 	select ARCH_HAS_GCOV_PROFILE_ALL
 	select ARCH_HAS_GIGANTIC_PAGE if (MEMORY_ISOLATION && COMPACTION) || CMA
 	select ARCH_HAS_KCOV
@@ -143,7 +144,6 @@ config S390
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_DYNAMIC_FTRACE_WITH_REGS
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS
-	select HAVE_EXIT_THREAD
 	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FUNCTION_TRACER
@@ -538,6 +538,22 @@ config ARCH_RANDOM
 
 	  If unsure, say Y.
 
+config ALTERNATIVES
+	def_bool y
+	prompt "Patch optimized instructions for running CPU type"
+	help
+	  When enabled the kernel code is compiled with additional
+	  alternative instructions blocks optimized for newer CPU types.
+	  These alternative instructions blocks are patched at kernel boot
+	  time when running CPU supports them. This mechanism is used to
+	  optimize some critical code paths (i.e. spinlocks) for newer CPUs
+	  even if kernel is build to support older machine generations.
+
+	  This mechanism could be disabled by appending "noaltinstr"
+	  option to the kernel command line.
+
+	  If unsure, say Y.
+
 endmenu
 
 menu "Memory setup"
@@ -809,18 +825,6 @@ config PFAULT
 	  Everybody who wants to run Linux under VM != VM4.2 should select
 	  this option.
 
-config SHARED_KERNEL
-	bool "VM shared kernel support"
-	depends on !JUMP_LABEL
-	help
-	  Select this option, if you want to share the text segment of the
-	  Linux kernel between different VM guests. This reduces memory
-	  usage with lots of guests but greatly increases kernel size.
-	  Also if a kernel was IPL'ed from a shared segment the kexec system
-	  call will not work.
-	  You should only select this option if you know what you are
-	  doing and want to exploit this feature.
-
 config CMM
 	def_tristate n
 	prompt "Cooperative memory management"
@@ -930,17 +934,4 @@ config S390_GUEST
 	  Select this option if you want to run the kernel as a guest under
 	  the KVM hypervisor.
 
-config S390_GUEST_OLD_TRANSPORT
-	def_bool y
-	prompt "Guest support for old s390 virtio transport (DEPRECATED)"
-	depends on S390_GUEST
-	help
-	  Enable this option to add support for the old s390-virtio
-	  transport (i.e. virtio devices NOT based on virtio-ccw). This
-	  type of virtio devices is only available on the experimental
-	  kuli userspace or with old (< 2.6) qemu. If you are running
-	  with a modern version of qemu (which supports virtio-ccw since
-	  1.4 and uses it by default since version 2.4), you probably won't
-	  need this.
-
 endmenu

arch/s390/Makefile

@@ -21,7 +21,7 @@ KBUILD_CFLAGS	+= -m64
 KBUILD_AFLAGS	+= -m64
 UTS_MACHINE	:= s390x
 STACK_SIZE	:= 16384
-CHECKFLAGS	+= -D__s390__ -D__s390x__
+CHECKFLAGS	+= -D__s390__ -D__s390x__ -mbig-endian
 
 export LD_BFD
 
@@ -133,6 +133,7 @@ archclean:
 
 archprepare:
 	$(Q)$(MAKE) $(build)=$(tools) include/generated/facilities.h
+	$(Q)$(MAKE) $(build)=$(tools) include/generated/dis.h
 
 # Don't use tabs in echo arguments
 define archhelp

arch/s390/boot/compressed/Makefile

@@ -12,7 +12,7 @@ targets += vmlinux.bin.xz vmlinux.bin.lzma vmlinux.bin.lzo vmlinux.bin.lz4
 targets += misc.o piggy.o sizes.h head.o
 
 KBUILD_CFLAGS := -m64 -D__KERNEL__ -O2
-KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING
+KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING -D__NO_FORTIFY
 KBUILD_CFLAGS += $(cflags-y) -fno-delete-null-pointer-checks -msoft-float
 KBUILD_CFLAGS += $(call cc-option,-mpacked-stack)
 KBUILD_CFLAGS += $(call cc-option,-ffreestanding)

arch/s390/boot/compressed/misc.c

@@ -170,9 +170,7 @@ unsigned long decompress_kernel(void)
 	free_mem_ptr = (unsigned long) &_end;
 	free_mem_end_ptr = free_mem_ptr + HEAP_SIZE;
 
-	puts("Uncompressing Linux... ");
 	__decompress(input_data, input_len, NULL, NULL, output, 0, NULL, error);
-	puts("Ok, booting the kernel.\n");
 	return (unsigned long) output;
 }
 

arch/s390/configs/default_defconfig

@@ -69,7 +69,6 @@ CONFIG_KSM=y
 CONFIG_TRANSPARENT_HUGEPAGE=y
 CONFIG_CLEANCACHE=y
 CONFIG_FRONTSWAP=y
-CONFIG_CMA=y
 CONFIG_CMA_DEBUG=y
 CONFIG_CMA_DEBUGFS=y
 CONFIG_MEM_SOFT_DIRTY=y
@@ -379,7 +378,6 @@ CONFIG_BLK_DEV_LOOP=m
 CONFIG_BLK_DEV_CRYPTOLOOP=m
 CONFIG_BLK_DEV_DRBD=m
 CONFIG_BLK_DEV_NBD=m
-CONFIG_BLK_DEV_OSD=m
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_SIZE=32768
 CONFIG_BLK_DEV_RAM_DAX=y
@@ -416,7 +414,6 @@ CONFIG_SCSI_OSD_ULD=m
 CONFIG_MD=y
 CONFIG_BLK_DEV_MD=y
 CONFIG_MD_LINEAR=m
-CONFIG_MD_RAID0=m
 CONFIG_MD_MULTIPATH=m
 CONFIG_MD_FAULTY=m
 CONFIG_BLK_DEV_DM=m
@@ -483,6 +480,8 @@ CONFIG_INFINIBAND=m
 CONFIG_INFINIBAND_USER_ACCESS=m
 CONFIG_MLX4_INFINIBAND=m
 CONFIG_MLX5_INFINIBAND=m
+CONFIG_VFIO=m
+CONFIG_VFIO_PCI=m
 CONFIG_VIRTIO_BALLOON=m
 CONFIG_EXT4_FS=y
 CONFIG_EXT4_FS_POSIX_ACL=y
@@ -599,7 +598,6 @@ CONFIG_DETECT_HUNG_TASK=y
 CONFIG_WQ_WATCHDOG=y
 CONFIG_PANIC_ON_OOPS=y
 CONFIG_DEBUG_TIMEKEEPING=y
-CONFIG_DEBUG_RT_MUTEXES=y
 CONFIG_DEBUG_WW_MUTEX_SLOWPATH=y
 CONFIG_PROVE_LOCKING=y
 CONFIG_LOCK_STAT=y
@@ -629,10 +627,8 @@ CONFIG_SCHED_TRACER=y
 CONFIG_FTRACE_SYSCALLS=y
 CONFIG_STACK_TRACER=y
 CONFIG_BLK_DEV_IO_TRACE=y
-CONFIG_UPROBE_EVENTS=y
 CONFIG_FUNCTION_PROFILER=y
 CONFIG_HIST_TRIGGERS=y
-CONFIG_TRACE_ENUM_MAP_FILE=y
 CONFIG_LKDTM=m
 CONFIG_TEST_LIST_SORT=y
 CONFIG_TEST_SORT=y
@@ -649,6 +645,7 @@ CONFIG_ENCRYPTED_KEYS=m
 CONFIG_SECURITY=y
 CONFIG_SECURITY_NETWORK=y
 CONFIG_HARDENED_USERCOPY=y
+CONFIG_FORTIFY_SOURCE=y
 CONFIG_SECURITY_SELINUX=y
 CONFIG_SECURITY_SELINUX_BOOTPARAM=y
 CONFIG_SECURITY_SELINUX_BOOTPARAM_VALUE=0
@@ -705,12 +702,12 @@ CONFIG_CRYPTO_USER_API_RNG=m
 CONFIG_CRYPTO_USER_API_AEAD=m
 CONFIG_ZCRYPT=m
 CONFIG_PKEY=m
+CONFIG_CRYPTO_PAES_S390=m
 CONFIG_CRYPTO_SHA1_S390=m
 CONFIG_CRYPTO_SHA256_S390=m
 CONFIG_CRYPTO_SHA512_S390=m
 CONFIG_CRYPTO_DES_S390=m
 CONFIG_CRYPTO_AES_S390=m
-CONFIG_CRYPTO_PAES_S390=m
 CONFIG_CRYPTO_GHASH_S390=m
 CONFIG_CRYPTO_CRC32_S390=y
 CONFIG_ASYMMETRIC_KEY_TYPE=y

arch/s390/configs/gcov_defconfig

@@ -70,7 +70,6 @@ CONFIG_KSM=y
 CONFIG_TRANSPARENT_HUGEPAGE=y
 CONFIG_CLEANCACHE=y
 CONFIG_FRONTSWAP=y
-CONFIG_CMA=y
 CONFIG_MEM_SOFT_DIRTY=y
 CONFIG_ZSWAP=y
 CONFIG_ZBUD=m
@@ -376,7 +375,6 @@ CONFIG_BLK_DEV_LOOP=m
 CONFIG_BLK_DEV_CRYPTOLOOP=m
 CONFIG_BLK_DEV_DRBD=m
 CONFIG_BLK_DEV_NBD=m
-CONFIG_BLK_DEV_OSD=m
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_SIZE=32768
 CONFIG_BLK_DEV_RAM_DAX=y
@@ -412,7 +410,6 @@ CONFIG_SCSI_OSD_ULD=m
 CONFIG_MD=y
 CONFIG_BLK_DEV_MD=y
 CONFIG_MD_LINEAR=m
-CONFIG_MD_RAID0=m
 CONFIG_MD_MULTIPATH=m
 CONFIG_MD_FAULTY=m
 CONFIG_BLK_DEV_DM=m
@@ -479,6 +476,8 @@ CONFIG_INFINIBAND=m
 CONFIG_INFINIBAND_USER_ACCESS=m
 CONFIG_MLX4_INFINIBAND=m
 CONFIG_MLX5_INFINIBAND=m
+CONFIG_VFIO=m
+CONFIG_VFIO_PCI=m
 CONFIG_VIRTIO_BALLOON=m
 CONFIG_EXT4_FS=y
 CONFIG_EXT4_FS_POSIX_ACL=y
@@ -575,10 +574,8 @@ CONFIG_SCHED_TRACER=y
 CONFIG_FTRACE_SYSCALLS=y
 CONFIG_STACK_TRACER=y
 CONFIG_BLK_DEV_IO_TRACE=y
-CONFIG_UPROBE_EVENTS=y
 CONFIG_FUNCTION_PROFILER=y
 CONFIG_HIST_TRIGGERS=y
-CONFIG_TRACE_ENUM_MAP_FILE=y
 CONFIG_LKDTM=m
 CONFIG_PERCPU_TEST=m
 CONFIG_ATOMIC64_SELFTEST=y
@@ -650,12 +647,12 @@ CONFIG_CRYPTO_USER_API_RNG=m
 CONFIG_CRYPTO_USER_API_AEAD=m
 CONFIG_ZCRYPT=m
 CONFIG_PKEY=m
+CONFIG_CRYPTO_PAES_S390=m
 CONFIG_CRYPTO_SHA1_S390=m
 CONFIG_CRYPTO_SHA256_S390=m
 CONFIG_CRYPTO_SHA512_S390=m
 CONFIG_CRYPTO_DES_S390=m
 CONFIG_CRYPTO_AES_S390=m
-CONFIG_CRYPTO_PAES_S390=m
 CONFIG_CRYPTO_GHASH_S390=m
 CONFIG_CRYPTO_CRC32_S390=y
 CONFIG_CRC7=m

arch/s390/configs/performance_defconfig

@@ -68,7 +68,6 @@ CONFIG_KSM=y
 CONFIG_TRANSPARENT_HUGEPAGE=y
 CONFIG_CLEANCACHE=y
 CONFIG_FRONTSWAP=y
-CONFIG_CMA=y
 CONFIG_MEM_SOFT_DIRTY=y
 CONFIG_ZSWAP=y
 CONFIG_ZBUD=m
@@ -374,7 +373,6 @@ CONFIG_BLK_DEV_LOOP=m
 CONFIG_BLK_DEV_CRYPTOLOOP=m
 CONFIG_BLK_DEV_DRBD=m
 CONFIG_BLK_DEV_NBD=m
-CONFIG_BLK_DEV_OSD=m
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_SIZE=32768
 CONFIG_BLK_DEV_RAM_DAX=y
@@ -410,7 +408,6 @@ CONFIG_SCSI_OSD_ULD=m
 CONFIG_MD=y
 CONFIG_BLK_DEV_MD=y
 CONFIG_MD_LINEAR=m
-CONFIG_MD_RAID0=m
 CONFIG_MD_MULTIPATH=m
 CONFIG_MD_FAULTY=m
 CONFIG_BLK_DEV_DM=m
@@ -477,6 +474,8 @@ CONFIG_INFINIBAND=m
 CONFIG_INFINIBAND_USER_ACCESS=m
 CONFIG_MLX4_INFINIBAND=m
 CONFIG_MLX5_INFINIBAND=m
+CONFIG_VFIO=m
+CONFIG_VFIO_PCI=m
 CONFIG_VIRTIO_BALLOON=m
 CONFIG_EXT4_FS=y
 CONFIG_EXT4_FS_POSIX_ACL=y
@@ -573,10 +572,8 @@ CONFIG_SCHED_TRACER=y
 CONFIG_FTRACE_SYSCALLS=y
 CONFIG_STACK_TRACER=y
 CONFIG_BLK_DEV_IO_TRACE=y
-CONFIG_UPROBE_EVENTS=y
 CONFIG_FUNCTION_PROFILER=y
 CONFIG_HIST_TRIGGERS=y
-CONFIG_TRACE_ENUM_MAP_FILE=y
 CONFIG_LKDTM=m
 CONFIG_PERCPU_TEST=m
 CONFIG_ATOMIC64_SELFTEST=y
@@ -648,12 +645,12 @@ CONFIG_CRYPTO_USER_API_RNG=m
 CONFIG_CRYPTO_USER_API_AEAD=m
 CONFIG_ZCRYPT=m
 CONFIG_PKEY=m
+CONFIG_CRYPTO_PAES_S390=m
 CONFIG_CRYPTO_SHA1_S390=m
 CONFIG_CRYPTO_SHA256_S390=m
 CONFIG_CRYPTO_SHA512_S390=m
 CONFIG_CRYPTO_DES_S390=m
 CONFIG_CRYPTO_AES_S390=m
-CONFIG_CRYPTO_PAES_S390=m
 CONFIG_CRYPTO_GHASH_S390=m
 CONFIG_CRYPTO_CRC32_S390=y
 CONFIG_CRC7=m

arch/s390/crypto/aes_s390.c

@@ -4,9 +4,11 @@
  * s390 implementation of the AES Cipher Algorithm.
  *
  * s390 Version:
- *   Copyright IBM Corp. 2005, 2007
+ *   Copyright IBM Corp. 2005, 2017
  *   Author(s): Jan Glauber (jang@de.ibm.com)
  *		Sebastian Siewior (sebastian@breakpoint.cc> SW-Fallback
+ *		Patrick Steuer <patrick.steuer@de.ibm.com>
+ *		Harald Freudenberger <freude@de.ibm.com>
  *
  * Derived from "crypto/aes_generic.c"
  *
@@ -22,20 +24,25 @@
 
 #include <crypto/aes.h>
 #include <crypto/algapi.h>
+#include <crypto/ghash.h>
+#include <crypto/internal/aead.h>
 #include <crypto/internal/skcipher.h>
+#include <crypto/scatterwalk.h>
 #include <linux/err.h>
 #include <linux/module.h>
 #include <linux/cpufeature.h>
 #include <linux/init.h>
 #include <linux/spinlock.h>
 #include <linux/fips.h>
+#include <linux/string.h>
 #include <crypto/xts.h>
 #include <asm/cpacf.h>
 
 static u8 *ctrblk;
 static DEFINE_SPINLOCK(ctrblk_lock);
 
-static cpacf_mask_t km_functions, kmc_functions, kmctr_functions;
+static cpacf_mask_t km_functions, kmc_functions, kmctr_functions,
+		    kma_functions;
 
 struct s390_aes_ctx {
 	u8 key[AES_MAX_KEY_SIZE];
@@ -55,6 +62,17 @@ struct s390_xts_ctx {
 	struct crypto_skcipher *fallback;
 };
 
