21 files changed, 426 insertions, 375 deletions

diff --git a/arch/s390/include/asm/abs_lowcore.h b/arch/s390/include/asm/abs_lowcore.h
index d20df8c923fc..004d17ea05cf 100644
--- a/arch/s390/include/asm/abs_lowcore.h
+++ b/arch/s390/include/asm/abs_lowcore.h
@@ -2,7 +2,7 @@
 #ifndef _ASM_S390_ABS_LOWCORE_H
 #define _ASM_S390_ABS_LOWCORE_H
 
-#include <asm/sections.h>
+#include <linux/smp.h>
 #include <asm/lowcore.h>
 
 #define ABS_LOWCORE_MAP_SIZE	(NR_CPUS * sizeof(struct lowcore))
@@ -25,7 +25,7 @@ static inline void put_abs_lowcore(struct lowcore *lc)
 	put_cpu();
 }
 
-extern int __bootdata_preserved(relocate_lowcore);
+extern int relocate_lowcore;
 
 static inline int have_relocated_lowcore(void)
 {
diff --git a/arch/s390/include/asm/atomic.h b/arch/s390/include/asm/atomic.h
index 6723fca64018..b36dd6a1d652 100644
--- a/arch/s390/include/asm/atomic.h
+++ b/arch/s390/include/asm/atomic.h
@@ -17,13 +17,13 @@
 
 static __always_inline int arch_atomic_read(const atomic_t *v)
 {
-	return __atomic_read(v);
+	return __atomic_read(&v->counter);
 }
 #define arch_atomic_read arch_atomic_read
 
 static __always_inline void arch_atomic_set(atomic_t *v, int i)
 {
-	__atomic_set(v, i);
+	__atomic_set(&v->counter, i);
 }
 #define arch_atomic_set arch_atomic_set
 
@@ -45,6 +45,36 @@ static __always_inline void arch_atomic_add(int i, atomic_t *v)
 }
 #define arch_atomic_add arch_atomic_add
 
+static __always_inline void arch_atomic_inc(atomic_t *v)
+{
+	__atomic_add_const(1, &v->counter);
+}
+#define arch_atomic_inc arch_atomic_inc
+
+static __always_inline void arch_atomic_dec(atomic_t *v)
+{
+	__atomic_add_const(-1, &v->counter);
+}
+#define arch_atomic_dec arch_atomic_dec
+
+static __always_inline bool arch_atomic_sub_and_test(int i, atomic_t *v)
+{
+	return __atomic_add_and_test_barrier(-i, &v->counter);
+}
+#define arch_atomic_sub_and_test arch_atomic_sub_and_test
+
+static __always_inline bool arch_atomic_dec_and_test(atomic_t *v)
+{
+	return __atomic_add_const_and_test_barrier(-1, &v->counter);
+}
+#define arch_atomic_dec_and_test arch_atomic_dec_and_test
+
+static __always_inline bool arch_atomic_inc_and_test(atomic_t *v)
+{
+	return __atomic_add_const_and_test_barrier(1, &v->counter);
+}
+#define arch_atomic_inc_and_test arch_atomic_inc_and_test
+
 #define arch_atomic_sub(_i, _v)		arch_atomic_add(-(int)(_i), _v)
 #define arch_atomic_sub_return(_i, _v)	arch_atomic_add_return(-(int)(_i), _v)
 #define arch_atomic_fetch_sub(_i, _v)	arch_atomic_fetch_add(-(int)(_i), _v)
@@ -94,13 +124,13 @@ static __always_inline bool arch_atomic_try_cmpxchg(atomic_t *v, int *old, int n
 
 static __always_inline s64 arch_atomic64_read(const atomic64_t *v)
 {
-	return __atomic64_read(v);
+	return __atomic64_read((long *)&v->counter);
 }
 #define arch_atomic64_read arch_atomic64_read
 
 static __always_inline void arch_atomic64_set(atomic64_t *v, s64 i)
 {
-	__atomic64_set(v, i);
+	__atomic64_set((long *)&v->counter, i);
 }
 #define arch_atomic64_set arch_atomic64_set
 
@@ -122,6 +152,36 @@ static __always_inline void arch_atomic64_add(s64 i, atomic64_t *v)
 }
 #define arch_atomic64_add arch_atomic64_add
 
+static __always_inline void arch_atomic64_inc(atomic64_t *v)
+{
+	__atomic64_add_const(1, (long *)&v->counter);
+}
+#define arch_atomic64_inc arch_atomic64_inc
+
+static __always_inline void arch_atomic64_dec(atomic64_t *v)
+{
+	__atomic64_add_const(-1, (long *)&v->counter);
+}
+#define arch_atomic64_dec arch_atomic64_dec
+
+static __always_inline bool arch_atomic64_sub_and_test(s64 i, atomic64_t *v)
+{
+	return __atomic64_add_and_test_barrier(-i, (long *)&v->counter);
+}
+#define arch_atomic64_sub_and_test arch_atomic64_sub_and_test
+
+static __always_inline bool arch_atomic64_dec_and_test(atomic64_t *v)
+{
+	return __atomic64_add_const_and_test_barrier(-1, (long *)&v->counter);
+}
+#define arch_atomic64_dec_and_test arch_atomic64_dec_and_test
+
+static __always_inline bool arch_atomic64_inc_and_test(atomic64_t *v)
+{
+	return __atomic64_add_const_and_test_barrier(1, (long *)&v->counter);
+}
+#define arch_atomic64_inc_and_test arch_atomic64_inc_and_test
+
 static __always_inline s64 arch_atomic64_xchg(atomic64_t *v, s64 new)
 {
 	return arch_xchg(&v->counter, new);
diff --git a/arch/s390/include/asm/atomic_ops.h b/arch/s390/include/asm/atomic_ops.h
index 1d6b2056fad8..585678bbcd7a 100644
--- a/arch/s390/include/asm/atomic_ops.h
+++ b/arch/s390/include/asm/atomic_ops.h
@@ -10,50 +10,51 @@
 
 #include <linux/limits.h>
 #include <asm/march.h>
+#include <asm/asm.h>
 
-static __always_inline int __atomic_read(const atomic_t *v)
+static __always_inline int __atomic_read(const int *ptr)
 {
-	int c;
+	int val;
 
 	asm volatile(
-		"	l	%[c],%[counter]\n"
-		: [c] "=d" (c) : [counter] "R" (v->counter));
-	return c;
+		"	l	%[val],%[ptr]\n"
+		: [val] "=d" (val) : [ptr] "R" (*ptr));
+	return val;
 }
 
-static __always_inline void __atomic_set(atomic_t *v, int i)
+static __always_inline void __atomic_set(int *ptr, int val)
 {
-	if (__builtin_constant_p(i) && i >= S16_MIN && i <= S16_MAX) {
+	if (__builtin_constant_p(val) && val >= S16_MIN && val <= S16_MAX) {
 		asm volatile(
-			"	mvhi	%[counter], %[i]\n"
-			: [counter] "=Q" (v->counter) : [i] "K" (i));
+			"	mvhi	%[ptr],%[val]\n"
+			: [ptr] "=Q" (*ptr) : [val] "K" (val));
 	} else {
 		asm volatile(
-			"	st	%[i],%[counter]\n"
-			: [counter] "=R" (v->counter) : [i] "d" (i));
+			"	st	%[val],%[ptr]\n"
+			: [ptr] "=R" (*ptr) : [val] "d" (val));
 	}
 }
 
