Merge tag 's390-6.9-1' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux

Pull s390 updates from Heiko Carstens:

 - Various virtual vs physical address usage fixes

 - Fix error handling in Processor Activity Instrumentation device
   driver, and export number of counters with a sysfs file

 - Allow for multiple events when Processor Activity Instrumentation
   counters are monitored in system wide sampling

 - Change multiplier and shift values of the Time-of-Day clock source to
   improve steering precision

 - Remove a couple of unneeded GFP_DMA flags from allocations

 - Disable mmap alignment if randomize_va_space is also disabled, to
   avoid a too small heap

 - Various changes to allow s390 to be compiled with LLVM=1, since
   ld.lld and llvm-objcopy will have proper s390 support witch clang 19

 - Add __uninitialized macro to Compiler Attributes. This is helpful
   with s390's FPU code where some users have up to 520 byte stack
   frames. Clearing such stack frames (if INIT_STACK_ALL_PATTERN or
   INIT_STACK_ALL_ZERO is enabled) before they are used contradicts the
   intention (performance improvement) of such code sections.

 - Convert switch_to() to an out-of-line function, and use the generic
   switch_to header file

 - Replace the usage of s390's debug feature with pr_debug() calls
   within the zcrypt device driver

 - Improve hotplug support of the Adjunct Processor device driver

 - Improve retry handling in the zcrypt device driver

 - Various changes to the in-kernel FPU code:

     - Make in-kernel FPU sections preemptible

     - Convert various larger inline assemblies and assembler files to
       C, mainly by using singe instruction inline assemblies. This
       increases readability, but also allows makes it easier to add
       proper instrumentation hooks

     - Cleanup of the header files

 - Provide fast variants of csum_partial() and
   csum_partial_copy_nocheck() based on vector instructions

 - Introduce and use a lock to synchronize accesses to zpci device data
   structures to avoid inconsistent states caused by concurrent accesses

 - Compile the kernel without -fPIE. This addresses the following
   problems if the kernel is compiled with -fPIE:

     - It uses dynamic symbols (.dynsym), for which the linker refuses
       to allow more than 64k sections. This can break features which
       use '-ffunction-sections' and '-fdata-sections', including
       kpatch-build and function granular KASLR

     - It unnecessarily uses GOT relocations, adding an extra layer of
       indirection for many memory accesses

 - Fix shared_cpu_list for CPU private L2 caches, which incorrectly were
   reported as globally shared

* tag 's390-6.9-1' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux: (117 commits)
  s390/tools: handle rela R_390_GOTPCDBL/R_390_GOTOFF64
  s390/cache: prevent rebuild of shared_cpu_list
  s390/crypto: remove retry loop with sleep from PAES pkey invocation
  s390/pkey: improve pkey retry behavior
  s390/zcrypt: improve zcrypt retry behavior
  s390/zcrypt: introduce retries on in-kernel send CPRB functions
  s390/ap: introduce mutex to lock the AP bus scan
  s390/ap: rework ap_scan_bus() to return true on config change
  s390/ap: clarify AP scan bus related functions and variables
  s390/ap: rearm APQNs bindings complete completion
  s390/configs: increase number of LOCKDEP_BITS
  s390/vfio-ap: handle hardware checkstop state on queue reset operation
  s390/pai: change sampling event assignment for PMU device driver
  s390/boot: fix minor comment style damages
  s390/boot: do not check for zero-termination relocation entry
  s390/boot: make type of __vmlinux_relocs_64_start|end consistent
  s390/boot: sanitize kaslr_adjust_relocs() function prototype
  s390/boot: simplify GOT handling
  s390: vmlinux.lds.S: fix .got.plt assertion
  s390/boot: workaround current 'llvm-objdump -t -j ...' behavior
  ...

Author: torvalds

arch/s390/Kconfig

@@ -127,6 +127,7 @@ config S390
 	select ARCH_WANT_DEFAULT_BPF_JIT
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select ARCH_WANT_KERNEL_PMD_MKWRITE
+	select ARCH_WANT_LD_ORPHAN_WARN
 	select ARCH_WANT_OPTIMIZE_HUGETLB_VMEMMAP
 	select BUILDTIME_TABLE_SORT
 	select CLONE_BACKWARDS2
@@ -448,7 +449,7 @@ config COMPAT
 	select COMPAT_OLD_SIGACTION
 	select HAVE_UID16
 	depends on MULTIUSER
-	depends on !CC_IS_CLANG
+	depends on !CC_IS_CLANG && !LD_IS_LLD
 	help
 	  Select this option if you want to enable your system kernel to
 	  handle system-calls from ELF binaries for 31 bit ESA.  This option
@@ -582,14 +583,23 @@ config RELOCATABLE
 	help
 	  This builds a kernel image that retains relocation information
 	  so it can be loaded at an arbitrary address.
-	  The kernel is linked as a position-independent executable (PIE)
-	  and contains dynamic relocations which are processed early in the
-	  bootup process.
 	  The relocations make the kernel image about 15% larger (compressed
 	  10%), but are discarded at runtime.
 	  Note: this option exists only for documentation purposes, please do
 	  not remove it.
 