+struct gcm_sg_walk {
+	struct scatter_walk walk;
+	unsigned int walk_bytes;
+	u8 *walk_ptr;
+	unsigned int walk_bytes_remain;
+	u8 buf[AES_BLOCK_SIZE];
+	unsigned int buf_bytes;
+	u8 *ptr;
+	unsigned int nbytes;
+};
+
 static int setkey_fallback_cip(struct crypto_tfm *tfm, const u8 *in_key,
 		unsigned int key_len)
 {
@@ -771,6 +789,267 @@ static struct crypto_alg ctr_aes_alg = {
 	}
 };
 
+static int gcm_aes_setkey(struct crypto_aead *tfm, const u8 *key,
+			  unsigned int keylen)
+{
+	struct s390_aes_ctx *ctx = crypto_aead_ctx(tfm);
+
+	switch (keylen) {
+	case AES_KEYSIZE_128:
+		ctx->fc = CPACF_KMA_GCM_AES_128;
+		break;
+	case AES_KEYSIZE_192:
+		ctx->fc = CPACF_KMA_GCM_AES_192;
+		break;
+	case AES_KEYSIZE_256:
+		ctx->fc = CPACF_KMA_GCM_AES_256;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	memcpy(ctx->key, key, keylen);
+	ctx->key_len = keylen;
+	return 0;
+}
+
+static int gcm_aes_setauthsize(struct crypto_aead *tfm, unsigned int authsize)
+{
+	switch (authsize) {
+	case 4:
+	case 8:
+	case 12:
+	case 13:
+	case 14:
+	case 15:
+	case 16:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void gcm_sg_walk_start(struct gcm_sg_walk *gw, struct scatterlist *sg,
+			      unsigned int len)
+{
+	memset(gw, 0, sizeof(*gw));
+	gw->walk_bytes_remain = len;
+	scatterwalk_start(&gw->walk, sg);
+}
+
+static int gcm_sg_walk_go(struct gcm_sg_walk *gw, unsigned int minbytesneeded)
+{
+	int n;
+
+	/* minbytesneeded <= AES_BLOCK_SIZE */
+	if (gw->buf_bytes && gw->buf_bytes >= minbytesneeded) {
+		gw->ptr = gw->buf;
+		gw->nbytes = gw->buf_bytes;
+		goto out;
+	}
+
+	if (gw->walk_bytes_remain == 0) {
+		gw->ptr = NULL;
+		gw->nbytes = 0;
+		goto out;
+	}
+
+	gw->walk_bytes = scatterwalk_clamp(&gw->walk, gw->walk_bytes_remain);
+	if (!gw->walk_bytes) {
+		scatterwalk_start(&gw->walk, sg_next(gw->walk.sg));
+		gw->walk_bytes = scatterwalk_clamp(&gw->walk,
+						   gw->walk_bytes_remain);
+	}
+	gw->walk_ptr = scatterwalk_map(&gw->walk);
+
+	if (!gw->buf_bytes && gw->walk_bytes >= minbytesneeded) {
+		gw->ptr = gw->walk_ptr;
+		gw->nbytes = gw->walk_bytes;
+		goto out;
+	}
+
+	while (1) {
+		n = min(gw->walk_bytes, AES_BLOCK_SIZE - gw->buf_bytes);
+		memcpy(gw->buf + gw->buf_bytes, gw->walk_ptr, n);
+		gw->buf_bytes += n;
+		gw->walk_bytes_remain -= n;
+		scatterwalk_unmap(&gw->walk);
+		scatterwalk_advance(&gw->walk, n);
+		scatterwalk_done(&gw->walk, 0, gw->walk_bytes_remain);
+
+		if (gw->buf_bytes >= minbytesneeded) {
+			gw->ptr = gw->buf;
+			gw->nbytes = gw->buf_bytes;
+			goto out;
+		}
+
+		gw->walk_bytes = scatterwalk_clamp(&gw->walk,
+						   gw->walk_bytes_remain);
+		if (!gw->walk_bytes) {
+			scatterwalk_start(&gw->walk, sg_next(gw->walk.sg));
+			gw->walk_bytes = scatterwalk_clamp(&gw->walk,
+							gw->walk_bytes_remain);
+		}
+		gw->walk_ptr = scatterwalk_map(&gw->walk);
+	}
+
+out:
+	return gw->nbytes;
+}
+
+static void gcm_sg_walk_done(struct gcm_sg_walk *gw, unsigned int bytesdone)
+{
+	int n;
+
+	if (gw->ptr == NULL)
+		return;
+
+	if (gw->ptr == gw->buf) {
+		n = gw->buf_bytes - bytesdone;
+		if (n > 0) {
+			memmove(gw->buf, gw->buf + bytesdone, n);
+			gw->buf_bytes -= n;
+		} else
+			gw->buf_bytes = 0;
+	} else {
+		gw->walk_bytes_remain -= bytesdone;
+		scatterwalk_unmap(&gw->walk);
+		scatterwalk_advance(&gw->walk, bytesdone);
+		scatterwalk_done(&gw->walk, 0, gw->walk_bytes_remain);
+	}
+}
+
+static int gcm_aes_crypt(struct aead_request *req, unsigned int flags)
+{
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	struct s390_aes_ctx *ctx = crypto_aead_ctx(tfm);
+	unsigned int ivsize = crypto_aead_ivsize(tfm);
+	unsigned int taglen = crypto_aead_authsize(tfm);
+	unsigned int aadlen = req->assoclen;
+	unsigned int pclen = req->cryptlen;
+	int ret = 0;
+
+	unsigned int len, in_bytes, out_bytes,
+		     min_bytes, bytes, aad_bytes, pc_bytes;
+	struct gcm_sg_walk gw_in, gw_out;
+	u8 tag[GHASH_DIGEST_SIZE];
+
+	struct {
+		u32 _[3];		/* reserved */
+		u32 cv;			/* Counter Value */
+		u8 t[GHASH_DIGEST_SIZE];/* Tag */
+		u8 h[AES_BLOCK_SIZE];	/* Hash-subkey */
+		u64 taadl;		/* Total AAD Length */
+		u64 tpcl;		/* Total Plain-/Cipher-text Length */
+		u8 j0[GHASH_BLOCK_SIZE];/* initial counter value */
+		u8 k[AES_MAX_KEY_SIZE];	/* Key */
+	} param;
+
+	/*
+	 * encrypt
+	 *   req->src: aad||plaintext
+	 *   req->dst: aad||ciphertext||tag
+	 * decrypt
+	 *   req->src: aad||ciphertext||tag
+	 *   req->dst: aad||plaintext, return 0 or -EBADMSG
+	 * aad, plaintext and ciphertext may be empty.
+	 */
+	if (flags & CPACF_DECRYPT)
+		pclen -= taglen;
+	len = aadlen + pclen;
+
+	memset(&param, 0, sizeof(param));
+	param.cv = 1;
+	param.taadl = aadlen * 8;
+	param.tpcl = pclen * 8;
+	memcpy(param.j0, req->iv, ivsize);
+	*(u32 *)(param.j0 + ivsize) = 1;
+	memcpy(param.k, ctx->key, ctx->key_len);
+
+	gcm_sg_walk_start(&gw_in, req->src, len);
+	gcm_sg_walk_start(&gw_out, req->dst, len);
+
+	do {
+		min_bytes = min_t(unsigned int,
+				  aadlen > 0 ? aadlen : pclen, AES_BLOCK_SIZE);
+		in_bytes = gcm_sg_walk_go(&gw_in, min_bytes);
+		out_bytes = gcm_sg_walk_go(&gw_out, min_bytes);
+		bytes = min(in_bytes, out_bytes);
+
+		if (aadlen + pclen <= bytes) {
+			aad_bytes = aadlen;
+			pc_bytes = pclen;
+			flags |= CPACF_KMA_LAAD | CPACF_KMA_LPC;
+		} else {
+			if (aadlen <= bytes) {
+				aad_bytes = aadlen;
+				pc_bytes = (bytes - aadlen) &
+					   ~(AES_BLOCK_SIZE - 1);
+				flags |= CPACF_KMA_LAAD;
+			} else {
+				aad_bytes = bytes & ~(AES_BLOCK_SIZE - 1);
+				pc_bytes = 0;
+			}
+		}
+
+		if (aad_bytes > 0)
+			memcpy(gw_out.ptr, gw_in.ptr, aad_bytes);
+
+		cpacf_kma(ctx->fc | flags, &param,
+			  gw_out.ptr + aad_bytes,
+			  gw_in.ptr + aad_bytes, pc_bytes,
+			  gw_in.ptr, aad_bytes);
+
+		gcm_sg_walk_done(&gw_in, aad_bytes + pc_bytes);
+		gcm_sg_walk_done(&gw_out, aad_bytes + pc_bytes);
+		aadlen -= aad_bytes;
+		pclen -= pc_bytes;
+	} while (aadlen + pclen > 0);
+
+	if (flags & CPACF_DECRYPT) {
+		scatterwalk_map_and_copy(tag, req->src, len, taglen, 0);
+		if (crypto_memneq(tag, param.t, taglen))
+			ret = -EBADMSG;
+	} else
+		scatterwalk_map_and_copy(param.t, req->dst, len, taglen, 1);
+
+	memzero_explicit(&param, sizeof(param));
+	return ret;
+}
+
+static int gcm_aes_encrypt(struct aead_request *req)
+{
+	return gcm_aes_crypt(req, CPACF_ENCRYPT);
+}
+
+static int gcm_aes_decrypt(struct aead_request *req)
+{
+	return gcm_aes_crypt(req, CPACF_DECRYPT);
+}
+
+static struct aead_alg gcm_aes_aead = {
+	.setkey			= gcm_aes_setkey,
+	.setauthsize		= gcm_aes_setauthsize,
+	.encrypt		= gcm_aes_encrypt,
+	.decrypt		= gcm_aes_decrypt,
+
+	.ivsize			= GHASH_BLOCK_SIZE - sizeof(u32),
+	.maxauthsize		= GHASH_DIGEST_SIZE,
+	.chunksize		= AES_BLOCK_SIZE,
+
+	.base			= {
+		.cra_flags		= CRYPTO_ALG_TYPE_AEAD,
+		.cra_blocksize		= 1,
+		.cra_ctxsize		= sizeof(struct s390_aes_ctx),
+		.cra_priority		= 900,
+		.cra_name		= "gcm(aes)",
+		.cra_driver_name	= "gcm-aes-s390",
+		.cra_module		= THIS_MODULE,
+	},
+};
+
 static struct crypto_alg *aes_s390_algs_ptr[5];
 static int aes_s390_algs_num;
 
@@ -790,16 +1069,19 @@ static void aes_s390_fini(void)
 		crypto_unregister_alg(aes_s390_algs_ptr[aes_s390_algs_num]);
 	if (ctrblk)
 		free_page((unsigned long) ctrblk);
+
+	crypto_unregister_aead(&gcm_aes_aead);
 }
 
 static int __init aes_s390_init(void)
 {
 	int ret;
 
-	/* Query available functions for KM, KMC and KMCTR */
+	/* Query available functions for KM, KMC, KMCTR and KMA */
 	cpacf_query(CPACF_KM, &km_functions);
 	cpacf_query(CPACF_KMC, &kmc_functions);
 	cpacf_query(CPACF_KMCTR, &kmctr_functions);
+	cpacf_query(CPACF_KMA, &kma_functions);
 
 	if (cpacf_test_func(&km_functions, CPACF_KM_AES_128) ||
 	    cpacf_test_func(&km_functions, CPACF_KM_AES_192) ||
@@ -840,6 +1122,14 @@ static int __init aes_s390_init(void)
 			goto out_err;
 	}
 
+	if (cpacf_test_func(&kma_functions, CPACF_KMA_GCM_AES_128) ||
+	    cpacf_test_func(&kma_functions, CPACF_KMA_GCM_AES_192) ||
+	    cpacf_test_func(&kma_functions, CPACF_KMA_GCM_AES_256)) {
+		ret = crypto_register_aead(&gcm_aes_aead);
+		if (ret)
+			goto out_err;
+	}
+
 	return 0;
 out_err:
 	aes_s390_fini();

arch/s390/defconfig

@@ -53,7 +53,6 @@ CONFIG_KSM=y
 CONFIG_TRANSPARENT_HUGEPAGE=y
 CONFIG_CLEANCACHE=y
 CONFIG_FRONTSWAP=y
-CONFIG_CMA=y
 CONFIG_ZSWAP=y
 CONFIG_ZBUD=m
 CONFIG_ZSMALLOC=m
@@ -163,7 +162,6 @@ CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_PAGEALLOC=y
 CONFIG_DETECT_HUNG_TASK=y
 CONFIG_PANIC_ON_OOPS=y
-CONFIG_DEBUG_RT_MUTEXES=y
 CONFIG_PROVE_LOCKING=y
 CONFIG_LOCK_STAT=y
 CONFIG_DEBUG_LOCKDEP=y
@@ -179,7 +177,6 @@ CONFIG_TRACER_SNAPSHOT_PER_CPU_SWAP=y
 CONFIG_STACK_TRACER=y
 CONFIG_BLK_DEV_IO_TRACE=y
 CONFIG_FUNCTION_PROFILER=y
-CONFIG_TRACE_ENUM_MAP_FILE=y
 CONFIG_KPROBES_SANITY_TEST=y
 CONFIG_S390_PTDUMP=y
 CONFIG_CRYPTO_CRYPTD=m

arch/s390/include/asm/Kbuild

@@ -15,6 +15,7 @@ generic-y += local64.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
 generic-y += preempt.h
+generic-y += rwsem.h
 generic-y += trace_clock.h
 generic-y += unaligned.h
 generic-y += word-at-a-time.h

