diff options
Diffstat (limited to 'arch/s390/kernel')
62 files changed, 4913 insertions, 4383 deletions
diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile index 2ac311ef5c9..a95c4ca9961 100644 --- a/arch/s390/kernel/Makefile +++ b/arch/s390/kernel/Makefile @@ -14,16 +14,25 @@ endif CFLAGS_smp.o := -Wno-nonnull # +# Disable tailcall optimizations for stack / callchain walking functions +# since this might generate broken code when accessing register 15 and +# passing its content to other functions. +# +CFLAGS_stacktrace.o += -fno-optimize-sibling-calls +CFLAGS_dumpstack.o += -fno-optimize-sibling-calls + +# # 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 machine_kexec.o pgm_check.o +obj-y := traps.o time.o process.o base.o early.o setup.o vtime.o +obj-y += processor.o sys_s390.o ptrace.o signal.o cpcmd.o ebcdic.o nmi.o +obj-y += debug.o irq.o ipl.o dis.o diag.o sclp.o vdso.o +obj-y += sysinfo.o jump_label.o lgr.o os_info.o machine_kexec.o pgm_check.o +obj-y += dumpstack.o obj-y += $(if $(CONFIG_64BIT),entry64.o,entry.o) obj-y += $(if $(CONFIG_64BIT),reipl64.o,reipl.o) @@ -38,9 +47,8 @@ obj-$(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_COMPAT) += compat_linux.o compat_signal.o +obj-$(CONFIG_COMPAT) += compat_wrapper.o $(compat-obj-y) obj-$(CONFIG_STACKTRACE) += stacktrace.o obj-$(CONFIG_KPROBES) += kprobes.o @@ -51,7 +59,8 @@ obj-$(CONFIG_FTRACE_SYSCALLS) += ftrace.o obj-$(CONFIG_CRASH_DUMP) += crash_dump.o ifdef CONFIG_64BIT -obj-$(CONFIG_PERF_EVENTS) += perf_event.o perf_cpum_cf.o +obj-$(CONFIG_PERF_EVENTS) += perf_event.o perf_cpum_cf.o perf_cpum_sf.o \ + perf_cpum_cf_events.o obj-y += runtime_instr.o cache.o endif diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c index fface87056e..afe1715a4eb 100644 --- a/arch/s390/kernel/asm-offsets.c +++ b/arch/s390/kernel/asm-offsets.c @@ -7,6 +7,7 @@ #define ASM_OFFSETS_C #include <linux/kbuild.h> +#include <linux/kvm_host.h> #include <linux/sched.h> #include <asm/cputime.h> #include <asm/vdso.h> @@ -35,6 +36,7 @@ int main(void) 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_sysc_table, offsetof(struct thread_info, sys_call_table)); 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)); @@ -46,7 +48,9 @@ int main(void) 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, offsetof(struct pt_regs, int_parm)); DEFINE(__PT_INT_PARM_LONG, offsetof(struct pt_regs, int_parm_long)); + DEFINE(__PT_FLAGS, offsetof(struct pt_regs, flags)); DEFINE(__PT_SIZE, sizeof(struct pt_regs)); BLANK(); DEFINE(__SF_BACKCHAIN, offsetof(struct stack_frame, back_chain)); @@ -62,12 +66,14 @@ int main(void) 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_TK_MULT, offsetof(struct vdso_data, tk_mult)); + DEFINE(__VDSO_TK_SHIFT, offsetof(struct vdso_data, tk_shift)); 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_THREAD_CPUTIME_ID, CLOCK_THREAD_CPUTIME_ID); DEFINE(__CLOCK_REALTIME_RES, MONOTONIC_RES_NSEC); BLANK(); /* idle data offsets */ @@ -84,16 +90,22 @@ int main(void) 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_MON_CLASS_NR, offsetof(struct _lowcore, mon_class_num)); + DEFINE(__LC_PER_CODE, offsetof(struct _lowcore, per_code)); + DEFINE(__LC_PER_ATMID, offsetof(struct _lowcore, per_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_EXC_ACCESS_ID, offsetof(struct _lowcore, exc_access_id)); + DEFINE(__LC_PER_ACCESS_ID, offsetof(struct _lowcore, per_access_id)); + DEFINE(__LC_OP_ACCESS_ID, offsetof(struct _lowcore, op_access_id)); + DEFINE(__LC_AR_MODE_ID, offsetof(struct _lowcore, ar_mode_id)); + DEFINE(__LC_MON_CODE, offsetof(struct _lowcore, monitor_code)); 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_MCCK_EXT_DAM_CODE, offsetof(struct _lowcore, external_damage_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)); @@ -110,6 +122,7 @@ int main(void) 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_CPU_FLAGS, offsetof(struct _lowcore, cpu_flags)); 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)); @@ -131,12 +144,12 @@ int main(void) DEFINE(__LC_RESTART_FN, offsetof(struct _lowcore, restart_fn)); DEFINE(__LC_RESTART_DATA, offsetof(struct _lowcore, restart_data)); DEFINE(__LC_RESTART_SOURCE, offsetof(struct _lowcore, restart_source)); + DEFINE(__LC_KERNEL_ASCE, offsetof(struct _lowcore, kernel_asce)); 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)); @@ -150,6 +163,8 @@ int main(void) #ifdef CONFIG_32BIT DEFINE(SAVE_AREA_BASE, offsetof(struct _lowcore, extended_save_area_addr)); #else /* CONFIG_32BIT */ + DEFINE(__LC_DATA_EXC_CODE, offsetof(struct _lowcore, data_exc_code)); + DEFINE(__LC_MCCK_FAIL_STOR_ADDR, offsetof(struct _lowcore, failing_storage_address)); 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)); @@ -160,6 +175,8 @@ int main(void) DEFINE(__LC_PGM_TDB, offsetof(struct _lowcore, pgm_tdb)); DEFINE(__THREAD_trap_tdb, offsetof(struct task_struct, thread.trap_tdb)); DEFINE(__GMAP_ASCE, offsetof(struct gmap, asce)); + DEFINE(__SIE_PROG0C, offsetof(struct kvm_s390_sie_block, prog0c)); + DEFINE(__SIE_PROG20, offsetof(struct kvm_s390_sie_block, prog20)); #endif /* CONFIG_32BIT */ return 0; } diff --git a/arch/s390/kernel/bitmap.c b/arch/s390/kernel/bitmap.c deleted file mode 100644 index 102da5e2303..00000000000 --- a/arch/s390/kernel/bitmap.c +++ /dev/null @@ -1,54 +0,0 @@ -/* - * 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/cache.c b/arch/s390/kernel/cache.c index 64b24650e4f..c0b03c28d15 100644 --- a/arch/s390/kernel/cache.c +++ b/arch/s390/kernel/cache.c @@ -146,15 +146,14 @@ static void __init cache_build_info(void) ct.raw = ecag(EXTRACT_TOPOLOGY, 0, 0); for (level = 0; level < CACHE_MAX_LEVEL; level++) { switch (ct.ci[level].scope) { - case CACHE_SCOPE_NOTEXISTS: - case CACHE_SCOPE_RESERVED: - return; case CACHE_SCOPE_SHARED: private = 0; break; case CACHE_SCOPE_PRIVATE: private = 1; break; + default: + return; } if (ct.ci[level].type == CACHE_TYPE_SEPARATE) { rc = cache_add(level, private, CACHE_TYPE_DATA); @@ -173,7 +172,7 @@ error: } } -static struct cache_dir *__cpuinit cache_create_cache_dir(int cpu) +static struct cache_dir *cache_create_cache_dir(int cpu) { struct cache_dir *cache_dir; struct kobject *kobj = NULL; @@ -289,9 +288,8 @@ static struct kobj_type cache_index_type = { .default_attrs = cache_index_default_attrs, }; -static int __cpuinit cache_create_index_dir(struct cache_dir *cache_dir, - struct cache *cache, int index, - int cpu) +static int cache_create_index_dir(struct cache_dir *cache_dir, + struct cache *cache, int index, int cpu) { struct cache_index_dir *index_dir; int rc; @@ -313,7 +311,7 @@ out: return rc; } -static int __cpuinit cache_add_cpu(int cpu) +static int cache_add_cpu(int cpu) { struct cache_dir *cache_dir; struct cache *cache; @@ -335,7 +333,7 @@ static int __cpuinit cache_add_cpu(int cpu) return 0; } -static void __cpuinit cache_remove_cpu(int cpu) +static void cache_remove_cpu(int cpu) { struct cache_index_dir *index, *next; struct cache_dir *cache_dir; @@ -354,8 +352,8 @@ static void __cpuinit cache_remove_cpu(int cpu) cache_dir_cpu[cpu] = NULL; } -static int __cpuinit cache_hotplug(struct notifier_block *nfb, - unsigned long action, void *hcpu) +static int cache_hotplug(struct notifier_block *nfb, unsigned long action, + void *hcpu) { int cpu = (long)hcpu; int rc = 0; @@ -380,9 +378,12 @@ static int __init cache_init(void) if (!test_facility(34)) return 0; cache_build_info(); + + cpu_notifier_register_begin(); for_each_online_cpu(cpu) cache_add_cpu(cpu); - hotcpu_notifier(cache_hotplug, 0); + __hotcpu_notifier(cache_hotplug, 0); + cpu_notifier_register_done(); return 0; } device_initcall(cache_init); diff --git a/arch/s390/kernel/compat_exec_domain.c b/arch/s390/kernel/compat_exec_domain.c deleted file mode 100644 index 765fabdada9..00000000000 --- a/arch/s390/kernel/compat_exec_domain.c +++ /dev/null @@ -1,29 +0,0 @@ -/* - * Support for 32-bit Linux for S390 personality. - * - * Copyright IBM Corp. 2000 - * 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 index 65cca95843e..ca38139423a 100644 --- a/arch/s390/kernel/compat_linux.c +++ b/arch/s390/kernel/compat_linux.c @@ -58,10 +58,6 @@ #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 @@ -90,48 +86,51 @@ u32 psw32_user_bits = PSW32_MASK_DAT | PSW32_MASK_IO | PSW32_MASK_EXT | #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) +COMPAT_SYSCALL_DEFINE3(s390_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) +COMPAT_SYSCALL_DEFINE3(s390_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) +COMPAT_SYSCALL_DEFINE3(s390_fchown16, unsigned int, fd, u16, user, u16, group) { return sys_fchown(fd, low2highuid(user), low2highgid(group)); } -asmlinkage long sys32_setregid16(u16 rgid, u16 egid) +COMPAT_SYSCALL_DEFINE2(s390_setregid16, u16, rgid, u16, egid) { return sys_setregid(low2highgid(rgid), low2highgid(egid)); } -asmlinkage long sys32_setgid16(u16 gid) +COMPAT_SYSCALL_DEFINE1(s390_setgid16, u16, gid) { return sys_setgid((gid_t)gid); } -asmlinkage long sys32_setreuid16(u16 ruid, u16 euid) +COMPAT_SYSCALL_DEFINE2(s390_setreuid16, u16, ruid, u16, euid) { return sys_setreuid(low2highuid(ruid), low2highuid(euid)); } -asmlinkage long sys32_setuid16(u16 uid) +COMPAT_SYSCALL_DEFINE1(s390_setuid16, u16, uid) { return sys_setuid((uid_t)uid); } -asmlinkage long sys32_setresuid16(u16 ruid, u16 euid, u16 suid) +COMPAT_SYSCALL_DEFINE3(s390_setresuid16, u16, ruid, u16, euid, u16, suid) { return sys_setresuid(low2highuid(ruid), low2highuid(euid), - low2highuid(suid)); + low2highuid(suid)); } -asmlinkage long sys32_getresuid16(u16 __user *ruidp, u16 __user *euidp, u16 __user *suidp) +COMPAT_SYSCALL_DEFINE3(s390_getresuid16, u16 __user *, ruidp, + u16 __user *, euidp, u16 __user *, suidp) { const struct cred *cred = current_cred(); int retval; @@ -148,13 +147,14 @@ asmlinkage long sys32_getresuid16(u16 __user *ruidp, u16 __user *euidp, u16 __us return retval; } -asmlinkage long sys32_setresgid16(u16 rgid, u16 egid, u16 sgid) +COMPAT_SYSCALL_DEFINE3(s390_setresgid16, u16, rgid, u16, egid, u16, sgid) { return sys_setresgid(low2highgid(rgid), low2highgid(egid), - low2highgid(sgid)); + low2highgid(sgid)); } -asmlinkage long sys32_getresgid16(u16 __user *rgidp, u16 __user *egidp, u16 __user *sgidp) +COMPAT_SYSCALL_DEFINE3(s390_getresgid16, u16 __user *, rgidp, + u16 __user *, egidp, u16 __user *, sgidp) { const struct cred *cred = current_cred(); int retval; @@ -171,12 +171,12 @@ asmlinkage long sys32_getresgid16(u16 __user *rgidp, u16 __user *egidp, u16 __us return retval; } -asmlinkage long sys32_setfsuid16(u16 uid) +COMPAT_SYSCALL_DEFINE1(s390_setfsuid16, u16, uid) { return sys_setfsuid((uid_t)uid); } -asmlinkage long sys32_setfsgid16(u16 gid) +COMPAT_SYSCALL_DEFINE1(s390_setfsgid16, u16, gid) { return sys_setfsgid((gid_t)gid); } @@ -219,31 +219,32 @@ static int groups16_from_user(struct group_info *group_info, u16 __user *groupli return 0; } -asmlinkage long sys32_getgroups16(int gidsetsize, u16 __user *grouplist) +COMPAT_SYSCALL_DEFINE2(s390_getgroups16, int, gidsetsize, u16 __user *, grouplist) { + const struct cred *cred = current_cred(); int i; if (gidsetsize < 0) return -EINVAL; - get_group_info(current->cred->group_info); - i = current->cred->group_info->ngroups; + get_group_info(cred->group_info); + i = cred->group_info->ngroups; if (gidsetsize) { if (i > gidsetsize) { i = -EINVAL; goto out; } - if (groups16_to_user(grouplist, current->cred->group_info)) { + if (groups16_to_user(grouplist, cred->group_info)) { i = -EFAULT; goto out; } } out: - put_group_info(current->cred->group_info); + put_group_info(cred->group_info); return i; } -asmlinkage long sys32_setgroups16(int gidsetsize, u16 __user *grouplist) +COMPAT_SYSCALL_DEFINE2(s390_setgroups16, int, gidsetsize, u16 __user *, grouplist) { struct group_info *group_info; int retval; @@ -268,231 +269,65 @@ asmlinkage long sys32_setgroups16(int gidsetsize, u16 __user *grouplist) return retval; } -asmlinkage long sys32_getuid16(void) +COMPAT_SYSCALL_DEFINE0(s390_getuid16) { return high2lowuid(from_kuid_munged(current_user_ns(), current_uid())); } -asmlinkage long sys32_geteuid16(void) +COMPAT_SYSCALL_DEFINE0(s390_geteuid16) { return high2lowuid(from_kuid_munged(current_user_ns(), current_euid())); } -asmlinkage long sys32_getgid16(void) +COMPAT_SYSCALL_DEFINE0(s390_getgid16) { return high2lowgid(from_kgid_munged(current_user_ns(), current_gid())); } -asmlinkage long sys32_getegid16(void) +COMPAT_SYSCALL_DEFINE0(s390_getegid16) { return high2lowgid(from_kgid_munged(current_user_ns(), current_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) +COMPAT_SYSCALL_DEFINE5(s390_ipc, uint, call, int, first, compat_ulong_t, second, + compat_ulong_t, third, compat_uptr_t, 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; + return compat_sys_ipc(call, first, second, third, ptr, third); } #endif -asmlinkage long sys32_truncate64(const char __user * path, unsigned long high, unsigned long low) +COMPAT_SYSCALL_DEFINE3(s390_truncate64, const char __user *, path, u32, high, u32, 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; + return sys_truncate(path, (unsigned long)high << 32 | low); } -asmlinkage long -sys32_rt_sigqueueinfo(int pid, int sig, compat_siginfo_t __user *uinfo) +COMPAT_SYSCALL_DEFINE3(s390_ftruncate64, unsigned int, fd, u32, high, u32, low) { - 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; + return sys_ftruncate(fd, (unsigned long)high << 32 | low); } -asmlinkage long sys32_pread64(unsigned int fd, char __user *ubuf, - size_t count, u32 poshi, u32 poslo) +COMPAT_SYSCALL_DEFINE5(s390_pread64, unsigned int, fd, char __user *, ubuf, + compat_size_t, count, u32, high, u32, low) { if ((compat_ssize_t) count < 0) return -EINVAL; - return sys_pread64(fd, ubuf, count, ((loff_t)AA(poshi) << 32) | AA(poslo)); + return sys_pread64(fd, ubuf, count, (unsigned long)high << 32 | low); } -asmlinkage long sys32_pwrite64(unsigned int fd, const char __user *ubuf, - size_t count, u32 poshi, u32 poslo) +COMPAT_SYSCALL_DEFINE5(s390_pwrite64, unsigned int, fd, const char __user *, ubuf, + compat_size_t, count, u32, high, u32, low) { 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); + return sys_pwrite64(fd, ubuf, count, (unsigned long)high << 32 | low); } -asmlinkage long sys32_sendfile(int out_fd, int in_fd, compat_off_t __user *offset, size_t count) +COMPAT_SYSCALL_DEFINE4(s390_readahead, int, fd, u32, high, u32, low, s32, 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; + return sys_readahead(fd, (unsigned long)high << 32 | low, count); } struct stat64_emu31 { @@ -544,7 +379,7 @@ static int cp_stat64(struct stat64_emu31 __user *ubuf, struct kstat *stat) return copy_to_user(ubuf,&tmp,sizeof(tmp)) ? -EFAULT : 0; } -asmlinkage long sys32_stat64(const char __user * filename, struct stat64_emu31 __user * statbuf) +COMPAT_SYSCALL_DEFINE2(s390_stat64, const char __user *, filename, struct stat64_emu31 __user *, statbuf) { struct kstat stat; int ret = vfs_stat(filename, &stat); @@ -553,7 +388,7 @@ asmlinkage long sys32_stat64(const char __user * filename, struct stat64_emu31 _ return ret; } -asmlinkage long sys32_lstat64(const char __user * filename, struct stat64_emu31 __user * statbuf) +COMPAT_SYSCALL_DEFINE2(s390_lstat64, const char __user *, filename, struct stat64_emu31 __user *, statbuf) { struct kstat stat; int ret = vfs_lstat(filename, &stat); @@ -562,7 +397,7 @@ asmlinkage long sys32_lstat64(const char __user * filename, struct stat64_emu31 return ret; } -asmlinkage long sys32_fstat64(unsigned long fd, struct stat64_emu31 __user * statbuf) +COMPAT_SYSCALL_DEFINE2(s390_fstat64, unsigned int, fd, struct stat64_emu31 __user *, statbuf) { struct kstat stat; int ret = vfs_fstat(fd, &stat); @@ -571,8 +406,8 @@ asmlinkage long sys32_fstat64(unsigned long fd, struct stat64_emu31 __user * sta return ret; } -asmlinkage long sys32_fstatat64(unsigned int dfd, const char __user *filename, - struct stat64_emu31 __user* statbuf, int flag) +COMPAT_SYSCALL_DEFINE4(s390_fstatat64, unsigned int, dfd, const char __user *, filename, + struct stat64_emu31 __user *, statbuf, int, flag) { struct kstat stat; int error; @@ -598,7 +433,7 @@ struct mmap_arg_struct_emu31 { compat_ulong_t offset; }; -asmlinkage unsigned long old32_mmap(struct mmap_arg_struct_emu31 __user *arg) +COMPAT_SYSCALL_DEFINE1(s390_old_mmap, struct mmap_arg_struct_emu31 __user *, arg) { struct mmap_arg_struct_emu31 a; @@ -610,7 +445,7 @@ asmlinkage unsigned long old32_mmap(struct mmap_arg_struct_emu31 __user *arg) a.offset >> PAGE_SHIFT); } -asmlinkage long sys32_mmap2(struct mmap_arg_struct_emu31 __user *arg) +COMPAT_SYSCALL_DEFINE1(s390_mmap2, struct mmap_arg_struct_emu31 __user *, arg) { struct mmap_arg_struct_emu31 a; @@ -619,7 +454,7 @@ asmlinkage long sys32_mmap2(struct mmap_arg_struct_emu31 __user *arg) 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) +COMPAT_SYSCALL_DEFINE3(s390_read, unsigned int, fd, char __user *, buf, compat_size_t, count) { if ((compat_ssize_t) count < 0) return -EINVAL; @@ -627,7 +462,7 @@ asmlinkage long sys32_read(unsigned int fd, char __user * buf, size_t count) return sys_read(fd, buf, count); } -asmlinkage long sys32_write(unsigned int fd, const char __user * buf, size_t count) +COMPAT_SYSCALL_DEFINE3(s390_write, unsigned int, fd, const char __user *, buf, compat_size_t, count) { if ((compat_ssize_t) count < 0) return -EINVAL; @@ -641,14 +476,13 @@ asmlinkage long sys32_write(unsigned int fd, const char __user * buf, size_t cou * 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) +COMPAT_SYSCALL_DEFINE5(s390_fadvise64, int, fd, u32, high, u32, low, compat_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); + return sys_fadvise64(fd, (unsigned long)high << 32 | low, len, advise); } struct fadvise64_64_args { @@ -658,8 +492,7 @@ struct fadvise64_64_args { int advice; }; -asmlinkage long -sys32_fadvise64_64(struct fadvise64_64_args __user *args) +COMPAT_SYSCALL_DEFINE1(s390_fadvise64_64, struct fadvise64_64_args __user *, args) { struct fadvise64_64_args a; @@ -671,3 +504,17 @@ sys32_fadvise64_64(struct fadvise64_64_args __user *args) a.advice = POSIX_FADV_NOREUSE; return sys_fadvise64_64(a.fd, a.offset, a.len, a.advice); } + +COMPAT_SYSCALL_DEFINE6(s390_sync_file_range, int, fd, u32, offhigh, u32, offlow, + u32, nhigh, u32, nlow, unsigned int, flags) +{ + return sys_sync_file_range(fd, ((loff_t)offhigh << 32) + offlow, + ((u64)nhigh << 32) + nlow, flags); +} + +COMPAT_SYSCALL_DEFINE6(s390_fallocate, int, fd, int, mode, u32, offhigh, u32, offlow, + u32, lenhigh, u32, lenlow) +{ + return sys_fallocate(fd, mode, ((loff_t)offhigh << 32) + offlow, + ((u64)lenhigh << 32) + lenlow); +} diff --git a/arch/s390/kernel/compat_linux.h b/arch/s390/kernel/compat_linux.h index d4d0239970a..70d4b7c4bea 100644 --- a/arch/s390/kernel/compat_linux.h +++ b/arch/s390/kernel/compat_linux.h @@ -17,13 +17,6 @@ struct ipc_kludge_32 { __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 */ -}; - /* asm/sigcontext.h */ typedef union { @@ -34,6 +27,7 @@ typedef union typedef struct { unsigned int fpc; + unsigned int pad; freg_t32 fprs[__NUM_FPRS]; } _s390_fp_regs32; @@ -68,90 +62,59 @@ struct sigcontext32 }; /* 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; + compat_stack_t uc_stack; _sigregs32 uc_mcontext; - compat_sigset_t uc_sigmask; /* mask last for extensibility */ + compat_sigset_t uc_sigmask; + /* Allow for uc_sigmask growth. Glibc uses a 1024-bit sigset_t. */ + unsigned char __unused[128 - sizeof(compat_sigset_t)]; }; 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_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); +long compat_sys_s390_chown16(const char __user *filename, u16 user, u16 group); +long compat_sys_s390_lchown16(const char __user *filename, u16 user, u16 group); +long compat_sys_s390_fchown16(unsigned int fd, u16 user, u16 group); +long compat_sys_s390_setregid16(u16 rgid, u16 egid); +long compat_sys_s390_setgid16(u16 gid); +long compat_sys_s390_setreuid16(u16 ruid, u16 euid); +long compat_sys_s390_setuid16(u16 uid); +long compat_sys_s390_setresuid16(u16 ruid, u16 euid, u16 suid); +long compat_sys_s390_getresuid16(u16 __user *ruid, u16 __user *euid, u16 __user *suid); +long compat_sys_s390_setresgid16(u16 rgid, u16 egid, u16 sgid); +long compat_sys_s390_getresgid16(u16 __user *rgid, u16 __user *egid, u16 __user *sgid); +long compat_sys_s390_setfsuid16(u16 uid); +long compat_sys_s390_setfsgid16(u16 gid); +long compat_sys_s390_getgroups16(int gidsetsize, u16 __user *grouplist); +long compat_sys_s390_setgroups16(int gidsetsize, u16 __user *grouplist); +long compat_sys_s390_getuid16(void); +long compat_sys_s390_geteuid16(void); +long compat_sys_s390_getgid16(void); +long compat_sys_s390_getegid16(void); +long compat_sys_s390_truncate64(const char __user *path, u32 high, u32 low); +long compat_sys_s390_ftruncate64(unsigned int fd, u32 high, u32 low); +long compat_sys_s390_pread64(unsigned int fd, char __user *ubuf, compat_size_t count, u32 high, u32 low); +long compat_sys_s390_pwrite64(unsigned int fd, const char __user *ubuf, compat_size_t count, u32 high, u32 low); +long compat_sys_s390_readahead(int fd, u32 high, u32 low, s32 count); +long compat_sys_s390_stat64(const char __user *filename, struct stat64_emu31 __user *statbuf); +long compat_sys_s390_lstat64(const char __user *filename, struct stat64_emu31 __user *statbuf); +long compat_sys_s390_fstat64(unsigned int fd, struct stat64_emu31 __user *statbuf); +long compat_sys_s390_fstatat64(unsigned int dfd, const char __user *filename, struct stat64_emu31 __user *statbuf, int flag); +long compat_sys_s390_old_mmap(struct mmap_arg_struct_emu31 __user *arg); +long compat_sys_s390_mmap2(struct mmap_arg_struct_emu31 __user *arg); +long compat_sys_s390_read(unsigned int fd, char __user * buf, compat_size_t count); +long compat_sys_s390_write(unsigned int fd, const char __user * buf, compat_size_t count); +long compat_sys_s390_fadvise64(int fd, u32 high, u32 low, compat_size_t len, int advise); +long compat_sys_s390_fadvise64_64(struct fadvise64_64_args __user *args); +long compat_sys_s390_sync_file_range(int fd, u32 offhigh, u32 offlow, u32 nhigh, u32 nlow, unsigned int flags); +long compat_sys_s390_fallocate(int fd, int mode, u32 offhigh, u32 offlow, u32 lenhigh, u32 lenlow); +long compat_sys_sigreturn(void); +long compat_sys_rt_sigreturn(void); + #endif /* _ASM_S390X_S390_H */ diff --git a/arch/s390/kernel/compat_signal.c b/arch/s390/kernel/compat_signal.c index 593fcc9253f..f204d692036 100644 --- a/arch/s390/kernel/compat_signal.c +++ b/arch/s390/kernel/compat_signal.c @@ -49,13 +49,10 @@ typedef struct __u32 gprs_high[NUM_GPRS]; } rt_sigframe32; -int copy_siginfo_to_user32(compat_siginfo_t __user *to, siginfo_t *from) +int copy_siginfo_to_user32(compat_siginfo_t __user *to, const 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 @@ -102,7 +99,7 @@ int copy_siginfo_to_user32(compat_siginfo_t __user *to, siginfo_t *from) break; } } - return err; + return err ? -EFAULT : 0; } int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from) @@ -110,9 +107,6 @@ 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); @@ -154,179 +148,72 @@ int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from) 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; + return err ? -EFAULT : 0; } static int save_sigregs32(struct pt_regs *regs, _sigregs32 __user *sregs) { - _s390_regs_common32 regs32; - int err, i; + _sigregs32 user_sregs; + int i; - regs32.psw.mask = psw32_user_bits | - ((__u32)(regs->psw.mask >> 32) & PSW32_MASK_USER); - regs32.psw.addr = (__u32) regs->psw.addr | + user_sregs.regs.psw.mask = (__u32)(regs->psw.mask >> 32); + user_sregs.regs.psw.mask &= PSW32_MASK_USER | PSW32_MASK_RI; + user_sregs.regs.psw.mask |= PSW32_USER_BITS; + user_sregs.regs.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]; + user_sregs.regs.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)); + memcpy(&user_sregs.regs.acrs, current->thread.acrs, + sizeof(user_sregs.regs.acrs)); + save_fp_ctl(¤t->thread.fp_regs.fpc); + save_fp_regs(current->thread.fp_regs.fprs); + memcpy(&user_sregs.fpregs, ¤t->thread.fp_regs, + sizeof(user_sregs.fpregs)); + if (__copy_to_user(sregs, &user_sregs, sizeof(_sigregs32))) + return -EFAULT; + return 0; } static int restore_sigregs32(struct pt_regs *regs,_sigregs32 __user *sregs) { - _s390_regs_common32 regs32; - int err, i; + _sigregs32 user_sregs; + int 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); + if (__copy_from_user(&user_sregs, &sregs->regs, sizeof(user_sregs))) + return -EFAULT; + + if (!is_ri_task(current) && (user_sregs.regs.psw.mask & PSW32_MASK_RI)) + return -EINVAL; + + /* Loading the floating-point-control word can fail. Do that first. */ + if (restore_fp_ctl(&user_sregs.fpregs.fpc)) + return -EINVAL; + + /* Use regs->psw.mask instead of PSW_USER_BITS to preserve PER bit. */ + regs->psw.mask = (regs->psw.mask & ~(PSW_MASK_USER | PSW_MASK_RI)) | + (__u64)(user_sregs.regs.psw.mask & PSW32_MASK_USER) << 32 | + (__u64)(user_sregs.regs.psw.mask & PSW32_MASK_RI) << 32 | + (__u64)(user_sregs.regs.psw.addr & PSW32_ADDR_AMODE); /* Check for invalid user address space control. */ - if ((regs->psw.mask & PSW_MASK_ASC) >= (psw_kernel_bits & PSW_MASK_ASC)) - regs->psw.mask = (psw_user_bits & PSW_MASK_ASC) | + if ((regs->psw.mask & PSW_MASK_ASC) == PSW_ASC_HOME) + regs->psw.mask = PSW_ASC_PRIMARY | (regs->psw.mask & ~PSW_MASK_ASC); - regs->psw.addr = (__u64)(regs32.psw.addr & PSW32_ADDR_INSN); + regs->psw.addr = (__u64)(user_sregs.regs.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)); + regs->gprs[i] = (__u64) user_sregs.regs.gprs[i]; + memcpy(¤t->thread.acrs, &user_sregs.regs.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; + memcpy(¤t->thread.fp_regs, &user_sregs.fpregs, + sizeof(current->thread.fp_regs)); - restore_fp_regs(¤t->thread.fp_regs); - clear_thread_flag(TIF_SYSCALL); /* No longer in a system call */ + restore_fp_regs(current->thread.fp_regs.fprs); + clear_pt_regs_flag(regs, PIF_SYSCALL); /* No longer in a system call */ return 0; } @@ -337,31 +224,29 @@ static int save_sigregs_gprs_high(struct pt_regs *regs, __u32 __user *uregs) for (i = 0; i < NUM_GPRS; i++) gprs_high[i] = regs->gprs[i] >> 32; - - return __copy_to_user(uregs, &gprs_high, sizeof(gprs_high)); + if (__copy_to_user(uregs, &gprs_high, sizeof(gprs_high))) + return -EFAULT; + return 0; } static int restore_sigregs_gprs_high(struct pt_regs *regs, __u32 __user *uregs) { __u32 gprs_high[NUM_GPRS]; - int err, i; + int i; - err = __copy_from_user(&gprs_high, uregs, sizeof(gprs_high)); - if (err) - return err; + if (__copy_from_user(&gprs_high, uregs, sizeof(gprs_high))) + return -EFAULT; for (i = 0; i < NUM_GPRS; i++) *(__u32 *)®s->gprs[i] = gprs_high[i]; return 0; } -asmlinkage long sys32_sigreturn(void) +COMPAT_SYSCALL_DEFINE0(sigreturn) { 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; set_current_blocked(&set); @@ -375,18 +260,12 @@ badframe: return 0; } -asmlinkage long sys32_rt_sigreturn(void) +COMPAT_SYSCALL_DEFINE0(rt_sigreturn) { 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; set_current_blocked(&set); @@ -394,15 +273,8 @@ asmlinkage long sys32_rt_sigreturn(void) 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) + if (compat_restore_altstack(&frame->uc.uc_stack)) 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); @@ -452,8 +324,6 @@ 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; @@ -471,9 +341,9 @@ static int setup_frame32(int sig, struct k_sigaction *ka, /* 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; + regs->gprs[14] = (__u64 __force) ka->sa.sa_restorer | PSW32_ADDR_AMODE; } else { - regs->gprs[14] = (__u64) frame->retcode | PSW32_ADDR_AMODE; + regs->gprs[14] = (__u64 __force) frame->retcode | PSW32_ADDR_AMODE; if (__put_user(S390_SYSCALL_OPCODE | __NR_sigreturn, (u16 __force __user *)(frame->retcode))) goto give_sigsegv; @@ -487,7 +357,7 @@ static int setup_frame32(int sig, struct k_sigaction *ka, regs->gprs[15] = (__force __u64) frame; /* Force 31 bit amode and default user address space control. */ regs->psw.mask = PSW_MASK_BA | - (psw_user_bits & PSW_MASK_ASC) | + (PSW_USER_BITS & PSW_MASK_ASC) | (regs->psw.mask & ~PSW_MASK_ASC); regs->psw.addr = (__force __u64) ka->sa.sa_handler; @@ -501,6 +371,7 @@ static int setup_frame32(int sig, struct k_sigaction *ka, /* 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. */ @@ -518,8 +389,6 @@ static int setup_rt_frame32(int sig, struct k_sigaction *ka, siginfo_t *info, { 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; @@ -530,10 +399,7 @@ static int setup_rt_frame32(int sig, struct k_sigaction *ka, siginfo_t *info, /* 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 |= __compat_save_altstack(&frame->uc.uc_stack, regs->gprs[15]); 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)); @@ -543,11 +409,12 @@ static int setup_rt_frame32(int sig, struct k_sigaction *ka, siginfo_t *info, /* 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; + regs->gprs[14] = (__u64 __force) 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)); + regs->gprs[14] = (__u64 __force) frame->retcode | PSW32_ADDR_AMODE; + if (__put_user(S390_SYSCALL_OPCODE | __NR_rt_sigreturn, + (u16 __force __user *)(frame->retcode))) + goto give_sigsegv; } /* Set up backchain. */ @@ -558,13 +425,14 @@ static int setup_rt_frame32(int sig, struct k_sigaction *ka, siginfo_t *info, regs->gprs[15] = (__force __u64) frame; /* Force 31 bit amode and default user address space control. */ regs->psw.mask = PSW_MASK_BA | - (psw_user_bits & PSW_MASK_ASC) | + (PSW_USER_BITS & PSW_MASK_ASC) | (regs->psw.mask & ~PSW_MASK_ASC); - regs->psw.addr = (__u64) ka->sa.sa_handler; + regs->psw.addr = (__u64 __force) ka->sa.sa_handler; regs->gprs[2] = map_signal(sig); regs->gprs[3] = (__force __u64) &frame->info; regs->gprs[4] = (__force __u64) &frame->uc; + regs->gprs[5] = task_thread_info(current)->last_break; return 0; give_sigsegv: diff --git a/arch/s390/kernel/compat_wrapper.S b/arch/s390/kernel/compat_wrapper.S deleted file mode 100644 index 9b9a805656b..00000000000 --- a/arch/s390/kernel/compat_wrapper.S +++ /dev/null @@ -1,1667 +0,0 @@ -/* -* wrapper for 31 bit compatible system calls. -* -* Copyright 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 compat_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 compat_sys_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 compat_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 compat_sys_process_vm_writev - -ENTRY(sys_s390_runtime_instr_wrapper) - lgfr %r2,%r2 # int - lgfr %r3,%r3 # int - jg sys_s390_runtime_instr - -ENTRY(sys_kcmp_wrapper) - lgfr %r2,%r2 # pid_t - lgfr %r3,%r3 # pid_t - lgfr %r4,%r4 # int - llgfr %r5,%r5 # unsigned long - llgfr %r6,%r6 # unsigned long - jg sys_kcmp - -ENTRY(sys_finit_module_wrapper) - lgfr %r2,%r2 # int - llgtr %r3,%r3 # const char __user * - lgfr %r4,%r4 # int - jg sys_finit_module diff --git a/arch/s390/kernel/compat_wrapper.c b/arch/s390/kernel/compat_wrapper.c new file mode 100644 index 00000000000..45cdb37aa6f --- /dev/null +++ b/arch/s390/kernel/compat_wrapper.c @@ -0,0 +1,216 @@ +/* + * Compat system call wrappers. + * + * Copyright IBM Corp. 2014 + */ + +#include <linux/syscalls.h> +#include <linux/compat.h> +#include "entry.h" + +#define COMPAT_SYSCALL_WRAP1(name, ...) \ + COMPAT_SYSCALL_WRAPx(1, _##name, __VA_ARGS__) +#define COMPAT_SYSCALL_WRAP2(name, ...) \ + COMPAT_SYSCALL_WRAPx(2, _##name, __VA_ARGS__) +#define COMPAT_SYSCALL_WRAP3(name, ...) \ + COMPAT_SYSCALL_WRAPx(3, _##name, __VA_ARGS__) +#define COMPAT_SYSCALL_WRAP4(name, ...) \ + COMPAT_SYSCALL_WRAPx(4, _##name, __VA_ARGS__) +#define COMPAT_SYSCALL_WRAP5(name, ...) \ + COMPAT_SYSCALL_WRAPx(5, _##name, __VA_ARGS__) +#define COMPAT_SYSCALL_WRAP6(name, ...) \ + COMPAT_SYSCALL_WRAPx(6, _##name, __VA_ARGS__) + +#define __SC_COMPAT_TYPE(t, a) \ + __typeof(__builtin_choose_expr(sizeof(t) > 4, 0L, (t)0)) a + +#define __SC_COMPAT_CAST(t, a) \ +({ \ + long __ReS = a; \ + \ + BUILD_BUG_ON((sizeof(t) > 4) && !__TYPE_IS_L(t) && \ + !__TYPE_IS_UL(t) && !