diff options
Diffstat (limited to 'arch/x86')
59 files changed, 1949 insertions, 2170 deletions
diff --git a/arch/x86/.gitignore b/arch/x86/.gitignore index 028079065af..7cab8c08e6d 100644 --- a/arch/x86/.gitignore +++ b/arch/x86/.gitignore @@ -1,3 +1,4 @@ boot/compressed/vmlinux tools/test_get_len +tools/insn_sanity diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 6c14ecd851d..864cc6e6ac8 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -125,16 +125,6 @@ config HAVE_LATENCYTOP_SUPPORT config MMU def_bool y -config ZONE_DMA - bool "DMA memory allocation support" if EXPERT - default y - help - DMA memory allocation support allows devices with less than 32-bit - addressing to allocate within the first 16MB of address space. - Disable if no such devices will be used. - - If unsure, say Y. - config SBUS bool @@ -255,6 +245,16 @@ source "kernel/Kconfig.freezer" menu "Processor type and features" +config ZONE_DMA + bool "DMA memory allocation support" if EXPERT + default y + help + DMA memory allocation support allows devices with less than 32-bit + addressing to allocate within the first 16MB of address space. + Disable if no such devices will be used. + + If unsure, say Y. + source "kernel/time/Kconfig" config SMP diff --git a/arch/x86/Makefile b/arch/x86/Makefile index b02e509072a..209ba129459 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -118,6 +118,12 @@ KBUILD_CFLAGS += $(mflags-y) KBUILD_AFLAGS += $(mflags-y) ### +# Syscall table generation + +archheaders: + $(Q)$(MAKE) $(build)=arch/x86/syscalls all + +### # Kernel objects head-y := arch/x86/kernel/head_$(BITS).o diff --git a/arch/x86/ia32/Makefile b/arch/x86/ia32/Makefile index 52d0ccfcf6e..455646e0e53 100644 --- a/arch/x86/ia32/Makefile +++ b/arch/x86/ia32/Makefile @@ -3,6 +3,7 @@ # obj-$(CONFIG_IA32_EMULATION) := ia32entry.o sys_ia32.o ia32_signal.o +obj-$(CONFIG_IA32_EMULATION) += nosyscall.o syscall_ia32.o sysv-$(CONFIG_SYSVIPC) := ipc32.o obj-$(CONFIG_IA32_EMULATION) += $(sysv-y) diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S index 3e274564f6b..e3e734005e1 100644 --- a/arch/x86/ia32/ia32entry.S +++ b/arch/x86/ia32/ia32entry.S @@ -14,6 +14,7 @@ #include <asm/segment.h> #include <asm/irqflags.h> #include <linux/linkage.h> +#include <linux/err.h> /* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */ #include <linux/elf-em.h> @@ -27,8 +28,6 @@ .section .entry.text, "ax" -#define IA32_NR_syscalls ((ia32_syscall_end - ia32_sys_call_table)/8) - .macro IA32_ARG_FIXUP noebp=0 movl %edi,%r8d .if \noebp @@ -191,7 +190,7 @@ sysexit_from_sys_call: movl %ebx,%edx /* 3rd arg: 1st syscall arg */ movl %eax,%esi /* 2nd arg: syscall number */ movl $AUDIT_ARCH_I386,%edi /* 1st arg: audit arch */ - call audit_syscall_entry + call __audit_syscall_entry movl RAX-ARGOFFSET(%rsp),%eax /* reload syscall number */ cmpq $(IA32_NR_syscalls-1),%rax ja ia32_badsys @@ -208,12 +207,13 @@ sysexit_from_sys_call: TRACE_IRQS_ON sti movl %eax,%esi /* second arg, syscall return value */ - cmpl $0,%eax /* is it < 0? */ - setl %al /* 1 if so, 0 if not */ + cmpl $-MAX_ERRNO,%eax /* is it an error ? */ + jbe 1f + movslq %eax, %rsi /* if error sign extend to 64 bits */ +1: setbe %al /* 1 if error, 0 if not */ movzbl %al,%edi /* zero-extend that into %edi */ - inc %edi /* first arg, 0->1(AUDITSC_SUCCESS), 1->2(AUDITSC_FAILURE) */ - call audit_syscall_exit - movl RAX-ARGOFFSET(%rsp),%eax /* reload syscall return value */ + call __audit_syscall_exit + movq RAX-ARGOFFSET(%rsp),%rax /* reload syscall return value */ movl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT),%edi cli TRACE_IRQS_OFF @@ -447,9 +447,6 @@ ia32_badsys: movq $-ENOSYS,%rax jmp ia32_sysret -quiet_ni_syscall: - movq $-ENOSYS,%rax - ret CFI_ENDPROC .macro PTREGSCALL label, func, arg @@ -494,357 +491,3 @@ ia32_ptregs_common: jmp ia32_sysret /* misbalances the return cache */ CFI_ENDPROC END(ia32_ptregs_common) - - .section .rodata,"a" - .align 8 -ia32_sys_call_table: - .quad sys_restart_syscall - .quad sys_exit - .quad stub32_fork - .quad sys_read - .quad sys_write - .quad compat_sys_open /* 5 */ - .quad sys_close - .quad sys32_waitpid - .quad sys_creat - .quad sys_link - .quad sys_unlink /* 10 */ - .quad stub32_execve - .quad sys_chdir - .quad compat_sys_time - .quad sys_mknod - .quad sys_chmod /* 15 */ - .quad sys_lchown16 - .quad quiet_ni_syscall /* old break syscall holder */ - .quad sys_stat - .quad sys32_lseek - .quad sys_getpid /* 20 */ - .quad compat_sys_mount /* mount */ - .quad sys_oldumount /* old_umount */ - .quad sys_setuid16 - .quad sys_getuid16 - .quad compat_sys_stime /* stime */ /* 25 */ - .quad compat_sys_ptrace /* ptrace */ - .quad sys_alarm - .quad sys_fstat /* (old)fstat */ - .quad sys_pause - .quad compat_sys_utime /* 30 */ - .quad quiet_ni_syscall /* old stty syscall holder */ - .quad quiet_ni_syscall /* old gtty syscall holder */ - .quad sys_access - .quad sys_nice - .quad quiet_ni_syscall /* 35 */ /* old ftime syscall holder */ - .quad sys_sync - .quad sys32_kill - .quad sys_rename - .quad sys_mkdir - .quad sys_rmdir /* 40 */ - .quad sys_dup - .quad sys_pipe - .quad compat_sys_times - .quad quiet_ni_syscall /* old prof syscall holder */ - .quad sys_brk /* 45 */ - .quad sys_setgid16 - .quad sys_getgid16 - .quad sys_signal - .quad sys_geteuid16 - .quad sys_getegid16 /* 50 */ - .quad sys_acct - .quad sys_umount /* new_umount */ - .quad quiet_ni_syscall /* old lock syscall holder */ - .quad compat_sys_ioctl - .quad compat_sys_fcntl64 /* 55 */ - .quad quiet_ni_syscall /* old mpx syscall holder */ - .quad sys_setpgid - .quad quiet_ni_syscall /* old ulimit syscall holder */ - .quad sys_olduname - .quad sys_umask /* 60 */ - .quad sys_chroot - .quad compat_sys_ustat - .quad sys_dup2 - .quad sys_getppid - .quad sys_getpgrp /* 65 */ - .quad sys_setsid - .quad sys32_sigaction - .quad sys_sgetmask - .quad sys_ssetmask - .quad sys_setreuid16 /* 70 */ - .quad sys_setregid16 - .quad sys32_sigsuspend - .quad compat_sys_sigpending - .quad sys_sethostname - .quad compat_sys_setrlimit /* 75 */ - .quad compat_sys_old_getrlimit /* old_getrlimit */ - .quad compat_sys_getrusage - .quad compat_sys_gettimeofday - .quad compat_sys_settimeofday - .quad sys_getgroups16 /* 80 */ - .quad sys_setgroups16 - .quad compat_sys_old_select - .quad sys_symlink - .quad sys_lstat - .quad sys_readlink /* 85 */ - .quad sys_uselib - .quad sys_swapon - .quad sys_reboot - .quad compat_sys_old_readdir - .quad sys32_mmap /* 90 */ - .quad sys_munmap - .quad sys_truncate - .quad sys_ftruncate - .quad sys_fchmod - .quad sys_fchown16 /* 95 */ - .quad sys_getpriority - .quad sys_setpriority - .quad quiet_ni_syscall /* old profil syscall holder */ - .quad compat_sys_statfs - .quad compat_sys_fstatfs /* 100 */ - .quad sys_ioperm - .quad compat_sys_socketcall - .quad sys_syslog - .quad compat_sys_setitimer - .quad compat_sys_getitimer /* 105 */ - .quad compat_sys_newstat - .quad compat_sys_newlstat - .quad compat_sys_newfstat - .quad sys_uname - .quad stub32_iopl /* 110 */ - .quad sys_vhangup - .quad quiet_ni_syscall /* old "idle" system call */ - .quad sys32_vm86_warning /* vm86old */ - .quad compat_sys_wait4 - .quad sys_swapoff /* 115 */ - .quad compat_sys_sysinfo - .quad sys32_ipc - .quad sys_fsync - .quad stub32_sigreturn - .quad stub32_clone /* 120 */ - .quad sys_setdomainname - .quad sys_newuname - .quad sys_modify_ldt - .quad compat_sys_adjtimex - .quad sys32_mprotect /* 125 */ - .quad compat_sys_sigprocmask - .quad quiet_ni_syscall /* create_module */ - .quad sys_init_module - .quad sys_delete_module - .quad quiet_ni_syscall /* 130 get_kernel_syms */ - .quad sys32_quotactl - .quad sys_getpgid - .quad sys_fchdir - .quad quiet_ni_syscall /* bdflush */ - .quad sys_sysfs /* 135 */ - .quad sys_personality - .quad quiet_ni_syscall /* for afs_syscall */ - .quad sys_setfsuid16 - .quad sys_setfsgid16 - .quad sys_llseek /* 140 */ - .quad compat_sys_getdents - .quad compat_sys_select - .quad sys_flock - .quad sys_msync - .quad compat_sys_readv /* 145 */ - .quad compat_sys_writev - .quad sys_getsid - .quad sys_fdatasync - .quad compat_sys_sysctl /* sysctl */ - .quad sys_mlock /* 150 */ - .quad sys_munlock - .quad sys_mlockall - .quad sys_munlockall - .quad sys_sched_setparam - .quad sys_sched_getparam /* 155 */ - .quad sys_sched_setscheduler - .quad sys_sched_getscheduler - .quad sys_sched_yield - .quad sys_sched_get_priority_max - .quad sys_sched_get_priority_min /* 160 */ - .quad sys32_sched_rr_get_interval - .quad compat_sys_nanosleep - .quad sys_mremap - .quad sys_setresuid16 - .quad sys_getresuid16 /* 165 */ - .quad sys32_vm86_warning /* vm86 */ - .quad quiet_ni_syscall /* query_module */ - .quad sys_poll - .quad quiet_ni_syscall /* old nfsservctl */ - .quad sys_setresgid16 /* 170 */ - .quad sys_getresgid16 - .quad sys_prctl - .quad stub32_rt_sigreturn - .quad sys32_rt_sigaction - .quad sys32_rt_sigprocmask /* 175 */ - .quad sys32_rt_sigpending - .quad compat_sys_rt_sigtimedwait - .quad sys32_rt_sigqueueinfo - .quad sys_rt_sigsuspend - .quad sys32_pread /* 180 */ - .quad sys32_pwrite - .quad sys_chown16 - .quad sys_getcwd - .quad sys_capget - .quad sys_capset - .quad stub32_sigaltstack - .quad sys32_sendfile - .quad quiet_ni_syscall /* streams1 */ - .quad quiet_ni_syscall /* streams2 */ - .quad stub32_vfork /* 190 */ - .quad compat_sys_getrlimit - .quad sys_mmap_pgoff - .quad sys32_truncate64 - .quad sys32_ftruncate64 - .quad sys32_stat64 /* 195 */ - .quad sys32_lstat64 - .quad sys32_fstat64 - .quad sys_lchown - .quad sys_getuid - .quad sys_getgid /* 200 */ - .quad sys_geteuid - .quad sys_getegid - .quad sys_setreuid - .quad sys_setregid - .quad sys_getgroups /* 205 */ - .quad sys_setgroups - .quad sys_fchown - .quad sys_setresuid - .quad sys_getresuid - .quad sys_setresgid /* 210 */ - .quad sys_getresgid - .quad sys_chown - .quad sys_setuid - .quad sys_setgid - .quad sys_setfsuid /* 215 */ - .quad sys_setfsgid - .quad sys_pivot_root - .quad sys_mincore - .quad sys_madvise - .quad compat_sys_getdents64 /* 220 getdents64 */ - .quad compat_sys_fcntl64 - .quad quiet_ni_syscall /* tux */ - .quad quiet_ni_syscall /* security */ - .quad sys_gettid - .quad sys32_readahead /* 225 */ - .quad sys_setxattr - .quad sys_lsetxattr - .quad sys_fsetxattr - .quad sys_getxattr - .quad sys_lgetxattr /* 230 */ - .quad sys_fgetxattr - .quad sys_listxattr - .quad sys_llistxattr - .quad sys_flistxattr - .quad sys_removexattr /* 235 */ - .quad sys_lremovexattr - .quad sys_fremovexattr - .quad sys_tkill - .quad sys_sendfile64 - .quad compat_sys_futex /* 240 */ - .quad compat_sys_sched_setaffinity - .quad compat_sys_sched_getaffinity - .quad sys_set_thread_area - .quad sys_get_thread_area - .quad compat_sys_io_setup /* 245 */ - .quad sys_io_destroy - .quad compat_sys_io_getevents - .quad compat_sys_io_submit - .quad sys_io_cancel - .quad sys32_fadvise64 /* 250 */ - .quad quiet_ni_syscall /* free_huge_pages */ - .quad sys_exit_group - .quad sys32_lookup_dcookie - .quad sys_epoll_create - .quad sys_epoll_ctl /* 255 */ - .quad sys_epoll_wait - .quad sys_remap_file_pages - .quad sys_set_tid_address - .quad compat_sys_timer_create - .quad compat_sys_timer_settime /* 260 */ - .quad compat_sys_timer_gettime - .quad sys_timer_getoverrun - .quad sys_timer_delete - .quad compat_sys_clock_settime - .quad compat_sys_clock_gettime /* 265 */ - .quad compat_sys_clock_getres - .quad compat_sys_clock_nanosleep - .quad compat_sys_statfs64 - .quad compat_sys_fstatfs64 - .quad sys_tgkill /* 270 */ - .quad compat_sys_utimes - .quad sys32_fadvise64_64 - .quad quiet_ni_syscall /* sys_vserver */ - .quad sys_mbind - .quad compat_sys_get_mempolicy /* 275 */ - .quad sys_set_mempolicy - .quad compat_sys_mq_open - .quad sys_mq_unlink - .quad compat_sys_mq_timedsend - .quad compat_sys_mq_timedreceive /* 280 */ - .quad compat_sys_mq_notify - .quad compat_sys_mq_getsetattr - .quad compat_sys_kexec_load /* reserved for kexec */ - .quad compat_sys_waitid - .quad quiet_ni_syscall /* 285: sys_altroot */ - .quad sys_add_key - .quad sys_request_key - .quad sys_keyctl - .quad sys_ioprio_set - .quad sys_ioprio_get /* 290 */ - .quad sys_inotify_init - .quad sys_inotify_add_watch - .quad sys_inotify_rm_watch - .quad sys_migrate_pages - .quad compat_sys_openat /* 295 */ - .quad sys_mkdirat - .quad sys_mknodat - .quad sys_fchownat - .quad compat_sys_futimesat - .quad sys32_fstatat /* 300 */ - .quad sys_unlinkat - .quad sys_renameat - .quad sys_linkat - .quad sys_symlinkat - .quad sys_readlinkat /* 305 */ - .quad sys_fchmodat - .quad sys_faccessat - .quad compat_sys_pselect6 - .quad compat_sys_ppoll - .quad sys_unshare /* 310 */ - .quad compat_sys_set_robust_list - .quad compat_sys_get_robust_list - .quad sys_splice - .quad sys32_sync_file_range - .quad sys_tee /* 315 */ - .quad compat_sys_vmsplice - .quad compat_sys_move_pages - .quad sys_getcpu - .quad sys_epoll_pwait - .quad compat_sys_utimensat /* 320 */ - .quad compat_sys_signalfd - .quad sys_timerfd_create - .quad sys_eventfd - .quad sys32_fallocate - .quad compat_sys_timerfd_settime /* 325 */ - .quad compat_sys_timerfd_gettime - .quad compat_sys_signalfd4 - .quad sys_eventfd2 - .quad sys_epoll_create1 - .quad sys_dup3 /* 330 */ - .quad sys_pipe2 - .quad sys_inotify_init1 - .quad compat_sys_preadv - .quad compat_sys_pwritev - .quad compat_sys_rt_tgsigqueueinfo /* 335 */ - .quad sys_perf_event_open - .quad compat_sys_recvmmsg - .quad sys_fanotify_init - .quad sys32_fanotify_mark - .quad sys_prlimit64 /* 340 */ - .quad sys_name_to_handle_at - .quad compat_sys_open_by_handle_at - .quad compat_sys_clock_adjtime - .quad sys_syncfs - .quad compat_sys_sendmmsg /* 345 */ - .quad sys_setns - .quad compat_sys_process_vm_readv - .quad compat_sys_process_vm_writev -ia32_syscall_end: diff --git a/arch/x86/ia32/nosyscall.c b/arch/x86/ia32/nosyscall.c new file mode 100644 index 00000000000..51ecd5b4e78 --- /dev/null +++ b/arch/x86/ia32/nosyscall.c @@ -0,0 +1,7 @@ +#include <linux/kernel.h> +#include <linux/errno.h> + +long compat_ni_syscall(void) +{ + return -ENOSYS; +} diff --git a/arch/x86/ia32/syscall_ia32.c b/arch/x86/ia32/syscall_ia32.c new file mode 100644 index 00000000000..4754ba0f5d9 --- /dev/null +++ b/arch/x86/ia32/syscall_ia32.c @@ -0,0 +1,25 @@ +/* System call table for ia32 emulation. */ + +#include <linux/linkage.h> +#include <linux/sys.h> +#include <linux/cache.h> +#include <asm/asm-offsets.h> + +#define __SYSCALL_I386(nr, sym, compat) extern asmlinkage void compat(void) ; +#include <asm/syscalls_32.h> +#undef __SYSCALL_I386 + +#define __SYSCALL_I386(nr, sym, compat) [nr] = compat, + +typedef void (*sys_call_ptr_t)(void); + +extern void compat_ni_syscall(void); + +const sys_call_ptr_t ia32_sys_call_table[__NR_ia32_syscall_max+1] = { + /* + * Smells like a compiler bug -- it doesn't work + * when the & below is removed. + */ + [0 ... __NR_ia32_syscall_max] = &compat_ni_syscall, +#include <asm/syscalls_32.h> +}; diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild index 6fa90a845e4..b57e6a43a37 100644 --- a/arch/x86/include/asm/Kbuild +++ b/arch/x86/include/asm/Kbuild @@ -19,7 +19,8 @@ header-y += processor-flags.h header-y += ptrace-abi.h header-y += sigcontext32.h header-y += ucontext.h -header-y += unistd_32.h -header-y += unistd_64.h header-y += vm86.h header-y += vsyscall.h + +genhdr-y += unistd_32.h +genhdr-y += unistd_64.h diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h index 24098aafce0..fa13f0ec287 100644 --- a/arch/x86/include/asm/atomic64_32.h +++ b/arch/x86/include/asm/atomic64_32.h @@ -82,7 +82,7 @@ static inline void atomic64_set(atomic64_t *v, long long i) * * Atomically reads the value of @v and returns it. */ -static inline long long atomic64_read(atomic64_t *v) +static inline long long atomic64_read(const atomic64_t *v) { long long r; asm volatile(ATOMIC64_ALTERNATIVE(read) diff --git a/arch/x86/include/asm/debugreg.h b/arch/x86/include/asm/debugreg.h index 078ad0caefc..b903d5ea394 100644 --- a/arch/x86/include/asm/debugreg.h +++ b/arch/x86/include/asm/debugreg.h @@ -101,6 +101,28 @@ extern void aout_dump_debugregs(struct user *dump); extern void hw_breakpoint_restore(void); +#ifdef CONFIG_X86_64 +DECLARE_PER_CPU(int, debug_stack_usage); +static inline void debug_stack_usage_inc(void) +{ + __get_cpu_var(debug_stack_usage)++; +} +static inline void debug_stack_usage_dec(void) +{ + __get_cpu_var(debug_stack_usage)--; +} +int is_debug_stack(unsigned long addr); +void debug_stack_set_zero(void); +void debug_stack_reset(void); +#else /* !X86_64 */ +static inline int is_debug_stack(unsigned long addr) { return 0; } +static inline void debug_stack_set_zero(void) { } +static inline void debug_stack_reset(void) { } +static inline void debug_stack_usage_inc(void) { } +static inline void debug_stack_usage_dec(void) { } +#endif /* X86_64 */ + + #endif /* __KERNEL__ */ #endif /* _ASM_X86_DEBUGREG_H */ diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h index 41935fadfdf..e95822d683f 100644 --- a/arch/x86/include/asm/desc.h +++ b/arch/x86/include/asm/desc.h @@ -35,6 +35,8 @@ static inline void fill_ldt(struct desc_struct *desc, const struct user_desc *in extern struct desc_ptr idt_descr; extern gate_desc idt_table[]; +extern struct desc_ptr nmi_idt_descr; +extern gate_desc nmi_idt_table[]; struct gdt_page { struct desc_struct gdt[GDT_ENTRIES]; @@ -307,6 +309,16 @@ static inline void set_desc_limit(struct desc_struct *desc, unsigned long limit) desc->limit = (limit >> 16) & 0xf; } +#ifdef CONFIG_X86_64 +static inline void set_nmi_gate(int gate, void *addr) +{ + gate_desc s; + + pack_gate(&s, GATE_INTERRUPT, (unsigned long)addr, 0, 0, __KERNEL_CS); + write_idt_entry(nmi_idt_table, gate, &s); +} +#endif + static inline void _set_gate(int gate, unsigned type, void *addr, unsigned dpl, unsigned ist, unsigned seg) { diff --git a/arch/x86/include/asm/ia32_unistd.h b/arch/x86/include/asm/ia32_unistd.h index 976f6ecd2ce..b0d5716ca1e 100644 --- a/arch/x86/include/asm/ia32_unistd.h +++ b/arch/x86/include/asm/ia32_unistd.h @@ -2,17 +2,10 @@ #define _ASM_X86_IA32_UNISTD_H /* - * This file contains the system call numbers of the ia32 port, + * This file contains the system call numbers of the ia32 compat ABI, * this is for the kernel only. - * Only add syscalls here where some part of the kernel needs to know - * the number. This should be otherwise in sync with asm-x86/unistd_32.h. -AK */ - -#define __NR_ia32_restart_syscall 0 -#define __NR_ia32_exit 1 -#define __NR_ia32_read 3 -#define __NR_ia32_write 4 -#define __NR_ia32_sigreturn 119 -#define __NR_ia32_rt_sigreturn 173 +#define __SYSCALL_ia32_NR(x) (x) +#include <asm/unistd_32_ia32.h> #endif /* _ASM_X86_IA32_UNISTD_H */ diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index f35ce43c1a7..6aefb14cbbc 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -151,7 +151,7 @@ static inline void enable_p5_mce(void) {} void mce_setup(struct mce *m); void mce_log(struct mce *m); -DECLARE_PER_CPU(struct device, mce_device); +extern struct device *mce_device[CONFIG_NR_CPUS]; /* * Maximum banks number. diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h index c4a348f7bd4..d962e5652a7 100644 --- a/arch/x86/include/asm/syscall.h +++ b/arch/x86/include/asm/syscall.h @@ -15,6 +15,7 @@ #include <linux/sched.h> #include <linux/err.h> +#include <asm/asm-offsets.h> /* For NR_syscalls */ extern const unsigned long sys_call_table[]; diff --git a/arch/x86/include/asm/unistd.h b/arch/x86/include/asm/unistd.h index 2a58ed3e51d..21f77b89e47 100644 --- a/arch/x86/include/asm/unistd.h +++ b/arch/x86/include/asm/unistd.h @@ -1,13 +1,60 @@ +#ifndef _ASM_X86_UNISTD_H +#define _ASM_X86_UNISTD_H 1 + #ifdef __KERNEL__ # ifdef CONFIG_X86_32 -# include "unistd_32.h" + +# include <asm/unistd_32.h> +# define __ARCH_WANT_IPC_PARSE_VERSION +# define __ARCH_WANT_STAT64 +# define __ARCH_WANT_SYS_IPC +# define __ARCH_WANT_SYS_OLD_MMAP +# define __ARCH_WANT_SYS_OLD_SELECT + # else -# include "unistd_64.h" + +# include <asm/unistd_64.h> +# define __ARCH_WANT_COMPAT_SYS_TIME + # endif + +# define __ARCH_WANT_OLD_READDIR +# define __ARCH_WANT_OLD_STAT +# define __ARCH_WANT_SYS_ALARM +# define __ARCH_WANT_SYS_FADVISE64 +# define __ARCH_WANT_SYS_GETHOSTNAME +# define __ARCH_WANT_SYS_GETPGRP +# define __ARCH_WANT_SYS_LLSEEK +# define __ARCH_WANT_SYS_NICE +# define __ARCH_WANT_SYS_OLDUMOUNT +# define __ARCH_WANT_SYS_OLD_GETRLIMIT +# define __ARCH_WANT_SYS_OLD_UNAME +# define __ARCH_WANT_SYS_PAUSE +# define __ARCH_WANT_SYS_RT_SIGACTION +# define __ARCH_WANT_SYS_RT_SIGSUSPEND +# define __ARCH_WANT_SYS_SGETMASK +# define __ARCH_WANT_SYS_SIGNAL +# define __ARCH_WANT_SYS_SIGPENDING +# define __ARCH_WANT_SYS_SIGPROCMASK +# define __ARCH_WANT_SYS_SOCKETCALL +# define __ARCH_WANT_SYS_TIME +# define __ARCH_WANT_SYS_UTIME +# define __ARCH_WANT_SYS_WAITPID + +/* + * "Conditional" syscalls + * + * What we want is __attribute__((weak,alias("sys_ni_syscall"))), + * but it doesn't work on all toolchains, so we just do it by hand + */ +# define cond_syscall(x) asm(".weak\t" #x "\n\t.set\t" #x ",sys_ni_syscall") + #else # ifdef __i386__ -# include "unistd_32.h" +# include <asm/unistd_32.h> # else -# include "unistd_64.h" +# include <asm/unistd_64.h> # endif #endif + +#endif /* _ASM_X86_UNISTD_H */ diff --git a/arch/x86/include/asm/unistd_32.h b/arch/x86/include/asm/unistd_32.h deleted file mode 100644 index 599c77d38f3..00000000000 --- a/arch/x86/include/asm/unistd_32.h +++ /dev/null @@ -1,401 +0,0 @@ -#ifndef _ASM_X86_UNISTD_32_H -#define _ASM_X86_UNISTD_32_H - -/* - * This file contains the system call numbers. - */ - -#define __NR_restart_syscall 0 -#define __NR_exit 1 -#define __NR_fork 2 -#define __NR_read 3 -#define __NR_write 4 -#define __NR_open 5 -#define __NR_close 6 -#define __NR_waitpid 7 -#define __NR_creat 8 -#define __NR_link 9 -#define __NR_unlink 10 -#define __NR_execve 11 -#define __NR_chdir 12 -#define __NR_time 13 -#define __NR_mknod 14 -#define __NR_chmod 15 -#define __NR_lchown 16 -#define __NR_break 17 -#define __NR_oldstat 18 -#define __NR_lseek 19 -#define __NR_getpid 20 -#define __NR_mount 21 -#define __NR_umount 22 -#define __NR_setuid 23 -#define __NR_getuid 24 -#define __NR_stime 25 -#define __NR_ptrace 26 -#define __NR_alarm 27 -#define __NR_oldfstat 28 -#define __NR_pause 29 -#define __NR_utime 30 -#define __NR_stty 31 -#define __NR_gtty 32 -#define __NR_access 33 -#define __NR_nice 34 -#define __NR_ftime 35 -#define __NR_sync 36 -#define __NR_kill 37 -#define __NR_rename 38 -#define __NR_mkdir 39 -#define __NR_rmdir 40 -#define __NR_dup 41 -#define __NR_pipe 42 -#define __NR_times 43 -#define __NR_prof 44 -#define __NR_brk 45 -#define __NR_setgid 46 -#define __NR_getgid 47 -#define __NR_signal 48 -#define __NR_geteuid 49 -#define __NR_getegid 50 -#define __NR_acct 51 -#define __NR_umount2 52 -#define __NR_lock 53 -#define __NR_ioctl 54 -#define __NR_fcntl 55 -#define __NR_mpx 56 -#define __NR_setpgid 57 -#define __NR_ulimit 58 -#define __NR_oldolduname 59 -#define __NR_umask 60 -#define __NR_chroot 61 -#define __NR_ustat 62 -#define __NR_dup2 63 -#define __NR_getppid 64 -#define __NR_getpgrp 65 -#define __NR_setsid 66 -#define __NR_sigaction 67 -#define __NR_sgetmask 68 -#define __NR_ssetmask 69 -#define __NR_setreuid 70 -#define __NR_setregid 71 -#define __NR_sigsuspend 72 -#define __NR_sigpending 73 -#define __NR_sethostname 74 -#define __NR_setrlimit 75 -#define __NR_getrlimit 76 /* Back compatible 2Gig limited rlimit */ -#define __NR_getrusage 77 -#define __NR_gettimeofday 78 -#define __NR_settimeofday 79 -#define __NR_getgroups 80 -#define __NR_setgroups 81 -#define __NR_select 82 -#define __NR_symlink 83 -#define __NR_oldlstat 84 -#define __NR_readlink 85 -#define __NR_uselib 86 -#define __NR_swapon 87 -#define __NR_reboot 88 -#define __NR_readdir 89 -#define __NR_mmap 90 -#define __NR_munmap 91 -#define __NR_truncate 92 -#define __NR_ftruncate 93 -#define __NR_fchmod 94 -#define __NR_fchown 95 -#define __NR_getpriority 96 -#define __NR_setpriority 97 -#define __NR_profil 98 -#define __NR_statfs 99 -#define __NR_fstatfs 100 -#define __NR_ioperm 101 -#define __NR_socketcall 102 -#define __NR_syslog 103 -#define __NR_setitimer 104 -#define __NR_getitimer 105 -#define __NR_stat 106 -#define __NR_lstat 107 -#define __NR_fstat 108 -#define __NR_olduname 109 -#define __NR_iopl 110 -#define __NR_vhangup 111 -#define __NR_idle 112 -#define __NR_vm86old 113 -#define __NR_wait4 114 -#define __NR_swapoff 115 -#define __NR_sysinfo 116 -#define __NR_ipc 117 -#define __NR_fsync 118 -#define __NR_sigreturn 119 -#define __NR_clone 120 -#define __NR_setdomainname 121 -#define __NR_uname 122 -#define __NR_modify_ldt 123 -#define __NR_adjtimex 124 -#define __NR_mprotect 125 -#define __NR_sigprocmask 126 -#define __NR_create_module 127 -#define __NR_init_module 128 -#define __NR_delete_module 129 -#define __NR_get_kernel_syms 130 -#define __NR_quotactl 131 -#define __NR_getpgid 132 -#define __NR_fchdir 133 -#define __NR_bdflush 134 -#define __NR_sysfs 135 -#define __NR_personality 136 -#define __NR_afs_syscall 137 /* Syscall for Andrew File System */ -#define __NR_setfsuid 138 -#define __NR_setfsgid 139 -#define __NR__llseek 140 -#define __NR_getdents 141 -#define __NR__newselect 142 -#define __NR_flock 143 -#define __NR_msync 144 -#define __NR_readv 145 -#define __NR_writev 146 -#define __NR_getsid 147 -#define __NR_fdatasync 148 -#define __NR__sysctl 149 -#define __NR_mlock 150 -#define __NR_munlock 151 -#define __NR_mlockall 152 -#define __NR_munlockall 153 -#define __NR_sched_setparam 154 -#define __NR_sched_getparam 155 -#define __NR_sched_setscheduler 156 -#define __NR_sched_getscheduler 157 -#define __NR_sched_yield 158 -#define __NR_sched_get_priority_max 159 -#define __NR_sched_get_priority_min 160 -#define __NR_sched_rr_get_interval 161 -#define __NR_nanosleep 162 -#define __NR_mremap 163 -#define __NR_setresuid 164 -#define __NR_getresuid 165 -#define __NR_vm86 166 -#define __NR_query_module 167 -#define __NR_poll 168 -#define __NR_nfsservctl 169 -#define __NR_setresgid 170 -#define __NR_getresgid 171 -#define __NR_prctl 172 -#define __NR_rt_sigreturn 173 -#define __NR_rt_sigaction 174 -#define __NR_rt_sigprocmask 175 -#define __NR_rt_sigpending 176 -#define __NR_rt_sigtimedwait 177 -#define __NR_rt_sigqueueinfo 178 -#define __NR_rt_sigsuspend 179 -#define __NR_pread64 180 -#define __NR_pwrite64 181 -#define __NR_chown 182 -#define __NR_getcwd 183 -#define __NR_capget 184 -#define __NR_capset 185 -#define __NR_sigaltstack 186 -#define __NR_sendfile 187 -#define __NR_getpmsg 188 /* some people actually want streams */ -#define __NR_putpmsg 189 /* some people actually want streams */ -#define __NR_vfork 190 -#define __NR_ugetrlimit 191 /* SuS compliant getrlimit */ -#define __NR_mmap2 192 -#define __NR_truncate64 193 -#define __NR_ftruncate64 194 -#define __NR_stat64 195 -#define __NR_lstat64 196 -#define __NR_fstat64 197 -#define __NR_lchown32 198 -#define __NR_getuid32 199 -#define __NR_getgid32 200 -#define __NR_geteuid32 201 -#define __NR_getegid32 202 -#define __NR_setreuid32 203 -#define __NR_setregid32 204 -#define __NR_getgroups32 205 -#define __NR_setgroups32 206 -#define __NR_fchown32 207 -#define __NR_setresuid32 208 -#define __NR_getresuid32 209 -#define __NR_setresgid32 210 -#define __NR_getresgid32 211 -#define __NR_chown32 212 -#define __NR_setuid32 213 -#define __NR_setgid32 214 -#define __NR_setfsuid32 215 -#define __NR_setfsgid32 216 -#define __NR_pivot_root 217 -#define __NR_mincore 218 -#define __NR_madvise 219 -#define __NR_madvise1 219 /* delete when C lib stub is removed */ -#define __NR_getdents64 220 -#define __NR_fcntl64 221 -/* 223 is unused */ -#define __NR_gettid 224 -#define __NR_readahead 225 -#define __NR_setxattr 226 -#define __NR_lsetxattr 227 -#define __NR_fsetxattr 228 -#define __NR_getxattr 229 -#define __NR_lgetxattr 230 -#define __NR_fgetxattr 231 -#define __NR_listxattr 232 -#define __NR_llistxattr 233 -#define __NR_flistxattr 234 -#define __NR_removexattr 235 -#define __NR_lremovexattr 236 -#define __NR_fremovexattr 237 -#define __NR_tkill 238 -#define __NR_sendfile64 239 -#define __NR_futex 240 -#define __NR_sched_setaffinity 241 -#define __NR_sched_getaffinity 242 -#define __NR_set_thread_area 243 -#define __NR_get_thread_area 244 -#define __NR_io_setup 245 -#define __NR_io_destroy 246 -#define __NR_io_getevents 247 -#define __NR_io_submit 248 -#define __NR_io_cancel 249 -#define __NR_fadvise64 250 -/* 251 is available for reuse (was briefly sys_set_zone_reclaim) */ -#define __NR_exit_group 252 -#define __NR_lookup_dcookie 253 -#define __NR_epoll_create 254 -#define __NR_epoll_ctl 255 -#define __NR_epoll_wait 256 -#define __NR_remap_file_pages 257 -#define __NR_set_tid_address 258 -#define __NR_timer_create 259 -#define __NR_timer_settime (__NR_timer_create+1) -#define __NR_timer_gettime (__NR_timer_create+2) -#define __NR_timer_getoverrun (__NR_timer_create+3) -#define __NR_timer_delete (__NR_timer_create+4) -#define __NR_clock_settime (__NR_timer_create+5) -#define __NR_clock_gettime (__NR_timer_create+6) -#define __NR_clock_getres (__NR_timer_create+7) -#define __NR_clock_nanosleep (__NR_timer_create+8) -#define __NR_statfs64 268 -#define __NR_fstatfs64 269 -#define __NR_tgkill 270 -#define __NR_utimes 271 -#define __NR_fadvise64_64 272 -#define __NR_vserver 273 -#define __NR_mbind 274 -#define __NR_get_mempolicy 275 -#define __NR_set_mempolicy 276 -#define __NR_mq_open 277 -#define __NR_mq_unlink (__NR_mq_open+1) -#define __NR_mq_timedsend (__NR_mq_open+2) -#define __NR_mq_timedreceive (__NR_mq_open+3) -#define __NR_mq_notify (__NR_mq_open+4) -#define __NR_mq_getsetattr (__NR_mq_open+5) -#define __NR_kexec_load 283 -#define __NR_waitid 284 -/* #define __NR_sys_setaltroot 285 */ -#define __NR_add_key 286 -#define __NR_request_key 287 -#define __NR_keyctl 288 -#define __NR_ioprio_set 289 -#define __NR_ioprio_get 290 -#define __NR_inotify_init 291 -#define __NR_inotify_add_watch 292 -#define __NR_inotify_rm_watch 293 -#define __NR_migrate_pages 294 -#define __NR_openat 295 -#define __NR_mkdirat 296 -#define __NR_mknodat 297 -#define __NR_fchownat 298 -#define __NR_futimesat 299 -#define __NR_fstatat64 300 -#define __NR_unlinkat 301 -#define __NR_renameat 302 -#define __NR_linkat 303 -#define __NR_symlinkat 304 -#define __NR_readlinkat 305 -#define __NR_fchmodat 306 -#define __NR_faccessat 307 -#define __NR_pselect6 308 -#define __NR_ppoll 309 -#define __NR_unshare 310 -#define __NR_set_robust_list 311 -#define __NR_get_robust_list 312 -#define __NR_splice 313 -#define __NR_sync_file_range 314 -#define __NR_tee 315 -#define __NR_vmsplice 316 -#define __NR_move_pages 317 -#define __NR_getcpu 318 -#define __NR_epoll_pwait 319 -#define __NR_utimensat 320 -#define __NR_signalfd 321 -#define __NR_timerfd_create 322 -#define __NR_eventfd 323 -#define __NR_fallocate 324 -#define __NR_timerfd_settime 325 -#define __NR_timerfd_gettime 326 -#define __NR_signalfd4 327 -#define __NR_eventfd2 328 -#define __NR_epoll_create1 329 -#define __NR_dup3 330 -#define __NR_pipe2 331 -#define __NR_inotify_init1 332 -#define __NR_preadv 333 -#define __NR_pwritev 334 -#define __NR_rt_tgsigqueueinfo 335 -#define __NR_perf_event_open 336 -#define __NR_recvmmsg 337 -#define __NR_fanotify_init 338 -#define __NR_fanotify_mark 339 -#define __NR_prlimit64 340 -#define __NR_name_to_handle_at 341 -#define __NR_open_by_handle_at 342 -#define __NR_clock_adjtime 343 -#define __NR_syncfs 344 -#define __NR_sendmmsg 345 -#define __NR_setns 346 -#define __NR_process_vm_readv 347 -#define __NR_process_vm_writev 348 - -#ifdef __KERNEL__ - -#define NR_syscalls 349 - -#define __ARCH_WANT_IPC_PARSE_VERSION -#define __ARCH_WANT_OLD_READDIR -#define __ARCH_WANT_OLD_STAT -#define __ARCH_WANT_STAT64 -#define __ARCH_WANT_SYS_ALARM -#define __ARCH_WANT_SYS_GETHOSTNAME -#define __ARCH_WANT_SYS_IPC -#define __ARCH_WANT_SYS_PAUSE -#define __ARCH_WANT_SYS_SGETMASK -#define __ARCH_WANT_SYS_SIGNAL -#define __ARCH_WANT_SYS_TIME -#define __ARCH_WANT_SYS_UTIME -#define __ARCH_WANT_SYS_WAITPID -#define __ARCH_WANT_SYS_SOCKETCALL -#define __ARCH_WANT_SYS_FADVISE64 -#define __ARCH_WANT_SYS_GETPGRP -#define __ARCH_WANT_SYS_LLSEEK -#define __ARCH_WANT_SYS_NICE -#define __ARCH_WANT_SYS_OLD_GETRLIMIT -#define __ARCH_WANT_SYS_OLD_UNAME -#define __ARCH_WANT_SYS_OLD_MMAP -#define __ARCH_WANT_SYS_OLD_SELECT -#define __ARCH_WANT_SYS_OLDUMOUNT -#define __ARCH_WANT_SYS_SIGPENDING -#define __ARCH_WANT_SYS_SIGPROCMASK -#define __ARCH_WANT_SYS_RT_SIGACTION -#define __ARCH_WANT_SYS_RT_SIGSUSPEND - -/* - * "Conditional" syscalls - * - * What we want is __attribute__((weak,alias("sys_ni_syscall"))), - * but it doesn't work on all toolchains, so we just do it by hand - */ -#ifndef cond_syscall -#define cond_syscall(x) asm(".weak\t" #x "\n\t.set\t" #x ",sys_ni_syscall") -#endif - -#endif /* __KERNEL__ */ -#endif /* _ASM_X86_UNISTD_32_H */ diff --git a/arch/x86/include/asm/unistd_64.h b/arch/x86/include/asm/unistd_64.h deleted file mode 100644 index 0431f193c3f..00000000000 --- a/arch/x86/include/asm/unistd_64.h +++ /dev/null @@ -1,732 +0,0 @@ -#ifndef _ASM_X86_UNISTD_64_H -#define _ASM_X86_UNISTD_64_H - -#ifndef __SYSCALL -#define __SYSCALL(a, b) -#endif - -/* - * This file contains the system call numbers. - * - * Note: holes are not allowed. - */ - -/* at least 8 syscall per cacheline */ -#define __NR_read 0 -__SYSCALL(__NR_read, sys_read) -#define __NR_write 1 -__SYSCALL(__NR_write, sys_write) -#define __NR_open 2 -__SYSCALL(__NR_open, sys_open) -#define __NR_close 3 -__SYSCALL(__NR_close, sys_close) -#define __NR_stat 4 -__SYSCALL(__NR_stat, sys_newstat) -#define __NR_fstat 5 -__SYSCALL(__NR_fstat, sys_newfstat) -#define __NR_lstat 6 -__SYSCALL(__NR_lstat, sys_newlstat) -#define __NR_poll 7 -__SYSCALL(__NR_poll, sys_poll) - -#define __NR_lseek 8 -__SYSCALL(__NR_lseek, sys_lseek) -#define __NR_mmap 9 -__SYSCALL(__NR_mmap, sys_mmap) -#define __NR_mprotect 10 -__SYSCALL(__NR_mprotect, sys_mprotect) -#define __NR_munmap 11 -__SYSCALL(__NR_munmap, sys_munmap) -#define __NR_brk 12 -__SYSCALL(__NR_brk, sys_brk) -#define __NR_rt_sigaction 13 -__SYSCALL(__NR_rt_sigaction, sys_rt_sigaction) -#define __NR_rt_sigprocmask 14 -__SYSCALL(__NR_rt_sigprocmask, sys_rt_sigprocmask) -#define __NR_rt_sigreturn 15 -__SYSCALL(__NR_rt_sigreturn, stub_rt_sigreturn) - -#define __NR_ioctl 16 -__SYSCALL(__NR_ioctl, sys_ioctl) -#define __NR_pread64 17 -__SYSCALL(__NR_pread64, sys_pread64) -#define __NR_pwrite64 18 -__SYSCALL(__NR_pwrite64, sys_pwrite64) -#define __NR_readv 19 -__SYSCALL(__NR_readv, sys_readv) -#define __NR_writev 20 -__SYSCALL(__NR_writev, sys_writev) -#define __NR_access 21 -__SYSCALL(__NR_access, sys_access) -#define __NR_pipe 22 -__SYSCALL(__NR_pipe, sys_pipe) -#define __NR_select 23 -__SYSCALL(__NR_select, sys_select) - -#define __NR_sched_yield 24 -__SYSCALL(__NR_sched_yield, sys_sched_yield) -#define __NR_mremap 25 -__SYSCALL(__NR_mremap, sys_mremap) -#define __NR_msync 26 -__SYSCALL(__NR_msync, sys_msync) -#define __NR_mincore 27 -__SYSCALL(__NR_mincore, sys_mincore) -#define __NR_madvise 28 -__SYSCALL(__NR_madvise, sys_madvise) -#define __NR_shmget 29 -__SYSCALL(__NR_shmget, sys_shmget) -#define __NR_shmat 30 -__SYSCALL(__NR_shmat, sys_shmat) -#define __NR_shmctl 31 -__SYSCALL(__NR_shmctl, sys_shmctl) - -#define __NR_dup 32 -__SYSCALL(__NR_dup, sys_dup) -#define __NR_dup2 33 -__SYSCALL(__NR_dup2, sys_dup2) -#define __NR_pause 34 -__SYSCALL(__NR_pause, sys_pause) -#define __NR_nanosleep 35 -__SYSCALL(__NR_nanosleep, sys_nanosleep) -#define __NR_getitimer 36 -__SYSCALL(__NR_getitimer, sys_getitimer) -#define __NR_alarm 37 -__SYSCALL(__NR_alarm, sys_alarm) -#define __NR_setitimer 38 -__SYSCALL(__NR_setitimer, sys_setitimer) -#define __NR_getpid 39 -__SYSCALL(__NR_getpid, sys_getpid) - -#define __NR_sendfile 40 -__SYSCALL(__NR_sendfile, sys_sendfile64) -#define __NR_socket 41 -__SYSCALL(__NR_socket, sys_socket) -#define __NR_connect 42 -__SYSCALL(__NR_connect, sys_connect) -#define __NR_accept 43 -__SYSCALL(__NR_accept, sys_accept) -#define __NR_sendto 44 -__SYSCALL(__NR_sendto, sys_sendto) -#define __NR_recvfrom 45 -__SYSCALL(__NR_recvfrom, sys_recvfrom) -#define __NR_sendmsg 46 -__SYSCALL(__NR_sendmsg, sys_sendmsg) -#define __NR_recvmsg 47 -__SYSCALL(__NR_recvmsg, sys_recvmsg) - -#define __NR_shutdown 48 -__SYSCALL(__NR_shutdown, sys_shutdown) -#define __NR_bind 49 -__SYSCALL(__NR_bind, sys_bind) -#define __NR_listen 50 -__SYSCALL(__NR_listen, sys_listen) -#define __NR_getsockname 51 -__SYSCALL(__NR_getsockname, sys_getsockname) -#define __NR_getpeername 52 -__SYSCALL(__NR_getpeername, sys_getpeername) -#define __NR_socketpair 53 -__SYSCALL(__NR_socketpair, sys_socketpair) -#define __NR_setsockopt 54 -__SYSCALL(__NR_setsockopt, sys_setsockopt) -#define __NR_getsockopt 55 -__SYSCALL(__NR_getsockopt, sys_getsockopt) - -#define __NR_clone 56 -__SYSCALL(__NR_clone, stub_clone) -#define __NR_fork 57 -__SYSCALL(__NR_fork, stub_fork) -#define __NR_vfork 58 -__SYSCALL(__NR_vfork, stub_vfork) -#define __NR_execve 59 -__SYSCALL(__NR_execve, stub_execve) -#define __NR_exit 60 -__SYSCALL(__NR_exit, sys_exit) -#define __NR_wait4 61 -__SYSCALL(__NR_wait4, sys_wait4) -#define __NR_kill 62 -__SYSCALL(__NR_kill, sys_kill) -#define __NR_uname 63 -__SYSCALL(__NR_uname, sys_newuname) - -#define __NR_semget 64 -__SYSCALL(__NR_semget, sys_semget) -#define __NR_semop 65 -__SYSCALL(__NR_semop, sys_semop) -#define __NR_semctl 66 -__SYSCALL(__NR_semctl, sys_semctl) -#define __NR_shmdt 67 -__SYSCALL(__NR_shmdt, sys_shmdt) -#define __NR_msgget 68 -__SYSCALL(__NR_msgget, sys_msgget) -#define __NR_msgsnd 69 -__SYSCALL(__NR_msgsnd, sys_msgsnd) -#define __NR_msgrcv 70 -__SYSCALL(__NR_msgrcv, sys_msgrcv) -#define __NR_msgctl 71 -__SYSCALL(__NR_msgctl, sys_msgctl) - -#define __NR_fcntl 72 -__SYSCALL(__NR_fcntl, sys_fcntl) -#define __NR_flock 73 -__SYSCALL(__NR_flock, sys_flock) -#define __NR_fsync 74 -__SYSCALL(__NR_fsync, sys_fsync) -#define __NR_fdatasync 75 -__SYSCALL(__NR_fdatasync, sys_fdatasync) -#define __NR_truncate 76 -__SYSCALL(__NR_truncate, sys_truncate) -#define __NR_ftruncate 77 -__SYSCALL(__NR_ftruncate, sys_ftruncate) -#define __NR_getdents 78 -__SYSCALL(__NR_getdents, sys_getdents) -#define __NR_getcwd 79 -__SYSCALL(__NR_getcwd, sys_getcwd) - -#define __NR_chdir 80 -__SYSCALL(__NR_chdir, sys_chdir) -#define __NR_fchdir 81 -__SYSCALL(__NR_fchdir, sys_fchdir) -#define __NR_rename 82 -__SYSCALL(__NR_rename, sys_rename) -#define __NR_mkdir 83 -__SYSCALL(__NR_mkdir, sys_mkdir) -#define __NR_rmdir 84 -__SYSCALL(__NR_rmdir, sys_rmdir) -#define __NR_creat 85 -__SYSCALL(__NR_creat, sys_creat) -#define __NR_link 86 -__SYSCALL(__NR_link, sys_link) -#define __NR_unlink 87 -__SYSCALL(__NR_unlink, sys_unlink) - -#define __NR_symlink 88 -__SYSCALL(__NR_symlink, sys_symlink) -#define __NR_readlink 89 -__SYSCALL(__NR_readlink, sys_readlink) -#define __NR_chmod 90 -__SYSCALL(__NR_chmod, sys_chmod) -#define __NR_fchmod 91 -__SYSCALL(__NR_fchmod, sys_fchmod) -#define __NR_chown 92 -__SYSCALL(__NR_chown, sys_chown) -#define __NR_fchown 93 -__SYSCALL(__NR_fchown, sys_fchown) -#define __NR_lchown 94 -__SYSCALL(__NR_lchown, sys_lchown) -#define __NR_umask 95 -__SYSCALL(__NR_umask, sys_umask) - -#define __NR_gettimeofday 96 -__SYSCALL(__NR_gettimeofday, sys_gettimeofday) -#define __NR_getrlimit 97 -__SYSCALL(__NR_getrlimit, sys_getrlimit) -#define __NR_getrusage 98 -__SYSCALL(__NR_getrusage, sys_getrusage) -#define __NR_sysinfo 99 -__SYSCALL(__NR_sysinfo, sys_sysinfo) -#define __NR_times 100 -__SYSCALL(__NR_times, sys_times) -#define __NR_ptrace 101 -__SYSCALL(__NR_ptrace, sys_ptrace) -#define __NR_getuid 102 -__SYSCALL(__NR_getuid, sys_getuid) -#define __NR_syslog 103 -__SYSCALL(__NR_syslog, sys_syslog) - -/* at the very end the stuff that never runs during the benchmarks */ -#define __NR_getgid 104 -__SYSCALL(__NR_getgid, sys_getgid) -#define __NR_setuid 105 -__SYSCALL(__NR_setuid, sys_setuid) -#define __NR_setgid 106 -__SYSCALL(__NR_setgid, sys_setgid) -#define __NR_geteuid 107 -__SYSCALL(__NR_geteuid, sys_geteuid) -#define __NR_getegid 108 -__SYSCALL(__NR_getegid, sys_getegid) -#define __NR_setpgid 109 -__SYSCALL(__NR_setpgid, sys_setpgid) -#define __NR_getppid 110 -__SYSCALL(__NR_getppid, sys_getppid) -#define __NR_getpgrp 111 -__SYSCALL(__NR_getpgrp, sys_getpgrp) - -#define __NR_setsid 112 -__SYSCALL(__NR_setsid, sys_setsid) -#define __NR_setreuid 113 -__SYSCALL(__NR_setreuid, sys_setreuid) -#define __NR_setregid 114 -__SYSCALL(__NR_setregid, sys_setregid) -#define __NR_getgroups 115 -__SYSCALL(__NR_getgroups, sys_getgroups) -#define __NR_setgroups 116 -__SYSCALL(__NR_setgroups, sys_setgroups) -#define __NR_setresuid 117 -__SYSCALL(__NR_setresuid, sys_setresuid) -#define __NR_getresuid 118 -__SYSCALL(__NR_getresuid, sys_getresuid) -#define __NR_setresgid 119 -__SYSCALL(__NR_setresgid, sys_setresgid) - -#define __NR_getresgid 120 -__SYSCALL(__NR_getresgid, sys_getresgid) -#define __NR_getpgid 121 -__SYSCALL(__NR_getpgid, sys_getpgid) -#define __NR_setfsuid 122 -__SYSCALL(__NR_setfsuid, sys_setfsuid) -#define __NR_setfsgid 123 -__SYSCALL(__NR_setfsgid, sys_setfsgid) -#define __NR_getsid 124 -__SYSCALL(__NR_getsid, sys_getsid) -#define __NR_capget 125 -__SYSCALL(__NR_capget, sys_capget) -#define __NR_capset 126 -__SYSCALL(__NR_capset, sys_capset) - -#define __NR_rt_sigpending 127 -__SYSCALL(__NR_rt_sigpending, sys_rt_sigpending) -#define __NR_rt_sigtimedwait 128 -__SYSCALL(__NR_rt_sigtimedwait, sys_rt_sigtimedwait) -#define __NR_rt_sigqueueinfo 129 -__SYSCALL(__NR_rt_sigqueueinfo, sys_rt_sigqueueinfo) -#define __NR_rt_sigsuspend 130 -__SYSCALL(__NR_rt_sigsuspend, sys_rt_sigsuspend) -#define __NR_sigaltstack 131 -__SYSCALL(__NR_sigaltstack, stub_sigaltstack) -#define __NR_utime 132 -__SYSCALL(__NR_utime, sys_utime) -#define __NR_mknod 133 -__SYSCALL(__NR_mknod, sys_mknod) - -/* Only needed for a.out */ -#define __NR_uselib 134 -__SYSCALL(__NR_uselib, sys_ni_syscall) -#define __NR_personality 135 -__SYSCALL(__NR_personality, sys_personality) - -#define __NR_ustat 136 -__SYSCALL(__NR_ustat, sys_ustat) -#define __NR_statfs 137 -__SYSCALL(__NR_statfs, sys_statfs) -#define __NR_fstatfs 138 -__SYSCALL(__NR_fstatfs, sys_fstatfs) -#define __NR_sysfs 139 -__SYSCALL(__NR_sysfs, sys_sysfs) - -#define __NR_getpriority 140 -__SYSCALL(__NR_getpriority, sys_getpriority) -#define __NR_setpriority 141 -__SYSCALL(__NR_setpriority, sys_setpriority) -#define __NR_sched_setparam 142 -__SYSCALL(__NR_sched_setparam, sys_sched_setparam) -#define __NR_sched_getparam 143 -__SYSCALL(__NR_sched_getparam, sys_sched_getparam) -#define __NR_sched_setscheduler 144 -__SYSCALL(__NR_sched_setscheduler, sys_sched_setscheduler) -#define __NR_sched_getscheduler 145 -__SYSCALL(__NR_sched_getscheduler, sys_sched_getscheduler) -#define __NR_sched_get_priority_max 146 -__SYSCALL(__NR_sched_get_priority_max, sys_sched_get_priority_max) -#define __NR_sched_get_priority_min 147 -__SYSCALL(__NR_sched_get_priority_min, sys_sched_get_priority_min) -#define __NR_sched_rr_get_interval 148 -__SYSCALL(__NR_sched_rr_get_interval, sys_sched_rr_get_interval) - -#define __NR_mlock 149 -__SYSCALL(__NR_mlock, sys_mlock) -#define __NR_munlock 150 -__SYSCALL(__NR_munlock, sys_munlock) -#define __NR_mlockall 151 -__SYSCALL(__NR_mlockall, sys_mlockall) -#define __NR_munlockall 152 -__SYSCALL(__NR_munlockall, sys_munlockall) - -#define __NR_vhangup 153 -__SYSCALL(__NR_vhangup, sys_vhangup) - -#define __NR_modify_ldt 154 -__SYSCALL(__NR_modify_ldt, sys_modify_ldt) - -#define __NR_pivot_root 155 -__SYSCALL(__NR_pivot_root, sys_pivot_root) - -#define __NR__sysctl 156 -__SYSCALL(__NR__sysctl, sys_sysctl) - -#define __NR_prctl 157 -__SYSCALL(__NR_prctl, sys_prctl) -#define __NR_arch_prctl 158 -__SYSCALL(__NR_arch_prctl, sys_arch_prctl) - -#define __NR_adjtimex 159 -__SYSCALL(__NR_adjtimex, sys_adjtimex) - -#define __NR_setrlimit 160 -__SYSCALL(__NR_setrlimit, sys_setrlimit) - -#define __NR_chroot 161 -__SYSCALL(__NR_chroot, sys_chroot) - -#define __NR_sync 162 -__SYSCALL(__NR_sync, sys_sync) - -#define __NR_acct 163 -__SYSCALL(__NR_acct, sys_acct) - -#define __NR_settimeofday 164 -__SYSCALL(__NR_settimeofday, sys_settimeofday) - -#define __NR_mount 165 -__SYSCALL(__NR_mount, sys_mount) -#define __NR_umount2 166 -__SYSCALL(__NR_umount2, sys_umount) - -#define __NR_swapon 167 -__SYSCALL(__NR_swapon, sys_swapon) -#define __NR_swapoff 168 -__SYSCALL(__NR_swapoff, sys_swapoff) - -#define __NR_reboot 169 -__SYSCALL(__NR_reboot, sys_reboot) - -#define __NR_sethostname 170 -__SYSCALL(__NR_sethostname, sys_sethostname) -#define __NR_setdomainname 171 -__SYSCALL(__NR_setdomainname, sys_setdomainname) - -#define __NR_iopl 172 -__SYSCALL(__NR_iopl, stub_iopl) -#define __NR_ioperm 173 -__SYSCALL(__NR_ioperm, sys_ioperm) - -#define __NR_create_module 174 -__SYSCALL(__NR_create_module, sys_ni_syscall) -#define __NR_init_module 175 -__SYSCALL(__NR_init_module, sys_init_module) -#define __NR_delete_module 176 -__SYSCALL(__NR_delete_module, sys_delete_module) -#define __NR_get_kernel_syms 177 -__SYSCALL(__NR_get_kernel_syms, sys_ni_syscall) -#define __NR_query_module 178 -__SYSCALL(__NR_query_module, sys_ni_syscall) - -#define __NR_quotactl 179 -__SYSCALL(__NR_quotactl, sys_quotactl) - -#define __NR_nfsservctl 180 -__SYSCALL(__NR_nfsservctl, sys_ni_syscall) - -/* reserved for LiS/STREAMS */ -#define __NR_getpmsg 181 -__SYSCALL(__NR_getpmsg, sys_ni_syscall) -#define __NR_putpmsg 182 -__SYSCALL(__NR_putpmsg, sys_ni_syscall) - -/* reserved for AFS */ -#define __NR_afs_syscall 183 -__SYSCALL(__NR_afs_syscall, sys_ni_syscall) - -/* reserved for tux */ -#define __NR_tuxcall 184 -__SYSCALL(__NR_tuxcall, sys_ni_syscall) - -#define __NR_security 185 -__SYSCALL(__NR_security, sys_ni_syscall) - -#define __NR_gettid 186 -__SYSCALL(__NR_gettid, sys_gettid) - -#define __NR_readahead 187 -__SYSCALL(__NR_readahead, sys_readahead) -#define __NR_setxattr 188 -__SYSCALL(__NR_setxattr, sys_setxattr) -#define __NR_lsetxattr 189 -__SYSCALL(__NR_lsetxattr, sys_lsetxattr) -#define __NR_fsetxattr 190 -__SYSCALL(__NR_fsetxattr, sys_fsetxattr) -#define __NR_getxattr 191 -__SYSCALL(__NR_getxattr, sys_getxattr) -#define __NR_lgetxattr 192 -__SYSCALL(__NR_lgetxattr, sys_lgetxattr) -#define __NR_fgetxattr 193 -__SYSCALL(__NR_fgetxattr, sys_fgetxattr) -#define __NR_listxattr 194 -__SYSCALL(__NR_listxattr, sys_listxattr) -#define __NR_llistxattr 195 -__SYSCALL(__NR_llistxattr, sys_llistxattr) -#define __NR_flistxattr 196 -__SYSCALL(__NR_flistxattr, sys_flistxattr) -#define __NR_removexattr 197 -__SYSCALL(__NR_removexattr, sys_removexattr) -#define __NR_lremovexattr 198 -__SYSCALL(__NR_lremovexattr, sys_lremovexattr) -#define __NR_fremovexattr 199 -__SYSCALL(__NR_fremovexattr, sys_fremovexattr) -#define __NR_tkill 200 -__SYSCALL(__NR_tkill, sys_tkill) -#define __NR_time 201 -__SYSCALL(__NR_time, sys_time) -#define __NR_futex 202 -__SYSCALL(__NR_futex, sys_futex) -#define __NR_sched_setaffinity 203 -__SYSCALL(__NR_sched_setaffinity, sys_sched_setaffinity) -#define __NR_sched_getaffinity 204 -__SYSCALL(__NR_sched_getaffinity, sys_sched_getaffinity) -#define __NR_set_thread_area 205 -__SYSCALL(__NR_set_thread_area, sys_ni_syscall) /* use arch_prctl */ -#define __NR_io_setup 206 -__SYSCALL(__NR_io_setup, sys_io_setup) -#define __NR_io_destroy 207 -__SYSCALL(__NR_io_destroy, sys_io_destroy) -#define __NR_io_getevents 208 -__SYSCALL(__NR_io_getevents, sys_io_getevents) -#define __NR_io_submit 209 -__SYSCALL(__NR_io_submit, sys_io_submit) -#define __NR_io_cancel 210 -__SYSCALL(__NR_io_cancel, sys_io_cancel) -#define __NR_get_thread_area 211 -__SYSCALL(__NR_get_thread_area, sys_ni_syscall) /* use arch_prctl */ -#define __NR_lookup_dcookie 212 -__SYSCALL(__NR_lookup_dcookie, sys_lookup_dcookie) -#define __NR_epoll_create 213 -__SYSCALL(__NR_epoll_create, sys_epoll_create) -#define __NR_epoll_ctl_old 214 -__SYSCALL(__NR_epoll_ctl_old, sys_ni_syscall) -#define __NR_epoll_wait_old 215 -__SYSCALL(__NR_epoll_wait_old, sys_ni_syscall) -#define __NR_remap_file_pages 216 -__SYSCALL(__NR_remap_file_pages, sys_remap_file_pages) -#define __NR_getdents64 217 -__SYSCALL(__NR_getdents64, sys_getdents64) -#define __NR_set_tid_address 218 -__SYSCALL(__NR_set_tid_address, sys_set_tid_address) -#define __NR_restart_syscall 219 -__SYSCALL(__NR_restart_syscall, sys_restart_syscall) -#define __NR_semtimedop 220 -__SYSCALL(__NR_semtimedop, sys_semtimedop) -#define __NR_fadvise64 221 -__SYSCALL(__NR_fadvise64, sys_fadvise64) -#define __NR_timer_create 222 -__SYSCALL(__NR_timer_create, sys_timer_create) -#define __NR_timer_settime 223 -__SYSCALL(__NR_timer_settime, sys_timer_settime) -#define __NR_timer_gettime 224 -__SYSCALL(__NR_timer_gettime, sys_timer_gettime) -#define __NR_timer_getoverrun 225 -__SYSCALL(__NR_timer_getoverrun, sys_timer_getoverrun) -#define __NR_timer_delete 226 -__SYSCALL(__NR_timer_delete, sys_timer_delete) -#define __NR_clock_settime 227 -__SYSCALL(__NR_clock_settime, sys_clock_settime) -#define __NR_clock_gettime 228 -__SYSCALL(__NR_clock_gettime, sys_clock_gettime) -#define __NR_clock_getres 229 -__SYSCALL(__NR_clock_getres, sys_clock_getres) -#define __NR_clock_nanosleep 230 -__SYSCALL(__NR_clock_nanosleep, sys_clock_nanosleep) -#define __NR_exit_group 231 -__SYSCALL(__NR_exit_group, sys_exit_group) -#define __NR_epoll_wait 232 -__SYSCALL(__NR_epoll_wait, sys_epoll_wait) -#define __NR_epoll_ctl 233 -__SYSCALL(__NR_epoll_ctl, sys_epoll_ctl) -#define __NR_tgkill 234 -__SYSCALL(__NR_tgkill, sys_tgkill) -#define __NR_utimes 235 -__SYSCALL(__NR_utimes, sys_utimes) -#define __NR_vserver 236 -__SYSCALL(__NR_vserver, sys_ni_syscall) -#define __NR_mbind 237 -__SYSCALL(__NR_mbind, sys_mbind) -#define __NR_set_mempolicy 238 -__SYSCALL(__NR_set_mempolicy, sys_set_mempolicy) -#define __NR_get_mempolicy 239 -__SYSCALL(__NR_get_mempolicy, sys_get_mempolicy) -#define __NR_mq_open 240 -__SYSCALL(__NR_mq_open, sys_mq_open) -#define __NR_mq_unlink 241 -__SYSCALL(__NR_mq_unlink, sys_mq_unlink) -#define __NR_mq_timedsend 242 -__SYSCALL(__NR_mq_timedsend, sys_mq_timedsend) -#define __NR_mq_timedreceive 243 -__SYSCALL(__NR_mq_timedreceive, sys_mq_timedreceive) -#define __NR_mq_notify 244 -__SYSCALL(__NR_mq_notify, sys_mq_notify) -#define __NR_mq_getsetattr 245 -__SYSCALL(__NR_mq_getsetattr, sys_mq_getsetattr) -#define __NR_kexec_load 246 -__SYSCALL(__NR_kexec_load, sys_kexec_load) -#define __NR_waitid 247 -__SYSCALL(__NR_waitid, sys_waitid) -#define __NR_add_key 248 -__SYSCALL(__NR_add_key, sys_add_key) -#define __NR_request_key 249 -__SYSCALL(__NR_request_key, sys_request_key) -#define __NR_keyctl 250 -__SYSCALL(__NR_keyctl, sys_keyctl) -#define __NR_ioprio_set 251 -__SYSCALL(__NR_ioprio_set, sys_ioprio_set) -#define __NR_ioprio_get 252 -__SYSCALL(__NR_ioprio_get, sys_ioprio_get) -#define __NR_inotify_init 253 -__SYSCALL(__NR_inotify_init, sys_inotify_init) -#define __NR_inotify_add_watch 254 -__SYSCALL(__NR_inotify_add_watch, sys_inotify_add_watch) -#define __NR_inotify_rm_watch 255 -__SYSCALL(__NR_inotify_rm_watch, sys_inotify_rm_watch) -#define __NR_migrate_pages 256 -__SYSCALL(__NR_migrate_pages, sys_migrate_pages) -#define __NR_openat 257 -__SYSCALL(__NR_openat, sys_openat) -#define __NR_mkdirat 258 -__SYSCALL(__NR_mkdirat, sys_mkdirat) -#define __NR_mknodat 259 -__SYSCALL(__NR_mknodat, sys_mknodat) -#define __NR_fchownat 260 -__SYSCALL(__NR_fchownat, sys_fchownat) -#define __NR_futimesat 261 -__SYSCALL(__NR_futimesat, sys_futimesat) -#define __NR_newfstatat 262 -__SYSCALL(__NR_newfstatat, sys_newfstatat) -#define __NR_unlinkat 263 -__SYSCALL(__NR_unlinkat, sys_unlinkat) -#define __NR_renameat 264 -__SYSCALL(__NR_renameat, sys_renameat) -#define __NR_linkat 265 -__SYSCALL(__NR_linkat, sys_linkat) -#define __NR_symlinkat 266 -__SYSCALL(__NR_symlinkat, sys_symlinkat) -#define __NR_readlinkat 267 -__SYSCALL(__NR_readlinkat, sys_readlinkat) -#define __NR_fchmodat 268 -__SYSCALL(__NR_fchmodat, sys_fchmodat) -#define __NR_faccessat 269 -__SYSCALL(__NR_faccessat, sys_faccessat) -#define __NR_pselect6 270 -__SYSCALL(__NR_pselect6, sys_pselect6) -#define __NR_ppoll 271 -__SYSCALL(__NR_ppoll, sys_ppoll) -#define __NR_unshare 272 -__SYSCALL(__NR_unshare, sys_unshare) -#define __NR_set_robust_list 273 -__SYSCALL(__NR_set_robust_list, sys_set_robust_list) -#define __NR_get_robust_list 274 -__SYSCALL(__NR_get_robust_list, sys_get_robust_list) -#define __NR_splice 275 -__SYSCALL(__NR_splice, sys_splice) -#define __NR_tee 276 -__SYSCALL(__NR_tee, sys_tee) -#define __NR_sync_file_range 277 -__SYSCALL(__NR_sync_file_range, sys_sync_file_range) -#define __NR_vmsplice 278 -__SYSCALL(__NR_vmsplice, sys_vmsplice) -#define __NR_move_pages 279 -__SYSCALL(__NR_move_pages, sys_move_pages) -#define __NR_utimensat 280 -__SYSCALL(__NR_utimensat, sys_utimensat) -#define __NR_epoll_pwait 281 -__SYSCALL(__NR_epoll_pwait, sys_epoll_pwait) -#define __NR_signalfd 282 -__SYSCALL(__NR_signalfd, sys_signalfd) -#define __NR_timerfd_create 283 -__SYSCALL(__NR_timerfd_create, sys_timerfd_create) -#define __NR_eventfd 284 -__SYSCALL(__NR_eventfd, sys_eventfd) -#define __NR_fallocate 285 -__SYSCALL(__NR_fallocate, sys_fallocate) -#define __NR_timerfd_settime 286 -__SYSCALL(__NR_timerfd_settime, sys_timerfd_settime) -#define __NR_timerfd_gettime 287 -__SYSCALL(__NR_timerfd_gettime, sys_timerfd_gettime) -#define __NR_accept4 288 -__SYSCALL(__NR_accept4, sys_accept4) -#define __NR_signalfd4 289 -__SYSCALL(__NR_signalfd4, sys_signalfd4) -#define __NR_eventfd2 290 -__SYSCALL(__NR_eventfd2, sys_eventfd2) -#define __NR_epoll_create1 291 -__SYSCALL(__NR_epoll_create1, sys_epoll_create1) -#define __NR_dup3 292 -__SYSCALL(__NR_dup3, sys_dup3) -#define __NR_pipe2 293 -__SYSCALL(__NR_pipe2, sys_pipe2) -#define __NR_inotify_init1 294 -__SYSCALL(__NR_inotify_init1, sys_inotify_init1) -#define __NR_preadv 295 -__SYSCALL(__NR_preadv, sys_preadv) -#define __NR_pwritev 296 -__SYSCALL(__NR_pwritev, sys_pwritev) -#define __NR_rt_tgsigqueueinfo 297 -__SYSCALL(__NR_rt_tgsigqueueinfo, sys_rt_tgsigqueueinfo) -#define __NR_perf_event_open 298 -__SYSCALL(__NR_perf_event_open, sys_perf_event_open) -#define __NR_recvmmsg 299 -__SYSCALL(__NR_recvmmsg, sys_recvmmsg) -#define __NR_fanotify_init 300 -__SYSCALL(__NR_fanotify_init, sys_fanotify_init) -#define __NR_fanotify_mark 301 -__SYSCALL(__NR_fanotify_mark, sys_fanotify_mark) -#define __NR_prlimit64 302 -__SYSCALL(__NR_prlimit64, sys_prlimit64) -#define __NR_name_to_handle_at 303 -__SYSCALL(__NR_name_to_handle_at, sys_name_to_handle_at) -#define __NR_open_by_handle_at 304 -__SYSCALL(__NR_open_by_handle_at, sys_open_by_handle_at) -#define __NR_clock_adjtime 305 -__SYSCALL(__NR_clock_adjtime, sys_clock_adjtime) -#define __NR_syncfs 306 -__SYSCALL(__NR_syncfs, sys_syncfs) -#define __NR_sendmmsg 307 -__SYSCALL(__NR_sendmmsg, sys_sendmmsg) -#define __NR_setns 308 -__SYSCALL(__NR_setns, sys_setns) -#define __NR_getcpu 309 -__SYSCALL(__NR_getcpu, sys_getcpu) -#define __NR_process_vm_readv 310 -__SYSCALL(__NR_process_vm_readv, sys_process_vm_readv) -#define __NR_process_vm_writev 311 -__SYSCALL(__NR_process_vm_writev, sys_process_vm_writev) - -#ifndef __NO_STUBS -#define __ARCH_WANT_OLD_READDIR -#define __ARCH_WANT_OLD_STAT -#define __ARCH_WANT_SYS_ALARM -#define __ARCH_WANT_SYS_GETHOSTNAME -#define __ARCH_WANT_SYS_PAUSE -#define __ARCH_WANT_SYS_SGETMASK -#define __ARCH_WANT_SYS_SIGNAL -#define __ARCH_WANT_SYS_UTIME -#define __ARCH_WANT_SYS_WAITPID -#define __ARCH_WANT_SYS_SOCKETCALL -#define __ARCH_WANT_SYS_FADVISE64 -#define __ARCH_WANT_SYS_GETPGRP -#define __ARCH_WANT_SYS_LLSEEK -#define __ARCH_WANT_SYS_NICE -#define __ARCH_WANT_SYS_OLD_GETRLIMIT -#define __ARCH_WANT_SYS_OLD_UNAME -#define __ARCH_WANT_SYS_OLDUMOUNT -#define __ARCH_WANT_SYS_SIGPENDING -#define __ARCH_WANT_SYS_SIGPROCMASK -#define __ARCH_WANT_SYS_RT_SIGACTION -#define __ARCH_WANT_SYS_RT_SIGSUSPEND -#define __ARCH_WANT_SYS_TIME -#define __ARCH_WANT_COMPAT_SYS_TIME -#endif /* __NO_STUBS */ - -#ifdef __KERNEL__ - -#ifndef COMPILE_OFFSETS -#include <asm/asm-offsets.h> -#define NR_syscalls (__NR_syscall_max + 1) -#endif - -/* - * "Conditional" syscalls - * - * What we want is __attribute__((weak,alias("sys_ni_syscall"))), - * but it doesn't work on all toolchains, so we just do it by hand - */ -#define cond_syscall(x) asm(".weak\t" #x "\n\t.set\t" #x ",sys_ni_syscall") -#endif /* __KERNEL__ */ - -#endif /* _ASM_X86_UNISTD_64_H */ diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h index 8e862aaf0d9..becf47b8173 100644 --- a/arch/x86/include/asm/uv/uv_bau.h +++ b/arch/x86/include/asm/uv/uv_bau.h @@ -65,7 +65,7 @@ * UV2: Bit 19 selects between * (0): 10 microsecond timebase and * (1): 80 microseconds - * we're using 655us, similar to UV1: 65 units of 10us + * we're using 560us, similar to UV1: 65 units of 10us */ #define UV1_INTD_SOFT_ACK_TIMEOUT_PERIOD (9UL) #define UV2_INTD_SOFT_ACK_TIMEOUT_PERIOD (15UL) @@ -167,6 +167,7 @@ #define FLUSH_RETRY_TIMEOUT 2 #define FLUSH_GIVEUP 3 #define FLUSH_COMPLETE 4 +#define FLUSH_RETRY_BUSYBUG 5 /* * tuning the action when the numalink network is extremely delayed @@ -235,10 +236,10 @@ struct bau_msg_payload { /* - * Message header: 16 bytes (128 bits) (bytes 0x30-0x3f of descriptor) + * UV1 Message header: 16 bytes (128 bits) (bytes 0x30-0x3f of descriptor) * see table 4.2.3.0.1 in broacast_assist spec. */ -struct bau_msg_header { +struct uv1_bau_msg_header { unsigned int dest_subnodeid:6; /* must be 0x10, for the LB */ /* bits 5:0 */ unsigned int base_dest_nasid:15; /* nasid of the first bit */ @@ -318,19 +319,87 @@ struct bau_msg_header { }; /* + * UV2 Message header: 16 bytes (128 bits) (bytes 0x30-0x3f of descriptor) + * see figure 9-2 of harp_sys.pdf + */ +struct uv2_bau_msg_header { + unsigned int base_dest_nasid:15; /* nasid of the first bit */ + /* bits 14:0 */ /* in uvhub map */ + unsigned int dest_subnodeid:5; /* must be 0x10, for the LB */ + /* bits 19:15 */ + unsigned int rsvd_1:1; /* must be zero */ + /* bit 20 */ + /* Address bits 59:21 */ + /* bits 25:2 of address (44:21) are payload */ + /* these next 24 bits become bytes 12-14 of msg */ + /* bits 28:21 land in byte 12 */ + unsigned int replied_to:1; /* sent as 0 by the source to + byte 12 */ + /* bit 21 */ + unsigned int msg_type:3; /* software type of the + message */ + /* bits 24:22 */ + unsigned int canceled:1; /* message canceled, resource + is to be freed*/ + /* bit 25 */ + unsigned int payload_1:3; /* not currently used */ + /* bits 28:26 */ + + /* bits 36:29 land in byte 13 */ + unsigned int payload_2a:3; /* not currently used */ + unsigned int payload_2b:5; /* not currently used */ + /* bits 36:29 */ + + /* bits 44:37 land in byte 14 */ + unsigned int payload_3:8; /* not currently used */ + /* bits 44:37 */ + + unsigned int rsvd_2:7; /* reserved */ + /* bits 51:45 */ + unsigned int swack_flag:1; /* software acknowledge flag */ + /* bit 52 */ + unsigned int rsvd_3a:3; /* must be zero */ + unsigned int rsvd_3b:8; /* must be zero */ + unsigned int rsvd_3c:8; /* must be zero */ + unsigned int rsvd_3d:3; /* must be zero */ + /* bits 74:53 */ + unsigned int fairness:3; /* usually zero */ + /* bits 77:75 */ + + unsigned int sequence:16; /* message sequence number */ + /* bits 93:78 Suppl_A */ + unsigned int chaining:1; /* next descriptor is part of + this activation*/ + /* bit 94 */ + unsigned int multilevel:1; /* multi-level multicast + format */ + /* bit 95 */ + unsigned int rsvd_4:24; /* ordered / source node / + source subnode / aging + must be zero */ + /* bits 119:96 */ + unsigned int command:8; /* message type */ + /* bits 127:120 */ +}; + +/* * The activation descriptor: * The format of the message to send, plus all accompanying control * Should be 64 bytes */ struct bau_desc { - struct pnmask distribution; + struct pnmask distribution; /* * message template, consisting of header and payload: */ - struct bau_msg_header header; - struct bau_msg_payload payload; + union bau_msg_header { + struct uv1_bau_msg_header uv1_hdr; + struct uv2_bau_msg_header uv2_hdr; + } header; + + struct bau_msg_payload payload; }; -/* +/* UV1: * -payload-- ---------header------ * bytes 0-11 bits 41-56 bits 58-81 * A B (2) C (3) @@ -340,6 +409,16 @@ struct bau_desc { * bytes 0-11 bytes 12-14 bytes 16-17 (byte 15 filled in by hw as vector) * ------------payload queue----------- */ +/* UV2: + * -payload-- ---------header------ + * bytes 0-11 bits 70-78 bits 21-44 + * A B (2) C (3) + * + * A/B/C are moved to: + * A C B + * bytes 0-11 bytes 12-14 bytes 16-17 (byte 15 filled in by hw as vector) + * ------------payload queue----------- + */ /* * The payload queue on the destination side is an array of these. @@ -385,7 +464,6 @@ struct bau_pq_entry { struct msg_desc { struct bau_pq_entry *msg; int msg_slot; - int swack_slot; struct bau_pq_entry *queue_first; struct bau_pq_entry *queue_last; }; @@ -405,6 +483,7 @@ struct ptc_stats { requests */ unsigned long s_stimeout; /* source side timeouts */ unsigned long s_dtimeout; /* destination side timeouts */ + unsigned long s_strongnacks; /* number of strong nack's */ unsigned long s_time; /* time spent in sending side */ unsigned long s_retriesok; /* successful retries */ unsigned long s_ntargcpu; /* total number of cpu's @@ -439,6 +518,9 @@ struct ptc_stats { unsigned long s_retry_messages; /* retry broadcasts */ unsigned long s_bau_reenabled; /* for bau enable/disable */ unsigned long s_bau_disabled; /* for bau enable/disable */ + unsigned long s_uv2_wars; /* uv2 workaround, perm. busy */ + unsigned long s_uv2_wars_hw; /* uv2 workaround, hiwater */ + unsigned long s_uv2_war_waits; /* uv2 workaround, long waits */ /* destination statistics */ unsigned long d_alltlb; /* times all tlb's on this cpu were flushed */ @@ -511,9 +593,12 @@ struct bau_control { short osnode; short uvhub_cpu; short uvhub; + short uvhub_version; short cpus_in_socket; short cpus_in_uvhub; short partition_base_pnode; + short using_desc; /* an index, like uvhub_cpu */ + unsigned int inuse_map; unsigned short message_number; unsigned short uvhub_quiesce; short socket_acknowledge_count[DEST_Q_SIZE]; @@ -531,6 +616,7 @@ struct bau_control { int cong_response_us; int cong_reps; int cong_period; + unsigned long clocks_per_100_usec; cycles_t period_time; long period_requests; struct hub_and_pnode *thp; @@ -591,6 +677,11 @@ static inline void write_mmr_sw_ack(unsigned long mr) uv_write_local_mmr(UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS, mr); } +static inline void write_gmmr_sw_ack(int pnode, unsigned long mr) +{ + write_gmmr(pnode, UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS, mr); +} + static inline unsigned long read_mmr_sw_ack(void) { return read_lmmr(UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE); diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 02b2f05b371..5369059c07a 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -25,7 +25,8 @@ obj-$(CONFIG_IRQ_WORK) += irq_work.o obj-y += probe_roms.o obj-$(CONFIG_X86_32) += sys_i386_32.o i386_ksyms_32.o obj-$(CONFIG_X86_64) += sys_x86_64.o x8664_ksyms_64.o -obj-$(CONFIG_X86_64) += syscall_64.o