arch/s390/include/asm/alternative.h

+#ifndef _ASM_S390_ALTERNATIVE_H
+#define _ASM_S390_ALTERNATIVE_H
+
+#ifndef __ASSEMBLY__
+
+#include <linux/types.h>
+#include <linux/stddef.h>
+#include <linux/stringify.h>
+
+struct alt_instr {
+	s32 instr_offset;	/* original instruction */
+	s32 repl_offset;	/* offset to replacement instruction */
+	u16 facility;		/* facility bit set for replacement */
+	u8  instrlen;		/* length of original instruction */
+	u8  replacementlen;	/* length of new instruction */
+} __packed;
+
+#ifdef CONFIG_ALTERNATIVES
+extern void apply_alternative_instructions(void);
+extern void apply_alternatives(struct alt_instr *start, struct alt_instr *end);
+#else
+static inline void apply_alternative_instructions(void) {};
+static inline void apply_alternatives(struct alt_instr *start,
+				      struct alt_instr *end) {};
+#endif
+/*
+ * |661:       |662:	  |6620      |663:
+ * +-----------+---------------------+
+ * | oldinstr  | oldinstr_padding    |
+ * |	       +----------+----------+
+ * |	       |	  |	     |
+ * |	       | >6 bytes |6/4/2 nops|
+ * |	       |6 bytes jg----------->
+ * +-----------+---------------------+
+ *		 ^^ static padding ^^
+ *
+ * .altinstr_replacement section
+ * +---------------------+-----------+
+ * |6641:			     |6651:
+ * | alternative instr 1	     |
+ * +-----------+---------+- - - - - -+
+ * |6642:		 |6652:      |
+ * | alternative instr 2 | padding
+ * +---------------------+- - - - - -+
+ *			  ^ runtime ^
+ *
+ * .altinstructions section
+ * +---------------------------------+
+ * | alt_instr entries for each      |
+ * | alternative instr		     |
+ * +---------------------------------+
+ */
+
+#define b_altinstr(num)	"664"#num
+#define e_altinstr(num)	"665"#num
+
+#define e_oldinstr_pad_end	"663"
+#define oldinstr_len		"662b-661b"
+#define oldinstr_total_len	e_oldinstr_pad_end"b-661b"
+#define altinstr_len(num)	e_altinstr(num)"b-"b_altinstr(num)"b"
+#define oldinstr_pad_len(num) \
+	"-(((" altinstr_len(num) ")-(" oldinstr_len ")) > 0) * " \
+	"((" altinstr_len(num) ")-(" oldinstr_len "))"
+
+#define INSTR_LEN_SANITY_CHECK(len)					\
+	".if " len " > 254\n"						\
+	"\t.error \"cpu alternatives does not support instructions "	\
+		"blocks > 254 bytes\"\n"				\
+	".endif\n"							\
+	".if (" len ") %% 2\n"						\
+	"\t.error \"cpu alternatives instructions length is odd\"\n"	\
+	".endif\n"
+
+#define OLDINSTR_PADDING(oldinstr, num)					\
+	".if " oldinstr_pad_len(num) " > 6\n"				\
+	"\tjg " e_oldinstr_pad_end "f\n"				\
+	"6620:\n"							\
+	"\t.fill (" oldinstr_pad_len(num) " - (6620b-662b)) / 2, 2, 0x0700\n" \
+	".else\n"							\
+	"\t.fill " oldinstr_pad_len(num) " / 6, 6, 0xc0040000\n"	\
+	"\t.fill " oldinstr_pad_len(num) " %% 6 / 4, 4, 0x47000000\n"	\
+	"\t.fill " oldinstr_pad_len(num) " %% 6 %% 4 / 2, 2, 0x0700\n"	\
+	".endif\n"
+
+#define OLDINSTR(oldinstr, num)						\
+	"661:\n\t" oldinstr "\n662:\n"					\
+	OLDINSTR_PADDING(oldinstr, num)					\
+	e_oldinstr_pad_end ":\n"					\
+	INSTR_LEN_SANITY_CHECK(oldinstr_len)
+
+#define OLDINSTR_2(oldinstr, num1, num2)				\
+	"661:\n\t" oldinstr "\n662:\n"					\
+	".if " altinstr_len(num1) " < " altinstr_len(num2) "\n"		\
+	OLDINSTR_PADDING(oldinstr, num2)				\
+	".else\n"							\
+	OLDINSTR_PADDING(oldinstr, num1)				\
+	".endif\n"							\
+	e_oldinstr_pad_end ":\n"					\
+	INSTR_LEN_SANITY_CHECK(oldinstr_len)
+
+#define ALTINSTR_ENTRY(facility, num)					\
+	"\t.long 661b - .\n"			/* old instruction */	\
+	"\t.long " b_altinstr(num)"b - .\n"	/* alt instruction */	\
+	"\t.word " __stringify(facility) "\n"	/* facility bit    */	\
+	"\t.byte " oldinstr_total_len "\n"	/* source len	   */	\
+	"\t.byte " altinstr_len(num) "\n"	/* alt instruction len */
+
+#define ALTINSTR_REPLACEMENT(altinstr, num)	/* replacement */	\
+	b_altinstr(num)":\n\t" altinstr "\n" e_altinstr(num) ":\n"	\
+	INSTR_LEN_SANITY_CHECK(altinstr_len(num))
+
+#ifdef CONFIG_ALTERNATIVES
+/* alternative assembly primitive: */
+#define ALTERNATIVE(oldinstr, altinstr, facility) \
+	".pushsection .altinstr_replacement, \"ax\"\n"			\
+	ALTINSTR_REPLACEMENT(altinstr, 1)				\
+	".popsection\n"							\
+	OLDINSTR(oldinstr, 1)						\
+	".pushsection .altinstructions,\"a\"\n"				\
+	ALTINSTR_ENTRY(facility, 1)					\
+	".popsection\n"
+
+#define ALTERNATIVE_2(oldinstr, altinstr1, facility1, altinstr2, facility2)\
+	".pushsection .altinstr_replacement, \"ax\"\n"			\
+	ALTINSTR_REPLACEMENT(altinstr1, 1)				\
+	ALTINSTR_REPLACEMENT(altinstr2, 2)				\
+	".popsection\n"							\
+	OLDINSTR_2(oldinstr, 1, 2)					\
+	".pushsection .altinstructions,\"a\"\n"				\
+	ALTINSTR_ENTRY(facility1, 1)					\
+	ALTINSTR_ENTRY(facility2, 2)					\
+	".popsection\n"
+#else
+/* Alternative instructions are disabled, let's put just oldinstr in */
+#define ALTERNATIVE(oldinstr, altinstr, facility) \
+	oldinstr "\n"
+
+#define ALTERNATIVE_2(oldinstr, altinstr1, facility1, altinstr2, facility2) \
+	oldinstr "\n"
+#endif
+
+/*
+ * Alternative instructions for different CPU types or capabilities.
+ *
+ * This allows to use optimized instructions even on generic binary
+ * kernels.
+ *
+ * oldinstr is padded with jump and nops at compile time if altinstr is
+ * longer. altinstr is padded with jump and nops at run-time during patching.
+ *
+ * For non barrier like inlines please define new variants
+ * without volatile and memory clobber.
+ */
+#define alternative(oldinstr, altinstr, facility)			\
+	asm volatile(ALTERNATIVE(oldinstr, altinstr, facility) : : : "memory")
+
+#define alternative_2(oldinstr, altinstr1, facility1, altinstr2, facility2) \
+	asm volatile(ALTERNATIVE_2(oldinstr, altinstr1, facility1,	    \
+				   altinstr2, facility2) ::: "memory")
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _ASM_S390_ALTERNATIVE_H */

arch/s390/include/asm/archrandom.h

@@ -28,42 +28,42 @@ static void s390_arch_random_generate(u8 *buf, unsigned int nbytes)
 
 static inline bool arch_has_random(void)
 {
-	if (static_branch_likely(&s390_arch_random_available))
-		return true;
 	return false;
 }
 
 static inline bool arch_has_random_seed(void)
 {
-	return arch_has_random();
+	if (static_branch_likely(&s390_arch_random_available))
+		return true;
+	return false;
 }
 
 static inline bool arch_get_random_long(unsigned long *v)
 {
-	if (static_branch_likely(&s390_arch_random_available)) {
-		s390_arch_random_generate((u8 *)v, sizeof(*v));
-		return true;
-	}
 	return false;
 }
 
 static inline bool arch_get_random_int(unsigned int *v)
 {
-	if (static_branch_likely(&s390_arch_random_available)) {
-		s390_arch_random_generate((u8 *)v, sizeof(*v));
-		return true;
-	}
 	return false;
 }
 
 static inline bool arch_get_random_seed_long(unsigned long *v)
 {
-	return arch_get_random_long(v);
+	if (static_branch_likely(&s390_arch_random_available)) {
+		s390_arch_random_generate((u8 *)v, sizeof(*v));
+		return true;
+	}
+	return false;
 }
 
 static inline bool arch_get_random_seed_int(unsigned int *v)
 {
-	return arch_get_random_int(v);
+	if (static_branch_likely(&s390_arch_random_available)) {
+		s390_arch_random_generate((u8 *)v, sizeof(*v));
+		return true;
+	}
+	return false;
 }
 
 #endif /* CONFIG_ARCH_RANDOM */

arch/s390/include/asm/atomic_ops.h

@@ -40,19 +40,24 @@ __ATOMIC_OPS(__atomic64_xor, long, "laxg")
 #undef __ATOMIC_OPS
 #undef __ATOMIC_OP
 
-static inline void __atomic_add_const(int val, int *ptr)
-{
-	asm volatile(
-		"	asi	%[ptr],%[val]\n"
-		: [ptr] "+Q" (*ptr) : [val] "i" (val) : "cc");
+#define __ATOMIC_CONST_OP(op_name, op_type, op_string, op_barrier)	\
+static inline void op_name(op_type val, op_type *ptr)			\
+{									\
+	asm volatile(							\
+		op_string "	%[ptr],%[val]\n"			\
+		op_barrier						\
+		: [ptr] "+Q" (*ptr) : [val] "i" (val) : "cc", "memory");\
 }
 
-static inline void __atomic64_add_const(long val, long *ptr)
-{
-	asm volatile(
-		"	agsi	%[ptr],%[val]\n"
-		: [ptr] "+Q" (*ptr) : [val] "i" (val) : "cc");
-}
+#define __ATOMIC_CONST_OPS(op_name, op_type, op_string)			\
+	__ATOMIC_CONST_OP(op_name, op_type, op_string, "\n")		\
+	__ATOMIC_CONST_OP(op_name##_barrier, op_type, op_string, "bcr 14,0\n")
+
+__ATOMIC_CONST_OPS(__atomic_add_const, int, "asi")
+__ATOMIC_CONST_OPS(__atomic64_add_const, long, "agsi")
+
+#undef __ATOMIC_CONST_OPS
+#undef __ATOMIC_CONST_OP
 
 #else /* CONFIG_HAVE_MARCH_Z196_FEATURES */
 
@@ -108,6 +113,11 @@ __ATOMIC64_OPS(__atomic64_xor, "xgr")
 
 #undef __ATOMIC64_OPS
 
+#define __atomic_add_const(val, ptr)		__atomic_add(val, ptr)
+#define __atomic_add_const_barrier(val, ptr)	__atomic_add(val, ptr)
+#define __atomic64_add_const(val, ptr)		__atomic64_add(val, ptr)
+#define __atomic64_add_const_barrier(val, ptr)	__atomic64_add(val, ptr)
+
 #endif /* CONFIG_HAVE_MARCH_Z196_FEATURES */
 
 static inline int __atomic_cmpxchg(int *ptr, int old, int new)

arch/s390/include/asm/ccwgroup.h

@@ -42,6 +42,7 @@ struct ccwgroup_device {
  * @thaw: undo work done in @freeze
  * @restore: callback for restoring after hibernation
  * @driver: embedded driver structure
+ * @ccw_driver: supported ccw_driver (optional)
  */
 struct ccwgroup_driver {
 	int (*setup) (struct ccwgroup_device *);
@@ -56,6 +57,7 @@ struct ccwgroup_driver {
 	int (*restore)(struct ccwgroup_device *);
 
 	struct device_driver driver;
+	struct ccw_driver *ccw_driver;
 };
 
 extern int  ccwgroup_driver_register   (struct ccwgroup_driver *cdriver);

arch/s390/include/asm/cpacf.h

@@ -2,7 +2,7 @@
 /*
  * CP Assist for Cryptographic Functions (CPACF)
  *
- * Copyright IBM Corp. 2003, 2016
+ * Copyright IBM Corp. 2003, 2017
  * Author(s): Thomas Spatzier
  *	      Jan Glauber
  *	      Harald Freudenberger (freude@de.ibm.com)
@@ -134,6 +134,22 @@
 #define CPACF_PRNO_TRNG_Q_R2C_RATIO	0x70
 #define CPACF_PRNO_TRNG			0x72
 
+/*
+ * Function codes for the KMA (CIPHER MESSAGE WITH AUTHENTICATION)
+ * instruction
+ */
+#define CPACF_KMA_QUERY		0x00
+#define CPACF_KMA_GCM_AES_128	0x12
+#define CPACF_KMA_GCM_AES_192	0x13
+#define CPACF_KMA_GCM_AES_256	0x14
+
+/*
+ * Flags for the KMA (CIPHER MESSAGE WITH AUTHENTICATION) instruction
+ */
+#define CPACF_KMA_LPC	0x100	/* Last-Plaintext/Ciphertext */
+#define CPACF_KMA_LAAD	0x200	/* Last-AAD */
+#define CPACF_KMA_HS	0x400	/* Hash-subkey Supplied */
+
 typedef struct { unsigned char bytes[16]; } cpacf_mask_t;
 
 /**
@@ -179,6 +195,8 @@ static inline int __cpacf_check_opcode(unsigned int opcode)
 		return test_facility(77);	/* check for MSA4 */
 	case CPACF_PRNO:
 		return test_facility(57);	/* check for MSA5 */
+	case CPACF_KMA:
+		return test_facility(146);	/* check for MSA8 */
 	default:
 		BUG();
 	}
@@ -470,4 +488,36 @@ static inline void cpacf_pckmo(long func, void *param)
 		: "cc", "memory");
 }
 
+/**
+ * cpacf_kma() - executes the KMA (CIPHER MESSAGE WITH AUTHENTICATION)
+ *		 instruction
+ * @func: the function code passed to KMA; see CPACF_KMA_xxx defines
+ * @param: address of parameter block; see POP for details on each func
+ * @dest: address of destination memory area
+ * @src: address of source memory area
+ * @src_len: length of src operand in bytes
+ * @aad: address of additional authenticated data memory area
+ * @aad_len: length of aad operand in bytes
+ */
+static inline void cpacf_kma(unsigned long func, void *param, u8 *dest,
+			     const u8 *src, unsigned long src_len,
+			     const u8 *aad, unsigned long aad_len)
+{
+	register unsigned long r0 asm("0") = (unsigned long) func;
+	register unsigned long r1 asm("1") = (unsigned long) param;
+	register unsigned long r2 asm("2") = (unsigned long) src;
+	register unsigned long r3 asm("3") = (unsigned long) src_len;
+	register unsigned long r4 asm("4") = (unsigned long) aad;
+	register unsigned long r5 asm("5") = (unsigned long) aad_len;
+	register unsigned long r6 asm("6") = (unsigned long) dest;
+
+	asm volatile(
+		"0:	.insn	rrf,%[opc] << 16,%[dst],%[src],%[aad],0\n"
+		"	brc	1,0b\n"	/* handle partial completion */
+		: [dst] "+a" (r6), [src] "+a" (r2), [slen] "+d" (r3),
+		  [aad] "+a" (r4), [alen] "+d" (r5)
+		: [fc] "d" (r0), [pba] "a" (r1), [opc] "i" (CPACF_KMA)
+		: "cc", "memory");
+}
+
 #endif	/* _ASM_S390_CPACF_H */

arch/s390/include/asm/ctl_reg.h

@@ -8,6 +8,18 @@
 #ifndef __ASM_CTL_REG_H
 #define __ASM_CTL_REG_H
 
+#include <linux/const.h>
+
+#define CR2_GUARDED_STORAGE		_BITUL(63 - 59)
+
+#define CR14_CHANNEL_REPORT_SUBMASK	_BITUL(63 - 35)
+#define CR14_RECOVERY_SUBMASK		_BITUL(63 - 36)
+#define CR14_DEGRADATION_SUBMASK	_BITUL(63 - 37)
+#define CR14_EXTERNAL_DAMAGE_SUBMASK	_BITUL(63 - 38)
+#define CR14_WARNING_SUBMASK		_BITUL(63 - 39)
+
+#ifndef __ASSEMBLY__
+
 #include <linux/bug.h>
 
 #define __ctl_load(array, low, high) do {				\
@@ -55,7 +67,11 @@ void smp_ctl_clear_bit(int cr, int bit);
 union ctlreg0 {
 	unsigned long val;
 	struct {
-		unsigned long	   : 32;
+		unsigned long	   : 8;
+		unsigned long tcx  : 1;	/* Transactional-Execution control */
+		unsigned long pifo : 1;	/* Transactional-Execution Program-
+					   Interruption-Filtering Override */
+		unsigned long	   : 22;
 		unsigned long	   : 3;
 		unsigned long lap  : 1; /* Low-address-protection control */
 		unsigned long	   : 4;
@@ -71,6 +87,19 @@ union ctlreg0 {
 	};
 };
 
+union ctlreg2 {
+	unsigned long val;
+	struct {
+		unsigned long	    : 33;
+		unsigned long ducto : 25;
+		unsigned long	    : 1;
+		unsigned long gse   : 1;
+		unsigned long	    : 1;
+		unsigned long tds   : 1;
+		unsigned long tdc   : 2;
+	};
+};
+
 #ifdef CONFIG_SMP
 # define ctl_set_bit(cr, bit) smp_ctl_set_bit(cr, bit)
 # define ctl_clear_bit(cr, bit) smp_ctl_clear_bit(cr, bit)
@@ -79,4 +108,5 @@ union ctlreg0 {
 # define ctl_clear_bit(cr, bit) __ctl_clear_bit(cr, bit)
 #endif
 
+#endif /* __ASSEMBLY__ */
 #endif /* __ASM_CTL_REG_H */

arch/s390/include/asm/dis.h

@@ -9,32 +9,7 @@
 #ifndef __ASM_S390_DIS_H__
 #define __ASM_S390_DIS_H__
 
-/* Type of operand */
-#define OPERAND_GPR	0x1	/* Operand printed as %rx */
-#define OPERAND_FPR	0x2	/* Operand printed as %fx */
-#define OPERAND_AR	0x4	/* Operand printed as %ax */
-#define OPERAND_CR	0x8	/* Operand printed as %cx */
-#define OPERAND_VR	0x10	/* Operand printed as %vx */
-#define OPERAND_DISP	0x20	/* Operand printed as displacement */
-#define OPERAND_BASE	0x40	/* Operand printed as base register */
-#define OPERAND_INDEX	0x80	/* Operand printed as index register */
-#define OPERAND_PCREL	0x100	/* Operand printed as pc-relative symbol */
-#define OPERAND_SIGNED	0x200	/* Operand printed as signed value */
-#define OPERAND_LENGTH	0x400	/* Operand printed as length (+1) */
-
-
-struct s390_operand {
-	int bits;		/* The number of bits in the operand. */
-	int shift;		/* The number of bits to shift. */
-	int flags;		/* One bit syntax flags. */
-};
-
-struct s390_insn {
-	const char name[5];
-	unsigned char opfrag;
-	unsigned char format;
-};
-
+#include <generated/dis.h>
 
 static inline int insn_length(unsigned char code)
 {
@@ -45,7 +20,6 @@ struct pt_regs;
 
 void show_code(struct pt_regs *regs);
 void print_fn_code(unsigned char *code, unsigned long len);
-int insn_to_mnemonic(unsigned char *instruction, char *buf, unsigned int len);
 struct s390_insn *find_insn(unsigned char *code);
 
 static inline int is_known_insn(unsigned char *code)

arch/s390/include/asm/ipl.h

@@ -13,6 +13,8 @@
 #include <asm/cio.h>
 #include <asm/setup.h>
 
+#define NSS_NAME_SIZE	8
+
 #define IPL_PARMBLOCK_ORIGIN	0x2000
 
 #define IPL_PARM_BLK_FCP_LEN (sizeof(struct ipl_list_hdr) + \
@@ -106,7 +108,6 @@ extern size_t append_ipl_scpdata(char *, size_t);
 enum {
 	IPL_DEVNO_VALID		= 1,
 	IPL_PARMBLOCK_VALID	= 2,
-	IPL_NSS_VALID		= 4,
 };
 
 enum ipl_type {

arch/s390/include/asm/kprobes.h

@@ -63,8 +63,6 @@ typedef u16 kprobe_opcode_t;
 
