summaryrefslogtreecommitdiffstats
path: root/arch/s390
diff options
context:
space:
mode:
Diffstat (limited to 'arch/s390')
-rw-r--r--arch/s390/Kconfig67
-rw-r--r--arch/s390/Makefile15
-rw-r--r--arch/s390/boot/Makefile9
-rw-r--r--arch/s390/boot/boot.h14
-rw-r--r--arch/s390/boot/decompressor.c15
-rw-r--r--arch/s390/boot/decompressor.h8
-rw-r--r--arch/s390/boot/kaslr.c2
-rw-r--r--arch/s390/boot/pgm_check_info.c4
-rw-r--r--arch/s390/boot/startup.c290
-rw-r--r--arch/s390/boot/vmem.c118
-rw-r--r--arch/s390/boot/vmlinux.lds.S29
-rw-r--r--arch/s390/configs/debug_defconfig49
-rw-r--r--arch/s390/configs/defconfig46
-rw-r--r--arch/s390/configs/zfcpdump_defconfig5
-rw-r--r--arch/s390/include/asm/alternative-asm.h1
-rw-r--r--arch/s390/include/asm/alternative.h1
-rw-r--r--arch/s390/include/asm/ap.h30
-rw-r--r--arch/s390/include/asm/asm-prototypes.h1
-rw-r--r--arch/s390/include/asm/chsc.h15
-rw-r--r--arch/s390/include/asm/cpacf.h109
-rw-r--r--arch/s390/include/asm/entry-common.h2
-rw-r--r--arch/s390/include/asm/extmem.h7
-rw-r--r--arch/s390/include/asm/ftrace.h8
-rw-r--r--arch/s390/include/asm/gmap.h2
-rw-r--r--arch/s390/include/asm/hugetlb.h6
-rw-r--r--arch/s390/include/asm/io.h15
-rw-r--r--arch/s390/include/asm/kvm_host.h1
-rw-r--r--arch/s390/include/asm/mmu.h5
-rw-r--r--arch/s390/include/asm/mmu_context.h1
-rw-r--r--arch/s390/include/asm/nospec-branch.h20
-rw-r--r--arch/s390/include/asm/nospec-insn.h13
-rw-r--r--arch/s390/include/asm/os_info.h29
-rw-r--r--arch/s390/include/asm/page.h50
-rw-r--r--arch/s390/include/asm/pgtable.h39
-rw-r--r--arch/s390/include/asm/physmem_info.h4
-rw-r--r--arch/s390/include/asm/processor.h17
-rw-r--r--arch/s390/include/asm/setup.h14
-rw-r--r--arch/s390/include/asm/stacktrace.h12
-rw-r--r--arch/s390/include/asm/vdso/gettimeofday.h7
-rw-r--r--arch/s390/include/asm/vtime.h2
-rw-r--r--arch/s390/kernel/Makefile3
-rw-r--r--arch/s390/kernel/alternative.c7
-rw-r--r--arch/s390/kernel/asm-offsets.c9
-rw-r--r--arch/s390/kernel/cert_store.c1
-rw-r--r--arch/s390/kernel/crash_dump.c71
-rw-r--r--arch/s390/kernel/entry.S23
-rw-r--r--arch/s390/kernel/fpu.c2
-rw-r--r--arch/s390/kernel/ftrace.c7
-rw-r--r--arch/s390/kernel/idle.c10
-rw-r--r--arch/s390/kernel/ipl.c326
-rw-r--r--arch/s390/kernel/irq.c2
-rw-r--r--arch/s390/kernel/kprobes.c71
-rw-r--r--arch/s390/kernel/kprobes.h9
-rw-r--r--arch/s390/kernel/kprobes_insn_page.S22
-rw-r--r--arch/s390/kernel/module.c42
-rw-r--r--arch/s390/kernel/nmi.c1
-rw-r--r--arch/s390/kernel/nospec-branch.c4
-rw-r--r--arch/s390/kernel/os_info.c29
-rw-r--r--arch/s390/kernel/perf_cpum_cf.c16
-rw-r--r--arch/s390/kernel/perf_cpum_cf_events.c11
-rw-r--r--arch/s390/kernel/perf_event.c34
-rw-r--r--arch/s390/kernel/process.c5
-rw-r--r--arch/s390/kernel/setup.c8
-rw-r--r--arch/s390/kernel/stacktrace.c108
-rw-r--r--arch/s390/kernel/syscall.c27
-rw-r--r--arch/s390/kernel/syscalls/Makefile4
-rw-r--r--arch/s390/kernel/syscalls/syscall.tbl3
-rw-r--r--arch/s390/kernel/uv.c59
-rw-r--r--arch/s390/kernel/vdso.c13
-rw-r--r--arch/s390/kernel/vdso32/Makefile16
-rw-r--r--arch/s390/kernel/vdso64/Makefile16
-rw-r--r--arch/s390/kernel/vdso64/vdso_user_wrapper.S19
-rw-r--r--arch/s390/kernel/vmcore_info.c2
-rw-r--r--arch/s390/kernel/vmlinux.lds.S38
-rw-r--r--arch/s390/kernel/vtime.c10
-rw-r--r--arch/s390/kvm/kvm-s390.c8
-rw-r--r--arch/s390/kvm/kvm-s390.h15
-rw-r--r--arch/s390/kvm/priv.c32
-rw-r--r--arch/s390/kvm/vsie.c5
-rw-r--r--arch/s390/lib/Makefile2
-rw-r--r--arch/s390/lib/expoline.S (renamed from arch/s390/lib/expoline/expoline.S)0
-rw-r--r--arch/s390/lib/expoline/Makefile3
-rw-r--r--arch/s390/mm/dump_pagetables.c21
-rw-r--r--arch/s390/mm/fault.c6
-rw-r--r--arch/s390/mm/gmap.c165
-rw-r--r--arch/s390/mm/hugetlbpage.c19
-rw-r--r--arch/s390/mm/init.c30
-rw-r--r--arch/s390/mm/mmap.c9
-rw-r--r--arch/s390/mm/pgalloc.c4
-rw-r--r--arch/s390/mm/vmem.c5
-rw-r--r--arch/s390/net/bpf_jit_comp.c14
-rw-r--r--arch/s390/pci/pci.c6
-rw-r--r--arch/s390/pci/pci_irq.c112
-rw-r--r--arch/s390/pci/pci_mmio.c4
-rw-r--r--arch/s390/pci/pci_sysfs.c4
-rw-r--r--arch/s390/purgatory/Makefile8
-rw-r--r--arch/s390/tools/relocs.c2
97 files changed, 1473 insertions, 1111 deletions
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 8f01ada684..c59d2b54df 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -17,6 +17,9 @@ config ARCH_HAS_ILOG2_U32
config ARCH_HAS_ILOG2_U64
def_bool n
+config ARCH_PROC_KCORE_TEXT
+ def_bool y
+
config GENERIC_HWEIGHT
def_bool y
@@ -174,7 +177,7 @@ config S390
select HAVE_DYNAMIC_FTRACE_WITH_REGS
select HAVE_EBPF_JIT if HAVE_MARCH_Z196_FEATURES
select HAVE_EFFICIENT_UNALIGNED_ACCESS
- select HAVE_FAST_GUP
+ select HAVE_GUP_FAST
select HAVE_FENTRY
select HAVE_FTRACE_MCOUNT_RECORD
select HAVE_FUNCTION_ARG_ACCESS_API
@@ -552,7 +555,7 @@ config EXPOLINE
If unsure, say N.
config EXPOLINE_EXTERN
- def_bool n
+ def_bool y if EXPOLINE
depends on EXPOLINE
depends on CC_IS_GCC && GCC_VERSION >= 110200
depends on $(success,$(srctree)/arch/s390/tools/gcc-thunk-extern.sh $(CC))
@@ -590,18 +593,6 @@ config RELOCATABLE
Note: this option exists only for documentation purposes, please do
not remove it.
-config PIE_BUILD
- def_bool CC_IS_CLANG && !$(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
@@ -611,6 +602,25 @@ config RANDOMIZE_BASE
as a security feature that deters exploit attempts relying on
knowledge of the location of kernel internals.
+config KERNEL_IMAGE_BASE
+ hex "Kernel image base address"
+ range 0x100000 0x1FFFFFE0000000 if !KASAN
+ range 0x100000 0x1BFFFFE0000000 if KASAN
+ default 0x3FFE0000000 if !KASAN
+ default 0x7FFFE0000000 if KASAN
+ help
+ This is the address at which the kernel image is loaded in case
+ Kernel Address Space Layout Randomization (KASLR) is disabled.
+
+ In case the Protected virtualization guest support is enabled the
+ Ultravisor imposes a virtual address limit. If the value of this
+ option leads to the kernel image exceeding the Ultravisor limit,
+ this option is ignored and the image is loaded below the limit.
+
+ If the value of this option leads to the kernel image overlapping
+ the virtual memory where other data structures are located, this
+ option is ignored and the image is loaded above the structures.
+
endmenu
menu "Memory setup"
@@ -724,6 +734,33 @@ config EADM_SCH
To compile this driver as a module, choose M here: the
module will be called eadm_sch.
+config AP
+ def_tristate y
+ prompt "Support for Adjunct Processors (ap)"
+ help
+ This driver allows usage to Adjunct Processor (AP) devices via
+ the ap bus, cards and queues. Supported Adjunct Processors are
+ the CryptoExpress Cards (CEX).
+
+ To compile this driver as a module, choose M here: the
+ module will be called ap.
+
+ If unsure, say Y (default).
+
+config AP_DEBUG
+ def_bool n
+ prompt "Enable debug features for Adjunct Processor (ap) devices"
+ depends on AP
+ help
+ Say 'Y' here to enable some additional debug features for Adjunct
+ Processor (ap) devices.
+
+ There will be some more sysfs attributes displayed for ap queues.
+
+ Do not enable on production level kernel build.
+
+ If unsure, say N.
+
config VFIO_CCW
def_tristate n
prompt "Support for VFIO-CCW subchannels"
@@ -740,7 +777,7 @@ config VFIO_AP
prompt "VFIO support for AP devices"
depends on KVM
depends on VFIO
- depends on ZCRYPT
+ depends on AP
select VFIO_MDEV
help
This driver grants access to Adjunct Processor (AP) devices
diff --git a/arch/s390/Makefile b/arch/s390/Makefile
index 2dbb2d2f22..f2b21c7a70 100644
--- a/arch/s390/Makefile
+++ b/arch/s390/Makefile
@@ -14,14 +14,9 @@ KBUILD_AFLAGS_MODULE += -fPIC
KBUILD_CFLAGS_MODULE += -fPIC
KBUILD_AFLAGS += -m64
KBUILD_CFLAGS += -m64
-ifdef CONFIG_PIE_BUILD
-KBUILD_CFLAGS += -fPIE
-LDFLAGS_vmlinux := -pie -z notext
-else
-KBUILD_CFLAGS += $(call cc-option,-munaligned-symbols,)
-LDFLAGS_vmlinux := --emit-relocs --discard-none
+KBUILD_CFLAGS += -fPIC
+LDFLAGS_vmlinux := -no-pie --emit-relocs --discard-none
extra_tools := relocs
-endif
aflags_dwarf := -Wa,-gdwarf-2
KBUILD_AFLAGS_DECOMPRESSOR := $(CLANG_FLAGS) -m64 -D__ASSEMBLY__
ifndef CONFIG_AS_IS_LLVM
@@ -88,7 +83,6 @@ endif
ifdef CONFIG_EXPOLINE
ifdef CONFIG_EXPOLINE_EXTERN
- KBUILD_LDFLAGS_MODULE += arch/s390/lib/expoline/expoline.o
CC_FLAGS_EXPOLINE := -mindirect-branch=thunk-extern
CC_FLAGS_EXPOLINE += -mfunction-return=thunk-extern
else
@@ -167,11 +161,6 @@ vdso_prepare: prepare0
vdso-install-y += arch/s390/kernel/vdso64/vdso64.so.dbg
vdso-install-$(CONFIG_COMPAT) += arch/s390/kernel/vdso32/vdso32.so.dbg
-ifdef CONFIG_EXPOLINE_EXTERN
-modules_prepare: expoline_prepare
-expoline_prepare: scripts
- $(Q)$(MAKE) $(build)=arch/s390/lib/expoline arch/s390/lib/expoline/expoline.o
-endif
endif
# Don't use tabs in echo arguments
diff --git a/arch/s390/boot/Makefile b/arch/s390/boot/Makefile
index 294f08a881..070c9b2e90 100644
--- a/arch/s390/boot/Makefile
+++ b/arch/s390/boot/Makefile
@@ -37,8 +37,7 @@ CFLAGS_sclp_early_core.o += -I$(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
-obj-y += $(if $(CONFIG_PIE_BUILD),machine_kexec_reloc.o,relocs.o)
+obj-y += version.o pgm_check_info.o ctype.o ipl_data.o relocs.o
obj-$(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
@@ -49,9 +48,7 @@ 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))
@@ -110,13 +107,11 @@ 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 $@
+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
diff --git a/arch/s390/boot/boot.h b/arch/s390/boot/boot.h
index 567d60f78b..18027fdc92 100644
--- a/arch/s390/boot/boot.h
+++ b/arch/s390/boot/boot.h
@@ -17,7 +17,6 @@ struct machine_info {
};
struct vmlinux_info {
- unsigned long default_lma;
unsigned long entry;
unsigned long image_size; /* does not include .bss */
unsigned long bss_size; /* uncompressed image .bss size */
@@ -25,14 +24,8 @@ 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;
@@ -74,10 +67,11 @@ void sclp_early_setup_buffer(void);
void print_pgm_check_info(void);
unsigned long randomize_within_range(unsigned long size, unsigned long align,
unsigned long min, unsigned long max);
-void setup_vmem(unsigned long asce_limit);
+void setup_vmem(unsigned long kernel_start, unsigned long kernel_end, unsigned long asce_limit);
void __printf(1, 2) decompressor_printk(const char *fmt, ...);
void print_stacktrace(unsigned long sp);
void error(char *m);
+int get_random(unsigned long limit, unsigned long *value);
extern struct machine_info machine;
@@ -98,6 +92,10 @@ extern struct vmlinux_info _vmlinux_info;
#define vmlinux _vmlinux_info
#define __abs_lowcore_pa(x) (((unsigned long)(x) - __abs_lowcore) % sizeof(struct lowcore))
+#define __kernel_va(x) ((void *)((unsigned long)(x) - __kaslr_offset_phys + __kaslr_offset))
+#define __kernel_pa(x) ((unsigned long)(x) - __kaslr_offset + __kaslr_offset_phys)
+#define __identity_va(x) ((void *)((unsigned long)(x) + __identity_base))
+#define __identity_pa(x) ((unsigned long)(x) - __identity_base)
static inline bool intersects(unsigned long addr0, unsigned long size0,
unsigned long addr1, unsigned long size1)
diff --git a/arch/s390/boot/decompressor.c b/arch/s390/boot/decompressor.c
index d762733a07..f478e8e9cb 100644
--- a/arch/s390/boot/decompressor.c
+++ b/arch/s390/boot/decompressor.c
@@ -63,24 +63,13 @@ static unsigned long free_mem_end_ptr = (unsigned long) _end + BOOT_HEAP_SIZE;
#include "../../../../lib/decompress_unzstd.c"
#endif
-#define decompress_offset ALIGN((unsigned long)_end + BOOT_HEAP_SIZE, PAGE_SIZE)
-
unsigned long mem_safe_offset(void)
{
- /*
- * due to 4MB HEAD_SIZE for bzip2
- * 'decompress_offset + vmlinux.image_size' could be larger than
- * kernel at final position + its .bss, so take the larger of two
- */
- return max(decompress_offset + vmlinux.image_size,
- vmlinux.default_lma + vmlinux.image_size + vmlinux.bss_size);
+ return ALIGN(free_mem_end_ptr, PAGE_SIZE);
}
-void *decompress_kernel(void)
+void deploy_kernel(void *output)
{
- void *output = (void *)decompress_offset;
-
__decompress(_compressed_start, _compressed_end - _compressed_start,
NULL, NULL, output, vmlinux.image_size, NULL, error);
- return output;
}
diff --git a/arch/s390/boot/decompressor.h b/arch/s390/boot/decompressor.h
index 92b81d2ea3..4f966f06bd 100644
--- a/arch/s390/boot/decompressor.h
+++ b/arch/s390/boot/decompressor.h
@@ -2,11 +2,9 @@
#ifndef BOOT_COMPRESSED_DECOMPRESSOR_H
#define BOOT_COMPRESSED_DECOMPRESSOR_H
-#ifdef CONFIG_KERNEL_UNCOMPRESSED
-static inline void *decompress_kernel(void) { return NULL; }
-#else
-void *decompress_kernel(void);
-#endif
+#ifndef CONFIG_KERNEL_UNCOMPRESSED
unsigned long mem_safe_offset(void);
+void deploy_kernel(void *output);
+#endif
#endif /* BOOT_COMPRESSED_DECOMPRESSOR_H */
diff --git a/arch/s390/boot/kaslr.c b/arch/s390/boot/kaslr.c
index 90602101e2..bd3bf5ef47 100644
--- a/arch/s390/boot/kaslr.c
+++ b/arch/s390/boot/kaslr.c
@@ -43,7 +43,7 @@ static int check_prng(void)
return PRNG_MODE_TDES;
}
-static int get_random(unsigned long limit, unsigned long *value)
+int get_random(unsigned long limit, unsigned long *value)
{
struct prng_parm prng = {
/* initial parameter block for tdes mode, copied from libica */
diff --git a/arch/s390/boot/pgm_check_info.c b/arch/s390/boot/pgm_check_info.c
index 97244cd7a2..ea96275b03 100644
--- a/arch/s390/boot/pgm_check_info.c
+++ b/arch/s390/boot/pgm_check_info.c
@@ -153,8 +153,10 @@ void print_pgm_check_info(void)
decompressor_printk("Kernel command line: %s\n", early_command_line);
decompressor_printk("Kernel fault: interruption code %04x ilc:%x\n",
S390_lowcore.pgm_code, S390_lowcore.pgm_ilc >> 1);
- if (kaslr_enabled())
+ if (kaslr_enabled()) {
decompressor_printk("Kernel random base: %lx\n", __kaslr_offset);
+ decompressor_printk("Kernel random base phys: %lx\n", __kaslr_offset_phys);
+ }
decompressor_printk("PSW : %016lx %016lx (%pS)\n",
S390_lowcore.psw_save_area.mask,
S390_lowcore.psw_save_area.addr,
diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c
index 6cf8931420..5a36d5538d 100644
--- a/arch/s390/boot/startup.c
+++ b/arch/s390/boot/startup.c
@@ -3,6 +3,7 @@
#include <linux/elf.h>
#include <asm/page-states.h>
#include <asm/boot_data.h>
+#include <asm/extmem.h>
#include <asm/sections.h>
#include <asm/maccess.h>
#include <asm/cpu_mf.h>
@@ -18,7 +19,7 @@
#include "boot.h"
#include "uv.h"
-unsigned long __bootdata_preserved(__kaslr_offset);
+struct vm_layout __bootdata_preserved(vm_layout);
unsigned long __bootdata_preserved(__abs_lowcore);
unsigned long __bootdata_preserved(__memcpy_real_area);
pte_t *__bootdata_preserved(memcpy_real_ptep);
@@ -29,10 +30,8 @@ unsigned long __bootdata_preserved(vmemmap_size);
unsigned long __bootdata_preserved(MODULES_VADDR);
unsigned long __bootdata_preserved(MODULES_END);
unsigned long __bootdata_preserved(max_mappable);
-unsigned long __bootdata(ident_map_size);
u64 __bootdata_preserved(stfle_fac_list[16]);
-u64 __bootdata_preserved(alt_stfle_fac_list[16]);
struct oldmem_data __bootdata_preserved(oldmem_data);
struct machine_info machine;
@@ -109,9 +108,19 @@ static void setup_lpp(void)
}
#ifdef CONFIG_KERNEL_UNCOMPRESSED
-unsigned long mem_safe_offset(void)
+static unsigned long mem_safe_offset(void)
{
- return vmlinux.default_lma + vmlinux.image_size + vmlinux.bss_size;
+ return (unsigned long)_compressed_start;
+}
+
+static void deploy_kernel(void *output)
+{
+ void *uncompressed_start = (void *)_compressed_start;
+
+ if (output == uncompressed_start)
+ return;
+ memmove(output, uncompressed_start, vmlinux.image_size);
+ memset(uncompressed_start, 0, vmlinux.image_size);
}
#endif
@@ -141,70 +150,18 @@ static void copy_bootdata(void)
memcpy((void *)vmlinux.bootdata_preserved_off, __boot_data_preserved_start, vmlinux.bootdata_preserved_size);
}
-#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;
- Elf64_Addr loc, val;
- Elf64_Sym *dynsym;
-
- rela_start = (Elf64_Rela *) vmlinux.rela_dyn_start;
- rela_end = (Elf64_Rela *) vmlinux.rela_dyn_end;
- dynsym = (Elf64_Sym *) vmlinux.dynsym_start;
- for (rela = rela_start; rela < rela_end; rela++) {
- loc = rela->r_offset + offset;
- val = rela->r_addend;
- r_sym = ELF64_R_SYM(rela->r_info);
- if (r_sym) {
- if (dynsym[r_sym].st_shndx != SHN_UNDEF)
- val += dynsym[r_sym].st_value + offset;
- } else {
- /*
- * 0 == undefined symbol table index (STN_UNDEF),
- * used for R_390_RELATIVE, only add KASLR offset
- */
- val += offset;
- }
- r_type = ELF64_R_TYPE(rela->r_info);
- rc = arch_kexec_do_relocs(r_type, (void *) loc, val, 0);
- if (rc)
- error("Unknown relocation type");
- }
-}
-
-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)
+static void kaslr_adjust_relocs(unsigned long min_addr, unsigned long max_addr,
+ unsigned long offset, unsigned long phys_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;
+ for (reloc = (int *)__vmlinux_relocs_64_start; reloc < (int *)__vmlinux_relocs_64_end; reloc++) {
+ loc = (long)*reloc + phys_offset;
if (loc < min_addr || loc > max_addr)
error("64-bit relocation outside of kernel!\n");
- *(u64 *)loc += offset;
+ *(u64 *)loc += offset - __START_KERNEL;
}
}
@@ -213,13 +170,15 @@ 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.
+ * Adjust GOT entries, except for ones for undefined weak symbols
+ * that resolved to zero. This also skips the first three reserved
+ * entries on s390x that are zero.
*/
- for (entry = (u64 *)vmlinux.got_start; entry < (u64 *)vmlinux.got_end; entry++)
- *entry += offset;
+ for (entry = (u64 *)vmlinux.got_start; entry < (u64 *)vmlinux.got_end; entry++) {
+ if (*entry)
+ *entry += offset - __START_KERNEL;
+ }
}
-#endif
/*
* Merge information from several sources into a single ident_map_size value.
@@ -261,9 +220,26 @@ static void setup_ident_map_size(unsigned long max_physmem_end)
#endif
}
-static unsigned long setup_kernel_memory_layout(void)
+#define FIXMAP_SIZE round_up(MEMCPY_REAL_SIZE + ABS_LOWCORE_MAP_SIZE, sizeof(struct lowcore))
+
+static unsigned long get_vmem_size(unsigned long identity_size,
+ unsigned long vmemmap_size,
+ unsigned long vmalloc_size,
+ unsigned long rte_size)
+{
+ unsigned long max_mappable, vsize;
+
+ max_mappable = max(identity_size, MAX_DCSS_ADDR);
+ vsize = round_up(SZ_2G + max_mappable, rte_size) +
+ round_up(vmemmap_size, rte_size) +
+ FIXMAP_SIZE + MODULES_LEN + KASLR_LEN;
+ return size_add(vsize, vmalloc_size);
+}
+
+static unsigned long setup_kernel_memory_layout(unsigned long kernel_size)
{
unsigned long vmemmap_start;
+ unsigned long kernel_start;
unsigned long asce_limit;
unsigned long rte_size;
unsigned long pages;
@@ -275,12 +251,19 @@ static unsigned long setup_kernel_memory_layout(void)
vmemmap_size = SECTION_ALIGN_UP(pages) * sizeof(struct page);
/* choose kernel address space layout: 4 or 3 levels. */
- vsize = round_up(ident_map_size, _REGION3_SIZE) + vmemmap_size +
- MODULES_LEN + MEMCPY_REAL_SIZE + ABS_LOWCORE_MAP_SIZE;
- vsize = size_add(vsize, vmalloc_size);
- if (IS_ENABLED(CONFIG_KASAN) || (vsize > _REGION2_SIZE)) {
+ BUILD_BUG_ON(!IS_ALIGNED(__START_KERNEL, THREAD_SIZE));
+ BUILD_BUG_ON(!IS_ALIGNED(__NO_KASLR_START_KERNEL, THREAD_SIZE));
+ BUILD_BUG_ON(__NO_KASLR_END_KERNEL > _REGION1_SIZE);
+ vsize = get_vmem_size(ident_map_size, vmemmap_size, vmalloc_size, _REGION3_SIZE);
+ if (IS_ENABLED(CONFIG_KASAN) || __NO_KASLR_END_KERNEL > _REGION2_SIZE ||
+ (vsize > _REGION2_SIZE && kaslr_enabled())) {
asce_limit = _REGION1_SIZE;
- rte_size = _REGION2_SIZE;
+ if (__NO_KASLR_END_KERNEL > _REGION2_SIZE) {
+ rte_size = _REGION2_SIZE;
+ vsize = get_vmem_size(ident_map_size, vmemmap_size, vmalloc_size, _REGION2_SIZE);
+ } else {
+ rte_size = _REGION3_SIZE;
+ }
} else {
asce_limit = _REGION2_SIZE;
rte_size = _REGION3_SIZE;
@@ -290,38 +273,67 @@ static unsigned long setup_kernel_memory_layout(void)
* Forcing modules and vmalloc area under the ultravisor
* secure storage limit, so that any vmalloc allocation
* we do could be used to back secure guest storage.
+ *
+ * Assume the secure storage limit always exceeds _REGION2_SIZE,
+ * otherwise asce_limit and rte_size would have been adjusted.
*/
vmax = adjust_to_uv_max(asce_limit);
#ifdef CONFIG_KASAN
+ BUILD_BUG_ON(__NO_KASLR_END_KERNEL > KASAN_SHADOW_START);
/* force vmalloc and modules below kasan shadow */
vmax = min(vmax, KASAN_SHADOW_START);
#endif
- __memcpy_real_area = round_down(vmax - MEMCPY_REAL_SIZE, PAGE_SIZE);
- __abs_lowcore = round_down(__memcpy_real_area - ABS_LOWCORE_MAP_SIZE,
- sizeof(struct lowcore));
- MODULES_END = round_down(__abs_lowcore, _SEGMENT_SIZE);
+ vsize = min(vsize, vmax);
+ if (kaslr_enabled()) {
+ unsigned long kernel_end, kaslr_len, slots, pos;
+
+ kaslr_len = max(KASLR_LEN, vmax - vsize);
+ slots = DIV_ROUND_UP(kaslr_len - kernel_size, THREAD_SIZE);
+ if (get_random(slots, &pos))
+ pos = 0;
+ kernel_end = vmax - pos * THREAD_SIZE;
+ kernel_start = round_down(kernel_end - kernel_size, THREAD_SIZE);
+ } else if (vmax < __NO_KASLR_END_KERNEL || vsize > __NO_KASLR_END_KERNEL) {
+ kernel_start = round_down(vmax - kernel_size, THREAD_SIZE);
+ decompressor_printk("The kernel base address is forced to %lx\n", kernel_start);
+ } else {
+ kernel_start = __NO_KASLR_START_KERNEL;
+ }
+ __kaslr_offset = kernel_start;
+
+ MODULES_END = round_down(kernel_start, _SEGMENT_SIZE);
MODULES_VADDR = MODULES_END - MODULES_LEN;
VMALLOC_END = MODULES_VADDR;
/* allow vmalloc area to occupy up to about 1/2 of the rest virtual space left */
- vsize = round_down(VMALLOC_END / 2, _SEGMENT_SIZE);
+ vsize = (VMALLOC_END - FIXMAP_SIZE) / 2;
+ vsize = round_down(vsize, _SEGMENT_SIZE);
vmalloc_size = min(vmalloc_size, vsize);
VMALLOC_START = VMALLOC_END - vmalloc_size;
+ __memcpy_real_area = round_down(VMALLOC_START - MEMCPY_REAL_SIZE, PAGE_SIZE);
+ __abs_lowcore = round_down(__memcpy_real_area - ABS_LOWCORE_MAP_SIZE,
+ sizeof(struct lowcore));
+
/* split remaining virtual space between 1:1 mapping & vmemmap array */
- pages = VMALLOC_START / (PAGE_SIZE + sizeof(struct page));
+ pages = __abs_lowcore / (PAGE_SIZE + sizeof(struct page));
pages = SECTION_ALIGN_UP(pages);
/* keep vmemmap_start aligned to a top level region table entry */
- vmemmap_start = round_down(VMALLOC_START - pages * sizeof(struct page), rte_size);
- vmemmap_start = min(vmemmap_start, 1UL << MAX_PHYSMEM_BITS);
- /* maximum mappable address as seen by arch_get_mappable_range() */
- max_mappable = vmemmap_start;
+ vmemmap_start = round_down(__abs_lowcore - pages * sizeof(struct page), rte_size);
/* make sure identity map doesn't overlay with vmemmap */
ident_map_size = min(ident_map_size, vmemmap_start);
vmemmap_size = SECTION_ALIGN_UP(ident_map_size / PAGE_SIZE) * sizeof(struct page);
- /* make sure vmemmap doesn't overlay with vmalloc area */
- VMALLOC_START = max(vmemmap_start + vmemmap_size, VMALLOC_START);
+ /* make sure vmemmap doesn't overlay with absolute lowcore area */
+ if (vmemmap_start + vmemmap_size > __abs_lowcore) {
+ vmemmap_size = SECTION_ALIGN_DOWN(ident_map_size / PAGE_SIZE) * sizeof(struct page);
+ ident_map_size = vmemmap_size / sizeof(struct page) * PAGE_SIZE;
+ }
vmemmap = (struct page *)vmemmap_start;
+ /* maximum address for which linear mapping could be created (DCSS, memory) */
+ BUILD_BUG_ON(MAX_DCSS_ADDR > (1UL << MAX_PHYSMEM_BITS));
+ max_mappable = max(ident_map_size, MAX_DCSS_ADDR);
+ max_mappable = min(max_mappable, vmemmap_start);
+ __identity_base = round_down(vmemmap_start - max_mappable, rte_size);
return asce_limit;
}
@@ -329,9 +341,9 @@ static unsigned long setup_kernel_memory_layout(void)
/*
* This function clears the BSS section of the decompressed Linux kernel and NOT the decompressor's.