vsyscall_64.o +obj-y += syscall_$(BITS).o +obj-$(CONFIG_X86_64) += vsyscall_64.o obj-$(CONFIG_X86_64) += vsyscall_emu_64.o obj-y += bootflag.o e820.o obj-y += pci-dma.o quirks.o topology.o kdebugfs.o diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 9d59bbacd4e..79b05b88aa1 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -769,7 +769,12 @@ void __init uv_system_init(void) for(i = 0; i < UVH_NODE_PRESENT_TABLE_DEPTH; i++) uv_possible_blades += hweight64(uv_read_local_mmr( UVH_NODE_PRESENT_TABLE + i * 8)); - printk(KERN_DEBUG "UV: Found %d blades\n", uv_num_possible_blades()); + + /* uv_num_possible_blades() is really the hub count */ + printk(KERN_INFO "UV: Found %d blades, %d hubs\n", + is_uv1_hub() ? uv_num_possible_blades() : + (uv_num_possible_blades() + 1) / 2, + uv_num_possible_blades()); bytes = sizeof(struct uv_blade_info) * uv_num_possible_blades(); uv_blade_info = kzalloc(bytes, GFP_KERNEL); diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index a46bd383953..f76623cbe26 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -383,21 +383,21 @@ static int ignore_sys_suspend; static int ignore_normal_resume; static int bounce_interval __read_mostly = DEFAULT_BOUNCE_INTERVAL; -static int debug __read_mostly; -static int smp __read_mostly; +static bool debug __read_mostly; +static bool smp __read_mostly; static int apm_disabled = -1; #ifdef CONFIG_SMP -static int power_off; +static bool power_off; #else -static int power_off = 1; +static bool power_off = 1; #endif -static int realmode_power_off; +static bool realmode_power_off; #ifdef CONFIG_APM_ALLOW_INTS -static int allow_ints = 1; +static bool allow_ints = 1; #else -static int allow_ints; +static bool allow_ints; #endif -static int broken_psr; +static bool broken_psr; static DECLARE_WAIT_QUEUE_HEAD(apm_waitqueue); static DECLARE_WAIT_QUEUE_HEAD(apm_suspend_waitqueue); diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c index 395a10e6806..85d98ab15cd 100644 --- a/arch/x86/kernel/asm-offsets_32.c +++ b/arch/x86/kernel/asm-offsets_32.c @@ -3,6 +3,11 @@ #include <linux/lguest.h> #include "../../../drivers/lguest/lg.h" +#define __SYSCALL_I386(nr, sym, compat) [nr] = 1, +static char syscalls[] = { +#include <asm/syscalls_32.h> +}; + /* workaround for a warning with -Wmissing-prototypes */ void foo(void); @@ -76,4 +81,7 @@ void foo(void) OFFSET(LGUEST_PAGES_regs_errcode, lguest_pages, regs.errcode); OFFSET(LGUEST_PAGES_regs, lguest_pages, regs); #endif + BLANK(); + DEFINE(__NR_syscall_max, sizeof(syscalls) - 1); + DEFINE(NR_syscalls, sizeof(syscalls)); } diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c index e72a1194af2..834e897b1e2 100644 --- a/arch/x86/kernel/asm-offsets_64.c +++ b/arch/x86/kernel/asm-offsets_64.c @@ -1,11 +1,12 @@ #include <asm/ia32.h> -#define __NO_STUBS 1 -#undef __SYSCALL -#undef _ASM_X86_UNISTD_64_H -#define __SYSCALL(nr, sym) [nr] = 1, -static char syscalls[] = { -#include <asm/unistd.h> +#define __SYSCALL_64(nr, sym, compat) [nr] = 1, +static char syscalls_64[] = { +#include <asm/syscalls_64.h> +}; +#define __SYSCALL_I386(nr, sym, compat) [nr] = 1, +static char syscalls_ia32[] = { +#include <asm/syscalls_32.h> }; int main(void) @@ -72,7 +73,11 @@ int main(void) OFFSET(TSS_ist, tss_struct, x86_tss.ist); BLANK(); - DEFINE(__NR_syscall_max, sizeof(syscalls) - 1); + DEFINE(__NR_syscall_max, sizeof(syscalls_64) - 1); + DEFINE(NR_syscalls, sizeof(syscalls_64)); + + DEFINE(__NR_ia32_syscall_max, sizeof(syscalls_ia32) - 1); + DEFINE(IA32_NR_syscalls, sizeof(syscalls_ia32)); return 0; } diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 850f2963a42..d43cad74f16 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1021,6 +1021,8 @@ __setup("clearcpuid=", setup_disablecpuid); #ifdef CONFIG_X86_64 struct desc_ptr idt_descr = { NR_VECTORS * 16 - 1, (unsigned long) idt_table }; +struct desc_ptr nmi_idt_descr = { NR_VECTORS * 16 - 1, + (unsigned long) nmi_idt_table }; DEFINE_PER_CPU_FIRST(union irq_stack_union, irq_stack_union) __aligned(PAGE_SIZE); @@ -1085,6 +1087,26 @@ unsigned long kernel_eflags; */ DEFINE_PER_CPU(struct orig_ist, orig_ist); +static DEFINE_PER_CPU(unsigned long, debug_stack_addr); +DEFINE_PER_CPU(int, debug_stack_usage); + +int is_debug_stack(unsigned long addr) +{ + return __get_cpu_var(debug_stack_usage) || + (addr <= __get_cpu_var(debug_stack_addr) && + addr > (__get_cpu_var(debug_stack_addr) - DEBUG_STKSZ)); +} + +void debug_stack_set_zero(void) +{ + load_idt((const struct desc_ptr *)&nmi_idt_descr); +} + +void debug_stack_reset(void) +{ + load_idt((const struct desc_ptr *)&idt_descr); +} + #else /* CONFIG_X86_64 */ DEFINE_PER_CPU(struct task_struct *, current_task) = &init_task; @@ -1212,6 +1234,8 @@ void __cpuinit cpu_init(void) estacks += exception_stack_sizes[v]; oist->ist[v] = t->x86_tss.ist[v] = (unsigned long)estacks; + if (v == DEBUG_STACK-1) + per_cpu(debug_stack_addr, cpu) = (unsigned long)estacks; } } diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index f22a9f7f639..5a11ae2e9e9 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -1859,7 +1859,7 @@ static struct bus_type mce_subsys = { .dev_name = "machinecheck", }; -DEFINE_PER_CPU(struct device, mce_device); +struct device *mce_device[CONFIG_NR_CPUS]; __cpuinitdata void (*threshold_cpu_callback)(unsigned long action, unsigned int cpu); @@ -2001,19 +2001,27 @@ static struct device_attribute *mce_device_attrs[] = { static cpumask_var_t mce_device_initialized; +static void mce_device_release(struct device *dev) +{ + kfree(dev); +} + /* Per cpu device init. All of the cpus still share the same ctrl bank: */ static __cpuinit int mce_device_create(unsigned int cpu) { - struct device *dev = &per_cpu(mce_device, cpu); + struct device *dev; int err; int i, j; if (!mce_available(&boot_cpu_data)) return -EIO; - memset(&dev->kobj, 0, sizeof(struct kobject)); + dev = kzalloc(sizeof *dev, GFP_KERNEL); + if (!dev) + return -ENOMEM; dev->id = cpu; dev->bus = &mce_subsys; + dev->release = &mce_device_release; err = device_register(dev); if (err) @@ -2030,6 +2038,7 @@ static __cpuinit int mce_device_create(unsigned int cpu) goto error2; } cpumask_set_cpu(cpu, mce_device_initialized); + mce_device[cpu] = dev; return 0; error2: @@ -2046,7 +2055,7 @@ error: static __cpuinit void mce_device_remove(unsigned int cpu) { - struct device *dev = &per_cpu(mce_device, cpu); + struct device *dev = mce_device[cpu]; int i; if (!cpumask_test_cpu(cpu, mce_device_initialized)) @@ -2060,6 +2069,7 @@ static __cpuinit void mce_device_remove(unsigned int cpu) device_unregister(dev); cpumask_clear_cpu(cpu, mce_device_initialized); + mce_device[cpu] = NULL; } /* Make sure there are no machine checks on offlined CPUs. */ diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index ba0b94a7e20..786e76a8632 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -523,6 +523,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank) { int i, err = 0; struct threshold_bank *b = NULL; + struct device *dev = mce_device[cpu]; char name[32]; sprintf(name, "threshold_bank%i", bank); @@ -543,8 +544,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank) if (!b) goto out; - err = sysfs_create_link(&per_cpu(mce_device, cpu).kobj, - b->kobj, name); + err = sysfs_create_link(&dev->kobj, b->kobj, name); if (err) goto out; @@ -565,7 +565,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank) goto out; } - b->kobj = kobject_create_and_add(name, &per_cpu(mce_device, cpu).kobj); + b->kobj = kobject_create_and_add(name, &dev->kobj); if (!b->kobj) goto out_free; @@ -585,8 +585,9 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank) if (i == cpu) continue; - err = sysfs_create_link(&per_cpu(mce_device, i).kobj, - b->kobj, name); + dev = mce_device[i]; + if (dev) + err = sysfs_create_link(&dev->kobj,b->kobj, name); if (err) goto out; @@ -649,6 +650,7 @@ static void deallocate_threshold_block(unsigned int cpu, static void threshold_remove_bank(unsigned int cpu, int bank) { struct threshold_bank *b; + struct device *dev; char name[32]; int i = 0; @@ -663,7 +665,7 @@ static void threshold_remove_bank(unsigned int cpu, int bank) #ifdef CONFIG_SMP /* sibling symlink */ if (shared_bank[bank] && b->blocks->cpu != cpu) { - sysfs_remove_link(&per_cpu(mce_device, cpu).kobj, name); + sysfs_remove_link(&mce_device[cpu]->kobj, name); per_cpu(threshold_banks, cpu)[bank] = NULL; return; @@ -675,7 +677,9 @@ static void threshold_remove_bank(unsigned int cpu, int bank) if (i == cpu) continue; - sysfs_remove_link(&per_cpu(mce_device, i).kobj, name); + dev = mce_device[i]; + if (dev) + sysfs_remove_link(&dev->kobj, name); per_cpu(threshold_banks, i)[bank] = NULL; } diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 174d938d576..62d61e9976e 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -703,7 +703,7 @@ void __init e820_mark_nosave_regions(unsigned long limit_pfn) } #endif -#ifdef CONFIG_HIBERNATION +#ifdef CONFIG_ACPI /** * Mark ACPI NVS memory region, so that we can save/restore it during * hibernation and the subsequent resume. @@ -716,7 +716,7 @@ static int __init e820_mark_nvs_memory(void) struct e820entry *ei = &e820.map[i]; if (ei->type == E820_NVS) - suspend_nvs_register(ei->addr, ei->size); + acpi_nvs_register(ei->addr, ei->size); } return 0; diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index 22d0e21b4dd..79d97e68f04 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -42,6 +42,7 @@ */ #include <linux/linkage.h> +#include <linux/err.h> #include <asm/thread_info.h> #include <asm/irqflags.h> #include <asm/errno.h> @@ -81,8 +82,6 @@ * enough to patch inline, increasing performance. */ -#define nr_syscalls ((syscall_table_size)/4) - #ifdef CONFIG_PREEMPT #define preempt_stop(clobbers) DISABLE_INTERRUPTS(clobbers); TRACE_IRQS_OFF #else @@ -423,7 +422,7 @@ sysenter_past_esp: testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags(%ebp) jnz sysenter_audit sysenter_do_call: - cmpl $(nr_syscalls), %eax + cmpl $(NR_syscalls), %eax jae syscall_badsys call *sys_call_table(,%eax,4) movl %eax,PT_EAX(%esp) @@ -455,7 +454,7 @@ sysenter_audit: movl %ebx,%ecx /* 3rd arg: 1st syscall arg */ movl %eax,%edx /* 2nd arg: syscall number */ movl $AUDIT_ARCH_I386,%eax /* 1st arg: audit arch */ - call audit_syscall_entry + call __audit_syscall_entry pushl_cfi %ebx movl PT_EAX(%esp),%eax /* reload syscall number */ jmp sysenter_do_call @@ -466,11 +465,10 @@ sysexit_audit: TRACE_IRQS_ON ENABLE_INTERRUPTS(CLBR_ANY) movl %eax,%edx /* second arg, syscall return value */ - cmpl $0,%eax /* is it < 0? */ - setl %al /* 1 if so, 0 if not */ + cmpl $-MAX_ERRNO,%eax /* is it an error ? */ + setbe %al /* 1 if so, 0 if not */ movzbl %al,%eax /* zero-extend that */ - inc %eax /* first arg, 0->1(AUDITSC_SUCCESS), 1->2(AUDITSC_FAILURE) */ - call audit_syscall_exit + call __audit_syscall_exit DISABLE_INTERRUPTS(CLBR_ANY) TRACE_IRQS_OFF movl TI_flags(%ebp), %ecx @@ -504,7 +502,7 @@ ENTRY(system_call) # system call tracing in operation / emulation testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags(%ebp) jnz syscall_trace_entry - cmpl $(nr_syscalls), %eax + cmpl $(NR_syscalls), %eax jae syscall_badsys syscall_call: call *sys_call_table(,%eax,4) @@ -654,7 +652,7 @@ syscall_trace_entry: movl %esp, %eax call syscall_trace_enter /* What it returned is what we'll actually use. */ - cmpl $(nr_syscalls), %eax + cmpl $(NR_syscalls), %eax jnae syscall_call jmp syscall_exit END(syscall_trace_entry) @@ -694,29 +692,28 @@ END(syscall_badsys) * System calls that need a pt_regs pointer. */ #define PTREGSCALL0(name) \ - ALIGN; \ -ptregs_##name: \ +ENTRY(ptregs_##name) ; \ leal 4(%esp),%eax; \ - jmp sys_##name; + jmp sys_##name; \ +ENDPROC(ptregs_##name) #define PTREGSCALL1(name) \ - ALIGN; \ -ptregs_##name: \ +ENTRY(ptregs_##name) ; \ leal 4(%esp),%edx; \ movl (PT_EBX+4)(%esp),%eax; \ - jmp sys_##name; + jmp sys_##name; \ +ENDPROC(ptregs_##name) #define PTREGSCALL2(name) \ - ALIGN; \ -ptregs_##name: \ +ENTRY(ptregs_##name) ; \ leal 4(%esp),%ecx; \ movl (PT_ECX+4)(%esp),%edx; \ movl (PT_EBX+4)(%esp),%eax; \ - jmp sys_##name; + jmp sys_##name; \ +ENDPROC(ptregs_##name) #define PTREGSCALL3(name) \ - ALIGN; \ -ptregs_##name: \ +ENTRY(ptregs_##name) ; \ CFI_STARTPROC; \ leal 4(%esp),%eax; \ pushl_cfi %eax; \ @@ -741,8 +738,7 @@ PTREGSCALL2(vm86) PTREGSCALL1(vm86old) /* Clone is an oddball. The 4th arg is in %edi */ - ALIGN; -ptregs_clone: +ENTRY(ptregs_clone) CFI_STARTPROC leal 4(%esp),%eax pushl_cfi %eax @@ -1213,11 +1209,6 @@ return_to_handler: jmp *%ecx #endif -.section .rodata,"a" -#include "syscall_table_32.S" - -syscall_table_size=(.-sys_call_table) - /* * Some functions should be protected against kprobes */ diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index a20e1cb9dc8..3fe8239fd8f 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -55,6 +55,7 @@ #include <asm/paravirt.h> #include <asm/ftrace.h> #include <asm/percpu.h> +#include <linux/err.h> /* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */ #include <linux/elf-em.h> @@ -548,7 +549,7 @@ badsys: #ifdef CONFIG_AUDITSYSCALL /* * Fast path for syscall audit without full syscall trace. - * We just call audit_syscall_entry() directly, and then + * We just call __audit_syscall_entry() directly, and then * jump back to the normal fast path. */ auditsys: @@ -558,22 +559,21 @@ auditsys: movq %rdi,%rdx /* 3rd arg: 1st syscall arg */ movq %rax,%rsi /* 2nd arg: syscall number */ movl $AUDIT_ARCH_X86_64,%edi /* 1st arg: audit arch */ - call audit_syscall_entry + call __audit_syscall_entry LOAD_ARGS 0 /* reload call-clobbered registers */ jmp system_call_fastpath /* - * Return fast path for syscall audit. Call audit_syscall_exit() + * Return fast path for syscall audit. Call __audit_syscall_exit() * directly and then jump back to the fast path with TIF_SYSCALL_AUDIT * masked off. */ sysret_audit: movq RAX-ARGOFFSET(%rsp),%rsi /* second arg, syscall return value */ - cmpq $0,%rsi /* is it < 0? */ - setl %al /* 1 if so, 0 if not */ + cmpq $-MAX_ERRNO,%rsi /* is it < -MAX_ERRNO? */ + setbe %al /* 1 if so, 0 if not */ movzbl %al,%edi /* zero-extend that into %edi */ - inc %edi /* first arg, 0->1(AUDITSC_SUCCESS), 1->2(AUDITSC_FAILURE) */ - call audit_syscall_exit + call __audit_syscall_exit movl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT),%edi jmp sysret_check #endif /* CONFIG_AUDITSYSCALL */ @@ -1480,62 +1480,214 @@ ENTRY(error_exit) CFI_ENDPROC END(error_exit) +/* + * Test if a given stack is an NMI stack or not. + */ + .macro test_in_nmi reg stack nmi_ret normal_ret + cmpq %\reg, \stack + ja \normal_ret + subq $EXCEPTION_STKSZ, %\reg + cmpq %\reg, \stack + jb \normal_ret + jmp \nmi_ret + .endm /* runs on exception stack */ ENTRY(nmi) INTR_FRAME PARAVIRT_ADJUST_EXCEPTION_FRAME - pushq_cfi $-1 + /* + * We allow breakpoints in NMIs. If a breakpoint occurs, then + * the iretq it performs will take us out of NMI context. + * This means that we can have nested NMIs where the next + * NMI is using the top of the stack of the previous NMI. We + * can't let it execute because the nested NMI will corrupt the + * stack of the previous NMI. NMI handlers are not re-entrant + * anyway. + * + * To handle this case we do the following: + * Check the a special location on the stack that contains + * a variable that is set when NMIs are executing. + * The interrupted task's stack is also checked to see if it + * is an NMI stack. + * If the variable is not set and the stack is not the NMI + * stack then: + * o Set the special variable on the stack + * o Copy the interrupt frame into a "saved" location on the stack + * o Copy the interrupt frame into a "copy" location on the stack + * o Continue processing the NMI + * If the variable is set or the previous stack is the NMI stack: + * o Modify the "copy" location to jump to the repeate_nmi + * o return back to the first NMI + * + * Now on exit of the first NMI, we first clear the stack variable + * The NMI stack will tell any nested NMIs at that point that it is + * nested. Then we pop the stack normally with iret, and if there was + * a nested NMI that updated the copy interrupt stack frame, a + * jump will be made to the repeat_nmi code that will handle the second + * NMI. + */ + + /* Use %rdx as out temp variable throughout */ + pushq_cfi %rdx + + /* + * Check the special variable on the stack to see if NMIs are + * executing. + */ + cmp $1, -8(%rsp) + je nested_nmi + + /* + * Now test if the previous stack was an NMI stack. + * We need the double check. We check the NMI stack to satisfy the + * race when the first NMI clears the variable before returning. + * We check the variable because the first NMI could be in a + * breakpoint routine using a breakpoint stack. + */ + lea 6*8(%rsp), %rdx + test_in_nmi rdx, 4*8(%rsp), nested_nmi, first_nmi + +nested_nmi: + /* + * Do nothing if we interrupted the fixup in repeat_nmi. + * It's about to repeat the NMI handler, so we are fine + * with ignoring this one. + */ + movq $repeat_nmi, %rdx + cmpq 8(%rsp), %rdx + ja 1f + movq $end_repeat_nmi, %rdx + cmpq 8(%rsp), %rdx + ja nested_nmi_out + +1: + /* Set up the interrupted NMIs stack to jump to repeat_nmi */ + leaq -6*8(%rsp), %rdx + movq %rdx, %rsp + CFI_ADJUST_CFA_OFFSET 6*8 + pushq_cfi $__KERNEL_DS + pushq_cfi %rdx + pushfq_cfi + pushq_cfi $__KERNEL_CS + pushq_cfi $repeat_nmi + + /* Put stack back */ + addq $(11*8), %rsp + CFI_ADJUST_CFA_OFFSET -11*8 + +nested_nmi_out: + popq_cfi %rdx + + /* No need to check faults here */ + INTERRUPT_RETURN + +first_nmi: + /* + * Because nested NMIs will use the pushed location that we + * stored in rdx, we must keep that space available. + * Here's what our stack frame will look like: + * +-------------------------+ + * | original SS | + * | original Return RSP | + * | original RFLAGS | + * | original CS | + * | original RIP | + * +-------------------------+ + * | temp storage for rdx | + * +-------------------------+ + * | NMI executing variable | + * +-------------------------+ + * | Saved SS | + * | Saved Return RSP | + * | Saved RFLAGS | + * | Saved CS | + * | Saved RIP | + * +-------------------------+ + * | copied SS | + * | copied Return RSP | + * | copied RFLAGS | + * | copied CS | + * | copied RIP | + * +-------------------------+ + * | pt_regs | + * +-------------------------+ + * + * The saved RIP is used to fix up the copied RIP that a nested + * NMI may zero out. The original stack frame and the temp storage + * is also used by nested NMIs and can not be trusted on exit. + */ + /* Set the NMI executing variable on the stack. */ + pushq_cfi $1 + + /* Copy the stack frame to the Saved frame */ + .rept 5 + pushq_cfi 6*8(%rsp) + .endr + + /* Make another copy, this one may be modified by nested NMIs */ + .rept 5 + pushq_cfi 4*8(%rsp) + .endr + + /* Do not pop rdx, nested NMIs will corrupt it */ + movq 11*8(%rsp), %rdx + + /* + * Everything below this point can be preempted by a nested + * NMI if the first NMI took an exception. Repeated NMIs + * caused by an exception and nested NMI will start here, and + * can still be preempted by another NMI. + */ +restart_nmi: + pushq_cfi $-1 /* ORIG_RAX: no syscall to restart */ subq $ORIG_RAX-R15, %rsp CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15 + /* + * Use save_paranoid to handle SWAPGS, but no need to use paranoid_exit + * as we should not be calling schedule in NMI context. + * Even with normal interrupts enabled. An NMI should not be + * setting NEED_RESCHED or anything that normal interrupts and + * exceptions might do. + */ call save_paranoid DEFAULT_FRAME 0 /* paranoidentry do_nmi, 0; without TRACE_IRQS_OFF */ movq %rsp,%rdi movq $-1,%rsi call do_nmi -#ifdef CONFIG_TRACE_IRQFLAGS - /* paranoidexit; without TRACE_IRQS_OFF */ - /* ebx: no swapgs flag */ - DISABLE_INTERRUPTS(CLBR_NONE) testl %ebx,%ebx /* swapgs needed? */ jnz nmi_restore - testl $3,CS(%rsp) - jnz nmi_userspace nmi_swapgs: SWAPGS_UNSAFE_STACK nmi_restore: RESTORE_ALL 8 + /* Clear the NMI executing stack variable */ + movq $0, 10*8(%rsp) jmp irq_return -nmi_userspace: - GET_THREAD_INFO(%rcx) - movl TI_flags(%rcx),%ebx - andl $_TIF_WORK_MASK,%ebx - jz nmi_swapgs - movq %rsp,%rdi /* &pt_regs */ - call sync_regs - movq %rax,%rsp /* switch stack for scheduling */ - testl $_TIF_NEED_RESCHED,%ebx - jnz nmi_schedule - movl %ebx,%edx /* arg3: thread flags */ - ENABLE_INTERRUPTS(CLBR_NONE) - xorl %esi,%esi /* arg2: oldset */ - movq %rsp,%rdi /* arg1: &pt_regs */ - call do_notify_resume - DISABLE_INTERRUPTS(CLBR_NONE) - jmp nmi_userspace -nmi_schedule: - ENABLE_INTERRUPTS(CLBR_ANY) - call schedule - DISABLE_INTERRUPTS(CLBR_ANY) - jmp nmi_userspace - CFI_ENDPROC -#else - jmp paranoid_exit CFI_ENDPROC -#endif END(nmi) + /* + * If an NMI hit an iret because of an exception or breakpoint, + * it can lose its NMI context, and a nested NMI may come in. + * In that case, the nested NMI will change the preempted NMI's + * stack to jump to here when it does the final iret. + */ +repeat_nmi: + INTR_FRAME + /* Update the stack variable to say we are still in NMI */ + movq $1, 5*8(%rsp) + + /* copy the saved stack back to copy stack */ + .rept 5 + pushq_cfi 4*8(%rsp) + .endr + + jmp restart_nmi + CFI_ENDPROC +end_repeat_nmi: + ENTRY(ignore_sysret) CFI_STARTPROC mov $-ENOSYS,%eax diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index e11e39478a4..40f4eb3766d 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -417,6 +417,10 @@ ENTRY(phys_base) ENTRY(idt_table) .skip IDT_ENTRIES * 16 + .align L1_CACHE_BYTES +ENTRY(nmi_idt_table) + .skip IDT_ENTRIES * 16 + __PAGE_ALIGNED_BSS .align PAGE_SIZE ENTRY(empty_zero_page) diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index e88f37b58dd..47acaf31916 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -405,9 +405,108 @@ static notrace __kprobes void default_do_nmi(struct pt_regs *regs) unknown_nmi_error(reason, regs); } +/* + * NMIs can hit breakpoints which will cause it to lose its + * NMI context with the CPU when the breakpoint does an iret. + */ +#ifdef CONFIG_X86_32 +/* + * For i386, NMIs use the same stack as the kernel, and we can + * add a workaround to the iret problem in C. Simply have 3 states + * the NMI can be in. + * + * 1) not running + * 2) executing + * 3) latched + * + * When no NMI is in progress, it is in the "not running" state. + * When an NMI comes in, it goes into the "executing" state. + * Normally, if another NMI is triggered, it does not interrupt + * the running NMI and the HW will simply latch it so that when + * the first NMI finishes, it will restart the second NMI. + * (Note, the latch is binary, thus multiple NMIs triggering, + * when one is running, are ignored. Only one NMI is restarted.) + * + * If an NMI hits a breakpoint that executes an iret, another + * NMI can preempt it. We do not want to allow this new NMI + * to run, but we want to execute it when the first one finishes. + * We set the state to "latched", and the first NMI will perform + * an cmpxchg on the state, and if it doesn't successfully + * reset the state to "not running" it will restart the next + * NMI. + */ +enum nmi_states { + NMI_NOT_RUNNING, + NMI_EXECUTING, + NMI_LATCHED, +}; +static DEFINE_PER_CPU(enum nmi_states, nmi_state); + +#define nmi_nesting_preprocess(regs) \ + do { \ + if (__get_cpu_var(nmi_state) != NMI_NOT_RUNNING) { \ + __get_cpu_var(nmi_state) = NMI_LATCHED; \ + return; \ + } \ + nmi_restart: \ + __get_cpu_var(nmi_state) = NMI_EXECUTING; \ + } while (0) + +#define nmi_nesting_postprocess() \ + do { \ + if (cmpxchg(&__get_cpu_var(nmi_state), \ + NMI_EXECUTING, NMI_NOT_RUNNING) != NMI_EXECUTING) \ + goto nmi_restart; \ + } while (0) +#else /* x86_64 */ +/* + * In x86_64 things are a bit more difficult. This has the same problem + * where an NMI hitting a breakpoint that calls iret will remove the + * NMI context, allowing a nested NMI to enter. What makes this more + * difficult is that both NMIs and breakpoints have their own stack. + * When a new NMI or breakpoint is executed, the stack is set to a fixed + * point. If an NMI is nested, it will have its stack set at that same + * fixed address that the first NMI had, and will start corrupting the + * stack. This is handled in entry_64.S, but the same problem exists with + * the breakpoint stack. + * + * If a breakpoint is being processed, and the debug stack is being used, + * if an NMI comes in and also hits a breakpoint, the stack pointer + * will be set to the same fixed address as the breakpoint that was + * interrupted, causing that stack to be corrupted. To handle this case, + * check if the stack that was interrupted is the debug stack, and if + * so, change the IDT so that new breakpoints will use the current stack + * and not switch to the fixed address. On return of the NMI, switch back + * to the original IDT. + */ +static DEFINE_PER_CPU(int, update_debug_stack); + +static inline void nmi_nesting_preprocess(struct pt_regs *regs) +{ + /* + * If we interrupted a breakpoint, it is possible that + * the nmi handler will have breakpoints too. We need to + * change the IDT such that breakpoints that happen here + * continue to use the NMI stack. + */ + if (unlikely(is_debug_stack(regs->sp))) { + debug_stack_set_zero(); + __get_cpu_var(update_debug_stack) = 1; + } +} + +static inline void nmi_nesting_postprocess(void) +{ + if (unlikely(__get_cpu_var(update_debug_stack))) + debug_stack_reset(); +} +#endif + dotraplinkage notrace __kprobes void do_nmi(struct pt_regs *regs, long error_code) { + nmi_nesting_preprocess(regs); + nmi_enter(); inc_irq_stat(__nmi_count); @@ -416,6 +515,9 @@ do_nmi(struct pt_regs *regs, long error_code) default_do_nmi(regs); nmi_exit(); + + /* On i386, may loop back to preprocess */ + nmi_nesting_postprocess(); } void stop_nmi(void) diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 89a04c7b5bb..50267386b76 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -1392,20 +1392,18 @@ long syscall_trace_enter(struct pt_regs *regs) if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT))) trace_sys_enter(regs, regs->orig_ax); - if (unlikely(current->audit_context)) { - if (IS_IA32) - audit_syscall_entry(AUDIT_ARCH_I386, - regs->orig_ax, - regs->bx, regs->cx, - regs->dx, regs->si); + if (IS_IA32) + audit_syscall_entry(AUDIT_ARCH_I386, + regs->orig_ax, + regs->bx, regs->cx, + regs->dx, regs->si); #ifdef CONFIG_X86_64 - else - audit_syscall_entry(AUDIT_ARCH_X86_64, - regs->orig_ax, - regs->di, regs->si, - regs->dx, regs->r10); + else + audit_syscall_entry(AUDIT_ARCH_X86_64, + regs->orig_ax, + regs->di, regs->si, + regs->dx, regs->r10); #endif - } return ret ?: regs->orig_ax; } @@ -1414,8 +1412,7 @@ void syscall_trace_leave(struct pt_regs *regs) { bool step; - if (unlikely(current->audit_context)) - audit_syscall_exit(AUDITSC_RESULT(regs->ax), regs->ax); + audit_syscall_exit(regs); if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT))) trace_sys_exit(regs, regs->ax); diff --git a/arch/x86/kernel/syscall_32.c b/arch/x86/kernel/syscall_32.c new file mode 100644 index 00000000000..147fcd4941c --- /dev/null +++ b/arch/x86/kernel/syscall_32.c @@ -0,0 +1,25 @@ +/* System call table for i386. */ + +#include <linux/linkage.h> +#include <linux/sys.h> +#include <linux/cache.h> +#include <asm/asm-offsets.h> + +#define __SYSCALL_I386(nr, sym, compat) extern asmlinkage void sym(void) ; +#include <asm/syscalls_32.h> +#undef __SYSCALL_I386 + +#define __SYSCALL_I386(nr, sym, compat) [nr] = sym, + +typedef asmlinkage void (*sys_call_ptr_t)(void); + +extern asmlinkage void sys_ni_syscall(void); + +const sys_call_ptr_t sys_call_table[__NR_syscall_max+1] = { + /* + * Smells like a compiler bug -- it doesn't work + * when the & below is removed. + */ + [0 ... __NR_syscall_max] = &sys_ni_syscall, +#include <asm/syscalls_32.h> +}; diff --git a/arch/x86/kernel/syscall_64.c b/arch/x86/kernel/syscall_64.c index de87d600829..7ac7943be02 100644 --- a/arch/x86/kernel/syscall_64.c +++ b/arch/x86/kernel/syscall_64.c @@ -5,15 +5,11 @@ #include <linux/cache.h> #include <asm/asm-offsets.h> -#define __NO_STUBS +#define __SYSCALL_64(nr, sym, compat) extern asmlinkage void sym(void) ; +#include <asm/syscalls_64.h> +#undef __SYSCALL_64 -#define __SYSCALL(nr, sym) extern asmlinkage void sym(void) ; -#undef _ASM_X86_UNISTD_64_H -#include <asm/unistd_64.h> - -#undef __SYSCALL -#define __SYSCALL(nr, sym) [nr] = sym, -#undef _ASM_X86_UNISTD_64_H +#define __SYSCALL_64(nr, sym, compat) [nr] = sym, typedef void (*sys_call_ptr_t)(void); @@ -21,9 +17,9 @@ extern void sys_ni_syscall(void); const sys_call_ptr_t sys_call_table[__NR_syscall_max+1] = { /* - *Smells like a like a compiler bug -- it doesn't work - *when the & below is removed. - */ + * Smells like a compiler bug -- it doesn't work + * when the & below is removed. + */ [0 ... __NR_syscall_max] = &sys_ni_syscall, -#include <asm/unistd_64.h> +#include <asm/syscalls_64.h> }; diff --git a/arch/x86/kernel/syscall_table_32.S b/arch/x86/kernel/syscall_table_32.S deleted file mode 100644 index 9a0e3129392..00000000000 --- a/arch/x86/kernel/syscall_table_32.S +++ /dev/null @@ -1,350 +0,0 @@ -ENTRY(sys_call_table) - .long sys_restart_syscall /* 0 - old "setup()" system call, used for restarting */ - .long sys_exit - .long ptregs_fork - .long sys_read - .long sys_write - .long sys_open /* 5 */ - .long sys_close - .long sys_waitpid - .long sys_creat - .long sys_link - .long sys_unlink /* 10 */ - .long ptregs_execve - .long sys_chdir - .long sys_time - .long sys_mknod - .long sys_chmod /* 15 */ - .long sys_lchown16 - .long sys_ni_syscall /* old break syscall holder */ - .long sys_stat - .long sys_lseek - .long sys_getpid /* 20 */ - .long sys_mount - .long sys_oldumount - .long sys_setuid16 - .long sys_getuid16 - .long sys_stime /* 25 */ - .long sys_ptrace - .long sys_alarm - .long sys_fstat - .long sys_pause - .long sys_utime /* 30 */ - .long sys_ni_syscall /* old stty syscall holder */ - .long sys_ni_syscall /* old gtty syscall holder */ - .long sys_access - .long sys_nice - .long sys_ni_syscall /* 35 - old ftime syscall holder */ - .long sys_sync - .long sys_kill - .long sys_rename - .long sys_mkdir - .long sys_rmdir /* 40 */ - .long sys_dup - .long sys_pipe - .long sys_times - .long sys_ni_syscall /* old prof syscall holder */ - .long sys_brk /* 45 */ - .long sys_setgid16 - .long sys_getgid16 - .long sys_signal - .long sys_geteuid16 - .long sys_getegid16 /* 50 */ - .long sys_acct - .long sys_umount /* recycled never used phys() */ - .long sys_ni_syscall /* old lock syscall holder */ - .long sys_ioctl - .long sys_fcntl /* 55 */ - .long sys_ni_syscall /* old mpx syscall holder */ - .long sys_setpgid - .long sys_ni_syscall /* old ulimit syscall holder */ - .long sys_olduname - .long sys_umask /* 60 */ - .long sys_chroot - .long sys_ustat - .long sys_dup2 - .long sys_getppid - .long sys_getpgrp /* 65 */ - .long sys_setsid - .long sys_sigaction - .long sys_sgetmask - .long sys_ssetmask - .long sys_setreuid16 /* 70 */ - .long sys_setregid16 - .long sys_sigsuspend - .long sys_sigpending - .long sys_sethostname - .long sys_setrlimit /* 75 */ - .long sys_old_getrlimit - .long sys_getrusage - .long sys_gettimeofday - .long sys_settimeofday - .long sys_getgroups16 /* 80 */ - .long sys_setgroups16 - .long sys_old_select - .long sys_symlink - .long sys_lstat - .long sys_readlink /* 85 */ - .long sys_uselib - .long sys_swapon - .long sys_reboot - .long sys_old_readdir - .long sys_old_mmap /* 90 */ - .long sys_munmap - .long sys_truncate - .long sys_ftruncate - .long sys_fchmod - .long sys_fchown16 /* 95 */ - .long sys_getpriority - .long sys_setpriority - .long sys_ni_syscall /* old profil syscall holder */ - .long sys_statfs - .long sys_fstatfs /* 100 */ - .long sys_ioperm - .long sys_socketcall - .long sys_syslog - .long sys_setitimer - .long sys_getitimer /* 105 */ - .long sys_newstat - .long sys_newlstat - .long sys_newfstat - .long sys_uname - .long ptregs_iopl /* 110 */ - .long sys_vhangup - .long sys_ni_syscall /* old "idle" system call */ - .long ptregs_vm86old - .long sys_wait4 - .long sys_swapoff /* 115 */ - .long sys_sysinfo - .long sys_ipc - .long sys_fsync - .long ptregs_sigreturn - .long ptregs_clone /* 120 */ - .long sys_setdomainname - .long sys_newuname - .long sys_modify_ldt - .long sys_adjtimex - .long sys_mprotect /* 125 */ - .long sys_sigprocmask - .long sys_ni_syscall /* old "create_module" */ - .long sys_init_module - .long sys_delete_module - .long sys_ni_syscall /* 130: old "get_kernel_syms" */ - .long sys_quotactl - .long sys_getpgid - .long sys_fchdir - .long sys_bdflush - .long sys_sysfs /* 135 */ - .long sys_personality - .long sys_ni_syscall /* reserved for afs_syscall */ - .long sys_setfsuid16 - .long sys_setfsgid16 - .long sys_llseek /* 140 */ - .long sys_getdents - .long sys_select - .long sys_flock - .long sys_msync - .long sys_readv /* 145 */ - .long sys_writev - .long sys_getsid - .long sys_fdatasync - .long sys_sysctl - .long sys_mlock /* 150 */ - .long sys_munlock - .long sys_mlockall - .long sys_munlockall - .long sys_sched_setparam - .long sys_sched_getparam /* 155 */ - .long sys_sched_setscheduler - .long sys_sched_getscheduler - .long sys_sched_yield - .long sys_sched_get_priority_max - .long sys_sched_get_priority_min /* 160 */ - .long sys_sched_rr_get_interval - .long sys_nanosleep - .long sys_mremap - .long sys_setresuid16 - .long sys_getresuid16 /* 165 */ - .long ptregs_vm86 - .long sys_ni_syscall /* Old sys_query_module */ - .long sys_poll - .long sys_ni_syscall /* Old nfsservctl */ - .long sys_setresgid16 /* 170 */ - .long sys_getresgid16 - .long sys_prctl - .long ptregs_rt_sigreturn - .long sys_rt_sigaction - .long sys_rt_sigprocmask /* 175 */ - .long sys_rt_sigpending - .long sys_rt_sigtimedwait - .long sys_rt_sigqueueinfo - .long sys_rt_sigsuspend - .long sys_pread64 /* 180 */ - .long sys_pwrite64 - .long sys_chown16 - .long sys_getcwd - .long sys_capget - .long sys_capset /* 185 */ - .long ptregs_sigaltstack - .long sys_sendfile - .long sys_ni_syscall /* reserved for streams1 */ - .long sys_ni_syscall /* reserved for streams2 */ - .long ptregs_vfork /* 190 */ - .long sys_getrlimit - .long sys_mmap_pgoff - .long sys_truncate64 - .long sys_ftruncate64 - .long sys_stat64 /* 195 */ - .long sys_lstat64 - .long sys_fstat64 - .long sys_lchown - .long sys_getuid - .long sys_getgid /* 200 */ - .long sys_geteuid - .long sys_getegid - .long sys_setreuid - .long sys_setregid - .long sys_getgroups /* 205 */ - .long sys_setgroups - .long sys_fchown - .long sys_setresuid - .long sys_getresuid - .long sys_setresgid /* 210 */ - .long sys_getresgid - .long sys_chown - .long sys_setuid - .long sys_setgid - .long sys_setfsuid /* 215 */ - .long sys_setfsgid - .long sys_pivot_root - .long sys_mincore - .long sys_madvise - .long sys_getdents64 /* 220 */ - .long sys_fcntl64 - .long sys_ni_syscall /* reserved for TUX */ - .long sys_ni_syscall - .long sys_gettid - .long sys_readahead /* 225 */ - .long sys_setxattr - .long sys_lsetxattr - .long sys_fsetxattr - .long sys_getxattr - .long sys_lgetxattr /* 230 */ - .long sys_fgetxattr - .long sys_listxattr - .long sys_llistxattr - .long sys_flistxattr - .long sys_removexattr /* 235 */ - .long sys_lremovexattr - .long sys_fremovexattr - .long sys_tkill - .long sys_sendfile64 - .long sys_futex /* 240 */ - .long sys_sched_setaffinity - .long sys_sched_getaffinity - .long sys_set_thread_area - .long sys_get_thread_area - .long sys_io_setup /* 245 */ - .long sys_io_destroy - .long sys_io_getevents - .long sys_io_submit - .long sys_io_cancel - .long sys_fadvise64 /* 250 */ - .long sys_ni_syscall - .long sys_exit_group - .long sys_lookup_dcookie - .long sys_epoll_create - .long sys_epoll_ctl /* 255 */ - .long sys_epoll_wait - .long sys_remap_file_pages - .long sys_set_tid_address - .long sys_timer_create - .long sys_timer_settime /* 260 */ - .long sys_timer_gettime - .long sys_timer_getoverrun - .long sys_timer_delete - .long sys_clock_settime - .long sys_clock_gettime /* 265 */ - .long sys_clock_getres - .long sys_clock_nanosleep - .long sys_statfs64 - .long sys_fstatfs64 - .long sys_tgkill /* 270 */ - .long sys_utimes - .long sys_fadvise64_64 - .long sys_ni_syscall /* sys_vserver */ - .long sys_mbind - .long sys_get_mempolicy - .long sys_set_mempolicy - .long sys_mq_open - .long sys_mq_unlink - .long sys_mq_timedsend - .long sys_mq_timedreceive /* 280 */ - .long sys_mq_notify - .long sys_mq_getsetattr - .long sys_kexec_load - .long sys_waitid - .long sys_ni_syscall /* 285 */ /* available */ - .long sys_add_key - .long sys_request_key - .long sys_keyctl - .long sys_ioprio_set - .long sys_ioprio_get /* 290 */ - .long sys_inotify_init - .long sys_inotify_add_watch - .long sys_inotify_rm_watch - .long sys_migrate_pages - .long sys_openat /* 295 */ - .long sys_mkdirat - .long sys_mknodat - .long sys_fchownat - .long sys_futimesat - .long sys_fstatat64 /* 300 */ - .long sys_unlinkat - .long sys_renameat - .long sys_linkat - .long sys_symlinkat - .long sys_readlinkat /* 305 */ - .long sys_fchmodat - .long sys_faccessat - .long sys_pselect6 - .long sys_ppoll - .long sys_unshare /* 310 */ - .long sys_set_robust_list - .long sys_get_robust_list - .long sys_splice - .long sys_sync_file_range - .long sys_tee /* 315 */ - .long sys_vmsplice - .long sys_move_pages - .long sys_getcpu - .long sys_epoll_pwait - .long sys_utimensat /* 320 */ - .long sys_signalfd - .long sys_timerfd_create - .long sys_eventfd - .long sys_fallocate - .long sys_timerfd_settime /* 325 */ - .long sys_timerfd_gettime - .long sys_signalfd4 - .long sys_eventfd2 - .long sys_epoll_create1 - .long sys_dup3 /* 330 */ - .long sys_pipe2 - .long sys_inotify_init1 - .long sys_preadv - .long sys_pwritev - .long sys_rt_tgsigqueueinfo /* 335 */ - .long sys_perf_event_open - .long sys_recvmmsg - .long sys_fanotify_init - .long sys_fanotify_mark - .long sys_prlimit64 /* 340 */ - .long sys_name_to_handle_at - .long sys_open_by_handle_at - .long sys_clock_adjtime - .long sys_syncfs - .long sys_sendmmsg /* 345 */ - .long sys_setns - .long sys_process_vm_readv - .long sys_process_vm_writev diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index fa1191fb679..482ec3af206 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -311,9 +311,15 @@ dotraplinkage void __kprobes do_int3(struct pt_regs *regs, long error_code) == NOTIFY_STOP) return; + /* + * Let others (NMI) know that the debug stack is in use + * as we may switch to the interrupt stack. + */ + debug_stack_usage_inc(); preempt_conditional_sti(regs); do_trap(3, SIGTRAP, "int3", regs, error_code, NULL); preempt_conditional_cli(regs); + debug_stack_usage_dec(); } #ifdef CONFIG_X86_64 @@ -406,6 +412,12 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code) SIGTRAP) == NOTIFY_STOP) return; + /* + * Let others (NMI) know that the debug stack is in use + * as we may switch to the interrupt stack. + */ + debug_stack_usage_inc(); + /* It's safe to allow irq's after DR6 has been saved */ preempt_conditional_sti(regs); @@ -413,6 +425,7 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code) handle_vm86_trap((struct kernel_vm86_regs *) regs, error_code, 1); preempt_conditional_cli(regs); + debug_stack_usage_dec(); return; } @@ -432,6 +445,7 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code) if (tsk->thread.debugreg6 & (DR_STEP | DR_TRAP_BITS) || user_icebp) send_sigtrap(tsk, regs, error_code, si_code); preempt_conditional_cli(regs); + debug_stack_usage_dec(); return; } @@ -718,4 +732,10 @@ void __init trap_init(void) cpu_init(); x86_init.irqs.trap_init(); + +#ifdef CONFIG_X86_64 + memcpy(&nmi_idt_table, &idt_table, IDT_ENTRIES * 16); + set_nmi_gate(1, &debug); + set_nmi_gate(3, &int3); +#endif } diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index c0dd5b60374..a62c201c97e 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -290,14 +290,15 @@ static inline int pit_verify_msb(unsigned char val) static inline int pit_expect_msb(unsigned char val, u64 *tscp, unsigned long *deltap) { int count; - u64 tsc = 0; + u64 tsc = 0, prev_tsc = 0; for (count = 0; count < 50000; count++) { if (!pit_verify_msb(val)) break; + prev_tsc = tsc; tsc = get_cycles(); } - *deltap = get_cycles() - tsc; + *deltap = get_cycles() - prev_tsc; *tscp = tsc; /* @@ -311,9 +312,9 @@ static inline int pit_expect_msb(unsigned char val, u64 *tscp, unsigned long *de * How many MSB values do we want to see? We aim for * a maximum error rate of 500ppm (in practice the * real error is much smaller), but refuse to spend - * more than 25ms on it. + * more than 50ms on it. */ -#define MAX_QUICK_PIT_MS 25 +#define MAX_QUICK_PIT_MS 50 #define MAX_QUICK_PIT_ITERATIONS (MAX_QUICK_PIT_MS * PIT_TICK_RATE / 1000 / 256) static unsigned long quick_pit_calibrate(void) @@ -383,15 +384,12 @@ success: * * As a result, we can depend on there not being * any odd delays anywhere, and the TSC reads are - * reliable (within the error). We also adjust the - * delta to the middle of the error bars, just - * because it looks nicer. + * reliable (within the error). * * kHz = ticks / time-in-seconds / 1000; * kHz = (t2 - t1) / (I * 256 / PIT_TICK_RATE) / 1000 * kHz = ((t2 - t1) * PIT_TICK_RATE) / (I * 256 * 1000) */ - delta += (long)(d2 - d1)/2; delta *= PIT_TICK_RATE; do_div(delta, i*256*1000); printk("Fast TSC calibration using PIT\n"); diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index 863f8753ab0..b466cab5ba1 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -335,9 +335,11 @@ static void do_sys_vm86(struct kernel_vm86_struct *info, struct task_struct *tsk if (info->flags & VM86_SCREEN_BITMAP) mark_screen_rdonly(tsk->mm); - /*call audit_syscall_exit since we do not exit via the normal paths */ + /*call __audit_syscall_exit since we do not exit via the normal paths */ +#ifdef CONFIG_AUDITSYSCALL if (unlikely(current->audit_context)) - audit_syscall_exit(AUDITSC_RESULT(0), 0); + __audit_syscall_exit(1, 0); +#endif __asm__ __volatile__( "movl %0,%%esp\n\t" diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 2a2a9b40db1..224b02c3cda 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -74,7 +74,7 @@ enum { #endif #ifdef MMU_DEBUG -static int dbg = 0; +static bool dbg = 0; module_param(dbg, bool, 0644); #endif diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 906a7e84200..d29216c462b 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -51,29 +51,29 @@ MODULE_AUTHOR("Qumranet"); MODULE_LICENSE("GPL"); -static int __read_mostly enable_vpid = 1; +static bool __read_mostly enable_vpid = 1; module_param_named(vpid, enable_vpid, bool, 0444); -static int __read_mostly flexpriority_enabled = 1; +static bool __read_mostly flexpriority_enabled = 1; module_param_named(flexpriority, flexpriority_enabled, bool, S_IRUGO); -static int __read_mostly enable_ept = 1; +static bool __read_mostly enable_ept = 1; module_param_named(ept, enable_ept, bool, S_IRUGO); -static int __read_mostly enable_unrestricted_guest = 1; +static bool __read_mostly enable_unrestricted_guest = 1; module_param_named(unrestricted_guest, enable_unrestricted_guest, bool, S_IRUGO); -static int __read_mostly emulate_invalid_guest_state = 0; +static bool __read_mostly emulate_invalid_guest_state = 0; module_param(emulate_invalid_guest_state, bool, S_IRUGO); -static int __read_mostly vmm_exclusive = 1; +static bool __read_mostly vmm_exclusive = 1; module_param(vmm_exclusive, bool, S_IRUGO); -static int __read_mostly yield_on_hlt = 1; +static bool __read_mostly yield_on_hlt = 1; module_param(yield_on_hlt, bool, S_IRUGO); -static int __read_mostly fasteoi = 1; +static bool __read_mostly fasteoi = 1; module_param(fasteoi, bool, S_IRUGO); /* @@ -81,7 +81,7 @@ module_param(fasteoi, bool, S_IRUGO); * VMX and be a hypervisor for its own guests. If nested=0, guests may not * use VMX instructions. */ -static int __read_mostly nested = 0; +static bool __read_mostly nested = 0; module_param(nested, bool, S_IRUGO); #define KVM_GUEST_CR0_MASK_UNRESTRICTED_GUEST \ diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 1171def5f96..14d6cadc4ba 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -88,8 +88,8 @@ static void process_nmi(struct kvm_vcpu *vcpu); struct kvm_x86_ops *kvm_x86_ops; EXPORT_SYMBOL_GPL(kvm_x86_ops); -int ignore_msrs = 0; -module_param_named(ignore_msrs, ignore_msrs, bool, S_IRUGO | S_IWUSR); +static bool ignore_msrs = 0; +module_param(ignore_msrs, bool, S_IRUGO | S_IWUSR); bool kvm_has_tsc_control; EXPORT_SYMBOL_GPL(kvm_has_tsc_control); diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt index 5b83c51c12e..81913790442 100644 --- a/arch/x86/lib/x86-opcode-map.txt +++ b/arch/x86/lib/x86-opcode-map.txt @@ -219,7 +219,9 @@ ab: STOS/W/D/Q Yv,rAX ac: LODS/B AL,Xb ad: LODS/W/D/Q rAX,Xv ae: SCAS/B AL,Yb -af: SCAS/W/D/Q rAX,Xv +# Note: The May 2011 Intel manual shows Xv for the second parameter of the +# next instruction but Yv is correct +af: SCAS/W/D/Q rAX,Yv # 0xb0 - 0xbf b0: MOV AL/R8L,Ib b1: MOV CL/R9L,Ib @@ -729,8 +731,8 @@ de: VAESDEC Vdq,Hdq,Wdq (66),(v1) df: VAESDECLAST Vdq,Hdq,Wdq (66),(v1) f0: MOVBE Gy,My | MOVBE Gw,Mw (66) | CRC32 Gd,Eb (F2) f1: MOVBE My,Gy | MOVBE Mw,Gw (66) | CRC32 Gd,Ey (F2) -f3: ANDN Gy,By,Ey (v) -f4: Grp17 (1A) +f2: ANDN Gy,By,Ey (v) +f3: Grp17 (1A) f5: BZHI Gy,Ey,By (v) | PEXT Gy,By,Ey (F3),(v) | PDEP Gy,By,Ey (F2),(v) f6: MULX By,Gy,rDX,Ey (F2),(v) f7: BEXTR Gy,Ey,By (v) | SHLX Gy,Ey,By (66),(v) | SARX Gy,Ey,By (F3),(v) | SHRX Gy,Ey,By (F2),(v) diff --git a/arch/x86/mm/mmio-mod.c b/arch/x86/mm/mmio-mod.c index de54b9b278a..dc0b727742f 100644 --- a/arch/x86/mm/mmio-mod.c +++ b/arch/x86/mm/mmio-mod.c @@ -75,8 +75,8 @@ static LIST_HEAD(trace_list); /* struct remap_trace */ /* module parameters */ static unsigned long filter_offset; -static int nommiotrace; -static int trace_pc; +static bool nommiotrace; +static bool trace_pc; module_param(filter_offset, ulong, 0); module_param(nommiotrace, bool, 0); diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c index fd61b3fb734..1c1c4f46a7c 100644 --- a/arch/x86/mm/srat.c +++ b/arch/x86/mm/srat.c @@ -109,6 +109,8 @@ acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa) if ((pa->flags & ACPI_SRAT_CPU_ENABLED) == 0) return; pxm = pa->proximity_domain_lo; + if (acpi_srat_revision >= 2) + pxm |= *((unsigned int*)pa->proximity_domain_hi) << 8; node = setup_node(pxm); if (node < 0) { printk(KERN_ERR "SRAT: Too many proximity domains %x\n", pxm); @@ -160,6 +162,8 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma) start = ma->base_address; end = start + ma->length; pxm = ma->proximity_domain; + if (acpi_srat_revision <= 1) + pxm &= 0xff; node = setup_node(pxm); if (node < 0) { printk(KERN_ERR "SRAT: Too many proximity domains.\n"); diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 7b65f752c5f..7c1b765ecc5 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -151,17 +151,18 @@ void bpf_jit_compile(struct sk_filter *fp) cleanup_addr = proglen; /* epilogue address */ for (pass = 0; pass < 10; pass++) { + u8 seen_or_pass0 = (pass == 0) ? (SEEN_XREG | SEEN_DATAREF | SEEN_MEM) : seen; /* no prologue/epilogue for trivial filters (RET something) */ proglen = 0; prog = temp; - if (seen) { + if (seen_or_pass0) { EMIT4(0x55, 0x48, 0x89, 0xe5); /* push %rbp; mov %rsp,%rbp */ EMIT4(0x48, 0x83, 0xec, 96); /* subq $96,%rsp */ /* note : must save %rbx in case bpf_error is hit */ - if (seen & (SEEN_XREG | SEEN_DATAREF)) + if (seen_or_pass0 & (SEEN_XREG | SEEN_DATAREF)) EMIT4(0x48, 0x89, 0x5d, 0xf8); /* mov %rbx, -8(%rbp) */ - if (seen & SEEN_XREG) + if (seen_or_pass0 & SEEN_XREG) CLEAR_X(); /* make sure we dont leek kernel memory */ /* @@ -170,7 +171,7 @@ void bpf_jit_compile(struct sk_filter *fp) * r9 = skb->len - skb->data_len * r8 = skb->data */ - if (seen & SEEN_DATAREF) { + if (seen_or_pass0 & SEEN_DATAREF) { if (offsetof(struct sk_buff, len) <= 127) /* mov off8(%rdi),%r9d */ EMIT4(0x44, 0x8b, 0x4f, offsetof(struct sk_buff, len)); @@ -260,9 +261,14 @@ void bpf_jit_compile(struct sk_filter *fp) case BPF_S_ALU_DIV_X: /* A /= X; */ seen |= SEEN_XREG; EMIT2(0x85, 0xdb); /* test %ebx,%ebx */ - if (pc_ret0 != -1) - EMIT_COND_JMP(X86_JE, addrs[pc_ret0] - (addrs[i] - 4)); - else { + if (pc_ret0 > 0) { + /* addrs[pc_ret0 - 1] is start address of target + * (addrs[i] - 4) is the address following this jmp + * ("xor %edx,%edx; div %ebx" being 4 bytes long) + */ + EMIT_COND_JMP(X86_JE, addrs[pc_ret0 - 1] - + (addrs[i] - 4)); + } else { EMIT_COND_JMP(X86_JNE, 2 + 5); CLEAR_A(); EMIT1_off32(0xe9, cleanup_addr - (addrs[i] - 4)); /* jmp .+off32 */ @@ -335,12 +341,12 @@ void bpf_jit_compile(struct sk_filter *fp) } /* fallinto */ case BPF_S_RET_A: - if (seen) { + if (seen_or_pass0) { if (i != flen - 1) { EMIT_JMP(cleanup_addr - addrs[i]); break; } - if (seen & SEEN_XREG) + if (seen_or_pass0 & SEEN_XREG) EMIT4(0x48, 0x8b, 0x5d, 0xf8); /* mov -8(%rbp),%rbx */ EMIT1(0xc9); /* leaveq */ } @@ -483,8 +489,9 @@ common_load: seen |= SEEN_DATAREF; goto common_load; case BPF_S_LDX_B_MSH: if ((int)K < 0) { - if (pc_ret0 != -1) { - EMIT_JMP(addrs[pc_ret0] - addrs[i]); + if (pc_ret0 > 0) { + /* addrs[pc_ret0 - 1] is the start address */ + EMIT_JMP(addrs[pc_ret0 - 1] - addrs[i]); break; } CLEAR_A(); @@ -599,13 +606,14 @@ cond_branch: f_offset = addrs[i + filter[i].jf] - addrs[i]; * use it to give the cleanup instruction(s) addr */ cleanup_addr = proglen - 1; /* ret */ - if (seen) + if (seen_or_pass0) cleanup_addr -= 1; /* leaveq */ - if (seen & SEEN_XREG) + if (seen_or_pass0 & SEEN_XREG) cleanup_addr -= 4; /* mov -8(%rbp),%rbx */ if (image) { - WARN_ON(proglen != oldproglen); + if (proglen != oldproglen) + pr_err("bpb_jit_compile proglen=%u != oldproglen=%u\n", proglen, oldproglen); break; } if (proglen == oldproglen) { diff --git a/arch/x86/platform/geode/alix.c b/arch/x86/platform/geode/alix.c index ca1973699d3..dc5f1d32ace 100644 --- a/arch/x86/platform/geode/alix.c +++ b/arch/x86/platform/geode/alix.c @@ -27,7 +27,7 @@ #include <asm/geode.h> -static int force = 0; +static bool force = 0; module_param(force, bool, 0444); /* FIXME: Award bios is not automatically detected as Alix platform */ MODULE_PARM_DESC(force, "Force detection as ALIX.2/ALIX.3 platform"); diff --git a/arch/x86/platform/iris/iris.c b/arch/x86/platform/iris/iris.c index 1ba7f5ed8c9..5917eb56b31 100644 --- a/arch/x86/platform/iris/iris.c +++ b/arch/x86/platform/iris/iris.c @@ -42,7 +42,7 @@ MODULE_AUTHOR("Sébastien Hinderer <Sebastien.Hinderer@ens-lyon.org>"); MODULE_DESCRIPTION("A power_off handler for Iris devices from EuroBraille"); MODULE_SUPPORTED_DEVICE("Eurobraille/Iris"); -static int force; +static bool force; module_param(force, bool, 0); MODULE_PARM_DESC(force, "Set to one to force poweroff handler installation."); diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c index 5b552198f77..9be4cff00a2 100644 --- a/arch/x86/platform/uv/tlb_uv.c +++ b/arch/x86/platform/uv/tlb_uv.c @@ -157,13 +157,14 @@ static int __init uvhub_to_first_apicid(int uvhub) * clear of the Timeout bit (as well) will free the resource. No reply will * be sent (the hardware will only do one reply per message). */ -static void reply_to_message(struct msg_desc *mdp, struct bau_control *bcp) +static void reply_to_message(struct msg_desc *mdp, struct bau_control *bcp, + int do_acknowledge) { unsigned long dw; struct bau_pq_entry *msg; msg = mdp->msg; - if (!msg->canceled) { + if (!msg->canceled && do_acknowledge) { dw = (msg->swack_vec << UV_SW_ACK_NPENDING) | msg->swack_vec; write_mmr_sw_ack(dw); } @@ -212,8 +213,8 @@ static void bau_process_retry_msg(struct msg_desc *mdp, if (mmr & (msg_res << UV_SW_ACK_NPENDING)) { unsigned long mr; /* - * is the resource timed out? - * make everyone ignore the cancelled message. + * Is the resource timed out? + * Make everyone ignore the cancelled message. */ msg2->canceled = 1; stat->d_canceled++; @@ -231,8 +232,8 @@ static void bau_process_retry_msg(struct msg_desc *mdp, * Do all the things a cpu should do for a TLB shootdown message. * Other cpu's may come here at the same time for this message. */ -static void bau_process_message(struct msg_desc *mdp, - struct bau_control *bcp) +static void bau_process_message(struct msg_desc *mdp, struct bau_control *bcp, + int do_acknowledge) { short socket_ack_count = 0; short *sp; @@ -284,8 +285,9 @@ static void bau_process_message(struct msg_desc *mdp, if (msg_ack_count == bcp->cpus_in_uvhub) { /* * All cpus in uvhub saw it; reply + * (unless we are in the UV2 workaround) */ - reply_to_message(mdp, bcp); + reply_to_message(mdp, bcp, do_acknowledge); } } @@ -491,27 +493,138 @@ static int uv1_wait_completion(struct bau_desc *bau_desc, /* * UV2 has an extra bit of status in the ACTIVATION_STATUS_2 register. */ -static unsigned long uv2_read_status(unsigned long offset, int rshft, int cpu) +static unsigned long uv2_read_status(unsigned long offset, int rshft, int desc) { unsigned long descriptor_status; unsigned long descriptor_status2; descriptor_status = ((read_lmmr(offset) >> rshft) & UV_ACT_STATUS_MASK); - descriptor_status2 = (read_mmr_uv2_status() >> cpu) & 0x1UL; + descriptor_status2 = (read_mmr_uv2_status() >> desc) & 0x1UL; descriptor_status = (descriptor_status << 1) | descriptor_status2; return descriptor_status; } +/* + * Return whether the status of the descriptor that is normally used for this + * cpu (the one indexed by its hub-relative cpu number) is busy. + * The status of the original 32 descriptors is always reflected in the 64 + * bits of UVH_LB_BAU_SB_ACTIVATION_STATUS_0. + * The bit provided by the activation_status_2 register is irrelevant to + * the status if it is only being tested for busy or not busy. + */ +int normal_busy(struct bau_control *bcp) +{ + int cpu = bcp->uvhub_cpu; + int mmr_offset; + int right_shift; + + mmr_offset = UVH_LB_BAU_SB_ACTIVATION_STATUS_0; + right_shift = cpu * UV_ACT_STATUS_SIZE; + return (((((read_lmmr(mmr_offset) >> right_shift) & + UV_ACT_STATUS_MASK)) << 1) == UV2H_DESC_BUSY); +} + +/* + * Entered when a bau descriptor has gone into a permanent busy wait because + * of a hardware bug. + * Workaround the bug. + */ +int handle_uv2_busy(struct bau_control *bcp) +{ + int busy_one = bcp->using_desc; + int normal = bcp->uvhub_cpu; + int selected = -1; + int i; + unsigned long descriptor_status; + unsigned long status; + int mmr_offset; + struct bau_desc *bau_desc_old; + struct bau_desc *bau_desc_new; + struct bau_control *hmaster = bcp->uvhub_master; + struct ptc_stats *stat = bcp->statp; + cycles_t ttm; + + stat->s_uv2_wars++; + spin_lock(&hmaster->uvhub_lock); + /* try for the original first */ + if (busy_one != normal) { + if (!normal_busy(bcp)) + selected = normal; + } + if (selected < 0) { + /* can't use the normal, select an alternate */ + mmr_offset = UVH_LB_BAU_SB_ACTIVATION_STATUS_1; + descriptor_status = read_lmmr(mmr_offset); + + /* scan available descriptors 32-63 */ + for (i = 0; i < UV_CPUS_PER_AS; i++) { + if ((hmaster->inuse_map & (1 << i)) == 0) { + status = ((descriptor_status >> + (i * UV_ACT_STATUS_SIZE)) & + UV_ACT_STATUS_MASK) << 1; + if (status != UV2H_DESC_BUSY) { + selected = i + UV_CPUS_PER_AS; + break; + } + } + } + } + + if (busy_one != normal) + /* mark the busy alternate as not in-use */ + hmaster->inuse_map &= ~(1 << (busy_one - UV_CPUS_PER_AS)); + + if (selected >= 0) { + /* switch to the selected descriptor */ + if (selected != normal) { + /* set the selected alternate as in-use */ + hmaster->inuse_map |= + (1 << (selected - UV_CPUS_PER_AS)); + if (selected > stat->s_uv2_wars_hw) + stat->s_uv2_wars_hw = selected; + } + bau_desc_old = bcp->descriptor_base; + bau_desc_old += (ITEMS_PER_DESC * busy_one); + bcp->using_desc = selected; + bau_desc_new = bcp->descriptor_base; + bau_desc_new += (ITEMS_PER_DESC * selected); + *bau_desc_new = *bau_desc_old; + } else { + /* + * All are busy. Wait for the normal one for this cpu to + * free up. + */ + stat->s_uv2_war_waits++; + spin_unlock(&hmaster->uvhub_lock); + ttm = get_cycles(); + do { + cpu_relax(); + } while (normal_busy(bcp)); + spin_lock(&hmaster->uvhub_lock); + /* switch to the original descriptor */ + bcp->using_desc = normal; + bau_desc_old = bcp->descriptor_base; + bau_desc_old += (ITEMS_PER_DESC * bcp->using_desc); + bcp->using_desc = (ITEMS_PER_DESC * normal); + bau_desc_new = bcp->descriptor_base; + bau_desc_new += (ITEMS_PER_DESC * normal); + *bau_desc_new = *bau_desc_old; /* copy the entire descriptor */ + } + spin_unlock(&hmaster->uvhub_lock); + return FLUSH_RETRY_BUSYBUG; +} + static int uv2_wait_completion(struct bau_desc *bau_desc, unsigned long mmr_offset, int right_shift, struct bau_control *bcp, long try) { unsigned long descriptor_stat; cycles_t ttm; - int cpu = bcp->uvhub_cpu; + int desc = bcp->using_desc; + long busy_reps = 0; struct ptc_stats *stat = bcp->statp; - descriptor_stat = uv2_read_status(mmr_offset, right_shift, cpu); + descriptor_stat = uv2_read_status(mmr_offset, right_shift, desc); /* spin on the status MMR, waiting for it to go idle */ while (descriptor_stat != UV2H_DESC_IDLE) { @@ -522,32 +635,35 @@ static int uv2_wait_completion(struct bau_desc *bau_desc, * our message and its state will stay IDLE. */ if ((descriptor_stat == UV2H_DESC_SOURCE_TIMEOUT) || - (descriptor_stat == UV2H_DESC_DEST_STRONG_NACK) || (descriptor_stat == UV2H_DESC_DEST_PUT_ERR)) { stat->s_stimeout++; return FLUSH_GIVEUP; + } else if (descriptor_stat == UV2H_DESC_DEST_STRONG_NACK) { + stat->s_strongnacks++; + bcp->conseccompletes = 0; + return FLUSH_GIVEUP; } else if (descriptor_stat == UV2H_DESC_DEST_TIMEOUT) { stat->s_dtimeout++; - ttm = get_cycles(); - /* - * Our retries may be blocked by all destination - * swack resources being consumed, and a timeout - * pending. In that case hardware returns the - * ERROR that looks like a destination timeout. - */ - if (cycles_2_us(ttm - bcp->send_message) < timeout_us) { - bcp->conseccompletes = 0; - return FLUSH_RETRY_PLUGGED; - } bcp->conseccompletes = 0; return FLUSH_RETRY_TIMEOUT; } else { + busy_reps++; + if (busy_reps > 1000000) { + /* not to hammer on the clock */ + busy_reps = 0; + ttm = get_cycles(); + if ((ttm - bcp->send_message) > + (bcp->clocks_per_100_usec)) { + return handle_uv2_busy(bcp); + } + } /* * descriptor_stat is still BUSY */ cpu_relax(); } - descriptor_stat = uv2_read_status(mmr_offset, right_shift, cpu); + descriptor_stat = uv2_read_status(mmr_offset, right_shift, + desc); } bcp->conseccompletes++; return FLUSH_COMPLETE; @@ -563,17 +679,17 @@ static int wait_completion(struct bau_desc *bau_desc, { int right_shift; unsigned long mmr_offset; - int cpu = bcp->uvhub_cpu; + int desc = bcp->using_desc; - if (cpu < UV_CPUS_PER_AS) { + if (desc < UV_CPUS_PER_AS) { mmr_offset = UVH_LB_BAU_SB_ACTIVATION_STATUS_0; - right_shift = cpu * UV_ACT_STATUS_SIZE; + right_shift = desc * UV_ACT_STATUS_SIZE; } else { mmr_offset = UVH_LB_BAU_SB_ACTIVATION_STATUS_1; - right_shift = ((cpu - UV_CPUS_PER_AS) * UV_ACT_STATUS_SIZE); + right_shift = ((desc - UV_CPUS_PER_AS) * UV_ACT_STATUS_SIZE); } - if (is_uv1_hub()) + if (bcp->uvhub_version == 1) return uv1_wait_completion(bau_desc, mmr_offset, right_shift, bcp, try); else @@ -752,19 +868,22 @@ static void handle_cmplt(int completion_status, struct bau_desc *bau_desc, * Returns 1 if it gives up entirely and the original cpu mask is to be * returned to the kernel. */ -int uv_flush_send_and_wait(struct bau_desc *bau_desc, - struct cpumask *flush_mask, struct bau_control *bcp) +int uv_flush_send_and_wait(struct cpumask *flush_mask, struct bau_control *bcp) { int seq_number = 0; int completion_stat = 0; + int uv1 = 0; long try = 0; unsigned long index; cycles_t time1; cycles_t time2; struct ptc_stats *stat = bcp->statp; struct bau_control *hmaster = bcp->uvhub_master; + struct uv1_bau_msg_header *uv1_hdr = NULL; + struct uv2_bau_msg_header *uv2_hdr = NULL; + struct bau_desc *bau_desc; - if (is_uv1_hub()) + if (bcp->uvhub_version == 1) uv1_throttle(hmaster, stat); while (hmaster->uvhub_quiesce) @@ -772,22 +891,39 @@ int uv_flush_send_and_wait(struct bau_desc *bau_desc, time1 = get_cycles(); do { - if (try == 0) { - bau_desc->header.msg_type = MSG_REGULAR; + bau_desc = bcp->descriptor_base; + bau_desc += (ITEMS_PER_DESC * bcp->using_desc); + if (bcp->uvhub_version == 1) { + uv1 = 1; + uv1_hdr = &bau_desc->header.uv1_hdr; + } else + uv2_hdr = &bau_desc->header.uv2_hdr; + if ((try == 0) || (completion_stat == FLUSH_RETRY_BUSYBUG)) { + if (uv1) + uv1_hdr->msg_type = MSG_REGULAR; + else + uv2_hdr->msg_type = MSG_REGULAR; seq_number = bcp->message_number++; } else { - bau_desc->header.msg_type = MSG_RETRY; + if (uv1) + uv1_hdr->msg_type = MSG_RETRY; + else + uv2_hdr->msg_type = MSG_RETRY; stat->s_retry_messages++; } - bau_desc->header.sequence = seq_number; - index = (1UL << AS_PUSH_SHIFT) | bcp->uvhub_cpu; + if (uv1) + uv1_hdr->sequence = seq_number; + else + uv2_hdr->sequence = seq_number; + index = (1UL << AS_PUSH_SHIFT) | bcp->using_desc; bcp->send_message = get_cycles(); write_mmr_activation(index); try++; completion_stat = wait_completion(bau_desc, bcp, try); + /* UV2: wait_completion() may change the bcp->using_desc */ handle_cmplt(completion_stat, bau_desc, bcp, hmaster, stat); @@ -798,6 +934,7 @@ int uv_flush_send_and_wait(struct bau_desc *bau_desc, } cpu_relax(); } while ((completion_stat == FLUSH_RETRY_PLUGGED) || + (completion_stat == FLUSH_RETRY_BUSYBUG) || (completion_stat == FLUSH_RETRY_TIMEOUT)); time2 = get_cycles(); @@ -812,6 +949,7 @@ int uv_flush_send_and_wait(struct bau_desc *bau_desc, record_send_stats(time1, time2, bcp, stat, completion_stat, try); if (completion_stat == FLUSH_GIVEUP) + /* FLUSH_GIVEUP will fall back to using IPI's for tlb flush */ return 1; return 0; } @@ -967,7 +1105,7 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask, stat->s_ntargself++; bau_desc = bcp->descriptor_base; - bau_desc += ITEMS_PER_DESC * bcp->uvhub_cpu; + bau_desc += (ITEMS_PER_DESC * bcp->using_desc); bau_uvhubs_clear(&bau_desc->distribution, UV_DISTRIBUTION_SIZE); if (set_distrib_bits(flush_mask, bcp, bau_desc, &locals, &remotes)) return NULL; @@ -980,13 +1118,86 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask, * uv_flush_send_and_wait returns 0 if all cpu's were messaged, * or 1 if it gave up and the original cpumask should be returned. */ - if (!uv_flush_send_and_wait(bau_desc, flush_mask, bcp)) + if (!uv_flush_send_and_wait(flush_mask, bcp)) return NULL; else return cpumask; } /* + * Search the message queue for any 'other' message with the same software + * acknowledge resource bit vector. + */ +struct bau_pq_entry *find_another_by_swack(struct bau_pq_entry *msg, + struct bau_control *bcp, unsigned char swack_vec) +{ + struct bau_pq_entry *msg_next = msg + 1; + + if (msg_next > bcp->queue_last) + msg_next = bcp->queue_first; + while ((msg_next->swack_vec != 0) && (msg_next != msg)) { + if (msg_next->swack_vec == swack_vec) + return msg_next; + msg_next++; + if (msg_next > bcp->queue_last) + msg_next = bcp->queue_first; + } + return NULL; +} + +/* + * UV2 needs to work around a bug in which an arriving message has not + * set a bit in the UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE register. + * Such a message