+config PIE_BUILD
+	def_bool CC_IS_CLANG && !$(cc-option,-munaligned-symbols)
+	help
+	  If the compiler is unable to generate code that can manage unaligned
+	  symbols, the kernel is linked as a position-independent executable
+	  (PIE) and includes dynamic relocations that are processed early
+	  during bootup.
+
+	  For kpatch functionality, it is recommended to build the kernel
+	  without the PIE_BUILD option. PIE_BUILD is only enabled when the
+	  compiler lacks proper support for handling unaligned symbols.
+
 config RANDOMIZE_BASE
 	bool "Randomize the address of the kernel image (KASLR)"
 	default y

arch/s390/Makefile

@@ -14,8 +14,14 @@ KBUILD_AFLAGS_MODULE += -fPIC
 KBUILD_CFLAGS_MODULE += -fPIC
 KBUILD_AFLAGS	+= -m64
 KBUILD_CFLAGS	+= -m64
+ifdef CONFIG_PIE_BUILD
 KBUILD_CFLAGS	+= -fPIE
-LDFLAGS_vmlinux	:= -pie
+LDFLAGS_vmlinux	:= -pie -z notext
+else
+KBUILD_CFLAGS	+= $(call cc-option,-munaligned-symbols,)
+LDFLAGS_vmlinux	:= --emit-relocs --discard-none
+extra_tools	:= relocs
+endif
 aflags_dwarf	:= -Wa,-gdwarf-2
 KBUILD_AFLAGS_DECOMPRESSOR := $(CLANG_FLAGS) -m64 -D__ASSEMBLY__
 ifndef CONFIG_AS_IS_LLVM
@@ -143,7 +149,7 @@ archheaders:
 
 archprepare:
 	$(Q)$(MAKE) $(build)=$(syscalls) kapi
-	$(Q)$(MAKE) $(build)=$(tools) kapi
+	$(Q)$(MAKE) $(build)=$(tools) kapi $(extra_tools)
 ifeq ($(KBUILD_EXTMOD),)
 # We need to generate vdso-offsets.h before compiling certain files in kernel/.
 # In order to do that, we should use the archprepare target, but we can't since

arch/s390/boot/.gitignore

@@ -1,6 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0-only
 image
 bzImage
+relocs.S
 section_cmp.*
 vmlinux
 vmlinux.lds

arch/s390/boot/Makefile

@@ -37,7 +37,8 @@ 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 machine_kexec_reloc.o
+obj-y	+= version.o pgm_check_info.o ctype.o ipl_data.o
+obj-y	+= $(if $(CONFIG_PIE_BUILD),machine_kexec_reloc.o,relocs.o)
 obj-$(findstring y, $(CONFIG_PROTECTED_VIRTUALIZATION_GUEST) $(CONFIG_PGSTE))	+= uv.o
 obj-$(CONFIG_RANDOMIZE_BASE)	+= kaslr.o
 obj-y	+= $(if $(CONFIG_KERNEL_UNCOMPRESSED),,decompressor.o) info.o
@@ -48,6 +49,9 @@ targets	:= bzImage section_cmp.boot.data section_cmp.boot.preserved.data $(obj-y
 targets	+= vmlinux.lds vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2
 targets += vmlinux.bin.xz vmlinux.bin.lzma vmlinux.bin.lzo vmlinux.bin.lz4
 targets += vmlinux.bin.zst info.bin syms.bin vmlinux.syms $(obj-all)
+ifndef CONFIG_PIE_BUILD
+targets += relocs.S
+endif
 
