Merge tag 's390-5.5-1' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux

Pull s390 updates from Vasily Gorbik:

 - Adjust PMU device drivers registration to avoid WARN_ON and few other
   perf improvements.

 - Enhance tracing in vfio-ccw.

 - Few stack unwinder fixes and improvements, convert get_wchan custom
   stack unwinding to generic api usage.

 - Fixes for mm helpers issues uncovered with tests validating
   architecture page table helpers.

 - Fix noexec bit handling when hardware doesn't support it.

 - Fix memleak and unsigned value compared with zero bugs in crypto
   code. Minor code simplification.

 - Fix crash during kdump with kasan enabled kernel.

 - Switch bug and alternatives from asm to asm_inline to improve
   inlining decisions.

 - Use 'depends on cc-option' for MARCH and TUNE options in Kconfig, add
   z13s and z14 ZR1 to TUNE descriptions.

 - Minor head64.S simplification.

 - Fix physical to logical CPU map for SMT.

 - Several cleanups in qdio code.

 - Other minor cleanups and fixes all over the code.

* tag 's390-5.5-1' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux: (41 commits)
  s390/cpumf: Adjust registration of s390 PMU device drivers
  s390/smp: fix physical to logical CPU map for SMT
  s390/early: move access registers setup in C code
  s390/head64: remove unnecessary vdso_per_cpu_data setup
  s390/early: move control registers setup in C code
  s390/kasan: support memcpy_real with TRACE_IRQFLAGS
  s390/crypto: Fix unsigned variable compared with zero
  s390/pkey: use memdup_user() to simplify code
  s390/pkey: fix memory leak within _copy_apqns_from_user()
  s390/disassembler: don't hide instruction addresses
  s390/cpum_sf: Assign error value to err variable
  s390/cpum_sf: Replace function name in debug statements
  s390/cpum_sf: Use consistant debug print format for sampling
  s390/unwind: drop unnecessary code around calling ftrace_graph_ret_addr()
  s390: add error handling to perf_callchain_kernel
  s390: always inline current_stack_pointer()
  s390/mm: add mm_pxd_folded() checks to pxd_free()
  s390/mm: properly clear _PAGE_NOEXEC bit when it is not supported
  s390/mm: simplify page table helpers for large entries
  s390/mm: make pmd/pud_bad() report large entries as bad
  ...

26 files changed, 276 insertions, 274 deletions

diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 43a81d0ad507..f0df9e48e651 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -246,8 +246,8 @@ choice
 
 config MARCH_Z900
 	bool "IBM zSeries model z800 and z900"
-	depends on !CC_IS_CLANG
 	select HAVE_MARCH_Z900_FEATURES
+	depends on $(cc-option,-march=z900)
 	help
 	  Select this to enable optimizations for model z800/z900 (2064 and
 	  2066 series). This will enable some optimizations that are not
@@ -255,8 +255,8 @@ config MARCH_Z900
 
 config MARCH_Z990
 	bool "IBM zSeries model z890 and z990"
-	depends on !CC_IS_CLANG
 	select HAVE_MARCH_Z990_FEATURES
+	depends on $(cc-option,-march=z990)
 	help
 	  Select this to enable optimizations for model z890/z990 (2084 and
 	  2086 series). The kernel will be slightly faster but will not work
@@ -264,8 +264,8 @@ config MARCH_Z990
 
 config MARCH_Z9_109
 	bool "IBM System z9"
-	depends on !CC_IS_CLANG
 	select HAVE_MARCH_Z9_109_FEATURES
+	depends on $(cc-option,-march=z9-109)
 	help
 	  Select this to enable optimizations for IBM System z9 (2094 and
 	  2096 series). The kernel will be slightly faster but will not work
@@ -274,6 +274,7 @@ config MARCH_Z9_109
 config MARCH_Z10
 	bool "IBM System z10"
 	select HAVE_MARCH_Z10_FEATURES
+	depends on $(cc-option,-march=z10)
 	help
 	  Select this to enable optimizations for IBM System z10 (2097 and
 	  2098 series). The kernel will be slightly faster but will not work
@@ -282,6 +283,7 @@ config MARCH_Z10
 config MARCH_Z196
 	bool "IBM zEnterprise 114 and 196"
 	select HAVE_MARCH_Z196_FEATURES
+	depends on $(cc-option,-march=z196)
 	help
 	  Select this to enable optimizations for IBM zEnterprise 114 and 196
 	  (2818 and 2817 series). The kernel will be slightly faster but will
@@ -290,6 +292,7 @@ config MARCH_Z196
 config MARCH_ZEC12
 	bool "IBM zBC12 and zEC12"
 	select HAVE_MARCH_ZEC12_FEATURES
+	depends on $(cc-option,-march=zEC12)
 	help
 	  Select this to enable optimizations for IBM zBC12 and zEC12 (2828 and
 	  2827 series). The kernel will be slightly faster but will not work on
@@ -298,6 +301,7 @@ config MARCH_ZEC12
 config MARCH_Z13
 	bool "IBM z13s and z13"
 	select HAVE_MARCH_Z13_FEATURES
+	depends on $(cc-option,-march=z13)
 	help
 	  Select this to enable optimizations for IBM z13s and z13 (2965 and
 	  2964 series). The kernel will be slightly faster but will not work on
@@ -306,6 +310,7 @@ config MARCH_Z13
 config MARCH_Z14
 	bool "IBM z14 ZR1 and z14"
 	select HAVE_MARCH_Z14_FEATURES
+	depends on $(cc-option,-march=z14)
 	help
 	  Select this to enable optimizations for IBM z14 ZR1 and z14 (3907
 	  and 3906 series). The kernel will be slightly faster but will not
@@ -314,6 +319,7 @@ config MARCH_Z14
 config MARCH_Z15
 	bool "IBM z15"
 	select HAVE_MARCH_Z15_FEATURES
+	depends on $(cc-option,-march=z15)
 	help
 	  Select this to enable optimizations for IBM z15 (8562
 	  and 8561 series). The kernel will be slightly faster but will not
@@ -367,33 +373,39 @@ config TUNE_DEFAULT
 
 config TUNE_Z900
 	bool "IBM zSeries model z800 and z900"
-	depends on !CC_IS_CLANG
+	depends on $(cc-option,-mtune=z900)
 
 config TUNE_Z990
 	bool "IBM zSeries model z890 and z990"
-	depends on !CC_IS_CLANG
+	depends on $(cc-option,-mtune=z990)
 
 config TUNE_Z9_109
 	bool "IBM System z9"
-	depends on !CC_IS_CLANG
+	depends on $(cc-option,-mtune=z9-109)
 
 config TUNE_Z10
 	bool "IBM System z10"
+	depends on $(cc-option,-mtune=z10)
 
 config TUNE_Z196
 	bool "IBM zEnterprise 114 and 196"
+	depends on $(cc-option,-mtune=z196)
 
 config TUNE_ZEC12
 	bool "IBM zBC12 and zEC12"
+	depends on $(cc-option,-mtune=zEC12)
 
 config TUNE_Z13
-	bool "IBM z13"
+	bool "IBM z13s and z13"
+	depends on $(cc-option,-mtune=z13)
 
 config TUNE_Z14
-	bool "IBM z14"
+	bool "IBM z14 ZR1 and z14"
+	depends on $(cc-option,-mtune=z14)
 
 config TUNE_Z15
 	bool "IBM z15"
+	depends on $(cc-option,-mtune=z15)
 
 endchoice
 
diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c
index 5367950510f6..fbd341ea03b8 100644
--- a/arch/s390/boot/startup.c
+++ b/arch/s390/boot/startup.c
@@ -46,7 +46,7 @@ struct diag_ops __bootdata_preserved(diag_dma_ops) = {
 	.diag0c = _diag0c_dma,
 	.diag308_reset = _diag308_reset_dma
 };
-static struct diag210 _diag210_tmp_dma __section(".dma.data");
+static struct diag210 _diag210_tmp_dma __section(.dma.data);
 struct diag210 *__bootdata_preserved(__diag210_tmp_dma) = &_diag210_tmp_dma;
 void _swsusp_reset_dma(void);
 unsigned long __bootdata_preserved(__swsusp_reset_dma) = __pa(_swsusp_reset_dma);
diff --git a/arch/s390/crypto/sha_common.c b/arch/s390/crypto/sha_common.c
index d39e0f079217..686fe7aa192f 100644
--- a/arch/s390/crypto/sha_common.c
+++ b/arch/s390/crypto/sha_common.c
@@ -74,14 +74,17 @@ int s390_sha_final(struct shash_desc *desc, u8 *out)
 	struct s390_sha_ctx *ctx = shash_desc_ctx(desc);
 	unsigned int bsize = crypto_shash_blocksize(desc->tfm);
 	u64 bits;
-	unsigned int n, mbl_offset;
+	unsigned int n;
+	int mbl_offset;
 
 	n = ctx->count % bsize;
 	bits = ctx->count * 8;
-	mbl_offset = s390_crypto_shash_parmsize(ctx->func) / sizeof(u32);
+	mbl_offset = s390_crypto_shash_parmsize(ctx->func);
 	if (mbl_offset < 0)
 		return -EINVAL;
 
