Merge tag 's390-6.15-1' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux

Pull s390 updates from Vasily Gorbik:

 - Add sorting of mcount locations at build time

 - Rework uaccess functions with C exception handling to shorten inline
   assembly size and enable full inlining. This yields near-optimal code
   for small constant copies with a ~40kb kernel size increase

 - Add support for a configurable STRICT_MM_TYPECHECKS which allows to
   generate better code, but also allows to have type checking for debug
   builds

 - Optimize get_lowcore() for common callers with alternatives that
   nearly revert to the pre-relocated lowcore code, while also slightly
   reducing syscall entry and exit time

 - Convert MACHINE_HAS_* checks for single facility tests into cpu_has_*
   style macros that call test_facility(), and for features with
   additional conditions, add a new ALT_TYPE_FEATURE alternative to
   provide a static branch via alternative patching. Also, move machine
   feature detection to the decompressor for early patching and add
   debugging functionality to easily show which alternatives are patched

 - Add exception table support to early boot / startup code to get rid
   of the open coded exception handling

 - Use asm_inline for all inline assemblies with EX_TABLE or ALTERNATIVE
   to ensure correct inlining and unrolling decisions

 - Remove 2k page table leftovers now that s390 has been switched to
   always allocate 4k page tables

 - Split kfence pool into 4k mappings in arch_kfence_init_pool() and
   remove the architecture-specific kfence_split_mapping()

 - Use READ_ONCE_NOCHECK() in regs_get_kernel_stack_nth() to silence
   spurious KASAN warnings from opportunistic ftrace argument tracing

 - Force __atomic_add_const() variants on s390 to always return void,
   ensuring compile errors for improper usage

 - Remove s390's ioremap_wt() and pgprot_writethrough() due to
   mismatched semantics and lack of known users, relying on asm-generic
   fallbacks

 - Signal eventfd in vfio-ap to notify userspace when the guest AP
   configuration changes, including during mdev removal

 - Convert mdev_types from an array to a pointer in vfio-ccw and vfio-ap
   drivers to avoid fake flex array confusion

 - Cleanup trap code

 - Remove references to the outdated [email protected] address

 - Other various small fixes and improvements all over the code

* tag 's390-6.15-1' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux: (78 commits)
  s390: Use inline qualifier for all EX_TABLE and ALTERNATIVE inline assemblies
  s390/kfence: Split kfence pool into 4k mappings in arch_kfence_init_pool()
  s390/ptrace: Avoid KASAN false positives in regs_get_kernel_stack_nth()
  s390/boot: Ignore vmlinux.map
  s390/sysctl: Remove "vm/allocate_pgste" sysctl
  s390: Remove 2k vs 4k page table leftovers
  s390/tlb: Use mm_has_pgste() instead of mm_alloc_pgste()
  s390/lowcore: Use lghi instead llilh to clear register
  s390/syscall: Merge __do_syscall() and do_syscall()
  s390/spinlock: Implement SPINLOCK_LOCKVAL with inline assembly
  s390/smp: Implement raw_smp_processor_id() with inline assembly
  s390/current: Implement current with inline assembly
  s390/lowcore: Use inline qualifier for get_lowcore() inline assembly
  s390: Move s390 sysctls into their own file under arch/s390
  s390/syscall: Simplify syscall_get_arguments()
  s390/vfio-ap: Notify userspace that guest's AP config changed when mdev removed
  s390: Remove ioremap_wt() and pgprot_writethrough()
  s390/mm: Add configurable STRICT_MM_TYPECHECKS
  s390/mm: Convert pgste_val() into function
  s390/mm: Convert pgprot_val() into function
  ...