 OBJECTS := $(addprefix $(obj)/,$(obj-y))
 OBJECTS_ALL := $(addprefix $(obj)/,$(obj-all))
@@ -56,9 +60,9 @@ clean-files += vmlinux.map
 
 quiet_cmd_section_cmp = SECTCMP $*
 define cmd_section_cmp
-	s1=`$(OBJDUMP) -t -j "$*" "$<" | sort | \
+	s1=`$(OBJDUMP) -t "$<" | grep "\s$*\s\+" | sort | \
 		sed -n "/0000000000000000/! s/.*\s$*\s\+//p" | sha256sum`; \
-	s2=`$(OBJDUMP) -t -j "$*" "$(word 2,$^)" | sort | \
+	s2=`$(OBJDUMP) -t "$(word 2,$^)" | grep "\s$*\s\+" | sort | \
 		sed -n "/0000000000000000/! s/.*\s$*\s\+//p" | sha256sum`; \
 	if [ "$$s1" != "$$s2" ]; then \
 		echo "error: section $* differs between $< and $(word 2,$^)" >&2; \
@@ -73,11 +77,12 @@ $(obj)/bzImage: $(obj)/vmlinux $(obj)/section_cmp.boot.data $(obj)/section_cmp.b
 $(obj)/section_cmp%: vmlinux $(obj)/vmlinux FORCE
 	$(call if_changed,section_cmp)
 
-LDFLAGS_vmlinux := --oformat $(LD_BFD) -e startup $(if $(CONFIG_VMLINUX_MAP),-Map=$(obj)/vmlinux.map) --build-id=sha1 -T
+LDFLAGS_vmlinux-$(CONFIG_LD_ORPHAN_WARN) := --orphan-handling=$(CONFIG_LD_ORPHAN_WARN_LEVEL)
+LDFLAGS_vmlinux := $(LDFLAGS_vmlinux-y) --oformat $(LD_BFD) -e startup $(if $(CONFIG_VMLINUX_MAP),-Map=$(obj)/vmlinux.map) --build-id=sha1 -T
 $(obj)/vmlinux: $(obj)/vmlinux.lds $(OBJECTS_ALL) FORCE
 	$(call if_changed,ld)
 
-LDFLAGS_vmlinux.syms := --oformat $(LD_BFD) -e startup -T
+LDFLAGS_vmlinux.syms := $(LDFLAGS_vmlinux-y) --oformat $(LD_BFD) -e startup -T
 $(obj)/vmlinux.syms: $(obj)/vmlinux.lds $(OBJECTS) FORCE
 	$(call if_changed,ld)
 
@@ -93,7 +98,7 @@ OBJCOPYFLAGS_syms.o := -I binary -O elf64-s390 -B s390:64-bit --rename-section .
 $(obj)/syms.o: $(obj)/syms.bin FORCE
 	$(call if_changed,objcopy)
 
-OBJCOPYFLAGS_info.bin := -O binary --only-section=.vmlinux.info --set-section-flags .vmlinux.info=load
+OBJCOPYFLAGS_info.bin := -O binary --only-section=.vmlinux.info --set-section-flags .vmlinux.info=alloc,load
 $(obj)/info.bin: vmlinux FORCE
 	$(call if_changed,objcopy)
 
@@ -105,6 +110,14 @@ OBJCOPYFLAGS_vmlinux.bin := -O binary --remove-section=.comment --remove-section
 $(obj)/vmlinux.bin: vmlinux FORCE
 	$(call if_changed,objcopy)
 
+ifndef CONFIG_PIE_BUILD
+CMD_RELOCS=arch/s390/tools/relocs
+quiet_cmd_relocs = RELOCS $@
+	cmd_relocs = $(CMD_RELOCS) $< > $@
+$(obj)/relocs.S: vmlinux FORCE
+	$(call if_changed,relocs)
+endif
+
 suffix-$(CONFIG_KERNEL_GZIP)  := .gz
 suffix-$(CONFIG_KERNEL_BZIP2) := .bz2
 suffix-$(CONFIG_KERNEL_LZ4)  := .lz4

arch/s390/boot/boot.h

@@ -25,9 +25,14 @@ struct vmlinux_info {
 	unsigned long bootdata_size;
 	unsigned long bootdata_preserved_off;
 	unsigned long bootdata_preserved_size;
+#ifdef CONFIG_PIE_BUILD
 	unsigned long dynsym_start;
 	unsigned long rela_dyn_start;
 	unsigned long rela_dyn_end;
+#else
+	unsigned long got_start;
+	unsigned long got_end;
+#endif
 	unsigned long amode31_size;
 	unsigned long init_mm_off;
 	unsigned long swapper_pg_dir_off;
@@ -83,6 +88,7 @@ extern unsigned long vmalloc_size;
 extern int vmalloc_size_set;
 extern char __boot_data_start[], __boot_data_end[];
 extern char __boot_data_preserved_start[], __boot_data_preserved_end[];
+extern char __vmlinux_relocs_64_start[], __vmlinux_relocs_64_end[];
 extern char _decompressor_syms_start[], _decompressor_syms_end[];
 extern char _stack_start[], _stack_end[];
 extern char _end[], _decompressor_end[];

arch/s390/boot/startup.c

@@ -141,7 +141,8 @@ static void copy_bootdata(void)
 	memcpy((void *)vmlinux.bootdata_preserved_off, __boot_data_preserved_start, vmlinux.bootdata_preserved_size);
 }
 