*/
-static void clear_bss_section(unsigned long vmlinux_lma)
+static void clear_bss_section(unsigned long kernel_start)
{
- memset((void *)vmlinux_lma + vmlinux.image_size, 0, vmlinux.bss_size);
+ memset((void *)kernel_start + vmlinux.image_size, 0, vmlinux.bss_size);
}
/*
@@ -348,19 +360,12 @@ static void setup_vmalloc_size(void)
vmalloc_size = max(size, vmalloc_size);
}
-static void kaslr_adjust_vmlinux_info(unsigned long offset)
+static void kaslr_adjust_vmlinux_info(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;
@@ -373,23 +378,36 @@ static void kaslr_adjust_vmlinux_info(unsigned long offset)
#endif
}
+static void fixup_vmlinux_info(void)
+{
+ vmlinux.entry -= __START_KERNEL;
+ kaslr_adjust_vmlinux_info(-__START_KERNEL);
+}
+
void startup_kernel(void)
{
- unsigned long max_physmem_end;
- unsigned long vmlinux_lma = 0;
+ unsigned long kernel_size = vmlinux.image_size + vmlinux.bss_size;
+ unsigned long nokaslr_offset_phys, kaslr_large_page_offset;
unsigned long amode31_lma = 0;
+ unsigned long max_physmem_end;
unsigned long asce_limit;
unsigned long safe_addr;
- void *img;
psw_t psw;
+ fixup_vmlinux_info();
setup_lpp();
- safe_addr = mem_safe_offset();
/*
- * Reserve decompressor memory together with decompression heap, buffer and
- * memory which might be occupied by uncompressed kernel at default 1Mb
- * position (if KASLR is off or failed).
+ * Non-randomized kernel physical start address must be _SEGMENT_SIZE
+ * aligned (see blow).
+ */
+ nokaslr_offset_phys = ALIGN(mem_safe_offset(), _SEGMENT_SIZE);
+ safe_addr = PAGE_ALIGN(nokaslr_offset_phys + kernel_size);
+
+ /*
+ * Reserve decompressor memory together with decompression heap,
+ * buffer and memory which might be occupied by uncompressed kernel
+ * (if KASLR is off or failed).
*/
physmem_reserve(RR_DECOMPRESSOR, 0, safe_addr);
if (IS_ENABLED(CONFIG_BLK_DEV_INITRD) && parmarea.initrd_size)
@@ -409,40 +427,54 @@ void startup_kernel(void)
max_physmem_end = detect_max_physmem_end();
setup_ident_map_size(max_physmem_end);
setup_vmalloc_size();
- asce_limit = setup_kernel_memory_layout();
+ asce_limit = setup_kernel_memory_layout(kernel_size);
/* got final ident_map_size, physmem allocations could be performed now */
physmem_set_usable_limit(ident_map_size);
detect_physmem_online_ranges(max_physmem_end);
save_ipl_cert_comp_list();
rescue_initrd(safe_addr, ident_map_size);
- rescue_relocs();
+ /*
+ * __kaslr_offset_phys must be _SEGMENT_SIZE aligned, so the lower
+ * 20 bits (the offset within a large page) are zero. Copy the last
+ * 20 bits of __kaslr_offset, which is THREAD_SIZE aligned, to
+ * __kaslr_offset_phys.
+ *
+ * With this the last 20 bits of __kaslr_offset_phys and __kaslr_offset
+ * are identical, which is required to allow for large mappings of the
+ * kernel image.
+ */
+ kaslr_large_page_offset = __kaslr_offset & ~_SEGMENT_MASK;
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;
- kaslr_adjust_vmlinux_info(__kaslr_offset);
- }
- }
- vmlinux_lma = vmlinux_lma ?: vmlinux.default_lma;
- physmem_reserve(RR_VMLINUX, vmlinux_lma, vmlinux.image_size + vmlinux.bss_size);
-
- if (!IS_ENABLED(CONFIG_KERNEL_UNCOMPRESSED)) {
- img = decompress_kernel();
- memmove((void *)vmlinux_lma, img, vmlinux.image_size);
- } else if (__kaslr_offset) {
- img = (void *)vmlinux.default_lma;
- memmove((void *)vmlinux_lma, img, vmlinux.image_size);
- memset(img, 0, vmlinux.image_size);
+ unsigned long end = ident_map_size - kaslr_large_page_offset;
+
+ __kaslr_offset_phys = randomize_within_range(kernel_size, _SEGMENT_SIZE, 0, end);
}
+ if (!__kaslr_offset_phys)
+ __kaslr_offset_phys = nokaslr_offset_phys;
+ __kaslr_offset_phys |= kaslr_large_page_offset;
+ kaslr_adjust_vmlinux_info(__kaslr_offset_phys);
+ physmem_reserve(RR_VMLINUX, __kaslr_offset_phys, kernel_size);
+ deploy_kernel((void *)__kaslr_offset_phys);
/* vmlinux decompression is done, shrink reserved low memory */
physmem_reserve(RR_DECOMPRESSOR, 0, (unsigned long)_decompressor_end);
+
+ /*
+ * In case KASLR is enabled the randomized location of .amode31
+ * section might overlap with .vmlinux.relocs section. To avoid that
+ * the below randomize_within_range() could have been called with
+ * __vmlinux_relocs_64_end as the lower range address. However,
+ * .amode31 section is written to by the decompressed kernel - at
+ * that time the contents of .vmlinux.relocs is not needed anymore.
+ * Conversly, .vmlinux.relocs is read only by the decompressor, even
+ * before the kernel started. Therefore, in case the two sections
+ * overlap there is no risk of corrupting any data.
+ */
if (kaslr_enabled())
amode31_lma = randomize_within_range(vmlinux.amode31_size, PAGE_SIZE, 0, SZ_2G);
- amode31_lma = amode31_lma ?: vmlinux.default_lma - vmlinux.amode31_size;
+ if (!amode31_lma)
+ amode31_lma = __kaslr_offset_phys - vmlinux.amode31_size;
physmem_reserve(RR_AMODE31, amode31_lma, vmlinux.amode31_size);
/*
@@ -458,23 +490,23 @@ void startup_kernel(void)
* - copy_bootdata() must follow setup_vmem() to propagate changes
* to bootdata made by setup_vmem()
*/
- clear_bss_section(vmlinux_lma);
- kaslr_adjust_relocs(vmlinux_lma, vmlinux_lma + vmlinux.image_size, __kaslr_offset);
+ clear_bss_section(__kaslr_offset_phys);
+ kaslr_adjust_relocs(__kaslr_offset_phys, __kaslr_offset_phys + vmlinux.image_size,
+ __kaslr_offset, __kaslr_offset_phys);
kaslr_adjust_got(__kaslr_offset);
- free_relocs();
- setup_vmem(asce_limit);
+ setup_vmem(__kaslr_offset, __kaslr_offset + kernel_size, asce_limit);
copy_bootdata();
/*
* Save KASLR offset for early dumps, before vmcore_info is set.
* Mark as uneven to distinguish from real vmcore_info pointer.
*/
- S390_lowcore.vmcore_info = __kaslr_offset ? __kaslr_offset | 0x1UL : 0;
+ S390_lowcore.vmcore_info = __kaslr_offset_phys ? __kaslr_offset_phys | 0x1UL : 0;
/*
* Jump to the decompressed kernel entry point and switch DAT mode on.
*/
- psw.addr = vmlinux.entry;
+ psw.addr = __kaslr_offset + vmlinux.entry;
psw.mask = PSW_KERNEL_BITS;
__load_psw(psw);
}
diff --git a/arch/s390/boot/vmem.c b/arch/s390/boot/vmem.c
index 09b10bb6e4..40cfce2687 100644
--- a/arch/s390/boot/vmem.c
+++ b/arch/s390/boot/vmem.c
@@ -27,6 +27,8 @@ enum populate_mode {
POPULATE_NONE,
POPULATE_DIRECT,
POPULATE_ABS_LOWCORE,
+ POPULATE_IDENTITY,
+ POPULATE_KERNEL,
#ifdef CONFIG_KASAN
POPULATE_KASAN_MAP_SHADOW,
POPULATE_KASAN_ZERO_SHADOW,
@@ -54,7 +56,7 @@ static inline void kasan_populate(unsigned long start, unsigned long end, enum p
pgtable_populate(start, end, mode);
}
-static void kasan_populate_shadow(void)
+static void kasan_populate_shadow(unsigned long kernel_start, unsigned long kernel_end)
{
pmd_t pmd_z = __pmd(__pa(kasan_early_shadow_pte) | _SEGMENT_ENTRY);
pud_t pud_z = __pud(__pa(kasan_early_shadow_pmd) | _REGION3_ENTRY);
@@ -76,44 +78,20 @@ static void kasan_populate_shadow(void)
__arch_set_page_dat(kasan_early_shadow_pmd, 1UL << CRST_ALLOC_ORDER);
__arch_set_page_dat(kasan_early_shadow_pte, 1);
- /*
- * Current memory layout:
- * +- 0 -------------+ +- shadow start -+
- * |1:1 ident mapping| /|1/8 of ident map|
- * | | / | |
- * +-end of ident map+ / +----------------+
- * | ... gap ... | / | kasan |
- * | | / | zero page |
- * +- vmalloc area -+ / | mapping |
- * | vmalloc_size | / | (untracked) |
- * +- modules vaddr -+ / +----------------+
- * | 2Gb |/ | unmapped | allocated per module
- * +- shadow start -+ +----------------+
- * | 1/8 addr space | | zero pg mapping| (untracked)
- * +- shadow end ----+---------+- shadow end ---+
- *
- * Current memory layout (KASAN_VMALLOC):
- * +- 0 -------------+ +- shadow start -+
- * |1:1 ident mapping| /|1/8 of ident map|
- * | | / | |
- * +-end of ident map+ / +----------------+
- * | ... gap ... | / | kasan zero page| (untracked)
- * | | / | mapping |
- * +- vmalloc area -+ / +----------------+
- * | vmalloc_size | / |shallow populate|
- * +- modules vaddr -+ / +----------------+
- * | 2Gb |/ |shallow populate|
- * +- shadow start -+ +----------------+
- * | 1/8 addr space | | zero pg mapping| (untracked)
- * +- shadow end ----+---------+- shadow end ---+
- */
-
for_each_physmem_usable_range(i, &start, &end) {
- kasan_populate(start, end, POPULATE_KASAN_MAP_SHADOW);
- if (memgap_start && physmem_info.info_source == MEM_DETECT_DIAG260)
- kasan_populate(memgap_start, start, POPULATE_KASAN_ZERO_SHADOW);
+ kasan_populate((unsigned long)__identity_va(start),
+ (unsigned long)__identity_va(end),
+ POPULATE_KASAN_MAP_SHADOW);
+ if (memgap_start && physmem_info.info_source == MEM_DETECT_DIAG260) {
+ kasan_populate((unsigned long)__identity_va(memgap_start),
+ (unsigned long)__identity_va(start),
+ POPULATE_KASAN_ZERO_SHADOW);
+ }
memgap_start = end;
}
+ kasan_populate(kernel_start, kernel_end, POPULATE_KASAN_MAP_SHADOW);
+ kasan_populate(0, (unsigned long)__identity_va(0), POPULATE_KASAN_ZERO_SHADOW);
+ kasan_populate(AMODE31_START, AMODE31_END, POPULATE_KASAN_ZERO_SHADOW);
if (IS_ENABLED(CONFIG_KASAN_VMALLOC)) {
untracked_end = VMALLOC_START;
/* shallowly populate kasan shadow for vmalloc and modules */
@@ -122,8 +100,9 @@ static void kasan_populate_shadow(void)
untracked_end = MODULES_VADDR;
}
/* populate kasan shadow for untracked memory */
- kasan_populate(ident_map_size, untracked_end, POPULATE_KASAN_ZERO_SHADOW);
- kasan_populate(MODULES_END, _REGION1_SIZE, POPULATE_KASAN_ZERO_SHADOW);
+ kasan_populate((unsigned long)__identity_va(ident_map_size), untracked_end,
+ POPULATE_KASAN_ZERO_SHADOW);
+ kasan_populate(kernel_end, _REGION1_SIZE, POPULATE_KASAN_ZERO_SHADOW);
}
static bool kasan_pgd_populate_zero_shadow(pgd_t *pgd, unsigned long addr,
@@ -180,7 +159,9 @@ static bool kasan_pte_populate_zero_shadow(pte_t *pte, enum populate_mode mode)
}
#else
-static inline void kasan_populate_shadow(void) {}
+static inline void kasan_populate_shadow(unsigned long kernel_start, unsigned long kernel_end)
+{
+}
static inline bool kasan_pgd_populate_zero_shadow(pgd_t *pgd, unsigned long addr,
unsigned long end, enum populate_mode mode)
@@ -263,6 +244,10 @@ static unsigned long _pa(unsigned long addr, unsigned long size, enum populate_m
return addr;
case POPULATE_ABS_LOWCORE:
return __abs_lowcore_pa(addr);
+ case POPULATE_KERNEL:
+ return __kernel_pa(addr);
+ case POPULATE_IDENTITY:
+ return __identity_pa(addr);
#ifdef CONFIG_KASAN
case POPULATE_KASAN_MAP_SHADOW:
addr = physmem_alloc_top_down(RR_VMEM, size, size);
@@ -274,16 +259,29 @@ static unsigned long _pa(unsigned long addr, unsigned long size, enum populate_m
}
}
-static bool can_large_pud(pud_t *pu_dir, unsigned long addr, unsigned long end)
+static bool large_allowed(enum populate_mode mode)
+{
+ return (mode == POPULATE_DIRECT) || (mode == POPULATE_IDENTITY) || (mode == POPULATE_KERNEL);
+}
+
+static bool can_large_pud(pud_t *pu_dir, unsigned long addr, unsigned long end,
+ enum populate_mode mode)
{
- return machine.has_edat2 &&
- IS_ALIGNED(addr, PUD_SIZE) && (end - addr) >= PUD_SIZE;
+ unsigned long size = end - addr;
+
+ return machine.has_edat2 && large_allowed(mode) &&
+ IS_ALIGNED(addr, PUD_SIZE) && (size >= PUD_SIZE) &&
+ IS_ALIGNED(_pa(addr, size, mode), PUD_SIZE);
}
-static bool can_large_pmd(pmd_t *pm_dir, unsigned long addr, unsigned long end)
+static bool can_large_pmd(pmd_t *pm_dir, unsigned long addr, unsigned long end,
+ enum populate_mode mode)
{
- return machine.has_edat1 &&
- IS_ALIGNED(addr, PMD_SIZE) && (end - addr) >= PMD_SIZE;
+ unsigned long size = end - addr;
+
+ return machine.has_edat1 && large_allowed(mode) &&
+ IS_ALIGNED(addr, PMD_SIZE) && (size >= PMD_SIZE) &&
+ IS_ALIGNED(_pa(addr, size, mode), PMD_SIZE);
}
static void pgtable_pte_populate(pmd_t *pmd, unsigned long addr, unsigned long end,
@@ -322,7 +320,7 @@ static void pgtable_pmd_populate(pud_t *pud, unsigned long addr, unsigned long e
if (pmd_none(*pmd)) {
if (kasan_pmd_populate_zero_shadow(pmd, addr, next, mode))
continue;
- if (can_large_pmd(pmd, addr, next)) {
+ if (can_large_pmd(pmd, addr, next, mode)) {
entry = __pmd(_pa(addr, _SEGMENT_SIZE, mode));
entry = set_pmd_bit(entry, SEGMENT_KERNEL);
if (!machine.has_nx)
@@ -355,7 +353,7 @@ static void pgtable_pud_populate(p4d_t *p4d, unsigned long addr, unsigned long e
if (pud_none(*pud)) {
if (kasan_pud_populate_zero_shadow(pud, addr, next, mode))
continue;
- if (can_large_pud(pud, addr, next)) {
+ if (can_large_pud(pud, addr, next, mode)) {
entry = __pud(_pa(addr, _REGION3_SIZE, mode));
entry = set_pud_bit(entry, REGION3_KERNEL);
if (!machine.has_nx)
@@ -418,11 +416,12 @@ static void pgtable_populate(unsigned long addr, unsigned long end, enum populat
}
}
-void setup_vmem(unsigned long asce_limit)
+void setup_vmem(unsigned long kernel_start, unsigned long kernel_end, unsigned long asce_limit)
{
unsigned long start, end;
unsigned long asce_type;
unsigned long asce_bits;
+ pgd_t *init_mm_pgd;
int i;
/*
@@ -433,6 +432,15 @@ void setup_vmem(unsigned long asce_limit)
for_each_physmem_online_range(i, &start, &end)
__arch_set_page_nodat((void *)start, (end - start) >> PAGE_SHIFT);
+ /*
+ * init_mm->pgd contains virtual address of swapper_pg_dir.
+ * It is unusable at this stage since DAT is yet off. Swap
+ * it for physical address of swapper_pg_dir and restore
+ * the virtual address after all page tables are created.
+ */
+ init_mm_pgd = init_mm.pgd;
+ init_mm.pgd = (pgd_t *)swapper_pg_dir;
+
if (asce_limit == _REGION1_SIZE) {
asce_type = _REGION2_ENTRY_EMPTY;
asce_bits = _ASCE_TYPE_REGION2 | _ASCE_TABLE_LENGTH;
@@ -453,15 +461,20 @@ void setup_vmem(unsigned long asce_limit)
* the lowcore and create the identity mapping only afterwards.
*/
pgtable_populate(0, sizeof(struct lowcore), POPULATE_DIRECT);
- for_each_physmem_usable_range(i, &start, &end)
- pgtable_populate(start, end, POPULATE_DIRECT);
+ for_each_physmem_usable_range(i, &start, &end) {
+ pgtable_populate((unsigned long)__identity_va(start),
+ (unsigned long)__identity_va(end),
+ POPULATE_IDENTITY);
+ }
+ pgtable_populate(kernel_start, kernel_end, POPULATE_KERNEL);
+ pgtable_populate(AMODE31_START, AMODE31_END, POPULATE_DIRECT);
pgtable_populate(__abs_lowcore, __abs_lowcore + sizeof(struct lowcore),
POPULATE_ABS_LOWCORE);
pgtable_populate(__memcpy_real_area, __memcpy_real_area + PAGE_SIZE,
POPULATE_NONE);
- memcpy_real_ptep = __virt_to_kpte(__memcpy_real_area);
+ memcpy_real_ptep = __identity_va(__virt_to_kpte(__memcpy_real_area));
- kasan_populate_shadow();
+ kasan_populate_shadow(kernel_start, kernel_end);
S390_lowcore.kernel_asce.val = swapper_pg_dir | asce_bits;
S390_lowcore.user_asce = s390_invalid_asce;
@@ -471,4 +484,5 @@ void setup_vmem(unsigned long asce_limit)
local_ctl_load(13, &S390_lowcore.kernel_asce);
init_mm.context.asce = S390_lowcore.kernel_asce.val;
+ init_mm.pgd = init_mm_pgd;
}
diff --git a/arch/s390/boot/vmlinux.lds.S b/arch/s390/boot/vmlinux.lds.S
index 3d7ea585ab..a750711d44 100644
--- a/arch/s390/boot/vmlinux.lds.S
+++ b/arch/s390/boot/vmlinux.lds.S
@@ -99,8 +99,17 @@ SECTIONS
_decompressor_end = .;
+ . = ALIGN(4);
+ .vmlinux.relocs : {
+ __vmlinux_relocs_64_start = .;
+ *(.vmlinux.relocs_64)
+ __vmlinux_relocs_64_end = .;
+ }
+
#ifdef CONFIG_KERNEL_UNCOMPRESSED
- . = 0x100000;
+ . = ALIGN(PAGE_SIZE);
+ . += AMODE31_SIZE; /* .amode31 section */
+ . = ALIGN(1 << 20); /* _SEGMENT_SIZE */
#else
. = ALIGN(8);
#endif
@@ -110,24 +119,6 @@ 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 */
diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig
index f1fb01cd5a..f3602414a9 100644
--- a/arch/s390/configs/debug_defconfig
+++ b/arch/s390/configs/debug_defconfig
@@ -43,7 +43,6 @@ CONFIG_PROFILING=y
CONFIG_KEXEC=y
CONFIG_KEXEC_FILE=y
CONFIG_KEXEC_SIG=y
-CONFIG_CRASH_DUMP=y
CONFIG_LIVEPATCH=y
CONFIG_MARCH_Z13=y
CONFIG_NR_CPUS=512
@@ -51,6 +50,7 @@ CONFIG_NUMA=y
CONFIG_HZ_100=y
CONFIG_CERT_STORE=y
CONFIG_EXPOLINE=y
+# CONFIG_EXPOLINE_EXTERN is not set
CONFIG_EXPOLINE_AUTO=y
CONFIG_CHSC_SCH=y
CONFIG_VFIO_CCW=m
@@ -76,6 +76,7 @@ CONFIG_MODULE_FORCE_UNLOAD=y
CONFIG_MODULE_UNLOAD_TAINT_TRACKING=y
CONFIG_MODVERSIONS=y
CONFIG_MODULE_SRCVERSION_ALL=y
+CONFIG_MODULE_SIG_SHA256=y
CONFIG_BLK_DEV_THROTTLING=y
CONFIG_BLK_WBT=y
CONFIG_BLK_CGROUP_IOLATENCY=y
@@ -100,7 +101,6 @@ CONFIG_MEMORY_HOTPLUG=y
CONFIG_MEMORY_HOTREMOVE=y
CONFIG_KSM=y
CONFIG_TRANSPARENT_HUGEPAGE=y
-CONFIG_CMA_DEBUG=y
CONFIG_CMA_DEBUGFS=y
CONFIG_CMA_SYSFS=y
CONFIG_CMA_AREAS=7
@@ -119,6 +119,7 @@ CONFIG_UNIX_DIAG=m
CONFIG_XFRM_USER=m
CONFIG_NET_KEY=m
CONFIG_SMC_DIAG=m
+CONFIG_SMC_LO=y
CONFIG_INET=y
CONFIG_IP_MULTICAST=y
CONFIG_IP_ADVANCED_ROUTER=y
@@ -133,7 +134,6 @@ CONFIG_IP_MROUTE=y
CONFIG_IP_MROUTE_MULTIPLE_TABLES=y
CONFIG_IP_PIMSM_V1=y
CONFIG_IP_PIMSM_V2=y
-CONFIG_SYN_COOKIES=y
CONFIG_NET_IPVTI=m
CONFIG_INET_AH=m
CONFIG_INET_ESP=m
@@ -167,6 +167,7 @@ CONFIG_BRIDGE_NETFILTER=m
CONFIG_NETFILTER_NETLINK_HOOK=m
CONFIG_NF_CONNTRACK=m
CONFIG_NF_CONNTRACK_SECMARK=y
+CONFIG_NF_CONNTRACK_ZONES=y
CONFIG_NF_CONNTRACK_PROCFS=y
CONFIG_NF_CONNTRACK_EVENTS=y
CONFIG_NF_CONNTRACK_TIMEOUT=y
@@ -183,17 +184,39 @@ CONFIG_NF_CONNTRACK_SIP=m
CONFIG_NF_CONNTRACK_TFTP=m
CONFIG_NF_CT_NETLINK=m
CONFIG_NF_CT_NETLINK_TIMEOUT=m
+CONFIG_NF_CT_NETLINK_HELPER=m
+CONFIG_NETFILTER_NETLINK_GLUE_CT=y
CONFIG_NF_TABLES=m
CONFIG_NF_TABLES_INET=y
+CONFIG_NF_TABLES_NETDEV=y
+CONFIG_NFT_NUMGEN=m
CONFIG_NFT_CT=m
+CONFIG_NFT_FLOW_OFFLOAD=m
+CONFIG_NFT_CONNLIMIT=m
CONFIG_NFT_LOG=m
CONFIG_NFT_LIMIT=m
+CONFIG_NFT_MASQ=m
+CONFIG_NFT_REDIR=m
CONFIG_NFT_NAT=m
+CONFIG_NFT_TUNNEL=m
+CONFIG_NFT_QUEUE=m
+CONFIG_NFT_QUOTA=m
CONFIG_NFT_REJECT=m
CONFIG_NFT_COMPAT=m
CONFIG_NFT_HASH=m
CONFIG_NFT_FIB_INET=m
-CONFIG_NETFILTER_XTABLES_COMPAT=y
+CONFIG_NFT_XFRM=m
+CONFIG_NFT_SOCKET=m
+CONFIG_NFT_OSF=m
+CONFIG_NFT_TPROXY=m
+CONFIG_NFT_SYNPROXY=m
+CONFIG_NFT_DUP_NETDEV=m
+CONFIG_NFT_FWD_NETDEV=m
+CONFIG_NFT_FIB_NETDEV=m
+CONFIG_NFT_REJECT_NETDEV=m
+CONFIG_NF_FLOW_TABLE_INET=m
+CONFIG_NF_FLOW_TABLE=m
+CONFIG_NF_FLOW_TABLE_PROCFS=y
CONFIG_NETFILTER_XT_SET=m
CONFIG_NETFILTER_XT_TARGET_AUDIT=m
CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
@@ -206,8 +229,10 @@ CONFIG_NETFILTER_XT_TARGET_HMARK=m
CONFIG_NETFILTER_XT_TARGET_IDLETIMER=m
CONFIG_NETFILTER_XT_TARGET_LOG=m
CONFIG_NETFILTER_XT_TARGET_MARK=m
+CONFIG_NETFILTER_XT_TARGET_NETMAP=m
