diff options
Diffstat (limited to 'arch/s390/kernel')
40 files changed, 974 insertions, 684 deletions
diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile index c75ed43b1a18..c7be8e10b87e 100644 --- a/arch/s390/kernel/Makefile +++ b/arch/s390/kernel/Makefile @@ -32,7 +32,7 @@ extra-y += head.o init_task.o vmlinux.lds obj-$(CONFIG_MODULES) += s390_ksyms.o module.o obj-$(CONFIG_SMP) += smp.o 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 \ @@ -41,7 +41,7 @@ obj-$(CONFIG_COMPAT) += compat_linux.o compat_signal.o \ obj-$(CONFIG_STACKTRACE) += stacktrace.o obj-$(CONFIG_KPROBES) += kprobes.o -obj-$(CONFIG_FUNCTION_TRACER) += mcount.o +obj-$(CONFIG_FUNCTION_TRACER) += $(if $(CONFIG_64BIT),mcount64.o,mcount.o) obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c index fa9905ce7d0b..63e46433e81d 100644 --- a/arch/s390/kernel/asm-offsets.c +++ b/arch/s390/kernel/asm-offsets.c @@ -7,6 +7,7 @@ #include <linux/sched.h> #include <linux/kbuild.h> #include <asm/vdso.h> +#include <asm/sigp.h> int main(void) { @@ -59,6 +60,10 @@ int main(void) DEFINE(CLOCK_REALTIME, CLOCK_REALTIME); DEFINE(CLOCK_MONOTONIC, CLOCK_MONOTONIC); DEFINE(CLOCK_REALTIME_RES, MONOTONIC_RES_NSEC); - + /* constants for SIGP */ + DEFINE(__SIGP_STOP, sigp_stop); + DEFINE(__SIGP_RESTART, sigp_restart); + DEFINE(__SIGP_SENSE, sigp_sense); + DEFINE(__SIGP_INITIAL_CPU_RESET, sigp_initial_cpu_reset); return 0; } diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c index 9ab188d67a3d..fda1a8123f9b 100644 --- a/arch/s390/kernel/compat_linux.c +++ b/arch/s390/kernel/compat_linux.c @@ -24,7 +24,6 @@ #include <linux/signal.h> #include <linux/resource.h> #include <linux/times.h> -#include <linux/utsname.h> #include <linux/smp.h> #include <linux/smp_lock.h> #include <linux/sem.h> @@ -443,66 +442,28 @@ sys32_rt_sigqueueinfo(int pid, int sig, compat_siginfo_t __user *uinfo) * sys32_execve() executes a new program after the asm stub has set * things up for us. This should basically do what I want it to. */ -asmlinkage long sys32_execve(void) +asmlinkage long sys32_execve(char __user *name, compat_uptr_t __user *argv, + compat_uptr_t __user *envp) { struct pt_regs *regs = task_pt_regs(current); char *filename; - unsigned long result; - int rc; - - filename = getname(compat_ptr(regs->orig_gpr2)); - if (IS_ERR(filename)) { - result = PTR_ERR(filename); - goto out; - } - rc = compat_do_execve(filename, compat_ptr(regs->gprs[3]), - compat_ptr(regs->gprs[4]), regs); - if (rc) { - result = rc; - goto out_putname; - } + long rc; + + filename = getname(name); + rc = PTR_ERR(filename); + if (IS_ERR(filename)) + return rc; + rc = compat_do_execve(filename, argv, envp, regs); + if (rc) + goto out; current->thread.fp_regs.fpc=0; asm volatile("sfpc %0,0" : : "d" (0)); - result = regs->gprs[2]; -out_putname: - putname(filename); + rc = regs->gprs[2]; out: - return result; -} - - -#ifdef CONFIG_MODULES - -asmlinkage long -sys32_init_module(void __user *umod, unsigned long len, - const char __user *uargs) -{ - return sys_init_module(umod, len, uargs); -} - -asmlinkage long -sys32_delete_module(const char __user *name_user, unsigned int flags) -{ - return sys_delete_module(name_user, flags); -} - -#else /* CONFIG_MODULES */ - -asmlinkage long -sys32_init_module(void __user *umod, unsigned long len, - const char __user *uargs) -{ - return -ENOSYS; -} - -asmlinkage long -sys32_delete_module(const char __user *name_user, unsigned int flags) -{ - return -ENOSYS; + putname(filename); + return rc; } -#endif /* CONFIG_MODULES */ - asmlinkage long sys32_pread64(unsigned int fd, char __user *ubuf, size_t count, u32 poshi, u32 poslo) { @@ -566,59 +527,6 @@ asmlinkage long sys32_sendfile64(int out_fd, int in_fd, return ret; } -#ifdef CONFIG_SYSCTL_SYSCALL -struct __sysctl_args32 { - u32 name; - int nlen; - u32 oldval; - u32 oldlenp; - u32 newval; - u32 newlen; - u32 __unused[4]; -}; - -asmlinkage long sys32_sysctl(struct __sysctl_args32 __user *args) -{ - struct __sysctl_args32 tmp; - int error; - size_t oldlen; - size_t __user *oldlenp = NULL; - unsigned long addr = (((unsigned long)&args->__unused[0]) + 7) & ~7; - - if (copy_from_user(&tmp, args, sizeof(tmp))) - return -EFAULT; - - if (tmp.oldval && tmp.oldlenp) { - /* Duh, this is ugly and might not work if sysctl_args - is in read-only memory, but do_sysctl does indirectly - a lot of uaccess in both directions and we'd have to - basically copy the whole sysctl.c here, and - glibc's __sysctl uses rw memory for the structure - anyway. */ - if (get_user(oldlen, (u32 __user *)compat_ptr(tmp.oldlenp)) || - put_user(oldlen, (size_t __user *)addr)) - return -EFAULT; - oldlenp = (size_t __user *)addr; - } - - lock_kernel(); - error = do_sysctl(compat_ptr(tmp.name), tmp.nlen, compat_ptr(tmp.oldval), - oldlenp, compat_ptr(tmp.newval), tmp.newlen); - unlock_kernel(); - if (oldlenp) { - if (!error) { - if (get_user(oldlen, (size_t __user *)addr) || - put_user(oldlen, (u32 __user *)compat_ptr(tmp.oldlenp))) - error = -EFAULT; - } - if (copy_to_user(args->__unused, tmp.__unused, - sizeof(tmp.__unused))) - error = -EFAULT; - } - return error; -} -#endif - struct stat64_emu31 { unsigned long long st_dev; unsigned int __pad1; @@ -801,23 +709,6 @@ asmlinkage long sys32_write(unsigned int fd, char __user * buf, size_t count) return sys_write(fd, buf, count); } -asmlinkage long sys32_clone(void) -{ - struct pt_regs *regs = task_pt_regs(current); - unsigned long clone_flags; - unsigned long newsp; - int __user *parent_tidptr, *child_tidptr; - - clone_flags = regs->gprs[3] & 0xffffffffUL; - newsp = regs->orig_gpr2 & 0x7fffffffUL; - parent_tidptr = compat_ptr(regs->gprs[4]); - child_tidptr = compat_ptr(regs->gprs[5]); - if (!newsp) - newsp = regs->gprs[15]; - return do_fork(clone_flags, newsp, regs, 0, - parent_tidptr, child_tidptr); -} - /* * 31 bit emulation wrapper functions for sys_fadvise64/fadvise64_64. * These need to rewrite the advise values for POSIX_FADV_{DONTNEED,NOREUSE} diff --git a/arch/s390/kernel/compat_linux.h b/arch/s390/kernel/compat_linux.h index 836a28842900..45e9092b3aad 100644 --- a/arch/s390/kernel/compat_linux.h +++ b/arch/s390/kernel/compat_linux.h @@ -162,7 +162,6 @@ struct ucontext32 { compat_sigset_t uc_sigmask; /* mask last for extensibility */ }; -struct __sysctl_args32; struct stat64_emu31; struct mmap_arg_struct_emu31; struct fadvise64_64_args; @@ -198,7 +197,8 @@ long sys32_rt_sigprocmask(int how, compat_sigset_t __user *set, compat_sigset_t __user *oset, size_t sigsetsize); long sys32_rt_sigpending(compat_sigset_t __user *set, size_t sigsetsize); long sys32_rt_sigqueueinfo(int pid, int sig, compat_siginfo_t __user *uinfo); -long sys32_execve(void); +long sys32_execve(char __user *name, compat_uptr_t __user *argv, + compat_uptr_t __user *envp); long sys32_init_module(void __user *umod, unsigned long len, const char __user *uargs); long sys32_delete_module(const char __user *name_user, unsigned int flags); @@ -211,7 +211,6 @@ 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_sysctl(struct __sysctl_args32 __user *args); long sys32_stat64(char __user * filename, struct stat64_emu31 __user * statbuf); long sys32_lstat64(char __user * filename, struct stat64_emu31 __user * statbuf); @@ -222,7 +221,6 @@ 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, char __user * buf, size_t count); -long sys32_clone(void); 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, diff --git a/arch/s390/kernel/compat_signal.c b/arch/s390/kernel/compat_signal.c index b537cb0e9b55..eee999853a7c 100644 --- a/arch/s390/kernel/compat_signal.c +++ b/arch/s390/kernel/compat_signal.c @@ -39,6 +39,7 @@ typedef struct struct sigcontext32 sc; _sigregs32 sregs; int signo; + __u32 gprs_high[NUM_GPRS]; __u8 retcode[S390_SYSCALL_SIZE]; } sigframe32; @@ -48,6 +49,7 @@ typedef struct __u8 retcode[S390_SYSCALL_SIZE]; compat_siginfo_t info; struct ucontext32 uc; + __u32 gprs_high[NUM_GPRS]; } rt_sigframe32; int copy_siginfo_to_user32(compat_siginfo_t __user *to, siginfo_t *from) @@ -344,6 +346,30 @@ static int restore_sigregs32(struct pt_regs *regs,_sigregs32 __user *sregs) return 0; } +static int save_sigregs_gprs_high(struct pt_regs *regs, __u32 __user *uregs) +{ + __u32 gprs_high[NUM_GPRS]; + int i; + + for (i = 0; i < NUM_GPRS; i++) + gprs_high[i] = regs->gprs[i] >> 32; + + return __copy_to_user(uregs, &gprs_high, sizeof(gprs_high)); +} + +static int restore_sigregs_gprs_high(struct pt_regs *regs, __u32 __user *uregs) +{ + __u32 gprs_high[NUM_GPRS]; + int err, i; + + err = __copy_from_user(&gprs_high, uregs, sizeof(gprs_high)); + if (err) + return err; + for (i = 0; i < NUM_GPRS; i++) + *(__u32 *)®s->gprs[i] = gprs_high[i]; + return 0; +} + asmlinkage long sys32_sigreturn(void) { struct pt_regs *regs = task_pt_regs(current); @@ -363,6 +389,8 @@ asmlinkage long sys32_sigreturn(void) if (restore_sigregs32(regs, &frame->sregs)) goto badframe; + if (restore_sigregs_gprs_high(regs, frame->gprs_high)) + goto badframe; return regs->gprs[2]; @@ -394,6 +422,8 @@ asmlinkage long sys32_rt_sigreturn(void) if (restore_sigregs32(regs, &frame->uc.uc_mcontext)) goto badframe; + if (restore_sigregs_gprs_high(regs, frame->gprs_high)) + goto badframe; err = __get_user(ss_sp, &frame->uc.uc_stack.ss_sp); st.ss_sp = compat_ptr(ss_sp); @@ -474,6 +504,8 @@ static int setup_frame32(int sig, struct k_sigaction *ka, if (save_sigregs32(regs, &frame->sregs)) goto give_sigsegv; + if (save_sigregs_gprs_high(regs, frame->gprs_high)) + goto give_sigsegv; if (__put_user((unsigned long) &frame->sregs, &frame->sc.sregs)) goto give_sigsegv; @@ -529,13 +561,14 @@ static int setup_rt_frame32(int sig, struct k_sigaction *ka, siginfo_t *info, goto give_sigsegv; /* Create the ucontext. */ - err |= __put_user(0, &frame->uc.uc_flags); + err |= __put_user(UC_EXTENDED, &frame->uc.uc_flags); err |= __put_user(0, &frame->uc.uc_link); err |= __put_user(current->sas_ss_sp, &frame->uc.uc_stack.ss_sp); err |= __put_user(sas_ss_flags(regs->gprs[15]), &frame->uc.uc_stack.ss_flags); err |= __put_user(current->sas_ss_size, &frame->uc.uc_stack.ss_size); err |= save_sigregs32(regs, &frame->uc.uc_mcontext); + err |= save_sigregs_gprs_high(regs, frame->gprs_high); err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)); if (err) goto give_sigsegv; diff --git a/arch/s390/kernel/compat_wrapper.S b/arch/s390/kernel/compat_wrapper.S index 88a83366819f..30de2d0e52bb 100644 --- a/arch/s390/kernel/compat_wrapper.S +++ b/arch/s390/kernel/compat_wrapper.S @@ -409,7 +409,7 @@ sys32_munmap_wrapper: .globl sys32_truncate_wrapper sys32_truncate_wrapper: llgtr %r2,%r2 # const char * - llgfr %r3,%r3 # unsigned long + lgfr %r3,%r3 # long jg sys_truncate # branch to system call .globl sys32_ftruncate_wrapper @@ -568,18 +568,18 @@ compat_sys_sigprocmask_wrapper: llgtr %r4,%r4 # compat_old_sigset_t * jg compat_sys_sigprocmask # branch to system call - .globl sys32_init_module_wrapper -sys32_init_module_wrapper: + .globl sys_init_module_wrapper +sys_init_module_wrapper: llgtr %r2,%r2 # void * llgfr %r3,%r3 # unsigned long llgtr %r4,%r4 # char * - jg sys32_init_module # branch to system call + jg sys_init_module # branch to system call - .globl sys32_delete_module_wrapper -sys32_delete_module_wrapper: + .globl sys_delete_module_wrapper +sys_delete_module_wrapper: llgtr %r2,%r2 # const char * llgfr %r3,%r3 # unsigned int - jg sys32_delete_module # branch to system call + jg sys_delete_module # branch to system call .globl sys32_quotactl_wrapper sys32_quotactl_wrapper: @@ -689,8 +689,6 @@ sys32_fdatasync_wrapper: llgfr %r2,%r2 # unsigned int jg sys_fdatasync # branch to system call -#sys32_sysctl_wrapper # tbd - .globl sys32_mlock_wrapper sys32_mlock_wrapper: llgfr %r2,%r2 # unsigned long @@ -1087,8 +1085,8 @@ sys32_stime_wrapper: .globl sys32_sysctl_wrapper sys32_sysctl_wrapper: - llgtr %r2,%r2 # struct __sysctl_args32 * - jg sys32_sysctl + llgtr %r2,%r2 # struct compat_sysctl_args * + jg compat_sys_sysctl .globl sys32_fstat64_wrapper sys32_fstat64_wrapper: @@ -1832,11 +1830,26 @@ compat_sys_rt_tgsigqueueinfo_wrapper: llgtr %r5,%r5 # struct compat_siginfo * jg compat_sys_rt_tgsigqueueinfo_wrapper # branch to system call - .globl sys_perf_counter_open_wrapper -sys_perf_counter_open_wrapper: - llgtr %r2,%r2 # const struct perf_counter_attr * + .globl sys_perf_event_open_wrapper +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_counter_open # branch to system call + jg sys_perf_event_open # branch to system call + + .globl sys_clone_wrapper +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 + + .globl sys32_execve_wrapper +sys32_execve_wrapper: + llgtr %r2,%r2 # char * + llgtr %r3,%r3 # compat_uptr_t * + llgtr %r4,%r4 # compat_uptr_t * + jg sys32_execve # branch to system call diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c index be8bceaf37d9..071c81f179ef 100644 --- a/arch/s390/kernel/debug.c +++ b/arch/s390/kernel/debug.c @@ -63,8 +63,6 @@ typedef struct } debug_sprintf_entry_t; -extern void tod_to_timeval(uint64_t todval, struct timespec *xtime); - /* internal function prototyes */ static int debug_init(void); @@ -883,11 +881,11 @@ static int debug_active=1; * if debug_active is already off */ static int -s390dbf_procactive(ctl_table *table, int write, struct file *filp, +s390dbf_procactive(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { if (!write || debug_stoppable || !debug_active) - return proc_dointvec(table, write, filp, buffer, lenp, ppos); + return proc_dointvec(table, write, buffer, lenp, ppos); else return 0; } @@ -895,35 +893,30 @@ s390dbf_procactive(ctl_table *table, int write, struct file *filp, static struct ctl_table s390dbf_table[] = { { - .ctl_name = CTL_S390DBF_STOPPABLE, .procname = "debug_stoppable", .data = &debug_stoppable, .maxlen = sizeof(int), .mode = S_IRUGO | S_IWUSR, - .proc_handler = &proc_dointvec, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = CTL_S390DBF_ACTIVE, .procname = "debug_active", .data = &debug_active, .maxlen = sizeof(int), .mode = S_IRUGO | S_IWUSR, - .proc_handler = &s390dbf_procactive, - .strategy = &sysctl_intvec, + .proc_handler = s390dbf_procactive, }, - { .ctl_name = 0 } + { } }; static struct ctl_table s390dbf_dir_table[] = { { - .ctl_name = CTL_S390DBF, .procname = "s390dbf", .maxlen = 0, .mode = S_IRUGO | S_IXUGO, .child = s390dbf_table, }, - { .ctl_name = 0 } + { } }; static struct ctl_table_header *s390dbf_sysctl_header; @@ -1450,17 +1443,13 @@ debug_dflt_header_fn(debug_info_t * id, struct debug_view *view, int area, debug_entry_t * entry, char *out_buf) { struct timespec time_spec; - unsigned long long time; char *except_str; unsigned long caller; int rc = 0; unsigned int level; level = entry->id.fields.level; - time = entry->id.stck; - /* adjust todclock to 1970 */ - time -= 0x8126d60e46000000LL - (0x3c26700LL * 1000000 * 4096); - tod_to_timeval(time, &time_spec); + stck_to_timespec(entry->id.stck, &time_spec); if (entry->id.fields.exception) except_str = "*"; diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c index cae14c499511..e49e9e0c69fd 100644 --- a/arch/s390/kernel/early.c +++ b/arch/s390/kernel/early.c @@ -6,6 +6,9 @@ * Heiko Carstens <heiko.carstens@de.ibm.com> */ +#define KMSG_COMPONENT "setup" +#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt + #include <linux/compiler.h> #include <linux/init.h> #include <linux/errno.h> @@ -16,6 +19,7 @@ #include <linux/module.h> #include <linux/pfn.h> #include <linux/uaccess.h> +#include <linux/kernel.h> #include <asm/ebcdic.h> #include <asm/ipl.h> #include <asm/lowcore.h> @@ -35,8 +39,6 @@ char kernel_nss_name[NSS_NAME_SIZE + 1]; -static unsigned long machine_flags; - static void __init setup_boot_command_line(void); /* @@ -53,6 +55,7 @@ static void __init reset_tod_clock(void) disabled_wait(0); sched_clock_base_cc = TOD_UNIX_EPOCH; + S390_lowcore.last_update_clock = sched_clock_base_cc; } #ifdef CONFIG_SHARED_KERNEL @@ -81,6 +84,8 @@ asm( " br 14\n" " .size savesys_ipl_nss, .-savesys_ipl_nss\n"); +static __initdata char upper_command_line[COMMAND_LINE_SIZE]; + static noinline __init void create_kernel_nss(void) { unsigned int i, stext_pfn, eshared_pfn, end_pfn, min_size; @@ -90,7 +95,6 @@ static noinline __init void create_kernel_nss(void) int response; size_t len; char *savesys_ptr; - char upper_command_line[COMMAND_LINE_SIZE]; char defsys_cmd[DEFSYS_CMD_SIZE]; char savesys_cmd[SAVESYS_CMD_SIZE]; @@ -141,6 +145,8 @@ static noinline __init void create_kernel_nss(void) __cpcmd(defsys_cmd, NULL, 0, &response); if (response != 0) { + pr_err("Defining the Linux kernel NSS failed with rc=%d\n", + response); kernel_nss_name[0] = '\0'; return; } @@ -153,12 +159,23 @@ static noinline __init void create_kernel_nss(void) * max SAVESYS_CMD_SIZE * On error: response contains the numeric portion of cp error message. * for SAVESYS it will be >= 263 + * for missing privilege class, it will be 1 */ - if (response > SAVESYS_CMD_SIZE) { + if (response > SAVESYS_CMD_SIZE || response == 1) { + pr_err("Saving the Linux kernel NSS failed with rc=%d\n", + response); kernel_nss_name[0] = '\0'; return; } + /* re-initialize cputime accounting. */ + sched_clock_base_cc = get_clock(); + S390_lowcore.last_update_clock = sched_clock_base_cc; + S390_lowcore.last_update_timer = 0x7fffffffffffffffULL; + S390_lowcore.user_timer = 0; + S390_lowcore.system_timer = 0; + asm volatile("SPT 0(%0)" : : "a" (&S390_lowcore.last_update_timer)); + /* re-setup boot command line with new ipl vm parms */ ipl_update_parameters(); setup_boot_command_line(); @@ -205,12 +222,9 @@ static noinline __init void detect_machine_type(void) /* Running under KVM? If not we assume z/VM */ if (!memcmp(vmms.vm[0].cpi, "\xd2\xe5\xd4", 3)) - machine_flags |= MACHINE_FLAG_KVM; + S390_lowcore.machine_flags |= MACHINE_FLAG_KVM; else - machine_flags |= MACHINE_FLAG_VM; - - /* Store machine flags for setting up lowcore early */ - S390_lowcore.machine_flags = machine_flags; + S390_lowcore.machine_flags |= MACHINE_FLAG_VM; } static __init void early_pgm_check_handler(void) @@ -245,7 +259,7 @@ static noinline __init void setup_hpage(void) facilities = stfl(); if (!(facilities & (1UL << 23)) || !(facilities & (1UL << 29))) return; - machine_flags |= MACHINE_FLAG_HPAGE; + S390_lowcore.machine_flags |= MACHINE_FLAG_HPAGE; __ctl_set_bit(0, 23); #endif } @@ -263,7 +277,7 @@ static __init void detect_mvpg(void) EX_TABLE(0b,1b) : "=d" (rc) : "0" (-EOPNOTSUPP), "a" (0) : "memory", "cc", "0"); if (!rc) - machine_flags |= MACHINE_FLAG_MVPG; + S390_lowcore.machine_flags |= MACHINE_FLAG_MVPG; #endif } @@ -279,7 +293,7 @@ static __init void detect_ieee(void) EX_TABLE(0b,1b) : "=d" (rc), "=d" (tmp): "0" (-EOPNOTSUPP) : "cc"); if (!rc) - machine_flags |= MACHINE_FLAG_IEEE; + S390_lowcore.machine_flags |= MACHINE_FLAG_IEEE; #endif } @@ -298,7 +312,7 @@ static __init void detect_csp(void) EX_TABLE(0b,1b) : "=d" (rc) : "0" (-EOPNOTSUPP) : "cc", "0", "1", "2"); if (!rc) - machine_flags |= MACHINE_FLAG_CSP; + S390_lowcore.machine_flags |= MACHINE_FLAG_CSP; #endif } @@ -315,7 +329,7 @@ static __init void detect_diag9c(void) EX_TABLE(0b,1b) : "=d" (rc) : "0" (-EOPNOTSUPP), "d" (cpu_address) : "cc"); if (!rc) - machine_flags |= MACHINE_FLAG_DIAG9C; + S390_lowcore.machine_flags |= MACHINE_FLAG_DIAG9C; } static __init void detect_diag44(void) @@ -330,7 +344,7 @@ static __init void detect_diag44(void) EX_TABLE(0b,1b) : "=d" (rc) : "0" (-EOPNOTSUPP) : "cc"); if (!rc) - machine_flags |= MACHINE_FLAG_DIAG44; + S390_lowcore.machine_flags |= MACHINE_FLAG_DIAG44; #endif } @@ -341,11 +355,11 @@ static __init void detect_machine_facilities(void) facilities = stfl(); if (facilities & (1 << 28)) - machine_flags |= MACHINE_FLAG_IDTE; + S390_lowcore.machine_flags |= MACHINE_FLAG_IDTE; if (facilities & (1 << 23)) - machine_flags |= MACHINE_FLAG_PFMF; + S390_lowcore.machine_flags |= MACHINE_FLAG_PFMF; if (facilities & (1 << 4)) - machine_flags |= MACHINE_FLAG_MVCOS; + S390_lowcore.machine_flags |= MACHINE_FLAG_MVCOS; #endif } @@ -367,21 +381,35 @@ static __init void rescue_initrd(void) } /* Set up boot command line */ -static void __init setup_boot_command_line(void) +static void __init append_to_cmdline(size_t (*ipl_data)(char *, size_t)) { - char *parm = NULL; + char *parm, *delim; + size_t rc, len; + + len = strlen(boot_command_line); + + delim = boot_command_line + len; /* '\0' character position */ + parm = boot_command_line + len + 1; /* append right after '\0' */ + rc = ipl_data(parm, COMMAND_LINE_SIZE - len - 1); + if (rc) { + if (*parm == '=') + memmove(boot_command_line, parm + 1, rc); + else + *delim = ' '; /* replace '\0' with space */ + } +} + +static void __init setup_boot_command_line(void) +{ /* copy arch command line */ strlcpy(boot_command_line, COMMAND_LINE, ARCH_COMMAND_LINE_SIZE); /* append IPL PARM data to the boot command line */ - if (MACHINE_IS_VM) { - parm = boot_command_line + strlen(boot_command_line); - *parm++ = ' '; - get_ipl_vmparm(parm); - if (parm[0] == '=') - memmove(boot_command_line, parm + 1, strlen(parm)); - } + if (MACHINE_IS_VM) + append_to_cmdline(append_ipl_vmparm); + + append_to_cmdline(append_ipl_scpdata); } @@ -413,7 +441,6 @@ void __init startup_init(void) setup_hpage(); sclp_facilities_detect(); detect_memory_layout(memory_chunk); - S390_lowcore.machine_flags = machine_flags; #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 c4c80a22bc1f..48215d15762b 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -54,7 +54,7 @@ _TIF_WORK_SVC = (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | \ _TIF_WORK_INT = (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | \ _TIF_MCCK_PENDING) _TIF_SYSCALL = (_TIF_SYSCALL_TRACE>>8 | _TIF_SYSCALL_AUDIT>>8 | \ - _TIF_SECCOMP>>8 | _TIF_SYSCALL_FTRACE>>8) + _TIF_SECCOMP>>8 | _TIF_SYSCALL_TRACEPOINT>>8) STACK_SHIFT = PAGE_SHIFT + THREAD_ORDER STACK_SIZE = 1 << STACK_SHIFT @@ -278,7 +278,8 @@ sysc_return: bnz BASED(sysc_work) # there is work to do (signals etc.) sysc_restore: #ifdef CONFIG_TRACE_IRQFLAGS - la %r1,BASED(sysc_restore_trace_psw) + la %r1,BASED(sysc_restore_trace_psw_addr) + l %r1,0(%r1) lpsw 0(%r1) sysc_restore_trace: TRACE_IRQS_CHECK @@ -289,10 +290,15 @@ sysc_leave: sysc_done: #ifdef CONFIG_TRACE_IRQFLAGS +sysc_restore_trace_psw_addr: + .long sysc_restore_trace_psw + + .section .data,"aw",@progbits .align 8 .globl sysc_restore_trace_psw sysc_restore_trace_psw: .long 0, sysc_restore_trace + 0x80000000 + .previous #endif # @@ -559,10 +565,10 @@ pgm_svcper: lh %r7,0x8a # get svc number from lowcore l %r9,__LC_THREAD_INFO # load pointer to thread_info struct TRACE_IRQS_OFF - l %r1,__TI_task(%r9) - mvc __THREAD_per+__PER_atmid(2,%r1),__LC_PER_ATMID - mvc __THREAD_per+__PER_address(4,%r1),__LC_PER_ADDRESS - mvc __THREAD_per+__PER_access_id(1,%r1),__LC_PER_ACCESS_ID + l %r8,__TI_task(%r9) + mvc __THREAD_per+__PER_atmid(2,%r8),__LC_PER_ATMID + mvc __THREAD_per+__PER_address(4,%r8),__LC_PER_ADDRESS + mvc __THREAD_per+__PER_access_id(1,%r8),__LC_PER_ACCESS_ID oi __TI_flags+3(%r9),_TIF_SINGLE_STEP # set TIF_SINGLE_STEP TRACE_IRQS_ON stosm __SF_EMPTY(%r15),0x03 # reenable interrupts @@ -606,7 +612,8 @@ io_return: bnz BASED(io_work) # there is work to do (signals etc.) io_restore: #ifdef CONFIG_TRACE_IRQFLAGS - la %r1,BASED(io_restore_trace_psw) + la %r1,BASED(io_restore_trace_psw_addr) + l %r1,0(%r1) lpsw 0(%r1) io_restore_trace: TRACE_IRQS_CHECK @@ -617,10 +624,15 @@ io_leave: io_done: #ifdef CONFIG_TRACE_IRQFLAGS +io_restore_trace_psw_addr: + .long io_restore_trace_psw + + .section .data,"aw",@progbits .align 8 .globl io_restore_trace_psw io_restore_trace_psw: .long 0, io_restore_trace + 0x80000000 + .previous #endif # diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h index 950c59c6688b..e1e5e767ab56 100644 --- a/arch/s390/kernel/entry.h +++ b/arch/s390/kernel/entry.h @@ -42,10 +42,12 @@ long sys_s390_fadvise64_64(struct fadvise64_64_args __user *args); long sys_s390_fallocate(int fd, int mode, loff_t offset, u32 len_high, u32 len_low); long sys_fork(void); -long sys_clone(void); +long sys_clone(unsigned long newsp, unsigned long clone_flags, + int __user *parent_tidptr, int __user *child_tidptr); long sys_vfork(void); void execve_tail(void); -long sys_execve(void); +long sys_execve(char __user *name, char __user * __user *argv, + char __user * __user *envp); long sys_sigsuspend(int history0, int history1, old_sigset_t mask); long sys_sigaction(int sig, const struct old_sigaction __user *act, struct old_sigaction __user *oact); diff --git a/arch/s390/kernel/entry64.S b/arch/s390/kernel/entry64.S index f6618e9e15ef..9aff1d449b6e 100644 --- a/arch/s390/kernel/entry64.S +++ b/arch/s390/kernel/entry64.S @@ -57,7 +57,7 @@ _TIF_WORK_SVC = (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | \ _TIF_WORK_INT = (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | \ _TIF_MCCK_PENDING) _TIF_SYSCALL = (_TIF_SYSCALL_TRACE>>8 | _TIF_SYSCALL_AUDIT>>8 | \ - _TIF_SECCOMP>>8 | _TIF_SYSCALL_FTRACE>>8) + _TIF_SECCOMP>>8 | _TIF_SYSCALL_TRACEPOINT>>8) #define BASED(name) name-system_call(%r13) @@ -284,10 +284,12 @@ sysc_leave: sysc_done: #ifdef CONFIG_TRACE_IRQFLAGS + .section .data,"aw",@progbits .align 8 .globl sysc_restore_trace_psw sysc_restore_trace_psw: .quad 0, sysc_restore_trace + .previous #endif # @@ -541,10 +543,10 @@ pgm_svcper: mvc __LC_LAST_UPDATE_TIMER(8),__LC_SYNC_ENTER_TIMER llgh %r7,__LC_SVC_INT_CODE # get svc number from lowcore lg %r9,__LC_THREAD_INFO # load pointer to thread_info struct - lg %r1,__TI_task(%r9) - mvc __THREAD_per+__PER_atmid(2,%r1),__LC_PER_ATMID - mvc __THREAD_per+__PER_address(8,%r1),__LC_PER_ADDRESS - mvc __THREAD_per+__PER_access_id(1,%r1),__LC_PER_ACCESS_ID + lg %r8,__TI_task(%r9) + mvc __THREAD_per+__PER_atmid(2,%r8),__LC_PER_ATMID + mvc __THREAD_per+__PER_address(8,%r8),__LC_PER_ADDRESS + mvc __THREAD_per+__PER_access_id(1,%r8),__LC_PER_ACCESS_ID oi __TI_flags+7(%r9),_TIF_SINGLE_STEP # set TIF_SINGLE_STEP TRACE_IRQS_ON stosm __SF_EMPTY(%r15),0x03 # reenable interrupts @@ -595,10 +597,12 @@ io_leave: io_done: #ifdef CONFIG_TRACE_IRQFLAGS + .section .data,"aw",@progbits .align 8 .globl io_restore_trace_psw io_restore_trace_psw: .quad 0, io_restore_trace + .previous #endif # diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c index 3e298e64f0db..5a82bc68193e 100644 --- a/arch/s390/kernel/ftrace.c +++ b/arch/s390/kernel/ftrace.c @@ -185,9 +185,6 @@ unsigned long prepare_ftrace_return(unsigned long ip, unsigned long parent) { struct ftrace_graph_ent trace; - /* Nmi's are currently unsupported. */ - if (unlikely(in_nmi())) - goto out; if (unlikely(atomic_read(¤t->tracing_graph_pause))) goto out; if (ftrace_push_return_trace(parent, ip, &trace.depth, 0) == -EBUSY) @@ -206,55 +203,10 @@ out: #ifdef CONFIG_FTRACE_SYSCALLS -extern unsigned long __start_syscalls_metadata[]; -extern unsigned long __stop_syscalls_metadata[]; extern unsigned int sys_call_table[]; -static struct syscall_metadata **syscalls_metadata; - -struct syscall_metadata *syscall_nr_to_meta(int nr) +unsigned long __init arch_syscall_addr(int nr) { - if (!syscalls_metadata || nr >= NR_syscalls || nr < 0) - return NULL; - - return syscalls_metadata[nr]; -} - -static struct syscall_metadata *find_syscall_meta(unsigned long syscall) -{ - struct syscall_metadata *start; - struct syscall_metadata *stop; - char str[KSYM_SYMBOL_LEN]; - - start = (struct syscall_metadata *)__start_syscalls_metadata; - stop = (struct syscall_metadata *)__stop_syscalls_metadata; - kallsyms_lookup(syscall, NULL, NULL, NULL, str); - - for ( ; start < stop; start++) { - if (start->name && !strcmp(start->name + 3, str + 3)) - return start; - } - return NULL; -} - -void arch_init_ftrace_syscalls(void) -{ - struct syscall_metadata *meta; - int i; - static atomic_t refs; - - if (atomic_inc_return(&refs) != 1) - goto out; - syscalls_metadata = kzalloc(sizeof(*syscalls_metadata) * NR_syscalls, - GFP_KERNEL); - if (!syscalls_metadata) - goto out; - for (i = 0; i < NR_syscalls; i++) { - meta = find_syscall_meta((unsigned long)sys_call_table[i]); - syscalls_metadata[i] = meta; - } - return; -out: - atomic_dec(&refs); + return (unsigned long)sys_call_table[nr]; } #endif diff --git a/arch/s390/kernel/head.S b/arch/s390/kernel/head.S index ec6882348520..c52b4f7742fa 100644 --- a/arch/s390/kernel/head.S +++ b/arch/s390/kernel/head.S @@ -27,6 +27,7 @@ #include <asm/asm-offsets.h> #include <asm/thread_info.h> #include <asm/page.h> +#include <asm/cpu.h> #ifdef CONFIG_64BIT #define ARCH_OFFSET 4 diff --git a/arch/s390/kernel/head31.S b/arch/s390/kernel/head31.S index 2ced846065b7..602b508cd4c4 100644 --- a/arch/s390/kernel/head31.S +++ b/arch/s390/kernel/head31.S @@ -24,6 +24,7 @@ startup_continue: # Setup stack # l %r15,.Linittu-.LPG1(%r13) + st %r15,__LC_THREAD_INFO # cache thread info in lowcore mvc __LC_CURRENT(4),__TI_task(%r15) ahi %r15,1<<(PAGE_SHIFT+THREAD_ORDER) # init_task_union+THREAD_SIZE st %r15,__LC_KERNEL_STACK # set end of kernel stack diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S index 65667b2e65ce..6a250808092b 100644 --- a/arch/s390/kernel/head64.S +++ b/arch/s390/kernel/head64.S @@ -62,9 +62,9 @@ startup_continue: clr %r11,%r12 je 5f # no more space in prefix array 4: - ahi %r8,1 # next cpu (r8 += 1) - cl %r8,.Llast_cpu-.LPG1(%r13) # is last possible cpu ? - jl 1b # jump if not last cpu + ahi %r8,1 # next cpu (r8 += 1) + chi %r8,MAX_CPU_ADDRESS # is last possible cpu ? + jle 1b # jump if not last cpu 5: lhi %r1,2 # mode 2 = esame (dump) j 6f @@ -92,6 +92,7 @@ startup_continue: # Setup stack # larl %r15,init_thread_union + stg %r15,__LC_THREAD_INFO # cache thread info in lowcore lg %r14,__TI_task(%r15) # cache current in lowcore stg %r14,__LC_CURRENT aghi %r15,1<<(PAGE_SHIFT+THREAD_ORDER) # init_task_union + THREAD_SIZE @@ -129,8 +130,6 @@ startup_continue: #ifdef CONFIG_ZFCPDUMP .Lcurrent_cpu: .long 0x0 -.Llast_cpu: - .long 0x0000ffff .Lpref_arr_ptr: .long zfcpdump_prefix_array #endif /* CONFIG_ZFCPDUMP */ diff --git a/arch/s390/kernel/init_task.c b/arch/s390/kernel/init_task.c index fe787f9e5f3f..4d1c9fb0b540 100644 --- a/arch/s390/kernel/init_task.c +++ b/arch/s390/kernel/init_task.c @@ -25,9 +25,8 @@ static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand); * way process stacks are handled. This is done by having a special * "init_task" linker map entry.. */ -union thread_union init_thread_union - __attribute__((__section__(".data.init_task"))) = - { INIT_THREAD_INFO(init_task) }; +union thread_union init_thread_union __init_task_data = + { INIT_THREAD_INFO(init_task) }; /* * Initial task