diff options
Diffstat (limited to 'arch/s390/kernel')
82 files changed, 28939 insertions, 0 deletions
diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile new file mode 100644 index 00000000..884b18af --- /dev/null +++ b/arch/s390/kernel/Makefile @@ -0,0 +1,61 @@ +# +# Makefile for the linux kernel. +# + +ifdef CONFIG_FUNCTION_TRACER +# Don't trace early setup code and tracing code +CFLAGS_REMOVE_early.o = -pg +CFLAGS_REMOVE_ftrace.o = -pg +endif + +# +# Passing null pointers is ok for smp code, since we access the lowcore here. +# +CFLAGS_smp.o := -Wno-nonnull + +# +# Pass UTS_MACHINE for user_regset definition +# +CFLAGS_ptrace.o += -DUTS_MACHINE='"$(UTS_MACHINE)"' + +CFLAGS_sysinfo.o += -Iinclude/math-emu -Iarch/s390/math-emu -w + +obj-y := bitmap.o traps.o time.o process.o base.o early.o setup.o vtime.o \ + processor.o sys_s390.o ptrace.o signal.o cpcmd.o ebcdic.o nmi.o \ + debug.o irq.o ipl.o dis.o diag.o mem_detect.o sclp.o vdso.o \ + sysinfo.o jump_label.o lgr.o os_info.o + +obj-y += $(if $(CONFIG_64BIT),entry64.o,entry.o) +obj-y += $(if $(CONFIG_64BIT),reipl64.o,reipl.o) + +extra-y += head.o init_task.o vmlinux.lds +extra-y += $(if $(CONFIG_64BIT),head64.o,head31.o) + +obj-$(CONFIG_MODULES) += s390_ksyms.o module.o +obj-$(CONFIG_SMP) += smp.o +obj-$(CONFIG_SCHED_BOOK) += topology.o +obj-$(CONFIG_HIBERNATION) += suspend.o swsusp_asm64.o +obj-$(CONFIG_AUDIT) += audit.o +compat-obj-$(CONFIG_AUDIT) += compat_audit.o +obj-$(CONFIG_COMPAT) += compat_linux.o compat_signal.o \ + compat_wrapper.o compat_exec_domain.o \ + $(compat-obj-y) + +obj-$(CONFIG_STACKTRACE) += stacktrace.o +obj-$(CONFIG_KPROBES) += kprobes.o +obj-$(CONFIG_FUNCTION_TRACER) += $(if $(CONFIG_64BIT),mcount64.o,mcount.o) +obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o +obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o +obj-$(CONFIG_FTRACE_SYSCALLS) += ftrace.o +obj-$(CONFIG_CRASH_DUMP) += crash_dump.o +obj-$(CONFIG_PERF_EVENTS) += perf_event.o perf_cpum_cf.o + +# Kexec part +S390_KEXEC_OBJS := machine_kexec.o crash.o +S390_KEXEC_OBJS += $(if $(CONFIG_64BIT),relocate_kernel64.o,relocate_kernel.o) +obj-$(CONFIG_KEXEC) += $(S390_KEXEC_OBJS) + +# vdso +obj-$(CONFIG_64BIT) += vdso64/ +obj-$(CONFIG_32BIT) += vdso32/ +obj-$(CONFIG_COMPAT) += vdso32/ diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c new file mode 100644 index 00000000..83e6edf5 --- /dev/null +++ b/arch/s390/kernel/asm-offsets.c @@ -0,0 +1,163 @@ +/* + * Generate definitions needed by assembly language modules. + * This code generates raw asm output which is post-processed to extract + * and format the required data. + */ + +#define ASM_OFFSETS_C + +#include <linux/kbuild.h> +#include <linux/sched.h> +#include <asm/cputime.h> +#include <asm/timer.h> +#include <asm/vdso.h> +#include <asm/pgtable.h> + +/* + * Make sure that the compiler is new enough. We want a compiler that + * is known to work with the "Q" assembler constraint. + */ +#if __GNUC__ < 3 || (__GNUC__ == 3 && __GNUC_MINOR__ < 3) +#error Your compiler is too old; please use version 3.3.3 or newer +#endif + +int main(void) +{ + DEFINE(__THREAD_info, offsetof(struct task_struct, stack)); + DEFINE(__THREAD_ksp, offsetof(struct task_struct, thread.ksp)); + DEFINE(__THREAD_mm_segment, offsetof(struct task_struct, thread.mm_segment)); + BLANK(); + DEFINE(__TASK_pid, offsetof(struct task_struct, pid)); + BLANK(); + DEFINE(__THREAD_per_cause, offsetof(struct task_struct, thread.per_event.cause)); + DEFINE(__THREAD_per_address, offsetof(struct task_struct, thread.per_event.address)); + DEFINE(__THREAD_per_paid, offsetof(struct task_struct, thread.per_event.paid)); + BLANK(); + DEFINE(__TI_task, offsetof(struct thread_info, task)); + DEFINE(__TI_domain, offsetof(struct thread_info, exec_domain)); + DEFINE(__TI_flags, offsetof(struct thread_info, flags)); + DEFINE(__TI_cpu, offsetof(struct thread_info, cpu)); + DEFINE(__TI_precount, offsetof(struct thread_info, preempt_count)); + DEFINE(__TI_user_timer, offsetof(struct thread_info, user_timer)); + DEFINE(__TI_system_timer, offsetof(struct thread_info, system_timer)); + DEFINE(__TI_last_break, offsetof(struct thread_info, last_break)); + BLANK(); + DEFINE(__PT_ARGS, offsetof(struct pt_regs, args)); + DEFINE(__PT_PSW, offsetof(struct pt_regs, psw)); + DEFINE(__PT_GPRS, offsetof(struct pt_regs, gprs)); + DEFINE(__PT_ORIG_GPR2, offsetof(struct pt_regs, orig_gpr2)); + DEFINE(__PT_INT_CODE, offsetof(struct pt_regs, int_code)); + DEFINE(__PT_INT_PARM_LONG, offsetof(struct pt_regs, int_parm_long)); + DEFINE(__PT_SIZE, sizeof(struct pt_regs)); + BLANK(); + DEFINE(__SF_BACKCHAIN, offsetof(struct stack_frame, back_chain)); + DEFINE(__SF_GPRS, offsetof(struct stack_frame, gprs)); + DEFINE(__SF_EMPTY, offsetof(struct stack_frame, empty1)); + BLANK(); + /* timeval/timezone offsets for use by vdso */ + DEFINE(__VDSO_UPD_COUNT, offsetof(struct vdso_data, tb_update_count)); + DEFINE(__VDSO_XTIME_STAMP, offsetof(struct vdso_data, xtime_tod_stamp)); + DEFINE(__VDSO_XTIME_SEC, offsetof(struct vdso_data, xtime_clock_sec)); + DEFINE(__VDSO_XTIME_NSEC, offsetof(struct vdso_data, xtime_clock_nsec)); + DEFINE(__VDSO_WTOM_SEC, offsetof(struct vdso_data, wtom_clock_sec)); + DEFINE(__VDSO_WTOM_NSEC, offsetof(struct vdso_data, wtom_clock_nsec)); + DEFINE(__VDSO_TIMEZONE, offsetof(struct vdso_data, tz_minuteswest)); + DEFINE(__VDSO_ECTG_OK, offsetof(struct vdso_data, ectg_available)); + DEFINE(__VDSO_NTP_MULT, offsetof(struct vdso_data, ntp_mult)); + DEFINE(__VDSO_ECTG_BASE, offsetof(struct vdso_per_cpu_data, ectg_timer_base)); + DEFINE(__VDSO_ECTG_USER, offsetof(struct vdso_per_cpu_data, ectg_user_time)); + /* constants used by the vdso */ + DEFINE(__CLOCK_REALTIME, CLOCK_REALTIME); + DEFINE(__CLOCK_MONOTONIC, CLOCK_MONOTONIC); + DEFINE(__CLOCK_REALTIME_RES, MONOTONIC_RES_NSEC); + BLANK(); + /* idle data offsets */ + DEFINE(__IDLE_ENTER, offsetof(struct s390_idle_data, idle_enter)); + DEFINE(__IDLE_EXIT, offsetof(struct s390_idle_data, idle_exit)); + /* vtimer queue offsets */ + DEFINE(__VQ_IDLE_ENTER, offsetof(struct vtimer_queue, idle_enter)); + DEFINE(__VQ_IDLE_EXIT, offsetof(struct vtimer_queue, idle_exit)); + /* lowcore offsets */ + DEFINE(__LC_EXT_PARAMS, offsetof(struct _lowcore, ext_params)); + DEFINE(__LC_EXT_CPU_ADDR, offsetof(struct _lowcore, ext_cpu_addr)); + DEFINE(__LC_EXT_INT_CODE, offsetof(struct _lowcore, ext_int_code)); + DEFINE(__LC_SVC_ILC, offsetof(struct _lowcore, svc_ilc)); + DEFINE(__LC_SVC_INT_CODE, offsetof(struct _lowcore, svc_code)); + DEFINE(__LC_PGM_ILC, offsetof(struct _lowcore, pgm_ilc)); + DEFINE(__LC_PGM_INT_CODE, offsetof(struct _lowcore, pgm_code)); + DEFINE(__LC_TRANS_EXC_CODE, offsetof(struct _lowcore, trans_exc_code)); + DEFINE(__LC_PER_CAUSE, offsetof(struct _lowcore, per_perc_atmid)); + DEFINE(__LC_PER_ADDRESS, offsetof(struct _lowcore, per_address)); + DEFINE(__LC_PER_PAID, offsetof(struct _lowcore, per_access_id)); + DEFINE(__LC_AR_MODE_ID, offsetof(struct _lowcore, ar_access_id)); + DEFINE(__LC_SUBCHANNEL_ID, offsetof(struct _lowcore, subchannel_id)); + DEFINE(__LC_SUBCHANNEL_NR, offsetof(struct _lowcore, subchannel_nr)); + DEFINE(__LC_IO_INT_PARM, offsetof(struct _lowcore, io_int_parm)); + DEFINE(__LC_IO_INT_WORD, offsetof(struct _lowcore, io_int_word)); + DEFINE(__LC_STFL_FAC_LIST, offsetof(struct _lowcore, stfl_fac_list)); + DEFINE(__LC_MCCK_CODE, offsetof(struct _lowcore, mcck_interruption_code)); + DEFINE(__LC_RST_OLD_PSW, offsetof(struct _lowcore, restart_old_psw)); + DEFINE(__LC_EXT_OLD_PSW, offsetof(struct _lowcore, external_old_psw)); + DEFINE(__LC_SVC_OLD_PSW, offsetof(struct _lowcore, svc_old_psw)); + DEFINE(__LC_PGM_OLD_PSW, offsetof(struct _lowcore, program_old_psw)); + DEFINE(__LC_MCK_OLD_PSW, offsetof(struct _lowcore, mcck_old_psw)); + DEFINE(__LC_IO_OLD_PSW, offsetof(struct _lowcore, io_old_psw)); + DEFINE(__LC_RST_NEW_PSW, offsetof(struct _lowcore, restart_psw)); + DEFINE(__LC_EXT_NEW_PSW, offsetof(struct _lowcore, external_new_psw)); + DEFINE(__LC_SVC_NEW_PSW, offsetof(struct _lowcore, svc_new_psw)); + DEFINE(__LC_PGM_NEW_PSW, offsetof(struct _lowcore, program_new_psw)); + DEFINE(__LC_MCK_NEW_PSW, offsetof(struct _lowcore, mcck_new_psw)); + DEFINE(__LC_IO_NEW_PSW, offsetof(struct _lowcore, io_new_psw)); + BLANK(); + DEFINE(__LC_SAVE_AREA_SYNC, offsetof(struct _lowcore, save_area_sync)); + DEFINE(__LC_SAVE_AREA_ASYNC, offsetof(struct _lowcore, save_area_async)); + DEFINE(__LC_SAVE_AREA_RESTART, offsetof(struct _lowcore, save_area_restart)); + DEFINE(__LC_RETURN_PSW, offsetof(struct _lowcore, return_psw)); + DEFINE(__LC_RETURN_MCCK_PSW, offsetof(struct _lowcore, return_mcck_psw)); + DEFINE(__LC_SYNC_ENTER_TIMER, offsetof(struct _lowcore, sync_enter_timer)); + DEFINE(__LC_ASYNC_ENTER_TIMER, offsetof(struct _lowcore, async_enter_timer)); + DEFINE(__LC_MCCK_ENTER_TIMER, offsetof(struct _lowcore, mcck_enter_timer)); + DEFINE(__LC_EXIT_TIMER, offsetof(struct _lowcore, exit_timer)); + DEFINE(__LC_USER_TIMER, offsetof(struct _lowcore, user_timer)); + DEFINE(__LC_SYSTEM_TIMER, offsetof(struct _lowcore, system_timer)); + DEFINE(__LC_STEAL_TIMER, offsetof(struct _lowcore, steal_timer)); + DEFINE(__LC_LAST_UPDATE_TIMER, offsetof(struct _lowcore, last_update_timer)); + DEFINE(__LC_LAST_UPDATE_CLOCK, offsetof(struct _lowcore, last_update_clock)); + DEFINE(__LC_CURRENT, offsetof(struct _lowcore, current_task)); + DEFINE(__LC_CURRENT_PID, offsetof(struct _lowcore, current_pid)); + DEFINE(__LC_THREAD_INFO, offsetof(struct _lowcore, thread_info)); + DEFINE(__LC_KERNEL_STACK, offsetof(struct _lowcore, kernel_stack)); + DEFINE(__LC_ASYNC_STACK, offsetof(struct _lowcore, async_stack)); + DEFINE(__LC_PANIC_STACK, offsetof(struct _lowcore, panic_stack)); + DEFINE(__LC_RESTART_STACK, offsetof(struct _lowcore, restart_stack)); + DEFINE(__LC_RESTART_FN, offsetof(struct _lowcore, restart_fn)); + DEFINE(__LC_USER_ASCE, offsetof(struct _lowcore, user_asce)); + DEFINE(__LC_INT_CLOCK, offsetof(struct _lowcore, int_clock)); + DEFINE(__LC_MCCK_CLOCK, offsetof(struct _lowcore, mcck_clock)); + DEFINE(__LC_MACHINE_FLAGS, offsetof(struct _lowcore, machine_flags)); + DEFINE(__LC_FTRACE_FUNC, offsetof(struct _lowcore, ftrace_func)); + DEFINE(__LC_IRB, offsetof(struct _lowcore, irb)); + DEFINE(__LC_DUMP_REIPL, offsetof(struct _lowcore, ipib)); + BLANK(); + DEFINE(__LC_CPU_TIMER_SAVE_AREA, offsetof(struct _lowcore, cpu_timer_save_area)); + DEFINE(__LC_CLOCK_COMP_SAVE_AREA, offsetof(struct _lowcore, clock_comp_save_area)); + DEFINE(__LC_PSW_SAVE_AREA, offsetof(struct _lowcore, psw_save_area)); + DEFINE(__LC_PREFIX_SAVE_AREA, offsetof(struct _lowcore, prefixreg_save_area)); + DEFINE(__LC_AREGS_SAVE_AREA, offsetof(struct _lowcore, access_regs_save_area)); + DEFINE(__LC_FPREGS_SAVE_AREA, offsetof(struct _lowcore, floating_pt_save_area)); + DEFINE(__LC_GPREGS_SAVE_AREA, offsetof(struct _lowcore, gpregs_save_area)); + DEFINE(__LC_CREGS_SAVE_AREA, offsetof(struct _lowcore, cregs_save_area)); +#ifdef CONFIG_32BIT + DEFINE(SAVE_AREA_BASE, offsetof(struct _lowcore, extended_save_area_addr)); +#else /* CONFIG_32BIT */ + DEFINE(__LC_EXT_PARAMS2, offsetof(struct _lowcore, ext_params2)); + DEFINE(SAVE_AREA_BASE, offsetof(struct _lowcore, floating_pt_save_area)); + DEFINE(__LC_PASTE, offsetof(struct _lowcore, paste)); + DEFINE(__LC_FP_CREG_SAVE_AREA, offsetof(struct _lowcore, fpt_creg_save_area)); + DEFINE(__LC_LAST_BREAK, offsetof(struct _lowcore, breaking_event_addr)); + DEFINE(__LC_VDSO_PER_CPU, offsetof(struct _lowcore, vdso_per_cpu_data)); + DEFINE(__LC_GMAP, offsetof(struct _lowcore, gmap)); + DEFINE(__GMAP_ASCE, offsetof(struct gmap, asce)); +#endif /* CONFIG_32BIT */ + return 0; +} diff --git a/arch/s390/kernel/audit.c b/arch/s390/kernel/audit.c new file mode 100644 index 00000000..f4932c22 --- /dev/null +++ b/arch/s390/kernel/audit.c @@ -0,0 +1,78 @@ +#include <linux/init.h> +#include <linux/types.h> +#include <linux/audit.h> +#include <asm/unistd.h> +#include "audit.h" + +static unsigned dir_class[] = { +#include <asm-generic/audit_dir_write.h> +~0U +}; + +static unsigned read_class[] = { +#include <asm-generic/audit_read.h> +~0U +}; + +static unsigned write_class[] = { +#include <asm-generic/audit_write.h> +~0U +}; + +static unsigned chattr_class[] = { +#include <asm-generic/audit_change_attr.h> +~0U +}; + +static unsigned signal_class[] = { +#include <asm-generic/audit_signal.h> +~0U +}; + +int audit_classify_arch(int arch) +{ +#ifdef CONFIG_COMPAT + if (arch == AUDIT_ARCH_S390) + return 1; +#endif + return 0; +} + +int audit_classify_syscall(int abi, unsigned syscall) +{ +#ifdef CONFIG_COMPAT + if (abi == AUDIT_ARCH_S390) + return s390_classify_syscall(syscall); +#endif + switch(syscall) { + case __NR_open: + return 2; + case __NR_openat: + return 3; + case __NR_socketcall: + return 4; + case __NR_execve: + return 5; + default: + return 0; + } +} + +static int __init audit_classes_init(void) +{ +#ifdef CONFIG_COMPAT + audit_register_class(AUDIT_CLASS_WRITE_32, s390_write_class); + audit_register_class(AUDIT_CLASS_READ_32, s390_read_class); + audit_register_class(AUDIT_CLASS_DIR_WRITE_32, s390_dir_class); + audit_register_class(AUDIT_CLASS_CHATTR_32, s390_chattr_class); + audit_register_class(AUDIT_CLASS_SIGNAL_32, s390_signal_class); +#endif + audit_register_class(AUDIT_CLASS_WRITE, write_class); + audit_register_class(AUDIT_CLASS_READ, read_class); + audit_register_class(AUDIT_CLASS_DIR_WRITE, dir_class); + audit_register_class(AUDIT_CLASS_CHATTR, chattr_class); + audit_register_class(AUDIT_CLASS_SIGNAL, signal_class); + return 0; +} + +__initcall(audit_classes_init); diff --git a/arch/s390/kernel/audit.h b/arch/s390/kernel/audit.h new file mode 100644 index 00000000..12b56f4b --- /dev/null +++ b/arch/s390/kernel/audit.h @@ -0,0 +1,15 @@ +#ifndef __ARCH_S390_KERNEL_AUDIT_H +#define __ARCH_S390_KERNEL_AUDIT_H + +#include <linux/types.h> + +#ifdef CONFIG_COMPAT +extern int s390_classify_syscall(unsigned); +extern __u32 s390_dir_class[]; +extern __u32 s390_write_class[]; +extern __u32 s390_read_class[]; +extern __u32 s390_chattr_class[]; +extern __u32 s390_signal_class[]; +#endif /* CONFIG_COMPAT */ + +#endif /* __ARCH_S390_KERNEL_AUDIT_H */ diff --git a/arch/s390/kernel/base.S b/arch/s390/kernel/base.S new file mode 100644 index 00000000..3aa4d00a --- /dev/null +++ b/arch/s390/kernel/base.S @@ -0,0 +1,193 @@ +/* + * arch/s390/kernel/base.S + * + * Copyright IBM Corp. 2006,2007 + * Author(s): Heiko Carstens <heiko.carstens@de.ibm.com> + * Michael Holzheu <holzheu@de.ibm.com> + */ + +#include <linux/linkage.h> +#include <asm/asm-offsets.h> +#include <asm/ptrace.h> + +#ifdef CONFIG_64BIT + +ENTRY(s390_base_mcck_handler) + basr %r13,0 +0: lg %r15,__LC_PANIC_STACK # load panic stack + aghi %r15,-STACK_FRAME_OVERHEAD + larl %r1,s390_base_mcck_handler_fn + lg %r1,0(%r1) + ltgr %r1,%r1 + jz 1f + basr %r14,%r1 +1: la %r1,4095 + lmg %r0,%r15,__LC_GPREGS_SAVE_AREA-4095(%r1) + lpswe __LC_MCK_OLD_PSW + + .section .bss + .align 8 + .globl s390_base_mcck_handler_fn +s390_base_mcck_handler_fn: + .quad 0 + .previous + +ENTRY(s390_base_ext_handler) + stmg %r0,%r15,__LC_SAVE_AREA_ASYNC + basr %r13,0 +0: aghi %r15,-STACK_FRAME_OVERHEAD + larl %r1,s390_base_ext_handler_fn + lg %r1,0(%r1) + ltgr %r1,%r1 + jz 1f + basr %r14,%r1 +1: lmg %r0,%r15,__LC_SAVE_AREA_ASYNC + ni __LC_EXT_OLD_PSW+1,0xfd # clear wait state bit + lpswe __LC_EXT_OLD_PSW + + .section .bss + .align 8 + .globl s390_base_ext_handler_fn +s390_base_ext_handler_fn: + .quad 0 + .previous + +ENTRY(s390_base_pgm_handler) + stmg %r0,%r15,__LC_SAVE_AREA_SYNC + basr %r13,0 +0: aghi %r15,-STACK_FRAME_OVERHEAD + larl %r1,s390_base_pgm_handler_fn + lg %r1,0(%r1) + ltgr %r1,%r1 + jz 1f + basr %r14,%r1 + lmg %r0,%r15,__LC_SAVE_AREA_SYNC + lpswe __LC_PGM_OLD_PSW +1: lpswe disabled_wait_psw-0b(%r13) + + .align 8 +disabled_wait_psw: + .quad 0x0002000180000000,0x0000000000000000 + s390_base_pgm_handler + + .section .bss + .align 8 + .globl s390_base_pgm_handler_fn +s390_base_pgm_handler_fn: + .quad 0 + .previous + +# +# Calls diag 308 subcode 1 and continues execution +# +# The following conditions must be ensured before calling this function: +# * Prefix register = 0 +# * Lowcore protection is disabled +# +ENTRY(diag308_reset) + larl %r4,.Lctlregs # Save control registers + stctg %c0,%c15,0(%r4) + larl %r4,.Lfpctl # Floating point control register + stfpc 0(%r4) + larl %r4,.Lrestart_psw # Setup restart PSW at absolute 0 + lghi %r3,0 + lg %r4,0(%r4) # Save PSW + sturg %r4,%r3 # Use sturg, because of large pages + lghi %r1,1 + diag %r1,%r1,0x308 +.Lrestart_part2: + lhi %r0,0 # Load r0 with zero + lhi %r1,2 # Use mode 2 = ESAME (dump) + sigp %r1,%r0,0x12 # Switch to ESAME mode + sam64 # Switch to 64 bit addressing mode + larl %r4,.Lctlregs # Restore control registers + lctlg %c0,%c15,0(%r4) + larl %r4,.Lfpctl # Restore floating point ctl register + lfpc 0(%r4) + br %r14 +.align 16 +.Lrestart_psw: + .long 0x00080000,0x80000000 + .Lrestart_part2 + + .section .bss +.align 8 +.Lctlregs: + .rept 16 + .quad 0 + .endr +.Lfpctl: + .long 0 + .previous + +#else /* CONFIG_64BIT */ + +ENTRY(s390_base_mcck_handler) + basr %r13,0 +0: l %r15,__LC_PANIC_STACK # load panic stack + ahi %r15,-STACK_FRAME_OVERHEAD + l %r1,2f-0b(%r13) + l %r1,0(%r1) + ltr %r1,%r1 + jz 1f + basr %r14,%r1 +1: lm %r0,%r15,__LC_GPREGS_SAVE_AREA + lpsw __LC_MCK_OLD_PSW + +2: .long s390_base_mcck_handler_fn + + .section .bss + .align 4 + .globl s390_base_mcck_handler_fn +s390_base_mcck_handler_fn: + .long 0 + .previous + +ENTRY(s390_base_ext_handler) + stm %r0,%r15,__LC_SAVE_AREA_ASYNC + basr %r13,0 +0: ahi %r15,-STACK_FRAME_OVERHEAD + l %r1,2f-0b(%r13) + l %r1,0(%r1) + ltr %r1,%r1 + jz 1f + basr %r14,%r1 +1: lm %r0,%r15,__LC_SAVE_AREA_ASYNC + ni __LC_EXT_OLD_PSW+1,0xfd # clear wait state bit + lpsw __LC_EXT_OLD_PSW + +2: .long s390_base_ext_handler_fn + + .section .bss + .align 4 + .globl s390_base_ext_handler_fn +s390_base_ext_handler_fn: + .long 0 + .previous + +ENTRY(s390_base_pgm_handler) + stm %r0,%r15,__LC_SAVE_AREA_SYNC + basr %r13,0 +0: ahi %r15,-STACK_FRAME_OVERHEAD + l %r1,2f-0b(%r13) + l %r1,0(%r1) + ltr %r1,%r1 + jz 1f + basr %r14,%r1 + lm %r0,%r15,__LC_SAVE_AREA_SYNC + lpsw __LC_PGM_OLD_PSW + +1: lpsw disabled_wait_psw-0b(%r13) + +2: .long s390_base_pgm_handler_fn + +disabled_wait_psw: + .align 8 + .long 0x000a0000,0x00000000 + s390_base_pgm_handler + + .section .bss + .align 4 + .globl s390_base_pgm_handler_fn +s390_base_pgm_handler_fn: + .long 0 + .previous + +#endif /* CONFIG_64BIT */ diff --git a/arch/s390/kernel/bitmap.c b/arch/s390/kernel/bitmap.c new file mode 100644 index 00000000..3ae4757b --- /dev/null +++ b/arch/s390/kernel/bitmap.c @@ -0,0 +1,54 @@ +/* + * Bitmaps for set_bit, clear_bit, test_and_set_bit, ... + * See include/asm/{bitops.h|posix_types.h} for details + * + * Copyright IBM Corp. 1999,2009 + * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>, + */ + +#include <linux/bitops.h> +#include <linux/module.h> + +const char _oi_bitmap[] = { 0x01, 0x02, 0x04, 0x08, 0x10, 0x20, 0x40, 0x80 }; +EXPORT_SYMBOL(_oi_bitmap); + +const char _ni_bitmap[] = { 0xfe, 0xfd, 0xfb, 0xf7, 0xef, 0xdf, 0xbf, 0x7f }; +EXPORT_SYMBOL(_ni_bitmap); + +const char _zb_findmap[] = { + 0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,4, + 0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,5, + 0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,4, + 0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,6, + 0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,4, + 0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,5, + 0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,4, + 0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,7, + 0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,4, + 0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,5, + 0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,4, + 0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,6, + 0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,4, + 0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,5, + 0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,4, + 0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,8 }; +EXPORT_SYMBOL(_zb_findmap); + +const char _sb_findmap[] = { + 8,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0, + 4,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0, + 5,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0, + 4,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0, + 6,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0, + 4,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0, + 5,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0, + 4,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0, + 7,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0, + 4,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0, + 5,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0, + 4,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0, + 6,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0, + 4,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0, + 5,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0, + 4,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0 }; +EXPORT_SYMBOL(_sb_findmap); diff --git a/arch/s390/kernel/compat_audit.c b/arch/s390/kernel/compat_audit.c new file mode 100644 index 00000000..d6487bf8 --- /dev/null +++ b/arch/s390/kernel/compat_audit.c @@ -0,0 +1,44 @@ +#undef __s390x__ +#include <asm/unistd.h> +#include "audit.h" + +unsigned s390_dir_class[] = { +#include <asm-generic/audit_dir_write.h> +~0U +}; + +unsigned s390_chattr_class[] = { +#include <asm-generic/audit_change_attr.h> +~0U +}; + +unsigned s390_write_class[] = { +#include <asm-generic/audit_write.h> +~0U +}; + +unsigned s390_read_class[] = { +#include <asm-generic/audit_read.h> +~0U +}; + +unsigned s390_signal_class[] = { +#include <asm-generic/audit_signal.h> +~0U +}; + +int s390_classify_syscall(unsigned syscall) +{ + switch(syscall) { + case __NR_open: + return 2; + case __NR_openat: + return 3; + case __NR_socketcall: + return 4; + case __NR_execve: + return 5; + default: + return 1; + } +} diff --git a/arch/s390/kernel/compat_exec_domain.c b/arch/s390/kernel/compat_exec_domain.c new file mode 100644 index 00000000..914d4944 --- /dev/null +++ b/arch/s390/kernel/compat_exec_domain.c @@ -0,0 +1,29 @@ +/* + * Support for 32-bit Linux for S390 personality. + * + * Copyright (C) 2000 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Author(s): Gerhard Tonn (ton@de.ibm.com) + * + * + */ + +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/personality.h> +#include <linux/sched.h> + +static struct exec_domain s390_exec_domain; + +static int __init s390_init (void) +{ + s390_exec_domain.name = "Linux/s390"; + s390_exec_domain.handler = NULL; + s390_exec_domain.pers_low = PER_LINUX32; + s390_exec_domain.pers_high = PER_LINUX32; + s390_exec_domain.signal_map = default_exec_domain.signal_map; + s390_exec_domain.signal_invmap = default_exec_domain.signal_invmap; + register_exec_domain(&s390_exec_domain); + return 0; +} + +__initcall(s390_init); diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c new file mode 100644 index 00000000..ab64bdba --- /dev/null +++ b/arch/s390/kernel/compat_linux.c @@ -0,0 +1,681 @@ +/* + * arch/s390x/kernel/linux32.c + * + * S390 version + * Copyright (C) 2000 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com), + * Gerhard Tonn (ton@de.ibm.com) + * Thomas Spatzier (tspat@de.ibm.com) + * + * Conversion between 31bit and 64bit native syscalls. + * + * Heavily inspired by the 32-bit Sparc compat code which is + * Copyright (C) 1997,1998 Jakub Jelinek (jj@sunsite.mff.cuni.cz) + * Copyright (C) 1997 David S. Miller (davem@caip.rutgers.edu) + * + */ + + +#include <linux/kernel.h> +#include <linux/sched.h> +#include <linux/fs.h> +#include <linux/mm.h> +#include <linux/file.h> +#include <linux/signal.h> +#include <linux/resource.h> +#include <linux/times.h> +#include <linux/smp.h> +#include <linux/sem.h> +#include <linux/msg.h> +#include <linux/shm.h> +#include <linux/uio.h> +#include <linux/quota.h> +#include <linux/module.h> +#include <linux/poll.h> +#include <linux/personality.h> +#include <linux/stat.h> +#include <linux/filter.h> +#include <linux/highmem.h> +#include <linux/highuid.h> +#include <linux/mman.h> +#include <linux/ipv6.h> +#include <linux/in.h> +#include <linux/icmpv6.h> +#include <linux/syscalls.h> +#include <linux/sysctl.h> +#include <linux/binfmts.h> +#include <linux/capability.h> +#include <linux/compat.h> +#include <linux/vfs.h> +#include <linux/ptrace.h> +#include <linux/fadvise.h> +#include <linux/ipc.h> +#include <linux/slab.h> + +#include <asm/types.h> +#include <asm/uaccess.h> + +#include <net/scm.h> +#include <net/sock.h> + +#include "compat_linux.h" + +u32 psw32_user_bits = PSW32_MASK_DAT | PSW32_MASK_IO | PSW32_MASK_EXT | + PSW32_DEFAULT_KEY | PSW32_MASK_BASE | PSW32_MASK_MCHECK | + PSW32_MASK_PSTATE | PSW32_ASC_HOME; + +/* For this source file, we want overflow handling. */ + +#undef high2lowuid +#undef high2lowgid +#undef low2highuid +#undef low2highgid +#undef SET_UID16 +#undef SET_GID16 +#undef NEW_TO_OLD_UID +#undef NEW_TO_OLD_GID +#undef SET_OLDSTAT_UID +#undef SET_OLDSTAT_GID +#undef SET_STAT_UID +#undef SET_STAT_GID + +#define high2lowuid(uid) ((uid) > 65535) ? (u16)overflowuid : (u16)(uid) +#define high2lowgid(gid) ((gid) > 65535) ? (u16)overflowgid : (u16)(gid) +#define low2highuid(uid) ((uid) == (u16)-1) ? (uid_t)-1 : (uid_t)(uid) +#define low2highgid(gid) ((gid) == (u16)-1) ? (gid_t)-1 : (gid_t)(gid) +#define SET_UID16(var, uid) var = high2lowuid(uid) +#define SET_GID16(var, gid) var = high2lowgid(gid) +#define NEW_TO_OLD_UID(uid) high2lowuid(uid) +#define NEW_TO_OLD_GID(gid) high2lowgid(gid) +#define SET_OLDSTAT_UID(stat, uid) (stat).st_uid = high2lowuid(uid) +#define SET_OLDSTAT_GID(stat, gid) (stat).st_gid = high2lowgid(gid) +#define SET_STAT_UID(stat, uid) (stat).st_uid = high2lowuid(uid) +#define SET_STAT_GID(stat, gid) (stat).st_gid = high2lowgid(gid) + +asmlinkage long sys32_chown16(const char __user * filename, u16 user, u16 group) +{ + return sys_chown(filename, low2highuid(user), low2highgid(group)); +} + +asmlinkage long sys32_lchown16(const char __user * filename, u16 user, u16 group) +{ + return sys_lchown(filename, low2highuid(user), low2highgid(group)); +} + +asmlinkage long sys32_fchown16(unsigned int fd, u16 user, u16 group) +{ + return sys_fchown(fd, low2highuid(user), low2highgid(group)); +} + +asmlinkage long sys32_setregid16(u16 rgid, u16 egid) +{ + return sys_setregid(low2highgid(rgid), low2highgid(egid)); +} + +asmlinkage long sys32_setgid16(u16 gid) +{ + return sys_setgid((gid_t)gid); +} + +asmlinkage long sys32_setreuid16(u16 ruid, u16 euid) +{ + return sys_setreuid(low2highuid(ruid), low2highuid(euid)); +} + +asmlinkage long sys32_setuid16(u16 uid) +{ + return sys_setuid((uid_t)uid); +} + +asmlinkage long sys32_setresuid16(u16 ruid, u16 euid, u16 suid) +{ + return sys_setresuid(low2highuid(ruid), low2highuid(euid), + low2highuid(suid)); +} + +asmlinkage long sys32_getresuid16(u16 __user *ruid, u16 __user *euid, u16 __user *suid) +{ + int retval; + + if (!(retval = put_user(high2lowuid(current->cred->uid), ruid)) && + !(retval = put_user(high2lowuid(current->cred->euid), euid))) + retval = put_user(high2lowuid(current->cred->suid), suid); + + return retval; +} + +asmlinkage long sys32_setresgid16(u16 rgid, u16 egid, u16 sgid) +{ + return sys_setresgid(low2highgid(rgid), low2highgid(egid), + low2highgid(sgid)); +} + +asmlinkage long sys32_getresgid16(u16 __user *rgid, u16 __user *egid, u16 __user *sgid) +{ + int retval; + + if (!(retval = put_user(high2lowgid(current->cred->gid), rgid)) && + !(retval = put_user(high2lowgid(current->cred->egid), egid))) + retval = put_user(high2lowgid(current->cred->sgid), sgid); + + return retval; +} + +asmlinkage long sys32_setfsuid16(u16 uid) +{ + return sys_setfsuid((uid_t)uid); +} + +asmlinkage long sys32_setfsgid16(u16 gid) +{ + return sys_setfsgid((gid_t)gid); +} + +static int groups16_to_user(u16 __user *grouplist, struct group_info *group_info) +{ + int i; + u16 group; + + for (i = 0; i < group_info->ngroups; i++) { + group = (u16)GROUP_AT(group_info, i); + if (put_user(group, grouplist+i)) + return -EFAULT; + } + + return 0; +} + +static int groups16_from_user(struct group_info *group_info, u16 __user *grouplist) +{ + int i; + u16 group; + + for (i = 0; i < group_info->ngroups; i++) { + if (get_user(group, grouplist+i)) + return -EFAULT; + GROUP_AT(group_info, i) = (gid_t)group; + } + + return 0; +} + +asmlinkage long sys32_getgroups16(int gidsetsize, u16 __user *grouplist) +{ + int i; + + if (gidsetsize < 0) + return -EINVAL; + + get_group_info(current->cred->group_info); + i = current->cred->group_info->ngroups; + if (gidsetsize) { + if (i > gidsetsize) { + i = -EINVAL; + goto out; + } + if (groups16_to_user(grouplist, current->cred->group_info)) { + i = -EFAULT; + goto out; + } + } +out: + put_group_info(current->cred->group_info); + return i; +} + +asmlinkage long sys32_setgroups16(int gidsetsize, u16 __user *grouplist) +{ + struct group_info *group_info; + int retval; + + if (!capable(CAP_SETGID)) + return -EPERM; + if ((unsigned)gidsetsize > NGROUPS_MAX) + return -EINVAL; + + group_info = groups_alloc(gidsetsize); + if (!group_info) + return -ENOMEM; + retval = groups16_from_user(group_info, grouplist); + if (retval) { + put_group_info(group_info); + return retval; + } + + retval = set_current_groups(group_info); + put_group_info(group_info); + + return retval; +} + +asmlinkage long sys32_getuid16(void) +{ + return high2lowuid(current->cred->uid); +} + +asmlinkage long sys32_geteuid16(void) +{ + return high2lowuid(current->cred->euid); +} + +asmlinkage long sys32_getgid16(void) +{ + return high2lowgid(current->cred->gid); +} + +asmlinkage long sys32_getegid16(void) +{ + return high2lowgid(current->cred->egid); +} + +/* + * sys32_ipc() is the de-multiplexer for the SysV IPC calls in 32bit emulation. + * + * This is really horribly ugly. + */ +#ifdef CONFIG_SYSVIPC +asmlinkage long sys32_ipc(u32 call, int first, int second, int third, u32 ptr) +{ + if (call >> 16) /* hack for backward compatibility */ + return -EINVAL; + switch (call) { + case SEMTIMEDOP: + return compat_sys_semtimedop(first, compat_ptr(ptr), + second, compat_ptr(third)); + case SEMOP: + /* struct sembuf is the same on 32 and 64bit :)) */ + return sys_semtimedop(first, compat_ptr(ptr), + second, NULL); + case SEMGET: + return sys_semget(first, second, third); + case SEMCTL: + return compat_sys_semctl(first, second, third, + compat_ptr(ptr)); + case MSGSND: + return compat_sys_msgsnd(first, second, third, + compat_ptr(ptr)); + case MSGRCV: + return compat_sys_msgrcv(first, second, 0, third, + 0, compat_ptr(ptr)); + case MSGGET: + return sys_msgget((key_t) first, second); + case MSGCTL: + return compat_sys_msgctl(first, second, compat_ptr(ptr)); + case SHMAT: + return compat_sys_shmat(first, second, third, + 0, compat_ptr(ptr)); + case SHMDT: + return sys_shmdt(compat_ptr(ptr)); + case SHMGET: + return sys_shmget(first, (unsigned)second, third); + case SHMCTL: + return compat_sys_shmctl(first, second, compat_ptr(ptr)); + } + + return -ENOSYS; +} +#endif + +asmlinkage long sys32_truncate64(const char __user * path, unsigned long high, unsigned long low) +{ + if ((int)high < 0) + return -EINVAL; + else + return sys_truncate(path, (high << 32) | low); +} + +asmlinkage long sys32_ftruncate64(unsigned int fd, unsigned long high, unsigned long low) +{ + if ((int)high < 0) + return -EINVAL; + else + return sys_ftruncate(fd, (high << 32) | low); +} + +asmlinkage long sys32_sched_rr_get_interval(compat_pid_t pid, + struct compat_timespec __user *interval) +{ + struct timespec t; + int ret; + mm_segment_t old_fs = get_fs (); + + set_fs (KERNEL_DS); + ret = sys_sched_rr_get_interval(pid, + (struct timespec __force __user *) &t); + set_fs (old_fs); + if (put_compat_timespec(&t, interval)) + return -EFAULT; + return ret; +} + +asmlinkage long sys32_rt_sigprocmask(int how, compat_sigset_t __user *set, + compat_sigset_t __user *oset, size_t sigsetsize) +{ + sigset_t s; + compat_sigset_t s32; + int ret; + mm_segment_t old_fs = get_fs(); + + if (set) { + if (copy_from_user (&s32, set, sizeof(compat_sigset_t))) + return -EFAULT; + s.sig[0] = s32.sig[0] | (((long)s32.sig[1]) << 32); + } + set_fs (KERNEL_DS); + ret = sys_rt_sigprocmask(how, + set ? (sigset_t __force __user *) &s : NULL, + oset ? (sigset_t __force __user *) &s : NULL, + sigsetsize); + set_fs (old_fs); + if (ret) return ret; + if (oset) { + s32.sig[1] = (s.sig[0] >> 32); + s32.sig[0] = s.sig[0]; + if (copy_to_user (oset, &s32, sizeof(compat_sigset_t))) + return -EFAULT; + } + return 0; +} + +asmlinkage long sys32_rt_sigpending(compat_sigset_t __user *set, + size_t sigsetsize) +{ + sigset_t s; + compat_sigset_t s32; + int ret; + mm_segment_t old_fs = get_fs(); + + set_fs (KERNEL_DS); + ret = sys_rt_sigpending((sigset_t __force __user *) &s, sigsetsize); + set_fs (old_fs); + if (!ret) { + s32.sig[1] = (s.sig[0] >> 32); + s32.sig[0] = s.sig[0]; + if (copy_to_user (set, &s32, sizeof(compat_sigset_t))) + return -EFAULT; + } + return ret; +} + +asmlinkage long +sys32_rt_sigqueueinfo(int pid, int sig, compat_siginfo_t __user *uinfo) +{ + siginfo_t info; + int ret; + mm_segment_t old_fs = get_fs(); + + if (copy_siginfo_from_user32(&info, uinfo)) + return -EFAULT; + set_fs (KERNEL_DS); + ret = sys_rt_sigqueueinfo(pid, sig, (siginfo_t __force __user *) &info); + set_fs (old_fs); + return ret; +} + +/* + * sys32_execve() executes a new program after the asm stub has set + * things up for us. This should basically do what I want it to. + */ +asmlinkage long sys32_execve(const char __user *name, compat_uptr_t __user *argv, + compat_uptr_t __user *envp) +{ + struct pt_regs *regs = task_pt_regs(current); + char *filename; + long rc; + + filename = getname(name); + rc = PTR_ERR(filename); + if (IS_ERR(filename)) + return rc; + rc = compat_do_execve(filename, argv, envp, regs); + if (rc) + goto out; + current->thread.fp_regs.fpc=0; + asm volatile("sfpc %0,0" : : "d" (0)); + rc = regs->gprs[2]; +out: + putname(filename); + return rc; +} + +asmlinkage long sys32_pread64(unsigned int fd, char __user *ubuf, + size_t count, u32 poshi, u32 poslo) +{ + if ((compat_ssize_t) count < 0) + return -EINVAL; + return sys_pread64(fd, ubuf, count, ((loff_t)AA(poshi) << 32) | AA(poslo)); +} + +asmlinkage long sys32_pwrite64(unsigned int fd, const char __user *ubuf, + size_t count, u32 poshi, u32 poslo) +{ + if ((compat_ssize_t) count < 0) + return -EINVAL; + return sys_pwrite64(fd, ubuf, count, ((loff_t)AA(poshi) << 32) | AA(poslo)); +} + +asmlinkage compat_ssize_t sys32_readahead(int fd, u32 offhi, u32 offlo, s32 count) +{ + return sys_readahead(fd, ((loff_t)AA(offhi) << 32) | AA(offlo), count); +} + +asmlinkage long sys32_sendfile(int out_fd, int in_fd, compat_off_t __user *offset, size_t count) +{ + mm_segment_t old_fs = get_fs(); + int ret; + off_t of; + + if (offset && get_user(of, offset)) + return -EFAULT; + + set_fs(KERNEL_DS); + ret = sys_sendfile(out_fd, in_fd, + offset ? (off_t __force __user *) &of : NULL, count); + set_fs(old_fs); + + if (offset && put_user(of, offset)) + return -EFAULT; + + return ret; +} + +asmlinkage long sys32_sendfile64(int out_fd, int in_fd, + compat_loff_t __user *offset, s32 count) +{ + mm_segment_t old_fs = get_fs(); + int ret; + loff_t lof; + + if (offset && get_user(lof, offset)) + return -EFAULT; + + set_fs(KERNEL_DS); + ret = sys_sendfile64(out_fd, in_fd, + offset ? (loff_t __force __user *) &lof : NULL, + count); + set_fs(old_fs); + + if (offset && put_user(lof, offset)) + return -EFAULT; + + return ret; +} + +struct stat64_emu31 { + unsigned long long st_dev; + unsigned int __pad1; +#define STAT64_HAS_BROKEN_ST_INO 1 + u32 __st_ino; + unsigned int st_mode; + unsigned int st_nlink; + u32 st_uid; + u32 st_gid; + unsigned long long st_rdev; + unsigned int __pad3; + long st_size; + u32 st_blksize; + unsigned char __pad4[4]; + u32 __pad5; /* future possible st_blocks high bits */ + u32 st_blocks; /* Number 512-byte blocks allocated. */ + u32 st_atime; + u32 __pad6; + u32 st_mtime; + u32 __pad7; + u32 st_ctime; + u32 __pad8; /* will be high 32 bits of ctime someday */ + unsigned long st_ino; +}; + +static int cp_stat64(struct stat64_emu31 __user *ubuf, struct kstat *stat) +{ + struct stat64_emu31 tmp; + + memset(&tmp, 0, sizeof(tmp)); + + tmp.st_dev = huge_encode_dev(stat->dev); + tmp.st_ino = stat->ino; + tmp.__st_ino = (u32)stat->ino; + tmp.st_mode = stat->mode; + tmp.st_nlink = (unsigned int)stat->nlink; + tmp.st_uid = stat->uid; + tmp.st_gid = stat->gid; + tmp.st_rdev = huge_encode_dev(stat->rdev); + tmp.st_size = stat->size; + tmp.st_blksize = (u32)stat->blksize; + tmp.st_blocks = (u32)stat->blocks; + tmp.st_atime = (u32)stat->atime.tv_sec; + tmp.st_mtime = (u32)stat->mtime.tv_sec; + tmp.st_ctime = (u32)stat->ctime.tv_sec; + + return copy_to_user(ubuf,&tmp,sizeof(tmp)) ? -EFAULT : 0; +} + +asmlinkage long sys32_stat64(const char __user * filename, struct stat64_emu31 __user * statbuf) +{ + struct kstat stat; + int ret = vfs_stat(filename, &stat); + if (!ret) + ret = cp_stat64(statbuf, &stat); + return ret; +} + +asmlinkage long sys32_lstat64(const char __user * filename, struct stat64_emu31 __user * statbuf) +{ + struct kstat stat; + int ret = vfs_lstat(filename, &stat); + if (!ret) + ret = cp_stat64(statbuf, &stat); + return ret; +} + +asmlinkage long sys32_fstat64(unsigned long fd, struct stat64_emu31 __user * statbuf) +{ + struct kstat stat; + int ret = vfs_fstat(fd, &stat); + if (!ret) + ret = cp_stat64(statbuf, &stat); + return ret; +} + +asmlinkage long sys32_fstatat64(unsigned int dfd, const char __user *filename, + struct stat64_emu31 __user* statbuf, int flag) +{ + struct kstat stat; + int error; + + error = vfs_fstatat(dfd, filename, &stat, flag); + if (error) + return error; + return cp_stat64(statbuf, &stat); +} + +/* + * Linux/i386 didn't use to be able to handle more than + * 4 system call parameters, so these system calls used a memory + * block for parameter passing.. + */ + +struct mmap_arg_struct_emu31 { + compat_ulong_t addr; + compat_ulong_t len; + compat_ulong_t prot; + compat_ulong_t flags; + compat_ulong_t fd; + compat_ulong_t offset; +}; + +asmlinkage unsigned long old32_mmap(struct mmap_arg_struct_emu31 __user *arg) +{ + struct mmap_arg_struct_emu31 a; + + if (copy_from_user(&a, arg, sizeof(a))) + return -EFAULT; + if (a.offset & ~PAGE_MASK) + return -EINVAL; + a.addr = (unsigned long) compat_ptr(a.addr); + return sys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd, + a.offset >> PAGE_SHIFT); +} + +asmlinkage long sys32_mmap2(struct mmap_arg_struct_emu31 __user *arg) +{ + struct mmap_arg_struct_emu31 a; + + if (copy_from_user(&a, arg, sizeof(a))) + return -EFAULT; + a.addr = (unsigned long) compat_ptr(a.addr); + return sys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd, a.offset); +} + +asmlinkage long sys32_read(unsigned int fd, char __user * buf, size_t count) +{ + if ((compat_ssize_t) count < 0) + return -EINVAL; + + return sys_read(fd, buf, count); +} + +asmlinkage long sys32_write(unsigned int fd, const char __user * buf, size_t count) +{ + if ((compat_ssize_t) count < 0) + return -EINVAL; + + return sys_write(fd, buf, count); +} + +/* + * 31 bit emulation wrapper functions for sys_fadvise64/fadvise64_64. + * These need to rewrite the advise values for POSIX_FADV_{DONTNEED,NOREUSE} + * because the 31 bit values differ from the 64 bit values. + */ + +asmlinkage long +sys32_fadvise64(int fd, loff_t offset, size_t len, int advise) +{ + if (advise == 4) + advise = POSIX_FADV_DONTNEED; + else if (advise == 5) + advise = POSIX_FADV_NOREUSE; + return sys_fadvise64(fd, offset, len, advise); +} + +struct fadvise64_64_args { + int fd; + long long offset; + long long len; + int advice; +}; + +asmlinkage long +sys32_fadvise64_64(struct fadvise64_64_args __user *args) +{ + struct fadvise64_64_args a; + + if ( copy_from_user(&a, args, sizeof(a)) ) + return -EFAULT; + if (a.advice == 4) + a.advice = POSIX_FADV_DONTNEED; + else if (a.advice == 5) + a.advice = POSIX_FADV_NOREUSE; + return sys_fadvise64_64(a.fd, a.offset, a.len, a.advice); +} diff --git a/arch/s390/kernel/compat_linux.h b/arch/s390/kernel/compat_linux.h new file mode 100644 index 00000000..9635d759 --- /dev/null +++ b/arch/s390/kernel/compat_linux.h @@ -0,0 +1,227 @@ +#ifndef _ASM_S390X_S390_H +#define _ASM_S390X_S390_H + +#include <linux/compat.h> +#include <linux/socket.h> +#include <linux/syscalls.h> + +/* Macro that masks the high order bit of an 32 bit pointer and converts it*/ +/* to a 64 bit pointer */ +#define A(__x) ((unsigned long)((__x) & 0x7FFFFFFFUL)) +#define AA(__x) \ + ((unsigned long)(__x)) + +/* Now 32bit compatibility types */ +struct ipc_kludge_32 { + __u32 msgp; /* pointer */ + __s32 msgtyp; +}; + +struct old_sigaction32 { + __u32 sa_handler; /* Really a pointer, but need to deal with 32 bits */ + compat_old_sigset_t sa_mask; /* A 32 bit mask */ + __u32 sa_flags; + __u32 sa_restorer; /* Another 32 bit pointer */ +}; + +typedef struct compat_siginfo { + int si_signo; + int si_errno; + int si_code; + + union { + int _pad[((128/sizeof(int)) - 3)]; + + /* kill() */ + struct { + pid_t _pid; /* sender's pid */ + uid_t _uid; /* sender's uid */ + } _kill; + + /* POSIX.1b timers */ + struct { + compat_timer_t _tid; /* timer id */ + int _overrun; /* overrun count */ + compat_sigval_t _sigval; /* same as below */ + int _sys_private; /* not to be passed to user */ + } _timer; + + /* POSIX.1b signals */ + struct { + pid_t _pid; /* sender's pid */ + uid_t _uid; /* sender's uid */ + compat_sigval_t _sigval; + } _rt; + + /* SIGCHLD */ + struct { + pid_t _pid; /* which child */ + uid_t _uid; /* sender's uid */ + int _status;/* exit code */ + compat_clock_t _utime; + compat_clock_t _stime; + } _sigchld; + + /* SIGILL, SIGFPE, SIGSEGV, SIGBUS */ + struct { + __u32 _addr; /* faulting insn/memory ref. - pointer */ + } _sigfault; + + /* SIGPOLL */ + struct { + int _band; /* POLL_IN, POLL_OUT, POLL_MSG */ + int _fd; + } _sigpoll; + } _sifields; +} compat_siginfo_t; + +/* + * How these fields are to be accessed. + */ +#define si_pid _sifields._kill._pid +#define si_uid _sifields._kill._uid +#define si_status _sifields._sigchld._status +#define si_utime _sifields._sigchld._utime +#define si_stime _sifields._sigchld._stime +#define si_value _sifields._rt._sigval +#define si_int _sifields._rt._sigval.sival_int +#define si_ptr _sifields._rt._sigval.sival_ptr +#define si_addr _sifields._sigfault._addr +#define si_band _sifields._sigpoll._band +#define si_fd _sifields._sigpoll._fd +#define si_tid _sifields._timer._tid +#define si_overrun _sifields._timer._overrun + +/* asm/sigcontext.h */ +typedef union +{ + __u64 d; + __u32 f; +} freg_t32; + +typedef struct +{ + unsigned int fpc; + freg_t32 fprs[__NUM_FPRS]; +} _s390_fp_regs32; + +typedef struct +{ + __u32 mask; + __u32 addr; +} _psw_t32 __attribute__ ((aligned(8))); + +typedef struct +{ + _psw_t32 psw; + __u32 gprs[__NUM_GPRS]; + __u32 acrs[__NUM_ACRS]; +} _s390_regs_common32; + +typedef struct +{ + _s390_regs_common32 regs; + _s390_fp_regs32 fpregs; +} _sigregs32; + +#define _SIGCONTEXT_NSIG32 64 +#define _SIGCONTEXT_NSIG_BPW32 32 +#define __SIGNAL_FRAMESIZE32 96 +#define _SIGMASK_COPY_SIZE32 (sizeof(u32)*2) + +struct sigcontext32 +{ + __u32 oldmask[_COMPAT_NSIG_WORDS]; + __u32 sregs; /* pointer */ +}; + +/* asm/signal.h */ +struct sigaction32 { + __u32 sa_handler; /* pointer */ + __u32 sa_flags; + __u32 sa_restorer; /* pointer */ + compat_sigset_t sa_mask; /* mask last for extensibility */ +}; + +typedef struct { + __u32 ss_sp; /* pointer */ + int ss_flags; + compat_size_t ss_size; +} stack_t32; + +/* asm/ucontext.h */ +struct ucontext32 { + __u32 uc_flags; + __u32 uc_link; /* pointer */ + stack_t32 uc_stack; + _sigregs32 uc_mcontext; + compat_sigset_t uc_sigmask; /* mask last for extensibility */ +}; + +struct stat64_emu31; +struct mmap_arg_struct_emu31; +struct fadvise64_64_args; +struct old_sigaction32; +struct old_sigaction32; + +long sys32_chown16(const char __user * filename, u16 user, u16 group); +long sys32_lchown16(const char __user * filename, u16 user, u16 group); +long sys32_fchown16(unsigned int fd, u16 user, u16 group); +long sys32_setregid16(u16 rgid, u16 egid); +long sys32_setgid16(u16 gid); +long sys32_setreuid16(u16 ruid, u16 euid); +long sys32_setuid16(u16 uid); +long sys32_setresuid16(u16 ruid, u16 euid, u16 suid); +long sys32_getresuid16(u16 __user *ruid, u16 __user *euid, u16 __user *suid); +long sys32_setresgid16(u16 rgid, u16 egid, u16 sgid); +long sys32_getresgid16(u16 __user *rgid, u16 __user *egid, u16 __user *sgid); +long sys32_setfsuid16(u16 uid); +long sys32_setfsgid16(u16 gid); +long sys32_getgroups16(int gidsetsize, u16 __user *grouplist); +long sys32_setgroups16(int gidsetsize, u16 __user *grouplist); +long sys32_getuid16(void); +long sys32_geteuid16(void); +long sys32_getgid16(void); +long sys32_getegid16(void); +long sys32_ipc(u32 call, int first, int second, int third, u32 ptr); +long sys32_truncate64(const char __user * path, unsigned long high, + unsigned long low); +long sys32_ftruncate64(unsigned int fd, unsigned long high, unsigned long low); +long sys32_sched_rr_get_interval(compat_pid_t pid, + struct compat_timespec __user *interval); +long sys32_rt_sigprocmask(int how, compat_sigset_t __user *set, + compat_sigset_t __user *oset, size_t sigsetsize); +long sys32_rt_sigpending(compat_sigset_t __user *set, size_t sigsetsize); +long sys32_rt_sigqueueinfo(int pid, int sig, compat_siginfo_t __user *uinfo); +long sys32_execve(const char __user *name, compat_uptr_t __user *argv, + compat_uptr_t __user *envp); +long sys32_init_module(void __user *umod, unsigned long len, + const char __user *uargs); +long sys32_delete_module(const char __user *name_user, unsigned int flags); +long sys32_pread64(unsigned int fd, char __user *ubuf, size_t count, + u32 poshi, u32 poslo); +long sys32_pwrite64(unsigned int fd, const char __user *ubuf, + size_t count, u32 poshi, u32 poslo); +compat_ssize_t sys32_readahead(int fd, u32 offhi, u32 offlo, s32 count); +long sys32_sendfile(int out_fd, int in_fd, compat_off_t __user *offset, + size_t count); +long sys32_sendfile64(int out_fd, int in_fd, compat_loff_t __user *offset, + s32 count); +long sys32_stat64(const char __user * filename, struct stat64_emu31 __user * statbuf); +long sys32_lstat64(const char __user * filename, + struct stat64_emu31 __user * statbuf); +long sys32_fstat64(unsigned long fd, struct stat64_emu31 __user * statbuf); +long sys32_fstatat64(unsigned int dfd, const char __user *filename, + struct stat64_emu31 __user* statbuf, int flag); +unsigned long old32_mmap(struct mmap_arg_struct_emu31 __user *arg); +long sys32_mmap2(struct mmap_arg_struct_emu31 __user *arg); +long sys32_read(unsigned int fd, char __user * buf, size_t count); +long sys32_write(unsigned int fd, const char __user * buf, size_t count); +long sys32_fadvise64(int fd, loff_t offset, size_t len, int advise); +long sys32_fadvise64_64(struct fadvise64_64_args __user *args); +long sys32_sigaction(int sig, const struct old_sigaction32 __user *act, + struct old_sigaction32 __user *oact); +long sys32_rt_sigaction(int sig, const struct sigaction32 __user *act, + struct sigaction32 __user *oact, size_t sigsetsize); +long sys32_sigaltstack(const stack_t32 __user *uss, stack_t32 __user *uoss); +#endif /* _ASM_S390X_S390_H */ diff --git a/arch/s390/kernel/compat_ptrace.h b/arch/s390/kernel/compat_ptrace.h new file mode 100644 index 00000000..12b82383 --- /dev/null +++ b/arch/s390/kernel/compat_ptrace.h @@ -0,0 +1,63 @@ +#ifndef _PTRACE32_H +#define _PTRACE32_H + +#include <asm/ptrace.h> /* needed for NUM_CR_WORDS */ +#include "compat_linux.h" /* needed for psw_compat_t */ + +struct compat_per_struct_kernel { + __u32 cr9; /* PER control bits */ + __u32 cr10; /* PER starting address */ + __u32 cr11; /* PER ending address */ + __u32 bits; /* Obsolete software bits */ + __u32 starting_addr; /* User specified start address */ + __u32 ending_addr; /* User specified end address */ + __u16 perc_atmid; /* PER trap ATMID */ + __u32 address; /* PER trap instruction address */ + __u8 access_id; /* PER trap access identification */ +}; + +struct compat_user_regs_struct +{ + psw_compat_t psw; + u32 gprs[NUM_GPRS]; + u32 acrs[NUM_ACRS]; + u32 orig_gpr2; + /* nb: there's a 4-byte hole here */ + s390_fp_regs fp_regs; + /* + * These per registers are in here so that gdb can modify them + * itself as there is no "official" ptrace interface for hardware + * watchpoints. This is the way intel does it. + */ + struct compat_per_struct_kernel per_info; + u32 ieee_instruction_pointer; /* obsolete, always 0 */ +}; + +struct compat_user { + /* We start with the registers, to mimic the way that "memory" + is returned from the ptrace(3,...) function. */ + struct compat_user_regs_struct regs; + /* The rest of this junk is to help gdb figure out what goes where */ + u32 u_tsize; /* Text segment size (pages). */ + u32 u_dsize; /* Data segment size (pages). */ + u32 u_ssize; /* Stack segment size (pages). */ + u32 start_code; /* Starting virtual address of text. */ + u32 start_stack; /* Starting virtual address of stack area. + This is actually the bottom of the stack, + the top of the stack is always found in the + esp register. */ + s32 signal; /* Signal that caused the core dump. */ + u32 u_ar0; /* Used by gdb to help find the values for */ + /* the registers. */ + u32 magic; /* To uniquely identify a core file */ + char u_comm[32]; /* User command that was responsible */ +}; + +typedef struct +{ + __u32 len; + __u32 kernel_addr; + __u32 process_addr; +} compat_ptrace_area; + +#endif /* _PTRACE32_H */ diff --git a/arch/s390/kernel/compat_signal.c b/arch/s390/kernel/compat_signal.c new file mode 100644 index 00000000..28040fd5 --- /dev/null +++ b/arch/s390/kernel/compat_signal.c @@ -0,0 +1,597 @@ +/* + * arch/s390/kernel/compat_signal.c + * + * Copyright (C) IBM Corp. 2000,2006 + * Author(s): Denis Joseph Barrow (djbarrow@de.ibm.com,barrow_dj@yahoo.com) + * Gerhard Tonn (ton@de.ibm.com) + * + * Copyright (C) 1991, 1992 Linus Torvalds + * + * 1997-11-28 Modified for POSIX.1b signals by Richard Henderson + */ + +#include <linux/compat.h> +#include <linux/sched.h> +#include <linux/mm.h> +#include <linux/smp.h> +#include <linux/kernel.h> +#include <linux/signal.h> +#include <linux/errno.h> +#include <linux/wait.h> +#include <linux/ptrace.h> +#include <linux/unistd.h> +#include <linux/stddef.h> +#include <linux/tty.h> +#include <linux/personality.h> +#include <linux/binfmts.h> +#include <asm/ucontext.h> +#include <asm/uaccess.h> +#include <asm/lowcore.h> +#include <asm/switch_to.h> +#include "compat_linux.h" +#include "compat_ptrace.h" +#include "entry.h" + +#define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP))) + +typedef struct +{ + __u8 callee_used_stack[__SIGNAL_FRAMESIZE32]; + struct sigcontext32 sc; + _sigregs32 sregs; + int signo; + __u32 gprs_high[NUM_GPRS]; + __u8 retcode[S390_SYSCALL_SIZE]; +} sigframe32; + +typedef struct +{ + __u8 callee_used_stack[__SIGNAL_FRAMESIZE32]; + __u8 retcode[S390_SYSCALL_SIZE]; + compat_siginfo_t info; + struct ucontext32 uc; + __u32 gprs_high[NUM_GPRS]; +} rt_sigframe32; + +int copy_siginfo_to_user32(compat_siginfo_t __user *to, siginfo_t *from) +{ + int err; + + if (!access_ok (VERIFY_WRITE, to, sizeof(compat_siginfo_t))) + return -EFAULT; + + /* If you change siginfo_t structure, please be sure + this code is fixed accordingly. + It should never copy any pad contained in the structure + to avoid security leaks, but must copy the generic + 3 ints plus the relevant union member. + This routine must convert siginfo from 64bit to 32bit as well + at the same time. */ + err = __put_user(from->si_signo, &to->si_signo); + err |= __put_user(from->si_errno, &to->si_errno); + err |= __put_user((short)from->si_code, &to->si_code); + if (from->si_code < 0) + err |= __copy_to_user(&to->_sifields._pad, &from->_sifields._pad, SI_PAD_SIZE); + else { + switch (from->si_code >> 16) { + case __SI_RT >> 16: /* This is not generated by the kernel as of now. */ + case __SI_MESGQ >> 16: + err |= __put_user(from->si_int, &to->si_int); + /* fallthrough */ + case __SI_KILL >> 16: + err |= __put_user(from->si_pid, &to->si_pid); + err |= __put_user(from->si_uid, &to->si_uid); + break; + case __SI_CHLD >> 16: + err |= __put_user(from->si_pid, &to->si_pid); + err |= __put_user(from->si_uid, &to->si_uid); + err |= __put_user(from->si_utime, &to->si_utime); + err |= __put_user(from->si_stime, &to->si_stime); + err |= __put_user(from->si_status, &to->si_status); + break; + case __SI_FAULT >> 16: + err |= __put_user((unsigned long) from->si_addr, + &to->si_addr); + break; + case __SI_POLL >> 16: + err |= __put_user(from->si_band, &to->si_band); + err |= __put_user(from->si_fd, &to->si_fd); + break; + case __SI_TIMER >> 16: + err |= __put_user(from->si_tid, &to->si_tid); + err |= __put_user(from->si_overrun, &to->si_overrun); + err |= __put_user(from->si_int, &to->si_int); + break; + default: + break; + } + } + return err; +} + +int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from) +{ + int err; + u32 tmp; + + if (!access_ok (VERIFY_READ, from, sizeof(compat_siginfo_t))) + return -EFAULT; + + err = __get_user(to->si_signo, &from->si_signo); + err |= __get_user(to->si_errno, &from->si_errno); + err |= __get_user(to->si_code, &from->si_code); + + if (to->si_code < 0) + err |= __copy_from_user(&to->_sifields._pad, &from->_sifields._pad, SI_PAD_SIZE); + else { + switch (to->si_code >> 16) { + case __SI_RT >> 16: /* This is not generated by the kernel as of now. */ + case __SI_MESGQ >> 16: + err |= __get_user(to->si_int, &from->si_int); + /* fallthrough */ + case __SI_KILL >> 16: + err |= __get_user(to->si_pid, &from->si_pid); + err |= __get_user(to->si_uid, &from->si_uid); + break; + case __SI_CHLD >> 16: + err |= __get_user(to->si_pid, &from->si_pid); + err |= __get_user(to->si_uid, &from->si_uid); + err |= __get_user(to->si_utime, &from->si_utime); + err |= __get_user(to->si_stime, &from->si_stime); + err |= __get_user(to->si_status, &from->si_status); + break; + case __SI_FAULT >> 16: + err |= __get_user(tmp, &from->si_addr); + to->si_addr = (void __force __user *) + (u64) (tmp & PSW32_ADDR_INSN); + break; + case __SI_POLL >> 16: + err |= __get_user(to->si_band, &from->si_band); + err |= __get_user(to->si_fd, &from->si_fd); + break; + case __SI_TIMER >> 16: + err |= __get_user(to->si_tid, &from->si_tid); + err |= __get_user(to->si_overrun, &from->si_overrun); + err |= __get_user(to->si_int, &from->si_int); + break; + default: + break; + } + } + return err; +} + +asmlinkage long +sys32_sigaction(int sig, const struct old_sigaction32 __user *act, + struct old_sigaction32 __user *oact) +{ + struct k_sigaction new_ka, old_ka; + unsigned long sa_handler, sa_restorer; + int ret; + + if (act) { + compat_old_sigset_t mask; + if (!access_ok(VERIFY_READ, act, sizeof(*act)) || + __get_user(sa_handler, &act->sa_handler) || + __get_user(sa_restorer, &act->sa_restorer) || + __get_user(new_ka.sa.sa_flags, &act->sa_flags) || + __get_user(mask, &act->sa_mask)) + return -EFAULT; + new_ka.sa.sa_handler = (__sighandler_t) sa_handler; + new_ka.sa.sa_restorer = (void (*)(void)) sa_restorer; + siginitset(&new_ka.sa.sa_mask, mask); + } + + ret = do_sigaction(sig, act ? &new_ka : NULL, oact ? &old_ka : NULL); + + if (!ret && oact) { + sa_handler = (unsigned long) old_ka.sa.sa_handler; + sa_restorer = (unsigned long) old_ka.sa.sa_restorer; + if (!access_ok(VERIFY_WRITE, oact, sizeof(*oact)) || + __put_user(sa_handler, &oact->sa_handler) || + __put_user(sa_restorer, &oact->sa_restorer) || + __put_user(old_ka.sa.sa_flags, &oact->sa_flags) || + __put_user(old_ka.sa.sa_mask.sig[0], &oact->sa_mask)) + return -EFAULT; + } + + return ret; +} + +asmlinkage long +sys32_rt_sigaction(int sig, const struct sigaction32 __user *act, + struct sigaction32 __user *oact, size_t sigsetsize) +{ + struct k_sigaction new_ka, old_ka; + unsigned long sa_handler; + int ret; + compat_sigset_t set32; + + /* XXX: Don't preclude handling different sized sigset_t's. */ + if (sigsetsize != sizeof(compat_sigset_t)) + return -EINVAL; + + if (act) { + ret = get_user(sa_handler, &act->sa_handler); + ret |= __copy_from_user(&set32, &act->sa_mask, + sizeof(compat_sigset_t)); + new_ka.sa.sa_mask.sig[0] = + set32.sig[0] | (((long)set32.sig[1]) << 32); + ret |= __get_user(new_ka.sa.sa_flags, &act->sa_flags); + + if (ret) + return -EFAULT; + new_ka.sa.sa_handler = (__sighandler_t) sa_handler; + } + + ret = do_sigaction(sig, act ? &new_ka : NULL, oact ? &old_ka : NULL); + + if (!ret && oact) { + set32.sig[1] = (old_ka.sa.sa_mask.sig[0] >> 32); + set32.sig[0] = old_ka.sa.sa_mask.sig[0]; + ret = put_user((unsigned long)old_ka.sa.sa_handler, &oact->sa_handler); + ret |= __copy_to_user(&oact->sa_mask, &set32, + sizeof(compat_sigset_t)); + ret |= __put_user(old_ka.sa.sa_flags, &oact->sa_flags); + } + + return ret; +} + +asmlinkage long +sys32_sigaltstack(const stack_t32 __user *uss, stack_t32 __user *uoss) +{ + struct pt_regs *regs = task_pt_regs(current); + stack_t kss, koss; + unsigned long ss_sp; + int ret, err = 0; + mm_segment_t old_fs = get_fs(); + + if (uss) { + if (!access_ok(VERIFY_READ, uss, sizeof(*uss))) + return -EFAULT; + err |= __get_user(ss_sp, &uss->ss_sp); + err |= __get_user(kss.ss_size, &uss->ss_size); + err |= __get_user(kss.ss_flags, &uss->ss_flags); + if (err) + return -EFAULT; + kss.ss_sp = (void __user *) ss_sp; + } + + set_fs (KERNEL_DS); + ret = do_sigaltstack((stack_t __force __user *) (uss ? &kss : NULL), + (stack_t __force __user *) (uoss ? &koss : NULL), + regs->gprs[15]); + set_fs (old_fs); + + if (!ret && uoss) { + if (!access_ok(VERIFY_WRITE, uoss, sizeof(*uoss))) + return -EFAULT; + ss_sp = (unsigned long) koss.ss_sp; + err |= __put_user(ss_sp, &uoss->ss_sp); + err |= __put_user(koss.ss_size, &uoss->ss_size); + err |= __put_user(koss.ss_flags, &uoss->ss_flags); + if (err) + return -EFAULT; + } + return ret; +} + +static int save_sigregs32(struct pt_regs *regs, _sigregs32 __user *sregs) +{ + _s390_regs_common32 regs32; + int err, i; + + regs32.psw.mask = psw32_user_bits | + ((__u32)(regs->psw.mask >> 32) & PSW32_MASK_USER); + regs32.psw.addr = (__u32) regs->psw.addr | + (__u32)(regs->psw.mask & PSW_MASK_BA); + for (i = 0; i < NUM_GPRS; i++) + regs32.gprs[i] = (__u32) regs->gprs[i]; + save_access_regs(current->thread.acrs); + memcpy(regs32.acrs, current->thread.acrs, sizeof(regs32.acrs)); + err = __copy_to_user(&sregs->regs, ®s32, sizeof(regs32)); + if (err) + return err; + save_fp_regs(¤t->thread.fp_regs); + /* s390_fp_regs and _s390_fp_regs32 are the same ! */ + return __copy_to_user(&sregs->fpregs, ¤t->thread.fp_regs, + sizeof(_s390_fp_regs32)); +} + +static int restore_sigregs32(struct pt_regs *regs,_sigregs32 __user *sregs) +{ + _s390_regs_common32 regs32; + int err, i; + + /* Alwys make any pending restarted system call return -EINTR */ + current_thread_info()->restart_block.fn = do_no_restart_syscall; + + err = __copy_from_user(®s32, &sregs->regs, sizeof(regs32)); + if (err) + return err; + regs->psw.mask = (regs->psw.mask & ~PSW_MASK_USER) | + (__u64)(regs32.psw.mask & PSW32_MASK_USER) << 32 | + (__u64)(regs32.psw.addr & PSW32_ADDR_AMODE); + regs->psw.addr = (__u64)(regs32.psw.addr & PSW32_ADDR_INSN); + for (i = 0; i < NUM_GPRS; i++) + regs->gprs[i] = (__u64) regs32.gprs[i]; + memcpy(current->thread.acrs, regs32.acrs, sizeof(current->thread.acrs)); + restore_access_regs(current->thread.acrs); + + err = __copy_from_user(¤t->thread.fp_regs, &sregs->fpregs, + sizeof(_s390_fp_regs32)); + current->thread.fp_regs.fpc &= FPC_VALID_MASK; + if (err) + return err; + + restore_fp_regs(¤t->thread.fp_regs); + clear_thread_flag(TIF_SYSCALL); /* No longer in a system call */ + return 0; +} + +static int save_sigregs_gprs_high(struct pt_regs *regs, __u32 __user *uregs) +{ + __u32 gprs_high[NUM_GPRS]; + int i; + + for (i = 0; i < NUM_GPRS; i++) + gprs_high[i] = regs->gprs[i] >> 32; + + return __copy_to_user(uregs, &gprs_high, sizeof(gprs_high)); +} + +static int restore_sigregs_gprs_high(struct pt_regs *regs, __u32 __user *uregs) +{ + __u32 gprs_high[NUM_GPRS]; + int err, i; + + err = __copy_from_user(&gprs_high, uregs, sizeof(gprs_high)); + if (err) + return err; + for (i = 0; i < NUM_GPRS; i++) + *(__u32 *)®s->gprs[i] = gprs_high[i]; + return 0; +} + +asmlinkage long sys32_sigreturn(void) +{ + struct pt_regs *regs = task_pt_regs(current); + sigframe32 __user *frame = (sigframe32 __user *)regs->gprs[15]; + sigset_t set; + + if (!access_ok(VERIFY_READ, frame, sizeof(*frame))) + goto badframe; + if (__copy_from_user(&set.sig, &frame->sc.oldmask, _SIGMASK_COPY_SIZE32)) + goto badframe; + sigdelsetmask(&set, ~_BLOCKABLE); + set_current_blocked(&set); + if (restore_sigregs32(regs, &frame->sregs)) + goto badframe; + if (restore_sigregs_gprs_high(regs, frame->gprs_high)) + goto badframe; + return regs->gprs[2]; +badframe: + force_sig(SIGSEGV, current); + return 0; +} + +asmlinkage long sys32_rt_sigreturn(void) +{ + struct pt_regs *regs = task_pt_regs(current); + rt_sigframe32 __user *frame = (rt_sigframe32 __user *)regs->gprs[15]; + sigset_t set; + stack_t st; + __u32 ss_sp; + int err; + mm_segment_t old_fs = get_fs(); + + if (!access_ok(VERIFY_READ, frame, sizeof(*frame))) + goto badframe; + if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set))) + goto badframe; + sigdelsetmask(&set, ~_BLOCKABLE); + set_current_blocked(&set); + if (restore_sigregs32(regs, &frame->uc.uc_mcontext)) + goto badframe; + if (restore_sigregs_gprs_high(regs, frame->gprs_high)) + goto badframe; + err = __get_user(ss_sp, &frame->uc.uc_stack.ss_sp); + st.ss_sp = compat_ptr(ss_sp); + err |= __get_user(st.ss_size, &frame->uc.uc_stack.ss_size); + err |= __get_user(st.ss_flags, &frame->uc.uc_stack.ss_flags); + if (err) + goto badframe; + set_fs (KERNEL_DS); + do_sigaltstack((stack_t __force __user *)&st, NULL, regs->gprs[15]); + set_fs (old_fs); + return regs->gprs[2]; +badframe: + force_sig(SIGSEGV, current); + return 0; +} + +/* + * Set up a signal frame. + */ + + +/* + * Determine which stack to use.. + */ +static inline void __user * +get_sigframe(struct k_sigaction *ka, struct pt_regs * regs, size_t frame_size) +{ + unsigned long sp; + + /* Default to using normal stack */ + sp = (unsigned long) A(regs->gprs[15]); + + /* Overflow on alternate signal stack gives SIGSEGV. */ + if (on_sig_stack(sp) && !on_sig_stack((sp - frame_size) & -8UL)) + return (void __user *) -1UL; + + /* This is the X/Open sanctioned signal stack switching. */ + if (ka->sa.sa_flags & SA_ONSTACK) { + if (! sas_ss_flags(sp)) + sp = current->sas_ss_sp + current->sas_ss_size; + } + + /* This is the legacy signal stack switching. */ + else if (!user_mode(regs) && + !(ka->sa.sa_flags & SA_RESTORER) && + ka->sa.sa_restorer) { + sp = (unsigned long) ka->sa.sa_restorer; + } + + return (void __user *)((sp - frame_size) & -8ul); +} + +static inline int map_signal(int sig) +{ + if (current_thread_info()->exec_domain + && current_thread_info()->exec_domain->signal_invmap + && sig < 32) + return current_thread_info()->exec_domain->signal_invmap[sig]; + else + return sig; +} + +static int setup_frame32(int sig, struct k_sigaction *ka, + sigset_t *set, struct pt_regs * regs) +{ + sigframe32 __user *frame = get_sigframe(ka, regs, sizeof(sigframe32)); + if (!access_ok(VERIFY_WRITE, frame, sizeof(sigframe32))) + goto give_sigsegv; + + if (frame == (void __user *) -1UL) + goto give_sigsegv; + + if (__copy_to_user(&frame->sc.oldmask, &set->sig, _SIGMASK_COPY_SIZE32)) + goto give_sigsegv; + + if (save_sigregs32(regs, &frame->sregs)) + goto give_sigsegv; + if (save_sigregs_gprs_high(regs, frame->gprs_high)) + goto give_sigsegv; + if (__put_user((unsigned long) &frame->sregs, &frame->sc.sregs)) + goto give_sigsegv; + + /* Set up to return from userspace. If provided, use a stub + already in userspace. */ + if (ka->sa.sa_flags & SA_RESTORER) { + regs->gprs[14] = (__u64) ka->sa.sa_restorer | PSW32_ADDR_AMODE; + } else { + regs->gprs[14] = (__u64) frame->retcode | PSW32_ADDR_AMODE; + if (__put_user(S390_SYSCALL_OPCODE | __NR_sigreturn, + (u16 __force __user *)(frame->retcode))) + goto give_sigsegv; + } + + /* Set up backchain. */ + if (__put_user(regs->gprs[15], (unsigned int __user *) frame)) + goto give_sigsegv; + + /* Set up registers for signal handler */ + regs->gprs[15] = (__force __u64) frame; + regs->psw.mask |= PSW_MASK_BA; /* force amode 31 */ + regs->psw.addr = (__force __u64) ka->sa.sa_handler; + + regs->gprs[2] = map_signal(sig); + regs->gprs[3] = (__force __u64) &frame->sc; + + /* We forgot to include these in the sigcontext. + To avoid breaking binary compatibility, they are passed as args. */ + if (sig == SIGSEGV || sig == SIGBUS || sig == SIGILL || + sig == SIGTRAP || sig == SIGFPE) { + /* set extra registers only for synchronous signals */ + regs->gprs[4] = regs->int_code & 127; + regs->gprs[5] = regs->int_parm_long; + } + + /* Place signal number on stack to allow backtrace from handler. */ + if (__put_user(regs->gprs[2], (int __force __user *) &frame->signo)) + goto give_sigsegv; + return 0; + +give_sigsegv: + force_sigsegv(sig, current); + return -EFAULT; +} + +static int setup_rt_frame32(int sig, struct k_sigaction *ka, siginfo_t *info, + sigset_t *set, struct pt_regs * regs) +{ + int err = 0; + rt_sigframe32 __user *frame = get_sigframe(ka, regs, sizeof(rt_sigframe32)); + if (!access_ok(VERIFY_WRITE, frame, sizeof(rt_sigframe32))) + goto give_sigsegv; + + if (frame == (void __user *) -1UL) + goto give_sigsegv; + + if (copy_siginfo_to_user32(&frame->info, info)) + goto give_sigsegv; + + /* Create the ucontext. */ + err |= __put_user(UC_EXTENDED, &frame->uc.uc_flags); + err |= __put_user(0, &frame->uc.uc_link); + err |= __put_user(current->sas_ss_sp, &frame->uc.uc_stack.ss_sp); + err |= __put_user(sas_ss_flags(regs->gprs[15]), + &frame->uc.uc_stack.ss_flags); + err |= __put_user(current->sas_ss_size, &frame->uc.uc_stack.ss_size); + err |= save_sigregs32(regs, &frame->uc.uc_mcontext); + err |= save_sigregs_gprs_high(regs, frame->gprs_high); + err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)); + if (err) + goto give_sigsegv; + + /* Set up to return from userspace. If provided, use a stub + already in userspace. */ + if (ka->sa.sa_flags & SA_RESTORER) { + regs->gprs[14] = (__u64) ka->sa.sa_restorer | PSW32_ADDR_AMODE; + } else { + regs->gprs[14] = (__u64) frame->retcode | PSW32_ADDR_AMODE; + err |= __put_user(S390_SYSCALL_OPCODE | __NR_rt_sigreturn, + (u16 __force __user *)(frame->retcode)); + } + + /* Set up backchain. */ + if (__put_user(regs->gprs[15], (unsigned int __force __user *) frame)) + goto give_sigsegv; + + /* Set up registers for signal handler */ + regs->gprs[15] = (__force __u64) frame; + regs->psw.mask |= PSW_MASK_BA; /* force amode 31 */ + regs->psw.addr = (__u64) ka->sa.sa_handler; + + regs->gprs[2] = map_signal(sig); + regs->gprs[3] = (__force __u64) &frame->info; + regs->gprs[4] = (__force __u64) &frame->uc; + return 0; + +give_sigsegv: + force_sigsegv(sig, current); + return -EFAULT; +} + +/* + * OK, we're invoking a handler + */ + +int handle_signal32(unsigned long sig, struct k_sigaction *ka, + siginfo_t *info, sigset_t *oldset, struct pt_regs *regs) +{ + int ret; + + /* Set up the stack frame */ + if (ka->sa.sa_flags & SA_SIGINFO) + ret = setup_rt_frame32(sig, ka, info, oldset, regs); + else + ret = setup_frame32(sig, ka, oldset, regs); + if (ret) + return ret; + block_sigmask(ka, sig); + return 0; +} + diff --git a/arch/s390/kernel/compat_wrapper.S b/arch/s390/kernel/compat_wrapper.S new file mode 100644 index 00000000..ff605a39 --- /dev/null +++ b/arch/s390/kernel/compat_wrapper.S @@ -0,0 +1,1649 @@ +/* +* arch/s390/kernel/compat_wrapper.S +* wrapper for 31 bit compatible system calls. +* +* Copyright (C) IBM Corp. 2000,2006 +* Author(s): Gerhard Tonn (ton@de.ibm.com), +* Thomas Spatzier (tspat@de.ibm.com) +*/ + +#include <linux/linkage.h> + +ENTRY(sys32_exit_wrapper) + lgfr %r2,%r2 # int + jg sys_exit # branch to sys_exit + +ENTRY(sys32_read_wrapper) + llgfr %r2,%r2 # unsigned int + llgtr %r3,%r3 # char * + llgfr %r4,%r4 # size_t + jg sys32_read # branch to sys_read + +ENTRY(sys32_write_wrapper) + llgfr %r2,%r2 # unsigned int + llgtr %r3,%r3 # const char * + llgfr %r4,%r4 # size_t + jg sys32_write # branch to system call + +ENTRY(sys32_open_wrapper) + llgtr %r2,%r2 # const char * + lgfr %r3,%r3 # int + lgfr %r4,%r4 # int + jg sys_open # branch to system call + +ENTRY(sys32_close_wrapper) + llgfr %r2,%r2 # unsigned int + jg sys_close # branch to system call + +ENTRY(sys32_creat_wrapper) + llgtr %r2,%r2 # const char * + lgfr %r3,%r3 # int + jg sys_creat # branch to system call + +ENTRY(sys32_link_wrapper) + llgtr %r2,%r2 # const char * + llgtr %r3,%r3 # const char * + jg sys_link # branch to system call + +ENTRY(sys32_unlink_wrapper) + llgtr %r2,%r2 # const char * + jg sys_unlink # branch to system call + +ENTRY(sys32_chdir_wrapper) + llgtr %r2,%r2 # const char * + jg sys_chdir # branch to system call + +ENTRY(sys32_time_wrapper) + llgtr %r2,%r2 # int * + jg compat_sys_time # branch to system call + +ENTRY(sys32_mknod_wrapper) + llgtr %r2,%r2 # const char * + lgfr %r3,%r3 # int + llgfr %r4,%r4 # dev + jg sys_mknod # branch to system call + +ENTRY(sys32_chmod_wrapper) + llgtr %r2,%r2 # const char * + llgfr %r3,%r3 # mode_t + jg sys_chmod # branch to system call + +ENTRY(sys32_lchown16_wrapper) + llgtr %r2,%r2 # const char * + llgfr %r3,%r3 # __kernel_old_uid_emu31_t + llgfr %r4,%r4 # __kernel_old_uid_emu31_t + jg sys32_lchown16 # branch to system call + +ENTRY(sys32_lseek_wrapper) + llgfr %r2,%r2 # unsigned int + lgfr %r3,%r3 # off_t + llgfr %r4,%r4 # unsigned int + jg sys_lseek # branch to system call + +#sys32_getpid_wrapper # void + +ENTRY(sys32_mount_wrapper) + llgtr %r2,%r2 # char * + llgtr %r3,%r3 # char * + llgtr %r4,%r4 # char * + llgfr %r5,%r5 # unsigned long + llgtr %r6,%r6 # void * + jg compat_sys_mount # branch to system call + +ENTRY(sys32_oldumount_wrapper) + llgtr %r2,%r2 # char * + jg sys_oldumount # branch to system call + +ENTRY(sys32_setuid16_wrapper) + llgfr %r2,%r2 # __kernel_old_uid_emu31_t + jg sys32_setuid16 # branch to system call + +#sys32_getuid16_wrapper # void + +ENTRY(sys32_ptrace_wrapper) + lgfr %r2,%r2 # long + lgfr %r3,%r3 # long + llgtr %r4,%r4 # long + llgfr %r5,%r5 # long + jg compat_sys_ptrace # branch to system call + +ENTRY(sys32_alarm_wrapper) + llgfr %r2,%r2 # unsigned int + jg sys_alarm # branch to system call + +ENTRY(compat_sys_utime_wrapper) + llgtr %r2,%r2 # char * + llgtr %r3,%r3 # struct compat_utimbuf * + jg compat_sys_utime # branch to system call + +ENTRY(sys32_access_wrapper) + llgtr %r2,%r2 # const char * + lgfr %r3,%r3 # int + jg sys_access # branch to system call + +ENTRY(sys32_nice_wrapper) + lgfr %r2,%r2 # int + jg sys_nice # branch to system call + +#sys32_sync_wrapper # void + +ENTRY(sys32_kill_wrapper) + lgfr %r2,%r2 # int + lgfr %r3,%r3 # int + jg sys_kill # branch to system call + +ENTRY(sys32_rename_wrapper) + llgtr %r2,%r2 # const char * + llgtr %r3,%r3 # const char * + jg sys_rename # branch to system call + +ENTRY(sys32_mkdir_wrapper) + llgtr %r2,%r2 # const char * + lgfr %r3,%r3 # int + jg sys_mkdir # branch to system call + +ENTRY(sys32_rmdir_wrapper) + llgtr %r2,%r2 # const char * + jg sys_rmdir # branch to system call + +ENTRY(sys32_dup_wrapper) + llgfr %r2,%r2 # unsigned int + jg sys_dup # branch to system call + +ENTRY(sys32_pipe_wrapper) + llgtr %r2,%r2 # u32 * + jg sys_pipe # branch to system call + +ENTRY(compat_sys_times_wrapper) + llgtr %r2,%r2 # struct compat_tms * + jg compat_sys_times # branch to system call + +ENTRY(sys32_brk_wrapper) + llgtr %r2,%r2 # unsigned long + jg sys_brk # branch to system call + +ENTRY(sys32_setgid16_wrapper) + llgfr %r2,%r2 # __kernel_old_gid_emu31_t + jg sys32_setgid16 # branch to system call + +#sys32_getgid16_wrapper # void + +ENTRY(sys32_signal_wrapper) + lgfr %r2,%r2 # int + llgtr %r3,%r3 # __sighandler_t + jg sys_signal + +#sys32_geteuid16_wrapper # void + +#sys32_getegid16_wrapper # void + +ENTRY(sys32_acct_wrapper) + llgtr %r2,%r2 # char * + jg sys_acct # branch to system call + +ENTRY(sys32_umount_wrapper) + llgtr %r2,%r2 # char * + lgfr %r3,%r3 # int + jg sys_umount # branch to system call + +ENTRY(compat_sys_ioctl_wrapper) + llgfr %r2,%r2 # unsigned int + llgfr %r3,%r3 # unsigned int + llgfr %r4,%r4 # unsigned int + jg compat_sys_ioctl # branch to system call + +ENTRY(compat_sys_fcntl_wrapper) + llgfr %r2,%r2 # unsigned int + llgfr %r3,%r3 # unsigned int + llgfr %r4,%r4 # unsigned long + jg compat_sys_fcntl # branch to system call + +ENTRY(sys32_setpgid_wrapper) + lgfr %r2,%r2 # pid_t + lgfr %r3,%r3 # pid_t + jg sys_setpgid # branch to system call + +ENTRY(sys32_umask_wrapper) + lgfr %r2,%r2 # int + jg sys_umask # branch to system call + +ENTRY(sys32_chroot_wrapper) + llgtr %r2,%r2 # char * + jg sys_chroot # branch to system call + +ENTRY(sys32_ustat_wrapper) + llgfr %r2,%r2 # dev_t + llgtr %r3,%r3 # struct ustat * + jg compat_sys_ustat + +ENTRY(sys32_dup2_wrapper) + llgfr %r2,%r2 # unsigned int + llgfr %r3,%r3 # unsigned int + jg sys_dup2 # branch to system call + +#sys32_getppid_wrapper # void + +#sys32_getpgrp_wrapper # void + +#sys32_setsid_wrapper # void + +ENTRY(sys32_sigaction_wrapper) + lgfr %r2,%r2 # int + llgtr %r3,%r3 # const struct old_sigaction * + llgtr %r4,%r4 # struct old_sigaction32 * + jg sys32_sigaction # branch to system call + +ENTRY(sys32_setreuid16_wrapper) + llgfr %r2,%r2 # __kernel_old_uid_emu31_t + llgfr %r3,%r3 # __kernel_old_uid_emu31_t + jg sys32_setreuid16 # branch to system call + +ENTRY(sys32_setregid16_wrapper) + llgfr %r2,%r2 # __kernel_old_gid_emu31_t + llgfr %r3,%r3 # __kernel_old_gid_emu31_t + jg sys32_setregid16 # branch to system call + +ENTRY(sys_sigsuspend_wrapper) + lgfr %r2,%r2 # int + lgfr %r3,%r3 # int + llgfr %r4,%r4 # old_sigset_t + jg sys_sigsuspend + +ENTRY(compat_sys_sigpending_wrapper) + llgtr %r2,%r2 # compat_old_sigset_t * + jg compat_sys_sigpending # branch to system call + +ENTRY(sys32_sethostname_wrapper) + llgtr %r2,%r2 # char * + lgfr %r3,%r3 # int + jg sys_sethostname # branch to system call + +ENTRY(compat_sys_setrlimit_wrapper) + llgfr %r2,%r2 # unsigned int + llgtr %r3,%r3 # struct rlimit_emu31 * + jg compat_sys_setrlimit # branch to system call + +ENTRY(compat_sys_old_getrlimit_wrapper) + llgfr %r2,%r2 # unsigned int + llgtr %r3,%r3 # struct rlimit_emu31 * + jg compat_sys_old_getrlimit # branch to system call + +ENTRY(compat_sys_getrlimit_wrapper) + llgfr %r2,%r2 # unsigned int + llgtr %r3,%r3 # struct rlimit_emu31 * + jg compat_sys_getrlimit # branch to system call + +ENTRY(sys32_mmap2_wrapper) + llgtr %r2,%r2 # struct mmap_arg_struct_emu31 * + jg sys32_mmap2 # branch to system call + +ENTRY(compat_sys_getrusage_wrapper) + lgfr %r2,%r2 # int + llgtr %r3,%r3 # struct rusage_emu31 * + jg compat_sys_getrusage # branch to system call + +ENTRY(compat_sys_gettimeofday_wrapper) + llgtr %r2,%r2 # struct timeval_emu31 * + llgtr %r3,%r3 # struct timezone * + jg compat_sys_gettimeofday # branch to system call + +ENTRY(compat_sys_settimeofday_wrapper) + llgtr %r2,%r2 # struct timeval_emu31 * + llgtr %r3,%r3 # struct timezone * + jg compat_sys_settimeofday # branch to system call + +ENTRY(sys32_getgroups16_wrapper) + lgfr %r2,%r2 # int + llgtr %r3,%r3 # __kernel_old_gid_emu31_t * + jg sys32_getgroups16 # branch to system call + +ENTRY(sys32_setgroups16_wrapper) + lgfr %r2,%r2 # int + llgtr %r3,%r3 # __kernel_old_gid_emu31_t * + jg sys32_setgroups16 # branch to system call + +ENTRY(sys32_symlink_wrapper) + llgtr %r2,%r2 # const char * + llgtr %r3,%r3 # const char * + jg sys_symlink # branch to system call + +ENTRY(sys32_readlink_wrapper) + llgtr %r2,%r2 # const char * + llgtr %r3,%r3 # char * + lgfr %r4,%r4 # int + jg sys_readlink # branch to system call + +ENTRY(sys32_uselib_wrapper) + llgtr %r2,%r2 # const char * + jg sys_uselib # branch to system call + +ENTRY(sys32_swapon_wrapper) + llgtr %r2,%r2 # const char * + lgfr %r3,%r3 # int + jg sys_swapon # branch to system call + +ENTRY(sys32_reboot_wrapper) + lgfr %r2,%r2 # int + lgfr %r3,%r3 # int + llgfr %r4,%r4 # unsigned int + llgtr %r5,%r5 # void * + jg sys_reboot # branch to system call + +ENTRY(old32_readdir_wrapper) + llgfr %r2,%r2 # unsigned int + llgtr %r3,%r3 # void * + llgfr %r4,%r4 # unsigned int + jg compat_sys_old_readdir # branch to system call + +ENTRY(old32_mmap_wrapper) + llgtr %r2,%r2 # struct mmap_arg_struct_emu31 * + jg old32_mmap # branch to system call + +ENTRY(sys32_munmap_wrapper) + llgfr %r2,%r2 # unsigned long + llgfr %r3,%r3 # size_t + jg sys_munmap # branch to system call + +ENTRY(sys32_truncate_wrapper) + llgtr %r2,%r2 # const char * + lgfr %r3,%r3 # long + jg sys_truncate # branch to system call + +ENTRY(sys32_ftruncate_wrapper) + llgfr %r2,%r2 # unsigned int + llgfr %r3,%r3 # unsigned long + jg sys_ftruncate # branch to system call + +ENTRY(sys32_fchmod_wrapper) + llgfr %r2,%r2 # unsigned int + llgfr %r3,%r3 # mode_t + jg sys_fchmod # branch to system call + +ENTRY(sys32_fchown16_wrapper) + llgfr %r2,%r2 # unsigned int + llgfr %r3,%r3 # compat_uid_t + llgfr %r4,%r4 # compat_uid_t + jg sys32_fchown16 # branch to system call + +ENTRY(sys32_getpriority_wrapper) + lgfr %r2,%r2 # int + lgfr %r3,%r3 # int + jg sys_getpriority # branch to system call + +ENTRY(sys32_setpriority_wrapper) + lgfr %r2,%r2 # int + lgfr %r3,%r3 # int + lgfr %r4,%r4 # int + jg sys_setpriority # branch to system call + +ENTRY(compat_sys_statfs_wrapper) + llgtr %r2,%r2 # char * + llgtr %r3,%r3 # struct compat_statfs * + jg compat_sys_statfs # branch to system call + +ENTRY(compat_sys_fstatfs_wrapper) + llgfr %r2,%r2 # unsigned int + llgtr %r3,%r3 # struct compat_statfs * + jg compat_sys_fstatfs # branch to system call + +ENTRY(compat_sys_socketcall_wrapper) + lgfr %r2,%r2 # int + llgtr %r3,%r3 # u32 * + jg compat_sys_socketcall # branch to system call + +ENTRY(sys32_syslog_wrapper) + lgfr %r2,%r2 # int + llgtr %r3,%r3 # char * + lgfr %r4,%r4 # int + jg sys_syslog # branch to system call + +ENTRY(compat_sys_setitimer_wrapper) + lgfr %r2,%r2 # int + llgtr %r3,%r3 # struct itimerval_emu31 * + llgtr %r4,%r4 # struct itimerval_emu31 * + jg compat_sys_setitimer # branch to system call + +ENTRY(compat_sys_getitimer_wrapper) + lgfr %r2,%r2 # int + llgtr %r3,%r3 # struct itimerval_emu31 * + jg compat_sys_getitimer # branch to system call + +ENTRY(compat_sys_newstat_wrapper) + llgtr %r2,%r2 # char * + llgtr %r3,%r3 # struct stat_emu31 * + jg compat_sys_newstat # branch to system call + +ENTRY(compat_sys_newlstat_wrapper) + llgtr %r2,%r2 # char * + llgtr %r3,%r3 # struct stat_emu31 * + jg compat_sys_newlstat # branch to system call + +ENTRY(compat_sys_newfstat_wrapper) + llgfr %r2,%r2 # unsigned int + llgtr %r3,%r3 # struct stat_emu31 * + jg compat_sys_newfstat # branch to system call + +#sys32_vhangup_wrapper # void + +ENTRY(compat_sys_wait4_wrapper) + lgfr %r2,%r2 # pid_t + llgtr %r3,%r3 # unsigned int * + lgfr %r4,%r4 # int + llgtr %r5,%r5 # struct rusage * + jg compat_sys_wait4 # branch to system call + +ENTRY(sys32_swapoff_wrapper) + llgtr %r2,%r2 # const char * + jg sys_swapoff # branch to system call + +ENTRY(compat_sys_sysinfo_wrapper) + llgtr %r2,%r2 # struct sysinfo_emu31 * + jg compat_sys_sysinfo # branch to system call + +ENTRY(sys32_ipc_wrapper) + llgfr %r2,%r2 # uint + lgfr %r3,%r3 # int + lgfr %r4,%r4 # int + lgfr %r5,%r5 # int + llgfr %r6,%r6 # u32 + jg sys32_ipc # branch to system call + +ENTRY(sys32_fsync_wrapper) + llgfr %r2,%r2 # unsigned int + jg sys_fsync # branch to system call + +#sys32_sigreturn_wrapper # done in sigreturn_glue + +#sys32_clone_wrapper # done in clone_glue + +ENTRY(sys32_setdomainname_wrapper) + llgtr %r2,%r2 # char * + lgfr %r3,%r3 # int + jg sys_setdomainname # branch to system call + +ENTRY(sys32_newuname_wrapper) + llgtr %r2,%r2 # struct new_utsname * + jg sys_newuname # branch to system call + +ENTRY(compat_sys_adjtimex_wrapper) + llgtr %r2,%r2 # struct compat_timex * + jg compat_sys_adjtimex # branch to system call + +ENTRY(sys32_mprotect_wrapper) + llgtr %r2,%r2 # unsigned long (actually pointer + llgfr %r3,%r3 # size_t + llgfr %r4,%r4 # unsigned long + jg sys_mprotect # branch to system call + +ENTRY(compat_sys_sigprocmask_wrapper) + lgfr %r2,%r2 # int + llgtr %r3,%r3 # compat_old_sigset_t * + llgtr %r4,%r4 # compat_old_sigset_t * + jg compat_sys_sigprocmask # branch to system call + +ENTRY(sys_init_module_wrapper) + llgtr %r2,%r2 # void * + llgfr %r3,%r3 # unsigned long + llgtr %r4,%r4 # char * + jg sys_init_module # branch to system call + +ENTRY(sys_delete_module_wrapper) + llgtr %r2,%r2 # const char * + llgfr %r3,%r3 # unsigned int + jg sys_delete_module # branch to system call + +ENTRY(sys32_quotactl_wrapper) + llgfr %r2,%r2 # unsigned int + llgtr %r3,%r3 # const char * + llgfr %r4,%r4 # qid_t + llgtr %r5,%r5 # caddr_t + jg sys_quotactl # branch to system call + +ENTRY(sys32_getpgid_wrapper) + lgfr %r2,%r2 # pid_t + jg sys_getpgid # branch to system call + +ENTRY(sys32_fchdir_wrapper) + llgfr %r2,%r2 # unsigned int + jg sys_fchdir # branch to system call + +ENTRY(sys32_bdflush_wrapper) + lgfr %r2,%r2 # int + lgfr %r3,%r3 # long + jg sys_bdflush # branch to system call + +ENTRY(sys32_sysfs_wrapper) + lgfr %r2,%r2 # int + llgfr %r3,%r3 # unsigned long + llgfr %r4,%r4 # unsigned long + jg sys_sysfs # branch to system call + +ENTRY(sys32_personality_wrapper) + llgfr %r2,%r2 # unsigned int + jg sys_s390_personality # branch to system call + +ENTRY(sys32_setfsuid16_wrapper) + llgfr %r2,%r2 # __kernel_old_uid_emu31_t + jg sys32_setfsuid16 # branch to system call + +ENTRY(sys32_setfsgid16_wrapper) + llgfr %r2,%r2 # __kernel_old_gid_emu31_t + jg sys32_setfsgid16 # branch to system call + +ENTRY(sys32_llseek_wrapper) + llgfr %r2,%r2 # unsigned int + llgfr %r3,%r3 # unsigned long + llgfr %r4,%r4 # unsigned long + llgtr %r5,%r5 # loff_t * + llgfr %r6,%r6 # unsigned int + jg sys_llseek # branch to system call + +ENTRY(sys32_getdents_wrapper) + llgfr %r2,%r2 # unsigned int + llgtr %r3,%r3 # void * + llgfr %r4,%r4 # unsigned int + jg compat_sys_getdents # branch to system call + +ENTRY(compat_sys_select_wrapper) + lgfr %r2,%r2 # int + llgtr %r3,%r3 # compat_fd_set * + llgtr %r4,%r4 # compat_fd_set * + llgtr %r5,%r5 # compat_fd_set * + llgtr %r6,%r6 # struct compat_timeval * + jg compat_sys_select # branch to system call + +ENTRY(sys32_flock_wrapper) + llgfr %r2,%r2 # unsigned int + llgfr %r3,%r3 # unsigned int + jg sys_flock # branch to system call + +ENTRY(sys32_msync_wrapper) + llgfr %r2,%r2 # unsigned long + llgfr %r3,%r3 # size_t + lgfr %r4,%r4 # int + jg sys_msync # branch to system call + +ENTRY(compat_sys_readv_wrapper) + lgfr %r2,%r2 # int + llgtr %r3,%r3 # const struct compat_iovec * + llgfr %r4,%r4 # unsigned long + jg compat_sys_readv # branch to system call + +ENTRY(compat_sys_writev_wrapper) + lgfr %r2,%r2 # int + llgtr %r3,%r3 # const struct compat_iovec * + llgfr %r4,%r4 # unsigned long + jg compat_sys_writev # branch to system call + +ENTRY(sys32_getsid_wrapper) + lgfr %r2,%r2 # pid_t + jg sys_getsid # branch to system call + +ENTRY(sys32_fdatasync_wrapper) + llgfr %r2,%r2 # unsigned int + jg sys_fdatasync # branch to system call + +ENTRY(sys32_mlock_wrapper) + llgfr %r2,%r2 # unsigned long + llgfr %r3,%r3 # size_t + jg sys_mlock # branch to system call + +ENTRY(sys32_munlock_wrapper) + llgfr %r2,%r2 # unsigned long + llgfr %r3,%r3 # size_t + jg sys_munlock # branch to system call + +ENTRY(sys32_mlockall_wrapper) + lgfr %r2,%r2 # int + jg sys_mlockall # branch to system call + +#sys32_munlockall_wrapper # void + +ENTRY(sys32_sched_setparam_wrapper) + lgfr %r2,%r2 # pid_t + llgtr %r3,%r3 # struct sched_param * + jg sys_sched_setparam # branch to system call + +ENTRY(sys32_sched_getparam_wrapper) + lgfr %r2,%r2 # pid_t + llgtr %r3,%r3 # struct sched_param * + jg sys_sched_getparam # branch to system call + +ENTRY(sys32_sched_setscheduler_wrapper) + lgfr %r2,%r2 # pid_t + lgfr %r3,%r3 # int + llgtr %r4,%r4 # struct sched_param * + jg sys_sched_setscheduler # branch to system call + +ENTRY(sys32_sched_getscheduler_wrapper) + lgfr %r2,%r2 # pid_t + jg sys_sched_getscheduler # branch to system call + +#sys32_sched_yield_wrapper # void + +ENTRY(sys32_sched_get_priority_max_wrapper) + lgfr %r2,%r2 # int + jg sys_sched_get_priority_max # branch to system call + +ENTRY(sys32_sched_get_priority_min_wrapper) + lgfr %r2,%r2 # int + jg sys_sched_get_priority_min # branch to system call + +ENTRY(sys32_sched_rr_get_interval_wrapper) + lgfr %r2,%r2 # pid_t + llgtr %r3,%r3 # struct compat_timespec * + jg sys32_sched_rr_get_interval # branch to system call + +ENTRY(compat_sys_nanosleep_wrapper) + llgtr %r2,%r2 # struct compat_timespec * + llgtr %r3,%r3 # struct compat_timespec * + jg compat_sys_nanosleep # branch to system call + +ENTRY(sys32_mremap_wrapper) + llgfr %r2,%r2 # unsigned long + llgfr %r3,%r3 # unsigned long + llgfr %r4,%r4 # unsigned long + llgfr %r5,%r5 # unsigned long + llgfr %r6,%r6 # unsigned long + jg sys_mremap # branch to system call + +ENTRY(sys32_setresuid16_wrapper) + llgfr %r2,%r2 # __kernel_old_uid_emu31_t + llgfr %r3,%r3 # __kernel_old_uid_emu31_t + llgfr %r4,%r4 # __kernel_old_uid_emu31_t + jg sys32_setresuid16 # branch to system call + +ENTRY(sys32_getresuid16_wrapper) + llgtr %r2,%r2 # __kernel_old_uid_emu31_t * + llgtr %r3,%r3 # __kernel_old_uid_emu31_t * + llgtr %r4,%r4 # __kernel_old_uid_emu31_t * + jg sys32_getresuid16 # branch to system call + +ENTRY(sys32_poll_wrapper) + llgtr %r2,%r2 # struct pollfd * + llgfr %r3,%r3 # unsigned int + lgfr %r4,%r4 # int + jg sys_poll # branch to system call + +ENTRY(sys32_setresgid16_wrapper) + llgfr %r2,%r2 # __kernel_old_gid_emu31_t + llgfr %r3,%r3 # __kernel_old_gid_emu31_t + llgfr %r4,%r4 # __kernel_old_gid_emu31_t + jg sys32_setresgid16 # branch to system call + +ENTRY(sys32_getresgid16_wrapper) + llgtr %r2,%r2 # __kernel_old_gid_emu31_t * + llgtr %r3,%r3 # __kernel_old_gid_emu31_t * + llgtr %r4,%r4 # __kernel_old_gid_emu31_t * + jg sys32_getresgid16 # branch to system call + +ENTRY(sys32_prctl_wrapper) + lgfr %r2,%r2 # int + llgfr %r3,%r3 # unsigned long + llgfr %r4,%r4 # unsigned long + llgfr %r5,%r5 # unsigned long + llgfr %r6,%r6 # unsigned long + jg sys_prctl # branch to system call + +#sys32_rt_sigreturn_wrapper # done in rt_sigreturn_glue + +ENTRY(sys32_rt_sigaction_wrapper) + lgfr %r2,%r2 # int + llgtr %r3,%r3 # const struct sigaction_emu31 * + llgtr %r4,%r4 # const struct sigaction_emu31 * + llgfr %r5,%r5 # size_t + jg sys32_rt_sigaction # branch to system call + +ENTRY(sys32_rt_sigprocmask_wrapper) + lgfr %r2,%r2 # int + llgtr %r3,%r3 # old_sigset_emu31 * + llgtr %r4,%r4 # old_sigset_emu31 * + llgfr %r5,%r5 # size_t + jg sys32_rt_sigprocmask # branch to system call + +ENTRY(sys32_rt_sigpending_wrapper) + llgtr %r2,%r2 # sigset_emu31 * + llgfr %r3,%r3 # size_t + jg sys32_rt_sigpending # branch to system call + +ENTRY(compat_sys_rt_sigtimedwait_wrapper) + llgtr %r2,%r2 # const sigset_emu31_t * + llgtr %r3,%r3 # siginfo_emu31_t * + llgtr %r4,%r4 # const struct compat_timespec * + llgfr %r5,%r5 # size_t + jg compat_sys_rt_sigtimedwait # branch to system call + +ENTRY(sys32_rt_sigqueueinfo_wrapper) + lgfr %r2,%r2 # int + lgfr %r3,%r3 # int + llgtr %r4,%r4 # siginfo_emu31_t * + jg sys32_rt_sigqueueinfo # branch to system call + +ENTRY(compat_sys_rt_sigsuspend_wrapper) + llgtr %r2,%r2 # compat_sigset_t * + llgfr %r3,%r3 # compat_size_t + jg compat_sys_rt_sigsuspend + +ENTRY(sys32_pread64_wrapper) + llgfr %r2,%r2 # unsigned int + llgtr %r3,%r3 # char * + llgfr %r4,%r4 # size_t + llgfr %r5,%r5 # u32 + llgfr %r6,%r6 # u32 + jg sys32_pread64 # branch to system call + +ENTRY(sys32_pwrite64_wrapper) + llgfr %r2,%r2 # unsigned int + llgtr %r3,%r3 # const char * + llgfr %r4,%r4 # size_t + llgfr %r5,%r5 # u32 + llgfr %r6,%r6 # u32 + jg sys32_pwrite64 # branch to system call + +ENTRY(sys32_chown16_wrapper) + llgtr %r2,%r2 # const char * + llgfr %r3,%r3 # __kernel_old_uid_emu31_t + llgfr %r4,%r4 # __kernel_old_gid_emu31_t + jg sys32_chown16 # branch to system call + +ENTRY(sys32_getcwd_wrapper) + llgtr %r2,%r2 # char * + llgfr %r3,%r3 # unsigned long + jg sys_getcwd # branch to system call + +ENTRY(sys32_capget_wrapper) + llgtr %r2,%r2 # cap_user_header_t + llgtr %r3,%r3 # cap_user_data_t + jg sys_capget # branch to system call + +ENTRY(sys32_capset_wrapper) + llgtr %r2,%r2 # cap_user_header_t + llgtr %r3,%r3 # const cap_user_data_t + jg sys_capset # branch to system call + +ENTRY(sys32_sigaltstack_wrapper) + llgtr %r2,%r2 # const stack_emu31_t * + llgtr %r3,%r3 # stack_emu31_t * + jg sys32_sigaltstack + +ENTRY(sys32_sendfile_wrapper) + lgfr %r2,%r2 # int + lgfr %r3,%r3 # int + llgtr %r4,%r4 # __kernel_off_emu31_t * + llgfr %r5,%r5 # size_t + jg sys32_sendfile # branch to system call + +#sys32_vfork_wrapper # done in vfork_glue + +ENTRY(sys32_truncate64_wrapper) + llgtr %r2,%r2 # const char * + llgfr %r3,%r3 # unsigned long + llgfr %r4,%r4 # unsigned long + jg sys32_truncate64 # branch to system call + +ENTRY(sys32_ftruncate64_wrapper) + llgfr %r2,%r2 # unsigned int + llgfr %r3,%r3 # unsigned long + llgfr %r4,%r4 # unsigned long + jg sys32_ftruncate64 # branch to system call + +ENTRY(sys32_lchown_wrapper) + llgtr %r2,%r2 # const char * + llgfr %r3,%r3 # uid_t + llgfr %r4,%r4 # gid_t + jg sys_lchown # branch to system call + +#sys32_getuid_wrapper # void +#sys32_getgid_wrapper # void +#sys32_geteuid_wrapper # void +#sys32_getegid_wrapper # void + +ENTRY(sys32_setreuid_wrapper) + llgfr %r2,%r2 # uid_t + llgfr %r3,%r3 # uid_t + jg sys_setreuid # branch to system call + +ENTRY(sys32_setregid_wrapper) + llgfr %r2,%r2 # gid_t + llgfr %r3,%r3 # gid_t + jg sys_setregid # branch to system call + +ENTRY(sys32_getgroups_wrapper) + lgfr %r2,%r2 # int + llgtr %r3,%r3 # gid_t * + jg sys_getgroups # branch to system call + +ENTRY(sys32_setgroups_wrapper) + lgfr %r2,%r2 # int + llgtr %r3,%r3 # gid_t * + jg sys_setgroups # branch to system call + +ENTRY(sys32_fchown_wrapper) + llgfr %r2,%r2 # unsigned int + llgfr %r3,%r3 # uid_t + llgfr %r4,%r4 # gid_t + jg sys_fchown # branch to system call + +ENTRY(sys32_setresuid_wrapper) + llgfr %r2,%r2 # uid_t + llgfr %r3,%r3 # uid_t + llgfr %r4,%r4 # uid_t + jg sys_setresuid # branch to system call + +ENTRY(sys32_getresuid_wrapper) + llgtr %r2,%r2 # uid_t * + llgtr %r3,%r3 # uid_t * + llgtr %r4,%r4 # uid_t * + jg sys_getresuid # branch to system call + +ENTRY(sys32_setresgid_wrapper) + llgfr %r2,%r2 # gid_t + llgfr %r3,%r3 # gid_t + llgfr %r4,%r4 # gid_t + jg sys_setresgid # branch to system call + +ENTRY(sys32_getresgid_wrapper) + llgtr %r2,%r2 # gid_t * + llgtr %r3,%r3 # gid_t * + llgtr %r4,%r4 # gid_t * + jg sys_getresgid # branch to system call + +ENTRY(sys32_chown_wrapper) + llgtr %r2,%r2 # const char * + llgfr %r3,%r3 # uid_t + llgfr %r4,%r4 # gid_t + jg sys_chown # branch to system call + +ENTRY(sys32_setuid_wrapper) + llgfr %r2,%r2 # uid_t + jg sys_setuid # branch to system call + +ENTRY(sys32_setgid_wrapper) + llgfr %r2,%r2 # gid_t + jg sys_setgid # branch to system call + +ENTRY(sys32_setfsuid_wrapper) + llgfr %r2,%r2 # uid_t + jg sys_setfsuid # branch to system call + +ENTRY(sys32_setfsgid_wrapper) + llgfr %r2,%r2 # gid_t + jg sys_setfsgid # branch to system call + +ENTRY(sys32_pivot_root_wrapper) + llgtr %r2,%r2 # const char * + llgtr %r3,%r3 # const char * + jg sys_pivot_root # branch to system call + +ENTRY(sys32_mincore_wrapper) + llgfr %r2,%r2 # unsigned long + llgfr %r3,%r3 # size_t + llgtr %r4,%r4 # unsigned char * + jg sys_mincore # branch to system call + +ENTRY(sys32_madvise_wrapper) + llgfr %r2,%r2 # unsigned long + llgfr %r3,%r3 # size_t + lgfr %r4,%r4 # int + jg sys_madvise # branch to system call + +ENTRY(sys32_getdents64_wrapper) + llgfr %r2,%r2 # unsigned int + llgtr %r3,%r3 # void * + llgfr %r4,%r4 # unsigned int + jg sys_getdents64 # branch to system call + +ENTRY(compat_sys_fcntl64_wrapper) + llgfr %r2,%r2 # unsigned int + llgfr %r3,%r3 # unsigned int + llgfr %r4,%r4 # unsigned long + jg compat_sys_fcntl64 # branch to system call + +ENTRY(sys32_stat64_wrapper) + llgtr %r2,%r2 # char * + llgtr %r3,%r3 # struct stat64 * + jg sys32_stat64 # branch to system call + +ENTRY(sys32_lstat64_wrapper) + llgtr %r2,%r2 # char * + llgtr %r3,%r3 # struct stat64 * + jg sys32_lstat64 # branch to system call + +ENTRY(sys32_stime_wrapper) + llgtr %r2,%r2 # long * + jg compat_sys_stime # branch to system call + +ENTRY(sys32_sysctl_wrapper) + llgtr %r2,%r2 # struct compat_sysctl_args * + jg compat_sys_sysctl + +ENTRY(sys32_fstat64_wrapper) + llgfr %r2,%r2 # unsigned long + llgtr %r3,%r3 # struct stat64 * + jg sys32_fstat64 # branch to system call + +ENTRY(compat_sys_futex_wrapper) + llgtr %r2,%r2 # u32 * + lgfr %r3,%r3 # int + lgfr %r4,%r4 # int + llgtr %r5,%r5 # struct compat_timespec * + llgtr %r6,%r6 # u32 * + lgf %r0,164(%r15) # int + stg %r0,160(%r15) + jg compat_sys_futex # branch to system call + +ENTRY(sys32_setxattr_wrapper) + llgtr %r2,%r2 # char * + llgtr %r3,%r3 # char * + llgtr %r4,%r4 # void * + llgfr %r5,%r5 # size_t + lgfr %r6,%r6 # int + jg sys_setxattr + +ENTRY(sys32_lsetxattr_wrapper) + llgtr %r2,%r2 # char * + llgtr %r3,%r3 # char * + llgtr %r4,%r4 # void * + llgfr %r5,%r5 # size_t + lgfr %r6,%r6 # int + jg sys_lsetxattr + +ENTRY(sys32_fsetxattr_wrapper) + lgfr %r2,%r2 # int + llgtr %r3,%r3 # char * + llgtr %r4,%r4 # void * + llgfr %r5,%r5 # size_t + lgfr %r6,%r6 # int + jg sys_fsetxattr + +ENTRY(sys32_getxattr_wrapper) + llgtr %r2,%r2 # char * + llgtr %r3,%r3 # char * + llgtr %r4,%r4 # void * + llgfr %r5,%r5 # size_t + jg sys_getxattr + +ENTRY(sys32_lgetxattr_wrapper) + llgtr %r2,%r2 # char * + llgtr %r3,%r3 # char * + llgtr %r4,%r4 # void * + llgfr %r5,%r5 # size_t + jg sys_lgetxattr + +ENTRY(sys32_fgetxattr_wrapper) + lgfr %r2,%r2 # int + llgtr %r3,%r3 # char * + llgtr %r4,%r4 # void * + llgfr %r5,%r5 # size_t + jg sys_fgetxattr + +ENTRY(sys32_listxattr_wrapper) + llgtr %r2,%r2 # char * + llgtr %r3,%r3 # char * + llgfr %r4,%r4 # size_t + jg sys_listxattr + +ENTRY(sys32_llistxattr_wrapper) + llgtr %r2,%r2 # char * + llgtr %r3,%r3 # char * + llgfr %r4,%r4 # size_t + jg sys_llistxattr + +ENTRY(sys32_flistxattr_wrapper) + lgfr %r2,%r2 # int + llgtr %r3,%r3 # char * + llgfr %r4,%r4 # size_t + jg sys_flistxattr + +ENTRY(sys32_removexattr_wrapper) + llgtr %r2,%r2 # char * + llgtr %r3,%r3 # char * + jg sys_removexattr + +ENTRY(sys32_lremovexattr_wrapper) + llgtr %r2,%r2 # char * + llgtr %r3,%r3 # char * + jg sys_lremovexattr + +ENTRY(sys32_fremovexattr_wrapper) + lgfr %r2,%r2 # int + llgtr %r3,%r3 # char * + jg sys_fremovexattr + +ENTRY(sys32_sched_setaffinity_wrapper) + lgfr %r2,%r2 # int + llgfr %r3,%r3 # unsigned int + llgtr %r4,%r4 # unsigned long * + jg compat_sys_sched_setaffinity + +ENTRY(sys32_sched_getaffinity_wrapper) + lgfr %r2,%r2 # int + llgfr %r3,%r3 # unsigned int + llgtr %r4,%r4 # unsigned long * + jg compat_sys_sched_getaffinity + +ENTRY(sys32_exit_group_wrapper) + lgfr %r2,%r2 # int + jg sys_exit_group # branch to system call + +ENTRY(sys32_set_tid_address_wrapper) + llgtr %r2,%r2 # int * + jg sys_set_tid_address # branch to system call + +ENTRY(sys_epoll_create_wrapper) + lgfr %r2,%r2 # int + jg sys_epoll_create # branch to system call + +ENTRY(sys_epoll_ctl_wrapper) + lgfr %r2,%r2 # int + lgfr %r3,%r3 # int + lgfr %r4,%r4 # int + llgtr %r5,%r5 # struct epoll_event * + jg sys_epoll_ctl # branch to system call + +ENTRY(sys_epoll_wait_wrapper) + lgfr %r2,%r2 # int + llgtr %r3,%r3 # struct epoll_event * + lgfr %r4,%r4 # int + lgfr %r5,%r5 # int + jg sys_epoll_wait # branch to system call + +ENTRY(sys32_lookup_dcookie_wrapper) + sllg %r2,%r2,32 # get high word of 64bit dcookie + or %r2,%r3 # get low word of 64bit dcookie + llgtr %r3,%r4 # char * + llgfr %r4,%r5 # size_t + jg sys_lookup_dcookie + +ENTRY(sys32_fadvise64_wrapper) + lgfr %r2,%r2 # int + sllg %r3,%r3,32 # get high word of 64bit loff_t + or %r3,%r4 # get low word of 64bit loff_t + llgfr %r4,%r5 # size_t (unsigned long) + lgfr %r5,%r6 # int + jg sys32_fadvise64 + +ENTRY(sys32_fadvise64_64_wrapper) + llgtr %r2,%r2 # struct fadvise64_64_args * + jg sys32_fadvise64_64 + +ENTRY(sys32_clock_settime_wrapper) + lgfr %r2,%r2 # clockid_t (int) + llgtr %r3,%r3 # struct compat_timespec * + jg compat_sys_clock_settime + +ENTRY(sys32_clock_gettime_wrapper) + lgfr %r2,%r2 # clockid_t (int) + llgtr %r3,%r3 # struct compat_timespec * + jg compat_sys_clock_gettime + +ENTRY(sys32_clock_getres_wrapper) + lgfr %r2,%r2 # clockid_t (int) + llgtr %r3,%r3 # struct compat_timespec * + jg compat_sys_clock_getres + +ENTRY(sys32_clock_nanosleep_wrapper) + lgfr %r2,%r2 # clockid_t (int) + lgfr %r3,%r3 # int + llgtr %r4,%r4 # struct compat_timespec * + llgtr %r5,%r5 # struct compat_timespec * + jg compat_sys_clock_nanosleep + +ENTRY(sys32_timer_create_wrapper) + lgfr %r2,%r2 # timer_t (int) + llgtr %r3,%r3 # struct compat_sigevent * + llgtr %r4,%r4 # timer_t * + jg compat_sys_timer_create + +ENTRY(sys32_timer_settime_wrapper) + lgfr %r2,%r2 # timer_t (int) + lgfr %r3,%r3 # int + llgtr %r4,%r4 # struct compat_itimerspec * + llgtr %r5,%r5 # struct compat_itimerspec * + jg compat_sys_timer_settime + +ENTRY(sys32_timer_gettime_wrapper) + lgfr %r2,%r2 # timer_t (int) + llgtr %r3,%r3 # struct compat_itimerspec * + jg compat_sys_timer_gettime + +ENTRY(sys32_timer_getoverrun_wrapper) + lgfr %r2,%r2 # timer_t (int) + jg sys_timer_getoverrun + +ENTRY(sys32_timer_delete_wrapper) + lgfr %r2,%r2 # timer_t (int) + jg sys_timer_delete + +ENTRY(sys32_io_setup_wrapper) + llgfr %r2,%r2 # unsigned int + llgtr %r3,%r3 # u32 * + jg compat_sys_io_setup + +ENTRY(sys32_io_destroy_wrapper) + llgfr %r2,%r2 # (aio_context_t) u32 + jg sys_io_destroy + +ENTRY(sys32_io_getevents_wrapper) + llgfr %r2,%r2 # (aio_context_t) u32 + lgfr %r3,%r3 # long + lgfr %r4,%r4 # long + llgtr %r5,%r5 # struct io_event * + llgtr %r6,%r6 # struct compat_timespec * + jg compat_sys_io_getevents + +ENTRY(sys32_io_submit_wrapper) + llgfr %r2,%r2 # (aio_context_t) u32 + lgfr %r3,%r3 # long + llgtr %r4,%r4 # struct iocb ** + jg compat_sys_io_submit + +ENTRY(sys32_io_cancel_wrapper) + llgfr %r2,%r2 # (aio_context_t) u32 + llgtr %r3,%r3 # struct iocb * + llgtr %r4,%r4 # struct io_event * + jg sys_io_cancel + +ENTRY(compat_sys_statfs64_wrapper) + llgtr %r2,%r2 # const char * + llgfr %r3,%r3 # compat_size_t + llgtr %r4,%r4 # struct compat_statfs64 * + jg compat_sys_statfs64 + +ENTRY(compat_sys_fstatfs64_wrapper) + llgfr %r2,%r2 # unsigned int fd + llgfr %r3,%r3 # compat_size_t + llgtr %r4,%r4 # struct compat_statfs64 * + jg compat_sys_fstatfs64 + +ENTRY(compat_sys_mq_open_wrapper) + llgtr %r2,%r2 # const char * + lgfr %r3,%r3 # int + llgfr %r4,%r4 # mode_t + llgtr %r5,%r5 # struct compat_mq_attr * + jg compat_sys_mq_open + +ENTRY(sys32_mq_unlink_wrapper) + llgtr %r2,%r2 # const char * + jg sys_mq_unlink + +ENTRY(compat_sys_mq_timedsend_wrapper) + lgfr %r2,%r2 # mqd_t + llgtr %r3,%r3 # const char * + llgfr %r4,%r4 # size_t + llgfr %r5,%r5 # unsigned int + llgtr %r6,%r6 # const struct compat_timespec * + jg compat_sys_mq_timedsend + +ENTRY(compat_sys_mq_timedreceive_wrapper) + lgfr %r2,%r2 # mqd_t + llgtr %r3,%r3 # char * + llgfr %r4,%r4 # size_t + llgtr %r5,%r5 # unsigned int * + llgtr %r6,%r6 # const struct compat_timespec * + jg compat_sys_mq_timedreceive + +ENTRY(compat_sys_mq_notify_wrapper) + lgfr %r2,%r2 # mqd_t + llgtr %r3,%r3 # struct compat_sigevent * + jg compat_sys_mq_notify + +ENTRY(compat_sys_mq_getsetattr_wrapper) + lgfr %r2,%r2 # mqd_t + llgtr %r3,%r3 # struct compat_mq_attr * + llgtr %r4,%r4 # struct compat_mq_attr * + jg compat_sys_mq_getsetattr + +ENTRY(compat_sys_add_key_wrapper) + llgtr %r2,%r2 # const char * + llgtr %r3,%r3 # const char * + llgtr %r4,%r4 # const void * + llgfr %r5,%r5 # size_t + llgfr %r6,%r6 # (key_serial_t) u32 + jg sys_add_key + +ENTRY(compat_sys_request_key_wrapper) + llgtr %r2,%r2 # const char * + llgtr %r3,%r3 # const char * + llgtr %r4,%r4 # const void * + llgfr %r5,%r5 # (key_serial_t) u32 + jg sys_request_key + +ENTRY(sys32_remap_file_pages_wrapper) + llgfr %r2,%r2 # unsigned long + llgfr %r3,%r3 # unsigned long + llgfr %r4,%r4 # unsigned long + llgfr %r5,%r5 # unsigned long + llgfr %r6,%r6 # unsigned long + jg sys_remap_file_pages + +ENTRY(compat_sys_waitid_wrapper) + lgfr %r2,%r2 # int + lgfr %r3,%r3 # pid_t + llgtr %r4,%r4 # siginfo_emu31_t * + lgfr %r5,%r5 # int + llgtr %r6,%r6 # struct rusage_emu31 * + jg compat_sys_waitid + +ENTRY(compat_sys_kexec_load_wrapper) + llgfr %r2,%r2 # unsigned long + llgfr %r3,%r3 # unsigned long + llgtr %r4,%r4 # struct kexec_segment * + llgfr %r5,%r5 # unsigned long + jg compat_sys_kexec_load + +ENTRY(sys_ioprio_set_wrapper) + lgfr %r2,%r2 # int + lgfr %r3,%r3 # int + lgfr %r4,%r4 # int + jg sys_ioprio_set + +ENTRY(sys_ioprio_get_wrapper) + lgfr %r2,%r2 # int + lgfr %r3,%r3 # int + jg sys_ioprio_get + +ENTRY(sys_inotify_add_watch_wrapper) + lgfr %r2,%r2 # int + llgtr %r3,%r3 # const char * + llgfr %r4,%r4 # u32 + jg sys_inotify_add_watch + +ENTRY(sys_inotify_rm_watch_wrapper) + lgfr %r2,%r2 # int + llgfr %r3,%r3 # u32 + jg sys_inotify_rm_watch + +ENTRY(compat_sys_openat_wrapper) + llgfr %r2,%r2 # unsigned int + llgtr %r3,%r3 # const char * + lgfr %r4,%r4 # int + lgfr %r5,%r5 # int + jg compat_sys_openat + +ENTRY(sys_mkdirat_wrapper) + lgfr %r2,%r2 # int + llgtr %r3,%r3 # const char * + lgfr %r4,%r4 # int + jg sys_mkdirat + +ENTRY(sys_mknodat_wrapper) + lgfr %r2,%r2 # int + llgtr %r3,%r3 # const char * + lgfr %r4,%r4 # int + llgfr %r5,%r5 # unsigned int + jg sys_mknodat + +ENTRY(sys_fchownat_wrapper) + lgfr %r2,%r2 # int + llgtr %r3,%r3 # const char * + llgfr %r4,%r4 # uid_t + llgfr %r5,%r5 # gid_t + lgfr %r6,%r6 # int + jg sys_fchownat + +ENTRY(compat_sys_futimesat_wrapper) + llgfr %r2,%r2 # unsigned int + llgtr %r3,%r3 # char * + llgtr %r4,%r4 # struct timeval * + jg compat_sys_futimesat + +ENTRY(sys32_fstatat64_wrapper) + llgfr %r2,%r2 # unsigned int + llgtr %r3,%r3 # char * + llgtr %r4,%r4 # struct stat64 * + lgfr %r5,%r5 # int + jg sys32_fstatat64 + +ENTRY(sys_unlinkat_wrapper) + lgfr %r2,%r2 # int + llgtr %r3,%r3 # const char * + lgfr %r4,%r4 # int + jg sys_unlinkat + +ENTRY(sys_renameat_wrapper) + lgfr %r2,%r2 # int + llgtr %r3,%r3 # const char * + lgfr %r4,%r4 # int + llgtr %r5,%r5 # const char * + jg sys_renameat + +ENTRY(sys_linkat_wrapper) + lgfr %r2,%r2 # int + llgtr %r3,%r3 # const char * + lgfr %r4,%r4 # int + llgtr %r5,%r5 # const char * + lgfr %r6,%r6 # int + jg sys_linkat + +ENTRY(sys_symlinkat_wrapper) + llgtr %r2,%r2 # const char * + lgfr %r3,%r3 # int + llgtr %r4,%r4 # const char * + jg sys_symlinkat + +ENTRY(sys_readlinkat_wrapper) + lgfr %r2,%r2 # int + llgtr %r3,%r3 # const char * + llgtr %r4,%r4 # char * + lgfr %r5,%r5 # int + jg sys_readlinkat + +ENTRY(sys_fchmodat_wrapper) + lgfr %r2,%r2 # int + llgtr %r3,%r3 # const char * + llgfr %r4,%r4 # mode_t + jg sys_fchmodat + +ENTRY(sys_faccessat_wrapper) + lgfr %r2,%r2 # int + llgtr %r3,%r3 # const char * + lgfr %r4,%r4 # int + jg sys_faccessat + +ENTRY(compat_sys_pselect6_wrapper) + lgfr %r2,%r2 # int + llgtr %r3,%r3 # fd_set * + llgtr %r4,%r4 # fd_set * + llgtr %r5,%r5 # fd_set * + llgtr %r6,%r6 # struct timespec * + llgt %r0,164(%r15) # void * + stg %r0,160(%r15) + jg compat_sys_pselect6 + +ENTRY(compat_sys_ppoll_wrapper) + llgtr %r2,%r2 # struct pollfd * + llgfr %r3,%r3 # unsigned int + llgtr %r4,%r4 # struct timespec * + llgtr %r5,%r5 # const sigset_t * + llgfr %r6,%r6 # size_t + jg compat_sys_ppoll + +ENTRY(sys_unshare_wrapper) + llgfr %r2,%r2 # unsigned long + jg sys_unshare + +ENTRY(compat_sys_set_robust_list_wrapper) + llgtr %r2,%r2 # struct compat_robust_list_head * + llgfr %r3,%r3 # size_t + jg compat_sys_set_robust_list + +ENTRY(compat_sys_get_robust_list_wrapper) + lgfr %r2,%r2 # int + llgtr %r3,%r3 # compat_uptr_t_t * + llgtr %r4,%r4 # compat_size_t * + jg compat_sys_get_robust_list + +ENTRY(sys_splice_wrapper) + lgfr %r2,%r2 # int + llgtr %r3,%r3 # loff_t * + lgfr %r4,%r4 # int + llgtr %r5,%r5 # loff_t * + llgfr %r6,%r6 # size_t + llgf %r0,164(%r15) # unsigned int + stg %r0,160(%r15) + jg sys_splice + +ENTRY(sys_sync_file_range_wrapper) + lgfr %r2,%r2 # int + sllg %r3,%r3,32 # get high word of 64bit loff_t + or %r3,%r4 # get low word of 64bit loff_t + sllg %r4,%r5,32 # get high word of 64bit loff_t + or %r4,%r6 # get low word of 64bit loff_t + llgf %r5,164(%r15) # unsigned int + jg sys_sync_file_range + +ENTRY(sys_tee_wrapper) + lgfr %r2,%r2 # int + lgfr %r3,%r3 # int + llgfr %r4,%r4 # size_t + llgfr %r5,%r5 # unsigned int + jg sys_tee + +ENTRY(compat_sys_vmsplice_wrapper) + lgfr %r2,%r2 # int + llgtr %r3,%r3 # compat_iovec * + llgfr %r4,%r4 # unsigned int + llgfr %r5,%r5 # unsigned int + jg compat_sys_vmsplice + +ENTRY(sys_getcpu_wrapper) + llgtr %r2,%r2 # unsigned * + llgtr %r3,%r3 # unsigned * + llgtr %r4,%r4 # struct getcpu_cache * + jg sys_getcpu + +ENTRY(compat_sys_epoll_pwait_wrapper) + lgfr %r2,%r2 # int + llgtr %r3,%r3 # struct compat_epoll_event * + lgfr %r4,%r4 # int + lgfr %r5,%r5 # int + llgtr %r6,%r6 # compat_sigset_t * + llgf %r0,164(%r15) # compat_size_t + stg %r0,160(%r15) + jg compat_sys_epoll_pwait + +ENTRY(compat_sys_utimes_wrapper) + llgtr %r2,%r2 # char * + llgtr %r3,%r3 # struct compat_timeval * + jg compat_sys_utimes + +ENTRY(compat_sys_utimensat_wrapper) + llgfr %r2,%r2 # unsigned int + llgtr %r3,%r3 # char * + llgtr %r4,%r4 # struct compat_timespec * + lgfr %r5,%r5 # int + jg compat_sys_utimensat + +ENTRY(compat_sys_signalfd_wrapper) + lgfr %r2,%r2 # int + llgtr %r3,%r3 # compat_sigset_t * + llgfr %r4,%r4 # compat_size_t + jg compat_sys_signalfd + +ENTRY(sys_eventfd_wrapper) + llgfr %r2,%r2 # unsigned int + jg sys_eventfd + +ENTRY(sys_fallocate_wrapper) + lgfr %r2,%r2 # int + lgfr %r3,%r3 # int + sllg %r4,%r4,32 # get high word of 64bit loff_t + lr %r4,%r5 # get low word of 64bit loff_t + sllg %r5,%r6,32 # get high word of 64bit loff_t + l %r5,164(%r15) # get low word of 64bit loff_t + jg sys_fallocate + +ENTRY(sys_timerfd_create_wrapper) + lgfr %r2,%r2 # int + lgfr %r3,%r3 # int + jg sys_timerfd_create + +ENTRY(compat_sys_timerfd_settime_wrapper) + lgfr %r2,%r2 # int + lgfr %r3,%r3 # int + llgtr %r4,%r4 # struct compat_itimerspec * + llgtr %r5,%r5 # struct compat_itimerspec * + jg compat_sys_timerfd_settime + +ENTRY(compat_sys_timerfd_gettime_wrapper) + lgfr %r2,%r2 # int + llgtr %r3,%r3 # struct compat_itimerspec * + jg compat_sys_timerfd_gettime + +ENTRY(compat_sys_signalfd4_wrapper) + lgfr %r2,%r2 # int + llgtr %r3,%r3 # compat_sigset_t * + llgfr %r4,%r4 # compat_size_t + lgfr %r5,%r5 # int + jg compat_sys_signalfd4 + +ENTRY(sys_eventfd2_wrapper) + llgfr %r2,%r2 # unsigned int + lgfr %r3,%r3 # int + jg sys_eventfd2 + +ENTRY(sys_inotify_init1_wrapper) + lgfr %r2,%r2 # int + jg sys_inotify_init1 + +ENTRY(sys_pipe2_wrapper) + llgtr %r2,%r2 # u32 * + lgfr %r3,%r3 # int + jg sys_pipe2 # branch to system call + +ENTRY(sys_dup3_wrapper) + llgfr %r2,%r2 # unsigned int + llgfr %r3,%r3 # unsigned int + lgfr %r4,%r4 # int + jg sys_dup3 # branch to system call + +ENTRY(sys_epoll_create1_wrapper) + lgfr %r2,%r2 # int + jg sys_epoll_create1 # branch to system call + +ENTRY(sys32_readahead_wrapper) + lgfr %r2,%r2 # int + llgfr %r3,%r3 # u32 + llgfr %r4,%r4 # u32 + lgfr %r5,%r5 # s32 + jg sys32_readahead # branch to system call + +ENTRY(sys32_sendfile64_wrapper) + lgfr %r2,%r2 # int + lgfr %r3,%r3 # int + llgtr %r4,%r4 # compat_loff_t * + lgfr %r5,%r5 # s32 + jg sys32_sendfile64 # branch to system call + +ENTRY(sys_tkill_wrapper) + lgfr %r2,%r2 # pid_t + lgfr %r3,%r3 # int + jg sys_tkill # branch to system call + +ENTRY(sys_tgkill_wrapper) + lgfr %r2,%r2 # pid_t + lgfr %r3,%r3 # pid_t + lgfr %r4,%r4 # int + jg sys_tgkill # branch to system call + +ENTRY(compat_sys_keyctl_wrapper) + llgfr %r2,%r2 # u32 + llgfr %r3,%r3 # u32 + llgfr %r4,%r4 # u32 + llgfr %r5,%r5 # u32 + llgfr %r6,%r6 # u32 + jg compat_sys_keyctl # branch to system call + +ENTRY(compat_sys_preadv_wrapper) + llgfr %r2,%r2 # unsigned long + llgtr %r3,%r3 # compat_iovec * + llgfr %r4,%r4 # unsigned long + llgfr %r5,%r5 # u32 + llgfr %r6,%r6 # u32 + jg compat_sys_preadv # branch to system call + +ENTRY(compat_sys_pwritev_wrapper) + llgfr %r2,%r2 # unsigned long + llgtr %r3,%r3 # compat_iovec * + llgfr %r4,%r4 # unsigned long + llgfr %r5,%r5 # u32 + llgfr %r6,%r6 # u32 + jg compat_sys_pwritev # branch to system call + +ENTRY(compat_sys_rt_tgsigqueueinfo_wrapper) + lgfr %r2,%r2 # compat_pid_t + lgfr %r3,%r3 # compat_pid_t + lgfr %r4,%r4 # int + llgtr %r5,%r5 # struct compat_siginfo * + jg compat_sys_rt_tgsigqueueinfo_wrapper # branch to system call + +ENTRY(sys_perf_event_open_wrapper) + llgtr %r2,%r2 # const struct perf_event_attr * + lgfr %r3,%r3 # pid_t + lgfr %r4,%r4 # int + lgfr %r5,%r5 # int + llgfr %r6,%r6 # unsigned long + jg sys_perf_event_open # branch to system call + +ENTRY(sys_clone_wrapper) + llgfr %r2,%r2 # unsigned long + llgfr %r3,%r3 # unsigned long + llgtr %r4,%r4 # int * + llgtr %r5,%r5 # int * + jg sys_clone # branch to system call + +ENTRY(sys32_execve_wrapper) + llgtr %r2,%r2 # char * + llgtr %r3,%r3 # compat_uptr_t * + llgtr %r4,%r4 # compat_uptr_t * + jg sys32_execve # branch to system call + +ENTRY(sys_fanotify_init_wrapper) + llgfr %r2,%r2 # unsigned int + llgfr %r3,%r3 # unsigned int + jg sys_fanotify_init # branch to system call + +ENTRY(sys_fanotify_mark_wrapper) + lgfr %r2,%r2 # int + llgfr %r3,%r3 # unsigned int + sllg %r4,%r4,32 # get high word of 64bit mask + lr %r4,%r5 # get low word of 64bit mask + llgfr %r5,%r6 # unsigned int + llgt %r6,164(%r15) # char * + jg sys_fanotify_mark # branch to system call + +ENTRY(sys_prlimit64_wrapper) + lgfr %r2,%r2 # pid_t + llgfr %r3,%r3 # unsigned int + llgtr %r4,%r4 # const struct rlimit64 __user * + llgtr %r5,%r5 # struct rlimit64 __user * + jg sys_prlimit64 # branch to system call + +ENTRY(sys_name_to_handle_at_wrapper) + lgfr %r2,%r2 # int + llgtr %r3,%r3 # const char __user * + llgtr %r4,%r4 # struct file_handle __user * + llgtr %r5,%r5 # int __user * + lgfr %r6,%r6 # int + jg sys_name_to_handle_at + +ENTRY(compat_sys_open_by_handle_at_wrapper) + lgfr %r2,%r2 # int + llgtr %r3,%r3 # struct file_handle __user * + lgfr %r4,%r4 # int + jg compat_sys_open_by_handle_at + +ENTRY(compat_sys_clock_adjtime_wrapper) + lgfr %r2,%r2 # clockid_t (int) + llgtr %r3,%r3 # struct compat_timex __user * + jg compat_sys_clock_adjtime + +ENTRY(sys_syncfs_wrapper) + lgfr %r2,%r2 # int + jg sys_syncfs + +ENTRY(sys_setns_wrapper) + lgfr %r2,%r2 # int + lgfr %r3,%r3 # int + jg sys_setns + +ENTRY(compat_sys_process_vm_readv_wrapper) + lgfr %r2,%r2 # compat_pid_t + llgtr %r3,%r3 # struct compat_iovec __user * + llgfr %r4,%r4 # unsigned long + llgtr %r5,%r5 # struct compat_iovec __user * + llgfr %r6,%r6 # unsigned long + llgf %r0,164(%r15) # unsigned long + stg %r0,160(%r15) + jg sys_process_vm_readv + +ENTRY(compat_sys_process_vm_writev_wrapper) + lgfr %r2,%r2 # compat_pid_t + llgtr %r3,%r3 # struct compat_iovec __user * + llgfr %r4,%r4 # unsigned long + llgtr %r5,%r5 # struct compat_iovec __user * + llgfr %r6,%r6 # unsigned long + llgf %r0,164(%r15) # unsigned long + stg %r0,160(%r15) + jg sys_process_vm_writev diff --git a/arch/s390/kernel/cpcmd.c b/arch/s390/kernel/cpcmd.c new file mode 100644 index 00000000..e3dd886e --- /dev/null +++ b/arch/s390/kernel/cpcmd.c @@ -0,0 +1,125 @@ +/* + * arch/s390/kernel/cpcmd.c + * + * S390 version + * Copyright IBM Corp. 1999,2007 + * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com), + * Christian Borntraeger (cborntra@de.ibm.com), + */ + +#define KMSG_COMPONENT "cpcmd" +#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/spinlock.h> +#include <linux/stddef.h> +#include <linux/string.h> +#include <asm/ebcdic.h> +#include <asm/cpcmd.h> +#include <asm/io.h> + +static DEFINE_SPINLOCK(cpcmd_lock); +static char cpcmd_buf[241]; + +static int diag8_noresponse(int cmdlen) +{ + register unsigned long reg2 asm ("2") = (addr_t) cpcmd_buf; + register unsigned long reg3 asm ("3") = cmdlen; + + asm volatile( +#ifndef CONFIG_64BIT + " diag %1,%0,0x8\n" +#else /* CONFIG_64BIT */ + " sam31\n" + " diag %1,%0,0x8\n" + " sam64\n" +#endif /* CONFIG_64BIT */ + : "+d" (reg3) : "d" (reg2) : "cc"); + return reg3; +} + +static int diag8_response(int cmdlen, char *response, int *rlen) +{ + register unsigned long reg2 asm ("2") = (addr_t) cpcmd_buf; + register unsigned long reg3 asm ("3") = (addr_t) response; + register unsigned long reg4 asm ("4") = cmdlen | 0x40000000L; + register unsigned long reg5 asm ("5") = *rlen; + + asm volatile( +#ifndef CONFIG_64BIT + " diag %2,%0,0x8\n" + " brc 8,1f\n" + " ar %1,%4\n" +#else /* CONFIG_64BIT */ + " sam31\n" + " diag %2,%0,0x8\n" + " sam64\n" + " brc 8,1f\n" + " agr %1,%4\n" +#endif /* CONFIG_64BIT */ + "1:\n" + : "+d" (reg4), "+d" (reg5) + : "d" (reg2), "d" (reg3), "d" (*rlen) : "cc"); + *rlen = reg5; + return reg4; +} + +/* + * __cpcmd has some restrictions over cpcmd + * - the response buffer must reside below 2GB (if any) + * - __cpcmd is unlocked and therefore not SMP-safe + */ +int __cpcmd(const char *cmd, char *response, int rlen, int *response_code) +{ + int cmdlen; + int rc; + int response_len; + + cmdlen = strlen(cmd); + BUG_ON(cmdlen > 240); + memcpy(cpcmd_buf, cmd, cmdlen); + ASCEBC(cpcmd_buf, cmdlen); + + if (response) { + memset(response, 0, rlen); + response_len = rlen; + rc = diag8_response(cmdlen, response, &rlen); + EBCASC(response, response_len); + } else { + rc = diag8_noresponse(cmdlen); + } + if (response_code) + *response_code = rc; + return rlen; +} +EXPORT_SYMBOL(__cpcmd); + +int cpcmd(const char *cmd, char *response, int rlen, int *response_code) +{ + char *lowbuf; + int len; + unsigned long flags; + + if ((virt_to_phys(response) != (unsigned long) response) || + (((unsigned long)response + rlen) >> 31)) { + lowbuf = kmalloc(rlen, GFP_KERNEL | GFP_DMA); + if (!lowbuf) { + pr_warning("The cpcmd kernel function failed to " + "allocate a response buffer\n"); + return -ENOMEM; + } + spin_lock_irqsave(&cpcmd_lock, flags); + len = __cpcmd(cmd, lowbuf, rlen, response_code); + spin_unlock_irqrestore(&cpcmd_lock, flags); + memcpy(response, lowbuf, rlen); + kfree(lowbuf); + } else { + spin_lock_irqsave(&cpcmd_lock, flags); + len = __cpcmd(cmd, response, rlen, response_code); + spin_unlock_irqrestore(&cpcmd_lock, flags); + } + return len; +} +EXPORT_SYMBOL(cpcmd); diff --git a/arch/s390/kernel/crash.c b/arch/s390/kernel/crash.c new file mode 100644 index 00000000..8cc7c9fa --- /dev/null +++ b/arch/s390/kernel/crash.c @@ -0,0 +1,16 @@ +/* + * arch/s390/kernel/crash.c + * + * (C) Copyright IBM Corp. 2005 + * + * Author(s): Heiko Carstens <heiko.carstens@de.ibm.com> + * + */ + +#include <linux/threads.h> +#include <linux/kexec.h> +#include <linux/reboot.h> + +void machine_crash_shutdown(struct pt_regs *regs) +{ +} diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c new file mode 100644 index 00000000..cc1172b2 --- /dev/null +++ b/arch/s390/kernel/crash_dump.c @@ -0,0 +1,442 @@ +/* + * S390 kdump implementation + * + * Copyright IBM Corp. 2011 + * Author(s): Michael Holzheu <holzheu@linux.vnet.ibm.com> + */ + +#include <linux/crash_dump.h> +#include <asm/lowcore.