diff options
Diffstat (limited to 'arch/s390')
89 files changed, 1262 insertions, 680 deletions
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index b86de61b8caa..8857ec3b97eb 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -153,12 +153,15 @@ config S390 select HAVE_DEBUG_KMEMLEAK select HAVE_DMA_CONTIGUOUS select HAVE_DYNAMIC_FTRACE + select HAVE_DYNAMIC_FTRACE_WITH_ARGS + select HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS select HAVE_DYNAMIC_FTRACE_WITH_REGS select HAVE_EBPF_JIT if PACK_STACK && HAVE_MARCH_Z196_FEATURES select HAVE_EFFICIENT_UNALIGNED_ACCESS select HAVE_FAST_GUP select HAVE_FENTRY select HAVE_FTRACE_MCOUNT_RECORD + select HAVE_FUNCTION_ARG_ACCESS_API select HAVE_FUNCTION_ERROR_INJECTION select HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_TRACER @@ -190,6 +193,7 @@ config S390 select HAVE_REGS_AND_STACK_ACCESS_API select HAVE_RELIABLE_STACKTRACE select HAVE_RSEQ + select HAVE_SAMPLE_FTRACE_DIRECT select HAVE_SOFTIRQ_ON_OWN_STACK select HAVE_SYSCALL_TRACEPOINTS select HAVE_VIRT_CPU_ACCOUNTING @@ -434,6 +438,14 @@ endchoice config 64BIT def_bool y +config COMMAND_LINE_SIZE + int "Maximum size of kernel command line" + default 4096 + range 896 1048576 + help + This allows you to specify the maximum length of the kernel command + line. + config COMPAT def_bool y prompt "Kernel support for 31 bit emulation" @@ -938,6 +950,8 @@ menu "Selftests" config S390_UNWIND_SELFTEST def_tristate n + depends on KUNIT + default KUNIT_ALL_TESTS prompt "Test unwind functions" help This option enables s390 specific stack unwinder testing kernel @@ -946,4 +960,16 @@ config S390_UNWIND_SELFTEST Say N if you are unsure. +config S390_KPROBES_SANITY_TEST + def_tristate n + prompt "Enable s390 specific kprobes tests" + depends on KPROBES + depends on KUNIT + help + This option enables an s390 specific kprobes test 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/boot/compressed/decompressor.h b/arch/s390/boot/compressed/decompressor.h index a59f75c5b049..f75cc31a77dd 100644 --- a/arch/s390/boot/compressed/decompressor.h +++ b/arch/s390/boot/compressed/decompressor.h @@ -24,6 +24,7 @@ struct vmlinux_info { unsigned long dynsym_start; unsigned long rela_dyn_start; unsigned long rela_dyn_end; + unsigned long amode31_size; }; /* Symbols defined by linker scripts */ diff --git a/arch/s390/boot/head.S b/arch/s390/boot/head.S index 40f4cff538b8..3a252d140c55 100644 --- a/arch/s390/boot/head.S +++ b/arch/s390/boot/head.S @@ -184,35 +184,23 @@ iplstart: bas %r14,.Lloader # load parameter file ltr %r2,%r2 # got anything ? bz .Lnopf - chi %r2,895 - bnh .Lnotrunc - la %r2,895 + l %r3,MAX_COMMAND_LINE_SIZE+ARCH_OFFSET-PARMAREA(%r12) + ahi %r3,-1 + clr %r2,%r3 + bl .Lnotrunc + lr %r2,%r3 .Lnotrunc: l %r4,.Linitrd clc 0(3,%r4),.L_hdr # if it is HDRx bz .Lagain1 # skip dataset header clc 0(3,%r4),.L_eof # if it is EOFx bz .Lagain1 # skip dateset trailer - la %r5,0(%r4,%r2) - lr %r3,%r2 - la %r3,COMMAND_LINE-PARMAREA(%r12) # load adr. of command line - mvc 0(256,%r3),0(%r4) - mvc 256(256,%r3),256(%r4) - mvc 512(256,%r3),512(%r4) - mvc 768(122,%r3),768(%r4) - slr %r0,%r0 - b .Lcntlp -.Ldelspc: - ic %r0,0(%r2,%r3) - chi %r0,0x20 # is it a space ? - be .Lcntlp - ahi %r2,1 - b .Leolp -.Lcntlp: - brct %r2,.Ldelspc -.Leolp: - slr %r0,%r0 - stc %r0,0(%r2,%r3) # terminate buffer + + lr %r5,%r2 + la %r6,COMMAND_LINE-PARMAREA(%r12) + lr %r7,%r2 + ahi %r7,1 + mvcl %r6,%r4 .Lnopf: # @@ -317,6 +305,7 @@ SYM_CODE_START_LOCAL(startup_normal) xc 0x300(256),0x300 xc 0xe00(256),0xe00 xc 0xf00(256),0xf00 + lctlg %c0,%c15,.Lctl-.LPG0(%r13) # load control registers stcke __LC_BOOT_CLOCK mvc __LC_LAST_UPDATE_CLOCK(8),__LC_BOOT_CLOCK+1 spt 6f-.LPG0(%r13) @@ -335,6 +324,22 @@ SYM_CODE_END(startup_normal) .quad 0x0000000180000000,startup_pgm_check_handler .Lio_new_psw: .quad 0x0002000180000000,0x1f0 # disabled wait +.Lctl: .quad 0x04040000 # cr0: AFP registers & secondary space + .quad 0 # cr1: primary space segment table + .quad 0 # cr2: dispatchable unit control table + .quad 0 # cr3: instruction authorization + .quad 0xffff # cr4: instruction authorization + .quad 0 # cr5: primary-aste origin + .quad 0 # cr6: I/O interrupts + .quad 0 # cr7: secondary space segment table + .quad 0x0000000000008000 # cr8: access registers translation + .quad 0 # cr9: tracing off + .quad 0 # cr10: tracing off + .quad 0 # cr11: tracing off + .quad 0 # cr12: tracing off + .quad 0 # cr13: home space segment table + .quad 0xc0000000 # cr14: machine check handling off + .quad 0 # cr15: linkage stack operations #include "head_kdump.S" @@ -377,11 +382,10 @@ SYM_DATA_START(parmarea) .quad 0 # OLDMEM_BASE .quad 0 # OLDMEM_SIZE .quad kernel_version # points to kernel version string + .quad COMMAND_LINE_SIZE .org COMMAND_LINE .byte "root=/dev/ram0 ro" .byte 0 .org PARMAREA+__PARMAREA_SIZE SYM_DATA_END(parmarea) - - .org HEAD_END diff --git a/arch/s390/boot/ipl_parm.c b/arch/s390/boot/ipl_parm.c index 0f84c072625e..9ed7e29c81d9 100644 --- a/arch/s390/boot/ipl_parm.c +++ b/arch/s390/boot/ipl_parm.c @@ -170,10 +170,10 @@ static inline int has_ebcdic_char(const char *str) void setup_boot_command_line(void) { - parmarea.command_line[ARCH_COMMAND_LINE_SIZE - 1] = 0; + parmarea.command_line[COMMAND_LINE_SIZE - 1] = 0; /* convert arch command line to ascii if necessary */ if (has_ebcdic_char(parmarea.command_line)) - EBCASC(parmarea.command_line, ARCH_COMMAND_LINE_SIZE); + EBCASC(parmarea.command_line, COMMAND_LINE_SIZE); /* copy arch command line */ strcpy(early_command_line, strim(parmarea.command_line)); diff --git a/arch/s390/boot/pgm_check_info.c b/arch/s390/boot/pgm_check_info.c index 75bcbfa27941..c2a1defc79da 100644 --- a/arch/s390/boot/pgm_check_info.c +++ b/arch/s390/boot/pgm_check_info.c @@ -175,6 +175,6 @@ void print_pgm_check_info(void) gpregs[12], gpregs[13], gpregs[14], gpregs[15]); print_stacktrace(); decompressor_printk("Last Breaking-Event-Address:\n"); - decompressor_printk(" [<%016lx>] %pS\n", (unsigned long)S390_lowcore.breaking_event_addr, - (void *)S390_lowcore.breaking_event_addr); + decompressor_printk(" [<%016lx>] %pS\n", (unsigned long)S390_lowcore.pgm_last_break, + (void *)S390_lowcore.pgm_last_break); } diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c index 6dc8d0a53864..7571dee72a0c 100644 --- a/arch/s390/boot/startup.c +++ b/arch/s390/boot/startup.c @@ -15,6 +15,7 @@ #include "uv.h" unsigned long __bootdata_preserved(__kaslr_offset); +unsigned long __bootdata(__amode31_base); unsigned long __bootdata_preserved(VMALLOC_START); unsigned long __bootdata_preserved(VMALLOC_END); struct page *__bootdata_preserved(vmemmap); @@ -259,6 +260,12 @@ static void offset_vmlinux_info(unsigned long offset) vmlinux.dynsym_start += offset; } +static unsigned long reserve_amode31(unsigned long safe_addr) +{ + __amode31_base = PAGE_ALIGN(safe_addr); + return safe_addr + vmlinux.amode31_size; +} + void startup_kernel(void) { unsigned long random_lma; @@ -273,6 +280,7 @@ void startup_kernel(void) setup_lpp(); store_ipl_parmblock(); safe_addr = mem_safe_offset(); + safe_addr = reserve_amode31(safe_addr); safe_addr = read_ipl_report(safe_addr); uv_query_info(); rescue_initrd(safe_addr); diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index 6aad18ee131d..fd825097cf04 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -61,7 +61,8 @@ CONFIG_PROTECTED_VIRTUALIZATION_GUEST=y CONFIG_CMM=m CONFIG_APPLDATA_BASE=y CONFIG_KVM=m -CONFIG_S390_UNWIND_SELFTEST=y +CONFIG_S390_UNWIND_SELFTEST=m +CONFIG_S390_KPROBES_SANITY_TEST=m CONFIG_KPROBES=y CONFIG_JUMP_LABEL=y CONFIG_STATIC_KEYS_SELFTEST=y @@ -776,7 +777,6 @@ CONFIG_CRC8=m CONFIG_RANDOM32_SELFTEST=y CONFIG_DMA_CMA=y CONFIG_CMA_SIZE_MBYTES=0 -CONFIG_DMA_API_DEBUG=y CONFIG_PRINTK_TIME=y CONFIG_DYNAMIC_DEBUG=y CONFIG_DEBUG_INFO=y @@ -839,8 +839,13 @@ CONFIG_BPF_KPROBE_OVERRIDE=y CONFIG_HIST_TRIGGERS=y CONFIG_FTRACE_STARTUP_TEST=y # CONFIG_EVENT_TRACE_STARTUP_TEST is not set +CONFIG_SAMPLES=y +CONFIG_SAMPLE_TRACE_PRINTK=m +CONFIG_SAMPLE_FTRACE_DIRECT=m CONFIG_DEBUG_ENTRY=y CONFIG_CIO_INJECT=y +CONFIG_KUNIT=m +CONFIG_KUNIT_DEBUGFS=y CONFIG_NOTIFIER_ERROR_INJECTION=m CONFIG_NETDEV_NOTIFIER_ERROR_INJECT=m CONFIG_FAULT_INJECTION=y diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index f08b161c9446..c9c3cedff2d8 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -60,6 +60,7 @@ CONFIG_CMM=m CONFIG_APPLDATA_BASE=y CONFIG_KVM=m CONFIG_S390_UNWIND_SELFTEST=m +CONFIG_S390_KPROBES_SANITY_TEST=m CONFIG_KPROBES=y CONFIG_JUMP_LABEL=y # CONFIG_GCC_PLUGINS is not set @@ -788,6 +789,11 @@ CONFIG_FTRACE_SYSCALLS=y CONFIG_BLK_DEV_IO_TRACE=y CONFIG_BPF_KPROBE_OVERRIDE=y CONFIG_HIST_TRIGGERS=y +CONFIG_SAMPLES=y +CONFIG_SAMPLE_TRACE_PRINTK=m +CONFIG_SAMPLE_FTRACE_DIRECT=m +CONFIG_KUNIT=m +CONFIG_KUNIT_DEBUGFS=y CONFIG_LKDTM=m CONFIG_PERCPU_TEST=m CONFIG_ATOMIC64_SELFTEST=y diff --git a/arch/s390/include/asm/barrier.h b/arch/s390/include/asm/barrier.h index f9eddbca79d2..2c057e1f3200 100644 --- a/arch/s390/include/asm/barrier.h +++ b/arch/s390/include/asm/barrier.h @@ -16,20 +16,24 @@ #ifdef CONFIG_HAVE_MARCH_Z196_FEATURES /* Fast-BCR without checkpoint synchronization */ -#define __ASM_BARRIER "bcr 14,0\n" +#define __ASM_BCR_SERIALIZE "bcr 14,0\n" #else -#define __ASM_BARRIER "bcr 15,0\n" +#define __ASM_BCR_SERIALIZE "bcr 15,0\n" #endif -#define mb() do { asm volatile(__ASM_BARRIER : : : "memory"); } while (0) +static __always_inline void bcr_serialize(void) +{ + asm volatile(__ASM_BCR_SERIALIZE : : : "memory"); +} -#define rmb() barrier() -#define wmb() barrier() -#define dma_rmb() mb() -#define dma_wmb() mb() -#define __smp_mb() mb() -#define __smp_rmb() rmb() -#define __smp_wmb() wmb() +#define mb() bcr_serialize() +#define rmb() barrier() +#define wmb() barrier() +#define dma_rmb() mb() +#define dma_wmb() mb() +#define __smp_mb() mb() +#define __smp_rmb() rmb() +#define __smp_wmb() wmb() #define __smp_store_release(p, v) \ do { \ diff --git a/arch/s390/include/asm/bitops.h b/arch/s390/include/asm/bitops.h index fd149480b6e2..5a530c552c23 100644 --- a/arch/s390/include/asm/bitops.h +++ b/arch/s390/include/asm/bitops.h @@ -188,7 +188,7 @@ static inline bool arch_test_and_set_bit_lock(unsigned long nr, volatile unsigned long *ptr) { if (arch_test_bit(nr, ptr)) - return 1; + return true; return arch_test_and_set_bit(nr, ptr); } diff --git a/arch/s390/include/asm/ccwgroup.h b/arch/s390/include/asm/ccwgroup.h index 36dbf5043fc0..aa995d91cd1d 100644 --- a/arch/s390/include/asm/ccwgroup.h +++ b/arch/s390/include/asm/ccwgroup.h @@ -55,7 +55,7 @@ int ccwgroup_create_dev(struct device *root, struct ccwgroup_driver *gdrv, int num_devices, const char *buf); extern int ccwgroup_set_online(struct ccwgroup_device *gdev); -extern int ccwgroup_set_offline(struct ccwgroup_device *gdev); +int ccwgroup_set_offline(struct ccwgroup_device *gdev, bool call_gdrv); extern int ccwgroup_probe_ccwdev(struct ccw_device *cdev); extern void ccwgroup_remove_ccwdev(struct ccw_device *cdev); diff --git a/arch/s390/include/asm/cpu.h b/arch/s390/include/asm/cpu.h index 62228a884e06..26c710cd3485 100644 --- a/arch/s390/include/asm/cpu.h +++ b/arch/s390/include/asm/cpu.h @@ -12,6 +12,7 @@ #ifndef __ASSEMBLY__ #include <linux/types.h> +#include <linux/jump_label.h> struct cpuid { @@ -21,5 +22,7 @@ struct cpuid unsigned int unused : 16; } __attribute__ ((packed, aligned(8))); +DECLARE_STATIC_KEY_FALSE(cpu_has_bear); + #endif /* __ASSEMBLY__ */ #endif /* _ASM_S390_CPU_H */ diff --git a/arch/s390/include/asm/debug.h b/arch/s390/include/asm/debug.h index 19a55e1e3a0c..77f24262c25c 100644 --- a/arch/s390/include/asm/debug.h +++ b/arch/s390/include/asm/debug.h @@ -462,7 +462,7 @@ arch_initcall(VNAME(var, reg)) * * @var: Name of debug_info_t variable * @name: Name of debug log (e.g. used for debugfs entry) - * @pages_per_area: Number of pages per area + * @pages: Number of pages per area * @nr_areas: Number of debug areas * @buf_size: Size of data area in each debug entry * @view: Pointer to debug view struct diff --git a/arch/s390/include/asm/ftrace.h b/arch/s390/include/asm/ftrace.h index e8b460f39c58..267f70f4393f 100644 --- a/arch/s390/include/asm/ftrace.h +++ b/arch/s390/include/asm/ftrace.h @@ -17,7 +17,6 @@ void ftrace_caller(void); -extern char ftrace_graph_caller_end; extern void *ftrace_func; struct dyn_arch_ftrace { }; @@ -42,6 +41,35 @@ static inline unsigned long ftrace_call_adjust(unsigned long addr) return addr; } +struct ftrace_regs { + struct pt_regs regs; +}; + +static __always_inline struct pt_regs *arch_ftrace_get_regs(struct ftrace_regs *fregs) +{ + return &fregs->regs; +} + +static __always_inline void ftrace_instruction_pointer_set(struct ftrace_regs *fregs, + unsigned long ip) +{ + struct pt_regs *regs = arch_ftrace_get_regs(fregs); + + regs->psw.addr = ip; +} + +/* + * When an ftrace registered caller is tracing a function that is + * also set by a register_ftrace_direct() call, it needs to be + * differentiated in the ftrace_caller trampoline. To do this, + * place the direct caller in the ORIG_GPR2 part of pt_regs. This + * tells the ftrace_caller that there's a direct caller. + */ +static inline void arch_ftrace_set_direct_caller(struct pt_regs *regs, unsigned long addr) +{ + regs->orig_gpr2 = addr; +} + /* * Even though the system call numbers are identical for s390/s390x a * different system call table is used for compat tasks. This may lead @@ -68,4 +96,32 @@ static inline bool arch_syscall_match_sym_name(const char *sym, } #endif /* __ASSEMBLY__ */ + +#ifdef CONFIG_FUNCTION_TRACER + +#define FTRACE_NOP_INSN .word 0xc004, 0x0000, 0x0000 /* brcl 0,0 */ + +#ifndef CC_USING_HOTPATCH + +#define FTRACE_GEN_MCOUNT_RECORD(name) \ + .section __mcount_loc, "a", @progbits; \ + .quad name; \ + .previous; + +#else /* !CC_USING_HOTPATCH */ + +#define FTRACE_GEN_MCOUNT_RECORD(name) + +#endif /* !CC_USING_HOTPATCH */ + +#define FTRACE_GEN_NOP_ASM(name) \ + FTRACE_GEN_MCOUNT_RECORD(name) \ + FTRACE_NOP_INSN + +#else /* CONFIG_FUNCTION_TRACER */ + +#define FTRACE_GEN_NOP_ASM(name) + +#endif /* CONFIG_FUNCTION_TRACER */ + #endif /* _ASM_S390_FTRACE_H */ diff --git a/arch/s390/include/asm/jump_label.h b/arch/s390/include/asm/jump_label.h index dcb1bba4f406..916cfcb36d8a 100644 --- a/arch/s390/include/asm/jump_label.h +++ b/arch/s390/include/asm/jump_label.h @@ -2,6 +2,8 @@ #ifndef _ASM_S390_JUMP_LABEL_H #define _ASM_S390_JUMP_LABEL_H +#define HAVE_JUMP_LABEL_BATCH + #ifndef __ASSEMBLY__ #include <linux/types.h> diff --git a/arch/s390/include/asm/kprobes.h b/arch/s390/include/asm/kprobes.h index 09cdb632a490..5eb722c984e4 100644 --- a/arch/s390/include/asm/kprobes.h +++ b/arch/s390/include/asm/kprobes.h @@ -70,7 +70,7 @@ struct kprobe_ctlblk { }; void arch_remove_kprobe(struct kprobe *p); -void kretprobe_trampoline(void); +void __kretprobe_trampoline(void); int kprobe_fault_handler(struct pt_regs *regs, int trapnr); int kprobe_exceptions_notify(struct notifier_block *self, diff --git a/arch/s390/include/asm/livepatch.h b/arch/s390/include/asm/livepatch.h index d578a8c76676..5209f223331a 100644 --- a/arch/s390/include/asm/livepatch.h +++ b/arch/s390/include/asm/livepatch.h @@ -16,9 +16,7 @@ static inline void klp_arch_set_pc(struct ftrace_regs *fregs, unsigned long ip) { - struct pt_regs *regs = ftrace_get_regs(fregs); - - regs->psw.addr = ip; + ftrace_instruction_pointer_set(fregs, ip); } #endif diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h index 11213c8bfca5..1262f5003acf 100644 --- a/arch/s390/include/asm/lowcore.h +++ b/arch/s390/include/asm/lowcore.h @@ -65,7 +65,7 @@ struct lowcore { __u32 external_damage_code; /* 0x00f4 */ __u64 failing_storage_address; /* 0x00f8 */ __u8 pad_0x0100[0x0110-0x0100]; /* 0x0100 */ - __u64 breaking_event_addr; /* 0x0110 */ + __u64 pgm_last_break; /* 0x0110 */ __u8 pad_0x0118[0x0120-0x0118]; /* 0x0118 */ psw_t restart_old_psw; /* 0x0120 */ psw_t external_old_psw; /* 0x0130 */ @@ -93,9 +93,10 @@ struct lowcore { psw_t return_psw; /* 0x0290 */ psw_t return_mcck_psw; /* 0x02a0 */ + __u64 last_break; /* 0x02b0 */ + /* CPU accounting and timing values. */ - __u64 sys_enter_timer; /* 0x02b0 */ - __u8 pad_0x02b8[0x02c0-0x02b8]; /* 0x02b8 */ + __u64 sys_enter_timer; /* 0x02b8 */ __u64 mcck_enter_timer; /* 0x02c0 */ __u64 exit_timer; /* 0x02c8 */ __u64 user_timer; /* 0x02d0 */ @@ -188,7 +189,7 @@ struct lowcore { __u32 tod_progreg_save_area; /* 0x1324 */ __u32 cpu_timer_save_area[2]; /* 0x1328 */ __u32 