structure. diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index 371a2d88f4ac..4890ac6d7faa 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -272,17 +272,18 @@ static ssize_t ipl_type_show(struct kobject *kobj, struct kobj_attribute *attr, static struct kobj_attribute sys_ipl_type_attr = __ATTR_RO(ipl_type); /* VM IPL PARM routines */ -static void reipl_get_ascii_vmparm(char *dest, +size_t reipl_get_ascii_vmparm(char *dest, size_t size, const struct ipl_parameter_block *ipb) { int i; - int len = 0; + size_t len; char has_lowercase = 0; + len = 0; if ((ipb->ipl_info.ccw.vm_flags & DIAG308_VM_FLAGS_VP_VALID) && (ipb->ipl_info.ccw.vm_parm_len > 0)) { - len = ipb->ipl_info.ccw.vm_parm_len; + len = min_t(size_t, size - 1, ipb->ipl_info.ccw.vm_parm_len); memcpy(dest, ipb->ipl_info.ccw.vm_parm, len); /* If at least one character is lowercase, we assume mixed * case; otherwise we convert everything to lowercase. @@ -299,14 +300,20 @@ static void reipl_get_ascii_vmparm(char *dest, EBCASC(dest, len); } dest[len] = 0; + + return len; } -void get_ipl_vmparm(char *dest) +size_t append_ipl_vmparm(char *dest, size_t size) { + size_t rc; + + rc = 0; if (diag308_set_works && (ipl_block.hdr.pbt == DIAG308_IPL_TYPE_CCW)) - reipl_get_ascii_vmparm(dest, &ipl_block); + rc = reipl_get_ascii_vmparm(dest, size, &ipl_block); else dest[0] = 0; + return rc; } static ssize_t ipl_vm_parm_show(struct kobject *kobj, @@ -314,10 +321,65 @@ static ssize_t ipl_vm_parm_show(struct kobject *kobj, { char parm[DIAG308_VMPARM_SIZE + 1] = {}; - get_ipl_vmparm(parm); + append_ipl_vmparm(parm, sizeof(parm)); return sprintf(page, "%s\n", parm); } +static size_t scpdata_length(const char* buf, size_t count) +{ + while (count) { + if (buf[count - 1] != '\0' && buf[count - 1] != ' ') + break; + count--; + } + return count; +} + +size_t reipl_append_ascii_scpdata(char *dest, size_t size, + const struct ipl_parameter_block *ipb) +{ + size_t count; + size_t i; + int has_lowercase; + + count = min(size - 1, scpdata_length(ipb->ipl_info.fcp.scp_data, + ipb->ipl_info.fcp.scp_data_len)); + if (!count) + goto out; + + has_lowercase = 0; + for (i = 0; i < count; i++) { + if (!isascii(ipb->ipl_info.fcp.scp_data[i])) { + count = 0; + goto out; + } + if (!has_lowercase && islower(ipb->ipl_info.fcp.scp_data[i])) + has_lowercase = 1; + } + + if (has_lowercase) + memcpy(dest, ipb->ipl_info.fcp.scp_data, count); + else + for (i = 0; i < count; i++) + dest[i] = tolower(ipb->ipl_info.fcp.scp_data[i]); +out: + dest[count] = '\0'; + return count; +} + +size_t append_ipl_scpdata(char *dest, size_t len) +{ + size_t rc; + + rc = 0; + if (ipl_block.hdr.pbt == DIAG308_IPL_TYPE_FCP) + rc = reipl_append_ascii_scpdata(dest, len, &ipl_block); + else + dest[0] = 0; + return rc; +} + + static struct kobj_attribute sys_ipl_vm_parm_attr = __ATTR(parm, S_IRUGO, ipl_vm_parm_show, NULL); @@ -553,7 +615,7 @@ static ssize_t reipl_generic_vmparm_show(struct ipl_parameter_block *ipb, { char vmparm[DIAG308_VMPARM_SIZE + 1] = {}; - reipl_get_ascii_vmparm(vmparm, ipb); + reipl_get_ascii_vmparm(vmparm, sizeof(vmparm), ipb); return sprintf(page, "%s\n", vmparm); } @@ -626,6 +688,59 @@ static struct kobj_attribute sys_reipl_ccw_vmparm_attr = /* FCP reipl device attributes */ +static ssize_t reipl_fcp_scpdata_read(struct kobject *kobj, + struct bin_attribute *attr, + char *buf, loff_t off, size_t count) +{ + size_t size = reipl_block_fcp->ipl_info.fcp.scp_data_len; + void *scp_data = reipl_block_fcp->ipl_info.fcp.scp_data; + + return memory_read_from_buffer(buf, count, &off, scp_data, size); +} + +static ssize_t reipl_fcp_scpdata_write(struct kobject *kobj, + struct bin_attribute *attr, + char *buf, loff_t off, size_t count) +{ + size_t padding; + size_t scpdata_len; + + if (off < 0) + return -EINVAL; + + if (off >= DIAG308_SCPDATA_SIZE) + return -ENOSPC; + + if (count > DIAG308_SCPDATA_SIZE - off) + count = DIAG308_SCPDATA_SIZE - off; + + memcpy(reipl_block_fcp->ipl_info.fcp.scp_data, buf + off, count); + scpdata_len = off + count; + + if (scpdata_len % 8) { + padding = 8 - (scpdata_len % 8); + memset(reipl_block_fcp->ipl_info.fcp.scp_data + scpdata_len, + 0, padding); + scpdata_len += padding; + } + + reipl_block_fcp->ipl_info.fcp.scp_data_len = scpdata_len; + reipl_block_fcp->hdr.len = IPL_PARM_BLK_FCP_LEN + scpdata_len; + reipl_block_fcp->hdr.blk0_len = IPL_PARM_BLK0_FCP_LEN + scpdata_len; + + return count; +} + +static struct bin_attribute sys_reipl_fcp_scp_data_attr = { + .attr = { + .name = "scp_data", + .mode = S_IRUGO | S_IWUSR, + }, + .size = PAGE_SIZE, + .read = reipl_fcp_scpdata_read, + .write = reipl_fcp_scpdata_write, +}; + DEFINE_IPL_ATTR_RW(reipl_fcp, wwpn, "0x%016llx\n", "%016llx\n", reipl_block_fcp->ipl_info.fcp.wwpn); DEFINE_IPL_ATTR_RW(reipl_fcp, lun, "0x%016llx\n", "%016llx\n", @@ -647,7 +762,6 @@ static struct attribute *reipl_fcp_attrs[] = { }; static struct attribute_group reipl_fcp_attr_group = { - .name = IPL_FCP_STR, .attrs = reipl_fcp_attrs, }; @@ -895,6 +1009,7 @@ static struct kobj_attribute reipl_type_attr = __ATTR(reipl_type, 0644, reipl_type_show, reipl_type_store); static struct kset *reipl_kset; +static struct kset *reipl_fcp_kset; static void get_ipl_string(char *dst, struct ipl_parameter_block *ipb, const enum ipl_method m) @@ -906,7 +1021,7 @@ static void get_ipl_string(char *dst, struct ipl_parameter_block *ipb, reipl_get_ascii_loadparm(loadparm, ipb); reipl_get_ascii_nss_name(nss_name, ipb); - reipl_get_ascii_vmparm(vmparm, ipb); + reipl_get_ascii_vmparm(vmparm, sizeof(vmparm), ipb); switch (m) { case REIPL_METHOD_CCW_VM: @@ -1076,23 +1191,44 @@ static int __init reipl_fcp_init(void) int rc; if (!diag308_set_works) { - if (ipl_info.type == IPL_TYPE_FCP) + if (ipl_info.type == IPL_TYPE_FCP) { make_attrs_ro(reipl_fcp_attrs); - else + sys_reipl_fcp_scp_data_attr.attr.mode = S_IRUGO; + } else return 0; } reipl_block_fcp = (void *) get_zeroed_page(GFP_KERNEL); if (!reipl_block_fcp) return -ENOMEM; - rc = sysfs_create_group(&reipl_kset->kobj, &reipl_fcp_attr_group); + + /* sysfs: create fcp kset for mixing attr group and bin attrs */ + reipl_fcp_kset = kset_create_and_add(IPL_FCP_STR, NULL, + &reipl_kset->kobj); + if (!reipl_kset) { + free_page((unsigned long) reipl_block_fcp); + return -ENOMEM; + } + + rc = sysfs_create_group(&reipl_fcp_kset->kobj, &reipl_fcp_attr_group); + if (rc) { + kset_unregister(reipl_fcp_kset); + free_page((unsigned long) reipl_block_fcp); + return rc; + } + + rc = sysfs_create_bin_file(&reipl_fcp_kset->kobj, + &sys_reipl_fcp_scp_data_attr); if (rc) { - free_page((unsigned long)reipl_block_fcp); + sysfs_remove_group(&reipl_fcp_kset->kobj, &reipl_fcp_attr_group); + kset_unregister(reipl_fcp_kset); + free_page((unsigned long) reipl_block_fcp); return rc; } - if (ipl_info.type == IPL_TYPE_FCP) { + + if (ipl_info.type == IPL_TYPE_FCP) memcpy(reipl_block_fcp, IPL_PARMBLOCK_START, PAGE_SIZE); - } else { + else { reipl_block_fcp->hdr.len = IPL_PARM_BLK_FCP_LEN; reipl_block_fcp->hdr.version = IPL_PARM_BLOCK_VERSION; reipl_block_fcp->hdr.blk0_len = IPL_PARM_BLK0_FCP_LEN; @@ -1459,10 +1595,9 @@ static void stop_run(struct shutdown_trigger *trigger) { if (strcmp(trigger->name, ON_PANIC_STR) == 0) disabled_wait((unsigned long) __builtin_return_address(0)); - else { - signal_processor(smp_processor_id(), sigp_stop); - for (;;); - } + while (signal_processor(smp_processor_id(), sigp_stop) == sigp_busy) + cpu_relax(); + for (;;); } static struct shutdown_action stop_action = {SHUTDOWN_ACTION_STOP_STR, diff --git a/arch/s390/kernel/mcount.S b/arch/s390/kernel/mcount.S index 2a0a5e97ba8c..dfe015d7398c 100644 --- a/arch/s390/kernel/mcount.S +++ b/arch/s390/kernel/mcount.S @@ -11,111 +11,27 @@ ftrace_stub: br %r14 -#ifdef CONFIG_64BIT - -#ifdef CONFIG_DYNAMIC_FTRACE - .globl _mcount _mcount: - br %r14 - - .globl ftrace_caller -ftrace_caller: - larl %r1,function_trace_stop - icm %r1,0xf,0(%r1) - bnzr %r14 - stmg %r2,%r5,32(%r15) - stg %r14,112(%r15) - lgr %r1,%r15 - aghi %r15,-160 - stg %r1,__SF_BACKCHAIN(%r15) - lgr %r2,%r14 - lg %r3,168(%r15) - larl %r14,ftrace_dyn_func - lg %r14,0(%r14) - basr %r14,%r14 -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - .globl ftrace_graph_caller -ftrace_graph_caller: - # This unconditional branch gets runtime patched. Change only if - # you know what you are doing. See ftrace_enable_graph_caller(). - j 0f - lg %r2,272(%r15) - lg %r3,168(%r15) - brasl %r14,prepare_ftrace_return - stg %r2,168(%r15) -0: -#endif - aghi %r15,160 - lmg %r2,%r5,32(%r15) - lg %r14,112(%r15) +#ifdef CONFIG_DYNAMIC_FTRACE br %r14 .data .globl ftrace_dyn_func ftrace_dyn_func: - .quad ftrace_stub + .long ftrace_stub .previous -#else /* CONFIG_DYNAMIC_FTRACE */ - - .globl _mcount -_mcount: - larl %r1,function_trace_stop - icm %r1,0xf,0(%r1) - bnzr %r14 - stmg %r2,%r5,32(%r15) - stg %r14,112(%r15) - lgr %r1,%r15 - aghi %r15,-160 - stg %r1,__SF_BACKCHAIN(%r15) - lgr %r2,%r14 - lg %r3,168(%r15) - larl %r14,ftrace_trace_function - lg %r14,0(%r14) - basr %r14,%r14 -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - lg %r2,272(%r15) - lg %r3,168(%r15) - brasl %r14,prepare_ftrace_return - stg %r2,168(%r15) -#endif - aghi %r15,160 - lmg %r2,%r5,32(%r15) - lg %r14,112(%r15) - br %r14 - -#endif /* CONFIG_DYNAMIC_FTRACE */ - -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - - .globl return_to_handler -return_to_handler: - stmg %r2,%r5,32(%r15) - lgr %r1,%r15 - aghi %r15,-160 - stg %r1,__SF_BACKCHAIN(%r15) - brasl %r14,ftrace_return_to_handler - aghi %r15,160 - lgr %r14,%r2 - lmg %r2,%r5,32(%r15) - br %r14 - -#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ - -#else /* CONFIG_64BIT */ - -#ifdef CONFIG_DYNAMIC_FTRACE - - .globl _mcount -_mcount: - br %r14 - .globl ftrace_caller ftrace_caller: +#endif stm %r2,%r5,16(%r15) bras %r1,2f +#ifdef CONFIG_DYNAMIC_FTRACE +0: .long ftrace_dyn_func +#else 0: .long ftrace_trace_function +#endif 1: .long function_trace_stop 2: l %r2,1b-0b(%r1) icm %r2,0xf,0(%r2) @@ -131,53 +47,13 @@ ftrace_caller: l %r14,0(%r14) basr %r14,%r14 #ifdef CONFIG_FUNCTION_GRAPH_TRACER +#ifdef CONFIG_DYNAMIC_FTRACE .globl ftrace_graph_caller ftrace_graph_caller: # This unconditional