Merge tag 's390-6.4-1' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux

Pull s390 updates from Vasily Gorbik:

 - Add support for stackleak feature. Also allow specifying
   architecture-specific stackleak poison function to enable faster
   implementation. On s390, the mvc-based implementation helps decrease
   typical overhead from a factor of 3 to just 25%

 - Convert all assembler files to use SYM* style macros, deprecating the
   ENTRY() macro and other annotations. Select ARCH_USE_SYM_ANNOTATIONS

 - Improve KASLR to also randomize module and special amode31 code base
   load addresses

 - Rework decompressor memory tracking to support memory holes and
   improve error handling

 - Add support for protected virtualization AP binding

 - Add support for set_direct_map() calls

 - Implement set_memory_rox() and noexec module_alloc()

 - Remove obsolete overriding of mem*() functions for KASAN

 - Rework kexec/kdump to avoid using nodat_stack to call purgatory

 - Convert the rest of the s390 code to use flexible-array member
   instead of a zero-length array

 - Clean up uaccess inline asm

 - Enable ARCH_HAS_MEMBARRIER_SYNC_CORE

 - Convert to using CONFIG_FUNCTION_ALIGNMENT and enable
   DEBUG_FORCE_FUNCTION_ALIGN_64B

 - Resolve last_break in userspace fault reports

 - Simplify one-level sysctl registration

 - Clean up branch prediction handling

 - Rework CPU counter facility to retrieve available counter sets just
   once

 - Other various small fixes and improvements all over the code

* tag 's390-6.4-1' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux: (118 commits)
  s390/stackleak: provide fast __stackleak_poison() implementation
  stackleak: allow to specify arch specific stackleak poison function
  s390: select ARCH_USE_SYM_ANNOTATIONS
  s390/mm: use VM_FLUSH_RESET_PERMS in module_alloc()
  s390: wire up memfd_secret system call
  s390/mm: enable ARCH_HAS_SET_DIRECT_MAP
  s390/mm: use BIT macro to generate SET_MEMORY bit masks
  s390/relocate_kernel: adjust indentation
  s390/relocate_kernel: use SYM* macros instead of ENTRY(), etc.
  s390/entry: use SYM* macros instead of ENTRY(), etc.
  s390/purgatory: use SYM* macros instead of ENTRY(), etc.
  s390/kprobes: use SYM* macros instead of ENTRY(), etc.
  s390/reipl: use SYM* macros instead of ENTRY(), etc.
  s390/head64: use SYM* macros instead of ENTRY(), etc.
  s390/earlypgm: use SYM* macros instead of ENTRY(), etc.
  s390/mcount: use SYM* macros instead of ENTRY(), etc.
  s390/crc32le: use SYM* macros instead of ENTRY(), etc.
  s390/crc32be: use SYM* macros instead of ENTRY(), etc.
  s390/crypto,chacha: use SYM* macros instead of ENTRY(), etc.
  s390/amode31: use SYM* macros instead of ENTRY(), etc.
  ...

18 files changed, 441 insertions, 237 deletions

diff --git a/arch/s390/include/asm/ap.h b/arch/s390/include/asm/ap.h
index c699f251a464..d5d967166bac 100644
--- a/arch/s390/include/asm/ap.h
+++ b/arch/s390/include/asm/ap.h
@@ -43,10 +43,11 @@ struct ap_queue_status {
 	unsigned int queue_empty	: 1;
 	unsigned int replies_waiting	: 1;
 	unsigned int queue_full		: 1;
-	unsigned int _pad1		: 4;
+	unsigned int			: 3;
+	unsigned int async		: 1;
 	unsigned int irq_enabled	: 1;
 	unsigned int response_code	: 8;
-	unsigned int _pad2		: 16;
+	unsigned int			: 16;
 };
 
 /*
@@ -86,6 +87,42 @@ static inline bool ap_instructions_available(void)
 	return reg1 != 0;
 }
 
+/* TAPQ register GR2 response struct */
+struct ap_tapq_gr2 {
+	union {
+		unsigned long value;
+		struct {
+			unsigned int fac    : 32; /* facility bits */
+			unsigned int apinfo : 32; /* ap type, ... */
+		};
+		struct {
+			unsigned int s	   :  1; /* APSC */
+			unsigned int m	   :  1; /* AP4KM */
+			unsigned int c	   :  1; /* AP4KC */
+			unsigned int mode  :  3;
+			unsigned int n	   :  1; /* APXA */
+			unsigned int	   :  1;
+			unsigned int class :  8;
+			unsigned int bs	   :  2; /* SE bind/assoc */
+			unsigned int	   : 14;
+			unsigned int at	   :  8; /* ap type */
+			unsigned int nd	   :  8; /* nr of domains */
+			unsigned int	   :  4;
+			unsigned int ml	   :  4; /* apxl ml */
+			unsigned int	   :  4;
+			unsigned int qd	   :  4; /* queue depth */
+		};
+	};
+};
+
+/*
+ * Convenience defines to be used with the bs field from struct ap_tapq_gr2
+ */
+#define AP_BS_Q_USABLE		      0
+#define AP_BS_Q_USABLE_NO_SECURE_KEY  1
+#define AP_BS_Q_AVAIL_FOR_BINDING     2
+#define AP_BS_Q_UNUSABLE	      3
+
 /**
  * ap_tapq(): Test adjunct processor queue.
  * @qid: The AP queue number
@@ -93,7 +130,7 @@ static inline bool ap_instructions_available(void)
  *
  * Returns AP queue status structure.
  */
-static inline struct ap_queue_status ap_tapq(ap_qid_t qid, unsigned long *info)
+static inline struct ap_queue_status ap_tapq(ap_qid_t qid, struct ap_tapq_gr2 *info)
 {
 	union ap_queue_status_reg reg1;
 	unsigned long reg2;
@@ -108,7 +145,7 @@ static inline struct ap_queue_status ap_tapq(ap_qid_t qid, unsigned long *info)
 		: [qid] "d" (qid)
 		: "cc", "0", "1", "2");
 	if (info)
-		*info = reg2;
+		info->value = reg2;
 	return reg1.status;
 }
 
