diff options
Diffstat (limited to 'xenolinux-2.4.24-sparse/arch/xeno/kernel')
| -rw-r--r-- | xenolinux-2.4.24-sparse/arch/xeno/kernel/Makefile | 15 | ||||
| -rw-r--r-- | xenolinux-2.4.24-sparse/arch/xeno/kernel/entry.S | 776 | ||||
| -rw-r--r-- | xenolinux-2.4.24-sparse/arch/xeno/kernel/head.S | 66 | ||||
| -rw-r--r-- | xenolinux-2.4.24-sparse/arch/xeno/kernel/hypervisor.c | 128 | ||||
| -rw-r--r-- | xenolinux-2.4.24-sparse/arch/xeno/kernel/i386_ksyms.c | 163 | ||||
| -rw-r--r-- | xenolinux-2.4.24-sparse/arch/xeno/kernel/ioport.c | 48 | ||||
| -rw-r--r-- | xenolinux-2.4.24-sparse/arch/xeno/kernel/irq.c | 1137 | ||||
| -rw-r--r-- | xenolinux-2.4.24-sparse/arch/xeno/kernel/ldt.c | 182 | ||||
| -rw-r--r-- | xenolinux-2.4.24-sparse/arch/xeno/kernel/process.c | 489 | ||||
| -rw-r--r-- | xenolinux-2.4.24-sparse/arch/xeno/kernel/setup.c | 1215 | ||||
| -rw-r--r-- | xenolinux-2.4.24-sparse/arch/xeno/kernel/signal.c | 717 | ||||
| -rw-r--r-- | xenolinux-2.4.24-sparse/arch/xeno/kernel/time.c | 526 | ||||
| -rw-r--r-- | xenolinux-2.4.24-sparse/arch/xeno/kernel/traps.c | 620 |
13 files changed, 6082 insertions, 0 deletions
diff --git a/xenolinux-2.4.24-sparse/arch/xeno/kernel/Makefile b/xenolinux-2.4.24-sparse/arch/xeno/kernel/Makefile new file mode 100644 index 0000000000..a43a615e2f --- /dev/null +++ b/xenolinux-2.4.24-sparse/arch/xeno/kernel/Makefile @@ -0,0 +1,15 @@ + +.S.o: + $(CC) $(AFLAGS) -traditional -c $< -o $*.o + +all: kernel.o head.o init_task.o + +O_TARGET := kernel.o + +export-objs := i386_ksyms.o + +obj-y := process.o semaphore.o signal.o entry.o traps.o irq.o \ + ptrace.o ioport.o ldt.o setup.o time.o sys_i386.o \ + i386_ksyms.o i387.o hypervisor.o + +include $(TOPDIR)/Rules.make diff --git a/xenolinux-2.4.24-sparse/arch/xeno/kernel/entry.S b/xenolinux-2.4.24-sparse/arch/xeno/kernel/entry.S new file mode 100644 index 0000000000..4f676eefc6 --- /dev/null +++ b/xenolinux-2.4.24-sparse/arch/xeno/kernel/entry.S @@ -0,0 +1,776 @@ +/* + * linux/arch/i386/entry.S + * + * Copyright (C) 1991, 1992 Linus Torvalds + */ + +/* + * entry.S contains the system-call and fault low-level handling routines. + * This also contains the timer-interrupt handler, as well as all interrupts + * and faults that can result in a task-switch. + * + * NOTE: This code handles signal-recognition, which happens every time + * after a timer-interrupt and after each system call. + * + * I changed all the .align's to 4 (16 byte alignment), as that's faster + * on a 486. + * + * Stack layout in 'ret_from_system_call': + * ptrace needs to have all regs on the stack. + * if the order here is changed, it needs to be + * updated in fork.c:copy_process, signal.c:do_signal, + * ptrace.c and ptrace.h + * + * 0(%esp) - %ebx + * 4(%esp) - %ecx + * 8(%esp) - %edx + * C(%esp) - %esi + * 10(%esp) - %edi + * 14(%esp) - %ebp + * 18(%esp) - %eax + * 1C(%esp) - %ds + * 20(%esp) - %es + * 24(%esp) - orig_eax + * 28(%esp) - %eip + * 2C(%esp) - %cs + * 30(%esp) - %eflags + * 34(%esp) - %oldesp + * 38(%esp) - %oldss + * + * "current" is in register %ebx during any slow entries. + */ + +#include <linux/config.h> +#include <linux/sys.h> +#include <linux/linkage.h> +#include <asm/segment.h> +#include <asm/smp.h> + +EBX = 0x00 +ECX = 0x04 +EDX = 0x08 +ESI = 0x0C +EDI = 0x10 +EBP = 0x14 +EAX = 0x18 +DS = 0x1C +ES = 0x20 +ORIG_EAX = 0x24 +EIP = 0x28 +CS = 0x2C +EFLAGS = 0x30 +OLDESP = 0x34 +OLDSS = 0x38 + +CF_MASK = 0x00000001 +TF_MASK = 0x00000100 +IF_MASK = 0x00000200 +DF_MASK = 0x00000400 +NT_MASK = 0x00004000 + +/* + * these are offsets into the task-struct. + */ +state = 0 +flags = 4 +sigpending = 8 +addr_limit = 12 +exec_domain = 16 +need_resched = 20 +tsk_ptrace = 24 +processor = 52 + +ENOSYS = 38 + + +#define SAVE_ALL \ + cld; \ + pushl %es; \ + pushl %ds; \ + pushl %eax; \ + pushl %ebp; \ + pushl %edi; \ + pushl %esi; \ + pushl %edx; \ + pushl %ecx; \ + pushl %ebx; \ + movl $(__KERNEL_DS),%edx; \ + movl %edx,%ds; \ + movl %edx,%es; + +#define RESTORE_ALL \ + popl %ebx; \ + popl %ecx; \ + popl %edx; \ + popl %esi; \ + popl %edi; \ + popl %ebp; \ + popl %eax; \ +1: popl %ds; \ +2: popl %es; \ + addl $4,%esp; \ +3: iret; \ +.section .fixup,"ax"; \ +4: movl $0,(%esp); \ + jmp 1b; \ +5: movl $0,(%esp); \ + jmp 2b; \ +6: pushl %ss; \ + popl %ds; \ + pushl %ss; \ + popl %es; \ + pushl $11; \ + call do_exit; \ +.previous; \ +.section __ex_table,"a";\ + .align 4; \ + .long 1b,4b; \ + .long 2b,5b; \ + .long 3b,6b; \ +.previous + +#define GET_CURRENT(reg) \ + movl $-8192, reg; \ + andl %esp, reg + +ENTRY(lcall7) + pushfl # We get a different stack layout with call + pushl %eax # gates, which has to be cleaned up later.. + SAVE_ALL + movl EIP(%esp),%eax # due to call gates, this is eflags, not eip.. + movl CS(%esp),%edx # this is eip.. + movl EFLAGS(%esp),%ecx # and this is cs.. + movl %eax,EFLAGS(%esp) # + andl $~(NT_MASK|TF_MASK|DF_MASK), %eax + pushl %eax + popfl + movl %edx,EIP(%esp) # Now we move them to their "normal" places + movl %ecx,CS(%esp) # + movl %esp,%ebx + pushl %ebx + andl $-8192,%ebx # GET_CURRENT + movl exec_domain(%ebx),%edx # Get the execution domain + movl 4(%edx),%edx # Get the lcall7 handler for the domain + pushl $0x7 + call *%edx + addl $4, %esp + popl %eax + jmp ret_from_sys_call + +ENTRY(lcall27) + pushfl # We get a different stack layout with call + pushl %eax # gates, which has to be cleaned up later.. + SAVE_ALL + movl EIP(%esp),%eax # due to call gates, this is eflags, not eip.. + movl CS(%esp),%edx # this is eip.. + movl EFLAGS(%esp),%ecx # and this is cs.. + movl %eax,EFLAGS(%esp) # + andl $~(NT_MASK|TF_MASK|DF_MASK), %eax + pushl %eax + popfl + movl %edx,EIP(%esp) # Now we move them to their "normal" places + movl %ecx,CS(%esp) # + movl %esp,%ebx + pushl %ebx + andl $-8192,%ebx # GET_CURRENT + movl exec_domain(%ebx),%edx # Get the execution domain + movl 4(%edx),%edx # Get the lcall7 handler for the domain + pushl $0x27 + call *%edx + addl $4, %esp + popl %eax + jmp ret_from_sys_call + +ENTRY(ret_from_fork) + pushl %ebx + call SYMBOL_NAME(schedule_tail) + addl $4, %esp + GET_CURRENT(%ebx) + testb $0x02,tsk_ptrace(%ebx) # PT_TRACESYS + jne tracesys_exit + jmp ret_from_sys_call + +/* + * Return to user mode is not as complex as all this looks, + * but we want the default path for a system call return to + * go as quickly as possible which is why some of this is + * less clear than it otherwise should be. + */ +ENTRY(system_call) + pushl %eax # save orig_eax + SAVE_ALL + GET_CURRENT(%ebx) + testb $0x02,tsk_ptrace(%ebx) # PT_TRACESYS + jne tracesys + cmpl $(NR_syscalls),%eax + jae badsys + call *SYMBOL_NAME(sys_call_table)(,%eax,4) + movl %eax,EAX(%esp) # save the return value +ENTRY(ret_from_sys_call) + movl SYMBOL_NAME(HYPERVISOR_shared_info),%esi + btrl $EVENTS_MASTER_ENABLE_BIT,4(%esi) # make tests atomic +ret_syscall_tests: + cmpl $0,need_resched(%ebx) + jne reschedule + cmpl $0,sigpending(%ebx) + je safesti # ensure need_resched updates are seen +signal_return: + btsl $EVENTS_MASTER_ENABLE_BIT,4(%esi) # reenable event callbacks + movl %esp,%eax + xorl %edx,%edx + call SYMBOL_NAME(do_signal) + jmp ret_from_sys_call + + ALIGN +restore_all: + RESTORE_ALL + + ALIGN +tracesys: + movl $-ENOSYS,EAX(%esp) + call SYMBOL_NAME(syscall_trace) + movl ORIG_EAX(%esp),%eax + cmpl $(NR_syscalls),%eax + jae tracesys_exit + call *SYMBOL_NAME(sys_call_table)(,%eax,4) + movl %eax,EAX(%esp) # save the return value +tracesys_exit: + call SYMBOL_NAME(syscall_trace) + jmp ret_from_sys_call +badsys: + movl $-ENOSYS,EAX(%esp) + jmp ret_from_sys_call + + ALIGN +ENTRY(ret_from_intr) + GET_CURRENT(%ebx) +ret_from_exception: + movb CS(%esp),%al + testl $2,%eax + jne ret_from_sys_call + jmp