diff options
Diffstat (limited to 'arch/s390')
149 files changed, 4145 insertions, 3150 deletions
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index a4ad2733eedf..8abe77536d9d 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -1,7 +1,4 @@ # SPDX-License-Identifier: GPL-2.0 -config ARCH_HAS_MEM_ENCRYPT - def_bool y - config MMU def_bool y @@ -33,7 +30,7 @@ config GENERIC_BUG_RELATIVE_POINTERS def_bool y config GENERIC_LOCKBREAK - def_bool y if PREEMPT + def_bool y if PREEMPTTION config PGSTE def_bool y if KVM @@ -68,6 +65,7 @@ config S390 select ARCH_HAS_GCOV_PROFILE_ALL select ARCH_HAS_GIGANTIC_PAGE select ARCH_HAS_KCOV + select ARCH_HAS_MEM_ENCRYPT select ARCH_HAS_PTE_SPECIAL select ARCH_HAS_SET_MEMORY select ARCH_HAS_STRICT_KERNEL_RWX @@ -105,13 +103,14 @@ config S390 select ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE select ARCH_KEEP_MEMBLOCK select ARCH_SAVE_PAGE_KEYS if HIBERNATION + select ARCH_STACKWALK select ARCH_SUPPORTS_ATOMIC_RMW select ARCH_SUPPORTS_NUMA_BALANCING select ARCH_USE_BUILTIN_BSWAP select ARCH_USE_CMPXCHG_LOCKREF select ARCH_WANTS_DYNAMIC_TASK_STRUCT select ARCH_WANT_IPC_PARSE_VERSION - select BUILDTIME_EXTABLE_SORT + select BUILDTIME_TABLE_SORT select CLONE_BACKWARDS2 select DYNAMIC_FTRACE if FUNCTION_TRACER select GENERIC_CLOCKEVENTS @@ -125,12 +124,14 @@ config S390 select HAVE_ARCH_JUMP_LABEL select HAVE_ARCH_JUMP_LABEL_RELATIVE select HAVE_ARCH_KASAN + select HAVE_ARCH_KASAN_VMALLOC select CPU_NO_EFFICIENT_FFS if !HAVE_MARCH_Z9_109_FEATURES select HAVE_ARCH_SECCOMP_FILTER select HAVE_ARCH_SOFT_DIRTY select HAVE_ARCH_TRACEHOOK select HAVE_ARCH_TRANSPARENT_HUGEPAGE select HAVE_ARCH_VMAP_STACK + select HAVE_ASM_MODVERSIONS select HAVE_EBPF_JIT if PACK_STACK && HAVE_MARCH_Z196_FEATURES select HAVE_CMPXCHG_DOUBLE select HAVE_CMPXCHG_LOCAL @@ -155,6 +156,7 @@ config S390 select HAVE_KERNEL_UNCOMPRESSED select HAVE_KERNEL_XZ select HAVE_KPROBES + select HAVE_KPROBES_ON_FTRACE select HAVE_KRETPROBES select HAVE_KVM select HAVE_LIVEPATCH @@ -162,14 +164,15 @@ config S390 select HAVE_PERF_USER_STACK_DUMP select HAVE_MEMBLOCK_NODE_MAP select HAVE_MEMBLOCK_PHYS_MAP - select HAVE_MMU_GATHER_NO_GATHER + select MMU_GATHER_NO_GATHER select HAVE_MOD_ARCH_SPECIFIC select HAVE_NOP_MCOUNT select HAVE_OPROFILE select HAVE_PCI select HAVE_PERF_EVENTS - select HAVE_RCU_TABLE_FREE + select MMU_GATHER_RCU_TABLE_FREE select HAVE_REGS_AND_STACK_ACCESS_API + select HAVE_RELIABLE_STACKTRACE select HAVE_RSEQ select HAVE_SYSCALL_TRACEPOINTS select HAVE_VIRT_CPU_ACCOUNTING @@ -236,14 +239,18 @@ config HAVE_MARCH_Z14_FEATURES def_bool n select HAVE_MARCH_Z13_FEATURES +config HAVE_MARCH_Z15_FEATURES + def_bool n + select HAVE_MARCH_Z14_FEATURES + choice prompt "Processor type" default MARCH_Z196 config MARCH_Z900 bool "IBM zSeries model z800 and z900" - depends on !CC_IS_CLANG select HAVE_MARCH_Z900_FEATURES + depends on $(cc-option,-march=z900) help Select this to enable optimizations for model z800/z900 (2064 and 2066 series). This will enable some optimizations that are not @@ -251,8 +258,8 @@ config MARCH_Z900 config MARCH_Z990 bool "IBM zSeries model z890 and z990" - depends on !CC_IS_CLANG select HAVE_MARCH_Z990_FEATURES + depends on $(cc-option,-march=z990) help Select this to enable optimizations for model z890/z990 (2084 and 2086 series). The kernel will be slightly faster but will not work @@ -260,8 +267,8 @@ config MARCH_Z990 config MARCH_Z9_109 bool "IBM System z9" - depends on !CC_IS_CLANG select HAVE_MARCH_Z9_109_FEATURES + depends on $(cc-option,-march=z9-109) help Select this to enable optimizations for IBM System z9 (2094 and 2096 series). The kernel will be slightly faster but will not work @@ -270,6 +277,7 @@ config MARCH_Z9_109 config MARCH_Z10 bool "IBM System z10" select HAVE_MARCH_Z10_FEATURES + depends on $(cc-option,-march=z10) help Select this to enable optimizations for IBM System z10 (2097 and 2098 series). The kernel will be slightly faster but will not work @@ -278,6 +286,7 @@ config MARCH_Z10 config MARCH_Z196 bool "IBM zEnterprise 114 and 196" select HAVE_MARCH_Z196_FEATURES + depends on $(cc-option,-march=z196) help Select this to enable optimizations for IBM zEnterprise 114 and 196 (2818 and 2817 series). The kernel will be slightly faster but will @@ -286,6 +295,7 @@ config MARCH_Z196 config MARCH_ZEC12 bool "IBM zBC12 and zEC12" select HAVE_MARCH_ZEC12_FEATURES + depends on $(cc-option,-march=zEC12) help Select this to enable optimizations for IBM zBC12 and zEC12 (2828 and 2827 series). The kernel will be slightly faster but will not work on @@ -294,6 +304,7 @@ config MARCH_ZEC12 config MARCH_Z13 bool "IBM z13s and z13" select HAVE_MARCH_Z13_FEATURES + depends on $(cc-option,-march=z13) help Select this to enable optimizations for IBM z13s and z13 (2965 and 2964 series). The kernel will be slightly faster but will not work on @@ -302,11 +313,21 @@ config MARCH_Z13 config MARCH_Z14 bool "IBM z14 ZR1 and z14" select HAVE_MARCH_Z14_FEATURES + depends on $(cc-option,-march=z14) help Select this to enable optimizations for IBM z14 ZR1 and z14 (3907 and 3906 series). The kernel will be slightly faster but will not work on older machines. +config MARCH_Z15 + bool "IBM z15" + select HAVE_MARCH_Z15_FEATURES + depends on $(cc-option,-march=z15) + help + Select this to enable optimizations for IBM z15 (8562 + and 8561 series). The kernel will be slightly faster but will not + work on older machines. + endchoice config MARCH_Z900_TUNE @@ -333,6 +354,9 @@ config MARCH_Z13_TUNE config MARCH_Z14_TUNE def_bool TUNE_Z14 || MARCH_Z14 && TUNE_DEFAULT +config MARCH_Z15_TUNE + def_bool TUNE_Z15 || MARCH_Z15 && TUNE_DEFAULT + choice prompt "Tune code generation" default TUNE_DEFAULT @@ -352,30 +376,39 @@ config TUNE_DEFAULT config TUNE_Z900 bool "IBM zSeries model z800 and z900" - depends on !CC_IS_CLANG + depends on $(cc-option,-mtune=z900) config TUNE_Z990 bool "IBM zSeries model z890 and z990" - depends on !CC_IS_CLANG + depends on $(cc-option,-mtune=z990) config TUNE_Z9_109 bool "IBM System z9" - depends on !CC_IS_CLANG + depends on $(cc-option,-mtune=z9-109) config TUNE_Z10 bool "IBM System z10" + depends on $(cc-option,-mtune=z10) config TUNE_Z196 bool "IBM zEnterprise 114 and 196" + depends on $(cc-option,-mtune=z196) config TUNE_ZEC12 bool "IBM zBC12 and zEC12" + depends on $(cc-option,-mtune=zEC12) config TUNE_Z13 - bool "IBM z13" + bool "IBM z13s and z13" + depends on $(cc-option,-mtune=z13) config TUNE_Z14 - bool "IBM z14" + bool "IBM z14 ZR1 and z14" + depends on $(cc-option,-mtune=z14) + +config TUNE_Z15 + bool "IBM z15" + depends on $(cc-option,-mtune=z15) endchoice @@ -396,9 +429,6 @@ config COMPAT (and some other stuff like libraries and such) is needed for executing 31 bit applications. It is safe to say "Y". -config COMPAT_VDSO - def_bool COMPAT && !CC_IS_CLANG - config SYSVIPC_COMPAT def_bool y if COMPAT && SYSVIPC @@ -536,9 +566,9 @@ config ARCH_HAS_KEXEC_PURGATORY def_bool y depends on KEXEC_FILE -config KEXEC_VERIFY_SIG +config KEXEC_SIG bool "Verify kernel signature during kexec_file_load() syscall" - depends on KEXEC_FILE && SYSTEM_DATA_VERIFICATION + depends on KEXEC_FILE && MODULE_SIG_FORMAT help This option makes kernel signature verification mandatory for the kexec_file_load() syscall. @@ -988,3 +1018,17 @@ config S390_GUEST the KVM hypervisor. endmenu + +menu "Selftests" + +config S390_UNWIND_SELFTEST + def_tristate n + prompt "Test unwind functions" + help + This option enables s390 specific stack unwinder testing kernel + module. This option is not useful for distributions or general + kernels, but only for kernel developers working on architecture code. + + Say N if you are unsure. + +endmenu diff --git a/arch/s390/Makefile b/arch/s390/Makefile index e0bab7ed4123..e0e3a465bbfd 100644 --- a/arch/s390/Makefile +++ b/arch/s390/Makefile @@ -45,6 +45,7 @@ mflags-$(CONFIG_MARCH_Z196) := -march=z196 mflags-$(CONFIG_MARCH_ZEC12) := -march=zEC12 mflags-$(CONFIG_MARCH_Z13) := -march=z13 mflags-$(CONFIG_MARCH_Z14) := -march=z14 +mflags-$(CONFIG_MARCH_Z15) := -march=z15 export CC_FLAGS_MARCH := $(mflags-y) @@ -59,6 +60,7 @@ cflags-$(CONFIG_MARCH_Z196_TUNE) += -mtune=z196 cflags-$(CONFIG_MARCH_ZEC12_TUNE) += -mtune=zEC12 cflags-$(CONFIG_MARCH_Z13_TUNE) += -mtune=z13 cflags-$(CONFIG_MARCH_Z14_TUNE) += -mtune=z14 +cflags-$(CONFIG_MARCH_Z15_TUNE) += -mtune=z15 cflags-y += -Wa,-I$(srctree)/arch/$(ARCH)/include @@ -67,7 +69,7 @@ cflags-y += -Wa,-I$(srctree)/arch/$(ARCH)/include # cflags-$(CONFIG_FRAME_POINTER) += -fno-optimize-sibling-calls -ifeq ($(call cc-option-yn,-mpacked-stack),y) +ifeq ($(call cc-option-yn,-mpacked-stack -mbackchain -msoft-float),y) cflags-$(CONFIG_PACK_STACK) += -mpacked-stack -D__PACK_STACK aflags-$(CONFIG_PACK_STACK) += -D__PACK_STACK endif @@ -155,7 +157,6 @@ zfcpdump: vdso_install: $(Q)$(MAKE) $(build)=arch/$(ARCH)/kernel/vdso64 $@ - $(Q)$(MAKE) $(build)=arch/$(ARCH)/kernel/vdso32 $@ archclean: $(Q)$(MAKE) $(clean)=$(boot) diff --git a/arch/s390/boot/Makefile b/arch/s390/boot/Makefile index 4cf0bddb7d92..e2c47d3a1c89 100644 --- a/arch/s390/boot/Makefile +++ b/arch/s390/boot/Makefile @@ -36,7 +36,7 @@ CFLAGS_sclp_early_core.o += -I$(srctree)/drivers/s390/char obj-y := head.o als.o startup.o mem_detect.o ipl_parm.o ipl_report.o obj-y += string.o ebcdic.o sclp_early_core.o mem.o ipl_vmparm.o cmdline.o -obj-y += version.o ctype.o text_dma.o +obj-y += version.o pgm_check_info.o ctype.o text_dma.o obj-$(CONFIG_PROTECTED_VIRTUALIZATION_GUEST) += uv.o obj-$(CONFIG_RELOCATABLE) += machine_kexec_reloc.o obj-$(CONFIG_RANDOMIZE_BASE) += kaslr.o diff --git a/arch/s390/boot/boot.h b/arch/s390/boot/boot.h index 1c3b2b257637..2ea603f70c3b 100644 --- a/arch/s390/boot/boot.h +++ b/arch/s390/boot/boot.h @@ -10,6 +10,7 @@ void parse_boot_command_line(void); void setup_memory_end(void); void verify_facilities(void); void print_missing_facilities(void); +void print_pgm_check_info(void); unsigned long get_random_base(unsigned long safe_addr); extern int kaslr_enabled; diff --git a/arch/s390/boot/compressed/.gitignore b/arch/s390/boot/compressed/.gitignore index 45aeb4f08752..e72fcd7ecebb 100644 --- a/arch/s390/boot/compressed/.gitignore +++ b/arch/s390/boot/compressed/.gitignore @@ -1,5 +1,2 @@ -sizes.h vmlinux vmlinux.lds -vmlinux.scr.lds -vmlinux.bin.full diff --git a/arch/s390/boot/compressed/decompressor.c b/arch/s390/boot/compressed/decompressor.c index 45046630c56a..368fd372c875 100644 --- a/arch/s390/boot/compressed/decompressor.c +++ b/arch/s390/boot/compressed/decompressor.c @@ -30,13 +30,13 @@ extern unsigned char _compressed_start[]; extern unsigned char _compressed_end[]; #ifdef CONFIG_HAVE_KERNEL_BZIP2 -#define HEAP_SIZE 0x400000 +#define BOOT_HEAP_SIZE 0x400000 #else -#define HEAP_SIZE 0x10000 +#define BOOT_HEAP_SIZE 0x10000 #endif static unsigned long free_mem_ptr = (unsigned long) _end; -static unsigned long free_mem_end_ptr = (unsigned long) _end + HEAP_SIZE; +static unsigned long free_mem_end_ptr = (unsigned long) _end + BOOT_HEAP_SIZE; #ifdef CONFIG_KERNEL_GZIP #include "../../../../lib/decompress_inflate.c" @@ -62,7 +62,7 @@ static unsigned long free_mem_end_ptr = (unsigned long) _end + HEAP_SIZE; #include "../../../../lib/decompress_unxz.c" #endif -#define decompress_offset ALIGN((unsigned long)_end + HEAP_SIZE, PAGE_SIZE) +#define decompress_offset ALIGN((unsigned long)_end + BOOT_HEAP_SIZE, PAGE_SIZE) unsigned long mem_safe_offset(void) { diff --git a/arch/s390/boot/compressed/vmlinux.lds.S b/arch/s390/boot/compressed/vmlinux.lds.S index 635217eb3d91..44561b2c3712 100644 --- a/arch/s390/boot/compressed/vmlinux.lds.S +++ b/arch/s390/boot/compressed/vmlinux.lds.S @@ -37,9 +37,9 @@ SECTIONS * .dma section for code, data, ex_table that need to stay below 2 GB, * even when the kernel is relocate: above 2 GB. */ + . = ALIGN(PAGE_SIZE); _sdma = .; .dma.text : { - . = ALIGN(PAGE_SIZE); _stext_dma = .; *(.dma.text) . = ALIGN(PAGE_SIZE); @@ -52,6 +52,7 @@ SECTIONS _stop_dma_ex_table = .; } .dma.data : { *(.dma.data) } + . = ALIGN(PAGE_SIZE); _edma = .; BOOT_DATA diff --git a/arch/s390/boot/head.S b/arch/s390/boot/head.S index 2087bed6e60f..dae10961d072 100644 --- a/arch/s390/boot/head.S +++ b/arch/s390/boot/head.S @@ -60,8 +60,10 @@ __HEAD .long 0x02000690,0x60000050 .long 0x020006e0,0x20000050 - .org 0x1a0 + .org __LC_RST_NEW_PSW # 0x1a0 .quad 0,iplstart + .org __LC_PGM_NEW_PSW # 0x1d0 + .quad 0x0000000180000000,startup_pgm_check_handler .org 0x200 @@ -327,7 +329,7 @@ ENTRY(startup_kdump) .quad .Lduct # cr5: primary-aste origin .quad 0 # cr6: I/O interrupts .quad 0 # cr7: secondary space segment table - .quad 0 # cr8: access registers translation + .quad 0x0000000000008000 # cr8: access registers translation .quad 0 # cr9: tracing off .quad 0 # cr10: tracing off .quad 0 # cr11: tracing off @@ -352,6 +354,34 @@ ENTRY(startup_kdump) #include "head_kdump.S" # +# This program check is active immediately after kernel start +# and until early_pgm_check_handler is set in kernel/early.c +# It simply saves general/control registers and psw in +# the save area and does disabled wait with a faulty address. +# +ENTRY(startup_pgm_check_handler) + stmg %r0,%r15,__LC_SAVE_AREA_SYNC + la %r1,4095 + stctg %c0,%c15,__LC_CREGS_SAVE_AREA-4095(%r1) + mvc __LC_GPREGS_SAVE_AREA-4095(128,%r1),__LC_SAVE_AREA_SYNC + mvc __LC_PSW_SAVE_AREA-4095(16,%r1),__LC_PGM_OLD_PSW + mvc __LC_RETURN_PSW(16),__LC_PGM_OLD_PSW + ni __LC_RETURN_PSW,0xfc # remove IO and EX bits + ni __LC_RETURN_PSW+1,0xfb # remove MCHK bit + oi __LC_RETURN_PSW+1,0x2 # set wait state bit + larl %r2,.Lold_psw_disabled_wait + stg %r2,__LC_PGM_NEW_PSW+8 + l %r15,.Ldump_info_stack-.Lold_psw_disabled_wait(%r2) + brasl %r14,print_pgm_check_info +.Lold_psw_disabled_wait: + la %r1,4095 + lmg %r0,%r15,__LC_GPREGS_SAVE_AREA-4095(%r1) + lpswe __LC_RETURN_PSW # disabled wait +.Ldump_info_stack: + .long 0x5000 + PAGE_SIZE - STACK_FRAME_OVERHEAD +ENDPROC(startup_pgm_check_handler) + +# # params at 10400 (setup.h) # Must be keept in sync with struct parmarea in setup.h # diff --git a/arch/s390/boot/ipl_parm.c b/arch/s390/boot/ipl_parm.c index b8aa6a9f937b..357adad991d2 100644 --- a/arch/s390/boot/ipl_parm.c +++ b/arch/s390/boot/ipl_parm.c @@ -7,13 +7,16 @@ #include <asm/sections.h> #include <asm/boot_data.h> #include <asm/facility.h> +#include <asm/pgtable.h> #include <asm/uv.h> #include "boot.h" char __bootdata(early_command_line)[COMMAND_LINE_SIZE]; struct ipl_parameter_block __bootdata_preserved(ipl_block); int __bootdata_preserved(ipl_block_valid); +unsigned int __bootdata_preserved(zlib_dfltcc_support) = ZLIB_DFLTCC_FULL; +unsigned long __bootdata(vmalloc_size) = VMALLOC_DEFAULT_SIZE; unsigned long __bootdata(memory_end); int __bootdata(memory_end_set); int __bootdata(noexec_disabled); @@ -219,18 +222,34 @@ void parse_boot_command_line(void) while (*args) { args = next_arg(args, ¶m, &val); - if (!strcmp(param, "mem")) { - memory_end = memparse(val, NULL); + if (!strcmp(param, "mem") && val) { + memory_end = round_down(memparse(val, NULL), PAGE_SIZE); memory_end_set = 1; } + if (!strcmp(param, "vmalloc") && val) + vmalloc_size = round_up(memparse(val, NULL), PAGE_SIZE); + + if (!strcmp(param, "dfltcc")) { + if (!strcmp(val, "off")) + zlib_dfltcc_support = ZLIB_DFLTCC_DISABLED; + else if (!strcmp(val, "on")) + zlib_dfltcc_support = ZLIB_DFLTCC_FULL; + else if (!strcmp(val, "def_only")) + zlib_dfltcc_support = ZLIB_DFLTCC_DEFLATE_ONLY; + else if (!strcmp(val, "inf_only")) + zlib_dfltcc_support = ZLIB_DFLTCC_INFLATE_ONLY; + else if (!strcmp(val, "always")) + zlib_dfltcc_support = ZLIB_DFLTCC_FULL_DEBUG; + } + if (!strcmp(param, "noexec")) { rc = kstrtobool(val, &enabled); if (!rc && !enabled) noexec_disabled = 1; } - if (!strcmp(param, "facilities")) + if (!strcmp(param, "facilities") && val) modify_fac_list(val); if (!strcmp(param, "nokaslr")) diff --git a/arch/s390/boot/kaslr.c b/arch/s390/boot/kaslr.c index c34a6387ce38..5d12352545c5 100644 --- a/arch/s390/boot/kaslr.c +++ b/arch/s390/boot/kaslr.c @@ -3,6 +3,7 @@ * Copyright IBM Corp. 2019 */ #include <asm/mem_detect.h> +#include <asm/pgtable.h> #include <asm/cpacf.h> #include <asm/timex.h> #include <asm/sclp.h> @@ -90,8 +91,10 @@ static unsigned long get_random(unsigned long limit) unsigned long get_random_base(unsigned long safe_addr) { + unsigned long memory_limit = memory_end_set ? memory_end : 0; unsigned long base, start, end, kernel_size; unsigned long block_sum, offset; + unsigned long kasan_needs; int i; if (IS_ENABLED(CONFIG_BLK_DEV_INITRD) && INITRD_START && INITRD_SIZE) { @@ -100,14 +103,36 @@ unsigned long get_random_base(unsigned long safe_addr) } safe_addr = ALIGN(safe_addr, THREAD_SIZE); + if ((IS_ENABLED(CONFIG_KASAN))) { + /* + * Estimate kasan memory requirements, which it will reserve + * at the very end of available physical memory. To estimate + * that, we take into account that kasan would require + * 1/8 of available physical memory (for shadow memory) + + * creating page tables for the whole memory + shadow memory + * region (1 + 1/8). To keep page tables estimates simple take + * the double of combined ptes size. + */ + memory_limit = get_mem_detect_end(); + if (memory_end_set && memory_limit > memory_end) + memory_limit = memory_end; + + /* for shadow memory */ + kasan_needs = memory_limit / 8; + /* for paging structures */ + kasan_needs += (memory_limit + kasan_needs) / PAGE_SIZE / + _PAGE_ENTRIES * _PAGE_TABLE_SIZE * 2; + memory_limit -= kasan_needs; + } + kernel_size = vmlinux.image_size + vmlinux.bss_size; block_sum = 0; for_each_mem_detect_block(i, &start, &end) { - if (memory_end_set) { - if (start >= memory_end) + if (memory_limit) { + if (start >= memory_limit) break; - if (end > memory_end) - end = memory_end; + if (end > memory_limit) + end = memory_limit; } if (end - start < kernel_size) continue; @@ -125,11 +150,11 @@ unsigned long get_random_base(unsigned long safe_addr) base = safe_addr; block_sum = offset = 0; for_each_mem_detect_block(i, &start, &end) { - if (memory_end_set) { - if (start >= memory_end) + if (memory_limit) { + if (start >= memory_limit) break; - if (end > memory_end) - end = memory_end; + if (end > memory_limit) + end = memory_limit; } if (end - start < kernel_size) continue; diff --git a/arch/s390/boot/mem_detect.c b/arch/s390/boot/mem_detect.c index 5d316fe40480..62e7c13ce85c 100644 --- a/arch/s390/boot/mem_detect.c +++ b/arch/s390/boot/mem_detect.c @@ -63,13 +63,6 @@ void add_mem_detect_block(u64 start, u64 end) mem_detect.count++; } -static unsigned long get_mem_detect_end(void) -{ - if (mem_detect.count) - return __get_mem_detect_block_ptr(mem_detect.count - 1)->end; - return 0; -} - static int __diag260(unsigned long rx1, unsigned long rx2) { register unsigned long _rx1 asm("2") = rx1; diff --git a/arch/s390/boot/pgm_check_info.c b/arch/s390/boot/pgm_check_info.c new file mode 100644 index 000000000000..83b5b7915c32 --- /dev/null +++ b/arch/s390/boot/pgm_check_info.c @@ -0,0 +1,90 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/kernel.h> +#include <linux/string.h> +#include <asm/lowcore.h> +#include <asm/sclp.h> +#include "boot.h" + +const char hex_asc[] = "0123456789abcdef"; + +#define add_val_as_hex(dst, val) \ + __add_val_as_hex(dst, (const unsigned char *)&val, sizeof(val)) + +static char *__add_val_as_hex(char *dst, const unsigned char *src, size_t count) +{ + while (count--) + dst = hex_byte_pack(dst, *src++); + return dst; +} + +static char *add_str(char *dst, char *src) +{ + strcpy(dst, src); + return dst + strlen(dst); +} + +void print_pgm_check_info(void) +{ + struct psw_bits *psw = &psw_bits(S390_lowcore.psw_save_area); + unsigned short ilc = S390_lowcore.pgm_ilc >> 1; + char buf[256]; + int row, col; + char *p; + + add_str(buf, "Linux version "); + strlcat(buf, kernel_version, sizeof(buf)); + sclp_early_printk(buf); + + p = add_str(buf, "Kernel fault: interruption code "); + p = add_val_as_hex(buf + strlen(buf), S390_lowcore.pgm_code); + p = add_str(p, " ilc:"); + *p++ = hex_asc_lo(ilc); + add_str(p, "\n"); + sclp_early_printk(buf); + + p = add_str(buf, "PSW : "); + p = add_val_as_hex(p, S390_lowcore.psw_save_area.mask); + p = add_str(p, " "); + p = add_val_as_hex(p, S390_lowcore.psw_save_area.addr); + add_str(p, "\n"); + sclp_early_printk(buf); + + p = add_str(buf, " R:"); + *p++ = hex_asc_lo(psw->per); + p = add_str(p, " T:"); + *p++ = hex_asc_lo(psw->dat); + p = add_str(p, " IO:"); + *p++ = hex_asc_lo(psw->io); + p = add_str(p, " EX:"); + *p++ = hex_asc_lo(psw->ext); + p = add_str(p, " Key:"); + *p++ = hex_asc_lo(psw->key); + p = add_str(p, " M:"); + *p++ = hex_asc_lo(psw->mcheck); + p = add_str(p, " W:"); + *p++ = hex_asc_lo(psw->wait); + p = add_str(p, " P:"); + *p++ = hex_asc_lo(psw->pstate); + p = add_str(p, " AS:"); + *p++ = hex_asc_lo(psw->as); + p = add_str(p, " CC:"); + *p++ = hex_asc_lo(psw->cc); + p = add_str(p, " PM:"); + *p++ = hex_asc_lo(psw->pm); + p = add_str(p, " RI:"); + *p++ = hex_asc_lo(psw->ri); + p = add_str(p, " EA:"); + *p++ = hex_asc_lo(psw->eaba); + add_str(p, "\n"); + sclp_early_printk(buf); + + for (row = 0; row < 4; row++) { + p = add_str(buf, row == 0 ? "GPRS:" : " "); + for (col = 0; col < 4; col++) { + p = add_str(p, " "); + p = add_val_as_hex(p, S390_lowcore.gpregs_save_area[row * 4 + col]); + } + add_str(p, "\n"); + sclp_early_printk(buf); + } +} diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c index 7b0d05414618..3b3a11f95269 100644 --- a/arch/s390/boot/startup.c +++ b/arch/s390/boot/startup.c @@ -46,7 +46,7 @@ struct diag_ops __bootdata_preserved(diag_dma_ops) = { .diag0c = _diag0c_dma, .diag308_reset = _diag308_reset_dma }; -static struct diag210 _diag210_tmp_dma __section(".dma.data"); +static struct diag210 _diag210_tmp_dma __section(.dma.data); struct diag210 *__bootdata_preserved(__diag210_tmp_dma) = &_diag210_tmp_dma; void _swsusp_reset_dma(void); unsigned long __bootdata_preserved(__swsusp_reset_dma) = __pa(_swsusp_reset_dma); @@ -101,10 +101,18 @@ static void handle_relocs(unsigned long offset) dynsym = (Elf64_Sym *) vmlinux.dynsym_start; for (rela = rela_start; rela < rela_end; rela++) { loc = rela->r_offset + offset; - val = rela->r_addend + offset; + val = rela->r_addend; r_sym = ELF64_R_SYM(rela->r_info); - if (r_sym) - val += dynsym[r_sym].st_value; + 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) @@ -112,6 +120,11 @@ static void handle_relocs(unsigned long offset) } } +static void clear_bss_section(void) +{ + memset((void *)vmlinux.default_lma + vmlinux.image_size, 0, vmlinux.bss_size); +} + void startup_kernel(void) { unsigned long random_lma; @@ -151,11 +164,17 @@ void startup_kernel(void) } else if (__kaslr_offset) memcpy((void *)vmlinux.default_lma, img, vmlinux.image_size); + clear_bss_section(); copy_bootdata(); if (IS_ENABLED(CONFIG_RELOCATABLE)) handle_relocs(__kaslr_offset); if (__kaslr_offset) { + /* + * 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 | 0x1UL; /* Clear non-relocated kernel */ if (IS_ENABLED(CONFIG_KERNEL_UNCOMPRESSED)) memset(img, 0, vmlinux.image_size); diff --git a/arch/s390/boot/uv.c b/arch/s390/boot/uv.c index ed007f4a6444..3f501159ee9f 100644 --- a/arch/s390/boot/uv.c +++ b/arch/s390/boot/uv.c @@ -15,7 +15,8 @@ void uv_query_info(void) if (!test_facility(158)) return; - if (uv_call(0, (uint64_t)&uvcb)) + /* rc==0x100 means that there is additional data we do not process */ + if (uv_call(0, (uint64_t)&uvcb) && uvcb.header.rc != 0x100) return; if (test_bit_inv(BIT_UVC_CMD_SET_SHARED_ACCESS, (unsigned long *)uvcb.inst_calls_list) && diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index 74e78ec5beb6..2e60c80395ab 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -44,6 +44,7 @@ CONFIG_NR_CPUS=512 CONFIG_NUMA=y CONFIG_HZ_100=y CONFIG_KEXEC_FILE=y +CONFIG_KEXEC_SIG=y CONFIG_EXPOLINE=y CONFIG_EXPOLINE_AUTO=y CONFIG_CHSC_SCH=y @@ -61,7 +62,6 @@ CONFIG_OPROFILE=m CONFIG_KPROBES=y CONFIG_JUMP_LABEL=y CONFIG_STATIC_KEYS_SELFTEST=y -CONFIG_REFCOUNT_FULL=y CONFIG_LOCK_EVENT_COUNTS=y CONFIG_MODULES=y CONFIG_MODULE_FORCE_LOAD=y @@ -69,12 +69,13 @@ CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y CONFIG_MODVERSIONS=y CONFIG_MODULE_SRCVERSION_ALL=y -CONFIG_MODULE_SIG=y CONFIG_MODULE_SIG_SHA256=y +CONFIG_UNUSED_SYMBOLS=y CONFIG_BLK_DEV_INTEGRITY=y CONFIG_BLK_DEV_THROTTLING=y CONFIG_BLK_WBT=y CONFIG_BLK_CGROUP_IOLATENCY=y +CONFIG_BLK_CGROUP_IOCOST=y CONFIG_PARTITION_ADVANCED=y CONFIG_IBM_PARTITION=y CONFIG_BSD_DISKLABEL=y @@ -370,6 +371,7 @@ CONFIG_NETLINK_DIAG=m CONFIG_CGROUP_NET_PRIO=y CONFIG_BPF_JIT=y CONFIG_NET_PKTGEN=m +# CONFIG_NET_DROP_MONITOR is not set CONFIG_PCI=y CONFIG_PCI_DEBUG=y CONFIG_HOTPLUG_PCI=y @@ -424,6 +426,7 @@ CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m CONFIG_DM_THIN_PROVISIONING=m CONFIG_DM_WRITECACHE=m +CONFIG_DM_CLONE=m CONFIG_DM_MIRROR=m CONFIG_DM_LOG_USERSPACE=m CONFIG_DM_RAID=m @@ -435,6 +438,7 @@ CONFIG_DM_DELAY=m CONFIG_DM_UEVENT=y CONFIG_DM_FLAKEY=m CONFIG_DM_VERITY=m +CONFIG_DM_VERITY_VERIFY_ROOTHASH_SIG=y CONFIG_DM_SWITCH=m CONFIG_NETDEVICES=y CONFIG_BONDING=m @@ -489,6 +493,7 @@ CONFIG_MLX5_CORE_EN=y # CONFIG_NET_VENDOR_NVIDIA is not set # CONFIG_NET_VENDOR_OKI is not set # CONFIG_NET_VENDOR_PACKET_ENGINES is not set +# CONFIG_NET_VENDOR_PENSANDO is not set # CONFIG_NET_VENDOR_QLOGIC is not set # CONFIG_NET_VENDOR_QUALCOMM is not set # CONFIG_NET_VENDOR_RDC is not set @@ -538,15 +543,16 @@ CONFIG_WATCHDOG=y CONFIG_WATCHDOG_NOWAYOUT=y CONFIG_SOFT_WATCHDOG=m CONFIG_DIAG288_WATCHDOG=m -CONFIG_DRM=y -CONFIG_DRM_VIRTIO_GPU=y +CONFIG_FB=y CONFIG_FRAMEBUFFER_CONSOLE=y +CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y # CONFIG_HID 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_VFIO_MDEV=m @@ -580,6 +586,8 @@ CONFIG_NILFS2_FS=m CONFIG_FS_DAX=y CONFIG_EXPORTFS_BLOCK_OPS=y CONFIG_FS_ENCRYPTION=y +CONFIG_FS_VERITY=y +CONFIG_FS_VERITY_BUILTIN_SIGNATURES=y CONFIG_FANOTIFY=y CONFIG_FANOTIFY_ACCESS_PERMISSIONS=y CONFIG_QUOTA_NETLINK_INTERFACE=y @@ -589,6 +597,7 @@ CONFIG_QFMT_V2=m CONFIG_AUTOFS4_FS=m CONFIG_FUSE_FS=y CONFIG_CUSE=m +CONFIG_VIRTIO_FS=m CONFIG_OVERLAY_FS=m CONFIG_FSCACHE=m CONFIG_CACHEFILES=m @@ -648,12 +657,15 @@ CONFIG_FORTIFY_SOURCE=y CONFIG_SECURITY_SELINUX=y CONFIG_SECURITY_SELINUX_BOOTPARAM=y CONFIG_SECURITY_SELINUX_DISABLE=y +CONFIG_SECURITY_LOCKDOWN_LSM=y +CONFIG_SECURITY_LOCKDOWN_LSM_EARLY=y CONFIG_INTEGRITY_SIGNATURE=y CONFIG_INTEGRITY_ASYMMETRIC_KEYS=y CONFIG_IMA=y CONFIG_IMA_DEFAULT_HASH_SHA256=y CONFIG_IMA_WRITE_POLICY=y CONFIG_IMA_APPRAISE=y +CONFIG_LSM="yama,loadpin,safesetid,integrity,selinux,smack,tomoyo,apparmor" CONFIG_CRYPTO_USER=m # CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set CONFIG_CRYPTO_PCRYPT=m @@ -664,10 +676,6 @@ CONFIG_CRYPTO_ECDH=m CONFIG_CRYPTO_ECRDSA=m CONFIG_CRYPTO_CHACHA20POLY1305=m CONFIG_CRYPTO_AEGIS128=m -CONFIG_CRYPTO_AEGIS128L=m -CONFIG_CRYPTO_AEGIS256=m -CONFIG_CRYPTO_MORUS640=m -CONFIG_CRYPTO_MORUS1280=m CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m @@ -717,6 +725,8 @@ CONFIG_CRYPTO_PAES_S390=m CONFIG_CRYPTO_SHA1_S390=m CONFIG_CRYPTO_SHA256_S390=m CONFIG_CRYPTO_SHA512_S390=m +CONFIG_CRYPTO_SHA3_256_S390=m +CONFIG_CRYPTO_SHA3_512_S390=m CONFIG_CRYPTO_DES_S390=m CONFIG_CRYPTO_AES_S390=m CONFIG_CRYPTO_GHASH_S390=m @@ -737,7 +747,6 @@ CONFIG_DEBUG_INFO=y CONFIG_DEBUG_INFO_DWARF4=y CONFIG_GDB_SCRIPTS=y CONFIG_FRAME_WARN=1024 -CONFIG_UNUSED_SYMBOLS=y CONFIG_HEADERS_INSTALL=y CONFIG_HEADERS_CHECK=y CONFIG_DEBUG_SECTION_MISMATCH=y diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index 68d3ca83302b..25f799849582 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -44,6 +44,7 @@ CONFIG_NUMA=y # CONFIG_NUMA_EMU is not set CONFIG_HZ_100=y CONFIG_KEXEC_FILE=y +CONFIG_KEXEC_SIG=y CONFIG_EXPOLINE=y CONFIG_EXPOLINE_AUTO=y CONFIG_CHSC_SCH=y @@ -66,11 +67,12 @@ CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y CONFIG_MODVERSIONS=y CONFIG_MODULE_SRCVERSION_ALL=y -CONFIG_MODULE_SIG=y CONFIG_MODULE_SIG_SHA256=y +CONFIG_UNUSED_SYMBOLS=y CONFIG_BLK_DEV_THROTTLING=y CONFIG_BLK_WBT=y CONFIG_BLK_CGROUP_IOLATENCY=y +CONFIG_BLK_CGROUP_IOCOST=y CONFIG_PARTITION_ADVANCED=y CONFIG_IBM_PARTITION=y CONFIG_BSD_DISKLABEL=y @@ -363,6 +365,7 @@ CONFIG_NETLINK_DIAG=m CONFIG_CGROUP_NET_PRIO=y CONFIG_BPF_JIT=y CONFIG_NET_PKTGEN=m +# CONFIG_NET_DROP_MONITOR is not set CONFIG_PCI=y CONFIG_HOTPLUG_PCI=y CONFIG_HOTPLUG_PCI_S390=y @@ -418,6 +421,7 @@ CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m CONFIG_DM_THIN_PROVISIONING=m CONFIG_DM_WRITECACHE=m +CONFIG_DM_CLONE=m CONFIG_DM_MIRROR=m CONFIG_DM_LOG_USERSPACE=m CONFIG_DM_RAID=m @@ -429,6 +433,7 @@ CONFIG_DM_DELAY=m CONFIG_DM_UEVENT=y CONFIG_DM_FLAKEY=m CONFIG_DM_VERITY=m +CONFIG_DM_VERITY_VERIFY_ROOTHASH_SIG=y CONFIG_DM_SWITCH=m CONFIG_DM_INTEGRITY=m CONFIG_NETDEVICES=y @@ -484,6 +489,7 @@ CONFIG_MLX5_CORE_EN=y # CONFIG_NET_VENDOR_NVIDIA is not set # CONFIG_NET_VENDOR_OKI is not set # CONFIG_NET_VENDOR_PACKET_ENGINES is not set +# CONFIG_NET_VENDOR_PENSANDO is not set # CONFIG_NET_VENDOR_QLOGIC is not set # CONFIG_NET_VENDOR_QUALCOMM is not set # CONFIG_NET_VENDOR_RDC is not set @@ -533,16 +539,16 @@ CONFIG_WATCHDOG_CORE=y CONFIG_WATCHDOG_NOWAYOUT=y CONFIG_SOFT_WATCHDOG=m CONFIG_DIAG288_WATCHDOG=m -CONFIG_DRM=y -CONFIG_DRM_VIRTIO_GPU=y -# CONFIG_BACKLIGHT_CLASS_DEVICE is not set +CONFIG_FB=y CONFIG_FRAMEBUFFER_CONSOLE=y +CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y # CONFIG_HID 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_VFIO_MDEV=m @@ -573,6 +579,8 @@ CONFIG_NILFS2_FS=m CONFIG_FS_DAX=y CONFIG_EXPORTFS_BLOCK_OPS=y CONFIG_FS_ENCRYPTION=y +CONFIG_FS_VERITY=y +CONFIG_FS_VERITY_BUILTIN_SIGNATURES=y CONFIG_FANOTIFY=y CONFIG_FANOTIFY_ACCESS_PERMISSIONS=y CONFIG_QUOTA_NETLINK_INTERFACE=y @@ -581,6 +589,7 @@ CONFIG_QFMT_V2=m CONFIG_AUTOFS4_FS=m CONFIG_FUSE_FS=y CONFIG_CUSE=m +CONFIG_VIRTIO_FS=m CONFIG_OVERLAY_FS=m CONFIG_FSCACHE=m CONFIG_CACHEFILES=m @@ -639,12 +648,15 @@ CONFIG_SECURITY_NETWORK=y CONFIG_SECURITY_SELINUX=y CONFIG_SECURITY_SELINUX_BOOTPARAM=y CONFIG_SECURITY_SELINUX_DISABLE=y +CONFIG_SECURITY_LOCKDOWN_LSM=y +CONFIG_SECURITY_LOCKDOWN_LSM_EARLY=y CONFIG_INTEGRITY_SIGNATURE=y CONFIG_INTEGRITY_ASYMMETRIC_KEYS=y CONFIG_IMA=y CONFIG_IMA_DEFAULT_HASH_SHA256=y CONFIG_IMA_WRITE_POLICY=y CONFIG_IMA_APPRAISE=y +CONFIG_LSM="yama,loadpin,safesetid,integrity,selinux,smack,tomoyo,apparmor" CONFIG_CRYPTO_FIPS=y CONFIG_CRYPTO_USER=m # CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set @@ -656,10 +668,6 @@ CONFIG_CRYPTO_ECDH=m CONFIG_CRYPTO_ECRDSA=m CONFIG_CRYPTO_CHACHA20POLY1305=m CONFIG_CRYPTO_AEGIS128=m -CONFIG_CRYPTO_AEGIS128L=m -CONFIG_CRYPTO_AEGIS256=m -CONFIG_CRYPTO_MORUS640=m -CONFIG_CRYPTO_MORUS1280=m CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_OFB=m @@ -710,6 +718,8 @@ CONFIG_CRYPTO_PAES_S390=m CONFIG_CRYPTO_SHA1_S390=m CONFIG_CRYPTO_SHA256_S390=m CONFIG_CRYPTO_SHA512_S390=m +CONFIG_CRYPTO_SHA3_256_S390=m +CONFIG_CRYPTO_SHA3_512_S390=m CONFIG_CRYPTO_DES_S390=m CONFIG_CRYPTO_AES_S390=m CONFIG_CRYPTO_GHASH_S390=m @@ -725,7 +735,6 @@ CONFIG_DEBUG_INFO=y CONFIG_DEBUG_INFO_DWARF4=y CONFIG_GDB_SCRIPTS=y CONFIG_FRAME_WARN=1024 -CONFIG_UNUSED_SYMBOLS=y CONFIG_DEBUG_SECTION_MISMATCH=y CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_MEMORY_INIT=y diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig index be09a208b608..20c51e5d9353 100644 --- a/arch/s390/configs/zfcpdump_defconfig +++ b/arch/s390/configs/zfcpdump_defconfig @@ -61,7 +61,7 @@ CONFIG_RAW_DRIVER=y CONFIG_CONFIGFS_FS=y # CONFIG_MISC_FILESYSTEMS is not set # CONFIG_NETWORK_FILESYSTEMS is not set -# CONFIG_DIMLIB is not set +CONFIG_LSM="yama,loadpin,safesetid,integrity" CONFIG_PRINTK_TIME=y CONFIG_DEBUG_INFO=y CONFIG_DEBUG_FS=y diff --git a/arch/s390/crypto/Makefile b/arch/s390/crypto/Makefile index a51010ea62fa..12889d4652cc 100644 --- a/arch/s390/crypto/Makefile +++ b/arch/s390/crypto/Makefile @@ -6,6 +6,8 @@ obj-$(CONFIG_CRYPTO_SHA1_S390) += sha1_s390.o sha_common.o obj-$(CONFIG_CRYPTO_SHA256_S390) += sha256_s390.o sha_common.o obj-$(CONFIG_CRYPTO_SHA512_S390) += sha512_s390.o sha_common.o +obj-$(CONFIG_CRYPTO_SHA3_256_S390) += sha3_256_s390.o sha_common.o +obj-$(CONFIG_CRYPTO_SHA3_512_S390) += sha3_512_s390.o sha_common.o obj-$(CONFIG_CRYPTO_DES_S390) += des_s390.o obj-$(CONFIG_CRYPTO_AES_S390) += aes_s390.o obj-$(CONFIG_CRYPTO_PAES_S390) += paes_s390.o diff --git a/arch/s390/crypto/aes_s390.c b/arch/s390/crypto/aes_s390.c index d00f84add5f4..1c23d84a9097 100644 --- a/arch/s390/crypto/aes_s390.c +++ b/arch/s390/crypto/aes_s390.c @@ -44,7 +44,7 @@ struct s390_aes_ctx { int key_len; unsigned long fc; union { - struct crypto_sync_skcipher *blk; + struct crypto_skcipher *skcipher; struct crypto_cipher *cip; } fallback; }; @@ -54,7 +54,7 @@ struct s390_xts_ctx { u8 pcc_key[32]; int key_len; unsigned long fc; - struct crypto_sync_skcipher *fallback; + struct crypto_skcipher *fallback; }; struct gcm_sg_walk { @@ -72,19 +72,12 @@ static int setkey_fallback_cip(struct crypto_tfm *tfm, const u8 *in_key, unsigned int key_len) { struct s390_aes_ctx *sctx = crypto_tfm_ctx(tfm); - int ret; sctx->fallback.cip->base.crt_flags &= ~CRYPTO_TFM_REQ_MASK; sctx->fallback.cip->base.crt_flags |= (tfm->crt_flags & CRYPTO_TFM_REQ_MASK); - ret = crypto_cipher_setkey(sctx->fallback.cip, in_key, key_len); - if (ret) { - tfm->crt_flags &= ~CRYPTO_TFM_RES_MASK; - tfm->crt_flags |= (sctx->fallback.cip->base.crt_flags & - CRYPTO_TFM_RES_MASK); - } - return ret; + return crypto_cipher_setkey(sctx->fallback.cip, in_key, key_len); } static int aes_set_key(struct crypto_tfm *tfm, const u8 *in_key, @@ -108,7 +101,7 @@ static int aes_set_key(struct crypto_tfm *tfm, const u8 *in_key, return 0; } -static void aes_encrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in) +static void crypto_aes_encrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in) { struct s390_aes_ctx *sctx = crypto_tfm_ctx(tfm); @@ -119,7 +112,7 @@ static void aes_encrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in) cpacf_km(sctx->fc, &sctx->key, out, in, AES_BLOCK_SIZE); } -static void aes_decrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in) +static void crypto_aes_decrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in) { struct s390_aes_ctx *sctx = crypto_tfm_ctx(tfm); @@ -172,72 +165,42 @@ static struct crypto_alg aes_alg = { .cia_min_keysize = AES_MIN_KEY_SIZE, .cia_max_keysize = AES_MAX_KEY_SIZE, .cia_setkey = aes_set_key, - .cia_encrypt = aes_encrypt, - .cia_decrypt = aes_decrypt, + .cia_encrypt = crypto_aes_encrypt, + .cia_decrypt = crypto_aes_decrypt, } } }; -static int setkey_fallback_blk(struct crypto_tfm *tfm, const u8 *key, - unsigned int len) -{ - struct s390_aes_ctx *sctx = crypto_tfm_ctx(tfm); - unsigned int ret; - - crypto_sync_skcipher_clear_flags(sctx->fallback.blk, - CRYPTO_TFM_REQ_MASK); - crypto_sync_skcipher_set_flags(sctx->fallback.blk, tfm->crt_flags & - CRYPTO_TFM_REQ_MASK); - - ret = crypto_sync_skcipher_setkey(sctx->fallback.blk, key, len); - - tfm->crt_flags &= ~CRYPTO_TFM_RES_MASK; - tfm->crt_flags |= crypto_sync_skcipher_get_flags(sctx->fallback.blk) & - CRYPTO_TFM_RES_MASK; - - return ret; -} - -static int fallback_blk_dec(struct blkcipher_desc *desc, - struct scatterlist *dst, struct scatterlist *src, - unsigned int nbytes) +static int setkey_fallback_skcipher(struct crypto_skcipher *tfm, const u8 *key, + unsigned int len) { - unsigned int ret; - struct crypto_blkcipher *tfm = desc->tfm; - struct s390_aes_ctx *sctx = crypto_blkcipher_ctx(tfm); - SYNC_SKCIPHER_REQUEST_ON_STACK(req, sctx->fallback.blk); - - skcipher_request_set_sync_tfm(req, sctx->fallback.blk); - skcipher_request_set_callback(req, desc->flags, NULL, NULL); - skcipher_request_set_crypt(req, src, dst, nbytes, desc->info); - - ret = crypto_skcipher_decrypt(req); - - skcipher_request_zero(req); - return ret; + struct s390_aes_ctx *sctx = crypto_skcipher_ctx(tfm); + + crypto_skcipher_clear_flags(sctx->fallback.skcipher, + CRYPTO_TFM_REQ_MASK); + crypto_skcipher_set_flags(sctx->fallback.skcipher, + crypto_skcipher_get_flags(tfm) & + CRYPTO_TFM_REQ_MASK); + return crypto_skcipher_setkey(sctx->fallback.skcipher, key, len); } -static int fallback_blk_enc(struct blkcipher_desc *desc, - struct scatterlist *dst, struct scatterlist *src, - unsigned int nbytes) +static int fallback_skcipher_crypt(struct s390_aes_ctx *sctx, + struct skcipher_request *req, + unsigned long modifier) { - unsigned int ret; - struct crypto_blkcipher *tfm = desc->tfm; - struct s390_aes_ctx *sctx = crypto_blkcipher_ctx(tfm); - SYNC_SKCIPHER_REQUEST_ON_STACK(req, sctx->fallback.blk); + struct skcipher_request *subreq = skcipher_request_ctx(req); - skcipher_request_set_sync_tfm(req, sctx->fallback.blk); - skcipher_request_set_callback(req, desc->flags, NULL, NULL); - skcipher_request_set_crypt(req, src, dst, nbytes, desc->info); - - ret = crypto_skcipher_encrypt(req); - return ret; + *subreq = *req; + skcipher_request_set_tfm(subreq, sctx->fallback.skcipher); + return (modifier & CPACF_DECRYPT) ? + crypto_skcipher_decrypt(subreq) : + crypto_skcipher_encrypt(subreq); } -static int ecb_aes_set_key(struct crypto_tfm *tfm, const u8 *in_key, +static int ecb_aes_set_key(struct crypto_skcipher *tfm, const u8 *in_key, unsigned int key_len) { - struct s390_aes_ctx *sctx = crypto_tfm_ctx(tfm); + struct s390_aes_ctx *sctx = crypto_skcipher_ctx(tfm); unsigned long fc; /* Pick the correct function code based on the key length */ @@ -248,111 +211,92 @@ static int ecb_aes_set_key(struct crypto_tfm *tfm, const u8 *in_key, /* Check if the function code is available */ sctx->fc = (fc && cpacf_test_func(&km_functions, fc)) ? fc : 0; if (!sctx->fc) - return setkey_fallback_blk(tfm, in_key, key_len); + return setkey_fallback_skcipher(tfm, in_key, key_len); sctx->key_len = key_len; memcpy(sctx->key, in_key, key_len); return 0; } -static int ecb_aes_crypt(struct blkcipher_desc *desc, unsigned long modifier, - struct blkcipher_walk *walk) +static int ecb_aes_crypt(struct skcipher_request *req, unsigned long modifier) { - struct s390_aes_ctx *sctx = crypto_blkcipher_ctx(desc->tfm); + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct s390_aes_ctx *sctx = crypto_skcipher_ctx(tfm); + struct skcipher_walk walk; unsigned int nbytes, n; int ret; - ret = blkcipher_walk_virt(desc, walk); - while ((nbytes = walk->nbytes) >= AES_BLOCK_SIZE) { + if (unlikely(!sctx->fc)) + return fallback_skcipher_crypt(sctx, req, modifier); + + ret = skcipher_walk_virt(&walk, req, false); + while ((nbytes = walk.nbytes) != 0) { /* only use complete blocks */ n = nbytes & ~(AES_BLOCK_SIZE - 1); cpacf_km(sctx->fc | modifier, sctx->key, - walk->dst.virt.addr, walk->src.virt.addr, n); - ret = blkcipher_walk_done(desc, walk, nbytes - n); + walk.dst.virt.addr, walk.src.virt.addr, n); + ret = skcipher_walk_done(&walk, nbytes - n); } - return ret; } -static int ecb_aes_encrypt(struct blkcipher_desc *desc, - struct scatterlist *dst, struct scatterlist *src, - unsigned int nbytes) +static int ecb_aes_encrypt(struct skcipher_request *req) { - struct s390_aes_ctx *sctx = crypto_blkcipher_ctx(desc->tfm); - struct blkcipher_walk walk; - - if (unlikely(!sctx->fc)) - return fallback_blk_enc(desc, dst, src, nbytes); - - blkcipher_walk_init(&walk, dst, src, nbytes); - return ecb_aes_crypt(desc, 0, &walk); + return ecb_aes_crypt(req, 0); } -static int ecb_aes_decrypt(struct blkcipher_desc *desc, - struct scatterlist *dst, struct scatterlist *src, - unsigned int nbytes) +static int ecb_aes_decrypt(struct skcipher_request *req) { - struct s390_aes_ctx *sctx = crypto_blkcipher_ctx(desc->tfm); - struct blkcipher_walk walk; - - if (unlikely(!sctx->fc)) - return fallback_blk_dec(desc, dst, src, nbytes); - - blkcipher_walk_init(&walk, dst, src, nbytes); - return ecb_aes_crypt(desc, CPACF_DECRYPT, &walk); + return ecb_aes_crypt(req, CPACF_DECRYPT); } -static int fallback_init_blk(struct crypto_tfm *tfm) +static int fallback_init_skcipher(struct crypto_skcipher *tfm) { - const char *name = tfm->__crt_alg->cra_name; - struct s390_aes_ctx *sctx = crypto_tfm_ctx(tfm); + const char *name = crypto_tfm_alg_name(&tfm->base); + struct s390_aes_ctx *sctx = crypto_skcipher_ctx(tfm); - sctx->fallback.blk = crypto_alloc_sync_skcipher(name, 0, - CRYPTO_ALG_NEED_FALLBACK); + sctx->fallback.skcipher = crypto_alloc_skcipher(name, 0, + CRYPTO_ALG_NEED_FALLBACK | CRYPTO_ALG_ASYNC); - if (IS_ERR(sctx->fallback.blk)) { + if (IS_ERR(sctx->fallback.skcipher)) { pr_err("Allocating AES fallback algorithm %s failed\n", name); - return PTR_ERR(sctx->fallback.blk); + return PTR_ERR(sctx->fallback.skcipher); } + crypto_skcipher_set_reqsize(tfm, sizeof(struct skcipher_request) + + crypto_skcipher_reqsize(sctx->fallback.skcipher)); return 0; } -static void fallback_exit_blk(struct crypto_tfm *tfm) +static void fallback_exit_skcipher(struct crypto_skcipher *tfm) { - struct s390_aes_ctx *sctx = crypto_tfm_ctx(tfm); + struct s390_aes_ctx *sctx = crypto_skcipher_ctx(tfm); - crypto_free_sync_skcipher(sctx->fallback.blk); + crypto_free_skcipher(sctx->fallback.skcipher); } -static struct crypto_alg ecb_aes_alg = { - .cra_name = "ecb(aes)", - .cra_driver_name = "ecb-aes-s390", - .cra_priority = 401, /* combo: aes + ecb + 1 */ - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | - CRYPTO_ALG_NEED_FALLBACK, - .cra_blocksize = AES_BLOCK_SIZE, - .cra_ctxsize = sizeof(struct s390_aes_ctx), - .cra_type = &crypto_blkcipher_type, - .cra_module = THIS_MODULE, - .cra_init = fallback_init_blk, - .cra_exit = fallback_exit_blk, - .cra_u = { - .blkcipher = { - .min_keysize = AES_MIN_KEY_SIZE, - .max_keysize = AES_MAX_KEY_SIZE, - .setkey = ecb_aes_set_key, - .encrypt = ecb_aes_encrypt, - .decrypt = ecb_aes_decrypt, - } - } +static struct skcipher_alg ecb_aes_alg = { + .base.cra_name = "ecb(aes)", + .base.cra_driver_name = "ecb-aes-s390", + .base.cra_priority = 401, /* combo: aes + ecb + 1 */ + .base.cra_flags = CRYPTO_ALG_NEED_FALLBACK, + .base.cra_blocksize = AES_BLOCK_SIZE, + .base.cra_ctxsize = sizeof(struct s390_aes_ctx), + .base.cra_module = THIS_MODULE, + .init = fallback_init_skcipher, + .exit = fallback_exit_skcipher, + .min_keysize = AES_MIN_KEY_SIZE, + .max_keysize = AES_MAX_KEY_SIZE, + .setkey = ecb_aes_set_key, + .encrypt = ecb_aes_encrypt, + .decrypt = ecb_aes_decrypt, }; -static int cbc_aes_set_key(struct crypto_tfm *tfm, const u8 *in_key, +static int cbc_aes_set_key(struct crypto_skcipher *tfm, const u8 *in_key, unsigned int key_len) { - struct s390_aes_ctx *sctx = crypto_tfm_ctx(tfm); + struct s390_aes_ctx *sctx = crypto_skcipher_ctx(tfm); unsigned long fc; /* Pick the correct function code based on the key length */ @@ -363,17 +307,18 @@ static int cbc_aes_set_key(struct crypto_tfm *tfm, const u8 *in_key, /* Check if the function code is available */ sctx->fc = (fc && cpacf_test_func(&kmc_functions, fc)) ? fc : 0; if (!sctx->fc) - return setkey_fallback_blk(tfm, in_key, key_len); + return setkey_fallback_skcipher(tfm, in_key, key_len); sctx->key_len = key_len; memcpy(sctx->key, in_key, key_len); return 0; } -static int cbc_aes_crypt(struct blkcipher_desc *desc, unsigned long modifier, - struct blkcipher_walk *walk) +static int cbc_aes_crypt(struct skcipher_request *req, unsigned long modifier) { - struct s390_aes_ctx *sctx = crypto_blkcipher_ctx(desc->tfm); + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct s390_aes_ctx *sctx = crypto_skcipher_ctx(tfm); + struct skcipher_walk walk; unsigned int nbytes, n; int ret; struct { @@ -381,146 +326,79 @@ static int cbc_aes_crypt(struct blkcipher_desc *desc, unsigned long modifier, u8 key[AES_MAX_KEY_SIZE]; } param; - ret = blkcipher_walk_virt(desc, walk); - memcpy(param.iv, walk->iv, AES_BLOCK_SIZE); + if (unlikely(!sctx->fc)) + return fallback_skcipher_crypt(sctx, req, modifier); + + ret = skcipher_walk_virt(&walk, req, false); + if (ret) + return ret; + memcpy(param.iv, walk.iv, AES_BLOCK_SIZE); memcpy(param.key, sctx->key, sctx->key_len); - while ((nbytes = walk->nbytes) >= AES_BLOCK_SIZE) { + while ((nbytes = walk.nbytes) != 0) { /* only use complete blocks */ n = nbytes & ~(AES_BLOCK_SIZE - 1); cpacf_kmc(sctx->fc | modifier, ¶m, - walk->dst.virt.addr, walk->src.virt.addr, n); - ret = blkcipher_walk_done(desc, walk, nbytes - n); + walk.dst.virt.addr, walk.src.virt.addr, n); + memcpy(walk.iv, param.iv, AES_BLOCK_SIZE); + ret = skcipher_walk_done(&walk, nbytes - n); } - memcpy(walk->iv, param.iv, AES_BLOCK_SIZE); return ret; } -static int cbc_aes_encrypt(struct blkcipher_desc *desc, - struct scatterlist *dst, struct scatterlist *src, - unsigned int nbytes) +static int cbc_aes_encrypt(struct skcipher_request *req) { - struct s390_aes_ctx *sctx = crypto_blkcipher_ctx(desc->tfm); - struct blkcipher_walk walk; - - if (unlikely(!sctx->fc)) - return fallback_blk_enc(desc, dst, src, nbytes); - - blkcipher_walk_init(&walk, dst, src, nbytes); - return cbc_aes_crypt(desc, 0, &walk); + return cbc_aes_crypt(req, 0); } -static int cbc_aes_decrypt(struct blkcipher_desc *desc, - struct scatterlist *dst, struct scatterlist *src, - unsigned int nbytes) +static int cbc_aes_decrypt(struct skcipher_request *req) { - struct s390_aes_ctx *sctx = crypto_blkcipher_ctx(desc->tfm); - struct blkcipher_walk walk; - - if (unlikely(!sctx->fc)) - return fallback_blk_dec(desc, dst, src, nbytes); - - blkcipher_walk_init(&walk, dst, src, nbytes); - return cbc_aes_crypt(desc, CPACF_DECRYPT, &walk); + return cbc_aes_crypt(req, CPACF_DECRYPT); } -static struct crypto_alg cbc_aes_alg = { - .cra_name = "cbc(aes)", - .cra_driver_name = "cbc-aes-s390", - .cra_priority = 402, /* ecb-aes-s390 + 1 */ - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | - CRYPTO_ALG_NEED_FALLBACK, - .cra_blocksize = AES_BLOCK_SIZE, - .cra_ctxsize = sizeof(struct s390_aes_ctx), - .cra_type = &crypto_blkcipher_type, - .cra_module = THIS_MODULE, - .cra_init = fallback_init_blk, - .cra_exit = fallback_exit_blk, - .cra_u = { - .blkcipher = { - .min_keysize = AES_MIN_KEY_SIZE, - .max_keysize = AES_MAX_KEY_SIZE, - .ivsize = AES_BLOCK_SIZE, - .setkey = cbc_aes_set_key, - .encrypt = cbc_aes_encrypt, - .decrypt = cbc_aes_decrypt, - } - } +static struct skcipher_alg cbc_aes_alg = { + .base.cra_name = "cbc(aes)", + .base.cra_driver_name = "cbc-aes-s390", + .base.cra_priority = 402, /* ecb-aes-s390 + 1 */ + .base.cra_flags = CRYPTO_ALG_NEED_FALLBACK, + .base.cra_blocksize = AES_BLOCK_SIZE, + .base.cra_ctxsize = sizeof(struct s390_aes_ctx), + .base.cra_module = THIS_MODULE, + .init = fallback_init_skcipher, + .exit = fallback_exit_skcipher, + .min_keysize = AES_MIN_KEY_SIZE, + .max_keysize = AES_MAX_KEY_SIZE, + .ivsize = AES_BLOCK_SIZE, + .setkey = cbc_aes_set_key, + .encrypt = cbc_aes_encrypt, + .decrypt = cbc_aes_decrypt, }; -static int xts_fallback_setkey(struct crypto_tfm *tfm, const u8 *key, - unsigned int len) -{ - struct s390_xts_ctx *xts_ctx = crypto_tfm_ctx(tfm); - unsigned int ret; - - crypto_sync_skcipher_clear_flags(xts_ctx->fallback, - CRYPTO_TFM_REQ_MASK); - crypto_sync_skcipher_set_flags(xts_ctx->fallback, tfm->crt_flags & - CRYPTO_TFM_REQ_MASK); - - ret = crypto_sync_skcipher_setkey(xts_ctx->fallback, key, len); - - tfm->crt_flags &= ~CRYPTO_TFM_RES_MASK; - tfm->crt_flags |= crypto_sync_skcipher_get_flags(xts_ctx->fallback) & - CRYPTO_TFM_RES_MASK; - - return ret; -} - -static int xts_fallback_decrypt(struct blkcipher_desc *desc, - struct scatterlist *dst, struct scatterlist *src, - unsigned int nbytes) -{ - struct crypto_blkcipher *tfm = desc->tfm; - struct s390_xts_ctx *xts_ctx = crypto_blkcipher_ctx(tfm); - SYNC_SKCIPHER_REQUEST_ON_STACK(req, xts_ctx->fallback); - unsigned int ret; - - skcipher_request_set_sync_tfm(req, xts_ctx->fallback); - skcipher_request_set_callback(req, desc->flags, NULL, NULL); - skcipher_request_set_crypt(req, src, dst, nbytes, desc->info); - - ret = crypto_skcipher_decrypt(req); - - skcipher_request_zero(req); - return ret; -} - -static int xts_fallback_encrypt(struct blkcipher_desc *desc, - struct scatterlist *dst, struct scatterlist *src, - unsigned int nbytes) +static int xts_fallback_setkey(struct crypto_skcipher *tfm, const u8 *key, + unsigned int len) { - struct crypto_blkcipher *tfm = desc->tfm; - struct s390_xts_ctx *xts_ctx = crypto_blkcipher_ctx(tfm); - SYNC_SKCIPHER_REQUEST_ON_STACK(req, xts_ctx->fallback); - unsigned int ret; - - skcipher_request_set_sync_tfm(req, xts_ctx->fallback); - skcipher_request_set_callback(req, desc->flags, NULL, NULL); - skcipher_request_set_crypt(req, src, dst, nbytes, desc->info); + struct s390_xts_ctx *xts_ctx = crypto_skcipher_ctx(tfm); - ret = crypto_skcipher_encrypt(req); - - skcipher_request_zero(req); - return ret; + crypto_skcipher_clear_flags(xts_ctx->fallback, CRYPTO_TFM_REQ_MASK); + crypto_skcipher_set_flags(xts_ctx->fallback, + crypto_skcipher_get_flags(tfm) & + CRYPTO_TFM_REQ_MASK); + return crypto_skcipher_setkey(xts_ctx->fallback, key, len); } -static int xts_aes_set_key(struct crypto_tfm *tfm, const u8 *in_key, +static int xts_aes_set_key(struct crypto_skcipher *tfm, const u8 *in_key, unsigned int key_len) { - struct s390_xts_ctx *xts_ctx = crypto_tfm_ctx(tfm); + struct s390_xts_ctx *xts_ctx = crypto_skcipher_ctx(tfm); unsigned long fc; int err; - err = xts_check_key(tfm, in_key, key_len); + err = xts_fallback_setkey(tfm, in_key, key_len); if (err) return err; /* In fips mode only 128 bit or 256 bit keys are valid */ - if (fips_enabled && key_len != 32 && key_len != 64) { - tfm->crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN; + if (fips_enabled && key_len != 32 && key_len != 64) return -EINVAL; - } /* Pick the correct function code based on the key length */ fc = (key_len == 32) ? CPACF_KM_XTS_128 : @@ -529,7 +407,7 @@ static int xts_aes_set_key(struct crypto_tfm *tfm, const u8 *in_key, /* Check if the function code is available */ xts_ctx->fc = (fc && cpacf_test_func(&km_functions, fc)) ? fc : 0; if (!xts_ctx->fc) - return xts_fallback_setkey(tfm, in_key, key_len); + return 0; /* Split the XTS key into the two subkeys */ key_len = key_len / 2; @@ -539,10 +417,11 @@ static int xts_aes_set_key(struct crypto_tfm *tfm, const u8 *in_key, return 0; } -static int xts_aes_crypt(struct blkcipher_desc *desc, unsigned long modifier, - struct blkcipher_walk *walk) +static int xts_aes_crypt(struct skcipher_request *req, unsigned long modifier) { - struct s390_xts_ctx *xts_ctx = crypto_blkcipher_ctx(desc->tfm); + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct s390_xts_ctx *xts_ctx = crypto_skcipher_ctx(tfm); + struct skcipher_walk walk; unsigned int offset, nbytes, n; int ret; struct { @@ -557,107 +436,100 @@ static int xts_aes_crypt(struct blkcipher_desc *desc, unsigned long modifier, u8 init[16]; } xts_param; - ret = blkcipher_walk_virt(desc, walk); + if (req->cryptlen < AES_BLOCK_SIZE) + return -EINVAL; + + if (unlikely(!xts_ctx->fc || (req->cryptlen % AES_BLOCK_SIZE) != 0)) { + struct skcipher_request *subreq = skcipher_request_ctx(req); + + *subreq = *req; + skcipher_request_set_tfm(subreq, xts_ctx->fallback); + return (modifier & CPACF_DECRYPT) ? + crypto_skcipher_decrypt(subreq) : + crypto_skcipher_encrypt(subreq); + } + + ret = skcipher_walk_virt(&walk, req, false); + if (ret) + return ret; offset = xts_ctx->key_len & 0x10; memset(pcc_param.block, 0, sizeof(pcc_param.block)); memset(pcc_param.bit, 0, sizeof(pcc_param.bit)); memset(pcc_param.xts, 0, sizeof(pcc_param.xts)); - memcpy(pcc_param.tweak, walk->iv, sizeof(pcc_param.tweak)); + memcpy(pcc_param.tweak, walk.iv, sizeof(pcc_param.tweak)); memcpy(pcc_param.key + offset, xts_ctx->pcc_key, xts_ctx->key_len); cpacf_pcc(xts_ctx->fc, pcc_param.key + offset); memcpy(xts_param.key + offset, xts_ctx->key, xts_ctx->key_len); memcpy(xts_param.init, pcc_param.xts, 16); - while ((nbytes = walk->nbytes) >= AES_BLOCK_SIZE) { + while ((nbytes = walk.nbytes) != 0) { /* only use complete blocks */ n = nbytes & ~(AES_BLOCK_SIZE - 1); cpacf_km(xts_ctx->fc | modifier, xts_param.key + offset, - walk->dst.virt.addr, walk->src.virt.addr, n); - ret = blkcipher_walk_done(desc, walk, nbytes - n); + walk.dst.virt.addr, walk.src.virt.addr, n); + ret = skcipher_walk_done(&walk, nbytes - n); } return ret; } -static int xts_aes_encrypt(struct blkcipher_desc *desc, - struct scatterlist *dst, struct scatterlist *src, - unsigned int nbytes) +static int xts_aes_encrypt(struct skcipher_request *req) { - struct s390_xts_ctx *xts_ctx = crypto_blkcipher_ctx(desc->tfm); - struct blkcipher_walk walk; - - if (unlikely(!xts_ctx->fc)) - return xts_fallback_encrypt(desc, dst, src, nbytes); - - blkcipher_walk_init(&walk, dst, src, nbytes); - return xts_aes_crypt(desc, 0, &walk); + return xts_aes_crypt(req, 0); } -static int xts_aes_decrypt(struct blkcipher_desc *desc, - struct scatterlist *dst, struct scatterlist *src, - unsigned int nbytes) +static int xts_aes_decrypt(struct skcipher_request *req) { - struct s390_xts_ctx *xts_ctx = crypto_blkcipher_ctx(desc->tfm); - struct blkcipher_walk walk; - - if (unlikely(!xts_ctx->fc)) - return xts_fallback_decrypt(desc, dst, src, nbytes); - - blkcipher_walk_init(&walk, dst, src, nbytes); - return xts_aes_crypt(desc, CPACF_DECRYPT, &walk); + return xts_aes_crypt(req, CPACF_DECRYPT); } -static int xts_fallback_init(struct crypto_tfm *tfm) +static int xts_fallback_init(struct crypto_skcipher *tfm) { - const char *name = tfm->__crt_alg->cra_name; - struct s390_xts_ctx *xts_ctx = crypto_tfm_ctx(tfm); + const char *name = crypto_tfm_alg_name(&tfm->base); + struct s390_xts_ctx *xts_ctx = crypto_skcipher_ctx(tfm); - xts_ctx->fallback = crypto_alloc_sync_skcipher(name, 0, - CRYPTO_ALG_NEED_FALLBACK); + xts_ctx->fallback = crypto_alloc_skcipher(name, 0, + CRYPTO_ALG_NEED_FALLBACK | CRYPTO_ALG_ASYNC); if (IS_ERR(xts_ctx->fallback)) { pr_err("Allocating XTS fallback algorithm %s failed\n", name); return PTR_ERR(xts_ctx->fallback); } + crypto_skcipher_set_reqsize(tfm, sizeof(struct skcipher_request) + + crypto_skcipher_reqsize(xts_ctx->fallback)); return 0; } -static void xts_fallback_exit(struct crypto_tfm *tfm) +static void xts_fallback_exit(struct crypto_skcipher *tfm) { - struct s390_xts_ctx *xts_ctx = crypto_tfm_ctx(tfm); + struct s390_xts_ctx *xts_ctx = crypto_skcipher_ctx(tfm); - crypto_free_sync_skcipher(xts_ctx->fallback); + crypto_free_skcipher(xts_ctx->fallback); } -static struct crypto_alg xts_aes_alg = { - .cra_name = "xts(aes)", - .cra_driver_name = "xts-aes-s390", - .cra_priority = 402, /* ecb-aes-s390 + 1 */ - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | - CRYPTO_ALG_NEED_FALLBACK, - .cra_blocksize = AES_BLOCK_SIZE, - .cra_ctxsize = sizeof(struct s390_xts_ctx), - .cra_type = &crypto_blkcipher_type, - .cra_module = THIS_MODULE, - .cra_init = xts_fallback_init, - .cra_exit = xts_fallback_exit, - .cra_u = { - .blkcipher = { - .min_keysize = 2 * AES_MIN_KEY_SIZE, - .max_keysize = 2 * AES_MAX_KEY_SIZE, - .ivsize = AES_BLOCK_SIZE, - .setkey = xts_aes_set_key, - .encrypt = xts_aes_encrypt, - .decrypt = xts_aes_decrypt, - } - } +static struct skcipher_alg xts_aes_alg = { + .base.cra_name = "xts(aes)", + .base.cra_driver_name = "xts-aes-s390", + .base.cra_priority = 402, /* ecb-aes-s390 + 1 */ + .base.cra_flags = CRYPTO_ALG_NEED_FALLBACK, + .base.cra_blocksize = AES_BLOCK_SIZE, + .base.cra_ctxsize = sizeof(struct s390_xts_ctx), + .base.cra_module = THIS_MODULE, + .init = xts_fallback_init, + .exit = xts_fallback_exit, + .min_keysize = 2 * AES_MIN_KEY_SIZE, + .max_keysize = 2 * AES_MAX_KEY_SIZE, + .ivsize = AES_BLOCK_SIZE, + .setkey = xts_aes_set_key, + .encrypt = xts_aes_encrypt, + .decrypt = xts_aes_decrypt, }; -static int ctr_aes_set_key(struct crypto_tfm *tfm, const u8 *in_key, +static int ctr_aes_set_key(struct crypto_skcipher *tfm, const u8 *in_key, unsigned int key_len) { - struct s390_aes_ctx *sctx = crypto_tfm_ctx(tfm); + struct s390_aes_ctx *sctx = crypto_skcipher_ctx(tfm); unsigned long fc; /* Pick the correct function code based on the key length */ @@ -668,7 +540,7 @@ static int ctr_aes_set_key(struct crypto_tfm *tfm, const u8 *in_key, /* Check if the function code is available */ sctx->fc = (fc && cpacf_test_func(&kmctr_functions, fc)) ? fc : 0; if (!sctx->fc) - return setkey_fallback_blk(tfm, in_key, key_len); + return setkey_fallback_skcipher(tfm, in_key, key_len); sctx->key_len = key_len; memcpy(sctx->key, in_key, key_len); @@ -690,30 +562,34 @@ static unsigned int __ctrblk_init(u8 *ctrptr, u8 *iv, unsigned int nbytes) return n; } -static int ctr_aes_crypt(struct blkcipher_desc *desc, unsigned long modifier, - struct blkcipher_walk *walk) +static int ctr_aes_crypt(struct skcipher_request *req) { - struct s390_aes_ctx *sctx = crypto_blkcipher_ctx(desc->tfm); + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct s390_aes_ctx *sctx = crypto_skcipher_ctx(tfm); u8 buf[AES_BLOCK_SIZE], *ctrptr; + struct skcipher_walk walk; unsigned int n, nbytes; int ret, locked; + if (unlikely(!sctx->fc)) + return fallback_skcipher_crypt(sctx, req, 0); + locked = mutex_trylock(&ctrblk_lock); - ret = blkcipher_walk_virt_block(desc, walk, AES_BLOCK_SIZE); - while ((nbytes = walk->nbytes) >= AES_BLOCK_SIZE) { + ret = skcipher_walk_virt(&walk, req, false); + while ((nbytes = walk.nbytes) >= AES_BLOCK_SIZE) { n = AES_BLOCK_SIZE; + if (nbytes >= 2*AES_BLOCK_SIZE && locked) - n = __ctrblk_init(ctrblk, walk->iv, nbytes); - ctrptr = (n > AES_BLOCK_SIZE) ? ctrblk : walk->iv; - cpacf_kmctr(sctx->fc | modifier, sctx->key, - walk->dst.virt.addr, walk->src.virt.addr, - n, ctrptr); + n = __ctrblk_init(ctrblk, walk.iv, nbytes); + ctrptr = (n > AES_BLOCK_SIZE) ? ctrblk : walk.iv; + cpacf_kmctr(sctx->fc, sctx->key, walk.dst.virt.addr, + walk.src.virt.addr, n, ctrptr); if (ctrptr == ctrblk) - memcpy(walk->iv, ctrptr + n - AES_BLOCK_SIZE, + memcpy(walk.iv, ctrptr + n - AES_BLOCK_SIZE, AES_BLOCK_SIZE); - crypto_inc(walk->iv, AES_BLOCK_SIZE); - ret = blkcipher_walk_done(desc, walk, nbytes - n); + crypto_inc(walk.iv, AES_BLOCK_SIZE); + ret = skcipher_walk_done(&walk, nbytes - n); } if (locked) mutex_unlock(&ctrblk_lock); @@ -721,67 +597,33 @@ static int ctr_aes_crypt(struct blkcipher_desc *desc, unsigned long modifier, * final block may be < AES_BLOCK_SIZE, copy only nbytes */ if (nbytes) { - cpacf_kmctr(sctx->fc | modifier, sctx->key, - buf, walk->src.virt.addr, - AES_BLOCK_SIZE, walk->iv); - memcpy(walk->dst.virt.addr, buf, nbytes); - crypto_inc(walk->iv, AES_BLOCK_SIZE); - ret = blkcipher_walk_done(desc, walk, 0); + cpacf_kmctr(sctx->fc, sctx->key, buf, walk.src.virt.addr, + AES_BLOCK_SIZE, walk.iv); + memcpy(walk.dst.virt.addr, buf, nbytes); + crypto_inc(walk.iv, AES_BLOCK_SIZE); + ret = skcipher_walk_done(&walk, 0); } return ret; } -static int ctr_aes_encrypt(struct blkcipher_desc *desc, - struct scatterlist *dst, struct scatterlist *src, - unsigned int nbytes) -{ - struct s390_aes_ctx *sctx = crypto_blkcipher_ctx(desc->tfm); - struct blkcipher_walk walk; - - if (unlikely(!sctx->fc)) - return fallback_blk_enc(desc, dst, src, nbytes); - - blkcipher_walk_init(&walk, dst, src, nbytes); - return ctr_aes_crypt(desc, 0, &walk); -} - -static int ctr_aes_decrypt(struct blkcipher_desc *desc, - struct scatterlist *dst, struct scatterlist *src, - unsigned int nbytes) -{ - struct s390_aes_ctx *sctx = crypto_blkcipher_ctx(desc->tfm); - struct blkcipher_walk walk; - - if (unlikely(!sctx->fc)) - return fallback_blk_dec(desc, dst, src, nbytes); - - blkcipher_walk_init(&walk, dst, src, nbytes); - return ctr_aes_crypt(desc, CPACF_DECRYPT, &walk); -} - -static struct crypto_alg ctr_aes_alg = { - .cra_name = "ctr(aes)", - .cra_driver_name = "ctr-aes-s390", - .cra_priority = 402, /* ecb-aes-s390 + 1 */ - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | - CRYPTO_ALG_NEED_FALLBACK, - .cra_blocksize = 1, - .cra_ctxsize = sizeof(struct s390_aes_ctx), - .cra_type = &crypto_blkcipher_type, - .cra_module = THIS_MODULE, - .cra_init = fallback_init_blk, - .cra_exit = fallback_exit_blk, - .cra_u = { - .blkcipher = { - .min_keysize = AES_MIN_KEY_SIZE, - .max_keysize = AES_MAX_KEY_SIZE, - .ivsize = AES_BLOCK_SIZE, - .setkey = ctr_aes_set_key, - .encrypt = ctr_aes_encrypt, - .decrypt = ctr_aes_decrypt, - } - } +static struct skcipher_alg ctr_aes_alg = { + .base.cra_name = "ctr(aes)", + .base.cra_driver_name = "ctr-aes-s390", + .base.cra_priority = 402, /* ecb-aes-s390 + 1 */ + .base.cra_flags = CRYPTO_ALG_NEED_FALLBACK, + .base.cra_blocksize = 1, + .base.cra_ctxsize = sizeof(struct s390_aes_ctx), + .base.cra_module = THIS_MODULE, + .init = fallback_init_skcipher, + .exit = fallback_exit_skcipher, + .min_keysize = AES_MIN_KEY_SIZE, + .max_keysize = AES_MAX_KEY_SIZE, + .ivsize = AES_BLOCK_SIZE, + .setkey = ctr_aes_set_key, + .encrypt = ctr_aes_crypt, + .decrypt = ctr_aes_crypt, + .chunksize = AES_BLOCK_SIZE, }; static int gcm_aes_setkey(struct crypto_aead *tfm, const u8 *key, @@ -1110,24 +952,27 @@ static struct aead_alg gcm_aes_aead = { }, }; -static struct crypto_alg *aes_s390_algs_ptr[5]; -static int aes_s390_algs_num; +static struct crypto_alg *aes_s390_alg; +static struct skcipher_alg *aes_s390_skcipher_algs[4]; +static int aes_s390_skciphers_num; static struct aead_alg *aes_s390_aead_alg; -static int aes_s390_register_alg(struct crypto_alg *alg) +static int aes_s390_register_skcipher(struct skcipher_alg *alg) { int ret; - ret = crypto_register_alg(alg); + ret = crypto_register_skcipher(alg); if (!ret) - aes_s390_algs_ptr[aes_s390_algs_num++] = alg; + aes_s390_skcipher_algs[aes_s390_skciphers_num++] = alg; return ret; } static void aes_s390_fini(void) { - while (aes_s390_algs_num--) - crypto_unregister_alg(aes_s390_algs_ptr[aes_s390_algs_num]); + if (aes_s390_alg) + crypto_unregister_alg(aes_s390_alg); + while (aes_s390_skciphers_num--) + crypto_unregister_skcipher(aes_s390_skcipher_algs[aes_s390_skciphers_num]); if (ctrblk) free_page((unsigned long) ctrblk); @@ -1148,10 +993,11 @@ static int __init aes_s390_init(void) if (cpacf_test_func(&km_functions, CPACF_KM_AES_128) || cpacf_test_func(&km_functions, CPACF_KM_AES_192) || cpacf_test_func(&km_functions, CPACF_KM_AES_256)) { - ret = aes_s390_register_alg(&aes_alg); + ret = crypto_register_alg(&aes_alg); if (ret) goto out_err; - ret = aes_s390_register_alg(&ecb_aes_alg); + aes_s390_alg = &aes_alg; + ret = aes_s390_register_skcipher(&ecb_aes_alg); if (ret) goto out_err; } @@ -1159,14 +1005,14 @@ static int __init aes_s390_init(void) if (cpacf_test_func(&kmc_functions, CPACF_KMC_AES_128) || cpacf_test_func(&kmc_functions, CPACF_KMC_AES_192) || cpacf_test_func(&kmc_functions, CPACF_KMC_AES_256)) { - ret = aes_s390_register_alg(&cbc_aes_alg); + ret = aes_s390_register_skcipher(&cbc_aes_alg); if (ret) goto out_err; } if (cpacf_test_func(&km_functions, CPACF_KM_XTS_128) || cpacf_test_func(&km_functions, CPACF_KM_XTS_256)) { - ret = aes_s390_register_alg(&xts_aes_alg); + ret = aes_s390_register_skcipher(&xts_aes_alg); if (ret) goto out_err; } @@ -1179,7 +1025,7 @@ static int __init aes_s390_init(void) ret = -ENOMEM; goto out_err; } - ret = aes_s390_register_alg(&ctr_aes_alg); + ret = aes_s390_register_skcipher(&ctr_aes_alg); if (ret) goto out_err; } diff --git a/arch/s390/crypto/crc32-vx.c b/arch/s390/crypto/crc32-vx.c index 423ee05887e6..fafecad20752 100644 --- a/arch/s390/crypto/crc32-vx.c +++ b/arch/s390/crypto/crc32-vx.c @@ -111,10 +111,8 @@ static int crc32_vx_setkey(struct crypto_shash *tfm, const u8 *newkey, { struct crc_ctx *mctx = crypto_shash_ctx(tfm); - if (newkeylen != sizeof(mctx->key)) { - crypto_shash_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN); + if (newkeylen != sizeof(mctx->key)) return -EINVAL; - } mctx->key = le32_to_cpu(*(__le32 *)newkey); return 0; } @@ -124,10 +122,8 @@ static int crc32be_vx_setkey(struct crypto_shash *tfm, const u8 *newkey, { struct crc_ctx *mctx = crypto_shash_ctx(tfm); - if (newkeylen != sizeof(mctx->key)) { - crypto_shash_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN); + if (newkeylen != sizeof(mctx->key)) return -EINVAL; - } mctx->key = be32_to_cpu(*(__be32 *)newkey); return 0; } diff --git a/arch/s390/crypto/des_s390.c b/arch/s390/crypto/des_s390.c index 374b42fc7637..bfbafd35bcbd 100644 --- a/arch/s390/crypto/des_s390.c +++ b/arch/s390/crypto/des_s390.c @@ -16,7 +16,8 @@ #include <linux/fips.h> #include <linux/mutex.h> #include <crypto/algapi.h> -#include <crypto/des.h> +#include <crypto/internal/des.h> +#include <crypto/internal/skcipher.h> #include <asm/cpacf.h> #define DES3_KEY_SIZE (3 * DES_KEY_SIZE) @@ -35,27 +36,30 @@ static int des_setkey(struct crypto_tfm *tfm, const u8 *key, unsigned int key_len) { struct s390_des_ctx *ctx = crypto_tfm_ctx(tfm); - u32 tmp[DES_EXPKEY_WORDS]; + int err; - /* check for weak keys */ - if (!des_ekey(tmp, key) && - (tfm->crt_flags & CRYPTO_TFM_REQ_FORBID_WEAK_KEYS)) { - tfm->crt_flags |= CRYPTO_TFM_RES_WEAK_KEY; - return -EINVAL; - } + err = crypto_des_verify_key(tfm, key); + if (err) + return err; memcpy(ctx->key, key, key_len); return 0; } -static void des_encrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in) +static int des_setkey_skcipher(struct crypto_skcipher *tfm, const u8 *key, + unsigned int key_len) +{ + return des_setkey(crypto_skcipher_tfm(tfm), key, key_len); +} + +static void s390_des_encrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in) { struct s390_des_ctx *ctx = crypto_tfm_ctx(tfm); cpacf_km(CPACF_KM_DEA, ctx->key, out, in, DES_BLOCK_SIZE); } -static void des_decrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in) +static void s390_des_decrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in) { struct s390_des_ctx *ctx = crypto_tfm_ctx(tfm); @@ -76,34 +80,36 @@ static struct crypto_alg des_alg = { .cia_min_keysize = DES_KEY_SIZE, .cia_max_keysize = DES_KEY_SIZE, .cia_setkey = des_setkey, - .cia_encrypt = des_encrypt, - .cia_decrypt = des_decrypt, + .cia_encrypt = s390_des_encrypt, + .cia_decrypt = s390_des_decrypt, } } }; -static int ecb_desall_crypt(struct blkcipher_desc *desc, unsigned long fc, - struct blkcipher_walk *walk) +static int ecb_desall_crypt(struct skcipher_request *req, unsigned long fc) { - struct s390_des_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct s390_des_ctx *ctx = crypto_skcipher_ctx(tfm); + struct skcipher_walk walk; unsigned int nbytes, n; int ret; - ret = blkcipher_walk_virt(desc, walk); - while ((nbytes = walk->nbytes) >= DES_BLOCK_SIZE) { + ret = skcipher_walk_virt(&walk, req, false); + while ((nbytes = walk.nbytes) != 0) { /* only use complete blocks */ n = nbytes & ~(DES_BLOCK_SIZE - 1); - cpacf_km(fc, ctx->key, walk->dst.virt.addr, - walk->src.virt.addr, n); - ret = blkcipher_walk_done(desc, walk, nbytes - n); + cpacf_km(fc, ctx->key, walk.dst.virt.addr, + walk.src.virt.addr, n); + ret = skcipher_walk_done(&walk, nbytes - n); } return ret; } -static int cbc_desall_crypt(struct blkcipher_desc *desc, unsigned long fc, - struct blkcipher_walk *walk) +static int cbc_desall_crypt(struct skcipher_request *req, unsigned long fc) { - struct s390_des_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct s390_des_ctx *ctx = crypto_skcipher_ctx(tfm); + struct skcipher_walk walk; unsigned int nbytes, n; int ret; struct { @@ -111,99 +117,69 @@ static int cbc_desall_crypt(struct blkcipher_desc *desc, unsigned long fc, u8 key[DES3_KEY_SIZE]; } param; - ret = blkcipher_walk_virt(desc, walk); - memcpy(param.iv, walk->iv, DES_BLOCK_SIZE); + ret = skcipher_walk_virt(&walk, req, false); + if (ret) + return ret; + memcpy(param.iv, walk.iv, DES_BLOCK_SIZE); memcpy(param.key, ctx->key, DES3_KEY_SIZE); - while ((nbytes = walk->nbytes) >= DES_BLOCK_SIZE) { + while ((nbytes = walk.nbytes) != 0) { /* only use complete blocks */ n = nbytes & ~(DES_BLOCK_SIZE - 1); - cpacf_kmc(fc, ¶m, walk->dst.virt.addr, - walk->src.virt.addr, n); - ret = blkcipher_walk_done(desc, walk, nbytes - n); + cpacf_kmc(fc, ¶m, walk.dst.virt.addr, + walk.src.virt.addr, n); + memcpy(walk.iv, param.iv, DES_BLOCK_SIZE); + ret = skcipher_walk_done(&walk, nbytes - n); } - memcpy(walk->iv, param.iv, DES_BLOCK_SIZE); return ret; } -static int ecb_des_encrypt(struct blkcipher_desc *desc, - struct scatterlist *dst, struct scatterlist *src, - unsigned int nbytes) +static int ecb_des_encrypt(struct skcipher_request *req) { - struct blkcipher_walk walk; - - blkcipher_walk_init(&walk, dst, src, nbytes); - return ecb_desall_crypt(desc, CPACF_KM_DEA, &walk); + return ecb_desall_crypt(req, CPACF_KM_DEA); } -static int ecb_des_decrypt(struct blkcipher_desc *desc, - struct scatterlist *dst, struct scatterlist *src, - unsigned int nbytes) +static int ecb_des_decrypt(struct skcipher_request *req) { - struct blkcipher_walk walk; - - blkcipher_walk_init(&walk, dst, src, nbytes); - return ecb_desall_crypt(desc, CPACF_KM_DEA | CPACF_DECRYPT, &walk); + return ecb_desall_crypt(req, CPACF_KM_DEA | CPACF_DECRYPT); } -static struct crypto_alg ecb_des_alg = { - .cra_name = "ecb(des)", - .cra_driver_name = "ecb-des-s390", - .cra_priority = 400, /* combo: des + ecb */ - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, - .cra_blocksize = DES_BLOCK_SIZE, - .cra_ctxsize = sizeof(struct s390_des_ctx), - .cra_type = &crypto_blkcipher_type, - .cra_module = THIS_MODULE, - .cra_u = { - .blkcipher = { - .min_keysize = DES_KEY_SIZE, - .max_keysize = DES_KEY_SIZE, - .setkey = des_setkey, - .encrypt = ecb_des_encrypt, - .decrypt = ecb_des_decrypt, - } - } +static struct skcipher_alg ecb_des_alg = { + .base.cra_name = "ecb(des)", + .base.cra_driver_name = "ecb-des-s390", + .base.cra_priority = 400, /* combo: des + ecb */ + .base.cra_blocksize = DES_BLOCK_SIZE, + .base.cra_ctxsize = sizeof(struct s390_des_ctx), + .base.cra_module = THIS_MODULE, + .min_keysize = DES_KEY_SIZE, + .max_keysize = DES_KEY_SIZE, + .setkey = des_setkey_skcipher, + .encrypt = ecb_des_encrypt, + .decrypt = ecb_des_decrypt, }; -static int cbc_des_encrypt(struct blkcipher_desc *desc, - struct scatterlist *dst, struct scatterlist *src, - unsigned int nbytes) +static int cbc_des_encrypt(struct skcipher_request *req) { - struct blkcipher_walk walk; - - blkcipher_walk_init(&walk, dst, src, nbytes); - return cbc_desall_crypt(desc, CPACF_KMC_DEA, &walk); + return cbc_desall_crypt(req, CPACF_KMC_DEA); } -static int cbc_des_decrypt(struct blkcipher_desc *desc, - struct scatterlist *dst, struct scatterlist *src, - unsigned int nbytes) +static int cbc_des_decrypt(struct skcipher_request *req) { - struct blkcipher_walk walk; - - blkcipher_walk_init(&walk, dst, src, nbytes); - return cbc_desall_crypt(desc, CPACF_KMC_DEA | CPACF_DECRYPT, &walk); + return cbc_desall_crypt(req, CPACF_KMC_DEA | CPACF_DECRYPT); } -static struct crypto_alg cbc_des_alg = { - .cra_name = "cbc(des)", - .cra_driver_name = "cbc-des-s390", - .cra_priority = 400, /* combo: des + cbc */ - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, - .cra_blocksize = DES_BLOCK_SIZE, - .cra_ctxsize = sizeof(struct s390_des_ctx), - .cra_type = &crypto_blkcipher_type, - .cra_module = THIS_MODULE, - .cra_u = { - .blkcipher = { - .min_keysize = DES_KEY_SIZE, - .max_keysize = DES_KEY_SIZE, - .ivsize = DES_BLOCK_SIZE, - .setkey = des_setkey, - .encrypt = cbc_des_encrypt, - .decrypt = cbc_des_decrypt, - } - } +static struct skcipher_alg cbc_des_alg = { + .base.cra_name = "cbc(des)", + .base.cra_driver_name = "cbc-des-s390", + .base.cra_priority = 400, /* combo: des + cbc */ + .base.cra_blocksize = DES_BLOCK_SIZE, + .base.cra_ctxsize = sizeof(struct s390_des_ctx), + .base.cra_module = THIS_MODULE, + .min_keysize = DES_KEY_SIZE, + .max_keysize = DES_KEY_SIZE, + .ivsize = DES_BLOCK_SIZE, + .setkey = des_setkey_skcipher, + .encrypt = cbc_des_encrypt, + .decrypt = cbc_des_decrypt, }; /* @@ -227,14 +203,20 @@ static int des3_setkey(struct crypto_tfm *tfm, const u8 *key, struct s390_des_ctx *ctx = crypto_tfm_ctx(tfm); int err; - err = __des3_verify_key(&tfm->crt_flags, key); - if (unlikely(err)) + err = crypto_des3_ede_verify_key(tfm, key); + if (err) return err; memcpy(ctx->key, key, key_len); return 0; } +static int des3_setkey_skcipher(struct crypto_skcipher *tfm, const u8 *key, + unsigned int key_len) +{ + return des3_setkey(crypto_skcipher_tfm(tfm), key, key_len); +} + static void des3_encrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src) { struct s390_des_ctx *ctx = crypto_tfm_ctx(tfm); @@ -269,87 +251,53 @@ static struct crypto_alg des3_alg = { } }; -static int ecb_des3_encrypt(struct blkcipher_desc *desc, - struct scatterlist *dst, struct scatterlist *src, - unsigned int nbytes) +static int ecb_des3_encrypt(struct skcipher_request *req) { - struct blkcipher_walk walk; - - blkcipher_walk_init(&walk, dst, src, nbytes); - return ecb_desall_crypt(desc, CPACF_KM_TDEA_192, &walk); + return ecb_desall_crypt(req, CPACF_KM_TDEA_192); } -static int ecb_des3_decrypt(struct blkcipher_desc *desc, - struct scatterlist *dst, struct scatterlist *src, - unsigned int nbytes) +static int ecb_des3_decrypt(struct skcipher_request *req) { - struct blkcipher_walk walk; - - blkcipher_walk_init(&walk, dst, src, nbytes); - return ecb_desall_crypt(desc, CPACF_KM_TDEA_192 | CPACF_DECRYPT, - &walk); + return ecb_desall_crypt(req, CPACF_KM_TDEA_192 | CPACF_DECRYPT); } -static struct crypto_alg ecb_des3_alg = { - .cra_name = "ecb(des3_ede)", - .cra_driver_name = "ecb-des3_ede-s390", - .cra_priority = 400, /* combo: des3 + ecb */ - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, - .cra_blocksize = DES_BLOCK_SIZE, - .cra_ctxsize = sizeof(struct s390_des_ctx), - .cra_type = &crypto_blkcipher_type, - .cra_module = THIS_MODULE, - .cra_u = { - .blkcipher = { - .min_keysize = DES3_KEY_SIZE, - .max_keysize = DES3_KEY_SIZE, - .setkey = des3_setkey, - .encrypt = ecb_des3_encrypt, - .decrypt = ecb_des3_decrypt, - } - } +static struct skcipher_alg ecb_des3_alg = { + .base.cra_name = "ecb(des3_ede)", + .base.cra_driver_name = "ecb-des3_ede-s390", + .base.cra_priority = 400, /* combo: des3 + ecb */ + .base.cra_blocksize = DES_BLOCK_SIZE, + .base.cra_ctxsize = sizeof(struct s390_des_ctx), + .base.cra_module = THIS_MODULE, + .min_keysize = DES3_KEY_SIZE, + .max_keysize = DES3_KEY_SIZE, + .setkey = des3_setkey_skcipher, + .encrypt = ecb_des3_encrypt, + .decrypt = ecb_des3_decrypt, }; -static int cbc_des3_encrypt(struct blkcipher_desc *desc, - struct scatterlist *dst, struct scatterlist *src, - unsigned int nbytes) +static int cbc_des3_encrypt(struct skcipher_request *req) { - struct blkcipher_walk walk; - - blkcipher_walk_init(&walk, dst, src, nbytes); - return cbc_desall_crypt(desc, CPACF_KMC_TDEA_192, &walk); + return cbc_desall_crypt(req, CPACF_KMC_TDEA_192); } -static int cbc_des3_decrypt(struct blkcipher_desc *desc, - struct scatterlist *dst, struct scatterlist *src, - unsigned int nbytes) +static int cbc_des3_decrypt(struct skcipher_request *req) { - struct blkcipher_walk walk; - - blkcipher_walk_init(&walk, dst, src, nbytes); - return cbc_desall_crypt(desc, CPACF_KMC_TDEA_192 | CPACF_DECRYPT, - &walk); + return cbc_desall_crypt(req, CPACF_KMC_TDEA_192 | CPACF_DECRYPT); } -static struct crypto_alg cbc_des3_alg = { - .cra_name = "cbc(des3_ede)", - .cra_driver_name = "cbc-des3_ede-s390", - .cra_priority = 400, /* combo: des3 + cbc */ - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, - .cra_blocksize = DES_BLOCK_SIZE, - .cra_ctxsize = sizeof(struct s390_des_ctx), - .cra_type = &crypto_blkcipher_type, - .cra_module = THIS_MODULE, - .cra_u = { - .blkcipher = { - .min_keysize = DES3_KEY_SIZE, - .max_keysize = DES3_KEY_SIZE, - .ivsize = DES_BLOCK_SIZE, - .setkey = des3_setkey, - .encrypt = cbc_des3_encrypt, - .decrypt = cbc_des3_decrypt, - } - } +static struct skcipher_alg cbc_des3_alg = { + .base.cra_name = "cbc(des3_ede)", + .base.cra_driver_name = "cbc-des3_ede-s390", + .base.cra_priority = 400, /* combo: des3 + cbc */ + .base.cra_blocksize = DES_BLOCK_SIZE, + .base.cra_ctxsize = sizeof(struct s390_des_ctx), + .base.cra_module = THIS_MODULE, + .min_keysize = DES3_KEY_SIZE, + .max_keysize = DES3_KEY_SIZE, + .ivsize = DES_BLOCK_SIZE, + .setkey = des3_setkey_skcipher, + .encrypt = cbc_des3_encrypt, + .decrypt = cbc_des3_decrypt, }; static unsigned int __ctrblk_init(u8 *ctrptr, u8 *iv, unsigned int nbytes) @@ -367,128 +315,90 @@ static unsigned int __ctrblk_init(u8 *ctrptr, u8 *iv, unsigned int nbytes) return n; } -static int ctr_desall_crypt(struct blkcipher_desc *desc, unsigned long fc, - struct blkcipher_walk *walk) +static int ctr_desall_crypt(struct skcipher_request *req, unsigned long fc) { - struct s390_des_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct s390_des_ctx *ctx = crypto_skcipher_ctx(tfm); u8 buf[DES_BLOCK_SIZE], *ctrptr; + struct skcipher_walk walk; unsigned int n, nbytes; int ret, locked; locked = mutex_trylock(&ctrblk_lock); - ret = blkcipher_walk_virt_block(desc, walk, DES_BLOCK_SIZE); - while ((nbytes = walk->nbytes) >= DES_BLOCK_SIZE) { + ret = skcipher_walk_virt(&walk, req, false); + while ((nbytes = walk.nbytes) >= DES_BLOCK_SIZE) { n = DES_BLOCK_SIZE; if (nbytes >= 2*DES_BLOCK_SIZE && locked) - n = __ctrblk_init(ctrblk, walk->iv, nbytes); - ctrptr = (n > DES_BLOCK_SIZE) ? ctrblk : walk->iv; - cpacf_kmctr(fc, ctx->key, walk->dst.virt.addr, - walk->src.virt.addr, n, ctrptr); + n = __ctrblk_init(ctrblk, walk.iv, nbytes); + ctrptr = (n > DES_BLOCK_SIZE) ? ctrblk : walk.iv; + cpacf_kmctr(fc, ctx->key, walk.dst.virt.addr, + walk.src.virt.addr, n, ctrptr); if (ctrptr == ctrblk) - memcpy(walk->iv, ctrptr + n - DES_BLOCK_SIZE, + memcpy(walk.iv, ctrptr + n - DES_BLOCK_SIZE, DES_BLOCK_SIZE); - crypto_inc(walk->iv, DES_BLOCK_SIZE); - ret = blkcipher_walk_done(desc, walk, nbytes - n); + crypto_inc(walk.iv, DES_BLOCK_SIZE); + ret = skcipher_walk_done(&walk, nbytes - n); } if (locked) mutex_unlock(&ctrblk_lock); /* final block may be < DES_BLOCK_SIZE, copy only nbytes */ if (nbytes) { - cpacf_kmctr(fc, ctx->key, buf, walk->src.virt.addr, - DES_BLOCK_SIZE, walk->iv); - memcpy(walk->dst.virt.addr, buf, nbytes); - crypto_inc(walk->iv, DES_BLOCK_SIZE); - ret = blkcipher_walk_done(desc, walk, 0); + cpacf_kmctr(fc, ctx->key, buf, walk.src.virt.addr, + DES_BLOCK_SIZE, walk.iv); + memcpy(walk.dst.virt.addr, buf, nbytes); + crypto_inc(walk.iv, DES_BLOCK_SIZE); + ret = skcipher_walk_done(&walk, 0); } return ret; } -static int ctr_des_encrypt(struct blkcipher_desc *desc, - struct scatterlist *dst, struct scatterlist *src, - unsigned int nbytes) +static int ctr_des_crypt(struct skcipher_request *req) { - struct blkcipher_walk walk; - - blkcipher_walk_init(&walk, dst, src, nbytes); - return ctr_desall_crypt(desc, CPACF_KMCTR_DEA, &walk); + return ctr_desall_crypt(req, CPACF_KMCTR_DEA); } -static int ctr_des_decrypt(struct blkcipher_desc *desc, - struct scatterlist *dst, struct scatterlist *src, - unsigned int nbytes) -{ - struct blkcipher_walk walk; - - blkcipher_walk_init(&walk, dst, src, nbytes); - return ctr_desall_crypt(desc, CPACF_KMCTR_DEA | CPACF_DECRYPT, &walk); -} - -static struct crypto_alg ctr_des_alg = { - .cra_name = "ctr(des)", - .cra_driver_name = "ctr-des-s390", - .cra_priority = 400, /* combo: des + ctr */ - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, - .cra_blocksize = 1, - .cra_ctxsize = sizeof(struct s390_des_ctx), - .cra_type = &crypto_blkcipher_type, - .cra_module = THIS_MODULE, - .cra_u = { - .blkcipher = { - .min_keysize = DES_KEY_SIZE, - .max_keysize = DES_KEY_SIZE, - .ivsize = DES_BLOCK_SIZE, - .setkey = des_setkey, - .encrypt = ctr_des_encrypt, - .decrypt = ctr_des_decrypt, - } - } +static struct skcipher_alg ctr_des_alg = { + .base.cra_name = "ctr(des)", + .base.cra_driver_name = "ctr-des-s390", + .base.cra_priority = 400, /* combo: des + ctr */ + .base.cra_blocksize = 1, + .base.cra_ctxsize = sizeof(struct s390_des_ctx), + .base.cra_module = THIS_MODULE, + .min_keysize = DES_KEY_SIZE, + .max_keysize = DES_KEY_SIZE, + .ivsize = DES_BLOCK_SIZE, + .setkey = des_setkey_skcipher, + .encrypt = ctr_des_crypt, + .decrypt = ctr_des_crypt, + .chunksize = DES_BLOCK_SIZE, }; -static int ctr_des3_encrypt(struct blkcipher_desc *desc, - struct scatterlist *dst, struct scatterlist *src, - unsigned int nbytes) +static int ctr_des3_crypt(struct skcipher_request *req) { - struct blkcipher_walk walk; - - blkcipher_walk_init(&walk, dst, src, nbytes); - return ctr_desall_crypt(desc, CPACF_KMCTR_TDEA_192, &walk); -} - -static int ctr_des3_decrypt(struct blkcipher_desc *desc, - struct scatterlist *dst, struct scatterlist *src, - unsigned int nbytes) -{ - struct blkcipher_walk walk; - - blkcipher_walk_init(&walk, dst, src, nbytes); - return ctr_desall_crypt(desc, CPACF_KMCTR_TDEA_192 | CPACF_DECRYPT, - &walk); + return ctr_desall_crypt(req, CPACF_KMCTR_TDEA_192); } -static struct crypto_alg ctr_des3_alg = { - .cra_name = "ctr(des3_ede)", - .cra_driver_name = "ctr-des3_ede-s390", - .cra_priority = 400, /* combo: des3 + ede */ - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, - .cra_blocksize = 1, - .cra_ctxsize = sizeof(struct s390_des_ctx), - .cra_type = &crypto_blkcipher_type, - .cra_module = THIS_MODULE, - .cra_u = { - .blkcipher = { - .min_keysize = DES3_KEY_SIZE, - .max_keysize = DES3_KEY_SIZE, - .ivsize = DES_BLOCK_SIZE, - .setkey = des3_setkey, - .encrypt = ctr_des3_encrypt, - .decrypt = ctr_des3_decrypt, - } - } +static struct skcipher_alg ctr_des3_alg = { + .base.cra_name = "ctr(des3_ede)", + .base.cra_driver_name = "ctr-des3_ede-s390", + .base.cra_priority = 400, /* combo: des3 + ede */ + .base.cra_blocksize = 1, + .base.cra_ctxsize = sizeof(struct s390_des_ctx), + .base.cra_module = THIS_MODULE, + .min_keysize = DES3_KEY_SIZE, + .max_keysize = DES3_KEY_SIZE, + .ivsize = DES_BLOCK_SIZE, + .setkey = des3_setkey_skcipher, + .encrypt = ctr_des3_crypt, + .decrypt = ctr_des3_crypt, + .chunksize = DES_BLOCK_SIZE, }; -static struct crypto_alg *des_s390_algs_ptr[8]; +static struct crypto_alg *des_s390_algs_ptr[2]; static int des_s390_algs_num; +static struct skcipher_alg *des_s390_skciphers_ptr[6]; +static int des_s390_skciphers_num; static int des_s390_register_alg(struct crypto_alg *alg) { @@ -500,10 +410,22 @@ static int des_s390_register_alg(struct crypto_alg *alg) return ret; } +static int des_s390_register_skcipher(struct skcipher_alg *alg) +{ + int ret; + + ret = crypto_register_skcipher(alg); + if (!ret) + des_s390_skciphers_ptr[des_s390_skciphers_num++] = alg; + return ret; +} + static void des_s390_exit(void) { while (des_s390_algs_num--) crypto_unregister_alg(des_s390_algs_ptr[des_s390_algs_num]); + while (des_s390_skciphers_num--) + crypto_unregister_skcipher(des_s390_skciphers_ptr[des_s390_skciphers_num]); if (ctrblk) free_page((unsigned long) ctrblk); } @@ -521,12 +443,12 @@ static int __init des_s390_init(void) ret = des_s390_register_alg(&des_alg); if (ret) goto out_err; - ret = des_s390_register_alg(&ecb_des_alg); + ret = des_s390_register_skcipher(&ecb_des_alg); if (ret) goto out_err; } if (cpacf_test_func(&kmc_functions, CPACF_KMC_DEA)) { - ret = des_s390_register_alg(&cbc_des_alg); + ret = des_s390_register_skcipher(&cbc_des_alg); if (ret) goto out_err; } @@ -534,12 +456,12 @@ static int __init des_s390_init(void) ret = des_s390_register_alg(&des3_alg); if (ret) goto out_err; - ret = des_s390_register_alg(&ecb_des3_alg); + ret = des_s390_register_skcipher(&ecb_des3_alg); if (ret) goto out_err; } if (cpacf_test_func(&kmc_functions, CPACF_KMC_TDEA_192)) { - ret = des_s390_register_alg(&cbc_des3_alg); + ret = des_s390_register_skcipher(&cbc_des3_alg); if (ret) goto out_err; } @@ -554,12 +476,12 @@ static int __init des_s390_init(void) } if (cpacf_test_func(&kmctr_functions, CPACF_KMCTR_DEA)) { - ret = des_s390_register_alg(&ctr_des_alg); + ret = des_s390_register_skcipher(&ctr_des_alg); if (ret) goto out_err; } if (cpacf_test_func(&kmctr_functions, CPACF_KMCTR_TDEA_192)) { - ret = des_s390_register_alg(&ctr_des3_alg); + ret = des_s390_register_skcipher(&ctr_des3_alg); if (ret) goto out_err; } diff --git a/arch/s390/crypto/ghash_s390.c b/arch/s390/crypto/ghash_s390.c index eeeb6a7737a4..6b07a2f1ce8a 100644 --- a/arch/s390/crypto/ghash_s390.c +++ b/arch/s390/crypto/ghash_s390.c @@ -43,10 +43,8 @@ static int ghash_setkey(struct crypto_shash *tfm, { struct ghash_ctx *ctx = crypto_shash_ctx(tfm); - if (keylen != GHASH_BLOCK_SIZE) { - crypto_shash_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN); + if (keylen != GHASH_BLOCK_SIZE) return -EINVAL; - } memcpy(ctx->key, key, GHASH_BLOCK_SIZE); @@ -153,4 +151,4 @@ module_exit(ghash_mod_exit); MODULE_ALIAS_CRYPTO("ghash"); MODULE_LICENSE("GPL"); -MODULE_DESCRIPTION("GHASH Message Digest Algorithm, s390 implementation"); +MODULE_DESCRIPTION("GHASH hash function, s390 implementation"); diff --git a/arch/s390/crypto/paes_s390.c b/arch/s390/crypto/paes_s390.c index e8d9fa54569c..f3caeb17c85b 100644 --- a/arch/s390/crypto/paes_s390.c +++ b/arch/s390/crypto/paes_s390.c @@ -5,7 +5,7 @@ * s390 implementation of the AES Cipher Algorithm with protected keys. * * s390 Version: - * Copyright IBM Corp. 2017 + * Copyright IBM Corp. 2017,2020 * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com> * Harald Freudenberger <freude@de.ibm.com> */ @@ -20,34 +20,108 @@ #include <linux/module.h> #include <linux/cpufeature.h> #include <linux/init.h> +#include <linux/mutex.h> #include <linux/spinlock.h> +#include <crypto/internal/skcipher.h> #include <crypto/xts.h> #include <asm/cpacf.h> #include <asm/pkey.h> +/* + * Key blobs smaller/bigger than these defines are rejected + * by the common code even before the individual setkey function + * is called. As paes can handle different kinds of key blobs + * and padding is also possible, the limits need to be generous. + */ +#define PAES_MIN_KEYSIZE 16 +#define PAES_MAX_KEYSIZE 320 + static u8 *ctrblk; -static DEFINE_SPINLOCK(ctrblk_lock); +static DEFINE_MUTEX(ctrblk_lock); static cpacf_mask_t km_functions, kmc_functions, kmctr_functions; struct key_blob { - __u8 key[MAXKEYBLOBSIZE]; + /* + * Small keys will be stored in the keybuf. Larger keys are + * stored in extra allocated memory. In both cases does + * key point to the memory where the key is stored. + * The code distinguishes by checking keylen against + * sizeof(keybuf). See the two following helper functions. + */ + u8 *key; + u8 keybuf[128]; unsigned int keylen; }; +static inline int _key_to_kb(struct key_blob *kb, + const u8 *key, + unsigned int keylen) +{ + struct clearkey_header { + u8 type; + u8 res0[3]; + u8 version; + u8 res1[3]; + u32 keytype; + u32 len; + } __packed * h; + + switch (keylen) { + case 16: + case 24: + case 32: + /* clear key value, prepare pkey clear key token in keybuf */ + memset(kb->keybuf, 0, sizeof(kb->keybuf)); + h = (struct clearkey_header *) kb->keybuf; + h->version = 0x02; /* TOKVER_CLEAR_KEY */ + h->keytype = (keylen - 8) >> 3; + h->len = keylen; + memcpy(kb->keybuf + sizeof(*h), key, keylen); + kb->keylen = sizeof(*h) + keylen; + kb->key = kb->keybuf; + break; + default: + /* other key material, let pkey handle this */ + if (keylen <= sizeof(kb->keybuf)) + kb->key = kb->keybuf; + else { + kb->key = kmalloc(keylen, GFP_KERNEL); + if (!kb->key) + return -ENOMEM; + } + memcpy(kb->key, key, keylen); + kb->keylen = keylen; + break; + } + + return 0; +} + +static inline void _free_kb_keybuf(struct key_blob *kb) +{ + if (kb->key && kb->key != kb->keybuf + && kb->keylen > sizeof(kb->keybuf)) { + kfree(kb->key); + kb->key = NULL; + } +} + struct s390_paes_ctx { struct key_blob kb; struct pkey_protkey pk; + spinlock_t pk_lock; unsigned long fc; }; struct s390_pxts_ctx { struct key_blob kb[2]; struct pkey_protkey pk[2]; + spinlock_t pk_lock; unsigned long fc; }; -static inline int __paes_convert_key(struct key_blob *kb, +static inline int __paes_keyblob2pkey(struct key_blob *kb, struct pkey_protkey *pk) { int i, ret; @@ -62,11 +136,42 @@ static inline int __paes_convert_key(struct key_blob *kb, return ret; } -static int __paes_set_key(struct s390_paes_ctx *ctx) +static inline int __paes_convert_key(struct s390_paes_ctx *ctx) +{ + struct pkey_protkey pkey; + + if (__paes_keyblob2pkey(&ctx->kb, &pkey)) + return -EINVAL; + + spin_lock_bh(&ctx->pk_lock); + memcpy(&ctx->pk, &pkey, sizeof(pkey)); + spin_unlock_bh(&ctx->pk_lock); + + return 0; +} + +static int ecb_paes_init(struct crypto_skcipher *tfm) +{ + struct s390_paes_ctx *ctx = crypto_skcipher_ctx(tfm); + + ctx->kb.key = NULL; + spin_lock_init(&ctx->pk_lock); + + return 0; +} + +static void ecb_paes_exit(struct crypto_skcipher *tfm) +{ + struct s390_paes_ctx *ctx = crypto_skcipher_ctx(tfm); + + _free_kb_keybuf(&ctx->kb); +} + +static inline int __ecb_paes_set_key(struct s390_paes_ctx *ctx) { unsigned long fc; - if (__paes_convert_key(&ctx->kb, &ctx->pk)) + if (__paes_convert_key(ctx)) return -EINVAL; /* Pick the correct function code based on the protected key type */ @@ -80,90 +185,106 @@ static int __paes_set_key(struct s390_paes_ctx *ctx) return ctx->fc ? 0 : -EINVAL; } -static int ecb_paes_set_key(struct crypto_tfm *tfm, const u8 *in_key, +static int ecb_paes_set_key(struct crypto_skcipher *tfm, const u8 *in_key, unsigned int key_len) { - struct s390_paes_ctx *ctx = crypto_tfm_ctx(tfm); + int rc; + struct s390_paes_ctx *ctx = crypto_skcipher_ctx(tfm); - memcpy(ctx->kb.key, in_key, key_len); - ctx->kb.keylen = key_len; - if (__paes_set_key(ctx)) { - tfm->crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN; - return -EINVAL; - } - return 0; + _free_kb_keybuf(&ctx->kb); + rc = _key_to_kb(&ctx->kb, in_key, key_len); + if (rc) + return rc; + + return __ecb_paes_set_key(ctx); } -static int ecb_paes_crypt(struct blkcipher_desc *desc, - unsigned long modifier, - struct blkcipher_walk *walk) +static int ecb_paes_crypt(struct skcipher_request *req, unsigned long modifier) { - struct s390_paes_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct s390_paes_ctx *ctx = crypto_skcipher_ctx(tfm); + struct skcipher_walk walk; unsigned int nbytes, n, k; int ret; + struct { + u8 key[MAXPROTKEYSIZE]; + } param; - ret = blkcipher_walk_virt(desc, walk); - while ((nbytes = walk->nbytes) >= AES_BLOCK_SIZE) { + ret = skcipher_walk_virt(&walk, req, false); + if (ret) + return ret; + + spin_lock_bh(&ctx->pk_lock); + memcpy(param.key, ctx->pk.protkey, MAXPROTKEYSIZE); + spin_unlock_bh(&ctx->pk_lock); + + while ((nbytes = walk.nbytes) != 0) { /* only use complete blocks */ n = nbytes & ~(AES_BLOCK_SIZE - 1); - k = cpacf_km(ctx->fc | modifier, ctx->pk.protkey, - walk->dst.virt.addr, walk->src.virt.addr, n); + k = cpacf_km(ctx->fc | modifier, ¶m, + walk.dst.virt.addr, walk.src.virt.addr, n); if (k) - ret = blkcipher_walk_done(desc, walk, nbytes - k); + ret = skcipher_walk_done(&walk, nbytes - k); if (k < n) { - if (__paes_set_key(ctx) != 0) - return blkcipher_walk_done(desc, walk, -EIO); + if (__paes_convert_key(ctx)) + return skcipher_walk_done(&walk, -EIO); + spin_lock_bh(&ctx->pk_lock); + memcpy(param.key, ctx->pk.protkey, MAXPROTKEYSIZE); + spin_unlock_bh(&ctx->pk_lock); } } return ret; } -static int ecb_paes_encrypt(struct blkcipher_desc *desc, - struct scatterlist *dst, struct scatterlist *src, - unsigned int nbytes) +static int ecb_paes_encrypt(struct skcipher_request *req) { - struct blkcipher_walk walk; + return ecb_paes_crypt(req, 0); +} - blkcipher_walk_init(&walk, dst, src, nbytes); - return ecb_paes_crypt(desc, CPACF_ENCRYPT, &walk); +static int ecb_paes_decrypt(struct skcipher_request *req) +{ + return ecb_paes_crypt(req, CPACF_DECRYPT); } -static int ecb_paes_decrypt(struct blkcipher_desc *desc, - struct scatterlist *dst, struct scatterlist *src, - unsigned int nbytes) +static struct skcipher_alg ecb_paes_alg = { + .base.cra_name = "ecb(paes)", + .base.cra_driver_name = "ecb-paes-s390", + .base.cra_priority = 401, /* combo: aes + ecb + 1 */ + .base.cra_blocksize = AES_BLOCK_SIZE, + .base.cra_ctxsize = sizeof(struct s390_paes_ctx), + .base.cra_module = THIS_MODULE, + .base.cra_list = LIST_HEAD_INIT(ecb_paes_alg.base.cra_list), + .init = ecb_paes_init, + .exit = ecb_paes_exit, + .min_keysize = PAES_MIN_KEYSIZE, + .max_keysize = PAES_MAX_KEYSIZE, + .setkey = ecb_paes_set_key, + .encrypt = ecb_paes_encrypt, + .decrypt = ecb_paes_decrypt, +}; + +static int cbc_paes_init(struct crypto_skcipher *tfm) { - struct blkcipher_walk walk; + struct s390_paes_ctx *ctx = crypto_skcipher_ctx(tfm); - blkcipher_walk_init(&walk, dst, src, nbytes); - return ecb_paes_crypt(desc, CPACF_DECRYPT, &walk); + ctx->kb.key = NULL; + spin_lock_init(&ctx->pk_lock); + + return 0; } -static struct crypto_alg ecb_paes_alg = { - .cra_name = "ecb(paes)", - .cra_driver_name = "ecb-paes-s390", - .cra_priority = 401, /* combo: aes + ecb + 1 */ - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, - .cra_blocksize = AES_BLOCK_SIZE, - .cra_ctxsize = sizeof(struct s390_paes_ctx), - .cra_type = &crypto_blkcipher_type, - .cra_module = THIS_MODULE, - .cra_list = LIST_HEAD_INIT(ecb_paes_alg.cra_list), - .cra_u = { - .blkcipher = { - .min_keysize = MINKEYBLOBSIZE, - .max_keysize = MAXKEYBLOBSIZE, - .setkey = ecb_paes_set_key, - .encrypt = ecb_paes_encrypt, - .decrypt = ecb_paes_decrypt, - } - } -}; +static void cbc_paes_exit(struct crypto_skcipher *tfm) +{ + struct s390_paes_ctx *ctx = crypto_skcipher_ctx(tfm); -static int __cbc_paes_set_key(struct s390_paes_ctx *ctx) + _free_kb_keybuf(&ctx->kb); +} + +static inline int __cbc_paes_set_key(struct s390_paes_ctx *ctx) { unsigned long fc; - if (__paes_convert_key(&ctx->kb, &ctx->pk)) + if (__paes_convert_key(ctx)) return -EINVAL; /* Pick the correct function code based on the protected key type */ @@ -177,24 +298,25 @@ static int __cbc_paes_set_key(struct s390_paes_ctx *ctx) return ctx->fc ? 0 : -EINVAL; } -static int cbc_paes_set_key(struct crypto_tfm *tfm, const u8 *in_key, +static int cbc_paes_set_key(struct crypto_skcipher *tfm, const u8 *in_key, unsigned int key_len) { - struct s390_paes_ctx *ctx = crypto_tfm_ctx(tfm); + int rc; + struct s390_paes_ctx *ctx = crypto_skcipher_ctx(tfm); - memcpy(ctx->kb.key, in_key, key_len); - ctx->kb.keylen = key_len; - if (__cbc_paes_set_key(ctx)) { - tfm->crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN; - return -EINVAL; - } - return 0; + _free_kb_keybuf(&ctx->kb); + rc = _key_to_kb(&ctx->kb, in_key, key_len); + if (rc) + return rc; + + return __cbc_paes_set_key(ctx); } -static int cbc_paes_crypt(struct blkcipher_desc *desc, unsigned long modifier, - struct blkcipher_walk *walk) +static int cbc_paes_crypt(struct skcipher_request *req, unsigned long modifier) { - struct s390_paes_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct s390_paes_ctx *ctx = crypto_skcipher_ctx(tfm); + struct skcipher_walk walk; unsigned int nbytes, n, k; int ret; struct { @@ -202,74 +324,103 @@ static int cbc_paes_crypt(struct blkcipher_desc *desc, unsigned long modifier, u8 key[MAXPROTKEYSIZE]; } param; - ret = blkcipher_walk_virt(desc, walk); - memcpy(param.iv, walk->iv, AES_BLOCK_SIZE); + ret = skcipher_walk_virt(&walk, req, false); + if (ret) + return ret; + + memcpy(param.iv, walk.iv, AES_BLOCK_SIZE); + spin_lock_bh(&ctx->pk_lock); memcpy(param.key, ctx->pk.protkey, MAXPROTKEYSIZE); - while ((nbytes = walk->nbytes) >= AES_BLOCK_SIZE) { + spin_unlock_bh(&ctx->pk_lock); + + while ((nbytes = walk.nbytes) != 0) { /* only use complete blocks */ n = nbytes & ~(AES_BLOCK_SIZE - 1); k = cpacf_kmc(ctx->fc | modifier, ¶m, - walk->dst.virt.addr, walk->src.virt.addr, n); - if (k) - ret = blkcipher_walk_done(desc, walk, nbytes - k); + walk.dst.virt.addr, walk.src.virt.addr, n); + if (k) { + memcpy(walk.iv, param.iv, AES_BLOCK_SIZE); + ret = skcipher_walk_done(&walk, nbytes - k); + } if (k < n) { - if (__cbc_paes_set_key(ctx) != 0) - return blkcipher_walk_done(desc, walk, -EIO); + if (__paes_convert_key(ctx)) + return skcipher_walk_done(&walk, -EIO); + spin_lock_bh(&ctx->pk_lock); memcpy(param.key, ctx->pk.protkey, MAXPROTKEYSIZE); + spin_unlock_bh(&ctx->pk_lock); } } - memcpy(walk->iv, param.iv, AES_BLOCK_SIZE); return ret; } -static int cbc_paes_encrypt(struct blkcipher_desc *desc, - struct scatterlist *dst, struct scatterlist *src, - unsigned int nbytes) +static int cbc_paes_encrypt(struct skcipher_request *req) { - struct blkcipher_walk walk; + return cbc_paes_crypt(req, 0); +} - blkcipher_walk_init(&walk, dst, src, nbytes); - return cbc_paes_crypt(desc, 0, &walk); +static int cbc_paes_decrypt(struct skcipher_request *req) +{ + return cbc_paes_crypt(req, CPACF_DECRYPT); } -static int cbc_paes_decrypt(struct blkcipher_desc *desc, - struct scatterlist *dst, struct scatterlist *src, - unsigned int nbytes) +static struct skcipher_alg cbc_paes_alg = { + .base.cra_name = "cbc(paes)", + .base.cra_driver_name = "cbc-paes-s390", + .base.cra_priority = 402, /* ecb-paes-s390 + 1 */ + .base.cra_blocksize = AES_BLOCK_SIZE, + .base.cra_ctxsize = sizeof(struct s390_paes_ctx), + .base.cra_module = THIS_MODULE, + .base.cra_list = LIST_HEAD_INIT(cbc_paes_alg.base.cra_list), + .init = cbc_paes_init, + .exit = cbc_paes_exit, + .min_keysize = PAES_MIN_KEYSIZE, + .max_keysize = PAES_MAX_KEYSIZE, + .ivsize = AES_BLOCK_SIZE, + .setkey = cbc_paes_set_key, + .encrypt = cbc_paes_encrypt, + .decrypt = cbc_paes_decrypt, +}; + +static int xts_paes_init(struct crypto_skcipher *tfm) { - struct blkcipher_walk walk; + struct s390_pxts_ctx *ctx = crypto_skcipher_ctx(tfm); + + ctx->kb[0].key = NULL; + ctx->kb[1].key = NULL; + spin_lock_init(&ctx->pk_lock); - blkcipher_walk_init(&walk, dst, src, nbytes); - return cbc_paes_crypt(desc, CPACF_DECRYPT, &walk); + return 0; } -static struct crypto_alg cbc_paes_alg = { - .cra_name = "cbc(paes)", - .cra_driver_name = "cbc-paes-s390", - .cra_priority = 402, /* ecb-paes-s390 + 1 */ - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, - .cra_blocksize = AES_BLOCK_SIZE, - .cra_ctxsize = sizeof(struct s390_paes_ctx), - .cra_type = &crypto_blkcipher_type, - .cra_module = THIS_MODULE, - .cra_list = LIST_HEAD_INIT(cbc_paes_alg.cra_list), - .cra_u = { - .blkcipher = { - .min_keysize = MINKEYBLOBSIZE, - .max_keysize = MAXKEYBLOBSIZE, - .ivsize = AES_BLOCK_SIZE, - .setkey = cbc_paes_set_key, - .encrypt = cbc_paes_encrypt, - .decrypt = cbc_paes_decrypt, - } - } -}; +static void xts_paes_exit(struct crypto_skcipher *tfm) +{ + struct s390_pxts_ctx *ctx = crypto_skcipher_ctx(tfm); + + _free_kb_keybuf(&ctx->kb[0]); + _free_kb_keybuf(&ctx->kb[1]); +} + +static inline int __xts_paes_convert_key(struct s390_pxts_ctx *ctx) +{ + struct pkey_protkey pkey0, pkey1; + + if (__paes_keyblob2pkey(&ctx->kb[0], &pkey0) || + __paes_keyblob2pkey(&ctx->kb[1], &pkey1)) + return -EINVAL; + + spin_lock_bh(&ctx->pk_lock); + memcpy(&ctx->pk[0], &pkey0, sizeof(pkey0)); + memcpy(&ctx->pk[1], &pkey1, sizeof(pkey1)); + spin_unlock_bh(&ctx->pk_lock); + + return 0; +} -static int __xts_paes_set_key(struct s390_pxts_ctx *ctx) +static inline int __xts_paes_set_key(struct s390_pxts_ctx *ctx) { unsigned long fc; - if (__paes_convert_key(&ctx->kb[0], &ctx->pk[0]) || - __paes_convert_key(&ctx->kb[1], &ctx->pk[1])) + if (__xts_paes_convert_key(ctx)) return -EINVAL; if (ctx->pk[0].type != ctx->pk[1].type) @@ -286,25 +437,31 @@ static int __xts_paes_set_key(struct s390_pxts_ctx *ctx) return ctx->fc ? 