@@ -116,13 +153,12 @@ static inline struct ap_queue_status ap_tapq(ap_qid_t qid, unsigned long *info)
  * ap_test_queue(): Test adjunct processor queue.
  * @qid: The AP queue number
  * @tbit: Test facilities bit
- * @info: Pointer to queue descriptor
+ * @info: Ptr to tapq gr2 struct
  *
  * Returns AP queue status structure.
  */
-static inline struct ap_queue_status ap_test_queue(ap_qid_t qid,
-						   int tbit,
-						   unsigned long *info)
+static inline struct ap_queue_status ap_test_queue(ap_qid_t qid, int tbit,
+						   struct ap_tapq_gr2 *info)
 {
 	if (tbit)
 		qid |= 1UL << 23; /* set T bit*/
@@ -132,14 +168,18 @@ static inline struct ap_queue_status ap_test_queue(ap_qid_t qid,
 /**
  * ap_pqap_rapq(): Reset adjunct processor queue.
  * @qid: The AP queue number
+ * @fbit: if != 0 set F bit
  *
  * Returns AP queue status structure.
  */
-static inline struct ap_queue_status ap_rapq(ap_qid_t qid)
+static inline struct ap_queue_status ap_rapq(ap_qid_t qid, int fbit)
 {
 	unsigned long reg0 = qid | (1UL << 24);  /* fc 1UL is RAPQ */
 	union ap_queue_status_reg reg1;
 
+	if (fbit)
+		reg0 |= 1UL << 22;
+
 	asm volatile(
 		"	lgr	0,%[reg0]\n"		/* qid arg into gr0 */
 		"	.insn	rre,0xb2af0000,0,0\n"	/* PQAP(RAPQ) */
@@ -153,14 +193,18 @@ static inline struct ap_queue_status ap_rapq(ap_qid_t qid)
 /**
  * ap_pqap_zapq(): Reset and zeroize adjunct processor queue.
  * @qid: The AP queue number
+ * @fbit: if != 0 set F bit
  *
  * Returns AP queue status structure.
  */
-static inline struct ap_queue_status ap_zapq(ap_qid_t qid)
+static inline struct ap_queue_status ap_zapq(ap_qid_t qid, int fbit)
 {
 	unsigned long reg0 = qid | (2UL << 24);  /* fc 2UL is ZAPQ */
 	union ap_queue_status_reg reg1;
 
+	if (fbit)
+		reg0 |= 1UL << 22;
+
 	asm volatile(
 		"	lgr	0,%[reg0]\n"		/* qid arg into gr0 */
 		"	.insn	rre,0xb2af0000,0,0\n"	/* PQAP(ZAPQ) */
@@ -180,15 +224,16 @@ struct ap_config_info {
 	unsigned int apxa	 : 1;	/* N bit */
 	unsigned int qact	 : 1;	/* C bit */
 	unsigned int rc8a	 : 1;	/* R bit */
-	unsigned char _reserved1 : 4;
-	unsigned char _reserved2[3];
-	unsigned char Na;		/* max # of APs - 1 */
-	unsigned char Nd;		/* max # of Domains - 1 */
-	unsigned char _reserved3[10];
+	unsigned int		 : 4;
+	unsigned int apsb	 : 1;	/* B bit */
+	unsigned int		 : 23;
+	unsigned char na;		/* max # of APs - 1 */
+	unsigned char nd;		/* max # of Domains - 1 */
+	unsigned char _reserved0[10];
 	unsigned int apm[8];		/* AP ID mask */
 	unsigned int aqm[8];		/* AP (usage) queue mask */
 	unsigned int adm[8];		/* AP (control) domain mask */
-	unsigned char _reserved4[16];
+	unsigned char _reserved1[16];
 } __aligned(8);
 
 /**
@@ -318,6 +363,59 @@ static inline struct ap_queue_status ap_qact(ap_qid_t qid, int ifbit,
 	return reg1.status;
 }
 
+/*
+ * ap_bapq(): SE bind AP queue.
+ * @qid: The AP queue number
+ *
+ * Returns AP queue status structure.
+ *
+ * Invoking this function in a non-SE environment
+ * may case a specification exception.
+ */
+static inline struct ap_queue_status ap_bapq(ap_qid_t qid)
+{
+	unsigned long reg0 = qid | (7UL << 24);  /* fc 7 is BAPQ */
+	union ap_queue_status_reg reg1;
+
+	asm volatile(
+		"	lgr	0,%[reg0]\n"		/* qid arg into gr0 */
+		"	.insn	rre,0xb2af0000,0,0\n"	/* PQAP(BAPQ) */
+		"	lgr	%[reg1],1\n"		/* gr1 (status) into reg1 */
+		: [reg1] "=&d" (reg1.value)
+		: [reg0] "d" (reg0)
+		: "cc", "0", "1");
+
+	return reg1.status;
+}
+
+/*
+ * ap_aapq(): SE associate AP queue.
+ * @qid: The AP queue number
+ * @sec_idx: The secret index
+ *
+ * Returns AP queue status structure.
+ *
+ * Invoking this function in a non-SE environment
+ * may case a specification exception.
+ */
+static inline struct ap_queue_status ap_aapq(ap_qid_t qid, unsigned int sec_idx)
+{
+	unsigned long reg0 = qid | (8UL << 24);  /* fc 8 is AAPQ */
+	unsigned long reg2 = sec_idx;
+	union ap_queue_status_reg reg1;
+
+	asm volatile(
+		"	lgr	0,%[reg0]\n"		/* qid arg into gr0 */
+		"	lgr	2,%[reg2]\n"		/* secret index into gr2 */
+		"	.insn	rre,0xb2af0000,0,0\n"	/* PQAP(AAPQ) */
+		"	lgr	%[reg1],1\n"		/* gr1 (status) into reg1 */
+		: [reg1] "=&d" (reg1.value)
+		: [reg0] "d" (reg0), [reg2] "d" (reg2)
+		: "cc", "0", "1", "2");
+
+	return reg1.status;
+}
+
 /**
  * ap_nqap(): Send message to adjunct processor queue.
  * @qid: The AP queue number
@@ -359,10 +457,11 @@ static inline struct ap_queue_status ap_nqap(ap_qid_t qid,
  * ap_dqap(): Receive message from adjunct processor queue.
  * @qid: The AP queue number
  * @psmid: Pointer to program supplied message identifier
- * @msg: The message text
- * @length: The message length
- * @reslength: Resitual length on return
- * @resgr0: input: gr0 value (only used if != 0), output: resitual gr0 content
+ * @msg: Pointer to message buffer
+ * @msglen: Message buffer size
+ * @length: Pointer to length of actually written bytes
+ * @reslength: Residual length on return
+ * @resgr0: input: gr0 value (only used if != 0), output: residual gr0 content
  *
  * Returns AP queue status structure.
  * Condition code 1 on DQAP means the receive has taken place
@@ -386,8 +485,9 @@ static inline struct ap_queue_status ap_nqap(ap_qid_t qid,
  * *resgr0 is to be used instead of qid to further process this entry.
  */
 static inline struct ap_queue_status ap_dqap(ap_qid_t qid,
-					     unsigned long long *psmid,
-					     void *msg, size_t length,
+					     unsigned long *psmid,
+					     void *msg, size_t msglen,
+					     size_t *length,
 					     size_t *reslength,
 					     unsigned long *resgr0)
 {
@@ -399,7 +499,7 @@ static inline struct ap_queue_status ap_dqap(ap_qid_t qid,
 	rp1.even = 0UL;
 	rp1.odd  = 0UL;
 	rp2.even = (unsigned long)msg;
-	rp2.odd  = (unsigned long)length;
+	rp2.odd  = (unsigned long)msglen;
 