must be ignored. + */ +void process_uv2_message(struct msg_desc *mdp, struct bau_control *bcp) +{ + unsigned long mmr_image; + unsigned char swack_vec; + struct bau_pq_entry *msg = mdp->msg; + struct bau_pq_entry *other_msg; + + mmr_image = read_mmr_sw_ack(); + swack_vec = msg->swack_vec; + + if ((swack_vec & mmr_image) == 0) { + /* + * This message was assigned a swack resource, but no + * reserved acknowlegment is pending. + * The bug has prevented this message from setting the MMR. + * And no other message has used the same sw_ack resource. + * Do the requested shootdown but do not reply to the msg. + * (the 0 means make no acknowledge) + */ + bau_process_message(mdp, bcp, 0); + return; + } + + /* + * Some message has set the MMR 'pending' bit; it might have been + * another message. Look for that message. + */ + other_msg = find_another_by_swack(msg, bcp, msg->swack_vec); + if (other_msg) { + /* There is another. Do not ack the current one. */ + bau_process_message(mdp, bcp, 0); + /* + * Let the natural processing of that message acknowledge + * it. Don't get the processing of sw_ack's out of order. + */ + return; + } + + /* + * There is no other message using this sw_ack, so it is safe to + * acknowledge it. + */ + bau_process_message(mdp, bcp, 1); + + return; +} + +/* * The BAU message interrupt comes here. (registered by set_intr_gate) * See entry_64.S * @@ -1009,6 +1220,7 @@ void uv_bau_message_interrupt(struct pt_regs *regs) struct ptc_stats *stat; struct msg_desc msgdesc; + ack_APIC_irq(); time_start = get_cycles(); bcp = &per_cpu(bau_control, smp_processor_id()); @@ -1022,9 +1234,11 @@ void uv_bau_message_interrupt(struct pt_regs *regs) count++; msgdesc.msg_slot = msg - msgdesc.queue_first; - msgdesc.swack_slot = ffs(msg->swack_vec) - 1; msgdesc.msg = msg; - bau_process_message(&msgdesc, bcp); + if (bcp->uvhub_version == 2) + process_uv2_message(&msgdesc, bcp); + else + bau_process_message(&msgdesc, bcp, 1); msg++; if (msg > msgdesc.queue_last) @@ -1036,8 +1250,6 @@ void uv_bau_message_interrupt(struct pt_regs *regs) stat->d_nomsg++; else if (count > 1) stat->d_multmsg++; - - ack_APIC_irq(); } /* @@ -1083,7 +1295,7 @@ static void __init enable_timeouts(void) */ mmr_image |= (1L << SOFTACK_MSHIFT); if (is_uv2_hub()) { - mmr_image |= (1L << UV2_LEG_SHFT); + mmr_image &= ~(1L << UV2_LEG_SHFT); mmr_image |= (1L << UV2_EXT_SHFT); } write_mmr_misc_control(pnode, mmr_image); @@ -1136,13 +1348,13 @@ static int ptc_seq_show(struct seq_file *file, void *data) seq_printf(file, "remotehub numuvhubs numuvhubs16 numuvhubs8 "); seq_printf(file, - "numuvhubs4 numuvhubs2 numuvhubs1 dto retries rok "); + "numuvhubs4 numuvhubs2 numuvhubs1 dto snacks retries rok "); seq_printf(file, "resetp resett giveup sto bz throt swack recv rtime "); seq_printf(file, "all one mult none retry canc nocan reset rcan "); seq_printf(file, - "disable enable\n"); + "disable enable wars warshw warwaits\n"); } if (cpu < num_possible_cpus() && cpu_online(cpu)) { stat = &per_cpu(ptcstats, cpu); @@ -1154,10 +1366,10 @@ static int ptc_seq_show(struct seq_file *file, void *data) stat->s_ntargremotes, stat->s_ntargcpu, stat->s_ntarglocaluvhub, stat->s_ntargremoteuvhub, stat->s_ntarguvhub, stat->s_ntarguvhub16); - seq_printf(file, "%ld %ld %ld %ld %ld ", + seq_printf(file, "%ld %ld %ld %ld %ld %ld ", stat->s_ntarguvhub8, stat->s_ntarguvhub4, stat->s_ntarguvhub2, stat->s_ntarguvhub1, - stat->s_dtimeout); + stat->s_dtimeout, stat->s_strongnacks); seq_printf(file, "%ld %ld %ld %ld %ld %ld %ld %ld ", stat->s_retry_messages, stat->s_retriesok, stat->s_resets_plug, stat->s_resets_timeout, @@ -1173,8 +1385,10 @@ static int ptc_seq_show(struct seq_file *file, void *data) stat->d_nomsg, stat->d_retries, stat->d_canceled, stat->d_nocanceled, stat->d_resets, stat->d_rcanceled); - seq_printf(file, "%ld %ld\n", - stat->s_bau_disabled, stat->s_bau_reenabled); + seq_printf(file, "%ld %ld %ld %ld %ld\n", + stat->s_bau_disabled, stat->s_bau_reenabled, + stat->s_uv2_wars, stat->s_uv2_wars_hw, + stat->s_uv2_war_waits); } return 0; } @@ -1432,12 +1646,15 @@ static void activation_descriptor_init(int node, int pnode, int base_pnode) { int i; int cpu; + int uv1 = 0; unsigned long gpa; unsigned long m; unsigned long n; size_t dsize; struct bau_desc *bau_desc; struct bau_desc *bd2; + struct uv1_bau_msg_header *uv1_hdr; + struct uv2_bau_msg_header *uv2_hdr; struct bau_control *bcp; /* @@ -1451,6 +1668,8 @@ static void activation_descriptor_init(int node, int pnode, int base_pnode) gpa = uv_gpa(bau_desc); n = uv_gpa_to_gnode(gpa); m = uv_gpa_to_offset(gpa); + if (is_uv1_hub()) + uv1 = 1; /* the 14-bit pnode */ write_mmr_descriptor_base(pnode, (n << UV_DESC_PSHIFT | m)); @@ -1461,21 +1680,33 @@ static void activation_descriptor_init(int node, int pnode, int base_pnode) */ for (i = 0, bd2 = bau_desc; i < (ADP_SZ * ITEMS_PER_DESC); i++, bd2++) { memset(bd2, 0, sizeof(struct bau_desc)); - bd2->header.swack_flag = 1; - /* - * The base_dest_nasid set in the message header is the nasid - * of the first uvhub in the partition. The bit map will - * indicate destination pnode numbers relative to that base. - * They may not be consecutive if nasid striding is being used. - */ - bd2->header.base_dest_nasid = UV_PNODE_TO_NASID(base_pnode); - bd2->header.dest_subnodeid = UV_LB_SUBNODEID; - bd2->header.command = UV_NET_ENDPOINT_INTD; - bd2->header.int_both = 1; - /* - * all others need to be set to zero: - * fairness chaining multilevel count replied_to - */ + if (uv1) { + uv1_hdr = &bd2->header.uv1_hdr; + uv1_hdr->swack_flag = 1; + /* + * The base_dest_nasid set in the message header + * is the nasid of the first uvhub in the partition. + * The bit map will indicate destination pnode numbers + * relative to that base. They may not be consecutive + * if nasid striding is being used. + */ + uv1_hdr->base_dest_nasid = + UV_PNODE_TO_NASID(base_pnode); + uv1_hdr->dest_subnodeid = UV_LB_SUBNODEID; + uv1_hdr->command = UV_NET_ENDPOINT_INTD; + uv1_hdr->int_both = 1; + /* + * all others need to be set to zero: + * fairness chaining multilevel count replied_to + */ + } else { + uv2_hdr = &bd2->header.uv2_hdr; + uv2_hdr->swack_flag = 1; + uv2_hdr->base_dest_nasid = + UV_PNODE_TO_NASID(base_pnode); + uv2_hdr->dest_subnodeid = UV_LB_SUBNODEID; + uv2_hdr->command = UV_NET_ENDPOINT_INTD; + } } for_each_present_cpu(cpu) { if (pnode != uv_blade_to_pnode(uv_cpu_to_blade_id(cpu))) @@ -1531,6 +1762,7 @@ static void pq_init(int node, int pnode) write_mmr_payload_first(pnode, pn_first); write_mmr_payload_tail(pnode, first); write_mmr_payload_last(pnode, last); + write_gmmr_sw_ack(pnode, 0xffffUL); /* in effect, all msg_type's are set to MSG_NOOP */ memset(pqp, 0, sizeof(struct bau_pq_entry) * DEST_Q_SIZE); @@ -1584,14 +1816,14 @@ static int calculate_destination_timeout(void) ts_ns = base * mult1 * mult2; ret = ts_ns / 1000; } else { - /* 4 bits 0/1 for 10/80us, 3 bits of multiplier */ - mmr_image = uv_read_local_mmr(UVH_AGING_PRESCALE_SEL); + /* 4 bits 0/1 for 10/80us base, 3 bits of multiplier */ + mmr_image = uv_read_local_mmr(UVH_LB_BAU_MISC_CONTROL); mmr_image = (mmr_image & UV_SA_MASK) >> UV_SA_SHFT; if (mmr_image & (1L << UV2_ACK_UNITS_SHFT)) - mult1 = 80; + base = 80; else - mult1 = 10; - base = mmr_image & UV2_ACK_MASK; + base = 10; + mult1 = mmr_image & UV2_ACK_MASK; ret = mult1 * base; } return ret; @@ -1618,6 +1850,7 @@ static void __init init_per_cpu_tunables(void) bcp->cong_response_us = congested_respns_us; bcp->cong_reps = congested_reps; bcp->cong_period = congested_period; + bcp->clocks_per_100_usec = usec_2_cycles(100); } } @@ -1728,8 +1961,17 @@ static int scan_sock(struct socket_desc *sdp, struct uvhub_desc *bdp, bcp->cpus_in_socket = sdp->num_cpus; bcp->socket_master = *smasterp; bcp->uvhub = bdp->uvhub; + if (is_uv1_hub()) + bcp->uvhub_version = 1; + else if (is_uv2_hub()) + bcp->uvhub_version = 2; + else { + printk(KERN_EMERG "uvhub version not 1 or 2\n"); + return 1; + } bcp->uvhub_master = *hmasterp; bcp->uvhub_cpu = uv_cpu_hub_info(cpu)->blade_processor_id; + bcp->using_desc = bcp->uvhub_cpu; if (bcp->uvhub_cpu >= MAX_CPUS_PER_UVHUB) { printk(KERN_EMERG "%d cpus per uvhub invalid\n", bcp->uvhub_cpu); @@ -1845,6 +2087,8 @@ static int __init uv_bau_init(void) uv_base_pnode = uv_blade_to_pnode(uvhub); } + enable_timeouts(); + if (init_per_cpu(nuvhubs, uv_base_pnode)) { nobau = 1; return 0; @@ -1855,7 +2099,6 @@ static int __init uv_bau_init(void) if (uv_blade_nr_possible_cpus(uvhub)) init_uvhub(uvhub, vector, uv_base_pnode); - enable_timeouts(); alloc_intr_gate(vector, uv_bau_message_intr1); for_each_possible_blade(uvhub) { @@ -1867,7 +2110,8 @@ static int __init uv_bau_init(void) val = 1L << 63; write_gmmr_activation(pnode, val); mmr = 1; /* should be 1 to broadcast to both sockets */ - write_mmr_data_broadcast(pnode, mmr); + if (!is_uv1_hub()) + write_mmr_data_broadcast(pnode, mmr); } } diff --git a/arch/x86/syscalls/Makefile b/arch/x86/syscalls/Makefile new file mode 100644 index 00000000000..564b2476fed --- /dev/null +++ b/arch/x86/syscalls/Makefile @@ -0,0 +1,43 @@ +out := $(obj)/../include/generated/asm + +# Create output directory if not already present +_dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)') + +syscall32 := $(srctree)/$(src)/syscall_32.tbl +syscall64 := $(srctree)/$(src)/syscall_64.tbl + +syshdr := $(srctree)/$(src)/syscallhdr.sh +systbl := $(srctree)/$(src)/syscalltbl.sh + +quiet_cmd_syshdr = SYSHDR $@ + cmd_syshdr = $(CONFIG_SHELL) '$(syshdr)' $< $@ \ + $(syshdr_abi_$(basetarget)) $(syshdr_pfx_$(basetarget)) +quiet_cmd_systbl = SYSTBL $@ + cmd_systbl = $(CONFIG_SHELL) '$(systbl)' $< $@ + +syshdr_abi_unistd_32 := i386 +$(out)/unistd_32.h: $(syscall32) $(syshdr) + $(call if_changed,syshdr) + +syshdr_abi_unistd_32_ia32 := i386 +syshdr_pfx_unistd_32_ia32 := ia32_ +$(out)/unistd_32_ia32.h: $(syscall32) $(syshdr) + $(call if_changed,syshdr) + +syshdr_abi_unistd_64 := 64 +$(out)/unistd_64.h: $(syscall64) $(syshdr) + $(call if_changed,syshdr) + +$(out)/syscalls_32.h: $(syscall32) $(systbl) + $(call if_changed,systbl) +$(out)/syscalls_64.h: $(syscall64) $(systbl) + $(call if_changed,systbl) + +syshdr-y += unistd_32.h unistd_64.h +syshdr-y += syscalls_32.h +syshdr-$(CONFIG_X86_64) += unistd_32_ia32.h +syshdr-$(CONFIG_X86_64) += syscalls_64.h + +targets += $(syshdr-y) + +all: $(addprefix $(out)/,$(targets)) diff --git a/arch/x86/syscalls/syscall_32.tbl b/arch/x86/syscalls/syscall_32.tbl new file mode 100644 index 00000000000..ce98e287c06 --- /dev/null +++ b/arch/x86/syscalls/syscall_32.tbl @@ -0,0 +1,357 @@ +# +# 32-bit system call numbers and entry vectors +# +# The format is: +# <number> <abi> <name> <entry point> <compat entry point> +# +# The abi is always "i386" for this file. +# +0 i386 restart_syscall sys_restart_syscall +1 i386 exit sys_exit +2 i386 fork ptregs_fork stub32_fork +3 i386 read sys_read +4 i386 write sys_write +5 i386 open sys_open compat_sys_open +6 i386 close sys_close +7 i386 waitpid sys_waitpid sys32_waitpid +8 i386 creat sys_creat +9 i386 link sys_link +10 i386 unlink sys_unlink +11 i386 execve ptregs_execve stub32_execve +12 i386 chdir sys_chdir +13 i386 time sys_time compat_sys_time +14 i386 mknod sys_mknod +15 i386 chmod sys_chmod +16 i386 lchown sys_lchown16 +17 i386 break +18 i386 oldstat sys_stat +19 i386 lseek sys_lseek sys32_lseek +20 i386 getpid sys_getpid +21 i386 mount sys_mount compat_sys_mount +22 i386 umount sys_oldumount +23 i386 setuid sys_setuid16 +24 i386 getuid sys_getuid16 +25 i386 stime sys_stime compat_sys_stime +26 i386 ptrace sys_ptrace compat_sys_ptrace +27 i386 alarm sys_alarm +28 i386 oldfstat sys_fstat +29 i386 pause sys_pause +30 i386 utime sys_utime compat_sys_utime +31 i386 stty +32 i386 gtty +33 i386 access sys_access +34 i386 nice sys_nice +35 i386 ftime +36 i386 sync sys_sync +37 i386 kill sys_kill sys32_kill +38 i386 rename sys_rename +39 i386 mkdir sys_mkdir +40 i386 rmdir sys_rmdir +41 i386 dup sys_dup +42 i386 pipe sys_pipe +43 i386 times sys_times compat_sys_times +44 i386 prof +45 i386 brk sys_brk +46 i386 setgid sys_setgid16 +47 i386 getgid sys_getgid16 +48 i386 signal sys_signal +49 i386 geteuid sys_geteuid16 +50 i386 getegid sys_getegid16 +51 i386 acct sys_acct +52 i386 umount2 sys_umount +53 i386 lock +54 i386 ioctl sys_ioctl compat_sys_ioctl +55 i386 fcntl sys_fcntl compat_sys_fcntl64 +56 i386 mpx +57 i386 setpgid sys_setpgid +58 i386 ulimit +59 i386 oldolduname sys_olduname +60 i386 umask sys_umask +61 i386 chroot sys_chroot +62 i386 ustat sys_ustat compat_sys_ustat +63 i386 dup2 sys_dup2 +64 i386 getppid sys_getppid +65 i386 getpgrp sys_getpgrp +66 i386 setsid sys_setsid +67 i386 sigaction sys_sigaction sys32_sigaction +68 i386 sgetmask sys_sgetmask +69 i386 ssetmask sys_ssetmask +70 i386 setreuid sys_setreuid16 +71 i386 setregid sys_setregid16 +72 i386 sigsuspend sys_sigsuspend sys32_sigsuspend +73 i386 sigpending sys_sigpending compat_sys_sigpending +74 i386 sethostname sys_sethostname +75 i386 setrlimit sys_setrlimit compat_sys_setrlimit +76 i386 getrlimit sys_old_getrlimit compat_sys_old_getrlimit +77 i386 getrusage sys_getrusage compat_sys_getrusage +78 i386 gettimeofday sys_gettimeofday compat_sys_gettimeofday +79 i386 settimeofday sys_settimeofday compat_sys_settimeofday +80 i386 getgroups sys_getgroups16 +81 i386 setgroups sys_setgroups16 +82 i386 select sys_old_select compat_sys_old_select +83 i386 symlink sys_symlink +84 i386 oldlstat sys_lstat +85 i386 readlink sys_readlink +86 i386 uselib sys_uselib +87 i386 swapon sys_swapon +88 i386 reboot sys_reboot +89 i386 readdir sys_old_readdir compat_sys_old_readdir +90 i386 mmap sys_old_mmap sys32_mmap +91 i386 munmap sys_munmap +92 i386 truncate sys_truncate +93 i386 ftruncate sys_ftruncate +94 i386 fchmod sys_fchmod +95 i386 fchown sys_fchown16 +96 i386 getpriority sys_getpriority +97 i386 setpriority sys_setpriority +98 i386 profil +99 i386 statfs sys_statfs compat_sys_statfs +100 i386 fstatfs sys_fstatfs compat_sys_fstatfs +101 i386 ioperm sys_ioperm +102 i386 socketcall sys_socketcall compat_sys_socketcall +103 i386 syslog sys_syslog +104 i386 setitimer sys_setitimer compat_sys_setitimer +105 i386 getitimer sys_getitimer compat_sys_getitimer +106 i386 stat sys_newstat compat_sys_newstat +107 i386 lstat sys_newlstat compat_sys_newlstat +108 i386 fstat sys_newfstat compat_sys_newfstat +109 i386 olduname sys_uname +110 i386 iopl ptregs_iopl stub32_iopl +111 i386 vhangup sys_vhangup +112 i386 idle +113 i386 vm86old ptregs_vm86old sys32_vm86_warning +114 i386 wait4 sys_wait4 compat_sys_wait4 +115 i386 swapoff sys_swapoff +116 i386 sysinfo sys_sysinfo compat_sys_sysinfo +117 i386 ipc sys_ipc sys32_ipc +118 i386 fsync sys_fsync +119 i386 sigreturn ptregs_sigreturn stub32_sigreturn +120 i386 clone ptregs_clone stub32_clone +121 i386 setdomainname sys_setdomainname +122 i386 uname sys_newuname +123 i386 modify_ldt sys_modify_ldt +124 i386 adjtimex sys_adjtimex compat_sys_adjtimex +125 i386 mprotect sys_mprotect sys32_mprotect +126 i386 sigprocmask sys_sigprocmask compat_sys_sigprocmask +127 i386 create_module +128 i386 init_module sys_init_module +129 i386 delete_module sys_delete_module +130 i386 get_kernel_syms +131 i386 quotactl sys_quotactl sys32_quotactl +132 i386 getpgid sys_getpgid +133 i386 fchdir sys_fchdir +134 i386 bdflush sys_bdflush +135 i386 sysfs sys_sysfs +136 i386 personality sys_personality +137 i386 afs_syscall +138 i386 setfsuid sys_setfsuid16 +139 i386 setfsgid sys_setfsgid16 +140 i386 _llseek sys_llseek +141 i386 getdents sys_getdents compat_sys_getdents +142 i386 _newselect sys_select compat_sys_select +143 i386 flock sys_flock +144 i386 msync sys_msync +145 i386 readv sys_readv compat_sys_readv +146 i386 writev sys_writev compat_sys_writev +147 i386 getsid sys_getsid +148 i386 fdatasync sys_fdatasync +149 i386 _sysctl sys_sysctl compat_sys_sysctl +150 i386 mlock sys_mlock +151 i386 munlock sys_munlock +152 i386 mlockall sys_mlockall +153 i386 munlockall sys_munlockall +154 i386 sched_setparam sys_sched_setparam +155 i386 sched_getparam sys_sched_getparam +156 i386 sched_setscheduler sys_sched_setscheduler +157 i386 sched_getscheduler sys_sched_getscheduler +158 i386 sched_yield sys_sched_yield +159 i386 sched_get_priority_max sys_sched_get_priority_max +160 i386 sched_get_priority_min sys_sched_get_priority_min +161 i386 sched_rr_get_interval sys_sched_rr_get_interval sys32_sched_rr_get_interval +162 i386 nanosleep sys_nanosleep compat_sys_nanosleep +163 i386 mremap sys_mremap +164 i386 setresuid sys_setresuid16 +165 i386 getresuid sys_getresuid16 +166 i386 vm86 ptregs_vm86 sys32_vm86_warning +167 i386 query_module +168 i386 poll sys_poll +169 i386 nfsservctl +170 i386 setresgid sys_setresgid16 +171 i386 getresgid sys_getresgid16 +172 i386 prctl sys_prctl +173 i386 rt_sigreturn ptregs_rt_sigreturn stub32_rt_sigreturn +174 i386 rt_sigaction sys_rt_sigaction sys32_rt_sigaction +175 i386 rt_sigprocmask sys_rt_sigprocmask sys32_rt_sigprocmask +176 i386 rt_sigpending sys_rt_sigpending sys32_rt_sigpending +177 i386 rt_sigtimedwait sys_rt_sigtimedwait compat_sys_rt_sigtimedwait +178 i386 rt_sigqueueinfo sys_rt_sigqueueinfo sys32_rt_sigqueueinfo +179 i386 rt_sigsuspend sys_rt_sigsuspend +180 i386 pread64 sys_pread64 sys32_pread +181 i386 pwrite64 sys_pwrite64 sys32_pwrite +182 i386 chown sys_chown16 +183 i386 getcwd sys_getcwd +184 i386 capget sys_capget +185 i386 capset sys_capset +186 i386 sigaltstack ptregs_sigaltstack stub32_sigaltstack +187 i386 sendfile sys_sendfile sys32_sendfile +188 i386 getpmsg +189 i386 putpmsg +190 i386 vfork ptregs_vfork stub32_vfork +191 i386 ugetrlimit sys_getrlimit compat_sys_getrlimit +192 i386 mmap2 sys_mmap_pgoff +193 i386 truncate64 sys_truncate64 sys32_truncate64 +194 i386 ftruncate64 sys_ftruncate64 sys32_ftruncate64 +195 i386 stat64 sys_stat64 sys32_stat64 +196 i386 lstat64 sys_lstat64 sys32_lstat64 +197 i386 fstat64 sys_fstat64 sys32_fstat64 +198 i386 lchown32 sys_lchown +199 i386 getuid32 sys_getuid +200 i386 getgid32 sys_getgid +201 i386 geteuid32 sys_geteuid +202 i386 getegid32 sys_getegid +203 i386 setreuid32 sys_setreuid +204 i386 setregid32 sys_setregid +205 i386 getgroups32 sys_getgroups +206 i386 setgroups32 sys_setgroups +207 i386 fchown32 sys_fchown +208 i386 setresuid32 sys_setresuid +209 i386 getresuid32 sys_getresuid +210 i386 setresgid32 sys_setresgid +211 i386 getresgid32 sys_getresgid +212 i386 chown32 sys_chown +213 i386 setuid32 sys_setuid +214 i386 setgid32 sys_setgid +215 i386 setfsuid32 sys_setfsuid +216 i386 setfsgid32 sys_setfsgid +217 i386 pivot_root sys_pivot_root +218 i386 mincore sys_mincore +219 i386 madvise sys_madvise +220 i386 getdents64 sys_getdents64 compat_sys_getdents64 +221 i386 fcntl64 sys_fcntl64 compat_sys_fcntl64 +# 222 is unused +# 223 is unused +224 i386 gettid sys_gettid +225 i386 readahead sys_readahead sys32_readahead +226 i386 setxattr sys_setxattr +227 i386 lsetxattr sys_lsetxattr +228 i386 fsetxattr sys_fsetxattr +229 i386 getxattr sys_getxattr +230 i386 lgetxattr sys_lgetxattr +231 i386 fgetxattr sys_fgetxattr +232 i386 listxattr sys_listxattr +233 i386 llistxattr sys_llistxattr +234 i386 flistxattr sys_flistxattr +235 i386 removexattr sys_removexattr +236 i386 lremovexattr sys_lremovexattr +237 i386 fremovexattr sys_fremovexattr +238 i386 tkill sys_tkill +239 i386 sendfile64 sys_sendfile64 +240 i386 futex sys_futex compat_sys_futex +241 i386 sched_setaffinity sys_sched_setaffinity compat_sys_sched_setaffinity +242 i386 sched_getaffinity sys_sched_getaffinity compat_sys_sched_getaffinity +243 i386 set_thread_area sys_set_thread_area +244 i386 get_thread_area sys_get_thread_area +245 i386 io_setup sys_io_setup compat_sys_io_setup +246 i386 io_destroy sys_io_destroy +247 i386 io_getevents sys_io_getevents compat_sys_io_getevents +248 i386 io_submit sys_io_submit compat_sys_io_submit +249 i386 io_cancel sys_io_cancel +250 i386 fadvise64 sys_fadvise64 sys32_fadvise64 +# 251 is available for reuse (was briefly sys_set_zone_reclaim) +252 i386 exit_group sys_exit_group +253 i386 lookup_dcookie sys_lookup_dcookie sys32_lookup_dcookie +254 i386 epoll_create sys_epoll_create +255 i386 epoll_ctl sys_epoll_ctl +256 i386 epoll_wait sys_epoll_wait +257 i386 remap_file_pages sys_remap_file_pages +258 i386 set_tid_address sys_set_tid_address +259 i386 timer_create sys_timer_create compat_sys_timer_create +260 i386 timer_settime sys_timer_settime compat_sys_timer_settime +261 i386 timer_gettime sys_timer_gettime compat_sys_timer_gettime +262 i386 timer_getoverrun sys_timer_getoverrun +263 i386 timer_delete sys_timer_delete +264 i386 clock_settime sys_clock_settime compat_sys_clock_settime +265 i386 clock_gettime sys_clock_gettime compat_sys_clock_gettime +266 i386 clock_getres sys_clock_getres compat_sys_clock_getres +267 i386 clock_nanosleep sys_clock_nanosleep compat_sys_clock_nanosleep +268 i386 statfs64 sys_statfs64 compat_sys_statfs64 +269 i386 fstatfs64 sys_fstatfs64 compat_sys_fstatfs64 +270 i386 tgkill sys_tgkill +271 i386 utimes sys_utimes