clock_comp_save_area[2]; /* 0x1330 */ - __u8 pad_0x1338[0x1340-0x1338]; /* 0x1338 */ + __u64 last_break_save_area; /* 0x1338 */ __u32 access_regs_save_area[16]; /* 0x1340 */ __u64 cregs_save_area[16]; /* 0x1380 */ __u8 pad_0x1400[0x1800-0x1400]; /* 0x1400 */ diff --git a/arch/s390/include/asm/mem_encrypt.h b/arch/s390/include/asm/mem_encrypt.h index 2542cbf7e2d1..08a8b96606d7 100644 --- a/arch/s390/include/asm/mem_encrypt.h +++ b/arch/s390/include/asm/mem_encrypt.h @@ -4,8 +4,6 @@ #ifndef __ASSEMBLY__ -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/nospec-branch.h b/arch/s390/include/asm/nospec-branch.h index b4bd8c41e9d3..82725cf783c7 100644 --- a/arch/s390/include/asm/nospec-branch.h +++ b/arch/s390/include/asm/nospec-branch.h @@ -12,6 +12,11 @@ void nospec_init_branches(void); void nospec_auto_detect(void); void nospec_revert(s32 *start, s32 *end); +static inline bool nospec_uses_trampoline(void) +{ + return __is_defined(CC_USING_EXPOLINE) && !nospec_disable; +} + #endif /* __ASSEMBLY__ */ #endif /* _ASM_S390_EXPOLINE_H */ diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h index e4803ec51110..6b3c366af78e 100644 --- a/arch/s390/include/asm/pci.h +++ b/arch/s390/include/asm/pci.h @@ -207,6 +207,8 @@ int zpci_enable_device(struct zpci_dev *); int zpci_disable_device(struct zpci_dev *); int zpci_scan_configured_device(struct zpci_dev *zdev, u32 fh); int zpci_deconfigure_device(struct zpci_dev *zdev); +void zpci_device_reserved(struct zpci_dev *zdev); +bool zpci_is_device_configured(struct zpci_dev *zdev); int zpci_register_ioat(struct zpci_dev *, u8, u64, u64, u64); int zpci_unregister_ioat(struct zpci_dev *, u8); diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index b61426c9ef17..008a6c856fa4 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -583,11 +583,11 @@ static inline void cspg(unsigned long *ptr, unsigned long old, unsigned long new #define CRDTE_DTT_REGION1 0x1cUL static inline void crdte(unsigned long old, unsigned long new, - unsigned long table, unsigned long dtt, + unsigned long *table, unsigned long dtt, unsigned long address, unsigned long asce) { union register_pair r1 = { .even = old, .odd = new, }; - union register_pair r2 = { .even = table | dtt, .odd = address, }; + union register_pair r2 = { .even = __pa(table) | dtt, .odd = address, }; asm volatile(".insn rrf,0xb98f0000,%[r1],%[r2],%[asce],0" : [r1] "+&d" (r1.pair) @@ -1001,7 +1001,7 @@ 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; + unsigned long pto = __pa(ptep); if (__builtin_constant_p(opt) && opt == 0) { /* Invalidation + TLB flush for the pte */ @@ -1023,7 +1023,7 @@ static __always_inline void __ptep_ipte(unsigned long address, pte_t *ptep, static __always_inline void __ptep_ipte_range(unsigned long address, int nr, pte_t *ptep, int local) { - unsigned long pto = (unsigned long) ptep; + unsigned long pto = __pa(ptep); /* Invalidate a range of ptes + TLB flush of the ptes */ do { @@ -1074,8 +1074,9 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, pte_t res; res = ptep_xchg_lazy(mm, addr, ptep, __pte(_PAGE_INVALID)); + /* At this point the reference through the mapping is still present */ if (mm_is_protected(mm) && pte_present(res)) - uv_convert_from_secure(pte_val(res) & PAGE_MASK); + uv_convert_owned_from_secure(pte_val(res) & PAGE_MASK); return res; } @@ -1091,8 +1092,9 @@ static inline pte_t ptep_clear_flush(struct vm_area_struct *vma, pte_t res; res = ptep_xchg_direct(vma->vm_mm, addr, ptep, __pte(_PAGE_INVALID)); + /* At this point the reference through the mapping is still present */ if (mm_is_protected(vma->vm_mm) && pte_present(res)) - uv_convert_from_secure(pte_val(res) & PAGE_MASK); + uv_convert_owned_from_secure(pte_val(res) & PAGE_MASK); return res; } @@ -1116,8 +1118,9 @@ static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm, } else { res = ptep_xchg_lazy(mm, addr, ptep, __pte(_PAGE_INVALID)); } + /* At this point the reference through the mapping is still present */ if (mm_is_protected(mm) && pte_present(res)) - uv_convert_from_secure(pte_val(res) & PAGE_MASK); + uv_convert_owned_from_secure(pte_val(res) & PAGE_MASK); return res; } @@ -1484,7 +1487,7 @@ static __always_inline void __pmdp_idte(unsigned long addr, pmd_t *pmdp, { unsigned long sto; - sto = (unsigned long) pmdp - pmd_index(addr) * sizeof(pmd_t); + sto = __pa(pmdp) - pmd_index(addr) * sizeof(pmd_t); if (__builtin_constant_p(opt) && opt == 0) { /* flush without guest asce */ asm volatile( @@ -1510,7 +1513,7 @@ static __always_inline void __pudp_idte(unsigned long addr, pud_t *pudp, { unsigned long r3o; - r3o = (unsigned long) pudp - pud_index(addr) * sizeof(pud_t); + r3o = __pa(pudp) - pud_index(addr) * sizeof(pud_t); r3o |= _ASCE_TYPE_REGION3; if (__builtin_constant_p(opt) && opt == 0) { /* flush without guest asce */ diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index 879b8e3f609c..f54c152bf2bf 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -192,7 +192,7 @@ static inline void release_thread(struct task_struct *tsk) { } void guarded_storage_release(struct task_struct *tsk); void gs_load_bc_cb(struct pt_regs *regs); -unsigned long get_wchan(struct task_struct *p); +unsigned long __get_wchan(struct task_struct *p); #define task_pt_regs(tsk) ((struct pt_regs *) \ (task_stack_page(tsk) + THREAD_SIZE) - 1) #define KSTK_EIP(tsk) (task_pt_regs(tsk)->psw.addr) diff --git a/arch/s390/include/asm/ptrace.h b/arch/s390/include/asm/ptrace.h index 61b22aa990e7..4ffa8e7f0ed3 100644 --- a/arch/s390/include/asm/ptrace.h +++ b/arch/s390/include/asm/ptrace.h @@ -76,8 +76,7 @@ enum { * The pt_regs struct defines the way the registers are stored on * the stack during a system call. */ -struct pt_regs -{ +struct pt_regs { union { user_pt_regs user_regs; struct { @@ -97,6 +96,7 @@ struct pt_regs }; unsigned long flags; unsigned long cr1; + unsigned long last_break; }; /* @@ -197,6 +197,25 @@ const char *regs_query_register_name(unsigned int offset); unsigned long regs_get_register(struct pt_regs *regs, unsigned int offset); unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, unsigned int n); +/** + * regs_get_kernel_argument() - get Nth function argument in kernel + * @regs: pt_regs of that context + * @n: function argument number (start from 0) + * + * regs_get_kernel_argument() returns @n th argument of the function call. + */ +static inline unsigned long regs_get_kernel_argument(struct pt_regs *regs, + unsigned int n) +{ + unsigned int argoffset = STACK_FRAME_OVERHEAD / sizeof(long); + +#define NR_REG_ARGUMENTS 5 + if (n < NR_REG_ARGUMENTS) + return regs_get_register(regs, 2 + n); + n -= NR_REG_ARGUMENTS; + return regs_get_kernel_stack_nth(regs, argoffset + n); +} + static inline unsigned long kernel_stack_pointer(struct pt_regs *regs) { return regs->gprs[15]; diff --git a/arch/s390/include/asm/qdio.h b/arch/s390/include/asm/qdio.h index 25b5dc34db75..4b9b14b20984 100644 --- a/arch/s390/include/asm/qdio.h +++ b/arch/s390/include/asm/qdio.h @@ -349,8 +349,6 @@ extern int qdio_allocate(struct ccw_device *cdev, unsigned int no_input_qs, extern int qdio_establish(struct ccw_device *cdev, struct qdio_initialize *init_data); extern int qdio_activate(struct ccw_device *); -extern struct qaob *qdio_allocate_aob(void); -extern void qdio_release_aob(struct qaob *); extern int do_QDIO(struct ccw_device *cdev, unsigned int callflags, int q_nr, unsigned int bufnr, unsigned int count, struct qaob *aob); extern int qdio_start_irq(struct ccw_device *cdev); diff --git a/arch/s390/include/asm/sclp.h b/arch/s390/include/asm/sclp.h index e3ae937bef1c..c68ea35de498 100644 --- a/arch/s390/include/asm/sclp.h +++ b/arch/s390/include/asm/sclp.h @@ -117,6 +117,7 @@ struct zpci_report_error_header { extern char *sclp_early_sccb; +void sclp_early_adjust_va(void); void sclp_early_set_buffer(void *sccb); int sclp_early_read_info(void); int sclp_early_read_storage_info(void); diff --git a/arch/s390/include/asm/sections.h b/arch/s390/include/asm/sections.h index 85881dd48022..3fecaa4e8b74 100644 --- a/arch/s390/include/asm/sections.h +++ b/arch/s390/include/asm/sections.h @@ -2,20 +2,8 @@ #ifndef _S390_SECTIONS_H #define _S390_SECTIONS_H -#define arch_is_kernel_initmem_freed arch_is_kernel_initmem_freed - #include <asm-generic/sections.h> -extern bool initmem_freed; - -static inline int arch_is_kernel_initmem_freed(unsigned long addr) -{ - if (!initmem_freed) - return 0; - return addr >= (unsigned long)__init_begin && - addr < (unsigned long)__init_end; -} - /* * .boot.data section contains variables "shared" between the decompressor and * the decompressed kernel. The decompressor will store values in them, and diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h index b6606ffd85d8..77e6506898f5 100644 --- a/arch/s390/include/asm/setup.h +++ b/arch/s390/include/asm/setup.h @@ -11,8 +11,8 @@ #include <linux/build_bug.h> #define PARMAREA 0x10400 -#define HEAD_END 0x11000 +#define COMMAND_LINE_SIZE CONFIG_COMMAND_LINE_SIZE /* * Machine features detected in early.c */ @@ -43,6 +43,8 @@ #define STARTUP_NORMAL_OFFSET 0x10000 #define STARTUP_KDUMP_OFFSET 0x10010 +#define LEGACY_COMMAND_LINE_SIZE 896 + #ifndef __ASSEMBLY__ #include <asm/lowcore.h> @@ -55,8 +57,9 @@ struct parmarea { unsigned long oldmem_base; /* 0x10418 */ unsigned long oldmem_size; /* 0x10420 */ unsigned long kernel_version; /* 0x10428 */ - char pad1[0x10480 - 0x10430]; /* 0x10430 - 0x10480 */ - char command_line[ARCH_COMMAND_LINE_SIZE]; /* 0x10480 */ + unsigned long max_command_line_size; /* 0x10430 */ + char pad1[0x10480-0x10438]; /* 0x10438 - 0x10480 */ + char command_line[COMMAND_LINE_SIZE]; /* 0x10480 */ }; extern struct parmarea parmarea; diff --git a/arch/s390/include/asm/spinlock.h b/arch/s390/include/asm/spinlock.h index ef59588a3042..888a2f1c9ee3 100644 --- a/arch/s390/include/asm/spinlock.h +++ b/arch/s390/include/asm/spinlock.h @@ -67,14 +67,6 @@ static inline void arch_spin_lock(arch_spinlock_t *lp) arch_spin_lock_wait(lp); } -static inline void arch_spin_lock_flags(arch_spinlock_t *lp, - unsigned long flags) -{ - if (!arch_spin_trylock_once(lp)) - arch_spin_lock_wait(lp); -} -#define arch_spin_lock_flags arch_spin_lock_flags - static inline int arch_spin_trylock(arch_spinlock_t *lp) { if (!arch_spin_trylock_once(lp)) diff --git a/arch/s390/include/asm/string.h b/arch/s390/include/asm/string.h index 4fd66c5e8934..3fae93ddb322 100644 --- a/arch/s390/include/asm/string.h +++ b/arch/s390/include/asm/string.h @@ -31,22 +31,18 @@ void *memmove(void *dest, const void *src, size_t n); #define __HAVE_ARCH_STRCMP /* arch function */ #define __HAVE_ARCH_STRCPY /* inline & arch function */ #define __HAVE_ARCH_STRLCAT /* arch function */ -#define __HAVE_ARCH_STRLCPY /* arch function */ #define __HAVE_ARCH_STRLEN /* inline & arch function */ #define __HAVE_ARCH_STRNCAT /* arch function */ #define __HAVE_ARCH_STRNCPY /* arch function */ #define __HAVE_ARCH_STRNLEN /* inline & arch function */ -#define __HAVE_ARCH_STRRCHR /* arch function */ #define __HAVE_ARCH_STRSTR /* arch function */ /* Prototypes for non-inlined arch strings functions. */ int memcmp(const void *s1, const void *s2, size_t n); int strcmp(const char *s1, const char *s2); size_t strlcat(char *dest, const char *src, size_t n); -size_t strlcpy(char *dest, const char *src, size_t size); char *strncat(char *dest, const char *src, size_t n); char *strncpy(char *dest, const char *src, size_t n); -char *strrchr(const char *s, int c); char *strstr(const char *s1, const char *s2); #endif /* !CONFIG_KASAN */ diff --git a/arch/s390/include/asm/text-patching.h b/arch/s390/include/asm/text-patching.h new file mode 100644 index 000000000000..b219056a8817 --- /dev/null +++ b/arch/s390/include/asm/text-patching.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _ASM_S390_TEXT_PATCHING_H +#define _ASM_S390_TEXT_PATCHING_H + +#include <asm/barrier.h> + +static __always_inline void sync_core(void) +{ + bcr_serialize(); +} + +void text_poke_sync(void); +void text_poke_sync_lock(void); + +#endif /* _ASM_S390_TEXT_PATCHING_H */ diff --git a/arch/s390/include/asm/thread_info.h b/arch/s390/include/asm/thread_info.h index e6674796aa6f..b2ffcb4fe000 100644 --- a/arch/s390/include/asm/thread_info.h +++ b/arch/s390/include/asm/thread_info.h @@ -37,6 +37,7 @@ struct thread_info { unsigned long flags; /* low level flags */ unsigned long syscall_work; /* SYSCALL_WORK_ flags */ + unsigned int cpu; /* current CPU */ }; /* diff --git a/arch/s390/include/asm/uv.h b/arch/s390/include/asm/uv.h index fe92a4caf5ec..72d3e49c2860 100644 --- a/arch/s390/include/asm/uv.h +++ b/arch/s390/include/asm/uv.h @@ -18,6 +18,11 @@ #include <asm/page.h> #include <asm/gmap.h> +#define UVC_CC_OK 0 +#define UVC_CC_ERROR 1 +#define UVC_CC_BUSY 2 +#define UVC_CC_PARTIAL 3 + #define UVC_RC_EXECUTED 0x0001 #define UVC_RC_INV_CMD 0x0002 #define UVC_RC_INV_STATE 0x0003 @@ -351,8 +356,9 @@ static inline int is_prot_virt_host(void) } int gmap_make_secure(struct gmap *gmap, unsigned long gaddr, void *uvcb); -int uv_destroy_page(unsigned long paddr); +int uv_destroy_owned_page(unsigned long paddr); int uv_convert_from_secure(unsigned long paddr); +int uv_convert_owned_from_secure(unsigned long paddr); int gmap_convert_to_secure(struct gmap *gmap, unsigned long gaddr); void setup_uv(void); @@ -360,7 +366,7 @@ void setup_uv(void); #define is_prot_virt_host() 0 static inline void setup_uv(void) {} -static inline int uv_destroy_page(unsigned long paddr) +static inline int uv_destroy_owned_page(unsigned long paddr) { return 0; } @@ -369,6 +375,11 @@ static inline int uv_convert_from_secure(unsigned long paddr) { return 0; } + +static inline int uv_convert_owned_from_secure(unsigned long paddr) +{ + return 0; +} #endif #endif /* _ASM_S390_UV_H */ diff --git a/arch/s390/include/uapi/asm/setup.h b/arch/s390/include/uapi/asm/setup.h index 1f8803a31079..598d769e76df 100644 --- a/arch/s390/include/uapi/asm/setup.h +++ b/arch/s390/include/uapi/asm/setup.h @@ -1,14 +1 @@ /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -/* - * S390 version - * Copyright IBM Corp. 1999, 2010 - */ - -#ifndef _UAPI_ASM_S390_SETUP_H -#define _UAPI_ASM_S390_SETUP_H - -#define COMMAND_LINE_SIZE 4096 - -#define ARCH_COMMAND_LINE_SIZE 896 - -#endif /* _UAPI_ASM_S390_SETUP_H */ diff --git a/arch/s390/kernel/alternative.c b/arch/s390/kernel/alternative.c index c22ea1c3ef84..cce0ddee2d02 100644 --- a/arch/s390/kernel/alternative.c +++ b/arch/s390/kernel/alternative.c @@ -1,5 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/module.h> +#include <linux/cpu.h> +#include <linux/smp.h> +#include <asm/text-patching.h> #include <asm/alternative.h> #include <asm/facility.h> #include <asm/nospec-branch.h> @@ -110,3 +113,20 @@ void __init apply_alternative_instructions(void) { apply_alternatives(__alt_instructions, __alt_instructions_end); } + +static void do_sync_core(void *info) +{ + sync_core(); +} + +void text_poke_sync(void) +{ + on_each_cpu(do_sync_core, NULL, 1); +} + +void text_poke_sync_lock(void) +{ + cpus_read_lock(); + text_poke_sync(); + cpus_read_unlock(); +} diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c index b57da9338588..8e00bb228662 100644 --- a/arch/s390/kernel/asm-offsets.c +++ b/arch/s390/kernel/asm-offsets.c @@ -35,6 +35,7 @@ int main(void) OFFSET(__PT_ORIG_GPR2, pt_regs, orig_gpr2); OFFSET(__PT_FLAGS, pt_regs, flags); OFFSET(__PT_CR1, pt_regs, cr1); + OFFSET(__PT_LAST_BREAK, pt_regs, last_break); DEFINE(__PT_SIZE, sizeof(struct pt_regs)); BLANK(); /* stack_frame offsets */ @@ -45,6 +46,7 @@ int main(void) OFFSET(__SF_SIE_SAVEAREA, stack_frame, empty1[2]); OFFSET(__SF_SIE_REASON, stack_frame, empty1[3]); OFFSET(__SF_SIE_FLAGS, stack_frame, empty1[4]); + DEFINE(STACK_FRAME_OVERHEAD, sizeof(struct stack_frame)); BLANK(); /* idle data offsets */ OFFSET(__CLOCK_IDLE_ENTER, s390_idle_data, clock_idle_enter); @@ -77,7 +79,7 @@ int main(void) OFFSET(__LC_MCCK_CODE, lowcore, mcck_interruption_code); OFFSET(__LC_EXT_DAMAGE_CODE, lowcore, external_damage_code); OFFSET(__LC_MCCK_FAIL_STOR_ADDR, lowcore, failing_storage_address); - OFFSET(__LC_LAST_BREAK, lowcore, breaking_event_addr); + OFFSET(__LC_PGM_LAST_BREAK, lowcore, pgm_last_break); OFFSET(__LC_RETURN_LPSWE, lowcore, return_lpswe); OFFSET(__LC_RETURN_MCCK_LPSWE, lowcore, return_mcck_lpswe); OFFSET(__LC_RST_OLD_PSW, lowcore, restart_old_psw); @@ -126,6 +128,7 @@ int main(void) OFFSET(__LC_PREEMPT_COUNT, lowcore, preempt_count); OFFSET(__LC_GMAP, lowcore, gmap); OFFSET(__LC_BR_R1, lowcore, br_r1_trampoline); + OFFSET(__LC_LAST_BREAK, lowcore, last_break); /* software defined ABI-relevant lowcore locations 0xe00 - 0xe20 */ OFFSET(__LC_DUMP_REIPL, lowcore, ipib); /* hardware defined lowcore locations 0x1000 - 0x18ff */ @@ -139,6 +142,7 @@ int main(void) OFFSET(__LC_TOD_PROGREG_SAVE_AREA, lowcore, tod_progreg_save_area); OFFSET(__LC_CPU_TIMER_SAVE_AREA, lowcore, cpu_timer_save_area); OFFSET(__LC_CLOCK_COMP_SAVE_AREA, lowcore, clock_comp_save_area); + OFFSET(__LC_LAST_BREAK_SAVE_AREA, lowcore, last_break_save_area); OFFSET(__LC_AREGS_SAVE_AREA, lowcore, access_regs_save_area); OFFSET(__LC_CREGS_SAVE_AREA, lowcore, cregs_save_area); OFFSET(__LC_PGM_TDB, lowcore, pgm_tdb); @@ -160,5 +164,6 @@ int main(void) DEFINE(OLDMEM_BASE, PARMAREA + offsetof(struct parmarea, oldmem_base)); DEFINE(OLDMEM_SIZE, PARMAREA + offsetof(struct parmarea, oldmem_size)); DEFINE(COMMAND_LINE, PARMAREA + offsetof(struct parmarea, command_line)); + DEFINE(MAX_COMMAND_LINE_SIZE, PARMAREA + offsetof(struct parmarea, max_command_line_size)); return 0; } diff --git a/arch/s390/kernel/audit.c b/arch/s390/kernel/audit.c index d395c6c9944c..02051a596b87 100644 --- a/arch/s390/kernel/audit.c +++ b/arch/s390/kernel/audit.c @@ -47,15 +47,17 @@ int audit_classify_syscall(int abi, unsigned syscall) #endif switch(syscall) { case __NR_open: - return 2; + return AUDITSC_OPEN; case __NR_openat: - return 3; + return AUDITSC_OPENAT; case __NR_socketcall: - return 4; + return AUDITSC_SOCKETCALL; case __NR_execve: - return 5; + return AUDITSC_EXECVE; + case __NR_openat2: + return AUDITSC_OPENAT2; default: - return 0; + return AUDITSC_NATIVE; } } diff --git a/arch/s390/kernel/compat_audit.c b/arch/s390/kernel/compat_audit.c index 444fb1f66944..a7c46e8310f0 100644 --- a/arch/s390/kernel/compat_audit.c +++ b/arch/s390/kernel/compat_audit.