 	asm volatile(
 		"	lgr	0,%[reg0]\n"   /* qid param into gr0 */
@@ -429,11 +529,15 @@ static inline struct ap_queue_status ap_dqap(ap_qid_t qid,
 		if (resgr0)
 			*resgr0 = reg0;
 	} else {
-		*psmid = (((unsigned long long)rp1.even) << 32) + rp1.odd;
+		*psmid = (rp1.even << 32) + rp1.odd;
 		if (resgr0)
 			*resgr0 = 0;
 	}
 
+	/* update *length with the nr of bytes stored into the msg buffer */
+	if (length)
+		*length = msglen - rp2.odd;
+
 	return reg1.status;
 }
 
diff --git a/arch/s390/include/asm/checksum.h b/arch/s390/include/asm/checksum.h
index d977a3a2f619..69837eec2ff5 100644
--- a/arch/s390/include/asm/checksum.h
+++ b/arch/s390/include/asm/checksum.h
@@ -12,13 +12,7 @@
 #ifndef _S390_CHECKSUM_H
 #define _S390_CHECKSUM_H
 
-#ifdef CONFIG_GENERIC_CSUM
-
-#include <asm-generic/checksum.h>
-
-#else /* CONFIG_GENERIC_CSUM */
-
-#include <linux/uaccess.h>
+#include <linux/kasan-checks.h>
 #include <linux/in6.h>
 
 /*
@@ -40,6 +34,7 @@ static inline __wsum csum_partial(const void *buff, int len, __wsum sum)
 		.odd = (unsigned long) len,
 	};
 
+	kasan_check_read(buff, len);
 	asm volatile(
 		"0:	cksm	%[sum],%[rp]\n"
 		"	jo	0b\n"
@@ -135,5 +130,4 @@ static inline __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
 	return csum_fold((__force __wsum)(sum >> 32));
 }
 
-#endif /* CONFIG_GENERIC_CSUM */
 #endif /* _S390_CHECKSUM_H */
diff --git a/arch/s390/include/asm/diag.h b/arch/s390/include/asm/diag.h
index 674a939f16ee..902e0330dd91 100644
--- a/arch/s390/include/asm/diag.h
+++ b/arch/s390/include/asm/diag.h
@@ -90,7 +90,7 @@ struct diag8c {
 	u8 num_partitions;
 	u16 width;
 	u16 height;
-	u8 data[0];
+	u8 data[];
 } __packed __aligned(4);
 
 extern int diag8c(struct diag8c *out, struct ccw_dev_id *devno);
diff --git a/arch/s390/include/asm/entry-common.h b/arch/s390/include/asm/entry-common.h
index 000de2b1e67a..fdd319a622b0 100644
--- a/arch/s390/include/asm/entry-common.h
+++ b/arch/s390/include/asm/entry-common.h
@@ -60,9 +60,4 @@ static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs,
 
 #define arch_exit_to_user_mode_prepare arch_exit_to_user_mode_prepare
 
-static inline bool on_thread_stack(void)
-{
-	return !(((unsigned long)(current->stack) ^ current_stack_pointer) & ~(THREAD_SIZE - 1));
-}
-
 #endif
diff --git a/arch/s390/include/asm/fcx.h b/arch/s390/include/asm/fcx.h
index b8a028a36173..29784b4b44f6 100644
--- a/arch/s390/include/asm/fcx.h
+++ b/arch/s390/include/asm/fcx.h
@@ -286,7 +286,7 @@ struct tccb_tcat {
  */
 struct tccb {
 	struct tccb_tcah tcah;
-	u8 tca[0];
+	u8 tca[];
 } __attribute__ ((packed, aligned(8)));
 
 struct tcw *tcw_get_intrg(struct tcw *tcw);
diff --git a/arch/s390/include/asm/kasan.h b/arch/s390/include/asm/kasan.h
index e5cfc81d5b61..0cffead0f2f2 100644
--- a/arch/s390/include/asm/kasan.h
+++ b/arch/s390/include/asm/kasan.h
@@ -2,7 +2,7 @@
 #ifndef __ASM_KASAN_H
 #define __ASM_KASAN_H
 
-#include <asm/pgtable.h>
+#include <linux/const.h>
 
 #ifdef CONFIG_KASAN
 
@@ -13,35 +13,6 @@
 #define KASAN_SHADOW_START	KASAN_SHADOW_OFFSET
 #define KASAN_SHADOW_END	(KASAN_SHADOW_START + KASAN_SHADOW_SIZE)
 