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/gfp.h> +#include <linux/slab.h> +#include <linux/bootmem.h> +#include <linux/elf.h> +#include <asm/ipl.h> +#include <asm/os_info.h> + +#define PTR_ADD(x, y) (((char *) (x)) + ((unsigned long) (y))) +#define PTR_SUB(x, y) (((char *) (x)) - ((unsigned long) (y))) +#define PTR_DIFF(x, y) ((unsigned long)(((char *) (x)) - ((unsigned long) (y)))) + +/* + * Copy one page from "oldmem" + * + * For the kdump reserved memory this functions performs a swap operation: + * - [OLDMEM_BASE - OLDMEM_BASE + OLDMEM_SIZE] is mapped to [0 - OLDMEM_SIZE]. + * - [0 - OLDMEM_SIZE] is mapped to [OLDMEM_BASE - OLDMEM_BASE + OLDMEM_SIZE] + */ +ssize_t copy_oldmem_page(unsigned long pfn, char *buf, + size_t csize, unsigned long offset, int userbuf) +{ + unsigned long src; + + if (!csize) + return 0; + + src = (pfn << PAGE_SHIFT) + offset; + if (src < OLDMEM_SIZE) + src += OLDMEM_BASE; + else if (src > OLDMEM_BASE && + src < OLDMEM_BASE + OLDMEM_SIZE) + src -= OLDMEM_BASE; + if (userbuf) + copy_to_user_real((void __force __user *) buf, (void *) src, + csize); + else + memcpy_real(buf, (void *) src, csize); + return csize; +} + +/* + * Copy memory from old kernel + */ +int copy_from_oldmem(void *dest, void *src, size_t count) +{ + unsigned long copied = 0; + int rc; + + if ((unsigned long) src < OLDMEM_SIZE) { + copied = min(count, OLDMEM_SIZE - (unsigned long) src); + rc = memcpy_real(dest, src + OLDMEM_BASE, copied); + if (rc) + return rc; + } + return memcpy_real(dest + copied, src + copied, count - copied); +} + +/* + * Alloc memory and panic in case of ENOMEM + */ +static void *kzalloc_panic(int len) +{ + void *rc; + + rc = kzalloc(len, GFP_KERNEL); + if (!rc) + panic("s390 kdump kzalloc (%d) failed", len); + return rc; +} + +/* + * Get memory layout and create hole for oldmem + */ +static struct mem_chunk *get_memory_layout(void) +{ + struct mem_chunk *chunk_array; + + chunk_array = kzalloc_panic(MEMORY_CHUNKS * sizeof(struct mem_chunk)); + detect_memory_layout(chunk_array); + create_mem_hole(chunk_array, OLDMEM_BASE, OLDMEM_SIZE, CHUNK_CRASHK); + return chunk_array; +} + +/* + * Initialize ELF note + */ +static void *nt_init(void *buf, Elf64_Word type, void *desc, int d_len, + const char *name) +{ + Elf64_Nhdr *note; + u64 len; + + note = (Elf64_Nhdr *)buf; + note->n_namesz = strlen(name) + 1; + note->n_descsz = d_len; + note->n_type = type; + len = sizeof(Elf64_Nhdr); + + memcpy(buf + len, name, note->n_namesz); + len = roundup(len + note->n_namesz, 4); + + memcpy(buf + len, desc, note->n_descsz); + len = roundup(len + note->n_descsz, 4); + + return PTR_ADD(buf, len); +} + +/* + * Initialize prstatus note + */ +static void *nt_prstatus(void *ptr, struct save_area *sa) +{ + struct elf_prstatus nt_prstatus; + static int cpu_nr = 1; + + memset(&nt_prstatus, 0, sizeof(nt_prstatus)); + memcpy(&nt_prstatus.pr_reg.gprs, sa->gp_regs, sizeof(sa->gp_regs)); + memcpy(&nt_prstatus.pr_reg.psw, sa->psw, sizeof(sa->psw)); + memcpy(&nt_prstatus.pr_reg.acrs, sa->acc_regs, sizeof(sa->acc_regs)); + nt_prstatus.pr_pid = cpu_nr; + cpu_nr++; + + return nt_init(ptr, NT_PRSTATUS, &nt_prstatus, sizeof(nt_prstatus), + "CORE"); +} + +/* + * Initialize fpregset (floating point) note + */ +static void *nt_fpregset(void *ptr, struct save_area *sa) +{ + elf_fpregset_t nt_fpregset; + + memset(&nt_fpregset, 0, sizeof(nt_fpregset)); + memcpy(&nt_fpregset.fpc, &sa->fp_ctrl_reg, sizeof(sa->fp_ctrl_reg)); + memcpy(&nt_fpregset.fprs, &sa->fp_regs, sizeof(sa->fp_regs)); + + return nt_init(ptr, NT_PRFPREG, &nt_fpregset, sizeof(nt_fpregset), + "CORE"); +} + +/* + * Initialize timer note + */ +static void *nt_s390_timer(void *ptr, struct save_area *sa) +{ + return nt_init(ptr, NT_S390_TIMER, &sa->timer, sizeof(sa->timer), + KEXEC_CORE_NOTE_NAME); +} + +/* + * Initialize TOD clock comparator note + */ +static void *nt_s390_tod_cmp(void *ptr, struct save_area *sa) +{ + return nt_init(ptr, NT_S390_TODCMP, &sa->clk_cmp, + sizeof(sa->clk_cmp), KEXEC_CORE_NOTE_NAME); +} + +/* + * Initialize TOD programmable register note + */ +static void *nt_s390_tod_preg(void *ptr, struct save_area *sa) +{ + return nt_init(ptr, NT_S390_TODPREG, &sa->tod_reg, + sizeof(sa->tod_reg), KEXEC_CORE_NOTE_NAME); +} + +/* + * Initialize control register note + */ +static void *nt_s390_ctrs(void *ptr, struct save_area *sa) +{ + return nt_init(ptr, NT_S390_CTRS, &sa->ctrl_regs, + sizeof(sa->ctrl_regs), KEXEC_CORE_NOTE_NAME); +} + +/* + * Initialize prefix register note + */ +static void *nt_s390_prefix(void *ptr, struct save_area *sa) +{ + return nt_init(ptr, NT_S390_PREFIX, &sa->pref_reg, + sizeof(sa->pref_reg), KEXEC_CORE_NOTE_NAME); +} + +/* + * Fill ELF notes for one CPU with save area registers + */ +void *fill_cpu_elf_notes(void *ptr, struct save_area *sa) +{ + ptr = nt_prstatus(ptr, sa); + ptr = nt_fpregset(ptr, sa); + ptr = nt_s390_timer(ptr, sa); + ptr = nt_s390_tod_cmp(ptr, sa); + ptr = nt_s390_tod_preg(ptr, sa); + ptr = nt_s390_ctrs(ptr, sa); + ptr = nt_s390_prefix(ptr, sa); + return ptr; +} + +/* + * Initialize prpsinfo note (new kernel) + */ +static void *nt_prpsinfo(void *ptr) +{ + struct elf_prpsinfo prpsinfo; + + memset(&prpsinfo, 0, sizeof(prpsinfo)); + prpsinfo.pr_sname = 'R'; + strcpy(prpsinfo.pr_fname, "vmlinux"); + return nt_init(ptr, NT_PRPSINFO, &prpsinfo, sizeof(prpsinfo), + KEXEC_CORE_NOTE_NAME); +} + +/* + * Get vmcoreinfo using lowcore->vmcore_info (new kernel) + */ +static void *get_vmcoreinfo_old(unsigned long *size) +{ + char nt_name[11], *vmcoreinfo; + Elf64_Nhdr note; + void *addr; + + if (copy_from_oldmem(&addr, &S390_lowcore.vmcore_info, sizeof(addr))) + return NULL; + memset(nt_name, 0, sizeof(nt_name)); + if (copy_from_oldmem(¬e, addr, sizeof(note))) + return NULL; + if (copy_from_oldmem(nt_name, addr + sizeof(note), sizeof(nt_name) - 1)) + return NULL; + if (strcmp(nt_name, "VMCOREINFO") != 0) + return NULL; + vmcoreinfo = kzalloc_panic(note.n_descsz); + if (copy_from_oldmem(vmcoreinfo, addr + 24, note.n_descsz)) + return NULL; + *size = note.n_descsz; + return vmcoreinfo; +} + +/* + * Initialize vmcoreinfo note (new kernel) + */ +static void *nt_vmcoreinfo(void *ptr) +{ + unsigned long size; + void *vmcoreinfo; + + vmcoreinfo = os_info_old_entry(OS_INFO_VMCOREINFO, &size); + if (!vmcoreinfo) + vmcoreinfo = get_vmcoreinfo_old(&size); + if (!vmcoreinfo) + return ptr; + return nt_init(ptr, 0, vmcoreinfo, size, "VMCOREINFO"); +} + +/* + * Initialize ELF header (new kernel) + */ +static void *ehdr_init(Elf64_Ehdr *ehdr, int mem_chunk_cnt) +{ + memset(ehdr, 0, sizeof(*ehdr)); + memcpy(ehdr->e_ident, ELFMAG, SELFMAG); + ehdr->e_ident[EI_CLASS] = ELFCLASS64; + ehdr->e_ident[EI_DATA] = ELFDATA2MSB; + ehdr->e_ident[EI_VERSION] = EV_CURRENT; + memset(ehdr->e_ident + EI_PAD, 0, EI_NIDENT - EI_PAD); + ehdr->e_type = ET_CORE; + ehdr->e_machine = EM_S390; + ehdr->e_version = EV_CURRENT; + ehdr->e_phoff = sizeof(Elf64_Ehdr); + ehdr->e_ehsize = sizeof(Elf64_Ehdr); + ehdr->e_phentsize = sizeof(Elf64_Phdr); + ehdr->e_phnum = mem_chunk_cnt + 1; + return ehdr + 1; +} + +/* + * Return CPU count for ELF header (new kernel) + */ +static int get_cpu_cnt(void) +{ + int i, cpus = 0; + + for (i = 0; zfcpdump_save_areas[i]; i++) { + if (zfcpdump_save_areas[i]->pref_reg == 0) + continue; + cpus++; + } + return cpus; +} + +/* + * Return memory chunk count for ELF header (new kernel) + */ +static int get_mem_chunk_cnt(void) +{ + struct mem_chunk *chunk_array, *mem_chunk; + int i, cnt = 0; + + chunk_array = get_memory_layout(); + for (i = 0; i < MEMORY_CHUNKS; i++) { + mem_chunk = &chunk_array[i]; + if (chunk_array[i].type != CHUNK_READ_WRITE && + chunk_array[i].type != CHUNK_READ_ONLY) + continue; + if (mem_chunk->size == 0) + continue; + cnt++; + } + kfree(chunk_array); + return cnt; +} + +/* + * Relocate pointer in order to allow vmcore code access the data + */ +static inline unsigned long relocate(unsigned long addr) +{ + return OLDMEM_BASE + addr; +} + +/* + * Initialize ELF loads (new kernel) + */ +static int loads_init(Elf64_Phdr *phdr, u64 loads_offset) +{ + struct mem_chunk *chunk_array, *mem_chunk; + int i; + + chunk_array = get_memory_layout(); + for (i = 0; i < MEMORY_CHUNKS; i++) { + mem_chunk = &chunk_array[i]; + if (mem_chunk->size == 0) + break; + if (chunk_array[i].type != CHUNK_READ_WRITE && + chunk_array[i].type != CHUNK_READ_ONLY) + continue; + else + phdr->p_filesz = mem_chunk->size; + phdr->p_type = PT_LOAD; + phdr->p_offset = mem_chunk->addr; + phdr->p_vaddr = mem_chunk->addr; + phdr->p_paddr = mem_chunk->addr; + phdr->p_memsz = mem_chunk->size; + phdr->p_flags = PF_R | PF_W | PF_X; + phdr->p_align = PAGE_SIZE; + phdr++; + } + kfree(chunk_array); + return i; +} + +/* + * Initialize notes (new kernel) + */ +static void *notes_init(Elf64_Phdr *phdr, void *ptr, u64 notes_offset) +{ + struct save_area *sa; + void *ptr_start = ptr; + int i; + + ptr = nt_prpsinfo(ptr); + + for (i = 0; zfcpdump_save_areas[i]; i++) { + sa = zfcpdump_save_areas[i]; + if (sa->pref_reg == 0) + continue; + ptr = fill_cpu_elf_notes(ptr, sa); + } + ptr = nt_vmcoreinfo(ptr); + memset(phdr, 0, sizeof(*phdr)); + phdr->p_type = PT_NOTE; + phdr->p_offset = relocate(notes_offset); + phdr->p_filesz = (unsigned long) PTR_SUB(ptr, ptr_start); + phdr->p_memsz = phdr->p_filesz; + return ptr; +} + +/* + * Create ELF core header (new kernel) + */ +static void s390_elf_corehdr_create(char **elfcorebuf, size_t *elfcorebuf_sz) +{ + Elf64_Phdr *phdr_notes, *phdr_loads; + int mem_chunk_cnt; + void *ptr, *hdr; + u32 alloc_size; + u64 hdr_off; + + mem_chunk_cnt = get_mem_chunk_cnt(); + + alloc_size = 0x1000 + get_cpu_cnt() * 0x300 + + mem_chunk_cnt * sizeof(Elf64_Phdr); + hdr = kzalloc_panic(alloc_size); + /* Init elf header */ + ptr = ehdr_init(hdr, mem_chunk_cnt); + /* Init program headers */ + phdr_notes = ptr; + ptr = PTR_ADD(ptr, sizeof(Elf64_Phdr)); + phdr_loads = ptr; + ptr = PTR_ADD(ptr, sizeof(Elf64_Phdr) * mem_chunk_cnt); + /* Init notes */ + hdr_off = PTR_DIFF(ptr, hdr); + ptr = notes_init(phdr_notes, ptr, ((unsigned long) hdr) + hdr_off); + /* Init loads */ + hdr_off = PTR_DIFF(ptr, hdr); + loads_init(phdr_loads, ((unsigned long) hdr) + hdr_off); + *elfcorebuf_sz = hdr_off; + *elfcorebuf = (void *) relocate((unsigned long) hdr); + BUG_ON(*elfcorebuf_sz > alloc_size); +} + +/* + * Create kdump ELF core header in new kernel, if it has not been passed via + * the "elfcorehdr" kernel parameter + */ +static int setup_kdump_elfcorehdr(void) +{ + size_t elfcorebuf_sz; + char *elfcorebuf; + + if (!OLDMEM_BASE || is_kdump_kernel()) + return -EINVAL; + s390_elf_corehdr_create(&elfcorebuf, &elfcorebuf_sz); + elfcorehdr_addr = (unsigned long long) elfcorebuf; + elfcorehdr_size = elfcorebuf_sz; + return 0; +} + +subsys_initcall(setup_kdump_elfcorehdr); diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c new file mode 100644 index 00000000..19e5e9eb --- /dev/null +++ b/arch/s390/kernel/debug.c @@ -0,0 +1,1566 @@ +/* + * arch/s390/kernel/debug.c + * S/390 debug facility + * + * Copyright IBM Corp. 1999, 2012 + * + * Author(s): Michael Holzheu (holzheu@de.ibm.com), + * Holger Smolinski (Holger.Smolinski@de.ibm.com) + * + * Bugreports to: <Linux390@de.ibm.com> + */ + +#define KMSG_COMPONENT "s390dbf" +#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt + +#include <linux/stddef.h> +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/slab.h> +#include <linux/ctype.h> +#include <linux/string.h> +#include <linux/sysctl.h> +#include <asm/uaccess.h> +#include <linux/module.h> +#include <linux/init.h> +#include <linux/fs.h> +#include <linux/debugfs.h> + +#include <asm/debug.h> + +#define DEBUG_PROLOG_ENTRY -1 + +#define ALL_AREAS 0 /* copy all debug areas */ +#define NO_AREAS 1 /* copy no debug areas */ + +/* typedefs */ + +typedef struct file_private_info { + loff_t offset; /* offset of last read in file */ + int act_area; /* number of last formated area */ + int act_page; /* act page in given area */ + int act_entry; /* last formated entry (offset */ + /* relative to beginning of last */ + /* formated page) */ + size_t act_entry_offset; /* up to this offset we copied */ + /* in last read the last formated */ + /* entry to userland */ + char temp_buf[2048]; /* buffer for output */ + debug_info_t *debug_info_org; /* original debug information */ + debug_info_t *debug_info_snap; /* snapshot of debug information */ + struct debug_view *view; /* used view of debug info */ +} file_private_info_t; + +typedef struct +{ + char *string; + /* + * This assumes that all args are converted into longs + * on L/390 this is the case for all types of parameter + * except of floats, and long long (32 bit) + * + */ + long args[0]; +} debug_sprintf_entry_t; + + +/* internal function prototyes */ + +static int debug_init(void); +static ssize_t debug_output(struct file *file, char __user *user_buf, + size_t user_len, loff_t * offset); +static ssize_t debug_input(struct file *file, const char __user *user_buf, + size_t user_len, loff_t * offset); +static int debug_open(struct inode *inode, struct file *file); +static int debug_close(struct inode *inode, struct file *file); +static debug_info_t *debug_info_create(const char *name, int pages_per_area, + int nr_areas, int buf_size, umode_t mode); +static void debug_info_get(debug_info_t *); +static void debug_info_put(debug_info_t *); +static int debug_prolog_level_fn(debug_info_t * id, + struct debug_view *view, char *out_buf); +static int debug_input_level_fn(debug_info_t * id, struct debug_view *view, + struct file *file, const char __user *user_buf, + size_t user_buf_size, loff_t * offset); +static int debug_prolog_pages_fn(debug_info_t * id, + struct debug_view *view, char *out_buf); +static int debug_input_pages_fn(debug_info_t * id, struct debug_view *view, + struct file *file, const char __user *user_buf, + size_t user_buf_size, loff_t * offset); +static int debug_input_flush_fn(debug_info_t * id, struct debug_view *view, + struct file *file, const char __user *user_buf, + size_t user_buf_size, loff_t * offset); +static int debug_hex_ascii_format_fn(debug_info_t * id, struct debug_view *view, + char *out_buf, const char *in_buf); +static int debug_raw_format_fn(debug_info_t * id, + struct debug_view *view, char *out_buf, + const char *in_buf); +static int debug_raw_header_fn(debug_info_t * id, struct debug_view *view, + int area, debug_entry_t * entry, char *out_buf); + +static int debug_sprintf_format_fn(debug_info_t * id, struct debug_view *view, + char *out_buf, debug_sprintf_entry_t *curr_event); + +/* globals */ + +struct debug_view debug_raw_view = { + "raw", + NULL, + &debug_raw_header_fn, + &debug_raw_format_fn, + NULL, + NULL +}; + +struct debug_view debug_hex_ascii_view = { + "hex_ascii", + NULL, + &debug_dflt_header_fn, + &debug_hex_ascii_format_fn, + NULL, + NULL +}; + +static struct debug_view debug_level_view = { + "level", + &debug_prolog_level_fn, + NULL, + NULL, + &debug_input_level_fn, + NULL +}; + +static struct debug_view debug_pages_view = { + "pages", + &debug_prolog_pages_fn, + NULL, + NULL, + &debug_input_pages_fn, + NULL +}; + +static struct debug_view debug_flush_view = { + "flush", + NULL, + NULL, + NULL, + &debug_input_flush_fn, + NULL +}; + +struct debug_view debug_sprintf_view = { + "sprintf", + NULL, + &debug_dflt_header_fn, + (debug_format_proc_t*)&debug_sprintf_format_fn, + NULL, + NULL +}; + +/* used by dump analysis tools to determine version of debug feature */ +static unsigned int __used debug_feature_version = __DEBUG_FEATURE_VERSION; + +/* static globals */ + +static debug_info_t *debug_area_first = NULL; +static debug_info_t *debug_area_last = NULL; +static DEFINE_MUTEX(debug_mutex); + +static int initialized; +static int debug_critical; + +static const struct file_operations debug_file_ops = { + .owner = THIS_MODULE, + .read = debug_output, + .write = debug_input, + .open = debug_open, + .release = debug_close, + .llseek = no_llseek, +}; + +static struct dentry *debug_debugfs_root_entry; + +/* functions */ + +/* + * debug_areas_alloc + * - Debug areas are implemented as a threedimensonal array: + * areas[areanumber][pagenumber][pageoffset] + */ + +static debug_entry_t*** +debug_areas_alloc(int pages_per_area, int nr_areas) +{ + debug_entry_t*** areas; + int i,j; + + areas = kmalloc(nr_areas * + sizeof(debug_entry_t**), + GFP_KERNEL); + if (!areas) + goto fail_malloc_areas; + for (i = 0; i < nr_areas; i++) { + areas[i] = kmalloc(pages_per_area * + sizeof(debug_entry_t*),GFP_KERNEL); + if (!areas[i]) { + goto fail_malloc_areas2; + } + for(j = 0; j < pages_per_area; j++) { + areas[i][j] = kzalloc(PAGE_SIZE, GFP_KERNEL); + if(!areas[i][j]) { + for(j--; j >=0 ; j--) { + kfree(areas[i][j]); + } + kfree(areas[i]); + goto fail_malloc_areas2; + } + } + } + return areas; + +fail_malloc_areas2: + for(i--; i >= 0; i--){ + for(j=0; j < pages_per_area;j++){ + kfree(areas[i][j]); + } + kfree(areas[i]); + } + kfree(areas); +fail_malloc_areas: + return NULL; + +} + + +/* + * debug_info_alloc + * - alloc new debug-info + */ + +static debug_info_t* +debug_info_alloc(const char *name, int pages_per_area, int nr_areas, + int buf_size, int level, int mode) +{ + debug_info_t* rc; + + /* alloc everything */ + + rc = kmalloc(sizeof(debug_info_t), GFP_KERNEL); + if(!rc) + goto fail_malloc_rc; + rc->active_entries = kcalloc(nr_areas, sizeof(int), GFP_KERNEL); + if(!rc->active_entries) + goto fail_malloc_active_entries; + rc->active_pages = kcalloc(nr_areas, sizeof(int), GFP_KERNEL); + if(!rc->active_pages) + goto fail_malloc_active_pages; + if((mode == ALL_AREAS) && (pages_per_area != 0)){ + rc->areas = debug_areas_alloc(pages_per_area, nr_areas); + if(!rc->areas) + goto fail_malloc_areas; + } else { + rc->areas = NULL; + } + + /* initialize members */ + + spin_lock_init(&rc->lock); + rc->pages_per_area = pages_per_area; + rc->nr_areas = nr_areas; + rc->active_area = 0; + rc->level = level; + rc->buf_size = buf_size; + rc->entry_size = sizeof(debug_entry_t) + buf_size; + strlcpy(rc->name, name, sizeof(rc->name)); + memset(rc->views, 0, DEBUG_MAX_VIEWS * sizeof(struct debug_view *)); + memset(rc->debugfs_entries, 0 ,DEBUG_MAX_VIEWS * + sizeof(struct dentry*)); + atomic_set(&(rc->ref_count), 0); + + return rc; + +fail_malloc_areas: + kfree(rc->active_pages); +fail_malloc_active_pages: + kfree(rc->active_entries); +fail_malloc_active_entries: + kfree(rc); +fail_malloc_rc: + return NULL; +} + +/* + * debug_areas_free + * - free all debug areas + */ + +static void +debug_areas_free(debug_info_t* db_info) +{ + int i,j; + + if(!db_info->areas) + return; + for (i = 0; i < db_info->nr_areas; i++) { + for(j = 0; j < db_info->pages_per_area; j++) { + kfree(db_info->areas[i][j]); + } + kfree(db_info->areas[i]); + } + kfree(db_info->areas); + db_info->areas = NULL; +} + +/* + * debug_info_free + * - free memory debug-info + */ + +static void +debug_info_free(debug_info_t* db_info){ + debug_areas_free(db_info); + kfree(db_info->active_entries); + kfree(db_info->active_pages); + kfree(db_info); +} + +/* + * debug_info_create + * - create new debug-info + */ + +static debug_info_t* +debug_info_create(const char *name, int pages_per_area, int nr_areas, + int buf_size, umode_t mode) +{ + debug_info_t* rc; + + rc = debug_info_alloc(name, pages_per_area, nr_areas, buf_size, + DEBUG_DEFAULT_LEVEL, ALL_AREAS); + if(!rc) + goto out; + + rc->mode = mode & ~S_IFMT; + + /* create root directory */ + rc->debugfs_root_entry = debugfs_create_dir(rc->name, + debug_debugfs_root_entry); + + /* append new element to linked list */ + if (!debug_area_first) { + /* first element in list */ + debug_area_first = rc; + rc->prev = NULL; + } else { + /* append element to end of list */ + debug_area_last->next = rc; + rc->prev = debug_area_last; + } + debug_area_last = rc; + rc->next = NULL; + + debug_info_get(rc); +out: + return rc; +} + +/* + * debug_info_copy + * - copy debug-info + */ + +static debug_info_t* +debug_info_copy(debug_info_t* in, int mode) +{ + int i,j; + debug_info_t* rc; + unsigned long flags; + + /* get a consistent copy of the debug areas */ + do { + rc = debug_info_alloc(in->name, in->pages_per_area, + in->nr_areas, in->buf_size, in->level, mode); + spin_lock_irqsave(&in->lock, flags); + if(!rc) + goto out; + /* has something changed in the meantime ? */ + if((rc->pages_per_area == in->pages_per_area) && + (rc->nr_areas == in->nr_areas)) { + break; + } + spin_unlock_irqrestore(&in->lock, flags); + debug_info_free(rc); + } while (1); + + if (mode == NO_AREAS) + goto out; + + for(i = 0; i < in->nr_areas; i++){ + for(j = 0; j < in->pages_per_area; j++) { + memcpy(rc->areas[i][j], in->areas[i][j],PAGE_SIZE); + } + } +out: + spin_unlock_irqrestore(&in->lock, flags); + return rc; +} + +/* + * debug_info_get + * - increments reference count for debug-info + */ + +static void +debug_info_get(debug_info_t * db_info) +{ + if (db_info) + atomic_inc(&db_info->ref_count); +} + +/* + * debug_info_put: + * - decreases reference count for debug-info and frees it if necessary + */ + +static void +debug_info_put(debug_info_t *db_info) +{ + int i; + + if (!db_info) + return; + if (atomic_dec_and_test(&db_info->ref_count)) { + for (i = 0; i < DEBUG_MAX_VIEWS; i++) { + if (!db_info->views[i]) + continue; + debugfs_remove(db_info->debugfs_entries[i]); + } + debugfs_remove(db_info->debugfs_root_entry); + if(db_info == debug_area_first) + debug_area_first = db_info->next; + if(db_info == debug_area_last) + debug_area_last = db_info->prev; + if(db_info->prev) db_info->prev->next = db_info->next; + if(db_info->next) db_info->next->prev = db_info->prev; + debug_info_free(db_info); + } +} + +/* + * debug_format_entry: + * - format one debug entry and return size of formated data + */ + +static int +debug_format_entry(file_private_info_t *p_info) +{ + debug_info_t *id_snap = p_info->debug_info_snap; + struct debug_view *view = p_info->view; + debug_entry_t *act_entry; + size_t len = 0; + if(p_info->act_entry == DEBUG_PROLOG_ENTRY){ + /* print prolog */ + if (view->prolog_proc) + len += view->prolog_proc(id_snap,view,p_info->temp_buf); + goto out; + } + if (!id_snap->areas) /* this is true, if we have a prolog only view */ + goto out; /* or if 'pages_per_area' is 0 */ + act_entry = (debug_entry_t *) ((char*)id_snap->areas[p_info->act_area] + [p_info->act_page] + p_info->act_entry); + + if (act_entry->id.stck == 0LL) + goto out; /* empty entry */ + if (view->header_proc) + len += view->header_proc(id_snap, view, p_info->act_area, + act_entry, p_info->temp_buf + len); + if (view->format_proc) + len += view->format_proc(id_snap, view, p_info->temp_buf + len, + DEBUG_DATA(act_entry)); +out: + return len; +} + +/* + * debug_next_entry: + * - goto next entry in p_info + */ + +static inline int +debug_next_entry(file_private_info_t *p_info) +{ + debug_info_t *id; + + id = p_info->debug_info_snap; + if(p_info->act_entry == DEBUG_PROLOG_ENTRY){ + p_info->act_entry = 0; + p_info->act_page = 0; + goto out; + } + if(!id->areas) + return 1; + p_info->act_entry += id->entry_size; + /* switch to next page, if we reached the end of the page */ + if (p_info->act_entry > (PAGE_SIZE - id->entry_size)){ + /* next page */ + p_info->act_entry = 0; + p_info->act_page += 1; + if((p_info->act_page % id->pages_per_area) == 0) { + /* next area */ + p_info->act_area++; + p_info->act_page=0; + } + if(p_info->act_area >= id->nr_areas) + return 1; + } +out: + return 0; +} + +/* + * debug_output: + * - called for user read() + * - copies formated debug entries to the user buffer + */ + +static ssize_t +debug_output(struct file *file, /* file descriptor */ + char __user *user_buf, /* user buffer */ + size_t len, /* length of buffer */ + loff_t *offset) /* offset in the file */ +{ + size_t count = 0; + size_t entry_offset; + file_private_info_t *p_info; + + p_info = ((file_private_info_t *) file->private_data); + if (*offset != p_info->offset) + return -EPIPE; + if(p_info->act_area >= p_info->debug_info_snap->nr_areas) + return 0; + entry_offset = p_info->act_entry_offset; + while(count < len){ + int formatted_line_size; + int formatted_line_residue; + int user_buf_residue; + size_t copy_size; + + formatted_line_size = debug_format_entry(p_info); + formatted_line_residue = formatted_line_size - entry_offset; + user_buf_residue = len-count; + copy_size = min(user_buf_residue, formatted_line_residue); + if(copy_size){ + if (copy_to_user(user_buf + count, p_info->temp_buf + + entry_offset, copy_size)) + return -EFAULT; + count += copy_size; + entry_offset += copy_size; + } + if(copy_size == formatted_line_residue){ + entry_offset = 0; + if(debug_next_entry(p_info)) + goto out; + } + } +out: + p_info->offset = *offset + count; + p_info->act_entry_offset = entry_offset; + *offset = p_info->offset; + return count; +} + +/* + * debug_input: + * - called for user write() + * - calls input function of view + */ + +static ssize_t +debug_input(struct file *file, const char __user *user_buf, size_t length, + loff_t *offset) +{ + int rc = 0; + file_private_info_t *p_info; + + mutex_lock(&debug_mutex); + p_info = ((file_private_info_t *) file->private_data); + if (p_info->view->input_proc) + rc = p_info->view->input_proc(p_info->debug_info_org, + p_info->view, file, user_buf, + length, offset); + else + rc = -EPERM; + mutex_unlock(&debug_mutex); + return rc; /* number of input characters */ +} + +/* + * debug_open: + * - called for user open() + * - copies formated output to private_data area of the file + * handle + */ + +static int +debug_open(struct inode *inode, struct file *file) +{ + int i, rc = 0; + file_private_info_t *p_info; + debug_info_t *debug_info, *debug_info_snapshot; + + mutex_lock(&debug_mutex); + debug_info = file->f_path.dentry->d_inode->i_private; + /* find debug view */ + for (i = 0; i < DEBUG_MAX_VIEWS; i++) { + if (!debug_info->views[i]) + continue; + else if (debug_info->debugfs_entries[i] == + file->f_path.dentry) { + goto found; /* found view ! */ + } + } + /* no entry found */ + rc = -EINVAL; + goto out; + +found: + + /* Make snapshot of current debug areas to get it consistent. */ + /* To copy all the areas is only needed, if we have a view which */ + /* formats the debug areas. */ + + if(!debug_info->views[i]->format_proc && + !debug_info->views[i]->header_proc){ + debug_info_snapshot = debug_info_copy(debug_info, NO_AREAS); + } else { + debug_info_snapshot = debug_info_copy(debug_info, ALL_AREAS); + } + + if(!debug_info_snapshot){ + rc = -ENOMEM; + goto out; + } + p_info = kmalloc(sizeof(file_private_info_t), + GFP_KERNEL); + if(!p_info){ + debug_info_free(debug_info_snapshot); + rc = -ENOMEM; + goto out; + } + p_info->offset = 0; + p_info->debug_info_snap = debug_info_snapshot; + p_info->debug_info_org = debug_info; + p_info->view = debug_info->views[i]; + p_info->act_area = 0; + p_info->act_page = 0; + p_info->act_entry = DEBUG_PROLOG_ENTRY; + p_info->act_entry_offset = 0; + file->private_data = p_info; + debug_info_get(debug_info); + nonseekable_open(inode, file); +out: + mutex_unlock(&debug_mutex); + return rc; +} + +/* + * debug_close: + * - called for user close() + * - deletes private_data area of the file handle + */ + +static int +debug_close(struct inode *inode, struct file *file) +{ + file_private_info_t *p_info; + p_info = (file_private_info_t *) file->private_data; + if(p_info->debug_info_snap) + debug_info_free(p_info->debug_info_snap); + debug_info_put(p_info->debug_info_org); + kfree(file->private_data); + return 0; /* success */ +} + +/* + * debug_register_mode: + * - Creates and initializes debug area for the caller + * The mode parameter allows to specify access rights for the s390dbf files + * - Returns handle for debug area + */ + +debug_info_t *debug_register_mode(const char *name, int pages_per_area, + int nr_areas, int buf_size, umode_t mode, + uid_t uid, gid_t gid) +{ + debug_info_t *rc = NULL; + + /* Since debugfs currently does not support uid/gid other than root, */ + /* we do not allow gid/uid != 0 until we get support for that. */ + if ((uid != 0) || (gid != 0)) + pr_warning("Root becomes the owner of all s390dbf files " + "in sysfs\n"); + BUG_ON(!initialized); + mutex_lock(&debug_mutex); + + /* create new debug_info */ + + rc = debug_info_create(name, pages_per_area, nr_areas, buf_size, mode); + if(!rc) + goto out; + debug_register_view(rc, &debug_level_view); + debug_register_view(rc, &debug_flush_view); + debug_register_view(rc, &debug_pages_view); +out: + if (!rc){ + pr_err("Registering debug feature %s failed\n", name); + } + mutex_unlock(&debug_mutex); + return rc; +} +EXPORT_SYMBOL(debug_register_mode); + +/* + * debug_register: + * - creates and initializes debug area for the caller + * - returns handle for debug area + */ + +debug_info_t *debug_register(const char *name, int pages_per_area, + int nr_areas, int buf_size) +{ + return debug_register_mode(name, pages_per_area, nr_areas, buf_size, + S_IRUSR | S_IWUSR, 0, 0); +} + +/* + * debug_unregister: + * - give back debug area + */ + +void +debug_unregister(debug_info_t * id) +{ + if (!id) + goto out; + mutex_lock(&debug_mutex); + debug_info_put(id); + mutex_unlock(&debug_mutex); + +out: + return; +} + +/* + * debug_set_size: + * - set area size (number of pages) and number of areas + */ +static int +debug_set_size(debug_info_t* id, int nr_areas, int pages_per_area) +{ + unsigned long flags; + debug_entry_t *** new_areas; + int rc=0; + + if(!id || (nr_areas <= 0) || (pages_per_area < 0)) + return -EINVAL; + if(pages_per_area > 0){ + new_areas = debug_areas_alloc(pages_per_area, nr_areas); + if(!new_areas) { + pr_info("Allocating memory for %i pages failed\n", + pages_per_area); + rc = -ENOMEM; + goto out; + } + } else { + new_areas = NULL; + } + spin_lock_irqsave(&id->lock,flags); + debug_areas_free(id); + id->areas = new_areas; + id->nr_areas = nr_areas; + id->pages_per_area = pages_per_area; + id->active_area = 0; + memset(id->active_entries,0,sizeof(int)*id->nr_areas); + memset(id->active_pages, 0, sizeof(int)*id->nr_areas); + spin_unlock_irqrestore(&id->lock,flags); + pr_info("%s: set new size (%i pages)\n" ,id->name, pages_per_area); +out: + return rc; +} + +/* + * debug_set_level: + * - set actual debug level + */ + +void +debug_set_level(debug_info_t* id, int new_level) +{ + unsigned long flags; + if(!id) + return; + spin_lock_irqsave(&id->lock,flags); + if(new_level == DEBUG_OFF_LEVEL){ + id->level = DEBUG_OFF_LEVEL; + pr_info("%s: switched off\n",id->name); + } else if ((new_level > DEBUG_MAX_LEVEL) || (new_level < 0)) { + pr_info("%s: level %i is out of range (%i - %i)\n", + id->name, new_level, 0, DEBUG_MAX_LEVEL); + } else { + id->level = new_level; + } + spin_unlock_irqrestore(&id->lock,flags); +} + + +/* + * proceed_active_entry: + * - set active entry to next in the ring buffer + */ + +static inline void +proceed_active_entry(debug_info_t * id) +{ + if ((id->active_entries[id->active_area] += id->entry_size) + > (PAGE_SIZE - id->entry_size)){ + id->active_entries[id->active_area] = 0; + id->active_pages[id->active_area] = + (id->active_pages[id->active_area] + 1) % + id->pages_per_area; + } +} + +/* + * proceed_active_area: + * - set active area to next in the ring buffer + */ + +static inline void +proceed_active_area(debug_info_t * id) +{ + id->active_area++; + id->active_area = id->active_area % id->nr_areas; +} + +/* + * get_active_entry: + */ + +static inline debug_entry_t* +get_active_entry(debug_info_t * id) +{ + return (debug_entry_t *) (((char *) id->areas[id->active_area] + [id->active_pages[id->active_area]]) + + id->active_entries[id->active_area]); +} + +/* + * debug_finish_entry: + * - set timestamp, caller address, cpu number etc. + */ + +static inline void +debug_finish_entry(debug_info_t * id, debug_entry_t* active, int level, + int exception) +{ + active->id.stck = get_clock(); + active->id.fields.cpuid = smp_processor_id(); + active->caller = __builtin_return_address(0); + active->id.fields.exception = exception; + active->id.fields.level = level; + proceed_active_entry(id); + if(exception) + proceed_active_area(id); +} + +static int debug_stoppable=1; +static int debug_active=1; + +#define CTL_S390DBF_STOPPABLE 5678 +#define CTL_S390DBF_ACTIVE 5679 + +/* + * proc handler for the running debug_active sysctl + * always allow read, allow write only if debug_stoppable is set or + * if debug_active is already off + */ +static int +s390dbf_procactive(ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + if (!write || debug_stoppable || !debug_active) + return proc_dointvec(table, write, buffer, lenp, ppos); + else + return 0; +} + + +static struct ctl_table s390dbf_table[] = { + { + .procname = "debug_stoppable", + .data = &debug_stoppable, + .maxlen = sizeof(int), + .mode = S_IRUGO | S_IWUSR, + .proc_handler = proc_dointvec, + }, + { + .procname = "debug_active", + .data = &debug_active, + .maxlen = sizeof(int), + .mode = S_IRUGO | S_IWUSR, + .proc_handler = s390dbf_procactive, + }, + { } +}; + +static struct ctl_table s390dbf_dir_table[] = { + { + .procname = "s390dbf", + .maxlen = 0, + .mode = S_IRUGO | S_IXUGO, + .child = s390dbf_table, + }, + { } +}; + +static struct ctl_table_header *s390dbf_sysctl_header; + +void +debug_stop_all(void) +{ + if (debug_stoppable) + debug_active = 0; +} + + +void debug_set_critical(void) +{ + debug_critical = 1; +} + +/* + * debug_event_common: + * - write debug entry with given size + */ + +debug_entry_t* +debug_event_common(debug_info_t * id, int level, const void *buf, int len) +{ + unsigned long flags; + debug_entry_t *active; + + if (!debug_active || !id->areas) + return NULL; + if (debug_critical) { + if (!spin_trylock_irqsave(&id->lock, flags)) + return NULL; + } else + spin_lock_irqsave(&id->lock, flags); + active = get_active_entry(id); + memset(DEBUG_DATA(active), 0, id->buf_size); + memcpy(DEBUG_DATA(active), buf, min(len, id->buf_size)); + debug_finish_entry(id, active, level, 0); + spin_unlock_irqrestore(&id->lock, flags); + + return active; +} + +/* + * debug_exception_common: + * - write debug entry with given size and switch to next debug area + */ + +debug_entry_t +*debug_exception_common(debug_info_t * id, int level, const void *buf, int len) +{ + unsigned long flags; + debug_entry_t *active; + + if (!debug_active || !id->areas) + return NULL; + if (debug_critical) { + if (!spin_trylock_irqsave(&id->lock, flags)) + return NULL; + } else + spin_lock_irqsave(&id->lock, flags); + active = get_active_entry(id); + memset(DEBUG_DATA(active), 0, id->buf_size); + memcpy(DEBUG_DATA(active), buf, min(len, id->buf_size)); + debug_finish_entry(id, active, level, 1); + spin_unlock_irqrestore(&id->lock, flags); + + return active; +} + +/* + * counts arguments in format string for sprintf view + */ + +static inline int +debug_count_numargs(char *string) +{ + int numargs=0; + + while(*string) { + if(*string++=='%') + numargs++; + } + return(numargs); +} + +/* + * debug_sprintf_event: + */ + +debug_entry_t* +debug_sprintf_event(debug_info_t* id, int level,char *string,...) +{ + va_list ap; + int numargs,idx; + unsigned long flags; + debug_sprintf_entry_t *curr_event; + debug_entry_t *active; + + if((!id) || (level > id->level)) + return NULL; + if (!debug_active || !id->areas) + return NULL; + numargs=debug_count_numargs(string); + + if (debug_critical) { + if (!spin_trylock_irqsave(&id->lock, flags)) + return NULL; + } else + spin_lock_irqsave(&id->lock, flags); + active = get_active_entry(id); + curr_event=(debug_sprintf_entry_t *) DEBUG_DATA(active); + va_start(ap,string); + curr_event->string=string; + for(idx=0;idx<min(numargs,(int)(id->buf_size / sizeof(long))-1);idx++) + curr_event->args[idx]=va_arg(ap,long); + va_end(ap); + debug_finish_entry(id, active, level, 0); + spin_unlock_irqrestore(&id->lock, flags); + + return active; +} + +/* + * debug_sprintf_exception: + */ + +debug_entry_t* +debug_sprintf_exception(debug_info_t* id, int level,char *string,...) +{ + va_list ap; + int numargs,idx; + unsigned long flags; + debug_sprintf_entry_t *curr_event; + debug_entry_t *active; + + if((!id) || (level > id->level)) + return NULL; + if (!debug_active || !id->areas) + return NULL; + + numargs=debug_count_numargs(string); + + if (debug_critical) { + if (!spin_trylock_irqsave(&id->lock, flags)) + return NULL; + } else + spin_lock_irqsave(&id->lock, flags); + active = get_active_entry(id); + curr_event=(debug_sprintf_entry_t *)DEBUG_DATA(active); + va_start(ap,string); + curr_event->string=string; + for(idx=0;idx<min(numargs,(int)(id->buf_size / sizeof(long))-1);idx++) + curr_event->args[idx]=va_arg(ap,long); + va_end(ap); + debug_finish_entry(id, active, level, 1); + spin_unlock_irqrestore(&id->lock, flags); + + return active; +} + +/* + * debug_init: + * - is called exactly once to initialize the debug feature + */ + +static int +__init debug_init(void) +{ + int rc = 0; + + s390dbf_sysctl_header = register_sysctl_table(s390dbf_dir_table); + mutex_lock(&debug_mutex); + debug_debugfs_root_entry = debugfs_create_dir(DEBUG_DIR_ROOT,NULL); + initialized = 1; + mutex_unlock(&debug_mutex); + + return rc; +} + +/* + * debug_register_view: + */ + +int +debug_register_view(debug_info_t * id, struct debug_view *view) +{ + int rc = 0; + int i; + unsigned long flags; + umode_t mode; + struct dentry *pde; + + if (!id) + goto out; + mode = (id->mode | S_IFREG) & ~S_IXUGO; + if (!(view->prolog_proc || view->format_proc || view->header_proc)) + mode &= ~(S_IRUSR | S_IRGRP | S_IROTH); + if (!view->input_proc) + mode &= ~(S_IWUSR | S_IWGRP | S_IWOTH); + pde = debugfs_create_file(view->name, mode, id->debugfs_root_entry, + id , &debug_file_ops); + if (!pde){ + pr_err("Registering view %s/%s failed due to out of " + "memory\n", id->name,view->name); + rc = -1; + goto out; + } + spin_lock_irqsave(&id->lock, flags); + for (i = 0; i < DEBUG_MAX_VIEWS; i++) { + if (!id->views[i]) + break; + } + if (i == DEBUG_MAX_VIEWS) { + pr_err("Registering view %s/%s would exceed the maximum " + "number of views %i\n", id->name, view->name, i); + debugfs_remove(pde); + rc = -1; + } else { + id->views[i] = view; + id->debugfs_entries[i] = pde; + } + spin_unlock_irqrestore(&id->lock, flags); +out: + return rc; +} + +/* + * debug_unregister_view: + */ + +int +debug_unregister_view(debug_info_t * id, struct debug_view *view) +{ + int rc = 0; + int i; + unsigned long flags; + + if (!id) + goto out; + spin_lock_irqsave(&id->lock, flags); + for (i = 0; i < DEBUG_MAX_VIEWS; i++) { + if (id->views[i] == view) + break; + } + if (i == DEBUG_MAX_VIEWS) + rc = -1; + else { + debugfs_remove(id->debugfs_entries[i]); + id->views[i] = NULL; + } + spin_unlock_irqrestore(&id->lock, flags); +out: + return rc; +} + +static inline char * +debug_get_user_string(const char __user *user_buf, size_t user_len) +{ + char* buffer; + + buffer = kmalloc(user_len + 1, GFP_KERNEL); + if (!buffer) + return ERR_PTR(-ENOMEM); + if (copy_from_user(buffer, user_buf, user_len) != 0) { + kfree(buffer); + return ERR_PTR(-EFAULT); + } + /* got the string, now strip linefeed. */ + if (buffer[user_len - 1] == '\n') + buffer[user_len - 1] = 0; + else + buffer[user_len] = 0; + return buffer; +} + +static inline int +debug_get_uint(char *buf) +{ + int rc; + + buf = skip_spaces(buf); + rc = simple_strtoul(buf, &buf, 10); + if(*buf){ + rc = -EINVAL; + } + return rc; +} + +/* + * functions for debug-views + *********************************** +*/ + +/* + * prints out actual debug level + */ + +static int +debug_prolog_pages_fn(debug_info_t * id, + struct debug_view *view, char *out_buf) +{ + return sprintf(out_buf, "%i\n", id->pages_per_area); +} + +/* + * reads new size (number of pages per debug area) + */ + +static int +debug_input_pages_fn(debug_info_t * id, struct debug_view *view, + struct file *file, const char __user *user_buf, + size_t user_len, loff_t * offset) +{ + char *str; + int rc,new_pages; + + if (user_len > 0x10000) + user_len = 0x10000; + if (*offset != 0){ + rc = -EPIPE; + goto out; + } + str = debug_get_user_string(user_buf,user_len); + if(IS_ERR(str)){ + rc = PTR_ERR(str); + goto out; + } + new_pages = debug_get_uint(str); + if(new_pages < 0){ + rc = -EINVAL; + goto free_str; + } + rc = debug_set_size(id,id->nr_areas, new_pages); + if(rc != 0){ + rc = -EINVAL; + goto free_str; + } + rc = user_len; +free_str: + kfree(str); +out: + *offset += user_len; + return rc; /* number of input characters */ +} + +/* + * prints out actual debug level + */ + +static int +debug_prolog_level_fn(debug_info_t * id, struct debug_view *view, char *out_buf) +{ + int rc = 0; + + if(id->level == DEBUG_OFF_LEVEL) { + rc = sprintf(out_buf,"-\n"); + } + else { + rc = sprintf(out_buf, "%i\n", id->level); + } + return rc; +} + +/* + * reads new debug level + */ + +static int +debug_input_level_fn(debug_info_t * id, struct debug_view *view, + struct file *file, const char __user *user_buf, + size_t user_len, loff_t * offset) +{ + char *str; + int rc,new_level; + + if (user_len > 0x10000) + user_len = 0x10000; + if (*offset != 0){ + rc = -EPIPE; + goto out; + } + str = debug_get_user_string(user_buf,user_len); + if(IS_ERR(str)){ + rc = PTR_ERR(str); + goto out; + } + if(str[0] == '-'){ + debug_set_level(id, DEBUG_OFF_LEVEL); + rc = user_len; + goto free_str; + } else { + new_level = debug_get_uint(str); + } + if(new_level < 0) { + pr_warning("%s is not a valid level for a debug " + "feature\n", str); + rc = -EINVAL; + } else { + debug_set_level(id, new_level); + rc = user_len; + } +free_str: + kfree(str); +out: + *offset += user_len; + return rc; /* number of input characters */ +} + + +/* + * flushes debug areas + */ + +static void debug_flush(debug_info_t* id, int area) +{ + unsigned long flags; + int i,j; + + if(!id || !id->areas) + return; + spin_lock_irqsave(&id->lock,flags); + if(area == DEBUG_FLUSH_ALL){ + id->active_area = 0; + memset(id->active_entries, 0, id->nr_areas * sizeof(int)); + for (i = 0; i < id->nr_areas; i++) { + id->active_pages[i] = 0; + for(j = 0; j < id->pages_per_area; j++) { + memset(id->areas[i][j], 0, PAGE_SIZE); + } + } + } else if(area >= 0 && area < id->nr_areas) { + id->active_entries[area] = 0; + id->active_pages[area] = 0; + for(i = 0; i < id->pages_per_area; i++) { + memset(id->areas[area][i],0,PAGE_SIZE); + } + } + spin_unlock_irqrestore(&id->lock,flags); +} + +/* + * view function: flushes debug areas + */ + +static int +debug_input_flush_fn(debug_info_t * id, struct debug_view *view, + struct file *file, const char __user *user_buf, + size_t user_len, loff_t * offset) +{ + char input_buf[1]; + int rc = user_len; + + if (user_len > 0x10000) + user_len = 0x10000; + if (*offset != 0){ + rc = -EPIPE; + goto out; + } + if (copy_from_user(input_buf, user_buf, 1)){ + rc = -EFAULT; + goto out; + } + if(input_buf[0] == '-') { + debug_flush(id, DEBUG_FLUSH_ALL); + goto out; + } + if (isdigit(input_buf[0])) { + int area = ((int) input_buf[0] - (int) '0'); + debug_flush(id, area); + goto out; + } + + pr_info("Flushing debug data failed because %c is not a valid " + "area\n", input_buf[0]); + +out: + *offset += user_len; + return rc; /* number of input characters */ +} + +/* + * prints debug header in raw format + */ + +static int +debug_raw_header_fn(debug_info_t * id, struct debug_view *view, + int area, debug_entry_t * entry, char *out_buf) +{ + int rc; + + rc = sizeof(debug_entry_t); + memcpy(out_buf,entry,sizeof(debug_entry_t)); + return rc; +} + +/* + * prints debug data in raw format + */ + +static int +debug_raw_format_fn(debug_info_t * id, struct debug_view *view, + char *out_buf, const char *in_buf) +{ + int rc; + + rc = id->buf_size; + memcpy(out_buf, in_buf, id->buf_size); + return rc; +} + +/* + * prints debug data in hex/ascii format + */ + +static int +debug_hex_ascii_format_fn(debug_info_t * id, struct debug_view *view, + char *out_buf, const char *in_buf) +{ + int i, rc = 0; + + for (i = 0; i < id->buf_size; i++) { + rc += sprintf(out_buf + rc, "%02x ", + ((unsigned char *) in_buf)[i]); + } + rc += sprintf(out_buf + rc, "| "); + for (i = 0; i < id->buf_size; i++) { + unsigned char c = in_buf[i]; + if (isascii(c) && isprint(c)) + rc += sprintf(out_buf + rc, "%c", c); + else + rc += sprintf(out_buf + rc, "."); + } + rc += sprintf(out_buf + rc, "\n"); + return rc; +} + +/* + * prints header for debug entry + */ + +int +debug_dflt_header_fn(debug_info_t * id, struct debug_view *view, + int area, debug_entry_t * entry, char *out_buf) +{ + struct timespec time_spec; + char *except_str; + unsigned long caller; + int rc = 0; + unsigned int level; + + level = entry->id.fields.level; + stck_to_timespec(entry->id.stck, &time_spec); + + if (entry->id.fields.exception) + except_str = "*"; + else + except_str = "-"; + caller = ((unsigned long) entry->caller) & PSW_ADDR_INSN; + rc += sprintf(out_buf, "%02i %011lu:%06lu %1u %1s %02i %p ", + area, time_spec.tv_sec, time_spec.tv_nsec / 1000, level, + except_str, entry->id.fields.cpuid, (void *) caller); + return rc; +} + +/* + * prints debug data sprintf-formated: + * debug_sprinf_event/exception calls must be used together with this view + */ + +#define DEBUG_SPRINTF_MAX_ARGS 10 + +static int +debug_sprintf_format_fn(debug_info_t * id, struct debug_view *view, + char *out_buf, debug_sprintf_entry_t *curr_event) +{ + int num_longs, num_used_args = 0,i, rc = 0; + int index[DEBUG_SPRINTF_MAX_ARGS]; + + /* count of longs fit into one entry */ + num_longs = id->buf_size / sizeof(long); + + if(num_longs < 1) + goto out; /* bufsize of entry too small */ + if(num_longs == 1) { + /* no args, we use only the string */ + strcpy(out_buf, curr_event->string); + rc = strlen(curr_event->string); + goto out; + } + + /* number of arguments used for sprintf (without the format string) */ + num_used_args = min(DEBUG_SPRINTF_MAX_ARGS, (num_longs - 1)); + + memset(index,0, DEBUG_SPRINTF_MAX_ARGS * sizeof(int)); + + for(i = 0; i < num_used_args; i++) + index[i] = i; + + rc = sprintf(out_buf, curr_event->string, curr_event->args[index[0]], + curr_event->args[index[1]], curr_event->args[index[2]], + curr_event->args[index[3]], curr_event->args[index[4]], + curr_event->args[index[5]], curr_event->args[index[6]], + curr_event->args[index[7]], curr_event->args[index[8]], + curr_event->args[index[9]]); + +out: + + return rc; +} + +/* + * clean up module + */ +static void __exit debug_exit(void) +{ + debugfs_remove(debug_debugfs_root_entry); + unregister_sysctl_table(s390dbf_sysctl_header); + return; +} + +/* + * module definitions + */ +postcore_initcall(debug_init); +module_exit(debug_exit); +MODULE_LICENSE("GPL"); + +EXPORT_SYMBOL(debug_register); +EXPORT_SYMBOL(debug_unregister); +EXPORT_SYMBOL(debug_set_level); +EXPORT_SYMBOL(debug_stop_all); +EXPORT_SYMBOL(debug_register_view); +EXPORT_SYMBOL(debug_unregister_view); +EXPORT_SYMBOL(debug_event_common); +EXPORT_SYMBOL(debug_exception_common); +EXPORT_SYMBOL(debug_hex_ascii_view); +EXPORT_SYMBOL(debug_raw_view); +EXPORT_SYMBOL(debug_dflt_header_fn); +EXPORT_SYMBOL(debug_sprintf_view); +EXPORT_SYMBOL(debug_sprintf_exception); +EXPORT_SYMBOL(debug_sprintf_event); diff --git a/arch/s390/kernel/diag.c b/arch/s390/kernel/diag.c new file mode 100644 index 00000000..8237fc07 --- /dev/null +++ b/arch/s390/kernel/diag.c @@ -0,0 +1,81 @@ +/* + * Implementation of s390 diagnose codes + * + * Copyright IBM Corp. 2007 + * Author(s): Michael Holzheu <holzheu@de.ibm.com> + */ + +#include <linux/module.h> +#include <asm/diag.h> + +/* + * Diagnose 14: Input spool file manipulation + */ +int diag14(unsigned long rx, unsigned long ry1, unsigned long subcode) +{ + register unsigned long _ry1 asm("2") = ry1; + register unsigned long _ry2 asm("3") = subcode; + int rc = 0; + + asm volatile( +#ifdef CONFIG_64BIT + " sam31\n" + " diag %2,2,0x14\n" + " sam64\n" +#else + " diag %2,2,0x14\n" +#endif + " ipm %0\n" + " srl %0,28\n" + : "=d" (rc), "+d" (_ry2) + : "d" (rx), "d" (_ry1) + : "cc"); + + return rc; +} +EXPORT_SYMBOL(diag14); + +/* + * Diagnose 210: Get information about a virtual device + */ +int diag210(struct diag210 *addr) +{ + /* + * diag 210 needs its data below the 2GB border, so we + * use a static data area to be sure + */ + static struct diag210 diag210_tmp; + static DEFINE_SPINLOCK(diag210_lock); + unsigned long flags; + int ccode; + + spin_lock_irqsave(&diag210_lock, flags); + diag210_tmp = *addr; + +#ifdef CONFIG_64BIT + asm volatile( + " lhi %0,-1\n" + " sam31\n" + " diag %1,0,0x210\n" + "0: ipm %0\n" + " srl %0,28\n" + "1: sam64\n" + EX_TABLE(0b, 1b) + : "=&d" (ccode) : "a" (&diag210_tmp) : "cc", "memory"); +#else + asm volatile( + " lhi %0,-1\n" + " diag %1,0,0x210\n" + "0: ipm %0\n" + " srl %0,28\n" + "1:\n" + EX_TABLE(0b, 1b) + : "=&d" (ccode) : "a" (&diag210_tmp) : "cc", "memory"); +#endif + + *addr = diag210_tmp; + spin_unlock_irqrestore(&diag210_lock, flags); + + return ccode; +} +EXPORT_SYMBOL(diag210); diff --git a/arch/s390/kernel/dis.c b/arch/s390/kernel/dis.c new file mode 100644 index 00000000..3221c6fc --- /dev/null +++ b/arch/s390/kernel/dis.c @@ -0,0 +1,1604 @@ +/* + * arch/s390/kernel/dis.c + * + * Disassemble s390 instructions. + * + * Copyright IBM Corp. 2007 + * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com), + */ + +#include <linux/sched.h> +#include <linux/kernel.h> +#include <linux/string.h> +#include <linux/errno.h> +#include <linux/ptrace.h> +#include <linux/timer.h> +#include <linux/mm.h> +#include <linux/smp.h> +#include <linux/init.h> +#include <linux/interrupt.h> +#include <linux/delay.h> +#include <linux/module.h> +#include <linux/kallsyms.h> +#include <linux/reboot.h> +#include <linux/kprobes.h> +#include <linux/kdebug.h> + +#include <asm/uaccess.h> +#include <asm/io.h> +#include <linux/atomic.h> +#include <asm/mathemu.h> +#include <asm/cpcmd.h> +#include <asm/lowcore.h> +#include <asm/debug.h> +#include <asm/irq.h> + +#ifndef CONFIG_64BIT +#define ONELONG "%08lx: " +#else /* CONFIG_64BIT */ +#define ONELONG "%016lx: " +#endif /* CONFIG_64BIT */ + +#define OPERAND_GPR 0x1 /* Operand printed as %rx */ +#define OPERAND_FPR 0x2 /* Operand printed as %fx */ +#define OPERAND_AR 0x4 /* Operand printed as %ax */ +#define OPERAND_CR 0x8 /* Operand printed as %cx */ +#define OPERAND_DISP 0x10 /* Operand printed as displacement */ +#define OPERAND_BASE 0x20 /* Operand printed as base register */ +#define OPERAND_INDEX 0x40 /* Operand printed as index register */ +#define OPERAND_PCREL 0x80 /* Operand printed as pc-relative symbol */ +#define OPERAND_SIGNED 0x100 /* Operand printed as signed value */ +#define OPERAND_LENGTH 0x200 /* Operand printed as length (+1) */ + +enum { + UNUSED, /* Indicates the end of the operand list */ + R_8, /* GPR starting at position 8 */ + R_12, /* GPR starting at position 12 */ + R_16, /* GPR starting at position 16 */ + R_20, /* GPR starting at position 20 */ + R_24, /* GPR starting at position 24 */ + R_28, /* GPR starting at position 28 */ + R_32, /* GPR starting at position 32 */ + F_8, /* FPR starting at position 8 */ + F_12, /* FPR starting at position 12 */ + F_16, /* FPR starting at position 16 */ + F_20, /* FPR starting at position 16 */ + F_24, /* FPR starting at position 24 */ + F_28, /* FPR starting at position 28 */ + F_32, /* FPR starting at position 32 */ + A_8, /* Access reg. starting at position 8 */ + A_12, /* Access reg. starting at position 12 */ + A_24, /* Access reg. starting at position 24 */ + A_28, /* Access reg. starting at position 28 */ + C_8, /* Control reg. starting at position 8 */ + C_12, /* Control reg. starting at position 12 */ + B_16, /* Base register starting at position 16 */ + B_32, /* Base register starting at position 32 */ + X_12, /* Index register starting at position 12 */ + D_20, /* Displacement starting at position 20 */ + D_36, /* Displacement starting at position 36 */ + D20_20, /* 20 bit displacement starting at 20 */ + L4_8, /* 4 bit length starting at position 8 */ + L4_12, /* 4 bit length starting at position 12 */ + L8_8, /* 8 bit length starting at position 8 */ + U4_8, /* 4 bit unsigned value starting at 8 */ + U4_12, /* 4 bit unsigned value starting at 12 */ + U4_16, /* 4 bit unsigned value starting at 16 */ + U4_20, /* 4 bit unsigned value starting at 20 */ + U4_32, /* 4 bit unsigned value starting at 32 */ + U8_8, /* 8 bit unsigned value starting at 8 */ + U8_16, /* 8 bit unsigned value starting at 16 */ + U8_24, /* 8 bit unsigned value starting at 24 */ + U8_32, /* 8 bit unsigned value starting at 32 */ + I8_8, /* 8 bit signed value starting at 8 */ + I8_32, /* 8 bit signed value starting at 32 */ + I16_16, /* 16 bit signed value starting at 16 */ + I16_32, /* 32 bit signed value starting at 16 */ + U16_16, /* 16 bit unsigned value starting at 16 */ + U16_32, /* 32 bit unsigned value starting at 16 */ + J16_16, /* PC relative jump offset at 16 */ + J32_16, /* PC relative long offset at 16 */ + I32_16, /* 32 bit signed value starting at 16 */ + U32_16, /* 32 bit unsigned value starting at 16 */ + M_16, /* 4 bit optional mask starting at 16 */ + RO_28, /* optional GPR starting at position 28 */ +}; + +/* + * Enumeration of the different instruction formats. + * For details consult the principles of operation. + */ +enum { + INSTR_INVALID, + INSTR_E, + INSTR_RIE_R0IU, INSTR_RIE_R0UU, INSTR_RIE_RRP, INSTR_RIE_RRPU, + INSTR_RIE_RRUUU, INSTR_RIE_RUPI, INSTR_RIE_RUPU, INSTR_RIE_RRI0, + INSTR_RIL_RI, INSTR_RIL_RP, INSTR_RIL_RU, INSTR_RIL_UP, + INSTR_RIS_R0RDU, INSTR_RIS_R0UU, INSTR_RIS_RURDI, INSTR_RIS_RURDU, + INSTR_RI_RI, INSTR_RI_RP, INSTR_RI_RU, INSTR_RI_UP, + INSTR_RRE_00, INSTR_RRE_0R, INSTR_RRE_AA, INSTR_RRE_AR, INSTR_RRE_F0, + INSTR_RRE_FF, INSTR_RRE_FR, INSTR_RRE_R0, INSTR_RRE_RA, INSTR_RRE_RF, + INSTR_RRE_RR, INSTR_RRE_RR_OPT, + INSTR_RRF_0UFF, INSTR_RRF_F0FF, INSTR_RRF_F0FF2, INSTR_RRF_F0FR, + INSTR_RRF_FFRU, INSTR_RRF_FUFF, INSTR_RRF_M0RR, INSTR_RRF_R0RR, + INSTR_RRF_R0RR2, INSTR_RRF_RURR, INSTR_RRF_U0FF, INSTR_RRF_U0RF, + INSTR_RRF_U0RR, INSTR_RRF_UUFF, INSTR_RRR_F0FF, INSTR_RRS_RRRDU, + INSTR_RR_FF, INSTR_RR_R0, INSTR_RR_RR, INSTR_RR_U0, INSTR_RR_UR, + INSTR_RSE_CCRD, INSTR_RSE_RRRD, INSTR_RSE_RURD, + INSTR_RSI_RRP, + INSTR_RSL_R0RD, + INSTR_RSY_AARD, INSTR_RSY_CCRD, INSTR_RSY_RRRD, INSTR_RSY_RURD, + INSTR_RSY_RDRM, + INSTR_RS_AARD, INSTR_RS_CCRD, INSTR_RS_R0RD, INSTR_RS_RRRD, + INSTR_RS_RURD, + INSTR_RXE_FRRD, INSTR_RXE_RRRD, + INSTR_RXF_FRRDF, + INSTR_RXY_FRRD, INSTR_RXY_RRRD, INSTR_RXY_URRD, + INSTR_RX_FRRD, INSTR_RX_RRRD, INSTR_RX_URRD, + INSTR_SIL_RDI, INSTR_SIL_RDU, + INSTR_SIY_IRD, INSTR_SIY_URD, + INSTR_SI_URD, + INSTR_SSE_RDRD, + INSTR_SSF_RRDRD, INSTR_SSF_RRDRD2, + INSTR_SS_L0RDRD, INSTR_SS_LIRDRD, INSTR_SS_LLRDRD, INSTR_SS_RRRDRD, + INSTR_SS_RRRDRD2, INSTR_SS_RRRDRD3, + INSTR_S_00, INSTR_S_RD, +}; + +struct operand { + int bits; /* The number of bits in the operand. */ + int shift; /* The number of bits to shift. */ + int flags; /* One bit syntax flags. */ +}; + +struct insn { + const char name[5]; + unsigned char opfrag; + unsigned char format; +}; + +static const struct operand operands[] = +{ + [UNUSED] = { 0, 0, 0 }, + [R_8] = { 4, 8, OPERAND_GPR }, + [R_12] = { 4, 12, OPERAND_GPR }, + [R_16] = { 4, 16, OPERAND_GPR }, + [R_20] = { 4, 20, OPERAND_GPR }, + [R_24] = { 4, 24, OPERAND_GPR }, + [R_28] = { 4, 28, OPERAND_GPR }, + [R_32] = { 4, 32, OPERAND_GPR }, + [F_8] = { 4, 8, OPERAND_FPR }, + [F_12] = { 4, 12, OPERAND_FPR }, + [F_16] = { 4, 16, OPERAND_FPR }, + [F_20] = { 4, 16, OPERAND_FPR }, + [F_24] = { 4, 24, OPERAND_FPR }, + [F_28] = { 4, 28, OPERAND_FPR }, + [F_32] = { 4, 32, OPERAND_FPR }, + [A_8] = { 4, 8, OPERAND_AR }, + [A_12] = { 4, 12, OPERAND_AR }, + [A_24] = { 4, 24, OPERAND_AR }, + [A_28] = { 4, 28, OPERAND_AR }, + [C_8] = { 4, 8, OPERAND_CR }, + [C_12] = { 4, 12, OPERAND_CR }, + [B_16] = { 4, 16, OPERAND_BASE | OPERAND_GPR }, + [B_32] = { 4, 32, OPERAND_BASE | OPERAND_GPR }, + [X_12] = { 4, 12, OPERAND_INDEX | OPERAND_GPR }, + [D_20] = { 12, 20, OPERAND_DISP }, + [D_36] = { 12, 36, OPERAND_DISP }, + [D20_20] = { 20, 20, OPERAND_DISP | OPERAND_SIGNED }, + [L4_8] = { 4, 8, OPERAND_LENGTH }, + [L4_12] = { 4, 12, OPERAND_LENGTH }, + [L8_8] = { 8, 8, OPERAND_LENGTH }, + [U4_8] = { 4, 8, 0 }, + [U4_12] = { 4, 12, 0 }, + [U4_16] = { 4, 16, 0 }, + [U4_20] = { 4, 20, 0 }, + [U4_32] = { 4, 32, 0 }, + [U8_8] = { 8, 8, 0 }, + [U8_16] = { 8, 16, 0 }, + [U8_24] = { 8, 24, 0 }, + [U8_32] = { 8, 32, 0 }, + [I16_16] = { 16, 16, OPERAND_SIGNED }, + [U16_16] = { 16, 16, 0 }, + [U16_32] = { 16, 32, 0 }, + [J16_16] = { 16, 16, OPERAND_PCREL }, + [I16_32] = { 16, 32, OPERAND_SIGNED }, + [J32_16] = { 32, 16, OPERAND_PCREL }, + [I32_16] = { 32, 16, OPERAND_SIGNED }, + [U32_16] = { 32, 16, 0 }, + [M_16] = { 4, 16, 0 }, + [RO_28] = { 4, 28, OPERAND_GPR } +}; + +static const unsigned char formats[][7] = { + [INSTR_E] = { 0xff, 0,0,0,0,0,0 }, + [INSTR_RIE_R0UU] = { 0xff, R_8,U16_16,U4_32,0,0,0 }, + [INSTR_RIE_RRPU] = { 0xff, R_8,R_12,U4_32,J16_16,0,0 }, + [INSTR_RIE_RRP] = { 0xff, R_8,R_12,J16_16,0,0,0 }, + [INSTR_RIE_RRUUU] = { 0xff, R_8,R_12,U8_16,U8_24,U8_32,0 }, + [INSTR_RIE_RUPI] = { 0xff, R_8,I8_32,U4_12,J16_16,0,0 }, + [INSTR_RIE_RRI0] = { 0xff, R_8,R_12,I16_16,0,0,0 }, + [INSTR_RIL_RI] = { 0x0f, R_8,I32_16,0,0,0,0 }, + [INSTR_RIL_RP] = { 0x0f, R_8,J32_16,0,0,0,0 }, + [INSTR_RIL_RU] = { 0x0f, R_8,U32_16,0,0,0,0 }, + [INSTR_RIL_UP] = { 0x0f, U4_8,J32_16,0,0,0,0 }, + [INSTR_RIS_R0RDU] = { 0xff, R_8,U8_32,D_20,B_16,0,0 }, + [INSTR_RIS_RURDI] = { 0xff, R_8,I8_32,U4_12,D_20,B_16,0 }, + [INSTR_RIS_RURDU] = { 0xff, R_8,U8_32,U4_12,D_20,B_16,0 }, + [INSTR_RI_RI] = { 0x0f, R_8,I16_16,0,0,0,0 }, + [INSTR_RI_RP] = { 0x0f, R_8,J16_16,0,0,0,0 }, + [INSTR_RI_RU] = { 0x0f, R_8,U16_16,0,0,0,0 }, + [INSTR_RI_UP] = { 0x0f, U4_8,J16_16,0,0,0,0 }, + [INSTR_RRE_00] = { 0xff, 0,0,0,0,0,0 }, + [INSTR_RRE_0R] = { 0xff, R_28,0,0,0,0,0 }, + [INSTR_RRE_AA] = { 0xff, A_24,A_28,0,0,0,0 }, + [INSTR_RRE_AR] = { 0xff, A_24,R_28,0,0,0,0 }, + [INSTR_RRE_F0] = { 0xff, F_24,0,0,0,0,0 }, + [INSTR_RRE_FF] = { 0xff, F_24,F_28,0,0,0,0 }, + [INSTR_RRE_FR] = { 0xff, F_24,R_28,0,0,0,0 }, + [INSTR_RRE_R0] = { 0xff, R_24,0,0,0,0,0 }, + [INSTR_RRE_RA] = { 0xff, R_24,A_28,0,0,0,0 }, + [INSTR_RRE_RF] = { 0xff, R_24,F_28,0,0,0,0 }, + [INSTR_RRE_RR] = { 0xff, R_24,R_28,0,0,0,0 }, + [INSTR_RRE_RR_OPT]= { 0xff, R_24,RO_28,0,0,0,0 }, + [INSTR_RRF_0UFF] = { 0xff, F_24,F_28,U4_20,0,0,0 }, + [INSTR_RRF_F0FF2] = { 0xff, F_24,F_16,F_28,0,0,0 }, + [INSTR_RRF_F0FF] = { 0xff, F_16,F_24,F_28,0,0,0 }, + [INSTR_RRF_F0FR] = { 0xff, F_24,F_16,R_28,0,0,0 }, + [INSTR_RRF_FFRU] = { 0xff, F_24,F_16,R_28,U4_20,0,0 }, + [INSTR_RRF_FUFF] = { 0xff, F_24,F_16,F_28,U4_20,0,0 }, + [INSTR_RRF_M0RR] = { 0xff, R_24,R_28,M_16,0,0,0 }, + [INSTR_RRF_R0RR] = { 0xff, R_24,R_16,R_28,0,0,0 }, + [INSTR_RRF_R0RR2] = { 0xff, R_24,R_28,R_16,0,0,0 }, + [INSTR_RRF_RURR] = { 0xff, R_24,R_28,R_16,U4_20,0,0 }, + [INSTR_RRF_U0FF] = { 0xff, F_24,U4_16,F_28,0,0,0 }, + [INSTR_RRF_U0RF] = { 0xff, R_24,U4_16,F_28,0,0,0 }, + [INSTR_RRF_U0RR] = { 0xff, R_24,R_28,U4_16,0,0,0 }, + [INSTR_RRF_UUFF] = { 0xff, F_24,U4_16,F_28,U4_20,0,0 }, + [INSTR_RRR_F0FF] = { 0xff, F_24,F_28,F_16,0,0,0 }, + [INSTR_RRS_RRRDU] = { 0xff, R_8,R_12,U4_32,D_20,B_16,0 }, + [INSTR_RR_FF] = { 0xff, F_8,F_12,0,0,0,0 }, + [INSTR_RR_R0] = { 0xff, R_8, 0,0,0,0,0 }, + [INSTR_RR_RR] = { 0xff, R_8,R_12,0,0,0,0 }, + [INSTR_RR_U0] = { 0xff, U8_8, 0,0,0,0,0 }, + [INSTR_RR_UR] = { 0xff, U4_8,R_12,0,0,0,0 }, + [INSTR_RSE_CCRD] = { 0xff, C_8,C_12,D_20,B_16,0,0 }, + [INSTR_RSE_RRRD] = { 0xff, R_8,R_12,D_20,B_16,0,0 }, + [INSTR_RSE_RURD] = { 0xff, R_8,U4_12,D_20,B_16,0,0 }, + [INSTR_RSI_RRP] = { 0xff, R_8,R_12,J16_16,0,0,0 }, + [INSTR_RSL_R0RD] = { 0xff, D_20,L4_8,B_16,0,0,0 }, + [INSTR_RSY_AARD] = { 0xff, A_8,A_12,D20_20,B_16,0,0 }, + [INSTR_RSY_CCRD] = { 0xff, C_8,C_12,D20_20,B_16,0,0 }, + [INSTR_RSY_RRRD] = { 0xff, R_8,R_12,D20_20,B_16,0,0 }, + [INSTR_RSY_RURD] = { 0xff, R_8,U4_12,D20_20,B_16,0,0 }, + [INSTR_RSY_RDRM] = { 0xff, R_8,D20_20,B_16,U4_12,0,0 }, + [INSTR_RS_AARD] = { 0xff, A_8,A_12,D_20,B_16,0,0 }, + [INSTR_RS_CCRD] = { 0xff, C_8,C_12,D_20,B_16,0,0 }, + [INSTR_RS_R0RD] = { 0xff, R_8,D_20,B_16,0,0,0 }, + [INSTR_RS_RRRD] = { 0xff, R_8,R_12,D_20,B_16,0,0 }, + [INSTR_RS_RURD] = { 0xff, R_8,U4_12,D_20,B_16,0,0 }, + [INSTR_RXE_FRRD] = { 0xff, F_8,D_20,X_12,B_16,0,0 }, + [INSTR_RXE_RRRD] = { 0xff, R_8,D_20,X_12,B_16,0,0 }, + [INSTR_RXF_FRRDF] = { 0xff, F_32,F_8,D_20,X_12,B_16,0 }, + [INSTR_RXY_FRRD] = { 0xff, F_8,D20_20,X_12,B_16,0,0 }, + [INSTR_RXY_RRRD] = { 0xff, R_8,D20_20,X_12,B_16,0,0 }, + [INSTR_RXY_URRD] = { 0xff, U4_8,D20_20,X_12,B_16,0,0 }, + [INSTR_RX_FRRD] = { 0xff, F_8,D_20,X_12,B_16,0,0 }, + [INSTR_RX_RRRD] = { 0xff, R_8,D_20,X_12,B_16,0,0 }, + [INSTR_RX_URRD] = { 0xff, U4_8,D_20,X_12,B_16,0,0 }, + [INSTR_SIL_RDI] = { 0xff, D_20,B_16,I16_32,0,0,0 }, + [INSTR_SIL_RDU] = { 0xff, D_20,B_16,U16_32,0,0,0 }, + [INSTR_SIY_IRD] = { 0xff, D20_20,B_16,I8_8,0,0,0 }, + [INSTR_SIY_URD] = { 0xff, D20_20,B_16,U8_8,0,0,0 }, + [INSTR_SI_URD] = { 0xff, D_20,B_16,U8_8,0,0,0 }, + [INSTR_SSE_RDRD] = { 0xff, D_20,B_16,D_36,B_32,0,0 }, + [INSTR_SSF_RRDRD] = { 0x00, D_20,B_16,D_36,B_32,R_8,0 }, + [INSTR_SSF_RRDRD2]= { 0x00, R_8,D_20,B_16,D_36,B_32,0 }, + [INSTR_SS_L0RDRD] = { 0xff, D_20,L8_8,B_16,D_36,B_32,0 }, + [INSTR_SS_LIRDRD] = { 0xff, D_20,L4_8,B_16,D_36,B_32,U4_12 }, + [INSTR_SS_LLRDRD] = { 0xff, D_20,L4_8,B_16,D_36,L4_12,B_32 }, + [INSTR_SS_RRRDRD2]= { 0xff, R_8,D_20,B_16,R_12,D_36,B_32 }, + [INSTR_SS_RRRDRD3]= { 0xff, R_8,R_12,D_20,B_16,D_36,B_32 }, + [INSTR_SS_RRRDRD] = { 0xff, D_20,R_8,B_16,D_36,B_32,R_12 }, + [INSTR_S_00] = { 0xff, 0,0,0,0,0,0 }, + [INSTR_S_RD] = { 0xff, D_20,B_16,0,0,0,0 }, +}; + +enum { + LONG_INSN_ALGHSIK, + LONG_INSN_ALHSIK, + LONG_INSN_CLFHSI, + LONG_INSN_CLGFRL, + LONG_INSN_CLGHRL, + LONG_INSN_CLGHSI, + LONG_INSN_CLHHSI, + LONG_INSN_LLGFRL, + LONG_INSN_LLGHRL, + LONG_INSN_POPCNT, + LONG_INSN_RISBHG, + LONG_INSN_RISBLG, +}; + +static char *long_insn_name[] = { + [LONG_INSN_ALGHSIK] = "alghsik", + [LONG_INSN_ALHSIK] = "alhsik", + [LONG_INSN_CLFHSI] = "clfhsi", + [LONG_INSN_CLGFRL] = "clgfrl", + [LONG_INSN_CLGHRL] = "clghrl", + [LONG_INSN_CLGHSI] = "clghsi", + [LONG_INSN_CLHHSI] = "clhhsi", + [LONG_INSN_LLGFRL] = "llgfrl", + [LONG_INSN_LLGHRL] = "llghrl", + [LONG_INSN_POPCNT] = "popcnt", + [LONG_INSN_RISBHG] = "risbhg", + [LONG_INSN_RISBLG] = "risblk", +}; + +static struct insn opcode[] = { +#ifdef CONFIG_64BIT + { "lmd", 0xef, INSTR_SS_RRRDRD3 }, +#endif + { "spm", 0x04, INSTR_RR_R0 }, + { "balr", 0x05, INSTR_RR_RR }, + { "bctr", 0x06, INSTR_RR_RR }, + { "bcr", 0x07, INSTR_RR_UR }, + { "svc", 0x0a, INSTR_RR_U0 }, + { "bsm", 0x0b, INSTR_RR_RR }, + { "bassm", 0x0c, INSTR_RR_RR }, + { "basr", 0x0d, INSTR_RR_RR }, + { "mvcl", 0x0e, INSTR_RR_RR }, + { "clcl", 0x0f, INSTR_RR_RR }, + { "lpr", 0x10, INSTR_RR_RR }, + { "lnr", 0x11, INSTR_RR_RR }, + { "ltr", 0x12, INSTR_RR_RR }, + { "lcr", 0x13, INSTR_RR_RR }, + { "nr", 0x14, INSTR_RR_RR }, + { "clr", 0x15, INSTR_RR_RR }, + { "or", 0x16, INSTR_RR_RR }, + { "xr", 0x17, INSTR_RR_RR }, + { "lr", 0x18, INSTR_RR_RR }, + { "cr", 0x19, INSTR_RR_RR }, + { "ar", 0x1a, INSTR_RR_RR }, + { "sr", 0x1b, INSTR_RR_RR }, + { "mr", 0x1c, INSTR_RR_RR }, + { "dr", 0x1d, INSTR_RR_RR }, + { "alr", 0x1e, INSTR_RR_RR }, + { "slr", 0x1f, INSTR_RR_RR }, + { "lpdr", 0x20, INSTR_RR_FF }, + { "lndr", 0x21, INSTR_RR_FF }, + { "ltdr", 0x22, INSTR_RR_FF }, + { "lcdr", 0x23, INSTR_RR_FF }, + { "hdr", 0x24, INSTR_RR_FF }, + { "ldxr", 0x25, INSTR_RR_FF }, + { "lrdr", 0x25, INSTR_RR_FF }, + { "mxr", 0x26, INSTR_RR_FF }, + { "mxdr", 0x27, INSTR_RR_FF }, + { "ldr", 0x28, INSTR_RR_FF }, + { "cdr", 0x29, INSTR_RR_FF }, + { "adr", 0x2a, INSTR_RR_FF }, + { "sdr", 0x2b, INSTR_RR_FF }, + { "mdr", 0x2c, INSTR_RR_FF }, + { "ddr", 0x2d, INSTR_RR_FF }, + { "awr", 0x2e, INSTR_RR_FF }, + { "swr", 0x2f, INSTR_RR_FF }, + { "lper", 0x30, INSTR_RR_FF }, + { "lner", 0x31, INSTR_RR_FF }, + { "lter", 0x32, INSTR_RR_FF }, + { "lcer", 0x33, INSTR_RR_FF }, + { "her", 0x34, INSTR_RR_FF }, + { "ledr", 0x35, INSTR_RR_FF }, + { "lrer", 0x35, INSTR_RR_FF }, + { "axr", 0x36, INSTR_RR_FF }, + { "sxr", 0x37, INSTR_RR_FF }, + { "ler", 0x38, INSTR_RR_FF }, + { "cer", 0x39, INSTR_RR_FF }, + { "aer", 0x3a, INSTR_RR_FF }, + { "ser", 0x3b, INSTR_RR_FF }, + { "mder", 0x3c, INSTR_RR_FF }, + { "mer", 0x3c, INSTR_RR_FF }, + { "der", 0x3d, INSTR_RR_FF }, + { "aur", 0x3e, INSTR_RR_FF }, + { "sur", 0x3f, INSTR_RR_FF }, + { "sth", 0x40, INSTR_RX_RRRD }, + { "la", 0x41, INSTR_RX_RRRD }, + { "stc", 0x42, INSTR_RX_RRRD }, + { "ic", 0x43, INSTR_RX_RRRD }, + { "ex", 0x44, INSTR_RX_RRRD }, + { "bal", 0x45, INSTR_RX_RRRD }, + { "bct", 0x46, INSTR_RX_RRRD }, + { "bc", 0x47, INSTR_RX_URRD }, + { "lh", 0x48, INSTR_RX_RRRD }, + { "ch", 0x49, INSTR_RX_RRRD }, + { "ah", 0x4a, INSTR_RX_RRRD }, + { "sh", 0x4b, INSTR_RX_RRRD }, + { "mh", 0x4c, INSTR_RX_RRRD }, + { "bas", 0x4d, INSTR_RX_RRRD }, + { "cvd", 0x4e, INSTR_RX_RRRD }, + { "cvb", 0x4f, INSTR_RX_RRRD }, + { "st", 0x50, INSTR_RX_RRRD }, + { "lae", 0x51, INSTR_RX_RRRD }, + { "n", 0x54, INSTR_RX_RRRD }, + { "cl", 0x55, INSTR_RX_RRRD }, + { "o", 0x56, INSTR_RX_RRRD }, + { "x", 0x57, INSTR_RX_RRRD }, + { "l", 0x58, INSTR_RX_RRRD }, + { "c", 0x59, INSTR_RX_RRRD }, + { "a", 0x5a, INSTR_RX_RRRD }, + { "s", 0x5b, INSTR_RX_RRRD }, + { "m", 0x5c, INSTR_RX_RRRD }, + { "d", 0x5d, INSTR_RX_RRRD }, + { "al", 0x5e, INSTR_RX_RRRD }, + { "sl", 0x5f, INSTR_RX_RRRD }, + { "std", 0x60, INSTR_RX_FRRD }, + { "mxd", 0x67, INSTR_RX_FRRD }, + { "ld", 0x68, INSTR_RX_FRRD }, + { "cd", 0x69, INSTR_RX_FRRD }, + { "ad", 0x6a, INSTR_RX_FRRD }, + { "sd", 0x6b, INSTR_RX_FRRD }, + { "md", 0x6c, INSTR_RX_FRRD }, + { "dd", 0x6d, INSTR_RX_FRRD }, + { "aw", 0x6e, INSTR_RX_FRRD }, + { "sw", 0x6f, INSTR_RX_FRRD }, + { "ste", 0x70, INSTR_RX_FRRD }, + { "ms", 0x71, INSTR_RX_RRRD }, + { "le", 0x78, INSTR_RX_FRRD }, + { "ce", 0x79, INSTR_RX_FRRD }, + { "ae", 0x7a, INSTR_RX_FRRD }, + { "se", 0x7b, INSTR_RX_FRRD }, + { "mde", 0x7c, INSTR_RX_FRRD }, + { "me", 0x7c, INSTR_RX_FRRD }, + { "de", 0x7d, INSTR_RX_FRRD }, + { "au", 0x7e, INSTR_RX_FRRD }, + { "su", 0x7f, INSTR_RX_FRRD }, + { "ssm", 0x80, INSTR_S_RD }, + { "lpsw", 0x82, INSTR_S_RD }, + { "diag", 0x83, INSTR_RS_RRRD }, + { "brxh", 0x84, INSTR_RSI_RRP }, + { "brxle", 0x85, INSTR_RSI_RRP }, + { "bxh", 0x86, INSTR_RS_RRRD }, + { "bxle", 0x87, INSTR_RS_RRRD }, + { "srl", 0x88, INSTR_RS_R0RD }, + { "sll", 0x89, INSTR_RS_R0RD }, + { "sra", 0x8a, INSTR_RS_R0RD }, + { "sla", 0x8b, INSTR_RS_R0RD }, + { "srdl", 0x8c, INSTR_RS_R0RD }, + { "sldl", 0x8d, INSTR_RS_R0RD }, + { "srda", 0x8e, INSTR_RS_R0RD }, + { "slda", 0x8f, INSTR_RS_R0RD }, + { "stm", 0x90, INSTR_RS_RRRD }, + { "tm", 0x91, INSTR_SI_URD }, + { "mvi", 0x92, INSTR_SI_URD }, + { "ts", 0x93, INSTR_S_RD }, + { "ni", 0x94, INSTR_SI_URD }, + { "cli", 0x95, INSTR_SI_URD }, + { "oi", 0x96, INSTR_SI_URD }, + { "xi", 0x97, INSTR_SI_URD }, + { "lm", 0x98, INSTR_RS_RRRD }, + { "trace", 0x99, INSTR_RS_RRRD }, + { "lam", 0x9a, INSTR_RS_AARD }, + { "stam", 0x9b, INSTR_RS_AARD }, + { "mvcle", 0xa8, INSTR_RS_RRRD }, + { "clcle", 0xa9, INSTR_RS_RRRD }, + { "stnsm", 0xac, INSTR_SI_URD }, + { "stosm", 0xad, INSTR_SI_URD }, + { "sigp", 0xae, INSTR_RS_RRRD }, + { "mc", 0xaf, INSTR_SI_URD }, + { "lra", 0xb1, INSTR_RX_RRRD }, + { "stctl", 0xb6, INSTR_RS_CCRD }, + { "lctl", 0xb7, INSTR_RS_CCRD }, + { "cs", 0xba, INSTR_RS_RRRD }, + { "cds", 0xbb, INSTR_RS_RRRD }, + { "clm", 0xbd, INSTR_RS_RURD }, + { "stcm", 0xbe, INSTR_RS_RURD }, + { "icm", 0xbf, INSTR_RS_RURD }, + { "mvn", 0xd1, INSTR_SS_L0RDRD }, + { "mvc", 0xd2, INSTR_SS_L0RDRD }, + { "mvz", 0xd3, INSTR_SS_L0RDRD }, + { "nc", 0xd4, INSTR_SS_L0RDRD }, + { "clc", 0xd5, INSTR_SS_L0RDRD }, + { "oc", 0xd6, INSTR_SS_L0RDRD }, + { "xc", 0xd7, INSTR_SS_L0RDRD }, + { "mvck", 0xd9, INSTR_SS_RRRDRD }, + { "mvcp", 0xda, INSTR_SS_RRRDRD }, + { "mvcs", 0xdb, INSTR_SS_RRRDRD }, + { "tr", 0xdc, INSTR_SS_L0RDRD }, + { "trt", 0xdd, INSTR_SS_L0RDRD }, + { "ed", 0xde, INSTR_SS_L0RDRD }, + { "edmk", 0xdf, INSTR_SS_L0RDRD }, + { "pku", 0xe1, INSTR_SS_L0RDRD }, + { "unpku", 0xe2, INSTR_SS_L0RDRD }, + { "mvcin", 0xe8, INSTR_SS_L0RDRD }, + { "pka", 0xe9, INSTR_SS_L0RDRD }, + { "unpka", 0xea, INSTR_SS_L0RDRD }, + { "plo", 0xee, INSTR_SS_RRRDRD2 }, + { "srp", 0xf0, INSTR_SS_LIRDRD }, + { "mvo", 0xf1, INSTR_SS_LLRDRD }, + { "pack", 0xf2, INSTR_SS_LLRDRD }, + { "unpk", 0xf3, INSTR_SS_LLRDRD }, + { "zap", 0xf8, INSTR_SS_LLRDRD }, + { "cp", 0xf9, INSTR_SS_LLRDRD }, + { "ap", 0xfa, INSTR_SS_LLRDRD }, + { "sp", 0xfb, INSTR_SS_LLRDRD }, + { "mp", 0xfc, INSTR_SS_LLRDRD }, + { "dp", 0xfd, INSTR_SS_LLRDRD }, + { "", 0, INSTR_INVALID } +}; + +static struct insn opcode_01[] = { +#ifdef CONFIG_64BIT + { "sam64", 0x0e, INSTR_E }, + { "pfpo", 0x0a, INSTR_E }, + { "ptff", 0x04, INSTR_E }, +#endif + { "pr", 0x01, INSTR_E }, + { "upt", 0x02, INSTR_E }, + { "sckpf", 0x07, INSTR_E }, + { "tam", 0x0b, INSTR_E }, + { "sam24", 0x0c, INSTR_E }, + { "sam31", 0x0d, INSTR_E }, + { "trap2", 0xff, INSTR_E }, + { "", 0, INSTR_INVALID } +}; + +static struct insn opcode_a5[] = { +#ifdef CONFIG_64BIT + { "iihh", 0x00, INSTR_RI_RU }, + { "iihl", 0x01, INSTR_RI_RU }, + { "iilh", 0x02, INSTR_RI_RU }, + { "iill", 0x03, INSTR_RI_RU }, + { "nihh", 0x04, INSTR_RI_RU }, + { "nihl", 0x05, INSTR_RI_RU }, + { "nilh", 0x06, INSTR_RI_RU }, + { "nill", 0x07, INSTR_RI_RU }, + { "oihh", 0x08, INSTR_RI_RU }, + { "oihl", 0x09, INSTR_RI_RU }, + { "oilh", 0x0a, INSTR_RI_RU }, + { "oill", 0x0b, INSTR_RI_RU }, + { "llihh", 0x0c, INSTR_RI_RU }, + { "llihl", 0x0d, INSTR_RI_RU }, + { "llilh", 0x0e, INSTR_RI_RU }, + { "llill", 0x0f, INSTR_RI_RU }, +#endif + { "", 0, INSTR_INVALID } +}; + +static struct insn opcode_a7[] = { +#ifdef CONFIG_64BIT + { "tmhh", 0x02, INSTR_RI_RU }, + { "tmhl", 0x03, INSTR_RI_RU }, + { "brctg", 0x07, INSTR_RI_RP }, + { "lghi", 0x09, INSTR_RI_RI }, + { "aghi", 0x0b, INSTR_RI_RI }, + { "mghi", 0x0d, INSTR_RI_RI }, + { "cghi", 0x0f, INSTR_RI_RI }, +#endif + { "tmlh", 0x00, INSTR_RI_RU }, + { "tmll", 0x01, INSTR_RI_RU }, + { "brc", 0x04, INSTR_RI_UP }, + { "bras", 0x05, INSTR_RI_RP }, + { "brct", 0x06, INSTR_RI_RP }, + { "lhi", 0x08, INSTR_RI_RI }, + { "ahi", 0x0a, INSTR_RI_RI }, + { "mhi", 0x0c, INSTR_RI_RI }, + { "chi", 0x0e, INSTR_RI_RI }, + { "", 0, INSTR_INVALID } +}; + +static struct insn opcode_b2[] = { +#ifdef CONFIG_64BIT + { "sske", 0x2b, INSTR_RRF_M0RR }, + { "stckf", 0x7c, INSTR_S_RD }, + { "cu21", 0xa6, INSTR_RRF_M0RR }, + { "cuutf", 0xa6, INSTR_RRF_M0RR }, + { "cu12", 0xa7, INSTR_RRF_M0RR }, + { "cutfu", 0xa7, INSTR_RRF_M0RR }, + { "stfle", 0xb0, INSTR_S_RD }, + { "lpswe", 0xb2, INSTR_S_RD }, + { "srnmt", 0xb9, INSTR_S_RD }, + { "lfas", 0xbd, INSTR_S_RD }, +#endif + { "stidp", 0x02, INSTR_S_RD }, + { "sck", 0x04, INSTR_S_RD }, + { "stck", 0x05, INSTR_S_RD }, + { "sckc", 0x06, INSTR_S_RD }, + { "stckc", 0x07, INSTR_S_RD }, + { "spt", 0x08, INSTR_S_RD }, + { "stpt", 0x09, INSTR_S_RD }, + { "spka", 0x0a, INSTR_S_RD }, + { "ipk", 0x0b, INSTR_S_00 }, + { "ptlb", 0x0d, INSTR_S_00 }, + { "spx", 0x10, INSTR_S_RD }, + { "stpx", 0x11, INSTR_S_RD }, + { "stap", 0x12, INSTR_S_RD }, + { "sie", 0x14, INSTR_S_RD }, + { "pc", 0x18, INSTR_S_RD }, + { "sac", 0x19, INSTR_S_RD }, + { "cfc", 0x1a, INSTR_S_RD }, + { "ipte", 0x21, INSTR_RRE_RR }, + { "ipm", 0x22, INSTR_RRE_R0 }, + { "ivsk", 0x23, INSTR_RRE_RR }, + { "iac", 0x24, INSTR_RRE_R0 }, + { "ssar", 0x25, INSTR_RRE_R0 }, + { "epar", 0x26, INSTR_RRE_R0 }, + { "esar", 0x27, INSTR_RRE_R0 }, + { "pt", 0x28, INSTR_RRE_RR }, + { "iske", 0x29, INSTR_RRE_RR }, + { "rrbe", 0x2a, INSTR_RRE_RR }, + { "sske", 0x2b, INSTR_RRE_RR }, + { "tb", 0x2c, INSTR_RRE_0R }, + { "dxr", 0x2d, INSTR_RRE_F0 }, + { "pgin", 0x2e, INSTR_RRE_RR }, + { "pgout", 0x2f, INSTR_RRE_RR }, + { "csch", 0x30, INSTR_S_00 }, + { "hsch", 0x31, INSTR_S_00 }, + { "msch", 0x32, INSTR_S_RD }, + { "ssch", 0x33, INSTR_S_RD }, + { "stsch", 0x34, INSTR_S_RD }, + { "tsch", 0x35, INSTR_S_RD }, + { "tpi", 0x36, INSTR_S_RD }, + { "sal", 0x37, INSTR_S_00 }, + { "rsch", 0x38, INSTR_S_00 }, + { "stcrw", 0x39, INSTR_S_RD }, + { "stcps", 0x3a, INSTR_S_RD }, + { "rchp", 0x3b, INSTR_S_00 }, + { "schm", 0x3c, INSTR_S_00 }, + { "bakr", 0x40, INSTR_RRE_RR }, + { "cksm", 0x41, INSTR_RRE_RR }, + { "sqdr", 0x44, INSTR_RRE_F0 }, + { "sqer", 0x45, INSTR_RRE_F0 }, + { "stura", 0x46, INSTR_RRE_RR }, + { "msta", 0x47, INSTR_RRE_R0 }, + { "palb", 0x48, INSTR_RRE_00 }, + { "ereg", 0x49, INSTR_RRE_RR }, + { "esta", 0x4a, INSTR_RRE_RR }, + { "lura", 0x4b, INSTR_RRE_RR }, + { "tar", 0x4c, INSTR_RRE_AR }, + { "cpya", 0x4d, INSTR_RRE_AA }, + { "sar", 0x4e, INSTR_RRE_AR }, + { "ear", 0x4f, INSTR_RRE_RA }, + { "csp", 0x50, INSTR_RRE_RR }, + { "msr", 0x52, INSTR_RRE_RR }, + { "mvpg", 0x54, INSTR_RRE_RR }, + { "mvst", 0x55, INSTR_RRE_RR }, + { "cuse", 0x57, INSTR_RRE_RR }, + { "bsg", 0x58, INSTR_RRE_RR }, + { "bsa", 0x5a, INSTR_RRE_RR }, + { "clst", 0x5d, INSTR_RRE_RR }, + { "srst", 0x5e, INSTR_RRE_RR }, + { "cmpsc", 0x63, INSTR_RRE_RR }, + { "siga", 0x74, INSTR_S_RD }, + { "xsch", 0x76, INSTR_S_00 }, + { "rp", 0x77, INSTR_S_RD }, + { "stcke", 0x78, INSTR_S_RD }, + { "sacf", 0x79, INSTR_S_RD }, + { "spp", 0x80, INSTR_S_RD }, + { "stsi", 0x7d, INSTR_S_RD }, + { "srnm", 0x99, INSTR_S_RD }, + { "stfpc", 0x9c, INSTR_S_RD }, + { "lfpc", 0x9d, INSTR_S_RD }, + { "tre", 0xa5, INSTR_RRE_RR }, + { "cuutf", 0xa6, INSTR_RRE_RR }, + { "cutfu", 0xa7, INSTR_RRE_RR }, + { "stfl", 0xb1, INSTR_S_RD }, + { "trap4", 0xff, INSTR_S_RD }, + { "", 0, INSTR_INVALID } +}; + +static struct insn opcode_b3[] = { +#ifdef CONFIG_64BIT + { "maylr", 0x38, INSTR_RRF_F0FF }, + { "mylr", 0x39, INSTR_RRF_F0FF }, + { "mayr", 0x3a, INSTR_RRF_F0FF }, + { "myr", 0x3b, INSTR_RRF_F0FF }, + { "mayhr", 0x3c, INSTR_RRF_F0FF }, + { "myhr", 0x3d, INSTR_RRF_F0FF }, + { "cegbr", 0xa4, INSTR_RRE_RR }, + { "cdgbr", 0xa5, INSTR_RRE_RR }, + { "cxgbr", 0xa6, INSTR_RRE_RR }, + { "cgebr", 0xa8, INSTR_RRF_U0RF }, + { "cgdbr", 0xa9, INSTR_RRF_U0RF }, + { "cgxbr", 0xaa, INSTR_RRF_U0RF }, + { "cfer", 0xb8, INSTR_RRF_U0RF }, + { "cfdr", 0xb9, INSTR_RRF_U0RF }, + { "cfxr", 0xba, INSTR_RRF_U0RF }, + { "cegr", 0xc4, INSTR_RRE_RR }, + { "cdgr", 0xc5, INSTR_RRE_RR }, + { "cxgr", 0xc6, INSTR_RRE_RR }, + { "cger", 0xc8, INSTR_RRF_U0RF }, + { "cgdr", 0xc9, INSTR_RRF_U0RF }, + { "cgxr", 0xca, INSTR_RRF_U0RF }, + { "lpdfr", 0x70, INSTR_RRE_FF }, + { "lndfr", 0x71, INSTR_RRE_FF }, + { "cpsdr", 0x72, INSTR_RRF_F0FF2 }, + { "lcdfr", 0x73, INSTR_RRE_FF }, + { "ldgr", 0xc1, INSTR_RRE_FR }, + { "lgdr", 0xcd, INSTR_RRE_RF }, + { "adtr", 0xd2, INSTR_RRR_F0FF }, + { "axtr", 0xda, INSTR_RRR_F0FF }, + { "cdtr", 0xe4, INSTR_RRE_FF }, + { "cxtr", 0xec, INSTR_RRE_FF }, + { "kdtr", 0xe0, INSTR_RRE_FF }, + { "kxtr", 0xe8, INSTR_RRE_FF }, + { "cedtr", 0xf4, INSTR_RRE_FF }, + { "cextr", 0xfc, INSTR_RRE_FF }, + { "cdgtr", 0xf1, INSTR_RRE_FR }, + { "cxgtr", 0xf9, INSTR_RRE_FR }, + { "cdstr", 0xf3, INSTR_RRE_FR }, + { "cxstr", 0xfb, INSTR_RRE_FR }, + { "cdutr", 0xf2, INSTR_RRE_FR }, + { "cxutr", 0xfa, INSTR_RRE_FR }, + { "cgdtr", 0xe1, INSTR_RRF_U0RF }, + { "cgxtr", 0xe9, INSTR_RRF_U0RF }, + { "csdtr", 0xe3, INSTR_RRE_RF }, + { "csxtr", 0xeb, INSTR_RRE_RF }, + { "cudtr", 0xe2, INSTR_RRE_RF }, + { "cuxtr", 0xea, INSTR_RRE_RF }, + { "ddtr", 0xd1, INSTR_RRR_F0FF }, + { "dxtr", 0xd9, INSTR_RRR_F0FF }, + { "eedtr", 0xe5, INSTR_RRE_RF }, + { "eextr", 0xed, INSTR_RRE_RF }, + { "esdtr", 0xe7, INSTR_RRE_RF }, + { "esxtr", 0xef, INSTR_RRE_RF }, + { "iedtr", 0xf6, INSTR_RRF_F0FR }, + { "iextr", 0xfe, INSTR_RRF_F0FR }, + { "ltdtr", 0xd6, INSTR_RRE_FF }, + { "ltxtr", 0xde, INSTR_RRE_FF }, + { "fidtr", 0xd7, INSTR_RRF_UUFF }, + { "fixtr", 0xdf, INSTR_RRF_UUFF }, + { "ldetr", 0xd4, INSTR_RRF_0UFF }, + { "lxdtr", 0xdc, INSTR_RRF_0UFF }, + { "ledtr", 0xd5, INSTR_RRF_UUFF }, + { "ldxtr", 0xdd, INSTR_RRF_UUFF }, + { "mdtr", 0xd0, INSTR_RRR_F0FF }, + { "mxtr", 0xd8, INSTR_RRR_F0FF }, + { "qadtr", 0xf5, INSTR_RRF_FUFF }, + { "qaxtr", 0xfd, INSTR_RRF_FUFF }, + { "rrdtr", 0xf7, INSTR_RRF_FFRU }, + { "rrxtr", 0xff, INSTR_RRF_FFRU }, + { "sfasr", 0x85, INSTR_RRE_R0 }, + { "sdtr", 0xd3, INSTR_RRR_F0FF }, + { "sxtr", 0xdb, INSTR_RRR_F0FF }, +#endif + { "lpebr", 0x00, INSTR_RRE_FF }, + { "lnebr", 0x01, INSTR_RRE_FF }, + { "ltebr", 0x02, INSTR_RRE_FF }, + { "lcebr", 0x03, INSTR_RRE_FF }, + { "ldebr", 0x04, INSTR_RRE_FF }, + { "lxdbr", 0x05, INSTR_RRE_FF }, + { "lxebr", 0x06, INSTR_RRE_FF }, + { "mxdbr", 0x07, INSTR_RRE_FF }, + { "kebr", 0x08, INSTR_RRE_FF }, + { "cebr", 0x09, INSTR_RRE_FF }, + { "aebr", 0x0a, INSTR_RRE_FF }, + { "sebr", 0x0b, INSTR_RRE_FF }, + { "mdebr", 0x0c, INSTR_RRE_FF }, + { "debr", 0x0d, INSTR_RRE_FF }, + { "maebr", 0x0e, INSTR_RRF_F0FF }, + { "msebr", 0x0f, INSTR_RRF_F0FF }, + { "lpdbr", 0x10, INSTR_RRE_FF }, + { "lndbr", 0x11, INSTR_RRE_FF }, + { "ltdbr", 0x12, INSTR_RRE_FF }, + { "lcdbr", 0x13, INSTR_RRE_FF }, + { "sqebr", 0x14, INSTR_RRE_FF }, + { "sqdbr", 0x15, INSTR_RRE_FF }, + { "sqxbr", 0x16, INSTR_RRE_FF }, + { "meebr", 0x17, INSTR_RRE_FF }, + { "kdbr", 0x18, INSTR_RRE_FF }, + { "cdbr", 0x19, INSTR_RRE_FF }, + { "adbr", 0x1a, INSTR_RRE_FF }, + { "sdbr", 0x1b, INSTR_RRE_FF }, + { "mdbr", 0x1c, INSTR_RRE_FF }, + { "ddbr", 0x1d, INSTR_RRE_FF }, + { "madbr", 0x1e, INSTR_RRF_F0FF }, + { "msdbr", 0x1f, INSTR_RRF_F0FF }, + { "lder", 0x24, INSTR_RRE_FF }, + { "lxdr", 0x25, INSTR_RRE_FF }, + { "lxer", 0x26, INSTR_RRE_FF }, + { "maer", 0x2e, INSTR_RRF_F0FF }, + { "mser", 0x2f, INSTR_RRF_F0FF }, + { "sqxr", 0x36, INSTR_RRE_FF }, + { "meer", 0x37, INSTR_RRE_FF }, + { "madr", 0x3e, INSTR_RRF_F0FF }, + { "msdr", 0x3f, INSTR_RRF_F0FF }, + { "lpxbr", 0x40, INSTR_RRE_FF }, + { "lnxbr", 0x41, INSTR_RRE_FF }, + { "ltxbr", 0x42, INSTR_RRE_FF }, + { "lcxbr", 0x43, INSTR_RRE_FF }, + { "ledbr", 0x44, INSTR_RRE_FF }, + { "ldxbr", 0x45, INSTR_RRE_FF }, + { "lexbr", 0x46, INSTR_RRE_FF }, + { "fixbr", 0x47, INSTR_RRF_U0FF }, + { "kxbr", 0x48, INSTR_RRE_FF }, + { "cxbr", 0x49, INSTR_RRE_FF }, + { "axbr", 0x4a, INSTR_RRE_FF }, + { "sxbr", 0x4b, INSTR_RRE_FF }, + { "mxbr", 0x4c, INSTR_RRE_FF }, + { "dxbr", 0x4d, INSTR_RRE_FF }, + { "tbedr", 0x50, INSTR_RRF_U0FF }, + { "tbdr", 0x51, INSTR_RRF_U0FF }, + { "diebr", 0x53, INSTR_RRF_FUFF }, + { "fiebr", 0x57, INSTR_RRF_U0FF }, + { "thder", 0x58, INSTR_RRE_RR }, + { "thdr", 0x59, INSTR_RRE_RR }, + { "didbr", 0x5b, INSTR_RRF_FUFF }, + { "fidbr", 0x5f, INSTR_RRF_U0FF }, + { "lpxr", 0x60, INSTR_RRE_FF }, + { "lnxr", 0x61, INSTR_RRE_FF }, + { "ltxr", 0x62, INSTR_RRE_FF }, + { "lcxr", 0x63, INSTR_RRE_FF }, + { "lxr", 0x65, INSTR_RRE_RR }, + { "lexr", 0x66, INSTR_RRE_FF }, + { "fixr", 0x67, INSTR_RRF_U0FF }, + { "cxr", 0x69, INSTR_RRE_FF }, + { "lzer", 0x74, INSTR_RRE_R0 }, + { "lzdr", 0x75, INSTR_RRE_R0 }, + { "lzxr", 0x76, INSTR_RRE_R0 }, + { "fier", 0x77, INSTR_RRF_U0FF }, + { "fidr", 0x7f, INSTR_RRF_U0FF }, + { "sfpc", 0x84, INSTR_RRE_RR_OPT }, + { "efpc", 0x8c, INSTR_RRE_RR_OPT }, + { "cefbr", 0x94, INSTR_RRE_RF }, + { "cdfbr", 0x95, INSTR_RRE_RF }, + { "cxfbr", 0x96, INSTR_RRE_RF }, + { "cfebr", 0x98, INSTR_RRF_U0RF }, + { "cfdbr", 0x99, INSTR_RRF_U0RF }, + { "cfxbr", 0x9a, INSTR_RRF_U0RF }, + { "cefr", 0xb4, INSTR_RRE_RF }, + { "cdfr", 0xb5, INSTR_RRE_RF }, + { "cxfr", 0xb6, INSTR_RRE_RF }, + { "", 0, INSTR_INVALID } +}; + +static struct insn opcode_b9[] = { +#ifdef CONFIG_64BIT + { "lpgr", 0x00, INSTR_RRE_RR }, + { "lngr", 0x01, INSTR_RRE_RR }, + { "ltgr", 0x02, INSTR_RRE_RR }, + { "lcgr", 0x03, INSTR_RRE_RR }, + { "lgr", 0x04, INSTR_RRE_RR }, + { "lurag", 0x05, INSTR_RRE_RR }, + { "lgbr", 0x06, INSTR_RRE_RR }, + { "lghr", 0x07, INSTR_RRE_RR }, + { "agr", 0x08, INSTR_RRE_RR }, + { "sgr", 0x09, INSTR_RRE_RR }, + { "algr", 0x0a, INSTR_RRE_RR }, + { "slgr", 0x0b, INSTR_RRE_RR }, + { "msgr", 0x0c, INSTR_RRE_RR }, + { "dsgr", 0x0d, INSTR_RRE_RR }, + { "eregg", 0x0e, INSTR_RRE_RR }, + { "lrvgr", 0x0f, INSTR_RRE_RR }, + { "lpgfr", 0x10, INSTR_RRE_RR }, + { "lngfr", 0x11, INSTR_RRE_RR }, + { "ltgfr", 0x12, INSTR_RRE_RR }, + { "lcgfr", 0x13, INSTR_RRE_RR }, + { "lgfr", 0x14, INSTR_RRE_RR }, + { "llgfr", 0x16, INSTR_RRE_RR }, + { "llgtr", 0x17, INSTR_RRE_RR }, + { "agfr", 0x18, INSTR_RRE_RR }, + { "sgfr", 0x19, INSTR_RRE_RR }, + { "algfr", 0x1a, INSTR_RRE_RR }, + { "slgfr", 0x1b, INSTR_RRE_RR }, + { "msgfr", 0x1c, INSTR_RRE_RR }, + { "dsgfr", 0x1d, INSTR_RRE_RR }, + { "cgr", 0x20, INSTR_RRE_RR }, + { "clgr", 0x21, INSTR_RRE_RR }, + { "sturg", 0x25, INSTR_RRE_RR }, + { "lbr", 0x26, INSTR_RRE_RR }, + { "lhr", 0x27, INSTR_RRE_RR }, + { "cgfr", 0x30, INSTR_RRE_RR }, + { "clgfr", 0x31, INSTR_RRE_RR }, + { "bctgr", 0x46, INSTR_RRE_RR }, + { "ngr", 0x80, INSTR_RRE_RR }, + { "ogr", 0x81, INSTR_RRE_RR }, + { "xgr", 0x82, INSTR_RRE_RR }, + { "flogr", 0x83, INSTR_RRE_RR }, + { "llgcr", 0x84, INSTR_RRE_RR }, + { "llghr", 0x85, INSTR_RRE_RR }, + { "mlgr", 0x86, INSTR_RRE_RR }, + { "dlgr", 0x87, INSTR_RRE_RR }, + { "alcgr", 0x88, INSTR_RRE_RR }, + { "slbgr", 0x89, INSTR_RRE_RR }, + { "cspg", 0x8a, INSTR_RRE_RR }, + { "idte", 0x8e, INSTR_RRF_R0RR }, + { "llcr", 0x94, INSTR_RRE_RR }, + { "llhr", 0x95, INSTR_RRE_RR }, + { "esea", 0x9d, INSTR_RRE_R0 }, + { "lptea", 0xaa, INSTR_RRF_RURR }, + { "cu14", 0xb0, INSTR_RRF_M0RR }, + { "cu24", 0xb1, INSTR_RRF_M0RR }, + { "cu41", 0xb2, INSTR_RRF_M0RR }, + { "cu42", 0xb3, INSTR_RRF_M0RR }, + { "crt", 0x72, INSTR_RRF_U0RR }, + { "cgrt", 0x60, INSTR_RRF_U0RR }, + { "clrt", 0x73, INSTR_RRF_U0RR }, + { "clgrt", 0x61, INSTR_RRF_U0RR }, + { "ptf", 0xa2, INSTR_RRE_R0 }, + { "pfmf", 0xaf, INSTR_RRE_RR }, + { "trte", 0xbf, INSTR_RRF_M0RR }, + { "trtre", 0xbd, INSTR_RRF_M0RR }, + { "ahhhr", 0xc8, INSTR_RRF_R0RR2 }, + { "shhhr", 0xc9, INSTR_RRF_R0RR2 }, + { "alhhh", 0xca, INSTR_RRF_R0RR2 }, + { "alhhl", 0xca, INSTR_RRF_R0RR2 }, + { "slhhh", 0xcb, INSTR_RRF_R0RR2 }, + { "chhr ", 0xcd, INSTR_RRE_RR }, + { "clhhr", 0xcf, INSTR_RRE_RR }, + { "ahhlr", 0xd8, INSTR_RRF_R0RR2 }, + { "shhlr", 0xd9, INSTR_RRF_R0RR2 }, + { "slhhl", 0xdb, INSTR_RRF_R0RR2 }, + { "chlr", 0xdd, INSTR_RRE_RR }, + { "clhlr", 0xdf, INSTR_RRE_RR }, + { { 0, LONG_INSN_POPCNT }, 0xe1, INSTR_RRE_RR }, + { "locgr", 0xe2, INSTR_RRF_M0RR }, + { "ngrk", 0xe4, INSTR_RRF_R0RR2 }, + { "ogrk", 0xe6, INSTR_RRF_R0RR2 }, + { "xgrk", 0xe7, INSTR_RRF_R0RR2 }, + { "agrk", 0xe8, INSTR_RRF_R0RR2 }, + { "sgrk", 0xe9, INSTR_RRF_R0RR2 }, + { "algrk", 0xea, INSTR_RRF_R0RR2 }, + { "slgrk", 0xeb, INSTR_RRF_R0RR2 }, + { "locr", 0xf2, INSTR_RRF_M0RR }, + { "nrk", 0xf4, INSTR_RRF_R0RR2 }, + { "ork", 0xf6, INSTR_RRF_R0RR2 }, + { "xrk", 0xf7, INSTR_RRF_R0RR2 }, + { "ark", 0xf8, INSTR_RRF_R0RR2 }, + { "srk", 0xf9, INSTR_RRF_R0RR2 }, + { "alrk", 0xfa, INSTR_RRF_R0RR2 }, + { "slrk", 0xfb, INSTR_RRF_R0RR2 }, +#endif + { "kmac", 0x1e, INSTR_RRE_RR }, + { "lrvr", 0x1f, INSTR_RRE_RR }, + { "km", 0x2e, INSTR_RRE_RR }, + { "kmc", 0x2f, INSTR_RRE_RR }, + { "kimd", 0x3e, INSTR_RRE_RR }, + { "klmd", 0x3f, INSTR_RRE_RR }, + { "epsw", 0x8d, INSTR_RRE_RR }, + { "trtt", 0x90, INSTR_RRE_RR }, + { "trtt", 0x90, INSTR_RRF_M0RR }, + { "trto", 0x91, INSTR_RRE_RR }, + { "trto", 0x91, INSTR_RRF_M0RR }, + { "trot", 0x92, INSTR_RRE_RR }, + { "trot", 0x92, INSTR_RRF_M0RR }, + { "troo", 0x93, INSTR_RRE_RR }, + { "troo", 0x93, INSTR_RRF_M0RR }, + { "mlr", 0x96, INSTR_RRE_RR }, + { "dlr", 0x97, INSTR_RRE_RR }, + { "alcr", 0x98, INSTR_RRE_RR }, + { "slbr", 0x99, INSTR_RRE_RR }, + { "", 0, INSTR_INVALID } +}; + +static struct insn opcode_c0[] = { +#ifdef CONFIG_64BIT + { "lgfi", 0x01, INSTR_RIL_RI }, + { "xihf", 0x06, INSTR_RIL_RU }, + { "xilf", 0x07, INSTR_RIL_RU }, + { "iihf", 0x08, INSTR_RIL_RU }, + { "iilf", 0x09, INSTR_RIL_RU }, + { "nihf", 0x0a, INSTR_RIL_RU }, + { "nilf", 0x0b, INSTR_RIL_RU }, + { "oihf", 0x0c, INSTR_RIL_RU }, + { "oilf", 0x0d, INSTR_RIL_RU }, + { "llihf", 0x0e, INSTR_RIL_RU }, + { "llilf", 0x0f, INSTR_RIL_RU }, +#endif + { "larl", 0x00, INSTR_RIL_RP }, + { "brcl", 0x04, INSTR_RIL_UP }, + { "brasl", 0x05, INSTR_RIL_RP }, + { "", 0, INSTR_INVALID } +}; + +static struct insn opcode_c2[] = { +#ifdef CONFIG_64BIT + { "slgfi", 0x04, INSTR_RIL_RU }, + { "slfi", 0x05, INSTR_RIL_RU }, + { "agfi", 0x08, INSTR_RIL_RI }, + { "afi", 0x09, INSTR_RIL_RI }, + { "algfi", 0x0a, INSTR_RIL_RU }, + { "alfi", 0x0b, INSTR_RIL_RU }, + { "cgfi", 0x0c, INSTR_RIL_RI }, + { "cfi", 0x0d, INSTR_RIL_RI }, + { "clgfi", 0x0e, INSTR_RIL_RU }, + { "clfi", 0x0f, INSTR_RIL_RU }, + { "msfi", 0x01, INSTR_RIL_RI }, + { "msgfi", 0x00, INSTR_RIL_RI }, +#endif + { "", 0, INSTR_INVALID } +}; + +static struct insn opcode_c4[] = { +#ifdef CONFIG_64BIT + { "lrl", 0x0d, INSTR_RIL_RP }, + { "lgrl", 0x08, INSTR_RIL_RP }, + { "lgfrl", 0x0c, INSTR_RIL_RP }, + { "lhrl", 0x05, INSTR_RIL_RP }, + { "lghrl", 0x04, INSTR_RIL_RP }, + { { 0, LONG_INSN_LLGFRL }, 0x0e, INSTR_RIL_RP }, + { "llhrl", 0x02, INSTR_RIL_RP }, + { { 0, LONG_INSN_LLGHRL }, 0x06, INSTR_RIL_RP }, + { "strl", 0x0f, INSTR_RIL_RP }, + { "stgrl", 0x0b, INSTR_RIL_RP }, + { "sthrl", 0x07, INSTR_RIL_RP }, +#endif + { "", 0, INSTR_INVALID } +}; + +static struct insn opcode_c6[] = { +#ifdef CONFIG_64BIT + { "crl", 0x0d, INSTR_RIL_RP }, + { "cgrl", 0x08, INSTR_RIL_RP }, + { "cgfrl", 0x0c, INSTR_RIL_RP }, + { "chrl", 0x05, INSTR_RIL_RP }, + { "cghrl", 0x04, INSTR_RIL_RP }, + { "clrl", 0x0f, INSTR_RIL_RP }, + { "clgrl", 0x0a, INSTR_RIL_RP }, + { { 0, LONG_INSN_CLGFRL }, 0x0e, INSTR_RIL_RP }, + { "clhrl", 0x07, INSTR_RIL_RP }, + { { 0, LONG_INSN_CLGHRL }, 0x06, INSTR_RIL_RP }, + { "pfdrl", 0x02, INSTR_RIL_UP }, + { "exrl", 0x00, INSTR_RIL_RP }, +#endif + { "", 0, INSTR_INVALID } +}; + +static struct insn opcode_c8[] = { +#ifdef CONFIG_64BIT + { "mvcos", 0x00, INSTR_SSF_RRDRD }, + { "ectg", 0x01, INSTR_SSF_RRDRD }, + { "csst", 0x02, INSTR_SSF_RRDRD }, + { "lpd", 0x04, INSTR_SSF_RRDRD2 }, + { "lpdg ", 0x05, INSTR_SSF_RRDRD2 }, +#endif + { "", 0, INSTR_INVALID } +}; + +static struct insn opcode_cc[] = { +#ifdef CONFIG_64BIT + { "brcth", 0x06, INSTR_RIL_RP }, + { "aih", 0x08, INSTR_RIL_RI }, + { "alsih", 0x0a, INSTR_RIL_RI }, + { "alsih", 0x0b, INSTR_RIL_RI }, + { "cih", 0x0d, INSTR_RIL_RI }, + { "clih ", 0x0f, INSTR_RIL_RI }, +#endif + { "", 0, INSTR_INVALID } +}; + +static struct insn opcode_e3[] = { +#ifdef CONFIG_64BIT + { "ltg", 0x02, INSTR_RXY_RRRD }, + { "lrag", 0x03, INSTR_RXY_RRRD }, + { "lg", 0x04, INSTR_RXY_RRRD }, + { "cvby", 0x06, INSTR_RXY_RRRD }, + { "ag", 0x08, INSTR_RXY_RRRD }, + { "sg", 0x09, INSTR_RXY_RRRD }, + { "alg", 0x0a, INSTR_RXY_RRRD }, + { "slg", 0x0b, INSTR_RXY_RRRD }, + { "msg", 0x0c, INSTR_RXY_RRRD }, + { "dsg", 0x0d, INSTR_RXY_RRRD }, + { "cvbg", 0x0e, INSTR_RXY_RRRD }, + { "lrvg", 0x0f, INSTR_RXY_RRRD }, + { "lt", 0x12, INSTR_RXY_RRRD }, + { "lray", 0x13, INSTR_RXY_RRRD }, + { "lgf", 0x14, INSTR_RXY_RRRD }, + { "lgh", 0x15, INSTR_RXY_RRRD }, + { "llgf", 0x16, INSTR_RXY_RRRD }, + { "llgt", 0x17, INSTR_RXY_RRRD }, + { "agf", 0x18, INSTR_RXY_RRRD }, + { "sgf", 0x19, INSTR_RXY_RRRD }, + { "algf", 0x1a, INSTR_RXY_RRRD }, + { "slgf", 0x1b, INSTR_RXY_RRRD }, + { "msgf", 0x1c, INSTR_RXY_RRRD }, + { "dsgf", 0x1d, INSTR_RXY_RRRD }, + { "cg", 0x20, INSTR_RXY_RRRD }, + { "clg", 0x21, INSTR_RXY_RRRD }, + { "stg", 0x24, INSTR_RXY_RRRD }, + { "cvdy", 0x26, INSTR_RXY_RRRD }, + { "cvdg", 0x2e, INSTR_RXY_RRRD }, + { "strvg", 0x2f, INSTR_RXY_RRRD }, + { "cgf", 0x30, INSTR_RXY_RRRD }, + { "clgf", 0x31, INSTR_RXY_RRRD }, + { "strvh", 0x3f, INSTR_RXY_RRRD }, + { "bctg", 0x46, INSTR_RXY_RRRD }, + { "sty", 0x50, INSTR_RXY_RRRD }, + { "msy", 0x51, INSTR_RXY_RRRD }, + { "ny", 0x54, INSTR_RXY_RRRD }, + { "cly", 0x55, INSTR_RXY_RRRD }, + { "oy", 0x56, INSTR_RXY_RRRD }, + { "xy", 0x57, INSTR_RXY_RRRD }, + { "ly", 0x58, INSTR_RXY_RRRD }, + { "cy", 0x59, INSTR_RXY_RRRD }, + { "ay", 0x5a, INSTR_RXY_RRRD }, + { "sy", 0x5b, INSTR_RXY_RRRD }, + { "aly", 0x5e, INSTR_RXY_RRRD }, + { "sly", 0x5f, INSTR_RXY_RRRD }, + { "sthy", 0x70, INSTR_RXY_RRRD }, + { "lay", 0x71, INSTR_RXY_RRRD }, + { "stcy", 0x72, INSTR_RXY_RRRD }, + { "icy", 0x73, INSTR_RXY_RRRD }, + { "lb", 0x76, INSTR_RXY_RRRD }, + { "lgb", 0x77, INSTR_RXY_RRRD }, + { "lhy", 0x78, INSTR_RXY_RRRD }, + { "chy", 0x79, INSTR_RXY_RRRD }, + { "ahy", 0x7a, INSTR_RXY_RRRD }, + { "shy", 0x7b, INSTR_RXY_RRRD }, + { "ng", 0x80, INSTR_RXY_RRRD }, + { "og", 0x81, INSTR_RXY_RRRD }, + { "xg", 0x82, INSTR_RXY_RRRD }, + { "mlg", 0x86, INSTR_RXY_RRRD }, + { "dlg", 0x87, INSTR_RXY_RRRD }, + { "alcg", 0x88, INSTR_RXY_RRRD }, + { "slbg", 0x89, INSTR_RXY_RRRD }, + { "stpq", 0x8e, INSTR_RXY_RRRD }, + { "lpq", 0x8f, INSTR_RXY_RRRD }, + { "llgc", 0x90, INSTR_RXY_RRRD }, + { "llgh", 0x91, INSTR_RXY_RRRD }, + { "llc", 0x94, INSTR_RXY_RRRD }, + { "llh", 0x95, INSTR_RXY_RRRD }, + { "cgh", 0x34, INSTR_RXY_RRRD }, + { "laey", 0x75, INSTR_RXY_RRRD }, + { "ltgf", 0x32, INSTR_RXY_RRRD }, + { "mfy", 0x5c, INSTR_RXY_RRRD }, + { "mhy", 0x7c, INSTR_RXY_RRRD }, + { "pfd", 0x36, INSTR_RXY_URRD }, + { "lbh", 0xc0, INSTR_RXY_RRRD }, + { "llch", 0xc2, INSTR_RXY_RRRD }, + { "stch", 0xc3, INSTR_RXY_RRRD }, + { "lhh", 0xc4, INSTR_RXY_RRRD }, + { "llhh", 0xc6, INSTR_RXY_RRRD }, + { "sthh", 0xc7, INSTR_RXY_RRRD }, + { "lfh", 0xca, INSTR_RXY_RRRD }, + { "stfh", 0xcb, INSTR_RXY_RRRD }, + { "chf", 0xcd, INSTR_RXY_RRRD }, + { "clhf", 0xcf, INSTR_RXY_RRRD }, +#endif + { "lrv", 0x1e, INSTR_RXY_RRRD }, + { "lrvh", 0x1f, INSTR_RXY_RRRD }, + { "strv", 0x3e, INSTR_RXY_RRRD }, + { "ml", 0x96, INSTR_RXY_RRRD }, + { "dl", 0x97, INSTR_RXY_RRRD }, + { "alc", 0x98, INSTR_RXY_RRRD }, + { "slb", 0x99, INSTR_RXY_RRRD }, + { "", 0, INSTR_INVALID } +}; + +static struct insn opcode_e5[] = { +#ifdef CONFIG_64BIT + { "strag", 0x02, INSTR_SSE_RDRD }, + { "chhsi", 0x54, INSTR_SIL_RDI }, + { "chsi", 0x5c, INSTR_SIL_RDI }, + { "cghsi", 0x58, INSTR_SIL_RDI }, + { { 0, LONG_INSN_CLHHSI }, 0x55, INSTR_SIL_RDU }, + { { 0, LONG_INSN_CLFHSI }, 0x5d, INSTR_SIL_RDU }, + { { 0, LONG_INSN_CLGHSI }, 0x59, INSTR_SIL_RDU }, + { "mvhhi", 0x44, INSTR_SIL_RDI }, + { "mvhi", 0x4c, INSTR_SIL_RDI }, + { "mvghi", 0x48, INSTR_SIL_RDI }, +#endif + { "lasp", 0x00, INSTR_SSE_RDRD }, + { "tprot", 0x01, INSTR_SSE_RDRD }, + { "mvcsk", 0x0e, INSTR_SSE_RDRD }, + { "mvcdk", 0x0f, INSTR_SSE_RDRD }, + { "", 0, INSTR_INVALID } +}; + +static struct insn opcode_eb[] = { +#ifdef CONFIG_64BIT + { "lmg", 0x04, INSTR_RSY_RRRD }, + { "srag", 0x0a, INSTR_RSY_RRRD }, + { "slag", 0x0b, INSTR_RSY_RRRD }, + { "srlg", 0x0c, INSTR_RSY_RRRD }, + { "sllg", 0x0d, INSTR_RSY_RRRD }, + { "tracg", 0x0f, INSTR_RSY_RRRD }, + { "csy", 0x14, INSTR_RSY_RRRD }, + { "rllg", 0x1c, INSTR_RSY_RRRD }, + { "clmh", 0x20, INSTR_RSY_RURD }, + { "clmy", 0x21, INSTR_RSY_RURD }, + { "stmg", 0x24, INSTR_RSY_RRRD }, + { "stctg", 0x25, INSTR_RSY_CCRD }, + { "stmh", 0x26, INSTR_RSY_RRRD }, + { "stcmh", 0x2c, INSTR_RSY_RURD }, + { "stcmy", 0x2d, INSTR_RSY_RURD }, + { "lctlg", 0x2f, INSTR_RSY_CCRD }, + { "csg", 0x30, INSTR_RSY_RRRD }, + { "cdsy", 0x31, INSTR_RSY_RRRD }, + { "cdsg", 0x3e, INSTR_RSY_RRRD }, + { "bxhg", 0x44, INSTR_RSY_RRRD }, + { "bxleg", 0x45, INSTR_RSY_RRRD }, + { "tmy", 0x51, INSTR_SIY_URD }, + { "mviy", 0x52, INSTR_SIY_URD }, + { "niy", 0x54, INSTR_SIY_URD }, + { "cliy", 0x55, INSTR_SIY_URD }, + { "oiy", 0x56, INSTR_SIY_URD }, + { "xiy", 0x57, INSTR_SIY_URD }, + { "icmh", 0x80, INSTR_RSE_RURD }, + { "icmh", 0x80, INSTR_RSY_RURD }, + { "icmy", 0x81, INSTR_RSY_RURD }, + { "clclu", 0x8f, INSTR_RSY_RRRD }, + { "stmy", 0x90, INSTR_RSY_RRRD }, + { "lmh", 0x96, INSTR_RSY_RRRD }, + { "lmy", 0x98, INSTR_RSY_RRRD }, + { "lamy", 0x9a, INSTR_RSY_AARD }, + { "stamy", 0x9b, INSTR_RSY_AARD }, + { "asi", 0x6a, INSTR_SIY_IRD }, + { "agsi", 0x7a, INSTR_SIY_IRD }, + { "alsi", 0x6e, INSTR_SIY_IRD }, + { "algsi", 0x7e, INSTR_SIY_IRD }, + { "ecag", 0x4c, INSTR_RSY_RRRD }, + { "srak", 0xdc, INSTR_RSY_RRRD }, + { "slak", 0xdd, INSTR_RSY_RRRD }, + { "srlk", 0xde, INSTR_RSY_RRRD }, + { "sllk", 0xdf, INSTR_RSY_RRRD }, + { "locg", 0xe2, INSTR_RSY_RDRM }, + { "stocg", 0xe3, INSTR_RSY_RDRM }, + { "lang", 0xe4, INSTR_RSY_RRRD }, + { "laog", 0xe6, INSTR_RSY_RRRD }, + { "laxg", 0xe7, INSTR_RSY_RRRD }, + { "laag", 0xe8, INSTR_RSY_RRRD }, + { "laalg", 0xea, INSTR_RSY_RRRD }, + { "loc", 0xf2, INSTR_RSY_RDRM }, + { "stoc", 0xf3, INSTR_RSY_RDRM }, + { "lan", 0xf4, INSTR_RSY_RRRD }, + { "lao", 0xf6, INSTR_RSY_RRRD }, + { "lax", 0xf7, INSTR_RSY_RRRD }, + { "laa", 0xf8, INSTR_RSY_RRRD }, + { "laal", 0xfa, INSTR_RSY_RRRD }, +#endif + { "rll", 0x1d, INSTR_RSY_RRRD }, + { "mvclu", 0x8e, INSTR_RSY_RRRD }, + { "tp", 0xc0, INSTR_RSL_R0RD }, + { "", 0, INSTR_INVALID } +}; + +static struct insn opcode_ec[] = { +#ifdef CONFIG_64BIT + { "brxhg", 0x44, INSTR_RIE_RRP }, + { "brxlg", 0x45, INSTR_RIE_RRP }, + { "crb", 0xf6, INSTR_RRS_RRRDU }, + { "cgrb", 0xe4, INSTR_RRS_RRRDU }, + { "crj", 0x76, INSTR_RIE_RRPU }, + { "cgrj", 0x64, INSTR_RIE_RRPU }, + { "cib", 0xfe, INSTR_RIS_RURDI }, + { "cgib", 0xfc, INSTR_RIS_RURDI }, + { "cij", 0x7e, INSTR_RIE_RUPI }, + { "cgij", 0x7c, INSTR_RIE_RUPI }, + { "cit", 0x72, INSTR_RIE_R0IU }, + { "cgit", 0x70, INSTR_RIE_R0IU }, + { "clrb", 0xf7, INSTR_RRS_RRRDU }, + { "clgrb", 0xe5, INSTR_RRS_RRRDU }, + { "clrj", 0x77, INSTR_RIE_RRPU }, + { "clgrj", 0x65, INSTR_RIE_RRPU }, + { "clib", 0xff, INSTR_RIS_RURDU }, + { "clgib", 0xfd, INSTR_RIS_RURDU }, + { "clij", 0x7f, INSTR_RIE_RUPU }, + { "clgij", 0x7d, INSTR_RIE_RUPU }, + { "clfit", 0x73, INSTR_RIE_R0UU }, + { "clgit", 0x71, INSTR_RIE_R0UU }, + { "rnsbg", 0x54, INSTR_RIE_RRUUU }, + { "rxsbg", 0x57, INSTR_RIE_RRUUU }, + { "rosbg", 0x56, INSTR_RIE_RRUUU }, + { "risbg", 0x55, INSTR_RIE_RRUUU }, + { { 0, LONG_INSN_RISBLG }, 0x51, INSTR_RIE_RRUUU }, + { { 0, LONG_INSN_RISBHG }, 0x5D, INSTR_RIE_RRUUU }, + { "ahik", 0xd8, INSTR_RIE_RRI0 }, + { "aghik", 0xd9, INSTR_RIE_RRI0 }, + { { 0, LONG_INSN_ALHSIK }, 0xda, INSTR_RIE_RRI0 }, + { { 0, LONG_INSN_ALGHSIK }, 0xdb, INSTR_RIE_RRI0 }, +#endif + { "", 0, INSTR_INVALID } +}; + +static struct insn opcode_ed[] = { +#ifdef CONFIG_64BIT + { "mayl", 0x38, INSTR_RXF_FRRDF }, + { "myl", 0x39, INSTR_RXF_FRRDF }, + { "may", 0x3a, INSTR_RXF_FRRDF }, + { "my", 0x3b, INSTR_RXF_FRRDF }, + { "mayh", 0x3c, INSTR_RXF_FRRDF }, + { "myh", 0x3d, INSTR_RXF_FRRDF }, + { "ley", 0x64, INSTR_RXY_FRRD }, + { "ldy", 0x65, INSTR_RXY_FRRD }, + { "stey", 0x66, INSTR_RXY_FRRD }, + { "stdy", 0x67, INSTR_RXY_FRRD }, + { "sldt", 0x40, INSTR_RXF_FRRDF }, + { "slxt", 0x48, INSTR_RXF_FRRDF }, + { "srdt", 0x41, INSTR_RXF_FRRDF }, + { "srxt", 0x49, INSTR_RXF_FRRDF }, + { "tdcet", 0x50, INSTR_RXE_FRRD }, + { "tdcdt", 0x54, INSTR_RXE_FRRD }, + { "tdcxt", 0x58, INSTR_RXE_FRRD }, + { "tdget", 0x51, INSTR_RXE_FRRD }, + { "tdgdt", 0x55, INSTR_RXE_FRRD }, + { "tdgxt", 0x59, INSTR_RXE_FRRD }, +#endif + { "ldeb", 0x04, INSTR_RXE_FRRD }, + { "lxdb", 0x05, INSTR_RXE_FRRD }, + { "lxeb", 0x06, INSTR_RXE_FRRD }, + { "mxdb", 0x07, INSTR_RXE_FRRD }, + { "keb", 0x08, INSTR_RXE_FRRD }, + { "ceb", 0x09, INSTR_RXE_FRRD }, + { "aeb", 0x0a, INSTR_RXE_FRRD }, + { "seb", 0x0b, INSTR_RXE_FRRD }, + { "mdeb", 0x0c, INSTR_RXE_FRRD }, + { "deb", 0x0d, INSTR_RXE_FRRD }, + { "maeb", 0x0e, INSTR_RXF_FRRDF }, + { "mseb", 0x0f, INSTR_RXF_FRRDF }, + { "tceb", 0x10, INSTR_RXE_FRRD }, + { "tcdb", 0x11, INSTR_RXE_FRRD }, + { "tcxb", 0x12, INSTR_RXE_FRRD }, + { "sqeb", 0x14, INSTR_RXE_FRRD }, + { "sqdb", 0x15, INSTR_RXE_FRRD }, + { "meeb", 0x17, INSTR_RXE_FRRD }, + { "kdb", 0x18, INSTR_RXE_FRRD }, + { "cdb", 0x19, INSTR_RXE_FRRD }, + { "adb", 0x1a, INSTR_RXE_FRRD }, + { "sdb", 0x1b, INSTR_RXE_FRRD }, + { "mdb", 0x1c, INSTR_RXE_FRRD }, + { "ddb", 0x1d, INSTR_RXE_FRRD }, + { "madb", 0x1e, INSTR_RXF_FRRDF }, + { "msdb", 0x1f, INSTR_RXF_FRRDF }, + { "lde", 0x24, INSTR_RXE_FRRD }, + { "lxd", 0x25, INSTR_RXE_FRRD }, + { "lxe", 0x26, INSTR_RXE_FRRD }, + { "mae", 0x2e, INSTR_RXF_FRRDF }, + { "mse", 0x2f, INSTR_RXF_FRRDF }, + { "sqe", 0x34, INSTR_RXE_FRRD }, + { "sqd", 0x35, INSTR_RXE_FRRD }, + { "mee", 0x37, INSTR_RXE_FRRD }, + { "mad", 0x3e, INSTR_RXF_FRRDF }, + { "msd", 0x3f, INSTR_RXF_FRRDF }, + { "", 0, INSTR_INVALID } +}; + +/* Extracts an operand value from an instruction. */ +static unsigned int extract_operand(unsigned char *code, + const struct operand *operand) +{ + unsigned int val; + int bits; + + /* Extract fragments of the operand byte for byte. */ + code += operand->shift / 8; + bits = (operand->shift & 7) + operand->bits; + val = 0; + do { + val <<= 8; + val |= (unsigned int) *code++; + bits -= 8; + } while (bits > 0); + val >>= -bits; + val &= ((1U << (operand->bits - 1)) << 1) - 1; + + /* Check for special long displacement case. */ + if (operand->bits == 20 && operand->shift == 20) + val = (val & 0xff) << 12 | (val & 0xfff00) >> 8; + + /* Sign extend value if the operand is signed or pc relative. */ + if ((operand->flags & (OPERAND_SIGNED | OPERAND_PCREL)) && + (val & (1U << (operand->bits - 1)))) + val |= (-1U << (operand->bits - 1)) << 1; + + /* Double value if the operand is pc relative. */ + if (operand->flags & OPERAND_PCREL) + val <<= 1; + + /* Length x in an instructions has real length x + 1. */ + if (operand->flags & OPERAND_LENGTH) + val++; + return val; +} + +static inline int insn_length(unsigned char code) +{ + return ((((int) code + 64) >> 7) + 1) << 1; +} + +static struct insn *find_insn(unsigned char *code) +{ + unsigned char opfrag = code[1]; + unsigned char opmask; + struct insn *table; + + switch (code[0]) { + case 0x01: + table = opcode_01; + break; + case 0xa5: + table = opcode_a5; + break; + case 0xa7: + table = opcode_a7; + break; + case 0xb2: + table = opcode_b2; + break; + case 0xb3: + table = opcode_b3; + break; + case 0xb9: + table = opcode_b9; + break; + case 0xc0: + table = opcode_c0; + break; + case 0xc2: + table = opcode_c2; + break; + case 0xc4: + table = opcode_c4; + break; + case 0xc6: + table = opcode_c6; + break; + case 0xc8: + table = opcode_c8; + break; + case 0xcc: + table = opcode_cc; + break; + case 0xe3: + table = opcode_e3; + opfrag = code[5]; + break; + case 0xe5: + table = opcode_e5; + break; + case 0xeb: + table = opcode_eb; + opfrag = code[5]; + break; + case 0xec: + table = opcode_ec; + opfrag = code[5]; + break; + case 0xed: + table = opcode_ed; + opfrag = code[5]; + break; + default: + table = opcode; + opfrag = code[0]; + break; + } + while (table->format != INSTR_INVALID) { + opmask = formats[table->format][0]; + if (table->opfrag == (opfrag & opmask)) + return table; + table++; + } + return NULL; +} + +static int print_insn(char *buffer, unsigned char *code, unsigned long addr) +{ + struct insn *insn; + const unsigned char *ops; + const struct operand *operand; + unsigned int value; + char separator; + char *ptr; + int i; + + ptr = buffer; + insn = find_insn(code); + if (insn) { + if (insn->name[0] == '\0') + ptr += sprintf(ptr, "%s\t", + long_insn_name[(int) insn->name[1]]); + else + ptr += sprintf(ptr, "%.5s\t", insn->name); + /* Extract the operands. */ + separator = 0; + for (ops = formats[insn->format] + 1, i = 0; + *ops != 0 && i < 6; ops++, i++) { + operand = operands + *ops; + value = extract_operand(code, operand); + if ((operand->flags & OPERAND_INDEX) && value == 0) + continue; + if ((operand->flags & OPERAND_BASE) && + value == 0 && separator == '(') { + separator = ','; + continue; + } + if (separator) + ptr += sprintf(ptr, "%c", separator); + if (operand->flags & OPERAND_GPR) + ptr += sprintf(ptr, "%%r%i", value); + else if (operand->flags & OPERAND_FPR) + ptr += sprintf(ptr, "%%f%i", value); + else if (operand->flags & OPERAND_AR) + ptr += sprintf(ptr, "%%a%i", value); + else if (operand->flags & OPERAND_CR) + ptr += sprintf(ptr, "%%c%i", value); + else if (operand->flags & OPERAND_PCREL) + ptr += sprintf(ptr, "%lx", (signed int) value + + addr); + else if (operand->flags & OPERAND_SIGNED) + ptr += sprintf(ptr, "%i", value); + else + ptr += sprintf(ptr, "%u", value); + if (operand->flags & OPERAND_DISP) + separator = '('; + else if (operand->flags & OPERAND_BASE) { + ptr += sprintf(ptr, ")"); + separator = ','; + } else + separator = ','; + } + } else + ptr += sprintf(ptr, "unknown"); + return (int) (ptr - buffer); +} + +void show_code(struct pt_regs *regs) +{ + char *mode = (regs->psw.mask & PSW_MASK_PSTATE) ? "User" : "Krnl"; + unsigned char code[64]; + char buffer[64], *ptr; + mm_segment_t old_fs; + unsigned long addr; + int start, end, opsize, hops, i; + + /* Get a snapshot of the 64 bytes surrounding the fault address. */ + old_fs = get_fs(); + set_fs((regs->psw.mask & PSW_MASK_PSTATE) ? USER_DS : KERNEL_DS); + for (start = 32; start && regs->psw.addr >= 34 - start; start -= 2) { + addr = regs->psw.addr - 34 + start; + if (__copy_from_user(code + start - 2, + (char __user *) addr, 2)) + break; + } + for (end = 32; end < 64; end += 2) { + addr = regs->psw.addr + end - 32; + if (__copy_from_user(code + end, + (char __user *) addr, 2)) + break; + } + set_fs(old_fs); + /* Code snapshot useable ? */ + if ((regs->psw.addr & 1) || start >= end) { + printk("%s Code: Bad PSW.