0 : -EINVAL; } -static int xts_paes_set_key(struct crypto_tfm *tfm, const u8 *in_key, - unsigned int key_len) +static int xts_paes_set_key(struct crypto_skcipher *tfm, const u8 *in_key, + unsigned int xts_key_len) { - struct s390_pxts_ctx *ctx = crypto_tfm_ctx(tfm); + int rc; + struct s390_pxts_ctx *ctx = crypto_skcipher_ctx(tfm); u8 ckey[2 * AES_MAX_KEY_SIZE]; - unsigned int ckey_len, keytok_len; + unsigned int ckey_len, key_len; - if (key_len % 2) + if (xts_key_len % 2) return -EINVAL; - keytok_len = key_len / 2; - memcpy(ctx->kb[0].key, in_key, keytok_len); - ctx->kb[0].keylen = keytok_len; - memcpy(ctx->kb[1].key, in_key + keytok_len, keytok_len); - ctx->kb[1].keylen = keytok_len; - if (__xts_paes_set_key(ctx)) { - tfm->crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN; - return -EINVAL; - } + key_len = xts_key_len / 2; + + _free_kb_keybuf(&ctx->kb[0]); + _free_kb_keybuf(&ctx->kb[1]); + rc = _key_to_kb(&ctx->kb[0], in_key, key_len); + if (rc) + return rc; + rc = _key_to_kb(&ctx->kb[1], in_key + key_len, key_len); + if (rc) + return rc; + + rc = __xts_paes_set_key(ctx); + if (rc) + return rc; /* * xts_check_key verifies the key length is not odd and makes @@ -315,13 +472,14 @@ static int xts_paes_set_key(struct crypto_tfm *tfm, const u8 *in_key, AES_KEYSIZE_128 : AES_KEYSIZE_256; memcpy(ckey, ctx->pk[0].protkey, ckey_len); memcpy(ckey + ckey_len, ctx->pk[1].protkey, ckey_len); - return xts_check_key(tfm, ckey, 2*ckey_len); + return xts_verify_key(tfm, ckey, 2*ckey_len); } -static int xts_paes_crypt(struct blkcipher_desc *desc, unsigned long modifier, - struct blkcipher_walk *walk) +static int xts_paes_crypt(struct skcipher_request *req, unsigned long modifier) { - struct s390_pxts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct s390_pxts_ctx *ctx = crypto_skcipher_ctx(tfm); + struct skcipher_walk walk; unsigned int keylen, offset, nbytes, n, k; int ret; struct { @@ -336,81 +494,92 @@ static int xts_paes_crypt(struct blkcipher_desc *desc, unsigned long modifier, u8 init[16]; } xts_param; - ret = blkcipher_walk_virt(desc, walk); + ret = skcipher_walk_virt(&walk, req, false); + if (ret) + return ret; + keylen = (ctx->pk[0].type == PKEY_KEYTYPE_AES_128) ? 48 : 64; offset = (ctx->pk[0].type == PKEY_KEYTYPE_AES_128) ? 16 : 0; -retry: + memset(&pcc_param, 0, sizeof(pcc_param)); - memcpy(pcc_param.tweak, walk->iv, sizeof(pcc_param.tweak)); + memcpy(pcc_param.tweak, walk.iv, sizeof(pcc_param.tweak)); + spin_lock_bh(&ctx->pk_lock); memcpy(pcc_param.key + offset, ctx->pk[1].protkey, keylen); - cpacf_pcc(ctx->fc, pcc_param.key + offset); - memcpy(xts_param.key + offset, ctx->pk[0].protkey, keylen); + spin_unlock_bh(&ctx->pk_lock); + cpacf_pcc(ctx->fc, pcc_param.key + offset); memcpy(xts_param.init, pcc_param.xts, 16); - while ((nbytes = walk->nbytes) >= AES_BLOCK_SIZE) { + while ((nbytes = walk.nbytes) != 0) { /* only use complete blocks */ n = nbytes & ~(AES_BLOCK_SIZE - 1); k = cpacf_km(ctx->fc | modifier, xts_param.key + offset, - walk->dst.virt.addr, walk->src.virt.addr, n); + walk.dst.virt.addr, walk.src.virt.addr, n); if (k) - ret = blkcipher_walk_done(desc, walk, nbytes - k); + ret = skcipher_walk_done(&walk, nbytes - k); if (k < n) { - if (__xts_paes_set_key(ctx) != 0) - return blkcipher_walk_done(desc, walk, -EIO); - goto retry; + if (__xts_paes_convert_key(ctx)) + return skcipher_walk_done(&walk, -EIO); + spin_lock_bh(&ctx->pk_lock); + memcpy(xts_param.key + offset, + ctx->pk[0].protkey, keylen); + spin_unlock_bh(&ctx->pk_lock); } } + return ret; } -static int xts_paes_encrypt(struct blkcipher_desc *desc, - struct scatterlist *dst, struct scatterlist *src, - unsigned int nbytes) +static int xts_paes_encrypt(struct skcipher_request *req) { - struct blkcipher_walk walk; + return xts_paes_crypt(req, 0); +} - blkcipher_walk_init(&walk, dst, src, nbytes); - return xts_paes_crypt(desc, 0, &walk); +static int xts_paes_decrypt(struct skcipher_request *req) +{ + return xts_paes_crypt(req, CPACF_DECRYPT); } -static int xts_paes_decrypt(struct blkcipher_desc *desc, - struct scatterlist *dst, struct scatterlist *src, - unsigned int nbytes) +static struct skcipher_alg xts_paes_alg = { + .base.cra_name = "xts(paes)", + .base.cra_driver_name = "xts-paes-s390", + .base.cra_priority = 402, /* ecb-paes-s390 + 1 */ + .base.cra_blocksize = AES_BLOCK_SIZE, + .base.cra_ctxsize = sizeof(struct s390_pxts_ctx), + .base.cra_module = THIS_MODULE, + .base.cra_list = LIST_HEAD_INIT(xts_paes_alg.base.cra_list), + .init = xts_paes_init, + .exit = xts_paes_exit, + .min_keysize = 2 * PAES_MIN_KEYSIZE, + .max_keysize = 2 * PAES_MAX_KEYSIZE, + .ivsize = AES_BLOCK_SIZE, + .setkey = xts_paes_set_key, + .encrypt = xts_paes_encrypt, + .decrypt = xts_paes_decrypt, +}; + +static int ctr_paes_init(struct crypto_skcipher *tfm) { - struct blkcipher_walk walk; + struct s390_paes_ctx *ctx = crypto_skcipher_ctx(tfm); + + ctx->kb.key = NULL; + spin_lock_init(&ctx->pk_lock); - blkcipher_walk_init(&walk, dst, src, nbytes); - return xts_paes_crypt(desc, CPACF_DECRYPT, &walk); + return 0; } -static struct crypto_alg xts_paes_alg = { - .cra_name = "xts(paes)", - .cra_driver_name = "xts-paes-s390", - .cra_priority = 402, /* ecb-paes-s390 + 1 */ - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, - .cra_blocksize = AES_BLOCK_SIZE, - .cra_ctxsize = sizeof(struct s390_pxts_ctx), - .cra_type = &crypto_blkcipher_type, - .cra_module = THIS_MODULE, - .cra_list = LIST_HEAD_INIT(xts_paes_alg.cra_list), - .cra_u = { - .blkcipher = { - .min_keysize = 2 * MINKEYBLOBSIZE, - .max_keysize = 2 * MAXKEYBLOBSIZE, - .ivsize = AES_BLOCK_SIZE, - .setkey = xts_paes_set_key, - .encrypt = xts_paes_encrypt, - .decrypt = xts_paes_decrypt, - } - } -}; +static void ctr_paes_exit(struct crypto_skcipher *tfm) +{ + struct s390_paes_ctx *ctx = crypto_skcipher_ctx(tfm); -static int __ctr_paes_set_key(struct s390_paes_ctx *ctx) + _free_kb_keybuf(&ctx->kb); +} + +static inline int __ctr_paes_set_key(struct s390_paes_ctx *ctx) { unsigned long fc; - if (__paes_convert_key(&ctx->kb, &ctx->pk)) + if (__paes_convert_key(ctx)) return -EINVAL; /* Pick the correct function code based on the protected key type */ @@ -425,18 +594,18 @@ static int __ctr_paes_set_key(struct s390_paes_ctx *ctx) return ctx->fc ? 0 : -EINVAL; } -static int ctr_paes_set_key(struct crypto_tfm *tfm, const u8 *in_key, +static int ctr_paes_set_key(struct crypto_skcipher *tfm, const u8 *in_key, unsigned int key_len) { - struct s390_paes_ctx *ctx = crypto_tfm_ctx(tfm); + int rc; + struct s390_paes_ctx *ctx = crypto_skcipher_ctx(tfm); - memcpy(ctx->kb.key, in_key, key_len); - ctx->kb.keylen = key_len; - if (__ctr_paes_set_key(ctx)) { - tfm->crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN; - return -EINVAL; - } - return 0; + _free_kb_keybuf(&ctx->kb); + rc = _key_to_kb(&ctx->kb, in_key, key_len); + if (rc) + return rc; + + return __ctr_paes_set_key(ctx); } static unsigned int __ctrblk_init(u8 *ctrptr, u8 *iv, unsigned int nbytes) @@ -454,119 +623,111 @@ static unsigned int __ctrblk_init(u8 *ctrptr, u8 *iv, unsigned int nbytes) return n; } -static int ctr_paes_crypt(struct blkcipher_desc *desc, unsigned long modifier, - struct blkcipher_walk *walk) +static int ctr_paes_crypt(struct skcipher_request *req) { - struct s390_paes_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct s390_paes_ctx *ctx = crypto_skcipher_ctx(tfm); u8 buf[AES_BLOCK_SIZE], *ctrptr; + struct skcipher_walk walk; unsigned int nbytes, n, k; int ret, locked; + struct { + u8 key[MAXPROTKEYSIZE]; + } param; + + ret = skcipher_walk_virt(&walk, req, false); + if (ret) + return ret; + + spin_lock_bh(&ctx->pk_lock); + memcpy(param.key, ctx->pk.protkey, MAXPROTKEYSIZE); + spin_unlock_bh(&ctx->pk_lock); - locked = spin_trylock(&ctrblk_lock); + locked = mutex_trylock(&ctrblk_lock); - ret = blkcipher_walk_virt_block(desc, walk, AES_BLOCK_SIZE); - while ((nbytes = walk->nbytes) >= AES_BLOCK_SIZE) { + while ((nbytes = walk.nbytes) >= AES_BLOCK_SIZE) { n = AES_BLOCK_SIZE; if (nbytes >= 2*AES_BLOCK_SIZE && locked) - n = __ctrblk_init(ctrblk, walk->iv, nbytes); - ctrptr = (n > AES_BLOCK_SIZE) ? ctrblk : walk->iv; - k = cpacf_kmctr(ctx->fc | modifier, ctx->pk.protkey, - walk->dst.virt.addr, walk->src.virt.addr, - n, ctrptr); + n = __ctrblk_init(ctrblk, walk.iv, nbytes); + ctrptr = (n > AES_BLOCK_SIZE) ? ctrblk : walk.iv; + k = cpacf_kmctr(ctx->fc, ¶m, walk.dst.virt.addr, + walk.src.virt.addr, n, ctrptr); if (k) { if (ctrptr == ctrblk) - memcpy(walk->iv, ctrptr + k - AES_BLOCK_SIZE, + memcpy(walk.iv, ctrptr + k - AES_BLOCK_SIZE, AES_BLOCK_SIZE); - crypto_inc(walk->iv, AES_BLOCK_SIZE); - ret = blkcipher_walk_done(desc, walk, nbytes - n); + crypto_inc(walk.iv, AES_BLOCK_SIZE); + ret = skcipher_walk_done(&walk, nbytes - k); } if (k < n) { - if (__ctr_paes_set_key(ctx) != 0) { + if (__paes_convert_key(ctx)) { if (locked) - spin_unlock(&ctrblk_lock); - return blkcipher_walk_done(desc, walk, -EIO); + mutex_unlock(&ctrblk_lock); + return skcipher_walk_done(&walk, -EIO); } + spin_lock_bh(&ctx->pk_lock); + memcpy(param.key, ctx->pk.protkey, MAXPROTKEYSIZE); + spin_unlock_bh(&ctx->pk_lock); } } if (locked) - spin_unlock(&ctrblk_lock); + mutex_unlock(&ctrblk_lock); /* * final block may be < AES_BLOCK_SIZE, copy only nbytes */ if (nbytes) { while (1) { - if (cpacf_kmctr(ctx->fc | modifier, - ctx->pk.protkey, buf, - walk->src.virt.addr, AES_BLOCK_SIZE, - walk->iv) == AES_BLOCK_SIZE) + if (cpacf_kmctr(ctx->fc, ¶m, buf, + walk.src.virt.addr, AES_BLOCK_SIZE, + walk.iv) == AES_BLOCK_SIZE) break; - if (__ctr_paes_set_key(ctx) != 0) - return blkcipher_walk_done(desc, walk, -EIO); + if (__paes_convert_key(ctx)) + return skcipher_walk_done(&walk, -EIO); + spin_lock_bh(&ctx->pk_lock); + memcpy(param.key, ctx->pk.protkey, MAXPROTKEYSIZE); + spin_unlock_bh(&ctx->pk_lock); } - memcpy(walk->dst.virt.addr, buf, nbytes); - crypto_inc(walk->iv, AES_BLOCK_SIZE); - ret = blkcipher_walk_done(desc, walk, 0); + memcpy(walk.dst.virt.addr, buf, nbytes); + crypto_inc(walk.iv, AES_BLOCK_SIZE); + ret = skcipher_walk_done(&walk, nbytes); } return ret; } -static int ctr_paes_encrypt(struct blkcipher_desc *desc, - struct scatterlist *dst, struct scatterlist *src, - unsigned int nbytes) -{ - struct blkcipher_walk walk; - - blkcipher_walk_init(&walk, dst, src, nbytes); - return ctr_paes_crypt(desc, 0, &walk); -} - -static int ctr_paes_decrypt(struct blkcipher_desc *desc, - struct scatterlist *dst, struct scatterlist *src, - unsigned int nbytes) -{ - struct blkcipher_walk walk; - - blkcipher_walk_init(&walk, dst, src, nbytes); - return ctr_paes_crypt(desc, CPACF_DECRYPT, &walk); -} - -static struct crypto_alg ctr_paes_alg = { - .cra_name = "ctr(paes)", - .cra_driver_name = "ctr-paes-s390", - .cra_priority = 402, /* ecb-paes-s390 + 1 */ - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, - .cra_blocksize = 1, - .cra_ctxsize = sizeof(struct s390_paes_ctx), - .cra_type = &crypto_blkcipher_type, - .cra_module = THIS_MODULE, - .cra_list = LIST_HEAD_INIT(ctr_paes_alg.cra_list), - .cra_u = { - .blkcipher = { - .min_keysize = MINKEYBLOBSIZE, - .max_keysize = MAXKEYBLOBSIZE, - .ivsize = AES_BLOCK_SIZE, - .setkey = ctr_paes_set_key, - .encrypt = ctr_paes_encrypt, - .decrypt = ctr_paes_decrypt, - } - } +static struct skcipher_alg ctr_paes_alg = { + .base.cra_name = "ctr(paes)", + .base.cra_driver_name = "ctr-paes-s390", + .base.cra_priority = 402, /* ecb-paes-s390 + 1 */ + .base.cra_blocksize = 1, + .base.cra_ctxsize = sizeof(struct s390_paes_ctx), + .base.cra_module = THIS_MODULE, + .base.cra_list = LIST_HEAD_INIT(ctr_paes_alg.base.cra_list), + .init = ctr_paes_init, + .exit = ctr_paes_exit, + .min_keysize = PAES_MIN_KEYSIZE, + .max_keysize = PAES_MAX_KEYSIZE, + .ivsize = AES_BLOCK_SIZE, + .setkey = ctr_paes_set_key, + .encrypt = ctr_paes_crypt, + .decrypt = ctr_paes_crypt, + .chunksize = AES_BLOCK_SIZE, }; -static inline void __crypto_unregister_alg(struct crypto_alg *alg) +static inline void __crypto_unregister_skcipher(struct skcipher_alg *alg) { - if (!list_empty(&alg->cra_list)) - crypto_unregister_alg(alg); + if (!list_empty(&alg->base.cra_list)) + crypto_unregister_skcipher(alg); } static void paes_s390_fini(void) { + __crypto_unregister_skcipher(&ctr_paes_alg); + __crypto_unregister_skcipher(&xts_paes_alg); + __crypto_unregister_skcipher(&cbc_paes_alg); + __crypto_unregister_skcipher(&ecb_paes_alg); if (ctrblk) free_page((unsigned long) ctrblk); - __crypto_unregister_alg(&ctr_paes_alg); - __crypto_unregister_alg(&xts_paes_alg); - __crypto_unregister_alg(&cbc_paes_alg); - __crypto_unregister_alg(&ecb_paes_alg); } static int __init paes_s390_init(void) @@ -581,7 +742,7 @@ static int __init paes_s390_init(void) if (cpacf_test_func(&km_functions, CPACF_KM_PAES_128) || cpacf_test_func(&km_functions, CPACF_KM_PAES_192) || cpacf_test_func(&km_functions, CPACF_KM_PAES_256)) { - ret = crypto_register_alg(&ecb_paes_alg); + ret = crypto_register_skcipher(&ecb_paes_alg); if (ret) goto out_err; } @@ -589,14 +750,14 @@ static int __init paes_s390_init(void) if (cpacf_test_func(&kmc_functions, CPACF_KMC_PAES_128) || cpacf_test_func(&kmc_functions, CPACF_KMC_PAES_192) || cpacf_test_func(&kmc_functions, CPACF_KMC_PAES_256)) { - ret = crypto_register_alg(&cbc_paes_alg); + ret = crypto_register_skcipher(&cbc_paes_alg); if (ret) goto out_err; } if (cpacf_test_func(&km_functions, CPACF_KM_PXTS_128) || cpacf_test_func(&km_functions, CPACF_KM_PXTS_256)) { - ret = crypto_register_alg(&xts_paes_alg); + ret = crypto_register_skcipher(&xts_paes_alg); if (ret) goto out_err; } @@ -604,14 +765,14 @@ static int __init paes_s390_init(void) if (cpacf_test_func(&kmctr_functions, CPACF_KMCTR_PAES_128) || cpacf_test_func(&kmctr_functions, CPACF_KMCTR_PAES_192) || cpacf_test_func(&kmctr_functions, CPACF_KMCTR_PAES_256)) { - ret = crypto_register_alg(&ctr_paes_alg); - if (ret) - goto out_err; ctrblk = (u8 *) __get_free_page(GFP_KERNEL); if (!ctrblk) { ret = -ENOMEM; goto out_err; } + ret = crypto_register_skcipher(&ctr_paes_alg); + if (ret) + goto out_err; } return 0; diff --git a/arch/s390/crypto/sha.h b/arch/s390/crypto/sha.h index d6f8258b44df..ada2f98c27b7 100644 --- a/arch/s390/crypto/sha.h +++ b/arch/s390/crypto/sha.h @@ -12,15 +12,17 @@ #include <linux/crypto.h> #include <crypto/sha.h> +#include <crypto/sha3.h> /* must be big enough for the largest SHA variant */ -#define SHA_MAX_STATE_SIZE (SHA512_DIGEST_SIZE / 4) -#define SHA_MAX_BLOCK_SIZE SHA512_BLOCK_SIZE +#define SHA3_STATE_SIZE 200 +#define CPACF_MAX_PARMBLOCK_SIZE SHA3_STATE_SIZE +#define SHA_MAX_BLOCK_SIZE SHA3_224_BLOCK_SIZE struct s390_sha_ctx { - u64 count; /* message length in bytes */ - u32 state[SHA_MAX_STATE_SIZE]; - u8 buf[2 * SHA_MAX_BLOCK_SIZE]; + u64 count; /* message length in bytes */ + u32 state[CPACF_MAX_PARMBLOCK_SIZE / sizeof(u32)]; + u8 buf[SHA_MAX_BLOCK_SIZE]; int func; /* KIMD function to use */ }; diff --git a/arch/s390/crypto/sha256_s390.c b/arch/s390/crypto/sha256_s390.c index af7505148f80..b52c87e44939 100644 --- a/arch/s390/crypto/sha256_s390.c +++ b/arch/s390/crypto/sha256_s390.c @@ -17,7 +17,7 @@ #include "sha.h" -static int sha256_init(struct shash_desc *desc) +static int s390_sha256_init(struct shash_desc *desc) { struct s390_sha_ctx *sctx = shash_desc_ctx(desc); @@ -60,7 +60,7 @@ static int sha256_import(struct shash_desc *desc, const void *in) static struct shash_alg sha256_alg = { .digestsize = SHA256_DIGEST_SIZE, - .init = sha256_init, + .init = s390_sha256_init, .update = s390_sha_update, .final = s390_sha_final, .export = sha256_export, @@ -76,7 +76,7 @@ static struct shash_alg sha256_alg = { } }; -static int sha224_init(struct shash_desc *desc) +static int s390_sha224_init(struct shash_desc *desc) { struct s390_sha_ctx *sctx = shash_desc_ctx(desc); @@ -96,7 +96,7 @@ static int sha224_init(struct shash_desc *desc) static struct shash_alg sha224_alg = { .digestsize = SHA224_DIGEST_SIZE, - .init = sha224_init, + .init = s390_sha224_init, .update = s390_sha_update, .final = s390_sha_final, .export = sha256_export, diff --git a/arch/s390/crypto/sha3_256_s390.c b/arch/s390/crypto/sha3_256_s390.c new file mode 100644 index 000000000000..460cbbbaa44a --- /dev/null +++ b/arch/s390/crypto/sha3_256_s390.c @@ -0,0 +1,147 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Cryptographic API. + * + * s390 implementation of the SHA256 and SHA224 Secure Hash Algorithm. + * + * s390 Version: + * Copyright IBM Corp. 2019 + * Author(s): Joerg Schmidbauer (jschmidb@de.ibm.com) + */ +#include <crypto/internal/hash.h> +#include <linux/init.h> +#include <linux/module.h> +#include <linux/cpufeature.h> +#include <crypto/sha.h> +#include <crypto/sha3.h> +#include <asm/cpacf.h> + +#include "sha.h" + +static int sha3_256_init(struct shash_desc *desc) +{ + struct s390_sha_ctx *sctx = shash_desc_ctx(desc); + + memset(sctx->state, 0, sizeof(sctx->state)); + sctx->count = 0; + sctx->func = CPACF_KIMD_SHA3_256; + + return 0; +} + +static int sha3_256_export(struct shash_desc *desc, void *out) +{ + struct s390_sha_ctx *sctx = shash_desc_ctx(desc); + struct sha3_state *octx = out; + + octx->rsiz = sctx->count; + memcpy(octx->st, sctx->state, sizeof(octx->st)); + memcpy(octx->buf, sctx->buf, sizeof(octx->buf)); + + return 0; +} + +static int sha3_256_import(struct shash_desc *desc, const void *in) +{ + struct s390_sha_ctx *sctx = shash_desc_ctx(desc); + const struct sha3_state *ictx = in; + + sctx->count = ictx->rsiz; + memcpy(sctx->state, ictx->st, sizeof(ictx->st)); + memcpy(sctx->buf, ictx->buf, sizeof(ictx->buf)); + sctx->func = CPACF_KIMD_SHA3_256; + + return 0; +} + +static int sha3_224_import(struct shash_desc *desc, const void *in) +{ + struct s390_sha_ctx *sctx = shash_desc_ctx(desc); + const struct sha3_state *ictx = in; + + sctx->count = ictx->rsiz; + memcpy(sctx->state, ictx->st, sizeof(ictx->st)); + memcpy(sctx->buf, ictx->buf, sizeof(ictx->buf)); + sctx->func = CPACF_KIMD_SHA3_224; + + return 0; +} + +static struct shash_alg sha3_256_alg = { + .digestsize = SHA3_256_DIGEST_SIZE, /* = 32 */ + .init = sha3_256_init, + .update = s390_sha_update, + .final = s390_sha_final, + .export = sha3_256_export, + .import = sha3_256_import, + .descsize = sizeof(struct s390_sha_ctx), + .statesize = sizeof(struct sha3_state), + .base = { + .cra_name = "sha3-256", + .cra_driver_name = "sha3-256-s390", + .cra_priority = 300, + .cra_blocksize = SHA3_256_BLOCK_SIZE, + .cra_module = THIS_MODULE, + } +}; + +static int sha3_224_init(struct shash_desc *desc) +{ + struct s390_sha_ctx *sctx = shash_desc_ctx(desc); + + memset(sctx->state, 0, sizeof(sctx->state)); + sctx->count = 0; + sctx->func = CPACF_KIMD_SHA3_224; + + return 0; +} + +static struct shash_alg sha3_224_alg = { + .digestsize = SHA3_224_DIGEST_SIZE, + .init = sha3_224_init, + .update = s390_sha_update, + .final = s390_sha_final, + .export = sha3_256_export, /* same as for 256 */ + .import = sha3_224_import, /* function code different! */ + .descsize = sizeof(struct s390_sha_ctx), + .statesize = sizeof(struct sha3_state), + .base = { + .cra_name = "sha3-224", + .cra_driver_name = "sha3-224-s390", + .cra_priority = 300, + .cra_blocksize = SHA3_224_BLOCK_SIZE, + .cra_module = THIS_MODULE, + } +}; + +static int __init sha3_256_s390_init(void) +{ + int ret; + + if (!cpacf_query_func(CPACF_KIMD, CPACF_KIMD_SHA3_256)) + return -ENODEV; + + ret = crypto_register_shash(&sha3_256_alg); + if (ret < 0) + goto out; + + ret = crypto_register_shash(&sha3_224_alg); + if (ret < 0) + crypto_unregister_shash(&sha3_256_alg); +out: + return ret; +} + +static void __exit sha3_256_s390_fini(void) +{ + crypto_unregister_shash(&sha3_224_alg); + crypto_unregister_shash(&sha3_256_alg); +} + +module_cpu_feature_match(MSA, sha3_256_s390_init); +module_exit(sha3_256_s390_fini); + +MODULE_ALIAS_CRYPTO("sha3-256"); +MODULE_ALIAS_CRYPTO("sha3-224"); +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("SHA3-256 and SHA3-224 Secure Hash Algorithm"); diff --git a/arch/s390/crypto/sha3_512_s390.c b/arch/s390/crypto/sha3_512_s390.c new file mode 100644 index 000000000000..72cf460a53e5 --- /dev/null +++ b/arch/s390/crypto/sha3_512_s390.c @@ -0,0 +1,155 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Cryptographic API. + * + * s390 implementation of the SHA512 and SHA384 Secure Hash Algorithm. + * + * Copyright IBM Corp. 2019 + * Author(s): Joerg Schmidbauer (jschmidb@de.ibm.com) + */ +#include <crypto/internal/hash.h> +#include <linux/init.h> +#include <linux/module.h> +#include <linux/cpufeature.h> +#include <crypto/sha.h> +#include <crypto/sha3.h> +#include <asm/cpacf.h> + +#include "sha.h" + +static int sha3_512_init(struct shash_desc *desc) +{ + struct s390_sha_ctx *sctx = shash_desc_ctx(desc); + + memset(sctx->state, 0, sizeof(sctx->state)); + sctx->count = 0; + sctx->func = CPACF_KIMD_SHA3_512; + + return 0; +} + +static int sha3_512_export(struct shash_desc *desc, void *out) +{ + struct s390_sha_ctx *sctx = shash_desc_ctx(desc); + struct sha3_state *octx = out; + + octx->rsiz = sctx->count; + octx->rsizw = sctx->count >> 32; + + memcpy(octx->st, sctx->state, sizeof(octx->st)); + memcpy(octx->buf, sctx->buf, sizeof(octx->buf)); + + return 0; +} + +static int sha3_512_import(struct shash_desc *desc, const void *in) +{ + struct s390_sha_ctx *sctx = shash_desc_ctx(desc); + const struct sha3_state *ictx = in; + + if (unlikely(ictx->rsizw)) + return -ERANGE; + sctx->count = ictx->rsiz; + + memcpy(sctx->state, ictx->st, sizeof(ictx->st)); + memcpy(sctx->buf, ictx->buf, sizeof(ictx->buf)); + sctx->func = CPACF_KIMD_SHA3_512; + + return 0; +} + +static int sha3_384_import(struct shash_desc *desc, const void *in) +{ + struct s390_sha_ctx *sctx = shash_desc_ctx(desc); + const struct sha3_state *ictx = in; + + if (unlikely(ictx->rsizw)) + return -ERANGE; + sctx->count = ictx->rsiz; + + memcpy(sctx->state, ictx->st, sizeof(ictx->st)); + memcpy(sctx->buf, ictx->buf, sizeof(ictx->buf)); + sctx->func = CPACF_KIMD_SHA3_384; + + return 0; +} + +static struct shash_alg sha3_512_alg = { + .digestsize = SHA3_512_DIGEST_SIZE, + .init = sha3_512_init, + .update = s390_sha_update, + .final = s390_sha_final, + .export = sha3_512_export, + .import = sha3_512_import, + .descsize = sizeof(struct s390_sha_ctx), + .statesize = sizeof(struct sha3_state), + .base = { + .cra_name = "sha3-512", + .cra_driver_name = "sha3-512-s390", + .cra_priority = 300, + .cra_blocksize = SHA3_512_BLOCK_SIZE, + .cra_module = THIS_MODULE, + } +}; + +MODULE_ALIAS_CRYPTO("sha3-512"); + +static int sha3_384_init(struct shash_desc *desc) +{ + struct s390_sha_ctx *sctx = shash_desc_ctx(desc); + + memset(sctx->state, 0, sizeof(sctx->state)); + sctx->count = 0; + sctx->func = CPACF_KIMD_SHA3_384; + + return 0; +} + +static struct shash_alg sha3_384_alg = { + .digestsize = SHA3_384_DIGEST_SIZE, + .init = sha3_384_init, + .update = s390_sha_update, + .final = s390_sha_final, + .export = sha3_512_export, /* same as for 512 */ + .import = sha3_384_import, /* function code different! */ + .descsize = sizeof(struct s390_sha_ctx), + .statesize = sizeof(struct sha3_state), + .base = { + .cra_name = "sha3-384", + .cra_driver_name = "sha3-384-s390", + .cra_priority = 300, + .cra_blocksize = SHA3_384_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct s390_sha_ctx), + .cra_module = THIS_MODULE, + } +}; + +MODULE_ALIAS_CRYPTO("sha3-384"); + +static int __init init(void) +{ + int ret; + + if (!cpacf_query_func(CPACF_KIMD, CPACF_KIMD_SHA3_512)) + return -ENODEV; + ret = crypto_register_shash(&sha3_512_alg); + if (ret < 0) + goto out; + ret = crypto_register_shash(&sha3_384_alg); + if (ret < 0) + crypto_unregister_shash(&sha3_512_alg); +out: + return ret; +} + +static void __exit fini(void) +{ + crypto_unregister_shash(&sha3_512_alg); + crypto_unregister_shash(&sha3_384_alg); +} + +module_cpu_feature_match(MSA, init); +module_exit(fini); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("SHA3-512 and SHA3-384 Secure Hash Algorithm"); diff --git a/arch/s390/crypto/sha_common.c b/arch/s390/crypto/sha_common.c index cf0718d121bc..686fe7aa192f 100644 --- a/arch/s390/crypto/sha_common.c +++ b/arch/s390/crypto/sha_common.c @@ -20,7 +20,7 @@ int s390_sha_update(struct shash_desc *desc, const u8 *data, unsigned int len) unsigned int index, n; /* how much is already in the buffer? */ - index = ctx->count & (bsize - 1); + index = ctx->count % bsize; ctx->count += len; if ((index + len) < bsize) @@ -37,7 +37,7 @@ int s390_sha_update(struct shash_desc *desc, const u8 *data, unsigned int len) /* process as many blocks as possible */ if (len >= bsize) { - n = len & ~(bsize - 1); + n = (len / bsize) * bsize; cpacf_kimd(ctx->func, ctx->state, data, n); data += n; len -= n; @@ -50,34 +50,66 @@ store: } EXPORT_SYMBOL_GPL(s390_sha_update); +static int s390_crypto_shash_parmsize(int func) +{ + switch (func) { + case CPACF_KLMD_SHA_1: + return 20; + case CPACF_KLMD_SHA_256: + return 32; + case CPACF_KLMD_SHA_512: + return 64; + case CPACF_KLMD_SHA3_224: + case CPACF_KLMD_SHA3_256: + case CPACF_KLMD_SHA3_384: + case CPACF_KLMD_SHA3_512: + return 200; + default: + return -EINVAL; + } +} + int s390_sha_final(struct shash_desc *desc, u8 *out) { struct s390_sha_ctx *ctx = shash_desc_ctx(desc); unsigned int bsize = crypto_shash_blocksize(desc->tfm); u64 bits; - unsigned int index, end, plen; - - /* SHA-512 uses 128 bit padding length */ - plen = (bsize > SHA256_BLOCK_SIZE) ? 16 : 8; + unsigned int n; + int mbl_offset; - /* must perform manual padding */ - index = ctx->count & (bsize - 1); - end = (index < bsize - plen) ? bsize : (2 * bsize); - - /* start pad with 1 */ - ctx->buf[index] = 0x80; - index++; - - /* pad with zeros */ - memset(ctx->buf + index, 0x00, end - index - 8); - - /* - * Append message length. Well, SHA-512 wants a 128 bit length value, - * nevertheless we use u64, should be enough for now... - */ + n = ctx->count % bsize; bits = ctx->count * 8; - memcpy(ctx->buf + end - 8, &bits, sizeof(bits)); - cpacf_kimd(ctx->func, ctx->state, ctx->buf, end); + mbl_offset = s390_crypto_shash_parmsize(ctx->func); + if (mbl_offset < 0) + return -EINVAL; + + mbl_offset = mbl_offset / sizeof(u32); + + /* set total msg bit length (mbl) in CPACF parmblock */ + switch (ctx->func) { + case CPACF_KLMD_SHA_1: + case CPACF_KLMD_SHA_256: + memcpy(ctx->state + mbl_offset, &bits, sizeof(bits)); + break; + case CPACF_KLMD_SHA_512: + /* + * the SHA512 parmblock has a 128-bit mbl field, clear + * high-order u64 field, copy bits to low-order u64 field + */ + memset(ctx->state + mbl_offset, 0x00, sizeof(bits)); + mbl_offset += sizeof(u64) / sizeof(u32); + memcpy(ctx->state + mbl_offset, &bits, sizeof(bits)); + break; + case CPACF_KLMD_SHA3_224: + case CPACF_KLMD_SHA3_256: + case CPACF_KLMD_SHA3_384: + case CPACF_KLMD_SHA3_512: + break; + default: + return -EINVAL; + } + + cpacf_klmd(ctx->func, ctx->state, ctx->buf, n); /* copy digest to out */ memcpy(out, ctx->state, crypto_shash_digestsize(desc->tfm)); diff --git a/arch/s390/hypfs/inode.c b/arch/s390/hypfs/inode.c index ccad1398abd4..5c97f48cea91 100644 --- a/arch/s390/hypfs/inode.c +++ b/arch/s390/hypfs/inode.c @@ -12,17 +12,17 @@ #include <linux/types.h> #include <linux/errno.h> #include <linux/fs.h> +#include <linux/fs_context.h> +#include <linux/fs_parser.h> #include <linux/namei.h> #include <linux/vfs.h> #include <linux/slab.h> #include <linux/pagemap.h> #include <linux/time.h> -#include <linux/parser.h> #include <linux/sysfs.h> #include <linux/init.h> #include <linux/kobject.h> #include <linux/seq_file.h> -#include <linux/mount.h> #include <linux/uio.h> #include <asm/ebcdic.h> #include "hypfs.h" @@ -76,7 +76,7 @@ static void hypfs_remove(struct dentry *dentry) else simple_unlink(d_inode(parent), dentry); } - d_delete(dentry); + d_drop(dentry); dput(dentry); inode_unlock(d_inode(parent)); } @@ -207,52 +207,39 @@ static int hypfs_release(struct inode *inode, struct file *filp) return 0; } -enum { opt_uid, opt_gid, opt_err }; +enum { Opt_uid, Opt_gid, }; -static const match_table_t hypfs_tokens = { - {opt_uid, "uid=%u"}, - {opt_gid, "gid=%u"}, - {opt_err, NULL} +static const struct fs_parameter_spec hypfs_fs_parameters[] = { + fsparam_u32("gid", Opt_gid), + fsparam_u32("uid", Opt_uid), + {} }; -static int hypfs_parse_options(char *options, struct super_block *sb) +static int hypfs_parse_param(struct fs_context *fc, struct fs_parameter *param) { - char *str; - substring_t args[MAX_OPT_ARGS]; + struct hypfs_sb_info *hypfs_info = fc->s_fs_info; + struct fs_parse_result result; kuid_t uid; kgid_t gid; - - if (!options) - return 0; - while ((str = strsep(&options, ",")) != NULL) { - int token, option; - struct hypfs_sb_info *hypfs_info = sb->s_fs_info; - - if (!*str) - continue; - token = match_token(str, hypfs_tokens, args); - switch (token) { - case opt_uid: - if (match_int(&args[0], &option)) - return -EINVAL; - uid = make_kuid(current_user_ns(), option); - if (!uid_valid(uid)) - return -EINVAL; - hypfs_info->uid = uid; - break; - case opt_gid: - if (match_int(&args[0], &option)) - return -EINVAL; - gid = make_kgid(current_user_ns(), option); - if (!gid_valid(gid)) - return -EINVAL; - hypfs_info->gid = gid; - break; - case opt_err: - default: - pr_err("%s is not a valid mount option\n", str); - return -EINVAL; - } + int opt; + + opt = fs_parse(fc, hypfs_fs_parameters, param, &result); + if (opt < 0) + return opt; + + switch (opt) { + case Opt_uid: + uid = make_kuid(current_user_ns(), result.uint_32); + if (!uid_valid(uid)) + return invalf(fc, "Unknown uid"); + hypfs_info->uid = uid; + break; + case Opt_gid: + gid = make_kgid(current_user_ns(), result.uint_32); + if (!gid_valid(gid)) + return invalf(fc, "Unknown gid"); + hypfs_info->gid = gid; + break; } return 0; } @@ -266,26 +253,18 @@ static int hypfs_show_options(struct seq_file *s, struct dentry *root) return 0; } -static int hypfs_fill_super(struct super_block *sb, void *data, int silent) +static int hypfs_fill_super(struct super_block *sb, struct fs_context *fc) { + struct hypfs_sb_info *sbi = sb->s_fs_info; struct inode *root_inode; - struct dentry *root_dentry; - int rc = 0; - struct hypfs_sb_info *sbi; + struct dentry *root_dentry, *update_file; + int rc; - sbi = kzalloc(sizeof(struct hypfs_sb_info), GFP_KERNEL); - if (!sbi) - return -ENOMEM; - mutex_init(&sbi->lock); - sbi->uid = current_uid(); - sbi->gid = current_gid(); - sb->s_fs_info = sbi; sb->s_blocksize = PAGE_SIZE; sb->s_blocksize_bits = PAGE_SHIFT; sb->s_magic = HYPFS_MAGIC; sb->s_op = &hypfs_s_ops; - if (hypfs_parse_options(data, sb)) - return -EINVAL; + root_inode = hypfs_make_inode(sb, S_IFDIR | 0755); if (!root_inode) return -ENOMEM; @@ -300,18 +279,46 @@ static int hypfs_fill_super(struct super_block *sb, void *data, int silent) rc = hypfs_diag_create_files(root_dentry); if (rc) return rc; - sbi->update_file = hypfs_create_update_file(root_dentry); - if (IS_ERR(sbi->update_file)) - return PTR_ERR(sbi->update_file); + update_file = hypfs_create_update_file(root_dentry); + if (IS_ERR(update_file)) + return PTR_ERR(update_file); + sbi->update_file = update_file; hypfs_update_update(sb); pr_info("Hypervisor filesystem mounted\n"); return 0; } -static struct dentry *hypfs_mount(struct file_system_type *fst, int flags, - const char *devname, void *data) +static int hypfs_get_tree(struct fs_context *fc) +{ + return get_tree_single(fc, hypfs_fill_super); +} + +static void hypfs_free_fc(struct fs_context *fc) { - return mount_single(fst, flags, data, hypfs_fill_super); + kfree(fc->s_fs_info); +} + +static const struct fs_context_operations hypfs_context_ops = { + .free = hypfs_free_fc, + .parse_param = hypfs_parse_param, + .get_tree = hypfs_get_tree, +}; + +static int hypfs_init_fs_context(struct fs_context *fc) +{ + struct hypfs_sb_info *sbi; + + sbi = kzalloc(sizeof(struct hypfs_sb_info), GFP_KERNEL); + if (!sbi) + return -ENOMEM; + + mutex_init(&sbi->lock); + sbi->uid = current_uid(); + sbi->gid = current_gid(); + + fc->s_fs_info = sbi; + fc->ops = &hypfs_context_ops; + return 0; } static void hypfs_kill_super(struct super_block *sb) @@ -442,7 +449,8 @@ static const struct file_operations hypfs_file_ops = { static struct file_system_type hypfs_type = { .owner = THIS_MODULE, .name = "s390_hypfs", - .mount = hypfs_mount, + .init_fs_context = hypfs_init_fs_context, + .parameters = hypfs_fs_parameters, .kill_sb = hypfs_kill_super }; diff --git a/arch/s390/include/asm/Kbuild b/arch/s390/include/asm/Kbuild index 2531f673f099..1832ae6442ef 100644 --- a/arch/s390/include/asm/Kbuild +++ b/arch/s390/include/asm/Kbuild @@ -7,7 +7,6 @@ generated-y += unistd_nr.h generic-y += asm-offsets.h generic-y += cacheflush.h generic-y += device.h -generic-y += dma-contiguous.h generic-y += dma-mapping.h generic-y += div64.h generic-y += emergency-restart.h diff --git a/arch/s390/include/asm/alternative.h b/arch/s390/include/asm/alternative.h index c2cf7bcdef9b..1c8a38f762a3 100644 --- a/arch/s390/include/asm/alternative.h +++ b/arch/s390/include/asm/alternative.h @@ -139,10 +139,10 @@ void apply_alternatives(struct alt_instr *start, struct alt_instr *end); * without volatile and memory clobber. */ #define alternative(oldinstr, altinstr, facility) \ - asm volatile(ALTERNATIVE(oldinstr, altinstr, facility) : : : "memory") + asm_inline volatile(ALTERNATIVE(oldinstr, altinstr, facility) : : : "memory") #define alternative_2(oldinstr, altinstr1, facility1, altinstr2, facility2) \ - asm volatile(ALTERNATIVE_2(oldinstr, altinstr1, facility1, \ + asm_inline volatile(ALTERNATIVE_2(oldinstr, altinstr1, facility1, \ altinstr2, facility2) ::: "memory") #endif /* __ASSEMBLY__ */ diff --git a/arch/s390/include/asm/archrandom.h b/arch/s390/include/asm/archrandom.h index c67b82dfa558..de61ce562052 100644 --- a/arch/s390/include/asm/archrandom.h +++ b/arch/s390/include/asm/archrandom.h @@ -21,29 +21,17 @@ extern atomic64_t s390_arch_random_counter; bool s390_arch_random_generate(u8 *buf, unsigned int nbytes); -static inline bool arch_has_random(void) +static inline bool __must_check arch_get_random_long(unsigned long *v) { return false; } -static inline bool arch_has_random_seed(void) +static inline bool __must_check arch_get_random_int(unsigned int *v) { - if (static_branch_likely(&s390_arch_random_available)) - return true; return false; } -static inline bool arch_get_random_long(unsigned long *v) -{ - return false; -} - -static inline bool arch_get_random_int(unsigned int *v) -{ - return false; -} - -static inline bool arch_get_random_seed_long(unsigned long *v) +static inline bool __must_check arch_get_random_seed_long(unsigned long *v) { if (static_branch_likely(&s390_arch_random_available)) { return s390_arch_random_generate((u8 *)v, sizeof(*v)); @@ -51,7 +39,7 @@ static inline bool arch_get_random_seed_long(unsigned long *v) return false; } -static inline bool arch_get_random_seed_int(unsigned int *v) +static inline bool __must_check arch_get_random_seed_int(unsigned int *v) { if (static_branch_likely(&s390_arch_random_available)) { return s390_arch_random_generate((u8 *)v, sizeof(*v)); diff --git a/arch/s390/include/asm/atomic_ops.h b/arch/s390/include/asm/atomic_ops.h index d3f09526ee19..61467b9eecc7 100644 --- a/arch/s390/include/asm/atomic_ops.h +++ b/arch/s390/include/asm/atomic_ops.h @@ -41,7 +41,7 @@ __ATOMIC_OPS(__atomic64_xor, long, "laxg") #undef __ATOMIC_OP #define __ATOMIC_CONST_OP(op_name, op_type, op_string, op_barrier) \ -static inline void op_name(op_type val, op_type *ptr) \ +static __always_inline void op_name(op_type val, op_type *ptr) \ { \ asm volatile( \ op_string " %[ptr],%[val]\n" \ diff --git a/arch/s390/include/asm/bitops.h b/arch/s390/include/asm/bitops.h index b8833ac983fa..431e208a5ea4 100644 --- a/arch/s390/include/asm/bitops.h +++ b/arch/s390/include/asm/bitops.h @@ -56,7 +56,7 @@ __bitops_byte(unsigned long nr, volatile unsigned long *ptr) return ((unsigned char *)ptr) + ((nr ^ (BITS_PER_LONG - 8)) >> 3); } -static inline void arch_set_bit(unsigned long nr, volatile unsigned long *ptr) +static __always_inline void arch_set_bit(unsigned long nr, volatile unsigned long *ptr) { unsigned long *addr = __bitops_word(nr, ptr); unsigned long mask; @@ -77,7 +77,7 @@ static inline void arch_set_bit(unsigned long nr, volatile unsigned long *ptr) __atomic64_or(mask, (long *)addr); } -static inline void arch_clear_bit(unsigned long nr, volatile unsigned long *ptr) +static __always_inline void arch_clear_bit(unsigned long nr, volatile unsigned long *ptr) { unsigned long *addr = __bitops_word(nr, ptr); unsigned long mask; @@ -98,8 +98,8 @@ static inline void arch_clear_bit(unsigned long nr, volatile unsigned long *ptr) __atomic64_and(mask, (long *)addr); } -static inline void arch_change_bit(unsigned long nr, - volatile unsigned long *ptr) +static __always_inline void arch_change_bit(unsigned long nr, + volatile unsigned long *ptr) { unsigned long *addr = __bitops_word(nr, ptr); unsigned long mask; @@ -241,7 +241,9 @@ static inline void arch___clear_bit_unlock(unsigned long nr, arch___clear_bit(nr, ptr); } -#include <asm-generic/bitops-instrumented.h> +#include <asm-generic/bitops/instrumented-atomic.h> +#include <asm-generic/bitops/instrumented-non-atomic.h> +#include <asm-generic/bitops/instrumented-lock.h> /* * Functions which use MSB0 bit numbering. diff --git a/arch/s390/include/asm/bug.h b/arch/s390/include/asm/bug.h index 713fc9735ffb..7725f8006fdf 100644 --- a/arch/s390/include/asm/bug.h +++ b/arch/s390/include/asm/bug.h @@ -9,16 +9,15 @@ #ifdef CONFIG_DEBUG_BUGVERBOSE #define __EMIT_BUG(x) do { \ - asm volatile( \ - "0: j 0b+2\n" \ - "1:\n" \ + asm_inline volatile( \ + "0: mc 0,0\n" \ ".section .rodata.str,\"aMS\",@progbits,1\n" \ - "2: .asciz \""__FILE__"\"\n" \ + "1: .asciz \""__FILE__"\"\n" \ ".previous\n" \ ".section __bug_table,\"awM\",@progbits,%2\n" \ - "3: .long 1b-3b,2b-3b\n" \ + "2: .long 0b-2b,1b-2b\n" \ " .short %0,%1\n" \ - " .org 3b+%2\n" \ + " .org 2b+%2\n" \ ".previous\n" \ : : "i" (__LINE__), \ "i" (x), \ @@ -28,13 +27,12 @@ #else /* CONFIG_DEBUG_BUGVERBOSE */ #define __EMIT_BUG(x) do { \ - asm volatile( \ - "0: j 0b+2\n" \ - "1:\n" \ + asm_inline volatile( \ + "0: mc 0,0\n" \ ".section __bug_table,\"awM\",@progbits,%1\n" \ - "2: .long 1b-2b\n" \ + "1: .long 0b-1b\n" \ " .short %0\n" \ - " .org 2b+%1\n" \ + " .org 1b+%1\n" \ ".previous\n" \ : : "i" (x), \ "i" (sizeof(struct bug_entry))); \ diff --git a/arch/s390/include/asm/compat.h b/arch/s390/include/asm/compat.h index 63b46e30b2c3..9547cd5d6cdc 100644 --- a/arch/s390/include/asm/compat.h +++ b/arch/s390/include/asm/compat.h @@ -177,11 +177,7 @@ static inline void __user *compat_ptr(compat_uptr_t uptr) { return (void __user *)(unsigned long)(uptr & 0x7fffffffUL); } - -static inline compat_uptr_t ptr_to_compat(void __user *uptr) -{ - return (u32)(unsigned long)uptr; -} +#define compat_ptr(uptr) compat_ptr(uptr) #ifdef CONFIG_COMPAT diff --git a/arch/s390/include/asm/cpacf.h b/arch/s390/include/asm/cpacf.h index e3d53eb6bcf5..c0f3bfeddcbe 100644 --- a/arch/s390/include/asm/cpacf.h +++ b/arch/s390/include/asm/cpacf.h @@ -93,6 +93,10 @@ #define CPACF_KIMD_SHA_1 0x01 #define CPACF_KIMD_SHA_256 0x02 #define CPACF_KIMD_SHA_512 0x03 +#define CPACF_KIMD_SHA3_224 0x20 +#define CPACF_KIMD_SHA3_256 0x21 +#define CPACF_KIMD_SHA3_384 0x22 +#define CPACF_KIMD_SHA3_512 0x23 #define CPACF_KIMD_GHASH 0x41 /* @@ -103,6 +107,10 @@ #define CPACF_KLMD_SHA_1 0x01 #define CPACF_KLMD_SHA_256 0x02 #define CPACF_KLMD_SHA_512 0x03 +#define CPACF_KLMD_SHA3_224 0x20 +#define CPACF_KLMD_SHA3_256 0x21 +#define CPACF_KLMD_SHA3_384 0x22 +#define CPACF_KLMD_SHA3_512 0x23 /* * function codes for the KMAC (COMPUTE MESSAGE AUTHENTICATION CODE) @@ -163,7 +171,7 @@ typedef struct { unsigned char bytes[16]; } cpacf_mask_t; * * Returns 1 if @func is available for @opcode, 0 otherwise */ -static inline void __cpacf_query(unsigned int opcode, cpacf_mask_t *mask) +static __always_inline void __cpacf_query(unsigned int opcode, cpacf_mask_t *mask) { register unsigned long r0 asm("0") = 0; /* query function */ register unsigned long r1 asm("1") = (unsigned long) mask; diff --git a/arch/s390/include/asm/cpu_mf.h b/arch/s390/include/asm/cpu_mf.h index ae3e3221d4b5..0d90cbeb89b4 100644 --- a/arch/s390/include/asm/cpu_mf.h +++ b/arch/s390/include/asm/cpu_mf.h @@ -28,6 +28,8 @@ asm(".include \"asm/cpu_mf-insn.h\"\n"); CPU_MF_INT_SF_PRA|CPU_MF_INT_SF_SACA| \ CPU_MF_INT_SF_LSDA) +#define CPU_MF_SF_RIBM_NOTAV 0x1 /* Sampling unavailable */ + /* CPU measurement facility support */ static inline int cpum_cf_avail(void) { @@ -69,8 +71,9 @@ struct hws_qsi_info_block { /* Bit(s) */ unsigned long max_sampl_rate; /* 16-23: maximum sampling interval*/ unsigned long tear; /* 24-31: TEAR contents */ unsigned long dear; /* 32-39: DEAR contents */ - unsigned int rsvrd0; /* 40-43: reserved */ - unsigned int cpu_speed; /* 44-47: CPU speed */ + unsigned int rsvrd0:24; /* 40-42: reserved */ + unsigned int ribm:8; /* 43: Reserved by IBM */ + unsigned int cpu_speed; /* 44-47: CPU speed */ unsigned long long rsvrd1; /* 48-55: reserved */ unsigned long long rsvrd2; /* 56-63: reserved */ } __packed; @@ -89,10 +92,10 @@ struct hws_lsctl_request_block { unsigned long tear; /* 16-23: TEAR contents */ unsigned long dear; /* 24-31: DEAR contents */ /* 32-63: */ - unsigned long rsvrd1; /* reserved */ - unsigned long rsvrd2; /* reserved */ - unsigned long rsvrd3; /* reserved */ - unsigned long rsvrd4; /* reserved */ + unsigned long rsvrd1; /* reserved */ + unsigned long rsvrd2; /* reserved */ + unsigned long rsvrd3; /* reserved */ + unsigned long rsvrd4; /* reserved */ } __packed; struct hws_basic_entry { @@ -220,7 +223,8 @@ enum stcctm_ctr_set { MT_DIAG = 5, MT_DIAG_CLEARING = 9, /* clears loss-of-MT-ctr-data alert */ }; -static inline int stcctm(enum stcctm_ctr_set set, u64 range, u64 *dest) + +static __always_inline int stcctm(enum stcctm_ctr_set set, u64 range, u64 *dest) { int cc; @@ -309,7 +313,7 @@ static inline unsigned long *trailer_entry_ptr(unsigned long v) return (unsigned long *) ret; } -/* Return if the entry in the sample data block table (sdbt) +/* Return true if the entry in the sample data block table (sdbt) * is a link to the next sdbt */ static inline int is_link_entry(unsigned long *s) { diff --git a/arch/s390/include/asm/ctl_reg.h b/arch/s390/include/asm/ctl_reg.h index 60f907516335..ed5efbb531c4 100644 --- a/arch/s390/include/asm/ctl_reg.h +++ b/arch/s390/include/asm/ctl_reg.h @@ -11,6 +11,7 @@ #include <linux/bits.h> #define CR0_CLOCK_COMPARATOR_SIGN BIT(63 - 10) +#define CR0_LOW_ADDRESS_PROTECTION BIT(63 - 35) #define CR0_EMERGENCY_SIGNAL_SUBMASK BIT(63 - 49) #define CR0_EXTERNAL_CALL_SUBMASK BIT(63 - 50) #define CR0_CLOCK_COMPARATOR_SUBMASK BIT(63 - 52) diff --git a/arch/s390/include/asm/gmap.h b/arch/s390/include/asm/gmap.h index fcbd638fb9f4..37f96b6f0e61 100644 --- a/arch/s390/include/asm/gmap.h +++ b/arch/s390/include/asm/gmap.h @@ -9,6 +9,8 @@ #ifndef _ASM_S390_GMAP_H #define _ASM_S390_GMAP_H +#include <linux/refcount.h> + /* Generic bits for GMAP notification on DAT table entry changes. */ #define GMAP_NOTIFY_SHADOW 0x2 #define GMAP_NOTIFY_MPROT 0x1 @@ -46,7 +48,7 @@ struct gmap { struct radix_tree_root guest_to_host; struct radix_tree_root host_to_guest; spinlock_t guest_table_lock; - atomic_t ref_count; + refcount_t ref_count; unsigned long *table; unsigned long asce; unsigned long asce_end; diff --git a/arch/s390/include/asm/hugetlb.h b/arch/s390/include/asm/hugetlb.h index bb59dd964590..de8f0bf5f238 100644 --- a/arch/s390/include/asm/hugetlb.h +++ b/arch/s390/include/asm/hugetlb.h @@ -12,8 +12,6 @@ #include <asm/page.h> #include <asm/pgtable.h> - -#define is_hugepage_only_range(mm, addr, len) 0 #define hugetlb_free_pgd_range free_pgd_range #define hugepages_supported() (MACHINE_HAS_EDAT1) @@ -23,6 +21,13 @@ pte_t huge_ptep_get(pte_t *ptep); pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep); +static inline bool is_hugepage_only_range(struct mm_struct *mm, + unsigned long addr, + unsigned long len) +{ + return false; +} + /* * If the arch doesn't supply something else, assume that hugepage * size aligned regions are ok without further preparation. diff --git a/arch/s390/include/asm/io.h b/arch/s390/include/asm/io.h index ca421614722f..5a16f500515a 100644 --- a/arch/s390/include/asm/io.h +++ b/arch/s390/include/asm/io.h @@ -26,10 +26,6 @@ void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr); #define IO_SPACE_LIMIT 0 -#define ioremap_nocache(addr, size) ioremap(addr, size) -#define ioremap_wc ioremap_nocache -#define ioremap_wt ioremap_nocache - void __iomem *ioremap(unsigned long offset, unsigned long size); void iounmap(volatile void __iomem *addr); diff --git a/arch/s390/include/asm/jump_label.h b/arch/s390/include/asm/jump_label.h index e548ec1ec12c..dcb1bba4f406 100644 --- a/arch/s390/include/asm/jump_label.h +++ b/arch/s390/include/asm/jump_label.h @@ -10,7 +10,9 @@ #define JUMP_LABEL_NOP_SIZE 6 #define JUMP_LABEL_NOP_OFFSET 2 -#if __GNUC__ < 9 +#ifdef CONFIG_CC_IS_CLANG +#define JUMP_LABEL_STATIC_KEY_CONSTRAINT "i" +#elif __GNUC__ < 9 #define JUMP_LABEL_STATIC_KEY_CONSTRAINT "X" #else #define JUMP_LABEL_STATIC_KEY_CONSTRAINT "jdd" @@ -20,7 +22,7 @@ * We use a brcl 0,2 instruction for jump labels at compile time so it * can be easily distinguished from a hotpatch generated instruction. */ -static inline bool arch_static_branch(struct static_key *key, bool branch) +static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { asm_volatile_goto("0: brcl 0,"__stringify(JUMP_LABEL_NOP_OFFSET)"\n" ".pushsection __jump_table,\"aw\"\n" @@ -34,7 +36,7 @@ label: return true; } -static inline bool arch_static_branch_jump(struct static_key *key, bool branch) +static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch) { asm_volatile_goto("0: brcl 15,%l[label]\n" ".pushsection __jump_table,\"aw\"\n" diff --git a/arch/s390/include/asm/kprobes.h b/arch/s390/include/asm/kprobes.h index b106aa29bf55..09cdb632a490 100644 --- a/arch/s390/include/asm/kprobes.h +++ b/arch/s390/include/asm/kprobes.h @@ -54,7 +54,6 @@ typedef u16 kprobe_opcode_t; struct arch_specific_insn { /* copy of original instruction */ kprobe_opcode_t *insn; - unsigned int is_ftrace_insn : 1; }; struct prev_kprobe { diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index abe60268335d..1726224e7772 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -122,6 +122,11 @@ struct mcck_volatile_info { __u32 reserved; }; +#define CR0_INITIAL_MASK (CR0_UNUSED_56 | CR0_INTERRUPT_KEY_SUBMASK | \ + CR0_MEASUREMENT_ALERT_SUBMASK) +#define CR14_INITIAL_MASK (CR14_UNUSED_32 | CR14_UNUSED_33 | \ + CR14_EXTERNAL_DAMAGE_SUBMASK) + #define CPUSTAT_STOPPED 0x80000000 #define CPUSTAT_WAIT 0x10000000 #define CPUSTAT_ECALL_PEND 0x08000000 @@ -392,6 +397,7 @@ struct kvm_vcpu_stat { u64 diagnose_10; u64 diagnose_44; u64 diagnose_9c; + u64 diagnose_9c_ignored; u64 diagnose_258; u64 diagnose_308; u64 diagnose_500; @@ -913,7 +919,6 @@ extern int kvm_s390_gisc_unregister(struct kvm *kvm, u32 gisc); static inline void kvm_arch_hardware_disable(void) {} static inline void kvm_arch_sync_events(struct kvm *kvm) {} -static inline void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) {} static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {} static inline void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free, struct kvm_memory_slot *dont) {} diff --git a/arch/s390/include/asm/mem_detect.h b/arch/s390/include/asm/mem_detect.h index 6114b92ab667..a7c922a69050 100644 --- a/arch/s390/include/asm/mem_detect.h +++ b/arch/s390/include/asm/mem_detect.h @@ -79,4 +79,16 @@ static inline void get_mem_detect_reserved(unsigned long *start, *size = 0; } +static inline unsigned long get_mem_detect_end(void) +{ + unsigned long start; + unsigned long end; + + if (mem_detect.count) { + __get_mem_detect_block(mem_detect.count - 1, &start, &end); + return end; + } + return 0; +} + #endif diff --git a/arch/s390/include/asm/mem_encrypt.h b/arch/s390/include/asm/mem_encrypt.h index 3eb018508190..2542cbf7e2d1 100644 --- a/arch/s390/include/asm/mem_encrypt.h +++ b/arch/s390/include/asm/mem_encrypt.h @@ -4,10 +4,7 @@ #ifndef __ASSEMBLY__ -#define sme_me_mask 0ULL - -static inline bool sme_active(void) { return false; } -extern bool sev_active(void); +static inline bool mem_encrypt_active(void) { return false; } int set_memory_encrypted(unsigned long addr, int numpages); int set_memory_decrypted(unsigned long addr, int numpages); diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h index 823578c6b9e2..85e944f04c70 100644 --- a/arch/s390/include/asm/page.h +++ b/arch/s390/include/asm/page.h @@ -33,6 +33,8 @@ #define