-static void handle_relocs(unsigned long offset)
+#ifdef CONFIG_PIE_BUILD
+static void kaslr_adjust_relocs(unsigned long min_addr, unsigned long max_addr, unsigned long offset)
 {
 	Elf64_Rela *rela_start, *rela_end, *rela;
 	int r_type, r_sym, rc;
@@ -172,6 +173,54 @@ static void handle_relocs(unsigned long offset)
 	}
 }
 
+static void kaslr_adjust_got(unsigned long offset) {}
+static void rescue_relocs(void) {}
+static void free_relocs(void) {}
+#else
+static int *vmlinux_relocs_64_start;
+static int *vmlinux_relocs_64_end;
+
+static void rescue_relocs(void)
+{
+	unsigned long size = __vmlinux_relocs_64_end - __vmlinux_relocs_64_start;
+
+	vmlinux_relocs_64_start = (void *)physmem_alloc_top_down(RR_RELOC, size, 0);
+	vmlinux_relocs_64_end = (void *)vmlinux_relocs_64_start + size;
+	memmove(vmlinux_relocs_64_start, __vmlinux_relocs_64_start, size);
+}
+
+static void free_relocs(void)
+{
+	physmem_free(RR_RELOC);
+}
+
+static void kaslr_adjust_relocs(unsigned long min_addr, unsigned long max_addr, unsigned long offset)
+{
+	int *reloc;
+	long loc;
+
+	/* Adjust R_390_64 relocations */
+	for (reloc = vmlinux_relocs_64_start; reloc < vmlinux_relocs_64_end; reloc++) {
+		loc = (long)*reloc + offset;
+		if (loc < min_addr || loc > max_addr)
+			error("64-bit relocation outside of kernel!\n");
+		*(u64 *)loc += offset;
+	}
+}
+
+static void kaslr_adjust_got(unsigned long offset)
+{
+	u64 *entry;
+
+	/*
+	 * Even without -fPIE, Clang still uses a global offset table for some
+	 * reason. Adjust the GOT entries.
+	 */
+	for (entry = (u64 *)vmlinux.got_start; entry < (u64 *)vmlinux.got_end; entry++)
+		*entry += offset;
+}
+#endif
+
 /*
  * Merge information from several sources into a single ident_map_size value.
  * "ident_map_size" represents the upper limit of physical memory we may ever
@@ -299,14 +348,19 @@ static void setup_vmalloc_size(void)
 	vmalloc_size = max(size, vmalloc_size);
 }
 
-static void offset_vmlinux_info(unsigned long offset)
+static void kaslr_adjust_vmlinux_info(unsigned long offset)
 {
 	*(unsigned long *)(&vmlinux.entry) += offset;
 	vmlinux.bootdata_off += offset;
 	vmlinux.bootdata_preserved_off += offset;
+#ifdef CONFIG_PIE_BUILD
 	vmlinux.rela_dyn_start += offset;
 	vmlinux.rela_dyn_end += offset;
 	vmlinux.dynsym_start += offset;
+#else
+	vmlinux.got_start += offset;
+	vmlinux.got_end += offset;
+#endif
 	vmlinux.init_mm_off += offset;
 	vmlinux.swapper_pg_dir_off += offset;
 	vmlinux.invalid_pg_dir_off += offset;
@@ -361,14 +415,15 @@ void startup_kernel(void)
 	detect_physmem_online_ranges(max_physmem_end);
 	save_ipl_cert_comp_list();
 	rescue_initrd(safe_addr, ident_map_size);
+	rescue_relocs();
 