Author: torvalds

arch/s390/Kconfig

@@ -70,7 +70,6 @@ config S390
 	imply IMA_SECURE_AND_OR_TRUSTED_BOOT
 	select ALTERNATE_USER_ADDRESS_SPACE
 	select ARCH_32BIT_USTAT_F_TINODE
-	select ARCH_BINFMT_ELF_STATE
 	select ARCH_CORRECT_STACKTRACE_ON_KRETPROBE
 	select ARCH_ENABLE_MEMORY_HOTPLUG if SPARSEMEM
 	select ARCH_ENABLE_MEMORY_HOTREMOVE
@@ -183,6 +182,7 @@ config S390
 	select HAVE_ARCH_TRANSPARENT_HUGEPAGE
 	select HAVE_ARCH_VMAP_STACK
 	select HAVE_ASM_MODVERSIONS
+	select HAVE_BUILDTIME_MCOUNT_SORT
 	select HAVE_CMPXCHG_DOUBLE
 	select HAVE_CMPXCHG_LOCAL
 	select HAVE_DEBUG_KMEMLEAK

arch/s390/Kconfig.debug

@@ -13,6 +13,16 @@ config DEBUG_ENTRY
 
 	  If unsure, say N.
 
+config STRICT_MM_TYPECHECKS
+	bool "Strict Memory Management Type Checks"
+	depends on DEBUG_KERNEL
+	help
+	  Enable strict type checking for memory management types like pte_t
+	  and pmd_t. This generates slightly worse code and should be used
+	  for debug builds.
+
+	  If unsure, say N.
+
 config CIO_INJECT
 	bool "CIO Inject interfaces"
 	depends on DEBUG_KERNEL && DEBUG_FS

arch/s390/boot/.gitignore

@@ -5,4 +5,5 @@ relocs.S
 section_cmp.*
 vmlinux
 vmlinux.lds
+vmlinux.map
 vmlinux.syms

arch/s390/boot/Makefile

@@ -26,7 +26,7 @@ CFLAGS_sclp_early_core.o += -I$(srctree)/drivers/s390/char
 
 obj-y	:= head.o als.o startup.o physmem_info.o ipl_parm.o ipl_report.o vmem.o
 obj-y	+= string.o ebcdic.o sclp_early_core.o mem.o ipl_vmparm.o cmdline.o
-obj-y	+= version.o pgm_check_info.o ctype.o ipl_data.o relocs.o alternative.o
+obj-y	+= version.o pgm_check.o ctype.o ipl_data.o relocs.o alternative.o
 obj-y	+= uv.o printk.o
 obj-$(CONFIG_RANDOMIZE_BASE)	+= kaslr.o
 obj-y	+= $(if $(CONFIG_KERNEL_UNCOMPRESSED),,decompressor.o) info.o

arch/s390/boot/alternative.c

@@ -1,3 +1,138 @@
 // SPDX-License-Identifier: GPL-2.0
+#define boot_fmt(fmt)	"alt: " fmt
+#include "boot.h"
+
+#define a_debug		boot_debug
 