CONFIG_NETFILTER_XT_TARGET_NFLOG=m
CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
+CONFIG_NETFILTER_XT_TARGET_REDIRECT=m
CONFIG_NETFILTER_XT_TARGET_TEE=m
CONFIG_NETFILTER_XT_TARGET_TPROXY=m
CONFIG_NETFILTER_XT_TARGET_TRACE=m
@@ -216,6 +241,7 @@ CONFIG_NETFILTER_XT_TARGET_TCPMSS=m
CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP=m
CONFIG_NETFILTER_XT_MATCH_ADDRTYPE=m
CONFIG_NETFILTER_XT_MATCH_BPF=m
+CONFIG_NETFILTER_XT_MATCH_CGROUP=m
CONFIG_NETFILTER_XT_MATCH_CLUSTER=m
CONFIG_NETFILTER_XT_MATCH_COMMENT=m
CONFIG_NETFILTER_XT_MATCH_CONNBYTES=m
@@ -230,6 +256,7 @@ CONFIG_NETFILTER_XT_MATCH_DSCP=m
CONFIG_NETFILTER_XT_MATCH_ESP=m
CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m
CONFIG_NETFILTER_XT_MATCH_HELPER=m
+CONFIG_NETFILTER_XT_MATCH_IPCOMP=m
CONFIG_NETFILTER_XT_MATCH_IPRANGE=m
CONFIG_NETFILTER_XT_MATCH_IPVS=m
CONFIG_NETFILTER_XT_MATCH_LENGTH=m
@@ -247,6 +274,7 @@ CONFIG_NETFILTER_XT_MATCH_QUOTA=m
CONFIG_NETFILTER_XT_MATCH_RATEEST=m
CONFIG_NETFILTER_XT_MATCH_REALM=m
CONFIG_NETFILTER_XT_MATCH_RECENT=m
+CONFIG_NETFILTER_XT_MATCH_SOCKET=m
CONFIG_NETFILTER_XT_MATCH_STATE=m
CONFIG_NETFILTER_XT_MATCH_STATISTIC=m
CONFIG_NETFILTER_XT_MATCH_STRING=m
@@ -302,7 +330,6 @@ CONFIG_IP_NF_TARGET_ECN=m
CONFIG_IP_NF_TARGET_TTL=m
CONFIG_IP_NF_RAW=m
CONFIG_IP_NF_SECURITY=m
-CONFIG_IP_NF_ARPTABLES=m
CONFIG_IP_NF_ARPFILTER=m
CONFIG_IP_NF_ARP_MANGLE=m
CONFIG_NFT_FIB_IPV6=m
@@ -373,7 +400,6 @@ CONFIG_NET_ACT_POLICE=m
CONFIG_NET_ACT_GACT=m
CONFIG_GACT_PROB=y
CONFIG_NET_ACT_MIRRED=m
-CONFIG_NET_ACT_IPT=m
CONFIG_NET_ACT_NAT=m
CONFIG_NET_ACT_PEDIT=m
CONFIG_NET_ACT_SIMP=m
@@ -462,6 +488,7 @@ CONFIG_DM_VERITY=m
CONFIG_DM_VERITY_VERIFY_ROOTHASH_SIG=y
CONFIG_DM_SWITCH=m
CONFIG_DM_INTEGRITY=m
+CONFIG_DM_VDO=m
CONFIG_NETDEVICES=y
CONFIG_BONDING=m
CONFIG_DUMMY=m
@@ -574,18 +601,16 @@ CONFIG_WATCHDOG=y
CONFIG_WATCHDOG_NOWAYOUT=y
CONFIG_SOFT_WATCHDOG=m
CONFIG_DIAG288_WATCHDOG=m
-# CONFIG_DRM_DEBUG_MODESET_LOCK is not set
+CONFIG_DRM=m
+CONFIG_DRM_VIRTIO_GPU=m
CONFIG_FB=y
# CONFIG_FB_DEVICE is not set
-CONFIG_FRAMEBUFFER_CONSOLE=y
-CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y
# CONFIG_HID_SUPPORT is not set
# CONFIG_USB_SUPPORT is not set
CONFIG_INFINIBAND=m
CONFIG_INFINIBAND_USER_ACCESS=m
CONFIG_MLX4_INFINIBAND=m
CONFIG_MLX5_INFINIBAND=m
-CONFIG_SYNC_FILE=y
CONFIG_VFIO=m
CONFIG_VFIO_PCI=m
CONFIG_MLX5_VFIO_PCI=m
@@ -645,7 +670,6 @@ CONFIG_MSDOS_FS=m
CONFIG_VFAT_FS=m
CONFIG_EXFAT_FS=m
CONFIG_NTFS_FS=m
-CONFIG_NTFS_RW=y
CONFIG_PROC_KCORE=y
CONFIG_TMPFS=y
CONFIG_TMPFS_POSIX_ACL=y
@@ -663,6 +687,7 @@ CONFIG_SQUASHFS_XZ=y
CONFIG_SQUASHFS_ZSTD=y
CONFIG_ROMFS_FS=m
CONFIG_NFS_FS=m
+CONFIG_NFS_V2=m
CONFIG_NFS_V3_ACL=y
CONFIG_NFS_V4=m
CONFIG_NFS_SWAP=y
@@ -760,7 +785,6 @@ CONFIG_CRYPTO_USER_API_HASH=m
CONFIG_CRYPTO_USER_API_SKCIPHER=m
CONFIG_CRYPTO_USER_API_RNG=m
CONFIG_CRYPTO_USER_API_AEAD=m
-CONFIG_CRYPTO_STATS=y
CONFIG_CRYPTO_CRC32_S390=y
CONFIG_CRYPTO_SHA512_S390=m
CONFIG_CRYPTO_SHA1_S390=m
@@ -880,6 +904,5 @@ CONFIG_RBTREE_TEST=y
CONFIG_INTERVAL_TREE_TEST=m
CONFIG_PERCPU_TEST=m
CONFIG_ATOMIC64_SELFTEST=y
-CONFIG_STRING_SELFTEST=y
CONFIG_TEST_BITOPS=m
CONFIG_TEST_BPF=m
diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig
index d33f814f78..d0d8925fdf 100644
--- a/arch/s390/configs/defconfig
+++ b/arch/s390/configs/defconfig
@@ -41,7 +41,6 @@ CONFIG_PROFILING=y
CONFIG_KEXEC=y
CONFIG_KEXEC_FILE=y
CONFIG_KEXEC_SIG=y
-CONFIG_CRASH_DUMP=y
CONFIG_LIVEPATCH=y
CONFIG_MARCH_Z13=y
CONFIG_NR_CPUS=512
@@ -49,6 +48,7 @@ CONFIG_NUMA=y
CONFIG_HZ_100=y
CONFIG_CERT_STORE=y
CONFIG_EXPOLINE=y
+# CONFIG_EXPOLINE_EXTERN is not set
CONFIG_EXPOLINE_AUTO=y
CONFIG_CHSC_SCH=y
CONFIG_VFIO_CCW=m
@@ -71,6 +71,7 @@ CONFIG_MODULE_FORCE_UNLOAD=y
CONFIG_MODULE_UNLOAD_TAINT_TRACKING=y
CONFIG_MODVERSIONS=y
CONFIG_MODULE_SRCVERSION_ALL=y
+CONFIG_MODULE_SIG_SHA256=y
CONFIG_BLK_DEV_THROTTLING=y
CONFIG_BLK_WBT=y
CONFIG_BLK_CGROUP_IOLATENCY=y
@@ -110,6 +111,7 @@ CONFIG_UNIX_DIAG=m
CONFIG_XFRM_USER=m
CONFIG_NET_KEY=m
CONFIG_SMC_DIAG=m
+CONFIG_SMC_LO=y
CONFIG_INET=y
CONFIG_IP_MULTICAST=y
CONFIG_IP_ADVANCED_ROUTER=y
@@ -124,7 +126,6 @@ CONFIG_IP_MROUTE=y
CONFIG_IP_MROUTE_MULTIPLE_TABLES=y
CONFIG_IP_PIMSM_V1=y
CONFIG_IP_PIMSM_V2=y
-CONFIG_SYN_COOKIES=y
CONFIG_NET_IPVTI=m
CONFIG_INET_AH=m
CONFIG_INET_ESP=m
@@ -158,6 +159,7 @@ CONFIG_BRIDGE_NETFILTER=m
CONFIG_NETFILTER_NETLINK_HOOK=m
CONFIG_NF_CONNTRACK=m
CONFIG_NF_CONNTRACK_SECMARK=y
+CONFIG_NF_CONNTRACK_ZONES=y
CONFIG_NF_CONNTRACK_PROCFS=y
CONFIG_NF_CONNTRACK_EVENTS=y
CONFIG_NF_CONNTRACK_TIMEOUT=y
@@ -174,17 +176,39 @@ CONFIG_NF_CONNTRACK_SIP=m
CONFIG_NF_CONNTRACK_TFTP=m
CONFIG_NF_CT_NETLINK=m
CONFIG_NF_CT_NETLINK_TIMEOUT=m
+CONFIG_NF_CT_NETLINK_HELPER=m
+CONFIG_NETFILTER_NETLINK_GLUE_CT=y
CONFIG_NF_TABLES=m
CONFIG_NF_TABLES_INET=y
+CONFIG_NF_TABLES_NETDEV=y
+CONFIG_NFT_NUMGEN=m
CONFIG_NFT_CT=m
+CONFIG_NFT_FLOW_OFFLOAD=m
+CONFIG_NFT_CONNLIMIT=m
CONFIG_NFT_LOG=m
CONFIG_NFT_LIMIT=m
+CONFIG_NFT_MASQ=m
+CONFIG_NFT_REDIR=m
CONFIG_NFT_NAT=m
+CONFIG_NFT_TUNNEL=m
+CONFIG_NFT_QUEUE=m
+CONFIG_NFT_QUOTA=m
CONFIG_NFT_REJECT=m
CONFIG_NFT_COMPAT=m
CONFIG_NFT_HASH=m
CONFIG_NFT_FIB_INET=m
-CONFIG_NETFILTER_XTABLES_COMPAT=y
+CONFIG_NFT_XFRM=m
+CONFIG_NFT_SOCKET=m
+CONFIG_NFT_OSF=m
+CONFIG_NFT_TPROXY=m
+CONFIG_NFT_SYNPROXY=m
+CONFIG_NFT_DUP_NETDEV=m
+CONFIG_NFT_FWD_NETDEV=m
+CONFIG_NFT_FIB_NETDEV=m
+CONFIG_NFT_REJECT_NETDEV=m
+CONFIG_NF_FLOW_TABLE_INET=m
+CONFIG_NF_FLOW_TABLE=m
+CONFIG_NF_FLOW_TABLE_PROCFS=y
CONFIG_NETFILTER_XT_SET=m
CONFIG_NETFILTER_XT_TARGET_AUDIT=m
CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
@@ -197,8 +221,10 @@ CONFIG_NETFILTER_XT_TARGET_HMARK=m
CONFIG_NETFILTER_XT_TARGET_IDLETIMER=m
CONFIG_NETFILTER_XT_TARGET_LOG=m
CONFIG_NETFILTER_XT_TARGET_MARK=m
+CONFIG_NETFILTER_XT_TARGET_NETMAP=m
CONFIG_NETFILTER_XT_TARGET_NFLOG=m
CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
+CONFIG_NETFILTER_XT_TARGET_REDIRECT=m
CONFIG_NETFILTER_XT_TARGET_TEE=m
CONFIG_NETFILTER_XT_TARGET_TPROXY=m
CONFIG_NETFILTER_XT_TARGET_TRACE=m
@@ -207,6 +233,7 @@ CONFIG_NETFILTER_XT_TARGET_TCPMSS=m
CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP=m
CONFIG_NETFILTER_XT_MATCH_ADDRTYPE=m
CONFIG_NETFILTER_XT_MATCH_BPF=m
+CONFIG_NETFILTER_XT_MATCH_CGROUP=m
CONFIG_NETFILTER_XT_MATCH_CLUSTER=m
CONFIG_NETFILTER_XT_MATCH_COMMENT=m
CONFIG_NETFILTER_XT_MATCH_CONNBYTES=m
@@ -221,6 +248,7 @@ CONFIG_NETFILTER_XT_MATCH_DSCP=m
CONFIG_NETFILTER_XT_MATCH_ESP=m
CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m
CONFIG_NETFILTER_XT_MATCH_HELPER=m
+CONFIG_NETFILTER_XT_MATCH_IPCOMP=m
CONFIG_NETFILTER_XT_MATCH_IPRANGE=m
CONFIG_NETFILTER_XT_MATCH_IPVS=m
CONFIG_NETFILTER_XT_MATCH_LENGTH=m
@@ -238,6 +266,7 @@ CONFIG_NETFILTER_XT_MATCH_QUOTA=m
CONFIG_NETFILTER_XT_MATCH_RATEEST=m
CONFIG_NETFILTER_XT_MATCH_REALM=m
CONFIG_NETFILTER_XT_MATCH_RECENT=m
+CONFIG_NETFILTER_XT_MATCH_SOCKET=m
CONFIG_NETFILTER_XT_MATCH_STATE=m
CONFIG_NETFILTER_XT_MATCH_STATISTIC=m
CONFIG_NETFILTER_XT_MATCH_STRING=m
@@ -293,7 +322,6 @@ CONFIG_IP_NF_TARGET_ECN=m
CONFIG_IP_NF_TARGET_TTL=m
CONFIG_IP_NF_RAW=m
CONFIG_IP_NF_SECURITY=m
-CONFIG_IP_NF_ARPTABLES=m
CONFIG_IP_NF_ARPFILTER=m
CONFIG_IP_NF_ARP_MANGLE=m
CONFIG_NFT_FIB_IPV6=m
@@ -363,7 +391,6 @@ CONFIG_NET_ACT_POLICE=m
CONFIG_NET_ACT_GACT=m
CONFIG_GACT_PROB=y
CONFIG_NET_ACT_MIRRED=m
-CONFIG_NET_ACT_IPT=m
CONFIG_NET_ACT_NAT=m
CONFIG_NET_ACT_PEDIT=m
CONFIG_NET_ACT_SIMP=m
@@ -452,6 +479,7 @@ CONFIG_DM_VERITY=m
CONFIG_DM_VERITY_VERIFY_ROOTHASH_SIG=y
CONFIG_DM_SWITCH=m
CONFIG_DM_INTEGRITY=m
+CONFIG_DM_VDO=m
CONFIG_NETDEVICES=y
CONFIG_BONDING=m
CONFIG_DUMMY=m
@@ -564,17 +592,16 @@ CONFIG_WATCHDOG_CORE=y
CONFIG_WATCHDOG_NOWAYOUT=y
CONFIG_SOFT_WATCHDOG=m
CONFIG_DIAG288_WATCHDOG=m
+CONFIG_DRM=m
+CONFIG_DRM_VIRTIO_GPU=m
CONFIG_FB=y
# CONFIG_FB_DEVICE is not set
-CONFIG_FRAMEBUFFER_CONSOLE=y
-CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y
# CONFIG_HID_SUPPORT is not set
# CONFIG_USB_SUPPORT is not set
CONFIG_INFINIBAND=m
CONFIG_INFINIBAND_USER_ACCESS=m
CONFIG_MLX4_INFINIBAND=m
CONFIG_MLX5_INFINIBAND=m
-CONFIG_SYNC_FILE=y
CONFIG_VFIO=m
CONFIG_VFIO_PCI=m
CONFIG_MLX5_VFIO_PCI=m
@@ -630,7 +657,6 @@ CONFIG_MSDOS_FS=m
CONFIG_VFAT_FS=m
CONFIG_EXFAT_FS=m
CONFIG_NTFS_FS=m
-CONFIG_NTFS_RW=y
CONFIG_PROC_KCORE=y
CONFIG_TMPFS=y
CONFIG_TMPFS_POSIX_ACL=y
@@ -649,6 +675,7 @@ CONFIG_SQUASHFS_XZ=y
CONFIG_SQUASHFS_ZSTD=y
CONFIG_ROMFS_FS=m
CONFIG_NFS_FS=m
+CONFIG_NFS_V2=m
CONFIG_NFS_V3_ACL=y
CONFIG_NFS_V4=m
CONFIG_NFS_SWAP=y
@@ -745,7 +772,6 @@ CONFIG_CRYPTO_USER_API_HASH=m
CONFIG_CRYPTO_USER_API_SKCIPHER=m
CONFIG_CRYPTO_USER_API_RNG=m
CONFIG_CRYPTO_USER_API_AEAD=m
-CONFIG_CRYPTO_STATS=y
CONFIG_CRYPTO_CRC32_S390=y
CONFIG_CRYPTO_SHA512_S390=m
CONFIG_CRYPTO_SHA1_S390=m
diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig
index c51f3ec4eb..8c2b61363b 100644
--- a/arch/s390/configs/zfcpdump_defconfig
+++ b/arch/s390/configs/zfcpdump_defconfig
@@ -9,25 +9,22 @@ CONFIG_BPF_SYSCALL=y
CONFIG_BLK_DEV_INITRD=y
CONFIG_CC_OPTIMIZE_FOR_SIZE=y
CONFIG_KEXEC=y
-CONFIG_CRASH_DUMP=y
CONFIG_MARCH_Z13=y
CONFIG_NR_CPUS=2
CONFIG_HZ_100=y
# CONFIG_CHSC_SCH is not set
# CONFIG_SCM_BUS is not set
+# CONFIG_AP is not set
# CONFIG_PFAULT is not set
# CONFIG_S390_HYPFS is not set
# CONFIG_VIRTUALIZATION is not set
# CONFIG_S390_GUEST is not set
# CONFIG_SECCOMP is not set
-# CONFIG_GCC_PLUGINS is not set
# CONFIG_BLOCK_LEGACY_AUTOLOAD is not set
CONFIG_PARTITION_ADVANCED=y
# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
# CONFIG_SWAP is not set
# CONFIG_COMPAT_BRK is not set
-# CONFIG_COMPACTION is not set
-# CONFIG_MIGRATION is not set
CONFIG_NET=y
# CONFIG_IUCV is not set
# CONFIG_PCPU_DEV_REFCNT is not set
diff --git a/arch/s390/include/asm/alternative-asm.h b/arch/s390/include/asm/alternative-asm.h
index 7db046596b..608f6287ca 100644
--- a/arch/s390/include/asm/alternative-asm.h
+++ b/arch/s390/include/asm/alternative-asm.h
@@ -15,6 +15,7 @@
.long \alt_start - .
.word \feature
.byte \orig_end - \orig_start
+ .org . - ( \orig_end - \orig_start ) & 1
.org . - ( \orig_end - \orig_start ) + ( \alt_end - \alt_start )
.org . - ( \alt_end - \alt_start ) + ( \orig_end - \orig_start )
.endm
diff --git a/arch/s390/include/asm/alternative.h b/arch/s390/include/asm/alternative.h
index 904dd049f9..dd93b92c3a 100644
--- a/arch/s390/include/asm/alternative.h
+++ b/arch/s390/include/asm/alternative.h
@@ -53,6 +53,7 @@ void apply_alternatives(struct alt_instr *start, struct alt_instr *end);
"\t.long " b_altinstr(num)"b - .\n" /* alt instruction */ \
"\t.word " __stringify(facility) "\n" /* facility bit */ \
"\t.byte " oldinstr_len "\n" /* instruction len */ \
+ "\t.org . - (" oldinstr_len ") & 1\n" \
"\t.org . - (" oldinstr_len ") + (" altinstr_len(num) ")\n" \
"\t.org . - (" altinstr_len(num) ") + (" oldinstr_len ")\n"
diff --git a/arch/s390/include/asm/ap.h b/arch/s390/include/asm/ap.h
index 43ac4a64f4..395b02d6a1 100644
--- a/arch/s390/include/asm/ap.h
+++ b/arch/s390/include/asm/ap.h
@@ -223,13 +223,18 @@ static inline struct ap_queue_status ap_zapq(ap_qid_t qid, int fbit)
* config info as returned by the ap_qci() function.
*/
struct ap_config_info {
- unsigned int apsc : 1; /* S bit */
- unsigned int apxa : 1; /* N bit */
- unsigned int qact : 1; /* C bit */
- unsigned int rc8a : 1; /* R bit */
- unsigned int : 4;
- unsigned int apsb : 1; /* B bit */
- unsigned int : 23;
+ union {
+ unsigned int flags;
+ struct {
+ unsigned int apsc : 1; /* S bit */
+ unsigned int apxa : 1; /* N bit */
+ unsigned int qact : 1; /* C bit */
+ unsigned int rc8a : 1; /* R bit */
+ unsigned int : 4;
+ unsigned int apsb : 1; /* B bit */
+ unsigned int : 23;
+ };
+ };
unsigned char na; /* max # of APs - 1 */
unsigned char nd; /* max # of Domains - 1 */
unsigned char _reserved0[10];
@@ -544,15 +549,4 @@ static inline struct ap_queue_status ap_dqap(ap_qid_t qid,
return reg1.status;
}
-/*
- * Interface to tell the AP bus code that a configuration
- * change has happened. The bus code should at least do
- * an ap bus resource rescan.
- */
-#if IS_ENABLED(CONFIG_ZCRYPT)
-void ap_bus_cfg_chg(void);
-#else
-static inline void ap_bus_cfg_chg(void){}
-#endif
-
#endif /* _ASM_S390_AP_H_ */
diff --git a/arch/s390/include/asm/asm-prototypes.h b/arch/s390/include/asm/asm-prototypes.h
index 56096ae26f..f662eb4b92 100644
--- a/arch/s390/include/asm/asm-prototypes.h
+++ b/arch/s390/include/asm/asm-prototypes.h
@@ -4,6 +4,7 @@
#include <linux/kvm_host.h>
#include <linux/ftrace.h>
#include <asm/fpu.h>
+#include <asm/nospec-branch.h>
#include <asm-generic/asm-prototypes.h>
__int128_t __ashlti3(__int128_t a, int b);
diff --git a/arch/s390/include/asm/chsc.h b/arch/s390/include/asm/chsc.h
index bb48ea380c..bb78159d80 100644
--- a/arch/s390/include/asm/chsc.h
+++ b/arch/s390/include/asm/chsc.h
@@ -11,6 +11,9 @@
#include <uapi/asm/chsc.h>
+/* struct from linux/notifier.h */
+struct notifier_block;
+
/**
* Operation codes for CHSC PNSO:
* PNSO_OC_NET_BRIDGE_INFO - only addresses that are visible to a bridgeport
@@ -66,4 +69,16 @@ struct chsc_pnso_area {
struct chsc_pnso_naid_l2 entries[];
} __packed __aligned(PAGE_SIZE);
+/*
+ * notifier interface - registered notifiers gets called on
+ * the following events:
+ * - ap config changed (CHSC_NOTIFY_AP_CFG)
+ */
+enum chsc_notify_type {
+ CHSC_NOTIFY_AP_CFG = 3,
+};
+
+int chsc_notifier_register(struct notifier_block *nb);
+int chsc_notifier_unregister(struct notifier_block *nb);
+
#endif /* _ASM_S390_CHSC_H */
diff --git a/arch/s390/include/asm/cpacf.h b/arch/s390/include/asm/cpacf.h
index b378e2b57a..c786538e39 100644
--- a/arch/s390/include/asm/cpacf.h
+++ b/arch/s390/include/asm/cpacf.h
@@ -166,28 +166,86 @@
typedef struct { unsigned char bytes[16]; } cpacf_mask_t;
-/**
- * cpacf_query() - check if a specific CPACF function is available
- * @opcode: the opcode of the crypto instruction
- * @func: the function code to test for
- *
- * Executes the query function for the given crypto instruction @opcode
- * and checks if @func is available
- *
- * Returns 1 if @func is available for @opcode, 0 otherwise
+/*
+ * Prototype for a not existing function to produce a link
+ * error if __cpacf_query() or __cpacf_check_opcode() is used
+ * with an invalid compile time const opcode.
*/
-static __always_inline void __cpacf_query(unsigned int opcode, cpacf_mask_t *mask)
+void __cpacf_bad_opcode(void);
+
+static __always_inline void __cpacf_query_rre(u32 opc, u8 r1, u8 r2,
+ cpacf_mask_t *mask)
{
asm volatile(
- " lghi 0,0\n" /* query function */
- " lgr 1,%[mask]\n"
- " spm 0\n" /* pckmo doesn't change the cc */
- /* Parameter regs are ignored, but must be nonzero and unique */
- "0: .insn rrf,%[opc] << 16,2,4,6,0\n"
- " brc 1,0b\n" /* handle partial completion */
- : "=m" (*mask)
- : [mask] "d" ((unsigned long)mask), [opc] "i" (opcode)
- : "cc", "0", "1");
+ " la %%r1,%[mask]\n"
+ " xgr %%r0,%%r0\n"
+ " .insn rre,%[opc] << 16,%[r1],%[r2]\n"
+ : [mask] "=R" (*mask)
+ : [opc] "i" (opc),
+ [r1] "i" (r1), [r2] "i" (r2)
+ : "cc", "r0", "r1");
+}
+
+static __always_inline void __cpacf_query_rrf(u32 opc,
+ u8 r1, u8 r2, u8 r3, u8 m4,
+ cpacf_mask_t *mask)
+{
+ asm volatile(
+ " la %%r1,%[mask]\n"
+ " xgr %%r0,%%r0\n"
+ " .insn rrf,%[opc] << 16,%[r1],%[r2],%[r3],%[m4]\n"
+ : [mask] "=R" (*mask)
+ : [opc] "i" (opc), [r1] "i" (r1), [r2] "i" (r2),
+ [r3] "i" (r3), [m4] "i" (m4)
+ : "cc", "r0", "r1");
+}
+
+static __always_inline void __cpacf_query(unsigned int opcode,
+ cpacf_mask_t *mask)
+{
+ switch (opcode) {
+ case CPACF_KDSA:
+ __cpacf_query_rre(CPACF_KDSA, 0, 2, mask);
+ break;
+ case CPACF_KIMD:
+ __cpacf_query_rre(CPACF_KIMD, 0, 2, mask);
+ break;
+ case CPACF_KLMD:
+ __cpacf_query_rre(CPACF_KLMD, 0, 2, mask);
+ break;
+ case CPACF_KM:
+ __cpacf_query_rre(CPACF_KM, 2, 4, mask);
+ break;
+ case CPACF_KMA:
+ __cpacf_query_rrf(CPACF_KMA, 2, 4, 6, 0, mask);
+ break;
+ case CPACF_KMAC:
+ __cpacf_query_rre(CPACF_KMAC, 0, 2, mask);
+ break;
+ case CPACF_KMC:
+ __cpacf_query_rre(CPACF_KMC, 2, 4, mask);
+ break;
+ case CPACF_KMCTR:
+ __cpacf_query_rrf(CPACF_KMCTR, 2, 4, 6, 0, mask);
+ break;
+ case CPACF_KMF:
+ __cpacf_query_rre(CPACF_KMF, 2, 4, mask);
+ break;
+ case CPACF_KMO:
+ __cpacf_query_rre(CPACF_KMO, 2, 4, mask);
+ break;
+ case CPACF_PCC:
+ __cpacf_query_rre(CPACF_PCC, 0, 0, mask);
+ break;
+ case CPACF_PCKMO:
+ __cpacf_query_rre(CPACF_PCKMO, 0, 0, mask);
+ break;
+ case CPACF_PRNO:
+ __cpacf_query_rre(CPACF_PRNO, 2, 4, mask);
+ break;
+ default:
+ __cpacf_bad_opcode();
+ }
}
static __always_inline int __cpacf_check_opcode(unsigned int opcode)
@@ -211,10 +269,21 @@ static __always_inline int __cpacf_check_opcode(unsigned int opcode)
case CPACF_KMA:
return test_facility(146); /* check for MSA8 */
default:
- BUG();
+ __cpacf_bad_opcode();
+ return 0;
}
}
+/**
+ * cpacf_query() - check if a specific CPACF function is available
+ * @opcode: the opcode of the crypto instruction
+ * @func: the function code to test for
+ *
+ * Executes the query function for the given crypto instruction @opcode
+ * and checks if @func is available
+ *
+ * Returns 1 if @func is available for @opcode, 0 otherwise
+ */
static __always_inline int cpacf_query(unsigned int opcode, cpacf_mask_t *mask)
{
if (__cpacf_check_opcode(opcode)) {
diff --git a/arch/s390/include/asm/entry-common.h b/arch/s390/include/asm/entry-common.h
index 7f5004065e..35555c9446 100644
--- a/arch/s390/include/asm/entry-common.h
+++ b/arch/s390/include/asm/entry-common.h
@@ -54,7 +54,7 @@ static __always_inline void arch_exit_to_user_mode(void)
static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs,
unsigned long ti_work)
{
- choose_random_kstack_offset(get_tod_clock_fast() & 0xff);
+ choose_random_kstack_offset(get_tod_clock_fast());
}
#define arch_exit_to_user_mode_prepare arch_exit_to_user_mode_prepare
diff --git a/arch/s390/include/asm/extmem.h b/arch/s390/include/asm/extmem.h
index 568fd81bb7..e0a06060af 100644
--- a/arch/s390/include/asm/extmem.h
+++ b/arch/s390/include/asm/extmem.h
@@ -8,6 +8,13 @@
#define _ASM_S390X_DCSS_H
#ifndef __ASSEMBLY__
+/*
+ * DCSS segment is defined as a contiguous range of pages using DEFSEG command.
+ * The range start and end is a page number with a value less than or equal to
+ * 0x7ffffff (see CP Commands and Utilities Reference).