-static __always_inline s64 __atomic64_read(const atomic64_t *v)
+static __always_inline long __atomic64_read(const long *ptr)
 {
-	s64 c;
+	long val;
 
 	asm volatile(
-		"	lg	%[c],%[counter]\n"
-		: [c] "=d" (c) : [counter] "RT" (v->counter));
-	return c;
+		"	lg	%[val],%[ptr]\n"
+		: [val] "=d" (val) : [ptr] "RT" (*ptr));
+	return val;
 }
 
-static __always_inline void __atomic64_set(atomic64_t *v, s64 i)
+static __always_inline void __atomic64_set(long *ptr, long val)
 {
-	if (__builtin_constant_p(i) && i >= S16_MIN && i <= S16_MAX) {
+	if (__builtin_constant_p(val) && val >= S16_MIN && val <= S16_MAX) {
 		asm volatile(
-			"	mvghi	%[counter], %[i]\n"
-			: [counter] "=Q" (v->counter) : [i] "K" (i));
+			"	mvghi	%[ptr],%[val]\n"
+			: [ptr] "=Q" (*ptr) : [val] "K" (val));
 	} else {
 		asm volatile(
-			"	stg	%[i],%[counter]\n"
-			: [counter] "=RT" (v->counter) : [i] "d" (i));
+			"	stg	%[val],%[ptr]\n"
+			: [ptr] "=RT" (*ptr) : [val] "d" (val));
 	}
 }
 
@@ -73,7 +74,7 @@ static __always_inline op_type op_name(op_type val, op_type *ptr)	\
 }									\
 
 #define __ATOMIC_OPS(op_name, op_type, op_string)			\
-	__ATOMIC_OP(op_name, op_type, op_string, "\n")			\
+	__ATOMIC_OP(op_name, op_type, op_string, "")			\
 	__ATOMIC_OP(op_name##_barrier, op_type, op_string, "bcr 14,0\n")
 
 __ATOMIC_OPS(__atomic_add, int, "laa")
@@ -99,7 +100,7 @@ static __always_inline void op_name(op_type val, op_type *ptr)		\
 }
 
 #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, op_type, op_string, "")		\
 	__ATOMIC_CONST_OP(op_name##_barrier, op_type, op_string, "bcr 14,0\n")
 