+	mbl_offset = mbl_offset / sizeof(u32);
+
 	/* set total msg bit length (mbl) in CPACF parmblock */
 	switch (ctx->func) {
 	case CPACF_KLMD_SHA_1:
diff --git a/arch/s390/include/asm/alternative.h b/arch/s390/include/asm/alternative.h
index c2cf7bcdef9b..1c8a38f762a3 100644
--- a/arch/s390/include/asm/alternative.h
+++ b/arch/s390/include/asm/alternative.h
@@ -139,10 +139,10 @@ void apply_alternatives(struct alt_instr *start, struct alt_instr *end);
  * without volatile and memory clobber.
  */
 #define alternative(oldinstr, altinstr, facility)			\
-	asm volatile(ALTERNATIVE(oldinstr, altinstr, facility) : : : "memory")
+	asm_inline volatile(ALTERNATIVE(oldinstr, altinstr, facility) : : : "memory")
 
 #define alternative_2(oldinstr, altinstr1, facility1, altinstr2, facility2) \
-	asm volatile(ALTERNATIVE_2(oldinstr, altinstr1, facility1,	    \
+	asm_inline volatile(ALTERNATIVE_2(oldinstr, altinstr1, facility1,   \
 				   altinstr2, facility2) ::: "memory")
 
 #endif /* __ASSEMBLY__ */
diff --git a/arch/s390/include/asm/bug.h b/arch/s390/include/asm/bug.h
index 713fc9735ffb..a2b11ac00f60 100644
--- a/arch/s390/include/asm/bug.h
+++ b/arch/s390/include/asm/bug.h
@@ -9,7 +9,7 @@
 #ifdef CONFIG_DEBUG_BUGVERBOSE
 
 #define __EMIT_BUG(x) do {					\
-	asm volatile(						\
+	asm_inline volatile(					\
 		"0:	j	0b+2\n"				\
 		"1:\n"						\
 		".section .rodata.str,\"aMS\",@progbits,1\n"	\
@@ -28,7 +28,7 @@
 #else /* CONFIG_DEBUG_BUGVERBOSE */
 
 #define __EMIT_BUG(x) do {					\
-	asm volatile(						\
+	asm_inline volatile(					\
 		"0:	j	0b+2\n"				\
 		"1:\n"						\
 		".section __bug_table,\"awM\",@progbits,%1\n"	\
diff --git a/arch/s390/include/asm/ctl_reg.h b/arch/s390/include/asm/ctl_reg.h
index 60f907516335..ed5efbb531c4 100644
--- a/arch/s390/include/asm/ctl_reg.h
+++ b/arch/s390/include/asm/ctl_reg.h
@@ -11,6 +11,7 @@
 #include <linux/bits.h>
 
 #define CR0_CLOCK_COMPARATOR_SIGN	BIT(63 - 10)
+#define CR0_LOW_ADDRESS_PROTECTION	BIT(63 - 35)
 #define CR0_EMERGENCY_SIGNAL_SUBMASK	BIT(63 - 49)
 #define CR0_EXTERNAL_CALL_SUBMASK	BIT(63 - 50)
 #define CR0_CLOCK_COMPARATOR_SUBMASK	BIT(63 - 52)
diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h
index bccb8f4a63e2..77606c4acd58 100644
--- a/arch/s390/include/asm/pgalloc.h
+++ b/arch/s390/include/asm/pgalloc.h
@@ -56,7 +56,12 @@ static inline p4d_t *p4d_alloc_one(struct mm_struct *mm, unsigned long address)
 		crst_table_init(table, _REGION2_ENTRY_EMPTY);
 	return (p4d_t *) table;
 }
-#define p4d_free(mm, p4d) crst_table_free(mm, (unsigned long *) p4d)
+
+static inline void p4d_free(struct mm_struct *mm, p4d_t *p4d)
+{
+	if (!mm_p4d_folded(mm))
+		crst_table_free(mm, (unsigned long *) p4d);
+}
 
 static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address)
 {
@@ -65,7 +70,12 @@ static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address)
 		crst_table_init(table, _REGION3_ENTRY_EMPTY);
 	return (pud_t *) table;
 }
-#define pud_free(mm, pud) crst_table_free(mm, (unsigned long *) pud)
+
+static inline void pud_free(struct mm_struct *mm, pud_t *pud)
+{
+	if (!mm_pud_folded(mm))
+		crst_table_free(mm, (unsigned long *) pud);
+}
 
 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long vmaddr)
 {
@@ -83,6 +93,8 @@ static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long vmaddr)
 
 static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
 {
+	if (mm_pmd_folded(mm))
+		return;
 	pgtable_pmd_page_dtor(virt_to_page(pmd));
 	crst_table_free(mm, (unsigned long *) pmd);
 }
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 5ff98d76a66c..7b03037a8475 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -266,11 +266,9 @@ static inline int is_module_addr(void *addr)
 #endif
 
 #define _REGION_ENTRY_BITS	 0xfffffffffffff22fUL
-#define _REGION_ENTRY_BITS_LARGE 0xffffffff8000fe2fUL
 
 /* Bits in the segment table entry */
 #define _SEGMENT_ENTRY_BITS			0xfffffffffffffe33UL
-#define _SEGMENT_ENTRY_BITS_LARGE		0xfffffffffff0ff33UL
 #define _SEGMENT_ENTRY_HARDWARE_BITS		0xfffffffffffffe30UL
 #define _SEGMENT_ENTRY_HARDWARE_BITS_LARGE	0xfffffffffff00730UL
 #define _SEGMENT_ENTRY_ORIGIN_LARGE ~0xfffffUL /* large page address	    */
@@ -699,10 +697,8 @@ static inline int pmd_large(pmd_t pmd)
 
 static inline int pmd_bad(pmd_t pmd)
 {
-	if ((pmd_val(pmd) & _SEGMENT_ENTRY_TYPE_MASK) > 0)
+	if ((pmd_val(pmd) & _SEGMENT_ENTRY_TYPE_MASK) > 0 || pmd_large(pmd))
 		return 1;
-	if (pmd_large(pmd))
-		return (pmd_val(pmd) & ~_SEGMENT_ENTRY_BITS_LARGE) != 0;
 	return (pmd_val(pmd) & ~_SEGMENT_ENTRY_BITS) != 0;
 }
 
@@ -710,12 +706,10 @@ static inline int pud_bad(pud_t pud)
 {
 	unsigned long type = pud_val(pud) & _REGION_ENTRY_TYPE_MASK;
 
-	if (type > _REGION_ENTRY_TYPE_R3)
+	if (type > _REGION_ENTRY_TYPE_R3 || pud_large(pud))
 		return 1;
 	if (type < _REGION_ENTRY_TYPE_R3)
 		return 0;
-	if (pud_large(pud))
-		return (pud_val(pud) & ~_REGION_ENTRY_BITS_LARGE) != 0;
 	return (pud_val(pud) & ~_REGION_ENTRY_BITS) != 0;
 }
 