\n", mode); + return; + } + /* Find a starting point for the disassembly. */ + while (start < 32) { + for (i = 0, hops = 0; start + i < 32 && hops < 3; hops++) { + if (!find_insn(code + start + i)) + break; + i += insn_length(code[start + i]); + } + if (start + i == 32) + /* Looks good, sequence ends at PSW. */ + break; + start += 2; + } + /* Decode the instructions. */ + ptr = buffer; + ptr += sprintf(ptr, "%s Code:", mode); + hops = 0; + while (start < end && hops < 8) { + opsize = insn_length(code[start]); + if (start + opsize == 32) + *ptr++ = '#'; + else if (start == 32) + *ptr++ = '>'; + else + *ptr++ = ' '; + addr = regs->psw.addr + start - 32; + ptr += sprintf(ptr, ONELONG, addr); + if (start + opsize >= end) + break; + for (i = 0; i < opsize; i++) + ptr += sprintf(ptr, "%02x", code[start + i]); + *ptr++ = '\t'; + if (i < 6) + *ptr++ = '\t'; + ptr += print_insn(ptr, code + start, addr); + start += opsize; + printk(buffer); + ptr = buffer; + ptr += sprintf(ptr, "\n "); + hops++; + } + printk("\n"); +} diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c new file mode 100644 index 00000000..9475e682 --- /dev/null +++ b/arch/s390/kernel/early.c @@ -0,0 +1,482 @@ +/* + * arch/s390/kernel/early.c + * + * Copyright IBM Corp. 2007, 2009 + * Author(s): Hongjie Yang <hongjie@us.ibm.com>, + * Heiko Carstens <heiko.carstens@de.ibm.com> + */ + +#define KMSG_COMPONENT "setup" +#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt + +#include <linux/compiler.h> +#include <linux/init.h> +#include <linux/errno.h> +#include <linux/string.h> +#include <linux/ctype.h> +#include <linux/ftrace.h> +#include <linux/lockdep.h> +#include <linux/module.h> +#include <linux/pfn.h> +#include <linux/uaccess.h> +#include <linux/kernel.h> +#include <asm/ebcdic.h> +#include <asm/ipl.h> +#include <asm/lowcore.h> +#include <asm/processor.h> +#include <asm/sections.h> +#include <asm/setup.h> +#include <asm/sysinfo.h> +#include <asm/cpcmd.h> +#include <asm/sclp.h> +#include <asm/facility.h> +#include "entry.h" + +/* + * Create a Kernel NSS if the SAVESYS= parameter is defined + */ +#define DEFSYS_CMD_SIZE 128 +#define SAVESYS_CMD_SIZE 32 + +char kernel_nss_name[NSS_NAME_SIZE + 1]; + +static void __init setup_boot_command_line(void); + +/* + * Get the TOD clock running. + */ +static void __init reset_tod_clock(void) +{ + u64 time; + + if (store_clock(&time) == 0) + return; + /* TOD clock not running. Set the clock to Unix Epoch. */ + if (set_clock(TOD_UNIX_EPOCH) != 0 || store_clock(&time) != 0) + disabled_wait(0); + + sched_clock_base_cc = TOD_UNIX_EPOCH; + S390_lowcore.last_update_clock = sched_clock_base_cc; +} + +#ifdef CONFIG_SHARED_KERNEL +int __init savesys_ipl_nss(char *cmd, const int cmdlen); + +asm( + " .section .init.text,\"ax\",@progbits\n" + " .align 4\n" + " .type savesys_ipl_nss, @function\n" + "savesys_ipl_nss:\n" +#ifdef CONFIG_64BIT + " stmg 6,15,48(15)\n" + " lgr 14,3\n" + " sam31\n" + " diag 2,14,0x8\n" + " sam64\n" + " lgr 2,14\n" + " lmg 6,15,48(15)\n" +#else + " stm 6,15,24(15)\n" + " lr 14,3\n" + " diag 2,14,0x8\n" + " lr 2,14\n" + " lm 6,15,24(15)\n" +#endif + " br 14\n" + " .size savesys_ipl_nss, .-savesys_ipl_nss\n" + " .previous\n"); + +static __initdata char upper_command_line[COMMAND_LINE_SIZE]; + +static noinline __init void create_kernel_nss(void) +{ + unsigned int i, stext_pfn, eshared_pfn, end_pfn, min_size; +#ifdef CONFIG_BLK_DEV_INITRD + unsigned int sinitrd_pfn, einitrd_pfn; +#endif + int response; + int hlen; + size_t len; + char *savesys_ptr; + char defsys_cmd[DEFSYS_CMD_SIZE]; + char savesys_cmd[SAVESYS_CMD_SIZE]; + + /* Do nothing if we are not running under VM */ + if (!MACHINE_IS_VM) + return; + + /* Convert COMMAND_LINE to upper case */ + for (i = 0; i < strlen(boot_command_line); i++) + upper_command_line[i] = toupper(boot_command_line[i]); + + savesys_ptr = strstr(upper_command_line, "SAVESYS="); + + if (!savesys_ptr) + return; + + savesys_ptr += 8; /* Point to the beginning of the NSS name */ + for (i = 0; i < NSS_NAME_SIZE; i++) { + if (savesys_ptr[i] == ' ' || savesys_ptr[i] == '\0') + break; + kernel_nss_name[i] = savesys_ptr[i]; + } + + stext_pfn = PFN_DOWN(__pa(&_stext)); + eshared_pfn = PFN_DOWN(__pa(&_eshared)); + end_pfn = PFN_UP(__pa(&_end)); + min_size = end_pfn << 2; + + hlen = snprintf(defsys_cmd, DEFSYS_CMD_SIZE, + "DEFSYS %s 00000-%.5X EW %.5X-%.5X SR %.5X-%.5X", + kernel_nss_name, stext_pfn - 1, stext_pfn, + eshared_pfn - 1, eshared_pfn, end_pfn); + +#ifdef CONFIG_BLK_DEV_INITRD + if (INITRD_START && INITRD_SIZE) { + sinitrd_pfn = PFN_DOWN(__pa(INITRD_START)); + einitrd_pfn = PFN_UP(__pa(INITRD_START + INITRD_SIZE)); + min_size = einitrd_pfn << 2; + hlen += snprintf(defsys_cmd + hlen, DEFSYS_CMD_SIZE - hlen, + " EW %.5X-%.5X", sinitrd_pfn, einitrd_pfn); + } +#endif + + snprintf(defsys_cmd + hlen, DEFSYS_CMD_SIZE - hlen, + " EW MINSIZE=%.7iK PARMREGS=0-13", min_size); + defsys_cmd[DEFSYS_CMD_SIZE - 1] = '\0'; + snprintf(savesys_cmd, SAVESYS_CMD_SIZE, "SAVESYS %s \n IPL %s", + kernel_nss_name, kernel_nss_name); + savesys_cmd[SAVESYS_CMD_SIZE - 1] = '\0'; + + __cpcmd(defsys_cmd, NULL, 0, &response); + + if (response != 0) { + pr_err("Defining the Linux kernel NSS failed with rc=%d\n", + response); + kernel_nss_name[0] = '\0'; + return; + } + + len = strlen(savesys_cmd); + ASCEBC(savesys_cmd, len); + response = savesys_ipl_nss(savesys_cmd, len); + + /* On success: response is equal to the command size, + * max SAVESYS_CMD_SIZE + * On error: response contains the numeric portion of cp error message. + * for SAVESYS it will be >= 263 + * for missing privilege class, it will be 1 + */ + if (response > SAVESYS_CMD_SIZE || response == 1) { + pr_err("Saving the Linux kernel NSS failed with rc=%d\n", + response); + kernel_nss_name[0] = '\0'; + return; + } + + /* re-initialize cputime accounting. */ + sched_clock_base_cc = get_clock(); + S390_lowcore.last_update_clock = sched_clock_base_cc; + S390_lowcore.last_update_timer = 0x7fffffffffffffffULL; + S390_lowcore.user_timer = 0; + S390_lowcore.system_timer = 0; + asm volatile("SPT 0(%0)" : : "a" (&S390_lowcore.last_update_timer)); + + /* re-setup boot command line with new ipl vm parms */ + ipl_update_parameters(); + setup_boot_command_line(); + + ipl_flags = IPL_NSS_VALID; +} + +#else /* CONFIG_SHARED_KERNEL */ + +static inline void create_kernel_nss(void) { } + +#endif /* CONFIG_SHARED_KERNEL */ + +/* + * Clear bss memory + */ +static noinline __init void clear_bss_section(void) +{ + memset(__bss_start, 0, __bss_stop - __bss_start); +} + +/* + * Initialize storage key for kernel pages + */ +static noinline __init void init_kernel_storage_key(void) +{ + unsigned long end_pfn, init_pfn; + + end_pfn = PFN_UP(__pa(&_end)); + + for (init_pfn = 0 ; init_pfn < end_pfn; init_pfn++) + page_set_storage_key(init_pfn << PAGE_SHIFT, + PAGE_DEFAULT_KEY, 0); +} + +static __initdata struct sysinfo_3_2_2 vmms __aligned(PAGE_SIZE); + +static noinline __init void detect_machine_type(void) +{ + /* Check current-configuration-level */ + if ((stsi(NULL, 0, 0, 0) >> 28) <= 2) { + S390_lowcore.machine_flags |= MACHINE_FLAG_LPAR; + return; + } + /* Get virtual-machine cpu information. */ + if (stsi(&vmms, 3, 2, 2) == -ENOSYS || !vmms.count) + return; + + /* Running under KVM? If not we assume z/VM */ + if (!memcmp(vmms.vm[0].cpi, "\xd2\xe5\xd4", 3)) + S390_lowcore.machine_flags |= MACHINE_FLAG_KVM; + else + S390_lowcore.machine_flags |= MACHINE_FLAG_VM; +} + +static __init void early_pgm_check_handler(void) +{ + unsigned long addr; + const struct exception_table_entry *fixup; + + addr = S390_lowcore.program_old_psw.addr; + fixup = search_exception_tables(addr & PSW_ADDR_INSN); + if (!fixup) + disabled_wait(0); + S390_lowcore.program_old_psw.addr = fixup->fixup | PSW_ADDR_AMODE; +} + +static noinline __init void setup_lowcore_early(void) +{ + psw_t psw; + + psw.mask = PSW_MASK_BASE | PSW_DEFAULT_KEY | PSW_MASK_EA | PSW_MASK_BA; + psw.addr = PSW_ADDR_AMODE | (unsigned long) s390_base_ext_handler; + S390_lowcore.external_new_psw = psw; + psw.addr = PSW_ADDR_AMODE | (unsigned long) s390_base_pgm_handler; + S390_lowcore.program_new_psw = psw; + s390_base_pgm_handler_fn = early_pgm_check_handler; +} + +static noinline __init void setup_facility_list(void) +{ + stfle(S390_lowcore.stfle_fac_list, + ARRAY_SIZE(S390_lowcore.stfle_fac_list)); +} + +static noinline __init void setup_hpage(void) +{ +#ifndef CONFIG_DEBUG_PAGEALLOC + if (!test_facility(2) || !test_facility(8)) + return; + S390_lowcore.machine_flags |= MACHINE_FLAG_HPAGE; + __ctl_set_bit(0, 23); +#endif +} + +static __init void detect_mvpg(void) +{ +#ifndef CONFIG_64BIT + int rc; + + asm volatile( + " la 0,0\n" + " mvpg %2,%2\n" + "0: la %0,0\n" + "1:\n" + EX_TABLE(0b,1b) + : "=d" (rc) : "0" (-EOPNOTSUPP), "a" (0) : "memory", "cc", "0"); + if (!rc) + S390_lowcore.machine_flags |= MACHINE_FLAG_MVPG; +#endif +} + +static __init void detect_ieee(void) +{ +#ifndef CONFIG_64BIT + int rc, tmp; + + asm volatile( + " efpc %1,0\n" + "0: la %0,0\n" + "1:\n" + EX_TABLE(0b,1b) + : "=d" (rc), "=d" (tmp): "0" (-EOPNOTSUPP) : "cc"); + if (!rc) + S390_lowcore.machine_flags |= MACHINE_FLAG_IEEE; +#endif +} + +static __init void detect_csp(void) +{ +#ifndef CONFIG_64BIT + int rc; + + asm volatile( + " la 0,0\n" + " la 1,0\n" + " la 2,4\n" + " csp 0,2\n" + "0: la %0,0\n" + "1:\n" + EX_TABLE(0b,1b) + : "=d" (rc) : "0" (-EOPNOTSUPP) : "cc", "0", "1", "2"); + if (!rc) + S390_lowcore.machine_flags |= MACHINE_FLAG_CSP; +#endif +} + +static __init void detect_diag9c(void) +{ + unsigned int cpu_address; + int rc; + + cpu_address = stap(); + asm volatile( + " diag %2,0,0x9c\n" + "0: la %0,0\n" + "1:\n" + EX_TABLE(0b,1b) + : "=d" (rc) : "0" (-EOPNOTSUPP), "d" (cpu_address) : "cc"); + if (!rc) + S390_lowcore.machine_flags |= MACHINE_FLAG_DIAG9C; +} + +static __init void detect_diag44(void) +{ +#ifdef CONFIG_64BIT + int rc; + + asm volatile( + " diag 0,0,0x44\n" + "0: la %0,0\n" + "1:\n" + EX_TABLE(0b,1b) + : "=d" (rc) : "0" (-EOPNOTSUPP) : "cc"); + if (!rc) + S390_lowcore.machine_flags |= MACHINE_FLAG_DIAG44; +#endif +} + +static __init void detect_machine_facilities(void) +{ +#ifdef CONFIG_64BIT + if (test_facility(3)) + S390_lowcore.machine_flags |= MACHINE_FLAG_IDTE; + if (test_facility(8)) + S390_lowcore.machine_flags |= MACHINE_FLAG_PFMF; + if (test_facility(11)) + S390_lowcore.machine_flags |= MACHINE_FLAG_TOPOLOGY; + if (test_facility(27)) + S390_lowcore.machine_flags |= MACHINE_FLAG_MVCOS; + if (test_facility(40)) + S390_lowcore.machine_flags |= MACHINE_FLAG_SPP; + if (test_facility(25)) + S390_lowcore.machine_flags |= MACHINE_FLAG_STCKF; +#endif +} + +static __init void rescue_initrd(void) +{ +#ifdef CONFIG_BLK_DEV_INITRD + unsigned long min_initrd_addr = (unsigned long) _end + (4UL << 20); + /* + * Just like in case of IPL from VM reader we make sure there is a + * gap of 4MB between end of kernel and start of initrd. + * That way we can also be sure that saving an NSS will succeed, + * which however only requires different segments. + */ + if (!INITRD_START || !INITRD_SIZE) + return; + if (INITRD_START >= min_initrd_addr) + return; + memmove((void *) min_initrd_addr, (void *) INITRD_START, INITRD_SIZE); + INITRD_START = min_initrd_addr; +#endif +} + +/* Set up boot command line */ +static void __init append_to_cmdline(size_t (*ipl_data)(char *, size_t)) +{ + char *parm, *delim; + size_t rc, len; + + len = strlen(boot_command_line); + + delim = boot_command_line + len; /* '\0' character position */ + parm = boot_command_line + len + 1; /* append right after '\0' */ + + rc = ipl_data(parm, COMMAND_LINE_SIZE - len - 1); + if (rc) { + if (*parm == '=') + memmove(boot_command_line, parm + 1, rc); + else + *delim = ' '; /* replace '\0' with space */ + } +} + +static inline int has_ebcdic_char(const char *str) +{ + int i; + + for (i = 0; str[i]; i++) + if (str[i] & 0x80) + return 1; + return 0; +} + +static void __init setup_boot_command_line(void) +{ + COMMAND_LINE[ARCH_COMMAND_LINE_SIZE - 1] = 0; + /* convert arch command line to ascii if necessary */ + if (has_ebcdic_char(COMMAND_LINE)) + EBCASC(COMMAND_LINE, ARCH_COMMAND_LINE_SIZE); + /* copy arch command line */ + strlcpy(boot_command_line, strstrip(COMMAND_LINE), + ARCH_COMMAND_LINE_SIZE); + + /* append IPL PARM data to the boot command line */ + if (MACHINE_IS_VM) + append_to_cmdline(append_ipl_vmparm); + + append_to_cmdline(append_ipl_scpdata); +} + + +/* + * Save ipl parameters, clear bss memory, initialize storage keys + * and create a kernel NSS at startup if the SAVESYS= parm is defined + */ +void __init startup_init(void) +{ + reset_tod_clock(); + ipl_save_parameters(); + rescue_initrd(); + clear_bss_section(); + init_kernel_storage_key(); + lockdep_init(); + lockdep_off(); + sort_main_extable(); + setup_lowcore_early(); + setup_facility_list(); + detect_machine_type(); + ipl_update_parameters(); + setup_boot_command_line(); + create_kernel_nss(); + detect_mvpg(); + detect_ieee(); + detect_csp(); + detect_diag9c(); + detect_diag44(); + detect_machine_facilities(); + setup_hpage(); + sclp_facilities_detect(); + detect_memory_layout(memory_chunk); +#ifdef CONFIG_DYNAMIC_FTRACE + S390_lowcore.ftrace_func = (unsigned long)ftrace_caller; +#endif + lockdep_on(); +} diff --git a/arch/s390/kernel/ebcdic.c b/arch/s390/kernel/ebcdic.c new file mode 100644 index 00000000..cc0dc609 --- /dev/null +++ b/arch/s390/kernel/ebcdic.c @@ -0,0 +1,401 @@ +/* + * arch/s390/kernel/ebcdic.c + * ECBDIC -> ASCII, ASCII -> ECBDIC, + * upper to lower case (EBCDIC) conversion tables. + * + * S390 version + * Copyright (C) 1999 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com> + * Martin Peschke <peschke@fh-brandenburg.de> + */ + +#include <linux/module.h> +#include <asm/types.h> +#include <asm/ebcdic.h> + +/* + * ASCII (IBM PC 437) -> EBCDIC 037 + */ +__u8 _ascebc[256] = +{ + /*00 NUL SOH STX ETX EOT ENQ ACK BEL */ + 0x00, 0x01, 0x02, 0x03, 0x37, 0x2D, 0x2E, 0x2F, + /*08 BS HT LF VT FF CR SO SI */ + /* ->NL */ + 0x16, 0x05, 0x15, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F, + /*10 DLE DC1 DC2 DC3 DC4 NAK SYN ETB */ + 0x10, 0x11, 0x12, 0x13, 0x3C, 0x3D, 0x32, 0x26, + /*18 CAN EM SUB ESC FS GS RS US */ + /* ->IGS ->IRS ->IUS */ + 0x18, 0x19, 0x3F, 0x27, 0x22, 0x1D, 0x1E, 0x1F, + /*20 SP ! " # $ % & ' */ + 0x40, 0x5A, 0x7F, 0x7B, 0x5B, 0x6C, 0x50, 0x7D, + /*28 ( ) * + , - . / */ + 0x4D, 0x5D, 0x5C, 0x4E, 0x6B, 0x60, 0x4B, 0x61, + /*30 0 1 2 3 4 5 6 7 */ + 0xF0, 0xF1, 0xF2, 0xF3, 0xF4, 0xF5, 0xF6, 0xF7, + /*38 8 9 : ; < = > ? */ + 0xF8, 0xF9, 0x7A, 0x5E, 0x4C, 0x7E, 0x6E, 0x6F, + /*40 @ A B C D E F G */ + 0x7C, 0xC1, 0xC2, 0xC3, 0xC4, 0xC5, 0xC6, 0xC7, + /*48 H I J K L M N O */ + 0xC8, 0xC9, 0xD1, 0xD2, 0xD3, 0xD4, 0xD5, 0xD6, + /*50 P Q R S T U V W */ + 0xD7, 0xD8, 0xD9, 0xE2, 0xE3, 0xE4, 0xE5, 0xE6, + /*58 X Y Z [ \ ] ^ _ */ + 0xE7, 0xE8, 0xE9, 0xBA, 0xE0, 0xBB, 0xB0, 0x6D, + /*60 ` a b c d e f g */ + 0x79, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, + /*68 h i j k l m n o */ + 0x88, 0x89, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, + /*70 p q r s t u v w */ + 0x97, 0x98, 0x99, 0xA2, 0xA3, 0xA4, 0xA5, 0xA6, + /*78 x y z { | } ~ DL */ + 0xA7, 0xA8, 0xA9, 0xC0, 0x4F, 0xD0, 0xA1, 0x07, + /*80*/ + 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, + /*88*/ + 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, + /*90*/ + 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, + /*98*/ + 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, + /*A0*/ + 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, + /*A8*/ + 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, + /*B0*/ + 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, + /*B8*/ + 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, + /*C0*/ + 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, + /*C8*/ + 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, + /*D0*/ + 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, + /*D8*/ + 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, + /*E0 sz */ + 0x3F, 0x59, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, + /*E8*/ + 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, + /*F0*/ + 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, + /*F8*/ + 0x90, 0x3F, 0x3F, 0x3F, 0x3F, 0xEA, 0x3F, 0xFF +}; + +/* + * EBCDIC 037 -> ASCII (IBM PC 437) + */ +__u8 _ebcasc[256] = +{ + /* 0x00 NUL SOH STX ETX *SEL HT *RNL DEL */ + 0x00, 0x01, 0x02, 0x03, 0x07, 0x09, 0x07, 0x7F, + /* 0x08 -GE -SPS -RPT VT FF CR SO SI */ + 0x07, 0x07, 0x07, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F, + /* 0x10 DLE DC1 DC2 DC3 -RES -NL BS -POC + -ENP ->LF */ + 0x10, 0x11, 0x12, 0x13, 0x07, 0x0A, 0x08, 0x07, + /* 0x18 CAN EM -UBS -CU1 -IFS -IGS -IRS -ITB + -IUS */ + 0x18, 0x19, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, + /* 0x20 -DS -SOS FS -WUS -BYP LF ETB ESC + -INP */ + 0x07, 0x07, 0x1C, 0x07, 0x07, 0x0A, 0x17, 0x1B, + /* 0x28 -SA -SFE -SM -CSP -MFA ENQ ACK BEL + -SW */ + 0x07, 0x07, 0x07, 0x07, 0x07, 0x05, 0x06, 0x07, + /* 0x30 ---- ---- SYN -IR -PP -TRN -NBS EOT */ + 0x07, 0x07, 0x16, 0x07, 0x07, 0x07, 0x07, 0x04, + /* 0x38 -SBS -IT -RFF -CU3 DC4 NAK ---- SUB */ + 0x07, 0x07, 0x07, 0x07, 0x14, 0x15, 0x07, 0x1A, + /* 0x40 SP RSP ä ---- */ + 0x20, 0xFF, 0x83, 0x84, 0x85, 0xA0, 0x07, 0x86, + /* 0x48 . < ( + | */ + 0x87, 0xA4, 0x9B, 0x2E, 0x3C, 0x28, 0x2B, 0x7C, + /* 0x50 & ---- */ + 0x26, 0x82, 0x88, 0x89, 0x8A, 0xA1, 0x8C, 0x07, + /* 0x58 ß ! $ * ) ; */ + 0x8D, 0xE1, 0x21, 0x24, 0x2A, 0x29, 0x3B, 0xAA, + /* 0x60 - / ---- Ä ---- ---- ---- */ + 0x2D, 0x2F, 0x07, 0x8E, 0x07, 0x07, 0x07, 0x8F, + /* 0x68 ---- , % _ > ? */ + 0x80, 0xA5, 0x07, 0x2C, 0x25, 0x5F, 0x3E, 0x3F, + /* 0x70 ---- ---- ---- ---- ---- ---- ---- */ + 0x07, 0x90, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, + /* 0x78 * ` : # @ ' = " */ + 0x70, 0x60, 0x3A, 0x23, 0x40, 0x27, 0x3D, 0x22, + /* 0x80 * a b c d e f g */ + 0x07, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, + /* 0x88 h i ---- ---- ---- */ + 0x68, 0x69, 0xAE, 0xAF, 0x07, 0x07, 0x07, 0xF1, + /* 0x90 ° j k l m n o p */ + 0xF8, 0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x6F, 0x70, + /* 0x98 q r ---- ---- */ + 0x71, 0x72, 0xA6, 0xA7, 0x91, 0x07, 0x92, 0x07, + /* 0xA0 ~ s t u v w x */ + 0xE6, 0x7E, 0x73, 0x74, 0x75, 0x76, 0x77, 0x78, + /* 0xA8 y z ---- ---- ---- ---- */ + 0x79, 0x7A, 0xAD, 0xAB, 0x07, 0x07, 0x07, 0x07, + /* 0xB0 ^ ---- § ---- */ + 0x5E, 0x9C, 0x9D, 0xFA, 0x07, 0x07, 0x07, 0xAC, + /* 0xB8 ---- [ ] ---- ---- ---- ---- */ + 0xAB, 0x07, 0x5B, 0x5D, 0x07, 0x07, 0x07, 0x07, + /* 0xC0 { A B C D E F G */ + 0x7B, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, + /* 0xC8 H I ---- ö ---- */ + 0x48, 0x49, 0x07, 0x93, 0x94, 0x95, 0xA2, 0x07, + /* 0xD0 } J K L M N O P */ + 0x7D, 0x4A, 0x4B, 0x4C, 0x4D, 0x4E, 0x4F, 0x50, + /* 0xD8 Q R ---- ü */ + 0x51, 0x52, 0x07, 0x96, 0x81, 0x97, 0xA3, 0x98, + /* 0xE0 \ S T U V W X */ + 0x5C, 0xF6, 0x53, 0x54, 0x55, 0x56, 0x57, 0x58, + /* 0xE8 Y Z ---- Ö ---- ---- ---- */ + 0x59, 0x5A, 0xFD, 0x07, 0x99, 0x07, 0x07, 0x07, + /* 0xF0 0 1 2 3 4 5 6 7 */ + 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, + /* 0xF8 8 9 ---- ---- Ü ---- ---- ---- */ + 0x38, 0x39, 0x07, 0x07, 0x9A, 0x07, 0x07, 0x07 +}; + + +/* + * ASCII (IBM PC 437) -> EBCDIC 500 + */ +__u8 _ascebc_500[256] = +{ + /*00 NUL SOH STX ETX EOT ENQ ACK BEL */ + 0x00, 0x01, 0x02, 0x03, 0x37, 0x2D, 0x2E, 0x2F, + /*08 BS HT LF VT FF CR SO SI */ + /* ->NL */ + 0x16, 0x05, 0x15, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F, + /*10 DLE DC1 DC2 DC3 DC4 NAK SYN ETB */ + 0x10, 0x11, 0x12, 0x13, 0x3C, 0x3D, 0x32, 0x26, + /*18 CAN EM SUB ESC FS GS RS US */ + /* ->IGS ->IRS ->IUS */ + 0x18, 0x19, 0x3F, 0x27, 0x22, 0x1D, 0x1E, 0x1F, + /*20 SP ! " # $ % & ' */ + 0x40, 0x4F, 0x7F, 0x7B, 0x5B, 0x6C, 0x50, 0x7D, + /*28 ( ) * + , - . / */ + 0x4D, 0x5D, 0x5C, 0x4E, 0x6B, 0x60, 0x4B, 0x61, + /*30 0 1 2 3 4 5 6 7 */ + 0xF0, 0xF1, 0xF2, 0xF3, 0xF4, 0xF5, 0xF6, 0xF7, + /*38 8 9 : ; < = > ? */ + 0xF8, 0xF9, 0x7A, 0x5E, 0x4C, 0x7E, 0x6E, 0x6F, + /*40 @ A B C D E F G */ + 0x7C, 0xC1, 0xC2, 0xC3, 0xC4, 0xC5, 0xC6, 0xC7, + /*48 H I J K L M N O */ + 0xC8, 0xC9, 0xD1, 0xD2, 0xD3, 0xD4, 0xD5, 0xD6, + /*50 P Q R S T U V W */ + 0xD7, 0xD8, 0xD9, 0xE2, 0xE3, 0xE4, 0xE5, 0xE6, + /*58 X Y Z [ \ ] ^ _ */ + 0xE7, 0xE8, 0xE9, 0x4A, 0xE0, 0x5A, 0x5F, 0x6D, + /*60 ` a b c d e f g */ + 0x79, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, + /*68 h i j k l m n o */ + 0x88, 0x89, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, + /*70 p q r s t u v w */ + 0x97, 0x98, 0x99, 0xA2, 0xA3, 0xA4, 0xA5, 0xA6, + /*78 x y z { | } ~ DL */ + 0xA7, 0xA8, 0xA9, 0xC0, 0xBB, 0xD0, 0xA1, 0x07, + /*80*/ + 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, + /*88*/ + 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, + /*90*/ + 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, + /*98*/ + 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, + /*A0*/ + 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, + /*A8*/ + 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, + /*B0*/ + 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, + /*B8*/ + 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, + /*C0*/ + 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, + /*C8*/ + 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, + /*D0*/ + 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, + /*D8*/ + 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, + /*E0 sz */ + 0x3F, 0x59, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, + /*E8*/ + 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, + /*F0*/ + 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, + /*F8*/ + 0x90, 0x3F, 0x3F, 0x3F, 0x3F, 0xEA, 0x3F, 0xFF +}; + +/* + * EBCDIC 500 -> ASCII (IBM PC 437) + */ +__u8 _ebcasc_500[256] = +{ + /* 0x00 NUL SOH STX ETX *SEL HT *RNL DEL */ + 0x00, 0x01, 0x02, 0x03, 0x07, 0x09, 0x07, 0x7F, + /* 0x08 -GE -SPS -RPT VT FF CR SO SI */ + 0x07, 0x07, 0x07, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F, + /* 0x10 DLE DC1 DC2 DC3 -RES -NL BS -POC + -ENP ->LF */ + 0x10, 0x11, 0x12, 0x13, 0x07, 0x0A, 0x08, 0x07, + /* 0x18 CAN EM -UBS -CU1 -IFS -IGS -IRS -ITB + -IUS */ + 0x18, 0x19, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, + /* 0x20 -DS -SOS FS -WUS -BYP LF ETB ESC + -INP */ + 0x07, 0x07, 0x1C, 0x07, 0x07, 0x0A, 0x17, 0x1B, + /* 0x28 -SA -SFE -SM -CSP -MFA ENQ ACK BEL + -SW */ + 0x07, 0x07, 0x07, 0x07, 0x07, 0x05, 0x06, 0x07, + /* 0x30 ---- ---- SYN -IR -PP -TRN -NBS EOT */ + 0x07, 0x07, 0x16, 0x07, 0x07, 0x07, 0x07, 0x04, + /* 0x38 -SBS -IT -RFF -CU3 DC4 NAK ---- SUB */ + 0x07, 0x07, 0x07, 0x07, 0x14, 0x15, 0x07, 0x1A, + /* 0x40 SP RSP ä ---- */ + 0x20, 0xFF, 0x83, 0x84, 0x85, 0xA0, 0x07, 0x86, + /* 0x48 [ . < ( + ! */ + 0x87, 0xA4, 0x5B, 0x2E, 0x3C, 0x28, 0x2B, 0x21, + /* 0x50 & ---- */ + 0x26, 0x82, 0x88, 0x89, 0x8A, 0xA1, 0x8C, 0x07, + /* 0x58 ß ] $ * ) ; ^ */ + 0x8D, 0xE1, 0x5D, 0x24, 0x2A, 0x29, 0x3B, 0x5E, + /* 0x60 - / ---- Ä ---- ---- ---- */ + 0x2D, 0x2F, 0x07, 0x8E, 0x07, 0x07, 0x07, 0x8F, + /* 0x68 ---- , % _ > ? */ + 0x80, 0xA5, 0x07, 0x2C, 0x25, 0x5F, 0x3E, 0x3F, + /* 0x70 ---- ---- ---- ---- ---- ---- ---- */ + 0x07, 0x90, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, + /* 0x78 * ` : # @ ' = " */ + 0x70, 0x60, 0x3A, 0x23, 0x40, 0x27, 0x3D, 0x22, + /* 0x80 * a b c d e f g */ + 0x07, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, + /* 0x88 h i ---- ---- ---- */ + 0x68, 0x69, 0xAE, 0xAF, 0x07, 0x07, 0x07, 0xF1, + /* 0x90 ° j k l m n o p */ + 0xF8, 0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x6F, 0x70, + /* 0x98 q r ---- ---- */ + 0x71, 0x72, 0xA6, 0xA7, 0x91, 0x07, 0x92, 0x07, + /* 0xA0 ~ s t u v w x */ + 0xE6, 0x7E, 0x73, 0x74, 0x75, 0x76, 0x77, 0x78, + /* 0xA8 y z ---- ---- ---- ---- */ + 0x79, 0x7A, 0xAD, 0xAB, 0x07, 0x07, 0x07, 0x07, + /* 0xB0 ---- § ---- */ + 0x9B, 0x9C, 0x9D, 0xFA, 0x07, 0x07, 0x07, 0xAC, + /* 0xB8 ---- | ---- ---- ---- ---- */ + 0xAB, 0x07, 0xAA, 0x7C, 0x07, 0x07, 0x07, 0x07, + /* 0xC0 { A B C D E F G */ + 0x7B, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, + /* 0xC8 H I ---- ö ---- */ + 0x48, 0x49, 0x07, 0x93, 0x94, 0x95, 0xA2, 0x07, + /* 0xD0 } J K L M N O P */ + 0x7D, 0x4A, 0x4B, 0x4C, 0x4D, 0x4E, 0x4F, 0x50, + /* 0xD8 Q R ---- ü */ + 0x51, 0x52, 0x07, 0x96, 0x81, 0x97, 0xA3, 0x98, + /* 0xE0 \ S T U V W X */ + 0x5C, 0xF6, 0x53, 0x54, 0x55, 0x56, 0x57, 0x58, + /* 0xE8 Y Z ---- Ö ---- ---- ---- */ + 0x59, 0x5A, 0xFD, 0x07, 0x99, 0x07, 0x07, 0x07, + /* 0xF0 0 1 2 3 4 5 6 7 */ + 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, + /* 0xF8 8 9 ---- ---- Ü ---- ---- ---- */ + 0x38, 0x39, 0x07, 0x07, 0x9A, 0x07, 0x07, 0x07 +}; + + +/* + * EBCDIC 037/500 conversion table: + * from upper to lower case + */ +__u8 _ebc_tolower[256] = +{ + 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, + 0x08, 0x09, 0x0A, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F, + 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, + 0x18, 0x19, 0x1A, 0x1B, 0x1C, 0x1D, 0x1E, 0x1F, + 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, + 0x28, 0x29, 0x2A, 0x2B, 0x2C, 0x2D, 0x2E, 0x2F, + 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, + 0x38, 0x39, 0x3A, 0x3B, 0x3C, 0x3D, 0x3E, 0x3F, + 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, + 0x48, 0x49, 0x4A, 0x4B, 0x4C, 0x4D, 0x4E, 0x4F, + 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, + 0x58, 0x59, 0x5A, 0x5B, 0x5C, 0x5D, 0x5E, 0x5F, + 0x60, 0x61, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, + 0x48, 0x49, 0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x6F, + 0x70, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, + 0x58, 0x79, 0x7A, 0x7B, 0x7C, 0x7D, 0x7E, 0x7F, + 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, + 0x88, 0x89, 0x8A, 0x8B, 0x8C, 0x8D, 0x8E, 0x8F, + 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, + 0x98, 0x99, 0x9A, 0x9B, 0x9C, 0x9D, 0x9C, 0x9F, + 0xA0, 0xA1, 0xA2, 0xA3, 0xA4, 0xA5, 0xA6, 0xA7, + 0xA8, 0xA9, 0xAA, 0xAB, 0x8C, 0x8D, 0x8E, 0xAF, + 0xB0, 0xB1, 0xB2, 0xB3, 0xB4, 0xB5, 0xB6, 0xB7, + 0xB8, 0xB9, 0xBA, 0xBB, 0xBC, 0xBD, 0xBE, 0xBF, + 0xC0, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, + 0x88, 0x89, 0xCA, 0xCB, 0xCC, 0xCD, 0xCE, 0xCF, + 0xD0, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, + 0x98, 0x99, 0xDA, 0xDB, 0xDC, 0xDD, 0xDE, 0xDF, + 0xE0, 0xE1, 0xA2, 0xA3, 0xA4, 0xA5, 0xA6, 0xA7, + 0xA8, 0xA9, 0xEA, 0xCB, 0xCC, 0xCD, 0xCE, 0xCF, + 0xF0, 0xF1, 0xF2, 0xF3, 0xF4, 0xF5, 0xF6, 0xF7, + 0xF8, 0xF9, 0xFA, 0xDB, 0xDC, 0xDD, 0xDE, 0xFF +}; + + +/* + * EBCDIC 037/500 conversion table: + * from lower to upper case + */ +__u8 _ebc_toupper[256] = +{ + 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, + 0x08, 0x09, 0x0A, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F, + 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, + 0x18, 0x19, 0x1A, 0x1B, 0x1C, 0x1D, 0x1E, 0x1F, + 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, + 0x28, 0x29, 0x2A, 0x2B, 0x2C, 0x2D, 0x2E, 0x2F, + 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, + 0x38, 0x39, 0x3A, 0x3B, 0x3C, 0x3D, 0x3E, 0x3F, + 0x40, 0x41, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, + 0x68, 0x69, 0x4A, 0x4B, 0x4C, 0x4D, 0x4E, 0x4F, + 0x50, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, + 0x78, 0x59, 0x5A, 0x5B, 0x5C, 0x5D, 0x5E, 0x5F, + 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, + 0x68, 0x69, 0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x6F, + 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, + 0x78, 0x79, 0x7A, 0x7B, 0x7C, 0x7D, 0x7E, 0x7F, + 0x80, 0xC1, 0xC2, 0xC3, 0xC4, 0xC5, 0xC6, 0xC7, + 0xC8, 0xC9, 0x8A, 0x8B, 0xAC, 0xAD, 0xAE, 0x8F, + 0x90, 0xD1, 0xD2, 0xD3, 0xD4, 0xD5, 0xD6, 0xD7, + 0xD8, 0xD9, 0x9A, 0x9B, 0x9E, 0x9D, 0x9E, 0x9F, + 0xA0, 0xA1, 0xE2, 0xE3, 0xE4, 0xE5, 0xE6, 0xE7, + 0xE8, 0xE9, 0xAA, 0xAB, 0xAC, 0xAD, 0xAE, 0xAF, + 0xB0, 0xB1, 0xB2, 0xB3, 0xB4, 0xB5, 0xB6, 0xB7, + 0xB8, 0xB9, 0xBA, 0xBB, 0xBC, 0xBD, 0xBE, 0xBF, + 0xC0, 0xC1, 0xC2, 0xC3, 0xC4, 0xC5, 0xC6, 0xC7, + 0xC8, 0xC9, 0xCA, 0xEB, 0xEC, 0xED, 0xEE, 0xEF, + 0xD0, 0xD1, 0xD2, 0xD3, 0xD4, 0xD5, 0xD6, 0xD7, + 0xD8, 0xD9, 0xDA, 0xFB, 0xFC, 0xFD, 0xFE, 0xDF, + 0xE0, 0xE1, 0xE2, 0xE3, 0xE4, 0xE5, 0xE6, 0xE7, + 0xE8, 0xE9, 0xEA, 0xEB, 0xEC, 0xED, 0xEE, 0xEF, + 0xF0, 0xF1, 0xF2, 0xF3, 0xF4, 0xF5, 0xF6, 0xF7, + 0xF8, 0xF9, 0xFA, 0xFB, 0xFC, 0xFD, 0xFE, 0xFF +}; + +EXPORT_SYMBOL(_ascebc_500); +EXPORT_SYMBOL(_ebcasc_500); +EXPORT_SYMBOL(_ascebc); +EXPORT_SYMBOL(_ebcasc); +EXPORT_SYMBOL(_ebc_tolower); +EXPORT_SYMBOL(_ebc_toupper); + diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S new file mode 100644 index 00000000..74ee563f --- /dev/null +++ b/arch/s390/kernel/entry.S @@ -0,0 +1,967 @@ +/* + * arch/s390/kernel/entry.S + * S390 low-level entry points. + * + * Copyright (C) IBM Corp. 1999,2012 + * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com), + * Hartmut Penner (hp@de.ibm.com), + * Denis Joseph Barrow (djbarrow@de.ibm.com,barrow_dj@yahoo.com), + * Heiko Carstens <heiko.carstens@de.ibm.com> + */ + +#include <linux/init.h> +#include <linux/linkage.h> +#include <asm/cache.h> +#include <asm/errno.h> +#include <asm/ptrace.h> +#include <asm/thread_info.h> +#include <asm/asm-offsets.h> +#include <asm/unistd.h> +#include <asm/page.h> + +__PT_R0 = __PT_GPRS +__PT_R1 = __PT_GPRS + 4 +__PT_R2 = __PT_GPRS + 8 +__PT_R3 = __PT_GPRS + 12 +__PT_R4 = __PT_GPRS + 16 +__PT_R5 = __PT_GPRS + 20 +__PT_R6 = __PT_GPRS + 24 +__PT_R7 = __PT_GPRS + 28 +__PT_R8 = __PT_GPRS + 32 +__PT_R9 = __PT_GPRS + 36 +__PT_R10 = __PT_GPRS + 40 +__PT_R11 = __PT_GPRS + 44 +__PT_R12 = __PT_GPRS + 48 +__PT_R13 = __PT_GPRS + 524 +__PT_R14 = __PT_GPRS + 56 +__PT_R15 = __PT_GPRS + 60 + +_TIF_WORK_SVC = (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | \ + _TIF_MCCK_PENDING | _TIF_PER_TRAP ) +_TIF_WORK_INT = (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | \ + _TIF_MCCK_PENDING) +_TIF_TRACE = (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | \ + _TIF_SYSCALL_TRACEPOINT) + +STACK_SHIFT = PAGE_SHIFT + THREAD_ORDER +STACK_SIZE = 1 << STACK_SHIFT + +#define BASED(name) name-system_call(%r13) + + .macro TRACE_IRQS_ON +#ifdef CONFIG_TRACE_IRQFLAGS + basr %r2,%r0 + l %r1,BASED(.Lhardirqs_on) + basr %r14,%r1 # call trace_hardirqs_on_caller +#endif + .endm + + .macro TRACE_IRQS_OFF +#ifdef CONFIG_TRACE_IRQFLAGS + basr %r2,%r0 + l %r1,BASED(.Lhardirqs_off) + basr %r14,%r1 # call trace_hardirqs_off_caller +#endif + .endm + + .macro LOCKDEP_SYS_EXIT +#ifdef CONFIG_LOCKDEP + tm __PT_PSW+1(%r11),0x01 # returning to user ? + jz .+10 + l %r1,BASED(.Llockdep_sys_exit) + basr %r14,%r1 # call lockdep_sys_exit +#endif + .endm + + .macro CHECK_STACK stacksize,savearea +#ifdef CONFIG_CHECK_STACK + tml %r15,\stacksize - CONFIG_STACK_GUARD + la %r14,\savearea + jz stack_overflow +#endif + .endm + + .macro SWITCH_ASYNC savearea,stack,shift + tmh %r8,0x0001 # interrupting from user ? + jnz 1f + lr %r14,%r9 + sl %r14,BASED(.Lcritical_start) + cl %r14,BASED(.Lcritical_length) + jhe 0f + la %r11,\savearea # inside critical section, do cleanup + bras %r14,cleanup_critical + tmh %r8,0x0001 # retest problem state after cleanup + jnz 1f +0: l %r14,\stack # are we already on the target stack? + slr %r14,%r15 + sra %r14,\shift + jnz 1f + CHECK_STACK 1<<\shift,\savearea + j 2f +1: l %r15,\stack # load target stack +2: ahi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) + la %r11,STACK_FRAME_OVERHEAD(%r15) + .endm + + .macro ADD64 high,low,timer + al \high,\timer + al \low,4+\timer + brc 12,.+8 + ahi \high,1 + .endm + + .macro SUB64 high,low,timer + sl \high,\timer + sl \low,4+\timer + brc 3,.+8 + ahi \high,-1 + .endm + + .macro UPDATE_VTIME high,low,enter_timer + lm \high,\low,__LC_EXIT_TIMER + SUB64 \high,\low,\enter_timer + ADD64 \high,\low,__LC_USER_TIMER + stm \high,\low,__LC_USER_TIMER + lm \high,\low,__LC_LAST_UPDATE_TIMER + SUB64 \high,\low,__LC_EXIT_TIMER + ADD64 \high,\low,__LC_SYSTEM_TIMER + stm \high,\low,__LC_SYSTEM_TIMER + mvc __LC_LAST_UPDATE_TIMER(8),\enter_timer + .endm + + .macro REENABLE_IRQS + st %r8,__LC_RETURN_PSW + ni __LC_RETURN_PSW,0xbf + ssm __LC_RETURN_PSW + .endm + + .section .kprobes.text, "ax" + +/* + * Scheduler resume function, called by switch_to + * gpr2 = (task_struct *) prev + * gpr3 = (task_struct *) next + * Returns: + * gpr2 = prev + */ +ENTRY(__switch_to) + l %r4,__THREAD_info(%r2) # get thread_info of prev + l %r5,__THREAD_info(%r3) # get thread_info of next + tm __TI_flags+3(%r4),_TIF_MCCK_PENDING # machine check pending? + jz 0f + ni __TI_flags+3(%r4),255-_TIF_MCCK_PENDING # clear flag in prev + oi __TI_flags+3(%r5),_TIF_MCCK_PENDING # set it in next +0: stm %r6,%r15,__SF_GPRS(%r15) # store gprs of prev task + st %r15,__THREAD_ksp(%r2) # store kernel stack of prev + l %r15,__THREAD_ksp(%r3) # load kernel stack of next + lctl %c4,%c4,__TASK_pid(%r3) # load pid to control reg. 4 + lm %r6,%r15,__SF_GPRS(%r15) # load gprs of next task + st %r3,__LC_CURRENT # store task struct of next + mvc __LC_CURRENT_PID(4,%r0),__TASK_pid(%r3) # store pid of next + st %r5,__LC_THREAD_INFO # store thread info of next + ahi %r5,STACK_SIZE # end of kernel stack of next + st %r5,__LC_KERNEL_STACK # store end of kernel stack + br %r14 + +__critical_start: +/* + * SVC interrupt handler routine. System calls are synchronous events and + * are executed with interrupts enabled. + */ + +ENTRY(system_call) + stpt __LC_SYNC_ENTER_TIMER +sysc_stm: + stm %r8,%r15,__LC_SAVE_AREA_SYNC + l %r12,__LC_THREAD_INFO + l %r13,__LC_SVC_NEW_PSW+4 +sysc_per: + l %r15,__LC_KERNEL_STACK + ahi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) + la %r11,STACK_FRAME_OVERHEAD(%r15) # pointer to pt_regs +sysc_vtime: + UPDATE_VTIME %r8,%r9,__LC_SYNC_ENTER_TIMER + stm %r0,%r7,__PT_R0(%r11) + mvc __PT_R8(32,%r11),__LC_SAVE_AREA_SYNC + mvc __PT_PSW(8,%r11),__LC_SVC_OLD_PSW + mvc __PT_INT_CODE(4,%r11),__LC_SVC_ILC +sysc_do_svc: + oi __TI_flags+3(%r12),_TIF_SYSCALL + lh %r8,__PT_INT_CODE+2(%r11) + sla %r8,2 # shift and test for svc0 + jnz sysc_nr_ok + # svc 0: system call number in %r1 + cl %r1,BASED(.Lnr_syscalls) + jnl sysc_nr_ok + sth %r1,__PT_INT_CODE+2(%r11) + lr %r8,%r1 + sla %r8,2 +sysc_nr_ok: + l %r10,BASED(.Lsys_call_table) # 31 bit system call table + xc __SF_BACKCHAIN(4,%r15),__SF_BACKCHAIN(%r15) + st %r2,__PT_ORIG_GPR2(%r11) + st %r7,STACK_FRAME_OVERHEAD(%r15) + l %r9,0(%r8,%r10) # get system call addr. + tm __TI_flags+2(%r12),_TIF_TRACE >> 8 + jnz sysc_tracesys + basr %r14,%r9 # call sys_xxxx + st %r2,__PT_R2(%r11) # store return value + +sysc_return: + LOCKDEP_SYS_EXIT +sysc_tif: + tm __PT_PSW+1(%r11),0x01 # returning to user ? + jno sysc_restore + tm __TI_flags+3(%r12),_TIF_WORK_SVC + jnz sysc_work # check for work + ni __TI_flags+3(%r12),255-_TIF_SYSCALL +sysc_restore: + mvc __LC_RETURN_PSW(8),__PT_PSW(%r11) + stpt __LC_EXIT_TIMER + lm %r0,%r15,__PT_R0(%r11) + lpsw __LC_RETURN_PSW +sysc_done: + +# +# One of the work bits is on. Find out which one. +# +sysc_work: + tm __TI_flags+3(%r12),_TIF_MCCK_PENDING + jo sysc_mcck_pending + tm __TI_flags+3(%r12),_TIF_NEED_RESCHED + jo sysc_reschedule + tm __TI_flags+3(%r12),_TIF_SIGPENDING + jo sysc_sigpending + tm __TI_flags+3(%r12),_TIF_NOTIFY_RESUME + jo sysc_notify_resume + tm __TI_flags+3(%r12),_TIF_PER_TRAP + jo sysc_singlestep + j sysc_return # beware of critical section cleanup + +# +# _TIF_NEED_RESCHED is set, call schedule +# +sysc_reschedule: + l %r1,BASED(.Lschedule) + la %r14,BASED(sysc_return) + br %r1 # call schedule + +# +# _TIF_MCCK_PENDING is set, call handler +# +sysc_mcck_pending: + l %r1,BASED(.Lhandle_mcck) + la %r14,BASED(sysc_return) + br %r1 # TIF bit will be cleared by handler + +# +# _TIF_SIGPENDING is set, call do_signal +# +sysc_sigpending: + ni __TI_flags+3(%r12),255-_TIF_PER_TRAP # clear TIF_PER_TRAP + lr %r2,%r11 # pass pointer to pt_regs + l %r1,BASED(.Ldo_signal) + basr %r14,%r1 # call do_signal + tm __TI_flags+3(%r12),_TIF_SYSCALL + jno sysc_return + lm %r2,%r7,__PT_R2(%r11) # load svc arguments + xr %r8,%r8 # svc 0 returns -ENOSYS + clc __PT_INT_CODE+2(2,%r11),BASED(.Lnr_syscalls+2) + jnl sysc_nr_ok # invalid svc number -> do svc 0 + lh %r8,__PT_INT_CODE+2(%r11) # load new svc number + sla %r8,2 + j sysc_nr_ok # restart svc + +# +# _TIF_NOTIFY_RESUME is set, call do_notify_resume +# +sysc_notify_resume: + lr %r2,%r11 # pass pointer to pt_regs + l %r1,BASED(.Ldo_notify_resume) + la %r14,BASED(sysc_return) + br %r1 # call do_notify_resume + +# +# _TIF_PER_TRAP is set, call do_per_trap +# +sysc_singlestep: + ni __TI_flags+3(%r12),255-(_TIF_SYSCALL | _TIF_PER_TRAP) + lr %r2,%r11 # pass pointer to pt_regs + l %r1,BASED(.Ldo_per_trap) + la %r14,BASED(sysc_return) + br %r1 # call do_per_trap + +# +# call tracehook_report_syscall_entry/tracehook_report_syscall_exit before +# and after the system call +# +sysc_tracesys: + l %r1,BASED(.Ltrace_enter) + lr %r2,%r11 # pass pointer to pt_regs + la %r3,0 + xr %r0,%r0 + icm %r0,3,__PT_INT_CODE+2(%r11) + st %r0,__PT_R2(%r11) + basr %r14,%r1 # call do_syscall_trace_enter + cl %r2,BASED(.Lnr_syscalls) + jnl sysc_tracenogo + lr %r8,%r2 + sll %r8,2 + l %r9,0(%r8,%r10) +sysc_tracego: + lm %r3,%r7,__PT_R3(%r11) + st %r7,STACK_FRAME_OVERHEAD(%r15) + l %r2,__PT_ORIG_GPR2(%r11) + basr %r14,%r9 # call sys_xxx + st %r2,__PT_R2(%r11) # store return value +sysc_tracenogo: + tm __TI_flags+2(%r12),_TIF_TRACE >> 8 + jz sysc_return + l %r1,BASED(.Ltrace_exit) + lr %r2,%r11 # pass pointer to pt_regs + la %r14,BASED(sysc_return) + br %r1 # call do_syscall_trace_exit + +# +# a new process exits the kernel with ret_from_fork +# +ENTRY(ret_from_fork) + la %r11,STACK_FRAME_OVERHEAD(%r15) + l %r12,__LC_THREAD_INFO + l %r13,__LC_SVC_NEW_PSW+4 + tm __PT_PSW+1(%r11),0x01 # forking a kernel thread ? + jo 0f + st %r15,__PT_R15(%r11) # store stack pointer for new kthread +0: l %r1,BASED(.Lschedule_tail) + basr %r14,%r1 # call schedule_tail + TRACE_IRQS_ON + ssm __LC_SVC_NEW_PSW # reenable interrupts + j sysc_tracenogo + +# +# kernel_execve function needs to deal with pt_regs that is not +# at the usual place +# +ENTRY(kernel_execve) + stm %r12,%r15,48(%r15) + lr %r14,%r15 + l %r13,__LC_SVC_NEW_PSW+4 + ahi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) + st %r14,__SF_BACKCHAIN(%r15) + la %r12,STACK_FRAME_OVERHEAD(%r15) + xc 0(__PT_SIZE,%r12),0(%r12) + l %r1,BASED(.Ldo_execve) + lr %r5,%r12 + basr %r14,%r1 # call do_execve + ltr %r2,%r2 + je 0f + ahi %r15,(STACK_FRAME_OVERHEAD + __PT_SIZE) + lm %r12,%r15,48(%r15) + br %r14 + # execve succeeded. +0: ssm __LC_PGM_NEW_PSW # disable I/O and ext. interrupts + l %r15,__LC_KERNEL_STACK # load ksp + ahi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) + la %r11,STACK_FRAME_OVERHEAD(%r15) + mvc 0(__PT_SIZE,%r11),0(%r12) # copy pt_regs + l %r12,__LC_THREAD_INFO + xc __SF_BACKCHAIN(4,%r15),__SF_BACKCHAIN(%r15) + ssm __LC_SVC_NEW_PSW # reenable interrupts + l %r1,BASED(.Lexecve_tail) + basr %r14,%r1 # call execve_tail + j sysc_return + +/* + * Program check handler routine + */ + +ENTRY(pgm_check_handler) + stpt __LC_SYNC_ENTER_TIMER + stm %r8,%r15,__LC_SAVE_AREA_SYNC + l %r12,__LC_THREAD_INFO + l %r13,__LC_SVC_NEW_PSW+4 + lm %r8,%r9,__LC_PGM_OLD_PSW + tmh %r8,0x0001 # test problem state bit + jnz 1f # -> fault in user space + tmh %r8,0x4000 # PER bit set in old PSW ? + jnz 0f # -> enabled, can't be a double fault + tm __LC_PGM_ILC+3,0x80 # check for per exception + jnz pgm_svcper # -> single stepped svc +0: CHECK_STACK STACK_SIZE,__LC_SAVE_AREA_SYNC + j 2f +1: UPDATE_VTIME %r14,%r15,__LC_SYNC_ENTER_TIMER + l %r15,__LC_KERNEL_STACK +2: ahi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) + la %r11,STACK_FRAME_OVERHEAD(%r15) + stm %r0,%r7,__PT_R0(%r11) + mvc __PT_R8(32,%r11),__LC_SAVE_AREA_SYNC + stm %r8,%r9,__PT_PSW(%r11) + mvc __PT_INT_CODE(4,%r11),__LC_PGM_ILC + mvc __PT_INT_PARM_LONG(4,%r11),__LC_TRANS_EXC_CODE + tm __LC_PGM_ILC+3,0x80 # check for per exception + jz 0f + l %r1,__TI_task(%r12) + tmh %r8,0x0001 # kernel per event ? + jz pgm_kprobe + oi __TI_flags+3(%r12),_TIF_PER_TRAP + mvc __THREAD_per_address(4,%r1),__LC_PER_ADDRESS + mvc __THREAD_per_cause(2,%r1),__LC_PER_CAUSE + mvc __THREAD_per_paid(1,%r1),__LC_PER_PAID +0: REENABLE_IRQS + xc __SF_BACKCHAIN(4,%r15),__SF_BACKCHAIN(%r15) + l %r1,BASED(.Ljump_table) + la %r10,0x7f + n %r10,__PT_INT_CODE(%r11) + je sysc_return + sll %r10,2 + l %r1,0(%r10,%r1) # load address of handler routine + lr %r2,%r11 # pass pointer to pt_regs + basr %r14,%r1 # branch to interrupt-handler + j sysc_return + +# +# PER event in supervisor state, must be kprobes +# +pgm_kprobe: + REENABLE_IRQS + xc __SF_BACKCHAIN(4,%r15),__SF_BACKCHAIN(%r15) + l %r1,BASED(.Ldo_per_trap) + lr %r2,%r11 # pass pointer to pt_regs + basr %r14,%r1 # call do_per_trap + j sysc_return + +# +# single stepped system call +# +pgm_svcper: + oi __TI_flags+3(%r12),_TIF_PER_TRAP + mvc __LC_RETURN_PSW(4),__LC_SVC_NEW_PSW + mvc __LC_RETURN_PSW+4(4),BASED(.Lsysc_per) + lpsw __LC_RETURN_PSW # branch to sysc_per and enable irqs + +/* + * IO interrupt handler routine + */ + +ENTRY(io_int_handler) + stck __LC_INT_CLOCK + stpt __LC_ASYNC_ENTER_TIMER + stm %r8,%r15,__LC_SAVE_AREA_ASYNC + l %r12,__LC_THREAD_INFO + l %r13,__LC_SVC_NEW_PSW+4 + lm %r8,%r9,__LC_IO_OLD_PSW + tmh %r8,0x0001 # interrupting from user ? + jz io_skip + UPDATE_VTIME %r14,%r15,__LC_ASYNC_ENTER_TIMER +io_skip: + SWITCH_ASYNC __LC_SAVE_AREA_ASYNC,__LC_ASYNC_STACK,STACK_SHIFT + stm %r0,%r7,__PT_R0(%r11) + mvc __PT_R8(32,%r11),__LC_SAVE_AREA_ASYNC + stm %r8,%r9,__PT_PSW(%r11) + TRACE_IRQS_OFF + xc __SF_BACKCHAIN(4,%r15),__SF_BACKCHAIN(%r15) + l %r1,BASED(.Ldo_IRQ) + lr %r2,%r11 # pass pointer to pt_regs + basr %r14,%r1 # call do_IRQ +io_return: + LOCKDEP_SYS_EXIT + TRACE_IRQS_ON +io_tif: + tm __TI_flags+3(%r12),_TIF_WORK_INT + jnz io_work # there is work to do (signals etc.) +io_restore: + mvc __LC_RETURN_PSW(8),__PT_PSW(%r11) + stpt __LC_EXIT_TIMER + lm %r0,%r15,__PT_R0(%r11) + lpsw __LC_RETURN_PSW +io_done: + +# +# There is work todo, find out in which context we have been interrupted: +# 1) if we return to user space we can do all _TIF_WORK_INT work +# 2) if we return to kernel code and preemptive scheduling is enabled check +# the preemption counter and if it is zero call preempt_schedule_irq +# Before any work can be done, a switch to the kernel stack is required. +# +io_work: + tm __PT_PSW+1(%r11),0x01 # returning to user ? + jo io_work_user # yes -> do resched & signal +#ifdef CONFIG_PREEMPT + # check for preemptive scheduling + icm %r0,15,__TI_precount(%r12) + jnz io_restore # preemption disabled + tm __TI_flags+3(%r12),_TIF_NEED_RESCHED + jno io_restore + # switch to kernel stack + l %r1,__PT_R15(%r11) + ahi %r1,-(STACK_FRAME_OVERHEAD + __PT_SIZE) + mvc STACK_FRAME_OVERHEAD(__PT_SIZE,%r1),0(%r11) + xc __SF_BACKCHAIN(4,%r1),__SF_BACKCHAIN(%r1) + la %r11,STACK_FRAME_OVERHEAD(%r1) + lr %r15,%r1 + # TRACE_IRQS_ON already done at io_return, call + # TRACE_IRQS_OFF to keep things symmetrical + TRACE_IRQS_OFF + l %r1,BASED(.Lpreempt_irq) + basr %r14,%r1 # call preempt_schedule_irq + j io_return +#else + j io_restore +#endif + +# +# Need to do work before returning to userspace, switch to kernel stack +# +io_work_user: + l %r1,__LC_KERNEL_STACK + ahi %r1,-(STACK_FRAME_OVERHEAD + __PT_SIZE) + mvc STACK_FRAME_OVERHEAD(__PT_SIZE,%r1),0(%r11) + xc __SF_BACKCHAIN(4,%r1),__SF_BACKCHAIN(%r1) + la %r11,STACK_FRAME_OVERHEAD(%r1) + lr %r15,%r1 + +# +# One of the work bits is on. Find out which one. +# Checked are: _TIF_SIGPENDING, _TIF_NOTIFY_RESUME, _TIF_NEED_RESCHED +# and _TIF_MCCK_PENDING +# +io_work_tif: + tm __TI_flags+3(%r12),_TIF_MCCK_PENDING + jo io_mcck_pending + tm __TI_flags+3(%r12),_TIF_NEED_RESCHED + jo io_reschedule + tm __TI_flags+3(%r12),_TIF_SIGPENDING + jo io_sigpending + tm __TI_flags+3(%r12),_TIF_NOTIFY_RESUME + jo io_notify_resume + j io_return # beware of critical section cleanup + +# +# _TIF_MCCK_PENDING is set, call handler +# +io_mcck_pending: + # TRACE_IRQS_ON already done at io_return + l %r1,BASED(.Lhandle_mcck) + basr %r14,%r1 # TIF bit will be cleared by handler + TRACE_IRQS_OFF + j io_return + +# +# _TIF_NEED_RESCHED is set, call schedule +# +io_reschedule: + # TRACE_IRQS_ON already done at io_return + l %r1,BASED(.Lschedule) + ssm __LC_SVC_NEW_PSW # reenable interrupts + basr %r14,%r1 # call scheduler + ssm __LC_PGM_NEW_PSW # disable I/O and ext. interrupts + TRACE_IRQS_OFF + j io_return + +# +# _TIF_SIGPENDING is set, call do_signal +# +io_sigpending: + # TRACE_IRQS_ON already done at io_return + l %r1,BASED(.Ldo_signal) + ssm __LC_SVC_NEW_PSW # reenable interrupts + lr %r2,%r11 # pass pointer to pt_regs + basr %r14,%r1 # call do_signal + ssm __LC_PGM_NEW_PSW # disable I/O and ext. interrupts + TRACE_IRQS_OFF + j io_return + +# +# _TIF_SIGPENDING is set, call do_signal +# +io_notify_resume: + # TRACE_IRQS_ON already done at io_return + l %r1,BASED(.Ldo_notify_resume) + ssm __LC_SVC_NEW_PSW # reenable interrupts + lr %r2,%r11 # pass pointer to pt_regs + basr %r14,%r1 # call do_notify_resume + ssm __LC_PGM_NEW_PSW # disable I/O and ext. interrupts + TRACE_IRQS_OFF + j io_return + +/* + * External interrupt handler routine + */ + +ENTRY(ext_int_handler) + stck __LC_INT_CLOCK + stpt __LC_ASYNC_ENTER_TIMER + stm %r8,%r15,__LC_SAVE_AREA_ASYNC + l %r12,__LC_THREAD_INFO + l %r13,__LC_SVC_NEW_PSW+4 + lm %r8,%r9,__LC_EXT_OLD_PSW + tmh %r8,0x0001 # interrupting from user ? + jz ext_skip + UPDATE_VTIME %r14,%r15,__LC_ASYNC_ENTER_TIMER +ext_skip: + SWITCH_ASYNC __LC_SAVE_AREA_ASYNC,__LC_ASYNC_STACK,STACK_SHIFT + stm %r0,%r7,__PT_R0(%r11) + mvc __PT_R8(32,%r11),__LC_SAVE_AREA_ASYNC + stm %r8,%r9,__PT_PSW(%r11) + TRACE_IRQS_OFF + lr %r2,%r11 # pass pointer to pt_regs + l %r3,__LC_EXT_CPU_ADDR # get cpu address + interruption code + l %r4,__LC_EXT_PARAMS # get external parameters + l %r1,BASED(.Ldo_extint) + basr %r14,%r1 # call do_extint + j io_return + +/* + * Load idle PSW. The second "half" of this function is in cleanup_idle. + */ +ENTRY(psw_idle) + st %r4,__SF_EMPTY(%r15) + basr %r1,0 + la %r1,psw_idle_lpsw+4-.(%r1) + st %r1,__SF_EMPTY+4(%r15) + oi __SF_EMPTY+4(%r15),0x80 + la %r1,.Lvtimer_max-psw_idle_lpsw-4(%r1) + stck __IDLE_ENTER(%r2) + ltr %r5,%r5 + stpt __VQ_IDLE_ENTER(%r3) + jz psw_idle_lpsw + spt 0(%r1) +psw_idle_lpsw: + lpsw __SF_EMPTY(%r15) + br %r14 +psw_idle_end: + +__critical_end: + +/* + * Machine check handler routines + */ + +ENTRY(mcck_int_handler) + stck __LC_MCCK_CLOCK + spt __LC_CPU_TIMER_SAVE_AREA # revalidate cpu timer + lm %r0,%r15,__LC_GPREGS_SAVE_AREA # revalidate gprs + l %r12,__LC_THREAD_INFO + l %r13,__LC_SVC_NEW_PSW+4 + lm %r8,%r9,__LC_MCK_OLD_PSW + tm __LC_MCCK_CODE,0x80 # system damage? + jo mcck_panic # yes -> rest of mcck code invalid + la %r14,__LC_CPU_TIMER_SAVE_AREA + mvc __LC_MCCK_ENTER_TIMER(8),0(%r14) + tm __LC_MCCK_CODE+5,0x02 # stored cpu timer value valid? + jo 3f + la %r14,__LC_SYNC_ENTER_TIMER + clc 0(8,%r14),__LC_ASYNC_ENTER_TIMER + jl 0f + la %r14,__LC_ASYNC_ENTER_TIMER +0: clc 0(8,%r14),__LC_EXIT_TIMER + jl 1f + la %r14,__LC_EXIT_TIMER +1: clc 0(8,%r14),__LC_LAST_UPDATE_TIMER + jl 2f + la %r14,__LC_LAST_UPDATE_TIMER +2: spt 0(%r14) + mvc __LC_MCCK_ENTER_TIMER(8),0(%r14) +3: tm __LC_MCCK_CODE+2,0x09 # mwp + ia of old psw valid? + jno mcck_panic # no -> skip cleanup critical + tm %r8,0x0001 # interrupting from user ? + jz mcck_skip + UPDATE_VTIME %r14,%r15,__LC_MCCK_ENTER_TIMER +mcck_skip: + SWITCH_ASYNC __LC_GPREGS_SAVE_AREA+32,__LC_PANIC_STACK,PAGE_SHIFT + mvc __PT_R0(64,%r11),__LC_GPREGS_SAVE_AREA + stm %r8,%r9,__PT_PSW(%r11) + xc __SF_BACKCHAIN(4,%r15),__SF_BACKCHAIN(%r15) + l %r1,BASED(.Ldo_machine_check) + lr %r2,%r11 # pass pointer to pt_regs + basr %r14,%r1 # call s390_do_machine_check + tm __PT_PSW+1(%r11),0x01 # returning to user ? + jno mcck_return + l %r1,__LC_KERNEL_STACK # switch to kernel stack + ahi %r1,-(STACK_FRAME_OVERHEAD + __PT_SIZE) + mvc STACK_FRAME_OVERHEAD(__PT_SIZE,%r1),0(%r11) + xc __SF_BACKCHAIN(4,%r1),__SF_BACKCHAIN(%r1) + la %r11,STACK_FRAME_OVERHEAD(%r15) + lr %r15,%r1 + ssm __LC_PGM_NEW_PSW # turn dat on, keep irqs off + tm __TI_flags+3(%r12),_TIF_MCCK_PENDING + jno mcck_return + TRACE_IRQS_OFF + l %r1,BASED(.Lhandle_mcck) + basr %r14,%r1 # call s390_handle_mcck + TRACE_IRQS_ON +mcck_return: + mvc __LC_RETURN_MCCK_PSW(8),__PT_PSW(%r11) # move return PSW + tm __LC_RETURN_MCCK_PSW+1,0x01 # returning to user ? + jno 0f + lm %r0,%r15,__PT_R0(%r11) + stpt __LC_EXIT_TIMER + lpsw __LC_RETURN_MCCK_PSW +0: lm %r0,%r15,__PT_R0(%r11) + lpsw __LC_RETURN_MCCK_PSW + +mcck_panic: + l %r14,__LC_PANIC_STACK + slr %r14,%r15 + sra %r14,PAGE_SHIFT + jz 0f + l %r15,__LC_PANIC_STACK +0: ahi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) + j mcck_skip + +# +# PSW restart interrupt handler +# +ENTRY(restart_int_handler) + st %r15,__LC_SAVE_AREA_RESTART + l %r15,__LC_RESTART_STACK + ahi %r15,-__PT_SIZE # create pt_regs on stack + xc 0(__PT_SIZE,%r15),0(%r15) + stm %r0,%r14,__PT_R0(%r15) + mvc __PT_R15(4,%r15),__LC_SAVE_AREA_RESTART + mvc __PT_PSW(8,%r15),__LC_RST_OLD_PSW # store restart old psw + ahi %r15,-STACK_FRAME_OVERHEAD # create stack frame on stack + xc 0(STACK_FRAME_OVERHEAD,%r15),0(%r15) + lm %r1,%r3,__LC_RESTART_FN # load fn, parm & source cpu + ltr %r3,%r3 # test source cpu address + jm 1f # negative -> skip source stop +0: sigp %r4,%r3,1 # sigp sense to source cpu + brc 10,0b # wait for status stored +1: basr %r14,%r1 # call function + stap __SF_EMPTY(%r15) # store cpu address + lh %r3,__SF_EMPTY(%r15) +2: sigp %r4,%r3,5 # sigp stop to current cpu + brc 2,2b +3: j 3b + + .section .kprobes.text, "ax" + +#ifdef CONFIG_CHECK_STACK +/* + * The synchronous or the asynchronous stack overflowed. We are dead. + * No need to properly save the registers, we are going to panic anyway. + * Setup a pt_regs so that show_trace can provide a good call trace. + */ +stack_overflow: + l %r15,__LC_PANIC_STACK # change to panic stack + ahi %r15,-__PT_SIZE # create pt_regs + stm %r0,%r7,__PT_R0(%r15) + stm %r8,%r9,__PT_PSW(%r15) + mvc __PT_R8(32,%r11),0(%r14) + lr %r15,%r11 + ahi %r15,-STACK_FRAME_OVERHEAD + l %r1,BASED(1f) + xc __SF_BACKCHAIN(4,%r15),__SF_BACKCHAIN(%r15) + lr %r2,%r11 # pass pointer to pt_regs + br %r1 # branch to kernel_stack_overflow +1: .long kernel_stack_overflow +#endif + +cleanup_table: + .long system_call + 0x80000000 + .long sysc_do_svc + 0x80000000 + .long sysc_tif + 0x80000000 + .long sysc_restore + 0x80000000 + .long sysc_done + 0x80000000 + .long io_tif + 0x80000000 + .long io_restore + 0x80000000 + .long io_done + 0x80000000 + .long psw_idle + 0x80000000 + .long psw_idle_end + 0x80000000 + +cleanup_critical: + cl %r9,BASED(cleanup_table) # system_call + jl 0f + cl %r9,BASED(cleanup_table+4) # sysc_do_svc + jl cleanup_system_call + cl %r9,BASED(cleanup_table+8) # sysc_tif + jl 0f + cl %r9,BASED(cleanup_table+12) # sysc_restore + jl cleanup_sysc_tif + cl %r9,BASED(cleanup_table+16) # sysc_done + jl cleanup_sysc_restore + cl %r9,BASED(cleanup_table+20) # io_tif + jl 0f + cl %r9,BASED(cleanup_table+24) # io_restore + jl cleanup_io_tif + cl %r9,BASED(cleanup_table+28) # io_done + jl cleanup_io_restore + cl %r9,BASED(cleanup_table+32) # psw_idle + jl 0f + cl %r9,BASED(cleanup_table+36) # psw_idle_end + jl cleanup_idle +0: br %r14 + +cleanup_system_call: + # check if stpt has been executed + cl %r9,BASED(cleanup_system_call_insn) + jh 0f + mvc __LC_SYNC_ENTER_TIMER(8),__LC_ASYNC_ENTER_TIMER + chi %r11,__LC_SAVE_AREA_ASYNC + je 0f + mvc __LC_SYNC_ENTER_TIMER(8),__LC_MCCK_ENTER_TIMER +0: # check if stm has been executed + cl %r9,BASED(cleanup_system_call_insn+4) + jh 0f + mvc __LC_SAVE_AREA_SYNC(32),0(%r11) +0: # set up saved registers r12, and r13 + st %r12,16(%r11) # r12 thread-info pointer + st %r13,20(%r11) # r13 literal-pool pointer + # check if the user time calculation has been done + cl %r9,BASED(cleanup_system_call_insn+8) + jh 0f + l %r10,__LC_EXIT_TIMER + l %r15,__LC_EXIT_TIMER+4 + SUB64 %r10,%r15,__LC_SYNC_ENTER_TIMER + ADD64 %r10,%r15,__LC_USER_TIMER + st %r10,__LC_USER_TIMER + st %r15,__LC_USER_TIMER+4 +0: # check if the system time calculation has been done + cl %r9,BASED(cleanup_system_call_insn+12) + jh 0f + l %r10,__LC_LAST_UPDATE_TIMER + l %r15,__LC_LAST_UPDATE_TIMER+4 + SUB64 %r10,%r15,__LC_EXIT_TIMER + ADD64 %r10,%r15,__LC_SYSTEM_TIMER + st %r10,__LC_SYSTEM_TIMER + st %r15,__LC_SYSTEM_TIMER+4 +0: # update accounting time stamp + mvc __LC_LAST_UPDATE_TIMER(8),__LC_SYNC_ENTER_TIMER + # set up saved register 11 + l %r15,__LC_KERNEL_STACK + ahi %r15,-__PT_SIZE + st %r15,12(%r11) # r11 pt_regs pointer + # fill pt_regs + mvc __PT_R8(32,%r15),__LC_SAVE_AREA_SYNC + stm %r0,%r7,__PT_R0(%r15) + mvc __PT_PSW(8,%r15),__LC_SVC_OLD_PSW + mvc __PT_INT_CODE(4,%r15),__LC_SVC_ILC + # setup saved register 15 + ahi %r15,-STACK_FRAME_OVERHEAD + st %r15,28(%r11) # r15 stack pointer + # set new psw address and exit + l %r9,BASED(cleanup_table+4) # sysc_do_svc + 0x80000000 + br %r14 +cleanup_system_call_insn: + .long system_call + 0x80000000 + .long sysc_stm + 0x80000000 + .long sysc_vtime + 0x80000000 + 36 + .long sysc_vtime + 0x80000000 + 76 + +cleanup_sysc_tif: + l %r9,BASED(cleanup_table+8) # sysc_tif + 0x80000000 + br %r14 + +cleanup_sysc_restore: + cl %r9,BASED(cleanup_sysc_restore_insn) + jhe 0f + l %r9,12(%r11) # get saved pointer to pt_regs + mvc __LC_RETURN_PSW(8),__PT_PSW(%r9) + mvc 0(32,%r11),__PT_R8(%r9) + lm %r0,%r7,__PT_R0(%r9) +0: lm %r8,%r9,__LC_RETURN_PSW + br %r14 +cleanup_sysc_restore_insn: + .long sysc_done - 4 + 0x80000000 + +cleanup_io_tif: + l %r9,BASED(cleanup_table+20) # io_tif + 0x80000000 + br %r14 + +cleanup_io_restore: + cl %r9,BASED(cleanup_io_restore_insn) + jhe 0f + l %r9,12(%r11) # get saved r11 pointer to pt_regs + mvc __LC_RETURN_PSW(8),__PT_PSW(%r9) + mvc 0(32,%r11),__PT_R8(%r9) + lm %r0,%r7,__PT_R0(%r9) +0: lm %r8,%r9,__LC_RETURN_PSW + br %r14 +cleanup_io_restore_insn: + .long io_done - 4 + 0x80000000 + +cleanup_idle: + # copy interrupt clock & cpu timer + mvc __IDLE_EXIT(8,%r2),__LC_INT_CLOCK + mvc __VQ_IDLE_EXIT(8,%r3),__LC_ASYNC_ENTER_TIMER + chi %r11,__LC_SAVE_AREA_ASYNC + je 0f + mvc __IDLE_EXIT(8,%r2),__LC_MCCK_CLOCK + mvc __VQ_IDLE_EXIT(8,%r3),__LC_MCCK_ENTER_TIMER +0: # check if stck has been executed + cl %r9,BASED(cleanup_idle_insn) + jhe 1f + mvc __IDLE_ENTER(8,%r2),__IDLE_EXIT(%r2) + mvc __VQ_IDLE_ENTER(8,%r3),__VQ_IDLE_EXIT(%r3) + j 2f +1: # check if the cpu timer has been reprogrammed + ltr %r5,%r5 + jz 2f + spt __VQ_IDLE_ENTER(%r3) +2: # account system time going idle + lm %r9,%r10,__LC_STEAL_TIMER + ADD64 %r9,%r10,__IDLE_ENTER(%r2) + SUB64 %r9,%r10,__LC_LAST_UPDATE_CLOCK + stm %r9,%r10,__LC_STEAL_TIMER + mvc __LC_LAST_UPDATE_CLOCK(8),__IDLE_EXIT(%r2) + lm %r9,%r10,__LC_SYSTEM_TIMER + ADD64 %r9,%r10,__LC_LAST_UPDATE_TIMER + SUB64 %r9,%r10,__VQ_IDLE_ENTER(%r3) + stm %r9,%r10,__LC_SYSTEM_TIMER + mvc __LC_LAST_UPDATE_TIMER(8),__VQ_IDLE_EXIT(%r3) + # prepare return psw + n %r8,BASED(cleanup_idle_wait) # clear wait state bit + l %r9,24(%r11) # return from psw_idle + br %r14 +cleanup_idle_insn: + .long psw_idle_lpsw + 0x80000000 +cleanup_idle_wait: + .long 0xfffdffff + +/* + * Integer constants + */ + .align 4 +.Lnr_syscalls: + .long NR_syscalls +.Lvtimer_max: + .quad 0x7fffffffffffffff + +/* + * Symbol constants + */ +.Ldo_machine_check: .long s390_do_machine_check +.Lhandle_mcck: .long s390_handle_mcck +.Ldo_IRQ: .long do_IRQ +.Ldo_extint: .long do_extint +.Ldo_signal: .long do_signal +.Ldo_notify_resume: .long do_notify_resume +.Ldo_per_trap: .long do_per_trap +.Ldo_execve: .long do_execve +.Lexecve_tail: .long execve_tail +.Ljump_table: .long pgm_check_table +.Lschedule: .long schedule +#ifdef CONFIG_PREEMPT +.Lpreempt_irq: .long preempt_schedule_irq +#endif +.Ltrace_enter: .long do_syscall_trace_enter +.Ltrace_exit: .long do_syscall_trace_exit +.Lschedule_tail: .long schedule_tail +.Lsys_call_table: .long sys_call_table +.Lsysc_per: .long sysc_per + 0x80000000 +#ifdef CONFIG_TRACE_IRQFLAGS +.Lhardirqs_on: .long trace_hardirqs_on_caller +.Lhardirqs_off: .long trace_hardirqs_off_caller +#endif +#ifdef CONFIG_LOCKDEP +.Llockdep_sys_exit: .long lockdep_sys_exit +#endif +.Lcritical_start: .long __critical_start + 0x80000000 +.Lcritical_length: .long __critical_end - __critical_start + + .section .rodata, "a" +#define SYSCALL(esa,esame,emu) .long esa + .globl sys_call_table +sys_call_table: +#include "syscalls.S" +#undef SYSCALL diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h new file mode 100644 index 00000000..6cdddac9 --- /dev/null +++ b/arch/s390/kernel/entry.h @@ -0,0 +1,75 @@ +#ifndef _ENTRY_H +#define _ENTRY_H + +#include <linux/types.h> +#include <linux/signal.h> +#include <asm/ptrace.h> +#include <asm/cputime.h> +#include <asm/timer.h> + +extern void (*pgm_check_table[128])(struct pt_regs *); +extern void *restart_stack; + +void system_call(void); +void pgm_check_handler(void); +void ext_int_handler(void); +void io_int_handler(void); +void mcck_int_handler(void); +void restart_int_handler(void); +void restart_call_handler(void); +void psw_idle(struct s390_idle_data *, struct vtimer_queue *, + unsigned long, int); + +asmlinkage long do_syscall_trace_enter(struct pt_regs *regs); +asmlinkage void do_syscall_trace_exit(struct pt_regs *regs); + +void do_protection_exception(struct pt_regs *regs); +void do_dat_exception(struct pt_regs *regs); +void do_asce_exception(struct pt_regs *regs); + +void do_per_trap(struct pt_regs *regs); +void syscall_trace(struct pt_regs *regs, int entryexit); +void kernel_stack_overflow(struct pt_regs * regs); +void do_signal(struct pt_regs *regs); +int handle_signal32(unsigned long sig, struct k_sigaction *ka, + siginfo_t *info, sigset_t *oldset, struct pt_regs *regs); +void do_notify_resume(struct pt_regs *regs); + +struct ext_code; +void do_extint(struct pt_regs *regs, struct ext_code, unsigned int, unsigned long); +void do_restart(void); +void __init startup_init(void); +void die(struct pt_regs *regs, const char *str); + +void __init time_init(void); + +struct s390_mmap_arg_struct; +struct fadvise64_64_args; +struct old_sigaction; + +long sys_mmap2(struct s390_mmap_arg_struct __user *arg); +long sys_s390_ipc(uint call, int first, unsigned long second, + unsigned long third, void __user *ptr); +long sys_s390_personality(unsigned int personality); +long sys_s390_fadvise64(int fd, u32 offset_high, u32 offset_low, + size_t len, int advice); +long sys_s390_fadvise64_64(struct fadvise64_64_args __user *args); +long sys_s390_fallocate(int fd, int mode, loff_t offset, u32 len_high, + u32 len_low); +long sys_fork(void); +long sys_clone(unsigned long newsp, unsigned long clone_flags, + int __user *parent_tidptr, int __user *child_tidptr); +long sys_vfork(void); +void execve_tail(void); +long sys_execve(const char __user *name, const char __user *const __user *argv, + const char __user *const __user *envp); +long sys_sigsuspend(int history0, int history1, old_sigset_t mask); +long sys_sigaction(int sig, const struct old_sigaction __user *act, + struct old_sigaction __user *oact); +long sys_sigaltstack(const stack_t __user *uss, stack_t __user *uoss); +long sys_sigreturn(void); +long sys_rt_sigreturn(void); +long sys32_sigreturn(void); +long sys32_rt_sigreturn(void); + +#endif /* _ENTRY_H */ diff --git a/arch/s390/kernel/entry64.S b/arch/s390/kernel/entry64.S new file mode 100644 index 00000000..4e1c292f --- /dev/null +++ b/arch/s390/kernel/entry64.S @@ -0,0 +1,1030 @@ +/* + * arch/s390/kernel/entry64.S + * S390 low-level entry points. + * + * Copyright (C) IBM Corp. 1999,2012 + * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com), + * Hartmut Penner (hp@de.ibm.com), + * Denis Joseph Barrow (djbarrow@de.ibm.com,barrow_dj@yahoo.com), + * Heiko Carstens <heiko.carstens@de.ibm.com> + */ + +#include <linux/init.h> +#include <linux/linkage.h> +#include <asm/cache.h> +#include <asm/errno.h> +#include <asm/ptrace.h> +#include <asm/thread_info.h> +#include <asm/asm-offsets.h> +#include <asm/unistd.h> +#include <asm/page.h> + +__PT_R0 = __PT_GPRS +__PT_R1 = __PT_GPRS + 8 +__PT_R2 = __PT_GPRS + 16 +__PT_R3 = __PT_GPRS + 24 +__PT_R4 = __PT_GPRS + 32 +__PT_R5 = __PT_GPRS + 40 +__PT_R6 = __PT_GPRS + 48 +__PT_R7 = __PT_GPRS + 56 +__PT_R8 = __PT_GPRS + 64 +__PT_R9 = __PT_GPRS + 72 +__PT_R10 = __PT_GPRS + 80 +__PT_R11 = __PT_GPRS + 88 +__PT_R12 = __PT_GPRS + 96 +__PT_R13 = __PT_GPRS + 104 +__PT_R14 = __PT_GPRS + 112 +__PT_R15 = __PT_GPRS + 120 + +STACK_SHIFT = PAGE_SHIFT + THREAD_ORDER +STACK_SIZE = 1 << STACK_SHIFT + +_TIF_WORK_SVC = (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | \ + _TIF_MCCK_PENDING | _TIF_PER_TRAP ) +_TIF_WORK_INT = (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | \ + _TIF_MCCK_PENDING) +_TIF_TRACE = (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | \ + _TIF_SYSCALL_TRACEPOINT) +_TIF_EXIT_SIE = (_TIF_SIGPENDING | _TIF_NEED_RESCHED | _TIF_MCCK_PENDING) + +#define BASED(name) name-system_call(%r13) + + .macro TRACE_IRQS_ON +#ifdef CONFIG_TRACE_IRQFLAGS + basr %r2,%r0 + brasl %r14,trace_hardirqs_on_caller +#endif + .endm + + .macro TRACE_IRQS_OFF +#ifdef CONFIG_TRACE_IRQFLAGS + basr %r2,%r0 + brasl %r14,trace_hardirqs_off_caller +#endif + .endm + + .macro LOCKDEP_SYS_EXIT +#ifdef CONFIG_LOCKDEP + tm __PT_PSW+1(%r11),0x01 # returning to user ? + jz .+10 + brasl %r14,lockdep_sys_exit +#endif + .endm + + .macro SPP newpp +#if defined(CONFIG_KVM) || defined(CONFIG_KVM_MODULE) + tm __LC_MACHINE_FLAGS+6,0x20 # MACHINE_FLAG_SPP + jz .+8 + .insn s,0xb2800000,\newpp +#endif + .endm + + .macro HANDLE_SIE_INTERCEPT scratch +#if defined(CONFIG_KVM) || defined(CONFIG_KVM_MODULE) + tm __TI_flags+6(%r12),_TIF_SIE>>8 + jz .+42 + tm __LC_MACHINE_FLAGS+6,0x20 # MACHINE_FLAG_SPP + jz .+8 + .insn s,0xb2800000,BASED(.Lhost_id) # set host id + lgr \scratch,%r9 + slg \scratch,BASED(.Lsie_loop) + clg \scratch,BASED(.Lsie_length) + jhe .+10 + lg %r9,BASED(.Lsie_loop) +#endif + .endm + + .macro CHECK_STACK stacksize,savearea +#ifdef CONFIG_CHECK_STACK + tml %r15,\stacksize - CONFIG_STACK_GUARD + lghi %r14,\savearea + jz stack_overflow +#endif + .endm + + .macro SWITCH_ASYNC savearea,stack,shift + tmhh %r8,0x0001 # interrupting from user ? + jnz 1f + lgr %r14,%r9 + slg %r14,BASED(.Lcritical_start) + clg %r14,BASED(.Lcritical_length) + jhe 0f + lghi %r11,\savearea # inside critical section, do cleanup + brasl %r14,cleanup_critical + tmhh %r8,0x0001 # retest problem state after cleanup + jnz 1f +0: lg %r14,\stack # are we already on the target stack? + slgr %r14,%r15 + srag %r14,%r14,\shift + jnz 1f + CHECK_STACK 1<<\shift,\savearea + j 2f +1: lg %r15,\stack # load target stack +2: aghi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) + la %r11,STACK_FRAME_OVERHEAD(%r15) + .endm + + .macro UPDATE_VTIME scratch,enter_timer + lg \scratch,__LC_EXIT_TIMER + slg \scratch,\enter_timer + alg \scratch,__LC_USER_TIMER + stg \scratch,__LC_USER_TIMER + lg \scratch,__LC_LAST_UPDATE_TIMER + slg \scratch,__LC_EXIT_TIMER + alg \scratch,__LC_SYSTEM_TIMER + stg \scratch,__LC_SYSTEM_TIMER + mvc __LC_LAST_UPDATE_TIMER(8),\enter_timer + .endm + + .macro LAST_BREAK scratch + srag \scratch,%r10,23 + jz .+10 + stg %r10,__TI_last_break(%r12) + .endm + + .macro REENABLE_IRQS + stg %r8,__LC_RETURN_PSW + ni __LC_RETURN_PSW,0xbf + ssm __LC_RETURN_PSW + .endm + + .section .kprobes.text, "ax" + +/* + * Scheduler resume function, called by switch_to + * gpr2 = (task_struct *) prev + * gpr3 = (task_struct *) next + * Returns: + * gpr2 = prev + */ +ENTRY(__switch_to) + lg %r4,__THREAD_info(%r2) # get thread_info of prev + lg %r5,__THREAD_info(%r3) # get thread_info of next + tm __TI_flags+7(%r4),_TIF_MCCK_PENDING # machine check pending? + jz 0f + ni __TI_flags+7(%r4),255-_TIF_MCCK_PENDING # clear flag in prev + oi __TI_flags+7(%r5),_TIF_MCCK_PENDING # set it in next +0: stmg %r6,%r15,__SF_GPRS(%r15) # store gprs of prev task + stg %r15,__THREAD_ksp(%r2) # store kernel stack of prev + lg %r15,__THREAD_ksp(%r3) # load kernel stack of next + lctl %c4,%c4,__TASK_pid(%r3) # load pid to control reg. 4 + lmg %r6,%r15,__SF_GPRS(%r15) # load gprs of next task + stg %r3,__LC_CURRENT # store task struct of next + mvc __LC_CURRENT_PID+4(4,%r0),__TASK_pid(%r3) # store pid of next + stg %r5,__LC_THREAD_INFO # store thread info of next + aghi %r5,STACK_SIZE # end of kernel stack of next + stg %r5,__LC_KERNEL_STACK # store end of kernel stack + br %r14 + +__critical_start: +/* + * SVC interrupt handler routine. System calls are synchronous events and + * are executed with interrupts enabled. + */ + +ENTRY(system_call) + stpt __LC_SYNC_ENTER_TIMER +sysc_stmg: + stmg %r8,%r15,__LC_SAVE_AREA_SYNC + lg %r10,__LC_LAST_BREAK + lg %r12,__LC_THREAD_INFO + larl %r13,system_call +sysc_per: + lg %r15,__LC_KERNEL_STACK + aghi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) + la %r11,STACK_FRAME_OVERHEAD(%r15) # pointer to pt_regs +sysc_vtime: + UPDATE_VTIME %r13,__LC_SYNC_ENTER_TIMER + LAST_BREAK %r13 + stmg %r0,%r7,__PT_R0(%r11) + mvc __PT_R8(64,%r11),__LC_SAVE_AREA_SYNC + mvc __PT_PSW(16,%r11),__LC_SVC_OLD_PSW + mvc __PT_INT_CODE(4,%r11),__LC_SVC_ILC +sysc_do_svc: + oi __TI_flags+7(%r12),_TIF_SYSCALL + llgh %r8,__PT_INT_CODE+2(%r11) + slag %r8,%r8,2 # shift and test for svc 0 + jnz sysc_nr_ok + # svc 0: system call number in %r1 + llgfr %r1,%r1 # clear high word in r1 + cghi %r1,NR_syscalls + jnl sysc_nr_ok + sth %r1,__PT_INT_CODE+2(%r11) + slag %r8,%r1,2 +sysc_nr_ok: + larl %r10,sys_call_table # 64 bit system call table +#ifdef CONFIG_COMPAT + tm __TI_flags+5(%r12),(_TIF_31BIT>>16) + jno sysc_noemu + larl %r10,sys_call_table_emu # 31 bit system call table +sysc_noemu: +#endif + xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) + stg %r2,__PT_ORIG_GPR2(%r11) + stg %r7,STACK_FRAME_OVERHEAD(%r15) + lgf %r9,0(%r8,%r10) # get system call add. + tm __TI_flags+6(%r12),_TIF_TRACE >> 8 + jnz sysc_tracesys + basr %r14,%r9 # call sys_xxxx + stg %r2,__PT_R2(%r11) # store return value + +sysc_return: + LOCKDEP_SYS_EXIT +sysc_tif: + tm __PT_PSW+1(%r11),0x01 # returning to user ? + jno sysc_restore + tm __TI_flags+7(%r12),_TIF_WORK_SVC + jnz sysc_work # check for work + ni __TI_flags+7(%r12),255-_TIF_SYSCALL +sysc_restore: + lg %r14,__LC_VDSO_PER_CPU + lmg %r0,%r10,__PT_R0(%r11) + mvc __LC_RETURN_PSW(16),__PT_PSW(%r11) + stpt __LC_EXIT_TIMER + mvc __VDSO_ECTG_BASE(16,%r14),__LC_EXIT_TIMER + lmg %r11,%r15,__PT_R11(%r11) + lpswe __LC_RETURN_PSW +sysc_done: + +# +# One of the work bits is on. Find out which one. +# +sysc_work: + tm __TI_flags+7(%r12),_TIF_MCCK_PENDING + jo sysc_mcck_pending + tm __TI_flags+7(%r12),_TIF_NEED_RESCHED + jo sysc_reschedule + tm __TI_flags+7(%r12),_TIF_SIGPENDING + jo sysc_sigpending + tm __TI_flags+7(%r12),_TIF_NOTIFY_RESUME + jo sysc_notify_resume + tm __TI_flags+7(%r12),_TIF_PER_TRAP + jo sysc_singlestep + j sysc_return # beware of critical section cleanup + +# +# _TIF_NEED_RESCHED is set, call schedule +# +sysc_reschedule: + larl %r14,sysc_return + jg schedule + +# +# _TIF_MCCK_PENDING is set, call handler +# +sysc_mcck_pending: + larl %r14,sysc_return + jg s390_handle_mcck # TIF bit will be cleared by handler + +# +# _TIF_SIGPENDING is set, call do_signal +# +sysc_sigpending: + ni __TI_flags+7(%r12),255-_TIF_PER_TRAP # clear TIF_PER_TRAP + lgr %r2,%r11 # pass pointer to pt_regs + brasl %r14,do_signal + tm __TI_flags+7(%r12),_TIF_SYSCALL + jno sysc_return + lmg %r2,%r7,__PT_R2(%r11) # load svc arguments + lghi %r8,0 # svc 0 returns -ENOSYS + lh %r1,__PT_INT_CODE+2(%r11) # load new svc number + cghi %r1,NR_syscalls + jnl sysc_nr_ok # invalid svc number -> do svc 0 + slag %r8,%r1,2 + j sysc_nr_ok # restart svc + +# +# _TIF_NOTIFY_RESUME is set, call do_notify_resume +# +sysc_notify_resume: + lgr %r2,%r11 # pass pointer to pt_regs + larl %r14,sysc_return + jg do_notify_resume + +# +# _TIF_PER_TRAP is set, call do_per_trap +# +sysc_singlestep: + ni __TI_flags+7(%r12),255-(_TIF_SYSCALL | _TIF_PER_TRAP) + lgr %r2,%r11 # pass pointer to pt_regs + larl %r14,sysc_return + jg do_per_trap + +# +# call tracehook_report_syscall_entry/tracehook_report_syscall_exit before +# and after the system call +# +sysc_tracesys: + lgr %r2,%r11 # pass pointer to pt_regs + la %r3,0 + llgh %r0,__PT_INT_CODE+2(%r11) + stg %r0,__PT_R2(%r11) + brasl %r14,do_syscall_trace_enter + lghi %r0,NR_syscalls + clgr %r0,%r2 + jnh sysc_tracenogo + sllg %r8,%r2,2 + lgf %r9,0(%r8,%r10) +sysc_tracego: + lmg %r3,%r7,__PT_R3(%r11) + stg %r7,STACK_FRAME_OVERHEAD(%r15) + lg %r2,__PT_ORIG_GPR2(%r11) + basr %r14,%r9 # call sys_xxx + stg %r2,__PT_R2(%r11) # store return value +sysc_tracenogo: + tm __TI_flags+6(%r12),_TIF_TRACE >> 8 + jz sysc_return + lgr %r2,%r11 # pass pointer to pt_regs + larl %r14,sysc_return + jg do_syscall_trace_exit + +# +# a new process exits the kernel with ret_from_fork +# +ENTRY(ret_from_fork) + la %r11,STACK_FRAME_OVERHEAD(%r15) + lg %r12,__LC_THREAD_INFO + tm __PT_PSW+1(%r11),0x01 # forking a kernel thread ? + jo 0f + stg %r15,__PT_R15(%r11) # store stack pointer for new kthread +0: brasl %r14,schedule_tail + TRACE_IRQS_ON + ssm __LC_SVC_NEW_PSW # reenable interrupts + j sysc_tracenogo + +# +# kernel_execve function needs to deal with pt_regs that is not +# at the usual place +# +ENTRY(kernel_execve) + stmg %r12,%r15,96(%r15) + lgr %r14,%r15 + aghi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) + stg %r14,__SF_BACKCHAIN(%r15) + la %r12,STACK_FRAME_OVERHEAD(%r15) + xc 0(__PT_SIZE,%r12),0(%r12) + lgr %r5,%r12 + brasl %r14,do_execve + ltgfr %r2,%r2 + je 0f + aghi %r15,(STACK_FRAME_OVERHEAD + __PT_SIZE) + lmg %r12,%r15,96(%r15) + br %r14 + # execve succeeded. +0: ssm __LC_PGM_NEW_PSW # disable I/O and ext. interrupts + lg %r15,__LC_KERNEL_STACK # load ksp + aghi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) + la %r11,STACK_FRAME_OVERHEAD(%r15) + mvc 0(__PT_SIZE,%r11),0(%r12) # copy pt_regs + lg %r12,__LC_THREAD_INFO + xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) + ssm __LC_SVC_NEW_PSW # reenable interrupts + brasl %r14,execve_tail + j sysc_return + +/* + * Program check handler routine + */ + +ENTRY(pgm_check_handler) + stpt __LC_SYNC_ENTER_TIMER + stmg %r8,%r15,__LC_SAVE_AREA_SYNC + lg %r10,__LC_LAST_BREAK + lg %r12,__LC_THREAD_INFO + larl %r13,system_call + lmg %r8,%r9,__LC_PGM_OLD_PSW + HANDLE_SIE_INTERCEPT %r14 + tmhh %r8,0x0001 # test problem state bit + jnz 1f # -> fault in user space + tmhh %r8,0x4000 # PER bit set in old PSW ? + jnz 0f # -> enabled, can't be a double fault + tm __LC_PGM_ILC+3,0x80 # check for per exception + jnz pgm_svcper # -> single stepped svc +0: CHECK_STACK STACK_SIZE,__LC_SAVE_AREA_SYNC + j 2f +1: UPDATE_VTIME %r14,__LC_SYNC_ENTER_TIMER + LAST_BREAK %r14 + lg %r15,__LC_KERNEL_STACK +2: aghi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) + la %r11,STACK_FRAME_OVERHEAD(%r15) + stmg %r0,%r7,__PT_R0(%r11) + mvc __PT_R8(64,%r11),__LC_SAVE_AREA_SYNC + stmg %r8,%r9,__PT_PSW(%r11) + mvc __PT_INT_CODE(4,%r11),__LC_PGM_ILC + mvc __PT_INT_PARM_LONG(8,%r11),__LC_TRANS_EXC_CODE + stg %r10,__PT_ARGS(%r11) + tm __LC_PGM_ILC+3,0x80 # check for per exception + jz 0f + lg %r1,__TI_task(%r12) + tmhh %r8,0x0001 # kernel per event ? + jz pgm_kprobe + oi __TI_flags+7(%r12),_TIF_PER_TRAP + mvc __THREAD_per_address(8,%r1),__LC_PER_ADDRESS + mvc __THREAD_per_cause(2,%r1),__LC_PER_CAUSE + mvc __THREAD_per_paid(1,%r1),__LC_PER_PAID +0: REENABLE_IRQS + xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) + larl %r1,pgm_check_table + llgh %r10,__PT_INT_CODE+2(%r11) + nill %r10,0x007f + sll %r10,3 + je sysc_return + lg %r1,0(%r10,%r1) # load address of handler routine + lgr %r2,%r11 # pass pointer to pt_regs + basr %r14,%r1 # branch to interrupt-handler + j sysc_return + +# +# PER event in supervisor state, must be kprobes +# +pgm_kprobe: + REENABLE_IRQS + xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) + lgr %r2,%r11 # pass pointer to pt_regs + brasl %r14,do_per_trap + j sysc_return + +# +# single stepped system call +# +pgm_svcper: + oi __TI_flags+7(%r12),_TIF_PER_TRAP + mvc __LC_RETURN_PSW(8),__LC_SVC_NEW_PSW + larl %r14,sysc_per + stg %r14,__LC_RETURN_PSW+8 + lpswe __LC_RETURN_PSW # branch to sysc_per and enable irqs + +/* + * IO interrupt handler routine + */ +ENTRY(io_int_handler) + stck __LC_INT_CLOCK + stpt __LC_ASYNC_ENTER_TIMER + stmg %r8,%r15,__LC_SAVE_AREA_ASYNC + lg %r10,__LC_LAST_BREAK + lg %r12,__LC_THREAD_INFO + larl %r13,system_call + lmg %r8,%r9,__LC_IO_OLD_PSW + HANDLE_SIE_INTERCEPT %r14 + SWITCH_ASYNC __LC_SAVE_AREA_ASYNC,__LC_ASYNC_STACK,STACK_SHIFT + tmhh %r8,0x0001 # interrupting from user? + jz io_skip + UPDATE_VTIME %r14,__LC_ASYNC_ENTER_TIMER + LAST_BREAK %r14 +io_skip: + stmg %r0,%r7,__PT_R0(%r11) + mvc __PT_R8(64,%r11),__LC_SAVE_AREA_ASYNC + stmg %r8,%r9,__PT_PSW(%r11) + TRACE_IRQS_OFF + xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) + lgr %r2,%r11 # pass pointer to pt_regs + brasl %r14,do_IRQ +io_return: + LOCKDEP_SYS_EXIT + TRACE_IRQS_ON +io_tif: + tm __TI_flags+7(%r12),_TIF_WORK_INT + jnz io_work # there is work to do (signals etc.) +io_restore: + lg %r14,__LC_VDSO_PER_CPU + lmg %r0,%r10,__PT_R0(%r11) + mvc __LC_RETURN_PSW(16),__PT_PSW(%r11) + stpt __LC_EXIT_TIMER + mvc __VDSO_ECTG_BASE(16,%r14),__LC_EXIT_TIMER + lmg %r11,%r15,__PT_R11(%r11) + lpswe __LC_RETURN_PSW +io_done: + +# +# There is work todo, find out in which context we have been interrupted: +# 1) if we return to user space we can do all _TIF_WORK_INT work +# 2) if we return to kernel code and kvm is enabled check if we need to +# modify the psw to leave SIE +# 3) if we return to kernel code and preemptive scheduling is enabled check +# the preemption counter and if it is zero call preempt_schedule_irq +# Before any work can be done, a switch to the kernel stack is required. +# +io_work: + tm __PT_PSW+1(%r11),0x01 # returning to user ? + jo io_work_user # yes -> do resched & signal +#ifdef CONFIG_PREEMPT + # check for preemptive scheduling + icm %r0,15,__TI_precount(%r12) + jnz io_restore # preemption is disabled + tm __TI_flags+7(%r12),_TIF_NEED_RESCHED + jno io_restore + # switch to kernel stack + lg %r1,__PT_R15(%r11) + aghi %r1,-(STACK_FRAME_OVERHEAD + __PT_SIZE) + mvc STACK_FRAME_OVERHEAD(__PT_SIZE,%r1),0(%r11) + xc __SF_BACKCHAIN(8,%r1),__SF_BACKCHAIN(%r1) + la %r11,STACK_FRAME_OVERHEAD(%r1) + lgr %r15,%r1 + # TRACE_IRQS_ON already done at io_return, call + # TRACE_IRQS_OFF to keep things symmetrical + TRACE_IRQS_OFF + brasl %r14,preempt_schedule_irq + j io_return +#else + j io_restore +#endif + +# +# Need to do work before returning to userspace, switch to kernel stack +# +io_work_user: + lg %r1,__LC_KERNEL_STACK + aghi %r1,-(STACK_FRAME_OVERHEAD + __PT_SIZE) + mvc STACK_FRAME_OVERHEAD(__PT_SIZE,%r1),0(%r11) + xc __SF_BACKCHAIN(8,%r1),__SF_BACKCHAIN(%r1) + la %r11,STACK_FRAME_OVERHEAD(%r1) + lgr %r15,%r1 + +# +# One of the work bits is on. Find out which one. +# Checked are: _TIF_SIGPENDING, _TIF_NOTIFY_RESUME, _TIF_NEED_RESCHED +# and _TIF_MCCK_PENDING +# +io_work_tif: + tm __TI_flags+7(%r12),_TIF_MCCK_PENDING + jo io_mcck_pending + tm __TI_flags+7(%r12),_TIF_NEED_RESCHED + jo io_reschedule + tm __TI_flags+7(%r12),_TIF_SIGPENDING + jo io_sigpending + tm __TI_flags+7(%r12),_TIF_NOTIFY_RESUME + jo io_notify_resume + j io_return # beware of critical section cleanup + +# +# _TIF_MCCK_PENDING is set, call handler +# +io_mcck_pending: + # TRACE_IRQS_ON already done at io_return + brasl %r14,s390_handle_mcck # TIF bit will be cleared by handler + TRACE_IRQS_OFF + j io_return + +# +# _TIF_NEED_RESCHED is set, call schedule +# +io_reschedule: + # TRACE_IRQS_ON already done at io_return + ssm __LC_SVC_NEW_PSW # reenable interrupts + brasl %r14,schedule # call scheduler + ssm __LC_PGM_NEW_PSW # disable I/O and ext. interrupts + TRACE_IRQS_OFF + j io_return + +# +# _TIF_SIGPENDING or is set, call do_signal +# +io_sigpending: + # TRACE_IRQS_ON already done at io_return + ssm __LC_SVC_NEW_PSW # reenable interrupts + lgr %r2,%r11 # pass pointer to pt_regs + brasl %r14,do_signal + ssm __LC_PGM_NEW_PSW # disable I/O and ext. interrupts + TRACE_IRQS_OFF + j io_return + +# +# _TIF_NOTIFY_RESUME or is set, call do_notify_resume +# +io_notify_resume: + # TRACE_IRQS_ON already done at io_return + ssm __LC_SVC_NEW_PSW # reenable interrupts + lgr %r2,%r11 # pass pointer to pt_regs + brasl %r14,do_notify_resume + ssm __LC_PGM_NEW_PSW # disable I/O and ext. interrupts + TRACE_IRQS_OFF + j io_return + +/* + * External interrupt handler routine + */ +ENTRY(ext_int_handler) + stck __LC_INT_CLOCK + stpt __LC_ASYNC_ENTER_TIMER + stmg %r8,%r15,__LC_SAVE_AREA_ASYNC + lg %r10,__LC_LAST_BREAK + lg %r12,__LC_THREAD_INFO + larl %r13,system_call + lmg %r8,%r9,__LC_EXT_OLD_PSW + HANDLE_SIE_INTERCEPT %r14 + SWITCH_ASYNC __LC_SAVE_AREA_ASYNC,__LC_ASYNC_STACK,STACK_SHIFT + tmhh %r8,0x0001 # interrupting from user ? + jz ext_skip + UPDATE_VTIME %r14,__LC_ASYNC_ENTER_TIMER + LAST_BREAK %r14 +ext_skip: + stmg %r0,%r7,__PT_R0(%r11) + mvc __PT_R8(64,%r11),__LC_SAVE_AREA_ASYNC + stmg %r8,%r9,__PT_PSW(%r11) + TRACE_IRQS_OFF + lghi %r1,4096 + lgr %r2,%r11 # pass pointer to pt_regs + llgf %r3,__LC_EXT_CPU_ADDR # get cpu address + interruption code + llgf %r4,__LC_EXT_PARAMS # get external parameter + lg %r5,__LC_EXT_PARAMS2-4096(%r1) # get 64 bit external parameter + brasl %r14,do_extint + j io_return + +/* + * Load idle PSW. The second "half" of this function is in cleanup_idle. + */ +ENTRY(psw_idle) + stg %r4,__SF_EMPTY(%r15) + larl %r1,psw_idle_lpsw+4 + stg %r1,__SF_EMPTY+8(%r15) + larl %r1,.Lvtimer_max + stck __IDLE_ENTER(%r2) + ltr %r5,%r5 + stpt __VQ_IDLE_ENTER(%r3) + jz psw_idle_lpsw + spt 0(%r1) +psw_idle_lpsw: + lpswe __SF_EMPTY(%r15) + br %r14 +psw_idle_end: + +__critical_end: + +/* + * Machine check handler routines + */ +ENTRY(mcck_int_handler) + stck __LC_MCCK_CLOCK + la %r1,4095 # revalidate r1 + spt __LC_CPU_TIMER_SAVE_AREA-4095(%r1) # revalidate cpu timer + lmg %r0,%r15,__LC_GPREGS_SAVE_AREA-4095(%r1)# revalidate gprs + lg %r10,__LC_LAST_BREAK + lg %r12,__LC_THREAD_INFO + larl %r13,system_call + lmg %r8,%r9,__LC_MCK_OLD_PSW + HANDLE_SIE_INTERCEPT %r14 + tm __LC_MCCK_CODE,0x80 # system damage? + jo mcck_panic # yes -> rest of mcck code invalid + lghi %r14,__LC_CPU_TIMER_SAVE_AREA + mvc __LC_MCCK_ENTER_TIMER(8),0(%r14) + tm __LC_MCCK_CODE+5,0x02 # stored cpu timer value valid? + jo 3f + la %r14,__LC_SYNC_ENTER_TIMER + clc 0(8,%r14),__LC_ASYNC_ENTER_TIMER + jl 0f + la %r14,__LC_ASYNC_ENTER_TIMER +0: clc 0(8,%r14),__LC_EXIT_TIMER + jl 1f + la %r14,__LC_EXIT_TIMER +1: clc 0(8,%r14),__LC_LAST_UPDATE_TIMER + jl 2f + la %r14,__LC_LAST_UPDATE_TIMER +2: spt 0(%r14) + mvc __LC_MCCK_ENTER_TIMER(8),0(%r14) +3: tm __LC_MCCK_CODE+2,0x09 # mwp + ia of old psw valid? + jno mcck_panic # no -> skip cleanup critical + SWITCH_ASYNC __LC_GPREGS_SAVE_AREA+64,__LC_PANIC_STACK,PAGE_SHIFT + tm %r8,0x0001 # interrupting from user ? + jz mcck_skip + UPDATE_VTIME %r14,__LC_MCCK_ENTER_TIMER + LAST_BREAK %r14 +mcck_skip: + lghi %r14,__LC_GPREGS_SAVE_AREA + mvc __PT_R0(128,%r11),0(%r14) + stmg %r8,%r9,__PT_PSW(%r11) + xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) + lgr %r2,%r11 # pass pointer to pt_regs + brasl %r14,s390_do_machine_check + tm __PT_PSW+1(%r11),0x01 # returning to user ? + jno mcck_return + lg %r1,__LC_KERNEL_STACK # switch to kernel stack + aghi %r1,-(STACK_FRAME_OVERHEAD + __PT_SIZE) + mvc STACK_FRAME_OVERHEAD(__PT_SIZE,%r1),0(%r11) + xc __SF_BACKCHAIN(8,%r1),__SF_BACKCHAIN(%r1) + la %r11,STACK_FRAME_OVERHEAD(%r1) + lgr %r15,%r1 + ssm __LC_PGM_NEW_PSW # turn dat on, keep irqs off + tm __TI_flags+7(%r12),_TIF_MCCK_PENDING + jno mcck_return + TRACE_IRQS_OFF + brasl %r14,s390_handle_mcck + TRACE_IRQS_ON +mcck_return: + lg %r14,__LC_VDSO_PER_CPU + lmg %r0,%r10,__PT_R0(%r11) + mvc __LC_RETURN_MCCK_PSW(16),__PT_PSW(%r11) # move return PSW + tm __LC_RETURN_MCCK_PSW+1,0x01 # returning to user ? + jno 0f + stpt __LC_EXIT_TIMER + mvc __VDSO_ECTG_BASE(16,%r14),__LC_EXIT_TIMER +0: lmg %r11,%r15,__PT_R11(%r11) + lpswe __LC_RETURN_MCCK_PSW + +mcck_panic: + lg %r14,__LC_PANIC_STACK + slgr %r14,%r15 + srag %r14,%r14,PAGE_SHIFT + jz 0f + lg %r15,__LC_PANIC_STACK +0: aghi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) + j mcck_skip + +# +# PSW restart interrupt handler +# +ENTRY(restart_int_handler) + stg %r15,__LC_SAVE_AREA_RESTART + lg %r15,__LC_RESTART_STACK + aghi %r15,-__PT_SIZE # create pt_regs on stack + xc 0(__PT_SIZE,%r15),0(%r15) + stmg %r0,%r14,__PT_R0(%r15) + mvc __PT_R15(8,%r15),__LC_SAVE_AREA_RESTART + mvc __PT_PSW(16,%r15),__LC_RST_OLD_PSW # store restart old psw + aghi %r15,-STACK_FRAME_OVERHEAD # create stack frame on stack + xc 0(STACK_FRAME_OVERHEAD,%r15),0(%r15) + lmg %r1,%r3,__LC_RESTART_FN # load fn, parm & source cpu + ltgr %r3,%r3 # test source cpu address + jm 1f # negative -> skip source stop +0: sigp %r4,%r3,1 # sigp sense to source cpu + brc 10,0b # wait for status stored +1: basr %r14,%r1 # call function + stap __SF_EMPTY(%r15) # store cpu address + llgh %r3,__SF_EMPTY(%r15) +2: sigp %r4,%r3,5 # sigp stop to current cpu + brc 2,2b +3: j 3b + + .section .kprobes.text, "ax" + +#ifdef CONFIG_CHECK_STACK +/* + * The synchronous or the asynchronous stack overflowed. We are dead. + * No need to properly save the registers, we are going to panic anyway. + * Setup a pt_regs so that show_trace can provide a good call trace. + */ +stack_overflow: + lg %r11,__LC_PANIC_STACK # change to panic stack + aghi %r11,-__PT_SIZE # create pt_regs + stmg %r0,%r7,__PT_R0(%r11) + stmg %r8,%r9,__PT_PSW(%r11) + mvc __PT_R8(64,%r11),0(%r14) + stg %r10,__PT_ORIG_GPR2(%r11) # store last break to orig_gpr2 + lgr %r15,%r11 + aghi %r15,-STACK_FRAME_OVERHEAD + xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) + lgr %r2,%r11 # pass pointer to pt_regs + jg kernel_stack_overflow +#endif + + .align 8 +cleanup_table: + .quad system_call + .quad sysc_do_svc + .quad sysc_tif + .quad sysc_restore + .quad sysc_done + .quad io_tif + .quad io_restore + .quad io_done + .quad psw_idle + .quad psw_idle_end + +cleanup_critical: + clg %r9,BASED(cleanup_table) # system_call + jl 0f + clg %r9,BASED(cleanup_table+8) # sysc_do_svc + jl cleanup_system_call + clg %r9,BASED(cleanup_table+16) # sysc_tif + jl 0f + clg %r9,BASED(cleanup_table+24) # sysc_restore + jl cleanup_sysc_tif + clg %r9,BASED(cleanup_table+32) # sysc_done + jl cleanup_sysc_restore + clg %r9,BASED(cleanup_table+40) # io_tif + jl 0f + clg %r9,BASED(cleanup_table+48) # io_restore + jl cleanup_io_tif + clg %r9,BASED(cleanup_table+56) # io_done + jl cleanup_io_restore + clg %r9,BASED(cleanup_table+64) # psw_idle + jl 0f + clg %r9,BASED(cleanup_table+72) # psw_idle_end + jl cleanup_idle +0: br %r14 + + +cleanup_system_call: + # check if stpt has been executed + clg %r9,BASED(cleanup_system_call_insn) + jh 0f + mvc __LC_SYNC_ENTER_TIMER(8),__LC_ASYNC_ENTER_TIMER + cghi %r11,__LC_SAVE_AREA_ASYNC + je 0f + mvc __LC_SYNC_ENTER_TIMER(8),__LC_MCCK_ENTER_TIMER +0: # check if stmg has been executed + clg %r9,BASED(cleanup_system_call_insn+8) + jh 0f + mvc __LC_SAVE_AREA_SYNC(64),0(%r11) +0: # check if base register setup + TIF bit load has been done + clg %r9,BASED(cleanup_system_call_insn+16) + jhe 0f + # set up saved registers r10 and r12 + stg %r10,16(%r11) # r10 last break + stg %r12,32(%r11) # r12 thread-info pointer +0: # check if the user time update has been done + clg %r9,BASED(cleanup_system_call_insn+24) + jh 0f + lg %r15,__LC_EXIT_TIMER + slg %r15,__LC_SYNC_ENTER_TIMER + alg %r15,__LC_USER_TIMER + stg %r15,__LC_USER_TIMER +0: # check if the system time update has been done + clg %r9,BASED(cleanup_system_call_insn+32) + jh 0f + lg %r15,__LC_LAST_UPDATE_TIMER + slg %r15,__LC_EXIT_TIMER + alg %r15,__LC_SYSTEM_TIMER + stg %r15,__LC_SYSTEM_TIMER +0: # update accounting time stamp + mvc __LC_LAST_UPDATE_TIMER(8),__LC_SYNC_ENTER_TIMER + # do LAST_BREAK + lg %r9,16(%r11) + srag %r9,%r9,23 + jz 0f + mvc __TI_last_break(8,%r12),16(%r11) +0: # set up saved register r11 + lg %r15,__LC_KERNEL_STACK + aghi %r15,-__PT_SIZE + stg %r15,24(%r11) # r11 pt_regs pointer + # fill pt_regs + mvc __PT_R8(64,%r15),__LC_SAVE_AREA_SYNC + stmg %r0,%r7,__PT_R0(%r15) + mvc __PT_PSW(16,%r15),__LC_SVC_OLD_PSW + mvc __PT_INT_CODE(4,%r15),__LC_SVC_ILC + # setup saved register r15 + aghi %r15,-STACK_FRAME_OVERHEAD + stg %r15,56(%r11) # r15 stack pointer + # set new psw address and exit + larl %r9,sysc_do_svc + br %r14 +cleanup_system_call_insn: + .quad system_call + .quad sysc_stmg + .quad sysc_per + .quad sysc_vtime+18 + .quad sysc_vtime+42 + +cleanup_sysc_tif: + larl %r9,sysc_tif + br %r14 + +cleanup_sysc_restore: + clg %r9,BASED(cleanup_sysc_restore_insn) + je 0f + lg %r9,24(%r11) # get saved pointer to pt_regs + mvc __LC_RETURN_PSW(16),__PT_PSW(%r9) + mvc 0(64,%r11),__PT_R8(%r9) + lmg %r0,%r7,__PT_R0(%r9) +0: lmg %r8,%r9,__LC_RETURN_PSW + br %r14 +cleanup_sysc_restore_insn: + .quad sysc_done - 4 + +cleanup_io_tif: + larl %r9,io_tif + br %r14 + +cleanup_io_restore: + clg %r9,BASED(cleanup_io_restore_insn) + je 0f + lg %r9,24(%r11) # get saved r11 pointer to pt_regs + mvc __LC_RETURN_PSW(16),__PT_PSW(%r9) + mvc 0(64,%r11),__PT_R8(%r9) + lmg %r0,%r7,__PT_R0(%r9) +0: lmg %r8,%r9,__LC_RETURN_PSW + br %r14 +cleanup_io_restore_insn: + .quad io_done - 4 + +cleanup_idle: + # copy interrupt clock & cpu timer + mvc __IDLE_EXIT(8,%r2),__LC_INT_CLOCK + mvc __VQ_IDLE_EXIT(8,%r3),__LC_ASYNC_ENTER_TIMER + cghi %r11,__LC_SAVE_AREA_ASYNC + je 0f + mvc __IDLE_EXIT(8,%r2),__LC_MCCK_CLOCK + mvc __VQ_IDLE_EXIT(8,%r3),__LC_MCCK_ENTER_TIMER +0: # check if stck & stpt have been executed + clg %r9,BASED(cleanup_idle_insn) + jhe 1f + mvc __IDLE_ENTER(8,%r2),__IDLE_EXIT(%r2) + mvc __VQ_IDLE_ENTER(8,%r3),__VQ_IDLE_EXIT(%r3) + j 2f +1: # check if the cpu timer has been reprogrammed + ltr %r5,%r5 + jz 2f + spt __VQ_IDLE_ENTER(%r3) +2: # account system time going idle + lg %r9,__LC_STEAL_TIMER + alg %r9,__IDLE_ENTER(%r2) + slg %r9,__LC_LAST_UPDATE_CLOCK + stg %r9,__LC_STEAL_TIMER + mvc __LC_LAST_UPDATE_CLOCK(8),__IDLE_EXIT(%r2) + lg %r9,__LC_SYSTEM_TIMER + alg %r9,__LC_LAST_UPDATE_TIMER + slg %r9,__VQ_IDLE_ENTER(%r3) + stg %r9,__LC_SYSTEM_TIMER + mvc __LC_LAST_UPDATE_TIMER(8),__VQ_IDLE_EXIT(%r3) + # prepare return psw + nihh %r8,0xfffd # clear wait state bit + lg %r9,48(%r11) # return from psw_idle + br %r14 +cleanup_idle_insn: + .quad psw_idle_lpsw + +/* + * Integer constants + */ + .align 8 +.Lcritical_start: + .quad __critical_start +.Lcritical_length: + .quad __critical_end - __critical_start +.Lvtimer_max: + .quad 0x7fffffffffffffff + + +#if defined(CONFIG_KVM) || defined(CONFIG_KVM_MODULE) +/* + * sie64a calling convention: + * %r2 pointer to sie control block + * %r3 guest register save area + */ +ENTRY(sie64a) + stmg %r6,%r14,__SF_GPRS(%r15) # save kernel registers + stg %r2,__SF_EMPTY(%r15) # save control block pointer + stg %r3,__SF_EMPTY+8(%r15) # save guest register save area + xc __SF_EMPTY+16(8,%r15),__SF_EMPTY+16(%r15) # host id == 0 + lmg %r0,%r13,0(%r3) # load guest gprs 0-13 + lg %r14,__LC_THREAD_INFO # pointer thread_info struct + oi __TI_flags+6(%r14),_TIF_SIE>>8 +sie_loop: + lg %r14,__LC_THREAD_INFO # pointer thread_info struct + tm __TI_flags+7(%r14),_TIF_EXIT_SIE + jnz sie_exit + lg %r14,__LC_GMAP # get gmap pointer + ltgr %r14,%r14 + jz sie_gmap + lctlg %c1,%c1,__GMAP_ASCE(%r14) # load primary asce +sie_gmap: + lg %r14,__SF_EMPTY(%r15) # get control block pointer + SPP __SF_EMPTY(%r15) # set guest id + sie 0(%r14) +sie_done: + SPP __SF_EMPTY+16(%r15) # set host id + lg %r14,__LC_THREAD_INFO # pointer thread_info struct +sie_exit: + lctlg %c1,%c1,__LC_USER_ASCE # load primary asce + ni __TI_flags+6(%r14),255-(_TIF_SIE>>8) + lg %r14,__SF_EMPTY+8(%r15) # load guest register save area + stmg %r0,%r13,0(%r14) # save guest gprs 0-13 + lmg %r6,%r14,__SF_GPRS(%r15) # restore kernel registers + lghi %r2,0 + br %r14 +sie_fault: + lctlg %c1,%c1,__LC_USER_ASCE # load primary asce + lg %r14,__LC_THREAD_INFO # pointer thread_info struct + ni __TI_flags+6(%r14),255-(_TIF_SIE>>8) + lg %r14,__SF_EMPTY+8(%r15) # load guest register save area + stmg %r0,%r13,0(%r14) # save guest gprs 0-13 + lmg %r6,%r14,__SF_GPRS(%r15) # restore kernel registers + lghi %r2,-EFAULT + br %r14 + + .align 8 +.Lsie_loop: + .quad sie_loop +.Lsie_length: + .quad sie_done - sie_loop +.Lhost_id: + .quad 0 + + .section __ex_table,"a" + .quad sie_loop,sie_fault + .previous +#endif + + .section .rodata, "a" +#define SYSCALL(esa,esame,emu) .long esame + .globl sys_call_table +sys_call_table: +#include "syscalls.S" +#undef SYSCALL + +#ifdef CONFIG_COMPAT + +#define SYSCALL(esa,esame,emu) .long emu +sys_call_table_emu: +#include "syscalls.S" +#undef SYSCALL +#endif diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c new file mode 100644 index 00000000..78bdf0e5 --- /dev/null +++ b/arch/s390/kernel/ftrace.c @@ -0,0 +1,198 @@ +/* + * Dynamic function tracer architecture backend. + * + * Copyright IBM Corp. 2009 + * + * Author(s): Heiko Carstens <heiko.carstens@de.ibm.com>, + * Martin Schwidefsky <schwidefsky@de.ibm.com> + */ + +#include <linux/hardirq.h> +#include <linux/uaccess.h> +#include <linux/ftrace.h> +#include <linux/kernel.h> +#include <linux/types.h> +#include <linux/kprobes.h> +#include <trace/syscall.h> +#include <asm/asm-offsets.h> + +#ifdef CONFIG_64BIT +#define MCOUNT_OFFSET_RET 12 +#else +#define MCOUNT_OFFSET_RET 22 +#endif + +#ifdef CONFIG_DYNAMIC_FTRACE + +void ftrace_disable_code(void); +void ftrace_enable_insn(void); + +#ifdef CONFIG_64BIT +/* + * The 64-bit mcount code looks like this: + * stg %r14,8(%r15) # offset 0 + * > larl %r1,<&counter> # offset 6 + * > brasl %r14,_mcount # offset 12 + * lg %r14,8(%r15) # offset 18 + * Total length is 24 bytes. The middle two instructions of the mcount + * block get overwritten by ftrace_make_nop / ftrace_make_call. + * The 64-bit enabled ftrace code block looks like this: + * stg %r14,8(%r15) # offset 0 + * > lg %r1,__LC_FTRACE_FUNC # offset 6 + * > lgr %r0,%r0 # offset 12 + * > basr %r14,%r1 # offset 16 + * lg %r14,8(%15) # offset 18 + * The return points of the mcount/ftrace function have the same offset 18. + * The 64-bit disable ftrace code block looks like this: + * stg %r14,8(%r15) # offset 0 + * > jg .