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #undef __s390x__ +#include <linux/audit_arch.h> #include <asm/unistd.h> #include "audit.h" @@ -32,14 +33,16 @@ int s390_classify_syscall(unsigned syscall) { switch(syscall) { case __NR_open: - return 2; + return AUDITSC_OPEN; case __NR_openat: - return 3; + return AUDITSC_OPENAT; case __NR_socketcall: - return 4; + return AUDITSC_SOCKETCALL; case __NR_execve: - return 5; + return AUDITSC_EXECVE; + case __NR_openat2: + return AUDITSC_OPENAT2; default: - return 1; + return AUDITSC_COMPAT; } } diff --git a/arch/s390/kernel/cpcmd.c b/arch/s390/kernel/cpcmd.c index 54efc279f54e..72e106cfd8c7 100644 --- a/arch/s390/kernel/cpcmd.c +++ b/arch/s390/kernel/cpcmd.c @@ -29,7 +29,7 @@ static int diag8_noresponse(int cmdlen) asm volatile( " diag %[rx],%[ry],0x8\n" : [ry] "+&d" (cmdlen) - : [rx] "d" ((addr_t) cpcmd_buf) + : [rx] "d" (__pa(cpcmd_buf)) : "cc"); return cmdlen; } @@ -39,8 +39,8 @@ static int diag8_response(int cmdlen, char *response, int *rlen) union register_pair rx, ry; int cc; - rx.even = (addr_t) cpcmd_buf; - rx.odd = (addr_t) response; + rx.even = __pa(cpcmd_buf); + rx.odd = __pa(response); ry.even = cmdlen | 0x40000000L; ry.odd = *rlen; asm volatile( diff --git a/arch/s390/kernel/dumpstack.c b/arch/s390/kernel/dumpstack.c index db1bc00229ca..85f326e258df 100644 --- a/arch/s390/kernel/dumpstack.c +++ b/arch/s390/kernel/dumpstack.c @@ -152,7 +152,7 @@ void show_stack(struct task_struct *task, unsigned long *stack, static void show_last_breaking_event(struct pt_regs *regs) { printk("Last Breaking-Event-Address:\n"); - printk(" [<%016lx>] %pSR\n", regs->args[0], (void *)regs->args[0]); + printk(" [<%016lx>] %pSR\n", regs->last_break, (void *)regs->last_break); } void show_registers(struct pt_regs *regs) diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c index 9857cb046726..3cdf68c53614 100644 --- a/arch/s390/kernel/early.c +++ b/arch/s390/kernel/early.c @@ -280,7 +280,7 @@ char __bootdata(early_command_line)[COMMAND_LINE_SIZE]; static void __init setup_boot_command_line(void) { /* copy arch command line */ - strlcpy(boot_command_line, early_command_line, ARCH_COMMAND_LINE_SIZE); + strlcpy(boot_command_line, early_command_line, COMMAND_LINE_SIZE); } static void __init check_image_bootable(void) @@ -296,6 +296,7 @@ static void __init check_image_bootable(void) void __init startup_init(void) { + sclp_early_adjust_va(); reset_tod_clock(); check_image_bootable(); time_early_init(); diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 4c9b967290ae..01bae1d51113 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -52,6 +52,22 @@ STACK_INIT = STACK_SIZE - STACK_FRAME_OVERHEAD - __PT_SIZE _LPP_OFFSET = __LC_LPP + .macro STBEAR address + ALTERNATIVE "", ".insn s,0xb2010000,\address", 193 + .endm + + .macro LBEAR address + ALTERNATIVE "", ".insn s,0xb2000000,\address", 193 + .endm + + .macro LPSWEY address,lpswe + ALTERNATIVE "b \lpswe", ".insn siy,0xeb0000000071,\address,0", 193 + .endm + + .macro MBEAR reg + ALTERNATIVE "", __stringify(mvc __PT_LAST_BREAK(8,\reg),__LC_LAST_BREAK), 193 + .endm + .macro CHECK_STACK savearea #ifdef CONFIG_CHECK_STACK tml %r15,STACK_SIZE - CONFIG_STACK_GUARD @@ -302,6 +318,7 @@ ENTRY(system_call) BPOFF lghi %r14,0 .Lsysc_per: + STBEAR __LC_LAST_BREAK lctlg %c1,%c1,__LC_KERNEL_ASCE lg %r12,__LC_CURRENT lg %r15,__LC_KERNEL_STACK @@ -321,14 +338,16 @@ ENTRY(system_call) xgr %r11,%r11 la %r2,STACK_FRAME_OVERHEAD(%r15) # pointer to pt_regs mvc __PT_R8(64,%r2),__LC_SAVE_AREA_SYNC + MBEAR %r2 lgr %r3,%r14 brasl %r14,__do_syscall lctlg %c1,%c1,__LC_USER_ASCE mvc __LC_RETURN_PSW(16),STACK_FRAME_OVERHEAD+__PT_PSW(%r15) BPEXIT __TI_flags(%r12),_TIF_ISOLATE_BP + LBEAR STACK_FRAME_OVERHEAD+__PT_LAST_BREAK(%r15) lmg %r0,%r15,STACK_FRAME_OVERHEAD+__PT_R0(%r15) stpt __LC_EXIT_TIMER - b __LC_RETURN_LPSWE + LPSWEY __LC_RETURN_PSW,__LC_RETURN_LPSWE ENDPROC(system_call) # @@ -340,9 +359,10 @@ ENTRY(ret_from_fork) lctlg %c1,%c1,__LC_USER_ASCE mvc __LC_RETURN_PSW(16),STACK_FRAME_OVERHEAD+__PT_PSW(%r15) BPEXIT __TI_flags(%r12),_TIF_ISOLATE_BP + LBEAR STACK_FRAME_OVERHEAD+__PT_LAST_BREAK(%r15) lmg %r0,%r15,STACK_FRAME_OVERHEAD+__PT_R0(%r15) stpt __LC_EXIT_TIMER - b __LC_RETURN_LPSWE + LPSWEY __LC_RETURN_PSW,__LC_RETURN_LPSWE ENDPROC(ret_from_fork) /* @@ -382,6 +402,7 @@ ENTRY(pgm_check_handler) xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) stmg %r0,%r7,__PT_R0(%r11) mvc __PT_R8(64,%r11),__LC_SAVE_AREA_SYNC + mvc __PT_LAST_BREAK(8,%r11),__LC_PGM_LAST_BREAK stmg %r8,%r9,__PT_PSW(%r11) # clear user controlled registers to prevent speculative use @@ -401,8 +422,9 @@ ENTRY(pgm_check_handler) stpt __LC_EXIT_TIMER .Lpgm_exit_kernel: mvc __LC_RETURN_PSW(16),STACK_FRAME_OVERHEAD+__PT_PSW(%r15) + LBEAR STACK_FRAME_OVERHEAD+__PT_LAST_BREAK(%r15) lmg %r0,%r15,STACK_FRAME_OVERHEAD+__PT_R0(%r15) - b __LC_RETURN_LPSWE + LPSWEY __LC_RETURN_PSW,__LC_RETURN_LPSWE # # single stepped system call @@ -412,7 +434,8 @@ ENTRY(pgm_check_handler) larl %r14,.Lsysc_per stg %r14,__LC_RETURN_PSW+8 lghi %r14,1 - lpswe __LC_RETURN_PSW # branch to .Lsysc_per + LBEAR __LC_PGM_LAST_BREAK + LPSWEY __LC_RETURN_PSW,__LC_RETURN_LPSWE # branch to .Lsysc_per ENDPROC(pgm_check_handler) /* @@ -422,6 +445,7 @@ ENDPROC(pgm_check_handler) ENTRY(\name) STCK __LC_INT_CLOCK stpt __LC_SYS_ENTER_TIMER + STBEAR __LC_LAST_BREAK BPOFF stmg %r8,%r15,__LC_SAVE_AREA_ASYNC lg %r12,__LC_CURRENT @@ -453,6 +477,7 @@ ENTRY(\name) xgr %r10,%r10 xc __PT_FLAGS(8,%r11),__PT_FLAGS(%r11) mvc __PT_R8(64,%r11),__LC_SAVE_AREA_ASYNC + MBEAR %r11 stmg %r8,%r9,__PT_PSW(%r11) tm %r8,0x0001 # coming from user space? jno 1f @@ -465,8 +490,9 @@ ENTRY(\name) lctlg %c1,%c1,__LC_USER_ASCE BPEXIT __TI_flags(%r12),_TIF_ISOLATE_BP stpt __LC_EXIT_TIMER -2: lmg %r0,%r15,__PT_R0(%r11) - b __LC_RETURN_LPSWE +2: LBEAR __PT_LAST_BREAK(%r11) + lmg %r0,%r15,__PT_R0(%r11) + LPSWEY __LC_RETURN_PSW,__LC_RETURN_LPSWE ENDPROC(\name) .endm @@ -505,6 +531,7 @@ ENTRY(mcck_int_handler) BPOFF la %r1,4095 # validate r1 spt __LC_CPU_TIMER_SAVE_AREA-4095(%r1) # validate cpu timer + LBEAR __LC_LAST_BREAK_SAVE_AREA-4095(%r1) # validate bear lmg %r0,%r15,__LC_GPREGS_SAVE_AREA-4095(%r1)# validate gprs lg %r12,__LC_CURRENT lmg %r8,%r9,__LC_MCK_OLD_PSW @@ -591,8 +618,10 @@ ENTRY(mcck_int_handler) jno 0f BPEXIT __TI_flags(%r12),_TIF_ISOLATE_BP stpt __LC_EXIT_TIMER -0: lmg %r11,%r15,__PT_R11(%r11) - b __LC_RETURN_MCCK_LPSWE +0: ALTERNATIVE "", __stringify(lghi %r12,__LC_LAST_BREAK_SAVE_AREA),193 + LBEAR 0(%r12) + lmg %r11,%r15,__PT_R11(%r11) + LPSWEY __LC_RETURN_MCCK_PSW,__LC_RETURN_MCCK_LPSWE .Lmcck_panic: /* diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h index 7f2696e8d511..6083090be1f4 100644 --- a/arch/s390/kernel/entry.h +++ b/arch/s390/kernel/entry.h @@ -70,5 +70,6 @@ extern struct exception_table_entry _stop_amode31_ex_table[]; #define __amode31_data __section(".amode31.data") #define __amode31_ref __section(".amode31.refs") extern long _start_amode31_refs[], _end_amode31_refs[]; +extern unsigned long __amode31_base; #endif /* _ENTRY_H */ diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c index 1d94ffdf347b..5510c7d10ddc 100644 --- a/arch/s390/kernel/ftrace.c +++ b/arch/s390/kernel/ftrace.c @@ -17,6 +17,7 @@ #include <linux/kprobes.h> #include <trace/syscall.h> #include <asm/asm-offsets.h> +#include <asm/text-patching.h> #include <asm/cacheflush.h> #include <asm/ftrace.lds.h> #include <asm/nospec-branch.h> @@ -80,17 +81,6 @@ asm( #ifdef CONFIG_MODULES static char *ftrace_plt; - -asm( - " .data\n" - "ftrace_plt_template:\n" - " basr %r1,%r0\n" - " lg %r1,0f-.(%r1)\n" - " br %r1\n" - "0: .quad ftrace_caller\n" - "ftrace_plt_template_end:\n" - " .previous\n" -); #endif /* CONFIG_MODULES */ static const char *ftrace_shared_hotpatch_trampoline(const char **end) @@ -116,7 +106,7 @@ static const char *ftrace_shared_hotpatch_trampoline(const char **end) bool ftrace_need_init_nop(void) { - return ftrace_shared_hotpatch_trampoline(NULL); + return true; } int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec) @@ -175,28 +165,6 @@ int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, return 0; } -static void ftrace_generate_nop_insn(struct ftrace_insn *insn) -{ - /* brcl 0,0 */ - insn->opc = 0xc004; - insn->disp = 0; -} - -static void ftrace_generate_call_insn(struct ftrace_insn *insn, - unsigned long ip) -{ - unsigned long target; - - /* brasl r0,ftrace_caller */ - target = FTRACE_ADDR; -#ifdef CONFIG_MODULES - if (is_module_addr((void *)ip)) - target = (unsigned long)ftrace_plt; -#endif /* CONFIG_MODULES */ - insn->opc = 0xc005; - insn->disp = (target - ip) / 2; -} - static void brcl_disable(void *brcl) { u8 op = 0x04; /* set mask field to zero */ @@ -207,23 +175,7 @@ static void brcl_disable(void *brcl) int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, unsigned long addr) { - struct ftrace_insn orig, new, old; - - if (ftrace_shared_hotpatch_trampoline(NULL)) { - brcl_disable((void *)rec->ip); - return 0; - } - - if (copy_from_kernel_nofault(&old, (void *) rec->ip, sizeof(old))) - return -EFAULT; - /* Replace ftrace call with a nop. */ - ftrace_generate_call_insn(&orig, rec->ip); - ftrace_generate_nop_insn(&new); - - /* Verify that the to be replaced code matches what we expect. */ - if (memcmp(&orig, &old, sizeof(old))) - return -EINVAL; - s390_kernel_write((void *) rec->ip, &new, sizeof(new)); + brcl_disable((void *)rec->ip); return 0; } @@ -236,23 +188,7 @@ static void brcl_enable(void *brcl) int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) { - struct ftrace_insn orig, new, old; - - if (ftrace_shared_hotpatch_trampoline(NULL)) { - brcl_enable((void *)rec->ip); - return 0; - } - - if (copy_from_kernel_nofault(&old, (void *) rec->ip, sizeof(old))) - return -EFAULT; - /* 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; - s390_kernel_write((void *) rec->ip, &new, sizeof(new)); + brcl_enable((void *)rec->ip); return 0; } @@ -262,29 +198,18 @@ int ftrace_update_ftrace_func(ftrace_func_t func) return 0; } -int __init ftrace_dyn_arch_init(void) -{ - return 0; -} - void arch_ftrace_update_code(int command) { - if (ftrace_shared_hotpatch_trampoline(NULL)) - ftrace_modify_all_code(command); - else - ftrace_run_stop_machine(command); -} - -static void __ftrace_sync(void *dummy) -{ + ftrace_modify_all_code(command); } int ftrace_arch_code_modify_post_process(void) { - if (ftrace_shared_hotpatch_trampoline(NULL)) { - /* Send SIGP to the other CPUs, so they see the new code. */ - smp_call_function(__ftrace_sync, NULL, 1); - } + /* + * Flush any pre-fetched instructions on all + * CPUs to make the new code visible. + */ + text_poke_sync_lock(); return 0; } @@ -299,10 +224,6 @@ static int __init ftrace_plt_init(void) panic("cannot allocate ftrace plt\n"); start = ftrace_shared_hotpatch_trampoline(&end); - if (!start) { - start = ftrace_plt_template; - end = ftrace_plt_template_end; - } memcpy(ftrace_plt, start, end - start); set_memory_ro((unsigned long)ftrace_plt, 1); return 0; @@ -342,12 +263,14 @@ NOKPROBE_SYMBOL(prepare_ftrace_return); int ftrace_enable_ftrace_graph_caller(void) { brcl_disable(ftrace_graph_caller); + text_poke_sync_lock(); return 0; } int ftrace_disable_ftrace_graph_caller(void) { brcl_enable(ftrace_graph_caller); + text_poke_sync_lock(); return 0; } diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S index 114b5490ad8e..42f9a325a257 100644 --- a/arch/s390/kernel/head64.S +++ b/arch/s390/kernel/head64.S @@ -20,8 +20,6 @@ __HEAD ENTRY(startup_continue) larl %r1,tod_clock_base mvc 0(16,%r1),__LC_BOOT_CLOCK - larl %r13,.LPG1 # get base - lctlg %c0,%c15,.Lctl-.LPG1(%r13) # load control registers # # Setup stack # @@ -42,19 +40,3 @@ ENTRY(startup_continue) .align 16 .LPG1: .Ldw: .quad 0x0002000180000000,0x0000000000000000 -.Lctl: .quad 0x04040000 # cr0: AFP registers & secondary space - .quad 0 # cr1: primary space segment table - .quad 0 # cr2: dispatchable unit control table - .quad 0 # cr3: instruction authorization - .quad 0xffff # cr4: instruction authorization - .quad 0 # cr5: primary-aste origin - .quad 0 # cr6: I/O interrupts - .quad 0 # cr7: secondary space segment table - .quad 0x0000000000008000 # cr8: access registers translation - .quad 0 # cr9: tracing off - .quad 0 # cr10: tracing off - .quad 0 # cr11: tracing off - .quad 0 # cr12: tracing off - .quad 0 # cr13: home space segment table - .quad 0xc0000000 # cr14: machine check handling off - .quad 0 # cr15: linkage stack operations diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c index 3a3145c4a3ba..0df83ecaa2e0 100644 --- a/arch/s390/kernel/irq.c +++ b/arch/s390/kernel/irq.c @@ -140,8 +140,11 @@ void noinstr do_io_irq(struct pt_regs *regs) irq_enter(); - if (user_mode(regs)) + if (user_mode(regs)) { update_timer_sys(); + if (static_branch_likely(&cpu_has_bear)) + current->thread.last_break = regs->last_break; + } from_idle = !user_mode(regs) && regs->psw.addr == (unsigned long)psw_idle_exit; if (from_idle) @@ -171,8 +174,11 @@ void noinstr do_ext_irq(struct pt_regs *regs) irq_enter(); - if (user_mode(regs)) + if (user_mode(regs)) { update_timer_sys(); + if (static_branch_likely(&cpu_has_bear)) + current->thread.last_break = regs->last_break; + } regs->int_code = S390_lowcore.ext_int_code_addr; regs->int_parm = S390_lowcore.ext_params; diff --git a/arch/s390/kernel/jump_label.c b/arch/s390/kernel/jump_label.c index 9156653b56f6..6bec000c6c1c 100644 --- a/arch/s390/kernel/jump_label.c +++ b/arch/s390/kernel/jump_label.c @@ -6,8 +6,9 @@ * Author(s): Jan Glauber <jang@linux.vnet.ibm.com> */ #include <linux/uaccess.h> -#include <linux/stop_machine.h> #include <linux/jump_label.h> +#include <linux/module.h> +#include <asm/text-patching.h> #include <asm/ipl.h> struct insn { @@ -48,9 +49,9 @@ static struct insn orignop = { .offset = JUMP_LABEL_NOP_OFFSET >> 1, }; -static void __jump_label_transform(struct jump_entry *entry, - enum jump_label_type type, - int init) +static void jump_label_transform(struct jump_entry *entry, + enum jump_label_type type, + int init) { void *code = (void *)jump_entry_code(entry); struct insn old, new; @@ -72,19 +73,28 @@ static void __jump_label_transform(struct jump_entry *entry, s390_kernel_write(code, &new, sizeof(new)); } -static void __jump_label_sync(void *dummy) +void arch_jump_label_transform(struct jump_entry *entry, + enum jump_label_type type) { + jump_label_transform(entry, type, 0); + text_poke_sync(); } -void arch_jump_label_transform(struct jump_entry *entry, - enum jump_label_type type) +bool arch_jump_label_transform_queue(struct jump_entry *entry, + enum