@@ -758,18 +752,12 @@ static inline int pmd_write(pmd_t pmd)
 
 static inline int pmd_dirty(pmd_t pmd)
 {
-	int dirty = 1;
-	if (pmd_large(pmd))
-		dirty = (pmd_val(pmd) & _SEGMENT_ENTRY_DIRTY) != 0;
-	return dirty;
+	return (pmd_val(pmd) & _SEGMENT_ENTRY_DIRTY) != 0;
 }
 
 static inline int pmd_young(pmd_t pmd)
 {
-	int young = 1;
-	if (pmd_large(pmd))
-		young = (pmd_val(pmd) & _SEGMENT_ENTRY_YOUNG) != 0;
-	return young;
+	return (pmd_val(pmd) & _SEGMENT_ENTRY_YOUNG) != 0;
 }
 
 static inline int pte_present(pte_t pte)
@@ -1173,8 +1161,6 @@ void gmap_pmdp_idte_global(struct mm_struct *mm, unsigned long vmaddr);
 static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 			      pte_t *ptep, pte_t entry)
 {
-	if (!MACHINE_HAS_NX)
-		pte_val(entry) &= ~_PAGE_NOEXEC;
 	if (pte_present(entry))
 		pte_val(entry) &= ~_PAGE_UNUSED;
 	if (mm_has_pgste(mm))
@@ -1191,6 +1177,8 @@ static inline pte_t mk_pte_phys(unsigned long physpage, pgprot_t pgprot)
 {
 	pte_t __pte;
 	pte_val(__pte) = physpage + pgprot_val(pgprot);
+	if (!MACHINE_HAS_NX)
+		pte_val(__pte) &= ~_PAGE_NOEXEC;
 	return pte_mkyoung(__pte);
 }
 
@@ -1297,29 +1285,23 @@ static inline pmd_t pmd_wrprotect(pmd_t pmd)
 static inline pmd_t pmd_mkwrite(pmd_t pmd)
 {
 	pmd_val(pmd) |= _SEGMENT_ENTRY_WRITE;
-	if (pmd_large(pmd) && !(pmd_val(pmd) & _SEGMENT_ENTRY_DIRTY))
-		return pmd;
-	pmd_val(pmd) &= ~_SEGMENT_ENTRY_PROTECT;
+	if (pmd_val(pmd) & _SEGMENT_ENTRY_DIRTY)
+		pmd_val(pmd) &= ~_SEGMENT_ENTRY_PROTECT;
 	return pmd;
 }
 
 static inline pmd_t pmd_mkclean(pmd_t pmd)
 {
-	if (pmd_large(pmd)) {
-		pmd_val(pmd) &= ~_SEGMENT_ENTRY_DIRTY;
-		pmd_val(pmd) |= _SEGMENT_ENTRY_PROTECT;
-	}
+	pmd_val(pmd) &= ~_SEGMENT_ENTRY_DIRTY;
+	pmd_val(pmd) |= _SEGMENT_ENTRY_PROTECT;
 	return pmd;
 }
 
 static inline pmd_t pmd_mkdirty(pmd_t pmd)
 {
-	if (pmd_large(pmd)) {
-		pmd_val(pmd) |= _SEGMENT_ENTRY_DIRTY |
-				_SEGMENT_ENTRY_SOFT_DIRTY;
-		if (pmd_val(pmd) & _SEGMENT_ENTRY_WRITE)
-			pmd_val(pmd) &= ~_SEGMENT_ENTRY_PROTECT;
-	}
+	pmd_val(pmd) |= _SEGMENT_ENTRY_DIRTY | _SEGMENT_ENTRY_SOFT_DIRTY;
+	if (pmd_val(pmd) & _SEGMENT_ENTRY_WRITE)
+		pmd_val(pmd) &= ~_SEGMENT_ENTRY_PROTECT;
 	return pmd;
 }
 
@@ -1333,29 +1315,23 @@ static inline pud_t pud_wrprotect(pud_t pud)
 static inline pud_t pud_mkwrite(pud_t pud)
 {
 	pud_val(pud) |= _REGION3_ENTRY_WRITE;
-	if (pud_large(pud) && !(pud_val(pud) & _REGION3_ENTRY_DIRTY))
-		return pud;
-	pud_val(pud) &= ~_REGION_ENTRY_PROTECT;
+	if (pud_val(pud) & _REGION3_ENTRY_DIRTY)
+		pud_val(pud) &= ~_REGION_ENTRY_PROTECT;
 	return pud;
 }
 
 static inline pud_t pud_mkclean(pud_t pud)
 {
-	if (pud_large(pud)) {
-		pud_val(pud) &= ~_REGION3_ENTRY_DIRTY;
-		pud_val(pud) |= _REGION_ENTRY_PROTECT;
-	}
+	pud_val(pud) &= ~_REGION3_ENTRY_DIRTY;
+	pud_val(pud) |= _REGION_ENTRY_PROTECT;
 	return pud;
 }
 
 static inline pud_t pud_mkdirty(pud_t pud)
 {
-	if (pud_large(pud)) {
-		pud_val(pud) |= _REGION3_ENTRY_DIRTY |
-				_REGION3_ENTRY_SOFT_DIRTY;
-		if (pud_val(pud) & _REGION3_ENTRY_WRITE)
-			pud_val(pud) &= ~_REGION_ENTRY_PROTECT;
-	}
+	pud_val(pud) |= _REGION3_ENTRY_DIRTY | _REGION3_ENTRY_SOFT_DIRTY;
+	if (pud_val(pud) & _REGION3_ENTRY_WRITE)
+		pud_val(pud) &= ~_REGION_ENTRY_PROTECT;
 	return pud;
 }
 
@@ -1379,38 +1355,29 @@ static inline unsigned long massage_pgprot_pmd(pgprot_t pgprot)
 
 static inline pmd_t pmd_mkyoung(pmd_t pmd)
 {
-	if (pmd_large(pmd)) {
-		pmd_val(pmd) |= _SEGMENT_ENTRY_YOUNG;
-		if (pmd_val(pmd) & _SEGMENT_ENTRY_READ)
-			pmd_val(pmd) &= ~_SEGMENT_ENTRY_INVALID;
-	}
+	pmd_val(pmd) |= _SEGMENT_ENTRY_YOUNG;
+	if (pmd_val(pmd) & _SEGMENT_ENTRY_READ)
+		pmd_val(pmd) &= ~_SEGMENT_ENTRY_INVALID;
 	return pmd;
 }
 
 static inline pmd_t pmd_mkold(pmd_t pmd)
 {
-	if (pmd_large(pmd)) {
-		pmd_val(pmd) &= ~_SEGMENT_ENTRY_YOUNG;
-		pmd_val(pmd) |= _SEGMENT_ENTRY_INVALID;
-	}
+	pmd_val(pmd) &= ~_SEGMENT_ENTRY_YOUNG;
+	pmd_val(pmd) |= _SEGMENT_ENTRY_INVALID;
 	return pmd;
 }
 
 static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
 {
-	if (pmd_large(pmd)) {
-		pmd_val(pmd) &= _SEGMENT_ENTRY_ORIGIN_LARGE |
-			_SEGMENT_ENTRY_DIRTY | _SEGMENT_ENTRY_YOUNG |
-			_SEGMENT_ENTRY_LARGE | _SEGMENT_ENTRY_SOFT_DIRTY;
-		pmd_val(pmd) |= massage_pgprot_pmd(newprot);
-		if (!(pmd_val(pmd) & _SEGMENT_ENTRY_DIRTY))
-			pmd_val(pmd) |= _SEGMENT_ENTRY_PROTECT;
-		if (!(pmd_val(pmd) & _SEGMENT_ENTRY_YOUNG))
-			pmd_val(pmd) |= _SEGMENT_ENTRY_INVALID;
-		return pmd;
-	}
-	pmd_val(pmd) &= _SEGMENT_ENTRY_ORIGIN;
+	pmd_val(pmd) &= _SEGMENT_ENTRY_ORIGIN_LARGE |
+		_SEGMENT_ENTRY_DIRTY | _SEGMENT_ENTRY_YOUNG |
+		_SEGMENT_ENTRY_LARGE | _SEGMENT_ENTRY_SOFT_DIRTY;
 	pmd_val(pmd) |= massage_pgprot_pmd(newprot);
+	if (!(pmd_val(pmd) & _SEGMENT_ENTRY_DIRTY))
+		pmd_val(pmd) |= _SEGMENT_ENTRY_PROTECT;
+	if (!(pmd_val(pmd) & _SEGMENT_ENTRY_YOUNG))
+		pmd_val(pmd) |= _SEGMENT_ENTRY_INVALID;
 	return pmd;
 }
 
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index 51a0e4a2dc96..881fc37c11c6 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -206,7 +206,7 @@ unsigned long get_wchan(struct task_struct *p);
 /* Has task runtime instrumentation enabled ? */
 #define is_ri_task(tsk) (!!(tsk)->thread.ri_cb)
 