+18 # offset 6 + * > lgr %r0,%r0 # offset 12 + * > basr %r14,%r1 # offset 16 + * lg %r14,8(%15) # offset 18 + * The jg instruction branches to offset 24 to skip as many instructions + * as possible. + */ +asm( + " .align 4\n" + "ftrace_disable_code:\n" + " jg 0f\n" + " lgr %r0,%r0\n" + " basr %r14,%r1\n" + "0:\n" + " .align 4\n" + "ftrace_enable_insn:\n" + " lg %r1,"__stringify(__LC_FTRACE_FUNC)"\n"); + +#define FTRACE_INSN_SIZE 6 + +#else /* CONFIG_64BIT */ +/* + * The 31-bit mcount code looks like this: + * st %r14,4(%r15) # offset 0 + * > bras %r1,0f # offset 4 + * > .long _mcount # offset 8 + * > .long <&counter> # offset 12 + * > 0: l %r14,0(%r1) # offset 16 + * > l %r1,4(%r1) # offset 20 + * basr %r14,%r14 # offset 24 + * l %r14,4(%r15) # offset 26 + * Total length is 30 bytes. The twenty bytes starting from offset 4 + * to offset 24 get overwritten by ftrace_make_nop / ftrace_make_call. + * The 31-bit enabled ftrace code block looks like this: + * st %r14,4(%r15) # offset 0 + * > l %r14,__LC_FTRACE_FUNC # offset 4 + * > j 0f # offset 8 + * > .fill 12,1,0x07 # offset 12 + * 0: basr %r14,%r14 # offset 24 + * l %r14,4(%r14) # offset 26 + * The return points of the mcount/ftrace function have the same offset 26. + * The 31-bit disabled ftrace code block looks like this: + * st %r14,4(%r15) # offset 0 + * > j .+26 # offset 4 + * > j 0f # offset 8 + * > .fill 12,1,0x07 # offset 12 + * 0: basr %r14,%r14 # offset 24 + * l %r14,4(%r14) # offset 26 + * The j instruction branches to offset 30 to skip as many instructions + * as possible. + */ +asm( + " .align 4\n" + "ftrace_disable_code:\n" + " j 1f\n" + " j 0f\n" + " .fill 12,1,0x07\n" + "0: basr %r14,%r14\n" + "1:\n" + " .align 4\n" + "ftrace_enable_insn:\n" + " l %r14,"__stringify(__LC_FTRACE_FUNC)"\n"); + +#define FTRACE_INSN_SIZE 4 + +#endif /* CONFIG_64BIT */ + + +int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, + unsigned long addr) +{ + if (probe_kernel_write((void *) rec->ip, ftrace_disable_code, + MCOUNT_INSN_SIZE)) + return -EPERM; + return 0; +} + +int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) +{ + if (probe_kernel_write((void *) rec->ip, ftrace_enable_insn, + FTRACE_INSN_SIZE)) + return -EPERM; + return 0; +} + +int ftrace_update_ftrace_func(ftrace_func_t func) +{ + return 0; +} + +int __init ftrace_dyn_arch_init(void *data) +{ + *(unsigned long *) data = 0; + return 0; +} + +#endif /* CONFIG_DYNAMIC_FTRACE */ + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +/* + * Hook the return address and push it in the stack of return addresses + * in current thread info. + */ +unsigned long __kprobes prepare_ftrace_return(unsigned long parent, + unsigned long ip) +{ + struct ftrace_graph_ent trace; + + if (unlikely(atomic_read(¤t->tracing_graph_pause))) + goto out; + if (ftrace_push_return_trace(parent, ip, &trace.depth, 0) == -EBUSY) + goto out; + trace.func = (ip & PSW_ADDR_INSN) - MCOUNT_OFFSET_RET; + /* Only trace if the calling function expects to. */ + if (!ftrace_graph_entry(&trace)) { + current->curr_ret_stack--; + goto out; + } + parent = (unsigned long) return_to_handler; +out: + return parent; +} + +#ifdef CONFIG_DYNAMIC_FTRACE +/* + * Patch the kernel code at ftrace_graph_caller location. The instruction + * there is branch relative and save to prepare_ftrace_return. To disable + * the call to prepare_ftrace_return we patch the bras offset to point + * directly after the instructions. To enable the call we calculate + * the original offset to prepare_ftrace_return and put it back. + */ +int ftrace_enable_ftrace_graph_caller(void) +{ + unsigned short offset; + + offset = ((void *) prepare_ftrace_return - + (void *) ftrace_graph_caller) / 2; + return probe_kernel_write(ftrace_graph_caller + 2, + &offset, sizeof(offset)); +} + +int ftrace_disable_ftrace_graph_caller(void) +{ + static unsigned short offset = 0x0002; + + return probe_kernel_write(ftrace_graph_caller + 2, + &offset, sizeof(offset)); +} + +#endif /* CONFIG_DYNAMIC_FTRACE */ +#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ diff --git a/arch/s390/kernel/head.S b/arch/s390/kernel/head.S new file mode 100644 index 00000000..adccd908 --- /dev/null +++ b/arch/s390/kernel/head.S @@ -0,0 +1,571 @@ +/* + * Copyright IBM Corp. 1999,2010 + * + * Author(s): Hartmut Penner <hp@de.ibm.com> + * Martin Schwidefsky <schwidefsky@de.ibm.com> + * Rob van der Heij <rvdhei@iae.nl> + * Heiko Carstens <heiko.carstens@de.ibm.com> + * + * There are 5 different IPL methods + * 1) load the image directly into ram at address 0 and do an PSW restart + * 2) linload will load the image from address 0x10000 to memory 0x10000 + * and start the code thru LPSW 0x0008000080010000 (VM only, deprecated) + * 3) generate the tape ipl header, store the generated image on a tape + * and ipl from it + * In case of SL tape you need to IPL 5 times to get past VOL1 etc + * 4) generate the vm reader ipl header, move the generated image to the + * VM reader (use option NOH!) and do a ipl from reader (VM only) + * 5) direct call of start by the SALIPL loader + * We use the cpuid to distinguish between VM and native ipl + * params for kernel are pushed to 0x10400 (see setup.h) + * + */ + +#include <linux/init.h> +#include <linux/linkage.h> +#include <asm/asm-offsets.h> +#include <asm/thread_info.h> +#include <asm/page.h> + +#ifdef CONFIG_64BIT +#define ARCH_OFFSET 4 +#else +#define ARCH_OFFSET 0 +#endif + +__HEAD +#ifndef CONFIG_IPL + .org 0 + .long 0x00080000,0x80000000+startup # Just a restart PSW +#else +#ifdef CONFIG_IPL_TAPE +#define IPL_BS 1024 + .org 0 + .long 0x00080000,0x80000000+iplstart # The first 24 bytes are loaded + .long 0x27000000,0x60000001 # by ipl to addresses 0-23. + .long 0x02000000,0x20000000+IPL_BS # (a PSW and two CCWs). + .long 0x00000000,0x00000000 # external old psw + .long 0x00000000,0x00000000 # svc old psw + .long 0x00000000,0x00000000 # program check old psw + .long 0x00000000,0x00000000 # machine check old psw + .long 0x00000000,0x00000000 # io old psw + .long 0x00000000,0x00000000 + .long 0x00000000,0x00000000 + .long 0x00000000,0x00000000 + .long 0x000a0000,0x00000058 # external new psw + .long 0x000a0000,0x00000060 # svc new psw + .long 0x000a0000,0x00000068 # program check new psw + .long 0x000a0000,0x00000070 # machine check new psw + .long 0x00080000,0x80000000+.Lioint # io new psw + + .org 0x100 +# +# subroutine for loading from tape +# Parameters: +# R1 = device number +# R2 = load address +.Lloader: + st %r14,.Lldret + la %r3,.Lorbread # r3 = address of orb + la %r5,.Lirb # r5 = address of irb + st %r2,.Lccwread+4 # initialize CCW data addresses + lctl %c6,%c6,.Lcr6 + slr %r2,%r2 +.Lldlp: + la %r6,3 # 3 retries +.Lssch: + ssch 0(%r3) # load chunk of IPL_BS bytes + bnz .Llderr +.Lw4end: + bas %r14,.Lwait4io + tm 8(%r5),0x82 # do we have a problem ? + bnz .Lrecov + slr %r7,%r7 + icm %r7,3,10(%r5) # get residual count + lcr %r7,%r7 + la %r7,IPL_BS(%r7) # IPL_BS-residual=#bytes read + ar %r2,%r7 # add to total size + tm 8(%r5),0x01 # found a tape mark ? + bnz .Ldone + l %r0,.Lccwread+4 # update CCW data addresses + ar %r0,%r7 + st %r0,.Lccwread+4 + b .Lldlp +.Ldone: + l %r14,.Lldret + br %r14 # r2 contains the total size +.Lrecov: + bas %r14,.Lsense # do the sensing + bct %r6,.Lssch # dec. retry count & branch + b .Llderr +# +# Sense subroutine +# +.Lsense: + st %r14,.Lsnsret + la %r7,.Lorbsense + ssch 0(%r7) # start sense command + bnz .Llderr + bas %r14,.Lwait4io + l %r14,.Lsnsret + tm 8(%r5),0x82 # do we have a problem ? + bnz .Llderr + br %r14 +# +# Wait for interrupt subroutine +# +.Lwait4io: + lpsw .Lwaitpsw +.Lioint: + c %r1,0xb8 # compare subchannel number + bne .Lwait4io + tsch 0(%r5) + slr %r0,%r0 + tm 8(%r5),0x82 # do we have a problem ? + bnz .Lwtexit + tm 8(%r5),0x04 # got device end ? + bz .Lwait4io +.Lwtexit: + br %r14 +.Llderr: + lpsw .Lcrash + + .align 8 +.Lorbread: + .long 0x00000000,0x0080ff00,.Lccwread + .align 8 +.Lorbsense: + .long 0x00000000,0x0080ff00,.Lccwsense + .align 8 +.Lccwread: + .long 0x02200000+IPL_BS,0x00000000 +.Lccwsense: + .long 0x04200001,0x00000000 +.Lwaitpsw: + .long 0x020a0000,0x80000000+.Lioint + +.Lirb: .long 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0 +.Lcr6: .long 0xff000000 + .align 8 +.Lcrash:.long 0x000a0000,0x00000000 +.Lldret:.long 0 +.Lsnsret: .long 0 +#endif /* CONFIG_IPL_TAPE */ + +#ifdef CONFIG_IPL_VM +#define IPL_BS 0x730 + .org 0 + .long 0x00080000,0x80000000+iplstart # The first 24 bytes are loaded + .long 0x02000018,0x60000050 # by ipl to addresses 0-23. + .long 0x02000068,0x60000050 # (a PSW and two CCWs). + .fill 80-24,1,0x40 # bytes 24-79 are discarded !! + .long 0x020000f0,0x60000050 # The next 160 byte are loaded + .long 0x02000140,0x60000050 # to addresses 0x18-0xb7 + .long 0x02000190,0x60000050 # They form the continuation + .long 0x020001e0,0x60000050 # of the CCW program started + .long 0x02000230,0x60000050 # by ipl and load the range + .long 0x02000280,0x60000050 # 0x0f0-0x730 from the image + .long 0x020002d0,0x60000050 # to the range 0x0f0-0x730 + .long 0x02000320,0x60000050 # in memory. At the end of + .long 0x02000370,0x60000050 # the channel program the PSW + .long 0x020003c0,0x60000050 # at location 0 is loaded. + .long 0x02000410,0x60000050 # Initial processing starts + .long 0x02000460,0x60000050 # at 0xf0 = iplstart. + .long 0x020004b0,0x60000050 + .long 0x02000500,0x60000050 + .long 0x02000550,0x60000050 + .long 0x020005a0,0x60000050 + .long 0x020005f0,0x60000050 + .long 0x02000640,0x60000050 + .long 0x02000690,0x60000050 + .long 0x020006e0,0x20000050 + + .org 0xf0 +# +# subroutine for loading cards from the reader +# +.Lloader: + la %r3,.Lorb # r2 = address of orb into r2 + la %r5,.Lirb # r4 = address of irb + la %r6,.Lccws + la %r7,20 +.Linit: + st %r2,4(%r6) # initialize CCW data addresses + la %r2,0x50(%r2) + la %r6,8(%r6) + bct 7,.Linit + + lctl %c6,%c6,.Lcr6 # set IO subclass mask + slr %r2,%r2 +.Lldlp: + ssch 0(%r3) # load chunk of 1600 bytes + bnz .Llderr +.Lwait4irq: + mvc 0x78(8),.Lnewpsw # set up IO interrupt psw + lpsw .Lwaitpsw +.Lioint: + c %r1,0xb8 # compare subchannel number + bne .Lwait4irq + tsch 0(%r5) + + slr %r0,%r0 + ic %r0,8(%r5) # get device status + chi %r0,8 # channel end ? + be .Lcont + chi %r0,12 # channel end + device end ? + be .Lcont + + l %r0,4(%r5) + s %r0,8(%r3) # r0/8 = number of ccws executed + mhi %r0,10 # *10 = number of bytes in ccws + lh %r3,10(%r5) # get residual count + sr %r0,%r3 # #ccws*80-residual=#bytes read + ar %r2,%r0 + + br %r14 # r2 contains the total size + +.Lcont: + ahi %r2,0x640 # add 0x640 to total size + la %r6,.Lccws + la %r7,20 +.Lincr: + l %r0,4(%r6) # update CCW data addresses + ahi %r0,0x640 + st %r0,4(%r6) + ahi %r6,8 + bct 7,.Lincr + + b .Lldlp +.Llderr: + lpsw .Lcrash + + .align 8 +.Lorb: .long 0x00000000,0x0080ff00,.Lccws +.Lirb: .long 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0 +.Lcr6: .long 0xff000000 +.Lloadp:.long 0,0 + .align 8 +.Lcrash:.long 0x000a0000,0x00000000 +.Lnewpsw: + .long 0x00080000,0x80000000+.Lioint +.Lwaitpsw: + .long 0x020a0000,0x80000000+.Lioint + + .align 8 +.Lccws: .rept 19 + .long 0x02600050,0x00000000 + .endr + .long 0x02200050,0x00000000 +#endif /* CONFIG_IPL_VM */ + +iplstart: + lh %r1,0xb8 # test if subchannel number + bct %r1,.Lnoload # is valid + l %r1,0xb8 # load ipl subchannel number + la %r2,IPL_BS # load start address + bas %r14,.Lloader # load rest of ipl image + l %r12,.Lparm # pointer to parameter area + st %r1,IPL_DEVICE+ARCH_OFFSET-PARMAREA(%r12) # save ipl device number + +# +# load parameter file from ipl device +# +.Lagain1: + l %r2,.Linitrd # ramdisk loc. is temp + bas %r14,.Lloader # load parameter file + ltr %r2,%r2 # got anything ? + bz .Lnopf + chi %r2,895 + bnh .Lnotrunc + la %r2,895 +.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 +.Lnopf: + +# +# load ramdisk from ipl device +# +.Lagain2: + l %r2,.Linitrd # addr of ramdisk + st %r2,INITRD_START+ARCH_OFFSET-PARMAREA(%r12) + bas %r14,.Lloader # load ramdisk + st %r2,INITRD_SIZE+ARCH_OFFSET-PARMAREA(%r12) # store size of rd + ltr %r2,%r2 + bnz .Lrdcont + st %r2,INITRD_START+ARCH_OFFSET-PARMAREA(%r12) # no ramdisk found +.Lrdcont: + l %r2,.Linitrd + + clc 0(3,%r2),.L_hdr # skip HDRx and EOFx + bz .Lagain2 + clc 0(3,%r2),.L_eof + bz .Lagain2 + +#ifdef CONFIG_IPL_VM +# +# reset files in VM reader +# + stidp __LC_SAVE_AREA_SYNC # store cpuid + tm __LC_SAVE_AREA_SYNC,0xff# running VM ? + bno .Lnoreset + la %r2,.Lreset + lhi %r3,26 + diag %r2,%r3,8 + la %r5,.Lirb + stsch 0(%r5) # check if irq is pending + tm 30(%r5),0x0f # by verifying if any of the + bnz .Lwaitforirq # activity or status control + tm 31(%r5),0xff # bits is set in the schib + bz .Lnoreset +.Lwaitforirq: + mvc 0x78(8),.Lrdrnewpsw # set up IO interrupt psw +.Lwaitrdrirq: + lpsw .Lrdrwaitpsw +.Lrdrint: + c %r1,0xb8 # compare subchannel number + bne .Lwaitrdrirq + la %r5,.Lirb + tsch 0(%r5) +.Lnoreset: + b .Lnoload + + .align 8 +.Lrdrnewpsw: + .long 0x00080000,0x80000000+.Lrdrint +.Lrdrwaitpsw: + .long 0x020a0000,0x80000000+.Lrdrint +#endif + +# +# everything loaded, go for it +# +.Lnoload: + l %r1,.Lstartup + br %r1 + +.Linitrd:.long _end # default address of initrd +.Lparm: .long PARMAREA +.Lstartup: .long startup +.Lreset:.byte 0xc3,0xc8,0xc1,0xd5,0xc7,0xc5,0x40,0xd9,0xc4,0xd9,0x40 + .byte 0xc1,0xd3,0xd3,0x40,0xd2,0xc5,0xc5,0xd7,0x40,0xd5,0xd6 + .byte 0xc8,0xd6,0xd3,0xc4 # "change rdr all keep nohold" +.L_eof: .long 0xc5d6c600 /* C'EOF' */ +.L_hdr: .long 0xc8c4d900 /* C'HDR' */ + +#endif /* CONFIG_IPL */ + +# +# SALIPL loader support. Based on a patch by Rob van der Heij. +# This entry point is called directly from the SALIPL loader and +# doesn't need a builtin ipl record. +# + .org 0x800 +ENTRY(start) + stm %r0,%r15,0x07b0 # store registers + basr %r12,%r0 +.base: + l %r11,.parm + l %r8,.cmd # pointer to command buffer + + ltr %r9,%r9 # do we have SALIPL parameters? + bp .sk8x8 + + mvc 0(64,%r8),0x00b0 # copy saved registers + xc 64(240-64,%r8),0(%r8) # remainder of buffer + tr 0(64,%r8),.lowcase + b .gotr +.sk8x8: + mvc 0(240,%r8),0(%r9) # copy iplparms into buffer +.gotr: + slr %r0,%r0 + st %r0,INITRD_SIZE+ARCH_OFFSET-PARMAREA(%r11) + st %r0,INITRD_START+ARCH_OFFSET-PARMAREA(%r11) + j startup # continue with startup +.cmd: .long COMMAND_LINE # address of command line buffer +.parm: .long PARMAREA +.lowcase: + .byte 0x00,0x01,0x02,0x03,0x04,0x05,0x06,0x07 + .byte 0x08,0x09,0x0a,0x0b,0x0c,0x0d,0x0e,0x0f + .byte 0x10,0x11,0x12,0x13,0x14,0x15,0x16,0x17 + .byte 0x18,0x19,0x1a,0x1b,0x1c,0x1d,0x1e,0x1f + .byte 0x20,0x21,0x22,0x23,0x24,0x25,0x26,0x27 + .byte 0x28,0x29,0x2a,0x2b,0x2c,0x2d,0x2e,0x2f + .byte 0x30,0x31,0x32,0x33,0x34,0x35,0x36,0x37 + .byte 0x38,0x39,0x3a,0x3b,0x3c,0x3d,0x3e,0x3f + .byte 0x40,0x41,0x42,0x43,0x44,0x45,0x46,0x47 + .byte 0x48,0x49,0x4a,0x4b,0x4c,0x4d,0x4e,0x4f + .byte 0x50,0x51,0x52,0x53,0x54,0x55,0x56,0x57 + .byte 0x58,0x59,0x5a,0x5b,0x5c,0x5d,0x5e,0x5f + .byte 0x60,0x61,0x62,0x63,0x64,0x65,0x66,0x67 + .byte 0x68,0x69,0x6a,0x6b,0x6c,0x6d,0x6e,0x6f + .byte 0x70,0x71,0x72,0x73,0x74,0x75,0x76,0x77 + .byte 0x78,0x79,0x7a,0x7b,0x7c,0x7d,0x7e,0x7f + + .byte 0x80,0x81,0x82,0x83,0x84,0x85,0x86,0x87 + .byte 0x88,0x89,0x8a,0x8b,0x8c,0x8d,0x8e,0x8f + .byte 0x90,0x91,0x92,0x93,0x94,0x95,0x96,0x97 + .byte 0x98,0x99,0x9a,0x9b,0x9c,0x9d,0x9e,0x9f + .byte 0xa0,0xa1,0xa2,0xa3,0xa4,0xa5,0xa6,0xa7 + .byte 0xa8,0xa9,0xaa,0xab,0xac,0xad,0xae,0xaf + .byte 0xb0,0xb1,0xb2,0xb3,0xb4,0xb5,0xb6,0xb7 + .byte 0xb8,0xb9,0xba,0xbb,0xbc,0xbd,0xbe,0xbf + .byte 0xc0,0x81,0x82,0x83,0x84,0x85,0x86,0x87 # .abcdefg + .byte 0x88,0x89,0xca,0xcb,0xcc,0xcd,0xce,0xcf # hi + .byte 0xd0,0x91,0x92,0x93,0x94,0x95,0x96,0x97 # .jklmnop + .byte 0x98,0x99,0xda,0xdb,0xdc,0xdd,0xde,0xdf # qr + .byte 0xe0,0xe1,0xa2,0xa3,0xa4,0xa5,0xa6,0xa7 # ..stuvwx + .byte 0xa8,0xa9,0xea,0xeb,0xec,0xed,0xee,0xef # yz + .byte 0xf0,0xf1,0xf2,0xf3,0xf4,0xf5,0xf6,0xf7 + .byte 0xf8,0xf9,0xfa,0xfb,0xfc,0xfd,0xfe,0xff + +# +# startup-code at 0x10000, running in absolute addressing mode +# this is called either by the ipl loader or directly by PSW restart +# or linload or SALIPL +# + .org 0x10000 +ENTRY(startup) + j .Lep_startup_normal + .org 0x10008 +# +# This is a list of s390 kernel entry points. At address 0x1000f the number of +# valid entry points is stored. +# +# IMPORTANT: Do not change this table, it is s390 kernel ABI! +# + .ascii "S390EP" + .byte 0x00,0x01 +# +# kdump startup-code at 0x10010, running in 64 bit absolute addressing mode +# + .org 0x10010 +ENTRY(startup_kdump) + j .Lep_startup_kdump +.Lep_startup_normal: + basr %r13,0 # get base +.LPG0: + xc 0x200(256),0x200 # partially clear lowcore + xc 0x300(256),0x300 + xc 0xe00(256),0xe00 + stck __LC_LAST_UPDATE_CLOCK + spt 5f-.LPG0(%r13) + mvc __LC_LAST_UPDATE_TIMER(8),5f-.LPG0(%r13) + xc __LC_STFL_FAC_LIST(8),__LC_STFL_FAC_LIST +#ifndef CONFIG_MARCH_G5 + # check capabilities against MARCH_{G5,Z900,Z990,Z9_109,Z10} + .insn s,0xb2b10000,__LC_STFL_FAC_LIST # store facility list + tm __LC_STFL_FAC_LIST,0x01 # stfle available ? + jz 0f + la %r0,0 + .insn s,0xb2b00000,__LC_STFL_FAC_LIST # store facility list extended +0: l %r0,__LC_STFL_FAC_LIST + n %r0,2f+8-.LPG0(%r13) + cl %r0,2f+8-.LPG0(%r13) + jne 1f + l %r0,__LC_STFL_FAC_LIST+4 + n %r0,2f+12-.LPG0(%r13) + cl %r0,2f+12-.LPG0(%r13) + je 3f +1: l %r15,.Lstack-.LPG0(%r13) + ahi %r15,-96 + la %r2,.Lals_string-.LPG0(%r13) + l %r3,.Lsclp_print-.LPG0(%r13) + basr %r14,%r3 + lpsw 2f-.LPG0(%r13) # machine type not good enough, crash +.Lals_string: + .asciz "The Linux kernel requires more recent processor hardware" +.Lsclp_print: + .long _sclp_print_early +.Lstack: + .long 0x8000 + (1<<(PAGE_SHIFT+THREAD_ORDER)) + .align 16 +2: .long 0x000a0000,0x8badcccc +#if defined(CONFIG_64BIT) +#if defined(CONFIG_MARCH_Z196) + .long 0xc100efe3, 0xf46c0000 +#elif defined(CONFIG_MARCH_Z10) + .long 0xc100efe3, 0xf0680000 +#elif defined(CONFIG_MARCH_Z9_109) + .long 0xc100efc3, 0x00000000 +#elif defined(CONFIG_MARCH_Z990) + .long 0xc0002000, 0x00000000 +#elif defined(CONFIG_MARCH_Z900) + .long 0xc0000000, 0x00000000 +#endif +#else +#if defined(CONFIG_MARCH_Z196) + .long 0x8100c880, 0x00000000 +#elif defined(CONFIG_MARCH_Z10) + .long 0x8100c880, 0x00000000 +#elif defined(CONFIG_MARCH_Z9_109) + .long 0x8100c880, 0x00000000 +#elif defined(CONFIG_MARCH_Z990) + .long 0x80002000, 0x00000000 +#elif defined(CONFIG_MARCH_Z900) + .long 0x80000000, 0x00000000 +#endif +#endif +3: +#endif + +#ifdef CONFIG_64BIT + mvi __LC_AR_MODE_ID,1 # set esame flag + slr %r0,%r0 # set cpuid to zero + lhi %r1,2 # mode 2 = esame (dump) + sigp %r1,%r0,0x12 # switch to esame mode + sam64 # switch to 64 bit mode + larl %r13,4f + lmh %r0,%r15,0(%r13) # clear high-order half + jg startup_continue +4: .fill 16,4,0x0 +#else + mvi __LC_AR_MODE_ID,0 # set ESA flag (mode 0) + l %r13,4f-.LPG0(%r13) + b 0(%r13) + .align 8 +4: .long startup_continue +#endif + .align 8 +5: .long 0x7fffffff,0xffffffff + +#include "head_kdump.S" + +# +# params at 10400 (setup.h) +# + .org PARMAREA + .long 0,0 # IPL_DEVICE + .long 0,0 # INITRD_START + .long 0,0 # INITRD_SIZE + .long 0,0 # OLDMEM_BASE + .long 0,0 # OLDMEM_SIZE + + .org COMMAND_LINE + .byte "root=/dev/ram0 ro" + .byte 0 + + .org 0x11000 diff --git a/arch/s390/kernel/head31.S b/arch/s390/kernel/head31.S new file mode 100644 index 00000000..d3f1ab7d --- /dev/null +++ b/arch/s390/kernel/head31.S @@ -0,0 +1,112 @@ +/* + * arch/s390/kernel/head31.S + * + * Copyright (C) IBM Corp. 2005,2010 + * + * Author(s): Hartmut Penner <hp@de.ibm.com> + * Martin Schwidefsky <schwidefsky@de.ibm.com> + * Rob van der Heij <rvdhei@iae.nl> + * Heiko Carstens <heiko.carstens@de.ibm.com> + * + */ + +#include <linux/init.h> +#include <linux/linkage.h> +#include <asm/asm-offsets.h> +#include <asm/thread_info.h> +#include <asm/page.h> + +__HEAD +ENTRY(startup_continue) + basr %r13,0 # get base +.LPG1: + + l %r1,.Lbase_cc-.LPG1(%r13) + mvc 0(8,%r1),__LC_LAST_UPDATE_CLOCK + lctl %c0,%c15,.Lctl-.LPG1(%r13) # load control registers + l %r12,.Lparmaddr-.LPG1(%r13) # pointer to parameter area + # move IPL device to lowcore +# +# Setup stack +# + l %r15,.Linittu-.LPG1(%r13) + st %r15,__LC_THREAD_INFO # cache thread info in lowcore + mvc __LC_CURRENT(4),__TI_task(%r15) + ahi %r15,1<<(PAGE_SHIFT+THREAD_ORDER) # init_task_union+THREAD_SIZE + st %r15,__LC_KERNEL_STACK # set end of kernel stack + ahi %r15,-96 +# +# Save ipl parameters, clear bss memory, initialize storage key for kernel pages, +# and create a kernel NSS if the SAVESYS= parm is defined +# + l %r14,.Lstartup_init-.LPG1(%r13) + basr %r14,%r14 + lpsw .Lentry-.LPG1(13) # jump to _stext in primary-space, + # virtual and never return ... + .align 8 +.Lentry:.long 0x00080000,0x80000000 + _stext +.Lctl: .long 0x04b50000 # cr0: various things + .long 0 # cr1: primary space segment table + .long .Lduct # cr2: dispatchable unit control table + .long 0 # cr3: instruction authorization + .long 0 # cr4: instruction authorization + .long .Lduct # cr5: primary-aste origin + .long 0 # cr6: I/O interrupts + .long 0 # cr7: secondary space segment table + .long 0 # cr8: access registers translation + .long 0 # cr9: tracing off + .long 0 # cr10: tracing off + .long 0 # cr11: tracing off + .long 0 # cr12: tracing off + .long 0 # cr13: home space segment table + .long 0xc0000000 # cr14: machine check handling off + .long 0 # cr15: linkage stack operations +.Lmchunk:.long memory_chunk +.Lbss_bgn: .long __bss_start +.Lbss_end: .long _end +.Lparmaddr: .long PARMAREA +.Linittu: .long init_thread_union +.Lstartup_init: + .long startup_init + .align 64 +.Lduct: .long 0,0,0,0,.Lduald,0,0,0 + .long 0,0,0,0,0,0,0,0 + .align 128 +.Lduald:.rept 8 + .long 0x80000000,0,0,0 # invalid access-list entries + .endr +.Lbase_cc: + .long sched_clock_base_cc + +ENTRY(_ehead) + +#ifdef CONFIG_SHARED_KERNEL + .org 0x100000 - 0x11000 # head.o ends at 0x11000 +#endif + +# +# startup-code, running in absolute addressing mode +# +ENTRY(_stext) + basr %r13,0 # get base +.LPG3: +# check control registers + stctl %c0,%c15,0(%r15) + oi 2(%r15),0x60 # enable sigp emergency & external call + oi 0(%r15),0x10 # switch on low address protection + lctl %c0,%c15,0(%r15) + +# + lam 0,15,.Laregs-.LPG3(%r13) # load access regs needed by uaccess + l %r14,.Lstart-.LPG3(%r13) + basr %r14,%r14 # call start_kernel +# +# We returned from start_kernel ?!? PANIK +# + basr %r13,0 + lpsw .Ldw-.(%r13) # load disabled wait psw +# + .align 8 +.Ldw: .long 0x000a0000,0x00000000 +.Lstart:.long start_kernel +.Laregs:.long 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0 diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S new file mode 100644 index 00000000..99348c0e --- /dev/null +++ b/arch/s390/kernel/head64.S @@ -0,0 +1,107 @@ +/* + * arch/s390/kernel/head64.S + * + * Copyright (C) IBM Corp. 1999,2010 + * + * Author(s): Hartmut Penner <hp@de.ibm.com> + * Martin Schwidefsky <schwidefsky@de.ibm.com> + * Rob van der Heij <rvdhei@iae.nl> + * Heiko Carstens <heiko.carstens@de.ibm.com> + * + */ + +#include <linux/init.h> +#include <linux/linkage.h> +#include <asm/asm-offsets.h> +#include <asm/thread_info.h> +#include <asm/page.h> + +__HEAD +ENTRY(startup_continue) + larl %r1,sched_clock_base_cc + mvc 0(8,%r1),__LC_LAST_UPDATE_CLOCK + larl %r13,.LPG1 # get base + lctlg %c0,%c15,.Lctl-.LPG1(%r13) # load control registers + lg %r12,.Lparmaddr-.LPG1(%r13) # pointer to parameter area + # move IPL device to lowcore + lghi %r0,__LC_PASTE + stg %r0,__LC_VDSO_PER_CPU +# +# Setup stack +# + larl %r15,init_thread_union + stg %r15,__LC_THREAD_INFO # cache thread info in lowcore + lg %r14,__TI_task(%r15) # cache current in lowcore + stg %r14,__LC_CURRENT + aghi %r15,1<<(PAGE_SHIFT+THREAD_ORDER) # init_task_union + THREAD_SIZE + stg %r15,__LC_KERNEL_STACK # set end of kernel stack + aghi %r15,-160 +# +# Save ipl parameters, clear bss memory, initialize storage key for kernel pages, +# and create a kernel NSS if the SAVESYS= parm is defined +# + brasl %r14,startup_init + lpswe .Lentry-.LPG1(13) # jump to _stext in primary-space, + # virtual and never return ... + .align 16 +.LPG1: +.Lentry:.quad 0x0000000180000000,_stext +.Lctl: .quad 0x04040000 # cr0: AFP registers & secondary space + .quad 0 # cr1: primary space segment table + .quad .Lduct # cr2: dispatchable unit control table + .quad 0 # cr3: instruction authorization + .quad 0 # cr4: instruction authorization + .quad .Lduct # cr5: primary-aste origin + .quad 0 # cr6: I/O interrupts + .quad 0 # cr7: secondary space segment table + .quad 0 # cr8: access registers translation + .quad 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 +.Lpcmsk:.quad 0x0000000180000000 +.L4malign:.quad 0xffffffffffc00000 +.Lscan2g:.quad 0x80000000 + 0x20000 - 8 # 2GB + 128K - 8 +.Lnop: .long 0x07000700 +.Lparmaddr: + .quad PARMAREA + .align 64 +.Lduct: .long 0,0,0,0,.Lduald,0,0,0 + .long 0,0,0,0,0,0,0,0 + .align 128 +.Lduald:.rept 8 + .long 0x80000000,0,0,0 # invalid access-list entries + .endr + +ENTRY(_ehead) + +#ifdef CONFIG_SHARED_KERNEL + .org 0x100000 - 0x11000 # head.o ends at 0x11000 +#endif + +# +# startup-code, running in absolute addressing mode +# +ENTRY(_stext) + basr %r13,0 # get base +.LPG3: +# check control registers + stctg %c0,%c15,0(%r15) + oi 6(%r15),0x60 # enable sigp emergency & external call + oi 4(%r15),0x10 # switch on low address proctection + lctlg %c0,%c15,0(%r15) + + lam 0,15,.Laregs-.LPG3(%r13) # load acrs needed by uaccess + brasl %r14,start_kernel # go to C code +# +# We returned from start_kernel ?!? PANIK +# + basr %r13,0 + lpswe .Ldw-.(%r13) # load disabled wait psw + + .align 8 +.Ldw: .quad 0x0002000180000000,0x0000000000000000 +.Laregs:.long 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0 diff --git a/arch/s390/kernel/head_kdump.S b/arch/s390/kernel/head_kdump.S new file mode 100644 index 00000000..e1ac3893 --- /dev/null +++ b/arch/s390/kernel/head_kdump.S @@ -0,0 +1,119 @@ +/* + * S390 kdump lowlevel functions (new kernel) + * + * Copyright IBM Corp. 2011 + * Author(s): Michael Holzheu <holzheu@linux.vnet.ibm.com> + */ + +#define DATAMOVER_ADDR 0x4000 +#define COPY_PAGE_ADDR 0x6000 + +#ifdef CONFIG_CRASH_DUMP + +# +# kdump entry (new kernel - not yet relocated) +# +# Note: This code has to be position independent +# + +.align 2 +.Lep_startup_kdump: + lhi %r1,2 # mode 2 = esame (dump) + sigp %r1,%r0,0x12 # Switch to esame mode + sam64 # Switch to 64 bit addressing + basr %r13,0 +.Lbase: + larl %r2,.Lbase_addr # Check, if we have been + lg %r2,0(%r2) # already relocated: + clgr %r2,%r13 # + jne .Lrelocate # No : Start data mover + lghi %r2,0 # Yes: Start kdump kernel + brasl %r14,startup_kdump_relocated + +.Lrelocate: + larl %r4,startup + lg %r2,0x418(%r4) # Get kdump base + lg %r3,0x420(%r4) # Get kdump size + + larl %r10,.Lcopy_start # Source of data mover + lghi %r8,DATAMOVER_ADDR # Target of data mover + mvc 0(256,%r8),0(%r10) # Copy data mover code + + agr %r8,%r2 # Copy data mover to + mvc 0(256,%r8),0(%r10) # reserved mem + + lghi %r14,DATAMOVER_ADDR # Jump to copied data mover + basr %r14,%r14 +.Lbase_addr: + .quad .Lbase + +# +# kdump data mover code (runs at address DATAMOVER_ADDR) +# +# r2: kdump base address +# r3: kdump size +# +.Lcopy_start: + basr %r13,0 # Base +0: + lgr %r11,%r2 # Save kdump base address + lgr %r12,%r2 + agr %r12,%r3 # Compute kdump end address + + lghi %r5,0 + lghi %r10,COPY_PAGE_ADDR # Load copy page address +1: + mvc 0(256,%r10),0(%r5) # Copy old kernel to tmp + mvc 0(256,%r5),0(%r11) # Copy new kernel to old + mvc 0(256,%r11),0(%r10) # Copy tmp to new + aghi %r11,256 + aghi %r5,256 + clgr %r11,%r12 + jl 1b + + lg %r14,.Lstartup_kdump-0b(%r13) + basr %r14,%r14 # Start relocated kernel +.Lstartup_kdump: + .long 0x00000000,0x00000000 + startup_kdump_relocated +.Lcopy_end: + +# +# Startup of kdump (relocated new kernel) +# +.align 2 +startup_kdump_relocated: + basr %r13,0 +0: + mvc 0(8,%r0),.Lrestart_psw-0b(%r13) # Setup restart PSW + mvc 464(16,%r0),.Lpgm_psw-0b(%r13) # Setup pgm check PSW + lhi %r1,1 # Start new kernel + diag %r1,%r1,0x308 # with diag 308 + +.Lno_diag308: # No diag 308 + sam31 # Switch to 31 bit addr mode + sr %r1,%r1 # Erase register r1 + sr %r2,%r2 # Erase register r2 + sigp %r1,%r2,0x12 # Switch to 31 bit arch mode + lpsw 0 # Start new kernel... +.align 8 +.Lrestart_psw: + .long 0x00080000,0x80000000 + startup +.Lpgm_psw: + .quad 0x0000000180000000,0x0000000000000000 + .Lno_diag308 +#else +.align 2 +.Lep_startup_kdump: +#ifdef CONFIG_64BIT + larl %r13,startup_kdump_crash + lpswe 0(%r13) +.align 8 +startup_kdump_crash: + .quad 0x0002000080000000,0x0000000000000000 + startup_kdump_crash +#else + basr %r13,0 +0: lpsw startup_kdump_crash-0b(%r13) +.align 8 +startup_kdump_crash: + .long 0x000a0000,0x00000000 + startup_kdump_crash +#endif /* CONFIG_64BIT */ +#endif /* CONFIG_CRASH_DUMP */ diff --git a/arch/s390/kernel/init_task.c b/arch/s390/kernel/init_task.c new file mode 100644 index 00000000..4d1c9fb0 --- /dev/null +++ b/arch/s390/kernel/init_task.c @@ -0,0 +1,38 @@ +/* + * arch/s390/kernel/init_task.c + * + * S390 version + * + * Derived from "arch/i386/kernel/init_task.c" + */ + +#include <linux/mm.h> +#include <linux/fs.h> +#include <linux/module.h> +#include <linux/sched.h> +#include <linux/init_task.h> +#include <linux/mqueue.h> + +#include <asm/uaccess.h> +#include <asm/pgtable.h> + +static struct signal_struct init_signals = INIT_SIGNALS(init_signals); +static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand); +/* + * Initial thread structure. + * + * We need to make sure that this is THREAD_SIZE aligned due to the + * way process stacks are handled. This is done by having a special + * "init_task" linker map entry.. + */ +union thread_union init_thread_union __init_task_data = + { INIT_THREAD_INFO(init_task) }; + +/* + * Initial task structure. + * + * All other task structs will be allocated on slabs in fork.c + */ +struct task_struct init_task = INIT_TASK(init_task); + +EXPORT_SYMBOL(init_task); diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c new file mode 100644 index 00000000..8342e65a --- /dev/null +++ b/arch/s390/kernel/ipl.c @@ -0,0 +1,2069 @@ +/* + * arch/s390/kernel/ipl.c + * ipl/reipl/dump support for Linux on s390. + * + * Copyright IBM Corp. 2005,2012 + * Author(s): Michael Holzheu <holzheu@de.ibm.com> + * Heiko Carstens <heiko.carstens@de.ibm.com> + * Volker Sameske <sameske@de.ibm.com> + */ + +#include <linux/types.h> +#include <linux/module.h> +#include <linux/device.h> +#include <linux/delay.h> +#include <linux/reboot.h> +#include <linux/ctype.h> +#include <linux/fs.h> +#include <linux/gfp.h> +#include <linux/crash_dump.h> +#include <linux/debug_locks.h> +#include <asm/ipl.h> +#include <asm/smp.h> +#include <asm/setup.h> +#include <asm/cpcmd.h> +#include <asm/cio.h> +#include <asm/ebcdic.h> +#include <asm/reset.h> +#include <asm/sclp.h> +#include <asm/checksum.h> +#include <asm/debug.h> +#include <asm/os_info.h> +#include "entry.h" + +#define IPL_PARM_BLOCK_VERSION 0 + +#define IPL_UNKNOWN_STR "unknown" +#define IPL_CCW_STR "ccw" +#define IPL_FCP_STR "fcp" +#define IPL_FCP_DUMP_STR "fcp_dump" +#define IPL_NSS_STR "nss" + +#define DUMP_CCW_STR "ccw" +#define DUMP_FCP_STR "fcp" +#define DUMP_NONE_STR "none" + +/* + * Four shutdown trigger types are supported: + * - panic + * - halt + * - power off + * - reipl + * - restart + */ +#define ON_PANIC_STR "on_panic" +#define ON_HALT_STR "on_halt" +#define ON_POFF_STR "on_poff" +#define ON_REIPL_STR "on_reboot" +#define ON_RESTART_STR "on_restart" + +struct shutdown_action; +struct shutdown_trigger { + char *name; + struct shutdown_action *action; +}; + +/* + * The following shutdown action types are supported: + */ +#define SHUTDOWN_ACTION_IPL_STR "ipl" +#define SHUTDOWN_ACTION_REIPL_STR "reipl" +#define SHUTDOWN_ACTION_DUMP_STR "dump" +#define SHUTDOWN_ACTION_VMCMD_STR "vmcmd" +#define SHUTDOWN_ACTION_STOP_STR "stop" +#define SHUTDOWN_ACTION_DUMP_REIPL_STR "dump_reipl" + +struct shutdown_action { + char *name; + void (*fn) (struct shutdown_trigger *trigger); + int (*init) (void); + int init_rc; +}; + +static char *ipl_type_str(enum ipl_type type) +{ + switch (type) { + case IPL_TYPE_CCW: + return IPL_CCW_STR; + case IPL_TYPE_FCP: + return IPL_FCP_STR; + case IPL_TYPE_FCP_DUMP: + return IPL_FCP_DUMP_STR; + case IPL_TYPE_NSS: + return IPL_NSS_STR; + case IPL_TYPE_UNKNOWN: + default: + return IPL_UNKNOWN_STR; + } +} + +enum dump_type { + DUMP_TYPE_NONE = 1, + DUMP_TYPE_CCW = 2, + DUMP_TYPE_FCP = 4, +}; + +static char *dump_type_str(enum dump_type type) +{ + switch (type) { + case DUMP_TYPE_NONE: + return DUMP_NONE_STR; + case DUMP_TYPE_CCW: + return DUMP_CCW_STR; + case DUMP_TYPE_FCP: + return DUMP_FCP_STR; + default: + return NULL; + } +} + +/* + * Must be in data section since the bss section + * is not cleared when these are accessed. + */ +static u16 ipl_devno __attribute__((__section__(".data"))) = 0; +u32 ipl_flags __attribute__((__section__(".data"))) = 0; + +enum ipl_method { + REIPL_METHOD_CCW_CIO, + REIPL_METHOD_CCW_DIAG, + REIPL_METHOD_CCW_VM, + REIPL_METHOD_FCP_RO_DIAG, + REIPL_METHOD_FCP_RW_DIAG, + REIPL_METHOD_FCP_RO_VM, + REIPL_METHOD_FCP_DUMP, + REIPL_METHOD_NSS, + REIPL_METHOD_NSS_DIAG, + REIPL_METHOD_DEFAULT, +}; + +enum dump_method { + DUMP_METHOD_NONE, + DUMP_METHOD_CCW_CIO, + DUMP_METHOD_CCW_DIAG, + DUMP_METHOD_CCW_VM, + DUMP_METHOD_FCP_DIAG, +}; + +static int diag308_set_works = 0; + +static struct ipl_parameter_block ipl_block; + +static int reipl_capabilities = IPL_TYPE_UNKNOWN; + +static enum ipl_type reipl_type = IPL_TYPE_UNKNOWN; +static enum ipl_method reipl_method = REIPL_METHOD_DEFAULT; +static struct ipl_parameter_block *reipl_block_fcp; +static struct ipl_parameter_block *reipl_block_ccw; +static struct ipl_parameter_block *reipl_block_nss; +static struct ipl_parameter_block *reipl_block_actual; + +static int dump_capabilities = DUMP_TYPE_NONE; +static enum dump_type dump_type = DUMP_TYPE_NONE; +static enum dump_method dump_method = DUMP_METHOD_NONE; +static struct ipl_parameter_block *dump_block_fcp; +static struct ipl_parameter_block *dump_block_ccw; + +static struct sclp_ipl_info sclp_ipl_info; + +int diag308(unsigned long subcode, void *addr) +{ + register unsigned long _addr asm("0") = (unsigned long) addr; + register unsigned long _rc asm("1") = 0; + + asm volatile( + " diag %0,%2,0x308\n" + "0:\n" + EX_TABLE(0b,0b) + : "+d" (_addr), "+d" (_rc) + : "d" (subcode) : "cc", "memory"); + return _rc; +} +EXPORT_SYMBOL_GPL(diag308); + +/* SYSFS */ + +#define DEFINE_IPL_ATTR_RO(_prefix, _name, _format, _value) \ +static ssize_t sys_##_prefix##_##_name##_show(struct kobject *kobj, \ + struct kobj_attribute *attr, \ + char *page) \ +{ \ + return sprintf(page, _format, _value); \ +} \ +static struct kobj_attribute sys_##_prefix##_##_name##_attr = \ + __ATTR(_name, S_IRUGO, sys_##_prefix##_##_name##_show, NULL); + +#define DEFINE_IPL_ATTR_RW(_prefix, _name, _fmt_out, _fmt_in, _value) \ +static ssize_t sys_##_prefix##_##_name##_show(struct kobject *kobj, \ + struct kobj_attribute *attr, \ + char *page) \ +{ \ + return sprintf(page, _fmt_out, \ + (unsigned long long) _value); \ +} \ +static ssize_t sys_##_prefix##_##_name##_store(struct kobject *kobj, \ + struct kobj_attribute *attr, \ + const char *buf, size_t len) \ +{ \ + unsigned long long value; \ + if (sscanf(buf, _fmt_in, &value) != 1) \ + return -EINVAL; \ + _value = value; \ + return len; \ +} \ +static struct kobj_attribute sys_##_prefix##_##_name##_attr = \ + __ATTR(_name,(S_IRUGO | S_IWUSR), \ + sys_##_prefix##_##_name##_show, \ + sys_##_prefix##_##_name##_store); + +#define DEFINE_IPL_ATTR_STR_RW(_prefix, _name, _fmt_out, _fmt_in, _value)\ +static ssize_t sys_##_prefix##_##_name##_show(struct kobject *kobj, \ + struct kobj_attribute *attr, \ + char *page) \ +{ \ + return sprintf(page, _fmt_out, _value); \ +} \ +static ssize_t sys_##_prefix##_##_name##_store(struct kobject *kobj, \ + struct kobj_attribute *attr, \ + const char *buf, size_t len) \ +{ \ + strncpy(_value, buf, sizeof(_value) - 1); \ + strim(_value); \ + return len; \ +} \ +static struct kobj_attribute sys_##_prefix##_##_name##_attr = \ + __ATTR(_name,(S_IRUGO | S_IWUSR), \ + sys_##_prefix##_##_name##_show, \ + sys_##_prefix##_##_name##_store); + +static void make_attrs_ro(struct attribute **attrs) +{ + while (*attrs) { + (*attrs)->mode = S_IRUGO; + attrs++; + } +} + +/* + * ipl section + */ + +static __init enum ipl_type get_ipl_type(void) +{ + struct ipl_parameter_block *ipl = IPL_PARMBLOCK_START; + + if (ipl_flags & IPL_NSS_VALID) + return IPL_TYPE_NSS; + if (!(ipl_flags & IPL_DEVNO_VALID)) + return IPL_TYPE_UNKNOWN; + if (!(ipl_flags & IPL_PARMBLOCK_VALID)) + return IPL_TYPE_CCW; + if (ipl->hdr.version > IPL_MAX_SUPPORTED_VERSION) + return IPL_TYPE_UNKNOWN; + if (ipl->hdr.pbt != DIAG308_IPL_TYPE_FCP) + return IPL_TYPE_UNKNOWN; + if (ipl->ipl_info.fcp.opt == DIAG308_IPL_OPT_DUMP) + return IPL_TYPE_FCP_DUMP; + return IPL_TYPE_FCP; +} + +struct ipl_info ipl_info; +EXPORT_SYMBOL_GPL(ipl_info); + +static ssize_t ipl_type_show(struct kobject *kobj, struct kobj_attribute *attr, + char *page) +{ + return sprintf(page, "%s\n", ipl_type_str(ipl_info.type)); +} + +static struct kobj_attribute sys_ipl_type_attr = __ATTR_RO(ipl_type); + +/* VM IPL PARM routines */ +static size_t reipl_get_ascii_vmparm(char *dest, size_t size, + const struct ipl_parameter_block *ipb) +{ + int i; + size_t len; + char has_lowercase = 0; + + len = 0; + if ((ipb->ipl_info.ccw.vm_flags & DIAG308_VM_FLAGS_VP_VALID) && + (ipb->ipl_info.ccw.vm_parm_len > 0)) { + + len = min_t(size_t, size - 1, ipb->ipl_info.ccw.vm_parm_len); + memcpy(dest, ipb->ipl_info.ccw.vm_parm, len); + /* If at least one character is lowercase, we assume mixed + * case; otherwise we convert everything to lowercase. + */ + for (i = 0; i < len; i++) + if ((dest[i] > 0x80 && dest[i] < 0x8a) || /* a-i */ + (dest[i] > 0x90 && dest[i] < 0x9a) || /* j-r */ + (dest[i] > 0xa1 && dest[i] < 0xaa)) { /* s-z */ + has_lowercase = 1; + break; + } + if (!has_lowercase) + EBC_TOLOWER(dest, len); + EBCASC(dest, len); + } + dest[len] = 0; + + return len; +} + +size_t append_ipl_vmparm(char *dest, size_t size) +{ + size_t rc; + + rc = 0; + if (diag308_set_works && (ipl_block.hdr.pbt == DIAG308_IPL_TYPE_CCW)) + rc = reipl_get_ascii_vmparm(dest, size, &ipl_block); + else + dest[0] = 0; + return rc; +} + +static ssize_t ipl_vm_parm_show(struct kobject *kobj, + struct kobj_attribute *attr, char *page) +{ + char parm[DIAG308_VMPARM_SIZE + 1] = {}; + + append_ipl_vmparm(parm, sizeof(parm)); + return sprintf(page, "%s\n", parm); +} + +static size_t scpdata_length(const char* buf, size_t count) +{ + while (count) { + if (buf[count - 1] != '\0' && buf[count - 1] != ' ') + break; + count--; + } + return count; +} + +static size_t reipl_append_ascii_scpdata(char *dest, size_t size, + const struct ipl_parameter_block *ipb) +{ + size_t count; + size_t i; + int has_lowercase; + + count = min(size - 1, scpdata_length(ipb->ipl_info.fcp.scp_data, + ipb->ipl_info.fcp.scp_data_len)); + if (!count) + goto out; + + has_lowercase = 0; + for (i = 0; i < count; i++) { + if (!isascii(ipb->ipl_info.fcp.scp_data[i])) { + count = 0; + goto out; + } + if (!has_lowercase && islower(ipb->ipl_info.fcp.scp_data[i])) + has_lowercase = 1; + } + + if (has_lowercase) + memcpy(dest, ipb->ipl_info.fcp.scp_data, count); + else + for (i = 0; i < count; i++) + dest[i] = tolower(ipb->ipl_info.fcp.scp_data[i]); +out: + dest[count] = '\0'; + return count; +} + +size_t append_ipl_scpdata(char *dest, size_t len) +{ + size_t rc; + + rc = 0; + if (ipl_block.hdr.pbt == DIAG308_IPL_TYPE_FCP) + rc = reipl_append_ascii_scpdata(dest, len, &ipl_block); + else + dest[0] = 0; + return rc; +} + + +static struct kobj_attribute sys_ipl_vm_parm_attr = + __ATTR(parm, S_IRUGO, ipl_vm_parm_show, NULL); + +static ssize_t sys_ipl_device_show(struct kobject *kobj, + struct kobj_attribute *attr, char *page) +{ + struct ipl_parameter_block *ipl = IPL_PARMBLOCK_START; + + switch (ipl_info.type) { + case IPL_TYPE_CCW: + return sprintf(page, "0.0.%04x\n", ipl_devno); + case IPL_TYPE_FCP: + case IPL_TYPE_FCP_DUMP: + return sprintf(page, "0.0.%04x\n", ipl->ipl_info.fcp.devno); + default: + return 0; + } +} + +static struct kobj_attribute sys_ipl_device_attr = + __ATTR(device, S_IRUGO, sys_ipl_device_show, NULL); + +static ssize_t ipl_parameter_read(struct file *filp, struct kobject *kobj, + struct bin_attribute *attr, char *buf, + loff_t off, size_t count) +{ + return memory_read_from_buffer(buf, count, &off, IPL_PARMBLOCK_START, + IPL_PARMBLOCK_SIZE); +} + +static struct bin_attribute ipl_parameter_attr = { + .attr = { + .name = "binary_parameter", + .mode = S_IRUGO, + }, + .size = PAGE_SIZE, + .read = &ipl_parameter_read, +}; + +static ssize_t ipl_scp_data_read(struct file *filp, struct kobject *kobj, + struct bin_attribute *attr, char *buf, + loff_t off, size_t count) +{ + unsigned int size = IPL_PARMBLOCK_START->ipl_info.fcp.scp_data_len; + void *scp_data = &IPL_PARMBLOCK_START->ipl_info.fcp.scp_data; + + return memory_read_from_buffer(buf, count, &off, scp_data, size); +} + +static struct bin_attribute ipl_scp_data_attr = { + .attr = { + .name = "scp_data", + .mode = S_IRUGO, + }, + .size = PAGE_SIZE, + .read = ipl_scp_data_read, +}; + +/* FCP ipl device attributes */ + +DEFINE_IPL_ATTR_RO(ipl_fcp, wwpn, "0x%016llx\n", (unsigned long long) + IPL_PARMBLOCK_START->ipl_info.fcp.wwpn); +DEFINE_IPL_ATTR_RO(ipl_fcp, lun, "0x%016llx\n", (unsigned long long) + IPL_PARMBLOCK_START->ipl_info.fcp.lun); +DEFINE_IPL_ATTR_RO(ipl_fcp, bootprog, "%lld\n", (unsigned long long) + IPL_PARMBLOCK_START->ipl_info.fcp.bootprog); +DEFINE_IPL_ATTR_RO(ipl_fcp, br_lba, "%lld\n", (unsigned long long) + IPL_PARMBLOCK_START->ipl_info.fcp.br_lba); + +static struct attribute *ipl_fcp_attrs[] = { + &sys_ipl_type_attr.attr, + &sys_ipl_device_attr.attr, + &sys_ipl_fcp_wwpn_attr.attr, + &sys_ipl_fcp_lun_attr.attr, + &sys_ipl_fcp_bootprog_attr.attr, + &sys_ipl_fcp_br_lba_attr.attr, + NULL, +}; + +static struct attribute_group ipl_fcp_attr_group = { + .attrs = ipl_fcp_attrs, +}; + +/* CCW ipl device attributes */ + +static ssize_t ipl_ccw_loadparm_show(struct kobject *kobj, + struct kobj_attribute *attr, char *page) +{ + char loadparm[LOADPARM_LEN + 1] = {}; + + if (!sclp_ipl_info.is_valid) + return sprintf(page, "#unknown#\n"); + memcpy(loadparm, &sclp_ipl_info.loadparm, LOADPARM_LEN); + EBCASC(loadparm, LOADPARM_LEN); + strim(loadparm); + return sprintf(page, "%s\n", loadparm); +} + +static struct kobj_attribute sys_ipl_ccw_loadparm_attr = + __ATTR(loadparm, 0444, ipl_ccw_loadparm_show, NULL); + +static struct attribute *ipl_ccw_attrs_vm[] = { + &sys_ipl_type_attr.attr, + &sys_ipl_device_attr.attr, + &sys_ipl_ccw_loadparm_attr.attr, + &sys_ipl_vm_parm_attr.attr, + NULL, +}; + +static struct attribute *ipl_ccw_attrs_lpar[] = { + &sys_ipl_type_attr.attr, + &sys_ipl_device_attr.attr, + &sys_ipl_ccw_loadparm_attr.attr, + NULL, +}; + +static struct attribute_group ipl_ccw_attr_group_vm = { + .attrs = ipl_ccw_attrs_vm, +}; + +static struct attribute_group ipl_ccw_attr_group_lpar = { + .attrs = ipl_ccw_attrs_lpar +}; + +/* NSS ipl device attributes */ + +DEFINE_IPL_ATTR_RO(ipl_nss, name, "%s\n", kernel_nss_name); + +static struct attribute *ipl_nss_attrs[] = { + &sys_ipl_type_attr.attr, + &sys_ipl_nss_name_attr.attr, + &sys_ipl_ccw_loadparm_attr.attr, + &sys_ipl_vm_parm_attr.attr, + NULL, +}; + +static struct attribute_group ipl_nss_attr_group = { + .attrs = ipl_nss_attrs, +}; + +/* UNKNOWN ipl device attributes */ + +static struct attribute *ipl_unknown_attrs[] = { + &sys_ipl_type_attr.attr, + NULL, +}; + +static struct attribute_group ipl_unknown_attr_group = { + .attrs = ipl_unknown_attrs, +}; + +static struct kset *ipl_kset; + +static int __init ipl_register_fcp_files(void) +{ + int rc; + + rc = sysfs_create_group(&ipl_kset->kobj, &ipl_fcp_attr_group); + if (rc) + goto out; + rc = sysfs_create_bin_file(&ipl_kset->kobj, &ipl_parameter_attr); + if (rc) + goto out_ipl_parm; + rc = sysfs_create_bin_file(&ipl_kset->kobj, &ipl_scp_data_attr); + if (!rc) + goto out; + + sysfs_remove_bin_file(&ipl_kset->kobj, &ipl_parameter_attr); + +out_ipl_parm: + sysfs_remove_group(&ipl_kset->kobj, &ipl_fcp_attr_group); +out: + return rc; +} + +static void __ipl_run(void *unused) +{ + diag308(DIAG308_IPL, NULL); + if (MACHINE_IS_VM) + __cpcmd("IPL", NULL, 0, NULL); + else if (ipl_info.type == IPL_TYPE_CCW) + reipl_ccw_dev(&ipl_info.data.ccw.dev_id); +} + +static void ipl_run(struct shutdown_trigger *trigger) +{ + smp_call_ipl_cpu(__ipl_run, NULL); +} + +static int __init ipl_init(void) +{ + int rc; + + ipl_kset = kset_create_and_add("ipl", NULL, firmware_kobj); + if (!ipl_kset) { + rc = -ENOMEM; + goto out; + } + switch (ipl_info.type) { + case IPL_TYPE_CCW: + if (MACHINE_IS_VM) + rc = sysfs_create_group(&ipl_kset->kobj, + &ipl_ccw_attr_group_vm); + else + rc = sysfs_create_group(&ipl_kset->kobj, + &ipl_ccw_attr_group_lpar); + break; + case IPL_TYPE_FCP: + case IPL_TYPE_FCP_DUMP: + rc = ipl_register_fcp_files(); + break; + case IPL_TYPE_NSS: + rc = sysfs_create_group(&ipl_kset->kobj, &ipl_nss_attr_group); + break; + default: + rc = sysfs_create_group(&ipl_kset->kobj, + &ipl_unknown_attr_group); + break; + } +out: + if (rc) + panic("ipl_init failed: rc = %i\n", rc); + + return 0; +} + +static struct shutdown_action __refdata ipl_action = { + .name = SHUTDOWN_ACTION_IPL_STR, + .fn = ipl_run, + .init = ipl_init, +}; + +/* + * reipl shutdown action: Reboot Linux on shutdown. + */ + +/* VM IPL PARM attributes */ +static ssize_t reipl_generic_vmparm_show(struct ipl_parameter_block *ipb, + char *page) +{ + char vmparm[DIAG308_VMPARM_SIZE + 1] = {}; + + reipl_get_ascii_vmparm(vmparm, sizeof(vmparm), ipb); + return sprintf(page, "%s\n", vmparm); +} + +static ssize_t reipl_generic_vmparm_store(struct ipl_parameter_block *ipb, + size_t vmparm_max, + const char *buf, size_t len) +{ + int i, ip_len; + + /* ignore trailing newline */ + ip_len = len; + if ((len > 0) && (buf[len - 1] == '\n')) + ip_len--; + + if (ip_len > vmparm_max) + return -EINVAL; + + /* parm is used to store kernel options, check for common chars */ + for (i = 0; i < ip_len; i++) + if (!(isalnum(buf[i]) || isascii(buf[i]) || isprint(buf[i]))) + return -EINVAL; + + memset(ipb->ipl_info.ccw.vm_parm, 0, DIAG308_VMPARM_SIZE); + ipb->ipl_info.ccw.vm_parm_len = ip_len; + if (ip_len > 0) { + ipb->ipl_info.ccw.vm_flags |= DIAG308_VM_FLAGS_VP_VALID; + memcpy(ipb->ipl_info.ccw.vm_parm, buf, ip_len); + ASCEBC(ipb->ipl_info.ccw.vm_parm, ip_len); + } else { + ipb->ipl_info.ccw.vm_flags &= ~DIAG308_VM_FLAGS_VP_VALID; + } + + return len; +} + +/* NSS wrapper */ +static ssize_t reipl_nss_vmparm_show(struct kobject *kobj, + struct kobj_attribute *attr, char *page) +{ + return reipl_generic_vmparm_show(reipl_block_nss, page); +} + +static ssize_t reipl_nss_vmparm_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t len) +{ + return reipl_generic_vmparm_store(reipl_block_nss, 56, buf, len); +} + +/* CCW wrapper */ +static ssize_t reipl_ccw_vmparm_show(struct kobject *kobj, + struct kobj_attribute *attr, char *page) +{ + return reipl_generic_vmparm_show(reipl_block_ccw, page); +} + +static ssize_t reipl_ccw_vmparm_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t len) +{ + return reipl_generic_vmparm_store(reipl_block_ccw, 64, buf, len); +} + +static struct kobj_attribute sys_reipl_nss_vmparm_attr = + __ATTR(parm, S_IRUGO | S_IWUSR, reipl_nss_vmparm_show, + reipl_nss_vmparm_store); +static struct kobj_attribute sys_reipl_ccw_vmparm_attr = + __ATTR(parm, S_IRUGO | S_IWUSR, reipl_ccw_vmparm_show, + reipl_ccw_vmparm_store); + +/* FCP reipl device attributes */ + +static ssize_t reipl_fcp_scpdata_read(struct file *filp, struct kobject *kobj, + struct bin_attribute *attr, + char *buf, loff_t off, size_t count) +{ + size_t size = reipl_block_fcp->ipl_info.fcp.scp_data_len; + void *scp_data = reipl_block_fcp->ipl_info.fcp.scp_data; + + return memory_read_from_buffer(buf, count, &off, scp_data, size); +} + +static ssize_t reipl_fcp_scpdata_write(struct file *filp, struct kobject *kobj, + struct bin_attribute *attr, + char *buf, loff_t off, size_t count) +{ + size_t padding; + size_t scpdata_len; + + if (off < 0) + return -EINVAL; + + if (off >= DIAG308_SCPDATA_SIZE) + return -ENOSPC; + + if (count > DIAG308_SCPDATA_SIZE - off) + count = DIAG308_SCPDATA_SIZE - off; + + memcpy(reipl_block_fcp->ipl_info.fcp.scp_data, buf + off, count); + scpdata_len = off + count; + + if (scpdata_len % 8) { + padding = 8 - (scpdata_len % 8); + memset(reipl_block_fcp->ipl_info.fcp.scp_data + scpdata_len, + 0, padding); + scpdata_len += padding; + } + + reipl_block_fcp->ipl_info.fcp.scp_data_len = scpdata_len; + reipl_block_fcp->hdr.len = IPL_PARM_BLK_FCP_LEN + scpdata_len; + reipl_block_fcp->hdr.blk0_len = IPL_PARM_BLK0_FCP_LEN + scpdata_len; + + return count; +} + +static struct bin_attribute sys_reipl_fcp_scp_data_attr = { + .attr = { + .name = "scp_data", + .mode = S_IRUGO | S_IWUSR, + }, + .size = PAGE_SIZE, + .read = reipl_fcp_scpdata_read, + .write = reipl_fcp_scpdata_write, +}; + +DEFINE_IPL_ATTR_RW(reipl_fcp, wwpn, "0x%016llx\n", "%016llx\n", + reipl_block_fcp->ipl_info.fcp.wwpn); +DEFINE_IPL_ATTR_RW(reipl_fcp, lun, "0x%016llx\n", "%016llx\n", + reipl_block_fcp->ipl_info.fcp.lun); +DEFINE_IPL_ATTR_RW(reipl_fcp, bootprog, "%lld\n", "%lld\n", + reipl_block_fcp->ipl_info.fcp.bootprog); +DEFINE_IPL_ATTR_RW(reipl_fcp, br_lba, "%lld\n", "%lld\n", + reipl_block_fcp->ipl_info.fcp.br_lba); +DEFINE_IPL_ATTR_RW(reipl_fcp, device, "0.0.%04llx\n", "0.0.%llx\n", + reipl_block_fcp->ipl_info.fcp.devno); + +static struct attribute *reipl_fcp_attrs[] = { + &sys_reipl_fcp_device_attr.attr, + &sys_reipl_fcp_wwpn_attr.attr, + &sys_reipl_fcp_lun_attr.attr, + &sys_reipl_fcp_bootprog_attr.attr, + &sys_reipl_fcp_br_lba_attr.attr, + NULL, +}; + +static struct attribute_group reipl_fcp_attr_group = { + .attrs = reipl_fcp_attrs, +}; + +/* CCW reipl device attributes */ + +DEFINE_IPL_ATTR_RW(reipl_ccw, device, "0.0.%04llx\n", "0.0.%llx\n", + reipl_block_ccw->ipl_info.ccw.devno); + +static void reipl_get_ascii_loadparm(char *loadparm, + struct ipl_parameter_block *ibp) +{ + memcpy(loadparm, ibp->ipl_info.ccw.load_parm, LOADPARM_LEN); + EBCASC(loadparm, LOADPARM_LEN); + loadparm[LOADPARM_LEN] = 0; + strim(loadparm); +} + +static ssize_t reipl_generic_loadparm_show(struct ipl_parameter_block *ipb, + char *page) +{ + char buf[LOADPARM_LEN + 1]; + + reipl_get_ascii_loadparm(buf, ipb); + return sprintf(page, "%s\n", buf); +} + +static ssize_t reipl_generic_loadparm_store(struct ipl_parameter_block *ipb, + const char *buf, size_t len) +{ + int i, lp_len; + + /* ignore trailing newline */ + lp_len = len; + if ((len > 0) && (buf[len - 1] == '\n')) + lp_len--; + /* loadparm can have max 8 characters and must not start with a blank */ + if ((lp_len > LOADPARM_LEN) || ((lp_len > 0) && (buf[0] == ' '))) + return -EINVAL; + /* loadparm can only contain "a-z,A-Z,0-9,SP,." */ + for (i = 0; i < lp_len; i++) { + if (isalpha(buf[i]) || isdigit(buf[i]) || (buf[i] == ' ') || + (buf[i] == '.')) + continue; + return -EINVAL; + } + /* initialize loadparm with blanks */ + memset(ipb->ipl_info.ccw.load_parm, ' ', LOADPARM_LEN); + /* copy and convert to ebcdic */ + memcpy(ipb->ipl_info.ccw.load_parm, buf, lp_len); + ASCEBC(ipb->ipl_info.ccw.load_parm, LOADPARM_LEN); + return len; +} + +/* NSS wrapper */ +static ssize_t reipl_nss_loadparm_show(struct kobject *kobj, + struct kobj_attribute *attr, char *page) +{ + return reipl_generic_loadparm_show(reipl_block_nss, page); +} + +static ssize_t reipl_nss_loadparm_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t len) +{ + return reipl_generic_loadparm_store(reipl_block_nss, buf, len); +} + +/* CCW wrapper */ +static ssize_t reipl_ccw_loadparm_show(struct kobject *kobj, + struct kobj_attribute *attr, char *page) +{ + return reipl_generic_loadparm_show(reipl_block_ccw, page); +} + +static ssize_t reipl_ccw_loadparm_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t len) +{ + return reipl_generic_loadparm_store(reipl_block_ccw, buf, len); +} + +static struct kobj_attribute sys_reipl_ccw_loadparm_attr = + __ATTR(loadparm, S_IRUGO | S_IWUSR, reipl_ccw_loadparm_show, + reipl_ccw_loadparm_store); + +static struct attribute *reipl_ccw_attrs_vm[] = { + &sys_reipl_ccw_device_attr.attr, + &sys_reipl_ccw_loadparm_attr.attr, + &sys_reipl_ccw_vmparm_attr.attr, + NULL, +}; + +static struct attribute *reipl_ccw_attrs_lpar[] = { + &sys_reipl_ccw_device_attr.attr, + &sys_reipl_ccw_loadparm_attr.attr, + NULL, +}; + +static struct attribute_group reipl_ccw_attr_group_vm = { + .name = IPL_CCW_STR, + .attrs = reipl_ccw_attrs_vm, +}; + +static struct attribute_group reipl_ccw_attr_group_lpar = { + .name = IPL_CCW_STR, + .attrs = reipl_ccw_attrs_lpar, +}; + + +/* NSS reipl device attributes */ +static void reipl_get_ascii_nss_name(char *dst, + struct ipl_parameter_block *ipb) +{ + memcpy(dst, ipb->ipl_info.ccw.nss_name, NSS_NAME_SIZE); + EBCASC(dst, NSS_NAME_SIZE); + dst[NSS_NAME_SIZE] = 0; +} + +static ssize_t reipl_nss_name_show(struct kobject *kobj, + struct kobj_attribute *attr, char *page) +{ + char nss_name[NSS_NAME_SIZE + 1] = {}; + + reipl_get_ascii_nss_name(nss_name, reipl_block_nss); + return sprintf(page, "%s\n", nss_name); +} + +static ssize_t reipl_nss_name_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t len) +{ + int nss_len; + + /* ignore trailing newline */ + nss_len = len; + if ((len > 0) && (buf[len - 1] == '\n')) + nss_len--; + + if (nss_len > NSS_NAME_SIZE) + return -EINVAL; + + memset(reipl_block_nss->ipl_info.ccw.nss_name, 0x40, NSS_NAME_SIZE); + if (nss_len > 0) { + reipl_block_nss->ipl_info.ccw.vm_flags |= + DIAG308_VM_FLAGS_NSS_VALID; + memcpy(reipl_block_nss->ipl_info.ccw.nss_name, buf, nss_len); + ASCEBC(reipl_block_nss->ipl_info.ccw.nss_name, nss_len); + EBC_TOUPPER(reipl_block_nss->ipl_info.ccw.nss_name, nss_len); + } else { + reipl_block_nss->ipl_info.ccw.vm_flags &= + ~DIAG308_VM_FLAGS_NSS_VALID; + } + + return len; +} + +static struct kobj_attribute sys_reipl_nss_name_attr = + __ATTR(name, S_IRUGO | S_IWUSR, reipl_nss_name_show, + reipl_nss_name_store); + +static struct kobj_attribute sys_reipl_nss_loadparm_attr = + __ATTR(loadparm, S_IRUGO | S_IWUSR, reipl_nss_loadparm_show, + reipl_nss_loadparm_store); + +static struct attribute *reipl_nss_attrs[] = { + &sys_reipl_nss_name_attr.attr, + &sys_reipl_nss_loadparm_attr.attr, + &sys_reipl_nss_vmparm_attr.attr, + NULL, +}; + +static struct attribute_group reipl_nss_attr_group = { + .name = IPL_NSS_STR, + .attrs = reipl_nss_attrs, +}; + +static void set_reipl_block_actual(struct ipl_parameter_block *reipl_block) +{ + reipl_block_actual = reipl_block; + os_info_entry_add(OS_INFO_REIPL_BLOCK, reipl_block_actual, + reipl_block->hdr.len); +} + +/* reipl type */ + +static int reipl_set_type(enum ipl_type type) +{ + if (!(reipl_capabilities & type)) + return -EINVAL; + + switch(type) { + case IPL_TYPE_CCW: + if (diag308_set_works) + reipl_method = REIPL_METHOD_CCW_DIAG; + else if (MACHINE_IS_VM) + reipl_method = REIPL_METHOD_CCW_VM; + else + reipl_method = REIPL_METHOD_CCW_CIO; + set_reipl_block_actual(reipl_block_ccw); + break; + case IPL_TYPE_FCP: + if (diag308_set_works) + reipl_method = REIPL_METHOD_FCP_RW_DIAG; + else if (MACHINE_IS_VM) + reipl_method = REIPL_METHOD_FCP_RO_VM; + else + reipl_method = REIPL_METHOD_FCP_RO_DIAG; + set_reipl_block_actual(reipl_block_fcp); + break; + case IPL_TYPE_FCP_DUMP: + reipl_method = REIPL_METHOD_FCP_DUMP; + break; + case IPL_TYPE_NSS: + if (diag308_set_works) + reipl_method = REIPL_METHOD_NSS_DIAG; + else + reipl_method = REIPL_METHOD_NSS; + set_reipl_block_actual(reipl_block_nss); + break; + case IPL_TYPE_UNKNOWN: + reipl_method = REIPL_METHOD_DEFAULT; + break; + default: + BUG(); + } + reipl_type = type; + return 0; +} + +static ssize_t reipl_type_show(struct kobject *kobj, + struct kobj_attribute *attr, char *page) +{ + return sprintf(page, "%s\n", ipl_type_str(reipl_type)); +} + +static ssize_t reipl_type_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t len) +{ + int rc = -EINVAL; + + if (strncmp(buf, IPL_CCW_STR, strlen(IPL_CCW_STR)) == 0) + rc = reipl_set_type(IPL_TYPE_CCW); + else if (strncmp(buf, IPL_FCP_STR, strlen(IPL_FCP_STR)) == 0) + rc = reipl_set_type(IPL_TYPE_FCP); + else if (strncmp(buf, IPL_NSS_STR, strlen(IPL_NSS_STR)) == 0) + rc = reipl_set_type(IPL_TYPE_NSS); + return (rc != 0) ? rc : len; +} + +static struct kobj_attribute reipl_type_attr = + __ATTR(reipl_type, 0644, reipl_type_show, reipl_type_store); + +static struct kset *reipl_kset; +static struct kset *reipl_fcp_kset; + +static void get_ipl_string(char *dst, struct ipl_parameter_block *ipb, + const enum ipl_method m) +{ + char loadparm[LOADPARM_LEN + 1] = {}; + char vmparm[DIAG308_VMPARM_SIZE + 1] = {}; + char nss_name[NSS_NAME_SIZE + 1] = {}; + size_t pos = 0; + + reipl_get_ascii_loadparm(loadparm, ipb); + reipl_get_ascii_nss_name(nss_name, ipb); + reipl_get_ascii_vmparm(vmparm, sizeof(vmparm), ipb); + + switch (m) { + case REIPL_METHOD_CCW_VM: + pos = sprintf(dst, "IPL %X CLEAR", ipb->ipl_info.ccw.devno); + break; + case REIPL_METHOD_NSS: + pos = sprintf(dst, "IPL %s", nss_name); + break; + default: + break; + } + if (strlen(loadparm) > 0) + pos += sprintf(dst + pos, " LOADPARM '%s'", loadparm); + if (strlen(vmparm) > 0) + sprintf(dst + pos, " PARM %s", vmparm); +} + +static void __reipl_run(void *unused) +{ + struct ccw_dev_id devid; + static char buf[128]; + + switch (reipl_method) { + case REIPL_METHOD_CCW_CIO: + devid.devno = reipl_block_ccw->ipl_info.ccw.devno; + devid.ssid = 0; + reipl_ccw_dev(&devid); + break; + case REIPL_METHOD_CCW_VM: + get_ipl_string(buf, reipl_block_ccw, REIPL_METHOD_CCW_VM); + __cpcmd(buf, NULL, 0, NULL); + break; + case REIPL_METHOD_CCW_DIAG: + diag308(DIAG308_SET, reipl_block_ccw); + diag308(DIAG308_IPL, NULL); + break; + case REIPL_METHOD_FCP_RW_DIAG: + diag308(DIAG308_SET, reipl_block_fcp); + diag308(DIAG308_IPL, NULL); + break; + case REIPL_METHOD_FCP_RO_DIAG: + diag308(DIAG308_IPL, NULL); + break; + case REIPL_METHOD_FCP_RO_VM: + __cpcmd("IPL", NULL, 0, NULL); + break; + case REIPL_METHOD_NSS_DIAG: + diag308(DIAG308_SET, reipl_block_nss); + diag308(DIAG308_IPL, NULL); + break; + case REIPL_METHOD_NSS: + get_ipl_string(buf, reipl_block_nss, REIPL_METHOD_NSS); + __cpcmd(buf, NULL, 0, NULL); + break; + case REIPL_METHOD_DEFAULT: + if (MACHINE_IS_VM) + __cpcmd("IPL", NULL, 0, NULL); + diag308(DIAG308_IPL, NULL); + break; + case REIPL_METHOD_FCP_DUMP: + break; + } + disabled_wait((unsigned long) __builtin_return_address(0)); +} + +static void reipl_run(struct shutdown_trigger *trigger) +{ + smp_call_ipl_cpu(__reipl_run, NULL); +} + +static void reipl_block_ccw_init(struct ipl_parameter_block *ipb) +{ + ipb->hdr.len = IPL_PARM_BLK_CCW_LEN; + ipb->hdr.version = IPL_PARM_BLOCK_VERSION; + ipb->hdr.blk0_len = IPL_PARM_BLK0_CCW_LEN; + ipb->hdr.pbt = DIAG308_IPL_TYPE_CCW; +} + +static void reipl_block_ccw_fill_parms(struct ipl_parameter_block *ipb) +{ + /* LOADPARM */ + /* check if read scp info worked and set loadparm */ + if (sclp_ipl_info.is_valid) + memcpy(ipb->ipl_info.ccw.load_parm, + &sclp_ipl_info.loadparm, LOADPARM_LEN); + else + /* read scp info failed: set empty loadparm (EBCDIC blanks) */ + memset(ipb->ipl_info.ccw.load_parm, 0x40, LOADPARM_LEN); + ipb->hdr.flags = DIAG308_FLAGS_LP_VALID; + + /* VM PARM */ + if (MACHINE_IS_VM && diag308_set_works && + (ipl_block.ipl_info.ccw.vm_flags & DIAG308_VM_FLAGS_VP_VALID)) { + + ipb->ipl_info.ccw.vm_flags |= DIAG308_VM_FLAGS_VP_VALID; + ipb->ipl_info.ccw.vm_parm_len = + ipl_block.ipl_info.ccw.vm_parm_len; + memcpy(ipb->ipl_info.ccw.vm_parm, + ipl_block.ipl_info.ccw.vm_parm, DIAG308_VMPARM_SIZE); + } +} + +static int __init reipl_nss_init(void) +{ + int rc; + + if (!MACHINE_IS_VM) + return 0; + + reipl_block_nss = (void *) get_zeroed_page(GFP_KERNEL); + if (!reipl_block_nss) + return -ENOMEM; + + if (!diag308_set_works) + sys_reipl_nss_vmparm_attr.attr.mode = S_IRUGO; + + rc = sysfs_create_group(&reipl_kset->kobj, &reipl_nss_attr_group); + if (rc) + return rc; + + reipl_block_ccw_init(reipl_block_nss); + if (ipl_info.type == IPL_TYPE_NSS) { + memset(reipl_block_nss->ipl_info.ccw.nss_name, + ' ', NSS_NAME_SIZE); + memcpy(reipl_block_nss->ipl_info.ccw.nss_name, + kernel_nss_name, strlen(kernel_nss_name)); + ASCEBC(reipl_block_nss->ipl_info.ccw.nss_name, NSS_NAME_SIZE); + reipl_block_nss->ipl_info.ccw.vm_flags |= + DIAG308_VM_FLAGS_NSS_VALID; + + reipl_block_ccw_fill_parms(reipl_block_nss); + } + + reipl_capabilities |= IPL_TYPE_NSS; + return 0; +} + +static int __init reipl_ccw_init(void) +{ + int rc; + + reipl_block_ccw = (void *) get_zeroed_page(GFP_KERNEL); + if (!reipl_block_ccw) + return -ENOMEM; + + if (MACHINE_IS_VM) { + if (!diag308_set_works) + sys_reipl_ccw_vmparm_attr.attr.mode = S_IRUGO; + rc = sysfs_create_group(&reipl_kset->kobj, + &reipl_ccw_attr_group_vm); + } else { + if(!diag308_set_works) + sys_reipl_ccw_loadparm_attr.attr.mode = S_IRUGO; + rc = sysfs_create_group(&reipl_kset->kobj, + &reipl_ccw_attr_group_lpar); + } + if (rc) + return rc; + + reipl_block_ccw_init(reipl_block_ccw); + if (ipl_info.type == IPL_TYPE_CCW) { + reipl_block_ccw->ipl_info.ccw.devno = ipl_devno; + reipl_block_ccw_fill_parms(reipl_block_ccw); + } + + reipl_capabilities |= IPL_TYPE_CCW; + return 0; +} + +static int __init reipl_fcp_init(void) +{ + int rc; + + if (!diag308_set_works) { + if (ipl_info.type == IPL_TYPE_FCP) { + make_attrs_ro(reipl_fcp_attrs); + sys_reipl_fcp_scp_data_attr.attr.mode = S_IRUGO; + } else + return 0; + } + + reipl_block_fcp = (void *) get_zeroed_page(GFP_KERNEL); + if (!reipl_block_fcp) + return -ENOMEM; + + /* sysfs: create fcp kset for mixing attr group and bin attrs */ + reipl_fcp_kset = kset_create_and_add(IPL_FCP_STR, NULL, + &reipl_kset->kobj); + if (!reipl_fcp_kset) { + free_page((unsigned long) reipl_block_fcp); + return -ENOMEM; + } + + rc = sysfs_create_group(&reipl_fcp_kset->kobj, &reipl_fcp_attr_group); + if (rc) { + kset_unregister(reipl_fcp_kset); + free_page((unsigned long) reipl_block_fcp); + return rc; + } + + rc = sysfs_create_bin_file(&reipl_fcp_kset->kobj, + &sys_reipl_fcp_scp_data_attr); + if (rc) { + sysfs_remove_group(&reipl_fcp_kset->kobj, &reipl_fcp_attr_group); + kset_unregister(reipl_fcp_kset); + free_page((unsigned long) reipl_block_fcp); + return rc; + } + + if (ipl_info.type == IPL_TYPE_FCP) + memcpy(reipl_block_fcp, IPL_PARMBLOCK_START, PAGE_SIZE); + else { + reipl_block_fcp->hdr.len = IPL_PARM_BLK_FCP_LEN; + reipl_block_fcp->hdr.version = IPL_PARM_BLOCK_VERSION; + reipl_block_fcp->hdr.blk0_len = IPL_PARM_BLK0_FCP_LEN; + reipl_block_fcp->hdr.pbt = DIAG308_IPL_TYPE_FCP; + reipl_block_fcp->ipl_info.fcp.opt = DIAG308_IPL_OPT_IPL; + } + reipl_capabilities |= IPL_TYPE_FCP; + return 0; +} + +static int __init reipl_type_init(void) +{ + enum ipl_type reipl_type = ipl_info.type; + struct ipl_parameter_block *reipl_block; + unsigned long size; + + reipl_block = os_info_old_entry(OS_INFO_REIPL_BLOCK, &size); + if (!reipl_block) + goto out; + /* + * If we have an OS info reipl block, this will be used + */ + if (reipl_block->hdr.pbt == DIAG308_IPL_TYPE_FCP) { + memcpy(reipl_block_fcp, reipl_block, size); + reipl_type = IPL_TYPE_FCP; + } else if (reipl_block->hdr.pbt == DIAG308_IPL_TYPE_CCW) { + memcpy(reipl_block_ccw, reipl_block, size); + reipl_type = IPL_TYPE_CCW; + } +out: + return reipl_set_type(reipl_type); +} + +static int __init reipl_init(void) +{ + int rc; + + reipl_kset = kset_create_and_add("reipl", NULL, firmware_kobj); + if (!reipl_kset) + return -ENOMEM; + rc = sysfs_create_file(&reipl_kset->kobj, &reipl_type_attr.attr); + if (rc) { + kset_unregister(reipl_kset); + return rc; + } + rc = reipl_ccw_init(); + if (rc) + return rc; + rc = reipl_fcp_init(); + if (rc) + return rc; + rc = reipl_nss_init(); + if (rc) + return rc; + return reipl_type_init(); +} + +static struct shutdown_action __refdata reipl_action = { + .name = SHUTDOWN_ACTION_REIPL_STR, + .fn = reipl_run, + .init = reipl_init, +}; + +/* + * dump shutdown action: Dump Linux on shutdown. + */ + +/* FCP dump device attributes */ + +DEFINE_IPL_ATTR_RW(dump_fcp, wwpn, "0x%016llx\n", "%016llx\n", + dump_block_fcp->ipl_info.fcp.wwpn); +DEFINE_IPL_ATTR_RW(dump_fcp, lun, "0x%016llx\n", "%016llx\n", + dump_block_fcp->ipl_info.fcp.lun); +DEFINE_IPL_ATTR_RW(dump_fcp, bootprog, "%lld\n", "%lld\n", + dump_block_fcp->ipl_info.fcp.bootprog); +DEFINE_IPL_ATTR_RW(dump_fcp, br_lba, "%lld\n", "%lld\n", + dump_block_fcp->ipl_info.fcp.br_lba); +DEFINE_IPL_ATTR_RW(dump_fcp, device, "0.0.%04llx\n", "0.0.%llx\n", + dump_block_fcp->ipl_info.fcp.devno); + +static struct attribute *dump_fcp_attrs[] = { + &sys_dump_fcp_device_attr.attr, + &sys_dump_fcp_wwpn_attr.attr, + &sys_dump_fcp_lun_attr.attr, + &sys_dump_fcp_bootprog_attr.attr, + &sys_dump_fcp_br_lba_attr.attr, + NULL, +}; + +static struct attribute_group dump_fcp_attr_group = { + .name = IPL_FCP_STR, + .attrs = dump_fcp_attrs, +}; + +/* CCW dump device attributes */ + +DEFINE_IPL_ATTR_RW(dump_ccw, device, "0.0.%04llx\n", "0.0.%llx\n", + dump_block_ccw->ipl_info.ccw.devno); + +static struct attribute *dump_ccw_attrs[] = { + &sys_dump_ccw_device_attr.attr, + NULL, +}; + +static struct attribute_group dump_ccw_attr_group = { + .name = IPL_CCW_STR, + .attrs = dump_ccw_attrs, +}; + +/* dump type */ + +static int dump_set_type(enum dump_type type) +{ + if (!(dump_capabilities & type)) + return -EINVAL; + switch (type) { + case DUMP_TYPE_CCW: + if (diag308_set_works) + dump_method = DUMP_METHOD_CCW_DIAG; + else if (MACHINE_IS_VM) + dump_method = DUMP_METHOD_CCW_VM; + else + dump_method = DUMP_METHOD_CCW_CIO; + break; + case DUMP_TYPE_FCP: + dump_method = DUMP_METHOD_FCP_DIAG; + break; + default: + dump_method = DUMP_METHOD_NONE; + } + dump_type = type; + return 0; +} + +static ssize_t dump_type_show(struct kobject *kobj, + struct kobj_attribute *attr, char *page) +{ + return sprintf(page, "%s\n", dump_type_str(dump_type)); +} + +static ssize_t dump_type_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t len) +{ + int rc = -EINVAL; + + if (strncmp(buf, DUMP_NONE_STR, strlen(DUMP_NONE_STR)) == 0) + rc = dump_set_type(DUMP_TYPE_NONE); + else if (strncmp(buf, DUMP_CCW_STR, strlen(DUMP_CCW_STR)) == 0) + rc = dump_set_type(DUMP_TYPE_CCW); + else if (strncmp(buf, DUMP_FCP_STR, strlen(DUMP_FCP_STR)) == 0) + rc = dump_set_type(DUMP_TYPE_FCP); + return (rc != 0) ? rc : len; +} + +static struct kobj_attribute dump_type_attr = + __ATTR(dump_type, 0644, dump_type_show, dump_type_store); + +static struct kset *dump_kset; + +static void __dump_run(void *unused) +{ + struct ccw_dev_id devid; + static char buf[100]; + + switch (dump_method) { + case DUMP_METHOD_CCW_CIO: + devid.devno = dump_block_ccw->ipl_info.ccw.devno; + devid.ssid = 0; + reipl_ccw_dev(&devid); + break; + case DUMP_METHOD_CCW_VM: + sprintf(buf, "STORE STATUS"); + __cpcmd(buf, NULL, 0, NULL); + sprintf(buf, "IPL %X", dump_block_ccw->ipl_info.ccw.devno); + __cpcmd(buf, NULL, 0, NULL); + break; + case DUMP_METHOD_CCW_DIAG: + diag308(DIAG308_SET, dump_block_ccw); + diag308(DIAG308_DUMP, NULL); + break; + case DUMP_METHOD_FCP_DIAG: + diag308(DIAG308_SET, dump_block_fcp); + diag308(DIAG308_DUMP, NULL); + break; + default: + break; + } +} + +static void dump_run(struct shutdown_trigger *trigger) +{ + if (dump_method == DUMP_METHOD_NONE) + return; + smp_send_stop(); + smp_call_ipl_cpu(__dump_run, NULL); +} + +static int __init dump_ccw_init(void) +{ + int rc; + + dump_block_ccw = (void *) get_zeroed_page(GFP_KERNEL); + if (!dump_block_ccw) + return -ENOMEM; + rc = sysfs_create_group(&dump_kset->kobj, &dump_ccw_attr_group); + if (rc) { + free_page((unsigned long)dump_block_ccw); + return rc; + } + dump_block_ccw->hdr.len = IPL_PARM_BLK_CCW_LEN; + dump_block_ccw->hdr.version = IPL_PARM_BLOCK_VERSION; + dump_block_ccw->hdr.blk0_len = IPL_PARM_BLK0_CCW_LEN; + dump_block_ccw->hdr.pbt = DIAG308_IPL_TYPE_CCW; + dump_capabilities |= DUMP_TYPE_CCW; + return 0; +} + +static int __init dump_fcp_init(void) +{ + int rc; + + if (!sclp_ipl_info.has_dump) + return 0; /* LDIPL DUMP is not installed */ + if (!diag308_set_works) + return 0; + dump_block_fcp = (void *) get_zeroed_page(GFP_KERNEL); + if (!dump_block_fcp) + return -ENOMEM; + rc = sysfs_create_group(&dump_kset->kobj, &dump_fcp_attr_group); + if (rc) { + free_page((unsigned long)dump_block_fcp); + return rc; + } + dump_block_fcp->hdr.len = IPL_PARM_BLK_FCP_LEN; + dump_block_fcp->hdr.version = IPL_PARM_BLOCK_VERSION; + dump_block_fcp->hdr.blk0_len = IPL_PARM_BLK0_FCP_LEN; + dump_block_fcp->hdr.pbt = DIAG308_IPL_TYPE_FCP; + dump_block_fcp->ipl_info.fcp.opt = DIAG308_IPL_OPT_DUMP; + dump_capabilities |= DUMP_TYPE_FCP; + return 0; +} + +static int __init dump_init(void) +{ + int rc; + + dump_kset = kset_create_and_add("dump", NULL, firmware_kobj); + if (!dump_kset) + return -ENOMEM; + rc = sysfs_create_file(&dump_kset->kobj, &dump_type_attr.attr); + if (rc) { + kset_unregister(dump_kset); + return rc; + } + rc = dump_ccw_init(); + if (rc) + return rc; + rc = dump_fcp_init(); + if (rc) + return rc; + dump_set_type(DUMP_TYPE_NONE); + return 0; +} + +static struct shutdown_action __refdata dump_action = { + .name = SHUTDOWN_ACTION_DUMP_STR, + .fn = dump_run, + .init = dump_init, +}; + +static void dump_reipl_run(struct shutdown_trigger *trigger) +{ + u32 csum; + + csum = csum_partial(reipl_block_actual, reipl_block_actual->hdr.len, 0); + copy_to_absolute_zero(&S390_lowcore.ipib_checksum, &csum, sizeof(csum)); + copy_to_absolute_zero(&S390_lowcore.ipib, &reipl_block_actual, + sizeof(reipl_block_actual)); + dump_run(trigger); +} + +static int __init dump_reipl_init(void) +{ + if (!diag308_set_works) + return -EOPNOTSUPP; + else + return 0; +} + +static struct shutdown_action __refdata dump_reipl_action = { + .name = SHUTDOWN_ACTION_DUMP_REIPL_STR, + .fn = dump_reipl_run, + .init = dump_reipl_init, +}; + +/* + * vmcmd shutdown action: Trigger vm command on shutdown. + */ + +static char vmcmd_on_reboot[128]; +static char vmcmd_on_panic[128]; +static char vmcmd_on_halt[128]; +static char vmcmd_on_poff[128]; +static char vmcmd_on_restart[128]; + +DEFINE_IPL_ATTR_STR_RW(vmcmd, on_reboot, "%s\n", "%s\n", vmcmd_on_reboot); +DEFINE_IPL_ATTR_STR_RW(vmcmd, on_panic, "%s\n", "%s\n", vmcmd_on_panic); +DEFINE_IPL_ATTR_STR_RW(vmcmd, on_halt, "%s\n", "%s\n", vmcmd_on_halt); +DEFINE_IPL_ATTR_STR_RW(vmcmd, on_poff, "%s\n", "%s\n", vmcmd_on_poff); +DEFINE_IPL_ATTR_STR_RW(vmcmd, on_restart, "%s\n", "%s\n", vmcmd_on_restart); + +static struct attribute *vmcmd_attrs[] = { + &sys_vmcmd_on_reboot_attr.attr, + &sys_vmcmd_on_panic_attr.attr, + &sys_vmcmd_on_halt_attr.attr, + &sys_vmcmd_on_poff_attr.attr, + &sys_vmcmd_on_restart_attr.attr, + NULL, +}; + +static struct attribute_group vmcmd_attr_group = { + .attrs = vmcmd_attrs, +}; + +static struct kset *vmcmd_kset; + +static void vmcmd_run(struct shutdown_trigger *trigger) +{ + char *cmd, *next_cmd; + + if (strcmp(trigger->name, ON_REIPL_STR) == 0) + cmd = vmcmd_on_reboot; + else if (strcmp(trigger->name, ON_PANIC_STR) == 0) + cmd = vmcmd_on_panic; + else if (strcmp(trigger->name, ON_HALT_STR) == 0) + cmd = vmcmd_on_halt; + else if (strcmp(trigger->name, ON_POFF_STR) == 0) + cmd = vmcmd_on_poff; + else if (strcmp(trigger->name, ON_RESTART_STR) == 0) + cmd = vmcmd_on_restart; + else + return; + + if (strlen(cmd) == 0) + return; + do { + next_cmd = strchr(cmd, '\n'); + if (next_cmd) { + next_cmd[0] = 0; + next_cmd += 1; + } + __cpcmd(cmd, NULL, 0, NULL); + cmd = next_cmd; + } while (cmd != NULL); +} + +static int vmcmd_init(void) +{ + if (!MACHINE_IS_VM) + return -EOPNOTSUPP; + vmcmd_kset = kset_create_and_add("vmcmd", NULL, firmware_kobj); + if (!vmcmd_kset) + return -ENOMEM; + return sysfs_create_group(&vmcmd_kset->kobj, &vmcmd_attr_group); +} + +static struct shutdown_action vmcmd_action = {SHUTDOWN_ACTION_VMCMD_STR, + vmcmd_run, vmcmd_init}; + +/* + * stop shutdown action: Stop Linux on shutdown. + */ + +static void stop_run(struct shutdown_trigger *trigger) +{ + if (strcmp(trigger->name, ON_PANIC_STR) == 0 || + strcmp(trigger->name, ON_RESTART_STR) == 0) + disabled_wait((unsigned long) __builtin_return_address(0)); + smp_stop_cpu(); +} + +static struct shutdown_action stop_action = {SHUTDOWN_ACTION_STOP_STR, + stop_run, NULL}; + +/* action list */ + +static struct shutdown_action *shutdown_actions_list[] = { + &ipl_action, &reipl_action, &dump_reipl_action, &dump_action, + &vmcmd_action, &stop_action}; +#define SHUTDOWN_ACTIONS_COUNT (sizeof(shutdown_actions_list) / sizeof(void *)) + +/* + * Trigger section + */ + +static struct kset *shutdown_actions_kset; + +static int set_trigger(const char *buf, struct shutdown_trigger *trigger, + size_t len) +{ + int i; + + for (i = 0; i < SHUTDOWN_ACTIONS_COUNT; i++) { + if (sysfs_streq(buf, shutdown_actions_list[i]->name)) { + if (shutdown_actions_list[i]->init_rc) { + return shutdown_actions_list[i]->init_rc; + } else { + trigger->action = shutdown_actions_list[i]; + return len; + } + } + } + return -EINVAL; +} + +/* on reipl */ + +static struct shutdown_trigger on_reboot_trigger = {ON_REIPL_STR, + &reipl_action}; + +static ssize_t on_reboot_show(struct kobject *kobj, + struct kobj_attribute *attr, char *page) +{ + return sprintf(page, "%s\n", on_reboot_trigger.action->name); +} + +static ssize_t on_reboot_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t len) +{ + return set_trigger(buf, &on_reboot_trigger, len); +} + +static struct kobj_attribute on_reboot_attr = + __ATTR(on_reboot, 0644, on_reboot_show, on_reboot_store); + +static void do_machine_restart(char *__unused) +{ + smp_send_stop(); + on_reboot_trigger.action->fn(&on_reboot_trigger); + reipl_run(NULL); +} +void (*_machine_restart)(char *command) = do_machine_restart; + +/* on panic */ + +static struct shutdown_trigger on_panic_trigger = {ON_PANIC_STR, &stop_action}; + +static ssize_t on_panic_show(struct kobject *kobj, + struct kobj_attribute *attr, char *page) +{ + return sprintf(page, "%s\n", on_panic_trigger.action->name); +} + +static ssize_t on_panic_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t len) +{ + return set_trigger(buf, &on_panic_trigger, len); +} + +static struct kobj_attribute on_panic_attr = + __ATTR(on_panic, 0644, on_panic_show, on_panic_store); + +static void do_panic(void) +{ + lgr_info_log(); + on_panic_trigger.action->fn(&on_panic_trigger); + stop_run(&on_panic_trigger); +} + +/* on restart */ + +static struct shutdown_trigger on_restart_trigger = {ON_RESTART_STR, + &stop_action}; + +static ssize_t on_restart_show(struct kobject *kobj, + struct kobj_attribute *attr, char *page) +{ + return sprintf(page, "%s\n", on_restart_trigger.action->name); +} + +static ssize_t on_restart_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t len) +{ + return set_trigger(buf, &on_restart_trigger, len); +} + +static struct kobj_attribute on_restart_attr = + __ATTR(on_restart, 0644, on_restart_show, on_restart_store); + +static void __do_restart(void *ignore) +{ + smp_send_stop(); +#ifdef CONFIG_CRASH_DUMP + crash_kexec(NULL); +#endif + on_restart_trigger.action->fn(&on_restart_trigger); + stop_run(&on_restart_trigger); +} + +void do_restart(void) +{ + tracing_off(); + debug_locks_off(); + lgr_info_log(); + smp_call_online_cpu(__do_restart, NULL); +} + +/* on halt */ + +static struct shutdown_trigger on_halt_trigger = {ON_HALT_STR, &stop_action}; + +static ssize_t on_halt_show(struct kobject *kobj, + struct kobj_attribute *attr, char *page) +{ + return sprintf(page, "%s\n", on_halt_trigger.action->name); +} + +static ssize_t on_halt_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t len) +{ + return set_trigger(buf, &on_halt_trigger, len); +} + +static struct kobj_attribute on_halt_attr = + __ATTR(on_halt, 0644, on_halt_show, on_halt_store); + + +static void do_machine_halt(void) +{ + smp_send_stop(); + on_halt_trigger.action->fn(&on_halt_trigger); + stop_run(&on_halt_trigger); +} +void (*_machine_halt)(void) = do_machine_halt; + +/* on power off */ + +static struct shutdown_trigger on_poff_trigger = {ON_POFF_STR, &stop_action}; + +static ssize_t on_poff_show(struct kobject *kobj, + struct kobj_attribute *attr, char *page) +{ + return sprintf(page, "%s\n", on_poff_trigger.action->name); +} + +static ssize_t on_poff_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t len) +{ + return set_trigger(buf, &on_poff_trigger, len); +} + +static struct kobj_attribute on_poff_attr = + __ATTR(on_poff, 0644, on_poff_show, on_poff_store); + + +static void do_machine_power_off(void) +{ + smp_send_stop(); + on_poff_trigger.action->fn(&on_poff_trigger); + stop_run(&on_poff_trigger); +} +void (*_machine_power_off)(void) = do_machine_power_off; + +static void __init shutdown_triggers_init(void) +{ + shutdown_actions_kset = kset_create_and_add("shutdown_actions", NULL, + firmware_kobj); + if (!shutdown_actions_kset) + goto fail; + if (sysfs_create_file(&shutdown_actions_kset->kobj, + &on_reboot_attr.attr)) + goto fail; + if (sysfs_create_file(&shutdown_actions_kset->kobj, + &on_panic_attr.attr)) + goto fail; + if (sysfs_create_file(&shutdown_actions_kset->kobj, + &on_halt_attr.attr)) + goto fail; + if (sysfs_create_file(&shutdown_actions_kset->kobj, + &on_poff_attr.attr)) + goto fail; + if (sysfs_create_file(&shutdown_actions_kset->kobj, + &on_restart_attr.attr)) + goto fail; + return; +fail: + panic("shutdown_triggers_init failed\n"); +} + +static void __init shutdown_actions_init(void) +{ + int i; + + for (i = 0; i < SHUTDOWN_ACTIONS_COUNT; i++) { + if (!shutdown_actions_list[i]->init) + continue; + shutdown_actions_list[i]->init_rc = + shutdown_actions_list[i]->init(); + } +} + +static int __init s390_ipl_init(void) +{ + sclp_get_ipl_info(&sclp_ipl_info); + shutdown_actions_init(); + shutdown_triggers_init(); + return 0; +} + +__initcall(s390_ipl_init); + +static void __init strncpy_skip_quote(char *dst, char *src, int n) +{ + int sx, dx; + + dx = 0; + for (sx = 0; src[sx] != 0; sx++) { + if (src[sx] == '"') + continue; + dst[dx++] = src[sx]; + if (dx >= n) + break; + } +} + +static int __init vmcmd_on_reboot_setup(char *str) +{ + if (!MACHINE_IS_VM) + return 1; + strncpy_skip_quote(vmcmd_on_reboot, str, 127); + vmcmd_on_reboot[127] = 0; + on_reboot_trigger.action = &vmcmd_action; + return 1; +} +__setup("vmreboot=", vmcmd_on_reboot_setup); + +static int __init vmcmd_on_panic_setup(char *str) +{ + if (!MACHINE_IS_VM) + return 1; + strncpy_skip_quote(vmcmd_on_panic, str, 127); + vmcmd_on_panic[127] = 0; + on_panic_trigger.action = &vmcmd_action; + return 1; +} +__setup("vmpanic=", vmcmd_on_panic_setup); + +static int __init vmcmd_on_halt_setup(char *str) +{ + if (!MACHINE_IS_VM) + return 1; + strncpy_skip_quote(vmcmd_on_halt, str, 127); + vmcmd_on_halt[127] = 0; + on_halt_trigger.action = &vmcmd_action; + return 1; +} +__setup("vmhalt=", vmcmd_on_halt_setup); + +static int __init vmcmd_on_poff_setup(char *str) +{ + if (!MACHINE_IS_VM) + return 1; + strncpy_skip_quote(vmcmd_on_poff, str, 127); + vmcmd_on_poff[127] = 0; + on_poff_trigger.action = &vmcmd_action; + return 1; +} +__setup("vmpoff=", vmcmd_on_poff_setup); + +static int on_panic_notify(struct notifier_block *self, + unsigned long event, void *data) +{ + do_panic(); + return NOTIFY_OK; +} + +static struct notifier_block on_panic_nb = { + .notifier_call = on_panic_notify, + .priority = INT_MIN, +}; + +void __init setup_ipl(void) +{ + ipl_info.type = get_ipl_type(); + switch (ipl_info.type) { + case IPL_TYPE_CCW: + ipl_info.data.ccw.dev_id.devno = ipl_devno; + ipl_info.data.ccw.dev_id.ssid = 0; + break; + case IPL_TYPE_FCP: + case IPL_TYPE_FCP_DUMP: + ipl_info.data.fcp.dev_id.devno = + IPL_PARMBLOCK_START->ipl_info.fcp.devno; + ipl_info.data.fcp.dev_id.ssid = 0; + ipl_info.data.fcp.wwpn = IPL_PARMBLOCK_START->ipl_info.fcp.wwpn; + ipl_info.data.fcp.lun = IPL_PARMBLOCK_START->ipl_info.fcp.lun; + break; + case IPL_TYPE_NSS: + strncpy(ipl_info.data.nss.name, kernel_nss_name, + sizeof(ipl_info.data.nss.name)); + break; + case IPL_TYPE_UNKNOWN: + /* We have no info to copy */ + break; + } + atomic_notifier_chain_register(&panic_notifier_list, &on_panic_nb); +} + +void __init ipl_update_parameters(void) +{ + int rc; + + rc = diag308(DIAG308_STORE, &ipl_block); + if ((rc == DIAG308_RC_OK) || (rc == DIAG308_RC_NOCONFIG)) + diag308_set_works = 1; +} + +void __init ipl_save_parameters(void) +{ + struct cio_iplinfo iplinfo; + void *src, *dst; + + if (cio_get_iplinfo(&iplinfo)) + return; + + ipl_devno = iplinfo.devno; + ipl_flags |= IPL_DEVNO_VALID; + if (!iplinfo.is_qdio) + return; + ipl_flags |= IPL_PARMBLOCK_VALID; + src = (void *)(unsigned long)S390_lowcore.ipl_parmblock_ptr; + dst = (void *)IPL_PARMBLOCK_ORIGIN; + memmove(dst, src, PAGE_SIZE); + S390_lowcore.ipl_parmblock_ptr = IPL_PARMBLOCK_ORIGIN; +} + +static LIST_HEAD(rcall); +static DEFINE_MUTEX(rcall_mutex); + +void register_reset_call(struct reset_call *reset) +{ + mutex_lock(&rcall_mutex); + list_add(&reset->list, &rcall); + mutex_unlock(&rcall_mutex); +} +EXPORT_SYMBOL_GPL(register_reset_call); + +void unregister_reset_call(struct reset_call *reset) +{ + mutex_lock(&rcall_mutex); + list_del(&reset->list); + mutex_unlock(&rcall_mutex); +} +EXPORT_SYMBOL_GPL(unregister_reset_call); + +static void do_reset_calls(void) +{ + struct reset_call *reset; + +#ifdef CONFIG_64BIT + if (diag308_set_works) { + diag308_reset(); + return; + } +#endif + list_for_each_entry(reset, &rcall, list) + reset->fn(); +} + +u32 dump_prefix_page; + +void s390_reset_system(void (*func)(void *), void *data) +{ + struct _lowcore *lc; + + lc = (struct _lowcore *)(unsigned long) store_prefix(); + + /* Stack for interrupt/machine check handler */ + lc->panic_stack = S390_lowcore.panic_stack; + + /* Save prefix page address for dump case */ + dump_prefix_page = (u32)(unsigned long) lc; + + /* Disable prefixing */ + set_prefix(0); + + /* Disable lowcore protection */ + __ctl_clear_bit(0,28); + + /* Set new machine check handler */ + S390_lowcore.mcck_new_psw.mask = psw_kernel_bits | PSW_MASK_DAT; + S390_lowcore.mcck_new_psw.addr = + PSW_ADDR_AMODE | (unsigned long) s390_base_mcck_handler; + + /* Set new program check handler */ + S390_lowcore.program_new_psw.mask = psw_kernel_bits | PSW_MASK_DAT; + S390_lowcore.program_new_psw.addr = + PSW_ADDR_AMODE | (unsigned long) s390_base_pgm_handler; + + /* Store status at absolute zero */ + store_status(); + + do_reset_calls(); + if (func) + func(data); +} diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c new file mode 100644 index 00000000..8a22c272 --- /dev/null +++ b/arch/s390/kernel/irq.c @@ -0,0 +1,283 @@ +/* + * Copyright IBM Corp. 2004,2011 + * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>, + * Holger Smolinski <Holger.Smolinski@de.ibm.com>, + * Thomas Spatzier <tspat@de.ibm.com>, + * + * This file contains interrupt related functions. + */ + +#include <linux/kernel_stat.h> +#include <linux/interrupt.h> +#include <linux/seq_file.h> +#include <linux/proc_fs.h> +#include <linux/profile.h> +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/ftrace.h> +#include <linux/errno.h> +#include <linux/slab.h> +#include <linux/cpu.h> +#include <asm/irq_regs.h> +#include <asm/cputime.h> +#include <asm/lowcore.h> +#include <asm/irq.h> +#include "entry.h" + +struct irq_class { + char *name; + char *desc; +}; + +static const struct irq_class intrclass_names[] = { + {.name = "EXT" }, + {.name = "I/O" }, + {.name = "CLK", .desc = "[EXT] Clock Comparator" }, + {.name = "EXC", .desc = "[EXT] External Call" }, + {.name = "EMS", .desc = "[EXT] Emergency Signal" }, + {.name = "TMR", .desc = "[EXT] CPU Timer" }, + {.name = "TAL", .desc = "[EXT] Timing Alert" }, + {.name = "PFL", .desc = "[EXT] Pseudo Page Fault" }, + {.name = "DSD", .desc = "[EXT] DASD Diag" }, + {.name = "VRT", .desc = "[EXT] Virtio" }, + {.name = "SCP", .desc = "[EXT] Service Call" }, + {.name = "IUC", .desc = "[EXT] IUCV" }, + {.name = "CPM", .desc = "[EXT] CPU Measurement" }, + {.name = "CIO", .desc = "[I/O] Common I/O Layer Interrupt" }, + {.name = "QAI", .desc = "[I/O] QDIO Adapter Interrupt" }, + {.name = "DAS", .desc = "[I/O] DASD" }, + {.name = "C15", .desc = "[I/O] 3215" }, + {.name = "C70", .desc = "[I/O] 3270" }, + {.name = "TAP", .desc = "[I/O] Tape" }, + {.name = "VMR", .desc = "[I/O] Unit Record Devices" }, + {.name = "LCS", .desc = "[I/O] LCS" }, + {.name = "CLW", .desc = "[I/O] CLAW" }, + {.name = "CTC", .desc = "[I/O] CTC" }, + {.name = "APB", .desc = "[I/O] AP Bus" }, + {.name = "CSC", .desc = "[I/O] CHSC Subchannel" }, + {.name = "NMI", .desc = "[NMI] Machine Check" }, +}; + +/* + * show_interrupts is needed by /proc/interrupts. + */ +int show_interrupts(struct seq_file *p, void *v) +{ + int i = *(loff_t *) v, j; + + get_online_cpus(); + if (i == 0) { + seq_puts(p, " "); + for_each_online_cpu(j) + seq_printf(p, "CPU%d ",j); + seq_putc(p, '\n'); + } + + if (i < NR_IRQS) { + seq_printf(p, "%s: ", intrclass_names[i].name); +#ifndef CONFIG_SMP + seq_printf(p, "%10u ", kstat_irqs(i)); +#else + for_each_online_cpu(j) + seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]); +#endif + if (intrclass_names[i].desc) + seq_printf(p, " %s", intrclass_names[i].desc); + seq_putc(p, '\n'); + } + put_online_cpus(); + return 0; +} + +/* + * Switch to the asynchronous interrupt stack for softirq execution. + */ +asmlinkage void do_softirq(void) +{ + unsigned long flags, old, new; + + if (in_interrupt()) + return; + + local_irq_save(flags); + + if (local_softirq_pending()) { + /* Get current stack pointer. */ + asm volatile("la %0,0(15)" : "=a" (old)); + /* Check against async. stack address range. */ + new = S390_lowcore.async_stack; + if (((new - old) >> (PAGE_SHIFT + THREAD_ORDER)) != 0) { + /* Need to switch to the async. stack. */ + new -= STACK_FRAME_OVERHEAD; + ((struct stack_frame *) new)->back_chain = old; + + asm volatile(" la 15,0(%0)\n" + " basr 14,%2\n" + " la 15,0(%1)\n" + : : "a" (new), "a" (old), + "a" (__do_softirq) + : "0", "1", "2", "3", "4", "5", "14", + "cc", "memory" ); + } else { + /* We are already on the async stack. */ + __do_softirq(); + } + } + + local_irq_restore(flags); +} + +#ifdef CONFIG_PROC_FS +void init_irq_proc(void) +{ + struct proc_dir_entry *root_irq_dir; + + root_irq_dir = proc_mkdir("irq", NULL); + create_prof_cpu_mask(root_irq_dir); +} +#endif + +/* + * ext_int_hash[index] is the list head for all external interrupts that hash + * to this index. + */ +static struct list_head ext_int_hash[256]; + +struct ext_int_info { + ext_int_handler_t handler; + u16 code; + struct list_head entry; + struct rcu_head rcu; +}; + +/* ext_int_hash_lock protects the handler lists for external interrupts */ +DEFINE_SPINLOCK(ext_int_hash_lock); + +static void __init init_external_interrupts(void) +{ + int idx; + + for (idx = 0; idx < ARRAY_SIZE(ext_int_hash); idx++) + INIT_LIST_HEAD(&ext_int_hash[idx]); +} + +static inline int ext_hash(u16 code) +{ + return (code + (code >> 9)) & 0xff; +} + +int register_external_interrupt(u16 code, ext_int_handler_t handler) +{ + struct ext_int_info *p; + unsigned long flags; + int index; + + p = kmalloc(sizeof(*p), GFP_ATOMIC); + if (!p) + return -ENOMEM; + p->code = code; + p->handler = handler; + index = ext_hash(code); + + spin_lock_irqsave(&ext_int_hash_lock, flags); + list_add_rcu(&p->entry, &ext_int_hash[index]); + spin_unlock_irqrestore(&ext_int_hash_lock, flags); + return 0; +} +EXPORT_SYMBOL(register_external_interrupt); + +int unregister_external_interrupt(u16 code, ext_int_handler_t handler) +{ + struct ext_int_info *p; + unsigned long flags; + int index = ext_hash(code); + + spin_lock_irqsave(&ext_int_hash_lock, flags); + list_for_each_entry_rcu(p, &ext_int_hash[index], entry) { + if (p->code == code && p->handler == handler) { + list_del_rcu(&p->entry); + kfree_rcu(p, rcu); + } + } + spin_unlock_irqrestore(&ext_int_hash_lock, flags); + return 0; +} +EXPORT_SYMBOL(unregister_external_interrupt); + +void __irq_entry do_extint(struct pt_regs *regs, struct ext_code ext_code, + unsigned int param32, unsigned long param64) +{ + struct pt_regs *old_regs; + struct ext_int_info *p; + int index; + + old_regs = set_irq_regs(regs); + irq_enter(); + if (S390_lowcore.int_clock >= S390_lowcore.clock_comparator) { + /* Serve timer interrupts first. */ + clock_comparator_work(); + } + kstat_cpu(smp_processor_id()).irqs[EXTERNAL_INTERRUPT]++; + if (ext_code.code != 0x1004) + __get_cpu_var(s390_idle).nohz_delay = 1; + + index = ext_hash(ext_code.code); + rcu_read_lock(); + list_for_each_entry_rcu(p, &ext_int_hash[index], entry) + if (likely(p->code == ext_code.code)) + p->handler(ext_code, param32, param64); + rcu_read_unlock(); + irq_exit(); + set_irq_regs(old_regs); +} + +void __init init_IRQ(void) +{ + init_external_interrupts(); +} + +static DEFINE_SPINLOCK(sc_irq_lock); +static int sc_irq_refcount; + +void service_subclass_irq_register(void) +{ + spin_lock(&sc_irq_lock); + if (!sc_irq_refcount) + ctl_set_bit(0, 9); + sc_irq_refcount++; + spin_unlock(&sc_irq_lock); +} +EXPORT_SYMBOL(service_subclass_irq_register); + +void service_subclass_irq_unregister(void) +{ + spin_lock(&sc_irq_lock); + sc_irq_refcount--; + if (!sc_irq_refcount) + ctl_clear_bit(0, 9); + spin_unlock(&sc_irq_lock); +} +EXPORT_SYMBOL(service_subclass_irq_unregister); + +static DEFINE_SPINLOCK(ma_subclass_lock); +static int ma_subclass_refcount; + +void measurement_alert_subclass_register(void) +{ + spin_lock(&ma_subclass_lock); + if (!ma_subclass_refcount) + ctl_set_bit(0, 5); + ma_subclass_refcount++; + spin_unlock(&ma_subclass_lock); +} +EXPORT_SYMBOL(measurement_alert_subclass_register); + +void measurement_alert_subclass_unregister(void) +{ + spin_lock(&ma_subclass_lock); + ma_subclass_refcount--; + if (!ma_subclass_refcount) + ctl_clear_bit(0, 5); + spin_unlock(&ma_subclass_lock); +} +EXPORT_SYMBOL(measurement_alert_subclass_unregister); diff --git a/arch/s390/kernel/jump_label.c b/arch/s390/kernel/jump_label.c new file mode 100644 index 00000000..b987ab2c --- /dev/null +++ b/arch/s390/kernel/jump_label.c @@ -0,0 +1,70 @@ +/* + * Jump label s390 support + * + * Copyright IBM Corp. 2011 + * Author(s): Jan Glauber <jang@linux.vnet.ibm.com> + */ +#include <linux/module.h> +#include <linux/uaccess.h> +#include <linux/stop_machine.h> +#include <linux/jump_label.h> +#include <asm/ipl.h> + +#ifdef HAVE_JUMP_LABEL + +struct insn { + u16 opcode; + s32 offset; +} __packed; + +struct insn_args { + struct jump_entry *entry; + enum jump_label_type type; +}; + +static void __jump_label_transform(struct jump_entry *entry, + enum jump_label_type type) +{ + struct insn insn; + int rc; + + if (type == JUMP_LABEL_ENABLE) { + /* brcl 15,offset */ + insn.opcode = 0xc0f4; + insn.offset = (entry->target - entry->code) >> 1; + } else { + /* brcl 0,0 */ + insn.opcode = 0xc004; + insn.offset = 0; + } + + rc = probe_kernel_write((void *)entry->code, &insn, JUMP_LABEL_NOP_SIZE); + WARN_ON_ONCE(rc < 0); +} + +static int __sm_arch_jump_label_transform(void *data) +{ + struct insn_args *args = data; + + __jump_label_transform(args->entry, args->type); + return 0; +} + +void arch_jump_label_transform(struct jump_entry *entry, + enum jump_label_type type) +{ + struct insn_args args; + + args.entry = entry; + args.type = type; + + stop_machine(__sm_arch_jump_label_transform, &args, NULL); +} + +void arch_jump_label_transform_static(struct jump_entry *entry, + enum jump_label_type type) +{ + __jump_label_transform(entry, type); +} + +#endif diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c new file mode 100644 index 00000000..64b761ae --- /dev/null +++ b/arch/s390/kernel/kprobes.c @@ -0,0 +1,671 @@ +/* + * Kernel Probes (KProbes) + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + * Copyright (C) IBM Corporation, 2002, 2006 + * + * s390 port, used ppc64 as template. Mike Grundy <grundym@us.ibm.com> + */ + +#include <linux/kprobes.h> +#include <linux/ptrace.h> +#include <linux/preempt.h> +#include <linux/stop_machine.h> +#include <linux/kdebug.h> +#include <linux/uaccess.h> +#include <asm/cacheflush.h> +#include <asm/sections.h> +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/hardirq.h> + +DEFINE_PER_CPU(struct kprobe *, current_kprobe); +DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk); + +struct kretprobe_blackpoint kretprobe_blacklist[] = { }; + +static int __kprobes is_prohibited_opcode(kprobe_opcode_t *insn) +{ + switch (insn[0] >> 8) { + case 0x0c: /* bassm */ + case 0x0b: /* bsm */ + case 0x83: /* diag */ + case 0x44: /* ex */ + case 0xac: /* stnsm */ + case 0xad: /* stosm */ + return -EINVAL; + } + switch (insn[0]) { + case 0x0101: /* pr */ + case 0xb25a: /* bsa */ + case 0xb240: /* bakr */ + case 0xb258: /* bsg */ + case 0xb218: /* pc */ + case 0xb228: /* pt */ + case 0xb98d: /* epsw */ + return -EINVAL; + } + return 0; +} + +static int __kprobes get_fixup_type(kprobe_opcode_t *insn) +{ + /* default fixup method */ + int fixup = FIXUP_PSW_NORMAL; + + switch (insn[0] >> 8) { + case 0x05: /* balr */ + case 0x0d: /* basr */ + fixup = FIXUP_RETURN_REGISTER; + /* if r2 = 0, no branch will be taken */ + if ((insn[0] & 0x0f) == 0) + fixup |= FIXUP_BRANCH_NOT_TAKEN; + break; + case 0x06: /* bctr */ + case 0x07: /* bcr */ + fixup = FIXUP_BRANCH_NOT_TAKEN; + break; + case 0x45: /* bal */ + case 0x4d: /* bas */ + fixup = FIXUP_RETURN_REGISTER; + break; + case 0x47: /* bc */ + case 0x46: /* bct */ + case 0x86: /* bxh */ + case 0x87: /* bxle */ + fixup = FIXUP_BRANCH_NOT_TAKEN; + break; + case 0x82: /* lpsw */ + fixup = FIXUP_NOT_REQUIRED; + break; + case 0xb2: /* lpswe */ + if ((insn[0] & 0xff) == 0xb2) + fixup = FIXUP_NOT_REQUIRED; + break; + case 0xa7: /* bras */ + if ((insn[0] & 0x0f) == 0x05) + fixup |= FIXUP_RETURN_REGISTER; + break; + case 0xc0: + if ((insn[0] & 0x0f) == 0x00 || /* larl */ + (insn[0] & 0x0f) == 0x05) /* brasl */ + fixup |= FIXUP_RETURN_REGISTER; + break; + case 0xeb: + if ((insn[2] & 0xff) == 0x44 || /* bxhg */ + (insn[2] & 0xff) == 0x45) /* bxleg */ + fixup = FIXUP_BRANCH_NOT_TAKEN; + break; + case 0xe3: /* bctg */ + if ((insn[2] & 0xff) == 0x46) + fixup = FIXUP_BRANCH_NOT_TAKEN; + break; + } + return fixup; +} + +int __kprobes arch_prepare_kprobe(struct kprobe *p) +{ + if ((unsigned long) p->addr & 0x01) + return -EINVAL; + + /* Make sure the probe isn't going on a difficult instruction */ + if (is_prohibited_opcode(p->addr)) + return -EINVAL; + + p->opcode = *p->addr; + memcpy(p->ainsn.insn, p->addr, ((p->opcode >> 14) + 3) & -2); + + return 0; +} + +struct ins_replace_args { + kprobe_opcode_t *ptr; + kprobe_opcode_t opcode; +}; + +static int __kprobes swap_instruction(void *aref) +{ + struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); + unsigned long status = kcb->kprobe_status; + struct ins_replace_args *args = aref; + + kcb->kprobe_status = KPROBE_SWAP_INST; + probe_kernel_write(args->ptr, &args->opcode, sizeof(args->opcode)); + kcb->kprobe_status = status; + return 0; +} + +void __kprobes arch_arm_kprobe(struct kprobe *p) +{ + struct ins_replace_args args; + + args.ptr = p->addr; + args.opcode = BREAKPOINT_INSTRUCTION; + stop_machine(swap_instruction, &args, NULL); +} + +void __kprobes arch_disarm_kprobe(struct kprobe *p) +{ + struct ins_replace_args args; + + args.ptr = p->addr; + args.opcode = p->opcode; + stop_machine(swap_instruction, &args, NULL); +} + +void __kprobes arch_remove_kprobe(struct kprobe *p) +{ +} + +static void __kprobes enable_singlestep(struct kprobe_ctlblk *kcb, + struct pt_regs *regs, + unsigned long ip) +{ + struct per_regs per_kprobe; + + /* Set up the PER control registers %cr9-%cr11 */ + per_kprobe.control = PER_EVENT_IFETCH; + per_kprobe.start = ip; + per_kprobe.end = ip; + + /* Save control regs and psw mask */ + __ctl_store(kcb->kprobe_saved_ctl, 9, 11); + kcb->kprobe_saved_imask = regs->psw.mask & + (PSW_MASK_PER | PSW_MASK_IO | PSW_MASK_EXT); + + /* Set PER control regs, turns on single step for the given address */ + __ctl_load(per_kprobe, 9, 11); + regs->psw.mask |= PSW_MASK_PER; + regs->psw.mask &= ~(PSW_MASK_IO | PSW_MASK_EXT); + regs->psw.addr = ip | PSW_ADDR_AMODE; +} + +static void __kprobes disable_singlestep(struct kprobe_ctlblk *kcb, + struct pt_regs *regs, + unsigned long ip) +{ + /* Restore control regs and psw mask, set new psw address */ + __ctl_load(kcb->kprobe_saved_ctl, 9, 11); + regs->psw.mask &= ~PSW_MASK_PER; + regs->psw.mask |= kcb->kprobe_saved_imask; + regs->psw.addr = ip | PSW_ADDR_AMODE; +} + +/* + * Activate a kprobe by storing its pointer to current_kprobe. The + * previous kprobe is stored in kcb->prev_kprobe. A stack of up to + * two kprobes can be active, see KPROBE_REENTER. + */ +static void __kprobes push_kprobe(struct kprobe_ctlblk *kcb, struct kprobe *p) +{ + kcb->prev_kprobe.kp = __get_cpu_var(current_kprobe); + kcb->prev_kprobe.status = kcb->kprobe_status; + __get_cpu_var(current_kprobe) = p; +} + +/* + * Deactivate a kprobe by backing up to the previous state. If the + * current state is KPROBE_REENTER prev_kprobe.kp will be non-NULL, + * for any other state prev_kprobe.kp will be NULL. + */ +static void __kprobes pop_kprobe(struct kprobe_ctlblk *kcb) +{ + __get_cpu_var(current_kprobe) = kcb->prev_kprobe.kp; + kcb->kprobe_status = kcb->prev_kprobe.status; +} + +void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri, + struct pt_regs *regs) +{ + ri->ret_addr = (kprobe_opcode_t *) regs->gprs[14]; + + /* Replace the return addr with trampoline addr */ + regs->gprs[14] = (unsigned long) &kretprobe_trampoline; +} + +static void __kprobes kprobe_reenter_check(struct kprobe_ctlblk *kcb, + struct kprobe *p) +{ + switch (kcb->kprobe_status) { + case KPROBE_HIT_SSDONE: + case KPROBE_HIT_ACTIVE: + kprobes_inc_nmissed_count(p); + break; + case KPROBE_HIT_SS: + case KPROBE_REENTER: + default: + /* + * A kprobe on the code path to single step an instruction + * is a BUG. The code path resides in the .kprobes.text + * section and is executed with interrupts disabled. + */ + printk(KERN_EMERG "Invalid kprobe detected at %p.