s390 updates for the 5.10 merge window

- Remove address space overrides using set_fs().
 
 - Convert to generic vDSO.
 
 - Convert to generic page table dumper.
 
 - Add ARCH_HAS_DEBUG_WX support.
 
 - Add leap seconds handling support.
 
 - Add NVMe firmware-assisted kernel dump support.
 
 - Extend NVMe boot support with memory clearing control and addition of
   kernel parameters.
 
 - AP bus and zcrypt api code rework. Add adapter configure/deconfigure
   interface. Extend debug features. Add failure injection support.
 
 - Add ECC secure private keys support.
 
 - Add KASan support for running protected virtualization host with
   4-level paging.
 
 - Utilize destroy page ultravisor call to speed up secure guests shutdown.
 
 - Implement ioremap_wc() and ioremap_prot() with MIO in PCI code.
 
 - Various checksum improvements.
 
 - Other small various fixes and improvements all over the code.
 -----BEGIN PGP SIGNATURE-----
 
 iQEzBAABCAAdFiEE3QHqV+H2a8xAv27vjYWKoQLXFBgFAl+JXIIACgkQjYWKoQLX
 FBgIWAf9FKpnIsy/aNI2RpvojfySEhgH3T5zxGDTjghCSUQzAu0hIBPKhQOs/YfV
 /apflXxNPneq7FsQPPpNqfdz2DXQrtgDfecK+7GyEVoOawFArgxiwP+tDVy4dmPT
 30PNfr+BpGs7GjKuj33fC0c5U33HYvKzUGJn/GQB2Fhw+5tTDxxCubuS1GVR9iuw
 /U1cQhG4KN0lwEeF2gO7BWWgqTH9C1t60+WzOQhIAbdvgtBRr1ctGu//F5S94BYL
 NBw5Wxb9vUHrMm2mL0n8bi16hSn2MWHmAMQLkxPXI2osBYun3soaHUWFSA3ryFMw
 4BGU+g7T66Pv3ZmLP4jH5UGrn8HWmg==
 =4zdC
 -----END PGP SIGNATURE-----

Merge tag 's390-5.10-1' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux

Pull s390 updates from Vasily Gorbik:

 - Remove address space overrides using set_fs()

 - Convert to generic vDSO

 - Convert to generic page table dumper

 - Add ARCH_HAS_DEBUG_WX support

 - Add leap seconds handling support

 - Add NVMe firmware-assisted kernel dump support

 - Extend NVMe boot support with memory clearing control and addition of
   kernel parameters

 - AP bus and zcrypt api code rework. Add adapter configure/deconfigure
   interface. Extend debug features. Add failure injection support

 - Add ECC secure private keys support

 - Add KASan support for running protected virtualization host with
   4-level paging

 - Utilize destroy page ultravisor call to speed up secure guests
   shutdown

 - Implement ioremap_wc() and ioremap_prot() with MIO in PCI code

 - Various checksum improvements

 - Other small various fixes and improvements all over the code

* tag 's390-5.10-1' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux: (85 commits)
  s390/uaccess: fix indentation
  s390/uaccess: add default cases for __put_user_fn()/__get_user_fn()
  s390/zcrypt: fix wrong format specifications
  s390/kprobes: move insn_page to text segment
  s390/sie: fix typo in SIGP code description
  s390/lib: fix kernel doc for memcmp()
  s390/zcrypt: Introduce Failure Injection feature
  s390/zcrypt: move ap_msg param one level up the call chain
  s390/ap/zcrypt: revisit ap and zcrypt error handling
  s390/ap: Support AP card SCLP config and deconfig operations
  s390/sclp: Add support for SCLP AP adapter config/deconfig
  s390/ap: add card/queue deconfig state
  s390/ap: add error response code field for ap queue devices
  s390/ap: split ap queue state machine state from device state
  s390/zcrypt: New config switch CONFIG_ZCRYPT_DEBUG
  s390/zcrypt: introduce msg tracking in zcrypt functions
  s390/startup: correct early pgm check info formatting
  s390: remove orphaned extern variables declarations
  s390/kasan: make sure int handler always run with DAT on
  s390/ipl: add support to control memory clearing for nvme re-IPL
  ...

Documentation/features/vm/ioremap_prot/arch-support.txt

@@ -24,7 +24,7 @@
     |      parisc: | TODO |
     |     powerpc: |  ok  |
     |       riscv: | TODO |
-    |        s390: | TODO |
+    |        s390: |  ok  |
     |          sh: |  ok  |
     |       sparc: | TODO |
     |          um: | TODO |

arch/s390/Kconfig

@@ -60,6 +60,7 @@ config S390
 	def_bool y
 	select ARCH_BINFMT_ELF_STATE
 	select ARCH_HAS_DEBUG_VM_PGTABLE
+	select ARCH_HAS_DEBUG_WX
 	select ARCH_HAS_DEVMEM_IS_ALLOWED
 	select ARCH_HAS_ELF_RANDOMIZE
 	select ARCH_HAS_FORTIFY_SOURCE
@@ -73,6 +74,7 @@ config S390
 	select ARCH_HAS_STRICT_MODULE_RWX
 	select ARCH_HAS_SYSCALL_WRAPPER
 	select ARCH_HAS_UBSAN_SANITIZE_ALL
+	select ARCH_HAS_VDSO_DATA
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select ARCH_INLINE_READ_LOCK
 	select ARCH_INLINE_READ_LOCK_BH
@@ -118,6 +120,8 @@ config S390
 	select GENERIC_CPU_AUTOPROBE
 	select GENERIC_CPU_VULNERABILITIES
 	select GENERIC_FIND_FIRST_BIT
+	select GENERIC_GETTIMEOFDAY
+	select GENERIC_PTDUMP
 	select GENERIC_SMP_IDLE_THREAD
 	select GENERIC_TIME_VSYSCALL
 	select HAVE_ALIGNED_STRUCT_PAGE if SLUB
@@ -149,6 +153,7 @@ config S390
 	select HAVE_FUNCTION_TRACER
 	select HAVE_FUTEX_CMPXCHG if FUTEX
 	select HAVE_GCC_PLUGINS
+	select HAVE_GENERIC_VDSO
 	select HAVE_KERNEL_BZIP2
 	select HAVE_KERNEL_GZIP
 	select HAVE_KERNEL_LZ4

arch/s390/Kconfig.debug

@@ -3,17 +3,5 @@
 config TRACE_IRQFLAGS_SUPPORT
 	def_bool y
 
-config S390_PTDUMP
-	bool "Export kernel pagetable layout to userspace via debugfs"
-	depends on DEBUG_KERNEL
-	select DEBUG_FS
-	help
-	  Say Y here if you want to show the kernel pagetable layout in a
-	  debugfs file. This information is only useful for kernel developers
-	  who are working in architecture specific areas of the kernel.
-	  It is probably not a good idea to enable this feature in a production
-	  kernel.
-	  If in doubt, say "N"
-
 config EARLY_PRINTK
 	def_bool y

arch/s390/boot/Makefile

@@ -73,7 +73,3 @@ $(obj)/startup.a: $(OBJECTS) FORCE
 install:
 	sh -x  $(srctree)/$(obj)/install.sh $(KERNELRELEASE) $(obj)/bzImage \
 	      System.map "$(INSTALL_PATH)"
-
-chkbss := $(obj-y)
-chkbss-target := startup.a
-include $(srctree)/arch/s390/scripts/Makefile.chkbss

arch/s390/boot/compressed/Makefile

@@ -62,7 +62,3 @@ $(obj)/vmlinux.bin.xz: $(vmlinux.bin.all-y) FORCE
 OBJCOPYFLAGS_piggy.o := -I binary -O elf64-s390 -B s390:64-bit --rename-section .data=.vmlinux.bin.compressed
 $(obj)/piggy.o: $(obj)/vmlinux.bin$(suffix-y) FORCE
 	$(call if_changed,objcopy)
-
-chkbss := $(filter-out piggy.o info.o, $(obj-y))
-chkbss-target := vmlinux.bin
-include $(srctree)/arch/s390/scripts/Makefile.chkbss

arch/s390/boot/compressed/decompressor.c

@@ -16,7 +16,6 @@
  * gzip declarations
  */
 #define STATIC static
-#define STATIC_RW_DATA static __section(.data)
 
 #undef memset
 #undef memcpy

arch/s390/boot/compressed/vmlinux.lds.S

@@ -58,6 +58,19 @@ SECTIONS
 	BOOT_DATA
 	BOOT_DATA_PRESERVED
 
+	/*
+	 * This is the BSS section of the decompressor and not of the decompressed Linux kernel.
+	 * It will consume place in the decompressor's image.
+	 */
+	. = ALIGN(8);
+	.bss : {
+		_bss = . ;
+		*(.bss)
+		*(.bss.*)
+		*(COMMON)
+		_ebss = .;
+	}
+
 	/*
 	 * uncompressed image info used by the decompressor it should match
 	 * struct vmlinux_info. It comes from .vmlinux.info section of
@@ -81,15 +94,6 @@ SECTIONS
 		FILL(0xff);
 		. = ALIGN(4096);
 	}
-	. = ALIGN(256);
-	.bss : {
-		_bss = . ;
-		*(.bss)
-		*(.bss.*)
-		*(COMMON)
-		. = ALIGN(8);	/* For convenience during zeroing */
-		_ebss = .;
-	}
 	_end = .;
 
 	/* Sections to be discarded */

arch/s390/boot/head.S

@@ -360,22 +360,23 @@ ENTRY(startup_kdump)
 # the save area and does disabled wait with a faulty address.
 #
 ENTRY(startup_pgm_check_handler)
-	stmg	%r0,%r15,__LC_SAVE_AREA_SYNC
+	stmg	%r8,%r15,__LC_SAVE_AREA_SYNC
-	la	%r1,4095
+	la	%r8,4095
-	stctg	%c0,%c15,__LC_CREGS_SAVE_AREA-4095(%r1)
+	stctg	%c0,%c15,__LC_CREGS_SAVE_AREA-4095(%r8)
-	mvc	__LC_GPREGS_SAVE_AREA-4095(128,%r1),__LC_SAVE_AREA_SYNC
+	stmg	%r0,%r7,__LC_GPREGS_SAVE_AREA-4095(%r8)
-	mvc	__LC_PSW_SAVE_AREA-4095(16,%r1),__LC_PGM_OLD_PSW
+	mvc	__LC_GPREGS_SAVE_AREA-4095+64(64,%r8),__LC_SAVE_AREA_SYNC
+	mvc	__LC_PSW_SAVE_AREA-4095(16,%r8),__LC_PGM_OLD_PSW
 	mvc	__LC_RETURN_PSW(16),__LC_PGM_OLD_PSW
 	ni	__LC_RETURN_PSW,0xfc	# remove IO and EX bits
 	ni	__LC_RETURN_PSW+1,0xfb	# remove MCHK bit
 	oi	__LC_RETURN_PSW+1,0x2	# set wait state bit
-	larl	%r2,.Lold_psw_disabled_wait
+	larl	%r9,.Lold_psw_disabled_wait
-	stg	%r2,__LC_PGM_NEW_PSW+8
+	stg	%r9,__LC_PGM_NEW_PSW+8
-	l	%r15,.Ldump_info_stack-.Lold_psw_disabled_wait(%r2)
+	l	%r15,.Ldump_info_stack-.Lold_psw_disabled_wait(%r9)
 	brasl	%r14,print_pgm_check_info
 .Lold_psw_disabled_wait:
-	la	%r1,4095
+	la	%r8,4095
-	lmg	%r0,%r15,__LC_GPREGS_SAVE_AREA-4095(%r1)
+	lmg	%r0,%r15,__LC_GPREGS_SAVE_AREA-4095(%r8)
 	lpswe	__LC_RETURN_PSW		# disabled wait
 .Ldump_info_stack:
 	.long	0x5000 + PAGE_SIZE - STACK_FRAME_OVERHEAD

arch/s390/boot/ipl_parm.c

@@ -21,7 +21,7 @@ unsigned long __bootdata(memory_end);
 int __bootdata(memory_end_set);
 int __bootdata(noexec_disabled);
 
-int kaslr_enabled __section(.data);
+int kaslr_enabled;
 
 static inline int __diag308(unsigned long subcode, void *addr)
 {
@@ -70,30 +70,44 @@ static size_t scpdata_length(const u8 *buf, size_t count)
 static size_t ipl_block_get_ascii_scpdata(char *dest, size_t size,
 					  const struct ipl_parameter_block *ipb)
 {
-	size_t count;
+	const __u8 *scp_data;
-	size_t i;
+	__u32 scp_data_len;
 	int has_lowercase;
+	size_t count = 0;
+	size_t i;
 
-	count = min(size - 1, scpdata_length(ipb->fcp.scp_data,
+	switch (ipb->pb0_hdr.pbt) {
-					     ipb->fcp.scp_data_len));
+	case IPL_PBT_FCP:
+		scp_data_len = ipb->fcp.scp_data_len;
+		scp_data = ipb->fcp.scp_data;
+		break;
+	case IPL_PBT_NVME:
+		scp_data_len = ipb->nvme.scp_data_len;
+		scp_data = ipb->nvme.scp_data;
+		break;
+	default:
+		goto out;
+	}
+
+	count = min(size - 1, scpdata_length(scp_data, scp_data_len));
 	if (!count)
 		goto out;
 
 	has_lowercase = 0;
 	for (i = 0; i < count; i++) {
-		if (!isascii(ipb->fcp.scp_data[i])) {
+		if (!isascii(scp_data[i])) {
 			count = 0;
 			goto out;
 		}
-		if (!has_lowercase && islower(ipb->fcp.scp_data[i]))
+		if (!has_lowercase && islower(scp_data[i]))
 			has_lowercase = 1;
 	}
 
 	if (has_lowercase)
-		memcpy(dest, ipb->fcp.scp_data, count);
+		memcpy(dest, scp_data, count);
 	else
 		for (i = 0; i < count; i++)
-			dest[i] = tolower(ipb->fcp.scp_data[i]);
+			dest[i] = tolower(scp_data[i]);
 out:
 	dest[count] = '\0';
 	return count;
@@ -115,6 +129,7 @@ static void append_ipl_block_parm(void)
 			parm, COMMAND_LINE_SIZE - len - 1, &ipl_block);
 		break;
 	case IPL_PBT_FCP:
+	case IPL_PBT_NVME:
 		rc = ipl_block_get_ascii_scpdata(
 			parm, COMMAND_LINE_SIZE - len - 1, &ipl_block);
 		break;
@@ -209,7 +224,7 @@ static void modify_fac_list(char *str)
 	check_cleared_facilities();
 }
 
-static char command_line_buf[COMMAND_LINE_SIZE] __section(.data);
+static char command_line_buf[COMMAND_LINE_SIZE];
 void parse_boot_command_line(void)
 {
 	char *param, *val;
@@ -230,7 +245,7 @@ void parse_boot_command_line(void)
 		if (!strcmp(param, "vmalloc") && val)
 			vmalloc_size = round_up(memparse(val, NULL), PAGE_SIZE);
 
-		if (!strcmp(param, "dfltcc")) {
+		if (!strcmp(param, "dfltcc") && val) {
 			if (!strcmp(val, "off"))
 				zlib_dfltcc_support = ZLIB_DFLTCC_DISABLED;
 			else if (!strcmp(val, "on"))
@@ -254,7 +269,26 @@ void parse_boot_command_line(void)
 
 		if (!strcmp(param, "nokaslr"))
 			kaslr_enabled = 0;
+
+#if IS_ENABLED(CONFIG_KVM)
+		if (!strcmp(param, "prot_virt")) {
+			rc = kstrtobool(val, &enabled);
+			if (!rc && enabled)
+				prot_virt_host = 1;
 		}
+#endif
+	}
+}
+
+static inline bool is_ipl_block_dump(void)
+{
+	if (ipl_block.pb0_hdr.pbt == IPL_PBT_FCP &&
+	    ipl_block.fcp.opt == IPL_PB0_FCP_OPT_DUMP)
+		return true;
+	if (ipl_block.pb0_hdr.pbt == IPL_PBT_NVME &&
+	    ipl_block.nvme.opt == IPL_PB0_NVME_OPT_DUMP)
+		return true;
+	return false;
 }
 
 void setup_memory_end(void)
@@ -262,9 +296,7 @@ void setup_memory_end(void)
 #ifdef CONFIG_CRASH_DUMP
 	if (OLDMEM_BASE) {
 		kaslr_enabled = 0;
-	} else if (ipl_block_valid &&
+	} else if (ipl_block_valid && is_ipl_block_dump()) {
-		   ipl_block.pb0_hdr.pbt == IPL_PBT_FCP &&
-		   ipl_block.fcp.opt == IPL_PB0_FCP_OPT_DUMP) {
 		kaslr_enabled = 0;
 		if (!sclp_early_get_hsa_size(&memory_end) && memory_end)
 			memory_end_set = 1;

arch/s390/boot/kaslr.c

@@ -42,7 +42,7 @@ static int check_prng(void)
 		return PRNG_MODE_TDES;
 }
 
-static unsigned long get_random(unsigned long limit)
+static int get_random(unsigned long limit, unsigned long *value)
 {
 	struct prng_parm prng = {
 		/* initial parameter block for tdes mode, copied from libica */
@@ -84,19 +84,101 @@ static unsigned long get_random(unsigned long limit)
 			  (u8 *) &random, sizeof(random));
 		break;
 	default:
-		random = 0;
+		return -1;
 	}
-	return random % limit;
+	*value = random % limit;
+	return 0;
+}
+
+/*
+ * To randomize kernel base address we have to consider several facts:
+ * 1. physical online memory might not be continuous and have holes. mem_detect
+ *    info contains list of online memory ranges we should consider.
+ * 2. we have several memory regions which are occupied and we should not
+ *    overlap and destroy them. Currently safe_addr tells us the border below
+ *    which all those occupied regions are. We are safe to use anything above
+ *    safe_addr.
+ * 3. the upper limit might apply as well, even if memory above that limit is
+ *    online. Currently those limitations are:
+ *    3.1. Limit set by "mem=" kernel command line option
+ *    3.2. memory reserved at the end for kasan initialization.
+ * 4. kernel base address must be aligned to THREAD_SIZE (kernel stack size).
+ *    Which is required for CONFIG_CHECK_STACK. Currently THREAD_SIZE is 4 pages
+ *    (16 pages when the kernel is built with kasan enabled)
+ * Assumptions:
+ * 1. kernel size (including .bss size) and upper memory limit are page aligned.
+ * 2. mem_detect memory region start is THREAD_SIZE aligned / end is PAGE_SIZE
+ *    aligned (in practice memory configurations granularity on z/VM and LPAR
+ *    is 1mb).
+ *
+ * To guarantee uniform distribution of kernel base address among all suitable
+ * addresses we generate random value just once. For that we need to build a
+ * continuous range in which every value would be suitable. We can build this
+ * range by simply counting all suitable addresses (let's call them positions)
+ * which would be valid as kernel base address. To count positions we iterate
+ * over online memory ranges. For each range which is big enough for the
+ * kernel image we count all suitable addresses we can put the kernel image at
+ * that is
+ * (end - start - kernel_size) / THREAD_SIZE + 1
+ * Two functions count_valid_kernel_positions and position_to_address help
+ * to count positions in memory range given and then convert position back
+ * to address.
+ */
+static unsigned long count_valid_kernel_positions(unsigned long kernel_size,
+						  unsigned long _min,
+						  unsigned long _max)
+{
+	unsigned long start, end, pos = 0;
+	int i;
+
+	for_each_mem_detect_block(i, &start, &end) {
+		if (_min >= end)
+			continue;
+		if (start >= _max)
+			break;
+		start = max(_min, start);
+		end = min(_max, end);
+		if (end - start < kernel_size)
+			continue;
+		pos += (end - start - kernel_size) / THREAD_SIZE + 1;
+	}
+
+	return pos;
+}
+
+static unsigned long position_to_address(unsigned long pos, unsigned long kernel_size,
+				 unsigned long _min, unsigned long _max)
+{
+	unsigned long start, end;
+	int i;
+
+	for_each_mem_detect_block(i, &start, &end) {
+		if (_min >= end)
+			continue;
+		if (start >= _max)
+			break;
+		start = max(_min, start);
+		end = min(_max, end);
+		if (end - start < kernel_size)
+			continue;
+		if ((end - start - kernel_size) / THREAD_SIZE + 1 >= pos)
+			return start + (pos - 1) * THREAD_SIZE;
+		pos -= (end - start - kernel_size) / THREAD_SIZE + 1;
+	}
+
+	return 0;
 }
 
 unsigned long get_random_base(unsigned long safe_addr)
 {
-	unsigned long memory_limit = memory_end_set ? memory_end : 0;
+	unsigned long memory_limit = get_mem_detect_end();
-	unsigned long base, start, end, kernel_size;
+	unsigned long base_pos, max_pos, kernel_size;
-	unsigned long block_sum, offset;
 	unsigned long kasan_needs;
 	int i;
 
+	if (memory_end_set)
+		memory_limit = min(memory_limit, memory_end);
+
 	if (IS_ENABLED(CONFIG_BLK_DEV_INITRD) && INITRD_START && INITRD_SIZE) {
 		if (safe_addr < INITRD_START + INITRD_SIZE)
 			safe_addr = INITRD_START + INITRD_SIZE;
@@ -126,45 +208,17 @@ unsigned long get_random_base(unsigned long safe_addr)
 	}
 
 	kernel_size = vmlinux.image_size + vmlinux.bss_size;
-	block_sum = 0;
+	if (safe_addr + kernel_size > memory_limit)
-	for_each_mem_detect_block(i, &start, &end) {
+		return 0;
-		if (memory_limit) {
+
-			if (start >= memory_limit)
+	max_pos = count_valid_kernel_positions(kernel_size, safe_addr, memory_limit);
-				break;
+	if (!max_pos) {
-			if (end > memory_limit)
-				end = memory_limit;
-		}
-		if (end - start < kernel_size)
-			continue;
-		block_sum += end - start - kernel_size;
-	}
-	if (!block_sum) {
 		sclp_early_printk("KASLR disabled: not enough memory\n");
 		return 0;
 	}
 
-	base = get_random(block_sum);
+	/* we need a value in the range [1, base_pos] inclusive */
-	if (base == 0)
+	if (get_random(max_pos, &base_pos))
 		return 0;
-	if (base < safe_addr)
+	return position_to_address(base_pos + 1, kernel_size, safe_addr, memory_limit);
-		base = safe_addr;
-	block_sum = offset = 0;
-	for_each_mem_detect_block(i, &start, &end) {
-		if (memory_limit) {
-			if (start >= memory_limit)
-				break;
-			if (end > memory_limit)
-				end = memory_limit;
-		}
-		if (end - start < kernel_size)
-			continue;
-		block_sum += end - start - kernel_size;
-		if (base <= block_sum) {
-			base = start + base - offset;
-			base = ALIGN_DOWN(base, THREAD_SIZE);
-			break;
-		}
-		offset = block_sum;
-	}
-	return base;
 }

arch/s390/boot/pgm_check_info.c

@@ -2,6 +2,7 @@
 #include <linux/kernel.h>
 #include <linux/string.h>
 #include <asm/lowcore.h>
+#include <asm/setup.h>
 #include <asm/sclp.h>
 #include "boot.h"
 
@@ -32,7 +33,8 @@ void print_pgm_check_info(void)
 	char *p;
 
 	add_str(buf, "Linux version ");
-	strlcat(buf, kernel_version, sizeof(buf));
+	strlcat(buf, kernel_version, sizeof(buf) - 1);
+	strlcat(buf, "\n", sizeof(buf));
 	sclp_early_printk(buf);
 
 	p = add_str(buf, "Kernel fault: interruption code ");
@@ -42,6 +44,13 @@ void print_pgm_check_info(void)
 	add_str(p, "\n");
 	sclp_early_printk(buf);
 
+	if (kaslr_enabled) {
+		p = add_str(buf, "Kernel random base: ");
+		p = add_val_as_hex(p, __kaslr_offset);
+		add_str(p, "\n");
+		sclp_early_printk(buf);
+	}
+
 	p = add_str(buf, "PSW : ");
 	p = add_val_as_hex(p, S390_lowcore.psw_save_area.mask);
 	p = add_str(p, " ");

arch/s390/boot/startup.c

@@ -48,8 +48,6 @@ struct diag_ops __bootdata_preserved(diag_dma_ops) = {
 };
 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);
 
 void error(char *x)
 {
@@ -120,6 +118,9 @@ static void handle_relocs(unsigned long offset)
 	}
 }
 
+/*
+ * This function clears the BSS section of the decompressed Linux kernel and NOT the decompressor's.
+ */
 static void clear_bss_section(void)
 {
 	memset((void *)vmlinux.default_lma + vmlinux.image_size, 0, vmlinux.bss_size);

arch/s390/boot/text_dma.S

@@ -96,23 +96,6 @@ ENTRY(_diag0c_dma)
 	BR_EX_DMA_r14
 ENDPROC(_diag0c_dma)
 