-static inline unsigned long current_stack_pointer(void)
+static __always_inline unsigned long current_stack_pointer(void)
 {
 	unsigned long sp;
 
diff --git a/arch/s390/include/asm/qdio.h b/arch/s390/include/asm/qdio.h
index e3f238e8c611..71e3f0146cda 100644
--- a/arch/s390/include/asm/qdio.h
+++ b/arch/s390/include/asm/qdio.h
@@ -276,6 +276,7 @@ struct qdio_outbuf_state {
 #define CHSC_AC2_MULTI_BUFFER_AVAILABLE	0x0080
 #define CHSC_AC2_MULTI_BUFFER_ENABLED	0x0040
 #define CHSC_AC2_DATA_DIV_AVAILABLE	0x0010
+#define CHSC_AC2_SNIFFER_AVAILABLE	0x0008
 #define CHSC_AC2_DATA_DIV_ENABLED	0x0002
 
 #define CHSC_AC3_FORMAT2_CQ_AVAILABLE	0x8000
diff --git a/arch/s390/include/asm/spinlock.h b/arch/s390/include/asm/spinlock.h
index c02bff33f6c7..3a37172d5398 100644
--- a/arch/s390/include/asm/spinlock.h
+++ b/arch/s390/include/asm/spinlock.h
@@ -85,7 +85,7 @@ static inline int arch_spin_trylock(arch_spinlock_t *lp)
 static inline void arch_spin_unlock(arch_spinlock_t *lp)
 {
 	typecheck(int, lp->lock);
-	asm volatile(
+	asm_inline volatile(
 		ALTERNATIVE("", ".long 0xb2fa0070", 49)	/* NIAI 7 */
 		"	sth	%1,%0\n"
 		: "=Q" (((unsigned short *) &lp->lock)[1])
diff --git a/arch/s390/include/asm/stacktrace.h b/arch/s390/include/asm/stacktrace.h
index 0ae4bbf7779c..fee40212af11 100644
--- a/arch/s390/include/asm/stacktrace.h
+++ b/arch/s390/include/asm/stacktrace.h
@@ -38,7 +38,7 @@ static inline unsigned long get_stack_pointer(struct task_struct *task,
 {
 	if (regs)
 		return (unsigned long) kernel_stack_pointer(regs);
-	if (task == current)
+	if (!task || task == current)
 		return current_stack_pointer();
 	return (unsigned long) task->thread.ksp;
 }
diff --git a/arch/s390/include/asm/timex.h b/arch/s390/include/asm/timex.h
index 64539c221672..6da8885251d6 100644
--- a/arch/s390/include/asm/timex.h
+++ b/arch/s390/include/asm/timex.h
@@ -10,8 +10,9 @@
 #ifndef _ASM_S390_TIMEX_H
 #define _ASM_S390_TIMEX_H
 
-#include <asm/lowcore.h>
+#include <linux/preempt.h>
 #include <linux/time64.h>
+#include <asm/lowcore.h>
 
 /* The value of the TOD clock for 1.1.1970. */
 #define TOD_UNIX_EPOCH 0x7d91048bca000000ULL
@@ -179,22 +180,24 @@ static inline cycles_t get_cycles(void)
 
 int get_phys_clock(unsigned long *clock);
 void init_cpu_timer(void);
-unsigned long long monotonic_clock(void);
 
 extern unsigned char tod_clock_base[16] __aligned(8);
 
 /**
  * get_clock_monotonic - returns current time in clock rate units
  *
- * The caller must ensure that preemption is disabled.
  * The clock and tod_clock_base get changed via stop_machine.
- * Therefore preemption must be disabled when calling this
- * function, otherwise the returned value is not guaranteed to
- * be monotonic.
+ * Therefore preemption must be disabled, otherwise the returned
+ * value is not guaranteed to be monotonic.
  */
 static inline unsigned long long get_tod_clock_monotonic(void)
 {
-	return get_tod_clock() - *(unsigned long long *) &tod_clock_base[1];
+	unsigned long long tod;
+
+	preempt_disable();
+	tod = get_tod_clock() - *(unsigned long long *) &tod_clock_base[1];
+	preempt_enable();
+	return tod;
 }
 
 /**
diff --git a/arch/s390/kernel/dis.c b/arch/s390/kernel/dis.c
index 7abe6ae261b4..f304802ecf7b 100644
--- a/arch/s390/kernel/dis.c
+++ b/arch/s390/kernel/dis.c
@@ -461,10 +461,11 @@ static int print_insn(char *buffer, unsigned char *code, unsigned long addr)
 				ptr += sprintf(ptr, "%%c%i", value);
 			else if (operand->flags & OPERAND_VR)
 				ptr += sprintf(ptr, "%%v%i", value);
-			else if (operand->flags & OPERAND_PCREL)
-				ptr += sprintf(ptr, "%lx", (signed int) value
-								      + addr);
-			else if (operand->flags & OPERAND_SIGNED)
+			else if (operand->flags & OPERAND_PCREL) {
+				void *pcrel = (void *)((int)value + addr);
+
+				ptr += sprintf(ptr, "%px", pcrel);
+			} else if (operand->flags & OPERAND_SIGNED)
 				ptr += sprintf(ptr, "%i", value);
 			else
 				ptr += sprintf(ptr, "%u", value);
@@ -536,7 +537,7 @@ void show_code(struct pt_regs *regs)
 		else
 			*ptr++ = ' ';
 		addr = regs->psw.addr + start - 32;
-		ptr += sprintf(ptr, "%016lx: ", addr);
+		ptr += sprintf(ptr, "%px: ", (void *)addr);
 		if (start + opsize >= end)
 			break;
 		for (i = 0; i < opsize; i++)
@@ -564,7 +565,7 @@ void print_fn_code(unsigned char *code, unsigned long len)
 		opsize = insn_length(*code);
 		if (opsize > len)
 			break;
-		ptr += sprintf(ptr, "%p: ", code);
+		ptr += sprintf(ptr, "%px: ", code);
 		for (i = 0; i < opsize; i++)
 			ptr += sprintf(ptr, "%02x", code[i]);
 		*ptr++ = '\t';
diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c
index b432d63d0b37..db32a55daaec 100644
--- a/arch/s390/kernel/early.c
+++ b/arch/s390/kernel/early.c
@@ -30,6 +30,7 @@
 #include <asm/sclp.h>
 #include <asm/facility.h>
 #include <asm/boot_data.h>
+#include <asm/switch_to.h>
 #include "entry.h"
 
 static void __init reset_tod_clock(void)
@@ -238,7 +239,7 @@ static __init void detect_machine_facilities(void)
 		S390_lowcore.machine_flags |= MACHINE_FLAG_VX;
 		__ctl_set_bit(0, 17);
 	}
-	if (test_facility(130)) {
+	if (test_facility(130) && !noexec_disabled) {
 		S390_lowcore.machine_flags |= MACHINE_FLAG_NX;
 		__ctl_set_bit(0, 20);
 	}
@@ -260,6 +261,24 @@ static inline void save_vector_registers(void)
 #endif
 }
 
+static inline void setup_control_registers(void)
+{
+	unsigned long reg;
+
+	__ctl_store(reg, 0, 0);
+	reg |= CR0_LOW_ADDRESS_PROTECTION;
+	reg |= CR0_EMERGENCY_SIGNAL_SUBMASK;
+	reg |= CR0_EXTERNAL_CALL_SUBMASK;
+	__ctl_load(reg, 0, 0);
+}
+
+static inline void setup_access_registers(void)
+{
+	unsigned int acrs[NUM_ACRS] = { 0 };
+
+	restore_access_regs(acrs);
+}
+
 static int __init disable_vector_extension(char *str)
 {
 	S390_lowcore.machine_flags &= ~MACHINE_FLAG_VX;
@@ -268,21 +287,6 @@ static int __init disable_vector_extension(char *str)
 }
 early_param("novx", disable_vector_extension);
 