 __ATOMIC_CONST_OPS(__atomic_add_const, int, "asi")
@@ -169,4 +170,76 @@ __ATOMIC64_OPS(__atomic64_xor, "xgr")
 
 #endif /* MARCH_HAS_Z196_FEATURES */
 
+#if defined(MARCH_HAS_Z196_FEATURES) && defined(__HAVE_ASM_FLAG_OUTPUTS__)
+
+#define __ATOMIC_TEST_OP(op_name, op_type, op_string, op_barrier)	\
+static __always_inline bool op_name(op_type val, op_type *ptr)		\
+{									\
+	op_type tmp;							\
+	int cc;								\
+									\
+	asm volatile(							\
+		op_string "	%[tmp],%[val],%[ptr]\n"			\
+		op_barrier						\
+		: "=@cc" (cc), [tmp] "=d" (tmp), [ptr] "+QS" (*ptr)	\
+		: [val] "d" (val)					\
+		: "memory");						\
+	return (cc == 0) || (cc == 2);					\
+}									\
+
+#define __ATOMIC_TEST_OPS(op_name, op_type, op_string)			\
+	__ATOMIC_TEST_OP(op_name, op_type, op_string, "")		\
+	__ATOMIC_TEST_OP(op_name##_barrier, op_type, op_string, "bcr 14,0\n")
+
+__ATOMIC_TEST_OPS(__atomic_add_and_test, int, "laal")
+__ATOMIC_TEST_OPS(__atomic64_add_and_test, long, "laalg")
+
+#undef __ATOMIC_TEST_OPS
+#undef __ATOMIC_TEST_OP
+
+#define __ATOMIC_CONST_TEST_OP(op_name, op_type, op_string, op_barrier)	\
+static __always_inline bool op_name(op_type val, op_type *ptr)		\
+{									\
+	int cc;								\
+									\
+	asm volatile(							\
+		op_string "	%[ptr],%[val]\n"			\
+		op_barrier						\
+		: "=@cc" (cc), [ptr] "+QS" (*ptr)			\
+		: [val] "i" (val)					\
+		: "memory");						\
+	return (cc == 0) || (cc == 2);					\
+}
+
+#define __ATOMIC_CONST_TEST_OPS(op_name, op_type, op_string)		\
+	__ATOMIC_CONST_TEST_OP(op_name, op_type, op_string, "")		\
+	__ATOMIC_CONST_TEST_OP(op_name##_barrier, op_type, op_string, "bcr 14,0\n")
+
+__ATOMIC_CONST_TEST_OPS(__atomic_add_const_and_test, int, "alsi")
+__ATOMIC_CONST_TEST_OPS(__atomic64_add_const_and_test, long, "algsi")
+
+#undef __ATOMIC_CONST_TEST_OPS
+#undef __ATOMIC_CONST_TEST_OP
+
+#else /* defined(MARCH_HAS_Z196_FEATURES) && defined(__HAVE_ASM_FLAG_OUTPUTS__) */
+
+#define __ATOMIC_TEST_OP(op_name, op_func, op_type)			\
+static __always_inline bool op_name(op_type val, op_type *ptr)		\
+{									\
+	return op_func(val, ptr) == -val;				\
+}
+
+__ATOMIC_TEST_OP(__atomic_add_and_test,			__atomic_add,		int)
+__ATOMIC_TEST_OP(__atomic_add_and_test_barrier,		__atomic_add_barrier,	int)
+__ATOMIC_TEST_OP(__atomic_add_const_and_test,		__atomic_add,		int)
+__ATOMIC_TEST_OP(__atomic_add_const_and_test_barrier,	__atomic_add_barrier,	int)
+__ATOMIC_TEST_OP(__atomic64_add_and_test,		__atomic64_add,		long)
+__ATOMIC_TEST_OP(__atomic64_add_and_test_barrier,	__atomic64_add_barrier, long)
+__ATOMIC_TEST_OP(__atomic64_add_const_and_test,		__atomic64_add,		long)
+__ATOMIC_TEST_OP(__atomic64_add_const_and_test_barrier,	__atomic64_add_barrier,	long)
+
+#undef __ATOMIC_TEST_OP
+
+#endif /* defined(MARCH_HAS_Z196_FEATURES) && defined(__HAVE_ASM_FLAG_OUTPUTS__) */
+
 #endif /* __ARCH_S390_ATOMIC_OPS__  */
diff --git a/arch/s390/include/asm/bitops.h b/arch/s390/include/asm/bitops.h
index 54a079cd39ed..15aa64e3020e 100644
--- a/arch/s390/include/asm/bitops.h
+++ b/arch/s390/include/asm/bitops.h
@@ -36,184 +36,41 @@
 #include <linux/typecheck.h>
 #include <linux/compiler.h>
 #include <linux/types.h>
-#include <asm/atomic_ops.h>
-#include <asm/barrier.h>
-
-#define __BITOPS_WORDS(bits) (((bits) + BITS_PER_LONG - 1) / BITS_PER_LONG)
-
-static inline unsigned long *
-__bitops_word(unsigned long nr, const volatile unsigned long *ptr)
-{
-	unsigned long addr;
-
-	addr = (unsigned long)ptr + ((nr ^ (nr & (BITS_PER_LONG - 1))) >> 3);
-	return (unsigned long *)addr;
-}
-
-static inline unsigned long __bitops_mask(unsigned long nr)
-{
-	return 1UL << (nr & (BITS_PER_LONG - 1));
-}
-
-static __always_inline void arch_set_bit(unsigned long nr, volatile unsigned long *ptr)
-{
-	unsigned long *addr = __bitops_word(nr, ptr);
-	unsigned long mask = __bitops_mask(nr);
-
-	__atomic64_or(mask, (long *)addr);
-}
-
-static __always_inline void arch_clear_bit(unsigned long nr, volatile unsigned long *ptr)
-{
-	unsigned long *addr = __bitops_word(nr, ptr);
-	unsigned long mask = __bitops_mask(nr);
-
-	__atomic64_and(~mask, (long *)addr);
-}
-
-static __always_inline void arch_change_bit(unsigned long nr,
-					    volatile unsigned long *ptr)
-{
-	unsigned long *addr = __bitops_word(nr, ptr);
-	unsigned long mask = __bitops_mask(nr);
-
-	__atomic64_xor(mask, (long *)addr);
-}
-
-static inline bool arch_test_and_set_bit(unsigned long nr,
-					 volatile unsigned long *ptr)
-{
-	unsigned long *addr = __bitops_word(nr, ptr);
-	unsigned long mask = __bitops_mask(nr);
-	unsigned long old;
-
-	old = __atomic64_or_barrier(mask, (long *)addr);
-	return old & mask;
-}
-
-static inline bool arch_test_and_clear_bit(unsigned long nr,
-					   volatile unsigned long *ptr)
-{
-	unsigned long *addr = __bitops_word(nr, ptr);
-	unsigned long mask = __bitops_mask(nr);
-	unsigned long old;
-
-	old = __atomic64_and_barrier(~mask, (long *)addr);
-	return old & mask;
-}
-
-static inline bool arch_test_and_change_bit(unsigned long nr,
-					    volatile unsigned long *ptr)
-{
-	unsigned long *addr = __bitops_word(nr, ptr);
-	unsigned long mask = __bitops_mask(nr);
-	unsigned long old;
-
-	old = __atomic64_xor_barrier(mask, (long *)addr);
-	return old & mask;
-}
-
-static __always_inline void
-arch___set_bit(unsigned long nr, volatile unsigned long *addr)
-{
-	unsigned long *p = __bitops_word(nr, addr);
-	unsigned long mask = __bitops_mask(nr);
-
-	*p |= mask;
-}
-
-static __always_inline void
-arch___clear_bit(unsigned long nr, volatile unsigned long *addr)
-{
-	unsigned long *p = __bitops_word(nr, addr);
-	unsigned long mask = __bitops_mask(nr);
-
-	*p &= ~mask;
-}
-
-static __always_inline void
-arch___change_bit(unsigned long nr, volatile unsigned long *addr)
-{
-	unsigned long *p = __bitops_word(nr, addr);
-	unsigned long mask = __bitops_mask(nr);
-
-	*p ^= mask;
-}
-
-static __always_inline bool
-arch___test_and_set_bit(unsigned long nr, volatile unsigned long *addr)
-{
-	unsigned long *p = __bitops_word(nr, addr);
-	unsigned long mask = __bitops_mask(nr);
-	unsigned long old;
-
-	old = *p;
-	*p |= mask;
-	return old & mask;
-}
-
-static __always_inline bool
-arch___test_and_clear_bit(unsigned long nr, volatile unsigned long *addr)
-{
-	unsigned long *p = __bitops_word(nr, addr);
-	unsigned long mask = __bitops_mask(nr);
-	unsigned long old;
-
-	old = *p;
-	*p &= ~mask;
-	return old & mask;
-}
-
-static __always_inline bool
-arch___test_and_change_bit(unsigned long nr, volatile unsigned long *addr)
-{
-	unsigned long *p = __bitops_word(nr, addr);
-	unsigned long mask = __bitops_mask(nr);
-	unsigned long old;
-
-	old = *p;
-	*p ^= mask;
-	return old & mask;
-}
-
-#define arch_test_bit generic_test_bit
-#define arch_test_bit_acquire generic_test_bit_acquire
-
-static inline bool arch_test_and_set_bit_lock(unsigned long nr,
-					      volatile unsigned long *ptr)
-{
-	if (arch_test_bit(nr, ptr))
-		return true;
-	return arch_test_and_set_bit(nr, ptr);
-}
-
-static inline void arch_clear_bit_unlock(unsigned long nr,
-					 volatile unsigned long *ptr)
-{
-	smp_mb__before_atomic();
-	arch_clear_bit(nr, ptr);
-}
-
-static inline void arch___clear_bit_unlock(unsigned long nr,
-					   volatile unsigned long *ptr)
-{
-	smp_mb();
-	arch___clear_bit(nr, ptr);
-}
-
-static inline bool arch_xor_unlock_is_negative_byte(unsigned long mask,
-		volatile unsigned long *ptr)
-{
-	unsigned long old;
-
-	old = __atomic64_xor_barrier(mask, (long *)ptr);
-	return old & BIT(7);
+#include <asm/asm.h>
+
+#define arch___set_bit			generic___set_bit
+#define arch___clear_bit		generic___clear_bit
+#define arch___change_bit		generic___change_bit
+#define arch___test_and_set_bit		generic___test_and_set_bit
+#define arch___test_and_clear_bit	generic___test_and_clear_bit
+#define arch___test_and_change_bit	generic___test_and_change_bit
+#define arch_test_bit_acquire		generic_test_bit_acquire
+
+static __always_inline bool arch_test_bit(unsigned long nr, const volatile unsigned long *ptr)
+{
+#ifdef __HAVE_ASM_FLAG_OUTPUTS__
+	const volatile unsigned char *addr;
+	unsigned long mask;
+	int cc;
+
+	if (__builtin_constant_p(nr)) {
+		addr = (const volatile unsigned char *)ptr;
+		addr += (nr ^ (BITS_PER_LONG - BITS_PER_BYTE)) / BITS_PER_BYTE;
+		mask = 1UL << (nr & (BITS_PER_BYTE - 1));
+		asm volatile(
+			"	tm	%[addr],%[mask]\n"
+			: "=@cc" (cc)
+			: [addr] "R" (*addr), [mask] "I" (mask)
+			);
+		return cc == 3;
+	}
+#endif
+	return generic_test_bit(nr, ptr);
 }
-#define arch_xor_unlock_is_negative_byte arch_xor_unlock_is_negative_byte
 
-#include <asm-generic/bitops/instrumented-atomic.h>
-#include <asm-generic/bitops/instrumented-non-atomic.h>
-#include <asm-generic/bitops/instrumented-lock.h>
+#include <asm-generic/bitops/atomic.h>
+#include <asm-generic/bitops/non-instrumented-non-atomic.h>
+#include <asm-generic/bitops/lock.h>
 