ARCH_HAS_PREPARE_HUGEPAGE #define ARCH_HAS_HUGEPAGE_CLEAR_FLUSH +#define HAVE_ARCH_HUGETLB_UNMAPPED_AREA + #include <asm/setup.h> #ifndef __ASSEMBLY__ @@ -177,8 +179,6 @@ static inline int devmem_is_allowed(unsigned long pfn) #define VM_DATA_DEFAULT_FLAGS (VM_READ | VM_WRITE | \ VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) -#define ARCH_ZONE_DMA_BITS 31 - #include <asm-generic/memory_model.h> #include <asm-generic/getorder.h> diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h index a2399eff84ca..b05187ce5dbd 100644 --- a/arch/s390/include/asm/pci.h +++ b/arch/s390/include/asm/pci.h @@ -2,9 +2,6 @@ #ifndef __ASM_S390_PCI_H #define __ASM_S390_PCI_H -/* must be set before including pci_clp.h */ -#define PCI_BAR_COUNT 6 - #include <linux/pci.h> #include <linux/mutex.h> #include <linux/iommu.h> @@ -138,7 +135,7 @@ struct zpci_dev { char res_name[16]; bool mio_capable; - struct zpci_bar_struct bars[PCI_BAR_COUNT]; + struct zpci_bar_struct bars[PCI_STD_NUM_BARS]; u64 start_dma; /* Start of available DMA addresses */ u64 end_dma; /* End of available DMA addresses */ @@ -183,7 +180,7 @@ void zpci_remove_reserved_devices(void); /* CLP */ int clp_scan_pci_devices(void); int clp_rescan_pci_devices(void); -int clp_rescan_pci_devices_simple(void); +int clp_rescan_pci_devices_simple(u32 *fid); int clp_add_pci_device(u32, u32, int); int clp_enable_fh(struct zpci_dev *, u8); int clp_disable_fh(struct zpci_dev *); diff --git a/arch/s390/include/asm/pci_clp.h b/arch/s390/include/asm/pci_clp.h index 50359172cc48..bd2cb4ea7d93 100644 --- a/arch/s390/include/asm/pci_clp.h +++ b/arch/s390/include/asm/pci_clp.h @@ -77,7 +77,7 @@ struct mio_info { struct { u64 wb; u64 wt; - } addr[PCI_BAR_COUNT]; + } addr[PCI_STD_NUM_BARS]; u32 reserved[6]; } __packed; @@ -98,9 +98,9 @@ struct clp_rsp_query_pci { u16 util_str_avail : 1; /* utility string available? */ u16 pfgid : 8; /* pci function group id */ u32 fid; /* pci function id */ - u8 bar_size[PCI_BAR_COUNT]; + u8 bar_size[PCI_STD_NUM_BARS]; u16 pchid; - __le32 bar[PCI_BAR_COUNT]; + __le32 bar[PCI_STD_NUM_BARS]; u8 pfip[CLP_PFIP_NR_SEGMENTS]; /* pci function internal path */ u32 : 16; u8 fmb_len; diff --git a/arch/s390/include/asm/perf_event.h b/arch/s390/include/asm/perf_event.h index 560d8f766ddf..b9da71632827 100644 --- a/arch/s390/include/asm/perf_event.h +++ b/arch/s390/include/asm/perf_event.h @@ -12,6 +12,7 @@ #include <linux/perf_event.h> #include <linux/device.h> +#include <asm/stacktrace.h> /* Per-CPU flags for PMU states */ #define PMU_F_RESERVED 0x1000 @@ -60,6 +61,7 @@ struct perf_sf_sde_regs { #define PERF_CPUM_SF_MODE_MASK (PERF_CPUM_SF_BASIC_MODE| \ PERF_CPUM_SF_DIAG_MODE) #define PERF_CPUM_SF_FULL_BLOCKS 0x0004 /* Process full SDBs only */ +#define PERF_CPUM_SF_FREQ_MODE 0x0008 /* Sampling with frequency */ #define REG_NONE 0 #define REG_OVERFLOW 1 @@ -70,5 +72,12 @@ struct perf_sf_sde_regs { #define SAMPL_FLAGS(hwc) ((hwc)->config_base) #define SAMPL_DIAG_MODE(hwc) (SAMPL_FLAGS(hwc) & PERF_CPUM_SF_DIAG_MODE) #define SDB_FULL_BLOCKS(hwc) (SAMPL_FLAGS(hwc) & PERF_CPUM_SF_FULL_BLOCKS) +#define SAMPLE_FREQ_MODE(hwc) (SAMPL_FLAGS(hwc) & PERF_CPUM_SF_FREQ_MODE) + +#define perf_arch_fetch_caller_regs(regs, __ip) do { \ + (regs)->psw.addr = (__ip); \ + (regs)->gprs[15] = (unsigned long)__builtin_frame_address(0) - \ + offsetof(struct stack_frame, back_chain); \ +} while (0) #endif /* _ASM_S390_PERF_EVENT_H */ diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h index bccb8f4a63e2..77606c4acd58 100644 --- a/arch/s390/include/asm/pgalloc.h +++ b/arch/s390/include/asm/pgalloc.h @@ -56,7 +56,12 @@ static inline p4d_t *p4d_alloc_one(struct mm_struct *mm, unsigned long address) crst_table_init(table, _REGION2_ENTRY_EMPTY); return (p4d_t *) table; } -#define p4d_free(mm, p4d) crst_table_free(mm, (unsigned long *) p4d) + +static inline void p4d_free(struct mm_struct *mm, p4d_t *p4d) +{ + if (!mm_p4d_folded(mm)) + crst_table_free(mm, (unsigned long *) p4d); +} static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address) { @@ -65,7 +70,12 @@ static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address) crst_table_init(table, _REGION3_ENTRY_EMPTY); return (pud_t *) table; } -#define pud_free(mm, pud) crst_table_free(mm, (unsigned long *) pud) + +static inline void pud_free(struct mm_struct *mm, pud_t *pud) +{ + if (!mm_pud_folded(mm)) + crst_table_free(mm, (unsigned long *) pud); +} static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long vmaddr) { @@ -83,6 +93,8 @@ static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long vmaddr) static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) { + if (mm_pmd_folded(mm)) + return; pgtable_pmd_page_dtor(virt_to_page(pmd)); crst_table_free(mm, (unsigned long *) pmd); } diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 9b274fcaacb6..137a3920ca36 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -86,6 +86,7 @@ extern unsigned long zero_page_mask; */ extern unsigned long VMALLOC_START; extern unsigned long VMALLOC_END; +#define VMALLOC_DEFAULT_SIZE ((128UL << 30) - MODULES_LEN) extern struct page *vmemmap; #define VMEM_MAX_PHYS ((unsigned long) vmemmap) @@ -265,11 +266,9 @@ static inline int is_module_addr(void *addr) #endif #define _REGION_ENTRY_BITS 0xfffffffffffff22fUL -#define _REGION_ENTRY_BITS_LARGE 0xffffffff8000fe2fUL /* Bits in the segment table entry */ #define _SEGMENT_ENTRY_BITS 0xfffffffffffffe33UL -#define _SEGMENT_ENTRY_BITS_LARGE 0xfffffffffff0ff33UL #define _SEGMENT_ENTRY_HARDWARE_BITS 0xfffffffffffffe30UL #define _SEGMENT_ENTRY_HARDWARE_BITS_LARGE 0xfffffffffff00730UL #define _SEGMENT_ENTRY_ORIGIN_LARGE ~0xfffffUL /* large page address */ @@ -674,6 +673,7 @@ static inline int pud_none(pud_t pud) return pud_val(pud) == _REGION3_ENTRY_EMPTY; } +#define pud_leaf pud_large static inline int pud_large(pud_t pud) { if ((pud_val(pud) & _REGION_ENTRY_TYPE_MASK) != _REGION_ENTRY_TYPE_R3) @@ -691,6 +691,7 @@ static inline unsigned long pud_pfn(pud_t pud) return (pud_val(pud) & origin_mask) >> PAGE_SHIFT; } +#define pmd_leaf pmd_large static inline int pmd_large(pmd_t pmd) { return (pmd_val(pmd) & _SEGMENT_ENTRY_LARGE) != 0; @@ -698,10 +699,8 @@ static inline int pmd_large(pmd_t pmd) static inline int pmd_bad(pmd_t pmd) { - if ((pmd_val(pmd) & _SEGMENT_ENTRY_TYPE_MASK) > 0) + if ((pmd_val(pmd) & _SEGMENT_ENTRY_TYPE_MASK) > 0 || pmd_large(pmd)) return 1; - if (pmd_large(pmd)) - return (pmd_val(pmd) & ~_SEGMENT_ENTRY_BITS_LARGE) != 0; return (pmd_val(pmd) & ~_SEGMENT_ENTRY_BITS) != 0; } @@ -709,12 +708,10 @@ static inline int pud_bad(pud_t pud) { unsigned long type = pud_val(pud) & _REGION_ENTRY_TYPE_MASK; - if (type > _REGION_ENTRY_TYPE_R3) + if (type > _REGION_ENTRY_TYPE_R3 || pud_large(pud)) return 1; if (type < _REGION_ENTRY_TYPE_R3) return 0; - if (pud_large(pud)) - return (pud_val(pud) & ~_REGION_ENTRY_BITS_LARGE) != 0; return (pud_val(pud) & ~_REGION_ENTRY_BITS) != 0; } @@ -757,18 +754,12 @@ static inline int pmd_write(pmd_t pmd) static inline int pmd_dirty(pmd_t pmd) { - int dirty = 1; - if (pmd_large(pmd)) - dirty = (pmd_val(pmd) & _SEGMENT_ENTRY_DIRTY) != 0; - return dirty; + return (pmd_val(pmd) & _SEGMENT_ENTRY_DIRTY) != 0; } static inline int pmd_young(pmd_t pmd) { - int young = 1; - if (pmd_large(pmd)) - young = (pmd_val(pmd) & _SEGMENT_ENTRY_YOUNG) != 0; - return young; + return (pmd_val(pmd) & _SEGMENT_ENTRY_YOUNG) != 0; } static inline int pte_present(pte_t pte) @@ -996,9 +987,9 @@ static inline pte_t pte_mkhuge(pte_t pte) #define IPTE_NODAT 0x400 #define IPTE_GUEST_ASCE 0x800 -static inline void __ptep_ipte(unsigned long address, pte_t *ptep, - unsigned long opt, unsigned long asce, - int local) +static __always_inline void __ptep_ipte(unsigned long address, pte_t *ptep, + unsigned long opt, unsigned long asce, + int local) { unsigned long pto = (unsigned long) ptep; @@ -1019,8 +1010,8 @@ static inline void __ptep_ipte(unsigned long address, pte_t *ptep, : [r1] "a" (pto), [m4] "i" (local) : "memory"); } -static inline void __ptep_ipte_range(unsigned long address, int nr, - pte_t *ptep, int local) +static __always_inline void __ptep_ipte_range(unsigned long address, int nr, + pte_t *ptep, int local) { unsigned long pto = (unsigned long) ptep; @@ -1172,8 +1163,6 @@ void gmap_pmdp_idte_global(struct mm_struct *mm, unsigned long vmaddr); static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t entry) { - if (!MACHINE_HAS_NX) - pte_val(entry) &= ~_PAGE_NOEXEC; if (pte_present(entry)) pte_val(entry) &= ~_PAGE_UNUSED; if (mm_has_pgste(mm)) @@ -1190,6 +1179,8 @@ static inline pte_t mk_pte_phys(unsigned long physpage, pgprot_t pgprot) { pte_t __pte; pte_val(__pte) = physpage + pgprot_val(pgprot); + if (!MACHINE_HAS_NX) + pte_val(__pte) &= ~_PAGE_NOEXEC; return pte_mkyoung(__pte); } @@ -1268,7 +1259,8 @@ static inline pte_t *pte_offset(pmd_t *pmd, unsigned long address) #define pte_offset_kernel(pmd, address) pte_offset(pmd, address) #define pte_offset_map(pmd, address) pte_offset_kernel(pmd, address) -#define pte_unmap(pte) do { } while (0) + +static inline void pte_unmap(pte_t *pte) { } static inline bool gup_fast_permitted(unsigned long start, unsigned long end) { @@ -1295,29 +1287,23 @@ static inline pmd_t pmd_wrprotect(pmd_t pmd) static inline pmd_t pmd_mkwrite(pmd_t pmd) { pmd_val(pmd) |= _SEGMENT_ENTRY_WRITE; - if (pmd_large(pmd) && !(pmd_val(pmd) & _SEGMENT_ENTRY_DIRTY)) - return pmd; - pmd_val(pmd) &= ~_SEGMENT_ENTRY_PROTECT; + if (pmd_val(pmd) & _SEGMENT_ENTRY_DIRTY) + pmd_val(pmd) &= ~_SEGMENT_ENTRY_PROTECT; return pmd; } static inline pmd_t pmd_mkclean(pmd_t pmd) { - if (pmd_large(pmd)) { - pmd_val(pmd) &= ~_SEGMENT_ENTRY_DIRTY; - pmd_val(pmd) |= _SEGMENT_ENTRY_PROTECT; - } + pmd_val(pmd) &= ~_SEGMENT_ENTRY_DIRTY; + pmd_val(pmd) |= _SEGMENT_ENTRY_PROTECT; return pmd; } static inline pmd_t pmd_mkdirty(pmd_t pmd) { - if (pmd_large(pmd)) { - pmd_val(pmd) |= _SEGMENT_ENTRY_DIRTY | - _SEGMENT_ENTRY_SOFT_DIRTY; - if (pmd_val(pmd) & _SEGMENT_ENTRY_WRITE) - pmd_val(pmd) &= ~_SEGMENT_ENTRY_PROTECT; - } + pmd_val(pmd) |= _SEGMENT_ENTRY_DIRTY | _SEGMENT_ENTRY_SOFT_DIRTY; + if (pmd_val(pmd) & _SEGMENT_ENTRY_WRITE) + pmd_val(pmd) &= ~_SEGMENT_ENTRY_PROTECT; return pmd; } @@ -1331,29 +1317,23 @@ static inline pud_t pud_wrprotect(pud_t pud) static inline pud_t pud_mkwrite(pud_t pud) { pud_val(pud) |= _REGION3_ENTRY_WRITE; - if (pud_large(pud) && !(pud_val(pud) & _REGION3_ENTRY_DIRTY)) - return pud; - pud_val(pud) &= ~_REGION_ENTRY_PROTECT; + if (pud_val(pud) & _REGION3_ENTRY_DIRTY) + pud_val(pud) &= ~_REGION_ENTRY_PROTECT; return pud; } static inline pud_t pud_mkclean(pud_t pud) { - if (pud_large(pud)) { - pud_val(pud) &= ~_REGION3_ENTRY_DIRTY; - pud_val(pud) |= _REGION_ENTRY_PROTECT; - } + pud_val(pud) &= ~_REGION3_ENTRY_DIRTY; + pud_val(pud) |= _REGION_ENTRY_PROTECT; return pud; } static inline pud_t pud_mkdirty(pud_t pud) { - if (pud_large(pud)) { - pud_val(pud) |= _REGION3_ENTRY_DIRTY | - _REGION3_ENTRY_SOFT_DIRTY; - if (pud_val(pud) & _REGION3_ENTRY_WRITE) - pud_val(pud) &= ~_REGION_ENTRY_PROTECT; - } + pud_val(pud) |= _REGION3_ENTRY_DIRTY | _REGION3_ENTRY_SOFT_DIRTY; + if (pud_val(pud) & _REGION3_ENTRY_WRITE) + pud_val(pud) &= ~_REGION_ENTRY_PROTECT; return pud; } @@ -1377,38 +1357,29 @@ static inline unsigned long massage_pgprot_pmd(pgprot_t pgprot) static inline pmd_t pmd_mkyoung(pmd_t pmd) { - if (pmd_large(pmd)) { - pmd_val(pmd) |= _SEGMENT_ENTRY_YOUNG; - if (pmd_val(pmd) & _SEGMENT_ENTRY_READ) - pmd_val(pmd) &= ~_SEGMENT_ENTRY_INVALID; - } + pmd_val(pmd) |= _SEGMENT_ENTRY_YOUNG; + if (pmd_val(pmd) & _SEGMENT_ENTRY_READ) + pmd_val(pmd) &= ~_SEGMENT_ENTRY_INVALID; return pmd; } static inline pmd_t pmd_mkold(pmd_t pmd) { - if (pmd_large(pmd)) { - pmd_val(pmd) &= ~_SEGMENT_ENTRY_YOUNG; - pmd_val(pmd) |= _SEGMENT_ENTRY_INVALID; - } + pmd_val(pmd) &= ~_SEGMENT_ENTRY_YOUNG; + pmd_val(pmd) |= _SEGMENT_ENTRY_INVALID; return pmd; } static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) { - if (pmd_large(pmd)) { - pmd_val(pmd) &= _SEGMENT_ENTRY_ORIGIN_LARGE | - _SEGMENT_ENTRY_DIRTY | _SEGMENT_ENTRY_YOUNG | - _SEGMENT_ENTRY_LARGE | _SEGMENT_ENTRY_SOFT_DIRTY; - pmd_val(pmd) |= massage_pgprot_pmd(newprot); - if (!(pmd_val(pmd) & _SEGMENT_ENTRY_DIRTY)) - pmd_val(pmd) |= _SEGMENT_ENTRY_PROTECT; - if (!(pmd_val(pmd) & _SEGMENT_ENTRY_YOUNG)) - pmd_val(pmd) |= _SEGMENT_ENTRY_INVALID; - return pmd; - } - pmd_val(pmd) &= _SEGMENT_ENTRY_ORIGIN; + pmd_val(pmd) &= _SEGMENT_ENTRY_ORIGIN_LARGE | + _SEGMENT_ENTRY_DIRTY | _SEGMENT_ENTRY_YOUNG | + _SEGMENT_ENTRY_LARGE | _SEGMENT_ENTRY_SOFT_DIRTY; pmd_val(pmd) |= massage_pgprot_pmd(newprot); + if (!(pmd_val(pmd) & _SEGMENT_ENTRY_DIRTY)) + pmd_val(pmd) |= _SEGMENT_ENTRY_PROTECT; + if (!(pmd_val(pmd) & _SEGMENT_ENTRY_YOUNG)) + pmd_val(pmd) |= _SEGMENT_ENTRY_INVALID; return pmd; } @@ -1434,9 +1405,9 @@ static inline void __pmdp_csp(pmd_t *pmdp) #define IDTE_NODAT 0x1000 #define IDTE_GUEST_ASCE 0x2000 -static inline void __pmdp_idte(unsigned long addr, pmd_t *pmdp, - unsigned long opt, unsigned long asce, - int local) +static __always_inline void __pmdp_idte(unsigned long addr, pmd_t *pmdp, + unsigned long opt, unsigned long asce, + int local) { unsigned long sto; @@ -1460,9 +1431,9 @@ static inline void __pmdp_idte(unsigned long addr, pmd_t *pmdp, } } -static inline void __pudp_idte(unsigned long addr, pud_t *pudp, - unsigned long opt, unsigned long asce, - int local) +static __always_inline void __pudp_idte(unsigned long addr, pud_t *pudp, + unsigned long opt, unsigned long asce, + int local) { unsigned long r3o; @@ -1681,12 +1652,6 @@ extern void s390_reset_cmma(struct mm_struct *mm); #define HAVE_ARCH_UNMAPPED_AREA #define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN -/* - * No page table caches to initialise - */ -static inline void pgtable_cache_init(void) { } -static inline void check_pgt_cache(void) { } - #include <asm-generic/pgtable.h> #endif /* _S390_PAGE_H */ diff --git a/arch/s390/include/asm/pkey.h b/arch/s390/include/asm/pkey.h index 9b6e79077866..dd3d20c332ac 100644 --- a/arch/s390/include/asm/pkey.h +++ b/arch/s390/include/asm/pkey.h @@ -2,7 +2,7 @@ /* * Kernelspace interface to the pkey device driver * - * Copyright IBM Corp. 2016 + * Copyright IBM Corp. 2016,2019 * * Author: Harald Freudenberger <freude@de.ibm.com> * @@ -16,123 +16,13 @@ #include <uapi/asm/pkey.h> /* - * Generate (AES) random secure key. - * @param cardnr may be -1 (use default card) - * @param domain may be -1 (use default domain) - * @param keytype one of the PKEY_KEYTYPE values - * @param seckey pointer to buffer receiving the secure key - * @return 0 on success, negative errno value on failure - */ -int pkey_genseckey(__u16 cardnr, __u16 domain, - __u32 keytype, struct pkey_seckey *seckey); - -/* - * Generate (AES) secure key with given key value. - * @param cardnr may be -1 (use default card) - * @param domain may be -1 (use default domain) - * @param keytype one of the PKEY_KEYTYPE values - * @param clrkey pointer to buffer with clear key data - * @param seckey pointer to buffer receiving the secure key - * @return 0 on success, negative errno value on failure - */ -int pkey_clr2seckey(__u16 cardnr, __u16 domain, __u32 keytype, - const struct pkey_clrkey *clrkey, - struct pkey_seckey *seckey); - -/* - * Derive (AES) proteced key from the (AES) secure key blob. - * @param cardnr may be -1 (use default card) - * @param domain may be -1 (use default domain) - * @param seckey pointer to buffer with the input secure key - * @param protkey pointer to buffer receiving the protected key and - * additional info (type, length) - * @return 0 on success, negative errno value on failure - */ -int pkey_sec2protkey(__u16 cardnr, __u16 domain, - const struct pkey_seckey *seckey, - struct pkey_protkey *protkey); - -/* - * Derive (AES) protected key from a given clear key value. - * @param keytype one of the PKEY_KEYTYPE values - * @param clrkey pointer to buffer with clear key data - * @param protkey pointer to buffer receiving the protected key and - * additional info (type, length) - * @return 0 on success, negative errno value on failure - */ -int pkey_clr2protkey(__u32 keytype, - const struct pkey_clrkey *clrkey, - struct pkey_protkey *protkey); - -/* - * Search for a matching crypto card based on the Master Key - * Verification Pattern provided inside a secure key. - * @param seckey pointer to buffer with the input secure key - * @param cardnr pointer to cardnr, receives the card number on success - * @param domain pointer to domain, receives the domain number on success - * @param verify if set, always verify by fetching verification pattern - * from card - * @return 0 on success, negative errno value on failure. If no card could be - * found, -ENODEV is returned. - */ -int pkey_findcard(const struct pkey_seckey *seckey, - __u16 *cardnr, __u16 *domain, int verify); - -/* - * Find card and transform secure key to protected key. - * @param seckey pointer to buffer with the input secure key - * @param protkey pointer to buffer receiving the protected key and - * additional info (type, length) - * @return 0 on success, negative errno value on failure - */ -int pkey_skey2pkey(const struct pkey_seckey *seckey, - struct pkey_protkey *protkey); - -/* - * Verify the given secure key for being able to be useable with - * the pkey module. Check for correct key type and check for having at - * least one crypto card being able to handle this key (master key - * or old master key verification pattern matches). - * Return some info about the key: keysize in bits, keytype (currently - * only AES), flag if key is wrapped with an old MKVP. - * @param seckey pointer to buffer with the input secure key - * @param pcardnr pointer to cardnr, receives the card number on success - * @param pdomain pointer to domain, receives the domain number on success - * @param pkeysize pointer to keysize, receives the bitsize of the key - * @param pattributes pointer to attributes, receives additional info - * PKEY_VERIFY_ATTR_AES if the key is an AES key - * PKEY_VERIFY_ATTR_OLD_MKVP if key has old mkvp stored in - * @return 0 on success, negative errno value on failure. If no card could - * be found which is able to handle this key, -ENODEV is returned. - */ -int pkey_verifykey(const struct pkey_seckey *seckey, - u16 *pcardnr, u16 *pdomain, - u16 *pkeysize, u32 *pattributes); - -/* - * In-kernel API: Generate (AES) random protected key. - * @param keytype one of the PKEY_KEYTYPE values - * @param protkey pointer to buffer receiving the protected key - * @return 0 on success, negative errno value on failure - */ -int pkey_genprotkey(__u32 keytype, struct pkey_protkey *protkey); - -/* - * In-kernel API: Verify an (AES) protected key. - * @param protkey pointer to buffer containing the protected key to verify - * @return 0 on success, negative errno value on failure. In case the protected - * key is not valid -EKEYREJECTED is returned - */ -int pkey_verifyprotkey(const struct pkey_protkey *protkey); - -/* * In-kernel API: Transform an key blob (of any type) into a protected key. * @param key pointer to a buffer containing the key blob * @param keylen size of the key blob in bytes * @param protkey pointer to buffer receiving the protected key * @return 0 on success, negative errno value on failure */ -int pkey_keyblob2pkey(const __u8 *key, __u32 keylen, +int pkey_keyblob2pkey(const u8 *key, u32 keylen, struct pkey_protkey *protkey); #endif /* _KAPI_PKEY_H */ diff --git a/arch/s390/include/asm/preempt.h b/arch/s390/include/asm/preempt.h index b5ea9e14c017..6ede29907fbf 100644 --- a/arch/s390/include/asm/preempt.h +++ b/arch/s390/include/asm/preempt.h @@ -130,11 +130,11 @@ static inline bool should_resched(int preempt_offset) #endif /* CONFIG_HAVE_MARCH_Z196_FEATURES */ -#ifdef CONFIG_PREEMPT +#ifdef CONFIG_PREEMPTION extern asmlinkage void preempt_schedule(void); #define __preempt_schedule() preempt_schedule() extern asmlinkage void preempt_schedule_notrace(void); #define __preempt_schedule_notrace() preempt_schedule_notrace() -#endif /* CONFIG_PREEMPT */ +#endif /* CONFIG_PREEMPTION */ #endif /* __ASM_PREEMPT_H */ diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index d56c519bc696..361ef5eda468 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -206,7 +206,7 @@ unsigned long get_wchan(struct task_struct *p); /* Has task runtime instrumentation enabled ? */ #define is_ri_task(tsk) (!!(tsk)->thread.ri_cb) -static inline unsigned long current_stack_pointer(void) +static __always_inline unsigned long current_stack_pointer(void) { unsigned long sp; @@ -310,7 +310,7 @@ void enabled_wait(void); /* * Function to drop a processor into disabled wait state */ -static inline void __noreturn disabled_wait(void) +static __always_inline void __noreturn disabled_wait(void) { psw_t psw; @@ -324,11 +324,9 @@ static inline void __noreturn disabled_wait(void) * Basic Machine Check/Program Check Handler. */ -extern void s390_base_mcck_handler(void); extern void s390_base_pgm_handler(void); extern void s390_base_ext_handler(void); -extern void (*s390_base_mcck_handler_fn)(void); extern void (*s390_base_pgm_handler_fn)(void); extern void (*s390_base_ext_handler_fn)(void); diff --git a/arch/s390/include/asm/qdio.h b/arch/s390/include/asm/qdio.h index f647d565bd6d..71e3f0146cda 100644 --- a/arch/s390/include/asm/qdio.h +++ b/arch/s390/include/asm/qdio.h @@ -16,6 +16,7 @@ #define QDIO_MAX_QUEUES_PER_IRQ 4 #define QDIO_MAX_BUFFERS_PER_Q 128 #define QDIO_MAX_BUFFERS_MASK (QDIO_MAX_BUFFERS_PER_Q - 1) +#define QDIO_BUFNR(num) ((num) & QDIO_MAX_BUFFERS_MASK) #define QDIO_MAX_ELEMENTS_PER_BUFFER 16 #define QDIO_SBAL_SIZE 256 @@ -110,7 +111,7 @@ struct qib { /* private: */ u8 res[88]; /* public: */ - u8 parm[QDIO_MAX_BUFFERS_PER_Q]; + u8 parm[128]; } __attribute__ ((packed, aligned(256))); /** @@ -275,6 +276,7 @@ struct qdio_outbuf_state { #define CHSC_AC2_MULTI_BUFFER_AVAILABLE 0x0080 #define CHSC_AC2_MULTI_BUFFER_ENABLED 0x0040 #define CHSC_AC2_DATA_DIV_AVAILABLE 0x0010 +#define CHSC_AC2_SNIFFER_AVAILABLE 0x0008 #define CHSC_AC2_DATA_DIV_ENABLED 0x0002 #define CHSC_AC3_FORMAT2_CQ_AVAILABLE 0x8000 @@ -359,7 +361,7 @@ struct qdio_initialize { qdio_handler_t *output_handler; void (**queue_start_poll_array) (struct ccw_device *, int, unsigned long); - int scan_threshold; + unsigned int scan_threshold; unsigned long int_parm; struct qdio_buffer **input_sbal_addr_array; struct qdio_buffer **output_sbal_addr_array; @@ -416,6 +418,9 @@ extern int do_QDIO(struct ccw_device *, unsigned int, int, unsigned int, extern int qdio_start_irq(struct ccw_device *, int); extern int qdio_stop_irq(struct ccw_device *, int); extern int qdio_get_next_buffers(struct ccw_device *, int, int *, int *); +extern int qdio_inspect_queue(struct ccw_device *cdev, unsigned int nr, + bool is_input, unsigned int *bufnr, + unsigned int *error); extern int qdio_shutdown(struct ccw_device *, int); extern int qdio_free(struct ccw_device *); extern int qdio_get_ssqd_desc(struct ccw_device *, struct qdio_ssqd_desc *); diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h index 70bd65724ec4..b241ddb67caf 100644 --- a/arch/s390/include/asm/setup.h +++ b/arch/s390/include/asm/setup.h @@ -27,7 +27,6 @@ #define MACHINE_FLAG_DIAG9C BIT(3) #define MACHINE_FLAG_ESOP BIT(4) #define MACHINE_FLAG_IDTE BIT(5) -#define MACHINE_FLAG_DIAG44 BIT(6) #define MACHINE_FLAG_EDAT1 BIT(7) #define MACHINE_FLAG_EDAT2 BIT(8) #define MACHINE_FLAG_TOPOLOGY BIT(10) @@ -80,9 +79,17 @@ struct parmarea { char command_line[ARCH_COMMAND_LINE_SIZE]; /* 0x10480 */ }; +extern unsigned int zlib_dfltcc_support; +#define ZLIB_DFLTCC_DISABLED 0 +#define ZLIB_DFLTCC_FULL 1 +#define ZLIB_DFLTCC_DEFLATE_ONLY 2 +#define ZLIB_DFLTCC_INFLATE_ONLY 3 +#define ZLIB_DFLTCC_FULL_DEBUG 4 + extern int noexec_disabled; extern int memory_end_set; extern unsigned long memory_end; +extern unsigned long vmalloc_size; extern unsigned long max_physmem_end; extern unsigned long __swsusp_reset_dma; @@ -93,7 +100,6 @@ extern unsigned long __swsusp_reset_dma; #define MACHINE_HAS_DIAG9C (S390_lowcore.machine_flags & MACHINE_FLAG_DIAG9C) #define MACHINE_HAS_ESOP (S390_lowcore.machine_flags & MACHINE_FLAG_ESOP) #define MACHINE_HAS_IDTE (S390_lowcore.machine_flags & MACHINE_FLAG_IDTE) -#define MACHINE_HAS_DIAG44 (S390_lowcore.machine_flags & MACHINE_FLAG_DIAG44) #define MACHINE_HAS_EDAT1 (S390_lowcore.machine_flags & MACHINE_FLAG_EDAT1) #define MACHINE_HAS_EDAT2 (S390_lowcore.machine_flags & MACHINE_FLAG_EDAT2) #define MACHINE_HAS_TOPOLOGY (S390_lowcore.machine_flags & MACHINE_FLAG_TOPOLOGY) diff --git a/arch/s390/include/asm/spinlock.h b/arch/s390/include/asm/spinlock.h index c02bff33f6c7..3a37172d5398 100644 --- a/arch/s390/include/asm/spinlock.h +++ b/arch/s390/include/asm/spinlock.h @@ -85,7 +85,7 @@ static inline int arch_spin_trylock(arch_spinlock_t *lp) static inline void arch_spin_unlock(arch_spinlock_t *lp) { typecheck(int, lp->lock); - asm volatile( + asm_inline volatile( ALTERNATIVE("", ".long 0xb2fa0070", 49) /* NIAI 7 */ " sth %1,%0\n" : "=Q" (((unsigned short *) &lp->lock)[1]) diff --git a/arch/s390/include/asm/stacktrace.h b/arch/s390/include/asm/stacktrace.h index 0ae4bbf7779c..ee056f4a4fa3 100644 --- a/arch/s390/include/asm/stacktrace.h +++ b/arch/s390/include/asm/stacktrace.h @@ -33,8 +33,8 @@ static inline bool on_stack(struct stack_info *info, return addr >= info->begin && addr + len <= info->end; } -static inline unsigned long get_stack_pointer(struct task_struct *task, - struct pt_regs *regs) +static __always_inline unsigned long get_stack_pointer(struct task_struct *task, + struct pt_regs *regs) { if (regs) return (unsigned long) kernel_stack_pointer(regs); @@ -62,6 +62,17 @@ struct stack_frame { }; #endif +/* + * Unlike current_stack_pointer() which simply returns current value of %r15 + * current_frame_address() returns function stack frame address, which matches + * %r15 upon function invocation. It may differ from %r15 later if function + * allocates stack for local variables or new stack frame to call other + * functions. + */ +#define current_frame_address() \ + ((unsigned long)__builtin_frame_address(0) - \ + offsetof(struct stack_frame, back_chain)) + #define CALL_ARGS_0() \ register unsigned long r2 asm("2") #define CALL_ARGS_1(arg1) \ @@ -95,20 +106,33 @@ struct stack_frame { #define CALL_ON_STACK(fn, stack, nr, args...) \ ({ \ + unsigned long frame = current_frame_address(); \ CALL_ARGS_##nr(args); \ unsigned long prev; \ \ asm volatile( \ " la %[_prev],0(15)\n" \ - " la 15,0(%[_stack])\n" \ - " stg %[_prev],%[_bc](15)\n" \ + " lg 15,%[_stack]\n" \ + " stg %[_frame],%[_bc](15)\n" \ " brasl 14,%[_fn]\n" \ " la 15,0(%[_prev])\n" \ : [_prev] "=&a" (prev), CALL_FMT_##nr \ - [_stack] "a" (stack), \ + [_stack] "R" (stack), \ [_bc] "i" (offsetof(struct stack_frame, back_chain)), \ + [_frame] "d" (frame), \ [_fn] "X" (fn) : CALL_CLOBBER_##nr); \ r2; \ }) +#define CALL_ON_STACK_NORETURN(fn, stack) \ +({ \ + asm volatile( \ + " la 15,0(%[_stack])\n" \ + " xc %[_bc](8,15),%[_bc](15)\n" \ + " brasl 14,%[_fn]\n" \ + ::[_bc] "i" (offsetof(struct stack_frame, back_chain)), \ + [_stack] "a" (stack), [_fn] "X" (fn)); \ + BUG(); \ +}) + #endif /* _ASM_S390_STACKTRACE_H */ diff --git a/arch/s390/include/asm/string.h b/arch/s390/include/asm/string.h index 70d87db54e62..4c0690fc5167 100644 --- a/arch/s390/include/asm/string.h +++ b/arch/s390/include/asm/string.h @@ -71,11 +71,16 @@ extern void *__memmove(void *dest, const void *src, size_t n); #define memcpy(dst, src, len) __memcpy(dst, src, len) #define memmove(dst, src, len) __memmove(dst, src, len) #define memset(s, c, n) __memset(s, c, n) +#define strlen(s) __strlen(s) + +#define __no_sanitize_prefix_strfunc(x) __##x #ifndef __NO_FORTIFY #define __NO_FORTIFY /* FORTIFY_SOURCE uses __builtin_memcpy, etc. */ #endif +#else +#define __no_sanitize_prefix_strfunc(x) x #endif /* defined(CONFIG_KASAN) && !defined(__SANITIZE_ADDRESS__) */ void *__memset16(uint16_t *s, uint16_t v, size_t count); @@ -163,8 +168,8 @@ static inline char *strcpy(char *dst, const char *src) } #endif -#ifdef __HAVE_ARCH_STRLEN -static inline size_t strlen(const char *s) +#if defined(__HAVE_ARCH_STRLEN) || (defined(CONFIG_KASAN) && !defined(__SANITIZE_ADDRESS__)) +static inline size_t __no_sanitize_prefix_strfunc(strlen)(const char *s) { register unsigned long r0 asm("0") = 0; const char *tmp = s; diff --git a/arch/s390/include/asm/timex.h b/arch/s390/include/asm/timex.h index 64539c221672..6bf3a45ccfec 100644 --- a/arch/s390/include/asm/timex.h +++ b/arch/s390/include/asm/timex.h @@ -10,8 +10,9 @@ #ifndef _ASM_S390_TIMEX_H #define _ASM_S390_TIMEX_H -#include <asm/lowcore.h> +#include <linux/preempt.h> #include <linux/time64.h> +#include <asm/lowcore.h> /* The value of the TOD clock for 1.1.1970. */ #define TOD_UNIX_EPOCH 0x7d91048bca000000ULL @@ -154,7 +155,7 @@ static inline void get_tod_clock_ext(char *clk) static inline unsigned long long get_tod_clock(void) { - unsigned char clk[STORE_CLOCK_EXT_SIZE]; + char clk[STORE_CLOCK_EXT_SIZE]; get_tod_clock_ext(clk); return *((unsigned long long *)&clk[1]); @@ -179,22 +180,24 @@ static inline cycles_t get_cycles(void) int get_phys_clock(unsigned long *clock); void init_cpu_timer(void); -unsigned long long monotonic_clock(void); extern unsigned char tod_clock_base[16] __aligned(8); /** * get_clock_monotonic - returns current time in clock rate units * - * The caller must ensure that preemption is disabled. * The clock and tod_clock_base get changed via stop_machine. - * Therefore preemption must be disabled when calling this - * function, otherwise the returned value is not guaranteed to - * be monotonic. + * Therefore preemption must be disabled, otherwise the returned + * value is not guaranteed to be monotonic. */ static inline unsigned long long get_tod_clock_monotonic(void) { - return get_tod_clock() - *(unsigned long long *) &tod_clock_base[1]; + unsigned long long tod; + + preempt_disable_notrace(); + tod = get_tod_clock() - *(unsigned long long *) &tod_clock_base[1]; + preempt_enable_notrace(); + return tod; } /** diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h index bd2fd9a7821d..a470f1fa9f2a 100644 --- a/arch/s390/include/asm/uaccess.h +++ b/arch/s390/include/asm/uaccess.h @@ -83,7 +83,7 @@ raw_copy_to_user(void __user *to, const void *from, unsigned long n); __rc; \ }) -static inline int __put_user_fn(void *x, void __user *ptr, unsigned long size) +static __always_inline int __put_user_fn(void *x, void __user *ptr, unsigned long size) { unsigned long spec = 0x010000UL; int rc; @@ -113,7 +113,7 @@ static inline int __put_user_fn(void *x, void __user *ptr, unsigned long size) return rc; } -static inline int __get_user_fn(void *x, const void __user *ptr, unsigned long size) +static __always_inline int __get_user_fn(void *x, const void __user *ptr, unsigned long size) { unsigned long spec = 0x01UL; int rc; diff --git a/arch/s390/include/asm/unwind.h b/arch/s390/include/asm/unwind.h index d827b5b9a32c..de9006b0cfeb 100644 --- a/arch/s390/include/asm/unwind.h +++ b/arch/s390/include/asm/unwind.h @@ -58,10 +58,11 @@ static inline bool unwind_error(struct unwind_state *state) static inline void unwind_start(struct unwind_state *state, struct task_struct *task, struct pt_regs *regs, - unsigned long sp) + unsigned long first_frame) { - sp = sp ? : get_stack_pointer(task, regs); - __unwind_start(state, task, regs, sp); + task = task ?: current; + first_frame = first_frame ?: get_stack_pointer(task, regs); + __unwind_start(state, task, regs, first_frame); } static inline struct pt_regs *unwind_get_entry_regs(struct unwind_state *state) diff --git a/arch/s390/include/asm/uv.h b/arch/s390/include/asm/uv.h index ef3c00b049ab..4093a2856929 100644 --- a/arch/s390/include/asm/uv.h +++ b/arch/s390/include/asm/uv.h @@ -86,7 +86,7 @@ static inline int share(unsigned long addr, u16 cmd) }; if (!is_prot_virt_guest()) - return -ENOTSUPP; + return -EOPNOTSUPP; /* * Sharing is page wise, if we encounter addresses that are * not page aligned, we assume something went wrong. If diff --git a/arch/s390/include/asm/vdso.h b/arch/s390/include/asm/vdso.h index 169d7604eb80..3bcfdeb01395 100644 --- a/arch/s390/include/asm/vdso.h +++ b/arch/s390/include/asm/vdso.h @@ -41,8 +41,17 @@ struct vdso_data { struct vdso_per_cpu_data { __u64 ectg_timer_base; __u64 ectg_user_time; - __u32 cpu_nr; - __u32 node_id; + /* + * Note: node_id and cpu_nr must be at adjacent memory locations. + * VDSO userspace must read both values with a single instruction. + */ + union { + __u64 getcpu_val; + struct { + __u32 node_id; + __u32 cpu_nr; + }; + }; }; extern struct vdso_data *vdso_data; diff --git a/arch/s390/include/asm/vmalloc.h b/arch/s390/include/asm/vmalloc.h new file mode 100644 index 000000000000..3ba3a6bdca25 --- /dev/null +++ b/arch/s390/include/asm/vmalloc.h @@ -0,0 +1,4 @@ +#ifndef _ASM_S390_VMALLOC_H +#define _ASM_S390_VMALLOC_H + +#endif /* _ASM_S390_VMALLOC_H */ diff --git a/arch/s390/include/uapi/asm/ipcbuf.h b/arch/s390/include/uapi/asm/ipcbuf.h index 5b1c4f47c656..1030cd186899 100644 --- a/arch/s390/include/uapi/asm/ipcbuf.h +++ b/arch/s390/include/uapi/asm/ipcbuf.h @@ -2,6 +2,8 @@ #ifndef __S390_IPCBUF_H__ #define __S390_IPCBUF_H__ +#include <linux/posix_types.h> + /* * The user_ipc_perm structure for S/390 architecture. * Note extra padding because this structure is passed back and forth diff --git a/arch/s390/include/uapi/asm/kvm.h b/arch/s390/include/uapi/asm/kvm.h index 47104e5b47fd..436ec7636927 100644 --- a/arch/s390/include/uapi/asm/kvm.h +++ b/arch/s390/include/uapi/asm/kvm.h @@ -231,6 +231,12 @@ struct kvm_guest_debug_arch { #define KVM_SYNC_GSCB (1UL << 9) #define KVM_SYNC_BPBC (1UL << 10) #define KVM_SYNC_ETOKEN (1UL << 11) + +#define KVM_SYNC_S390_VALID_FIELDS \ + (KVM_SYNC_PREFIX | KVM_SYNC_GPRS | KVM_SYNC_ACRS | KVM_SYNC_CRS | \ + KVM_SYNC_ARCH0 | KVM_SYNC_PFAULT | KVM_SYNC_VRS | KVM_SYNC_RICCB | \ + KVM_SYNC_FPRS | KVM_SYNC_GSCB | KVM_SYNC_BPBC | KVM_SYNC_ETOKEN) + /* length and alignment of the sdnx as a power of two */ #define SDNXC 8 #define SDNXL (1UL << SDNXC) diff --git a/arch/s390/include/uapi/asm/pkey.h b/arch/s390/include/uapi/asm/pkey.h index c0e86ce4a00b..d27d7d329263 100644 --- a/arch/s390/include/uapi/asm/pkey.h +++ b/arch/s390/include/uapi/asm/pkey.h @@ -2,7 +2,7 @@ /* * Userspace interface to the pkey device driver * - * Copyright IBM Corp. 2017 + * Copyright IBM Corp. 2017, 2019 * * Author: Harald Freudenberger <freude@de.ibm.com> * @@ -20,38 +20,76 @@ #define PKEY_IOCTL_MAGIC 'p' -#define SECKEYBLOBSIZE 64 /* secure key blob size is always 64 bytes */ -#define PROTKEYBLOBSIZE 80 /* protected key blob size is always 80 bytes */ -#define MAXPROTKEYSIZE 64 /* a protected key blob may be up to 64 bytes */ -#define MAXCLRKEYSIZE 32 /* a clear key value may be up to 32 bytes */ +#define SECKEYBLOBSIZE 64 /* secure key blob size is always 64 bytes */ +#define PROTKEYBLOBSIZE 80 /* protected key blob size is always 80 bytes */ +#define MAXPROTKEYSIZE 64 /* a protected key blob may be up to 64 bytes */ +#define MAXCLRKEYSIZE 32 /* a clear key value may be up to 32 bytes */ +#define MAXAESCIPHERKEYSIZE 136 /* our aes cipher keys have always 136 bytes */ +#define MINEP11AESKEYBLOBSIZE 256 /* min EP11 AES key blob size */ +#define MAXEP11AESKEYBLOBSIZE 320 /* max EP11 AES key blob size */ -#define MINKEYBLOBSIZE SECKEYBLOBSIZE /* Minimum size of a key blob */ -#define MAXKEYBLOBSIZE PROTKEYBLOBSIZE /* Maximum size of a key blob */ +/* Minimum size of a key blob */ +#define MINKEYBLOBSIZE SECKEYBLOBSIZE /* defines for the type field within the pkey_protkey struct */ -#define PKEY_KEYTYPE_AES_128 1 -#define PKEY_KEYTYPE_AES_192 2 -#define PKEY_KEYTYPE_AES_256 3 +#define PKEY_KEYTYPE_AES_128 1 +#define PKEY_KEYTYPE_AES_192 2 +#define PKEY_KEYTYPE_AES_256 3 -/* Struct to hold a secure key blob */ +/* the newer ioctls use a pkey_key_type enum for type information */ +enum pkey_key_type { + PKEY_TYPE_CCA_DATA = (__u32) 1, + PKEY_TYPE_CCA_CIPHER = (__u32) 2, + PKEY_TYPE_EP11 = (__u32) 3, +}; + +/* the newer ioctls use a pkey_key_size enum for key size information */ +enum pkey_key_size { + PKEY_SIZE_AES_128 = (__u32) 128, + PKEY_SIZE_AES_192 = (__u32) 192, + PKEY_SIZE_AES_256 = (__u32) 256, + PKEY_SIZE_UNKNOWN = (__u32) 0xFFFFFFFF, +}; + +/* some of the newer ioctls use these flags */ +#define PKEY_FLAGS_MATCH_CUR_MKVP 0x00000002 +#define PKEY_FLAGS_MATCH_ALT_MKVP 0x00000004 + +/* keygenflags defines for CCA AES cipher keys */ +#define PKEY_KEYGEN_XPRT_SYM 0x00008000 +#define PKEY_KEYGEN_XPRT_UASY 0x00004000 +#define PKEY_KEYGEN_XPRT_AASY 0x00002000 +#define PKEY_KEYGEN_XPRT_RAW 0x00001000 +#define PKEY_KEYGEN_XPRT_CPAC 0x00000800 +#define PKEY_KEYGEN_XPRT_DES 0x00000080 +#define PKEY_KEYGEN_XPRT_AES 0x00000040 +#define PKEY_KEYGEN_XPRT_RSA 0x00000008 + +/* Struct to hold apqn target info (card/domain pair) */ +struct pkey_apqn { + __u16 card; + __u16 domain; +}; + +/* Struct to hold a CCA AES secure key blob */ struct pkey_seckey { __u8 seckey[SECKEYBLOBSIZE]; /* the secure key blob */ }; /* Struct to hold protected key and length info */ struct pkey_protkey { - __u32 type; /* key type, one of the PKEY_KEYTYPE values */ + __u32 type; /* key type, one of the PKEY_KEYTYPE_AES values */ __u32 len; /* bytes actually stored in protkey[] */ __u8 protkey[MAXPROTKEYSIZE]; /* the protected key blob */ }; -/* Struct to hold a clear key value */ +/* Struct to hold an AES clear key value */ struct pkey_clrkey { __u8 clrkey[MAXCLRKEYSIZE]; /* 16, 24, or 32 byte clear key value */ }; /* - * Generate secure key + * Generate CCA AES secure key. */ struct pkey_genseck { __u16 cardnr; /* in: card to use or FFFF for any */ @@ -62,7 +100,7 @@ struct pkey_genseck { #define PKEY_GENSECK _IOWR(PKEY_IOCTL_MAGIC, 0x01, struct pkey_genseck) /* - * Construct secure key from clear key value + * Construct CCA AES secure key from clear key value */ struct pkey_clr2seck { __u16 cardnr; /* in: card to use or FFFF for any */ @@ -74,7 +112,7 @@ struct pkey_clr2seck { #define PKEY_CLR2SECK _IOWR(PKEY_IOCTL_MAGIC, 0x02, struct pkey_clr2seck) /* - * Fabricate protected key from a secure key + * Fabricate AES protected key from a CCA AES secure key */ struct pkey_sec2protk { __u16 cardnr; /* in: card to use or FFFF for any */ @@ -85,7 +123,7 @@ struct pkey_sec2protk { #define PKEY_SEC2PROTK _IOWR(PKEY_IOCTL_MAGIC, 0x03, struct pkey_sec2protk) /* - * Fabricate protected key from an clear key value + * Fabricate AES protected key from clear key value */ struct pkey_clr2protk { __u32 keytype; /* in: key type to generate */ @@ -96,7 +134,7 @@ struct pkey_clr2protk { /* * Search for matching crypto card based on the Master Key - * Verification Pattern provided inside a secure key. + * Verification Pattern provided inside a CCA AES secure key. */ struct pkey_findcard { struct pkey_seckey seckey; /* in: the secure key blob */ @@ -115,7 +153,7 @@ struct pkey_skey2pkey { #define PKEY_SKEY2PKEY _IOWR(PKEY_IOCTL_MAGIC, 0x06, struct pkey_skey2pkey) /* - * Verify the given secure key for being able to be useable with + * Verify the given CCA AES secure key for being able to be useable with * the pkey module. Check for correct key type and check for having at * least one crypto card being able to handle this key (master key * or old master key verification pattern matches). @@ -134,7 +172,7 @@ struct pkey_verifykey { #define PKEY_VERIFY_ATTR_OLD_MKVP 0x00000100 /* key has old MKVP value */ /* - * Generate (AES) random protected key. + * Generate AES random protected key. */ struct pkey_genprotk { __u32 keytype; /* in: key type to generate */ @@ -144,7 +182,7 @@ struct pkey_genprotk { #define PKEY_GENPROTK _IOWR(PKEY_IOCTL_MAGIC, 0x08, struct pkey_genprotk) /* - * Verify an (AES) protected key. + * Verify an AES protected key. */ struct pkey_verifyprotk { struct pkey_protkey protkey; /* in: the protected key to verify */ @@ -160,7 +198,203 @@ struct pkey_kblob2pkey { __u32 keylen; /* in: the key blob length */ struct pkey_protkey protkey; /* out: the protected key */ }; - #define PKEY_KBLOB2PROTK _IOWR(PKEY_IOCTL_MAGIC, 0x0A, struct pkey_kblob2pkey) +/* + * Generate secure key, version 2. + * Generate CCA AES secure key, CCA AES cipher key or EP11 AES secure key. + * There needs to be a list of apqns given with at least one entry in there. + * All apqns in the list need to be exact apqns, 0xFFFF as ANY card or domain + * is not supported. The implementation walks through the list of apqns and + * tries to send the request to each apqn without any further checking (like + * card type or online state). If the apqn fails, simple the next one in the + * list is tried until success (return 0) or the end of the list is reached + * (return -1 with errno ENODEV). You may use the PKEY_APQNS4KT ioctl to + * generate a list of apqns based on the key type to generate. + * The keygenflags argument is passed to the low level generation functions + * individual for the key type and has a key type specific meaning. When + * generating CCA cipher keys you can use one or more of the PKEY_KEYGEN_* + * flags to widen the export possibilities. By default a cipher key is + * only exportable for CPACF (PKEY_KEYGEN_XPRT_CPAC). + * The keygenflag argument for generating an EP11 AES key should either be 0 + * to use the defaults which are XCP_BLOB_ENCRYPT, XCP_BLOB_DECRYPT and + * XCP_BLOB_PROTKEY_EXTRACTABLE or a valid combination of XCP_BLOB_* flags. + */ +struct pkey_genseck2 { + struct pkey_apqn __user *apqns; /* in: ptr to list of apqn targets*/ + __u32 apqn_entries; /* in: # of apqn target list entries */ + enum pkey_key_type type; /* in: key type to generate */ + enum pkey_key_size size; /* in: key size to generate */ + __u32 keygenflags; /* in: key generation flags */ + __u8 __user *key; /* in: pointer to key blob buffer */ + __u32 keylen; /* in: available key blob buffer size */ + /* out: actual key blob size */ +}; +#define PKEY_GENSECK2 _IOWR(PKEY_IOCTL_MAGIC, 0x11, struct pkey_genseck2) + +/* + * Generate secure key from clear key value, version 2. + * Construct an CCA AES secure key, CCA AES cipher key or EP11 AES secure + * key from a given clear key value. + * There needs to be a list of apqns given with at least one entry in there. + * All apqns in the list need to be exact apqns, 0xFFFF as ANY card or domain + * is not supported. The implementation walks through the list of apqns and + * tries to send the request to each apqn without any further checking (like + * card type or online state). If the apqn fails, simple the next one in the + * list is tried until success (return 0) or the end of the list is reached + * (return -1 with errno ENODEV). You may use the PKEY_APQNS4KT ioctl to + * generate a list of apqns based on the key type to generate. + * The keygenflags argument is passed to the low level generation functions + * individual for the key type and has a key type specific meaning. When + * generating CCA cipher keys you can use one or more of the PKEY_KEYGEN_* + * flags to widen the export possibilities. By default a cipher key is + * only exportable for CPACF (PKEY_KEYGEN_XPRT_CPAC). + * The keygenflag argument for generating an EP11 AES key should either be 0 + * to use the defaults which are XCP_BLOB_ENCRYPT, XCP_BLOB_DECRYPT and + * XCP_BLOB_PROTKEY_EXTRACTABLE or a valid combination of XCP_BLOB_* flags. + */ +struct pkey_clr2seck2 { + struct pkey_apqn __user *apqns; /* in: ptr to list of apqn targets */ + __u32 apqn_entries; /* in: # of apqn target list entries */ + enum pkey_key_type type; /* in: key type to generate */ + enum pkey_key_size size; /* in: key size to generate */ + __u32 keygenflags; /* in: key generation flags */ + struct pkey_clrkey clrkey; /* in: the clear key value */ + __u8 __user *key; /* in: pointer to key blob buffer */ + __u32 keylen; /* in: available key blob buffer size */ + /* out: actual key blob size */ +}; +#define PKEY_CLR2SECK2 _IOWR(PKEY_IOCTL_MAGIC, 0x12, struct pkey_clr2seck2) + +/* + * Verify the given secure key, version 2. + * Check for correct key type. If cardnr and domain are given (are not + * 0xFFFF) also check if this apqn is able to handle this type of key. + * If cardnr and/or domain is 0xFFFF, on return these values are filled + * with one apqn able to handle this key. + * The function also checks for the master key verification patterns + * of the key matching to the current or alternate mkvp of the apqn. + * For CCA AES secure keys and CCA AES cipher keys this means to check + * the key's mkvp against the current or old mkvp of the apqns. The flags + * field is updated with some additional info about the apqn mkvp + * match: If the current mkvp matches to the key's mkvp then the + * PKEY_FLAGS_MATCH_CUR_MKVP bit is set, if the alternate mkvp matches to + * the key's mkvp the PKEY_FLAGS_MATCH_ALT_MKVP is set. For CCA keys the + * alternate mkvp is the old master key verification pattern. + * CCA AES secure keys are also checked to have the CPACF export allowed + * bit enabled (XPRTCPAC) in the kmf1 field. + * EP11 keys are also supported and the wkvp of the key is checked against + * the current wkvp of the apqns. There is no alternate for this type of + * key and so on a match the flag PKEY_FLAGS_MATCH_CUR_MKVP always is set. + * EP11 keys are also checked to have XCP_BLOB_PROTKEY_EXTRACTABLE set. + * The ioctl returns 0 as long as the given or found apqn matches to + * matches with the current or alternate mkvp to the key's mkvp. If the given + * apqn does not match or there is no such apqn found, -1 with errno + * ENODEV is returned. + */ +struct pkey_verifykey2 { + __u8 __user *key; /* in: pointer to key blob */ + __u32 keylen; /* in: key blob size */ + __u16 cardnr; /* in/out: card number */ + __u16 domain; /* in/out: domain number */ + enum pkey_key_type type; /* out: the key type */ + enum pkey_key_size size; /* out: the key size */ + __u32 flags; /* out: additional key info flags */ +}; +#define PKEY_VERIFYKEY2 _IOWR(PKEY_IOCTL_MAGIC, 0x17, struct pkey_verifykey2) + +/* + * Transform a key blob (of any type) into a protected key, version 2. + * There needs to be a list of apqns given with at least one entry in there. + * All apqns in the list need to be exact apqns, 0xFFFF as ANY card or domain + * is not supported. The implementation walks through the list of apqns and + * tries to send the request to each apqn without any further checking (like + * card type or online state). If the apqn fails, simple the next one in the + * list is tried until success (return 0) or the end of the list is reached + * (return -1 with errno ENODEV). You may use the PKEY_APQNS4K ioctl to + * generate a list of apqns based on the key. + */ +struct pkey_kblob2pkey2 { + __u8 __user *key; /* in: pointer to key blob */ + __u32 keylen; /* in: key blob size */ + struct pkey_apqn __user *apqns; /* in: ptr to list of apqn targets */ + __u32 apqn_entries; /* in: # of apqn target list entries */ + struct pkey_protkey protkey; /* out: the protected key */ +}; +#define PKEY_KBLOB2PROTK2 _IOWR(PKEY_IOCTL_MAGIC, 0x1A, struct pkey_kblob2pkey2) + +/* + * Build a list of APQNs based on a key blob given. + * Is able to find out which type of secure key is given (CCA AES secure + * key, CCA AES cipher key or EP11 AES key) and tries to find all matching + * crypto cards based on the MKVP and maybe other criterias (like CCA AES + * cipher keys need a CEX5C or higher, EP11 keys with BLOB_PKEY_EXTRACTABLE + * need a CEX7 and EP11 api version 4). The list of APQNs is further filtered + * by the key's mkvp which needs to match to either the current mkvp (CCA and + * EP11) or the alternate mkvp (old mkvp, CCA adapters only) of the apqns. The + * flags argument may be used to limit the matching apqns. If the + * PKEY_FLAGS_MATCH_CUR_MKVP is given, only the current mkvp of each apqn is + * compared. Likewise with the PKEY_FLAGS_MATCH_ALT_MKVP. If both are given, it + * is assumed to return apqns where either the current or the alternate mkvp + * matches. At least one of the matching flags needs to be given. + * The flags argument for EP11 keys has no further action and is currently + * ignored (but needs to be given as PKEY_FLAGS_MATCH_CUR_MKVP) as there is only + * the wkvp from the key to match against the apqn's wkvp. + * The list of matching apqns is stored into the space given by the apqns + * argument and the number of stored entries goes into apqn_entries. If the list + * is empty (apqn_entries is 0) the apqn_entries field is updated to the number + * of apqn targets found and the ioctl returns with 0. If apqn_entries is > 0 + * but the number of apqn targets does not fit into the list, the apqn_targets + * field is updatedd with the number of reqired entries but there are no apqn + * values stored in the list and the ioctl returns with ENOSPC. If no matching + * APQN is found, the ioctl returns with 0 but the apqn_entries value is 0. + */ +struct pkey_apqns4key { + __u8 __user *key; /* in: pointer to key blob */ + __u32 keylen; /* in: key blob size */ + __u32 flags; /* in: match controlling flags */ + struct