+ */
+#define MAX_DCSS_ADDR (512UL * SZ_1G)
+
/* possible values for segment type as returned by segment_info */
#define SEG_TYPE_SW 0
#define SEG_TYPE_EW 1
diff --git a/arch/s390/include/asm/ftrace.h b/arch/s390/include/asm/ftrace.h
index 621f23d5ae..77e479d44f 100644
--- a/arch/s390/include/asm/ftrace.h
+++ b/arch/s390/include/asm/ftrace.h
@@ -8,12 +8,8 @@
#ifndef __ASSEMBLY__
-#ifdef CONFIG_CC_IS_CLANG
-/* https://llvm.org/pr41424 */
-#define ftrace_return_address(n) 0UL
-#else
-#define ftrace_return_address(n) __builtin_return_address(n)
-#endif
+unsigned long return_address(unsigned int n);
+#define ftrace_return_address(n) return_address(n)
void ftrace_caller(void);
diff --git a/arch/s390/include/asm/gmap.h b/arch/s390/include/asm/gmap.h
index 5cc46e0dde..9725586f42 100644
--- a/arch/s390/include/asm/gmap.h
+++ b/arch/s390/include/asm/gmap.h
@@ -146,7 +146,7 @@ int gmap_mprotect_notify(struct gmap *, unsigned long start,
void gmap_sync_dirty_log_pmd(struct gmap *gmap, unsigned long dirty_bitmap[4],
unsigned long gaddr, unsigned long vmaddr);
-int gmap_mark_unmergeable(void);
+int s390_disable_cow_sharing(void);
void s390_unlist_old_asce(struct gmap *gmap);
int s390_replace_asce(struct gmap *gmap);
void s390_uv_destroy_pfns(unsigned long count, unsigned long *pfns);
diff --git a/arch/s390/include/asm/hugetlb.h b/arch/s390/include/asm/hugetlb.h
index deb198a610..ce5f4fe8be 100644
--- a/arch/s390/include/asm/hugetlb.h
+++ b/arch/s390/include/asm/hugetlb.h
@@ -39,11 +39,11 @@ static inline int prepare_hugepage_range(struct file *file,
return 0;
}
-static inline void arch_clear_hugepage_flags(struct page *page)
+static inline void arch_clear_hugetlb_flags(struct folio *folio)
{
- clear_bit(PG_arch_1, &page->flags);
+ clear_bit(PG_arch_1, &folio->flags);
}
-#define arch_clear_hugepage_flags arch_clear_hugepage_flags
+#define arch_clear_hugetlb_flags arch_clear_hugetlb_flags
static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, unsigned long sz)
diff --git a/arch/s390/include/asm/io.h b/arch/s390/include/asm/io.h
index 4453ad7c11..0fbc992d7a 100644
--- a/arch/s390/include/asm/io.h
+++ b/arch/s390/include/asm/io.h
@@ -73,6 +73,21 @@ static inline void ioport_unmap(void __iomem *p)
#define __raw_writel zpci_write_u32
#define __raw_writeq zpci_write_u64
+/* combine single writes by using store-block insn */
+static inline void __iowrite32_copy(void __iomem *to, const void *from,
+ size_t count)
+{
+ zpci_memcpy_toio(to, from, count * 4);
+}
+#define __iowrite32_copy __iowrite32_copy
+
+static inline void __iowrite64_copy(void __iomem *to, const void *from,
+ size_t count)
+{
+ zpci_memcpy_toio(to, from, count * 8);
+}
+#define __iowrite64_copy __iowrite64_copy
+
#endif /* CONFIG_PCI */
#include <asm-generic/io.h>
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index 9599046188..9281063636 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -427,6 +427,7 @@ struct kvm_vcpu_stat {
u64 instruction_io_other;
u64 instruction_lpsw;
u64 instruction_lpswe;
+ u64 instruction_lpswey;
u64 instruction_pfmf;
u64 instruction_ptff;
u64 instruction_sck;
diff --git a/arch/s390/include/asm/mmu.h b/arch/s390/include/asm/mmu.h
index bb1b4bef18..4c2dc7abc2 100644
--- a/arch/s390/include/asm/mmu.h
+++ b/arch/s390/include/asm/mmu.h
@@ -32,6 +32,11 @@ typedef struct {
unsigned int uses_skeys:1;
/* The mmu context uses CMM. */
unsigned int uses_cmm:1;
+ /*
+ * The mmu context allows COW-sharing of memory pages (KSM, zeropage).
+ * Note that COW-sharing during fork() is currently always allowed.
+ */
+ unsigned int allow_cow_sharing:1;
/* The gmaps associated with this context are allowed to use huge pages. */
unsigned int allow_gmap_hpage_1m:1;
} mm_context_t;
diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h
index 929af18b09..a7789a9f62 100644
--- a/arch/s390/include/asm/mmu_context.h
+++ b/arch/s390/include/asm/mmu_context.h
@@ -35,6 +35,7 @@ static inline int init_new_context(struct task_struct *tsk,
mm->context.has_pgste = 0;
mm->context.uses_skeys = 0;
mm->context.uses_cmm = 0;
+ mm->context.allow_cow_sharing = 1;
mm->context.allow_gmap_hpage_1m = 0;
#endif
switch (mm->context.asce_limit) {
diff --git a/arch/s390/include/asm/nospec-branch.h b/arch/s390/include/asm/nospec-branch.h
index 82725cf783..b9c1f3cae8 100644
--- a/arch/s390/include/asm/nospec-branch.h
+++ b/arch/s390/include/asm/nospec-branch.h
@@ -17,6 +17,26 @@ static inline bool nospec_uses_trampoline(void)
return __is_defined(CC_USING_EXPOLINE) && !nospec_disable;
}
+#ifdef CONFIG_EXPOLINE_EXTERN
+
+void __s390_indirect_jump_r1(void);
+void __s390_indirect_jump_r2(void);
+void __s390_indirect_jump_r3(void);
+void __s390_indirect_jump_r4(void);
+void __s390_indirect_jump_r5(void);
+void __s390_indirect_jump_r6(void);
+void __s390_indirect_jump_r7(void);
+void __s390_indirect_jump_r8(void);
+void __s390_indirect_jump_r9(void);
+void __s390_indirect_jump_r10(void);
+void __s390_indirect_jump_r11(void);
+void __s390_indirect_jump_r12(void);
+void __s390_indirect_jump_r13(void);
+void __s390_indirect_jump_r14(void);
+void __s390_indirect_jump_r15(void);
+
+#endif
+
#endif /* __ASSEMBLY__ */
#endif /* _ASM_S390_EXPOLINE_H */
diff --git a/arch/s390/include/asm/nospec-insn.h b/arch/s390/include/asm/nospec-insn.h
index 7a946c42ad..cb15dd25bf 100644
--- a/arch/s390/include/asm/nospec-insn.h
+++ b/arch/s390/include/asm/nospec-insn.h
@@ -16,24 +16,25 @@
*/
.macro __THUNK_PROLOG_NAME name
#ifdef CONFIG_EXPOLINE_EXTERN
- .pushsection .text,"ax",@progbits
- __ALIGN
+ SYM_CODE_START(\name)
#else
.pushsection .text.\name,"axG",@progbits,\name,comdat
-#endif
.globl \name
.hidden \name
.type \name,@function
\name:
CFI_STARTPROC
+#endif
.endm
.macro __THUNK_EPILOG_NAME name
- CFI_ENDPROC
#ifdef CONFIG_EXPOLINE_EXTERN
- .size \name, .-\name
-#endif
+ SYM_CODE_END(\name)
+ EXPORT_SYMBOL(\name)
+#else
+ CFI_ENDPROC
.popsection
+#endif
.endm
.macro __THUNK_PROLOG_BR r1
diff --git a/arch/s390/include/asm/os_info.h b/arch/s390/include/asm/os_info.h
index a4d2e103f1..3ee9e8f5ce 100644
--- a/arch/s390/include/asm/os_info.h
+++ b/arch/s390/include/asm/os_info.h
@@ -17,11 +17,25 @@
#define OS_INFO_VMCOREINFO 0
#define OS_INFO_REIPL_BLOCK 1
#define OS_INFO_FLAGS_ENTRY 2
+#define OS_INFO_RESERVED 3
+#define OS_INFO_IDENTITY_BASE 4
+#define OS_INFO_KASLR_OFFSET 5
+#define OS_INFO_KASLR_OFF_PHYS 6
+#define OS_INFO_VMEMMAP 7
+#define OS_INFO_AMODE31_START 8
+#define OS_INFO_AMODE31_END 9
+#define OS_INFO_IMAGE_START 10
+#define OS_INFO_IMAGE_END 11
+#define OS_INFO_IMAGE_PHYS 12
+#define OS_INFO_MAX 13
#define OS_INFO_FLAG_REIPL_CLEAR (1UL << 0)
struct os_info_entry {
- u64 addr;
+ union {
+ u64 addr;
+ u64 val;
+ };
u64 size;
u32 csum;
} __packed;
@@ -33,17 +47,24 @@ struct os_info {
u16 version_minor;
u64 crashkernel_addr;
u64 crashkernel_size;
- struct os_info_entry entry[3];
- u8 reserved[4004];
+ struct os_info_entry entry[OS_INFO_MAX];
+ u8 reserved[3804];
} __packed;
void os_info_init(void);
-void os_info_entry_add(int nr, void *ptr, u64 len);
+void os_info_entry_add_data(int nr, void *ptr, u64 len);
+void os_info_entry_add_val(int nr, u64 val);
void os_info_crashkernel_add(unsigned long base, unsigned long size);
u32 os_info_csum(struct os_info *os_info);
#ifdef CONFIG_CRASH_DUMP
void *os_info_old_entry(int nr, unsigned long *size);
+static inline unsigned long os_info_old_value(int nr)
+{
+ unsigned long size;
+
+ return (unsigned long)os_info_old_entry(nr, &size);
+}
#else
static inline void *os_info_old_entry(int nr, unsigned long *size)
{
diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h
index 9381879f7e..224ff9d433 100644
--- a/arch/s390/include/asm/page.h
+++ b/arch/s390/include/asm/page.h
@@ -178,19 +178,52 @@ int arch_make_page_accessible(struct page *page);
#define HAVE_ARCH_MAKE_PAGE_ACCESSIBLE
#endif
-#define __PAGE_OFFSET 0x0UL
-#define PAGE_OFFSET 0x0UL
+struct vm_layout {
+ unsigned long kaslr_offset;
+ unsigned long kaslr_offset_phys;
+ unsigned long identity_base;
+ unsigned long identity_size;
+};
-#define __pa_nodebug(x) ((unsigned long)(x))
+extern struct vm_layout vm_layout;
+
+#define __kaslr_offset vm_layout.kaslr_offset
+#define __kaslr_offset_phys vm_layout.kaslr_offset_phys
+#define __identity_base vm_layout.identity_base
+#define ident_map_size vm_layout.identity_size
+
+static inline unsigned long kaslr_offset(void)
+{
+ return __kaslr_offset;
+}
+
+extern int __kaslr_enabled;
+static inline int kaslr_enabled(void)
+{
+ if (IS_ENABLED(CONFIG_RANDOMIZE_BASE))
+ return __kaslr_enabled;
+ return 0;
+}
+
+#define __PAGE_OFFSET __identity_base
+#define PAGE_OFFSET __PAGE_OFFSET
#ifdef __DECOMPRESSOR
+#define __pa_nodebug(x) ((unsigned long)(x))
#define __pa(x) __pa_nodebug(x)
#define __pa32(x) __pa(x)
#define __va(x) ((void *)(unsigned long)(x))
#else /* __DECOMPRESSOR */
+static inline unsigned long __pa_nodebug(unsigned long x)
+{
+ if (x < __kaslr_offset)
+ return x - __identity_base;
+ return x - __kaslr_offset + __kaslr_offset_phys;
+}
+
#ifdef CONFIG_DEBUG_VIRTUAL
unsigned long __phys_addr(unsigned long x, bool is_31bit);
@@ -206,7 +239,7 @@ static inline unsigned long __phys_addr(unsigned long x, bool is_31bit)
#define __pa(x) __phys_addr((unsigned long)(x), false)
#define __pa32(x) __phys_addr((unsigned long)(x), true)
-#define __va(x) ((void *)(unsigned long)(x))
+#define __va(x) ((void *)((unsigned long)(x) + __identity_base))
#endif /* __DECOMPRESSOR */
@@ -231,7 +264,7 @@ static inline unsigned long virt_to_pfn(const void *kaddr)
#define virt_to_page(kaddr) pfn_to_page(virt_to_pfn(kaddr))
#define page_to_virt(page) pfn_to_virt(page_to_pfn(page))
-#define virt_addr_valid(kaddr) pfn_valid(phys_to_pfn(__pa_nodebug(kaddr)))
+#define virt_addr_valid(kaddr) pfn_valid(phys_to_pfn(__pa_nodebug((unsigned long)(kaddr))))
#define VM_DATA_DEFAULT_FLAGS VM_DATA_FLAGS_NON_EXEC
@@ -240,4 +273,11 @@ static inline unsigned long virt_to_pfn(const void *kaddr)
#include <asm-generic/memory_model.h>
#include <asm-generic/getorder.h>
+#define AMODE31_SIZE (3 * PAGE_SIZE)
+
+#define KERNEL_IMAGE_SIZE (512 * 1024 * 1024)
+#define __START_KERNEL 0x100000
+#define __NO_KASLR_START_KERNEL CONFIG_KERNEL_IMAGE_BASE
+#define __NO_KASLR_END_KERNEL (__NO_KASLR_START_KERNEL + KERNEL_IMAGE_SIZE)
+
#endif /* _S390_PAGE_H */
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 60950e7a25..70b6ee557e 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -107,6 +107,12 @@ static inline int is_module_addr(void *addr)
return 1;
}
+#ifdef CONFIG_RANDOMIZE_BASE
+#define KASLR_LEN (1UL << 31)
+#else
+#define KASLR_LEN 0UL
+#endif
+
/*
* A 64 bit pagetable entry of S390 has following format:
* | PFRA |0IPC| OS |
@@ -262,12 +268,14 @@ static inline int is_module_addr(void *addr)
#define _REGION3_ENTRY (_REGION_ENTRY_TYPE_R3 | _REGION_ENTRY_LENGTH)
#define _REGION3_ENTRY_EMPTY (_REGION_ENTRY_TYPE_R3 | _REGION_ENTRY_INVALID)
+#define _REGION3_ENTRY_HARDWARE_BITS 0xfffffffffffff6ffUL
+#define _REGION3_ENTRY_HARDWARE_BITS_LARGE 0xffffffff8001073cUL
#define _REGION3_ENTRY_ORIGIN_LARGE ~0x7fffffffUL /* large page address */
#define _REGION3_ENTRY_DIRTY 0x2000 /* SW region dirty bit */
#define _REGION3_ENTRY_YOUNG 0x1000 /* SW region young bit */
#define _REGION3_ENTRY_LARGE 0x0400 /* RTTE-format control, large page */
-#define _REGION3_ENTRY_READ 0x0002 /* SW region read bit */
-#define _REGION3_ENTRY_WRITE 0x0001 /* SW region write bit */
+#define _REGION3_ENTRY_WRITE 0x0002 /* SW region write bit */
+#define _REGION3_ENTRY_READ 0x0001 /* SW region read bit */
#ifdef CONFIG_MEM_SOFT_DIRTY
#define _REGION3_ENTRY_SOFT_DIRTY 0x4000 /* SW region soft dirty bit */
@@ -278,9 +286,9 @@ static inline int is_module_addr(void *addr)
#define _REGION_ENTRY_BITS 0xfffffffffffff22fUL
/* Bits in the segment table entry */
-#define _SEGMENT_ENTRY_BITS 0xfffffffffffffe33UL
-#define _SEGMENT_ENTRY_HARDWARE_BITS 0xfffffffffffffe30UL
-#define _SEGMENT_ENTRY_HARDWARE_BITS_LARGE 0xfffffffffff00730UL
+#define _SEGMENT_ENTRY_BITS 0xfffffffffffffe3fUL
+#define _SEGMENT_ENTRY_HARDWARE_BITS 0xfffffffffffffe3cUL
+#define _SEGMENT_ENTRY_HARDWARE_BITS_LARGE 0xfffffffffff1073cUL
#define _SEGMENT_ENTRY_ORIGIN_LARGE ~0xfffffUL /* large page address */
#define _SEGMENT_ENTRY_ORIGIN ~0x7ffUL/* page table origin */
#define _SEGMENT_ENTRY_PROTECT 0x200 /* segment protection bit */
@@ -566,10 +574,20 @@ static inline pud_t set_pud_bit(pud_t pud, pgprot_t prot)
}
/*
- * In the case that a guest uses storage keys
- * faults should no longer be backed by zero pages
+ * As soon as the guest uses storage keys or enables PV, we deduplicate all
+ * mapped shared zeropages and prevent new shared zeropages from getting
+ * mapped.
*/
-#define mm_forbids_zeropage mm_has_pgste
+#define mm_forbids_zeropage mm_forbids_zeropage
+static inline int mm_forbids_zeropage(struct mm_struct *mm)
+{
+#ifdef CONFIG_PGSTE
+ if (!mm->context.allow_cow_sharing)
+ return 1;
+#endif
+ return 0;
+}
+
static inline int mm_uses_skeys(struct mm_struct *mm)
{
#ifdef CONFIG_PGSTE
@@ -1405,6 +1423,7 @@ static inline unsigned long pud_deref(pud_t pud)
return (unsigned long)__va(pud_val(pud) & origin_mask);
}
+#define pud_pfn pud_pfn
static inline unsigned long pud_pfn(pud_t pud)
{
return __pa(pud_deref(pud)) >> PAGE_SHIFT;
@@ -1768,8 +1787,10 @@ static inline pmd_t pmdp_huge_clear_flush(struct vm_area_struct *vma,
static inline pmd_t pmdp_invalidate(struct vm_area_struct *vma,
unsigned long addr, pmd_t *pmdp)
{
- pmd_t pmd = __pmd(pmd_val(*pmdp) | _SEGMENT_ENTRY_INVALID);
+ pmd_t pmd;
+ VM_WARN_ON_ONCE(!pmd_present(*pmdp));
+ pmd = __pmd(pmd_val(*pmdp) | _SEGMENT_ENTRY_INVALID);
return pmdp_xchg_direct(vma->vm_mm, addr, pmdp, pmd);
}
diff --git a/arch/s390/include/asm/physmem_info.h b/arch/s390/include/asm/physmem_info.h
index e747b067f8..f45cfc8bc2 100644
--- a/arch/s390/include/asm/physmem_info.h
+++ b/arch/s390/include/asm/physmem_info.h
@@ -22,7 +22,6 @@ enum reserved_range_type {
RR_DECOMPRESSOR,
RR_INITRD,
RR_VMLINUX,
- RR_RELOC,
RR_AMODE31,
RR_IPLREPORT,
RR_CERT_COMP_LIST,
@@ -170,4 +169,7 @@ static inline unsigned long get_physmem_reserved(enum reserved_range_type type,
return *size;
}
+#define AMODE31_START (physmem_info.reserved[RR_AMODE31].start)
+#define AMODE31_END (physmem_info.reserved[RR_AMODE31].end)
+
#endif
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index db9982f0e8..07ad5a1df8 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -40,6 +40,7 @@
#include <asm/setup.h>
#include <asm/runtime_instr.h>
#include <asm/irqflags.h>
+#include <asm/alternative.h>
typedef long (*sys_call_ptr_t)(struct pt_regs *regs);
@@ -92,12 +93,21 @@ static inline void get_cpu_id(struct cpuid *ptr)
asm volatile("stidp %0" : "=Q" (*ptr));
}
+static __always_inline unsigned long get_cpu_timer(void)
+{
+ unsigned long timer;
+
+ asm volatile("stpt %[timer]" : [timer] "=Q" (timer));
+ return timer;
+}
+
void s390_adjust_jiffies(void);
void s390_update_cpu_mhz(void);
void cpu_detect_mhz_feature(void);
extern const struct seq_operations cpuinfo_op;
extern void execve_tail(void);
+unsigned long vdso_text_size(void);
unsigned long vdso_size(void);
/*
@@ -304,8 +314,8 @@ static inline void __load_psw(psw_t psw)
*/
static __always_inline void __load_psw_mask(unsigned long mask)
{
+ psw_t psw __uninitialized;
unsigned long addr;
- psw_t psw;
psw.mask = mask;
@@ -393,6 +403,11 @@ static __always_inline bool regs_irqs_disabled(struct pt_regs *regs)
return arch_irqs_disabled_flags(regs->psw.mask);
}
+static __always_inline void bpon(void)
+{
+ asm volatile(ALTERNATIVE("nop", ".insn rrf,0xb2e80000,0,0,13,0", 82));
+}
+
#endif /* __ASSEMBLY__ */
#endif /* __ASM_S390_PROCESSOR_H */
diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h
index 03bcaa8eff..32f70873e2 100644
--- a/arch/s390/include/asm/setup.h
+++ b/arch/s390/include/asm/setup.h
@@ -127,20 +127,6 @@ extern void (*_machine_restart)(char *command);
extern void (*_machine_halt)(void);
extern void (*_machine_power_off)(void);
-extern unsigned long __kaslr_offset;
-static inline unsigned long kaslr_offset(void)
-{
- return __kaslr_offset;
-}
-
-extern int __kaslr_enabled;
-static inline int kaslr_enabled(void)
-{
- if (IS_ENABLED(CONFIG_RANDOMIZE_BASE))
- return __kaslr_enabled;
- return 0;
-}
-
struct oldmem_data {
unsigned long start;
unsigned long size;
diff --git a/arch/s390/include/asm/stacktrace.h b/arch/s390/include/asm/stacktrace.h
index 433fde85b1..85b6738b82 100644
--- a/arch/s390/include/asm/stacktrace.h
+++ b/arch/s390/include/asm/stacktrace.h
@@ -2,6 +2,7 @@
#ifndef _ASM_S390_STACKTRACE_H
#define _ASM_S390_STACKTRACE_H
+#include <linux/stacktrace.h>
#include <linux/uaccess.h>
#include <linux/ptrace.h>
@@ -12,6 +13,17 @@ struct stack_frame_user {
unsigned long empty2[4];
};
+struct stack_frame_vdso_wrapper {
+ struct stack_frame_user sf;
+ unsigned long return_address;
+};
+
+struct perf_callchain_entry_ctx;
+
+void arch_stack_walk_user_common(stack_trace_consume_fn consume_entry, void *cookie,
+ struct perf_callchain_entry_ctx *entry,
+ const struct pt_regs *regs, bool perf);
+
enum stack_type {
STACK_TYPE_UNKNOWN,
STACK_TYPE_TASK,
diff --git a/arch/s390/include/asm/vdso/gettimeofday.h b/arch/s390/include/asm/vdso/gettimeofday.h
index db84942eb7..7937765ccf 100644
--- a/arch/s390/include/asm/vdso/gettimeofday.h
+++ b/arch/s390/include/asm/vdso/gettimeofday.h
@@ -6,16 +6,13 @@
#define VDSO_HAS_CLOCK_GETRES 1
+#define VDSO_DELTA_NOMASK 1
+
#include <asm/syscall.h>
#include <asm/timex.h>
#include <asm/unistd.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)
{
diff --git a/arch/s390/include/asm/vtime.h b/arch/s390/include/asm/vtime.h
index fe17e448c0..561c91c1a8 100644
--- a/arch/s390/include/asm/vtime.h
+++ b/arch/s390/include/asm/vtime.h
@@ -2,8 +2,6 @@
#ifndef _S390_VTIME_H
#define _S390_VTIME_H
-#define __ARCH_HAS_VTIME_TASK_SWITCH
-
static inline void update_timer_sys(void)
{
S390_lowcore.system_timer += S390_lowcore.last_update_timer - S390_lowcore.exit_timer;
diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile
index fa029d0dc2..7241fa1947 100644
--- a/arch/s390/kernel/Makefile
+++ b/arch/s390/kernel/Makefile
@@ -11,6 +11,8 @@ CFLAGS_REMOVE_ftrace.o = $(CC_FLAGS_FTRACE)
# Do not trace early setup code
CFLAGS_REMOVE_early.o = $(CC_FLAGS_FTRACE)
CFLAGS_REMOVE_rethook.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_stacktrace.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_unwind_bc.o = $(CC_FLAGS_FTRACE)
endif
@@ -57,7 +59,6 @@ obj-$(CONFIG_COMPAT) += compat_linux.o compat_signal.o
obj-$(CONFIG_COMPAT) += $(compat-obj-y)
obj-$(CONFIG_EARLY_PRINTK) += early_printk.o
obj-$(CONFIG_KPROBES) += kprobes.o
-obj-$(CONFIG_KPROBES) += kprobes_insn_page.o
obj-$(CONFIG_KPROBES) += mcount.o
obj-$(CONFIG_RETHOOK) += rethook.o
obj-$(CONFIG_FUNCTION_TRACER) += ftrace.o
diff --git a/arch/s390/kernel/alternative.c b/arch/s390/kernel/alternative.c
index e7bca29f9c..1ac5f707dd 100644
--- a/arch/s390/kernel/alternative.c
+++ b/arch/s390/kernel/alternative.c
@@ -33,13 +33,6 @@ static void __init_or_module __apply_alternatives(struct alt_instr *start,
if (!__test_facility(a->facility, alt_stfle_fac_list))
continue;
-
- if (unlikely(a->instrlen % 2)) {
- WARN_ONCE(1, "cpu alternatives instructions length is "
- "odd, skipping patching\n");
- continue;
- }
-
s390_kernel_write(instr, replacement, a->instrlen);
}
}
diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c
index fa5f6885c7..f55979f64d 100644
--- a/arch/s390/kernel/asm-offsets.c
+++ b/arch/s390/kernel/asm-offsets.c
@@ -13,7 +13,6 @@
#include <linux/purgatory.h>
#include <linux/pgtable.h>
#include <linux/ftrace.h>
-#include <asm/idle.h>
#include <asm/gmap.h>
#include <asm/stacktrace.h>
@@ -66,10 +65,10 @@ int main(void)
OFFSET(__SF_SIE_CONTROL_PHYS, stack_frame, sie_control_block_phys);
DEFINE(STACK_FRAME_OVERHEAD, sizeof(struct stack_frame));
BLANK();
- /* idle data offsets */
- OFFSET(__CLOCK_IDLE_ENTER, s390_idle_data, clock_idle_enter);
- OFFSET(__TIMER_IDLE_ENTER, s390_idle_data, timer_idle_enter);
- OFFSET(__MT_CYCLES_ENTER, s390_idle_data, mt_cycles_enter);
+ OFFSET(__SFUSER_BACKCHAIN, stack_frame_user, back_chain);
+ DEFINE(STACK_FRAME_USER_OVERHEAD, sizeof(struct stack_frame_user));
+ OFFSET(__SFVDSO_RETURN_ADDRESS, stack_frame_vdso_wrapper, return_address);
+ DEFINE(STACK_FRAME_VDSO_OVERHEAD, sizeof(struct stack_frame_vdso_wrapper));
BLANK();
/* hardware defined lowcore locations 0x000 - 0x1ff */
OFFSET(__LC_EXT_PARAMS, lowcore, ext_params);
diff --git a/arch/s390/kernel/cert_store.c b/arch/s390/kernel/cert_store.c
index 554447768b..bf983513dd 100644
--- a/arch/s390/kernel/cert_store.c
+++ b/arch/s390/kernel/cert_store.c
@@ -21,6 +21,7 @@
#include <linux/seq_file.h>
#include <linux/slab.h>
#include <linux/sysfs.h>
+#include <linux/vmalloc.h>
#include <crypto/sha2.h>
#include <keys/user-type.h>
#include <asm/debug.h>
diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c
index d09ebb6f52..edae134161 100644
--- a/arch/s390/kernel/crash_dump.c
+++ b/arch/s390/kernel/crash_dump.c
@@ -451,7 +451,7 @@ static void *nt_final(void *ptr)
/*
* Initialize ELF header (new kernel)
*/
-static void *ehdr_init(Elf64_Ehdr *ehdr, int mem_chunk_cnt)
+static void *ehdr_init(Elf64_Ehdr *ehdr, int phdr_count)
{
memset(ehdr, 0, sizeof(*ehdr));
memcpy(ehdr->e_ident, ELFMAG, SELFMAG);
@@ -465,7 +465,8 @@ static void *ehdr_init(Elf64_Ehdr *ehdr, int mem_chunk_cnt)
ehdr->e_phoff = sizeof(Elf64_Ehdr);
ehdr->e_ehsize = sizeof(Elf64_Ehdr);
ehdr->e_phentsize = sizeof(Elf64_Phdr);
- ehdr->e_phnum = mem_chunk_cnt + 1;
+ /* Number of PT_LOAD program headers plus PT_NOTE program header */
+ ehdr->e_phnum = phdr_count + 1;
return ehdr + 1;
}
@@ -499,17 +500,20 @@ static int get_mem_chunk_cnt(void)
/*
* Initialize ELF loads (new kernel)
*/
-static void loads_init(Elf64_Phdr *phdr)
+static void loads_init(Elf64_Phdr *phdr, bool os_info_has_vm)
{
+ unsigned long old_identity_base = 0;
phys_addr_t start, end;
u64 idx;
+ if (os_info_has_vm)
+ old_identity_base = os_info_old_value(OS_INFO_IDENTITY_BASE);
for_each_physmem_range(idx, &oldmem_type, &start, &end) {
- phdr->p_filesz = end - start;
phdr->p_type = PT_LOAD;
+ phdr->p_vaddr = old_identity_base + start;
phdr->p_offset = start;
- phdr->p_vaddr = (unsigned long)__va(start);
phdr->p_paddr = start;
+ phdr->p_filesz = end - start;
phdr->p_memsz = end - start;
phdr->p_flags = PF_R | PF_W | PF_X;
phdr->p_align = PAGE_SIZE;
@@ -517,6 +521,30 @@ static void loads_init(Elf64_Phdr *phdr)
}
}
+static bool os_info_has_vm(void)
+{
+ return os_info_old_value(OS_INFO_KASLR_OFFSET);
+}
+
+/*
+ * Prepare PT_LOAD type program header for kernel image region
+ */
+static void text_init(Elf64_Phdr *phdr)
+{
+ unsigned long start_phys = os_info_old_value(OS_INFO_IMAGE_PHYS);
+ unsigned long start = os_info_old_value(OS_INFO_IMAGE_START);
+ unsigned long end = os_info_old_value(OS_INFO_IMAGE_END);
+
+ phdr->p_type = PT_LOAD;
+ phdr->p_vaddr = start;
+ phdr->p_filesz = end - start;
+ phdr->p_memsz = end - start;
+ phdr->p_offset = start_phys;
+ phdr->p_paddr = start_phys;
+ phdr->p_flags = PF_R | PF_W | PF_X;
+ phdr->p_align = PAGE_SIZE;
+}
+
/*
* Initialize notes (new kernel)
*/
@@ -542,7 +570,7 @@ static void *notes_init(Elf64_Phdr *phdr, void *ptr, u64 notes_offset)
return ptr;
}
-static size_t get_elfcorehdr_size(int mem_chunk_cnt)
+static size_t get_elfcorehdr_size(int phdr_count)
{
size_t size;
@@ -558,7 +586,7 @@ static size_t get_elfcorehdr_size(int mem_chunk_cnt)
/* nt_final */
size += sizeof(Elf64_Nhdr);
/* PT_LOADS */
- size += mem_chunk_cnt * sizeof(Elf64_Phdr);
+ size += phdr_count * sizeof(Elf64_Phdr);
return size;
}
@@ -568,9 +596,9 @@ static size_t get_elfcorehdr_size(int mem_chunk_cnt)
*/
int elfcorehdr_alloc(unsigned long long *addr, unsigned long long *size)
{
- Elf64_Phdr *phdr_notes, *phdr_loads;
+ Elf64_Phdr *phdr_notes, *phdr_loads, *phdr_text;
+ int mem_chunk_cnt, phdr_text_cnt;
size_t alloc_size;
- int mem_chunk_cnt;
void *ptr, *hdr;
u64 hdr_off;
@@ -589,12 +617,14 @@ int elfcorehdr_alloc(unsigned long long *addr, unsigned long long *size)
}
mem_chunk_cnt = get_mem_chunk_cnt();
+ phdr_text_cnt = os_info_has_vm() ? 1 : 0;
- alloc_size = get_elfcorehdr_size(mem_chunk_cnt);
+ alloc_size = get_elfcorehdr_size(mem_chunk_cnt + phdr_text_cnt);
hdr = kzalloc(alloc_size, GFP_KERNEL);
- /* Without elfcorehdr /proc/vmcore cannot be created. Thus creating
+ /*
+ * Without elfcorehdr /proc/vmcore cannot be created. Thus creating
* a dump with this crash kernel will fail. Panic now to allow other
* dump mechanisms to take over.