__TYPE_IS_PTR(t)); \ + if (__TYPE_IS_L(t)) \ + __ReS = (s32)a; \ + if (__TYPE_IS_UL(t)) \ + __ReS = (u32)a; \ + if (__TYPE_IS_PTR(t)) \ + __ReS = a & 0x7fffffff; \ + (t)__ReS; \ +}) + +/* + * The COMPAT_SYSCALL_WRAP macro generates system call wrappers to be used by + * compat tasks. These wrappers will only be used for system calls where only + * the system call arguments need sign or zero extension or zeroing of the upper + * 33 bits of pointers. + * Note: since the wrapper function will afterwards call a system call which + * again performs zero and sign extension for all system call arguments with + * a size of less than eight bytes, these compat wrappers only touch those + * system call arguments with a size of eight bytes ((unsigned) long and + * pointers). Zero and sign extension for e.g. int parameters will be done by + * the regular system call wrappers. + */ +#define COMPAT_SYSCALL_WRAPx(x, name, ...) \ + asmlinkage long sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)); \ + asmlinkage long compat_sys##name(__MAP(x,__SC_COMPAT_TYPE,__VA_ARGS__));\ + asmlinkage long compat_sys##name(__MAP(x,__SC_COMPAT_TYPE,__VA_ARGS__)) \ + { \ + return sys##name(__MAP(x,__SC_COMPAT_CAST,__VA_ARGS__)); \ + } + +COMPAT_SYSCALL_WRAP1(exit, int, error_code); +COMPAT_SYSCALL_WRAP1(close, unsigned int, fd); +COMPAT_SYSCALL_WRAP2(creat, const char __user *, pathname, umode_t, mode); +COMPAT_SYSCALL_WRAP2(link, const char __user *, oldname, const char __user *, newname); +COMPAT_SYSCALL_WRAP1(unlink, const char __user *, pathname); +COMPAT_SYSCALL_WRAP1(chdir, const char __user *, filename); +COMPAT_SYSCALL_WRAP3(mknod, const char __user *, filename, umode_t, mode, unsigned, dev); +COMPAT_SYSCALL_WRAP2(chmod, const char __user *, filename, umode_t, mode); +COMPAT_SYSCALL_WRAP1(oldumount, char __user *, name); +COMPAT_SYSCALL_WRAP1(alarm, unsigned int, seconds); +COMPAT_SYSCALL_WRAP2(access, const char __user *, filename, int, mode); +COMPAT_SYSCALL_WRAP1(nice, int, increment); +COMPAT_SYSCALL_WRAP2(kill, int, pid, int, sig); +COMPAT_SYSCALL_WRAP2(rename, const char __user *, oldname, const char __user *, newname); +COMPAT_SYSCALL_WRAP2(mkdir, const char __user *, pathname, umode_t, mode); +COMPAT_SYSCALL_WRAP1(rmdir, const char __user *, pathname); +COMPAT_SYSCALL_WRAP1(dup, unsigned int, fildes); +COMPAT_SYSCALL_WRAP1(pipe, int __user *, fildes); +COMPAT_SYSCALL_WRAP1(brk, unsigned long, brk); +COMPAT_SYSCALL_WRAP2(signal, int, sig, __sighandler_t, handler); +COMPAT_SYSCALL_WRAP1(acct, const char __user *, name); +COMPAT_SYSCALL_WRAP2(umount, char __user *, name, int, flags); +COMPAT_SYSCALL_WRAP2(setpgid, pid_t, pid, pid_t, pgid); +COMPAT_SYSCALL_WRAP1(umask, int, mask); +COMPAT_SYSCALL_WRAP1(chroot, const char __user *, filename); +COMPAT_SYSCALL_WRAP2(dup2, unsigned int, oldfd, unsigned int, newfd); +COMPAT_SYSCALL_WRAP3(sigsuspend, int, unused1, int, unused2, old_sigset_t, mask); +COMPAT_SYSCALL_WRAP2(sethostname, char __user *, name, int, len); +COMPAT_SYSCALL_WRAP2(symlink, const char __user *, old, const char __user *, new); +COMPAT_SYSCALL_WRAP3(readlink, const char __user *, path, char __user *, buf, int, bufsiz); +COMPAT_SYSCALL_WRAP1(uselib, const char __user *, library); +COMPAT_SYSCALL_WRAP2(swapon, const char __user *, specialfile, int, swap_flags); +COMPAT_SYSCALL_WRAP4(reboot, int, magic1, int, magic2, unsigned int, cmd, void __user *, arg); +COMPAT_SYSCALL_WRAP2(munmap, unsigned long, addr, size_t, len); +COMPAT_SYSCALL_WRAP2(fchmod, unsigned int, fd, umode_t, mode); +COMPAT_SYSCALL_WRAP2(getpriority, int, which, int, who); +COMPAT_SYSCALL_WRAP3(setpriority, int, which, int, who, int, niceval); +COMPAT_SYSCALL_WRAP3(syslog, int, type, char __user *, buf, int, len); +COMPAT_SYSCALL_WRAP1(swapoff, const char __user *, specialfile); +COMPAT_SYSCALL_WRAP1(fsync, unsigned int, fd); +COMPAT_SYSCALL_WRAP2(setdomainname, char __user *, name, int, len); +COMPAT_SYSCALL_WRAP1(newuname, struct new_utsname __user *, name); +COMPAT_SYSCALL_WRAP3(mprotect, unsigned long, start, size_t, len, unsigned long, prot); +COMPAT_SYSCALL_WRAP3(init_module, void __user *, umod, unsigned long, len, const char __user *, uargs); +COMPAT_SYSCALL_WRAP2(delete_module, const char __user *, name_user, unsigned int, flags); +COMPAT_SYSCALL_WRAP4(quotactl, unsigned int, cmd, const char __user *, special, qid_t, id, void __user *, addr); +COMPAT_SYSCALL_WRAP1(getpgid, pid_t, pid); +COMPAT_SYSCALL_WRAP1(fchdir, unsigned int, fd); +COMPAT_SYSCALL_WRAP2(bdflush, int, func, long, data); +COMPAT_SYSCALL_WRAP3(sysfs, int, option, unsigned long, arg1, unsigned long, arg2); +COMPAT_SYSCALL_WRAP1(s390_personality, unsigned int, personality); +COMPAT_SYSCALL_WRAP5(llseek, unsigned int, fd, unsigned long, high, unsigned long, low, loff_t __user *, result, unsigned int, whence); +COMPAT_SYSCALL_WRAP2(flock, unsigned int, fd, unsigned int, cmd); +COMPAT_SYSCALL_WRAP3(msync, unsigned long, start, size_t, len, int, flags); +COMPAT_SYSCALL_WRAP1(getsid, pid_t, pid); +COMPAT_SYSCALL_WRAP1(fdatasync, unsigned int, fd); +COMPAT_SYSCALL_WRAP2(mlock, unsigned long, start, size_t, len); +COMPAT_SYSCALL_WRAP2(munlock, unsigned long, start, size_t, len); +COMPAT_SYSCALL_WRAP1(mlockall, int, flags); +COMPAT_SYSCALL_WRAP2(sched_setparam, pid_t, pid, struct sched_param __user *, param); +COMPAT_SYSCALL_WRAP2(sched_getparam, pid_t, pid, struct sched_param __user *, param); +COMPAT_SYSCALL_WRAP3(sched_setscheduler, pid_t, pid, int, policy, struct sched_param __user *, param); +COMPAT_SYSCALL_WRAP1(sched_getscheduler, pid_t, pid); +COMPAT_SYSCALL_WRAP1(sched_get_priority_max, int, policy); +COMPAT_SYSCALL_WRAP1(sched_get_priority_min, int, policy); +COMPAT_SYSCALL_WRAP5(mremap, unsigned long, addr, unsigned long, old_len, unsigned long, new_len, unsigned long, flags, unsigned long, new_addr); +COMPAT_SYSCALL_WRAP3(poll, struct pollfd __user *, ufds, unsigned int, nfds, int, timeout); +COMPAT_SYSCALL_WRAP5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, unsigned long, arg4, unsigned long, arg5); +COMPAT_SYSCALL_WRAP2(getcwd, char __user *, buf, unsigned long, size); +COMPAT_SYSCALL_WRAP2(capget, cap_user_header_t, header, cap_user_data_t, dataptr); +COMPAT_SYSCALL_WRAP2(capset, cap_user_header_t, header, const cap_user_data_t, data); +COMPAT_SYSCALL_WRAP3(lchown, const char __user *, filename, uid_t, user, gid_t, group); +COMPAT_SYSCALL_WRAP2(setreuid, uid_t, ruid, uid_t, euid); +COMPAT_SYSCALL_WRAP2(setregid, gid_t, rgid, gid_t, egid); +COMPAT_SYSCALL_WRAP2(getgroups, int, gidsetsize, gid_t __user *, grouplist); +COMPAT_SYSCALL_WRAP2(setgroups, int, gidsetsize, gid_t __user *, grouplist); +COMPAT_SYSCALL_WRAP3(fchown, unsigned int, fd, uid_t, user, gid_t, group); +COMPAT_SYSCALL_WRAP3(setresuid, uid_t, ruid, uid_t, euid, uid_t, suid); +COMPAT_SYSCALL_WRAP3(getresuid, uid_t __user *, ruid, uid_t __user *, euid, uid_t __user *, suid); +COMPAT_SYSCALL_WRAP3(setresgid, gid_t, rgid, gid_t, egid, gid_t, sgid); +COMPAT_SYSCALL_WRAP3(getresgid, gid_t __user *, rgid, gid_t __user *, egid, gid_t __user *, sgid); +COMPAT_SYSCALL_WRAP3(chown, const char __user *, filename, uid_t, user, gid_t, group); +COMPAT_SYSCALL_WRAP1(setuid, uid_t, uid); +COMPAT_SYSCALL_WRAP1(setgid, gid_t, gid); +COMPAT_SYSCALL_WRAP1(setfsuid, uid_t, uid); +COMPAT_SYSCALL_WRAP1(setfsgid, gid_t, gid); +COMPAT_SYSCALL_WRAP2(pivot_root, const char __user *, new_root, const char __user *, put_old); +COMPAT_SYSCALL_WRAP3(mincore, unsigned long, start, size_t, len, unsigned char __user *, vec); +COMPAT_SYSCALL_WRAP3(madvise, unsigned long, start, size_t, len, int, behavior); +COMPAT_SYSCALL_WRAP5(setxattr, const char __user *, path, const char __user *, name, const void __user *, value, size_t, size, int, flags); +COMPAT_SYSCALL_WRAP5(lsetxattr, const char __user *, path, const char __user *, name, const void __user *, value, size_t, size, int, flags); +COMPAT_SYSCALL_WRAP5(fsetxattr, int, fd, const char __user *, name, const void __user *, value, size_t, size, int, flags); +COMPAT_SYSCALL_WRAP3(getdents64, unsigned int, fd, struct linux_dirent64 __user *, dirent, unsigned int, count); +COMPAT_SYSCALL_WRAP4(getxattr, const char __user *, path, const char __user *, name, void __user *, value, size_t, size); +COMPAT_SYSCALL_WRAP4(lgetxattr, const char __user *, path, const char __user *, name, void __user *, value, size_t, size); +COMPAT_SYSCALL_WRAP4(fgetxattr, int, fd, const char __user *, name, void __user *, value, size_t, size); +COMPAT_SYSCALL_WRAP3(listxattr, const char __user *, path, char __user *, list, size_t, size); +COMPAT_SYSCALL_WRAP3(llistxattr, const char __user *, path, char __user *, list, size_t, size); +COMPAT_SYSCALL_WRAP3(flistxattr, int, fd, char __user *, list, size_t, size); +COMPAT_SYSCALL_WRAP2(removexattr, const char __user *, path, const char __user *, name); +COMPAT_SYSCALL_WRAP2(lremovexattr, const char __user *, path, const char __user *, name); +COMPAT_SYSCALL_WRAP2(fremovexattr, int, fd, const char __user *, name); +COMPAT_SYSCALL_WRAP1(exit_group, int, error_code); +COMPAT_SYSCALL_WRAP1(set_tid_address, int __user *, tidptr); +COMPAT_SYSCALL_WRAP1(epoll_create, int, size); +COMPAT_SYSCALL_WRAP4(epoll_ctl, int, epfd, int, op, int, fd, struct epoll_event __user *, event); +COMPAT_SYSCALL_WRAP4(epoll_wait, int, epfd, struct epoll_event __user *, events, int, maxevents, int, timeout); +COMPAT_SYSCALL_WRAP1(timer_getoverrun, timer_t, timer_id); +COMPAT_SYSCALL_WRAP1(timer_delete, compat_timer_t, compat_timer_id); +COMPAT_SYSCALL_WRAP1(io_destroy, aio_context_t, ctx); +COMPAT_SYSCALL_WRAP3(io_cancel, aio_context_t, ctx_id, struct iocb __user *, iocb, struct io_event __user *, result); +COMPAT_SYSCALL_WRAP1(mq_unlink, const char __user *, name); +COMPAT_SYSCALL_WRAP5(add_key, const char __user *, tp, const char __user *, dsc, const void __user *, pld, size_t, len, key_serial_t, id); +COMPAT_SYSCALL_WRAP4(request_key, const char __user *, tp, const char __user *, dsc, const char __user *, info, key_serial_t, id); +COMPAT_SYSCALL_WRAP5(remap_file_pages, unsigned long, start, unsigned long, size, unsigned long, prot, unsigned long, pgoff, unsigned long, flags); +COMPAT_SYSCALL_WRAP3(ioprio_set, int, which, int, who, int, ioprio); +COMPAT_SYSCALL_WRAP2(ioprio_get, int, which, int, who); +COMPAT_SYSCALL_WRAP3(inotify_add_watch, int, fd, const char __user *, path, u32, mask); +COMPAT_SYSCALL_WRAP2(inotify_rm_watch, int, fd, __s32, wd); +COMPAT_SYSCALL_WRAP3(mkdirat, int, dfd, const char __user *, pathname, umode_t, mode); +COMPAT_SYSCALL_WRAP4(mknodat, int, dfd, const char __user *, filename, umode_t, mode, unsigned, dev); +COMPAT_SYSCALL_WRAP5(fchownat, int, dfd, const char __user *, filename, uid_t, user, gid_t, group, int, flag); +COMPAT_SYSCALL_WRAP3(unlinkat, int, dfd, const char __user *, pathname, int, flag); +COMPAT_SYSCALL_WRAP4(renameat, int, olddfd, const char __user *, oldname, int, newdfd, const char __user *, newname); +COMPAT_SYSCALL_WRAP5(linkat, int, olddfd, const char __user *, oldname, int, newdfd, const char __user *, newname, int, flags); +COMPAT_SYSCALL_WRAP3(symlinkat, const char __user *, oldname, int, newdfd, const char __user *, newname); +COMPAT_SYSCALL_WRAP4(readlinkat, int, dfd, const char __user *, path, char __user *, buf, int, bufsiz); +COMPAT_SYSCALL_WRAP3(fchmodat, int, dfd, const char __user *, filename, umode_t, mode); +COMPAT_SYSCALL_WRAP3(faccessat, int, dfd, const char __user *, filename, int, mode); +COMPAT_SYSCALL_WRAP1(unshare, unsigned long, unshare_flags); +COMPAT_SYSCALL_WRAP6(splice, int, fd_in, loff_t __user *, off_in, int, fd_out, loff_t __user *, off_out, size_t, len, unsigned int, flags); +COMPAT_SYSCALL_WRAP4(tee, int, fdin, int, fdout, size_t, len, unsigned int, flags); +COMPAT_SYSCALL_WRAP3(getcpu, unsigned __user *, cpu, unsigned __user *, node, struct getcpu_cache __user *, cache); +COMPAT_SYSCALL_WRAP1(eventfd, unsigned int, count); +COMPAT_SYSCALL_WRAP2(timerfd_create, int, clockid, int, flags); +COMPAT_SYSCALL_WRAP2(eventfd2, unsigned int, count, int, flags); +COMPAT_SYSCALL_WRAP1(inotify_init1, int, flags); +COMPAT_SYSCALL_WRAP2(pipe2, int __user *, fildes, int, flags); +COMPAT_SYSCALL_WRAP3(dup3, unsigned int, oldfd, unsigned int, newfd, int, flags); +COMPAT_SYSCALL_WRAP1(epoll_create1, int, flags); +COMPAT_SYSCALL_WRAP2(tkill, int, pid, int, sig); +COMPAT_SYSCALL_WRAP3(tgkill, int, tgid, int, pid, int, sig); +COMPAT_SYSCALL_WRAP5(perf_event_open, struct perf_event_attr __user *, attr_uptr, pid_t, pid, int, cpu, int, group_fd, unsigned long, flags); +COMPAT_SYSCALL_WRAP5(clone, unsigned long, newsp, unsigned long, clone_flags, int __user *, parent_tidptr, int __user *, child_tidptr, int, tls_val); +COMPAT_SYSCALL_WRAP2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags); +COMPAT_SYSCALL_WRAP4(prlimit64, pid_t, pid, unsigned int, resource, const struct rlimit64 __user *, new_rlim, struct rlimit64 __user *, old_rlim); +COMPAT_SYSCALL_WRAP5(name_to_handle_at, int, dfd, const char __user *, name, struct file_handle __user *, handle, int __user *, mnt_id, int, flag); +COMPAT_SYSCALL_WRAP1(syncfs, int, fd); +COMPAT_SYSCALL_WRAP2(setns, int, fd, int, nstype); +COMPAT_SYSCALL_WRAP2(s390_runtime_instr, int, command, int, signum); +COMPAT_SYSCALL_WRAP5(kcmp, pid_t, pid1, pid_t, pid2, int, type, unsigned long, idx1, unsigned long, idx2); +COMPAT_SYSCALL_WRAP3(finit_module, int, fd, const char __user *, uargs, int, flags); +COMPAT_SYSCALL_WRAP3(sched_setattr, pid_t, pid, struct sched_attr __user *, attr, unsigned int, flags); +COMPAT_SYSCALL_WRAP4(sched_getattr, pid_t, pid, struct sched_attr __user *, attr, unsigned int, size, unsigned int, flags); +COMPAT_SYSCALL_WRAP5(renameat2, int, olddfd, const char __user *, oldname, int, newdfd, const char __user *, newname, unsigned int, flags); diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c index fb8d8781a01..a3b9150e680 100644 --- a/arch/s390/kernel/crash_dump.c +++ b/arch/s390/kernel/crash_dump.c @@ -13,41 +13,233 @@ #include <linux/slab.h> #include <linux/bootmem.h> #include <linux/elf.h> +#include <linux/memblock.h> #include <asm/os_info.h> #include <asm/elf.h> #include <asm/ipl.h> +#include <asm/sclp.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)))) +static struct memblock_region oldmem_region; + +static struct memblock_type oldmem_type = { + .cnt = 1, + .max = 1, + .total_size = 0, + .regions = &oldmem_region, +}; + +#define for_each_dump_mem_range(i, nid, p_start, p_end, p_nid) \ + for (i = 0, __next_mem_range(&i, nid, &memblock.physmem, \ + &oldmem_type, p_start, \ + p_end, p_nid); \ + i != (u64)ULLONG_MAX; \ + __next_mem_range(&i, nid, &memblock.physmem, \ + &oldmem_type, \ + p_start, p_end, p_nid)) + +struct dump_save_areas dump_save_areas; + /* - * Copy one page from "oldmem" + * Allocate and add a save area for a CPU + */ +struct save_area *dump_save_area_create(int cpu) +{ + struct save_area **save_areas, *save_area; + + save_area = kmalloc(sizeof(*save_area), GFP_KERNEL); + if (!save_area) + return NULL; + if (cpu + 1 > dump_save_areas.count) { + dump_save_areas.count = cpu + 1; + save_areas = krealloc(dump_save_areas.areas, + dump_save_areas.count * sizeof(void *), + GFP_KERNEL | __GFP_ZERO); + if (!save_areas) { + kfree(save_area); + return NULL; + } + dump_save_areas.areas = save_areas; + } + dump_save_areas.areas[cpu] = save_area; + return save_area; +} + +/* + * Return physical address for virtual address + */ +static inline void *load_real_addr(void *addr) +{ + unsigned long real_addr; + + asm volatile( + " lra %0,0(%1)\n" + " jz 0f\n" + " la %0,0\n" + "0:" + : "=a" (real_addr) : "a" (addr) : "cc"); + return (void *)real_addr; +} + +/* + * Copy real to virtual or real memory + */ +static int copy_from_realmem(void *dest, void *src, size_t count) +{ + unsigned long size; + + if (!count) + return 0; + if (!is_vmalloc_or_module_addr(dest)) + return memcpy_real(dest, src, count); + do { + size = min(count, PAGE_SIZE - (__pa(dest) & ~PAGE_MASK)); + if (memcpy_real(load_real_addr(dest), src, size)) + return -EFAULT; + count -= size; + dest += size; + src += size; + } while (count); + return 0; +} + +/* + * Pointer to ELF header in new kernel + */ +static void *elfcorehdr_newmem; + +/* + * Copy one page from zfcpdump "oldmem" + * + * For pages below HSA size memory from the HSA is copied. Otherwise + * real memory copy is used. + */ +static ssize_t copy_oldmem_page_zfcpdump(char *buf, size_t csize, + unsigned long src, int userbuf) +{ + int rc; + + if (src < sclp_get_hsa_size()) { + rc = memcpy_hsa(buf, src, csize, userbuf); + } else { + if (userbuf) + rc = copy_to_user_real((void __force __user *) buf, + (void *) src, csize); + else + rc = memcpy_real(buf, (void *) src, csize); + } + return rc ? rc : csize; +} + +/* + * Copy one page from kdump "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; +static ssize_t copy_oldmem_page_kdump(char *buf, size_t csize, + unsigned long src, int userbuf) - if (!csize) - return 0; +{ + int rc; - 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); + rc = copy_to_user_real((void __force __user *) buf, + (void *) src, csize); + else + rc = copy_from_realmem(buf, (void *) src, csize); + return (rc == 0) ? rc : csize; +} + +/* + * Copy one page from "oldmem" + */ +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 (OLDMEM_BASE) + return copy_oldmem_page_kdump(buf, csize, src, userbuf); + else + return copy_oldmem_page_zfcpdump(buf, csize, src, userbuf); +} + +/* + * Remap "oldmem" for kdump + * + * For the kdump reserved memory this functions performs a swap operation: + * [0 - OLDMEM_SIZE] is mapped to [OLDMEM_BASE - OLDMEM_BASE + OLDMEM_SIZE] + */ +static int remap_oldmem_pfn_range_kdump(struct vm_area_struct *vma, + unsigned long from, unsigned long pfn, + unsigned long size, pgprot_t prot) +{ + unsigned long size_old; + int rc; + + if (pfn < OLDMEM_SIZE >> PAGE_SHIFT) { + size_old = min(size, OLDMEM_SIZE - (pfn << PAGE_SHIFT)); + rc = remap_pfn_range(vma, from, + pfn + (OLDMEM_BASE >> PAGE_SHIFT), + size_old, prot); + if (rc || size == size_old) + return rc; + size -= size_old; + from += size_old; + pfn += size_old >> PAGE_SHIFT; + } + return remap_pfn_range(vma, from, pfn, size, prot); +} + +/* + * Remap "oldmem" for zfcpdump + * + * We only map available memory above HSA size. Memory below HSA size + * is read on demand using the copy_oldmem_page() function. + */ +static int remap_oldmem_pfn_range_zfcpdump(struct vm_area_struct *vma, + unsigned long from, + unsigned long pfn, + unsigned long size, pgprot_t prot) +{ + unsigned long hsa_end = sclp_get_hsa_size(); + unsigned long size_hsa; + + if (pfn < hsa_end >> PAGE_SHIFT) { + size_hsa = min(size, hsa_end - (pfn << PAGE_SHIFT)); + if (size == size_hsa) + return 0; + size -= size_hsa; + from += size_hsa; + pfn += size_hsa >> PAGE_SHIFT; + } + return remap_pfn_range(vma, from, pfn, size, prot); +} + +/* + * Remap "oldmem" for kdump or zfcpdump + */ +int remap_oldmem_pfn_range(struct vm_area_struct *vma, unsigned long from, + unsigned long pfn, unsigned long size, pgprot_t prot) +{ + if (OLDMEM_BASE) + return remap_oldmem_pfn_range_kdump(vma, from, pfn, size, prot); else - memcpy_real(buf, (void *) src, csize); - return csize; + return remap_oldmem_pfn_range_zfcpdump(vma, from, pfn, size, + prot); } /* @@ -58,13 +250,23 @@ 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; + if (OLDMEM_BASE) { + if ((unsigned long) src < OLDMEM_SIZE) { + copied = min(count, OLDMEM_SIZE - (unsigned long) src); + rc = copy_from_realmem(dest, src + OLDMEM_BASE, copied); + if (rc) + return rc; + } + } else { + unsigned long hsa_end = sclp_get_hsa_size(); + if ((unsigned long) src < hsa_end) { + copied = min(count, hsa_end - (unsigned long) src); + rc = memcpy_hsa(dest, (unsigned long) src, copied, 0); + if (rc) + return rc; + } } - return memcpy_real(dest + copied, src + copied, count - copied); + return copy_from_realmem(dest + copied, src + copied, count - copied); } /* @@ -81,19 +283,6 @@ static void *kzalloc_panic(int len) } /* - * 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, @@ -294,8 +483,8 @@ 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) + for (i = 0; i < dump_save_areas.count; i++) { + if (dump_save_areas.areas[i]->pref_reg == 0) continue; cpus++; } @@ -307,60 +496,33 @@ static int get_cpu_cnt(void) */ static int get_mem_chunk_cnt(void) { - struct mem_chunk *chunk_array, *mem_chunk; - int i, cnt = 0; + int cnt = 0; + u64 idx; - 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; + for_each_dump_mem_range(idx, NUMA_NO_NODE, NULL, NULL, NULL) 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) +static void loads_init(Elf64_Phdr *phdr, u64 loads_offset) { - struct mem_chunk *chunk_array, *mem_chunk; - int i; + phys_addr_t start, end; + u64 idx; - 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; + for_each_dump_mem_range(idx, NUMA_NO_NODE, &start, &end, NULL) { + phdr->p_filesz = end - start; 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_offset = start; + phdr->p_vaddr = start; + phdr->p_paddr = start; + phdr->p_memsz = end - start; phdr->p_flags = PF_R | PF_W | PF_X; phdr->p_align = PAGE_SIZE; phdr++; } - kfree(chunk_array); - return i; } /* @@ -374,8 +536,8 @@ static void *notes_init(Elf64_Phdr *phdr, void *ptr, u64 notes_offset) ptr = nt_prpsinfo(ptr); - for (i = 0; zfcpdump_save_areas[i]; i++) { - sa = zfcpdump_save_areas[i]; + for (i = 0; i < dump_save_areas.count; i++) { + sa = dump_save_areas.areas[i]; if (sa->pref_reg == 0) continue; ptr = fill_cpu_elf_notes(ptr, sa); @@ -383,7 +545,7 @@ static void *notes_init(Elf64_Phdr *phdr, void *ptr, u64 notes_offset) ptr = nt_vmcoreinfo(ptr); memset(phdr, 0, sizeof(*phdr)); phdr->p_type = PT_NOTE; - phdr->p_offset = relocate(notes_offset); + phdr->p_offset = notes_offset; phdr->p_filesz = (unsigned long) PTR_SUB(ptr, ptr_start); phdr->p_memsz = phdr->p_filesz; return ptr; @@ -392,7 +554,7 @@ static void *notes_init(Elf64_Phdr *phdr, void *ptr, u64 notes_offset) /* * Create ELF core header (new kernel) */ -static void s390_elf_corehdr_create(char **elfcorebuf, size_t *elfcorebuf_sz) +int elfcorehdr_alloc(unsigned long long *addr, unsigned long long *size) { Elf64_Phdr *phdr_notes, *phdr_loads; int mem_chunk_cnt; @@ -400,6 +562,23 @@ static void s390_elf_corehdr_create(char **elfcorebuf, size_t *elfcorebuf_sz) u32 alloc_size; u64 hdr_off; + /* If we are not in kdump or zfcpdump mode return */ + if (!OLDMEM_BASE && ipl_info.type != IPL_TYPE_FCP_DUMP) + return 0; + /* If elfcorehdr= has been passed via cmdline, we use that one */ + if (elfcorehdr_addr != ELFCORE_ADDR_MAX) + return 0; + /* If we cannot get HSA size for zfcpdump return error */ + if (ipl_info.type == IPL_TYPE_FCP_DUMP && !sclp_get_hsa_size()) + return -ENODEV; + + /* For kdump, exclude previous crashkernel memory */ + if (OLDMEM_BASE) { + oldmem_region.base = OLDMEM_BASE; + oldmem_region.size = OLDMEM_SIZE; + oldmem_type.total_size = OLDMEM_SIZE; + } + mem_chunk_cnt = get_mem_chunk_cnt(); alloc_size = 0x1000 + get_cpu_cnt() * 0x300 + @@ -417,27 +596,52 @@ static void s390_elf_corehdr_create(char **elfcorebuf, size_t *elfcorebuf_sz) 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); + loads_init(phdr_loads, hdr_off); + *addr = (unsigned long long) hdr; + elfcorehdr_newmem = hdr; + *size = (unsigned long long) hdr_off; + BUG_ON(elfcorehdr_size > alloc_size); + return 0; } /* - * Create kdump ELF core header in new kernel, if it has not been passed via - * the "elfcorehdr" kernel parameter + * Free ELF core header (new kernel) */ -static int setup_kdump_elfcorehdr(void) +void elfcorehdr_free(unsigned long long addr) { - size_t elfcorebuf_sz; - char *elfcorebuf; + if (!elfcorehdr_newmem) + return; + kfree((void *)(unsigned long)addr); +} - 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; +/* + * Read from ELF header + */ +ssize_t elfcorehdr_read(char *buf, size_t count, u64 *ppos) +{ + void *src = (void *)(unsigned long)*ppos; + + src = elfcorehdr_newmem ? src : src - OLDMEM_BASE; + memcpy(buf, src, count); + *ppos += count; + return count; } -subsys_initcall(setup_kdump_elfcorehdr); +/* + * Read from ELF notes data + */ +ssize_t elfcorehdr_read_notes(char *buf, size_t count, u64 *ppos) +{ + void *src = (void *)(unsigned long)*ppos; + int rc; + + if (elfcorehdr_newmem) { + memcpy(buf, src, count); + } else { + rc = copy_from_oldmem(buf, src, count); + if (rc) + return rc; + } + *ppos += count; + return count; +} diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c index 4e8215e0d4b..ee8390da6ea 100644 --- a/arch/s390/kernel/debug.c +++ b/arch/s390/kernel/debug.c @@ -611,7 +611,7 @@ debug_open(struct inode *inode, struct file *file) debug_info_t *debug_info, *debug_info_snapshot; mutex_lock(&debug_mutex); - debug_info = file->f_path.dentry->d_inode->i_private; + debug_info = file_inode(file)->i_private; /* find debug view */ for (i = 0; i < DEBUG_MAX_VIEWS; i++) { if (!debug_info->views[i]) @@ -867,7 +867,7 @@ 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.stck = get_tod_clock_fast(); active->id.fields.cpuid = smp_processor_id(); active->caller = __builtin_return_address(0); active->id.fields.exception = exception; @@ -889,7 +889,7 @@ static int debug_active=1; * if debug_active is already off */ static int -s390dbf_procactive(ctl_table *table, int write, +s390dbf_procactive(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { if (!write || debug_stoppable || !debug_active) diff --git a/arch/s390/kernel/dis.c b/arch/s390/kernel/dis.c index a7f9abd98cf..993efe6a887 100644 --- a/arch/s390/kernel/dis.c +++ b/arch/s390/kernel/dis.c @@ -23,6 +23,7 @@ #include <linux/kdebug.h> #include <asm/uaccess.h> +#include <asm/dis.h> #include <asm/io.h> #include <linux/atomic.h> #include <asm/mathemu.h> @@ -37,17 +38,6 @@ #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 */ @@ -155,19 +145,7 @@ enum { 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[] = +static const struct s390_operand operands[] = { [UNUSED] = { 0, 0, 0 }, [R_8] = { 4, 8, OPERAND_GPR }, @@ -479,7 +457,7 @@ static char *long_insn_name[] = { [LONG_INSN_PCISTB] = "pcistb", }; -static struct insn opcode[] = { +static struct s390_insn opcode[] = { #ifdef CONFIG_64BIT { "bprp", 0xc5, INSTR_MII_UPI }, { "bpp", 0xc7, INSTR_SMI_U0RDP }, @@ -668,7 +646,7 @@ static struct insn opcode[] = { { "", 0, INSTR_INVALID } }; -static struct insn opcode_01[] = { +static struct s390_insn opcode_01[] = { #ifdef CONFIG_64BIT { "ptff", 0x04, INSTR_E }, { "pfpo", 0x0a, INSTR_E }, @@ -684,7 +662,7 @@ static struct insn opcode_01[] = { { "", 0, INSTR_INVALID } }; -static struct insn opcode_a5[] = { +static struct s390_insn opcode_a5[] = { #ifdef CONFIG_64BIT { "iihh", 0x00, INSTR_RI_RU }, { "iihl", 0x01, INSTR_RI_RU }, @@ -706,7 +684,7 @@ static struct insn opcode_a5[] = { { "", 0, INSTR_INVALID } }; -static struct insn opcode_a7[] = { +static struct s390_insn opcode_a7[] = { #ifdef CONFIG_64BIT { "tmhh", 0x02, INSTR_RI_RU }, { "tmhl", 0x03, INSTR_RI_RU }, @@ -728,7 +706,7 @@ static struct insn opcode_a7[] = { { "", 0, INSTR_INVALID } }; -static struct insn opcode_aa[] = { +static struct s390_insn opcode_aa[] = { #ifdef CONFIG_64BIT { { 0, LONG_INSN_RINEXT }, 0x00, INSTR_RI_RI }, { "rion", 0x01, INSTR_RI_RI }, @@ -739,7 +717,7 @@ static struct insn opcode_aa[] = { { "", 0, INSTR_INVALID } }; -static struct insn opcode_b2[] = { +static struct s390_insn opcode_b2[] = { #ifdef CONFIG_64BIT { "stckf", 0x7c, INSTR_S_RD }, { "lpp", 0x80, INSTR_S_RD }, @@ -840,7 +818,6 @@ static struct insn opcode_b2[] = { { "stcke", 0x78, INSTR_S_RD }, { "sacf", 0x79, INSTR_S_RD }, { "stsi", 0x7d, INSTR_S_RD }, - { "spp", 0x80, INSTR_S_RD }, { "srnm", 0x99, INSTR_S_RD }, { "stfpc", 0x9c, INSTR_S_RD }, { "lfpc", 0x9d, INSTR_S_RD }, @@ -852,7 +829,7 @@ static struct insn opcode_b2[] = { { "", 0, INSTR_INVALID } }; -static struct insn opcode_b3[] = { +static struct s390_insn opcode_b3[] = { #ifdef CONFIG_64BIT { "maylr", 0x38, INSTR_RRF_F0FF }, { "mylr", 0x39, INSTR_RRF_F0FF }, @@ -1035,7 +1012,7 @@ static struct insn opcode_b3[] = { { "", 0, INSTR_INVALID } }; -static struct insn opcode_b9[] = { +static struct s390_insn opcode_b9[] = { #ifdef CONFIG_64BIT { "lpgr", 0x00, INSTR_RRE_RR }, { "lngr", 0x01, INSTR_RRE_RR }, @@ -1168,7 +1145,7 @@ static struct insn opcode_b9[] = { { "", 0, INSTR_INVALID } }; -static struct insn opcode_c0[] = { +static struct s390_insn opcode_c0[] = { #ifdef CONFIG_64BIT { "lgfi", 0x01, INSTR_RIL_RI }, { "xihf", 0x06, INSTR_RIL_RU }, @@ -1188,7 +1165,7 @@ static struct insn opcode_c0[] = { { "", 0, INSTR_INVALID } }; -static struct insn opcode_c2[] = { +static struct s390_insn opcode_c2[] = { #ifdef CONFIG_64BIT { "msgfi", 0x00, INSTR_RIL_RI }, { "msfi", 0x01, INSTR_RIL_RI }, @@ -1206,7 +1183,7 @@ static struct insn opcode_c2[] = { { "", 0, INSTR_INVALID } }; -static struct insn opcode_c4[] = { +static struct s390_insn opcode_c4[] = { #ifdef CONFIG_64BIT { "llhrl", 0x02, INSTR_RIL_RP }, { "lghrl", 0x04, INSTR_RIL_RP }, @@ -1223,7 +1200,7 @@ static struct insn opcode_c4[] = { { "", 0, INSTR_INVALID } }; -static struct insn opcode_c6[] = { +static struct s390_insn opcode_c6[] = { #ifdef CONFIG_64BIT { "exrl", 0x00, INSTR_RIL_RP }, { "pfdrl", 0x02, INSTR_RIL_UP }, @@ -1241,7 +1218,7 @@ static struct insn opcode_c6[] = { { "", 0, INSTR_INVALID } }; -static struct insn opcode_c8[] = { +static struct s390_insn opcode_c8[] = { #ifdef CONFIG_64BIT { "mvcos", 0x00, INSTR_SSF_RRDRD }, { "ectg", 0x01, INSTR_SSF_RRDRD }, @@ -1252,7 +1229,7 @@ static struct insn opcode_c8[] = { { "", 0, INSTR_INVALID } }; -static struct insn opcode_cc[] = { +static struct s390_insn opcode_cc[] = { #ifdef CONFIG_64BIT { "brcth", 0x06, INSTR_RIL_RP }, { "aih", 0x08, INSTR_RIL_RI }, @@ -1264,7 +1241,7 @@ static struct insn opcode_cc[] = { { "", 0, INSTR_INVALID } }; -static struct insn opcode_e3[] = { +static struct s390_insn opcode_e3[] = { #ifdef CONFIG_64BIT { "ltg", 0x02, INSTR_RXY_RRRD }, { "lrag", 0x03, INSTR_RXY_RRRD }, @@ -1370,7 +1347,7 @@ static struct insn opcode_e3[] = { { "", 0, INSTR_INVALID } }; -static struct insn opcode_e5[] = { +static struct s390_insn opcode_e5[] = { #ifdef CONFIG_64BIT { "strag", 0x02, INSTR_SSE_RDRD }, { "mvhhi", 0x44, INSTR_SIL_RDI }, @@ -1392,7 +1369,7 @@ static struct insn opcode_e5[] = { { "", 0, INSTR_INVALID } }; -static struct insn opcode_eb[] = { +static struct s390_insn opcode_eb[] = { #ifdef CONFIG_64BIT { "lmg", 0x04, INSTR_RSY_RRRD }, { "srag", 0x0a, INSTR_RSY_RRRD }, @@ -1466,7 +1443,7 @@ static struct insn opcode_eb[] = { { "", 0, INSTR_INVALID } }; -static struct insn opcode_ec[] = { +static struct s390_insn opcode_ec[] = { #ifdef CONFIG_64BIT { "brxhg", 0x44, INSTR_RIE_RRP }, { "brxlg", 0x45, INSTR_RIE_RRP }, @@ -1505,7 +1482,7 @@ static struct insn opcode_ec[] = { { "", 0, INSTR_INVALID } }; -static struct insn opcode_ed[] = { +static struct s390_insn opcode_ed[] = { #ifdef CONFIG_64BIT { "mayl", 0x38, INSTR_RXF_FRRDF }, { "myl", 0x39, INSTR_RXF_FRRDF }, @@ -1573,7 +1550,7 @@ static struct insn opcode_ed[] = { /* Extracts an operand value from an instruction. */ static unsigned int extract_operand(unsigned char *code, - const struct operand *operand) + const struct s390_operand *operand) { unsigned int val; int bits; @@ -1609,16 +1586,11 @@ static unsigned int extract_operand(unsigned char *code, 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) +struct s390_insn *find_insn(unsigned char *code) { unsigned char opfrag = code[1]; unsigned char opmask; - struct insn *table; + struct s390_insn *table; switch (code[0]) { case 0x01: @@ -1697,34 +1669,35 @@ static struct insn *find_insn(unsigned char *code) * insn_to_mnemonic - decode an s390 instruction * @instruction: instruction to decode * @buf: buffer to fill with mnemonic + * @len: length of buffer * * Decode the instruction at @instruction and store the corresponding - * mnemonic into @buf. + * mnemonic into @buf of length @len. * @buf is left unchanged if the instruction could not be decoded. * Returns: * %0 on success, %-ENOENT if the instruction was not found. */ -int insn_to_mnemonic(unsigned char *instruction, char buf[8]) +int insn_to_mnemonic(unsigned char *instruction, char *buf, unsigned int len) { - struct insn *insn; + struct s390_insn *insn; insn = find_insn(instruction); if (!insn) return -ENOENT; if (insn->name[0] == '\0') - snprintf(buf, sizeof(buf), "%s", + snprintf(buf, len, "%s", long_insn_name[(int) insn->name[1]]); else - snprintf(buf, sizeof(buf), "%.5s", insn->name); + snprintf(buf, len, "%.5s", insn->name); return 0; } EXPORT_SYMBOL_GPL(insn_to_mnemonic); static int print_insn(char *buffer, unsigned char *code, unsigned long addr) { - struct insn *insn; + struct s390_insn *insn; const unsigned char *ops; - const struct operand *operand; + const struct s390_operand *operand; unsigned int value; char separator; char *ptr; @@ -1862,6 +1835,8 @@ void print_fn_code(unsigned char *code, unsigned long len) while (len) { ptr = buffer; opsize = insn_length(*code); + if (opsize > len) + break; ptr += sprintf(ptr, "%p: ", code); for (i = 0; i < opsize; i++) ptr += sprintf(ptr, "%02x", code[i]); diff --git a/arch/s390/kernel/dumpstack.c b/arch/s390/kernel/dumpstack.c new file mode 100644 index 00000000000..acb412442e5 --- /dev/null +++ b/arch/s390/kernel/dumpstack.c @@ -0,0 +1,217 @@ +/* + * Stack dumping functions + * + * Copyright IBM Corp. 1999, 2013 + */ + +#include <linux/kallsyms.h> +#include <linux/hardirq.h> +#include <linux/kprobes.h> +#include <linux/utsname.h> +#include <linux/export.h> +#include <linux/kdebug.h> +#include <linux/ptrace.h> +#include <linux/module.h> +#include <linux/sched.h> +#include <asm/processor.h> +#include <asm/debug.h> +#include <asm/dis.h> +#include <asm/ipl.h> + +#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; + unsigned long addr; + + while (1) { + sp = sp & PSW_ADDR_INSN; + if (sp < low || sp > high - sizeof(*sf)) + return sp; + sf = (struct stack_frame *) sp; + addr = sf->gprs[8] & PSW_ADDR_INSN; + printk("([<%016lx>] %pSR)\n", addr, (void *)addr); + /* 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; + addr = sf->gprs[8] & PSW_ADDR_INSN; + printk(" [<%016lx>] %pSR\n", addr, (void *)addr); + } + /* 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; + printk(" [<%016lx>] %pSR\n", addr, (void *)addr); + low = sp; + sp = regs->gprs[15]; + } +} + +static void show_trace(struct task_struct *task, unsigned long *stack) +{ + const unsigned long frame_size = + STACK_FRAME_OVERHEAD + sizeof(struct pt_regs); + 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 + frame_size - 4096, + S390_lowcore.panic_stack + frame_size); +#endif + sp = __show_trace(sp, + S390_lowcore.async_stack + frame_size - ASYNC_SIZE, + S390_lowcore.async_stack + frame_size); + 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>] %pSR\n", regs->args[0], (void *)regs->args[0]); +#endif +} + +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 = user_mode(regs) ? "User" : "Krnl"; + printk("%s PSW : %p %p", mode, (void *)regs->psw.mask, (void *)regs->psw.addr); + if (!user_mode(regs)) + printk(" (%pSR)", (void *)regs->psw.addr); + printk("\n"); + 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) +{ + show_regs_print_info(KERN_DEFAULT); + show_registers(regs); + /* Show stack backtrace if pt_regs is from kernel mode */ + if (!user_mode(regs)) + 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); + print_modules(); + show_regs(regs); + bust_spinlocks(0); + add_taint(TAINT_DIE, LOCKDEP_NOW_UNRELIABLE); + 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); +} diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c index 1f0eee9e7da..0dff972a169 100644 --- a/arch/s390/kernel/early.c +++ b/arch/s390/kernel/early.c @@ -47,10 +47,10 @@ static void __init reset_tod_clock(void) { u64 time; - if (store_clock(&time) == 0) + if (store_tod_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) + if (set_tod_clock(TOD_UNIX_EPOCH) != 0 || store_tod_clock(&time) != 0) disabled_wait(0); sched_clock_base_cc = TOD_UNIX_EPOCH; @@ -173,7 +173,7 @@ static noinline __init void create_kernel_nss(void) } /* re-initialize cputime accounting. */ - sched_clock_base_cc = get_clock(); + sched_clock_base_cc = get_tod_clock(); S390_lowcore.last_update_clock = sched_clock_base_cc; S390_lowcore.last_update_timer = 0x7fffffffffffffffULL; S390_lowcore.user_timer = 0; @@ -206,6 +206,7 @@ static noinline __init void clear_bss_section(void) */ static noinline __init void init_kernel_storage_key(void) { +#if PAGE_DEFAULT_KEY unsigned long end_pfn, init_pfn; end_pfn = PFN_UP(__pa(&_end)); @@ -213,6 +214,7 @@ static noinline __init void init_kernel_storage_key(void) for (init_pfn = 0 ; init_pfn < end_pfn; init_pfn++) page_set_storage_key(init_pfn << PAGE_SHIFT, PAGE_DEFAULT_KEY, 0); +#endif } static __initdata char sysinfo_page[PAGE_SIZE] __aligned(PAGE_SIZE); @@ -256,13 +258,19 @@ static __init void setup_topology(void) static void early_pgm_check_handler(void) { const struct exception_table_entry *fixup; + unsigned long cr0, cr0_new; unsigned long addr; addr = S390_lowcore.program_old_psw.addr; fixup = search_exception_tables(addr & PSW_ADDR_INSN); if (!fixup) disabled_wait(0); + /* Disable low address protection before storing into lowcore. */ + __ctl_store(cr0, 0, 0); + cr0_new = cr0 & ~(1UL << 28); + __ctl_load(cr0_new, 0, 0); S390_lowcore.program_old_psw.addr = extable_fixup(fixup)|PSW_ADDR_AMODE; + __ctl_load(cr0, 0, 0); } static noinline __init void setup_lowcore_early(void) @@ -378,14 +386,14 @@ static __init void detect_machine_facilities(void) S390_lowcore.machine_flags |= MACHINE_FLAG_EDAT2; if (test_facility(3)) S390_lowcore.machine_flags |= MACHINE_FLAG_IDTE; - if (test_facility(27)) - S390_lowcore.machine_flags |= MACHINE_FLAG_MVCOS; if (test_facility(40)) - S390_lowcore.machine_flags |= MACHINE_FLAG_SPP; + S390_lowcore.machine_flags |= MACHINE_FLAG_LPP; if (test_facility(50) && test_facility(73)) S390_lowcore.machine_flags |= MACHINE_FLAG_TE; if (test_facility(66)) S390_lowcore.machine_flags |= MACHINE_FLAG_RRBM; + if (test_facility(51)) + S390_lowcore.machine_flags |= MACHINE_FLAG_TLB_LC; #endif } @@ -481,8 +489,7 @@ void __init startup_init(void) detect_diag44(); detect_machine_facilities(); setup_topology(); - sclp_facilities_detect(); - detect_memory_layout(memory_chunk); + sclp_early_detect(); #ifdef CONFIG_DYNAMIC_FTRACE S390_lowcore.ftrace_func = (unsigned long)ftrace_caller; #endif diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 55022852326..70203265196 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -10,6 +10,7 @@ #include <linux/init.h> #include <linux/linkage.h> +#include <asm/processor.h> #include <asm/cache.h> #include <asm/errno.h> #include <asm/ptrace.h> @@ -18,6 +19,7 @@ #include <asm/unistd.h> #include <asm/page.h> #include <asm/sigp.h> +#include <asm/irq.h> __PT_R0 = __PT_GPRS __PT_R1 = __PT_GPRS + 4 @@ -36,15 +38,15 @@ __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 +STACK_INIT = STACK_SIZE - STACK_FRAME_OVERHEAD - __PT_SIZE + +_TIF_WORK = (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED) +_TIF_TRACE = (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | \ + _TIF_SYSCALL_TRACEPOINT) +_CIF_WORK = (_CIF_MCCK_PENDING | _CIF_ASCE) +_PIF_WORK = (_PIF_PER_TRAP) #define BASED(name) name-system_call(%r13) @@ -97,10 +99,10 @@ STACK_SIZE = 1 << STACK_SHIFT sra %r14,\shift jnz 1f CHECK_STACK 1<<\shift,\savearea + ahi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) j 2f 1: l %r15,\stack # load target stack -2: ahi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) - la %r11,STACK_FRAME_OVERHEAD(%r15) +2: la %r11,STACK_FRAME_OVERHEAD(%r15) .endm .macro ADD64 high,low,timer @@ -150,18 +152,14 @@ ENTRY(__switch_to) l %r4,__THREAD_info(%r2) # get thread_info of prev l %r5,__THREAD_info(%r3) # get thread_info of next lr %r15,%r5 - ahi %r15,STACK_SIZE # end of kernel stack of next + ahi %r15,STACK_INIT # end of kernel stack of next st %r3,__LC_CURRENT # store task struct of next st %r5,__LC_THREAD_INFO # store thread info of next st %r15,__LC_KERNEL_STACK # store end of kernel stack lctl %c4,%c4,__TASK_pid(%r3) # load pid to control reg. 4 mvc __LC_CURRENT_PID(4,%r0),__TASK_pid(%r3) # store pid of next l %r15,__THREAD_ksp(%r3) # load kernel stack 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: lm %r6,%r15,__SF_GPRS(%r15) # load gprs of next task + lm %r6,%r15,__SF_GPRS(%r15) # load gprs of next task br %r14 __critical_start: @@ -176,9 +174,9 @@ sysc_stm: stm %r8,%r15,__LC_SAVE_AREA_SYNC l %r12,__LC_THREAD_INFO l %r13,__LC_SVC_NEW_PSW+4 + lhi %r14,_PIF_SYSCALL 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 @@ -186,8 +184,9 @@ sysc_vtime: 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 + st %r14,__PT_FLAGS(%r11) sysc_do_svc: - oi __TI_flags+3(%r12),_TIF_SYSCALL + l %r10,__TI_sysc_table(%r12) # 31 bit system call table lh %r8,__PT_INT_CODE+2(%r11) sla %r8,2 # shift and test for svc0 jnz sysc_nr_ok @@ -198,12 +197,11 @@ sysc_do_svc: 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 + tm __TI_flags+3(%r12),_TIF_TRACE jnz sysc_tracesys basr %r14,%r9 # call sys_xxxx st %r2,__PT_R2(%r11) # store return value @@ -213,9 +211,12 @@ sysc_return: 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 + tm __PT_FLAGS+3(%r11),_PIF_WORK + jnz sysc_work + tm __TI_flags+3(%r12),_TIF_WORK + jnz sysc_work # check for thread work + tm __LC_CPU_FLAGS+3,_CIF_WORK + jnz sysc_work sysc_restore: mvc __LC_RETURN_PSW(8),__PT_PSW(%r11) stpt __LC_EXIT_TIMER @@ -227,16 +228,18 @@ sysc_done: # One of the work bits is on. Find out which one. # sysc_work: - tm __TI_flags+3(%r12),_TIF_MCCK_PENDING + tm __LC_CPU_FLAGS+3,_CIF_MCCK_PENDING jo sysc_mcck_pending tm __TI_flags+3(%r12),_TIF_NEED_RESCHED jo sysc_reschedule - tm __TI_flags+3(%r12),_TIF_PER_TRAP + tm __PT_FLAGS+3(%r11),_PIF_PER_TRAP jo sysc_singlestep tm __TI_flags+3(%r12),_TIF_SIGPENDING jo sysc_sigpending tm __TI_flags+3(%r12),_TIF_NOTIFY_RESUME jo sysc_notify_resume + tm __LC_CPU_FLAGS+3,_CIF_ASCE + jo sysc_uaccess j sysc_return # beware of critical section cleanup # @@ -248,7 +251,7 @@ sysc_reschedule: br %r1 # call schedule # -# _TIF_MCCK_PENDING is set, call handler +# _CIF_MCCK_PENDING is set, call handler # sysc_mcck_pending: l %r1,BASED(.Lhandle_mcck) @@ -256,15 +259,24 @@ sysc_mcck_pending: br %r1 # TIF bit will be cleared by handler # +# _CIF_ASCE is set, load user space asce +# +sysc_uaccess: + ni __LC_CPU_FLAGS+3,255-_CIF_ASCE + lctl %c1,%c1,__LC_USER_ASCE # load primary asce + j sysc_return + +# # _TIF_SIGPENDING is set, call do_signal # sysc_sigpending: 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 + tm __PT_FLAGS+3(%r11),_PIF_SYSCALL jno sysc_return lm %r2,%r7,__PT_R2(%r11) # load svc arguments + l %r10,__TI_sysc_table(%r12) # 31 bit system call table 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 @@ -282,10 +294,10 @@ sysc_notify_resume: br %r1 # call do_notify_resume # -# _TIF_PER_TRAP is set, call do_per_trap +# _PIF_PER_TRAP is set, call do_per_trap # sysc_singlestep: - ni __TI_flags+3(%r12),255-_TIF_PER_TRAP + ni __PT_FLAGS+3(%r11),255-_PIF_PER_TRAP lr %r2,%r11 # pass pointer to pt_regs l %r1,BASED(.Ldo_per_trap) la %r14,BASED(sysc_return) @@ -315,7 +327,7 @@ sysc_tracego: basr %r14,%r9 # call sys_xxx st %r2,__PT_R2(%r11) # store return value sysc_tracenogo: - tm __TI_flags+2(%r12),_TIF_TRACE >> 8 + tm __TI_flags+3(%r12),_TIF_TRACE jz sysc_return l %r1,BASED(.Ltrace_exit) lr %r2,%r11 # pass pointer to pt_regs @@ -359,25 +371,26 @@ ENTRY(pgm_check_handler) 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 + ahi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) 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) +2: 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 + xc __PT_FLAGS(4,%r11),__PT_FLAGS(%r11) 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 + oi __PT_FLAGS+3(%r11),_PIF_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 + mvc __THREAD_per_cause(2,%r1),__LC_PER_CODE + mvc __THREAD_per_paid(1,%r1),__LC_PER_ACCESS_ID 0: REENABLE_IRQS xc __SF_BACKCHAIN(4,%r15),__SF_BACKCHAIN(%r15) l %r1,BASED(.Ljump_table) @@ -405,9 +418,9 @@ pgm_kprobe: # 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) + lhi %r14,_PIF_SYSCALL | _PIF_PER_TRAP lpsw __LC_RETURN_PSW # branch to sysc_per and enable irqs /* @@ -429,17 +442,33 @@ io_skip: stm %r0,%r7,__PT_R0(%r11) mvc __PT_R8(32,%r11),__LC_SAVE_AREA_ASYNC stm %r8,%r9,__PT_PSW(%r11) + mvc __PT_INT_CODE(12,%r11),__LC_SUBCHANNEL_ID + xc __PT_FLAGS(4,%r11),__PT_FLAGS(%r11) TRACE_IRQS_OFF xc __SF_BACKCHAIN(4,%r15),__SF_BACKCHAIN(%r15) +io_loop: l %r1,BASED(.Ldo_IRQ) lr %r2,%r11 # pass pointer to pt_regs + lhi %r3,IO_INTERRUPT + tm __PT_INT_CODE+8(%r11),0x80 # adapter interrupt ? + jz io_call + lhi %r3,THIN_INTERRUPT +io_call: basr %r14,%r1 # call do_IRQ + tm __LC_MACHINE_FLAGS+2,0x10 # MACHINE_FLAG_LPAR + jz io_return + tpi 0 + jz io_return + mvc __PT_INT_CODE(12,%r11),__LC_SUBCHANNEL_ID + j io_loop io_return: LOCKDEP_SYS_EXIT TRACE_IRQS_ON io_tif: - tm __TI_flags+3(%r12),_TIF_WORK_INT + tm __TI_flags+3(%r12),_TIF_WORK jnz io_work # there is work to do (signals etc.) + tm __LC_CPU_FLAGS+3,_CIF_WORK + jnz io_work io_restore: mvc __LC_RETURN_PSW(8),__PT_PSW(%r11) stpt __LC_EXIT_TIMER @@ -449,7 +478,7 @@ 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 +# 1) if we return to user space we can do all _TIF_WORK 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. @@ -485,7 +514,6 @@ io_work: # 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) @@ -493,11 +521,9 @@ io_work_user: # # 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 + tm __LC_CPU_FLAGS+3(%r12),_CIF_MCCK_PENDING jo io_mcck_pending tm __TI_flags+3(%r12),_TIF_NEED_RESCHED jo io_reschedule @@ -505,10 +531,12 @@ io_work_tif: jo io_sigpending tm __TI_flags+3(%r12),_TIF_NOTIFY_RESUME jo io_notify_resume + tm __LC_CPU_FLAGS+3,_CIF_ASCE + jo io_uaccess j io_return # beware of critical section cleanup # -# _TIF_MCCK_PENDING is set, call handler +# _CIF_MCCK_PENDING is set, call handler # io_mcck_pending: # TRACE_IRQS_ON already done at io_return @@ -518,6 +546,14 @@ io_mcck_pending: j io_return # +# _CIF_ASCE is set, load user space asce +# +io_uaccess: + ni __LC_CPU_FLAGS+3,255-_CIF_ASCE + lctl %c1,%c1,__LC_USER_ASCE # load primary asce + j io_return + +# # _TIF_NEED_RESCHED is set, call schedule # io_reschedule: @@ -574,12 +610,14 @@ ext_skip: stm %r0,%r7,__PT_R0(%r11) mvc __PT_R8(32,%r11),__LC_SAVE_AREA_ASYNC stm %r8,%r9,__PT_PSW(%r11) + mvc __PT_INT_CODE(4,%r11),__LC_EXT_CPU_ADDR + mvc __PT_INT_PARM(4,%r11),__LC_EXT_PARAMS + xc __PT_FLAGS(4,%r11),__PT_FLAGS(%r11) TRACE_IRQS_OFF + l %r1,BASED(.Ldo_IRQ) 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 + lhi %r3,EXT_INTERRUPT + basr %r14,%r1 # call do_IRQ j io_return /* @@ -636,8 +674,10 @@ ENTRY(mcck_int_handler) 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 %r0,%r7,__PT_R0(%r11) + mvc __PT_R8(32,%r11),__LC_GPREGS_SAVE_AREA+32 stm %r8,%r9,__PT_PSW(%r11) + xc __PT_FLAGS(4,%r11),__PT_FLAGS(%r11) xc __SF_BACKCHAIN(4,%r15),__SF_BACKCHAIN(%r15) l %r1,BASED(.Ldo_machine_check) lr %r2,%r11 # pass pointer to pt_regs @@ -645,13 +685,12 @@ mcck_skip: 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 + tm __LC_CPU_FLAGS+3,_CIF_MCCK_PENDING jno mcck_return TRACE_IRQS_OFF l %r1,BASED(.Lhandle_mcck) @@ -673,6 +712,7 @@ mcck_panic: sra %r14,PAGE_SHIFT jz 0f l %r15,__LC_PANIC_STACK + j mcck_skip 0: ahi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) j mcck_skip @@ -713,12 +753,10 @@ ENTRY(restart_int_handler) */ 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) + la %r11,STACK_FRAME_OVERHEAD(%r15) + stm %r0,%r7,__PT_R0(%r11) + stm %r8,%r9,__PT_PSW(%r11) 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 @@ -798,15 +836,16 @@ cleanup_system_call: 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 + la %r9,STACK_FRAME_OVERHEAD(%r15) + st %r9,12(%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 + mvc __PT_R8(32,%r9),__LC_SAVE_AREA_SYNC + stm %r0,%r7,__PT_R0(%r9) + mvc __PT_PSW(8,%r9),__LC_SVC_OLD_PSW + mvc __PT_INT_CODE(4,%r9),__LC_SVC_ILC + xc __PT_FLAGS(4,%r9),__PT_FLAGS(%r9) + mvi __PT_FLAGS+3(%r9),_PIF_SYSCALL # 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 @@ -874,13 +913,13 @@ cleanup_idle: stm %r9,%r10,__LC_SYSTEM_TIMER mvc __LC_LAST_UPDATE_TIMER(8),__TIMER_IDLE_EXIT(%r2) # prepare return psw - n %r8,BASED(cleanup_idle_wait) # clear wait state bit + n %r8,BASED(cleanup_idle_wait) # clear irq & wait state bits l %r9,24(%r11) # return from psw_idle br %r14 cleanup_idle_insn: .long psw_idle_lpsw + 0x80000000 cleanup_idle_wait: - .long 0xfffdffff + .long 0xfcfdffff /* * Integer constants @@ -897,7 +936,6 @@ cleanup_idle_wait: .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 @@ -909,7 +947,6 @@ cleanup_idle_wait: .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 diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h index 2711936fe70..6ac78192455 100644 --- a/arch/s390/kernel/entry.h +++ b/arch/s390/kernel/entry.h @@ -7,6 +7,7 @@ #include <asm/cputime.h> extern void *restart_stack; +extern unsigned long suspend_zero_pages; void system_call(void); void pgm_check_handler(void); @@ -22,7 +23,6 @@ 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 addressing_exception(struct pt_regs *regs); void data_exception(struct pt_regs *regs); @@ -52,34 +52,22 @@ void 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 __init init_IRQ(void); +void do_IRQ(struct pt_regs *regs, int irq); void do_restart(void); void __init startup_init(void); void die(struct pt_regs *regs, const char *str); - +int setup_profiling_timer(unsigned int multiplier); void __init time_init(void); +int pfn_is_nosave(unsigned long); +void s390_early_resume(void); +unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip); 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_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); +long sys_s390_runtime_instr(int command, int signum); #endif /* _ENTRY_H */ diff --git a/arch/s390/kernel/entry64.S b/arch/s390/kernel/entry64.S index 6d34e0c97a3..f2e674c702e 100644 --- a/arch/s390/kernel/entry64.S +++ b/arch/s390/kernel/entry64.S @@ -19,6 +19,7 @@ #include <asm/unistd.h> #include <asm/page.h> #include <asm/sigp.h> +#include <asm/irq.h> __PT_R0 = __PT_GPRS __PT_R1 = __PT_GPRS + 8 @@ -39,14 +40,13 @@ __PT_R15 = __PT_GPRS + 120 STACK_SHIFT = PAGE_SHIFT + THREAD_ORDER STACK_SIZE = 1 << STACK_SHIFT +STACK_INIT = STACK_SIZE - STACK_FRAME_OVERHEAD - __PT_SIZE -_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) +_TIF_WORK = (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED) +_TIF_TRACE = (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | \ + _TIF_SYSCALL_TRACEPOINT) +_CIF_WORK = (_CIF_MCCK_PENDING | _CIF_ASCE) +_PIF_WORK = (_PIF_PER_TRAP) #define BASED(name) name-system_call(%r13) @@ -72,31 +72,35 @@ _TIF_EXIT_SIE = (_TIF_SIGPENDING | _TIF_NEED_RESCHED | _TIF_MCCK_PENDING) #endif .endm - .macro SPP newpp -#if defined(CONFIG_KVM) || defined(CONFIG_KVM_MODULE) - tm __LC_MACHINE_FLAGS+6,0x20 # MACHINE_FLAG_SPP + .macro LPP newpp +#if IS_ENABLED(CONFIG_KVM) + tm __LC_MACHINE_FLAGS+6,0x20 # MACHINE_FLAG_LPP jz .+8 .insn s,0xb2800000,\newpp #endif .endm - .macro HANDLE_SIE_INTERCEPT scratch,pgmcheck -#if defined(CONFIG_KVM) || defined(CONFIG_KVM_MODULE) + .macro HANDLE_SIE_INTERCEPT scratch,reason +#if IS_ENABLED(CONFIG_KVM) tmhh %r8,0x0001 # interrupting from user ? - jnz .+42 + jnz .+62 lgr \scratch,%r9 - slg \scratch,BASED(.Lsie_loop) - clg \scratch,BASED(.Lsie_length) - .if \pgmcheck + slg \scratch,BASED(.Lsie_critical) + clg \scratch,BASED(.Lsie_critical_length) + .if \reason==1 # Some program interrupts are suppressing (e.g. protection). # We must also check the instruction after SIE in that case. # do_protection_exception will rewind to rewind_pad - jh .+22 + jh .+42 .else - jhe .+22 + jhe .+42 .endif - lg %r9,BASED(.Lsie_loop) - SPP BASED(.Lhost_id) # set host id + lg %r14,__SF_EMPTY(%r15) # get control block pointer + LPP __SF_EMPTY+16(%r15) # set host id + ni __SIE_PROG0C+3(%r14),0xfe # no longer in SIE + lctlg %c1,%c1,__LC_USER_ASCE # load primary asce + larl %r9,sie_exit # skip forward to sie_exit + mvi __SF_EMPTY+31(%r15),\reason # set exit reason #endif .endm @@ -124,10 +128,10 @@ _TIF_EXIT_SIE = (_TIF_SIGPENDING | _TIF_NEED_RESCHED | _TIF_MCCK_PENDING) srag %r14,%r14,\shift jnz 1f CHECK_STACK 1<<\shift,\savearea + aghi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) j 2f 1: lg %r15,\stack # load target stack -2: aghi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) - la %r11,STACK_FRAME_OVERHEAD(%r15) +2: la %r11,STACK_FRAME_OVERHEAD(%r15) .endm .macro UPDATE_VTIME scratch,enter_timer @@ -177,18 +181,14 @@ ENTRY(__switch_to) lg %r4,__THREAD_info(%r2) # get thread_info of prev lg %r5,__THREAD_info(%r3) # get thread_info of next lgr %r15,%r5 - aghi %r15,STACK_SIZE # end of kernel stack of next + aghi %r15,STACK_INIT # end of kernel stack of next stg %r3,__LC_CURRENT # store task struct of next stg %r5,__LC_THREAD_INFO # store thread info of next stg %r15,__LC_KERNEL_STACK # store end of kernel stack lctl %c4,%c4,__TASK_pid(%r3) # load pid to control reg. 4 mvc __LC_CURRENT_PID+4(4,%r0),__TASK_pid(%r3) # store pid of next lg %r15,__THREAD_ksp(%r3) # load kernel stack 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: lmg %r6,%r15,__SF_GPRS(%r15) # load gprs of next task + lmg %r6,%r15,__SF_GPRS(%r15) # load gprs of next task br %r14 __critical_start: @@ -203,10 +203,9 @@ sysc_stmg: stmg %r8,%r15,__LC_SAVE_AREA_SYNC lg %r10,__LC_LAST_BREAK lg %r12,__LC_THREAD_INFO - larl %r13,system_call + lghi %r14,_PIF_SYSCALL 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 @@ -215,8 +214,9 @@ sysc_vtime: 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 + stg %r14,__PT_FLAGS(%r11) sysc_do_svc: - oi __TI_flags+7(%r12),_TIF_SYSCALL + lg %r10,__TI_sysc_table(%r12) # address of system call table llgh %r8,__PT_INT_CODE+2(%r11) slag %r8,%r8,2 # shift and test for svc 0 jnz sysc_nr_ok @@ -227,18 +227,11 @@ sysc_do_svc: 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 + tm __TI_flags+7(%r12),_TIF_TRACE jnz sysc_tracesys basr %r14,%r9 # call sys_xxxx stg %r2,__PT_R2(%r11) # store return value @@ -248,9 +241,12 @@ sysc_return: sysc_tif: tm __PT_PSW+1(%r11),0x01 # returning to user ? jno sysc_restore - tm __TI_flags+7(%r12),_TIF_WORK_SVC + tm __PT_FLAGS+7(%r11),_PIF_WORK + jnz sysc_work + tm __TI_flags+7(%r12),_TIF_WORK jnz sysc_work # check for work - ni __TI_flags+7(%r12),255-_TIF_SYSCALL + tm __LC_CPU_FLAGS+7,_CIF_WORK + jnz sysc_work sysc_restore: lg %r14,__LC_VDSO_PER_CPU lmg %r0,%r10,__PT_R0(%r11) @@ -265,16 +261,18 @@ sysc_done: # One of the work bits is on. Find out which one. # sysc_work: - tm __TI_flags+7(%r12),_TIF_MCCK_PENDING + tm __LC_CPU_FLAGS+7,_CIF_MCCK_PENDING jo sysc_mcck_pending tm __TI_flags+7(%r12),_TIF_NEED_RESCHED jo sysc_reschedule - tm __TI_flags+7(%r12),_TIF_PER_TRAP + tm __PT_FLAGS+7(%r11),_PIF_PER_TRAP jo sysc_singlestep tm __TI_flags+7(%r12),_TIF_SIGPENDING jo sysc_sigpending tm __TI_flags+7(%r12),_TIF_NOTIFY_RESUME jo sysc_notify_resume + tm __LC_CPU_FLAGS+7,_CIF_ASCE + jo sysc_uaccess j sysc_return # beware of critical section cleanup # @@ -285,21 +283,30 @@ sysc_reschedule: jg schedule # -# _TIF_MCCK_PENDING is set, call handler +# _CIF_MCCK_PENDING is set, call handler # sysc_mcck_pending: larl %r14,sysc_return jg s390_handle_mcck # TIF bit will be cleared by handler # +# _CIF_ASCE is set, load user space asce +# +sysc_uaccess: + ni __LC_CPU_FLAGS+7,255-_CIF_ASCE + lctlg %c1,%c1,__LC_USER_ASCE # load primary asce + j sysc_return + +# # _TIF_SIGPENDING is set, call do_signal # sysc_sigpending: lgr %r2,%r11 # pass pointer to pt_regs brasl %r14,do_signal - tm __TI_flags+7(%r12),_TIF_SYSCALL + tm __PT_FLAGS+7(%r11),_PIF_SYSCALL jno sysc_return lmg %r2,%r7,__PT_R2(%r11) # load svc arguments + lg %r10,__TI_sysc_table(%r12) # address of system call table lghi %r8,0 # svc 0 returns -ENOSYS llgh %r1,__PT_INT_CODE+2(%r11) # load new svc number cghi %r1,NR_syscalls @@ -316,10 +323,10 @@ sysc_notify_resume: jg do_notify_resume # -# _TIF_PER_TRAP is set, call do_per_trap +# _PIF_PER_TRAP is set, call do_per_trap # sysc_singlestep: - ni __TI_flags+7(%r12),255-_TIF_PER_TRAP + ni __PT_FLAGS+7(%r11),255-_PIF_PER_TRAP lgr %r2,%r11 # pass pointer to pt_regs larl %r14,sysc_return jg do_per_trap @@ -346,7 +353,7 @@ sysc_tracego: basr %r14,%r9 # call sys_xxx stg %r2,__PT_R2(%r11) # store return value sysc_tracenogo: - tm __TI_flags+6(%r12),_TIF_TRACE >> 8 + tm __TI_flags+7(%r12),_TIF_TRACE jz sysc_return lgr %r2,%r11 # pass pointer to pt_regs larl %r14,sysc_return @@ -389,6 +396,7 @@ ENTRY(pgm_check_handler) 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 + aghi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) j 2f 1: UPDATE_VTIME %r14,__LC_SYNC_ENTER_TIMER LAST_BREAK %r14 @@ -398,22 +406,22 @@ ENTRY(pgm_check_handler) tm __LC_PGM_ILC+2,0x02 # check for transaction abort jz 2f mvc __THREAD_trap_tdb(256,%r14),0(%r13) -2: aghi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) - la %r11,STACK_FRAME_OVERHEAD(%r15) +2: 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 + xc __PT_FLAGS(8,%r11),__PT_FLAGS(%r11) stg %r10,__PT_ARGS(%r11) tm __LC_PGM_ILC+3,0x80 # check for per exception jz 0f tmhh %r8,0x0001 # kernel per event ? jz pgm_kprobe - oi __TI_flags+7(%r12),_TIF_PER_TRAP + oi __PT_FLAGS+7(%r11),_PIF_PER_TRAP mvc __THREAD_per_address(8,%r14),__LC_PER_ADDRESS - mvc __THREAD_per_cause(2,%r14),__LC_PER_CAUSE - mvc __THREAD_per_paid(1,%r14),__LC_PER_PAID + mvc __THREAD_per_cause(2,%r14),__LC_PER_CODE + mvc __THREAD_per_paid(1,%r14),__LC_PER_ACCESS_ID 0: REENABLE_IRQS xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) larl %r1,pgm_check_table @@ -440,10 +448,10 @@ pgm_kprobe: # 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 + lghi %r14,_PIF_SYSCALL | _PIF_PER_TRAP lpswe __LC_RETURN_PSW # branch to sysc_per and enable irqs /* @@ -457,7 +465,7 @@ ENTRY(io_int_handler) lg %r12,__LC_THREAD_INFO larl %r13,system_call lmg %r8,%r9,__LC_IO_OLD_PSW - HANDLE_SIE_INTERCEPT %r14,0 + HANDLE_SIE_INTERCEPT %r14,2 SWITCH_ASYNC __LC_SAVE_AREA_ASYNC,__LC_ASYNC_STACK,STACK_SHIFT tmhh %r8,0x0001 # interrupting from user? jz io_skip @@ -467,16 +475,32 @@ io_skip: stmg %r0,%r7,__PT_R0(%r11) mvc __PT_R8(64,%r11),__LC_SAVE_AREA_ASYNC stmg %r8,%r9,__PT_PSW(%r11) + mvc __PT_INT_CODE(12,%r11),__LC_SUBCHANNEL_ID + xc __PT_FLAGS(8,%r11),__PT_FLAGS(%r11) TRACE_IRQS_OFF xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) +io_loop: lgr %r2,%r11 # pass pointer to pt_regs + lghi %r3,IO_INTERRUPT + tm __PT_INT_CODE+8(%r11),0x80 # adapter interrupt ? + jz io_call + lghi %r3,THIN_INTERRUPT +io_call: brasl %r14,do_IRQ + tm __LC_MACHINE_FLAGS+6,0x10 # MACHINE_FLAG_LPAR + jz io_return + tpi 0 + jz io_return + mvc __PT_INT_CODE(12,%r11),__LC_SUBCHANNEL_ID + j io_loop io_return: LOCKDEP_SYS_EXIT TRACE_IRQS_ON io_tif: - tm __TI_flags+7(%r12),_TIF_WORK_INT + tm __TI_flags+7(%r12),_TIF_WORK jnz io_work # there is work to do (signals etc.) + tm __LC_CPU_FLAGS+7,_CIF_WORK + jnz io_work io_restore: lg %r14,__LC_VDSO_PER_CPU lmg %r0,%r10,__PT_R0(%r11) @@ -489,7 +513,7 @@ 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 +# 1) if we return to user space we can do all _TIF_WORK 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 @@ -526,7 +550,6 @@ io_work: # 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) @@ -534,11 +557,9 @@ io_work_user: # # 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 + tm __LC_CPU_FLAGS+7,_CIF_MCCK_PENDING jo io_mcck_pending tm __TI_flags+7(%r12),_TIF_NEED_RESCHED jo io_reschedule @@ -546,10 +567,12 @@ io_work_tif: jo io_sigpending tm __TI_flags+7(%r12),_TIF_NOTIFY_RESUME jo io_notify_resume + tm __LC_CPU_FLAGS+7,_CIF_ASCE + jo io_uaccess j io_return # beware of critical section cleanup # -# _TIF_MCCK_PENDING is set, call handler +# _CIF_MCCK_PENDING is set, call handler # io_mcck_pending: # TRACE_IRQS_ON already done at io_return @@ -558,6 +581,14 @@ io_mcck_pending: j io_return # +# _CIF_ASCE is set, load user space asce +# +io_uaccess: + ni __LC_CPU_FLAGS+7,255-_CIF_ASCE + lctlg %c1,%c1,__LC_USER_ASCE # load primary asce + j io_return + +# # _TIF_NEED_RESCHED is set, call schedule # io_reschedule: @@ -603,7 +634,7 @@ ENTRY(ext_int_handler) lg %r12,__LC_THREAD_INFO larl %r13,system_call lmg %r8,%r9,__LC_EXT_OLD_PSW - HANDLE_SIE_INTERCEPT %r14,0 + HANDLE_SIE_INTERCEPT %r14,3 SWITCH_ASYNC __LC_SAVE_AREA_ASYNC,__LC_ASYNC_STACK,STACK_SHIFT tmhh %r8,0x0001 # interrupting from user ? jz ext_skip @@ -613,14 +644,16 @@ ext_skip: stmg %r0,%r7,__PT_R0(%r11) mvc __PT_R8(64,%r11),__LC_SAVE_AREA_ASYNC stmg %r8,%r9,__PT_PSW(%r11) + lghi %r1,__LC_EXT_PARAMS2 + mvc __PT_INT_CODE(4,%r11),__LC_EXT_CPU_ADDR + mvc __PT_INT_PARM(4,%r11),__LC_EXT_PARAMS + mvc __PT_INT_PARM_LONG(8,%r11),0(%r1) + xc __PT_FLAGS(8,%r11),__PT_FLAGS(%r11) TRACE_IRQS_OFF xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) - 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 + lghi %r3,EXT_INTERRUPT + brasl %r14,do_IRQ j io_return /* @@ -651,7 +684,7 @@ ENTRY(mcck_int_handler) lg %r12,__LC_THREAD_INFO larl %r13,system_call lmg %r8,%r9,__LC_MCK_OLD_PSW - HANDLE_SIE_INTERCEPT %r14,0 + HANDLE_SIE_INTERCEPT %r14,4 tm __LC_MCCK_CODE,0x80 # system damage? jo mcck_panic # yes -> rest of mcck code invalid lghi %r14,__LC_CPU_TIMER_SAVE_AREA @@ -678,22 +711,23 @@ ENTRY(mcck_int_handler) 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) + lghi %r14,__LC_GPREGS_SAVE_AREA+64 + stmg %r0,%r7,__PT_R0(%r11) + mvc __PT_R8(64,%r11),0(%r14) stmg %r8,%r9,__PT_PSW(%r11) + xc __PT_FLAGS(8,%r11),__PT_FLAGS(%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 + tm __LC_CPU_FLAGS+7,_CIF_MCCK_PENDING jno mcck_return TRACE_IRQS_OFF brasl %r14,s390_handle_mcck @@ -754,14 +788,12 @@ ENTRY(restart_int_handler) * 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 + lg %r15,__LC_PANIC_STACK # change to panic stack + la %r11,STACK_FRAME_OVERHEAD(%r15) 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 @@ -845,15 +877,16 @@ cleanup_system_call: 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 + la %r9,STACK_FRAME_OVERHEAD(%r15) + stg %r9,24(%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 + mvc __PT_R8(64,%r9),__LC_SAVE_AREA_SYNC + stmg %r0,%r7,__PT_R0(%r9) + mvc __PT_PSW(16,%r9),__LC_SVC_OLD_PSW + mvc __PT_INT_CODE(4,%r9),__LC_SVC_ILC + xc __PT_FLAGS(8,%r9),__PT_FLAGS(%r9) + mvi __PT_FLAGS+7(%r9),_PIF_SYSCALL # 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 @@ -922,7 +955,7 @@ cleanup_idle: stg %r9,__LC_SYSTEM_TIMER mvc __LC_LAST_UPDATE_TIMER(8),__TIMER_IDLE_EXIT(%r2) # prepare return psw - nihh %r8,0xfffd # clear wait state bit + nihh %r8,0xfcfd # clear irq & wait state bits lg %r9,48(%r11) # return from psw_idle br %r14 cleanup_idle_insn: @@ -938,7 +971,7 @@ cleanup_idle_insn: .quad __critical_end - __critical_start -#if defined(CONFIG_KVM) || defined(CONFIG_KVM_MODULE) +#if IS_ENABLED(CONFIG_KVM) /* * sie64a calling convention: * %r2 pointer to sie control block @@ -948,56 +981,50 @@ 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 + xc __SF_EMPTY+16(16,%r15),__SF_EMPTY+16(%r15) # host id & reason lmg %r0,%r13,0(%r3) # load guest gprs 0-13 -# some program checks are suppressing. C code (e.g. do_protection_exception) -# will rewind the PSW by the ILC, which is 4 bytes in case of SIE. Other -# instructions in the sie_loop should not cause program interrupts. So -# lets use a nop (47 00 00 00) as a landing pad. -# See also HANDLE_SIE_INTERCEPT -rewind_pad: - nop 0 -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 + oi __SIE_PROG0C+3(%r14),1 # we are going into SIE now + tm __SIE_PROG20+3(%r14),1 # last exit... + jnz sie_done + LPP __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: + LPP __SF_EMPTY+16(%r15) # set host id + ni __SIE_PROG0C+3(%r14),0xfe # no longer in SIE lctlg %c1,%c1,__LC_USER_ASCE # load primary asce +# some program checks are suppressing. C code (e.g. do_protection_exception) +# will rewind the PSW by the ILC, which is 4 bytes in case of SIE. Other +# instructions between sie64a and sie_done should not cause program +# interrupts. So lets use a nop (47 00 00 00) as a landing pad. +# See also HANDLE_SIE_INTERCEPT +rewind_pad: + nop 0 + .globl sie_exit +sie_exit: 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 + lg %r2,__SF_EMPTY+24(%r15) # return exit reason code br %r14 sie_fault: - lctlg %c1,%c1,__LC_USER_ASCE # load primary asce - lg %r14,__LC_THREAD_INFO # pointer thread_info struct - 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 + lghi %r14,-EFAULT + stg %r14,__SF_EMPTY+24(%r15) # set exit reason code + j sie_exit .align 8 -.Lsie_loop: - .quad sie_loop -.Lsie_length: - .quad sie_done - sie_loop -.Lhost_id: - .quad 0 +.Lsie_critical: + .quad sie_gmap +.Lsie_critical_length: + .quad sie_done - sie_gmap EX_TABLE(rewind_pad,sie_fault) - EX_TABLE(sie_loop,sie_fault) + EX_TABLE(sie_exit,sie_fault) #endif .section .rodata, "a" @@ -1010,6 +1037,7 @@ sys_call_table: #ifdef CONFIG_COMPAT #define SYSCALL(esa,esame,emu) .long emu + .globl sys_call_table_emu sys_call_table_emu: #include "syscalls.S" #undef SYSCALL diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c index 78bdf0e5dff..54d6493c4a5 100644 --- a/arch/s390/kernel/ftrace.c +++ b/arch/s390/kernel/ftrace.c @@ -15,12 +15,7 @@ #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 +#include "entry.h" #ifdef CONFIG_DYNAMIC_FTRACE @@ -135,9 +130,8 @@ int ftrace_update_ftrace_func(ftrace_func_t func) return 0; } -int __init ftrace_dyn_arch_init(void *data) +int __init ftrace_dyn_arch_init(void) { - *(unsigned long *) data = 0; return 0; } @@ -155,14 +149,14 @@ unsigned long __kprobes prepare_ftrace_return(unsigned long parent, 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; + ip = (ip & PSW_ADDR_INSN) - MCOUNT_INSN_SIZE; + trace.func = ip; + trace.depth = current->curr_ret_stack + 1; /* Only trace if the calling function expects to. */ - if (!ftrace_graph_entry(&trace)) { - current->curr_ret_stack--; + if (!ftrace_graph_entry(&trace)) + goto out; + if (ftrace_push_return_trace(parent, ip, &trace.depth, 0) == -EBUSY) goto out; - } parent = (unsigned long) return_to_handler; out: return parent; @@ -182,7 +176,7 @@ int ftrace_enable_ftrace_graph_caller(void) offset = ((void *) prepare_ftrace_return - (void *) ftrace_graph_caller) / 2; - return probe_kernel_write(ftrace_graph_caller + 2, + return probe_kernel_write((void *) ftrace_graph_caller + 2, &offset, sizeof(offset)); } @@ -190,7 +184,7 @@ int ftrace_disable_ftrace_graph_caller(void) { static unsigned short offset = 0x0002; - return probe_kernel_write(ftrace_graph_caller + 2, + return probe_kernel_write((void *) ftrace_graph_caller + 2, &offset, sizeof(offset)); } diff --git a/arch/s390/kernel/head.S b/arch/s390/kernel/head.S index fd8db63dfc9..e88d35d7495 100644 --- a/arch/s390/kernel/head.S +++ b/arch/s390/kernel/head.S @@ -437,13 +437,13 @@ ENTRY(startup_kdump) #if defined(CONFIG_64BIT) #if defined(CONFIG_MARCH_ZEC12) - .long 3, 0xc100efe3, 0xf46ce000, 0x00400000 + .long 3, 0xc100eff2, 0xf46ce800, 0x00400000 #elif defined(CONFIG_MARCH_Z196) - .long 2, 0xc100efe3, 0xf46c0000 + .long 2, 0xc100eff2, 0xf46c0000 #elif defined(CONFIG_MARCH_Z10) - .long 2, 0xc100efe3, 0xf0680000 + .long 2, 0xc100eff2, 0xf0680000 #elif defined(CONFIG_MARCH_Z9_109) - .long 1, 0xc100efc3 + .long 1, 0xc100efc2 #elif defined(CONFIG_MARCH_Z990) .long 1, 0xc0002000 #elif defined(CONFIG_MARCH_Z900) diff --git a/arch/s390/kernel/head31.S b/arch/s390/kernel/head31.S index 9a99856df1c..6dbe80983a2 100644 --- a/arch/s390/kernel/head31.S +++ b/arch/s390/kernel/head31.S @@ -59,7 +59,6 @@ ENTRY(startup_continue) .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 diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S index b9e25ae2579..d7c00507568 100644 --- a/arch/s390/kernel/head64.S +++ b/arch/s390/kernel/head64.S @@ -59,7 +59,7 @@ ENTRY(startup_continue) .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 + .quad .Llinkage_stack # cr15: linkage stack operations .Lpcmsk:.quad 0x0000000180000000 .L4malign:.quad 0xffffffffffc00000 .Lscan2g:.quad 0x80000000 + 0x20000 - 8 # 2GB + 128K - 8 @@ -67,12 +67,15 @@ ENTRY(startup_continue) .Lparmaddr: .quad PARMAREA .align 64 -.Lduct: .long 0,0,0,0,.Lduald,0,0,0 +.Lduct: .long 0,.Laste,.Laste,0,.Lduald,0,0,0 .long 0,0,0,0,0,0,0,0 +.Laste: .quad 0,0xffffffffffffffff,0,0,0,0,0,0 .align 128 .Lduald:.rept 8 .long 0x80000000,0,0,0 # invalid access-list entries .endr +.Llinkage_stack: + .long 0,0,0x89000000,0,0,0,0x8a000000,0 ENTRY(_ehead) diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index 6ffcd320321..633ca750453 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -754,9 +754,9 @@ static struct bin_attribute sys_reipl_fcp_scp_data_attr = { .write = reipl_fcp_scpdata_write, }; -DEFINE_IPL_ATTR_RW(reipl_fcp, wwpn, "0x%016llx\n", "%016llx\n", +DEFINE_IPL_ATTR_RW(reipl_fcp, wwpn, "0x%016llx\n", "%llx\n", reipl_block_fcp->ipl_info.fcp.wwpn); -DEFINE_IPL_ATTR_RW(reipl_fcp, lun, "0x%016llx\n", "%016llx\n", +DEFINE_IPL_ATTR_RW(reipl_fcp, lun, "0x%016llx\n", "%llx\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); @@ -1323,9 +1323,9 @@ static struct shutdown_action __refdata reipl_action = { /* FCP dump device attributes */ -DEFINE_IPL_ATTR_RW(dump_fcp, wwpn, "0x%016llx\n", "%016llx\n", +DEFINE_IPL_ATTR_RW(dump_fcp, wwpn, "0x%016llx\n", "%llx\n", dump_block_fcp->ipl_info.fcp.wwpn); -DEFINE_IPL_ATTR_RW(dump_fcp, lun, "0x%016llx\n", "%016llx\n", +DEFINE_IPL_ATTR_RW(dump_fcp, lun, "0x%016llx\n", "%llx\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); @@ -1414,6 +1414,16 @@ static struct kobj_attribute dump_type_attr = static struct kset *dump_kset; +static void diag308_dump(void *dump_block) +{ + diag308(DIAG308_SET, dump_block); + while (1) { + if (diag308(DIAG308_DUMP, NULL) != 0x302) + break; + udelay_simple(USEC_PER_SEC); + } +} + static void __dump_run(void *unused) { struct ccw_dev_id devid; @@ -1432,12 +1442,10 @@ static void __dump_run(void *unused) __cpcmd(buf, NULL, 0, NULL); break; case DUMP_METHOD_CCW_DIAG: - diag308(DIAG308_SET, dump_block_ccw); - diag308(DIAG308_DUMP, NULL); + diag308_dump(dump_block_ccw); break; case DUMP_METHOD_FCP_DIAG: - diag308(DIAG308_SET, dump_block_fcp); - diag308(DIAG308_DUMP, NULL); + diag308_dump(dump_block_fcp); break; default: break; @@ -2043,12 +2051,12 @@ void s390_reset_system(void (*func)(void *), void *data) __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.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.mask = PSW_KERNEL_BITS | PSW_MASK_DAT; S390_lowcore.program_new_psw.addr = PSW_ADDR_AMODE | (unsigned long) s390_base_pgm_handler; diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c index 9df824ea166..99b0b09646c 100644 --- a/arch/s390/kernel/irq.c +++ b/arch/s390/kernel/irq.c @@ -18,10 +18,12 @@ #include <linux/errno.h> #include <linux/slab.h> #include <linux/cpu.h> +#include <linux/irq.h> #include <asm/irq_regs.h> #include <asm/cputime.h> #include <asm/lowcore.h> #include <asm/irq.h> +#include <asm/hw_irq.h> #include "entry.h" DEFINE_PER_CPU_SHARED_ALIGNED(struct irq_stat, irq_stat); @@ -33,7 +35,7 @@ struct irq_class { }; /* - * The list of "main" irq classes on s390. This is the list of interrrupts + * The list of "main" irq classes on s390. This is the list of interrupts * that appear both in /proc/stat ("intr" line) and /proc/interrupts. * Historically only external and I/O interrupts have been part of /proc/stat. * We can't add the split external and I/O sub classes since the first field @@ -42,9 +44,10 @@ struct irq_class { * Since the external and I/O interrupt fields are already sums we would end * up with having a sum which accounts each interrupt twice. */ -static const struct irq_class irqclass_main_desc[NR_IRQS] = { - [EXTERNAL_INTERRUPT] = {.name = "EXT"}, - [IO_INTERRUPT] = {.name = "I/O"} +static const struct irq_class irqclass_main_desc[NR_IRQS_BASE] = { + [EXT_INTERRUPT] = {.name = "EXT"}, + [IO_INTERRUPT] = {.name = "I/O"}, + [THIN_INTERRUPT] = {.name = "AIO"}, }; /* @@ -81,10 +84,33 @@ static const struct irq_class irqclass_sub_desc[NR_ARCH_IRQS] = { [IRQIO_CSC] = {.name = "CSC", .desc = "[I/O] CHSC Subchannel"}, [IRQIO_PCI] = {.name = "PCI", .desc = "[I/O] PCI Interrupt" }, [IRQIO_MSI] = {.name = "MSI", .desc = "[I/O] MSI Interrupt" }, + [IRQIO_VIR] = {.name = "VIR", .desc = "[I/O] Virtual I/O Devices"}, + [IRQIO_VAI] = {.name = "VAI", .desc = "[I/O] Virtual I/O Devices AI"}, [NMI_NMI] = {.name = "NMI", .desc = "[NMI] Machine Check"}, [CPU_RST] = {.name = "RST", .desc = "[CPU] CPU Restart"}, }; +void __init init_IRQ(void) +{ + init_cio_interrupts(); + init_airq_interrupts(); + init_ext_interrupts(); +} + +void do_IRQ(struct pt_regs *regs, int irq) +{ + struct pt_regs *old_regs; + + old_regs = set_irq_regs(regs); + irq_enter(); + if (S390_lowcore.int_clock >= S390_lowcore.clock_comparator) + /* Serve timer interrupts first. */ + clock_comparator_work(); + generic_handle_irq(irq); + irq_exit(); + set_irq_regs(old_regs); +} + /* * show_interrupts is needed by /proc/interrupts. */ @@ -99,105 +125,88 @@ int show_interrupts(struct seq_file *p, void *v) for_each_online_cpu(cpu) seq_printf(p, "CPU%d ", cpu); seq_putc(p, '\n'); + goto out; } if (irq < NR_IRQS) { + if (irq >= NR_IRQS_BASE) + goto out; seq_printf(p, "%s: ", irqclass_main_desc[irq].name); for_each_online_cpu(cpu) - seq_printf(p, "%10u ", kstat_cpu(cpu).irqs[irq]); + seq_printf(p, "%10u ", kstat_irqs_cpu(irq, cpu)); seq_putc(p, '\n'); - goto skip_arch_irqs; + goto out; } for (irq = 0; irq < NR_ARCH_IRQS; irq++) { seq_printf(p, "%s: ", irqclass_sub_desc[irq].name); for_each_online_cpu(cpu) - seq_printf(p, "%10u ", per_cpu(irq_stat, cpu).irqs[irq]); + seq_printf(p, "%10u ", + per_cpu(irq_stat, cpu).irqs[irq]); if (irqclass_sub_desc[irq].desc) seq_printf(p, " %s", irqclass_sub_desc[irq].desc); seq_putc(p, '\n'); } -skip_arch_irqs: +out: put_online_cpus(); return 0; } +unsigned int arch_dynirq_lower_bound(unsigned int from) +{ + return from < THIN_INTERRUPT ? THIN_INTERRUPT : from; +} + /* * Switch to the asynchronous interrupt stack for softirq execution. */ -asmlinkage void do_softirq(void) +void do_softirq_own_stack(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(); - } + unsigned long old, new; + + /* 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]; +static struct hlist_head ext_int_hash[32] ____cacheline_aligned; struct ext_int_info { ext_int_handler_t handler; - u16 code; - struct list_head entry; + struct hlist_node entry; struct rcu_head rcu; + u16 code; }; /* 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 DEFINE_SPINLOCK(ext_int_hash_lock); static inline int ext_hash(u16 code) { - return (code + (code >> 9)) & 0xff; + BUILD_BUG_ON(!is_power_of_2(ARRAY_SIZE(ext_int_hash))); + + return (code + (code >> 9)) & (ARRAY_SIZE(ext_int_hash) - 1); } -int register_external_interrupt(u16 code, ext_int_handler_t handler) +int register_external_irq(u16 code, ext_int_handler_t handler) { struct ext_int_info *p; unsigned long flags; @@ -211,104 +220,88 @@ int register_external_interrupt(u16 code, ext_int_handler_t handler) index = ext_hash(code); spin_lock_irqsave(&ext_int_hash_lock, flags); - list_add_rcu(&p->entry, &ext_int_hash[index]); + hlist_add_head_rcu(&p->entry, &ext_int_hash[index]); spin_unlock_irqrestore(&ext_int_hash_lock, flags); return 0; } -EXPORT_SYMBOL(register_external_interrupt); +EXPORT_SYMBOL(register_external_irq); -int unregister_external_interrupt(u16 code, ext_int_handler_t handler) +int unregister_external_irq(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) { + hlist_for_each_entry_rcu(p, &ext_int_hash[index], entry) { if (p->code == code && p->handler == handler) { - list_del_rcu(&p->entry); + hlist_del_rcu(&p->entry); kfree_rcu(p, rcu); } } spin_unlock_irqrestore(&ext_int_hash_lock, flags); return 0; } -EXPORT_SYMBOL(unregister_external_interrupt); +EXPORT_SYMBOL(unregister_external_irq); -void __irq_entry do_extint(struct pt_regs *regs, struct ext_code ext_code, - unsigned int param32, unsigned long param64) +static irqreturn_t do_ext_interrupt(int irq, void *dummy) { - struct pt_regs *old_regs; + struct pt_regs *regs = get_irq_regs(); + struct ext_code ext_code; 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_incr_irqs_this_cpu(EXTERNAL_INTERRUPT, NULL); - if (ext_code.code != 0x1004) + ext_code = *(struct ext_code *) ®s->int_code; + if (ext_code.code != EXT_IRQ_CLK_COMP) __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); + hlist_for_each_entry_rcu(p, &ext_int_hash[index], entry) { + if (unlikely(p->code != ext_code.code)) + continue; + p->handler(ext_code, regs->int_parm, regs->int_parm_long); + } rcu_read_unlock(); - irq_exit(); - set_irq_regs(old_regs); -} - -void __init init_IRQ(void) -{ - init_external_interrupts(); + return IRQ_HANDLED; } -static DEFINE_SPINLOCK(sc_irq_lock); -static int sc_irq_refcount; +static struct irqaction external_interrupt = { + .name = "EXT", + .handler = do_ext_interrupt, +}; -void service_subclass_irq_register(void) +void __init init_ext_interrupts(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); + int idx; -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); + for (idx = 0; idx < ARRAY_SIZE(ext_int_hash); idx++) + INIT_HLIST_HEAD(&ext_int_hash[idx]); + + irq_set_chip_and_handler(EXT_INTERRUPT, + &dummy_irq_chip, handle_percpu_irq); + setup_irq(EXT_INTERRUPT, &external_interrupt); } -EXPORT_SYMBOL(service_subclass_irq_unregister); -static DEFINE_SPINLOCK(ma_subclass_lock); -static int ma_subclass_refcount; +static DEFINE_SPINLOCK(irq_subclass_lock); +static unsigned char irq_subclass_refcount[64]; -void measurement_alert_subclass_register(void) +void irq_subclass_register(enum irq_subclass subclass) { - spin_lock(&ma_subclass_lock); - if (!ma_subclass_refcount) - ctl_set_bit(0, 5); - ma_subclass_refcount++; - spin_unlock(&ma_subclass_lock); + spin_lock(&irq_subclass_lock); + if (!irq_subclass_refcount[subclass]) + ctl_set_bit(0, subclass); + irq_subclass_refcount[subclass]++; + spin_unlock(&irq_subclass_lock); } -EXPORT_SYMBOL(measurement_alert_subclass_register); +EXPORT_SYMBOL(irq_subclass_register); -void measurement_alert_subclass_unregister(void) +void irq_subclass_unregister(enum irq_subclass subclass) { - spin_lock(&ma_subclass_lock); - ma_subclass_refcount--; - if (!ma_subclass_refcount) - ctl_clear_bit(0, 5); - spin_unlock(&ma_subclass_lock); + spin_lock(&irq_subclass_lock); + irq_subclass_refcount[subclass]--; + if (!irq_subclass_refcount[subclass]) + ctl_clear_bit(0, subclass); + spin_unlock(&irq_subclass_lock); } -EXPORT_SYMBOL(measurement_alert_subclass_unregister); +EXPORT_SYMBOL(irq_subclass_unregister); diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c index d1c7214e157..bc71a7b95af 100644 --- a/arch/s390/kernel/kprobes.c +++ b/arch/s390/kernel/kprobes.c @@ -26,19 +26,42 @@ #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> +#include <asm/cacheflush.h> +#include <asm/sections.h> +#include <asm/dis.h> DEFINE_PER_CPU(struct kprobe *, current_kprobe); DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk); struct kretprobe_blackpoint kretprobe_blacklist[] = { }; +DEFINE_INSN_CACHE_OPS(dmainsn); + +static void *alloc_dmainsn_page(void) +{ + return (void *)__get_free_page(GFP_KERNEL | GFP_DMA); +} + +static void free_dmainsn_page(void *page) +{ + free_page((unsigned long)page); +} + +struct kprobe_insn_cache kprobe_dmainsn_slots = { + .mutex = __MUTEX_INITIALIZER(kprobe_dmainsn_slots.mutex), + .alloc = alloc_dmainsn_page, + .free = free_dmainsn_page, + .pages = LIST_HEAD_INIT(kprobe_dmainsn_slots.pages), + .insn_size = MAX_INSN_SIZE, +}; + static int __kprobes is_prohibited_opcode(kprobe_opcode_t *insn) { + if (!is_known_insn((unsigned char *)insn)) + return -EINVAL; switch (insn[0] >> 8) { case 0x0c: /* bassm */ case 0x0b: /* bsm */ @@ -47,6 +70,11 @@ static int __kprobes is_prohibited_opcode(kprobe_opcode_t *insn) case 0xac: /* stnsm */ case 0xad: /* stosm */ return -EINVAL; + case 0xc6: + switch (insn[0] & 0x0f) { + case 0x00: /* exrl */ + return -EINVAL; + } } switch (insn[0]) { case 0x0101: /* pr */ @@ -100,35 +128,160 @@ static int __kprobes get_fixup_type(kprobe_opcode_t *insn) fixup |= FIXUP_RETURN_REGISTER; break; case 0xc0: - if ((insn[0] & 0x0f) == 0x00 || /* larl */ - (insn[0] & 0x0f) == 0x05) /* brasl */ - fixup |= FIXUP_RETURN_REGISTER; + if ((insn[0] & 0x0f) == 0x05) /* brasl */ + fixup |= FIXUP_RETURN_REGISTER; break; case 0xeb: - if ((insn[2] & 0xff) == 0x44 || /* bxhg */ - (insn[2] & 0xff) == 0x45) /* bxleg */ + switch (insn[2] & 0xff) { + case 0x44: /* bxhg */ + case 0x45: /* bxleg */ fixup = FIXUP_BRANCH_NOT_TAKEN; + break; + } break; case 0xe3: /* bctg */ if ((insn[2] & 0xff) == 0x46) fixup = FIXUP_BRANCH_NOT_TAKEN; break; + case 0xec: + switch (insn[2] & 0xff) { + case 0xe5: /* clgrb */ + case 0xe6: /* cgrb */ + case 0xf6: /* crb */ + case 0xf7: /* clrb */ + case 0xfc: /* cgib */ + case 0xfd: /* cglib */ + case 0xfe: /* cib */ + case 0xff: /* clib */ + fixup = FIXUP_BRANCH_NOT_TAKEN; + break; + } + break; } return fixup; } +static int __kprobes is_insn_relative_long(kprobe_opcode_t *insn) +{ + /* Check if we have a RIL-b or RIL-c format instruction which + * we need to modify in order to avoid instruction emulation. */ + switch (insn[0] >> 8) { + case 0xc0: + if ((insn[0] & 0x0f) == 0x00) /* larl */ + return true; + break; + case 0xc4: + switch (insn[0] & 0x0f) { + case 0x02: /* llhrl */ + case 0x04: /* lghrl */ + case 0x05: /* lhrl */ + case 0x06: /* llghrl */ + case 0x07: /* sthrl */ + case 0x08: /* lgrl */ + case 0x0b: /* stgrl */ + case 0x0c: /* lgfrl */ + case 0x0d: /* lrl */ + case 0x0e: /* llgfrl */ + case 0x0f: /* strl */ + return true; + } + break; + case 0xc6: + switch (insn[0] & 0x0f) { + case 0x02: /* pfdrl */ + case 0x04: /* cghrl */ + case 0x05: /* chrl */ + case 0x06: /* clghrl */ + case 0x07: /* clhrl */ + case 0x08: /* cgrl */ + case 0x0a: /* clgrl */ + case 0x0c: /* cgfrl */ + case 0x0d: /* crl */ + case 0x0e: /* clgfrl */ + case 0x0f: /* clrl */ + return true; + } + break; + } + return false; +} + +static void __kprobes copy_instruction(struct kprobe *p) +{ + s64 disp, new_disp; + u64 addr, new_addr; + + memcpy(p->ainsn.insn, p->addr, insn_length(p->opcode >> 8)); + if (!is_insn_relative_long(p->ainsn.insn)) + return; + /* + * For pc-relative instructions in RIL-b or RIL-c format patch the + * RI2 displacement field. We have already made sure that the insn + * slot for the patched instruction is within the same 2GB area + * as the original instruction (either kernel image or module area). + * Therefore the new displacement will always fit. + */ + disp = *(s32 *)&p->ainsn.insn[1]; + addr = (u64)(unsigned long)p->addr; + new_addr = (u64)(unsigned long)p->ainsn.insn; + new_disp = ((addr + (disp * 2)) - new_addr) / 2; + *(s32 *)&p->ainsn.insn[1] = new_disp; +} + +static inline int is_kernel_addr(void *addr) +{ + return addr < (void *)_end; +} + +static inline int is_module_addr(void *addr) +{ +#ifdef CONFIG_64BIT + BUILD_BUG_ON(MODULES_LEN > (1UL << 31)); + if (addr < (void *)MODULES_VADDR) + return 0; + if (addr > (void *)MODULES_END) + return 0; +#endif + return 1; +} + +static int __kprobes s390_get_insn_slot(struct kprobe *p) +{ + /* + * Get an insn slot that is within the same 2GB area like the original + * instruction. That way instructions with a 32bit signed displacement + * field can be patched and executed within the insn slot. + */ + p->ainsn.insn = NULL; + if (is_kernel_addr(p->addr)) + p->ainsn.insn = get_dmainsn_slot(); + else if (is_module_addr(p->addr)) + p->ainsn.insn = get_insn_slot(); + return p->ainsn.insn ? 0 : -ENOMEM; +} + +static void __kprobes s390_free_insn_slot(struct kprobe *p) +{ + if (!p->ainsn.insn) + return; + if (is_kernel_addr(p->addr)) + free_dmainsn_slot(p->ainsn.insn, 0); + else + free_insn_slot(p->ainsn.insn, 0); + p->ainsn.insn = NULL; +} + 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; - + if (s390_get_insn_slot(p)) + return -ENOMEM; p->opcode = *p->addr; - memcpy(p->ainsn.insn, p->addr, ((p->opcode >> 14) + 3) & -2); - + copy_instruction(p); return 0; } @@ -169,6 +322,7 @@ void __kprobes arch_disarm_kprobe(struct kprobe *p) void __kprobes arch_remove_kprobe(struct kprobe *p) { + s390_free_insn_slot(p); } static void __kprobes enable_singlestep(struct kprobe_ctlblk *kcb, @@ -354,7 +508,7 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p, { struct kretprobe_instance *ri; struct hlist_head *head, empty_rp; - struct hlist_node *node, *tmp; + struct hlist_node *tmp; unsigned long flags, orig_ret_address; unsigned long trampoline_address; kprobe_opcode_t *correct_ret_addr; @@ -379,7 +533,7 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p, orig_ret_address = 0; correct_ret_addr = NULL; trampoline_address = (unsigned long) &kretprobe_trampoline; - hlist_for_each_entry_safe(ri, node, tmp, head, hlist) { + hlist_for_each_entry_safe(ri, tmp, head, hlist) { if (ri->task != current) /* another task is sharing our hash bucket */ continue; @@ -398,7 +552,7 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p, kretprobe_assert(ri, orig_ret_address, trampoline_address); correct_ret_addr = ri->ret_addr; - hlist_for_each_entry_safe(ri, node, tmp, head, hlist) { + hlist_for_each_entry_safe(ri, tmp, head, hlist) { if (ri->task != current) /* another task is sharing our hash bucket */ continue; @@ -427,7 +581,7 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p, kretprobe_hash_unlock(current, &flags); preempt_enable_no_resched(); - hlist_for_each_entry_safe(ri, node, tmp, &empty_rp, hlist) { + hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) { hlist_del(&ri->hlist); kfree(ri); } @@ -457,7 +611,7 @@ static void __kprobes resume_execution(struct kprobe *p, struct pt_regs *regs) 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; + int ilen = insn_length(p->ainsn.insn[0] >> 8); if (ip - (unsigned long) p->ainsn.insn == ilen) ip = (unsigned long) p->addr + ilen; } @@ -526,7 +680,7 @@ static int __kprobes kprobe_trap_handler(struct pt_regs *regs, int trapnr) case KPROBE_HIT_SSDONE: /* * We increment the nmissed count for accounting, - * we can also use npre/npostfault count for accouting + * we can also use npre/npostfault count for accounting * these specific fault cases. */ kprobes_inc_nmissed_count(p); diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c index b3de2770001..719e27b2cf2 100644 --- a/arch/s390/kernel/machine_kexec.c +++ b/arch/s390/kernel/machine_kexec.c @@ -13,6 +13,7 @@ #include <linux/reboot.h> #include <linux/ftrace.h> #include <linux/debug_locks.h> +#include <linux/suspend.h> #include <asm/cio.h> #include <asm/setup.h> #include <asm/pgtable.h> @@ -49,7 +50,7 @@ static void add_elf_notes(int cpu) /* * Initialize CPU ELF notes */ -void setup_regs(void) +static void setup_regs(void) { unsigned long sa = S390_lowcore.prefixreg_save_area + SAVE_AREA_BASE; int cpu, this_cpu; @@ -67,6 +68,35 @@ void setup_regs(void) memcpy((void *) SAVE_AREA_BASE, (void *) sa, sizeof(struct save_area)); } +/* + * PM notifier callback for kdump + */ +static int machine_kdump_pm_cb(struct notifier_block *nb, unsigned long action, + void *ptr) +{ + switch (action) { + case PM_SUSPEND_PREPARE: + case PM_HIBERNATION_PREPARE: + if (crashk_res.start) + crash_map_reserved_pages(); + break; + case PM_POST_SUSPEND: + case PM_POST_HIBERNATION: + if (crashk_res.start) + crash_unmap_reserved_pages(); + break; + default: + return NOTIFY_DONE; + } + return NOTIFY_OK; +} + +static int __init machine_kdump_pm_init(void) +{ + pm_notifier(machine_kdump_pm_cb, 0); + return 0; +} +arch_initcall(machine_kdump_pm_init); #endif /* diff --git a/arch/s390/kernel/mcount.S b/arch/s390/kernel/mcount.S index 4567ce20d90..08dcf21cb8d 100644 --- a/arch/s390/kernel/mcount.S +++ b/arch/s390/kernel/mcount.S @@ -7,6 +7,7 @@ #include <linux/linkage.h> #include <asm/asm-offsets.h> +#include <asm/ftrace.h> .section .kprobes.text, "ax" @@ -33,6 +34,7 @@ ENTRY(ftrace_caller) la %r2,0(%r14) st %r0,__SF_BACKCHAIN(%r15) la %r3,0(%r3) + ahi %r2,-MCOUNT_INSN_SIZE l %r14,0b-0b(%r1) l %r14,0(%r14) basr %r14,%r14 diff --git a/arch/s390/kernel/mcount64.S b/arch/s390/kernel/mcount64.S index 11332193db3..1c52eae3396 100644 --- a/arch/s390/kernel/mcount64.S +++ b/arch/s390/kernel/mcount64.S @@ -7,6 +7,7 @@ #include <linux/linkage.h> #include <asm/asm-offsets.h> +#include <asm/ftrace.h> .section .kprobes.text, "ax" @@ -29,6 +30,7 @@ ENTRY(ftrace_caller) stg %r1,__SF_BACKCHAIN(%r15) lgr %r2,%r14 lg %r3,168(%r15) + aghi %r2,-MCOUNT_INSN_SIZE larl %r14,ftrace_trace_function lg %r14,0(%r14) basr %r14,%r14 diff --git a/arch/s390/kernel/mem_detect.c b/arch/s390/kernel/mem_detect.c deleted file mode 100644 index 22d502e885e..00000000000 --- a/arch/s390/kernel/mem_detect.c +++ /dev/null @@ -1,145 +0,0 @@ -/* - * 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 index 4610deafd95..b89b59158b9 100644 --- a/arch/s390/kernel/module.c +++ b/arch/s390/kernel/module.c @@ -50,7 +50,7 @@ void *module_alloc(unsigned long size) if (PAGE_ALIGN(size) > MODULES_LEN) return NULL; return __vmalloc_node_range(size, 1, MODULES_VADDR, MODULES_END, - GFP_KERNEL, PAGE_KERNEL, -1, + GFP_KERNEL, PAGE_KERNEL, NUMA_NO_NODE, __builtin_return_address(0)); } #endif @@ -65,8 +65,7 @@ void module_free(struct module *mod, void *module_region) vfree(module_region); } -static void -check_rela(Elf_Rela *rela, struct module *me) +static void check_rela(Elf_Rela *rela, struct module *me) { struct mod_arch_syminfo *info; @@ -115,9 +114,8 @@ check_rela(Elf_Rela *rela, struct module *me) * 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) +int module_frob_arch_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs, + char *secstrings, struct module *me) { Elf_Shdr *symtab; Elf_Sym *symbols; @@ -179,13 +177,52 @@ module_frob_arch_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs, return 0; } -static int -apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab, - struct module *me) +static int apply_rela_bits(Elf_Addr loc, Elf_Addr val, + int sign, int bits, int shift) +{ + unsigned long umax; + long min, max; + + if (val & ((1UL << shift) - 1)) + return -ENOEXEC; + if (sign) { + val = (Elf_Addr)(((long) val) >> shift); + min = -(1L << (bits - 1)); + max = (1L << (bits - 1)) - 1; + if ((long) val < min || (long) val > max) + return -ENOEXEC; + } else { + val >>= shift; + umax = ((1UL << (bits - 1)) << 1) - 1; + if ((unsigned long) val > umax) + return -ENOEXEC; + } + + if (bits == 8) + *(unsigned char *) loc = val; + else if (bits == 12) + *(unsigned short *) loc = (val & 0xfff) | + (*(unsigned short *) loc & 0xf000); + else if (bits == 16) + *(unsigned short *) loc = val; + else if (bits == 20) + *(unsigned int *) loc = (val & 0xfff) << 16 | + (val & 0xff000) >> 4 | + (*(unsigned int *) loc & 0xf00000ff); + else if (bits == 32) + *(unsigned int *) loc = val; + else if (bits == 64) + *(unsigned long *) loc = val; + return 0; +} + +static int apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab, + const char *strtab, struct module *me) { struct mod_arch_syminfo *info; Elf_Addr loc, val; int r_type, r_sym; + int rc = -ENOEXEC; /* This is where to make the change */ loc = base + rela->r_offset; @@ -197,6 +234,9 @@ apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab, val = symtab[r_sym].st_value; switch (r_type) { + case R_390_NONE: /* No relocation. */ + rc = 0; + break; case R_390_8: /* Direct 8 bit. */ case R_390_12: /* Direct 12 bit. */ case R_390_16: /* Direct 16 bit. */ @@ -205,20 +245,17 @@ apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab, case R_390_64: /* Direct 64 bit. */ val += rela->r_addend; if (r_type == R_390_8) - *(unsigned char *) loc = val; + rc = apply_rela_bits(loc, val, 0, 8, 0); else if (r_type == R_390_12) - *(unsigned short *) loc = (val & 0xfff) | - (*(unsigned short *) loc & 0xf000); + rc = apply_rela_bits(loc, val, 0, 12, 0); else if (r_type == R_390_16) - *(unsigned short *) loc = val; + rc = apply_rela_bits(loc, val, 0, 16, 0); else if (r_type == R_390_20) - *(unsigned int *) loc = - (*(unsigned int *) loc & 0xf00000ff) | - (val & 0xfff) << 16 | (val & 0xff000) >> 4; + rc = apply_rela_bits(loc, val, 1, 20, 0); else if (r_type == R_390_32) - *(unsigned int *) loc = val; + rc = apply_rela_bits(loc, val, 0, 32, 0); else if (r_type == R_390_64) - *(unsigned long *) loc = val; + rc = apply_rela_bits(loc, val, 0, 64, 0); break; case R_390_PC16: /* PC relative 16 bit. */ case R_390_PC16DBL: /* PC relative 16 bit shifted by 1. */ @@ -227,15 +264,15 @@ apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab, case R_390_PC64: /* PC relative 64 bit. */ val += rela->r_addend - loc; if (r_type == R_390_PC16) - *(unsigned short *) loc = val; + rc = apply_rela_bits(loc, val, 1, 16, 0); else if (r_type == R_390_PC16DBL) - *(unsigned short *) loc = val >> 1; + rc = apply_rela_bits(loc, val, 1, 16, 1); else if (r_type == R_390_PC32DBL) - *(unsigned int *) loc = val >> 1; + rc = apply_rela_bits(loc, val, 1, 32, 1); else if (r_type == R_390_PC32) - *(unsigned int *) loc = val; + rc = apply_rela_bits(loc, val, 1, 32, 0); else if (r_type == R_390_PC64) - *(unsigned long *) loc = val; + rc = apply_rela_bits(loc, val, 1, 64, 0); break; case R_390_GOT12: /* 12 bit GOT offset. */ case R_390_GOT16: /* 16 bit GOT offset. */ @@ -260,26 +297,24 @@ apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab, 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); + rc = apply_rela_bits(loc, val, 0, 12, 0); else if (r_type == R_390_GOT16 || r_type == R_390_GOTPLT16) - *(unsigned short *) loc = val; + rc = apply_rela_bits(loc, val, 0, 16, 0); 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; + rc = apply_rela_bits(loc, val, 1, 20, 0); 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; + rc = apply_rela_bits(loc, val, 0, 32, 0); else if (r_type == R_390_GOT64 || r_type == R_390_GOTPLT64) - *(unsigned long *) loc = val; + rc = apply_rela_bits(loc, val, 0, 64, 0); + else if (r_type == R_390_GOTENT || + r_type == R_390_GOTPLTENT) { + val += (Elf_Addr) me->module_core - loc; + rc = apply_rela_bits(loc, val, 1, 32, 1); + } 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. */ @@ -321,17 +356,17 @@ apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab, val += rela->r_addend - loc; } if (r_type == R_390_PLT16DBL) - *(unsigned short *) loc = val >> 1; + rc = apply_rela_bits(loc, val, 1, 16, 1); else if (r_type == R_390_PLTOFF16) - *(unsigned short *) loc = val; + rc = apply_rela_bits(loc, val, 0, 16, 0); else if (r_type == R_390_PLT32DBL) - *(unsigned int *) loc = val >> 1; + rc = apply_rela_bits(loc, val, 1, 32, 1); else if (r_type == R_390_PLT32 || r_type == R_390_PLTOFF32) - *(unsigned int *) loc = val; + rc = apply_rela_bits(loc, val, 0, 32, 0); else if (r_type == R_390_PLT64 || r_type == R_390_PLTOFF64) - *(unsigned long *) loc = val; + rc = apply_rela_bits(loc, val, 0, 64, 0); break; case R_390_GOTOFF16: /* 16 bit offset to GOT. */ case R_390_GOTOFF32: /* 32 bit offset to GOT. */ @@ -339,20 +374,20 @@ apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab, val = val + rela->r_addend - ((Elf_Addr) me->module_core + me->arch.got_offset); if (r_type == R_390_GOTOFF16) - *(unsigned short *) loc = val; + rc = apply_rela_bits(loc, val, 0, 16, 0); else if (r_type == R_390_GOTOFF32) - *(unsigned int *) loc = val; + rc = apply_rela_bits(loc, val, 0, 32, 0); else if (r_type == R_390_GOTOFF64) - *(unsigned long *) loc = val; + rc = apply_rela_bits(loc, val, 0, 64, 0); 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; + rc = apply_rela_bits(loc, val, 1, 32, 0); else if (r_type == R_390_GOTPCDBL) - *(unsigned int *) loc = val >> 1; + rc = apply_rela_bits(loc, val, 1, 32, 1); break; case R_390_COPY: case R_390_GLOB_DAT: /* Create GOT entry. */ @@ -360,19 +395,25 @@ apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab, case R_390_RELATIVE: /* Adjust by program base. */ /* Only needed if we want to support loading of modules linked with -shared. */ - break; + return -ENOEXEC; default: - printk(KERN_ERR "module %s: Unknown relocation: %u\n", + printk(KERN_ERR "module %s: unknown relocation: %u\n", me->name, r_type); return -ENOEXEC; } + if (rc) { + printk(KERN_ERR "module %s: relocation error for symbol %s " + "(r_type %i, value 0x%lx)\n", + me->name, strtab + symtab[r_sym].st_name, + r_type, (unsigned long) val); + return rc; + } return 0; } -int -apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab, - unsigned int symindex, unsigned int relsec, - struct module *me) +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; @@ -388,7 +429,7 @@ apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab, n = sechdrs[relsec].sh_size / sizeof(Elf_Rela); for (i = 0; i < n; i++, rela++) { - rc = apply_rela(rela, base, symtab, me); + rc = apply_rela(rela, base, symtab, strtab, me); if (rc) return rc; } diff --git a/arch/s390/kernel/nmi.c b/arch/s390/kernel/nmi.c index 7918fbea36b..210e1285f75 100644 --- a/arch/s390/kernel/nmi.c +++ b/arch/s390/kernel/nmi.c @@ -55,7 +55,7 @@ void s390_handle_mcck(void) 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); + clear_cpu_flag(CIF_MCCK_PENDING); local_mcck_enable(); local_irq_restore(flags); @@ -214,10 +214,7 @@ static int notrace s390_revalidate_registers(struct mci *mci) : "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); + set_clock_comparator(S390_lowcore.clock_comparator); /* Check if old PSW is valid */ if (!mci->wp) /* @@ -293,7 +290,7 @@ void notrace s390_do_machine_check(struct pt_regs *regs) * retry this instruction. */ spin_lock(&ipd_lock); - tmp = get_clock(); + tmp = get_tod_clock(); if (((tmp - last_ipd) >> 12) < MAX_IPD_TIME) ipd_count++; else @@ -316,7 +313,7 @@ void notrace s390_do_machine_check(struct pt_regs *regs) */ mcck->kill_task = 1; mcck->mcck_code = *(unsigned long long *) mci; - set_thread_flag(TIF_MCCK_PENDING); + set_cpu_flag(CIF_MCCK_PENDING); } else { /* * Couldn't restore all register contents while in @@ -355,12 +352,12 @@ void notrace s390_do_machine_check(struct pt_regs *regs) if (mci->cp) { /* Channel report word pending */ mcck->channel_report = 1; - set_thread_flag(TIF_MCCK_PENDING); + set_cpu_flag(CIF_MCCK_PENDING); } if (mci->w) { /* Warning pending */ mcck->warning = 1; - set_thread_flag(TIF_MCCK_PENDING); + set_cpu_flag(CIF_MCCK_PENDING); } nmi_exit(); } diff --git a/arch/s390/kernel/os_info.c b/arch/s390/kernel/os_info.c index 46480d81df0..d112fc66f99 100644 --- a/arch/s390/kernel/os_info.c +++ b/arch/s390/kernel/os_info.c @@ -10,6 +10,7 @@ #include <linux/crash_dump.h> #include <linux/kernel.h> +#include <linux/slab.h> #include <asm/checksum.h> #include <asm/lowcore.h> #include <asm/os_info.h> diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c index 86ec7447e1f..ea75d011a6f 100644 --- a/arch/s390/kernel/perf_cpum_cf.c +++ b/arch/s390/kernel/perf_cpum_cf.c @@ -274,7 +274,7 @@ static int reserve_pmc_hardware(void) int flags = PMC_INIT; on_each_cpu(setup_pmc_cpu, &flags, 1); - measurement_alert_subclass_register(); + irq_subclass_register(IRQ_SUBCLASS_MEASUREMENT_ALERT); return 0; } @@ -285,7 +285,7 @@ static void release_pmc_hardware(void) int flags = PMC_RELEASE; on_each_cpu(setup_pmc_cpu, &flags, 1); - measurement_alert_subclass_unregister(); + irq_subclass_unregister(IRQ_SUBCLASS_MEASUREMENT_ALERT); } /* Release the PMU if event is the last perf event */ @@ -367,13 +367,6 @@ static int __hw_perf_event_init(struct perf_event *event) 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 @@ -418,6 +411,12 @@ static int cpumf_pmu_event_init(struct perf_event *event) case PERF_TYPE_HARDWARE: case PERF_TYPE_HW_CACHE: case PERF_TYPE_RAW: + /* The CPU measurement counter facility does not have overflow + * interrupts to do sampling. Sampling must be provided by + * external means, for example, by timers. + */ + if (is_sampling_event(event)) + return -ENOENT; err = __hw_perf_event_init(event); break; default: @@ -640,8 +639,8 @@ static struct pmu cpumf_pmu = { .cancel_txn = cpumf_pmu_cancel_txn, }; -static int __cpuinit cpumf_pmu_notifier(struct notifier_block *self, - unsigned long action, void *hcpu) +static int cpumf_pmu_notifier(struct notifier_block *self, unsigned long action, + void *hcpu) { unsigned int cpu = (long) hcpu; int flags; @@ -674,17 +673,20 @@ static int __init cpumf_pmu_init(void) ctl_clear_bit(0, 48); /* register handler for measurement-alert interruptions */ - rc = register_external_interrupt(0x1407, cpumf_measurement_alert); + rc = register_external_irq(EXT_IRQ_MEASURE_ALERT, + cpumf_measurement_alert); if (rc) { pr_err("Registering for CPU-measurement alerts " "failed with rc=%i\n", rc); goto out; } + cpumf_pmu.attr_groups = cpumf_cf_event_group(); 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); + unregister_external_irq(EXT_IRQ_MEASURE_ALERT, + cpumf_measurement_alert); goto out; } perf_cpu_notifier(cpumf_pmu_notifier); diff --git a/arch/s390/kernel/perf_cpum_cf_events.c b/arch/s390/kernel/perf_cpum_cf_events.c new file mode 100644 index 00000000000..4554a4bae39 --- /dev/null +++ b/arch/s390/kernel/perf_cpum_cf_events.c @@ -0,0 +1,322 @@ +/* + * Perf PMU sysfs events attributes for available CPU-measurement counters + * + */ + +#include <linux/slab.h> +#include <linux/perf_event.h> + + +/* BEGIN: CPUM_CF COUNTER DEFINITIONS =================================== */ + +CPUMF_EVENT_ATTR(cf, CPU_CYCLES, 0x0000); +CPUMF_EVENT_ATTR(cf, INSTRUCTIONS, 0x0001); +CPUMF_EVENT_ATTR(cf, L1I_DIR_WRITES, 0x0002); +CPUMF_EVENT_ATTR(cf, L1I_PENALTY_CYCLES, 0x0003); +CPUMF_EVENT_ATTR(cf, PROBLEM_STATE_CPU_CYCLES, 0x0020); +CPUMF_EVENT_ATTR(cf, PROBLEM_STATE_INSTRUCTIONS, 0x0021); +CPUMF_EVENT_ATTR(cf, PROBLEM_STATE_L1I_DIR_WRITES, 0x0022); +CPUMF_EVENT_ATTR(cf, PROBLEM_STATE_L1I_PENALTY_CYCLES, 0x0023); +CPUMF_EVENT_ATTR(cf, PROBLEM_STATE_L1D_DIR_WRITES, 0x0024); +CPUMF_EVENT_ATTR(cf, PROBLEM_STATE_L1D_PENALTY_CYCLES, 0x0025); +CPUMF_EVENT_ATTR(cf, L1D_DIR_WRITES, 0x0004); +CPUMF_EVENT_ATTR(cf, L1D_PENALTY_CYCLES, 0x0005); +CPUMF_EVENT_ATTR(cf, PRNG_FUNCTIONS, 0x0040); +CPUMF_EVENT_ATTR(cf, PRNG_CYCLES, 0x0041); +CPUMF_EVENT_ATTR(cf, PRNG_BLOCKED_FUNCTIONS, 0x0042); +CPUMF_EVENT_ATTR(cf, PRNG_BLOCKED_CYCLES, 0x0043); +CPUMF_EVENT_ATTR(cf, SHA_FUNCTIONS, 0x0044); +CPUMF_EVENT_ATTR(cf, SHA_CYCLES, 0x0045); +CPUMF_EVENT_ATTR(cf, SHA_BLOCKED_FUNCTIONS, 0x0046); +CPUMF_EVENT_ATTR(cf, SHA_BLOCKED_CYCLES, 0x0047); +CPUMF_EVENT_ATTR(cf, DEA_FUNCTIONS, 0x0048); +CPUMF_EVENT_ATTR(cf, DEA_CYCLES, 0x0049); +CPUMF_EVENT_ATTR(cf, DEA_BLOCKED_FUNCTIONS, 0x004a); +CPUMF_EVENT_ATTR(cf, DEA_BLOCKED_CYCLES, 0x004b); +CPUMF_EVENT_ATTR(cf, AES_FUNCTIONS, 0x004c); +CPUMF_EVENT_ATTR(cf, AES_CYCLES, 0x004d); +CPUMF_EVENT_ATTR(cf, AES_BLOCKED_FUNCTIONS, 0x004e); +CPUMF_EVENT_ATTR(cf, AES_BLOCKED_CYCLES, 0x004f); +CPUMF_EVENT_ATTR(cf_z10, L1I_L2_SOURCED_WRITES, 0x0080); +CPUMF_EVENT_ATTR(cf_z10, L1D_L2_SOURCED_WRITES, 0x0081); +CPUMF_EVENT_ATTR(cf_z10, L1I_L3_LOCAL_WRITES, 0x0082); +CPUMF_EVENT_ATTR(cf_z10, L1D_L3_LOCAL_WRITES, 0x0083); +CPUMF_EVENT_ATTR(cf_z10, L1I_L3_REMOTE_WRITES, 0x0084); +CPUMF_EVENT_ATTR(cf_z10, L1D_L3_REMOTE_WRITES, 0x0085); +CPUMF_EVENT_ATTR(cf_z10, L1D_LMEM_SOURCED_WRITES, 0x0086); +CPUMF_EVENT_ATTR(cf_z10, L1I_LMEM_SOURCED_WRITES, 0x0087); +CPUMF_EVENT_ATTR(cf_z10, L1D_RO_EXCL_WRITES, 0x0088); +CPUMF_EVENT_ATTR(cf_z10, L1I_CACHELINE_INVALIDATES, 0x0089); +CPUMF_EVENT_ATTR(cf_z10, ITLB1_WRITES, 0x008a); +CPUMF_EVENT_ATTR(cf_z10, DTLB1_WRITES, 0x008b); +CPUMF_EVENT_ATTR(cf_z10, TLB2_PTE_WRITES, 0x008c); +CPUMF_EVENT_ATTR(cf_z10, TLB2_CRSTE_WRITES, 0x008d); +CPUMF_EVENT_ATTR(cf_z10, TLB2_CRSTE_HPAGE_WRITES, 0x008e); +CPUMF_EVENT_ATTR(cf_z10, ITLB1_MISSES, 0x0091); +CPUMF_EVENT_ATTR(cf_z10, DTLB1_MISSES, 0x0092); +CPUMF_EVENT_ATTR(cf_z10, L2C_STORES_SENT, 0x0093); +CPUMF_EVENT_ATTR(cf_z196, L1D_L2_SOURCED_WRITES, 0x0080); +CPUMF_EVENT_ATTR(cf_z196, L1I_L2_SOURCED_WRITES, 0x0081); +CPUMF_EVENT_ATTR(cf_z196, DTLB1_MISSES, 0x0082); +CPUMF_EVENT_ATTR(cf_z196, ITLB1_MISSES, 0x0083); +CPUMF_EVENT_ATTR(cf_z196, L2C_STORES_SENT, 0x0085); +CPUMF_EVENT_ATTR(cf_z196, L1D_OFFBOOK_L3_SOURCED_WRITES, 0x0086); +CPUMF_EVENT_ATTR(cf_z196, L1D_ONBOOK_L4_SOURCED_WRITES, 0x0087); +CPUMF_EVENT_ATTR(cf_z196, L1I_ONBOOK_L4_SOURCED_WRITES, 0x0088); +CPUMF_EVENT_ATTR(cf_z196, L1D_RO_EXCL_WRITES, 0x0089); +CPUMF_EVENT_ATTR(cf_z196, L1D_OFFBOOK_L4_SOURCED_WRITES, 0x008a); +CPUMF_EVENT_ATTR(cf_z196, L1I_OFFBOOK_L4_SOURCED_WRITES, 0x008b); +CPUMF_EVENT_ATTR(cf_z196, DTLB1_HPAGE_WRITES, 0x008c); +CPUMF_EVENT_ATTR(cf_z196, L1D_LMEM_SOURCED_WRITES, 0x008d); +CPUMF_EVENT_ATTR(cf_z196, L1I_LMEM_SOURCED_WRITES, 0x008e); +CPUMF_EVENT_ATTR(cf_z196, L1I_OFFBOOK_L3_SOURCED_WRITES, 0x008f); +CPUMF_EVENT_ATTR(cf_z196, DTLB1_WRITES, 0x0090); +CPUMF_EVENT_ATTR(cf_z196, ITLB1_WRITES, 0x0091); +CPUMF_EVENT_ATTR(cf_z196, TLB2_PTE_WRITES, 0x0092); +CPUMF_EVENT_ATTR(cf_z196, TLB2_CRSTE_HPAGE_WRITES, 0x0093); +CPUMF_EVENT_ATTR(cf_z196, TLB2_CRSTE_WRITES, 0x0094); +CPUMF_EVENT_ATTR(cf_z196, L1D_ONCHIP_L3_SOURCED_WRITES, 0x0096); +CPUMF_EVENT_ATTR(cf_z196, L1D_OFFCHIP_L3_SOURCED_WRITES, 0x0098); +CPUMF_EVENT_ATTR(cf_z196, L1I_ONCHIP_L3_SOURCED_WRITES, 0x0099); +CPUMF_EVENT_ATTR(cf_z196, L1I_OFFCHIP_L3_SOURCED_WRITES, 0x009b); +CPUMF_EVENT_ATTR(cf_zec12, DTLB1_MISSES, 0x0080); +CPUMF_EVENT_ATTR(cf_zec12, ITLB1_MISSES, 0x0081); +CPUMF_EVENT_ATTR(cf_zec12, L1D_L2I_SOURCED_WRITES, 0x0082); +CPUMF_EVENT_ATTR(cf_zec12, L1I_L2I_SOURCED_WRITES, 0x0083); +CPUMF_EVENT_ATTR(cf_zec12, L1D_L2D_SOURCED_WRITES, 0x0084); +CPUMF_EVENT_ATTR(cf_zec12, DTLB1_WRITES, 0x0085); +CPUMF_EVENT_ATTR(cf_zec12, L1D_LMEM_SOURCED_WRITES, 0x0087); +CPUMF_EVENT_ATTR(cf_zec12, L1I_LMEM_SOURCED_WRITES, 0x0089); +CPUMF_EVENT_ATTR(cf_zec12, L1D_RO_EXCL_WRITES, 0x008a); +CPUMF_EVENT_ATTR(cf_zec12, DTLB1_HPAGE_WRITES, 0x008b); +CPUMF_EVENT_ATTR(cf_zec12, ITLB1_WRITES, 0x008c); +CPUMF_EVENT_ATTR(cf_zec12, TLB2_PTE_WRITES, 0x008d); +CPUMF_EVENT_ATTR(cf_zec12, TLB2_CRSTE_HPAGE_WRITES, 0x008e); +CPUMF_EVENT_ATTR(cf_zec12, TLB2_CRSTE_WRITES, 0x008f); +CPUMF_EVENT_ATTR(cf_zec12, L1D_ONCHIP_L3_SOURCED_WRITES, 0x0090); +CPUMF_EVENT_ATTR(cf_zec12, L1D_OFFCHIP_L3_SOURCED_WRITES, 0x0091); +CPUMF_EVENT_ATTR(cf_zec12, L1D_OFFBOOK_L3_SOURCED_WRITES, 0x0092); +CPUMF_EVENT_ATTR(cf_zec12, L1D_ONBOOK_L4_SOURCED_WRITES, 0x0093); +CPUMF_EVENT_ATTR(cf_zec12, L1D_OFFBOOK_L4_SOURCED_WRITES, 0x0094); +CPUMF_EVENT_ATTR(cf_zec12, TX_NC_TEND, 0x0095); +CPUMF_EVENT_ATTR(cf_zec12, L1D_ONCHIP_L3_SOURCED_WRITES_IV, 0x0096); +CPUMF_EVENT_ATTR(cf_zec12, L1D_OFFCHIP_L3_SOURCED_WRITES_IV, 0x0097); +CPUMF_EVENT_ATTR(cf_zec12, L1D_OFFBOOK_L3_SOURCED_WRITES_IV, 0x0098); +CPUMF_EVENT_ATTR(cf_zec12, L1I_ONCHIP_L3_SOURCED_WRITES, 0x0099); +CPUMF_EVENT_ATTR(cf_zec12, L1I_OFFCHIP_L3_SOURCED_WRITES, 0x009a); +CPUMF_EVENT_ATTR(cf_zec12, L1I_OFFBOOK_L3_SOURCED_WRITES, 0x009b); +CPUMF_EVENT_ATTR(cf_zec12, L1I_ONBOOK_L4_SOURCED_WRITES, 0x009c); +CPUMF_EVENT_ATTR(cf_zec12, L1I_OFFBOOK_L4_SOURCED_WRITES, 0x009d); +CPUMF_EVENT_ATTR(cf_zec12, TX_C_TEND, 0x009e); +CPUMF_EVENT_ATTR(cf_zec12, L1I_ONCHIP_L3_SOURCED_WRITES_IV, 0x009f); +CPUMF_EVENT_ATTR(cf_zec12, L1I_OFFCHIP_L3_SOURCED_WRITES_IV, 0x00a0); +CPUMF_EVENT_ATTR(cf_zec12, L1I_OFFBOOK_L3_SOURCED_WRITES_IV, 0x00a1); +CPUMF_EVENT_ATTR(cf_zec12, TX_NC_TABORT, 0x00b1); +CPUMF_EVENT_ATTR(cf_zec12, TX_C_TABORT_NO_SPECIAL, 0x00b2); +CPUMF_EVENT_ATTR(cf_zec12, TX_C_TABORT_SPECIAL, 0x00b3); + +static struct attribute *cpumcf_pmu_event_attr[] = { + CPUMF_EVENT_PTR(cf, CPU_CYCLES), + CPUMF_EVENT_PTR(cf, INSTRUCTIONS), + CPUMF_EVENT_PTR(cf, L1I_DIR_WRITES), + CPUMF_EVENT_PTR(cf, L1I_PENALTY_CYCLES), + CPUMF_EVENT_PTR(cf, PROBLEM_STATE_CPU_CYCLES), + CPUMF_EVENT_PTR(cf, PROBLEM_STATE_INSTRUCTIONS), + CPUMF_EVENT_PTR(cf, PROBLEM_STATE_L1I_DIR_WRITES), + CPUMF_EVENT_PTR(cf, PROBLEM_STATE_L1I_PENALTY_CYCLES), + CPUMF_EVENT_PTR(cf, PROBLEM_STATE_L1D_DIR_WRITES), + CPUMF_EVENT_PTR(cf, PROBLEM_STATE_L1D_PENALTY_CYCLES), + CPUMF_EVENT_PTR(cf, L1D_DIR_WRITES), + CPUMF_EVENT_PTR(cf, L1D_PENALTY_CYCLES), + CPUMF_EVENT_PTR(cf, PRNG_FUNCTIONS), + CPUMF_EVENT_PTR(cf, PRNG_CYCLES), + CPUMF_EVENT_PTR(cf, PRNG_BLOCKED_FUNCTIONS), + CPUMF_EVENT_PTR(cf, PRNG_BLOCKED_CYCLES), + CPUMF_EVENT_PTR(cf, SHA_FUNCTIONS), + CPUMF_EVENT_PTR(cf, SHA_CYCLES), + CPUMF_EVENT_PTR(cf, SHA_BLOCKED_FUNCTIONS), + CPUMF_EVENT_PTR(cf, SHA_BLOCKED_CYCLES), + CPUMF_EVENT_PTR(cf, DEA_FUNCTIONS), + CPUMF_EVENT_PTR(cf, DEA_CYCLES), + CPUMF_EVENT_PTR(cf, DEA_BLOCKED_FUNCTIONS), + CPUMF_EVENT_PTR(cf, DEA_BLOCKED_CYCLES), + CPUMF_EVENT_PTR(cf, AES_FUNCTIONS), + CPUMF_EVENT_PTR(cf, AES_CYCLES), + CPUMF_EVENT_PTR(cf, AES_BLOCKED_FUNCTIONS), + CPUMF_EVENT_PTR(cf, AES_BLOCKED_CYCLES), + NULL, +}; + +static struct attribute *cpumcf_z10_pmu_event_attr[] __initdata = { + CPUMF_EVENT_PTR(cf_z10, L1I_L2_SOURCED_WRITES), + CPUMF_EVENT_PTR(cf_z10, L1D_L2_SOURCED_WRITES), + CPUMF_EVENT_PTR(cf_z10, L1I_L3_LOCAL_WRITES), + CPUMF_EVENT_PTR(cf_z10, L1D_L3_LOCAL_WRITES), + CPUMF_EVENT_PTR(cf_z10, L1I_L3_REMOTE_WRITES), + CPUMF_EVENT_PTR(cf_z10, L1D_L3_REMOTE_WRITES), + CPUMF_EVENT_PTR(cf_z10, L1D_LMEM_SOURCED_WRITES), + CPUMF_EVENT_PTR(cf_z10, L1I_LMEM_SOURCED_WRITES), + CPUMF_EVENT_PTR(cf_z10, L1D_RO_EXCL_WRITES), + CPUMF_EVENT_PTR(cf_z10, L1I_CACHELINE_INVALIDATES), + CPUMF_EVENT_PTR(cf_z10, ITLB1_WRITES), + CPUMF_EVENT_PTR(cf_z10, DTLB1_WRITES), + CPUMF_EVENT_PTR(cf_z10, TLB2_PTE_WRITES), + CPUMF_EVENT_PTR(cf_z10, TLB2_CRSTE_WRITES), + CPUMF_EVENT_PTR(cf_z10, TLB2_CRSTE_HPAGE_WRITES), + CPUMF_EVENT_PTR(cf_z10, ITLB1_MISSES), + CPUMF_EVENT_PTR(cf_z10, DTLB1_MISSES), + CPUMF_EVENT_PTR(cf_z10, L2C_STORES_SENT), + NULL, +}; + +static struct attribute *cpumcf_z196_pmu_event_attr[] __initdata = { + CPUMF_EVENT_PTR(cf_z196, L1D_L2_SOURCED_WRITES), + CPUMF_EVENT_PTR(cf_z196, L1I_L2_SOURCED_WRITES), + CPUMF_EVENT_PTR(cf_z196, DTLB1_MISSES), + CPUMF_EVENT_PTR(cf_z196, ITLB1_MISSES), + CPUMF_EVENT_PTR(cf_z196, L2C_STORES_SENT), + CPUMF_EVENT_PTR(cf_z196, L1D_OFFBOOK_L3_SOURCED_WRITES), + CPUMF_EVENT_PTR(cf_z196, L1D_ONBOOK_L4_SOURCED_WRITES), + CPUMF_EVENT_PTR(cf_z196, L1I_ONBOOK_L4_SOURCED_WRITES), + CPUMF_EVENT_PTR(cf_z196, L1D_RO_EXCL_WRITES), + CPUMF_EVENT_PTR(cf_z196, L1D_OFFBOOK_L4_SOURCED_WRITES), + CPUMF_EVENT_PTR(cf_z196, L1I_OFFBOOK_L4_SOURCED_WRITES), + CPUMF_EVENT_PTR(cf_z196, DTLB1_HPAGE_WRITES), + CPUMF_EVENT_PTR(cf_z196, L1D_LMEM_SOURCED_WRITES), + CPUMF_EVENT_PTR(cf_z196, L1I_LMEM_SOURCED_WRITES), + CPUMF_EVENT_PTR(cf_z196, L1I_OFFBOOK_L3_SOURCED_WRITES), + CPUMF_EVENT_PTR(cf_z196, DTLB1_WRITES), + CPUMF_EVENT_PTR(cf_z196, ITLB1_WRITES), + CPUMF_EVENT_PTR(cf_z196, TLB2_PTE_WRITES), + CPUMF_EVENT_PTR(cf_z196, TLB2_CRSTE_HPAGE_WRITES), + CPUMF_EVENT_PTR(cf_z196, TLB2_CRSTE_WRITES), + CPUMF_EVENT_PTR(cf_z196, L1D_ONCHIP_L3_SOURCED_WRITES), + CPUMF_EVENT_PTR(cf_z196, L1D_OFFCHIP_L3_SOURCED_WRITES), + CPUMF_EVENT_PTR(cf_z196, L1I_ONCHIP_L3_SOURCED_WRITES), + CPUMF_EVENT_PTR(cf_z196, L1I_OFFCHIP_L3_SOURCED_WRITES), + NULL, +}; + +static struct attribute *cpumcf_zec12_pmu_event_attr[] __initdata = { + CPUMF_EVENT_PTR(cf_zec12, DTLB1_MISSES), + CPUMF_EVENT_PTR(cf_zec12, ITLB1_MISSES), + CPUMF_EVENT_PTR(cf_zec12, L1D_L2I_SOURCED_WRITES), + CPUMF_EVENT_PTR(cf_zec12, L1I_L2I_SOURCED_WRITES), + CPUMF_EVENT_PTR(cf_zec12, L1D_L2D_SOURCED_WRITES), + CPUMF_EVENT_PTR(cf_zec12, DTLB1_WRITES), + CPUMF_EVENT_PTR(cf_zec12, L1D_LMEM_SOURCED_WRITES), + CPUMF_EVENT_PTR(cf_zec12, L1I_LMEM_SOURCED_WRITES), + CPUMF_EVENT_PTR(cf_zec12, L1D_RO_EXCL_WRITES), + CPUMF_EVENT_PTR(cf_zec12, DTLB1_HPAGE_WRITES), + CPUMF_EVENT_PTR(cf_zec12, ITLB1_WRITES), + CPUMF_EVENT_PTR(cf_zec12, TLB2_PTE_WRITES), + CPUMF_EVENT_PTR(cf_zec12, TLB2_CRSTE_HPAGE_WRITES), + CPUMF_EVENT_PTR(cf_zec12, TLB2_CRSTE_WRITES), + CPUMF_EVENT_PTR(cf_zec12, L1D_ONCHIP_L3_SOURCED_WRITES), + CPUMF_EVENT_PTR(cf_zec12, L1D_OFFCHIP_L3_SOURCED_WRITES), + CPUMF_EVENT_PTR(cf_zec12, L1D_OFFBOOK_L3_SOURCED_WRITES), + CPUMF_EVENT_PTR(cf_zec12, L1D_ONBOOK_L4_SOURCED_WRITES), + CPUMF_EVENT_PTR(cf_zec12, L1D_OFFBOOK_L4_SOURCED_WRITES), + CPUMF_EVENT_PTR(cf_zec12, TX_NC_TEND), + CPUMF_EVENT_PTR(cf_zec12, L1D_ONCHIP_L3_SOURCED_WRITES_IV), + CPUMF_EVENT_PTR(cf_zec12, L1D_OFFCHIP_L3_SOURCED_WRITES_IV), + CPUMF_EVENT_PTR(cf_zec12, L1D_OFFBOOK_L3_SOURCED_WRITES_IV), + CPUMF_EVENT_PTR(cf_zec12, L1I_ONCHIP_L3_SOURCED_WRITES), + CPUMF_EVENT_PTR(cf_zec12, L1I_OFFCHIP_L3_SOURCED_WRITES), + CPUMF_EVENT_PTR(cf_zec12, L1I_OFFBOOK_L3_SOURCED_WRITES), + CPUMF_EVENT_PTR(cf_zec12, L1I_ONBOOK_L4_SOURCED_WRITES), + CPUMF_EVENT_PTR(cf_zec12, L1I_OFFBOOK_L4_SOURCED_WRITES), + CPUMF_EVENT_PTR(cf_zec12, TX_C_TEND), + CPUMF_EVENT_PTR(cf_zec12, L1I_ONCHIP_L3_SOURCED_WRITES_IV), + CPUMF_EVENT_PTR(cf_zec12, L1I_OFFCHIP_L3_SOURCED_WRITES_IV), + CPUMF_EVENT_PTR(cf_zec12, L1I_OFFBOOK_L3_SOURCED_WRITES_IV), + CPUMF_EVENT_PTR(cf_zec12, TX_NC_TABORT), + CPUMF_EVENT_PTR(cf_zec12, TX_C_TABORT_NO_SPECIAL), + CPUMF_EVENT_PTR(cf_zec12, TX_C_TABORT_SPECIAL), + NULL, +}; + +/* END: CPUM_CF COUNTER DEFINITIONS ===================================== */ + +static struct attribute_group cpumsf_pmu_events_group = { + .name = "events", + .attrs = cpumcf_pmu_event_attr, +}; + +PMU_FORMAT_ATTR(event, "config:0-63"); + +static struct attribute *cpumsf_pmu_format_attr[] = { + &format_attr_event.attr, + NULL, +}; + +static struct attribute_group cpumsf_pmu_format_group = { + .name = "format", + .attrs = cpumsf_pmu_format_attr, +}; + +static const struct attribute_group *cpumsf_pmu_attr_groups[] = { + &cpumsf_pmu_events_group, + &cpumsf_pmu_format_group, + NULL, +}; + + +static __init struct attribute **merge_attr(struct attribute **a, + struct attribute **b) +{ + struct attribute **new; + int j, i; + + for (j = 0; a[j]; j++) + ; + for (i = 0; b[i]; i++) + j++; + j++; + + new = kmalloc(sizeof(struct attribute *) * j, GFP_KERNEL); + if (!new) + return NULL; + j = 0; + for (i = 0; a[i]; i++) + new[j++] = a[i]; + for (i = 0; b[i]; i++) + new[j++] = b[i]; + new[j] = NULL; + + return new; +} + +__init const struct attribute_group **cpumf_cf_event_group(void) +{ + struct attribute **combined, **model; + struct cpuid cpu_id; + + get_cpu_id(&cpu_id); + switch (cpu_id.machine) { + case 0x2097: + case 0x2098: + model = cpumcf_z10_pmu_event_attr; + break; + case 0x2817: + case 0x2818: + model = cpumcf_z196_pmu_event_attr; + break; + case 0x2827: + case 0x2828: + model = cpumcf_zec12_pmu_event_attr; + break; + default: + model = NULL; + break; + }; + + if (!model) + goto out; + + combined = merge_attr(cpumcf_pmu_event_attr, model); + if (combined) + cpumsf_pmu_events_group.attrs = combined; +out: + return cpumsf_pmu_attr_groups; +} diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c new file mode 100644 index 00000000000..ea0c7b2ef03 --- /dev/null +++ b/arch/s390/kernel/perf_cpum_sf.c @@ -0,0 +1,1643 @@ +/* + * Performance event support for the System z CPU-measurement Sampling Facility + * + * Copyright IBM Corp. 2013 + * 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_sf" +#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/export.h> +#include <linux/slab.h> +#include <linux/mm.h> +#include <linux/moduleparam.h> +#include <asm/cpu_mf.h> +#include <asm/irq.h> +#include <asm/debug.h> +#include <asm/timex.h> + +/* Minimum number of sample-data-block-tables: + * At least one table is required for the sampling buffer structure. + * A single table contains up to 511 pointers to sample-data-blocks. + */ +#define CPUM_SF_MIN_SDBT 1 + +/* Number of sample-data-blocks per sample-data-block-table (SDBT): + * A table contains SDB pointers (8 bytes) and one table-link entry + * that points to the origin of the next SDBT. + */ +#define CPUM_SF_SDB_PER_TABLE ((PAGE_SIZE - 8) / 8) + +/* Maximum page offset for an SDBT table-link entry: + * If this page offset is reached, a table-link entry to the next SDBT + * must be added. + */ +#define CPUM_SF_SDBT_TL_OFFSET (CPUM_SF_SDB_PER_TABLE * 8) +static inline int require_table_link(const void *sdbt) +{ + return ((unsigned long) sdbt & ~PAGE_MASK) == CPUM_SF_SDBT_TL_OFFSET; +} + +/* Minimum and maximum sampling buffer sizes: + * + * This number represents the maximum size of the sampling buffer taking + * the number of sample-data-block-tables into account. Note that these + * numbers apply to the basic-sampling function only. + * The maximum number of SDBs is increased by CPUM_SF_SDB_DIAG_FACTOR if + * the diagnostic-sampling function is active. + * + * Sampling buffer size Buffer characteristics + * --------------------------------------------------- + * 64KB == 16 pages (4KB per page) + * 1 page for SDB-tables + * 15 pages for SDBs + * + * 32MB == 8192 pages (4KB per page) + * 16 pages for SDB-tables + * 8176 pages for SDBs + */ +static unsigned long __read_mostly CPUM_SF_MIN_SDB = 15; +static unsigned long __read_mostly CPUM_SF_MAX_SDB = 8176; +static unsigned long __read_mostly CPUM_SF_SDB_DIAG_FACTOR = 1; + +struct sf_buffer { + unsigned long *sdbt; /* Sample-data-block-table origin */ + /* buffer characteristics (required for buffer increments) */ + unsigned long num_sdb; /* Number of sample-data-blocks */ + unsigned long num_sdbt; /* Number of sample-data-block-tables */ + unsigned long *tail; /* last sample-data-block-table */ +}; + +struct cpu_hw_sf { + /* CPU-measurement sampling information block */ + struct hws_qsi_info_block qsi; + /* CPU-measurement sampling control block */ + struct hws_lsctl_request_block lsctl; + struct sf_buffer sfb; /* Sampling buffer */ + unsigned int flags; /* Status flags */ + struct perf_event *event; /* Scheduled perf event */ +}; +static DEFINE_PER_CPU(struct cpu_hw_sf, cpu_hw_sf); + +/* Debug feature */ +static debug_info_t *sfdbg; + +/* + * sf_disable() - Switch off sampling facility + */ +static int sf_disable(void) +{ + struct hws_lsctl_request_block sreq; + + memset(&sreq, 0, sizeof(sreq)); + return lsctl(&sreq); +} + +/* + * sf_buffer_available() - Check for an allocated sampling buffer + */ +static int sf_buffer_available(struct cpu_hw_sf *cpuhw) +{ + return !!cpuhw->sfb.sdbt; +} + +/* + * deallocate sampling facility buffer + */ +static void free_sampling_buffer(struct sf_buffer *sfb) +{ + unsigned long *sdbt, *curr; + + if (!sfb->sdbt) + return; + + sdbt = sfb->sdbt; + curr = sdbt; + + /* Free the SDBT after all SDBs are processed... */ + while (1) { + if (!*curr || !sdbt) + break; + + /* Process table-link entries */ + if (is_link_entry(curr)) { + curr = get_next_sdbt(curr); + if (sdbt) + free_page((unsigned long) sdbt); + + /* If the origin is reached, sampling buffer is freed */ + if (curr == sfb->sdbt) + break; + else + sdbt = curr; + } else { + /* Process SDB pointer */ + if (*curr) { + free_page(*curr); + curr++; + } + } + } + + debug_sprintf_event(sfdbg, 5, + "free_sampling_buffer: freed sdbt=%p\n", sfb->sdbt); + memset(sfb, 0, sizeof(*sfb)); +} + +static int alloc_sample_data_block(unsigned long *sdbt, gfp_t gfp_flags) +{ + unsigned long sdb, *trailer; + + /* Allocate and initialize sample-data-block */ + sdb = get_zeroed_page(gfp_flags); + if (!sdb) + return -ENOMEM; + trailer = trailer_entry_ptr(sdb); + *trailer = SDB_TE_ALERT_REQ_MASK; + + /* Link SDB into the sample-data-block-table */ + *sdbt = sdb; + + return 0; +} + +/* + * realloc_sampling_buffer() - extend sampler memory + * + * Allocates new sample-data-blocks and adds them to the specified sampling + * buffer memory. + * + * Important: This modifies the sampling buffer and must be called when the + * sampling facility is disabled. + * + * Returns zero on success, non-zero otherwise. + */ +static int realloc_sampling_buffer(struct sf_buffer *sfb, + unsigned long num_sdb, gfp_t gfp_flags) +{ + int i, rc; + unsigned long *new, *tail; + + if (!sfb->sdbt || !sfb->tail) + return -EINVAL; + + if (!is_link_entry(sfb->tail)) + return -EINVAL; + + /* Append to the existing sampling buffer, overwriting the table-link + * register. + * The tail variables always points to the "tail" (last and table-link) + * entry in an SDB-table. + */ + tail = sfb->tail; + + /* Do a sanity check whether the table-link entry points to + * the sampling buffer origin. + */ + if (sfb->sdbt != get_next_sdbt(tail)) { + debug_sprintf_event(sfdbg, 3, "realloc_sampling_buffer: " + "sampling buffer is not linked: origin=%p" + "tail=%p\n", + (void *) sfb->sdbt, (void *) tail); + return -EINVAL; + } + + /* Allocate remaining SDBs */ + rc = 0; + for (i = 0; i < num_sdb; i++) { + /* Allocate a new SDB-table if it is full. */ + if (require_table_link(tail)) { + new = (unsigned long *) get_zeroed_page(gfp_flags); + if (!new) { + rc = -ENOMEM; + break; + } + sfb->num_sdbt++; + /* Link current page to tail of chain */ + *tail = (unsigned long)(void *) new + 1; + tail = new; + } + + /* Allocate a new sample-data-block. + * If there is not enough memory, stop the realloc process + * and simply use what was allocated. If this is a temporary + * issue, a new realloc call (if required) might succeed. + */ + rc = alloc_sample_data_block(tail, gfp_flags); + if (rc) + break; + sfb->num_sdb++; + tail++; + } + + /* Link sampling buffer to its origin */ + *tail = (unsigned long) sfb->sdbt + 1; + sfb->tail = tail; + + debug_sprintf_event(sfdbg, 4, "realloc_sampling_buffer: new buffer" + " settings: sdbt=%lu sdb=%lu\n", + sfb->num_sdbt, sfb->num_sdb); + return rc; +} + +/* + * allocate_sampling_buffer() - allocate sampler memory + * + * Allocates and initializes a sampling buffer structure using the + * specified number of sample-data-blocks (SDB). For each allocation, + * a 4K page is used. The number of sample-data-block-tables (SDBT) + * are calculated from SDBs. + * Also set the ALERT_REQ mask in each SDBs trailer. + * + * Returns zero on success, non-zero otherwise. + */ +static int alloc_sampling_buffer(struct sf_buffer *sfb, unsigned long num_sdb) +{ + int rc; + + if (sfb->sdbt) + return -EINVAL; + + /* Allocate the sample-data-block-table origin */ + sfb->sdbt = (unsigned long *) get_zeroed_page(GFP_KERNEL); + if (!sfb->sdbt) + return -ENOMEM; + sfb->num_sdb = 0; + sfb->num_sdbt = 1; + + /* Link the table origin to point to itself to prepare for + * realloc_sampling_buffer() invocation. + */ + sfb->tail = sfb->sdbt; + *sfb->tail = (unsigned long)(void *) sfb->sdbt + 1; + + /* Allocate requested number of sample-data-blocks */ + rc = realloc_sampling_buffer(sfb, num_sdb, GFP_KERNEL); + if (rc) { + free_sampling_buffer(sfb); + debug_sprintf_event(sfdbg, 4, "alloc_sampling_buffer: " + "realloc_sampling_buffer failed with rc=%i\n", rc); + } else + debug_sprintf_event(sfdbg, 4, + "alloc_sampling_buffer: tear=%p dear=%p\n", + sfb->sdbt, (void *) *sfb->sdbt); + return rc; +} + +static void sfb_set_limits(unsigned long min, unsigned long max) +{ + struct hws_qsi_info_block si; + + CPUM_SF_MIN_SDB = min; + CPUM_SF_MAX_SDB = max; + + memset(&si, 0, sizeof(si)); + if (!qsi(&si)) + CPUM_SF_SDB_DIAG_FACTOR = DIV_ROUND_UP(si.dsdes, si.bsdes); +} + +static unsigned long sfb_max_limit(struct hw_perf_event *hwc) +{ + return SAMPL_DIAG_MODE(hwc) ? CPUM_SF_MAX_SDB * CPUM_SF_SDB_DIAG_FACTOR + : CPUM_SF_MAX_SDB; +} + +static unsigned long sfb_pending_allocs(struct sf_buffer *sfb, + struct hw_perf_event *hwc) +{ + if (!sfb->sdbt) + return SFB_ALLOC_REG(hwc); + if (SFB_ALLOC_REG(hwc) > sfb->num_sdb) + return SFB_ALLOC_REG(hwc) - sfb->num_sdb; + return 0; +} + +static int sfb_has_pending_allocs(struct sf_buffer *sfb, + struct hw_perf_event *hwc) +{ + return sfb_pending_allocs(sfb, hwc) > 0; +} + +static void sfb_account_allocs(unsigned long num, struct hw_perf_event *hwc) +{ + /* Limit the number of SDBs to not exceed the maximum */ + num = min_t(unsigned long, num, sfb_max_limit(hwc) - SFB_ALLOC_REG(hwc)); + if (num) + SFB_ALLOC_REG(hwc) += num; +} + +static void sfb_init_allocs(unsigned long num, struct hw_perf_event *hwc) +{ + SFB_ALLOC_REG(hwc) = 0; + sfb_account_allocs(num, hwc); +} + +static size_t event_sample_size(struct hw_perf_event *hwc) +{ + struct sf_raw_sample *sfr = (struct sf_raw_sample *) RAWSAMPLE_REG(hwc); + size_t sample_size; + + /* The sample size depends on the sampling function: The basic-sampling + * function must be always enabled, diagnostic-sampling function is + * optional. + */ + sample_size = sfr->bsdes; + if (SAMPL_DIAG_MODE(hwc)) + sample_size += sfr->dsdes; + + return sample_size; +} + +static void deallocate_buffers(struct cpu_hw_sf *cpuhw) +{ + if (cpuhw->sfb.sdbt) + free_sampling_buffer(&cpuhw->sfb); +} + +static int allocate_buffers(struct cpu_hw_sf *cpuhw, struct hw_perf_event *hwc) +{ + unsigned long n_sdb, freq, factor; + size_t sfr_size, sample_size; + struct sf_raw_sample *sfr; + + /* Allocate raw sample buffer + * + * The raw sample buffer is used to temporarily store sampling data + * entries for perf raw sample processing. The buffer size mainly + * depends on the size of diagnostic-sampling data entries which is + * machine-specific. The exact size calculation includes: + * 1. The first 4 bytes of diagnostic-sampling data entries are + * already reflected in the sf_raw_sample structure. Subtract + * these bytes. + * 2. The perf raw sample data must be 8-byte aligned (u64) and + * perf's internal data size must be considered too. So add + * an additional u32 for correct alignment and subtract before + * allocating the buffer. + * 3. Store the raw sample buffer pointer in the perf event + * hardware structure. + */ + sfr_size = ALIGN((sizeof(*sfr) - sizeof(sfr->diag) + cpuhw->qsi.dsdes) + + sizeof(u32), sizeof(u64)); + sfr_size -= sizeof(u32); + sfr = kzalloc(sfr_size, GFP_KERNEL); + if (!sfr) + return -ENOMEM; + sfr->size = sfr_size; + sfr->bsdes = cpuhw->qsi.bsdes; + sfr->dsdes = cpuhw->qsi.dsdes; + RAWSAMPLE_REG(hwc) = (unsigned long) sfr; + + /* Calculate sampling buffers using 4K pages + * + * 1. Determine the sample data size which depends on the used + * sampling functions, for example, basic-sampling or + * basic-sampling with diagnostic-sampling. + * + * 2. Use the sampling frequency as input. The sampling buffer is + * designed for almost one second. This can be adjusted through + * the "factor" variable. + * In any case, alloc_sampling_buffer() sets the Alert Request + * Control indicator to trigger a measurement-alert to harvest + * sample-data-blocks (sdb). + * + * 3. Compute the number of sample-data-blocks and ensure a minimum + * of CPUM_SF_MIN_SDB. Also ensure the upper limit does not + * exceed a "calculated" maximum. The symbolic maximum is + * designed for basic-sampling only and needs to be increased if + * diagnostic-sampling is active. + * See also the remarks for these symbolic constants. + * + * 4. Compute the number of sample-data-block-tables (SDBT) and + * ensure a minimum of CPUM_SF_MIN_SDBT (one table can manage up + * to 511 SDBs). + */ + sample_size = event_sample_size(hwc); + freq = sample_rate_to_freq(&cpuhw->qsi, SAMPL_RATE(hwc)); + factor = 1; + n_sdb = DIV_ROUND_UP(freq, factor * ((PAGE_SIZE-64) / sample_size)); + if (n_sdb < CPUM_SF_MIN_SDB) + n_sdb = CPUM_SF_MIN_SDB; + + /* If there is already a sampling buffer allocated, it is very likely + * that the sampling facility is enabled too. If the event to be + * initialized requires a greater sampling buffer, the allocation must + * be postponed. Changing the sampling buffer requires the sampling + * facility to be in the disabled state. So, account the number of + * required SDBs and let cpumsf_pmu_enable() resize the buffer just + * before the event is started. + */ + sfb_init_allocs(n_sdb, hwc); + if (sf_buffer_available(cpuhw)) + return 0; + + debug_sprintf_event(sfdbg, 3, + "allocate_buffers: rate=%lu f=%lu sdb=%lu/%lu" + " sample_size=%lu cpuhw=%p\n", + SAMPL_RATE(hwc), freq, n_sdb, sfb_max_limit(hwc), + sample_size, cpuhw); + + return alloc_sampling_buffer(&cpuhw->sfb, + sfb_pending_allocs(&cpuhw->sfb, hwc)); +} + +static unsigned long min_percent(unsigned int percent, unsigned long base, + unsigned long min) +{ + return min_t(unsigned long, min, DIV_ROUND_UP(percent * base, 100)); +} + +static unsigned long compute_sfb_extent(unsigned long ratio, unsigned long base) +{ + /* Use a percentage-based approach to extend the sampling facility + * buffer. Accept up to 5% sample data loss. + * Vary the extents between 1% to 5% of the current number of + * sample-data-blocks. + */ + if (ratio <= 5) + return 0; + if (ratio <= 25) + return min_percent(1, base, 1); + if (ratio <= 50) + return min_percent(1, base, 1); + if (ratio <= 75) + return min_percent(2, base, 2); + if (ratio <= 100) + return min_percent(3, base, 3); + if (ratio <= 250) + return min_percent(4, base, 4); + + return min_percent(5, base, 8); +} + +static void sfb_account_overflows(struct cpu_hw_sf *cpuhw, + struct hw_perf_event *hwc) +{ + unsigned long ratio, num; + + if (!OVERFLOW_REG(hwc)) + return; + + /* The sample_overflow contains the average number of sample data + * that has been lost because sample-data-blocks were full. + * + * Calculate the total number of sample data entries that has been + * discarded. Then calculate the ratio of lost samples to total samples + * per second in percent. + */ + ratio = DIV_ROUND_UP(100 * OVERFLOW_REG(hwc) * cpuhw->sfb.num_sdb, + sample_rate_to_freq(&cpuhw->qsi, SAMPL_RATE(hwc))); + + /* Compute number of sample-data-blocks */ + num = compute_sfb_extent(ratio, cpuhw->sfb.num_sdb); + if (num) + sfb_account_allocs(num, hwc); + + debug_sprintf_event(sfdbg, 5, "sfb: overflow: overflow=%llu ratio=%lu" + " num=%lu\n", OVERFLOW_REG(hwc), ratio, num); + OVERFLOW_REG(hwc) = 0; +} + +/* extend_sampling_buffer() - Extend sampling buffer + * @sfb: Sampling buffer structure (for local CPU) + * @hwc: Perf event hardware structure + * + * Use this function to extend the sampling buffer based on the overflow counter + * and postponed allocation extents stored in the specified Perf event hardware. + * + * Important: This function disables the sampling facility in order to safely + * change the sampling buffer structure. Do not call this function + * when the PMU is active. + */ +static void extend_sampling_buffer(struct sf_buffer *sfb, + struct hw_perf_event *hwc) +{ + unsigned long num, num_old; + int rc; + + num = sfb_pending_allocs(sfb, hwc); + if (!num) + return; + num_old = sfb->num_sdb; + + /* Disable the sampling facility to reset any states and also + * clear pending measurement alerts. + */ + sf_disable(); + + /* Extend the sampling buffer. + * This memory allocation typically happens in an atomic context when + * called by perf. Because this is a reallocation, it is fine if the + * new SDB-request cannot be satisfied immediately. + */ + rc = realloc_sampling_buffer(sfb, num, GFP_ATOMIC); + if (rc) + debug_sprintf_event(sfdbg, 5, "sfb: extend: realloc " + "failed with rc=%i\n", rc); + + if (sfb_has_pending_allocs(sfb, hwc)) + debug_sprintf_event(sfdbg, 5, "sfb: extend: " + "req=%lu alloc=%lu remaining=%lu\n", + num, sfb->num_sdb - num_old, + sfb_pending_allocs(sfb, hwc)); +} + + +/* Number of perf events counting hardware events */ +static atomic_t num_events; +/* Used to avoid races in calling reserve/release_cpumf_hardware */ +static DEFINE_MUTEX(pmc_reserve_mutex); + +#define PMC_INIT 0 +#define PMC_RELEASE 1 +#define PMC_FAILURE 2 +static void setup_pmc_cpu(void *flags) +{ + int err; + struct cpu_hw_sf *cpusf = &__get_cpu_var(cpu_hw_sf); + + err = 0; + switch (*((int *) flags)) { + case PMC_INIT: + memset(cpusf, 0, sizeof(*cpusf)); + err = qsi(&cpusf->qsi); + if (err) + break; + cpusf->flags |= PMU_F_RESERVED; + err = sf_disable(); + if (err) + pr_err("Switching off the sampling facility failed " + "with rc=%i\n", err); + debug_sprintf_event(sfdbg, 5, + "setup_pmc_cpu: initialized: cpuhw=%p\n", cpusf); + break; + case PMC_RELEASE: + cpusf->flags &= ~PMU_F_RESERVED; + err = sf_disable(); + if (err) { + pr_err("Switching off the sampling facility failed " + "with rc=%i\n", err); + } else + deallocate_buffers(cpusf); + debug_sprintf_event(sfdbg, 5, + "setup_pmc_cpu: released: cpuhw=%p\n", cpusf); + break; + } + if (err) + *((int *) flags) |= PMC_FAILURE; +} + +static void release_pmc_hardware(void) +{ + int flags = PMC_RELEASE; + + irq_subclass_unregister(IRQ_SUBCLASS_MEASUREMENT_ALERT); + on_each_cpu(setup_pmc_cpu, &flags, 1); + perf_release_sampling(); +} + +static int reserve_pmc_hardware(void) +{ + int flags = PMC_INIT; + int err; + + err = perf_reserve_sampling(); + if (err) + return err; + on_each_cpu(setup_pmc_cpu, &flags, 1); + if (flags & PMC_FAILURE) { + release_pmc_hardware(); + return -ENODEV; + } + irq_subclass_register(IRQ_SUBCLASS_MEASUREMENT_ALERT); + + return 0; +} + +static void hw_perf_event_destroy(struct perf_event *event) +{ + /* Free raw sample buffer */ + if (RAWSAMPLE_REG(&event->hw)) + kfree((void *) RAWSAMPLE_REG(&event->hw)); + + /* Release PMC if this is the last perf 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); + } +} + +static void hw_init_period(struct hw_perf_event *hwc, u64 period) +{ + hwc->sample_period = period; + hwc->last_period = hwc->sample_period; + local64_set(&hwc->period_left, hwc->sample_period); +} + +static void hw_reset_registers(struct hw_perf_event *hwc, + unsigned long *sdbt_origin) +{ + struct sf_raw_sample *sfr; + + /* (Re)set to first sample-data-block-table */ + TEAR_REG(hwc) = (unsigned long) sdbt_origin; + + /* (Re)set raw sampling buffer register */ + sfr = (struct sf_raw_sample *) RAWSAMPLE_REG(hwc); + memset(&sfr->basic, 0, sizeof(sfr->basic)); + memset(&sfr->diag, 0, sfr->dsdes); +} + +static unsigned long hw_limit_rate(const struct hws_qsi_info_block *si, + unsigned long rate) +{ + return clamp_t(unsigned long, rate, + si->min_sampl_rate, si->max_sampl_rate); +} + +static int __hw_perf_event_init(struct perf_event *event) +{ + struct cpu_hw_sf *cpuhw; + struct hws_qsi_info_block si; + struct perf_event_attr *attr = &event->attr; + struct hw_perf_event *hwc = &event->hw; + unsigned long rate; + int cpu, err; + + /* Reserve CPU-measurement sampling facility */ + err = 0; + 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; + + if (err) + goto out; + + /* Access per-CPU sampling information (query sampling info) */ + /* + * The event->cpu value can be -1 to count on every CPU, for example, + * when attaching to a task. If this is specified, use the query + * sampling info from the current CPU, otherwise use event->cpu to + * retrieve the per-CPU information. + * Later, cpuhw indicates whether to allocate sampling buffers for a + * particular CPU (cpuhw!=NULL) or each online CPU (cpuw==NULL). + */ + memset(&si, 0, sizeof(si)); + cpuhw = NULL; + if (event->cpu == -1) + qsi(&si); + else { + /* Event is pinned to a particular CPU, retrieve the per-CPU + * sampling structure for accessing the CPU-specific QSI. + */ + cpuhw = &per_cpu(cpu_hw_sf, event->cpu); + si = cpuhw->qsi; + } + + /* Check sampling facility authorization and, if not authorized, + * fall back to other PMUs. It is safe to check any CPU because + * the authorization is identical for all configured CPUs. + */ + if (!si.as) { + err = -ENOENT; + goto out; + } + + /* Always enable basic sampling */ + SAMPL_FLAGS(hwc) = PERF_CPUM_SF_BASIC_MODE; + + /* Check if diagnostic sampling is requested. Deny if the required + * sampling authorization is missing. + */ + if (attr->config == PERF_EVENT_CPUM_SF_DIAG) { + if (!si.ad) { + err = -EPERM; + goto out; + } + SAMPL_FLAGS(hwc) |= PERF_CPUM_SF_DIAG_MODE; + } + + /* Check and set other sampling flags */ + if (attr->config1 & PERF_CPUM_SF_FULL_BLOCKS) + SAMPL_FLAGS(hwc) |= PERF_CPUM_SF_FULL_BLOCKS; + + /* The sampling information (si) contains information about the + * min/max sampling intervals and the CPU speed. So calculate the + * correct sampling interval and avoid the whole period adjust + * feedback loop. + */ + rate = 0; + if (attr->freq) { + rate = freq_to_sample_rate(&si, attr->sample_freq); + rate = hw_limit_rate(&si, rate); + attr->freq = 0; + attr->sample_period = rate; + } else { + /* The min/max sampling rates specifies the valid range + * of sample periods. If the specified sample period is + * out of range, limit the period to the range boundary. + */ + rate = hw_limit_rate(&si, hwc->sample_period); + + /* The perf core maintains a maximum sample rate that is + * configurable through the sysctl interface. Ensure the + * sampling rate does not exceed this value. This also helps + * to avoid throttling when pushing samples with + * perf_event_overflow(). + */ + if (sample_rate_to_freq(&si, rate) > + sysctl_perf_event_sample_rate) { + err = -EINVAL; + debug_sprintf_event(sfdbg, 1, "Sampling rate exceeds maximum perf sample rate\n"); + goto out; + } + } + SAMPL_RATE(hwc) = rate; + hw_init_period(hwc, SAMPL_RATE(hwc)); + + /* Initialize sample data overflow accounting */ + hwc->extra_reg.reg = REG_OVERFLOW; + OVERFLOW_REG(hwc) = 0; + + /* Allocate the per-CPU sampling buffer using the CPU information + * from the event. If the event is not pinned to a particular + * CPU (event->cpu == -1; or cpuhw == NULL), allocate sampling + * buffers for each online CPU. + */ + if (cpuhw) + /* Event is pinned to a particular CPU */ + err = allocate_buffers(cpuhw, hwc); + else { + /* Event is not pinned, allocate sampling buffer on + * each online CPU + */ + for_each_online_cpu(cpu) { + cpuhw = &per_cpu(cpu_hw_sf, cpu); + err = allocate_buffers(cpuhw, hwc); + if (err) + break; + } + } +out: + return err; +} + +static int cpumsf_pmu_event_init(struct perf_event *event) +{ + int err; + + /* No support for taken branch sampling */ + if (has_branch_stack(event)) + return -EOPNOTSUPP; + + switch (event->attr.type) { + case PERF_TYPE_RAW: + if ((event->attr.config != PERF_EVENT_CPUM_SF) && + (event->attr.config != PERF_EVENT_CPUM_SF_DIAG)) + return -ENOENT; + break; + case PERF_TYPE_HARDWARE: + /* Support sampling of CPU cycles in addition to the + * counter facility. However, the counter facility + * is more precise and, hence, restrict this PMU to + * sampling events only. + */ + if (event->attr.config != PERF_COUNT_HW_CPU_CYCLES) + return -ENOENT; + if (!is_sampling_event(event)) + return -ENOENT; + break; + default: + return -ENOENT; + } + + /* Check online status of the CPU to which the event is pinned */ + if (event->cpu >= nr_cpumask_bits || + (event->cpu >= 0 && !cpu_online(event->cpu))) + return -ENODEV; + + /* Force reset of idle/hv excludes regardless of what the + * user requested. + */ + if (event->attr.exclude_hv) + event->attr.exclude_hv = 0; + if (event->attr.exclude_idle) + event->attr.exclude_idle = 0; + + err = __hw_perf_event_init(event); + if (unlikely(err)) + if (event->destroy) + event->destroy(event); + return err; +} + +static void cpumsf_pmu_enable(struct pmu *pmu) +{ + struct cpu_hw_sf *cpuhw = &__get_cpu_var(cpu_hw_sf); + struct hw_perf_event *hwc; + int err; + + if (cpuhw->flags & PMU_F_ENABLED) + return; + + if (cpuhw->flags & PMU_F_ERR_MASK) + return; + + /* Check whether to extent the sampling buffer. + * + * Two conditions trigger an increase of the sampling buffer for a + * perf event: + * 1. Postponed buffer allocations from the event initialization. + * 2. Sampling overflows that contribute to pending allocations. + * + * Note that the extend_sampling_buffer() function disables the sampling + * facility, but it can be fully re-enabled using sampling controls that + * have been saved in cpumsf_pmu_disable(). + */ + if (cpuhw->event) { + hwc = &cpuhw->event->hw; + /* Account number of overflow-designated buffer extents */ + sfb_account_overflows(cpuhw, hwc); + if (sfb_has_pending_allocs(&cpuhw->sfb, hwc)) + extend_sampling_buffer(&cpuhw->sfb, hwc); + } + + /* (Re)enable the PMU and sampling facility */ + cpuhw->flags |= PMU_F_ENABLED; + barrier(); + + err = lsctl(&cpuhw->lsctl); + if (err) { + cpuhw->flags &= ~PMU_F_ENABLED; + pr_err("Loading sampling controls failed: op=%i err=%i\n", + 1, err); + return; + } + + debug_sprintf_event(sfdbg, 6, "pmu_enable: es=%i cs=%i ed=%i cd=%i " + "tear=%p dear=%p\n", cpuhw->lsctl.es, cpuhw->lsctl.cs, + cpuhw->lsctl.ed, cpuhw->lsctl.cd, + (void *) cpuhw->lsctl.tear, (void *) cpuhw->lsctl.dear); +} + +static void cpumsf_pmu_disable(struct pmu *pmu) +{ + struct cpu_hw_sf *cpuhw = &__get_cpu_var(cpu_hw_sf); + struct hws_lsctl_request_block inactive; + struct hws_qsi_info_block si; + int err; + + if (!(cpuhw->flags & PMU_F_ENABLED)) + return; + + if (cpuhw->flags & PMU_F_ERR_MASK) + return; + + /* Switch off sampling activation control */ + inactive = cpuhw->lsctl; + inactive.cs = 0; + inactive.cd = 0; + + err = lsctl(&inactive); + if (err) { + pr_err("Loading sampling controls failed: op=%i err=%i\n", + 2, err); + return; + } + + /* Save state of TEAR and DEAR register contents */ + if (!qsi(&si)) { + /* TEAR/DEAR values are valid only if the sampling facility is + * enabled. Note that cpumsf_pmu_disable() might be called even + * for a disabled sampling facility because cpumsf_pmu_enable() + * controls the enable/disable state. + */ + if (si.es) { + cpuhw->lsctl.tear = si.tear; + cpuhw->lsctl.dear = si.dear; + } + } else + debug_sprintf_event(sfdbg, 3, "cpumsf_pmu_disable: " + "qsi() failed with err=%i\n", err); + + cpuhw->flags &= ~PMU_F_ENABLED; +} + +/* perf_exclude_event() - Filter event + * @event: The perf event + * @regs: pt_regs structure + * @sde_regs: Sample-data-entry (sde) regs structure + * + * Filter perf events according to their exclude specification. + * + * Return non-zero if the event shall be excluded. + */ +static int perf_exclude_event(struct perf_event *event, struct pt_regs *regs, + struct perf_sf_sde_regs *sde_regs) +{ + if (event->attr.exclude_user && user_mode(regs)) + return 1; + if (event->attr.exclude_kernel && !user_mode(regs)) + return 1; + if (event->attr.exclude_guest && sde_regs->in_guest) + return 1; + if (event->attr.exclude_host && !sde_regs->in_guest) + return 1; + return 0; +} + +/* perf_push_sample() - Push samples to perf + * @event: The perf event + * @sample: Hardware sample data + * + * Use the hardware sample data to create perf event sample. The sample + * is the pushed to the event subsystem and the function checks for + * possible event overflows. If an event overflow occurs, the PMU is + * stopped. + * + * Return non-zero if an event overflow occurred. + */ +static int perf_push_sample(struct perf_event *event, struct sf_raw_sample *sfr) +{ + int overflow; + struct pt_regs regs; + struct perf_sf_sde_regs *sde_regs; + struct perf_sample_data data; + struct perf_raw_record raw; + + /* Setup perf sample */ + perf_sample_data_init(&data, 0, event->hw.last_period); + raw.size = sfr->size; + raw.data = sfr; + data.raw = &raw; + + /* Setup pt_regs to look like an CPU-measurement external interrupt + * using the Program Request Alert code. The regs.int_parm_long + * field which is unused contains additional sample-data-entry related + * indicators. + */ + memset(®s, 0, sizeof(regs)); + regs.int_code = 0x1407; + regs.int_parm = CPU_MF_INT_SF_PRA; + sde_regs = (struct perf_sf_sde_regs *) ®s.int_parm_long; + + regs.psw.addr = sfr->basic.ia; + if (sfr->basic.T) + regs.psw.mask |= PSW_MASK_DAT; + if (sfr->basic.W) + regs.psw.mask |= PSW_MASK_WAIT; + if (sfr->basic.P) + regs.psw.mask |= PSW_MASK_PSTATE; + switch (sfr->basic.AS) { + case 0x0: + regs.psw.mask |= PSW_ASC_PRIMARY; + break; + case 0x1: + regs.psw.mask |= PSW_ASC_ACCREG; + break; + case 0x2: + regs.psw.mask |= PSW_ASC_SECONDARY; + break; + case 0x3: + regs.psw.mask |= PSW_ASC_HOME; + break; + } + + /* The host-program-parameter (hpp) contains the sie control + * block that is set by sie64a() in entry64.S. Check if hpp + * refers to a valid control block and set sde_regs flags + * accordingly. This would allow to use hpp values for other + * purposes too. + * For now, simply use a non-zero value as guest indicator. + */ + if (sfr->basic.hpp) + sde_regs->in_guest = 1; + + overflow = 0; + if (perf_exclude_event(event, ®s, sde_regs)) + goto out; + if (perf_event_overflow(event, &data, ®s)) { + overflow = 1; + event->pmu->stop(event, 0); + } + perf_event_update_userpage(event); +out: + return overflow; +} + +static void perf_event_count_update(struct perf_event *event, u64 count) +{ + local64_add(count, &event->count); +} + +static int sample_format_is_valid(struct hws_combined_entry *sample, + unsigned int flags) +{ + if (likely(flags & PERF_CPUM_SF_BASIC_MODE)) + /* Only basic-sampling data entries with data-entry-format + * version of 0x0001 can be processed. + */ + if (sample->basic.def != 0x0001) + return 0; + if (flags & PERF_CPUM_SF_DIAG_MODE) + /* The data-entry-format number of diagnostic-sampling data + * entries can vary. Because diagnostic data is just passed + * through, do only a sanity check on the DEF. + */ + if (sample->diag.def < 0x8001) + return 0; + return 1; +} + +static int sample_is_consistent(struct hws_combined_entry *sample, + unsigned long flags) +{ + /* This check applies only to basic-sampling data entries of potentially + * combined-sampling data entries. Invalid entries cannot be processed + * by the PMU and, thus, do not deliver an associated + * diagnostic-sampling data entry. + */ + if (unlikely(!(flags & PERF_CPUM_SF_BASIC_MODE))) + return 0; + /* + * Samples are skipped, if they are invalid or for which the + * instruction address is not predictable, i.e., the wait-state bit is + * set. + */ + if (sample->basic.I || sample->basic.W) + return 0; + return 1; +} + +static void reset_sample_slot(struct hws_combined_entry *sample, + unsigned long flags) +{ + if (likely(flags & PERF_CPUM_SF_BASIC_MODE)) + sample->basic.def = 0; + if (flags & PERF_CPUM_SF_DIAG_MODE) + sample->diag.def = 0; +} + +static void sfr_store_sample(struct sf_raw_sample *sfr, + struct hws_combined_entry *sample) +{ + if (likely(sfr->format & PERF_CPUM_SF_BASIC_MODE)) + sfr->basic = sample->basic; + if (sfr->format & PERF_CPUM_SF_DIAG_MODE) + memcpy(&sfr->diag, &sample->diag, sfr->dsdes); +} + +static void debug_sample_entry(struct hws_combined_entry *sample, + struct hws_trailer_entry *te, + unsigned long flags) +{ + debug_sprintf_event(sfdbg, 4, "hw_collect_samples: Found unknown " + "sampling data entry: te->f=%i basic.def=%04x (%p)" + " diag.def=%04x (%p)\n", te->f, + sample->basic.def, &sample->basic, + (flags & PERF_CPUM_SF_DIAG_MODE) + ? sample->diag.def : 0xFFFF, + (flags & PERF_CPUM_SF_DIAG_MODE) + ? &sample->diag : NULL); +} + +/* hw_collect_samples() - Walk through a sample-data-block and collect samples + * @event: The perf event + * @sdbt: Sample-data-block table + * @overflow: Event overflow counter + * + * Walks through a sample-data-block and collects sampling data entries that are + * then pushed to the perf event subsystem. Depending on the sampling function, + * there can be either basic-sampling or combined-sampling data entries. A + * combined-sampling data entry consists of a basic- and a diagnostic-sampling + * data entry. The sampling function is determined by the flags in the perf + * event hardware structure. The function always works with a combined-sampling + * data entry but ignores the the diagnostic portion if it is not available. + * + * Note that the implementation focuses on basic-sampling data entries and, if + * such an entry is not valid, the entire combined-sampling data entry is + * ignored. + * + * The overflow variables counts the number of samples that has been discarded + * due to a perf event overflow. + */ +static void hw_collect_samples(struct perf_event *event, unsigned long *sdbt, + unsigned long long *overflow) +{ + unsigned long flags = SAMPL_FLAGS(&event->hw); + struct hws_combined_entry *sample; + struct hws_trailer_entry *te; + struct sf_raw_sample *sfr; + size_t sample_size; + + /* Prepare and initialize raw sample data */ + sfr = (struct sf_raw_sample *) RAWSAMPLE_REG(&event->hw); + sfr->format = flags & PERF_CPUM_SF_MODE_MASK; + + sample_size = event_sample_size(&event->hw); + te = (struct hws_trailer_entry *) trailer_entry_ptr(*sdbt); + sample = (struct hws_combined_entry *) *sdbt; + while ((unsigned long *) sample < (unsigned long *) te) { + /* Check for an empty sample */ + if (!sample->basic.def) + break; + + /* Update perf event period */ + perf_event_count_update(event, SAMPL_RATE(&event->hw)); + + /* Check sampling data entry */ + if (sample_format_is_valid(sample, flags)) { + /* If an event overflow occurred, the PMU is stopped to + * throttle event delivery. Remaining sample data is + * discarded. + */ + if (!