-static int __init noexec_setup(char *str)
-{
-	bool enabled;
-	int rc;
-
-	rc = kstrtobool(str, &enabled);
-	if (!rc && !enabled) {
-		/* Disable no-execute support */
-		S390_lowcore.machine_flags &= ~MACHINE_FLAG_NX;
-		__ctl_clear_bit(0, 20);
-	}
-	return rc;
-}
-early_param("noexec", noexec_setup);
-
 static int __init cad_setup(char *str)
 {
 	bool enabled;
@@ -332,5 +336,7 @@ void __init startup_init(void)
 	save_vector_registers();
 	setup_topology();
 	sclp_early_detect();
+	setup_control_registers();
+	setup_access_registers();
 	lockdep_on();
 }
diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S
index 0d9ee198f4eb..b9e585f528a6 100644
--- a/arch/s390/kernel/head64.S
+++ b/arch/s390/kernel/head64.S
@@ -26,8 +26,6 @@ ENTRY(startup_continue)
 0:	larl	%r1,tod_clock_base
 	mvc	0(16,%r1),__LC_BOOT_CLOCK
 	larl	%r13,.LPG1		# get base
-	larl	%r0,boot_vdso_data
-	stg	%r0,__LC_VDSO_PER_CPU
 #
 # Setup stack
 #
@@ -37,19 +35,8 @@ ENTRY(startup_continue)
 #ifdef CONFIG_KASAN
 	brasl	%r14,kasan_early_init
 #endif
-#
-# Early machine initialization and detection functions.
-#
-	brasl	%r14,startup_init
-
-# check control registers
-	stctg	%c0,%c15,0(%r15)
-	oi	6(%r15),0x60		# enable sigp emergency & external call
-	oi	4(%r15),0x10		# switch on low address proctection
-	lctlg	%c0,%c15,0(%r15)
-
-	lam	0,15,.Laregs-.LPG1(%r13)	# load acrs needed by uaccess
-	brasl	%r14,start_kernel		# go to C code
+	brasl	%r14,startup_init		# s390 specific early init
+	brasl	%r14,start_kernel		# common init code
 #
 # We returned from start_kernel ?!? PANIK
 #
@@ -59,4 +46,3 @@ ENTRY(startup_continue)
 	.align	16
 .LPG1:
 .Ldw:	.quad	0x0002000180000000,0x0000000000000000
-.Laregs:.long	0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0
diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c
index 48d48b6187c0..0eb1d1cc53a8 100644
--- a/arch/s390/kernel/perf_cpum_cf.c
+++ b/arch/s390/kernel/perf_cpum_cf.c
@@ -199,7 +199,7 @@ static const int cpumf_generic_events_user[] = {
 	[PERF_COUNT_HW_BUS_CYCLES]	    = -1,
 };
 
-static int __hw_perf_event_init(struct perf_event *event)
+static int __hw_perf_event_init(struct perf_event *event, unsigned int type)
 {
 	struct perf_event_attr *attr = &event->attr;
 	struct hw_perf_event *hwc = &event->hw;
@@ -207,7 +207,7 @@ static int __hw_perf_event_init(struct perf_event *event)
 	int err = 0;
 	u64 ev;
 
-	switch (attr->type) {
+	switch (type) {
 	case PERF_TYPE_RAW:
 		/* Raw events are used to access counters directly,
 		 * hence do not permit excludes */
@@ -294,17 +294,16 @@ static int __hw_perf_event_init(struct perf_event *event)
 
 static int cpumf_pmu_event_init(struct perf_event *event)
 {
+	unsigned int type = event->attr.type;
 	int err;
 
-	switch (event->attr.type) {
-	case PERF_TYPE_HARDWARE:
-	case PERF_TYPE_HW_CACHE:
-	case PERF_TYPE_RAW:
-		err = __hw_perf_event_init(event);
-		break;
-	default:
+	if (type == PERF_TYPE_HARDWARE || type == PERF_TYPE_RAW)
+		err = __hw_perf_event_init(event, type);
+	else if (event->pmu->type == type)
+		/* Registered as unknown PMU */
+		err = __hw_perf_event_init(event, PERF_TYPE_RAW);
+	else
 		return -ENOENT;
-	}
 
 	if (unlikely(err) && event->destroy)
 		event->destroy(event);
@@ -553,7 +552,7 @@ static int __init cpumf_pmu_init(void)
 		return -ENODEV;
 
 	cpumf_pmu.attr_groups = cpumf_cf_event_group();
-	rc = perf_pmu_register(&cpumf_pmu, "cpum_cf", PERF_TYPE_RAW);
+	rc = perf_pmu_register(&cpumf_pmu, "cpum_cf", -1);
 	if (rc)
 		pr_err("Registering the cpum_cf PMU failed with rc=%i\n", rc);
 	return rc;
diff --git a/arch/s390/kernel/perf_cpum_cf_diag.c b/arch/s390/kernel/perf_cpum_cf_diag.c
index 2654e348801a..e949ab832ed7 100644
--- a/arch/s390/kernel/perf_cpum_cf_diag.c
+++ b/arch/s390/kernel/perf_cpum_cf_diag.c
@@ -243,13 +243,13 @@ static int cf_diag_event_init(struct perf_event *event)
 	int err = -ENOENT;
 
 	debug_sprintf_event(cf_diag_dbg, 5,
-			    "%s event %p cpu %d config %#llx "
+			    "%s event %p cpu %d config %#llx type:%u "
 			    "sample_type %#llx cf_diag_events %d\n", __func__,
-			    event, event->cpu, attr->config, attr->sample_type,
-			    atomic_read(&cf_diag_events));
+			    event, event->cpu, attr->config, event->pmu->type,
+			    attr->sample_type, atomic_read(&cf_diag_events));
 
 	if (event->attr.config != PERF_EVENT_CPUM_CF_DIAG ||
-	    event->attr.type != PERF_TYPE_RAW)
+	    event->attr.type != event->pmu->type)
 		goto out;
 
 	/* Raw events are used to access counters directly,
@@ -693,7 +693,7 @@ static int __init cf_diag_init(void)
 	}
 	debug_register_view(cf_diag_dbg, &debug_sprintf_view);
 
-	rc = perf_pmu_register(&cf_diag, "cpum_cf_diag", PERF_TYPE_RAW);
+	rc = perf_pmu_register(&cf_diag, "cpum_cf_diag", -1);
 	if (rc) {
 		debug_unregister_view(cf_diag_dbg, &debug_sprintf_view);
 		debug_unregister(cf_diag_dbg);
diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
index 3d8b12a9a6ff..69506fdbd9a1 100644
--- a/arch/s390/kernel/perf_cpum_sf.c
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -156,8 +156,8 @@ static void free_sampling_buffer(struct sf_buffer *sfb)
 		}
 	}
 
-	debug_sprintf_event(sfdbg, 5,
-			    "free_sampling_buffer: freed sdbt=%p\n", sfb->sdbt);
+	debug_sprintf_event(sfdbg, 5, "%s freed sdbt %p\n", __func__,
+			    sfb->sdbt);
 	memset(sfb, 0, sizeof(*sfb));
 }
 
@@ -212,10 +212,10 @@ static int realloc_sampling_buffer(struct sf_buffer *sfb,
 	 * the sampling buffer origin.
 	 */
 	if (sfb->sdbt != get_next_sdbt(tail)) {
-		debug_sprintf_event(sfdbg, 3, "realloc_sampling_buffer: "
-				    "sampling buffer is not linked: origin=%p"
-				    "tail=%p\n",
-				    (void *) sfb->sdbt, (void *) tail);
+		debug_sprintf_event(sfdbg, 3, "%s: "
+				    "sampling buffer is not linked: origin %p"
+				    " tail %p\n", __func__,
+				    (void *)sfb->sdbt, (void *)tail);
 		return -EINVAL;
 	}
 
@@ -252,7 +252,7 @@ static int realloc_sampling_buffer(struct sf_buffer *sfb,
 	sfb->tail = tail;
 
 	debug_sprintf_event(sfdbg, 4, "realloc_sampling_buffer: new buffer"
-			    " settings: sdbt=%lu sdb=%lu\n",
+			    " settings: sdbt %lu sdb %lu\n",
 			    sfb->num_sdbt, sfb->num_sdb);
 	return rc;
 }
@@ -293,11 +293,11 @@ static int alloc_sampling_buffer(struct sf_buffer *sfb, unsigned long num_sdb)
 	if (rc) {
 		free_sampling_buffer(sfb);
 		debug_sprintf_event(sfdbg, 4, "alloc_sampling_buffer: "
-			"realloc_sampling_buffer failed with rc=%i\n", rc);
+			"realloc_sampling_buffer failed with rc %i\n", rc);
 	} else
 		debug_sprintf_event(sfdbg, 4,
-			"alloc_sampling_buffer: tear=%p dear=%p\n",
-			sfb->sdbt, (void *) *sfb->sdbt);
+			"alloc_sampling_buffer: tear %p dear %p\n",
+			sfb->sdbt, (void *)*sfb->sdbt);
 	return rc;
 }
 