*/
@@ -602,18 +632,25 @@ int elfcorehdr_alloc(unsigned long long *addr, unsigned long long *size)
panic("s390 kdump allocating elfcorehdr failed");
/* Init elf header */
- ptr = ehdr_init(hdr, mem_chunk_cnt);
+ phdr_notes = ehdr_init(hdr, mem_chunk_cnt + phdr_text_cnt);
/* Init program headers */
- phdr_notes = ptr;
- ptr = PTR_ADD(ptr, sizeof(Elf64_Phdr));
- phdr_loads = ptr;
- ptr = PTR_ADD(ptr, sizeof(Elf64_Phdr) * mem_chunk_cnt);
+ if (phdr_text_cnt) {
+ phdr_text = phdr_notes + 1;
+ phdr_loads = phdr_text + 1;
+ } else {
+ phdr_loads = phdr_notes + 1;
+ }
+ ptr = PTR_ADD(phdr_loads, sizeof(Elf64_Phdr) * mem_chunk_cnt);
/* Init notes */
hdr_off = PTR_DIFF(ptr, hdr);
ptr = notes_init(phdr_notes, ptr, ((unsigned long) hdr) + hdr_off);
+ /* Init kernel text program header */
+ if (phdr_text_cnt)
+ text_init(phdr_text);
/* Init loads */
+ loads_init(phdr_loads, phdr_text_cnt);
+ /* Finalize program headers */
hdr_off = PTR_DIFF(ptr, hdr);
- loads_init(phdr_loads);
*addr = (unsigned long long) hdr;
*size = (unsigned long long) hdr_off;
BUG_ON(elfcorehdr_size > alloc_size);
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index 6a1e0fbbaa..60cf917a71 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -441,29 +441,6 @@ INT_HANDLER ext_int_handler,__LC_EXT_OLD_PSW,do_ext_irq
INT_HANDLER io_int_handler,__LC_IO_OLD_PSW,do_io_irq
/*
- * Load idle PSW.
- */
-SYM_FUNC_START(psw_idle)
- stg %r14,(__SF_GPRS+8*8)(%r15)
- stg %r3,__SF_EMPTY(%r15)
- larl %r1,psw_idle_exit
- stg %r1,__SF_EMPTY+8(%r15)
- larl %r1,smp_cpu_mtid
- llgf %r1,0(%r1)
- ltgr %r1,%r1
- jz .Lpsw_idle_stcctm
- .insn rsy,0xeb0000000017,%r1,5,__MT_CYCLES_ENTER(%r2)
-.Lpsw_idle_stcctm:
- oi __LC_CPU_FLAGS+7,_CIF_ENABLED_WAIT
- BPON
- stckf __CLOCK_IDLE_ENTER(%r2)
- stpt __TIMER_IDLE_ENTER(%r2)
- lpswe __SF_EMPTY(%r15)
-SYM_INNER_LABEL(psw_idle_exit, SYM_L_GLOBAL)
- BR_EX %r14
-SYM_FUNC_END(psw_idle)
-
-/*
* Machine check handler routines
*/
SYM_CODE_START(mcck_int_handler)
diff --git a/arch/s390/kernel/fpu.c b/arch/s390/kernel/fpu.c
index fa90bbdc5e..6f2e879202 100644
--- a/arch/s390/kernel/fpu.c
+++ b/arch/s390/kernel/fpu.c
@@ -113,7 +113,7 @@ void load_fpu_state(struct fpu *state, int flags)
int mask;
if (flags & KERNEL_FPC)
- fpu_lfpc(&state->fpc);
+ fpu_lfpc_safe(&state->fpc);
if (!cpu_has_vx()) {
if (flags & KERNEL_VXR_V0V7)
load_fp_regs_vx(state->vxrs);
diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c
index c46381ea04..ddf2ee47cb 100644
--- a/arch/s390/kernel/ftrace.c
+++ b/arch/s390/kernel/ftrace.c
@@ -7,13 +7,13 @@
* Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
*/
-#include <linux/moduleloader.h>
#include <linux/hardirq.h>
#include <linux/uaccess.h>
#include <linux/ftrace.h>
#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/kprobes.h>
+#include <linux/execmem.h>
#include <trace/syscall.h>
#include <asm/asm-offsets.h>
#include <asm/text-patching.h>
@@ -220,7 +220,7 @@ static int __init ftrace_plt_init(void)
{
const char *start, *end;
- ftrace_plt = module_alloc(PAGE_SIZE);
+ ftrace_plt = execmem_alloc(EXECMEM_FTRACE, PAGE_SIZE);
if (!ftrace_plt)
panic("cannot allocate ftrace plt\n");
@@ -296,6 +296,9 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
struct kprobe *p;
int bit;
+ if (unlikely(kprobe_ftrace_disabled))
+ return;
+
bit = ftrace_test_recursion_trylock(ip, parent_ip);
if (bit < 0)
return;
diff --git a/arch/s390/kernel/idle.c b/arch/s390/kernel/idle.c
index e7239aaf42..af9c97c0ad 100644
--- a/arch/s390/kernel/idle.c
+++ b/arch/s390/kernel/idle.c
@@ -57,9 +57,13 @@ void noinstr arch_cpu_idle(void)
psw_mask = PSW_KERNEL_BITS | PSW_MASK_WAIT |
PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK;
clear_cpu_flag(CIF_NOHZ_DELAY);
-
- /* psw_idle() returns with interrupts disabled. */
- psw_idle(idle, psw_mask);
+ set_cpu_flag(CIF_ENABLED_WAIT);
+ if (smp_cpu_mtid)
+ stcctm(MT_DIAG, smp_cpu_mtid, (u64 *)&idle->mt_cycles_enter);
+ idle->clock_idle_enter = get_tod_clock_fast();
+ idle->timer_idle_enter = get_cpu_timer();
+ bpon();
+ __load_psw_mask(psw_mask);
}
static ssize_t show_idle_count(struct device *dev,
diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c
index 1486350a41..3a7d6e1722 100644
--- a/arch/s390/kernel/ipl.c
+++ b/arch/s390/kernel/ipl.c
@@ -20,6 +20,7 @@
#include <linux/gfp.h>
#include <linux/crash_dump.h>
#include <linux/debug_locks.h>
+#include <linux/vmalloc.h>
#include <asm/asm-extable.h>
#include <asm/diag.h>
#include <asm/ipl.h>
@@ -266,7 +267,11 @@ static ssize_t sys_##_prefix##_##_name##_store(struct kobject *kobj, \
struct kobj_attribute *attr, \
const char *buf, size_t len) \
{ \
- strscpy(_value, buf, sizeof(_value)); \
+ if (len >= sizeof(_value)) \
+ return -E2BIG; \
+ len = strscpy(_value, buf, sizeof(_value)); \
+ if (len < 0) \
+ return len; \
strim(_value); \
return len; \
} \
@@ -275,6 +280,61 @@ static struct kobj_attribute sys_##_prefix##_##_name##_attr = \
sys_##_prefix##_##_name##_show, \
sys_##_prefix##_##_name##_store)
+#define IPL_ATTR_SCP_DATA_SHOW_FN(_prefix, _ipl_block) \
+static ssize_t sys_##_prefix##_scp_data_show(struct file *filp, \
+ struct kobject *kobj, \
+ struct bin_attribute *attr, \
+ char *buf, loff_t off, \
+ size_t count) \
+{ \
+ size_t size = _ipl_block.scp_data_len; \
+ void *scp_data = _ipl_block.scp_data; \
+ \
+ return memory_read_from_buffer(buf, count, &off, \
+ scp_data, size); \
+}
+
+#define IPL_ATTR_SCP_DATA_STORE_FN(_prefix, _ipl_block_hdr, _ipl_block, _ipl_bp_len, _ipl_bp0_len)\
+static ssize_t sys_##_prefix##_scp_data_store(struct file *filp, \
+ struct kobject *kobj, \
+ struct bin_attribute *attr, \
+ char *buf, loff_t off, \
+ size_t count) \
+{ \
+ size_t scpdata_len = count; \
+ size_t padding; \
+ \
+ if (off) \
+ return -EINVAL; \
+ \
+ memcpy(_ipl_block.scp_data, buf, count); \
+ if (scpdata_len % 8) { \
+ padding = 8 - (scpdata_len % 8); \
+ memset(_ipl_block.scp_data + scpdata_len, \
+ 0, padding); \
+ scpdata_len += padding; \
+ } \
+ \
+ _ipl_block_hdr.len = _ipl_bp_len + scpdata_len; \
+ _ipl_block.len = _ipl_bp0_len + scpdata_len; \
+ _ipl_block.scp_data_len = scpdata_len; \
+ \
+ return count; \
+}
+
+#define DEFINE_IPL_ATTR_SCP_DATA_RO(_prefix, _ipl_block, _size) \
+IPL_ATTR_SCP_DATA_SHOW_FN(_prefix, _ipl_block) \
+static struct bin_attribute sys_##_prefix##_scp_data_attr = \
+ __BIN_ATTR(scp_data, 0444, sys_##_prefix##_scp_data_show, \
+ NULL, _size)
+
+#define DEFINE_IPL_ATTR_SCP_DATA_RW(_prefix, _ipl_block_hdr, _ipl_block, _ipl_bp_len, _ipl_bp0_len, _size)\
+IPL_ATTR_SCP_DATA_SHOW_FN(_prefix, _ipl_block) \
+IPL_ATTR_SCP_DATA_STORE_FN(_prefix, _ipl_block_hdr, _ipl_block, _ipl_bp_len, _ipl_bp0_len)\
+static struct bin_attribute sys_##_prefix##_scp_data_attr = \
+ __BIN_ATTR(scp_data, 0644, sys_##_prefix##_scp_data_show, \
+ sys_##_prefix##_scp_data_store, _size)
+
/*
* ipl section
*/
@@ -373,71 +433,38 @@ static ssize_t sys_ipl_device_show(struct kobject *kobj,
static struct kobj_attribute sys_ipl_device_attr =
__ATTR(device, 0444, sys_ipl_device_show, NULL);
-static ssize_t ipl_parameter_read(struct file *filp, struct kobject *kobj,
- struct bin_attribute *attr, char *buf,
- loff_t off, size_t count)
+static ssize_t sys_ipl_parameter_read(struct file *filp, struct kobject *kobj,
+ struct bin_attribute *attr, char *buf,
+ loff_t off, size_t count)
{
return memory_read_from_buffer(buf, count, &off, &ipl_block,
ipl_block.hdr.len);
}
-static struct bin_attribute ipl_parameter_attr =
- __BIN_ATTR(binary_parameter, 0444, ipl_parameter_read, NULL,
+static struct bin_attribute sys_ipl_parameter_attr =
+ __BIN_ATTR(binary_parameter, 0444, sys_ipl_parameter_read, NULL,
PAGE_SIZE);
-static ssize_t ipl_scp_data_read(struct file *filp, struct kobject *kobj,
- struct bin_attribute *attr, char *buf,
- loff_t off, size_t count)
-{
- unsigned int size = ipl_block.fcp.scp_data_len;
- void *scp_data = &ipl_block.fcp.scp_data;
-
- return memory_read_from_buffer(buf, count, &off, scp_data, size);
-}
-
-static ssize_t ipl_nvme_scp_data_read(struct file *filp, struct kobject *kobj,
- struct bin_attribute *attr, char *buf,
- loff_t off, size_t count)
-{
- unsigned int size = ipl_block.nvme.scp_data_len;
- void *scp_data = &ipl_block.nvme.scp_data;
-
- return memory_read_from_buffer(buf, count, &off, scp_data, size);
-}
-
-static ssize_t ipl_eckd_scp_data_read(struct file *filp, struct kobject *kobj,
- struct bin_attribute *attr, char *buf,
- loff_t off, size_t count)
-{
- unsigned int size = ipl_block.eckd.scp_data_len;
- void *scp_data = &ipl_block.eckd.scp_data;
-
- return memory_read_from_buffer(buf, count, &off, scp_data, size);
-}
-
-static struct bin_attribute ipl_scp_data_attr =
- __BIN_ATTR(scp_data, 0444, ipl_scp_data_read, NULL, PAGE_SIZE);
-
-static struct bin_attribute ipl_nvme_scp_data_attr =
- __BIN_ATTR(scp_data, 0444, ipl_nvme_scp_data_read, NULL, PAGE_SIZE);
-
-static struct bin_attribute ipl_eckd_scp_data_attr =
- __BIN_ATTR(scp_data, 0444, ipl_eckd_scp_data_read, NULL, PAGE_SIZE);
+DEFINE_IPL_ATTR_SCP_DATA_RO(ipl_fcp, ipl_block.fcp, PAGE_SIZE);
static struct bin_attribute *ipl_fcp_bin_attrs[] = {
- &ipl_parameter_attr,
- &ipl_scp_data_attr,
+ &sys_ipl_parameter_attr,
+ &sys_ipl_fcp_scp_data_attr,
NULL,
};
+DEFINE_IPL_ATTR_SCP_DATA_RO(ipl_nvme, ipl_block.nvme, PAGE_SIZE);
+
static struct bin_attribute *ipl_nvme_bin_attrs[] = {
- &ipl_parameter_attr,
- &ipl_nvme_scp_data_attr,
+ &sys_ipl_parameter_attr,
+ &sys_ipl_nvme_scp_data_attr,
NULL,
};
+DEFINE_IPL_ATTR_SCP_DATA_RO(ipl_eckd, ipl_block.eckd, PAGE_SIZE);
+
static struct bin_attribute *ipl_eckd_bin_attrs[] = {
- &ipl_parameter_attr,
- &ipl_eckd_scp_data_attr,
+ &sys_ipl_parameter_attr,
+ &sys_ipl_eckd_scp_data_attr,
NULL,
};
@@ -776,44 +803,10 @@ static struct kobj_attribute sys_reipl_ccw_vmparm_attr =
/* FCP reipl device attributes */
-static ssize_t reipl_fcp_scpdata_read(struct file *filp, struct kobject *kobj,
- struct bin_attribute *attr,
- char *buf, loff_t off, size_t count)
-{
- size_t size = reipl_block_fcp->fcp.scp_data_len;
- void *scp_data = reipl_block_fcp->fcp.scp_data;
-
- return memory_read_from_buffer(buf, count, &off, scp_data, size);
-}
-
-static ssize_t reipl_fcp_scpdata_write(struct file *filp, struct kobject *kobj,
- struct bin_attribute *attr,
- char *buf, loff_t off, size_t count)
-{
- size_t scpdata_len = count;
- size_t padding;
-
-
- if (off)
- return -EINVAL;
-
- memcpy(reipl_block_fcp->fcp.scp_data, buf, count);
- if (scpdata_len % 8) {
- padding = 8 - (scpdata_len % 8);
- memset(reipl_block_fcp->fcp.scp_data + scpdata_len,
- 0, padding);
- scpdata_len += padding;
- }
-
- reipl_block_fcp->hdr.len = IPL_BP_FCP_LEN + scpdata_len;
- reipl_block_fcp->fcp.len = IPL_BP0_FCP_LEN + scpdata_len;
- reipl_block_fcp->fcp.scp_data_len = scpdata_len;
-
- return count;
-}
-static struct bin_attribute sys_reipl_fcp_scp_data_attr =
- __BIN_ATTR(scp_data, 0644, reipl_fcp_scpdata_read,
- reipl_fcp_scpdata_write, DIAG308_SCPDATA_SIZE);
+DEFINE_IPL_ATTR_SCP_DATA_RW(reipl_fcp, reipl_block_fcp->hdr,
+ reipl_block_fcp->fcp,
+ IPL_BP_FCP_LEN, IPL_BP0_FCP_LEN,
+ DIAG308_SCPDATA_SIZE);
static struct bin_attribute *reipl_fcp_bin_attrs[] = {
&sys_reipl_fcp_scp_data_attr,
@@ -934,44 +927,10 @@ static struct kobj_attribute sys_reipl_fcp_clear_attr =
/* NVME reipl device attributes */
-static ssize_t reipl_nvme_scpdata_read(struct file *filp, struct kobject *kobj,
- struct bin_attribute *attr,
- char *buf, loff_t off, size_t count)
-{
- size_t size = reipl_block_nvme->nvme.scp_data_len;
- void *scp_data = reipl_block_nvme->nvme.scp_data;
-
- return memory_read_from_buffer(buf, count, &off, scp_data, size);
-}
-
-static ssize_t reipl_nvme_scpdata_write(struct file *filp, struct kobject *kobj,
- struct bin_attribute *attr,
- char *buf, loff_t off, size_t count)
-{
- size_t scpdata_len = count;
- size_t padding;
-
- if (off)
- return -EINVAL;
-
- memcpy(reipl_block_nvme->nvme.scp_data, buf, count);
- if (scpdata_len % 8) {
- padding = 8 - (scpdata_len % 8);
- memset(reipl_block_nvme->nvme.scp_data + scpdata_len,
- 0, padding);
- scpdata_len += padding;
- }
-
- reipl_block_nvme->hdr.len = IPL_BP_FCP_LEN + scpdata_len;
- reipl_block_nvme->nvme.len = IPL_BP0_FCP_LEN + scpdata_len;
- reipl_block_nvme->nvme.scp_data_len = scpdata_len;
-
- return count;
-}
-
-static struct bin_attribute sys_reipl_nvme_scp_data_attr =
- __BIN_ATTR(scp_data, 0644, reipl_nvme_scpdata_read,
- reipl_nvme_scpdata_write, DIAG308_SCPDATA_SIZE);
+DEFINE_IPL_ATTR_SCP_DATA_RW(reipl_nvme, reipl_block_nvme->hdr,
+ reipl_block_nvme->nvme,
+ IPL_BP_NVME_LEN, IPL_BP0_NVME_LEN,
+ DIAG308_SCPDATA_SIZE);
static struct bin_attribute *reipl_nvme_bin_attrs[] = {
&sys_reipl_nvme_scp_data_attr,
@@ -1067,44 +1026,10 @@ static struct attribute_group reipl_ccw_attr_group_lpar = {
/* ECKD reipl device attributes */
-static ssize_t reipl_eckd_scpdata_read(struct file *filp, struct kobject *kobj,
- struct bin_attribute *attr,
- char *buf, loff_t off, size_t count)
-{
- size_t size = reipl_block_eckd->eckd.scp_data_len;
- void *scp_data = reipl_block_eckd->eckd.scp_data;
-
- return memory_read_from_buffer(buf, count, &off, scp_data, size);
-}
-
-static ssize_t reipl_eckd_scpdata_write(struct file *filp, struct kobject *kobj,
- struct bin_attribute *attr,
- char *buf, loff_t off, size_t count)
-{
- size_t scpdata_len = count;
- size_t padding;
-
- if (off)
- return -EINVAL;
-
- memcpy(reipl_block_eckd->eckd.scp_data, buf, count);
- if (scpdata_len % 8) {
- padding = 8 - (scpdata_len % 8);
- memset(reipl_block_eckd->eckd.scp_data + scpdata_len,
- 0, padding);
- scpdata_len += padding;
- }
-
- reipl_block_eckd->hdr.len = IPL_BP_ECKD_LEN + scpdata_len;
- reipl_block_eckd->eckd.len = IPL_BP0_ECKD_LEN + scpdata_len;
- reipl_block_eckd->eckd.scp_data_len = scpdata_len;
-
- return count;
-}
-
-static struct bin_attribute sys_reipl_eckd_scp_data_attr =
- __BIN_ATTR(scp_data, 0644, reipl_eckd_scpdata_read,
- reipl_eckd_scpdata_write, DIAG308_SCPDATA_SIZE);
+DEFINE_IPL_ATTR_SCP_DATA_RW(reipl_eckd, reipl_block_eckd->hdr,
+ reipl_block_eckd->eckd,
+ IPL_BP_ECKD_LEN, IPL_BP0_ECKD_LEN,
+ DIAG308_SCPDATA_SIZE);
static struct bin_attribute *reipl_eckd_bin_attrs[] = {
&sys_reipl_eckd_scp_data_attr,
@@ -1209,8 +1134,8 @@ static struct attribute_group reipl_nss_attr_group = {
void set_os_info_reipl_block(void)
{
- os_info_entry_add(OS_INFO_REIPL_BLOCK, reipl_block_actual,
- reipl_block_actual->hdr.len);
+ os_info_entry_add_data(OS_INFO_REIPL_BLOCK, reipl_block_actual,
+ reipl_block_actual->hdr.len);
}
/* reipl type */
@@ -1648,6 +1573,11 @@ DEFINE_IPL_ATTR_RW(dump_fcp, br_lba, "%lld\n", "%lld\n",
DEFINE_IPL_ATTR_RW(dump_fcp, device, "0.0.%04llx\n", "0.0.%llx\n",
dump_block_fcp->fcp.devno);
+DEFINE_IPL_ATTR_SCP_DATA_RW(dump_fcp, dump_block_fcp->hdr,
+ dump_block_fcp->fcp,
+ IPL_BP_FCP_LEN, IPL_BP0_FCP_LEN,
+ DIAG308_SCPDATA_SIZE);
+
static struct attribute *dump_fcp_attrs[] = {
&sys_dump_fcp_device_attr.attr,
&sys_dump_fcp_wwpn_attr.attr,
@@ -1657,9 +1587,15 @@ static struct attribute *dump_fcp_attrs[] = {
NULL,
};
+static struct bin_attribute *dump_fcp_bin_attrs[] = {
+ &sys_dump_fcp_scp_data_attr,
+ NULL,
+};
+
static struct attribute_group dump_fcp_attr_group = {
.name = IPL_FCP_STR,
.attrs = dump_fcp_attrs,
+ .bin_attrs = dump_fcp_bin_attrs,
};
/* NVME dump device attributes */
@@ -1672,6 +1608,11 @@ DEFINE_IPL_ATTR_RW(dump_nvme, bootprog, "%lld\n", "%llx\n",
DEFINE_IPL_ATTR_RW(dump_nvme, br_lba, "%lld\n", "%llx\n",
dump_block_nvme->nvme.br_lba);
+DEFINE_IPL_ATTR_SCP_DATA_RW(dump_nvme, dump_block_nvme->hdr,
+ dump_block_nvme->nvme,
+ IPL_BP_NVME_LEN, IPL_BP0_NVME_LEN,
+ DIAG308_SCPDATA_SIZE);
+
static struct attribute *dump_nvme_attrs[] = {
&sys_dump_nvme_fid_attr.attr,
&sys_dump_nvme_nsid_attr.attr,
@@ -1680,9 +1621,15 @@ static struct attribute *dump_nvme_attrs[] = {
NULL,
};
+static struct bin_attribute *dump_nvme_bin_attrs[] = {
+ &sys_dump_nvme_scp_data_attr,
+ NULL,
+};
+
static struct attribute_group dump_nvme_attr_group = {
.name = IPL_NVME_STR,
.attrs = dump_nvme_attrs,
+ .bin_attrs = dump_nvme_bin_attrs,
};
/* ECKD dump device attributes */
@@ -1696,6 +1643,11 @@ IPL_ATTR_BR_CHR_STORE_FN(dump, dump_block_eckd->eckd);
static struct kobj_attribute sys_dump_eckd_br_chr_attr =
__ATTR(br_chr, 0644, eckd_dump_br_chr_show, eckd_dump_br_chr_store);
+DEFINE_IPL_ATTR_SCP_DATA_RW(dump_eckd, dump_block_eckd->hdr,
+ dump_block_eckd->eckd,
+ IPL_BP_ECKD_LEN, IPL_BP0_ECKD_LEN,
+ DIAG308_SCPDATA_SIZE);
+
static struct attribute *dump_eckd_attrs[] = {
&sys_dump_eckd_device_attr.attr,
&sys_dump_eckd_bootprog_attr.attr,
@@ -1703,9 +1655,15 @@ static struct attribute *dump_eckd_attrs[] = {
NULL,
};
+static struct bin_attribute *dump_eckd_bin_attrs[] = {
+ &sys_dump_eckd_scp_data_attr,
+ NULL,
+};
+
static struct attribute_group dump_eckd_attr_group = {
.name = IPL_ECKD_STR,
.attrs = dump_eckd_attrs,
+ .bin_attrs = dump_eckd_bin_attrs,
};
/* CCW dump device attributes */
@@ -1858,9 +1816,9 @@ static int __init dump_nvme_init(void)
}
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_block_nvme->nvme.len = IPL_BP0_NVME_LEN;
+ dump_block_nvme->nvme.pbt = IPL_PBT_NVME;
+ dump_block_nvme->nvme.opt = IPL_PB0_NVME_OPT_DUMP;
dump_capabilities |= DUMP_TYPE_NVME;
return 0;
}
@@ -1940,7 +1898,7 @@ static void dump_reipl_run(struct shutdown_trigger *trigger)
reipl_type == IPL_TYPE_NSS ||
reipl_type == IPL_TYPE_UNKNOWN)
os_info_flags |= OS_INFO_FLAG_REIPL_CLEAR;
- os_info_entry_add(OS_INFO_FLAGS_ENTRY, &os_info_flags, sizeof(os_info_flags));
+ os_info_entry_add_data(OS_INFO_FLAGS_ENTRY, &os_info_flags, sizeof(os_info_flags));
csum = (__force unsigned int)cksm(reipl_block_actual, reipl_block_actual->hdr.len, 0);
abs_lc = get_abs_lowcore();
abs_lc->ipib = __pa(reipl_block_actual);
@@ -1958,11 +1916,13 @@ static struct shutdown_action __refdata dump_reipl_action = {
* vmcmd shutdown action: Trigger vm command on shutdown.