branch gets runtime patched. Change only if # you know what you are doing. See ftrace_enable_graph_caller(). j 1f - bras %r1,0f - .long prepare_ftrace_return -0: l %r2,152(%r15) - l %r4,0(%r1) - l %r3,100(%r15) - basr %r14,%r4 - st %r2,100(%r15) -1: #endif - ahi %r15,96 - l %r14,56(%r15) -3: lm %r2,%r5,16(%r15) - br %r14 - - .data - .globl ftrace_dyn_func -ftrace_dyn_func: - .long ftrace_stub - .previous - -#else /* CONFIG_DYNAMIC_FTRACE */ - - .globl _mcount -_mcount: - stm %r2,%r5,16(%r15) - bras %r1,2f -0: .long ftrace_trace_function -1: .long function_trace_stop -2: l %r2,1b-0b(%r1) - icm %r2,0xf,0(%r2) - jnz 3f - st %r14,56(%r15) - lr %r0,%r15 - ahi %r15,-96 - l %r3,100(%r15) - la %r2,0(%r14) - st %r0,__SF_BACKCHAIN(%r15) - la %r3,0(%r3) - l %r14,0b-0b(%r1) - l %r14,0(%r14) - basr %r14,%r14 -#ifdef CONFIG_FUNCTION_GRAPH_TRACER bras %r1,0f .long prepare_ftrace_return 0: l %r2,152(%r15) @@ -185,14 +61,13 @@ _mcount: l %r3,100(%r15) basr %r14,%r4 st %r2,100(%r15) +1: #endif ahi %r15,96 l %r14,56(%r15) 3: lm %r2,%r5,16(%r15) br %r14 -#endif /* CONFIG_DYNAMIC_FTRACE */ - #ifdef CONFIG_FUNCTION_GRAPH_TRACER .globl return_to_handler @@ -211,6 +86,4 @@ return_to_handler: lm %r2,%r5,16(%r15) br %r14 -#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ - -#endif /* CONFIG_64BIT */ +#endif diff --git a/arch/s390/kernel/mcount64.S b/arch/s390/kernel/mcount64.S new file mode 100644 index 000000000000..c37211c6092b --- /dev/null +++ b/arch/s390/kernel/mcount64.S @@ -0,0 +1,78 @@ +/* + * Copyright IBM Corp. 2008,2009 + * + * Author(s): Heiko Carstens <heiko.carstens@de.ibm.com>, + * + */ + +#include <asm/asm-offsets.h> + + .globl ftrace_stub +ftrace_stub: + br %r14 + + .globl _mcount +_mcount: +#ifdef CONFIG_DYNAMIC_FTRACE + br %r14 + + .data + .globl ftrace_dyn_func +ftrace_dyn_func: + .quad ftrace_stub + .previous + + .globl ftrace_caller +ftrace_caller: +#endif + larl %r1,function_trace_stop + icm %r1,0xf,0(%r1) + bnzr %r14 + stmg %r2,%r5,32(%r15) + stg %r14,112(%r15) + lgr %r1,%r15 + aghi %r15,-160 + stg %r1,__SF_BACKCHAIN(%r15) + lgr %r2,%r14 + lg %r3,168(%r15) +#ifdef CONFIG_DYNAMIC_FTRACE + larl %r14,ftrace_dyn_func +#else + larl %r14,ftrace_trace_function +#endif + lg %r14,0(%r14) + basr %r14,%r14 +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +#ifdef CONFIG_DYNAMIC_FTRACE + .globl ftrace_graph_caller +ftrace_graph_caller: + # This unconditional branch gets runtime patched. Change only if + # you know what you are doing. See ftrace_enable_graph_caller(). + j 0f +#endif + lg %r2,272(%r15) + lg %r3,168(%r15) + brasl %r14,prepare_ftrace_return + stg %r2,168(%r15) +0: +#endif + aghi %r15,160 + lmg %r2,%r5,32(%r15) + lg %r14,112(%r15) + br %r14 + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + + .globl return_to_handler +return_to_handler: + stmg %r2,%r5,32(%r15) + lgr %r1,%r15 + aghi %r15,-160 + stg %r1,__SF_BACKCHAIN(%r15) + brasl %r14,ftrace_return_to_handler + aghi %r15,160 + lgr %r14,%r2 + lmg %r2,%r5,32(%r15) + br %r14 + +#endif diff --git a/arch/s390/kernel/module.c b/arch/s390/kernel/module.c index ab2e3ed28abc..639380a0c45c 100644 --- a/arch/s390/kernel/module.c +++ b/arch/s390/kernel/module.c @@ -55,6 +55,8 @@ void *module_alloc(unsigned long size) /* Free memory returned from module_alloc */ void module_free(struct module *mod, void *module_region) { + vfree(mod->arch.syminfo); + mod->arch.syminfo = NULL; vfree(module_region); } @@ -402,6 +404,7 @@ int module_finalize(const Elf_Ehdr *hdr, struct module *me) { vfree(me->arch.syminfo); + me->arch.syminfo = NULL; return module_bug_finalize(hdr, sechdrs, me); } diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c index 5a43f27eec13..5417eb57271a 100644 --- a/arch/s390/kernel/process.c +++ b/arch/s390/kernel/process.c @@ -27,11 +27,11 @@ #include <linux/init.h> #include <linux/module.h> #include <linux/notifier.h> -#include <linux/utsname.h> #include <linux/tick.h> #include <linux/elfcore.h> #include <linux/kernel_stat.h> #include <linux/syscalls.h> +#include <linux/compat.h> #include <asm/compat.h> #include <asm/uaccess.h> #include <asm/pgtable.h> @@ -230,17 +230,11 @@ SYSCALL_DEFINE0(fork) return do_fork(SIGCHLD, regs->gprs[15], regs, 0, NULL, NULL); } -SYSCALL_DEFINE0(clone) +SYSCALL_DEFINE4(clone, unsigned long, newsp, unsigned long, clone_flags, + int __user *, parent_tidptr, int __user *, child_tidptr) { struct pt_regs *regs = task_pt_regs(current); - unsigned long clone_flags; - unsigned long newsp; - int __user *parent_tidptr, *child_tidptr; - clone_flags = regs->gprs[3]; - newsp = regs->orig_gpr2; - parent_tidptr = (int __user *) regs->gprs[4]; - child_tidptr = (int __user *) regs->gprs[5]; if (!newsp) newsp = regs->gprs[15]; return do_fork(clone_flags, newsp, regs, 0, @@ -274,30 +268,25 @@ asmlinkage void execve_tail(void) /* * sys_execve() executes a new program. */ -SYSCALL_DEFINE0(execve) +SYSCALL_DEFINE3(execve, char __user *, name, char __user * __user *, argv, + char __user * __user *, envp) { struct pt_regs *regs = task_pt_regs(current); char *filename; - unsigned long result; - int rc; + long rc; - filename = getname((char __user *) regs->orig_gpr2); - if (IS_ERR(filename)) { - result = PTR_ERR(filename); + filename = getname(name); + rc = PTR_ERR(filename); + if (IS_ERR(filename)) + return rc; + rc = do_execve(filename, argv, envp, regs); + if (rc) goto out; - } - rc = do_execve(filename, (char __user * __user *) regs->gprs[3], - (char __user * __user *) regs->gprs[4], regs); - if (rc) { - result = rc; - goto out_putname; - } execve_tail(); - result = regs->gprs[2]; -out_putname: - putname(filename); + rc = regs->gprs[2]; out: - return result; + putname(filename); + return rc; } /* diff --git a/arch/s390/kernel/processor.c b/arch/s390/kernel/processor.c index 802c8ab247f3..0729f36c2fe3 100644 --- a/arch/s390/kernel/processor.c +++ b/arch/s390/kernel/processor.c @@ -31,9 +31,9 @@ void __cpuinit print_cpu_info(void) static int show_cpuinfo(struct seq_file *m, void *v) { - static const char *hwcap_str[9] = { + static const char *hwcap_str[10] = { "esan3", "zarch", "stfle", "msa", "ldisp", "eimm", "dfp", - "edat", "etf3eh" + "edat", "etf3eh", "highgprs" }; struct _lowcore *lc; unsigned long n = (unsigned long) v - 1; @@ -48,7 +48,7 @@ static int show_cpuinfo(struct seq_file *m, void *v) num_online_cpus(), loops_per_jiffy/(500000/HZ), (loops_per_jiffy/(5000/HZ))%100); seq_puts(m, "features\t: "); - for (i = 0; i < 9; i++) + for (i = 0; i < 10; i++) if (hwcap_str[i] && (elf_hwcap & (1UL << i))) seq_printf(m, "%s ", hwcap_str[i]); seq_puts(m, "\n"); diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c index 43acd73105b7..653c6a178740 100644 --- a/arch/s390/kernel/ptrace.c +++ b/arch/s390/kernel/ptrace.c @@ -51,9 +51,13 @@ #include "compat_ptrace.h" #endif +#define CREATE_TRACE_POINTS +#include <trace/events/syscalls.h> + enum s390_regset { REGSET_GENERAL, REGSET_FP, + REGSET_GENERAL_EXTENDED, }; static void @@ -336,24 +340,10 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) int copied, ret; switch (request) { - case PTRACE_PEEKTEXT: - case PTRACE_PEEKDATA: - /* Remove high order bit from address (only for 31 bit). */ - addr &= PSW_ADDR_INSN; - /* read word at location addr. */ - return generic_ptrace_peekdata(child, addr, data); - case PTRACE_PEEKUSR: /* read the word at location addr in the USER area. */ return peek_user(child, addr, data); - case PTRACE_POKETEXT: - case PTRACE_POKEDATA: - /* Remove high order bit from address (only for 31 bit). */ - addr &= PSW_ADDR_INSN; - /* write the word at location addr. */ - return generic_ptrace_pokedata(child, addr, data); - case PTRACE_POKEUSR: /* write the word at location addr in the USER area */ return poke_user(child, addr, data); @@ -383,8 +373,11 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) copied += sizeof(unsigned long); } return 0; + default: + /* Removing high order bit from addr (only for 31 bit). */ + addr &= PSW_ADDR_INSN; + return ptrace_request(child, request, addr, data); } - return ptrace_request(child, request, addr, data); } #ifdef CONFIG_COMPAT @@ -661,8 +654,8 @@ asmlinkage long do_syscall_trace_enter(struct pt_regs *regs) ret = -1; } - if (unlikely(test_thread_flag(TIF_SYSCALL_FTRACE))) - ftrace_syscall_enter(regs); + if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT))) + trace_sys_enter(regs, regs->gprs[2]); if (unlikely(current->audit_context)) audit_syscall_entry(is_compat_task() ? @@ -679,8 +672,8 @@ asmlinkage void do_syscall_trace_exit(struct pt_regs *regs) audit_syscall_exit(AUDITSC_RESULT(regs->gprs[2]), regs->gprs[2]); - if (unlikely(test_thread_flag(TIF_SYSCALL_FTRACE))) - ftrace_syscall_exit(regs); + if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT))) + trace_sys_exit(regs, regs->gprs[2]); if (test_thread_flag(TIF_SYSCALL_TRACE)) tracehook_report_syscall_exit(regs, 0); @@ -887,6 +880,67 @@ static int s390_compat_regs_set(struct task_struct *target, return rc; } +static int s390_compat_regs_high_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + compat_ulong_t *gprs_high; + + gprs_high = (compat_ulong_t *) + &task_pt_regs(target)->gprs[pos / sizeof(compat_ulong_t)]; + if (kbuf) { + compat_ulong_t *k = kbuf; + while (count > 0) { + *k++ = *gprs_high; + gprs_high += 2; + count -= sizeof(*k); + } + } else { + compat_ulong_t __user *u = ubuf; + while (count > 0) { + if (__put_user(*gprs_high, u++)) + return -EFAULT; + gprs_high += 2; + count -= sizeof(*u); + } + } + return 0; +} + +static int s390_compat_regs_high_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + compat_ulong_t *gprs_high; + int rc = 0; + + gprs_high = (compat_ulong_t *) + &task_pt_regs(target)->gprs[pos / sizeof(compat_ulong_t)]; + if (kbuf) { + const compat_ulong_t *k = kbuf; + while (count > 0) { + *gprs_high = *k++; + *gprs_high += 2; + count -= sizeof(*k); + } + } else { + const compat_ulong_t __user *u = ubuf; + while (count > 0 && !rc) { + unsigned long word; + rc = __get_user(word, u++); + if (rc) + break; + *gprs_high = word; + *gprs_high += 2; + count -= sizeof(*u); + } + } + + return rc; +} + static const struct user_regset s390_compat_regsets[] = { [REGSET_GENERAL] = { .core_note_type = NT_PRSTATUS, @@ -904,6 +958,14 @@ static const struct user_regset s390_compat_regsets[] = { .get = s390_fpregs_get, .set = s390_fpregs_set, }, + [REGSET_GENERAL_EXTENDED] = { + .core_note_type = NT_PRXSTATUS, + .n = sizeof(s390_compat_regs_high) / sizeof(compat_long_t), + .size = sizeof(compat_long_t), + .align = sizeof(compat_long_t), + .get = s390_compat_regs_high_get, + .set = s390_compat_regs_high_set, + }, }; static const struct user_regset_view user_s390_compat_view = { diff --git a/arch/s390/kernel/s390_ext.c b/arch/s390/kernel/s390_ext.c index 0de305b598ce..59618bcd99b7 100644 --- a/arch/s390/kernel/s390_ext.c +++ b/arch/s390/kernel/s390_ext.c @@ -126,6 +126,8 @@ void __irq_entry do_extint(struct pt_regs *regs, unsigned short code) /* Serve timer interrupts first. */ clock_comparator_work(); kstat_cpu(smp_processor_id()).irqs[EXTERNAL_INTERRUPT]++; + if (code != 0x1004) + __get_cpu_var(s390_idle).nohz_delay = 1; index = ext_hash(code); for (p = ext_int_hash[index]; p; p = p->next) { if (likely(p->code == code)) diff --git a/arch/s390/kernel/sclp.S b/arch/s390/kernel/sclp.S index 20639dfe0c42..e27ca63076d1 100644 --- a/arch/s390/kernel/sclp.S +++ b/arch/s390/kernel/sclp.S @@ -24,8 +24,6 @@ LC_EXT_INT_CODE = 0x86 # addr of ext int code # R3 = external interruption parameter if R2=0 # -.section ".init.text","ax" - _sclp_wait_int: stm %r6,%r15,24(%r15) # save registers basr %r13,0 # get base register @@ -318,9 +316,8 @@ _sclp_print_early: .long _sclp_work_area .Lascebc: .long _ascebc -.previous -.section ".init.data","a" +.section .data,"aw",@progbits .balign 4096 _sclp_work_area: .fill 4096 diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index cbb897bc50bd..061479ff029f 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -156,15 +156,11 @@ __setup("condev=", condev_setup); static void __init set_preferred_console(void) { - if (MACHINE_IS_KVM) { + if (MACHINE_IS_KVM) add_preferred_console("hvc", 0, NULL); - s390_virtio_console_init(); - return; - } - - if (CONSOLE_IS_3215 || CONSOLE_IS_SCLP) + else if (CONSOLE_IS_3215 || CONSOLE_IS_SCLP) add_preferred_console("ttyS", 0, NULL); - if (CONSOLE_IS_3270) + else if (CONSOLE_IS_3270) add_preferred_console("tty3270", 0, NULL); } @@ -733,7 +729,7 @@ static void __init setup_hwcaps(void) if ((facility_list & (1UL << (31 - 22))) && (facility_list & (1UL << (31 - 30)))) - elf_hwcap |= 1UL << 8; + elf_hwcap |= HWCAP_S390_ETF3EH; /* * Check for additional facilities with store-facility-list-extended. @@ -752,11 +748,20 @@ static void __init setup_hwcaps(void) __stfle(&facility_list_extended, 1) > 0) { if ((facility_list_extended & (1ULL << (63 - 42))) && (facility_list_extended & (1ULL << (63 - 44)))) - elf_hwcap |= 1UL << 6; + elf_hwcap |= HWCAP_S390_DFP; } + /* + * Huge page support HWCAP_S390_HPAGE is bit 7. + */ if (MACHINE_HAS_HPAGE) - elf_hwcap |= 1UL << 7; + elf_hwcap |= HWCAP_S390_HPAGE; + + /* + * 64-bit register support for 31-bit processes + * HWCAP_S390_HIGH_GPRS is bit 9. + */ + elf_hwcap |= HWCAP_S390_HIGH_GPRS; switch (S390_lowcore.cpu_id.machine) { case 0x9672: diff --git a/arch/s390/kernel/signal.c b/arch/s390/kernel/signal.c index 062bd64e65fa..6b4fef877f9d 100644 --- a/arch/s390/kernel/signal.c +++ b/arch/s390/kernel/signal.c @@ -536,4 +536,6 @@ void do_notify_resume(struct pt_regs *regs) { clear_thread_flag(TIF_NOTIFY_RESUME); tracehook_notify_resume(regs); + if (current->replacement_session_keyring) + key_replace_session_keyring(); } diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index be2cae083406..93e52039321b 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -49,6 +49,7 @@ #include <asm/sclp.h> #include <asm/cputime.h> #include <asm/vdso.h> +#include <asm/cpu.h> #include "entry.h" static struct task_struct *current_set[NR_CPUS]; @@ -70,6 +71,22 @@ static DEFINE_PER_CPU(struct cpu, cpu_devices); static void smp_ext_bitcall(int, ec_bit_sig); +static int cpu_stopped(int cpu) +{ + __u32 status; + + switch (signal_processor_ps(&status, 0, cpu, sigp_sense)) { + case sigp_status_stored: + /* Check for stopped and check stop state */ + if (status & 0x50) + return 1; + break; + default: + break; + } + return 0; +} + void smp_send_stop(void) { int cpu, rc; @@ -86,7 +103,7 @@ void smp_send_stop(void) rc = signal_processor(cpu, sigp_stop); } while (rc == sigp_busy); - while (!smp_cpu_not_running(cpu)) + while (!cpu_stopped(cpu)) cpu_relax(); } } @@ -129,11 +146,11 @@ static void smp_ext_bitcall(int cpu, ec_bit_sig sig) udelay(10); } -void arch_send_call_function_ipi(cpumask_t mask) +void arch_send_call_function_ipi_mask(const struct cpumask *mask) { int cpu; - for_each_cpu_mask(cpu, mask) + for_each_cpu(cpu, mask) smp_ext_bitcall(cpu, ec_call_function); } @@ -269,19 +286,6 @@ static inline void smp_get_save_area(unsigned int cpu, unsigned int phy_cpu) { } #endif /* CONFIG_ZFCPDUMP */ -static int cpu_stopped(int cpu) -{ - __u32 status; - - /* Check for stopped state */ - if (signal_processor_ps(&status, 0, cpu, sigp_sense) == - sigp_status_stored) { - if (status & 0x40) - return 1; - } - return 0; -} - static int cpu_known(int cpu_id) { int cpu; @@ -300,7 +304,7 @@ static int smp_rescan_cpus_sigp(cpumask_t avail) logical_cpu = cpumask_first(&avail); if (logical_cpu >= nr_cpu_ids) return 0; - for (cpu_id = 0; cpu_id <= 65535; cpu_id++) { + for (cpu_id = 0; cpu_id <= MAX_CPU_ADDRESS; cpu_id++) { if (cpu_known(cpu_id)) continue; __cpu_logical_map[logical_cpu] = cpu_id; @@ -379,7 +383,7 @@ static void __init smp_detect_cpus(void) /* Use sigp detection algorithm if sclp doesn't work. */ if (sclp_get_cpu_info(info)) { smp_use_sigp_detection = 1; - for (cpu = 0; cpu <= 65535; cpu++) { + for (cpu = 0; cpu <= MAX_CPU_ADDRESS; cpu++) { if (cpu == boot_cpu_addr) continue; __cpu_logical_map[CPU_INIT_NO] = cpu; @@ -470,10 +474,8 @@ static int __cpuinit smp_alloc_lowcore(int cpu) { unsigned long async_stack, panic_stack; struct _lowcore *lowcore; - int lc_order; - lc_order = sizeof(long) == 8 ? 1 : 0; - lowcore = (void *) __get_free_pages(GFP_KERNEL | GFP_DMA, lc_order); + lowcore = (void *) __get_free_pages(GFP_KERNEL | GFP_DMA, LC_ORDER); if (!lowcore) return -ENOMEM; async_stack = __get_free_pages(GFP_KERNEL, ASYNC_ORDER); @@ -504,16 +506,14 @@ static int __cpuinit smp_alloc_lowcore(int cpu) out: free_page(panic_stack); free_pages(async_stack, ASYNC_ORDER); - free_pages((unsigned long) lowcore, lc_order); + free_pages((unsigned long) lowcore, LC_ORDER); return -ENOMEM; } static void smp_free_lowcore(int cpu) { struct _lowcore *lowcore; - int lc_order; - lc_order = sizeof(long) == 8 ? 1 : 0; lowcore = lowcore_ptr[cpu]; #ifndef CONFIG_64BIT if (MACHINE_HAS_IEEE) @@ -523,7 +523,7 @@ static void smp_free_lowcore(int cpu) #endif free_page(lowcore->panic_stack - PAGE_SIZE); free_pages(lowcore->async_stack - ASYNC_SIZE, ASYNC_ORDER); - free_pages((unsigned long) lowcore, lc_order); + free_pages((unsigned long) lowcore, LC_ORDER); lowcore_ptr[cpu] = NULL; } @@ -635,8 +635,10 @@ int __cpu_disable(void) void __cpu_die(unsigned int cpu) { /* Wait until target cpu is down */ - while (!smp_cpu_not_running(cpu)) + while (!cpu_stopped(cpu)) cpu_relax(); + while (signal_processor_p(0, cpu, sigp_set_prefix) == sigp_busy) + udelay(10); smp_free_lowcore(cpu); pr_info("Processor %d stopped\n", cpu); } @@ -644,8 +646,8 @@ void __cpu_die(unsigned int cpu) void cpu_die(void) { idle_task_exit(); - signal_processor(smp_processor_id(), sigp_stop); - BUG(); + while (signal_processor(smp_processor_id(), sigp_stop) == sigp_busy) + cpu_relax(); for (;;); } @@ -659,7 +661,6 @@ void __init smp_prepare_cpus(unsigned int max_cpus) unsigned long async_stack, panic_stack; struct _lowcore *lowcore; unsigned int cpu; - int lc_order; smp_detect_cpus(); @@ -669,8 +670,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus) print_cpu_info(); /* Reallocate current lowcore, but keep its contents. */ - lc_order = sizeof(long) == 8 ? 1 : 0; - lowcore = (void *) __get_free_pages(GFP_KERNEL | GFP_DMA, lc_order); + lowcore = (void *) __get_free_pages(GFP_KERNEL | GFP_DMA, LC_ORDER); panic_stack = __get_free_page(GFP_KERNEL); async_stack = __get_free_pages(GFP_KERNEL, ASYNC_ORDER); BUG_ON(!lowcore || !panic_stack || !async_stack); @@ -1042,42 +1042,6 @@ out: static SYSDEV_CLASS_ATTR(dispatching, 0644, dispatching_show, dispatching_store); -/* - * If the resume kernel runs on another cpu than the suspended kernel, - * we have to switch the cpu IDs in the logical map. - */ -void smp_switch_boot_cpu_in_resume(u32 resume_phys_cpu_id, - struct _lowcore *suspend_lowcore) -{ - int cpu, suspend_cpu_id, resume_cpu_id; - u32 suspend_phys_cpu_id; - - suspend_phys_cpu_id = __cpu_logical_map[suspend_lowcore->cpu_nr]; - suspend_cpu_id = suspend_lowcore->cpu_nr; - - for_each_present_cpu(cpu) { - if (__cpu_logical_map[cpu] == resume_phys_cpu_id) { - resume_cpu_id = cpu; - goto found; - } - } - panic("Could not find resume cpu in logical map.