 #define kretprobe_blacklist_size 0
 
-#define KPROBE_SWAP_INST	0x10
-
 /* Architecture specific copy of original instruction */
 struct arch_specific_insn {
 	/* copy of original instruction */

arch/s390/include/asm/kvm_host.h

@@ -736,7 +736,6 @@ struct kvm_arch{
 	wait_queue_head_t ipte_wq;
 	int ipte_lock_count;
 	struct mutex ipte_mutex;
-	struct ratelimit_state sthyi_limit;
 	spinlock_t start_stop_lock;
 	struct sie_page2 *sie_page2;
 	struct kvm_s390_cpu_model model;

arch/s390/include/asm/lowcore.h

@@ -134,8 +134,9 @@ struct lowcore {
 	__u8	pad_0x03b4[0x03b8-0x03b4];	/* 0x03b4 */
 	__u64	gmap;				/* 0x03b8 */
 	__u32	spinlock_lockval;		/* 0x03c0 */
-	__u32	fpu_flags;			/* 0x03c4 */
-	__u8	pad_0x03c8[0x0400-0x03c8];	/* 0x03c8 */
+	__u32	spinlock_index;			/* 0x03c4 */
+	__u32	fpu_flags;			/* 0x03c8 */
+	__u8	pad_0x03cc[0x0400-0x03cc];	/* 0x03cc */
 
 	/* Per cpu primary space access list */
 	__u32	paste[16];			/* 0x0400 */

arch/s390/include/asm/nmi.h

@@ -26,12 +26,9 @@
 #define MCCK_CODE_CPU_TIMER_VALID	_BITUL(63 - 46)
 #define MCCK_CODE_PSW_MWP_VALID		_BITUL(63 - 20)
 #define MCCK_CODE_PSW_IA_VALID		_BITUL(63 - 23)
-
-#define MCCK_CR14_CR_PENDING_SUB_MASK	(1 << 28)
-#define MCCK_CR14_RECOVERY_SUB_MASK	(1 << 27)
-#define MCCK_CR14_DEGRAD_SUB_MASK	(1 << 26)
-#define MCCK_CR14_EXT_DAMAGE_SUB_MASK	(1 << 25)
-#define MCCK_CR14_WARN_SUB_MASK		(1 << 24)
+#define MCCK_CODE_CR_VALID		_BITUL(63 - 29)
+#define MCCK_CODE_GS_VALID		_BITUL(63 - 36)
+#define MCCK_CODE_FC_VALID		_BITUL(63 - 43)
 
 #ifndef __ASSEMBLY__
 
@@ -87,6 +84,8 @@ union mci {
 
 #define MCESA_ORIGIN_MASK	(~0x3ffUL)
 #define MCESA_LC_MASK		(0xfUL)
+#define MCESA_MIN_SIZE		(1024)
+#define MCESA_MAX_SIZE		(2048)
 
 struct mcesa {
 	u8 vector_save_area[1024];
@@ -95,8 +94,12 @@ struct mcesa {
 
 struct pt_regs;
 
-extern void s390_handle_mcck(void);
-extern void s390_do_machine_check(struct pt_regs *regs);
+void nmi_alloc_boot_cpu(struct lowcore *lc);
+int nmi_alloc_per_cpu(struct lowcore *lc);
+void nmi_free_per_cpu(struct lowcore *lc);
+
+void s390_handle_mcck(void);
+void s390_do_machine_check(struct pt_regs *regs);
 
 #endif /* __ASSEMBLY__ */
 #endif /* _ASM_S390_NMI_H */

arch/s390/include/asm/pci_debug.h

@@ -19,11 +19,7 @@ extern debug_info_t *pci_debug_err_id;
 
 static inline void zpci_err_hex(void *addr, int len)
 {
-	while (len > 0) {
-		debug_event(pci_debug_err_id, 0, (void *) addr, len);
-		len -= pci_debug_err_id->buf_size;
-		addr += pci_debug_err_id->buf_size;
-	}
+	debug_event(pci_debug_err_id, 0, addr, len);
 }
 
 #endif

arch/s390/include/asm/pci_insn.h

@@ -82,6 +82,6 @@ int zpci_refresh_trans(u64 fn, u64 addr, u64 range);
 int zpci_load(u64 *data, u64 req, u64 offset);
 int zpci_store(u64 data, u64 req, u64 offset);
 int zpci_store_block(const u64 *data, u64 req, u64 offset);
-void zpci_set_irq_ctrl(u16 ctl, char *unused, u8 isc);
+int zpci_set_irq_ctrl(u16 ctl, char *unused, u8 isc);
 
 #endif

arch/s390/include/asm/pgalloc.h

@@ -13,6 +13,7 @@
 #define _S390_PGALLOC_H
 
 #include <linux/threads.h>
+#include <linux/string.h>
 #include <linux/gfp.h>
 #include <linux/mm.h>
 
@@ -28,24 +29,9 @@ void page_table_free_rcu(struct mmu_gather *, unsigned long *, unsigned long);
 void page_table_free_pgste(struct page *page);
 extern int page_table_allocate_pgste;
 
-static inline void clear_table(unsigned long *s, unsigned long val, size_t n)
-{
-	struct addrtype { char _[256]; };
-	int i;
-
-	for (i = 0; i < n; i += 256) {
-		*s = val;
-		asm volatile(
-			"mvc	8(248,%[s]),0(%[s])\n"
-			: "+m" (*(struct addrtype *) s)
-			: [s] "a" (s));
-		s += 256 / sizeof(long);
-	}
-}
-
 static inline void crst_table_init(unsigned long *crst, unsigned long entry)
 {
-	clear_table(crst, entry, _CRST_TABLE_SIZE);
+	memset64((u64 *)crst, entry, _CRST_ENTRIES);
 }
 
 static inline unsigned long pgd_entry_type(struct mm_struct *mm)

arch/s390/include/asm/processor.h

@@ -22,6 +22,7 @@
 #define CIF_IGNORE_IRQ		5	/* ignore interrupt (for udelay) */
 #define CIF_ENABLED_WAIT	6	/* in enabled wait state */
 #define CIF_MCCK_GUEST		7	/* machine check happening in guest */
+#define CIF_DEDICATED_CPU	8	/* this CPU is dedicated */
 
 #define _CIF_MCCK_PENDING	_BITUL(CIF_MCCK_PENDING)
 #define _CIF_ASCE_PRIMARY	_BITUL(CIF_ASCE_PRIMARY)
@@ -31,6 +32,7 @@
 #define _CIF_IGNORE_IRQ		_BITUL(CIF_IGNORE_IRQ)
 #define _CIF_ENABLED_WAIT	_BITUL(CIF_ENABLED_WAIT)
 #define _CIF_MCCK_GUEST		_BITUL(CIF_MCCK_GUEST)
+#define _CIF_DEDICATED_CPU	_BITUL(CIF_DEDICATED_CPU)
 
 #ifndef __ASSEMBLY__
 
@@ -219,10 +221,10 @@ void show_registers(struct pt_regs *regs);
 void show_cacheinfo(struct seq_file *m);
 
 /* Free all resources held by a thread. */
-extern void release_thread(struct task_struct *);
+static inline void release_thread(struct task_struct *tsk) { }
 
-/* Free guarded storage control block for current */
-void exit_thread_gs(void);
+/* Free guarded storage control block */
+void guarded_storage_release(struct task_struct *tsk);
 
 unsigned long get_wchan(struct task_struct *p);
 #define task_pt_regs(tsk) ((struct pt_regs *) \

arch/s390/include/asm/runtime_instr.h

@@ -6,55 +6,55 @@
 #define S390_RUNTIME_INSTR_STOP		0x2
 
 struct runtime_instr_cb {
-	__u64 buf_current;
-	__u64 buf_origin;
-	__u64 buf_limit;
+	__u64 rca;
+	__u64 roa;
+	__u64 rla;
 
-	__u32 valid		: 1;
-	__u32 pstate		: 1;
-	__u32 pstate_set_buf	: 1;
-	__u32 home_space	: 1;
-	__u32 altered		: 1;
-	__u32			: 3;
-	__u32 pstate_sample	: 1;
-	__u32 sstate_sample	: 1;
-	__u32 pstate_collect	: 1;
-	__u32 sstate_collect	: 1;
-	__u32			: 1;
-	__u32 halted_int	: 1;
-	__u32 int_requested	: 1;
-	__u32 buffer_full_int	: 1;
+	__u32 v			: 1;
+	__u32 s			: 1;
+	__u32 k			: 1;
+	__u32 h			: 1;
+	__u32 a			: 1;
+	__u32 reserved1		: 3;
+	__u32 ps		: 1;
+	__u32 qs		: 1;
+	__u32 pc		: 1;
+	__u32 qc		: 1;
+	__u32 reserved2		: 1;
+	__u32 g			: 1;
+	__u32 u			: 1;
+	__u32 l			: 1;
 	__u32 key		: 4;
-	__u32			: 9;
+	__u32 reserved3		: 8;
+	__u32 t			: 1;
 	__u32 rgs		: 3;
 
-	__u32 mode		: 4;
-	__u32 next		: 1;
+	__u32 m			: 4;
+	__u32 n			: 1;
 	__u32 mae		: 1;
-	__u32			: 2;
-	__u32 call_type_br	: 1;
-	__u32 return_type_br	: 1;
-	__u32 other_type_br	: 1;
-	__u32 bc_other_type	: 1;
-	__u32 emit		: 1;
-	__u32 tx_abort		: 1;
-	__u32			: 2;
-	__u32 bp_xn		: 1;
-	__u32 bp_xt		: 1;
-	__u32 bp_ti		: 1;
-	__u32 bp_ni		: 1;
-	__u32 suppr_y		: 1;
-	__u32 suppr_z		: 1;
+	__u32 reserved4		: 2;
+	__u32 c			: 1;
+	__u32 r			: 1;
+	__u32 b			: 1;
+	__u32 j			: 1;
+	__u32 e			: 1;
+	__u32 x			: 1;
+	__u32 reserved5		: 2;
+	__u32 bpxn		: 1;
+	__u32 bpxt		: 1;
+	__u32 bpti		: 1;
+	__u32 bpni		: 1;
+	__u32 reserved6		: 2;
 
-	__u32 dc_miss_extra	: 1;
-	__u32 lat_lev_ignore	: 1;
-	__u32 ic_lat_lev	: 4;
-	__u32 dc_lat_lev	: 4;
+	__u32 d			: 1;
+	__u32 f			: 1;
+	__u32 ic		: 4;
+	__u32 dc		: 4;
 
-	__u64 reserved1;
-	__u64 scaling_factor;
+	__u64 reserved7;
+	__u64 sf;
 	__u64 rsic;
-	__u64 reserved2;
+	__u64 reserved8;
 } __packed __aligned(8);
 
 extern struct runtime_instr_cb runtime_instr_empty_cb;
@@ -86,6 +86,8 @@ static inline void restore_ri_cb(struct runtime_instr_cb *cb_next,
 		load_runtime_instr_cb(&runtime_instr_empty_cb);
 }
 
-void exit_thread_runtime_instr(void);
+struct task_struct;
+
+void runtime_instr_release(struct task_struct *tsk);
 
 #endif /* _RUNTIME_INSTR_H */

arch/s390/include/asm/rwsem.h

-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _S390_RWSEM_H
-#define _S390_RWSEM_H
-
-/*
- *  S390 version
- *    Copyright IBM Corp. 2002
- *    Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com)
- *
- *  Based on asm-alpha/semaphore.h and asm-i386/rwsem.h
- */
-
-/*
- *
- * The MSW of the count is the negated number of active writers and waiting
- * lockers, and the LSW is the total number of active locks
- *
- * The lock count is initialized to 0 (no active and no waiting lockers).
- *
- * When a writer subtracts WRITE_BIAS, it'll get 0xffff0001 for the case of an
- * uncontended lock. This can be determined because XADD returns the old value.
- * Readers increment by 1 and see a positive value when uncontended, negative
- * if there are writers (and maybe) readers waiting (in which case it goes to
- * sleep).
- *
- * The value of WAITING_BIAS supports up to 32766 waiting processes. This can
- * be extended to 65534 by manually checking the whole MSW rather than relying
- * on the S flag.
- *
- * The value of ACTIVE_BIAS supports up to 65535 active processes.
- *
- * This should be totally fair - if anything is waiting, a process that wants a
- * lock will go to the back of the queue. When the currently active lock is
- * released, if there's a writer at the front of the queue, then that and only
- * that will be woken up; if there's a bunch of consecutive readers at the
- * front, then they'll all be woken up, but no other readers will be.
- */
-
-#ifndef _LINUX_RWSEM_H
-#error "please don't include asm/rwsem.h directly, use linux/rwsem.h instead"
-#endif
-
-#define RWSEM_UNLOCKED_VALUE	0x0000000000000000L
-#define RWSEM_ACTIVE_BIAS	0x0000000000000001L
-#define RWSEM_ACTIVE_MASK	0x00000000ffffffffL
-#define RWSEM_WAITING_BIAS	(-0x0000000100000000L)
-#define RWSEM_ACTIVE_READ_BIAS	RWSEM_ACTIVE_BIAS
-#define RWSEM_ACTIVE_WRITE_BIAS	(RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
-
-/*
- * lock for reading
- */
-static inline void __down_read(struct rw_semaphore *sem)
-{
-	signed long old, new;
-
-	asm volatile(
-		"	lg	%0,%2\n"
-		"0:	lgr	%1,%0\n"
-		"	aghi	%1,%4\n"
-		"	csg	%0,%1,%2\n"
-		"	jl	0b"
-		: "=&d" (old), "=&d" (new), "=Q" (sem->count)
-		: "Q" (sem->count), "i" (RWSEM_ACTIVE_READ_BIAS)
-		: "cc", "memory");
-	if (old < 0)
-		rwsem_down_read_failed(sem);
-}
-
-/*
- * trylock for reading -- returns 1 if successful, 0 if contention
- */
-static inline int __down_read_trylock(struct rw_semaphore *sem)
-{
-	signed long old, new;
-
-	asm volatile(
-		"	lg	%0,%2\n"
-		"0:	ltgr	%1,%0\n"
-		"	jm	1f\n"
-		"	aghi	%1,%4\n"
-		"	csg	%0,%1,%2\n"
-		"	jl	0b\n"
-		"1:"
-		: "=&d" (old), "=&d" (new), "=Q" (sem->count)
-		: "Q" (sem->count), "i" (RWSEM_ACTIVE_READ_BIAS)
-		: "cc", "memory");
-	return old >= 0 ? 1 : 0;
-}
-
-/*
- * lock for writing
- */
-static inline long ___down_write(struct rw_semaphore *sem)
-{
-	signed long old, new, tmp;
-
-	tmp = RWSEM_ACTIVE_WRITE_BIAS;
-	asm volatile(
-		"	lg	%0,%2\n"
-		"0:	lgr	%1,%0\n"
-		"	ag	%1,%4\n"
-		"	csg	%0,%1,%2\n"
-		"	jl	0b"
-		: "=&d" (old), "=&d" (new), "=Q" (sem->count)
-		: "Q" (sem->count), "m" (tmp)
-		: "cc", "memory");
-
-	return old;
-}
-
-static inline void __down_write(struct rw_semaphore *sem)
-{
-	if (___down_write(sem))
-		rwsem_down_write_failed(sem);
-}
-
-static inline int __down_write_killable(struct rw_semaphore *sem)
-{
-	if (___down_write(sem))
-		if (IS_ERR(rwsem_down_write_failed_killable(sem)))
-			return -EINTR;
-
-	return 0;
-}
-
-/*
- * trylock for writing -- returns 1 if successful, 0 if contention
- */
-static inline int __down_write_trylock(struct rw_semaphore *sem)
-{
-	signed long old;
-
-	asm volatile(
-		"	lg	%0,%1\n"
-		"0:	ltgr	%0,%0\n"
-		"	jnz	1f\n"
-		"	csg	%0,%3,%1\n"
-		"	jl	0b\n"
-		"1:"
-		: "=&d" (old), "=Q" (sem->count)
-		: "Q" (sem->count), "d" (RWSEM_ACTIVE_WRITE_BIAS)
-		: "cc", "memory");
-	return (old == RWSEM_UNLOCKED_VALUE) ? 1 : 0;
-}
-
-/*
- * unlock after reading
- */
-static inline void __up_read(struct rw_semaphore *sem)
-{
-	signed long old, new;
-
-	asm volatile(
-		"	lg	%0,%2\n"
-		"0:	lgr	%1,%0\n"
-		"	aghi	%1,%4\n"
-		"	csg	%0,%1,%2\n"
-		"	jl	0b"
-		: "=&d" (old), "=&d" (new), "=Q" (sem->count)
-		: "Q" (sem->count), "i" (-RWSEM_ACTIVE_READ_BIAS)
-		: "cc", "memory");
-	if (new < 0)
-		if ((new & RWSEM_ACTIVE_MASK) == 0)
-			rwsem_wake(sem);
-}
-
-/*
- * unlock after writing
- */
-static inline void __up_write(struct rw_semaphore *sem)
-{
-	signed long old, new, tmp;
-
-	tmp = -RWSEM_ACTIVE_WRITE_BIAS;
-	asm volatile(
-		"	lg	%0,%2\n"
-		"0:	lgr	%1,%0\n"
-		"	ag	%1,%4\n"
-		"	csg	%0,%1,%2\n"
-		"	jl	0b"
-		: "=&d" (old), "=&d" (new), "=Q" (sem->count)
-		: "Q" (sem->count), "m" (tmp)
-		: "cc", "memory");
-	if (new < 0)
-		if ((new & RWSEM_ACTIVE_MASK) == 0)
-			rwsem_wake(sem);
-}
-
-/*
- * downgrade write lock to read lock
- */
-static inline void __downgrade_write(struct rw_semaphore *sem)
-{
-	signed long old, new, tmp;
-
-	tmp = -RWSEM_WAITING_BIAS;
-	asm volatile(
-		"	lg	%0,%2\n"
-		"0:	lgr	%1,%0\n"
-		"	ag	%1,%4\n"
-		"	csg	%0,%1,%2\n"
-		"	jl	0b"
-		: "=&d" (old), "=&d" (new), "=Q" (sem->count)
-		: "Q" (sem->count), "m" (tmp)
-		: "cc", "memory");
-	if (new > 1)
-		rwsem_downgrade_wake(sem);
-}
-
-#endif /* _S390_RWSEM_H */