*/
-static char vmcmd_on_reboot[128];
-static char vmcmd_on_panic[128];
-static char vmcmd_on_halt[128];
-static char vmcmd_on_poff[128];
-static char vmcmd_on_restart[128];
+#define VMCMD_MAX_SIZE 240
+
+static char vmcmd_on_reboot[VMCMD_MAX_SIZE + 1];
+static char vmcmd_on_panic[VMCMD_MAX_SIZE + 1];
+static char vmcmd_on_halt[VMCMD_MAX_SIZE + 1];
+static char vmcmd_on_poff[VMCMD_MAX_SIZE + 1];
+static char vmcmd_on_restart[VMCMD_MAX_SIZE + 1];
DEFINE_IPL_ATTR_STR_RW(vmcmd, on_reboot, "%s\n", "%s\n", vmcmd_on_reboot);
DEFINE_IPL_ATTR_STR_RW(vmcmd, on_panic, "%s\n", "%s\n", vmcmd_on_panic);
@@ -2288,8 +2248,8 @@ static int __init vmcmd_on_reboot_setup(char *str)
{
if (!MACHINE_IS_VM)
return 1;
- strncpy_skip_quote(vmcmd_on_reboot, str, 127);
- vmcmd_on_reboot[127] = 0;
+ strncpy_skip_quote(vmcmd_on_reboot, str, VMCMD_MAX_SIZE);
+ vmcmd_on_reboot[VMCMD_MAX_SIZE] = 0;
on_reboot_trigger.action = &vmcmd_action;
return 1;
}
@@ -2299,8 +2259,8 @@ static int __init vmcmd_on_panic_setup(char *str)
{
if (!MACHINE_IS_VM)
return 1;
- strncpy_skip_quote(vmcmd_on_panic, str, 127);
- vmcmd_on_panic[127] = 0;
+ strncpy_skip_quote(vmcmd_on_panic, str, VMCMD_MAX_SIZE);
+ vmcmd_on_panic[VMCMD_MAX_SIZE] = 0;
on_panic_trigger.action = &vmcmd_action;
return 1;
}
@@ -2310,8 +2270,8 @@ static int __init vmcmd_on_halt_setup(char *str)
{
if (!MACHINE_IS_VM)
return 1;
- strncpy_skip_quote(vmcmd_on_halt, str, 127);
- vmcmd_on_halt[127] = 0;
+ strncpy_skip_quote(vmcmd_on_halt, str, VMCMD_MAX_SIZE);
+ vmcmd_on_halt[VMCMD_MAX_SIZE] = 0;
on_halt_trigger.action = &vmcmd_action;
return 1;
}
@@ -2321,8 +2281,8 @@ static int __init vmcmd_on_poff_setup(char *str)
{
if (!MACHINE_IS_VM)
return 1;
- strncpy_skip_quote(vmcmd_on_poff, str, 127);
- vmcmd_on_poff[127] = 0;
+ strncpy_skip_quote(vmcmd_on_poff, str, VMCMD_MAX_SIZE);
+ vmcmd_on_poff[VMCMD_MAX_SIZE] = 0;
on_poff_trigger.action = &vmcmd_action;
return 1;
}
diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c
index 6f71b0ce10..9acc6630ab 100644
--- a/arch/s390/kernel/irq.c
+++ b/arch/s390/kernel/irq.c
@@ -29,6 +29,7 @@
#include <asm/hw_irq.h>
#include <asm/stacktrace.h>
#include <asm/softirq_stack.h>
+#include <asm/vtime.h>
#include "entry.h"
DEFINE_PER_CPU_SHARED_ALIGNED(struct irq_stat, irq_stat);
@@ -150,6 +151,7 @@ void noinstr do_io_irq(struct pt_regs *regs)
if (from_idle)
account_idle_time_irq();
+ set_cpu_flag(CIF_NOHZ_DELAY);
do {
regs->tpi_info = S390_lowcore.tpi_info;
if (S390_lowcore.tpi_info.adapter_IO)
diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c
index f0cf20d4b3..05c83505e9 100644
--- a/arch/s390/kernel/kprobes.c
+++ b/arch/s390/kernel/kprobes.c
@@ -9,7 +9,6 @@
#define pr_fmt(fmt) "kprobes: " fmt
-#include <linux/moduleloader.h>
#include <linux/kprobes.h>
#include <linux/ptrace.h>
#include <linux/preempt.h>
@@ -21,10 +20,10 @@
#include <linux/slab.h>
#include <linux/hardirq.h>
#include <linux/ftrace.h>
+#include <linux/execmem.h>
#include <asm/set_memory.h>
#include <asm/sections.h>
#include <asm/dis.h>
-#include "kprobes.h"
#include "entry.h"
DEFINE_PER_CPU(struct kprobe *, current_kprobe);
@@ -32,39 +31,17 @@ DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
struct kretprobe_blackpoint kretprobe_blacklist[] = { };
-static int insn_page_in_use;
-
void *alloc_insn_page(void)
{
void *page;
- page = module_alloc(PAGE_SIZE);
+ page = execmem_alloc(EXECMEM_KPROBES, PAGE_SIZE);
if (!page)
return NULL;
set_memory_rox((unsigned long)page, 1);
return page;
}
-static void *alloc_s390_insn_page(void)
-{
- if (xchg(&insn_page_in_use, 1) == 1)
- return NULL;
- return &kprobes_insn_page;
-}
-
-static void free_s390_insn_page(void *page)
-{
- xchg(&insn_page_in_use, 0);
-}
-
-struct kprobe_insn_cache kprobe_s390_insn_slots = {
- .mutex = __MUTEX_INITIALIZER(kprobe_s390_insn_slots.mutex),
- .alloc = alloc_s390_insn_page,
- .free = free_s390_insn_page,
- .pages = LIST_HEAD_INIT(kprobe_s390_insn_slots.pages),
- .insn_size = MAX_INSN_SIZE,
-};
-
static void copy_instruction(struct kprobe *p)
{
kprobe_opcode_t insn[MAX_INSN_SIZE];
@@ -78,10 +55,10 @@ static void copy_instruction(struct kprobe *p)
if (probe_is_insn_relative_long(&insn[0])) {
/*
* For pc-relative instructions in RIL-b or RIL-c format patch
- * the RI2 displacement field. We have already made sure that
- * the insn slot for the patched instruction is within the same
- * 2GB area as the original instruction (either kernel image or
- * module area). Therefore the new displacement will always fit.
+ * the RI2 displacement field. The insn slot for the to be
+ * patched instruction is within the same 4GB area like the
+ * original instruction. Therefore the new displacement will
+ * always fit.
*/
disp = *(s32 *)&insn[1];
addr = (u64)(unsigned long)p->addr;
@@ -93,34 +70,6 @@ static void copy_instruction(struct kprobe *p)
}
NOKPROBE_SYMBOL(copy_instruction);
-static int s390_get_insn_slot(struct kprobe *p)
-{
- /*
- * Get an insn slot that is within the same 2GB area like the original
- * instruction. That way instructions with a 32bit signed displacement
- * field can be patched and executed within the insn slot.
- */
- p->ainsn.insn = NULL;
- if (is_kernel((unsigned long)p->addr))
- p->ainsn.insn = get_s390_insn_slot();
- else if (is_module_addr(p->addr))
- p->ainsn.insn = get_insn_slot();
- return p->ainsn.insn ? 0 : -ENOMEM;
-}
-NOKPROBE_SYMBOL(s390_get_insn_slot);
-
-static void s390_free_insn_slot(struct kprobe *p)
-{
- if (!p->ainsn.insn)
- return;
- if (is_kernel((unsigned long)p->addr))
- free_s390_insn_slot(p->ainsn.insn, 0);
- else
- free_insn_slot(p->ainsn.insn, 0);
- p->ainsn.insn = NULL;
-}
-NOKPROBE_SYMBOL(s390_free_insn_slot);
-
/* Check if paddr is at an instruction boundary */
static bool can_probe(unsigned long paddr)
{
@@ -174,7 +123,8 @@ int arch_prepare_kprobe(struct kprobe *p)
/* Make sure the probe isn't going on a difficult instruction */
if (probe_is_prohibited_opcode(p->addr))
return -EINVAL;
- if (s390_get_insn_slot(p))
+ p->ainsn.insn = get_insn_slot();
+ if (!p->ainsn.insn)
return -ENOMEM;
copy_instruction(p);
return 0;
@@ -216,7 +166,10 @@ NOKPROBE_SYMBOL(arch_disarm_kprobe);
void arch_remove_kprobe(struct kprobe *p)
{
- s390_free_insn_slot(p);
+ if (!p->ainsn.insn)
+ return;
+ free_insn_slot(p->ainsn.insn, 0);
+ p->ainsn.insn = NULL;
}
NOKPROBE_SYMBOL(arch_remove_kprobe);
diff --git a/arch/s390/kernel/kprobes.h b/arch/s390/kernel/kprobes.h
deleted file mode 100644
index dc3ed5098e..0000000000
--- a/arch/s390/kernel/kprobes.h
+++ /dev/null
@@ -1,9 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0+ */
-#ifndef _ARCH_S390_KPROBES_H
-#define _ARCH_S390_KPROBES_H
-
-#include <linux/kprobes.h>
-
-DEFINE_INSN_CACHE_OPS(s390_insn);
-
-#endif
diff --git a/arch/s390/kernel/kprobes_insn_page.S b/arch/s390/kernel/kprobes_insn_page.S
deleted file mode 100644
index 0fe4d725e9..0000000000
--- a/arch/s390/kernel/kprobes_insn_page.S
+++ /dev/null
@@ -1,22 +0,0 @@
-/* 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"
- .balign 4096
-SYM_CODE_START(kprobes_insn_page)
- .rept 2048
- .word 0x07fe
- .endr
-SYM_CODE_END(kprobes_insn_page)
- .previous
diff --git a/arch/s390/kernel/module.c b/arch/s390/kernel/module.c
index 42215f9404..91e207b503 100644
--- a/arch/s390/kernel/module.c
+++ b/arch/s390/kernel/module.c
@@ -21,6 +21,7 @@
#include <linux/moduleloader.h>
#include <linux/bug.h>
#include <linux/memory.h>
+#include <linux/execmem.h>
#include <asm/alternative.h>
#include <asm/nospec-branch.h>
#include <asm/facility.h>
@@ -36,47 +37,10 @@
#define PLT_ENTRY_SIZE 22
-static unsigned long get_module_load_offset(void)
-{
- static DEFINE_MUTEX(module_kaslr_mutex);
- static unsigned long module_load_offset;
-
- if (!kaslr_enabled())
- return 0;
- /*
- * Calculate the module_load_offset the first time this code
- * is called. Once calculated it stays the same until reboot.
- */
- mutex_lock(&module_kaslr_mutex);
- if (!module_load_offset)
- module_load_offset = get_random_u32_inclusive(1, 1024) * PAGE_SIZE;
- mutex_unlock(&module_kaslr_mutex);
- return module_load_offset;
-}
-
-void *module_alloc(unsigned long size)
-{
- gfp_t gfp_mask = GFP_KERNEL;
- void *p;
-
- if (PAGE_ALIGN(size) > MODULES_LEN)
- return NULL;
- p = __vmalloc_node_range(size, MODULE_ALIGN,
- MODULES_VADDR + get_module_load_offset(),
- MODULES_END, gfp_mask, PAGE_KERNEL,
- VM_FLUSH_RESET_PERMS | VM_DEFER_KMEMLEAK,
- NUMA_NO_NODE, __builtin_return_address(0));
- if (p && (kasan_alloc_module_shadow(p, size, gfp_mask) < 0)) {
- vfree(p);
- return NULL;
- }
- return p;
-}
-
#ifdef CONFIG_FUNCTION_TRACER
void module_arch_cleanup(struct module *mod)
{
- module_memfree(mod->arch.trampolines_start);
+ execmem_free(mod->arch.trampolines_start);
}
#endif
@@ -510,7 +474,7 @@ static int module_alloc_ftrace_hotpatch_trampolines(struct module *me,
size = FTRACE_HOTPATCH_TRAMPOLINES_SIZE(s->sh_size);
numpages = DIV_ROUND_UP(size, PAGE_SIZE);
- start = module_alloc(numpages * PAGE_SIZE);
+ start = execmem_alloc(EXECMEM_FTRACE, numpages * PAGE_SIZE);
if (!start)
return -ENOMEM;
set_memory_rox((unsigned long)start, numpages);
diff --git a/arch/s390/kernel/nmi.c b/arch/s390/kernel/nmi.c
index c77382a673..230d010bac 100644
--- a/arch/s390/kernel/nmi.c
+++ b/arch/s390/kernel/nmi.c
@@ -31,6 +31,7 @@
#include <asm/crw.h>
#include <asm/asm-offsets.h>
#include <asm/pai.h>
+#include <asm/vtime.h>
struct mcck_struct {
unsigned int kill_task : 1;
diff --git a/arch/s390/kernel/nospec-branch.c b/arch/s390/kernel/nospec-branch.c
index d1b16d83e4..9b8c24ebb0 100644
--- a/arch/s390/kernel/nospec-branch.c
+++ b/arch/s390/kernel/nospec-branch.c
@@ -114,10 +114,10 @@ static void __init_or_module __nospec_revert(s32 *start, s32 *end)
type = BRASL_EXPOLINE; /* brasl instruction */
else
continue;
- thunk = instr + (*(int *)(instr + 2)) * 2;
+ thunk = instr + (long)(*(int *)(instr + 2)) * 2;
if (thunk[0] == 0xc6 && thunk[1] == 0x00)
/* exrl %r0,<target-br> */
- br = thunk + (*(int *)(thunk + 2)) * 2;
+ br = thunk + (long)(*(int *)(thunk + 2)) * 2;
else
continue;
if (br[0] != 0x07 || (br[1] & 0xf0) != 0xf0)
diff --git a/arch/s390/kernel/os_info.c b/arch/s390/kernel/os_info.c
index a801e6bd53..b695f980bb 100644
--- a/arch/s390/kernel/os_info.c
+++ b/arch/s390/kernel/os_info.c
@@ -15,8 +15,10 @@
#include <asm/checksum.h>
#include <asm/abs_lowcore.h>
#include <asm/os_info.h>
+#include <asm/physmem_info.h>
#include <asm/maccess.h>
#include <asm/asm-offsets.h>
+#include <asm/ipl.h>
/*
* OS info structure has to be page aligned
@@ -43,9 +45,9 @@ void os_info_crashkernel_add(unsigned long base, unsigned long size)
}
/*
- * Add OS info entry and update checksum
+ * Add OS info data entry and update checksum
*/
-void os_info_entry_add(int nr, void *ptr, u64 size)
+void os_info_entry_add_data(int nr, void *ptr, u64 size)
{
os_info.entry[nr].addr = __pa(ptr);
os_info.entry[nr].size = size;
@@ -54,15 +56,36 @@ void os_info_entry_add(int nr, void *ptr, u64 size)
}
/*
+ * Add OS info value entry and update checksum
+ */
+void os_info_entry_add_val(int nr, u64 value)
+{
+ os_info.entry[nr].val = value;
+ os_info.entry[nr].size = 0;
+ os_info.entry[nr].csum = 0;
+ os_info.csum = os_info_csum(&os_info);
+}
+
+/*
* Initialize OS info structure and set lowcore pointer
*/
void __init os_info_init(void)
{
struct lowcore *abs_lc;
+ BUILD_BUG_ON(sizeof(struct os_info) != PAGE_SIZE);
os_info.version_major = OS_INFO_VERSION_MAJOR;
os_info.version_minor = OS_INFO_VERSION_MINOR;
os_info.magic = OS_INFO_MAGIC;
+ os_info_entry_add_val(OS_INFO_IDENTITY_BASE, __identity_base);
+ os_info_entry_add_val(OS_INFO_KASLR_OFFSET, kaslr_offset());
+ os_info_entry_add_val(OS_INFO_KASLR_OFF_PHYS, __kaslr_offset_phys);
+ os_info_entry_add_val(OS_INFO_VMEMMAP, (unsigned long)vmemmap);
+ os_info_entry_add_val(OS_INFO_AMODE31_START, AMODE31_START);
+ os_info_entry_add_val(OS_INFO_AMODE31_END, AMODE31_END);
+ os_info_entry_add_val(OS_INFO_IMAGE_START, (unsigned long)_stext);
+ os_info_entry_add_val(OS_INFO_IMAGE_END, (unsigned long)_end);
+ os_info_entry_add_val(OS_INFO_IMAGE_PHYS, __pa_symbol(_stext));
os_info.csum = os_info_csum(&os_info);
abs_lc = get_abs_lowcore();
abs_lc->os_info = __pa(&os_info);
@@ -125,7 +148,7 @@ static void os_info_old_init(void)
if (os_info_init)
return;
- if (!oldmem_data.start)
+ if (!oldmem_data.start && !is_ipl_type_dump())
goto fail;
if (copy_oldmem_kernel(&addr, __LC_OS_INFO, sizeof(addr)))
goto fail;
diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c
index 41ed6e0f0a..6968be98af 100644
--- a/arch/s390/kernel/perf_cpum_cf.c
+++ b/arch/s390/kernel/perf_cpum_cf.c
@@ -428,7 +428,7 @@ static void cpum_cf_make_setsize(enum cpumf_ctr_set ctrset)
case CPUMF_CTR_SET_CRYPTO:
if (cpumf_ctr_info.csvn >= 1 && cpumf_ctr_info.csvn <= 5)
ctrset_size = 16;
- else if (cpumf_ctr_info.csvn == 6 || cpumf_ctr_info.csvn == 7)
+ else if (cpumf_ctr_info.csvn >= 6)
ctrset_size = 20;
break;
case CPUMF_CTR_SET_EXT:
@@ -556,25 +556,31 @@ static int cfdiag_diffctr(struct cpu_cf_events *cpuhw, unsigned long auth)
struct cf_trailer_entry *trailer_start, *trailer_stop;
struct cf_ctrset_entry *ctrstart, *ctrstop;
size_t offset = 0;
+ int i;
- auth &= (1 << CPUMF_LCCTL_ENABLE_SHIFT) - 1;
- do {
+ for (i = CPUMF_CTR_SET_BASIC; i < CPUMF_CTR_SET_MAX; ++i) {
ctrstart = (struct cf_ctrset_entry *)(cpuhw->start + offset);
ctrstop = (struct cf_ctrset_entry *)(cpuhw->stop + offset);
+ /* Counter set not authorized */
+ if (!(auth & cpumf_ctr_ctl[i]))
+ continue;
+ /* Counter set size zero was not saved */
+ if (!cpum_cf_read_setsize(i))
+ continue;
+
if (memcmp(ctrstop, ctrstart, sizeof(*ctrstop))) {
pr_err_once("cpum_cf_diag counter set compare error "
"in set %i\n", ctrstart->set);
return 0;
}
- auth &= ~cpumf_ctr_ctl[ctrstart->set];
if (ctrstart->def == CF_DIAG_CTRSET_DEF) {
cfdiag_diffctrset((u64 *)(ctrstart + 1),
(u64 *)(ctrstop + 1), ctrstart->ctr);
offset += ctrstart->ctr * sizeof(u64) +
sizeof(*ctrstart);
}
- } while (ctrstart->def && auth);
+ }
/* Save time_stamp from start of event in stop's trailer */
trailer_start = (struct cf_trailer_entry *)(cpuhw->start + offset);
diff --git a/arch/s390/kernel/perf_cpum_cf_events.c b/arch/s390/kernel/perf_cpum_cf_events.c
index 0d64aafd15..e4a6bfc910 100644
--- a/arch/s390/kernel/perf_cpum_cf_events.c
+++ b/arch/s390/kernel/perf_cpum_cf_events.c
@@ -855,16 +855,11 @@ __init const struct attribute_group **cpumf_cf_event_group(void)
}
/* Determine version specific crypto set */
- switch (ci.csvn) {
- case 1 ... 5:
+ csvn = none;
+ if (ci.csvn >= 1 && ci.csvn <= 5)
csvn = cpumcf_svn_12345_pmu_event_attr;
- break;
- case 6 ... 7:
+ else if (ci.csvn >= 6)
csvn = cpumcf_svn_67_pmu_event_attr;
- break;
- default:
- csvn = none;
- }
/* Determine model-specific counter set(s) */
get_cpu_id(&cpu_id);
diff --git a/arch/s390/kernel/perf_event.c b/arch/s390/kernel/perf_event.c
index dfa77da2fd..5fff629b1a 100644
--- a/arch/s390/kernel/perf_event.c
+++ b/arch/s390/kernel/perf_event.c
@@ -218,39 +218,7 @@ void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
void perf_callchain_user(struct perf_callchain_entry_ctx *entry,
struct pt_regs *regs)
{
- struct stack_frame_user __user *sf;
- unsigned long ip, sp;
- bool first = true;
-
- if (is_compat_task())
- return;
- perf_callchain_store(entry, instruction_pointer(regs));
- sf = (void __user *)user_stack_pointer(regs);
- pagefault_disable();
- while (entry->nr < entry->max_stack) {
- if (__get_user(sp, &sf->back_chain))
- break;
- if (__get_user(ip, &sf->gprs[8]))
- break;
- if (ip & 0x1) {
- /*
- * If the instruction address is invalid, and this
- * is the first stack frame, assume r14 has not
- * been written to the stack yet. Otherwise exit.
- */
- if (first && !(regs->gprs[14] & 0x1))
- ip = regs->gprs[14];
- else
- break;
- }
- perf_callchain_store(entry, ip);
- /* Sanity check: ABI requires SP to be aligned 8 bytes. */
- if (!sp || sp & 0x7)
- break;
- sf = (void __user *)sp;
- first = false;
- }
- pagefault_enable();
+ arch_stack_walk_user_common(NULL, NULL, entry, regs, true);
}
/* Perf definitions for PMU event attributes in sysfs */
diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
index dd456b4758..d8740631df 100644
--- a/arch/s390/kernel/process.c
+++ b/arch/s390/kernel/process.c
@@ -86,11 +86,6 @@ void arch_release_task_struct(struct task_struct *tsk)
int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
{
- /*
- * Save the floating-point or vector register state of the current
- * task and set the TIF_FPU flag to lazy restore the FPU register
- * state when returning to user space.
- */
save_user_fpu_regs();
*dst = *src;
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 24ed33f044..610e6f7945 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -146,16 +146,16 @@ static u32 __amode31_ref *__ctl_linkage_stack = __ctl_linkage_stack_amode31;
static u32 __amode31_ref *__ctl_duct = __ctl_duct_amode31;
unsigned long __bootdata_preserved(max_mappable);
-unsigned long __bootdata(ident_map_size);
struct physmem_info __bootdata(physmem_info);
-unsigned long __bootdata_preserved(__kaslr_offset);
+struct vm_layout __bootdata_preserved(vm_layout);
+EXPORT_SYMBOL(vm_layout);
int __bootdata_preserved(__kaslr_enabled);
unsigned int __bootdata_preserved(zlib_dfltcc_support);
EXPORT_SYMBOL(zlib_dfltcc_support);
u64 __bootdata_preserved(stfle_fac_list[16]);
EXPORT_SYMBOL(stfle_fac_list);
-u64 __bootdata_preserved(alt_stfle_fac_list[16]);
+u64 alt_stfle_fac_list[16];
struct oldmem_data __bootdata_preserved(oldmem_data);
unsigned long VMALLOC_START;
@@ -765,7 +765,7 @@ static void __init relocate_amode31_section(void)
unsigned long amode31_size = __eamode31 - __samode31;
long amode31_offset, *ptr;
- amode31_offset = physmem_info.reserved[RR_AMODE31].start - (unsigned long)__samode31;
+ amode31_offset = AMODE31_START - (unsigned long)__samode31;
pr_info("Relocating AMODE31 section of size 0x%08lx\n", amode31_size);
/* Move original AMODE31 section to the new one */
diff --git a/arch/s390/kernel/stacktrace.c b/arch/s390/kernel/stacktrace.c
index 94f440e383..640363b2a1 100644
--- a/arch/s390/kernel/stacktrace.c
+++ b/arch/s390/kernel/stacktrace.c
@@ -5,6 +5,7 @@
* Copyright IBM Corp. 2006
*/
+#include <linux/perf_event.h>
#include <linux/stacktrace.h>
#include <linux/uaccess.h>
#include <linux/compat.h>
@@ -62,42 +63,121 @@ int arch_stack_walk_reliable(stack_trace_consume_fn consume_entry,
return 0;
}
-void arch_stack_walk_user(stack_trace_consume_fn consume_entry, void *cookie,
- const struct pt_regs *regs)
+static inline bool store_ip(stack_trace_consume_fn consume_entry, void *cookie,
+ struct perf_callchain_entry_ctx *entry, bool perf,
+ unsigned long ip)
+{
+#ifdef CONFIG_PERF_EVENTS
+ if (perf) {
+ if (perf_callchain_store(entry, ip))
+ return false;
+ return true;
+ }
+#endif
+ return consume_entry(cookie, ip);
+}
+
+static inline bool ip_invalid(unsigned long ip)
+{
+ /*
+ * Perform some basic checks if an instruction address taken
+ * from unreliable source is invalid.
+ */
+ if (ip & 1)
+ return true;
+ if (ip < mmap_min_addr)
+ return true;
+ if (ip >= current->mm->context.asce_limit)
+ return true;
+ return false;
+}
+
+static inline bool ip_within_vdso(unsigned long ip)
{
+ return in_range(ip, current->mm->context.vdso_base, vdso_text_size());
+}
+
+void arch_stack_walk_user_common(stack_trace_consume_fn consume_entry, void *cookie,
+ struct perf_callchain_entry_ctx *entry,
+ const struct pt_regs *regs, bool perf)
+{
+ struct stack_frame_vdso_wrapper __user *sf_vdso;
struct stack_frame_user __user *sf;
unsigned long ip, sp;
bool first = true;
if (is_compat_task())
return;
- if (!consume_entry(cookie, instruction_pointer(regs)))
+ if (!current->mm)
+ return;
+ ip = instruction_pointer(regs);
+ if (!store_ip(consume_entry, cookie, entry, perf, ip))
return;
sf = (void __user *)user_stack_pointer(regs);
pagefault_disable();
while (1) {
if (__get_user(sp, &sf->back_chain))
break;
- if (__get_user(ip, &sf->gprs[8]))
+ /*
+ * VDSO entry code has a non-standard stack frame layout.
+ * See VDSO user wrapper code for details.
+ */
+ if (!sp && ip_within_vdso(ip)) {
+ sf_vdso = (void __user *)sf;
+ if (__get_user(ip, &sf_vdso->return_address))
+ break;
+ sp = (unsigned long)sf + STACK_FRAME_VDSO_OVERHEAD;
+ sf = (void __user *)sp;
+ if (__get_user(sp, &sf->back_chain))
+ break;
+ } else {
+ sf = (void __user *)sp;
+ if (__get_user(ip, &sf->gprs[8]))
+ break;
+ }
+ /* Sanity check: ABI requires SP to be 8 byte aligned. */
+ if (sp & 0x7)
break;
- if (ip & 0x1) {
+ if (ip_invalid(ip)) {
/*
* If the instruction address is invalid, and this
* is the first stack frame, assume r14 has not
* been written to the stack yet. Otherwise exit.
*/
- if (first && !(regs->gprs[14] & 0x1))
- ip = regs->gprs[14];
- else
+ if (!first)
+ break;
+ ip = regs->gprs[14];
+ if (ip_invalid(ip))
break;
}
- if (!consume_entry(cookie, ip))
- break;
- /* Sanity check: ABI requires SP to be aligned 8 bytes. */
- if (!sp || sp & 0x7)
- break;
- sf = (void __user *)sp;
+ if (!store_ip(consume_entry, cookie, entry, perf, ip))
+ return;
first = false;
}
pagefault_enable();
}
+
+void arch_stack_walk_user(stack_trace_consume_fn consume_entry, void *cookie,
+ const struct pt_regs *regs)
+{
+ arch_stack_walk_user_common(consume_entry, cookie, NULL, regs, false);
+}
+
+unsigned long return_address(unsigned int n)
+{
+ struct unwind_state state;
+ unsigned long addr;
+
+ /* Increment to skip current stack entry */
+ n++;
+
+ unwind_for_each_frame(&state, NULL, NULL, 0) {
+ addr = unwind_get_return_address(&state);
+ if (!addr)
+ break;
+ if (!n--)
+ return addr;
+ }
+ return 0;
+}
+EXPORT_SYMBOL_GPL(return_address);
diff --git a/arch/s390/kernel/syscall.c b/arch/s390/kernel/syscall.c
index dc2355c623..50cbcbbaa0 100644
--- a/arch/s390/kernel/syscall.c
+++ b/arch/s390/kernel/syscall.c
@@ -38,33 +38,6 @@
#include "entry.h"
-/*
- * Perform the mmap() system call. Linux for S/390 isn't able to handle more
- * than 5 system call parameters, so this system call uses a memory block
- * for parameter passing.