-/*
- * void _swsusp_reset_dma(void)
- */
-ENTRY(_swsusp_reset_dma)
-	larl	%r1,restart_entry
-	larl	%r2,.Lrestart_diag308_psw
-	og	%r1,0(%r2)
-	stg	%r1,0(%r0)
-	lghi	%r0,0
-	diag	%r0,%r0,0x308
-restart_entry:
-	lhi	%r1,1
-	sigp	%r1,%r0,SIGP_SET_ARCHITECTURE
-	sam64
-	BR_EX_DMA_r14
-ENDPROC(_swsusp_reset_dma)
-
 /*
  * void _diag308_reset_dma(void)
  *

arch/s390/boot/uv.c

@@ -7,6 +7,9 @@
 #ifdef CONFIG_PROTECTED_VIRTUALIZATION_GUEST
 int __bootdata_preserved(prot_virt_guest);
 #endif
+#if IS_ENABLED(CONFIG_KVM)
+int __bootdata_preserved(prot_virt_host);
+#endif
 struct uv_info __bootdata_preserved(uv_info);
 
 void uv_query_info(void)

arch/s390/configs/debug_defconfig

@@ -775,6 +775,8 @@ CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_PAGEALLOC=y
 CONFIG_PAGE_OWNER=y
 CONFIG_DEBUG_RODATA_TEST=y
+CONFIG_DEBUG_WX=y
+CONFIG_PTDUMP_DEBUGFS=y
 CONFIG_DEBUG_OBJECTS=y
 CONFIG_DEBUG_OBJECTS_SELFTEST=y
 CONFIG_DEBUG_OBJECTS_FREE=y
@@ -822,7 +824,6 @@ CONFIG_FTRACE_SYSCALLS=y
 CONFIG_BLK_DEV_IO_TRACE=y
 CONFIG_BPF_KPROBE_OVERRIDE=y
 CONFIG_HIST_TRIGGERS=y
-CONFIG_S390_PTDUMP=y
 CONFIG_NOTIFIER_ERROR_INJECTION=m
 CONFIG_NETDEV_NOTIFIER_ERROR_INJECT=m
 CONFIG_FAULT_INJECTION=y

arch/s390/configs/defconfig

@@ -759,6 +759,8 @@ CONFIG_GDB_SCRIPTS=y
 CONFIG_FRAME_WARN=1024
 CONFIG_DEBUG_SECTION_MISMATCH=y
 CONFIG_MAGIC_SYSRQ=y
+CONFIG_DEBUG_WX=y
+CONFIG_PTDUMP_DEBUGFS=y
 CONFIG_DEBUG_MEMORY_INIT=y
 CONFIG_PANIC_ON_OOPS=y
 CONFIG_TEST_LOCKUP=m
@@ -775,7 +777,6 @@ CONFIG_FTRACE_SYSCALLS=y
 CONFIG_BLK_DEV_IO_TRACE=y
 CONFIG_BPF_KPROBE_OVERRIDE=y
 CONFIG_HIST_TRIGGERS=y
-CONFIG_S390_PTDUMP=y
 CONFIG_LKDTM=m
 CONFIG_PERCPU_TEST=m
 CONFIG_ATOMIC64_SELFTEST=y

arch/s390/include/asm/checksum.h

@@ -13,21 +13,21 @@
 #define _S390_CHECKSUM_H
 
 #include <linux/uaccess.h>
+#include <linux/in6.h>
 
 /*
- * computes the checksum of a memory block at buff, length len,
+ * Computes the checksum of a memory block at buff, length len,
- * and adds in "sum" (32-bit)
+ * and adds in "sum" (32-bit).
  *
- * returns a 32-bit number suitable for feeding into itself
+ * Returns a 32-bit number suitable for feeding into itself
- * or csum_tcpudp_magic
+ * or csum_tcpudp_magic.
  *
- * this function must be called with even lengths, except
+ * This function must be called with even lengths, except
- * for the last fragment, which may be odd
+ * for the last fragment, which may be odd.
  *
- * it's best to have buff aligned on a 32-bit boundary
+ * It's best to have buff aligned on a 32-bit boundary.
  */
-static inline __wsum
+static inline __wsum csum_partial(const void *buff, int len, __wsum sum)
-csum_partial(const void *buff, int len, __wsum sum)
 {
 	register unsigned long reg2 asm("2") = (unsigned long) buff;
 	register unsigned long reg3 asm("3") = (unsigned long) len;
@@ -40,74 +40,91 @@ csum_partial(const void *buff, int len, __wsum sum)
 }
 
 /*
- *      Fold a partial checksum without adding pseudo headers
+ * Fold a partial checksum without adding pseudo headers.
  */
 static inline __sum16 csum_fold(__wsum sum)
 {
 	u32 csum = (__force u32) sum;
 
-	csum += (csum >> 16) + (csum << 16);
+	csum += (csum >> 16) | (csum << 16);
 	csum >>= 16;
 	return (__force __sum16) ~csum;
 }
 
 /*
  * This is a version of ip_compute_csum() optimized for IP headers,
- *	which always checksum on 4 octet boundaries.
+ * which always checksums on 4 octet boundaries.
- *
  */
 static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
 {
-	return csum_fold(csum_partial(iph, ihl*4, 0));
+	__u64 csum = 0;
+	__u32 *ptr = (u32 *)iph;
+
+	csum += *ptr++;
+	csum += *ptr++;
+	csum += *ptr++;
+	csum += *ptr++;
+	ihl -= 4;
+	while (ihl--)
+		csum += *ptr++;
+	csum += (csum >> 32) | (csum << 32);
+	return csum_fold((__force __wsum)(csum >> 32));
 }
 
 /*
- * computes the checksum of the TCP/UDP pseudo-header
+ * Computes the checksum of the TCP/UDP pseudo-header.
- * returns a 32-bit checksum
+ * Returns a 32-bit checksum.
  */
-static inline __wsum
+static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr, __u32 len,
-csum_tcpudp_nofold(__be32 saddr, __be32 daddr, __u32 len, __u8 proto,
+					__u8 proto, __wsum sum)
-                   __wsum sum)
 {
-	__u32 csum = (__force __u32)sum;
+	__u64 csum = (__force __u64)sum;
 
 	csum += (__force __u32)saddr;
-	if (csum < (__force __u32)saddr)
-		csum++;
-
 	csum += (__force __u32)daddr;
-	if (csum < (__force __u32)daddr)
+	csum += len;
-		csum++;
+	csum += proto;
-
+	csum += (csum >> 32) | (csum << 32);
-	csum += len + proto;
+	return (__force __wsum)(csum >> 32);
-	if (csum < len + proto)
-		csum++;
-
-	return (__force __wsum)csum;
 }
 
 /*
- * computes the checksum of the TCP/UDP pseudo-header
+ * Computes the checksum of the TCP/UDP pseudo-header.
- * returns a 16-bit checksum, already complemented
+ * Returns a 16-bit checksum, already complemented.
  */
-
+static inline __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr, __u32 len,
-static inline __sum16
+					__u8 proto, __wsum sum)
-csum_tcpudp_magic(__be32 saddr, __be32 daddr, __u32 len, __u8 proto,
-                  __wsum sum)
 {
 	return csum_fold(csum_tcpudp_nofold(saddr, daddr, len, proto, sum));
 }
 
 /*
- * this routine is used for miscellaneous IP-like checksums, mainly
+ * Used for miscellaneous IP-like checksums, mainly icmp.
- * in icmp.c
  */
-
 static inline __sum16 ip_compute_csum(const void *buff, int len)
 {
 	return csum_fold(csum_partial(buff, len, 0));
 }
 
+#define _HAVE_ARCH_IPV6_CSUM
+static inline __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
+				      const struct in6_addr *daddr,
+				      __u32 len, __u8 proto, __wsum csum)
+{
+	__u64 sum = (__force __u64)csum;
+
+	sum += (__force __u32)saddr->s6_addr32[0];
+	sum += (__force __u32)saddr->s6_addr32[1];
+	sum += (__force __u32)saddr->s6_addr32[2];
+	sum += (__force __u32)saddr->s6_addr32[3];
+	sum += (__force __u32)daddr->s6_addr32[0];
+	sum += (__force __u32)daddr->s6_addr32[1];
+	sum += (__force __u32)daddr->s6_addr32[2];
+	sum += (__force __u32)daddr->s6_addr32[3];
+	sum += len;
+	sum += proto;
+	sum += (sum >> 32) | (sum << 32);
+	return csum_fold((__force __wsum)(sum >> 32));
+}
+
 #endif /* _S390_CHECKSUM_H */
-
-

arch/s390/include/asm/cio.h

@@ -356,7 +356,6 @@ static inline u8 pathmask_to_pos(u8 mask)
 	return 8 - ffs(mask);
 }
 
-void channel_subsystem_reinit(void);
 extern void css_schedule_reprobe(void);
 
 extern void *cio_dma_zalloc(size_t size);
@@ -372,6 +371,7 @@ struct gen_pool *cio_gp_dma_create(struct device *dma_dev, int nr_pages);
 /* Function from drivers/s390/cio/chsc.c */
 int chsc_sstpc(void *page, unsigned int op, u16 ctrl, u64 *clock_delta);
 int chsc_sstpi(void *page, void *result, size_t size);
+int chsc_stzi(void *page, void *result, size_t size);
 int chsc_sgib(u32 origin);
 
 #endif

arch/s390/include/asm/clocksource.h

@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* s390-specific clocksource additions */
+
+#ifndef _ASM_S390_CLOCKSOURCE_H
+#define _ASM_S390_CLOCKSOURCE_H
+
+#endif /* _ASM_S390_CLOCKSOURCE_H */

arch/s390/include/asm/clp.h

@@ -5,6 +5,9 @@
 /* CLP common request & response block size */
 #define CLP_BLK_SIZE			PAGE_SIZE
 
+/* Call Logical Processor - Command Code */
+#define CLP_SLPC		0x0001
+
 #define CLP_LPS_BASE	0
 #define CLP_LPS_PCI	2
 

arch/s390/include/asm/gmap.h

@@ -140,8 +140,6 @@ int gmap_shadow_page(struct gmap *sg, unsigned long saddr, pte_t pte);
 
 void gmap_register_pte_notifier(struct gmap_notifier *);
 void gmap_unregister_pte_notifier(struct gmap_notifier *);
-void gmap_pte_notify(struct mm_struct *, unsigned long addr, pte_t *,
-		     unsigned long bits);
 
 int gmap_mprotect_notify(struct gmap *, unsigned long start,
 			 unsigned long len, int prot);

arch/s390/include/asm/io.h

@@ -12,6 +12,7 @@
 
 #include <linux/kernel.h>
 #include <asm/page.h>
+#include <asm/pgtable.h>
 #include <asm/pci_io.h>
 
 #define xlate_dev_mem_ptr xlate_dev_mem_ptr
@@ -26,7 +27,10 @@ void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr);
 
 #define IO_SPACE_LIMIT 0
 
+void __iomem *ioremap_prot(phys_addr_t addr, size_t size, unsigned long prot);
 void __iomem *ioremap(phys_addr_t addr, size_t size);
+void __iomem *ioremap_wc(phys_addr_t addr, size_t size);
+void __iomem *ioremap_wt(phys_addr_t addr, size_t size);
 void iounmap(volatile void __iomem *addr);
 
 static inline void __iomem *ioport_map(unsigned long port, unsigned int nr)
@@ -52,6 +56,10 @@ static inline void ioport_unmap(void __iomem *p)
 #define pci_iomap_wc pci_iomap_wc
 #define pci_iomap_wc_range pci_iomap_wc_range
 
+#define ioremap ioremap
+#define ioremap_wt ioremap_wt
+#define ioremap_wc ioremap_wc
+
 #define memcpy_fromio(dst, src, count)	zpci_memcpy_fromio(dst, src, count)
 #define memcpy_toio(dst, src, count)	zpci_memcpy_toio(dst, src, count)
 #define memset_io(dst, val, count)	zpci_memset_io(dst, val, count)

arch/s390/include/asm/ipl.h

@@ -66,6 +66,7 @@ enum ipl_type {
 	IPL_TYPE_FCP_DUMP	= 8,
 	IPL_TYPE_NSS		= 16,
 	IPL_TYPE_NVME		= 32,
+	IPL_TYPE_NVME_DUMP	= 64,
 };
 
 struct ipl_info
@@ -94,6 +95,12 @@ extern struct ipl_info ipl_info;
 extern void setup_ipl(void);
 extern void set_os_info_reipl_block(void);
 
+static inline bool is_ipl_type_dump(void)
+{
+	return (ipl_info.type == IPL_TYPE_FCP_DUMP) ||
+		(ipl_info.type == IPL_TYPE_NVME_DUMP);
+}
+
 struct ipl_report {
 	struct ipl_parameter_block *ipib;
 	struct list_head components;

arch/s390/include/asm/kasan.h

@@ -19,6 +19,7 @@
 extern void kasan_early_init(void);
 extern void kasan_copy_shadow(pgd_t *dst);
 extern void kasan_free_early_identity(void);
+extern unsigned long kasan_vmax;
 #else
 static inline void kasan_early_init(void) { }
 static inline void kasan_copy_shadow(pgd_t *dst) { }

arch/s390/include/asm/pci.h

@@ -208,9 +208,8 @@ int zpci_unregister_ioat(struct zpci_dev *, u8);
 void zpci_remove_reserved_devices(void);
 
 /* CLP */
+int clp_setup_writeback_mio(void);
 int clp_scan_pci_devices(void);
-int clp_rescan_pci_devices(void);
-int clp_rescan_pci_devices_simple(u32 *fid);
 int clp_add_pci_device(u32, u32, int);
 int clp_enable_fh(struct zpci_dev *, u8);
 int clp_disable_fh(struct zpci_dev *);
@@ -232,12 +231,10 @@ static inline bool zpci_use_mio(struct zpci_dev *zdev)
 /* Error handling and recovery */
 void zpci_event_error(void *);
 void zpci_event_availability(void *);
-void zpci_rescan(void);
 bool zpci_is_enabled(void);
 #else /* CONFIG_PCI */
 static inline void zpci_event_error(void *e) {}
 static inline void zpci_event_availability(void *e) {}
-static inline void zpci_rescan(void) {}
 #endif /* CONFIG_PCI */
 
 #ifdef CONFIG_HOTPLUG_PCI_S390
@@ -282,7 +279,6 @@ int zpci_debug_init(void);
 void zpci_debug_exit(void);
 void zpci_debug_init_device(struct zpci_dev *, const char *);
 void zpci_debug_exit_device(struct zpci_dev *);
-void zpci_debug_info(struct zpci_dev *, struct seq_file *);
 
 /* Error reporting */
 int zpci_report_error(struct pci_dev *, struct zpci_report_error_header *);

arch/s390/include/asm/pci_clp.h

@@ -7,6 +7,7 @@
 /*
  * Call Logical Processor - Command Codes
  */
+#define CLP_SLPC		0x0001
 #define CLP_LIST_PCI		0x0002
 #define CLP_QUERY_PCI_FN	0x0003
 #define CLP_QUERY_PCI_FNGRP	0x0004
@@ -51,6 +52,19 @@ struct clp_fh_list_entry {
 
 extern bool zpci_unique_uid;
 
+struct clp_rsp_slpc_pci {
+	struct clp_rsp_hdr hdr;
+	u32 reserved2[4];
+	u32 lpif[8];
+	u32 reserved3[4];
+	u32 vwb		:  1;
+	u32		:  1;
+	u32 mio_wb	:  6;
+	u32		: 24;
+	u32 reserved5[3];
+	u32 lpic[8];
+} __packed;
+
 /* List PCI functions request */
 struct clp_req_list_pci {
 	struct clp_req_hdr hdr;
@@ -172,6 +186,11 @@ struct clp_rsp_set_pci {
 } __packed;
 
 /* Combined request/response block structures used by clp insn */
+struct clp_req_rsp_slpc_pci {
+	struct clp_req_slpc request;
+	struct clp_rsp_slpc_pci response;
+} __packed;
+
 struct clp_req_rsp_list_pci {
 	struct clp_req_list_pci request;
 	struct clp_rsp_list_pci response;

arch/s390/include/asm/pgalloc.h

@@ -146,8 +146,6 @@ static inline void pmd_populate(struct mm_struct *mm,
 #define pte_free_kernel(mm, pte) page_table_free(mm, (unsigned long *) pte)
 #define pte_free(mm, pte) page_table_free(mm, (unsigned long *) pte)
 
-extern void rcu_table_freelist_finish(void);
-
 void vmem_map_init(void);
 void *vmem_crst_alloc(unsigned long val);
 pte_t *vmem_pte_alloc(void);

arch/s390/include/asm/pgtable.h

@@ -89,6 +89,7 @@ extern unsigned long VMALLOC_START;
 extern unsigned long VMALLOC_END;
 #define VMALLOC_DEFAULT_SIZE	((128UL << 30) - MODULES_LEN)
 extern struct page *vmemmap;
+extern unsigned long vmemmap_size;
 
 #define VMEM_MAX_PHYS ((unsigned long) vmemmap)
 
@@ -1186,6 +1187,12 @@ void gmap_pmdp_invalidate(struct mm_struct *mm, unsigned long vmaddr);
 void gmap_pmdp_idte_local(struct mm_struct *mm, unsigned long vmaddr);
 void gmap_pmdp_idte_global(struct mm_struct *mm, unsigned long vmaddr);
 
+#define pgprot_writecombine	pgprot_writecombine
+pgprot_t pgprot_writecombine(pgprot_t prot);
+
+#define pgprot_writethrough	pgprot_writethrough
+pgprot_t pgprot_writethrough(pgprot_t prot);
+
 /*
  * Certain architectures need to do special things when PTEs
  * within a page table are directly modified.  Thus, the following
@@ -1209,7 +1216,8 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 static inline pte_t mk_pte_phys(unsigned long physpage, pgprot_t pgprot)
 {
 	pte_t __pte;
-	pte_val(__pte) = physpage + pgprot_val(pgprot);
+
+	pte_val(__pte) = physpage | pgprot_val(pgprot);
 	if (!MACHINE_HAS_NX)
 		pte_val(__pte) &= ~_PAGE_NOEXEC;
 	return pte_mkyoung(__pte);

arch/s390/include/asm/ptdump.h

@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _ASM_S390_PTDUMP_H
+#define _ASM_S390_PTDUMP_H
+
+void ptdump_check_wx(void);
+
+static inline void debug_checkwx(void)
+{
+	if (IS_ENABLED(CONFIG_DEBUG_WX))
+		ptdump_check_wx();
+}
+
+#endif /* _ASM_S390_PTDUMP_H */

arch/s390/include/asm/qdio.h

@@ -26,9 +26,9 @@
 
 /**
  * struct qdesfmt0 - queue descriptor, format 0
- * @sliba: storage list information block address
+ * @sliba: absolute address of storage list information block
- * @sla: storage list address
+ * @sla: absolute address of storage list
- * @slsba: storage list state block address
+ * @slsba: absolute address of storage list state block
  * @akey: access key for SLIB
  * @bkey: access key for SL
  * @ckey: access key for SBALs
@@ -56,7 +56,7 @@ struct qdesfmt0 {
  * @oqdcnt: output queue descriptor count
  * @iqdsz: input queue descriptor size
  * @oqdsz: output queue descriptor size
- * @qiba: queue information block address
+ * @qiba: absolute address of queue information block
  * @qkey: queue information block key
  * @qdf0: queue descriptions
  */
@@ -327,7 +327,6 @@ typedef void qdio_handler_t(struct ccw_device *, unsigned int, int,
  * struct qdio_initialize - qdio initialization data
  * @q_format: queue format
  * @qdr_ac: feature flags to set
- * @adapter_name: name for the adapter
  * @qib_param_field_format: format for qib_parm_field
  * @qib_param_field: pointer to 128 bytes or NULL, if no param field
  * @qib_rflags: rflags to set
@@ -347,7 +346,6 @@ typedef void qdio_handler_t(struct ccw_device *, unsigned int, int,
 struct qdio_initialize {
 	unsigned char q_format;
 	unsigned char qdr_ac;
-	unsigned char adapter_name[8];
 	unsigned int qib_param_field_format;
 	unsigned char *qib_param_field;
 	unsigned char qib_rflags;

arch/s390/include/asm/sclp.h

@@ -114,8 +114,7 @@ int sclp_early_get_core_info(struct sclp_core_info *info);
 void sclp_early_get_ipl_info(struct sclp_ipl_info *info);
 void sclp_early_detect(void);
 void sclp_early_printk(const char *s);
-void sclp_early_printk_force(const char *s);
+void __sclp_early_printk(const char *s, unsigned int len);
-void __sclp_early_printk(const char *s, unsigned int len, unsigned int force);
 
 int sclp_early_get_memsize(unsigned long *mem);
 int sclp_early_get_hsa_size(unsigned long *hsa_size);
@@ -129,6 +128,8 @@ int sclp_chp_deconfigure(struct chp_id chpid);
 int sclp_chp_read_info(struct sclp_chp_info *info);
 int sclp_pci_configure(u32 fid);
 int sclp_pci_deconfigure(u32 fid);
+int sclp_ap_configure(u32 apid);
+int sclp_ap_deconfigure(u32 apid);
 int sclp_pci_report(struct zpci_report_error_header *report, u32 fh, u32 fid);
 int memcpy_hsa_kernel(void *dest, unsigned long src, size_t count);
 int memcpy_hsa_user(void __user *dest, unsigned long src, size_t count);

arch/s390/include/asm/set_memory.h

@@ -2,6 +2,10 @@
 #ifndef _ASMS390_SET_MEMORY_H
 #define _ASMS390_SET_MEMORY_H
 
+#include <linux/mutex.h>
+
+extern struct mutex cpa_mutex;
+
 #define SET_MEMORY_RO	1UL
 #define SET_MEMORY_RW	2UL
 #define SET_MEMORY_NX	4UL

arch/s390/include/asm/setup.h

@@ -92,7 +92,9 @@ extern int memory_end_set;
 extern unsigned long memory_end;
 extern unsigned long vmalloc_size;
 extern unsigned long max_physmem_end;
-extern unsigned long __swsusp_reset_dma;
+
+/* The Write Back bit position in the physaddr is given by the SLPC PCI */
+extern unsigned long mio_wb_bit_mask;
 
 #define MACHINE_IS_VM		(S390_lowcore.machine_flags & MACHINE_FLAG_VM)
 #define MACHINE_IS_KVM		(S390_lowcore.machine_flags & MACHINE_FLAG_KVM)
@@ -119,9 +121,6 @@ extern unsigned int console_mode;
 extern unsigned int console_devno;
 extern unsigned int console_irq;
 
-extern char vmhalt_cmd[];
-extern char vmpoff_cmd[];
-
 #define CONSOLE_IS_UNDEFINED	(console_mode == 0)
 #define CONSOLE_IS_SCLP		(console_mode == 1)
 #define CONSOLE_IS_3215		(console_mode == 2)

arch/s390/include/asm/smp.h

@@ -31,7 +31,6 @@ extern void smp_emergency_stop(void);
 extern int smp_find_processor_id(u16 address);
 extern int smp_store_status(int cpu);
 extern void smp_save_dump_cpus(void);
-extern int smp_vcpu_scheduled(int cpu);
 extern void smp_yield_cpu(int cpu);
 extern void smp_cpu_set_polarization(int cpu, int val);
 extern int smp_cpu_get_polarization(int cpu);

arch/s390/include/asm/stp.h

@@ -6,43 +6,89 @@
 #ifndef __S390_STP_H
 #define __S390_STP_H
 
+#include <linux/compiler.h>
+
 /* notifier for syncs */
 extern struct atomic_notifier_head s390_epoch_delta_notifier;
 
 /* STP interruption parameter */
 struct stp_irq_parm {
-	unsigned int _pad0	: 14;
+	u32		: 14;
-	unsigned int tsc	: 1;	/* Timing status change */
+	u32 tsc		:  1;	/* Timing status change */
-	unsigned int lac	: 1;	/* Link availability change */
+	u32 lac		:  1;	/* Link availability change */
-	unsigned int tcpc	: 1;	/* Time control parameter change */
+	u32 tcpc	:  1;	/* Time control parameter change */
-	unsigned int _pad2	: 15;
+	u32		: 15;
-} __attribute__ ((packed));
+} __packed;
 
 #define STP_OP_SYNC	1
 #define STP_OP_CTRL	3
 
 struct stp_sstpi {
-	unsigned int rsvd0;
+	u32		: 32;
-	unsigned int rsvd1 : 8;
+	u32 tu		:  1;
-	unsigned int stratum : 8;
+	u32 lu		:  1;
-	unsigned int vbits : 16;
+	u32		:  6;
-	unsigned int leaps : 16;
+	u32 stratum	:  8;
-	unsigned int tmd : 4;
+	u32 vbits	: 16;
-	unsigned int ctn : 4;
+	u32 leaps	: 16;
-	unsigned int rsvd2 : 3;
+	u32 tmd		:  4;
-	unsigned int c : 1;
+	u32 ctn		:  4;
-	unsigned int tst : 4;
+	u32		:  3;
-	unsigned int tzo : 16;
+	u32 c		:  1;
-	unsigned int dsto : 16;
+	u32 tst		:  4;
-	unsigned int ctrl : 16;
+	u32 tzo		: 16;
-	unsigned int rsvd3 : 16;
+	u32 dsto	: 16;
-	unsigned int tto;
+	u32 ctrl	: 16;
-	unsigned int rsvd4;
+	u32		: 16;
-	unsigned int ctnid[3];
+	u32 tto;
-	unsigned int rsvd5;
+	u32		: 32;
-	unsigned int todoff[4];
+	u32 ctnid[3];
-	unsigned int rsvd6[48];
+	u32		: 32;
-} __attribute__ ((packed));
+	u32 todoff[4];
+	u32 rsvd[48];
+} __packed;
+
+struct stp_tzib {
+	u32 tzan	: 16;
+	u32		: 16;
+	u32 tzo		: 16;
+	u32 dsto	: 16;
+	u32 stn;
+	u32 dstn;
+	u64 dst_on_alg;
+	u64 dst_off_alg;
+} __packed;
+
+struct stp_tcpib {
+	u32 atcode	: 4;
+	u32 ntcode	: 4;
+	u32 d		: 1;
+	u32		: 23;
+	s32 tto;
+	struct stp_tzib atzib;
+	struct stp_tzib ntzib;
+	s32 adst_offset : 16;
+	s32 ndst_offset : 16;
+	u32 rsvd1;
+	u64 ntzib_update;
+	u64 ndsto_update;
+} __packed;
+
+struct stp_lsoib {
+	u32 p		: 1;
+	u32		: 31;
+	s32 also	: 16;
+	s32 nlso	: 16;
+	u64 nlsout;
+} __packed;
+
+struct stp_stzi {
+	u32 rsvd0[3];
+	u64 data_ts;
+	u32 rsvd1[22];
+	struct stp_tcpib tcpib;
+	struct stp_lsoib lsoib;
+} __packed;
 
 /* Functions needed by the machine check handler */
 int stp_sync_check(void);

arch/s390/include/asm/tlbflush.h

@@ -30,8 +30,6 @@ static inline void __tlb_flush_idte(unsigned long asce)
 		: : "a" (opt), "a" (asce) : "cc");
 }
 
-void smp_ptlb_all(void);
-
 /*
  * Flush all TLB entries on all CPUs.
  */

arch/s390/include/asm/uaccess.h

@@ -60,6 +60,9 @@ raw_copy_to_user(void __user *to, const void *from, unsigned long n);
 #define INLINE_COPY_TO_USER
 #endif
 
+int __put_user_bad(void) __attribute__((noreturn));
+int __get_user_bad(void) __attribute__((noreturn));
+
 #ifdef CONFIG_HAVE_MARCH_Z10_FEATURES
 
 #define __put_get_user_asm(to, from, size, spec)		\
@@ -109,6 +112,9 @@ static __always_inline int __put_user_fn(void *x, void __user *ptr, unsigned lon
 					(unsigned long *)x,
 					size, spec);
 		break;
+	default:
+		__put_user_bad();
+		break;
 	}
 	return rc;
 }
@@ -139,6 +145,9 @@ static __always_inline int __get_user_fn(void *x, const void __user *ptr, unsign
 					(unsigned long __user *)ptr,
 					size, spec);
 		break;
+	default:
+		__get_user_bad();
+		break;
 	}
 	return rc;
 }
@@ -190,8 +199,6 @@ static inline int __get_user_fn(void *x, const void __user *ptr, unsigned long s
 })
 
 
-int __put_user_bad(void) __attribute__((noreturn));
-
 #define __get_user(x, ptr)					\
 ({								\
 	int __gu_err = -EFAULT;					\
@@ -238,8 +245,6 @@ int __put_user_bad(void) __attribute__((noreturn));
 	__get_user(x, ptr);					\
 })
 
-int __get_user_bad(void) __attribute__((noreturn));
-
 unsigned long __must_check
 raw_copy_in_user(void __user *to, const void __user *from, unsigned long n);
 