arch/s390/include/asm/sections.h

@@ -4,6 +4,6 @@
 
 #include <asm-generic/sections.h>
 
-extern char _eshared[], _ehead[];
+extern char _ehead[];
 
 #endif

arch/s390/include/asm/setup.h

@@ -98,9 +98,6 @@ extern char vmpoff_cmd[];
 #define SET_CONSOLE_VT220	do { console_mode = 4; } while (0)
 #define SET_CONSOLE_HVC		do { console_mode = 5; } while (0)
 
-#define NSS_NAME_SIZE	8
-extern char kernel_nss_name[];
-
 #ifdef CONFIG_PFAULT
 extern int pfault_init(void);
 extern void pfault_fini(void);

arch/s390/include/asm/smp.h

@@ -28,6 +28,7 @@ extern void arch_send_call_function_ipi_mask(const struct cpumask *mask);
 
 extern void smp_call_online_cpu(void (*func)(void *), void *);
 extern void smp_call_ipl_cpu(void (*func)(void *), void *);
+extern void smp_emergency_stop(void);
 
 extern int smp_find_processor_id(u16 address);
 extern int smp_store_status(int cpu);
@@ -53,6 +54,10 @@ static inline void smp_call_online_cpu(void (*func)(void *), void *data)
 	func(data);
 }
 
+static inline void smp_emergency_stop(void)
+{
+}
+
 static inline int smp_find_processor_id(u16 address) { return 0; }
 static inline int smp_store_status(int cpu) { return 0; }
 static inline int smp_vcpu_scheduled(int cpu) { return 1; }

arch/s390/include/asm/spinlock.h

@@ -14,6 +14,7 @@
 #include <asm/atomic_ops.h>
 #include <asm/barrier.h>
 #include <asm/processor.h>
+#include <asm/alternative.h>
 
 #define SPINLOCK_LOCKVAL (S390_lowcore.spinlock_lockval)
 
@@ -36,20 +37,15 @@ bool arch_vcpu_is_preempted(int cpu);
  * (the type definitions are in asm/spinlock_types.h)
  */
 
-void arch_lock_relax(int cpu);
+void arch_spin_relax(arch_spinlock_t *lock);
 
 void arch_spin_lock_wait(arch_spinlock_t *);
 int arch_spin_trylock_retry(arch_spinlock_t *);
-void arch_spin_lock_wait_flags(arch_spinlock_t *, unsigned long flags);
-
-static inline void arch_spin_relax(arch_spinlock_t *lock)
-{
-	arch_lock_relax(lock->lock);
-}
+void arch_spin_lock_setup(int cpu);
 
 static inline u32 arch_spin_lockval(int cpu)
 {
-	return ~cpu;
+	return cpu + 1;
 }
 
 static inline int arch_spin_value_unlocked(arch_spinlock_t lock)
@@ -65,8 +61,7 @@ static inline int arch_spin_is_locked(arch_spinlock_t *lp)
 static inline int arch_spin_trylock_once(arch_spinlock_t *lp)
 {
 	barrier();
-	return likely(arch_spin_value_unlocked(*lp) &&
-		      __atomic_cmpxchg_bool(&lp->lock, 0, SPINLOCK_LOCKVAL));
+	return likely(__atomic_cmpxchg_bool(&lp->lock, 0, SPINLOCK_LOCKVAL));
 }
 
 static inline void arch_spin_lock(arch_spinlock_t *lp)
@@ -79,7 +74,7 @@ static inline void arch_spin_lock_flags(arch_spinlock_t *lp,
 					unsigned long flags)
 {
 	if (!arch_spin_trylock_once(lp))
-		arch_spin_lock_wait_flags(lp, flags);
+		arch_spin_lock_wait(lp);
 }
 
 static inline int arch_spin_trylock(arch_spinlock_t *lp)
@@ -93,11 +88,10 @@ static inline void arch_spin_unlock(arch_spinlock_t *lp)
 {
 	typecheck(int, lp->lock);
 	asm volatile(
-#ifdef CONFIG_HAVE_MARCH_ZEC12_FEATURES
-		"	.long	0xb2fa0070\n"	/* NIAI 7 */
-#endif
-		"	st	%1,%0\n"
-		: "=Q" (lp->lock) : "d" (0) : "cc", "memory");
+		ALTERNATIVE("", ".long 0xb2fa0070", 49)	/* NIAI 7 */
+		"	sth	%1,%0\n"
+		: "=Q" (((unsigned short *) &lp->lock)[1])
+		: "d" (0) : "cc", "memory");
 }
 
 /*
@@ -115,164 +109,63 @@ static inline void arch_spin_unlock(arch_spinlock_t *lp)
  * read_can_lock - would read_trylock() succeed?
  * @lock: the rwlock in question.
  */
-#define arch_read_can_lock(x) ((int)(x)->lock >= 0)
+#define arch_read_can_lock(x) (((x)->cnts & 0xffff0000) == 0)
 
 /**
  * write_can_lock - would write_trylock() succeed?
  * @lock: the rwlock in question.
  */
-#define arch_write_can_lock(x) ((x)->lock == 0)
-
-extern int _raw_read_trylock_retry(arch_rwlock_t *lp);
-extern int _raw_write_trylock_retry(arch_rwlock_t *lp);
+#define arch_write_can_lock(x) ((x)->cnts == 0)
 
 #define arch_read_lock_flags(lock, flags) arch_read_lock(lock)
 #define arch_write_lock_flags(lock, flags) arch_write_lock(lock)
+#define arch_read_relax(rw) barrier()
+#define arch_write_relax(rw) barrier()
 
-static inline int arch_read_trylock_once(arch_rwlock_t *rw)
-{
-	int old = ACCESS_ONCE(rw->lock);
-	return likely(old >= 0 &&
-		      __atomic_cmpxchg_bool(&rw->lock, old, old + 1));
-}
-
-static inline int arch_write_trylock_once(arch_rwlock_t *rw)
-{
-	int old = ACCESS_ONCE(rw->lock);
-	return likely(old == 0 &&
-		      __atomic_cmpxchg_bool(&rw->lock, 0, 0x80000000));
-}
-
-#ifdef CONFIG_HAVE_MARCH_Z196_FEATURES
-
-#define __RAW_OP_OR	"lao"
-#define __RAW_OP_AND	"lan"
-#define __RAW_OP_ADD	"laa"
-
-#define __RAW_LOCK(ptr, op_val, op_string)		\
-({							\
-	int old_val;					\
-							\
-	typecheck(int *, ptr);				\
-	asm volatile(					\
-		op_string "	%0,%2,%1\n"		\
-		"bcr	14,0\n"				\
-		: "=d" (old_val), "+Q" (*ptr)		\
-		: "d" (op_val)				\
-		: "cc", "memory");			\
-	old_val;					\
-})
-
-#define __RAW_UNLOCK(ptr, op_val, op_string)		\
-({							\
-	int old_val;					\
-							\
-	typecheck(int *, ptr);				\
-	asm volatile(					\
-		op_string "	%0,%2,%1\n"		\
-		: "=d" (old_val), "+Q" (*ptr)		\
-		: "d" (op_val)				\
-		: "cc", "memory");			\
-	old_val;					\
-})
-
-extern void _raw_read_lock_wait(arch_rwlock_t *lp);
-extern void _raw_write_lock_wait(arch_rwlock_t *lp, int prev);
+void arch_read_lock_wait(arch_rwlock_t *lp);
+void arch_write_lock_wait(arch_rwlock_t *lp);
 
 static inline void arch_read_lock(arch_rwlock_t *rw)
 {
 	int old;
 
-	old = __RAW_LOCK(&rw->lock, 1, __RAW_OP_ADD);
-	if (old < 0)
-		_raw_read_lock_wait(rw);
+	old = __atomic_add(1, &rw->cnts);
+	if (old & 0xffff0000)
+		arch_read_lock_wait(rw);
 }
 
 static inline void arch_read_unlock(arch_rwlock_t *rw)
 {
-	__RAW_UNLOCK(&rw->lock, -1, __RAW_OP_ADD);
+	__atomic_add_const_barrier(-1, &rw->cnts);
 }
 
 static inline void arch_write_lock(arch_rwlock_t *rw)
 {
-	int old;
-
-	old = __RAW_LOCK(&rw->lock, 0x80000000, __RAW_OP_OR);
-	if (old != 0)
-		_raw_write_lock_wait(rw, old);
-	rw->owner = SPINLOCK_LOCKVAL;
+	if (!__atomic_cmpxchg_bool(&rw->cnts, 0, 0x30000))
+		arch_write_lock_wait(rw);
 }
 
 static inline void arch_write_unlock(arch_rwlock_t *rw)
 {
-	rw->owner = 0;
-	__RAW_UNLOCK(&rw->lock, 0x7fffffff, __RAW_OP_AND);
+	__atomic_add_barrier(-0x30000, &rw->cnts);
 }
 
-#else /* CONFIG_HAVE_MARCH_Z196_FEATURES */
 
-extern void _raw_read_lock_wait(arch_rwlock_t *lp);
-extern void _raw_write_lock_wait(arch_rwlock_t *lp);
-
-static inline void arch_read_lock(arch_rwlock_t *rw)
-{
-	if (!arch_read_trylock_once(rw))
-		_raw_read_lock_wait(rw);
-}
-
-static inline void arch_read_unlock(arch_rwlock_t *rw)
+static inline int arch_read_trylock(arch_rwlock_t *rw)
 {
 	int old;
 
-	do {
-		old = ACCESS_ONCE(rw->lock);
-	} while (!__atomic_cmpxchg_bool(&rw->lock, old, old - 1));
-}
-
-static inline void arch_write_lock(arch_rwlock_t *rw)
-{
-	if (!arch_write_trylock_once(rw))
-		_raw_write_lock_wait(rw);
-	rw->owner = SPINLOCK_LOCKVAL;
-}
-
-static inline void arch_write_unlock(arch_rwlock_t *rw)
-{
-	typecheck(int, rw->lock);
-
-	rw->owner = 0;
-	asm volatile(
-		"st	%1,%0\n"
-		: "+Q" (rw->lock)
-		: "d" (0)
-		: "cc", "memory");
-}
-
-#endif /* CONFIG_HAVE_MARCH_Z196_FEATURES */
-
-static inline int arch_read_trylock(arch_rwlock_t *rw)
-{
-	if (!arch_read_trylock_once(rw))
-		return _raw_read_trylock_retry(rw);
-	return 1;
+	old = READ_ONCE(rw->cnts);
+	return (!(old & 0xffff0000) &&
+		__atomic_cmpxchg_bool(&rw->cnts, old, old + 1));
 }
 
 static inline int arch_write_trylock(arch_rwlock_t *rw)
 {
-	if (!arch_write_trylock_once(rw) && !_raw_write_trylock_retry(rw))
-		return 0;
-	rw->owner = SPINLOCK_LOCKVAL;
-	return 1;
-}
-
-static inline void arch_read_relax(arch_rwlock_t *rw)
-{
-	arch_lock_relax(rw->owner);
-}
+	int old;
 
-static inline void arch_write_relax(arch_rwlock_t *rw)
-{
-	arch_lock_relax(rw->owner);
+	old = READ_ONCE(rw->cnts);
+	return !old && __atomic_cmpxchg_bool(&rw->cnts, 0, 0x30000);
 }
 
 #endif /* __ASM_SPINLOCK_H */

arch/s390/include/asm/spinlock_types.h

@@ -13,8 +13,8 @@ typedef struct {
 #define __ARCH_SPIN_LOCK_UNLOCKED { .lock = 0, }
 
 typedef struct {
-	int lock;
-	int owner;
+	int cnts;
+	arch_spinlock_t wait;
 } arch_rwlock_t;
 
 #define __ARCH_RW_LOCK_UNLOCKED		{ 0 }

arch/s390/include/asm/string.h

@@ -18,6 +18,9 @@
 #define __HAVE_ARCH_MEMMOVE	/* gcc builtin & arch function */
 #define __HAVE_ARCH_MEMSCAN	/* inline & arch function */
 #define __HAVE_ARCH_MEMSET	/* gcc builtin & arch function */
+#define __HAVE_ARCH_MEMSET16	/* arch function */
+#define __HAVE_ARCH_MEMSET32	/* arch function */
+#define __HAVE_ARCH_MEMSET64	/* arch function */
 #define __HAVE_ARCH_STRCAT	/* inline & arch function */
 #define __HAVE_ARCH_STRCMP	/* arch function */
 #define __HAVE_ARCH_STRCPY	/* inline & arch function */
@@ -31,17 +34,17 @@
 #define __HAVE_ARCH_STRSTR	/* arch function */
 
 /* Prototypes for non-inlined arch strings functions. */
-extern int memcmp(const void *, const void *, size_t);
-extern void *memcpy(void *, const void *, size_t);
-extern void *memset(void *, int, size_t);
-extern void *memmove(void *, const void *, size_t);
-extern int strcmp(const char *,const char *);
-extern size_t strlcat(char *, const char *, size_t);
-extern size_t strlcpy(char *, const char *, size_t);
-extern char *strncat(char *, const char *, size_t);
-extern char *strncpy(char *, const char *, size_t);
-extern char *strrchr(const char *, int);
-extern char *strstr(const char *, const char *);
+int memcmp(const void *s1, const void *s2, size_t n);
+void *memcpy(void *dest, const void *src, size_t n);
+void *memset(void *s, int c, size_t n);
+void *memmove(void *dest, const void *src, size_t n);
+int strcmp(const char *s1, const char *s2);
+size_t strlcat(char *dest, const char *src, size_t n);
+size_t strlcpy(char *dest, const char *src, size_t size);
+char *strncat(char *dest, const char *src, size_t n);
+char *strncpy(char *dest, const char *src, size_t n);
+char *strrchr(const char *s, int c);
+char *strstr(const char *s1, const char *s2);
 