 #include "../kernel/alternative.c"
+
+static void alt_debug_all(int type)
+{
+	int i;
+
+	switch (type) {
+	case ALT_TYPE_FACILITY:
+		for (i = 0; i < ARRAY_SIZE(alt_debug.facilities); i++)
+			alt_debug.facilities[i] = -1UL;
+		break;
+	case ALT_TYPE_FEATURE:
+		for (i = 0; i < ARRAY_SIZE(alt_debug.mfeatures); i++)
+			alt_debug.mfeatures[i] = -1UL;
+		break;
+	case ALT_TYPE_SPEC:
+		alt_debug.spec = 1;
+		break;
+	}
+}
+
+static void alt_debug_modify(int type, unsigned int nr, bool clear)
+{
+	switch (type) {
+	case ALT_TYPE_FACILITY:
+		if (clear)
+			__clear_facility(nr, alt_debug.facilities);
+		else
+			__set_facility(nr, alt_debug.facilities);
+		break;
+	case ALT_TYPE_FEATURE:
+		if (clear)
+			__clear_machine_feature(nr, alt_debug.mfeatures);
+		else
+			__set_machine_feature(nr, alt_debug.mfeatures);
+		break;
+	}
+}
+
+static char *alt_debug_parse(int type, char *str)
+{
+	unsigned long val, endval;
+	char *endp;
+	bool clear;
+	int i;
+
+	if (*str == ':') {
+		str++;
+	} else {
+		alt_debug_all(type);
+		return str;
+	}
+	clear = false;
+	if (*str == '!') {
+		alt_debug_all(type);
+		clear = true;
+		str++;
+	}
+	while (*str) {
+		val = simple_strtoull(str, &endp, 0);
+		if (str == endp)
+			break;
+		str = endp;
+		if (*str == '-') {
+			str++;
+			endval = simple_strtoull(str, &endp, 0);
+			if (str == endp)
+				break;
+			str = endp;
+			while (val <= endval) {
+				alt_debug_modify(type, val, clear);
+				val++;
+			}
+		} else {
+			alt_debug_modify(type, val, clear);
+		}
+		if (*str != ',')
+			break;
+		str++;
+	}
+	return str;
+}
+
+/*
+ * Use debug-alternative command line parameter for debugging:
+ * "debug-alternative"
+ *  -> print debug message for every single alternative
+ *
+ * "debug-alternative=0;2"
+ * -> print debug message for all alternatives with type 0 and 2
+ *
+ * "debug-alternative=0:0-7"
+ * -> print debug message for all alternatives with type 0 and with
+ *    facility numbers within the range of 0-7
+ *    (if type 0 is ALT_TYPE_FACILITY)
+ *
+ * "debug-alternative=0:!8;1"
+ * -> print debug message for all alternatives with type 0, for all
+ *    facility number, except facility 8, and in addition print all
+ *    alternatives with type 1
+ */
+void alt_debug_setup(char *str)
+{
+	unsigned long type;
+	char *endp;
+	int i;
+
+	if (!str) {
+		alt_debug_all(ALT_TYPE_FACILITY);
+		alt_debug_all(ALT_TYPE_FEATURE);
+		alt_debug_all(ALT_TYPE_SPEC);
+		return;
+	}
+	while (*str) {
+		type = simple_strtoull(str, &endp, 0);
+		if (str == endp)
+			break;
+		str = endp;
+		switch (type) {
+		case ALT_TYPE_FACILITY:
+		case ALT_TYPE_FEATURE:
+			str = alt_debug_parse(type, str);
+			break;
+		case ALT_TYPE_SPEC:
+			alt_debug_all(ALT_TYPE_SPEC);
+			break;
+		}
+		if (*str != ';')
+			break;
+		str++;
+	}
+}

arch/s390/boot/boot.h

@@ -11,11 +11,6 @@
 #include <linux/printk.h>
 #include <asm/physmem_info.h>
 
-struct machine_info {
-	unsigned char has_edat1 : 1;
-	unsigned char has_edat2 : 1;
-};
-
 struct vmlinux_info {
 	unsigned long entry;
 	unsigned long image_size;	/* does not include .bss */
@@ -69,7 +64,8 @@ void parse_boot_command_line(void);
 void verify_facilities(void);
 void print_missing_facilities(void);
 void sclp_early_setup_buffer(void);
-void print_pgm_check_info(void);
+void alt_debug_setup(char *str);
+void do_pgm_check(struct pt_regs *regs);
 unsigned long randomize_within_range(unsigned long size, unsigned long align,
 				     unsigned long min, unsigned long max);
 void setup_vmem(unsigned long kernel_start, unsigned long kernel_end, unsigned long asce_limit);

arch/s390/boot/head.S

@@ -254,8 +254,9 @@ SYM_CODE_START_LOCAL(startup_normal)
 	xc	0xf00(256),0xf00
 	larl	%r13,.Lctl
 	lctlg	%c0,%c15,0(%r13)	# load control registers
-	stcke	__LC_BOOT_CLOCK
-	mvc	__LC_LAST_UPDATE_CLOCK(8),__LC_BOOT_CLOCK+1
+	larl	%r13,tod_clock_base
+	stcke	0(%r13)
+	mvc	__LC_LAST_UPDATE_CLOCK(8),1(%r13)
 	larl	%r13,6f
 	spt	0(%r13)
 	mvc	__LC_LAST_UPDATE_TIMER(8),0(%r13)
@@ -292,12 +293,6 @@ SYM_CODE_END(startup_normal)
 
 #include "head_kdump.S"
 