@@ -278,4 +283,115 @@ static inline unsigned long __must_check clear_user(void __user *to, unsigned lo
 int copy_to_user_real(void __user *dest, void *src, unsigned long count);
 void *s390_kernel_write(void *dst, const void *src, size_t size);
 
+#define HAVE_GET_KERNEL_NOFAULT
+
+int __noreturn __put_kernel_bad(void);
+
+#define __put_kernel_asm(val, to, insn)					\
+({									\
+	int __rc;							\
+									\
+	asm volatile(							\
+		"0:   " insn "  %2,%1\n"				\
+		"1:	xr	%0,%0\n"				\
+		"2:\n"							\
+		".pushsection .fixup, \"ax\"\n"				\
+		"3:	lhi	%0,%3\n"				\
+		"	jg	2b\n"					\
+		".popsection\n"						\
+		EX_TABLE(0b,3b) EX_TABLE(1b,3b)				\
+		: "=d" (__rc), "+Q" (*(to))				\
+		: "d" (val), "K" (-EFAULT)				\
+		: "cc");						\
+	__rc;								\
+})
+
+#define __put_kernel_nofault(dst, src, type, err_label)			\
+do {									\
+	u64 __x = (u64)(*((type *)(src)));				\
+	int __pk_err;							\
+									\
+	switch (sizeof(type)) {						\
+	case 1:								\
+		__pk_err = __put_kernel_asm(__x, (type *)(dst), "stc"); \
+		break;							\
+	case 2:								\
+		__pk_err = __put_kernel_asm(__x, (type *)(dst), "sth"); \
+		break;							\
+	case 4:								\
+		__pk_err = __put_kernel_asm(__x, (type *)(dst), "st");	\
+		break;							\
+	case 8:								\
+		__pk_err = __put_kernel_asm(__x, (type *)(dst), "stg"); \
+		break;							\
+	default:							\
+		__pk_err = __put_kernel_bad();				\
+		break;							\
+	}								\
+	if (unlikely(__pk_err))						\
+		goto err_label;						\
+} while (0)
+
+int __noreturn __get_kernel_bad(void);
+
+#define __get_kernel_asm(val, from, insn)				\
+({									\
+	int __rc;							\
+									\
+	asm volatile(							\
+		"0:   " insn "  %1,%2\n"				\
+		"1:	xr	%0,%0\n"				\
+		"2:\n"							\
+		".pushsection .fixup, \"ax\"\n"				\
+		"3:	lhi	%0,%3\n"				\
+		"	jg	2b\n"					\
+		".popsection\n"						\
+		EX_TABLE(0b,3b) EX_TABLE(1b,3b)				\
+		: "=d" (__rc), "+d" (val)				\
+		: "Q" (*(from)), "K" (-EFAULT)				\
+		: "cc");						\
+	__rc;								\
+})
+
+#define __get_kernel_nofault(dst, src, type, err_label)			\
+do {									\
+	int __gk_err;							\
+									\
+	switch (sizeof(type)) {						\
+	case 1: {							\
+		u8 __x = 0;						\
+									\
+		__gk_err = __get_kernel_asm(__x, (type *)(src), "ic");	\
+		*((type *)(dst)) = (type)__x;				\
+		break;							\
+	};								\
+	case 2: {							\
+		u16 __x = 0;						\
+									\
+		__gk_err = __get_kernel_asm(__x, (type *)(src), "lh");	\
+		*((type *)(dst)) = (type)__x;				\
+		break;							\
+	};								\
+	case 4: {							\
+		u32 __x = 0;						\
+									\
+		__gk_err = __get_kernel_asm(__x, (type *)(src), "l");	\
+		*((type *)(dst)) = (type)__x;				\
+		break;							\
+	};								\
+	case 8: {							\
+		u64 __x = 0;						\
+									\
+		__gk_err = __get_kernel_asm(__x, (type *)(src), "lg");	\
+		*((type *)(dst)) = (type)__x;				\
+		break;							\
+	};								\
+	default:							\
+		__gk_err = __get_kernel_bad();				\
+		break;							\
+	}								\
+	if (unlikely(__gk_err))						\
+		goto err_label;						\
+} while (0)
+
 #endif /* __S390_UACCESS_H */

arch/s390/include/asm/uv.h

@@ -33,6 +33,7 @@
 #define UVC_CMD_DESTROY_SEC_CPU		0x0121
 #define UVC_CMD_CONV_TO_SEC_STOR	0x0200
 #define UVC_CMD_CONV_FROM_SEC_STOR	0x0201
+#define UVC_CMD_DESTR_SEC_STOR		0x0202
 #define UVC_CMD_SET_SEC_CONF_PARAMS	0x0300
 #define UVC_CMD_UNPACK_IMG		0x0301
 #define UVC_CMD_VERIFY_IMG		0x0302
@@ -344,6 +345,7 @@ static inline int is_prot_virt_host(void)
 }
 
 int gmap_make_secure(struct gmap *gmap, unsigned long gaddr, void *uvcb);
+int uv_destroy_page(unsigned long paddr);
 int uv_convert_from_secure(unsigned long paddr);
 int gmap_convert_to_secure(struct gmap *gmap, unsigned long gaddr);
 
@@ -354,6 +356,11 @@ void adjust_to_uv_max(unsigned long *vmax);
 static inline void setup_uv(void) {}
 static inline void adjust_to_uv_max(unsigned long *vmax) {}
 
+static inline int uv_destroy_page(unsigned long paddr)
+{
+	return 0;
+}
+
 static inline int uv_convert_from_secure(unsigned long paddr)
 {
 	return 0;

arch/s390/include/asm/vdso.h

@@ -2,6 +2,8 @@
 #ifndef __S390_VDSO_H__
 #define __S390_VDSO_H__
 
+#include <vdso/datapage.h>
+
 /* Default link addresses for the vDSOs */
 #define VDSO32_LBASE	0
 #define VDSO64_LBASE	0
@@ -18,30 +20,7 @@
  * itself and may change without notice.
  */
 
-struct vdso_data {
-	__u64 tb_update_count;		/* Timebase atomicity ctr	0x00 */
-	__u64 xtime_tod_stamp;		/* TOD clock for xtime		0x08 */
-	__u64 xtime_clock_sec;		/* Kernel time			0x10 */
-	__u64 xtime_clock_nsec;		/*				0x18 */
-	__u64 xtime_coarse_sec;		/* Coarse kernel time		0x20 */
-	__u64 xtime_coarse_nsec;	/*				0x28 */
-	__u64 wtom_clock_sec;		/* Wall to monotonic clock	0x30 */
-	__u64 wtom_clock_nsec;		/*				0x38 */
-	__u64 wtom_coarse_sec;		/* Coarse wall to monotonic	0x40 */
-	__u64 wtom_coarse_nsec;		/*				0x48 */
-	__u32 tz_minuteswest;		/* Minutes west of Greenwich	0x50 */
-	__u32 tz_dsttime;		/* Type of dst correction	0x54 */
-	__u32 ectg_available;		/* ECTG instruction present	0x58 */
-	__u32 tk_mult;			/* Mult. used for xtime_nsec	0x5c */
-	__u32 tk_shift;			/* Shift used for xtime_nsec	0x60 */
-	__u32 ts_dir;			/* TOD steering direction	0x64 */
-	__u64 ts_end;			/* TOD steering end		0x68 */
-	__u32 hrtimer_res;		/* hrtimer resolution		0x70 */
-};
-
 struct vdso_per_cpu_data {
-	__u64 ectg_timer_base;
-	__u64 ectg_user_time;
 	/*
 	 * Note: node_id and cpu_nr must be at adjacent memory locations.
 	 * VDSO userspace must read both values with a single instruction.
@@ -56,9 +35,7 @@ struct vdso_per_cpu_data {
 };
 
 extern struct vdso_data *vdso_data;
-extern struct vdso_data boot_vdso_data;
 
-void vdso_alloc_boot_cpu(struct lowcore *lowcore);
 int vdso_alloc_per_cpu(struct lowcore *lowcore);
 void vdso_free_per_cpu(struct lowcore *lowcore);
 

arch/s390/include/asm/vdso/clocksource.h

@@ -0,0 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_VDSO_CLOCKSOURCE_H
+#define __ASM_VDSO_CLOCKSOURCE_H
+
+#define VDSO_ARCH_CLOCKMODES	\
+	VDSO_CLOCKMODE_TOD
+
+#endif /* __ASM_VDSO_CLOCKSOURCE_H */

arch/s390/include/asm/vdso/data.h

@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __S390_ASM_VDSO_DATA_H
+#define __S390_ASM_VDSO_DATA_H
+
+#include <linux/types.h>
+#include <vdso/datapage.h>
+
+struct arch_vdso_data {
+	__u64 tod_steering_delta;
+	__u64 tod_steering_end;
+};
+
+#endif /* __S390_ASM_VDSO_DATA_H */

arch/s390/include/asm/vdso/gettimeofday.h

@@ -0,0 +1,71 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef ASM_VDSO_GETTIMEOFDAY_H
+#define ASM_VDSO_GETTIMEOFDAY_H
+
+#define VDSO_HAS_TIME 1
+
+#define VDSO_HAS_CLOCK_GETRES 1
+
+#include <asm/timex.h>
+#include <asm/unistd.h>
+#include <asm/vdso.h>
+#include <linux/compiler.h>
+
+#define vdso_calc_delta __arch_vdso_calc_delta
+static __always_inline u64 __arch_vdso_calc_delta(u64 cycles, u64 last, u64 mask, u32 mult)
+{
+	return (cycles - last) * mult;
+}
+
+static __always_inline const struct vdso_data *__arch_get_vdso_data(void)
+{
+	return _vdso_data;
+}
+
+static inline u64 __arch_get_hw_counter(s32 clock_mode, const struct vdso_data *vd)
+{
+	const struct vdso_data *vdso = __arch_get_vdso_data();
+	u64 adj, now;
+
+	now = get_tod_clock();
+	adj = vdso->arch_data.tod_steering_end - now;
+	if (unlikely((s64) adj > 0))
+		now += (vdso->arch_data.tod_steering_delta < 0) ? (adj >> 15) : -(adj >> 15);
+	return now;
+}
+
+static __always_inline
+long clock_gettime_fallback(clockid_t clkid, struct __kernel_timespec *ts)
+{
+	register unsigned long r1 __asm__("r1") = __NR_clock_gettime;
+	register unsigned long r2 __asm__("r2") = (unsigned long)clkid;
+	register void *r3 __asm__("r3") = ts;
+
+	asm ("svc 0\n" : "+d" (r2) : "d" (r1), "d" (r3) : "cc", "memory");
+	return r2;
+}
+
+static __always_inline
+long gettimeofday_fallback(register struct __kernel_old_timeval *tv,
+			   register struct timezone *tz)
+{
+	register unsigned long r1 __asm__("r1") = __NR_gettimeofday;
+	register unsigned long r2 __asm__("r2") = (unsigned long)tv;
+	register void *r3 __asm__("r3") = tz;
+
+	asm ("svc 0\n" : "+d" (r2) : "d" (r1), "d" (r3) : "cc", "memory");
+	return r2;
+}
+
+static __always_inline
+long clock_getres_fallback(clockid_t clkid, struct __kernel_timespec *ts)
+{
+	register unsigned long r1 __asm__("r1") = __NR_clock_getres;
+	register unsigned long r2 __asm__("r2") = (unsigned long)clkid;
+	register void *r3 __asm__("r3") = ts;
+
+	asm ("svc 0\n" : "+d" (r2) : "d" (r1), "d" (r3) : "cc", "memory");
+	return r2;
+}
+
+#endif

arch/s390/include/asm/vdso/processor.h

@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef __ASM_VDSO_PROCESSOR_H
+#define __ASM_VDSO_PROCESSOR_H
+
+#define cpu_relax() barrier()
+
+#endif /* __ASM_VDSO_PROCESSOR_H */

arch/s390/include/asm/vdso/vsyscall.h

@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_VDSO_VSYSCALL_H
+#define __ASM_VDSO_VSYSCALL_H
+
+#ifndef __ASSEMBLY__
+
+#include <linux/hrtimer.h>
+#include <linux/timekeeper_internal.h>
+#include <vdso/datapage.h>
+#include <asm/vdso.h>
+/*
+ * Update the vDSO data page to keep in sync with kernel timekeeping.
+ */
+
+static __always_inline struct vdso_data *__s390_get_k_vdso_data(void)
+{
+	return vdso_data;
+}
+#define __arch_get_k_vdso_data __s390_get_k_vdso_data
+
+/* The asm-generic header needs to be included after the definitions above */
+#include <asm-generic/vdso/vsyscall.h>
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* __ASM_VDSO_VSYSCALL_H */

arch/s390/include/asm/vtimer.h

@@ -25,8 +25,6 @@ extern void add_virt_timer_periodic(struct vtimer_list *timer);
 extern int mod_virt_timer(struct vtimer_list *timer, u64 expires);
 extern int mod_virt_timer_periodic(struct vtimer_list *timer, u64 expires);
 extern int del_virt_timer(struct vtimer_list *timer);
-
-extern void init_cpu_vtimer(void);
 extern void vtime_init(void);
 
 #endif /* _ASM_S390_TIMER_H */

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

@@ -35,12 +35,16 @@
 #define PKEY_KEYTYPE_AES_128		      1
 #define PKEY_KEYTYPE_AES_192		      2
 #define PKEY_KEYTYPE_AES_256		      3
+#define PKEY_KEYTYPE_ECC		      4
 
 /* the newer ioctls use a pkey_key_type enum for type information */
 enum pkey_key_type {
 	PKEY_TYPE_CCA_DATA   = (__u32) 1,
 	PKEY_TYPE_CCA_CIPHER = (__u32) 2,
 	PKEY_TYPE_EP11	     = (__u32) 3,
+	PKEY_TYPE_CCA_ECC    = (__u32) 0x1f,
+	PKEY_TYPE_EP11_AES   = (__u32) 6,
+	PKEY_TYPE_EP11_ECC   = (__u32) 7,
 };
 
 /* the newer ioctls use a pkey_key_size enum for key size information */
@@ -88,6 +92,20 @@ struct pkey_clrkey {
 	__u8  clrkey[MAXCLRKEYSIZE]; /* 16, 24, or 32 byte clear key value */
 };
 
+/*
+ * EP11 key blobs of type PKEY_TYPE_EP11_AES and PKEY_TYPE_EP11_ECC
+ * are ep11 blobs prepended by this header:
+ */
+struct ep11kblob_header {
+	__u8  type;	/* always 0x00 */
+	__u8  hver;	/* header version,  currently needs to be 0x00 */
+	__u16 len;	/* total length in bytes (including this header) */
+	__u8  version;	/* PKEY_TYPE_EP11_AES or PKEY_TYPE_EP11_ECC */
+	__u8  res0;	/* unused */
+	__u16 bitlen;	/* clear key bit len, 0 for unknown */
+	__u8  res1[8];	/* unused */
+} __packed;
+
 /*
  * Generate CCA AES secure key.
  */
@@ -304,7 +322,7 @@ struct pkey_verifykey2 {
 #define PKEY_VERIFYKEY2 _IOWR(PKEY_IOCTL_MAGIC, 0x17, struct pkey_verifykey2)
 
 /*
- * Transform a key blob (of any type) into a protected key, version 2.
+ * Transform a key blob into a protected key, version 2.
  * There needs to be a list of apqns given with at least one entry in there.
  * All apqns in the list need to be exact apqns, 0xFFFF as ANY card or domain
  * is not supported. The implementation walks through the list of apqns and
@@ -313,6 +331,8 @@ struct pkey_verifykey2 {
  * list is tried until success (return 0) or the end of the list is reached
  * (return -1 with errno ENODEV). You may use the PKEY_APQNS4K ioctl to
  * generate a list of apqns based on the key.
+ * Deriving ECC protected keys from ECC secure keys is not supported with
+ * this ioctl, use PKEY_KBLOB2PROTK3 for this purpose.
  */
 struct pkey_kblob2pkey2 {
 	__u8 __user *key;	     /* in: pointer to key blob		   */
@@ -326,17 +346,17 @@ struct pkey_kblob2pkey2 {
 /*
  * Build a list of APQNs based on a key blob given.
  * Is able to find out which type of secure key is given (CCA AES secure
- * key, CCA AES cipher key or EP11 AES key) and tries to find all matching
+ * key, CCA AES cipher key, CCA ECC private key, EP11 AES key, EP11 ECC private
- * crypto cards based on the MKVP and maybe other criterias (like CCA AES
+ * key) and tries to find all matching crypto cards based on the MKVP and maybe
- * cipher keys need a CEX5C or higher, EP11 keys with BLOB_PKEY_EXTRACTABLE
+ * other criterias (like CCA AES cipher keys need a CEX5C or higher, EP11 keys
- * need a CEX7 and EP11 api version 4). The list of APQNs is further filtered
+ * with BLOB_PKEY_EXTRACTABLE need a CEX7 and EP11 api version 4). The list of
- * by the key's mkvp which needs to match to either the current mkvp (CCA and
+ * APQNs is further filtered by the key's mkvp which needs to match to either
- * EP11) or the alternate mkvp (old mkvp, CCA adapters only) of the apqns. The
+ * the current mkvp (CCA and EP11) or the alternate mkvp (old mkvp, CCA adapters
- * flags argument may be used to limit the matching apqns. If the
+ * only) of the apqns. The flags argument may be used to limit the matching
- * PKEY_FLAGS_MATCH_CUR_MKVP is given, only the current mkvp of each apqn is
+ * apqns. If the PKEY_FLAGS_MATCH_CUR_MKVP is given, only the current mkvp of
- * compared. Likewise with the PKEY_FLAGS_MATCH_ALT_MKVP. If both are given, it
+ * each apqn is compared. Likewise with the PKEY_FLAGS_MATCH_ALT_MKVP. If both
- * is assumed to return apqns where either the current or the alternate mkvp
+ * are given, it is assumed to return apqns where either the current or the
- * matches. At least one of the matching flags needs to be given.
+ * alternate mkvp matches. At least one of the matching flags needs to be given.
  * The flags argument for EP11 keys has no further action and is currently
  * ignored (but needs to be given as PKEY_FLAGS_MATCH_CUR_MKVP) as there is only
  * the wkvp from the key to match against the apqn's wkvp.
@@ -365,9 +385,10 @@ struct pkey_apqns4key {
  * restrict the list by given master key verification patterns.
  * For different key types there may be different ways to match the
  * master key verification patterns. For CCA keys (CCA data key and CCA
- * cipher key) the first 8 bytes of cur_mkvp refer to the current mkvp value
+ * cipher key) the first 8 bytes of cur_mkvp refer to the current AES mkvp value
- * of the apqn and the first 8 bytes of the alt_mkvp refer to the old mkvp.
+ * of the apqn and the first 8 bytes of the alt_mkvp refer to the old AES mkvp.
- * The flags argument controls if the apqns current and/or alternate mkvp
+ * For CCA ECC keys it is similar but the match is against the APKA current/old
+ * mkvp. The flags argument controls if the apqns current and/or alternate mkvp
  * should match. If the PKEY_FLAGS_MATCH_CUR_MKVP is given, only the current
  * mkvp of each apqn is compared. Likewise with the PKEY_FLAGS_MATCH_ALT_MKVP.
  * If both are given, it is assumed to return apqns where either the
@@ -397,4 +418,30 @@ struct pkey_apqns4keytype {
 };
 #define PKEY_APQNS4KT _IOWR(PKEY_IOCTL_MAGIC, 0x1C, struct pkey_apqns4keytype)
 
+/*
+ * Transform a key blob into a protected key, version 3.
+ * The difference to version 2 of this ioctl is that the protected key
+ * buffer is now explicitly and not within a struct pkey_protkey any more.
+ * So this ioctl is also able to handle EP11 and CCA ECC secure keys and
+ * provide ECC protected keys.
+ * There needs to be a list of apqns given with at least one entry in there.
+ * All apqns in the list need to be exact apqns, 0xFFFF as ANY card or domain
+ * is not supported. The implementation walks through the list of apqns and
+ * tries to send the request to each apqn without any further checking (like
+ * card type or online state). If the apqn fails, simple the next one in the
+ * list is tried until success (return 0) or the end of the list is reached
+ * (return -1 with errno ENODEV). You may use the PKEY_APQNS4K ioctl to
+ * generate a list of apqns based on the key.
+ */
+struct pkey_kblob2pkey3 {
+	__u8 __user *key;	     /* in: pointer to key blob		   */
+	__u32 keylen;		     /* in: key blob size		   */
+	struct pkey_apqn __user *apqns; /* in: ptr to list of apqn targets */
+	__u32 apqn_entries;	     /* in: # of apqn target list entries  */
+	__u32 pkeytype;		/* out: prot key type (enum pkey_key_type) */
+	__u32 pkeylen;	 /* in/out: size of pkey buffer/actual len of pkey */
+	__u8 __user *pkey;		 /* in: pkey blob buffer space ptr */
+};
+#define PKEY_KBLOB2PROTK3 _IOWR(PKEY_IOCTL_MAGIC, 0x1D, struct pkey_kblob2pkey3)
+
 #endif /* _UAPI_PKEY_H */

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

@@ -29,7 +29,7 @@
 	{ 0x13, "SIGP conditional emergency signal" },		\
 	{ 0x15, "SIGP sense running" },				\
 	{ 0x16, "SIGP set multithreading"},			\
-	{ 0x17, "SIGP store additional status ait address"}
+	{ 0x17, "SIGP store additional status at address"}
 
 #define icpt_prog_codes						\
 	{ 0x0001, "Prog Operation" },				\

arch/s390/kernel/Makefile

@@ -57,6 +57,7 @@ obj-$(CONFIG_COMPAT)		+= $(compat-obj-y)
 obj-$(CONFIG_EARLY_PRINTK)	+= early_printk.o
 obj-$(CONFIG_STACKTRACE)	+= stacktrace.o
 obj-$(CONFIG_KPROBES)		+= kprobes.o
+obj-$(CONFIG_KPROBES)		+= kprobes_insn_page.o
 obj-$(CONFIG_FUNCTION_TRACER)	+= mcount.o ftrace.o
 obj-$(CONFIG_CRASH_DUMP)	+= crash_dump.o
 obj-$(CONFIG_UPROBES)		+= uprobes.o

arch/s390/kernel/asm-offsets.c

@@ -59,26 +59,6 @@ int main(void)
 	OFFSET(__SF_SIE_REASON, stack_frame, empty1[2]);
 	OFFSET(__SF_SIE_FLAGS, stack_frame, empty1[3]);
 	BLANK();
-	/* timeval/timezone offsets for use by vdso */
-	OFFSET(__VDSO_UPD_COUNT, vdso_data, tb_update_count);
-	OFFSET(__VDSO_XTIME_STAMP, vdso_data, xtime_tod_stamp);
-	OFFSET(__VDSO_XTIME_SEC, vdso_data, xtime_clock_sec);
-	OFFSET(__VDSO_XTIME_NSEC, vdso_data, xtime_clock_nsec);
-	OFFSET(__VDSO_XTIME_CRS_SEC, vdso_data, xtime_coarse_sec);
-	OFFSET(__VDSO_XTIME_CRS_NSEC, vdso_data, xtime_coarse_nsec);
-	OFFSET(__VDSO_WTOM_SEC, vdso_data, wtom_clock_sec);
-	OFFSET(__VDSO_WTOM_NSEC, vdso_data, wtom_clock_nsec);
-	OFFSET(__VDSO_WTOM_CRS_SEC, vdso_data, wtom_coarse_sec);
-	OFFSET(__VDSO_WTOM_CRS_NSEC, vdso_data, wtom_coarse_nsec);
-	OFFSET(__VDSO_TIMEZONE, vdso_data, tz_minuteswest);
-	OFFSET(__VDSO_ECTG_OK, vdso_data, ectg_available);
-	OFFSET(__VDSO_TK_MULT, vdso_data, tk_mult);
-	OFFSET(__VDSO_TK_SHIFT, vdso_data, tk_shift);
-	OFFSET(__VDSO_TS_DIR, vdso_data, ts_dir);
-	OFFSET(__VDSO_TS_END, vdso_data, ts_end);
-	OFFSET(__VDSO_CLOCK_REALTIME_RES, vdso_data, hrtimer_res);
-	OFFSET(__VDSO_ECTG_BASE, vdso_per_cpu_data, ectg_timer_base);
-	OFFSET(__VDSO_ECTG_USER, vdso_per_cpu_data, ectg_user_time);
 	OFFSET(__VDSO_GETCPU_VAL, vdso_per_cpu_data, getcpu_val);
 	BLANK();
 	/* constants used by the vdso */

arch/s390/kernel/crash_dump.c

@@ -141,7 +141,7 @@ int copy_oldmem_kernel(void *dst, void *src, size_t count)
 	while (count) {
 		from = __pa(src);
 		if (!OLDMEM_BASE && from < sclp.hsa_size) {
-			/* Copy from zfcpdump HSA area */
+			/* Copy from zfcp/nvme dump HSA area */
 			len = min(count, sclp.hsa_size - from);
 			rc = memcpy_hsa_kernel(dst, from, len);
 			if (rc)
@@ -184,7 +184,7 @@ static int copy_oldmem_user(void __user *dst, void *src, size_t count)
 	while (count) {
 		from = __pa(src);
 		if (!OLDMEM_BASE && from < sclp.hsa_size) {
-			/* Copy from zfcpdump HSA area */
+			/* Copy from zfcp/nvme dump HSA area */
 			len = min(count, sclp.hsa_size - from);
 			rc = memcpy_hsa_user(dst, from, len);
 			if (rc)
@@ -258,7 +258,7 @@ static int remap_oldmem_pfn_range_kdump(struct vm_area_struct *vma,
 }
 
 /*
- * Remap "oldmem" for zfcpdump
+ * Remap "oldmem" for zfcp/nvme dump
  *
  * We only map available memory above HSA size. Memory below HSA size
  * is read on demand using the copy_oldmem_page() function.
@@ -283,7 +283,7 @@ static int remap_oldmem_pfn_range_zfcpdump(struct vm_area_struct *vma,
 }
 
 /*
- * Remap "oldmem" for kdump or zfcpdump
+ * Remap "oldmem" for kdump or zfcp/nvme dump
  */
 int remap_oldmem_pfn_range(struct vm_area_struct *vma, unsigned long from,
 			   unsigned long pfn, unsigned long size, pgprot_t prot)
@@ -632,11 +632,11 @@ int elfcorehdr_alloc(unsigned long long *addr, unsigned long long *size)
 	u32 alloc_size;
 	u64 hdr_off;
 
-	/* If we are not in kdump or zfcpdump mode return */
+	/* If we are not in kdump or zfcp/nvme dump mode return */
-	if (!OLDMEM_BASE && ipl_info.type != IPL_TYPE_FCP_DUMP)
+	if (!OLDMEM_BASE && !is_ipl_type_dump())
 		return 0;
-	/* If we cannot get HSA size for zfcpdump return error */
+	/* If we cannot get HSA size for zfcp/nvme dump return error */
-	if (ipl_info.type == IPL_TYPE_FCP_DUMP && !sclp.hsa_size)
+	if (is_ipl_type_dump() && !sclp.hsa_size)
 		return -ENODEV;
 