*overflow) { + if (sample_is_consistent(sample, flags)) { + /* Deliver sample data to perf */ + sfr_store_sample(sfr, sample); + *overflow = perf_push_sample(event, sfr); + } + } else + /* Count discarded samples */ + *overflow += 1; + } else { + debug_sample_entry(sample, te, flags); + /* Sample slot is not yet written or other record. + * + * This condition can occur if the buffer was reused + * from a combined basic- and diagnostic-sampling. + * If only basic-sampling is then active, entries are + * written into the larger diagnostic entries. + * This is typically the case for sample-data-blocks + * that are not full. Stop processing if the first + * invalid format was detected. + */ + if (!te->f) + break; + } + + /* Reset sample slot and advance to next sample */ + reset_sample_slot(sample, flags); + sample += sample_size; + } +} + +/* hw_perf_event_update() - Process sampling buffer + * @event: The perf event + * @flush_all: Flag to also flush partially filled sample-data-blocks + * + * Processes the sampling buffer and create perf event samples. + * The sampling buffer position are retrieved and saved in the TEAR_REG + * register of the specified perf event. + * + * Only full sample-data-blocks are processed. Specify the flash_all flag + * to also walk through partially filled sample-data-blocks. It is ignored + * if PERF_CPUM_SF_FULL_BLOCKS is set. The PERF_CPUM_SF_FULL_BLOCKS flag + * enforces the processing of full sample-data-blocks only (trailer entries + * with the block-full-indicator bit set). + */ +static void hw_perf_event_update(struct perf_event *event, int flush_all) +{ + struct hw_perf_event *hwc = &event->hw; + struct hws_trailer_entry *te; + unsigned long *sdbt; + unsigned long long event_overflow, sampl_overflow, num_sdb, te_flags; + int done; + + if (flush_all && SDB_FULL_BLOCKS(hwc)) + flush_all = 0; + + sdbt = (unsigned long *) TEAR_REG(hwc); + done = event_overflow = sampl_overflow = num_sdb = 0; + while (!done) { + /* Get the trailer entry of the sample-data-block */ + te = (struct hws_trailer_entry *) trailer_entry_ptr(*sdbt); + + /* Leave loop if no more work to do (block full indicator) */ + if (!te->f) { + done = 1; + if (!flush_all) + break; + } + + /* Check the sample overflow count */ + if (te->overflow) + /* Account sample overflows and, if a particular limit + * is reached, extend the sampling buffer. + * For details, see sfb_account_overflows(). + */ + sampl_overflow += te->overflow; + + /* Timestamps are valid for full sample-data-blocks only */ + debug_sprintf_event(sfdbg, 6, "hw_perf_event_update: sdbt=%p " + "overflow=%llu timestamp=0x%llx\n", + sdbt, te->overflow, + (te->f) ? trailer_timestamp(te) : 0ULL); + + /* Collect all samples from a single sample-data-block and + * flag if an (perf) event overflow happened. If so, the PMU + * is stopped and remaining samples will be discarded. + */ + hw_collect_samples(event, sdbt, &event_overflow); + num_sdb++; + + /* Reset trailer (using compare-double-and-swap) */ + do { + te_flags = te->flags & ~SDB_TE_BUFFER_FULL_MASK; + te_flags |= SDB_TE_ALERT_REQ_MASK; + } while (!cmpxchg_double(&te->flags, &te->overflow, + te->flags, te->overflow, + te_flags, 0ULL)); + + /* Advance to next sample-data-block */ + sdbt++; + if (is_link_entry(sdbt)) + sdbt = get_next_sdbt(sdbt); + + /* Update event hardware registers */ + TEAR_REG(hwc) = (unsigned long) sdbt; + + /* Stop processing sample-data if all samples of the current + * sample-data-block were flushed even if it was not full. + */ + if (flush_all && done) + break; + + /* If an event overflow happened, discard samples by + * processing any remaining sample-data-blocks. + */ + if (event_overflow) + flush_all = 1; + } + + /* Account sample overflows in the event hardware structure */ + if (sampl_overflow) + OVERFLOW_REG(hwc) = DIV_ROUND_UP(OVERFLOW_REG(hwc) + + sampl_overflow, 1 + num_sdb); + if (sampl_overflow || event_overflow) + debug_sprintf_event(sfdbg, 4, "hw_perf_event_update: " + "overflow stats: sample=%llu event=%llu\n", + sampl_overflow, event_overflow); +} + +static void cpumsf_pmu_read(struct perf_event *event) +{ + /* Nothing to do ... updates are interrupt-driven */ +} + +/* Activate sampling control. + * Next call of pmu_enable() starts sampling. + */ +static void cpumsf_pmu_start(struct perf_event *event, int flags) +{ + struct cpu_hw_sf *cpuhw = &__get_cpu_var(cpu_hw_sf); + + if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED))) + return; + + if (flags & PERF_EF_RELOAD) + WARN_ON_ONCE(!(event->hw.state & PERF_HES_UPTODATE)); + + perf_pmu_disable(event->pmu); + event->hw.state = 0; + cpuhw->lsctl.cs = 1; + if (SAMPL_DIAG_MODE(&event->hw)) + cpuhw->lsctl.cd = 1; + perf_pmu_enable(event->pmu); +} + +/* Deactivate sampling control. + * Next call of pmu_enable() stops sampling. + */ +static void cpumsf_pmu_stop(struct perf_event *event, int flags) +{ + struct cpu_hw_sf *cpuhw = &__get_cpu_var(cpu_hw_sf); + + if (event->hw.state & PERF_HES_STOPPED) + return; + + perf_pmu_disable(event->pmu); + cpuhw->lsctl.cs = 0; + cpuhw->lsctl.cd = 0; + event->hw.state |= PERF_HES_STOPPED; + + if ((flags & PERF_EF_UPDATE) && !(event->hw.state & PERF_HES_UPTODATE)) { + hw_perf_event_update(event, 1); + event->hw.state |= PERF_HES_UPTODATE; + } + perf_pmu_enable(event->pmu); +} + +static int cpumsf_pmu_add(struct perf_event *event, int flags) +{ + struct cpu_hw_sf *cpuhw = &__get_cpu_var(cpu_hw_sf); + int err; + + if (cpuhw->flags & PMU_F_IN_USE) + return -EAGAIN; + + if (!cpuhw->sfb.sdbt) + return -EINVAL; + + err = 0; + perf_pmu_disable(event->pmu); + + event->hw.state = PERF_HES_UPTODATE | PERF_HES_STOPPED; + + /* Set up sampling controls. Always program the sampling register + * using the SDB-table start. Reset TEAR_REG event hardware register + * that is used by hw_perf_event_update() to store the sampling buffer + * position after samples have been flushed. + */ + cpuhw->lsctl.s = 0; + cpuhw->lsctl.h = 1; + cpuhw->lsctl.tear = (unsigned long) cpuhw->sfb.sdbt; + cpuhw->lsctl.dear = *(unsigned long *) cpuhw->sfb.sdbt; + cpuhw->lsctl.interval = SAMPL_RATE(&event->hw); + hw_reset_registers(&event->hw, cpuhw->sfb.sdbt); + + /* Ensure sampling functions are in the disabled state. If disabled, + * switch on sampling enable control. */ + if (WARN_ON_ONCE(cpuhw->lsctl.es == 1 || cpuhw->lsctl.ed == 1)) { + err = -EAGAIN; + goto out; + } + cpuhw->lsctl.es = 1; + if (SAMPL_DIAG_MODE(&event->hw)) + cpuhw->lsctl.ed = 1; + + /* Set in_use flag and store event */ + event->hw.idx = 0; /* only one sampling event per CPU supported */ + cpuhw->event = event; + cpuhw->flags |= PMU_F_IN_USE; + + if (flags & PERF_EF_START) + cpumsf_pmu_start(event, PERF_EF_RELOAD); +out: + perf_event_update_userpage(event); + perf_pmu_enable(event->pmu); + return err; +} + +static void cpumsf_pmu_del(struct perf_event *event, int flags) +{ + struct cpu_hw_sf *cpuhw = &__get_cpu_var(cpu_hw_sf); + + perf_pmu_disable(event->pmu); + cpumsf_pmu_stop(event, PERF_EF_UPDATE); + + cpuhw->lsctl.es = 0; + cpuhw->lsctl.ed = 0; + cpuhw->flags &= ~PMU_F_IN_USE; + cpuhw->event = NULL; + + perf_event_update_userpage(event); + perf_pmu_enable(event->pmu); +} + +static int cpumsf_pmu_event_idx(struct perf_event *event) +{ + return event->hw.idx; +} + +CPUMF_EVENT_ATTR(SF, SF_CYCLES_BASIC, PERF_EVENT_CPUM_SF); +CPUMF_EVENT_ATTR(SF, SF_CYCLES_BASIC_DIAG, PERF_EVENT_CPUM_SF_DIAG); + +static struct attribute *cpumsf_pmu_events_attr[] = { + CPUMF_EVENT_PTR(SF, SF_CYCLES_BASIC), + CPUMF_EVENT_PTR(SF, SF_CYCLES_BASIC_DIAG), + NULL, +}; + +PMU_FORMAT_ATTR(event, "config:0-63"); + +static struct attribute *cpumsf_pmu_format_attr[] = { + &format_attr_event.attr, + NULL, +}; + +static struct attribute_group cpumsf_pmu_events_group = { + .name = "events", + .attrs = cpumsf_pmu_events_attr, +}; +static struct attribute_group cpumsf_pmu_format_group = { + .name = "format", + .attrs = cpumsf_pmu_format_attr, +}; +static const struct attribute_group *cpumsf_pmu_attr_groups[] = { + &cpumsf_pmu_events_group, + &cpumsf_pmu_format_group, + NULL, +}; + +static struct pmu cpumf_sampling = { + .pmu_enable = cpumsf_pmu_enable, + .pmu_disable = cpumsf_pmu_disable, + + .event_init = cpumsf_pmu_event_init, + .add = cpumsf_pmu_add, + .del = cpumsf_pmu_del, + + .start = cpumsf_pmu_start, + .stop = cpumsf_pmu_stop, + .read = cpumsf_pmu_read, + + .event_idx = cpumsf_pmu_event_idx, + .attr_groups = cpumsf_pmu_attr_groups, +}; + +static void cpumf_measurement_alert(struct ext_code ext_code, + unsigned int alert, unsigned long unused) +{ + struct cpu_hw_sf *cpuhw; + + if (!(alert & CPU_MF_INT_SF_MASK)) + return; + inc_irq_stat(IRQEXT_CMS); + cpuhw = &__get_cpu_var(cpu_hw_sf); + + /* 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; + + /* The processing below must take care of multiple alert events that + * might be indicated concurrently. */ + + /* Program alert request */ + if (alert & CPU_MF_INT_SF_PRA) { + if (cpuhw->flags & PMU_F_IN_USE) + hw_perf_event_update(cpuhw->event, 0); + else + WARN_ON_ONCE(!(cpuhw->flags & PMU_F_IN_USE)); + } + + /* Report measurement alerts only for non-PRA codes */ + if (alert != CPU_MF_INT_SF_PRA) + debug_sprintf_event(sfdbg, 6, "measurement alert: 0x%x\n", alert); + + /* Sampling authorization change request */ + if (alert & CPU_MF_INT_SF_SACA) + qsi(&cpuhw->qsi); + + /* Loss of sample data due to high-priority machine activities */ + if (alert & CPU_MF_INT_SF_LSDA) { + pr_err("Sample data was lost\n"); + cpuhw->flags |= PMU_F_ERR_LSDA; + sf_disable(); + } + + /* Invalid sampling buffer entry */ + if (alert & (CPU_MF_INT_SF_IAE|CPU_MF_INT_SF_ISE)) { + pr_err("A sampling buffer entry is incorrect (alert=0x%x)\n", + alert); + cpuhw->flags |= PMU_F_ERR_IBE; + sf_disable(); + } +} + +static int cpumf_pmu_notifier(struct notifier_block *self, + unsigned long action, void *hcpu) +{ + unsigned int cpu = (long) hcpu; + int flags; + + /* Ignore the notification if no events are scheduled on the PMU. + * This might be racy... + */ + if (!atomic_read(&num_events)) + return NOTIFY_OK; + + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_ONLINE: + case CPU_ONLINE_FROZEN: + 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 param_get_sfb_size(char *buffer, const struct kernel_param *kp) +{ + if (!cpum_sf_avail()) + return -ENODEV; + return sprintf(buffer, "%lu,%lu", CPUM_SF_MIN_SDB, CPUM_SF_MAX_SDB); +} + +static int param_set_sfb_size(const char *val, const struct kernel_param *kp) +{ + int rc; + unsigned long min, max; + + if (!cpum_sf_avail()) + return -ENODEV; + if (!val || !strlen(val)) + return -EINVAL; + + /* Valid parameter values: "min,max" or "max" */ + min = CPUM_SF_MIN_SDB; + max = CPUM_SF_MAX_SDB; + if (strchr(val, ',')) + rc = (sscanf(val, "%lu,%lu", &min, &max) == 2) ? 0 : -EINVAL; + else + rc = kstrtoul(val, 10, &max); + + if (min < 2 || min >= max || max > get_num_physpages()) + rc = -EINVAL; + if (rc) + return rc; + + sfb_set_limits(min, max); + pr_info("The sampling buffer limits have changed to: " + "min=%lu max=%lu (diag=x%lu)\n", + CPUM_SF_MIN_SDB, CPUM_SF_MAX_SDB, CPUM_SF_SDB_DIAG_FACTOR); + return 0; +} + +#define param_check_sfb_size(name, p) __param_check(name, p, void) +static struct kernel_param_ops param_ops_sfb_size = { + .set = param_set_sfb_size, + .get = param_get_sfb_size, +}; + +#define RS_INIT_FAILURE_QSI 0x0001 +#define RS_INIT_FAILURE_BSDES 0x0002 +#define RS_INIT_FAILURE_ALRT 0x0003 +#define RS_INIT_FAILURE_PERF 0x0004 +static void __init pr_cpumsf_err(unsigned int reason) +{ + pr_err("Sampling facility support for perf is not available: " + "reason=%04x\n", reason); +} + +static int __init init_cpum_sampling_pmu(void) +{ + struct hws_qsi_info_block si; + int err; + + if (!cpum_sf_avail()) + return -ENODEV; + + memset(&si, 0, sizeof(si)); + if (qsi(&si)) { + pr_cpumsf_err(RS_INIT_FAILURE_QSI); + return -ENODEV; + } + + if (si.bsdes != sizeof(struct hws_basic_entry)) { + pr_cpumsf_err(RS_INIT_FAILURE_BSDES); + return -EINVAL; + } + + if (si.ad) + sfb_set_limits(CPUM_SF_MIN_SDB, CPUM_SF_MAX_SDB); + + sfdbg = debug_register(KMSG_COMPONENT, 2, 1, 80); + if (!sfdbg) + pr_err("Registering for s390dbf failed\n"); + debug_register_view(sfdbg, &debug_sprintf_view); + + err = register_external_irq(EXT_IRQ_MEASURE_ALERT, + cpumf_measurement_alert); + if (err) { + pr_cpumsf_err(RS_INIT_FAILURE_ALRT); + goto out; + } + + err = perf_pmu_register(&cpumf_sampling, "cpum_sf", PERF_TYPE_RAW); + if (err) { + pr_cpumsf_err(RS_INIT_FAILURE_PERF); + unregister_external_irq(EXT_IRQ_MEASURE_ALERT, + cpumf_measurement_alert); + goto out; + } + perf_cpu_notifier(cpumf_pmu_notifier); +out: + return err; +} +arch_initcall(init_cpum_sampling_pmu); +core_param(cpum_sfb_size, CPUM_SF_MAX_SDB, sfb_size, 0640); diff --git a/arch/s390/kernel/perf_event.c b/arch/s390/kernel/perf_event.c index f58f37f6682..61595c1f0a0 100644 --- a/arch/s390/kernel/perf_event.c +++ b/arch/s390/kernel/perf_event.c @@ -1,7 +1,7 @@ /* * Performance event support for s390x * - * Copyright IBM Corp. 2012 + * Copyright IBM Corp. 2012, 2013 * Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com> * * This program is free software; you can redistribute it and/or modify @@ -13,17 +13,22 @@ #include <linux/kernel.h> #include <linux/perf_event.h> +#include <linux/kvm_host.h> #include <linux/percpu.h> #include <linux/export.h> +#include <linux/seq_file.h> +#include <linux/spinlock.h> +#include <linux/sysfs.h> #include <asm/irq.h> #include <asm/cpu_mf.h> #include <asm/lowcore.h> #include <asm/processor.h> +#include <asm/sysinfo.h> const char *perf_pmu_name(void) { if (cpum_cf_avail() || cpum_sf_avail()) - return "CPU-measurement facilities (CPUMF)"; + return "CPU-Measurement Facilities (CPU-MF)"; return "pmu"; } EXPORT_SYMBOL(perf_pmu_name); @@ -34,35 +39,189 @@ int perf_num_counters(void) if (cpum_cf_avail()) num += PERF_CPUM_CF_MAX_CTR; + if (cpum_sf_avail()) + num += PERF_CPUM_SF_MAX_CTR; return num; } EXPORT_SYMBOL(perf_num_counters); -void perf_event_print_debug(void) +static struct kvm_s390_sie_block *sie_block(struct pt_regs *regs) { - struct cpumf_ctr_info cf_info; + struct stack_frame *stack = (struct stack_frame *) regs->gprs[15]; + + if (!stack) + return NULL; + + return (struct kvm_s390_sie_block *) stack->empty1[0]; +} + +static bool is_in_guest(struct pt_regs *regs) +{ + if (user_mode(regs)) + return false; +#if IS_ENABLED(CONFIG_KVM) + return instruction_pointer(regs) == (unsigned long) &sie_exit; +#else + return false; +#endif +} + +static unsigned long guest_is_user_mode(struct pt_regs *regs) +{ + return sie_block(regs)->gpsw.mask & PSW_MASK_PSTATE; +} + +static unsigned long instruction_pointer_guest(struct pt_regs *regs) +{ + return sie_block(regs)->gpsw.addr & PSW_ADDR_INSN; +} + +unsigned long perf_instruction_pointer(struct pt_regs *regs) +{ + return is_in_guest(regs) ? instruction_pointer_guest(regs) + : instruction_pointer(regs); +} + +static unsigned long perf_misc_guest_flags(struct pt_regs *regs) +{ + return guest_is_user_mode(regs) ? PERF_RECORD_MISC_GUEST_USER + : PERF_RECORD_MISC_GUEST_KERNEL; +} + +static unsigned long perf_misc_flags_sf(struct pt_regs *regs) +{ + struct perf_sf_sde_regs *sde_regs; unsigned long flags; - int cpu; - if (!cpum_cf_avail()) - return; + sde_regs = (struct perf_sf_sde_regs *) ®s->int_parm_long; + if (sde_regs->in_guest) + flags = user_mode(regs) ? PERF_RECORD_MISC_GUEST_USER + : PERF_RECORD_MISC_GUEST_KERNEL; + else + flags = user_mode(regs) ? PERF_RECORD_MISC_USER + : PERF_RECORD_MISC_KERNEL; + return flags; +} - local_irq_save(flags); +unsigned long perf_misc_flags(struct pt_regs *regs) +{ + /* Check if the cpum_sf PMU has created the pt_regs structure. + * In this case, perf misc flags can be easily extracted. Otherwise, + * do regular checks on the pt_regs content. + */ + if (regs->int_code == 0x1407 && regs->int_parm == CPU_MF_INT_SF_PRA) + if (!regs->gprs[15]) + return perf_misc_flags_sf(regs); + + if (is_in_guest(regs)) + return perf_misc_guest_flags(regs); + + return user_mode(regs) ? PERF_RECORD_MISC_USER + : PERF_RECORD_MISC_KERNEL; +} + +static void print_debug_cf(void) +{ + struct cpumf_ctr_info cf_info; + int cpu = smp_processor_id(); - cpu = smp_processor_id(); memset(&cf_info, 0, sizeof(cf_info)); - if (!qctri(&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)); - } +} + +static void print_debug_sf(void) +{ + struct hws_qsi_info_block si; + int cpu = smp_processor_id(); + + memset(&si, 0, sizeof(si)); + if (qsi(&si)) + return; + + pr_info("CPU[%i] CPUM_SF: basic=%i diag=%i min=%lu max=%lu cpu_speed=%u\n", + cpu, si.as, si.ad, si.min_sampl_rate, si.max_sampl_rate, + si.cpu_speed); + + if (si.as) + pr_info("CPU[%i] CPUM_SF: Basic-sampling: a=%i e=%i c=%i" + " bsdes=%i tear=%016lx dear=%016lx\n", cpu, + si.as, si.es, si.cs, si.bsdes, si.tear, si.dear); + if (si.ad) + pr_info("CPU[%i] CPUM_SF: Diagnostic-sampling: a=%i e=%i c=%i" + " dsdes=%i tear=%016lx dear=%016lx\n", cpu, + si.ad, si.ed, si.cd, si.dsdes, si.tear, si.dear); +} + +void perf_event_print_debug(void) +{ + unsigned long flags; + local_irq_save(flags); + if (cpum_cf_avail()) + print_debug_cf(); + if (cpum_sf_avail()) + print_debug_sf(); local_irq_restore(flags); } +/* Service level infrastructure */ +static void sl_print_counter(struct seq_file *m) +{ + struct cpumf_ctr_info ci; + + memset(&ci, 0, sizeof(ci)); + if (qctri(&ci)) + return; + + seq_printf(m, "CPU-MF: Counter facility: version=%u.%u " + "authorization=%04x\n", ci.cfvn, ci.csvn, ci.auth_ctl); +} + +static void sl_print_sampling(struct seq_file *m) +{ + struct hws_qsi_info_block si; + + memset(&si, 0, sizeof(si)); + if (qsi(&si)) + return; + + if (!si.as && !si.ad) + return; + + seq_printf(m, "CPU-MF: Sampling facility: min_rate=%lu max_rate=%lu" + " cpu_speed=%u\n", si.min_sampl_rate, si.max_sampl_rate, + si.cpu_speed); + if (si.as) + seq_printf(m, "CPU-MF: Sampling facility: mode=basic" + " sample_size=%u\n", si.bsdes); + if (si.ad) + seq_printf(m, "CPU-MF: Sampling facility: mode=diagnostic" + " sample_size=%u\n", si.dsdes); +} + +static void service_level_perf_print(struct seq_file *m, + struct service_level *sl) +{ + if (cpum_cf_avail()) + sl_print_counter(m); + if (cpum_sf_avail()) + sl_print_sampling(m); +} + +static struct service_level service_level_perf = { + .seq_print = service_level_perf_print, +}; + +static int __init service_level_perf_register(void) +{ + return register_service_level(&service_level_perf); +} +arch_initcall(service_level_perf_register); + /* See also arch/s390/kernel/traps.c */ static unsigned long __store_trace(struct perf_callchain_entry *entry, unsigned long sp, @@ -122,3 +281,44 @@ void perf_callchain_kernel(struct perf_callchain_entry *entry, __store_trace(entry, head, S390_lowcore.thread_info, S390_lowcore.thread_info + THREAD_SIZE); } + +/* Perf defintions for PMU event attributes in sysfs */ +ssize_t cpumf_events_sysfs_show(struct device *dev, + struct device_attribute *attr, char *page) +{ + struct perf_pmu_events_attr *pmu_attr; + + pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr); + return sprintf(page, "event=0x%04llx,name=%s\n", + pmu_attr->id, attr->attr.name); +} + +/* Reserve/release functions for sharing perf hardware */ +static DEFINE_SPINLOCK(perf_hw_owner_lock); +static void *perf_sampling_owner; + +int perf_reserve_sampling(void) +{ + int err; + + err = 0; + spin_lock(&perf_hw_owner_lock); + if (perf_sampling_owner) { + pr_warn("The sampling facility is already reserved by %p\n", + perf_sampling_owner); + err = -EBUSY; + } else + perf_sampling_owner = __builtin_return_address(0); + spin_unlock(&perf_hw_owner_lock); + return err; +} +EXPORT_SYMBOL(perf_reserve_sampling); + +void perf_release_sampling(void) +{ + spin_lock(&perf_hw_owner_lock); + WARN_ON(!perf_sampling_owner); + perf_sampling_owner = NULL; + spin_unlock(&perf_hw_owner_lock); +} +EXPORT_SYMBOL(perf_release_sampling); diff --git a/arch/s390/kernel/pgm_check.S b/arch/s390/kernel/pgm_check.S index 14bdecb6192..813ec726087 100644 --- a/arch/s390/kernel/pgm_check.S +++ b/arch/s390/kernel/pgm_check.S @@ -78,7 +78,7 @@ PGM_CHECK_DEFAULT /* 34 */ PGM_CHECK_DEFAULT /* 35 */ PGM_CHECK_DEFAULT /* 36 */ PGM_CHECK_DEFAULT /* 37 */ -PGM_CHECK_64BIT(do_asce_exception) /* 38 */ +PGM_CHECK_64BIT(do_dat_exception) /* 38 */ PGM_CHECK_64BIT(do_dat_exception) /* 39 */ PGM_CHECK_64BIT(do_dat_exception) /* 3a */ PGM_CHECK_64BIT(do_dat_exception) /* 3b */ diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c index 536d64579d9..93b9ca42e5c 100644 --- a/arch/s390/kernel/process.c +++ b/arch/s390/kernel/process.c @@ -61,41 +61,28 @@ unsigned long thread_saved_pc(struct task_struct *tsk) return sf->gprs[8]; } -/* - * The idle loop on a S390... - */ -static void default_idle(void) +void arch_cpu_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)) { + if (test_cpu_flag(CIF_MCCK_PENDING)) { local_mcck_enable(); local_irq_enable(); return; } /* Halt the cpu and keep track of cpu time accounting. */ vtime_stop_cpu(); + local_irq_enable(); } -void cpu_idle(void) +void arch_cpu_idle_exit(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(); - } + if (test_cpu_flag(CIF_MCCK_PENDING)) + s390_handle_mcck(); +} + +void arch_cpu_idle_dead(void) +{ + cpu_die(); } extern void __kprobes kernel_thread_starter(void); @@ -136,7 +123,6 @@ int copy_thread(unsigned long clone_flags, unsigned long new_stackp, 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; @@ -152,7 +138,7 @@ int copy_thread(unsigned long clone_flags, unsigned long new_stackp, if (unlikely(p->flags & PF_KTHREAD)) { /* kernel thread */ memset(&frame->childregs, 0, sizeof(struct pt_regs)); - frame->childregs.psw.mask = psw_kernel_bits | PSW_MASK_DAT | + frame->childregs.psw.mask = PSW_KERNEL_BITS | PSW_MASK_DAT | PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK; frame->childregs.psw.addr = PSW_ADDR_AMODE | (unsigned long) kernel_thread_starter; @@ -165,6 +151,7 @@ int copy_thread(unsigned long clone_flags, unsigned long new_stackp, } frame->childregs = *current_pt_regs(); frame->childregs.gprs[2] = 0; /* child returns 0 on fork. */ + frame->childregs.flags = 0; if (new_stackp) frame->childregs.gprs[15] = new_stackp; @@ -178,7 +165,8 @@ int copy_thread(unsigned long clone_flags, unsigned long new_stackp, * 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); + save_fp_ctl(¤t->thread.fp_regs.fpc); + save_fp_regs(current->thread.fp_regs.fprs); memcpy(&p->thread.fp_regs, ¤t->thread.fp_regs, sizeof(s390_fp_regs)); /* Set a new TLS ? */ @@ -186,7 +174,9 @@ int copy_thread(unsigned long clone_flags, unsigned long new_stackp, p->thread.acrs[0] = frame->childregs.gprs[6]; #else /* CONFIG_64BIT */ /* Save the fpu registers to new thread structure. */ - save_fp_regs(&p->thread.fp_regs); + save_fp_ctl(&p->thread.fp_regs.fpc); + save_fp_regs(p->thread.fp_regs.fprs); + p->thread.fp_regs.pad = 0; /* Set a new TLS ? */ if (clone_flags & CLONE_SETTLS) { unsigned long tls = frame->childregs.gprs[6]; @@ -218,10 +208,12 @@ int dump_fpu (struct pt_regs * regs, s390_fp_regs *fpregs) * 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); + save_fp_ctl(¤t->thread.fp_regs.fpc); + save_fp_regs(current->thread.fp_regs.fprs); memcpy(fpregs, ¤t->thread.fp_regs, sizeof(s390_fp_regs)); #else /* CONFIG_64BIT */ - save_fp_regs(fpregs); + save_fp_ctl(&fpregs->fpc); + save_fp_regs(fpregs->fprs); #endif /* CONFIG_64BIT */ return 1; } @@ -269,20 +261,18 @@ static inline unsigned long brk_rnd(void) unsigned long arch_randomize_brk(struct mm_struct *mm) { - unsigned long ret = PAGE_ALIGN(mm->brk + brk_rnd()); + unsigned long ret; - if (ret < mm->brk) - return mm->brk; - return ret; + ret = PAGE_ALIGN(mm->brk + brk_rnd()); + return (ret > mm->brk) ? ret : mm->brk; } unsigned long randomize_et_dyn(unsigned long base) { - unsigned long ret = PAGE_ALIGN(base + brk_rnd()); + unsigned long ret; if (!(current->flags & PF_RANDOMIZE)) return base; - if (ret < base) - return base; - return ret; + ret = PAGE_ALIGN(base + brk_rnd()); + return (ret > base) ? ret : base; } diff --git a/arch/s390/kernel/processor.c b/arch/s390/kernel/processor.c index 753c41d0ffd..24612029f45 100644 --- a/arch/s390/kernel/processor.c +++ b/arch/s390/kernel/processor.c @@ -21,7 +21,7 @@ static DEFINE_PER_CPU(struct cpuid, cpu_id); /* * cpu_init - initializes state that is per-CPU. */ -void __cpuinit cpu_init(void) +void cpu_init(void) { struct s390_idle_data *idle = &__get_cpu_var(s390_idle); struct cpuid *id = &__get_cpu_var(cpu_id); diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c index a314c57f4e9..5dc7ad9e2fb 100644 --- a/arch/s390/kernel/ptrace.c +++ b/arch/s390/kernel/ptrace.c @@ -47,7 +47,7 @@ enum s390_regset { REGSET_GENERAL_EXTENDED, }; -void update_per_regs(struct task_struct *task) +void update_cr_regs(struct task_struct *task) { struct pt_regs *regs = task_pt_regs(task); struct thread_struct *thread = &task->thread; @@ -56,17 +56,26 @@ void update_per_regs(struct task_struct *task) #ifdef CONFIG_64BIT /* Take care of the enable/disable of transactional execution. */ if (MACHINE_HAS_TE) { - unsigned long cr0, cr0_new; + unsigned long cr, cr_new; - __ctl_store(cr0, 0, 0); - /* set or clear transaction execution bits 8 and 9. */ + __ctl_store(cr, 0, 0); + /* Set or clear transaction execution TXC bit 8. */ + cr_new = cr | (1UL << 55); if (task->thread.per_flags & PER_FLAG_NO_TE) - cr0_new = cr0 & ~(3UL << 54); - else - cr0_new = cr0 | (3UL << 54); - /* Only load control register 0 if necessary. */ - if (cr0 != cr0_new) - __ctl_load(cr0_new, 0, 0); + cr_new &= ~(1UL << 55); + if (cr_new != cr) + __ctl_load(cr_new, 0, 0); + /* Set or clear transaction execution TDC bits 62 and 63. */ + __ctl_store(cr, 2, 2); + cr_new = cr & ~3UL; + if (task->thread.per_flags & PER_FLAG_TE_ABORT_RAND) { + if (task->thread.per_flags & PER_FLAG_TE_ABORT_RAND_TEND) + cr_new |= 1UL; + else + cr_new |= 2UL; + } + if (cr_new != cr) + __ctl_load(cr_new, 2, 2); } #endif /* Copy user specified PER registers */ @@ -76,7 +85,10 @@ void update_per_regs(struct task_struct *task) /* merge TIF_SINGLE_STEP into user specified PER registers. */ if (test_tsk_thread_flag(task, TIF_SINGLE_STEP)) { - new.control |= PER_EVENT_IFETCH; + if (test_tsk_thread_flag(task, TIF_BLOCK_STEP)) + new.control |= PER_EVENT_BRANCH; + else + new.control |= PER_EVENT_IFETCH; #ifdef CONFIG_64BIT new.control |= PER_CONTROL_SUSPENSION; new.control |= PER_EVENT_TRANSACTION_END; @@ -98,16 +110,20 @@ void update_per_regs(struct task_struct *task) void user_enable_single_step(struct task_struct *task) { + clear_tsk_thread_flag(task, TIF_BLOCK_STEP); 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_BLOCK_STEP); clear_tsk_thread_flag(task, TIF_SINGLE_STEP); - if (task == current) - update_per_regs(task); +} + +void user_enable_block_step(struct task_struct *task) +{ + set_tsk_thread_flag(task, TIF_SINGLE_STEP); + set_tsk_thread_flag(task, TIF_BLOCK_STEP); } /* @@ -120,7 +136,7 @@ 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); + clear_pt_regs_flag(task_pt_regs(task), PIF_PER_TRAP); task->thread.per_flags = 0; } @@ -190,9 +206,11 @@ static unsigned long __peek_user(struct task_struct *child, addr_t addr) * 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) + if (addr == (addr_t) &dummy->regs.psw.mask) { /* Return a clean psw mask. */ - tmp = psw_user_bits | (tmp & PSW_MASK_USER); + tmp &= PSW_MASK_USER | PSW_MASK_RI; + tmp |= PSW_USER_BITS; + } } else if (addr < (addr_t) &dummy->regs.orig_gpr2) { /* @@ -231,8 +249,7 @@ static unsigned long __peek_user(struct task_struct *child, addr_t addr) 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); + tmp <<= BITS_PER_LONG - 32; } else if (addr < (addr_t) (&dummy->regs.per_info + 1)) { /* @@ -313,11 +330,20 @@ static int __poke_user(struct task_struct *child, addr_t addr, addr_t data) /* * 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; + if (addr == (addr_t) &dummy->regs.psw.mask) { + unsigned long mask = PSW_MASK_USER; + + mask |= is_ri_task(child) ? PSW_MASK_RI : 0; + if ((data ^ PSW_USER_BITS) & ~mask) + /* Invalid psw mask. */ + return -EINVAL; + if ((data & PSW_MASK_ASC) == PSW_ASC_HOME) + /* Invalid address-space-control bits */ + return -EINVAL; + if ((data & PSW_MASK_EA) && !(data & PSW_MASK_BA)) + /* Invalid addressing mode bits */ + return -EINVAL; + } *(addr_t *)((addr_t) &task_pt_regs(child)->psw + addr) = data; } else if (addr < (addr_t) (&dummy->regs.orig_gpr2)) { @@ -355,10 +381,10 @@ static int __poke_user(struct task_struct *child, addr_t addr, addr_t data) /* * 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; + if (addr == (addr_t) &dummy->regs.fp_regs.fpc) + if ((unsigned int) data != 0 || + test_fp_ctl(data >> (BITS_PER_LONG - 32))) + return -EINVAL; offset = addr - (addr_t) &dummy->regs.fp_regs; *(addr_t *)((addr_t) &child->thread.fp_regs + offset) = data; @@ -447,6 +473,26 @@ long arch_ptrace(struct task_struct *child, long request, if (!MACHINE_HAS_TE) return -EIO; child->thread.per_flags |= PER_FLAG_NO_TE; + child->thread.per_flags &= ~PER_FLAG_TE_ABORT_RAND; + return 0; + case PTRACE_TE_ABORT_RAND: + if (!MACHINE_HAS_TE || (child->thread.per_flags & PER_FLAG_NO_TE)) + return -EIO; + switch (data) { + case 0UL: + child->thread.per_flags &= ~PER_FLAG_TE_ABORT_RAND; + break; + case 1UL: + child->thread.per_flags |= PER_FLAG_TE_ABORT_RAND; + child->thread.per_flags |= PER_FLAG_TE_ABORT_RAND_TEND; + break; + case 2UL: + child->thread.per_flags |= PER_FLAG_TE_ABORT_RAND; + child->thread.per_flags &= ~PER_FLAG_TE_ABORT_RAND_TEND; + break; + default: + return -EINVAL; + } return 0; default: /* Removing high order bit from addr (only for 31 bit). */ @@ -529,7 +575,8 @@ static u32 __peek_user_compat(struct task_struct *child, addr_t addr) 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); + tmp &= PSW32_MASK_USER | PSW32_MASK_RI; + tmp |= PSW32_USER_BITS; } else if (addr == (addr_t) &dummy32->regs.psw.addr) { /* Fake a 31 bit psw address. */ tmp = (__u32) regs->psw.addr | @@ -626,13 +673,19 @@ static int __poke_user_compat(struct task_struct *child, * psw, gprs, acrs and orig_gpr2 are stored on the stack */ if (addr == (addr_t) &dummy32->regs.psw.mask) { + __u32 mask = PSW32_MASK_USER; + + mask |= is_ri_task(child) ? PSW32_MASK_RI : 0; /* Build a 64 bit psw mask from 31 bit mask. */ - if ((tmp & ~PSW32_MASK_USER) != psw32_user_bits) + if ((tmp ^ PSW32_USER_BITS) & ~mask) /* Invalid psw mask. */ return -EINVAL; + if ((data & PSW32_MASK_ASC) == PSW32_ASC_HOME) + /* Invalid address-space-control bits */ + return -EINVAL; regs->psw.mask = (regs->psw.mask & ~PSW_MASK_USER) | (regs->psw.mask & PSW_MASK_BA) | - (__u64)(tmp & PSW32_MASK_USER) << 32; + (__u64)(tmp & mask) << 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; @@ -668,8 +721,7 @@ static int __poke_user_compat(struct task_struct *child, * 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. */ + test_fp_ctl(tmp)) return -EINVAL; offset = addr - (addr_t) &dummy32->regs.fp_regs; *(__u32 *)((addr_t) &child->thread.fp_regs + offset) = tmp; @@ -769,7 +821,7 @@ asmlinkage long do_syscall_trace_enter(struct pt_regs *regs) * debugger stored an invalid system call number. Skip * the system call and the system call restart handling. */ - clear_thread_flag(TIF_SYSCALL); + clear_pt_regs_flag(regs, PIF_SYSCALL); ret = -1; } @@ -867,8 +919,10 @@ 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); + if (target == current) { + save_fp_ctl(&target->thread.fp_regs.fpc); + save_fp_regs(target->thread.fp_regs.fprs); + } return user_regset_copyout(&pos, &count, &kbuf, &ubuf, &target->thread.fp_regs, 0, -1); @@ -881,19 +935,21 @@ static int s390_fpregs_set(struct task_struct *target, { int rc = 0; - if (target == current) - save_fp_regs(&target->thread.fp_regs); + if (target == current) { + save_fp_ctl(&target->thread.fp_regs.fpc); + save_fp_regs(target->thread.fp_regs.fprs); + } /* 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, + u32 ufpc[2] = { target->thread.fp_regs.fpc, 0 }; + rc = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &ufpc, 0, offsetof(s390_fp_regs, fprs)); if (rc) return rc; - if ((fpc[0] & ~FPC_VALID_MASK) != 0 || fpc[1] != 0) + if (ufpc[1] != 0 || test_fp_ctl(ufpc[0])) return -EINVAL; - target->thread.fp_regs.fpc = fpc[0]; + target->thread.fp_regs.fpc = ufpc[0]; } if (rc == 0 && count > 0) @@ -901,8 +957,10 @@ static int s390_fpregs_set(struct task_struct *target, target->thread.fp_regs.fprs, offsetof(s390_fp_regs, fprs), -1); - if (rc == 0 && target == current) - restore_fp_regs(&target->thread.fp_regs); + if (rc == 0 && target == current) { + restore_fp_ctl(&target->thread.fp_regs.fpc); + restore_fp_regs(target->thread.fp_regs.fprs); + } return rc; } @@ -1271,7 +1329,7 @@ int regs_query_register_offset(const char *name) if (!name || *name != 'r') return -EINVAL; - if (strict_strtoul(name + 1, 10, &offset)) + if (kstrtoul(name + 1, 10, &offset)) return -EINVAL; if (offset >= NUM_GPRS) return -EINVAL; diff --git a/arch/s390/kernel/runtime_instr.c b/arch/s390/kernel/runtime_instr.c index 077a99389b0..26b4ae96fdd 100644 --- a/arch/s390/kernel/runtime_instr.c +++ b/arch/s390/kernel/runtime_instr.c @@ -40,8 +40,6 @@ static void disable_runtime_instr(void) static void init_runtime_instr_cb(struct runtime_instr_cb *cb) { cb->buf_limit = 0xfff; - if (s390_user_mode == HOME_SPACE_MODE) - cb->home_space = 1; cb->int_requested = 1; cb->pstate = 1; cb->pstate_set_buf = 1; @@ -139,10 +137,11 @@ static int __init runtime_instr_init(void) if (!runtime_instr_avail()) return 0; - measurement_alert_subclass_register(); - rc = register_external_interrupt(0x1407, runtime_instr_int_handler); + irq_subclass_register(IRQ_SUBCLASS_MEASUREMENT_ALERT); + rc = register_external_irq(EXT_IRQ_MEASURE_ALERT, + runtime_instr_int_handler); if (rc) - measurement_alert_subclass_unregister(); + irq_subclass_unregister(IRQ_SUBCLASS_MEASUREMENT_ALERT); else pr_info("Runtime instrumentation facility initialized\n"); return rc; diff --git a/arch/s390/kernel/s390_ksyms.c b/arch/s390/kernel/s390_ksyms.c index 9bdbcef1da9..9f60467938d 100644 --- a/arch/s390/kernel/s390_ksyms.c +++ b/arch/s390/kernel/s390_ksyms.c @@ -5,8 +5,9 @@ #ifdef CONFIG_FUNCTION_TRACER EXPORT_SYMBOL(_mcount); #endif -#if defined(CONFIG_KVM) || defined(CONFIG_KVM_MODULE) +#if IS_ENABLED(CONFIG_KVM) EXPORT_SYMBOL(sie64a); +EXPORT_SYMBOL(sie_exit); #endif EXPORT_SYMBOL(memcpy); EXPORT_SYMBOL(memset); diff --git a/arch/s390/kernel/sclp.S b/arch/s390/kernel/sclp.S index b6506ee32a3..a41f2c99dcc 100644 --- a/arch/s390/kernel/sclp.S +++ b/arch/s390/kernel/sclp.S @@ -9,6 +9,7 @@ */ #include <linux/linkage.h> +#include <asm/irq.h> LC_EXT_NEW_PSW = 0x58 # addr of ext int handler LC_EXT_NEW_PSW_64 = 0x1b0 # addr of ext int handler 64 bit @@ -73,9 +74,9 @@ _sclp_wait_int: lpsw .LwaitpswS1-.LbaseS1(%r13) # wait until interrupt .LwaitS1: lh %r7,LC_EXT_INT_CODE - chi %r7,0x1004 # timeout? + chi %r7,EXT_IRQ_CLK_COMP # timeout? je .LtimeoutS1 - chi %r7,0x2401 # service int? + chi %r7,EXT_IRQ_SERVICE_SIG # service int? jne .LloopS1 sr %r2,%r2 l %r3,LC_EXT_INT_PARAM @@ -225,7 +226,7 @@ _sclp_print: ahi %r2,1 ltr %r0,%r0 # end of string? jz .LfinalizemtoS4 - chi %r0,0x15 # end of line (NL)? + chi %r0,0x0a # end of line (NL)? jz .LfinalizemtoS4 stc %r0,0(%r6,%r7) # copy to mto la %r11,0(%r6,%r7) diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index a5360de85ec..1e2264b46e4 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -47,7 +47,6 @@ #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> @@ -64,18 +63,6 @@ #include <asm/sclp.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.. */ @@ -91,10 +78,9 @@ 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 __initdata max_physmem_end; unsigned long VMALLOC_START; EXPORT_SYMBOL(VMALLOC_START); @@ -225,27 +211,19 @@ static void __init conmode_default(void) } } -#ifdef CONFIG_ZFCPDUMP -static void __init setup_zfcpdump(unsigned int console_devno) +#ifdef CONFIG_CRASH_DUMP +static void __init setup_zfcpdump(void) { - 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); + strcat(boot_command_line, " cio_ignore=all,!ipldev,!condev"); console_loglevel = 2; } #else -static inline void setup_zfcpdump(unsigned int console_devno) {} -#endif /* CONFIG_ZFCPDUMP */ +static inline void setup_zfcpdump(void) {} +#endif /* CONFIG_CRASH_DUMP */ /* * Reboot, halt and power_off stubs. They just call _machine_restart, @@ -294,6 +272,7 @@ EXPORT_SYMBOL_GPL(pm_power_off); static int __init early_parse_mem(char *p) { memory_end = memparse(p, &p); + memory_end &= PAGE_MASK; memory_end_set = 1; return 0; } @@ -308,43 +287,6 @@ static int __init parse_vmalloc(char *arg) } early_param("vmalloc", parse_vmalloc); -unsigned int s390_user_mode = PRIMARY_SPACE_MODE; -EXPORT_SYMBOL_GPL(s390_user_mode); - -static void __init set_user_mode_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 - uaccess = MACHINE_HAS_MVCOS ? uaccess_mvcos_switch : uaccess_pt; -} - -static int __init early_parse_user_mode(char *p) -{ - if (p && strcmp(p, "primary") == 0) - s390_user_mode = PRIMARY_SPACE_MODE; - else if (!p || strcmp(p, "home") == 0) - s390_user_mode = HOME_SPACE_MODE; - else - return 1; - return 0; -} -early_param("user_mode", early_parse_user_mode); - -static void __init setup_addressing_mode(void) -{ - if (s390_user_mode != PRIMARY_SPACE_MODE) - return; - set_user_mode_primary(); - if (MACHINE_HAS_MVCOS) - 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) @@ -356,32 +298,35 @@ static void __init setup_lowcore(void) */ 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.mask = PSW_KERNEL_BITS; lc->restart_psw.addr = PSW_ADDR_AMODE | (unsigned long) restart_int_handler; - lc->external_new_psw.mask = psw_kernel_bits | + 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 | + 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 | + 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.