\n", p->addr); + dump_kprobe(p); + BUG(); + } +} + +static int __kprobes kprobe_handler(struct pt_regs *regs) +{ + struct kprobe_ctlblk *kcb; + struct kprobe *p; + + /* + * We want to disable preemption for the entire duration of kprobe + * processing. That includes the calls to the pre/post handlers + * and single stepping the kprobe instruction. + */ + preempt_disable(); + kcb = get_kprobe_ctlblk(); + p = get_kprobe((void *)((regs->psw.addr & PSW_ADDR_INSN) - 2)); + + if (p) { + if (kprobe_running()) { + /* + * We have hit a kprobe while another is still + * active. This can happen in the pre and post + * handler. Single step the instruction of the + * new probe but do not call any handler function + * of this secondary kprobe. + * push_kprobe and pop_kprobe saves and restores + * the currently active kprobe. + */ + kprobe_reenter_check(kcb, p); + push_kprobe(kcb, p); + kcb->kprobe_status = KPROBE_REENTER; + } else { + /* + * If we have no pre-handler or it returned 0, we + * continue with single stepping. If we have a + * pre-handler and it returned non-zero, it prepped + * for calling the break_handler below on re-entry + * for jprobe processing, so get out doing nothing + * more here. + */ + push_kprobe(kcb, p); + kcb->kprobe_status = KPROBE_HIT_ACTIVE; + if (p->pre_handler && p->pre_handler(p, regs)) + return 1; + kcb->kprobe_status = KPROBE_HIT_SS; + } + enable_singlestep(kcb, regs, (unsigned long) p->ainsn.insn); + return 1; + } else if (kprobe_running()) { + p = __get_cpu_var(current_kprobe); + if (p->break_handler && p->break_handler(p, regs)) { + /* + * Continuation after the jprobe completed and + * caused the jprobe_return trap. The jprobe + * break_handler "returns" to the original + * function that still has the kprobe breakpoint + * installed. We continue with single stepping. + */ + kcb->kprobe_status = KPROBE_HIT_SS; + enable_singlestep(kcb, regs, + (unsigned long) p->ainsn.insn); + return 1; + } /* else: + * No kprobe at this address and the current kprobe + * has no break handler (no jprobe!). The kernel just + * exploded, let the standard trap handler pick up the + * pieces. + */ + } /* else: + * No kprobe at this address and no active kprobe. The trap has + * not been caused by a kprobe breakpoint. The race of breakpoint + * vs. kprobe remove does not exist because on s390 as we use + * stop_machine to arm/disarm the breakpoints. + */ + preempt_enable_no_resched(); + return 0; +} + +/* + * Function return probe trampoline: + * - init_kprobes() establishes a probepoint here + * - When the probed function returns, this probe + * causes the handlers to fire + */ +static void __used kretprobe_trampoline_holder(void) +{ + asm volatile(".global kretprobe_trampoline\n" + "kretprobe_trampoline: bcr 0,0\n"); +} + +/* + * Called when the probe at kretprobe trampoline is hit + */ +static int __kprobes trampoline_probe_handler(struct kprobe *p, + struct pt_regs *regs) +{ + struct kretprobe_instance *ri; + struct hlist_head *head, empty_rp; + struct hlist_node *node, *tmp; + unsigned long flags, orig_ret_address; + unsigned long trampoline_address; + kprobe_opcode_t *correct_ret_addr; + + INIT_HLIST_HEAD(&empty_rp); + kretprobe_hash_lock(current, &head, &flags); + + /* + * It is possible to have multiple instances associated with a given + * task either because an multiple functions in the call path + * have a return probe installed on them, and/or more than one return + * return probe was registered for a target function. + * + * We can handle this because: + * - instances are always inserted at the head of the list + * - when multiple return probes are registered for the same + * function, the first instance's ret_addr will point to the + * real return address, and all the rest will point to + * kretprobe_trampoline + */ + ri = NULL; + orig_ret_address = 0; + correct_ret_addr = NULL; + trampoline_address = (unsigned long) &kretprobe_trampoline; + hlist_for_each_entry_safe(ri, node, tmp, head, hlist) { + if (ri->task != current) + /* another task is sharing our hash bucket */ + continue; + + orig_ret_address = (unsigned long) ri->ret_addr; + + if (orig_ret_address != trampoline_address) + /* + * This is the real return address. Any other + * instances associated with this task are for + * other calls deeper on the call stack + */ + break; + } + + kretprobe_assert(ri, orig_ret_address, trampoline_address); + + correct_ret_addr = ri->ret_addr; + hlist_for_each_entry_safe(ri, node, tmp, head, hlist) { + if (ri->task != current) + /* another task is sharing our hash bucket */ + continue; + + orig_ret_address = (unsigned long) ri->ret_addr; + + if (ri->rp && ri->rp->handler) { + ri->ret_addr = correct_ret_addr; + ri->rp->handler(ri, regs); + } + + recycle_rp_inst(ri, &empty_rp); + + if (orig_ret_address != trampoline_address) + /* + * This is the real return address. Any other + * instances associated with this task are for + * other calls deeper on the call stack + */ + break; + } + + regs->psw.addr = orig_ret_address | PSW_ADDR_AMODE; + + pop_kprobe(get_kprobe_ctlblk()); + kretprobe_hash_unlock(current, &flags); + preempt_enable_no_resched(); + + hlist_for_each_entry_safe(ri, node, tmp, &empty_rp, hlist) { + hlist_del(&ri->hlist); + kfree(ri); + } + /* + * By returning a non-zero value, we are telling + * kprobe_handler() that we don't want the post_handler + * to run (and have re-enabled preemption) + */ + return 1; +} + +/* + * Called after single-stepping. p->addr is the address of the + * instruction whose first byte has been replaced by the "breakpoint" + * instruction. To avoid the SMP problems that can occur when we + * temporarily put back the original opcode to single-step, we + * single-stepped a copy of the instruction. The address of this + * copy is p->ainsn.insn. + */ +static void __kprobes resume_execution(struct kprobe *p, struct pt_regs *regs) +{ + struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); + unsigned long ip = regs->psw.addr & PSW_ADDR_INSN; + int fixup = get_fixup_type(p->ainsn.insn); + + if (fixup & FIXUP_PSW_NORMAL) + ip += (unsigned long) p->addr - (unsigned long) p->ainsn.insn; + + if (fixup & FIXUP_BRANCH_NOT_TAKEN) { + int ilen = ((p->ainsn.insn[0] >> 14) + 3) & -2; + if (ip - (unsigned long) p->ainsn.insn == ilen) + ip = (unsigned long) p->addr + ilen; + } + + if (fixup & FIXUP_RETURN_REGISTER) { + int reg = (p->ainsn.insn[0] & 0xf0) >> 4; + regs->gprs[reg] += (unsigned long) p->addr - + (unsigned long) p->ainsn.insn; + } + + disable_singlestep(kcb, regs, ip); +} + +static int __kprobes post_kprobe_handler(struct pt_regs *regs) +{ + struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); + struct kprobe *p = kprobe_running(); + + if (!p) + return 0; + + if (kcb->kprobe_status != KPROBE_REENTER && p->post_handler) { + kcb->kprobe_status = KPROBE_HIT_SSDONE; + p->post_handler(p, regs, 0); + } + + resume_execution(p, regs); + pop_kprobe(kcb); + preempt_enable_no_resched(); + + /* + * if somebody else is singlestepping across a probe point, psw mask + * will have PER set, in which case, continue the remaining processing + * of do_single_step, as if this is not a probe hit. + */ + if (regs->psw.mask & PSW_MASK_PER) + return 0; + + return 1; +} + +static int __kprobes kprobe_trap_handler(struct pt_regs *regs, int trapnr) +{ + struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); + struct kprobe *p = kprobe_running(); + const struct exception_table_entry *entry; + + switch(kcb->kprobe_status) { + case KPROBE_SWAP_INST: + /* We are here because the instruction replacement failed */ + return 0; + case KPROBE_HIT_SS: + case KPROBE_REENTER: + /* + * We are here because the instruction being single + * stepped caused a page fault. We reset the current + * kprobe and the nip points back to the probe address + * and allow the page fault handler to continue as a + * normal page fault. + */ + disable_singlestep(kcb, regs, (unsigned long) p->addr); + pop_kprobe(kcb); + preempt_enable_no_resched(); + break; + case KPROBE_HIT_ACTIVE: + case KPROBE_HIT_SSDONE: + /* + * We increment the nmissed count for accounting, + * we can also use npre/npostfault count for accouting + * these specific fault cases. + */ + kprobes_inc_nmissed_count(p); + + /* + * We come here because instructions in the pre/post + * handler caused the page_fault, this could happen + * if handler tries to access user space by + * copy_from_user(), get_user() etc. Let the + * user-specified handler try to fix it first. + */ + if (p->fault_handler && p->fault_handler(p, regs, trapnr)) + return 1; + + /* + * In case the user-specified fault handler returned + * zero, try to fix up. + */ + entry = search_exception_tables(regs->psw.addr & PSW_ADDR_INSN); + if (entry) { + regs->psw.addr = entry->fixup | PSW_ADDR_AMODE; + return 1; + } + + /* + * fixup_exception() could not handle it, + * Let do_page_fault() fix it. + */ + break; + default: + break; + } + return 0; +} + +int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr) +{ + int ret; + + if (regs->psw.mask & (PSW_MASK_IO | PSW_MASK_EXT)) + local_irq_disable(); + ret = kprobe_trap_handler(regs, trapnr); + if (regs->psw.mask & (PSW_MASK_IO | PSW_MASK_EXT)) + local_irq_restore(regs->psw.mask & ~PSW_MASK_PER); + return ret; +} + +/* + * Wrapper routine to for handling exceptions. + */ +int __kprobes kprobe_exceptions_notify(struct notifier_block *self, + unsigned long val, void *data) +{ + struct die_args *args = (struct die_args *) data; + struct pt_regs *regs = args->regs; + int ret = NOTIFY_DONE; + + if (regs->psw.mask & (PSW_MASK_IO | PSW_MASK_EXT)) + local_irq_disable(); + + switch (val) { + case DIE_BPT: + if (kprobe_handler(regs)) + ret = NOTIFY_STOP; + break; + case DIE_SSTEP: + if (post_kprobe_handler(regs)) + ret = NOTIFY_STOP; + break; + case DIE_TRAP: + if (!preemptible() && kprobe_running() && + kprobe_trap_handler(regs, args->trapnr)) + ret = NOTIFY_STOP; + break; + default: + break; + } + + if (regs->psw.mask & (PSW_MASK_IO | PSW_MASK_EXT)) + local_irq_restore(regs->psw.mask & ~PSW_MASK_PER); + + return ret; +} + +int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) +{ + struct jprobe *jp = container_of(p, struct jprobe, kp); + struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); + unsigned long stack; + + memcpy(&kcb->jprobe_saved_regs, regs, sizeof(struct pt_regs)); + + /* setup return addr to the jprobe handler routine */ + regs->psw.addr = (unsigned long) jp->entry | PSW_ADDR_AMODE; + regs->psw.mask &= ~(PSW_MASK_IO | PSW_MASK_EXT); + + /* r15 is the stack pointer */ + stack = (unsigned long) regs->gprs[15]; + + memcpy(kcb->jprobes_stack, (void *) stack, MIN_STACK_SIZE(stack)); + return 1; +} + +void __kprobes jprobe_return(void) +{ + asm volatile(".word 0x0002"); +} + +static void __used __kprobes jprobe_return_end(void) +{ + asm volatile("bcr 0,0"); +} + +int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) +{ + struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); + unsigned long stack; + + stack = (unsigned long) kcb->jprobe_saved_regs.gprs[15]; + + /* Put the regs back */ + memcpy(regs, &kcb->jprobe_saved_regs, sizeof(struct pt_regs)); + /* put the stack back */ + memcpy((void *) stack, kcb->jprobes_stack, MIN_STACK_SIZE(stack)); + preempt_enable_no_resched(); + return 1; +} + +static struct kprobe trampoline = { + .addr = (kprobe_opcode_t *) &kretprobe_trampoline, + .pre_handler = trampoline_probe_handler +}; + +int __init arch_init_kprobes(void) +{ + return register_kprobe(&trampoline); +} + +int __kprobes arch_trampoline_kprobe(struct kprobe *p) +{ + return p->addr == (kprobe_opcode_t *) &kretprobe_trampoline; +} diff --git a/arch/s390/kernel/lgr.c b/arch/s390/kernel/lgr.c new file mode 100644 index 00000000..87f080b1 --- /dev/null +++ b/arch/s390/kernel/lgr.c @@ -0,0 +1,200 @@ +/* + * Linux Guest Relocation (LGR) detection + * + * Copyright IBM Corp. 2012 + * Author(s): Michael Holzheu <holzheu@linux.vnet.ibm.com> + */ + +#include <linux/module.h> +#include <linux/timer.h> +#include <linux/slab.h> +#include <asm/facility.h> +#include <asm/sysinfo.h> +#include <asm/ebcdic.h> +#include <asm/debug.h> +#include <asm/ipl.h> + +#define LGR_TIMER_INTERVAL_SECS (30 * 60) +#define VM_LEVEL_MAX 2 /* Maximum is 8, but we only record two levels */ + +/* + * LGR info: Contains stfle and stsi data + */ +struct lgr_info { + /* Bit field with facility information: 4 DWORDs are stored */ + u64 stfle_fac_list[4]; + /* Level of system (1 = CEC, 2 = LPAR, 3 = z/VM */ + u32 level; + /* Level 1: CEC info (stsi 1.1.1) */ + char manufacturer[16]; + char type[4]; + char sequence[16]; + char plant[4]; + char model[16]; + /* Level 2: LPAR info (stsi 2.2.2) */ + u16 lpar_number; + char name[8]; + /* Level 3: VM info (stsi 3.2.2) */ + u8 vm_count; + struct { + char name[8]; + char cpi[16]; + } vm[VM_LEVEL_MAX]; +} __packed __aligned(8); + +/* + * LGR globals + */ +static void *lgr_page; +static struct lgr_info lgr_info_last; +static struct lgr_info lgr_info_cur; +static struct debug_info *lgr_dbf; + +/* + * Return number of valid stsi levels + */ +static inline int stsi_0(void) +{ + int rc = stsi(NULL, 0, 0, 0); + + return rc == -ENOSYS ? rc : (((unsigned int) rc) >> 28); +} + +/* + * Copy buffer and then convert it to ASCII + */ +static void cpascii(char *dst, char *src, int size) +{ + memcpy(dst, src, size); + EBCASC(dst, size); +} + +/* + * Fill LGR info with 1.1.1 stsi data + */ +static void lgr_stsi_1_1_1(struct lgr_info *lgr_info) +{ + struct sysinfo_1_1_1 *si = lgr_page; + + if (stsi(si, 1, 1, 1) == -ENOSYS) + return; + cpascii(lgr_info->manufacturer, si->manufacturer, + sizeof(si->manufacturer)); + cpascii(lgr_info->type, si->type, sizeof(si->type)); + cpascii(lgr_info->model, si->model, sizeof(si->model)); + cpascii(lgr_info->sequence, si->sequence, sizeof(si->sequence)); + cpascii(lgr_info->plant, si->plant, sizeof(si->plant)); +} + +/* + * Fill LGR info with 2.2.2 stsi data + */ +static void lgr_stsi_2_2_2(struct lgr_info *lgr_info) +{ + struct sysinfo_2_2_2 *si = lgr_page; + + if (stsi(si, 2, 2, 2) == -ENOSYS) + return; + cpascii(lgr_info->name, si->name, sizeof(si->name)); + memcpy(&lgr_info->lpar_number, &si->lpar_number, + sizeof(lgr_info->lpar_number)); +} + +/* + * Fill LGR info with 3.2.2 stsi data + */ +static void lgr_stsi_3_2_2(struct lgr_info *lgr_info) +{ + struct sysinfo_3_2_2 *si = lgr_page; + int i; + + if (stsi(si, 3, 2, 2) == -ENOSYS) + return; + for (i = 0; i < min_t(u8, si->count, VM_LEVEL_MAX); i++) { + cpascii(lgr_info->vm[i].name, si->vm[i].name, + sizeof(si->vm[i].name)); + cpascii(lgr_info->vm[i].cpi, si->vm[i].cpi, + sizeof(si->vm[i].cpi)); + } + lgr_info->vm_count = si->count; +} + +/* + * Fill LGR info with current data + */ +static void lgr_info_get(struct lgr_info *lgr_info) +{ + memset(lgr_info, 0, sizeof(*lgr_info)); + stfle(lgr_info->stfle_fac_list, ARRAY_SIZE(lgr_info->stfle_fac_list)); + lgr_info->level = stsi_0(); + if (lgr_info->level == -ENOSYS) + return; + if (lgr_info->level >= 1) + lgr_stsi_1_1_1(lgr_info); + if (lgr_info->level >= 2) + lgr_stsi_2_2_2(lgr_info); + if (lgr_info->level >= 3) + lgr_stsi_3_2_2(lgr_info); +} + +/* + * Check if LGR info has changed and if yes log new LGR info to s390dbf + */ +void lgr_info_log(void) +{ + static DEFINE_SPINLOCK(lgr_info_lock); + unsigned long flags; + + if (!spin_trylock_irqsave(&lgr_info_lock, flags)) + return; + lgr_info_get(&lgr_info_cur); + if (memcmp(&lgr_info_last, &lgr_info_cur, sizeof(lgr_info_cur)) != 0) { + debug_event(lgr_dbf, 1, &lgr_info_cur, sizeof(lgr_info_cur)); + lgr_info_last = lgr_info_cur; + } + spin_unlock_irqrestore(&lgr_info_lock, flags); +} +EXPORT_SYMBOL_GPL(lgr_info_log); + +static void lgr_timer_set(void); + +/* + * LGR timer callback + */ +static void lgr_timer_fn(unsigned long ignored) +{ + lgr_info_log(); + lgr_timer_set(); +} + +static struct timer_list lgr_timer = + TIMER_DEFERRED_INITIALIZER(lgr_timer_fn, 0, 0); + +/* + * Setup next LGR timer + */ +static void lgr_timer_set(void) +{ + mod_timer(&lgr_timer, jiffies + LGR_TIMER_INTERVAL_SECS * HZ); +} + +/* + * Initialize LGR: Add s390dbf, write initial lgr_info and setup timer + */ +static int __init lgr_init(void) +{ + lgr_page = (void *) __get_free_pages(GFP_KERNEL, 0); + if (!lgr_page) + return -ENOMEM; + lgr_dbf = debug_register("lgr", 1, 1, sizeof(struct lgr_info)); + if (!lgr_dbf) { + free_page((unsigned long) lgr_page); + return -ENOMEM; + } + debug_register_view(lgr_dbf, &debug_hex_ascii_view); + lgr_info_get(&lgr_info_last); + debug_event(lgr_dbf, 1, &lgr_info_last, sizeof(lgr_info_last)); + lgr_timer_set(); + return 0; +} +module_init(lgr_init); diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c new file mode 100644 index 00000000..bdad47d5 --- /dev/null +++ b/arch/s390/kernel/machine_kexec.c @@ -0,0 +1,234 @@ +/* + * arch/s390/kernel/machine_kexec.c + * + * Copyright IBM Corp. 2005,2011 + * + * Author(s): Rolf Adelsberger, + * Heiko Carstens <heiko.carstens@de.ibm.com> + * Michael Holzheu <holzheu@linux.vnet.ibm.com> + */ + +#include <linux/device.h> +#include <linux/mm.h> +#include <linux/kexec.h> +#include <linux/delay.h> +#include <linux/reboot.h> +#include <linux/ftrace.h> +#include <linux/debug_locks.h> +#include <asm/cio.h> +#include <asm/setup.h> +#include <asm/pgtable.h> +#include <asm/pgalloc.h> +#include <asm/smp.h> +#include <asm/reset.h> +#include <asm/ipl.h> +#include <asm/diag.h> +#include <asm/asm-offsets.h> + +typedef void (*relocate_kernel_t)(kimage_entry_t *, unsigned long); + +extern const unsigned char relocate_kernel[]; +extern const unsigned long long relocate_kernel_len; + +#ifdef CONFIG_CRASH_DUMP + +void *fill_cpu_elf_notes(void *ptr, struct save_area *sa); + +/* + * Create ELF notes for one CPU + */ +static void add_elf_notes(int cpu) +{ + struct save_area *sa = (void *) 4608 + store_prefix(); + void *ptr; + + memcpy((void *) (4608UL + sa->pref_reg), sa, sizeof(*sa)); + ptr = (u64 *) per_cpu_ptr(crash_notes, cpu); + ptr = fill_cpu_elf_notes(ptr, sa); + memset(ptr, 0, sizeof(struct elf_note)); +} + +/* + * Initialize CPU ELF notes + */ +void setup_regs(void) +{ + unsigned long sa = S390_lowcore.prefixreg_save_area + SAVE_AREA_BASE; + int cpu, this_cpu; + + this_cpu = smp_find_processor_id(stap()); + add_elf_notes(this_cpu); + for_each_online_cpu(cpu) { + if (cpu == this_cpu) + continue; + if (smp_store_status(cpu)) + continue; + add_elf_notes(cpu); + } + /* Copy dump CPU store status info to absolute zero */ + memcpy((void *) SAVE_AREA_BASE, (void *) sa, sizeof(struct save_area)); +} + +#endif + +/* + * Start kdump: We expect here that a store status has been done on our CPU + */ +static void __do_machine_kdump(void *image) +{ +#ifdef CONFIG_CRASH_DUMP + int (*start_kdump)(int) = (void *)((struct kimage *) image)->start; + + __load_psw_mask(PSW_MASK_BASE | PSW_DEFAULT_KEY | PSW_MASK_EA | PSW_MASK_BA); + setup_regs(); + start_kdump(1); +#endif +} + +/* + * Check if kdump checksums are valid: We call purgatory with parameter "0" + */ +static int kdump_csum_valid(struct kimage *image) +{ +#ifdef CONFIG_CRASH_DUMP + int (*start_kdump)(int) = (void *)image->start; + int rc; + + __arch_local_irq_stnsm(0xfb); /* disable DAT */ + rc = start_kdump(0); + __arch_local_irq_stosm(0x04); /* enable DAT */ + return rc ? 0 : -EINVAL; +#else + return -EINVAL; +#endif +} + +/* + * Map or unmap crashkernel memory + */ +static void crash_map_pages(int enable) +{ + unsigned long size = resource_size(&crashk_res); + + BUG_ON(crashk_res.start % KEXEC_CRASH_MEM_ALIGN || + size % KEXEC_CRASH_MEM_ALIGN); + if (enable) + vmem_add_mapping(crashk_res.start, size); + else + vmem_remove_mapping(crashk_res.start, size); +} + +/* + * Map crashkernel memory + */ +void crash_map_reserved_pages(void) +{ + crash_map_pages(1); +} + +/* + * Unmap crashkernel memory + */ +void crash_unmap_reserved_pages(void) +{ + crash_map_pages(0); +} + +/* + * Give back memory to hypervisor before new kdump is loaded + */ +static int machine_kexec_prepare_kdump(void) +{ +#ifdef CONFIG_CRASH_DUMP + if (MACHINE_IS_VM) + diag10_range(PFN_DOWN(crashk_res.start), + PFN_DOWN(crashk_res.end - crashk_res.start + 1)); + return 0; +#else + return -EINVAL; +#endif +} + +int machine_kexec_prepare(struct kimage *image) +{ + void *reboot_code_buffer; + + /* Can't replace kernel image since it is read-only. */ + if (ipl_flags & IPL_NSS_VALID) + return -ENOSYS; + + if (image->type == KEXEC_TYPE_CRASH) + return machine_kexec_prepare_kdump(); + + /* We don't support anything but the default image type for now. */ + if (image->type != KEXEC_TYPE_DEFAULT) + return -EINVAL; + + /* Get the destination where the assembler code should be copied to.*/ + reboot_code_buffer = (void *) page_to_phys(image->control_code_page); + + /* Then copy it */ + memcpy(reboot_code_buffer, relocate_kernel, relocate_kernel_len); + return 0; +} + +void machine_kexec_cleanup(struct kimage *image) +{ +} + +void arch_crash_save_vmcoreinfo(void) +{ + VMCOREINFO_SYMBOL(lowcore_ptr); + VMCOREINFO_SYMBOL(high_memory); + VMCOREINFO_LENGTH(lowcore_ptr, NR_CPUS); +} + +void machine_shutdown(void) +{ +} + +/* + * Do normal kexec + */ +static void __do_machine_kexec(void *data) +{ + relocate_kernel_t data_mover; + struct kimage *image = data; + + data_mover = (relocate_kernel_t) page_to_phys(image->control_code_page); + + /* Call the moving routine */ + (*data_mover)(&image->head, image->start); +} + +/* + * Reset system and call either kdump or normal kexec + */ +static void __machine_kexec(void *data) +{ + struct kimage *image = data; + + pfault_fini(); + tracing_off(); + debug_locks_off(); + if (image->type == KEXEC_TYPE_CRASH) { + lgr_info_log(); + s390_reset_system(__do_machine_kdump, data); + } else { + s390_reset_system(__do_machine_kexec, data); + } + disabled_wait((unsigned long) __builtin_return_address(0)); +} + +/* + * Do either kdump or normal kexec. In case of kdump we first ask + * purgatory, if kdump checksums are valid. + */ +void machine_kexec(struct kimage *image) +{ + if (image->type == KEXEC_TYPE_CRASH && !kdump_csum_valid(image)) + return; + tracer_disable(); + smp_send_stop(); + smp_call_ipl_cpu(__machine_kexec, image); +} diff --git a/arch/s390/kernel/mcount.S b/arch/s390/kernel/mcount.S new file mode 100644 index 00000000..7e2c38ba --- /dev/null +++ b/arch/s390/kernel/mcount.S @@ -0,0 +1,71 @@ +/* + * Copyright IBM Corp. 2008,2009 + * + * Author(s): Heiko Carstens <heiko.carstens@de.ibm.com>, + * + */ + +#include <linux/linkage.h> +#include <asm/asm-offsets.h> + + .section .kprobes.text, "ax" + +ENTRY(ftrace_stub) + br %r14 + +ENTRY(_mcount) +#ifdef CONFIG_DYNAMIC_FTRACE + br %r14 + +ENTRY(ftrace_caller) +#endif + stm %r2,%r5,16(%r15) + bras %r1,2f +0: .long ftrace_trace_function +1: .long function_trace_stop +2: l %r2,1b-0b(%r1) + icm %r2,0xf,0(%r2) + jnz 3f + st %r14,56(%r15) + lr %r0,%r15 + ahi %r15,-96 + l %r3,100(%r15) + la %r2,0(%r14) + st %r0,__SF_BACKCHAIN(%r15) + la %r3,0(%r3) + l %r14,0b-0b(%r1) + l %r14,0(%r14) + basr %r14,%r14 +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + l %r2,100(%r15) + l %r3,152(%r15) +ENTRY(ftrace_graph_caller) +# The bras instruction gets runtime patched to call prepare_ftrace_return. +# See ftrace_enable_ftrace_graph_caller. The patched instruction is: +# bras %r14,prepare_ftrace_return + bras %r14,0f +0: st %r2,100(%r15) +#endif + ahi %r15,96 + l %r14,56(%r15) +3: lm %r2,%r5,16(%r15) + br %r14 + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + +ENTRY(return_to_handler) + stm %r2,%r5,16(%r15) + st %r14,56(%r15) + lr %r0,%r15 + ahi %r15,-96 + st %r0,__SF_BACKCHAIN(%r15) + bras %r1,0f + .long ftrace_return_to_handler +0: l %r2,0b-0b(%r1) + basr %r14,%r2 + lr %r14,%r2 + ahi %r15,96 + lm %r2,%r5,16(%r15) + br %r14 + +#endif diff --git a/arch/s390/kernel/mcount64.S b/arch/s390/kernel/mcount64.S new file mode 100644 index 00000000..f70cadec --- /dev/null +++ b/arch/s390/kernel/mcount64.S @@ -0,0 +1,63 @@ +/* + * Copyright IBM Corp. 2008,2009 + * + * Author(s): Heiko Carstens <heiko.carstens@de.ibm.com>, + * + */ + +#include <linux/linkage.h> +#include <asm/asm-offsets.h> + + .section .kprobes.text, "ax" + +ENTRY(ftrace_stub) + br %r14 + +ENTRY(_mcount) +#ifdef CONFIG_DYNAMIC_FTRACE + br %r14 + +ENTRY(ftrace_caller) +#endif + larl %r1,function_trace_stop + icm %r1,0xf,0(%r1) + bnzr %r14 + stmg %r2,%r5,32(%r15) + stg %r14,112(%r15) + lgr %r1,%r15 + aghi %r15,-160 + stg %r1,__SF_BACKCHAIN(%r15) + lgr %r2,%r14 + lg %r3,168(%r15) + larl %r14,ftrace_trace_function + lg %r14,0(%r14) + basr %r14,%r14 +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + lg %r2,168(%r15) + lg %r3,272(%r15) +ENTRY(ftrace_graph_caller) +# The bras instruction gets runtime patched to call prepare_ftrace_return. +# See ftrace_enable_ftrace_graph_caller. The patched instruction is: +# bras %r14,prepare_ftrace_return + bras %r14,0f +0: stg %r2,168(%r15) +#endif + aghi %r15,160 + lmg %r2,%r5,32(%r15) + lg %r14,112(%r15) + br %r14 + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + +ENTRY(return_to_handler) + stmg %r2,%r5,32(%r15) + lgr %r1,%r15 + aghi %r15,-160 + stg %r1,__SF_BACKCHAIN(%r15) + brasl %r14,ftrace_return_to_handler + aghi %r15,160 + lgr %r14,%r2 + lmg %r2,%r5,32(%r15) + br %r14 + +#endif diff --git a/arch/s390/kernel/mem_detect.c b/arch/s390/kernel/mem_detect.c new file mode 100644 index 00000000..22d502e8 --- /dev/null +++ b/arch/s390/kernel/mem_detect.c @@ -0,0 +1,145 @@ +/* + * Copyright IBM Corp. 2008, 2009 + * + * Author(s): Heiko Carstens <heiko.carstens@de.ibm.com> + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <asm/ipl.h> +#include <asm/sclp.h> +#include <asm/setup.h> + +#define ADDR2G (1ULL << 31) + +static void find_memory_chunks(struct mem_chunk chunk[]) +{ + unsigned long long memsize, rnmax, rzm; + unsigned long addr = 0, size; + int i = 0, type; + + rzm = sclp_get_rzm(); + rnmax = sclp_get_rnmax(); + memsize = rzm * rnmax; + if (!rzm) + rzm = 1ULL << 17; + if (sizeof(long) == 4) { + rzm = min(ADDR2G, rzm); + memsize = memsize ? min(ADDR2G, memsize) : ADDR2G; + } + do { + size = 0; + type = tprot(addr); + do { + size += rzm; + if (memsize && addr + size >= memsize) + break; + } while (type == tprot(addr + size)); + if (type == CHUNK_READ_WRITE || type == CHUNK_READ_ONLY) { + chunk[i].addr = addr; + chunk[i].size = size; + chunk[i].type = type; + i++; + } + addr += size; + } while (addr < memsize && i < MEMORY_CHUNKS); +} + +void detect_memory_layout(struct mem_chunk chunk[]) +{ + unsigned long flags, cr0; + + memset(chunk, 0, MEMORY_CHUNKS * sizeof(struct mem_chunk)); + /* Disable IRQs, DAT and low address protection so tprot does the + * right thing and we don't get scheduled away with low address + * protection disabled. + */ + flags = __arch_local_irq_stnsm(0xf8); + __ctl_store(cr0, 0, 0); + __ctl_clear_bit(0, 28); + find_memory_chunks(chunk); + __ctl_load(cr0, 0, 0); + arch_local_irq_restore(flags); +} +EXPORT_SYMBOL(detect_memory_layout); + +/* + * Move memory chunks array from index "from" to index "to" + */ +static void mem_chunk_move(struct mem_chunk chunk[], int to, int from) +{ + int cnt = MEMORY_CHUNKS - to; + + memmove(&chunk[to], &chunk[from], cnt * sizeof(struct mem_chunk)); +} + +/* + * Initialize memory chunk + */ +static void mem_chunk_init(struct mem_chunk *chunk, unsigned long addr, + unsigned long size, int type) +{ + chunk->type = type; + chunk->addr = addr; + chunk->size = size; +} + +/* + * Create memory hole with given address, size, and type + */ +void create_mem_hole(struct mem_chunk chunk[], unsigned long addr, + unsigned long size, int type) +{ + unsigned long lh_start, lh_end, lh_size, ch_start, ch_end, ch_size; + int i, ch_type; + + for (i = 0; i < MEMORY_CHUNKS; i++) { + if (chunk[i].size == 0) + continue; + + /* Define chunk properties */ + ch_start = chunk[i].addr; + ch_size = chunk[i].size; + ch_end = ch_start + ch_size - 1; + ch_type = chunk[i].type; + + /* Is memory chunk hit by memory hole? */ + if (addr + size <= ch_start) + continue; /* No: memory hole in front of chunk */ + if (addr > ch_end) + continue; /* No: memory hole after chunk */ + + /* Yes: Define local hole properties */ + lh_start = max(addr, chunk[i].addr); + lh_end = min(addr + size - 1, ch_end); + lh_size = lh_end - lh_start + 1; + + if (lh_start == ch_start && lh_end == ch_end) { + /* Hole covers complete memory chunk */ + mem_chunk_init(&chunk[i], lh_start, lh_size, type); + } else if (lh_end == ch_end) { + /* Hole starts in memory chunk and convers chunk end */ + mem_chunk_move(chunk, i + 1, i); + mem_chunk_init(&chunk[i], ch_start, ch_size - lh_size, + ch_type); + mem_chunk_init(&chunk[i + 1], lh_start, lh_size, type); + i += 1; + } else if (lh_start == ch_start) { + /* Hole ends in memory chunk */ + mem_chunk_move(chunk, i + 1, i); + mem_chunk_init(&chunk[i], lh_start, lh_size, type); + mem_chunk_init(&chunk[i + 1], lh_end + 1, + ch_size - lh_size, ch_type); + break; + } else { + /* Hole splits memory chunk */ + mem_chunk_move(chunk, i + 2, i); + mem_chunk_init(&chunk[i], ch_start, + lh_start - ch_start, ch_type); + mem_chunk_init(&chunk[i + 1], lh_start, lh_size, type); + mem_chunk_init(&chunk[i + 2], lh_end + 1, + ch_end - lh_end, ch_type); + break; + } + } +} diff --git a/arch/s390/kernel/module.c b/arch/s390/kernel/module.c new file mode 100644 index 00000000..dfcb3436 --- /dev/null +++ b/arch/s390/kernel/module.c @@ -0,0 +1,395 @@ +/* + * arch/s390/kernel/module.c - Kernel module help for s390. + * + * S390 version + * Copyright (C) 2002, 2003 IBM Deutschland Entwicklung GmbH, + * IBM Corporation + * Author(s): Arnd Bergmann (arndb@de.ibm.com) + * Martin Schwidefsky (schwidefsky@de.ibm.com) + * + * based on i386 version + * Copyright (C) 2001 Rusty Russell. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ +#include <linux/module.h> +#include <linux/elf.h> +#include <linux/vmalloc.h> +#include <linux/fs.h> +#include <linux/string.h> +#include <linux/kernel.h> +#include <linux/moduleloader.h> +#include <linux/bug.h> + +#if 0 +#define DEBUGP printk +#else +#define DEBUGP(fmt , ...) +#endif + +#ifndef CONFIG_64BIT +#define PLT_ENTRY_SIZE 12 +#else /* CONFIG_64BIT */ +#define PLT_ENTRY_SIZE 20 +#endif /* CONFIG_64BIT */ + +/* Free memory returned from module_alloc */ +void module_free(struct module *mod, void *module_region) +{ + if (mod) { + vfree(mod->arch.syminfo); + mod->arch.syminfo = NULL; + } + vfree(module_region); +} + +static void +check_rela(Elf_Rela *rela, struct module *me) +{ + struct mod_arch_syminfo *info; + + info = me->arch.syminfo + ELF_R_SYM (rela->r_info); + switch (ELF_R_TYPE (rela->r_info)) { + case R_390_GOT12: /* 12 bit GOT offset. */ + case R_390_GOT16: /* 16 bit GOT offset. */ + case R_390_GOT20: /* 20 bit GOT offset. */ + case R_390_GOT32: /* 32 bit GOT offset. */ + case R_390_GOT64: /* 64 bit GOT offset. */ + case R_390_GOTENT: /* 32 bit PC rel. to GOT entry shifted by 1. */ + case R_390_GOTPLT12: /* 12 bit offset to jump slot. */ + case R_390_GOTPLT16: /* 16 bit offset to jump slot. */ + case R_390_GOTPLT20: /* 20 bit offset to jump slot. */ + case R_390_GOTPLT32: /* 32 bit offset to jump slot. */ + case R_390_GOTPLT64: /* 64 bit offset to jump slot. */ + case R_390_GOTPLTENT: /* 32 bit rel. offset to jump slot >> 1. */ + if (info->got_offset == -1UL) { + info->got_offset = me->arch.got_size; + me->arch.got_size += sizeof(void*); + } + break; + case R_390_PLT16DBL: /* 16 bit PC rel. PLT shifted by 1. */ + case R_390_PLT32DBL: /* 32 bit PC rel. PLT shifted by 1. */ + case R_390_PLT32: /* 32 bit PC relative PLT address. */ + case R_390_PLT64: /* 64 bit PC relative PLT address. */ + case R_390_PLTOFF16: /* 16 bit offset from GOT to PLT. */ + case R_390_PLTOFF32: /* 32 bit offset from GOT to PLT. */ + case R_390_PLTOFF64: /* 16 bit offset from GOT to PLT. */ + if (info->plt_offset == -1UL) { + info->plt_offset = me->arch.plt_size; + me->arch.plt_size += PLT_ENTRY_SIZE; + } + break; + case R_390_COPY: + case R_390_GLOB_DAT: + case R_390_JMP_SLOT: + case R_390_RELATIVE: + /* Only needed if we want to support loading of + modules linked with -shared. */ + break; + } +} + +/* + * Account for GOT and PLT relocations. We can't add sections for + * got and plt but we can increase the core module size. + */ +int +module_frob_arch_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs, + char *secstrings, struct module *me) +{ + Elf_Shdr *symtab; + Elf_Sym *symbols; + Elf_Rela *rela; + char *strings; + int nrela, i, j; + + /* Find symbol table and string table. */ + symtab = NULL; + for (i = 0; i < hdr->e_shnum; i++) + switch (sechdrs[i].sh_type) { + case SHT_SYMTAB: + symtab = sechdrs + i; + break; + } + if (!symtab) { + printk(KERN_ERR "module %s: no symbol table\n", me->name); + return -ENOEXEC; + } + + /* Allocate one syminfo structure per symbol. */ + me->arch.nsyms = symtab->sh_size / sizeof(Elf_Sym); + me->arch.syminfo = vmalloc(me->arch.nsyms * + sizeof(struct mod_arch_syminfo)); + if (!me->arch.syminfo) + return -ENOMEM; + symbols = (void *) hdr + symtab->sh_offset; + strings = (void *) hdr + sechdrs[symtab->sh_link].sh_offset; + for (i = 0; i < me->arch.nsyms; i++) { + if (symbols[i].st_shndx == SHN_UNDEF && + strcmp(strings + symbols[i].st_name, + "_GLOBAL_OFFSET_TABLE_") == 0) + /* "Define" it as absolute. */ + symbols[i].st_shndx = SHN_ABS; + me->arch.syminfo[i].got_offset = -1UL; + me->arch.syminfo[i].plt_offset = -1UL; + me->arch.syminfo[i].got_initialized = 0; + me->arch.syminfo[i].plt_initialized = 0; + } + + /* Search for got/plt relocations. */ + me->arch.got_size = me->arch.plt_size = 0; + for (i = 0; i < hdr->e_shnum; i++) { + if (sechdrs[i].sh_type != SHT_RELA) + continue; + nrela = sechdrs[i].sh_size / sizeof(Elf_Rela); + rela = (void *) hdr + sechdrs[i].sh_offset; + for (j = 0; j < nrela; j++) + check_rela(rela + j, me); + } + + /* Increase core size by size of got & plt and set start + offsets for got and plt. */ + me->core_size = ALIGN(me->core_size, 4); + me->arch.got_offset = me->core_size; + me->core_size += me->arch.got_size; + me->arch.plt_offset = me->core_size; + me->core_size += me->arch.plt_size; + return 0; +} + +static int +apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab, + struct module *me) +{ + struct mod_arch_syminfo *info; + Elf_Addr loc, val; + int r_type, r_sym; + + /* This is where to make the change */ + loc = base + rela->r_offset; + /* This is the symbol it is referring to. Note that all + undefined symbols have been resolved. */ + r_sym = ELF_R_SYM(rela->r_info); + r_type = ELF_R_TYPE(rela->r_info); + info = me->arch.syminfo + r_sym; + val = symtab[r_sym].st_value; + + switch (r_type) { + case R_390_8: /* Direct 8 bit. */ + case R_390_12: /* Direct 12 bit. */ + case R_390_16: /* Direct 16 bit. */ + case R_390_20: /* Direct 20 bit. */ + case R_390_32: /* Direct 32 bit. */ + case R_390_64: /* Direct 64 bit. */ + val += rela->r_addend; + if (r_type == R_390_8) + *(unsigned char *) loc = val; + else if (r_type == R_390_12) + *(unsigned short *) loc = (val & 0xfff) | + (*(unsigned short *) loc & 0xf000); + else if (r_type == R_390_16) + *(unsigned short *) loc = val; + else if (r_type == R_390_20) + *(unsigned int *) loc = + (*(unsigned int *) loc & 0xf00000ff) | + (val & 0xfff) << 16 | (val & 0xff000) >> 4; + else if (r_type == R_390_32) + *(unsigned int *) loc = val; + else if (r_type == R_390_64) + *(unsigned long *) loc = val; + break; + case R_390_PC16: /* PC relative 16 bit. */ + case R_390_PC16DBL: /* PC relative 16 bit shifted by 1. */ + case R_390_PC32DBL: /* PC relative 32 bit shifted by 1. */ + case R_390_PC32: /* PC relative 32 bit. */ + case R_390_PC64: /* PC relative 64 bit. */ + val += rela->r_addend - loc; + if (r_type == R_390_PC16) + *(unsigned short *) loc = val; + else if (r_type == R_390_PC16DBL) + *(unsigned short *) loc = val >> 1; + else if (r_type == R_390_PC32DBL) + *(unsigned int *) loc = val >> 1; + else if (r_type == R_390_PC32) + *(unsigned int *) loc = val; + else if (r_type == R_390_PC64) + *(unsigned long *) loc = val; + break; + case R_390_GOT12: /* 12 bit GOT offset. */ + case R_390_GOT16: /* 16 bit GOT offset. */ + case R_390_GOT20: /* 20 bit GOT offset. */ + case R_390_GOT32: /* 32 bit GOT offset. */ + case R_390_GOT64: /* 64 bit GOT offset. */ + case R_390_GOTENT: /* 32 bit PC rel. to GOT entry shifted by 1. */ + case R_390_GOTPLT12: /* 12 bit offset to jump slot. */ + case R_390_GOTPLT20: /* 20 bit offset to jump slot. */ + case R_390_GOTPLT16: /* 16 bit offset to jump slot. */ + case R_390_GOTPLT32: /* 32 bit offset to jump slot. */ + case R_390_GOTPLT64: /* 64 bit offset to jump slot. */ + case R_390_GOTPLTENT: /* 32 bit rel. offset to jump slot >> 1. */ + if (info->got_initialized == 0) { + Elf_Addr *gotent; + + gotent = me->module_core + me->arch.got_offset + + info->got_offset; + *gotent = val; + info->got_initialized = 1; + } + val = info->got_offset + rela->r_addend; + if (r_type == R_390_GOT12 || + r_type == R_390_GOTPLT12) + *(unsigned short *) loc = (val & 0xfff) | + (*(unsigned short *) loc & 0xf000); + else if (r_type == R_390_GOT16 || + r_type == R_390_GOTPLT16) + *(unsigned short *) loc = val; + else if (r_type == R_390_GOT20 || + r_type == R_390_GOTPLT20) + *(unsigned int *) loc = + (*(unsigned int *) loc & 0xf00000ff) | + (val & 0xfff) << 16 | (val & 0xff000) >> 4; + else if (r_type == R_390_GOT32 || + r_type == R_390_GOTPLT32) + *(unsigned int *) loc = val; + else if (r_type == R_390_GOTENT || + r_type == R_390_GOTPLTENT) + *(unsigned int *) loc = + (val + (Elf_Addr) me->module_core - loc) >> 1; + else if (r_type == R_390_GOT64 || + r_type == R_390_GOTPLT64) + *(unsigned long *) loc = val; + break; + case R_390_PLT16DBL: /* 16 bit PC rel. PLT shifted by 1. */ + case R_390_PLT32DBL: /* 32 bit PC rel. PLT shifted by 1. */ + case R_390_PLT32: /* 32 bit PC relative PLT address. */ + case R_390_PLT64: /* 64 bit PC relative PLT address. */ + case R_390_PLTOFF16: /* 16 bit offset from GOT to PLT. */ + case R_390_PLTOFF32: /* 32 bit offset from GOT to PLT. */ + case R_390_PLTOFF64: /* 16 bit offset from GOT to PLT. */ + if (info->plt_initialized == 0) { + unsigned int *ip; + ip = me->module_core + me->arch.plt_offset + + info->plt_offset; +#ifndef CONFIG_64BIT + ip[0] = 0x0d105810; /* basr 1,0; l 1,6(1); br 1 */ + ip[1] = 0x100607f1; + ip[2] = val; +#else /* CONFIG_64BIT */ + ip[0] = 0x0d10e310; /* basr 1,0; lg 1,10(1); br 1 */ + ip[1] = 0x100a0004; + ip[2] = 0x07f10000; + ip[3] = (unsigned int) (val >> 32); + ip[4] = (unsigned int) val; +#endif /* CONFIG_64BIT */ + info->plt_initialized = 1; + } + if (r_type == R_390_PLTOFF16 || + r_type == R_390_PLTOFF32 || + r_type == R_390_PLTOFF64) + val = me->arch.plt_offset - me->arch.got_offset + + info->plt_offset + rela->r_addend; + else { + if (!((r_type == R_390_PLT16DBL && + val - loc + 0xffffUL < 0x1ffffeUL) || + (r_type == R_390_PLT32DBL && + val - loc + 0xffffffffULL < 0x1fffffffeULL))) + val = (Elf_Addr) me->module_core + + me->arch.plt_offset + + info->plt_offset; + val += rela->r_addend - loc; + } + if (r_type == R_390_PLT16DBL) + *(unsigned short *) loc = val >> 1; + else if (r_type == R_390_PLTOFF16) + *(unsigned short *) loc = val; + else if (r_type == R_390_PLT32DBL) + *(unsigned int *) loc = val >> 1; + else if (r_type == R_390_PLT32 || + r_type == R_390_PLTOFF32) + *(unsigned int *) loc = val; + else if (r_type == R_390_PLT64 || + r_type == R_390_PLTOFF64) + *(unsigned long *) loc = val; + break; + case R_390_GOTOFF16: /* 16 bit offset to GOT. */ + case R_390_GOTOFF32: /* 32 bit offset to GOT. */ + case R_390_GOTOFF64: /* 64 bit offset to GOT. */ + val = val + rela->r_addend - + ((Elf_Addr) me->module_core + me->arch.got_offset); + if (r_type == R_390_GOTOFF16) + *(unsigned short *) loc = val; + else if (r_type == R_390_GOTOFF32) + *(unsigned int *) loc = val; + else if (r_type == R_390_GOTOFF64) + *(unsigned long *) loc = val; + break; + case R_390_GOTPC: /* 32 bit PC relative offset to GOT. */ + case R_390_GOTPCDBL: /* 32 bit PC rel. off. to GOT shifted by 1. */ + val = (Elf_Addr) me->module_core + me->arch.got_offset + + rela->r_addend - loc; + if (r_type == R_390_GOTPC) + *(unsigned int *) loc = val; + else if (r_type == R_390_GOTPCDBL) + *(unsigned int *) loc = val >> 1; + break; + case R_390_COPY: + case R_390_GLOB_DAT: /* Create GOT entry. */ + case R_390_JMP_SLOT: /* Create PLT entry. */ + case R_390_RELATIVE: /* Adjust by program base. */ + /* Only needed if we want to support loading of + modules linked with -shared. */ + break; + default: + printk(KERN_ERR "module %s: Unknown relocation: %u\n", + me->name, r_type); + return -ENOEXEC; + } + return 0; +} + +int +apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab, + unsigned int symindex, unsigned int relsec, + struct module *me) +{ + Elf_Addr base; + Elf_Sym *symtab; + Elf_Rela *rela; + unsigned long i, n; + int rc; + + DEBUGP("Applying relocate section %u to %u\n", + relsec, sechdrs[relsec].sh_info); + base = sechdrs[sechdrs[relsec].sh_info].sh_addr; + symtab = (Elf_Sym *) sechdrs[symindex].sh_addr; + rela = (Elf_Rela *) sechdrs[relsec].sh_addr; + n = sechdrs[relsec].sh_size / sizeof(Elf_Rela); + + for (i = 0; i < n; i++, rela++) { + rc = apply_rela(rela, base, symtab, me); + if (rc) + return rc; + } + return 0; +} + +int module_finalize(const Elf_Ehdr *hdr, + const Elf_Shdr *sechdrs, + struct module *me) +{ + vfree(me->arch.syminfo); + me->arch.syminfo = NULL; + return 0; +} diff --git a/arch/s390/kernel/nmi.c b/arch/s390/kernel/nmi.c new file mode 100644 index 00000000..8c372ca6 --- /dev/null +++ b/arch/s390/kernel/nmi.c @@ -0,0 +1,375 @@ +/* + * Machine check handler + * + * Copyright IBM Corp. 2000,2009 + * Author(s): Ingo Adlung <adlung@de.ibm.com>, + * Martin Schwidefsky <schwidefsky@de.ibm.com>, + * Cornelia Huck <cornelia.huck@de.ibm.com>, + * Heiko Carstens <heiko.carstens@de.ibm.com>, + */ + +#include <linux/kernel_stat.h> +#include <linux/init.h> +#include <linux/errno.h> +#include <linux/hardirq.h> +#include <linux/time.h> +#include <linux/module.h> +#include <asm/lowcore.h> +#include <asm/smp.h> +#include <asm/etr.h> +#include <asm/cputime.h> +#include <asm/nmi.h> +#include <asm/crw.h> + +struct mcck_struct { + int kill_task; + int channel_report; + int warning; + unsigned long long mcck_code; +}; + +static DEFINE_PER_CPU(struct mcck_struct, cpu_mcck); + +static void s390_handle_damage(char *msg) +{ + smp_send_stop(); + disabled_wait((unsigned long) __builtin_return_address(0)); + while (1); +} + +/* + * Main machine check handler function. Will be called with interrupts enabled + * or disabled and machine checks enabled or disabled. + */ +void s390_handle_mcck(void) +{ + unsigned long flags; + struct mcck_struct mcck; + + /* + * Disable machine checks and get the current state of accumulated + * machine checks. Afterwards delete the old state and enable machine + * checks again. + */ + local_irq_save(flags); + local_mcck_disable(); + mcck = __get_cpu_var(cpu_mcck); + memset(&__get_cpu_var(cpu_mcck), 0, sizeof(struct mcck_struct)); + clear_thread_flag(TIF_MCCK_PENDING); + local_mcck_enable(); + local_irq_restore(flags); + + if (mcck.channel_report) + crw_handle_channel_report(); + /* + * A warning may remain for a prolonged period on the bare iron. + * (actually until the machine is powered off, or the problem is gone) + * So we just stop listening for the WARNING MCH and avoid continuously + * being interrupted. One caveat is however, that we must do this per + * processor and cannot use the smp version of ctl_clear_bit(). + * On VM we only get one interrupt per virtally presented machinecheck. + * Though one suffices, we may get one interrupt per (virtual) cpu. + */ + if (mcck.warning) { /* WARNING pending ? */ + static int mchchk_wng_posted = 0; + + /* Use single cpu clear, as we cannot handle smp here. */ + __ctl_clear_bit(14, 24); /* Disable WARNING MCH */ + if (xchg(&mchchk_wng_posted, 1) == 0) + kill_cad_pid(SIGPWR, 1); + } + if (mcck.kill_task) { + local_irq_enable(); + printk(KERN_EMERG "mcck: Terminating task because of machine " + "malfunction (code 0x%016llx).\n", mcck.mcck_code); + printk(KERN_EMERG "mcck: task: %s, pid: %d.\n", + current->comm, current->pid); + do_exit(SIGSEGV); + } +} +EXPORT_SYMBOL_GPL(s390_handle_mcck); + +/* + * returns 0 if all registers could be validated + * returns 1 otherwise + */ +static int notrace s390_revalidate_registers(struct mci *mci) +{ + int kill_task; + u64 zero; + void *fpt_save_area, *fpt_creg_save_area; + + kill_task = 0; + zero = 0; + + if (!mci->gr) { + /* + * General purpose registers couldn't be restored and have + * unknown contents. Process needs to be terminated. + */ + kill_task = 1; + } + if (!mci->fp) { + /* + * Floating point registers can't be restored and + * therefore the process needs to be terminated. + */ + kill_task = 1; + } +#ifndef CONFIG_64BIT + asm volatile( + " ld 0,0(%0)\n" + " ld 2,8(%0)\n" + " ld 4,16(%0)\n" + " ld 6,24(%0)" + : : "a" (&S390_lowcore.floating_pt_save_area)); +#endif + + if (MACHINE_HAS_IEEE) { +#ifdef CONFIG_64BIT + fpt_save_area = &S390_lowcore.floating_pt_save_area; + fpt_creg_save_area = &S390_lowcore.fpt_creg_save_area; +#else + fpt_save_area = (void *) S390_lowcore.extended_save_area_addr; + fpt_creg_save_area = fpt_save_area + 128; +#endif + if (!mci->fc) { + /* + * Floating point control register can't be restored. + * Task will be terminated. + */ + asm volatile("lfpc 0(%0)" : : "a" (&zero), "m" (zero)); + kill_task = 1; + + } else + asm volatile("lfpc 0(%0)" : : "a" (fpt_creg_save_area)); + + asm volatile( + " ld 0,0(%0)\n" + " ld 1,8(%0)\n" + " ld 2,16(%0)\n" + " ld 3,24(%0)\n" + " ld 4,32(%0)\n" + " ld 5,40(%0)\n" + " ld 6,48(%0)\n" + " ld 7,56(%0)\n" + " ld 8,64(%0)\n" + " ld 9,72(%0)\n" + " ld 10,80(%0)\n" + " ld 11,88(%0)\n" + " ld 12,96(%0)\n" + " ld 13,104(%0)\n" + " ld 14,112(%0)\n" + " ld 15,120(%0)\n" + : : "a" (fpt_save_area)); + } + /* Revalidate access registers */ + asm volatile( + " lam 0,15,0(%0)" + : : "a" (&S390_lowcore.access_regs_save_area)); + if (!mci->ar) { + /* + * Access registers have unknown contents. + * Terminating task. + */ + kill_task = 1; + } + /* Revalidate control registers */ + if (!mci->cr) { + /* + * Control registers have unknown contents. + * Can't recover and therefore stopping machine. + */ + s390_handle_damage("invalid control registers."); + } else { +#ifdef CONFIG_64BIT + asm volatile( + " lctlg 0,15,0(%0)" + : : "a" (&S390_lowcore.cregs_save_area)); +#else + asm volatile( + " lctl 0,15,0(%0)" + : : "a" (&S390_lowcore.cregs_save_area)); +#endif + } + /* + * We don't even try to revalidate the TOD register, since we simply + * can't write something sensible into that register. + */ +#ifdef CONFIG_64BIT + /* + * See if we can revalidate the TOD programmable register with its + * old contents (should be zero) otherwise set it to zero. + */ + if (!mci->pr) + asm volatile( + " sr 0,0\n" + " sckpf" + : : : "0", "cc"); + else + asm volatile( + " l 0,0(%0)\n" + " sckpf" + : : "a" (&S390_lowcore.tod_progreg_save_area) + : "0", "cc"); +#endif + /* Revalidate clock comparator register */ + if (S390_lowcore.clock_comparator == -1) + set_clock_comparator(S390_lowcore.mcck_clock); + else + set_clock_comparator(S390_lowcore.clock_comparator); + /* Check if old PSW is valid */ + if (!mci->wp) + /* + * Can't tell if we come from user or kernel mode + * -> stopping machine. + */ + s390_handle_damage("old psw invalid."); + + if (!mci->ms || !mci->pm || !mci->ia) + kill_task = 1; + + return kill_task; +} + +#define MAX_IPD_COUNT 29 +#define MAX_IPD_TIME (5 * 60 * USEC_PER_SEC) /* 5 minutes */ + +#define ED_STP_ISLAND 6 /* External damage STP island check */ +#define ED_STP_SYNC 7 /* External damage STP sync check */ +#define ED_ETR_SYNC 12 /* External damage ETR sync check */ +#define ED_ETR_SWITCH 13 /* External damage ETR switch to local */ + +/* + * machine check handler. + */ +void notrace s390_do_machine_check(struct pt_regs *regs) +{ + static int ipd_count; + static DEFINE_SPINLOCK(ipd_lock); + static unsigned long long last_ipd; + struct mcck_struct *mcck; + unsigned long long tmp; + struct mci *mci; + int umode; + + nmi_enter(); + kstat_cpu(smp_processor_id()).irqs[NMI_NMI]++; + mci = (struct mci *) &S390_lowcore.mcck_interruption_code; + mcck = &__get_cpu_var(cpu_mcck); + umode = user_mode(regs); + + if (mci->sd) { + /* System damage -> stopping machine */ + s390_handle_damage("received system damage machine check."); + } + if (mci->pd) { + if (mci->b) { + /* Processing backup -> verify if we can survive this */ + u64 z_mcic, o_mcic, t_mcic; +#ifdef CONFIG_64BIT + z_mcic = (1ULL<<63 | 1ULL<<59 | 1ULL<<29); + o_mcic = (1ULL<<43 | 1ULL<<42 | 1ULL<<41 | 1ULL<<40 | + 1ULL<<36 | 1ULL<<35 | 1ULL<<34 | 1ULL<<32 | + 1ULL<<30 | 1ULL<<21 | 1ULL<<20 | 1ULL<<17 | + 1ULL<<16); +#else + z_mcic = (1ULL<<63 | 1ULL<<59 | 1ULL<<57 | 1ULL<<50 | + 1ULL<<29); + o_mcic = (1ULL<<43 | 1ULL<<42 | 1ULL<<41 | 1ULL<<40 | + 1ULL<<36 | 1ULL<<35 | 1ULL<<34 | 1ULL<<32 | + 1ULL<<30 | 1ULL<<20 | 1ULL<<17 | 1ULL<<16); +#endif + t_mcic = *(u64 *)mci; + + if (((t_mcic & z_mcic) != 0) || + ((t_mcic & o_mcic) != o_mcic)) { + s390_handle_damage("processing backup machine " + "check with damage."); + } + + /* + * Nullifying exigent condition, therefore we might + * retry this instruction. + */ + spin_lock(&ipd_lock); + tmp = get_clock(); + if (((tmp - last_ipd) >> 12) < MAX_IPD_TIME) + ipd_count++; + else + ipd_count = 1; + last_ipd = tmp; + if (ipd_count == MAX_IPD_COUNT) + s390_handle_damage("too many ipd retries."); + spin_unlock(&ipd_lock); + } else { + /* Processing damage -> stopping machine */ + s390_handle_damage("received instruction processing " + "damage machine check."); + } + } + if (s390_revalidate_registers(mci)) { + if (umode) { + /* + * Couldn't restore all register contents while in + * user mode -> mark task for termination. + */ + mcck->kill_task = 1; + mcck->mcck_code = *(unsigned long long *) mci; + set_thread_flag(TIF_MCCK_PENDING); + } else { + /* + * Couldn't restore all register contents while in + * kernel mode -> stopping machine. + */ + s390_handle_damage("unable to revalidate registers."); + } + } + if (mci->cd) { + /* Timing facility damage */ + s390_handle_damage("TOD clock damaged"); + } + if (mci->ed && mci->ec) { + /* External damage */ + if (S390_lowcore.external_damage_code & (1U << ED_ETR_SYNC)) + etr_sync_check(); + if (S390_lowcore.external_damage_code & (1U << ED_ETR_SWITCH)) + etr_switch_to_local(); + if (S390_lowcore.external_damage_code & (1U << ED_STP_SYNC)) + stp_sync_check(); + if (S390_lowcore.external_damage_code & (1U << ED_STP_ISLAND)) + stp_island_check(); + } + if (mci->se) + /* Storage error uncorrected */ + s390_handle_damage("received storage error uncorrected " + "machine check."); + if (mci->ke) + /* Storage key-error uncorrected */ + s390_handle_damage("received storage key-error uncorrected " + "machine check."); + if (mci->ds && mci->fa) + /* Storage degradation */ + s390_handle_damage("received storage degradation machine " + "check."); + if (mci->cp) { + /* Channel report word pending */ + mcck->channel_report = 1; + set_thread_flag(TIF_MCCK_PENDING); + } + if (mci->w) { + /* Warning pending */ + mcck->warning = 1; + set_thread_flag(TIF_MCCK_PENDING); + } + nmi_exit(); +} + +static int __init machine_check_init(void) +{ + ctl_set_bit(14, 25); /* enable external damage MCH */ + ctl_set_bit(14, 27); /* enable system recovery MCH */ + ctl_set_bit(14, 24); /* enable warning MCH */ + return 0; +} +arch_initcall(machine_check_init); diff --git a/arch/s390/kernel/os_info.c b/arch/s390/kernel/os_info.c new file mode 100644 index 00000000..e8d6c214 --- /dev/null +++ b/arch/s390/kernel/os_info.c @@ -0,0 +1,168 @@ +/* + * OS info memory interface + * + * Copyright IBM Corp. 2012 + * Author(s): Michael Holzheu <holzheu@linux.vnet.ibm.com> + */ + +#define KMSG_COMPONENT "os_info" +#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt + +#include <linux/crash_dump.h> +#include <linux/kernel.h> +#include <asm/checksum.h> +#include <asm/lowcore.h> +#include <asm/os_info.h> + +/* + * OS info structure has to be page aligned + */ +static struct os_info os_info __page_aligned_data; + +/* + * Compute checksum over OS info structure + */ +u32 os_info_csum(struct os_info *os_info) +{ + int size = sizeof(*os_info) - offsetof(struct os_info, version_major); + return csum_partial(&os_info->version_major, size, 0); +} + +/* + * Add crashkernel info to OS info and update checksum + */ +void os_info_crashkernel_add(unsigned long base, unsigned long size) +{ + os_info.crashkernel_addr = (u64)(unsigned long)base; + os_info.crashkernel_size = (u64)(unsigned long)size; + os_info.csum = os_info_csum(&os_info); +} + +/* + * Add OS info entry and update checksum + */ +void os_info_entry_add(int nr, void *ptr, u64 size) +{ + os_info.entry[nr].addr = (u64)(unsigned long)ptr; + os_info.entry[nr].size = size; + os_info.entry[nr].csum = csum_partial(ptr, size, 0); + os_info.csum = os_info_csum(&os_info); +} + +/* + * Initialize OS info struture and set lowcore pointer + */ +void __init os_info_init(void) +{ + void *ptr = &os_info; + + os_info.version_major = OS_INFO_VERSION_MAJOR; + os_info.version_minor = OS_INFO_VERSION_MINOR; + os_info.magic = OS_INFO_MAGIC; + os_info.csum = os_info_csum(&os_info); + copy_to_absolute_zero(&S390_lowcore.os_info, &ptr, sizeof(ptr)); +} + +#ifdef CONFIG_CRASH_DUMP + +static struct os_info *os_info_old; + +/* + * Allocate and copy OS info entry from oldmem + */ +static void os_info_old_alloc(int nr, int align) +{ + unsigned long addr, size = 0; + char *buf, *buf_align, *msg; + u32 csum; + + addr = os_info_old->entry[nr].addr; + if (!addr) { + msg = "not available"; + goto fail; + } + size = os_info_old->entry[nr].size; + buf = kmalloc(size + align - 1, GFP_KERNEL); + if (!buf) { + msg = "alloc failed"; + goto fail; + } + buf_align = PTR_ALIGN(buf, align); + if (copy_from_oldmem(buf_align, (void *) addr, size)) { + msg = "copy failed"; + goto fail_free; + } + csum = csum_partial(buf_align, size, 0); + if (csum != os_info_old->entry[nr].csum) { + msg = "checksum failed"; + goto fail_free; + } + os_info_old->entry[nr].addr = (u64)(unsigned long)buf_align; + msg = "copied"; + goto out; +fail_free: + kfree(buf); +fail: + os_info_old->entry[nr].addr = 0; +out: + pr_info("entry %i: %s (addr=0x%lx size=%lu)\n", + nr, msg, addr, size); +} + +/* + * Initialize os info and os info entries from oldmem + */ +static void os_info_old_init(void) +{ + static int os_info_init; + unsigned long addr; + + if (os_info_init) + return; + if (!OLDMEM_BASE) + goto fail; + if (copy_from_oldmem(&addr, &S390_lowcore.os_info, sizeof(addr))) + goto fail; + if (addr == 0 || addr % PAGE_SIZE) + goto fail; + os_info_old = kzalloc(sizeof(*os_info_old), GFP_KERNEL); + if (!os_info_old) + goto fail; + if (copy_from_oldmem(os_info_old, (void *) addr, sizeof(*os_info_old))) + goto fail_free; + if (os_info_old->magic != OS_INFO_MAGIC) + goto fail_free; + if (os_info_old->csum != os_info_csum(os_info_old)) + goto fail_free; + if (os_info_old->version_major > OS_INFO_VERSION_MAJOR) + goto fail_free; + os_info_old_alloc(OS_INFO_VMCOREINFO, 1); + os_info_old_alloc(OS_INFO_REIPL_BLOCK, 1); + os_info_old_alloc(OS_INFO_INIT_FN, PAGE_SIZE); + pr_info("crashkernel: addr=0x%lx size=%lu\n", + (unsigned long) os_info_old->crashkernel_addr, + (unsigned long) os_info_old->crashkernel_size); + os_info_init = 1; + return; +fail_free: + kfree(os_info_old); +fail: + os_info_init = 1; + os_info_old = NULL; +} + +/* + * Return pointer to os infor entry and its size + */ +void *os_info_old_entry(int nr, unsigned long *size) +{ + os_info_old_init(); + + if (!os_info_old) + return NULL; + if (!os_info_old->entry[nr].addr) + return NULL; + *size = (unsigned long) os_info_old->entry[nr].size; + return (void *)(unsigned long)os_info_old->entry[nr].addr; +} +#endif diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c new file mode 100644 index 00000000..cb019f42 --- /dev/null +++ b/arch/s390/kernel/perf_cpum_cf.c @@ -0,0 +1,690 @@ +/* + * Performance event support for s390x - CPU-measurement Counter Facility + * + * Copyright IBM Corp. 2012 + * Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License (version 2 only) + * as published by the Free Software Foundation. + */ +#define KMSG_COMPONENT "cpum_cf" +#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt + +#include <linux/kernel.h> +#include <linux/kernel_stat.h> +#include <linux/perf_event.h> +#include <linux/percpu.h> +#include <linux/notifier.h> +#include <linux/init.h> +#include <linux/export.h> +#include <asm/ctl_reg.h> +#include <asm/irq.h> +#include <asm/cpu_mf.h> + +/* CPU-measurement counter facility supports these CPU counter sets: + * For CPU counter sets: + * Basic counter set: 0-31 + * Problem-state counter set: 32-63 + * Crypto-activity counter set: 64-127 + * Extented counter set: 128-159 + */ +enum cpumf_ctr_set { + /* CPU counter sets */ + CPUMF_CTR_SET_BASIC = 0, + CPUMF_CTR_SET_USER = 1, + CPUMF_CTR_SET_CRYPTO = 2, + CPUMF_CTR_SET_EXT = 3, + + /* Maximum number of counter sets */ + CPUMF_CTR_SET_MAX, +}; + +#define CPUMF_LCCTL_ENABLE_SHIFT 16 +#define CPUMF_LCCTL_ACTCTL_SHIFT 0 +static const u64 cpumf_state_ctl[CPUMF_CTR_SET_MAX] = { + [CPUMF_CTR_SET_BASIC] = 0x02, + [CPUMF_CTR_SET_USER] = 0x04, + [CPUMF_CTR_SET_CRYPTO] = 0x08, + [CPUMF_CTR_SET_EXT] = 0x01, +}; + +static void ctr_set_enable(u64 *state, int ctr_set) +{ + *state |= cpumf_state_ctl[ctr_set] << CPUMF_LCCTL_ENABLE_SHIFT; +} +static void ctr_set_disable(u64 *state, int ctr_set) +{ + *state &= ~(cpumf_state_ctl[ctr_set] << CPUMF_LCCTL_ENABLE_SHIFT); +} +static void ctr_set_start(u64 *state, int ctr_set) +{ + *state |= cpumf_state_ctl[ctr_set] << CPUMF_LCCTL_ACTCTL_SHIFT; +} +static void ctr_set_stop(u64 *state, int ctr_set) +{ + *state &= ~(cpumf_state_ctl[ctr_set] << CPUMF_LCCTL_ACTCTL_SHIFT); +} + +/* Local CPUMF event structure */ +struct cpu_hw_events { + struct cpumf_ctr_info info; + atomic_t ctr_set[CPUMF_CTR_SET_MAX]; + u64 state, tx_state; + unsigned int flags; +}; +static DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events) = { + .ctr_set = { + [CPUMF_CTR_SET_BASIC] = ATOMIC_INIT(0), + [CPUMF_CTR_SET_USER] = ATOMIC_INIT(0), + [CPUMF_CTR_SET_CRYPTO] = ATOMIC_INIT(0), + [CPUMF_CTR_SET_EXT] = ATOMIC_INIT(0), + }, + .state = 0, + .flags = 0, +}; + +static int get_counter_set(u64 event) +{ + int set = -1; + + if (event < 32) + set = CPUMF_CTR_SET_BASIC; + else if (event < 64) + set = CPUMF_CTR_SET_USER; + else if (event < 128) + set = CPUMF_CTR_SET_CRYPTO; + else if (event < 160) + set = CPUMF_CTR_SET_EXT; + + return set; +} + +static int validate_event(const struct hw_perf_event *hwc) +{ + switch (hwc->config_base) { + case CPUMF_CTR_SET_BASIC: + case CPUMF_CTR_SET_USER: + case CPUMF_CTR_SET_CRYPTO: + case CPUMF_CTR_SET_EXT: + /* check for reserved counters */ + if ((hwc->config >= 6 && hwc->config <= 31) || + (hwc->config >= 38 && hwc->config <= 63) || + (hwc->config >= 80 && hwc->config <= 127)) + return -EOPNOTSUPP; + break; + default: + return -EINVAL; + } + + return 0; +} + +static int validate_ctr_version(const struct hw_perf_event *hwc) +{ + struct cpu_hw_events *cpuhw; + int err = 0; + + cpuhw = &get_cpu_var(cpu_hw_events); + + /* check required version for counter sets */ + switch (hwc->config_base) { + case CPUMF_CTR_SET_BASIC: + case CPUMF_CTR_SET_USER: + if (cpuhw->info.cfvn < 1) + err = -EOPNOTSUPP; + break; + case CPUMF_CTR_SET_CRYPTO: + case CPUMF_CTR_SET_EXT: + if (cpuhw->info.csvn < 1) + err = -EOPNOTSUPP; + break; + } + + put_cpu_var(cpu_hw_events); + return err; +} + +static int validate_ctr_auth(const struct hw_perf_event *hwc) +{ + struct cpu_hw_events *cpuhw; + u64 ctrs_state; + int err = 0; + + cpuhw = &get_cpu_var(cpu_hw_events); + + /* check authorization for cpu counter sets */ + ctrs_state = cpumf_state_ctl[hwc->config_base]; + if (!(ctrs_state & cpuhw->info.auth_ctl)) + err = -EPERM; + + put_cpu_var(cpu_hw_events); + return err; +} + +/* + * Change the CPUMF state to active. + * Enable and activate the CPU-counter sets according + * to the per-cpu control state. + */ +static void cpumf_pmu_enable(struct pmu *pmu) +{ + struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events); + int err; + + if (cpuhw->flags & PMU_F_ENABLED) + return; + + err = lcctl(cpuhw->state); + if (err) { + pr_err("Enabling the performance measuring unit " + "failed with rc=%x\n", err); + return; + } + + cpuhw->flags |= PMU_F_ENABLED; +} + +/* + * Change the CPUMF state to inactive. + * Disable and enable (inactive) the CPU-counter sets according + * to the per-cpu control state. + */ +static void cpumf_pmu_disable(struct pmu *pmu) +{ + struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events); + int err; + u64 inactive; + + if (!(cpuhw->flags & PMU_F_ENABLED)) + return; + + inactive = cpuhw->state & ~((1 << CPUMF_LCCTL_ENABLE_SHIFT) - 1); + err = lcctl(inactive); + if (err) { + pr_err("Disabling the performance measuring unit " + "failed with rc=%x\n", err); + return; + } + + cpuhw->flags &= ~PMU_F_ENABLED; +} + + +/* Number of perf events counting hardware events */ +static atomic_t num_events = ATOMIC_INIT(0); +/* Used to avoid races in calling reserve/release_cpumf_hardware */ +static DEFINE_MUTEX(pmc_reserve_mutex); + +/* CPU-measurement alerts for the counter facility */ +static void cpumf_measurement_alert(struct ext_code ext_code, + unsigned int alert, unsigned long unused) +{ + struct cpu_hw_events *cpuhw; + + if (!(alert & CPU_MF_INT_CF_MASK)) + return; + + kstat_cpu(smp_processor_id()).irqs[EXTINT_CPM]++; + cpuhw = &__get_cpu_var(cpu_hw_events); + + /* Measurement alerts are shared and might happen when the PMU + * is not reserved. Ignore these alerts in this case. */ + if (!(cpuhw->flags & PMU_F_RESERVED)) + return; + + /* counter authorization change alert */ + if (alert & CPU_MF_INT_CF_CACA) + qctri(&cpuhw->info); + + /* loss of counter data alert */ + if (alert & CPU_MF_INT_CF_LCDA) + pr_err("CPU[%i] Counter data was lost\n", smp_processor_id()); +} + +#define PMC_INIT 0 +#define PMC_RELEASE 1 +static void setup_pmc_cpu(void *flags) +{ + struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events); + + switch (*((int *) flags)) { + case PMC_INIT: + memset(&cpuhw->info, 0, sizeof(cpuhw->info)); + qctri(&cpuhw->info); + cpuhw->flags |= PMU_F_RESERVED; + break; + + case PMC_RELEASE: + cpuhw->flags &= ~PMU_F_RESERVED; + break; + } + + /* Disable CPU counter sets */ + lcctl(0); +} + +/* Initialize the CPU-measurement facility */ +static int reserve_pmc_hardware(void) +{ + int flags = PMC_INIT; + + on_each_cpu(setup_pmc_cpu, &flags, 1); + measurement_alert_subclass_register(); + + return 0; +} + +/* Release the CPU-measurement facility */ +static void release_pmc_hardware(void) +{ + int flags = PMC_RELEASE; + + on_each_cpu(setup_pmc_cpu, &flags, 1); + measurement_alert_subclass_unregister(); +} + +/* Release the PMU if event is the last perf event */ +static void hw_perf_event_destroy(struct perf_event *event) +{ + if (!atomic_add_unless(&num_events, -1, 1)) { + mutex_lock(&pmc_reserve_mutex); + if (atomic_dec_return(&num_events) == 0) + release_pmc_hardware(); + mutex_unlock(&pmc_reserve_mutex); + } +} + +/* CPUMF <-> perf event mappings for kernel+userspace (basic set) */ +static const int cpumf_generic_events_basic[] = { + [PERF_COUNT_HW_CPU_CYCLES] = 0, + [PERF_COUNT_HW_INSTRUCTIONS] = 1, + [PERF_COUNT_HW_CACHE_REFERENCES] = -1, + [PERF_COUNT_HW_CACHE_MISSES] = -1, + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = -1, + [PERF_COUNT_HW_BRANCH_MISSES] = -1, + [PERF_COUNT_HW_BUS_CYCLES] = -1, +}; +/* CPUMF <-> perf event mappings for userspace (problem-state set) */ +static const int cpumf_generic_events_user[] = { + [PERF_COUNT_HW_CPU_CYCLES] = 32, + [PERF_COUNT_HW_INSTRUCTIONS] = 33, + [PERF_COUNT_HW_CACHE_REFERENCES] = -1, + [PERF_COUNT_HW_CACHE_MISSES] = -1, + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = -1, + [PERF_COUNT_HW_BRANCH_MISSES] = -1, + [PERF_COUNT_HW_BUS_CYCLES] = -1, +}; + +static int __hw_perf_event_init(struct perf_event *event) +{ + struct perf_event_attr *attr = &event->attr; + struct hw_perf_event *hwc = &event->hw; + int err; + u64 ev; + + switch (attr->type) { + case PERF_TYPE_RAW: + /* Raw events are used to access counters directly, + * hence do not permit excludes */ + if (attr->exclude_kernel || attr->exclude_user || + attr->exclude_hv) + return -EOPNOTSUPP; + ev = attr->config; + break; + + case PERF_TYPE_HARDWARE: + ev = attr->config; + /* Count user space (problem-state) only */ + if (!attr->exclude_user && attr->exclude_kernel) { + if (ev >= ARRAY_SIZE(cpumf_generic_events_user)) + return -EOPNOTSUPP; + ev = cpumf_generic_events_user[ev]; + + /* No support for kernel space counters only */ + } else if (!attr->exclude_kernel && attr->exclude_user) { + return -EOPNOTSUPP; + + /* Count user and kernel space */ + } else { + if (ev >= ARRAY_SIZE(cpumf_generic_events_basic)) + return -EOPNOTSUPP; + ev = cpumf_generic_events_basic[ev]; + } + break; + + default: + return -ENOENT; + } + + if (ev == -1) + return -ENOENT; + + if (ev >= PERF_CPUM_CF_MAX_CTR) + return -EINVAL; + + /* The CPU measurement counter facility does not have any interrupts + * to do sampling. Sampling must be provided by external means, + * for example, by timers. + */ + if (hwc->sample_period) + return -EINVAL; + + /* Use the hardware perf event structure to store the counter number + * in 'config' member and the counter set to which the counter belongs + * in the 'config_base'. The counter set (config_base) is then used + * to enable/disable the counters. + */ + hwc->config = ev; + hwc->config_base = get_counter_set(ev); + + /* Validate the counter that is assigned to this event. + * Because the counter facility can use numerous counters at the + * same time without constraints, it is not necessary to explicity + * validate event groups (event->group_leader != event). + */ + err = validate_event(hwc); + if (err) + return err; + + /* Initialize for using the CPU-measurement counter facility */ + if (!atomic_inc_not_zero(&num_events)) { + mutex_lock(&pmc_reserve_mutex); + if (atomic_read(&num_events) == 0 && reserve_pmc_hardware()) + err = -EBUSY; + else + atomic_inc(&num_events); + mutex_unlock(&pmc_reserve_mutex); + } + event->destroy = hw_perf_event_destroy; + + /* Finally, validate version and authorization of the counter set */ + err = validate_ctr_auth(hwc); + if (!err) + err = validate_ctr_version(hwc); + + return err; +} + +static int cpumf_pmu_event_init(struct perf_event *event) +{ + int err; + + switch (event->attr.type) { + case PERF_TYPE_HARDWARE: + case PERF_TYPE_HW_CACHE: + case PERF_TYPE_RAW: + err = __hw_perf_event_init(event); + break; + default: + return -ENOENT; + } + + if (unlikely(err) && event->destroy) + event->destroy(event); + + return err; +} + +static int hw_perf_event_reset(struct perf_event *event) +{ + u64 prev, new; + int err; + + do { + prev = local64_read(&event->hw.prev_count); + err = ecctr(event->hw.config, &new); + if (err) { + if (err != 3) + break; + /* The counter is not (yet) available. This + * might happen if the counter set to which + * this counter belongs is in the disabled + * state. + */ + new = 0; + } + } while (local64_cmpxchg(&event->hw.prev_count, prev, new) != prev); + + return err; +} + +static int hw_perf_event_update(struct perf_event *event) +{ + u64 prev, new, delta; + int err; + + do { + prev = local64_read(&event->hw.prev_count); + err = ecctr(event->hw.config, &new); + if (err) + goto out; + } while (local64_cmpxchg(&event->hw.prev_count, prev, new) != prev); + + delta = (prev <= new) ? new - prev + : (-1ULL - prev) + new + 1; /* overflow */ + local64_add(delta, &event->count); +out: + return err; +} + +static void cpumf_pmu_read(struct perf_event *event) +{ + if (event->hw.state & PERF_HES_STOPPED) + return; + + hw_perf_event_update(event); +} + +static void cpumf_pmu_start(struct perf_event *event, int flags) +{ + struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events); + struct hw_perf_event *hwc = &event->hw; + + if (WARN_ON_ONCE(!(hwc->state & PERF_HES_STOPPED))) + return; + + if (WARN_ON_ONCE(hwc->config == -1)) + return; + + if (flags & PERF_EF_RELOAD) + WARN_ON_ONCE(!(hwc->state & PERF_HES_UPTODATE)); + + hwc->state = 0; + + /* (Re-)enable and activate the counter set */ + ctr_set_enable(&cpuhw->state, hwc->config_base); + ctr_set_start(&cpuhw->state, hwc->config_base); + + /* The counter set to which this counter belongs can be already active. + * Because all counters in a set are active, the event->hw.prev_count + * needs to be synchronized. At this point, the counter set can be in + * the inactive or disabled state. + */ + hw_perf_event_reset(event); + + /* increment refcount for this counter set */ + atomic_inc(&cpuhw->ctr_set[hwc->config_base]); +} + +static void cpumf_pmu_stop(struct perf_event *event, int flags) +{ + struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events); + struct hw_perf_event *hwc = &event->hw; + + if (!(hwc->state & PERF_HES_STOPPED)) { + /* Decrement reference count for this counter set and if this + * is the last used counter in the set, clear activation + * control and set the counter set state to inactive. + */ + if (!atomic_dec_return(&cpuhw->ctr_set[hwc->config_base])) + ctr_set_stop(&cpuhw->state, hwc->config_base); + event->hw.state |= PERF_HES_STOPPED; + } + + if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) { + hw_perf_event_update(event); + event->hw.state |= PERF_HES_UPTODATE; + } +} + +static int cpumf_pmu_add(struct perf_event *event, int flags) +{ + struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events); + + /* Check authorization for the counter set to which this + * counter belongs. + * For group events transaction, the authorization check is + * done in cpumf_pmu_commit_txn(). + */ + if (!(cpuhw->flags & PERF_EVENT_TXN)) + if (validate_ctr_auth(&event->hw)) + return -EPERM; + + ctr_set_enable(&cpuhw->state, event->hw.config_base); + event->hw.state = PERF_HES_UPTODATE | PERF_HES_STOPPED; + + if (flags & PERF_EF_START) + cpumf_pmu_start(event, PERF_EF_RELOAD); + + perf_event_update_userpage(event); + + return 0; +} + +static void cpumf_pmu_del(struct perf_event *event, int flags) +{ + struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events); + + cpumf_pmu_stop(event, PERF_EF_UPDATE); + + /* Check if any counter in the counter set is still used. If not used, + * change the counter set to the disabled state. This also clears the + * content of all counters in the set. + * + * When a new perf event has been added but not yet started, this can + * clear enable control and resets all counters in a set. Therefore, + * cpumf_pmu_start() always has to reenable a counter set. + */ + if (!atomic_read(&cpuhw->ctr_set[event->hw.config_base])) + ctr_set_disable(&cpuhw->state, event->hw.config_base); + + perf_event_update_userpage(event); +} + +/* + * Start group events scheduling transaction. + * Set flags to perform a single test at commit time. + */ +static void cpumf_pmu_start_txn(struct pmu *pmu) +{ + struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events); + + perf_pmu_disable(pmu); + cpuhw->flags |= PERF_EVENT_TXN; + cpuhw->tx_state = cpuhw->state; +} + +/* + * Stop and cancel a group events scheduling tranctions. + * Assumes cpumf_pmu_del() is called for each successful added + * cpumf_pmu_add() during the transaction. + */ +static void cpumf_pmu_cancel_txn(struct pmu *pmu) +{ + struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events); + + WARN_ON(cpuhw->tx_state != cpuhw->state); + + cpuhw->flags &= ~PERF_EVENT_TXN; + perf_pmu_enable(pmu); +} + +/* + * Commit the group events scheduling transaction. On success, the + * transaction is closed. On error, the transaction is kept open + * until cpumf_pmu_cancel_txn() is called. + */ +static int cpumf_pmu_commit_txn(struct pmu *pmu) +{ + struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events); + u64 state; + + /* check if the updated state can be scheduled */ + state = cpuhw->state & ~((1 << CPUMF_LCCTL_ENABLE_SHIFT) - 1); + state >>= CPUMF_LCCTL_ENABLE_SHIFT; + if ((state & cpuhw->info.auth_ctl) != state) + return -EPERM; + + cpuhw->flags &= ~PERF_EVENT_TXN; + perf_pmu_enable(pmu); + return 0; +} + +/* Performance monitoring unit for s390x */ +static struct pmu cpumf_pmu = { + .pmu_enable = cpumf_pmu_enable, + .pmu_disable = cpumf_pmu_disable, + .event_init = cpumf_pmu_event_init, + .add = cpumf_pmu_add, + .del = cpumf_pmu_del, + .start = cpumf_pmu_start, + .stop = cpumf_pmu_stop, + .read = cpumf_pmu_read, + .start_txn = cpumf_pmu_start_txn, + .commit_txn = cpumf_pmu_commit_txn, + .cancel_txn = cpumf_pmu_cancel_txn, +}; + +static int __cpuinit cpumf_pmu_notifier(struct notifier_block *self, + unsigned long action, void *hcpu) +{ + unsigned int cpu = (long) hcpu; + int flags; + + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_ONLINE: + flags = PMC_INIT; + smp_call_function_single(cpu, setup_pmc_cpu, &flags, 1); + break; + case CPU_DOWN_PREPARE: + flags = PMC_RELEASE; + smp_call_function_single(cpu, setup_pmc_cpu, &flags, 1); + break; + default: + break; + } + + return NOTIFY_OK; +} + +static int __init cpumf_pmu_init(void) +{ + int rc; + + if (!cpum_cf_avail()) + return -ENODEV; + + /* clear bit 15 of cr0 to unauthorize problem-state to + * extract measurement counters */ + ctl_clear_bit(0, 48); + + /* register handler for measurement-alert interruptions */ + rc = register_external_interrupt(0x1407, cpumf_measurement_alert); + if (rc) { + pr_err("Registering for CPU-measurement alerts " + "failed with rc=%i\n", rc); + goto out; + } + + rc = perf_pmu_register(&cpumf_pmu, "cpum_cf", PERF_TYPE_RAW); + if (rc) { + pr_err("Registering the cpum_cf PMU failed with rc=%i\n", rc); + unregister_external_interrupt(0x1407, cpumf_measurement_alert); + goto out; + } + perf_cpu_notifier(cpumf_pmu_notifier); +out: + return rc; +} +early_initcall(cpumf_pmu_init); diff --git a/arch/s390/kernel/perf_event.c b/arch/s390/kernel/perf_event.c new file mode 100644 index 00000000..f58f37f6 --- /dev/null +++ b/arch/s390/kernel/perf_event.c @@ -0,0 +1,124 @@ +/* + * Performance event support for s390x + * + * Copyright IBM Corp. 2012 + * Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License (version 2 only) + * as published by the Free Software Foundation. + */ +#define KMSG_COMPONENT "perf" +#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt + +#include <linux/kernel.h> +#include <linux/perf_event.h> +#include <linux/percpu.h> +#include <linux/export.h> +#include <asm/irq.h> +#include <asm/cpu_mf.h> +#include <asm/lowcore.h> +#include <asm/processor.h> + +const char *perf_pmu_name(void) +{ + if (cpum_cf_avail() || cpum_sf_avail()) + return "CPU-measurement facilities (CPUMF)"; + return "pmu"; +} +EXPORT_SYMBOL(perf_pmu_name); + +int perf_num_counters(void) +{ + int num = 0; + + if (cpum_cf_avail()) + num += PERF_CPUM_CF_MAX_CTR; + + return num; +} +EXPORT_SYMBOL(perf_num_counters); + +void perf_event_print_debug(void) +{ + struct cpumf_ctr_info cf_info; + unsigned long flags; + int cpu; + + if (!cpum_cf_avail()) + return; + + local_irq_save(flags); + + cpu = smp_processor_id(); + memset(&cf_info, 0, sizeof(cf_info)); + if (!qctri(&cf_info)) { + pr_info("CPU[%i] CPUM_CF: ver=%u.%u A=%04x E=%04x C=%04x\n", + cpu, cf_info.cfvn, cf_info.csvn, + cf_info.auth_ctl, cf_info.enable_ctl, cf_info.act_ctl); + print_hex_dump_bytes("CPUMF Query: ", DUMP_PREFIX_OFFSET, + &cf_info, sizeof(cf_info)); + } + + local_irq_restore(flags); +} + +/* See also arch/s390/kernel/traps.c */ +static unsigned long __store_trace(struct perf_callchain_entry *entry, + unsigned long sp, + unsigned long low, unsigned long high) +{ + struct stack_frame *sf; + struct pt_regs *regs; + + while (1) { + sp = sp & PSW_ADDR_INSN; + if (sp < low || sp > high - sizeof(*sf)) + return sp; + sf = (struct stack_frame *) sp; + perf_callchain_store(entry, sf->gprs[8] & PSW_ADDR_INSN); + /* Follow the backchain. */ + while (1) { + low = sp; + sp = sf->back_chain & PSW_ADDR_INSN; + if (!sp) + break; + if (sp <= low || sp > high - sizeof(*sf)) + return sp; + sf = (struct stack_frame *) sp; + perf_callchain_store(entry, + sf->gprs[8] & PSW_ADDR_INSN); + } + /* Zero backchain detected, check for interrupt frame. */ + sp = (unsigned long) (sf + 1); + if (sp <= low || sp > high - sizeof(*regs)) + return sp; + regs = (struct pt_regs *) sp; + perf_callchain_store(entry, sf->gprs[8] & PSW_ADDR_INSN); + low = sp; + sp = regs->gprs[15]; + } +} + +void perf_callchain_kernel(struct perf_callchain_entry *entry, + struct pt_regs *regs) +{ + unsigned long head; + struct stack_frame *head_sf; + + if (user_mode(regs)) + return; + + head = regs->gprs[15]; + head_sf = (struct stack_frame *) head; + + if (!head_sf || !head_sf->back_chain) + return; + + head = head_sf->back_chain; + head = __store_trace(entry, head, S390_lowcore.async_stack - ASYNC_SIZE, + S390_lowcore.async_stack); + + __store_trace(entry, head, S390_lowcore.thread_info, + S390_lowcore.thread_info + THREAD_SIZE); +} diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c new file mode 100644 index 00000000..60055cef --- /dev/null +++ b/arch/s390/kernel/process.c @@ -0,0 +1,354 @@ +/* + * This file handles the architecture dependent parts of process handling. + * + * Copyright IBM Corp. 1999,2009 + * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>, + * Hartmut Penner <hp@de.ibm.com>, + * Denis Joseph Barrow, + */ + +#include <linux/compiler.h> +#include <linux/cpu.h> +#include <linux/sched.h> +#include <linux/kernel.h> +#include <linux/mm.h> +#include <linux/elfcore.h> +#include <linux/smp.h> +#include <linux/slab.h> +#include <linux/interrupt.h> +#include <linux/tick.h> +#include <linux/personality.h> +#include <linux/syscalls.h> +#include <linux/compat.h> +#include <linux/kprobes.h> +#include <linux/random.h> +#include <linux/module.h> +#include <asm/io.h> +#include <asm/processor.h> +#include <asm/irq.h> +#include <asm/timer.h> +#include <asm/nmi.h> +#include <asm/smp.h> +#include <asm/switch_to.h> +#include "entry.h" + +asmlinkage void ret_from_fork(void) asm ("ret_from_fork"); + +/* + * Return saved PC of a blocked thread. used in kernel/sched. + * resume in entry.S does not create a new stack frame, it + * just stores the registers %r6-%r15 to the frame given by + * schedule. We want to return the address of the caller of + * schedule, so we have to walk the backchain one time to + * find the frame schedule() store its return address. + */ +unsigned long thread_saved_pc(struct task_struct *tsk) +{ + struct stack_frame *sf, *low, *high; + + if (!tsk || !task_stack_page(tsk)) + return 0; + low = task_stack_page(tsk); + high = (struct stack_frame *) task_pt_regs(tsk); + sf = (struct stack_frame *) (tsk->thread.ksp & PSW_ADDR_INSN); + if (sf <= low || sf > high) + return 0; + sf = (struct stack_frame *) (sf->back_chain & PSW_ADDR_INSN); + if (sf <= low || sf > high) + return 0; + return sf->gprs[8]; +} + +/* + * The idle loop on a S390... + */ +static void default_idle(void) +{ + if (cpu_is_offline(smp_processor_id())) + cpu_die(); + local_irq_disable(); + if (need_resched()) { + local_irq_enable(); + return; + } + local_mcck_disable(); + if (test_thread_flag(TIF_MCCK_PENDING)) { + local_mcck_enable(); + local_irq_enable(); + return; + } + /* Halt the cpu and keep track of cpu time accounting. */ + vtime_stop_cpu(); +} + +void cpu_idle(void) +{ + for (;;) { + tick_nohz_idle_enter(); + rcu_idle_enter(); + while (!need_resched() && !test_thread_flag(TIF_MCCK_PENDING)) + default_idle(); + rcu_idle_exit(); + tick_nohz_idle_exit(); + if (test_thread_flag(TIF_MCCK_PENDING)) + s390_handle_mcck(); + schedule_preempt_disabled(); + } +} + +extern void __kprobes kernel_thread_starter(void); + +asm( + ".section .kprobes.text, \"ax\"\n" + ".global kernel_thread_starter\n" + "kernel_thread_starter:\n" + " la 2,0(10)\n" + " basr 14,9\n" + " la 2,0\n" + " br 11\n" + ".previous\n"); + +int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags) +{ + struct pt_regs regs; + + memset(®s, 0, sizeof(regs)); + regs.psw.mask = psw_kernel_bits | + PSW_MASK_DAT | PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK; + regs.psw.addr = (unsigned long) kernel_thread_starter | PSW_ADDR_AMODE; + regs.gprs[9] = (unsigned long) fn; + regs.gprs[10] = (unsigned long) arg; + regs.gprs[11] = (unsigned long) do_exit; + regs.orig_gpr2 = -1; + + /* Ok, create the new process.. */ + return do_fork(flags | CLONE_VM | CLONE_UNTRACED, + 0, ®s, 0, NULL, NULL); +} +EXPORT_SYMBOL(kernel_thread); + +/* + * Free current thread data structures etc.. + */ +void exit_thread(void) +{ +} + +void flush_thread(void) +{ +} + +void release_thread(struct task_struct *dead_task) +{ +} + +int copy_thread(unsigned long clone_flags, unsigned long new_stackp, + unsigned long unused, + struct task_struct *p, struct pt_regs *regs) +{ + struct thread_info *ti; + struct fake_frame + { + struct stack_frame sf; + struct pt_regs childregs; + } *frame; + + frame = container_of(task_pt_regs(p), struct fake_frame, childregs); + p->thread.ksp = (unsigned long) frame; + /* Store access registers to kernel stack of new process. */ + frame->childregs = *regs; + frame->childregs.gprs[2] = 0; /* child returns 0 on fork. */ + frame->childregs.gprs[15] = new_stackp; + frame->sf.back_chain = 0; + + /* new return point is ret_from_fork */ + frame->sf.gprs[8] = (unsigned long) ret_from_fork; + + /* fake return stack for resume(), don't go back to schedule */ + frame->sf.gprs[9] = (unsigned long) frame; + + /* Save access registers to new thread structure. */ + save_access_regs(&p->thread.acrs[0]); + +#ifndef CONFIG_64BIT + /* + * save fprs to current->thread.fp_regs to merge them with + * the emulated registers and then copy the result to the child. + */ + save_fp_regs(¤t->thread.fp_regs); + memcpy(&p->thread.fp_regs, ¤t->thread.fp_regs, + sizeof(s390_fp_regs)); + /* Set a new TLS ? */ + if (clone_flags & CLONE_SETTLS) + p->thread.acrs[0] = regs->gprs[6]; +#else /* CONFIG_64BIT */ + /* Save the fpu registers to new thread structure. */ + save_fp_regs(&p->thread.fp_regs); + /* Set a new TLS ? */ + if (clone_flags & CLONE_SETTLS) { + if (is_compat_task()) { + p->thread.acrs[0] = (unsigned int) regs->gprs[6]; + } else { + p->thread.acrs[0] = (unsigned int)(regs->gprs[6] >> 32); + p->thread.acrs[1] = (unsigned int) regs->gprs[6]; + } + } +#endif /* CONFIG_64BIT */ + /* start new process with ar4 pointing to the correct address space */ + p->thread.mm_segment = get_fs(); + /* Don't copy debug registers */ + memset(&p->thread.per_user, 0, sizeof(p->thread.per_user)); + memset(&p->thread.per_event, 0, sizeof(p->thread.per_event)); + clear_tsk_thread_flag(p, TIF_SINGLE_STEP); + clear_tsk_thread_flag(p, TIF_PER_TRAP); + /* Initialize per thread user and system timer values */ + ti = task_thread_info(p); + ti->user_timer = 0; + ti->system_timer = 0; + return 0; +} + +SYSCALL_DEFINE0(fork) +{ + struct pt_regs *regs = task_pt_regs(current); + return do_fork(SIGCHLD, regs->gprs[15], regs, 0, NULL, NULL); +} + +SYSCALL_DEFINE4(clone, unsigned long, newsp, unsigned long, clone_flags, + int __user *, parent_tidptr, int __user *, child_tidptr) +{ + struct pt_regs *regs = task_pt_regs(current); + + if (!newsp) + newsp = regs->gprs[15]; + return do_fork(clone_flags, newsp, regs, 0, + parent_tidptr, child_tidptr); +} + +/* + * This is trivial, and on the face of it looks like it + * could equally well be done in user mode. + * + * Not so, for quite unobvious reasons - register pressure. + * In user mode vfork() cannot have a stack frame, and if + * done by calling the "clone()" system call directly, you + * do not have enough call-clobbered registers to hold all + * the information you need. + */ +SYSCALL_DEFINE0(vfork) +{ + struct pt_regs *regs = task_pt_regs(current); + return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, + regs->gprs[15], regs, 0, NULL, NULL); +} + +asmlinkage void execve_tail(void) +{ + current->thread.fp_regs.fpc = 0; + if (MACHINE_HAS_IEEE) + asm volatile("sfpc %0,%0" : : "d" (0)); +} + +/* + * sys_execve() executes a new program. + */ +SYSCALL_DEFINE3(execve, const char __user *, name, + const char __user *const __user *, argv, + const char __user *const __user *, envp) +{ + struct pt_regs *regs = task_pt_regs(current); + char *filename; + long rc; + + filename = getname(name); + rc = PTR_ERR(filename); + if (IS_ERR(filename)) + return rc; + rc = do_execve(filename, argv, envp, regs); + if (rc) + goto out; + execve_tail(); + rc = regs->gprs[2]; +out: + putname(filename); + return rc; +} + +/* + * fill in the FPU structure for a core dump. + */ +int dump_fpu (struct pt_regs * regs, s390_fp_regs *fpregs) +{ +#ifndef CONFIG_64BIT + /* + * save fprs to current->thread.fp_regs to merge them with + * the emulated registers and then copy the result to the dump. + */ + save_fp_regs(¤t->thread.fp_regs); + memcpy(fpregs, ¤t->thread.fp_regs, sizeof(s390_fp_regs)); +#else /* CONFIG_64BIT */ + save_fp_regs(fpregs); +#endif /* CONFIG_64BIT */ + return 1; +} +EXPORT_SYMBOL(dump_fpu); + +unsigned long get_wchan(struct task_struct *p) +{ + struct stack_frame *sf, *low, *high; + unsigned long return_address; + int count; + + if (!p || p == current || p->state == TASK_RUNNING || !task_stack_page(p)) + return 0; + low = task_stack_page(p); + high = (struct stack_frame *) task_pt_regs(p); + sf = (struct stack_frame *) (p->thread.ksp & PSW_ADDR_INSN); + if (sf <= low || sf > high) + return 0; + for (count = 0; count < 16; count++) { + sf = (struct stack_frame *) (sf->back_chain & PSW_ADDR_INSN); + if (sf <= low || sf > high) + return 0; + return_address = sf->gprs[8] & PSW_ADDR_INSN; + if (!in_sched_functions(return_address)) + return return_address; + } + return 0; +} + +unsigned long arch_align_stack(unsigned long sp) +{ + if (!(current->personality & ADDR_NO_RANDOMIZE) && randomize_va_space) + sp -= get_random_int() & ~PAGE_MASK; + return sp & ~0xf; +} + +static inline unsigned long brk_rnd(void) +{ + /* 8MB for 32bit, 1GB for 64bit */ + if (is_32bit_task()) + return (get_random_int() & 0x7ffUL) << PAGE_SHIFT; + else + return (get_random_int() & 0x3ffffUL) << PAGE_SHIFT; +} + +unsigned long arch_randomize_brk(struct mm_struct *mm) +{ + unsigned long ret = PAGE_ALIGN(mm->brk + brk_rnd()); + + if (ret < mm->brk) + return mm->brk; + return ret; +} + +unsigned long randomize_et_dyn(unsigned long base) +{ + unsigned long ret = PAGE_ALIGN(base + brk_rnd()); + + if (!(current->flags & PF_RANDOMIZE)) + return base; + if (ret < base) + return base; + return ret; +} diff --git a/arch/s390/kernel/processor.c b/arch/s390/kernel/processor.c new file mode 100644 index 00000000..6e0073e4 --- /dev/null +++ b/arch/s390/kernel/processor.c @@ -0,0 +1,96 @@ +/* + * arch/s390/kernel/processor.c + * + * Copyright IBM Corp. 2008 + * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com) + */ + +#define KMSG_COMPONENT "cpu" +#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt + +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/smp.h> +#include <linux/seq_file.h> +#include <linux/delay.h> +#include <linux/cpu.h> +#include <asm/elf.h> +#include <asm/lowcore.h> +#include <asm/param.h> + +static DEFINE_PER_CPU(struct cpuid, cpu_id); + +/* + * cpu_init - initializes state that is per-CPU. + */ +void __cpuinit cpu_init(void) +{ + struct cpuid *id = &per_cpu(cpu_id, smp_processor_id()); + + get_cpu_id(id); + atomic_inc(&init_mm.mm_count); + current->active_mm = &init_mm; + BUG_ON(current->mm); + enter_lazy_tlb(&init_mm, current); +} + +/* + * show_cpuinfo - Get information on one CPU for use by procfs. + */ +static int show_cpuinfo(struct seq_file *m, void *v) +{ + static const char *hwcap_str[10] = { + "esan3", "zarch", "stfle", "msa", "ldisp", "eimm", "dfp", + "edat", "etf3eh", "highgprs" + }; + unsigned long n = (unsigned long) v - 1; + int i; + + if (!n) { + s390_adjust_jiffies(); + seq_printf(m, "vendor_id : IBM/S390\n" + "# processors : %i\n" + "bogomips per cpu: %lu.%02lu\n", + num_online_cpus(), loops_per_jiffy/(500000/HZ), + (loops_per_jiffy/(5000/HZ))%100); + seq_puts(m, "features\t: "); + for (i = 0; i < 10; i++) + if (hwcap_str[i] && (elf_hwcap & (1UL << i))) + seq_printf(m, "%s ", hwcap_str[i]); + seq_puts(m, "\n"); + } + get_online_cpus(); + if (cpu_online(n)) { + struct cpuid *id = &per_cpu(cpu_id, n); + seq_printf(m, "processor %li: " + "version = %02X, " + "identification = %06X, " + "machine = %04X\n", + n, id->version, id->ident, id->machine); + } + put_online_cpus(); + return 0; +} + +static void *c_start(struct seq_file *m, loff_t *pos) +{ + return *pos < nr_cpu_ids ? (void *)((unsigned long) *pos + 1) : NULL; +} + +static void *c_next(struct seq_file *m, void *v, loff_t *pos) +{ + ++*pos; + return c_start(m, pos); +} + +static void c_stop(struct seq_file *m, void *v) +{ +} + +const struct seq_operations cpuinfo_op = { + .start = c_start, + .next = c_next, + .stop = c_stop, + .show = show_cpuinfo, +}; + diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c new file mode 100644 index 00000000..02f300fb --- /dev/null +++ b/arch/s390/kernel/ptrace.c @@ -0,0 +1,1237 @@ +/* + * Ptrace user space interface. + * + * Copyright IBM Corp. 1999,2010 + * Author(s): Denis Joseph Barrow + * Martin Schwidefsky (schwidefsky@de.ibm.com) + */ + +#include <linux/kernel.h> +#include <linux/sched.h> +#include <linux/mm.h> +#include <linux/smp.h> +#include <linux/errno.h> +#include <linux/ptrace.h> +#include <linux/user.h> +#include <linux/security.h> +#include <linux/audit.h> +#include <linux/signal.h> +#include <linux/elf.h> +#include <linux/regset.h> +#include <linux/tracehook.h> +#include <linux/seccomp.h> +#include <linux/compat.h> +#include <trace/syscall.h> +#include <asm/segment.h> +#include <asm/page.h> +#include <asm/pgtable.h> +#include <asm/pgalloc.h> +#include <asm/uaccess.h> +#include <asm/unistd.h> +#include <asm/switch_to.h> +#include "entry.h" + +#ifdef CONFIG_COMPAT +#include "compat_ptrace.h" +#endif + +#define CREATE_TRACE_POINTS +#include <trace/events/syscalls.h> + +enum s390_regset { + REGSET_GENERAL, + REGSET_FP, + REGSET_LAST_BREAK, + REGSET_SYSTEM_CALL, + REGSET_GENERAL_EXTENDED, +}; + +void update_per_regs(struct task_struct *task) +{ + struct pt_regs *regs = task_pt_regs(task); + struct thread_struct *thread = &task->thread; + struct per_regs old, new; + + /* Copy user specified PER registers */ + new.control = thread->per_user.control; + new.start = thread->per_user.start; + new.end = thread->per_user.end; + + /* merge TIF_SINGLE_STEP into user specified PER registers. */ + if (test_tsk_thread_flag(task, TIF_SINGLE_STEP)) { + new.control |= PER_EVENT_IFETCH; + new.start = 0; + new.end = PSW_ADDR_INSN; + } + + /* Take care of the PER enablement bit in the PSW. */ + if (!(new.control & PER_EVENT_MASK)) { + regs->psw.mask &= ~PSW_MASK_PER; + return; + } + regs->psw.mask |= PSW_MASK_PER; + __ctl_store(old, 9, 11); + if (memcmp(&new, &old, sizeof(struct per_regs)) != 0) + __ctl_load(new, 9, 11); +} + +void user_enable_single_step(struct task_struct *task) +{ + set_tsk_thread_flag(task, TIF_SINGLE_STEP); + if (task == current) + update_per_regs(task); +} + +void user_disable_single_step(struct task_struct *task) +{ + clear_tsk_thread_flag(task, TIF_SINGLE_STEP); + if (task == current) + update_per_regs(task); +} + +/* + * Called by kernel/ptrace.c when detaching.. + * + * Clear all debugging related fields. + */ +void ptrace_disable(struct task_struct *task) +{ + memset(&task->thread.per_user, 0, sizeof(task->thread.per_user)); + memset(&task->thread.per_event, 0, sizeof(task->thread.per_event)); + clear_tsk_thread_flag(task, TIF_SINGLE_STEP); + clear_tsk_thread_flag(task, TIF_PER_TRAP); +} + +#ifndef CONFIG_64BIT +# define __ADDR_MASK 3 +#else +# define __ADDR_MASK 7 +#endif + +static inline unsigned long __peek_user_per(struct task_struct *child, + addr_t addr) +{ + struct per_struct_kernel *dummy = NULL; + + if (addr == (addr_t) &dummy->cr9) + /* Control bits of the active per set. */ + return test_thread_flag(TIF_SINGLE_STEP) ? + PER_EVENT_IFETCH : child->thread.per_user.control; + else if (addr == (addr_t) &dummy->cr10) + /* Start address of the active per set. */ + return test_thread_flag(TIF_SINGLE_STEP) ? + 0 : child->thread.per_user.start; + else if (addr == (addr_t) &dummy->cr11) + /* End address of the active per set. */ + return test_thread_flag(TIF_SINGLE_STEP) ? + PSW_ADDR_INSN : child->thread.per_user.end; + else if (addr == (addr_t) &dummy->bits) + /* Single-step bit. */ + return test_thread_flag(TIF_SINGLE_STEP) ? + (1UL << (BITS_PER_LONG - 1)) : 0; + else if (addr == (addr_t) &dummy->starting_addr) + /* Start address of the user specified per set. */ + return child->thread.per_user.start; + else if (addr == (addr_t) &dummy->ending_addr) + /* End address of the user specified per set. */ + return child->thread.per_user.end; + else if (addr == (addr_t) &dummy->perc_atmid) + /* PER code, ATMID and AI of the last PER trap */ + return (unsigned long) + child->thread.per_event.cause << (BITS_PER_LONG - 16); + else if (addr == (addr_t) &dummy->address) + /* Address of the last PER trap */ + return child->thread.per_event.address; + else if (addr == (addr_t) &dummy->access_id) + /* Access id of the last PER trap */ + return (unsigned long) + child->thread.per_event.paid << (BITS_PER_LONG - 8); + return 0; +} + +/* + * Read the word at offset addr from the user area of a process. The + * trouble here is that the information is littered over different + * locations. The process registers are found on the kernel stack, + * the floating point stuff and the trace settings are stored in + * the task structure. In addition the different structures in + * struct user contain pad bytes that should be read as zeroes. + * Lovely... + */ +static unsigned long __peek_user(struct task_struct *child, addr_t addr) +{ + struct user *dummy = NULL; + addr_t offset, tmp; + + if (addr < (addr_t) &dummy->regs.acrs) { + /* + * psw and gprs are stored on the stack + */ + tmp = *(addr_t *)((addr_t) &task_pt_regs(child)->psw + addr); + if (addr == (addr_t) &dummy->regs.psw.mask) + /* Return a clean psw mask. */ + tmp = psw_user_bits | (tmp & PSW_MASK_USER); + + } else if (addr < (addr_t) &dummy->regs.orig_gpr2) { + /* + * access registers are stored in the thread structure + */ + offset = addr - (addr_t) &dummy->regs.acrs; +#ifdef CONFIG_64BIT + /* + * Very special case: old & broken 64 bit gdb reading + * from acrs[15]. Result is a 64 bit value. Read the + * 32 bit acrs[15] value and shift it by 32. Sick... + */ + if (addr == (addr_t) &dummy->regs.acrs[15]) + tmp = ((unsigned long) child->thread.acrs[15]) << 32; + else +#endif + tmp = *(addr_t *)((addr_t) &child->thread.acrs + offset); + + } else if (addr == (addr_t) &dummy->regs.orig_gpr2) { + /* + * orig_gpr2 is stored on the kernel stack + */ + tmp = (addr_t) task_pt_regs(child)->orig_gpr2; + + } else if (addr < (addr_t) &dummy->regs.fp_regs) { + /* + * prevent reads of padding hole between + * orig_gpr2 and fp_regs on s390. + */ + tmp = 0; + + } else if (addr < (addr_t) (&dummy->regs.fp_regs + 1)) { + /* + * floating point regs. are stored in the thread structure + */ + offset = addr - (addr_t) &dummy->regs.fp_regs; + tmp = *(addr_t *)((addr_t) &child->thread.fp_regs + offset); + if (addr == (addr_t) &dummy->regs.fp_regs.fpc) + tmp &= (unsigned long) FPC_VALID_MASK + << (BITS_PER_LONG - 32); + + } else if (addr < (addr_t) (&dummy->regs.per_info + 1)) { + /* + * Handle access to the per_info structure. + */ + addr -= (addr_t) &dummy->regs.per_info; + tmp = __peek_user_per(child, addr); + + } else + tmp = 0; + + return tmp; +} + +static int +peek_user(struct task_struct *child, addr_t addr, addr_t data) +{ + addr_t tmp, mask; + + /* + * Stupid gdb peeks/pokes the access registers in 64 bit with + * an alignment of 4. Programmers from hell... + */ + mask = __ADDR_MASK; +#ifdef CONFIG_64BIT + if (addr >= (addr_t) &((struct user *) NULL)->regs.acrs && + addr < (addr_t) &((struct user *) NULL)->regs.orig_gpr2) + mask = 3; +#endif + if ((addr & mask) || addr > sizeof(struct user) - __ADDR_MASK) + return -EIO; + + tmp = __peek_user(child, addr); + return put_user(tmp, (addr_t __user *) data); +} + +static inline void __poke_user_per(struct task_struct *child, + addr_t addr, addr_t data) +{ + struct per_struct_kernel *dummy = NULL; + + /* + * There are only three fields in the per_info struct that the + * debugger user can write to. + * 1) cr9: the debugger wants to set a new PER event mask + * 2) starting_addr: the debugger wants to set a new starting + * address to use with the PER event mask. + * 3) ending_addr: the debugger wants to set a new ending + * address to use with the PER event mask. + * The user specified PER event mask and the start and end + * addresses are used only if single stepping is not in effect. + * Writes to any other field in per_info are ignored. + */ + if (addr == (addr_t) &dummy->cr9) + /* PER event mask of the user specified per set. */ + child->thread.per_user.control = + data & (PER_EVENT_MASK | PER_CONTROL_MASK); + else if (addr == (addr_t) &dummy->starting_addr) + /* Starting address of the user specified per set. */ + child->thread.per_user.start = data; + else if (addr == (addr_t) &dummy->ending_addr) + /* Ending address of the user specified per set. */ + child->thread.per_user.end = data; +} + +/* + * Write a word to the user area of a process at location addr. This + * operation does have an additional problem compared to peek_user. + * Stores to the program status word and on the floating point + * control register needs to get checked for validity. + */ +static int __poke_user(struct task_struct *child, addr_t addr, addr_t data) +{ + struct user *dummy = NULL; + addr_t offset; + + if (addr < (addr_t) &dummy->regs.acrs) { + /* + * psw and gprs are stored on the stack + */ + if (addr == (addr_t) &dummy->regs.psw.mask && + ((data & ~PSW_MASK_USER) != psw_user_bits || + ((data & PSW_MASK_EA) && !