-#
-# This program check is active immediately after kernel start
-# and until early_pgm_check_handler is set in kernel/early.c
-# It simply saves general/control registers and psw in
-# the save area and does disabled wait with a faulty address.
-#
 SYM_CODE_START_LOCAL(startup_pgm_check_handler)
 	stmg	%r8,%r15,__LC_SAVE_AREA
 	la	%r8,4095
@@ -311,8 +306,18 @@ SYM_CODE_START_LOCAL(startup_pgm_check_handler)
 	oi	__LC_RETURN_PSW+1,0x2	# set wait state bit
 	larl	%r9,.Lold_psw_disabled_wait
 	stg	%r9,__LC_PGM_NEW_PSW+8
-	larl	%r15,_dump_info_stack_end-STACK_FRAME_OVERHEAD
-	brasl	%r14,print_pgm_check_info
+	larl	%r15,_dump_info_stack_end-(STACK_FRAME_OVERHEAD+__PT_SIZE)
+	la	%r2,STACK_FRAME_OVERHEAD(%r15)
+	mvc	__PT_PSW(16,%r2),__LC_PSW_SAVE_AREA-4095(%r8)
+	mvc	__PT_R0(128,%r2),__LC_GPREGS_SAVE_AREA-4095(%r8)
+	mvc	__PT_LAST_BREAK(8,%r2),__LC_PGM_LAST_BREAK
+	mvc	__PT_INT_CODE(4,%r2),__LC_PGM_INT_CODE
+	brasl	%r14,do_pgm_check
+	larl	%r9,startup_pgm_check_handler
+	stg	%r9,__LC_PGM_NEW_PSW+8
+	mvc	__LC_RETURN_PSW(16),STACK_FRAME_OVERHEAD+__PT_PSW(%r15)
+	lmg	%r0,%r15,STACK_FRAME_OVERHEAD+__PT_R0(%r15)
+	lpswe	__LC_RETURN_PSW
 .Lold_psw_disabled_wait:
 	la	%r8,4095
 	lmg	%r0,%r15,__LC_GPREGS_SAVE_AREA-4095(%r8)

arch/s390/boot/ipl_parm.c

@@ -5,6 +5,7 @@
 #include <linux/pgtable.h>
 #include <asm/abs_lowcore.h>
 #include <asm/page-states.h>
+#include <asm/machine.h>
 #include <asm/ebcdic.h>
 #include <asm/sclp.h>
 #include <asm/sections.h>
@@ -34,29 +35,14 @@ int vmalloc_size_set;
 
 static inline int __diag308(unsigned long subcode, void *addr)
 {
-	unsigned long reg1, reg2;
-	union register_pair r1;
-	psw_t old;
-
-	r1.even = (unsigned long) addr;
-	r1.odd	= 0;
-	asm volatile(
-		"	mvc	0(16,%[psw_old]),0(%[psw_pgm])\n"
-		"	epsw	%[reg1],%[reg2]\n"
-		"	st	%[reg1],0(%[psw_pgm])\n"
-		"	st	%[reg2],4(%[psw_pgm])\n"
-		"	larl	%[reg1],1f\n"
-		"	stg	%[reg1],8(%[psw_pgm])\n"
+	union register_pair r1 = { .even = (unsigned long)addr, .odd = 0 };
+
+	asm_inline volatile(
 		"	diag	%[r1],%[subcode],0x308\n"
-		"1:	mvc	0(16,%[psw_pgm]),0(%[psw_old])\n"
-		: [r1] "+&d" (r1.pair),
-		  [reg1] "=&d" (reg1),
-		  [reg2] "=&a" (reg2),
-		  "+Q" (get_lowcore()->program_new_psw),
-		  "=Q" (old)
-		: [subcode] "d" (subcode),
-		  [psw_old] "a" (&old),
-		  [psw_pgm] "a" (&get_lowcore()->program_new_psw)
+		"0:\n"
+		EX_TABLE(0b, 0b)
+		: [r1] "+d" (r1.pair)
+		: [subcode] "d" (subcode)
 		: "cc", "memory");
 	return r1.odd;
 }
@@ -295,6 +281,9 @@ void parse_boot_command_line(void)
 		if (!strcmp(param, "facilities") && val)
 			modify_fac_list(val);
 
+		if (!strcmp(param, "debug-alternative"))
+			alt_debug_setup(val);
+
 		if (!strcmp(param, "nokaslr"))
 			__kaslr_enabled = 0;
 