restore_all + + ALIGN +reschedule: + btsl $EVENTS_MASTER_ENABLE_BIT,4(%esi) # reenable event callbacks + call SYMBOL_NAME(schedule) # test + jmp ret_from_sys_call + +ENTRY(divide_error) + pushl $0 # no error code + pushl $ SYMBOL_NAME(do_divide_error) + ALIGN +error_code: + pushl %ds + pushl %eax + xorl %eax,%eax + pushl %ebp + pushl %edi + pushl %esi + pushl %edx + decl %eax # eax = -1 + pushl %ecx + pushl %ebx + GET_CURRENT(%ebx) + cld + movl %es,%ecx + movl ORIG_EAX(%esp), %esi # get the error code + movl ES(%esp), %edi # get the function address + movl %eax, ORIG_EAX(%esp) + movl %ecx, ES(%esp) + movl %esp,%edx + pushl %esi # push the error code + pushl %edx # push the pt_regs pointer + movl $(__KERNEL_DS),%edx + movl %edx,%ds + movl %edx,%es + call *%edi + addl $8,%esp + jmp ret_from_exception + +# A note on the "critical region" in our callback handler. +# We want to avoid stacking callback handlers due to events occurring +# during handling of the last event. To do this, we keep events disabled +# until we've done all processing. HOWEVER, we must enable events before +# popping the stack frame (can't be done atomically) and so it would still +# be possible to get enough handler activations to overflow the stack. +# Although unlikely, bugs of that kind are hard to track down, so we'd +# like to avoid the possibility. +# So, on entry to the handler we detect whether we interrupted an +# existing activation in its critical region -- if so, we pop the current +# activation and restart the handler using the previous one. +ENTRY(hypervisor_callback) + pushl %eax + SAVE_ALL + GET_CURRENT(%ebx) + movl EIP(%esp),%eax + cmpl $scrit,%eax + jb 11f + cmpl $ecrit,%eax + jb critical_region_fixup +11: push %esp + call do_hypervisor_callback + add $4,%esp + movl SYMBOL_NAME(HYPERVISOR_shared_info),%esi + movb CS(%esp),%cl + test $2,%cl # slow return to ring 2 or 3 + jne ret_syscall_tests +safesti:btsl $EVENTS_MASTER_ENABLE_BIT,4(%esi) # reenable event callbacks +scrit: /**** START OF CRITICAL REGION ****/ + cmpl $0,(%esi) + jne 14f # process more events if necessary... + RESTORE_ALL +14: btrl $EVENTS_MASTER_ENABLE_BIT,4(%esi) + jmp 11b +ecrit: /**** END OF CRITICAL REGION ****/ +# [How we do the fixup]. We want to merge the current stack frame with the +# just-interrupted frame. How we do this depends on where in the critical +# region the interrupted handler was executing, and so how many saved +# registers are in each frame. We do this quickly using the lookup table +# 'critical_fixup_table'. For each byte offset in the critical region, it +# provides the number of bytes which have already been popped from the +# interrupted stack frame. +critical_region_fixup: + addl $critical_fixup_table-scrit,%eax + movzbl (%eax),%eax # %eax contains num bytes popped + mov %esp,%esi + add %eax,%esi # %esi points at end of src region + mov %esp,%edi + add $0x34,%edi # %edi points at end of dst region + mov %eax,%ecx + shr $2,%ecx # convert words to bytes + je 16f # skip loop if nothing to copy +15: subl $4,%esi # pre-decrementing copy loop + subl $4,%edi + movl (%esi),%eax + movl %eax,(%edi) + loop 15b +16: movl %edi,%esp # final %edi is top of merged stack + jmp 11b + +critical_fixup_table: + .byte 0x00,0x00,0x00 # cmpl $0,(%esi) + .byte 0x00,0x00 # jne 14f + .byte 0x00 # pop %ebx + .byte 0x04 # pop %ecx + .byte 0x08 # pop %edx + .byte 0x0c # pop %esi + .byte 0x10 # pop %edi + .byte 0x14 # pop %ebp + .byte 0x18 # pop %eax + .byte 0x1c # pop %ds + .byte 0x20 # pop %es + .byte 0x24,0x24,0x24 # add $4,%esp + .byte 0x28 # iret + .byte 0x00,0x00,0x00,0x00,0x00 # btrl $31,4(%esi) + .byte 0x00,0x00 # jmp 11b + +# Hypervisor uses this for application faults while it executes. +ENTRY(failsafe_callback) +1: pop %ds +2: pop %es +3: pop %fs +4: pop %gs +5: iret +.section .fixup,"ax"; \ +6: movl $0,(%esp); \ + jmp 1b; \ +7: movl $0,(%esp); \ + jmp 2b; \ +8: movl $0,(%esp); \ + jmp 3b; \ +9: movl $0,(%esp); \ + jmp 4b; \ +10: pushl %ss; \ + popl %ds; \ + pushl %ss; \ + popl %es; \ + pushl $11; \ + call do_exit; \ +.previous; \ +.section __ex_table,"a";\ + .align 4; \ + .long 1b,6b; \ + .long 2b,7b; \ + .long 3b,8b; \ + .long 4b,9b; \ + .long 5b,10b; \ +.previous + +ENTRY(coprocessor_error) + pushl $0 + pushl $ SYMBOL_NAME(do_coprocessor_error) + jmp error_code + +ENTRY(simd_coprocessor_error) + pushl $0 + pushl $ SYMBOL_NAME(do_simd_coprocessor_error) + jmp error_code + +ENTRY(device_not_available) + pushl $-1 # mark this as an int + SAVE_ALL + GET_CURRENT(%ebx) + call SYMBOL_NAME(math_state_restore) + jmp ret_from_exception + +ENTRY(debug) + pushl $0 + pushl $ SYMBOL_NAME(do_debug) + jmp error_code + +ENTRY(int3) + pushl $0 + pushl $ SYMBOL_NAME(do_int3) + jmp error_code + +ENTRY(overflow) + pushl $0 + pushl $ SYMBOL_NAME(do_overflow) + jmp error_code + +ENTRY(bounds) + pushl $0 + pushl $ SYMBOL_NAME(do_bounds) + jmp error_code + +ENTRY(invalid_op) + pushl $0 + pushl $ SYMBOL_NAME(do_invalid_op) + jmp error_code + +ENTRY(coprocessor_segment_overrun) + pushl $0 + pushl $ SYMBOL_NAME(do_coprocessor_segment_overrun) + jmp error_code + +ENTRY(double_fault) + pushl $ SYMBOL_NAME(do_double_fault) + jmp error_code + +ENTRY(invalid_TSS) + pushl $ SYMBOL_NAME(do_invalid_TSS) + jmp error_code + +ENTRY(segment_not_present) + pushl $ SYMBOL_NAME(do_segment_not_present) + jmp error_code + +ENTRY(stack_segment) + pushl $ SYMBOL_NAME(do_stack_segment) + jmp error_code + +ENTRY(general_protection) + pushl $ SYMBOL_NAME(do_general_protection) + jmp error_code + +ENTRY(alignment_check) + pushl $ SYMBOL_NAME(do_alignment_check) + jmp error_code + +# This handler is special, because it gets an extra value on its stack, +# which is the linear faulting address. +ENTRY(page_fault) + pushl %ds + pushl %eax + xorl %eax,%eax + pushl %ebp + pushl %edi + pushl %esi + pushl %edx + decl %eax # eax = -1 + pushl %ecx + pushl %ebx + GET_CURRENT(%ebx) + cld + movl %es,%ecx + movl ORIG_EAX(%esp), %esi # get the error code + movl ES(%esp), %edi # get the faulting address + movl %eax, ORIG_EAX(%esp) + movl %ecx, ES(%esp) + movl %esp,%edx + pushl %edi # push the faulting address + pushl %esi # push the error code + pushl %edx # push the pt_regs pointer + movl $(__KERNEL_DS),%edx + movl %edx,%ds + movl %edx,%es + call SYMBOL_NAME(do_page_fault) + addl $12,%esp + jmp ret_from_exception + +ENTRY(machine_check) + pushl $0 + pushl $ SYMBOL_NAME(do_machine_check) + jmp error_code + +ENTRY(spurious_interrupt_bug) + pushl $0 + pushl $ SYMBOL_NAME(do_spurious_interrupt_bug) + jmp error_code + +.data +ENTRY(sys_call_table) + .long SYMBOL_NAME(sys_ni_syscall) /* 0 - old "setup()" system call*/ + .long SYMBOL_NAME(sys_exit) + .long SYMBOL_NAME(sys_fork) + .long SYMBOL_NAME(sys_read) + .long SYMBOL_NAME(sys_write) + .long SYMBOL_NAME(sys_open) /* 5 */ + .long SYMBOL_NAME(sys_close) + .long SYMBOL_NAME(sys_waitpid) + .long SYMBOL_NAME(sys_creat) + .long SYMBOL_NAME(sys_link) + .long SYMBOL_NAME(sys_unlink) /* 10 */ + .long SYMBOL_NAME(sys_execve) + .long SYMBOL_NAME(sys_chdir) + .long SYMBOL_NAME(sys_time) + .long SYMBOL_NAME(sys_mknod) + .long SYMBOL_NAME(sys_chmod) /* 15 */ + .long SYMBOL_NAME(sys_lchown16) + .long SYMBOL_NAME(sys_ni_syscall) /* old break syscall holder */ + .long SYMBOL_NAME(sys_stat) + .long SYMBOL_NAME(sys_lseek) + .long SYMBOL_NAME(sys_getpid) /* 20 */ + .long SYMBOL_NAME(sys_mount) + .long SYMBOL_NAME(sys_oldumount) + .long SYMBOL_NAME(sys_setuid16) + .long SYMBOL_NAME(sys_getuid16) + .long SYMBOL_NAME(sys_stime) /* 25 */ + .long SYMBOL_NAME(sys_ptrace) + .long SYMBOL_NAME(sys_alarm) + .long SYMBOL_NAME(sys_fstat) + .long SYMBOL_NAME(sys_pause) + .long SYMBOL_NAME(sys_utime) /* 30 */ + .long