(data & PSW_MASK_BA)))) + /* Invalid psw mask. */ + return -EINVAL; + *(addr_t *)((addr_t) &task_pt_regs(child)->psw + addr) = data; + + } else if (addr < (addr_t) (&dummy->regs.orig_gpr2)) { + /* + * access registers are stored in the thread structure + */ + offset = addr - (addr_t) &dummy->regs.acrs; +#ifdef CONFIG_64BIT + /* + * Very special case: old & broken 64 bit gdb writing + * to acrs[15] with a 64 bit value. Ignore the lower + * half of the value and write the upper 32 bit to + * acrs[15]. Sick... + */ + if (addr == (addr_t) &dummy->regs.acrs[15]) + child->thread.acrs[15] = (unsigned int) (data >> 32); + else +#endif + *(addr_t *)((addr_t) &child->thread.acrs + offset) = data; + + } else if (addr == (addr_t) &dummy->regs.orig_gpr2) { + /* + * orig_gpr2 is stored on the kernel stack + */ + task_pt_regs(child)->orig_gpr2 = data; + + } else if (addr < (addr_t) &dummy->regs.fp_regs) { + /* + * prevent writes of padding hole between + * orig_gpr2 and fp_regs on s390. + */ + return 0; + + } else if (addr < (addr_t) (&dummy->regs.fp_regs + 1)) { + /* + * floating point regs. are stored in the thread structure + */ + if (addr == (addr_t) &dummy->regs.fp_regs.fpc && + (data & ~((unsigned long) FPC_VALID_MASK + << (BITS_PER_LONG - 32))) != 0) + return -EINVAL; + offset = addr - (addr_t) &dummy->regs.fp_regs; + *(addr_t *)((addr_t) &child->thread.fp_regs + offset) = data; + + } else if (addr < (addr_t) (&dummy->regs.per_info + 1)) { + /* + * Handle access to the per_info structure. + */ + addr -= (addr_t) &dummy->regs.per_info; + __poke_user_per(child, addr, data); + + } + + return 0; +} + +static int poke_user(struct task_struct *child, addr_t addr, addr_t data) +{ + addr_t mask; + + /* + * Stupid gdb peeks/pokes the access registers in 64 bit with + * an alignment of 4. Programmers from hell indeed... + */ + mask = __ADDR_MASK; +#ifdef CONFIG_64BIT + if (addr >= (addr_t) &((struct user *) NULL)->regs.acrs && + addr < (addr_t) &((struct user *) NULL)->regs.orig_gpr2) + mask = 3; +#endif + if ((addr & mask) || addr > sizeof(struct user) - __ADDR_MASK) + return -EIO; + + return __poke_user(child, addr, data); +} + +long arch_ptrace(struct task_struct *child, long request, + unsigned long addr, unsigned long data) +{ + ptrace_area parea; + int copied, ret; + + switch (request) { + case PTRACE_PEEKUSR: + /* read the word at location addr in the USER area. */ + return peek_user(child, addr, data); + + case PTRACE_POKEUSR: + /* write the word at location addr in the USER area */ + return poke_user(child, addr, data); + + case PTRACE_PEEKUSR_AREA: + case PTRACE_POKEUSR_AREA: + if (copy_from_user(&parea, (void __force __user *) addr, + sizeof(parea))) + return -EFAULT; + addr = parea.kernel_addr; + data = parea.process_addr; + copied = 0; + while (copied < parea.len) { + if (request == PTRACE_PEEKUSR_AREA) + ret = peek_user(child, addr, data); + else { + addr_t utmp; + if (get_user(utmp, + (addr_t __force __user *) data)) + return -EFAULT; + ret = poke_user(child, addr, utmp); + } + if (ret) + return ret; + addr += sizeof(unsigned long); + data += sizeof(unsigned long); + copied += sizeof(unsigned long); + } + return 0; + case PTRACE_GET_LAST_BREAK: + put_user(task_thread_info(child)->last_break, + (unsigned long __user *) data); + return 0; + default: + /* Removing high order bit from addr (only for 31 bit). */ + addr &= PSW_ADDR_INSN; + return ptrace_request(child, request, addr, data); + } +} + +#ifdef CONFIG_COMPAT +/* + * Now the fun part starts... a 31 bit program running in the + * 31 bit emulation tracing another program. PTRACE_PEEKTEXT, + * PTRACE_PEEKDATA, PTRACE_POKETEXT and PTRACE_POKEDATA are easy + * to handle, the difference to the 64 bit versions of the requests + * is that the access is done in multiples of 4 byte instead of + * 8 bytes (sizeof(unsigned long) on 31/64 bit). + * The ugly part are PTRACE_PEEKUSR, PTRACE_PEEKUSR_AREA, + * PTRACE_POKEUSR and PTRACE_POKEUSR_AREA. If the traced program + * is a 31 bit program too, the content of struct user can be + * emulated. A 31 bit program peeking into the struct user of + * a 64 bit program is a no-no. + */ + +/* + * Same as peek_user_per but for a 31 bit program. + */ +static inline __u32 __peek_user_per_compat(struct task_struct *child, + addr_t addr) +{ + struct compat_per_struct_kernel *dummy32 = NULL; + + if (addr == (addr_t) &dummy32->cr9) + /* Control bits of the active per set. */ + return (__u32) test_thread_flag(TIF_SINGLE_STEP) ? + PER_EVENT_IFETCH : child->thread.per_user.control; + else if (addr == (addr_t) &dummy32->cr10) + /* Start address of the active per set. */ + return (__u32) test_thread_flag(TIF_SINGLE_STEP) ? + 0 : child->thread.per_user.start; + else if (addr == (addr_t) &dummy32->cr11) + /* End address of the active per set. */ + return test_thread_flag(TIF_SINGLE_STEP) ? + PSW32_ADDR_INSN : child->thread.per_user.end; + else if (addr == (addr_t) &dummy32->bits) + /* Single-step bit. */ + return (__u32) test_thread_flag(TIF_SINGLE_STEP) ? + 0x80000000 : 0; + else if (addr == (addr_t) &dummy32->starting_addr) + /* Start address of the user specified per set. */ + return (__u32) child->thread.per_user.start; + else if (addr == (addr_t) &dummy32->ending_addr) + /* End address of the user specified per set. */ + return (__u32) child->thread.per_user.end; + else if (addr == (addr_t) &dummy32->perc_atmid) + /* PER code, ATMID and AI of the last PER trap */ + return (__u32) child->thread.per_event.cause << 16; + else if (addr == (addr_t) &dummy32->address) + /* Address of the last PER trap */ + return (__u32) child->thread.per_event.address; + else if (addr == (addr_t) &dummy32->access_id) + /* Access id of the last PER trap */ + return (__u32) child->thread.per_event.paid << 24; + return 0; +} + +/* + * Same as peek_user but for a 31 bit program. + */ +static u32 __peek_user_compat(struct task_struct *child, addr_t addr) +{ + struct compat_user *dummy32 = NULL; + addr_t offset; + __u32 tmp; + + if (addr < (addr_t) &dummy32->regs.acrs) { + struct pt_regs *regs = task_pt_regs(child); + /* + * psw and gprs are stored on the stack + */ + if (addr == (addr_t) &dummy32->regs.psw.mask) { + /* Fake a 31 bit psw mask. */ + tmp = (__u32)(regs->psw.mask >> 32); + tmp = psw32_user_bits | (tmp & PSW32_MASK_USER); + } else if (addr == (addr_t) &dummy32->regs.psw.addr) { + /* Fake a 31 bit psw address. */ + tmp = (__u32) regs->psw.addr | + (__u32)(regs->psw.mask & PSW_MASK_BA); + } else { + /* gpr 0-15 */ + tmp = *(__u32 *)((addr_t) ®s->psw + addr*2 + 4); + } + } else if (addr < (addr_t) (&dummy32->regs.orig_gpr2)) { + /* + * access registers are stored in the thread structure + */ + offset = addr - (addr_t) &dummy32->regs.acrs; + tmp = *(__u32*)((addr_t) &child->thread.acrs + offset); + + } else if (addr == (addr_t) (&dummy32->regs.orig_gpr2)) { + /* + * orig_gpr2 is stored on the kernel stack + */ + tmp = *(__u32*)((addr_t) &task_pt_regs(child)->orig_gpr2 + 4); + + } else if (addr < (addr_t) &dummy32->regs.fp_regs) { + /* + * prevent reads of padding hole between + * orig_gpr2 and fp_regs on s390. + */ + tmp = 0; + + } else if (addr < (addr_t) (&dummy32->regs.fp_regs + 1)) { + /* + * floating point regs. are stored in the thread structure + */ + offset = addr - (addr_t) &dummy32->regs.fp_regs; + tmp = *(__u32 *)((addr_t) &child->thread.fp_regs + offset); + + } else if (addr < (addr_t) (&dummy32->regs.per_info + 1)) { + /* + * Handle access to the per_info structure. + */ + addr -= (addr_t) &dummy32->regs.per_info; + tmp = __peek_user_per_compat(child, addr); + + } else + tmp = 0; + + return tmp; +} + +static int peek_user_compat(struct task_struct *child, + addr_t addr, addr_t data) +{ + __u32 tmp; + + if (!is_compat_task() || (addr & 3) || addr > sizeof(struct user) - 3) + return -EIO; + + tmp = __peek_user_compat(child, addr); + return put_user(tmp, (__u32 __user *) data); +} + +/* + * Same as poke_user_per but for a 31 bit program. + */ +static inline void __poke_user_per_compat(struct task_struct *child, + addr_t addr, __u32 data) +{ + struct compat_per_struct_kernel *dummy32 = NULL; + + if (addr == (addr_t) &dummy32->cr9) + /* PER event mask of the user specified per set. */ + child->thread.per_user.control = + data & (PER_EVENT_MASK | PER_CONTROL_MASK); + else if (addr == (addr_t) &dummy32->starting_addr) + /* Starting address of the user specified per set. */ + child->thread.per_user.start = data; + else if (addr == (addr_t) &dummy32->ending_addr) + /* Ending address of the user specified per set. */ + child->thread.per_user.end = data; +} + +/* + * Same as poke_user but for a 31 bit program. + */ +static int __poke_user_compat(struct task_struct *child, + addr_t addr, addr_t data) +{ + struct compat_user *dummy32 = NULL; + __u32 tmp = (__u32) data; + addr_t offset; + + if (addr < (addr_t) &dummy32->regs.acrs) { + struct pt_regs *regs = task_pt_regs(child); + /* + * psw, gprs, acrs and orig_gpr2 are stored on the stack + */ + if (addr == (addr_t) &dummy32->regs.psw.mask) { + /* Build a 64 bit psw mask from 31 bit mask. */ + if ((tmp & ~PSW32_MASK_USER) != psw32_user_bits) + /* Invalid psw mask. */ + return -EINVAL; + regs->psw.mask = (regs->psw.mask & ~PSW_MASK_USER) | + (regs->psw.mask & PSW_MASK_BA) | + (__u64)(tmp & PSW32_MASK_USER) << 32; + } else if (addr == (addr_t) &dummy32->regs.psw.addr) { + /* Build a 64 bit psw address from 31 bit address. */ + regs->psw.addr = (__u64) tmp & PSW32_ADDR_INSN; + /* Transfer 31 bit amode bit to psw mask. */ + regs->psw.mask = (regs->psw.mask & ~PSW_MASK_BA) | + (__u64)(tmp & PSW32_ADDR_AMODE); + } else { + /* gpr 0-15 */ + *(__u32*)((addr_t) ®s->psw + addr*2 + 4) = tmp; + } + } else if (addr < (addr_t) (&dummy32->regs.orig_gpr2)) { + /* + * access registers are stored in the thread structure + */ + offset = addr - (addr_t) &dummy32->regs.acrs; + *(__u32*)((addr_t) &child->thread.acrs + offset) = tmp; + + } else if (addr == (addr_t) (&dummy32->regs.orig_gpr2)) { + /* + * orig_gpr2 is stored on the kernel stack + */ + *(__u32*)((addr_t) &task_pt_regs(child)->orig_gpr2 + 4) = tmp; + + } else if (addr < (addr_t) &dummy32->regs.fp_regs) { + /* + * prevent writess of padding hole between + * orig_gpr2 and fp_regs on s390. + */ + return 0; + + } else if (addr < (addr_t) (&dummy32->regs.fp_regs + 1)) { + /* + * floating point regs. are stored in the thread structure + */ + if (addr == (addr_t) &dummy32->regs.fp_regs.fpc && + (tmp & ~FPC_VALID_MASK) != 0) + /* Invalid floating point control. */ + return -EINVAL; + offset = addr - (addr_t) &dummy32->regs.fp_regs; + *(__u32 *)((addr_t) &child->thread.fp_regs + offset) = tmp; + + } else if (addr < (addr_t) (&dummy32->regs.per_info + 1)) { + /* + * Handle access to the per_info structure. + */ + addr -= (addr_t) &dummy32->regs.per_info; + __poke_user_per_compat(child, addr, data); + } + + return 0; +} + +static int poke_user_compat(struct task_struct *child, + addr_t addr, addr_t data) +{ + if (!is_compat_task() || (addr & 3) || + addr > sizeof(struct compat_user) - 3) + return -EIO; + + return __poke_user_compat(child, addr, data); +} + +long compat_arch_ptrace(struct task_struct *child, compat_long_t request, + compat_ulong_t caddr, compat_ulong_t cdata) +{ + unsigned long addr = caddr; + unsigned long data = cdata; + compat_ptrace_area parea; + int copied, ret; + + switch (request) { + case PTRACE_PEEKUSR: + /* read the word at location addr in the USER area. */ + return peek_user_compat(child, addr, data); + + case PTRACE_POKEUSR: + /* write the word at location addr in the USER area */ + return poke_user_compat(child, addr, data); + + case PTRACE_PEEKUSR_AREA: + case PTRACE_POKEUSR_AREA: + if (copy_from_user(&parea, (void __force __user *) addr, + sizeof(parea))) + return -EFAULT; + addr = parea.kernel_addr; + data = parea.process_addr; + copied = 0; + while (copied < parea.len) { + if (request == PTRACE_PEEKUSR_AREA) + ret = peek_user_compat(child, addr, data); + else { + __u32 utmp; + if (get_user(utmp, + (__u32 __force __user *) data)) + return -EFAULT; + ret = poke_user_compat(child, addr, utmp); + } + if (ret) + return ret; + addr += sizeof(unsigned int); + data += sizeof(unsigned int); + copied += sizeof(unsigned int); + } + return 0; + case PTRACE_GET_LAST_BREAK: + put_user(task_thread_info(child)->last_break, + (unsigned int __user *) data); + return 0; + } + return compat_ptrace_request(child, request, addr, data); +} +#endif + +asmlinkage long do_syscall_trace_enter(struct pt_regs *regs) +{ + long ret = 0; + + /* Do the secure computing check first. */ + secure_computing(regs->gprs[2]); + + /* + * The sysc_tracesys code in entry.S stored the system + * call number to gprs[2]. + */ + if (test_thread_flag(TIF_SYSCALL_TRACE) && + (tracehook_report_syscall_entry(regs) || + regs->gprs[2] >= NR_syscalls)) { + /* + * Tracing decided this syscall should not happen or the + * debugger stored an invalid system call number. Skip + * the system call and the system call restart handling. + */ + clear_thread_flag(TIF_SYSCALL); + ret = -1; + } + + if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT))) + trace_sys_enter(regs, regs->gprs[2]); + + audit_syscall_entry(is_compat_task() ? + AUDIT_ARCH_S390 : AUDIT_ARCH_S390X, + regs->gprs[2], regs->orig_gpr2, + regs->gprs[3], regs->gprs[4], + regs->gprs[5]); + return ret ?: regs->gprs[2]; +} + +asmlinkage void do_syscall_trace_exit(struct pt_regs *regs) +{ + audit_syscall_exit(regs); + + if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT))) + trace_sys_exit(regs, regs->gprs[2]); + + if (test_thread_flag(TIF_SYSCALL_TRACE)) + tracehook_report_syscall_exit(regs, 0); +} + +/* + * user_regset definitions. + */ + +static int s390_regs_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + if (target == current) + save_access_regs(target->thread.acrs); + + if (kbuf) { + unsigned long *k = kbuf; + while (count > 0) { + *k++ = __peek_user(target, pos); + count -= sizeof(*k); + pos += sizeof(*k); + } + } else { + unsigned long __user *u = ubuf; + while (count > 0) { + if (__put_user(__peek_user(target, pos), u++)) + return -EFAULT; + count -= sizeof(*u); + pos += sizeof(*u); + } + } + return 0; +} + +static int s390_regs_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + int rc = 0; + + if (target == current) + save_access_regs(target->thread.acrs); + + if (kbuf) { + const unsigned long *k = kbuf; + while (count > 0 && !rc) { + rc = __poke_user(target, pos, *k++); + count -= sizeof(*k); + pos += sizeof(*k); + } + } else { + const unsigned long __user *u = ubuf; + while (count > 0 && !rc) { + unsigned long word; + rc = __get_user(word, u++); + if (rc) + break; + rc = __poke_user(target, pos, word); + count -= sizeof(*u); + pos += sizeof(*u); + } + } + + if (rc == 0 && target == current) + restore_access_regs(target->thread.acrs); + + return rc; +} + +static int s390_fpregs_get(struct task_struct *target, + const struct user_regset *regset, unsigned int pos, + unsigned int count, void *kbuf, void __user *ubuf) +{ + if (target == current) + save_fp_regs(&target->thread.fp_regs); + + return user_regset_copyout(&pos, &count, &kbuf, &ubuf, + &target->thread.fp_regs, 0, -1); +} + +static int s390_fpregs_set(struct task_struct *target, + const struct user_regset *regset, unsigned int pos, + unsigned int count, const void *kbuf, + const void __user *ubuf) +{ + int rc = 0; + + if (target == current) + save_fp_regs(&target->thread.fp_regs); + + /* If setting FPC, must validate it first. */ + if (count > 0 && pos < offsetof(s390_fp_regs, fprs)) { + u32 fpc[2] = { target->thread.fp_regs.fpc, 0 }; + rc = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &fpc, + 0, offsetof(s390_fp_regs, fprs)); + if (rc) + return rc; + if ((fpc[0] & ~FPC_VALID_MASK) != 0 || fpc[1] != 0) + return -EINVAL; + target->thread.fp_regs.fpc = fpc[0]; + } + + if (rc == 0 && count > 0) + rc = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + target->thread.fp_regs.fprs, + offsetof(s390_fp_regs, fprs), -1); + + if (rc == 0 && target == current) + restore_fp_regs(&target->thread.fp_regs); + + return rc; +} + +#ifdef CONFIG_64BIT + +static int s390_last_break_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + if (count > 0) { + if (kbuf) { + unsigned long *k = kbuf; + *k = task_thread_info(target)->last_break; + } else { + unsigned long __user *u = ubuf; + if (__put_user(task_thread_info(target)->last_break, u)) + return -EFAULT; + } + } + return 0; +} + +static int s390_last_break_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + return 0; +} + +#endif + +static int s390_system_call_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + unsigned int *data = &task_thread_info(target)->system_call; + return user_regset_copyout(&pos, &count, &kbuf, &ubuf, + data, 0, sizeof(unsigned int)); +} + +static int s390_system_call_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + unsigned int *data = &task_thread_info(target)->system_call; + return user_regset_copyin(&pos, &count, &kbuf, &ubuf, + data, 0, sizeof(unsigned int)); +} + +static const struct user_regset s390_regsets[] = { + [REGSET_GENERAL] = { + .core_note_type = NT_PRSTATUS, + .n = sizeof(s390_regs) / sizeof(long), + .size = sizeof(long), + .align = sizeof(long), + .get = s390_regs_get, + .set = s390_regs_set, + }, + [REGSET_FP] = { + .core_note_type = NT_PRFPREG, + .n = sizeof(s390_fp_regs) / sizeof(long), + .size = sizeof(long), + .align = sizeof(long), + .get = s390_fpregs_get, + .set = s390_fpregs_set, + }, +#ifdef CONFIG_64BIT + [REGSET_LAST_BREAK] = { + .core_note_type = NT_S390_LAST_BREAK, + .n = 1, + .size = sizeof(long), + .align = sizeof(long), + .get = s390_last_break_get, + .set = s390_last_break_set, + }, +#endif + [REGSET_SYSTEM_CALL] = { + .core_note_type = NT_S390_SYSTEM_CALL, + .n = 1, + .size = sizeof(unsigned int), + .align = sizeof(unsigned int), + .get = s390_system_call_get, + .set = s390_system_call_set, + }, +}; + +static const struct user_regset_view user_s390_view = { + .name = UTS_MACHINE, + .e_machine = EM_S390, + .regsets = s390_regsets, + .n = ARRAY_SIZE(s390_regsets) +}; + +#ifdef CONFIG_COMPAT +static int s390_compat_regs_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + if (target == current) + save_access_regs(target->thread.acrs); + + if (kbuf) { + compat_ulong_t *k = kbuf; + while (count > 0) { + *k++ = __peek_user_compat(target, pos); + count -= sizeof(*k); + pos += sizeof(*k); + } + } else { + compat_ulong_t __user *u = ubuf; + while (count > 0) { + if (__put_user(__peek_user_compat(target, pos), u++)) + return -EFAULT; + count -= sizeof(*u); + pos += sizeof(*u); + } + } + return 0; +} + +static int s390_compat_regs_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + int rc = 0; + + if (target == current) + save_access_regs(target->thread.acrs); + + if (kbuf) { + const compat_ulong_t *k = kbuf; + while (count > 0 && !rc) { + rc = __poke_user_compat(target, pos, *k++); + count -= sizeof(*k); + pos += sizeof(*k); + } + } else { + const compat_ulong_t __user *u = ubuf; + while (count > 0 && !rc) { + compat_ulong_t word; + rc = __get_user(word, u++); + if (rc) + break; + rc = __poke_user_compat(target, pos, word); + count -= sizeof(*u); + pos += sizeof(*u); + } + } + + if (rc == 0 && target == current) + restore_access_regs(target->thread.acrs); + + return rc; +} + +static int s390_compat_regs_high_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + compat_ulong_t *gprs_high; + + gprs_high = (compat_ulong_t *) + &task_pt_regs(target)->gprs[pos / sizeof(compat_ulong_t)]; + if (kbuf) { + compat_ulong_t *k = kbuf; + while (count > 0) { + *k++ = *gprs_high; + gprs_high += 2; + count -= sizeof(*k); + } + } else { + compat_ulong_t __user *u = ubuf; + while (count > 0) { + if (__put_user(*gprs_high, u++)) + return -EFAULT; + gprs_high += 2; + count -= sizeof(*u); + } + } + return 0; +} + +static int s390_compat_regs_high_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + compat_ulong_t *gprs_high; + int rc = 0; + + gprs_high = (compat_ulong_t *) + &task_pt_regs(target)->gprs[pos / sizeof(compat_ulong_t)]; + if (kbuf) { + const compat_ulong_t *k = kbuf; + while (count > 0) { + *gprs_high = *k++; + *gprs_high += 2; + count -= sizeof(*k); + } + } else { + const compat_ulong_t __user *u = ubuf; + while (count > 0 && !rc) { + unsigned long word; + rc = __get_user(word, u++); + if (rc) + break; + *gprs_high = word; + *gprs_high += 2; + count -= sizeof(*u); + } + } + + return rc; +} + +static int s390_compat_last_break_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + compat_ulong_t last_break; + + if (count > 0) { + last_break = task_thread_info(target)->last_break; + if (kbuf) { + unsigned long *k = kbuf; + *k = last_break; + } else { + unsigned long __user *u = ubuf; + if (__put_user(last_break, u)) + return -EFAULT; + } + } + return 0; +} + +static int s390_compat_last_break_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + return 0; +} + +static const struct user_regset s390_compat_regsets[] = { + [REGSET_GENERAL] = { + .core_note_type = NT_PRSTATUS, + .n = sizeof(s390_compat_regs) / sizeof(compat_long_t), + .size = sizeof(compat_long_t), + .align = sizeof(compat_long_t), + .get = s390_compat_regs_get, + .set = s390_compat_regs_set, + }, + [REGSET_FP] = { + .core_note_type = NT_PRFPREG, + .n = sizeof(s390_fp_regs) / sizeof(compat_long_t), + .size = sizeof(compat_long_t), + .align = sizeof(compat_long_t), + .get = s390_fpregs_get, + .set = s390_fpregs_set, + }, + [REGSET_LAST_BREAK] = { + .core_note_type = NT_S390_LAST_BREAK, + .n = 1, + .size = sizeof(long), + .align = sizeof(long), + .get = s390_compat_last_break_get, + .set = s390_compat_last_break_set, + }, + [REGSET_SYSTEM_CALL] = { + .core_note_type = NT_S390_SYSTEM_CALL, + .n = 1, + .size = sizeof(compat_uint_t), + .align = sizeof(compat_uint_t), + .get = s390_system_call_get, + .set = s390_system_call_set, + }, + [REGSET_GENERAL_EXTENDED] = { + .core_note_type = NT_S390_HIGH_GPRS, + .n = sizeof(s390_compat_regs_high) / sizeof(compat_long_t), + .size = sizeof(compat_long_t), + .align = sizeof(compat_long_t), + .get = s390_compat_regs_high_get, + .set = s390_compat_regs_high_set, + }, +}; + +static const struct user_regset_view user_s390_compat_view = { + .name = "s390", + .e_machine = EM_S390, + .regsets = s390_compat_regsets, + .n = ARRAY_SIZE(s390_compat_regsets) +}; +#endif + +const struct user_regset_view *task_user_regset_view(struct task_struct *task) +{ +#ifdef CONFIG_COMPAT + if (test_tsk_thread_flag(task, TIF_31BIT)) + return &user_s390_compat_view; +#endif + return &user_s390_view; +} + +static const char *gpr_names[NUM_GPRS] = { + "r0", "r1", "r2", "r3", "r4", "r5", "r6", "r7", + "r8", "r9", "r10", "r11", "r12", "r13", "r14", "r15", +}; + +unsigned long regs_get_register(struct pt_regs *regs, unsigned int offset) +{ + if (offset >= NUM_GPRS) + return 0; + return regs->gprs[offset]; +} + +int regs_query_register_offset(const char *name) +{ + unsigned long offset; + + if (!name || *name != 'r') + return -EINVAL; + if (strict_strtoul(name + 1, 10, &offset)) + return -EINVAL; + if (offset >= NUM_GPRS) + return -EINVAL; + return offset; +} + +const char *regs_query_register_name(unsigned int offset) +{ + if (offset >= NUM_GPRS) + return NULL; + return gpr_names[offset]; +} + +static int regs_within_kernel_stack(struct pt_regs *regs, unsigned long addr) +{ + unsigned long ksp = kernel_stack_pointer(regs); + + return (addr & ~(THREAD_SIZE - 1)) == (ksp & ~(THREAD_SIZE - 1)); +} + +/** + * regs_get_kernel_stack_nth() - get Nth entry of the stack + * @regs:pt_regs which contains kernel stack pointer. + * @n:stack entry number. + * + * regs_get_kernel_stack_nth() returns @n th entry of the kernel stack which + * is specifined by @regs. If the @n th entry is NOT in the kernel stack, + * this returns 0. + */ +unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, unsigned int n) +{ + unsigned long addr; + + addr = kernel_stack_pointer(regs) + n * sizeof(long); + if (!regs_within_kernel_stack(regs, addr)) + return 0; + return *(unsigned long *)addr; +} diff --git a/arch/s390/kernel/reipl.S b/arch/s390/kernel/reipl.S new file mode 100644 index 00000000..ad67c214 --- /dev/null +++ b/arch/s390/kernel/reipl.S @@ -0,0 +1,93 @@ +/* + * arch/s390/kernel/reipl.S + * + * S390 version + * Copyright (C) 2000 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Author(s): Holger Smolinski (Holger.Smolinski@de.ibm.com) + */ + +#include <linux/linkage.h> +#include <asm/asm-offsets.h> + +# +# store_status: Empty implementation until kdump is supported on 31 bit +# +ENTRY(store_status) + br %r14 + +# +# do_reipl_asm +# Parameter: r2 = schid of reipl device +# +ENTRY(do_reipl_asm) + basr %r13,0 +.Lpg0: lpsw .Lnewpsw-.Lpg0(%r13) +.Lpg1: # do store status of all registers + + stm %r0,%r15,__LC_GPREGS_SAVE_AREA + stctl %c0,%c15,__LC_CREGS_SAVE_AREA + stam %a0,%a15,__LC_AREGS_SAVE_AREA + l %r10,.Ldump_pfx-.Lpg0(%r13) + mvc __LC_PREFIX_SAVE_AREA(4),0(%r10) + stckc .Lclkcmp-.Lpg0(%r13) + mvc __LC_CLOCK_COMP_SAVE_AREA(8),.Lclkcmp-.Lpg0(%r13) + stpt __LC_CPU_TIMER_SAVE_AREA + st %r13, __LC_PSW_SAVE_AREA+4 + lctl %c6,%c6,.Lall-.Lpg0(%r13) + lr %r1,%r2 + mvc __LC_PGM_NEW_PSW(8),.Lpcnew-.Lpg0(%r13) + stsch .Lschib-.Lpg0(%r13) + oi .Lschib+5-.Lpg0(%r13),0x84 +.Lecs: xi .Lschib+27-.Lpg0(%r13),0x01 + msch .Lschib-.Lpg0(%r13) + lhi %r0,5 +.Lssch: ssch .Liplorb-.Lpg0(%r13) + jz .L001 + brct %r0,.Lssch + bas %r14,.Ldisab-.Lpg0(%r13) +.L001: mvc __LC_IO_NEW_PSW(8),.Lionew-.Lpg0(%r13) +.Ltpi: lpsw .Lwaitpsw-.Lpg0(%r13) +.Lcont: c %r1,__LC_SUBCHANNEL_ID + jnz .Ltpi + clc __LC_IO_INT_PARM(4),.Liplorb-.Lpg0(%r13) + jnz .Ltpi + tsch .Liplirb-.Lpg0(%r13) + tm .Liplirb+9-.Lpg0(%r13),0xbf + jz .L002 + bas %r14,.Ldisab-.Lpg0(%r13) +.L002: tm .Liplirb+8-.Lpg0(%r13),0xf3 + jz .L003 + bas %r14,.Ldisab-.Lpg0(%r13) +.L003: st %r1,__LC_SUBCHANNEL_ID + lpsw 0 + sigp 0,0,0(6) +.Ldisab: st %r14,.Ldispsw+4-.Lpg0(%r13) + lpsw .Ldispsw-.Lpg0(%r13) + .align 8 +.Lclkcmp: .quad 0x0000000000000000 +.Lall: .long 0xff000000 +.Ldump_pfx: .long dump_prefix_page + .align 8 +.Lnewpsw: .long 0x00080000,0x80000000+.Lpg1 +.Lpcnew: .long 0x00080000,0x80000000+.Lecs +.Lionew: .long 0x00080000,0x80000000+.Lcont +.Lwaitpsw: .long 0x020a0000,0x00000000+.Ltpi +.Ldispsw: .long 0x000a0000,0x00000000 +.Liplccws: .long 0x02000000,0x60000018 + .long 0x08000008,0x20000001 +.Liplorb: .long 0x0049504c,0x0040ff80 + .long 0x00000000+.Liplccws +.Lschib: .long 0x00000000,0x00000000 + .long 0x00000000,0x00000000 + .long 0x00000000,0x00000000 + .long 0x00000000,0x00000000 + .long 0x00000000,0x00000000 + .long 0x00000000,0x00000000 +.Liplirb: .long 0x00000000,0x00000000 + .long 0x00000000,0x00000000 + .long 0x00000000,0x00000000 + .long 0x00000000,0x00000000 + .long 0x00000000,0x00000000 + .long 0x00000000,0x00000000 + .long 0x00000000,0x00000000 + .long 0x00000000,0x00000000 diff --git a/arch/s390/kernel/reipl64.S b/arch/s390/kernel/reipl64.S new file mode 100644 index 00000000..36b32658 --- /dev/null +++ b/arch/s390/kernel/reipl64.S @@ -0,0 +1,154 @@ +/* + * Copyright IBM Corp 2000,2011 + * Author(s): Holger Smolinski <Holger.Smolinski@de.ibm.com>, + * Denis Joseph Barrow, + */ + +#include <linux/linkage.h> +#include <asm/asm-offsets.h> + +# +# store_status +# +# Prerequisites to run this function: +# - Prefix register is set to zero +# - Original prefix register is stored in "dump_prefix_page" +# - Lowcore protection is off +# +ENTRY(store_status) + /* Save register one and load save area base */ + stg %r1,__LC_SAVE_AREA_RESTART + lghi %r1,SAVE_AREA_BASE + /* General purpose registers */ + stmg %r0,%r15,__LC_GPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1) + lg %r2,__LC_SAVE_AREA_RESTART + stg %r2,__LC_GPREGS_SAVE_AREA-SAVE_AREA_BASE+8(%r1) + /* Control registers */ + stctg %c0,%c15,__LC_CREGS_SAVE_AREA-SAVE_AREA_BASE(%r1) + /* Access registers */ + stam %a0,%a15,__LC_AREGS_SAVE_AREA-SAVE_AREA_BASE(%r1) + /* Floating point registers */ + std %f0, 0x00 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1) + std %f1, 0x08 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1) + std %f2, 0x10 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1) + std %f3, 0x18 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1) + std %f4, 0x20 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1) + std %f5, 0x28 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1) + std %f6, 0x30 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1) + std %f7, 0x38 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1) + std %f8, 0x40 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1) + std %f9, 0x48 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1) + std %f10,0x50 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1) + std %f11,0x58 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1) + std %f12,0x60 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1) + std %f13,0x68 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1) + std %f14,0x70 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1) + std %f15,0x78 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1) + /* Floating point control register */ + stfpc __LC_FP_CREG_SAVE_AREA-SAVE_AREA_BASE(%r1) + /* CPU timer */ + stpt __LC_CPU_TIMER_SAVE_AREA-SAVE_AREA_BASE(%r1) + /* Saved prefix register */ + larl %r2,dump_prefix_page + mvc __LC_PREFIX_SAVE_AREA-SAVE_AREA_BASE(4,%r1),0(%r2) + /* Clock comparator - seven bytes */ + larl %r2,.Lclkcmp + stckc 0(%r2) + mvc __LC_CLOCK_COMP_SAVE_AREA-SAVE_AREA_BASE + 1(7,%r1),1(%r2) + /* Program status word */ + epsw %r2,%r3 + st %r2,__LC_PSW_SAVE_AREA-SAVE_AREA_BASE + 0(%r1) + st %r3,__LC_PSW_SAVE_AREA-SAVE_AREA_BASE + 4(%r1) + larl %r2,store_status + stg %r2,__LC_PSW_SAVE_AREA-SAVE_AREA_BASE + 8(%r1) + br %r14 + + .section .bss + .align 8 +.Lclkcmp: .quad 0x0000000000000000 + .previous + +# +# do_reipl_asm +# Parameter: r2 = schid of reipl device +# + +ENTRY(do_reipl_asm) + basr %r13,0 +.Lpg0: lpswe .Lnewpsw-.Lpg0(%r13) +.Lpg1: brasl %r14,store_status + + lctlg %c6,%c6,.Lall-.Lpg0(%r13) + lgr %r1,%r2 + mvc __LC_PGM_NEW_PSW(16),.Lpcnew-.Lpg0(%r13) + stsch .Lschib-.Lpg0(%r13) + oi .Lschib+5-.Lpg0(%r13),0x84 +.Lecs: xi .Lschib+27-.Lpg0(%r13),0x01 + msch .Lschib-.Lpg0(%r13) + lghi %r0,5 +.Lssch: ssch .Liplorb-.Lpg0(%r13) + jz .L001 + brct %r0,.Lssch + bas %r14,.Ldisab-.Lpg0(%r13) +.L001: mvc __LC_IO_NEW_PSW(16),.Lionew-.Lpg0(%r13) +.Ltpi: lpswe .Lwaitpsw-.Lpg0(%r13) +.Lcont: c %r1,__LC_SUBCHANNEL_ID + jnz .Ltpi + clc __LC_IO_INT_PARM(4),.Liplorb-.Lpg0(%r13) + jnz .Ltpi + tsch .Liplirb-.Lpg0(%r13) + tm .Liplirb+9-.Lpg0(%r13),0xbf + jz .L002 + bas %r14,.Ldisab-.Lpg0(%r13) +.L002: tm .Liplirb+8-.Lpg0(%r13),0xf3 + jz .L003 + bas %r14,.Ldisab-.Lpg0(%r13) +.L003: st %r1,__LC_SUBCHANNEL_ID + lhi %r1,0 # mode 0 = esa + slr %r0,%r0 # set cpuid to zero + sigp %r1,%r0,0x12 # switch to esa mode + lpsw 0 +.Ldisab: sll %r14,1 + srl %r14,1 # need to kill hi bit to avoid specification exceptions. + st %r14,.Ldispsw+12-.Lpg0(%r13) + lpswe .Ldispsw-.Lpg0(%r13) + .align 8 +.Lall: .quad 0x00000000ff000000 + .align 16 +/* + * These addresses have to be 31 bit otherwise + * the sigp will throw a specifcation exception + * when switching to ESA mode as bit 31 be set + * in the ESA psw. + * Bit 31 of the addresses has to be 0 for the + * 31bit lpswe instruction a fact they appear to have + * omitted from the pop. + */ +.Lnewpsw: .quad 0x0000000080000000 + .quad .Lpg1 +.Lpcnew: .quad 0x0000000080000000 + .quad .Lecs +.Lionew: .quad 0x0000000080000000 + .quad .Lcont +.Lwaitpsw: .quad 0x0202000080000000 + .quad .Ltpi +.Ldispsw: .quad 0x0002000080000000 + .quad 0x0000000000000000 +.Liplccws: .long 0x02000000,0x60000018 + .long 0x08000008,0x20000001 +.Liplorb: .long 0x0049504c,0x0040ff80 + .long 0x00000000+.Liplccws +.Lschib: .long 0x00000000,0x00000000 + .long 0x00000000,0x00000000 + .long 0x00000000,0x00000000 + .long 0x00000000,0x00000000 + .long 0x00000000,0x00000000 + .long 0x00000000,0x00000000 +.Liplirb: .long 0x00000000,0x00000000 + .long 0x00000000,0x00000000 + .long 0x00000000,0x00000000 + .long 0x00000000,0x00000000 + .long 0x00000000,0x00000000 + .long 0x00000000,0x00000000 + .long 0x00000000,0x00000000 + .long 0x00000000,0x00000000 diff --git a/arch/s390/kernel/relocate_kernel.S b/arch/s390/kernel/relocate_kernel.S new file mode 100644 index 00000000..c91d70ae --- /dev/null +++ b/arch/s390/kernel/relocate_kernel.S @@ -0,0 +1,119 @@ +/* + * arch/s390/kernel/relocate_kernel.S + * + * (C) Copyright IBM Corp. 2005 + * + * Author(s): Rolf Adelsberger, + * Heiko Carstens <heiko.carstens@de.ibm.com> + * + */ + +#include <linux/linkage.h> + +/* + * moves the new kernel to its destination... + * %r2 = pointer to first kimage_entry_t + * %r3 = start address - where to jump to after the job is done... + * + * %r5 will be used as temp. storage + * %r6 holds the destination address + * %r7 = PAGE_SIZE + * %r8 holds the source address + * %r9 = PAGE_SIZE + * %r10 is a page mask + */ + + .text +ENTRY(relocate_kernel) + basr %r13,0 # base address + .base: + stnsm sys_msk-.base(%r13),0xfb # disable DAT + stctl %c0,%c15,ctlregs-.base(%r13) + stm %r0,%r15,gprregs-.base(%r13) + la %r1,load_psw-.base(%r13) + mvc 0(8,%r0),0(%r1) + la %r0,.back-.base(%r13) + st %r0,4(%r0) + oi 4(%r0),0x80 + mvc 0x68(8,%r0),0(%r1) + la %r0,.back_pgm-.base(%r13) + st %r0,0x6c(%r0) + oi 0x6c(%r0),0x80 + lhi %r0,0 + diag %r0,%r0,0x308 + .back: + basr %r13,0 + .back_base: + oi have_diag308-.back_base(%r13),0x01 + lctl %c0,%c15,ctlregs-.back_base(%r13) + lm %r0,%r15,gprregs-.back_base(%r13) + j .start_reloc + .back_pgm: + lm %r0,%r15,gprregs-.base(%r13) + .start_reloc: + lhi %r10,-1 # preparing the mask + sll %r10,12 # shift it such that it becomes 0xf000 + .top: + lhi %r7,4096 # load PAGE_SIZE in r7 + lhi %r9,4096 # load PAGE_SIZE in r9 + l %r5,0(%r2) # read another word for indirection page + ahi %r2,4 # increment pointer + tml %r5,0x1 # is it a destination page? + je .indir_check # NO, goto "indir_check" + lr %r6,%r5 # r6 = r5 + nr %r6,%r10 # mask it out and... + j .top # ...next iteration + .indir_check: + tml %r5,0x2 # is it a indirection page? + je .done_test # NO, goto "done_test" + nr %r5,%r10 # YES, mask out, + lr %r2,%r5 # move it into the right register, + j .top # and read next... + .done_test: + tml %r5,0x4 # is it the done indicator? + je .source_test # NO! Well, then it should be the source indicator... + j .done # ok, lets finish it here... + .source_test: + tml %r5,0x8 # it should be a source indicator... + je .top # NO, ignore it... + lr %r8,%r5 # r8 = r5 + nr %r8,%r10 # masking + 0: mvcle %r6,%r8,0x0 # copy PAGE_SIZE bytes from r8 to r6 - pad with 0 + jo 0b + j .top + .done: + sr %r0,%r0 # clear register r0 + la %r4,load_psw-.base(%r13) # load psw-address into the register + o %r3,4(%r4) # or load address into psw + st %r3,4(%r4) + mvc 0(8,%r0),0(%r4) # copy psw to absolute address 0 + tm have_diag308-.base(%r13),0x01 + jno .no_diag308 + diag %r0,%r0,0x308 + .no_diag308: + sr %r1,%r1 # clear %r1 + sr %r2,%r2 # clear %r2 + sigp %r1,%r2,0x12 # set cpuid to zero + lpsw 0 # hopefully start new kernel... + + .align 8 + load_psw: + .long 0x00080000,0x80000000 + sys_msk: + .quad 0 + ctlregs: + .rept 16 + .long 0 + .endr + gprregs: + .rept 16 + .long 0 + .endr + have_diag308: + .byte 0 + .align 8 + relocate_kernel_end: + .align 8 + .globl relocate_kernel_len + relocate_kernel_len: + .quad relocate_kernel_end - relocate_kernel diff --git a/arch/s390/kernel/relocate_kernel64.S b/arch/s390/kernel/relocate_kernel64.S new file mode 100644 index 00000000..7c3ce589 --- /dev/null +++ b/arch/s390/kernel/relocate_kernel64.S @@ -0,0 +1,122 @@ +/* + * arch/s390/kernel/relocate_kernel64.S + * + * (C) Copyright IBM Corp. 2005 + * + * Author(s): Rolf Adelsberger, + * Heiko Carstens <heiko.carstens@de.ibm.com> + * + */ + +#include <linux/linkage.h> + +/* + * moves the new kernel to its destination... + * %r2 = pointer to first kimage_entry_t + * %r3 = start address - where to jump to after the job is done... + * + * %r5 will be used as temp. storage + * %r6 holds the destination address + * %r7 = PAGE_SIZE + * %r8 holds the source address + * %r9 = PAGE_SIZE + * + * 0xf000 is a page_mask + */ + + .text +ENTRY(relocate_kernel) + basr %r13,0 # base address + .base: + stnsm sys_msk-.base(%r13),0xfb # disable DAT + stctg %c0,%c15,ctlregs-.base(%r13) + stmg %r0,%r15,gprregs-.base(%r13) + lghi %r0,3 + sllg %r0,%r0,31 + stg %r0,0x1d0(%r0) + la %r0,.back_pgm-.base(%r13) + stg %r0,0x1d8(%r0) + la %r1,load_psw-.base(%r13) + mvc 0(8,%r0),0(%r1) + la %r0,.back-.base(%r13) + st %r0,4(%r0) + oi 4(%r0),0x80 + lghi %r0,0 + diag %r0,%r0,0x308 + .back: + lhi %r1,1 # mode 1 = esame + sigp %r1,%r0,0x12 # switch to esame mode + sam64 # switch to 64 bit addressing mode + basr %r13,0 + .back_base: + oi have_diag308-.back_base(%r13),0x01 + lctlg %c0,%c15,ctlregs-.back_base(%r13) + lmg %r0,%r15,gprregs-.back_base(%r13) + j .top + .back_pgm: + lmg %r0,%r15,gprregs-.base(%r13) + .top: + lghi %r7,4096 # load PAGE_SIZE in r7 + lghi %r9,4096 # load PAGE_SIZE in r9 + lg %r5,0(%r2) # read another word for indirection page + aghi %r2,8 # increment pointer + tml %r5,0x1 # is it a destination page? + je .indir_check # NO, goto "indir_check" + lgr %r6,%r5 # r6 = r5 + nill %r6,0xf000 # mask it out and... + j .top # ...next iteration + .indir_check: + tml %r5,0x2 # is it a indirection page? + je .done_test # NO, goto "done_test" + nill %r5,0xf000 # YES, mask out, + lgr %r2,%r5 # move it into the right register, + j .top # and read next... + .done_test: + tml %r5,0x4 # is it the done indicator? + je .source_test # NO! Well, then it should be the source indicator... + j .done # ok, lets finish it here... + .source_test: + tml %r5,0x8 # it should be a source indicator... + je .top # NO, ignore it... + lgr %r8,%r5 # r8 = r5 + nill %r8,0xf000 # masking + 0: mvcle %r6,%r8,0x0 # copy PAGE_SIZE bytes from r8 to r6 - pad with 0 + jo 0b + j .top + .done: + sgr %r0,%r0 # clear register r0 + la %r4,load_psw-.base(%r13) # load psw-address into the register + o %r3,4(%r4) # or load address into psw + st %r3,4(%r4) + mvc 0(8,%r0),0(%r4) # copy psw to absolute address 0 + tm have_diag308-.base(%r13),0x01 + jno .no_diag308 + diag %r0,%r0,0x308 + .no_diag308: + sam31 # 31 bit mode + sr %r1,%r1 # erase register r1 + sr %r2,%r2 # erase register r2 + sigp %r1,%r2,0x12 # set cpuid to zero + lpsw 0 # hopefully start new kernel... + + .align 8 + load_psw: + .long 0x00080000,0x80000000 + sys_msk: + .quad 0 + ctlregs: + .rept 16 + .quad 0 + .endr + gprregs: + .rept 16 + .quad 0 + .endr + have_diag308: + .byte 0 + .align 8 + relocate_kernel_end: + .align 8 + .globl relocate_kernel_len + relocate_kernel_len: + .quad relocate_kernel_end - relocate_kernel diff --git a/arch/s390/kernel/s390_ksyms.c b/arch/s390/kernel/s390_ksyms.c new file mode 100644 index 00000000..57b53664 --- /dev/null +++ b/arch/s390/kernel/s390_ksyms.c @@ -0,0 +1,10 @@ +#include <linux/module.h> +#include <linux/kvm_host.h> +#include <asm/ftrace.h> + +#ifdef CONFIG_FUNCTION_TRACER +EXPORT_SYMBOL(_mcount); +#endif +#if defined(CONFIG_KVM) || defined(CONFIG_KVM_MODULE) +EXPORT_SYMBOL(sie64a); +#endif diff --git a/arch/s390/kernel/sclp.S b/arch/s390/kernel/sclp.S new file mode 100644 index 00000000..95792d84 --- /dev/null +++ b/arch/s390/kernel/sclp.S @@ -0,0 +1,353 @@ +/* + * Mini SCLP driver. + * + * Copyright IBM Corp. 2004,2009 + * + * Author(s): Peter Oberparleiter <Peter.Oberparleiter@de.ibm.com>, + * Heiko Carstens <heiko.carstens@de.ibm.com>, + * + */ + +#include <linux/linkage.h> + +LC_EXT_NEW_PSW = 0x58 # addr of ext int handler +LC_EXT_NEW_PSW_64 = 0x1b0 # addr of ext int handler 64 bit +LC_EXT_INT_PARAM = 0x80 # addr of ext int parameter +LC_EXT_INT_CODE = 0x86 # addr of ext int code +LC_AR_MODE_ID = 0xa3 + +# +# Subroutine which waits synchronously until either an external interruption +# or a timeout occurs. +# +# Parameters: +# R2 = 0 for no timeout, non-zero for timeout in (approximated) seconds +# +# Returns: +# R2 = 0 on interrupt, 2 on timeout +# R3 = external interruption parameter if R2=0 +# + +_sclp_wait_int: + stm %r6,%r15,24(%r15) # save registers + basr %r13,0 # get base register +.LbaseS1: + ahi %r15,-96 # create stack frame + la %r8,LC_EXT_NEW_PSW # register int handler + la %r9,.LextpswS1-.LbaseS1(%r13) +#ifdef CONFIG_64BIT + tm LC_AR_MODE_ID,1 + jno .Lesa1 + la %r8,LC_EXT_NEW_PSW_64 # register int handler 64 bit + la %r9,.LextpswS1_64-.LbaseS1(%r13) +.Lesa1: +#endif + mvc .LoldpswS1-.LbaseS1(16,%r13),0(%r8) + mvc 0(16,%r8),0(%r9) + lhi %r6,0x0200 # cr mask for ext int (cr0.54) + ltr %r2,%r2 + jz .LsetctS1 + ahi %r6,0x0800 # cr mask for clock int (cr0.52) + stck .LtimeS1-.LbaseS1(%r13) # initiate timeout + al %r2,.LtimeS1-.LbaseS1(%r13) + st %r2,.LtimeS1-.LbaseS1(%r13) + sckc .LtimeS1-.LbaseS1(%r13) + +.LsetctS1: + stctl %c0,%c0,.LctlS1-.LbaseS1(%r13) # enable required interrupts + l %r0,.LctlS1-.LbaseS1(%r13) + lhi %r1,~(0x200 | 0x800) # clear old values + nr %r1,%r0 + or %r1,%r6 # set new value + st %r1,.LctlS1-.LbaseS1(%r13) + lctl %c0,%c0,.LctlS1-.LbaseS1(%r13) + st %r0,.LctlS1-.LbaseS1(%r13) + lhi %r2,2 # return code for timeout +.LloopS1: + lpsw .LwaitpswS1-.LbaseS1(%r13) # wait until interrupt +.LwaitS1: + lh %r7,LC_EXT_INT_CODE + chi %r7,0x1004 # timeout? + je .LtimeoutS1 + chi %r7,0x2401 # service int? + jne .LloopS1 + sr %r2,%r2 + l %r3,LC_EXT_INT_PARAM +.LtimeoutS1: + lctl %c0,%c0,.LctlS1-.LbaseS1(%r13) # restore interrupt setting + # restore old handler + mvc 0(16,%r8),.LoldpswS1-.LbaseS1(%r13) + lm %r6,%r15,120(%r15) # restore registers + br %r14 # return to caller + + .align 8 +.LoldpswS1: + .long 0, 0, 0, 0 # old ext int PSW +.LextpswS1: + .long 0x00080000, 0x80000000+.LwaitS1 # PSW to handle ext int +#ifdef CONFIG_64BIT +.LextpswS1_64: + .quad 0x0000000180000000, .LwaitS1 # PSW to handle ext int, 64 bit +#endif +.LwaitpswS1: + .long 0x010a0000, 0x00000000+.LloopS1 # PSW to wait for ext int +.LtimeS1: + .quad 0 # current time +.LctlS1: + .long 0 # CT0 contents + +# +# Subroutine to synchronously issue a service call. +# +# Parameters: +# R2 = command word +# R3 = sccb address +# +# Returns: +# R2 = 0 on success, 1 on failure +# R3 = sccb response code if R2 = 0 +# + +_sclp_servc: + stm %r6,%r15,24(%r15) # save registers + ahi %r15,-96 # create stack frame + lr %r6,%r2 # save command word + lr %r7,%r3 # save sccb address +.LretryS2: + lhi %r2,1 # error return code + .insn rre,0xb2200000,%r6,%r7 # servc + brc 1,.LendS2 # exit if not operational + brc 8,.LnotbusyS2 # go on if not busy + sr %r2,%r2 # wait until no longer busy + bras %r14,_sclp_wait_int + j .LretryS2 # retry +.LnotbusyS2: + sr %r2,%r2 # wait until result + bras %r14,_sclp_wait_int + sr %r2,%r2 + lh %r3,6(%r7) +.LendS2: + lm %r6,%r15,120(%r15) # restore registers + br %r14 + +# +# Subroutine to set up the SCLP interface. +# +# Parameters: +# R2 = 0 to activate, non-zero to deactivate +# +# Returns: +# R2 = 0 on success, non-zero on failure +# + +_sclp_setup: + stm %r6,%r15,24(%r15) # save registers + ahi %r15,-96 # create stack frame + basr %r13,0 # get base register +.LbaseS3: + l %r6,.LsccbS0-.LbaseS3(%r13) # prepare init mask sccb + mvc 0(.LinitendS3-.LinitsccbS3,%r6),.LinitsccbS3-.LbaseS3(%r13) + ltr %r2,%r2 # initialization? + jz .LdoinitS3 # go ahead + # clear masks + xc .LinitmaskS3-.LinitsccbS3(8,%r6),.LinitmaskS3-.LinitsccbS3(%r6) +.LdoinitS3: + l %r2,.LwritemaskS3-.LbaseS3(%r13)# get command word + lr %r3,%r6 # get sccb address + bras %r14,_sclp_servc # issue service call + ltr %r2,%r2 # servc successful? + jnz .LerrorS3 + chi %r3,0x20 # write mask successful? + jne .LerrorS3 + # check masks + la %r2,.LinitmaskS3-.LinitsccbS3(%r6) + l %r1,0(%r2) # receive mask ok? + n %r1,12(%r2) + cl %r1,0(%r2) + jne .LerrorS3 + l %r1,4(%r2) # send mask ok? + n %r1,8(%r2) + cl %r1,4(%r2) + sr %r2,%r2 + je .LendS3 +.LerrorS3: + lhi %r2,1 # error return code +.LendS3: + lm %r6,%r15,120(%r15) # restore registers + br %r14 +.LwritemaskS3: + .long 0x00780005 # SCLP command for write mask +.LinitsccbS3: + .word .LinitendS3-.LinitsccbS3 + .byte 0,0,0,0 + .word 0 + .word 0 + .word 4 +.LinitmaskS3: + .long 0x80000000 + .long 0x40000000 + .long 0 + .long 0 +.LinitendS3: + +# +# Subroutine which prints a given text to the SCLP console. +# +# Parameters: +# R2 = address of nil-terminated ASCII text +# +# Returns: +# R2 = 0 on success, 1 on failure +# + +_sclp_print: + stm %r6,%r15,24(%r15) # save registers + ahi %r15,-96 # create stack frame + basr %r13,0 # get base register +.LbaseS4: + l %r8,.LsccbS0-.LbaseS4(%r13) # prepare write data sccb + mvc 0(.LmtoS4-.LwritesccbS4,%r8),.LwritesccbS4-.LbaseS4(%r13) + la %r7,.LmtoS4-.LwritesccbS4(%r8) # current mto addr + sr %r0,%r0 + l %r10,.Lascebc-.LbaseS4(%r13) # address of translation table +.LinitmtoS4: + # initialize mto + mvc 0(.LmtoendS4-.LmtoS4,%r7),.LmtoS4-.LbaseS4(%r13) + lhi %r6,.LmtoendS4-.LmtoS4 # current mto length +.LloopS4: + ic %r0,0(%r2) # get character + ahi %r2,1 + ltr %r0,%r0 # end of string? + jz .LfinalizemtoS4 + chi %r0,0x15 # end of line (NL)? + jz .LfinalizemtoS4 + stc %r0,0(%r6,%r7) # copy to mto + la %r11,0(%r6,%r7) + tr 0(1,%r11),0(%r10) # translate to EBCDIC + ahi %r6,1 + j .LloopS4 +.LfinalizemtoS4: + sth %r6,0(%r7) # update mto length + lh %r9,.LmdbS4-.LwritesccbS4(%r8) # update mdb length + ar %r9,%r6 + sth %r9,.LmdbS4-.LwritesccbS4(%r8) + lh %r9,.LevbufS4-.LwritesccbS4(%r8)# update evbuf length + ar %r9,%r6 + sth %r9,.LevbufS4-.LwritesccbS4(%r8) + lh %r9,0(%r8) # update sccb length + ar %r9,%r6 + sth %r9,0(%r8) + ar %r7,%r6 # update current mto address + ltr %r0,%r0 # more characters? + jnz .LinitmtoS4 + l %r2,.LwritedataS4-.LbaseS4(%r13)# write data + lr %r3,%r8 + bras %r14,_sclp_servc + ltr %r2,%r2 # servc successful? + jnz .LendS4 + chi %r3,0x20 # write data successful? + je .LendS4 + lhi %r2,1 # error return code +.LendS4: + lm %r6,%r15,120(%r15) # restore registers + br %r14 + +# +# Function which prints a given text to the SCLP console. +# +# Parameters: +# R2 = address of nil-terminated ASCII text +# +# Returns: +# R2 = 0 on success, 1 on failure +# + +ENTRY(_sclp_print_early) + stm %r6,%r15,24(%r15) # save registers + ahi %r15,-96 # create stack frame +#ifdef CONFIG_64BIT + tm LC_AR_MODE_ID,1 + jno .Lesa2 + ahi %r15,-80 + stmh %r6,%r15,96(%r15) # store upper register halves +.Lesa2: +#endif + lr %r10,%r2 # save string pointer + lhi %r2,0 + bras %r14,_sclp_setup # enable console + ltr %r2,%r2 + jnz .LendS5 + lr %r2,%r10 + bras %r14,_sclp_print # print string + ltr %r2,%r2 + jnz .LendS5 + lhi %r2,1 + bras %r14,_sclp_setup # disable console +.LendS5: +#ifdef CONFIG_64BIT + tm LC_AR_MODE_ID,1 + jno .Lesa3 + lmh %r6,%r15,96(%r15) # store upper register halves + ahi %r15,80 +.Lesa3: +#endif + lm %r6,%r15,120(%r15) # restore registers + br %r14 + +.LwritedataS4: + .long 0x00760005 # SCLP command for write data +.LwritesccbS4: + # sccb + .word .LmtoS4-.LwritesccbS4 + .byte 0 + .byte 0,0,0 + .word 0 + + # evbuf +.LevbufS4: + .word .LmtoS4-.LevbufS4 + .byte 0x02 + .byte 0 + .word 0 + +.LmdbS4: + # mdb + .word .LmtoS4-.LmdbS4 + .word 1 + .long 0xd4c4c240 + .long 1 + + # go +.LgoS4: + .word .LmtoS4-.LgoS4 + .word 1 + .long 0 + .byte 0,0,0,0,0,0,0,0 + .byte 0,0,0 + .byte 0 + .byte 0,0,0,0,0,0,0 + .byte 0 + .word 0 + .byte 0,0,0,0,0,0,0,0,0,0 + .byte 0,0,0,0,0,0,0,0 + .byte 0,0,0,0,0,0,0,0 + +.LmtoS4: + .word .LmtoendS4-.LmtoS4 + .word 4 + .word 0x1000 + .byte 0 + .byte 0,0,0 +.LmtoendS4: + + # Global constants +.LsccbS0: + .long _sclp_work_area +.Lascebc: + .long _ascebc + +.section .data,"aw",@progbits + .balign 4096 +_sclp_work_area: + .fill 4096 +.previous diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c new file mode 100644 index 00000000..06264ae8 --- /dev/null +++ b/arch/s390/kernel/setup.c @@ -0,0 +1,1092 @@ +/* + * arch/s390/kernel/setup.c + * + * S390 version + * Copyright (C) IBM Corp. 1999,2012 + * Author(s): Hartmut Penner (hp@de.ibm.com), + * Martin Schwidefsky (schwidefsky@de.ibm.com) + * + * Derived from "arch/i386/kernel/setup.c" + * Copyright (C) 1995, Linus Torvalds + */ + +/* + * This file handles the architecture-dependent parts of initialization + */ + +#define KMSG_COMPONENT "setup" +#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt + +#include <linux/errno.h> +#include <linux/module.h> +#include <linux/sched.h> +#include <linux/kernel.h> +#include <linux/memblock.h> +#include <linux/mm.h> +#include <linux/stddef.h> +#include <linux/unistd.h> +#include <linux/ptrace.h> +#include <linux/user.h> +#include <linux/tty.h> +#include <linux/ioport.h> +#include <linux/delay.h> +#include <linux/init.h> +#include <linux/initrd.h> +#include <linux/bootmem.h> +#include <linux/root_dev.h> +#include <linux/console.h> +#include <linux/kernel_stat.h> +#include <linux/device.h> +#include <linux/notifier.h> +#include <linux/pfn.h> +#include <linux/ctype.h> +#include <linux/reboot.h> +#include <linux/topology.h> +#include <linux/ftrace.h> +#include <linux/kexec.h> +#include <linux/crash_dump.h> +#include <linux/memory.h> +#include <linux/compat.h> + +#include <asm/ipl.h> +#include <asm/uaccess.h> +#include <asm/facility.h> +#include <asm/smp.h> +#include <asm/mmu_context.h> +#include <asm/cpcmd.h> +#include <asm/lowcore.h> +#include <asm/irq.h> +#include <asm/page.h> +#include <asm/ptrace.h> +#include <asm/sections.h> +#include <asm/ebcdic.h> +#include <asm/kvm_virtio.h> +#include <asm/diag.h> +#include <asm/os_info.h> +#include "entry.h" + +long psw_kernel_bits = PSW_DEFAULT_KEY | PSW_MASK_BASE | PSW_ASC_PRIMARY | + PSW_MASK_EA | PSW_MASK_BA; +long psw_user_bits = PSW_MASK_DAT | PSW_MASK_IO | PSW_MASK_EXT | + PSW_DEFAULT_KEY | PSW_MASK_BASE | PSW_MASK_MCHECK | + PSW_MASK_PSTATE | PSW_ASC_HOME; + +/* + * User copy operations. + */ +struct uaccess_ops uaccess; +EXPORT_SYMBOL(uaccess); + +/* + * Machine setup.. + */ +unsigned int console_mode = 0; +EXPORT_SYMBOL(console_mode); + +unsigned int console_devno = -1; +EXPORT_SYMBOL(console_devno); + +unsigned int console_irq = -1; +EXPORT_SYMBOL(console_irq); + +unsigned long elf_hwcap = 0; +char elf_platform[ELF_PLATFORM_SIZE]; + +struct mem_chunk __initdata memory_chunk[MEMORY_CHUNKS]; + +int __initdata memory_end_set; +unsigned long __initdata memory_end; + +unsigned long VMALLOC_START; +EXPORT_SYMBOL(VMALLOC_START); + +unsigned long VMALLOC_END; +EXPORT_SYMBOL(VMALLOC_END); + +struct page *vmemmap; +EXPORT_SYMBOL(vmemmap); + +/* An array with a pointer to the lowcore of every CPU. */ +struct _lowcore *lowcore_ptr[NR_CPUS]; +EXPORT_SYMBOL(lowcore_ptr); + +/* + * This is set up by the setup-routine at boot-time + * for S390 need to find out, what we have to setup + * using address 0x10400 ... + */ + +#include <asm/setup.h> + +/* + * condev= and conmode= setup parameter. + */ + +static int __init condev_setup(char *str) +{ + int vdev; + + vdev = simple_strtoul(str, &str, 0); + if (vdev >= 0 && vdev < 65536) { + console_devno = vdev; + console_irq = -1; + } + return 1; +} + +__setup("condev=", condev_setup); + +static void __init set_preferred_console(void) +{ + if (MACHINE_IS_KVM) + add_preferred_console("hvc", 0, NULL); + else if (CONSOLE_IS_3215 || CONSOLE_IS_SCLP) + add_preferred_console("ttyS", 0, NULL); + else if (CONSOLE_IS_3270) + add_preferred_console("tty3270", 0, NULL); +} + +static int __init conmode_setup(char *str) +{ +#if defined(CONFIG_SCLP_CONSOLE) || defined(CONFIG_SCLP_VT220_CONSOLE) + if (strncmp(str, "hwc", 4) == 0 || strncmp(str, "sclp", 5) == 0) + SET_CONSOLE_SCLP; +#endif +#if defined(CONFIG_TN3215_CONSOLE) + if (strncmp(str, "3215", 5) == 0) + SET_CONSOLE_3215; +#endif +#if defined(CONFIG_TN3270_CONSOLE) + if (strncmp(str, "3270", 5) == 0) + SET_CONSOLE_3270; +#endif + set_preferred_console(); + return 1; +} + +__setup("conmode=", conmode_setup); + +static void __init conmode_default(void) +{ + char query_buffer[1024]; + char *ptr; + + if (MACHINE_IS_VM) { + cpcmd("QUERY CONSOLE", query_buffer, 1024, NULL); + console_devno = simple_strtoul(query_buffer + 5, NULL, 16); + ptr = strstr(query_buffer, "SUBCHANNEL ="); + console_irq = simple_strtoul(ptr + 13, NULL, 16); + cpcmd("QUERY TERM", query_buffer, 1024, NULL); + ptr = strstr(query_buffer, "CONMODE"); + /* + * Set the conmode to 3215 so that the device recognition + * will set the cu_type of the console to 3215. If the + * conmode is 3270 and we don't set it back then both + * 3215 and the 3270 driver will try to access the console + * device (3215 as console and 3270 as normal tty). + */ + cpcmd("TERM CONMODE 3215", NULL, 0, NULL); + if (ptr == NULL) { +#if defined(CONFIG_SCLP_CONSOLE) || defined(CONFIG_SCLP_VT220_CONSOLE) + SET_CONSOLE_SCLP; +#endif + return; + } + if (strncmp(ptr + 8, "3270", 4) == 0) { +#if defined(CONFIG_TN3270_CONSOLE) + SET_CONSOLE_3270; +#elif defined(CONFIG_TN3215_CONSOLE) + SET_CONSOLE_3215; +#elif defined(CONFIG_SCLP_CONSOLE) || defined(CONFIG_SCLP_VT220_CONSOLE) + SET_CONSOLE_SCLP; +#endif + } else if (strncmp(ptr + 8, "3215", 4) == 0) { +#if defined(CONFIG_TN3215_CONSOLE) + SET_CONSOLE_3215; +#elif defined(CONFIG_TN3270_CONSOLE) + SET_CONSOLE_3270; +#elif defined(CONFIG_SCLP_CONSOLE) || defined(CONFIG_SCLP_VT220_CONSOLE) + SET_CONSOLE_SCLP; +#endif + } + } else { +#if defined(CONFIG_SCLP_CONSOLE) || defined(CONFIG_SCLP_VT220_CONSOLE) + SET_CONSOLE_SCLP; +#endif + } +} + +#ifdef CONFIG_ZFCPDUMP +static void __init setup_zfcpdump(unsigned int console_devno) +{ + static char str[41]; + + if (ipl_info.type != IPL_TYPE_FCP_DUMP) + return; + if (OLDMEM_BASE) + return; + if (console_devno != -1) + sprintf(str, " cio_ignore=all,!0.0.%04x,!0.0.%04x", + ipl_info.data.fcp.dev_id.devno, console_devno); + else + sprintf(str, " cio_ignore=all,!0.0.%04x", + ipl_info.data.fcp.dev_id.devno); + strcat(boot_command_line, str); + console_loglevel = 2; +} +#else +static inline void setup_zfcpdump(unsigned int console_devno) {} +#endif /* CONFIG_ZFCPDUMP */ + + /* + * Reboot, halt and power_off stubs. They just call _machine_restart, + * _machine_halt or _machine_power_off. + */ + +void machine_restart(char *command) +{ + if ((!in_interrupt() && !in_atomic()) || oops_in_progress) + /* + * Only unblank the console if we are called in enabled + * context or a bust_spinlocks cleared the way for us. + */ + console_unblank(); + _machine_restart(command); +} + +void machine_halt(void) +{ + if (!in_interrupt() || oops_in_progress) + /* + * Only unblank the console if we are called in enabled + * context or a bust_spinlocks cleared the way for us. + */ + console_unblank(); + _machine_halt(); +} + +void machine_power_off(void) +{ + if (!in_interrupt() || oops_in_progress) + /* + * Only unblank the console if we are called in enabled + * context or a bust_spinlocks cleared the way for us. + */ + console_unblank(); + _machine_power_off(); +} + +/* + * Dummy power off function. + */ +void (*pm_power_off)(void) = machine_power_off; + +static int __init early_parse_mem(char *p) +{ + memory_end = memparse(p, &p); + memory_end_set = 1; + return 0; +} +early_param("mem", early_parse_mem); + +static int __init parse_vmalloc(char *arg) +{ + if (!arg) + return -EINVAL; + VMALLOC_END = (memparse(arg, &arg) + PAGE_SIZE - 1) & PAGE_MASK; + return 0; +} +early_param("vmalloc", parse_vmalloc); + +unsigned int user_mode = HOME_SPACE_MODE; +EXPORT_SYMBOL_GPL(user_mode); + +static int set_amode_primary(void) +{ + psw_kernel_bits = (psw_kernel_bits & ~PSW_MASK_ASC) | PSW_ASC_HOME; + psw_user_bits = (psw_user_bits & ~PSW_MASK_ASC) | PSW_ASC_PRIMARY; +#ifdef CONFIG_COMPAT + psw32_user_bits = + (psw32_user_bits & ~PSW32_MASK_ASC) | PSW32_ASC_PRIMARY; +#endif + + if (MACHINE_HAS_MVCOS) { + memcpy(&uaccess, &uaccess_mvcos_switch, sizeof(uaccess)); + return 1; + } else { + memcpy(&uaccess, &uaccess_pt, sizeof(uaccess)); + return 0; + } +} + +/* + * Switch kernel/user addressing modes? + */ +static int __init early_parse_switch_amode(char *p) +{ + user_mode = PRIMARY_SPACE_MODE; + return 0; +} +early_param("switch_amode", early_parse_switch_amode); + +static int __init early_parse_user_mode(char *p) +{ + if (p && strcmp(p, "primary") == 0) + user_mode = PRIMARY_SPACE_MODE; + else if (!p || strcmp(p, "home") == 0) + user_mode = HOME_SPACE_MODE; + else + return 1; + return 0; +} +early_param("user_mode", early_parse_user_mode); + +static void setup_addressing_mode(void) +{ + if (user_mode == PRIMARY_SPACE_MODE) { + if (set_amode_primary()) + pr_info("Address spaces switched, " + "mvcos available\n"); + else + pr_info("Address spaces switched, " + "mvcos not available\n"); + } +} + +void *restart_stack __attribute__((__section__(".data"))); + +static void __init setup_lowcore(void) +{ + struct _lowcore *lc; + + /* + * Setup lowcore for boot cpu + */ + BUILD_BUG_ON(sizeof(struct _lowcore) != LC_PAGES * 4096); + lc = __alloc_bootmem_low(LC_PAGES * PAGE_SIZE, LC_PAGES * PAGE_SIZE, 0); + lc->restart_psw.mask = psw_kernel_bits; + lc->restart_psw.addr = + PSW_ADDR_AMODE | (unsigned long) restart_int_handler; + lc->external_new_psw.mask = psw_kernel_bits | + PSW_MASK_DAT | PSW_MASK_MCHECK; + lc->external_new_psw.addr = + PSW_ADDR_AMODE | (unsigned long) ext_int_handler; + lc->svc_new_psw.mask = psw_kernel_bits | + PSW_MASK_DAT | PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK; + lc->svc_new_psw.addr = PSW_ADDR_AMODE | (unsigned long) system_call; + lc->program_new_psw.mask = psw_kernel_bits | + PSW_MASK_DAT | PSW_MASK_MCHECK; + lc->program_new_psw.addr = + PSW_ADDR_AMODE | (unsigned long) pgm_check_handler; + lc->mcck_new_psw.mask = psw_kernel_bits; + lc->mcck_new_psw.addr = + PSW_ADDR_AMODE | (unsigned long) mcck_int_handler; + lc->io_new_psw.mask = psw_kernel_bits | + PSW_MASK_DAT | PSW_MASK_MCHECK; + lc->io_new_psw.addr = PSW_ADDR_AMODE | (unsigned long) io_int_handler; + lc->clock_comparator = -1ULL; + lc->kernel_stack = ((unsigned long) &init_thread_union) + THREAD_SIZE; + lc->async_stack = (unsigned long) + __alloc_bootmem(ASYNC_SIZE, ASYNC_SIZE, 0) + ASYNC_SIZE; + lc->panic_stack = (unsigned long) + __alloc_bootmem(PAGE_SIZE, PAGE_SIZE, 0) + PAGE_SIZE; + lc->current_task = (unsigned long) init_thread_union.thread_info.task; + lc->thread_info = (unsigned long) &init_thread_union; + lc->machine_flags = S390_lowcore.machine_flags; + lc->stfl_fac_list = S390_lowcore.stfl_fac_list; + memcpy(lc->stfle_fac_list, S390_lowcore.stfle_fac_list, + MAX_FACILITY_BIT/8); +#ifndef CONFIG_64BIT + if (MACHINE_HAS_IEEE) { + lc->extended_save_area_addr = (__u32) + __alloc_bootmem_low(PAGE_SIZE, PAGE_SIZE, 0); + /* enable extended save area */ + __ctl_set_bit(14, 29); + } +#else + lc->vdso_per_cpu_data = (unsigned long) &lc->paste[0]; +#endif + lc->sync_enter_timer = S390_lowcore.sync_enter_timer; + lc->async_enter_timer = S390_lowcore.async_enter_timer; + lc->exit_timer = S390_lowcore.exit_timer; + lc->user_timer = S390_lowcore.user_timer; + lc->system_timer = S390_lowcore.system_timer; + lc->steal_timer = S390_lowcore.steal_timer; + lc->last_update_timer = S390_lowcore.last_update_timer; + lc->last_update_clock = S390_lowcore.last_update_clock; + lc->ftrace_func = S390_lowcore.ftrace_func; + + restart_stack = __alloc_bootmem(ASYNC_SIZE, ASYNC_SIZE, 0); + restart_stack += ASYNC_SIZE; + + /* + * Set up PSW restart to call ipl.c:do_restart(). Copy the relevant + * restart data to the absolute zero lowcore. This is necesary if + * PSW restart is done on an offline CPU that has lowcore zero. + */ + lc->restart_stack = (unsigned long) restart_stack; + lc->restart_fn = (unsigned long) do_restart; + lc->restart_data = 0; + lc->restart_source = -1UL; + memcpy(&S390_lowcore.restart_stack, &lc->restart_stack, + 4*sizeof(unsigned long)); + copy_to_absolute_zero(&S390_lowcore.restart_psw, + &lc->restart_psw, sizeof(psw_t)); + + set_prefix((u32)(unsigned long) lc); + lowcore_ptr[0] = lc; +} + +static struct resource code_resource = { + .name = "Kernel code", + .flags = IORESOURCE_BUSY | IORESOURCE_MEM, +}; + +static struct resource data_resource = { + .name = "Kernel data", + .flags = IORESOURCE_BUSY | IORESOURCE_MEM, +}; + +static struct resource bss_resource = { + .name = "Kernel bss", + .flags = IORESOURCE_BUSY | IORESOURCE_MEM, +}; + +static struct resource __initdata *standard_resources[] = { + &code_resource, + &data_resource, + &bss_resource, +}; + +static void __init setup_resources(void) +{ + struct resource *res, *std_res, *sub_res; + int i, j; + + code_resource.start = (unsigned long) &_text; + code_resource.end = (unsigned long) &_etext - 1; + data_resource.start = (unsigned long) &_etext; + data_resource.end = (unsigned long) &_edata - 1; + bss_resource.start = (unsigned long) &__bss_start; + bss_resource.end = (unsigned long) &__bss_stop - 1; + + for (i = 0; i < MEMORY_CHUNKS; i++) { + if (!memory_chunk[i].size) + continue; + if (memory_chunk[i].type == CHUNK_OLDMEM || + memory_chunk[i].type == CHUNK_CRASHK) + continue; + res = alloc_bootmem_low(sizeof(*res)); + res->flags = IORESOURCE_BUSY | IORESOURCE_MEM; + switch (memory_chunk[i].type) { + case CHUNK_READ_WRITE: + case CHUNK_CRASHK: + res->name = "System RAM"; + break; + case CHUNK_READ_ONLY: + res->name = "System ROM"; + res->flags |= IORESOURCE_READONLY; + break; + default: + res->name = "reserved"; + } + res->start = memory_chunk[i].addr; + res->end = res->start + memory_chunk[i].size - 1; + request_resource(&iomem_resource, res); + + for (j = 0; j < ARRAY_SIZE(standard_resources); j++) { + std_res = standard_resources[j]; + if (std_res->start < res->start || + std_res->start > res->end) + continue; + if (std_res->end > res->end) { + sub_res = alloc_bootmem_low(sizeof(*sub_res)); + *sub_res = *std_res; + sub_res->end = res->end; + std_res->start = res->end + 1; + request_resource(res, sub_res); + } else { + request_resource(res, std_res); + } + } + } +} + +unsigned long real_memory_size; +EXPORT_SYMBOL_GPL(real_memory_size); + +static void __init setup_memory_end(void) +{ + unsigned long vmax, vmalloc_size, tmp; + int i; + + +#ifdef CONFIG_ZFCPDUMP + if (ipl_info.type == IPL_TYPE_FCP_DUMP && !OLDMEM_BASE) { + memory_end = ZFCPDUMP_HSA_SIZE; + memory_end_set = 1; + } +#endif + real_memory_size = 0; + memory_end &= PAGE_MASK; + + /* + * Make sure all chunks are MAX_ORDER aligned so we don't need the + * extra checks that HOLES_IN_ZONE would require. + */ + for (i = 0; i < MEMORY_CHUNKS; i++) { + unsigned long start, end; + struct mem_chunk *chunk; + unsigned long align; + + chunk = &memory_chunk[i]; + align = 1UL << (MAX_ORDER + PAGE_SHIFT - 1); + start = (chunk->addr + align - 1) & ~(align - 1); + end = (chunk->addr + chunk->size) & ~(align - 1); + if (start >= end) + memset(chunk, 0, sizeof(*chunk)); + else { + chunk->addr = start; + chunk->size = end - start; + } + real_memory_size = max(real_memory_size, + chunk->addr + chunk->size); + } + + /* Choose kernel address space layout: 2, 3, or 4 levels. */ +#ifdef CONFIG_64BIT + vmalloc_size = VMALLOC_END ?: 128UL << 30; + tmp = (memory_end ?: real_memory_size) / PAGE_SIZE; + tmp = tmp * (sizeof(struct page) + PAGE_SIZE) + vmalloc_size; + if (tmp <= (1UL << 42)) + vmax = 1UL << 42; /* 3-level kernel page table */ + else + vmax = 1UL << 53; /* 4-level kernel page table */ +#else + vmalloc_size = VMALLOC_END ?: 96UL << 20; + vmax = 1UL << 31; /* 2-level kernel page table */ +#endif + /* vmalloc area is at the end of the kernel address space. */ + VMALLOC_END = vmax; + VMALLOC_START = vmax - vmalloc_size; + + /* Split remaining virtual space between 1:1 mapping & vmemmap array */ + tmp = VMALLOC_START / (PAGE_SIZE + sizeof(struct page)); + tmp = VMALLOC_START - tmp * sizeof(struct page); + tmp &= ~((vmax >> 11) - 1); /* align to page table level */ + tmp = min(tmp, 1UL << MAX_PHYSMEM_BITS); + vmemmap = (struct page *) tmp; + + /* Take care that memory_end is set and <= vmemmap */ + memory_end = min(memory_end ?: real_memory_size, tmp); + + /* Fixup memory chunk array to fit into 0..memory_end */ + for (i = 0; i < MEMORY_CHUNKS; i++) { + struct mem_chunk *chunk = &memory_chunk[i]; + + if (chunk->addr >= memory_end) { + memset(chunk, 0, sizeof(*chunk)); + continue; + } + if (chunk->addr + chunk->size > memory_end) + chunk->size = memory_end - chunk->addr; + } +} + +static void __init setup_vmcoreinfo(void) +{ +#ifdef CONFIG_KEXEC + unsigned long ptr = paddr_vmcoreinfo_note(); + + copy_to_absolute_zero(&S390_lowcore.vmcore_info, &ptr, sizeof(ptr)); +#endif +} + +#ifdef CONFIG_CRASH_DUMP + +/* + * Find suitable location for crashkernel memory + */ +static unsigned long __init find_crash_base(unsigned long crash_size, + char **msg) +{ + unsigned long crash_base; + struct mem_chunk *chunk; + int i; + + if (memory_chunk[0].size < crash_size) { + *msg = "first memory chunk must be at least crashkernel size"; + return 0; + } + if (OLDMEM_BASE && crash_size == OLDMEM_SIZE) + return OLDMEM_BASE; + + for (i = MEMORY_CHUNKS - 1; i >= 0; i--) { + chunk = &memory_chunk[i]; + if (chunk->size == 0) + continue; + if (chunk->type != CHUNK_READ_WRITE) + continue; + if (chunk->size < crash_size) + continue; + crash_base = (chunk->addr + chunk->size) - crash_size; + if (crash_base < crash_size) + continue; + if (crash_base < ZFCPDUMP_HSA_SIZE_MAX) + continue; + if (crash_base < (unsigned long) INITRD_START + INITRD_SIZE) + continue; + return crash_base; + } + *msg = "no suitable area found"; + return 0; +} + +/* + * Check if crash_base and crash_size is valid + */ +static int __init verify_crash_base(unsigned long crash_base, + unsigned long crash_size, + char **msg) +{ + struct mem_chunk *chunk; + int i; + + /* + * Because we do the swap to zero, we must have at least 'crash_size' + * bytes free space before crash_base + */ + if (crash_size > crash_base) { + *msg = "crashkernel offset must be greater than size"; + return -EINVAL; + } + + /* First memory chunk must be at least crash_size */ + if (memory_chunk[0].size < crash_size) { + *msg = "first memory chunk must be at least crashkernel size"; + return -EINVAL; + } + /* Check if we fit into the respective memory chunk */ + for (i = 0; i < MEMORY_CHUNKS; i++) { + chunk = &memory_chunk[i]; + if (chunk->size == 0) + continue; + if (crash_base < chunk->addr) + continue; + if (crash_base >= chunk->addr + chunk->size) + continue; + /* we have found the memory chunk */ + if (crash_base + crash_size > chunk->addr + chunk->size) { + *msg = "selected memory chunk is too small for " + "crashkernel memory"; + return -EINVAL; + } + return 0; + } + *msg = "invalid memory range specified"; + return -EINVAL; +} + +/* + * Reserve kdump memory by creating a memory hole in the mem_chunk array + */ +static void __init reserve_kdump_bootmem(unsigned long addr, unsigned long size, + int type) +{ + create_mem_hole(memory_chunk, addr, size, type); +} + +/* + * When kdump is enabled, we have to ensure that no memory from + * the area [0 - crashkernel memory size] and + * [crashk_res.start - crashk_res.end] is set offline. + */ +static int kdump_mem_notifier(struct notifier_block *nb, + unsigned long action, void *data) +{ + struct memory_notify *arg = data; + + if (arg->start_pfn < PFN_DOWN(resource_size(&crashk_res))) + return NOTIFY_BAD; + if (arg->start_pfn > PFN_DOWN(crashk_res.end)) + return NOTIFY_OK; + if (arg->start_pfn + arg->nr_pages - 1 < PFN_DOWN(crashk_res.start)) + return NOTIFY_OK; + return NOTIFY_BAD; +} + +static struct notifier_block kdump_mem_nb = { + .notifier_call = kdump_mem_notifier, +}; + +#endif + +/* + * Make sure that oldmem, where the dump is stored, is protected + */ +static void reserve_oldmem(void) +{ +#ifdef CONFIG_CRASH_DUMP + if (!OLDMEM_BASE) + return; + + reserve_kdump_bootmem(OLDMEM_BASE, OLDMEM_SIZE, CHUNK_OLDMEM); + reserve_kdump_bootmem(OLDMEM_SIZE, memory_end - OLDMEM_SIZE, + CHUNK_OLDMEM); + if (OLDMEM_BASE + OLDMEM_SIZE == real_memory_size) + saved_max_pfn = PFN_DOWN(OLDMEM_BASE) - 1; + else + saved_max_pfn = PFN_DOWN(real_memory_size) - 1; +#endif +} + +/* + * Reserve memory for kdump kernel to be loaded with kexec + */ +static void __init reserve_crashkernel(void) +{ +#ifdef CONFIG_CRASH_DUMP + unsigned long long crash_base, crash_size; + char *msg = NULL; + int rc; + + rc = parse_crashkernel(boot_command_line, memory_end, &crash_size, + &crash_base); + if (rc || crash_size == 0) + return; + crash_base = ALIGN(crash_base, KEXEC_CRASH_MEM_ALIGN); + crash_size = ALIGN(crash_size, KEXEC_CRASH_MEM_ALIGN); + if (register_memory_notifier(&kdump_mem_nb)) + return; + if (!crash_base) + crash_base = find_crash_base(crash_size, &msg); + if (!crash_base) { + pr_info("crashkernel reservation failed: %s\n", msg); + unregister_memory_notifier(&kdump_mem_nb); + return; + } + if (verify_crash_base(crash_base, crash_size, &msg)) { + pr_info("crashkernel reservation failed: %s\n", msg); + unregister_memory_notifier(&kdump_mem_nb); + return; + } + if (!OLDMEM_BASE && MACHINE_IS_VM) + diag10_range(PFN_DOWN(crash_base), PFN_DOWN(crash_size)); + crashk_res.start = crash_base; + crashk_res.end = crash_base + crash_size - 1; + insert_resource(&iomem_resource, &crashk_res); + reserve_kdump_bootmem(crash_base, crash_size, CHUNK_CRASHK); + pr_info("Reserving %lluMB of memory at %lluMB " + "for crashkernel (System RAM: %luMB)\n", + crash_size >> 20, crash_base >> 20, memory_end >> 20); + os_info_crashkernel_add(crash_base, crash_size); +#endif +} + +static void __init setup_memory(void) +{ + unsigned long bootmap_size; + unsigned long start_pfn, end_pfn; + int i; + + /* + * partially used pages are not usable - thus + * we are rounding upwards: + */ + start_pfn = PFN_UP(__pa(&_end)); + end_pfn = max_pfn = PFN_DOWN(memory_end); + +#ifdef CONFIG_BLK_DEV_INITRD + /* + * Move the initrd in case the bitmap of the bootmem allocater + * would overwrite it. + */ + + if (INITRD_START && INITRD_SIZE) { + unsigned long bmap_size; + unsigned long start; + + bmap_size = bootmem_bootmap_pages(end_pfn - start_pfn + 1); + bmap_size = PFN_PHYS(bmap_size); + + if (PFN_PHYS(start_pfn) + bmap_size > INITRD_START) { + start = PFN_PHYS(start_pfn) + bmap_size + PAGE_SIZE; + +#ifdef CONFIG_CRASH_DUMP + if (OLDMEM_BASE) { + /* Move initrd behind kdump oldmem */ + if (start + INITRD_SIZE > OLDMEM_BASE && + start < OLDMEM_BASE + OLDMEM_SIZE) + start = OLDMEM_BASE + OLDMEM_SIZE; + } +#endif + if (start + INITRD_SIZE > memory_end) { + pr_err("initrd extends beyond end of " + "memory (0x%08lx > 0x%08lx) " + "disabling initrd\n", + start + INITRD_SIZE, memory_end); + INITRD_START = INITRD_SIZE = 0; + } else { + pr_info("Moving initrd (0x%08lx -> " + "0x%08lx, size: %ld)\n", + INITRD_START, start, INITRD_SIZE); + memmove((void *) start, (void *) INITRD_START, + INITRD_SIZE); + INITRD_START = start; + } + } + } +#endif + + /* + * Initialize the boot-time allocator + */ + bootmap_size = init_bootmem(start_pfn, end_pfn); + + /* + * Register RAM areas with the bootmem allocator. + */ + + for (i = 0; i < MEMORY_CHUNKS && memory_chunk[i].size > 0; i++) { + unsigned long start_chunk, end_chunk, pfn; + + if (memory_chunk[i].type != CHUNK_READ_WRITE && + memory_chunk[i].type != CHUNK_CRASHK) + continue; + start_chunk = PFN_DOWN(memory_chunk[i].addr); + end_chunk = start_chunk + PFN_DOWN(memory_chunk[i].size); + end_chunk = min(end_chunk, end_pfn); + if (start_chunk >= end_chunk) + continue; + memblock_add_node(PFN_PHYS(start_chunk), + PFN_PHYS(end_chunk - start_chunk), 0); + pfn = max(start_chunk, start_pfn); + for (; pfn < end_chunk; pfn++) + page_set_storage_key(PFN_PHYS(pfn), + PAGE_DEFAULT_KEY, 0); + } + + psw_set_key(PAGE_DEFAULT_KEY); + + free_bootmem_with_active_regions(0, max_pfn); + + /* + * Reserve memory used for lowcore/command line/kernel image. + */ + reserve_bootmem(0, (unsigned long)_ehead, BOOTMEM_DEFAULT); + reserve_bootmem((unsigned long)_stext, + PFN_PHYS(start_pfn) - (unsigned long)_stext, + BOOTMEM_DEFAULT); + /* + * Reserve the bootmem bitmap itself as well. We do this in two + * steps (first step was init_bootmem()) because this catches + * the (very unlikely) case of us accidentally initializing the + * bootmem allocator with an invalid RAM area. + */ + reserve_bootmem(start_pfn << PAGE_SHIFT, bootmap_size, + BOOTMEM_DEFAULT); + +#ifdef CONFIG_CRASH_DUMP + if (crashk_res.start) + reserve_bootmem(crashk_res.start, + crashk_res.end - crashk_res.start + 1, + BOOTMEM_DEFAULT); + if (is_kdump_kernel()) + reserve_bootmem(elfcorehdr_addr - OLDMEM_BASE, + PAGE_ALIGN(elfcorehdr_size), BOOTMEM_DEFAULT); +#endif +#ifdef CONFIG_BLK_DEV_INITRD + if (INITRD_START && INITRD_SIZE) { + if (INITRD_START + INITRD_SIZE <= memory_end) { + reserve_bootmem(INITRD_START, INITRD_SIZE, + BOOTMEM_DEFAULT); + initrd_start = INITRD_START; + initrd_end = initrd_start + INITRD_SIZE; + } else { + pr_err("initrd extends beyond end of " + "memory (0x%08lx > 0x%08lx) " + "disabling initrd\n", + initrd_start + INITRD_SIZE, memory_end); + initrd_start = initrd_end = 0; + } + } +#endif +} + +/* + * Setup hardware capabilities. + */ +static void __init setup_hwcaps(void) +{ + static const int stfl_bits[6] = { 0, 2, 7, 17, 19, 21 }; + struct cpuid cpu_id; + int i; + + /* + * The store facility list bits numbers as found in the principles + * of operation are numbered with bit 1UL<<31 as number 0 to + * bit 1UL<<0 as number 31. + * Bit 0: instructions named N3, "backported" to esa-mode + * Bit 2: z/Architecture mode is active + * Bit 7: the store-facility-list-extended facility is installed + * Bit 17: the message-security assist is installed + * Bit 19: the long-displacement facility is installed + * Bit 21: the extended-immediate facility is installed + * Bit 22: extended-translation facility 3 is installed + * Bit 30: extended-translation facility 3 enhancement facility + * These get translated to: + * HWCAP_S390_ESAN3 bit 0, HWCAP_S390_ZARCH bit 1, + * HWCAP_S390_STFLE bit 2, HWCAP_S390_MSA bit 3, + * HWCAP_S390_LDISP bit 4, HWCAP_S390_EIMM bit 5 and + * HWCAP_S390_ETF3EH bit 8 (22 && 30). + */ + for (i = 0; i < 6; i++) + if (test_facility(stfl_bits[i])) + elf_hwcap |= 1UL << i; + + if (test_facility(22) && test_facility(30)) + elf_hwcap |= HWCAP_S390_ETF3EH; + + /* + * Check for additional facilities with store-facility-list-extended. + * stfle stores doublewords (8 byte) with bit 1ULL<<63 as bit 0 + * and 1ULL<<0 as bit 63. Bits 0-31 contain the same information + * as stored by stfl, bits 32-xxx contain additional facilities. + * How many facility words are stored depends on the number of + * doublewords passed to the instruction. The additional facilities + * are: + * Bit 42: decimal floating point facility is installed + * Bit 44: perform floating point operation facility is installed + * translated to: + * HWCAP_S390_DFP bit 6 (42 && 44). + */ + if ((elf_hwcap & (1UL << 2)) && test_facility(42) && test_facility(44)) + elf_hwcap |= HWCAP_S390_DFP; + + /* + * Huge page support HWCAP_S390_HPAGE is bit 7. + */ + if (MACHINE_HAS_HPAGE) + elf_hwcap |= HWCAP_S390_HPAGE; + + /* + * 64-bit register support for 31-bit processes + * HWCAP_S390_HIGH_GPRS is bit 9. + */ + elf_hwcap |= HWCAP_S390_HIGH_GPRS; + + get_cpu_id(&cpu_id); + switch (cpu_id.machine) { + case 0x9672: +#if !defined(CONFIG_64BIT) + default: /* Use "g5" as default for 31 bit kernels. */ +#endif + strcpy(elf_platform, "g5"); + break; + case 0x2064: + case 0x2066: +#if defined(CONFIG_64BIT) + default: /* Use "z900" as default for 64 bit kernels. */ +#endif + strcpy(elf_platform, "z900"); + break; + case 0x2084: + case 0x2086: + strcpy(elf_platform, "z990"); + break; + case 0x2094: + case 0x2096: + strcpy(elf_platform, "z9-109"); + break; + case 0x2097: + case 0x2098: + strcpy(elf_platform, "z10"); + break; + case 0x2817: + case 0x2818: + strcpy(elf_platform, "z196"); + break; + } +} + +/* + * Setup function called from init/main.c just after the banner + * was printed. + */ + +void __init setup_arch(char **cmdline_p) +{ + /* + * print what head.S has found out about the machine + */ +#ifndef CONFIG_64BIT + if (MACHINE_IS_VM) + pr_info("Linux is running as a z/VM " + "guest operating system in 31-bit mode\n"); + else if (MACHINE_IS_LPAR) + pr_info("Linux is running natively in 31-bit mode\n"); + if (MACHINE_HAS_IEEE) + pr_info("The hardware system has IEEE compatible " + "floating point units\n"); + else + pr_info("The hardware system has no IEEE compatible " + "floating point units\n"); +#else /* CONFIG_64BIT */ + if (MACHINE_IS_VM) + pr_info("Linux is running as a z/VM " + "guest operating system in 64-bit mode\n"); + else if (MACHINE_IS_KVM) + pr_info("Linux is running under KVM in 64-bit mode\n"); + else if (MACHINE_IS_LPAR) + pr_info("Linux is running natively in 64-bit mode\n"); +#endif /* CONFIG_64BIT */ + + /* Have one command line that is parsed and saved in /proc/cmdline */ + /* boot_command_line has been already set up in early.c */ + *cmdline_p = boot_command_line; + + ROOT_DEV = Root_RAM0; + + init_mm.start_code = PAGE_OFFSET; + init_mm.end_code = (unsigned long) &_etext; + init_mm.end_data = (unsigned long) &_edata; + init_mm.brk = (unsigned long) &_end; + + if (MACHINE_HAS_MVCOS) + memcpy(&uaccess, &uaccess_mvcos, sizeof(uaccess)); + else + memcpy(&uaccess, &uaccess_std, sizeof(uaccess)); + + parse_early_param(); + + os_info_init(); + setup_ipl(); + setup_memory_end(); + setup_addressing_mode(); + reserve_oldmem(); + reserve_crashkernel(); + setup_memory(); + setup_resources(); + setup_vmcoreinfo(); + setup_lowcore(); + + cpu_init(); + s390_init_cpu_topology(); + + /* + * Setup capabilities (ELF_HWCAP & ELF_PLATFORM). + */ + setup_hwcaps(); + + /* + * Create kernel page tables and switch to virtual addressing. + */ + paging_init(); + + /* Setup default console */ + conmode_default(); + set_preferred_console(); + + /* Setup zfcpdump support */ + setup_zfcpdump(console_devno); +} diff --git a/arch/s390/kernel/signal.c b/arch/s390/kernel/signal.c new file mode 100644 index 00000000..f7582b27 --- /dev/null +++ b/arch/s390/kernel/signal.c @@ -0,0 +1,522 @@ +/* + * arch/s390/kernel/signal.c + * + * Copyright (C) IBM Corp. 1999,2006 + * Author(s): Denis Joseph Barrow (djbarrow@de.ibm.com,barrow_dj@yahoo.com) + * + * Based on Intel version + * + * Copyright (C) 1991, 1992 Linus Torvalds + * + * 1997-11-28 Modified for POSIX.1b signals by Richard Henderson + */ + +#include <linux/sched.h> +#include <linux/mm.h> +#include <linux/smp.h> +#include <linux/kernel.h> +#include <linux/signal.h> +#include <linux/errno.h> +#include <linux/wait.h> +#include <linux/ptrace.h> +#include <linux/unistd.h> +#include <linux/stddef.h> +#include <linux/tty.h> +#include <linux/personality.h> +#include <linux/binfmts.h> +#include <linux/tracehook.h> +#include <linux/syscalls.h> +#include <linux/compat.h> +#include <asm/ucontext.h> +#include <asm/uaccess.h> +#include <asm/lowcore.h> +#include <asm/switch_to.h> +#include "entry.h" + +#define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP))) + + +typedef struct +{ + __u8 callee_used_stack[__SIGNAL_FRAMESIZE]; + struct sigcontext sc; + _sigregs sregs; + int signo; + __u8 retcode[S390_SYSCALL_SIZE]; +} sigframe; + +typedef struct +{ + __u8 callee_used_stack[__SIGNAL_FRAMESIZE]; + __u8 retcode[S390_SYSCALL_SIZE]; + struct siginfo info; + struct ucontext uc; +} rt_sigframe; + +/* + * Atomically swap in the new signal mask, and wait for a signal. + */ +SYSCALL_DEFINE3(sigsuspend, int, history0, int, history1, old_sigset_t, mask) +{ + sigset_t blocked; + + current->saved_sigmask = current->blocked; + mask &= _BLOCKABLE; + siginitset(&blocked, mask); + set_current_blocked(&blocked); + set_current_state(TASK_INTERRUPTIBLE); + schedule(); + set_restore_sigmask(); + return -ERESTARTNOHAND; +} + +SYSCALL_DEFINE3(sigaction, int, sig, const struct old_sigaction __user *, act, + struct old_sigaction __user *, oact) +{ + struct k_sigaction new_ka, old_ka; + int ret; + + if (act) { + old_sigset_t mask; + if (!access_ok(VERIFY_READ, act, sizeof(*act)) || + __get_user(new_ka.sa.sa_handler, &act->sa_handler) || + __get_user(new_ka.sa.sa_restorer, &act->sa_restorer) || + __get_user(new_ka.sa.sa_flags, &act->sa_flags) || + __get_user(mask, &act->sa_mask)) + return -EFAULT; + siginitset(&new_ka.sa.sa_mask, mask); + } + + ret = do_sigaction(sig, act ? &new_ka : NULL, oact ? &old_ka : NULL); + + if (!ret && oact) { + if (!access_ok(VERIFY_WRITE, oact, sizeof(*oact)) || + __put_user(old_ka.sa.sa_handler, &oact->sa_handler) || + __put_user(old_ka.sa.sa_restorer, &oact->sa_restorer) || + __put_user(old_ka.sa.sa_flags, &oact->sa_flags) || + __put_user(old_ka.sa.sa_mask.sig[0], &oact->sa_mask)) + return -EFAULT; + } + + return ret; +} + +SYSCALL_DEFINE2(sigaltstack, const stack_t __user *, uss, + stack_t __user *, uoss) +{ + struct pt_regs *regs = task_pt_regs(current); + return do_sigaltstack(uss, uoss, regs->gprs[15]); +} + +/* Returns non-zero on fault. */ +static int save_sigregs(struct pt_regs *regs, _sigregs __user *sregs) +{ + _sigregs user_sregs; + + save_access_regs(current->thread.acrs); + + /* Copy a 'clean' PSW mask to the user to avoid leaking + information about whether PER is currently on. */ + user_sregs.regs.psw.mask = psw_user_bits | + (regs->psw.mask & PSW_MASK_USER); + user_sregs.regs.psw.addr = regs->psw.addr; + memcpy(&user_sregs.regs.gprs, ®s->gprs, sizeof(sregs->regs.gprs)); + memcpy(&user_sregs.regs.acrs, current->thread.acrs, + sizeof(sregs->regs.acrs)); + /* + * We have to store the fp registers to current->thread.fp_regs + * to merge them with the emulated registers. + */ + save_fp_regs(¤t->thread.fp_regs); + memcpy(&user_sregs.fpregs, ¤t->thread.fp_regs, + sizeof(s390_fp_regs)); + return __copy_to_user(sregs, &user_sregs, sizeof(_sigregs)); +} + +/* Returns positive number on error */ +static int restore_sigregs(struct pt_regs *regs, _sigregs __user *sregs) +{ + int err; + _sigregs user_sregs; + + /* Alwys make any pending restarted system call return -EINTR */ + current_thread_info()->restart_block.fn = do_no_restart_syscall; + + err = __copy_from_user(&user_sregs, sregs, sizeof(_sigregs)); + if (err) + return err; + /* Use regs->psw.mask instead of psw_user_bits to preserve PER bit. */ + regs->psw.mask = (regs->psw.mask & ~PSW_MASK_USER) | + (user_sregs.regs.psw.mask & PSW_MASK_USER); + /* Check for invalid amode */ + if (regs->psw.mask & PSW_MASK_EA) + regs->psw.mask |= PSW_MASK_BA; + regs->psw.addr = user_sregs.regs.psw.addr; + memcpy(®s->gprs, &user_sregs.regs.gprs, sizeof(sregs->regs.gprs)); + memcpy(¤t->thread.acrs, &user_sregs.regs.acrs, + sizeof(sregs->regs.acrs)); + restore_access_regs(current->thread.acrs); + + memcpy(¤t->thread.fp_regs, &user_sregs.fpregs, + sizeof(s390_fp_regs)); + current->thread.fp_regs.fpc &= FPC_VALID_MASK; + + restore_fp_regs(¤t->thread.fp_regs); + clear_thread_flag(TIF_SYSCALL); /* No longer in a system call */ + return 0; +} + +SYSCALL_DEFINE0(sigreturn) +{ + struct pt_regs *regs = task_pt_regs(current); + sigframe __user *frame = (sigframe __user *)regs->gprs[15]; + sigset_t set; + + if (!access_ok(VERIFY_READ, frame, sizeof(*frame))) + goto badframe; + if (__copy_from_user(&set.sig, &frame->sc.oldmask, _SIGMASK_COPY_SIZE)) + goto badframe; + sigdelsetmask(&set, ~_BLOCKABLE); + set_current_blocked(&set); + if (restore_sigregs(regs, &frame->sregs)) + goto badframe; + return regs->gprs[2]; +badframe: + force_sig(SIGSEGV, current); + return 0; +} + +SYSCALL_DEFINE0(rt_sigreturn) +{ + struct pt_regs *regs = task_pt_regs(current); + rt_sigframe __user *frame = (rt_sigframe __user *)regs->gprs[15]; + sigset_t set; + + if (!access_ok(VERIFY_READ, frame, sizeof(*frame))) + goto badframe; + if (__copy_from_user(&set.sig, &frame->uc.uc_sigmask, sizeof(set))) + goto badframe; + sigdelsetmask(&set, ~_BLOCKABLE); + set_current_blocked(&set); + if (restore_sigregs(regs, &frame->uc.uc_mcontext)) + goto badframe; + if (do_sigaltstack(&frame->uc.uc_stack, NULL, + regs->gprs[15]) == -EFAULT) + goto badframe; + return regs->gprs[2]; +badframe: + force_sig(SIGSEGV, current); + return 0; +} + +/* + * Set up a signal frame. + */ + + +/* + * Determine which stack to use.. + */ +static inline void __user * +get_sigframe(struct k_sigaction *ka, struct pt_regs * regs, size_t frame_size) +{ + unsigned long sp; + + /* Default to using normal stack */ + sp = regs->gprs[15]; + + /* Overflow on alternate signal stack gives SIGSEGV. */ + if (on_sig_stack(sp) && !on_sig_stack((sp - frame_size) & -8UL)) + return (void __user *) -1UL; + + /* This is the X/Open sanctioned signal stack switching. */ + if (ka->sa.sa_flags & SA_ONSTACK) { + if (! sas_ss_flags(sp)) + sp = current->sas_ss_sp + current->sas_ss_size; + } + + /* This is the legacy signal stack switching. */ + else if (!user_mode(regs) && + !(ka->sa.sa_flags & SA_RESTORER) && + ka->sa.sa_restorer) { + sp = (unsigned long) ka->sa.sa_restorer; + } + + return (void __user *)((sp - frame_size) & -8ul); +} + +static inline int map_signal(int sig) +{ + if (current_thread_info()->exec_domain + && current_thread_info()->exec_domain->signal_invmap + && sig < 32) + return current_thread_info()->exec_domain->signal_invmap[sig]; + else + return sig; +} + +static int setup_frame(int sig, struct k_sigaction *ka, + sigset_t *set, struct pt_regs * regs) +{ + sigframe __user *frame; + + frame = get_sigframe(ka, regs, sizeof(sigframe)); + if (!access_ok(VERIFY_WRITE, frame, sizeof(sigframe))) + goto give_sigsegv; + + if (frame == (void __user *) -1UL) + goto give_sigsegv; + + if (__copy_to_user(&frame->sc.oldmask, &set->sig, _SIGMASK_COPY_SIZE)) + goto give_sigsegv; + + if (save_sigregs(regs, &frame->sregs)) + goto give_sigsegv; + if (__put_user(&frame->sregs, &frame->sc.sregs)) + goto give_sigsegv; + + /* Set up to return from userspace. If provided, use a stub + already in userspace. */ + if (ka->sa.sa_flags & SA_RESTORER) { + regs->gprs[14] = (unsigned long) + ka->sa.sa_restorer | PSW_ADDR_AMODE; + } else { + regs->gprs[14] = (unsigned long) + frame->retcode | PSW_ADDR_AMODE; + if (__put_user(S390_SYSCALL_OPCODE | __NR_sigreturn, + (u16 __user *)(frame->retcode))) + goto give_sigsegv; + } + + /* Set up backchain. */ + if (__put_user(regs->gprs[15], (addr_t __user *) frame)) + goto give_sigsegv; + + /* Set up registers for signal handler */ + regs->gprs[15] = (unsigned long) frame; + regs->psw.mask |= PSW_MASK_EA | PSW_MASK_BA; /* 64 bit amode */ + regs->psw.addr = (unsigned long) ka->sa.sa_handler | PSW_ADDR_AMODE; + + regs->gprs[2] = map_signal(sig); + regs->gprs[3] = (unsigned long) &frame->sc; + + /* We forgot to include these in the sigcontext. + To avoid breaking binary compatibility, they are passed as args. */ + if (sig == SIGSEGV || sig == SIGBUS || sig == SIGILL || + sig == SIGTRAP || sig == SIGFPE) { + /* set extra registers only for synchronous signals */ + regs->gprs[4] = regs->int_code & 127; + regs->gprs[5] = regs->int_parm_long; + regs->gprs[6] = task_thread_info(current)->last_break; + } + + /* Place signal number on stack to allow backtrace from handler. */ + if (__put_user(regs->gprs[2], (int __user *) &frame->signo)) + goto give_sigsegv; + return 0; + +give_sigsegv: + force_sigsegv(sig, current); + return -EFAULT; +} + +static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, + sigset_t *set, struct pt_regs * regs) +{ + int err = 0; + rt_sigframe __user *frame; + + frame = get_sigframe(ka, regs, sizeof(rt_sigframe)); + if (!access_ok(VERIFY_WRITE, frame, sizeof(rt_sigframe))) + goto give_sigsegv; + + if (frame == (void __user *) -1UL) + goto give_sigsegv; + + if (copy_siginfo_to_user(&frame->info, info)) + goto give_sigsegv; + + /* Create the ucontext. */ + err |= __put_user(0, &frame->uc.uc_flags); + err |= __put_user(NULL, &frame->uc.uc_link); + err |= __put_user((void __user *)current->sas_ss_sp, &frame->uc.uc_stack.ss_sp); + err |= __put_user(sas_ss_flags(regs->gprs[15]), + &frame->uc.uc_stack.ss_flags); + err |= __put_user(current->sas_ss_size, &frame->uc.uc_stack.ss_size); + err |= save_sigregs(regs, &frame->uc.uc_mcontext); + err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)); + if (err) + goto give_sigsegv; + + /* Set up to return from userspace. If provided, use a stub + already in userspace. */ + if (ka->sa.sa_flags & SA_RESTORER) { + regs->gprs[14] = (unsigned long) + ka->sa.sa_restorer | PSW_ADDR_AMODE; + } else { + regs->gprs[14] = (unsigned long) + frame->retcode | PSW_ADDR_AMODE; + if (__put_user(S390_SYSCALL_OPCODE | __NR_rt_sigreturn, + (u16 __user *)(frame->retcode))) + goto give_sigsegv; + } + + /* Set up backchain. */ + if (__put_user(regs->gprs[15], (addr_t __user *) frame)) + goto give_sigsegv; + + /* Set up registers for signal handler */ + regs->gprs[15] = (unsigned long) frame; + regs->psw.mask |= PSW_MASK_EA | PSW_MASK_BA; /* 64 bit amode */ + regs->psw.addr = (unsigned long) ka->sa.sa_handler | PSW_ADDR_AMODE; + + regs->gprs[2] = map_signal(sig); + regs->gprs[3] = (unsigned long) &frame->info; + regs->gprs[4] = (unsigned long) &frame->uc; + regs->gprs[5] = task_thread_info(current)->last_break; + return 0; + +give_sigsegv: + force_sigsegv(sig, current); + return -EFAULT; +} + +static int handle_signal(unsigned long sig, struct k_sigaction *ka, + siginfo_t *info, sigset_t *oldset, + struct pt_regs *regs) +{ + int ret; + + /* Set up the stack frame */ + if (ka->sa.sa_flags & SA_SIGINFO) + ret = setup_rt_frame(sig, ka, info, oldset, regs); + else + ret = setup_frame(sig, ka, oldset, regs); + if (ret) + return ret; + block_sigmask(ka, sig); + return 0; +} + +/* + * Note that 'init' is a special process: it doesn't get signals it doesn't + * want to handle. Thus you cannot kill init even with a SIGKILL even by + * mistake. + * + * Note that we go through the signals twice: once to check the signals that + * the kernel can handle, and then we build all the user-level signal handling + * stack-frames in one go after that. + */ +void do_signal(struct pt_regs *regs) +{ + siginfo_t info; + int signr; + struct k_sigaction ka; + sigset_t *oldset; + + /* + * We want the common case to go fast, which + * is why we may in certain cases get here from + * kernel mode. Just return without doing anything + * if so. + */ + if (!user_mode(regs)) + return; + + if (test_thread_flag(TIF_RESTORE_SIGMASK)) + oldset = ¤t->saved_sigmask; + else + oldset = ¤t->blocked; + + /* + * Get signal to deliver. When running under ptrace, at this point + * the debugger may change all our registers, including the system + * call information. + */ + current_thread_info()->system_call = + test_thread_flag(TIF_SYSCALL) ? regs->int_code : 0; + signr = get_signal_to_deliver(&info, &ka, regs, NULL); + + if (signr > 0) { + /* Whee! Actually deliver the signal. */ + if (current_thread_info()->system_call) { + regs->int_code = current_thread_info()->system_call; + /* Check for system call restarting. */ + switch (regs->gprs[2]) { + case -ERESTART_RESTARTBLOCK: + case -ERESTARTNOHAND: + regs->gprs[2] = -EINTR; + break; + case -ERESTARTSYS: + if (!(ka.sa.sa_flags & SA_RESTART)) { + regs->gprs[2] = -EINTR; + break; + } + /* fallthrough */ + case -ERESTARTNOINTR: + regs->gprs[2] = regs->orig_gpr2; + regs->psw.addr = + __rewind_psw(regs->psw, + regs->int_code >> 16); + break; + } + } + /* No longer in a system call */ + clear_thread_flag(TIF_SYSCALL); + + if ((is_compat_task() ? + handle_signal32(signr, &ka, &info, oldset, regs) : + handle_signal(signr, &ka, &info, oldset, regs)) == 0) { + /* + * A signal was successfully delivered; the saved + * sigmask will have been stored in the signal frame, + * and will be restored by sigreturn, so we can simply + * clear the TIF_RESTORE_SIGMASK flag. + */ + if (test_thread_flag(TIF_RESTORE_SIGMASK)) + clear_thread_flag(TIF_RESTORE_SIGMASK); + + /* + * Let tracing know that we've done the handler setup. + */ + tracehook_signal_handler(signr, &info, &ka, regs, + test_thread_flag(TIF_SINGLE_STEP)); + } + return; + } + + /* No handlers present - check for system call restart */ + clear_thread_flag(TIF_SYSCALL); + if (current_thread_info()->system_call) { + regs->int_code = current_thread_info()->system_call; + switch (regs->gprs[2]) { + case -ERESTART_RESTARTBLOCK: + /* Restart with sys_restart_syscall */ + regs->int_code = __NR_restart_syscall; + /* fallthrough */ + case -ERESTARTNOHAND: + case -ERESTARTSYS: + case -ERESTARTNOINTR: + /* Restart system call with magic TIF bit. */ + regs->gprs[2] = regs->orig_gpr2; + set_thread_flag(TIF_SYSCALL); + break; + } + } + + /* + * If there's no signal to deliver, we just put the saved sigmask back. + */ + if (test_thread_flag(TIF_RESTORE_SIGMASK)) { + clear_thread_flag(TIF_RESTORE_SIGMASK); + sigprocmask(SIG_SETMASK, ¤t->saved_sigmask, NULL); + } +} + +void do_notify_resume(struct pt_regs *regs) +{ + clear_thread_flag(TIF_NOTIFY_RESUME); + tracehook_notify_resume(regs); + if (current->replacement_session_keyring) + key_replace_session_keyring(); +} diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c new file mode 100644 index 00000000..1f772276 --- /dev/null +++ b/arch/s390/kernel/smp.c @@ -0,0 +1,1146 @@ +/* + * SMP related functions + * + * Copyright IBM Corp. 1999,2012 + * Author(s): Denis Joseph Barrow, + * Martin Schwidefsky <schwidefsky@de.ibm.com>, + * Heiko Carstens <heiko.carstens@de.ibm.com>, + * + * based on other smp stuff by + * (c) 1995 Alan Cox, CymruNET Ltd <alan@cymru.net> + * (c) 1998 Ingo Molnar + * + * The code outside of smp.c uses logical cpu numbers, only smp.c does + * the translation of logical to physical cpu ids. All new code that + * operates on physical cpu numbers needs to go into smp.c. + */ + +#define KMSG_COMPONENT "cpu" +#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt + +#include <linux/workqueue.h> +#include <linux/module.h> +#include <linux/init.h> +#include <linux/mm.h> +#include <linux/err.h> +#include <linux/spinlock.h> +#include <linux/kernel_stat.h> +#include <linux/delay.h> +#include <linux/interrupt.h> +#include <linux/irqflags.h> +#include <linux/cpu.h> +#include <linux/slab.h> +#include <linux/crash_dump.h> +#include <asm/asm-offsets.h> +#include <asm/switch_to.h> +#include <asm/facility.h> +#include <asm/ipl.h> +#include <asm/setup.h> +#include <asm/irq.h> +#include <asm/tlbflush.h> +#include <asm/timer.h> +#include <asm/lowcore.h> +#include <asm/sclp.h> +#include <asm/vdso.h> +#include <asm/debug.h> +#include <asm/os_info.h> +#include "entry.h" + +enum { + sigp_sense = 1, + sigp_external_call = 2, + sigp_emergency_signal = 3, + sigp_start = 4, + sigp_stop = 5, + sigp_restart = 6, + sigp_stop_and_store_status = 9, + sigp_initial_cpu_reset = 11, + sigp_cpu_reset = 12, + sigp_set_prefix = 13, + sigp_store_status_at_address = 14, + sigp_store_extended_status_at_address = 15, + sigp_set_architecture = 18, + sigp_conditional_emergency_signal = 19, + sigp_sense_running = 21, +}; + +enum { + sigp_order_code_accepted = 0, + sigp_status_stored = 1, + sigp_busy = 2, + sigp_not_operational = 3, +}; + +enum { + ec_schedule = 0, + ec_call_function, + ec_call_function_single, + ec_stop_cpu, +}; + +enum { + CPU_STATE_STANDBY, + CPU_STATE_CONFIGURED, +}; + +struct pcpu { + struct cpu cpu; + struct task_struct *idle; /* idle process for the cpu */ + struct _lowcore *lowcore; /* lowcore page(s) for the cpu */ + unsigned long async_stack; /* async stack for the cpu */ + unsigned long panic_stack; /* panic stack for the cpu */ + unsigned long ec_mask; /* bit mask for ec_xxx functions */ + int state; /* physical cpu state */ + u32 status; /* last status received via sigp */ + u16 address; /* physical cpu address */ +}; + +static u8 boot_cpu_type; +static u16 boot_cpu_address; +static struct pcpu pcpu_devices[NR_CPUS]; + +DEFINE_MUTEX(smp_cpu_state_mutex); + +/* + * Signal processor helper functions. + */ +static inline int __pcpu_sigp(u16 addr, u8 order, u32 parm, u32 *status) +{ + register unsigned int reg1 asm ("1") = parm; + int cc; + + asm volatile( + " sigp %1,%2,0(%3)\n" + " ipm %0\n" + " srl %0,28\n" + : "=d" (cc), "+d" (reg1) : "d" (addr), "a" (order) : "cc"); + if (status && cc == 1) + *status = reg1; + return cc; +} + +static inline int __pcpu_sigp_relax(u16 addr, u8 order, u32 parm, u32 *status) +{ + int cc; + + while (1) { + cc = __pcpu_sigp(addr, order, parm, status); + if (cc != sigp_busy) + return cc; + cpu_relax(); + } +} + +static int pcpu_sigp_retry(struct pcpu *pcpu, u8 order, u32 parm) +{ + int cc, retry; + + for (retry = 0; ; retry++) { + cc = __pcpu_sigp(pcpu->address, order, parm, &pcpu->status); + if (cc != sigp_busy) + break; + if (retry >= 3) + udelay(10); + } + return cc; +} + +static inline int pcpu_stopped(struct pcpu *pcpu) +{ + if (__pcpu_sigp(pcpu->address, sigp_sense, + 0, &pcpu->status) != sigp_status_stored) + return 0; + /* Check for stopped and check stop state */ + return !!(pcpu->status & 0x50); +} + +static inline int pcpu_running(struct pcpu *pcpu) +{ + if (__pcpu_sigp(pcpu->address, sigp_sense_running, + 0, &pcpu->status) != sigp_status_stored) + return 1; + /* Check for running status */ + return !