-extern void kasan_early_init(void);
-
-/*
- * Estimate kasan memory requirements, which it will reserve
- * at the very end of available physical memory. To estimate
- * that, we take into account that kasan would require
- * 1/8 of available physical memory (for shadow memory) +
- * creating page tables for the shadow memory region.
- * To keep page tables estimates simple take the double of
- * combined ptes size.
- *
- * physmem parameter has to be already adjusted if not entire physical memory
- * would be used (e.g. due to effect of "mem=" option).
- */
-static inline unsigned long kasan_estimate_memory_needs(unsigned long physmem)
-{
-	unsigned long kasan_needs;
-	unsigned long pages;
-	/* for shadow memory */
-	kasan_needs = round_up(physmem / 8, PAGE_SIZE);
-	/* for paging structures */
-	pages = DIV_ROUND_UP(kasan_needs, PAGE_SIZE);
-	kasan_needs += DIV_ROUND_UP(pages, _PAGE_ENTRIES) * _PAGE_TABLE_SIZE * 2;
-
-	return kasan_needs;
-}
-#else
-static inline void kasan_early_init(void) { }
-static inline unsigned long kasan_estimate_memory_needs(unsigned long physmem) { return 0; }
 #endif
 
 #endif
diff --git a/arch/s390/include/asm/linkage.h b/arch/s390/include/asm/linkage.h
index c76777b15fec..df3fb7d8227b 100644
--- a/arch/s390/include/asm/linkage.h
+++ b/arch/s390/include/asm/linkage.h
@@ -4,7 +4,7 @@
 
 #include <linux/stringify.h>
 
-#define __ALIGN .align 16, 0x07
+#define __ALIGN .balign CONFIG_FUNCTION_ALIGNMENT, 0x07
 #define __ALIGN_STR __stringify(__ALIGN)
 
 #endif
diff --git a/arch/s390/include/asm/mem_detect.h b/arch/s390/include/asm/mem_detect.h
deleted file mode 100644
index f9e7354036d2..000000000000
--- a/arch/s390/include/asm/mem_detect.h
+++ /dev/null
@@ -1,117 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_S390_MEM_DETECT_H
-#define _ASM_S390_MEM_DETECT_H
-
-#include <linux/types.h>
-
-enum mem_info_source {
-	MEM_DETECT_NONE = 0,
-	MEM_DETECT_SCLP_STOR_INFO,
-	MEM_DETECT_DIAG260,
-	MEM_DETECT_SCLP_READ_INFO,
-	MEM_DETECT_BIN_SEARCH
-};
-
-struct mem_detect_block {
-	u64 start;
-	u64 end;
-};
-
-/*
- * Storage element id is defined as 1 byte (up to 256 storage elements).
- * In practise only storage element id 0 and 1 are used).
- * According to architecture one storage element could have as much as
- * 1020 subincrements. 255 mem_detect_blocks are embedded in mem_detect_info.
- * If more mem_detect_blocks are required, a block of memory from already
- * known mem_detect_block is taken (entries_extended points to it).
- */
-#define MEM_INLINED_ENTRIES 255 /* (PAGE_SIZE - 16) / 16 */
-
-struct mem_detect_info {
-	u32 count;
-	u8 info_source;
-	unsigned long usable;
-	struct mem_detect_block entries[MEM_INLINED_ENTRIES];
-	struct mem_detect_block *entries_extended;
-};
-extern struct mem_detect_info mem_detect;
-
-void add_mem_detect_block(u64 start, u64 end);
-
-static inline int __get_mem_detect_block(u32 n, unsigned long *start,
-					 unsigned long *end, bool respect_usable_limit)
-{
-	if (n >= mem_detect.count) {
-		*start = 0;
-		*end = 0;
-		return -1;
-	}
-
-	if (n < MEM_INLINED_ENTRIES) {
-		*start = (unsigned long)mem_detect.entries[n].start;
-		*end = (unsigned long)mem_detect.entries[n].end;
-	} else {
-		*start = (unsigned long)mem_detect.entries_extended[n - MEM_INLINED_ENTRIES].start;
-		*end = (unsigned long)mem_detect.entries_extended[n - MEM_INLINED_ENTRIES].end;
-	}
-
-	if (respect_usable_limit && mem_detect.usable) {
-		if (*start >= mem_detect.usable)
-			return -1;
-		if (*end > mem_detect.usable)
-			*end = mem_detect.usable;
-	}
-	return 0;
-}
-
-/**
- * for_each_mem_detect_usable_block - early online memory range iterator
- * @i: an integer used as loop variable
- * @p_start: ptr to unsigned long for start address of the range
- * @p_end: ptr to unsigned long for end address of the range
- *
- * Walks over detected online memory ranges below usable limit.
- */
-#define for_each_mem_detect_usable_block(i, p_start, p_end)		\
-	for (i = 0; !__get_mem_detect_block(i, p_start, p_end, true); i++)
-
-/* Walks over all detected online memory ranges disregarding usable limit. */
-#define for_each_mem_detect_block(i, p_start, p_end)		\
-	for (i = 0; !__get_mem_detect_block(i, p_start, p_end, false); i++)
-
-static inline unsigned long get_mem_detect_usable_total(void)
-{
-	unsigned long start, end, total = 0;
-	int i;
-
-	for_each_mem_detect_usable_block(i, &start, &end)
-		total += end - start;
-
-	return total;
-}
-
-static inline void get_mem_detect_reserved(unsigned long *start,
-					   unsigned long *size)
-{
-	*start = (unsigned long)mem_detect.entries_extended;
-	if (mem_detect.count > MEM_INLINED_ENTRIES)
-		*size = (mem_detect.count - MEM_INLINED_ENTRIES) * sizeof(struct mem_detect_block);
-	else
-		*size = 0;
-}
-
-static inline unsigned long get_mem_detect_end(void)
-{
-	unsigned long start;
-	unsigned long end;
-
-	if (mem_detect.usable)
-		return mem_detect.usable;
-	if (mem_detect.count) {
-		__get_mem_detect_block(mem_detect.count - 1, &start, &end, false);
-		return end;
-	}
-	return 0;
-}
-
-#endif
diff --git a/arch/s390/include/asm/nospec-insn.h b/arch/s390/include/asm/nospec-insn.h
index 7e9e99523e95..7a946c42ad13 100644
--- a/arch/s390/include/asm/nospec-insn.h
+++ b/arch/s390/include/asm/nospec-insn.h
@@ -2,6 +2,7 @@
 #ifndef _ASM_S390_NOSPEC_ASM_H
 #define _ASM_S390_NOSPEC_ASM_H
 