- */
-
-struct s390_mmap_arg_struct {
- unsigned long addr;
- unsigned long len;
- unsigned long prot;
- unsigned long flags;
- unsigned long fd;
- unsigned long offset;
-};
-
-SYSCALL_DEFINE1(mmap2, struct s390_mmap_arg_struct __user *, arg)
-{
- struct s390_mmap_arg_struct a;
- int error = -EFAULT;
-
- if (copy_from_user(&a, arg, sizeof(a)))
- goto out;
- error = ksys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd, a.offset);
-out:
- return error;
-}
-
#ifdef CONFIG_SYSVIPC
/*
* sys_ipc() is the de-multiplexer for the SysV IPC calls.
diff --git a/arch/s390/kernel/syscalls/Makefile b/arch/s390/kernel/syscalls/Makefile
index fb85e79794..1bb78b9468 100644
--- a/arch/s390/kernel/syscalls/Makefile
+++ b/arch/s390/kernel/syscalls/Makefile
@@ -4,8 +4,8 @@ gen := arch/$(ARCH)/include/generated
kapi := $(gen)/asm
uapi := $(gen)/uapi/asm
-syscall := $(srctree)/$(src)/syscall.tbl
-systbl := $(srctree)/$(src)/syscalltbl
+syscall := $(src)/syscall.tbl
+systbl := $(src)/syscalltbl
gen-y := $(kapi)/syscall_table.h
kapi-hdrs-y := $(kapi)/unistd_nr.h
diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl
index 095bb86339..0107118276 100644
--- a/arch/s390/kernel/syscalls/syscall.tbl
+++ b/arch/s390/kernel/syscalls/syscall.tbl
@@ -418,7 +418,7 @@
412 32 utimensat_time64 - sys_utimensat
413 32 pselect6_time64 - compat_sys_pselect6_time64
414 32 ppoll_time64 - compat_sys_ppoll_time64
-416 32 io_pgetevents_time64 - sys_io_pgetevents
+416 32 io_pgetevents_time64 - compat_sys_io_pgetevents_time64
417 32 recvmmsg_time64 - compat_sys_recvmmsg_time64
418 32 mq_timedsend_time64 - sys_mq_timedsend
419 32 mq_timedreceive_time64 - sys_mq_timedreceive
@@ -464,3 +464,4 @@
459 common lsm_get_self_attr sys_lsm_get_self_attr sys_lsm_get_self_attr
460 common lsm_set_self_attr sys_lsm_set_self_attr sys_lsm_set_self_attr
461 common lsm_list_modules sys_lsm_list_modules sys_lsm_list_modules
+462 common mseal sys_mseal sys_mseal
diff --git a/arch/s390/kernel/uv.c b/arch/s390/kernel/uv.c
index fc07bc39e6..016993e9eb 100644
--- a/arch/s390/kernel/uv.c
+++ b/arch/s390/kernel/uv.c
@@ -21,6 +21,7 @@
/* the bootdata_preserved fields come from ones in arch/s390/boot/uv.c */
#ifdef CONFIG_PROTECTED_VIRTUALIZATION_GUEST
int __bootdata_preserved(prot_virt_guest);
+EXPORT_SYMBOL(prot_virt_guest);
#endif
/*
@@ -181,36 +182,36 @@ int uv_convert_owned_from_secure(unsigned long paddr)
}
/*
- * Calculate the expected ref_count for a page that would otherwise have no
+ * Calculate the expected ref_count for a folio that would otherwise have no
* further pins. This was cribbed from similar functions in other places in
* the kernel, but with some slight modifications. We know that a secure
- * page can not be a huge page for example.
+ * folio can not be a large folio, for example.
*/
-static int expected_page_refs(struct page *page)
+static int expected_folio_refs(struct folio *folio)
{
int res;
- res = page_mapcount(page);
- if (PageSwapCache(page)) {
+ res = folio_mapcount(folio);
+ if (folio_test_swapcache(folio)) {
res++;
- } else if (page_mapping(page)) {
+ } else if (folio_mapping(folio)) {
res++;
- if (page_has_private(page))
+ if (folio->private)
res++;
}
return res;
}
-static int make_page_secure(struct page *page, struct uv_cb_header *uvcb)
+static int make_folio_secure(struct folio *folio, struct uv_cb_header *uvcb)
{
int expected, cc = 0;
- if (PageWriteback(page))
+ if (folio_test_writeback(folio))
return -EAGAIN;
- expected = expected_page_refs(page);
- if (!page_ref_freeze(page, expected))
+ expected = expected_folio_refs(folio);
+ if (!folio_ref_freeze(folio, expected))
return -EBUSY;
- set_bit(PG_arch_1, &page->flags);
+ set_bit(PG_arch_1, &folio->flags);
/*
* If the UVC does not succeed or fail immediately, we don't want to
* loop for long, or we might get stall notifications.
@@ -220,9 +221,9 @@ static int make_page_secure(struct page *page, struct uv_cb_header *uvcb)
* -EAGAIN and we let the callers deal with it.
*/
cc = __uv_call(0, (u64)uvcb);
- page_ref_unfreeze(page, expected);
+ folio_ref_unfreeze(folio, expected);
/*
- * Return -ENXIO if the page was not mapped, -EINVAL for other errors.
+ * Return -ENXIO if the folio was not mapped, -EINVAL for other errors.
* If busy or partially completed, return -EAGAIN.
*/
if (cc == UVC_CC_OK)
@@ -277,7 +278,7 @@ int gmap_make_secure(struct gmap *gmap, unsigned long gaddr, void *uvcb)
bool local_drain = false;
spinlock_t *ptelock;
unsigned long uaddr;
- struct page *page;
+ struct folio *folio;
pte_t *ptep;
int rc;
@@ -306,15 +307,26 @@ again:
if (!ptep)
goto out;
if (pte_present(*ptep) && !(pte_val(*ptep) & _PAGE_INVALID) && pte_write(*ptep)) {
- page = pte_page(*ptep);
+ folio = page_folio(pte_page(*ptep));
+ rc = -EINVAL;
+ if (folio_test_large(folio))
+ goto unlock;
rc = -EAGAIN;
- if (trylock_page(page)) {
+ if (folio_trylock(folio)) {
if (should_export_before_import(uvcb, gmap->mm))
- uv_convert_from_secure(page_to_phys(page));
- rc = make_page_secure(page, uvcb);
- unlock_page(page);
+ uv_convert_from_secure(PFN_PHYS(folio_pfn(folio)));
+ rc = make_folio_secure(folio, uvcb);
+ folio_unlock(folio);
}
+
+ /*
+ * Once we drop the PTL, the folio may get unmapped and
+ * freed immediately. We need a temporary reference.
+ */
+ if (rc == -EAGAIN)
+ folio_get(folio);
}
+unlock:
pte_unmap_unlock(ptep, ptelock);
out:
mmap_read_unlock(gmap->mm);
@@ -324,10 +336,11 @@ out:
* If we are here because the UVC returned busy or partial
* completion, this is just a useless check, but it is safe.
*/
- wait_on_page_writeback(page);
+ folio_wait_writeback(folio);
+ folio_put(folio);
} else if (rc == -EBUSY) {
/*
- * If we have tried a local drain and the page refcount
+ * If we have tried a local drain and the folio refcount
* still does not match our expected safe value, try with a
* system wide drain. This is needed if the pagevecs holding
* the page are on a different CPU.
@@ -338,7 +351,7 @@ out:
return -EAGAIN;
}
/*
- * We are here if the page refcount does not match the
+ * We are here if the folio refcount does not match the
* expected safe value. The main culprits are usually
* pagevecs. With lru_add_drain() we drain the pagevecs
* on the local CPU so that hopefully the refcount will
diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c
index a45b3a4c91..2f967ac2b8 100644
--- a/arch/s390/kernel/vdso.c
+++ b/arch/s390/kernel/vdso.c
@@ -210,17 +210,22 @@ static unsigned long vdso_addr(unsigned long start, unsigned long len)
return addr;
}
-unsigned long vdso_size(void)
+unsigned long vdso_text_size(void)
{
- unsigned long size = VVAR_NR_PAGES * PAGE_SIZE;
+ unsigned long size;
if (is_compat_task())
- size += vdso32_end - vdso32_start;
+ size = vdso32_end - vdso32_start;
else
- size += vdso64_end - vdso64_start;
+ size = vdso64_end - vdso64_start;
return PAGE_ALIGN(size);
}
+unsigned long vdso_size(void)
+{
+ return vdso_text_size() + VVAR_NR_PAGES * PAGE_SIZE;
+}
+
int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
{
unsigned long addr = VDSO_BASE;
diff --git a/arch/s390/kernel/vdso32/Makefile b/arch/s390/kernel/vdso32/Makefile
index b12a274cbb..2c5afb88d2 100644
--- a/arch/s390/kernel/vdso32/Makefile
+++ b/arch/s390/kernel/vdso32/Makefile
@@ -1,8 +1,6 @@
# SPDX-License-Identifier: GPL-2.0
# List of files in the vdso
-KCOV_INSTRUMENT := n
-
# Include the generic Makefile to check the built vdso.
include $(srctree)/lib/vdso/Makefile
obj-vdso32 = vdso_user_wrapper-32.o note-32.o
@@ -19,8 +17,10 @@ KBUILD_AFLAGS_32 := $(filter-out -m64,$(KBUILD_AFLAGS))
KBUILD_AFLAGS_32 += -m31 -s
KBUILD_CFLAGS_32 := $(filter-out -m64,$(KBUILD_CFLAGS))
+KBUILD_CFLAGS_32 := $(filter-out -mpacked-stack,$(KBUILD_CFLAGS))
KBUILD_CFLAGS_32 := $(filter-out -mno-pic-data-is-text-relative,$(KBUILD_CFLAGS_32))
-KBUILD_CFLAGS_32 += -m31 -fPIC -shared -fno-common -fno-builtin
+KBUILD_CFLAGS_32 := $(filter-out -fno-asynchronous-unwind-tables,$(KBUILD_CFLAGS_32))
+KBUILD_CFLAGS_32 += -m31 -fPIC -shared -fno-common -fno-builtin -fasynchronous-unwind-tables
LDFLAGS_vdso32.so.dbg += -shared -soname=linux-vdso32.so.1 \
--hash-style=both --build-id=sha1 -melf_s390 -T
@@ -32,19 +32,13 @@ obj-y += vdso32_wrapper.o
targets += vdso32.lds
CPPFLAGS_vdso32.lds += -P -C -U$(ARCH)
-# Disable gcov profiling, ubsan and kasan for VDSO code
-GCOV_PROFILE := n
-UBSAN_SANITIZE := n
-KASAN_SANITIZE := n
-KCSAN_SANITIZE := n
-
# Force dependency (incbin is bad)
$(obj)/vdso32_wrapper.o : $(obj)/vdso32.so
quiet_cmd_vdso_and_check = VDSO $@
cmd_vdso_and_check = $(cmd_ld); $(cmd_vdso_check)
-$(obj)/vdso32.so.dbg: $(src)/vdso32.lds $(obj-vdso32) FORCE
+$(obj)/vdso32.so.dbg: $(obj)/vdso32.lds $(obj-vdso32) FORCE
$(call if_changed,vdso_and_check)
# strip rule for the .so file
@@ -62,7 +56,7 @@ quiet_cmd_vdso32cc = VDSO32C $@
cmd_vdso32cc = $(CC) $(c_flags) -c -o $@ $<
# Generate VDSO offsets using helper script
-gen-vdsosym := $(srctree)/$(src)/gen_vdso_offsets.sh
+gen-vdsosym := $(src)/gen_vdso_offsets.sh
quiet_cmd_vdsosym = VDSOSYM $@
cmd_vdsosym = $(NM) $< | $(gen-vdsosym) | LC_ALL=C sort > $@
diff --git a/arch/s390/kernel/vdso64/Makefile b/arch/s390/kernel/vdso64/Makefile
index ef98327260..ba19c0ca7c 100644
--- a/arch/s390/kernel/vdso64/Makefile
+++ b/arch/s390/kernel/vdso64/Makefile
@@ -1,8 +1,6 @@
# SPDX-License-Identifier: GPL-2.0
# List of files in the vdso
-KCOV_INSTRUMENT := n
-
# Include the generic Makefile to check the built vdso.
include $(srctree)/lib/vdso/Makefile
obj-vdso64 = vdso_user_wrapper.o note.o
@@ -24,9 +22,11 @@ KBUILD_AFLAGS_64 := $(filter-out -m64,$(KBUILD_AFLAGS))
KBUILD_AFLAGS_64 += -m64
KBUILD_CFLAGS_64 := $(filter-out -m64,$(KBUILD_CFLAGS))
+KBUILD_CFLAGS_64 := $(filter-out -mpacked-stack,$(KBUILD_CFLAGS_64))
KBUILD_CFLAGS_64 := $(filter-out -mno-pic-data-is-text-relative,$(KBUILD_CFLAGS_64))
KBUILD_CFLAGS_64 := $(filter-out -munaligned-symbols,$(KBUILD_CFLAGS_64))
-KBUILD_CFLAGS_64 += -m64 -fPIC -fno-common -fno-builtin
+KBUILD_CFLAGS_64 := $(filter-out -fno-asynchronous-unwind-tables,$(KBUILD_CFLAGS_64))
+KBUILD_CFLAGS_64 += -m64 -fPIC -fno-common -fno-builtin -fasynchronous-unwind-tables
ldflags-y := -shared -soname=linux-vdso64.so.1 \
--hash-style=both --build-id=sha1 -T
@@ -37,12 +37,6 @@ obj-y += vdso64_wrapper.o
targets += vdso64.lds
CPPFLAGS_vdso64.lds += -P -C -U$(ARCH)
-# Disable gcov profiling, ubsan and kasan for VDSO code
-GCOV_PROFILE := n
-UBSAN_SANITIZE := n
-KASAN_SANITIZE := n
-KCSAN_SANITIZE := n
-
# Force dependency (incbin is bad)
$(obj)/vdso64_wrapper.o : $(obj)/vdso64.so
@@ -50,7 +44,7 @@ quiet_cmd_vdso_and_check = VDSO $@
cmd_vdso_and_check = $(cmd_ld); $(cmd_vdso_check)
# link rule for the .so file, .lds has to be first
-$(obj)/vdso64.so.dbg: $(src)/vdso64.lds $(obj-vdso64) $(obj-cvdso64) FORCE
+$(obj)/vdso64.so.dbg: $(obj)/vdso64.lds $(obj-vdso64) $(obj-cvdso64) FORCE
$(call if_changed,vdso_and_check)
# strip rule for the .so file
@@ -72,7 +66,7 @@ quiet_cmd_vdso64cc = VDSO64C $@
cmd_vdso64cc = $(CC) $(c_flags) -c -o $@ $<
# Generate VDSO offsets using helper script
-gen-vdsosym := $(srctree)/$(src)/gen_vdso_offsets.sh
+gen-vdsosym := $(src)/gen_vdso_offsets.sh
quiet_cmd_vdsosym = VDSOSYM $@
cmd_vdsosym = $(NM) $< | $(gen-vdsosym) | LC_ALL=C sort > $@
diff --git a/arch/s390/kernel/vdso64/vdso_user_wrapper.S b/arch/s390/kernel/vdso64/vdso_user_wrapper.S
index 85247ef5a4..e26e68675c 100644
--- a/arch/s390/kernel/vdso64/vdso_user_wrapper.S
+++ b/arch/s390/kernel/vdso64/vdso_user_wrapper.S
@@ -6,8 +6,6 @@
#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
@@ -20,16 +18,17 @@
__ALIGN
__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)
- CFI_REL_OFFSET 14, STACK_FRAME_OVERHEAD
+ aghi %r15,-STACK_FRAME_VDSO_OVERHEAD
+ CFI_DEF_CFA_OFFSET (STACK_FRAME_USER_OVERHEAD + STACK_FRAME_VDSO_OVERHEAD)
+ CFI_VAL_OFFSET 15,-STACK_FRAME_USER_OVERHEAD
+ stg %r14,__SFVDSO_RETURN_ADDRESS(%r15)
+ CFI_REL_OFFSET 14,__SFVDSO_RETURN_ADDRESS
+ xc __SFUSER_BACKCHAIN(8,%r15),__SFUSER_BACKCHAIN(%r15)
brasl %r14,__s390_vdso_\func
- lg %r14,STACK_FRAME_OVERHEAD(%r15)
+ lg %r14,__SFVDSO_RETURN_ADDRESS(%r15)
CFI_RESTORE 14
- aghi %r15,WRAPPER_FRAME_SIZE
- CFI_DEF_CFA_OFFSET STACK_FRAME_OVERHEAD
+ aghi %r15,STACK_FRAME_VDSO_OVERHEAD
+ CFI_DEF_CFA_OFFSET STACK_FRAME_USER_OVERHEAD
CFI_RESTORE 15
br %r14
CFI_ENDPROC
diff --git a/arch/s390/kernel/vmcore_info.c b/arch/s390/kernel/vmcore_info.c
index d296dfc221..23f7d7619a 100644
--- a/arch/s390/kernel/vmcore_info.c
+++ b/arch/s390/kernel/vmcore_info.c
@@ -14,7 +14,9 @@ void arch_crash_save_vmcoreinfo(void)
VMCOREINFO_LENGTH(lowcore_ptr, NR_CPUS);
vmcoreinfo_append_str("SAMODE31=%lx\n", (unsigned long)__samode31);
vmcoreinfo_append_str("EAMODE31=%lx\n", (unsigned long)__eamode31);
+ vmcoreinfo_append_str("IDENTITYBASE=%lx\n", __identity_base);
vmcoreinfo_append_str("KERNELOFFSET=%lx\n", kaslr_offset());
+ vmcoreinfo_append_str("KERNELOFFPHYS=%lx\n", __kaslr_offset_phys);
abs_lc = get_abs_lowcore();
abs_lc->vmcore_info = paddr_vmcoreinfo_note();
put_abs_lowcore(abs_lc);
diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S
index 48de296e89..a1ce3925ec 100644
--- a/arch/s390/kernel/vmlinux.lds.S
+++ b/arch/s390/kernel/vmlinux.lds.S
@@ -39,7 +39,7 @@ PHDRS {
SECTIONS
{
- . = 0x100000;
+ . = __START_KERNEL;
.text : {
_stext = .; /* Start of text section */
_text = .; /* Text and read-only data */
@@ -183,7 +183,7 @@ SECTIONS
.amode31.data : {
*(.amode31.data)
}
- . = ALIGN(PAGE_SIZE);
+ . = _samode31 + AMODE31_SIZE;
_eamode31 = .;
/* early.c uses stsi, which requires page aligned data. */
@@ -192,31 +192,6 @@ SECTIONS
PERCPU_SECTION(0x100)
-#ifdef CONFIG_PIE_BUILD
- .dynsym ALIGN(8) : {
- __dynsym_start = .;
- *(.dynsym)
- __dynsym_end = .;
- }
- .rela.dyn ALIGN(8) : {
- __rela_dyn_start = .;
- *(.rela*)
- __rela_dyn_end = .;
- }
- .dynamic ALIGN(8) : {
- *(.dynamic)
- }
- .dynstr ALIGN(8) : {
- *(.dynstr)
- }
-#endif
- .hash ALIGN(8) : {
- *(.hash)
- }
- .gnu.hash ALIGN(8) : {
- *(.gnu.hash)
- }
-
. = ALIGN(PAGE_SIZE);
__init_end = .; /* freed after init ends here */
@@ -230,7 +205,6 @@ SECTIONS
* it should match struct vmlinux_info
*/
.vmlinux.info 0 (INFO) : {
- QUAD(_stext) /* default_lma */
QUAD(startup_continue) /* entry */
QUAD(__bss_start - _stext) /* image_size */
QUAD(__bss_stop - __bss_start) /* bss_size */
@@ -239,14 +213,8 @@ SECTIONS
QUAD(__boot_data_preserved_start) /* bootdata_preserved_off */
QUAD(__boot_data_preserved_end -
__boot_data_preserved_start) /* bootdata_preserved_size */
-#ifdef CONFIG_PIE_BUILD
- QUAD(__dynsym_start) /* dynsym_start */
- QUAD(__rela_dyn_start) /* rela_dyn_start */
- QUAD(__rela_dyn_end) /* rela_dyn_end */
-#else
QUAD(__got_start) /* got_start */
QUAD(__got_end) /* got_end */
-#endif
QUAD(_eamode31 - _samode31) /* amode31_size */
QUAD(init_mm)
QUAD(swapper_pg_dir)
@@ -282,12 +250,10 @@ SECTIONS
*(.plt) *(.plt.*) *(.iplt) *(.igot .igot.plt)
}
ASSERT(SIZEOF(.plt) == 0, "Unexpected run-time procedure linkages detected!")
-#ifndef CONFIG_PIE_BUILD
.rela.dyn : {
*(.rela.*) *(.rela_*)
}
ASSERT(SIZEOF(.rela.dyn) == 0, "Unexpected run-time relocations (.rela) detected!")
-#endif
/* Sections to be discarded */
DISCARDS
diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c
index 24a18e5ef6..ffc1db0cbf 100644
--- a/arch/s390/kernel/vtime.c
+++ b/arch/s390/kernel/vtime.c
@@ -33,14 +33,6 @@ static DEFINE_PER_CPU(u64, mt_scaling_mult) = { 1 };
static DEFINE_PER_CPU(u64, mt_scaling_div) = { 1 };
static DEFINE_PER_CPU(u64, mt_scaling_jiffies);
-static inline u64 get_vtimer(void)
-{
- u64 timer;
-
- asm volatile("stpt %0" : "=Q" (timer));
- return timer;
-}
-
static inline void set_vtimer(u64 expires)
{
u64 timer;
@@ -223,7 +215,7 @@ static u64 vtime_delta(void)
{
u64 timer = S390_lowcore.last_update_timer;
- S390_lowcore.last_update_timer = get_vtimer();
+ S390_lowcore.last_update_timer = get_cpu_timer();
return timer - S390_lowcore.last_update_timer;
}
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 7721eb522f..4a74effe68 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -132,6 +132,7 @@ const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = {
STATS_DESC_COUNTER(VCPU, instruction_io_other),
STATS_DESC_COUNTER(VCPU, instruction_lpsw),
STATS_DESC_COUNTER(VCPU, instruction_lpswe),
+ STATS_DESC_COUNTER(VCPU, instruction_lpswey),
STATS_DESC_COUNTER(VCPU, instruction_pfmf),
STATS_DESC_COUNTER(VCPU, instruction_ptff),
STATS_DESC_COUNTER(VCPU, instruction_sck),
@@ -2631,9 +2632,7 @@ static int kvm_s390_handle_pv(struct kvm *kvm, struct kvm_pv_cmd *cmd)
if (r)
break;
- mmap_write_lock(current->mm);
- r = gmap_mark_unmergeable();
- mmap_write_unlock(current->mm);
+ r = s390_disable_cow_sharing();
if (r)
break;
@@ -5750,6 +5749,9 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
{
gpa_t size;
+ if (kvm_is_ucontrol(kvm))
+ return -EINVAL;
+
/* When we are protected, we should not change the memory slots */
if (kvm_s390_pv_get_handle(kvm))
return -EINVAL;
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index 111eb5c747..bf8534218a 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -138,6 +138,21 @@ static inline u64 kvm_s390_get_base_disp_s(struct kvm_vcpu *vcpu, u8 *ar)
return (base2 ? vcpu->run->s.regs.gprs[base2] : 0) + disp2;
}
+static inline u64 kvm_s390_get_base_disp_siy(struct kvm_vcpu *vcpu, u8 *ar)
+{
+ u32 base1 = vcpu->arch.sie_block->ipb >> 28;
+ s64 disp1;
+
+ /* The displacement is a 20bit _SIGNED_ value */
+ disp1 = sign_extend64(((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16) +
+ ((vcpu->arch.sie_block->ipb & 0xff00) << 4), 19);
+
+ if (ar)
+ *ar = base1;
+
+ return (base1 ? vcpu->run->s.regs.gprs[base1] : 0) + disp1;
+}
+
static inline void kvm_s390_get_base_disp_sse(struct kvm_vcpu *vcpu,
u64 *address1, u64 *address2,
u8 *ar_b1, u8 *ar_b2)
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index 1be19cc9d7..1a49b89706 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -797,6 +797,36 @@ static int handle_lpswe(struct kvm_vcpu *vcpu)
return 0;
}
+static int handle_lpswey(struct kvm_vcpu *vcpu)
+{
+ psw_t new_psw;
+ u64 addr;
+ int rc;
+ u8 ar;
+
+ vcpu->stat.instruction_lpswey++;
+
+ if (!test_kvm_facility(vcpu->kvm, 193))
+ return kvm_s390_inject_program_int(vcpu, PGM_OPERATION);
+
+ if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
+ return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
+
+ addr = kvm_s390_get_base_disp_siy(vcpu, &ar);
+ if (addr & 7)
+ return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+
+ rc = read_guest(vcpu, addr, ar, &new_psw, sizeof(new_psw));
+ if (rc)
+ return kvm_s390_inject_prog_cond(vcpu, rc);
+
+ vcpu->arch.sie_block->gpsw = new_psw;
+ if (!is_valid_psw(&vcpu->arch.sie_block->gpsw))
+ return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+
+ return 0;
+}
+
static int handle_stidp(struct kvm_vcpu *vcpu)
{
u64 stidp_data = vcpu->kvm->arch.model.cpuid;
@@ -1462,6 +1492,8 @@ int kvm_s390_handle_eb(struct kvm_vcpu *vcpu)
case 0x61:
case 0x62:
return handle_ri(vcpu);
+ case 0x71:
+ return handle_lpswey(vcpu);
default:
return -EOPNOTSUPP;
}
diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c
index b2c9f010f0..c9ecae8306 100644
--- a/arch/s390/kvm/vsie.c
+++ b/arch/s390/kvm/vsie.c
@@ -12,6 +12,7 @@
#include <linux/list.h>
#include <linux/bitmap.h>
#include <linux/sched/signal.h>
+#include <linux/io.h>
#include <asm/gmap.h>
#include <asm/mmu_context.h>
@@ -361,7 +362,7 @@ end:
case -EACCES:
return set_validity_icpt(scb_s, 0x003CU);
}
- scb_s->crycbd = ((__u32)(__u64) &vsie_page->crycb) | CRYCB_FORMAT2;
+ scb_s->crycbd = (u32)virt_to_phys(&vsie_page->crycb) | CRYCB_FORMAT2;
return 0;
}
@@ -1005,7 +1006,7 @@ static int handle_stfle(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
if (read_guest_real(vcpu, fac, &vsie_page->fac,
stfle_size() * sizeof(u64)))
return set_validity_icpt(scb_s, 0x1090U);
- scb_s->fac = (__u32)(__u64) &vsie_page->fac;
+ scb_s->fac = (u32)virt_to_phys(&vsie_page->fac);
}
return 0;
}
diff --git a/arch/s390/lib/Makefile b/arch/s390/lib/Makefile
index 90eac15ea6..f43f897d3f 100644
--- a/arch/s390/lib/Makefile
+++ b/arch/s390/lib/Makefile
@@ -23,4 +23,4 @@ obj-$(CONFIG_S390_MODULES_SANITY_TEST_HELPERS) += test_modules_helpers.o
lib-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o
-obj-$(CONFIG_EXPOLINE_EXTERN) += expoline/
+obj-$(CONFIG_EXPOLINE_EXTERN) += expoline.o
diff --git a/arch/s390/lib/expoline/expoline.S b/arch/s390/lib/expoline.S
index 92ed8409a7..92ed8409a7 100644
--- a/arch/s390/lib/expoline/expoline.S
+++ b/arch/s390/lib/expoline.S
diff --git a/arch/s390/lib/expoline/Makefile b/arch/s390/lib/expoline/Makefile
deleted file mode 100644
index 854631d9cb..0000000000
--- a/arch/s390/lib/expoline/Makefile
+++ /dev/null
@@ -1,3 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-
-obj-y += expoline.o
diff --git a/arch/s390/mm/dump_pagetables.c b/arch/s390/mm/dump_pagetables.c
index ffd07ed7b4..9d0805d6dc 100644
--- a/arch/s390/mm/dump_pagetables.c
+++ b/arch/s390/mm/dump_pagetables.c
@@ -20,8 +20,8 @@ struct addr_marker {
};
enum address_markers_idx {
- IDENTITY_BEFORE_NR = 0,
- IDENTITY_BEFORE_END_NR,
+ LOWCORE_START_NR = 0,
+ LOWCORE_END_NR,
AMODE31_START_NR,
AMODE31_END_NR,
KERNEL_START_NR,
@@ -30,8 +30,8 @@ enum address_markers_idx {
KFENCE_START_NR,
KFENCE_END_NR,
#endif
- IDENTITY_AFTER_NR,
- IDENTITY_AFTER_END_NR,
+ IDENTITY_START_NR,
+ IDENTITY_END_NR,
VMEMMAP_NR,
VMEMMAP_END_NR,
VMALLOC_NR,
@@ -49,8 +49,10 @@ enum address_markers_idx {
};
static struct addr_marker address_markers[] = {
- [IDENTITY_BEFORE_NR] = {0, "Identity Mapping Start"},
- [IDENTITY_BEFORE_END_NR] = {(unsigned long)_stext, "Identity Mapping End"},
+ [LOWCORE_START_NR] = {0, "Lowcore Start"},
+ [LOWCORE_END_NR] = {0, "Lowcore End"},
+ [IDENTITY_START_NR] = {0, "Identity Mapping Start"},
+ [IDENTITY_END_NR] = {0, "Identity Mapping End"},
[AMODE31_START_NR] = {0, "Amode31 Area Start"},
[AMODE31_END_NR] = {0, "Amode31 Area End"},
[KERNEL_START_NR] = {(unsigned long)_stext, "Kernel Image Start"},
@@ -59,8 +61,6 @@ static struct addr_marker address_markers[] = {
[KFENCE_START_NR] = {0, "KFence Pool Start"},
[KFENCE_END_NR] = {0, "KFence Pool End"},
#endif
- [IDENTITY_AFTER_NR] = {(unsigned long)_end, "Identity Mapping Start"},
- [IDENTITY_AFTER_END_NR] = {0, "Identity Mapping End"},
[VMEMMAP_NR] = {0, "vmemmap Area Start"},
[VMEMMAP_END_NR] = {0, "vmemmap Area End"},
[VMALLOC_NR] = {0, "vmalloc Area Start"},
@@ -290,7 +290,10 @@ static int pt_dump_init(void)
*/
max_addr = (S390_lowcore.kernel_asce.val & _REGION_ENTRY_TYPE_MASK) >> 2;
max_addr = 1UL << (max_addr * 11 + 31);
- address_markers[IDENTITY_AFTER_END_NR].start_address = ident_map_size;
+ address_markers[LOWCORE_START_NR].start_address = 0;
+ address_markers[LOWCORE_END_NR].start_address = sizeof(struct lowcore);
+ address_markers[IDENTITY_START_NR].start_address = __identity_base;
+ address_markers[IDENTITY_END_NR].start_address = __identity_base + ident_map_size;
address_markers[AMODE31_START_NR].start_address = (unsigned long)__samode31;
address_markers[AMODE31_END_NR].start_address = (unsigned long)__eamode31;
address_markers[MODULES_NR].start_address = MODULES_VADDR;
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index 0c66b32e0f..c848966ed1 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -325,7 +325,8 @@ static void do_exception(struct pt_regs *regs, int access)
goto lock_mmap;
if (!(vma->vm_flags & access)) {
vma_end_read(vma);
- goto lock_mmap;
+ count_vm_vma_lock_event(VMA_LOCK_SUCCESS);
+ return handle_fault_error_nolock(regs, SEGV_ACCERR);
}
fault = handle_mm_fault(vma, address, flags | FAULT_FLAG_VMA_LOCK, regs);
if (!(fault & (VM_FAULT_RETRY | VM_FAULT_COMPLETED)))
@@ -432,12 +433,13 @@ error:
handle_fault_error_nolock(regs, 0);
else
do_sigsegv(regs, SEGV_MAPERR);
- } else if (fault & VM_FAULT_SIGBUS) {
+ } else if (fault & (VM_FAULT_SIGBUS | VM_FAULT_HWPOISON)) {
if (!user_mode(regs))
handle_fault_error_nolock(regs, 0);
else
do_sigbus(regs);
} else {
+ pr_emerg("Unexpected fault flags: %08x\n", fault);
BUG();
}
}
diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index 12d22a7fa3..474a25ca5c 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -2550,41 +2550,6 @@ static inline void thp_split_mm(struct mm_struct *mm)
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
/*
- * Remove all empty zero pages from the mapping for lazy refaulting
- * - This must be called after mm->context.has_pgste is set, to avoid
- * future creation of zero pages
- * - This must be called after THP was disabled.