pkey_apqn __user *apqns; /* in/out: ptr to list of apqn targets*/ + __u32 apqn_entries; /* in: max # of apqn entries in the list */ + /* out: # apqns stored into the list */ +}; +#define PKEY_APQNS4K _IOWR(PKEY_IOCTL_MAGIC, 0x1B, struct pkey_apqns4key) + +/* + * Build a list of APQNs based on a key type given. + * Build a list of APQNs based on a given key type and maybe further + * restrict the list by given master key verification patterns. + * For different key types there may be different ways to match the + * master key verification patterns. For CCA keys (CCA data key and CCA + * cipher key) the first 8 bytes of cur_mkvp refer to the current mkvp value + * of the apqn and the first 8 bytes of the alt_mkvp refer to the old mkvp. + * The flags argument controls if the apqns current and/or alternate mkvp + * should match. If the PKEY_FLAGS_MATCH_CUR_MKVP is given, only the current + * mkvp of each apqn is compared. Likewise with the PKEY_FLAGS_MATCH_ALT_MKVP. + * If both are given, it is assumed to return apqns where either the + * current or the alternate mkvp matches. If no match flag is given + * (flags is 0) the mkvp values are ignored for the match process. + * For EP11 keys there is only the current wkvp. So if the apqns should also + * match to a given wkvp, then the PKEY_FLAGS_MATCH_CUR_MKVP flag should be + * set. The wkvp value is 32 bytes but only the leftmost 16 bytes are compared + * against the leftmost 16 byte of the wkvp of the apqn. + * The list of matching apqns is stored into the space given by the apqns + * argument and the number of stored entries goes into apqn_entries. If the list + * is empty (apqn_entries is 0) the apqn_entries field is updated to the number + * of apqn targets found and the ioctl returns with 0. If apqn_entries is > 0 + * but the number of apqn targets does not fit into the list, the apqn_targets + * field is updatedd with the number of reqired entries but there are no apqn + * values stored in the list and the ioctl returns with ENOSPC. If no matching + * APQN is found, the ioctl returns with 0 but the apqn_entries value is 0. + */ +struct pkey_apqns4keytype { + enum pkey_key_type type; /* in: key type */ + __u8 cur_mkvp[32]; /* in: current mkvp */ + __u8 alt_mkvp[32]; /* in: alternate mkvp */ + __u32 flags; /* in: match controlling flags */ + struct pkey_apqn __user *apqns; /* in/out: ptr to list of apqn targets*/ + __u32 apqn_entries; /* in: max # of apqn entries in the list */ + /* out: # apqns stored into the list */ +}; +#define PKEY_APQNS4KT _IOWR(PKEY_IOCTL_MAGIC, 0x1C, struct pkey_apqns4keytype) + #endif /* _UAPI_PKEY_H */ diff --git a/arch/s390/include/uapi/asm/zcrypt.h b/arch/s390/include/uapi/asm/zcrypt.h index 8c5755f41dde..5a2177e96e88 100644 --- a/arch/s390/include/uapi/asm/zcrypt.h +++ b/arch/s390/include/uapi/asm/zcrypt.h @@ -4,7 +4,7 @@ * * zcrypt 2.2.1 (user-visible header) * - * Copyright IBM Corp. 2001, 2018 + * Copyright IBM Corp. 2001, 2019 * Author(s): Robert Burroughs * Eric Rossman (edrossma@us.ibm.com) * @@ -161,17 +161,17 @@ struct ica_xcRB { * @payload_len: Payload length */ struct ep11_cprb { - __u16 cprb_len; - unsigned char cprb_ver_id; - unsigned char pad_000[2]; - unsigned char flags; - unsigned char func_id[2]; - __u32 source_id; - __u32 target_id; - __u32 ret_code; - __u32 reserved1; - __u32 reserved2; - __u32 payload_len; + __u16 cprb_len; + __u8 cprb_ver_id; + __u8 pad_000[2]; + __u8 flags; + __u8 func_id[2]; + __u32 source_id; + __u32 target_id; + __u32 ret_code; + __u32 reserved1; + __u32 reserved2; + __u32 payload_len; } __attribute__((packed)); /** @@ -197,13 +197,13 @@ struct ep11_target_dev { */ struct ep11_urb { __u16 targets_num; - __u64 targets; + __u8 __user *targets; __u64 weight; __u64 req_no; __u64 req_len; - __u64 req; + __u8 __user *req; __u64 resp_len; - __u64 resp; + __u8 __user *resp; } __attribute__((packed)); /** @@ -237,7 +237,9 @@ struct zcrypt_device_matrix_ext { struct zcrypt_device_status_ext device[MAX_ZDEV_ENTRIES_EXT]; }; -#define AUTOSELECT 0xFFFFFFFF +#define AUTOSELECT 0xFFFFFFFF +#define AUTOSEL_AP ((__u16) 0xFFFF) +#define AUTOSEL_DOM ((__u16) 0xFFFF) #define ZCRYPT_IOCTL_MAGIC 'z' @@ -286,7 +288,7 @@ struct zcrypt_device_matrix_ext { * 0x08: CEX3A * 0x0a: CEX4 * 0x0b: CEX5 - * 0x0c: CEX6 + * 0x0c: CEX6 and CEX7 * 0x0d: device is disabled * * ZCRYPT_QDEPTH_MASK diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile index 0f255b54b051..2b1203cf7be6 100644 --- a/arch/s390/kernel/Makefile +++ b/arch/s390/kernel/Makefile @@ -10,20 +10,12 @@ CFLAGS_REMOVE_ftrace.o = $(CC_FLAGS_FTRACE) # Do not trace early setup code CFLAGS_REMOVE_early.o = $(CC_FLAGS_FTRACE) -CFLAGS_REMOVE_early_nobss.o = $(CC_FLAGS_FTRACE) endif GCOV_PROFILE_early.o := n -GCOV_PROFILE_early_nobss.o := n - KCOV_INSTRUMENT_early.o := n -KCOV_INSTRUMENT_early_nobss.o := n - UBSAN_SANITIZE_early.o := n -UBSAN_SANITIZE_early_nobss.o := n - -KASAN_SANITIZE_early_nobss.o := n KASAN_SANITIZE_ipl.o := n KASAN_SANITIZE_machine_kexec.o := n @@ -48,7 +40,7 @@ CFLAGS_ptrace.o += -DUTS_MACHINE='"$(UTS_MACHINE)"' obj-y := traps.o time.o process.o base.o early.o setup.o idle.o vtime.o obj-y += processor.o sys_s390.o ptrace.o signal.o cpcmd.o ebcdic.o nmi.o -obj-y += debug.o irq.o ipl.o dis.o diag.o vdso.o early_nobss.o +obj-y += debug.o irq.o ipl.o dis.o diag.o vdso.o obj-y += sysinfo.o lgr.o os_info.o machine_kexec.o pgm_check.o obj-y += runtime_instr.o cache.o fpu.o dumpstack.o guarded_storage.o sthyi.o obj-y += entry.o reipl.o relocate_kernel.o kdebugfs.o alternative.o @@ -89,7 +81,3 @@ obj-$(CONFIG_TRACEPOINTS) += trace.o # vdso obj-y += vdso64/ -obj-$(CONFIG_COMPAT_VDSO) += vdso32/ - -chkbss := head64.o early_nobss.o -include $(srctree)/arch/s390/scripts/Makefile.chkbss diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c index 41ac4ad21311..ce33406cfe83 100644 --- a/arch/s390/kernel/asm-offsets.c +++ b/arch/s390/kernel/asm-offsets.c @@ -78,8 +78,7 @@ int main(void) OFFSET(__VDSO_TS_END, vdso_data, ts_end); OFFSET(__VDSO_ECTG_BASE, vdso_per_cpu_data, ectg_timer_base); OFFSET(__VDSO_ECTG_USER, vdso_per_cpu_data, ectg_user_time); - OFFSET(__VDSO_CPU_NR, vdso_per_cpu_data, cpu_nr); - OFFSET(__VDSO_NODE_ID, vdso_per_cpu_data, node_id); + OFFSET(__VDSO_GETCPU_VAL, vdso_per_cpu_data, getcpu_val); BLANK(); /* constants used by the vdso */ DEFINE(__CLOCK_REALTIME, CLOCK_REALTIME); diff --git a/arch/s390/kernel/base.S b/arch/s390/kernel/base.S index 2f39ea57f358..b79e0fd571f8 100644 --- a/arch/s390/kernel/base.S +++ b/arch/s390/kernel/base.S @@ -16,27 +16,6 @@ GEN_BR_THUNK %r9 GEN_BR_THUNK %r14 -ENTRY(s390_base_mcck_handler) - basr %r13,0 -0: lg %r15,__LC_NODAT_STACK # load panic stack - aghi %r15,-STACK_FRAME_OVERHEAD - larl %r1,s390_base_mcck_handler_fn - lg %r9,0(%r1) - ltgr %r9,%r9 - jz 1f - BASR_EX %r14,%r9 -1: la %r1,4095 - lmg %r0,%r15,__LC_GPREGS_SAVE_AREA-4095(%r1) - lpswe __LC_MCK_OLD_PSW -ENDPROC(s390_base_mcck_handler) - - .section .bss - .align 8 - .globl s390_base_mcck_handler_fn -s390_base_mcck_handler_fn: - .quad 0 - .previous - ENTRY(s390_base_ext_handler) stmg %r0,%r15,__LC_SAVE_AREA_ASYNC basr %r13,0 diff --git a/arch/s390/kernel/dis.c b/arch/s390/kernel/dis.c index 7abe6ae261b4..f304802ecf7b 100644 --- a/arch/s390/kernel/dis.c +++ b/arch/s390/kernel/dis.c @@ -461,10 +461,11 @@ static int print_insn(char *buffer, unsigned char *code, unsigned long addr) ptr += sprintf(ptr, "%%c%i", value); else if (operand->flags & OPERAND_VR) ptr += sprintf(ptr, "%%v%i", value); - else if (operand->flags & OPERAND_PCREL) - ptr += sprintf(ptr, "%lx", (signed int) value - + addr); - else if (operand->flags & OPERAND_SIGNED) + else if (operand->flags & OPERAND_PCREL) { + void *pcrel = (void *)((int)value + addr); + + ptr += sprintf(ptr, "%px", pcrel); + } else if (operand->flags & OPERAND_SIGNED) ptr += sprintf(ptr, "%i", value); else ptr += sprintf(ptr, "%u", value); @@ -536,7 +537,7 @@ void show_code(struct pt_regs *regs) else *ptr++ = ' '; addr = regs->psw.addr + start - 32; - ptr += sprintf(ptr, "%016lx: ", addr); + ptr += sprintf(ptr, "%px: ", (void *)addr); if (start + opsize >= end) break; for (i = 0; i < opsize; i++) @@ -564,7 +565,7 @@ void print_fn_code(unsigned char *code, unsigned long len) opsize = insn_length(*code); if (opsize > len) break; - ptr += sprintf(ptr, "%p: ", code); + ptr += sprintf(ptr, "%px: ", code); for (i = 0; i < opsize; i++) ptr += sprintf(ptr, "%02x", code[i]); *ptr++ = '\t'; diff --git a/arch/s390/kernel/dumpstack.c b/arch/s390/kernel/dumpstack.c index 34bdc60c0b11..2c122d8bab93 100644 --- a/arch/s390/kernel/dumpstack.c +++ b/arch/s390/kernel/dumpstack.c @@ -38,6 +38,7 @@ const char *stack_type_name(enum stack_type type) return "unknown"; } } +EXPORT_SYMBOL_GPL(stack_type_name); static inline bool in_stack(unsigned long sp, struct stack_info *info, enum stack_type type, unsigned long low, @@ -93,7 +94,9 @@ int get_stack_info(unsigned long sp, struct task_struct *task, if (!sp) goto unknown; - task = task ? : current; + /* Sanity check: ABI requires SP to be aligned 8 bytes. */ + if (sp & 0x7) + goto unknown; /* Check per-task stack */ if (in_task_stack(sp, task, info)) @@ -128,8 +131,6 @@ void show_stack(struct task_struct *task, unsigned long *stack) struct unwind_state state; printk("Call Trace:\n"); - if (!task) - task = current; unwind_for_each_frame(&state, task, NULL, (unsigned long) stack) printk(state.reliable ? " [<%016lx>] %pSR \n" : "([<%016lx>] %pSR)\n", @@ -194,6 +195,8 @@ void die(struct pt_regs *regs, const char *str) regs->int_code >> 17, ++die_counter); #ifdef CONFIG_PREEMPT pr_cont("PREEMPT "); +#elif defined(CONFIG_PREEMPT_RT) + pr_cont("PREEMPT_RT "); #endif pr_cont("SMP "); if (debug_pagealloc_enabled()) diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c index 6312fed48530..cd241ee66eff 100644 --- a/arch/s390/kernel/early.c +++ b/arch/s390/kernel/early.c @@ -30,8 +30,24 @@ #include <asm/sclp.h> #include <asm/facility.h> #include <asm/boot_data.h> +#include <asm/switch_to.h> #include "entry.h" +static void __init reset_tod_clock(void) +{ + u64 time; + + if (store_tod_clock(&time) == 0) + return; + /* TOD clock not running. Set the clock to Unix Epoch. */ + if (set_tod_clock(TOD_UNIX_EPOCH) != 0 || store_tod_clock(&time) != 0) + disabled_wait(); + + memset(tod_clock_base, 0, 16); + *(__u64 *) &tod_clock_base[1] = TOD_UNIX_EPOCH; + S390_lowcore.last_update_clock = TOD_UNIX_EPOCH; +} + /* * Initialize storage key for kernel pages */ @@ -188,21 +204,6 @@ static __init void detect_diag9c(void) S390_lowcore.machine_flags |= MACHINE_FLAG_DIAG9C; } -static __init void detect_diag44(void) -{ - int rc; - - diag_stat_inc(DIAG_STAT_X044); - asm volatile( - " diag 0,0,0x44\n" - "0: la %0,0\n" - "1:\n" - EX_TABLE(0b,1b) - : "=d" (rc) : "0" (-EOPNOTSUPP) : "cc"); - if (!rc) - S390_lowcore.machine_flags |= MACHINE_FLAG_DIAG44; -} - static __init void detect_machine_facilities(void) { if (test_facility(8)) { @@ -223,7 +224,7 @@ static __init void detect_machine_facilities(void) S390_lowcore.machine_flags |= MACHINE_FLAG_VX; __ctl_set_bit(0, 17); } - if (test_facility(130)) { + if (test_facility(130) && !noexec_disabled) { S390_lowcore.machine_flags |= MACHINE_FLAG_NX; __ctl_set_bit(0, 20); } @@ -245,6 +246,24 @@ static inline void save_vector_registers(void) #endif } +static inline void setup_control_registers(void) +{ + unsigned long reg; + + __ctl_store(reg, 0, 0); + reg |= CR0_LOW_ADDRESS_PROTECTION; + reg |= CR0_EMERGENCY_SIGNAL_SUBMASK; + reg |= CR0_EXTERNAL_CALL_SUBMASK; + __ctl_load(reg, 0, 0); +} + +static inline void setup_access_registers(void) +{ + unsigned int acrs[NUM_ACRS] = { 0 }; + + restore_access_regs(acrs); +} + static int __init disable_vector_extension(char *str) { S390_lowcore.machine_flags &= ~MACHINE_FLAG_VX; @@ -253,21 +272,6 @@ static int __init disable_vector_extension(char *str) } early_param("novx", disable_vector_extension); -static int __init noexec_setup(char *str) -{ - bool enabled; - int rc; - - rc = kstrtobool(str, &enabled); - if (!rc && !enabled) { - /* Disable no-execute support */ - S390_lowcore.machine_flags &= ~MACHINE_FLAG_NX; - __ctl_clear_bit(0, 20); - } - return rc; -} -early_param("noexec", noexec_setup); - static int __init cad_setup(char *str) { bool enabled; @@ -301,6 +305,7 @@ static void __init check_image_bootable(void) void __init startup_init(void) { + reset_tod_clock(); check_image_bootable(); time_early_init(); init_kernel_storage_key(); @@ -311,10 +316,11 @@ void __init startup_init(void) setup_arch_string(); setup_boot_command_line(); detect_diag9c(); - detect_diag44(); detect_machine_facilities(); save_vector_registers(); setup_topology(); sclp_early_detect(); + setup_control_registers(); + setup_access_registers(); lockdep_on(); } diff --git a/arch/s390/kernel/early_nobss.c b/arch/s390/kernel/early_nobss.c deleted file mode 100644 index 52a3ef959341..000000000000 --- a/arch/s390/kernel/early_nobss.c +++ /dev/null @@ -1,45 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Copyright IBM Corp. 2007, 2018 - */ - -/* - * Early setup functions which may not rely on an initialized bss - * section. The last thing that is supposed to happen here is - * initialization of the bss section. - */ - -#include <linux/processor.h> -#include <linux/string.h> -#include <asm/sections.h> -#include <asm/lowcore.h> -#include <asm/timex.h> -#include <asm/kasan.h> -#include "entry.h" - -static void __init reset_tod_clock(void) -{ - u64 time; - - if (store_tod_clock(&time) == 0) - return; - /* TOD clock not running. Set the clock to Unix Epoch. */ - if (set_tod_clock(TOD_UNIX_EPOCH) != 0 || store_tod_clock(&time) != 0) - disabled_wait(); - - memset(tod_clock_base, 0, 16); - *(__u64 *) &tod_clock_base[1] = TOD_UNIX_EPOCH; - S390_lowcore.last_update_clock = TOD_UNIX_EPOCH; -} - -static void __init clear_bss_section(void) -{ - memset(__bss_start, 0, __bss_stop - __bss_start); -} - -void __init startup_init_nobss(void) -{ - reset_tod_clock(); - clear_bss_section(); - kasan_early_init(); -} diff --git a/arch/s390/kernel/early_printk.c b/arch/s390/kernel/early_printk.c index 40c1dfec944e..6f24d83bc5dc 100644 --- a/arch/s390/kernel/early_printk.c +++ b/arch/s390/kernel/early_printk.c @@ -25,7 +25,7 @@ static int __init setup_early_printk(char *buf) if (early_console) return 0; /* Accept only "earlyprintk" and "earlyprintk=sclp" */ - if (buf && strncmp(buf, "sclp", 4)) + if (buf && !str_has_prefix(buf, "sclp")) return 0; if (!sclp.has_linemode && !sclp.has_vt220) return 0; diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 270d1d145761..9205add8481d 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -790,7 +790,7 @@ ENTRY(io_int_handler) .Lio_work: tm __PT_PSW+1(%r11),0x01 # returning to user ? jo .Lio_work_user # yes -> do resched & signal -#ifdef CONFIG_PREEMPT +#ifdef CONFIG_PREEMPTION # check for preemptive scheduling icm %r0,15,__LC_PREEMPT_COUNT jnz .Lio_restore # preemption is disabled diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h index b2956d49b6ad..1d3927e01a5f 100644 --- a/arch/s390/kernel/entry.h +++ b/arch/s390/kernel/entry.h @@ -45,6 +45,7 @@ void specification_exception(struct pt_regs *regs); void transaction_exception(struct pt_regs *regs); void translation_exception(struct pt_regs *regs); void vector_exception(struct pt_regs *regs); +void monitor_event_exception(struct pt_regs *regs); void do_per_trap(struct pt_regs *regs); void do_report_trap(struct pt_regs *regs, int si_signo, int si_code, char *str); diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c index 1bb85f60c0dd..4cd9b1ada834 100644 --- a/arch/s390/kernel/ftrace.c +++ b/arch/s390/kernel/ftrace.c @@ -72,15 +72,6 @@ static inline void ftrace_generate_orig_insn(struct ftrace_insn *insn) #endif } -static inline int is_kprobe_on_ftrace(struct ftrace_insn *insn) -{ -#ifdef CONFIG_KPROBES - if (insn->opc == BREAKPOINT_INSTRUCTION) - return 1; -#endif - return 0; -} - static inline void ftrace_generate_kprobe_nop_insn(struct ftrace_insn *insn) { #ifdef CONFIG_KPROBES @@ -114,16 +105,6 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, /* Initial code replacement */ ftrace_generate_orig_insn(&orig); ftrace_generate_nop_insn(&new); - } else if (is_kprobe_on_ftrace(&old)) { - /* - * If we find a breakpoint instruction, a kprobe has been - * placed at the beginning of the function. We write the - * constant KPROBE_ON_FTRACE_NOP into the remaining four - * bytes of the original instruction so that the kprobes - * handler can execute a nop, if it reaches this breakpoint. - */ - ftrace_generate_kprobe_call_insn(&orig); - ftrace_generate_kprobe_nop_insn(&new); } else { /* Replace ftrace call with a nop. */ ftrace_generate_call_insn(&orig, rec->ip); @@ -142,21 +123,10 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) if (probe_kernel_read(&old, (void *) rec->ip, sizeof(old))) return -EFAULT; - if (is_kprobe_on_ftrace(&old)) { - /* - * If we find a breakpoint instruction, a kprobe has been - * placed at the beginning of the function. We write the - * constant KPROBE_ON_FTRACE_CALL into the remaining four - * bytes of the original instruction so that the kprobes - * handler can execute a brasl if it reaches this breakpoint. - */ - ftrace_generate_kprobe_nop_insn(&orig); - ftrace_generate_kprobe_call_insn(&new); - } else { - /* Replace nop with an ftrace call. */ - ftrace_generate_nop_insn(&orig); - ftrace_generate_call_insn(&new, rec->ip); - } + /* Replace nop with an ftrace call. */ + ftrace_generate_nop_insn(&orig); + ftrace_generate_call_insn(&new, rec->ip); + /* Verify that the to be replaced code matches what we expect. */ if (memcmp(&orig, &old, sizeof(old))) return -EINVAL; @@ -241,3 +211,45 @@ int ftrace_disable_ftrace_graph_caller(void) } #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ + +#ifdef CONFIG_KPROBES_ON_FTRACE +void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *ops, struct pt_regs *regs) +{ + struct kprobe_ctlblk *kcb; + struct kprobe *p = get_kprobe((kprobe_opcode_t *)ip); + + if (unlikely(!p) || kprobe_disabled(p)) + return; + + if (kprobe_running()) { + kprobes_inc_nmissed_count(p); + return; + } + + __this_cpu_write(current_kprobe, p); + + kcb = get_kprobe_ctlblk(); + kcb->kprobe_status = KPROBE_HIT_ACTIVE; + + instruction_pointer_set(regs, ip); + + if (!p->pre_handler || !p->pre_handler(p, regs)) { + + instruction_pointer_set(regs, ip + MCOUNT_INSN_SIZE); + + if (unlikely(p->post_handler)) { + kcb->kprobe_status = KPROBE_HIT_SSDONE; + p->post_handler(p, regs, 0); + } + } + __this_cpu_write(current_kprobe, NULL); +} +NOKPROBE_SYMBOL(kprobe_ftrace_handler); + +int arch_prepare_kprobe_ftrace(struct kprobe *p) +{ + p->ainsn.insn = NULL; + return 0; +} +#endif diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S index f384a18e6c26..8b88dbbda7df 100644 --- a/arch/s390/kernel/head64.S +++ b/arch/s390/kernel/head64.S @@ -26,32 +26,17 @@ ENTRY(startup_continue) 0: larl %r1,tod_clock_base mvc 0(16,%r1),__LC_BOOT_CLOCK larl %r13,.LPG1 # get base - larl %r0,boot_vdso_data - stg %r0,__LC_VDSO_PER_CPU # # Setup stack # larl %r14,init_task stg %r14,__LC_CURRENT - larl %r15,init_thread_union+THREAD_SIZE-STACK_FRAME_OVERHEAD -# -# Early setup functions that may not rely on an initialized bss section, -# like moving the initrd. Returns with an initialized bss section. -# - brasl %r14,startup_init_nobss -# -# Early machine initialization and detection functions. -# - brasl %r14,startup_init - -# check control registers - stctg %c0,%c15,0(%r15) - oi 6(%r15),0x60 # enable sigp emergency & external call - oi 4(%r15),0x10 # switch on low address proctection - lctlg %c0,%c15,0(%r15) - - lam 0,15,.Laregs-.LPG1(%r13) # load acrs needed by uaccess - brasl %r14,start_kernel # go to C code + larl %r15,init_thread_union+THREAD_SIZE-STACK_FRAME_OVERHEAD-__PT_SIZE +#ifdef CONFIG_KASAN + brasl %r14,kasan_early_init +#endif + brasl %r14,startup_init # s390 specific early init + brasl %r14,start_kernel # common init code # # We returned from start_kernel ?!? PANIK # @@ -61,4 +46,3 @@ ENTRY(startup_continue) .align 16 .LPG1: .Ldw: .quad 0x0002000180000000,0x0000000000000000 -.Laregs:.long 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0 diff --git a/arch/s390/kernel/idle.c b/arch/s390/kernel/idle.c index b9d8fe45737a..8f8456816d83 100644 --- a/arch/s390/kernel/idle.c +++ b/arch/s390/kernel/idle.c @@ -69,18 +69,26 @@ DEVICE_ATTR(idle_count, 0444, show_idle_count, NULL); static ssize_t show_idle_time(struct device *dev, struct device_attribute *attr, char *buf) { + unsigned long long now, idle_time, idle_enter, idle_exit, in_idle; struct s390_idle_data *idle = &per_cpu(s390_idle, dev->id); - unsigned long long now, idle_time, idle_enter, idle_exit; unsigned int seq; do { - now = get_tod_clock(); seq = read_seqcount_begin(&idle->seqcount); idle_time = READ_ONCE(idle->idle_time); idle_enter = READ_ONCE(idle->clock_idle_enter); idle_exit = READ_ONCE(idle->clock_idle_exit); } while (read_seqcount_retry(&idle->seqcount, seq)); - idle_time += idle_enter ? ((idle_exit ? : now) - idle_enter) : 0; + in_idle = 0; + now = get_tod_clock(); + if (idle_enter) { + if (idle_exit) { + in_idle = idle_exit - idle_enter; + } else if (now > idle_enter) { + in_idle = now - idle_enter; + } + } + idle_time += in_idle; return sprintf(buf, "%llu\n", idle_time >> 12); } DEVICE_ATTR(idle_time_us, 0444, show_idle_time, NULL); @@ -88,17 +96,24 @@ DEVICE_ATTR(idle_time_us, 0444, show_idle_time, NULL); u64 arch_cpu_idle_time(int cpu) { struct s390_idle_data *idle = &per_cpu(s390_idle, cpu); - unsigned long long now, idle_enter, idle_exit; + unsigned long long now, idle_enter, idle_exit, in_idle; unsigned int seq; do { - now = get_tod_clock(); seq = read_seqcount_begin(&idle->seqcount); idle_enter = READ_ONCE(idle->clock_idle_enter); idle_exit = READ_ONCE(idle->clock_idle_exit); } while (read_seqcount_retry(&idle->seqcount, seq)); - - return cputime_to_nsecs(idle_enter ? ((idle_exit ?: now) - idle_enter) : 0); + in_idle = 0; + now = get_tod_clock(); + if (idle_enter) { + if (idle_exit) { + in_idle = idle_exit - idle_enter; + } else if (now > idle_enter) { + in_idle = now - idle_enter; + } + } + return cputime_to_nsecs(in_idle); } void arch_cpu_idle_enter(void) diff --git a/arch/s390/kernel/kexec_elf.c b/arch/s390/kernel/kexec_elf.c index 6d0635ceddd0..9da6fa30c447 100644 --- a/arch/s390/kernel/kexec_elf.c +++ b/arch/s390/kernel/kexec_elf.c @@ -130,7 +130,7 @@ static int s390_elf_probe(const char *buf, unsigned long len) const struct kexec_file_ops s390_kexec_elf_ops = { .probe = s390_elf_probe, .load = s390_elf_load, -#ifdef CONFIG_KEXEC_VERIFY_SIG +#ifdef CONFIG_KEXEC_SIG .verify_sig = s390_verify_sig, -#endif /* CONFIG_KEXEC_VERIFY_SIG */ +#endif /* CONFIG_KEXEC_SIG */ }; diff --git a/arch/s390/kernel/kexec_image.c b/arch/s390/kernel/kexec_image.c index 58318bf89fd9..af23eff5774d 100644 --- a/arch/s390/kernel/kexec_image.c +++ b/arch/s390/kernel/kexec_image.c @@ -59,7 +59,7 @@ static int s390_image_probe(const char *buf, unsigned long len) const struct kexec_file_ops s390_kexec_image_ops = { .probe = s390_image_probe, .load = s390_image_load, -#ifdef CONFIG_KEXEC_VERIFY_SIG +#ifdef CONFIG_KEXEC_SIG .verify_sig = s390_verify_sig, -#endif /* CONFIG_KEXEC_VERIFY_SIG */ +#endif /* CONFIG_KEXEC_SIG */ }; diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c index 6f1388391620..548d0ea9808d 100644 --- a/arch/s390/kernel/kprobes.c +++ b/arch/s390/kernel/kprobes.c @@ -56,21 +56,10 @@ struct kprobe_insn_cache kprobe_s390_insn_slots = { static void copy_instruction(struct kprobe *p) { - unsigned long ip = (unsigned long) p->addr; s64 disp, new_disp; u64 addr, new_addr; - if (ftrace_location(ip) == ip) { - /* - * If kprobes patches the instruction that is morphed by - * ftrace make sure that kprobes always sees the branch - * "jg .+24" that skips the mcount block or the "brcl 0,0" - * in case of hotpatch. - */ - ftrace_generate_nop_insn((struct ftrace_insn *)p->ainsn.insn); - p->ainsn.is_ftrace_insn = 1; - } else - memcpy(p->ainsn.insn, p->addr, insn_length(*p->addr >> 8)); + memcpy(p->ainsn.insn, p->addr, insn_length(*p->addr >> 8)); p->opcode = p->ainsn.insn[0]; if (!probe_is_insn_relative_long(p->ainsn.insn)) return; @@ -136,11 +125,6 @@ int arch_prepare_kprobe(struct kprobe *p) } NOKPROBE_SYMBOL(arch_prepare_kprobe); -int arch_check_ftrace_location(struct kprobe *p) -{ - return 0; -} - struct swap_insn_args { struct kprobe *p; unsigned int arm_kprobe : 1; @@ -149,28 +133,11 @@ struct swap_insn_args { static int swap_instruction(void *data) { struct swap_insn_args *args = data; - struct ftrace_insn new_insn, *insn; struct kprobe *p = args->p; - size_t len; - - new_insn.opc = args->arm_kprobe ? BREAKPOINT_INSTRUCTION : p->opcode; - len = sizeof(new_insn.opc); - if (!p->ainsn.is_ftrace_insn) - goto skip_ftrace; - len = sizeof(new_insn); - insn = (struct ftrace_insn *) p->addr; - if (args->arm_kprobe) { - if (is_ftrace_nop(insn)) - new_insn.disp = KPROBE_ON_FTRACE_NOP; - else - new_insn.disp = KPROBE_ON_FTRACE_CALL; - } else { - ftrace_generate_call_insn(&new_insn, (unsigned long)p->addr); - if (insn->disp == KPROBE_ON_FTRACE_NOP) - ftrace_generate_nop_insn(&new_insn); - } -skip_ftrace: - s390_kernel_write(p->addr, &new_insn, len); + u16 opc; + + opc = args->arm_kprobe ? BREAKPOINT_INSTRUCTION : p->opcode; + s390_kernel_write(p->addr, &opc, sizeof(opc)); return 0; } NOKPROBE_SYMBOL(swap_instruction); @@ -464,24 +431,6 @@ static void resume_execution(struct kprobe *p, struct pt_regs *regs) unsigned long ip = regs->psw.addr; int fixup = probe_get_fixup_type(p->ainsn.insn); - /* Check if the kprobes location is an enabled ftrace caller */ - if (p->ainsn.is_ftrace_insn) { - struct ftrace_insn *insn = (struct ftrace_insn *) p->addr; - struct ftrace_insn call_insn; - - ftrace_generate_call_insn(&call_insn, (unsigned long) p->addr); - /* - * A kprobe on an enabled ftrace call site actually single - * stepped an unconditional branch (ftrace nop equivalent). - * Now we need to fixup things and pretend that a brasl r0,... - * was executed instead. - */ - if (insn->disp == KPROBE_ON_FTRACE_CALL) { - ip += call_insn.disp * 2 - MCOUNT_INSN_SIZE; - regs->gprs[0] = (unsigned long)p->addr + sizeof(*insn); - } - } - if (fixup & FIXUP_PSW_NORMAL) ip += (unsigned long) p->addr - (unsigned long) p->ainsn.insn; diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c index 444a19125a81..cb8b1cc285c9 100644 --- a/arch/s390/kernel/machine_kexec.c +++ b/arch/s390/kernel/machine_kexec.c @@ -164,7 +164,9 @@ static bool kdump_csum_valid(struct kimage *image) #ifdef CONFIG_CRASH_DUMP int rc; + preempt_disable(); rc = CALL_ON_STACK(do_start_kdump, S390_lowcore.nodat_stack, 1, image); + preempt_enable(); return rc == 0; #else return false; @@ -254,10 +256,10 @@ void arch_crash_save_vmcoreinfo(void) VMCOREINFO_SYMBOL(lowcore_ptr); VMCOREINFO_SYMBOL(high_memory); VMCOREINFO_LENGTH(lowcore_ptr, NR_CPUS); - mem_assign_absolute(S390_lowcore.vmcore_info, paddr_vmcoreinfo_note()); vmcoreinfo_append_str("SDMA=%lx\n", __sdma); vmcoreinfo_append_str("EDMA=%lx\n", __edma); vmcoreinfo_append_str("KERNELOFFSET=%lx\n", kaslr_offset()); + mem_assign_absolute(S390_lowcore.vmcore_info, paddr_vmcoreinfo_note()); } void machine_shutdown(void) diff --git a/arch/s390/kernel/machine_kexec_file.c b/arch/s390/kernel/machine_kexec_file.c index fbdd3ea73667..8415ae7d2a23 100644 --- a/arch/s390/kernel/machine_kexec_file.c +++ b/arch/s390/kernel/machine_kexec_file.c @@ -10,7 +10,7 @@ #include <linux/elf.h> #include <linux/errno.h> #include <linux/kexec.h> -#include <linux/module.h> +#include <linux/module_signature.h> #include <linux/verification.h> #include <asm/boot_data.h> #include <asm/ipl.h> @@ -22,29 +22,7 @@ const struct kexec_file_ops * const kexec_file_loaders[] = { NULL, }; -#ifdef CONFIG_KEXEC_VERIFY_SIG -/* - * Module signature information block. - * - * The constituents of the signature section are, in order: - * - * - Signer's name - * - Key identifier - * - Signature data - * - Information block - */ -struct module_signature { - u8 algo; /* Public-key crypto algorithm [0] */ - u8 hash; /* Digest algorithm [0] */ - u8 id_type; /* Key identifier type [PKEY_ID_PKCS7] */ - u8 signer_len; /* Length of signer's name [0] */ - u8 key_id_len; /* Length of key identifier [0] */ - u8 __pad[3]; - __be32 sig_len; /* Length of signature data */ -}; - -#define PKEY_ID_PKCS7 2 - +#ifdef CONFIG_KEXEC_SIG int s390_verify_sig(const char *kernel, unsigned long kernel_len) { const unsigned long marker_len = sizeof(MODULE_SIG_STRING) - 1; @@ -90,7 +68,7 @@ int s390_verify_sig(const char *kernel, unsigned long kernel_len) VERIFYING_MODULE_SIGNATURE, NULL, NULL); } -#endif /* CONFIG_KEXEC_VERIFY_SIG */ +#endif /* CONFIG_KEXEC_SIG */ static int kexec_file_update_purgatory(struct kimage *image, struct s390_load_data *data) diff --git a/arch/s390/kernel/machine_kexec_reloc.c b/arch/s390/kernel/machine_kexec_reloc.c index 3b664cb3ec4d..d5035de9020e 100644 --- a/arch/s390/kernel/machine_kexec_reloc.c +++ b/arch/s390/kernel/machine_kexec_reloc.c @@ -27,6 +27,7 @@ int arch_kexec_do_relocs(int r_type, void *loc, unsigned long val, *(u32 *)loc = val; break; case R_390_64: /* Direct 64 bit. */ + case R_390_GLOB_DAT: *(u64 *)loc = val; break; case R_390_PC16: /* PC relative 16 bit. */ diff --git a/arch/s390/kernel/mcount.S b/arch/s390/kernel/mcount.S index 9e1660a6b9db..7458dcfd6464 100644 --- a/arch/s390/kernel/mcount.S +++ b/arch/s390/kernel/mcount.S @@ -26,6 +26,12 @@ ENDPROC(ftrace_stub) #define STACK_PTREGS (STACK_FRAME_OVERHEAD) #define STACK_PTREGS_GPRS (STACK_PTREGS + __PT_GPRS) #define STACK_PTREGS_PSW (STACK_PTREGS + __PT_PSW) +#ifdef __PACK_STACK +/* allocate just enough for r14, r15 and backchain */ +#define TRACED_FUNC_FRAME_SIZE 24 +#else +#define TRACED_FUNC_FRAME_SIZE STACK_FRAME_OVERHEAD +#endif ENTRY(_mcount) BR_EX %r14 @@ -35,13 +41,27 @@ EXPORT_SYMBOL(_mcount) ENTRY(ftrace_caller) .globl ftrace_regs_caller .set ftrace_regs_caller,ftrace_caller + stg %r14,(__SF_GPRS+8*8)(%r15) # save traced function caller + lghi %r14,0 # save condition code + ipm %r14 # don't put any instructions + sllg %r14,%r14,16 # clobbering CC before this point lgr %r1,%r15 #if !(defined(CC_USING_HOTPATCH) || defined(CC_USING_NOP_MCOUNT)) aghi %r0,MCOUNT_RETURN_FIXUP #endif - aghi %r15,-STACK_FRAME_SIZE + # allocate stack frame for ftrace_caller to contain traced function + aghi %r15,-TRACED_FUNC_FRAME_SIZE stg %r1,__SF_BACKCHAIN(%r15) + stg %r0,(__SF_GPRS+8*8)(%r15) + stg %r15,(__SF_GPRS+9*8)(%r15) + # allocate pt_regs and stack frame for ftrace_trace_function + aghi %r15,-STACK_FRAME_SIZE stg %r1,(STACK_PTREGS_GPRS+15*8)(%r15) + stg %r14,(STACK_PTREGS_PSW)(%r15) + lg %r14,(__SF_GPRS+8*8)(%r1) # restore original return address + stosm (STACK_PTREGS_PSW)(%r15),0 + aghi %r1,-TRACED_FUNC_FRAME_SIZE + stg %r1,__SF_BACKCHAIN(%r15) stg %r0,(STACK_PTREGS_PSW+8)(%r15) stmg %r2,%r14,(STACK_PTREGS_GPRS+2*8)(%r15) #ifdef CONFIG_HAVE_MARCH_Z196_FEATURES diff --git a/arch/s390/kernel/module.c b/arch/s390/kernel/module.c index 31889db609e9..ba8f19bb438b 100644 --- a/arch/s390/kernel/module.c +++ b/arch/s390/kernel/module.c @@ -472,11 +472,11 @@ int module_finalize(const Elf_Ehdr *hdr, apply_alternatives(aseg, aseg + s->sh_size); if (IS_ENABLED(CONFIG_EXPOLINE) && - (!strncmp(".s390_indirect", secname, 14))) + (str_has_prefix(secname, ".s390_indirect"))) nospec_revert(aseg, aseg + s->sh_size); if (IS_ENABLED(CONFIG_EXPOLINE) && - (!strncmp(".s390_return", secname, 12))) + (str_has_prefix(secname, ".s390_return"))) nospec_revert(aseg, aseg + s->sh_size); } diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c index 48d48b6187c0..0eb1d1cc53a8 100644 --- a/arch/s390/kernel/perf_cpum_cf.c +++ b/arch/s390/kernel/perf_cpum_cf.c @@ -199,7 +199,7 @@ static const int cpumf_generic_events_user[] = { [PERF_COUNT_HW_BUS_CYCLES] = -1, }; -static int __hw_perf_event_init(struct perf_event *event) +static int __hw_perf_event_init(struct perf_event *event, unsigned int type) { struct perf_event_attr *attr = &event->attr; struct hw_perf_event *hwc = &event->hw; @@ -207,7 +207,7 @@ static int __hw_perf_event_init(struct perf_event *event) int err = 0; u64 ev; - switch (attr->type) { + switch (type) { case PERF_TYPE_RAW: /* Raw events are used to access counters directly, * hence do not permit excludes */ @@ -294,17 +294,16 @@ static int __hw_perf_event_init(struct perf_event *event) static int cpumf_pmu_event_init(struct perf_event *event) { + unsigned int type = event->attr.type; int err; - switch (event->attr.type) { - case PERF_TYPE_HARDWARE: - case PERF_TYPE_HW_CACHE: - case PERF_TYPE_RAW: - err = __hw_perf_event_init(event); - break; - default: + if (type == PERF_TYPE_HARDWARE || type == PERF_TYPE_RAW) + err = __hw_perf_event_init(event, type); + else if (event->pmu->type == type) + /* Registered as unknown PMU */ + err = __hw_perf_event_init(event, PERF_TYPE_RAW); + else return -ENOENT; - } if (unlikely(err) && event->destroy) event->destroy(event); @@ -553,7 +552,7 @@ static int __init cpumf_pmu_init(void) return -ENODEV; cpumf_pmu.attr_groups = cpumf_cf_event_group(); - rc = perf_pmu_register(&cpumf_pmu, "cpum_cf", PERF_TYPE_RAW); + rc = perf_pmu_register(&cpumf_pmu, "cpum_cf", -1); if (rc) pr_err("Registering the cpum_cf PMU failed with rc=%i\n", rc); return rc; diff --git a/arch/s390/kernel/perf_cpum_cf_diag.c b/arch/s390/kernel/perf_cpum_cf_diag.c index 5f1fd1581330..e949ab832ed7 100644 --- a/arch/s390/kernel/perf_cpum_cf_diag.c +++ b/arch/s390/kernel/perf_cpum_cf_diag.c @@ -243,13 +243,13 @@ static int cf_diag_event_init(struct perf_event *event) int err = -ENOENT; debug_sprintf_event(cf_diag_dbg, 5, - "%s event %p cpu %d config %#llx " + "%s event %p cpu %d config %#llx type:%u " "sample_type %#llx cf_diag_events %d\n", __func__, - event, event->cpu, attr->config, attr->sample_type, - atomic_read(&cf_diag_events)); + event, event->cpu, attr->config, event->pmu->type, + attr->sample_type, atomic_read(&cf_diag_events)); if (event->attr.config != PERF_EVENT_CPUM_CF_DIAG || - event->attr.type != PERF_TYPE_RAW) + event->attr.type != event->pmu->type) goto out; /* Raw events are used to access counters directly, @@ -390,7 +390,7 @@ static size_t cf_diag_getctrset(struct cf_ctrset_entry *ctrdata, int ctrset, debug_sprintf_event(cf_diag_dbg, 6, "%s ctrset %d ctrset_size %zu cfvn %d csvn %d" - " need %zd rc:%d\n", + " need %zd rc %d\n", __func__, ctrset, ctrset_size, cpuhw->info.cfvn, cpuhw->info.csvn, need, rc); return need; @@ -567,7 +567,7 @@ static int cf_diag_add(struct perf_event *event, int flags) int err = 0; debug_sprintf_event(cf_diag_dbg, 5, - "%s event %p cpu %d flags %#x cpuhw:%p\n", + "%s event %p cpu %d flags %#x cpuhw %p\n", __func__, event, event->cpu, flags, cpuhw); if (cpuhw->flags & PMU_F_IN_USE) { @@ -693,7 +693,7 @@ static int __init cf_diag_init(void) } debug_register_view(cf_diag_dbg, &debug_sprintf_view); - rc = perf_pmu_register(&cf_diag, "cpum_cf_diag", PERF_TYPE_RAW); + rc = perf_pmu_register(&cf_diag, "cpum_cf_diag", -1); if (rc) { debug_unregister_view(cf_diag_dbg, &debug_sprintf_view); debug_unregister(cf_diag_dbg); diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c index 1266194afb02..b095b1c78987 100644 --- a/arch/s390/kernel/perf_cpum_sf.c +++ b/arch/s390/kernel/perf_cpum_sf.c @@ -156,8 +156,8 @@ static void free_sampling_buffer(struct sf_buffer *sfb) } } - debug_sprintf_event(sfdbg, 5, - "free_sampling_buffer: freed sdbt=%p\n", sfb->sdbt); + debug_sprintf_event(sfdbg, 5, "%s: freed sdbt %#lx\n", __func__, + (unsigned long)sfb->sdbt); memset(sfb, 0, sizeof(*sfb)); } @@ -193,7 +193,7 @@ static int realloc_sampling_buffer(struct sf_buffer *sfb, unsigned long num_sdb, gfp_t gfp_flags) { int i, rc; - unsigned long *new, *tail; + unsigned long *new, *tail, *tail_prev = NULL; if (!sfb->sdbt || !sfb->tail) return -EINVAL; @@ -212,10 +212,11 @@ static int realloc_sampling_buffer(struct sf_buffer *sfb, * the sampling buffer origin. */ if (sfb->sdbt != get_next_sdbt(tail)) { - debug_sprintf_event(sfdbg, 3, "realloc_sampling_buffer: " - "sampling buffer is not linked: origin=%p" - "tail=%p\n", - (void *) sfb->sdbt, (void *) tail); + debug_sprintf_event(sfdbg, 3, "%s: " + "sampling buffer is not linked: origin %#lx" + " tail %#lx\n", __func__, + (unsigned long)sfb->sdbt, + (unsigned long)tail); return -EINVAL; } @@ -232,6 +233,7 @@ static int realloc_sampling_buffer(struct sf_buffer *sfb, sfb->num_sdbt++; /* Link current page to tail of chain */ *tail = (unsigned long)(void *) new + 1; + tail_prev = tail; tail = new; } @@ -241,18 +243,30 @@ static int realloc_sampling_buffer(struct sf_buffer *sfb, * issue, a new realloc call (if required) might succeed. */ rc = alloc_sample_data_block(tail, gfp_flags); - if (rc) + if (rc) { + /* Undo last SDBT. An SDBT with no SDB at its first + * entry but with an SDBT entry instead can not be + * handled by the interrupt handler code. + * Avoid this situation. + */ + if (tail_prev) { + sfb->num_sdbt--; + free_page((unsigned long) new); + tail = tail_prev; + } break; + } sfb->num_sdb++; tail++; + tail_prev = new = NULL; /* Allocated at least one SBD */ } /* Link sampling buffer to its origin */ *tail = (unsigned long) sfb->sdbt + 1; sfb->tail = tail; - debug_sprintf_event(sfdbg, 4, "realloc_sampling_buffer: new buffer" - " settings: sdbt=%lu sdb=%lu\n", + debug_sprintf_event(sfdbg, 4, "%s: new buffer" + " settings: sdbt %lu sdb %lu\n", __func__, sfb->num_sdbt, sfb->num_sdb); return rc; } @@ -292,12 +306,13 @@ static int alloc_sampling_buffer(struct sf_buffer *sfb, unsigned long num_sdb) rc = realloc_sampling_buffer(sfb, num_sdb, GFP_KERNEL); if (rc) { free_sampling_buffer(sfb); - debug_sprintf_event(sfdbg, 4, "alloc_sampling_buffer: " - "realloc_sampling_buffer failed with rc=%i\n", rc); + debug_sprintf_event(sfdbg, 4, "%s: " + "realloc_sampling_buffer failed with rc %i\n", + __func__, rc); } else debug_sprintf_event(sfdbg, 4, - "alloc_sampling_buffer: tear=%p dear=%p\n", - sfb->sdbt, (void *) *sfb->sdbt); + "%s: tear %#lx dear %#lx\n", __func__, + (unsigned long)sfb->sdbt, (unsigned long)*sfb->sdbt); return rc; } @@ -404,8 +419,8 @@ static int allocate_buffers(struct cpu_hw_sf *cpuhw, struct hw_perf_event *hwc) return 0; debug_sprintf_event(sfdbg, 3, - "allocate_buffers: rate=%lu f=%lu sdb=%lu/%lu" - " sample_size=%lu cpuhw=%p\n", + "%s: rate %lu f %lu sdb %lu/%lu" + " sample_size %lu cpuhw %p\n", __func__, SAMPL_RATE(hwc), freq, n_sdb, sfb_max_limit(hwc), sample_size, cpuhw); @@ -465,8 +480,8 @@ static void sfb_account_overflows(struct cpu_hw_sf *cpuhw, if (num) sfb_account_allocs(num, hwc); - debug_sprintf_event(sfdbg, 5, "sfb: overflow: overflow=%llu ratio=%lu" - " num=%lu\n", OVERFLOW_REG(hwc), ratio, num); + debug_sprintf_event(sfdbg, 5, "%s: overflow %llu ratio %lu num %lu\n", + __func__, OVERFLOW_REG(hwc), ratio, num); OVERFLOW_REG(hwc) = 0; } @@ -504,17 +519,16 @@ static void extend_sampling_buffer(struct sf_buffer *sfb, */ rc = realloc_sampling_buffer(sfb, num, GFP_ATOMIC); if (rc) - debug_sprintf_event(sfdbg, 5, "sfb: extend: realloc " - "failed with rc=%i\n", rc); + debug_sprintf_event(sfdbg, 5, "%s: realloc failed with rc %i\n", + __func__, rc); if (sfb_has_pending_allocs(sfb, hwc)) - debug_sprintf_event(sfdbg, 5, "sfb: extend: " - "req=%lu alloc=%lu remaining=%lu\n", - num, sfb->num_sdb - num_old, + debug_sprintf_event(sfdbg, 5, "%s: " + "req %lu alloc %lu remaining %lu\n", + __func__, num, sfb->num_sdb - num_old, sfb_pending_allocs(sfb, hwc)); } - /* Number of perf events counting hardware events */ static atomic_t num_events; /* Used to avoid races in calling reserve/release_cpumf_hardware */ @@ -539,20 +553,22 @@ static void setup_pmc_cpu(void *flags) err = sf_disable(); if (err) pr_err("Switching off the sampling facility failed " - "with rc=%i\n", err); + "with rc %i\n", err); debug_sprintf_event(sfdbg, 5, - "setup_pmc_cpu: initialized: cpuhw=%p\n", cpusf); + "%s: initialized: cpuhw %p\n", __func__, + cpusf); break; case PMC_RELEASE: cpusf->flags &= ~PMU_F_RESERVED; err = sf_disable(); if (err) { pr_err("Switching off the sampling facility failed " - "with rc=%i\n", err); + "with rc %i\n", err); } else deallocate_buffers(cpusf); debug_sprintf_event(sfdbg, 5, - "setup_pmc_cpu: released: cpuhw=%p\n", cpusf); + "%s: released: cpuhw %p\n", __func__, + cpusf); break; } if (err) @@ -599,13 +615,6 @@ static void hw_init_period(struct hw_perf_event *hwc, u64 period) local64_set(&hwc->period_left, hwc->sample_period); } -static void hw_reset_registers(struct hw_perf_event *hwc, - unsigned long *sdbt_origin) -{ - /* (Re)set to first sample-data-block-table */ - TEAR_REG(hwc) = (unsigned long) sdbt_origin; -} - static unsigned long hw_limit_rate(const struct hws_qsi_info_block *si, unsigned long rate) { @@ -674,13 +683,88 @@ out: rcu_read_unlock(); } +static unsigned long getrate(bool freq, unsigned long sample, + struct hws_qsi_info_block *si) +{ + unsigned long rate; + + if (freq) { + rate = freq_to_sample_rate(si, sample); + rate = hw_limit_rate(si, rate); + } else { + /* The min/max sampling rates specifies the valid range + * of sample periods. If the specified sample period is + * out of range, limit the period to the range boundary. + */ + rate = hw_limit_rate(si, sample); + + /* The perf core maintains a maximum sample rate that is + * configurable through the sysctl interface. Ensure the + * sampling rate does not exceed this value. This also helps + * to avoid throttling when pushing samples with + * perf_event_overflow(). + */ + if (sample_rate_to_freq(si, rate) > + sysctl_perf_event_sample_rate) { + debug_sprintf_event(sfdbg, 1, "%s: " + "Sampling rate exceeds maximum " + "perf sample rate\n", __func__); + rate = 0; + } + } + return rate; +} + +/* The sampling information (si) contains information about the + * min/max sampling intervals and the CPU speed. So calculate the + * correct sampling interval and avoid the whole period adjust + * feedback loop. + * + * Since the CPU Measurement sampling facility can not handle frequency + * calculate the sampling interval when frequency is specified using + * this formula: + * interval := cpu_speed * 1000000 / sample_freq + * + * Returns errno on bad input and zero on success with parameter interval + * set to the correct sampling rate. + * + * Note: This function turns off freq bit to avoid calling function + * perf_adjust_period(). This causes frequency adjustment in the common + * code part which causes tremendous variations in the counter values. + */ +static int __hw_perf_event_init_rate(struct perf_event *event, + struct hws_qsi_info_block *si) +{ + struct perf_event_attr *attr = &event->attr; + struct hw_perf_event *hwc = &event->hw; + unsigned long rate; + + if (attr->freq) { + if (!attr->sample_freq) + return -EINVAL; + rate = getrate(attr->freq, attr->sample_freq, si); + attr->freq = 0; /* Don't call perf_adjust_period() */ + SAMPL_FLAGS(hwc) |= PERF_CPUM_SF_FREQ_MODE; + } else { + rate = getrate(attr->freq, attr->sample_period, si); + if (!rate) + return -EINVAL; + } + attr->sample_period = rate; + SAMPL_RATE(hwc) = rate; + hw_init_period(hwc, SAMPL_RATE(hwc)); + debug_sprintf_event(sfdbg, 4, "%s: cpu %d period %#llx freq %d,%#lx\n", + __func__, event->cpu, event->attr.sample_period, + event->attr.freq, SAMPLE_FREQ_MODE(hwc)); + return 0; +} + static int __hw_perf_event_init(struct perf_event *event) { struct cpu_hw_sf *cpuhw; struct hws_qsi_info_block si; struct perf_event_attr *attr = &event->attr; struct hw_perf_event *hwc = &event->hw; - unsigned long rate; int cpu, err; /* Reserve CPU-measurement sampling facility */ @@ -728,6 +812,12 @@ static int __hw_perf_event_init(struct perf_event *event) goto out; } + if (si.ribm & CPU_MF_SF_RIBM_NOTAV) { + pr_warn("CPU Measurement Facility sampling is temporarily not available\n"); + err = -EBUSY; + goto out; + } + /* Always enable basic sampling */ SAMPL_FLAGS(hwc) = PERF_CPUM_SF_BASIC_MODE; @@ -746,43 +836,9 @@ static int __hw_perf_event_init(struct perf_event *event) if (attr->config1 & PERF_CPUM_SF_FULL_BLOCKS) SAMPL_FLAGS(hwc) |= PERF_CPUM_SF_FULL_BLOCKS; - /* The sampling information (si) contains information about the - * min/max sampling intervals and the CPU speed. So calculate the - * correct sampling interval and avoid the whole period adjust - * feedback loop. - */ - rate = 0; - if (attr->freq) { - if (!attr->sample_freq) { - err = -EINVAL; - goto out; - } - rate = freq_to_sample_rate(&si, attr->sample_freq); - rate = hw_limit_rate(&si, rate); - attr->freq = 0; - attr->sample_period = rate; - } else { - /* The min/max sampling rates specifies the valid range - * of sample periods. If the specified sample period is - * out of range, limit the period to the range boundary. - */ - rate = hw_limit_rate(&si, hwc->sample_period); - - /* The perf core maintains a maximum sample rate that is - * configurable through the sysctl interface. Ensure the - * sampling rate does not exceed this value. This also helps - * to avoid throttling when pushing samples with - * perf_event_overflow(). - */ - if (sample_rate_to_freq(&si, rate) > - sysctl_perf_event_sample_rate) { - err = -EINVAL; - debug_sprintf_event(sfdbg, 1, "Sampling rate exceeds maximum perf sample rate\n"); - goto out; - } - } - SAMPL_RATE(hwc) = rate; - hw_init_period(hwc, SAMPL_RATE(hwc)); + err = __hw_perf_event_init_rate(event, &si); + if (err) + goto out; /* Initialize sample data overflow accounting */ hwc->extra_reg.reg = REG_OVERFLOW; @@ -854,7 +910,7 @@ static int cpumsf_pmu_event_init(struct perf_event *event) /* Check online status of the CPU to which the event is pinned */ if (event->cpu >= 0 && !cpu_online(event->cpu)) - return -ENODEV; + return -ENODEV; /* Force reset of idle/hv excludes regardless of what the * user requested. @@ -902,9 +958,10 @@ static void cpumsf_pmu_enable(struct pmu *pmu) * buffer extents */ sfb_account_overflows(cpuhw, hwc); - if (sfb_has_pending_allocs(&cpuhw->sfb, hwc)) - extend_sampling_buffer(&cpuhw->sfb, hwc); + extend_sampling_buffer(&cpuhw->sfb, hwc); } + /* Rate may be adjusted with ioctl() */ + cpuhw->lsctl.interval = SAMPL_RATE(&cpuhw->event->hw); } /* (Re)enable the PMU and sampling facility */ @@ -914,7 +971,7 @@ static void cpumsf_pmu_enable(struct pmu *pmu) err = lsctl(&cpuhw->lsctl); if (err) { cpuhw->flags &= ~PMU_F_ENABLED; - pr_err("Loading sampling controls failed: op=%i err=%i\n", + pr_err("Loading sampling controls failed: op %i err %i\n", 1, err); return; } @@ -922,10 +979,11 @@ static void cpumsf_pmu_enable(struct pmu *pmu) /* Load current program parameter */ lpp(&S390_lowcore.lpp); - debug_sprintf_event(sfdbg, 6, "pmu_enable: es=%i cs=%i ed=%i cd=%i " - "tear=%p dear=%p\n", cpuhw->lsctl.es, cpuhw->lsctl.cs, - cpuhw->lsctl.ed, cpuhw->lsctl.cd, - (void *) cpuhw->lsctl.tear, (void *) cpuhw->lsctl.dear); + debug_sprintf_event(sfdbg, 6, "%s: es %i cs %i ed %i cd %i " + "interval %#lx tear %#lx dear %#lx\n", __func__, + cpuhw->lsctl.es, cpuhw->lsctl.cs, cpuhw->lsctl.ed, + cpuhw->lsctl.cd, cpuhw->lsctl.interval, + cpuhw->lsctl.tear, cpuhw->lsctl.dear); } static void cpumsf_pmu_disable(struct pmu *pmu) @@ -948,13 +1006,14 @@ static void cpumsf_pmu_disable(struct pmu *pmu) err = lsctl(&inactive); if (err) { - pr_err("Loading sampling controls failed: op=%i err=%i\n", + pr_err("Loading sampling controls failed: op %i err %i\n", 2, err); return; } /* Save state of TEAR and DEAR register contents */ - if (!qsi(&si)) { + err = qsi(&si); + if (!err) { /* TEAR/DEAR values are valid only if the sampling facility is * enabled. Note that cpumsf_pmu_disable() might be called even * for a disabled sampling facility because cpumsf_pmu_enable() @@ -965,8 +1024,8 @@ static void cpumsf_pmu_disable(struct pmu *pmu) cpuhw->lsctl.dear = si.dear; } } else - debug_sprintf_event(sfdbg, 3, "cpumsf_pmu_disable: " - "qsi() failed with err=%i\n", err); + debug_sprintf_event(sfdbg, 3, "%s: qsi() failed with err %i\n", + __func__, err); cpuhw->flags &= ~PMU_F_ENABLED; } @@ -1079,14 +1138,6 @@ static void perf_event_count_update(struct perf_event *event, u64 count) local64_add(count, &event->count); } -static void debug_sample_entry(struct hws_basic_entry *sample, - struct hws_trailer_entry *te) -{ - debug_sprintf_event(sfdbg, 4, "hw_collect_samples: Found unknown " - "sampling data entry: te->f=%i basic.def=%04x (%p)\n", - te->f, sample->def, sample); -} - /* hw_collect_samples() - Walk through a sample-data-block and collect samples * @event: The perf event * @sdbt: Sample-data-block table @@ -1140,7 +1191,11 @@ static void hw_collect_samples(struct perf_event *event, unsigned long *sdbt, /* Count discarded samples */ *overflow += 1; } else { - debug_sample_entry(sample, te); + debug_sprintf_event(sfdbg, 4, + "%s: Found unknown" + " sampling data entry: te->f %i" + " basic.def %#4x (%p)\n", __func__, + te->f, sample->def, sample); /* Sample slot is not yet written or other record. * * This condition can occur if the buffer was reused @@ -1215,9 +1270,9 @@ static void hw_perf_event_update(struct perf_event *event, int flush_all) sampl_overflow += te->overflow; /* Timestamps are valid for full sample-data-blocks only */ - debug_sprintf_event(sfdbg, 6, "hw_perf_event_update: sdbt=%p " - "overflow=%llu timestamp=0x%llx\n", - sdbt, te->overflow, + debug_sprintf_event(sfdbg, 6, "%s: sdbt %#lx " + "overflow %llu timestamp %#llx\n", + __func__, (unsigned long)sdbt, te->overflow, (te->f) ? trailer_timestamp(te) : 0ULL); /* Collect all samples from a single sample-data-block and @@ -1248,22 +1303,34 @@ static void hw_perf_event_update(struct perf_event *event, int flush_all) */ if (flush_all && done) break; - - /* If an event overflow happened, discard samples by - * processing any remaining sample-data-blocks. - */ - if (event_overflow) - flush_all = 1; } /* Account sample overflows in the event hardware structure */ if (sampl_overflow) OVERFLOW_REG(hwc) = DIV_ROUND_UP(OVERFLOW_REG(hwc) + sampl_overflow, 1 + num_sdb); + + /* Perf_event_overflow() and perf_event_account_interrupt() limit + * the interrupt rate to an upper limit. Roughly 1000 samples per + * task tick. + * Hitting this limit results in a large number + * of throttled REF_REPORT_THROTTLE entries and the samples + * are dropped. + * Slightly increase the interval to avoid hitting this limit. + */ + if (event_overflow) { + SAMPL_RATE(hwc) += DIV_ROUND_UP(SAMPL_RATE(hwc), 10); + debug_sprintf_event(sfdbg, 1, "%s: rate adjustment %ld\n", + __func__, + DIV_ROUND_UP(SAMPL_RATE(hwc), 10)); + } + if (sampl_overflow || event_overflow) - debug_sprintf_event(sfdbg, 4, "hw_perf_event_update: " - "overflow stats: sample=%llu event=%llu\n", - sampl_overflow, event_overflow); + debug_sprintf_event(sfdbg, 4, "%s: " + "overflows: sample %llu event %llu" + " total %llu num_sdb %llu\n", + __func__, sampl_overflow, event_overflow, + OVERFLOW_REG(hwc), num_sdb); } #define AUX_SDB_INDEX(aux, i) ((i) % aux->sfb.num_sdb) @@ -1316,7 +1383,8 @@ static void aux_output_end(struct perf_output_handle *handle) te = aux_sdb_trailer(aux, aux->alert_mark); te->flags &= ~SDB_TE_ALERT_REQ_MASK; - debug_sprintf_event(sfdbg, 6, "aux_output_end: collect %lx SDBs\n", i); + debug_sprintf_event(sfdbg, 6, "%s: SDBs %ld range %ld head %ld\n", + __func__, i, range_scan, aux->head); } /* @@ -1349,13 +1417,17 @@ static int aux_output_begin(struct perf_output_handle *handle, * SDBs between aux->head and aux->empty_mark are already ready * for new data. range_scan is num of SDBs not within them. */ + debug_sprintf_event(sfdbg, 6, + "%s: range %ld head %ld alert %ld empty %ld\n", + __func__, range, aux->head, aux->alert_mark, + aux->empty_mark); if (range > AUX_SDB_NUM_EMPTY(aux)) { range_scan = range - AUX_SDB_NUM_EMPTY(aux); idx = aux->empty_mark + 1; for (i = 0; i < range_scan; i++, idx++) { te = aux_sdb_trailer(aux, idx); - te->flags = te->flags & ~SDB_TE_BUFFER_FULL_MASK; - te->flags = te->flags & ~SDB_TE_ALERT_REQ_MASK; + te->flags &= ~(SDB_TE_BUFFER_FULL_MASK | + SDB_TE_ALERT_REQ_MASK); te->overflow = 0; } /* Save the position of empty SDBs */ @@ -1374,15 +1446,11 @@ static int aux_output_begin(struct perf_output_handle *handle, cpuhw->lsctl.tear = base + offset * sizeof(unsigned long); cpuhw->lsctl.dear = aux->sdb_index[head]; - debug_sprintf_event(sfdbg, 6, "aux_output_begin: " - "head->alert_mark->empty_mark (num_alert, range)" - "[%lx -> %lx -> %lx] (%lx, %lx) " - "tear index %lx, tear %lx dear %lx\n", + debug_sprintf_event(sfdbg, 6, "%s: head %ld alert %ld empty %ld " + "index %ld tear %#lx dear %#lx\n", __func__, aux->head, aux->alert_mark, aux->empty_mark, - AUX_SDB_NUM_ALERT(aux), range, head / CPUM_SF_SDB_PER_TABLE, - cpuhw->lsctl.tear, - cpuhw->lsctl.dear); + cpuhw->lsctl.tear, cpuhw->lsctl.dear); return 0; } @@ -1402,8 +1470,7 @@ static bool aux_set_alert(struct aux_buffer *aux, unsigned long alert_index, te = aux_sdb_trailer(aux, alert_index); do { orig_flags = te->flags; - orig_overflow = te->overflow; - *overflow = orig_overflow; + *overflow = orig_overflow = te->overflow; if (orig_flags & SDB_TE_BUFFER_FULL_MASK) { /* * SDB is already set by hardware. @@ -1445,9 +1512,12 @@ static bool aux_reset_buffer(struct aux_buffer *aux, unsigned long range, unsigned long long *overflow) { unsigned long long orig_overflow, orig_flags, new_flags; - unsigned long i, range_scan, idx; + unsigned long i, range_scan, idx, idx_old; struct hws_trailer_entry *te; + debug_sprintf_event(sfdbg, 6, "%s: range %ld head %ld alert %ld " + "empty %ld\n", __func__, range, aux->head, + aux->alert_mark, aux->empty_mark); if (range <= AUX_SDB_NUM_EMPTY(aux)) /* * No need to scan. All SDBs in range are marked as empty. @@ -1470,7 +1540,7 @@ static bool aux_reset_buffer(struct aux_buffer *aux, unsigned long range, * indicator fall into this range, set it. */ range_scan = range - AUX_SDB_NUM_EMPTY(aux); - idx = aux->empty_mark + 1; + idx_old = idx = aux->empty_mark + 1; for (i = 0; i < range_scan; i++, idx++) { te = aux_sdb_trailer(aux, idx); do { @@ -1490,6 +1560,9 @@ static bool aux_reset_buffer(struct aux_buffer *aux, unsigned long range, /* Update empty_mark to new position */ aux->empty_mark = aux->head + range - 1; + debug_sprintf_event(sfdbg, 6, "%s: range_scan %ld idx %ld..