+#include <linux/linkage.h>
 #include <asm/dwarf.h>
 
 #ifdef __ASSEMBLY__
@@ -16,7 +17,7 @@
 	.macro __THUNK_PROLOG_NAME name
 #ifdef CONFIG_EXPOLINE_EXTERN
 	.pushsection .text,"ax",@progbits
-	.align 16,0x07
+	__ALIGN
 #else
 	.pushsection .text.\name,"axG",@progbits,\name,comdat
 #endif
diff --git a/arch/s390/include/asm/perf_event.h b/arch/s390/include/asm/perf_event.h
index b9da71632827..9917e2717b2b 100644
--- a/arch/s390/include/asm/perf_event.h
+++ b/arch/s390/include/asm/perf_event.h
@@ -60,7 +60,6 @@ struct perf_sf_sde_regs {
 #define PERF_CPUM_SF_DIAG_MODE		0x0002	  /* Diagnostic-sampling flag */
 #define PERF_CPUM_SF_MODE_MASK		(PERF_CPUM_SF_BASIC_MODE| \
 					 PERF_CPUM_SF_DIAG_MODE)
-#define PERF_CPUM_SF_FULL_BLOCKS	0x0004	  /* Process full SDBs only */
 #define PERF_CPUM_SF_FREQ_MODE		0x0008	  /* Sampling with frequency */
 
 #define REG_NONE		0
@@ -71,7 +70,6 @@ struct perf_sf_sde_regs {
 #define SAMPL_RATE(hwc)		((hwc)->event_base)
 #define SAMPL_FLAGS(hwc)	((hwc)->config_base)
 #define SAMPL_DIAG_MODE(hwc)	(SAMPL_FLAGS(hwc) & PERF_CPUM_SF_DIAG_MODE)
-#define SDB_FULL_BLOCKS(hwc)	(SAMPL_FLAGS(hwc) & PERF_CPUM_SF_FULL_BLOCKS)
 #define SAMPLE_FREQ_MODE(hwc)	(SAMPL_FLAGS(hwc) & PERF_CPUM_SF_FREQ_MODE)
 
 #define perf_arch_fetch_caller_regs(regs, __ip) do {			\
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index c1f6b46ec555..6822a11c2c8a 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -34,7 +34,7 @@ enum {
 	PG_DIRECT_MAP_MAX
 };
 
-extern atomic_long_t direct_pages_count[PG_DIRECT_MAP_MAX];
+extern atomic_long_t __bootdata_preserved(direct_pages_count[PG_DIRECT_MAP_MAX]);
 