 	/* For kdump, exclude previous crashkernel memory */

arch/s390/kernel/diag.c

@@ -104,18 +104,7 @@ static const struct seq_operations show_diag_stat_sops = {
 	.show	= show_diag_stat,
 };
 
-static int show_diag_stat_open(struct inode *inode, struct file *file)
+DEFINE_SEQ_ATTRIBUTE(show_diag_stat);
-{
-	return seq_open(file, &show_diag_stat_sops);
-}
-
-static const struct file_operations show_diag_stat_fops = {
-	.open		= show_diag_stat_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
-
 
 static int __init show_diag_stat_init(void)
 {

arch/s390/kernel/dis.c

@@ -482,31 +482,37 @@ static int print_insn(char *buffer, unsigned char *code, unsigned long addr)
 	return (int) (ptr - buffer);
 }
 
+static int copy_from_regs(struct pt_regs *regs, void *dst, void *src, int len)
+{
+	if (user_mode(regs)) {
+		if (copy_from_user(dst, (char __user *)src, len))
+			return -EFAULT;
+	} else {
+		if (copy_from_kernel_nofault(dst, src, len))
+			return -EFAULT;
+	}
+	return 0;
+}
+
 void show_code(struct pt_regs *regs)
 {
 	char *mode = user_mode(regs) ? "User" : "Krnl";
 	unsigned char code[64];
 	char buffer[128], *ptr;
-	mm_segment_t old_fs;
 	unsigned long addr;
 	int start, end, opsize, hops, i;
 
 	/* Get a snapshot of the 64 bytes surrounding the fault address. */
-	old_fs = get_fs();
-	set_fs(user_mode(regs) ? USER_DS : KERNEL_DS);
 	for (start = 32; start && regs->psw.addr >= 34 - start; start -= 2) {
 		addr = regs->psw.addr - 34 + start;
-		if (__copy_from_user(code + start - 2,
+		if (copy_from_regs(regs, code + start - 2, (void *)addr, 2))
-				     (char __user *) addr, 2))
 			break;
 	}
 	for (end = 32; end < 64; end += 2) {
 		addr = regs->psw.addr + end - 32;
-		if (__copy_from_user(code + end,
+		if (copy_from_regs(regs, code + end, (void *)addr, 2))
-				     (char __user *) addr, 2))
 			break;
 	}
-	set_fs(old_fs);
 	/* Code snapshot useable ? */
 	if ((regs->psw.addr & 1) || start >= end) {
 		printk("%s Code: Bad PSW.\n", mode);

arch/s390/kernel/early.c

@@ -274,19 +274,6 @@ static int __init disable_vector_extension(char *str)
 }
 early_param("novx", disable_vector_extension);
 
-static int __init cad_setup(char *str)
-{
-	bool enabled;
-	int rc;
-
-	rc = kstrtobool(str, &enabled);
-	if (!rc && enabled && test_facility(128))
-		/* Enable problem state CAD. */
-		__ctl_set_bit(2, 3);
-	return rc;
-}
-early_param("cad", cad_setup);
-
 char __bootdata(early_command_line)[COMMAND_LINE_SIZE];
 static void __init setup_boot_command_line(void)
 {

arch/s390/kernel/early_printk.c

@@ -10,7 +10,7 @@
 
 static void sclp_early_write(struct console *con, const char *s, unsigned int len)
 {
-	__sclp_early_printk(s, len, 0);
+	__sclp_early_printk(s, len);
 }
 
 static struct console sclp_early_console = {

arch/s390/kernel/entry.S

@@ -435,10 +435,8 @@ ENTRY(system_call)
 	jz	.Lsysc_skip_fpu
 	brasl	%r14,load_fpu_regs
 .Lsysc_skip_fpu:
-	lg	%r14,__LC_VDSO_PER_CPU
 	mvc	__LC_RETURN_PSW(16),__PT_PSW(%r11)
 	stpt	__LC_EXIT_TIMER
-	mvc	__VDSO_ECTG_BASE(16,%r14),__LC_EXIT_TIMER
 	lmg	%r0,%r15,__PT_R0(%r11)
 	b	__LC_RETURN_LPSWE
 
@@ -797,13 +795,11 @@ ENTRY(io_int_handler)
 	TRACE_IRQS_ON
 0:
 #endif
-	lg	%r14,__LC_VDSO_PER_CPU
 	mvc	__LC_RETURN_PSW(16),__PT_PSW(%r11)
 	tm	__PT_PSW+1(%r11),0x01	# returning to user ?
 	jno	.Lio_exit_kernel
 	BPEXIT	__TI_flags(%r12),_TIF_ISOLATE_BP
 	stpt	__LC_EXIT_TIMER
-	mvc	__VDSO_ECTG_BASE(16,%r14),__LC_EXIT_TIMER
 .Lio_exit_kernel:
 	lmg	%r0,%r15,__PT_R0(%r11)
 	b	__LC_RETURN_LPSWE
@@ -1213,14 +1209,12 @@ ENTRY(mcck_int_handler)
 	brasl	%r14,s390_handle_mcck
 	TRACE_IRQS_ON
 .Lmcck_return:
-	lg	%r14,__LC_VDSO_PER_CPU
 	lmg	%r0,%r10,__PT_R0(%r11)
 	mvc	__LC_RETURN_MCCK_PSW(16),__PT_PSW(%r11) # move return PSW
 	tm	__LC_RETURN_MCCK_PSW+1,0x01 # returning to user ?
 	jno	0f
 	BPEXIT	__TI_flags(%r12),_TIF_ISOLATE_BP
 	stpt	__LC_EXIT_TIMER
-	mvc	__VDSO_ECTG_BASE(16,%r14),__LC_EXIT_TIMER
 0:	lmg	%r11,%r15,__PT_R11(%r11)
 	b	__LC_RETURN_MCCK_LPSWE
 

arch/s390/kernel/entry.h

@@ -9,7 +9,6 @@
 #include <asm/idle.h>
 
 extern void *restart_stack;
-extern unsigned long suspend_zero_pages;
 
 void system_call(void);
 void pgm_check_handler(void);
@@ -17,7 +16,6 @@ void ext_int_handler(void);
 void io_int_handler(void);
 void mcck_int_handler(void);
 void restart_int_handler(void);
-void restart_call_handler(void);
 
 asmlinkage long do_syscall_trace_enter(struct pt_regs *regs);
 asmlinkage void do_syscall_trace_exit(struct pt_regs *regs);
@@ -62,12 +60,10 @@ void do_notify_resume(struct pt_regs *regs);
 void __init init_IRQ(void);
 void do_IRQ(struct pt_regs *regs, int irq);
 void do_restart(void);
-void __init startup_init_nobss(void);
 void __init startup_init(void);
 void die(struct pt_regs *regs, const char *str);
 int setup_profiling_timer(unsigned int multiplier);
 void __init time_init(void);
-void s390_early_resume(void);
 unsigned long prepare_ftrace_return(unsigned long parent, unsigned long sp, unsigned long ip);
 
 struct s390_mmap_arg_struct;
@@ -92,4 +88,6 @@ void set_fs_fixup(void);
 unsigned long stack_alloc(void);
 void stack_free(unsigned long stack);
 
+extern char kprobes_insn_page[];
+
 #endif /* _ENTRY_H */

arch/s390/kernel/ipl.c

@@ -40,10 +40,12 @@
 #define IPL_FCP_STR		"fcp"
 #define IPL_FCP_DUMP_STR	"fcp_dump"
 #define IPL_NVME_STR		"nvme"
+#define IPL_NVME_DUMP_STR	"nvme_dump"
 #define IPL_NSS_STR		"nss"
 
 #define DUMP_CCW_STR		"ccw"
 #define DUMP_FCP_STR		"fcp"
+#define DUMP_NVME_STR		"nvme"
 #define DUMP_NONE_STR		"none"
 
 /*
@@ -96,6 +98,8 @@ static char *ipl_type_str(enum ipl_type type)
 		return IPL_NSS_STR;
 	case IPL_TYPE_NVME:
 		return IPL_NVME_STR;
+	case IPL_TYPE_NVME_DUMP:
+		return IPL_NVME_DUMP_STR;
 	case IPL_TYPE_UNKNOWN:
 	default:
 		return IPL_UNKNOWN_STR;
@@ -106,6 +110,7 @@ enum dump_type {
 	DUMP_TYPE_NONE	= 1,
 	DUMP_TYPE_CCW	= 2,
 	DUMP_TYPE_FCP	= 4,
+	DUMP_TYPE_NVME	= 8,
 };
 
 static char *dump_type_str(enum dump_type type)
@@ -117,6 +122,8 @@ static char *dump_type_str(enum dump_type type)
 		return DUMP_CCW_STR;
 	case DUMP_TYPE_FCP:
 		return DUMP_FCP_STR;
+	case DUMP_TYPE_NVME:
+		return DUMP_NVME_STR;
 	default:
 		return NULL;
 	}
@@ -144,10 +151,12 @@ static struct ipl_parameter_block *reipl_block_actual;
 static int dump_capabilities = DUMP_TYPE_NONE;
 static enum dump_type dump_type = DUMP_TYPE_NONE;
 static struct ipl_parameter_block *dump_block_fcp;
+static struct ipl_parameter_block *dump_block_nvme;
 static struct ipl_parameter_block *dump_block_ccw;
 
 static struct sclp_ipl_info sclp_ipl_info;
 
+static bool reipl_nvme_clear;
 static bool reipl_fcp_clear;
 static bool reipl_ccw_clear;
 
@@ -266,6 +275,9 @@ static __init enum ipl_type get_ipl_type(void)
 		else
 			return IPL_TYPE_FCP;
 	case IPL_PBT_NVME:
+		if (ipl_block.nvme.opt == IPL_PB0_NVME_OPT_DUMP)
+			return IPL_TYPE_NVME_DUMP;
+		else
 			return IPL_TYPE_NVME;
 	}
 	return IPL_TYPE_UNKNOWN;
@@ -324,6 +336,7 @@ static ssize_t sys_ipl_device_show(struct kobject *kobj,
 	case IPL_TYPE_FCP_DUMP:
 		return sprintf(page, "0.0.%04x\n", ipl_block.fcp.devno);
 	case IPL_TYPE_NVME:
+	case IPL_TYPE_NVME_DUMP:
 		return sprintf(page, "%08ux\n", ipl_block.nvme.fid);
 	default:
 		return 0;
@@ -531,6 +544,7 @@ static int __init ipl_init(void)
 		rc = sysfs_create_group(&ipl_kset->kobj, &ipl_fcp_attr_group);
 		break;
 	case IPL_TYPE_NVME:
+	case IPL_TYPE_NVME_DUMP:
 		rc = sysfs_create_group(&ipl_kset->kobj, &ipl_nvme_attr_group);
 		break;
 	default:
@@ -873,6 +887,24 @@ static struct attribute_group reipl_nvme_attr_group = {
 	.bin_attrs = reipl_nvme_bin_attrs
 };
 
+static ssize_t reipl_nvme_clear_show(struct kobject *kobj,
+				     struct kobj_attribute *attr, char *page)
+{
+	return sprintf(page, "%u\n", reipl_nvme_clear);
+}
+
+static ssize_t reipl_nvme_clear_store(struct kobject *kobj,
+				      struct kobj_attribute *attr,
+				      const char *buf, size_t len)
+{
+	if (strtobool(buf, &reipl_nvme_clear) < 0)
+		return -EINVAL;
+	return len;
+}
+
+static struct kobj_attribute sys_reipl_nvme_clear_attr =
+	__ATTR(clear, 0644, reipl_nvme_clear_show, reipl_nvme_clear_store);
+
 /* CCW reipl device attributes */
 DEFINE_IPL_CCW_ATTR_RW(reipl_ccw, device, reipl_block_ccw->ccw);
 
@@ -1099,7 +1131,10 @@ static void __reipl_run(void *unused)
 		break;
 	case IPL_TYPE_NVME:
 		diag308(DIAG308_SET, reipl_block_nvme);
+		if (reipl_nvme_clear)
 			diag308(DIAG308_LOAD_CLEAR, NULL);
+		else
+			diag308(DIAG308_LOAD_NORMAL, NULL);
 		break;
 	case IPL_TYPE_NSS:
 		diag308(DIAG308_SET, reipl_block_nss);
@@ -1109,6 +1144,7 @@ static void __reipl_run(void *unused)
 		diag308(DIAG308_LOAD_CLEAR, NULL);
 		break;
 	case IPL_TYPE_FCP_DUMP:
+	case IPL_TYPE_NVME_DUMP:
 		break;
 	}
 	disabled_wait();
@@ -1219,8 +1255,9 @@ static int __init reipl_fcp_init(void)
 				       &sys_reipl_fcp_clear_attr.attr);
 		if (rc)
 			goto out2;
-	} else
+	} else {
 		reipl_fcp_clear = true;
+	}
 
 	if (ipl_info.type == IPL_TYPE_FCP) {
 		memcpy(reipl_block_fcp, &ipl_block, sizeof(ipl_block));
@@ -1266,10 +1303,16 @@ static int __init reipl_nvme_init(void)
 	}
 
 	rc = sysfs_create_group(&reipl_nvme_kset->kobj, &reipl_nvme_attr_group);
-	if (rc) {
+	if (rc)
-		kset_unregister(reipl_nvme_kset);
+		goto out1;
-		free_page((unsigned long) reipl_block_nvme);
+
-		return rc;
+	if (test_facility(141)) {
+		rc = sysfs_create_file(&reipl_nvme_kset->kobj,
+				       &sys_reipl_nvme_clear_attr.attr);
+		if (rc)
+			goto out2;
+	} else {
+		reipl_nvme_clear = true;
 	}
 
 	if (ipl_info.type == IPL_TYPE_NVME) {
@@ -1290,6 +1333,13 @@ static int __init reipl_nvme_init(void)
 	}
 	reipl_capabilities |= IPL_TYPE_NVME;
 	return 0;
+
+out2:
+	sysfs_remove_group(&reipl_nvme_kset->kobj, &reipl_nvme_attr_group);
+out1:
+	kset_unregister(reipl_nvme_kset);
+	free_page((unsigned long) reipl_block_nvme);
+	return rc;
 }
 
 static int __init reipl_type_init(void)
@@ -1382,6 +1432,29 @@ static struct attribute_group dump_fcp_attr_group = {
 	.attrs = dump_fcp_attrs,
 };
 
+/* NVME dump device attributes */
+DEFINE_IPL_ATTR_RW(dump_nvme, fid, "0x%08llx\n", "%llx\n",
+		   dump_block_nvme->nvme.fid);
+DEFINE_IPL_ATTR_RW(dump_nvme, nsid, "0x%08llx\n", "%llx\n",
+		   dump_block_nvme->nvme.nsid);
+DEFINE_IPL_ATTR_RW(dump_nvme, bootprog, "%lld\n", "%llx\n",
+		   dump_block_nvme->nvme.bootprog);
+DEFINE_IPL_ATTR_RW(dump_nvme, br_lba, "%lld\n", "%llx\n",
+		   dump_block_nvme->nvme.br_lba);
+
+static struct attribute *dump_nvme_attrs[] = {
+	&sys_dump_nvme_fid_attr.attr,
+	&sys_dump_nvme_nsid_attr.attr,
+	&sys_dump_nvme_bootprog_attr.attr,
+	&sys_dump_nvme_br_lba_attr.attr,
+	NULL,
+};
+
+static struct attribute_group dump_nvme_attr_group = {
+	.name  = IPL_NVME_STR,
+	.attrs = dump_nvme_attrs,
+};
+
 /* CCW dump device attributes */
 DEFINE_IPL_CCW_ATTR_RW(dump_ccw, device, dump_block_ccw->ccw);
 
@@ -1423,6 +1496,8 @@ static ssize_t dump_type_store(struct kobject *kobj,
 		rc = dump_set_type(DUMP_TYPE_CCW);
 	else if (strncmp(buf, DUMP_FCP_STR, strlen(DUMP_FCP_STR)) == 0)
 		rc = dump_set_type(DUMP_TYPE_FCP);
+	else if (strncmp(buf, DUMP_NVME_STR, strlen(DUMP_NVME_STR)) == 0)
+		rc = dump_set_type(DUMP_TYPE_NVME);
 	return (rc != 0) ? rc : len;
 }
 
@@ -1450,6 +1525,9 @@ static void __dump_run(void *unused)
 	case DUMP_TYPE_FCP:
 		diag308_dump(dump_block_fcp);
 		break;
+	case DUMP_TYPE_NVME:
+		diag308_dump(dump_block_nvme);
+		break;
 	default:
 		break;
 	}
@@ -1506,6 +1584,29 @@ static int __init dump_fcp_init(void)
 	return 0;
 }
 
+static int __init dump_nvme_init(void)
+{
+	int rc;
+
+	if (!sclp_ipl_info.has_dump)
+		return 0; /* LDIPL DUMP is not installed */
+	dump_block_nvme = (void *) get_zeroed_page(GFP_KERNEL);
+	if (!dump_block_nvme)
+		return -ENOMEM;
+	rc = sysfs_create_group(&dump_kset->kobj, &dump_nvme_attr_group);
+	if (rc) {
+		free_page((unsigned long)dump_block_nvme);
+		return rc;
+	}
+	dump_block_nvme->hdr.len = IPL_BP_NVME_LEN;
+	dump_block_nvme->hdr.version = IPL_PARM_BLOCK_VERSION;
+	dump_block_nvme->fcp.len = IPL_BP0_NVME_LEN;
+	dump_block_nvme->fcp.pbt = IPL_PBT_NVME;
+	dump_block_nvme->fcp.opt = IPL_PB0_NVME_OPT_DUMP;
+	dump_capabilities |= DUMP_TYPE_NVME;
+	return 0;
+}
+
 static int __init dump_init(void)
 {
 	int rc;
@@ -1522,6 +1623,9 @@ static int __init dump_init(void)
 	if (rc)
 		return rc;
 	rc = dump_fcp_init();
+	if (rc)
+		return rc;
+	rc = dump_nvme_init();
 	if (rc)
 		return rc;
 	dump_set_type(DUMP_TYPE_NONE);
@@ -1956,6 +2060,7 @@ void __init setup_ipl(void)
 		ipl_info.data.fcp.lun = ipl_block.fcp.lun;
 		break;
 	case IPL_TYPE_NVME:
+	case IPL_TYPE_NVME_DUMP:
 		ipl_info.data.nvme.fid = ipl_block.nvme.fid;
 		ipl_info.data.nvme.nsid = ipl_block.nvme.nsid;
 		break;

arch/s390/kernel/kprobes.c

@@ -7,6 +7,7 @@
  * s390 port, used ppc64 as template. Mike Grundy <grundym@us.ibm.com>
  */
 
+#include <linux/moduleloader.h>
 #include <linux/kprobes.h>
 #include <linux/ptrace.h>
 #include <linux/preempt.h>
@@ -21,6 +22,7 @@
 #include <asm/set_memory.h>
 #include <asm/sections.h>
 #include <asm/dis.h>
+#include "entry.h"
 
 DEFINE_PER_CPU(struct kprobe *, current_kprobe);
 DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
@@ -30,19 +32,32 @@ struct kretprobe_blackpoint kretprobe_blacklist[] = { };
 DEFINE_INSN_CACHE_OPS(s390_insn);
 
 static int insn_page_in_use;
-static char insn_page[PAGE_SIZE] __aligned(PAGE_SIZE);
+
+void *alloc_insn_page(void)
+{
+	void *page;
+
+	page = module_alloc(PAGE_SIZE);
+	if (!page)
+		return NULL;
+	__set_memory((unsigned long) page, 1, SET_MEMORY_RO | SET_MEMORY_X);
+	return page;
+}
+
+void free_insn_page(void *page)
+{
+	module_memfree(page);
+}
 
 static void *alloc_s390_insn_page(void)
 {
 	if (xchg(&insn_page_in_use, 1) == 1)
 		return NULL;
-	set_memory_x((unsigned long) &insn_page, 1);
+	return &kprobes_insn_page;
-	return &insn_page;
 }
 
 static void free_s390_insn_page(void *page)
 {
-	set_memory_nx((unsigned long) page, 1);
 	xchg(&insn_page_in_use, 0);
 }
 
@@ -56,25 +71,29 @@ struct kprobe_insn_cache kprobe_s390_insn_slots = {
 
 static void copy_instruction(struct kprobe *p)
 {
+	kprobe_opcode_t insn[MAX_INSN_SIZE];
 	s64 disp, new_disp;
 	u64 addr, new_addr;
+	unsigned int len;
 
-	memcpy(p->ainsn.insn, p->addr, insn_length(*p->addr >> 8));
+	len = insn_length(*p->addr >> 8);
-	p->opcode = p->ainsn.insn[0];
+	memcpy(&insn, p->addr, len);
-	if (!probe_is_insn_relative_long(p->ainsn.insn))
+	p->opcode = insn[0];
-		return;
+	if (probe_is_insn_relative_long(&insn[0])) {
 		/*
-	 * For pc-relative instructions in RIL-b or RIL-c format patch the
+		 * For pc-relative instructions in RIL-b or RIL-c format patch
-	 * RI2 displacement field. We have already made sure that the insn
+		 * the RI2 displacement field. We have already made sure that
-	 * slot for the patched instruction is within the same 2GB area
+		 * the insn slot for the patched instruction is within the same
-	 * as the original instruction (either kernel image or module area).
+		 * 2GB area as the original instruction (either kernel image or
-	 * Therefore the new displacement will always fit.
+		 * module area). Therefore the new displacement will always fit.
 		 */
-	disp = *(s32 *)&p->ainsn.insn[1];
+		disp = *(s32 *)&insn[1];
 		addr = (u64)(unsigned long)p->addr;
 		new_addr = (u64)(unsigned long)p->ainsn.insn;
 		new_disp = ((addr + (disp * 2)) - new_addr) / 2;
-	*(s32 *)&p->ainsn.insn[1] = new_disp;
+		*(s32 *)&insn[1] = new_disp;
+	}
+	s390_kernel_write(p->ainsn.insn, &insn, len);
 }
 NOKPROBE_SYMBOL(copy_instruction);
 

arch/s390/kernel/kprobes_insn_page.S

@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#include <linux/linkage.h>
+
+/*
+ * insn_page is a special 4k aligned dummy function for kprobes.
+ * It will contain all kprobed instructions that are out-of-line executed.
+ * The page must be within the kernel image to guarantee that the
+ * out-of-line instructions are within 2GB distance of their original
+ * location. Using a dummy function ensures that the insn_page is within
+ * the text section of the kernel and mapped read-only/executable from
+ * the beginning on, thus avoiding to split large mappings if the page
+ * would be in the data section instead.
+ */
+	.section .kprobes.text, "ax"
+	.align 4096
+ENTRY(kprobes_insn_page)
+	.rept 2048
+	.word 0x07fe
+	.endr
+ENDPROC(kprobes_insn_page)
+	.previous

arch/s390/kernel/setup.c

@@ -102,7 +102,6 @@ struct mem_detect_info __bootdata(mem_detect);
 
 struct exception_table_entry *__bootdata_preserved(__start_dma_ex_table);
 struct exception_table_entry *__bootdata_preserved(__stop_dma_ex_table);
-unsigned long __bootdata_preserved(__swsusp_reset_dma);
 unsigned long __bootdata_preserved(__stext_dma);
 unsigned long __bootdata_preserved(__etext_dma);
 unsigned long __bootdata_preserved(__sdma);
@@ -119,6 +118,7 @@ EXPORT_SYMBOL(VMALLOC_END);
 
 struct page *vmemmap;
 EXPORT_SYMBOL(vmemmap);
+unsigned long vmemmap_size;
 
 unsigned long MODULES_VADDR;
 unsigned long MODULES_END;
@@ -127,6 +127,12 @@ unsigned long MODULES_END;
 struct lowcore *lowcore_ptr[NR_CPUS];
 EXPORT_SYMBOL(lowcore_ptr);
 
+/*
+ * The Write Back bit position in the physaddr is given by the SLPC PCI.
+ * Leaving the mask zero always uses write through which is safe
+ */
+unsigned long mio_wb_bit_mask __ro_after_init;
+
 /*
  * This is set up by the setup-routine at boot-time
  * for S390 need to find out, what we have to setup
@@ -245,7 +251,7 @@ static void __init conmode_default(void)
 #ifdef CONFIG_CRASH_DUMP
 static void __init setup_zfcpdump(void)
 {
-	if (ipl_info.type != IPL_TYPE_FCP_DUMP)
+	if (!is_ipl_type_dump())
 		return;
 	if (OLDMEM_BASE)
 		return;
@@ -300,7 +306,7 @@ void machine_power_off(void)
 void (*pm_power_off)(void) = machine_power_off;
 EXPORT_SYMBOL_GPL(pm_power_off);
 
-void *restart_stack __section(.data);
+void *restart_stack;
 
 unsigned long stack_alloc(void)
 {
@@ -366,8 +372,12 @@ void __init arch_call_rest_init(void)
 
 static void __init setup_lowcore_dat_off(void)
 {
+	unsigned long int_psw_mask = PSW_KERNEL_BITS;
 	struct lowcore *lc;
 
+	if (IS_ENABLED(CONFIG_KASAN))
+		int_psw_mask |= PSW_MASK_DAT;
+
 	/*
 	 * Setup lowcore for boot cpu
 	 */
@@ -379,15 +389,15 @@ static void __init setup_lowcore_dat_off(void)
 
 	lc->restart_psw.mask = PSW_KERNEL_BITS;
 	lc->restart_psw.addr = (unsigned long) restart_int_handler;
-	lc->external_new_psw.mask = PSW_KERNEL_BITS | PSW_MASK_MCHECK;
+	lc->external_new_psw.mask = int_psw_mask | PSW_MASK_MCHECK;
 	lc->external_new_psw.addr = (unsigned long) ext_int_handler;
-	lc->svc_new_psw.mask = PSW_KERNEL_BITS | PSW_MASK_MCHECK;
+	lc->svc_new_psw.mask = int_psw_mask | PSW_MASK_MCHECK;
 	lc->svc_new_psw.addr = (unsigned long) system_call;
-	lc->program_new_psw.mask = PSW_KERNEL_BITS | PSW_MASK_MCHECK;
+	lc->program_new_psw.mask = int_psw_mask | PSW_MASK_MCHECK;
 	lc->program_new_psw.addr = (unsigned long) pgm_check_handler;
 	lc->mcck_new_psw.mask = PSW_KERNEL_BITS;
 	lc->mcck_new_psw.addr = (unsigned long) mcck_int_handler;
-	lc->io_new_psw.mask = PSW_KERNEL_BITS | PSW_MASK_MCHECK;
+	lc->io_new_psw.mask = int_psw_mask | PSW_MASK_MCHECK;
 	lc->io_new_psw.addr = (unsigned long) io_int_handler;
 	lc->clock_comparator = clock_comparator_max;
 	lc->nodat_stack = ((unsigned long) &init_thread_union)
@@ -402,7 +412,6 @@ static void __init setup_lowcore_dat_off(void)
 	memcpy(lc->alt_stfle_fac_list, S390_lowcore.alt_stfle_fac_list,
 	       sizeof(lc->alt_stfle_fac_list));
 	nmi_alloc_boot_cpu(lc);
-	vdso_alloc_boot_cpu(lc);
 	lc->sync_enter_timer = S390_lowcore.sync_enter_timer;
 	lc->async_enter_timer = S390_lowcore.async_enter_timer;
 	lc->exit_timer = S390_lowcore.exit_timer;
@@ -552,22 +561,17 @@ static void __init setup_memory_end(void)
 	unsigned long vmax, tmp;
 