 #undef __HAVE_ARCH_STRCHR
 #undef __HAVE_ARCH_STRNCHR
@@ -50,7 +53,26 @@ extern char *strstr(const char *, const char *);
 #undef __HAVE_ARCH_STRSEP
 #undef __HAVE_ARCH_STRSPN
 
-#if !defined(IN_ARCH_STRING_C)
+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);
+
+static inline void *memset16(uint16_t *s, uint16_t v, size_t count)
+{
+	return __memset16(s, v, count * sizeof(v));
+}
+
+static inline void *memset32(uint32_t *s, uint32_t v, size_t count)
+{
+	return __memset32(s, v, count * sizeof(v));
+}
+
+static inline void *memset64(uint64_t *s, uint64_t v, size_t count)
+{
+	return __memset64(s, v, count * sizeof(v));
+}
+
+#if !defined(IN_ARCH_STRING_C) && (!defined(CONFIG_FORTIFY_SOURCE) || defined(__NO_FORTIFY))
 
 static inline void *memchr(const void * s, int c, size_t n)
 {

arch/s390/include/asm/switch_to.h

@@ -37,8 +37,8 @@ static inline void restore_access_regs(unsigned int *acrs)
 		save_ri_cb(prev->thread.ri_cb);				\
 		save_gs_cb(prev->thread.gs_cb);				\
 	}								\
+	update_cr_regs(next);						\
 	if (next->mm) {							\
-		update_cr_regs(next);					\
 		set_cpu_flag(CIF_FPU);					\
 		restore_access_regs(&next->thread.acrs[0]);		\
 		restore_ri_cb(next->thread.ri_cb, prev->thread.ri_cb);	\

arch/s390/include/asm/sysinfo.h

@@ -156,7 +156,8 @@ static inline unsigned char topology_mnest_limit(void)
 struct topology_core {
 	unsigned char nl;
 	unsigned char reserved0[3];
-	unsigned char :6;
+	unsigned char :5;
+	unsigned char d:1;
 	unsigned char pp:2;
 	unsigned char reserved1;
 	unsigned short origin;
@@ -198,4 +199,5 @@ struct service_level {
 int register_service_level(struct service_level *);
 int unregister_service_level(struct service_level *);
 
+int sthyi_fill(void *dst, u64 *rc);
 #endif /* __ASM_S390_SYSINFO_H */

arch/s390/include/asm/topology.h

@@ -17,6 +17,7 @@ struct cpu_topology_s390 {
 	unsigned short book_id;
 	unsigned short drawer_id;
 	unsigned short node_id;
+	unsigned short dedicated : 1;
 	cpumask_t thread_mask;
 	cpumask_t core_mask;
 	cpumask_t book_mask;
@@ -35,6 +36,7 @@ extern cpumask_t cpus_with_topology;
 #define topology_book_cpumask(cpu)	  (&cpu_topology[cpu].book_mask)
 #define topology_drawer_id(cpu)		  (cpu_topology[cpu].drawer_id)
 #define topology_drawer_cpumask(cpu)	  (&cpu_topology[cpu].drawer_mask)
+#define topology_cpu_dedicated(cpu)	  (cpu_topology[cpu].dedicated)
 
 #define mc_capable() 1
 

arch/s390/include/asm/vdso.h

@@ -47,6 +47,7 @@ struct vdso_per_cpu_data {
 
 extern struct vdso_data *vdso_data;
 
+void vdso_alloc_boot_cpu(struct lowcore *lowcore);
 int vdso_alloc_per_cpu(struct lowcore *lowcore);
 void vdso_free_per_cpu(struct lowcore *lowcore);
 

arch/s390/include/uapi/asm/kvm_virtio.h

-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-/*
- * definition for virtio for kvm on s390
- *
- * Copyright IBM Corp. 2008
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
- *    Author(s): Christian Borntraeger <borntraeger@de.ibm.com>
- */
-
-#ifndef __KVM_S390_VIRTIO_H
-#define __KVM_S390_VIRTIO_H
-
-#include <linux/types.h>
-
-struct kvm_device_desc {
-	/* The device type: console, network, disk etc.  Type 0 terminates. */
-	__u8 type;
-	/* The number of virtqueues (first in config array) */
-	__u8 num_vq;
-	/*
-	 * The number of bytes of feature bits.  Multiply by 2: one for host
-	 * features and one for guest acknowledgements.
-	 */
-	__u8 feature_len;
-	/* The number of bytes of the config array after virtqueues. */
-	__u8 config_len;
-	/* A status byte, written by the Guest. */
-	__u8 status;
-	__u8 config[0];
-};
-
-/*
- * This is how we expect the device configuration field for a virtqueue
- * to be laid out in config space.
- */
-struct kvm_vqconfig {
-	/* The token returned with an interrupt. Set by the guest */
-	__u64 token;
-	/* The address of the virtio ring */
-	__u64 address;
-	/* The number of entries in the virtio_ring */
-	__u16 num;
-
-};
-
-#define KVM_S390_VIRTIO_NOTIFY		0
-#define KVM_S390_VIRTIO_RESET		1
-#define KVM_S390_VIRTIO_SET_STATUS	2
-
-/* The alignment to use between consumer and producer parts of vring.
- * This is pagesize for historical reasons. */
-#define KVM_S390_VIRTIO_RING_ALIGN	4096
-
-
-/* These values are supposed to be in ext_params on an interrupt */
-#define VIRTIO_PARAM_MASK		0xff
-#define VIRTIO_PARAM_VRING_INTERRUPT	0x0
-#define VIRTIO_PARAM_CONFIG_CHANGED	0x1
-#define VIRTIO_PARAM_DEV_ADD		0x2
-
-#endif

arch/s390/include/uapi/asm/sthyi.h

+#ifndef _UAPI_ASM_STHYI_H
+#define _UAPI_ASM_STHYI_H
+
+#define STHYI_FC_CP_IFL_CAP	0
+
+#endif /* _UAPI_ASM_STHYI_H */

arch/s390/include/uapi/asm/unistd.h

@@ -316,7 +316,8 @@
 #define __NR_pwritev2		377
 #define __NR_s390_guarded_storage	378
 #define __NR_statx		379
-#define NR_syscalls 380
+#define __NR_s390_sthyi		380
+#define NR_syscalls 381
 
 /* 
  * There are some system calls that are not present on 64 bit, some

arch/s390/kernel/Makefile

@@ -34,6 +34,8 @@ AFLAGS_REMOVE_head.o	+= $(CC_FLAGS_MARCH)
 AFLAGS_head.o		+= -march=z900
 endif
 
+CFLAGS_als.o		+= -D__NO_FORTIFY
+
 #
 # Passing null pointers is ok for smp code, since we access the lowcore here.
 #
@@ -56,7 +58,7 @@ obj-y	:= traps.o time.o process.o base.o early.o setup.o idle.o vtime.o
 obj-y	+= processor.o sys_s390.o ptrace.o signal.o cpcmd.o ebcdic.o nmi.o
 obj-y	+= debug.o irq.o ipl.o dis.o diag.o vdso.o als.o
 obj-y	+= sysinfo.o jump_label.o lgr.o os_info.o machine_kexec.o pgm_check.o
-obj-y	+= runtime_instr.o cache.o fpu.o dumpstack.o guarded_storage.o
+obj-y	+= runtime_instr.o cache.o fpu.o dumpstack.o guarded_storage.o sthyi.o
 obj-y	+= entry.o reipl.o relocate_kernel.o kdebugfs.o
 
 extra-y				+= head.o head64.o vmlinux.lds
@@ -75,6 +77,7 @@ obj-$(CONFIG_KPROBES)		+= kprobes.o
 obj-$(CONFIG_FUNCTION_TRACER)	+= mcount.o ftrace.o
 obj-$(CONFIG_CRASH_DUMP)	+= crash_dump.o
 obj-$(CONFIG_UPROBES)		+= uprobes.o
+obj-$(CONFIG_ALTERNATIVES)	+= alternative.o
 
 obj-$(CONFIG_PERF_EVENTS)	+= perf_event.o perf_cpum_cf.o perf_cpum_sf.o
 obj-$(CONFIG_PERF_EVENTS)	+= perf_cpum_cf_events.o

arch/s390/kernel/alternative.c

+#include <linux/module.h>
+#include <asm/alternative.h>
+#include <asm/facility.h>
+
+#define MAX_PATCH_LEN (255 - 1)
+
+static int __initdata_or_module alt_instr_disabled;
+
+static int __init disable_alternative_instructions(char *str)
+{
+	alt_instr_disabled = 1;
+	return 0;
+}
+
+early_param("noaltinstr", disable_alternative_instructions);
+
+struct brcl_insn {
+	u16 opc;
+	s32 disp;
+} __packed;
+
+static u16 __initdata_or_module nop16 = 0x0700;
+static u32 __initdata_or_module nop32 = 0x47000000;
+static struct brcl_insn __initdata_or_module nop48 = {
+	0xc004, 0
+};
+
+static const void *nops[] __initdata_or_module = {
+	&nop16,
+	&nop32,
+	&nop48
+};
+
+static void __init_or_module add_jump_padding(void *insns, unsigned int len)
+{
+	struct brcl_insn brcl = {
+		0xc0f4,
+		len / 2
+	};
+
+	memcpy(insns, &brcl, sizeof(brcl));
+	insns += sizeof(brcl);
+	len -= sizeof(brcl);
+
+	while (len > 0) {
+		memcpy(insns, &nop16, 2);
+		insns += 2;
+		len -= 2;
+	}
+}
+
+static void __init_or_module add_padding(void *insns, unsigned int len)
+{
+	if (len > 6)
+		add_jump_padding(insns, len);
+	else if (len >= 2)
+		memcpy(insns, nops[len / 2 - 1], len);
+}
+
+static void __init_or_module __apply_alternatives(struct alt_instr *start,
+						  struct alt_instr *end)
+{
+	struct alt_instr *a;
+	u8 *instr, *replacement;
+	u8 insnbuf[MAX_PATCH_LEN];
+
+	/*
+	 * The scan order should be from start to end. A later scanned
+	 * alternative code can overwrite previously scanned alternative code.
+	 */
+	for (a = start; a < end; a++) {
+		int insnbuf_sz = 0;
+
+		instr = (u8 *)&a->instr_offset + a->instr_offset;
+		replacement = (u8 *)&a->repl_offset + a->repl_offset;
+
+		if (!test_facility(a->facility))
+			continue;
+
+		if (unlikely(a->instrlen % 2 || a->replacementlen % 2)) {
+			WARN_ONCE(1, "cpu alternatives instructions length is "
+				     "odd, skipping patching\n");
+			continue;
+		}
+
+		memcpy(insnbuf, replacement, a->replacementlen);
+		insnbuf_sz = a->replacementlen;
+
+		if (a->instrlen > a->replacementlen) {
+			add_padding(insnbuf + a->replacementlen,
+				    a->instrlen - a->replacementlen);
+			insnbuf_sz += a->instrlen - a->replacementlen;
+		}
+
+		s390_kernel_write(instr, insnbuf, insnbuf_sz);
+	}
+}
+
+void __init_or_module apply_alternatives(struct alt_instr *start,
+					 struct alt_instr *end)
+{
+	if (!alt_instr_disabled)
+		__apply_alternatives(start, end);
+}
+
+extern struct alt_instr __alt_instructions[], __alt_instructions_end[];
+void __init apply_alternative_instructions(void)
+{
+	apply_alternatives(__alt_instructions, __alt_instructions_end);
+}

arch/s390/kernel/asm-offsets.c

@@ -14,6 +14,7 @@
 #include <asm/vdso.h>
 #include <asm/pgtable.h>
 #include <asm/gmap.h>
+#include <asm/nmi.h>
 
 /*
  * Make sure that the compiler is new enough. We want a compiler that
@@ -159,6 +160,7 @@ int main(void)
 	OFFSET(__LC_LAST_UPDATE_CLOCK, lowcore, last_update_clock);
 	OFFSET(__LC_INT_CLOCK, lowcore, int_clock);
 	OFFSET(__LC_MCCK_CLOCK, lowcore, mcck_clock);
+	OFFSET(__LC_CLOCK_COMPARATOR, lowcore, clock_comparator);
 	OFFSET(__LC_BOOT_CLOCK, lowcore, boot_clock);
 	OFFSET(__LC_CURRENT, lowcore, current_task);
 	OFFSET(__LC_KERNEL_STACK, lowcore, kernel_stack);
@@ -194,6 +196,9 @@ int main(void)
 	OFFSET(__LC_CREGS_SAVE_AREA, lowcore, cregs_save_area);
 	OFFSET(__LC_PGM_TDB, lowcore, pgm_tdb);
 	BLANK();
+	/* extended machine check save area */
+	OFFSET(__MCESA_GS_SAVE_AREA, mcesa, guarded_storage_save_area);
+	BLANK();
 	/* gmap/sie offsets */
 	OFFSET(__GMAP_ASCE, gmap, asce);
 	OFFSET(__SIE_PROG0C, kvm_s390_sie_block, prog0c);

arch/s390/kernel/compat_wrapper.c

@@ -181,3 +181,4 @@ COMPAT_SYSCALL_WRAP3(mlock2, unsigned long, start, size_t, len, int, flags);
 COMPAT_SYSCALL_WRAP6(copy_file_range, int, fd_in, loff_t __user *, off_in, int, fd_out, loff_t __user *, off_out, size_t, len, unsigned int, flags);
 COMPAT_SYSCALL_WRAP2(s390_guarded_storage, int, command, struct gs_cb *, gs_cb);
 COMPAT_SYSCALL_WRAP5(statx, int, dfd, const char __user *, path, unsigned, flags, unsigned, mask, struct statx __user *, buffer);
+COMPAT_SYSCALL_WRAP4(s390_sthyi, unsigned long, code, void __user *, info, u64 __user *, rc, unsigned long, flags);

arch/s390/kernel/early.c

@@ -31,14 +31,6 @@
 #include <asm/facility.h>
 #include "entry.h"
 
-/*
- * Create a Kernel NSS if the SAVESYS= parameter is defined
- */
-#define DEFSYS_CMD_SIZE		128
-#define SAVESYS_CMD_SIZE	32
-
-char kernel_nss_name[NSS_NAME_SIZE + 1];
-
 static void __init setup_boot_command_line(void);
 
 /*
@@ -59,134 +51,6 @@ static void __init reset_tod_clock(void)
 	S390_lowcore.last_update_clock = TOD_UNIX_EPOCH;
 }
 