%ld " + "empty %ld\n", __func__, range_scan, idx_old, + idx - 1, aux->empty_mark); return true; } @@ -1503,7 +1576,6 @@ static void hw_collect_aux(struct cpu_hw_sf *cpuhw) unsigned long range = 0, size; unsigned long long overflow = 0; struct perf_output_handle *handle = &cpuhw->handle; - unsigned long num_sdb; aux = perf_get_aux(handle); if (WARN_ON_ONCE(!aux)) @@ -1511,8 +1583,9 @@ static void hw_collect_aux(struct cpu_hw_sf *cpuhw) /* Inform user space new data arrived */ size = AUX_SDB_NUM_ALERT(aux) << PAGE_SHIFT; + debug_sprintf_event(sfdbg, 6, "%s: #alert %ld\n", __func__, + size >> PAGE_SHIFT); perf_aux_output_end(handle, size); - num_sdb = aux->sfb.num_sdb; while (!done) { /* Get an output handle */ @@ -1520,8 +1593,10 @@ static void hw_collect_aux(struct cpu_hw_sf *cpuhw) if (handle->size == 0) { pr_err("The AUX buffer with %lu pages for the " "diagnostic-sampling mode is full\n", - num_sdb); - debug_sprintf_event(sfdbg, 1, "AUX buffer used up\n"); + aux->sfb.num_sdb); + debug_sprintf_event(sfdbg, 1, + "%s: AUX buffer used up\n", + __func__); break; } if (WARN_ON_ONCE(!aux)) @@ -1543,24 +1618,24 @@ static void hw_collect_aux(struct cpu_hw_sf *cpuhw) size = range << PAGE_SHIFT; perf_aux_output_end(&cpuhw->handle, size); pr_err("Sample data caused the AUX buffer with %lu " - "pages to overflow\n", num_sdb); - debug_sprintf_event(sfdbg, 1, "head %lx range %lx " - "overflow %llx\n", + "pages to overflow\n", aux->sfb.num_sdb); + debug_sprintf_event(sfdbg, 1, "%s: head %ld range %ld " + "overflow %lld\n", __func__, aux->head, range, overflow); } else { size = AUX_SDB_NUM_ALERT(aux) << PAGE_SHIFT; perf_aux_output_end(&cpuhw->handle, size); - debug_sprintf_event(sfdbg, 6, "head %lx alert %lx " + debug_sprintf_event(sfdbg, 6, "%s: head %ld alert %ld " "already full, try another\n", + __func__, aux->head, aux->alert_mark); } } if (done) - debug_sprintf_event(sfdbg, 6, "aux_reset_buffer: " - "[%lx -> %lx -> %lx] (%lx, %lx)\n", - aux->head, aux->alert_mark, aux->empty_mark, - AUX_SDB_NUM_ALERT(aux), range); + debug_sprintf_event(sfdbg, 6, "%s: head %ld alert %ld " + "empty %ld\n", __func__, aux->head, + aux->alert_mark, aux->empty_mark); } /* @@ -1583,8 +1658,7 @@ static void aux_buffer_free(void *data) kfree(aux->sdb_index); kfree(aux); - debug_sprintf_event(sfdbg, 4, "aux_buffer_free: free " - "%lu SDBTs\n", num_sdbt); + debug_sprintf_event(sfdbg, 4, "%s: SDBTs %lu\n", __func__, num_sdbt); } static void aux_sdb_init(unsigned long sdb) @@ -1636,13 +1710,13 @@ static void *aux_buffer_setup(struct perf_event *event, void **pages, } /* Allocate aux_buffer struct for the event */ - aux = kmalloc(sizeof(struct aux_buffer), GFP_KERNEL); + aux = kzalloc(sizeof(struct aux_buffer), GFP_KERNEL); if (!aux) goto no_aux; sfb = &aux->sfb; /* Allocate sdbt_index for fast reference */ - n_sdbt = (nr_pages + CPUM_SF_SDB_PER_TABLE - 1) / CPUM_SF_SDB_PER_TABLE; + n_sdbt = DIV_ROUND_UP(nr_pages, CPUM_SF_SDB_PER_TABLE); aux->sdbt_index = kmalloc_array(n_sdbt, sizeof(void *), GFP_KERNEL); if (!aux->sdbt_index) goto no_sdbt_index; @@ -1692,8 +1766,7 @@ static void *aux_buffer_setup(struct perf_event *event, void **pages, */ aux->empty_mark = sfb->num_sdb - 1; - debug_sprintf_event(sfdbg, 4, "aux_buffer_setup: setup %lu SDBTs" - " and %lu SDBs\n", + debug_sprintf_event(sfdbg, 4, "%s: SDBTs %lu SDBs %lu\n", __func__, sfb->num_sdbt, sfb->num_sdb); return aux; @@ -1716,6 +1789,44 @@ static void cpumsf_pmu_read(struct perf_event *event) /* Nothing to do ... updates are interrupt-driven */ } +/* Check if the new sampling period/freqeuncy is appropriate. + * + * Return non-zero on error and zero on passed checks. + */ +static int cpumsf_pmu_check_period(struct perf_event *event, u64 value) +{ + struct hws_qsi_info_block si; + unsigned long rate; + bool do_freq; + + memset(&si, 0, sizeof(si)); + if (event->cpu == -1) { + if (qsi(&si)) + return -ENODEV; + } else { + /* Event is pinned to a particular CPU, retrieve the per-CPU + * sampling structure for accessing the CPU-specific QSI. + */ + struct cpu_hw_sf *cpuhw = &per_cpu(cpu_hw_sf, event->cpu); + + si = cpuhw->qsi; + } + + do_freq = !!SAMPLE_FREQ_MODE(&event->hw); + rate = getrate(do_freq, value, &si); + if (!rate) + return -EINVAL; + + event->attr.sample_period = rate; + SAMPL_RATE(&event->hw) = rate; + hw_init_period(&event->hw, SAMPL_RATE(&event->hw)); + debug_sprintf_event(sfdbg, 4, "%s:" + " cpu %d value %#llx period %#llx freq %d\n", + __func__, event->cpu, value, + event->attr.sample_period, do_freq); + return 0; +} + /* Activate sampling control. * Next call of pmu_enable() starts sampling. */ @@ -1787,7 +1898,7 @@ static int cpumsf_pmu_add(struct perf_event *event, int flags) if (!SAMPL_DIAG_MODE(&event->hw)) { cpuhw->lsctl.tear = (unsigned long) cpuhw->sfb.sdbt; cpuhw->lsctl.dear = *(unsigned long *) cpuhw->sfb.sdbt; - hw_reset_registers(&event->hw, cpuhw->sfb.sdbt); + TEAR_REG(&event->hw) = (unsigned long) cpuhw->sfb.sdbt; } /* Ensure sampling functions are in the disabled state. If disabled, @@ -1879,10 +1990,12 @@ static struct attribute_group cpumsf_pmu_events_group = { .name = "events", .attrs = cpumsf_pmu_events_attr, }; + static struct attribute_group cpumsf_pmu_format_group = { .name = "format", .attrs = cpumsf_pmu_format_attr, }; + static const struct attribute_group *cpumsf_pmu_attr_groups[] = { &cpumsf_pmu_events_group, &cpumsf_pmu_format_group, @@ -1905,6 +2018,8 @@ static struct pmu cpumf_sampling = { .setup_aux = aux_buffer_setup, .free_aux = aux_buffer_free, + + .check_period = cpumsf_pmu_check_period, }; static void cpumf_measurement_alert(struct ext_code ext_code, @@ -1938,7 +2053,8 @@ static void cpumf_measurement_alert(struct ext_code ext_code, /* Report measurement alerts only for non-PRA codes */ if (alert != CPU_MF_INT_SF_PRA) - debug_sprintf_event(sfdbg, 6, "measurement alert: 0x%x\n", alert); + debug_sprintf_event(sfdbg, 6, "%s: alert %#x\n", __func__, + alert); /* Sampling authorization change request */ if (alert & CPU_MF_INT_SF_SACA) @@ -1959,6 +2075,7 @@ static void cpumf_measurement_alert(struct ext_code ext_code, sf_disable(); } } + static int cpusf_pmu_setup(unsigned int cpu, int flags) { /* Ignore the notification if no events are scheduled on the PMU. @@ -2015,7 +2132,7 @@ static int param_set_sfb_size(const char *val, const struct kernel_param *kp) sfb_set_limits(min, max); pr_info("The sampling buffer limits have changed to: " - "min=%lu max=%lu (diag=x%lu)\n", + "min %lu max %lu (diag %lu)\n", CPUM_SF_MIN_SDB, CPUM_SF_MAX_SDB, CPUM_SF_SDB_DIAG_FACTOR); return 0; } @@ -2033,7 +2150,7 @@ static const struct kernel_param_ops param_ops_sfb_size = { static void __init pr_cpumsf_err(unsigned int reason) { pr_err("Sampling facility support for perf is not available: " - "reason=%04x\n", reason); + "reason %#x\n", reason); } static int __init init_cpum_sampling_pmu(void) @@ -2096,5 +2213,6 @@ static int __init init_cpum_sampling_pmu(void) out: return err; } + arch_initcall(init_cpum_sampling_pmu); core_param(cpum_sfb_size, CPUM_SF_MAX_SDB, sfb_size, 0640); diff --git a/arch/s390/kernel/perf_event.c b/arch/s390/kernel/perf_event.c index fcb6c2e92b07..1e75cc983546 100644 --- a/arch/s390/kernel/perf_event.c +++ b/arch/s390/kernel/perf_event.c @@ -224,9 +224,13 @@ void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs) { struct unwind_state state; + unsigned long addr; - unwind_for_each_frame(&state, current, regs, 0) - perf_callchain_store(entry, state.ip); + unwind_for_each_frame(&state, current, regs, 0) { + addr = unwind_get_return_address(&state); + if (!addr || perf_callchain_store(entry, addr)) + return; + } } /* Perf definitions for PMU event attributes in sysfs */ diff --git a/arch/s390/kernel/pgm_check.S b/arch/s390/kernel/pgm_check.S index 59dee9d3bebf..eee3a482195a 100644 --- a/arch/s390/kernel/pgm_check.S +++ b/arch/s390/kernel/pgm_check.S @@ -81,7 +81,7 @@ PGM_CHECK_DEFAULT /* 3c */ PGM_CHECK_DEFAULT /* 3d */ PGM_CHECK_DEFAULT /* 3e */ PGM_CHECK_DEFAULT /* 3f */ -PGM_CHECK_DEFAULT /* 40 */ +PGM_CHECK(monitor_event_exception) /* 40 */ PGM_CHECK_DEFAULT /* 41 */ PGM_CHECK_DEFAULT /* 42 */ PGM_CHECK_DEFAULT /* 43 */ diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c index 63873aa6693f..6ccef5f29761 100644 --- a/arch/s390/kernel/process.c +++ b/arch/s390/kernel/process.c @@ -40,6 +40,7 @@ #include <asm/stacktrace.h> #include <asm/switch_to.h> #include <asm/runtime_instr.h> +#include <asm/unwind.h> #include "entry.h" asmlinkage void ret_from_fork(void) asm ("ret_from_fork"); @@ -178,26 +179,31 @@ EXPORT_SYMBOL(dump_fpu); unsigned long get_wchan(struct task_struct *p) { - struct stack_frame *sf, *low, *high; - unsigned long return_address; - int count; + struct unwind_state state; + unsigned long ip = 0; if (!p || p == current || p->state == TASK_RUNNING || !task_stack_page(p)) return 0; - low = task_stack_page(p); - high = (struct stack_frame *) task_pt_regs(p); - sf = (struct stack_frame *) p->thread.ksp; - if (sf <= low || sf > high) + + if (!try_get_task_stack(p)) return 0; - for (count = 0; count < 16; count++) { - sf = (struct stack_frame *) sf->back_chain; - if (sf <= low || sf > high) - return 0; - return_address = sf->gprs[8]; - if (!in_sched_functions(return_address)) - return return_address; + + unwind_for_each_frame(&state, p, NULL, 0) { + if (state.stack_info.type != STACK_TYPE_TASK) { + ip = 0; + break; + } + + ip = unwind_get_return_address(&state); + if (!ip) + break; + + if (!in_sched_functions(ip)) + break; } - return 0; + + put_task_stack(p); + return ip; } unsigned long arch_align_stack(unsigned long sp) diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c index ad71132374f0..58faa12542a1 100644 --- a/arch/s390/kernel/ptrace.c +++ b/arch/s390/kernel/ptrace.c @@ -856,7 +856,7 @@ asmlinkage long do_syscall_trace_enter(struct pt_regs *regs) } /* Do the secure computing check after ptrace. */ - if (secure_computing(NULL)) { + if (secure_computing()) { /* seccomp failures shouldn't expose any additional code. */ return -1; } diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index 253177900950..b2c2f75860e8 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -99,6 +99,7 @@ int __bootdata_preserved(prot_virt_guest); int __bootdata(noexec_disabled); int __bootdata(memory_end_set); unsigned long __bootdata(memory_end); +unsigned long __bootdata(vmalloc_size); unsigned long __bootdata(max_physmem_end); struct mem_detect_info __bootdata(mem_detect); @@ -110,6 +111,8 @@ unsigned long __bootdata_preserved(__etext_dma); unsigned long __bootdata_preserved(__sdma); unsigned long __bootdata_preserved(__edma); unsigned long __bootdata_preserved(__kaslr_offset); +unsigned int __bootdata_preserved(zlib_dfltcc_support); +EXPORT_SYMBOL(zlib_dfltcc_support); unsigned long VMALLOC_START; EXPORT_SYMBOL(VMALLOC_START); @@ -168,15 +171,15 @@ static void __init set_preferred_console(void) static int __init conmode_setup(char *str) { #if defined(CONFIG_SCLP_CONSOLE) || defined(CONFIG_SCLP_VT220_CONSOLE) - if (strncmp(str, "hwc", 4) == 0 || strncmp(str, "sclp", 5) == 0) + if (!strcmp(str, "hwc") || !strcmp(str, "sclp")) SET_CONSOLE_SCLP; #endif #if defined(CONFIG_TN3215_CONSOLE) - if (strncmp(str, "3215", 5) == 0) + if (!strcmp(str, "3215")) SET_CONSOLE_3215; #endif #if defined(CONFIG_TN3270_CONSOLE) - if (strncmp(str, "3270", 5) == 0) + if (!strcmp(str, "3270")) SET_CONSOLE_3270; #endif set_preferred_console(); @@ -211,7 +214,7 @@ static void __init conmode_default(void) #endif return; } - if (strncmp(ptr + 8, "3270", 4) == 0) { + if (str_has_prefix(ptr + 8, "3270")) { #if defined(CONFIG_TN3270_CONSOLE) SET_CONSOLE_3270; #elif defined(CONFIG_TN3215_CONSOLE) @@ -219,7 +222,7 @@ static void __init conmode_default(void) #elif defined(CONFIG_SCLP_CONSOLE) || defined(CONFIG_SCLP_VT220_CONSOLE) SET_CONSOLE_SCLP; #endif - } else if (strncmp(ptr + 8, "3215", 4) == 0) { + } else if (str_has_prefix(ptr + 8, "3215")) { #if defined(CONFIG_TN3215_CONSOLE) SET_CONSOLE_3215; #elif defined(CONFIG_TN3270_CONSOLE) @@ -240,8 +243,6 @@ static void __init conmode_default(void) SET_CONSOLE_SCLP; #endif } - if (IS_ENABLED(CONFIG_VT) && IS_ENABLED(CONFIG_DUMMY_CONSOLE)) - conswitchp = &dummy_con; } #ifdef CONFIG_CRASH_DUMP @@ -302,15 +303,6 @@ void machine_power_off(void) void (*pm_power_off)(void) = machine_power_off; EXPORT_SYMBOL_GPL(pm_power_off); -static int __init parse_vmalloc(char *arg) -{ - if (!arg) - return -EINVAL; - VMALLOC_END = (memparse(arg, &arg) + PAGE_SIZE - 1) & PAGE_MASK; - return 0; -} -early_param("vmalloc", parse_vmalloc); - void *restart_stack __section(.data); unsigned long stack_alloc(void) @@ -363,7 +355,6 @@ early_initcall(async_stack_realloc); void __init arch_call_rest_init(void) { - struct stack_frame *frame; unsigned long stack; stack = stack_alloc(); @@ -376,13 +367,7 @@ void __init arch_call_rest_init(void) set_task_stack_end_magic(current); stack += STACK_INIT_OFFSET; S390_lowcore.kernel_stack = stack; - frame = (struct stack_frame *) stack; - memset(frame, 0, sizeof(*frame)); - /* Branch to rest_init on the new stack, never returns */ - asm volatile( - " la 15,0(%[_frame])\n" - " jg rest_init\n" - : : [_frame] "a" (frame)); + CALL_ON_STACK_NORETURN(rest_init, stack); } static void __init setup_lowcore_dat_off(void) @@ -563,10 +548,9 @@ static void __init setup_resources(void) static void __init setup_memory_end(void) { - unsigned long vmax, vmalloc_size, tmp; + unsigned long vmax, tmp; /* Choose kernel address space layout: 3 or 4 levels. */ - vmalloc_size = VMALLOC_END ?: (128UL << 30) - MODULES_LEN; if (IS_ENABLED(CONFIG_KASAN)) { vmax = IS_ENABLED(CONFIG_KASAN_S390_4_LEVEL_PAGING) ? _REGION1_SIZE @@ -777,14 +761,6 @@ static void __init free_mem_detect_info(void) memblock_free(start, size); } -static void __init memblock_physmem_add(phys_addr_t start, phys_addr_t size) -{ - memblock_dbg("memblock_physmem_add: [%#016llx-%#016llx]\n", - start, start + size - 1); - memblock_add_range(&memblock.memory, start, size, 0, 0); - memblock_add_range(&memblock.physmem, start, size, 0, 0); -} - static const char * __init get_mem_info_source(void) { switch (mem_detect.info_source) { @@ -809,8 +785,10 @@ static void __init memblock_add_mem_detect_info(void) get_mem_info_source(), mem_detect.info_source); /* keep memblock lists close to the kernel */ memblock_set_bottom_up(true); - for_each_mem_detect_block(i, &start, &end) + for_each_mem_detect_block(i, &start, &end) { + memblock_add(start, end - start); memblock_physmem_add(start, end - start); + } memblock_set_bottom_up(false); memblock_dump_all(); } @@ -990,6 +968,10 @@ static int __init setup_hwcaps(void) case 0x3907: strcpy(elf_platform, "z14"); break; + case 0x8561: + case 0x8562: + strcpy(elf_platform, "z15"); + break; } /* @@ -1064,7 +1046,7 @@ static void __init log_component_list(void) if (!early_ipl_comp_list_addr) return; - if (ipl_block.hdr.flags & IPL_PL_FLAG_IPLSR) + if (ipl_block.hdr.flags & IPL_PL_FLAG_SIPL) pr_info("Linux is running with Secure-IPL enabled\n"); else pr_info("Linux is running with Secure-IPL disabled\n"); diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index 44974654cbd0..a08bd2522dd9 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -262,10 +262,13 @@ static void pcpu_prepare_secondary(struct pcpu *pcpu, int cpu) lc->spinlock_index = 0; lc->percpu_offset = __per_cpu_offset[cpu]; lc->kernel_asce = S390_lowcore.kernel_asce; + lc->user_asce = S390_lowcore.kernel_asce; lc->machine_flags = S390_lowcore.machine_flags; lc->user_timer = lc->system_timer = lc->steal_timer = lc->avg_steal_timer = 0; __ctl_store(lc->cregs_save_area, 0, 15); + lc->cregs_save_area[1] = lc->kernel_asce; + lc->cregs_save_area[7] = lc->vdso_asce; save_access_regs((unsigned int *) lc->access_regs_save_area); memcpy(lc->stfle_fac_list, S390_lowcore.stfle_fac_list, sizeof(lc->stfle_fac_list)); @@ -410,14 +413,11 @@ EXPORT_SYMBOL(arch_vcpu_is_preempted); void smp_yield_cpu(int cpu) { - if (MACHINE_HAS_DIAG9C) { - diag_stat_inc_norecursion(DIAG_STAT_X09C); - asm volatile("diag %0,0,0x9c" - : : "d" (pcpu_devices[cpu].address)); - } else if (MACHINE_HAS_DIAG44 && !smp_cpu_mtid) { - diag_stat_inc_norecursion(DIAG_STAT_X044); - asm volatile("diag 0,0,0x44"); - } + if (!MACHINE_HAS_DIAG9C) + return; + diag_stat_inc_norecursion(DIAG_STAT_X09C); + asm volatile("diag %0,0,0x9c" + : : "d" (pcpu_devices[cpu].address)); } /* @@ -724,39 +724,67 @@ static void __ref smp_get_core_info(struct sclp_core_info *info, int early) static int smp_add_present_cpu(int cpu); -static int __smp_rescan_cpus(struct sclp_core_info *info, int sysfs_add) +static int smp_add_core(struct sclp_core_entry *core, cpumask_t *avail, + bool configured, bool early) { struct pcpu *pcpu; - cpumask_t avail; - int cpu, nr, i, j; + int cpu, nr, i; u16 address; nr = 0; - cpumask_xor(&avail, cpu_possible_mask, cpu_present_mask); - cpu = cpumask_first(&avail); - for (i = 0; (i < info->combined) && (cpu < nr_cpu_ids); i++) { - if (sclp.has_core_type && info->core[i].type != boot_core_type) + if (sclp.has_core_type && core->type != boot_core_type) + return nr; + cpu = cpumask_first(avail); + address = core->core_id << smp_cpu_mt_shift; + for (i = 0; (i <= smp_cpu_mtid) && (cpu < nr_cpu_ids); i++) { + if (pcpu_find_address(cpu_present_mask, address + i)) continue; - address = info->core[i].core_id << smp_cpu_mt_shift; - for (j = 0; j <= smp_cpu_mtid; j++) { - if (pcpu_find_address(cpu_present_mask, address + j)) - continue; - pcpu = pcpu_devices + cpu; - pcpu->address = address + j; - pcpu->state = - (cpu >= info->configured*(smp_cpu_mtid + 1)) ? - CPU_STATE_STANDBY : CPU_STATE_CONFIGURED; - smp_cpu_set_polarization(cpu, POLARIZATION_UNKNOWN); - set_cpu_present(cpu, true); - if (sysfs_add && smp_add_present_cpu(cpu) != 0) - set_cpu_present(cpu, false); - else - nr++; - cpu = cpumask_next(cpu, &avail); - if (cpu >= nr_cpu_ids) + pcpu = pcpu_devices + cpu; + pcpu->address = address + i; + if (configured) + pcpu->state = CPU_STATE_CONFIGURED; + else + pcpu->state = CPU_STATE_STANDBY; + smp_cpu_set_polarization(cpu, POLARIZATION_UNKNOWN); + set_cpu_present(cpu, true); + if (!early && smp_add_present_cpu(cpu) != 0) + set_cpu_present(cpu, false); + else + nr++; + cpumask_clear_cpu(cpu, avail); + cpu = cpumask_next(cpu, avail); + } + return nr; +} + +static int __smp_rescan_cpus(struct sclp_core_info *info, bool early) +{ + struct sclp_core_entry *core; + cpumask_t avail; + bool configured; + u16 core_id; + int nr, i; + + nr = 0; + cpumask_xor(&avail, cpu_possible_mask, cpu_present_mask); + /* + * Add IPL core first (which got logical CPU number 0) to make sure + * that all SMT threads get subsequent logical CPU numbers. + */ + if (early) { + core_id = pcpu_devices[0].address >> smp_cpu_mt_shift; + for (i = 0; i < info->configured; i++) { + core = &info->core[i]; + if (core->core_id == core_id) { + nr += smp_add_core(core, &avail, true, early); break; + } } } + for (i = 0; i < info->combined; i++) { + configured = i < info->configured; + nr += smp_add_core(&info->core[i], &avail, configured, early); + } return nr; } @@ -805,7 +833,7 @@ void __init smp_detect_cpus(void) /* Add CPUs present at boot */ get_online_cpus(); - __smp_rescan_cpus(info, 0); + __smp_rescan_cpus(info, true); put_online_cpus(); memblock_free_early((unsigned long)info, sizeof(*info)); } @@ -816,6 +844,8 @@ static void smp_init_secondary(void) S390_lowcore.last_update_clock = get_tod_clock(); restore_access_regs(S390_lowcore.access_regs_save_area); + set_cpu_flag(CIF_ASCE_PRIMARY); + set_cpu_flag(CIF_ASCE_SECONDARY); cpu_init(); preempt_disable(); init_cpu_timer(); @@ -843,7 +873,7 @@ static void __no_sanitize_address smp_start_secondary(void *cpuvoid) S390_lowcore.restart_source = -1UL; __ctl_load(S390_lowcore.cregs_save_area, 0, 15); __load_psw_mask(PSW_KERNEL_BITS | PSW_MASK_DAT); - CALL_ON_STACK(smp_init_secondary, S390_lowcore.kernel_stack, 0); + CALL_ON_STACK_NORETURN(smp_init_secondary, S390_lowcore.kernel_stack); } /* Upping and downing of CPUs */ @@ -1148,7 +1178,7 @@ int __ref smp_rescan_cpus(void) smp_get_core_info(info, 0); get_online_cpus(); mutex_lock(&smp_cpu_state_mutex); - nr = __smp_rescan_cpus(info, 1); + nr = __smp_rescan_cpus(info, false); mutex_unlock(&smp_cpu_state_mutex); put_online_cpus(); kfree(info); diff --git a/arch/s390/kernel/stacktrace.c b/arch/s390/kernel/stacktrace.c index f6a620f854e1..fc5419ac64c8 100644 --- a/arch/s390/kernel/stacktrace.c +++ b/arch/s390/kernel/stacktrace.c @@ -6,57 +6,62 @@ * Author(s): Heiko Carstens <heiko.carstens@de.ibm.com> */ -#include <linux/sched.h> -#include <linux/sched/debug.h> #include <linux/stacktrace.h> -#include <linux/kallsyms.h> -#include <linux/export.h> #include <asm/stacktrace.h> #include <asm/unwind.h> +#include <asm/kprobes.h> -void save_stack_trace(struct stack_trace *trace) +void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie, + struct task_struct *task, struct pt_regs *regs) { struct unwind_state state; + unsigned long addr; - unwind_for_each_frame(&state, current, NULL, 0) { - if (trace->nr_entries >= trace->max_entries) + unwind_for_each_frame(&state, task, regs, 0) { + addr = unwind_get_return_address(&state); + if (!addr || !consume_entry(cookie, addr, false)) break; - if (trace->skip > 0) - trace->skip--; - else - trace->entries[trace->nr_entries++] = state.ip; } } -EXPORT_SYMBOL_GPL(save_stack_trace); -void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) +/* + * This function returns an error if it detects any unreliable features of the + * stack. Otherwise it guarantees that the stack trace is reliable. + * + * If the task is not 'current', the caller *must* ensure the task is inactive. + */ +int arch_stack_walk_reliable(stack_trace_consume_fn consume_entry, + void *cookie, struct task_struct *task) { struct unwind_state state; + unsigned long addr; - unwind_for_each_frame(&state, tsk, NULL, 0) { - if (trace->nr_entries >= trace->max_entries) - break; - if (in_sched_functions(state.ip)) - continue; - if (trace->skip > 0) - trace->skip--; - else - trace->entries[trace->nr_entries++] = state.ip; - } -} -EXPORT_SYMBOL_GPL(save_stack_trace_tsk); + unwind_for_each_frame(&state, task, NULL, 0) { + if (state.stack_info.type != STACK_TYPE_TASK) + return -EINVAL; -void save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace) -{ - struct unwind_state state; + if (state.regs) + return -EINVAL; - unwind_for_each_frame(&state, current, regs, 0) { - if (trace->nr_entries >= trace->max_entries) - break; - if (trace->skip > 0) - trace->skip--; - else - trace->entries[trace->nr_entries++] = state.ip; + addr = unwind_get_return_address(&state); + if (!addr) + return -EINVAL; + +#ifdef CONFIG_KPROBES + /* + * Mark stacktraces with kretprobed functions on them + * as unreliable. + */ + if (state.ip == (unsigned long)kretprobe_trampoline) + return -EINVAL; +#endif + + if (!consume_entry(cookie, addr, false)) + return -EINVAL; } + + /* Check for stack corruption */ + if (unwind_error(&state)) + return -EINVAL; + return 0; } -EXPORT_SYMBOL_GPL(save_stack_trace_regs); diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl index 3054e9c035a3..bd7bd3581a0f 100644 --- a/arch/s390/kernel/syscalls/syscall.tbl +++ b/arch/s390/kernel/syscalls/syscall.tbl @@ -438,3 +438,5 @@ 433 common fspick sys_fspick sys_fspick 434 common pidfd_open sys_pidfd_open sys_pidfd_open 435 common clone3 sys_clone3 sys_clone3 +437 common openat2 sys_openat2 sys_openat2 +438 common pidfd_getfd sys_pidfd_getfd sys_pidfd_getfd diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c index e8766beee5ad..f9d070d016e3 100644 --- a/arch/s390/kernel/time.c +++ b/arch/s390/kernel/time.c @@ -110,15 +110,6 @@ unsigned long long notrace sched_clock(void) } NOKPROBE_SYMBOL(sched_clock); -/* - * Monotonic_clock - returns # of nanoseconds passed since time_init() - */ -unsigned long long monotonic_clock(void) -{ - return sched_clock(); -} -EXPORT_SYMBOL(monotonic_clock); - static void ext_to_timespec64(unsigned char *clk, struct timespec64 *xt) { unsigned long long high, low, rem, sec, nsec; diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c index 2db6fb405a9a..3627953007ed 100644 --- a/arch/s390/kernel/topology.c +++ b/arch/s390/kernel/topology.c @@ -311,7 +311,8 @@ int arch_update_cpu_topology(void) on_each_cpu(__arch_update_dedicated_flag, NULL, 0); for_each_online_cpu(cpu) { dev = get_cpu_device(cpu); - kobject_uevent(&dev->kobj, KOBJ_CHANGE); + if (dev) + kobject_uevent(&dev->kobj, KOBJ_CHANGE); } return rc; } diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c index 164c0282b41a..dc75588d7894 100644 --- a/arch/s390/kernel/traps.c +++ b/arch/s390/kernel/traps.c @@ -53,11 +53,6 @@ void do_report_trap(struct pt_regs *regs, int si_signo, int si_code, char *str) if (fixup) regs->psw.addr = extable_fixup(fixup); else { - enum bug_trap_type btt; - - btt = report_bug(regs->psw.addr, regs); - if (btt == BUG_TRAP_TYPE_WARN) - return; die(regs, str); } } @@ -245,6 +240,27 @@ void space_switch_exception(struct pt_regs *regs) do_trap(regs, SIGILL, ILL_PRVOPC, "space switch event"); } +void monitor_event_exception(struct pt_regs *regs) +{ + const struct exception_table_entry *fixup; + + if (user_mode(regs)) + return; + + switch (report_bug(regs->psw.addr - (regs->int_code >> 16), regs)) { + case BUG_TRAP_TYPE_NONE: + fixup = s390_search_extables(regs->psw.addr); + if (fixup) + regs->psw.addr = extable_fixup(fixup); + break; + case BUG_TRAP_TYPE_WARN: + break; + case BUG_TRAP_TYPE_BUG: + die(regs, "monitor event"); + break; + } +} + void kernel_stack_overflow(struct pt_regs *regs) { bust_spinlocks(1); @@ -255,8 +271,23 @@ void kernel_stack_overflow(struct pt_regs *regs) } NOKPROBE_SYMBOL(kernel_stack_overflow); +static void test_monitor_call(void) +{ + int val = 1; + + asm volatile( + " mc 0,0\n" + "0: xgr %0,%0\n" + "1:\n" + EX_TABLE(0b,1b) + : "+d" (val)); + if (!val) + panic("Monitor call doesn't work!\n"); +} + void __init trap_init(void) { sort_extable(__start_dma_ex_table, __stop_dma_ex_table); local_mcck_enable(); + test_monitor_call(); } diff --git a/arch/s390/kernel/unwind_bc.c b/arch/s390/kernel/unwind_bc.c index 8fc9daae47a2..707fd99f6734 100644 --- a/arch/s390/kernel/unwind_bc.c +++ b/arch/s390/kernel/unwind_bc.c @@ -36,6 +36,19 @@ static bool update_stack_info(struct unwind_state *state, unsigned long sp) return true; } +static inline bool is_final_pt_regs(struct unwind_state *state, + struct pt_regs *regs) +{ + /* user mode or kernel thread pt_regs at the bottom of task stack */ + if (task_pt_regs(state->task) == regs) + return true; + + /* user mode pt_regs at the bottom of irq stack */ + return state->stack_info.type == STACK_TYPE_IRQ && + state->stack_info.end - sizeof(struct pt_regs) == (unsigned long)regs && + READ_ONCE_NOCHECK(regs->psw.mask) & PSW_MASK_PSTATE; +} + bool unwind_next_frame(struct unwind_state *state) { struct stack_info *info = &state->stack_info; @@ -46,15 +59,16 @@ bool unwind_next_frame(struct unwind_state *state) regs = state->regs; if (unlikely(regs)) { - sp = READ_ONCE_NOCHECK(regs->gprs[15]); - if (unlikely(outside_of_stack(state, sp))) { - if (!update_stack_info(state, sp)) - goto out_err; - } + sp = state->sp; sf = (struct stack_frame *) sp; ip = READ_ONCE_NOCHECK(sf->gprs[8]); reliable = false; regs = NULL; + if (!__kernel_text_address(ip)) { + /* skip bogus %r14 */ + state->regs = NULL; + return unwind_next_frame(state); + } } else { sf = (struct stack_frame *) state->sp; sp = READ_ONCE_NOCHECK(sf->back_chain); @@ -71,21 +85,25 @@ bool unwind_next_frame(struct unwind_state *state) /* No back-chain, look for a pt_regs structure */ sp = state->sp + STACK_FRAME_OVERHEAD; if (!on_stack(info, sp, sizeof(struct pt_regs))) - goto out_stop; + goto out_err; regs = (struct pt_regs *) sp; - if (READ_ONCE_NOCHECK(regs->psw.mask) & PSW_MASK_PSTATE) + if (is_final_pt_regs(state, regs)) goto out_stop; ip = READ_ONCE_NOCHECK(regs->psw.addr); + sp = READ_ONCE_NOCHECK(regs->gprs[15]); + if (unlikely(outside_of_stack(state, sp))) { + if (!update_stack_info(state, sp)) + goto out_err; + } reliable = true; } } -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - /* Decode any ftrace redirection */ - if (ip == (unsigned long) return_to_handler) - ip = ftrace_graph_ret_addr(state->task, &state->graph_idx, - ip, (void *) sp); -#endif + /* Sanity check: ABI requires SP to be aligned 8 bytes. */ + if (sp & 0x7) + goto out_err; + + ip = ftrace_graph_ret_addr(state->task, &state->graph_idx, ip, (void *) sp); /* Update unwind state */ state->sp = sp; @@ -103,13 +121,11 @@ out_stop: EXPORT_SYMBOL_GPL(unwind_next_frame); void __unwind_start(struct unwind_state *state, struct task_struct *task, - struct pt_regs *regs, unsigned long sp) + struct pt_regs *regs, unsigned long first_frame) { struct stack_info *info = &state->stack_info; - unsigned long *mask = &state->stack_mask; struct stack_frame *sf; - unsigned long ip; - bool reliable; + unsigned long ip, sp; memset(state, 0, sizeof(*state)); state->task = task; @@ -121,35 +137,46 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task, return; } + /* Get the instruction pointer from pt_regs or the stack frame */ + if (regs) { + ip = regs->psw.addr; + sp = regs->gprs[15]; + } else if (task == current) { + sp = current_frame_address(); + } else { + sp = task->thread.ksp; + } + /* Get current stack pointer and initialize stack info */ - if (get_stack_info(sp, task, info, mask) != 0 || - !on_stack(info, sp, sizeof(struct stack_frame))) { + if (!update_stack_info(state, sp)) { /* Something is wrong with the stack pointer */ info->type = STACK_TYPE_UNKNOWN; state->error = true; return; } - /* Get the instruction pointer from pt_regs or the stack frame */ - if (regs) { - ip = READ_ONCE_NOCHECK(regs->psw.addr); - reliable = true; - } else { - sf = (struct stack_frame *) sp; + if (!regs) { + /* Stack frame is within valid stack */ + sf = (struct stack_frame *)sp; ip = READ_ONCE_NOCHECK(sf->gprs[8]); - reliable = false; } -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - /* Decode any ftrace redirection */ - if (ip == (unsigned long) return_to_handler) - ip = ftrace_graph_ret_addr(state->task, &state->graph_idx, - ip, NULL); -#endif + ip = ftrace_graph_ret_addr(state->task, &state->graph_idx, ip, NULL); /* Update unwind state */ state->sp = sp; state->ip = ip; - state->reliable = reliable; + state->reliable = true; + + if (!first_frame) + return; + /* Skip through the call chain to the specified starting frame */ + while (!unwind_done(state)) { + if (on_stack(&state->stack_info, first_frame, sizeof(struct stack_frame))) { + if (state->sp >= first_frame) + break; + } + unwind_next_frame(state); + } } EXPORT_SYMBOL_GPL(__unwind_start); diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c index c6bc190f3c28..bcc9bdb39ba2 100644 --- a/arch/s390/kernel/vdso.c +++ b/arch/s390/kernel/vdso.c @@ -29,13 +29,6 @@ #include <asm/vdso.h> #include <asm/facility.h> -#ifdef CONFIG_COMPAT_VDSO -extern char vdso32_start, vdso32_end; -static void *vdso32_kbase = &vdso32_start; -static unsigned int vdso32_pages; -static struct page **vdso32_pagelist; -#endif - extern char vdso64_start, vdso64_end; static void *vdso64_kbase = &vdso64_start; static unsigned int vdso64_pages; @@ -55,12 +48,6 @@ static vm_fault_t vdso_fault(const struct vm_special_mapping *sm, vdso_pagelist = vdso64_pagelist; vdso_pages = vdso64_pages; -#ifdef CONFIG_COMPAT_VDSO - if (vma->vm_mm->context.compat_mm) { - vdso_pagelist = vdso32_pagelist; - vdso_pages = vdso32_pages; - } -#endif if (vmf->pgoff >= vdso_pages) return VM_FAULT_SIGBUS; @@ -76,10 +63,6 @@ static int vdso_mremap(const struct vm_special_mapping *sm, unsigned long vdso_pages; vdso_pages = vdso64_pages; -#ifdef CONFIG_COMPAT_VDSO - if (vma->vm_mm->context.compat_mm) - vdso_pages = vdso32_pages; -#endif if ((vdso_pages << PAGE_SHIFT) != vma->vm_end - vma->vm_start) return -EINVAL; @@ -97,21 +80,13 @@ static const struct vm_special_mapping vdso_mapping = { .mremap = vdso_mremap, }; -static int __init vdso_setup(char *s) +static int __init vdso_setup(char *str) { - unsigned long val; - int rc; + bool enabled; - rc = 0; - if (strncmp(s, "on", 3) == 0) - vdso_enabled = 1; - else if (strncmp(s, "off", 4) == 0) - vdso_enabled = 0; - else { - rc = kstrtoul(s, 0, &val); - vdso_enabled = rc ? 0 : !!val; - } - return !rc; + if (!kstrtobool(str, &enabled)) + vdso_enabled = enabled; + return 1; } __setup("vdso=", vdso_setup); @@ -217,12 +192,10 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) if (!vdso_enabled) return 0; + if (is_compat_task()) + return 0; + vdso_pages = vdso64_pages; -#ifdef CONFIG_COMPAT_VDSO - mm->context.compat_mm = is_compat_task(); - if (mm->context.compat_mm) - vdso_pages = vdso32_pages; -#endif /* * vDSO has a problem and was disabled, just don't "enable" it for * the process @@ -275,23 +248,6 @@ static int __init vdso_init(void) int i; vdso_init_data(vdso_data); -#ifdef CONFIG_COMPAT_VDSO - /* Calculate the size of the 32 bit vDSO */ - vdso32_pages = ((&vdso32_end - &vdso32_start - + PAGE_SIZE - 1) >> PAGE_SHIFT) + 1; - - /* Make sure pages are in the correct state */ - vdso32_pagelist = kcalloc(vdso32_pages + 1, sizeof(struct page *), - GFP_KERNEL); - BUG_ON(vdso32_pagelist == NULL); - for (i = 0; i < vdso32_pages - 1; i++) { - struct page *pg = virt_to_page(vdso32_kbase + i*PAGE_SIZE); - get_page(pg); - vdso32_pagelist[i] = pg; - } - vdso32_pagelist[vdso32_pages - 1] = virt_to_page(vdso_data); - vdso32_pagelist[vdso32_pages] = NULL; -#endif /* Calculate the size of the 64 bit vDSO */ vdso64_pages = ((&vdso64_end - &vdso64_start diff --git a/arch/s390/kernel/vdso32/.gitignore b/arch/s390/kernel/vdso32/.gitignore deleted file mode 100644 index e45fba9d0ced..000000000000 --- a/arch/s390/kernel/vdso32/.gitignore +++ /dev/null @@ -1 +0,0 @@ -vdso32.lds diff --git a/arch/s390/kernel/vdso32/Makefile b/arch/s390/kernel/vdso32/Makefile deleted file mode 100644 index aee9ffbccb54..000000000000 --- a/arch/s390/kernel/vdso32/Makefile +++ /dev/null @@ -1,66 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 -# List of files in the vdso, has to be asm only for now - -KCOV_INSTRUMENT := n - -obj-vdso32 = gettimeofday.o clock_getres.o clock_gettime.o note.o getcpu.o - -# Build rules - -targets := $(obj-vdso32) vdso32.so vdso32.so.dbg -obj-vdso32 := $(addprefix $(obj)/, $(obj-vdso32)) - -KBUILD_AFLAGS += -DBUILD_VDSO -KBUILD_CFLAGS += -DBUILD_VDSO - -KBUILD_AFLAGS_31 := $(filter-out -m64,$(KBUILD_AFLAGS)) -KBUILD_AFLAGS_31 += -m31 -s - -KBUILD_CFLAGS_31 := $(filter-out -m64,$(KBUILD_CFLAGS)) -KBUILD_CFLAGS_31 += -m31 -fPIC -shared -fno-common -fno-builtin -KBUILD_CFLAGS_31 += -nostdlib -Wl,-soname=linux-vdso32.so.1 \ - -Wl,--hash-style=both - -$(targets:%=$(obj)/%.dbg): KBUILD_CFLAGS = $(KBUILD_CFLAGS_31) -$(targets:%=$(obj)/%.dbg): KBUILD_AFLAGS = $(KBUILD_AFLAGS_31) - -obj-y += vdso32_wrapper.o -extra-y += vdso32.lds -CPPFLAGS_vdso32.lds += -P -C -U$(ARCH) - -# Disable gcov profiling, ubsan and kasan for VDSO code -GCOV_PROFILE := n -UBSAN_SANITIZE := n -KASAN_SANITIZE := n - -# Force dependency (incbin is bad) -$(obj)/vdso32_wrapper.o : $(obj)/vdso32.so - -# link rule for the .so file, .lds has to be first -$(obj)/vdso32.so.dbg: $(src)/vdso32.lds $(obj-vdso32) FORCE - $(call if_changed,vdso32ld) - -# strip rule for the .so file -$(obj)/%.so: OBJCOPYFLAGS := -S -$(obj)/%.so: $(obj)/%.so.dbg FORCE - $(call if_changed,objcopy) - -# assembly rules for the .S files -$(obj-vdso32): %.o: %.S FORCE - $(call if_changed_dep,vdso32as) - -# actual build commands -quiet_cmd_vdso32ld = VDSO32L $@ - cmd_vdso32ld = $(CC) $(c_flags) -Wl,-T $(filter %.lds %.o,$^) -o $@ -quiet_cmd_vdso32as = VDSO32A $@ - cmd_vdso32as = $(CC) $(a_flags) -c -o $@ $< - -# install commands for the unstripped file -quiet_cmd_vdso_install = INSTALL $@ - cmd_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/vdso/$@ - -vdso32.so: $(obj)/vdso32.so.dbg - @mkdir -p $(MODLIB)/vdso - $(call cmd,vdso_install) - -vdso_install: vdso32.so diff --git a/arch/s390/kernel/vdso32/clock_getres.S b/arch/s390/kernel/vdso32/clock_getres.S deleted file mode 100644 index eaf9cf1417f6..000000000000 --- a/arch/s390/kernel/vdso32/clock_getres.S +++ /dev/null @@ -1,44 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Userland implementation of clock_getres() for 32 bits processes in a - * s390 kernel for use in the vDSO - * - * Copyright IBM Corp. 2008 - * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com) - */ -#include <asm/vdso.h> -#include <asm/asm-offsets.h> -#include <asm/unistd.h> -#include <asm/dwarf.h> - - .text - .align 4 - .globl __kernel_clock_getres - .type __kernel_clock_getres,@function -__kernel_clock_getres: - CFI_STARTPROC - basr %r1,0 - la %r1,4f-.(%r1) - chi %r2,__CLOCK_REALTIME - je 0f - chi %r2,__CLOCK_MONOTONIC - je 0f - la %r1,5f-4f(%r1) - chi %r2,__CLOCK_REALTIME_COARSE - je 0f - chi %r2,__CLOCK_MONOTONIC_COARSE - jne 3f -0: ltr %r3,%r3 - jz 2f /* res == NULL */ -1: l %r0,0(%r1) - xc 0(4,%r3),0(%r3) /* set tp->tv_sec to zero */ - st %r0,4(%r3) /* store tp->tv_usec */ -2: lhi %r2,0 - br %r14 -3: lhi %r1,__NR_clock_getres /* fallback to svc */ - svc 0 - br %r14 - CFI_ENDPROC -4: .long __CLOCK_REALTIME_RES -5: .long __CLOCK_COARSE_RES - .size __kernel_clock_getres,.-__kernel_clock_getres diff --git a/arch/s390/kernel/vdso32/clock_gettime.S b/arch/s390/kernel/vdso32/clock_gettime.S deleted file mode 100644 index ada5c11a16e5..000000000000 --- a/arch/s390/kernel/vdso32/clock_gettime.S +++ /dev/null @@ -1,179 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Userland implementation of clock_gettime() for 32 bits processes in a - * s390 kernel for use in the vDSO - * - * Copyright IBM Corp. 2008 - * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com) - */ -#include <asm/vdso.h> -#include <asm/asm-offsets.h> -#include <asm/unistd.h> -#include <asm/dwarf.h> -#include <asm/ptrace.h> - - .text - .align 4 - .globl __kernel_clock_gettime - .type __kernel_clock_gettime,@function -__kernel_clock_gettime: - CFI_STARTPROC - ahi %r15,-16 - CFI_DEF_CFA_OFFSET STACK_FRAME_OVERHEAD+16 - CFI_VAL_OFFSET 15, -STACK_FRAME_OVERHEAD - basr %r5,0 -0: al %r5,21f-0b(%r5) /* get &_vdso_data */ - chi %r2,__CLOCK_REALTIME_COARSE - je 10f - chi %r2,__CLOCK_REALTIME - je 11f - chi %r2,__CLOCK_MONOTONIC_COARSE - je 9f - chi %r2,__CLOCK_MONOTONIC - jne 19f - - /* CLOCK_MONOTONIC */ -1: l %r4,__VDSO_UPD_COUNT+4(%r5) /* load update counter */ - tml %r4,0x0001 /* pending update ? loop */ - jnz 1b - stcke 0(%r15) /* Store TOD clock */ - lm %r0,%r1,1(%r15) - s %r0,__VDSO_XTIME_STAMP(%r5) /* TOD - cycle_last */ - sl %r1,__VDSO_XTIME_STAMP+4(%r5) - brc 3,2f - ahi %r0,-1 -2: ms %r0,__VDSO_TK_MULT(%r5) /* * tk->mult */ - lr %r2,%r0 - l %r0,__VDSO_TK_MULT(%r5) - ltr %r1,%r1 - mr %r0,%r0 - jnm 3f - a %r0,__VDSO_TK_MULT(%r5) -3: alr %r0,%r2 - al %r0,__VDSO_WTOM_NSEC(%r5) - al %r1,__VDSO_WTOM_NSEC+4(%r5) - brc 12,5f - ahi %r0,1 -5: l %r2,__VDSO_TK_SHIFT(%r5) /* Timekeeper shift */ - srdl %r0,0(%r2) /* >> tk->shift */ - l %r2,__VDSO_WTOM_SEC+4(%r5) - cl %r4,__VDSO_UPD_COUNT+4(%r5) /* check update counter */ - jne 1b - basr %r5,0 -6: ltr %r0,%r0 - jnz 7f - cl %r1,20f-6b(%r5) - jl 8f -7: ahi %r2,1 - sl %r1,20f-6b(%r5) - brc 3,6b - ahi %r0,-1 - j 6b -8: st %r2,0(%r3) /* store tp->tv_sec */ - st %r1,4(%r3) /* store tp->tv_nsec */ - lhi %r2,0 - ahi %r15,16 - CFI_DEF_CFA_OFFSET STACK_FRAME_OVERHEAD - CFI_RESTORE 15 - br %r14 - - /* CLOCK_MONOTONIC_COARSE */ - CFI_DEF_CFA_OFFSET STACK_FRAME_OVERHEAD+16 - CFI_VAL_OFFSET 15, -STACK_FRAME_OVERHEAD -9: l %r4,__VDSO_UPD_COUNT+4(%r5) /* load update counter */ - tml %r4,0x0001 /* pending update ? loop */ - jnz 9b - l %r2,__VDSO_WTOM_CRS_SEC+4(%r5) - l %r1,__VDSO_WTOM_CRS_NSEC+4(%r5) - cl %r4,__VDSO_UPD_COUNT+4(%r5) /* check update counter */ - jne 9b - j 8b - - /* CLOCK_REALTIME_COARSE */ -10: l %r4,__VDSO_UPD_COUNT+4(%r5) /* load update counter */ - tml %r4,0x0001 /* pending update ? loop */ - jnz 10b - l %r2,__VDSO_XTIME_CRS_SEC+4(%r5) - l %r1,__VDSO_XTIME_CRS_NSEC+4(%r5) - cl %r4,__VDSO_UPD_COUNT+4(%r5) /* check update counter */ - jne 10b - j 17f - - /* CLOCK_REALTIME */ -11: l %r4,__VDSO_UPD_COUNT+4(%r5) /* load update counter */ - tml %r4,0x0001 /* pending update ? loop */ - jnz 11b - stcke 0(%r15) /* Store TOD clock */ - lm %r0,%r1,__VDSO_TS_END(%r5) /* TOD steering end time */ - s %r0,1(%r15) /* no - ts_steering_end */ - sl %r1,5(%r15) - brc 3,22f - ahi %r0,-1 -22: ltr %r0,%r0 /* past end of steering? */ - jm 24f - srdl %r0,15 /* 1 per 2^16 */ - tm __VDSO_TS_DIR+3(%r5),0x01 /* steering direction? */ - jz 23f - lcr %r0,%r0 /* negative TOD offset */ - lcr %r1,%r1 - je 23f - ahi %r0,-1 -23: a %r0,1(%r15) /* add TOD timestamp */ - al %r1,5(%r15) - brc 12,25f - ahi %r0,1 - j 25f -24: lm %r0,%r1,1(%r15) /* load TOD timestamp */ -25: s %r0,__VDSO_XTIME_STAMP(%r5) /* TOD - cycle_last */ - sl %r1,__VDSO_XTIME_STAMP+4(%r5) - brc 3,12f - ahi %r0,-1 -12: ms %r0,__VDSO_TK_MULT(%r5) /* * tk->mult */ - lr %r2,%r0 - l %r0,__VDSO_TK_MULT(%r5) - ltr %r1,%r1 - mr %r0,%r0 - jnm 13f - a %r0,__VDSO_TK_MULT(%r5) -13: alr %r0,%r2 - al %r0,__VDSO_XTIME_NSEC(%r5) /* + tk->xtime_nsec */ - al %r1,__VDSO_XTIME_NSEC+4(%r5) - brc 12,14f - ahi %r0,1 -14: l %r2,__VDSO_TK_SHIFT(%r5) /* Timekeeper shift */ - srdl %r0,0(%r2) /* >> tk->shift */ - l %r2,__VDSO_XTIME_SEC+4(%r5) - cl %r4,__VDSO_UPD_COUNT+4(%r5) /* check update counter */ - jne 11b - basr %r5,0 -15: ltr %r0,%r0 - jnz 16f - cl %r1,20f-15b(%r5) - jl 17f -16: ahi %r2,1 - sl %r1,20f-15b(%r5) - brc 3,15b - ahi %r0,-1 - j 15b -17: st %r2,0(%r3) /* store tp->tv_sec */ - st %r1,4(%r3) /* store tp->tv_nsec */ - lhi %r2,0 - ahi %r15,16 - CFI_DEF_CFA_OFFSET STACK_FRAME_OVERHEAD - CFI_RESTORE 15 - br %r14 - - /* Fallback to system call */ - CFI_DEF_CFA_OFFSET STACK_FRAME_OVERHEAD+16 - CFI_VAL_OFFSET 15, -STACK_FRAME_OVERHEAD -19: lhi %r1,__NR_clock_gettime - svc 0 - ahi %r15,16 - CFI_DEF_CFA_OFFSET STACK_FRAME_OVERHEAD - CFI_RESTORE 15 - br %r14 - CFI_ENDPROC - -20: .long 1000000000 -21: .long _vdso_data - 0b - .size __kernel_clock_gettime,.-__kernel_clock_gettime diff --git a/arch/s390/kernel/vdso32/getcpu.S b/arch/s390/kernel/vdso32/getcpu.S deleted file mode 100644 index 25515f3fbcea..000000000000 --- a/arch/s390/kernel/vdso32/getcpu.S +++ /dev/null @@ -1,33 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Userland implementation of getcpu() for 32 bits processes in a - * s390 kernel for use in the vDSO - * - * Copyright IBM Corp. 2016 - * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com> - */ -#include <asm/vdso.h> -#include <asm/asm-offsets.h> -#include <asm/dwarf.h> - - .text - .align 4 - .globl __kernel_getcpu - .type __kernel_getcpu,@function -__kernel_getcpu: - CFI_STARTPROC - la %r4,0 - sacf 256 - l %r5,__VDSO_CPU_NR(%r4) - l %r4,__VDSO_NODE_ID(%r4) - sacf 0 - ltr %r2,%r2 - jz 2f - st %r5,0(%r2) -2: ltr %r3,%r3 - jz 3f - st %r4,0(%r3) -3: lhi %r2,0 - br %r14 - CFI_ENDPROC - .size __kernel_getcpu,.