(pcpu->status & 0x400); +} + +/* + * Find struct pcpu by cpu address. + */ +static struct pcpu *pcpu_find_address(const struct cpumask *mask, int address) +{ + int cpu; + + for_each_cpu(cpu, mask) + if (pcpu_devices[cpu].address == address) + return pcpu_devices + cpu; + return NULL; +} + +static void pcpu_ec_call(struct pcpu *pcpu, int ec_bit) +{ + int order; + + set_bit(ec_bit, &pcpu->ec_mask); + order = pcpu_running(pcpu) ? + sigp_external_call : sigp_emergency_signal; + pcpu_sigp_retry(pcpu, order, 0); +} + +static int __cpuinit pcpu_alloc_lowcore(struct pcpu *pcpu, int cpu) +{ + struct _lowcore *lc; + + if (pcpu != &pcpu_devices[0]) { + pcpu->lowcore = (struct _lowcore *) + __get_free_pages(GFP_KERNEL | GFP_DMA, LC_ORDER); + pcpu->async_stack = __get_free_pages(GFP_KERNEL, ASYNC_ORDER); + pcpu->panic_stack = __get_free_page(GFP_KERNEL); + if (!pcpu->lowcore || !pcpu->panic_stack || !pcpu->async_stack) + goto out; + } + lc = pcpu->lowcore; + memcpy(lc, &S390_lowcore, 512); + memset((char *) lc + 512, 0, sizeof(*lc) - 512); + lc->async_stack = pcpu->async_stack + ASYNC_SIZE; + lc->panic_stack = pcpu->panic_stack + PAGE_SIZE; + lc->cpu_nr = cpu; +#ifndef CONFIG_64BIT + if (MACHINE_HAS_IEEE) { + lc->extended_save_area_addr = get_zeroed_page(GFP_KERNEL); + if (!lc->extended_save_area_addr) + goto out; + } +#else + if (vdso_alloc_per_cpu(lc)) + goto out; +#endif + lowcore_ptr[cpu] = lc; + pcpu_sigp_retry(pcpu, sigp_set_prefix, (u32)(unsigned long) lc); + return 0; +out: + if (pcpu != &pcpu_devices[0]) { + free_page(pcpu->panic_stack); + free_pages(pcpu->async_stack, ASYNC_ORDER); + free_pages((unsigned long) pcpu->lowcore, LC_ORDER); + } + return -ENOMEM; +} + +static void pcpu_free_lowcore(struct pcpu *pcpu) +{ + pcpu_sigp_retry(pcpu, sigp_set_prefix, 0); + lowcore_ptr[pcpu - pcpu_devices] = NULL; +#ifndef CONFIG_64BIT + if (MACHINE_HAS_IEEE) { + struct _lowcore *lc = pcpu->lowcore; + + free_page((unsigned long) lc->extended_save_area_addr); + lc->extended_save_area_addr = 0; + } +#else + vdso_free_per_cpu(pcpu->lowcore); +#endif + if (pcpu != &pcpu_devices[0]) { + free_page(pcpu->panic_stack); + free_pages(pcpu->async_stack, ASYNC_ORDER); + free_pages((unsigned long) pcpu->lowcore, LC_ORDER); + } +} + +static void pcpu_prepare_secondary(struct pcpu *pcpu, int cpu) +{ + struct _lowcore *lc = pcpu->lowcore; + + atomic_inc(&init_mm.context.attach_count); + lc->cpu_nr = cpu; + lc->percpu_offset = __per_cpu_offset[cpu]; + lc->kernel_asce = S390_lowcore.kernel_asce; + lc->machine_flags = S390_lowcore.machine_flags; + lc->ftrace_func = S390_lowcore.ftrace_func; + lc->user_timer = lc->system_timer = lc->steal_timer = 0; + __ctl_store(lc->cregs_save_area, 0, 15); + save_access_regs((unsigned int *) lc->access_regs_save_area); + memcpy(lc->stfle_fac_list, S390_lowcore.stfle_fac_list, + MAX_FACILITY_BIT/8); +} + +static void pcpu_attach_task(struct pcpu *pcpu, struct task_struct *tsk) +{ + struct _lowcore *lc = pcpu->lowcore; + struct thread_info *ti = task_thread_info(tsk); + + lc->kernel_stack = (unsigned long) task_stack_page(tsk) + THREAD_SIZE; + lc->thread_info = (unsigned long) task_thread_info(tsk); + lc->current_task = (unsigned long) tsk; + lc->user_timer = ti->user_timer; + lc->system_timer = ti->system_timer; + lc->steal_timer = 0; +} + +static void pcpu_start_fn(struct pcpu *pcpu, void (*func)(void *), void *data) +{ + struct _lowcore *lc = pcpu->lowcore; + + lc->restart_stack = lc->kernel_stack; + lc->restart_fn = (unsigned long) func; + lc->restart_data = (unsigned long) data; + lc->restart_source = -1UL; + pcpu_sigp_retry(pcpu, sigp_restart, 0); +} + +/* + * Call function via PSW restart on pcpu and stop the current cpu. + */ +static void pcpu_delegate(struct pcpu *pcpu, void (*func)(void *), + void *data, unsigned long stack) +{ + struct _lowcore *lc = pcpu->lowcore; + unsigned short this_cpu; + + __load_psw_mask(psw_kernel_bits); + this_cpu = stap(); + if (pcpu->address == this_cpu) + func(data); /* should not return */ + /* Stop target cpu (if func returns this stops the current cpu). */ + pcpu_sigp_retry(pcpu, sigp_stop, 0); + /* Restart func on the target cpu and stop the current cpu. */ + lc->restart_stack = stack; + lc->restart_fn = (unsigned long) func; + lc->restart_data = (unsigned long) data; + lc->restart_source = (unsigned long) this_cpu; + asm volatile( + "0: sigp 0,%0,6 # sigp restart to target cpu\n" + " brc 2,0b # busy, try again\n" + "1: sigp 0,%1,5 # sigp stop to current cpu\n" + " brc 2,1b # busy, try again\n" + : : "d" (pcpu->address), "d" (this_cpu) : "0", "1", "cc"); + for (;;) ; +} + +/* + * Call function on an online CPU. + */ +void smp_call_online_cpu(void (*func)(void *), void *data) +{ + struct pcpu *pcpu; + + /* Use the current cpu if it is online. */ + pcpu = pcpu_find_address(cpu_online_mask, stap()); + if (!pcpu) + /* Use the first online cpu. */ + pcpu = pcpu_devices + cpumask_first(cpu_online_mask); + pcpu_delegate(pcpu, func, data, (unsigned long) restart_stack); +} + +/* + * Call function on the ipl CPU. + */ +void smp_call_ipl_cpu(void (*func)(void *), void *data) +{ + pcpu_delegate(&pcpu_devices[0], func, data, + pcpu_devices->panic_stack + PAGE_SIZE); +} + +int smp_find_processor_id(u16 address) +{ + int cpu; + + for_each_present_cpu(cpu) + if (pcpu_devices[cpu].address == address) + return cpu; + return -1; +} + +int smp_vcpu_scheduled(int cpu) +{ + return pcpu_running(pcpu_devices + cpu); +} + +void smp_yield(void) +{ + if (MACHINE_HAS_DIAG44) + asm volatile("diag 0,0,0x44"); +} + +void smp_yield_cpu(int cpu) +{ + if (MACHINE_HAS_DIAG9C) + asm volatile("diag %0,0,0x9c" + : : "d" (pcpu_devices[cpu].address)); + else if (MACHINE_HAS_DIAG44) + asm volatile("diag 0,0,0x44"); +} + +/* + * Send cpus emergency shutdown signal. This gives the cpus the + * opportunity to complete outstanding interrupts. + */ +void smp_emergency_stop(cpumask_t *cpumask) +{ + u64 end; + int cpu; + + end = get_clock() + (1000000UL << 12); + for_each_cpu(cpu, cpumask) { + struct pcpu *pcpu = pcpu_devices + cpu; + set_bit(ec_stop_cpu, &pcpu->ec_mask); + while (__pcpu_sigp(pcpu->address, sigp_emergency_signal, + 0, NULL) == sigp_busy && + get_clock() < end) + cpu_relax(); + } + while (get_clock() < end) { + for_each_cpu(cpu, cpumask) + if (pcpu_stopped(pcpu_devices + cpu)) + cpumask_clear_cpu(cpu, cpumask); + if (cpumask_empty(cpumask)) + break; + cpu_relax(); + } +} + +/* + * Stop all cpus but the current one. + */ +void smp_send_stop(void) +{ + cpumask_t cpumask; + int cpu; + + /* Disable all interrupts/machine checks */ + __load_psw_mask(psw_kernel_bits | PSW_MASK_DAT); + trace_hardirqs_off(); + + debug_set_critical(); + cpumask_copy(&cpumask, cpu_online_mask); + cpumask_clear_cpu(smp_processor_id(), &cpumask); + + if (oops_in_progress) + smp_emergency_stop(&cpumask); + + /* stop all processors */ + for_each_cpu(cpu, &cpumask) { + struct pcpu *pcpu = pcpu_devices + cpu; + pcpu_sigp_retry(pcpu, sigp_stop, 0); + while (!pcpu_stopped(pcpu)) + cpu_relax(); + } +} + +/* + * Stop the current cpu. + */ +void smp_stop_cpu(void) +{ + pcpu_sigp_retry(pcpu_devices + smp_processor_id(), sigp_stop, 0); + for (;;) ; +} + +/* + * This is the main routine where commands issued by other + * cpus are handled. + */ +static void do_ext_call_interrupt(struct ext_code ext_code, + unsigned int param32, unsigned long param64) +{ + unsigned long bits; + int cpu; + + cpu = smp_processor_id(); + if (ext_code.code == 0x1202) + kstat_cpu(cpu).irqs[EXTINT_EXC]++; + else + kstat_cpu(cpu).irqs[EXTINT_EMS]++; + /* + * handle bit signal external calls + */ + bits = xchg(&pcpu_devices[cpu].ec_mask, 0); + + if (test_bit(ec_stop_cpu, &bits)) + smp_stop_cpu(); + + if (test_bit(ec_schedule, &bits)) + scheduler_ipi(); + + if (test_bit(ec_call_function, &bits)) + generic_smp_call_function_interrupt(); + + if (test_bit(ec_call_function_single, &bits)) + generic_smp_call_function_single_interrupt(); + +} + +void arch_send_call_function_ipi_mask(const struct cpumask *mask) +{ + int cpu; + + for_each_cpu(cpu, mask) + pcpu_ec_call(pcpu_devices + cpu, ec_call_function); +} + +void arch_send_call_function_single_ipi(int cpu) +{ + pcpu_ec_call(pcpu_devices + cpu, ec_call_function_single); +} + +#ifndef CONFIG_64BIT +/* + * this function sends a 'purge tlb' signal to another CPU. + */ +static void smp_ptlb_callback(void *info) +{ + __tlb_flush_local(); +} + +void smp_ptlb_all(void) +{ + on_each_cpu(smp_ptlb_callback, NULL, 1); +} +EXPORT_SYMBOL(smp_ptlb_all); +#endif /* ! CONFIG_64BIT */ + +/* + * this function sends a 'reschedule' IPI to another CPU. + * it goes straight through and wastes no time serializing + * anything. Worst case is that we lose a reschedule ... + */ +void smp_send_reschedule(int cpu) +{ + pcpu_ec_call(pcpu_devices + cpu, ec_schedule); +} + +/* + * parameter area for the set/clear control bit callbacks + */ +struct ec_creg_mask_parms { + unsigned long orval; + unsigned long andval; + int cr; +}; + +/* + * callback for setting/clearing control bits + */ +static void smp_ctl_bit_callback(void *info) +{ + struct ec_creg_mask_parms *pp = info; + unsigned long cregs[16]; + + __ctl_store(cregs, 0, 15); + cregs[pp->cr] = (cregs[pp->cr] & pp->andval) | pp->orval; + __ctl_load(cregs, 0, 15); +} + +/* + * Set a bit in a control register of all cpus + */ +void smp_ctl_set_bit(int cr, int bit) +{ + struct ec_creg_mask_parms parms = { 1UL << bit, -1UL, cr }; + + on_each_cpu(smp_ctl_bit_callback, &parms, 1); +} +EXPORT_SYMBOL(smp_ctl_set_bit); + +/* + * Clear a bit in a control register of all cpus + */ +void smp_ctl_clear_bit(int cr, int bit) +{ + struct ec_creg_mask_parms parms = { 0, ~(1UL << bit), cr }; + + on_each_cpu(smp_ctl_bit_callback, &parms, 1); +} +EXPORT_SYMBOL(smp_ctl_clear_bit); + +#if defined(CONFIG_ZFCPDUMP) || defined(CONFIG_CRASH_DUMP) + +struct save_area *zfcpdump_save_areas[NR_CPUS + 1]; +EXPORT_SYMBOL_GPL(zfcpdump_save_areas); + +static void __init smp_get_save_area(int cpu, u16 address) +{ + void *lc = pcpu_devices[0].lowcore; + struct save_area *save_area; + + if (is_kdump_kernel()) + return; + if (!OLDMEM_BASE && (address == boot_cpu_address || + ipl_info.type != IPL_TYPE_FCP_DUMP)) + return; + if (cpu >= NR_CPUS) { + pr_warning("CPU %i exceeds the maximum %i and is excluded " + "from the dump\n", cpu, NR_CPUS - 1); + return; + } + save_area = kmalloc(sizeof(struct save_area), GFP_KERNEL); + if (!save_area) + panic("could not allocate memory for save area\n"); + zfcpdump_save_areas[cpu] = save_area; +#ifdef CONFIG_CRASH_DUMP + if (address == boot_cpu_address) { + /* Copy the registers of the boot cpu. */ + copy_oldmem_page(1, (void *) save_area, sizeof(*save_area), + SAVE_AREA_BASE - PAGE_SIZE, 0); + return; + } +#endif + /* Get the registers of a non-boot cpu. */ + __pcpu_sigp_relax(address, sigp_stop_and_store_status, 0, NULL); + memcpy_real(save_area, lc + SAVE_AREA_BASE, sizeof(*save_area)); +} + +int smp_store_status(int cpu) +{ + struct pcpu *pcpu; + + pcpu = pcpu_devices + cpu; + if (__pcpu_sigp_relax(pcpu->address, sigp_stop_and_store_status, + 0, NULL) != sigp_order_code_accepted) + return -EIO; + return 0; +} + +#else /* CONFIG_ZFCPDUMP || CONFIG_CRASH_DUMP */ + +static inline void smp_get_save_area(int cpu, u16 address) { } + +#endif /* CONFIG_ZFCPDUMP || CONFIG_CRASH_DUMP */ + +static struct sclp_cpu_info *smp_get_cpu_info(void) +{ + static int use_sigp_detection; + struct sclp_cpu_info *info; + int address; + + info = kzalloc(sizeof(*info), GFP_KERNEL); + if (info && (use_sigp_detection || sclp_get_cpu_info(info))) { + use_sigp_detection = 1; + for (address = 0; address <= MAX_CPU_ADDRESS; address++) { + if (__pcpu_sigp_relax(address, sigp_sense, 0, NULL) == + sigp_not_operational) + continue; + info->cpu[info->configured].address = address; + info->configured++; + } + info->combined = info->configured; + } + return info; +} + +static int __devinit smp_add_present_cpu(int cpu); + +static int __devinit __smp_rescan_cpus(struct sclp_cpu_info *info, + int sysfs_add) +{ + struct pcpu *pcpu; + cpumask_t avail; + int cpu, nr, i; + + nr = 0; + cpumask_xor(&avail, cpu_possible_mask, cpu_present_mask); + cpu = cpumask_first(&avail); + for (i = 0; (i < info->combined) && (cpu < nr_cpu_ids); i++) { + if (info->has_cpu_type && info->cpu[i].type != boot_cpu_type) + continue; + if (pcpu_find_address(cpu_present_mask, info->cpu[i].address)) + continue; + pcpu = pcpu_devices + cpu; + pcpu->address = info->cpu[i].address; + pcpu->state = (cpu >= info->configured) ? + CPU_STATE_STANDBY : CPU_STATE_CONFIGURED; + cpu_set_polarization(cpu, POLARIZATION_UNKNOWN); + set_cpu_present(cpu, true); + if (sysfs_add && smp_add_present_cpu(cpu) != 0) + set_cpu_present(cpu, false); + else + nr++; + cpu = cpumask_next(cpu, &avail); + } + return nr; +} + +static void __init smp_detect_cpus(void) +{ + unsigned int cpu, c_cpus, s_cpus; + struct sclp_cpu_info *info; + + info = smp_get_cpu_info(); + if (!info) + panic("smp_detect_cpus failed to allocate memory\n"); + if (info->has_cpu_type) { + for (cpu = 0; cpu < info->combined; cpu++) { + if (info->cpu[cpu].address != boot_cpu_address) + continue; + /* The boot cpu dictates the cpu type. */ + boot_cpu_type = info->cpu[cpu].type; + break; + } + } + c_cpus = s_cpus = 0; + for (cpu = 0; cpu < info->combined; cpu++) { + if (info->has_cpu_type && info->cpu[cpu].type != boot_cpu_type) + continue; + if (cpu < info->configured) { + smp_get_save_area(c_cpus, info->cpu[cpu].address); + c_cpus++; + } else + s_cpus++; + } + pr_info("%d configured CPUs, %d standby CPUs\n", c_cpus, s_cpus); + get_online_cpus(); + __smp_rescan_cpus(info, 0); + put_online_cpus(); + kfree(info); +} + +/* + * Activate a secondary processor. + */ +static void __cpuinit smp_start_secondary(void *cpuvoid) +{ + S390_lowcore.last_update_clock = get_clock(); + S390_lowcore.restart_stack = (unsigned long) restart_stack; + S390_lowcore.restart_fn = (unsigned long) do_restart; + S390_lowcore.restart_data = 0; + S390_lowcore.restart_source = -1UL; + restore_access_regs(S390_lowcore.access_regs_save_area); + __ctl_load(S390_lowcore.cregs_save_area, 0, 15); + __load_psw_mask(psw_kernel_bits | PSW_MASK_DAT); + cpu_init(); + preempt_disable(); + init_cpu_timer(); + init_cpu_vtimer(); + pfault_init(); + notify_cpu_starting(smp_processor_id()); + ipi_call_lock(); + set_cpu_online(smp_processor_id(), true); + ipi_call_unlock(); + local_irq_enable(); + /* cpu_idle will call schedule for us */ + cpu_idle(); +} + +struct create_idle { + struct work_struct work; + struct task_struct *idle; + struct completion done; + int cpu; +}; + +static void __cpuinit smp_fork_idle(struct work_struct *work) +{ + struct create_idle *c_idle; + + c_idle = container_of(work, struct create_idle, work); + c_idle->idle = fork_idle(c_idle->cpu); + complete(&c_idle->done); +} + +/* Upping and downing of CPUs */ +int __cpuinit __cpu_up(unsigned int cpu) +{ + struct create_idle c_idle; + struct pcpu *pcpu; + int rc; + + pcpu = pcpu_devices + cpu; + if (pcpu->state != CPU_STATE_CONFIGURED) + return -EIO; + if (pcpu_sigp_retry(pcpu, sigp_initial_cpu_reset, 0) != + sigp_order_code_accepted) + return -EIO; + if (!pcpu->idle) { + c_idle.done = COMPLETION_INITIALIZER_ONSTACK(c_idle.done); + INIT_WORK_ONSTACK(&c_idle.work, smp_fork_idle); + c_idle.cpu = cpu; + schedule_work(&c_idle.work); + wait_for_completion(&c_idle.done); + if (IS_ERR(c_idle.idle)) + return PTR_ERR(c_idle.idle); + pcpu->idle = c_idle.idle; + } + init_idle(pcpu->idle, cpu); + rc = pcpu_alloc_lowcore(pcpu, cpu); + if (rc) + return rc; + pcpu_prepare_secondary(pcpu, cpu); + pcpu_attach_task(pcpu, pcpu->idle); + pcpu_start_fn(pcpu, smp_start_secondary, NULL); + while (!cpu_online(cpu)) + cpu_relax(); + return 0; +} + +static int __init setup_possible_cpus(char *s) +{ + int max, cpu; + + if (kstrtoint(s, 0, &max) < 0) + return 0; + init_cpu_possible(cpumask_of(0)); + for (cpu = 1; cpu < max && cpu < nr_cpu_ids; cpu++) + set_cpu_possible(cpu, true); + return 0; +} +early_param("possible_cpus", setup_possible_cpus); + +#ifdef CONFIG_HOTPLUG_CPU + +int __cpu_disable(void) +{ + unsigned long cregs[16]; + + set_cpu_online(smp_processor_id(), false); + /* Disable pseudo page faults on this cpu. */ + pfault_fini(); + /* Disable interrupt sources via control register. */ + __ctl_store(cregs, 0, 15); + cregs[0] &= ~0x0000ee70UL; /* disable all external interrupts */ + cregs[6] &= ~0xff000000UL; /* disable all I/O interrupts */ + cregs[14] &= ~0x1f000000UL; /* disable most machine checks */ + __ctl_load(cregs, 0, 15); + return 0; +} + +void __cpu_die(unsigned int cpu) +{ + struct pcpu *pcpu; + + /* Wait until target cpu is down */ + pcpu = pcpu_devices + cpu; + while (!pcpu_stopped(pcpu)) + cpu_relax(); + pcpu_free_lowcore(pcpu); + atomic_dec(&init_mm.context.attach_count); +} + +void __noreturn cpu_die(void) +{ + idle_task_exit(); + pcpu_sigp_retry(pcpu_devices + smp_processor_id(), sigp_stop, 0); + for (;;) ; +} + +#endif /* CONFIG_HOTPLUG_CPU */ + +static void smp_call_os_info_init_fn(void) +{ + int (*init_fn)(void); + unsigned long size; + + init_fn = os_info_old_entry(OS_INFO_INIT_FN, &size); + if (!init_fn) + return; + init_fn(); +} + +void __init smp_prepare_cpus(unsigned int max_cpus) +{ + /* request the 0x1201 emergency signal external interrupt */ + if (register_external_interrupt(0x1201, do_ext_call_interrupt) != 0) + panic("Couldn't request external interrupt 0x1201"); + /* request the 0x1202 external call external interrupt */ + if (register_external_interrupt(0x1202, do_ext_call_interrupt) != 0) + panic("Couldn't request external interrupt 0x1202"); + smp_call_os_info_init_fn(); + smp_detect_cpus(); +} + +void __init smp_prepare_boot_cpu(void) +{ + struct pcpu *pcpu = pcpu_devices; + + boot_cpu_address = stap(); + pcpu->idle = current; + pcpu->state = CPU_STATE_CONFIGURED; + pcpu->address = boot_cpu_address; + pcpu->lowcore = (struct _lowcore *)(unsigned long) store_prefix(); + pcpu->async_stack = S390_lowcore.async_stack - ASYNC_SIZE; + pcpu->panic_stack = S390_lowcore.panic_stack - PAGE_SIZE; + S390_lowcore.percpu_offset = __per_cpu_offset[0]; + cpu_set_polarization(0, POLARIZATION_UNKNOWN); + set_cpu_present(0, true); + set_cpu_online(0, true); +} + +void __init smp_cpus_done(unsigned int max_cpus) +{ +} + +void __init smp_setup_processor_id(void) +{ + S390_lowcore.cpu_nr = 0; +} + +/* + * the frequency of the profiling timer can be changed + * by writing a multiplier value into /proc/profile. + * + * usually you want to run this on all CPUs ;) + */ +int setup_profiling_timer(unsigned int multiplier) +{ + return 0; +} + +#ifdef CONFIG_HOTPLUG_CPU +static ssize_t cpu_configure_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + ssize_t count; + + mutex_lock(&smp_cpu_state_mutex); + count = sprintf(buf, "%d\n", pcpu_devices[dev->id].state); + mutex_unlock(&smp_cpu_state_mutex); + return count; +} + +static ssize_t cpu_configure_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct pcpu *pcpu; + int cpu, val, rc; + char delim; + + if (sscanf(buf, "%d %c", &val, &delim) != 1) + return -EINVAL; + if (val != 0 && val != 1) + return -EINVAL; + get_online_cpus(); + mutex_lock(&smp_cpu_state_mutex); + rc = -EBUSY; + /* disallow configuration changes of online cpus and cpu 0 */ + cpu = dev->id; + if (cpu_online(cpu) || cpu == 0) + goto out; + pcpu = pcpu_devices + cpu; + rc = 0; + switch (val) { + case 0: + if (pcpu->state != CPU_STATE_CONFIGURED) + break; + rc = sclp_cpu_deconfigure(pcpu->address); + if (rc) + break; + pcpu->state = CPU_STATE_STANDBY; + cpu_set_polarization(cpu, POLARIZATION_UNKNOWN); + topology_expect_change(); + break; + case 1: + if (pcpu->state != CPU_STATE_STANDBY) + break; + rc = sclp_cpu_configure(pcpu->address); + if (rc) + break; + pcpu->state = CPU_STATE_CONFIGURED; + cpu_set_polarization(cpu, POLARIZATION_UNKNOWN); + topology_expect_change(); + break; + default: + break; + } +out: + mutex_unlock(&smp_cpu_state_mutex); + put_online_cpus(); + return rc ? rc : count; +} +static DEVICE_ATTR(configure, 0644, cpu_configure_show, cpu_configure_store); +#endif /* CONFIG_HOTPLUG_CPU */ + +static ssize_t show_cpu_address(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return sprintf(buf, "%d\n", pcpu_devices[dev->id].address); +} +static DEVICE_ATTR(address, 0444, show_cpu_address, NULL); + +static struct attribute *cpu_common_attrs[] = { +#ifdef CONFIG_HOTPLUG_CPU + &dev_attr_configure.attr, +#endif + &dev_attr_address.attr, + NULL, +}; + +static struct attribute_group cpu_common_attr_group = { + .attrs = cpu_common_attrs, +}; + +static ssize_t show_capability(struct device *dev, + struct device_attribute *attr, char *buf) +{ + unsigned int capability; + int rc; + + rc = get_cpu_capability(&capability); + if (rc) + return rc; + return sprintf(buf, "%u\n", capability); +} +static DEVICE_ATTR(capability, 0444, show_capability, NULL); + +static ssize_t show_idle_count(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct s390_idle_data *idle = &per_cpu(s390_idle, dev->id); + unsigned long long idle_count; + unsigned int sequence; + + do { + sequence = ACCESS_ONCE(idle->sequence); + idle_count = ACCESS_ONCE(idle->idle_count); + if (ACCESS_ONCE(idle->idle_enter)) + idle_count++; + } while ((sequence & 1) || (idle->sequence != sequence)); + return sprintf(buf, "%llu\n", idle_count); +} +static DEVICE_ATTR(idle_count, 0444, show_idle_count, NULL); + +static ssize_t show_idle_time(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct s390_idle_data *idle = &per_cpu(s390_idle, dev->id); + unsigned long long now, idle_time, idle_enter, idle_exit; + unsigned int sequence; + + do { + now = get_clock(); + sequence = ACCESS_ONCE(idle->sequence); + idle_time = ACCESS_ONCE(idle->idle_time); + idle_enter = ACCESS_ONCE(idle->idle_enter); + idle_exit = ACCESS_ONCE(idle->idle_exit); + } while ((sequence & 1) || (idle->sequence != sequence)); + idle_time += idle_enter ? ((idle_exit ? : now) - idle_enter) : 0; + return sprintf(buf, "%llu\n", idle_time >> 12); +} +static DEVICE_ATTR(idle_time_us, 0444, show_idle_time, NULL); + +static struct attribute *cpu_online_attrs[] = { + &dev_attr_capability.attr, + &dev_attr_idle_count.attr, + &dev_attr_idle_time_us.attr, + NULL, +}; + +static struct attribute_group cpu_online_attr_group = { + .attrs = cpu_online_attrs, +}; + +static int __cpuinit smp_cpu_notify(struct notifier_block *self, + unsigned long action, void *hcpu) +{ + unsigned int cpu = (unsigned int)(long)hcpu; + struct cpu *c = &pcpu_devices[cpu].cpu; + struct device *s = &c->dev; + struct s390_idle_data *idle; + int err = 0; + + switch (action) { + case CPU_ONLINE: + case CPU_ONLINE_FROZEN: + idle = &per_cpu(s390_idle, cpu); + memset(idle, 0, sizeof(struct s390_idle_data)); + err = sysfs_create_group(&s->kobj, &cpu_online_attr_group); + break; + case CPU_DEAD: + case CPU_DEAD_FROZEN: + sysfs_remove_group(&s->kobj, &cpu_online_attr_group); + break; + } + return notifier_from_errno(err); +} + +static struct notifier_block __cpuinitdata smp_cpu_nb = { + .notifier_call = smp_cpu_notify, +}; + +static int __devinit smp_add_present_cpu(int cpu) +{ + struct cpu *c = &pcpu_devices[cpu].cpu; + struct device *s = &c->dev; + int rc; + + c->hotpluggable = 1; + rc = register_cpu(c, cpu); + if (rc) + goto out; + rc = sysfs_create_group(&s->kobj, &cpu_common_attr_group); + if (rc) + goto out_cpu; + if (cpu_online(cpu)) { + rc = sysfs_create_group(&s->kobj, &cpu_online_attr_group); + if (rc) + goto out_online; + } + rc = topology_cpu_init(c); + if (rc) + goto out_topology; + return 0; + +out_topology: + if (cpu_online(cpu)) + sysfs_remove_group(&s->kobj, &cpu_online_attr_group); +out_online: + sysfs_remove_group(&s->kobj, &cpu_common_attr_group); +out_cpu: +#ifdef CONFIG_HOTPLUG_CPU + unregister_cpu(c); +#endif +out: + return rc; +} + +#ifdef CONFIG_HOTPLUG_CPU + +int __ref smp_rescan_cpus(void) +{ + struct sclp_cpu_info *info; + int nr; + + info = smp_get_cpu_info(); + if (!info) + return -ENOMEM; + get_online_cpus(); + mutex_lock(&smp_cpu_state_mutex); + nr = __smp_rescan_cpus(info, 1); + mutex_unlock(&smp_cpu_state_mutex); + put_online_cpus(); + kfree(info); + if (nr) + topology_schedule_update(); + return 0; +} + +static ssize_t __ref rescan_store(struct device *dev, + struct device_attribute *attr, + const char *buf, + size_t count) +{ + int rc; + + rc = smp_rescan_cpus(); + return rc ? rc : count; +} +static DEVICE_ATTR(rescan, 0200, NULL, rescan_store); +#endif /* CONFIG_HOTPLUG_CPU */ + +static int __init s390_smp_init(void) +{ + int cpu, rc; + + register_cpu_notifier(&smp_cpu_nb); +#ifdef CONFIG_HOTPLUG_CPU + rc = device_create_file(cpu_subsys.dev_root, &dev_attr_rescan); + if (rc) + return rc; +#endif + for_each_present_cpu(cpu) { + rc = smp_add_present_cpu(cpu); + if (rc) + return rc; + } + return 0; +} +subsys_initcall(s390_smp_init); diff --git a/arch/s390/kernel/stacktrace.c b/arch/s390/kernel/stacktrace.c new file mode 100644 index 00000000..8841919e --- /dev/null +++ b/arch/s390/kernel/stacktrace.c @@ -0,0 +1,98 @@ +/* + * arch/s390/kernel/stacktrace.c + * + * Stack trace management functions + * + * Copyright (C) IBM Corp. 2006 + * Author(s): Heiko Carstens <heiko.carstens@de.ibm.com> + */ + +#include <linux/sched.h> +#include <linux/stacktrace.h> +#include <linux/kallsyms.h> +#include <linux/module.h> + +static unsigned long save_context_stack(struct stack_trace *trace, + unsigned long sp, + unsigned long low, + unsigned long high, + int savesched) +{ + struct stack_frame *sf; + struct pt_regs *regs; + unsigned long addr; + + while(1) { + sp &= PSW_ADDR_INSN; + if (sp < low || sp > high) + return sp; + sf = (struct stack_frame *)sp; + while(1) { + addr = sf->gprs[8] & PSW_ADDR_INSN; + if (!trace->skip) + trace->entries[trace->nr_entries++] = addr; + else + trace->skip--; + if (trace->nr_entries >= trace->max_entries) + return sp; + low = sp; + sp = sf->back_chain & PSW_ADDR_INSN; + if (!sp) + break; + if (sp <= low || sp > high - sizeof(*sf)) + return sp; + sf = (struct stack_frame *)sp; + } + /* Zero backchain detected, check for interrupt frame. */ + sp = (unsigned long)(sf + 1); + if (sp <= low || sp > high - sizeof(*regs)) + return sp; + regs = (struct pt_regs *)sp; + addr = regs->psw.addr & PSW_ADDR_INSN; + if (savesched || !in_sched_functions(addr)) { + if (!trace->skip) + trace->entries[trace->nr_entries++] = addr; + else + trace->skip--; + } + if (trace->nr_entries >= trace->max_entries) + return sp; + low = sp; + sp = regs->gprs[15]; + } +} + +void save_stack_trace(struct stack_trace *trace) +{ + register unsigned long sp asm ("15"); + unsigned long orig_sp, new_sp; + + orig_sp = sp & PSW_ADDR_INSN; + new_sp = save_context_stack(trace, orig_sp, + S390_lowcore.panic_stack - PAGE_SIZE, + S390_lowcore.panic_stack, 1); + if (new_sp != orig_sp) + return; + new_sp = save_context_stack(trace, new_sp, + S390_lowcore.async_stack - ASYNC_SIZE, + S390_lowcore.async_stack, 1); + if (new_sp != orig_sp) + return; + save_context_stack(trace, new_sp, + S390_lowcore.thread_info, + S390_lowcore.thread_info + THREAD_SIZE, 1); +} +EXPORT_SYMBOL_GPL(save_stack_trace); + +void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) +{ + unsigned long sp, low, high; + + sp = tsk->thread.ksp & PSW_ADDR_INSN; + low = (unsigned long) task_stack_page(tsk); + high = (unsigned long) task_pt_regs(tsk); + save_context_stack(trace, sp, low, high, 0); + if (trace->nr_entries < trace->max_entries) + trace->entries[trace->nr_entries++] = ULONG_MAX; +} +EXPORT_SYMBOL_GPL(save_stack_trace_tsk); diff --git a/arch/s390/kernel/suspend.c b/arch/s390/kernel/suspend.c new file mode 100644 index 00000000..aa1494d0 --- /dev/null +++ b/arch/s390/kernel/suspend.c @@ -0,0 +1,182 @@ +/* + * Suspend support specific for s390. + * + * Copyright IBM Corp. 2009 + * + * Author(s): Hans-Joachim Picht <hans@linux.vnet.ibm.com> + */ + +#include <linux/pfn.h> +#include <linux/suspend.h> +#include <linux/mm.h> +#include <asm/ctl_reg.h> + +/* + * References to section boundaries + */ +extern const void __nosave_begin, __nosave_end; + +/* + * The restore of the saved pages in an hibernation image will set + * the change and referenced bits in the storage key for each page. + * Overindication of the referenced bits after an hibernation cycle + * does not cause any harm but the overindication of the change bits + * would cause trouble. + * Use the ARCH_SAVE_PAGE_KEYS hooks to save the storage key of each + * page to the most significant byte of the associated page frame + * number in the hibernation image. + */ + +/* + * Key storage is allocated as a linked list of pages. + * The size of the keys array is (PAGE_SIZE - sizeof(long)) + */ +struct page_key_data { + struct page_key_data *next; + unsigned char data[]; +}; + +#define PAGE_KEY_DATA_SIZE (PAGE_SIZE - sizeof(struct page_key_data *)) + +static struct page_key_data *page_key_data; +static struct page_key_data *page_key_rp, *page_key_wp; +static unsigned long page_key_rx, page_key_wx; + +/* + * For each page in the hibernation image one additional byte is + * stored in the most significant byte of the page frame number. + * On suspend no additional memory is required but on resume the + * keys need to be memorized until the page data has been restored. + * Only then can the storage keys be set to their old state. + */ +unsigned long page_key_additional_pages(unsigned long pages) +{ + return DIV_ROUND_UP(pages, PAGE_KEY_DATA_SIZE); +} + +/* + * Free page_key_data list of arrays. + */ +void page_key_free(void) +{ + struct page_key_data *pkd; + + while (page_key_data) { + pkd = page_key_data; + page_key_data = pkd->next; + free_page((unsigned long) pkd); + } +} + +/* + * Allocate page_key_data list of arrays with enough room to store + * one byte for each page in the hibernation image. + */ +int page_key_alloc(unsigned long pages) +{ + struct page_key_data *pk; + unsigned long size; + + size = DIV_ROUND_UP(pages, PAGE_KEY_DATA_SIZE); + while (size--) { + pk = (struct page_key_data *) get_zeroed_page(GFP_KERNEL); + if (!pk) { + page_key_free(); + return -ENOMEM; + } + pk->next = page_key_data; + page_key_data = pk; + } + page_key_rp = page_key_wp = page_key_data; + page_key_rx = page_key_wx = 0; + return 0; +} + +/* + * Save the storage key into the upper 8 bits of the page frame number. + */ +void page_key_read(unsigned long *pfn) +{ + unsigned long addr; + + addr = (unsigned long) page_address(pfn_to_page(*pfn)); + *(unsigned char *) pfn = (unsigned char) page_get_storage_key(addr); +} + +/* + * Extract the storage key from the upper 8 bits of the page frame number + * and store it in the page_key_data list of arrays. + */ +void page_key_memorize(unsigned long *pfn) +{ + page_key_wp->data[page_key_wx] = *(unsigned char *) pfn; + *(unsigned char *) pfn = 0; + if (++page_key_wx < PAGE_KEY_DATA_SIZE) + return; + page_key_wp = page_key_wp->next; + page_key_wx = 0; +} + +/* + * Get the next key from the page_key_data list of arrays and set the + * storage key of the page referred by @address. If @address refers to + * a "safe" page the swsusp_arch_resume code will transfer the storage + * key from the buffer page to the original page. + */ +void page_key_write(void *address) +{ + page_set_storage_key((unsigned long) address, + page_key_rp->data[page_key_rx], 0); + if (++page_key_rx >= PAGE_KEY_DATA_SIZE) + return; + page_key_rp = page_key_rp->next; + page_key_rx = 0; +} + +int pfn_is_nosave(unsigned long pfn) +{ + unsigned long nosave_begin_pfn = PFN_DOWN(__pa(&__nosave_begin)); + unsigned long nosave_end_pfn = PFN_DOWN(__pa(&__nosave_end)); + + /* Always save lowcore pages (LC protection might be enabled). */ + if (pfn <= LC_PAGES) + return 0; + if (pfn >= nosave_begin_pfn && pfn < nosave_end_pfn) + return 1; + /* Skip memory holes and read-only pages (NSS, DCSS, ...). */ + if (tprot(PFN_PHYS(pfn))) + return 1; + return 0; +} + +void save_processor_state(void) +{ + /* swsusp_arch_suspend() actually saves all cpu register contents. + * Machine checks must be disabled since swsusp_arch_suspend() stores + * register contents to their lowcore save areas. That's the same + * place where register contents on machine checks would be saved. + * To avoid register corruption disable machine checks. + * We must also disable machine checks in the new psw mask for + * program checks, since swsusp_arch_suspend() may generate program + * checks. Disabling machine checks for all other new psw masks is + * just paranoia. + */ + local_mcck_disable(); + /* Disable lowcore protection */ + __ctl_clear_bit(0,28); + S390_lowcore.external_new_psw.mask &= ~PSW_MASK_MCHECK; + S390_lowcore.svc_new_psw.mask &= ~PSW_MASK_MCHECK; + S390_lowcore.io_new_psw.mask &= ~PSW_MASK_MCHECK; + S390_lowcore.program_new_psw.mask &= ~PSW_MASK_MCHECK; +} + +void restore_processor_state(void) +{ + S390_lowcore.external_new_psw.mask |= PSW_MASK_MCHECK; + S390_lowcore.svc_new_psw.mask |= PSW_MASK_MCHECK; + S390_lowcore.io_new_psw.mask |= PSW_MASK_MCHECK; + S390_lowcore.program_new_psw.mask |= PSW_MASK_MCHECK; + /* Enable lowcore protection */ + __ctl_set_bit(0,28); + local_mcck_enable(); +} diff --git a/arch/s390/kernel/swsusp_asm64.S b/arch/s390/kernel/swsusp_asm64.S new file mode 100644 index 00000000..dd70ef04 --- /dev/null +++ b/arch/s390/kernel/swsusp_asm64.S @@ -0,0 +1,285 @@ +/* + * S390 64-bit swsusp implementation + * + * Copyright IBM Corp. 2009 + * + * Author(s): Hans-Joachim Picht <hans@linux.vnet.ibm.com> + * Michael Holzheu <holzheu@linux.vnet.ibm.com> + */ + +#include <linux/linkage.h> +#include <asm/page.h> +#include <asm/ptrace.h> +#include <asm/thread_info.h> +#include <asm/asm-offsets.h> + +/* + * Save register context in absolute 0 lowcore and call swsusp_save() to + * create in-memory kernel image. The context is saved in the designated + * "store status" memory locations (see POP). + * We return from this function twice. The first time during the suspend to + * disk process. The second time via the swsusp_arch_resume() function + * (see below) in the resume process. + * This function runs with disabled interrupts. + */ + .section .text +ENTRY(swsusp_arch_suspend) + stmg %r6,%r15,__SF_GPRS(%r15) + lgr %r1,%r15 + aghi %r15,-STACK_FRAME_OVERHEAD + stg %r1,__SF_BACKCHAIN(%r15) + + /* Deactivate DAT */ + stnsm __SF_EMPTY(%r15),0xfb + + /* Store prefix register on stack */ + stpx __SF_EMPTY(%r15) + + /* Save prefix register contents for lowcore */ + llgf %r4,__SF_EMPTY(%r15) + + /* Get pointer to save area */ + lghi %r1,0x1000 + + /* Save CPU address */ + stap __LC_EXT_CPU_ADDR(%r0) + + /* Store registers */ + mvc 0x318(4,%r1),__SF_EMPTY(%r15) /* move prefix to lowcore */ + stfpc 0x31c(%r1) /* store fpu control */ + std 0,0x200(%r1) /* store f0 */ + std 1,0x208(%r1) /* store f1 */ + std 2,0x210(%r1) /* store f2 */ + std 3,0x218(%r1) /* store f3 */ + std 4,0x220(%r1) /* store f4 */ + std 5,0x228(%r1) /* store f5 */ + std 6,0x230(%r1) /* store f6 */ + std 7,0x238(%r1) /* store f7 */ + std 8,0x240(%r1) /* store f8 */ + std 9,0x248(%r1) /* store f9 */ + std 10,0x250(%r1) /* store f10 */ + std 11,0x258(%r1) /* store f11 */ + std 12,0x260(%r1) /* store f12 */ + std 13,0x268(%r1) /* store f13 */ + std 14,0x270(%r1) /* store f14 */ + std 15,0x278(%r1) /* store f15 */ + stam %a0,%a15,0x340(%r1) /* store access registers */ + stctg %c0,%c15,0x380(%r1) /* store control registers */ + stmg %r0,%r15,0x280(%r1) /* store general registers */ + + stpt 0x328(%r1) /* store timer */ + stck __SF_EMPTY(%r15) /* store clock */ + stckc 0x330(%r1) /* store clock comparator */ + + /* Update cputime accounting before going to sleep */ + lg %r0,__LC_LAST_UPDATE_TIMER + slg %r0,0x328(%r1) + alg %r0,__LC_SYSTEM_TIMER + stg %r0,__LC_SYSTEM_TIMER + mvc __LC_LAST_UPDATE_TIMER(8),0x328(%r1) + lg %r0,__LC_LAST_UPDATE_CLOCK + slg %r0,__SF_EMPTY(%r15) + alg %r0,__LC_STEAL_TIMER + stg %r0,__LC_STEAL_TIMER + mvc __LC_LAST_UPDATE_CLOCK(8),__SF_EMPTY(%r15) + + /* Activate DAT */ + stosm __SF_EMPTY(%r15),0x04 + + /* Set prefix page to zero */ + xc __SF_EMPTY(4,%r15),__SF_EMPTY(%r15) + spx __SF_EMPTY(%r15) + + lghi %r2,0 + lghi %r3,2*PAGE_SIZE + lghi %r5,2*PAGE_SIZE +1: mvcle %r2,%r4,0 + jo 1b + + /* Save image */ + brasl %r14,swsusp_save + + /* Restore prefix register and return */ + lghi %r1,0x1000 + spx 0x318(%r1) + lmg %r6,%r15,STACK_FRAME_OVERHEAD + __SF_GPRS(%r15) + lghi %r2,0 + br %r14 + +/* + * Restore saved memory image to correct place and restore register context. + * Then we return to the function that called swsusp_arch_suspend(). + * swsusp_arch_resume() runs with disabled interrupts. + */ +ENTRY(swsusp_arch_resume) + stmg %r6,%r15,__SF_GPRS(%r15) + lgr %r1,%r15 + aghi %r15,-STACK_FRAME_OVERHEAD + stg %r1,__SF_BACKCHAIN(%r15) + + /* Make all free pages stable */ + lghi %r2,1 + brasl %r14,arch_set_page_states + + /* Deactivate DAT */ + stnsm __SF_EMPTY(%r15),0xfb + + /* Set prefix page to zero */ + xc __SF_EMPTY(4,%r15),__SF_EMPTY(%r15) + spx __SF_EMPTY(%r15) + + /* Restore saved image */ + larl %r1,restore_pblist + lg %r1,0(%r1) + ltgr %r1,%r1 + jz 2f +0: + lg %r2,8(%r1) + lg %r4,0(%r1) + iske %r0,%r4 + lghi %r3,PAGE_SIZE + lghi %r5,PAGE_SIZE +1: + mvcle %r2,%r4,0 + jo 1b + lg %r2,8(%r1) + sske %r0,%r2 + lg %r1,16(%r1) + ltgr %r1,%r1 + jnz 0b +2: + ptlb /* flush tlb */ + + /* Reset System */ + larl %r1,restart_entry + larl %r2,.Lrestart_diag308_psw + og %r1,0(%r2) + stg %r1,0(%r0) + larl %r1,.Lnew_pgm_check_psw + epsw %r2,%r3 + stm %r2,%r3,0(%r1) + mvc __LC_PGM_NEW_PSW(16,%r0),0(%r1) + lghi %r0,0 + diag %r0,%r0,0x308 +restart_entry: + lhi %r1,1 + sigp %r1,%r0,0x12 + sam64 + larl %r1,.Lnew_pgm_check_psw + lpswe 0(%r1) +pgm_check_entry: + + /* Switch to original suspend CPU */ + larl %r1,.Lresume_cpu /* Resume CPU address: r2 */ + stap 0(%r1) + llgh %r2,0(%r1) + llgh %r1,__LC_EXT_CPU_ADDR(%r0) /* Suspend CPU address: r1 */ + cgr %r1,%r2 + je restore_registers /* r1 = r2 -> nothing to do */ + larl %r4,.Lrestart_suspend_psw /* Set new restart PSW */ + mvc __LC_RST_NEW_PSW(16,%r0),0(%r4) +3: + sigp %r9,%r1,11 /* sigp initial cpu reset */ + brc 8,4f /* accepted */ + brc 2,3b /* busy, try again */ + + /* Suspend CPU not available -> panic */ + larl %r15,init_thread_union + ahi %r15,1<<(PAGE_SHIFT+THREAD_ORDER) + larl %r2,.Lpanic_string + larl %r3,_sclp_print_early + lghi %r1,0 + sam31 + sigp %r1,%r0,0x12 + basr %r14,%r3 + larl %r3,.Ldisabled_wait_31 + lpsw 0(%r3) +4: + /* Switch to suspend CPU */ + sigp %r9,%r1,6 /* sigp restart to suspend CPU */ + brc 2,4b /* busy, try again */ +5: + sigp %r9,%r2,5 /* sigp stop to current resume CPU */ + brc 2,5b /* busy, try again */ +6: j 6b + +restart_suspend: + larl %r1,.Lresume_cpu + llgh %r2,0(%r1) +7: + sigp %r9,%r2,1 /* sigp sense, wait for resume CPU */ + brc 8,7b /* accepted, status 0, still running */ + brc 2,7b /* busy, try again */ + tmll %r9,0x40 /* Test if resume CPU is stopped */ + jz 7b + +restore_registers: + /* Restore registers */ + lghi %r13,0x1000 /* %r1 = pointer to save area */ + + /* Ignore time spent in suspended state. */ + llgf %r1,0x318(%r13) + stck __LC_LAST_UPDATE_CLOCK(%r1) + spt 0x328(%r13) /* reprogram timer */ + //sckc 0x330(%r13) /* set clock comparator */ + + lctlg %c0,%c15,0x380(%r13) /* load control registers */ + lam %a0,%a15,0x340(%r13) /* load access registers */ + + lfpc 0x31c(%r13) /* load fpu control */ + ld 0,0x200(%r13) /* load f0 */ + ld 1,0x208(%r13) /* load f1 */ + ld 2,0x210(%r13) /* load f2 */ + ld 3,0x218(%r13) /* load f3 */ + ld 4,0x220(%r13) /* load f4 */ + ld 5,0x228(%r13) /* load f5 */ + ld 6,0x230(%r13) /* load f6 */ + ld 7,0x238(%r13) /* load f7 */ + ld 8,0x240(%r13) /* load f8 */ + ld 9,0x248(%r13) /* load f9 */ + ld 10,0x250(%r13) /* load f10 */ + ld 11,0x258(%r13) /* load f11 */ + ld 12,0x260(%r13) /* load f12 */ + ld 13,0x268(%r13) /* load f13 */ + ld 14,0x270(%r13) /* load f14 */ + ld 15,0x278(%r13) /* load f15 */ + + /* Load old stack */ + lg %r15,0x2f8(%r13) + + /* Restore prefix register */ + spx 0x318(%r13) + + /* Activate DAT */ + stosm __SF_EMPTY(%r15),0x04 + + /* Make all free pages unstable */ + lghi %r2,0 + brasl %r14,arch_set_page_states + + /* Log potential guest relocation */ + brasl %r14,lgr_info_log + + /* Reinitialize the channel subsystem */ + brasl %r14,channel_subsystem_reinit + + /* Return 0 */ + lmg %r6,%r15,STACK_FRAME_OVERHEAD + __SF_GPRS(%r15) + lghi %r2,0 + br %r14 + + .section .data..nosave,"aw",@progbits + .align 8 +.Ldisabled_wait_31: + .long 0x000a0000,0x00000000 +.Lpanic_string: + .asciz "Resume not possible because suspend CPU is no longer available" + .align 8 +.Lrestart_diag308_psw: + .long 0x00080000,0x80000000 +.Lrestart_suspend_psw: + .quad 0x0000000180000000,restart_suspend +.Lnew_pgm_check_psw: + .quad 0,pgm_check_entry +.Lresume_cpu: + .byte 0,0 diff --git a/arch/s390/kernel/sys_s390.c b/arch/s390/kernel/sys_s390.c new file mode 100644 index 00000000..78ea1948 --- /dev/null +++ b/arch/s390/kernel/sys_s390.c @@ -0,0 +1,151 @@ +/* + * arch/s390/kernel/sys_s390.c + * + * S390 version + * Copyright (C) 1999,2000 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com), + * Thomas Spatzier (tspat@de.ibm.com) + * + * Derived from "arch/i386/kernel/sys_i386.c" + * + * This file contains various random system calls that + * have a non-standard calling sequence on the Linux/s390 + * platform. + */ + +#include <linux/errno.h> +#include <linux/sched.h> +#include <linux/mm.h> +#include <linux/fs.h> +#include <linux/smp.h> +#include <linux/sem.h> +#include <linux/msg.h> +#include <linux/shm.h> +#include <linux/stat.h> +#include <linux/syscalls.h> +#include <linux/mman.h> +#include <linux/file.h> +#include <linux/utsname.h> +#include <linux/personality.h> +#include <linux/unistd.h> +#include <linux/ipc.h> +#include <asm/uaccess.h> +#include "entry.h" + +/* + * Perform the mmap() system call. Linux for S/390 isn't able to handle more + * than 5 system call parameters, so this system call uses a memory block + * for parameter passing. + */ + +struct s390_mmap_arg_struct { + unsigned long addr; + unsigned long len; + unsigned long prot; + unsigned long flags; + unsigned long fd; + unsigned long offset; +}; + +SYSCALL_DEFINE1(mmap2, struct s390_mmap_arg_struct __user *, arg) +{ + struct s390_mmap_arg_struct a; + int error = -EFAULT; + + if (copy_from_user(&a, arg, sizeof(a))) + goto out; + error = sys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd, a.offset); +out: + return error; +} + +/* + * sys_ipc() is the de-multiplexer for the SysV IPC calls. + */ +SYSCALL_DEFINE5(s390_ipc, uint, call, int, first, unsigned long, second, + unsigned long, third, void __user *, ptr) +{ + if (call >> 16) + return -EINVAL; + /* The s390 sys_ipc variant has only five parameters instead of six + * like the generic variant. The only difference is the handling of + * the SEMTIMEDOP subcall where on s390 the third parameter is used + * as a pointer to a struct timespec where the generic variant uses + * the fifth parameter. + * Therefore we can call the generic variant by simply passing the + * third parameter also as fifth parameter. + */ + return sys_ipc(call, first, second, third, ptr, third); +} + +#ifdef CONFIG_64BIT +SYSCALL_DEFINE1(s390_personality, unsigned int, personality) +{ + unsigned int ret; + + if (current->personality == PER_LINUX32 && personality == PER_LINUX) + personality = PER_LINUX32; + ret = sys_personality(personality); + if (ret == PER_LINUX32) + ret = PER_LINUX; + + return ret; +} +#endif /* CONFIG_64BIT */ + +/* + * Wrapper function for sys_fadvise64/fadvise64_64 + */ +#ifndef CONFIG_64BIT + +SYSCALL_DEFINE5(s390_fadvise64, int, fd, u32, offset_high, u32, offset_low, + size_t, len, int, advice) +{ + return sys_fadvise64(fd, (u64) offset_high << 32 | offset_low, + len, advice); +} + +struct fadvise64_64_args { + int fd; + long long offset; + long long len; + int advice; +}; + +SYSCALL_DEFINE1(s390_fadvise64_64, struct fadvise64_64_args __user *, args) +{ + struct fadvise64_64_args a; + + if ( copy_from_user(&a, args, sizeof(a)) ) + return -EFAULT; + return sys_fadvise64_64(a.fd, a.offset, a.len, a.advice); +} + +/* + * This is a wrapper to call sys_fallocate(). For 31 bit s390 the last + * 64 bit argument "len" is split into the upper and lower 32 bits. The + * system call wrapper in the user space loads the value to %r6/%r7. + * The code in entry.S keeps the values in %r2 - %r6 where they are and + * stores %r7 to 96(%r15). But the standard C linkage requires that + * the whole 64 bit value for len is stored on the stack and doesn't + * use %r6 at all. So s390_fallocate has to convert the arguments from + * %r2: fd, %r3: mode, %r4/%r5: offset, %r6/96(%r15)-99(%r15): len + * to + * %r2: fd, %r3: mode, %r4/%r5: offset, 96(%r15)-103(%r15): len + */ +SYSCALL_DEFINE(s390_fallocate)(int fd, int mode, loff_t offset, + u32 len_high, u32 len_low) +{ + return sys_fallocate(fd, mode, offset, ((u64)len_high << 32) | len_low); +} +#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS +asmlinkage long SyS_s390_fallocate(long fd, long mode, loff_t offset, + long len_high, long len_low) +{ + return SYSC_s390_fallocate((int) fd, (int) mode, offset, + (u32) len_high, (u32) len_low); +} +SYSCALL_ALIAS(sys_s390_fallocate, SyS_s390_fallocate); +#endif + +#endif diff --git a/arch/s390/kernel/syscalls.S b/arch/s390/kernel/syscalls.S new file mode 100644 index 00000000..bcab2f04 --- /dev/null +++ b/arch/s390/kernel/syscalls.S @@ -0,0 +1,352 @@ +/* + * definitions for sys_call_table, each line represents an + * entry in the table in the form + * SYSCALL(31 bit syscall, 64 bit syscall, 31 bit emulated syscall) + * + * this file is meant to be included from entry.S and entry64.S + */ + +#define NI_SYSCALL SYSCALL(sys_ni_syscall,sys_ni_syscall,sys_ni_syscall) + +NI_SYSCALL /* 0 */ +SYSCALL(sys_exit,sys_exit,sys32_exit_wrapper) +SYSCALL(sys_fork,sys_fork,sys_fork) +SYSCALL(sys_read,sys_read,sys32_read_wrapper) +SYSCALL(sys_write,sys_write,sys32_write_wrapper) +SYSCALL(sys_open,sys_open,sys32_open_wrapper) /* 5 */ +SYSCALL(sys_close,sys_close,sys32_close_wrapper) +SYSCALL(sys_restart_syscall,sys_restart_syscall,sys_restart_syscall) +SYSCALL(sys_creat,sys_creat,sys32_creat_wrapper) +SYSCALL(sys_link,sys_link,sys32_link_wrapper) +SYSCALL(sys_unlink,sys_unlink,sys32_unlink_wrapper) /* 10 */ +SYSCALL(sys_execve,sys_execve,sys32_execve_wrapper) +SYSCALL(sys_chdir,sys_chdir,sys32_chdir_wrapper) +SYSCALL(sys_time,sys_ni_syscall,sys32_time_wrapper) /* old time syscall */ +SYSCALL(sys_mknod,sys_mknod,sys32_mknod_wrapper) +SYSCALL(sys_chmod,sys_chmod,sys32_chmod_wrapper) /* 15 */ +SYSCALL(sys_lchown16,sys_ni_syscall,sys32_lchown16_wrapper) /* old lchown16 syscall*/ +NI_SYSCALL /* old break syscall holder */ +NI_SYSCALL /* old stat syscall holder */ +SYSCALL(sys_lseek,sys_lseek,sys32_lseek_wrapper) +SYSCALL(sys_getpid,sys_getpid,sys_getpid) /* 20 */ +SYSCALL(sys_mount,sys_mount,sys32_mount_wrapper) +SYSCALL(sys_oldumount,sys_oldumount,sys32_oldumount_wrapper) +SYSCALL(sys_setuid16,sys_ni_syscall,sys32_setuid16_wrapper) /* old setuid16 syscall*/ +SYSCALL(sys_getuid16,sys_ni_syscall,sys32_getuid16) /* old getuid16 syscall*/ +SYSCALL(sys_stime,sys_ni_syscall,sys32_stime_wrapper) /* 25 old stime syscall */ +SYSCALL(sys_ptrace,sys_ptrace,sys32_ptrace_wrapper) +SYSCALL(sys_alarm,sys_alarm,sys32_alarm_wrapper) +NI_SYSCALL /* old fstat syscall */ +SYSCALL(sys_pause,sys_pause,sys_pause) +SYSCALL(sys_utime,sys_utime,compat_sys_utime_wrapper) /* 30 */ +NI_SYSCALL /* old stty syscall */ +NI_SYSCALL /* old gtty syscall */ +SYSCALL(sys_access,sys_access,sys32_access_wrapper) +SYSCALL(sys_nice,sys_nice,sys32_nice_wrapper) +NI_SYSCALL /* 35 old ftime syscall */ +SYSCALL(sys_sync,sys_sync,sys_sync) +SYSCALL(sys_kill,sys_kill,sys32_kill_wrapper) +SYSCALL(sys_rename,sys_rename,sys32_rename_wrapper) +SYSCALL(sys_mkdir,sys_mkdir,sys32_mkdir_wrapper) +SYSCALL(sys_rmdir,sys_rmdir,sys32_rmdir_wrapper) /* 40 */ +SYSCALL(sys_dup,sys_dup,sys32_dup_wrapper) +SYSCALL(sys_pipe,sys_pipe,sys32_pipe_wrapper) +SYSCALL(sys_times,sys_times,compat_sys_times_wrapper) +NI_SYSCALL /* old prof syscall */ +SYSCALL(sys_brk,sys_brk,sys32_brk_wrapper) /* 45 */ +SYSCALL(sys_setgid16,sys_ni_syscall,sys32_setgid16_wrapper) /* old setgid16 syscall*/ +SYSCALL(sys_getgid16,sys_ni_syscall,sys32_getgid16) /* old getgid16 syscall*/ +SYSCALL(sys_signal,sys_signal,sys32_signal_wrapper) +SYSCALL(sys_geteuid16,sys_ni_syscall,sys32_geteuid16) /* old geteuid16 syscall */ +SYSCALL(sys_getegid16,sys_ni_syscall,sys32_getegid16) /* 50 old getegid16 syscall */ +SYSCALL(sys_acct,sys_acct,sys32_acct_wrapper) +SYSCALL(sys_umount,sys_umount,sys32_umount_wrapper) +NI_SYSCALL /* old lock syscall */ +SYSCALL(sys_ioctl,sys_ioctl,compat_sys_ioctl_wrapper) +SYSCALL(sys_fcntl,sys_fcntl,compat_sys_fcntl_wrapper) /* 55 */ +NI_SYSCALL /* intel mpx syscall */ +SYSCALL(sys_setpgid,sys_setpgid,sys32_setpgid_wrapper) +NI_SYSCALL /* old ulimit syscall */ +NI_SYSCALL /* old uname syscall */ +SYSCALL(sys_umask,sys_umask,sys32_umask_wrapper) /* 60 */ +SYSCALL(sys_chroot,sys_chroot,sys32_chroot_wrapper) +SYSCALL(sys_ustat,sys_ustat,sys32_ustat_wrapper) +SYSCALL(sys_dup2,sys_dup2,sys32_dup2_wrapper) +SYSCALL(sys_getppid,sys_getppid,sys_getppid) +SYSCALL(sys_getpgrp,sys_getpgrp,sys_getpgrp) /* 65 */ +SYSCALL(sys_setsid,sys_setsid,sys_setsid) +SYSCALL(sys_sigaction,sys_sigaction,sys32_sigaction_wrapper) +NI_SYSCALL /* old sgetmask syscall*/ +NI_SYSCALL /* old ssetmask syscall*/ +SYSCALL(sys_setreuid16,sys_ni_syscall,sys32_setreuid16_wrapper) /* old setreuid16 syscall */ +SYSCALL(sys_setregid16,sys_ni_syscall,sys32_setregid16_wrapper) /* old setregid16 syscall */ +SYSCALL(sys_sigsuspend,sys_sigsuspend,sys_sigsuspend_wrapper) +SYSCALL(sys_sigpending,sys_sigpending,compat_sys_sigpending_wrapper) +SYSCALL(sys_sethostname,sys_sethostname,sys32_sethostname_wrapper) +SYSCALL(sys_setrlimit,sys_setrlimit,compat_sys_setrlimit_wrapper) /* 75 */ +SYSCALL(sys_old_getrlimit,sys_getrlimit,compat_sys_old_getrlimit_wrapper) +SYSCALL(sys_getrusage,sys_getrusage,compat_sys_getrusage_wrapper) +SYSCALL(sys_gettimeofday,sys_gettimeofday,compat_sys_gettimeofday_wrapper) +SYSCALL(sys_settimeofday,sys_settimeofday,compat_sys_settimeofday_wrapper) +SYSCALL(sys_getgroups16,sys_ni_syscall,sys32_getgroups16_wrapper) /* 80 old getgroups16 syscall */ +SYSCALL(sys_setgroups16,sys_ni_syscall,sys32_setgroups16_wrapper) /* old setgroups16 syscall */ +NI_SYSCALL /* old select syscall */ +SYSCALL(sys_symlink,sys_symlink,sys32_symlink_wrapper) +NI_SYSCALL /* old lstat syscall */ +SYSCALL(sys_readlink,sys_readlink,sys32_readlink_wrapper) /* 85 */ +SYSCALL(sys_uselib,sys_uselib,sys32_uselib_wrapper) +SYSCALL(sys_swapon,sys_swapon,sys32_swapon_wrapper) +SYSCALL(sys_reboot,sys_reboot,sys32_reboot_wrapper) +SYSCALL(sys_ni_syscall,sys_ni_syscall,old32_readdir_wrapper) /* old readdir syscall */ +SYSCALL(sys_old_mmap,sys_old_mmap,old32_mmap_wrapper) /* 90 */ +SYSCALL(sys_munmap,sys_munmap,sys32_munmap_wrapper) +SYSCALL(sys_truncate,sys_truncate,sys32_truncate_wrapper) +SYSCALL(sys_ftruncate,sys_ftruncate,sys32_ftruncate_wrapper) +SYSCALL(sys_fchmod,sys_fchmod,sys32_fchmod_wrapper) +SYSCALL(sys_fchown16,sys_ni_syscall,sys32_fchown16_wrapper) /* 95 old fchown16 syscall*/ +SYSCALL(sys_getpriority,sys_getpriority,sys32_getpriority_wrapper) +SYSCALL(sys_setpriority,sys_setpriority,sys32_setpriority_wrapper) +NI_SYSCALL /* old profil syscall */ +SYSCALL(sys_statfs,sys_statfs,compat_sys_statfs_wrapper) +SYSCALL(sys_fstatfs,sys_fstatfs,compat_sys_fstatfs_wrapper) /* 100 */ +NI_SYSCALL /* ioperm for i386 */ +SYSCALL(sys_socketcall,sys_socketcall,compat_sys_socketcall_wrapper) +SYSCALL(sys_syslog,sys_syslog,sys32_syslog_wrapper) +SYSCALL(sys_setitimer,sys_setitimer,compat_sys_setitimer_wrapper) +SYSCALL(sys_getitimer,sys_getitimer,compat_sys_getitimer_wrapper) /* 105 */ +SYSCALL(sys_newstat,sys_newstat,compat_sys_newstat_wrapper) +SYSCALL(sys_newlstat,sys_newlstat,compat_sys_newlstat_wrapper) +SYSCALL(sys_newfstat,sys_newfstat,compat_sys_newfstat_wrapper) +NI_SYSCALL /* old uname syscall */ +SYSCALL(sys_lookup_dcookie,sys_lookup_dcookie,sys32_lookup_dcookie_wrapper) /* 110 */ +SYSCALL(sys_vhangup,sys_vhangup,sys_vhangup) +NI_SYSCALL /* old "idle" system call */ +NI_SYSCALL /* vm86old for i386 */ +SYSCALL(sys_wait4,sys_wait4,compat_sys_wait4_wrapper) +SYSCALL(sys_swapoff,sys_swapoff,sys32_swapoff_wrapper) /* 115 */ +SYSCALL(sys_sysinfo,sys_sysinfo,compat_sys_sysinfo_wrapper) +SYSCALL(sys_s390_ipc,sys_s390_ipc,sys32_ipc_wrapper) +SYSCALL(sys_fsync,sys_fsync,sys32_fsync_wrapper) +SYSCALL(sys_sigreturn,sys_sigreturn,sys32_sigreturn) +SYSCALL(sys_clone,sys_clone,sys_clone_wrapper) /* 120 */ +SYSCALL(sys_setdomainname,sys_setdomainname,sys32_setdomainname_wrapper) +SYSCALL(sys_newuname,sys_newuname,sys32_newuname_wrapper) +NI_SYSCALL /* modify_ldt for i386 */ +SYSCALL(sys_adjtimex,sys_adjtimex,compat_sys_adjtimex_wrapper) +SYSCALL(sys_mprotect,sys_mprotect,sys32_mprotect_wrapper) /* 125 */ +SYSCALL(sys_sigprocmask,sys_sigprocmask,compat_sys_sigprocmask_wrapper) +NI_SYSCALL /* old "create module" */ +SYSCALL(sys_init_module,sys_init_module,sys_init_module_wrapper) +SYSCALL(sys_delete_module,sys_delete_module,sys_delete_module_wrapper) +NI_SYSCALL /* 130: old get_kernel_syms */ +SYSCALL(sys_quotactl,sys_quotactl,sys32_quotactl_wrapper) +SYSCALL(sys_getpgid,sys_getpgid,sys32_getpgid_wrapper) +SYSCALL(sys_fchdir,sys_fchdir,sys32_fchdir_wrapper) +SYSCALL(sys_bdflush,sys_bdflush,sys32_bdflush_wrapper) +SYSCALL(sys_sysfs,sys_sysfs,sys32_sysfs_wrapper) /* 135 */ +SYSCALL(sys_personality,sys_s390_personality,sys32_personality_wrapper) +NI_SYSCALL /* for afs_syscall */ +SYSCALL(sys_setfsuid16,sys_ni_syscall,sys32_setfsuid16_wrapper) /* old setfsuid16 syscall */ +SYSCALL(sys_setfsgid16,sys_ni_syscall,sys32_setfsgid16_wrapper) /* old setfsgid16 syscall */ +SYSCALL(sys_llseek,sys_llseek,sys32_llseek_wrapper) /* 140 */ +SYSCALL(sys_getdents,sys_getdents,sys32_getdents_wrapper) +SYSCALL(sys_select,sys_select,compat_sys_select_wrapper) +SYSCALL(sys_flock,sys_flock,sys32_flock_wrapper) +SYSCALL(sys_msync,sys_msync,sys32_msync_wrapper) +SYSCALL(sys_readv,sys_readv,compat_sys_readv_wrapper) /* 145 */ +SYSCALL(sys_writev,sys_writev,compat_sys_writev_wrapper) +SYSCALL(sys_getsid,sys_getsid,sys32_getsid_wrapper) +SYSCALL(sys_fdatasync,sys_fdatasync,sys32_fdatasync_wrapper) +SYSCALL(sys_sysctl,sys_sysctl,sys32_sysctl_wrapper) +SYSCALL(sys_mlock,sys_mlock,sys32_mlock_wrapper) /* 150 */ +SYSCALL(sys_munlock,sys_munlock,sys32_munlock_wrapper) +SYSCALL(sys_mlockall,sys_mlockall,sys32_mlockall_wrapper) +SYSCALL(sys_munlockall,sys_munlockall,sys_munlockall) +SYSCALL(sys_sched_setparam,sys_sched_setparam,sys32_sched_setparam_wrapper) +SYSCALL(sys_sched_getparam,sys_sched_getparam,sys32_sched_getparam_wrapper) /* 155 */ +SYSCALL(sys_sched_setscheduler,sys_sched_setscheduler,sys32_sched_setscheduler_wrapper) +SYSCALL(sys_sched_getscheduler,sys_sched_getscheduler,sys32_sched_getscheduler_wrapper) +SYSCALL(sys_sched_yield,sys_sched_yield,sys_sched_yield) +SYSCALL(sys_sched_get_priority_max,sys_sched_get_priority_max,sys32_sched_get_priority_max_wrapper) +SYSCALL(sys_sched_get_priority_min,sys_sched_get_priority_min,sys32_sched_get_priority_min_wrapper) /* 160 */ +SYSCALL(sys_sched_rr_get_interval,sys_sched_rr_get_interval,sys32_sched_rr_get_interval_wrapper) +SYSCALL(sys_nanosleep,sys_nanosleep,compat_sys_nanosleep_wrapper) +SYSCALL(sys_mremap,sys_mremap,sys32_mremap_wrapper) +SYSCALL(sys_setresuid16,sys_ni_syscall,sys32_setresuid16_wrapper) /* old setresuid16 syscall */ +SYSCALL(sys_getresuid16,sys_ni_syscall,sys32_getresuid16_wrapper) /* 165 old getresuid16 syscall */ +NI_SYSCALL /* for vm86 */ +NI_SYSCALL /* old sys_query_module */ +SYSCALL(sys_poll,sys_poll,sys32_poll_wrapper) +NI_SYSCALL /* old nfsservctl */ +SYSCALL(sys_setresgid16,sys_ni_syscall,sys32_setresgid16_wrapper) /* 170 old setresgid16 syscall */ +SYSCALL(sys_getresgid16,sys_ni_syscall,sys32_getresgid16_wrapper) /* old getresgid16 syscall */ +SYSCALL(sys_prctl,sys_prctl,sys32_prctl_wrapper) +SYSCALL(sys_rt_sigreturn,sys_rt_sigreturn,sys32_rt_sigreturn) +SYSCALL(sys_rt_sigaction,sys_rt_sigaction,sys32_rt_sigaction_wrapper) +SYSCALL(sys_rt_sigprocmask,sys_rt_sigprocmask,sys32_rt_sigprocmask_wrapper) /* 175 */ +SYSCALL(sys_rt_sigpending,sys_rt_sigpending,sys32_rt_sigpending_wrapper) +SYSCALL(sys_rt_sigtimedwait,sys_rt_sigtimedwait,compat_sys_rt_sigtimedwait_wrapper) +SYSCALL(sys_rt_sigqueueinfo,sys_rt_sigqueueinfo,sys32_rt_sigqueueinfo_wrapper) +SYSCALL(sys_rt_sigsuspend,sys_rt_sigsuspend,compat_sys_rt_sigsuspend_wrapper) +SYSCALL(sys_pread64,sys_pread64,sys32_pread64_wrapper) /* 180 */ +SYSCALL(sys_pwrite64,sys_pwrite64,sys32_pwrite64_wrapper) +SYSCALL(sys_chown16,sys_ni_syscall,sys32_chown16_wrapper) /* old chown16 syscall */ +SYSCALL(sys_getcwd,sys_getcwd,sys32_getcwd_wrapper) +SYSCALL(sys_capget,sys_capget,sys32_capget_wrapper) +SYSCALL(sys_capset,sys_capset,sys32_capset_wrapper) /* 185 */ +SYSCALL(sys_sigaltstack,sys_sigaltstack,sys32_sigaltstack_wrapper) +SYSCALL(sys_sendfile,sys_sendfile64,sys32_sendfile_wrapper) +NI_SYSCALL /* streams1 */ +NI_SYSCALL /* streams2 */ +SYSCALL(sys_vfork,sys_vfork,sys_vfork) /* 190 */ +SYSCALL(sys_getrlimit,sys_getrlimit,compat_sys_getrlimit_wrapper) +SYSCALL(sys_mmap2,sys_mmap2,sys32_mmap2_wrapper) +SYSCALL(sys_truncate64,sys_ni_syscall,sys32_truncate64_wrapper) +SYSCALL(sys_ftruncate64,sys_ni_syscall,sys32_ftruncate64_wrapper) +SYSCALL(sys_stat64,sys_ni_syscall,sys32_stat64_wrapper) /* 195 */ +SYSCALL(sys_lstat64,sys_ni_syscall,sys32_lstat64_wrapper) +SYSCALL(sys_fstat64,sys_ni_syscall,sys32_fstat64_wrapper) +SYSCALL(sys_lchown,sys_lchown,sys32_lchown_wrapper) +SYSCALL(sys_getuid,sys_getuid,sys_getuid) +SYSCALL(sys_getgid,sys_getgid,sys_getgid) /* 200 */ +SYSCALL(sys_geteuid,sys_geteuid,sys_geteuid) +SYSCALL(sys_getegid,sys_getegid,sys_getegid) +SYSCALL(sys_setreuid,sys_setreuid,sys32_setreuid_wrapper) +SYSCALL(sys_setregid,sys_setregid,sys32_setregid_wrapper) +SYSCALL(sys_getgroups,sys_getgroups,sys32_getgroups_wrapper) /* 205 */ +SYSCALL(sys_setgroups,sys_setgroups,sys32_setgroups_wrapper) +SYSCALL(sys_fchown,sys_fchown,sys32_fchown_wrapper) +SYSCALL(sys_setresuid,sys_setresuid,sys32_setresuid_wrapper) +SYSCALL(sys_getresuid,sys_getresuid,sys32_getresuid_wrapper) +SYSCALL(sys_setresgid,sys_setresgid,sys32_setresgid_wrapper) /* 210 */ +SYSCALL(sys_getresgid,sys_getresgid,sys32_getresgid_wrapper) +SYSCALL(sys_chown,sys_chown,sys32_chown_wrapper) +SYSCALL(sys_setuid,sys_setuid,sys32_setuid_wrapper) +SYSCALL(sys_setgid,sys_setgid,sys32_setgid_wrapper) +SYSCALL(sys_setfsuid,sys_setfsuid,sys32_setfsuid_wrapper) /* 215 */ +SYSCALL(sys_setfsgid,sys_setfsgid,sys32_setfsgid_wrapper) +SYSCALL(sys_pivot_root,sys_pivot_root,sys32_pivot_root_wrapper) +SYSCALL(sys_mincore,sys_mincore,sys32_mincore_wrapper) +SYSCALL(sys_madvise,sys_madvise,sys32_madvise_wrapper) +SYSCALL(sys_getdents64,sys_getdents64,sys32_getdents64_wrapper) /* 220 */ +SYSCALL(sys_fcntl64,sys_ni_syscall,compat_sys_fcntl64_wrapper) +SYSCALL(sys_readahead,sys_readahead,sys32_readahead_wrapper) +SYSCALL(sys_sendfile64,sys_ni_syscall,sys32_sendfile64_wrapper) +SYSCALL(sys_setxattr,sys_setxattr,sys32_setxattr_wrapper) +SYSCALL(sys_lsetxattr,sys_lsetxattr,sys32_lsetxattr_wrapper) /* 225 */ +SYSCALL(sys_fsetxattr,sys_fsetxattr,sys32_fsetxattr_wrapper) +SYSCALL(sys_getxattr,sys_getxattr,sys32_getxattr_wrapper) +SYSCALL(sys_lgetxattr,sys_lgetxattr,sys32_lgetxattr_wrapper) +SYSCALL(sys_fgetxattr,sys_fgetxattr,sys32_fgetxattr_wrapper) +SYSCALL(sys_listxattr,sys_listxattr,sys32_listxattr_wrapper) /* 230 */ +SYSCALL(sys_llistxattr,sys_llistxattr,sys32_llistxattr_wrapper) +SYSCALL(sys_flistxattr,sys_flistxattr,sys32_flistxattr_wrapper) +SYSCALL(sys_removexattr,sys_removexattr,sys32_removexattr_wrapper) +SYSCALL(sys_lremovexattr,sys_lremovexattr,sys32_lremovexattr_wrapper) +SYSCALL(sys_fremovexattr,sys_fremovexattr,sys32_fremovexattr_wrapper) /* 235 */ +SYSCALL(sys_gettid,sys_gettid,sys_gettid) +SYSCALL(sys_tkill,sys_tkill,sys_tkill_wrapper) +SYSCALL(sys_futex,sys_futex,compat_sys_futex_wrapper) +SYSCALL(sys_sched_setaffinity,sys_sched_setaffinity,sys32_sched_setaffinity_wrapper) +SYSCALL(sys_sched_getaffinity,sys_sched_getaffinity,sys32_sched_getaffinity_wrapper) /* 240 */ +SYSCALL(sys_tgkill,sys_tgkill,sys_tgkill_wrapper) +NI_SYSCALL /* reserved for TUX */ +SYSCALL(sys_io_setup,sys_io_setup,sys32_io_setup_wrapper) +SYSCALL(sys_io_destroy,sys_io_destroy,sys32_io_destroy_wrapper) +SYSCALL(sys_io_getevents,sys_io_getevents,sys32_io_getevents_wrapper) /* 245 */ +SYSCALL(sys_io_submit,sys_io_submit,sys32_io_submit_wrapper) +SYSCALL(sys_io_cancel,sys_io_cancel,sys32_io_cancel_wrapper) +SYSCALL(sys_exit_group,sys_exit_group,sys32_exit_group_wrapper) +SYSCALL(sys_epoll_create,sys_epoll_create,sys_epoll_create_wrapper) +SYSCALL(sys_epoll_ctl,sys_epoll_ctl,sys_epoll_ctl_wrapper) /* 250 */ +SYSCALL(sys_epoll_wait,sys_epoll_wait,sys_epoll_wait_wrapper) +SYSCALL(sys_set_tid_address,sys_set_tid_address,sys32_set_tid_address_wrapper) +SYSCALL(sys_s390_fadvise64,sys_fadvise64_64,sys32_fadvise64_wrapper) +SYSCALL(sys_timer_create,sys_timer_create,sys32_timer_create_wrapper) +SYSCALL(sys_timer_settime,sys_timer_settime,sys32_timer_settime_wrapper) /* 255 */ +SYSCALL(sys_timer_gettime,sys_timer_gettime,sys32_timer_gettime_wrapper) +SYSCALL(sys_timer_getoverrun,sys_timer_getoverrun,sys32_timer_getoverrun_wrapper) +SYSCALL(sys_timer_delete,sys_timer_delete,sys32_timer_delete_wrapper) +SYSCALL(sys_clock_settime,sys_clock_settime,sys32_clock_settime_wrapper) +SYSCALL(sys_clock_gettime,sys_clock_gettime,sys32_clock_gettime_wrapper) /* 260 */ +SYSCALL(sys_clock_getres,sys_clock_getres,sys32_clock_getres_wrapper) +SYSCALL(sys_clock_nanosleep,sys_clock_nanosleep,sys32_clock_nanosleep_wrapper) +NI_SYSCALL /* reserved for vserver */ +SYSCALL(sys_s390_fadvise64_64,sys_ni_syscall,sys32_fadvise64_64_wrapper) +SYSCALL(sys_statfs64,sys_statfs64,compat_sys_statfs64_wrapper) +SYSCALL(sys_fstatfs64,sys_fstatfs64,compat_sys_fstatfs64_wrapper) +SYSCALL(sys_remap_file_pages,sys_remap_file_pages,sys32_remap_file_pages_wrapper) +NI_SYSCALL /* 268 sys_mbind */ +NI_SYSCALL /* 269 sys_get_mempolicy */ +NI_SYSCALL /* 270 sys_set_mempolicy */ +SYSCALL(sys_mq_open,sys_mq_open,compat_sys_mq_open_wrapper) +SYSCALL(sys_mq_unlink,sys_mq_unlink,sys32_mq_unlink_wrapper) +SYSCALL(sys_mq_timedsend,sys_mq_timedsend,compat_sys_mq_timedsend_wrapper) +SYSCALL(sys_mq_timedreceive,sys_mq_timedreceive,compat_sys_mq_timedreceive_wrapper) +SYSCALL(sys_mq_notify,sys_mq_notify,compat_sys_mq_notify_wrapper) /* 275 */ +SYSCALL(sys_mq_getsetattr,sys_mq_getsetattr,compat_sys_mq_getsetattr_wrapper) +SYSCALL(sys_kexec_load,sys_kexec_load,compat_sys_kexec_load_wrapper) +SYSCALL(sys_add_key,sys_add_key,compat_sys_add_key_wrapper) +SYSCALL(sys_request_key,sys_request_key,compat_sys_request_key_wrapper) +SYSCALL(sys_keyctl,sys_keyctl,compat_sys_keyctl_wrapper) /* 280 */ +SYSCALL(sys_waitid,sys_waitid,compat_sys_waitid_wrapper) +SYSCALL(sys_ioprio_set,sys_ioprio_set,sys_ioprio_set_wrapper) +SYSCALL(sys_ioprio_get,sys_ioprio_get,sys_ioprio_get_wrapper) +SYSCALL(sys_inotify_init,sys_inotify_init,sys_inotify_init) +SYSCALL(sys_inotify_add_watch,sys_inotify_add_watch,sys_inotify_add_watch_wrapper) /* 285 */ +SYSCALL(sys_inotify_rm_watch,sys_inotify_rm_watch,sys_inotify_rm_watch_wrapper) +NI_SYSCALL /* 287 sys_migrate_pages */ +SYSCALL(sys_openat,sys_openat,compat_sys_openat_wrapper) +SYSCALL(sys_mkdirat,sys_mkdirat,sys_mkdirat_wrapper) +SYSCALL(sys_mknodat,sys_mknodat,sys_mknodat_wrapper) /* 290 */ +SYSCALL(sys_fchownat,sys_fchownat,sys_fchownat_wrapper) +SYSCALL(sys_futimesat,sys_futimesat,compat_sys_futimesat_wrapper) +SYSCALL(sys_fstatat64,sys_newfstatat,sys32_fstatat64_wrapper) +SYSCALL(sys_unlinkat,sys_unlinkat,sys_unlinkat_wrapper) +SYSCALL(sys_renameat,sys_renameat,sys_renameat_wrapper) /* 295 */ +SYSCALL(sys_linkat,sys_linkat,sys_linkat_wrapper) +SYSCALL(sys_symlinkat,sys_symlinkat,sys_symlinkat_wrapper) +SYSCALL(sys_readlinkat,sys_readlinkat,sys_readlinkat_wrapper) +SYSCALL(sys_fchmodat,sys_fchmodat,sys_fchmodat_wrapper) +SYSCALL(sys_faccessat,sys_faccessat,sys_faccessat_wrapper) /* 300 */ +SYSCALL(sys_pselect6,sys_pselect6,compat_sys_pselect6_wrapper) +SYSCALL(sys_ppoll,sys_ppoll,compat_sys_ppoll_wrapper) +SYSCALL(sys_unshare,sys_unshare,sys_unshare_wrapper) +SYSCALL(sys_set_robust_list,sys_set_robust_list,compat_sys_set_robust_list_wrapper) +SYSCALL(sys_get_robust_list,sys_get_robust_list,compat_sys_get_robust_list_wrapper) +SYSCALL(sys_splice,sys_splice,sys_splice_wrapper) +SYSCALL(sys_sync_file_range,sys_sync_file_range,sys_sync_file_range_wrapper) +SYSCALL(sys_tee,sys_tee,sys_tee_wrapper) +SYSCALL(sys_vmsplice,sys_vmsplice,compat_sys_vmsplice_wrapper) +NI_SYSCALL /* 310 sys_move_pages */ +SYSCALL(sys_getcpu,sys_getcpu,sys_getcpu_wrapper) +SYSCALL(sys_epoll_pwait,sys_epoll_pwait,compat_sys_epoll_pwait_wrapper) +SYSCALL(sys_utimes,sys_utimes,compat_sys_utimes_wrapper) +SYSCALL(sys_s390_fallocate,sys_fallocate,sys_fallocate_wrapper) +SYSCALL(sys_utimensat,sys_utimensat,compat_sys_utimensat_wrapper) /* 315 */ +SYSCALL(sys_signalfd,sys_signalfd,compat_sys_signalfd_wrapper) +NI_SYSCALL /* 317 old sys_timer_fd */ +SYSCALL(sys_eventfd,sys_eventfd,sys_eventfd_wrapper) +SYSCALL(sys_timerfd_create,sys_timerfd_create,sys_timerfd_create_wrapper) +SYSCALL(sys_timerfd_settime,sys_timerfd_settime,compat_sys_timerfd_settime_wrapper) /* 320 */ +SYSCALL(sys_timerfd_gettime,sys_timerfd_gettime,compat_sys_timerfd_gettime_wrapper) +SYSCALL(sys_signalfd4,sys_signalfd4,compat_sys_signalfd4_wrapper) +SYSCALL(sys_eventfd2,sys_eventfd2,sys_eventfd2_wrapper) +SYSCALL(sys_inotify_init1,sys_inotify_init1,sys_inotify_init1_wrapper) +SYSCALL(sys_pipe2,sys_pipe2,sys_pipe2_wrapper) /* 325 */ +SYSCALL(sys_dup3,sys_dup3,sys_dup3_wrapper) +SYSCALL(sys_epoll_create1,sys_epoll_create1,sys_epoll_create1_wrapper) +SYSCALL(sys_preadv,sys_preadv,compat_sys_preadv_wrapper) +SYSCALL(sys_pwritev,sys_pwritev,compat_sys_pwritev_wrapper) +SYSCALL(sys_rt_tgsigqueueinfo,sys_rt_tgsigqueueinfo,compat_sys_rt_tgsigqueueinfo_wrapper) /* 330 */ +SYSCALL(sys_perf_event_open,sys_perf_event_open,sys_perf_event_open_wrapper) +SYSCALL(sys_fanotify_init,sys_fanotify_init,sys_fanotify_init_wrapper) +SYSCALL(sys_fanotify_mark,sys_fanotify_mark,sys_fanotify_mark_wrapper) +SYSCALL(sys_prlimit64,sys_prlimit64,sys_prlimit64_wrapper) +SYSCALL(sys_name_to_handle_at,sys_name_to_handle_at,sys_name_to_handle_at_wrapper) /* 335 */ +SYSCALL(sys_open_by_handle_at,sys_open_by_handle_at,compat_sys_open_by_handle_at_wrapper) +SYSCALL(sys_clock_adjtime,sys_clock_adjtime,compat_sys_clock_adjtime_wrapper) +SYSCALL(sys_syncfs,sys_syncfs,sys_syncfs_wrapper) +SYSCALL(sys_setns,sys_setns,sys_setns_wrapper) +SYSCALL(sys_process_vm_readv,sys_process_vm_readv,compat_sys_process_vm_readv_wrapper) /* 340 */ +SYSCALL(sys_process_vm_writev,sys_process_vm_writev,compat_sys_process_vm_writev_wrapper) diff --git a/arch/s390/kernel/sysinfo.c b/arch/s390/kernel/sysinfo.c new file mode 100644 index 00000000..2a94b774 --- /dev/null +++ b/arch/s390/kernel/sysinfo.c @@ -0,0 +1,470 @@ +/* + * Copyright IBM Corp. 2001, 2009 + * Author(s): Ulrich Weigand <Ulrich.Weigand@de.ibm.com>, + * Martin Schwidefsky <schwidefsky@de.ibm.com>, + */ + +#include <linux/kernel.h> +#include <linux/mm.h> +#include <linux/proc_fs.h> +#include <linux/seq_file.h> +#include <linux/init.h> +#include <linux/delay.h> +#include <linux/module.h> +#include <linux/slab.h> +#include <asm/ebcdic.h> +#include <asm/sysinfo.h> +#include <asm/cpcmd.h> +#include <asm/topology.h> + +/* Sigh, math-emu. Don't ask. */ +#include <asm/sfp-util.h> +#include <math-emu/soft-fp.h> +#include <math-emu/single.h> + +static inline int stsi_0(void) +{ + int rc = stsi(NULL, 0, 0, 0); + return rc == -ENOSYS ? rc : (((unsigned int) rc) >> 28); +} + +static int stsi_1_1_1(struct sysinfo_1_1_1 *info, char *page, int len) +{ + if (stsi(info, 1, 1, 1) == -ENOSYS) + return len; + + EBCASC(info->manufacturer, sizeof(info->manufacturer)); + EBCASC(info->type, sizeof(info->type)); + EBCASC(info->model, sizeof(info->model)); + EBCASC(info->sequence, sizeof(info->sequence)); + EBCASC(info->plant, sizeof(info->plant)); + EBCASC(info->model_capacity, sizeof(info->model_capacity)); + EBCASC(info->model_perm_cap, sizeof(info->model_perm_cap)); + EBCASC(info->model_temp_cap, sizeof(info->model_temp_cap)); + len += sprintf(page + len, "Manufacturer: %-16.16s\n", + info->manufacturer); + len += sprintf(page + len, "Type: %-4.4s\n", + info->type); + if (info->model[0] != '\0') + /* + * Sigh: the model field has been renamed with System z9 + * to model_capacity and a new model field has been added + * after the plant field. To avoid confusing older programs + * the "Model:" prints "model_capacity model" or just + * "model_capacity" if the model string is empty . + */ + len += sprintf(page + len, + "Model: %-16.16s %-16.16s\n", + info->model_capacity, info->model); + else + len += sprintf(page + len, "Model: %-16.16s\n", + info->model_capacity); + len += sprintf(page + len, "Sequence Code: %-16.16s\n", + info->sequence); + len += sprintf(page + len, "Plant: %-4.4s\n", + info->plant); + len += sprintf(page + len, "Model Capacity: %-16.16s %08u\n", + info->model_capacity, *(u32 *) info->model_cap_rating); + if (info->model_perm_cap[0] != '\0') + len += sprintf(page + len, + "Model Perm. Capacity: %-16.16s %08u\n", + info->model_perm_cap, + *(u32 *) info->model_perm_cap_rating); + if (info->model_temp_cap[0] != '\0') + len += sprintf(page + len, + "Model Temp. Capacity: %-16.16s %08u\n", + info->model_temp_cap, + *(u32 *) info->model_temp_cap_rating); + if (info->cai) { + len += sprintf(page + len, + "Capacity Adj. Ind.: %d\n", + info->cai); + len += sprintf(page + len, "Capacity Ch. Reason: %d\n", + info->ccr); + } + return len; +} + +static int stsi_15_1_x(struct sysinfo_15_1_x *info, char *page, int len) +{ + static int max_mnest; + int i, rc; + + len += sprintf(page + len, "\n"); + if (!MACHINE_HAS_TOPOLOGY) + return len; + if (max_mnest) { + stsi(info, 15, 1, max_mnest); + } else { + for (max_mnest = 6; max_mnest > 1; max_mnest--) { + rc = stsi(info, 15, 1, max_mnest); + if (rc != -ENOSYS) + break; + } + } + len += sprintf(page + len, "CPU Topology HW: "); + for (i = 0; i < TOPOLOGY_NR_MAG; i++) + len += sprintf(page + len, " %d", info->mag[i]); + len += sprintf(page + len, "\n"); +#ifdef CONFIG_SCHED_MC + store_topology(info); + len += sprintf(page + len, "CPU Topology SW: "); + for (i = 0; i < TOPOLOGY_NR_MAG; i++) + len += sprintf(page + len, " %d", info->mag[i]); + len += sprintf(page + len, "\n"); +#endif + return len; +} + +static int stsi_1_2_2(struct sysinfo_1_2_2 *info, char *page, int len) +{ + struct sysinfo_1_2_2_extension *ext; + int i; + + if (stsi(info, 1, 2, 2) == -ENOSYS) + return len; + ext = (struct sysinfo_1_2_2_extension *) + ((unsigned long) info + info->acc_offset); + + len += sprintf(page + len, "CPUs Total: %d\n", + info->cpus_total); + len += sprintf(page + len, "CPUs Configured: %d\n", + info->cpus_configured); + len += sprintf(page + len, "CPUs Standby: %d\n", + info->cpus_standby); + len += sprintf(page + len, "CPUs Reserved: %d\n", + info->cpus_reserved); + + if (info->format == 1) { + /* + * Sigh 2. According to the specification the alternate + * capability field is a 32 bit floating point number + * if the higher order 8 bits are not zero. Printing + * a floating point number in the kernel is a no-no, + * always print the number as 32 bit unsigned integer. + * The user-space needs to know about the strange + * encoding of the alternate cpu capability. + */ + len += sprintf(page + len, "Capability: %u %u\n", + info->capability, ext->alt_capability); + for (i = 2; i <= info->cpus_total; i++) + len += sprintf(page + len, + "Adjustment %02d-way: %u %u\n", + i, info->adjustment[i-2], + ext->alt_adjustment[i-2]); + + } else { + len += sprintf(page + len, "Capability: %u\n", + info->capability); + for (i = 2; i <= info->cpus_total; i++) + len += sprintf(page + len, + "Adjustment %02d-way: %u\n", + i, info->adjustment[i-2]); + } + + if (info->secondary_capability != 0) + len += sprintf(page + len, "Secondary Capability: %d\n", + info->secondary_capability); + return len; +} + +static int stsi_2_2_2(struct sysinfo_2_2_2 *info, char *page, int len) +{ + if (stsi(info, 2, 2, 2) == -ENOSYS) + return len; + + EBCASC(info->name, sizeof(info->name)); + + len += sprintf(page + len, "\n"); + len += sprintf(page + len, "LPAR Number: %d\n", + info->lpar_number); + + len += sprintf(page + len, "LPAR Characteristics: "); + if (info->characteristics & LPAR_CHAR_DEDICATED) + len += sprintf(page + len, "Dedicated "); + if (info->characteristics & LPAR_CHAR_SHARED) + len += sprintf(page + len, "Shared "); + if (info->characteristics & LPAR_CHAR_LIMITED) + len += sprintf(page + len, "Limited "); + len += sprintf(page + len, "\n"); + + len += sprintf(page + len, "LPAR Name: %-8.8s\n", + info->name); + + len += sprintf(page + len, "LPAR Adjustment: %d\n", + info->caf); + + len += sprintf(page + len, "LPAR CPUs Total: %d\n", + info->cpus_total); + len += sprintf(page + len, "LPAR CPUs Configured: %d\n", + info->cpus_configured); + len += sprintf(page + len, "LPAR CPUs Standby: %d\n", + info->cpus_standby); + len += sprintf(page + len, "LPAR CPUs Reserved: %d\n", + info->cpus_reserved); + len += sprintf(page + len, "LPAR CPUs Dedicated: %d\n", + info->cpus_dedicated); + len += sprintf(page + len, "LPAR CPUs Shared: %d\n", + info->cpus_shared); + return len; +} + +static int stsi_3_2_2(struct sysinfo_3_2_2 *info, char *page, int len) +{ + int i; + + if (stsi(info, 3, 2, 2) == -ENOSYS) + return len; + for (i = 0; i < info->count; i++) { + EBCASC(info->vm[i].name, sizeof(info->vm[i].name)); + EBCASC(info->vm[i].cpi, sizeof(info->vm[i].cpi)); + len += sprintf(page + len, "\n"); + len += sprintf(page + len, "VM%02d Name: %-8.8s\n", + i, info->vm[i].name); + len += sprintf(page + len, "VM%02d Control Program: %-16.16s\n", + i, info->vm[i].cpi); + + len += sprintf(page + len, "VM%02d Adjustment: %d\n", + i, info->vm[i].caf); + + len += sprintf(page + len, "VM%02d CPUs Total: %d\n", + i, info->vm[i].cpus_total); + len += sprintf(page + len, "VM%02d CPUs Configured: %d\n", + i, info->vm[i].cpus_configured); + len += sprintf(page + len, "VM%02d CPUs Standby: %d\n", + i, info->vm[i].cpus_standby); + len += sprintf(page + len, "VM%02d CPUs Reserved: %d\n", + i, info->vm[i].cpus_reserved); + } + return len; +} + +static int proc_read_sysinfo(char *page, char **start, + off_t off, int count, + int *eof, void *data) +{ + unsigned long info = get_zeroed_page(GFP_KERNEL); + int level, len; + + if (!info) + return 0; + + len = 0; + level = stsi_0(); + if (level >= 1) + len = stsi_1_1_1((struct sysinfo_1_1_1 *) info, page, len); + + if (level >= 1) + len = stsi_15_1_x((struct sysinfo_15_1_x *) info, page, len); + + if (level >= 1) + len = stsi_1_2_2((struct sysinfo_1_2_2 *) info, page, len); + + if (level >= 2) + len = stsi_2_2_2((struct sysinfo_2_2_2 *) info, page, len); + + if (level >= 3) + len = stsi_3_2_2((struct sysinfo_3_2_2 *) info, page, len); + + free_page(info); + return len; +} + +static __init int create_proc_sysinfo(void) +{ + create_proc_read_entry("sysinfo", 0444, NULL, + proc_read_sysinfo, NULL); + return 0; +} +device_initcall(create_proc_sysinfo); + +/* + * Service levels interface. + */ + +static DECLARE_RWSEM(service_level_sem); +static LIST_HEAD(service_level_list); + +int register_service_level(struct service_level *slr) +{ + struct service_level *ptr; + + down_write(&service_level_sem); + list_for_each_entry(ptr, &service_level_list, list) + if (ptr == slr) { + up_write(&service_level_sem); + return -EEXIST; + } + list_add_tail(&slr->list, &service_level_list); + up_write(&service_level_sem); + return 0; +} +EXPORT_SYMBOL(register_service_level); + +int unregister_service_level(struct service_level *slr) +{ + struct service_level *ptr, *next; + int rc = -ENOENT; + + down_write(&service_level_sem); + list_for_each_entry_safe(ptr, next, &service_level_list, list) { + if (ptr != slr) + continue; + list_del(&ptr->list); + rc = 0; + break; + } + up_write(&service_level_sem); + return rc; +} +EXPORT_SYMBOL(unregister_service_level); + +static void *service_level_start(struct seq_file *m, loff_t *pos) +{ + down_read(&service_level_sem); + return seq_list_start(&service_level_list, *pos); +} + +static void *service_level_next(struct seq_file *m, void *p, loff_t *pos) +{ + return seq_list_next(p, &service_level_list, pos); +} + +static void service_level_stop(struct seq_file *m, void *p) +{ + up_read(&service_level_sem); +} + +static int service_level_show(struct seq_file *m, void *p) +{ + struct service_level *slr; + + slr = list_entry(p, struct service_level, list); + slr->seq_print(m, slr); + return 0; +} + +static const struct seq_operations service_level_seq_ops = { + .start = service_level_start, + .next = service_level_next, + .stop = service_level_stop, + .show = service_level_show +}; + +static int service_level_open(struct inode *inode, struct file *file) +{ + return seq_open(file, &service_level_seq_ops); +} + +static const struct file_operations service_level_ops = { + .open = service_level_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release +}; + +static void service_level_vm_print(struct seq_file *m, + struct service_level *slr) +{ + char *query_buffer, *str; + + query_buffer = kmalloc(1024, GFP_KERNEL | GFP_DMA); + if (!query_buffer) + return; + cpcmd("QUERY CPLEVEL", query_buffer, 1024, NULL); + str = strchr(query_buffer, '\n'); + if (str) + *str = 0; + seq_printf(m, "VM: %s\n", query_buffer); + kfree(query_buffer); +} + +static struct service_level service_level_vm = { + .seq_print = service_level_vm_print +}; + +static __init int create_proc_service_level(void) +{ + proc_create("service_levels", 0, NULL, &service_level_ops); + if (MACHINE_IS_VM) + register_service_level(&service_level_vm); + return 0; +} +subsys_initcall(create_proc_service_level); + +/* + * Bogomips calculation based on cpu capability. + */ +int get_cpu_capability(unsigned int *capability) +{ + struct sysinfo_1_2_2 *info; + int rc; + + info = (void *) get_zeroed_page(GFP_KERNEL); + if (!info) + return -ENOMEM; + rc = stsi(info, 1, 2, 2); + if (rc == -ENOSYS) + goto out; + rc = 0; + *capability = info->capability; +out: + free_page((unsigned long) info); + return rc; +} + +/* + * CPU capability might have changed. Therefore recalculate loops_per_jiffy. + */ +void s390_adjust_jiffies(void) +{ + struct sysinfo_1_2_2 *info; + const unsigned int fmil = 0x4b189680; /* 1e7 as 32-bit float. */ + FP_DECL_S(SA); FP_DECL_S(SB); FP_DECL_S(SR); + FP_DECL_EX; + unsigned int capability; + + info = (void *) get_zeroed_page(GFP_KERNEL); + if (!info) + return; + + if (stsi(info, 1, 2, 2) != -ENOSYS) { + /* + * Major sigh. The cpu capability encoding is "special". + * If the first 9 bits of info->capability are 0 then it + * is a 32 bit unsigned integer in the range 0 .. 2^23. + * If the first 9 bits are != 0 then it is a 32 bit float. + * In addition a lower value indicates a proportionally + * higher cpu capacity. Bogomips are the other way round. + * To get to a halfway suitable number we divide 1e7 + * by the cpu capability number. Yes, that means a floating + * point division .. math-emu here we come :-) + */ + FP_UNPACK_SP(SA, &fmil); + if ((info->capability >> 23) == 0) + FP_FROM_INT_S(SB, (long) info->capability, 64, long); + else + FP_UNPACK_SP(SB, &info->capability); + FP_DIV_S(SR, SA, SB); + FP_TO_INT_S(capability, SR, 32, 0); + } else + /* + * Really old machine without stsi block for basic + * cpu information. Report 42.0 bogomips. + */ + capability = 42; + loops_per_jiffy = capability * (500000/HZ); + free_page((unsigned long) info); +} + +/* + * calibrate the delay loop + */ +void __cpuinit calibrate_delay(void) +{ + s390_adjust_jiffies(); + /* Print the good old Bogomips line .. */ + printk(KERN_DEBUG "Calibrating delay loop (skipped)... " + "%lu.%02lu BogoMIPS preset\n", loops_per_jiffy/(500000/HZ), + (loops_per_jiffy/(5000/HZ)) % 100); +} diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c new file mode 100644 index 00000000..d4e1cb1d --- /dev/null +++ b/arch/s390/kernel/time.c @@ -0,0 +1,1789 @@ +/* + * arch/s390/kernel/time.c + * Time of day based timer functions. + * + * S390 version + * Copyright IBM Corp. 1999, 2008 + * Author(s): Hartmut Penner (hp@de.ibm.com), + * Martin Schwidefsky (schwidefsky@de.ibm.com), + * Denis Joseph Barrow (djbarrow@de.ibm.com,barrow_dj@yahoo.com) + * + * Derived from "arch/i386/kernel/time.c" + * Copyright (C) 1991, 1992, 1995 Linus Torvalds + */ + +#define KMSG_COMPONENT "time" +#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt + +#include <linux/kernel_stat.h> +#include <linux/errno.h> +#include <linux/module.h> +#include <linux/sched.h> +#include <linux/kernel.h> +#include <linux/param.h> +#include <linux/string.h> +#include <linux/mm.h> +#include <linux/interrupt.h> +#include <linux/cpu.h> +#include <linux/stop_machine.h> +#include <linux/time.h> +#include <linux/device.h> +#include <linux/delay.h> +#include <linux/init.h> +#include <linux/smp.h> +#include <linux/types.h> +#include <linux/profile.h> +#include <linux/timex.h> +#include <linux/notifier.h> +#include <linux/clocksource.h> +#include <linux/clockchips.h> +#include <linux/gfp.h> +#include <linux/kprobes.h> +#include <asm/uaccess.h> +#include <asm/delay.h> +#include <asm/div64.h> +#include <asm/vdso.h> +#include <asm/irq.h> +#include <asm/irq_regs.h> +#include <asm/timer.h> +#include <asm/etr.h> +#include <asm/cio.h> +#include "entry.h" + +/* change this if you have some constant time drift */ +#define USECS_PER_JIFFY ((unsigned long) 1000000/HZ) +#define CLK_TICKS_PER_JIFFY ((unsigned long) USECS_PER_JIFFY << 12) + +u64 sched_clock_base_cc = -1; /* Force to data section. */ +EXPORT_SYMBOL_GPL(sched_clock_base_cc); + +static DEFINE_PER_CPU(struct clock_event_device, comparators); + +/* + * Scheduler clock - returns current time in nanosec units. + */ +unsigned long long notrace __kprobes sched_clock(void) +{ + return (get_clock_monotonic() * 125) >> 9; +} + +/* + * Monotonic_clock - returns # of nanoseconds passed since time_init() + */ +unsigned long long monotonic_clock(void) +{ + return sched_clock(); +} +EXPORT_SYMBOL(monotonic_clock); + +void tod_to_timeval(__u64 todval, struct timespec *xt) +{ + unsigned long long sec; + + sec = todval >> 12; + do_div(sec, 1000000); + xt->tv_sec = sec; + todval -= (sec * 1000000) << 12; + xt->tv_nsec = ((todval * 1000) >> 12); +} +EXPORT_SYMBOL(tod_to_timeval); + +void clock_comparator_work(void) +{ + struct clock_event_device *cd; + + S390_lowcore.clock_comparator = -1ULL; + set_clock_comparator(S390_lowcore.clock_comparator); + cd = &__get_cpu_var(comparators); + cd->event_handler(cd); +} + +/* + * Fixup the clock comparator. + */ +static void fixup_clock_comparator(unsigned long long delta) +{ + /* If nobody is waiting there's nothing to fix. */ + if (S390_lowcore.clock_comparator == -1ULL) + return; + S390_lowcore.clock_comparator += delta; + set_clock_comparator(S390_lowcore.clock_comparator); +} + +static int s390_next_ktime(ktime_t expires, + struct clock_event_device *evt) +{ + struct timespec ts; + u64 nsecs; + + ts.tv_sec = ts.tv_nsec = 0; + monotonic_to_bootbased(&ts); + nsecs = ktime_to_ns(ktime_add(timespec_to_ktime(ts), expires)); + do_div(nsecs, 125); + S390_lowcore.clock_comparator = sched_clock_base_cc + (nsecs << 9); + set_clock_comparator(S390_lowcore.clock_comparator); + return 0; +} + +static void s390_set_mode(enum clock_event_mode mode, + struct clock_event_device *evt) +{ +} + +/* + * Set up lowcore and control register of the current cpu to + * enable TOD clock and clock comparator interrupts. + */ +void init_cpu_timer(void) +{ + struct clock_event_device *cd; + int cpu; + + S390_lowcore.clock_comparator = -1ULL; + set_clock_comparator(S390_lowcore.clock_comparator); + + cpu = smp_processor_id(); + cd = &per_cpu(comparators, cpu); + cd->name = "comparator"; + cd->features = CLOCK_EVT_FEAT_ONESHOT | + CLOCK_EVT_FEAT_KTIME; + cd->mult = 16777; + cd->shift = 12; + cd->min_delta_ns = 1; + cd->max_delta_ns = LONG_MAX; + cd->rating = 400; + cd->cpumask = cpumask_of(cpu); + cd->set_next_ktime = s390_next_ktime; + cd->set_mode = s390_set_mode; + + clockevents_register_device(cd); + + /* Enable clock comparator timer interrupt. */ + __ctl_set_bit(0,11); + + /* Always allow the timing alert external interrupt. */ + __ctl_set_bit(0, 4); +} + +static void clock_comparator_interrupt(struct ext_code ext_code, + unsigned int param32, + unsigned long param64) +{ + kstat_cpu(smp_processor_id()).irqs[EXTINT_CLK]++; + if (S390_lowcore.clock_comparator == -1ULL) + set_clock_comparator(S390_lowcore.clock_comparator); +} + +static void etr_timing_alert(struct etr_irq_parm *); +static void stp_timing_alert(struct stp_irq_parm *); + +static void timing_alert_interrupt(struct ext_code ext_code, + unsigned int param32, unsigned long param64) +{ + kstat_cpu(smp_processor_id()).irqs[EXTINT_TLA]++; + if (param32 & 0x00c40000) + etr_timing_alert((struct etr_irq_parm *) ¶m32); + if (param32 & 0x00038000) + stp_timing_alert((struct stp_irq_parm *) ¶m32); +} + +static void etr_reset(void); +static void stp_reset(void); + +void read_persistent_clock(struct timespec *ts) +{ + tod_to_timeval(get_clock() - TOD_UNIX_EPOCH, ts); +} + +void read_boot_clock(struct timespec *ts) +{ + tod_to_timeval(sched_clock_base_cc - TOD_UNIX_EPOCH, ts); +} + +static cycle_t read_tod_clock(struct clocksource *cs) +{ + return get_clock(); +} + +static struct clocksource clocksource_tod = { + .name = "tod", + .rating = 400, + .read = read_tod_clock, + .mask = -1ULL, + .mult = 1000, + .shift = 12, + .flags = CLOCK_SOURCE_IS_CONTINUOUS, +}; + +struct clocksource * __init clocksource_default_clock(void) +{ + return &clocksource_tod; +} + +void update_vsyscall(struct timespec *wall_time, struct timespec *wtm, + struct clocksource *clock, u32 mult) +{ + if (clock != &clocksource_tod) + return; + + /* Make userspace gettimeofday spin until we're done. */ + ++vdso_data->tb_update_count; + smp_wmb(); + vdso_data->xtime_tod_stamp = clock->cycle_last; + vdso_data->xtime_clock_sec = wall_time->tv_sec; + vdso_data->xtime_clock_nsec = wall_time->tv_nsec; + vdso_data->wtom_clock_sec = wtm->tv_sec; + vdso_data->wtom_clock_nsec = wtm->tv_nsec; + vdso_data->ntp_mult = mult; + smp_wmb(); + ++vdso_data->tb_update_count; +} + +extern struct timezone sys_tz; + +void update_vsyscall_tz(void) +{ + /* Make userspace gettimeofday spin until we're done. */ + ++vdso_data->tb_update_count; + smp_wmb(); + vdso_data->tz_minuteswest = sys_tz.tz_minuteswest; + vdso_data->tz_dsttime = sys_tz.tz_dsttime; + smp_wmb(); + ++vdso_data->tb_update_count; +} + +/* + * Initialize the TOD clock and the CPU timer of + * the boot cpu. + */ +void __init time_init(void) +{ + /* Reset time synchronization interfaces. */ + etr_reset(); + stp_reset(); + + /* request the clock comparator external interrupt */ + if (register_external_interrupt(0x1004, clock_comparator_interrupt)) + panic("Couldn't request external interrupt 0x1004"); + + /* request the timing alert external interrupt */ + if (register_external_interrupt(0x1406, timing_alert_interrupt)) + panic("Couldn't request external interrupt 0x1406"); + + if (clocksource_register(&clocksource_tod) != 0) + panic("Could not register TOD clock source"); + + /* Enable TOD clock interrupts on the boot cpu. */ + init_cpu_timer(); + + /* Enable cpu timer interrupts on the boot cpu. */ + vtime_init(); +} + +/* + * The time is "clock". old is what we think the time is. + * Adjust the value by a multiple of jiffies and add the delta to ntp. + * "delay" is an approximation how long the synchronization took. If + * the time correction is positive, then "delay" is subtracted from + * the time difference and only the remaining part is passed to ntp. + */ +static unsigned long long adjust_time(unsigned long long old, + unsigned long long clock, + unsigned long long delay) +{ + unsigned long long delta, ticks; + struct timex adjust; + + if (clock > old) { + /* It is later than we thought. */ + delta = ticks = clock - old; + delta = ticks = (delta < delay) ? 0 : delta - delay; + delta -= do_div(ticks, CLK_TICKS_PER_JIFFY); + adjust.offset = ticks * (1000000 / HZ); + } else { + /* It is earlier than we thought. */ + delta = ticks = old - clock; + delta -= do_div(ticks, CLK_TICKS_PER_JIFFY); + delta = -delta; + adjust.offset = -ticks * (1000000 / HZ); + } + sched_clock_base_cc += delta; + if (adjust.offset != 0) { + pr_notice("The ETR interface has adjusted the clock " + "by %li microseconds\n", adjust.offset); + adjust.modes = ADJ_OFFSET_SINGLESHOT; + do_adjtimex(&adjust); + } + return delta; +} + +static DEFINE_PER_CPU(atomic_t, clock_sync_word); +static DEFINE_MUTEX(clock_sync_mutex); +static unsigned long clock_sync_flags; + +#define CLOCK_SYNC_HAS_ETR 0 +#define CLOCK_SYNC_HAS_STP 1 +#define CLOCK_SYNC_ETR 2 +#define CLOCK_SYNC_STP 3 + +/* + * The synchronous get_clock function. It will write the current clock + * value to the clock pointer and return 0 if the clock is in sync with + * the external time source. If the clock mode is local it will return + * -ENOSYS and -EAGAIN if the clock is not in sync with the external + * reference. + */ +int get_sync_clock(unsigned long long *clock) +{ + atomic_t *sw_ptr; + unsigned int sw0, sw1; + + sw_ptr = &get_cpu_var(clock_sync_word); + sw0 = atomic_read(sw_ptr); + *clock = get_clock(); + sw1 = atomic_read(sw_ptr); + put_cpu_var(clock_sync_word); + if (sw0 == sw1 && (sw0 & 0x80000000U)) + /* Success: time is in sync. */ + return 0; + if (!test_bit(CLOCK_SYNC_HAS_ETR, &clock_sync_flags) && + !test_bit(CLOCK_SYNC_HAS_STP, &clock_sync_flags)) + return -ENOSYS; + if (!test_bit(CLOCK_SYNC_ETR, &clock_sync_flags) && + !test_bit(CLOCK_SYNC_STP, &clock_sync_flags)) + return -EACCES; + return -EAGAIN; +} +EXPORT_SYMBOL(get_sync_clock); + +/* + * Make get_sync_clock return -EAGAIN. + */ +static void disable_sync_clock(void *dummy) +{ + atomic_t *sw_ptr = &__get_cpu_var(clock_sync_word); + /* + * Clear the in-sync bit 2^31. All get_sync_clock calls will + * fail until the sync bit is turned back on. In addition + * increase the "sequence" counter to avoid the race of an + * etr event and the complete recovery against get_sync_clock. + */ + atomic_clear_mask(0x80000000, sw_ptr); + atomic_inc(sw_ptr); +} + +/* + * Make get_sync_clock return 0 again. + * Needs to be called from a context disabled for preemption. + */ +static void enable_sync_clock(void) +{ + atomic_t *sw_ptr = &__get_cpu_var(clock_sync_word); + atomic_set_mask(0x80000000, sw_ptr); +} + +/* + * Function to check if the clock is in sync. + */ +static inline int check_sync_clock(void) +{ + atomic_t *sw_ptr; + int rc; + + sw_ptr = &get_cpu_var(clock_sync_word); + rc = (atomic_read(sw_ptr) & 0x80000000U) != 0; + put_cpu_var(clock_sync_word); + return rc; +} + +/* Single threaded workqueue used for etr and stp sync events */ +static struct workqueue_struct *time_sync_wq; + +static void __init time_init_wq(void) +{ + if (time_sync_wq) + return; + time_sync_wq = create_singlethread_workqueue("timesync"); +} + +/* + * External Time Reference (ETR) code. + */ +static int etr_port0_online; +static int etr_port1_online; +static int etr_steai_available; + +static int __init early_parse_etr(char *p) +{ + if (strncmp(p, "off", 3) == 0) + etr_port0_online = etr_port1_online = 0; + else if (strncmp(p, "port0", 5) == 0) + etr_port0_online = 1; + else if (strncmp(p, "port1", 5) == 0) + etr_port1_online = 1; + else if (strncmp(p, "on", 2) == 0) + etr_port0_online = etr_port1_online = 1; + return 0; +} +early_param("etr", early_parse_etr); + +enum etr_event { + ETR_EVENT_PORT0_CHANGE, + ETR_EVENT_PORT1_CHANGE, + ETR_EVENT_PORT_ALERT, + ETR_EVENT_SYNC_CHECK, + ETR_EVENT_SWITCH_LOCAL, + ETR_EVENT_UPDATE, +}; + +/* + * Valid bit combinations of the eacr register are (x = don't care): + * e0 e1 dp p0 p1 ea es sl + * 0 0 x 0 0 0 0 0 initial, disabled state + * 0 0 x 0 1 1 0 0 port 1 online + * 0 0 x 1 0 1 0 0 port 0 online + * 0 0 x 1 1 1 0 0 both ports online + * 0 1 x 0 1 1 0 0 port 1 online and usable, ETR or PPS mode + * 0 1 x 0 1 1 0 1 port 1 online, usable and ETR mode + * 0 1 x 0 1 1 1 0 port 1 online, usable, PPS mode, in-sync + * 0 1 x 0 1 1 1 1 port 1 online, usable, ETR mode, in-sync + * 0 1 x 1 1 1 0 0 both ports online, port 1 usable + * 0 1 x 1 1 1 1 0 both ports online, port 1 usable, PPS mode, in-sync + * 0 1 x 1 1 1 1 1 both ports online, port 1 usable, ETR mode, in-sync + * 1 0 x 1 0 1 0 0 port 0 online and usable, ETR or PPS mode + * 1 0 x 1 0 1 0 1 port 0 online, usable and ETR mode + * 1 0 x 1 0 1 1 0 port 0 online, usable, PPS mode, in-sync + * 1 0 x 1 0 1 1 1 port 0 online, usable, ETR mode, in-sync + * 1 0 x 1 1 1 0 0 both ports online, port 0 usable + * 1 0 x 1 1 1 1 0 both ports online, port 0 usable, PPS mode, in-sync + * 1 0 x 1 1 1 1 1 both ports online, port 0 usable, ETR mode, in-sync + * 1 1 x 1 1 1 1 0 both ports online & usable, ETR, in-sync + * 1 1 x 1 1 1 1 1 both ports online & usable, ETR, in-sync + */ +static struct etr_eacr etr_eacr; +static u64 etr_tolec; /* time of last eacr update */ +static struct etr_aib etr_port0; +static int etr_port0_uptodate; +static struct etr_aib etr_port1; +static int etr_port1_uptodate; +static unsigned long etr_events; +static struct timer_list etr_timer; + +static void etr_timeout(unsigned long dummy); +static void etr_work_fn(struct work_struct *work); +static DEFINE_MUTEX(etr_work_mutex); +static DECLARE_WORK(etr_work, etr_work_fn); + +/* + * Reset ETR attachment. + */ +static void etr_reset(void) +{ + etr_eacr = (struct etr_eacr) { + .e0 = 0, .e1 = 0, ._pad0 = 4, .dp = 0, + .p0 = 0, .p1 = 0, ._pad1 = 0, .ea = 0, + .es = 0, .sl = 0 }; + if (etr_setr(&etr_eacr) == 0) { + etr_tolec = get_clock(); + set_bit(CLOCK_SYNC_HAS_ETR, &clock_sync_flags); + if (etr_port0_online && etr_port1_online) + set_bit(CLOCK_SYNC_ETR, &clock_sync_flags); + } else if (etr_port0_online || etr_port1_online) { + pr_warning("The real or virtual hardware system does " + "not provide an ETR interface\n"); + etr_port0_online = etr_port1_online = 0; + } +} + +static int __init etr_init(void) +{ + struct etr_aib aib; + + if (!test_bit(CLOCK_SYNC_HAS_ETR, &clock_sync_flags)) + return 0; + time_init_wq(); + /* Check if this machine has the steai instruction. */ + if (etr_steai(&aib, ETR_STEAI_STEPPING_PORT) == 0) + etr_steai_available = 1; + setup_timer(&etr_timer, etr_timeout, 0UL); + if (etr_port0_online) { + set_bit(ETR_EVENT_PORT0_CHANGE, &etr_events); + queue_work(time_sync_wq, &etr_work); + } + if (etr_port1_online) { + set_bit(ETR_EVENT_PORT1_CHANGE, &etr_events); + queue_work(time_sync_wq, &etr_work); + } + return 0; +} + +arch_initcall(etr_init); + +/* + * Two sorts of ETR machine checks. The architecture reads: + * "When a machine-check niterruption occurs and if a switch-to-local or + * ETR-sync-check interrupt request is pending but disabled, this pending + * disabled interruption request is indicated and is cleared". + * Which means that we can get etr_switch_to_local events from the machine + * check handler although the interruption condition is disabled. Lovely.. + */ + +/* + * Switch to local machine check. This is called when the last usable + * ETR port goes inactive. After switch to local the clock is not in sync. + */ +void etr_switch_to_local(void) +{ + if (!etr_eacr.sl) + return; + disable_sync_clock(NULL); + if (!test_and_set_bit(ETR_EVENT_SWITCH_LOCAL, &etr_events)) { + etr_eacr.es = etr_eacr.sl = 0; + etr_setr(&etr_eacr); + queue_work(time_sync_wq, &etr_work); + } +} + +/* + * ETR sync check machine check. This is called when the ETR OTE and the + * local clock OTE are farther apart than the ETR sync check tolerance. + * After a ETR sync check the clock is not in sync. The machine check + * is broadcasted to all cpus at the same time. + */ +void etr_sync_check(void) +{ + if (!etr_eacr.es) + return; + disable_sync_clock(NULL); + if (!test_and_set_bit(ETR_EVENT_SYNC_CHECK, &etr_events)) { + etr_eacr.es = 0; + etr_setr(&etr_eacr); + queue_work(time_sync_wq, &etr_work); + } +} + +/* + * ETR timing alert. There are two causes: + * 1) port state change, check the usability of the port + * 2) port alert, one of the ETR-data-validity bits (v1-v2 bits of the + * sldr-status word) or ETR-data word 1 (edf1) or ETR-data word 3 (edf3) + * or ETR-data word 4 (edf4) has changed. + */ +static void etr_timing_alert(struct etr_irq_parm *intparm) +{ + if (intparm->pc0) + /* ETR port 0 state change. */ + set_bit(ETR_EVENT_PORT0_CHANGE, &etr_events); + if (intparm->pc1) + /* ETR port 1 state change. */ + set_bit(ETR_EVENT_PORT1_CHANGE, &etr_events); + if (intparm->eai) + /* + * ETR port alert on either port 0, 1 or both. + * Both ports are not up-to-date now. + */ + set_bit(ETR_EVENT_PORT_ALERT, &etr_events); + queue_work(time_sync_wq, &etr_work); +} + +static void etr_timeout(unsigned long dummy) +{ + set_bit(ETR_EVENT_UPDATE, &etr_events); + queue_work(time_sync_wq, &etr_work); +} + +/* + * Check if the etr mode is pss. + */ +static inline int etr_mode_is_pps(struct etr_eacr eacr) +{ + return eacr.es && !eacr.sl; +} + +/* + * Check if the etr mode is etr. + */ +static inline int etr_mode_is_etr(struct etr_eacr eacr) +{ + return eacr.es && eacr.sl; +} + +/* + * Check if the port can be used for TOD synchronization. + * For PPS mode the port has to receive OTEs. For ETR mode + * the port has to receive OTEs, the ETR stepping bit has to + * be zero and the validity bits for data frame 1, 2, and 3 + * have to be 1. + */ +static int etr_port_valid(struct etr_aib *aib, int port) +{ + unsigned int psc; + + /* Check that this port is receiving OTEs. */ + if (aib->tsp == 0) + return 0; + + psc = port ? aib->esw.psc1 : aib->esw.psc0; + if (psc == etr_lpsc_pps_mode) + return 1; + if (psc == etr_lpsc_operational_step) + return !aib->esw.y && aib->slsw.v1 && + aib->slsw.v2 && aib->slsw.v3; + return 0; +} + +/* + * Check if two ports are on the same network. + */ +static int etr_compare_network(struct etr_aib *aib1, struct etr_aib *aib2) +{ + // FIXME: any other fields we have to compare? + return aib1->edf1.net_id == aib2->edf1.net_id; +} + +/* + * Wrapper for etr_stei that converts physical port states + * to logical port states to be consistent with the output + * of stetr (see etr_psc vs. etr_lpsc). + */ +static void etr_steai_cv(struct etr_aib *aib, unsigned int func) +{ + BUG_ON(etr_steai(aib, func) != 0); + /* Convert port state to logical port state. */ + if (aib->esw.psc0 == 1) + aib->esw.psc0 = 2; + else if (aib->esw.psc0 == 0 && aib->esw.p == 0) + aib->esw.psc0 = 1; + if (aib->esw.psc1 == 1) + aib->esw.psc1 = 2; + else if (aib->esw.psc1 == 0 && aib->esw.p == 1) + aib->esw.psc1 = 1; +} + +/* + * Check if the aib a2 is still connected to the same attachment as + * aib a1, the etv values differ by one and a2 is valid. + */ +static int etr_aib_follows(struct etr_aib *a1, struct etr_aib *a2, int p) +{ + int state_a1, state_a2; + + /* Paranoia check: e0/e1 should better be the same. */ + if (a1->esw.eacr.e0 != a2->esw.eacr.e0 || + a1->esw.eacr.e1 != a2->esw.eacr.e1) + return 0; + + /* Still connected to the same etr ? */ + state_a1 = p ? a1->esw.psc1 : a1->esw.psc0; + state_a2 = p ? a2->esw.psc1 : a2->esw.psc0; + if (state_a1 == etr_lpsc_operational_step) { + if (state_a2 != etr_lpsc_operational_step || + a1->edf1.net_id != a2->edf1.net_id || + a1->edf1.etr_id != a2->edf1.etr_id || + a1->edf1.etr_pn != a2->edf1.etr_pn) + return 0; + } else if (state_a2 != etr_lpsc_pps_mode) + return 0; + + /* The ETV value of a2 needs to be ETV of a1 + 1. */ + if (a1->edf2.etv + 1 != a2->edf2.etv) + return 0; + + if (!etr_port_valid(a2, p)) + return 0; + + return 1; +} + +struct clock_sync_data { + atomic_t cpus; + int in_sync; + unsigned long long fixup_cc; + int etr_port; + struct etr_aib *etr_aib; +}; + +static void clock_sync_cpu(struct clock_sync_data *sync) +{ + atomic_dec(&sync->cpus); + enable_sync_clock(); + /* + * This looks like a busy wait loop but it isn't. etr_sync_cpus + * is called on all other cpus while the TOD clocks is stopped. + * __udelay will stop the cpu on an enabled wait psw until the + * TOD is running again. + */ + while (sync->in_sync == 0) { + __udelay(1); + /* + * A different cpu changes *in_sync. Therefore use + * barrier() to force memory access. + */ + barrier(); + } + if (sync->in_sync != 1) + /* Didn't work. Clear per-cpu in sync bit again. */ + disable_sync_clock(NULL); + /* + * This round of TOD syncing is done. Set the clock comparator + * to the next tick and let the processor continue. + */ + fixup_clock_comparator(sync->fixup_cc); +} + +/* + * Sync the TOD clock using the port referred to by aibp. This port + * has to be enabled and the other port has to be disabled. The + * last eacr update has to be more than 1.6 seconds in the past. + */ +static int etr_sync_clock(void *data) +{ + static int first; + unsigned long long clock, old_clock, delay, delta; + struct clock_sync_data *etr_sync; + struct etr_aib *sync_port, *aib; + int port; + int rc; + + etr_sync = data; + + if (xchg(&first, 1) == 1) { + /* Slave */ + clock_sync_cpu(etr_sync); + return 0; + } + + /* Wait until all other cpus entered the sync function. */ + while (atomic_read(&etr_sync->cpus) != 0) + cpu_relax(); + + port = etr_sync->etr_port; + aib = etr_sync->etr_aib; + sync_port = (port == 0) ? &etr_port0 : &etr_port1; + enable_sync_clock(); + + /* Set clock to next OTE. */ + __ctl_set_bit(14, 21); + __ctl_set_bit(0, 29); + clock = ((unsigned long long) (aib->edf2.etv + 1)) << 32; + old_clock = get_clock(); + if (set_clock(clock) == 0) { + __udelay(1); /* Wait for the clock to start. */ + __ctl_clear_bit(0, 29); + __ctl_clear_bit(14, 21); + etr_stetr(aib); + /* Adjust Linux timing variables. */ + delay = (unsigned long long) + (aib->edf2.etv - sync_port->edf2.etv) << 32; + delta = adjust_time(old_clock, clock, delay); + etr_sync->fixup_cc = delta; + fixup_clock_comparator(delta); + /* Verify that the clock is properly set. */ + if (!etr_aib_follows(sync_port, aib, port)) { + /* Didn't work. */ + disable_sync_clock(NULL); + etr_sync->in_sync = -EAGAIN; + rc = -EAGAIN; + } else { + etr_sync->in_sync = 1; + rc = 0; + } + } else { + /* Could not set the clock ?!? */ + __ctl_clear_bit(0, 29); + __ctl_clear_bit(14, 21); + disable_sync_clock(NULL); + etr_sync->in_sync = -EAGAIN; + rc = -EAGAIN; + } + xchg(&first, 0); + return rc; +} + +static int etr_sync_clock_stop(struct etr_aib *aib, int port) +{ + struct clock_sync_data etr_sync; + struct etr_aib *sync_port; + int follows; + int rc; + + /* Check if the current aib is adjacent to the sync port aib. */ + sync_port = (port == 0) ? &etr_port0 : &etr_port1; + follows = etr_aib_follows(sync_port, aib, port); + memcpy(sync_port, aib, sizeof(*aib)); + if (!follows) + return -EAGAIN; + memset(&etr_sync, 0, sizeof(etr_sync)); + etr_sync.etr_aib = aib; + etr_sync.etr_port = port; + get_online_cpus(); + atomic_set(&etr_sync.cpus, num_online_cpus() - 1); + rc = stop_machine(etr_sync_clock, &etr_sync, cpu_online_mask); + put_online_cpus(); + return rc; +} + +/* + * Handle the immediate effects of the different events. + * The port change event is used for online/offline changes. + */ +static struct etr_eacr etr_handle_events(struct etr_eacr eacr) +{ + if (test_and_clear_bit(ETR_EVENT_SYNC_CHECK, &etr_events)) + eacr.es = 0; + if (test_and_clear_bit(ETR_EVENT_SWITCH_LOCAL, &etr_events)) + eacr.es = eacr.sl = 0; + if (test_and_clear_bit(ETR_EVENT_PORT_ALERT, &etr_events)) + etr_port0_uptodate = etr_port1_uptodate = 0; + + if (test_and_clear_bit(ETR_EVENT_PORT0_CHANGE, &etr_events)) { + if (eacr.e0) + /* + * Port change of an enabled port. We have to + * assume that this can have caused an stepping + * port switch. + */ + etr_tolec = get_clock(); + eacr.p0 = etr_port0_online; + if (!eacr.p0) + eacr.e0 = 0; + etr_port0_uptodate = 0; + } + if (test_and_clear_bit(ETR_EVENT_PORT1_CHANGE, &etr_events)) { + if (eacr.e1) + /* + * Port change of an enabled port. We have to + * assume that this can have caused an stepping + * port switch. + */ + etr_tolec = get_clock(); + eacr.p1 = etr_port1_online; + if (!eacr.p1) + eacr.e1 = 0; + etr_port1_uptodate = 0; + } + clear_bit(ETR_EVENT_UPDATE, &etr_events); + return eacr; +} + +/* + * Set up a timer that expires after the etr_tolec + 1.6 seconds if + * one of the ports needs an update. + */ +static void etr_set_tolec_timeout(unsigned long long now) +{ + unsigned long micros; + + if ((!etr_eacr.p0 || etr_port0_uptodate) && + (!etr_eacr.p1 || etr_port1_uptodate)) + return; + micros = (now > etr_tolec) ? ((now - etr_tolec) >> 12) : 0; + micros = (micros > 1600000) ? 