 /*
  * Functions which use MSB0 bit numbering.
diff --git a/arch/s390/include/asm/checksum.h b/arch/s390/include/asm/checksum.h
index 46f5c9660616..d86dea5900e7 100644
--- a/arch/s390/include/asm/checksum.h
+++ b/arch/s390/include/asm/checksum.h
@@ -25,7 +25,7 @@ static inline __wsum cksm(const void *buff, int len, __wsum sum)
 
 	instrument_read(buff, len);
 	kmsan_check_memory(buff, len);
-	asm volatile("\n"
+	asm volatile(
 		"0:	cksm	%[sum],%[rp]\n"
 		"	jo	0b\n"
 		: [sum] "+&d" (sum), [rp] "+&d" (rp.pair) : : "cc", "memory");
diff --git a/arch/s390/include/asm/css_chars.h b/arch/s390/include/asm/css_chars.h
index 638137d46c85..a03f64033760 100644
--- a/arch/s390/include/asm/css_chars.h
+++ b/arch/s390/include/asm/css_chars.h
@@ -25,7 +25,7 @@ struct css_general_char {
 	u64 : 2;
 
 	u64 : 3;
-	u64 aif_osa : 1; /* bit 67 */
+	u64 aif_qdio : 1;/* bit 67 */
 	u64 : 12;
 	u64 eadm_rf : 1; /* bit 80 */
 	u64 : 1;
diff --git a/arch/s390/include/asm/debug.h b/arch/s390/include/asm/debug.h
index a7f7bdc9e19c..6375276d94ea 100644
--- a/arch/s390/include/asm/debug.h
+++ b/arch/s390/include/asm/debug.h
@@ -85,6 +85,10 @@ int debug_dflt_header_fn(debug_info_t *id, struct debug_view *view,
 			 int area, debug_entry_t *entry,
 			 char *out_buf, size_t out_buf_size);
 
+#define DEBUG_SPRINTF_MAX_ARGS 10
+int debug_sprintf_format_fn(debug_info_t *id, struct debug_view *view,
+			    char *out_buf, size_t out_buf_size,
+			    const char *inbuf);
 struct debug_view {
 	char name[DEBUG_MAX_NAME_LEN];
 	debug_prolog_proc_t *prolog_proc;
@@ -114,6 +118,9 @@ debug_info_t *debug_register_mode(const char *name, int pages, int nr_areas,
 				  int buf_size, umode_t mode, uid_t uid,
 				  gid_t gid);
 
+ssize_t debug_dump(debug_info_t *id, struct debug_view *view,
+		   char *buf, size_t buf_size, bool reverse);
+
 void debug_unregister(debug_info_t *id);
 
 void debug_set_level(debug_info_t *id, int new_level);
diff --git a/arch/s390/include/asm/diag.h b/arch/s390/include/asm/diag.h
index e1316e181230..5790630e31f0 100644
--- a/arch/s390/include/asm/diag.h
+++ b/arch/s390/include/asm/diag.h
@@ -36,8 +36,10 @@ enum diag_stat_enum {
 	DIAG_STAT_X2FC,
 	DIAG_STAT_X304,
 	DIAG_STAT_X308,
+	DIAG_STAT_X310,
 	DIAG_STAT_X318,
 	DIAG_STAT_X320,
+	DIAG_STAT_X324,
 	DIAG_STAT_X49C,
 	DIAG_STAT_X500,
 	NR_DIAG_STAT
diff --git a/arch/s390/include/asm/ebcdic.h b/arch/s390/include/asm/ebcdic.h
index efb50fc6866c..7164cb658435 100644
--- a/arch/s390/include/asm/ebcdic.h
+++ b/arch/s390/include/asm/ebcdic.h
@@ -22,18 +22,18 @@ extern __u8 _ebc_toupper[256]; /* EBCDIC -> uppercase */
 static inline void
 codepage_convert(const __u8 *codepage, volatile char *addr, unsigned long nr)
 {
-	if (nr-- <= 0)
+	if (!nr--)
 		return;
 	asm volatile(
-		"	bras	1,1f\n"
-		"	tr	0(1,%0),0(%2)\n"
-		"0:	tr	0(256,%0),0(%2)\n"
+		"	j	2f\n"
+		"0:	tr	0(1,%0),0(%2)\n"
+		"1:	tr	0(256,%0),0(%2)\n"
 		"	la	%0,256(%0)\n"
-		"1:	ahi	%1,-256\n"
-		"	jnm	0b\n"
-		"	ex	%1,0(1)"
+		"2:	aghi	%1,-256\n"
+		"	jnm	1b\n"
+		"	exrl	%1,0b"
 		: "+&a" (addr), "+&a" (nr)
-		: "a" (codepage) : "cc", "memory", "1");
+		: "a" (codepage) : "cc", "memory");
 }
 
 #define ASCEBC(addr,nr) codepage_convert(_ascebc, addr, nr)
diff --git a/arch/s390/include/asm/fprobe.h b/arch/s390/include/asm/fprobe.h
new file mode 100644
index 000000000000..5ef600b372f4
--- /dev/null
+++ b/arch/s390/include/asm/fprobe.h
@@ -0,0 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_S390_FPROBE_H
+#define _ASM_S390_FPROBE_H
+
+#include <asm-generic/fprobe.h>
+
+#undef FPROBE_HEADER_MSB_PATTERN
+#define FPROBE_HEADER_MSB_PATTERN 0
+
+#endif /* _ASM_S390_FPROBE_H */
diff --git a/arch/s390/include/asm/fpu-insn.h b/arch/s390/include/asm/fpu-insn.h
index c1e2e521d9af..de510c9f6efa 100644
--- a/arch/s390/include/asm/fpu-insn.h
+++ b/arch/s390/include/asm/fpu-insn.h
@@ -103,7 +103,7 @@ static inline void fpu_lfpc_safe(unsigned int *fpc)
 	u32 tmp;
 
 	instrument_read(fpc, sizeof(*fpc));
-	asm volatile("\n"
+	asm_inline volatile(
 		"0:	lfpc	%[fpc]\n"
 		"1:	nopr	%%r7\n"
 		".pushsection .fixup, \"ax\"\n"
@@ -188,7 +188,7 @@ static __always_inline void fpu_vgfmg(u8 v1, u8 v2, u8 v3)
 static __always_inline void fpu_vl(u8 v1, const void *vxr)
 {
 	instrument_read(vxr, sizeof(__vector128));
-	asm volatile("\n"
+	asm volatile(
 		"	la	1,%[vxr]\n"
 		"	VL	%[v1],0,,1\n"
 		:
@@ -246,7 +246,7 @@ static __always_inline void fpu_vll(u8 v1, u32 index, const void *vxr)
 
 	size = min(index + 1, sizeof(__vector128));
 	instrument_read(vxr, size);
-	asm volatile("\n"
+	asm volatile(
 		"	la	1,%[vxr]\n"
 		"	VLL	%[v1],%[index],0,1\n"
 		:
@@ -284,7 +284,7 @@ static __always_inline void fpu_vll(u8 v1, u32 index, const void *vxr)
 	} *_v = (void *)(_vxrs);					\
 									\
 	instrument_read(_v, size);					\
-	asm volatile("\n"						\
+	asm volatile(							\
 		"	la	1,%[vxrs]\n"				\
 		"	VLM	%[v1],%[v3],0,1\n"			\
 		:							\
@@ -367,7 +367,7 @@ static __always_inline void fpu_vsrlb(u8 v1, u8 v2, u8 v3)
 static __always_inline void fpu_vst(u8 v1, const void *vxr)
 {
 	instrument_write(vxr, sizeof(__vector128));
-	asm volatile("\n"
+	asm volatile(
 		"	la	1,%[vxr]\n"
 		"	VST	%[v1],0,,1\n"
 		: [vxr] "=R" (*(__vector128 *)vxr)
@@ -396,7 +396,7 @@ static __always_inline void fpu_vstl(u8 v1, u32 index, const void *vxr)
 