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 | + 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->kernel_stack = ((unsigned long) &init_thread_union) + + THREAD_SIZE - STACK_FRAME_OVERHEAD - sizeof(struct pt_regs); lc->async_stack = (unsigned long) - __alloc_bootmem(ASYNC_SIZE, ASYNC_SIZE, 0) + ASYNC_SIZE; + __alloc_bootmem(ASYNC_SIZE, ASYNC_SIZE, 0) + + ASYNC_SIZE - STACK_FRAME_OVERHEAD - sizeof(struct pt_regs); lc->panic_stack = (unsigned long) - __alloc_bootmem(PAGE_SIZE, PAGE_SIZE, 0) + PAGE_SIZE; + __alloc_bootmem(PAGE_SIZE, PAGE_SIZE, 0) + + PAGE_SIZE - STACK_FRAME_OVERHEAD - sizeof(struct pt_regs); 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; @@ -413,7 +358,7 @@ static void __init setup_lowcore(void) /* * Set up PSW restart to call ipl.c:do_restart(). Copy the relevant - * restart data to the absolute zero lowcore. This is necesary if + * restart data to the absolute zero lowcore. This is necessary if * PSW restart is done on an offline CPU that has lowcore zero. */ lc->restart_stack = (unsigned long) restart_stack; @@ -428,6 +373,10 @@ static void __init setup_lowcore(void) mem_assign_absolute(S390_lowcore.restart_source, lc->restart_source); mem_assign_absolute(S390_lowcore.restart_psw, lc->restart_psw); +#ifdef CONFIG_SMP + lc->spinlock_lockval = arch_spin_lockval(0); +#endif + set_prefix((u32)(unsigned long) lc); lowcore_ptr[0] = lc; } @@ -456,7 +405,8 @@ static struct resource __initdata *standard_resources[] = { static void __init setup_resources(void) { struct resource *res, *std_res, *sub_res; - int i, j; + struct memblock_region *reg; + int j; code_resource.start = (unsigned long) &_text; code_resource.end = (unsigned long) &_etext - 1; @@ -465,28 +415,13 @@ static void __init setup_resources(void) 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; + for_each_memblock(memory, reg) { 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; + + res->name = "System RAM"; + res->start = reg->base; + res->end = reg->base + reg->size - 1; request_resource(&iomem_resource, res); for (j = 0; j < ARRAY_SIZE(standard_resources); j++) { @@ -507,51 +442,14 @@ static void __init setup_resources(void) } } -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) - MODULES_LEN; - tmp = (memory_end ?: real_memory_size) / PAGE_SIZE; + tmp = (memory_end ?: max_physmem_end) / PAGE_SIZE; tmp = tmp * (sizeof(struct page) + PAGE_SIZE) + vmalloc_size; if (tmp <= (1UL << 42)) vmax = 1UL << 42; /* 3-level kernel page table */ @@ -571,25 +469,19 @@ static void __init setup_memory_end(void) /* Split remaining virtual space between 1:1 mapping & vmemmap array */ tmp = VMALLOC_START / (PAGE_SIZE + sizeof(struct page)); + /* vmemmap contains a multiple of PAGES_PER_SECTION struct pages */ + tmp = SECTION_ALIGN_UP(tmp); 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]; + memory_end = min(memory_end ?: max_physmem_end, tmp); + max_pfn = max_low_pfn = PFN_DOWN(memory_end); + memblock_remove(memory_end, ULONG_MAX); - if (chunk->addr >= memory_end) { - memset(chunk, 0, sizeof(*chunk)); - continue; - } - if (chunk->addr + chunk->size > memory_end) - chunk->size = memory_end - chunk->addr; - } + pr_notice("Max memory size: %luMB\n", memory_end >> 20); } static void __init setup_vmcoreinfo(void) @@ -600,98 +492,6 @@ static void __init setup_vmcoreinfo(void) #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. @@ -717,21 +517,44 @@ static struct notifier_block kdump_mem_nb = { #endif /* + * Make sure that the area behind memory_end is protected + */ +static void reserve_memory_end(void) +{ +#ifdef CONFIG_CRASH_DUMP + if (ipl_info.type == IPL_TYPE_FCP_DUMP && + !OLDMEM_BASE && sclp_get_hsa_size()) { + memory_end = sclp_get_hsa_size(); + memory_end &= PAGE_MASK; + memory_end_set = 1; + } +#endif + if (!memory_end_set) + return; + memblock_reserve(memory_end, ULONG_MAX); +} + +/* * Make sure that oldmem, where the dump is stored, is protected */ static void reserve_oldmem(void) { #ifdef CONFIG_CRASH_DUMP - if (!OLDMEM_BASE) - return; + if (OLDMEM_BASE) + /* Forget all memory above the running kdump system */ + memblock_reserve(OLDMEM_SIZE, (phys_addr_t)ULONG_MAX); +#endif +} - 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; +/* + * Make sure that oldmem, where the dump is stored, is protected + */ +static void remove_oldmem(void) +{ +#ifdef CONFIG_CRASH_DUMP + if (OLDMEM_BASE) + /* Forget all memory above the running kdump system */ + memblock_remove(OLDMEM_SIZE, (phys_addr_t)ULONG_MAX); #endif } @@ -742,168 +565,132 @@ static void __init reserve_crashkernel(void) { #ifdef CONFIG_CRASH_DUMP unsigned long long crash_base, crash_size; - char *msg = NULL; + phys_addr_t low, high; 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)) + if (rc || crash_size == 0) 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); + + if (memblock.memory.regions[0].size < crash_size) { + pr_info("crashkernel reservation failed: %s\n", + "first memory chunk must be at least crashkernel size"); return; } - if (verify_crash_base(crash_base, crash_size, &msg)) { - pr_info("crashkernel reservation failed: %s\n", msg); - unregister_memory_notifier(&kdump_mem_nb); + + low = crash_base ?: OLDMEM_BASE; + high = low + crash_size; + if (low >= OLDMEM_BASE && high <= OLDMEM_BASE + OLDMEM_SIZE) { + /* The crashkernel fits into OLDMEM, reuse OLDMEM */ + crash_base = low; + } else { + /* Find suitable area in free memory */ + low = max_t(unsigned long, crash_size, sclp_get_hsa_size()); + high = crash_base ? crash_base + crash_size : ULONG_MAX; + + if (crash_base && crash_base < low) { + pr_info("crashkernel reservation failed: %s\n", + "crash_base too low"); + return; + } + low = crash_base ?: low; + crash_base = memblock_find_in_range(low, high, crash_size, + KEXEC_CRASH_MEM_ALIGN); + } + + if (!crash_base) { + pr_info("crashkernel reservation failed: %s\n", + "no suitable area found"); return; } + + if (register_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); + memblock_remove(crash_base, crash_size); pr_info("Reserving %lluMB of memory at %lluMB " "for crashkernel (System RAM: %luMB)\n", - crash_size >> 20, crash_base >> 20, memory_end >> 20); + crash_size >> 20, crash_base >> 20, + (unsigned long)memblock.memory.total_size >> 20); os_info_crashkernel_add(crash_base, crash_size); #endif } -static void __init setup_memory(void) +/* + * Reserve the initrd from being used by memblock + */ +static void __init reserve_initrd(void) { - unsigned long bootmap_size; - unsigned long start_pfn, end_pfn; - int i; +#ifdef CONFIG_BLK_DEV_INITRD + initrd_start = INITRD_START; + initrd_end = initrd_start + INITRD_SIZE; + memblock_reserve(INITRD_START, INITRD_SIZE); +#endif +} - /* - * partially used pages are not usable - thus - * we are rounding upwards: - */ +/* + * Check for initrd being in usable memory + */ +static void __init check_initrd(void) +{ +#ifdef CONFIG_BLK_DEV_INITRD + if (INITRD_START && INITRD_SIZE && + !memblock_is_region_memory(INITRD_START, INITRD_SIZE)) { + pr_err("initrd does not fit memory.\n"); + memblock_free(INITRD_START, INITRD_SIZE); + initrd_start = initrd_end = 0; + } +#endif +} + +/* + * Reserve all kernel text + */ +static void __init reserve_kernel(void) +{ + unsigned long start_pfn; 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. + * Reserve memory used for lowcore/command line/kernel image. */ + memblock_reserve(0, (unsigned long)_ehead); + memblock_reserve((unsigned long)_stext, PFN_PHYS(start_pfn) + - (unsigned long)_stext); +} - 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; - +static void __init reserve_elfcorehdr(void) +{ #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; - } - } - } + if (is_kdump_kernel()) + memblock_reserve(elfcorehdr_addr - OLDMEM_BASE, + PAGE_ALIGN(elfcorehdr_size)); #endif +} - /* - * Initialize the boot-time allocator - */ - bootmap_size = init_bootmem(start_pfn, end_pfn); +static void __init setup_memory(void) +{ + struct memblock_region *reg; /* - * Register RAM areas with the bootmem allocator. + * Init storage key for present memory */ - - 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); - storage_key_init_range(PFN_PHYS(pfn), PFN_PHYS(end_chunk)); + for_each_memblock(memory, reg) { + storage_key_init_range(reg->base, reg->base + reg->size); } - 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 + /* Only cosmetics */ + memblock_enforce_memory_limit(memblock_end_of_DRAM()); } /* @@ -1008,6 +795,7 @@ static void __init setup_hwcaps(void) strcpy(elf_platform, "z196"); break; case 0x2827: + case 0x2828: strcpy(elf_platform, "zEC12"); break; } @@ -1051,29 +839,47 @@ void __init setup_arch(char **cmdline_p) ROOT_DEV = Root_RAM0; + /* Is init_mm really needed? */ 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(); + + /* Do some memory reservations *before* memory is added to memblock */ + reserve_memory_end(); reserve_oldmem(); - reserve_crashkernel(); + reserve_kernel(); + reserve_initrd(); + reserve_elfcorehdr(); + memblock_allow_resize(); + + /* Get information about *all* installed memory */ + detect_memory_memblock(); + + remove_oldmem(); + + /* + * Make sure all chunks are MAX_ORDER aligned so we don't need the + * extra checks that HOLES_IN_ZONE would require. + * + * Is this still required? + */ + memblock_trim_memory(1UL << (MAX_ORDER - 1 + PAGE_SHIFT)); + + setup_memory_end(); setup_memory(); + + check_initrd(); + reserve_crashkernel(); + setup_resources(); setup_vmcoreinfo(); setup_lowcore(); - + smp_fill_possible_mask(); cpu_init(); s390_init_cpu_topology(); @@ -1092,5 +898,37 @@ void __init setup_arch(char **cmdline_p) set_preferred_console(); /* Setup zfcpdump support */ - setup_zfcpdump(console_devno); + setup_zfcpdump(); +} + +#ifdef CONFIG_32BIT +static int no_removal_warning __initdata; + +static int __init parse_no_removal_warning(char *str) +{ + no_removal_warning = 1; + return 0; } +__setup("no_removal_warning", parse_no_removal_warning); + +static int __init removal_warning(void) +{ + if (no_removal_warning) + return 0; + printk(KERN_ALERT "\n\n"); + printk(KERN_CONT "Warning - you are using a 31 bit kernel!\n\n"); + printk(KERN_CONT "We plan to remove 31 bit kernel support from the kernel sources in March 2015.\n"); + printk(KERN_CONT "Currently we assume that nobody is using the 31 bit kernel on old 31 bit\n"); + printk(KERN_CONT "hardware anymore. If you think that the code should not be removed and also\n"); + printk(KERN_CONT "future versions of the Linux kernel should be able to run in 31 bit mode\n"); + printk(KERN_CONT "please let us know. Please write to:\n"); + printk(KERN_CONT "linux390@de.ibm.com (mail address) and/or\n"); + printk(KERN_CONT "linux-s390@vger.kernel.org (mailing list).\n\n"); + printk(KERN_CONT "Thank you!\n\n"); + printk(KERN_CONT "If this kernel runs on a 64 bit machine you may consider using a 64 bit kernel.\n"); + printk(KERN_CONT "This message can be disabled with the \"no_removal_warning\" kernel parameter.\n"); + schedule_timeout_uninterruptible(300 * HZ); + return 0; +} +early_initcall(removal_warning); +#endif diff --git a/arch/s390/kernel/signal.c b/arch/s390/kernel/signal.c index c3ff70a7b24..42b49f9e19b 100644 --- a/arch/s390/kernel/signal.c +++ b/arch/s390/kernel/signal.c @@ -48,54 +48,6 @@ typedef struct 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; - siginitset(&blocked, mask); - return sigsuspend(&blocked); -} - -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) { @@ -105,40 +57,48 @@ static int save_sigregs(struct pt_regs *regs, _sigregs __user *sregs) /* 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.mask = PSW_USER_BITS | + (regs->psw.mask & (PSW_MASK_USER | PSW_MASK_RI)); 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)); + sizeof(user_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); + save_fp_ctl(¤t->thread.fp_regs.fpc); + save_fp_regs(current->thread.fp_regs.fprs); memcpy(&user_sregs.fpregs, ¤t->thread.fp_regs, - sizeof(s390_fp_regs)); - return __copy_to_user(sregs, &user_sregs, sizeof(_sigregs)); + sizeof(user_sregs.fpregs)); + if (__copy_to_user(sregs, &user_sregs, sizeof(_sigregs))) + return -EFAULT; + return 0; } -/* 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); + if (__copy_from_user(&user_sregs, sregs, sizeof(user_sregs))) + return -EFAULT; + + if (!is_ri_task(current) && (user_sregs.regs.psw.mask & PSW_MASK_RI)) + return -EINVAL; + + /* Loading the floating-point-control word can fail. Do that first. */ + if (restore_fp_ctl(&user_sregs.fpregs.fpc)) + return -EINVAL; + + /* Use regs->psw.mask instead of PSW_USER_BITS to preserve PER bit. */ + regs->psw.mask = (regs->psw.mask & ~(PSW_MASK_USER | PSW_MASK_RI)) | + (user_sregs.regs.psw.mask & (PSW_MASK_USER | PSW_MASK_RI)); /* Check for invalid user address space control. */ - if ((regs->psw.mask & PSW_MASK_ASC) >= (psw_kernel_bits & PSW_MASK_ASC)) - regs->psw.mask = (psw_user_bits & PSW_MASK_ASC) | + if ((regs->psw.mask & PSW_MASK_ASC) == PSW_ASC_HOME) + regs->psw.mask = PSW_ASC_PRIMARY | (regs->psw.mask & ~PSW_MASK_ASC); /* Check for invalid amode */ if (regs->psw.mask & PSW_MASK_EA) @@ -146,15 +106,14 @@ static int restore_sigregs(struct pt_regs *regs, _sigregs __user *sregs) 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)); + sizeof(current->thread.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; + sizeof(current->thread.fp_regs)); - restore_fp_regs(¤t->thread.fp_regs); - clear_thread_flag(TIF_SYSCALL); /* No longer in a system call */ + restore_fp_regs(current->thread.fp_regs.fprs); + clear_pt_regs_flag(regs, PIF_SYSCALL); /* No longer in a system call */ return 0; } @@ -164,8 +123,6 @@ SYSCALL_DEFINE0(sigreturn) 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; set_current_blocked(&set); @@ -183,15 +140,12 @@ SYSCALL_DEFINE0(rt_sigreturn) 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; 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) + if (restore_altstack(&frame->uc.uc_stack)) goto badframe; return regs->gprs[2]; badframe: @@ -244,8 +198,6 @@ static int setup_frame(int sig, struct k_sigaction *ka, 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; @@ -279,7 +231,7 @@ static int setup_frame(int sig, struct k_sigaction *ka, regs->gprs[15] = (unsigned long) frame; /* Force default amode and default user address space control. */ regs->psw.mask = PSW_MASK_EA | PSW_MASK_BA | - (psw_user_bits & PSW_MASK_ASC) | + (PSW_USER_BITS & PSW_MASK_ASC) | (regs->psw.mask & ~PSW_MASK_ASC); regs->psw.addr = (unsigned long) ka->sa.sa_handler | PSW_ADDR_AMODE; @@ -313,8 +265,6 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, 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; @@ -325,10 +275,7 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, /* 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_altstack(&frame->uc.uc_stack, regs->gprs[15]); err |= save_sigregs(regs, &frame->uc.uc_mcontext); err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)); if (err) @@ -355,7 +302,7 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, regs->gprs[15] = (unsigned long) frame; /* Force default amode and default user address space control. */ regs->psw.mask = PSW_MASK_EA | PSW_MASK_BA | - (psw_user_bits & PSW_MASK_ASC) | + (PSW_USER_BITS & PSW_MASK_ASC) | (regs->psw.mask & ~PSW_MASK_ASC); regs->psw.addr = (unsigned long) ka->sa.sa_handler | PSW_ADDR_AMODE; @@ -409,7 +356,7 @@ void do_signal(struct pt_regs *regs) * call information. */ current_thread_info()->system_call = - test_thread_flag(TIF_SYSCALL) ? regs->int_code : 0; + test_pt_regs_flag(regs, PIF_SYSCALL) ? regs->int_code : 0; signr = get_signal_to_deliver(&info, &ka, regs, NULL); if (signr > 0) { @@ -437,7 +384,7 @@ void do_signal(struct pt_regs *regs) } } /* No longer in a system call */ - clear_thread_flag(TIF_SYSCALL); + clear_pt_regs_flag(regs, PIF_SYSCALL); if (is_compat_task()) handle_signal32(signr, &ka, &info, oldset, regs); @@ -447,7 +394,7 @@ void do_signal(struct pt_regs *regs) } /* No handlers present - check for system call restart */ - clear_thread_flag(TIF_SYSCALL); + clear_pt_regs_flag(regs, PIF_SYSCALL); if (current_thread_info()->system_call) { regs->int_code = current_thread_info()->system_call; switch (regs->gprs[2]) { @@ -460,9 +407,9 @@ void do_signal(struct pt_regs *regs) case -ERESTARTNOINTR: /* Restart system call with magic TIF bit. */ regs->gprs[2] = regs->orig_gpr2; - set_thread_flag(TIF_SYSCALL); + set_pt_regs_flag(regs, PIF_SYSCALL); if (test_thread_flag(TIF_SINGLE_STEP)) - set_thread_flag(TIF_PER_TRAP); + clear_pt_regs_flag(regs, PIF_PER_TRAP); break; } } diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index 7433a2f9e5c..243c7e51260 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -49,7 +49,6 @@ enum { ec_schedule = 0, - ec_call_function, ec_call_function_single, ec_stop_cpu, }; @@ -60,7 +59,7 @@ enum { }; struct pcpu { - struct cpu cpu; + struct cpu *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 */ @@ -83,21 +82,6 @@ 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; @@ -160,13 +144,13 @@ 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; + if (test_and_set_bit(ec_bit, &pcpu->ec_mask)) + return; + 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) +static int pcpu_alloc_lowcore(struct pcpu *pcpu, int cpu) { struct _lowcore *lc; @@ -181,9 +165,12 @@ static int __cpuinit pcpu_alloc_lowcore(struct pcpu *pcpu, int cpu) 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->async_stack = pcpu->async_stack + ASYNC_SIZE + - STACK_FRAME_OVERHEAD - sizeof(struct pt_regs); + lc->panic_stack = pcpu->panic_stack + PAGE_SIZE + - STACK_FRAME_OVERHEAD - sizeof(struct pt_regs); lc->cpu_nr = cpu; + lc->spinlock_lockval = arch_spin_lockval(cpu); #ifndef CONFIG_64BIT if (MACHINE_HAS_IEEE) { lc->extended_save_area_addr = get_zeroed_page(GFP_KERNEL); @@ -235,8 +222,12 @@ static void pcpu_prepare_secondary(struct pcpu *pcpu, int cpu) { struct _lowcore *lc = pcpu->lowcore; + if (MACHINE_HAS_TLB_LC) + cpumask_set_cpu(cpu, &init_mm.context.cpu_attach_mask); + cpumask_set_cpu(cpu, mm_cpumask(&init_mm)); atomic_inc(&init_mm.context.attach_count); lc->cpu_nr = cpu; + lc->spinlock_lockval = arch_spin_lockval(cpu); lc->percpu_offset = __per_cpu_offset[cpu]; lc->kernel_asce = S390_lowcore.kernel_asce; lc->machine_flags = S390_lowcore.machine_flags; @@ -253,7 +244,8 @@ 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->kernel_stack = (unsigned long) task_stack_page(tsk) + + THREAD_SIZE - STACK_FRAME_OVERHEAD - sizeof(struct pt_regs); lc->thread_info = (unsigned long) task_thread_info(tsk); lc->current_task = (unsigned long) tsk; lc->user_timer = ti->user_timer; @@ -281,7 +273,7 @@ static void pcpu_delegate(struct pcpu *pcpu, void (*func)(void *), struct _lowcore *lc = lowcore_ptr[pcpu - pcpu_devices]; unsigned long source_cpu = stap(); - __load_psw_mask(psw_kernel_bits); + __load_psw_mask(PSW_KERNEL_BITS); if (pcpu->address == source_cpu) func(data); /* should not return */ /* Stop target cpu (if func returns this stops the current cpu). */ @@ -360,21 +352,21 @@ void smp_yield_cpu(int cpu) * Send cpus emergency shutdown signal. This gives the cpus the * opportunity to complete outstanding interrupts. */ -void smp_emergency_stop(cpumask_t *cpumask) +static void smp_emergency_stop(cpumask_t *cpumask) { u64 end; int cpu; - end = get_clock() + (1000000UL << 12); + end = get_tod_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_CC_BUSY && - get_clock() < end) + get_tod_clock() < end) cpu_relax(); } - while (get_clock() < end) { + while (get_tod_clock() < end) { for_each_cpu(cpu, cpumask) if (pcpu_stopped(pcpu_devices + cpu)) cpumask_clear_cpu(cpu, cpumask); @@ -393,7 +385,7 @@ void smp_send_stop(void) int cpu; /* Disable all interrupts/machine checks */ - __load_psw_mask(psw_kernel_bits | PSW_MASK_DAT); + __load_psw_mask(PSW_KERNEL_BITS | PSW_MASK_DAT); trace_hardirqs_off(); debug_set_critical(); @@ -413,46 +405,28 @@ void smp_send_stop(void) } /* - * 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) +static void smp_handle_ext_call(void) { unsigned long bits; - int cpu; - - cpu = smp_processor_id(); - if (ext_code.code == 0x1202) - inc_irq_stat(IRQEXT_EXC); - else - inc_irq_stat(IRQEXT_EMS); - /* - * handle bit signal external calls - */ - bits = xchg(&pcpu_devices[cpu].ec_mask, 0); + /* handle bit signal external calls */ + bits = xchg(&pcpu_devices[smp_processor_id()].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(); +} +static void do_ext_call_interrupt(struct ext_code ext_code, + unsigned int param32, unsigned long param64) +{ + inc_irq_stat(ext_code.code == 0x1202 ? IRQEXT_EXC : IRQEXT_EMS); + smp_handle_ext_call(); } void arch_send_call_function_ipi_mask(const struct cpumask *mask) @@ -460,7 +434,7 @@ 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); + pcpu_ec_call(pcpu_devices + cpu, ec_call_function_single); } void arch_send_call_function_single_ipi(int cpu) @@ -538,10 +512,7 @@ void smp_ctl_clear_bit(int cr, int bit) } 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); +#ifdef CONFIG_CRASH_DUMP static void __init smp_get_save_area(int cpu, u16 address) { @@ -553,23 +524,15 @@ static void __init smp_get_save_area(int cpu, u16 address) 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); + save_area = dump_save_area_create(cpu); 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)); @@ -586,11 +549,11 @@ int smp_store_status(int cpu) return 0; } -#else /* CONFIG_ZFCPDUMP || CONFIG_CRASH_DUMP */ +#else /* CONFIG_CRASH_DUMP */ static inline void smp_get_save_area(int cpu, u16 address) { } -#endif /* CONFIG_ZFCPDUMP || CONFIG_CRASH_DUMP */ +#endif /* CONFIG_CRASH_DUMP */ void smp_cpu_set_polarization(int cpu, int val) { @@ -623,10 +586,9 @@ static struct sclp_cpu_info *smp_get_cpu_info(void) return info; } -static int __cpuinit smp_add_present_cpu(int cpu); +static int smp_add_present_cpu(int cpu); -static int __cpuinit __smp_rescan_cpus(struct sclp_cpu_info *info, - int sysfs_add) +static int __smp_rescan_cpus(struct sclp_cpu_info *info, int sysfs_add) { struct pcpu *pcpu; cpumask_t avail; @@ -642,7 +604,7 @@ static int __cpuinit __smp_rescan_cpus(struct sclp_cpu_info *info, continue; pcpu = pcpu_devices + cpu; pcpu->address = info->cpu[i].address; - pcpu->state = (cpu >= info->configured) ? + pcpu->state = (i >= info->configured) ? CPU_STATE_STANDBY : CPU_STATE_CONFIGURED; smp_cpu_set_polarization(cpu, POLARIZATION_UNKNOWN); set_cpu_present(cpu, true); @@ -692,16 +654,16 @@ static void __init smp_detect_cpus(void) /* * Activate a secondary processor. */ -static void __cpuinit smp_start_secondary(void *cpuvoid) +static void smp_start_secondary(void *cpuvoid) { - S390_lowcore.last_update_clock = get_clock(); + S390_lowcore.last_update_clock = get_tod_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); + __load_psw_mask(PSW_KERNEL_BITS | PSW_MASK_DAT); cpu_init(); preempt_disable(); init_cpu_timer(); @@ -711,12 +673,11 @@ static void __cpuinit smp_start_secondary(void *cpuvoid) set_cpu_online(smp_processor_id(), true); inc_irq_stat(CPU_RST); local_irq_enable(); - /* cpu_idle will call schedule for us */ - cpu_idle(); + cpu_startup_entry(CPUHP_ONLINE); } /* Upping and downing of CPUs */ -int __cpuinit __cpu_up(unsigned int cpu, struct task_struct *tidle) +int __cpu_up(unsigned int cpu, struct task_struct *tidle) { struct pcpu *pcpu; int rc; @@ -739,18 +700,14 @@ int __cpuinit __cpu_up(unsigned int cpu, struct task_struct *tidle) return 0; } -static int __init setup_possible_cpus(char *s) -{ - int max, cpu; +static unsigned int setup_possible_cpus __initdata; - 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); +static int __init _setup_possible_cpus(char *s) +{ + get_option(&s, &setup_possible_cpus); return 0; } -early_param("possible_cpus", setup_possible_cpus); +early_param("possible_cpus", _setup_possible_cpus); #ifdef CONFIG_HOTPLUG_CPU @@ -758,6 +715,8 @@ int __cpu_disable(void) { unsigned long cregs[16]; + /* Handle possible pending IPIs */ + smp_handle_ext_call(); set_cpu_online(smp_processor_id(), false); /* Disable pseudo page faults on this cpu. */ pfault_fini(); @@ -780,6 +739,9 @@ void __cpu_die(unsigned int cpu) cpu_relax(); pcpu_free_lowcore(pcpu); atomic_dec(&init_mm.context.attach_count); + cpumask_clear_cpu(cpu, mm_cpumask(&init_mm)); + if (MACHINE_HAS_TLB_LC) + cpumask_clear_cpu(cpu, &init_mm.context.cpu_attach_mask); } void __noreturn cpu_die(void) @@ -791,13 +753,24 @@ void __noreturn cpu_die(void) #endif /* CONFIG_HOTPLUG_CPU */ +void __init smp_fill_possible_mask(void) +{ + unsigned int possible, sclp, cpu; + + sclp = sclp_get_max_cpu() ?: nr_cpu_ids; + possible = setup_possible_cpus ?: nr_cpu_ids; + possible = min(possible, sclp); + for (cpu = 0; cpu < possible && cpu < nr_cpu_ids; cpu++) + set_cpu_possible(cpu, true); +} + 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) + if (register_external_irq(EXT_IRQ_EMERGENCY_SIG, do_ext_call_interrupt)) panic("Couldn't request external interrupt 0x1201"); /* request the 0x1202 external call external interrupt */ - if (register_external_interrupt(0x1202, do_ext_call_interrupt) != 0) + if (register_external_irq(EXT_IRQ_EXTERNAL_CALL, do_ext_call_interrupt)) panic("Couldn't request external interrupt 0x1202"); smp_detect_cpus(); } @@ -810,8 +783,10 @@ void __init smp_prepare_boot_cpu(void) 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; + pcpu->async_stack = S390_lowcore.async_stack - ASYNC_SIZE + + STACK_FRAME_OVERHEAD + sizeof(struct pt_regs); + pcpu->panic_stack = S390_lowcore.panic_stack - PAGE_SIZE + + STACK_FRAME_OVERHEAD + sizeof(struct pt_regs); S390_lowcore.percpu_offset = __per_cpu_offset[0]; smp_cpu_set_polarization(0, POLARIZATION_UNKNOWN); set_cpu_present(0, true); @@ -825,6 +800,7 @@ void __init smp_cpus_done(unsigned int max_cpus) void __init smp_setup_processor_id(void) { S390_lowcore.cpu_nr = 0; + S390_lowcore.spinlock_lockval = arch_spin_lockval(0); } /* @@ -934,7 +910,7 @@ static ssize_t show_idle_count(struct device *dev, idle_count = ACCESS_ONCE(idle->idle_count); if (ACCESS_ONCE(idle->clock_idle_enter)) idle_count++; - } while ((sequence & 1) || (idle->sequence != sequence)); + } while ((sequence & 1) || (ACCESS_ONCE(idle->sequence) != sequence)); return sprintf(buf, "%llu\n", idle_count); } static DEVICE_ATTR(idle_count, 0444, show_idle_count, NULL); @@ -947,12 +923,12 @@ static ssize_t show_idle_time(struct device *dev, unsigned int sequence; do { - now = get_clock(); + now = get_tod_clock(); sequence = ACCESS_ONCE(idle->sequence); idle_time = ACCESS_ONCE(idle->idle_time); idle_enter = ACCESS_ONCE(idle->clock_idle_enter); idle_exit = ACCESS_ONCE(idle->clock_idle_exit); - } while ((sequence & 1) || (idle->sequence != sequence)); + } while ((sequence & 1) || (ACCESS_ONCE(idle->sequence) != sequence)); idle_time += idle_enter ? ((idle_exit ? : now) - idle_enter) : 0; return sprintf(buf, "%llu\n", idle_time >> 12); } @@ -968,11 +944,11 @@ 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) +static int 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 cpu *c = pcpu_devices[cpu].cpu; struct device *s = &c->dev; int err = 0; @@ -987,12 +963,17 @@ static int __cpuinit smp_cpu_notify(struct notifier_block *self, return notifier_from_errno(err); } -static int __cpuinit smp_add_present_cpu(int cpu) +static int smp_add_present_cpu(int cpu) { - struct cpu *c = &pcpu_devices[cpu].cpu; - struct device *s = &c->dev; + struct device *s; + struct cpu *c; int rc; + c = kzalloc(sizeof(*c), GFP_KERNEL); + if (!c) + return -ENOMEM; + pcpu_devices[cpu].cpu = c; + s = &c->dev; c->hotpluggable = 1; rc = register_cpu(c, cpu); if (rc) @@ -1059,19 +1040,24 @@ static DEVICE_ATTR(rescan, 0200, NULL, rescan_store); static int __init s390_smp_init(void) { - int cpu, rc; + int cpu, rc = 0; - hotcpu_notifier(smp_cpu_notify, 0); #ifdef CONFIG_HOTPLUG_CPU rc = device_create_file(cpu_subsys.dev_root, &dev_attr_rescan); if (rc) return rc; #endif + cpu_notifier_register_begin(); for_each_present_cpu(cpu) { rc = smp_add_present_cpu(cpu); if (rc) - return rc; + goto out; } - return 0; + + __hotcpu_notifier(smp_cpu_notify, 0); + +out: + cpu_notifier_register_done(); + return rc; } subsys_initcall(s390_smp_init); diff --git a/arch/s390/kernel/suspend.c b/arch/s390/kernel/suspend.c index aa1494d0e38..a7a7537ce1e 100644 --- a/arch/s390/kernel/suspend.c +++ b/arch/s390/kernel/suspend.c @@ -10,6 +10,10 @@ #include <linux/suspend.h> #include <linux/mm.h> #include <asm/ctl_reg.h> +#include <asm/ipl.h> +#include <asm/cio.h> +#include <asm/pci.h> +#include "entry.h" /* * References to section boundaries @@ -41,6 +45,7 @@ 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; +unsigned long suspend_zero_pages; /* * For each page in the hibernation image one additional byte is @@ -149,6 +154,36 @@ int pfn_is_nosave(unsigned long pfn) return 0; } +/* + * PM notifier callback for suspend + */ +static int suspend_pm_cb(struct notifier_block *nb, unsigned long action, + void *ptr) +{ + switch (action) { + case PM_SUSPEND_PREPARE: + case PM_HIBERNATION_PREPARE: + suspend_zero_pages = __get_free_pages(GFP_KERNEL, LC_ORDER); + if (!suspend_zero_pages) + return NOTIFY_BAD; + break; + case PM_POST_SUSPEND: + case PM_POST_HIBERNATION: + free_pages(suspend_zero_pages, LC_ORDER); + break; + default: + return NOTIFY_DONE; + } + return NOTIFY_OK; +} + +static int __init suspend_pm_init(void) +{ + pm_notifier(suspend_pm_cb, 0); + return 0; +} +arch_initcall(suspend_pm_init); + void save_processor_state(void) { /* swsusp_arch_suspend() actually saves all cpu register contents. @@ -180,3 +215,11 @@ void restore_processor_state(void) __ctl_set_bit(0,28); local_mcck_enable(); } + +/* Called at the end of swsusp_arch_resume */ +void s390_early_resume(void) +{ + lgr_info_log(); + channel_subsystem_reinit(); + zpci_rescan(); +} diff --git a/arch/s390/kernel/swsusp_asm64.S b/arch/s390/kernel/swsusp_asm64.S index d4ca4e0617b..6b09fdffbd2 100644 --- a/arch/s390/kernel/swsusp_asm64.S +++ b/arch/s390/kernel/swsusp_asm64.S @@ -36,8 +36,8 @@ ENTRY(swsusp_arch_suspend) /* Store prefix register on stack */ stpx __SF_EMPTY(%r15) - /* Save prefix register contents for lowcore */ - llgf %r4,__SF_EMPTY(%r15) + /* Save prefix register contents for lowcore copy */ + llgf %r10,__SF_EMPTY(%r15) /* Get pointer to save area */ lghi %r1,0x1000 @@ -91,7 +91,18 @@ ENTRY(swsusp_arch_suspend) xc __SF_EMPTY(4,%r15),__SF_EMPTY(%r15) spx __SF_EMPTY(%r15) + /* Save absolute zero pages */ + larl %r2,suspend_zero_pages + lg %r2,0(%r2) + lghi %r4,0 + lghi %r3,2*PAGE_SIZE + lghi %r5,2*PAGE_SIZE +1: mvcle %r2,%r4,0 + jo 1b + + /* Copy lowcore to absolute zero lowcore */ lghi %r2,0 + lgr %r4,%r10 lghi %r3,2*PAGE_SIZE lghi %r5,2*PAGE_SIZE 1: mvcle %r2,%r4,0 @@ -248,8 +259,20 @@ restore_registers: /* Load old stack */ lg %r15,0x2f8(%r13) + /* Save prefix register */ + mvc __SF_EMPTY(4,%r15),0x318(%r13) + + /* Restore absolute zero pages */ + lghi %r2,0 + larl %r4,suspend_zero_pages + lg %r4,0(%r4) + lghi %r3,2*PAGE_SIZE + lghi %r5,2*PAGE_SIZE +1: mvcle %r2,%r4,0 + jo 1b + /* Restore prefix register */ - spx 0x318(%r13) + spx __SF_EMPTY(%r15) /* Activate DAT */ stosm __SF_EMPTY(%r15),0x04 @@ -258,11 +281,8 @@ restore_registers: 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 + /* Call arch specific early resume code */ + brasl %r14,s390_early_resume /* Return 0 */ lmg %r6,%r15,STACK_FRAME_OVERHEAD + __SF_GPRS(%r15) diff --git a/arch/s390/kernel/sys_s390.c b/arch/s390/kernel/sys_s390.c index d0964d22adb..23eb222c165 100644 --- a/arch/s390/kernel/sys_s390.c +++ b/arch/s390/kernel/sys_s390.c @@ -132,19 +132,9 @@ SYSCALL_DEFINE1(s390_fadvise64_64, struct fadvise64_64_args __user *, args) * 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) +SYSCALL_DEFINE5(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 index 6a6c61f94dd..fe5cdf29a00 100644 --- a/arch/s390/kernel/syscalls.S +++ b/arch/s390/kernel/syscalls.S @@ -9,347 +9,350 @@ #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_exit,sys_exit,compat_sys_exit) 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_read,sys_read,compat_sys_s390_read) +SYSCALL(sys_write,sys_write,compat_sys_s390_write) +SYSCALL(sys_open,sys_open,compat_sys_open) /* 5 */ +SYSCALL(sys_close,sys_close,compat_sys_close) 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*/ +SYSCALL(sys_creat,sys_creat,compat_sys_creat) +SYSCALL(sys_link,sys_link,compat_sys_link) +SYSCALL(sys_unlink,sys_unlink,compat_sys_unlink) /* 10 */ +SYSCALL(sys_execve,sys_execve,compat_sys_execve) +SYSCALL(sys_chdir,sys_chdir,compat_sys_chdir) +SYSCALL(sys_time,sys_ni_syscall,compat_sys_time) /* old time syscall */ +SYSCALL(sys_mknod,sys_mknod,compat_sys_mknod) +SYSCALL(sys_chmod,sys_chmod,compat_sys_chmod) /* 15 */ +SYSCALL(sys_lchown16,sys_ni_syscall,compat_sys_s390_lchown16) /* 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_lseek,sys_lseek,compat_sys_lseek) 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) +SYSCALL(sys_mount,sys_mount,compat_sys_mount) +SYSCALL(sys_oldumount,sys_oldumount,compat_sys_oldumount) +SYSCALL(sys_setuid16,sys_ni_syscall,compat_sys_s390_setuid16) /* old setuid16 syscall*/ +SYSCALL(sys_getuid16,sys_ni_syscall,compat_sys_s390_getuid16) /* old getuid16 syscall*/ +SYSCALL(sys_stime,sys_ni_syscall,compat_sys_stime) /* 25 old stime syscall */ +SYSCALL(sys_ptrace,sys_ptrace,compat_sys_ptrace) +SYSCALL(sys_alarm,sys_alarm,compat_sys_alarm) NI_SYSCALL /* old fstat syscall */ SYSCALL(sys_pause,sys_pause,sys_pause) -SYSCALL(sys_utime,sys_utime,compat_sys_utime_wrapper) /* 30 */ +SYSCALL(sys_utime,sys_utime,compat_sys_utime) /* 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) +SYSCALL(sys_access,sys_access,compat_sys_access) +SYSCALL(sys_nice,sys_nice,compat_sys_nice) 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) +SYSCALL(sys_kill,sys_kill,compat_sys_kill) +SYSCALL(sys_rename,sys_rename,compat_sys_rename) +SYSCALL(sys_mkdir,sys_mkdir,compat_sys_mkdir) +SYSCALL(sys_rmdir,sys_rmdir,compat_sys_rmdir) /* 40 */ +SYSCALL(sys_dup,sys_dup,compat_sys_dup) +SYSCALL(sys_pipe,sys_pipe,compat_sys_pipe) +SYSCALL(sys_times,sys_times,compat_sys_times) 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) +SYSCALL(sys_brk,sys_brk,compat_sys_brk) /* 45 */ +SYSCALL(sys_setgid16,sys_ni_syscall,compat_sys_s390_setgid16) /* old setgid16 syscall*/ +SYSCALL(sys_getgid16,sys_ni_syscall,compat_sys_s390_getgid16) /* old getgid16 syscall*/ +SYSCALL(sys_signal,sys_signal,compat_sys_signal) +SYSCALL(sys_geteuid16,sys_ni_syscall,compat_sys_s390_geteuid16) /* old geteuid16 syscall */ +SYSCALL(sys_getegid16,sys_ni_syscall,compat_sys_s390_getegid16) /* 50 old getegid16 syscall */ +SYSCALL(sys_acct,sys_acct,compat_sys_acct) +SYSCALL(sys_umount,sys_umount,compat_sys_umount) NI_SYSCALL /* old lock syscall */ -SYSCALL(sys_ioctl,sys_ioctl,compat_sys_ioctl_wrapper) -SYSCALL(sys_fcntl,sys_fcntl,compat_sys_fcntl_wrapper) /* 55 */ +SYSCALL(sys_ioctl,sys_ioctl,compat_sys_ioctl) +SYSCALL(sys_fcntl,sys_fcntl,compat_sys_fcntl) /* 55 */ NI_SYSCALL /* intel mpx syscall */ -SYSCALL(sys_setpgid,sys_setpgid,sys32_setpgid_wrapper) +SYSCALL(sys_setpgid,sys_setpgid,compat_sys_setpgid) 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_umask,sys_umask,compat_sys_umask) /* 60 */ +SYSCALL(sys_chroot,sys_chroot,compat_sys_chroot) +SYSCALL(sys_ustat,sys_ustat,compat_sys_ustat) +SYSCALL(sys_dup2,sys_dup2,compat_sys_dup2) 