 	/* Choose kernel address space layout: 3 or 4 levels. */
-	if (IS_ENABLED(CONFIG_KASAN)) {
-		vmax = IS_ENABLED(CONFIG_KASAN_S390_4_LEVEL_PAGING)
-			   ? _REGION1_SIZE
-			   : _REGION2_SIZE;
-	} else {
 	tmp = (memory_end ?: max_physmem_end) / PAGE_SIZE;
 	tmp = tmp * (sizeof(struct page) + PAGE_SIZE);
 	if (tmp + vmalloc_size + MODULES_LEN <= _REGION2_SIZE)
 		vmax = _REGION2_SIZE; /* 3-level kernel page table */
 	else
 		vmax = _REGION1_SIZE; /* 4-level kernel page table */
-	}
-
 	if (is_prot_virt_host())
 		adjust_to_uv_max(&vmax);
-
+#ifdef CONFIG_KASAN
+	vmax = kasan_vmax;
+#endif
 	/* module area is at the end of the kernel address space. */
 	MODULES_END = vmax;
 	MODULES_VADDR = MODULES_END - MODULES_LEN;
@@ -586,8 +590,13 @@ static void __init setup_memory_end(void)
 	/* Take care that memory_end is set and <= vmemmap */
 	memory_end = min(memory_end ?: max_physmem_end, (unsigned long)vmemmap);
 #ifdef CONFIG_KASAN
-	/* fit in kasan shadow memory region between 1:1 and vmemmap */
 	memory_end = min(memory_end, KASAN_SHADOW_START);
+#endif
+	vmemmap_size = SECTION_ALIGN_UP(memory_end / PAGE_SIZE) * sizeof(struct page);
+#ifdef CONFIG_KASAN
+	/* move vmemmap above kasan shadow only if stands in a way */
+	if (KASAN_SHADOW_END > (unsigned long)vmemmap &&
+	    (unsigned long)vmemmap + vmemmap_size > KASAN_SHADOW_START)
 		vmemmap = max(vmemmap, (struct page *)KASAN_SHADOW_END);
 #endif
 	max_pfn = max_low_pfn = PFN_DOWN(memory_end);
@@ -1133,7 +1142,6 @@ void __init setup_arch(char **cmdline_p)
 	free_mem_detect_info();
 	remove_oldmem();
 
-	if (is_prot_virt_host())
 	setup_uv();
 	setup_memory_end();
 	setup_memory();
@@ -1178,7 +1186,7 @@ void __init setup_arch(char **cmdline_p)
 	if (IS_ENABLED(CONFIG_EXPOLINE))
 		nospec_init_branches();
 
-	/* Setup zfcpdump support */
+	/* Setup zfcp/nvme dump support */
 	setup_zfcpdump();
 
 	/* Add system specific data to the random pool */

arch/s390/kernel/smp.c

@@ -606,14 +606,14 @@ int smp_store_status(int cpu)
 /*
  * Collect CPU state of the previous, crashed system.
  * There are four cases:
- * 1) standard zfcp dump
+ * 1) standard zfcp/nvme dump
- *    condition: OLDMEM_BASE == NULL && ipl_info.type == IPL_TYPE_FCP_DUMP
+ *    condition: OLDMEM_BASE == NULL && is_ipl_type_dump() == true
  *    The state for all CPUs except the boot CPU needs to be collected
  *    with sigp stop-and-store-status. The boot CPU state is located in
  *    the absolute lowcore of the memory stored in the HSA. The zcore code
  *    will copy the boot CPU state from the HSA.
- * 2) stand-alone kdump for SCSI (zfcp dump with swapped memory)
+ * 2) stand-alone kdump for SCSI/NVMe (zfcp/nvme dump with swapped memory)
- *    condition: OLDMEM_BASE != NULL && ipl_info.type == IPL_TYPE_FCP_DUMP
+ *    condition: OLDMEM_BASE != NULL && is_ipl_type_dump() == true
  *    The state for all CPUs except the boot CPU needs to be collected
  *    with sigp stop-and-store-status. The firmware or the boot-loader
  *    stored the registers of the boot CPU in the absolute lowcore in the
@@ -660,7 +660,7 @@ void __init smp_save_dump_cpus(void)
 	unsigned long page;
 	bool is_boot_cpu;
 
-	if (!(OLDMEM_BASE || ipl_info.type == IPL_TYPE_FCP_DUMP))
+	if (!(OLDMEM_BASE || is_ipl_type_dump()))
 		/* No previous system present, normal boot. */
 		return;
 	/* Allocate a page as dumping area for the store status sigps */
@@ -686,7 +686,7 @@ void __init smp_save_dump_cpus(void)
 			/* Get the vector registers */
 			smp_save_cpu_vxrs(sa, addr, is_boot_cpu, page);
 		/*
-		 * For a zfcp dump OLDMEM_BASE == NULL and the registers
+		 * For a zfcp/nvme dump OLDMEM_BASE == NULL and the registers
 		 * of the boot CPU are stored in the HSA. To retrieve
 		 * these registers an SCLP request is required which is
 		 * done by drivers/s390/char/zcore.c:init_cpu_info()

arch/s390/kernel/time.c

@@ -41,6 +41,9 @@
 #include <linux/gfp.h>
 #include <linux/kprobes.h>
 #include <linux/uaccess.h>
+#include <vdso/vsyscall.h>
+#include <vdso/clocksource.h>
+#include <vdso/helpers.h>
 #include <asm/facility.h>
 #include <asm/delay.h>
 #include <asm/div64.h>
@@ -84,7 +87,7 @@ void __init time_early_init(void)
 
 	/* Initialize TOD steering parameters */
 	tod_steering_end = *(unsigned long long *) &tod_clock_base[1];
-	vdso_data->ts_end = tod_steering_end;
+	vdso_data->arch_data.tod_steering_end = tod_steering_end;
 
 	if (!test_facility(28))
 		return;
@@ -257,6 +260,7 @@ static struct clocksource clocksource_tod = {
 	.mult		= 1000,
 	.shift		= 12,
 	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
+	.vdso_clock_mode = VDSO_CLOCKMODE_TOD,
 };
 
 struct clocksource * __init clocksource_default_clock(void)
@@ -264,56 +268,6 @@ struct clocksource * __init clocksource_default_clock(void)
 	return &clocksource_tod;
 }
 
-void update_vsyscall(struct timekeeper *tk)
-{
-	u64 nsecps;
-
-	if (tk->tkr_mono.clock != &clocksource_tod)
-		return;
-
-	/* Make userspace gettimeofday spin until we're done. */
-	++vdso_data->tb_update_count;
-	smp_wmb();
-	vdso_data->xtime_tod_stamp = tk->tkr_mono.cycle_last;
-	vdso_data->xtime_clock_sec = tk->xtime_sec;
-	vdso_data->xtime_clock_nsec = tk->tkr_mono.xtime_nsec;
-	vdso_data->wtom_clock_sec =
-		tk->xtime_sec + tk->wall_to_monotonic.tv_sec;
-	vdso_data->wtom_clock_nsec = tk->tkr_mono.xtime_nsec +
-		+ ((u64) tk->wall_to_monotonic.tv_nsec << tk->tkr_mono.shift);
-	nsecps = (u64) NSEC_PER_SEC << tk->tkr_mono.shift;
-	while (vdso_data->wtom_clock_nsec >= nsecps) {
-		vdso_data->wtom_clock_nsec -= nsecps;
-		vdso_data->wtom_clock_sec++;
-	}
-
-	vdso_data->xtime_coarse_sec = tk->xtime_sec;
-	vdso_data->xtime_coarse_nsec =
-		(long)(tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift);
-	vdso_data->wtom_coarse_sec =
-		vdso_data->xtime_coarse_sec + tk->wall_to_monotonic.tv_sec;
-	vdso_data->wtom_coarse_nsec =
-		vdso_data->xtime_coarse_nsec + tk->wall_to_monotonic.tv_nsec;
-	while (vdso_data->wtom_coarse_nsec >= NSEC_PER_SEC) {
-		vdso_data->wtom_coarse_nsec -= NSEC_PER_SEC;
-		vdso_data->wtom_coarse_sec++;
-	}
-
-	vdso_data->tk_mult = tk->tkr_mono.mult;
-	vdso_data->tk_shift = tk->tkr_mono.shift;
-	vdso_data->hrtimer_res = hrtimer_resolution;
-	smp_wmb();
-	++vdso_data->tb_update_count;
-}
-
-extern struct timezone sys_tz;
-
-void update_vsyscall_tz(void)
-{
-	vdso_data->tz_minuteswest = sys_tz.tz_minuteswest;
-	vdso_data->tz_dsttime = sys_tz.tz_dsttime;
-}
-
 /*
  * Initialize the TOD clock and the CPU timer of
  * the boot cpu.
@@ -342,11 +296,12 @@ void __init time_init(void)
 }
 
 static DEFINE_PER_CPU(atomic_t, clock_sync_word);
-static DEFINE_MUTEX(clock_sync_mutex);
+static DEFINE_MUTEX(stp_mutex);
 static unsigned long clock_sync_flags;
 
 #define CLOCK_SYNC_HAS_STP		0
 #define CLOCK_SYNC_STP			1
+#define CLOCK_SYNC_STPINFO_VALID	2
 
 /*
  * The get_clock function for the physical clock. It will get the current
@@ -431,7 +386,6 @@ static void clock_sync_global(unsigned long long delta)
 		/* Epoch overflow */
 		tod_clock_base[0]++;
 	/* Adjust TOD steering parameters. */
-	vdso_data->tb_update_count++;
 	now = get_tod_clock();
 	adj = tod_steering_end - now;
 	if (unlikely((s64) adj >= 0))
@@ -443,9 +397,8 @@ static void clock_sync_global(unsigned long long delta)
 		panic("TOD clock sync offset %lli is too large to drift\n",
 		      tod_steering_delta);
 	tod_steering_end = now + (abs(tod_steering_delta) << 15);
-	vdso_data->ts_dir = (tod_steering_delta < 0) ? 0 : 1;
+	vdso_data->arch_data.tod_steering_end = tod_steering_end;
-	vdso_data->ts_end = tod_steering_end;
+
-	vdso_data->tb_update_count++;
 	/* Update LPAR offset. */
 	if (ptff_query(PTFF_QTO) && ptff(&qto, sizeof(qto), PTFF_QTO) == 0)
 		lpar_offset = qto.tod_epoch_difference;
@@ -492,7 +445,6 @@ static struct stp_sstpi stp_info;
 static void *stp_page;
 
 static void stp_work_fn(struct work_struct *work);
-static DEFINE_MUTEX(stp_work_mutex);
 static DECLARE_WORK(stp_work, stp_work_fn);
 static struct timer_list stp_timer;
 
@@ -583,10 +535,26 @@ void stp_queue_work(void)
 	queue_work(time_sync_wq, &stp_work);
 }
 
+static int __store_stpinfo(void)
+{
+	int rc = chsc_sstpi(stp_page, &stp_info, sizeof(struct stp_sstpi));
+
+	if (rc)
+		clear_bit(CLOCK_SYNC_STPINFO_VALID, &clock_sync_flags);
+	else
+		set_bit(CLOCK_SYNC_STPINFO_VALID, &clock_sync_flags);
+	return rc;
+}
+
+static int stpinfo_valid(void)
+{
+	return stp_online && test_bit(CLOCK_SYNC_STPINFO_VALID, &clock_sync_flags);
+}
+
 static int stp_sync_clock(void *data)
 {
 	struct clock_sync_data *sync = data;
-	unsigned long long clock_delta;
+	unsigned long long clock_delta, flags;
 	static int first;
 	int rc;
 
@@ -599,16 +567,17 @@ static int stp_sync_clock(void *data)
 		if (stp_info.todoff[0] || stp_info.todoff[1] ||
 		    stp_info.todoff[2] || stp_info.todoff[3] ||
 		    stp_info.tmd != 2) {
+			flags = vdso_update_begin();
 			rc = chsc_sstpc(stp_page, STP_OP_SYNC, 0,
 					&clock_delta);
 			if (rc == 0) {
 				sync->clock_delta = clock_delta;
 				clock_sync_global(clock_delta);
-				rc = chsc_sstpi(stp_page, &stp_info,
+				rc = __store_stpinfo();
-						sizeof(struct stp_sstpi));
 				if (rc == 0 && stp_info.tmd != 2)
 					rc = -EAGAIN;
 			}
+			vdso_update_end(flags);
 		}
 		sync->in_sync = rc ? -EAGAIN : 1;
 		xchg(&first, 0);
@@ -628,6 +597,81 @@ static int stp_sync_clock(void *data)
 	return 0;
 }
 
+static int stp_clear_leap(void)
+{
+	struct __kernel_timex txc;
+	int ret;
+
+	memset(&txc, 0, sizeof(txc));
+
+	ret = do_adjtimex(&txc);
+	if (ret < 0)
+		return ret;
+
+	txc.modes = ADJ_STATUS;
+	txc.status &= ~(STA_INS|STA_DEL);
+	return do_adjtimex(&txc);
+}
+
+static void stp_check_leap(void)
+{
+	struct stp_stzi stzi;
+	struct stp_lsoib *lsoib = &stzi.lsoib;
+	struct __kernel_timex txc;
+	int64_t timediff;
+	int leapdiff, ret;
+
+	if (!stp_info.lu || !check_sync_clock()) {
+		/*
+		 * Either a scheduled leap second was removed by the operator,
+		 * or STP is out of sync. In both cases, clear the leap second
+		 * kernel flags.
+		 */
+		if (stp_clear_leap() < 0)
+			pr_err("failed to clear leap second flags\n");
+		return;
+	}
+
+	if (chsc_stzi(stp_page, &stzi, sizeof(stzi))) {
+		pr_err("stzi failed\n");
+		return;
+	}
+
+	timediff = tod_to_ns(lsoib->nlsout - get_tod_clock()) / NSEC_PER_SEC;
+	leapdiff = lsoib->nlso - lsoib->also;
+
+	if (leapdiff != 1 && leapdiff != -1) {
+		pr_err("Cannot schedule %d leap seconds\n", leapdiff);
+		return;
+	}
+
+	if (timediff < 0) {
+		if (stp_clear_leap() < 0)
+			pr_err("failed to clear leap second flags\n");
+	} else if (timediff < 7200) {
+		memset(&txc, 0, sizeof(txc));
+		ret = do_adjtimex(&txc);
+		if (ret < 0)
+			return;
+
+		txc.modes = ADJ_STATUS;
+		if (leapdiff > 0)
+			txc.status |= STA_INS;
+		else
+			txc.status |= STA_DEL;
+		ret = do_adjtimex(&txc);
+		if (ret < 0)
+			pr_err("failed to set leap second flags\n");
+		/* arm Timer to clear leap second flags */
+		mod_timer(&stp_timer, jiffies + msecs_to_jiffies(14400 * MSEC_PER_SEC));
+	} else {
+		/* The day the leap second is scheduled for hasn't been reached. Retry
+		 * in one hour.
+		 */
+		mod_timer(&stp_timer, jiffies + msecs_to_jiffies(3600 * MSEC_PER_SEC));
+	}
+}
+
 /*
  * STP work. Check for the STP state and take over the clock
  * synchronization if the STP clock source is usable.
@@ -638,7 +682,7 @@ static void stp_work_fn(struct work_struct *work)
 	int rc;
 
 	/* prevent multiple execution. */
-	mutex_lock(&stp_work_mutex);
+	mutex_lock(&stp_mutex);
 
 	if (!stp_online) {
 		chsc_sstpc(stp_page, STP_OP_CTRL, 0x0000, NULL);
@@ -646,23 +690,22 @@ static void stp_work_fn(struct work_struct *work)
 		goto out_unlock;
 	}
 
-	rc = chsc_sstpc(stp_page, STP_OP_CTRL, 0xb0e0, NULL);
+	rc = chsc_sstpc(stp_page, STP_OP_CTRL, 0xf0e0, NULL);
 	if (rc)
 		goto out_unlock;
 
-	rc = chsc_sstpi(stp_page, &stp_info, sizeof(struct stp_sstpi));
+	rc = __store_stpinfo();
 	if (rc || stp_info.c == 0)
 		goto out_unlock;
 
 	/* Skip synchronization if the clock is already in sync. */
-	if (check_sync_clock())
+	if (!check_sync_clock()) {
-		goto out_unlock;
-
 		memset(&stp_sync, 0, sizeof(stp_sync));
 		cpus_read_lock();
 		atomic_set(&stp_sync.cpus, num_online_cpus() - 1);
 		stop_machine_cpuslocked(stp_sync_clock, &stp_sync, cpu_online_mask);
 		cpus_read_unlock();
+	}
 
 	if (!check_sync_clock())
 		/*
@@ -670,9 +713,11 @@ static void stp_work_fn(struct work_struct *work)
 		 * Retry after a second.
 		 */
 		mod_timer(&stp_timer, jiffies + msecs_to_jiffies(MSEC_PER_SEC));
+	else if (stp_info.lu)
+		stp_check_leap();
 
 out_unlock:
-	mutex_unlock(&stp_work_mutex);
+	mutex_unlock(&stp_mutex);
 }
 
 /*
@@ -687,10 +732,14 @@ static ssize_t ctn_id_show(struct device *dev,
 				struct device_attribute *attr,
 				char *buf)
 {
-	if (!stp_online)
+	ssize_t ret = -ENODATA;
-		return -ENODATA;
+
-	return sprintf(buf, "%016llx\n",
+	mutex_lock(&stp_mutex);
+	if (stpinfo_valid())
+		ret = sprintf(buf, "%016llx\n",
 			      *(unsigned long long *) stp_info.ctnid);
+	mutex_unlock(&stp_mutex);
+	return ret;
 }
 
 static DEVICE_ATTR_RO(ctn_id);
@@ -699,9 +748,13 @@ static ssize_t ctn_type_show(struct device *dev,
 				struct device_attribute *attr,
 				char *buf)
 {
-	if (!stp_online)
+	ssize_t ret = -ENODATA;
-		return -ENODATA;
+
-	return sprintf(buf, "%i\n", stp_info.ctn);
+	mutex_lock(&stp_mutex);
+	if (stpinfo_valid())
+		ret = sprintf(buf, "%i\n", stp_info.ctn);
+	mutex_unlock(&stp_mutex);
+	return ret;
 }
 
 static DEVICE_ATTR_RO(ctn_type);
@@ -710,9 +763,13 @@ static ssize_t dst_offset_show(struct device *dev,
 				   struct device_attribute *attr,
 				   char *buf)
 {
-	if (!stp_online || !(stp_info.vbits & 0x2000))
+	ssize_t ret = -ENODATA;
-		return -ENODATA;
+
-	return sprintf(buf, "%i\n", (int)(s16) stp_info.dsto);
+	mutex_lock(&stp_mutex);
+	if (stpinfo_valid() && (stp_info.vbits & 0x2000))
+		ret = sprintf(buf, "%i\n", (int)(s16) stp_info.dsto);
+	mutex_unlock(&stp_mutex);
+	return ret;
 }
 
 static DEVICE_ATTR_RO(dst_offset);
@@ -721,20 +778,56 @@ static ssize_t leap_seconds_show(struct device *dev,
 					struct device_attribute *attr,
 					char *buf)
 {
-	if (!stp_online || !(stp_info.vbits & 0x8000))
+	ssize_t ret = -ENODATA;
-		return -ENODATA;
+
-	return sprintf(buf, "%i\n", (int)(s16) stp_info.leaps);
+	mutex_lock(&stp_mutex);
+	if (stpinfo_valid() && (stp_info.vbits & 0x8000))
+		ret = sprintf(buf, "%i\n", (int)(s16) stp_info.leaps);
+	mutex_unlock(&stp_mutex);
+	return ret;
 }
 
 static DEVICE_ATTR_RO(leap_seconds);
 
+static ssize_t leap_seconds_scheduled_show(struct device *dev,
+						struct device_attribute *attr,
+						char *buf)
+{
+	struct stp_stzi stzi;
+	ssize_t ret;
+
+	mutex_lock(&stp_mutex);
+	if (!stpinfo_valid() || !(stp_info.vbits & 0x8000) || !stp_info.lu) {
+		mutex_unlock(&stp_mutex);
+		return -ENODATA;
+	}
+
+	ret = chsc_stzi(stp_page, &stzi, sizeof(stzi));
+	mutex_unlock(&stp_mutex);
+	if (ret < 0)
+		return ret;
+
+	if (!stzi.lsoib.p)
+		return sprintf(buf, "0,0\n");
+
+	return sprintf(buf, "%llu,%d\n",
+		       tod_to_ns(stzi.lsoib.nlsout - TOD_UNIX_EPOCH) / NSEC_PER_SEC,
+		       stzi.lsoib.nlso - stzi.lsoib.also);
+}
+
+static DEVICE_ATTR_RO(leap_seconds_scheduled);
+
 static ssize_t stratum_show(struct device *dev,
 				struct device_attribute *attr,
 				char *buf)
 {
-	if (!stp_online)
+	ssize_t ret = -ENODATA;
-		return -ENODATA;
+
-	return sprintf(buf, "%i\n", (int)(s16) stp_info.stratum);
+	mutex_lock(&stp_mutex);
+	if (stpinfo_valid())
+		ret = sprintf(buf, "%i\n", (int)(s16) stp_info.stratum);
+	mutex_unlock(&stp_mutex);
+	return ret;
 }
 
 static DEVICE_ATTR_RO(stratum);
@@ -743,9 +836,13 @@ static ssize_t time_offset_show(struct device *dev,
 				struct device_attribute *attr,
 				char *buf)
 {
-	if (!stp_online || !(stp_info.vbits & 0x0800))
+	ssize_t ret = -ENODATA;
-		return -ENODATA;
+
-	return sprintf(buf, "%i\n", (int) stp_info.tto);
+	mutex_lock(&stp_mutex);
+	if (stpinfo_valid() && (stp_info.vbits & 0x0800))
+		ret = sprintf(buf, "%i\n", (int) stp_info.tto);
+	mutex_unlock(&stp_mutex);
+	return ret;
 }
 
 static DEVICE_ATTR_RO(time_offset);
@@ -754,9 +851,13 @@ static ssize_t time_zone_offset_show(struct device *dev,
 				struct device_attribute *attr,
 				char *buf)
 {
-	if (!stp_online || !(stp_info.vbits & 0x4000))
+	ssize_t ret = -ENODATA;
-		return -ENODATA;
+
-	return sprintf(buf, "%i\n", (int)(s16) stp_info.tzo);
+	mutex_lock(&stp_mutex);
+	if (stpinfo_valid() && (stp_info.vbits & 0x4000))
+		ret = sprintf(buf, "%i\n", (int)(s16) stp_info.tzo);
+	mutex_unlock(&stp_mutex);
+	return ret;
 }
 
 static DEVICE_ATTR_RO(time_zone_offset);
@@ -765,9 +866,13 @@ static ssize_t timing_mode_show(struct device *dev,
 				struct device_attribute *attr,
 				char *buf)
 {
-	if (!stp_online)
+	ssize_t ret = -ENODATA;
-		return -ENODATA;
+
-	return sprintf(buf, "%i\n", stp_info.tmd);
+	mutex_lock(&stp_mutex);
+	if (stpinfo_valid())
+		ret = sprintf(buf, "%i\n", stp_info.tmd);
+	mutex_unlock(&stp_mutex);
+	return ret;
 }
 
 static DEVICE_ATTR_RO(timing_mode);
@@ -776,9 +881,13 @@ static ssize_t timing_state_show(struct device *dev,
 				struct device_attribute *attr,
 				char *buf)
 {
-	if (!stp_online)
+	ssize_t ret = -ENODATA;
-		return -ENODATA;
+
-	return sprintf(buf, "%i\n", stp_info.tst);
+	mutex_lock(&stp_mutex);
+	if (stpinfo_valid())
+		ret = sprintf(buf, "%i\n", stp_info.tst);
+	mutex_unlock(&stp_mutex);
+	return ret;
 }
 
 static DEVICE_ATTR_RO(timing_state);
@@ -801,14 +910,14 @@ static ssize_t online_store(struct device *dev,
 		return -EINVAL;
 	if (!test_bit(CLOCK_SYNC_HAS_STP, &clock_sync_flags))
 		return -EOPNOTSUPP;
-	mutex_lock(&clock_sync_mutex);
+	mutex_lock(&stp_mutex);
 	stp_online = value;
 	if (stp_online)
 		set_bit(CLOCK_SYNC_STP, &clock_sync_flags);
 	else
 		clear_bit(CLOCK_SYNC_STP, &clock_sync_flags);
 	queue_work(time_sync_wq, &stp_work);
-	mutex_unlock(&clock_sync_mutex);
+	mutex_unlock(&stp_mutex);
 	return count;
 }
 
@@ -824,6 +933,7 @@ static struct device_attribute *stp_attributes[] = {
 	&dev_attr_dst_offset,
 	&dev_attr_leap_seconds,
 	&dev_attr_online,
+	&dev_attr_leap_seconds_scheduled,
 	&dev_attr_stratum,
 	&dev_attr_time_offset,
 	&dev_attr_time_zone_offset,

arch/s390/kernel/uv.c

@@ -26,33 +26,10 @@ int __bootdata_preserved(prot_virt_guest);
 struct uv_info __bootdata_preserved(uv_info);
 
 #if IS_ENABLED(CONFIG_KVM)
-int prot_virt_host;
+int __bootdata_preserved(prot_virt_host);
 EXPORT_SYMBOL(prot_virt_host);
 EXPORT_SYMBOL(uv_info);
 
-static int __init prot_virt_setup(char *val)
-{
-	bool enabled;
-	int rc;
-
-	rc = kstrtobool(val, &enabled);
-	if (!rc && enabled)
-		prot_virt_host = 1;
-
-	if (is_prot_virt_guest() && prot_virt_host) {
-		prot_virt_host = 0;
-		pr_warn("Protected virtualization not available in protected guests.");
-	}
-
-	if (prot_virt_host && !test_facility(158)) {
-		prot_virt_host = 0;
-		pr_warn("Protected virtualization not supported by the hardware.");
-	}
-
-	return rc;
-}
-early_param("prot_virt", prot_virt_setup);
-
 static int __init uv_init(unsigned long stor_base, unsigned long stor_len)
 {
 	struct uv_cb_init uvcb = {
@@ -74,6 +51,24 @@ void __init setup_uv(void)
 {
 	unsigned long uv_stor_base;
 