@@ -404,8 +404,8 @@ static int allocate_buffers(struct cpu_hw_sf *cpuhw, struct hw_perf_event *hwc)
 		return 0;
 
 	debug_sprintf_event(sfdbg, 3,
-			    "allocate_buffers: rate=%lu f=%lu sdb=%lu/%lu"
-			    " sample_size=%lu cpuhw=%p\n",
+			    "%s: rate %lu f %lu sdb %lu/%lu"
+			    " sample_size %lu cpuhw %p\n", __func__,
 			    SAMPL_RATE(hwc), freq, n_sdb, sfb_max_limit(hwc),
 			    sample_size, cpuhw);
 
@@ -465,8 +465,8 @@ static void sfb_account_overflows(struct cpu_hw_sf *cpuhw,
 	if (num)
 		sfb_account_allocs(num, hwc);
 
-	debug_sprintf_event(sfdbg, 5, "sfb: overflow: overflow=%llu ratio=%lu"
-			    " num=%lu\n", OVERFLOW_REG(hwc), ratio, num);
+	debug_sprintf_event(sfdbg, 5, "sfb: overflow: overflow %llu ratio %lu"
+			    " num %lu\n", OVERFLOW_REG(hwc), ratio, num);
 	OVERFLOW_REG(hwc) = 0;
 }
 
@@ -505,11 +505,11 @@ static void extend_sampling_buffer(struct sf_buffer *sfb,
 	rc = realloc_sampling_buffer(sfb, num, GFP_ATOMIC);
 	if (rc)
 		debug_sprintf_event(sfdbg, 5, "sfb: extend: realloc "
-				    "failed with rc=%i\n", rc);
+				    "failed with rc %i\n", rc);
 
 	if (sfb_has_pending_allocs(sfb, hwc))
 		debug_sprintf_event(sfdbg, 5, "sfb: extend: "
-				    "req=%lu alloc=%lu remaining=%lu\n",
+				    "req %lu alloc %lu remaining %lu\n",
 				    num, sfb->num_sdb - num_old,
 				    sfb_pending_allocs(sfb, hwc));
 }
@@ -538,20 +538,22 @@ static void setup_pmc_cpu(void *flags)
 		err = sf_disable();
 		if (err)
 			pr_err("Switching off the sampling facility failed "
-			       "with rc=%i\n", err);
+			       "with rc %i\n", err);
 		debug_sprintf_event(sfdbg, 5,
-				    "setup_pmc_cpu: initialized: cpuhw=%p\n", cpusf);
+				    "%s: initialized: cpuhw %p\n", __func__,
+				    cpusf);
 		break;
 	case PMC_RELEASE:
 		cpusf->flags &= ~PMU_F_RESERVED;
 		err = sf_disable();
 		if (err) {
 			pr_err("Switching off the sampling facility failed "
-			       "with rc=%i\n", err);
+			       "with rc %i\n", err);
 		} else
 			deallocate_buffers(cpusf);
 		debug_sprintf_event(sfdbg, 5,
-				    "setup_pmc_cpu: released: cpuhw=%p\n", cpusf);
+				    "%s: released: cpuhw %p\n", __func__,
+				    cpusf);
 		break;
 	}
 	if (err)
@@ -744,7 +746,7 @@ static int __hw_perf_event_init_rate(struct perf_event *event,
 	SAMPL_RATE(hwc) = rate;
 	hw_init_period(hwc, SAMPL_RATE(hwc));
 	debug_sprintf_event(sfdbg, 4, "__hw_perf_event_init_rate:"
-			    "cpu:%d period:%llx freq:%d,%#lx\n", event->cpu,
+			    "cpu:%d period:%#llx freq:%d,%#lx\n", event->cpu,
 			    event->attr.sample_period, event->attr.freq,
 			    SAMPLE_FREQ_MODE(hwc));
 	return 0;
@@ -963,7 +965,7 @@ static void cpumsf_pmu_enable(struct pmu *pmu)
 	err = lsctl(&cpuhw->lsctl);
 	if (err) {
 		cpuhw->flags &= ~PMU_F_ENABLED;
-		pr_err("Loading sampling controls failed: op=%i err=%i\n",
+		pr_err("Loading sampling controls failed: op %i err %i\n",
 			1, err);
 		return;
 	}
@@ -971,8 +973,8 @@ static void cpumsf_pmu_enable(struct pmu *pmu)
 	/* Load current program parameter */
 	lpp(&S390_lowcore.lpp);
 
-	debug_sprintf_event(sfdbg, 6, "pmu_enable: es=%i cs=%i ed=%i cd=%i "
-			    "interval:%lx tear=%p dear=%p\n",
+	debug_sprintf_event(sfdbg, 6, "pmu_enable: es %i cs %i ed %i cd %i "
+			    "interval %#lx tear %p dear %p\n",
 			    cpuhw->lsctl.es, cpuhw->lsctl.cs, cpuhw->lsctl.ed,
 			    cpuhw->lsctl.cd, cpuhw->lsctl.interval,
 			    (void *) cpuhw->lsctl.tear,
@@ -999,13 +1001,14 @@ static void cpumsf_pmu_disable(struct pmu *pmu)
 
 	err = lsctl(&inactive);
 	if (err) {
-		pr_err("Loading sampling controls failed: op=%i err=%i\n",
+		pr_err("Loading sampling controls failed: op %i err %i\n",
 			2, err);
 		return;
 	}
 
 	/* Save state of TEAR and DEAR register contents */
-	if (!qsi(&si)) {
+	err = qsi(&si);
+	if (!err) {
 		/* TEAR/DEAR values are valid only if the sampling facility is
 		 * enabled.  Note that cpumsf_pmu_disable() might be called even
 		 * for a disabled sampling facility because cpumsf_pmu_enable()
@@ -1017,7 +1020,7 @@ static void cpumsf_pmu_disable(struct pmu *pmu)
 		}
 	} else
 		debug_sprintf_event(sfdbg, 3, "cpumsf_pmu_disable: "
-				    "qsi() failed with err=%i\n", err);
+				    "qsi() failed with err %i\n", err);
 
 	cpuhw->flags &= ~PMU_F_ENABLED;
 }
@@ -1130,15 +1133,6 @@ static void perf_event_count_update(struct perf_event *event, u64 count)
 	local64_add(count, &event->count);
 }
 
-static void debug_sample_entry(struct hws_basic_entry *sample,
-			       struct hws_trailer_entry *te)
-{
-	debug_sprintf_event(sfdbg, 4, "hw_collect_samples: Found unknown "
-			    "sampling data entry: te->f=%i basic.def=%04x "
-			    "(%p)\n",
-			    te->f, sample->def, sample);
-}
-
 /* hw_collect_samples() - Walk through a sample-data-block and collect samples
  * @event:	The perf event
  * @sdbt:	Sample-data-block table
@@ -1192,7 +1186,11 @@ static void hw_collect_samples(struct perf_event *event, unsigned long *sdbt,
 				/* Count discarded samples */
 				*overflow += 1;
 		} else {
-			debug_sample_entry(sample, te);
+			debug_sprintf_event(sfdbg, 4,
+					    "%s: Found unknown"
+					    " sampling data entry: te->f %i"
+					    " basic.def %#4x (%p)\n", __func__,
+					    te->f, sample->def, sample);
 			/* Sample slot is not yet written or other record.
 			 *
 			 * This condition can occur if the buffer was reused
@@ -1267,9 +1265,9 @@ static void hw_perf_event_update(struct perf_event *event, int flush_all)
 			sampl_overflow += te->overflow;
 
 		/* Timestamps are valid for full sample-data-blocks only */
-		debug_sprintf_event(sfdbg, 6, "hw_perf_event_update: sdbt=%p "
-				    "overflow=%llu timestamp=%#llx\n",
-				    sdbt, te->overflow,
+		debug_sprintf_event(sfdbg, 6, "%s: sdbt %p "
+				    "overflow %llu timestamp %#llx\n",
+				    __func__, sdbt, te->overflow,
 				    (te->f) ? trailer_timestamp(te) : 0ULL);
 
 		/* Collect all samples from a single sample-data-block and
@@ -1313,9 +1311,9 @@ static void hw_perf_event_update(struct perf_event *event, int flush_all)
 		OVERFLOW_REG(hwc) = DIV_ROUND_UP(OVERFLOW_REG(hwc) +
 						 sampl_overflow, 1 + num_sdb);
 	if (sampl_overflow || event_overflow)
-		debug_sprintf_event(sfdbg, 4, "hw_perf_event_update: "
-				    "overflow stats: sample=%llu event=%llu\n",
-				    sampl_overflow, event_overflow);
+		debug_sprintf_event(sfdbg, 4, "%s: "
+				    "overflow stats: sample %llu event %llu\n",
+				    __func__, sampl_overflow, event_overflow);
 }
 