jump_label_type type) +{ + jump_label_transform(entry, type, 0); + return true; +} + +void arch_jump_label_transform_apply(void) { - __jump_label_transform(entry, type, 0); - smp_call_function(__jump_label_sync, NULL, 1); + text_poke_sync(); } -void arch_jump_label_transform_static(struct jump_entry *entry, - enum jump_label_type type) +void __init_or_module arch_jump_label_transform_static(struct jump_entry *entry, + enum jump_label_type type) { - __jump_label_transform(entry, type, 1); + jump_label_transform(entry, type, 1); + text_poke_sync(); } diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c index 52d056a5f89f..e27a7d3b0364 100644 --- a/arch/s390/kernel/kprobes.c +++ b/arch/s390/kernel/kprobes.c @@ -7,6 +7,8 @@ * s390 port, used ppc64 as template. Mike Grundy <grundym@us.ibm.com> */ +#define pr_fmt(fmt) "kprobes: " fmt + #include <linux/moduleloader.h> #include <linux/kprobes.h> #include <linux/ptrace.h> @@ -120,9 +122,55 @@ static void s390_free_insn_slot(struct kprobe *p) } NOKPROBE_SYMBOL(s390_free_insn_slot); +/* Check if paddr is at an instruction boundary */ +static bool can_probe(unsigned long paddr) +{ + unsigned long addr, offset = 0; + kprobe_opcode_t insn; + struct kprobe *kp; + + if (paddr & 0x01) + return false; + + if (!kallsyms_lookup_size_offset(paddr, NULL, &offset)) + return false; + + /* Decode instructions */ + addr = paddr - offset; + while (addr < paddr) { + if (copy_from_kernel_nofault(&insn, (void *)addr, sizeof(insn))) + return false; + + if (insn >> 8 == 0) { + if (insn != BREAKPOINT_INSTRUCTION) { + /* + * Note that QEMU inserts opcode 0x0000 to implement + * software breakpoints for guests. Since the size of + * the original instruction is unknown, stop following + * instructions and prevent setting a kprobe. + */ + return false; + } + /* + * Check if the instruction has been modified by another + * kprobe, in which case the original instruction is + * decoded. + */ + kp = get_kprobe((void *)addr); + if (!kp) { + /* not a kprobe */ + return false; + } + insn = kp->opcode; + } + addr += insn_length(insn >> 8); + } + return addr == paddr; +} + int arch_prepare_kprobe(struct kprobe *p) { - if ((unsigned long) p->addr & 0x01) + if (!can_probe((unsigned long)p->addr)) return -EINVAL; /* Make sure the probe isn't going on a difficult instruction */ if (probe_is_prohibited_opcode(p->addr)) @@ -240,7 +288,7 @@ void arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs) ri->fp = NULL; /* Replace the return addr with trampoline addr */ - regs->gprs[14] = (unsigned long) &kretprobe_trampoline; + regs->gprs[14] = (unsigned long) &__kretprobe_trampoline; } NOKPROBE_SYMBOL(arch_prepare_kretprobe); @@ -259,7 +307,7 @@ static void kprobe_reenter_check(struct kprobe_ctlblk *kcb, struct kprobe *p) * is a BUG. The code path resides in the .kprobes.text * section and is executed with interrupts disabled. */ - pr_err("Invalid kprobe detected.\n"); + pr_err("Failed to recover from reentered kprobes.\n"); dump_kprobe(p); BUG(); } @@ -332,8 +380,8 @@ NOKPROBE_SYMBOL(kprobe_handler); */ static void __used kretprobe_trampoline_holder(void) { - asm volatile(".global kretprobe_trampoline\n" - "kretprobe_trampoline: bcr 0,0\n"); + asm volatile(".global __kretprobe_trampoline\n" + "__kretprobe_trampoline: bcr 0,0\n"); } /* @@ -341,7 +389,7 @@ static void __used kretprobe_trampoline_holder(void) */ static int trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) { - regs->psw.addr = __kretprobe_trampoline_handler(regs, &kretprobe_trampoline, NULL); + regs->psw.addr = __kretprobe_trampoline_handler(regs, NULL); /* * By returning a non-zero value, we are telling * kprobe_handler() that we don't want the post_handler @@ -507,7 +555,7 @@ int kprobe_exceptions_notify(struct notifier_block *self, NOKPROBE_SYMBOL(kprobe_exceptions_notify); static struct kprobe trampoline = { - .addr = (kprobe_opcode_t *) &kretprobe_trampoline, + .addr = (kprobe_opcode_t *) &__kretprobe_trampoline, .pre_handler = trampoline_probe_handler }; @@ -518,6 +566,6 @@ int __init arch_init_kprobes(void) int arch_trampoline_kprobe(struct kprobe *p) { - return p->addr == (kprobe_opcode_t *) &kretprobe_trampoline; + return p->addr == (kprobe_opcode_t *) &__kretprobe_trampoline; } NOKPROBE_SYMBOL(arch_trampoline_kprobe); diff --git a/arch/s390/kernel/machine_kexec_file.c b/arch/s390/kernel/machine_kexec_file.c index f9e4baa64b67..528edff085d9 100644 --- a/arch/s390/kernel/machine_kexec_file.c +++ b/arch/s390/kernel/machine_kexec_file.c @@ -216,7 +216,9 @@ void *kexec_file_add_components(struct kimage *image, int (*add_kernel)(struct kimage *image, struct s390_load_data *data)) { + unsigned long max_command_line_size = LEGACY_COMMAND_LINE_SIZE; struct s390_load_data data = {0}; + unsigned long minsize; int ret; data.report = ipl_report_init(&ipl_block); @@ -227,10 +229,23 @@ void *kexec_file_add_components(struct kimage *image, if (ret) goto out; - if (image->cmdline_buf_len >= ARCH_COMMAND_LINE_SIZE) { - ret = -EINVAL; + ret = -EINVAL; + minsize = PARMAREA + offsetof(struct parmarea, command_line); + if (image->kernel_buf_len < minsize) goto out; - } + + if (data.parm->max_command_line_size) + max_command_line_size = data.parm->max_command_line_size; + + if (minsize + max_command_line_size < minsize) + goto out; + + if (image->kernel_buf_len < minsize + max_command_line_size) + goto out; + + if (image->cmdline_buf_len >= max_command_line_size) + goto out; + memcpy(data.parm->command_line, image->cmdline_buf, image->cmdline_buf_len); @@ -307,17 +322,3 @@ int arch_kexec_apply_relocations_add(struct purgatory_info *pi, } return 0; } - -int arch_kexec_kernel_image_probe(struct kimage *image, void *buf, - unsigned long buf_len) -{ - /* A kernel must be at least large enough to contain head.S. During - * load memory in head.S will be accessed, e.g. to register the next - * command line. If the next kernel were smaller the current kernel - * will panic at load. - */ - if (buf_len < HEAD_END) - return -ENOEXEC; - - return kexec_image_probe_default(image, buf, buf_len); -} diff --git a/arch/s390/kernel/mcount.S b/arch/s390/kernel/mcount.S index 6b13797143a7..39bcc0e39a10 100644 --- a/arch/s390/kernel/mcount.S +++ b/arch/s390/kernel/mcount.S @@ -22,10 +22,11 @@ ENTRY(ftrace_stub) BR_EX %r14 ENDPROC(ftrace_stub) -#define STACK_FRAME_SIZE (STACK_FRAME_OVERHEAD + __PT_SIZE) -#define STACK_PTREGS (STACK_FRAME_OVERHEAD) -#define STACK_PTREGS_GPRS (STACK_PTREGS + __PT_GPRS) -#define STACK_PTREGS_PSW (STACK_PTREGS + __PT_PSW) +#define STACK_FRAME_SIZE (STACK_FRAME_OVERHEAD + __PT_SIZE) +#define STACK_PTREGS (STACK_FRAME_OVERHEAD) +#define STACK_PTREGS_GPRS (STACK_PTREGS + __PT_GPRS) +#define STACK_PTREGS_PSW (STACK_PTREGS + __PT_PSW) +#define STACK_PTREGS_ORIG_GPR2 (STACK_PTREGS + __PT_ORIG_GPR2) #ifdef __PACK_STACK /* allocate just enough for r14, r15 and backchain */ #define TRACED_FUNC_FRAME_SIZE 24 @@ -33,13 +34,15 @@ ENDPROC(ftrace_stub) #define TRACED_FUNC_FRAME_SIZE STACK_FRAME_OVERHEAD #endif -ENTRY(ftrace_caller) - .globl ftrace_regs_caller - .set ftrace_regs_caller,ftrace_caller + .macro ftrace_regs_entry, allregs=0 stg %r14,(__SF_GPRS+8*8)(%r15) # save traced function caller + + .if \allregs == 1 lghi %r14,0 # save condition code ipm %r14 # don't put any instructions sllg %r14,%r14,16 # clobbering CC before this point + .endif + lgr %r1,%r15 # allocate stack frame for ftrace_caller to contain traced function aghi %r15,-TRACED_FUNC_FRAME_SIZE @@ -49,13 +52,31 @@ ENTRY(ftrace_caller) # allocate pt_regs and stack frame for ftrace_trace_function aghi %r15,-STACK_FRAME_SIZE stg %r1,(STACK_PTREGS_GPRS+15*8)(%r15) + xc STACK_PTREGS_ORIG_GPR2(8,%r15),STACK_PTREGS_ORIG_GPR2(%r15) + + .if \allregs == 1 stg %r14,(STACK_PTREGS_PSW)(%r15) - lg %r14,(__SF_GPRS+8*8)(%r1) # restore original return address stosm (STACK_PTREGS_PSW)(%r15),0 + .endif + + lg %r14,(__SF_GPRS+8*8)(%r1) # restore original return address 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) + .endm + +SYM_CODE_START(ftrace_regs_caller) + ftrace_regs_entry 1 + j ftrace_common +SYM_CODE_END(ftrace_regs_caller) + +SYM_CODE_START(ftrace_caller) + ftrace_regs_entry 0 + j ftrace_common +SYM_CODE_END(ftrace_caller) + +SYM_CODE_START(ftrace_common) #ifdef CONFIG_HAVE_MARCH_Z196_FEATURES aghik %r2,%r0,-MCOUNT_INSN_SIZE lgrl %r4,function_trace_op @@ -74,24 +95,31 @@ ENTRY(ftrace_caller) #ifdef CONFIG_FUNCTION_GRAPH_TRACER # The j instruction gets runtime patched to a nop instruction. # See ftrace_enable_ftrace_graph_caller. - .globl ftrace_graph_caller -ftrace_graph_caller: - j ftrace_graph_caller_end +SYM_INNER_LABEL(ftrace_graph_caller, SYM_L_GLOBAL) + j .Lftrace_graph_caller_end lmg %r2,%r3,(STACK_PTREGS_GPRS+14*8)(%r15) lg %r4,(STACK_PTREGS_PSW+8)(%r15) brasl %r14,prepare_ftrace_return stg %r2,(STACK_PTREGS_GPRS+14*8)(%r15) -ftrace_graph_caller_end: - .globl ftrace_graph_caller_end +.Lftrace_graph_caller_end: +#endif + lg %r0,(STACK_PTREGS_PSW+8)(%r15) +#ifdef CONFIG_HAVE_MARCH_Z196_FEATURES + ltg %r1,STACK_PTREGS_ORIG_GPR2(%r15) + locgrz %r1,%r0 +#else + lg %r1,STACK_PTREGS_ORIG_GPR2(%r15) + ltgr %r1,%r1 + jnz 0f + lgr %r1,%r0 #endif - lg %r1,(STACK_PTREGS_PSW+8)(%r15) - lmg %r2,%r15,(STACK_PTREGS_GPRS+2*8)(%r15) +0: lmg %r2,%r15,(STACK_PTREGS_GPRS+2*8)(%r15) BR_EX %r1 -ENDPROC(ftrace_caller) +SYM_CODE_END(ftrace_common) #ifdef CONFIG_FUNCTION_GRAPH_TRACER -ENTRY(return_to_handler) +SYM_FUNC_START(return_to_handler) stmg %r2,%r5,32(%r15) lgr %r1,%r15 aghi %r15,-STACK_FRAME_OVERHEAD @@ -101,6 +129,6 @@ ENTRY(return_to_handler) lgr %r14,%r2 lmg %r2,%r5,32(%r15) BR_EX %r14 -ENDPROC(return_to_handler) +SYM_FUNC_END(return_to_handler) #endif diff --git a/arch/s390/kernel/nospec-branch.c b/arch/s390/kernel/nospec-branch.c index 250e4dbf653c..60e6fec27bba 100644 --- a/arch/s390/kernel/nospec-branch.c +++ b/arch/s390/kernel/nospec-branch.c @@ -38,7 +38,7 @@ static int __init nospec_report(void) { if (test_facility(156)) pr_info("Spectre V2 mitigation: etokens\n"); - if (__is_defined(CC_USING_EXPOLINE) && !nospec_disable) + if (nospec_uses_trampoline()) pr_info("Spectre V2 mitigation: execute trampolines\n"); if (__test_facility(82, alt_stfle_fac_list)) pr_info("Spectre V2 mitigation: limited branch prediction\n"); diff --git a/arch/s390/kernel/nospec-sysfs.c b/arch/s390/kernel/nospec-sysfs.c index b4b5c8c21166..52d4353188ad 100644 --- a/arch/s390/kernel/nospec-sysfs.c +++ b/arch/s390/kernel/nospec-sysfs.c @@ -15,7 +15,7 @@ ssize_t cpu_show_spectre_v2(struct device *dev, { if (test_facility(156)) return sprintf(buf, "Mitigation: etokens\n"); - if (__is_defined(CC_USING_EXPOLINE) && !nospec_disable) + if (nospec_uses_trampoline()) return sprintf(buf, "Mitigation: execute trampolines\n"); if (__test_facility(82, alt_stfle_fac_list)) return sprintf(buf, "Mitigation: limited branch prediction\n"); diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c index 4a99154fe651..6f431fa9e4d7 100644 --- a/arch/s390/kernel/perf_cpum_cf.c +++ b/arch/s390/kernel/perf_cpum_cf.c @@ -773,22 +773,46 @@ static int __init cpumf_pmu_init(void) * counter set via normal file operations. */ -static atomic_t cfset_opencnt = ATOMIC_INIT(0); /* Excl. access */ +static atomic_t cfset_opencnt = ATOMIC_INIT(0); /* Access count */ static DEFINE_MUTEX(cfset_ctrset_mutex);/* Synchronize access to hardware */ struct cfset_call_on_cpu_parm { /* Parm struct for smp_call_on_cpu */ unsigned int sets; /* Counter set bit mask */ atomic_t cpus_ack; /* # CPUs successfully executed func */ }; -static struct cfset_request { /* CPUs and counter set bit mask */ +static struct cfset_session { /* CPUs and counter set bit mask */ + struct list_head head; /* Head of list of active processes */ +} cfset_session = { + .head = LIST_HEAD_INIT(cfset_session.head) +}; + +struct cfset_request { /* CPUs and counter set bit mask */ unsigned long ctrset; /* Bit mask of counter set to read */ cpumask_t mask; /* CPU mask to read from */ -} cfset_request; + struct list_head node; /* Chain to cfset_session.head */ +}; + +static void cfset_session_init(void) +{ + INIT_LIST_HEAD(&cfset_session.head); +} + +/* Remove current request from global bookkeeping. Maintain a counter set bit + * mask on a per CPU basis. + * Done in process context under mutex protection. + */ +static void cfset_session_del(struct cfset_request *p) +{ + list_del(&p->node); +} -static void cfset_ctrset_clear(void) +/* Add current request to global bookkeeping. Maintain a counter set bit mask + * on a per CPU basis. + * Done in process context under mutex protection. + */ +static void cfset_session_add(struct cfset_request *p) { - cpumask_clear(&cfset_request.mask); - cfset_request.ctrset = 0; + list_add(&p->node, &cfset_session.head); } /* The /dev/hwctr device access uses PMU_F_IN_USE to mark the device access @@ -827,15 +851,23 @@ static void cfset_ioctl_off(void *parm) struct cfset_call_on_cpu_parm *p = parm; int rc; - cpuhw->dev_state = 0; + /* Check if any counter set used by /dev/hwc */ for (rc = CPUMF_CTR_SET_BASIC; rc < CPUMF_CTR_SET_MAX; ++rc) - if ((p->sets & cpumf_ctr_ctl[rc])) - atomic_dec(&cpuhw->ctr_set[rc]); - rc = lcctl(cpuhw->state); /* Keep perf_event_open counter sets */ + if ((p->sets & cpumf_ctr_ctl[rc])) { + if (!atomic_dec_return(&cpuhw->ctr_set[rc])) { + ctr_set_disable(&cpuhw->dev_state, + cpumf_ctr_ctl[rc]); + ctr_set_stop(&cpuhw->dev_state, + cpumf_ctr_ctl[rc]); + } + } + /* Keep perf_event_open counter sets */ + rc = lcctl(cpuhw->dev_state | cpuhw->state); if (rc) pr_err("Counter set stop %#llx of /dev/%s failed rc=%i\n", cpuhw->state, S390_HWCTR_DEVICE, rc); - cpuhw->flags &= ~PMU_F_IN_USE; + if (!cpuhw->dev_state) + cpuhw->flags &= ~PMU_F_IN_USE; debug_sprintf_event(cf_dbg, 4, "%s rc %d state %#llx dev_state %#llx\n", __func__, rc, cpuhw->state, cpuhw->dev_state); } @@ -870,11 +902,26 @@ static void cfset_release_cpu(void *p) debug_sprintf_event(cf_dbg, 4, "%s state %#llx dev_state %#llx\n", __func__, cpuhw->state, cpuhw->dev_state); + cpuhw->dev_state = 0; rc = lcctl(cpuhw->state); /* Keep perf_event_open counter sets */ if (rc) pr_err("Counter set release %#llx of /dev/%s failed rc=%i\n", cpuhw->state, S390_HWCTR_DEVICE, rc); - cpuhw->dev_state = 0; +} + +/* This modifies the process CPU mask to adopt it to the currently online + * CPUs. Offline CPUs can not be addresses. This call terminates the access + * and is usually followed by close() or a new iotcl(..., START, ...) which + * creates a new request structure. + */ +static void cfset_all_stop(struct cfset_request *req) +{ + struct cfset_call_on_cpu_parm p = { + .sets = req->ctrset, + }; + + cpumask_and(&req->mask, &req->mask, cpu_online_mask); + on_each_cpu_mask(&req->mask, cfset_ioctl_off, &p, 1); } /* Release function is also called when application gets terminated without @@ -882,10 +929,19 @@ static void cfset_release_cpu(void *p) */ static int cfset_release(struct inode *inode, struct file *file) { - on_each_cpu(cfset_release_cpu, NULL, 1); + mutex_lock(&cfset_ctrset_mutex); + /* Open followed by close/exit has no private_data */ + if (file->private_data) { + cfset_all_stop(file->private_data); + cfset_session_del(file->private_data); + kfree(file->private_data); + file->private_data = NULL; + } + if (!atomic_dec_return(&cfset_opencnt)) + on_each_cpu(cfset_release_cpu, NULL, 1); + mutex_unlock(&cfset_ctrset_mutex); + hw_perf_event_destroy(NULL); - cfset_ctrset_clear(); - atomic_set(&cfset_opencnt, 0); return 0; } @@ -893,9 +949,10 @@ static int cfset_open(struct inode *inode, struct file *file) { if (!capable(CAP_SYS_ADMIN)) return -EPERM; - /* Only one user space program can open /dev/hwctr */ - if (atomic_xchg(&cfset_opencnt, 1)) - return -EBUSY; + mutex_lock(&cfset_ctrset_mutex); + if (atomic_inc_return(&cfset_opencnt) == 1) + cfset_session_init(); + mutex_unlock(&cfset_ctrset_mutex); cpumf_hw_inuse(); file->private_data = NULL; @@ -903,25 +960,10 @@ static int cfset_open(struct inode *inode, struct file *file) return nonseekable_open(inode, file); } -static int cfset_all_stop(void) +static int cfset_all_start(struct cfset_request *req) { struct cfset_call_on_cpu_parm p = { - .sets = cfset_request.ctrset, - }; - cpumask_var_t mask; - - if (!alloc_cpumask_var(&mask, GFP_KERNEL)) - return -ENOMEM; - cpumask_and(mask, &cfset_request.mask, cpu_online_mask); - on_each_cpu_mask(mask, cfset_ioctl_off, &p, 1); - free_cpumask_var(mask); - return 0; -} - -static int cfset_all_start(void) -{ - struct