 static inline void update_page_count(int level, long count)
 {
diff --git a/arch/s390/include/asm/physmem_info.h b/arch/s390/include/asm/physmem_info.h
new file mode 100644
index 000000000000..8e9c582592b3
--- /dev/null
+++ b/arch/s390/include/asm/physmem_info.h
@@ -0,0 +1,171 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_S390_MEM_DETECT_H
+#define _ASM_S390_MEM_DETECT_H
+
+#include <linux/types.h>
+
+enum physmem_info_source {
+	MEM_DETECT_NONE = 0,
+	MEM_DETECT_SCLP_STOR_INFO,
+	MEM_DETECT_DIAG260,
+	MEM_DETECT_SCLP_READ_INFO,
+	MEM_DETECT_BIN_SEARCH
+};
+
+struct physmem_range {
+	u64 start;
+	u64 end;
+};
+
+enum reserved_range_type {
+	RR_DECOMPRESSOR,
+	RR_INITRD,
+	RR_VMLINUX,
+	RR_AMODE31,
+	RR_IPLREPORT,
+	RR_CERT_COMP_LIST,
+	RR_MEM_DETECT_EXTENDED,
+	RR_VMEM,
+	RR_MAX
+};
+
+struct reserved_range {
+	unsigned long start;
+	unsigned long end;
+	struct reserved_range *chain;
+};
+
+/*
+ * Storage element id is defined as 1 byte (up to 256 storage elements).
+ * In practise only storage element id 0 and 1 are used).
+ * According to architecture one storage element could have as much as
+ * 1020 subincrements. 255 physmem_ranges are embedded in physmem_info.
+ * If more physmem_ranges are required, a block of memory from already
+ * known physmem_range is taken (online_extended points to it).
+ */
+#define MEM_INLINED_ENTRIES 255 /* (PAGE_SIZE - 16) / 16 */
+
+struct physmem_info {
+	u32 range_count;
+	u8 info_source;
+	unsigned long usable;
+	struct reserved_range reserved[RR_MAX];
+	struct physmem_range online[MEM_INLINED_ENTRIES];
+	struct physmem_range *online_extended;
+};
+
+extern struct physmem_info physmem_info;
+
+void add_physmem_online_range(u64 start, u64 end);
+
+static inline int __get_physmem_range(u32 n, unsigned long *start,
+				      unsigned long *end, bool respect_usable_limit)
+{
+	if (n >= physmem_info.range_count) {
+		*start = 0;
+		*end = 0;
+		return -1;
+	}
+
+	if (n < MEM_INLINED_ENTRIES) {
+		*start = (unsigned long)physmem_info.online[n].start;
+		*end = (unsigned long)physmem_info.online[n].end;
+	} else {
+		*start = (unsigned long)physmem_info.online_extended[n - MEM_INLINED_ENTRIES].start;
+		*end = (unsigned long)physmem_info.online_extended[n - MEM_INLINED_ENTRIES].end;
+	}
+
+	if (respect_usable_limit && physmem_info.usable) {
+		if (*start >= physmem_info.usable)
+			return -1;
+		if (*end > physmem_info.usable)
+			*end = physmem_info.usable;
+	}
+	return 0;
+}
+
+/**
+ * for_each_physmem_usable_range - early online memory range iterator
+ * @i: an integer used as loop variable
+ * @p_start: ptr to unsigned long for start address of the range
+ * @p_end: ptr to unsigned long for end address of the range
+ *
+ * Walks over detected online memory ranges below usable limit.
+ */
+#define for_each_physmem_usable_range(i, p_start, p_end)		\
+	for (i = 0; !__get_physmem_range(i, p_start, p_end, true); i++)
+
+/* Walks over all detected online memory ranges disregarding usable limit. */
+#define for_each_physmem_online_range(i, p_start, p_end)		\
+	for (i = 0; !__get_physmem_range(i, p_start, p_end, false); i++)
+
+static inline const char *get_physmem_info_source(void)
+{
+	switch (physmem_info.info_source) {
+	case MEM_DETECT_SCLP_STOR_INFO:
+		return "sclp storage info";
+	case MEM_DETECT_DIAG260:
+		return "diag260";
+	case MEM_DETECT_SCLP_READ_INFO:
+		return "sclp read info";
+	case MEM_DETECT_BIN_SEARCH:
+		return "binary search";
+	}
+	return "none";
+}
+
+#define RR_TYPE_NAME(t) case RR_ ## t: return #t
+static inline const char *get_rr_type_name(enum reserved_range_type t)
+{
+	switch (t) {
+	RR_TYPE_NAME(DECOMPRESSOR);
+	RR_TYPE_NAME(INITRD);
+	RR_TYPE_NAME(VMLINUX);
+	RR_TYPE_NAME(AMODE31);
+	RR_TYPE_NAME(IPLREPORT);
+	RR_TYPE_NAME(CERT_COMP_LIST);
+	RR_TYPE_NAME(MEM_DETECT_EXTENDED);
+	RR_TYPE_NAME(VMEM);
+	default:
+		return "UNKNOWN";
+	}
+}
+
+#define for_each_physmem_reserved_type_range(t, range, p_start, p_end)				\
+	for (range = &physmem_info.reserved[t], *p_start = range->start, *p_end = range->end;	\
+	     range && range->end; range = range->chain,						\
+	     *p_start = range ? range->start : 0, *p_end = range ? range->end : 0)
+
+static inline struct reserved_range *__physmem_reserved_next(enum reserved_range_type *t,
+							     struct reserved_range *range)
+{
+	if (!range) {
+		range = &physmem_info.reserved[*t];
+		if (range->end)
+			return range;
+	}
+	if (range->chain)
+		return range->chain;
+	while (++*t < RR_MAX) {
+		range = &physmem_info.reserved[*t];
+		if (range->end)
+			return range;
+	}
+	return NULL;
+}
+
+#define for_each_physmem_reserved_range(t, range, p_start, p_end)			\
+	for (t = 0, range = __physmem_reserved_next(&t, NULL),			\
+	    *p_start = range ? range->start : 0, *p_end = range ? range->end : 0;	\
+	     range; range = __physmem_reserved_next(&t, range),			\
+	    *p_start = range ? range->start : 0, *p_end = range ? range->end : 0)
+
+static inline unsigned long get_physmem_reserved(enum reserved_range_type type,
+						 unsigned long *addr, unsigned long *size)
+{
+	*addr = physmem_info.reserved[type].start;
+	*size = physmem_info.reserved[type].end - physmem_info.reserved[type].start;
+	return *size;
+}
+
+#endif
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index e98d9650764b..dc17896a001a 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -99,7 +99,6 @@ void cpu_detect_mhz_feature(void);
 
 extern const struct seq_operations cpuinfo_op;
 extern void execve_tail(void);
-extern void __bpon(void);
 unsigned long vdso_size(void);
 
 /*
@@ -119,6 +118,41 @@ unsigned long vdso_size(void);
 
 #define HAVE_ARCH_PICK_MMAP_LAYOUT
 
+#define __stackleak_poison __stackleak_poison
+static __always_inline void __stackleak_poison(unsigned long erase_low,
+					       unsigned long erase_high,
+					       unsigned long poison)
+{
+	unsigned long tmp, count;
+
+	count = erase_high - erase_low;
+	if (!count)
+		return;
+	asm volatile(
+		"	cghi	%[count],8\n"
+		"	je	2f\n"
+		"	aghi	%[count],-(8+1)\n"
+		"	srlg	%[tmp],%[count],8\n"
+		"	ltgr	%[tmp],%[tmp]\n"
+		"	jz	1f\n"
+		"0:	stg	%[poison],0(%[addr])\n"
+		"	mvc	8(256-8,%[addr]),0(%[addr])\n"
+		"	la	%[addr],256(%[addr])\n"
+		"	brctg	%[tmp],0b\n"
+		"1:	stg	%[poison],0(%[addr])\n"
+		"	larl	%[tmp],3f\n"
+		"	ex	%[count],0(%[tmp])\n"
+		"	j	4f\n"
+		"2:	stg	%[poison],0(%[addr])\n"
+		"	j	4f\n"
+		"3:	mvc	8(1,%[addr]),0(%[addr])\n"
+		"4:\n"
+		: [addr] "+&a" (erase_low), [count] "+&d" (count), [tmp] "=&a" (tmp)
+		: [poison] "d" (poison)
+		: "memory", "cc"
+		);
+}
+
 /*
  * Thread structure
  */
@@ -227,6 +261,13 @@ static __always_inline unsigned long __current_stack_pointer(void)
 	return sp;
 }
 
+static __always_inline bool on_thread_stack(void)
+{
+	unsigned long ksp = S390_lowcore.kernel_stack;
+
+	return !((ksp ^ current_stack_pointer) & ~(THREAD_SIZE - 1));
+}
+
 static __always_inline unsigned short stap(void)
 {
 	unsigned short cpu_address;
@@ -329,9 +370,6 @@ static __always_inline void __noreturn disabled_wait(void)
 