 #define AUX_SDB_INDEX(aux, i) ((i) % aux->sfb.num_sdb)
@@ -1368,7 +1366,7 @@ static void aux_output_end(struct perf_output_handle *handle)
 	te = aux_sdb_trailer(aux, aux->alert_mark);
 	te->flags &= ~SDB_TE_ALERT_REQ_MASK;
 
-	debug_sprintf_event(sfdbg, 6, "aux_output_end: collect %lx SDBs\n", i);
+	debug_sprintf_event(sfdbg, 6, "%s: collect %#lx SDBs\n", __func__, i);
 }
 
 /*
@@ -1428,8 +1426,8 @@ static int aux_output_begin(struct perf_output_handle *handle,
 
 	debug_sprintf_event(sfdbg, 6, "aux_output_begin: "
 			    "head->alert_mark->empty_mark (num_alert, range)"
-			    "[%lx -> %lx -> %lx] (%lx, %lx) "
-			    "tear index %lx, tear %lx dear %lx\n",
+			    "[%#lx -> %#lx -> %#lx] (%#lx, %#lx) "
+			    "tear index %#lx, tear %#lx dear %#lx\n",
 			    aux->head, aux->alert_mark, aux->empty_mark,
 			    AUX_SDB_NUM_ALERT(aux), range,
 			    head / CPUM_SF_SDB_PER_TABLE,
@@ -1596,13 +1594,13 @@ static void hw_collect_aux(struct cpu_hw_sf *cpuhw)
 			perf_aux_output_end(&cpuhw->handle, size);
 			pr_err("Sample data caused the AUX buffer with %lu "
 			       "pages to overflow\n", num_sdb);
-			debug_sprintf_event(sfdbg, 1, "head %lx range %lx "
-					    "overflow %llx\n",
+			debug_sprintf_event(sfdbg, 1, "head %#lx range %#lx "
+					    "overflow %#llx\n",
 					    aux->head, range, overflow);
 		} else {
 			size = AUX_SDB_NUM_ALERT(aux) << PAGE_SHIFT;
 			perf_aux_output_end(&cpuhw->handle, size);
-			debug_sprintf_event(sfdbg, 6, "head %lx alert %lx "
+			debug_sprintf_event(sfdbg, 6, "head %#lx alert %#lx "
 					    "already full, try another\n",
 					    aux->head, aux->alert_mark);
 		}
@@ -1610,7 +1608,7 @@ static void hw_collect_aux(struct cpu_hw_sf *cpuhw)
 
 	if (done)
 		debug_sprintf_event(sfdbg, 6, "aux_reset_buffer: "
-				    "[%lx -> %lx -> %lx] (%lx, %lx)\n",
+				    "[%#lx -> %#lx -> %#lx] (%#lx, %#lx)\n",
 				    aux->head, aux->alert_mark, aux->empty_mark,
 				    AUX_SDB_NUM_ALERT(aux), range);
 }
@@ -1800,7 +1798,7 @@ static int cpumsf_pmu_check_period(struct perf_event *event, u64 value)
 	SAMPL_RATE(&event->hw) = rate;
 	hw_init_period(&event->hw, SAMPL_RATE(&event->hw));
 	debug_sprintf_event(sfdbg, 4, "cpumsf_pmu_check_period:"
-			    "cpu:%d value:%llx period:%llx freq:%d\n",
+			    "cpu:%d value:%#llx period:%#llx freq:%d\n",
 			    event->cpu, value,
 			    event->attr.sample_period, do_freq);
 	return 0;
@@ -2111,7 +2109,7 @@ static int param_set_sfb_size(const char *val, const struct kernel_param *kp)
 
 	sfb_set_limits(min, max);
 	pr_info("The sampling buffer limits have changed to: "
-		"min=%lu max=%lu (diag=x%lu)\n",
+		"min %lu max %lu (diag %lu)\n",
 		CPUM_SF_MIN_SDB, CPUM_SF_MAX_SDB, CPUM_SF_SDB_DIAG_FACTOR);
 	return 0;
 }
@@ -2129,7 +2127,7 @@ static const struct kernel_param_ops param_ops_sfb_size = {
 static void __init pr_cpumsf_err(unsigned int reason)
 {
 	pr_err("Sampling facility support for perf is not available: "
-	       "reason=%04x\n", reason);
+	       "reason %#x\n", reason);
 }
 
 static int __init init_cpum_sampling_pmu(void)
diff --git a/arch/s390/kernel/perf_event.c b/arch/s390/kernel/perf_event.c
index fcb6c2e92b07..1e75cc983546 100644
--- a/arch/s390/kernel/perf_event.c
+++ b/arch/s390/kernel/perf_event.c
@@ -224,9 +224,13 @@ void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
 			   struct pt_regs *regs)
 {
 	struct unwind_state state;
+	unsigned long addr;
 
-	unwind_for_each_frame(&state, current, regs, 0)
-		perf_callchain_store(entry, state.ip);
+	unwind_for_each_frame(&state, current, regs, 0) {
+		addr = unwind_get_return_address(&state);
+		if (!addr || perf_callchain_store(entry, addr))
+			return;
+	}
 }
 
 /* Perf definitions for PMU event attributes in sysfs */
diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
index b0afec673f77..6ccef5f29761 100644
--- a/arch/s390/kernel/process.c
+++ b/arch/s390/kernel/process.c
@@ -40,6 +40,7 @@
 #include <asm/stacktrace.h>
 #include <asm/switch_to.h>
 #include <asm/runtime_instr.h>
+#include <asm/unwind.h>
 #include "entry.h"
 
 asmlinkage void ret_from_fork(void) asm ("ret_from_fork");
@@ -178,9 +179,8 @@ EXPORT_SYMBOL(dump_fpu);
 
 unsigned long get_wchan(struct task_struct *p)
 {
-	struct stack_frame *sf, *low, *high;
-	unsigned long return_address;
-	int count;
+	struct unwind_state state;
+	unsigned long ip = 0;
 
 	if (!p || p == current || p->state == TASK_RUNNING || !task_stack_page(p))
 		return 0;
@@ -188,26 +188,22 @@ unsigned long get_wchan(struct task_struct *p)
 	if (!try_get_task_stack(p))
 		return 0;
 
-	low = task_stack_page(p);
-	high = (struct stack_frame *) task_pt_regs(p);
-	sf = (struct stack_frame *) p->thread.ksp;
-	if (sf <= low || sf > high) {
-		return_address = 0;
-		goto out;
-	}
-	for (count = 0; count < 16; count++) {
-		sf = (struct stack_frame *)READ_ONCE_NOCHECK(sf->back_chain);
-		if (sf <= low || sf > high) {
-			return_address = 0;
-			goto out;
+	unwind_for_each_frame(&state, p, NULL, 0) {
+		if (state.stack_info.type != STACK_TYPE_TASK) {
+			ip = 0;
+			break;
 		}
-		return_address = READ_ONCE_NOCHECK(sf->gprs[8]);
-		if (!in_sched_functions(return_address))
-			goto out;
+
+		ip = unwind_get_return_address(&state);
+		if (!ip)
+			break;
+
+		if (!in_sched_functions(ip))
+			break;
 	}
-out:
+
 	put_task_stack(p);
-	return return_address;
+	return ip;
 }
 
 unsigned long arch_align_stack(unsigned long sp)
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index 44974654cbd0..6acdcf1d4074 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -724,39 +724,67 @@ static void __ref smp_get_core_info(struct sclp_core_info *info, int early)
 
 static int smp_add_present_cpu(int cpu);
 