 	size = min(index + 1, sizeof(__vector128));
 	instrument_write(vxr, size);
-	asm volatile("\n"
+	asm volatile(
 		"	la	1,%[vxr]\n"
 		"	VSTL	%[v1],%[index],0,1\n"
 		: [vxr] "=R" (*(u8 *)vxr)
@@ -430,7 +430,7 @@ static __always_inline void fpu_vstl(u8 v1, u32 index, const void *vxr)
 	} *_v = (void *)(_vxrs);					\
 									\
 	instrument_write(_v, size);					\
-	asm volatile("\n"						\
+	asm volatile(							\
 		"	la	1,%[vxrs]\n"				\
 		"	VSTM	%[v1],%[v3],0,1\n"			\
 		: [vxrs] "=R" (*_v)					\
diff --git a/arch/s390/include/asm/ftrace.h b/arch/s390/include/asm/ftrace.h
index fc97d75dc752..a3b73a4f626e 100644
--- a/arch/s390/include/asm/ftrace.h
+++ b/arch/s390/include/asm/ftrace.h
@@ -39,6 +39,7 @@ struct dyn_arch_ftrace { };
 
 struct module;
 struct dyn_ftrace;
+struct ftrace_ops;
 
 bool ftrace_need_init_nop(void);
 #define ftrace_need_init_nop ftrace_need_init_nop
@@ -62,30 +63,32 @@ static __always_inline struct pt_regs *arch_ftrace_get_regs(struct ftrace_regs *
 	return NULL;
 }
 
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-struct fgraph_ret_regs {
-	unsigned long gpr2;
-	unsigned long fp;
-};
-
-static __always_inline unsigned long fgraph_ret_regs_return_value(struct fgraph_ret_regs *ret_regs)
+static __always_inline void
+ftrace_regs_set_instruction_pointer(struct ftrace_regs *fregs,
+				    unsigned long ip)
 {
-	return ret_regs->gpr2;
+	arch_ftrace_regs(fregs)->regs.psw.addr = ip;
 }
 
-static __always_inline unsigned long fgraph_ret_regs_frame_pointer(struct fgraph_ret_regs *ret_regs)
+#undef ftrace_regs_get_frame_pointer
+static __always_inline unsigned long
+ftrace_regs_get_frame_pointer(struct ftrace_regs *fregs)
 {
-	return ret_regs->fp;
+	return ftrace_regs_get_stack_pointer(fregs);
 }
-#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
 
-static __always_inline void
-ftrace_regs_set_instruction_pointer(struct ftrace_regs *fregs,
-				    unsigned long ip)
+static __always_inline unsigned long
+ftrace_regs_get_return_address(const struct ftrace_regs *fregs)
 {
-	arch_ftrace_regs(fregs)->regs.psw.addr = ip;
+	return arch_ftrace_regs(fregs)->regs.gprs[14];
 }
 
+#define arch_ftrace_fill_perf_regs(fregs, _regs)	 do {		\
+		(_regs)->psw.mask = 0;					\
+		(_regs)->psw.addr = arch_ftrace_regs(fregs)->regs.psw.addr;		\
+		(_regs)->gprs[15] = arch_ftrace_regs(fregs)->regs.gprs[15];		\
+	} while (0)
+
 #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
 /*
  * When an ftrace registered caller is tracing a function that is
@@ -126,6 +129,10 @@ static inline bool arch_syscall_match_sym_name(const char *sym,
 	return !strcmp(sym + 7, name) || !strcmp(sym + 8, name);
 }
 
+void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
+		       struct ftrace_ops *op, struct ftrace_regs *fregs);
+#define ftrace_graph_func ftrace_graph_func
+
 #endif /* __ASSEMBLY__ */
 
 #ifdef CONFIG_FUNCTION_TRACER
diff --git a/arch/s390/include/asm/futex.h b/arch/s390/include/asm/futex.h
index eaeaeb3ff0be..752a2310f0d6 100644
--- a/arch/s390/include/asm/futex.h
+++ b/arch/s390/include/asm/futex.h
@@ -44,7 +44,7 @@ static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval,
 		break;
 	case FUTEX_OP_ANDN:
 		__futex_atomic_op("lr %2,%1\nnr %2,%5\n",
-				  ret, oldval, newval, uaddr, oparg);
+				  ret, oldval, newval, uaddr, ~oparg);
 		break;
 	case FUTEX_OP_XOR:
 		__futex_atomic_op("lr %2,%1\nxr %2,%5\n",
diff --git a/arch/s390/include/asm/hugetlb.h b/arch/s390/include/asm/hugetlb.h
index a40664b236e9..7c52acaf9f82 100644
--- a/arch/s390/include/asm/hugetlb.h
+++ b/arch/s390/include/asm/hugetlb.h
@@ -20,12 +20,13 @@
 void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 		     pte_t *ptep, pte_t pte, unsigned long sz);
 void __set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
-		     pte_t *ptep, pte_t pte);
+		       pte_t *ptep, pte_t pte);
+
 #define __HAVE_ARCH_HUGE_PTEP_GET
-extern pte_t huge_ptep_get(struct mm_struct *mm, unsigned long addr, pte_t *ptep);
+pte_t huge_ptep_get(struct mm_struct *mm, unsigned long addr, pte_t *ptep);
+
 #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
-extern pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-			      unsigned long addr, pte_t *ptep);
+pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep);
 
 static inline void arch_clear_hugetlb_flags(struct folio *folio)
 {
@@ -56,6 +57,7 @@ static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 					     pte_t pte, int dirty)
 {
 	int changed = !pte_same(huge_ptep_get(vma->vm_mm, addr, ptep), pte);
+
 	if (changed) {
 		huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
 		__set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
@@ -68,19 +70,8 @@ static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
 					   unsigned long addr, pte_t *ptep)
 {
 	pte_t pte = huge_ptep_get_and_clear(mm, addr, ptep);
-	__set_huge_pte_at(mm, addr, ptep, pte_wrprotect(pte));
-}
 
-#define __HAVE_ARCH_HUGE_PTE_NONE
-static inline int huge_pte_none(pte_t pte)
-{
-	return pte_none(pte);
-}
-
-#define __HAVE_ARCH_HUGE_PTE_NONE_MOSTLY
-static inline int huge_pte_none_mostly(pte_t pte)
-{
-	return huge_pte_none(pte) || is_pte_marker(pte);
+	__set_huge_pte_at(mm, addr, ptep, pte_wrprotect(pte));
 }
 
 #define __HAVE_ARCH_HUGE_PTE_MKUFFD_WP
diff --git a/arch/s390/include/asm/page-states.h b/arch/s390/include/asm/page-states.h
index 08fcbd628120..794fdb21500a 100644
--- a/arch/s390/include/asm/page-states.h
+++ b/arch/s390/include/asm/page-states.h
@@ -7,7 +7,6 @@
 #ifndef PAGE_STATES_H
 #define PAGE_STATES_H
 