\n"); - -found: - printk("Resume cpu ID: %i/%i\n", resume_phys_cpu_id, resume_cpu_id); - printk("Suspend cpu ID: %i/%i\n", suspend_phys_cpu_id, suspend_cpu_id); - - __cpu_logical_map[resume_cpu_id] = suspend_phys_cpu_id; - __cpu_logical_map[suspend_cpu_id] = resume_phys_cpu_id; - - lowcore_ptr[suspend_cpu_id]->cpu_addr = resume_phys_cpu_id; -} - -u32 smp_get_phys_cpu_id(void) -{ - return __cpu_logical_map[smp_processor_id()]; -} - static int __init topology_init(void) { int cpu; diff --git a/arch/s390/kernel/suspend.c b/arch/s390/kernel/suspend.c new file mode 100644 index 000000000000..cf9e5c6d5527 --- /dev/null +++ b/arch/s390/kernel/suspend.c @@ -0,0 +1,63 @@ +/* + * Suspend support specific for s390. + * + * Copyright IBM Corp. 2009 + * + * Author(s): Hans-Joachim Picht <hans@linux.vnet.ibm.com> + */ + +#include <linux/pfn.h> +#include <asm/system.h> + +/* + * References to section boundaries + */ +extern const void __nosave_begin, __nosave_end; + +int pfn_is_nosave(unsigned long pfn) +{ + unsigned long nosave_begin_pfn = PFN_DOWN(__pa(&__nosave_begin)); + unsigned long nosave_end_pfn = PFN_DOWN(__pa(&__nosave_end)); + + /* Always save lowcore pages (LC protection might be enabled). */ + if (pfn <= LC_PAGES) + return 0; + if (pfn >= nosave_begin_pfn && pfn < nosave_end_pfn) + return 1; + /* Skip memory holes and read-only pages (NSS, DCSS, ...). */ + if (tprot(PFN_PHYS(pfn))) + return 1; + return 0; +} + +void save_processor_state(void) +{ + /* swsusp_arch_suspend() actually saves all cpu register contents. + * Machine checks must be disabled since swsusp_arch_suspend() stores + * register contents to their lowcore save areas. That's the same + * place where register contents on machine checks would be saved. + * To avoid register corruption disable machine checks. + * We must also disable machine checks in the new psw mask for + * program checks, since swsusp_arch_suspend() may generate program + * checks. Disabling machine checks for all other new psw masks is + * just paranoia. + */ + local_mcck_disable(); + /* Disable lowcore protection */ + __ctl_clear_bit(0,28); + S390_lowcore.external_new_psw.mask &= ~PSW_MASK_MCHECK; + S390_lowcore.svc_new_psw.mask &= ~PSW_MASK_MCHECK; + S390_lowcore.io_new_psw.mask &= ~PSW_MASK_MCHECK; + S390_lowcore.program_new_psw.mask &= ~PSW_MASK_MCHECK; +} + +void restore_processor_state(void) +{ + S390_lowcore.external_new_psw.mask |= PSW_MASK_MCHECK; + S390_lowcore.svc_new_psw.mask |= PSW_MASK_MCHECK; + S390_lowcore.io_new_psw.mask |= PSW_MASK_MCHECK; + S390_lowcore.program_new_psw.mask |= PSW_MASK_MCHECK; + /* Enable lowcore protection */ + __ctl_set_bit(0,28); + local_mcck_enable(); +} diff --git a/arch/s390/kernel/swsusp_asm64.S b/arch/s390/kernel/swsusp_asm64.S new file mode 100644 index 000000000000..0c26cc1898ec --- /dev/null +++ b/arch/s390/kernel/swsusp_asm64.S @@ -0,0 +1,278 @@ +/* + * S390 64-bit swsusp implementation + * + * Copyright IBM Corp. 2009 + * + * Author(s): Hans-Joachim Picht <hans@linux.vnet.ibm.com> + * Michael Holzheu <holzheu@linux.vnet.ibm.com> + */ + +#include <asm/page.h> +#include <asm/ptrace.h> +#include <asm/thread_info.h> +#include <asm/asm-offsets.h> + +/* + * Save register context in absolute 0 lowcore and call swsusp_save() to + * create in-memory kernel image. The context is saved in the designated + * "store status" memory locations (see POP). + * We return from this function twice. The first time during the suspend to + * disk process. The second time via the swsusp_arch_resume() function + * (see below) in the resume process. + * This function runs with disabled interrupts. + */ + .section .text + .align 4 + .globl swsusp_arch_suspend +swsusp_arch_suspend: + stmg %r6,%r15,__SF_GPRS(%r15) + lgr %r1,%r15 + aghi %r15,-STACK_FRAME_OVERHEAD + stg %r1,__SF_BACKCHAIN(%r15) + + /* Deactivate DAT */ + stnsm __SF_EMPTY(%r15),0xfb + + /* Store prefix register on stack */ + stpx __SF_EMPTY(%r15) + + /* Save prefix register contents for lowcore */ + llgf %r4,__SF_EMPTY(%r15) + + /* Get pointer to save area */ + lghi %r1,0x1000 + + /* Save CPU address */ + stap __LC_CPU_ADDRESS(%r0) + + /* Store registers */ + mvc 0x318(4,%r1),__SF_EMPTY(%r15) /* move prefix to lowcore */ + stfpc 0x31c(%r1) /* store fpu control */ + std 0,0x200(%r1) /* store f0 */ + std 1,0x208(%r1) /* store f1 */ + std 2,0x210(%r1) /* store f2 */ + std 3,0x218(%r1) /* store f3 */ + std 4,0x220(%r1) /* store f4 */ + std 5,0x228(%r1) /* store f5 */ + std 6,0x230(%r1) /* store f6 */ + std 7,0x238(%r1) /* store f7 */ + std 8,0x240(%r1) /* store f8 */ + std 9,0x248(%r1) /* store f9 */ + std 10,0x250(%r1) /* store f10 */ + std 11,0x258(%r1) /* store f11 */ + std 12,0x260(%r1) /* store f12 */ + std 13,0x268(%r1) /* store f13 */ + std 14,0x270(%r1) /* store f14 */ + std 15,0x278(%r1) /* store f15 */ + stam %a0,%a15,0x340(%r1) /* store access registers */ + stctg %c0,%c15,0x380(%r1) /* store control registers */ + stmg %r0,%r15,0x280(%r1) /* store general registers */ + + stpt 0x328(%r1) /* store timer */ + stck __SF_EMPTY(%r15) /* store clock */ + stckc 0x330(%r1) /* store clock comparator */ + + /* Update cputime accounting before going to sleep */ + lg %r0,__LC_LAST_UPDATE_TIMER + slg %r0,0x328(%r1) + alg %r0,__LC_SYSTEM_TIMER + stg %r0,__LC_SYSTEM_TIMER + mvc __LC_LAST_UPDATE_TIMER(8),0x328(%r1) + lg %r0,__LC_LAST_UPDATE_CLOCK + slg %r0,__SF_EMPTY(%r15) + alg %r0,__LC_STEAL_TIMER + stg %r0,__LC_STEAL_TIMER + mvc __LC_LAST_UPDATE_CLOCK(8),__SF_EMPTY(%r15) + + /* Activate DAT */ + stosm __SF_EMPTY(%r15),0x04 + + /* Set prefix page to zero */ + xc __SF_EMPTY(4,%r15),__SF_EMPTY(%r15) + spx __SF_EMPTY(%r15) + + lghi %r2,0 + lghi %r3,2*PAGE_SIZE + lghi %r5,2*PAGE_SIZE +1: mvcle %r2,%r4,0 + jo 1b + + /* Save image */ + brasl %r14,swsusp_save + + /* Restore prefix register and return */ + lghi %r1,0x1000 + spx 0x318(%r1) + lmg %r6,%r15,STACK_FRAME_OVERHEAD + __SF_GPRS(%r15) + lghi %r2,0 + br %r14 + +/* + * Restore saved memory image to correct place and restore register context. + * Then we return to the function that called swsusp_arch_suspend(). + * swsusp_arch_resume() runs with disabled interrupts. + */ + .globl swsusp_arch_resume +swsusp_arch_resume: + stmg %r6,%r15,__SF_GPRS(%r15) + lgr %r1,%r15 + aghi %r15,-STACK_FRAME_OVERHEAD + stg %r1,__SF_BACKCHAIN(%r15) + + /* Make all free pages stable */ + lghi %r2,1 + brasl %r14,arch_set_page_states + + /* Deactivate DAT */ + stnsm __SF_EMPTY(%r15),0xfb + + /* Set prefix page to zero */ + xc __SF_EMPTY(4,%r15),__SF_EMPTY(%r15) + spx __SF_EMPTY(%r15) + + /* Restore saved image */ + larl %r1,restore_pblist + lg %r1,0(%r1) + ltgr %r1,%r1 + jz 2f +0: + lg %r2,8(%r1) + lg %r4,0(%r1) + lghi %r3,PAGE_SIZE + lghi %r5,PAGE_SIZE +1: + mvcle %r2,%r4,0 + jo 1b + lg %r1,16(%r1) + ltgr %r1,%r1 + jnz 0b +2: + ptlb /* flush tlb */ + + /* Reset System */ + larl %r1,restart_entry + larl %r2,.Lrestart_diag308_psw + og %r1,0(%r2) + stg %r1,0(%r0) + larl %r1,.Lnew_pgm_check_psw + epsw %r2,%r3 + stm %r2,%r3,0(%r1) + mvc __LC_PGM_NEW_PSW(16,%r0),0(%r1) + lghi %r0,0 + diag %r0,%r0,0x308 +restart_entry: + lhi %r1,1 + sigp %r1,%r0,0x12 + sam64 + larl %r1,.Lnew_pgm_check_psw + lpswe 0(%r1) +pgm_check_entry: + + /* Switch to original suspend CPU */ + larl %r1,.Lresume_cpu /* Resume CPU address: r2 */ + stap 0(%r1) + llgh %r2,0(%r1) + llgh %r1,__LC_CPU_ADDRESS(%r0) /* Suspend CPU address: r1 */ + cgr %r1,%r2 + je restore_registers /* r1 = r2 -> nothing to do */ + larl %r4,.Lrestart_suspend_psw /* Set new restart PSW */ + mvc __LC_RESTART_PSW(16,%r0),0(%r4) +3: + sigp %r9,%r1,__SIGP_INITIAL_CPU_RESET + brc 8,4f /* accepted */ + brc 2,3b /* busy, try again */ + + /* Suspend CPU not available -> panic */ + larl %r15,init_thread_union + ahi %r15,1<<(PAGE_SHIFT+THREAD_ORDER) + larl %r2,.Lpanic_string + larl %r3,_sclp_print_early + lghi %r1,0 + sam31 + sigp %r1,%r0,0x12 + basr %r14,%r3 + larl %r3,.Ldisabled_wait_31 + lpsw 0(%r3) +4: + /* Switch to suspend CPU */ + sigp %r9,%r1,__SIGP_RESTART /* start suspend CPU */ + brc 2,4b /* busy, try again */ +5: + sigp %r9,%r2,__SIGP_STOP /* stop resume (current) CPU */ + brc 2,5b /* busy, try again */ +6: j 6b + +restart_suspend: + larl %r1,.Lresume_cpu + llgh %r2,0(%r1) +7: + sigp %r9,%r2,__SIGP_SENSE /* Wait for resume CPU */ + brc 8,7b /* accepted, status 0, still running */ + brc 2,7b /* busy, try again */ + tmll %r9,0x40 /* Test if resume CPU is stopped */ + jz 7b + +restore_registers: + /* Restore registers */ + lghi %r13,0x1000 /* %r1 = pointer to save area */ + + /* Ignore time spent in suspended state. */ + llgf %r1,0x318(%r13) + stck __LC_LAST_UPDATE_CLOCK(%r1) + spt 0x328(%r13) /* reprogram timer */ + //sckc 0x330(%r13) /* set clock comparator */ + + lctlg %c0,%c15,0x380(%r13) /* load control registers */ + lam %a0,%a15,0x340(%r13) /* load access registers */ + + lfpc 0x31c(%r13) /* load fpu control */ + ld 0,0x200(%r13) /* load f0 */ + ld 1,0x208(%r13) /* load f1 */ + ld 2,0x210(%r13) /* load f2 */ + ld 3,0x218(%r13) /* load f3 */ + ld 4,0x220(%r13) /* load f4 */ + ld 5,0x228(%r13) /* load f5 */ + ld 6,0x230(%r13) /* load f6 */ + ld 7,0x238(%r13) /* load f7 */ + ld 8,0x240(%r13) /* load f8 */ + ld 9,0x248(%r13) /* load f9 */ + ld 10,0x250(%r13) /* load f10 */ + ld 11,0x258(%r13) /* load f11 */ + ld 12,0x260(%r13) /* load f12 */ + ld 13,0x268(%r13) /* load f13 */ + ld 14,0x270(%r13) /* load f14 */ + ld 15,0x278(%r13) /* load f15 */ + + /* Load old stack */ + lg %r15,0x2f8(%r13) + + /* Restore prefix register */ + spx 0x318(%r13) + + /* Activate DAT */ + stosm __SF_EMPTY(%r15),0x04 + + /* Make all free pages unstable */ + lghi %r2,0 + brasl %r14,arch_set_page_states + + /* Return 0 */ + lmg %r6,%r15,STACK_FRAME_OVERHEAD + __SF_GPRS(%r15) + lghi %r2,0 + br %r14 + + .section .data.nosave,"aw",@progbits + .align 8 +.Ldisabled_wait_31: + .long 0x000a0000,0x00000000 +.Lpanic_string: + .asciz "Resume not possible because suspend CPU is no longer available" + .align 8 +.Lrestart_diag308_psw: + .long 0x00080000,0x80000000 +.Lrestart_suspend_psw: + .quad 0x0000000180000000,restart_suspend +.Lnew_pgm_check_psw: + .quad 0,pgm_check_entry +.Lresume_cpu: + .byte 0,0 diff --git a/arch/s390/kernel/sys_s390.c b/arch/s390/kernel/sys_s390.c index c7ae4b17e0e3..e9d94f61d500 100644 --- a/arch/s390/kernel/sys_s390.c +++ b/arch/s390/kernel/sys_s390.c @@ -29,7 +29,6 @@ #include <linux/personality.h> #include <linux/unistd.h> #include <linux/ipc.h> -#include <linux/syscalls.h> #include <asm/uaccess.h> #include "entry.h" diff --git a/arch/s390/kernel/syscalls.S b/arch/s390/kernel/syscalls.S index ad1acd200385..30eca070d426 100644 --- a/arch/s390/kernel/syscalls.S +++ b/arch/s390/kernel/syscalls.S @@ -19,7 +19,7 @@ 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) +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) @@ -128,7 +128,7 @@ SYSCALL(sys_sysinfo,sys_sysinfo,compat_sys_sysinfo_wrapper) SYSCALL(sys_ipc,sys_ipc,sys32_ipc_wrapper) SYSCALL(sys_fsync,sys_fsync,sys32_fsync_wrapper) SYSCALL(sys_sigreturn,sys_sigreturn,sys32_sigreturn) -SYSCALL(sys_clone,sys_clone,sys32_clone) /* 120 */ +SYSCALL(sys_clone,sys_clone,sys_clone_wrapper) /* 120 */ SYSCALL(sys_setdomainname,sys_setdomainname,sys32_setdomainname_wrapper) SYSCALL(sys_newuname,sys_s390_newuname,sys32_newuname_wrapper) NI_SYSCALL /* modify_ldt for i386 */ @@ -136,8 +136,8 @@ SYSCALL(sys_adjtimex,sys_adjtimex,compat_sys_adjtimex_wrapper) SYSCALL(sys_mprotect,sys_mprotect,sys32_mprotect_wrapper) /* 