 	if (kaslr_enabled()) {
 		vmlinux_lma = randomize_within_range(vmlinux.image_size + vmlinux.bss_size,
 						     THREAD_SIZE, vmlinux.default_lma,
 						     ident_map_size);
 		if (vmlinux_lma) {
 			__kaslr_offset = vmlinux_lma - vmlinux.default_lma;
-			offset_vmlinux_info(__kaslr_offset);
+			kaslr_adjust_vmlinux_info(__kaslr_offset);
 		}
 	}
 	vmlinux_lma = vmlinux_lma ?: vmlinux.default_lma;
@@ -393,18 +448,20 @@ void startup_kernel(void)
 	/*
 	 * The order of the following operations is important:
 	 *
-	 * - handle_relocs() must follow clear_bss_section() to establish static
-	 *   memory references to data in .bss to be used by setup_vmem()
+	 * - kaslr_adjust_relocs() must follow clear_bss_section() to establish
+	 *   static memory references to data in .bss to be used by setup_vmem()
 	 *   (i.e init_mm.pgd)
 	 *
-	 * - setup_vmem() must follow handle_relocs() to be able using
+	 * - setup_vmem() must follow kaslr_adjust_relocs() to be able using
 	 *   static memory references to data in .bss (i.e init_mm.pgd)
 	 *
-	 * - copy_bootdata() must follow setup_vmem() to propagate changes to
-	 *   bootdata made by setup_vmem()
+	 * - copy_bootdata() must follow setup_vmem() to propagate changes
+	 *   to bootdata made by setup_vmem()
 	 */
 	clear_bss_section(vmlinux_lma);
-	handle_relocs(__kaslr_offset);
+	kaslr_adjust_relocs(vmlinux_lma, vmlinux_lma + vmlinux.image_size, __kaslr_offset);
+	kaslr_adjust_got(__kaslr_offset);
+	free_relocs();
 	setup_vmem(asce_limit);
 	copy_bootdata();
 

arch/s390/boot/vmlinux.lds.S

@@ -31,6 +31,7 @@ SECTIONS
 		_text = .;	/* Text */
 		*(.text)
 		*(.text.*)
+		INIT_TEXT
 		_etext = . ;
 	}
 	.rodata : {
@@ -39,6 +40,9 @@ SECTIONS
 		*(.rodata.*)
 		_erodata = . ;
 	}
+	.got : {
+		*(.got)
+	}
 	NOTES
 	.data :	{
 		_data = . ;
@@ -106,6 +110,24 @@ SECTIONS
 		_compressed_end = .;
 	}
 
+#ifndef CONFIG_PIE_BUILD
+	/*
+	 * When the kernel is built with CONFIG_KERNEL_UNCOMPRESSED, the entire
+	 * uncompressed vmlinux.bin is positioned in the bzImage decompressor
+	 * image at the default kernel LMA of 0x100000, enabling it to be
+	 * executed in-place. However, the size of .vmlinux.relocs could be
+	 * large enough to cause an overlap with the uncompressed kernel at the
+	 * address 0x100000. To address this issue, .vmlinux.relocs is
+	 * positioned after the .rodata.compressed.
+	 */
+	. = ALIGN(4);
+	.vmlinux.relocs : {
+		__vmlinux_relocs_64_start = .;
+		*(.vmlinux.relocs_64)
+		__vmlinux_relocs_64_end = .;
+	}
+#endif
+
 #define SB_TRAILER_SIZE 32
 	/* Trailer needed for Secure Boot */
 	. += SB_TRAILER_SIZE; /* make sure .sb.trailer does not overwrite the previous section */
@@ -118,8 +140,34 @@ SECTIONS
 	}
 	_end = .;
 
+	DWARF_DEBUG
+	ELF_DETAILS
+
+	/*
+	 * Make sure that the .got.plt is either completely empty or it
+	 * contains only the three reserved double words.
+	 */
+	.got.plt : {
+		*(.got.plt)
+	}
+	ASSERT(SIZEOF(.got.plt) == 0 || SIZEOF(.got.plt) == 0x18, "Unexpected GOT/PLT entries detected!")
+
+	/*
+	 * Sections that should stay zero sized, which is safer to
+	 * explicitly check instead of blindly discarding.
+	 */
+	.plt : {
+		*(.plt) *(.plt.*) *(.iplt) *(.igot .igot.plt)
+	}
+	ASSERT(SIZEOF(.plt) == 0, "Unexpected run-time procedure linkages detected!")
+	.rela.dyn : {
+		*(.rela.*) *(.rela_*)
+	}
+	ASSERT(SIZEOF(.rela.dyn) == 0, "Unexpected run-time relocations (.rela) detected!")
+
 	/* Sections to be discarded */
 	/DISCARD/ : {
+		COMMON_DISCARDS
 		*(.eh_frame)
 		*(__ex_table)
 		*(*__ksymtab*)

arch/s390/configs/debug_defconfig

@@ -824,6 +824,8 @@ CONFIG_TEST_LOCKUP=m
 CONFIG_DEBUG_PREEMPT=y
 CONFIG_PROVE_LOCKING=y
 CONFIG_LOCK_STAT=y
+CONFIG_LOCKDEP_BITS=16
+CONFIG_LOCKDEP_CHAINS_BITS=17
 CONFIG_DEBUG_ATOMIC_SLEEP=y
 CONFIG_DEBUG_LOCKING_API_SELFTESTS=y
 CONFIG_DEBUG_IRQFLAGS=y