-#include <asm/sections.h>
 #include <asm/page.h>
 
 #define ESSA_GET_STATE			0
@@ -21,7 +20,7 @@
 
 #define ESSA_MAX	ESSA_SET_STABLE_NODAT
 
-extern int __bootdata_preserved(cmma_flag);
+extern int cmma_flag;
 
 static __always_inline unsigned long essa(unsigned long paddr, unsigned char cmd)
 {
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 48268095b0a3..a3b51056a177 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -17,7 +17,6 @@
 #include <linux/page-flags.h>
 #include <linux/radix-tree.h>
 #include <linux/atomic.h>
-#include <asm/sections.h>
 #include <asm/ctlreg.h>
 #include <asm/bug.h>
 #include <asm/page.h>
@@ -35,7 +34,7 @@ enum {
 	PG_DIRECT_MAP_MAX
 };
 
-extern atomic_long_t __bootdata_preserved(direct_pages_count[PG_DIRECT_MAP_MAX]);
+extern atomic_long_t direct_pages_count[PG_DIRECT_MAP_MAX];
 
 static inline void update_page_count(int level, long count)
 {
@@ -85,14 +84,14 @@ extern unsigned long zero_page_mask;
  * happen without trampolines and in addition the placement within a
  * 2GB frame is branch prediction unit friendly.
  */
-extern unsigned long __bootdata_preserved(VMALLOC_START);
-extern unsigned long __bootdata_preserved(VMALLOC_END);
+extern unsigned long VMALLOC_START;
+extern unsigned long VMALLOC_END;
 #define VMALLOC_DEFAULT_SIZE	((512UL << 30) - MODULES_LEN)
-extern struct page *__bootdata_preserved(vmemmap);
-extern unsigned long __bootdata_preserved(vmemmap_size);
+extern struct page *vmemmap;
+extern unsigned long vmemmap_size;
 
-extern unsigned long __bootdata_preserved(MODULES_VADDR);
-extern unsigned long __bootdata_preserved(MODULES_END);
+extern unsigned long MODULES_VADDR;
+extern unsigned long MODULES_END;
 #define MODULES_VADDR	MODULES_VADDR
 #define MODULES_END	MODULES_END
 #define MODULES_LEN	(1UL << 31)
@@ -125,6 +124,8 @@ static inline int is_module_addr(void *addr)
 #define KASLR_LEN	0UL
 #endif
 
+void setup_protection_map(void);
+
 /*
  * A 64 bit pagetable entry of S390 has following format:
  * |			 PFRA			      |0IPC|  OS  |
@@ -443,98 +444,107 @@ static inline int is_module_addr(void *addr)
 /*
  * Page protection definitions.
  */
-#define PAGE_NONE	__pgprot(_PAGE_PRESENT | _PAGE_INVALID | _PAGE_PROTECT)
-#define PAGE_RO		__pgprot(_PAGE_PRESENT | _PAGE_READ | \
+#define __PAGE_NONE		(_PAGE_PRESENT | _PAGE_INVALID | _PAGE_PROTECT)
+#define __PAGE_RO		(_PAGE_PRESENT | _PAGE_READ | \
 				 _PAGE_NOEXEC  | _PAGE_INVALID | _PAGE_PROTECT)
-#define PAGE_RX		__pgprot(_PAGE_PRESENT | _PAGE_READ | \
+#define __PAGE_RX		(_PAGE_PRESENT | _PAGE_READ | \
 				 _PAGE_INVALID | _PAGE_PROTECT)
-#define PAGE_RW		__pgprot(_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE | \
+#define __PAGE_RW		(_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE | \
 				 _PAGE_NOEXEC  | _PAGE_INVALID | _PAGE_PROTECT)
-#define PAGE_RWX	__pgprot(_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE | \
+#define __PAGE_RWX		(_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE | \
 				 _PAGE_INVALID | _PAGE_PROTECT)
-
-#define PAGE_SHARED	__pgprot(_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE | \
+#define __PAGE_SHARED		(_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE | \
 				 _PAGE_YOUNG | _PAGE_DIRTY | _PAGE_NOEXEC)
-#define PAGE_KERNEL	__pgprot(_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE | \
+#define __PAGE_KERNEL		(_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE | \
 				 _PAGE_YOUNG | _PAGE_DIRTY | _PAGE_NOEXEC)
-#define PAGE_KERNEL_RO	__pgprot(_PAGE_PRESENT | _PAGE_READ | _PAGE_YOUNG | \
+#define __PAGE_KERNEL_RO	(_PAGE_PRESENT | _PAGE_READ | _PAGE_YOUNG | \
 				 _PAGE_PROTECT | _PAGE_NOEXEC)
-#define PAGE_KERNEL_EXEC __pgprot(_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE | \
-				  _PAGE_YOUNG |	_PAGE_DIRTY)
 
-/*
- * On s390 the page table entry has an invalid bit and a read-only bit.
- * Read permission implies execute permission and write permission
- * implies read permission.
- */
-         /*xwr*/
+extern unsigned long page_noexec_mask;
+
+#define __pgprot_page_mask(x)	__pgprot((x) & page_noexec_mask)
+
+#define PAGE_NONE		__pgprot_page_mask(__PAGE_NONE)
+#define PAGE_RO			__pgprot_page_mask(__PAGE_RO)
+#define PAGE_RX			__pgprot_page_mask(__PAGE_RX)
+#define PAGE_RW			__pgprot_page_mask(__PAGE_RW)
+#define PAGE_RWX		__pgprot_page_mask(__PAGE_RWX)
+#define PAGE_SHARED		__pgprot_page_mask(__PAGE_SHARED)
+#define PAGE_KERNEL		__pgprot_page_mask(__PAGE_KERNEL)
+#define PAGE_KERNEL_RO		__pgprot_page_mask(__PAGE_KERNEL_RO)
 
 /*
  * Segment entry (large page) protection definitions.
  */
-#define SEGMENT_NONE	__pgprot(_SEGMENT_ENTRY_PRESENT | \
+#define __SEGMENT_NONE		(_SEGMENT_ENTRY_PRESENT | \
 				 _SEGMENT_ENTRY_INVALID | \
 				 _SEGMENT_ENTRY_PROTECT)
-#define SEGMENT_RO	__pgprot(_SEGMENT_ENTRY_PRESENT | \
+#define __SEGMENT_RO		(_SEGMENT_ENTRY_PRESENT | \
 				 _SEGMENT_ENTRY_PROTECT | \
 				 _SEGMENT_ENTRY_READ | \
 				 _SEGMENT_ENTRY_NOEXEC)
-#define SEGMENT_RX	__pgprot(_SEGMENT_ENTRY_PRESENT | \
+#define __SEGMENT_RX		(_SEGMENT_ENTRY_PRESENT | \
 				 _SEGMENT_ENTRY_PROTECT | \
 				 _SEGMENT_ENTRY_READ)
-#define SEGMENT_RW	__pgprot(_SEGMENT_ENTRY_PRESENT | \
+#define __SEGMENT_RW		(_SEGMENT_ENTRY_PRESENT | \
 				 _SEGMENT_ENTRY_READ | \
 				 _SEGMENT_ENTRY_WRITE | \
 				 _SEGMENT_ENTRY_NOEXEC)
-#define SEGMENT_RWX	__pgprot(_SEGMENT_ENTRY_PRESENT | \
+#define __SEGMENT_RWX		(_SEGMENT_ENTRY_PRESENT | \
 				 _SEGMENT_ENTRY_READ | \
 				 _SEGMENT_ENTRY_WRITE)
-#define SEGMENT_KERNEL	__pgprot(_SEGMENT_ENTRY |	\
+#define __SEGMENT_KERNEL	(_SEGMENT_ENTRY |	\
 				 _SEGMENT_ENTRY_LARGE |	\
 				 _SEGMENT_ENTRY_READ |	\
 				 _SEGMENT_ENTRY_WRITE | \
 				 _SEGMENT_ENTRY_YOUNG | \
 				 _SEGMENT_ENTRY_DIRTY | \
 				 _SEGMENT_ENTRY_NOEXEC)
-#define SEGMENT_KERNEL_RO __pgprot(_SEGMENT_ENTRY |	\
+#define __SEGMENT_KERNEL_RO	(_SEGMENT_ENTRY |	\
 				 _SEGMENT_ENTRY_LARGE |	\
 				 _SEGMENT_ENTRY_READ |	\
 				 _SEGMENT_ENTRY_YOUNG |	\
 				 _SEGMENT_ENTRY_PROTECT | \
 				 _SEGMENT_ENTRY_NOEXEC)
-#define SEGMENT_KERNEL_EXEC __pgprot(_SEGMENT_ENTRY |	\
-				 _SEGMENT_ENTRY_LARGE |	\
-				 _SEGMENT_ENTRY_READ |	\
-				 _SEGMENT_ENTRY_WRITE | \
-				 _SEGMENT_ENTRY_YOUNG |	\
-				 _SEGMENT_ENTRY_DIRTY)
+
+extern unsigned long segment_noexec_mask;
+
+#define __pgprot_segment_mask(x) __pgprot((x) & segment_noexec_mask)
+
+#define SEGMENT_NONE		__pgprot_segment_mask(__SEGMENT_NONE)
+#define SEGMENT_RO		__pgprot_segment_mask(__SEGMENT_RO)
+#define SEGMENT_RX		__pgprot_segment_mask(__SEGMENT_RX)
+#define SEGMENT_RW		__pgprot_segment_mask(__SEGMENT_RW)
+#define SEGMENT_RWX		__pgprot_segment_mask(__SEGMENT_RWX)
+#define SEGMENT_KERNEL		__pgprot_segment_mask(__SEGMENT_KERNEL)
+#define SEGMENT_KERNEL_RO	__pgprot_segment_mask(__SEGMENT_KERNEL_RO)
 