cfset_call_on_cpu_parm p = { - .sets = cfset_request.ctrset, + .sets = req->ctrset, .cpus_ack = ATOMIC_INIT(0), }; cpumask_var_t mask; @@ -929,7 +971,7 @@ static int cfset_all_start(void) if (!alloc_cpumask_var(&mask, GFP_KERNEL)) return -ENOMEM; - cpumask_and(mask, &cfset_request.mask, cpu_online_mask); + cpumask_and(mask, &req->mask, cpu_online_mask); on_each_cpu_mask(mask, cfset_ioctl_on, &p, 1); if (atomic_read(&p.cpus_ack) != cpumask_weight(mask)) { on_each_cpu_mask(mask, cfset_ioctl_off, &p, 1); @@ -1045,7 +1087,7 @@ static void cfset_cpu_read(void *parm) cpuhw->sets, cpuhw->used); } -static int cfset_all_read(unsigned long arg) +static int cfset_all_read(unsigned long arg, struct cfset_request *req) { struct cfset_call_on_cpu_parm p; cpumask_var_t mask; @@ -1054,46 +1096,53 @@ static int cfset_all_read(unsigned long arg) if (!alloc_cpumask_var(&mask, GFP_KERNEL)) return -ENOMEM; - p.sets = cfset_request.ctrset; - cpumask_and(mask, &cfset_request.mask, cpu_online_mask); + p.sets = req->ctrset; + cpumask_and(mask, &req->mask, cpu_online_mask); on_each_cpu_mask(mask, cfset_cpu_read, &p, 1); rc = cfset_all_copy(arg, mask); free_cpumask_var(mask); return rc; } -static long cfset_ioctl_read(unsigned long arg) +static long cfset_ioctl_read(unsigned long arg, struct cfset_request *req) { struct s390_ctrset_read read; - int ret = 0; + int ret = -ENODATA; - if (copy_from_user(&read, (char __user *)arg, sizeof(read))) - return -EFAULT; - ret = cfset_all_read(arg); + if (req && req->ctrset) { + if (copy_from_user(&read, (char __user *)arg, sizeof(read))) + return -EFAULT; + ret = cfset_all_read(arg, req); + } return ret; } -static long cfset_ioctl_stop(void) +static long cfset_ioctl_stop(struct file *file) { - int ret = ENXIO; - - if (cfset_request.ctrset) { - ret = cfset_all_stop(); - cfset_ctrset_clear(); + struct cfset_request *req = file->private_data; + int ret = -ENXIO; + + if (req) { + cfset_all_stop(req); + cfset_session_del(req); + kfree(req); + file->private_data = NULL; + ret = 0; } return ret; } -static long cfset_ioctl_start(unsigned long arg) +static long cfset_ioctl_start(unsigned long arg, struct file *file) { struct s390_ctrset_start __user *ustart; struct s390_ctrset_start start; + struct cfset_request *preq; void __user *umask; unsigned int len; int ret = 0; size_t need; - if (cfset_request.ctrset) + if (file->private_data) return -EBUSY; ustart = (struct s390_ctrset_start __user *)arg; if (copy_from_user(&start, ustart, sizeof(start))) @@ -1108,25 +1157,36 @@ static long cfset_ioctl_start(unsigned long arg) return -EINVAL; /* Invalid counter set */ if (!start.counter_sets) return -EINVAL; /* No counter set at all? */ - cpumask_clear(&cfset_request.mask); + + preq = kzalloc(sizeof(*preq), GFP_KERNEL); + if (!preq) + return -ENOMEM; + cpumask_clear(&preq->mask); len = min_t(u64, start.cpumask_len, cpumask_size()); umask = (void __user *)start.cpumask; - if (copy_from_user(&cfset_request.mask, umask, len)) + if (copy_from_user(&preq->mask, umask, len)) { + kfree(preq); return -EFAULT; - if (cpumask_empty(&cfset_request.mask)) + } + if (cpumask_empty(&preq->mask)) { + kfree(preq); return -EINVAL; + } need = cfset_needspace(start.counter_sets); - if (put_user(need, &ustart->data_bytes)) - ret = -EFAULT; - if (ret) - goto out; - cfset_request.ctrset = start.counter_sets; - ret = cfset_all_start(); -out: - if (ret) - cfset_ctrset_clear(); - debug_sprintf_event(cf_dbg, 4, "%s sets %#lx need %ld ret %d\n", - __func__, cfset_request.ctrset, need, ret); + if (put_user(need, &ustart->data_bytes)) { + kfree(preq); + return -EFAULT; + } + preq->ctrset = start.counter_sets; + ret = cfset_all_start(preq); + if (!ret) { + cfset_session_add(preq); + file->private_data = preq; + debug_sprintf_event(cf_dbg, 4, "%s set %#lx need %ld ret %d\n", + __func__, preq->ctrset, need, ret); + } else { + kfree(preq); + } return ret; } @@ -1136,7 +1196,7 @@ out: * counter set keeps running until explicitly stopped. Returns the number * of bytes needed to store the counter values. If another S390_HWCTR_START * ioctl subcommand is called without a previous S390_HWCTR_STOP stop - * command, -EBUSY is returned. + * command on the same file descriptor, -EBUSY is returned. * S390_HWCTR_READ: Read the counter set values from specified CPU list given * with the S390_HWCTR_START command. * S390_HWCTR_STOP: Stops the counter sets on the CPU list given with the @@ -1150,13 +1210,13 @@ static long cfset_ioctl(struct file *file, unsigned int cmd, unsigned long arg) mutex_lock(&cfset_ctrset_mutex); switch (cmd) { case S390_HWCTR_START: - ret = cfset_ioctl_start(arg); + ret = cfset_ioctl_start(arg, file); break; case S390_HWCTR_STOP: - ret = cfset_ioctl_stop(); + ret = cfset_ioctl_stop(file); break; case S390_HWCTR_READ: - ret = cfset_ioctl_read(arg); + ret = cfset_ioctl_read(arg, file->private_data); break; default: ret = -ENOTTY; @@ -1182,29 +1242,41 @@ static struct miscdevice cfset_dev = { .fops = &cfset_fops, }; +/* Hotplug add of a CPU. Scan through all active processes and add + * that CPU to the list of CPUs supplied with ioctl(..., START, ...). + */ int cfset_online_cpu(unsigned int cpu) { struct cfset_call_on_cpu_parm p; + struct cfset_request *rp; mutex_lock(&cfset_ctrset_mutex); - if (cfset_request.ctrset) { - p.sets = cfset_request.ctrset; - cfset_ioctl_on(&p); - cpumask_set_cpu(cpu, &cfset_request.mask); + if (!list_empty(&cfset_session.head)) { + list_for_each_entry(rp, &cfset_session.head, node) { + p.sets = rp->ctrset; + cfset_ioctl_on(&p); + cpumask_set_cpu(cpu, &rp->mask); + } } mutex_unlock(&cfset_ctrset_mutex); return 0; } +/* Hotplug remove of a CPU. Scan through all active processes and clear + * that CPU from the list of CPUs supplied with ioctl(..., START, ...). + */ int cfset_offline_cpu(unsigned int cpu) { struct cfset_call_on_cpu_parm p; + struct cfset_request *rp; mutex_lock(&cfset_ctrset_mutex); - if (cfset_request.ctrset) { - p.sets = cfset_request.ctrset; - cfset_ioctl_off(&p); - cpumask_clear_cpu(cpu, &cfset_request.mask); + if (!list_empty(&cfset_session.head)) { + list_for_each_entry(rp, &cfset_session.head, node) { + p.sets = rp->ctrset; + cfset_ioctl_off(&p); + cpumask_clear_cpu(cpu, &rp->mask); + } } mutex_unlock(&cfset_ctrset_mutex); return 0; diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c index 350e94d0cac2..e8858b2de24b 100644 --- a/arch/s390/kernel/process.c +++ b/arch/s390/kernel/process.c @@ -141,7 +141,7 @@ int copy_thread(unsigned long clone_flags, unsigned long new_stackp, frame->childregs.gprs[10] = arg; frame->childregs.gprs[11] = (unsigned long)do_exit; frame->childregs.orig_gpr2 = -1; - + frame->childregs.last_break = 1; return 0; } frame->childregs = *current_pt_regs(); @@ -181,12 +181,12 @@ void execve_tail(void) asm volatile("sfpc %0" : : "d" (0)); } -unsigned long get_wchan(struct task_struct *p) +unsigned long __get_wchan(struct task_struct *p) { struct unwind_state state; unsigned long ip = 0; - if (!p || p == current || task_is_running(p) || !task_stack_page(p)) + if (!task_stack_page(p)) return 0; if (!try_get_task_stack(p)) diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index 67e5fff96ee0..40405f2304f1 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -95,10 +95,10 @@ EXPORT_SYMBOL(console_irq); * relocated above 2 GB, because it has to use 31 bit addresses. * Such code and data is part of the .amode31 section. */ -unsigned long __amode31_ref __samode31 = __pa(&_samode31); -unsigned long __amode31_ref __eamode31 = __pa(&_eamode31); -unsigned long __amode31_ref __stext_amode31 = __pa(&_stext_amode31); -unsigned long __amode31_ref __etext_amode31 = __pa(&_etext_amode31); +unsigned long __amode31_ref __samode31 = (unsigned long)&_samode31; +unsigned long __amode31_ref __eamode31 = (unsigned long)&_eamode31; +unsigned long __amode31_ref __stext_amode31 = (unsigned long)&_stext_amode31; +unsigned long __amode31_ref __etext_amode31 = (unsigned long)&_etext_amode31; struct exception_table_entry __amode31_ref *__start_amode31_ex_table = _start_amode31_ex_table; struct exception_table_entry __amode31_ref *__stop_amode31_ex_table = _stop_amode31_ex_table; @@ -149,6 +149,7 @@ struct mem_detect_info __bootdata(mem_detect); struct initrd_data __bootdata(initrd_data); unsigned long __bootdata_preserved(__kaslr_offset); +unsigned long __bootdata(__amode31_base); unsigned int __bootdata_preserved(zlib_dfltcc_support); EXPORT_SYMBOL(zlib_dfltcc_support); u64 __bootdata_preserved(stfle_fac_list[16]); @@ -173,6 +174,8 @@ unsigned long MODULES_END; struct lowcore *lowcore_ptr[NR_CPUS]; EXPORT_SYMBOL(lowcore_ptr); +DEFINE_STATIC_KEY_FALSE(cpu_has_bear); + /* * The Write Back bit position in the physaddr is given by the SLPC PCI. * Leaving the mask zero always uses write through which is safe @@ -593,7 +596,8 @@ static void __init setup_resources(void) * part of the System RAM resource. */ if (crashk_res.end) { - memblock_add_node(crashk_res.start, resource_size(&crashk_res), 0); + memblock_add_node(crashk_res.start, resource_size(&crashk_res), + 0, MEMBLOCK_NONE); memblock_reserve(crashk_res.start, resource_size(&crashk_res)); insert_resource(&iomem_resource, &crashk_res); } @@ -693,7 +697,7 @@ static void __init reserve_crashkernel(void) } if (register_memory_notifier(&kdump_mem_nb)) { - memblock_free(crash_base, crash_size); + memblock_phys_free(crash_base, crash_size); return; } @@ -718,7 +722,7 @@ static void __init reserve_initrd(void) #ifdef CONFIG_BLK_DEV_INITRD if (!initrd_data.start || !initrd_data.size) return; - initrd_start = initrd_data.start; + initrd_start = (unsigned long)__va(initrd_data.start); initrd_end = initrd_start + initrd_data.size; memblock_reserve(initrd_data.start, initrd_data.size); #endif @@ -748,7 +752,7 @@ static void __init free_mem_detect_info(void) get_mem_detect_reserved(&start, &size); if (size) - memblock_free(start, size); + memblock_phys_free(start, size); } static const char * __init get_mem_info_source(void) @@ -793,7 +797,7 @@ static void __init check_initrd(void) if (initrd_data.start && initrd_data.size && !memblock_is_region_memory(initrd_data.start, initrd_data.size)) { pr_err("The initial RAM disk does not fit into the memory\n"); - memblock_free(initrd_data.start, initrd_data.size); + memblock_phys_free(initrd_data.start, initrd_data.size); initrd_start = initrd_end = 0; } #endif @@ -804,12 +808,10 @@ static void __init check_initrd(void) */ static void __init reserve_kernel(void) { - unsigned long start_pfn = PFN_UP(__pa(_end)); - memblock_reserve(0, STARTUP_NORMAL_OFFSET); - memblock_reserve((unsigned long)sclp_early_sccb, EXT_SCCB_READ_SCP); - memblock_reserve((unsigned long)_stext, PFN_PHYS(start_pfn) - - (unsigned long)_stext); + memblock_reserve(__amode31_base, __eamode31 - __samode31); + memblock_reserve(__pa(sclp_early_sccb), EXT_SCCB_READ_SCP); + memblock_reserve(__pa(_stext), _end - _stext); } static void __init setup_memory(void) @@ -831,20 +833,14 @@ static void __init setup_memory(void) static void __init relocate_amode31_section(void) { - unsigned long amode31_addr, amode31_size; - long amode31_offset; + unsigned long amode31_size = __eamode31 - __samode31; + long amode31_offset = __amode31_base - __samode31; long *ptr; - /* Allocate a new AMODE31 capable memory region */ - amode31_size = __eamode31 - __samode31; pr_info("Relocating AMODE31 section of size 0x%08lx\n", amode31_size); - amode31_addr = (unsigned long)memblock_alloc_low(amode31_size, PAGE_SIZE); - if (!amode31_addr) - panic("Failed to allocate memory for AMODE31 section\n"); - amode31_offset = amode31_addr - __samode31; /* Move original AMODE31 section to the new one */ - memmove((void *)amode31_addr, (void *)__samode31, amode31_size); + memmove((void *)__amode31_base, (void *)__samode31, amode31_size); /* Zero out the old AMODE31 section to catch invalid accesses within it */ memset((void *)__samode31, 0, amode31_size); @@ -883,14 +879,12 @@ static void __init setup_randomness(void) { struct sysinfo_3_2_2 *vmms; - vmms = (struct sysinfo_3_2_2 *) memblock_phys_alloc(PAGE_SIZE, - PAGE_SIZE); + vmms = memblock_alloc(PAGE_SIZE, PAGE_SIZE); if (!vmms) panic("Failed to allocate memory for sysinfo structure\n"); - if (stsi(vmms, 3, 2, 2) == 0 && vmms->count) add_device_randomness(&vmms->vm, sizeof(vmms->vm[0]) * vmms->count); - memblock_free((unsigned long) vmms, PAGE_SIZE); + memblock_free(vmms, PAGE_SIZE); } /* @@ -1047,6 +1041,9 @@ void __init setup_arch(char **cmdline_p) smp_detect_cpus(); topology_init_early(); + if (test_facility(193)) + static_branch_enable(&cpu_has_bear); + /* * Create kernel page tables and switch to virtual addressing. */ diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index 1a04e5bdf655..78a8ea6fd582 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -723,7 +723,7 @@ void __init smp_save_dump_cpus(void) /* Get the CPU registers */ smp_save_cpu_regs(sa, addr, is_boot_cpu, page); } - memblock_free(page, PAGE_SIZE); + memblock_phys_free(page, PAGE_SIZE); diag_amode31_ops.diag308_reset(); pcpu_set_smt(0); } @@ -880,7 +880,7 @@ void __init smp_detect_cpus(void) /* Add CPUs present at boot */ __smp_rescan_cpus(info, true); - memblock_free_early((unsigned long)info, sizeof(*info)); + memblock_phys_free((unsigned long)info, sizeof(*info)); } /* diff --git a/arch/s390/kernel/stacktrace.c b/arch/s390/kernel/stacktrace.c index 101477b3e263..b7bb1981e9ee 100644 --- a/arch/s390/kernel/stacktrace.c +++ b/arch/s390/kernel/stacktrace.c @@ -46,7 +46,7 @@ int arch_stack_walk_reliable(stack_trace_consume_fn consume_entry, * Mark stacktraces with kretprobed functions on them * as unreliable. */ - if (state.ip == (unsigned long)kretprobe_trampoline) + if (state.ip == (unsigned long)__kretprobe_trampoline) return -EINVAL; #endif diff --git a/arch/s390/kernel/syscall.c b/arch/s390/kernel/syscall.c index 8fe2d23b64f4..dc2355c623d6 100644 --- a/arch/s390/kernel/syscall.c +++ b/arch/s390/kernel/syscall.c @@ -154,6 +154,8 @@ void noinstr __do_syscall(struct pt_regs *regs, int per_trap) regs->psw = S390_lowcore.svc_old_psw; regs->int_code = S390_lowcore.svc_int_code; update_timer_sys(); + if (static_branch_likely(&cpu_has_bear)) + current->thread.last_break = regs->last_break; local_irq_enable(); regs->orig_gpr2 = regs->gprs[2]; diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c index bcefc2173de4..6c6f7dcce1a5 100644 --- a/arch/s390/kernel/traps.c +++ b/arch/s390/kernel/traps.c @@ -300,7 +300,6 @@ static void (*pgm_check_table[128])(struct pt_regs *regs); void noinstr __do_pgm_check(struct pt_regs *regs) { - unsigned long last_break = S390_lowcore.breaking_event_addr; unsigned int trapnr; irqentry_state_t state; @@ -311,10 +310,11 @@ void noinstr __do_pgm_check(struct pt_regs *regs) if (user_mode(regs)) { update_timer_sys(); - if (last_break < 4096) - last_break = 1; - current->thread.last_break = last_break; - regs->args[0] = last_break; + if (!static_branch_likely(&cpu_has_bear)) { + if (regs->last_break < 4096) + regs->last_break = 1; + } + current->thread.last_break = regs->last_break; } if (S390_lowcore.pgm_code & 0x0200) { diff --git a/arch/s390/kernel/uv.c b/arch/s390/kernel/uv.c index 5a656c7b7a67..386d4e42b8d3 100644 --- a/arch/s390/kernel/uv.c +++ b/arch/s390/kernel/uv.c @@ -64,7 +64,7 @@ void __init setup_uv(void) } if (uv_init(uv_stor_base, uv_info.uv_base_stor_len)) { - memblock_free(uv_stor_base, uv_info.uv_base_stor_len); + memblock_phys_free(uv_stor_base, uv_info.uv_base_stor_len); goto fail; } @@ -100,7 +100,7 @@ static int uv_pin_shared(unsigned long paddr) * * @paddr: Absolute host address of page to be destroyed */ -int uv_destroy_page(unsigned long paddr) +static int uv_destroy_page(unsigned long paddr) { struct uv_cb_cfs uvcb = { .header.cmd = UVC_CMD_DESTR_SEC_STOR, @@ -121,6 +121,22 @@ int uv_destroy_page(unsigned long paddr) } /* + * The caller must already hold a reference to the page + */ +int uv_destroy_owned_page(unsigned long paddr) +{ + struct page *page = phys_to_page(paddr); + int rc; + + get_page(page); + rc = uv_destroy_page(paddr); + if (!rc) + clear_bit(PG_arch_1, &page->flags); + put_page(page); + return rc; +} + +/* * Requests the Ultravisor to encrypt a guest page and make it * accessible to the host for paging (export). * @@ -140,6 +156,22 @@ int uv_convert_from_secure(unsigned long paddr) } /* + * The caller must already hold a reference to the page + */ +int uv_convert_owned_from_secure(unsigned long paddr) +{ + struct page *page = phys_to_page(paddr); + int rc; + + get_page(page); + rc = uv_convert_from_secure(paddr); + if (!rc) + clear_bit(PG_arch_1, &page->flags); + put_page(page); + return rc; +} + +/* * Calculate the expected ref_count for a page that would otherwise have no * further pins. This was cribbed from similar functions in other places in * the kernel, but with some slight modifications. We know that a secure @@ -165,7 +197,7 @@ static int make_secure_pte(pte_t *ptep, unsigned long addr, { pte_t entry = READ_ONCE(*ptep); struct page *page; - int expected, rc = 0; + int expected, cc = 0; if (!pte_present(entry)) return -ENXIO; @@ -181,12 +213,25 @@ static int make_secure_pte(pte_t *ptep, unsigned long addr, if (!page_ref_freeze(page, expected)) return -EBUSY; set_bit(PG_arch_1, &page->flags); - rc = uv_call(0, (u64)uvcb); + /* + * If the UVC does not succeed or fail immediately, we don't want to + * loop for long, or we might get stall notifications. + * On the other hand, this is a complex scenario and we are holding a lot of + * locks, so we can't easily sleep and reschedule. We try only once, + * and if the UVC returned busy or partial completion, we return + * -EAGAIN and we let the callers deal with it. + */ + cc = __uv_call(0, (u64)uvcb); page_ref_unfreeze(page, expected); - /* Return -ENXIO if the page was not mapped, -EINVAL otherwise */ - if (rc) - rc = uvcb->rc == 0x10a ? -ENXIO : -EINVAL; - return rc; + /* + * Return -ENXIO if the page was not mapped, -EINVAL for other errors. + * If busy or partially completed, return -EAGAIN. + */ + if (cc == UVC_CC_OK) + return 0; + else if (cc == UVC_CC_BUSY || cc == UVC_CC_PARTIAL) + return -EAGAIN; + return uvcb->rc == 0x10a ? -ENXIO : -EINVAL; } /* @@ -212,7 +257,7 @@ again: uaddr = __gmap_translate(gmap, gaddr); if (IS_ERR_VALUE(uaddr)) goto out; - vma = find_vma(gmap->mm, uaddr); + vma = vma_lookup(gmap->mm, uaddr); if (!vma) goto out; /* @@ -239,6 +284,10 @@ out: mmap_read_unlock(gmap->mm); if (rc == -EAGAIN) { + /* + * If we are here because the UVC returned busy or partial + * completion, this is just a useless check, but it is safe. + */ wait_on_page_writeback(page); } else if (rc == -EBUSY) { /* diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S index 63bdb9e1bfc1..42c43521878f 100644 --- a/arch/s390/kernel/vmlinux.lds.S +++ b/arch/s390/kernel/vmlinux.lds.S @@ -212,6 +212,7 @@ SECTIONS QUAD(__dynsym_start) /* dynsym_start */ QUAD(__rela_dyn_start) /* rela_dyn_start */ QUAD(__rela_dyn_end) /* rela_dyn_end */ + QUAD(_eamode31 - _samode31) /* amode31_size */ } :NONE /* Debugging sections. */ diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c index b9f85b2dc053..6af59c59cc1b 100644 --- a/arch/s390/kvm/gaccess.c +++ b/arch/s390/kvm/gaccess.c @@ -894,6 +894,11 @@ int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra, /** * guest_translate_address - translate guest logical into guest absolute address + * @vcpu: virtual cpu + * @gva: Guest virtual address + * @ar: Access register + * @gpa: Guest physical address + * @mode: Translation access mode * * Parameter semantics are the same as the ones from guest_translate. * The memory contents at the guest address are not changed. @@ -934,6 +939,11 @@ int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva, u8 ar, /** * check_gva_range - test a range of guest virtual addresses for accessibility + * @vcpu: virtual cpu + * @gva: Guest virtual address + * @ar: Access register + * @length: Length of test range + * @mode: Translation access mode */ int check_gva_range(struct kvm_vcpu *vcpu, unsigned long gva, u8 ar, unsigned long length, enum gacc_mode mode) @@ -956,6 +966,7 @@ int check_gva_range(struct kvm_vcpu *vcpu, unsigned long gva, u8 ar, /** * kvm_s390_check_low_addr_prot_real - check for low-address protection + * @vcpu: virtual cpu * @gra: Guest real address * * Checks whether an address is subject to low-address protection and set @@ -979,6 +990,7 @@ int kvm_s390_check_low_addr_prot_real(struct kvm_vcpu *vcpu, unsigned long gra) * @pgt: pointer to the beginning of the page table for the given address if * successful (return value 0), or to the first invalid DAT entry in * case of exceptions (return value > 0) + * @dat_protection: referenced memory is write protected * @fake: pgt references contiguous guest memory block, not a pgtable */ static int kvm_s390_shadow_tables(struct gmap *sg, unsigned long saddr, diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c index 72b25b7cc6ae..d07ff646d844 100644 --- a/arch/s390/kvm/intercept.c +++ b/arch/s390/kvm/intercept.c @@ -269,6 +269,7 @@ static int handle_prog(struct kvm_vcpu *vcpu) /** * handle_external_interrupt - used for external interruption interceptions + * @vcpu: virtual cpu * * This interception only occurs if the CPUSTAT_EXT_INT bit was set, or if * the new PSW does not have external interrupts disabled. In the first case, @@ -315,7 +316,8 @@ static int handle_external_interrupt(struct kvm_vcpu *vcpu) } /** - * Handle MOVE PAGE partial execution interception. + * handle_mvpg_pei - Handle MOVE PAGE partial execution interception. + * @vcpu: virtual cpu * * This interception can only happen for guests with DAT disabled and * addresses that are currently not mapped in the host. Thus we try to @@ -516,6 +518,11 @@ static int handle_pv_uvc(struct kvm_vcpu *vcpu) */ if (rc == -EINVAL) return 0; + /* + * If we got -EAGAIN here, we simply return it. It will eventually + * get propagated all the way to userspace, which should then try + * again. + */ return rc; } diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 16256e17a544..c3bd993fdd0c 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -419,13 +419,13 @@ static unsigned long deliverable_irqs(struct kvm_vcpu *vcpu) static void __set_cpu_idle(struct kvm_vcpu *vcpu) { kvm_s390_set_cpuflags(vcpu, CPUSTAT_WAIT); - set_bit(kvm_vcpu_get_idx(vcpu), vcpu->kvm->arch.idle_mask); + set_bit(vcpu->vcpu_idx, vcpu->kvm->arch.idle_mask); } static void __unset_cpu_idle(struct kvm_vcpu *vcpu) { kvm_s390_clear_cpuflags(vcpu, CPUSTAT_WAIT); - clear_bit(kvm_vcpu_get_idx(vcpu), vcpu->kvm->arch.idle_mask); + clear_bit(vcpu->vcpu_idx, vcpu->kvm->arch.idle_mask); } static void __reset_intercept_indicators(struct kvm_vcpu *vcpu) @@ -960,7 +960,7 @@ static int __must_check __deliver_prog(struct kvm_vcpu *vcpu) /* bit 1+2 of the target are the ilc, so we can directly use ilen */ rc |= put_guest_lc(vcpu, ilen, (u16 *) __LC_PGM_ILC); rc |= put_guest_lc(vcpu, vcpu->arch.sie_block->gbea, - (u64 *) __LC_LAST_BREAK); + (u64 *) __LC_PGM_LAST_BREAK); rc |= put_guest_lc(vcpu, pgm_info.code, (u16 *)__LC_PGM_INT_CODE); rc |= write_guest_lc(vcpu, __LC_PGM_OLD_PSW, @@ -3053,13 +3053,14 @@ static void __airqs_kick_single_vcpu(struct kvm *kvm, u8 deliverable_mask) int vcpu_idx, online_vcpus = atomic_read(&kvm->online_vcpus); struct kvm_s390_gisa_interrupt *gi = &kvm->arch.gisa_int; struct kvm_vcpu *vcpu; + u8 vcpu_isc_mask; for_each_set_bit(vcpu_idx, kvm->arch.idle_mask, online_vcpus) { vcpu = kvm_get_vcpu(kvm, vcpu_idx); if (psw_ioint_disabled(vcpu)) continue; - deliverable_mask &= (u8)(vcpu->arch.sie_block->gcr[6] >> 24); - if (deliverable_mask) { + vcpu_isc_mask = (u8)(vcpu->arch.sie_block->gcr[6] >> 24); + if (deliverable_mask & vcpu_isc_mask) { /* lately kicked but not yet running */ if (test_and_set_bit(vcpu_idx, gi->kicked_mask)) return; diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 752a0ffab9bf..c6257f625929 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -2487,8 +2487,8 @@ long kvm_arch_vm_ioctl(struct file *filp, case KVM_S390_PV_COMMAND: { struct kvm_pv_cmd args; - /* protvirt means user sigp */ - kvm->arch.user_cpu_state_ctrl = 1; + /* protvirt means user cpu state */ + kvm_s390_set_user_cpu_state_ctrl(kvm); r = 0; if (!is_prot_virt_host()) { r = -EINVAL; @@ -3363,6 +3363,7 @@ out_free_sie_block: int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu) { + clear_bit(vcpu->vcpu_idx, vcpu->kvm->arch.gisa_int.kicked_mask); return kvm_s390_vcpu_has_irq(vcpu, 0); } @@ -3801,7 +3802,7 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, vcpu_load(vcpu); /* user space knows about this interface - let it control the state */ - vcpu->kvm->arch.user_cpu_state_ctrl = 1; + kvm_s390_set_user_cpu_state_ctrl(vcpu->kvm); switch (mp_state->mp_state) { case KVM_MP_STATE_STOPPED: @@ -4066,7 +4067,7 @@ static int vcpu_pre_run(struct kvm_vcpu *vcpu) kvm_s390_patch_guest_per_regs(vcpu); } - clear_bit(kvm_vcpu_get_idx(vcpu), vcpu->kvm->arch.gisa_int.kicked_mask); + clear_bit(vcpu->vcpu_idx, vcpu->kvm->arch.gisa_int.kicked_mask); vcpu->arch.sie_block->icptcode = 0; cpuflags = atomic_read(&vcpu->arch.sie_block->cpuflags); @@ -4254,6 +4255,7 @@ static void sync_regs_fmt2(struct kvm_vcpu *vcpu) if (kvm_run->kvm_dirty_regs & KVM_SYNC_DIAG318) { vcpu->arch.diag318_info.val = kvm_run->s.regs.diag318; vcpu->arch.sie_block->cpnc = vcpu->arch.diag318_info.cpnc; + VCPU_EVENT(vcpu, 3, "setting cpnc to %d", vcpu->arch.diag318_info.cpnc); } /* * If userspace sets the riccb (e.g. after migration) to a valid state, diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index ecd741ee3276..c07a050d757d 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -79,7 +79,7 @@ static inline int is_vcpu_stopped(struct kvm_vcpu *vcpu) static inline int is_vcpu_idle(struct kvm_vcpu *vcpu) { - return test_bit(kvm_vcpu_get_idx(vcpu), vcpu->kvm->arch.idle_mask); + return test_bit(vcpu->vcpu_idx, vcpu->kvm->arch.idle_mask); } static inline int kvm_is_ucontrol(struct kvm *kvm) @@ -208,6 +208,15 @@ static inline int kvm_s390_user_cpu_state_ctrl(struct kvm *kvm) return kvm->arch.user_cpu_state_ctrl != 0; } +static inline void kvm_s390_set_user_cpu_state_ctrl(struct kvm *kvm) +{ + if (kvm->arch.user_cpu_state_ctrl) + return; + + VM_EVENT(kvm, 3, "%s", "ENABLE: Userspace CPU state control"); + kvm->arch.user_cpu_state_ctrl = 1; +} + /* implemented in pv.c */ int kvm_s390_pv_destroy_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc); int kvm_s390_pv_create_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc); diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index 53da4ceb16a3..417154b314a6 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -397,6 +397,8 @@ static int handle_sske(struct kvm_vcpu *vcpu) mmap_read_unlock(current->mm); if (rc == -EFAULT) return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); + if (rc == -EAGAIN) + continue; if (rc < 0) return rc; start += PAGE_SIZE; diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c index c8841f476e91..00d272d134c2 100644 --- a/arch/s390/kvm/pv.c +++ b/arch/s390/kvm/pv.c @@ -16,18 +16,17 @@ int kvm_s390_pv_destroy_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc) { - int cc = 0; + int cc; - if (kvm_s390_pv_cpu_get_handle(vcpu)) { - cc = uv_cmd_nodata(kvm_s390_pv_cpu_get_handle(vcpu), - UVC_CMD_DESTROY_SEC_CPU, rc, rrc); + if (!kvm_s390_pv_cpu_get_handle(vcpu)) + return 0; + + cc = uv_cmd_nodata(kvm_s390_pv_cpu_get_handle(vcpu), UVC_CMD_DESTROY_SEC_CPU, rc, rrc); + + KVM_UV_EVENT(vcpu->kvm, 3, "PROTVIRT DESTROY VCPU %d: rc %x rrc %x", + vcpu->vcpu_id, *rc, *rrc); + WARN_ONCE(cc, "protvirt destroy cpu failed rc %x rrc %x", *rc, *rrc); - KVM_UV_EVENT(vcpu->kvm, 3, - "PROTVIRT DESTROY VCPU %d: rc %x rrc %x", - vcpu->vcpu_id, *rc, *rrc); - WARN_ONCE(cc, "protvirt destroy cpu failed rc %x rrc %x", - *rc, *rrc); - } /* Intended memory leak for something that should never happen. */ if (!cc) free_pages(vcpu->arch.pv.stor_base, @@ -196,7 +195,7 @@ int kvm_s390_pv_init_vm(struct kvm *kvm, u16 *rc, u16 *rrc) uvcb.conf_base_stor_origin = (u64)kvm->arch.pv.stor_base; uvcb.conf_virt_stor_origin = (u64)kvm->arch.pv.stor_var; - cc = uv_call(0, (u64)&uvcb); + cc = uv_call_sched(0, (u64)&uvcb); *rc = uvcb.header.rc; *rrc = uvcb.header.rrc; KVM_UV_EVENT(kvm, 3, "PROTVIRT CREATE VM: handle %llx len %llx rc %x rrc %x", diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c index 683036c1c92a..cf4de80bd541 100644 --- a/arch/s390/kvm/sigp.c +++ b/arch/s390/kvm/sigp.c @@ -151,22 +151,10 @@ static int __sigp_stop_and_store_status(struct kvm_vcpu *vcpu, static int __sigp_set_arch(struct kvm_vcpu *vcpu, u32 parameter, u64 *status_reg) { - unsigned int i; - struct kvm_vcpu *v; - bool all_stopped = true; - - kvm_for_each_vcpu(i, v, vcpu->kvm) { - if (v == vcpu) - continue; - if (!is_vcpu_stopped(v)) - all_stopped = false; - } - *status_reg &= 0xffffffff00000000UL; /* Reject set arch order, with czam we're always in z/Arch mode. */ - *status_reg |= (all_stopped ? SIGP_STATUS_INVALID_PARAMETER : - SIGP_STATUS_INCORRECT_STATE); + *status_reg |= SIGP_STATUS_INVALID_PARAMETER; return SIGP_CC_STATUS_STORED; } diff --git a/arch/s390/lib/Makefile b/arch/s390/lib/Makefile index 678333936f78..707cd4622c13 100644 --- a/arch/s390/lib/Makefile +++ b/arch/s390/lib/Makefile @@ -7,6 +7,8 @@ lib-y += delay.o string.o uaccess.o find.o spinlock.o obj-y += mem.o xor.o lib-$(CONFIG_KPROBES) += probes.o lib-$(CONFIG_UPROBES) += probes.o +obj-$(CONFIG_S390_KPROBES_SANITY_TEST) += test_kprobes_s390.o +test_kprobes_s390-objs += test_kprobes_asm.o test_kprobes.o # Instrumenting memory accesses to __user data (in different address space) # produce false positives diff --git a/arch/s390/lib/spinlock.c b/arch/s390/lib/spinlock.c index 9b2dab5a69f9..692dc84cd19c 100644 --- a/arch/s390/lib/spinlock.c +++ b/arch/s390/lib/spinlock.c @@ -26,7 +26,7 @@ static int __init spin_retry_init(void) } early_initcall(spin_retry_init); -/** +/* * spin_retry= parameter */ static int __init spin_retry_setup(char *str) diff --git a/arch/s390/lib/string.c b/arch/s390/lib/string.c index cfcdf76d6a95..7d8741818239 100644 --- a/arch/s390/lib/string.c +++ b/arch/s390/lib/string.c @@ -8,6 +8,9 @@ */ #define IN_ARCH_STRING_C 1 +#ifndef __NO_FORTIFY +# define __NO_FORTIFY +#endif #include <linux/types.h> #include <linux/string.h> @@ -98,32 +101,6 @@ EXPORT_SYMBOL(strcpy); #endif /** - * strlcpy - Copy a %NUL terminated string into a sized buffer - * @dest: Where to copy the string to - * @src: Where to copy the string from - * @size: size of destination buffer - * - * Compatible with *BSD: the result is always a valid - * NUL-terminated string that fits in the buffer (unless, - * of course, the buffer size is zero). It does not pad - * out the result like strncpy() does. - */ -#ifdef __HAVE_ARCH_STRLCPY -size_t strlcpy(char *dest, const char *src, size_t size) -{ - size_t ret = __strend(src) - src; - - if (size) { - size_t len = (ret >= size) ? size-1 : ret; - dest[len] = '\0'; - memcpy(dest, src, len); - } - return ret; -} -EXPORT_SYMBOL(strlcpy); -#endif - -/** * strncpy - Copy a length-limited, %NUL-terminated string * @dest: Where to copy the string to * @src: Where to copy the string from @@ -251,26 +228,6 @@ int strcmp(const char *s1, const char *s2) EXPORT_SYMBOL(strcmp); #endif -/** - * strrchr - Find the last occurrence of a character in a string - * @s: The string to be searched - * @c: The character to search for - */ -#ifdef __HAVE_ARCH_STRRCHR -char *strrchr(const char *s, int c) -{ - size_t len = __strend(s) - s; - - if (len) - do { - if (s[len] == (char) c) - return (char *) s + len; - } while (--len > 0); - return NULL; -} -EXPORT_SYMBOL(strrchr); -#endif - static inline int clcle(const char *s1, unsigned long l1, const char *s2, unsigned long l2) { diff --git a/arch/s390/lib/test_kprobes.c b/arch/s390/lib/test_kprobes.c new file mode 100644 index 000000000000..9e62d62812e5 --- /dev/null +++ b/arch/s390/lib/test_kprobes.c @@ -0,0 +1,75 @@ +// SPDX-License-Identifier: GPL-2.0+ + +#include <linux/kernel.h> +#include <linux/kprobes.h> +#include <linux/random.h> +#include <kunit/test.h> +#include "test_kprobes.h" + +static struct kprobe kp; + +static void setup_kprobe(struct kunit *test, struct kprobe *kp, + const char *symbol, int offset) +{ + kp->offset = offset; + kp->addr = NULL; + kp->symbol_name = symbol; +} + +static void test_kprobe_offset(struct kunit *test, struct kprobe *kp, + const char *target, int offset) +{ + int ret; + + setup_kprobe(test, kp, target, 0); + ret = register_kprobe(kp); + if (!ret) + unregister_kprobe(kp); + KUNIT_EXPECT_EQ(test, 0, ret); + setup_kprobe(test, kp, target, offset); + ret = register_kprobe(kp); + KUNIT_EXPECT_EQ(test, -EINVAL, ret); + if (!ret) + unregister_kprobe(kp); +} + +static void test_kprobe_odd(struct kunit *test) +{ + test_kprobe_offset(test, &kp, "kprobes_target_odd", + kprobes_target_odd_offs); +} + +static