 #define ARCH_LOW_ADDRESS_LIMIT	0x7fffffffUL
 
-extern int s390_isolate_bp(void);
-extern int s390_isolate_bp_guest(void);
-
 static __always_inline bool regs_irqs_disabled(struct pt_regs *regs)
 {
 	return arch_irqs_disabled_flags(regs->psw.mask);
diff --git a/arch/s390/include/asm/set_memory.h b/arch/s390/include/asm/set_memory.h
index 950d87bd997a..7a3eefd7a242 100644
--- a/arch/s390/include/asm/set_memory.h
+++ b/arch/s390/include/asm/set_memory.h
@@ -6,11 +6,23 @@
 
 extern struct mutex cpa_mutex;
 
-#define SET_MEMORY_RO	1UL
-#define SET_MEMORY_RW	2UL
-#define SET_MEMORY_NX	4UL
-#define SET_MEMORY_X	8UL
-#define SET_MEMORY_4K  16UL
+enum {
+	_SET_MEMORY_RO_BIT,
+	_SET_MEMORY_RW_BIT,
+	_SET_MEMORY_NX_BIT,
+	_SET_MEMORY_X_BIT,
+	_SET_MEMORY_4K_BIT,
+	_SET_MEMORY_INV_BIT,
+	_SET_MEMORY_DEF_BIT,
+};
+
+#define SET_MEMORY_RO	BIT(_SET_MEMORY_RO_BIT)
+#define SET_MEMORY_RW	BIT(_SET_MEMORY_RW_BIT)
+#define SET_MEMORY_NX	BIT(_SET_MEMORY_NX_BIT)
+#define SET_MEMORY_X	BIT(_SET_MEMORY_X_BIT)
+#define SET_MEMORY_4K	BIT(_SET_MEMORY_4K_BIT)
+#define SET_MEMORY_INV	BIT(_SET_MEMORY_INV_BIT)
+#define SET_MEMORY_DEF	BIT(_SET_MEMORY_DEF_BIT)
 
 int __set_memory(unsigned long addr, int numpages, unsigned long flags);
 
@@ -34,9 +46,23 @@ static inline int set_memory_x(unsigned long addr, int numpages)
 	return __set_memory(addr, numpages, SET_MEMORY_X);
 }
 
+#define set_memory_rox set_memory_rox
+static inline int set_memory_rox(unsigned long addr, int numpages)
+{
+	return __set_memory(addr, numpages, SET_MEMORY_RO | SET_MEMORY_X);
+}
+
+static inline int set_memory_rwnx(unsigned long addr, int numpages)
+{
+	return __set_memory(addr, numpages, SET_MEMORY_RW | SET_MEMORY_NX);
+}
+
 static inline int set_memory_4k(unsigned long addr, int numpages)
 {
 	return __set_memory(addr, numpages, SET_MEMORY_4K);
 }
 
+int set_direct_map_invalid_noflush(struct page *page);
+int set_direct_map_default_noflush(struct page *page);
+
 #endif
diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h
index 3a1f8825bc7d..f191255c60db 100644
--- a/arch/s390/include/asm/setup.h
+++ b/arch/s390/include/asm/setup.h
@@ -74,10 +74,6 @@ extern unsigned int zlib_dfltcc_support;
 
 extern int noexec_disabled;
 extern unsigned long ident_map_size;
-extern unsigned long pgalloc_pos;
-extern unsigned long pgalloc_end;
-extern unsigned long pgalloc_low;
-extern unsigned long __amode31_base;
 
 /* The Write Back bit position in the physaddr is given by the SLPC PCI */
 extern unsigned long mio_wb_bit_mask;
@@ -150,13 +146,13 @@ static inline unsigned long kaslr_offset(void)
 	return __kaslr_offset;
 }
 
-extern int is_full_image;
-
-struct initrd_data {
-	unsigned long start;
-	unsigned long size;
-};
-extern struct initrd_data initrd_data;
+extern int __kaslr_enabled;
+static inline int kaslr_enabled(void)
+{
+	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE))
+		return __kaslr_enabled;
+	return 0;
+}
 
 struct oldmem_data {
 	unsigned long start;
@@ -164,7 +160,7 @@ struct oldmem_data {
 };
 extern struct oldmem_data oldmem_data;
 
-static inline u32 gen_lpswe(unsigned long addr)
+static __always_inline u32 gen_lpswe(unsigned long addr)
 {
 	BUILD_BUG_ON(addr > 0xfff);
 	return 0xb2b20000 | addr;
diff --git a/arch/s390/include/asm/stacktrace.h b/arch/s390/include/asm/stacktrace.h
index 1802be5abb5d..78f7b729b65f 100644
--- a/arch/s390/include/asm/stacktrace.h
+++ b/arch/s390/include/asm/stacktrace.h
@@ -189,17 +189,53 @@ static __always_inline unsigned long get_stack_pointer(struct task_struct *task,
 	(rettype)r2;							\
 })
 