@@ -312,7 +301,7 @@ void parse_boot_command_line(void)
 		}
 #endif
 		if (!strcmp(param, "relocate_lowcore") && test_facility(193))
-			relocate_lowcore = 1;
+			set_machine_feature(MFEATURE_LOWCORE);
 		if (!strcmp(param, "earlyprintk"))
 			boot_earlyprintk = true;
 		if (!strcmp(param, "debug"))

arch/s390/boot/pgm_check_info.c arch/s390/boot/pgm_check.c

@@ -32,35 +32,61 @@ void print_stacktrace(unsigned long sp)
 	}
 }
 
-void print_pgm_check_info(void)
+extern struct exception_table_entry __start___ex_table[];
+extern struct exception_table_entry __stop___ex_table[];
+
+static inline unsigned long extable_insn(const struct exception_table_entry *x)
+{
+	return (unsigned long)&x->insn + x->insn;
+}
+
+static bool ex_handler(struct pt_regs *regs)
+{
+	const struct exception_table_entry *ex;
+
+	for (ex = __start___ex_table; ex < __stop___ex_table; ex++) {
+		if (extable_insn(ex) != regs->psw.addr)
+			continue;
+		if (ex->type != EX_TYPE_FIXUP)
+			return false;
+		regs->psw.addr = extable_fixup(ex);
+		return true;
+	}
+	return false;
+}
+
+void do_pgm_check(struct pt_regs *regs)
 {
-	unsigned long *gpregs = (unsigned long *)get_lowcore()->gpregs_save_area;
-	struct psw_bits *psw = &psw_bits(get_lowcore()->psw_save_area);
+	struct psw_bits *psw = &psw_bits(regs->psw);
+	unsigned long *gpregs = regs->gprs;
 
+	if (ex_handler(regs))
+		return;
 	if (bootdebug)
 		boot_rb_dump();
 	boot_emerg("Linux version %s\n", kernel_version);
 	if (!is_prot_virt_guest() && early_command_line[0])
 		boot_emerg("Kernel command line: %s\n", early_command_line);
 	boot_emerg("Kernel fault: interruption code %04x ilc:%d\n",
-		   get_lowcore()->pgm_code, get_lowcore()->pgm_ilc >> 1);
+		   regs->int_code & 0xffff, regs->int_code >> 17);
 	if (kaslr_enabled()) {
 		boot_emerg("Kernel random base: %lx\n", __kaslr_offset);
 		boot_emerg("Kernel random base phys: %lx\n", __kaslr_offset_phys);
 	}
 	boot_emerg("PSW : %016lx %016lx (%pS)\n",
-		   get_lowcore()->psw_save_area.mask,
-		   get_lowcore()->psw_save_area.addr,
-		   (void *)get_lowcore()->psw_save_area.addr);
+		   regs->psw.mask, regs->psw.addr, (void *)regs->psw.addr);
 	boot_emerg("      R:%x T:%x IO:%x EX:%x Key:%x M:%x W:%x P:%x AS:%x CC:%x PM:%x RI:%x EA:%x\n",
 		   psw->per, psw->dat, psw->io, psw->ext, psw->key, psw->mcheck,
 		   psw->wait, psw->pstate, psw->as, psw->cc, psw->pm, psw->ri, psw->eaba);
 	boot_emerg("GPRS: %016lx %016lx %016lx %016lx\n", gpregs[0], gpregs[1], gpregs[2], gpregs[3]);
 	boot_emerg("      %016lx %016lx %016lx %016lx\n", gpregs[4], gpregs[5], gpregs[6], gpregs[7]);
 	boot_emerg("      %016lx %016lx %016lx %016lx\n", gpregs[8], gpregs[9], gpregs[10], gpregs[11]);
 	boot_emerg("      %016lx %016lx %016lx %016lx\n", gpregs[12], gpregs[13], gpregs[14], gpregs[15]);
-	print_stacktrace(get_lowcore()->gpregs_save_area[15]);
+	print_stacktrace(gpregs[15]);
 	boot_emerg("Last Breaking-Event-Address:\n");
-	boot_emerg(" [<%016lx>] %pS\n", (unsigned long)get_lowcore()->pgm_last_break,
-		   (void *)get_lowcore()->pgm_last_break);
+	boot_emerg(" [<%016lx>] %pS\n", regs->last_break, (void *)regs->last_break);
+	/* Convert to disabled wait PSW */
+	psw->io = 0;
+	psw->ext = 0;
+	psw->wait = 1;
 }