void test_kprobe_in_insn4(struct kunit *test) +{ + test_kprobe_offset(test, &kp, "kprobes_target_in_insn4", + kprobes_target_in_insn4_offs); +} + +static void test_kprobe_in_insn6_lo(struct kunit *test) +{ + test_kprobe_offset(test, &kp, "kprobes_target_in_insn6_lo", + kprobes_target_in_insn6_lo_offs); +} + +static void test_kprobe_in_insn6_hi(struct kunit *test) +{ + test_kprobe_offset(test, &kp, "kprobes_target_in_insn6_hi", + kprobes_target_in_insn6_hi_offs); +} + +static struct kunit_case kprobes_testcases[] = { + KUNIT_CASE(test_kprobe_odd), + KUNIT_CASE(test_kprobe_in_insn4), + KUNIT_CASE(test_kprobe_in_insn6_lo), + KUNIT_CASE(test_kprobe_in_insn6_hi), + {} +}; + +static struct kunit_suite kprobes_test_suite = { + .name = "kprobes_test_s390", + .test_cases = kprobes_testcases, +}; + +kunit_test_suites(&kprobes_test_suite); + +MODULE_LICENSE("GPL"); diff --git a/arch/s390/lib/test_kprobes.h b/arch/s390/lib/test_kprobes.h new file mode 100644 index 000000000000..2b4c9bc337f1 --- /dev/null +++ b/arch/s390/lib/test_kprobes.h @@ -0,0 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +#ifndef TEST_KPROBES_H +#define TEST_KPROBES_H + +extern unsigned long kprobes_target_odd_offs; +extern unsigned long kprobes_target_in_insn4_offs; +extern unsigned long kprobes_target_in_insn6_lo_offs; +extern unsigned long kprobes_target_in_insn6_hi_offs; + +#endif diff --git a/arch/s390/lib/test_kprobes_asm.S b/arch/s390/lib/test_kprobes_asm.S new file mode 100644 index 000000000000..ade7a3042334 --- /dev/null +++ b/arch/s390/lib/test_kprobes_asm.S @@ -0,0 +1,45 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ + +#include <linux/linkage.h> +#include <asm/ftrace.h> + +#define KPROBES_TARGET_START(name) \ + SYM_FUNC_START(name); \ + FTRACE_GEN_NOP_ASM(name) + +#define KPROBES_TARGET_END(name) \ + SYM_FUNC_END(name); \ + SYM_DATA(name##_offs, .quad 1b - name) + +KPROBES_TARGET_START(kprobes_target_in_insn4) + .word 0x4700 // bc 0,0 +1: .word 0x0000 + br %r14 +KPROBES_TARGET_END(kprobes_target_in_insn4) + +KPROBES_TARGET_START(kprobes_target_in_insn6_lo) + .word 0xe310 // ly 1,0 +1: .word 0x0000 + .word 0x0058 + br %r14 +KPROBES_TARGET_END(kprobes_target_in_insn6_lo) + +KPROBES_TARGET_START(kprobes_target_in_insn6_hi) + .word 0xe310 // ly 1,0 + .word 0x0000 +1: .word 0x0058 + br %r14 +KPROBES_TARGET_END(kprobes_target_in_insn6_hi) + +KPROBES_TARGET_START(kprobes_target_bp) + nop + .word 0x0000 + nop +1: br %r14 +KPROBES_TARGET_END(kprobes_target_bp) + +KPROBES_TARGET_START(kprobes_target_odd) + .byte 0x07 +1: .byte 0x07 + br %r14 +KPROBES_TARGET_END(kprobes_target_odd) diff --git a/arch/s390/lib/test_unwind.c b/arch/s390/lib/test_unwind.c index ecf327d743a0..cfc5f5557c06 100644 --- a/arch/s390/lib/test_unwind.c +++ b/arch/s390/lib/test_unwind.c @@ -3,7 +3,7 @@ * Test module for unwind_for_each_frame */ -#define pr_fmt(fmt) "test_unwind: " fmt +#include <kunit/test.h> #include <asm/unwind.h> #include <linux/completion.h> #include <linux/kallsyms.h> @@ -16,6 +16,8 @@ #include <linux/wait.h> #include <asm/irq.h> +struct kunit *current_test; + #define BT_BUF_SIZE (PAGE_SIZE * 4) /* @@ -29,7 +31,7 @@ static void print_backtrace(char *bt) p = strsep(&bt, "\n"); if (!p) break; - pr_err("%s\n", p); + kunit_err(current_test, "%s\n", p); } } @@ -49,7 +51,7 @@ static noinline int test_unwind(struct task_struct *task, struct pt_regs *regs, bt = kmalloc(BT_BUF_SIZE, GFP_ATOMIC); if (!bt) { - pr_err("failed to allocate backtrace buffer\n"); + kunit_err(current_test, "failed to allocate backtrace buffer\n"); return -ENOMEM; } /* Unwind. */ @@ -63,7 +65,7 @@ static noinline int test_unwind(struct task_struct *task, struct pt_regs *regs, if (frame_count++ == max_frames) break; if (state.reliable && !addr) { - pr_err("unwind state reliable but addr is 0\n"); + kunit_err(current_test, "unwind state reliable but addr is 0\n"); ret = -EINVAL; break; } @@ -75,7 +77,7 @@ static noinline int test_unwind(struct task_struct *task, struct pt_regs *regs, 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"); + kunit_err(current_test, "backtrace buffer is too small\n"); } frame_count += 1; if (prev_is_func2 && str_has_prefix(sym, "unwindme_func1")) @@ -85,15 +87,15 @@ static noinline int test_unwind(struct task_struct *task, struct pt_regs *regs, /* Check the results. */ if (unwind_error(&state)) { - pr_err("unwind error\n"); + kunit_err(current_test, "unwind error\n"); ret = -EINVAL; } if (!seen_func2_func1) { - pr_err("unwindme_func2 and unwindme_func1 not found\n"); + kunit_err(current_test, "unwindme_func2 and unwindme_func1 not found\n"); ret = -EINVAL; } if (frame_count == max_frames) { - pr_err("Maximum number of frames exceeded\n"); + kunit_err(current_test, "Maximum number of frames exceeded\n"); ret = -EINVAL; } if (ret) @@ -166,7 +168,7 @@ static noinline int unwindme_func4(struct unwindme *u) kp.pre_handler = pgm_pre_handler; ret = register_kprobe(&kp); if (ret < 0) { - pr_err("register_kprobe failed %d\n", ret); + kunit_err(current_test, "register_kprobe failed %d\n", ret); return -EINVAL; } @@ -252,7 +254,7 @@ static int test_unwind_irq(struct unwindme *u) } /* Spawns a task and passes it to test_unwind(). */ -static int test_unwind_task(struct unwindme *u) +static int test_unwind_task(struct kunit *test, struct unwindme *u) { struct task_struct *task; int ret; @@ -267,7 +269,7 @@ static int test_unwind_task(struct unwindme *u) */ task = kthread_run(unwindme_func1, u, "%s", __func__); if (IS_ERR(task)) { - pr_err("kthread_run() failed\n"); + kunit_err(test, "kthread_run() failed\n"); return PTR_ERR(task); } /* @@ -282,77 +284,98 @@ static int test_unwind_task(struct unwindme *u) return ret; } -static int test_unwind_flags(int flags) +struct test_params { + int flags; + char *name; +}; + +/* + * Create required parameter list for tests + */ +static const struct test_params param_list[] = { + {.flags = UWM_DEFAULT, .name = "UWM_DEFAULT"}, + {.flags = UWM_SP, .name = "UWM_SP"}, + {.flags = UWM_REGS, .name = "UWM_REGS"}, + {.flags = UWM_SWITCH_STACK, + .name = "UWM_SWITCH_STACK"}, + {.flags = UWM_SP | UWM_REGS, + .name = "UWM_SP | UWM_REGS"}, + {.flags = UWM_CALLER | UWM_SP, + .name = "WM_CALLER | UWM_SP"}, + {.flags = UWM_CALLER | UWM_SP | UWM_REGS, + .name = "UWM_CALLER | UWM_SP | UWM_REGS"}, + {.flags = UWM_CALLER | UWM_SP | UWM_REGS | UWM_SWITCH_STACK, + .name = "UWM_CALLER | UWM_SP | UWM_REGS | UWM_SWITCH_STACK"}, + {.flags = UWM_THREAD, .name = "UWM_THREAD"}, + {.flags = UWM_THREAD | UWM_SP, + .name = "UWM_THREAD | UWM_SP"}, + {.flags = UWM_THREAD | UWM_CALLER | UWM_SP, + .name = "UWM_THREAD | UWM_CALLER | UWM_SP"}, + {.flags = UWM_IRQ, .name = "UWM_IRQ"}, + {.flags = UWM_IRQ | UWM_SWITCH_STACK, + .name = "UWM_IRQ | UWM_SWITCH_STACK"}, + {.flags = UWM_IRQ | UWM_SP, + .name = "UWM_IRQ | UWM_SP"}, + {.flags = UWM_IRQ | UWM_REGS, + .name = "UWM_IRQ | UWM_REGS"}, + {.flags = UWM_IRQ | UWM_SP | UWM_REGS, + .name = "UWM_IRQ | UWM_SP | UWM_REGS"}, + {.flags = UWM_IRQ | UWM_CALLER | UWM_SP, + .name = "UWM_IRQ | UWM_CALLER | UWM_SP"}, + {.flags = UWM_IRQ | UWM_CALLER | UWM_SP | UWM_REGS, + .name = "UWM_IRQ | UWM_CALLER | UWM_SP | UWM_REGS"}, + {.flags = UWM_IRQ | UWM_CALLER | UWM_SP | UWM_REGS | UWM_SWITCH_STACK, + .name = "UWM_IRQ | UWM_CALLER | UWM_SP | UWM_REGS | UWM_SWITCH_STACK"}, + #ifdef CONFIG_KPROBES + {.flags = UWM_PGM, .name = "UWM_PGM"}, + {.flags = UWM_PGM | UWM_SP, + .name = "UWM_PGM | UWM_SP"}, + {.flags = UWM_PGM | UWM_REGS, + .name = "UWM_PGM | UWM_REGS"}, + {.flags = UWM_PGM | UWM_SP | UWM_REGS, + .name = "UWM_PGM | UWM_SP | UWM_REGS"}, + #endif +}; + +/* + * Parameter description generator: required for KUNIT_ARRAY_PARAM() + */ +static void get_desc(const struct test_params *params, char *desc) +{ + strscpy(desc, params->name, KUNIT_PARAM_DESC_SIZE); +} + +/* + * Create test_unwind_gen_params + */ +KUNIT_ARRAY_PARAM(test_unwind, param_list, get_desc); + +static void test_unwind_flags(struct kunit *test) { struct unwindme u; + const struct test_params *params; - u.flags = flags; + current_test = test; + params = (const struct test_params *)test->param_value; + u.flags = params->flags; if (u.flags & UWM_THREAD) - return test_unwind_task(&u); + KUNIT_EXPECT_EQ(test, 0, test_unwind_task(test, &u)); else if (u.flags & UWM_IRQ) - return test_unwind_irq(&u); + KUNIT_EXPECT_EQ(test, 0, test_unwind_irq(&u)); else - return unwindme_func1(&u); + KUNIT_EXPECT_EQ(test, 0, unwindme_func1(&u)); } -static int test_unwind_init(void) -{ - int failed = 0; - int total = 0; - -#define TEST(flags) \ -do { \ - pr_info("[ RUN ] " #flags "\n"); \ - total++; \ - if (!test_unwind_flags((flags))) { \ - pr_info("[ OK ] " #flags "\n"); \ - } else { \ - pr_err("[ FAILED ] " #flags "\n"); \ - failed++; \ - } \ -} while (0) - - pr_info("running stack unwinder tests"); - 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 - if (failed) { - pr_err("%d of %d stack unwinder tests failed", failed, total); - WARN(1, "%d of %d stack unwinder tests failed", failed, total); - } else { - pr_info("all %d stack unwinder tests passed", total); - } +static struct kunit_case unwind_test_cases[] = { + KUNIT_CASE_PARAM(test_unwind_flags, test_unwind_gen_params), + {} +}; - return failed ? -EINVAL : 0; -} +static struct kunit_suite test_unwind_suite = { + .name = "test_unwind", + .test_cases = unwind_test_cases, +}; -static void test_unwind_exit(void) -{ -} +kunit_test_suites(&test_unwind_suite); -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 1141c8d5c0d0..2203164b39da 100644 --- a/arch/s390/mm/cmm.c +++ b/arch/s390/mm/cmm.c @@ -14,8 +14,8 @@ #include <linux/moduleparam.h> #include <linux/gfp.h> #include <linux/sched.h> +#include <linux/string_helpers.h> #include <linux/sysctl.h> -#include <linux/ctype.h> #include <linux/swap.h> #include <linux/kthread.h> #include <linux/oom.h> @@ -394,13 +394,10 @@ static int __init cmm_init(void) goto out_sysctl; #ifdef CONFIG_CMM_IUCV /* convert sender to uppercase characters */ - if (sender) { - int len = strlen(sender); - while (len--) - sender[len] = toupper(sender[len]); - } else { + if (sender) + string_upper(sender, sender); + else sender = cmm_default_sender; - } rc = smsg_register_callback(SMSG_PREFIX, cmm_smsg_target); if (rc < 0) diff --git a/arch/s390/mm/dump_pagetables.c b/arch/s390/mm/dump_pagetables.c index 0b0c8c284953..9f9af5298dd6 100644 --- a/arch/s390/mm/dump_pagetables.c +++ b/arch/s390/mm/dump_pagetables.c @@ -8,6 +8,7 @@ #include <linux/kasan.h> #include <asm/ptdump.h> #include <asm/kasan.h> +#include <asm/nospec-branch.h> #include <asm/sections.h> static unsigned long max_addr; @@ -116,8 +117,13 @@ static void note_prot_wx(struct pg_state *st, unsigned long addr) return; if (st->current_prot & _PAGE_NOEXEC) return; - /* The first lowcore page is currently still W+X. */ - if (addr == PAGE_SIZE) + /* + * The first lowcore page is W+X if spectre mitigations are using + * trampolines or the BEAR enhancements facility is not installed, + * in which case we have two lpswe instructions in lowcore that need + * to be executable. + */ + if (addr == PAGE_SIZE && (nospec_uses_trampoline() || !static_key_enabled(&cpu_has_bear))) return; WARN_ONCE(1, "s390/mm: Found insecure W+X mapping at address %pS\n", (void *)st->start_address); @@ -203,7 +209,9 @@ void ptdump_check_wx(void) if (st.wx_pages) pr_warn("Checked W+X mappings: FAILED, %lu W+X pages found\n", st.wx_pages); else - pr_info("Checked W+X mappings: passed, no unexpected W+X pages found\n"); + pr_info("Checked W+X mappings: passed, no %sW+X pages found\n", + (nospec_uses_trampoline() || !static_key_enabled(&cpu_has_bear)) ? + "unexpected " : ""); } #endif /* CONFIG_DEBUG_WX */ diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c index 4d3b33ce81c6..dfee0ebb2fac 100644 --- a/arch/s390/mm/gmap.c +++ b/arch/s390/mm/gmap.c @@ -672,6 +672,7 @@ EXPORT_SYMBOL_GPL(gmap_fault); */ void __gmap_zap(struct gmap *gmap, unsigned long gaddr) { + struct vm_area_struct *vma; unsigned long vmaddr; spinlock_t *ptl; pte_t *ptep; @@ -681,11 +682,17 @@ void __gmap_zap(struct gmap *gmap, unsigned long gaddr) gaddr >> PMD_SHIFT); if (vmaddr) { vmaddr |= gaddr & ~PMD_MASK; + + vma = vma_lookup(gmap->mm, vmaddr); + if (!vma || is_vm_hugetlb_page(vma)) + return; + /* Get pointer to the page table entry */ ptep = get_locked_pte(gmap->mm, vmaddr, &ptl); - if (likely(ptep)) + if (likely(ptep)) { ptep_zap_unused(gmap->mm, vmaddr, ptep, 0); - pte_unmap_unlock(ptep, ptl); + pte_unmap_unlock(ptep, ptl); + } } } EXPORT_SYMBOL_GPL(__gmap_zap); @@ -2677,8 +2684,10 @@ static int __s390_reset_acc(pte_t *ptep, unsigned long addr, { pte_t pte = READ_ONCE(*ptep); + /* There is a reference through the mapping */ if (pte_present(pte)) - WARN_ON_ONCE(uv_destroy_page(pte_val(pte) & PAGE_MASK)); + WARN_ON_ONCE(uv_destroy_owned_page(pte_val(pte) & PAGE_MASK)); + return 0; } diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index a04faf49001a..8c6f258a6183 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -58,8 +58,6 @@ unsigned long empty_zero_page, zero_page_mask; EXPORT_SYMBOL(empty_zero_page); EXPORT_SYMBOL(zero_page_mask); -bool initmem_freed; - static void __init setup_zero_pages(void) { unsigned int order; @@ -214,7 +212,6 @@ void __init mem_init(void) void free_initmem(void) { - initmem_freed = true; __set_memory((unsigned long)_sinittext, (unsigned long)(_einittext - _sinittext) >> PAGE_SHIFT, SET_MEMORY_RW | SET_MEMORY_NX); diff --git a/arch/s390/mm/kasan_init.c b/arch/s390/mm/kasan_init.c index 3e4735168019..483b9dbe0970 100644 --- a/arch/s390/mm/kasan_init.c +++ b/arch/s390/mm/kasan_init.c @@ -399,5 +399,5 @@ void __init kasan_copy_shadow_mapping(void) void __init kasan_free_early_identity(void) { - memblock_free(pgalloc_pos, pgalloc_freeable - pgalloc_pos); + memblock_phys_free(pgalloc_pos, pgalloc_freeable - pgalloc_pos); } diff --git a/arch/s390/mm/pageattr.c b/arch/s390/mm/pageattr.c index fdc86c0e4e6c..654019181a37 100644 --- a/arch/s390/mm/pageattr.c +++ b/arch/s390/mm/pageattr.c @@ -57,7 +57,7 @@ void arch_report_meminfo(struct seq_file *m) static void pgt_set(unsigned long *old, unsigned long new, unsigned long addr, unsigned long dtt) { - unsigned long table, mask; + unsigned long *table, mask; mask = 0; if (MACHINE_HAS_EDAT2) { @@ -72,7 +72,7 @@ static void pgt_set(unsigned long *old, unsigned long new, unsigned long addr, mask = ~(PTRS_PER_PTE * sizeof(pte_t) - 1); break; } - table = (unsigned long)old & mask; + table = (unsigned long *)((unsigned long)old & mask); crdte(*old, new, table, dtt, addr, S390_lowcore.kernel_asce); } else if (MACHINE_HAS_IDTE) { cspg(old, *old, new); diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index 034721a68d8f..c16232cd0ec5 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -429,22 +429,36 @@ static inline pmd_t pmdp_flush_lazy(struct mm_struct *mm, } #ifdef CONFIG_PGSTE -static pmd_t *pmd_alloc_map(struct mm_struct *mm, unsigned long addr) +static int pmd_lookup(struct mm_struct *mm, unsigned long addr, pmd_t **pmdp) { + struct vm_area_struct *vma; pgd_t *pgd; p4d_t *p4d; pud_t *pud; - pmd_t *pmd; + + /* We need a valid VMA, otherwise this is clearly a fault. */ + vma = vma_lookup(mm, addr); + if (!vma) + return -EFAULT; pgd = pgd_offset(mm, addr); - p4d = p4d_alloc(mm, pgd, addr); - if (!p4d) - return NULL; - pud = pud_alloc(mm, p4d, addr); - if (!pud) - return NULL; - pmd = pmd_alloc(mm, pud, addr); - return pmd; + if (!pgd_present(*pgd)) + return -ENOENT; + + p4d = p4d_offset(pgd, addr); + if (!p4d_present(*p4d)) + return -ENOENT; + + pud = pud_offset(p4d, addr); + if (!pud_present(*pud)) + return -ENOENT; + + /* Large PUDs are not supported yet. */ + if (pud_large(*pud)) + return -EFAULT; + + *pmdp = pmd_offset(pud, addr); + return 0; } #endif @@ -778,14 +792,23 @@ int set_guest_storage_key(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp; pte_t *ptep; - pmdp = pmd_alloc_map(mm, addr); - if (unlikely(!pmdp)) + /* + * If we don't have a PTE table and if there is no huge page mapped, + * we can ignore attempts to set the key to 0, because it already is 0. + */ + switch (pmd_lookup(mm, addr, &pmdp)) { + case -ENOENT: + return key ? -EFAULT : 0; + case 0: + break; + default: return -EFAULT; + } ptl = pmd_lock(mm, pmdp); if (!pmd_present(*pmdp)) { spin_unlock(ptl); - return -EFAULT; + return key ? -EFAULT : 0; } if (pmd_large(*pmdp)) { @@ -801,10 +824,7 @@ int set_guest_storage_key(struct mm_struct *mm, unsigned long addr, } spin_unlock(ptl); - ptep = pte_alloc_map_lock(mm, pmdp, addr, &ptl); - if (unlikely(!ptep)) - return -EFAULT; - + ptep = pte_offset_map_lock(mm, pmdp, addr, &ptl); new = old = pgste_get_lock(ptep); pgste_val(new) &= ~(PGSTE_GR_BIT | PGSTE_GC_BIT | PGSTE_ACC_BITS | PGSTE_FP_BIT); @@ -881,14 +901,23 @@ int reset_guest_reference_bit(struct mm_struct *mm, unsigned long addr) pte_t *ptep; int cc = 0; - pmdp = pmd_alloc_map(mm, addr); - if (unlikely(!pmdp)) + /* + * If we don't have a PTE table and if there is no huge page mapped, + * the storage key is 0 and there is nothing for us to do. + */ + switch (pmd_lookup(mm, addr, &pmdp)) { + case -ENOENT: + return 0; + case 0: + break; + default: return -EFAULT; + } ptl = pmd_lock(mm, pmdp); if (!pmd_present(*pmdp)) { spin_unlock(ptl); - return -EFAULT; + return 0; } if (pmd_large(*pmdp)) { @@ -900,10 +929,7 @@ int reset_guest_reference_bit(struct mm_struct *mm, unsigned long addr) } spin_unlock(ptl); - ptep = pte_alloc_map_lock(mm, pmdp, addr, &ptl); - if (unlikely(!ptep)) - return -EFAULT; - + ptep = pte_offset_map_lock(mm, pmdp, addr, &ptl); new = old = pgste_get_lock(ptep); /* Reset guest reference bit only */ pgste_val(new) &= ~PGSTE_GR_BIT; @@ -935,15 +961,24 @@ int get_guest_storage_key(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp; pte_t *ptep; - pmdp = pmd_alloc_map(mm, addr); - if (unlikely(!pmdp)) + /* + * If we don't have a PTE table and if there is no huge page mapped, + * the storage key is 0. + */ + *key = 0; + + switch (pmd_lookup(mm, addr, &pmdp)) { + case -ENOENT: + return 0; + case 0: + break; + default: return -EFAULT; + } ptl = pmd_lock(mm, pmdp); if (!pmd_present(*pmdp)) { - /* Not yet mapped memory has a zero key */ spin_unlock(ptl); - *key = 0; return 0; } @@ -956,10 +991,7 @@ int get_guest_storage_key(struct mm_struct *mm, unsigned long addr, } spin_unlock(ptl); - ptep = pte_alloc_map_lock(mm, pmdp, addr, &ptl); - if (unlikely(!ptep)) - return -EFAULT; - + ptep = pte_offset_map_lock(mm, pmdp, addr, &ptl); pgste = pgste_get_lock(ptep); *key = (pgste_val(pgste) & (PGSTE_ACC_BITS | PGSTE_FP_BIT)) >> 56; paddr = pte_val(*ptep) & PAGE_MASK; @@ -988,6 +1020,7 @@ EXPORT_SYMBOL(get_guest_storage_key); int pgste_perform_essa(struct mm_struct *mm, unsigned long hva, int orc, unsigned long *oldpte, unsigned long *oldpgste) { + struct vm_area_struct *vma; unsigned long pgstev; spinlock_t *ptl; pgste_t pgste; @@ -997,6 +1030,10 @@ int pgste_perform_essa(struct mm_struct *mm, unsigned long hva, int orc, WARN_ON_ONCE(orc > ESSA_MAX); if (unlikely(orc > ESSA_MAX)) return -EINVAL; + + vma = vma_lookup(mm, hva); + if (!vma || is_vm_hugetlb_page(vma)) + return -EFAULT; ptep = get_locked_pte(mm, hva, &ptl); if (unlikely(!ptep)) return -EFAULT; @@ -1089,10 +1126,14 @@ EXPORT_SYMBOL(pgste_perform_essa); int set_pgste_bits(struct mm_struct *mm, unsigned long hva, unsigned long bits, unsigned long value) { + struct vm_area_struct *vma; spinlock_t *ptl; pgste_t new; pte_t *ptep; + vma = vma_lookup(mm, hva); + if (!vma || is_vm_hugetlb_page(vma)) + return -EFAULT; ptep = get_locked_pte(mm, hva, &ptl); if (unlikely(!ptep)) return -EFAULT; @@ -1117,9 +1158,13 @@ EXPORT_SYMBOL(set_pgste_bits); */ int get_pgste(struct mm_struct *mm, unsigned long hva, unsigned long *pgstep) { + struct vm_area_struct *vma; spinlock_t *ptl; pte_t *ptep; + vma = vma_lookup(mm, hva); + if (!vma || is_vm_hugetlb_page(vma)) + return -EFAULT; ptep = get_locked_pte(mm, hva, &ptl); if (unlikely(!ptep)) return -EFAULT; diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c index 2b1c6d916cf9..7d9705eeb02f 100644 --- a/arch/s390/mm/vmem.c +++ b/arch/s390/mm/vmem.c @@ -13,6 +13,7 @@ #include <linux/hugetlb.h> #include <linux/slab.h> #include <asm/cacheflush.h> +#include <asm/nospec-branch.h> #include <asm/pgalloc.h> #include <asm/setup.h> #include <asm/tlbflush.h> @@ -584,8 +585,13 @@ void __init vmem_map_init(void) __set_memory(__stext_amode31, (__etext_amode31 - __stext_amode31) >> PAGE_SHIFT, SET_MEMORY_RO | SET_MEMORY_X); - /* we need lowcore executable for our LPSWE instructions */ - set_memory_x(0, 1); + if (nospec_uses_trampoline() || !static_key_enabled(&cpu_has_bear)) { + /* + * Lowcore must be executable for LPSWE + * and expoline trampoline branch instructions. + */ + set_memory_x(0, 1); + } pr_info("Write protected kernel read-only data: %luk\n", (unsigned long)(__end_rodata - _stext) >> 10); diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index 88419263a89a..233cc9bcd652 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -248,8 +248,7 @@ static inline void reg_set_seen(struct bpf_jit *jit, u32 b1) #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;\ + int rel = (addrs[(i) + (off) + 1] - jit->prg) / 2; \ _EMIT6((op1) | reg(b1, b2) << 16 | (rel & 0xffff), (op2) | (mask));\ REG_SET_SEEN(b1); \ REG_SET_SEEN(b2); \ @@ -568,7 +567,7 @@ static void bpf_jit_epilogue(struct bpf_jit *jit, u32 stack_depth) EMIT4(0xb9040000, REG_2, BPF_REG_0); /* Restore registers */ save_restore_regs(jit, REGS_RESTORE, stack_depth); - if (__is_defined(CC_USING_EXPOLINE) && !nospec_disable) { + if (nospec_uses_trampoline()) { jit->r14_thunk_ip = jit->prg; /* Generate __s390_indirect_jump_r14 thunk */ if (test_facility(35)) { @@ -586,7 +585,7 @@ static void bpf_jit_epilogue(struct bpf_jit *jit, u32 stack_depth) /* br %r14 */ _EMIT2(0x07fe); - if (__is_defined(CC_USING_EXPOLINE) && !nospec_disable && + if ((nospec_uses_trampoline()) && (is_first_pass(jit) || (jit->seen & SEEN_FUNC))) { jit->r1_thunk_ip = jit->prg; /* Generate __s390_indirect_jump_r1 thunk */ @@ -761,10 +760,10 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, EMIT4(0xb9080000, dst_reg, src_reg); break; case BPF_ALU | BPF_ADD | BPF_K: /* dst = (u32) dst + (u32) imm */ - if (!imm) - break; - /* alfi %dst,imm */ - EMIT6_IMM(0xc20b0000, dst_reg, imm); + if (imm != 0) { + /* alfi %dst,imm */ + EMIT6_IMM(0xc20b0000, dst_reg, imm); + } EMIT_ZERO(dst_reg); break; case BPF_ALU64 | BPF_ADD | BPF_K: /* dst = dst + imm */ @@ -786,17 +785,22 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, EMIT4(0xb9090000, dst_reg, src_reg); break; case BPF_ALU | BPF_SUB | BPF_K: /* dst = (u32) dst - (u32) imm */ - if (!imm) - break; - /* alfi %dst,-imm */ - EMIT6_IMM(0xc20b0000, dst_reg, -imm); + if (imm != 0) { + /* alfi %dst,-imm */ + EMIT6_IMM(0xc20b0000, dst_reg, -imm); + } EMIT_ZERO(dst_reg); break; case BPF_ALU64 | BPF_SUB | BPF_K: /* dst = dst - imm */ if (!imm) break; - /* agfi %dst,-imm */ - EMIT6_IMM(0xc2080000, dst_reg, -imm); + if (imm == -0x80000000) { + /* algfi %dst,0x80000000 */ + EMIT6_IMM(0xc20a0000, dst_reg, 0x80000000); + } else { + /* agfi %dst,-imm */ + EMIT6_IMM(0xc2080000, dst_reg, -imm); + } break; /* * BPF_MUL @@ -811,10 +815,10 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, EMIT4(0xb90c0000, dst_reg, src_reg); break; case BPF_ALU | BPF_MUL | BPF_K: /* dst = (u32) dst * (u32) imm */ - if (imm == 1) - break; - /* msfi %r5,imm */ - EMIT6_IMM(0xc2010000, dst_reg, imm); + if (imm != 1) { + /* msfi %r5,imm */ + EMIT6_IMM(0xc2010000, dst_reg, imm); + } EMIT_ZERO(dst_reg); break; case BPF_ALU64 | BPF_MUL | BPF_K: /* dst = dst * imm */ @@ -867,6 +871,8 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, if (BPF_OP(insn->code) == BPF_MOD) /* lhgi %dst,0 */ EMIT4_IMM(0xa7090000, dst_reg, 0); + else + EMIT_ZERO(dst_reg); break; } /* lhi %w0,0 */ @@ -999,10 +1005,10 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, EMIT4(0xb9820000, dst_reg, src_reg); break; case BPF_ALU | BPF_XOR | BPF_K: /* dst = (u32) dst ^ (u32) imm */ - if (!imm) - break; - /* xilf %dst,imm */ - EMIT6_IMM(0xc0070000, dst_reg, imm); + if (imm != 0) { + /* xilf %dst,imm */ + EMIT6_IMM(0xc0070000, dst_reg, imm); + } EMIT_ZERO(dst_reg); break; case BPF_ALU64 | BPF_XOR | BPF_K: /* dst = dst ^ imm */ @@ -1033,10 +1039,10 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, EMIT6_DISP_LH(0xeb000000, 0x000d, dst_reg, dst_reg, src_reg, 0); break; case BPF_ALU | BPF_LSH | BPF_K: /* dst = (u32) dst << (u32) imm */ - if (imm == 0) - break; - /* sll %dst,imm(%r0) */ - EMIT4_DISP(0x89000000, dst_reg, REG_0, imm); + if (imm != 0) { + /* sll %dst,imm(%r0) */ + EMIT4_DISP(0x89000000, dst_reg, REG_0, imm); + } EMIT_ZERO(dst_reg); break; case BPF_ALU64 | BPF_LSH | BPF_K: /* dst = dst << imm */ @@ -1058,10 +1064,10 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, EMIT6_DISP_LH(0xeb000000, 0x000c, dst_reg, dst_reg, src_reg, 0); break; case BPF_ALU | BPF_RSH | BPF_K: /* dst = (u32) dst >> (u32) imm */ - if (imm == 0) - break; - /* srl %dst,imm(%r0) */ - EMIT4_DISP(0x88000000, dst_reg, REG_0, imm); + if (imm != 0) { + /* srl %dst,imm(%r0) */ + EMIT4_DISP(0x88000000, dst_reg, REG_0, imm); + } EMIT_ZERO(dst_reg); break; case BPF_ALU64 | BPF_RSH | BPF_K: /* dst = dst >> imm */ @@ -1083,10 +1089,10 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, EMIT6_DISP_LH(0xeb000000, 0x000a, dst_reg, dst_reg, src_reg, 0); break; case BPF_ALU | BPF_ARSH | BPF_K: /* ((s32) dst >> imm */ - if (imm == 0) - break; - /* sra %dst,imm(%r0) */ - EMIT4_DISP(0x8a000000, dst_reg, REG_0, imm); + if (imm != 0) { + /* sra %dst,imm(%r0) */ + EMIT4_DISP(0x8a000000, dst_reg, REG_0, imm); + } EMIT_ZERO(dst_reg); break; case BPF_ALU64 | BPF_ARSH | BPF_K: /* ((s64) dst) >>= imm */ @@ -1326,7 +1332,7 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, jit->seen |= SEEN_FUNC; /* lgrl %w1,func */ EMIT6_PCREL_RILB(0xc4080000, REG_W1, _EMIT_CONST_U64(func)); - if (__is_defined(CC_USING_EXPOLINE) && !nospec_disable) { + if (nospec_uses_trampoline()) { /* brasl %r14,__s390_indirect_jump_r1 */ EMIT6_PCREL_RILB(0xc0050000, REG_14, jit->r1_thunk_ip); } else { @@ -1820,7 +1826,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp) jit.addrs = kvcalloc(fp->len + 1, sizeof(*jit.addrs), GFP_KERNEL); if (jit.addrs == NULL) { fp = orig_fp; - goto out; + goto free_addrs; } /* * Three initial passes: diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index e7e6788d75a8..872d772b73d2 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -92,7 +92,7 @@ void zpci_remove_reserved_devices(void) spin_unlock(&zpci_list_lock); list_for_each_entry_safe(zdev, tmp, &remove, entry) - zpci_zdev_put(zdev); + zpci_device_reserved(zdev); } int pci_domain_nr(struct pci_bus *bus) @@ -561,7 +561,7 @@ static void zpci_cleanup_bus_resources(struct zpci_dev *zdev) zdev->has_resources = 0; } -int pcibios_add_device(struct pci_dev *pdev) +int pcibios_device_add(struct pci_dev *pdev) { struct zpci_dev *zdev = to_zpci(pdev); struct resource *res; @@ -751,6 +751,14 @@ error: return ERR_PTR(rc); } +bool zpci_is_device_configured(struct zpci_dev *zdev) +{ + enum zpci_state state = zdev->state; + + return state != ZPCI_FN_STATE_RESERVED && + state != ZPCI_FN_STATE_STANDBY; +} + /** * zpci_scan_configured_device() - Scan a freshly configured zpci_dev * @zdev: The zpci_dev to be configured @@ -822,6 +830,31 @@ int zpci_deconfigure_device(struct zpci_dev *zdev) return 0; } +/** + * zpci_device_reserved() - Mark device as resverved + * @zdev: the zpci_dev that was reserved + * + * Handle the case that a given zPCI function was reserved by another system. + * After a call to this function the zpci_dev can not be found via + * get_zdev_by_fid() anymore but may still be accessible via existing + * references though it will not be functional anymore. + */ +void zpci_device_reserved(struct zpci_dev *zdev) +{ + if (zdev->has_hp_slot) + zpci_exit_slot(zdev); + /* + * Remove device from zpci_list as it is going away. This also + * makes sure we ignore subsequent zPCI events for this device. + */ + spin_lock(&zpci_list_lock); + list_del(&zdev->entry); + spin_unlock(&zpci_list_lock); + zdev->state = ZPCI_FN_STATE_RESERVED; + zpci_dbg(3, "rsv fid:%x\n", zdev->fid); + zpci_zdev_put(zdev); +} + void zpci_release_device(struct kref *kref) { struct zpci_dev *zdev = container_of(kref, struct zpci_dev, kref); @@ -843,6 +876,12 @@ void zpci_release_device(struct kref *kref) case ZPCI_FN_STATE_STANDBY: if (zdev->has_hp_slot) zpci_exit_slot(zdev); + spin_lock(&zpci_list_lock); + list_del(&zdev->entry); + spin_unlock(&zpci_list_lock); + zpci_dbg(3, "rsv fid:%x\n", zdev->fid); + fallthrough; + case ZPCI_FN_STATE_RESERVED: if (zdev->has_resources) zpci_cleanup_bus_resources(zdev); zpci_bus_device_unregister(zdev); @@ -851,10 +890,6 @@ void zpci_release_device(struct kref *kref) default: break; } - - spin_lock(&zpci_list_lock); - list_del(&zdev->entry); - spin_unlock(&zpci_list_lock); zpci_dbg(3, "rem fid:%x\n", zdev->fid); kfree(zdev); } diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c index 93223bd110c3..1f4540d6bd2d 100644 --- a/arch/s390/pci/pci_dma.c +++ b/arch/s390/pci/pci_dma.c @@ -18,6 +18,8 @@ static struct kmem_cache *dma_region_table_cache; static struct kmem_cache *dma_page_table_cache; static int s390_iommu_strict; +static u64 s390_iommu_aperture; +static u32 s390_iommu_aperture_factor = 1; static int zpci_refresh_global(struct zpci_dev *zdev) { @@ -565,15 +567,19 @@ int zpci_dma_init_device(struct zpci_dev *zdev) /* * Restrict the iommu bitmap size to the minimum of the following: - * - main memory size + * - s390_iommu_aperture which defaults to high_memory * - 3-level pagetable address limit minus start_dma offset * - DMA address range allowed by the hardware (clp query pci fn) * * Also set zdev->end_dma to the actual end address of the usable * range, instead of the theoretical maximum as reported by hardware. + * + * This limits the number of concurrently usable DMA mappings since + * for each DMA mapped memory address we need a DMA address including + * extra DMA addresses for multiple mappings of the same memory address. */ zdev->start_dma = PAGE_ALIGN(zdev->start_dma); - zdev->iommu_size = min3((u64) high_memory, + zdev->iommu_size = min3(s390_iommu_aperture, ZPCI_TABLE_SIZE_RT - zdev->start_dma, zdev->end_dma - zdev->start_dma + 1); zdev->end_dma = zdev->start_dma + zdev->iommu_size - 1; @@ -660,6 +666,12 @@ static int __init dma_alloc_cpu_table_caches(void) int __init zpci_dma_init(void) { + s390_iommu_aperture = (u64)high_memory; + if (!s390_iommu_aperture_factor) + s390_iommu_aperture = ULONG_MAX; + else + s390_iommu_aperture *= s390_iommu_aperture_factor; + return dma_alloc_cpu_table_caches(); } @@ -692,3 +704,12 @@ static int __init s390_iommu_setup(char *str) } __setup("s390_iommu=", s390_iommu_setup); + +static int __init s390_iommu_aperture_setup(char *str) +{ + if (kstrtou32(str, 10, &s390_iommu_aperture_factor)) + s390_iommu_aperture_factor = 1; + return 1; +} + +__setup("s390_iommu_aperture=", s390_iommu_aperture_setup); diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c index c856f80cb21b..6a5bfa9dc1f2 100644 --- a/arch/s390/pci/pci_event.c +++ b/arch/s390/pci/pci_event.c @@ -52,6 +52,8 @@ static void __zpci_event_error(struct zpci_ccdf_err *ccdf) struct zpci_dev *zdev = get_zdev_by_fid(ccdf->fid); struct pci_dev *pdev = NULL; + zpci_dbg(3, "err fid:%x, fh:%x, pec:%x\n", + ccdf->fid, ccdf->fh, ccdf->pec); zpci_err("error CCDF:\n"); zpci_err_hex(ccdf, sizeof(*ccdf)); @@ -96,6 +98,8 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf) struct zpci_dev *zdev = get_zdev_by_fid(ccdf->fid); enum zpci_state state; + zpci_dbg(3, "avl fid:%x, fh:%x, pec:%x\n", + ccdf->fid, ccdf->fh, ccdf->pec); zpci_err("avail CCDF:\n"); zpci_err_hex(ccdf, sizeof(*ccdf)); @@ -140,7 +144,7 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf) /* The 0x0304 event may immediately reserve the device */ if (!clp_get_state(zdev->fid, &state) && state == ZPCI_FN_STATE_RESERVED) { - zpci_zdev_put(zdev); + zpci_device_reserved(zdev); } } break; @@ -151,7 +155,7 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf) case 0x0308: /* Standby -> Reserved */ if (!zdev) break; - zpci_zdev_put(zdev); + zpci_device_reserved(zdev); break; default: break; diff --git a/arch/s390/pci/pci_sysfs.c b/arch/s390/pci/pci_sysfs.c index 335c281811c7..cae280e5c047 100644 --- a/arch/s390/pci/pci_sysfs.c +++ b/arch/s390/pci/pci_sysfs.c @@ -90,6 +90,14 @@ static ssize_t recover_store(struct device *dev, struct device_attribute *attr, if (zdev_enabled(zdev)) { ret = zpci_disable_device(zdev); + /* + * Due to a z/VM vs LPAR inconsistency in the error + * state the FH may indicate an enabled device but + * disable says the device is already disabled don't + * treat it as an error here. + */ + if (ret == -EINVAL) + ret = 0; if (ret) goto out; } |