-static int __smp_rescan_cpus(struct sclp_core_info *info, int sysfs_add)
+static int smp_add_core(struct sclp_core_entry *core, cpumask_t *avail,
+			bool configured, bool early)
 {
 	struct pcpu *pcpu;
-	cpumask_t avail;
-	int cpu, nr, i, j;
+	int cpu, nr, i;
 	u16 address;
 
 	nr = 0;
-	cpumask_xor(&avail, cpu_possible_mask, cpu_present_mask);
-	cpu = cpumask_first(&avail);
-	for (i = 0; (i < info->combined) && (cpu < nr_cpu_ids); i++) {
-		if (sclp.has_core_type && info->core[i].type != boot_core_type)
+	if (sclp.has_core_type && core->type != boot_core_type)
+		return nr;
+	cpu = cpumask_first(avail);
+	address = core->core_id << smp_cpu_mt_shift;
+	for (i = 0; (i <= smp_cpu_mtid) && (cpu < nr_cpu_ids); i++) {
+		if (pcpu_find_address(cpu_present_mask, address + i))
 			continue;
-		address = info->core[i].core_id << smp_cpu_mt_shift;
-		for (j = 0; j <= smp_cpu_mtid; j++) {
-			if (pcpu_find_address(cpu_present_mask, address + j))
-				continue;
-			pcpu = pcpu_devices + cpu;
-			pcpu->address = address + j;
-			pcpu->state =
-				(cpu >= info->configured*(smp_cpu_mtid + 1)) ?
-				CPU_STATE_STANDBY : CPU_STATE_CONFIGURED;
-			smp_cpu_set_polarization(cpu, POLARIZATION_UNKNOWN);
-			set_cpu_present(cpu, true);
-			if (sysfs_add && smp_add_present_cpu(cpu) != 0)
-				set_cpu_present(cpu, false);
-			else
-				nr++;
-			cpu = cpumask_next(cpu, &avail);
-			if (cpu >= nr_cpu_ids)
+		pcpu = pcpu_devices + cpu;
+		pcpu->address = address + i;
+		if (configured)
+			pcpu->state = CPU_STATE_CONFIGURED;
+		else
+			pcpu->state = CPU_STATE_STANDBY;
+		smp_cpu_set_polarization(cpu, POLARIZATION_UNKNOWN);
+		set_cpu_present(cpu, true);
+		if (!early && smp_add_present_cpu(cpu) != 0)
+			set_cpu_present(cpu, false);
+		else
+			nr++;
+		cpumask_clear_cpu(cpu, avail);
+		cpu = cpumask_next(cpu, avail);
+	}
+	return nr;
+}
+
+static int __smp_rescan_cpus(struct sclp_core_info *info, bool early)
+{
+	struct sclp_core_entry *core;
+	cpumask_t avail;
+	bool configured;
+	u16 core_id;
+	int nr, i;
+
+	nr = 0;
+	cpumask_xor(&avail, cpu_possible_mask, cpu_present_mask);
+	/*
+	 * Add IPL core first (which got logical CPU number 0) to make sure
+	 * that all SMT threads get subsequent logical CPU numbers.
+	 */
+	if (early) {
+		core_id = pcpu_devices[0].address >> smp_cpu_mt_shift;
+		for (i = 0; i < info->configured; i++) {
+			core = &info->core[i];
+			if (core->core_id == core_id) {
+				nr += smp_add_core(core, &avail, true, early);
 				break;
+			}
 		}
 	}
+	for (i = 0; i < info->combined; i++) {
+		configured = i < info->configured;
+		nr += smp_add_core(&info->core[i], &avail, configured, early);
+	}
 	return nr;
 }
 
@@ -805,7 +833,7 @@ void __init smp_detect_cpus(void)
 
 	/* Add CPUs present at boot */
 	get_online_cpus();
-	__smp_rescan_cpus(info, 0);
+	__smp_rescan_cpus(info, true);
 	put_online_cpus();
 	memblock_free_early((unsigned long)info, sizeof(*info));
 }
@@ -1148,7 +1176,7 @@ int __ref smp_rescan_cpus(void)
 	smp_get_core_info(info, 0);
 	get_online_cpus();
 	mutex_lock(&smp_cpu_state_mutex);
-	nr = __smp_rescan_cpus(info, 1);
+	nr = __smp_rescan_cpus(info, false);
 	mutex_unlock(&smp_cpu_state_mutex);
 	put_online_cpus();
 	kfree(info);
diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index e8766beee5ad..f9d070d016e3 100644
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -110,15 +110,6 @@ unsigned long long notrace sched_clock(void)
 }
 NOKPROBE_SYMBOL(sched_clock);
 
-/*
- * Monotonic_clock - returns # of nanoseconds passed since time_init()
- */
-unsigned long long monotonic_clock(void)
-{
-	return sched_clock();
-}
-EXPORT_SYMBOL(monotonic_clock);
-
 static void ext_to_timespec64(unsigned char *clk, struct timespec64 *xt)
 {
 	unsigned long long high, low, rem, sec, nsec;
diff --git a/arch/s390/kernel/unwind_bc.c b/arch/s390/kernel/unwind_bc.c
index a8204f952315..fa111d3d378f 100644
--- a/arch/s390/kernel/unwind_bc.c
+++ b/arch/s390/kernel/unwind_bc.c
@@ -85,12 +85,7 @@ bool unwind_next_frame(struct unwind_state *state)
 		}
 	}
 
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	/* Decode any ftrace redirection */
-	if (ip == (unsigned long) return_to_handler)
-		ip = ftrace_graph_ret_addr(state->task, &state->graph_idx,
-					   ip, (void *) sp);
-#endif
+	ip = ftrace_graph_ret_addr(state->task, &state->graph_idx, ip, (void *) sp);
 
 	/* Update unwind state */
 	state->sp = sp;
@@ -147,12 +142,7 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task,
 		reuse_sp = false;
 	}
 
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	/* Decode any ftrace redirection */
-	if (ip == (unsigned long) return_to_handler)
-		ip = ftrace_graph_ret_addr(state->task, &state->graph_idx,
-					   ip, NULL);
-#endif
+	ip = ftrace_graph_ret_addr(state->task, &state->graph_idx, ip, NULL);
 
 	/* Update unwind state */
 	state->sp = sp;
diff --git a/arch/s390/lib/spinlock.c b/arch/s390/lib/spinlock.c
index 30a7c8c29964..ce1e4bbe53aa 100644
--- a/arch/s390/lib/spinlock.c
+++ b/arch/s390/lib/spinlock.c
@@ -74,7 +74,7 @@ static inline int arch_load_niai4(int *lock)
 {
 	int owner;
 
-	asm volatile(
+	asm_inline volatile(
 		ALTERNATIVE("", ".long 0xb2fa0040", 49)	/* NIAI 4 */
 		"	l	%0,%1\n"
 		: "=d" (owner) : "Q" (*lock) : "memory");
@@ -85,7 +85,7 @@ static inline int arch_cmpxchg_niai8(int *lock, int old, int new)
 {
 	int expected = old;
 
-	asm volatile(
+	asm_inline volatile(
 		ALTERNATIVE("", ".long 0xb2fa0080", 49)	/* NIAI 8 */
 		"	cs	%0,%3,%1\n"
 		: "=d" (old), "=Q" (*lock)
diff --git a/arch/s390/mm/maccess.c b/arch/s390/mm/maccess.c
index 1864a8bb9622..59ad7997fed1 100644
--- a/arch/s390/mm/maccess.c
+++ b/arch/s390/mm/maccess.c
@@ -70,7 +70,7 @@ void notrace s390_kernel_write(void *dst, const void *src, size_t size)
 	spin_unlock_irqrestore(&s390_kernel_write_lock, flags);
 }
 
-static int __memcpy_real(void *dest, void *src, size_t count)
+static int __no_sanitize_address __memcpy_real(void *dest, void *src, size_t count)
 {
 	register unsigned long _dest asm("2") = (unsigned long) dest;
 	register unsigned long _len1 asm("3") = (unsigned long) count;
@@ -91,19 +91,23 @@ static int __memcpy_real(void *dest, void *src, size_t count)
 	return rc;
 }
 
-static unsigned long _memcpy_real(unsigned long dest, unsigned long src,
-				  unsigned long count)
+static unsigned long __no_sanitize_address _memcpy_real(unsigned long dest,
+							unsigned long src,
+							unsigned long count)
 {
 	int irqs_disabled, rc;
 	unsigned long flags;
 
 	if (!count)
 		return 0;
-	flags = __arch_local_irq_stnsm(0xf8UL);
+	flags = arch_local_irq_save();
 	irqs_disabled = arch_irqs_disabled_flags(flags);
 	if (!irqs_disabled)
 		trace_hardirqs_off();
+	__arch_local_irq_stnsm(0xf8); // disable DAT
 	rc = __memcpy_real((void *) dest, (void *) src, (size_t) count);
+	if (flags & PSW_MASK_DAT)
+		__arch_local_irq_stosm(0x04); // enable DAT
 	if (!irqs_disabled)
 		trace_hardirqs_on();
 	__arch_local_irq_ssm(flags);