-#ifdef CONFIG_SHARED_KERNEL
-int __init savesys_ipl_nss(char *cmd, const int cmdlen);
-
-asm(
-	"	.section .init.text,\"ax\",@progbits\n"
-	"	.align	4\n"
-	"	.type	savesys_ipl_nss, @function\n"
-	"savesys_ipl_nss:\n"
-	"	stmg	6,15,48(15)\n"
-	"	lgr	14,3\n"
-	"	sam31\n"
-	"	diag	2,14,0x8\n"
-	"	sam64\n"
-	"	lgr	2,14\n"
-	"	lmg	6,15,48(15)\n"
-	"	br	14\n"
-	"	.size	savesys_ipl_nss, .-savesys_ipl_nss\n"
-	"	.previous\n");
-
-static __initdata char upper_command_line[COMMAND_LINE_SIZE];
-
-static noinline __init void create_kernel_nss(void)
-{
-	unsigned int i, stext_pfn, eshared_pfn, end_pfn, min_size;
-#ifdef CONFIG_BLK_DEV_INITRD
-	unsigned int sinitrd_pfn, einitrd_pfn;
-#endif
-	int response;
-	int hlen;
-	size_t len;
-	char *savesys_ptr;
-	char defsys_cmd[DEFSYS_CMD_SIZE];
-	char savesys_cmd[SAVESYS_CMD_SIZE];
-
-	/* Do nothing if we are not running under VM */
-	if (!MACHINE_IS_VM)
-		return;
-
-	/* Convert COMMAND_LINE to upper case */
-	for (i = 0; i < strlen(boot_command_line); i++)
-		upper_command_line[i] = toupper(boot_command_line[i]);
-
-	savesys_ptr = strstr(upper_command_line, "SAVESYS=");
-
-	if (!savesys_ptr)
-		return;
-
-	savesys_ptr += 8;    /* Point to the beginning of the NSS name */
-	for (i = 0; i < NSS_NAME_SIZE; i++) {
-		if (savesys_ptr[i] == ' ' || savesys_ptr[i] == '\0')
-			break;
-		kernel_nss_name[i] = savesys_ptr[i];
-	}
-
-	stext_pfn = PFN_DOWN(__pa(&_stext));
-	eshared_pfn = PFN_DOWN(__pa(&_eshared));
-	end_pfn = PFN_UP(__pa(&_end));
-	min_size = end_pfn << 2;
-
-	hlen = snprintf(defsys_cmd, DEFSYS_CMD_SIZE,
-			"DEFSYS %s 00000-%.5X EW %.5X-%.5X SR %.5X-%.5X",
-			kernel_nss_name, stext_pfn - 1, stext_pfn,
-			eshared_pfn - 1, eshared_pfn, end_pfn);
-
-#ifdef CONFIG_BLK_DEV_INITRD
-	if (INITRD_START && INITRD_SIZE) {
-		sinitrd_pfn = PFN_DOWN(__pa(INITRD_START));
-		einitrd_pfn = PFN_UP(__pa(INITRD_START + INITRD_SIZE));
-		min_size = einitrd_pfn << 2;
-		hlen += snprintf(defsys_cmd + hlen, DEFSYS_CMD_SIZE - hlen,
-				 " EW %.5X-%.5X", sinitrd_pfn, einitrd_pfn);
-	}
-#endif
-
-	snprintf(defsys_cmd + hlen, DEFSYS_CMD_SIZE - hlen,
-		 " EW MINSIZE=%.7iK PARMREGS=0-13", min_size);
-	defsys_cmd[DEFSYS_CMD_SIZE - 1] = '\0';
-	snprintf(savesys_cmd, SAVESYS_CMD_SIZE, "SAVESYS %s \n IPL %s",
-		 kernel_nss_name, kernel_nss_name);
-	savesys_cmd[SAVESYS_CMD_SIZE - 1] = '\0';
-
-	__cpcmd(defsys_cmd, NULL, 0, &response);
-
-	if (response != 0) {
-		pr_err("Defining the Linux kernel NSS failed with rc=%d\n",
-			response);
-		kernel_nss_name[0] = '\0';
-		return;
-	}
-
-	len = strlen(savesys_cmd);
-	ASCEBC(savesys_cmd, len);
-	response = savesys_ipl_nss(savesys_cmd, len);
-
-	/* On success: response is equal to the command size,
-	 *	       max SAVESYS_CMD_SIZE
-	 * On error: response contains the numeric portion of cp error message.
-	 *	     for SAVESYS it will be >= 263
-	 *	     for missing privilege class, it will be 1
-	 */
-	if (response > SAVESYS_CMD_SIZE || response == 1) {
-		pr_err("Saving the Linux kernel NSS failed with rc=%d\n",
-			response);
-		kernel_nss_name[0] = '\0';
-		return;
-	}
-
-	/* re-initialize cputime accounting. */
-	get_tod_clock_ext(tod_clock_base);
-	S390_lowcore.last_update_clock = *(__u64 *) &tod_clock_base[1];
-	S390_lowcore.last_update_timer = 0x7fffffffffffffffULL;
-	S390_lowcore.user_timer = 0;
-	S390_lowcore.system_timer = 0;
-	asm volatile("SPT 0(%0)" : : "a" (&S390_lowcore.last_update_timer));
-
-	/* re-setup boot command line with new ipl vm parms */
-	ipl_update_parameters();
-	setup_boot_command_line();
-
-	ipl_flags = IPL_NSS_VALID;
-}
-
-#else /* CONFIG_SHARED_KERNEL */
-
-static inline void create_kernel_nss(void) { }
-
-#endif /* CONFIG_SHARED_KERNEL */
-
 /*
  * Clear bss memory
  */
@@ -375,8 +239,10 @@ static __init void detect_machine_facilities(void)
 		S390_lowcore.machine_flags |= MACHINE_FLAG_IDTE;
 	if (test_facility(40))
 		S390_lowcore.machine_flags |= MACHINE_FLAG_LPP;
-	if (test_facility(50) && test_facility(73))
+	if (test_facility(50) && test_facility(73)) {
 		S390_lowcore.machine_flags |= MACHINE_FLAG_TE;
+		__ctl_set_bit(0, 55);
+	}
 	if (test_facility(51))
 		S390_lowcore.machine_flags |= MACHINE_FLAG_TLB_LC;
 	if (test_facility(129)) {
@@ -549,10 +415,6 @@ static void __init setup_boot_command_line(void)
 	append_to_cmdline(append_ipl_scpdata);
 }
 
-/*
- * Save ipl parameters, clear bss memory, initialize storage keys
- * and create a kernel NSS at startup if the SAVESYS= parm is defined
- */
 void __init startup_init(void)
 {
 	reset_tod_clock();
@@ -569,7 +431,6 @@ void __init startup_init(void)
 	setup_arch_string();
 	ipl_update_parameters();
 	setup_boot_command_line();
-	create_kernel_nss();
 	detect_diag9c();
 	detect_diag44();
 	detect_machine_facilities();

arch/s390/kernel/entry.S

@@ -13,6 +13,7 @@
 #include <linux/linkage.h>
 #include <asm/processor.h>
 #include <asm/cache.h>
+#include <asm/ctl_reg.h>
 #include <asm/errno.h>
 #include <asm/ptrace.h>
 #include <asm/thread_info.h>
@@ -952,15 +953,56 @@ load_fpu_regs:
  */
 ENTRY(mcck_int_handler)
 	STCK	__LC_MCCK_CLOCK
-	la	%r1,4095		# revalidate r1
-	spt	__LC_CPU_TIMER_SAVE_AREA-4095(%r1)	# revalidate cpu timer
-	lmg	%r0,%r15,__LC_GPREGS_SAVE_AREA-4095(%r1)# revalidate gprs
+	la	%r1,4095		# validate r1
+	spt	__LC_CPU_TIMER_SAVE_AREA-4095(%r1)	# validate cpu timer
+	sckc	__LC_CLOCK_COMPARATOR			# validate comparator
+	lam	%a0,%a15,__LC_AREGS_SAVE_AREA-4095(%r1) # validate acrs
+	lmg	%r0,%r15,__LC_GPREGS_SAVE_AREA-4095(%r1)# validate gprs
 	lg	%r12,__LC_CURRENT
 	larl	%r13,cleanup_critical
 	lmg	%r8,%r9,__LC_MCK_OLD_PSW
 	TSTMSK	__LC_MCCK_CODE,MCCK_CODE_SYSTEM_DAMAGE
 	jo	.Lmcck_panic		# yes -> rest of mcck code invalid
-	lghi	%r14,__LC_CPU_TIMER_SAVE_AREA
+	TSTMSK	__LC_MCCK_CODE,MCCK_CODE_CR_VALID
+	jno	.Lmcck_panic		# control registers invalid -> panic
+	la	%r14,4095
+	lctlg	%c0,%c15,__LC_CREGS_SAVE_AREA-4095(%r14) # validate ctl regs
+	ptlb
+	lg	%r11,__LC_MCESAD-4095(%r14) # extended machine check save area
+	nill	%r11,0xfc00		# MCESA_ORIGIN_MASK
+	TSTMSK	__LC_CREGS_SAVE_AREA+16-4095(%r14),CR2_GUARDED_STORAGE
+	jno	0f
+	TSTMSK	__LC_MCCK_CODE,MCCK_CODE_GS_VALID
+	jno	0f
+	.insn	 rxy,0xe3000000004d,0,__MCESA_GS_SAVE_AREA(%r11) # LGSC
+0:	l	%r14,__LC_FP_CREG_SAVE_AREA-4095(%r14)
+	TSTMSK	__LC_MCCK_CODE,MCCK_CODE_FC_VALID
+	jo	0f
+	sr	%r14,%r14
+0:	sfpc	%r14
+	TSTMSK	__LC_MACHINE_FLAGS,MACHINE_FLAG_VX
+	jo	0f
+	lghi	%r14,__LC_FPREGS_SAVE_AREA
+	ld	%f0,0(%r14)
+	ld	%f1,8(%r14)
+	ld	%f2,16(%r14)
+	ld	%f3,24(%r14)
+	ld	%f4,32(%r14)
+	ld	%f5,40(%r14)
+	ld	%f6,48(%r14)
+	ld	%f7,56(%r14)
+	ld	%f8,64(%r14)
+	ld	%f9,72(%r14)
+	ld	%f10,80(%r14)
+	ld	%f11,88(%r14)
+	ld	%f12,96(%r14)
+	ld	%f13,104(%r14)
+	ld	%f14,112(%r14)
+	ld	%f15,120(%r14)
+	j	1f
+0:	VLM	%v0,%v15,0,%r11
+	VLM	%v16,%v31,256,%r11
+1:	lghi	%r14,__LC_CPU_TIMER_SAVE_AREA
 	mvc	__LC_MCCK_ENTER_TIMER(8),0(%r14)
 	TSTMSK	__LC_MCCK_CODE,MCCK_CODE_CPU_TIMER_VALID
 	jo	3f
@@ -976,9 +1018,13 @@ ENTRY(mcck_int_handler)
 	la	%r14,__LC_LAST_UPDATE_TIMER
 2:	spt	0(%r14)
 	mvc	__LC_MCCK_ENTER_TIMER(8),0(%r14)
-3:	TSTMSK	__LC_MCCK_CODE,(MCCK_CODE_PSW_MWP_VALID|MCCK_CODE_PSW_IA_VALID)
-	jno	.Lmcck_panic		# no -> skip cleanup critical
-	SWITCH_ASYNC __LC_GPREGS_SAVE_AREA+64,__LC_MCCK_ENTER_TIMER
+3:	TSTMSK	__LC_MCCK_CODE,MCCK_CODE_PSW_MWP_VALID
+	jno	.Lmcck_panic
+	tmhh	%r8,0x0001		# interrupting from user ?
+	jnz	4f
+	TSTMSK	__LC_MCCK_CODE,MCCK_CODE_PSW_IA_VALID
+	jno	.Lmcck_panic
+4:	SWITCH_ASYNC __LC_GPREGS_SAVE_AREA+64,__LC_MCCK_ENTER_TIMER
 .Lmcck_skip:
 	lghi	%r14,__LC_GPREGS_SAVE_AREA+64
 	stmg	%r0,%r7,__PT_R0(%r11)

arch/s390/kernel/entry.h

@@ -78,6 +78,7 @@ long sys_s390_runtime_instr(int command, int signum);
 long sys_s390_guarded_storage(int command, struct gs_cb __user *);
 long sys_s390_pci_mmio_write(unsigned long, const void __user *, size_t);
 long sys_s390_pci_mmio_read(unsigned long, void __user *, size_t);
+long sys_s390_sthyi(unsigned long function_code, void __user *buffer, u64 __user *return_code, unsigned long flags);
 
 DECLARE_PER_CPU(u64, mt_cycles[8]);
 

arch/s390/kernel/guarded_storage.c

@@ -12,11 +12,10 @@
 #include <asm/guarded_storage.h>
 #include "entry.h"
 
-void exit_thread_gs(void)
+void guarded_storage_release(struct task_struct *tsk)
 {
-	kfree(current->thread.gs_cb);
-	kfree(current->thread.gs_bc_cb);
-	current->thread.gs_cb = current->thread.gs_bc_cb = NULL;
+	kfree(tsk->thread.gs_cb);
+	kfree(tsk->thread.gs_bc_cb);
 }
 
 static int gs_enable(void)

arch/s390/kernel/ipl.c

@@ -279,8 +279,6 @@ static __init enum ipl_type get_ipl_type(void)
 {
 	struct ipl_parameter_block *ipl = IPL_PARMBLOCK_START;
 
-	if (ipl_flags & IPL_NSS_VALID)
-		return IPL_TYPE_NSS;
 	if (!(ipl_flags & IPL_DEVNO_VALID))
 		return IPL_TYPE_UNKNOWN;
 	if (!(ipl_flags & IPL_PARMBLOCK_VALID))
@@ -533,22 +531,6 @@ static struct attribute_group ipl_ccw_attr_group_lpar = {
 	.attrs = ipl_ccw_attrs_lpar
 };
 
-/* NSS ipl device attributes */
-
-DEFINE_IPL_ATTR_RO(ipl_nss, name, "%s\n", kernel_nss_name);
-
-static struct attribute *ipl_nss_attrs[] = {
-	&sys_ipl_type_attr.attr,
-	&sys_ipl_nss_name_attr.attr,
-	&sys_ipl_ccw_loadparm_attr.attr,
-	&sys_ipl_vm_parm_attr.attr,
-	NULL,
-};
-
-static struct attribute_group ipl_nss_attr_group = {
-	.attrs = ipl_nss_attrs,
-};
-
 /* UNKNOWN ipl device attributes */
 
 static struct attribute *ipl_unknown_attrs[] = {
@@ -598,9 +580,6 @@ static int __init ipl_init(void)
 	case IPL_TYPE_FCP_DUMP:
 		rc = sysfs_create_group(&ipl_kset->kobj, &ipl_fcp_attr_group);
 		break;
-	case IPL_TYPE_NSS:
-		rc = sysfs_create_group(&ipl_kset->kobj, &ipl_nss_attr_group);
-		break;
 	default:
 		rc = sysfs_create_group(&ipl_kset->kobj,
 					&ipl_unknown_attr_group);
@@ -1172,18 +1151,6 @@ static int __init reipl_nss_init(void)
 		return rc;
 
 	reipl_block_ccw_init(reipl_block_nss);
-	if (ipl_info.type == IPL_TYPE_NSS) {
-		memset(reipl_block_nss->ipl_info.ccw.nss_name,
-			' ', NSS_NAME_SIZE);
-		memcpy(reipl_block_nss->ipl_info.ccw.nss_name,
-			kernel_nss_name, strlen(kernel_nss_name));
-		ASCEBC(reipl_block_nss->ipl_info.ccw.nss_name, NSS_NAME_SIZE);
-		reipl_block_nss->ipl_info.ccw.vm_flags |=
-			DIAG308_VM_FLAGS_NSS_VALID;
-
-		reipl_block_ccw_fill_parms(reipl_block_nss);
-	}
-
 	reipl_capabilities |= IPL_TYPE_NSS;
 	return 0;
 }
@@ -1971,9 +1938,6 @@ void __init setup_ipl(void)
 		ipl_info.data.fcp.lun = IPL_PARMBLOCK_START->ipl_info.fcp.lun;
 		break;
 	case IPL_TYPE_NSS:
-		strncpy(ipl_info.data.nss.name, kernel_nss_name,
-			sizeof(ipl_info.data.nss.name));
-		break;
 	case IPL_TYPE_UNKNOWN:
 		/* We have no info to copy */
 		break;

arch/s390/kernel/kprobes.c

@@ -161,8 +161,6 @@ struct swap_insn_args {
 
 static int swap_instruction(void *data)
 {
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-	unsigned long status = kcb->kprobe_status;
 	struct swap_insn_args *args = data;
 	struct ftrace_insn new_insn, *insn;
 	struct kprobe *p = args->p;
@@ -185,9 +183,7 @@ static int swap_instruction(void *data)
 			ftrace_generate_nop_insn(&new_insn);
 	}
 skip_ftrace:
-	kcb->kprobe_status = KPROBE_SWAP_INST;
 	s390_kernel_write(p->addr, &new_insn, len);
-	kcb->kprobe_status = status;
 	return 0;
 }
 NOKPROBE_SYMBOL(swap_instruction);
@@ -574,9 +570,6 @@ static int kprobe_trap_handler(struct pt_regs *regs, int trapnr)
 	const struct exception_table_entry *entry;
 
 	switch(kcb->kprobe_status) {
-	case KPROBE_SWAP_INST:
-		/* We are here because the instruction replacement failed */
-		return 0;
 	case KPROBE_HIT_SS:
 	case KPROBE_REENTER:
 		/*

arch/s390/kernel/machine_kexec.c

@@ -106,7 +106,7 @@ static void __do_machine_kdump(void *image)
 static noinline void __machine_kdump(void *image)
 {
 	struct mcesa *mcesa;
-	unsigned long cr2_old, cr2_new;
+	union ctlreg2 cr2_old, cr2_new;
 	int this_cpu, cpu;
 
 	lgr_info_log();
@@ -123,11 +123,12 @@ static noinline void __machine_kdump(void *image)
 	if (MACHINE_HAS_VX)
 		save_vx_regs((__vector128 *) mcesa->vector_save_area);
 	if (MACHINE_HAS_GS) {
-		__ctl_store(cr2_old, 2, 2);
-		cr2_new = cr2_old | (1UL << 4);
-		__ctl_load(cr2_new, 2, 2);
+		__ctl_store(cr2_old.val, 2, 2);
+		cr2_new = cr2_old;
+		cr2_new.gse = 1;
+		__ctl_load(cr2_new.val, 2, 2);
 		save_gs_cb((struct gs_cb *) mcesa->guarded_storage_save_area);
-		__ctl_load(cr2_old, 2, 2);
+		__ctl_load(cr2_old.val, 2, 2);
 	}
 	/*
 	 * To create a good backchain for this CPU in the dump store_status
@@ -145,7 +146,7 @@ static noinline void __machine_kdump(void *image)
 /*
  * Check if kdump checksums are valid: We call purgatory with parameter "0"
  */
-static int kdump_csum_valid(struct kimage *image)
+static bool kdump_csum_valid(struct kimage *image)
 {
 #ifdef CONFIG_CRASH_DUMP
 	int (*start_kdump)(int) = (void *)image->start;
@@ -154,9 +155,9 @@ static int kdump_csum_valid(struct kimage *image)
 	__arch_local_irq_stnsm(0xfb); /* disable DAT */
 	rc = start_kdump(0);
 	__arch_local_irq_stosm(0x04); /* enable DAT */
-	return rc ? 0 : -EINVAL;
+	return rc == 0;
 #else
-	return -EINVAL;
+	return false;
 #endif
 }
 