0 : 1600000 - micros; + mod_timer(&etr_timer, jiffies + (micros * HZ) / 1000000 + 1); +} + +/* + * Set up a time that expires after 1/2 second. + */ +static void etr_set_sync_timeout(void) +{ + mod_timer(&etr_timer, jiffies + HZ/2); +} + +/* + * Update the aib information for one or both ports. + */ +static struct etr_eacr etr_handle_update(struct etr_aib *aib, + struct etr_eacr eacr) +{ + /* With both ports disabled the aib information is useless. */ + if (!eacr.e0 && !eacr.e1) + return eacr; + + /* Update port0 or port1 with aib stored in etr_work_fn. */ + if (aib->esw.q == 0) { + /* Information for port 0 stored. */ + if (eacr.p0 && !etr_port0_uptodate) { + etr_port0 = *aib; + if (etr_port0_online) + etr_port0_uptodate = 1; + } + } else { + /* Information for port 1 stored. */ + if (eacr.p1 && !etr_port1_uptodate) { + etr_port1 = *aib; + if (etr_port0_online) + etr_port1_uptodate = 1; + } + } + + /* + * Do not try to get the alternate port aib if the clock + * is not in sync yet. + */ + if (!eacr.es || !check_sync_clock()) + return eacr; + + /* + * If steai is available we can get the information about + * the other port immediately. If only stetr is available the + * data-port bit toggle has to be used. + */ + if (etr_steai_available) { + if (eacr.p0 && !etr_port0_uptodate) { + etr_steai_cv(&etr_port0, ETR_STEAI_PORT_0); + etr_port0_uptodate = 1; + } + if (eacr.p1 && !etr_port1_uptodate) { + etr_steai_cv(&etr_port1, ETR_STEAI_PORT_1); + etr_port1_uptodate = 1; + } + } else { + /* + * One port was updated above, if the other + * port is not uptodate toggle dp bit. + */ + if ((eacr.p0 && !etr_port0_uptodate) || + (eacr.p1 && !etr_port1_uptodate)) + eacr.dp ^= 1; + else + eacr.dp = 0; + } + return eacr; +} + +/* + * Write new etr control register if it differs from the current one. + * Return 1 if etr_tolec has been updated as well. + */ +static void etr_update_eacr(struct etr_eacr eacr) +{ + int dp_changed; + + if (memcmp(&etr_eacr, &eacr, sizeof(eacr)) == 0) + /* No change, return. */ + return; + /* + * The disable of an active port of the change of the data port + * bit can/will cause a change in the data port. + */ + dp_changed = etr_eacr.e0 > eacr.e0 || etr_eacr.e1 > eacr.e1 || + (etr_eacr.dp ^ eacr.dp) != 0; + etr_eacr = eacr; + etr_setr(&etr_eacr); + if (dp_changed) + etr_tolec = get_clock(); +} + +/* + * ETR work. In this function you'll find the main logic. In + * particular this is the only function that calls etr_update_eacr(), + * it "controls" the etr control register. + */ +static void etr_work_fn(struct work_struct *work) +{ + unsigned long long now; + struct etr_eacr eacr; + struct etr_aib aib; + int sync_port; + + /* prevent multiple execution. */ + mutex_lock(&etr_work_mutex); + + /* Create working copy of etr_eacr. */ + eacr = etr_eacr; + + /* Check for the different events and their immediate effects. */ + eacr = etr_handle_events(eacr); + + /* Check if ETR is supposed to be active. */ + eacr.ea = eacr.p0 || eacr.p1; + if (!eacr.ea) { + /* Both ports offline. Reset everything. */ + eacr.dp = eacr.es = eacr.sl = 0; + on_each_cpu(disable_sync_clock, NULL, 1); + del_timer_sync(&etr_timer); + etr_update_eacr(eacr); + goto out_unlock; + } + + /* Store aib to get the current ETR status word. */ + BUG_ON(etr_stetr(&aib) != 0); + etr_port0.esw = etr_port1.esw = aib.esw; /* Copy status word. */ + now = get_clock(); + + /* + * Update the port information if the last stepping port change + * or data port change is older than 1.6 seconds. + */ + if (now >= etr_tolec + (1600000 << 12)) + eacr = etr_handle_update(&aib, eacr); + + /* + * Select ports to enable. The preferred synchronization mode is PPS. + * If a port can be enabled depends on a number of things: + * 1) The port needs to be online and uptodate. A port is not + * disabled just because it is not uptodate, but it is only + * enabled if it is uptodate. + * 2) The port needs to have the same mode (pps / etr). + * 3) The port needs to be usable -> etr_port_valid() == 1 + * 4) To enable the second port the clock needs to be in sync. + * 5) If both ports are useable and are ETR ports, the network id + * has to be the same. + * The eacr.sl bit is used to indicate etr mode vs. pps mode. + */ + if (eacr.p0 && aib.esw.psc0 == etr_lpsc_pps_mode) { + eacr.sl = 0; + eacr.e0 = 1; + if (!etr_mode_is_pps(etr_eacr)) + eacr.es = 0; + if (!eacr.es || !eacr.p1 || aib.esw.psc1 != etr_lpsc_pps_mode) + eacr.e1 = 0; + // FIXME: uptodate checks ? + else if (etr_port0_uptodate && etr_port1_uptodate) + eacr.e1 = 1; + sync_port = (etr_port0_uptodate && + etr_port_valid(&etr_port0, 0)) ? 0 : -1; + } else if (eacr.p1 && aib.esw.psc1 == etr_lpsc_pps_mode) { + eacr.sl = 0; + eacr.e0 = 0; + eacr.e1 = 1; + if (!etr_mode_is_pps(etr_eacr)) + eacr.es = 0; + sync_port = (etr_port1_uptodate && + etr_port_valid(&etr_port1, 1)) ? 1 : -1; + } else if (eacr.p0 && aib.esw.psc0 == etr_lpsc_operational_step) { + eacr.sl = 1; + eacr.e0 = 1; + if (!etr_mode_is_etr(etr_eacr)) + eacr.es = 0; + if (!eacr.es || !eacr.p1 || + aib.esw.psc1 != etr_lpsc_operational_alt) + eacr.e1 = 0; + else if (etr_port0_uptodate && etr_port1_uptodate && + etr_compare_network(&etr_port0, &etr_port1)) + eacr.e1 = 1; + sync_port = (etr_port0_uptodate && + etr_port_valid(&etr_port0, 0)) ? 0 : -1; + } else if (eacr.p1 && aib.esw.psc1 == etr_lpsc_operational_step) { + eacr.sl = 1; + eacr.e0 = 0; + eacr.e1 = 1; + if (!etr_mode_is_etr(etr_eacr)) + eacr.es = 0; + sync_port = (etr_port1_uptodate && + etr_port_valid(&etr_port1, 1)) ? 1 : -1; + } else { + /* Both ports not usable. */ + eacr.es = eacr.sl = 0; + sync_port = -1; + } + + /* + * If the clock is in sync just update the eacr and return. + * If there is no valid sync port wait for a port update. + */ + if ((eacr.es && check_sync_clock()) || sync_port < 0) { + etr_update_eacr(eacr); + etr_set_tolec_timeout(now); + goto out_unlock; + } + + /* + * Prepare control register for clock syncing + * (reset data port bit, set sync check control. + */ + eacr.dp = 0; + eacr.es = 1; + + /* + * Update eacr and try to synchronize the clock. If the update + * of eacr caused a stepping port switch (or if we have to + * assume that a stepping port switch has occurred) or the + * clock syncing failed, reset the sync check control bit + * and set up a timer to try again after 0.5 seconds + */ + etr_update_eacr(eacr); + if (now < etr_tolec + (1600000 << 12) || + etr_sync_clock_stop(&aib, sync_port) != 0) { + /* Sync failed. Try again in 1/2 second. */ + eacr.es = 0; + etr_update_eacr(eacr); + etr_set_sync_timeout(); + } else + etr_set_tolec_timeout(now); +out_unlock: + mutex_unlock(&etr_work_mutex); +} + +/* + * Sysfs interface functions + */ +static struct bus_type etr_subsys = { + .name = "etr", + .dev_name = "etr", +}; + +static struct device etr_port0_dev = { + .id = 0, + .bus = &etr_subsys, +}; + +static struct device etr_port1_dev = { + .id = 1, + .bus = &etr_subsys, +}; + +/* + * ETR subsys attributes + */ +static ssize_t etr_stepping_port_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + return sprintf(buf, "%i\n", etr_port0.esw.p); +} + +static DEVICE_ATTR(stepping_port, 0400, etr_stepping_port_show, NULL); + +static ssize_t etr_stepping_mode_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + char *mode_str; + + if (etr_mode_is_pps(etr_eacr)) + mode_str = "pps"; + else if (etr_mode_is_etr(etr_eacr)) + mode_str = "etr"; + else + mode_str = "local"; + return sprintf(buf, "%s\n", mode_str); +} + +static DEVICE_ATTR(stepping_mode, 0400, etr_stepping_mode_show, NULL); + +/* + * ETR port attributes + */ +static inline struct etr_aib *etr_aib_from_dev(struct device *dev) +{ + if (dev == &etr_port0_dev) + return etr_port0_online ? &etr_port0 : NULL; + else + return etr_port1_online ? &etr_port1 : NULL; +} + +static ssize_t etr_online_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + unsigned int online; + + online = (dev == &etr_port0_dev) ? etr_port0_online : etr_port1_online; + return sprintf(buf, "%i\n", online); +} + +static ssize_t etr_online_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + unsigned int value; + + value = simple_strtoul(buf, NULL, 0); + if (value != 0 && value != 1) + return -EINVAL; + if (!test_bit(CLOCK_SYNC_HAS_ETR, &clock_sync_flags)) + return -EOPNOTSUPP; + mutex_lock(&clock_sync_mutex); + if (dev == &etr_port0_dev) { + if (etr_port0_online == value) + goto out; /* Nothing to do. */ + etr_port0_online = value; + if (etr_port0_online && etr_port1_online) + set_bit(CLOCK_SYNC_ETR, &clock_sync_flags); + else + clear_bit(CLOCK_SYNC_ETR, &clock_sync_flags); + set_bit(ETR_EVENT_PORT0_CHANGE, &etr_events); + queue_work(time_sync_wq, &etr_work); + } else { + if (etr_port1_online == value) + goto out; /* Nothing to do. */ + etr_port1_online = value; + if (etr_port0_online && etr_port1_online) + set_bit(CLOCK_SYNC_ETR, &clock_sync_flags); + else + clear_bit(CLOCK_SYNC_ETR, &clock_sync_flags); + set_bit(ETR_EVENT_PORT1_CHANGE, &etr_events); + queue_work(time_sync_wq, &etr_work); + } +out: + mutex_unlock(&clock_sync_mutex); + return count; +} + +static DEVICE_ATTR(online, 0600, etr_online_show, etr_online_store); + +static ssize_t etr_stepping_control_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + return sprintf(buf, "%i\n", (dev == &etr_port0_dev) ? + etr_eacr.e0 : etr_eacr.e1); +} + +static DEVICE_ATTR(stepping_control, 0400, etr_stepping_control_show, NULL); + +static ssize_t etr_mode_code_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + if (!etr_port0_online && !etr_port1_online) + /* Status word is not uptodate if both ports are offline. */ + return -ENODATA; + return sprintf(buf, "%i\n", (dev == &etr_port0_dev) ? + etr_port0.esw.psc0 : etr_port0.esw.psc1); +} + +static DEVICE_ATTR(state_code, 0400, etr_mode_code_show, NULL); + +static ssize_t etr_untuned_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct etr_aib *aib = etr_aib_from_dev(dev); + + if (!aib || !aib->slsw.v1) + return -ENODATA; + return sprintf(buf, "%i\n", aib->edf1.u); +} + +static DEVICE_ATTR(untuned, 0400, etr_untuned_show, NULL); + +static ssize_t etr_network_id_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct etr_aib *aib = etr_aib_from_dev(dev); + + if (!aib || !aib->slsw.v1) + return -ENODATA; + return sprintf(buf, "%i\n", aib->edf1.net_id); +} + +static DEVICE_ATTR(network, 0400, etr_network_id_show, NULL); + +static ssize_t etr_id_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct etr_aib *aib = etr_aib_from_dev(dev); + + if (!aib || !aib->slsw.v1) + return -ENODATA; + return sprintf(buf, "%i\n", aib->edf1.etr_id); +} + +static DEVICE_ATTR(id, 0400, etr_id_show, NULL); + +static ssize_t etr_port_number_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct etr_aib *aib = etr_aib_from_dev(dev); + + if (!aib || !aib->slsw.v1) + return -ENODATA; + return sprintf(buf, "%i\n", aib->edf1.etr_pn); +} + +static DEVICE_ATTR(port, 0400, etr_port_number_show, NULL); + +static ssize_t etr_coupled_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct etr_aib *aib = etr_aib_from_dev(dev); + + if (!aib || !aib->slsw.v3) + return -ENODATA; + return sprintf(buf, "%i\n", aib->edf3.c); +} + +static DEVICE_ATTR(coupled, 0400, etr_coupled_show, NULL); + +static ssize_t etr_local_time_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct etr_aib *aib = etr_aib_from_dev(dev); + + if (!aib || !aib->slsw.v3) + return -ENODATA; + return sprintf(buf, "%i\n", aib->edf3.blto); +} + +static DEVICE_ATTR(local_time, 0400, etr_local_time_show, NULL); + +static ssize_t etr_utc_offset_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct etr_aib *aib = etr_aib_from_dev(dev); + + if (!aib || !aib->slsw.v3) + return -ENODATA; + return sprintf(buf, "%i\n", aib->edf3.buo); +} + +static DEVICE_ATTR(utc_offset, 0400, etr_utc_offset_show, NULL); + +static struct device_attribute *etr_port_attributes[] = { + &dev_attr_online, + &dev_attr_stepping_control, + &dev_attr_state_code, + &dev_attr_untuned, + &dev_attr_network, + &dev_attr_id, + &dev_attr_port, + &dev_attr_coupled, + &dev_attr_local_time, + &dev_attr_utc_offset, + NULL +}; + +static int __init etr_register_port(struct device *dev) +{ + struct device_attribute **attr; + int rc; + + rc = device_register(dev); + if (rc) + goto out; + for (attr = etr_port_attributes; *attr; attr++) { + rc = device_create_file(dev, *attr); + if (rc) + goto out_unreg; + } + return 0; +out_unreg: + for (; attr >= etr_port_attributes; attr--) + device_remove_file(dev, *attr); + device_unregister(dev); +out: + return rc; +} + +static void __init etr_unregister_port(struct device *dev) +{ + struct device_attribute **attr; + + for (attr = etr_port_attributes; *attr; attr++) + device_remove_file(dev, *attr); + device_unregister(dev); +} + +static int __init etr_init_sysfs(void) +{ + int rc; + + rc = subsys_system_register(&etr_subsys, NULL); + if (rc) + goto out; + rc = device_create_file(etr_subsys.dev_root, &dev_attr_stepping_port); + if (rc) + goto out_unreg_subsys; + rc = device_create_file(etr_subsys.dev_root, &dev_attr_stepping_mode); + if (rc) + goto out_remove_stepping_port; + rc = etr_register_port(&etr_port0_dev); + if (rc) + goto out_remove_stepping_mode; + rc = etr_register_port(&etr_port1_dev); + if (rc) + goto out_remove_port0; + return 0; + +out_remove_port0: + etr_unregister_port(&etr_port0_dev); +out_remove_stepping_mode: + device_remove_file(etr_subsys.dev_root, &dev_attr_stepping_mode); +out_remove_stepping_port: + device_remove_file(etr_subsys.dev_root, &dev_attr_stepping_port); +out_unreg_subsys: + bus_unregister(&etr_subsys); +out: + return rc; +} + +device_initcall(etr_init_sysfs); + +/* + * Server Time Protocol (STP) code. + */ +static int stp_online; +static struct stp_sstpi stp_info; +static void *stp_page; + +static void stp_work_fn(struct work_struct *work); +static DEFINE_MUTEX(stp_work_mutex); +static DECLARE_WORK(stp_work, stp_work_fn); +static struct timer_list stp_timer; + +static int __init early_parse_stp(char *p) +{ + if (strncmp(p, "off", 3) == 0) + stp_online = 0; + else if (strncmp(p, "on", 2) == 0) + stp_online = 1; + return 0; +} +early_param("stp", early_parse_stp); + +/* + * Reset STP attachment. + */ +static void __init stp_reset(void) +{ + int rc; + + stp_page = (void *) get_zeroed_page(GFP_ATOMIC); + rc = chsc_sstpc(stp_page, STP_OP_CTRL, 0x0000); + if (rc == 0) + set_bit(CLOCK_SYNC_HAS_STP, &clock_sync_flags); + else if (stp_online) { + pr_warning("The real or virtual hardware system does " + "not provide an STP interface\n"); + free_page((unsigned long) stp_page); + stp_page = NULL; + stp_online = 0; + } +} + +static void stp_timeout(unsigned long dummy) +{ + queue_work(time_sync_wq, &stp_work); +} + +static int __init stp_init(void) +{ + if (!test_bit(CLOCK_SYNC_HAS_STP, &clock_sync_flags)) + return 0; + setup_timer(&stp_timer, stp_timeout, 0UL); + time_init_wq(); + if (!stp_online) + return 0; + queue_work(time_sync_wq, &stp_work); + return 0; +} + +arch_initcall(stp_init); + +/* + * STP timing alert. There are three causes: + * 1) timing status change + * 2) link availability change + * 3) time control parameter change + * In all three cases we are only interested in the clock source state. + * If a STP clock source is now available use it. + */ +static void stp_timing_alert(struct stp_irq_parm *intparm) +{ + if (intparm->tsc || intparm->lac || intparm->tcpc) + queue_work(time_sync_wq, &stp_work); +} + +/* + * STP sync check machine check. This is called when the timing state + * changes from the synchronized state to the unsynchronized state. + * After a STP sync check the clock is not in sync. The machine check + * is broadcasted to all cpus at the same time. + */ +void stp_sync_check(void) +{ + disable_sync_clock(NULL); + queue_work(time_sync_wq, &stp_work); +} + +/* + * STP island condition machine check. This is called when an attached + * server attempts to communicate over an STP link and the servers + * have matching CTN ids and have a valid stratum-1 configuration + * but the configurations do not match. + */ +void stp_island_check(void) +{ + disable_sync_clock(NULL); + queue_work(time_sync_wq, &stp_work); +} + + +static int stp_sync_clock(void *data) +{ + static int first; + unsigned long long old_clock, delta; + struct clock_sync_data *stp_sync; + int rc; + + stp_sync = data; + + if (xchg(&first, 1) == 1) { + /* Slave */ + clock_sync_cpu(stp_sync); + return 0; + } + + /* Wait until all other cpus entered the sync function. */ + while (atomic_read(&stp_sync->cpus) != 0) + cpu_relax(); + + enable_sync_clock(); + + rc = 0; + if (stp_info.todoff[0] || stp_info.todoff[1] || + stp_info.todoff[2] || stp_info.todoff[3] || + stp_info.tmd != 2) { + old_clock = get_clock(); + rc = chsc_sstpc(stp_page, STP_OP_SYNC, 0); + if (rc == 0) { + delta = adjust_time(old_clock, get_clock(), 0); + fixup_clock_comparator(delta); + rc = chsc_sstpi(stp_page, &stp_info, + sizeof(struct stp_sstpi)); + if (rc == 0 && stp_info.tmd != 2) + rc = -EAGAIN; + } + } + if (rc) { + disable_sync_clock(NULL); + stp_sync->in_sync = -EAGAIN; + } else + stp_sync->in_sync = 1; + xchg(&first, 0); + return 0; +} + +/* + * STP work. Check for the STP state and take over the clock + * synchronization if the STP clock source is usable. + */ +static void stp_work_fn(struct work_struct *work) +{ + struct clock_sync_data stp_sync; + int rc; + + /* prevent multiple execution. */ + mutex_lock(&stp_work_mutex); + + if (!stp_online) { + chsc_sstpc(stp_page, STP_OP_CTRL, 0x0000); + del_timer_sync(&stp_timer); + goto out_unlock; + } + + rc = chsc_sstpc(stp_page, STP_OP_CTRL, 0xb0e0); + if (rc) + goto out_unlock; + + rc = chsc_sstpi(stp_page, &stp_info, sizeof(struct stp_sstpi)); + if (rc || stp_info.c == 0) + goto out_unlock; + + /* Skip synchronization if the clock is already in sync. */ + if (check_sync_clock()) + goto out_unlock; + + memset(&stp_sync, 0, sizeof(stp_sync)); + get_online_cpus(); + atomic_set(&stp_sync.cpus, num_online_cpus() - 1); + stop_machine(stp_sync_clock, &stp_sync, cpu_online_mask); + put_online_cpus(); + + if (!check_sync_clock()) + /* + * There is a usable clock but the synchonization failed. + * Retry after a second. + */ + mod_timer(&stp_timer, jiffies + HZ); + +out_unlock: + mutex_unlock(&stp_work_mutex); +} + +/* + * STP subsys sysfs interface functions + */ +static struct bus_type stp_subsys = { + .name = "stp", + .dev_name = "stp", +}; + +static ssize_t stp_ctn_id_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + if (!stp_online) + return -ENODATA; + return sprintf(buf, "%016llx\n", + *(unsigned long long *) stp_info.ctnid); +} + +static DEVICE_ATTR(ctn_id, 0400, stp_ctn_id_show, NULL); + +static ssize_t stp_ctn_type_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + if (!stp_online) + return -ENODATA; + return sprintf(buf, "%i\n", stp_info.ctn); +} + +static DEVICE_ATTR(ctn_type, 0400, stp_ctn_type_show, NULL); + +static ssize_t stp_dst_offset_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + if (!stp_online || !(stp_info.vbits & 0x2000)) + return -ENODATA; + return sprintf(buf, "%i\n", (int)(s16) stp_info.dsto); +} + +static DEVICE_ATTR(dst_offset, 0400, stp_dst_offset_show, NULL); + +static ssize_t stp_leap_seconds_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + if (!stp_online || !(stp_info.vbits & 0x8000)) + return -ENODATA; + return sprintf(buf, "%i\n", (int)(s16) stp_info.leaps); +} + +static DEVICE_ATTR(leap_seconds, 0400, stp_leap_seconds_show, NULL); + +static ssize_t stp_stratum_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + if (!stp_online) + return -ENODATA; + return sprintf(buf, "%i\n", (int)(s16) stp_info.stratum); +} + +static DEVICE_ATTR(stratum, 0400, stp_stratum_show, NULL); + +static ssize_t stp_time_offset_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + if (!stp_online || !(stp_info.vbits & 0x0800)) + return -ENODATA; + return sprintf(buf, "%i\n", (int) stp_info.tto); +} + +static DEVICE_ATTR(time_offset, 0400, stp_time_offset_show, NULL); + +static ssize_t stp_time_zone_offset_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + if (!stp_online || !(stp_info.vbits & 0x4000)) + return -ENODATA; + return sprintf(buf, "%i\n", (int)(s16) stp_info.tzo); +} + +static DEVICE_ATTR(time_zone_offset, 0400, + stp_time_zone_offset_show, NULL); + +static ssize_t stp_timing_mode_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + if (!stp_online) + return -ENODATA; + return sprintf(buf, "%i\n", stp_info.tmd); +} + +static DEVICE_ATTR(timing_mode, 0400, stp_timing_mode_show, NULL); + +static ssize_t stp_timing_state_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + if (!stp_online) + return -ENODATA; + return sprintf(buf, "%i\n", stp_info.tst); +} + +static DEVICE_ATTR(timing_state, 0400, stp_timing_state_show, NULL); + +static ssize_t stp_online_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + return sprintf(buf, "%i\n", stp_online); +} + +static ssize_t stp_online_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + unsigned int value; + + value = simple_strtoul(buf, NULL, 0); + if (value != 0 && value != 1) + return -EINVAL; + if (!test_bit(CLOCK_SYNC_HAS_STP, &clock_sync_flags)) + return -EOPNOTSUPP; + mutex_lock(&clock_sync_mutex); + stp_online = value; + if (stp_online) + set_bit(CLOCK_SYNC_STP, &clock_sync_flags); + else + clear_bit(CLOCK_SYNC_STP, &clock_sync_flags); + queue_work(time_sync_wq, &stp_work); + mutex_unlock(&clock_sync_mutex); + return count; +} + +/* + * Can't use DEVICE_ATTR because the attribute should be named + * stp/online but dev_attr_online already exists in this file .. + */ +static struct device_attribute dev_attr_stp_online = { + .attr = { .name = "online", .mode = 0600 }, + .show = stp_online_show, + .store = stp_online_store, +}; + +static struct device_attribute *stp_attributes[] = { + &dev_attr_ctn_id, + &dev_attr_ctn_type, + &dev_attr_dst_offset, + &dev_attr_leap_seconds, + &dev_attr_stp_online, + &dev_attr_stratum, + &dev_attr_time_offset, + &dev_attr_time_zone_offset, + &dev_attr_timing_mode, + &dev_attr_timing_state, + NULL +}; + +static int __init stp_init_sysfs(void) +{ + struct device_attribute **attr; + int rc; + + rc = subsys_system_register(&stp_subsys, NULL); + if (rc) + goto out; + for (attr = stp_attributes; *attr; attr++) { + rc = device_create_file(stp_subsys.dev_root, *attr); + if (rc) + goto out_unreg; + } + return 0; +out_unreg: + for (; attr >= stp_attributes; attr--) + device_remove_file(stp_subsys.dev_root, *attr); + bus_unregister(&stp_subsys); +out: + return rc; +} + +device_initcall(stp_init_sysfs); diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c new file mode 100644 index 00000000..4f8dc942 --- /dev/null +++ b/arch/s390/kernel/topology.c @@ -0,0 +1,465 @@ +/* + * Copyright IBM Corp. 2007,2011 + * Author(s): Heiko Carstens <heiko.carstens@de.ibm.com> + */ + +#define KMSG_COMPONENT "cpu" +#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt + +#include <linux/workqueue.h> +#include <linux/bootmem.h> +#include <linux/cpuset.h> +#include <linux/device.h> +#include <linux/kernel.h> +#include <linux/sched.h> +#include <linux/init.h> +#include <linux/delay.h> +#include <linux/cpu.h> +#include <linux/smp.h> +#include <linux/mm.h> + +#define PTF_HORIZONTAL (0UL) +#define PTF_VERTICAL (1UL) +#define PTF_CHECK (2UL) + +struct mask_info { + struct mask_info *next; + unsigned char id; + cpumask_t mask; +}; + +static int topology_enabled = 1; +static void topology_work_fn(struct work_struct *work); +static struct sysinfo_15_1_x *tl_info; +static void set_topology_timer(void); +static DECLARE_WORK(topology_work, topology_work_fn); +/* topology_lock protects the core linked list */ +static DEFINE_SPINLOCK(topology_lock); + +static struct mask_info core_info; +cpumask_t cpu_core_map[NR_CPUS]; +unsigned char cpu_core_id[NR_CPUS]; + +static struct mask_info book_info; +cpumask_t cpu_book_map[NR_CPUS]; +unsigned char cpu_book_id[NR_CPUS]; + +/* smp_cpu_state_mutex must be held when accessing this array */ +int cpu_polarization[NR_CPUS]; + +static cpumask_t cpu_group_map(struct mask_info *info, unsigned int cpu) +{ + cpumask_t mask; + + cpumask_clear(&mask); + if (!topology_enabled || !MACHINE_HAS_TOPOLOGY) { + cpumask_copy(&mask, cpumask_of(cpu)); + return mask; + } + while (info) { + if (cpumask_test_cpu(cpu, &info->mask)) { + mask = info->mask; + break; + } + info = info->next; + } + if (cpumask_empty(&mask)) + cpumask_copy(&mask, cpumask_of(cpu)); + return mask; +} + +static struct mask_info *add_cpus_to_mask(struct topology_cpu *tl_cpu, + struct mask_info *book, + struct mask_info *core, + int one_core_per_cpu) +{ + unsigned int cpu; + + for (cpu = find_first_bit(&tl_cpu->mask[0], TOPOLOGY_CPU_BITS); + cpu < TOPOLOGY_CPU_BITS; + cpu = find_next_bit(&tl_cpu->mask[0], TOPOLOGY_CPU_BITS, cpu + 1)) + { + unsigned int rcpu; + int lcpu; + + rcpu = TOPOLOGY_CPU_BITS - 1 - cpu + tl_cpu->origin; + lcpu = smp_find_processor_id(rcpu); + if (lcpu >= 0) { + cpumask_set_cpu(lcpu, &book->mask); + cpu_book_id[lcpu] = book->id; + cpumask_set_cpu(lcpu, &core->mask); + if (one_core_per_cpu) { + cpu_core_id[lcpu] = rcpu; + core = core->next; + } else { + cpu_core_id[lcpu] = core->id; + } + cpu_set_polarization(lcpu, tl_cpu->pp); + } + } + return core; +} + +static void clear_masks(void) +{ + struct mask_info *info; + + info = &core_info; + while (info) { + cpumask_clear(&info->mask); + info = info->next; + } + info = &book_info; + while (info) { + cpumask_clear(&info->mask); + info = info->next; + } +} + +static union topology_entry *next_tle(union topology_entry *tle) +{ + if (!tle->nl) + return (union topology_entry *)((struct topology_cpu *)tle + 1); + return (union topology_entry *)((struct topology_container *)tle + 1); +} + +static void __tl_to_cores_generic(struct sysinfo_15_1_x *info) +{ + struct mask_info *core = &core_info; + struct mask_info *book = &book_info; + union topology_entry *tle, *end; + + tle = info->tle; + end = (union topology_entry *)((unsigned long)info + info->length); + while (tle < end) { + switch (tle->nl) { + case 2: + book = book->next; + book->id = tle->container.id; + break; + case 1: + core = core->next; + core->id = tle->container.id; + break; + case 0: + add_cpus_to_mask(&tle->cpu, book, core, 0); + break; + default: + clear_masks(); + return; + } + tle = next_tle(tle); + } +} + +static void __tl_to_cores_z10(struct sysinfo_15_1_x *info) +{ + struct mask_info *core = &core_info; + struct mask_info *book = &book_info; + union topology_entry *tle, *end; + + tle = info->tle; + end = (union topology_entry *)((unsigned long)info + info->length); + while (tle < end) { + switch (tle->nl) { + case 1: + book = book->next; + book->id = tle->container.id; + break; + case 0: + core = add_cpus_to_mask(&tle->cpu, book, core, 1); + break; + default: + clear_masks(); + return; + } + tle = next_tle(tle); + } +} + +static void tl_to_cores(struct sysinfo_15_1_x *info) +{ + struct cpuid cpu_id; + + get_cpu_id(&cpu_id); + spin_lock_irq(&topology_lock); + clear_masks(); + switch (cpu_id.machine) { + case 0x2097: + case 0x2098: + __tl_to_cores_z10(info); + break; + default: + __tl_to_cores_generic(info); + } + spin_unlock_irq(&topology_lock); +} + +static void topology_update_polarization_simple(void) +{ + int cpu; + + mutex_lock(&smp_cpu_state_mutex); + for_each_possible_cpu(cpu) + cpu_set_polarization(cpu, POLARIZATION_HRZ); + mutex_unlock(&smp_cpu_state_mutex); +} + +static int ptf(unsigned long fc) +{ + int rc; + + asm volatile( + " .insn rre,0xb9a20000,%1,%1\n" + " ipm %0\n" + " srl %0,28\n" + : "=d" (rc) + : "d" (fc) : "cc"); + return rc; +} + +int topology_set_cpu_management(int fc) +{ + int cpu, rc; + + if (!MACHINE_HAS_TOPOLOGY) + return -EOPNOTSUPP; + if (fc) + rc = ptf(PTF_VERTICAL); + else + rc = ptf(PTF_HORIZONTAL); + if (rc) + return -EBUSY; + for_each_possible_cpu(cpu) + cpu_set_polarization(cpu, POLARIZATION_UNKNOWN); + return rc; +} + +static void update_cpu_core_map(void) +{ + unsigned long flags; + int cpu; + + spin_lock_irqsave(&topology_lock, flags); + for_each_possible_cpu(cpu) { + cpu_core_map[cpu] = cpu_group_map(&core_info, cpu); + cpu_book_map[cpu] = cpu_group_map(&book_info, cpu); + } + spin_unlock_irqrestore(&topology_lock, flags); +} + +void store_topology(struct sysinfo_15_1_x *info) +{ + int rc; + + rc = stsi(info, 15, 1, 3); + if (rc != -ENOSYS) + return; + stsi(info, 15, 1, 2); +} + +int arch_update_cpu_topology(void) +{ + struct sysinfo_15_1_x *info = tl_info; + struct device *dev; + int cpu; + + if (!MACHINE_HAS_TOPOLOGY) { + update_cpu_core_map(); + topology_update_polarization_simple(); + return 0; + } + store_topology(info); + tl_to_cores(info); + update_cpu_core_map(); + for_each_online_cpu(cpu) { + dev = get_cpu_device(cpu); + kobject_uevent(&dev->kobj, KOBJ_CHANGE); + } + return 1; +} + +static void topology_work_fn(struct work_struct *work) +{ + rebuild_sched_domains(); +} + +void topology_schedule_update(void) +{ + schedule_work(&topology_work); +} + +static void topology_timer_fn(unsigned long ignored) +{ + if (ptf(PTF_CHECK)) + topology_schedule_update(); + set_topology_timer(); +} + +static struct timer_list topology_timer = + TIMER_DEFERRED_INITIALIZER(topology_timer_fn, 0, 0); + +static atomic_t topology_poll = ATOMIC_INIT(0); + +static void set_topology_timer(void) +{ + if (atomic_add_unless(&topology_poll, -1, 0)) + mod_timer(&topology_timer, jiffies + HZ / 10); + else + mod_timer(&topology_timer, jiffies + HZ * 60); +} + +void topology_expect_change(void) +{ + if (!MACHINE_HAS_TOPOLOGY) + return; + /* This is racy, but it doesn't matter since it is just a heuristic. + * Worst case is that we poll in a higher frequency for a bit longer. + */ + if (atomic_read(&topology_poll) > 60) + return; + atomic_add(60, &topology_poll); + set_topology_timer(); +} + +static int __init early_parse_topology(char *p) +{ + if (strncmp(p, "off", 3)) + return 0; + topology_enabled = 0; + return 0; +} +early_param("topology", early_parse_topology); + +static void __init alloc_masks(struct sysinfo_15_1_x *info, + struct mask_info *mask, int offset) +{ + int i, nr_masks; + + nr_masks = info->mag[TOPOLOGY_NR_MAG - offset]; + for (i = 0; i < info->mnest - offset; i++) + nr_masks *= info->mag[TOPOLOGY_NR_MAG - offset - 1 - i]; + nr_masks = max(nr_masks, 1); + for (i = 0; i < nr_masks; i++) { + mask->next = alloc_bootmem(sizeof(struct mask_info)); + mask = mask->next; + } +} + +void __init s390_init_cpu_topology(void) +{ + struct sysinfo_15_1_x *info; + int i; + + if (!MACHINE_HAS_TOPOLOGY) + return; + tl_info = alloc_bootmem_pages(PAGE_SIZE); + info = tl_info; + store_topology(info); + pr_info("The CPU configuration topology of the machine is:"); + for (i = 0; i < TOPOLOGY_NR_MAG; i++) + printk(KERN_CONT " %d", info->mag[i]); + printk(KERN_CONT " / %d\n", info->mnest); + alloc_masks(info, &core_info, 1); + alloc_masks(info, &book_info, 2); +} + +static int cpu_management; + +static ssize_t dispatching_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + ssize_t count; + + mutex_lock(&smp_cpu_state_mutex); + count = sprintf(buf, "%d\n", cpu_management); + mutex_unlock(&smp_cpu_state_mutex); + return count; +} + +static ssize_t dispatching_store(struct device *dev, + struct device_attribute *attr, + const char *buf, + size_t count) +{ + int val, rc; + char delim; + + if (sscanf(buf, "%d %c", &val, &delim) != 1) + return -EINVAL; + if (val != 0 && val != 1) + return -EINVAL; + rc = 0; + get_online_cpus(); + mutex_lock(&smp_cpu_state_mutex); + if (cpu_management == val) + goto out; + rc = topology_set_cpu_management(val); + if (rc) + goto out; + cpu_management = val; + topology_expect_change(); +out: + mutex_unlock(&smp_cpu_state_mutex); + put_online_cpus(); + return rc ? rc : count; +} +static DEVICE_ATTR(dispatching, 0644, dispatching_show, + dispatching_store); + +static ssize_t cpu_polarization_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + int cpu = dev->id; + ssize_t count; + + mutex_lock(&smp_cpu_state_mutex); + switch (cpu_read_polarization(cpu)) { + case POLARIZATION_HRZ: + count = sprintf(buf, "horizontal\n"); + break; + case POLARIZATION_VL: + count = sprintf(buf, "vertical:low\n"); + break; + case POLARIZATION_VM: + count = sprintf(buf, "vertical:medium\n"); + break; + case POLARIZATION_VH: + count = sprintf(buf, "vertical:high\n"); + break; + default: + count = sprintf(buf, "unknown\n"); + break; + } + mutex_unlock(&smp_cpu_state_mutex); + return count; +} +static DEVICE_ATTR(polarization, 0444, cpu_polarization_show, NULL); + +static struct attribute *topology_cpu_attrs[] = { + &dev_attr_polarization.attr, + NULL, +}; + +static struct attribute_group topology_cpu_attr_group = { + .attrs = topology_cpu_attrs, +}; + +int topology_cpu_init(struct cpu *cpu) +{ + return sysfs_create_group(&cpu->dev.kobj, &topology_cpu_attr_group); +} + +static int __init topology_init(void) +{ + if (!MACHINE_HAS_TOPOLOGY) { + topology_update_polarization_simple(); + goto out; + } + set_topology_timer(); +out: + update_cpu_core_map(); + return device_create_file(cpu_subsys.dev_root, &dev_attr_dispatching); +} +device_initcall(topology_init); diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c new file mode 100644 index 00000000..77cdf423 --- /dev/null +++ b/arch/s390/kernel/traps.c @@ -0,0 +1,656 @@ +/* + * arch/s390/kernel/traps.c + * + * S390 version + * Copyright (C) 1999,2000 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com), + * Denis Joseph Barrow (djbarrow@de.ibm.com,barrow_dj@yahoo.com), + * + * Derived from "arch/i386/kernel/traps.c" + * Copyright (C) 1991, 1992 Linus Torvalds + */ + +/* + * 'Traps.c' handles hardware traps and faults after we have saved some + * state in 'asm.s'. + */ +#include <linux/sched.h> +#include <linux/kernel.h> +#include <linux/string.h> +#include <linux/errno.h> +#include <linux/ptrace.h> +#include <linux/timer.h> +#include <linux/mm.h> +#include <linux/smp.h> +#include <linux/init.h> +#include <linux/interrupt.h> +#include <linux/seq_file.h> +#include <linux/delay.h> +#include <linux/module.h> +#include <linux/kdebug.h> +#include <linux/kallsyms.h> +#include <linux/reboot.h> +#include <linux/kprobes.h> +#include <linux/bug.h> +#include <linux/utsname.h> +#include <asm/uaccess.h> +#include <asm/io.h> +#include <linux/atomic.h> +#include <asm/mathemu.h> +#include <asm/cpcmd.h> +#include <asm/lowcore.h> +#include <asm/debug.h> +#include <asm/ipl.h> +#include "entry.h" + +void (*pgm_check_table[128])(struct pt_regs *regs); + +int show_unhandled_signals = 1; + +#define stack_pointer ({ void **sp; asm("la %0,0(15)" : "=&d" (sp)); sp; }) + +#ifndef CONFIG_64BIT +#define LONG "%08lx " +#define FOURLONG "%08lx %08lx %08lx %08lx\n" +static int kstack_depth_to_print = 12; +#else /* CONFIG_64BIT */ +#define LONG "%016lx " +#define FOURLONG "%016lx %016lx %016lx %016lx\n" +static int kstack_depth_to_print = 20; +#endif /* CONFIG_64BIT */ + +/* + * For show_trace we have tree different stack to consider: + * - the panic stack which is used if the kernel stack has overflown + * - the asynchronous interrupt stack (cpu related) + * - the synchronous kernel stack (process related) + * The stack trace can start at any of the three stack and can potentially + * touch all of them. The order is: panic stack, async stack, sync stack. + */ +static unsigned long +__show_trace(unsigned long sp, unsigned long low, unsigned long high) +{ + struct stack_frame *sf; + struct pt_regs *regs; + + while (1) { + sp = sp & PSW_ADDR_INSN; + if (sp < low || sp > high - sizeof(*sf)) + return sp; + sf = (struct stack_frame *) sp; + printk("([<%016lx>] ", sf->gprs[8] & PSW_ADDR_INSN); + print_symbol("%s)\n", sf->gprs[8] & PSW_ADDR_INSN); + /* Follow the backchain. */ + while (1) { + low = sp; + sp = sf->back_chain & PSW_ADDR_INSN; + if (!sp) + break; + if (sp <= low || sp > high - sizeof(*sf)) + return sp; + sf = (struct stack_frame *) sp; + printk(" [<%016lx>] ", sf->gprs[8] & PSW_ADDR_INSN); + print_symbol("%s\n", sf->gprs[8] & PSW_ADDR_INSN); + } + /* Zero backchain detected, check for interrupt frame. */ + sp = (unsigned long) (sf + 1); + if (sp <= low || sp > high - sizeof(*regs)) + return sp; + regs = (struct pt_regs *) sp; + printk(" [<%016lx>] ", regs->psw.addr & PSW_ADDR_INSN); + print_symbol("%s\n", regs->psw.addr & PSW_ADDR_INSN); + low = sp; + sp = regs->gprs[15]; + } +} + +static void show_trace(struct task_struct *task, unsigned long *stack) +{ + register unsigned long __r15 asm ("15"); + unsigned long sp; + + sp = (unsigned long) stack; + if (!sp) + sp = task ? task->thread.ksp : __r15; + printk("Call Trace:\n"); +#ifdef CONFIG_CHECK_STACK + sp = __show_trace(sp, S390_lowcore.panic_stack - 4096, + S390_lowcore.panic_stack); +#endif + sp = __show_trace(sp, S390_lowcore.async_stack - ASYNC_SIZE, + S390_lowcore.async_stack); + if (task) + __show_trace(sp, (unsigned long) task_stack_page(task), + (unsigned long) task_stack_page(task) + THREAD_SIZE); + else + __show_trace(sp, S390_lowcore.thread_info, + S390_lowcore.thread_info + THREAD_SIZE); + if (!task) + task = current; + debug_show_held_locks(task); +} + +void show_stack(struct task_struct *task, unsigned long *sp) +{ + register unsigned long * __r15 asm ("15"); + unsigned long *stack; + int i; + + if (!sp) + stack = task ? (unsigned long *) task->thread.ksp : __r15; + else + stack = sp; + + for (i = 0; i < kstack_depth_to_print; i++) { + if (((addr_t) stack & (THREAD_SIZE-1)) == 0) + break; + if ((i * sizeof(long) % 32) == 0) + printk("%s ", i == 0 ? "" : "\n"); + printk(LONG, *stack++); + } + printk("\n"); + show_trace(task, sp); +} + +static void show_last_breaking_event(struct pt_regs *regs) +{ +#ifdef CONFIG_64BIT + printk("Last Breaking-Event-Address:\n"); + printk(" [<%016lx>] ", regs->args[0] & PSW_ADDR_INSN); + print_symbol("%s\n", regs->args[0] & PSW_ADDR_INSN); +#endif +} + +/* + * The architecture-independent dump_stack generator + */ +void dump_stack(void) +{ + printk("CPU: %d %s %s %.*s\n", + task_thread_info(current)->cpu, print_tainted(), + init_utsname()->release, + (int)strcspn(init_utsname()->version, " "), + init_utsname()->version); + printk("Process %s (pid: %d, task: %p, ksp: %p)\n", + current->comm, current->pid, current, + (void *) current->thread.ksp); + show_stack(NULL, NULL); +} +EXPORT_SYMBOL(dump_stack); + +static inline int mask_bits(struct pt_regs *regs, unsigned long bits) +{ + return (regs->psw.mask & bits) / ((~bits + 1) & bits); +} + +void show_registers(struct pt_regs *regs) +{ + char *mode; + + mode = (regs->psw.mask & PSW_MASK_PSTATE) ? "User" : "Krnl"; + printk("%s PSW : %p %p", + mode, (void *) regs->psw.mask, + (void *) regs->psw.addr); + print_symbol(" (%s)\n", regs->psw.addr & PSW_ADDR_INSN); + printk(" R:%x T:%x IO:%x EX:%x Key:%x M:%x W:%x " + "P:%x AS:%x CC:%x PM:%x", mask_bits(regs, PSW_MASK_PER), + mask_bits(regs, PSW_MASK_DAT), mask_bits(regs, PSW_MASK_IO), + mask_bits(regs, PSW_MASK_EXT), mask_bits(regs, PSW_MASK_KEY), + mask_bits(regs, PSW_MASK_MCHECK), mask_bits(regs, PSW_MASK_WAIT), + mask_bits(regs, PSW_MASK_PSTATE), mask_bits(regs, PSW_MASK_ASC), + mask_bits(regs, PSW_MASK_CC), mask_bits(regs, PSW_MASK_PM)); +#ifdef CONFIG_64BIT + printk(" EA:%x", mask_bits(regs, PSW_MASK_EA | PSW_MASK_BA)); +#endif + printk("\n%s GPRS: " FOURLONG, mode, + regs->gprs[0], regs->gprs[1], regs->gprs[2], regs->gprs[3]); + printk(" " FOURLONG, + regs->gprs[4], regs->gprs[5], regs->gprs[6], regs->gprs[7]); + printk(" " FOURLONG, + regs->gprs[8], regs->gprs[9], regs->gprs[10], regs->gprs[11]); + printk(" " FOURLONG, + regs->gprs[12], regs->gprs[13], regs->gprs[14], regs->gprs[15]); + + show_code(regs); +} + +void show_regs(struct pt_regs *regs) +{ + print_modules(); + printk("CPU: %d %s %s %.*s\n", + task_thread_info(current)->cpu, print_tainted(), + init_utsname()->release, + (int)strcspn(init_utsname()->version, " "), + init_utsname()->version); + printk("Process %s (pid: %d, task: %p, ksp: %p)\n", + current->comm, current->pid, current, + (void *) current->thread.ksp); + show_registers(regs); + /* Show stack backtrace if pt_regs is from kernel mode */ + if (!(regs->psw.mask & PSW_MASK_PSTATE)) + show_trace(NULL, (unsigned long *) regs->gprs[15]); + show_last_breaking_event(regs); +} + +static DEFINE_SPINLOCK(die_lock); + +void die(struct pt_regs *regs, const char *str) +{ + static int die_counter; + + oops_enter(); + lgr_info_log(); + debug_stop_all(); + console_verbose(); + spin_lock_irq(&die_lock); + bust_spinlocks(1); + printk("%s: %04x [#%d] ", str, regs->int_code & 0xffff, ++die_counter); +#ifdef CONFIG_PREEMPT + printk("PREEMPT "); +#endif +#ifdef CONFIG_SMP + printk("SMP "); +#endif +#ifdef CONFIG_DEBUG_PAGEALLOC + printk("DEBUG_PAGEALLOC"); +#endif + printk("\n"); + notify_die(DIE_OOPS, str, regs, 0, regs->int_code & 0xffff, SIGSEGV); + show_regs(regs); + bust_spinlocks(0); + add_taint(TAINT_DIE); + spin_unlock_irq(&die_lock); + if (in_interrupt()) + panic("Fatal exception in interrupt"); + if (panic_on_oops) + panic("Fatal exception: panic_on_oops"); + oops_exit(); + do_exit(SIGSEGV); +} + +static inline void report_user_fault(struct pt_regs *regs, int signr) +{ + if ((task_pid_nr(current) > 1) && !show_unhandled_signals) + return; + if (!unhandled_signal(current, signr)) + return; + if (!printk_ratelimit()) + return; + printk("User process fault: interruption code 0x%X ", regs->int_code); + print_vma_addr("in ", regs->psw.addr & PSW_ADDR_INSN); + printk("\n"); + show_regs(regs); +} + +int is_valid_bugaddr(unsigned long addr) +{ + return 1; +} + +static inline void __user *get_psw_address(struct pt_regs *regs) +{ + return (void __user *) + ((regs->psw.addr - (regs->int_code >> 16)) & PSW_ADDR_INSN); +} + +static void __kprobes do_trap(struct pt_regs *regs, + int si_signo, int si_code, char *str) +{ + siginfo_t info; + + if (notify_die(DIE_TRAP, str, regs, 0, + regs->int_code, si_signo) == NOTIFY_STOP) + return; + + if (regs->psw.mask & PSW_MASK_PSTATE) { + info.si_signo = si_signo; + info.si_errno = 0; + info.si_code = si_code; + info.si_addr = get_psw_address(regs); + force_sig_info(si_signo, &info, current); + report_user_fault(regs, si_signo); + } else { + const struct exception_table_entry *fixup; + fixup = search_exception_tables(regs->psw.addr & PSW_ADDR_INSN); + if (fixup) + regs->psw.addr = fixup->fixup | PSW_ADDR_AMODE; + else { + enum bug_trap_type btt; + + btt = report_bug(regs->psw.addr & PSW_ADDR_INSN, regs); + if (btt == BUG_TRAP_TYPE_WARN) + return; + die(regs, str); + } + } +} + +void __kprobes do_per_trap(struct pt_regs *regs) +{ + siginfo_t info; + + if (notify_die(DIE_SSTEP, "sstep", regs, 0, 0, SIGTRAP) == NOTIFY_STOP) + return; + if (!current->ptrace) + return; + info.si_signo = SIGTRAP; + info.si_errno = 0; + info.si_code = TRAP_HWBKPT; + info.si_addr = + (void __force __user *) current->thread.per_event.address; + force_sig_info(SIGTRAP, &info, current); +} + +static void default_trap_handler(struct pt_regs *regs) +{ + if (regs->psw.mask & PSW_MASK_PSTATE) { + report_user_fault(regs, SIGSEGV); + do_exit(SIGSEGV); + } else + die(regs, "Unknown program exception"); +} + +#define DO_ERROR_INFO(name, signr, sicode, str) \ +static void name(struct pt_regs *regs) \ +{ \ + do_trap(regs, signr, sicode, str); \ +} + +DO_ERROR_INFO(addressing_exception, SIGILL, ILL_ILLADR, + "addressing exception") +DO_ERROR_INFO(execute_exception, SIGILL, ILL_ILLOPN, + "execute exception") +DO_ERROR_INFO(divide_exception, SIGFPE, FPE_INTDIV, + "fixpoint divide exception") +DO_ERROR_INFO(overflow_exception, SIGFPE, FPE_INTOVF, + "fixpoint overflow exception") +DO_ERROR_INFO(hfp_overflow_exception, SIGFPE, FPE_FLTOVF, + "HFP overflow exception") +DO_ERROR_INFO(hfp_underflow_exception, SIGFPE, FPE_FLTUND, + "HFP underflow exception") +DO_ERROR_INFO(hfp_significance_exception, SIGFPE, FPE_FLTRES, + "HFP significance exception") +DO_ERROR_INFO(hfp_divide_exception, SIGFPE, FPE_FLTDIV, + "HFP divide exception") +DO_ERROR_INFO(hfp_sqrt_exception, SIGFPE, FPE_FLTINV, + "HFP square root exception") +DO_ERROR_INFO(operand_exception, SIGILL, ILL_ILLOPN, + "operand exception") +DO_ERROR_INFO(privileged_op, SIGILL, ILL_PRVOPC, + "privileged operation") +DO_ERROR_INFO(special_op_exception, SIGILL, ILL_ILLOPN, + "special operation exception") +DO_ERROR_INFO(translation_exception, SIGILL, ILL_ILLOPN, + "translation exception") + +static inline void do_fp_trap(struct pt_regs *regs, int fpc) +{ + int si_code = 0; + /* FPC[2] is Data Exception Code */ + if ((fpc & 0x00000300) == 0) { + /* bits 6 and 7 of DXC are 0 iff IEEE exception */ + if (fpc & 0x8000) /* invalid fp operation */ + si_code = FPE_FLTINV; + else if (fpc & 0x4000) /* div by 0 */ + si_code = FPE_FLTDIV; + else if (fpc & 0x2000) /* overflow */ + si_code = FPE_FLTOVF; + else if (fpc & 0x1000) /* underflow */ + si_code = FPE_FLTUND; + else if (fpc & 0x0800) /* inexact */ + si_code = FPE_FLTRES; + } + do_trap(regs, SIGFPE, si_code, "floating point exception"); +} + +static void __kprobes illegal_op(struct pt_regs *regs) +{ + siginfo_t info; + __u8 opcode[6]; + __u16 __user *location; + int signal = 0; + + location = get_psw_address(regs); + + if (regs->psw.mask & PSW_MASK_PSTATE) { + if (get_user(*((__u16 *) opcode), (__u16 __user *) location)) + return; + if (*((__u16 *) opcode) == S390_BREAKPOINT_U16) { + if (current->ptrace) { + info.si_signo = SIGTRAP; + info.si_errno = 0; + info.si_code = TRAP_BRKPT; + info.si_addr = location; + force_sig_info(SIGTRAP, &info, current); + } else + signal = SIGILL; +#ifdef CONFIG_MATHEMU + } else if (opcode[0] == 0xb3) { + if (get_user(*((__u16 *) (opcode+2)), location+1)) + return; + signal = math_emu_b3(opcode, regs); + } else if (opcode[0] == 0xed) { + if (get_user(*((__u32 *) (opcode+2)), + (__u32 __user *)(location+1))) + return; + signal = math_emu_ed(opcode, regs); + } else if (*((__u16 *) opcode) == 0xb299) { + if (get_user(*((__u16 *) (opcode+2)), location+1)) + return; + signal = math_emu_srnm(opcode, regs); + } else if (*((__u16 *) opcode) == 0xb29c) { + if (get_user(*((__u16 *) (opcode+2)), location+1)) + return; + signal = math_emu_stfpc(opcode, regs); + } else if (*((__u16 *) opcode) == 0xb29d) { + if (get_user(*((__u16 *) (opcode+2)), location+1)) + return; + signal = math_emu_lfpc(opcode, regs); +#endif + } else + signal = SIGILL; + } else { + /* + * If we get an illegal op in kernel mode, send it through the + * kprobes notifier. If kprobes doesn't pick it up, SIGILL + */ + if (notify_die(DIE_BPT, "bpt", regs, 0, + 3, SIGTRAP) != NOTIFY_STOP) + signal = SIGILL; + } + +#ifdef CONFIG_MATHEMU + if (signal == SIGFPE) + do_fp_trap(regs, current->thread.fp_regs.fpc); + else if (signal == SIGSEGV) + do_trap(regs, signal, SEGV_MAPERR, "user address fault"); + else +#endif + if (signal) + do_trap(regs, signal, ILL_ILLOPC, "illegal operation"); +} + + +#ifdef CONFIG_MATHEMU +void specification_exception(struct pt_regs *regs) +{ + __u8 opcode[6]; + __u16 __user *location = NULL; + int signal = 0; + + location = (__u16 __user *) get_psw_address(regs); + + if (regs->psw.mask & PSW_MASK_PSTATE) { + get_user(*((__u16 *) opcode), location); + switch (opcode[0]) { + case 0x28: /* LDR Rx,Ry */ + signal = math_emu_ldr(opcode); + break; + case 0x38: /* LER Rx,Ry */ + signal = math_emu_ler(opcode); + break; + case 0x60: /* STD R,D(X,B) */ + get_user(*((__u16 *) (opcode+2)), location+1); + signal = math_emu_std(opcode, regs); + break; + case 0x68: /* LD R,D(X,B) */ + get_user(*((__u16 *) (opcode+2)), location+1); + signal = math_emu_ld(opcode, regs); + break; + case 0x70: /* STE R,D(X,B) */ + get_user(*((__u16 *) (opcode+2)), location+1); + signal = math_emu_ste(opcode, regs); + break; + case 0x78: /* LE R,D(X,B) */ + get_user(*((__u16 *) (opcode+2)), location+1); + signal = math_emu_le(opcode, regs); + break; + default: + signal = SIGILL; + break; + } + } else + signal = SIGILL; + + if (signal == SIGFPE) + do_fp_trap(regs, current->thread.fp_regs.fpc); + else if (signal) + do_trap(regs, signal, ILL_ILLOPN, "specification exception"); +} +#else +DO_ERROR_INFO(specification_exception, SIGILL, ILL_ILLOPN, + "specification exception"); +#endif + +static void data_exception(struct pt_regs *regs) +{ + __u16 __user *location; + int signal = 0; + + location = get_psw_address(regs); + + if (MACHINE_HAS_IEEE) + asm volatile("stfpc %0" : "=m" (current->thread.fp_regs.fpc)); + +#ifdef CONFIG_MATHEMU + else if (regs->psw.mask & PSW_MASK_PSTATE) { + __u8 opcode[6]; + get_user(*((__u16 *) opcode), location); + switch (opcode[0]) { + case 0x28: /* LDR Rx,Ry */ + signal = math_emu_ldr(opcode); + break; + case 0x38: /* LER Rx,Ry */ + signal = math_emu_ler(opcode); + break; + case 0x60: /* STD R,D(X,B) */ + get_user(*((__u16 *) (opcode+2)), location+1); + signal = math_emu_std(opcode, regs); + break; + case 0x68: /* LD R,D(X,B) */ + get_user(*((__u16 *) (opcode+2)), location+1); + signal = math_emu_ld(opcode, regs); + break; + case 0x70: /* STE R,D(X,B) */ + get_user(*((__u16 *) (opcode+2)), location+1); + signal = math_emu_ste(opcode, regs); + break; + case 0x78: /* LE R,D(X,B) */ + get_user(*((__u16 *) (opcode+2)), location+1); + signal = math_emu_le(opcode, regs); + break; + case 0xb3: + get_user(*((__u16 *) (opcode+2)), location+1); + signal = math_emu_b3(opcode, regs); + break; + case 0xed: + get_user(*((__u32 *) (opcode+2)), + (__u32 __user *)(location+1)); + signal = math_emu_ed(opcode, regs); + break; + case 0xb2: + if (opcode[1] == 0x99) { + get_user(*((__u16 *) (opcode+2)), location+1); + signal = math_emu_srnm(opcode, regs); + } else if (opcode[1] == 0x9c) { + get_user(*((__u16 *) (opcode+2)), location+1); + signal = math_emu_stfpc(opcode, regs); + } else if (opcode[1] == 0x9d) { + get_user(*((__u16 *) (opcode+2)), location+1); + signal = math_emu_lfpc(opcode, regs); + } else + signal = SIGILL; + break; + default: + signal = SIGILL; + break; + } + } +#endif + if (current->thread.fp_regs.fpc & FPC_DXC_MASK) + signal = SIGFPE; + else + signal = SIGILL; + if (signal == SIGFPE) + do_fp_trap(regs, current->thread.fp_regs.fpc); + else if (signal) + do_trap(regs, signal, ILL_ILLOPN, "data exception"); +} + +static void space_switch_exception(struct pt_regs *regs) +{ + /* Set user psw back to home space mode. */ + if (regs->psw.mask & PSW_MASK_PSTATE) + regs->psw.mask |= PSW_ASC_HOME; + /* Send SIGILL. */ + do_trap(regs, SIGILL, ILL_PRVOPC, "space switch event"); +} + +void __kprobes kernel_stack_overflow(struct pt_regs * regs) +{ + bust_spinlocks(1); + printk("Kernel stack overflow.\n"); + show_regs(regs); + bust_spinlocks(0); + panic("Corrupt kernel stack, can't continue."); +} + +/* init is done in lowcore.S and head.S */ + +void __init trap_init(void) +{ + int i; + + for (i = 0; i < 128; i++) + pgm_check_table[i] = &default_trap_handler; + pgm_check_table[1] = &illegal_op; + pgm_check_table[2] = &privileged_op; + pgm_check_table[3] = &execute_exception; + pgm_check_table[4] = &do_protection_exception; + pgm_check_table[5] = &addressing_exception; + pgm_check_table[6] = &specification_exception; + pgm_check_table[7] = &data_exception; + pgm_check_table[8] = &overflow_exception; + pgm_check_table[9] = ÷_exception; + pgm_check_table[0x0A] = &overflow_exception; + pgm_check_table[0x0B] = ÷_exception; + pgm_check_table[0x0C] = &hfp_overflow_exception; + pgm_check_table[0x0D] = &hfp_underflow_exception; + pgm_check_table[0x0E] = &hfp_significance_exception; + pgm_check_table[0x0F] = &hfp_divide_exception; + pgm_check_table[0x10] = &do_dat_exception; + pgm_check_table[0x11] = &do_dat_exception; + pgm_check_table[0x12] = &translation_exception; + pgm_check_table[0x13] = &special_op_exception; +#ifdef CONFIG_64BIT + pgm_check_table[0x38] = &do_asce_exception; + pgm_check_table[0x39] = &do_dat_exception; + pgm_check_table[0x3A] = &do_dat_exception; + pgm_check_table[0x3B] = &do_dat_exception; +#endif /* CONFIG_64BIT */ + pgm_check_table[0x15] = &operand_exception; + pgm_check_table[0x1C] = &space_switch_exception; + pgm_check_table[0x1D] = &hfp_sqrt_exception; + /* Enable machine checks early. */ + local_mcck_enable(); +} diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c new file mode 100644 index 00000000..ea5590fd --- /dev/null +++ b/arch/s390/kernel/vdso.c @@ -0,0 +1,333 @@ +/* + * vdso setup for s390 + * + * Copyright IBM Corp. 2008 + * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com) + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License (version 2 only) + * as published by the Free Software Foundation. + */ + +#include <linux/module.h> +#include <linux/errno.h> +#include <linux/sched.h> +#include <linux/kernel.h> +#include <linux/mm.h> +#include <linux/smp.h> +#include <linux/stddef.h> +#include <linux/unistd.h> +#include <linux/slab.h> +#include <linux/user.h> +#include <linux/elf.h> +#include <linux/security.h> +#include <linux/bootmem.h> +#include <linux/compat.h> +#include <asm/asm-offsets.h> +#include <asm/pgtable.h> +#include <asm/processor.h> +#include <asm/mmu.h> +#include <asm/mmu_context.h> +#include <asm/sections.h> +#include <asm/vdso.h> +#include <asm/facility.h> + +#if defined(CONFIG_32BIT) || defined(CONFIG_COMPAT) +extern char vdso32_start, vdso32_end; +static void *vdso32_kbase = &vdso32_start; +static unsigned int vdso32_pages; +static struct page **vdso32_pagelist; +#endif + +#ifdef CONFIG_64BIT +extern char vdso64_start, vdso64_end; +static void *vdso64_kbase = &vdso64_start; +static unsigned int vdso64_pages; +static struct page **vdso64_pagelist; +#endif /* CONFIG_64BIT */ + +/* + * Should the kernel map a VDSO page into processes and pass its + * address down to glibc upon exec()? + */ +unsigned int __read_mostly vdso_enabled = 1; + +static int __init vdso_setup(char *s) +{ + unsigned long val; + int rc; + + rc = 0; + if (strncmp(s, "on", 3) == 0) + vdso_enabled = 1; + else if (strncmp(s, "off", 4) == 0) + vdso_enabled = 0; + else { + rc = strict_strtoul(s, 0, &val); + vdso_enabled = rc ? 0 : !!val; + } + return !rc; +} +__setup("vdso=", vdso_setup); + +/* + * The vdso data page + */ +static union { + struct vdso_data data; + u8 page[PAGE_SIZE]; +} vdso_data_store __page_aligned_data; +struct vdso_data *vdso_data = &vdso_data_store.data; + +/* + * Setup vdso data page. + */ +static void vdso_init_data(struct vdso_data *vd) +{ + vd->ectg_available = user_mode != HOME_SPACE_MODE && test_facility(31); +} + +#ifdef CONFIG_64BIT +/* + * Allocate/free per cpu vdso data. + */ +#define SEGMENT_ORDER 2 + +int vdso_alloc_per_cpu(struct _lowcore *lowcore) +{ + unsigned long segment_table, page_table, page_frame; + u32 *psal, *aste; + int i; + + lowcore->vdso_per_cpu_data = __LC_PASTE; + + if (user_mode == HOME_SPACE_MODE || !vdso_enabled) + return 0; + + segment_table = __get_free_pages(GFP_KERNEL, SEGMENT_ORDER); + page_table = get_zeroed_page(GFP_KERNEL | GFP_DMA); + page_frame = get_zeroed_page(GFP_KERNEL); + if (!segment_table || !page_table || !page_frame) + goto out; + + clear_table((unsigned long *) segment_table, _SEGMENT_ENTRY_EMPTY, + PAGE_SIZE << SEGMENT_ORDER); + clear_table((unsigned long *) page_table, _PAGE_TYPE_EMPTY, + 256*sizeof(unsigned long)); + + *(unsigned long *) segment_table = _SEGMENT_ENTRY + page_table; + *(unsigned long *) page_table = _PAGE_RO + page_frame; + + psal = (u32 *) (page_table + 256*sizeof(unsigned long)); + aste = psal + 32; + + for (i = 4; i < 32; i += 4) + psal[i] = 0x80000000; + + lowcore->paste[4] = (u32)(addr_t) psal; + psal[0] = 0x20000000; + psal[2] = (u32)(addr_t) aste; + *(unsigned long *) (aste + 2) = segment_table + + _ASCE_TABLE_LENGTH + _ASCE_USER_BITS + _ASCE_TYPE_SEGMENT; + aste[4] = (u32)(addr_t) psal; + lowcore->vdso_per_cpu_data = page_frame; + + return 0; + +out: + free_page(page_frame); + free_page(page_table); + free_pages(segment_table, SEGMENT_ORDER); + return -ENOMEM; +} + +void vdso_free_per_cpu(struct _lowcore *lowcore) +{ + unsigned long segment_table, page_table, page_frame; + u32 *psal, *aste; + + if (user_mode == HOME_SPACE_MODE || !vdso_enabled) + return; + + psal = (u32 *)(addr_t) lowcore->paste[4]; + aste = (u32 *)(addr_t) psal[2]; + segment_table = *(unsigned long *)(aste + 2) & PAGE_MASK; + page_table = *(unsigned long *) segment_table; + page_frame = *(unsigned long *) page_table; + + free_page(page_frame); + free_page(page_table); + free_pages(segment_table, SEGMENT_ORDER); +} + +static void vdso_init_cr5(void) +{ + unsigned long cr5; + + if (user_mode == HOME_SPACE_MODE || !vdso_enabled) + return; + cr5 = offsetof(struct _lowcore, paste); + __ctl_load(cr5, 5, 5); +} +#endif /* CONFIG_64BIT */ + +/* + * This is called from binfmt_elf, we create the special vma for the + * vDSO and insert it into the mm struct tree + */ +int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) +{ + struct mm_struct *mm = current->mm; + struct page **vdso_pagelist; + unsigned long vdso_pages; + unsigned long vdso_base; + int rc; + + if (!vdso_enabled) + return 0; + /* + * Only map the vdso for dynamically linked elf binaries. + */ + if (!uses_interp) + return 0; + +#ifdef CONFIG_64BIT + vdso_pagelist = vdso64_pagelist; + vdso_pages = vdso64_pages; +#ifdef CONFIG_COMPAT + if (is_compat_task()) { + vdso_pagelist = vdso32_pagelist; + vdso_pages = vdso32_pages; + } +#endif +#else + vdso_pagelist = vdso32_pagelist; + vdso_pages = vdso32_pages; +#endif + + /* + * vDSO has a problem and was disabled, just don't "enable" it for + * the process + */ + if (vdso_pages == 0) + return 0; + + current->mm->context.vdso_base = 0; + + /* + * pick a base address for the vDSO in process space. We try to put + * it at vdso_base which is the "natural" base for it, but we might + * fail and end up putting it elsewhere. + */ + down_write(&mm->mmap_sem); + vdso_base = get_unmapped_area(NULL, 0, vdso_pages << PAGE_SHIFT, 0, 0); + if (IS_ERR_VALUE(vdso_base)) { + rc = vdso_base; + goto out_up; + } + + /* + * Put vDSO base into mm struct. We need to do this before calling + * install_special_mapping or the perf counter mmap tracking code + * will fail to recognise it as a vDSO (since arch_vma_name fails). + */ + current->mm->context.vdso_base = vdso_base; + + /* + * our vma flags don't have VM_WRITE so by default, the process + * isn't allowed to write those pages. + * gdb can break that with ptrace interface, and thus trigger COW + * on those pages but it's then your responsibility to never do that + * on the "data" page of the vDSO or you'll stop getting kernel + * updates and your nice userland gettimeofday will be totally dead. + * It's fine to use that for setting breakpoints in the vDSO code + * pages though. + */ + rc = install_special_mapping(mm, vdso_base, vdso_pages << PAGE_SHIFT, + VM_READ|VM_EXEC| + VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC, + vdso_pagelist); + if (rc) + current->mm->context.vdso_base = 0; +out_up: + up_write(&mm->mmap_sem); + return rc; +} + +const char *arch_vma_name(struct vm_area_struct *vma) +{ + if (vma->vm_mm && vma->vm_start == vma->vm_mm->context.vdso_base) + return "[vdso]"; + return NULL; +} + +static int __init vdso_init(void) +{ + int i; + + if (!vdso_enabled) + return 0; + vdso_init_data(vdso_data); +#if defined(CONFIG_32BIT) || defined(CONFIG_COMPAT) + /* Calculate the size of the 32 bit vDSO */ + vdso32_pages = ((&vdso32_end - &vdso32_start + + PAGE_SIZE - 1) >> PAGE_SHIFT) + 1; + + /* Make sure pages are in the correct state */ + vdso32_pagelist = kzalloc(sizeof(struct page *) * (vdso32_pages + 1), + GFP_KERNEL); + BUG_ON(vdso32_pagelist == NULL); + for (i = 0; i < vdso32_pages - 1; i++) { + struct page *pg = virt_to_page(vdso32_kbase + i*PAGE_SIZE); + ClearPageReserved(pg); + get_page(pg); + vdso32_pagelist[i] = pg; + } + vdso32_pagelist[vdso32_pages - 1] = virt_to_page(vdso_data); + vdso32_pagelist[vdso32_pages] = NULL; +#endif + +#ifdef CONFIG_64BIT + /* Calculate the size of the 64 bit vDSO */ + vdso64_pages = ((&vdso64_end - &vdso64_start + + PAGE_SIZE - 1) >> PAGE_SHIFT) + 1; + + /* Make sure pages are in the correct state */ + vdso64_pagelist = kzalloc(sizeof(struct page *) * (vdso64_pages + 1), + GFP_KERNEL); + BUG_ON(vdso64_pagelist == NULL); + for (i = 0; i < vdso64_pages - 1; i++) { + struct page *pg = virt_to_page(vdso64_kbase + i*PAGE_SIZE); + ClearPageReserved(pg); + get_page(pg); + vdso64_pagelist[i] = pg; + } + vdso64_pagelist[vdso64_pages - 1] = virt_to_page(vdso_data); + vdso64_pagelist[vdso64_pages] = NULL; + if (vdso_alloc_per_cpu(&S390_lowcore)) + BUG(); + vdso_init_cr5(); +#endif /* CONFIG_64BIT */ + + get_page(virt_to_page(vdso_data)); + + smp_wmb(); + + return 0; +} +early_initcall(vdso_init); + +int in_gate_area_no_mm(unsigned long addr) +{ + return 0; +} + +int in_gate_area(struct mm_struct *mm, unsigned long addr) +{ + return 0; +} + +struct vm_area_struct *get_gate_vma(struct mm_struct *mm) +{ + return NULL; +} diff --git a/arch/s390/kernel/vdso32/Makefile b/arch/s390/kernel/vdso32/Makefile new file mode 100644 index 00000000..8ad2b34a --- /dev/null +++ b/arch/s390/kernel/vdso32/Makefile @@ -0,0 +1,58 @@ +# List of files in the vdso, has to be asm only for now + +obj-vdso32 = gettimeofday.o clock_getres.o clock_gettime.o note.o + +# Build rules + +targets := $(obj-vdso32) vdso32.so vdso32.so.dbg +obj-vdso32 := $(addprefix $(obj)/, $(obj-vdso32)) + +KBUILD_AFLAGS_31 := $(filter-out -m64,$(KBUILD_AFLAGS)) +KBUILD_AFLAGS_31 += -m31 -s + +KBUILD_CFLAGS_31 := $(filter-out -m64,$(KBUILD_CFLAGS)) +KBUILD_CFLAGS_31 += -m31 -fPIC -shared -fno-common -fno-builtin +KBUILD_CFLAGS_31 += -nostdlib -Wl,-soname=linux-vdso32.so.1 \ + $(call cc-ldoption, -Wl$(comma)--hash-style=sysv) + +$(targets:%=$(obj)/%.dbg): KBUILD_CFLAGS = $(KBUILD_CFLAGS_31) +$(targets:%=$(obj)/%.dbg): KBUILD_AFLAGS = $(KBUILD_AFLAGS_31) + +obj-y += vdso32_wrapper.o +extra-y += vdso32.lds +CPPFLAGS_vdso32.lds += -P -C -U$(ARCH) + +# Disable gcov profiling for VDSO code +GCOV_PROFILE := n + +# Force dependency (incbin is bad) +$(obj)/vdso32_wrapper.o : $(obj)/vdso32.so + +# link rule for the .so file, .lds has to be first +$(obj)/vdso32.so.dbg: $(src)/vdso32.lds $(obj-vdso32) + $(call if_changed,vdso32ld) + +# strip rule for the .so file +$(obj)/%.so: OBJCOPYFLAGS := -S +$(obj)/%.so: $(obj)/%.so.dbg FORCE + $(call if_changed,objcopy) + +# assembly rules for the .S files +$(obj-vdso32): %.o: %.S + $(call if_changed_dep,vdso32as) + +# actual build commands +quiet_cmd_vdso32ld = VDSO32L $@ + cmd_vdso32ld = $(CC) $(c_flags) -Wl,-T $^ -o $@ +quiet_cmd_vdso32as = VDSO32A $@ + cmd_vdso32as = $(CC) $(a_flags) -c -o $@ $< + +# install commands for the unstripped file +quiet_cmd_vdso_install = INSTALL $@ + cmd_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/vdso/$@ + +vdso32.so: $(obj)/vdso32.so.dbg + @mkdir -p $(MODLIB)/vdso + $(call cmd,vdso_install) + +vdso_install: vdso32.so diff --git a/arch/s390/kernel/vdso32/clock_getres.S b/arch/s390/kernel/vdso32/clock_getres.S new file mode 100644 index 00000000..36aaa25d --- /dev/null +++ b/arch/s390/kernel/vdso32/clock_getres.S @@ -0,0 +1,39 @@ +/* + * Userland implementation of clock_getres() for 32 bits processes in a + * s390 kernel for use in the vDSO + * + * Copyright IBM Corp. 2008 + * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com) + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License (version 2 only) + * as published by the Free Software Foundation. + */ +#include <asm/vdso.h> +#include <asm/asm-offsets.h> +#include <asm/unistd.h> + + .text + .align 4 + .globl __kernel_clock_getres + .type __kernel_clock_getres,@function +__kernel_clock_getres: + .cfi_startproc + chi %r2,__CLOCK_REALTIME + je 0f + chi %r2,__CLOCK_MONOTONIC + jne 3f +0: ltr %r3,%r3 + jz 2f /* res == NULL */ + basr %r1,0 +1: l %r0,4f-1b(%r1) + xc 0(4,%r3),0(%r3) /* set tp->tv_sec to zero */ + st %r0,4(%r3) /* store tp->tv_usec */ +2: lhi %r2,0 + br %r14 +3: lhi %r1,__NR_clock_getres /* fallback to svc */ + svc 0 + br %r14 +4: .long __CLOCK_REALTIME_RES + .cfi_endproc + .size __kernel_clock_getres,.-__kernel_clock_getres diff --git a/arch/s390/kernel/vdso32/clock_gettime.S b/arch/s390/kernel/vdso32/clock_gettime.S new file mode 100644 index 00000000..b2224e0b --- /dev/null +++ b/arch/s390/kernel/vdso32/clock_gettime.S @@ -0,0 +1,128 @@ +/* + * Userland implementation of clock_gettime() for 32 bits processes in a + * s390 kernel for use in the vDSO + * + * Copyright IBM Corp. 2008 + * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com) + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License (version 2 only) + * as published by the Free Software Foundation. + */ +#include <asm/vdso.h> +#include <asm/asm-offsets.h> +#include <asm/unistd.h> + + .text + .align 4 + .globl __kernel_clock_gettime + .type __kernel_clock_gettime,@function +__kernel_clock_gettime: + .cfi_startproc + basr %r5,0 +0: al %r5,21f-0b(%r5) /* get &_vdso_data */ + chi %r2,__CLOCK_REALTIME + je 10f + chi %r2,__CLOCK_MONOTONIC + jne 19f + + /* CLOCK_MONOTONIC */ + ltr %r3,%r3 + jz 9f /* tp == NULL */ +1: l %r4,__VDSO_UPD_COUNT+4(%r5) /* load update counter */ + tml %r4,0x0001 /* pending update ? loop */ + jnz 1b + stck 24(%r15) /* Store TOD clock */ + lm %r0,%r1,24(%r15) + s %r0,__VDSO_XTIME_STAMP(%r5) /* TOD - cycle_last */ + sl %r1,__VDSO_XTIME_STAMP+4(%r5) + brc 3,2f + ahi %r0,-1 +2: ms %r0,__VDSO_NTP_MULT(%r5) /* cyc2ns(clock,cycle_delta) */ + lr %r2,%r0 + l %r0,__VDSO_NTP_MULT(%r5) + ltr %r1,%r1 + mr %r0,%r0 + jnm 3f + a %r0,__VDSO_NTP_MULT(%r5) +3: alr %r0,%r2 + srdl %r0,12 + al %r0,__VDSO_XTIME_NSEC(%r5) /* + xtime */ + al %r1,__VDSO_XTIME_NSEC+4(%r5) + brc 12,4f + ahi %r0,1 +4: l %r2,__VDSO_XTIME_SEC+4(%r5) + al %r0,__VDSO_WTOM_NSEC(%r5) /* + wall_to_monotonic */ + al %r1,__VDSO_WTOM_NSEC+4(%r5) + brc 12,5f + ahi %r0,1 +5: al %r2,__VDSO_WTOM_SEC+4(%r5) + cl %r4,__VDSO_UPD_COUNT+4(%r5) /* check update counter */ + jne 1b + basr %r5,0 +6: ltr %r0,%r0 + jnz 7f + cl %r1,20f-6b(%r5) + jl 8f +7: ahi %r2,1 + sl %r1,20f-6b(%r5) + brc 3,6b + ahi %r0,-1 + j 6b +8: st %r2,0(%r3) /* store tp->tv_sec */ + st %r1,4(%r3) /* store tp->tv_nsec */ +9: lhi %r2,0 + br %r14 + + /* CLOCK_REALTIME */ +10: ltr %r3,%r3 /* tp == NULL */ + jz 18f +11: l %r4,__VDSO_UPD_COUNT+4(%r5) /* load update counter */ + tml %r4,0x0001 /* pending update ? loop */ + jnz 11b + stck 24(%r15) /* Store TOD clock */ + lm %r0,%r1,24(%r15) + s %r0,__VDSO_XTIME_STAMP(%r5) /* TOD - cycle_last */ + sl %r1,__VDSO_XTIME_STAMP+4(%r5) + brc 3,12f + ahi %r0,-1 +12: ms %r0,__VDSO_NTP_MULT(%r5) /* cyc2ns(clock,cycle_delta) */ + lr %r2,%r0 + l %r0,__VDSO_NTP_MULT(%r5) + ltr %r1,%r1 + mr %r0,%r0 + jnm 13f + a %r0,__VDSO_NTP_MULT(%r5) +13: alr %r0,%r2 + srdl %r0,12 + al %r0,__VDSO_XTIME_NSEC(%r5) /* + xtime */ + al %r1,__VDSO_XTIME_NSEC+4(%r5) + brc 12,14f + ahi %r0,1 +14: l %r2,__VDSO_XTIME_SEC+4(%r5) + cl %r4,__VDSO_UPD_COUNT+4(%r5) /* check update counter */ + jne 11b + basr %r5,0 +15: ltr %r0,%r0 + jnz 16f + cl %r1,20f-15b(%r5) + jl 17f +16: ahi %r2,1 + sl %r1,20f-15b(%r5) + brc 3,15b + ahi %r0,-1 + j 15b +17: st %r2,0(%r3) /* store tp->tv_sec */ + st %r1,4(%r3) /* store tp->tv_nsec */ +18: lhi %r2,0 + br %r14 + + /* Fallback to system call */ +19: lhi %r1,__NR_clock_gettime + svc 0 + br %r14 + +20: .long 1000000000 +21: .long _vdso_data - 0b + .cfi_endproc + .size __kernel_clock_gettime,.-__kernel_clock_gettime diff --git a/arch/s390/kernel/vdso32/gettimeofday.S b/arch/s390/kernel/vdso32/gettimeofday.S new file mode 100644 index 00000000..2d363317 --- /dev/null +++ b/arch/s390/kernel/vdso32/gettimeofday.S @@ -0,0 +1,78 @@ +/* + * Userland implementation of gettimeofday() for 32 bits processes in a + * s390 kernel for use in the vDSO + * + * Copyright IBM Corp. 2008 + * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com) + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License (version 2 only) + * as published by the Free Software Foundation. + */ +#include <asm/vdso.h> +#include <asm/asm-offsets.h> +#include <asm/unistd.h> + + .text + .align 4 + .globl __kernel_gettimeofday + .type __kernel_gettimeofday,@function +__kernel_gettimeofday: + .cfi_startproc + basr %r5,0 +0: al %r5,13f-0b(%r5) /* get &_vdso_data */ +1: ltr %r3,%r3 /* check if tz is NULL */ + je 2f + mvc 0(8,%r3),__VDSO_TIMEZONE(%r5) +2: ltr %r2,%r2 /* check if tv is NULL */ + je 10f + l %r4,__VDSO_UPD_COUNT+4(%r5) /* load update counter */ + tml %r4,0x0001 /* pending update ? loop */ + jnz 1b + stck 24(%r15) /* Store TOD clock */ + lm %r0,%r1,24(%r15) + s %r0,__VDSO_XTIME_STAMP(%r5) /* TOD - cycle_last */ + sl %r1,__VDSO_XTIME_STAMP+4(%r5) + brc 3,3f + ahi %r0,-1 +3: ms %r0,__VDSO_NTP_MULT(%r5) /* cyc2ns(clock,cycle_delta) */ + st %r0,24(%r15) + l %r0,__VDSO_NTP_MULT(%r5) + ltr %r1,%r1 + mr %r0,%r0 + jnm 4f + a %r0,__VDSO_NTP_MULT(%r5) +4: al %r0,24(%r15) + srdl %r0,12 + al %r0,__VDSO_XTIME_NSEC(%r5) /* + xtime */ + al %r1,__VDSO_XTIME_NSEC+4(%r5) + brc 12,5f + ahi %r0,1 +5: mvc 24(4,%r15),__VDSO_XTIME_SEC+4(%r5) + cl %r4,__VDSO_UPD_COUNT+4(%r5) /* check update counter */ + jne 1b + l %r4,24(%r15) /* get tv_sec from stack */ + basr %r5,0 +6: ltr %r0,%r0 + jnz 7f + cl %r1,11f-6b(%r5) + jl 8f +7: ahi %r4,1 + sl %r1,11f-6b(%r5) + brc 3,6b + ahi %r0,-1 + j 6b +8: st %r4,0(%r2) /* store tv->tv_sec */ + ltr %r1,%r1 + m %r0,12f-6b(%r5) + jnm 9f + al %r0,12f-6b(%r5) +9: srl %r0,6 + st %r0,4(%r2) /* store tv->tv_usec */ +10: slr %r2,%r2 + br %r14 +11: .long 1000000000 +12: .long 274877907 +13: .long _vdso_data - 0b + .cfi_endproc + .size __kernel_gettimeofday,.-__kernel_gettimeofday diff --git a/arch/s390/kernel/vdso32/note.S b/arch/s390/kernel/vdso32/note.S new file mode 100644 index 00000000..79a071e4 --- /dev/null +++ b/arch/s390/kernel/vdso32/note.S @@ -0,0 +1,12 @@ +/* + * This supplies .note.* sections to go into the PT_NOTE inside the vDSO text. + * Here we can supply some information useful to userland. + */ + +#include <linux/uts.h> +#include <linux/version.h> +#include <linux/elfnote.h> + +ELFNOTE_START(Linux, 0, "a") + .long LINUX_VERSION_CODE +ELFNOTE_END diff --git a/arch/s390/kernel/vdso32/vdso32.lds.S b/arch/s390/kernel/vdso32/vdso32.lds.S new file mode 100644 index 00000000..a8c379fa --- /dev/null +++ b/arch/s390/kernel/vdso32/vdso32.lds.S @@ -0,0 +1,138 @@ +/* + * This is the infamous ld script for the 32 bits vdso + * library + */ +#include <asm/vdso.h> + +OUTPUT_FORMAT("elf32-s390", "elf32-s390", "elf32-s390") +OUTPUT_ARCH(s390:31-bit) +ENTRY(_start) + +SECTIONS +{ + . = VDSO32_LBASE + SIZEOF_HEADERS; + + .hash : { *(.hash) } :text + .gnu.hash : { *(.gnu.hash) } + .dynsym : { *(.dynsym) } + .dynstr : { *(.dynstr) } + .gnu.version : { *(.gnu.version) } + .gnu.version_d : { *(.gnu.version_d) } + .gnu.version_r : { *(.gnu.version_r) } + + .note : { *(.note.*) } :text :note + + . = ALIGN(16); + .text : { + *(.text .stub .text.* .gnu.linkonce.t.*) + } :text + PROVIDE(__etext = .); + PROVIDE(_etext = .); + PROVIDE(etext = .); + + /* + * Other stuff is appended to the text segment: + */ + .rodata : { *(.rodata .rodata.* .gnu.linkonce.r.*) } + .rodata1 : { *(.rodata1) } + + .dynamic : { *(.dynamic) } :text :dynamic + + .eh_frame_hdr : { *(.eh_frame_hdr) } :text :eh_frame_hdr + .eh_frame : { KEEP (*(.eh_frame)) } :text + .gcc_except_table : { *(.gcc_except_table .gcc_except_table.*) } + + .rela.dyn ALIGN(8) : { *(.rela.dyn) } + .got ALIGN(8) : { *(.got .toc) } + + _end = .; + PROVIDE(end = .); + + /* + * Stabs debugging sections are here too. + */ + .stab 0 : { *(.stab) } + .stabstr 0 : { *(.stabstr) } + .stab.excl 0 : { *(.stab.excl) } + .stab.exclstr 0 : { *(.stab.exclstr) } + .stab.index 0 : { *(.stab.index) } + .stab.indexstr 0 : { *(.stab.indexstr) } + .comment 0 : { *(.comment) } + + /* + * DWARF debug sections. + * Symbols in the DWARF debugging sections are relative to the + * beginning of the section so we begin them at 0. + */ + /* DWARF 1 */ + .debug 0 : { *(.debug) } + .line 0 : { *(.line) } + /* GNU DWARF 1 extensions */ + .debug_srcinfo 0 : { *(.debug_srcinfo) } + .debug_sfnames 0 : { *(.debug_sfnames) } + /* DWARF 1.1 and DWARF 2 */ + .debug_aranges 0 : { *(.debug_aranges) } + .debug_pubnames 0 : { *(.debug_pubnames) } + /* DWARF 2 */ + .debug_info 0 : { *(.debug_info .gnu.linkonce.wi.*) } + .debug_abbrev 0 : { *(.debug_abbrev) } + .debug_line 0 : { *(.debug_line) } + .debug_frame 0 : { *(.debug_frame) } + .debug_str 0 : { *(.debug_str) } + .debug_loc 0 : { *(.debug_loc) } + .debug_macinfo 0 : { *(.debug_macinfo) } + /* SGI/MIPS DWARF 2 extensions */ + .debug_weaknames 0 : { *(.debug_weaknames) } + .debug_funcnames 0 : { *(.debug_funcnames) } + .debug_typenames 0 : { *(.debug_typenames) } + .debug_varnames 0 : { *(.debug_varnames) } + /* DWARF 3 */ + .debug_pubtypes 0 : { *(.debug_pubtypes) } + .debug_ranges 0 : { *(.debug_ranges) } + .gnu.attributes 0 : { KEEP (*(.gnu.attributes)) } + + . = ALIGN(4096); + PROVIDE(_vdso_data = .); + + /DISCARD/ : { + *(.note.GNU-stack) + *(.branch_lt) + *(.data .data.* .gnu.linkonce.d.* .sdata*) + *(.bss .sbss .dynbss .dynsbss) + } +} + +/* + * Very old versions of ld do not recognize this name token; use the constant. + */ +#define PT_GNU_EH_FRAME 0x6474e550 + +/* + * We must supply the ELF program headers explicitly to get just one + * PT_LOAD segment, and set the flags explicitly to make segments read-only. + */ +PHDRS +{ + text PT_LOAD FILEHDR PHDRS FLAGS(5); /* PF_R|PF_X */ + dynamic PT_DYNAMIC FLAGS(4); /* PF_R */ + note PT_NOTE FLAGS(4); /* PF_R */ + eh_frame_hdr PT_GNU_EH_FRAME; +} + +/* + * This controls what symbols we export from the DSO. + */ +VERSION +{ + VDSO_VERSION_STRING { + global: + /* + * Has to be there for the kernel to find + */ + __kernel_gettimeofday; + __kernel_clock_gettime; + __kernel_clock_getres; + + local: *; + }; +} diff --git a/arch/s390/kernel/vdso32/vdso32_wrapper.S b/arch/s390/kernel/vdso32/vdso32_wrapper.S new file mode 100644 index 00000000..ae42f8ce --- /dev/null +++ b/arch/s390/kernel/vdso32/vdso32_wrapper.S @@ -0,0 +1,14 @@ +#include <linux/init.h> +#include <linux/linkage.h> +#include <asm/page.h> + + __PAGE_ALIGNED_DATA + + .globl vdso32_start, vdso32_end + .balign PAGE_SIZE +vdso32_start: + .incbin "arch/s390/kernel/vdso32/vdso32.so" + .balign PAGE_SIZE +vdso32_end: + + .previous diff --git a/arch/s390/kernel/vdso64/Makefile b/arch/s390/kernel/vdso64/Makefile new file mode 100644 index 00000000..2a8ddfd1 --- /dev/null +++ b/arch/s390/kernel/vdso64/Makefile @@ -0,0 +1,58 @@ +# List of files in the vdso, has to be asm only for now + +obj-vdso64 = gettimeofday.o clock_getres.o clock_gettime.o note.o + +# Build rules + +targets := $(obj-vdso64) vdso64.so vdso64.so.dbg +obj-vdso64 := $(addprefix $(obj)/, $(obj-vdso64)) + +KBUILD_AFLAGS_64 := $(filter-out -m64,$(KBUILD_AFLAGS)) +KBUILD_AFLAGS_64 += -m64 -s + +KBUILD_CFLAGS_64 := $(filter-out -m64,$(KBUILD_CFLAGS)) +KBUILD_CFLAGS_64 += -m64 -fPIC -shared -fno-common -fno-builtin +KBUILD_CFLAGS_64 += -nostdlib -Wl,-soname=linux-vdso64.so.1 \ + $(call cc-ldoption, -Wl$(comma)--hash-style=sysv) + +$(targets:%=$(obj)/%.dbg): KBUILD_CFLAGS = $(KBUILD_CFLAGS_64) +$(targets:%=$(obj)/%.dbg): KBUILD_AFLAGS = $(KBUILD_AFLAGS_64) + +obj-y += vdso64_wrapper.o +extra-y += vdso64.lds +CPPFLAGS_vdso64.lds += -P -C -U$(ARCH) + +# Disable gcov profiling for VDSO code +GCOV_PROFILE := n + +# Force dependency (incbin is bad) +$(obj)/vdso64_wrapper.o : $(obj)/vdso64.so + +# link rule for the .so file, .lds has to be first +$(obj)/vdso64.so.dbg: $(src)/vdso64.lds $(obj-vdso64) + $(call if_changed,vdso64ld) + +# strip rule for the .so file +$(obj)/%.so: OBJCOPYFLAGS := -S +$(obj)/%.so: $(obj)/%.so.dbg FORCE + $(call if_changed,objcopy) + +# assembly rules for the .S files +$(obj-vdso64): %.o: %.S + $(call if_changed_dep,vdso64as) + +# actual build commands +quiet_cmd_vdso64ld = VDSO64L $@ + cmd_vdso64ld = $(CC) $(c_flags) -Wl,-T $^ -o $@ +quiet_cmd_vdso64as = VDSO64A $@ + cmd_vdso64as = $(CC) $(a_flags) -c -o $@ $< + +# install commands for the unstripped file +quiet_cmd_vdso_install = INSTALL $@ + cmd_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/vdso/$@ + +vdso64.so: $(obj)/vdso64.so.dbg + @mkdir -p $(MODLIB)/vdso + $(call cmd,vdso_install) + +vdso_install: vdso64.so diff --git a/arch/s390/kernel/vdso64/clock_getres.S b/arch/s390/kernel/vdso64/clock_getres.S new file mode 100644 index 00000000..176e1f75 --- /dev/null +++ b/arch/s390/kernel/vdso64/clock_getres.S @@ -0,0 +1,44 @@ +/* + * Userland implementation of clock_getres() for 64 bits processes in a + * s390 kernel for use in the vDSO + * + * Copyright IBM Corp. 2008 + * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com) + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License (version 2 only) + * as published by the Free Software Foundation. + */ +#include <asm/vdso.h> +#include <asm/asm-offsets.h> +#include <asm/unistd.h> + + .text + .align 4 + .globl __kernel_clock_getres + .type __kernel_clock_getres,@function +__kernel_clock_getres: + .cfi_startproc + cghi %r2,__CLOCK_REALTIME + je 0f + cghi %r2,__CLOCK_MONOTONIC + je 0f + cghi %r2,-2 /* CLOCK_THREAD_CPUTIME_ID for this thread */ + jne 2f + larl %r5,_vdso_data + icm %r0,15,__LC_ECTG_OK(%r5) + jz 2f +0: ltgr %r3,%r3 + jz 1f /* res == NULL */ + larl %r1,3f + lg %r0,0(%r1) + xc 0(8,%r3),0(%r3) /* set tp->tv_sec to zero */ + stg %r0,8(%r3) /* store tp->tv_usec */ +1: lghi %r2,0 + br %r14 +2: lghi %r1,__NR_clock_getres /* fallback to svc */ + svc 0 + br %r14 +3: .quad __CLOCK_REALTIME_RES + .cfi_endproc + .size __kernel_clock_getres,.-__kernel_clock_getres diff --git a/arch/s390/kernel/vdso64/clock_gettime.S b/arch/s390/kernel/vdso64/clock_gettime.S new file mode 100644 index 00000000..d46c95ed --- /dev/null +++ b/arch/s390/kernel/vdso64/clock_gettime.S @@ -0,0 +1,125 @@ +/* + * Userland implementation of clock_gettime() for 64 bits processes in a + * s390 kernel for use in the vDSO + * + * Copyright IBM Corp. 2008 + * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com) + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License (version 2 only) + * as published by the Free Software Foundation. + */ +#include <asm/vdso.h> +#include <asm/asm-offsets.h> +#include <asm/unistd.h> + + .text + .align 4 + .globl __kernel_clock_gettime + .type __kernel_clock_gettime,@function +__kernel_clock_gettime: + .cfi_startproc + larl %r5,_vdso_data + cghi %r2,__CLOCK_REALTIME + je 4f + cghi %r2,-2 /* CLOCK_THREAD_CPUTIME_ID for this thread */ + je 9f + cghi %r2,__CLOCK_MONOTONIC + jne 12f + + /* CLOCK_MONOTONIC */ + ltgr %r3,%r3 + jz 3f /* tp == NULL */ +0: lg %r4,__VDSO_UPD_COUNT(%r5) /* load update counter */ + tmll %r4,0x0001 /* pending update ? loop */ + jnz 0b + stck 48(%r15) /* Store TOD clock */ + lg %r1,48(%r15) + sg %r1,__VDSO_XTIME_STAMP(%r5) /* TOD - cycle_last */ + msgf %r1,__VDSO_NTP_MULT(%r5) /* * NTP adjustment */ + srlg %r1,%r1,12 /* cyc2ns(clock,cycle_delta) */ + alg %r1,__VDSO_XTIME_NSEC(%r5) /* + xtime */ + lg %r0,__VDSO_XTIME_SEC(%r5) + alg %r1,__VDSO_WTOM_NSEC(%r5) /* + wall_to_monotonic */ + alg %r0,__VDSO_WTOM_SEC(%r5) + clg %r4,__VDSO_UPD_COUNT(%r5) /* check update counter */ + jne 0b + larl %r5,13f +1: clg %r1,0(%r5) + jl 2f + slg %r1,0(%r5) + aghi %r0,1 + j 1b +2: stg %r0,0(%r3) /* store tp->tv_sec */ + stg %r1,8(%r3) /* store tp->tv_nsec */ +3: lghi %r2,0 + br %r14 + + /* CLOCK_REALTIME */ +4: ltr %r3,%r3 /* tp == NULL */ + jz 8f +5: lg %r4,__VDSO_UPD_COUNT(%r5) /* load update counter */ + tmll %r4,0x0001 /* pending update ? loop */ + jnz 5b + stck 48(%r15) /* Store TOD clock */ + lg %r1,48(%r15) + sg %r1,__VDSO_XTIME_STAMP(%r5) /* TOD - cycle_last */ + msgf %r1,__VDSO_NTP_MULT(%r5) /* * NTP adjustment */ + srlg %r1,%r1,12 /* cyc2ns(clock,cycle_delta) */ + alg %r1,__VDSO_XTIME_NSEC(%r5) /* + xtime */ + lg %r0,__VDSO_XTIME_SEC(%r5) + clg %r4,__VDSO_UPD_COUNT(%r5) /* check update counter */ + jne 5b + larl %r5,13f +6: clg %r1,0(%r5) + jl 7f + slg %r1,0(%r5) + aghi %r0,1 + j 6b +7: stg %r0,0(%r3) /* store tp->tv_sec */ + stg %r1,8(%r3) /* store tp->tv_nsec */ +8: lghi %r2,0 + br %r14 + + /* CLOCK_THREAD_CPUTIME_ID for this thread */ +9: icm %r0,15,__VDSO_ECTG_OK(%r5) + jz 12f + ear %r2,%a4 + llilh %r4,0x0100 + sar %a4,%r4 + lghi %r4,0 + epsw %r5,0 + sacf 512 /* Magic ectg instruction */ + .insn ssf,0xc80100000000,__VDSO_ECTG_BASE(4),__VDSO_ECTG_USER(4),4 + tml %r5,0x4000 + jo 11f + tml %r5,0x8000 + jno 10f + sacf 256 + j 11f +10: sacf 0 +11: sar %a4,%r2 + algr %r1,%r0 /* r1 = cputime as TOD value */ + mghi %r1,1000 /* convert to nanoseconds */ + srlg %r1,%r1,12 /* r1 = cputime in nanosec */ + lgr %r4,%r1 + larl %r5,13f + srlg %r1,%r1,9 /* divide by 1000000000 */ + mlg %r0,8(%r5) + srlg %r0,%r0,11 /* r0 = tv_sec */ + stg %r0,0(%r3) + msg %r0,0(%r5) /* calculate tv_nsec */ + slgr %r4,%r0 /* r4 = tv_nsec */ + stg %r4,8(%r3) + lghi %r2,0 + br %r14 + + /* Fallback to system call */ +12: lghi %r1,__NR_clock_gettime + svc 0 + br %r14 + +13: .quad 1000000000 +14: .quad 19342813113834067 + .cfi_endproc + .size __kernel_clock_gettime,.-__kernel_clock_gettime diff --git a/arch/s390/kernel/vdso64/gettimeofday.S b/arch/s390/kernel/vdso64/gettimeofday.S new file mode 100644 index 00000000..36ee6747 --- /dev/null +++ b/arch/s390/kernel/vdso64/gettimeofday.S @@ -0,0 +1,56 @@ +/* + * Userland implementation of gettimeofday() for 64 bits processes in a + * s390 kernel for use in the vDSO + * + * Copyright IBM Corp. 2008 + * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com) + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License (version 2 only) + * as published by the Free Software Foundation. + */ +#include <asm/vdso.h> +#include <asm/asm-offsets.h> +#include <asm/unistd.h> + + .text + .align 4 + .globl __kernel_gettimeofday + .type __kernel_gettimeofday,@function +__kernel_gettimeofday: + .cfi_startproc + larl %r5,_vdso_data +0: ltgr %r3,%r3 /* check if tz is NULL */ + je 1f + mvc 0(8,%r3),__VDSO_TIMEZONE(%r5) +1: ltgr %r2,%r2 /* check if tv is NULL */ + je 4f + lg %r4,__VDSO_UPD_COUNT(%r5) /* load update counter */ + tmll %r4,0x0001 /* pending update ? loop */ + jnz 0b + stck 48(%r15) /* Store TOD clock */ + lg %r1,48(%r15) + sg %r1,__VDSO_XTIME_STAMP(%r5) /* TOD - cycle_last */ + msgf %r1,__VDSO_NTP_MULT(%r5) /* * NTP adjustment */ + srlg %r1,%r1,12 /* cyc2ns(clock,cycle_delta) */ + alg %r1,__VDSO_XTIME_NSEC(%r5) /* + xtime.tv_nsec */ + lg %r0,__VDSO_XTIME_SEC(%r5) /* xtime.tv_sec */ + clg %r4,__VDSO_UPD_COUNT(%r5) /* check update counter */ + jne 0b + larl %r5,5f +2: clg %r1,0(%r5) + jl 3f + slg %r1,0(%r5) + aghi %r0,1 + j 2b +3: stg %r0,0(%r2) /* store tv->tv_sec */ + slgr %r0,%r0 /* tv_nsec -> tv_usec */ + ml %r0,8(%r5) + srlg %r0,%r0,6 + stg %r0,8(%r2) /* store tv->tv_usec */ +4: lghi %r2,0 + br %r14 +5: .quad 1000000000 + .long 274877907 + .cfi_endproc + .size __kernel_gettimeofday,.-__kernel_gettimeofday diff --git a/arch/s390/kernel/vdso64/note.S b/arch/s390/kernel/vdso64/note.S new file mode 100644 index 00000000..79a071e4 --- /dev/null +++ b/arch/s390/kernel/vdso64/note.S @@ -0,0 +1,12 @@ +/* + * This supplies .note.* sections to go into the PT_NOTE inside the vDSO text. + * Here we can supply some information useful to userland. + */ + +#include <linux/uts.h> +#include <linux/version.h> +#include <linux/elfnote.h> + +ELFNOTE_START(Linux, 0, "a") + .long LINUX_VERSION_CODE +ELFNOTE_END diff --git a/arch/s390/kernel/vdso64/vdso64.lds.S b/arch/s390/kernel/vdso64/vdso64.lds.S new file mode 100644 index 00000000..9f5979d1 --- /dev/null +++ b/arch/s390/kernel/vdso64/vdso64.lds.S @@ -0,0 +1,138 @@ +/* + * This is the infamous ld script for the 64 bits vdso + * library + */ +#include <asm/vdso.h> + +OUTPUT_FORMAT("elf64-s390", "elf64-s390", "elf64-s390") +OUTPUT_ARCH(s390:64-bit) +ENTRY(_start) + +SECTIONS +{ + . = VDSO64_LBASE + SIZEOF_HEADERS; + + .hash : { *(.hash) } :text + .gnu.hash : { *(.gnu.hash) } + .dynsym : { *(.dynsym) } + .dynstr : { *(.dynstr) } + .gnu.version : { *(.gnu.version) } + .gnu.version_d : { *(.gnu.version_d) } + .gnu.version_r : { *(.gnu.version_r) } + + .note : { *(.note.*) } :text :note + + . = ALIGN(16); + .text : { + *(.text .stub .text.* .gnu.linkonce.t.*) + } :text + PROVIDE(__etext = .); + PROVIDE(_etext = .); + PROVIDE(etext = .); + + /* + * Other stuff is appended to the text segment: + */ + .rodata : { *(.rodata .rodata.* .gnu.linkonce.r.*) } + .rodata1 : { *(.rodata1) } + + .dynamic : { *(.dynamic) } :text :dynamic + + .eh_frame_hdr : { *(.eh_frame_hdr) } :text :eh_frame_hdr + .eh_frame : { KEEP (*(.eh_frame)) } :text + .gcc_except_table : { *(.gcc_except_table .gcc_except_table.*) } + + .rela.dyn ALIGN(8) : { *(.rela.dyn) } + .got ALIGN(8) : { *(.got .toc) } + + _end = .; + PROVIDE(end = .); + + /* + * Stabs debugging sections are here too. + */ + .stab 0 : { *(.stab) } + .stabstr 0 : { *(.stabstr) } + .stab.excl 0 : { *(.stab.excl) } + .stab.exclstr 0 : { *(.stab.exclstr) } + .stab.index 0 : { *(.stab.index) } + .stab.indexstr 0 : { *(.stab.indexstr) } + .comment 0 : { *(.comment) } + + /* + * DWARF debug sections. + * Symbols in the DWARF debugging sections are relative to the + * beginning of the section so we begin them at 0. + */ + /* DWARF 1 */ + .debug 0 : { *(.debug) } + .line 0 : { *(.line) } + /* GNU DWARF 1 extensions */ + .debug_srcinfo 0 : { *(.debug_srcinfo) } + .debug_sfnames 0 : { *(.debug_sfnames) } + /* DWARF 1.1 and DWARF 2 */ + .debug_aranges 0 : { *(.debug_aranges) } + .debug_pubnames 0 : { *(.debug_pubnames) } + /* DWARF 2 */ + .debug_info 0 : { *(.debug_info .gnu.linkonce.wi.*) } + .debug_abbrev 0 : { *(.debug_abbrev) } + .debug_line 0 : { *(.debug_line) } + .debug_frame 0 : { *(.debug_frame) } + .debug_str 0 : { *(.debug_str) } + .debug_loc 0 : { *(.debug_loc) } + .debug_macinfo 0 : { *(.debug_macinfo) } + /* SGI/MIPS DWARF 2 extensions */ + .debug_weaknames 0 : { *(.debug_weaknames) } + .debug_funcnames 0 : { *(.debug_funcnames) } + .debug_typenames 0 : { *(.debug_typenames) } + .debug_varnames 0 : { *(.debug_varnames) } + /* DWARF 3 */ + .debug_pubtypes 0 : { *(.debug_pubtypes) } + .debug_ranges 0 : { *(.debug_ranges) } + .gnu.attributes 0 : { KEEP (*(.gnu.attributes)) } + + . = ALIGN(4096); + PROVIDE(_vdso_data = .); + + /DISCARD/ : { + *(.note.GNU-stack) + *(.branch_lt) + *(.data .data.* .gnu.linkonce.d.* .sdata*) + *(.bss .sbss .dynbss .dynsbss) + } +} + +/* + * Very old versions of ld do not recognize this name token; use the constant. + */ +#define PT_GNU_EH_FRAME 0x6474e550 + +/* + * We must supply the ELF program headers explicitly to get just one + * PT_LOAD segment, and set the flags explicitly to make segments read-only. + */ +PHDRS +{ + text PT_LOAD FILEHDR PHDRS FLAGS(5); /* PF_R|PF_X */ + dynamic PT_DYNAMIC FLAGS(4); /* PF_R */ + note PT_NOTE FLAGS(4); /* PF_R */ + eh_frame_hdr PT_GNU_EH_FRAME; +} + +/* + * This controls what symbols we export from the DSO. + */ +VERSION +{ + VDSO_VERSION_STRING { + global: + /* + * Has to be there for the kernel to find + */ + __kernel_gettimeofday; + __kernel_clock_gettime; + __kernel_clock_getres; + + local: *; + }; +} diff --git a/arch/s390/kernel/vdso64/vdso64_wrapper.S b/arch/s390/kernel/vdso64/vdso64_wrapper.S new file mode 100644 index 00000000..c245842b --- /dev/null +++ b/arch/s390/kernel/vdso64/vdso64_wrapper.S @@ -0,0 +1,14 @@ +#include <linux/init.h> +#include <linux/linkage.h> +#include <asm/page.h> + + __PAGE_ALIGNED_DATA + + .globl vdso64_start, vdso64_end + .balign PAGE_SIZE +vdso64_start: + .incbin "arch/s390/kernel/vdso64/vdso64.so" + .balign PAGE_SIZE +vdso64_end: + + .previous diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S new file mode 100644 index 00000000..21109c63 --- /dev/null +++ b/arch/s390/kernel/vmlinux.lds.S @@ -0,0 +1,96 @@ +/* ld script to make s390 Linux kernel + * Written by Martin Schwidefsky (schwidefsky@de.ibm.com) + */ + +#include <asm/thread_info.h> +#include <asm/page.h> +#include <asm-generic/vmlinux.lds.h> + +#ifndef CONFIG_64BIT +OUTPUT_FORMAT("elf32-s390", "elf32-s390", "elf32-s390") +OUTPUT_ARCH(s390) +ENTRY(startup) +jiffies = jiffies_64 + 4; +#else +OUTPUT_FORMAT("elf64-s390", "elf64-s390", "elf64-s390") +OUTPUT_ARCH(s390:64-bit) +ENTRY(startup) +jiffies = jiffies_64; +#endif + +PHDRS { + text PT_LOAD FLAGS(5); /* R_E */ + data PT_LOAD FLAGS(7); /* RWE */ + note PT_NOTE FLAGS(0); /* ___ */ +} + +SECTIONS +{ + . = 0x00000000; + .text : { + _text = .; /* Text and read-only data */ + HEAD_TEXT + TEXT_TEXT + SCHED_TEXT + LOCK_TEXT + KPROBES_TEXT + IRQENTRY_TEXT + *(.fixup) + *(.gnu.warning) + } :text = 0x0700 + + _etext = .; /* End of text section */ + + NOTES :text :note + + .dummy : { *(.dummy) } :data + + RODATA + +#ifdef CONFIG_SHARED_KERNEL + . = ALIGN(0x100000); /* VM shared segments are 1MB aligned */ +#endif + + . = ALIGN(PAGE_SIZE); + _eshared = .; /* End of shareable data */ + _sdata = .; /* Start of data section */ + + EXCEPTION_TABLE(16) :data + + RW_DATA_SECTION(0x100, PAGE_SIZE, THREAD_SIZE) + + _edata = .; /* End of data section */ + + /* will be freed after init */ + . = ALIGN(PAGE_SIZE); /* Init code and data */ + __init_begin = .; + + INIT_TEXT_SECTION(PAGE_SIZE) + + /* + * .exit.text is discarded at runtime, not link time, + * to deal with references from __bug_table + */ + .exit.text : { + EXIT_TEXT + } + + /* early.c uses stsi, which requires page aligned data. */ + . = ALIGN(PAGE_SIZE); + INIT_DATA_SECTION(0x100) + + PERCPU_SECTION(0x100) + . = ALIGN(PAGE_SIZE); + __init_end = .; /* freed after init ends here */ + + BSS_SECTION(0, 2, 0) + + _end = . ; + + /* Debugging sections. */ + STABS_DEBUG + DWARF_DEBUG + + /* Sections to be discarded */ + DISCARDS +} diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c new file mode 100644 index 00000000..39ebff50 --- /dev/null +++ b/arch/s390/kernel/vtime.c @@ -0,0 +1,504 @@ +/* + * arch/s390/kernel/vtime.c + * Virtual cpu timer based timer functions. + * + * S390 version + * Copyright (C) 2004 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Author(s): Jan Glauber <jan.glauber@de.ibm.com> + */ + +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/time.h> +#include <linux/delay.h> +#include <linux/init.h> +#include <linux/smp.h> +#include <linux/types.h> +#include <linux/timex.h> +#include <linux/notifier.h> +#include <linux/kernel_stat.h> +#include <linux/rcupdate.h> +#include <linux/posix-timers.h> +#include <linux/cpu.h> +#include <linux/kprobes.h> + +#include <asm/timer.h> +#include <asm/irq_regs.h> +#include <asm/cputime.h> +#include <asm/irq.h> +#include "entry.h" + +static DEFINE_PER_CPU(struct vtimer_queue, virt_cpu_timer); + +DEFINE_PER_CPU(struct s390_idle_data, s390_idle); + +static inline __u64 get_vtimer(void) +{ + __u64 timer; + + asm volatile("STPT %0" : "=m" (timer)); + return timer; +} + +static inline void set_vtimer(__u64 expires) +{ + __u64 timer; + + asm volatile (" STPT %0\n" /* Store current cpu timer value */ + " SPT %1" /* Set new value immediately afterwards */ + : "=m" (timer) : "m" (expires) ); + S390_lowcore.system_timer += S390_lowcore.last_update_timer - timer; + S390_lowcore.last_update_timer = expires; +} + +/* + * Update process times based on virtual cpu times stored by entry.S + * to the lowcore fields user_timer, system_timer & steal_clock. + */ +static void do_account_vtime(struct task_struct *tsk, int hardirq_offset) +{ + struct thread_info *ti = task_thread_info(tsk); + __u64 timer, clock, user, system, steal; + + timer = S390_lowcore.last_update_timer; + clock = S390_lowcore.last_update_clock; + asm volatile (" STPT %0\n" /* Store current cpu timer value */ + " STCK %1" /* Store current tod clock value */ + : "=m" (S390_lowcore.last_update_timer), + "=m" (S390_lowcore.last_update_clock) ); + S390_lowcore.system_timer += timer - S390_lowcore.last_update_timer; + S390_lowcore.steal_timer += S390_lowcore.last_update_clock - clock; + + user = S390_lowcore.user_timer - ti->user_timer; + S390_lowcore.steal_timer -= user; + ti->user_timer = S390_lowcore.user_timer; + account_user_time(tsk, user, user); + + system = S390_lowcore.system_timer - ti->system_timer; + S390_lowcore.steal_timer -= system; + ti->system_timer = S390_lowcore.system_timer; + account_system_time(tsk, hardirq_offset, system, system); + + steal = S390_lowcore.steal_timer; + if ((s64) steal > 0) { + S390_lowcore.steal_timer = 0; + account_steal_time(steal); + } +} + +void account_vtime(struct task_struct *prev, struct task_struct *next) +{ + struct thread_info *ti; + + do_account_vtime(prev, 0); + ti = task_thread_info(prev); + ti->user_timer = S390_lowcore.user_timer; + ti->system_timer = S390_lowcore.system_timer; + ti = task_thread_info(next); + S390_lowcore.user_timer = ti->user_timer; + S390_lowcore.system_timer = ti->system_timer; +} + +void account_process_tick(struct task_struct *tsk, int user_tick) +{ + do_account_vtime(tsk, HARDIRQ_OFFSET); +} + +/* + * Update process times based on virtual cpu times stored by entry.S + * to the lowcore fields user_timer, system_timer & steal_clock. + */ +void account_system_vtime(struct task_struct *tsk) +{ + struct thread_info *ti = task_thread_info(tsk); + __u64 timer, system; + + timer = S390_lowcore.last_update_timer; + S390_lowcore.last_update_timer = get_vtimer(); + S390_lowcore.system_timer += timer - S390_lowcore.last_update_timer; + + system = S390_lowcore.system_timer - ti->system_timer; + S390_lowcore.steal_timer -= system; + ti->system_timer = S390_lowcore.system_timer; + account_system_time(tsk, 0, system, system); +} +EXPORT_SYMBOL_GPL(account_system_vtime); + +void __kprobes vtime_stop_cpu(void) +{ + struct s390_idle_data *idle = &__get_cpu_var(s390_idle); + struct vtimer_queue *vq = &__get_cpu_var(virt_cpu_timer); + unsigned long long idle_time; + unsigned long psw_mask; + + trace_hardirqs_on(); + /* Don't trace preempt off for idle. */ + stop_critical_timings(); + + /* Wait for external, I/O or machine check interrupt. */ + psw_mask = psw_kernel_bits | PSW_MASK_WAIT | PSW_MASK_DAT | + PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK; + idle->nohz_delay = 0; + + /* Call the assembler magic in entry.S */ + psw_idle(idle, vq, psw_mask, !list_empty(&vq->list)); + + /* Reenable preemption tracer. */ + start_critical_timings(); + + /* Account time spent with enabled wait psw loaded as idle time. */ + idle->sequence++; + smp_wmb(); + idle_time = idle->idle_exit - idle->idle_enter; + idle->idle_time += idle_time; + idle->idle_enter = idle->idle_exit = 0ULL; + idle->idle_count++; + account_idle_time(idle_time); + smp_wmb(); + idle->sequence++; +} + +cputime64_t s390_get_idle_time(int cpu) +{ + struct s390_idle_data *idle = &per_cpu(s390_idle, cpu); + unsigned long long now, idle_enter, idle_exit; + unsigned int sequence; + + do { + now = get_clock(); + sequence = ACCESS_ONCE(idle->sequence); + idle_enter = ACCESS_ONCE(idle->idle_enter); + idle_exit = ACCESS_ONCE(idle->idle_exit); + } while ((sequence & 1) || (idle->sequence != sequence)); + return idle_enter ? ((idle_exit ? : now) - idle_enter) : 0; +} + +/* + * Sorted add to a list. List is linear searched until first bigger + * element is found. + */ +static void list_add_sorted(struct vtimer_list *timer, struct list_head *head) +{ + struct vtimer_list *event; + + list_for_each_entry(event, head, entry) { + if (event->expires > timer->expires) { + list_add_tail(&timer->entry, &event->entry); + return; + } + } + list_add_tail(&timer->entry, head); +} + +/* + * Do the callback functions of expired vtimer events. + * Called from within the interrupt handler. + */ +static void do_callbacks(struct list_head *cb_list) +{ + struct vtimer_queue *vq; + struct vtimer_list *event, *tmp; + + if (list_empty(cb_list)) + return; + + vq = &__get_cpu_var(virt_cpu_timer); + + list_for_each_entry_safe(event, tmp, cb_list, entry) { + list_del_init(&event->entry); + (event->function)(event->data); + if (event->interval) { + /* Recharge interval timer */ + event->expires = event->interval + vq->elapsed; + spin_lock(&vq->lock); + list_add_sorted(event, &vq->list); + spin_unlock(&vq->lock); + } + } +} + +/* + * Handler for the virtual CPU timer. + */ +static void do_cpu_timer_interrupt(struct ext_code ext_code, + unsigned int param32, unsigned long param64) +{ + struct vtimer_queue *vq; + struct vtimer_list *event, *tmp; + struct list_head cb_list; /* the callback queue */ + __u64 elapsed, next; + + kstat_cpu(smp_processor_id()).irqs[EXTINT_TMR]++; + INIT_LIST_HEAD(&cb_list); + vq = &__get_cpu_var(virt_cpu_timer); + + /* walk timer list, fire all expired events */ + spin_lock(&vq->lock); + + elapsed = vq->elapsed + (vq->timer - S390_lowcore.async_enter_timer); + BUG_ON((s64) elapsed < 0); + vq->elapsed = 0; + list_for_each_entry_safe(event, tmp, &vq->list, entry) { + if (event->expires < elapsed) + /* move expired timer to the callback queue */ + list_move_tail(&event->entry, &cb_list); + else + event->expires -= elapsed; + } + spin_unlock(&vq->lock); + + do_callbacks(&cb_list); + + /* next event is first in list */ + next = VTIMER_MAX_SLICE; + spin_lock(&vq->lock); + if (!list_empty(&vq->list)) { + event = list_first_entry(&vq->list, struct vtimer_list, entry); + next = event->expires; + } + spin_unlock(&vq->lock); + /* + * To improve precision add the time spent by the + * interrupt handler to the elapsed time. + * Note: CPU timer counts down and we got an interrupt, + * the current content is negative + */ + elapsed = S390_lowcore.async_enter_timer - get_vtimer(); + set_vtimer(next - elapsed); + vq->timer = next - elapsed; + vq->elapsed = elapsed; +} + +void init_virt_timer(struct vtimer_list *timer) +{ + timer->function = NULL; + INIT_LIST_HEAD(&timer->entry); +} +EXPORT_SYMBOL(init_virt_timer); + +static inline int vtimer_pending(struct vtimer_list *timer) +{ + return (!list_empty(&timer->entry)); +} + +/* + * this function should only run on the specified CPU + */ +static void internal_add_vtimer(struct vtimer_list *timer) +{ + struct vtimer_queue *vq; + unsigned long flags; + __u64 left, expires; + + vq = &per_cpu(virt_cpu_timer, timer->cpu); + spin_lock_irqsave(&vq->lock, flags); + + BUG_ON(timer->cpu != smp_processor_id()); + + if (list_empty(&vq->list)) { + /* First timer on this cpu, just program it. */ + list_add(&timer->entry, &vq->list); + set_vtimer(timer->expires); + vq->timer = timer->expires; + vq->elapsed = 0; + } else { + /* Check progress of old timers. */ + expires = timer->expires; + left = get_vtimer(); + if (likely((s64) expires < (s64) left)) { + /* The new timer expires before the current timer. */ + set_vtimer(expires); + vq->elapsed += vq->timer - left; + vq->timer = expires; + } else { + vq->elapsed += vq->timer - left; + vq->timer = left; + } + /* Insert new timer into per cpu list. */ + timer->expires += vq->elapsed; + list_add_sorted(timer, &vq->list); + } + + spin_unlock_irqrestore(&vq->lock, flags); + /* release CPU acquired in prepare_vtimer or mod_virt_timer() */ + put_cpu(); +} + +static inline void prepare_vtimer(struct vtimer_list *timer) +{ + BUG_ON(!timer->function); + BUG_ON(!timer->expires || timer->expires > VTIMER_MAX_SLICE); + BUG_ON(vtimer_pending(timer)); + timer->cpu = get_cpu(); +} + +/* + * add_virt_timer - add an oneshot virtual CPU timer + */ +void add_virt_timer(void *new) +{ + struct vtimer_list *timer; + + timer = (struct vtimer_list *)new; + prepare_vtimer(timer); + timer->interval = 0; + internal_add_vtimer(timer); +} +EXPORT_SYMBOL(add_virt_timer); + +/* + * add_virt_timer_int - add an interval virtual CPU timer + */ +void add_virt_timer_periodic(void *new) +{ + struct vtimer_list *timer; + + timer = (struct vtimer_list *)new; + prepare_vtimer(timer); + timer->interval = timer->expires; + internal_add_vtimer(timer); +} +EXPORT_SYMBOL(add_virt_timer_periodic); + +static int __mod_vtimer(struct vtimer_list *timer, __u64 expires, int periodic) +{ + struct vtimer_queue *vq; + unsigned long flags; + int cpu; + + BUG_ON(!timer->function); + BUG_ON(!expires || expires > VTIMER_MAX_SLICE); + + if (timer->expires == expires && vtimer_pending(timer)) + return 1; + + cpu = get_cpu(); + vq = &per_cpu(virt_cpu_timer, cpu); + + /* disable interrupts before test if timer is pending */ + spin_lock_irqsave(&vq->lock, flags); + + /* if timer isn't pending add it on the current CPU */ + if (!vtimer_pending(timer)) { + spin_unlock_irqrestore(&vq->lock, flags); + + if (periodic) + timer->interval = expires; + else + timer->interval = 0; + timer->expires = expires; + timer->cpu = cpu; + internal_add_vtimer(timer); + return 0; + } + + /* check if we run on the right CPU */ + BUG_ON(timer->cpu != cpu); + + list_del_init(&timer->entry); + timer->expires = expires; + if (periodic) + timer->interval = expires; + + /* the timer can't expire anymore so we can release the lock */ + spin_unlock_irqrestore(&vq->lock, flags); + internal_add_vtimer(timer); + return 1; +} + +/* + * If we change a pending timer the function must be called on the CPU + * where the timer is running on. + * + * returns whether it has modified a pending timer (1) or not (0) + */ +int mod_virt_timer(struct vtimer_list *timer, __u64 expires) +{ + return __mod_vtimer(timer, expires, 0); +} +EXPORT_SYMBOL(mod_virt_timer); + +/* + * If we change a pending timer the function must be called on the CPU + * where the timer is running on. + * + * returns whether it has modified a pending timer (1) or not (0) + */ +int mod_virt_timer_periodic(struct vtimer_list *timer, __u64 expires) +{ + return __mod_vtimer(timer, expires, 1); +} +EXPORT_SYMBOL(mod_virt_timer_periodic); + +/* + * delete a virtual timer + * + * returns whether the deleted timer was pending (1) or not (0) + */ +int del_virt_timer(struct vtimer_list *timer) +{ + unsigned long flags; + struct vtimer_queue *vq; + + /* check if timer is pending */ + if (!vtimer_pending(timer)) + return 0; + + vq = &per_cpu(virt_cpu_timer, timer->cpu); + spin_lock_irqsave(&vq->lock, flags); + + /* we don't interrupt a running timer, just let it expire! */ + list_del_init(&timer->entry); + + spin_unlock_irqrestore(&vq->lock, flags); + return 1; +} +EXPORT_SYMBOL(del_virt_timer); + +/* + * Start the virtual CPU timer on the current CPU. + */ +void init_cpu_vtimer(void) +{ + struct vtimer_queue *vq; + + /* initialize per cpu vtimer structure */ + vq = &__get_cpu_var(virt_cpu_timer); + INIT_LIST_HEAD(&vq->list); + spin_lock_init(&vq->lock); + + /* enable cpu timer interrupts */ + __ctl_set_bit(0,10); + + /* set initial cpu timer */ + set_vtimer(0x7fffffffffffffffULL); +} + +static int __cpuinit s390_nohz_notify(struct notifier_block *self, + unsigned long action, void *hcpu) +{ + struct s390_idle_data *idle; + long cpu = (long) hcpu; + + idle = &per_cpu(s390_idle, cpu); + switch (action) { + case CPU_DYING: + case CPU_DYING_FROZEN: + idle->nohz_delay = 0; + default: + break; + } + return NOTIFY_OK; +} + +void __init vtime_init(void) +{ + /* request the cpu timer external interrupt */ + if (register_external_interrupt(0x1005, do_cpu_timer_interrupt)) + panic("Couldn't request external interrupt 0x1005"); + + /* Enable cpu timer interrupts on the boot cpu. */ + init_cpu_vtimer(); + cpu_notifier(s390_nohz_notify, 0); +} + |