+	/*
+	 * keep these conditions in line with kasan init code has_uv_sec_stor_limit()
+	 */
+	if (!is_prot_virt_host())
+		return;
+
+	if (is_prot_virt_guest()) {
+		prot_virt_host = 0;
+		pr_warn("Protected virtualization not available in protected guests.");
+		return;
+	}
+
+	if (!test_facility(158)) {
+		prot_virt_host = 0;
+		pr_warn("Protected virtualization not supported by the hardware.");
+		return;
+	}
+
 	uv_stor_base = (unsigned long)memblock_alloc_try_nid(
 		uv_info.uv_base_stor_len, SZ_1M, SZ_2G,
 		MEMBLOCK_ALLOC_ACCESSIBLE, NUMA_NO_NODE);
@@ -98,6 +93,7 @@ void __init setup_uv(void)
 
 void adjust_to_uv_max(unsigned long *vmax)
 {
+	if (uv_info.max_sec_stor_addr)
 		*vmax = min_t(unsigned long, *vmax, uv_info.max_sec_stor_addr);
 }
 
@@ -118,6 +114,26 @@ static int uv_pin_shared(unsigned long paddr)
 	return 0;
 }
 
+/*
+ * Requests the Ultravisor to destroy a guest page and make it
+ * accessible to the host. The destroy clears the page instead of
+ * exporting.
+ *
+ * @paddr: Absolute host address of page to be destroyed
+ */
+int uv_destroy_page(unsigned long paddr)
+{
+	struct uv_cb_cfs uvcb = {
+		.header.cmd = UVC_CMD_DESTR_SEC_STOR,
+		.header.len = sizeof(uvcb),
+		.paddr = paddr
+	};
+
+	if (uv_call(0, (u64)&uvcb))
+		return -EINVAL;
+	return 0;
+}
+
 /*
  * Requests the Ultravisor to encrypt a guest page and make it
  * accessible to the host for paging (export).

arch/s390/kernel/vdso.c

@@ -20,6 +20,8 @@
 #include <linux/security.h>
 #include <linux/memblock.h>
 #include <linux/compat.h>
+#include <linux/binfmts.h>
+#include <vdso/datapage.h>
 #include <asm/asm-offsets.h>
 #include <asm/processor.h>
 #include <asm/mmu.h>
@@ -96,35 +98,12 @@ static union {
 	struct vdso_data	data;
 	u8			page[PAGE_SIZE];
 } vdso_data_store __page_aligned_data;
-struct vdso_data *vdso_data = &vdso_data_store.data;
+struct vdso_data *vdso_data = (struct vdso_data *)&vdso_data_store.data;
-
-/*
- * Setup vdso data page.
- */
-static void __init vdso_init_data(struct vdso_data *vd)
-{
-	vd->ectg_available = test_facility(31);
-}
-
 /*
  * Allocate/free per cpu vdso data.
  */
 #define SEGMENT_ORDER	2
 
-/*
- * The initial vdso_data structure for the boot CPU. Eventually
- * it is replaced with a properly allocated structure in vdso_init.
- * This is necessary because a valid S390_lowcore.vdso_per_cpu_data
- * pointer is required to be able to return from an interrupt or
- * program check. See the exit paths in entry.S.
- */
-struct vdso_data boot_vdso_data __initdata;
-
-void __init vdso_alloc_boot_cpu(struct lowcore *lowcore)
-{
-	lowcore->vdso_per_cpu_data = (unsigned long) &boot_vdso_data;
-}
-
 int vdso_alloc_per_cpu(struct lowcore *lowcore)
 {
 	unsigned long segment_table, page_table, page_frame;
@@ -246,8 +225,6 @@ static int __init vdso_init(void)
 {
 	int i;
 
-	vdso_init_data(vdso_data);
-
 	/* Calculate the size of the 64 bit vDSO */
 	vdso64_pages = ((&vdso64_end - &vdso64_start
 			 + PAGE_SIZE - 1) >> PAGE_SHIFT) + 1;

arch/s390/kernel/vdso64/Makefile

@@ -1,17 +1,23 @@
 # SPDX-License-Identifier: GPL-2.0
-# List of files in the vdso, has to be asm only for now
+# List of files in the vdso
 
 KCOV_INSTRUMENT := n
+ARCH_REL_TYPE_ABS := R_390_COPY|R_390_GLOB_DAT|R_390_JMP_SLOT|R_390_RELATIVE
+ARCH_REL_TYPE_ABS += R_390_GOT|R_390_PLT
 
-obj-vdso64 = gettimeofday.o clock_getres.o clock_gettime.o note.o getcpu.o
+include $(srctree)/lib/vdso/Makefile
+obj-vdso64 = vdso_user_wrapper.o note.o getcpu.o
+obj-cvdso64 = vdso64_generic.o
+CFLAGS_REMOVE_vdso64_generic.o = -pg $(CC_FLAGS_FTRACE) $(CC_FLAGS_EXPOLINE)
 
 # Build rules
 
-targets := $(obj-vdso64) vdso64.so vdso64.so.dbg
+targets := $(obj-vdso64) $(obj-cvdso64) vdso64.so vdso64.so.dbg
 obj-vdso64 := $(addprefix $(obj)/, $(obj-vdso64))
+obj-cvdso64 := $(addprefix $(obj)/, $(obj-cvdso64))
 
 KBUILD_AFLAGS += -DBUILD_VDSO
-KBUILD_CFLAGS += -DBUILD_VDSO
+KBUILD_CFLAGS += -DBUILD_VDSO -DDISABLE_BRANCH_PROFILING
 
 KBUILD_AFLAGS_64 := $(filter-out -m64,$(KBUILD_AFLAGS))
 KBUILD_AFLAGS_64 += -m64 -s
@@ -37,7 +43,7 @@ KASAN_SANITIZE := n
 $(obj)/vdso64_wrapper.o : $(obj)/vdso64.so
 
 # link rule for the .so file, .lds has to be first
-$(obj)/vdso64.so.dbg: $(obj)/vdso64.lds $(obj-vdso64) FORCE
+$(obj)/vdso64.so.dbg: $(src)/vdso64.lds $(obj-vdso64) $(obj-cvdso64) FORCE
 	$(call if_changed,ld)
 
 # strip rule for the .so file
@@ -49,9 +55,14 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE
 $(obj-vdso64): %.o: %.S FORCE
 	$(call if_changed_dep,vdso64as)
 
+$(obj-cvdso64): %.o: %.c FORCE
+	$(call if_changed_dep,vdso64cc)
+
 # actual build commands
 quiet_cmd_vdso64as = VDSO64A $@
       cmd_vdso64as = $(CC) $(a_flags) -c -o $@ $<
+quiet_cmd_vdso64cc = VDSO64C $@
+      cmd_vdso64cc = $(CC) $(c_flags) -c -o $@ $<
 
 # install commands for the unstripped file
 quiet_cmd_vdso_install = INSTALL $@

arch/s390/kernel/vdso64/clock_getres.S

@@ -1,50 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Userland implementation of clock_getres() for 64 bits processes in a
- * s390 kernel for use in the vDSO
- *
- *  Copyright IBM Corp. 2008
- *  Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com)
- */
-#include <asm/vdso.h>
-#include <asm/asm-offsets.h>
-#include <asm/unistd.h>
-#include <asm/dwarf.h>
-
-	.text
-	.align 4
-	.globl __kernel_clock_getres
-	.type  __kernel_clock_getres,@function
-__kernel_clock_getres:
-	CFI_STARTPROC
-	larl	%r1,3f
-	lg	%r0,0(%r1)
-	cghi	%r2,__CLOCK_REALTIME_COARSE
-	je	0f
-	cghi	%r2,__CLOCK_MONOTONIC_COARSE
-	je	0f
-	larl	%r1,_vdso_data
-	llgf	%r0,__VDSO_CLOCK_REALTIME_RES(%r1)
-	cghi	%r2,__CLOCK_REALTIME
-	je	0f
-	cghi	%r2,__CLOCK_MONOTONIC
-	je	0f
-	cghi	%r2,__CLOCK_THREAD_CPUTIME_ID
-	je	0f
-	cghi	%r2,-2		/* Per-thread CPUCLOCK with PID=0, VIRT=1 */
-	jne	2f
-	larl	%r5,_vdso_data
-	icm	%r0,15,__LC_ECTG_OK(%r5)
-	jz	2f
-0:	ltgr	%r3,%r3
-	jz	1f				/* res == NULL */
-	xc	0(8,%r3),0(%r3)			/* set tp->tv_sec to zero */
-	stg	%r0,8(%r3)			/* store tp->tv_usec */
-1:	lghi	%r2,0
-	br	%r14
-2:	lghi	%r1,__NR_clock_getres		/* fallback to svc */
-	svc	0
-	br	%r14
-	CFI_ENDPROC
-3:	.quad	__CLOCK_COARSE_RES
-	.size	__kernel_clock_getres,.-__kernel_clock_getres

arch/s390/kernel/vdso64/clock_gettime.S

@@ -1,163 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Userland implementation of clock_gettime() for 64 bits processes in a
- * s390 kernel for use in the vDSO
- *
- *  Copyright IBM Corp. 2008
- *  Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com)
- */
-#include <asm/vdso.h>
-#include <asm/asm-offsets.h>
-#include <asm/unistd.h>
-#include <asm/dwarf.h>
-#include <asm/ptrace.h>
-
-	.text
-	.align 4
-	.globl __kernel_clock_gettime
-	.type  __kernel_clock_gettime,@function
-__kernel_clock_gettime:
-	CFI_STARTPROC
-	aghi	%r15,-16
-	CFI_DEF_CFA_OFFSET STACK_FRAME_OVERHEAD+16
-	CFI_VAL_OFFSET 15, -STACK_FRAME_OVERHEAD
-	larl	%r5,_vdso_data
-	cghi	%r2,__CLOCK_REALTIME_COARSE
-	je	4f
-	cghi	%r2,__CLOCK_REALTIME
-	je	5f
-	cghi	%r2,-3		/* Per-thread CPUCLOCK with PID=0, VIRT=1 */
-	je	9f
-	cghi	%r2,__CLOCK_MONOTONIC_COARSE
-	je	3f
-	cghi	%r2,__CLOCK_MONOTONIC
-	jne	12f
-
-	/* CLOCK_MONOTONIC */
-0:	lg	%r4,__VDSO_UPD_COUNT(%r5)	/* load update counter */
-	tmll	%r4,0x0001			/* pending update ? loop */
-	jnz	0b
-	stcke	0(%r15)				/* Store TOD clock */
-	lgf	%r2,__VDSO_TK_SHIFT(%r5)	/* Timekeeper shift */
-	lg	%r0,__VDSO_WTOM_SEC(%r5)
-	lg	%r1,1(%r15)
-	sg	%r1,__VDSO_XTIME_STAMP(%r5)	/* TOD - cycle_last */
-	msgf	%r1,__VDSO_TK_MULT(%r5)		/*  * tk->mult */
-	alg	%r1,__VDSO_WTOM_NSEC(%r5)
-	srlg	%r1,%r1,0(%r2)			/*  >> tk->shift */
-	clg	%r4,__VDSO_UPD_COUNT(%r5)	/* check update counter */
-	jne	0b
-	larl	%r5,13f
-1:	clg	%r1,0(%r5)
-	jl	2f
-	slg	%r1,0(%r5)
-	aghi	%r0,1
-	j	1b
-2:	stg	%r0,0(%r3)			/* store tp->tv_sec */
-	stg	%r1,8(%r3)			/* store tp->tv_nsec */
-	lghi	%r2,0
-	aghi	%r15,16
-	CFI_DEF_CFA_OFFSET STACK_FRAME_OVERHEAD
-	CFI_RESTORE 15
-	br	%r14
-
-	/* CLOCK_MONOTONIC_COARSE */
-	CFI_DEF_CFA_OFFSET STACK_FRAME_OVERHEAD+16
-	CFI_VAL_OFFSET 15, -STACK_FRAME_OVERHEAD
-3:	lg	%r4,__VDSO_UPD_COUNT(%r5)	/* load update counter */
-	tmll	%r4,0x0001			/* pending update ? loop */
-	jnz	3b
-	lg	%r0,__VDSO_WTOM_CRS_SEC(%r5)
-	lg	%r1,__VDSO_WTOM_CRS_NSEC(%r5)
-	clg	%r4,__VDSO_UPD_COUNT(%r5)	/* check update counter */
-	jne	3b
-	j	2b
-
-	/* CLOCK_REALTIME_COARSE */
-4:	lg	%r4,__VDSO_UPD_COUNT(%r5)	/* load update counter */
-	tmll	%r4,0x0001			/* pending update ? loop */
-	jnz	4b
-	lg	%r0,__VDSO_XTIME_CRS_SEC(%r5)
-	lg	%r1,__VDSO_XTIME_CRS_NSEC(%r5)
-	clg	%r4,__VDSO_UPD_COUNT(%r5)	/* check update counter */
-	jne	4b
-	j	7f
-
-	/* CLOCK_REALTIME */
-5:	lg	%r4,__VDSO_UPD_COUNT(%r5)	/* load update counter */
-	tmll	%r4,0x0001			/* pending update ? loop */
-	jnz	5b
-	stcke	0(%r15)				/* Store TOD clock */
-	lg	%r1,1(%r15)
-	lg	%r0,__VDSO_TS_END(%r5)		/* TOD steering end time */
-	slgr	%r0,%r1				/* now - ts_steering_end */
-	ltgr	%r0,%r0				/* past end of steering ? */
-	jm	17f
-	srlg	%r0,%r0,15			/* 1 per 2^16 */
-	tm	__VDSO_TS_DIR+3(%r5),0x01	/* steering direction? */
-	jz	18f
-	lcgr	%r0,%r0				/* negative TOD offset */
-18:	algr	%r1,%r0				/* add steering offset */
-17:	lgf	%r2,__VDSO_TK_SHIFT(%r5)	/* Timekeeper shift */
-	sg	%r1,__VDSO_XTIME_STAMP(%r5)	/* TOD - cycle_last */
-	msgf	%r1,__VDSO_TK_MULT(%r5)		/*  * tk->mult */
-	alg	%r1,__VDSO_XTIME_NSEC(%r5)	/*  + tk->xtime_nsec */
-	srlg	%r1,%r1,0(%r2)			/*  >> tk->shift */
-	lg	%r0,__VDSO_XTIME_SEC(%r5)	/* tk->xtime_sec */
-	clg	%r4,__VDSO_UPD_COUNT(%r5)	/* check update counter */
-	jne	5b
-	larl	%r5,13f
-6:	clg	%r1,0(%r5)
-	jl	7f
-	slg	%r1,0(%r5)
-	aghi	%r0,1
-	j	6b
-7:	stg	%r0,0(%r3)			/* store tp->tv_sec */
-	stg	%r1,8(%r3)			/* store tp->tv_nsec */
-	lghi	%r2,0
-	aghi	%r15,16
-	CFI_DEF_CFA_OFFSET STACK_FRAME_OVERHEAD
-	CFI_RESTORE 15
-	br	%r14
-
-	/* CPUCLOCK_VIRT for this thread */
-	CFI_DEF_CFA_OFFSET STACK_FRAME_OVERHEAD+16
-	CFI_VAL_OFFSET 15, -STACK_FRAME_OVERHEAD
-9:	lghi	%r4,0
-	icm	%r0,15,__VDSO_ECTG_OK(%r5)
-	jz	12f
-	sacf	256				/* Magic ectg instruction */
-	.insn	ssf,0xc80100000000,__VDSO_ECTG_BASE(4),__VDSO_ECTG_USER(4),4
-	sacf	0
-	algr	%r1,%r0				/* r1 = cputime as TOD value */
-	mghi	%r1,1000			/* convert to nanoseconds */
-	srlg	%r1,%r1,12			/* r1 = cputime in nanosec */
-	lgr	%r4,%r1
-	larl	%r5,13f
-	srlg	%r1,%r1,9			/* divide by 1000000000 */
-	mlg	%r0,8(%r5)
-	srlg	%r0,%r0,11			/* r0 = tv_sec */
-	stg	%r0,0(%r3)
-	msg	%r0,0(%r5)			/* calculate tv_nsec */
-	slgr	%r4,%r0				/* r4 = tv_nsec */
-	stg	%r4,8(%r3)
-	lghi	%r2,0
-	aghi	%r15,16
-	CFI_DEF_CFA_OFFSET STACK_FRAME_OVERHEAD
-	CFI_RESTORE 15
-	br	%r14
-
-	/* Fallback to system call */
-	CFI_DEF_CFA_OFFSET STACK_FRAME_OVERHEAD+16
-	CFI_VAL_OFFSET 15, -STACK_FRAME_OVERHEAD
-12:	lghi	%r1,__NR_clock_gettime
-	svc	0
-	aghi	%r15,16
-	CFI_DEF_CFA_OFFSET STACK_FRAME_OVERHEAD
-	CFI_RESTORE 15
-	br	%r14
-	CFI_ENDPROC
-
-13:	.quad	1000000000
-14:	.quad	19342813113834067
-	.size	__kernel_clock_gettime,.-__kernel_clock_gettime

arch/s390/kernel/vdso64/gettimeofday.S

@@ -1,71 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Userland implementation of gettimeofday() for 64 bits processes in a
- * s390 kernel for use in the vDSO
- *
- *  Copyright IBM Corp. 2008
- *  Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com)
- */
-#include <asm/vdso.h>
-#include <asm/asm-offsets.h>
-#include <asm/unistd.h>
-#include <asm/dwarf.h>
-#include <asm/ptrace.h>
-
-	.text
-	.align 4
-	.globl __kernel_gettimeofday
-	.type  __kernel_gettimeofday,@function
-__kernel_gettimeofday:
-	CFI_STARTPROC
-	aghi	%r15,-16
-	CFI_ADJUST_CFA_OFFSET 16
-	CFI_VAL_OFFSET 15, -STACK_FRAME_OVERHEAD
-	larl	%r5,_vdso_data
-0:	ltgr	%r3,%r3				/* check if tz is NULL */
-	je	1f
-	mvc	0(8,%r3),__VDSO_TIMEZONE(%r5)
-1:	ltgr	%r2,%r2				/* check if tv is NULL */
-	je	4f
-	lg	%r4,__VDSO_UPD_COUNT(%r5)	/* load update counter */
-	tmll	%r4,0x0001			/* pending update ? loop */
-	jnz	0b
-	stcke	0(%r15)				/* Store TOD clock */
-	lg	%r1,1(%r15)
-	lg	%r0,__VDSO_TS_END(%r5)		/* TOD steering end time */
-	slgr	%r0,%r1				/* now - ts_steering_end */
-	ltgr	%r0,%r0				/* past end of steering ? */
-	jm	6f
-	srlg	%r0,%r0,15			/* 1 per 2^16 */
-	tm	__VDSO_TS_DIR+3(%r5),0x01	/* steering direction? */
-	jz	7f
-	lcgr	%r0,%r0				/* negative TOD offset */
-7:	algr	%r1,%r0				/* add steering offset */
-6:	sg	%r1,__VDSO_XTIME_STAMP(%r5)	/* TOD - cycle_last */
-	msgf	%r1,__VDSO_TK_MULT(%r5)		/*  * tk->mult */
-	alg	%r1,__VDSO_XTIME_NSEC(%r5)	/*  + tk->xtime_nsec */
-	lg	%r0,__VDSO_XTIME_SEC(%r5)	/* tk->xtime_sec */
-	clg	%r4,__VDSO_UPD_COUNT(%r5)	/* check update counter */
-	jne	0b
-	lgf	%r5,__VDSO_TK_SHIFT(%r5)	/* Timekeeper shift */
-	srlg	%r1,%r1,0(%r5)			/*  >> tk->shift */
-	larl	%r5,5f
-2:	clg	%r1,0(%r5)
-	jl	3f
-	slg	%r1,0(%r5)
-	aghi	%r0,1
-	j	2b
-3:	stg	%r0,0(%r2)			/* store tv->tv_sec */
-	slgr	%r0,%r0				/* tv_nsec -> tv_usec */
-	ml	%r0,8(%r5)
-	srlg	%r0,%r0,6
-	stg	%r0,8(%r2)			/* store tv->tv_usec */
-4:	lghi	%r2,0
-	aghi	%r15,16
-	CFI_ADJUST_CFA_OFFSET -16
-	CFI_RESTORE 15
-	br	%r14
-	CFI_ENDPROC
-5:	.quad	1000000000
-	.long	274877907
-	.size	__kernel_gettimeofday,.-__kernel_gettimeofday

arch/s390/kernel/vdso64/vdso64_generic.c

@@ -0,0 +1,18 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "../../../../lib/vdso/gettimeofday.c"
+
+int __s390_vdso_gettimeofday(struct __kernel_old_timeval *tv,
+			     struct timezone *tz)
+{
+	return __cvdso_gettimeofday(tv, tz);
+}
+
+int __s390_vdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts)
+{
+	return __cvdso_clock_gettime(clock, ts);
+}
+
+int __s390_vdso_clock_getres(clockid_t clock, struct __kernel_timespec *ts)
+{
+	return __cvdso_clock_getres(clock, ts);
+}

arch/s390/kernel/vdso64/vdso_user_wrapper.S

@@ -0,0 +1,38 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <asm/vdso.h>
+#include <asm/unistd.h>
+#include <asm/asm-offsets.h>
+#include <asm/dwarf.h>
+#include <asm/ptrace.h>
+
+#define WRAPPER_FRAME_SIZE (STACK_FRAME_OVERHEAD+8)
+
+/*
+ * Older glibc version called vdso without allocating a stackframe. This wrapper
+ * is just used to allocate a stackframe. See
+ * https://sourceware.org/git/?p=glibc.git;a=commit;h=478593e6374f3818da39332260dc453cb19cfa1e
+ * for details.
+ */
+.macro vdso_func func
+	.globl __kernel_\func
+	.type  __kernel_\func,@function
+	.align 8
+__kernel_\func:
+	CFI_STARTPROC
+	aghi	%r15,-WRAPPER_FRAME_SIZE
+	CFI_DEF_CFA_OFFSET (STACK_FRAME_OVERHEAD + WRAPPER_FRAME_SIZE)
+	CFI_VAL_OFFSET 15, -STACK_FRAME_OVERHEAD
+	stg	%r14,STACK_FRAME_OVERHEAD(%r15)
+	brasl	%r14,__s390_vdso_\func
+	lg	%r14,STACK_FRAME_OVERHEAD(%r15)
+	aghi	%r15,WRAPPER_FRAME_SIZE
+	CFI_DEF_CFA_OFFSET STACK_FRAME_OVERHEAD
+	CFI_RESTORE 15
+	br	%r14
+	CFI_ENDPROC
+	.size	__kernel_\func,.-__kernel_\func
+.endm
+
+vdso_func gettimeofday
+vdso_func clock_getres
+vdso_func clock_gettime

arch/s390/lib/string.c

@@ -333,7 +333,7 @@ EXPORT_SYMBOL(memchr);
  * memcmp - Compare two areas of memory
  * @s1: One area of memory
  * @s2: Another area of memory
- * @count: The size of the area.
+ * @n: The size of the area.
  */
 #ifdef __HAVE_ARCH_MEMCMP
 int memcmp(const void *s1, const void *s2, size_t n)

arch/s390/mm/Makefile

@@ -8,7 +8,7 @@ obj-y		+= page-states.o pageattr.o pgtable.o pgalloc.o
 
 obj-$(CONFIG_CMM)		+= cmm.o
 obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o
-obj-$(CONFIG_S390_PTDUMP)	+= dump_pagetables.o
+obj-$(CONFIG_PTDUMP_CORE)	+= dump_pagetables.o
 obj-$(CONFIG_PGSTE)		+= gmap.o
 
 KASAN_SANITIZE_kasan_init.o	:= n

arch/s390/mm/dump_pagetables.c

@@ -1,9 +1,11 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <linux/set_memory.h>
+#include <linux/ptdump.h>
 #include <linux/seq_file.h>
 #include <linux/debugfs.h>
-#include <linux/sched.h>
 #include <linux/mm.h>
 #include <linux/kasan.h>
+#include <asm/ptdump.h>
 #include <asm/kasan.h>
 #include <asm/sections.h>
 
@@ -15,263 +17,234 @@ struct addr_marker {
 };
 
 enum address_markers_idx {
-	IDENTITY_NR = 0,
+	IDENTITY_BEFORE_NR = 0,
+	IDENTITY_BEFORE_END_NR,
 	KERNEL_START_NR,
 	KERNEL_END_NR,
+	IDENTITY_AFTER_NR,
+	IDENTITY_AFTER_END_NR,
 #ifdef CONFIG_KASAN
 	KASAN_SHADOW_START_NR,
 	KASAN_SHADOW_END_NR,
 #endif
 	VMEMMAP_NR,
+	VMEMMAP_END_NR,
 	VMALLOC_NR,
+	VMALLOC_END_NR,
 	MODULES_NR,
+	MODULES_END_NR,
 };
 
 static struct addr_marker address_markers[] = {
-	[IDENTITY_NR]		= {0, "Identity Mapping"},
+	[IDENTITY_BEFORE_NR]	= {0, "Identity Mapping Start"},
+	[IDENTITY_BEFORE_END_NR] = {(unsigned long)_stext, "Identity Mapping End"},
 	[KERNEL_START_NR]	= {(unsigned long)_stext, "Kernel Image Start"},
 	[KERNEL_END_NR]		= {(unsigned long)_end, "Kernel Image End"},
+	[IDENTITY_AFTER_NR]	= {(unsigned long)_end, "Identity Mapping Start"},
+	[IDENTITY_AFTER_END_NR]	= {0, "Identity Mapping End"},
 #ifdef CONFIG_KASAN
 	[KASAN_SHADOW_START_NR]	= {KASAN_SHADOW_START, "Kasan Shadow Start"},
 	[KASAN_SHADOW_END_NR]	= {KASAN_SHADOW_END, "Kasan Shadow End"},
 #endif
-	[VMEMMAP_NR]		= {0, "vmemmap Area"},
+	[VMEMMAP_NR]		= {0, "vmemmap Area Start"},
-	[VMALLOC_NR]		= {0, "vmalloc Area"},
+	[VMEMMAP_END_NR]	= {0, "vmemmap Area End"},
-	[MODULES_NR]		= {0, "Modules Area"},
+	[VMALLOC_NR]		= {0, "vmalloc Area Start"},
+	[VMALLOC_END_NR]	= {0, "vmalloc Area End"},
+	[MODULES_NR]		= {0, "Modules Area Start"},
+	[MODULES_END_NR]	= {0, "Modules Area End"},
 	{ -1, NULL }
 };
 
 struct pg_state {
+	struct ptdump_state ptdump;
+	struct seq_file *seq;
 	int level;
 	unsigned int current_prot;
+	bool check_wx;
+	unsigned long wx_pages;
 	unsigned long start_address;
-	unsigned long current_address;
 	const struct addr_marker *marker;
 };
 