 /*
  * Region3 entry (large page) protection definitions.
  */
 
-#define REGION3_KERNEL	__pgprot(_REGION_ENTRY_TYPE_R3 | \
+#define __REGION3_KERNEL	(_REGION_ENTRY_TYPE_R3 | \
 				 _REGION3_ENTRY_PRESENT | \
-				 _REGION3_ENTRY_LARGE |	 \
-				 _REGION3_ENTRY_READ |	 \
-				 _REGION3_ENTRY_WRITE |	 \
-				 _REGION3_ENTRY_YOUNG |	 \
+				 _REGION3_ENTRY_LARGE | \
+				 _REGION3_ENTRY_READ | \
+				 _REGION3_ENTRY_WRITE | \
+				 _REGION3_ENTRY_YOUNG | \
 				 _REGION3_ENTRY_DIRTY | \
 				 _REGION_ENTRY_NOEXEC)
-#define REGION3_KERNEL_RO __pgprot(_REGION_ENTRY_TYPE_R3 | \
-				   _REGION3_ENTRY_PRESENT | \
-				   _REGION3_ENTRY_LARGE |  \
-				   _REGION3_ENTRY_READ |   \
-				   _REGION3_ENTRY_YOUNG |  \
-				   _REGION_ENTRY_PROTECT | \
-				   _REGION_ENTRY_NOEXEC)
-#define REGION3_KERNEL_EXEC __pgprot(_REGION_ENTRY_TYPE_R3 | \
+#define __REGION3_KERNEL_RO	(_REGION_ENTRY_TYPE_R3 | \
 				 _REGION3_ENTRY_PRESENT | \
-				 _REGION3_ENTRY_LARGE |	 \
-				 _REGION3_ENTRY_READ |	 \
-				 _REGION3_ENTRY_WRITE |	 \
-				 _REGION3_ENTRY_YOUNG |	 \
-				 _REGION3_ENTRY_DIRTY)
+				 _REGION3_ENTRY_LARGE | \
+				 _REGION3_ENTRY_READ | \
+				 _REGION3_ENTRY_YOUNG | \
+				 _REGION_ENTRY_PROTECT | \
+				 _REGION_ENTRY_NOEXEC)
+
+extern unsigned long region_noexec_mask;
+
+#define __pgprot_region_mask(x)	__pgprot((x) & region_noexec_mask)
+
+#define REGION3_KERNEL		__pgprot_region_mask(__REGION3_KERNEL)
+#define REGION3_KERNEL_RO	__pgprot_region_mask(__REGION3_KERNEL_RO)
 
 static inline bool mm_p4d_folded(struct mm_struct *mm)
 {
@@ -1435,8 +1445,6 @@ static inline pte_t mk_pte_phys(unsigned long physpage, pgprot_t pgprot)
 	pte_t __pte;
 
 	__pte = __pte(physpage | pgprot_val(pgprot));
-	if (!MACHINE_HAS_NX)
-		__pte = clear_pte_bit(__pte, __pgprot(_PAGE_NOEXEC));
 	return pte_mkyoung(__pte);
 }
 
@@ -1804,8 +1812,6 @@ static inline int pmdp_clear_flush_young(struct vm_area_struct *vma,
 static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 			      pmd_t *pmdp, pmd_t entry)
 {
-	if (!MACHINE_HAS_NX)
-		entry = clear_pmd_bit(entry, __pgprot(_SEGMENT_ENTRY_NOEXEC));
 	set_pmd(pmdp, entry);
 }
 
diff --git a/arch/s390/include/asm/preempt.h b/arch/s390/include/asm/preempt.h
index 2c29bdf12127..6ccd033acfe5 100644
--- a/arch/s390/include/asm/preempt.h
+++ b/arch/s390/include/asm/preempt.h
@@ -8,12 +8,19 @@
 #include <asm/cmpxchg.h>
 #include <asm/march.h>
 
-#ifdef MARCH_HAS_Z196_FEATURES
-
 /* We use the MSB mostly because its available */
 #define PREEMPT_NEED_RESCHED	0x80000000
+
+/*
+ * We use the PREEMPT_NEED_RESCHED bit as an inverted NEED_RESCHED such
+ * that a decrement hitting 0 means we can and should reschedule.
+ */
 #define PREEMPT_ENABLED	(0 + PREEMPT_NEED_RESCHED)
 
+/*
+ * We mask the PREEMPT_NEED_RESCHED bit so as not to confuse all current users
+ * that think a non-zero value indicates we cannot preempt.
+ */
 static __always_inline int preempt_count(void)
 {
 	return READ_ONCE(get_lowcore()->preempt_count) & ~PREEMPT_NEED_RESCHED;
@@ -29,6 +36,15 @@ static __always_inline void preempt_count_set(int pc)
 	} while (!arch_try_cmpxchg(&get_lowcore()->preempt_count, &old, new));
 }
 
+/*
+ * We fold the NEED_RESCHED bit into the preempt count such that
+ * preempt_enable() can decrement and test for needing to reschedule with a
+ * short instruction sequence.
+ *
+ * We invert the actual bit, so that when the decrement hits 0 we know we both
+ * need to resched (the bit is cleared) and can resched (no preempt count).
+ */
+
 static __always_inline void set_preempt_need_resched(void)
 {
 	__atomic_and(~PREEMPT_NEED_RESCHED, &get_lowcore()->preempt_count);
@@ -64,67 +80,24 @@ static __always_inline void __preempt_count_sub(int val)
 	__preempt_count_add(-val);
 }
 