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) +SYSCALL(sys_sigaction,sys_sigaction,compat_sys_sigaction) 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 */ +SYSCALL(sys_setreuid16,sys_ni_syscall,compat_sys_s390_setreuid16) /* old setreuid16 syscall */ +SYSCALL(sys_setregid16,sys_ni_syscall,compat_sys_s390_setregid16) /* old setregid16 syscall */ +SYSCALL(sys_sigsuspend,sys_sigsuspend,compat_sys_sigsuspend) +SYSCALL(sys_sigpending,sys_sigpending,compat_sys_sigpending) +SYSCALL(sys_sethostname,sys_sethostname,compat_sys_sethostname) +SYSCALL(sys_setrlimit,sys_setrlimit,compat_sys_setrlimit) /* 75 */ +SYSCALL(sys_old_getrlimit,sys_getrlimit,compat_sys_old_getrlimit) +SYSCALL(sys_getrusage,sys_getrusage,compat_sys_getrusage) +SYSCALL(sys_gettimeofday,sys_gettimeofday,compat_sys_gettimeofday) +SYSCALL(sys_settimeofday,sys_settimeofday,compat_sys_settimeofday) +SYSCALL(sys_getgroups16,sys_ni_syscall,compat_sys_s390_getgroups16) /* 80 old getgroups16 syscall */ +SYSCALL(sys_setgroups16,sys_ni_syscall,compat_sys_s390_setgroups16) /* old setgroups16 syscall */ NI_SYSCALL /* old select syscall */ -SYSCALL(sys_symlink,sys_symlink,sys32_symlink_wrapper) +SYSCALL(sys_symlink,sys_symlink,compat_sys_symlink) 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) +SYSCALL(sys_readlink,sys_readlink,compat_sys_readlink) /* 85 */ +SYSCALL(sys_uselib,sys_uselib,compat_sys_uselib) +SYSCALL(sys_swapon,sys_swapon,compat_sys_swapon) +SYSCALL(sys_reboot,sys_reboot,compat_sys_reboot) +SYSCALL(sys_ni_syscall,sys_ni_syscall,compat_sys_old_readdir) /* old readdir syscall */ +SYSCALL(sys_old_mmap,sys_old_mmap,compat_sys_s390_old_mmap) /* 90 */ +SYSCALL(sys_munmap,sys_munmap,compat_sys_munmap) +SYSCALL(sys_truncate,sys_truncate,compat_sys_truncate) +SYSCALL(sys_ftruncate,sys_ftruncate,compat_sys_ftruncate) +SYSCALL(sys_fchmod,sys_fchmod,compat_sys_fchmod) +SYSCALL(sys_fchown16,sys_ni_syscall,compat_sys_s390_fchown16) /* 95 old fchown16 syscall*/ +SYSCALL(sys_getpriority,sys_getpriority,compat_sys_getpriority) +SYSCALL(sys_setpriority,sys_setpriority,compat_sys_setpriority) NI_SYSCALL /* old profil syscall */ -SYSCALL(sys_statfs,sys_statfs,compat_sys_statfs_wrapper) -SYSCALL(sys_fstatfs,sys_fstatfs,compat_sys_fstatfs_wrapper) /* 100 */ +SYSCALL(sys_statfs,sys_statfs,compat_sys_statfs) +SYSCALL(sys_fstatfs,sys_fstatfs,compat_sys_fstatfs) /* 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) +SYSCALL(sys_socketcall,sys_socketcall,compat_sys_socketcall) +SYSCALL(sys_syslog,sys_syslog,compat_sys_syslog) +SYSCALL(sys_setitimer,sys_setitimer,compat_sys_setitimer) +SYSCALL(sys_getitimer,sys_getitimer,compat_sys_getitimer) /* 105 */ +SYSCALL(sys_newstat,sys_newstat,compat_sys_newstat) +SYSCALL(sys_newlstat,sys_newlstat,compat_sys_newlstat) +SYSCALL(sys_newfstat,sys_newfstat,compat_sys_newfstat) NI_SYSCALL /* old uname syscall */ -SYSCALL(sys_lookup_dcookie,sys_lookup_dcookie,sys32_lookup_dcookie_wrapper) /* 110 */ +SYSCALL(sys_lookup_dcookie,sys_lookup_dcookie,compat_sys_lookup_dcookie) /* 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) +SYSCALL(sys_wait4,sys_wait4,compat_sys_wait4) +SYSCALL(sys_swapoff,sys_swapoff,compat_sys_swapoff) /* 115 */ +SYSCALL(sys_sysinfo,sys_sysinfo,compat_sys_sysinfo) +SYSCALL(sys_s390_ipc,sys_s390_ipc,compat_sys_s390_ipc) +SYSCALL(sys_fsync,sys_fsync,compat_sys_fsync) +SYSCALL(sys_sigreturn,sys_sigreturn,compat_sys_sigreturn) +SYSCALL(sys_clone,sys_clone,compat_sys_clone) /* 120 */ +SYSCALL(sys_setdomainname,sys_setdomainname,compat_sys_setdomainname) +SYSCALL(sys_newuname,sys_newuname,compat_sys_newuname) 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) +SYSCALL(sys_adjtimex,sys_adjtimex,compat_sys_adjtimex) +SYSCALL(sys_mprotect,sys_mprotect,compat_sys_mprotect) /* 125 */ +SYSCALL(sys_sigprocmask,sys_sigprocmask,compat_sys_sigprocmask) 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) +SYSCALL(sys_init_module,sys_init_module,compat_sys_init_module) +SYSCALL(sys_delete_module,sys_delete_module,compat_sys_delete_module) 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) +SYSCALL(sys_quotactl,sys_quotactl,compat_sys_quotactl) +SYSCALL(sys_getpgid,sys_getpgid,compat_sys_getpgid) +SYSCALL(sys_fchdir,sys_fchdir,compat_sys_fchdir) +SYSCALL(sys_bdflush,sys_bdflush,compat_sys_bdflush) +SYSCALL(sys_sysfs,sys_sysfs,compat_sys_sysfs) /* 135 */ +SYSCALL(sys_personality,sys_s390_personality,compat_sys_s390_personality) 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_setfsuid16,sys_ni_syscall,compat_sys_s390_setfsuid16) /* old setfsuid16 syscall */ +SYSCALL(sys_setfsgid16,sys_ni_syscall,compat_sys_s390_setfsgid16) /* old setfsgid16 syscall */ +SYSCALL(sys_llseek,sys_llseek,compat_sys_llseek) /* 140 */ +SYSCALL(sys_getdents,sys_getdents,compat_sys_getdents) +SYSCALL(sys_select,sys_select,compat_sys_select) +SYSCALL(sys_flock,sys_flock,compat_sys_flock) +SYSCALL(sys_msync,sys_msync,compat_sys_msync) +SYSCALL(sys_readv,sys_readv,compat_sys_readv) /* 145 */ +SYSCALL(sys_writev,sys_writev,compat_sys_writev) +SYSCALL(sys_getsid,sys_getsid,compat_sys_getsid) +SYSCALL(sys_fdatasync,sys_fdatasync,compat_sys_fdatasync) +SYSCALL(sys_sysctl,sys_sysctl,compat_sys_sysctl) +SYSCALL(sys_mlock,sys_mlock,compat_sys_mlock) /* 150 */ +SYSCALL(sys_munlock,sys_munlock,compat_sys_munlock) +SYSCALL(sys_mlockall,sys_mlockall,compat_sys_mlockall) 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_setparam,sys_sched_setparam,compat_sys_sched_setparam) +SYSCALL(sys_sched_getparam,sys_sched_getparam,compat_sys_sched_getparam) /* 155 */ +SYSCALL(sys_sched_setscheduler,sys_sched_setscheduler,compat_sys_sched_setscheduler) +SYSCALL(sys_sched_getscheduler,sys_sched_getscheduler,compat_sys_sched_getscheduler) 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 */ +SYSCALL(sys_sched_get_priority_max,sys_sched_get_priority_max,compat_sys_sched_get_priority_max) +SYSCALL(sys_sched_get_priority_min,sys_sched_get_priority_min,compat_sys_sched_get_priority_min) /* 160 */ +SYSCALL(sys_sched_rr_get_interval,sys_sched_rr_get_interval,compat_sys_sched_rr_get_interval) +SYSCALL(sys_nanosleep,sys_nanosleep,compat_sys_nanosleep) +SYSCALL(sys_mremap,sys_mremap,compat_sys_mremap) +SYSCALL(sys_setresuid16,sys_ni_syscall,compat_sys_s390_setresuid16) /* old setresuid16 syscall */ +SYSCALL(sys_getresuid16,sys_ni_syscall,compat_sys_s390_getresuid16) /* 165 old getresuid16 syscall */ NI_SYSCALL /* for vm86 */ NI_SYSCALL /* old sys_query_module */ -SYSCALL(sys_poll,sys_poll,sys32_poll_wrapper) +SYSCALL(sys_poll,sys_poll,compat_sys_poll) 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) +SYSCALL(sys_setresgid16,sys_ni_syscall,compat_sys_s390_setresgid16) /* 170 old setresgid16 syscall */ +SYSCALL(sys_getresgid16,sys_ni_syscall,compat_sys_s390_getresgid16) /* old getresgid16 syscall */ +SYSCALL(sys_prctl,sys_prctl,compat_sys_prctl) +SYSCALL(sys_rt_sigreturn,sys_rt_sigreturn,compat_sys_rt_sigreturn) +SYSCALL(sys_rt_sigaction,sys_rt_sigaction,compat_sys_rt_sigaction) +SYSCALL(sys_rt_sigprocmask,sys_rt_sigprocmask,compat_sys_rt_sigprocmask) /* 175 */ +SYSCALL(sys_rt_sigpending,sys_rt_sigpending,compat_sys_rt_sigpending) +SYSCALL(sys_rt_sigtimedwait,sys_rt_sigtimedwait,compat_sys_rt_sigtimedwait) +SYSCALL(sys_rt_sigqueueinfo,sys_rt_sigqueueinfo,compat_sys_rt_sigqueueinfo) +SYSCALL(sys_rt_sigsuspend,sys_rt_sigsuspend,compat_sys_rt_sigsuspend) +SYSCALL(sys_pread64,sys_pread64,compat_sys_s390_pread64) /* 180 */ +SYSCALL(sys_pwrite64,sys_pwrite64,compat_sys_s390_pwrite64) +SYSCALL(sys_chown16,sys_ni_syscall,compat_sys_s390_chown16) /* old chown16 syscall */ +SYSCALL(sys_getcwd,sys_getcwd,compat_sys_getcwd) +SYSCALL(sys_capget,sys_capget,compat_sys_capget) +SYSCALL(sys_capset,sys_capset,compat_sys_capset) /* 185 */ +SYSCALL(sys_sigaltstack,sys_sigaltstack,compat_sys_sigaltstack) +SYSCALL(sys_sendfile,sys_sendfile64,compat_sys_sendfile) 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_getrlimit,sys_getrlimit,compat_sys_getrlimit) +SYSCALL(sys_mmap2,sys_mmap2,compat_sys_s390_mmap2) +SYSCALL(sys_truncate64,sys_ni_syscall,compat_sys_s390_truncate64) +SYSCALL(sys_ftruncate64,sys_ni_syscall,compat_sys_s390_ftruncate64) +SYSCALL(sys_stat64,sys_ni_syscall,compat_sys_s390_stat64) /* 195 */ +SYSCALL(sys_lstat64,sys_ni_syscall,compat_sys_s390_lstat64) +SYSCALL(sys_fstat64,sys_ni_syscall,compat_sys_s390_fstat64) +SYSCALL(sys_lchown,sys_lchown,compat_sys_lchown) 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_setreuid,sys_setreuid,compat_sys_setreuid) +SYSCALL(sys_setregid,sys_setregid,compat_sys_setregid) +SYSCALL(sys_getgroups,sys_getgroups,compat_sys_getgroups) /* 205 */ +SYSCALL(sys_setgroups,sys_setgroups,compat_sys_setgroups) +SYSCALL(sys_fchown,sys_fchown,compat_sys_fchown) +SYSCALL(sys_setresuid,sys_setresuid,compat_sys_setresuid) +SYSCALL(sys_getresuid,sys_getresuid,compat_sys_getresuid) +SYSCALL(sys_setresgid,sys_setresgid,compat_sys_setresgid) /* 210 */ +SYSCALL(sys_getresgid,sys_getresgid,compat_sys_getresgid) +SYSCALL(sys_chown,sys_chown,compat_sys_chown) +SYSCALL(sys_setuid,sys_setuid,compat_sys_setuid) +SYSCALL(sys_setgid,sys_setgid,compat_sys_setgid) +SYSCALL(sys_setfsuid,sys_setfsuid,compat_sys_setfsuid) /* 215 */ +SYSCALL(sys_setfsgid,sys_setfsgid,compat_sys_setfsgid) +SYSCALL(sys_pivot_root,sys_pivot_root,compat_sys_pivot_root) +SYSCALL(sys_mincore,sys_mincore,compat_sys_mincore) +SYSCALL(sys_madvise,sys_madvise,compat_sys_madvise) +SYSCALL(sys_getdents64,sys_getdents64,compat_sys_getdents64) /* 220 */ +SYSCALL(sys_fcntl64,sys_ni_syscall,compat_sys_fcntl64) +SYSCALL(sys_readahead,sys_readahead,compat_sys_s390_readahead) +SYSCALL(sys_sendfile64,sys_ni_syscall,compat_sys_sendfile64) +SYSCALL(sys_setxattr,sys_setxattr,compat_sys_setxattr) +SYSCALL(sys_lsetxattr,sys_lsetxattr,compat_sys_lsetxattr) /* 225 */ +SYSCALL(sys_fsetxattr,sys_fsetxattr,compat_sys_fsetxattr) +SYSCALL(sys_getxattr,sys_getxattr,compat_sys_getxattr) +SYSCALL(sys_lgetxattr,sys_lgetxattr,compat_sys_lgetxattr) +SYSCALL(sys_fgetxattr,sys_fgetxattr,compat_sys_fgetxattr) +SYSCALL(sys_listxattr,sys_listxattr,compat_sys_listxattr) /* 230 */ +SYSCALL(sys_llistxattr,sys_llistxattr,compat_sys_llistxattr) +SYSCALL(sys_flistxattr,sys_flistxattr,compat_sys_flistxattr) +SYSCALL(sys_removexattr,sys_removexattr,compat_sys_removexattr) +SYSCALL(sys_lremovexattr,sys_lremovexattr,compat_sys_lremovexattr) +SYSCALL(sys_fremovexattr,sys_fremovexattr,compat_sys_fremovexattr) /* 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) +SYSCALL(sys_tkill,sys_tkill,compat_sys_tkill) +SYSCALL(sys_futex,sys_futex,compat_sys_futex) +SYSCALL(sys_sched_setaffinity,sys_sched_setaffinity,compat_sys_sched_setaffinity) +SYSCALL(sys_sched_getaffinity,sys_sched_getaffinity,compat_sys_sched_getaffinity) /* 240 */ +SYSCALL(sys_tgkill,sys_tgkill,compat_sys_tgkill) 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) +SYSCALL(sys_io_setup,sys_io_setup,compat_sys_io_setup) +SYSCALL(sys_io_destroy,sys_io_destroy,compat_sys_io_destroy) +SYSCALL(sys_io_getevents,sys_io_getevents,compat_sys_io_getevents) /* 245 */ +SYSCALL(sys_io_submit,sys_io_submit,compat_sys_io_submit) +SYSCALL(sys_io_cancel,sys_io_cancel,compat_sys_io_cancel) +SYSCALL(sys_exit_group,sys_exit_group,compat_sys_exit_group) +SYSCALL(sys_epoll_create,sys_epoll_create,compat_sys_epoll_create) +SYSCALL(sys_epoll_ctl,sys_epoll_ctl,compat_sys_epoll_ctl) /* 250 */ +SYSCALL(sys_epoll_wait,sys_epoll_wait,compat_sys_epoll_wait) +SYSCALL(sys_set_tid_address,sys_set_tid_address,compat_sys_set_tid_address) +SYSCALL(sys_s390_fadvise64,sys_fadvise64_64,compat_sys_s390_fadvise64) +SYSCALL(sys_timer_create,sys_timer_create,compat_sys_timer_create) +SYSCALL(sys_timer_settime,sys_timer_settime,compat_sys_timer_settime) /* 255 */ +SYSCALL(sys_timer_gettime,sys_timer_gettime,compat_sys_timer_gettime) +SYSCALL(sys_timer_getoverrun,sys_timer_getoverrun,compat_sys_timer_getoverrun) +SYSCALL(sys_timer_delete,sys_timer_delete,compat_sys_timer_delete) +SYSCALL(sys_clock_settime,sys_clock_settime,compat_sys_clock_settime) +SYSCALL(sys_clock_gettime,sys_clock_gettime,compat_sys_clock_gettime) /* 260 */ +SYSCALL(sys_clock_getres,sys_clock_getres,compat_sys_clock_getres) +SYSCALL(sys_clock_nanosleep,sys_clock_nanosleep,compat_sys_clock_nanosleep) 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) +SYSCALL(sys_s390_fadvise64_64,sys_ni_syscall,compat_sys_s390_fadvise64_64) +SYSCALL(sys_statfs64,sys_statfs64,compat_sys_statfs64) +SYSCALL(sys_fstatfs64,sys_fstatfs64,compat_sys_fstatfs64) +SYSCALL(sys_remap_file_pages,sys_remap_file_pages,compat_sys_remap_file_pages) 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_mq_open,sys_mq_open,compat_sys_mq_open) +SYSCALL(sys_mq_unlink,sys_mq_unlink,compat_sys_mq_unlink) +SYSCALL(sys_mq_timedsend,sys_mq_timedsend,compat_sys_mq_timedsend) +SYSCALL(sys_mq_timedreceive,sys_mq_timedreceive,compat_sys_mq_timedreceive) +SYSCALL(sys_mq_notify,sys_mq_notify,compat_sys_mq_notify) /* 275 */ +SYSCALL(sys_mq_getsetattr,sys_mq_getsetattr,compat_sys_mq_getsetattr) +SYSCALL(sys_kexec_load,sys_kexec_load,compat_sys_kexec_load) +SYSCALL(sys_add_key,sys_add_key,compat_sys_add_key) +SYSCALL(sys_request_key,sys_request_key,compat_sys_request_key) +SYSCALL(sys_keyctl,sys_keyctl,compat_sys_keyctl) /* 280 */ +SYSCALL(sys_waitid,sys_waitid,compat_sys_waitid) +SYSCALL(sys_ioprio_set,sys_ioprio_set,compat_sys_ioprio_set) +SYSCALL(sys_ioprio_get,sys_ioprio_get,compat_sys_ioprio_get) 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) +SYSCALL(sys_inotify_add_watch,sys_inotify_add_watch,compat_sys_inotify_add_watch) /* 285 */ +SYSCALL(sys_inotify_rm_watch,sys_inotify_rm_watch,compat_sys_inotify_rm_watch) 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) +SYSCALL(sys_openat,sys_openat,compat_sys_openat) +SYSCALL(sys_mkdirat,sys_mkdirat,compat_sys_mkdirat) +SYSCALL(sys_mknodat,sys_mknodat,compat_sys_mknodat) /* 290 */ +SYSCALL(sys_fchownat,sys_fchownat,compat_sys_fchownat) +SYSCALL(sys_futimesat,sys_futimesat,compat_sys_futimesat) +SYSCALL(sys_fstatat64,sys_newfstatat,compat_sys_s390_fstatat64) +SYSCALL(sys_unlinkat,sys_unlinkat,compat_sys_unlinkat) +SYSCALL(sys_renameat,sys_renameat,compat_sys_renameat) /* 295 */ +SYSCALL(sys_linkat,sys_linkat,compat_sys_linkat) +SYSCALL(sys_symlinkat,sys_symlinkat,compat_sys_symlinkat) +SYSCALL(sys_readlinkat,sys_readlinkat,compat_sys_readlinkat) +SYSCALL(sys_fchmodat,sys_fchmodat,compat_sys_fchmodat) +SYSCALL(sys_faccessat,sys_faccessat,compat_sys_faccessat) /* 300 */ +SYSCALL(sys_pselect6,sys_pselect6,compat_sys_pselect6) +SYSCALL(sys_ppoll,sys_ppoll,compat_sys_ppoll) +SYSCALL(sys_unshare,sys_unshare,compat_sys_unshare) +SYSCALL(sys_set_robust_list,sys_set_robust_list,compat_sys_set_robust_list) +SYSCALL(sys_get_robust_list,sys_get_robust_list,compat_sys_get_robust_list) +SYSCALL(sys_splice,sys_splice,compat_sys_splice) +SYSCALL(sys_sync_file_range,sys_sync_file_range,compat_sys_s390_sync_file_range) +SYSCALL(sys_tee,sys_tee,compat_sys_tee) +SYSCALL(sys_vmsplice,sys_vmsplice,compat_sys_vmsplice) 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) +SYSCALL(sys_getcpu,sys_getcpu,compat_sys_getcpu) +SYSCALL(sys_epoll_pwait,sys_epoll_pwait,compat_sys_epoll_pwait) +SYSCALL(sys_utimes,sys_utimes,compat_sys_utimes) +SYSCALL(sys_s390_fallocate,sys_fallocate,compat_sys_s390_fallocate) +SYSCALL(sys_utimensat,sys_utimensat,compat_sys_utimensat) /* 315 */ +SYSCALL(sys_signalfd,sys_signalfd,compat_sys_signalfd) 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) -SYSCALL(sys_ni_syscall,sys_s390_runtime_instr,sys_s390_runtime_instr_wrapper) -SYSCALL(sys_kcmp,sys_kcmp,sys_kcmp_wrapper) -SYSCALL(sys_finit_module,sys_finit_module,sys_finit_module_wrapper) +SYSCALL(sys_eventfd,sys_eventfd,compat_sys_eventfd) +SYSCALL(sys_timerfd_create,sys_timerfd_create,compat_sys_timerfd_create) +SYSCALL(sys_timerfd_settime,sys_timerfd_settime,compat_sys_timerfd_settime) /* 320 */ +SYSCALL(sys_timerfd_gettime,sys_timerfd_gettime,compat_sys_timerfd_gettime) +SYSCALL(sys_signalfd4,sys_signalfd4,compat_sys_signalfd4) +SYSCALL(sys_eventfd2,sys_eventfd2,compat_sys_eventfd2) +SYSCALL(sys_inotify_init1,sys_inotify_init1,compat_sys_inotify_init1) +SYSCALL(sys_pipe2,sys_pipe2,compat_sys_pipe2) /* 325 */ +SYSCALL(sys_dup3,sys_dup3,compat_sys_dup3) +SYSCALL(sys_epoll_create1,sys_epoll_create1,compat_sys_epoll_create1) +SYSCALL(sys_preadv,sys_preadv,compat_sys_preadv) +SYSCALL(sys_pwritev,sys_pwritev,compat_sys_pwritev) +SYSCALL(sys_rt_tgsigqueueinfo,sys_rt_tgsigqueueinfo,compat_sys_rt_tgsigqueueinfo) /* 330 */ +SYSCALL(sys_perf_event_open,sys_perf_event_open,compat_sys_perf_event_open) +SYSCALL(sys_fanotify_init,sys_fanotify_init,compat_sys_fanotify_init) +SYSCALL(sys_fanotify_mark,sys_fanotify_mark,compat_sys_fanotify_mark) +SYSCALL(sys_prlimit64,sys_prlimit64,compat_sys_prlimit64) +SYSCALL(sys_name_to_handle_at,sys_name_to_handle_at,compat_sys_name_to_handle_at) /* 335 */ +SYSCALL(sys_open_by_handle_at,sys_open_by_handle_at,compat_sys_open_by_handle_at) +SYSCALL(sys_clock_adjtime,sys_clock_adjtime,compat_sys_clock_adjtime) +SYSCALL(sys_syncfs,sys_syncfs,compat_sys_syncfs) +SYSCALL(sys_setns,sys_setns,compat_sys_setns) +SYSCALL(sys_process_vm_readv,sys_process_vm_readv,compat_sys_process_vm_readv) /* 340 */ +SYSCALL(sys_process_vm_writev,sys_process_vm_writev,compat_sys_process_vm_writev) +SYSCALL(sys_ni_syscall,sys_s390_runtime_instr,compat_sys_s390_runtime_instr) +SYSCALL(sys_kcmp,sys_kcmp,compat_sys_kcmp) +SYSCALL(sys_finit_module,sys_finit_module,compat_sys_finit_module) +SYSCALL(sys_sched_setattr,sys_sched_setattr,compat_sys_sched_setattr) /* 345 */ +SYSCALL(sys_sched_getattr,sys_sched_getattr,compat_sys_sched_getattr) +SYSCALL(sys_renameat2,sys_renameat2,compat_sys_renameat2) diff --git a/arch/s390/kernel/sysinfo.c b/arch/s390/kernel/sysinfo.c index 62f89d98e88..811f542b8ed 100644 --- a/arch/s390/kernel/sysinfo.c +++ b/arch/s390/kernel/sysinfo.c @@ -418,7 +418,7 @@ void s390_adjust_jiffies(void) /* * calibrate the delay loop */ -void __cpuinit calibrate_delay(void) +void calibrate_delay(void) { s390_adjust_jiffies(); /* Print the good old Bogomips line .. */ diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c index a5f4f5a1d24..0931b110c82 100644 --- a/arch/s390/kernel/time.c +++ b/arch/s390/kernel/time.c @@ -63,7 +63,7 @@ static DEFINE_PER_CPU(struct clock_event_device, comparators); */ unsigned long long notrace __kprobes sched_clock(void) { - return tod_to_ns(get_clock_monotonic()); + return tod_to_ns(get_tod_clock_monotonic()); } /* @@ -92,7 +92,6 @@ 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); } @@ -109,17 +108,10 @@ static void fixup_clock_comparator(unsigned long long delta) set_clock_comparator(S390_lowcore.clock_comparator); } -static int s390_next_ktime(ktime_t expires, +static int s390_next_event(unsigned long delta, 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); + S390_lowcore.clock_comparator = get_tod_clock() + delta; set_clock_comparator(S390_lowcore.clock_comparator); return 0; } @@ -144,15 +136,14 @@ void init_cpu_timer(void) cpu = smp_processor_id(); cd = &per_cpu(comparators, cpu); cd->name = "comparator"; - cd->features = CLOCK_EVT_FEAT_ONESHOT | - CLOCK_EVT_FEAT_KTIME; + cd->features = CLOCK_EVT_FEAT_ONESHOT; 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_next_event = s390_next_event; cd->set_mode = s390_set_mode; clockevents_register_device(cd); @@ -191,7 +182,7 @@ static void stp_reset(void); void read_persistent_clock(struct timespec *ts) { - tod_to_timeval(get_clock() - TOD_UNIX_EPOCH, ts); + tod_to_timeval(get_tod_clock() - TOD_UNIX_EPOCH, ts); } void read_boot_clock(struct timespec *ts) @@ -201,7 +192,7 @@ void read_boot_clock(struct timespec *ts) static cycle_t read_tod_clock(struct clocksource *cs) { - return get_clock(); + return get_tod_clock(); } static struct clocksource clocksource_tod = { @@ -219,21 +210,30 @@ struct clocksource * __init clocksource_default_clock(void) return &clocksource_tod; } -void update_vsyscall_old(struct timespec *wall_time, struct timespec *wtm, - struct clocksource *clock, u32 mult) +void update_vsyscall(struct timekeeper *tk) { - if (clock != &clocksource_tod) + u64 nsecps; + + if (tk->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; + vdso_data->xtime_tod_stamp = tk->clock->cycle_last; + vdso_data->xtime_clock_sec = tk->xtime_sec; + vdso_data->xtime_clock_nsec = tk->xtime_nsec; + vdso_data->wtom_clock_sec = + tk->xtime_sec + tk->wall_to_monotonic.tv_sec; + vdso_data->wtom_clock_nsec = tk->xtime_nsec + + + ((u64) tk->wall_to_monotonic.tv_nsec << tk->shift); + nsecps = (u64) NSEC_PER_SEC << tk->shift; + while (vdso_data->wtom_clock_nsec >= nsecps) { + vdso_data->wtom_clock_nsec -= nsecps; + vdso_data->wtom_clock_sec++; + } + vdso_data->tk_mult = tk->mult; + vdso_data->tk_shift = tk->shift; smp_wmb(); ++vdso_data->tb_update_count; } @@ -262,11 +262,11 @@ void __init time_init(void) stp_reset(); /* request the clock comparator external interrupt */ - if (register_external_interrupt(0x1004, clock_comparator_interrupt)) - panic("Couldn't request external interrupt 0x1004"); + if (register_external_irq(EXT_IRQ_CLK_COMP, clock_comparator_interrupt)) + panic("Couldn't request external interrupt 0x1004"); /* request the timing alert external interrupt */ - if (register_external_interrupt(0x1406, timing_alert_interrupt)) + if (register_external_irq(EXT_IRQ_TIMING_ALERT, timing_alert_interrupt)) panic("Couldn't request external interrupt 0x1406"); if (clocksource_register(&clocksource_tod) != 0) @@ -339,7 +339,7 @@ int get_sync_clock(unsigned long long *clock) sw_ptr = &get_cpu_var(clock_sync_word); sw0 = atomic_read(sw_ptr); - *clock = get_clock(); + *clock = get_tod_clock(); sw1 = atomic_read(sw_ptr); put_cpu_var(clock_sync_word); if (sw0 == sw1 && (sw0 & 0x80000000U)) @@ -483,7 +483,7 @@ static void etr_reset(void) .p0 = 0, .p1 = 0, ._pad1 = 0, .ea = 0, .es = 0, .sl = 0 }; if (etr_setr(&etr_eacr) == 0) { - etr_tolec = get_clock(); + etr_tolec = get_tod_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); @@ -765,8 +765,8 @@ static int etr_sync_clock(void *data) __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) { + old_clock = get_tod_clock(); + if (set_tod_clock(clock) == 0) { __udelay(1); /* Wait for the clock to start. */ __ctl_clear_bit(0, 29); __ctl_clear_bit(14, 21); @@ -842,7 +842,7 @@ static struct etr_eacr etr_handle_events(struct etr_eacr eacr) * assume that this can have caused an stepping * port switch. */ - etr_tolec = get_clock(); + etr_tolec = get_tod_clock(); eacr.p0 = etr_port0_online; if (!eacr.p0) eacr.e0 = 0; @@ -855,7 +855,7 @@ static struct etr_eacr etr_handle_events(struct etr_eacr eacr) * assume that this can have caused an stepping * port switch. */ - etr_tolec = get_clock(); + etr_tolec = get_tod_clock(); eacr.p1 = etr_port1_online; if (!eacr.p1) eacr.e1 = 0; @@ -971,7 +971,7 @@ static void etr_update_eacr(struct etr_eacr eacr) etr_eacr = eacr; etr_setr(&etr_eacr); if (dp_changed) - etr_tolec = get_clock(); + etr_tolec = get_tod_clock(); } /* @@ -1009,7 +1009,7 @@ static void etr_work_fn(struct work_struct *work) /* 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(); + now = get_tod_clock(); /* * Update the port information if the last stepping port change @@ -1534,10 +1534,10 @@ static int stp_sync_clock(void *data) 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(); + old_clock = get_tod_clock(); rc = chsc_sstpc(stp_page, STP_OP_SYNC, 0); if (rc == 0) { - delta = adjust_time(old_clock, get_clock(), 0); + delta = adjust_time(old_clock, get_tod_clock(), 0); fixup_clock_comparator(delta); rc = chsc_sstpi(stp_page, &stp_info, sizeof(struct stp_sstpi)); diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c index 4b2e3e31700..355a16c5570 100644 --- a/arch/s390/kernel/topology.c +++ b/arch/s390/kernel/topology.c @@ -333,7 +333,9 @@ static void __init alloc_masks(struct sysinfo_15_1_x *info, 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->next = alloc_bootmem_align( + roundup_pow_of_two(sizeof(struct mask_info)), + roundup_pow_of_two(sizeof(struct mask_info))); mask = mask->next; } } @@ -443,6 +445,23 @@ int topology_cpu_init(struct cpu *cpu) return sysfs_create_group(&cpu->dev.kobj, &topology_cpu_attr_group); } +const struct cpumask *cpu_coregroup_mask(int cpu) +{ + return &cpu_topology[cpu].core_mask; +} + +static const struct cpumask *cpu_book_mask(int cpu) +{ + return &cpu_topology[cpu].book_mask; +} + +static struct sched_domain_topology_level s390_topology[] = { + { cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) }, + { cpu_book_mask, SD_INIT_NAME(BOOK) }, + { cpu_cpu_mask, SD_INIT_NAME(DIE) }, + { NULL, }, +}; + static int __init topology_init(void) { if (!MACHINE_HAS_TOPOLOGY) { @@ -451,7 +470,9 @@ static int __init topology_init(void) } set_topology_timer(); out: - update_cpu_masks(); + + set_sched_topology(s390_topology); + 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 index 70ecfc5fe8f..c5762324d9e 100644 --- a/arch/s390/kernel/traps.c +++ b/arch/s390/kernel/traps.c @@ -12,49 +12,16 @@ * '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/kprobes.h> +#include <linux/kdebug.h> +#include <linux/module.h> #include <linux/ptrace.h> -#include <linux/timer.h> +#include <linux/sched.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" 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 */ - static inline void __user *get_trap_ip(struct pt_regs *regs) { #ifdef CONFIG_64BIT @@ -72,215 +39,6 @@ static inline void __user *get_trap_ip(struct pt_regs *regs) #endif } -/* - * 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 = user_mode(regs) ? "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) -{ - 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 (!user_mode(regs)) - 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); - print_modules(); - 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) diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c index d7776281cb6..61364909678 100644 --- a/arch/s390/kernel/vdso.c +++ b/arch/s390/kernel/vdso.c @@ -63,7 +63,7 @@ static int __init vdso_setup(char *s) else if (strncmp(s, "off", 4) == 0) vdso_enabled = 0; else { - rc = strict_strtoul(s, 0, &val); + rc = kstrtoul(s, 0, &val); vdso_enabled = rc ? 0 : !!val; } return !rc; @@ -84,8 +84,7 @@ struct vdso_data *vdso_data = &vdso_data_store.data; */ static void vdso_init_data(struct vdso_data *vd) { - vd->ectg_available = - s390_user_mode != HOME_SPACE_MODE && test_facility(31); + vd->ectg_available = test_facility(31); } #ifdef CONFIG_64BIT @@ -102,7 +101,7 @@ int vdso_alloc_per_cpu(struct _lowcore *lowcore) lowcore->vdso_per_cpu_data = __LC_PASTE; - if (s390_user_mode == HOME_SPACE_MODE || !vdso_enabled) + if (!vdso_enabled) return 0; segment_table = __get_free_pages(GFP_KERNEL, SEGMENT_ORDER); @@ -113,11 +112,11 @@ int vdso_alloc_per_cpu(struct _lowcore *lowcore) clear_table((unsigned long *) segment_table, _SEGMENT_ENTRY_EMPTY, PAGE_SIZE << SEGMENT_ORDER); - clear_table((unsigned long *) page_table, _PAGE_TYPE_EMPTY, + clear_table((unsigned long *) page_table, _PAGE_INVALID, 256*sizeof(unsigned long)); *(unsigned long *) segment_table = _SEGMENT_ENTRY + page_table; - *(unsigned long *) page_table = _PAGE_RO + page_frame; + *(unsigned long *) page_table = _PAGE_PROTECT + page_frame; psal = (u32 *) (page_table + 256*sizeof(unsigned long)); aste = psal + 32; @@ -126,7 +125,7 @@ int vdso_alloc_per_cpu(struct _lowcore *lowcore) psal[i] = 0x80000000; lowcore->paste[4] = (u32)(addr_t) psal; - psal[0] = 0x20000000; + psal[0] = 0x02000000; psal[2] = (u32)(addr_t) aste; *(unsigned long *) (aste + 2) = segment_table + _ASCE_TABLE_LENGTH + _ASCE_USER_BITS + _ASCE_TYPE_SEGMENT; @@ -147,7 +146,7 @@ void vdso_free_per_cpu(struct _lowcore *lowcore) unsigned long segment_table, page_table, page_frame; u32 *psal, *aste; - if (s390_user_mode == HOME_SPACE_MODE || !vdso_enabled) + if (!vdso_enabled) return; psal = (u32 *)(addr_t) lowcore->paste[4]; @@ -165,7 +164,7 @@ static void vdso_init_cr5(void) { unsigned long cr5; - if (s390_user_mode == HOME_SPACE_MODE || !vdso_enabled) + if (!vdso_enabled) return; cr5 = offsetof(struct _lowcore, paste); __ctl_load(cr5, 5, 5); diff --git a/arch/s390/kernel/vdso32/clock_gettime.S b/arch/s390/kernel/vdso32/clock_gettime.S index b2224e0b974..65fc3979c2f 100644 --- a/arch/s390/kernel/vdso32/clock_gettime.S +++ b/arch/s390/kernel/vdso32/clock_gettime.S @@ -38,25 +38,21 @@ __kernel_clock_gettime: sl %r1,__VDSO_XTIME_STAMP+4(%r5) brc 3,2f ahi %r0,-1 -2: ms %r0,__VDSO_NTP_MULT(%r5) /* cyc2ns(clock,cycle_delta) */ +2: ms %r0,__VDSO_TK_MULT(%r5) /* * tk->mult */ lr %r2,%r0 - l %r0,__VDSO_NTP_MULT(%r5) + l %r0,__VDSO_TK_MULT(%r5) ltr %r1,%r1 mr %r0,%r0 jnm 3f - a %r0,__VDSO_NTP_MULT(%r5) + a %r0,__VDSO_TK_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 %r0,__VDSO_WTOM_NSEC(%r5) al %r1,__VDSO_WTOM_NSEC+4(%r5) brc 12,5f ahi %r0,1 -5: al %r2,__VDSO_WTOM_SEC+4(%r5) +5: l %r2,__VDSO_TK_SHIFT(%r5) /* Timekeeper shift */ + srdl %r0,0(%r2) /* >> tk->shift */ + l %r2,__VDSO_WTOM_SEC+4(%r5) cl %r4,__VDSO_UPD_COUNT+4(%r5) /* check update counter */ jne 1b basr %r5,0 @@ -86,20 +82,21 @@ __kernel_clock_gettime: sl %r1,__VDSO_XTIME_STAMP+4(%r5) brc 3,12f ahi %r0,-1 -12: ms %r0,__VDSO_NTP_MULT(%r5) /* cyc2ns(clock,cycle_delta) */ +12: ms %r0,__VDSO_TK_MULT(%r5) /* * tk->mult */ lr %r2,%r0 - l %r0,__VDSO_NTP_MULT(%r5) + l %r0,__VDSO_TK_MULT(%r5) ltr %r1,%r1 mr %r0,%r0 jnm 13f - a %r0,__VDSO_NTP_MULT(%r5) + a %r0,__VDSO_TK_MULT(%r5) 13: alr %r0,%r2 - srdl %r0,12 - al %r0,__VDSO_XTIME_NSEC(%r5) /* + xtime */ + al %r0,__VDSO_XTIME_NSEC(%r5) /* + tk->xtime_nsec */ al %r1,__VDSO_XTIME_NSEC+4(%r5) brc 12,14f ahi %r0,1 -14: l %r2,__VDSO_XTIME_SEC+4(%r5) +14: l %r2,__VDSO_TK_SHIFT(%r5) /* Timekeeper shift */ + srdl %r0,0(%r2) /* >> tk->shift */ + l %r2,__VDSO_XTIME_SEC+4(%r5) cl %r4,__VDSO_UPD_COUNT+4(%r5) /* check update counter */ jne 11b basr %r5,0 diff --git a/arch/s390/kernel/vdso32/gettimeofday.S b/arch/s390/kernel/vdso32/gettimeofday.S index 2d3633175e3..fd621a950f7 100644 --- a/arch/s390/kernel/vdso32/gettimeofday.S +++ b/arch/s390/kernel/vdso32/gettimeofday.S @@ -35,15 +35,14 @@ __kernel_gettimeofday: sl %r1,__VDSO_XTIME_STAMP+4(%r5) brc 3,3f ahi %r0,-1 -3: ms %r0,__VDSO_NTP_MULT(%r5) /* cyc2ns(clock,cycle_delta) */ +3: ms %r0,__VDSO_TK_MULT(%r5) /* * tk->mult */ st %r0,24(%r15) - l %r0,__VDSO_NTP_MULT(%r5) + l %r0,__VDSO_TK_MULT(%r5) ltr %r1,%r1 mr %r0,%r0 jnm 4f - a %r0,__VDSO_NTP_MULT(%r5) + a %r0,__VDSO_TK_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 @@ -51,6 +50,8 @@ __kernel_gettimeofday: 5: mvc 24(4,%r15),__VDSO_XTIME_SEC+4(%r5) cl %r4,__VDSO_UPD_COUNT+4(%r5) /* check update counter */ jne 1b + l %r4,__VDSO_TK_SHIFT(%r5) /* Timekeeper shift */ + srdl %r0,0(%r4) /* >> tk->shift */ l %r4,24(%r15) /* get tv_sec from stack */ basr %r5,0 6: ltr %r0,%r0 diff --git a/arch/s390/kernel/vdso64/clock_getres.S b/arch/s390/kernel/vdso64/clock_getres.S index 176e1f75f9a..34deba7c7ed 100644 --- a/arch/s390/kernel/vdso64/clock_getres.S +++ b/arch/s390/kernel/vdso64/clock_getres.S @@ -23,7 +23,9 @@ __kernel_clock_getres: je 0f cghi %r2,__CLOCK_MONOTONIC je 0f - cghi %r2,-2 /* CLOCK_THREAD_CPUTIME_ID for this thread */ + cghi %r2,__CLOCK_THREAD_CPUTIME_ID + je 0f + cghi %r2,-2 /* Per-thread CPUCLOCK with PID=0, VIRT=1 */ jne 2f larl %r5,_vdso_data icm %r0,15,__LC_ECTG_OK(%r5) diff --git a/arch/s390/kernel/vdso64/clock_gettime.S b/arch/s390/kernel/vdso64/clock_gettime.S index d46c95ed5f1..91940ed33a4 100644 --- a/arch/s390/kernel/vdso64/clock_gettime.S +++ b/arch/s390/kernel/vdso64/clock_gettime.S @@ -22,7 +22,9 @@ __kernel_clock_gettime: larl %r5,_vdso_data cghi %r2,__CLOCK_REALTIME je 4f - cghi %r2,-2 /* CLOCK_THREAD_CPUTIME_ID for this thread */ + cghi %r2,__CLOCK_THREAD_CPUTIME_ID + je 9f + cghi %r2,-2 /* Per-thread CPUCLOCK with PID=0, VIRT=1 */ je 9f cghi %r2,__CLOCK_MONOTONIC jne 12f @@ -34,14 +36,13 @@ __kernel_clock_gettime: tmll %r4,0x0001 /* pending update ? loop */ jnz 0b stck 48(%r15) /* Store TOD clock */ + lgf %r2,__VDSO_TK_SHIFT(%r5) /* Timekeeper shift */ + lg %r0,__VDSO_WTOM_SEC(%r5) 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) + msgf %r1,__VDSO_TK_MULT(%r5) /* * tk->mult */ + alg %r1,__VDSO_WTOM_NSEC(%r5) + srlg %r1,%r1,0(%r2) /* >> tk->shift */ clg %r4,__VDSO_UPD_COUNT(%r5) /* check update counter */ jne 0b larl %r5,13f @@ -62,12 +63,13 @@ __kernel_clock_gettime: tmll %r4,0x0001 /* pending update ? loop */ jnz 5b stck 48(%r15) /* Store TOD clock */ + lgf %r2,__VDSO_TK_SHIFT(%r5) /* Timekeeper shift */ 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) + msgf %r1,__VDSO_TK_MULT(%r5) /* * tk->mult */ + alg %r1,__VDSO_XTIME_NSEC(%r5) /* + tk->xtime_nsec */ + srlg %r1,%r1,0(%r2) /* >> tk->shift */ + lg %r0,__VDSO_XTIME_SEC(%r5) /* tk->xtime_sec */ clg %r4,__VDSO_UPD_COUNT(%r5) /* check update counter */ jne 5b larl %r5,13f diff --git a/arch/s390/kernel/vdso64/gettimeofday.S b/arch/s390/kernel/vdso64/gettimeofday.S index 36ee674722e..d0860d1d0cc 100644 --- a/arch/s390/kernel/vdso64/gettimeofday.S +++ b/arch/s390/kernel/vdso64/gettimeofday.S @@ -31,12 +31,13 @@ __kernel_gettimeofday: 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 */ + msgf %r1,__VDSO_TK_MULT(%r5) /* * tk->mult */ + alg %r1,__VDSO_XTIME_NSEC(%r5) /* + tk->xtime_nsec */ + lg %r0,__VDSO_XTIME_SEC(%r5) /* tk->xtime_sec */ clg %r4,__VDSO_UPD_COUNT(%r5) /* check update counter */ jne 0b + lgf %r5,__VDSO_TK_SHIFT(%r5) /* Timekeeper shift */ + srlg %r1,%r1,0(%r5) /* >> tk->shift */ larl %r5,5f 2: clg %r1,0(%r5) jl 3f diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S index 79cb51adc74..35b13ed0af5 100644 --- a/arch/s390/kernel/vmlinux.lds.S +++ b/arch/s390/kernel/vmlinux.lds.S @@ -75,6 +75,10 @@ SECTIONS EXIT_TEXT } + .exit.data : { + EXIT_DATA + } + /* early.c uses stsi, which requires page aligned data. */ . = ALIGN(PAGE_SIZE); INIT_DATA_SECTION(0x100) diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c index e84b8b68444..8c34363d6f1 100644 --- a/arch/s390/kernel/vtime.c +++ b/arch/s390/kernel/vtime.c @@ -19,6 +19,7 @@ #include <asm/irq_regs.h> #include <asm/cputime.h> #include <asm/vtimer.h> +#include <asm/vtime.h> #include <asm/irq.h> #include "entry.h" @@ -127,7 +128,7 @@ void vtime_account_user(struct task_struct *tsk) * Update process times based on virtual cpu times stored by entry.S * to the lowcore fields user_timer, system_timer & steal_clock. */ -void vtime_account(struct task_struct *tsk) +void vtime_account_irq_enter(struct task_struct *tsk) { struct thread_info *ti = task_thread_info(tsk); u64 timer, system; @@ -145,10 +146,10 @@ void vtime_account(struct task_struct *tsk) virt_timer_forward(system); } -EXPORT_SYMBOL_GPL(vtime_account); +EXPORT_SYMBOL_GPL(vtime_account_irq_enter); void vtime_account_system(struct task_struct *tsk) -__attribute__((alias("vtime_account"))); +__attribute__((alias("vtime_account_irq_enter"))); EXPORT_SYMBOL_GPL(vtime_account_system); void __kprobes vtime_stop_cpu(void) @@ -158,20 +159,15 @@ void __kprobes vtime_stop_cpu(void) 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 = 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, psw_mask); - /* Reenable preemption tracer. */ - start_critical_timings(); - /* Account time spent with enabled wait psw loaded as idle time. */ idle->sequence++; smp_wmb(); @@ -191,11 +187,11 @@ cputime64_t s390_get_idle_time(int cpu) unsigned int sequence; do { - now = get_clock(); + now = get_tod_clock(); sequence = ACCESS_ONCE(idle->sequence); idle_enter = ACCESS_ONCE(idle->clock_idle_enter); idle_exit = ACCESS_ONCE(idle->clock_idle_exit); - } while ((sequence & 1) || (idle->sequence != sequence)); + } while ((sequence & 1) || (ACCESS_ONCE(idle->sequence) != sequence)); return idle_enter ? ((idle_exit ?: now) - idle_enter) : 0; } @@ -376,14 +372,14 @@ EXPORT_SYMBOL(del_virt_timer); /* * Start the virtual CPU timer on the current CPU. */ -void __cpuinit init_cpu_vtimer(void) +void init_cpu_vtimer(void) { /* set initial cpu timer */ set_vtimer(VTIMER_MAX_SLICE); } -static int __cpuinit s390_nohz_notify(struct notifier_block *self, - unsigned long action, void *hcpu) +static int s390_nohz_notify(struct notifier_block *self, unsigned long action, + void *hcpu) { struct s390_idle_data *idle; long cpu = (long) hcpu; |