+#define pt_dump_seq_printf(m, fmt, args...)	\
+({						\
+	struct seq_file *__m = (m);		\
+						\
+	if (__m)				\
+		seq_printf(__m, fmt, ##args);	\
+})
+
+#define pt_dump_seq_puts(m, fmt)		\
+({						\
+	struct seq_file *__m = (m);		\
+						\
+	if (__m)				\
+		seq_printf(__m, fmt);		\
+})
+
 static void print_prot(struct seq_file *m, unsigned int pr, int level)
 {
 	static const char * const level_name[] =
 		{ "ASCE", "PGD", "PUD", "PMD", "PTE" };
 
-	seq_printf(m, "%s ", level_name[level]);
+	pt_dump_seq_printf(m, "%s ", level_name[level]);
 	if (pr & _PAGE_INVALID) {
-		seq_printf(m, "I\n");
+		pt_dump_seq_printf(m, "I\n");
 		return;
 	}
-	seq_puts(m, (pr & _PAGE_PROTECT) ? "RO " : "RW ");
+	pt_dump_seq_puts(m, (pr & _PAGE_PROTECT) ? "RO " : "RW ");
-	seq_puts(m, (pr & _PAGE_NOEXEC) ? "NX\n" : "X\n");
+	pt_dump_seq_puts(m, (pr & _PAGE_NOEXEC) ? "NX\n" : "X\n");
 }
 
-static void note_page(struct seq_file *m, struct pg_state *st,
+static void note_prot_wx(struct pg_state *st, unsigned long addr)
-		     unsigned int new_prot, int level)
+{
+#ifdef CONFIG_DEBUG_WX
+	if (!st->check_wx)
+		return;
+	if (st->current_prot & _PAGE_INVALID)
+		return;
+	if (st->current_prot & _PAGE_PROTECT)
+		return;
+	if (st->current_prot & _PAGE_NOEXEC)
+		return;
+	/* The first lowcore page is currently still W+X. */
+	if (addr == PAGE_SIZE)
+		return;
+	WARN_ONCE(1, "s390/mm: Found insecure W+X mapping at address %pS\n",
+		  (void *)st->start_address);
+	st->wx_pages += (addr - st->start_address) / PAGE_SIZE;
+#endif /* CONFIG_DEBUG_WX */
+}
+
+static void note_page(struct ptdump_state *pt_st, unsigned long addr, int level, u64 val)
 {
-	static const char units[] = "KMGTPE";
 	int width = sizeof(unsigned long) * 2;
+	static const char units[] = "KMGTPE";
 	const char *unit = units;
-	unsigned int prot, cur;
 	unsigned long delta;
+	struct pg_state *st;
+	struct seq_file *m;
+	unsigned int prot;
 
-	/*
+	st = container_of(pt_st, struct pg_state, ptdump);
-	 * If we have a "break" in the series, we need to flush the state
+	m = st->seq;
-	 * that we have now. "break" is either changing perms, levels or
+	prot = val & (_PAGE_PROTECT | _PAGE_NOEXEC);
-	 * address space marker.
+	if (level == 4 && (val & _PAGE_INVALID))
-	 */
+		prot = _PAGE_INVALID;
-	prot = new_prot;
+	/* For pmd_none() & friends val gets passed as zero. */
-	cur = st->current_prot;
+	if (level != 4 && !val)
-
+		prot = _PAGE_INVALID;
-	if (!st->level) {
+	/* Final flush from generic code. */
-		/* First entry */
+	if (level == -1)
-		st->current_prot = new_prot;
+		addr = max_addr;
+	if (st->level == -1) {
+		pt_dump_seq_printf(m, "---[ %s ]---\n", st->marker->name);
+		st->start_address = addr;
+		st->current_prot = prot;
 		st->level = level;
-		st->marker = address_markers;
+	} else if (prot != st->current_prot || level != st->level ||
-		seq_printf(m, "---[ %s ]---\n", st->marker->name);
+		   addr >= st->marker[1].start_address) {
-	} else if (prot != cur || level != st->level ||
+		note_prot_wx(st, addr);
-		   st->current_address >= st->marker[1].start_address) {
+		pt_dump_seq_printf(m, "0x%0*lx-0x%0*lx ",
-		/* Print the actual finished series */
-		seq_printf(m, "0x%0*lx-0x%0*lx ",
 				   width, st->start_address,
-			   width, st->current_address);
+				   width, addr);
-		delta = (st->current_address - st->start_address) >> 10;
+		delta = (addr - st->start_address) >> 10;
 		while (!(delta & 0x3ff) && unit[1]) {
 			delta >>= 10;
 			unit++;
 		}
-		seq_printf(m, "%9lu%c ", delta, *unit);
+		pt_dump_seq_printf(m, "%9lu%c ", delta, *unit);
 		print_prot(m, st->current_prot, st->level);
-		while (st->current_address >= st->marker[1].start_address) {
+		while (addr >= st->marker[1].start_address) {
 			st->marker++;
-			seq_printf(m, "---[ %s ]---\n", st->marker->name);
+			pt_dump_seq_printf(m, "---[ %s ]---\n", st->marker->name);
 		}
-		st->start_address = st->current_address;
+		st->start_address = addr;
-		st->current_prot = new_prot;
+		st->current_prot = prot;
 		st->level = level;
 	}
 }
 
-#ifdef CONFIG_KASAN
+#ifdef CONFIG_DEBUG_WX
-static void note_kasan_early_shadow_page(struct seq_file *m,
+void ptdump_check_wx(void)
-						struct pg_state *st)
 {
-	unsigned int prot;
+	struct pg_state st = {
-
+		.ptdump = {
-	prot = pte_val(*kasan_early_shadow_pte) &
+			.note_page = note_page,
-		(_PAGE_PROTECT | _PAGE_INVALID | _PAGE_NOEXEC);
+			.range = (struct ptdump_range[]) {
-	note_page(m, st, prot, 4);
+				{.start = 0, .end = max_addr},
+				{.start = 0, .end = 0},
 			}
-#endif
+		},
+		.seq = NULL,
+		.level = -1,
+		.current_prot = 0,
+		.check_wx = true,
+		.wx_pages = 0,
+		.start_address = 0,
+		.marker = (struct addr_marker[]) {
+			{ .start_address =  0, .name = NULL},
+			{ .start_address = -1, .name = NULL},
+		},
+	};
 
-/*
+	if (!MACHINE_HAS_NX)
- * The actual page table walker functions. In order to keep the
- * implementation of print_prot() short, we only check and pass
- * _PAGE_INVALID and _PAGE_PROTECT flags to note_page() if a region,
- * segment or page table entry is invalid or read-only.
- * After all it's just a hint that the current level being walked
- * contains an invalid or read-only entry.
- */
-static void walk_pte_level(struct seq_file *m, struct pg_state *st,
-			   pmd_t *pmd, unsigned long addr)
-{
-	unsigned int prot;
-	pte_t *pte;
-	int i;
-
-	for (i = 0; i < PTRS_PER_PTE && addr < max_addr; i++) {
-		st->current_address = addr;
-		pte = pte_offset_kernel(pmd, addr);
-		prot = pte_val(*pte) &
-			(_PAGE_PROTECT | _PAGE_INVALID | _PAGE_NOEXEC);
-		note_page(m, st, prot, 4);
-		addr += PAGE_SIZE;
-	}
-}
-
-static void walk_pmd_level(struct seq_file *m, struct pg_state *st,
-			   pud_t *pud, unsigned long addr)
-{
-	unsigned int prot;
-	pmd_t *pmd;
-	int i;
-
-#ifdef CONFIG_KASAN
-	if ((pud_val(*pud) & PAGE_MASK) == __pa(kasan_early_shadow_pmd)) {
-		note_kasan_early_shadow_page(m, st);
 		return;
-	}
+	ptdump_walk_pgd(&st.ptdump, &init_mm, NULL);
-#endif
+	if (st.wx_pages)
-
+		pr_warn("Checked W+X mappings: FAILED, %lu W+X pages found\n", st.wx_pages);
-	pmd = pmd_offset(pud, addr);
-	for (i = 0; i < PTRS_PER_PMD && addr < max_addr; i++, pmd++) {
-		st->current_address = addr;
-		if (!pmd_none(*pmd)) {
-			if (pmd_large(*pmd)) {
-				prot = pmd_val(*pmd) &
-					(_SEGMENT_ENTRY_PROTECT |
-					 _SEGMENT_ENTRY_NOEXEC);
-				note_page(m, st, prot, 3);
-			} else
-				walk_pte_level(m, st, pmd, addr);
-		} else
-			note_page(m, st, _PAGE_INVALID, 3);
-		addr += PMD_SIZE;
-	}
-}
-
-static void walk_pud_level(struct seq_file *m, struct pg_state *st,
-			   p4d_t *p4d, unsigned long addr)
-{
-	unsigned int prot;
-	pud_t *pud;
-	int i;
-
-#ifdef CONFIG_KASAN
-	if ((p4d_val(*p4d) & PAGE_MASK) == __pa(kasan_early_shadow_pud)) {
-		note_kasan_early_shadow_page(m, st);
-		return;
-	}
-#endif
-
-	pud = pud_offset(p4d, addr);
-	for (i = 0; i < PTRS_PER_PUD && addr < max_addr; i++, pud++) {
-		st->current_address = addr;
-		if (!pud_none(*pud))
-			if (pud_large(*pud)) {
-				prot = pud_val(*pud) &
-					(_REGION_ENTRY_PROTECT |
-					 _REGION_ENTRY_NOEXEC);
-				note_page(m, st, prot, 2);
-			} else
-				walk_pmd_level(m, st, pud, addr);
 	else
-			note_page(m, st, _PAGE_INVALID, 2);
+		pr_info("Checked W+X mappings: passed, no unexpected W+X pages found\n");
-		addr += PUD_SIZE;
-	}
-}
-
-static void walk_p4d_level(struct seq_file *m, struct pg_state *st,
-			   pgd_t *pgd, unsigned long addr)
-{
-	p4d_t *p4d;
-	int i;
-
-#ifdef CONFIG_KASAN
-	if ((pgd_val(*pgd) & PAGE_MASK) == __pa(kasan_early_shadow_p4d)) {
-		note_kasan_early_shadow_page(m, st);
-		return;
-	}
-#endif
-
-	p4d = p4d_offset(pgd, addr);
-	for (i = 0; i < PTRS_PER_P4D && addr < max_addr; i++, p4d++) {
-		st->current_address = addr;
-		if (!p4d_none(*p4d))
-			walk_pud_level(m, st, p4d, addr);
-		else
-			note_page(m, st, _PAGE_INVALID, 2);
-		addr += P4D_SIZE;
-	}
-}
-
-static void walk_pgd_level(struct seq_file *m)
-{
-	unsigned long addr = 0;
-	struct pg_state st;
-	pgd_t *pgd;
-	int i;
-
-	memset(&st, 0, sizeof(st));
-	for (i = 0; i < PTRS_PER_PGD && addr < max_addr; i++) {
-		st.current_address = addr;
-		pgd = pgd_offset_k(addr);
-		if (!pgd_none(*pgd))
-			walk_p4d_level(m, &st, pgd, addr);
-		else
-			note_page(m, &st, _PAGE_INVALID, 1);
-		addr += PGDIR_SIZE;
-		cond_resched();
-	}
-	/* Flush out the last page */
-	st.current_address = max_addr;
-	note_page(m, &st, 0, 0);
 }
+#endif /* CONFIG_DEBUG_WX */
 
+#ifdef CONFIG_PTDUMP_DEBUGFS
 static int ptdump_show(struct seq_file *m, void *v)
 {
-	walk_pgd_level(m);
+	struct pg_state st = {
+		.ptdump = {
+			.note_page = note_page,
+			.range = (struct ptdump_range[]) {
+				{.start = 0, .end = max_addr},
+				{.start = 0, .end = 0},
+			}
+		},
+		.seq = m,
+		.level = -1,
+		.current_prot = 0,
+		.check_wx = false,
+		.wx_pages = 0,
+		.start_address = 0,
+		.marker = address_markers,
+	};
+
+	get_online_mems();
+	mutex_lock(&cpa_mutex);
+	ptdump_walk_pgd(&st.ptdump, &init_mm, NULL);
+	mutex_unlock(&cpa_mutex);
+	put_online_mems();
 	return 0;
 }
+DEFINE_SHOW_ATTRIBUTE(ptdump);
+#endif /* CONFIG_PTDUMP_DEBUGFS */
 
-static int ptdump_open(struct inode *inode, struct file *filp)
+/*
+ * Heapsort from lib/sort.c is not a stable sorting algorithm, do a simple
+ * insertion sort to preserve the original order of markers with the same
+ * start address.
+ */
+static void sort_address_markers(void)
 {
-	return single_open(filp, ptdump_show, NULL);
+	struct addr_marker tmp;
-}
+	int i, j;
 
-static const struct file_operations ptdump_fops = {
+	for (i = 1; i < ARRAY_SIZE(address_markers) - 1; i++) {
-	.open		= ptdump_open,
+		tmp = address_markers[i];
-	.read		= seq_read,
+		for (j = i - 1; j >= 0 && address_markers[j].start_address > tmp.start_address; j--)
-	.llseek		= seq_lseek,
+			address_markers[j + 1] = address_markers[j];
-	.release	= single_release,
+		address_markers[j + 1] = tmp;
-};
+	}
+}
 
 static int pt_dump_init(void)
 {
@@ -282,10 +255,17 @@ static int pt_dump_init(void)
 	 */
 	max_addr = (S390_lowcore.kernel_asce & _REGION_ENTRY_TYPE_MASK) >> 2;
 	max_addr = 1UL << (max_addr * 11 + 31);
+	address_markers[IDENTITY_AFTER_END_NR].start_address = memory_end;
 	address_markers[MODULES_NR].start_address = MODULES_VADDR;
+	address_markers[MODULES_END_NR].start_address = MODULES_END;
 	address_markers[VMEMMAP_NR].start_address = (unsigned long) vmemmap;
+	address_markers[VMEMMAP_END_NR].start_address = (unsigned long)vmemmap + vmemmap_size;
 	address_markers[VMALLOC_NR].start_address = VMALLOC_START;
+	address_markers[VMALLOC_END_NR].start_address = VMALLOC_END;
+	sort_address_markers();
+#ifdef CONFIG_PTDUMP_DEBUGFS
 	debugfs_create_file("kernel_page_tables", 0400, NULL, NULL, &ptdump_fops);
+#endif /* CONFIG_PTDUMP_DEBUGFS */
 	return 0;
 }
 device_initcall(pt_dump_init);

arch/s390/mm/gmap.c

@@ -2679,7 +2679,7 @@ static int __s390_reset_acc(pte_t *ptep, unsigned long addr,
 	pte_t pte = READ_ONCE(*ptep);
 
 	if (pte_present(pte))
-		WARN_ON_ONCE(uv_convert_from_secure(pte_val(pte) & PAGE_MASK));
+		WARN_ON_ONCE(uv_destroy_page(pte_val(pte) & PAGE_MASK));
 	return 0;
 }
 

arch/s390/mm/init.c

@@ -34,6 +34,7 @@
 #include <asm/processor.h>
 #include <linux/uaccess.h>
 #include <asm/pgalloc.h>
+#include <asm/ptdump.h>
 #include <asm/dma.h>
 #include <asm/lowcore.h>
 #include <asm/tlb.h>
@@ -129,6 +130,7 @@ void mark_rodata_ro(void)
 
 	set_memory_ro((unsigned long)__start_ro_after_init, size >> PAGE_SHIFT);
 	pr_info("Write protected read-only-after-init data: %luk\n", size >> 10);
+	debug_checkwx();
 }
 
 int set_memory_encrypted(unsigned long addr, int numpages)

arch/s390/mm/kasan_init.c

@@ -11,7 +11,9 @@
 #include <asm/facility.h>
 #include <asm/sections.h>
 #include <asm/setup.h>
+#include <asm/uv.h>
 
+unsigned long kasan_vmax;
 static unsigned long segment_pos __initdata;
 static unsigned long segment_low __initdata;
 static unsigned long pgalloc_pos __initdata;
@@ -99,8 +101,12 @@ static void __init kasan_early_vmemmap_populate(unsigned long address,
 	pgt_prot_zero = pgprot_val(PAGE_KERNEL_RO);
 	if (!has_nx)
 		pgt_prot_zero &= ~_PAGE_NOEXEC;
-	pgt_prot = pgprot_val(PAGE_KERNEL_EXEC);
+	pgt_prot = pgprot_val(PAGE_KERNEL);
-	sgt_prot = pgprot_val(SEGMENT_KERNEL_EXEC);
+	sgt_prot = pgprot_val(SEGMENT_KERNEL);
+	if (!has_nx || mode == POPULATE_ONE2ONE) {
+		pgt_prot &= ~_PAGE_NOEXEC;
+		sgt_prot &= ~_SEGMENT_ENTRY_NOEXEC;
+	}
 
 	while (address < end) {
 		pg_dir = pgd_offset_k(address);
@@ -252,14 +258,31 @@ static void __init kasan_early_detect_facilities(void)
 	}
 }
 
+static bool __init has_uv_sec_stor_limit(void)
+{
+	/*
+	 * keep these conditions in line with setup_uv()
+	 */
+	if (!is_prot_virt_host())
+		return false;
+
+	if (is_prot_virt_guest())
+		return false;
+
+	if (!test_facility(158))
+		return false;
+
+	return !!uv_info.max_sec_stor_addr;
+}
+
 void __init kasan_early_init(void)
 {
 	unsigned long untracked_mem_end;
 	unsigned long shadow_alloc_size;
+	unsigned long vmax_unlimited;
 	unsigned long initrd_end;
 	unsigned long asce_type;
 	unsigned long memsize;
-	unsigned long vmax;
 	unsigned long pgt_prot = pgprot_val(PAGE_KERNEL_RO);
 	pte_t pte_z;
 	pmd_t pmd_z = __pmd(__pa(kasan_early_shadow_pte) | _SEGMENT_ENTRY);
@@ -287,7 +310,9 @@ void __init kasan_early_init(void)
 		BUILD_BUG_ON(!IS_ALIGNED(KASAN_SHADOW_END, P4D_SIZE));
 		crst_table_init((unsigned long *)early_pg_dir,
 				_REGION2_ENTRY_EMPTY);
-		untracked_mem_end = vmax = _REGION1_SIZE;
+		untracked_mem_end = kasan_vmax = vmax_unlimited = _REGION1_SIZE;
+		if (has_uv_sec_stor_limit())
+			kasan_vmax = min(vmax_unlimited, uv_info.max_sec_stor_addr);
 		asce_type = _ASCE_TYPE_REGION2;
 	} else {
 		/* 3 level paging */
@@ -295,7 +320,7 @@ void __init kasan_early_init(void)
 		BUILD_BUG_ON(!IS_ALIGNED(KASAN_SHADOW_END, PUD_SIZE));
 		crst_table_init((unsigned long *)early_pg_dir,
 				_REGION3_ENTRY_EMPTY);
-		untracked_mem_end = vmax = _REGION2_SIZE;
+		untracked_mem_end = kasan_vmax = vmax_unlimited = _REGION2_SIZE;
 		asce_type = _ASCE_TYPE_REGION3;
 	}
 
@@ -365,17 +390,20 @@ void __init kasan_early_init(void)
 	/* populate kasan shadow (for identity mapping and zero page mapping) */
 	kasan_early_vmemmap_populate(__sha(0), __sha(memsize), POPULATE_MAP);
 	if (IS_ENABLED(CONFIG_MODULES))
-		untracked_mem_end = vmax - MODULES_LEN;
+		untracked_mem_end = kasan_vmax - MODULES_LEN;
 	if (IS_ENABLED(CONFIG_KASAN_VMALLOC)) {
-		untracked_mem_end = vmax - vmalloc_size - MODULES_LEN;
+		untracked_mem_end = kasan_vmax - vmalloc_size - MODULES_LEN;
 		/* shallowly populate kasan shadow for vmalloc and modules */
 		kasan_early_vmemmap_populate(__sha(untracked_mem_end),
-					     __sha(vmax), POPULATE_SHALLOW);
+					     __sha(kasan_vmax), POPULATE_SHALLOW);
 	}
 	/* populate kasan shadow for untracked memory */
 	kasan_early_vmemmap_populate(__sha(max_physmem_end),
 				     __sha(untracked_mem_end),
 				     POPULATE_ZERO_SHADOW);
+	kasan_early_vmemmap_populate(__sha(kasan_vmax),
+				     __sha(vmax_unlimited),
+				     POPULATE_ZERO_SHADOW);
 	/* memory allocated for identity mapping structs will be freed later */
 	pgalloc_freeable = pgalloc_pos;
 	/* populate identity mapping */

arch/s390/mm/pageattr.c

@@ -278,7 +278,7 @@ static int walk_p4d_level(pgd_t *pgd, unsigned long addr, unsigned long end,
 	return rc;
 }
 
-static DEFINE_MUTEX(cpa_mutex);
+DEFINE_MUTEX(cpa_mutex);
 
 static int change_page_attr(unsigned long addr, unsigned long end,
 			    unsigned long flags)

arch/s390/mm/pgtable.c

@@ -24,6 +24,26 @@
 #include <asm/mmu_context.h>
 #include <asm/page-states.h>
 
+pgprot_t pgprot_writecombine(pgprot_t prot)
+{
+	/*
+	 * mio_wb_bit_mask may be set on a different CPU, but it is only set
+	 * once at init and only read afterwards.
+	 */
+	return __pgprot(pgprot_val(prot) | mio_wb_bit_mask);
+}
+EXPORT_SYMBOL_GPL(pgprot_writecombine);
+
+pgprot_t pgprot_writethrough(pgprot_t prot)
+{
+	/*
+	 * mio_wb_bit_mask may be set on a different CPU, but it is only set
+	 * once at init and only read afterwards.
+	 */
+	return __pgprot(pgprot_val(prot) & ~mio_wb_bit_mask);
+}
+EXPORT_SYMBOL_GPL(pgprot_writethrough);
+
 static inline void ptep_ipte_local(struct mm_struct *mm, unsigned long addr,
 				   pte_t *ptep, int nodat)
 {

arch/s390/pci/Makefile

@@ -6,3 +6,4 @@
 obj-$(CONFIG_PCI)	+= pci.o pci_irq.o pci_dma.o pci_clp.o pci_sysfs.o \
 			   pci_event.o pci_debug.o pci_insn.o pci_mmio.o \
 			   pci_bus.o
+obj-$(CONFIG_PCI_IOV)	+= pci_iov.o

arch/s390/pci/pci.c

@@ -37,6 +37,7 @@
 #include <asm/pci_dma.h>
 
 #include "pci_bus.h"
+#include "pci_iov.h"
 
 /* list of all detected zpci devices */
 static LIST_HEAD(zpci_list);
@@ -226,7 +227,7 @@ void __iowrite64_copy(void __iomem *to, const void *from, size_t count)
        zpci_memcpy_toio(to, from, count);
 }
 
-void __iomem *ioremap(phys_addr_t addr, size_t size)
+static void __iomem *__ioremap(phys_addr_t addr, size_t size, pgprot_t prot)
 {
 	unsigned long offset, vaddr;
 	struct vm_struct *area;
@@ -247,14 +248,37 @@ void __iomem *ioremap(phys_addr_t addr, size_t size)
 		return NULL;
 
 	vaddr = (unsigned long) area->addr;
-	if (ioremap_page_range(vaddr, vaddr + size, addr, PAGE_KERNEL)) {
+	if (ioremap_page_range(vaddr, vaddr + size, addr, prot)) {
 		free_vm_area(area);
 		return NULL;
 	}
 	return (void __iomem *) ((unsigned long) area->addr + offset);
 }
+
+void __iomem *ioremap_prot(phys_addr_t addr, size_t size, unsigned long prot)
+{
+	return __ioremap(addr, size, __pgprot(prot));
+}
+EXPORT_SYMBOL(ioremap_prot);
+
+void __iomem *ioremap(phys_addr_t addr, size_t size)
+{
+	return __ioremap(addr, size, PAGE_KERNEL);
+}
 EXPORT_SYMBOL(ioremap);
 
+void __iomem *ioremap_wc(phys_addr_t addr, size_t size)
+{
+	return __ioremap(addr, size, pgprot_writecombine(PAGE_KERNEL));
+}
+EXPORT_SYMBOL(ioremap_wc);
+
+void __iomem *ioremap_wt(phys_addr_t addr, size_t size)
+{
+	return __ioremap(addr, size, pgprot_writethrough(PAGE_KERNEL));
+}
+EXPORT_SYMBOL(ioremap_wt);
+
 void iounmap(volatile void __iomem *addr)
 {
 	if (static_branch_likely(&have_mio))
@@ -390,15 +414,6 @@ static struct pci_ops pci_root_ops = {
 	.write = pci_write,
 };
 
-#ifdef CONFIG_PCI_IOV
-static struct resource iov_res = {
-	.name	= "PCI IOV res",
-	.start	= 0,
-	.end	= -1,
-	.flags	= IORESOURCE_MEM,
-};
-#endif
-
 static void zpci_map_resources(struct pci_dev *pdev)
 {
 	struct zpci_dev *zdev = to_zpci(pdev);
@@ -419,16 +434,7 @@ static void zpci_map_resources(struct pci_dev *pdev)
 		pdev->resource[i].end = pdev->resource[i].start + len - 1;
 	}
 
-#ifdef CONFIG_PCI_IOV
+	zpci_iov_map_resources(pdev);
-	for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) {
-		int bar = i + PCI_IOV_RESOURCES;
-
-		len = pci_resource_len(pdev, bar);
-		if (!len)
-			continue;
-		pdev->resource[bar].parent = &iov_res;
-	}
-#endif
 }
 
 static void zpci_unmap_resources(struct pci_dev *pdev)
@@ -684,7 +690,7 @@ void zpci_remove_device(struct zpci_dev *zdev)
 	pdev = pci_get_slot(zbus->bus, zdev->devfn);
 	if (pdev) {
 		if (pdev->is_virtfn)
-			return zpci_remove_virtfn(pdev, zdev->vfn);
+			return zpci_iov_remove_virtfn(pdev, zdev->vfn);
 		pci_stop_and_remove_bus_device_locked(pdev);
 	}
 }
@@ -788,6 +794,9 @@ static int zpci_mem_init(void)
 	if (!zpci_iomap_bitmap)
 		goto error_iomap_bitmap;
 
+	if (static_branch_likely(&have_mio))
+		clp_setup_writeback_mio();
+
 	return 0;
 error_iomap_bitmap:
 	kfree(zpci_iomap_start);
@@ -885,9 +894,3 @@ static int __init pci_base_init(void)
 	return rc;
 }
 subsys_initcall_sync(pci_base_init);
-
-void zpci_rescan(void)
-{
-	if (zpci_is_enabled())
-		clp_rescan_pci_devices_simple(NULL);
-}

arch/s390/pci/pci_bus.c

@@ -24,6 +24,7 @@
 #include <asm/pci_dma.h>
 
 #include "pci_bus.h"
+#include "pci_iov.h"
 
 static LIST_HEAD(zbus_list);
 static DEFINE_SPINLOCK(zbus_list_lock);
@@ -126,69 +127,6 @@ static struct zpci_bus *zpci_bus_alloc(int pchid)
 	return zbus;
 }
 