-#define call_on_stack_noreturn(fn, stack)				\
+/*
+ * Use call_nodat() to call a function with DAT disabled.
+ * Proper sign and zero extension of function arguments is done.
+ * Usage:
+ *
+ * rc = call_nodat(nr, rettype, fn, t1, a1, t2, a2, ...)
+ *
+ * - nr specifies the number of function arguments of fn.
+ * - fn is the function to be called, where fn is a physical address.
+ * - rettype is the return type of fn.
+ * - t1, a1, ... are pairs, where t1 must match the type of the first
+ *   argument of fn, t2 the second, etc. a1 is the corresponding
+ *   first function argument (not name), etc.
+ *
+ * fn() is called with standard C function call ABI, with the exception
+ * that no useful stackframe or stackpointer is passed via register 15.
+ * Therefore the called function must not use r15 to access the stack.
+ */
+#define call_nodat(nr, rettype, fn, ...)				\
 ({									\
-	void (*__fn)(void) = fn;					\
+	rettype (*__fn)(CALL_PARM_##nr(__VA_ARGS__)) = (fn);		\
+	/* aligned since psw_leave must not cross page boundary */	\
+	psw_t __aligned(16) psw_leave;					\
+	psw_t psw_enter;						\
+	CALL_LARGS_##nr(__VA_ARGS__);					\
+	CALL_REGS_##nr;							\
 									\
+	CALL_TYPECHECK_##nr(__VA_ARGS__);				\
+	psw_enter.mask = PSW_KERNEL_BITS & ~PSW_MASK_DAT;		\
+	psw_enter.addr = (unsigned long)__fn;				\
 	asm volatile(							\
-		"	la	15,0(%[_stack])\n"			\
-		"	xc	%[_bc](8,15),%[_bc](15)\n"		\
-		"	brasl	14,%[_fn]\n"				\
-		::[_bc] "i" (offsetof(struct stack_frame, back_chain)),	\
-		  [_stack] "a" (stack), [_fn] "X" (__fn));		\
-	BUG();								\
+		"	epsw	0,1\n"					\
+		"	risbg	1,0,0,31,32\n"				\
+		"	larl	7,1f\n"					\
+		"	stg	1,%[psw_leave]\n"			\
+		"	stg	7,8+%[psw_leave]\n"			\
+		"	la	7,%[psw_leave]\n"			\
+		"	lra	7,0(7)\n"				\
+		"	larl	1,0f\n"					\
+		"	lra	14,0(1)\n"				\
+		"	lpswe	%[psw_enter]\n"				\
+		"0:	lpswe	0(7)\n"					\
+		"1:\n"							\
+		: CALL_FMT_##nr, [psw_leave] "=Q" (psw_leave)		\
+		: [psw_enter] "Q" (psw_enter)				\
+		: "7", CALL_CLOBBER_##nr);				\
+	(rettype)r2;							\
 })
 
 #endif /* _ASM_S390_STACKTRACE_H */
diff --git a/arch/s390/include/asm/string.h b/arch/s390/include/asm/string.h
index 3fae93ddb322..351685de53d2 100644
--- a/arch/s390/include/asm/string.h
+++ b/arch/s390/include/asm/string.h
@@ -55,18 +55,6 @@ char *strstr(const char *s1, const char *s2);
 
 #if defined(CONFIG_KASAN) && !defined(__SANITIZE_ADDRESS__)
 
-extern void *__memcpy(void *dest, const void *src, size_t n);
-extern void *__memset(void *s, int c, size_t n);
-extern void *__memmove(void *dest, const void *src, size_t n);
-
-/*
- * For files that are not instrumented (e.g. mm/slub.c) we
- * should use not instrumented version of mem* functions.
- */
-
-#define memcpy(dst, src, len) __memcpy(dst, src, len)
-#define memmove(dst, src, len) __memmove(dst, src, len)
-#define memset(s, c, n) __memset(s, c, n)
 #define strlen(s) __strlen(s)
 
 #define __no_sanitize_prefix_strfunc(x) __##x
@@ -79,6 +67,9 @@ extern void *__memmove(void *dest, const void *src, size_t n);
 #define __no_sanitize_prefix_strfunc(x) x
 #endif /* defined(CONFIG_KASAN) && !defined(__SANITIZE_ADDRESS__) */
 
+void *__memcpy(void *dest, const void *src, size_t n);
+void *__memset(void *s, int c, size_t n);
+void *__memmove(void *dest, const void *src, size_t n);
 void *__memset16(uint16_t *s, uint16_t v, size_t count);
 void *__memset32(uint32_t *s, uint32_t v, size_t count);
 void *__memset64(uint64_t *s, uint64_t v, size_t count);
diff --git a/arch/s390/include/asm/thread_info.h b/arch/s390/include/asm/thread_info.h
index b2ffcb4fe000..c7c97921ed8d 100644
--- a/arch/s390/include/asm/thread_info.h
+++ b/arch/s390/include/asm/thread_info.h
@@ -9,6 +9,9 @@
 #define _ASM_THREAD_INFO_H
 
 #include <linux/bits.h>
+#ifndef ASM_OFFSETS_C
+#include <asm/asm-offsets.h>
+#endif
 
 /*
  * General size of kernel stacks
@@ -21,13 +24,12 @@
 #define BOOT_STACK_SIZE (PAGE_SIZE << 2)
 #define THREAD_SIZE (PAGE_SIZE << THREAD_SIZE_ORDER)
 
+#define STACK_INIT_OFFSET (THREAD_SIZE - STACK_FRAME_OVERHEAD - __PT_SIZE)
+
 #ifndef __ASSEMBLY__
 #include <asm/lowcore.h>
 #include <asm/page.h>
 
-#define STACK_INIT_OFFSET \
-	(THREAD_SIZE - STACK_FRAME_OVERHEAD - sizeof(struct pt_regs))
-
 /*
  * low level task data that entry.S needs immediate access to
  * - this struct should fit entirely inside of one cache line
@@ -70,7 +72,6 @@ void arch_setup_new_exec(void);
 #define TIF_PATCH_PENDING	5	/* pending live patching update */
 #define TIF_PGSTE		6	/* New mm's will use 4K page tables */
 #define TIF_NOTIFY_SIGNAL	7	/* signal notifications exist */
-#define TIF_ISOLATE_BP		8	/* Run process with isolated BP */
 #define TIF_ISOLATE_BP_GUEST	9	/* Run KVM guests with isolated BP */
 #define TIF_PER_TRAP		10	/* Need to handle PER trap on exit to usermode */
 
@@ -94,7 +95,6 @@ void arch_setup_new_exec(void);
 #define _TIF_UPROBE		BIT(TIF_UPROBE)
 #define _TIF_GUARDED_STORAGE	BIT(TIF_GUARDED_STORAGE)
 #define _TIF_PATCH_PENDING	BIT(TIF_PATCH_PENDING)
-#define _TIF_ISOLATE_BP		BIT(TIF_ISOLATE_BP)
 #define _TIF_ISOLATE_BP_GUEST	BIT(TIF_ISOLATE_BP_GUEST)
 #define _TIF_PER_TRAP		BIT(TIF_PER_TRAP)