125 */ SYSCALL(sys_sigprocmask,sys_sigprocmask,compat_sys_sigprocmask_wrapper) NI_SYSCALL /* old "create module" */ -SYSCALL(sys_init_module,sys_init_module,sys32_init_module_wrapper) -SYSCALL(sys_delete_module,sys_delete_module,sys32_delete_module_wrapper) +SYSCALL(sys_init_module,sys_init_module,sys_init_module_wrapper) +SYSCALL(sys_delete_module,sys_delete_module,sys_delete_module_wrapper) NI_SYSCALL /* 130: old get_kernel_syms */ SYSCALL(sys_quotactl,sys_quotactl,sys32_quotactl_wrapper) SYSCALL(sys_getpgid,sys_getpgid,sys32_getpgid_wrapper) @@ -339,4 +339,4 @@ 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_counter_open,sys_perf_counter_open,sys_perf_counter_open_wrapper) +SYSCALL(sys_perf_event_open,sys_perf_event_open,sys_perf_event_open_wrapper) diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c index d4c8e9c47c81..68e1ecf5ebab 100644 --- a/arch/s390/kernel/time.c +++ b/arch/s390/kernel/time.c @@ -60,6 +60,7 @@ #define TICK_SIZE tick u64 sched_clock_base_cc = -1; /* Force to data section. */ +EXPORT_SYMBOL_GPL(sched_clock_base_cc); static DEFINE_PER_CPU(struct clock_event_device, comparators); @@ -68,7 +69,7 @@ static DEFINE_PER_CPU(struct clock_event_device, comparators); */ unsigned long long notrace sched_clock(void) { - return ((get_clock_xt() - sched_clock_base_cc) * 125) >> 9; + return (get_clock_monotonic() * 125) >> 9; } /* @@ -90,6 +91,7 @@ void tod_to_timeval(__u64 todval, struct timespec *xtime) todval -= (sec * 1000000) << 12; xtime->tv_nsec = ((todval * 1000) >> 12); } +EXPORT_SYMBOL(tod_to_timeval); void clock_comparator_work(void) { @@ -182,12 +184,14 @@ static void timing_alert_interrupt(__u16 code) static void etr_reset(void); static void stp_reset(void); -unsigned long read_persistent_clock(void) +void read_persistent_clock(struct timespec *ts) { - struct timespec ts; + tod_to_timeval(get_clock() - TOD_UNIX_EPOCH, ts); +} - tod_to_timeval(get_clock() - TOD_UNIX_EPOCH, &ts); - return ts.tv_sec; +void read_boot_clock(struct timespec *ts) +{ + tod_to_timeval(sched_clock_base_cc - TOD_UNIX_EPOCH, ts); } static cycle_t read_tod_clock(struct clocksource *cs) @@ -205,8 +209,13 @@ static struct clocksource clocksource_tod = { .flags = CLOCK_SOURCE_IS_CONTINUOUS, }; +struct clocksource * __init clocksource_default_clock(void) +{ + return &clocksource_tod; +} -void update_vsyscall(struct timespec *wall_time, struct clocksource *clock) +void update_vsyscall(struct timespec *wall_time, struct clocksource *clock, + u32 mult) { if (clock != &clocksource_tod) return; @@ -242,10 +251,6 @@ void update_vsyscall_tz(void) */ void __init time_init(void) { - struct timespec ts; - unsigned long flags; - cycle_t now; - /* Reset time synchronization interfaces. */ etr_reset(); stp_reset(); @@ -261,26 +266,6 @@ void __init time_init(void) if (clocksource_register(&clocksource_tod) != 0) panic("Could not register TOD clock source"); - /* - * The TOD clock is an accurate clock. The xtime should be - * initialized in a way that the difference between TOD and - * xtime is reasonably small. Too bad that timekeeping_init - * sets xtime.tv_nsec to zero. In addition the clock source - * change from the jiffies clock source to the TOD clock - * source add another error of up to 1/HZ second. The same - * function sets wall_to_monotonic to a value that is too - * small for /proc/uptime to be accurate. - * Reset xtime and wall_to_monotonic to sane values. - */ - write_seqlock_irqsave(&xtime_lock, flags); - now = get_clock(); - tod_to_timeval(now - TOD_UNIX_EPOCH, &xtime); - clocksource_tod.cycle_last = now; - clocksource_tod.raw_time = xtime; - tod_to_timeval(sched_clock_base_cc - TOD_UNIX_EPOCH, &ts); - set_normalized_timespec(&wall_to_monotonic, -ts.tv_sec, -ts.tv_nsec); - write_sequnlock_irqrestore(&xtime_lock, flags); - /* Enable TOD clock interrupts on the boot cpu. */ init_cpu_timer(); diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c index 45e1708b70fd..adfb32aa6d59 100644 --- a/arch/s390/kernel/vdso.c +++ b/arch/s390/kernel/vdso.c @@ -75,7 +75,7 @@ __setup("vdso=", vdso_setup); static union { struct vdso_data data; u8 page[PAGE_SIZE]; -} vdso_data_store __attribute__((__section__(".data.page_aligned"))); +} vdso_data_store __page_aligned_data; struct vdso_data *vdso_data = &vdso_data_store.data; /* @@ -247,6 +247,13 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) } /* + * Put vDSO base into mm struct. We need to do this before calling + * install_special_mapping or the perf counter mmap tracking code + * will fail to recognise it as a vDSO (since arch_vma_name fails). + */ + current->mm->context.vdso_base = vdso_base; + + /* * our vma flags don't have VM_WRITE so by default, the process * isn't allowed to write those pages. * gdb can break that with ptrace interface, and thus trigger COW @@ -267,14 +274,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) VM_ALWAYSDUMP, vdso_pagelist); if (rc) - goto out_up; - - /* Put vDSO base into mm struct */ - current->mm->context.vdso_base = vdso_base; - - up_write(&mm->mmap_sem); - return 0; - + current->mm->context.vdso_base = 0; out_up: up_write(&mm->mmap_sem); return rc; diff --git a/arch/s390/kernel/vdso32/Makefile b/arch/s390/kernel/vdso32/Makefile index ca78ad60ba24..d13e8755a8cc 100644 --- a/arch/s390/kernel/vdso32/Makefile +++ b/arch/s390/kernel/vdso32/Makefile @@ -13,7 +13,7 @@ KBUILD_AFLAGS_31 += -m31 -s KBUILD_CFLAGS_31 := $(filter-out -m64,$(KBUILD_CFLAGS)) KBUILD_CFLAGS_31 += -m31 -fPIC -shared -fno-common -fno-builtin KBUILD_CFLAGS_31 += -nostdlib -Wl,-soname=linux-vdso32.so.1 \ - $(call ld-option, -Wl$(comma)--hash-style=sysv) + $(call cc-ldoption, -Wl$(comma)--hash-style=sysv) $(targets:%=$(obj)/%.dbg): KBUILD_CFLAGS = $(KBUILD_CFLAGS_31) $(targets:%=$(obj)/%.dbg): KBUILD_AFLAGS = $(KBUILD_AFLAGS_31) diff --git a/arch/s390/kernel/vdso32/vdso32_wrapper.S b/arch/s390/kernel/vdso32/vdso32_wrapper.S index 61639a89e70b..ae42f8ce350b 100644 --- a/arch/s390/kernel/vdso32/vdso32_wrapper.S +++ b/arch/s390/kernel/vdso32/vdso32_wrapper.S @@ -1,7 +1,8 @@ #include <linux/init.h> +#include <linux/linkage.h> #include <asm/page.h> - .section ".data.page_aligned" + __PAGE_ALIGNED_DATA .globl vdso32_start, vdso32_end .balign PAGE_SIZE diff --git a/arch/s390/kernel/vdso64/Makefile b/arch/s390/kernel/vdso64/Makefile index 6fc8e829258c..449352dda9cd 100644 --- a/arch/s390/kernel/vdso64/Makefile +++ b/arch/s390/kernel/vdso64/Makefile @@ -13,7 +13,7 @@ KBUILD_AFLAGS_64 += -m64 -s KBUILD_CFLAGS_64 := $(filter-out -m64,$(KBUILD_CFLAGS)) KBUILD_CFLAGS_64 += -m64 -fPIC -shared -fno-common -fno-builtin KBUILD_CFLAGS_64 += -nostdlib -Wl,-soname=linux-vdso64.so.1 \ - $(call ld-option, -Wl$(comma)--hash-style=sysv) + $(call cc-ldoption, -Wl$(comma)--hash-style=sysv) $(targets:%=$(obj)/%.dbg): KBUILD_CFLAGS = $(KBUILD_CFLAGS_64) $(targets:%=$(obj)/%.dbg): KBUILD_AFLAGS = $(KBUILD_AFLAGS_64) diff --git a/arch/s390/kernel/vdso64/vdso64_wrapper.S b/arch/s390/kernel/vdso64/vdso64_wrapper.S index d8e2ac14d564..c245842b516f 100644 --- a/arch/s390/kernel/vdso64/vdso64_wrapper.S +++ b/arch/s390/kernel/vdso64/vdso64_wrapper.S @@ -1,7 +1,8 @@ #include <linux/init.h> +#include <linux/linkage.h> #include <asm/page.h> - .section ".data.page_aligned" + __PAGE_ALIGNED_DATA .globl vdso64_start, vdso64_end .balign PAGE_SIZE diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S index a53db23ee092..a68ac10213b2 100644 --- a/arch/s390/kernel/vmlinux.lds.S +++ b/arch/s390/kernel/vmlinux.lds.S @@ -51,56 +51,20 @@ SECTIONS . = ALIGN(PAGE_SIZE); _eshared = .; /* End of shareable data */ + _sdata = .; /* Start of data section */ - . = ALIGN(16); /* Exception table */ - __ex_table : { - __start___ex_table = .; - *(__ex_table) - __stop___ex_table = .; - } :data + EXCEPTION_TABLE(16) :data - .data : { /* Data */ - DATA_DATA - CONSTRUCTORS - } - - . = ALIGN(PAGE_SIZE); - .data_nosave : { - __nosave_begin = .; - *(.data.nosave) - } - . = ALIGN(PAGE_SIZE); - __nosave_end = .; - - . = ALIGN(PAGE_SIZE); - .data.page_aligned : { - *(.data.idt) - } + RW_DATA_SECTION(0x100, PAGE_SIZE, THREAD_SIZE) - . = ALIGN(0x100); - .data.cacheline_aligned : { - *(.data.cacheline_aligned) - } - - . = ALIGN(0x100); - .data.read_mostly : { - *(.data.read_mostly) - } _edata = .; /* End of data section */ - . = ALIGN(THREAD_SIZE); /* init_task */ - .data.init_task : { - *(.data.init_task) - } - /* will be freed after init */ . = ALIGN(PAGE_SIZE); /* Init code and data */ __init_begin = .; - .init.text : { - _sinittext = .; - INIT_TEXT - _einittext = .; - } + + INIT_TEXT_SECTION(PAGE_SIZE) + /* * .exit.text is discarded at runtime, not link time, * to deal with references from __bug_table @@ -111,59 +75,20 @@ SECTIONS /* early.c uses stsi, which requires page aligned data. */ . = ALIGN(PAGE_SIZE); - .init.data : { - INIT_DATA - } - . = ALIGN(0x100); - .init.setup : { - __setup_start = .; - *(.init.setup) - __setup_end = .; - } - .initcall.init : { - __initcall_start = .; - INITCALLS - __initcall_end = .; - } - - .con_initcall.init : { - __con_initcall_start = .; - *(.con_initcall.init) - __con_initcall_end = .; - } - SECURITY_INIT - -#ifdef CONFIG_BLK_DEV_INITRD - . = ALIGN(0x100); - .init.ramfs : { - __initramfs_start = .; - *(.init.ramfs) - . = ALIGN(2); - __initramfs_end = .; - } -#endif + INIT_DATA_SECTION(0x100) PERCPU(PAGE_SIZE) . = ALIGN(PAGE_SIZE); __init_end = .; /* freed after init ends here */ - /* BSS */ - .bss : { - __bss_start = .; - *(.bss) - . = ALIGN(2); - __bss_stop = .; - } + BSS_SECTION(0, 2, 0) _end = . ; - /* Sections to be discarded */ - /DISCARD/ : { - EXIT_DATA - *(.exitcall.exit) - } - /* Debugging sections. */ STABS_DEBUG DWARF_DEBUG + + /* Sections to be discarded */ + DISCARDS } diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c index c41bb0d416e1..b59a812a010e 100644 --- a/arch/s390/kernel/vtime.c +++ b/arch/s390/kernel/vtime.c @@ -167,6 +167,8 @@ void vtime_stop_cpu(void) /* Wait for external, I/O or machine check interrupt. */ psw.mask = psw_kernel_bits | PSW_MASK_WAIT | PSW_MASK_IO | PSW_MASK_EXT; + idle->nohz_delay = 0; + /* Check if the CPU timer needs to be reprogrammed. */ if (vq->do_spt) { __u64 vmax = VTIMER_MAX_SLICE; |