-__kernel_getcpu diff --git a/arch/s390/kernel/vdso32/gettimeofday.S b/arch/s390/kernel/vdso32/gettimeofday.S deleted file mode 100644 index b23063fbc892..000000000000 --- a/arch/s390/kernel/vdso32/gettimeofday.S +++ /dev/null @@ -1,103 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Userland implementation of gettimeofday() for 32 bits processes in a - * s390 kernel for use in the vDSO - * - * Copyright IBM Corp. 2008 - * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com) - */ -#include <asm/vdso.h> -#include <asm/asm-offsets.h> -#include <asm/unistd.h> -#include <asm/dwarf.h> -#include <asm/ptrace.h> - - .text - .align 4 - .globl __kernel_gettimeofday - .type __kernel_gettimeofday,@function -__kernel_gettimeofday: - CFI_STARTPROC - ahi %r15,-16 - CFI_ADJUST_CFA_OFFSET 16 - CFI_VAL_OFFSET 15, -STACK_FRAME_OVERHEAD - basr %r5,0 -0: al %r5,13f-0b(%r5) /* get &_vdso_data */ -1: ltr %r3,%r3 /* check if tz is NULL */ - je 2f - mvc 0(8,%r3),__VDSO_TIMEZONE(%r5) -2: ltr %r2,%r2 /* check if tv is NULL */ - je 10f - l %r4,__VDSO_UPD_COUNT+4(%r5) /* load update counter */ - tml %r4,0x0001 /* pending update ? loop */ - jnz 1b - stcke 0(%r15) /* Store TOD clock */ - lm %r0,%r1,__VDSO_TS_END(%r5) /* TOD steering end time */ - s %r0,1(%r15) - sl %r1,5(%r15) - brc 3,14f - ahi %r0,-1 -14: ltr %r0,%r0 /* past end of steering? */ - jm 16f - srdl %r0,15 /* 1 per 2^16 */ - tm __VDSO_TS_DIR+3(%r5),0x01 /* steering direction? */ - jz 15f - lcr %r0,%r0 /* negative TOD offset */ - lcr %r1,%r1 - je 15f - ahi %r0,-1 -15: a %r0,1(%r15) /* add TOD timestamp */ - al %r1,5(%r15) - brc 12,17f - ahi %r0,1 - j 17f -16: lm %r0,%r1,1(%r15) /* load TOD timestamp */ -17: s %r0,__VDSO_XTIME_STAMP(%r5) /* TOD - cycle_last */ - sl %r1,__VDSO_XTIME_STAMP+4(%r5) - brc 3,3f - ahi %r0,-1 -3: ms %r0,__VDSO_TK_MULT(%r5) /* * tk->mult */ - st %r0,0(%r15) - l %r0,__VDSO_TK_MULT(%r5) - ltr %r1,%r1 - mr %r0,%r0 - jnm 4f - a %r0,__VDSO_TK_MULT(%r5) -4: al %r0,0(%r15) - al %r0,__VDSO_XTIME_NSEC(%r5) /* + xtime */ - al %r1,__VDSO_XTIME_NSEC+4(%r5) - brc 12,5f - ahi %r0,1 -5: mvc 0(4,%r15),__VDSO_XTIME_SEC+4(%r5) - cl %r4,__VDSO_UPD_COUNT+4(%r5) /* check update counter */ - jne 1b - l %r4,__VDSO_TK_SHIFT(%r5) /* Timekeeper shift */ - srdl %r0,0(%r4) /* >> tk->shift */ - l %r4,0(%r15) /* get tv_sec from stack */ - basr %r5,0 -6: ltr %r0,%r0 - jnz 7f - cl %r1,11f-6b(%r5) - jl 8f -7: ahi %r4,1 - sl %r1,11f-6b(%r5) - brc 3,6b - ahi %r0,-1 - j 6b -8: st %r4,0(%r2) /* store tv->tv_sec */ - ltr %r1,%r1 - m %r0,12f-6b(%r5) - jnm 9f - al %r0,12f-6b(%r5) -9: srl %r0,6 - st %r0,4(%r2) /* store tv->tv_usec */ -10: slr %r2,%r2 - ahi %r15,16 - CFI_ADJUST_CFA_OFFSET -16 - CFI_RESTORE 15 - br %r14 - CFI_ENDPROC -11: .long 1000000000 -12: .long 274877907 -13: .long _vdso_data - 0b - .size __kernel_gettimeofday,.-__kernel_gettimeofday diff --git a/arch/s390/kernel/vdso32/note.S b/arch/s390/kernel/vdso32/note.S deleted file mode 100644 index db19d0680a0a..000000000000 --- a/arch/s390/kernel/vdso32/note.S +++ /dev/null @@ -1,13 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * This supplies .note.* sections to go into the PT_NOTE inside the vDSO text. - * Here we can supply some information useful to userland. - */ - -#include <linux/uts.h> -#include <linux/version.h> -#include <linux/elfnote.h> - -ELFNOTE_START(Linux, 0, "a") - .long LINUX_VERSION_CODE -ELFNOTE_END diff --git a/arch/s390/kernel/vdso32/vdso32.lds.S b/arch/s390/kernel/vdso32/vdso32.lds.S deleted file mode 100644 index 721c4954cb6e..000000000000 --- a/arch/s390/kernel/vdso32/vdso32.lds.S +++ /dev/null @@ -1,142 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * This is the infamous ld script for the 32 bits vdso - * library - */ - -#include <asm/page.h> -#include <asm/vdso.h> - -OUTPUT_FORMAT("elf32-s390", "elf32-s390", "elf32-s390") -OUTPUT_ARCH(s390:31-bit) -ENTRY(_start) - -SECTIONS -{ - . = VDSO32_LBASE + SIZEOF_HEADERS; - - .hash : { *(.hash) } :text - .gnu.hash : { *(.gnu.hash) } - .dynsym : { *(.dynsym) } - .dynstr : { *(.dynstr) } - .gnu.version : { *(.gnu.version) } - .gnu.version_d : { *(.gnu.version_d) } - .gnu.version_r : { *(.gnu.version_r) } - - .note : { *(.note.*) } :text :note - - . = ALIGN(16); - .text : { - *(.text .stub .text.* .gnu.linkonce.t.*) - } :text - PROVIDE(__etext = .); - PROVIDE(_etext = .); - PROVIDE(etext = .); - - /* - * Other stuff is appended to the text segment: - */ - .rodata : { *(.rodata .rodata.* .gnu.linkonce.r.*) } - .rodata1 : { *(.rodata1) } - - .dynamic : { *(.dynamic) } :text :dynamic - - .eh_frame_hdr : { *(.eh_frame_hdr) } :text :eh_frame_hdr - .eh_frame : { KEEP (*(.eh_frame)) } :text - .gcc_except_table : { *(.gcc_except_table .gcc_except_table.*) } - - .rela.dyn ALIGN(8) : { *(.rela.dyn) } - .got ALIGN(8) : { *(.got .toc) } - - _end = .; - PROVIDE(end = .); - - /* - * Stabs debugging sections are here too. - */ - .stab 0 : { *(.stab) } - .stabstr 0 : { *(.stabstr) } - .stab.excl 0 : { *(.stab.excl) } - .stab.exclstr 0 : { *(.stab.exclstr) } - .stab.index 0 : { *(.stab.index) } - .stab.indexstr 0 : { *(.stab.indexstr) } - .comment 0 : { *(.comment) } - - /* - * DWARF debug sections. - * Symbols in the DWARF debugging sections are relative to the - * beginning of the section so we begin them at 0. - */ - /* DWARF 1 */ - .debug 0 : { *(.debug) } - .line 0 : { *(.line) } - /* GNU DWARF 1 extensions */ - .debug_srcinfo 0 : { *(.debug_srcinfo) } - .debug_sfnames 0 : { *(.debug_sfnames) } - /* DWARF 1.1 and DWARF 2 */ - .debug_aranges 0 : { *(.debug_aranges) } - .debug_pubnames 0 : { *(.debug_pubnames) } - /* DWARF 2 */ - .debug_info 0 : { *(.debug_info .gnu.linkonce.wi.*) } - .debug_abbrev 0 : { *(.debug_abbrev) } - .debug_line 0 : { *(.debug_line) } - .debug_frame 0 : { *(.debug_frame) } - .debug_str 0 : { *(.debug_str) } - .debug_loc 0 : { *(.debug_loc) } - .debug_macinfo 0 : { *(.debug_macinfo) } - /* SGI/MIPS DWARF 2 extensions */ - .debug_weaknames 0 : { *(.debug_weaknames) } - .debug_funcnames 0 : { *(.debug_funcnames) } - .debug_typenames 0 : { *(.debug_typenames) } - .debug_varnames 0 : { *(.debug_varnames) } - /* DWARF 3 */ - .debug_pubtypes 0 : { *(.debug_pubtypes) } - .debug_ranges 0 : { *(.debug_ranges) } - .gnu.attributes 0 : { KEEP (*(.gnu.attributes)) } - - . = ALIGN(PAGE_SIZE); - PROVIDE(_vdso_data = .); - - /DISCARD/ : { - *(.note.GNU-stack) - *(.branch_lt) - *(.data .data.* .gnu.linkonce.d.* .sdata*) - *(.bss .sbss .dynbss .dynsbss) - } -} - -/* - * Very old versions of ld do not recognize this name token; use the constant. - */ -#define PT_GNU_EH_FRAME 0x6474e550 - -/* - * We must supply the ELF program headers explicitly to get just one - * PT_LOAD segment, and set the flags explicitly to make segments read-only. - */ -PHDRS -{ - text PT_LOAD FILEHDR PHDRS FLAGS(5); /* PF_R|PF_X */ - dynamic PT_DYNAMIC FLAGS(4); /* PF_R */ - note PT_NOTE FLAGS(4); /* PF_R */ - eh_frame_hdr PT_GNU_EH_FRAME; -} - -/* - * This controls what symbols we export from the DSO. - */ -VERSION -{ - VDSO_VERSION_STRING { - global: - /* - * Has to be there for the kernel to find - */ - __kernel_gettimeofday; - __kernel_clock_gettime; - __kernel_clock_getres; - __kernel_getcpu; - - local: *; - }; -} diff --git a/arch/s390/kernel/vdso32/vdso32_wrapper.S b/arch/s390/kernel/vdso32/vdso32_wrapper.S deleted file mode 100644 index de2fb930471a..000000000000 --- a/arch/s390/kernel/vdso32/vdso32_wrapper.S +++ /dev/null @@ -1,15 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#include <linux/init.h> -#include <linux/linkage.h> -#include <asm/page.h> - - __PAGE_ALIGNED_DATA - - .globl vdso32_start, vdso32_end - .balign PAGE_SIZE -vdso32_start: - .incbin "arch/s390/kernel/vdso32/vdso32.so" - .balign PAGE_SIZE -vdso32_end: - - .previous diff --git a/arch/s390/kernel/vdso64/getcpu.S b/arch/s390/kernel/vdso64/getcpu.S index 2446e9dac8ab..3c04f7328500 100644 --- a/arch/s390/kernel/vdso64/getcpu.S +++ b/arch/s390/kernel/vdso64/getcpu.S @@ -16,10 +16,8 @@ .type __kernel_getcpu,@function __kernel_getcpu: CFI_STARTPROC - la %r4,0 sacf 256 - l %r5,__VDSO_CPU_NR(%r4) - l %r4,__VDSO_NODE_ID(%r4) + lm %r4,%r5,__VDSO_GETCPU_VAL(%r0) sacf 0 ltgr %r2,%r2 jz 2f diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S index 7e0eb4020917..37695499717d 100644 --- a/arch/s390/kernel/vmlinux.lds.S +++ b/arch/s390/kernel/vmlinux.lds.S @@ -15,6 +15,8 @@ /* Handle ro_after_init data on our own. */ #define RO_AFTER_INIT_DATA +#define EMITS_PT_NOTE + #include <asm-generic/vmlinux.lds.h> #include <asm/vmlinux.lds.h> @@ -50,11 +52,7 @@ SECTIONS _etext = .; /* End of text section */ } :text = 0x0700 - NOTES :text :note - - .dummy : { *(.dummy) } :data - - RO_DATA_SECTION(PAGE_SIZE) + RO_DATA(PAGE_SIZE) . = ALIGN(PAGE_SIZE); _sdata = .; /* Start of data section */ @@ -64,12 +62,12 @@ SECTIONS .data..ro_after_init : { *(.data..ro_after_init) JUMP_TABLE_DATA - } + } :data EXCEPTION_TABLE(16) . = ALIGN(PAGE_SIZE); __end_ro_after_init = .; - RW_DATA_SECTION(0x100, PAGE_SIZE, THREAD_SIZE) + RW_DATA(0x100, PAGE_SIZE, THREAD_SIZE) BOOT_DATA_PRESERVED _edata = .; /* End of data section */ diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c index c475ca49cfc6..8df10d3c8f6c 100644 --- a/arch/s390/kernel/vtime.c +++ b/arch/s390/kernel/vtime.c @@ -247,9 +247,9 @@ void vtime_account_irq_enter(struct task_struct *tsk) } EXPORT_SYMBOL_GPL(vtime_account_irq_enter); -void vtime_account_system(struct task_struct *tsk) +void vtime_account_kernel(struct task_struct *tsk) __attribute__((alias("vtime_account_irq_enter"))); -EXPORT_SYMBOL_GPL(vtime_account_system); +EXPORT_SYMBOL_GPL(vtime_account_kernel); /* * Sorted add to a list. List is linear searched until first bigger diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c index 45634b3d2e0a..3fb54ec2cf3e 100644 --- a/arch/s390/kvm/diag.c +++ b/arch/s390/kvm/diag.c @@ -158,14 +158,28 @@ static int __diag_time_slice_end_directed(struct kvm_vcpu *vcpu) tid = vcpu->run->s.regs.gprs[(vcpu->arch.sie_block->ipa & 0xf0) >> 4]; vcpu->stat.diagnose_9c++; - VCPU_EVENT(vcpu, 5, "diag time slice end directed to %d", tid); + /* yield to self */ if (tid == vcpu->vcpu_id) - return 0; + goto no_yield; + /* yield to invalid */ tcpu = kvm_get_vcpu_by_id(vcpu->kvm, tid); - if (tcpu) - kvm_vcpu_yield_to(tcpu); + if (!tcpu) + goto no_yield; + + /* target already running */ + if (READ_ONCE(tcpu->cpu) >= 0) + goto no_yield; + + if (kvm_vcpu_yield_to(tcpu) <= 0) + goto no_yield; + + VCPU_EVENT(vcpu, 5, "diag time slice end directed to %d: done", tid); + return 0; +no_yield: + VCPU_EVENT(vcpu, 5, "diag time slice end directed to %d: ignored", tid); + vcpu->stat.diagnose_9c_ignored++; return 0; } diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index b5fd6e85657c..c06c89d370a7 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -1477,8 +1477,7 @@ static int __inject_sigp_stop(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq) return 0; } -static int __inject_sigp_restart(struct kvm_vcpu *vcpu, - struct kvm_s390_irq *irq) +static int __inject_sigp_restart(struct kvm_vcpu *vcpu) { struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; @@ -1961,6 +1960,16 @@ int s390int_to_s390irq(struct kvm_s390_interrupt *s390int, case KVM_S390_MCHK: irq->u.mchk.mcic = s390int->parm64; break; + case KVM_S390_INT_PFAULT_INIT: + irq->u.ext.ext_params = s390int->parm; + irq->u.ext.ext_params2 = s390int->parm64; + break; + case KVM_S390_RESTART: + case KVM_S390_INT_CLOCK_COMP: + case KVM_S390_INT_CPU_TIMER: + break; + default: + return -EINVAL; } return 0; } @@ -1997,7 +2006,7 @@ static int do_inject_vcpu(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq) rc = __inject_sigp_stop(vcpu, irq); break; case KVM_S390_RESTART: - rc = __inject_sigp_restart(vcpu, irq); + rc = __inject_sigp_restart(vcpu); break; case KVM_S390_INT_CLOCK_COMP: rc = __inject_ckc(vcpu); @@ -2181,7 +2190,7 @@ static int flic_ais_mode_get_all(struct kvm *kvm, struct kvm_device_attr *attr) return -EINVAL; if (!test_kvm_facility(kvm, 72)) - return -ENOTSUPP; + return -EOPNOTSUPP; mutex_lock(&fi->ais_lock); ais.simm = fi->simm; @@ -2490,7 +2499,7 @@ static int modify_ais_mode(struct kvm *kvm, struct kvm_device_attr *attr) int ret = 0; if (!test_kvm_facility(kvm, 72)) - return -ENOTSUPP; + return -EOPNOTSUPP; if (copy_from_user(&req, (void __user *)attr->addr, sizeof(req))) return -EFAULT; @@ -2570,7 +2579,7 @@ static int flic_ais_mode_set_all(struct kvm *kvm, struct kvm_device_attr *attr) struct kvm_s390_ais_all ais; if (!test_kvm_facility(kvm, 72)) - return -ENOTSUPP; + return -EOPNOTSUPP; if (copy_from_user(&ais, (void __user *)attr->addr, sizeof(ais))) return -EFAULT; diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index f329dcb3f44c..d7ff30e45589 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -155,6 +155,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "instruction_diag_10", VCPU_STAT(diagnose_10) }, { "instruction_diag_44", VCPU_STAT(diagnose_44) }, { "instruction_diag_9c", VCPU_STAT(diagnose_9c) }, + { "diag_9c_ignored", VCPU_STAT(diagnose_9c_ignored) }, { "instruction_diag_258", VCPU_STAT(diagnose_258) }, { "instruction_diag_308", VCPU_STAT(diagnose_308) }, { "instruction_diag_500", VCPU_STAT(diagnose_500) }, @@ -332,7 +333,7 @@ static inline int plo_test_bit(unsigned char nr) return cc == 0; } -static inline void __insn32_query(unsigned int opcode, u8 query[32]) +static __always_inline void __insn32_query(unsigned int opcode, u8 *query) { register unsigned long r0 asm("0") = 0; /* query function */ register unsigned long r1 asm("1") = (unsigned long) query; @@ -340,9 +341,9 @@ static inline void __insn32_query(unsigned int opcode, u8 query[32]) asm volatile( /* Parameter regs are ignored */ " .insn rrf,%[opc] << 16,2,4,6,0\n" - : "=m" (*query) + : : "d" (r0), "a" (r1), [opc] "i" (opcode) - : "cc"); + : "cc", "memory"); } #define INSN_SORTL 0xb938 @@ -453,16 +454,14 @@ static void kvm_s390_cpu_feat_init(void) int kvm_arch_init(void *opaque) { - int rc; + int rc = -ENOMEM; kvm_s390_dbf = debug_register("kvm-trace", 32, 1, 7 * sizeof(long)); if (!kvm_s390_dbf) return -ENOMEM; - if (debug_register_view(kvm_s390_dbf, &debug_sprintf_view)) { - rc = -ENOMEM; - goto out_debug_unreg; - } + if (debug_register_view(kvm_s390_dbf, &debug_sprintf_view)) + goto out; kvm_s390_cpu_feat_init(); @@ -470,19 +469,17 @@ int kvm_arch_init(void *opaque) rc = kvm_register_device_ops(&kvm_flic_ops, KVM_DEV_TYPE_FLIC); if (rc) { pr_err("A FLIC registration call failed with rc=%d\n", rc); - goto out_debug_unreg; + goto out; } rc = kvm_s390_gib_init(GAL_ISC); if (rc) - goto out_gib_destroy; + goto out; return 0; -out_gib_destroy: - kvm_s390_gib_destroy(); -out_debug_unreg: - debug_unregister(kvm_s390_dbf); +out: + kvm_arch_exit(); return rc; } @@ -532,6 +529,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_S390_CMMA_MIGRATION: case KVM_CAP_S390_AIS: case KVM_CAP_S390_AIS_MIGRATION: + case KVM_CAP_S390_VCPU_RESETS: r = 1; break; case KVM_CAP_S390_HPAGE_1M: @@ -1018,6 +1016,8 @@ static int kvm_s390_vm_start_migration(struct kvm *kvm) /* mark all the pages in active slots as dirty */ for (slotnr = 0; slotnr < slots->used_slots; slotnr++) { ms = slots->memslots + slotnr; + if (!ms->dirty_bitmap) + return -EINVAL; /* * The second half of the bitmap is only used on x86, * and would be wasted otherwise, so we put it to good @@ -2531,9 +2531,6 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) if (vcpu->kvm->arch.use_cmma) kvm_s390_vcpu_unsetup_cmma(vcpu); free_page((unsigned long)(vcpu->arch.sie_block)); - - kvm_vcpu_uninit(vcpu); - kmem_cache_free(kvm_vcpu_cache, vcpu); } static void kvm_free_vcpus(struct kvm *kvm) @@ -2542,7 +2539,7 @@ static void kvm_free_vcpus(struct kvm *kvm) struct kvm_vcpu *vcpu; kvm_for_each_vcpu(i, vcpu, kvm) - kvm_arch_vcpu_destroy(vcpu); + kvm_vcpu_destroy(vcpu); mutex_lock(&kvm->lock); for (i = 0; i < atomic_read(&kvm->online_vcpus); i++) @@ -2704,39 +2701,6 @@ static int sca_can_add_vcpu(struct kvm *kvm, unsigned int id) return rc == 0 && id < KVM_S390_ESCA_CPU_SLOTS; } -int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) -{ - vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID; - kvm_clear_async_pf_completion_queue(vcpu); - vcpu->run->kvm_valid_regs = KVM_SYNC_PREFIX | - KVM_SYNC_GPRS | - KVM_SYNC_ACRS | - KVM_SYNC_CRS | - KVM_SYNC_ARCH0 | - KVM_SYNC_PFAULT; - kvm_s390_set_prefix(vcpu, 0); - if (test_kvm_facility(vcpu->kvm, 64)) - vcpu->run->kvm_valid_regs |= KVM_SYNC_RICCB; - if (test_kvm_facility(vcpu->kvm, 82)) - vcpu->run->kvm_valid_regs |= KVM_SYNC_BPBC; - if (test_kvm_facility(vcpu->kvm, 133)) - vcpu->run->kvm_valid_regs |= KVM_SYNC_GSCB; - if (test_kvm_facility(vcpu->kvm, 156)) - vcpu->run->kvm_valid_regs |= KVM_SYNC_ETOKEN; - /* fprs can be synchronized via vrs, even if the guest has no vx. With - * MACHINE_HAS_VX, (load|store)_fpu_regs() will work with vrs format. - */ - if (MACHINE_HAS_VX) - vcpu->run->kvm_valid_regs |= KVM_SYNC_VRS; - else - vcpu->run->kvm_valid_regs |= KVM_SYNC_FPRS; - - if (kvm_is_ucontrol(vcpu->kvm)) - return __kvm_ucontrol_vcpu_init(vcpu); - - return 0; -} - /* needs disabled preemption to protect from TOD sync and vcpu_load/put */ static void __start_cpu_timer_accounting(struct kvm_vcpu *vcpu) { @@ -2845,35 +2809,6 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) } -static void kvm_s390_vcpu_initial_reset(struct kvm_vcpu *vcpu) -{ - /* this equals initial cpu reset in pop, but we don't switch to ESA */ - vcpu->arch.sie_block->gpsw.mask = 0UL; - vcpu->arch.sie_block->gpsw.addr = 0UL; - kvm_s390_set_prefix(vcpu, 0); - kvm_s390_set_cpu_timer(vcpu, 0); - vcpu->arch.sie_block->ckc = 0UL; - vcpu->arch.sie_block->todpr = 0; - memset(vcpu->arch.sie_block->gcr, 0, 16 * sizeof(__u64)); - vcpu->arch.sie_block->gcr[0] = CR0_UNUSED_56 | - CR0_INTERRUPT_KEY_SUBMASK | - CR0_MEASUREMENT_ALERT_SUBMASK; - vcpu->arch.sie_block->gcr[14] = CR14_UNUSED_32 | - CR14_UNUSED_33 | - CR14_EXTERNAL_DAMAGE_SUBMASK; - /* make sure the new fpc will be lazily loaded */ - save_fpu_regs(); - current->thread.fpu.fpc = 0; - vcpu->arch.sie_block->gbea = 1; - vcpu->arch.sie_block->pp = 0; - vcpu->arch.sie_block->fpf &= ~FPF_BPBC; - vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID; - kvm_clear_async_pf_completion_queue(vcpu); - if (!kvm_s390_user_cpu_state_ctrl(vcpu->kvm)) - kvm_s390_vcpu_stop(vcpu); - kvm_s390_clear_local_irqs(vcpu); -} - void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) { mutex_lock(&vcpu->kvm->lock); @@ -2963,7 +2898,7 @@ static void kvm_s390_vcpu_setup_model(struct kvm_vcpu *vcpu) vcpu->arch.sie_block->fac = (u32)(u64) model->fac_list; } -int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) +static int kvm_s390_vcpu_setup(struct kvm_vcpu *vcpu) { int rc = 0; @@ -3036,26 +2971,22 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) return rc; } -struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, - unsigned int id) +int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id) { - struct kvm_vcpu *vcpu; - struct sie_page *sie_page; - int rc = -EINVAL; - if (!kvm_is_ucontrol(kvm) && !sca_can_add_vcpu(kvm, id)) - goto out; - - rc = -ENOMEM; + return -EINVAL; + return 0; +} - vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL); - if (!vcpu) - goto out; +int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) +{ + struct sie_page *sie_page; + int rc; BUILD_BUG_ON(sizeof(struct sie_page) != 4096); sie_page = (struct sie_page *) get_zeroed_page(GFP_KERNEL); if (!sie_page) - goto out_free_cpu; + return -ENOMEM; vcpu->arch.sie_block = &sie_page->sie_block; vcpu->arch.sie_block->itdba = (unsigned long) &sie_page->itdb; @@ -3064,27 +2995,59 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, vcpu->arch.sie_block->mso = 0; vcpu->arch.sie_block->msl = sclp.hamax; - vcpu->arch.sie_block->icpua = id; + vcpu->arch.sie_block->icpua = vcpu->vcpu_id; spin_lock_init(&vcpu->arch.local_int.lock); - vcpu->arch.sie_block->gd = (u32)(u64)kvm->arch.gisa_int.origin; + vcpu->arch.sie_block->gd = (u32)(u64)vcpu->kvm->arch.gisa_int.origin; if (vcpu->arch.sie_block->gd && sclp.has_gisaf) vcpu->arch.sie_block->gd |= GISA_FORMAT1; seqcount_init(&vcpu->arch.cputm_seqcount); - rc = kvm_vcpu_init(vcpu, kvm, id); + vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID; + kvm_clear_async_pf_completion_queue(vcpu); + vcpu->run->kvm_valid_regs = KVM_SYNC_PREFIX | + KVM_SYNC_GPRS | + KVM_SYNC_ACRS | + KVM_SYNC_CRS | + KVM_SYNC_ARCH0 | + KVM_SYNC_PFAULT; + kvm_s390_set_prefix(vcpu, 0); + if (test_kvm_facility(vcpu->kvm, 64)) + vcpu->run->kvm_valid_regs |= KVM_SYNC_RICCB; + if (test_kvm_facility(vcpu->kvm, 82)) + vcpu->run->kvm_valid_regs |= KVM_SYNC_BPBC; + if (test_kvm_facility(vcpu->kvm, 133)) + vcpu->run->kvm_valid_regs |= KVM_SYNC_GSCB; + if (test_kvm_facility(vcpu->kvm, 156)) + vcpu->run->kvm_valid_regs |= KVM_SYNC_ETOKEN; + /* fprs can be synchronized via vrs, even if the guest has no vx. With + * MACHINE_HAS_VX, (load|store)_fpu_regs() will work with vrs format. + */ + if (MACHINE_HAS_VX) + vcpu->run->kvm_valid_regs |= KVM_SYNC_VRS; + else + vcpu->run->kvm_valid_regs |= KVM_SYNC_FPRS; + + if (kvm_is_ucontrol(vcpu->kvm)) { + rc = __kvm_ucontrol_vcpu_init(vcpu); + if (rc) + goto out_free_sie_block; + } + + VM_EVENT(vcpu->kvm, 3, "create cpu %d at 0x%pK, sie block at 0x%pK", + vcpu->vcpu_id, vcpu, vcpu->arch.sie_block); + trace_kvm_s390_create_vcpu(vcpu->vcpu_id, vcpu, vcpu->arch.sie_block); + + rc = kvm_s390_vcpu_setup(vcpu); if (rc) - goto out_free_sie_block; - VM_EVENT(kvm, 3, "create cpu %d at 0x%pK, sie block at 0x%pK", id, vcpu, - vcpu->arch.sie_block); - trace_kvm_s390_create_vcpu(id, vcpu, vcpu->arch.sie_block); + goto out_ucontrol_uninit; + return 0; - return vcpu; +out_ucontrol_uninit: + if (kvm_is_ucontrol(vcpu->kvm)) + gmap_remove(vcpu->arch.gmap); out_free_sie_block: free_page((unsigned long)(vcpu->arch.sie_block)); -out_free_cpu: - kmem_cache_free(kvm_vcpu_cache, vcpu); -out: - return ERR_PTR(rc); + return rc; } int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu) @@ -3288,10 +3251,53 @@ static int kvm_arch_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, return r; } -static int kvm_arch_vcpu_ioctl_initial_reset(struct kvm_vcpu *vcpu) +static void kvm_arch_vcpu_ioctl_normal_reset(struct kvm_vcpu *vcpu) { - kvm_s390_vcpu_initial_reset(vcpu); - return 0; + vcpu->arch.sie_block->gpsw.mask &= ~PSW_MASK_RI; + vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID; + memset(vcpu->run->s.regs.riccb, 0, sizeof(vcpu->run->s.regs.riccb)); + + kvm_clear_async_pf_completion_queue(vcpu); + if (!kvm_s390_user_cpu_state_ctrl(vcpu->kvm)) + kvm_s390_vcpu_stop(vcpu); + kvm_s390_clear_local_irqs(vcpu); +} + +static void kvm_arch_vcpu_ioctl_initial_reset(struct kvm_vcpu *vcpu) +{ + /* Initial reset is a superset of the normal reset */ + kvm_arch_vcpu_ioctl_normal_reset(vcpu); + + /* this equals initial cpu reset in pop, but we don't switch to ESA */ + vcpu->arch.sie_block->gpsw.mask = 0; + vcpu->arch.sie_block->gpsw.addr = 0; + kvm_s390_set_prefix(vcpu, 0); + kvm_s390_set_cpu_timer(vcpu, 0); + vcpu->arch.sie_block->ckc = 0; + vcpu->arch.sie_block->todpr = 0; + memset(vcpu->arch.sie_block->gcr, 0, sizeof(vcpu->arch.sie_block->gcr)); + vcpu->arch.sie_block->gcr[0] = CR0_INITIAL_MASK; + vcpu->arch.sie_block->gcr[14] = CR14_INITIAL_MASK; + vcpu->run->s.regs.fpc = 0; + vcpu->arch.sie_block->gbea = 1; + vcpu->arch.sie_block->pp = 0; + vcpu->arch.sie_block->fpf &= ~FPF_BPBC; +} + +static void kvm_arch_vcpu_ioctl_clear_reset(struct kvm_vcpu *vcpu) +{ + struct kvm_sync_regs *regs = &vcpu->run->s.regs; + + /* Clear reset is a superset of the initial reset */ + kvm_arch_vcpu_ioctl_initial_reset(vcpu); + + memset(®s->gprs, 0, sizeof(regs->gprs)); + memset(®s->vrs, 0, sizeof(regs->vrs)); + memset(®s->acrs, 0, sizeof(regs->acrs)); + memset(®s->gscb, 0, sizeof(regs->gscb)); + + regs->etoken = 0; + regs->etoken_extension = 0; } int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) @@ -3998,6 +4004,10 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) if (kvm_run->immediate_exit) return -EINTR; + if (kvm_run->kvm_valid_regs & ~KVM_SYNC_S390_VALID_FIELDS || + kvm_run->kvm_dirty_regs & ~KVM_SYNC_S390_VALID_FIELDS) + return -EINVAL; + vcpu_load(vcpu); if (guestdbg_exit_pending(vcpu)) { @@ -4255,7 +4265,7 @@ static long kvm_s390_guest_mem_op(struct kvm_vcpu *vcpu, const u64 supported_flags = KVM_S390_MEMOP_F_INJECT_EXCEPTION | KVM_S390_MEMOP_F_CHECK_ONLY; - if (mop->flags & ~supported_flags) + if (mop->flags & ~supported_flags || mop->ar >= NUM_ACRS || !mop->size) return -EINVAL; if (mop->size > MEM_OP_MAX_SIZE) @@ -4323,7 +4333,7 @@ long kvm_arch_vcpu_async_ioctl(struct file *filp, } case KVM_S390_INTERRUPT: { struct kvm_s390_interrupt s390int; - struct kvm_s390_irq s390irq; + struct kvm_s390_irq s390irq = {}; if (copy_from_user(&s390int, argp, sizeof(s390int))) return -EFAULT; @@ -4348,7 +4358,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp, switch (ioctl) { case KVM_S390_STORE_STATUS: idx = srcu_read_lock(&vcpu->kvm->srcu); - r = kvm_s390_vcpu_store_status(vcpu, arg); + r = kvm_s390_store_status_unloaded(vcpu, arg); srcu_read_unlock(&vcpu->kvm->srcu, idx); break; case KVM_S390_SET_INITIAL_PSW: { @@ -4360,8 +4370,17 @@ long kvm_arch_vcpu_ioctl(struct file *filp, r = kvm_arch_vcpu_ioctl_set_initial_psw(vcpu, psw); break; } + case KVM_S390_CLEAR_RESET: + r = 0; + kvm_arch_vcpu_ioctl_clear_reset(vcpu); + break; case KVM_S390_INITIAL_RESET: - r = kvm_arch_vcpu_ioctl_initial_reset(vcpu); + r = 0; + kvm_arch_vcpu_ioctl_initial_reset(vcpu); + break; + case KVM_S390_NORMAL_RESET: + r = 0; + kvm_arch_vcpu_ioctl_normal_reset(vcpu); break; case KVM_SET_ONE_REG: case KVM_GET_ONE_REG: { diff --git a/arch/s390/lib/Makefile b/arch/s390/lib/Makefile index a1ec63abfb95..28fd66d558ff 100644 --- a/arch/s390/lib/Makefile +++ b/arch/s390/lib/Makefile @@ -12,5 +12,5 @@ lib-$(CONFIG_UPROBES) += probes.o # produce false positives KASAN_SANITIZE_uaccess.o := n -chkbss := mem.o -include $(srctree)/arch/s390/scripts/Makefile.chkbss +obj-$(CONFIG_S390_UNWIND_SELFTEST) += test_unwind.o +CFLAGS_test_unwind.o += -fno-optimize-sibling-calls diff --git a/arch/s390/lib/spinlock.c b/arch/s390/lib/spinlock.c index 30a7c8c29964..9b2dab5a69f9 100644 --- a/arch/s390/lib/spinlock.c +++ b/arch/s390/lib/spinlock.c @@ -74,7 +74,7 @@ static inline int arch_load_niai4(int *lock) { int owner; - asm volatile( + asm_inline volatile( ALTERNATIVE("", ".long 0xb2fa0040", 49) /* NIAI 4 */ " l %0,%1\n" : "=d" (owner) : "Q" (*lock) : "memory"); @@ -85,7 +85,7 @@ static inline int arch_cmpxchg_niai8(int *lock, int old, int new) { int expected = old; - asm volatile( + asm_inline volatile( ALTERNATIVE("", ".long 0xb2fa0080", 49) /* NIAI 8 */ " cs %0,%3,%1\n" : "=d" (old), "=Q" (*lock) @@ -242,7 +242,6 @@ static inline void arch_spin_lock_classic(arch_spinlock_t *lp) void arch_spin_lock_wait(arch_spinlock_t *lp) { - /* Use classic spinlocks + niai if the steal time is >= 10% */ if (test_cpu_flag(CIF_DEDICATED_CPU)) arch_spin_lock_queued(lp); else diff --git a/arch/s390/lib/test_unwind.c b/arch/s390/lib/test_unwind.c new file mode 100644 index 000000000000..32b7a30b2485 --- /dev/null +++ b/arch/s390/lib/test_unwind.c @@ -0,0 +1,347 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Test module for unwind_for_each_frame + */ + +#define pr_fmt(fmt) "test_unwind: " fmt +#include <asm/unwind.h> +#include <linux/completion.h> +#include <linux/kallsyms.h> +#include <linux/kthread.h> +#include <linux/module.h> +#include <linux/string.h> +#include <linux/kprobes.h> +#include <linux/wait.h> +#include <asm/irq.h> +#include <asm/delay.h> + +#define BT_BUF_SIZE (PAGE_SIZE * 4) + +/* + * To avoid printk line limit split backtrace by lines + */ +static void print_backtrace(char *bt) +{ + char *p; + + while (true) { + p = strsep(&bt, "\n"); + if (!p) + break; + pr_err("%s\n", p); + } +} + +/* + * Calls unwind_for_each_frame(task, regs, sp) and verifies that the result + * contains unwindme_func2 followed by unwindme_func1. + */ +static noinline int test_unwind(struct task_struct *task, struct pt_regs *regs, + unsigned long sp) +{ + int frame_count, prev_is_func2, seen_func2_func1; + const int max_frames = 128; + struct unwind_state state; + size_t bt_pos = 0; + int ret = 0; + char *bt; + + bt = kmalloc(BT_BUF_SIZE, GFP_ATOMIC); + if (!bt) { + pr_err("failed to allocate backtrace buffer\n"); + return -ENOMEM; + } + /* Unwind. */ + frame_count = 0; + prev_is_func2 = 0; + seen_func2_func1 = 0; + unwind_for_each_frame(&state, task, regs, sp) { + unsigned long addr = unwind_get_return_address(&state); + char sym[KSYM_SYMBOL_LEN]; + + if (frame_count++ == max_frames) + break; + if (state.reliable && !addr) { + pr_err("unwind state reliable but addr is 0\n"); + return -EINVAL; + } + sprint_symbol(sym, addr); + if (bt_pos < BT_BUF_SIZE) { + bt_pos += snprintf(bt + bt_pos, BT_BUF_SIZE - bt_pos, + state.reliable ? " [%-7s%px] %pSR\n" : + "([%-7s%px] %pSR)\n", + stack_type_name(state.stack_info.type), + (void *)state.sp, (void *)state.ip); + if (bt_pos >= BT_BUF_SIZE) + pr_err("backtrace buffer is too small\n"); + } + frame_count += 1; + if (prev_is_func2 && str_has_prefix(sym, "unwindme_func1")) + seen_func2_func1 = 1; + prev_is_func2 = str_has_prefix(sym, "unwindme_func2"); + } + + /* Check the results. */ + if (unwind_error(&state)) { + pr_err("unwind error\n"); + ret = -EINVAL; + } + if (!seen_func2_func1) { + pr_err("unwindme_func2 and unwindme_func1 not found\n"); + ret = -EINVAL; + } + if (frame_count == max_frames) { + pr_err("Maximum number of frames exceeded\n"); + ret = -EINVAL; + } + if (ret) + print_backtrace(bt); + kfree(bt); + return ret; +} + +/* State of the task being unwound. */ +struct unwindme { + int flags; + int ret; + struct task_struct *task; + struct completion task_ready; + wait_queue_head_t task_wq; + unsigned long sp; +}; + +static struct unwindme *unwindme; + +/* Values of unwindme.flags. */ +#define UWM_DEFAULT 0x0 +#define UWM_THREAD 0x1 /* Unwind a separate task. */ +#define UWM_REGS 0x2 /* Pass regs to test_unwind(). */ +#define UWM_SP 0x4 /* Pass sp to test_unwind(). */ +#define UWM_CALLER 0x8 /* Unwind starting from caller. */ +#define UWM_SWITCH_STACK 0x10 /* Use CALL_ON_STACK. */ +#define UWM_IRQ 0x20 /* Unwind from irq context. */ +#define UWM_PGM 0x40 /* Unwind from program check handler. */ + +static __always_inline unsigned long get_psw_addr(void) +{ + unsigned long psw_addr; + + asm volatile( + "basr %[psw_addr],0\n" + : [psw_addr] "=d" (psw_addr)); + return psw_addr; +} + +#ifdef CONFIG_KPROBES +static int pgm_pre_handler(struct kprobe *p, struct pt_regs *regs) +{ + struct unwindme *u = unwindme; + + u->ret = test_unwind(NULL, (u->flags & UWM_REGS) ? regs : NULL, + (u->flags & UWM_SP) ? u->sp : 0); + return 0; +} +#endif + +/* This function may or may not appear in the backtrace. */ +static noinline int unwindme_func4(struct unwindme *u) +{ + if (!(u->flags & UWM_CALLER)) + u->sp = current_frame_address(); + if (u->flags & UWM_THREAD) { + complete(&u->task_ready); + wait_event(u->task_wq, kthread_should_park()); + kthread_parkme(); + return 0; +#ifdef CONFIG_KPROBES + } else if (u->flags & UWM_PGM) { + struct kprobe kp; + int ret; + + unwindme = u; + memset(&kp, 0, sizeof(kp)); + kp.symbol_name = "do_report_trap"; + kp.pre_handler = pgm_pre_handler; + ret = register_kprobe(&kp); + if (ret < 0) { + pr_err("register_kprobe failed %d\n", ret); + return -EINVAL; + } + + /* + * trigger specification exception + */ + asm volatile( + " mvcl %%r1,%%r1\n" + "0: nopr %%r7\n" + EX_TABLE(0b, 0b) + :); + + unregister_kprobe(&kp); + unwindme = NULL; + return u->ret; +#endif + } else { + struct pt_regs regs; + + memset(®s, 0, sizeof(regs)); + regs.psw.addr = get_psw_addr(); + regs.gprs[15] = current_stack_pointer(); + return test_unwind(NULL, + (u->flags & UWM_REGS) ? ®s : NULL, + (u->flags & UWM_SP) ? u->sp : 0); + } +} + +/* This function may or may not appear in the backtrace. */ +static noinline int unwindme_func3(struct unwindme *u) +{ + u->sp = current_frame_address(); + return unwindme_func4(u); +} + +/* This function must appear in the backtrace. */ +static noinline int unwindme_func2(struct unwindme *u) +{ + int rc; + + if (u->flags & UWM_SWITCH_STACK) { + preempt_disable(); + rc = CALL_ON_STACK(unwindme_func3, S390_lowcore.nodat_stack, 1, u); + preempt_enable(); + return rc; + } else { + return unwindme_func3(u); + } +} + +/* This function must follow unwindme_func2 in the backtrace. */ +static noinline int unwindme_func1(void *u) +{ + return unwindme_func2((struct unwindme *)u); +} + +static void unwindme_irq_handler(struct ext_code ext_code, + unsigned int param32, + unsigned long param64) +{ + struct unwindme *u = READ_ONCE(unwindme); + + if (u && u->task == current) { + unwindme = NULL; + u->task = NULL; + u->ret = unwindme_func1(u); + } +} + +static int test_unwind_irq(struct unwindme *u) +{ + preempt_disable(); + if (register_external_irq(EXT_IRQ_CLK_COMP, unwindme_irq_handler)) { + pr_info("Couldn't register external interrupt handler"); + return -1; + } + u->task = current; + unwindme = u; + udelay(1); + unregister_external_irq(EXT_IRQ_CLK_COMP, unwindme_irq_handler); + preempt_enable(); + return u->ret; +} + +/* Spawns a task and passes it to test_unwind(). */ +static int test_unwind_task(struct unwindme *u) +{ + struct task_struct *task; + int ret; + + /* Initialize thread-related fields. */ + init_completion(&u->task_ready); + init_waitqueue_head(&u->task_wq); + + /* + * Start the task and wait until it reaches unwindme_func4() and sleeps + * in (task_ready, unwind_done] range. + */ + task = kthread_run(unwindme_func1, u, "%s", __func__); + if (IS_ERR(task)) { + pr_err("kthread_run() failed\n"); + return PTR_ERR(task); + } + /* + * Make sure task reaches unwindme_func4 before parking it, + * we might park it before kthread function has been executed otherwise + */ + wait_for_completion(&u->task_ready); + kthread_park(task); + /* Unwind. */ + ret = test_unwind(task, NULL, (u->flags & UWM_SP) ? u->sp : 0); + kthread_stop(task); + return ret; +} + +static int test_unwind_flags(int flags) +{ + struct unwindme u; + + u.flags = flags; + if (u.flags & UWM_THREAD) + return test_unwind_task(&u); + else if (u.flags & UWM_IRQ) + return test_unwind_irq(&u); + else + return unwindme_func1(&u); +} + +static int test_unwind_init(void) +{ + int ret = 0; + +#define TEST(flags) \ +do { \ + pr_info("[ RUN ] " #flags "\n"); \ + if (!test_unwind_flags((flags))) { \ + pr_info("[ OK ] " #flags "\n"); \ + } else { \ + pr_err("[ FAILED ] " #flags "\n"); \ + ret = -EINVAL; \ + } \ +} while (0) + + TEST(UWM_DEFAULT); + TEST(UWM_SP); + TEST(UWM_REGS); + TEST(UWM_SWITCH_STACK); + TEST(UWM_SP | UWM_REGS); + TEST(UWM_CALLER | UWM_SP); + TEST(UWM_CALLER | UWM_SP | UWM_REGS); + TEST(UWM_CALLER | UWM_SP | UWM_REGS | UWM_SWITCH_STACK); + TEST(UWM_THREAD); + TEST(UWM_THREAD | UWM_SP); + TEST(UWM_THREAD | UWM_CALLER | UWM_SP); + TEST(UWM_IRQ); + TEST(UWM_IRQ | UWM_SWITCH_STACK); + TEST(UWM_IRQ | UWM_SP); + TEST(UWM_IRQ | UWM_REGS); + TEST(UWM_IRQ | UWM_SP | UWM_REGS); + TEST(UWM_IRQ | UWM_CALLER | UWM_SP); + TEST(UWM_IRQ | UWM_CALLER | UWM_SP | UWM_REGS); + TEST(UWM_IRQ | UWM_CALLER | UWM_SP | UWM_REGS | UWM_SWITCH_STACK); +#ifdef CONFIG_KPROBES + TEST(UWM_PGM); + TEST(UWM_PGM | UWM_SP); + TEST(UWM_PGM | UWM_REGS); + TEST(UWM_PGM | UWM_SP | UWM_REGS); +#endif +#undef TEST + + return ret; +} + +static void test_unwind_exit(void) +{ +} + +module_init(test_unwind_init); +module_exit(test_unwind_exit); +MODULE_LICENSE("GPL"); diff --git a/arch/s390/mm/cmm.c b/arch/s390/mm/cmm.c index 510a18299196..a51c892f14f3 100644 --- a/arch/s390/mm/cmm.c +++ b/arch/s390/mm/cmm.c @@ -298,16 +298,16 @@ static int cmm_timeout_handler(struct ctl_table *ctl, int write, } if (write) { - len = *lenp; - if (copy_from_user(buf, buffer, - len > sizeof(buf) ? sizeof(buf) : len)) + len = min(*lenp, sizeof(buf)); + if (copy_from_user(buf, buffer, len)) return -EFAULT; - buf[sizeof(buf) - 1] = '\0'; + buf[len - 1] = '\0'; cmm_skip_blanks(buf, &p); nr = simple_strtoul(p, &p, 0); cmm_skip_blanks(p, &p); seconds = simple_strtoul(p, &p, 0); cmm_set_timeout(nr, seconds); + *ppos += *lenp; } else { len = sprintf(buf, "%ld %ld\n", cmm_timeout_pages, cmm_timeout_seconds); @@ -315,9 +315,9 @@ static int cmm_timeout_handler(struct ctl_table *ctl, int write, len = *lenp; if (copy_to_user(buffer, buf, len)) return -EFAULT; + *lenp = len; + *ppos += len; } - *lenp = len; - *ppos += len; return 0; } diff --git a/arch/s390/mm/extmem.c b/arch/s390/mm/extmem.c index 0b5622714c12..fd0dae9d10f4 100644 --- a/arch/s390/mm/extmem.c +++ b/arch/s390/mm/extmem.c @@ -19,6 +19,7 @@ #include <linux/memblock.h> #include <linux/ctype.h> #include <linux/ioport.h> +#include <linux/refcount.h> #include <asm/diag.h> #include <asm/page.h> #include <asm/pgtable.h> @@ -64,7 +65,7 @@ struct dcss_segment { char res_name[16]; unsigned long start_addr; unsigned long end; - atomic_t ref_count; + refcount_t ref_count; int do_nonshared; unsigned int vm_segtype; struct qrange range[6]; @@ -362,7 +363,7 @@ __segment_load (char *name, int do_nonshared, unsigned long *addr, unsigned long seg->start_addr = start_addr; seg->end = end_addr; seg->do_nonshared = do_nonshared; - atomic_set(&seg->ref_count, 1); + refcount_set(&seg->ref_count, 1); list_add(&seg->list, &dcss_list); *addr = seg->start_addr; *end = seg->end; @@ -422,7 +423,7 @@ segment_load (char *name, int do_nonshared, unsigned long *addr, rc = __segment_load (name, do_nonshared, addr, end); else { if (do_nonshared == seg->do_nonshared) { - atomic_inc(&seg->ref_count); + refcount_inc(&seg->ref_count); *addr = seg->start_addr; *end = seg->end; rc = seg->vm_segtype; @@ -468,7 +469,7 @@ segment_modify_shared (char *name, int do_nonshared) rc = 0; goto out_unlock; } - if (atomic_read (&seg->ref_count) != 1) { + if (refcount_read(&seg->ref_count) != 1) { pr_warn("DCSS %s is in use and cannot be reloaded\n", name); rc = -EAGAIN; goto out_unlock; @@ -544,7 +545,7 @@ segment_unload(char *name) pr_err("Unloading unknown DCSS %s failed\n", name); goto out_unlock; } - if (atomic_dec_return(&seg->ref_count) != 0) + if (!refcount_dec_and_test(&seg->ref_count)) goto out_unlock; release_resource(seg->res); kfree(seg->res); diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c index 39c3a6e3d262..edcdca97e85e 100644 --- a/arch/s390/mm/gmap.c +++ b/arch/s390/mm/gmap.c @@ -9,7 +9,7 @@ */ #include <linux/kernel.h> -#include <linux/mm.h> +#include <linux/pagewalk.h> #include <linux/swap.h> #include <linux/smp.h> #include <linux/spinlock.h> @@ -67,7 +67,7 @@ static struct gmap *gmap_alloc(unsigned long limit) INIT_RADIX_TREE(&gmap->host_to_rmap, GFP_ATOMIC); spin_lock_init(&gmap->guest_table_lock); spin_lock_init(&gmap->shadow_lock); - atomic_set(&gmap->ref_count, 1); + refcount_set(&gmap->ref_count, 1); page = alloc_pages(GFP_KERNEL, CRST_ALLOC_ORDER); if (!page) goto out_free; @@ -214,7 +214,7 @@ static void gmap_free(struct gmap *gmap) */ struct gmap *gmap_get(struct gmap *gmap) { - atomic_inc(&gmap->ref_count); + refcount_inc(&gmap->ref_count); return gmap; } EXPORT_SYMBOL_GPL(gmap_get); @@ -227,7 +227,7 @@ EXPORT_SYMBOL_GPL(gmap_get); */ void gmap_put(struct gmap *gmap) { - if (atomic_dec_return(&gmap->ref_count) == 0) + if (refcount_dec_and_test(&gmap->ref_count)) gmap_free(gmap); } EXPORT_SYMBOL_GPL(gmap_put); @@ -1594,7 +1594,7 @@ static struct gmap *gmap_find_shadow(struct gmap *parent, unsigned long asce, continue; if (!sg->initialized) return ERR_PTR(-EAGAIN); - atomic_inc(&sg->ref_count); + refcount_inc(&sg->ref_count); return sg; } return NULL; @@ -1682,7 +1682,7 @@ struct gmap *gmap_shadow(struct gmap *parent, unsigned long asce, } } } - atomic_set(&new->ref_count, 2); + refcount_set(&new->ref_count, 2); list_add(&new->list, &parent->children); if (asce & _ASCE_REAL_SPACE) { /* nothing to protect, return right away */ @@ -2521,13 +2521,9 @@ static int __zap_zero_pages(pmd_t *pmd, unsigned long start, return 0; } -static inline void zap_zero_pages(struct mm_struct *mm) -{ - struct mm_walk walk = { .pmd_entry = __zap_zero_pages }; - - walk.mm = mm; - walk_page_range(0, TASK_SIZE, &walk); -} +static const struct mm_walk_ops zap_zero_walk_ops = { + .pmd_entry = __zap_zero_pages, +}; /* * switch on pgstes for its userspace process (for kvm) @@ -2546,7 +2542,7 @@ int s390_enable_sie(void) mm->context.has_pgste = 1; /* split thp mappings and disable thp for future mappings */ thp_split_mm(mm); - zap_zero_pages(mm); + walk_page_range(mm, 0, TASK_SIZE, &zap_zero_walk_ops, NULL); up_write(&mm->mmap_sem); return 0; } @@ -2589,12 +2585,13 @@ static int __s390_enable_skey_hugetlb(pte_t *pte, unsigned long addr, return 0; } +static const struct mm_walk_ops enable_skey_walk_ops = { + .hugetlb_entry = __s390_enable_skey_hugetlb, + .pte_entry = __s390_enable_skey_pte, +}; + int s390_enable_skey(void) { - struct mm_walk walk = { - .hugetlb_entry = __s390_enable_skey_hugetlb, - .pte_entry = __s390_enable_skey_pte, - }; struct mm_struct *mm = current->mm; struct vm_area_struct *vma; int rc = 0; @@ -2614,8 +2611,7 @@ int s390_enable_skey(void) } mm->def_flags &= ~VM_MERGEABLE; - walk.mm = mm; - walk_page_range(0, TASK_SIZE, &walk); + walk_page_range(mm, 0, TASK_SIZE, &enable_skey_walk_ops, NULL); out_up: up_write(&mm->mmap_sem); @@ -2633,13 +2629,14 @@ static int __s390_reset_cmma(pte_t *pte, unsigned long addr, return 0; } +static const struct mm_walk_ops reset_cmma_walk_ops = { + .pte_entry = __s390_reset_cmma, +}; + void s390_reset_cmma(struct mm_struct *mm) { - struct mm_walk walk = { .pte_entry = __s390_reset_cmma }; - down_write(&mm->mmap_sem); - walk.mm = mm; - walk_page_range(0, TASK_SIZE, &walk); + walk_page_range(mm, 0, TASK_SIZE, &reset_cmma_walk_ops, NULL); up_write(&mm->mmap_sem); } EXPORT_SYMBOL_GPL(s390_reset_cmma); diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c index b0246c705a19..5674710a4841 100644 --- a/arch/s390/mm/hugetlbpage.c +++ b/arch/s390/mm/hugetlbpage.c @@ -2,7 +2,7 @@ /* * IBM System z Huge TLB Page Support for Kernel. * - * Copyright IBM Corp. 2007,2016 + * Copyright IBM Corp. 2007,2020 * Author(s): Gerald Schaefer <gerald.schaefer@de.ibm.com> */ @@ -11,6 +11,9 @@ #include <linux/mm.h> #include <linux/hugetlb.h> +#include <linux/mman.h> +#include <linux/sched/mm.h> +#include <linux/security.h> /* * If the bit selected by single-bit bitmask "a" is set within "x", move @@ -267,3 +270,98 @@ static __init int setup_hugepagesz(char *opt) return 1; } __setup("hugepagesz=", setup_hugepagesz); + +static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *file, + unsigned long addr, unsigned long len, + unsigned long pgoff, unsigned long flags) +{ + struct hstate *h = hstate_file(file); + 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); +} + +static unsigned long hugetlb_get_unmapped_area_topdown(struct file *file, + unsigned long addr0, unsigned long len, + unsigned long pgoff, unsigned long flags) +{ + struct hstate *h = hstate_file(file); + struct vm_unmapped_area_info info; + unsigned long addr; + + info.flags = VM_UNMAPPED_AREA_TOPDOWN; + info.length = len; + info.low_limit = max(PAGE_SIZE, mmap_min_addr); + 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); + + /* + * A failed mmap() very likely causes application failure, + * so fall back to the bottom-up function here. This scenario + * can happen with large stack limits and large mmap() + * allocations. + */ + if (addr & ~PAGE_MASK) { + VM_BUG_ON(addr != -ENOMEM); + info.flags = 0; + info.low_limit = TASK_UNMAPPED_BASE; + info.high_limit = TASK_SIZE; + addr = vm_unmapped_area(&info); + } + + return addr; +} + +unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, + unsigned long len, unsigned long pgoff, unsigned long flags) +{ + struct hstate *h = hstate_file(file); + struct mm_struct *mm = current->mm; + struct vm_area_struct *vma; + int rc; + + if (len & ~huge_page_mask(h)) + return -EINVAL; + if (len > TASK_SIZE - mmap_min_addr) + return -ENOMEM; + + if (flags & MAP_FIXED) { + if (prepare_hugepage_range(file, addr, len)) + return -EINVAL; + goto check_asce_limit; + } + + if (addr) { + addr = ALIGN(addr, huge_page_size(h)); + vma = find_vma(mm, addr); + if (TASK_SIZE - len >= addr && addr >= mmap_min_addr && + (!vma || addr + len <= vm_start_gap(vma))) + goto check_asce_limit; + } + + if (mm->get_unmapped_area == arch_get_unmapped_area) + addr = hugetlb_get_unmapped_area_bottomup(file, addr, len, + pgoff, flags); + else + addr = hugetlb_get_unmapped_area_topdown(file, addr, len, + pgoff, flags); + if (addr & ~PAGE_MASK) + return addr; + +check_asce_limit: + if (addr + len > current->mm->context.asce_limit && + addr + len <= TASK_SIZE) { + rc = crst_table_upgrade(mm, addr + len); + if (rc) + return (unsigned long) rc; + } + return addr; +} diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index 20340a03ad90..ac44bd76db4b 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -118,6 +118,7 @@ void __init paging_init(void) sparse_memory_present_with_active_regions(MAX_NUMNODES); sparse_init(); + zone_dma_bits = 31; memset(max_zone_pfns, 0, sizeof(max_zone_pfns)); max_zone_pfns[ZONE_DMA] = PFN_DOWN(MAX_DMA_ADDRESS); max_zone_pfns[ZONE_NORMAL] = max_low_pfn; @@ -156,14 +157,9 @@ int set_memory_decrypted(unsigned long addr, int numpages) } /* are we a protected virtualization guest? */ -bool sev_active(void) -{ - return is_prot_virt_guest(); -} - bool force_dma_unencrypted(struct device *dev) { - return sev_active(); + return is_prot_virt_guest(); } /* protected virtualization */ @@ -296,10 +292,8 @@ void arch_remove_memory(int nid, u64 start, u64 size, { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; - struct zone *zone; - zone = page_zone(pfn_to_page(start_pfn)); - __remove_pages(zone, start_pfn, nr_pages, altmap); + __remove_pages(start_pfn, nr_pages, altmap); vmem_remove_mapping(start, size); } #endif /* CONFIG_MEMORY_HOTPLUG */ diff --git a/arch/s390/mm/kasan_init.c b/arch/s390/mm/kasan_init.c index 0c1f257be422..06345616a646 100644 --- a/arch/s390/mm/kasan_init.c +++ b/arch/s390/mm/kasan_init.c @@ -82,7 +82,8 @@ static pte_t * __init kasan_early_pte_alloc(void) enum populate_mode { POPULATE_ONE2ONE, POPULATE_MAP, - POPULATE_ZERO_SHADOW + POPULATE_ZERO_SHADOW, + POPULATE_SHALLOW }; static void __init kasan_early_vmemmap_populate(unsigned long address, unsigned long end, @@ -116,6 +117,12 @@ static void __init kasan_early_vmemmap_populate(unsigned long address, pgd_populate(&init_mm, pg_dir, p4_dir); } + if (IS_ENABLED(CONFIG_KASAN_S390_4_LEVEL_PAGING) && + mode == POPULATE_SHALLOW) { + address = (address + P4D_SIZE) & P4D_MASK; + continue; + } + p4_dir = p4d_offset(pg_dir, address); if (p4d_none(*p4_dir)) { if (mode == POPULATE_ZERO_SHADOW && @@ -130,6 +137,12 @@ static void __init kasan_early_vmemmap_populate(unsigned long address, p4d_populate(&init_mm, p4_dir, pu_dir); } + if (!IS_ENABLED(CONFIG_KASAN_S390_4_LEVEL_PAGING) && + mode == POPULATE_SHALLOW) { + address = (address + PUD_SIZE) & PUD_MASK; + continue; + } + pu_dir = pud_offset(p4_dir, address); if (pud_none(*pu_dir)) { if (mode == POPULATE_ZERO_SHADOW && @@ -195,6 +208,9 @@ static void __init kasan_early_vmemmap_populate(unsigned long address, page = kasan_early_shadow_page; pte_val(*pt_dir) = __pa(page) | pgt_prot_zero; break; + case POPULATE_SHALLOW: + /* should never happen */ + break; } } address += PAGE_SIZE; @@ -236,18 +252,6 @@ static void __init kasan_early_detect_facilities(void) } } -static unsigned long __init get_mem_detect_end(void) -{ - unsigned long start; - unsigned long end; - - if (mem_detect.count) { - __get_mem_detect_block(mem_detect.count - 1, &start, &end); - return end; - } - return 0; -} - void __init kasan_early_init(void) { unsigned long untracked_mem_end; @@ -273,6 +277,8 @@ void __init kasan_early_init(void) /* respect mem= cmdline parameter */ if (memory_end_set && memsize > memory_end) memsize = memory_end; + if (IS_ENABLED(CONFIG_CRASH_DUMP) && OLDMEM_BASE) + memsize = min(memsize, OLDMEM_SIZE); memsize = min(memsize, KASAN_SHADOW_START); if (IS_ENABLED(CONFIG_KASAN_S390_4_LEVEL_PAGING)) { @@ -323,22 +329,50 @@ void __init kasan_early_init(void) init_mm.pgd = early_pg_dir; /* * Current memory layout: - * +- 0 -------------+ +- shadow start -+ - * | 1:1 ram mapping | /| 1/8 ram | - * +- end of ram ----+ / +----------------+ - * | ... gap ... |/ | kasan | - * +- shadow start --+ | zero | - * | 1/8 addr space | | page | - * +- shadow end -+ | mapping | - * | ... gap ... |\ | (untracked) | - * +- modules vaddr -+ \ +----------------+ - * | 2Gb | \| unmapped | allocated per module - * +-----------------+ +- shadow end ---+ + * +- 0 -------------+ +- shadow start -+ + * | 1:1 ram mapping | /| 1/8 ram | + * | | / | | + * +- end of ram ----+ / +----------------+ + * | ... gap ... | / | | + * | |/ | kasan | + * +- shadow start --+ | zero | + * | 1/8 addr space | | page | + * +- shadow end -+ | mapping | + * | ... gap ... |\ | (untracked) | + * +- vmalloc area -+ \ | | + * | vmalloc_size | \ | | + * +- modules vaddr -+ \ +----------------+ + * | 2Gb | \| unmapped | allocated per module + * +-----------------+ +- shadow end ---+ + * + * Current memory layout (KASAN_VMALLOC): + * +- 0 -------------+ +- shadow start -+ + * | 1:1 ram mapping | /| 1/8 ram | + * | | / | | + * +- end of ram ----+ / +----------------+ + * | ... gap ... | / | kasan | + * | |/ | zero | + * +- shadow start --+ | page | + * | 1/8 addr space | | mapping | + * +- shadow end -+ | (untracked) | + * | ... gap ... |\ | | + * +- vmalloc area -+ \ +- vmalloc area -+ + * | vmalloc_size | \ |shallow populate| + * +- modules vaddr -+ \ +- modules area -+ + * | 2Gb | \|shallow populate| + * +-----------------+ +- shadow end ---+ */ /* populate kasan shadow (for identity mapping and zero page mapping) */ kasan_early_vmemmap_populate(__sha(0), __sha(memsize), POPULATE_MAP); if (IS_ENABLED(CONFIG_MODULES)) untracked_mem_end = vmax - MODULES_LEN; + if (IS_ENABLED(CONFIG_KASAN_VMALLOC)) { + untracked_mem_end = vmax - vmalloc_size - MODULES_LEN; + /* shallowly populate kasan shadow for vmalloc and modules */ + kasan_early_vmemmap_populate(__sha(untracked_mem_end), + __sha(vmax), POPULATE_SHALLOW); + } + /* populate kasan