SYMBOL_NAME(sys_ni_syscall) /* old stty syscall holder */ + .long SYMBOL_NAME(sys_ni_syscall) /* old gtty syscall holder */ + .long SYMBOL_NAME(sys_access) + .long SYMBOL_NAME(sys_nice) + .long SYMBOL_NAME(sys_ni_syscall) /* 35 */ /* old ftime syscall holder */ + .long SYMBOL_NAME(sys_sync) + .long SYMBOL_NAME(sys_kill) + .long SYMBOL_NAME(sys_rename) + .long SYMBOL_NAME(sys_mkdir) + .long SYMBOL_NAME(sys_rmdir) /* 40 */ + .long SYMBOL_NAME(sys_dup) + .long SYMBOL_NAME(sys_pipe) + .long SYMBOL_NAME(sys_times) + .long SYMBOL_NAME(sys_ni_syscall) /* old prof syscall holder */ + .long SYMBOL_NAME(sys_brk) /* 45 */ + .long SYMBOL_NAME(sys_setgid16) + .long SYMBOL_NAME(sys_getgid16) + .long SYMBOL_NAME(sys_signal) + .long SYMBOL_NAME(sys_geteuid16) + .long SYMBOL_NAME(sys_getegid16) /* 50 */ + .long SYMBOL_NAME(sys_acct) + .long SYMBOL_NAME(sys_umount) /* recycled never used phys() */ + .long SYMBOL_NAME(sys_ni_syscall) /* old lock syscall holder */ + .long SYMBOL_NAME(sys_ioctl) + .long SYMBOL_NAME(sys_fcntl) /* 55 */ + .long SYMBOL_NAME(sys_ni_syscall) /* old mpx syscall holder */ + .long SYMBOL_NAME(sys_setpgid) + .long SYMBOL_NAME(sys_ni_syscall) /* old ulimit syscall holder */ + .long SYMBOL_NAME(sys_olduname) + .long SYMBOL_NAME(sys_umask) /* 60 */ + .long SYMBOL_NAME(sys_chroot) + .long SYMBOL_NAME(sys_ustat) + .long SYMBOL_NAME(sys_dup2) + .long SYMBOL_NAME(sys_getppid) + .long SYMBOL_NAME(sys_getpgrp) /* 65 */ + .long SYMBOL_NAME(sys_setsid) + .long SYMBOL_NAME(sys_sigaction) + .long SYMBOL_NAME(sys_sgetmask) + .long SYMBOL_NAME(sys_ssetmask) + .long SYMBOL_NAME(sys_setreuid16) /* 70 */ + .long SYMBOL_NAME(sys_setregid16) + .long SYMBOL_NAME(sys_sigsuspend) + .long SYMBOL_NAME(sys_sigpending) + .long SYMBOL_NAME(sys_sethostname) + .long SYMBOL_NAME(sys_setrlimit) /* 75 */ + .long SYMBOL_NAME(sys_old_getrlimit) + .long SYMBOL_NAME(sys_getrusage) + .long SYMBOL_NAME(sys_gettimeofday) + .long SYMBOL_NAME(sys_settimeofday) + .long SYMBOL_NAME(sys_getgroups16) /* 80 */ + .long SYMBOL_NAME(sys_setgroups16) + .long SYMBOL_NAME(old_select) + .long SYMBOL_NAME(sys_symlink) + .long SYMBOL_NAME(sys_lstat) + .long SYMBOL_NAME(sys_readlink) /* 85 */ + .long SYMBOL_NAME(sys_uselib) + .long SYMBOL_NAME(sys_swapon) + .long SYMBOL_NAME(sys_reboot) + .long SYMBOL_NAME(old_readdir) + .long SYMBOL_NAME(old_mmap) /* 90 */ + .long SYMBOL_NAME(sys_munmap) + .long SYMBOL_NAME(sys_truncate) + .long SYMBOL_NAME(sys_ftruncate) + .long SYMBOL_NAME(sys_fchmod) + .long SYMBOL_NAME(sys_fchown16) /* 95 */ + .long SYMBOL_NAME(sys_getpriority) + .long SYMBOL_NAME(sys_setpriority) + .long SYMBOL_NAME(sys_ni_syscall) /* old profil syscall holder */ + .long SYMBOL_NAME(sys_statfs) + .long SYMBOL_NAME(sys_fstatfs) /* 100 */ + .long SYMBOL_NAME(sys_ioperm) + .long SYMBOL_NAME(sys_socketcall) + .long SYMBOL_NAME(sys_syslog) + .long SYMBOL_NAME(sys_setitimer) + .long SYMBOL_NAME(sys_getitimer) /* 105 */ + .long SYMBOL_NAME(sys_newstat) + .long SYMBOL_NAME(sys_newlstat) + .long SYMBOL_NAME(sys_newfstat) + .long SYMBOL_NAME(sys_uname) + .long SYMBOL_NAME(sys_iopl) /* 110 */ + .long SYMBOL_NAME(sys_vhangup) + .long SYMBOL_NAME(sys_ni_syscall) /* old "idle" system call */ + .long SYMBOL_NAME(sys_ni_syscall) /* was VM86 */ + .long SYMBOL_NAME(sys_wait4) + .long SYMBOL_NAME(sys_swapoff) /* 115 */ + .long SYMBOL_NAME(sys_sysinfo) + .long SYMBOL_NAME(sys_ipc) + .long SYMBOL_NAME(sys_fsync) + .long SYMBOL_NAME(sys_sigreturn) + .long SYMBOL_NAME(sys_clone) /* 120 */ + .long SYMBOL_NAME(sys_setdomainname) + .long SYMBOL_NAME(sys_newuname) + .long SYMBOL_NAME(sys_modify_ldt) + .long SYMBOL_NAME(sys_adjtimex) + .long SYMBOL_NAME(sys_mprotect) /* 125 */ + .long SYMBOL_NAME(sys_sigprocmask) + .long SYMBOL_NAME(sys_create_module) + .long SYMBOL_NAME(sys_init_module) + .long SYMBOL_NAME(sys_delete_module) + .long SYMBOL_NAME(sys_get_kernel_syms) /* 