+/*
+ * Because we keep PREEMPT_NEED_RESCHED set when we do _not_ need to reschedule
+ * a decrement which hits zero means we have no preempt_count and should
+ * reschedule.
+ */
 static __always_inline bool __preempt_count_dec_and_test(void)
 {
-	return __atomic_add(-1, &get_lowcore()->preempt_count) == 1;
-}
-
-static __always_inline bool should_resched(int preempt_offset)
-{
-	return unlikely(READ_ONCE(get_lowcore()->preempt_count) ==
-			preempt_offset);
-}
-
-#else /* MARCH_HAS_Z196_FEATURES */
-
-#define PREEMPT_ENABLED	(0)
-
-static __always_inline int preempt_count(void)
-{
-	return READ_ONCE(get_lowcore()->preempt_count);
-}
-
-static __always_inline void preempt_count_set(int pc)
-{
-	get_lowcore()->preempt_count = pc;
-}
-
-static __always_inline void set_preempt_need_resched(void)
-{
-}
-
-static __always_inline void clear_preempt_need_resched(void)
-{
-}
-
-static __always_inline bool test_preempt_need_resched(void)
-{
-	return false;
-}
-
-static __always_inline void __preempt_count_add(int val)
-{
-	get_lowcore()->preempt_count += val;
-}
-
-static __always_inline void __preempt_count_sub(int val)
-{
-	get_lowcore()->preempt_count -= val;
-}
-
-static __always_inline bool __preempt_count_dec_and_test(void)
-{
-	return !--get_lowcore()->preempt_count && tif_need_resched();
+	return __atomic_add_const_and_test(-1, &get_lowcore()->preempt_count);
 }
 
+/*
+ * Returns true when we need to resched and can (barring IRQ state).
+ */
 static __always_inline bool should_resched(int preempt_offset)
 {
-	return unlikely(preempt_count() == preempt_offset &&
-			tif_need_resched());
+	return unlikely(READ_ONCE(get_lowcore()->preempt_count) == preempt_offset);
 }
 
-#endif /* MARCH_HAS_Z196_FEATURES */
-
 #define init_task_preempt_count(p)	do { } while (0)
 /* Deferred to CPU bringup time */
 #define init_idle_preempt_count(p, cpu)	do { } while (0)
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index 8761fd01a9f0..4f8d5592c298 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -163,8 +163,7 @@ static __always_inline void __stackleak_poison(unsigned long erase_low,
 		"	la	%[addr],256(%[addr])\n"
 		"	brctg	%[tmp],0b\n"
 		"1:	stg	%[poison],0(%[addr])\n"
-		"	larl	%[tmp],3f\n"
-		"	ex	%[count],0(%[tmp])\n"
+		"	exrl	%[count],3f\n"
 		"	j	4f\n"
 		"2:	stg	%[poison],0(%[addr])\n"
 		"	j	4f\n"
diff --git a/arch/s390/include/asm/sclp.h b/arch/s390/include/asm/sclp.h
index eb00fa1771da..4da3b2956285 100644
--- a/arch/s390/include/asm/sclp.h
+++ b/arch/s390/include/asm/sclp.h
@@ -16,6 +16,11 @@
 /* 24 + 16 * SCLP_MAX_CORES */
 #define EXT_SCCB_READ_CPU	(3 * PAGE_SIZE)
 
+#define SCLP_ERRNOTIFY_AQ_RESET			0
+#define SCLP_ERRNOTIFY_AQ_REPAIR		1
+#define SCLP_ERRNOTIFY_AQ_INFO_LOG		2
+#define SCLP_ERRNOTIFY_AQ_OPTICS_DATA		3
+
 #ifndef __ASSEMBLY__
 #include <linux/uio.h>
 #include <asm/chpid.h>
@@ -87,8 +92,10 @@ struct sclp_info {
 	unsigned char has_kss : 1;
 	unsigned char has_diag204_bif : 1;
 	unsigned char has_gisaf : 1;
+	unsigned char has_diag310 : 1;
 	unsigned char has_diag318 : 1;
 	unsigned char has_diag320 : 1;
+	unsigned char has_diag324 : 1;
 	unsigned char has_sipl : 1;
 	unsigned char has_sipl_eckd : 1;
 	unsigned char has_dirq : 1;
@@ -111,6 +118,34 @@ struct sclp_info {
 };
 extern struct sclp_info sclp;
 
+struct sccb_header {
+	u16	length;
+	u8	function_code;
+	u8	control_mask[3];
+	u16	response_code;
+} __packed;
+
+struct evbuf_header {
+	u16	length;
+	u8	type;
+	u8	flags;
+	u16	_reserved;
+} __packed;
+
+struct err_notify_evbuf {
+	struct evbuf_header header;
+	u8 action;
+	u8 atype;
+	u32 fh;
+	u32 fid;
+	u8 data[];
+} __packed;
+
+struct err_notify_sccb {
+	struct sccb_header header;
+	struct err_notify_evbuf evbuf;
+} __packed;
+
 struct zpci_report_error_header {
 	u8 version;	/* Interface version byte */
 	u8 action;	/* Action qualifier byte
diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h
index e95b2c8081eb..ea150ea83e57 100644
--- a/arch/s390/include/asm/tlb.h
+++ b/arch/s390/include/asm/tlb.h
@@ -140,11 +140,11 @@ static inline void pud_free_tlb(struct mmu_gather *tlb, pud_t *pud,
 {
 	if (mm_pud_folded(tlb->mm))
 		return;
+	__tlb_adjust_range(tlb, address, PAGE_SIZE);
 	tlb->mm->context.flush_mm = 1;
 	tlb->freed_tables = 1;
 	tlb->cleared_p4ds = 1;
 	tlb_remove_ptdesc(tlb, pud);
 }
 
-
 #endif /* _S390_TLB_H */
diff --git a/arch/s390/include/uapi/asm/diag.h b/arch/s390/include/uapi/asm/diag.h
new file mode 100644
index 000000000000..b7e6ccb4ff6e
--- /dev/null
+++ b/arch/s390/include/uapi/asm/diag.h
@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Diag ioctls and its associated structures definitions.
+ *
+ * Copyright IBM Corp. 2024
+ */
+
+#ifndef __S390_UAPI_ASM_DIAG_H
+#define __S390_UAPI_ASM_DIAG_H
+
+#include <linux/types.h>
+
+#define DIAG_MAGIC_STR 'D'
+
+struct diag324_pib {
+	__u64 address;
+	__u64 sequence;
+};
+
+struct diag310_memtop {
+	__u64 address;
+	__u64 nesting_lvl;
+};
+
+/* Diag ioctl definitions */
+#define DIAG324_GET_PIBBUF	_IOWR(DIAG_MAGIC_STR, 0x77, struct diag324_pib)
+#define DIAG324_GET_PIBLEN	_IOR(DIAG_MAGIC_STR, 0x78, size_t)
+#define DIAG310_GET_STRIDE	_IOR(DIAG_MAGIC_STR, 0x79, size_t)
+#define DIAG310_GET_MEMTOPLEN	_IOWR(DIAG_MAGIC_STR, 0x7a, size_t)
+#define DIAG310_GET_MEMTOPBUF	_IOWR(DIAG_MAGIC_STR, 0x7b, struct diag310_memtop)
+
+#endif /* __S390_UAPI_ASM_DIAG_H */