compat_sys_utimes +272 i386 fadvise64_64 sys_fadvise64_64 sys32_fadvise64_64 +273 i386 vserver +274 i386 mbind sys_mbind +275 i386 get_mempolicy sys_get_mempolicy compat_sys_get_mempolicy +276 i386 set_mempolicy sys_set_mempolicy +277 i386 mq_open sys_mq_open compat_sys_mq_open +278 i386 mq_unlink sys_mq_unlink +279 i386 mq_timedsend sys_mq_timedsend compat_sys_mq_timedsend +280 i386 mq_timedreceive sys_mq_timedreceive compat_sys_mq_timedreceive +281 i386 mq_notify sys_mq_notify compat_sys_mq_notify +282 i386 mq_getsetaddr sys_mq_getsetattr compat_sys_mq_getsetattr +283 i386 kexec_load sys_kexec_load compat_sys_kexec_load +284 i386 waitid sys_waitid compat_sys_waitid +# 285 sys_setaltroot +286 i386 add_key sys_add_key +287 i386 request_key sys_request_key +288 i386 keyctl sys_keyctl +289 i386 ioprio_set sys_ioprio_set +290 i386 ioprio_get sys_ioprio_get +291 i386 inotify_init sys_inotify_init +292 i386 inotify_add_watch sys_inotify_add_watch +293 i386 inotify_rm_watch sys_inotify_rm_watch +294 i386 migrate_pages sys_migrate_pages +295 i386 openat sys_openat compat_sys_openat +296 i386 mkdirat sys_mkdirat +297 i386 mknodat sys_mknodat +298 i386 fchownat sys_fchownat +299 i386 futimesat sys_futimesat compat_sys_futimesat +300 i386 fstatat64 sys_fstatat64 sys32_fstatat +301 i386 unlinkat sys_unlinkat +302 i386 renameat sys_renameat +303 i386 linkat sys_linkat +304 i386 symlinkat sys_symlinkat +305 i386 readlinkat sys_readlinkat +306 i386 fchmodat sys_fchmodat +307 i386 faccessat sys_faccessat +308 i386 pselect6 sys_pselect6 compat_sys_pselect6 +309 i386 ppoll sys_ppoll compat_sys_ppoll +310 i386 unshare sys_unshare +311 i386 set_robust_list sys_set_robust_list compat_sys_set_robust_list +312 i386 get_robust_list sys_get_robust_list compat_sys_get_robust_list +313 i386 splice sys_splice +314 i386 sync_file_range sys_sync_file_range sys32_sync_file_range +315 i386 tee sys_tee +316 i386 vmsplice sys_vmsplice compat_sys_vmsplice +317 i386 move_pages sys_move_pages compat_sys_move_pages +318 i386 getcpu sys_getcpu +319 i386 epoll_pwait sys_epoll_pwait +320 i386 utimensat sys_utimensat compat_sys_utimensat +321 i386 signalfd sys_signalfd compat_sys_signalfd +322 i386 timerfd_create sys_timerfd_create +323 i386 eventfd sys_eventfd +324 i386 fallocate sys_fallocate sys32_fallocate +325 i386 timerfd_settime sys_timerfd_settime compat_sys_timerfd_settime +326 i386 timerfd_gettime sys_timerfd_gettime compat_sys_timerfd_gettime +327 i386 signalfd4 sys_signalfd4 compat_sys_signalfd4 +328 i386 eventfd2 sys_eventfd2 +329 i386 epoll_create1 sys_epoll_create1 +330 i386 dup3 sys_dup3 +331 i386 pipe2 sys_pipe2 +332 i386 inotify_init1 sys_inotify_init1 +333 i386 preadv sys_preadv compat_sys_preadv +334 i386 pwritev sys_pwritev compat_sys_pwritev +335 i386 rt_tgsigqueueinfo sys_rt_tgsigqueueinfo compat_sys_rt_tgsigqueueinfo +336 i386 perf_event_open sys_perf_event_open +337 i386 recvmmsg sys_recvmmsg compat_sys_recvmmsg +338 i386 fanotify_init sys_fanotify_init +339 i386 fanotify_mark sys_fanotify_mark sys32_fanotify_mark +340 i386 prlimit64 sys_prlimit64 +341 i386 name_to_handle_at sys_name_to_handle_at +342 i386 open_by_handle_at sys_open_by_handle_at compat_sys_open_by_handle_at +343 i386 clock_adjtime sys_clock_adjtime compat_sys_clock_adjtime +344 i386 syncfs sys_syncfs +345 i386 sendmmsg sys_sendmmsg compat_sys_sendmmsg +346 i386 setns sys_setns +347 i386 process_vm_readv sys_process_vm_readv compat_sys_process_vm_readv +348 i386 process_vm_writev sys_process_vm_writev compat_sys_process_vm_writev diff --git a/arch/x86/syscalls/syscall_64.tbl b/arch/x86/syscalls/syscall_64.tbl new file mode 100644 index 00000000000..b440a8f7eef --- /dev/null +++ b/arch/x86/syscalls/syscall_64.tbl @@ -0,0 +1,320 @@ +# +# 64-bit system call numbers and entry vectors +# +# The format is: +# <number> <abi> <name> <entry point> +# +# The abi is always "64" for this file (for now.) +# +0 64 read sys_read +1 64 write sys_write +2 64 open sys_open +3 64 close sys_close +4 64 stat sys_newstat +5 64 fstat sys_newfstat +6 64 lstat sys_newlstat +7 64 poll sys_poll +8 64 lseek sys_lseek +9 64 mmap sys_mmap +10 64 mprotect sys_mprotect +11 64 munmap sys_munmap +12 64 brk sys_brk +13 64 rt_sigaction sys_rt_sigaction +14 64 rt_sigprocmask sys_rt_sigprocmask +15 64 rt_sigreturn stub_rt_sigreturn +16 64 ioctl sys_ioctl +17 64 pread64 sys_pread64 +18 64 pwrite64 sys_pwrite64 +19 64 readv sys_readv +20 64 writev sys_writev +21 64 access sys_access +22 64 pipe sys_pipe +23 64 select sys_select +24 64 sched_yield sys_sched_yield +25 64 mremap sys_mremap +26 64 msync sys_msync +27 64 mincore sys_mincore +28 64 madvise sys_madvise +29 64 shmget sys_shmget +30 64 shmat sys_shmat +31 64 shmctl sys_shmctl +32 64 dup sys_dup +33 64 dup2 sys_dup2 +34 64 pause sys_pause +35 64 nanosleep sys_nanosleep +36 64 getitimer sys_getitimer +37 64 alarm sys_alarm +38 64 setitimer sys_setitimer +39 64 getpid sys_getpid +40 64 sendfile sys_sendfile64 +41 64 socket sys_socket +42 64 connect sys_connect +43 64 accept sys_accept +44 64 sendto sys_sendto +45 64 recvfrom sys_recvfrom +46 64 sendmsg sys_sendmsg +47 64 recvmsg sys_recvmsg +48 64 shutdown sys_shutdown +49 64 bind sys_bind +50 64 listen sys_listen +51 64 getsockname sys_getsockname +52 64 getpeername sys_getpeername +53 64 socketpair sys_socketpair +54 64 setsockopt sys_setsockopt +55 64 getsockopt sys_getsockopt +56 64 clone stub_clone +57 64 fork stub_fork +58 64 vfork stub_vfork +59 64 execve stub_execve +60 64 exit sys_exit +61 64 wait4 sys_wait4 +62 64 kill sys_kill +63 64 uname sys_newuname +64 64 semget sys_semget +65 64 semop sys_semop +66 64 semctl sys_semctl +67 64 shmdt sys_shmdt +68 64 msgget sys_msgget +69 64 msgsnd sys_msgsnd +70 64 msgrcv sys_msgrcv +71 64 msgctl sys_msgctl +72 64 fcntl sys_fcntl +73 64 flock sys_flock +74 64 fsync sys_fsync +75 64 fdatasync sys_fdatasync +76 64 truncate sys_truncate +77 64 ftruncate sys_ftruncate +78 64 getdents sys_getdents +79 64 getcwd sys_getcwd +80 64 chdir sys_chdir +81 64 fchdir sys_fchdir +82 64 rename sys_rename +83 64 mkdir sys_mkdir +84 64 rmdir sys_rmdir +85 64 creat sys_creat +86 64 link sys_link +87 64 unlink sys_unlink +88 64 symlink sys_symlink +89 64 readlink sys_readlink +90 64 chmod sys_chmod +91 64 fchmod sys_fchmod +92 64 chown sys_chown +93 64 fchown sys_fchown +94 64 lchown sys_lchown +95 64 umask sys_umask +96 64 gettimeofday sys_gettimeofday +97 64 getrlimit sys_getrlimit +98 64 getrusage sys_getrusage +99 64 sysinfo sys_sysinfo +100 64 times sys_times +101 64 ptrace sys_ptrace +102 64 getuid sys_getuid +103 64 syslog sys_syslog +104 64 getgid sys_getgid +105 64 setuid sys_setuid +106 64 setgid sys_setgid +107 64 geteuid sys_geteuid +108 64 getegid sys_getegid +109 64 setpgid sys_setpgid +110 64 getppid sys_getppid +111 64 getpgrp sys_getpgrp +112 64 setsid sys_setsid +113 64 setreuid sys_setreuid +114 64 setregid sys_setregid +115 64 getgroups sys_getgroups +116 64 setgroups sys_setgroups +117 64 setresuid sys_setresuid +118 64 getresuid sys_getresuid +119 64 setresgid sys_setresgid +120 64 getresgid sys_getresgid +121 64 getpgid sys_getpgid +122 64 setfsuid sys_setfsuid +123 64 setfsgid sys_setfsgid +124 64 getsid sys_getsid +125 64 capget sys_capget +126 64 capset sys_capset +127 64 rt_sigpending sys_rt_sigpending +128 64 rt_sigtimedwait sys_rt_sigtimedwait +129 64 rt_sigqueueinfo sys_rt_sigqueueinfo +130 64 rt_sigsuspend sys_rt_sigsuspend +131 64 sigaltstack stub_sigaltstack +132 64 utime sys_utime +133 64 mknod sys_mknod +134 64 uselib +135 64 personality sys_personality +136 64 ustat sys_ustat +137 64 statfs sys_statfs +138 64 fstatfs sys_fstatfs +139 64 sysfs sys_sysfs +140 64 getpriority sys_getpriority +141 64 setpriority sys_setpriority +142 64 sched_setparam sys_sched_setparam +143 64 sched_getparam sys_sched_getparam +144 64 sched_setscheduler sys_sched_setscheduler +145 64 sched_getscheduler sys_sched_getscheduler +146 64 sched_get_priority_max sys_sched_get_priority_max +147 64 sched_get_priority_min sys_sched_get_priority_min +148 64 sched_rr_get_interval sys_sched_rr_get_interval +149 64 mlock sys_mlock +150 64 munlock sys_munlock +151 64 mlockall sys_mlockall +152 64 munlockall sys_munlockall +153 64 vhangup sys_vhangup +154 64 modify_ldt sys_modify_ldt +155 64 pivot_root sys_pivot_root +156 64 _sysctl sys_sysctl +157 64 prctl sys_prctl +158 64 arch_prctl sys_arch_prctl +159 64 adjtimex sys_adjtimex +160 64 setrlimit sys_setrlimit +161 64 chroot sys_chroot +162 64 sync sys_sync +163 64 acct sys_acct +164 64 settimeofday sys_settimeofday +165 64 mount sys_mount +166 64 umount2 sys_umount +167 64 swapon sys_swapon +168 64 swapoff sys_swapoff +169 64 reboot sys_reboot +170 64 sethostname sys_sethostname +171 64 setdomainname sys_setdomainname +172 64 iopl stub_iopl +173 64 ioperm sys_ioperm +174 64 create_module +175 64 init_module sys_init_module +176 64 delete_module sys_delete_module +177 64 get_kernel_syms +178 64 query_module +179 64 quotactl sys_quotactl +180 64 nfsservctl +181 64 getpmsg +182 64 putpmsg +183 64 afs_syscall +184 64 tuxcall +185 64 security +186 64 gettid sys_gettid +187 64 readahead sys_readahead +188 64 setxattr sys_setxattr +189 64 lsetxattr sys_lsetxattr +190 64 fsetxattr sys_fsetxattr +191 64 getxattr sys_getxattr +192 64 lgetxattr sys_lgetxattr +193 64 fgetxattr sys_fgetxattr +194 64 listxattr sys_listxattr +195 64 llistxattr sys_llistxattr +196 64 flistxattr sys_flistxattr +197 64 removexattr sys_removexattr +198 64 lremovexattr sys_lremovexattr +199 64 fremovexattr sys_fremovexattr +200 64 tkill sys_tkill +201 64 time sys_time +202 64 futex sys_futex +203 64 sched_setaffinity sys_sched_setaffinity +204 64 sched_getaffinity sys_sched_getaffinity +205 64 set_thread_area +206 64 io_setup sys_io_setup +207 64 io_destroy sys_io_destroy +208 64 io_getevents sys_io_getevents +209 64 io_submit sys_io_submit +210 64 io_cancel sys_io_cancel +211 64 get_thread_area +212 64 lookup_dcookie sys_lookup_dcookie +213 64 epoll_create sys_epoll_create +214 64 epoll_ctl_old +215 64 epoll_wait_old +216 64 remap_file_pages sys_remap_file_pages +217 64 getdents64 sys_getdents64 +218 64 set_tid_address sys_set_tid_address +219 64 restart_syscall sys_restart_syscall +220 64 semtimedop sys_semtimedop +221 64 fadvise64 sys_fadvise64 +222 64 timer_create sys_timer_create +223 64 timer_settime sys_timer_settime +224 64 timer_gettime sys_timer_gettime +225 64 timer_getoverrun sys_timer_getoverrun +226 64 timer_delete sys_timer_delete +227 64 clock_settime sys_clock_settime +228 64 clock_gettime sys_clock_gettime +229 64 clock_getres sys_clock_getres +230 64 clock_nanosleep sys_clock_nanosleep +231 64 exit_group sys_exit_group +232 64 epoll_wait sys_epoll_wait +233 64 epoll_ctl sys_epoll_ctl +234 64 tgkill sys_tgkill +235 64 utimes sys_utimes +236 64 vserver +237 64 mbind sys_mbind +238 64 set_mempolicy sys_set_mempolicy +239 64 get_mempolicy sys_get_mempolicy +240 64 mq_open sys_mq_open +241 64 mq_unlink sys_mq_unlink +242 64 mq_timedsend sys_mq_timedsend +243 64 mq_timedreceive sys_mq_timedreceive +244 64 mq_notify sys_mq_notify +245 64 mq_getsetattr sys_mq_getsetattr +246 64 kexec_load sys_kexec_load +247 64 waitid sys_waitid +248 64 add_key sys_add_key +249 64 request_key sys_request_key +250 64 keyctl sys_keyctl +251 64 ioprio_set sys_ioprio_set +252 64 ioprio_get sys_ioprio_get +253 64 inotify_init sys_inotify_init +254 64 inotify_add_watch sys_inotify_add_watch +255 64 inotify_rm_watch sys_inotify_rm_watch +256 64 migrate_pages sys_migrate_pages +257 64 openat sys_openat +258 64 mkdirat sys_mkdirat +259 64 mknodat sys_mknodat +260 64 fchownat sys_fchownat +261 64 futimesat sys_futimesat +262 64 newfstatat sys_newfstatat +263 64 unlinkat sys_unlinkat +264 64 renameat sys_renameat +265 64 linkat sys_linkat +266 64 symlinkat sys_symlinkat +267 64 readlinkat sys_readlinkat +268 64 fchmodat sys_fchmodat +269 64 faccessat sys_faccessat +270 64 pselect6 sys_pselect6 +271 64 ppoll sys_ppoll +272 64 unshare sys_unshare +273 64 set_robust_list sys_set_robust_list +274 64 get_robust_list sys_get_robust_list +275 64 splice sys_splice +276 64 tee sys_tee +277 64 sync_file_range sys_sync_file_range +278 64 vmsplice sys_vmsplice +279 64 move_pages sys_move_pages +280 64 utimensat sys_utimensat +281 64 epoll_pwait sys_epoll_pwait +282 64 signalfd sys_signalfd +283 64 timerfd_create sys_timerfd_create +284 64 eventfd sys_eventfd +285 64 fallocate sys_fallocate +286 64 timerfd_settime sys_timerfd_settime +287 64 timerfd_gettime sys_timerfd_gettime +288 64 accept4 sys_accept4 +289 64 signalfd4 sys_signalfd4 +290 64 eventfd2 sys_eventfd2 +291 64 epoll_create1 sys_epoll_create1 +292 64 dup3 sys_dup3 +293 64 pipe2 sys_pipe2 +294 64 inotify_init1 sys_inotify_init1 +295 64 preadv sys_preadv +296 64 pwritev sys_pwritev +297 64 rt_tgsigqueueinfo sys_rt_tgsigqueueinfo +298 64 perf_event_open sys_perf_event_open +299 64 recvmmsg sys_recvmmsg +300 64 fanotify_init sys_fanotify_init +301 64 fanotify_mark sys_fanotify_mark +302 64 prlimit64 sys_prlimit64 +303 64 name_to_handle_at sys_name_to_handle_at +304 64 open_by_handle_at sys_open_by_handle_at +305 64 clock_adjtime sys_clock_adjtime +306 64 syncfs sys_syncfs +307 64 sendmmsg sys_sendmmsg +308 64 setns sys_setns +309 64 getcpu sys_getcpu +310 64 process_vm_readv sys_process_vm_readv +311 64 process_vm_writev sys_process_vm_writev diff --git a/arch/x86/syscalls/syscallhdr.sh b/arch/x86/syscalls/syscallhdr.sh new file mode 100644 index 00000000000..31fd5f1f38f --- /dev/null +++ b/arch/x86/syscalls/syscallhdr.sh @@ -0,0 +1,27 @@ +#!/bin/sh + +in="$1" +out="$2" +my_abis=`echo "($3)" | tr ',' '|'` +prefix="$4" +offset="$5" + +fileguard=_ASM_X86_`basename "$out" | sed \ + -e 'y/abcdefghijklmnopqrstuvwxyz/ABCDEFGHIJKLMNOPQRSTUVWXYZ/' \ + -e 's/[^A-Z0-9_]/_/g' -e 's/__/_/g'` +grep -E "^[0-9A-Fa-fXx]+[[:space:]]+${my_abis}" "$in" | sort -n | ( + echo "#ifndef ${fileguard}" + echo "#define ${fileguard} 1" + echo "" + + while read nr abi name entry ; do + if [ -z "$offset" ]; then + echo "#define __NR_${prefix}${name} $nr" + else + echo "#define __NR_${prefix}${name} ($offset + $nr)" + fi + done + + echo "" + echo "#endif /* ${fileguard} */" +) > "$out" diff --git a/arch/x86/syscalls/syscalltbl.sh b/arch/x86/syscalls/syscalltbl.sh new file mode 100644 index 00000000000..0e7f8ec071e --- /dev/null +++ b/arch/x86/syscalls/syscalltbl.sh @@ -0,0 +1,15 @@ +#!/bin/sh + +in="$1" +out="$2" + +grep '^[0-9]' "$in" | sort -n | ( + while read nr abi name entry compat; do + abi=`echo "$abi" | tr '[a-z]' '[A-Z]'` + if [ -n "$compat" ]; then + echo "__SYSCALL_${abi}($nr, $entry, $compat)" + elif [ -n "$entry" ]; then + echo "__SYSCALL_${abi}($nr, $entry, $entry)" + fi + done +) > "$out" diff --git a/arch/x86/um/Makefile b/arch/x86/um/Makefile index 8fb58400e41..5d065b2222d 100644 --- a/arch/x86/um/Makefile +++ b/arch/x86/um/Makefile @@ -37,7 +37,8 @@ subarch-$(CONFIG_MODULES) += ../kernel/module.o USER_OBJS := bugs_$(BITS).o ptrace_user.o fault.o extra-y += user-offsets.s -$(obj)/user-offsets.s: c_flags = -Wp,-MD,$(depfile) $(USER_CFLAGS) +$(obj)/user-offsets.s: c_flags = -Wp,-MD,$(depfile) $(USER_CFLAGS) \ + -Iarch/x86/include/generated UNPROFILE_OBJS := stub_segv.o CFLAGS_stub_segv.o := $(CFLAGS_NO_HARDENING) diff --git a/arch/x86/um/shared/sysdep/ptrace.h b/arch/x86/um/shared/sysdep/ptrace.h index 711b1621747..2bbe1ec2d96 100644 --- a/arch/x86/um/shared/sysdep/ptrace.h +++ b/arch/x86/um/shared/sysdep/ptrace.h @@ -1,5 +1,15 @@ +#ifndef __SYSDEP_X86_PTRACE_H +#define __SYSDEP_X86_PTRACE_H + #ifdef __i386__ #include "ptrace_32.h" #else #include "ptrace_64.h" #endif + +static inline long regs_return_value(struct uml_pt_regs *regs) +{ + return UPT_SYSCALL_RET(regs); +} + +#endif /* __SYSDEP_X86_PTRACE_H */ diff --git a/arch/x86/um/sys_call_table_32.S b/arch/x86/um/sys_call_table_32.S deleted file mode 100644 index a7ca80d2dce..00000000000 --- a/arch/x86/um/sys_call_table_32.S +++ /dev/null @@ -1,26 +0,0 @@ -#include <linux/linkage.h> -/* Steal i386 syscall table for our purposes, but with some slight changes.*/ - -#define sys_iopl sys_ni_syscall -#define sys_ioperm sys_ni_syscall - -#define sys_vm86old sys_ni_syscall -#define sys_vm86 sys_ni_syscall - -#define old_mmap sys_old_mmap - -#define ptregs_fork sys_fork -#define ptregs_execve sys_execve -#define ptregs_iopl sys_iopl -#define ptregs_vm86old sys_vm86old -#define ptregs_clone sys_clone -#define ptregs_vm86 sys_vm86 -#define ptregs_sigaltstack sys_sigaltstack -#define ptregs_vfork sys_vfork - -.section .rodata,"a" - -#include "../kernel/syscall_table_32.S" - -ENTRY(syscall_table_size) -.long .-sys_call_table diff --git a/arch/x86/um/sys_call_table_32.c b/arch/x86/um/sys_call_table_32.c new file mode 100644 index 00000000000..416bd40c0eb --- /dev/null +++ b/arch/x86/um/sys_call_table_32.c @@ -0,0 +1,55 @@ +/* + * System call table for UML/i386, copied from arch/x86/kernel/syscall_*.c + * with some changes for UML. + */ + +#include <linux/linkage.h> +#include <linux/sys.h> +#include <linux/cache.h> +#include <generated/user_constants.h> + +#define __NO_STUBS + +/* + * Below you can see, in terms of #define's, the differences between the x86-64 + * and the UML syscall table. + */ + +/* Not going to be implemented by UML, since we have no hardware. */ +#define sys_iopl sys_ni_syscall +#define sys_ioperm sys_ni_syscall + +#define sys_vm86old sys_ni_syscall +#define sys_vm86 sys_ni_syscall + +#define old_mmap sys_old_mmap + +#define ptregs_fork sys_fork +#define ptregs_execve sys_execve +#define ptregs_iopl sys_iopl +#define ptregs_vm86old sys_vm86old +#define ptregs_clone sys_clone +#define ptregs_vm86 sys_vm86 +#define ptregs_sigaltstack sys_sigaltstack +#define ptregs_vfork sys_vfork + +#define __SYSCALL_I386(nr, sym, compat) extern asmlinkage void sym(void) ; +#include <asm/syscalls_32.h> + +#undef __SYSCALL_I386 +#define __SYSCALL_I386(nr, sym, compat) [ nr ] = sym, + +typedef void (*sys_call_ptr_t)(void); + +extern void sys_ni_syscall(void); + +const sys_call_ptr_t sys_call_table[] __cacheline_aligned = { + /* + * Smells like a compiler bug -- it doesn't work + * when the & below is removed. + */ + [0 ... __NR_syscall_max] = &sys_ni_syscall, +#include <asm/syscalls_32.h> +}; + +int syscall_table_size = sizeof(sys_call_table); diff --git a/arch/x86/um/sys_call_table_64.c b/arch/x86/um/sys_call_table_64.c index 99522f78b16..fe626c3ba01 100644 --- a/arch/x86/um/sys_call_table_64.c +++ b/arch/x86/um/sys_call_table_64.c @@ -1,11 +1,12 @@ /* - * System call table for UML/x86-64, copied from arch/x86_64/kernel/syscall.c + * System call table for UML/x86-64, copied from arch/x86/kernel/syscall_*.c * with some changes for UML. */ #include <linux/linkage.h> #include <linux/sys.h> #include <linux/cache.h> +#include <generated/user_constants.h> #define __NO_STUBS @@ -34,31 +35,23 @@ #define stub_sigaltstack sys_sigaltstack #define stub_rt_sigreturn sys_rt_sigreturn -#define __SYSCALL(nr, sym) extern asmlinkage void sym(void) ; -#undef _ASM_X86_UNISTD_64_H -#include "../../x86/include/asm/unistd_64.h" +#define __SYSCALL_64(nr, sym, compat) extern asmlinkage void sym(void) ; +#include <asm/syscalls_64.h> -#undef __SYSCALL -#define __SYSCALL(nr, sym) [ nr ] = sym, -#undef _ASM_X86_UNISTD_64_H +#undef __SYSCALL_64 +#define __SYSCALL_64(nr, sym, compat) [ nr ] = sym, typedef void (*sys_call_ptr_t)(void); extern void sys_ni_syscall(void); -/* - * We used to have a trick here which made sure that holes in the - * x86_64 table were filled in with sys_ni_syscall, but a comment in - * unistd_64.h says that holes aren't allowed, so the trick was - * removed. - * The trick looked like this - * [0 ... UM_NR_syscall_max] = &sys_ni_syscall - * before including unistd_64.h - the later initializations overwrote - * the sys_ni_syscall filler. - */ - -sys_call_ptr_t sys_call_table[] __cacheline_aligned = { -#include <asm/unistd_64.h> +const sys_call_ptr_t sys_call_table[] __cacheline_aligned = { + /* + * Smells like a compiler bug -- it doesn't work + * when the & below is removed. + */ + [0 ... __NR_syscall_max] = &sys_ni_syscall, +#include <asm/syscalls_64.h> }; int syscall_table_size = sizeof(sys_call_table); diff --git a/arch/x86/um/user-offsets.c b/arch/x86/um/user-offsets.c index ca49be8ddd0..5edf4f4bbf5 100644 --- a/arch/x86/um/user-offsets.c +++ b/arch/x86/um/user-offsets.c @@ -8,6 +8,18 @@ #include <asm/ptrace.h> #include <asm/types.h> +#ifdef __i386__ +#define __SYSCALL_I386(nr, sym, compat) [nr] = 1, +static char syscalls[] = { +#include <asm/syscalls_32.h> +}; +#else +#define __SYSCALL_64(nr, sym, compat) [nr] = 1, +static char syscalls[] = { +#include <asm/syscalls_64.h> +}; +#endif + #define DEFINE(sym, val) \ asm volatile("\n->" #sym " %0 " #val : : "i" (val)) @@ -77,4 +89,7 @@ void foo(void) DEFINE(UM_PROT_READ, PROT_READ); DEFINE(UM_PROT_WRITE, PROT_WRITE); DEFINE(UM_PROT_EXEC, PROT_EXEC); + + DEFINE(__NR_syscall_max, sizeof(syscalls) - 1); + DEFINE(NR_syscalls, sizeof(syscalls)); } |