-#ifdef CONFIG_PCI_IOV
-static int zpci_bus_link_virtfn(struct pci_dev *pdev,
-		struct pci_dev *virtfn, int vfid)
-{
-	int rc;
-
-	rc = pci_iov_sysfs_link(pdev, virtfn, vfid);
-	if (rc)
-		return rc;
-
-	virtfn->is_virtfn = 1;
-	virtfn->multifunction = 0;
-	virtfn->physfn = pci_dev_get(pdev);
-
-	return 0;
-}
-
-static int zpci_bus_setup_virtfn(struct zpci_bus *zbus,
-		struct pci_dev *virtfn, int vfn)
-{
-	int i, cand_devfn;
-	struct zpci_dev *zdev;
-	struct pci_dev *pdev;
-	int vfid = vfn - 1; /* Linux' vfid's start at 0 vfn at 1*/
-	int rc = 0;
-
-	if (!zbus->multifunction)
-		return 0;
-
-	/* If the parent PF for the given VF is also configured in the
-	 * instance, it must be on the same zbus.
-	 * We can then identify the parent PF by checking what
-	 * devfn the VF would have if it belonged to that PF using the PF's
-	 * stride and offset. Only if this candidate devfn matches the
-	 * actual devfn will we link both functions.
-	 */
-	for (i = 0; i < ZPCI_FUNCTIONS_PER_BUS; i++) {
-		zdev = zbus->function[i];
-		if (zdev && zdev->is_physfn) {
-			pdev = pci_get_slot(zbus->bus, zdev->devfn);
-			if (!pdev)
-				continue;
-			cand_devfn = pci_iov_virtfn_devfn(pdev, vfid);
-			if (cand_devfn == virtfn->devfn) {
-				rc = zpci_bus_link_virtfn(pdev, virtfn, vfid);
-				/* balance pci_get_slot() */
-				pci_dev_put(pdev);
-				break;
-			}
-			/* balance pci_get_slot() */
-			pci_dev_put(pdev);
-		}
-	}
-	return rc;
-}
-#else
-static inline int zpci_bus_setup_virtfn(struct zpci_bus *zbus,
-		struct pci_dev *virtfn, int vfn)
-{
-	return 0;
-}
-#endif
-
 void pcibios_bus_add_device(struct pci_dev *pdev)
 {
 	struct zpci_dev *zdev = to_zpci(pdev);
@@ -198,7 +136,7 @@ void pcibios_bus_add_device(struct pci_dev *pdev)
 	 * perform PF/VF linking.
 	 */
 	if (zdev->vfn)
-		zpci_bus_setup_virtfn(zdev->zbus, pdev, zdev->vfn);
+		zpci_iov_setup_virtfn(zdev->zbus, pdev, zdev->vfn);
 
 }
 

arch/s390/pci/pci_bus.h

@@ -9,7 +9,6 @@
 
 int zpci_bus_device_register(struct zpci_dev *zdev, struct pci_ops *ops);
 void zpci_bus_device_unregister(struct zpci_dev *zdev);
-int zpci_bus_init(void);
 
 void zpci_release_device(struct kref *kref);
 static inline void zpci_zdev_put(struct zpci_dev *zdev)
@@ -30,15 +29,3 @@ static inline struct zpci_dev *get_zdev_by_bus(struct pci_bus *bus,
 	return (devfn >= ZPCI_FUNCTIONS_PER_BUS) ? NULL : zbus->function[devfn];
 }
 
-#ifdef CONFIG_PCI_IOV
-static inline void zpci_remove_virtfn(struct pci_dev *pdev, int vfn)
-{
-
-	pci_lock_rescan_remove();
-	/* Linux' vfid's start at 0 vfn at 1 */
-	pci_iov_remove_virtfn(pdev->physfn, vfn - 1);
-	pci_unlock_rescan_remove();
-}
-#else /* CONFIG_PCI_IOV */
-static inline void zpci_remove_virtfn(struct pci_dev *pdev, int vfn) {}
-#endif /* CONFIG_PCI_IOV */

arch/s390/pci/pci_clp.c

@@ -244,6 +244,7 @@ int clp_add_pci_device(u32 fid, u32 fh, int configured)
 	return rc;
 }
 
+static int clp_refresh_fh(u32 fid);
 /*
  * Enable/Disable a given PCI function and update its function handle if
  * necessary
@@ -286,7 +287,41 @@ static int clp_set_pci_fn(struct zpci_dev *zdev, u8 nr_dma_as, u8 command)
 	} else if (!rc && rrb->response.hdr.rsp == CLP_RC_SETPCIFN_ALRDY &&
 			rrb->response.fh == 0) {
 		/* Function is already in desired state - update handle */
-		rc = clp_rescan_pci_devices_simple(&fid);
+		rc = clp_refresh_fh(fid);
+	}
+	clp_free_block(rrb);
+	return rc;
+}
+
+int clp_setup_writeback_mio(void)
+{
+	struct clp_req_rsp_slpc_pci *rrb;
+	u8  wb_bit_pos;
+	int rc;
+
+	rrb = clp_alloc_block(GFP_KERNEL);
+	if (!rrb)
+		return -ENOMEM;
+
+	memset(rrb, 0, sizeof(*rrb));
+	rrb->request.hdr.len = sizeof(rrb->request);
+	rrb->request.hdr.cmd = CLP_SLPC;
+	rrb->response.hdr.len = sizeof(rrb->response);
+
+	rc = clp_req(rrb, CLP_LPS_PCI);
+	if (!rc && rrb->response.hdr.rsp == CLP_RC_OK) {
+		if (rrb->response.vwb) {
+			wb_bit_pos = rrb->response.mio_wb;
+			set_bit_inv(wb_bit_pos, &mio_wb_bit_mask);
+			zpci_dbg(3, "wb bit: %d\n", wb_bit_pos);
+		} else {
+			zpci_dbg(3, "wb bit: n.a.\n");
+		}
+
+	} else {
+		zpci_err("SLPC PCI:\n");
+		zpci_err_clp(rrb->response.hdr.rsp, rc);
+		rc = -EIO;
 	}
 	clp_free_block(rrb);
 	return rc;
@@ -374,24 +409,6 @@ static void __clp_add(struct clp_fh_list_entry *entry, void *data)
 		clp_add_pci_device(entry->fid, entry->fh, entry->config_state);
 }
 
-static void __clp_update(struct clp_fh_list_entry *entry, void *data)
-{
-	struct zpci_dev *zdev;
-	u32 *fid = data;
-
-	if (!entry->vendor_id)
-		return;
-
-	if (fid && *fid != entry->fid)
-		return;
-
-	zdev = get_zdev_by_fid(entry->fid);
-	if (!zdev)
-		return;
-
-	zdev->fh = entry->fh;
-}
-
 int clp_scan_pci_devices(void)
 {
 	struct clp_req_rsp_list_pci *rrb;
@@ -407,27 +424,25 @@ int clp_scan_pci_devices(void)
 	return rc;
 }
 
-int clp_rescan_pci_devices(void)
+static void __clp_refresh_fh(struct clp_fh_list_entry *entry, void *data)
 {
-	struct clp_req_rsp_list_pci *rrb;
+	struct zpci_dev *zdev;
-	int rc;
+	u32 fid = *((u32 *)data);
 
-	zpci_remove_reserved_devices();
+	if (!entry->vendor_id || fid != entry->fid)
+		return;
 
-	rrb = clp_alloc_block(GFP_KERNEL);
+	zdev = get_zdev_by_fid(fid);
-	if (!rrb)
+	if (!zdev)
-		return -ENOMEM;
+		return;
 
-	rc = clp_list_pci(rrb, NULL, __clp_add);
+	zdev->fh = entry->fh;
-
-	clp_free_block(rrb);
-	return rc;
 }
 
-/* Rescan PCI functions and refresh function handles. If fid is non-NULL only
+/*
- * refresh the handle of the function matching @fid
+ * Refresh the function handle of the function matching @fid
  */
-int clp_rescan_pci_devices_simple(u32 *fid)
+static int clp_refresh_fh(u32 fid)
 {
 	struct clp_req_rsp_list_pci *rrb;
 	int rc;
@@ -436,7 +451,7 @@ int clp_rescan_pci_devices_simple(u32 *fid)
 	if (!rrb)
 		return -ENOMEM;
 
-	rc = clp_list_pci(rrb, fid, __clp_update);
+	rc = clp_list_pci(rrb, &fid, __clp_refresh_fh);
 
 	clp_free_block(rrb);
 	return rc;
@@ -495,7 +510,7 @@ static int clp_base_command(struct clp_req *req, struct clp_req_hdr *lpcb)
 	}
 }
 
-static int clp_pci_slpc(struct clp_req *req, struct clp_req_rsp_slpc *lpcb)
+static int clp_pci_slpc(struct clp_req *req, struct clp_req_rsp_slpc_pci *lpcb)
 {
 	unsigned long limit = PAGE_SIZE - sizeof(lpcb->request);
 

arch/s390/pci/pci_event.c

@@ -152,7 +152,8 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf)
 		}
 		break;
 	case 0x0306: /* 0x308 or 0x302 for multiple devices */
-		clp_rescan_pci_devices();
+		zpci_remove_reserved_devices();
+		clp_scan_pci_devices();
 		break;
 	case 0x0308: /* Standby -> Reserved */
 		if (!zdev)

arch/s390/pci/pci_iov.c

@@ -0,0 +1,99 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright IBM Corp. 2020
+ *
+ * Author(s):
+ *   Niklas Schnelle <schnelle@linux.ibm.com>
+ *
+ */
+
+#define KMSG_COMPONENT "zpci"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/pci.h>
+
+#include "pci_iov.h"
+
+static struct resource iov_res = {
+	.name	= "PCI IOV res",
+	.start	= 0,
+	.end	= -1,
+	.flags	= IORESOURCE_MEM,
+};
+
+void zpci_iov_map_resources(struct pci_dev *pdev)
+{
+	resource_size_t len;
+	int i;
+
+	for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) {
+		int bar = i + PCI_IOV_RESOURCES;
+
+		len = pci_resource_len(pdev, bar);
+		if (!len)
+			continue;
+		pdev->resource[bar].parent = &iov_res;
+	}
+}
+
+void zpci_iov_remove_virtfn(struct pci_dev *pdev, int vfn)
+{
+	pci_lock_rescan_remove();
+	/* Linux' vfid's start at 0 vfn at 1 */
+	pci_iov_remove_virtfn(pdev->physfn, vfn - 1);
+	pci_unlock_rescan_remove();
+}
+
+static int zpci_iov_link_virtfn(struct pci_dev *pdev, struct pci_dev *virtfn, int vfid)
+{
+	int rc;
+
+	rc = pci_iov_sysfs_link(pdev, virtfn, vfid);
+	if (rc)
+		return rc;
+
+	virtfn->is_virtfn = 1;
+	virtfn->multifunction = 0;
+	virtfn->physfn = pci_dev_get(pdev);
+
+	return 0;
+}
+
+int zpci_iov_setup_virtfn(struct zpci_bus *zbus, struct pci_dev *virtfn, int vfn)
+{
+	int i, cand_devfn;
+	struct zpci_dev *zdev;
+	struct pci_dev *pdev;
+	int vfid = vfn - 1; /* Linux' vfid's start at 0 vfn at 1*/
+	int rc = 0;
+
+	if (!zbus->multifunction)
+		return 0;
+
+	/* If the parent PF for the given VF is also configured in the
+	 * instance, it must be on the same zbus.
+	 * We can then identify the parent PF by checking what
+	 * devfn the VF would have if it belonged to that PF using the PF's
+	 * stride and offset. Only if this candidate devfn matches the
+	 * actual devfn will we link both functions.
+	 */
+	for (i = 0; i < ZPCI_FUNCTIONS_PER_BUS; i++) {
+		zdev = zbus->function[i];
+		if (zdev && zdev->is_physfn) {
+			pdev = pci_get_slot(zbus->bus, zdev->devfn);
+			if (!pdev)
+				continue;
+			cand_devfn = pci_iov_virtfn_devfn(pdev, vfid);
+			if (cand_devfn == virtfn->devfn) {
+				rc = zpci_iov_link_virtfn(pdev, virtfn, vfid);
+				/* balance pci_get_slot() */
+				pci_dev_put(pdev);
+				break;
+			}
+			/* balance pci_get_slot() */
+			pci_dev_put(pdev);
+		}
+	}
+	return rc;
+}

arch/s390/pci/pci_iov.h

@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright IBM Corp. 2020
+ *
+ * Author(s):
+ *   Niklas Schnelle <schnelle@linux.ibm.com>
+ *
+ */
+
+#ifndef __S390_PCI_IOV_H
+#define __S390_PCI_IOV_H
+
+#ifdef CONFIG_PCI_IOV
+void zpci_iov_remove_virtfn(struct pci_dev *pdev, int vfn);
+
+void zpci_iov_map_resources(struct pci_dev *pdev);
+
+int zpci_iov_setup_virtfn(struct zpci_bus *zbus, struct pci_dev *virtfn, int vfn);
+
+#else /* CONFIG_PCI_IOV */
+static inline void zpci_iov_remove_virtfn(struct pci_dev *pdev, int vfn) {}
+
+static inline void zpci_iov_map_resources(struct pci_dev *pdev) {}
+
+static inline int zpci_iov_setup_virtfn(struct zpci_bus *zbus, struct pci_dev *virtfn, int vfn)
+{
+	return 0;
+}
+#endif /* CONFIG_PCI_IOV */
+#endif /* __S390_PCI_IOV_h */

arch/s390/scripts/Makefile.chkbss

@@ -1,20 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-
-chkbss-target ?= built-in.a
-$(obj)/$(chkbss-target): chkbss
-
-chkbss-files := $(addsuffix .chkbss, $(chkbss))
-clean-files += $(chkbss-files)
-
-PHONY += chkbss
-chkbss: $(addprefix $(obj)/, $(chkbss-files))
-
-quiet_cmd_chkbss = CHKBSS  $<
-      cmd_chkbss = \
-	if ! $(OBJSIZE) --common $< | $(AWK) 'END { if ($$3) exit 1 }'; then \
-		echo "error: $< .bss section is not empty" >&2; exit 1; \
-	fi; \
-	touch $@;
-
-$(obj)/%.o.chkbss: $(obj)/%.o
-	$(call cmd,chkbss)

drivers/crypto/Kconfig

@@ -71,10 +71,26 @@ config ZCRYPT
 	help
 	  Select this option if you want to enable support for
 	  s390 cryptographic adapters like:
-	  + PCI-X Cryptographic Coprocessor (PCIXCC)
+	  + Crypto Express 2 up to 7 Coprocessor (CEXxC)
-	  + Crypto Express 2,3,4 or 5 Coprocessor (CEXxC)
+	  + Crypto Express 2 up to 7 Accelerator (CEXxA)
-	  + Crypto Express 2,3,4 or 5 Accelerator (CEXxA)
+	  + Crypto Express 4 up to 7 EP11 Coprocessor (CEXxP)
-	  + Crypto Express 4 or 5 EP11 Coprocessor (CEXxP)
+
+config ZCRYPT_DEBUG
+	bool "Enable debug features for s390 cryptographic adapters"
+	default n
+	depends on DEBUG_KERNEL
+	depends on ZCRYPT
+	help
+	  Say 'Y' here to enable some additional debug features on the
+	  s390 cryptographic adapters driver.
+
+	  There will be some more sysfs attributes displayed for ap cards
+	  and queues and some flags on crypto requests are interpreted as
+	  debugging messages to force error injection.
+
+	  Do not enable on production level kernel build.
+
+	  If unsure, say N.
 
 config ZCRYPT_MULTIDEVNODES
 	bool "Support for multiple zcrypt device nodes"

drivers/s390/char/Makefile

@@ -34,6 +34,8 @@ obj-$(CONFIG_SCLP_VT220_TTY) += sclp_vt220.o
 
 obj-$(CONFIG_PCI) += sclp_pci.o
 
+obj-$(subst m,y,$(CONFIG_ZCRYPT)) += sclp_ap.o
+
 obj-$(CONFIG_VMLOGRDR) += vmlogrdr.o
 obj-$(CONFIG_VMCP) += vmcp.o
 

drivers/s390/char/con3215.c

@@ -978,7 +978,6 @@ static int tty3215_install(struct tty_driver *driver, struct tty_struct *tty)
 static int tty3215_open(struct tty_struct *tty, struct file * filp)
 {
 	struct raw3215_info *raw = tty->driver_data;
-	int retval;
 
 	tty_port_tty_set(&raw->port, tty);
 
@@ -986,11 +985,7 @@ static int tty3215_open(struct tty_struct *tty, struct file * filp)
 	/*
 	 * Start up 3215 device
 	 */
-	retval = raw3215_startup(raw);
+	return raw3215_startup(raw);
-	if (retval)
-		return retval;
-
-	return 0;
 }
 
 /*

drivers/s390/char/raw3270.h

@@ -110,7 +110,6 @@ struct raw3270_request {
 };
 
 struct raw3270_request *raw3270_request_alloc(size_t size);
-struct raw3270_request *raw3270_request_alloc_bootmem(size_t size);
 void raw3270_request_free(struct raw3270_request *);
 void raw3270_request_reset(struct raw3270_request *);
 void raw3270_request_set_cmd(struct raw3270_request *, u8 cmd);

drivers/s390/char/sclp.h

@@ -229,7 +229,7 @@ static inline void sclp_fill_core_info(struct sclp_core_info *info,
 #define SCLP_HAS_CPU_INFO	(sclp.facilities & 0x0800000000000000ULL)
 #define SCLP_HAS_CPU_RECONFIG	(sclp.facilities & 0x0400000000000000ULL)
 #define SCLP_HAS_PCI_RECONFIG	(sclp.facilities & 0x0000000040000000ULL)
-
+#define SCLP_HAS_AP_RECONFIG	(sclp.facilities & 0x0000000100000000ULL)
 
 struct gds_subvector {
 	u8	length;
@@ -305,9 +305,7 @@ int sclp_deactivate(void);
 int sclp_reactivate(void);
 int sclp_sync_request(sclp_cmdw_t command, void *sccb);
 int sclp_sync_request_timeout(sclp_cmdw_t command, void *sccb, int timeout);
-
 int sclp_sdias_init(void);
-void sclp_sdias_exit(void);
 
 enum {
 	sclp_init_state_uninitialized,

drivers/s390/char/sclp_ap.c

@@ -0,0 +1,63 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * s390 crypto adapter related sclp functions.
+ *
+ * Copyright IBM Corp. 2020
+ */
+#define KMSG_COMPONENT "sclp_cmd"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
+#include <linux/export.h>
+#include <linux/slab.h>
+#include <asm/sclp.h>
+#include "sclp.h"
+
+#define SCLP_CMDW_CONFIGURE_AP			0x001f0001
+#define SCLP_CMDW_DECONFIGURE_AP		0x001e0001
+
+struct ap_cfg_sccb {
+	struct sccb_header header;
+} __packed;
+
+static int do_ap_configure(sclp_cmdw_t cmd, u32 apid)
+{
+	struct ap_cfg_sccb *sccb;
+	int rc;
+
+	if (!SCLP_HAS_AP_RECONFIG)
+		return -EOPNOTSUPP;
+
+	sccb = (struct ap_cfg_sccb *) get_zeroed_page(GFP_KERNEL | GFP_DMA);
+	if (!sccb)
+		return -ENOMEM;
+
+	sccb->header.length = PAGE_SIZE;
+	cmd |= (apid & 0xFF) << 8;
+	rc = sclp_sync_request(cmd, sccb);
+	if (rc)
+		goto out;
+	switch (sccb->header.response_code) {
+	case 0x0020: case 0x0120: case 0x0440: case 0x0450:
+		break;
+	default:
+		pr_warn("configure AP adapter %u failed: cmd=0x%08x response=0x%04x\n",
+			apid, cmd, sccb->header.response_code);
+		rc = -EIO;
+		break;
+	}
+out:
+	free_page((unsigned long) sccb);
+	return rc;
+}
+
+int sclp_ap_configure(u32 apid)
+{
+	return do_ap_configure(SCLP_CMDW_CONFIGURE_AP, apid);
+}
+EXPORT_SYMBOL(sclp_ap_configure);
+
+int sclp_ap_deconfigure(u32 apid)
+{
+	return do_ap_configure(SCLP_CMDW_DECONFIGURE_AP, apid);
+}
+EXPORT_SYMBOL(sclp_ap_deconfigure);

drivers/s390/char/sclp_early_core.c

@@ -17,12 +17,12 @@
 static struct read_info_sccb __bootdata(sclp_info_sccb);
 static int __bootdata(sclp_info_sccb_valid);
 char *sclp_early_sccb = (char *) EARLY_SCCB_OFFSET;
-int sclp_init_state __section(.data) = sclp_init_state_uninitialized;
+int sclp_init_state = sclp_init_state_uninitialized;
 /*
  * Used to keep track of the size of the event masks. Qemu until version 2.11
  * only supports 4 and needs a workaround.
  */
-bool sclp_mask_compat_mode __section(.data);
+bool sclp_mask_compat_mode;
 
 void sclp_early_wait_irq(void)
 {
@@ -214,11 +214,11 @@ static int sclp_early_setup(int disable, int *have_linemode, int *have_vt220)
  * Output one or more lines of text on the SCLP console (VT220 and /
  * or line-mode).
  */
-void __sclp_early_printk(const char *str, unsigned int len, unsigned int force)
+void __sclp_early_printk(const char *str, unsigned int len)
 {
 	int have_linemode, have_vt220;
 
-	if (!force && sclp_init_state != sclp_init_state_uninitialized)
+	if (sclp_init_state != sclp_init_state_uninitialized)
 		return;
 	if (sclp_early_setup(0, &have_linemode, &have_vt220) != 0)
 		return;
@@ -231,12 +231,7 @@ void __sclp_early_printk(const char *str, unsigned int len, unsigned int force)
 
 void sclp_early_printk(const char *str)
 {
-	__sclp_early_printk(str, strlen(str), 0);
+	__sclp_early_printk(str, strlen(str));
-}
-
-void sclp_early_printk_force(const char *str)
-{
-	__sclp_early_printk(str, strlen(str), 1);
 }
 
 int __init sclp_early_read_info(void)

drivers/s390/char/sclp_rw.c

@@ -336,24 +336,6 @@ sclp_chars_in_buffer(struct sclp_buffer *buffer)
 	return count;
 }
 
-/*
- * sets or provides some values that influence the drivers behaviour
- */
-void
-sclp_set_columns(struct sclp_buffer *buffer, unsigned short columns)
-{
-	buffer->columns = columns;
-	if (buffer->current_line != NULL &&
-	    buffer->current_length > buffer->columns)
-		sclp_finalize_mto(buffer);
-}
-
-void
-sclp_set_htab(struct sclp_buffer *buffer, unsigned short htab)
-{
-	buffer->htab = htab;
-}
-
 /*
  * called by sclp_console_init and/or sclp_tty_init
  */

drivers/s390/char/sclp_rw.h

@@ -86,8 +86,6 @@ void *sclp_unmake_buffer(struct sclp_buffer *);
 int sclp_buffer_space(struct sclp_buffer *);
 int sclp_write(struct sclp_buffer *buffer, const unsigned char *, int);
 int sclp_emit_buffer(struct sclp_buffer *,void (*)(struct sclp_buffer *,int));
-void sclp_set_columns(struct sclp_buffer *, unsigned short);
-void sclp_set_htab(struct sclp_buffer *, unsigned short);
 int sclp_chars_in_buffer(struct sclp_buffer *);
 
 #ifdef CONFIG_SCLP_CONSOLE

drivers/s390/char/sclp_sdias.c

@@ -257,7 +257,7 @@ static int __init sclp_sdias_init_async(void)
 
 int __init sclp_sdias_init(void)
 {
-	if (ipl_info.type != IPL_TYPE_FCP_DUMP)
+	if (!is_ipl_type_dump())
 		return 0;
 	sclp_sdias_sccb = (void *) __get_free_page(GFP_KERNEL | GFP_DMA);
 	BUG_ON(!sclp_sdias_sccb);
@@ -275,9 +275,3 @@ int __init sclp_sdias_init(void)
 	TRACE("init done\n");
 	return 0;
 }
-
-void __exit sclp_sdias_exit(void)
-{
-	debug_unregister(sdias_dbf);
-	sclp_unregister(&sclp_sdias_register);
-}

drivers/s390/char/tape.h

@@ -238,7 +238,6 @@ extern int tape_do_io(struct tape_device *, struct tape_request *);
 extern int tape_do_io_async(struct tape_device *, struct tape_request *);
 extern int tape_do_io_interruptible(struct tape_device *, struct tape_request *);
 extern int tape_cancel_io(struct tape_device *, struct tape_request *);
-void tape_hotplug_event(struct tape_device *, int major, int action);
 
 static inline int
 tape_do_io_free(struct tape_device *device, struct tape_request *request)
@@ -258,8 +257,6 @@ tape_do_io_async_free(struct tape_device *device, struct tape_request *request)
 	tape_do_io_async(device, request);
 }
 
-extern int tape_oper_handler(int irq, int status);
-extern void tape_noper_handler(int irq, int status);
 extern int tape_open(struct tape_device *);
 extern int tape_release(struct tape_device *);
 extern int tape_mtop(struct tape_device *, int, int);

drivers/s390/char/tape_std.h

@@ -101,7 +101,6 @@ struct tape_request *tape_std_read_block(struct tape_device *, size_t);
 void tape_std_read_backward(struct tape_device *device,
 			    struct tape_request *request);
 struct tape_request *tape_std_write_block(struct tape_device *, size_t);
-void tape_std_check_locate(struct tape_device *, struct tape_request *);
 
 /* Some non-mtop commands. */
 int tape_std_assign(struct tape_device *);
@@ -131,19 +130,8 @@ int tape_std_mtunload(struct tape_device *, int);
 int tape_std_mtweof(struct tape_device *, int);
 
 /* Event handlers */
-void tape_std_default_handler(struct tape_device *);
-void tape_std_unexpect_uchk_handler(struct tape_device *);
-void tape_std_irq(struct tape_device *);
 void tape_std_process_eov(struct tape_device *);
 
-// the error recovery stuff:
-void tape_std_error_recovery(struct tape_device *);
-void tape_std_error_recovery_has_failed(struct tape_device *,int error_id);
-void tape_std_error_recovery_succeded(struct tape_device *);
-void tape_std_error_recovery_do_retry(struct tape_device *);
-void tape_std_error_recovery_read_opposite(struct tape_device *);
-void tape_std_error_recovery_HWBUG(struct tape_device *, int condno);
-
 /* S390 tape types */
 enum s390_tape_type {
         tape_3480,