- *
- * mm contracts with s390, that even if mm were to remove a page table,
- * racing with the loop below and so causing pte_offset_map_lock() to fail,
- * it will never insert a page table containing empty zero pages once
- * mm_forbids_zeropage(mm) i.e. mm->context.has_pgste is set.
- */
-static int __zap_zero_pages(pmd_t *pmd, unsigned long start,
- unsigned long end, struct mm_walk *walk)
-{
- unsigned long addr;
-
- for (addr = start; addr != end; addr += PAGE_SIZE) {
- pte_t *ptep;
- spinlock_t *ptl;
-
- ptep = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
- if (!ptep)
- break;
- if (is_zero_pfn(pte_pfn(*ptep)))
- ptep_xchg_direct(walk->mm, addr, ptep, __pte(_PAGE_INVALID));
- pte_unmap_unlock(ptep, ptl);
- }
- return 0;
-}
-
-static const struct mm_walk_ops zap_zero_walk_ops = {
- .pmd_entry = __zap_zero_pages,
- .walk_lock = PGWALK_WRLOCK,
-};
-
-/*
* switch on pgstes for its userspace process (for kvm)
*/
int s390_enable_sie(void)
@@ -2601,22 +2566,142 @@ int s390_enable_sie(void)
mm->context.has_pgste = 1;
/* split thp mappings and disable thp for future mappings */
thp_split_mm(mm);
- walk_page_range(mm, 0, TASK_SIZE, &zap_zero_walk_ops, NULL);
mmap_write_unlock(mm);
return 0;
}
EXPORT_SYMBOL_GPL(s390_enable_sie);
-int gmap_mark_unmergeable(void)
+static int find_zeropage_pte_entry(pte_t *pte, unsigned long addr,
+ unsigned long end, struct mm_walk *walk)
+{
+ unsigned long *found_addr = walk->private;
+
+ /* Return 1 of the page is a zeropage. */
+ if (is_zero_pfn(pte_pfn(*pte))) {
+ /*
+ * Shared zeropage in e.g., a FS DAX mapping? We cannot do the
+ * right thing and likely don't care: FAULT_FLAG_UNSHARE
+ * currently only works in COW mappings, which is also where
+ * mm_forbids_zeropage() is checked.
+ */
+ if (!is_cow_mapping(walk->vma->vm_flags))
+ return -EFAULT;
+
+ *found_addr = addr;
+ return 1;
+ }
+ return 0;
+}
+
+static const struct mm_walk_ops find_zeropage_ops = {
+ .pte_entry = find_zeropage_pte_entry,
+ .walk_lock = PGWALK_WRLOCK,
+};
+
+/*
+ * Unshare all shared zeropages, replacing them by anonymous pages. Note that
+ * we cannot simply zap all shared zeropages, because this could later
+ * trigger unexpected userfaultfd missing events.
+ *
+ * This must be called after mm->context.allow_cow_sharing was
+ * set to 0, to avoid future mappings of shared zeropages.
+ *
+ * mm contracts with s390, that even if mm were to remove a page table,
+ * and racing with walk_page_range_vma() calling pte_offset_map_lock()
+ * would fail, it will never insert a page table containing empty zero
+ * pages once mm_forbids_zeropage(mm) i.e.
+ * mm->context.allow_cow_sharing is set to 0.
+ */
+static int __s390_unshare_zeropages(struct mm_struct *mm)
+{
+ struct vm_area_struct *vma;
+ VMA_ITERATOR(vmi, mm, 0);
+ unsigned long addr;
+ vm_fault_t fault;
+ int rc;
+
+ for_each_vma(vmi, vma) {
+ /*
+ * We could only look at COW mappings, but it's more future
+ * proof to catch unexpected zeropages in other mappings and
+ * fail.
+ */
+ if ((vma->vm_flags & VM_PFNMAP) || is_vm_hugetlb_page(vma))
+ continue;
+ addr = vma->vm_start;
+
+retry:
+ rc = walk_page_range_vma(vma, addr, vma->vm_end,
+ &find_zeropage_ops, &addr);
+ if (rc < 0)
+ return rc;
+ else if (!rc)
+ continue;
+
+ /* addr was updated by find_zeropage_pte_entry() */
+ fault = handle_mm_fault(vma, addr,
+ FAULT_FLAG_UNSHARE | FAULT_FLAG_REMOTE,
+ NULL);
+ if (fault & VM_FAULT_OOM)
+ return -ENOMEM;
+ /*
+ * See break_ksm(): even after handle_mm_fault() returned 0, we
+ * must start the lookup from the current address, because
+ * handle_mm_fault() may back out if there's any difficulty.
+ *
+ * VM_FAULT_SIGBUS and VM_FAULT_SIGSEGV are unexpected but
+ * maybe they could trigger in the future on concurrent
+ * truncation. In that case, the shared zeropage would be gone
+ * and we can simply retry and make progress.
+ */
+ cond_resched();
+ goto retry;
+ }
+
+ return 0;
+}
+
+static int __s390_disable_cow_sharing(struct mm_struct *mm)
{
+ int rc;
+
+ if (!mm->context.allow_cow_sharing)
+ return 0;
+
+ mm->context.allow_cow_sharing = 0;
+
+ /* Replace all shared zeropages by anonymous pages. */
+ rc = __s390_unshare_zeropages(mm);
/*
* Make sure to disable KSM (if enabled for the whole process or
* individual VMAs). Note that nothing currently hinders user space
* from re-enabling it.
*/
- return ksm_disable(current->mm);
+ if (!rc)
+ rc = ksm_disable(mm);
+ if (rc)
+ mm->context.allow_cow_sharing = 1;
+ return rc;
+}
+
+/*
+ * Disable most COW-sharing of memory pages for the whole process:
+ * (1) Disable KSM and unmerge/unshare any KSM pages.
+ * (2) Disallow shared zeropages and unshare any zerpages that are mapped.
+ *
+ * Not that we currently don't bother with COW-shared pages that are shared
+ * with parent/child processes due to fork().
+ */
+int s390_disable_cow_sharing(void)
+{
+ int rc;
+
+ mmap_write_lock(current->mm);
+ rc = __s390_disable_cow_sharing(current->mm);
+ mmap_write_unlock(current->mm);
+ return rc;
}
-EXPORT_SYMBOL_GPL(gmap_mark_unmergeable);
+EXPORT_SYMBOL_GPL(s390_disable_cow_sharing);
/*
* Enable storage key handling from now on and initialize the storage
@@ -2685,7 +2770,7 @@ int s390_enable_skey(void)
goto out_up;
mm->context.uses_skeys = 1;
- rc = gmap_mark_unmergeable();
+ rc = __s390_disable_cow_sharing(mm);
if (rc) {
mm->context.uses_skeys = 0;
goto out_up;
diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c
index dc3db86e13..2675aab4ac 100644
--- a/arch/s390/mm/hugetlbpage.c
+++ b/arch/s390/mm/hugetlbpage.c
@@ -233,16 +233,6 @@ pte_t *huge_pte_offset(struct mm_struct *mm,
return (pte_t *) pmdp;
}
-int pmd_huge(pmd_t pmd)
-{
- return pmd_leaf(pmd);
-}
-
-int pud_huge(pud_t pud)
-{
- return pud_leaf(pud);
-}
-
bool __init arch_hugetlb_valid_size(unsigned long size)
{
if (MACHINE_HAS_EDAT1 && size == PMD_SIZE)
@@ -258,14 +248,12 @@ static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *file,
unsigned long pgoff, unsigned long flags)
{
struct hstate *h = hstate_file(file);
- struct vm_unmapped_area_info info;
+ struct vm_unmapped_area_info info = {};
- info.flags = 0;
info.length = len;
info.low_limit = current->mm->mmap_base;
info.high_limit = TASK_SIZE;
info.align_mask = PAGE_MASK & ~huge_page_mask(h);
- info.align_offset = 0;
return vm_unmapped_area(&info);
}
@@ -274,7 +262,7 @@ static unsigned long hugetlb_get_unmapped_area_topdown(struct file *file,
unsigned long pgoff, unsigned long flags)
{
struct hstate *h = hstate_file(file);
- struct vm_unmapped_area_info info;
+ struct vm_unmapped_area_info info = {};
unsigned long addr;
info.flags = VM_UNMAPPED_AREA_TOPDOWN;
@@ -282,7 +270,6 @@ static unsigned long hugetlb_get_unmapped_area_topdown(struct file *file,
info.low_limit = PAGE_SIZE;
info.high_limit = current->mm->mmap_base;
info.align_mask = PAGE_MASK & ~huge_page_mask(h);
- info.align_offset = 0;
addr = vm_unmapped_area(&info);
/*
@@ -328,7 +315,7 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
goto check_asce_limit;
}
- if (mm->get_unmapped_area == arch_get_unmapped_area)
+ if (!test_bit(MMF_TOPDOWN, &mm->flags))
addr = hugetlb_get_unmapped_area_bottomup(file, addr, len,
pgoff, flags);
else
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index f6391442c0..e769d2726f 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -49,6 +49,7 @@
#include <asm/uv.h>
#include <linux/virtio_anchor.h>
#include <linux/virtio_config.h>
+#include <linux/execmem.h>
pgd_t swapper_pg_dir[PTRS_PER_PGD] __section(".bss..swapper_pg_dir");
pgd_t invalid_pg_dir[PTRS_PER_PGD] __section(".bss..invalid_pg_dir");
@@ -302,3 +303,32 @@ void arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap)
vmem_remove_mapping(start, size);
}
#endif /* CONFIG_MEMORY_HOTPLUG */
+
+#ifdef CONFIG_EXECMEM
+static struct execmem_info execmem_info __ro_after_init;
+
+struct execmem_info __init *execmem_arch_setup(void)
+{
+ unsigned long module_load_offset = 0;
+ unsigned long start;
+
+ if (kaslr_enabled())
+ module_load_offset = get_random_u32_inclusive(1, 1024) * PAGE_SIZE;
+
+ start = MODULES_VADDR + module_load_offset;
+
+ execmem_info = (struct execmem_info){
+ .ranges = {
+ [EXECMEM_DEFAULT] = {
+ .flags = EXECMEM_KASAN_SHADOW,
+ .start = start,
+ .end = MODULES_END,
+ .pgprot = PAGE_KERNEL,
+ .alignment = MODULE_ALIGN,
+ },
+ },
+ };
+
+ return &execmem_info;
+}
+#endif /* CONFIG_EXECMEM */
diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c
index b14fc08876..2067569465 100644
--- a/arch/s390/mm/mmap.c
+++ b/arch/s390/mm/mmap.c
@@ -86,7 +86,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr,
{
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma;
- struct vm_unmapped_area_info info;
+ struct vm_unmapped_area_info info = {};
if (len > TASK_SIZE - mmap_min_addr)
return -ENOMEM;
@@ -102,7 +102,6 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr,
goto check_asce_limit;
}
- info.flags = 0;
info.length = len;
info.low_limit = mm->mmap_base;
info.high_limit = TASK_SIZE;
@@ -122,7 +121,7 @@ unsigned long arch_get_unmapped_area_topdown(struct file *filp, unsigned long ad
{
struct vm_area_struct *vma;
struct mm_struct *mm = current->mm;
- struct vm_unmapped_area_info info;
+ struct vm_unmapped_area_info info = {};
/* requested length too big for entire address space */
if (len > TASK_SIZE - mmap_min_addr)
@@ -185,10 +184,10 @@ void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack)
*/
if (mmap_is_legacy(rlim_stack)) {
mm->mmap_base = mmap_base_legacy(random_factor);
- mm->get_unmapped_area = arch_get_unmapped_area;
+ clear_bit(MMF_TOPDOWN, &mm->flags);
} else {
mm->mmap_base = mmap_base(random_factor, rlim_stack);
- mm->get_unmapped_area = arch_get_unmapped_area_topdown;
+ set_bit(MMF_TOPDOWN, &mm->flags);
}
}
diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c
index abb629d7e1..7e3e767ab8 100644
--- a/arch/s390/mm/pgalloc.c
+++ b/arch/s390/mm/pgalloc.c
@@ -55,6 +55,8 @@ unsigned long *crst_table_alloc(struct mm_struct *mm)
void crst_table_free(struct mm_struct *mm, unsigned long *table)
{
+ if (!table)
+ return;
pagetable_free(virt_to_ptdesc(table));
}
@@ -262,6 +264,8 @@ static unsigned long *base_crst_alloc(unsigned long val)
static void base_crst_free(unsigned long *table)
{
+ if (!table)
+ return;
pagetable_free(virt_to_ptdesc(table));
}
diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c
index 85cddf904c..41c714e212 100644
--- a/arch/s390/mm/vmem.c
+++ b/arch/s390/mm/vmem.c
@@ -13,7 +13,9 @@
#include <linux/slab.h>
#include <linux/sort.h>
#include <asm/page-states.h>
+#include <asm/abs_lowcore.h>
#include <asm/cacheflush.h>
+#include <asm/maccess.h>
#include <asm/nospec-branch.h>
#include <asm/ctlreg.h>
#include <asm/pgalloc.h>
@@ -21,6 +23,7 @@
#include <asm/tlbflush.h>
#include <asm/sections.h>
#include <asm/set_memory.h>
+#include <asm/physmem_info.h>
static DEFINE_MUTEX(vmem_mutex);
@@ -436,7 +439,7 @@ static int modify_pagetable(unsigned long start, unsigned long end, bool add,
if (WARN_ON_ONCE(!PAGE_ALIGNED(start | end)))
return -EINVAL;
/* Don't mess with any tables not fully in 1:1 mapping & vmemmap area */
- if (WARN_ON_ONCE(end > VMALLOC_START))
+ if (WARN_ON_ONCE(end > __abs_lowcore))
return -EINVAL;
for (addr = start; addr < end; addr = next) {
next = pgd_addr_end(addr, end);
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index 5af0402e94..4be8f5cadd 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -1427,8 +1427,12 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp,
EMIT6_DISP_LH(0xeb000000, is32 ? (op32) : (op64), \
(insn->imm & BPF_FETCH) ? src_reg : REG_W0, \
src_reg, dst_reg, off); \
- if (is32 && (insn->imm & BPF_FETCH)) \
- EMIT_ZERO(src_reg); \
+ if (insn->imm & BPF_FETCH) { \
+ /* bcr 14,0 - see atomic_fetch_{add,and,or,xor}() */ \
+ _EMIT2(0x07e0); \
+ if (is32) \
+ EMIT_ZERO(src_reg); \
+ } \
} while (0)
case BPF_ADD:
case BPF_ADD | BPF_FETCH:
@@ -2108,7 +2112,11 @@ skip_init_ctx:
print_fn_code(jit.prg_buf, jit.size_prg);
}
if (!fp->is_func || extra_pass) {
- bpf_jit_binary_lock_ro(header);
+ if (bpf_jit_binary_lock_ro(header)) {
+ bpf_jit_binary_free(header);
+ fp = orig_fp;
+ goto free_addrs;
+ }
} else {
jit_data->header = header;
jit_data->ctx = jit;
diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
index 26afde0d1e..0de0f6e405 100644
--- a/arch/s390/pci/pci.c
+++ b/arch/s390/pci/pci.c
@@ -250,12 +250,6 @@ resource_size_t pcibios_align_resource(void *data, const struct resource *res,
return 0;
}
-/* combine single writes by using store-block insn */
-void __iowrite64_copy(void __iomem *to, const void *from, size_t count)
-{
- zpci_memcpy_toio(to, from, count * 8);
-}
-
void __iomem *ioremap_prot(phys_addr_t phys_addr, size_t size,
unsigned long prot)
{
diff --git a/arch/s390/pci/pci_irq.c b/arch/s390/pci/pci_irq.c
index ff8f24854c..84482a9213 100644
--- a/arch/s390/pci/pci_irq.c
+++ b/arch/s390/pci/pci_irq.c
@@ -268,33 +268,20 @@ static void zpci_floating_irq_handler(struct airq_struct *airq,
}
}
-int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
+static int __alloc_airq(struct zpci_dev *zdev, int msi_vecs,
+ unsigned long *bit)
{
- struct zpci_dev *zdev = to_zpci(pdev);
- unsigned int hwirq, msi_vecs, cpu;
- unsigned long bit;
- struct msi_desc *msi;
- struct msi_msg msg;
- int cpu_addr;
- int rc, irq;
-
- zdev->aisb = -1UL;
- zdev->msi_first_bit = -1U;
- if (type == PCI_CAP_ID_MSI && nvec > 1)
- return 1;
- msi_vecs = min_t(unsigned int, nvec, zdev->max_msi);
-
if (irq_delivery == DIRECTED) {
/* Allocate cpu vector bits */
- bit = airq_iv_alloc(zpci_ibv[0], msi_vecs);
- if (bit == -1UL)
+ *bit = airq_iv_alloc(zpci_ibv[0], msi_vecs);
+ if (*bit == -1UL)
return -EIO;
} else {
/* Allocate adapter summary indicator bit */
- bit = airq_iv_alloc_bit(zpci_sbv);
- if (bit == -1UL)
+ *bit = airq_iv_alloc_bit(zpci_sbv);
+ if (*bit == -1UL)
return -EIO;
- zdev->aisb = bit;
+ zdev->aisb = *bit;
/* Create adapter interrupt vector */
zdev->aibv = airq_iv_create(msi_vecs, AIRQ_IV_DATA | AIRQ_IV_BITLOCK, NULL);
@@ -302,27 +289,66 @@ int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
return -ENOMEM;
/* Wire up shortcut pointer */
- zpci_ibv[bit] = zdev->aibv;
+ zpci_ibv[*bit] = zdev->aibv;
/* Each function has its own interrupt vector */
- bit = 0;
+ *bit = 0;
}
+ return 0;
+}
- /* Request MSI interrupts */
+int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
+{
+ unsigned int hwirq, msi_vecs, irqs_per_msi, i, cpu;
+ struct zpci_dev *zdev = to_zpci(pdev);
+ struct msi_desc *msi;
+ struct msi_msg msg;
+ unsigned long bit;
+ int cpu_addr;
+ int rc, irq;
+
+ zdev->aisb = -1UL;
+ zdev->msi_first_bit = -1U;
+
+ msi_vecs = min_t(unsigned int, nvec, zdev->max_msi);
+ if (msi_vecs < nvec) {
+ pr_info("%s requested %d irqs, allocate system limit of %d",
+ pci_name(pdev), nvec, zdev->max_msi);
+ }
+
+ rc = __alloc_airq(zdev, msi_vecs, &bit);
+ if (rc < 0)
+ return rc;
+
+ /*
+ * Request MSI interrupts:
+ * When using MSI, nvec_used interrupt sources and their irq
+ * descriptors are controlled through one msi descriptor.
+ * Thus the outer loop over msi descriptors shall run only once,
+ * while two inner loops iterate over the interrupt vectors.
+ * When using MSI-X, each interrupt vector/irq descriptor
+ * is bound to exactly one msi descriptor (nvec_used is one).
+ * So the inner loops are executed once, while the outer iterates
+ * over the MSI-X descriptors.
+ */
hwirq = bit;
msi_for_each_desc(msi, &pdev->dev, MSI_DESC_NOTASSOCIATED) {
- rc = -EIO;
if (hwirq - bit >= msi_vecs)
break;
- irq = __irq_alloc_descs(-1, 0, 1, 0, THIS_MODULE,
- (irq_delivery == DIRECTED) ?
- msi->affinity : NULL);
+ irqs_per_msi = min_t(unsigned int, msi_vecs, msi->nvec_used);
+ irq = __irq_alloc_descs(-1, 0, irqs_per_msi, 0, THIS_MODULE,
+ (irq_delivery == DIRECTED) ?
+ msi->affinity : NULL);
if (irq < 0)
return -ENOMEM;
- rc = irq_set_msi_desc(irq, msi);
- if (rc)
- return rc;
- irq_set_chip_and_handler(irq, &zpci_irq_chip,
- handle_percpu_irq);
+
+ for (i = 0; i < irqs_per_msi; i++) {
+ rc = irq_set_msi_desc_off(irq, i, msi);
+ if (rc)
+ return rc;
+ irq_set_chip_and_handler(irq + i, &zpci_irq_chip,
+ handle_percpu_irq);
+ }
+
msg.data = hwirq - bit;
if (irq_delivery == DIRECTED) {
if (msi->affinity)
@@ -335,31 +361,35 @@ int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
msg.address_lo |= (cpu_addr << 8);
for_each_possible_cpu(cpu) {
- airq_iv_set_data(zpci_ibv[cpu], hwirq, irq);
+ for (i = 0; i < irqs_per_msi; i++)
+ airq_iv_set_data(zpci_ibv[cpu],
+ hwirq + i, irq + i);
}
} else {
msg.address_lo = zdev->msi_addr & 0xffffffff;
- airq_iv_set_data(zdev->aibv, hwirq, irq);
+ for (i = 0; i < irqs_per_msi; i++)
+ airq_iv_set_data(zdev->aibv, hwirq + i, irq + i);
}
msg.address_hi = zdev->msi_addr >> 32;
pci_write_msi_msg(irq, &msg);
- hwirq++;
+ hwirq += irqs_per_msi;
}
zdev->msi_first_bit = bit;
- zdev->msi_nr_irqs = msi_vecs;
+ zdev->msi_nr_irqs = hwirq - bit;
rc = zpci_set_irq(zdev);
if (rc)
return rc;
- return (msi_vecs == nvec) ? 0 : msi_vecs;
+ return (zdev->msi_nr_irqs == nvec) ? 0 : zdev->msi_nr_irqs;
}
void arch_teardown_msi_irqs(struct pci_dev *pdev)
{
struct zpci_dev *zdev = to_zpci(pdev);
struct msi_desc *msi;
+ unsigned int i;
int rc;
/* Disable interrupts */
@@ -369,8 +399,10 @@ void arch_teardown_msi_irqs(struct pci_dev *pdev)
/* Release MSI interrupts */
msi_for_each_desc(msi, &pdev->dev, MSI_DESC_ASSOCIATED) {
- irq_set_msi_desc(msi->irq, NULL);
- irq_free_desc(msi->irq);
+ for (i = 0; i < msi->nvec_used; i++) {
+ irq_set_msi_desc(msi->irq + i, NULL);
+ irq_free_desc(msi->irq + i);
+ }
msi->msg.address_lo = 0;
msi->msg.address_hi = 0;
msi->msg.data = 0;
@@ -410,7 +442,7 @@ static void __init cpu_enable_directed_irq(void *unused)
union zpci_sic_iib iib = {{0}};
union zpci_sic_iib ziib = {{0}};
- iib.cdiib.dibv_addr = (u64) zpci_ibv[smp_processor_id()]->vector;
+ iib.cdiib.dibv_addr = virt_to_phys(zpci_ibv[smp_processor_id()]->vector);
zpci_set_irq_ctrl(SIC_IRQ_MODE_SET_CPU, 0, &iib);
zpci_set_irq_ctrl(SIC_IRQ_MODE_D_SINGLE, PCI_ISC, &ziib);
diff --git a/arch/s390/pci/pci_mmio.c b/arch/s390/pci/pci_mmio.c
index a90499c087..5398729bfe 100644
--- a/arch/s390/pci/pci_mmio.c
+++ b/arch/s390/pci/pci_mmio.c
@@ -169,7 +169,7 @@ SYSCALL_DEFINE3(s390_pci_mmio_write, unsigned long, mmio_addr,
if (!(vma->vm_flags & VM_WRITE))
goto out_unlock_mmap;
- ret = follow_pte(vma->vm_mm, mmio_addr, &ptep, &ptl);
+ ret = follow_pte(vma, mmio_addr, &ptep, &ptl);
if (ret)
goto out_unlock_mmap;
@@ -308,7 +308,7 @@ SYSCALL_DEFINE3(s390_pci_mmio_read, unsigned long, mmio_addr,
if (!(vma->vm_flags & VM_WRITE))
goto out_unlock_mmap;
- ret = follow_pte(vma->vm_mm, mmio_addr, &ptep, &ptl);
+ ret = follow_pte(vma, mmio_addr, &ptep, &ptl);
if (ret)
goto out_unlock_mmap;
diff --git a/arch/s390/pci/pci_sysfs.c b/arch/s390/pci/pci_sysfs.c
index a0b872b74f..0f4f1e8fc4 100644
--- a/arch/s390/pci/pci_sysfs.c
+++ b/arch/s390/pci/pci_sysfs.c
@@ -172,7 +172,6 @@ static ssize_t uid_is_unique_show(struct device *dev,
}
static DEVICE_ATTR_RO(uid_is_unique);
-#ifndef CONFIG_DMI
/* analogous to smbios index */
static ssize_t index_show(struct device *dev,
struct device_attribute *attr, char *buf)
@@ -202,7 +201,6 @@ static struct attribute_group zpci_ident_attr_group = {
.attrs = zpci_ident_attrs,
.is_visible = zpci_index_is_visible,
};
-#endif
static struct bin_attribute *zpci_bin_attrs[] = {
&bin_attr_util_string,
@@ -245,8 +243,6 @@ static struct attribute_group pfip_attr_group = {
const struct attribute_group *zpci_attr_groups[] = {
&zpci_attr_group,
&pfip_attr_group,
-#ifndef CONFIG_DMI
&zpci_ident_attr_group,
-#endif
NULL,
};
diff --git a/arch/s390/purgatory/Makefile b/arch/s390/purgatory/Makefile
index 4e930f5668..24eccaa293 100644
--- a/arch/s390/purgatory/Makefile
+++ b/arch/s390/purgatory/Makefile
@@ -1,7 +1,5 @@
# SPDX-License-Identifier: GPL-2.0
-OBJECT_FILES_NON_STANDARD := y
-
purgatory-y := head.o purgatory.o string.o sha256.o mem.o
targets += $(purgatory-y) purgatory.lds purgatory purgatory.chk purgatory.ro
@@ -15,12 +13,6 @@ CFLAGS_sha256.o := -D__DISABLE_EXPORTS -D__NO_FORTIFY
$(obj)/mem.o: $(srctree)/arch/s390/lib/mem.S FORCE
$(call if_changed_rule,as_o_S)
-KCOV_INSTRUMENT := n
-GCOV_PROFILE := n
-UBSAN_SANITIZE := n
-KASAN_SANITIZE := n
-KCSAN_SANITIZE := n
-
KBUILD_CFLAGS := -fno-strict-aliasing -Wall -Wstrict-prototypes
KBUILD_CFLAGS += -Wno-pointer-sign -Wno-sign-compare
KBUILD_CFLAGS += -fno-zero-initialized-in-bss -fno-builtin -ffreestanding
diff --git a/arch/s390/tools/relocs.c b/arch/s390/tools/relocs.c
index 30a732c808..a74dbd5c98 100644
--- a/arch/s390/tools/relocs.c
+++ b/arch/s390/tools/relocs.c
@@ -280,7 +280,7 @@ static int do_reloc(struct section *sec, Elf_Rel *rel)
case R_390_GOTOFF64:
break;
case R_390_64:
- add_reloc(&relocs64, offset);
+ add_reloc(&relocs64, offset - ehdr.e_entry);
break;
default:
die("Unsupported relocation type: %d\n", r_type);