shadow for untracked memory */ kasan_early_vmemmap_populate(__sha(max_physmem_end), __sha(untracked_mem_end), POPULATE_ZERO_SHADOW); diff --git a/arch/s390/mm/maccess.c b/arch/s390/mm/maccess.c index 1864a8bb9622..de7ca4b6718f 100644 --- a/arch/s390/mm/maccess.c +++ b/arch/s390/mm/maccess.c @@ -70,7 +70,7 @@ void notrace s390_kernel_write(void *dst, const void *src, size_t size) spin_unlock_irqrestore(&s390_kernel_write_lock, flags); } -static int __memcpy_real(void *dest, void *src, size_t count) +static int __no_sanitize_address __memcpy_real(void *dest, void *src, size_t count) { register unsigned long _dest asm("2") = (unsigned long) dest; register unsigned long _len1 asm("3") = (unsigned long) count; @@ -91,19 +91,23 @@ static int __memcpy_real(void *dest, void *src, size_t count) return rc; } -static unsigned long _memcpy_real(unsigned long dest, unsigned long src, - unsigned long count) +static unsigned long __no_sanitize_address _memcpy_real(unsigned long dest, + unsigned long src, + unsigned long count) { int irqs_disabled, rc; unsigned long flags; if (!count) return 0; - flags = __arch_local_irq_stnsm(0xf8UL); + flags = arch_local_irq_save(); irqs_disabled = arch_irqs_disabled_flags(flags); if (!irqs_disabled) trace_hardirqs_off(); + __arch_local_irq_stnsm(0xf8); // disable DAT rc = __memcpy_real((void *) dest, (void *) src, (size_t) count); + if (flags & PSW_MASK_DAT) + __arch_local_irq_stosm(0x04); // enable DAT if (!irqs_disabled) trace_hardirqs_on(); __arch_local_irq_ssm(flags); @@ -115,9 +119,15 @@ static unsigned long _memcpy_real(unsigned long dest, unsigned long src, */ int memcpy_real(void *dest, void *src, size_t count) { - if (S390_lowcore.nodat_stack != 0) - return CALL_ON_STACK(_memcpy_real, S390_lowcore.nodat_stack, - 3, dest, src, count); + int rc; + + if (S390_lowcore.nodat_stack != 0) { + preempt_disable(); + rc = CALL_ON_STACK(_memcpy_real, S390_lowcore.nodat_stack, 3, + dest, src, count); + preempt_enable(); + return rc; + } /* * This is a really early memcpy_real call, the stacks are * not set up yet. Just call _memcpy_real on the early boot diff --git a/arch/s390/mm/page-states.c b/arch/s390/mm/page-states.c index dc3cede7f2ec..fc141893d028 100644 --- a/arch/s390/mm/page-states.c +++ b/arch/s390/mm/page-states.c @@ -21,17 +21,11 @@ static int cmma_flag = 1; static int __init cmma(char *str) { - char *parm; + bool enabled; - parm = strstrip(str); - if (strcmp(parm, "yes") == 0 || strcmp(parm, "on") == 0) { - cmma_flag = 1; - return 1; - } - cmma_flag = 0; - if (strcmp(parm, "no") == 0 || strcmp(parm, "off") == 0) - return 1; - return 0; + if (!kstrtobool(str, &enabled)) + cmma_flag = enabled; + return 1; } __setup("cmma=", cmma); diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c index 54fcdf66ae96..3dd253f81a77 100644 --- a/arch/s390/mm/pgalloc.c +++ b/arch/s390/mm/pgalloc.c @@ -210,7 +210,7 @@ unsigned long *page_table_alloc(struct mm_struct *mm) page = alloc_page(GFP_KERNEL); if (!page) return NULL; - if (!pgtable_page_ctor(page)) { + if (!pgtable_pte_page_ctor(page)) { __free_page(page); return NULL; } @@ -256,7 +256,7 @@ void page_table_free(struct mm_struct *mm, unsigned long *table) atomic_xor_bits(&page->_refcount, 3U << 24); } - pgtable_page_dtor(page); + pgtable_pte_page_dtor(page); __free_page(page); } @@ -308,7 +308,7 @@ void __tlb_remove_table(void *_table) case 3: /* 4K page table with pgstes */ if (mask & 3) atomic_xor_bits(&page->_refcount, 3 << 24); - pgtable_page_dtor(page); + pgtable_pte_page_dtor(page); __free_page(page); break; } diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index e636728ab452..8d2134136290 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -23,6 +23,8 @@ #include <linux/filter.h> #include <linux/init.h> #include <linux/bpf.h> +#include <linux/mm.h> +#include <linux/kernel.h> #include <asm/cacheflush.h> #include <asm/dis.h> #include <asm/facility.h> @@ -38,10 +40,11 @@ struct bpf_jit { int size; /* Size of program and literal pool */ int size_prg; /* Size of program */ int prg; /* Current position in program */ - int lit_start; /* Start of literal pool */ - int lit; /* Current position in literal pool */ + int lit32_start; /* Start of 32-bit literal pool */ + int lit32; /* Current position in 32-bit literal pool */ + int lit64_start; /* Start of 64-bit literal pool */ + int lit64; /* Current position in 64-bit literal pool */ int base_ip; /* Base address for literal pool */ - int ret0_ip; /* Address of return 0 */ int exit_ip; /* Address of exit */ int r1_thunk_ip; /* Address of expoline thunk for 'br %r1' */ int r14_thunk_ip; /* Address of expoline thunk for 'br %r14' */ @@ -49,14 +52,10 @@ struct bpf_jit { int labels[1]; /* Labels for local jumps */ }; -#define BPF_SIZE_MAX 0xffff /* Max size for program (16 bit branches) */ - -#define SEEN_MEM (1 << 0) /* use mem[] for temporary storage */ -#define SEEN_RET0 (1 << 1) /* ret0_ip points to a valid return 0 */ -#define SEEN_LITERAL (1 << 2) /* code uses literals */ -#define SEEN_FUNC (1 << 3) /* calls C functions */ -#define SEEN_TAIL_CALL (1 << 4) /* code uses tail calls */ -#define SEEN_REG_AX (1 << 5) /* code uses constant blinding */ +#define SEEN_MEM BIT(0) /* use mem[] for temporary storage */ +#define SEEN_LITERAL BIT(1) /* code uses literals */ +#define SEEN_FUNC BIT(2) /* calls C functions */ +#define SEEN_TAIL_CALL BIT(3) /* code uses tail calls */ #define SEEN_STACK (SEEN_FUNC | SEEN_MEM) /* @@ -131,13 +130,13 @@ static inline void reg_set_seen(struct bpf_jit *jit, u32 b1) #define _EMIT2(op) \ ({ \ if (jit->prg_buf) \ - *(u16 *) (jit->prg_buf + jit->prg) = op; \ + *(u16 *) (jit->prg_buf + jit->prg) = (op); \ jit->prg += 2; \ }) #define EMIT2(op, b1, b2) \ ({ \ - _EMIT2(op | reg(b1, b2)); \ + _EMIT2((op) | reg(b1, b2)); \ REG_SET_SEEN(b1); \ REG_SET_SEEN(b2); \ }) @@ -145,20 +144,20 @@ static inline void reg_set_seen(struct bpf_jit *jit, u32 b1) #define _EMIT4(op) \ ({ \ if (jit->prg_buf) \ - *(u32 *) (jit->prg_buf + jit->prg) = op; \ + *(u32 *) (jit->prg_buf + jit->prg) = (op); \ jit->prg += 4; \ }) #define EMIT4(op, b1, b2) \ ({ \ - _EMIT4(op | reg(b1, b2)); \ + _EMIT4((op) | reg(b1, b2)); \ REG_SET_SEEN(b1); \ REG_SET_SEEN(b2); \ }) #define EMIT4_RRF(op, b1, b2, b3) \ ({ \ - _EMIT4(op | reg_high(b3) << 8 | reg(b1, b2)); \ + _EMIT4((op) | reg_high(b3) << 8 | reg(b1, b2)); \ REG_SET_SEEN(b1); \ REG_SET_SEEN(b2); \ REG_SET_SEEN(b3); \ @@ -167,13 +166,13 @@ static inline void reg_set_seen(struct bpf_jit *jit, u32 b1) #define _EMIT4_DISP(op, disp) \ ({ \ unsigned int __disp = (disp) & 0xfff; \ - _EMIT4(op | __disp); \ + _EMIT4((op) | __disp); \ }) #define EMIT4_DISP(op, b1, b2, disp) \ ({ \ - _EMIT4_DISP(op | reg_high(b1) << 16 | \ - reg_high(b2) << 8, disp); \ + _EMIT4_DISP((op) | reg_high(b1) << 16 | \ + reg_high(b2) << 8, (disp)); \ REG_SET_SEEN(b1); \ REG_SET_SEEN(b2); \ }) @@ -181,21 +180,27 @@ static inline void reg_set_seen(struct bpf_jit *jit, u32 b1) #define EMIT4_IMM(op, b1, imm) \ ({ \ unsigned int __imm = (imm) & 0xffff; \ - _EMIT4(op | reg_high(b1) << 16 | __imm); \ + _EMIT4((op) | reg_high(b1) << 16 | __imm); \ REG_SET_SEEN(b1); \ }) #define EMIT4_PCREL(op, pcrel) \ ({ \ long __pcrel = ((pcrel) >> 1) & 0xffff; \ - _EMIT4(op | __pcrel); \ + _EMIT4((op) | __pcrel); \ +}) + +#define EMIT4_PCREL_RIC(op, mask, target) \ +({ \ + int __rel = ((target) - jit->prg) / 2; \ + _EMIT4((op) | (mask) << 20 | (__rel & 0xffff)); \ }) #define _EMIT6(op1, op2) \ ({ \ if (jit->prg_buf) { \ - *(u32 *) (jit->prg_buf + jit->prg) = op1; \ - *(u16 *) (jit->prg_buf + jit->prg + 4) = op2; \ + *(u32 *) (jit->prg_buf + jit->prg) = (op1); \ + *(u16 *) (jit->prg_buf + jit->prg + 4) = (op2); \ } \ jit->prg += 6; \ }) @@ -203,20 +208,20 @@ static inline void reg_set_seen(struct bpf_jit *jit, u32 b1) #define _EMIT6_DISP(op1, op2, disp) \ ({ \ unsigned int __disp = (disp) & 0xfff; \ - _EMIT6(op1 | __disp, op2); \ + _EMIT6((op1) | __disp, op2); \ }) #define _EMIT6_DISP_LH(op1, op2, disp) \ ({ \ - u32 _disp = (u32) disp; \ + u32 _disp = (u32) (disp); \ unsigned int __disp_h = _disp & 0xff000; \ unsigned int __disp_l = _disp & 0x00fff; \ - _EMIT6(op1 | __disp_l, op2 | __disp_h >> 4); \ + _EMIT6((op1) | __disp_l, (op2) | __disp_h >> 4); \ }) #define EMIT6_DISP_LH(op1, op2, b1, b2, b3, disp) \ ({ \ - _EMIT6_DISP_LH(op1 | reg(b1, b2) << 16 | \ + _EMIT6_DISP_LH((op1) | reg(b1, b2) << 16 | \ reg_high(b3) << 8, op2, disp); \ REG_SET_SEEN(b1); \ REG_SET_SEEN(b2); \ @@ -226,8 +231,8 @@ static inline void reg_set_seen(struct bpf_jit *jit, u32 b1) #define EMIT6_PCREL_LABEL(op1, op2, b1, b2, label, mask) \ ({ \ int rel = (jit->labels[label] - jit->prg) >> 1; \ - _EMIT6(op1 | reg(b1, b2) << 16 | (rel & 0xffff), \ - op2 | mask << 12); \ + _EMIT6((op1) | reg(b1, b2) << 16 | (rel & 0xffff), \ + (op2) | (mask) << 12); \ REG_SET_SEEN(b1); \ REG_SET_SEEN(b2); \ }) @@ -235,68 +240,83 @@ static inline void reg_set_seen(struct bpf_jit *jit, u32 b1) #define EMIT6_PCREL_IMM_LABEL(op1, op2, b1, imm, label, mask) \ ({ \ int rel = (jit->labels[label] - jit->prg) >> 1; \ - _EMIT6(op1 | (reg_high(b1) | mask) << 16 | \ - (rel & 0xffff), op2 | (imm & 0xff) << 8); \ + _EMIT6((op1) | (reg_high(b1) | (mask)) << 16 | \ + (rel & 0xffff), (op2) | ((imm) & 0xff) << 8); \ REG_SET_SEEN(b1); \ - BUILD_BUG_ON(((unsigned long) imm) > 0xff); \ + BUILD_BUG_ON(((unsigned long) (imm)) > 0xff); \ }) #define EMIT6_PCREL(op1, op2, b1, b2, i, off, mask) \ ({ \ /* Branch instruction needs 6 bytes */ \ - int rel = (addrs[i + off + 1] - (addrs[i + 1] - 6)) / 2;\ - _EMIT6(op1 | reg(b1, b2) << 16 | (rel & 0xffff), op2 | mask); \ + int rel = (addrs[(i) + (off) + 1] - (addrs[(i) + 1] - 6)) / 2;\ + _EMIT6((op1) | reg(b1, b2) << 16 | (rel & 0xffff), (op2) | (mask));\ REG_SET_SEEN(b1); \ REG_SET_SEEN(b2); \ }) #define EMIT6_PCREL_RILB(op, b, target) \ ({ \ - int rel = (target - jit->prg) / 2; \ - _EMIT6(op | reg_high(b) << 16 | rel >> 16, rel & 0xffff); \ + unsigned int rel = (int)((target) - jit->prg) / 2; \ + _EMIT6((op) | reg_high(b) << 16 | rel >> 16, rel & 0xffff);\ REG_SET_SEEN(b); \ }) #define EMIT6_PCREL_RIL(op, target) \ ({ \ - int rel = (target - jit->prg) / 2; \ - _EMIT6(op | rel >> 16, rel & 0xffff); \ + unsigned int rel = (int)((target) - jit->prg) / 2; \ + _EMIT6((op) | rel >> 16, rel & 0xffff); \ +}) + +#define EMIT6_PCREL_RILC(op, mask, target) \ +({ \ + EMIT6_PCREL_RIL((op) | (mask) << 20, (target)); \ }) #define _EMIT6_IMM(op, imm) \ ({ \ unsigned int __imm = (imm); \ - _EMIT6(op | (__imm >> 16), __imm & 0xffff); \ + _EMIT6((op) | (__imm >> 16), __imm & 0xffff); \ }) #define EMIT6_IMM(op, b1, imm) \ ({ \ - _EMIT6_IMM(op | reg_high(b1) << 16, imm); \ + _EMIT6_IMM((op) | reg_high(b1) << 16, imm); \ REG_SET_SEEN(b1); \ }) -#define EMIT_CONST_U32(val) \ +#define _EMIT_CONST_U32(val) \ ({ \ unsigned int ret; \ - ret = jit->lit - jit->base_ip; \ - jit->seen |= SEEN_LITERAL; \ + ret = jit->lit32; \ if (jit->prg_buf) \ - *(u32 *) (jit->prg_buf + jit->lit) = (u32) val; \ - jit->lit += 4; \ + *(u32 *)(jit->prg_buf + jit->lit32) = (u32)(val);\ + jit->lit32 += 4; \ ret; \ }) -#define EMIT_CONST_U64(val) \ +#define EMIT_CONST_U32(val) \ ({ \ - unsigned int ret; \ - ret = jit->lit - jit->base_ip; \ jit->seen |= SEEN_LITERAL; \ + _EMIT_CONST_U32(val) - jit->base_ip; \ +}) + +#define _EMIT_CONST_U64(val) \ +({ \ + unsigned int ret; \ + ret = jit->lit64; \ if (jit->prg_buf) \ - *(u64 *) (jit->prg_buf + jit->lit) = (u64) val; \ - jit->lit += 8; \ + *(u64 *)(jit->prg_buf + jit->lit64) = (u64)(val);\ + jit->lit64 += 8; \ ret; \ }) +#define EMIT_CONST_U64(val) \ +({ \ + jit->seen |= SEEN_LITERAL; \ + _EMIT_CONST_U64(val) - jit->base_ip; \ +}) + #define EMIT_ZERO(b1) \ ({ \ if (!fp->aux->verifier_zext) { \ @@ -307,6 +327,67 @@ static inline void reg_set_seen(struct bpf_jit *jit, u32 b1) }) /* + * Return whether this is the first pass. The first pass is special, since we + * don't know any sizes yet, and thus must be conservative. + */ +static bool is_first_pass(struct bpf_jit *jit) +{ + return jit->size == 0; +} + +/* + * Return whether this is the code generation pass. The code generation pass is + * special, since we should change as little as possible. + */ +static bool is_codegen_pass(struct bpf_jit *jit) +{ + return jit->prg_buf; +} + +/* + * Return whether "rel" can be encoded as a short PC-relative offset + */ +static bool is_valid_rel(int rel) +{ + return rel >= -65536 && rel <= 65534; +} + +/* + * Return whether "off" can be reached using a short PC-relative offset + */ +static bool can_use_rel(struct bpf_jit *jit, int off) +{ + return is_valid_rel(off - jit->prg); +} + +/* + * Return whether given displacement can be encoded using + * Long-Displacement Facility + */ +static bool is_valid_ldisp(int disp) +{ + return disp >= -524288 && disp <= 524287; +} + +/* + * Return whether the next 32-bit literal pool entry can be referenced using + * Long-Displacement Facility + */ +static bool can_use_ldisp_for_lit32(struct bpf_jit *jit) +{ + return is_valid_ldisp(jit->lit32 - jit->base_ip); +} + +/* + * Return whether the next 64-bit literal pool entry can be referenced using + * Long-Displacement Facility + */ +static bool can_use_ldisp_for_lit64(struct bpf_jit *jit) +{ + return is_valid_ldisp(jit->lit64 - jit->base_ip); +} + +/* * Fill whole space with illegal instructions */ static void jit_fill_hole(void *area, unsigned int size) @@ -383,9 +464,18 @@ static int get_end(struct bpf_jit *jit, int start) */ static void save_restore_regs(struct bpf_jit *jit, int op, u32 stack_depth) { - + const int last = 15, save_restore_size = 6; int re = 6, rs; + if (is_first_pass(jit)) { + /* + * We don't know yet which registers are used. Reserve space + * conservatively. + */ + jit->prg += (last - re + 1) * save_restore_size; + return; + } + do { rs = get_start(jit, re); if (!rs) @@ -396,7 +486,7 @@ static void save_restore_regs(struct bpf_jit *jit, int op, u32 stack_depth) else restore_regs(jit, rs, re, stack_depth); re++; - } while (re <= 15); + } while (re <= last); } /* @@ -420,21 +510,28 @@ static void bpf_jit_prologue(struct bpf_jit *jit, u32 stack_depth) /* Save registers */ save_restore_regs(jit, REGS_SAVE, stack_depth); /* Setup literal pool */ - if (jit->seen & SEEN_LITERAL) { - /* basr %r13,0 */ - EMIT2(0x0d00, REG_L, REG_0); - jit->base_ip = jit->prg; + if (is_first_pass(jit) || (jit->seen & SEEN_LITERAL)) { + if (!is_first_pass(jit) && + is_valid_ldisp(jit->size - (jit->prg + 2))) { + /* basr %l,0 */ + EMIT2(0x0d00, REG_L, REG_0); + jit->base_ip = jit->prg; + } else { + /* larl %l,lit32_start */ + EMIT6_PCREL_RILB(0xc0000000, REG_L, jit->lit32_start); + jit->base_ip = jit->lit32_start; + } } /* Setup stack and backchain */ - if (jit->seen & SEEN_STACK) { - if (jit->seen & SEEN_FUNC) + if (is_first_pass(jit) || (jit->seen & SEEN_STACK)) { + if (is_first_pass(jit) || (jit->seen & SEEN_FUNC)) /* lgr %w1,%r15 (backchain) */ EMIT4(0xb9040000, REG_W1, REG_15); /* la %bfp,STK_160_UNUSED(%r15) (BPF frame pointer) */ EMIT4_DISP(0x41000000, BPF_REG_FP, REG_15, STK_160_UNUSED); /* aghi %r15,-STK_OFF */ EMIT4_IMM(0xa70b0000, REG_15, -(STK_OFF + stack_depth)); - if (jit->seen & SEEN_FUNC) + if (is_first_pass(jit) || (jit->seen & SEEN_FUNC)) /* stg %w1,152(%r15) (backchain) */ EMIT6_DISP_LH(0xe3000000, 0x0024, REG_W1, REG_0, REG_15, 152); @@ -446,12 +543,6 @@ static void bpf_jit_prologue(struct bpf_jit *jit, u32 stack_depth) */ static void bpf_jit_epilogue(struct bpf_jit *jit, u32 stack_depth) { - /* Return 0 */ - if (jit->seen & SEEN_RET0) { - jit->ret0_ip = jit->prg; - /* lghi %b0,0 */ - EMIT4_IMM(0xa7090000, BPF_REG_0, 0); - } jit->exit_ip = jit->prg; /* Load exit code: lgr %r2,%b0 */ EMIT4(0xb9040000, REG_2, BPF_REG_0); @@ -476,7 +567,7 @@ static void bpf_jit_epilogue(struct bpf_jit *jit, u32 stack_depth) _EMIT2(0x07fe); if (__is_defined(CC_USING_EXPOLINE) && !nospec_disable && - (jit->seen & SEEN_FUNC)) { + (is_first_pass(jit) || (jit->seen & SEEN_FUNC))) { jit->r1_thunk_ip = jit->prg; /* Generate __s390_indirect_jump_r1 thunk */ if (test_facility(35)) { @@ -502,19 +593,18 @@ static void bpf_jit_epilogue(struct bpf_jit *jit, u32 stack_depth) * NOTE: Use noinline because for gcov (-fprofile-arcs) gcc allocates a lot of * stack space for the large switch statement. */ -static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i) +static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, + int i, bool extra_pass) { struct bpf_insn *insn = &fp->insnsi[i]; - int jmp_off, last, insn_count = 1; u32 dst_reg = insn->dst_reg; u32 src_reg = insn->src_reg; + int last, insn_count = 1; u32 *addrs = jit->addrs; s32 imm = insn->imm; s16 off = insn->off; unsigned int mask; - if (dst_reg == BPF_REG_AX || src_reg == BPF_REG_AX) - jit->seen |= SEEN_REG_AX; switch (insn->code) { /* * BPF_MOV @@ -548,9 +638,8 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i u64 imm64; imm64 = (u64)(u32) insn[0].imm | ((u64)(u32) insn[1].imm) << 32; - /* lg %dst,<d(imm)>(%l) */ - EMIT6_DISP_LH(0xe3000000, 0x0004, dst_reg, REG_0, REG_L, - EMIT_CONST_U64(imm64)); + /* lgrl %dst,imm */ + EMIT6_PCREL_RILB(0xc4080000, dst_reg, _EMIT_CONST_U64(imm64)); insn_count = 2; break; } @@ -679,9 +768,18 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i EMIT4_IMM(0xa7080000, REG_W0, 0); /* lr %w1,%dst */ EMIT2(0x1800, REG_W1, dst_reg); - /* dl %w0,<d(imm)>(%l) */ - EMIT6_DISP_LH(0xe3000000, 0x0097, REG_W0, REG_0, REG_L, - EMIT_CONST_U32(imm)); + if (!is_first_pass(jit) && can_use_ldisp_for_lit32(jit)) { + /* dl %w0,<d(imm)>(%l) */ + EMIT6_DISP_LH(0xe3000000, 0x0097, REG_W0, REG_0, REG_L, + EMIT_CONST_U32(imm)); + } else { + /* lgfrl %dst,imm */ + EMIT6_PCREL_RILB(0xc40c0000, dst_reg, + _EMIT_CONST_U32(imm)); + jit->seen |= SEEN_LITERAL; + /* dlr %w0,%dst */ + EMIT4(0xb9970000, REG_W0, dst_reg); + } /* llgfr %dst,%rc */ EMIT4(0xb9160000, dst_reg, rc_reg); if (insn_is_zext(&insn[1])) @@ -703,9 +801,18 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i EMIT4_IMM(0xa7090000, REG_W0, 0); /* lgr %w1,%dst */ EMIT4(0xb9040000, REG_W1, dst_reg); - /* dlg %w0,<d(imm)>(%l) */ - EMIT6_DISP_LH(0xe3000000, 0x0087, REG_W0, REG_0, REG_L, - EMIT_CONST_U64(imm)); + if (!is_first_pass(jit) && can_use_ldisp_for_lit64(jit)) { + /* dlg %w0,<d(imm)>(%l) */ + EMIT6_DISP_LH(0xe3000000, 0x0087, REG_W0, REG_0, REG_L, + EMIT_CONST_U64(imm)); + } else { + /* lgrl %dst,imm */ + EMIT6_PCREL_RILB(0xc4080000, dst_reg, + _EMIT_CONST_U64(imm)); + jit->seen |= SEEN_LITERAL; + /* dlgr %w0,%dst */ + EMIT4(0xb9870000, REG_W0, dst_reg); + } /* lgr %dst,%rc */ EMIT4(0xb9040000, dst_reg, rc_reg); break; @@ -728,9 +835,19 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i EMIT_ZERO(dst_reg); break; case BPF_ALU64 | BPF_AND | BPF_K: /* dst = dst & imm */ - /* ng %dst,<d(imm)>(%l) */ - EMIT6_DISP_LH(0xe3000000, 0x0080, dst_reg, REG_0, REG_L, - EMIT_CONST_U64(imm)); + if (!is_first_pass(jit) && can_use_ldisp_for_lit64(jit)) { + /* ng %dst,<d(imm)>(%l) */ + EMIT6_DISP_LH(0xe3000000, 0x0080, + dst_reg, REG_0, REG_L, + EMIT_CONST_U64(imm)); + } else { + /* lgrl %w0,imm */ + EMIT6_PCREL_RILB(0xc4080000, REG_W0, + _EMIT_CONST_U64(imm)); + jit->seen |= SEEN_LITERAL; + /* ngr %dst,%w0 */ + EMIT4(0xb9800000, dst_reg, REG_W0); + } break; /* * BPF_OR @@ -750,9 +867,19 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i EMIT_ZERO(dst_reg); break; case BPF_ALU64 | BPF_OR | BPF_K: /* dst = dst | imm */ - /* og %dst,<d(imm)>(%l) */ - EMIT6_DISP_LH(0xe3000000, 0x0081, dst_reg, REG_0, REG_L, - EMIT_CONST_U64(imm)); + if (!is_first_pass(jit) && can_use_ldisp_for_lit64(jit)) { + /* og %dst,<d(imm)>(%l) */ + EMIT6_DISP_LH(0xe3000000, 0x0081, + dst_reg, REG_0, REG_L, + EMIT_CONST_U64(imm)); + } else { + /* lgrl %w0,imm */ + EMIT6_PCREL_RILB(0xc4080000, REG_W0, + _EMIT_CONST_U64(imm)); + jit->seen |= SEEN_LITERAL; + /* ogr %dst,%w0 */ + EMIT4(0xb9810000, dst_reg, REG_W0); + } break; /* * BPF_XOR @@ -774,9 +901,19 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i EMIT_ZERO(dst_reg); break; case BPF_ALU64 | BPF_XOR | BPF_K: /* dst = dst ^ imm */ - /* xg %dst,<d(imm)>(%l) */ - EMIT6_DISP_LH(0xe3000000, 0x0082, dst_reg, REG_0, REG_L, - EMIT_CONST_U64(imm)); + if (!is_first_pass(jit) && can_use_ldisp_for_lit64(jit)) { + /* xg %dst,<d(imm)>(%l) */ + EMIT6_DISP_LH(0xe3000000, 0x0082, + dst_reg, REG_0, REG_L, + EMIT_CONST_U64(imm)); + } else { + /* lgrl %w0,imm */ + EMIT6_PCREL_RILB(0xc4080000, REG_W0, + _EMIT_CONST_U64(imm)); + jit->seen |= SEEN_LITERAL; + /* xgr %dst,%w0 */ + EMIT4(0xb9820000, dst_reg, REG_W0); + } break; /* * BPF_LSH @@ -863,7 +1000,7 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i break; case BPF_ALU64 | BPF_NEG: /* dst = -dst */ /* lcgr %dst,%dst */ - EMIT4(0xb9130000, dst_reg, dst_reg); + EMIT4(0xb9030000, dst_reg, dst_reg); break; /* * BPF_FROM_BE/LE @@ -1011,16 +1148,19 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i */ case BPF_JMP | BPF_CALL: { - /* - * b0 = (__bpf_call_base + imm)(b1, b2, b3, b4, b5) - */ - const u64 func = (u64)__bpf_call_base + imm; + u64 func; + bool func_addr_fixed; + int ret; + + ret = bpf_jit_get_func_addr(fp, insn, extra_pass, + &func, &func_addr_fixed); + if (ret < 0) + return -1; REG_SET_SEEN(BPF_REG_5); jit->seen |= SEEN_FUNC; - /* lg %w1,<d(imm)>(%l) */ - EMIT6_DISP_LH(0xe3000000, 0x0004, REG_W1, REG_0, REG_L, - EMIT_CONST_U64(func)); + /* lgrl %w1,func */ + EMIT6_PCREL_RILB(0xc4080000, REG_W1, _EMIT_CONST_U64(func)); if (__is_defined(CC_USING_EXPOLINE) && !nospec_disable) { /* brasl %r14,__s390_indirect_jump_r1 */ EMIT6_PCREL_RILB(0xc0050000, REG_14, jit->r1_thunk_ip); @@ -1049,9 +1189,17 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i /* llgf %w1,map.max_entries(%b2) */ EMIT6_DISP_LH(0xe3000000, 0x0016, REG_W1, REG_0, BPF_REG_2, offsetof(struct bpf_array, map.max_entries)); - /* clgrj %b3,%w1,0xa,label0: if %b3 >= %w1 goto out */ - EMIT6_PCREL_LABEL(0xec000000, 0x0065, BPF_REG_3, - REG_W1, 0, 0xa); + /* if ((u32)%b3 >= (u32)%w1) goto out; */ + if (!is_first_pass(jit) && can_use_rel(jit, jit->labels[0])) { + /* clrj %b3,%w1,0xa,label0 */ + EMIT6_PCREL_LABEL(0xec000000, 0x0077, BPF_REG_3, + REG_W1, 0, 0xa); + } else { + /* clr %b3,%w1 */ + EMIT2(0x1500, BPF_REG_3, REG_W1); + /* brcl 0xa,label0 */ + EMIT6_PCREL_RILC(0xc0040000, 0xa, jit->labels[0]); + } /* * if (tail_call_cnt++ > MAX_TAIL_CALL_CNT) @@ -1066,9 +1214,16 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i EMIT4_IMM(0xa7080000, REG_W0, 1); /* laal %w1,%w0,off(%r15) */ EMIT6_DISP_LH(0xeb000000, 0x00fa, REG_W1, REG_W0, REG_15, off); - /* clij %w1,MAX_TAIL_CALL_CNT,0x2,label0 */ - EMIT6_PCREL_IMM_LABEL(0xec000000, 0x007f, REG_W1, - MAX_TAIL_CALL_CNT, 0, 0x2); + if (!is_first_pass(jit) && can_use_rel(jit, jit->labels[0])) { + /* clij %w1,MAX_TAIL_CALL_CNT,0x2,label0 */ + EMIT6_PCREL_IMM_LABEL(0xec000000, 0x007f, REG_W1, + MAX_TAIL_CALL_CNT, 0, 0x2); + } else { + /* clfi %w1,MAX_TAIL_CALL_CNT */ + EMIT6_IMM(0xc20f0000, REG_W1, MAX_TAIL_CALL_CNT); + /* brcl 0x2,label0 */ + EMIT6_PCREL_RILC(0xc0040000, 0x2, jit->labels[0]); + } /* * prog = array->ptrs[index]; @@ -1076,13 +1231,20 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i * goto out; */ - /* sllg %r1,%b3,3: %r1 = index * 8 */ - EMIT6_DISP_LH(0xeb000000, 0x000d, REG_1, BPF_REG_3, REG_0, 3); - /* lg %r1,prog(%b2,%r1) */ - EMIT6_DISP_LH(0xe3000000, 0x0004, REG_1, BPF_REG_2, + /* llgfr %r1,%b3: %r1 = (u32) index */ + EMIT4(0xb9160000, REG_1, BPF_REG_3); + /* sllg %r1,%r1,3: %r1 *= 8 */ + EMIT6_DISP_LH(0xeb000000, 0x000d, REG_1, REG_1, REG_0, 3); + /* ltg %r1,prog(%b2,%r1) */ + EMIT6_DISP_LH(0xe3000000, 0x0002, REG_1, BPF_REG_2, REG_1, offsetof(struct bpf_array, ptrs)); - /* clgij %r1,0,0x8,label0 */ - EMIT6_PCREL_IMM_LABEL(0xec000000, 0x007d, REG_1, 0, 0, 0x8); + if (!is_first_pass(jit) && can_use_rel(jit, jit->labels[0])) { + /* brc 0x8,label0 */ + EMIT4_PCREL_RIC(0xa7040000, 0x8, jit->labels[0]); + } else { + /* brcl 0x8,label0 */ + EMIT6_PCREL_RILC(0xc0040000, 0x8, jit->labels[0]); + } /* * Restore registers before calling function @@ -1103,7 +1265,7 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i break; case BPF_JMP | BPF_EXIT: /* return b0 */ last = (i == fp->len - 1) ? 1 : 0; - if (last && !(jit->seen & SEEN_RET0)) + if (last) break; /* j <exit> */ EMIT4_PCREL(0xa7f40000, jit->exit_ip - jit->prg); @@ -1239,36 +1401,83 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i goto branch_oc; branch_ks: is_jmp32 = BPF_CLASS(insn->code) == BPF_JMP32; - /* lgfi %w1,imm (load sign extend imm) */ - EMIT6_IMM(0xc0010000, REG_W1, imm); - /* crj or cgrj %dst,%w1,mask,off */ - EMIT6_PCREL(0xec000000, (is_jmp32 ? 0x0076 : 0x0064), - dst_reg, REG_W1, i, off, mask); + /* cfi or cgfi %dst,imm */ + EMIT6_IMM(is_jmp32 ? 0xc20d0000 : 0xc20c0000, + dst_reg, imm); + if (!is_first_pass(jit) && + can_use_rel(jit, addrs[i + off + 1])) { + /* brc mask,off */ + EMIT4_PCREL_RIC(0xa7040000, + mask >> 12, addrs[i + off + 1]); + } else { + /* brcl mask,off */ + EMIT6_PCREL_RILC(0xc0040000, + mask >> 12, addrs[i + off + 1]); + } break; branch_ku: is_jmp32 = BPF_CLASS(insn->code) == BPF_JMP32; - /* lgfi %w1,imm (load sign extend imm) */ - EMIT6_IMM(0xc0010000, REG_W1, imm); - /* clrj or clgrj %dst,%w1,mask,off */ - EMIT6_PCREL(0xec000000, (is_jmp32 ? 0x0077 : 0x0065), - dst_reg, REG_W1, i, off, mask); + /* clfi or clgfi %dst,imm */ + EMIT6_IMM(is_jmp32 ? 0xc20f0000 : 0xc20e0000, + dst_reg, imm); + if (!is_first_pass(jit) && + can_use_rel(jit, addrs[i + off + 1])) { + /* brc mask,off */ + EMIT4_PCREL_RIC(0xa7040000, + mask >> 12, addrs[i + off + 1]); + } else { + /* brcl mask,off */ + EMIT6_PCREL_RILC(0xc0040000, + mask >> 12, addrs[i + off + 1]); + } break; branch_xs: is_jmp32 = BPF_CLASS(insn->code) == BPF_JMP32; - /* crj or cgrj %dst,%src,mask,off */ - EMIT6_PCREL(0xec000000, (is_jmp32 ? 0x0076 : 0x0064), - dst_reg, src_reg, i, off, mask); + if (!is_first_pass(jit) && + can_use_rel(jit, addrs[i + off + 1])) { + /* crj or cgrj %dst,%src,mask,off */ + EMIT6_PCREL(0xec000000, (is_jmp32 ? 0x0076 : 0x0064), + dst_reg, src_reg, i, off, mask); + } else { + /* cr or cgr %dst,%src */ + if (is_jmp32) + EMIT2(0x1900, dst_reg, src_reg); + else + EMIT4(0xb9200000, dst_reg, src_reg); + /* brcl mask,off */ + EMIT6_PCREL_RILC(0xc0040000, + mask >> 12, addrs[i + off + 1]); + } break; branch_xu: is_jmp32 = BPF_CLASS(insn->code) == BPF_JMP32; - /* clrj or clgrj %dst,%src,mask,off */ - EMIT6_PCREL(0xec000000, (is_jmp32 ? 0x0077 : 0x0065), - dst_reg, src_reg, i, off, mask); + if (!is_first_pass(jit) && + can_use_rel(jit, addrs[i + off + 1])) { + /* clrj or clgrj %dst,%src,mask,off */ + EMIT6_PCREL(0xec000000, (is_jmp32 ? 0x0077 : 0x0065), + dst_reg, src_reg, i, off, mask); + } else { + /* clr or clgr %dst,%src */ + if (is_jmp32) + EMIT2(0x1500, dst_reg, src_reg); + else + EMIT4(0xb9210000, dst_reg, src_reg); + /* brcl mask,off */ + EMIT6_PCREL_RILC(0xc0040000, + mask >> 12, addrs[i + off + 1]); + } break; branch_oc: - /* brc mask,jmp_off (branch instruction needs 4 bytes) */ - jmp_off = addrs[i + off + 1] - (addrs[i + 1] - 4); - EMIT4_PCREL(0xa7040000 | mask << 8, jmp_off); + if (!is_first_pass(jit) && + can_use_rel(jit, addrs[i + off + 1])) { + /* brc mask,off */ + EMIT4_PCREL_RIC(0xa7040000, + mask >> 12, addrs[i + off + 1]); + } else { + /* brcl mask,off */ + EMIT6_PCREL_RILC(0xc0040000, + mask >> 12, addrs[i + off + 1]); + } break; } default: /* too complex, give up */ @@ -1279,27 +1488,67 @@ branch_oc: } /* + * Return whether new i-th instruction address does not violate any invariant + */ +static bool bpf_is_new_addr_sane(struct bpf_jit *jit, int i) +{ + /* On the first pass anything goes */ + if (is_first_pass(jit)) + return true; + + /* The codegen pass must not change anything */ + if (is_codegen_pass(jit)) + return jit->addrs[i] == jit->prg; + + /* Passes in between must not increase code size */ + return jit->addrs[i] >= jit->prg; +} + +/* + * Update the address of i-th instruction + */ +static int bpf_set_addr(struct bpf_jit *jit, int i) +{ + if (!bpf_is_new_addr_sane(jit, i)) + return -1; + jit->addrs[i] = jit->prg; + return 0; +} + +/* * Compile eBPF program into s390x code */ -static int bpf_jit_prog(struct bpf_jit *jit, struct bpf_prog *fp) +static int bpf_jit_prog(struct bpf_jit *jit, struct bpf_prog *fp, + bool extra_pass) { - int i, insn_count; + int i, insn_count, lit32_size, lit64_size; - jit->lit = jit->lit_start; + jit->lit32 = jit->lit32_start; + jit->lit64 = jit->lit64_start; jit->prg = 0; bpf_jit_prologue(jit, fp->aux->stack_depth); + if (bpf_set_addr(jit, 0) < 0) + return -1; for (i = 0; i < fp->len; i += insn_count) { - insn_count = bpf_jit_insn(jit, fp, i); + insn_count = bpf_jit_insn(jit, fp, i, extra_pass); if (insn_count < 0) return -1; /* Next instruction address */ - jit->addrs[i + insn_count] = jit->prg; + if (bpf_set_addr(jit, i + insn_count) < 0) + return -1; } bpf_jit_epilogue(jit, fp->aux->stack_depth); - jit->lit_start = jit->prg; - jit->size = jit->lit; + lit32_size = jit->lit32 - jit->lit32_start; + lit64_size = jit->lit64 - jit->lit64_start; + jit->lit32_start = jit->prg; + if (lit32_size) + jit->lit32_start = ALIGN(jit->lit32_start, 4); + jit->lit64_start = jit->lit32_start + lit32_size; + if (lit64_size) + jit->lit64_start = ALIGN(jit->lit64_start, 8); + jit->size = jit->lit64_start + lit64_size; jit->size_prg = jit->prg; return 0; } @@ -1309,6 +1558,12 @@ bool bpf_jit_needs_zext(void) return true; } +struct s390_jit_data { + struct bpf_binary_header *header; + struct bpf_jit ctx; + int pass; +}; + /* * Compile eBPF program "fp" */ @@ -1316,7 +1571,9 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp) { struct bpf_prog *tmp, *orig_fp = fp; struct bpf_binary_header *header; + struct s390_jit_data *jit_data; bool tmp_blinded = false; + bool extra_pass = false; struct bpf_jit jit; int pass; @@ -1335,8 +1592,25 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp) fp = tmp; } + jit_data = fp->aux->jit_data; + if (!jit_data) { + jit_data = kzalloc(sizeof(*jit_data), GFP_KERNEL); + if (!jit_data) { + fp = orig_fp; + goto out; + } + fp->aux->jit_data = jit_data; + } + if (jit_data->ctx.addrs) { + jit = jit_data->ctx; + header = jit_data->header; + extra_pass = true; + pass = jit_data->pass + 1; + goto skip_init_ctx; + } + memset(&jit, 0, sizeof(jit)); - jit.addrs = kcalloc(fp->len + 1, sizeof(*jit.addrs), GFP_KERNEL); + jit.addrs = kvcalloc(fp->len + 1, sizeof(*jit.addrs), GFP_KERNEL); if (jit.addrs == NULL) { fp = orig_fp; goto out; @@ -1347,7 +1621,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp) * - 3: Calculate program size and addrs arrray */ for (pass = 1; pass <= 3; pass++) { - if (bpf_jit_prog(&jit, fp)) { + if (bpf_jit_prog(&jit, fp, extra_pass)) { fp = orig_fp; goto free_addrs; } @@ -1355,16 +1629,13 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp) /* * Final pass: Allocate and generate program */ - if (jit.size >= BPF_SIZE_MAX) { - fp = orig_fp; - goto free_addrs; - } - header = bpf_jit_binary_alloc(jit.size, &jit.prg_buf, 2, jit_fill_hole); + header = bpf_jit_binary_alloc(jit.size, &jit.prg_buf, 8, jit_fill_hole); if (!header) { fp = orig_fp; goto free_addrs; } - if (bpf_jit_prog(&jit, fp)) { +skip_init_ctx: + if (bpf_jit_prog(&jit, fp, extra_pass)) { bpf_jit_binary_free(header); fp = orig_fp; goto free_addrs; @@ -1373,12 +1644,24 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp) bpf_jit_dump(fp->len, jit.size, pass, jit.prg_buf); print_fn_code(jit.prg_buf, jit.size_prg); } - bpf_jit_binary_lock_ro(header); + if (!fp->is_func || extra_pass) { + bpf_jit_binary_lock_ro(header); + } else { + jit_data->header = header; + jit_data->ctx = jit; + jit_data->pass = pass; + } fp->bpf_func = (void *) jit.prg_buf; fp->jited = 1; fp->jited_len = jit.size; + + if (!fp->is_func || extra_pass) { + bpf_prog_fill_jited_linfo(fp, jit.addrs + 1); free_addrs: - kfree(jit.addrs); + kvfree(jit.addrs); + kfree(jit_data); + fp->aux->jit_data = NULL; + } out: if (tmp_blinded) bpf_jit_prog_release_other(fp, fp == orig_fp ? diff --git a/arch/s390/numa/mode_emu.c b/arch/s390/numa/mode_emu.c index 71a12a4f4906..72d742bb2d17 100644 --- a/arch/s390/numa/mode_emu.c +++ b/arch/s390/numa/mode_emu.c @@ -558,9 +558,7 @@ static int __init early_parse_emu_nodes(char *p) { int count; - if (kstrtoint(p, 0, &count) != 0 || count <= 0) - return 0; - if (count <= 0) + if (!p || kstrtoint(p, 0, &count) != 0 || count <= 0) return 0; emu_nodes = min(count, MAX_NUMNODES); return 0; @@ -572,7 +570,8 @@ early_param("emu_nodes", early_parse_emu_nodes); */ static int __init early_parse_emu_size(char *p) { - emu_size = memparse(p, NULL); + if (p) + emu_size = memparse(p, NULL); return 0; } early_param("emu_size", early_parse_emu_size); diff --git a/arch/s390/numa/numa.c b/arch/s390/numa/numa.c index 8eb9e9743f5d..d2910fa834c8 100644 --- a/arch/s390/numa/numa.c +++ b/arch/s390/numa/numa.c @@ -158,6 +158,8 @@ early_param("numa_debug", parse_debug); static int __init parse_numa(char *parm) { + if (!parm) + return 1; if (strcmp(parm, numa_mode_plain.name) == 0) mode = &numa_mode_plain; #ifdef CONFIG_NUMA_EMU diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index b0e3b9a0e488..bc61ea18e88d 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -27,6 +27,7 @@ #include <linux/seq_file.h> #include <linux/jump_label.h> #include <linux/pci.h> +#include <linux/printk.h> #include <asm/isc.h> #include <asm/airq.h> @@ -43,7 +44,7 @@ static DECLARE_BITMAP(zpci_domain, ZPCI_NR_DEVICES); static DEFINE_SPINLOCK(zpci_domain_lock); #define ZPCI_IOMAP_ENTRIES \ - min(((unsigned long) ZPCI_NR_DEVICES * PCI_BAR_COUNT / 2), \ + min(((unsigned long) ZPCI_NR_DEVICES * PCI_STD_NUM_BARS / 2), \ ZPCI_IOMAP_MAX_ENTRIES) static DEFINE_SPINLOCK(zpci_iomap_lock); @@ -294,7 +295,7 @@ static void __iomem *pci_iomap_range_mio(struct pci_dev *pdev, int bar, void __iomem *pci_iomap_range(struct pci_dev *pdev, int bar, unsigned long offset, unsigned long max) { - if (!pci_resource_len(pdev, bar) || bar >= PCI_BAR_COUNT) + if (bar >= PCI_STD_NUM_BARS || !pci_resource_len(pdev, bar)) return NULL; if (static_branch_likely(&have_mio)) @@ -324,7 +325,7 @@ static void __iomem *pci_iomap_wc_range_mio(struct pci_dev *pdev, int bar, void __iomem *pci_iomap_wc_range(struct pci_dev *pdev, int bar, unsigned long offset, unsigned long max) { - if (!pci_resource_len(pdev, bar) || bar >= PCI_BAR_COUNT) + if (bar >= PCI_STD_NUM_BARS || !pci_resource_len(pdev, bar)) return NULL; if (static_branch_likely(&have_mio)) @@ -416,7 +417,7 @@ static void zpci_map_resources(struct pci_dev *pdev) resource_size_t len; int i; - for (i = 0; i < PCI_BAR_COUNT; i++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { len = pci_resource_len(pdev, i); if (!len) continue; @@ -431,13 +432,13 @@ static void zpci_map_resources(struct pci_dev *pdev) } #ifdef CONFIG_PCI_IOV - i = PCI_IOV_RESOURCES; + for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) { + int bar = i + PCI_IOV_RESOURCES; - for (; i < PCI_SRIOV_NUM_BARS + PCI_IOV_RESOURCES; i++) { - len = pci_resource_len(pdev, i); + len = pci_resource_len(pdev, bar); if (!len) continue; - pdev->resource[i].parent = &iov_res; + pdev->resource[bar].parent = &iov_res; } #endif } @@ -451,7 +452,7 @@ static void zpci_unmap_resources(struct pci_dev *pdev) if (zpci_use_mio(zdev)) return; - for (i = 0; i < PCI_BAR_COUNT; i++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { len = pci_resource_len(pdev, i); if (!len) continue; @@ -514,7 +515,7 @@ static int zpci_setup_bus_resources(struct zpci_dev *zdev, snprintf(zdev->res_name, sizeof(zdev->res_name), "PCI Bus %04x:%02x", zdev->domain, ZPCI_BUS_NR); - for (i = 0; i < PCI_BAR_COUNT; i++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { if (!zdev->bars[i].size) continue; entry = zpci_alloc_iomap(zdev); @@ -551,7 +552,7 @@ static void zpci_cleanup_bus_resources(struct zpci_dev *zdev) { int i; - for (i = 0; i < PCI_BAR_COUNT; i++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { if (!zdev->bars[i].size || !zdev->bars[i].res) continue; @@ -573,7 +574,7 @@ int pcibios_add_device(struct pci_dev *pdev) pdev->dev.dma_ops = &s390_pci_dma_ops; zpci_map_resources(pdev); - for (i = 0; i < PCI_BAR_COUNT; i++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { res = &pdev->resource[i]; if (res->parent || !res->flags) continue; @@ -659,6 +660,8 @@ static int zpci_alloc_domain(struct zpci_dev *zdev) spin_lock(&zpci_domain_lock); if (test_bit(zdev->domain, zpci_domain)) { spin_unlock(&zpci_domain_lock); + pr_err("Adding PCI function %08x failed because domain %04x is already assigned\n", + zdev->fid, zdev->domain); return -EEXIST; } set_bit(zdev->domain, zpci_domain); @@ -670,6 +673,8 @@ static int zpci_alloc_domain(struct zpci_dev *zdev) zdev->domain = find_first_zero_bit(zpci_domain, ZPCI_NR_DEVICES); if (zdev->domain == ZPCI_NR_DEVICES) { spin_unlock(&zpci_domain_lock); + pr_err("Adding PCI function %08x failed because the configured limit of %d is reached\n", + zdev->fid, ZPCI_NR_DEVICES); return -ENOSPC; } set_bit(zdev->domain, zpci_domain); @@ -934,5 +939,5 @@ subsys_initcall_sync(pci_base_init); void zpci_rescan(void) { if (zpci_is_enabled()) - clp_rescan_pci_devices_simple(); + clp_rescan_pci_devices_simple(NULL); } diff --git a/arch/s390/pci/pci_clp.c b/arch/s390/pci/pci_clp.c index 9bdff4defef1..0d3d8f170ea4 100644 --- a/arch/s390/pci/pci_clp.c +++ b/arch/s390/pci/pci_clp.c @@ -66,7 +66,7 @@ static inline int clp_get_ilp(unsigned long *ilp) /* * Call Logical Processor with c=0, the give constant lps and an lpcb request. */ -static inline int clp_req(void *data, unsigned int lps) +static __always_inline int clp_req(void *data, unsigned int lps) { struct { u8 _[CLP_BLK_SIZE]; } *req = data; u64 ignored; @@ -145,7 +145,7 @@ static int clp_store_query_pci_fn(struct zpci_dev *zdev, { int i; - for (i = 0; i < PCI_BAR_COUNT; i++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { zdev->bars[i].val = le32_to_cpu(response->bar[i]); zdev->bars[i].size = response->bar_size[i]; } @@ -164,8 +164,8 @@ static int clp_store_query_pci_fn(struct zpci_dev *zdev, sizeof(zdev->util_str)); } zdev->mio_capable = response->mio_addr_avail; - for (i = 0; i < PCI_BAR_COUNT; i++) { - if (!(response->mio.valid & (1 << (PCI_BAR_COUNT - i - 1)))) + for (i = 0; i < PCI_STD_NUM_BARS; i++) { + if (!(response->mio.valid & (1 << (PCI_STD_NUM_BARS - i - 1)))) continue; zdev->bars[i].mio_wb = (void __iomem *) response->mio.addr[i].wb; @@ -240,12 +240,14 @@ error: } /* - * Enable/Disable a given PCI function defined by its function handle. + * Enable/Disable a given PCI function and update its function handle if + * necessary */ -static int clp_set_pci_fn(u32 *fh, u8 nr_dma_as, u8 command) +static int clp_set_pci_fn(struct zpci_dev *zdev, u8 nr_dma_as, u8 command) { struct clp_req_rsp_set_pci *rrb; int rc, retries = 100; + u32 fid = zdev->fid; rrb = clp_alloc_block(GFP_KERNEL); if (!rrb) @@ -256,7 +258,7 @@ static int clp_set_pci_fn(u32 *fh, u8 nr_dma_as, u8 command) rrb->request.hdr.len = sizeof(rrb->request); rrb->request.hdr.cmd = CLP_SET_PCI_FN; rrb->response.hdr.len = sizeof(rrb->response); - rrb->request.fh = *fh; + rrb->request.fh = zdev->fh; rrb->request.oc = command; rrb->request.ndas = nr_dma_as; @@ -269,12 +271,17 @@ static int clp_set_pci_fn(u32 *fh, u8 nr_dma_as, u8 command) } } while (rrb->response.hdr.rsp == CLP_RC_SETPCIFN_BUSY); - if (!rc && rrb->response.hdr.rsp == CLP_RC_OK) - *fh = rrb->response.fh; - else { + if (rc || rrb->response.hdr.rsp != CLP_RC_OK) { zpci_err("Set PCI FN:\n"); zpci_err_clp(rrb->response.hdr.rsp, rc); - rc = -EIO; + } + + if (!rc && rrb->response.hdr.rsp == CLP_RC_OK) { + zdev->fh = rrb->response.fh; + } else if (!rc && rrb->response.hdr.rsp == CLP_RC_SETPCIFN_ALRDY && + rrb->response.fh == 0) { + /* Function is already in desired state - update handle */ + rc = clp_rescan_pci_devices_simple(&fid); } clp_free_block(rrb); return rc; @@ -282,18 +289,17 @@ static int clp_set_pci_fn(u32 *fh, u8 nr_dma_as, u8 command) int clp_enable_fh(struct zpci_dev *zdev, u8 nr_dma_as) { - u32 fh = zdev->fh; int rc; - rc = clp_set_pci_fn(&fh, nr_dma_as, CLP_SET_ENABLE_PCI_FN); - zpci_dbg(3, "ena fid:%x, fh:%x, rc:%d\n", zdev->fid, fh, rc); + rc = clp_set_pci_fn(zdev, nr_dma_as, CLP_SET_ENABLE_PCI_FN); + zpci_dbg(3, "ena fid:%x, fh:%x, rc:%d\n", zdev->fid, zdev->fh, rc); if (rc) goto out; - zdev->fh = fh; if (zpci_use_mio(zdev)) { - rc = clp_set_pci_fn(&fh, nr_dma_as, CLP_SET_ENABLE_MIO); - zpci_dbg(3, "ena mio fid:%x, fh:%x, rc:%d\n", zdev->fid, fh, rc); + rc = clp_set_pci_fn(zdev, nr_dma_as, CLP_SET_ENABLE_MIO); + zpci_dbg(3, "ena mio fid:%x, fh:%x, rc:%d\n", + zdev->fid, zdev->fh, rc); if (rc) clp_disable_fh(zdev); } @@ -309,11 +315,8 @@ int clp_disable_fh(struct zpci_dev *zdev) if (!zdev_enabled(zdev)) return 0; - rc = clp_set_pci_fn(&fh, 0, CLP_SET_DISABLE_PCI_FN); + rc = clp_set_pci_fn(zdev, 0, CLP_SET_DISABLE_PCI_FN); zpci_dbg(3, "dis fid:%x, fh:%x, rc:%d\n", zdev->fid, fh, rc); - if (!rc) - zdev->fh = fh; - return rc; } @@ -370,10 +373,14 @@ static void __clp_add(struct clp_fh_list_entry *entry, void *data) static void __clp_update(struct clp_fh_list_entry *entry, void *data) { struct zpci_dev *zdev; + u32 *fid = data; if (!entry->vendor_id) return; + if (fid && *fid != entry->fid) + return; + zdev = get_zdev_by_fid(entry->fid); if (!zdev) return; @@ -413,7 +420,10 @@ int clp_rescan_pci_devices(void) return rc; } -int clp_rescan_pci_devices_simple(void) +/* Rescan PCI functions and refresh function handles. If fid is non-NULL only + * refresh the handle of the function matching @fid + */ +int clp_rescan_pci_devices_simple(u32 *fid) { struct clp_req_rsp_list_pci *rrb; int rc; @@ -422,7 +432,7 @@ int clp_rescan_pci_devices_simple(void) if (!rrb) return -ENOMEM; - rc = clp_list_pci(rrb, NULL, __clp_update); + rc = clp_list_pci(rrb, fid, __clp_update); clp_free_block(rrb); return rc; diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c index 9e52d1527f71..64b1399a73f0 100644 --- a/arch/s390/pci/pci_dma.c +++ b/arch/s390/pci/pci_dma.c @@ -668,15 +668,17 @@ const struct dma_map_ops s390_pci_dma_ops = { .unmap_sg = s390_dma_unmap_sg, .map_page = s390_dma_map_pages, .unmap_page = s390_dma_unmap_pages, + .mmap = dma_common_mmap, + .get_sgtable = dma_common_get_sgtable, /* dma_supported is unconditionally true without a callback */ }; EXPORT_SYMBOL_GPL(s390_pci_dma_ops); static int __init s390_iommu_setup(char *str) { - if (!strncmp(str, "strict", 6)) + if (!strcmp(str, "strict")) s390_iommu_strict = 1; - return 0; + return 1; } __setup("s390_iommu=", s390_iommu_setup); diff --git a/arch/s390/pci/pci_irq.c b/arch/s390/pci/pci_irq.c index d80616ae8dd8..fbe97ab2e228 100644 --- a/arch/s390/pci/pci_irq.c +++ b/arch/s390/pci/pci_irq.c @@ -284,7 +284,7 @@ int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) return rc; irq_set_chip_and_handler(irq, &zpci_irq_chip, handle_percpu_irq); - msg.data = hwirq; + msg.data = hwirq - bit; if (irq_delivery == DIRECTED) { msg.address_lo = zdev->msi_addr & 0xff0000ff; msg.address_lo |= msi->affinity ? diff --git a/arch/s390/pci/pci_sysfs.c b/arch/s390/pci/pci_sysfs.c index a433ba01a317..215f17437a4f 100644 --- a/arch/s390/pci/pci_sysfs.c +++ b/arch/s390/pci/pci_sysfs.c @@ -13,6 +13,8 @@ #include <linux/stat.h> #include <linux/pci.h> +#include "../../../drivers/pci/pci.h" + #include <asm/sclp.h> #define zpci_attr(name, fmt, member) \ @@ -49,31 +51,50 @@ static DEVICE_ATTR_RO(mio_enabled); static ssize_t recover_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { + struct kernfs_node *kn; struct pci_dev *pdev = to_pci_dev(dev); struct zpci_dev *zdev = to_zpci(pdev); - int ret; - - if (!device_remove_file_self(dev, attr)) - return count; - + int ret = 0; + + /* Can't use device_remove_self() here as that would lead us to lock + * the pci_rescan_remove_lock while holding the device' kernfs lock. + * This would create a possible deadlock with disable_slot() which is + * not directly protected by the device' kernfs lock but takes it + * during the device removal which happens under + * pci_rescan_remove_lock. + * + * This is analogous to sdev_store_delete() in + * drivers/scsi/scsi_sysfs.c + */ + kn = sysfs_break_active_protection(&dev->kobj, &attr->attr); + WARN_ON_ONCE(!kn); + /* device_remove_file() serializes concurrent calls ignoring all but + * the first + */ + device_remove_file(dev, attr); + + /* A concurrent call to recover_store() may slip between + * sysfs_break_active_protection() and the sysfs file removal. + * Once it unblocks from pci_lock_rescan_remove() the original pdev + * will already be removed. + */ pci_lock_rescan_remove(); - pci_stop_and_remove_bus_device(pdev); - ret = zpci_disable_device(zdev); - if (ret) - goto error; - - ret = zpci_enable_device(zdev); - if (ret) - goto error; - - pci_rescan_bus(zdev->bus); + if (pci_dev_is_added(pdev)) { + pci_stop_and_remove_bus_device(pdev); + ret = zpci_disable_device(zdev); + if (ret) + goto out; + + ret = zpci_enable_device(zdev); + if (ret) + goto out; + pci_rescan_bus(zdev->bus); + } +out: pci_unlock_rescan_remove(); - - return count; - -error: - pci_unlock_rescan_remove(); - return ret; + if (kn) + sysfs_unbreak_active_protection(kn); + return ret ? ret : count; } static DEVICE_ATTR_WO(recover); diff --git a/arch/s390/purgatory/.gitignore b/arch/s390/purgatory/.gitignore index 04a03433c720..c82157f46b18 100644 --- a/arch/s390/purgatory/.gitignore +++ b/arch/s390/purgatory/.gitignore @@ -1,3 +1,4 @@ purgatory +purgatory.chk purgatory.lds purgatory.ro diff --git a/arch/s390/purgatory/Makefile b/arch/s390/purgatory/Makefile index dc1ae4ff79d7..c57f8c40e992 100644 --- a/arch/s390/purgatory/Makefile +++ b/arch/s390/purgatory/Makefile @@ -4,17 +4,21 @@ OBJECT_FILES_NON_STANDARD := y purgatory-y := head.o purgatory.o string.o sha256.o mem.o -targets += $(purgatory-y) purgatory.lds purgatory purgatory.ro +targets += $(purgatory-y) purgatory.lds purgatory purgatory.chk purgatory.ro PURGATORY_OBJS = $(addprefix $(obj)/,$(purgatory-y)) -$(obj)/sha256.o: $(srctree)/lib/sha256.c FORCE +$(obj)/sha256.o: $(srctree)/lib/crypto/sha256.c FORCE $(call if_changed_rule,cc_o_c) +CFLAGS_sha256.o := -D__DISABLE_EXPORTS + $(obj)/mem.o: $(srctree)/arch/s390/lib/mem.S FORCE $(call if_changed_rule,as_o_S) -$(obj)/string.o: $(srctree)/arch/s390/lib/string.c FORCE - $(call if_changed_rule,cc_o_c) +KCOV_INSTRUMENT := n +GCOV_PROFILE := n +UBSAN_SANITIZE := n +KASAN_SANITIZE := n KBUILD_CFLAGS := -fno-strict-aliasing -Wall -Wstrict-prototypes KBUILD_CFLAGS += -Wno-pointer-sign -Wno-sign-compare @@ -24,15 +28,22 @@ KBUILD_CFLAGS += $(CLANG_FLAGS) KBUILD_CFLAGS += $(call cc-option,-fno-PIE) KBUILD_AFLAGS := $(filter-out -DCC_USING_EXPOLINE,$(KBUILD_AFLAGS)) -LDFLAGS_purgatory := -r --no-undefined -nostdlib -z nodefaultlib -T +# Since we link purgatory with -r unresolved symbols are not checked, so we +# also link a purgatory.chk binary without -r to check for unresolved symbols. +PURGATORY_LDFLAGS := -nostdlib -z nodefaultlib +LDFLAGS_purgatory := -r $(PURGATORY_LDFLAGS) -T +LDFLAGS_purgatory.chk := -e purgatory_start $(PURGATORY_LDFLAGS) $(obj)/purgatory: $(obj)/purgatory.lds $(PURGATORY_OBJS) FORCE $(call if_changed,ld) +$(obj)/purgatory.chk: $(obj)/purgatory FORCE + $(call if_changed,ld) + OBJCOPYFLAGS_purgatory.ro := -O elf64-s390 OBJCOPYFLAGS_purgatory.ro += --remove-section='*debug*' OBJCOPYFLAGS_purgatory.ro += --remove-section='.comment' OBJCOPYFLAGS_purgatory.ro += --remove-section='.note.*' -$(obj)/purgatory.ro: $(obj)/purgatory FORCE +$(obj)/purgatory.ro: $(obj)/purgatory $(obj)/purgatory.chk FORCE $(call if_changed,objcopy) $(obj)/kexec-purgatory.o: $(obj)/kexec-purgatory.S $(obj)/purgatory.ro FORCE diff --git a/arch/s390/purgatory/purgatory.c b/arch/s390/purgatory/purgatory.c index 3528e6da4e87..0a423bcf6746 100644 --- a/arch/s390/purgatory/purgatory.c +++ b/arch/s390/purgatory/purgatory.c @@ -8,8 +8,8 @@ */ #include <linux/kexec.h> -#include <linux/sha256.h> #include <linux/string.h> +#include <crypto/sha.h> #include <asm/purgatory.h> int verify_sha256_digest(void) diff --git a/arch/s390/purgatory/string.c b/arch/s390/purgatory/string.c new file mode 100644 index 000000000000..c98c22a72db7 --- /dev/null +++ b/arch/s390/purgatory/string.c @@ -0,0 +1,3 @@ +// SPDX-License-Identifier: GPL-2.0 +#define __HAVE_ARCH_MEMCMP /* arch function */ +#include "../lib/string.c" diff --git a/arch/s390/tools/Makefile b/arch/s390/tools/Makefile index b5e35e8f999a..f9dd47ff9ac4 100644 --- a/arch/s390/tools/Makefile +++ b/arch/s390/tools/Makefile @@ -10,8 +10,8 @@ PHONY += kapi kapi: $(kapi-hdrs-y) -hostprogs-y += gen_facilities -hostprogs-y += gen_opcode_table +hostprogs += gen_facilities +hostprogs += gen_opcode_table HOSTCFLAGS_gen_facilities.o += $(LINUXINCLUDE) diff --git a/arch/s390/tools/gen_facilities.c b/arch/s390/tools/gen_facilities.c index cead9e0dcffb..61ce5b59b828 100644 --- a/arch/s390/tools/gen_facilities.c +++ b/arch/s390/tools/gen_facilities.c @@ -58,6 +58,9 @@ static struct facility_def facility_defs[] = { #ifdef CONFIG_HAVE_MARCH_Z14_FEATURES 58, /* miscellaneous-instruction-extension 2 */ #endif +#ifdef CONFIG_HAVE_MARCH_Z15_FEATURES + 61, /* miscellaneous-instruction-extension 3 */ +#endif -1 /* END */ } }, |