@@ -219,10 +220,6 @@ int machine_kexec_prepare(struct kimage *image)
 {
 	void *reboot_code_buffer;
 
-	/* Can't replace kernel image since it is read-only. */
-	if (ipl_flags & IPL_NSS_VALID)
-		return -EOPNOTSUPP;
-
 	if (image->type == KEXEC_TYPE_CRASH)
 		return machine_kexec_prepare_kdump();
 
@@ -269,6 +266,7 @@ static void __do_machine_kexec(void *data)
 	s390_reset_system();
 	data_mover = (relocate_kernel_t) page_to_phys(image->control_code_page);
 
+	__arch_local_irq_stnsm(0xfb); /* disable DAT - avoid no-execute */
 	/* Call the moving routine */
 	(*data_mover)(&image->head, image->start);
 

arch/s390/kernel/module.c

@@ -31,6 +31,7 @@
 #include <linux/kernel.h>
 #include <linux/moduleloader.h>
 #include <linux/bug.h>
+#include <asm/alternative.h>
 
 #if 0
 #define DEBUGP printk
@@ -429,6 +430,22 @@ int module_finalize(const Elf_Ehdr *hdr,
 		    const Elf_Shdr *sechdrs,
 		    struct module *me)
 {
+	const Elf_Shdr *s;
+	char *secstrings;
+
+	if (IS_ENABLED(CONFIG_ALTERNATIVES)) {
+		secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
+		for (s = sechdrs; s < sechdrs + hdr->e_shnum; s++) {
+			if (!strcmp(".altinstructions",
+				    secstrings + s->sh_name)) {
+				/* patch .altinstructions */
+				void *aseg = (void *)s->sh_addr;
+
+				apply_alternatives(aseg, aseg + s->sh_size);
+			}
+		}
+	}
+
 	jump_label_apply_nops(me);
 	return 0;
 }

arch/s390/kernel/nmi.c

@@ -12,6 +12,9 @@
 #include <linux/init.h>
 #include <linux/errno.h>
 #include <linux/hardirq.h>
+#include <linux/log2.h>
+#include <linux/kprobes.h>
+#include <linux/slab.h>
 #include <linux/time.h>
 #include <linux/module.h>
 #include <linux/sched/signal.h>
@@ -37,13 +40,94 @@ struct mcck_struct {
 };
 
 static DEFINE_PER_CPU(struct mcck_struct, cpu_mcck);
+static struct kmem_cache *mcesa_cache;
+static unsigned long mcesa_origin_lc;
 
-static void s390_handle_damage(void)
+static inline int nmi_needs_mcesa(void)
 {
-	smp_send_stop();
+	return MACHINE_HAS_VX || MACHINE_HAS_GS;
+}
+
+static inline unsigned long nmi_get_mcesa_size(void)
+{
+	if (MACHINE_HAS_GS)
+		return MCESA_MAX_SIZE;
+	return MCESA_MIN_SIZE;
+}
+
+/*
+ * The initial machine check extended save area for the boot CPU.
+ * It will be replaced by nmi_init() with an allocated structure.
+ * The structure is required for machine check happening early in
+ * the boot process.
+ */
+static struct mcesa boot_mcesa __initdata __aligned(MCESA_MAX_SIZE);
+
+void __init nmi_alloc_boot_cpu(struct lowcore *lc)
+{
+	if (!nmi_needs_mcesa())
+		return;
+	lc->mcesad = (unsigned long) &boot_mcesa;
+	if (MACHINE_HAS_GS)
+		lc->mcesad |= ilog2(MCESA_MAX_SIZE);
+}
+
+static int __init nmi_init(void)
+{
+	unsigned long origin, cr0, size;
+
+	if (!nmi_needs_mcesa())
+		return 0;
+	size = nmi_get_mcesa_size();
+	if (size > MCESA_MIN_SIZE)
+		mcesa_origin_lc = ilog2(size);
+	/* create slab cache for the machine-check-extended-save-areas */
+	mcesa_cache = kmem_cache_create("nmi_save_areas", size, size, 0, NULL);
+	if (!mcesa_cache)
+		panic("Couldn't create nmi save area cache");
+	origin = (unsigned long) kmem_cache_alloc(mcesa_cache, GFP_KERNEL);
+	if (!origin)
+		panic("Couldn't allocate nmi save area");
+	/* The pointer is stored with mcesa_bits ORed in */
+	kmemleak_not_leak((void *) origin);
+	__ctl_store(cr0, 0, 0);
+	__ctl_clear_bit(0, 28); /* disable lowcore protection */
+	/* Replace boot_mcesa on the boot CPU */
+	S390_lowcore.mcesad = origin | mcesa_origin_lc;
+	__ctl_load(cr0, 0, 0);
+	return 0;
+}
+early_initcall(nmi_init);
+
+int nmi_alloc_per_cpu(struct lowcore *lc)
+{
+	unsigned long origin;
+
+	if (!nmi_needs_mcesa())
+		return 0;
+	origin = (unsigned long) kmem_cache_alloc(mcesa_cache, GFP_KERNEL);
+	if (!origin)
+		return -ENOMEM;
+	/* The pointer is stored with mcesa_bits ORed in */
+	kmemleak_not_leak((void *) origin);
+	lc->mcesad = origin | mcesa_origin_lc;
+	return 0;
+}
+
+void nmi_free_per_cpu(struct lowcore *lc)
+{
+	if (!nmi_needs_mcesa())
+		return;
+	kmem_cache_free(mcesa_cache, (void *)(lc->mcesad & MCESA_ORIGIN_MASK));
+}
+
+static notrace void s390_handle_damage(void)
+{
+	smp_emergency_stop();
 	disabled_wait((unsigned long) __builtin_return_address(0));
 	while (1);
 }
+NOKPROBE_SYMBOL(s390_handle_damage);
 
 /*
  * Main machine check handler function. Will be called with interrupts enabled
@@ -100,18 +184,16 @@ void s390_handle_mcck(void)
 EXPORT_SYMBOL_GPL(s390_handle_mcck);
 
 /*
- * returns 0 if all registers could be validated
+ * returns 0 if all required registers are available
  * returns 1 otherwise
  */
-static int notrace s390_validate_registers(union mci mci, int umode)
+static int notrace s390_check_registers(union mci mci, int umode)
 {
+	union ctlreg2 cr2;
 	int kill_task;
-	u64 zero;
 	void *fpt_save_area;
-	struct mcesa *mcesa;
 
 	kill_task = 0;
-	zero = 0;
 
 	if (!mci.gr) {
 		/*
@@ -122,18 +204,13 @@ static int notrace s390_validate_registers(union mci mci, int umode)
 			s390_handle_damage();
 		kill_task = 1;
 	}
-	/* Validate control registers */
+	/* Check control registers */
 	if (!mci.cr) {
 		/*
 		 * Control registers have unknown contents.
 		 * Can't recover and therefore stopping machine.
 		 */
 		s390_handle_damage();
-	} else {
-		asm volatile(
-			"	lctlg	0,15,0(%0)\n"
-			"	ptlb\n"
-			: : "a" (&S390_lowcore.cregs_save_area) : "memory");
 	}
 	if (!mci.fp) {
 		/*
@@ -141,7 +218,6 @@ static int notrace s390_validate_registers(union mci mci, int umode)
 		 * kernel currently uses floating point registers the
 		 * system is stopped. If the process has its floating
 		 * pointer registers loaded it is terminated.
-		 * Otherwise just revalidate the registers.
 		 */
 		if (S390_lowcore.fpu_flags & KERNEL_VXR_V0V7)
 			s390_handle_damage();
@@ -155,72 +231,29 @@ static int notrace s390_validate_registers(union mci mci, int umode)
 		 * If the kernel currently uses the floating pointer
 		 * registers and needs the FPC register the system is
 		 * stopped. If the process has its floating pointer
-		 * registers loaded it is terminated. Otherwiese the
-		 * FPC is just revalidated.
+		 * registers loaded it is terminated.
 		 */
 		if (S390_lowcore.fpu_flags & KERNEL_FPC)
 			s390_handle_damage();
-		asm volatile("lfpc %0" : : "Q" (zero));
 		if (!test_cpu_flag(CIF_FPU))
 			kill_task = 1;
-	} else {
-		asm volatile("lfpc %0"
-			     : : "Q" (S390_lowcore.fpt_creg_save_area));
 	}
 
-	mcesa = (struct mcesa *)(S390_lowcore.mcesad & MCESA_ORIGIN_MASK);
-	if (!MACHINE_HAS_VX) {
-		/* Validate floating point registers */
-		asm volatile(
-			"	ld	0,0(%0)\n"
-			"	ld	1,8(%0)\n"
-			"	ld	2,16(%0)\n"
-			"	ld	3,24(%0)\n"
-			"	ld	4,32(%0)\n"
-			"	ld	5,40(%0)\n"
-			"	ld	6,48(%0)\n"
-			"	ld	7,56(%0)\n"
-			"	ld	8,64(%0)\n"
-			"	ld	9,72(%0)\n"
-			"	ld	10,80(%0)\n"
-			"	ld	11,88(%0)\n"
-			"	ld	12,96(%0)\n"
-			"	ld	13,104(%0)\n"
-			"	ld	14,112(%0)\n"
-			"	ld	15,120(%0)\n"
-			: : "a" (fpt_save_area) : "memory");
-	} else {
-		/* Validate vector registers */
-		union ctlreg0 cr0;
-
+	if (MACHINE_HAS_VX) {
 		if (!mci.vr) {
 			/*
 			 * Vector registers can't be restored. If the kernel
 			 * currently uses vector registers the system is
 			 * stopped. If the process has its vector registers
-			 * loaded it is terminated. Otherwise just revalidate
-			 * the registers.
+			 * loaded it is terminated.
 			 */
 			if (S390_lowcore.fpu_flags & KERNEL_VXR)
 				s390_handle_damage();
 			if (!test_cpu_flag(CIF_FPU))
 				kill_task = 1;
 		}
-		cr0.val = S390_lowcore.cregs_save_area[0];
-		cr0.afp = cr0.vx = 1;
-		__ctl_load(cr0.val, 0, 0);
-		asm volatile(
-			"	la	1,%0\n"
-			"	.word	0xe70f,0x1000,0x0036\n"	/* vlm 0,15,0(1) */
-			"	.word	0xe70f,0x1100,0x0c36\n"	/* vlm 16,31,256(1) */
-			: : "Q" (*(struct vx_array *) mcesa->vector_save_area)
-			: "1");
-		__ctl_load(S390_lowcore.cregs_save_area[0], 0, 0);
 	}
-	/* Validate access registers */
-	asm volatile(
-		"	lam	0,15,0(%0)"
-		: : "a" (&S390_lowcore.access_regs_save_area));
+	/* Check if access registers are valid */
 	if (!mci.ar) {
 		/*
 		 * Access registers have unknown contents.
@@ -228,53 +261,41 @@ static int notrace s390_validate_registers(union mci mci, int umode)
 		 */
 		kill_task = 1;
 	}
-	/* Validate guarded storage registers */
-	if (MACHINE_HAS_GS && (S390_lowcore.cregs_save_area[2] & (1UL << 4))) {
-		if (!mci.gs)
+	/* Check guarded storage registers */
+	cr2.val = S390_lowcore.cregs_save_area[2];
+	if (cr2.gse) {
+		if (!mci.gs) {
 			/*
 			 * Guarded storage register can't be restored and
 			 * the current processes uses guarded storage.
 			 * It has to be terminated.
 			 */
 			kill_task = 1;
-		else
-			load_gs_cb((struct gs_cb *)
-				   mcesa->guarded_storage_save_area);
+		}
 	}
-	/*
-	 * We don't even try to validate the TOD register, since we simply
-	 * can't write something sensible into that register.
-	 */
-	/*
-	 * See if we can validate the TOD programmable register with its
-	 * old contents (should be zero) otherwise set it to zero.
-	 */
-	if (!mci.pr)
-		asm volatile(
-			"	sr	0,0\n"
-			"	sckpf"
-			: : : "0", "cc");
-	else
-		asm volatile(
-			"	l	0,%0\n"
-			"	sckpf"
-			: : "Q" (S390_lowcore.tod_progreg_save_area)
-			: "0", "cc");
-	/* Validate clock comparator register */
-	set_clock_comparator(S390_lowcore.clock_comparator);
 	/* Check if old PSW is valid */
-	if (!mci.wp)
+	if (!mci.wp) {
 		/*
 		 * Can't tell if we come from user or kernel mode
 		 * -> stopping machine.
 		 */
 		s390_handle_damage();
+	}
+	/* Check for invalid kernel instruction address */
+	if (!mci.ia && !umode) {
+		/*
+		 * The instruction address got lost while running
+		 * in the kernel -> stopping machine.
+		 */
+		s390_handle_damage();
+	}
 
 	if (!mci.ms || !mci.pm || !mci.ia)
 		kill_task = 1;
 
 	return kill_task;
 }
+NOKPROBE_SYMBOL(s390_check_registers);
 
 /*
  * Backup the guest's machine check info to its description block
@@ -300,6 +321,7 @@ static void notrace s390_backup_mcck_info(struct pt_regs *regs)
 	mcck_backup->failing_storage_address
 			= S390_lowcore.failing_storage_address;
 }
+NOKPROBE_SYMBOL(s390_backup_mcck_info);
 
 #define MAX_IPD_COUNT	29
 #define MAX_IPD_TIME	(5 * 60 * USEC_PER_SEC) /* 5 minutes */
@@ -372,7 +394,7 @@ void notrace s390_do_machine_check(struct pt_regs *regs)
 			s390_handle_damage();
 		}
 	}
-	if (s390_validate_registers(mci, user_mode(regs))) {
+	if (s390_check_registers(mci, user_mode(regs))) {
 		/*
 		 * Couldn't restore all register contents for the
 		 * user space process -> mark task for termination.
@@ -443,6 +465,7 @@ void notrace s390_do_machine_check(struct pt_regs *regs)
 	clear_cpu_flag(CIF_MCCK_GUEST);
 	nmi_exit();
 }
+NOKPROBE_SYMBOL(s390_do_machine_check);
 
 static int __init machine_check_init(void)
 {

arch/s390/kernel/perf_cpum_sf.c

@@ -823,12 +823,8 @@ static int cpumsf_pmu_event_init(struct perf_event *event)
 	}
 
 	/* Check online status of the CPU to which the event is pinned */
-	if (event->cpu >= 0) {
-		if ((unsigned int)event->cpu >= nr_cpumask_bits)
+	if (event->cpu >= 0 && !cpu_online(event->cpu))
 			return -ENODEV;
-		if (!cpu_online(event->cpu))
-			return -ENODEV;
-	}
 
 	/* Force reset of idle/hv excludes regardless of what the
 	 * user requested.

arch/s390/kernel/relocate_kernel.S

@@ -29,7 +29,6 @@
 ENTRY(relocate_kernel)
 		basr	%r13,0		# base address
 	.base:
-		stnsm	sys_msk-.base(%r13),0xfb	# disable DAT
 		stctg	%c0,%c15,ctlregs-.base(%r13)
 		stmg	%r0,%r15,gprregs-.base(%r13)
 		lghi	%r0,3
@@ -103,8 +102,6 @@ ENTRY(relocate_kernel)
 		.align	8
 	load_psw:
 		.long	0x00080000,0x80000000
-	sys_msk:
-		.quad	0
 	ctlregs:
 		.rept	16
 		.quad	0