130 */ + .long SYMBOL_NAME(sys_quotactl) + .long SYMBOL_NAME(sys_getpgid) + .long SYMBOL_NAME(sys_fchdir) + .long SYMBOL_NAME(sys_bdflush) + .long SYMBOL_NAME(sys_sysfs) /* 135 */ + .long SYMBOL_NAME(sys_personality) + .long SYMBOL_NAME(sys_ni_syscall) /* for afs_syscall */ + .long SYMBOL_NAME(sys_setfsuid16) + .long SYMBOL_NAME(sys_setfsgid16) + .long SYMBOL_NAME(sys_llseek) /* 140 */ + .long SYMBOL_NAME(sys_getdents) + .long SYMBOL_NAME(sys_select) + .long SYMBOL_NAME(sys_flock) + .long SYMBOL_NAME(sys_msync) + .long SYMBOL_NAME(sys_readv) /* 145 */ + .long SYMBOL_NAME(sys_writev) + .long SYMBOL_NAME(sys_getsid) + .long SYMBOL_NAME(sys_fdatasync) + .long SYMBOL_NAME(sys_sysctl) + .long SYMBOL_NAME(sys_mlock) /* 150 */ + .long SYMBOL_NAME(sys_munlock) + .long SYMBOL_NAME(sys_mlockall) + .long SYMBOL_NAME(sys_munlockall) + .long SYMBOL_NAME(sys_sched_setparam) + .long SYMBOL_NAME(sys_sched_getparam) /* 155 */ + .long SYMBOL_NAME(sys_sched_setscheduler) + .long SYMBOL_NAME(sys_sched_getscheduler) + .long SYMBOL_NAME(sys_sched_yield) + .long SYMBOL_NAME(sys_sched_get_priority_max) + .long SYMBOL_NAME(sys_sched_get_priority_min) /* 160 */ + .long SYMBOL_NAME(sys_sched_rr_get_interval) + .long SYMBOL_NAME(sys_nanosleep) + .long SYMBOL_NAME(sys_mremap) + .long SYMBOL_NAME(sys_setresuid16) + .long SYMBOL_NAME(sys_getresuid16) /* 165 */ + .long SYMBOL_NAME(sys_ni_syscall) /* was VM86 */ + .long SYMBOL_NAME(sys_query_module) + .long SYMBOL_NAME(sys_poll) + .long SYMBOL_NAME(sys_nfsservctl) + .long SYMBOL_NAME(sys_setresgid16) /* 170 */ + .long SYMBOL_NAME(sys_getresgid16) + .long SYMBOL_NAME(sys_prctl) + .long SYMBOL_NAME(sys_rt_sigreturn) + .long SYMBOL_NAME(sys_rt_sigaction) + .long SYMBOL_NAME(sys_rt_sigprocmask) /* 175 */ + .long SYMBOL_NAME(sys_rt_sigpending) + .long SYMBOL_NAME(sys_rt_sigtimedwait) + .long SYMBOL_NAME(sys_rt_sigqueueinfo) + .long SYMBOL_NAME(sys_rt_sigsuspend) + .long SYMBOL_NAME(sys_pread) /* 180 */ + .long SYMBOL_NAME(sys_pwrite) + .long SYMBOL_NAME(sys_chown16) + .long SYMBOL_NAME(sys_getcwd) + .long SYMBOL_NAME(sys_capget) + .long SYMBOL_NAME(sys_capset) /* 185 */ + .long SYMBOL_NAME(sys_sigaltstack) + .long SYMBOL_NAME(sys_sendfile) + .long SYMBOL_NAME(sys_ni_syscall) /* streams1 */ + .long SYMBOL_NAME(sys_ni_syscall) /* streams2 */ + .long SYMBOL_NAME(sys_vfork) /* 190 */ + .long SYMBOL_NAME(sys_getrlimit) + .long SYMBOL_NAME(sys_mmap2) + .long SYMBOL_NAME(sys_truncate64) + .long SYMBOL_NAME(sys_ftruncate64) + .long SYMBOL_NAME(sys_stat64) /* 195 */ + .long SYMBOL_NAME(sys_lstat64) + .long SYMBOL_NAME(sys_fstat64) + .long SYMBOL_NAME(sys_lchown) + .long SYMBOL_NAME(sys_getuid) + .long SYMBOL_NAME(sys_getgid) /* 200 */ + .long SYMBOL_NAME(sys_geteuid) + .long SYMBOL_NAME(sys_getegid) + .long SYMBOL_NAME(sys_setreuid) + .long SYMBOL_NAME(sys_setregid) + .long SYMBOL_NAME(sys_getgroups) /* 205 */ + .long SYMBOL_NAME(sys_setgroups) + .long SYMBOL_NAME(sys_fchown) + .long SYMBOL_NAME(sys_setresuid) + .long SYMBOL_NAME(sys_getresuid) + .long SYMBOL_NAME(sys_setresgid) /* 210 */ + .long SYMBOL_NAME(sys_getresgid) + .long SYMBOL_NAME(sys_chown) + .long SYMBOL_NAME(sys_setuid) + .long SYMBOL_NAME(sys_setgid) + .long SYMBOL_NAME(sys_setfsuid) /* 215 */ + .long SYMBOL_NAME(sys_setfsgid) + .long SYMBOL_NAME(sys_pivot_root) + .long SYMBOL_NAME(sys_mincore) + .long SYMBOL_NAME(sys_madvise) + .long SYMBOL_NAME(sys_getdents64) /* 220 */ + .long SYMBOL_NAME(sys_fcntl64) + .long SYMBOL_NAME(sys_ni_syscall) /* reserved for TUX */ + .long SYMBOL_NAME(sys_ni_syscall) /* Reserved for Security */ + .long SYMBOL_NAME(sys_gettid) + .long SYMBOL_NAME(sys_readahead) /* 225 */ + .long SYMBOL_NAME(sys_setxattr) + .long SYMBOL_NAME(sys_lsetxattr) + .long SYMBOL_NAME(sys_fsetxattr) + .long SYMBOL_NAME(sys_getxattr) + .long SYMBOL_NAME(sys_lgetxattr) /* 230 */ + .long SYMBOL_NAME(sys_fgetxattr) + .long SYMBOL_NAME(sys_listxattr) + .long SYMBOL_NAME(sys_llistxattr) + .long SYMBOL_NAME(sys_flistxattr) + .long SYMBOL_NAME(sys_removexattr) /* 235 */ + .long SYMBOL_NAME(sys_lremovexattr) + .long SYMBOL_NAME(sys_fremovexattr) + .long SYMBOL_NAME(sys_tkill) + .long SYMBOL_NAME(sys_sendfile64) + .long SYMBOL_NAME(sys_ni_syscall) /* 240 reserved for futex */ + .long SYMBOL_NAME(sys_ni_syscall) /* reserved for sched_setaffinity */ + .long SYMBOL_NAME(sys_ni_syscall) /* reserved for sched_getaffinity */ + .long SYMBOL_NAME(sys_ni_syscall) /* sys_set_thread_area */ + .long SYMBOL_NAME(sys_ni_syscall) /* sys_get_thread_area */ + .long SYMBOL_NAME(sys_ni_syscall) /* 245 sys_io_setup */ + .long SYMBOL_NAME(sys_ni_syscall) /* sys_io_destroy */ + .long SYMBOL_NAME(sys_ni_syscall) /* sys_io_getevents */ + .long SYMBOL_NAME(sys_ni_syscall) /* sys_io_submit */ + .long SYMBOL_NAME(sys_ni_syscall) /* sys_io_cancel */ + .long SYMBOL_NAME(sys_ni_syscall) /* 250 sys_alloc_hugepages */ + .long SYMBOL_NAME(sys_ni_syscall) /* sys_free_hugepages */ + .long SYMBOL_NAME(sys_ni_syscall) /* sys_exit_group */ + .long SYMBOL_NAME(sys_ni_syscall) /* sys_lookup_dcookie */ + .long SYMBOL_NAME(sys_ni_syscall) /* sys_epoll_create */ + .long SYMBOL_NAME(sys_ni_syscall) /* sys_epoll_ctl 255 */ + .long SYMBOL_NAME(sys_ni_syscall) /* sys_epoll_wait */ + .long SYMBOL_NAME(sys_ni_syscall) /* sys_remap_file_pages */ + .long SYMBOL_NAME(sys_ni_syscall) /* sys_set_tid_address */ + + .rept NR_syscalls-(.-sys_call_table)/4 + .long SYMBOL_NAME(sys_ni_syscall) + .endr diff --git a/xenolinux-2.4.24-sparse/arch/xeno/kernel/head.S b/xenolinux-2.4.24-sparse/arch/xeno/kernel/head.S new file mode 100644 index 0000000000..d9934d1f5b --- /dev/null +++ b/xenolinux-2.4.24-sparse/arch/xeno/kernel/head.S @@ -0,0 +1,66 @@ + +.text +#include <linux/config.h> +#include <linux/threads.h> +#include <linux/linkage.h> +#include <asm/segment.h> +#include <asm/page.h> +#include <asm/pgtable.h> +#include <asm/desc.h> + +/* Offsets in start_info structure */ +#define MOD_START 20 +#define MOD_LEN 24 + +startup_32: + cld + + lss stack_start,%esp + + /* Copy initrd somewhere safe before it's clobbered by BSS. */ + mov MOD_LEN(%esi),%ecx + shr $2,%ecx + jz 2f /* bail from copy loop if no initrd */ + mov $SYMBOL_NAME(_end),%edi + add MOD_LEN(%esi),%edi + mov MOD_START(%esi),%eax + add MOD_LEN(%esi),%eax +1: sub $4,%eax + sub $4,%edi + mov (%eax),%ebx + mov %ebx,(%edi) + loop 1b + mov %edi,MOD_START(%esi) + + /* Clear BSS first so that there are no surprises... */ +2: xorl %eax,%eax + movl $SYMBOL_NAME(__bss_start),%edi + movl $SYMBOL_NAME(_end),%ecx + subl %edi,%ecx + rep stosb + + /* Copy the necessary stuff from start_info structure. */ + mov $SYMBOL_NAME(start_info_union),%edi + mov $128,%ecx + rep movsl + + jmp SYMBOL_NAME(start_kernel) + +ENTRY(stack_start) + .long SYMBOL_NAME(init_task_union)+8192, __KERNEL_DS + +.org 0x1000 +ENTRY(empty_zero_page) + +.org 0x2000 +ENTRY(default_ldt) + +.org 0x3000 +ENTRY(cpu0_pte_quicklist) + +.org 0x3400 +ENTRY(cpu0_pgd_quicklist) + +.org 0x3800 +ENTRY(stext) +ENTRY(_stext) diff --git a/xenolinux-2.4.24-sparse/arch/xeno/kernel/hypervisor.c b/xenolinux-2.4.24-sparse/arch/xeno/kernel/hypervisor.c new file mode 100644 index 0000000000..3f414e9876 --- /dev/null +++ b/xenolinux-2.4.24-sparse/arch/xeno/kernel/hypervisor.c @@ -0,0 +1,128 @@ +/****************************************************************************** + * hypervisor.c + * + * Communication to/from hypervisor. + * + * Copyright (c) 2002, K A Fraser + */ + +#include <linux/config.h> +#include <asm/atomic.h> +#include <linux/irq.h> +#include <asm/hypervisor.h> +#include <asm/system.h> +#include <asm/ptrace.h> + +multicall_entry_t multicall_list[8]; +int nr_multicall_ents = 0; + +static unsigned long event_mask = 0; + +void frobb(void) {} + +void do_hypervisor_callback(struct pt_regs *regs) +{ + unsigned long events, flags; + shared_info_t *shared = HYPERVISOR_shared_info; + + do { + /* Specialised local_irq_save(). */ + flags = test_and_clear_bit(EVENTS_MASTER_ENABLE_BIT, + &shared->events_mask); + barrier(); + + events = xchg(&shared->events, 0); + events &= event_mask; + + __asm__ __volatile__ ( + " push %1 ;" + " sub $4,%%esp ;" + " jmp 2f ;" + "1: btrl %%eax,%0 ;" /* clear bit */ + " mov %%eax,(%%esp) ;" + " call do_IRQ ;" /* do_IRQ(event) */ + "2: bsfl %0,%%eax ;" /* %eax == bit # */ + " jnz 1b ;" + " add $8,%%esp ;" + /* we use %ebx because it is callee-saved */ + : : "b" (events), "r" (regs) + /* clobbered by callback function calls */ + : "eax", "ecx", "edx", "memory" ); + + /* Specialised local_irq_restore(). */ + if ( flags ) set_bit(EVENTS_MASTER_ENABLE_BIT, &shared->events_mask); + barrier(); + } + while ( shared->events ); +} + + + +/* + * Define interface to generic handling in irq.c + */ + +static void shutdown_hypervisor_event(unsigned int irq) +{ + clear_bit(irq, &event_mask); + clear_bit(irq, &HYPERVISOR_shared_info->events_mask); +} + +static void enable_hypervisor_event(unsigned int irq) +{ + set_bit(irq, &event_mask); + set_bit(irq, &HYPERVISOR_shared_info->events_mask); + if ( test_bit(EVENTS_MASTER_ENABLE_BIT, + &HYPERVISOR_shared_info->events_mask) ) + do_hypervisor_callback(NULL); +} + +static void disable_hypervisor_event(unsigned int irq) +{ + clear_bit(irq, &event_mask); + clear_bit(irq, &HYPERVISOR_shared_info->events_mask); +} + +static void ack_hypervisor_event(unsigned int irq) +{ + if ( !(event_mask & (1<<irq)) ) + { + printk("Unexpected hypervisor event %d\n", irq); + atomic_inc(&irq_err_count); + } + set_bit(irq, &HYPERVISOR_shared_info->events_mask); +} + +static unsigned int startup_hypervisor_event(unsigned int irq) +{ + enable_hypervisor_event(irq); + return 0; +} + +static void end_hypervisor_event(unsigned int irq) +{ +} + +static struct hw_interrupt_type hypervisor_irq_type = { + "Hypervisor-event", + startup_hypervisor_event, + shutdown_hypervisor_event, + enable_hypervisor_event, + disable_hypervisor_event, + ack_hypervisor_event, + end_hypervisor_event, + NULL +}; + +void __init init_IRQ(void) +{ + int i; + + for ( i = 0; i < NR_IRQS; i++ ) + { + irq_desc[i].status = IRQ_DISABLED; + irq_desc[i].action = 0; + irq_desc[i].depth = 1; + irq_desc[i].handler = &hypervisor_irq_type; + } +} diff --git a/xenolinux-2.4.24-sparse/arch/xeno/kernel/i386_ksyms.c b/xenolinux-2.4.24-sparse/arch/xeno/kernel/i386_ksyms.c new file mode 100644 index 0000000000..e62ca85c04 --- /dev/null +++ b/xenolinux-2.4.24-sparse/arch/xeno/kernel/i386_ksyms.c @@ -0,0 +1,163 @@ +#include <linux/config.h> +#include <linux/module.h> +#include <linux/smp.h> +#include <linux/user.h> +#include <linux/elfcore.h> +#include <linux/mca.h> +#include <linux/sched.h> +#include <linux/in6.h> +#include <linux/interrupt.h> +#include <linux/smp_lock.h> +#include <linux/pm.h> +//XXX ??? #include <linux/pci.h> +#include <linux/apm_bios.h> +#include <linux/kernel.h> +#include <linux/string.h> +#include <linux/tty.h> + +#include <asm/semaphore.h> +#include <asm/processor.h> +#include <asm/i387.h> +#include <asm/uaccess.h> +#include <asm/checksum.h> +#include <asm/io.h> +#include <asm/hardirq.h> +#include <asm/delay.h> +#include <asm/irq.h> +#include <asm/mmx.h> +#include <asm/desc.h> +#include <asm/pgtable.h> +#include <asm/pgalloc.h> + +extern void dump_thread(struct pt_regs *, struct user *); +extern spinlock_t rtc_lock; + +#if defined(CONFIG_APMXXX) || defined(CONFIG_APM_MODULEXXX) +extern void machine_real_restart(unsigned char *, int); +EXPORT_SYMBOL(machine_real_restart); +extern void default_idle(void); +EXPORT_SYMBOL(default_idle); +#endif + +#ifdef CONFIG_SMP +extern void FASTCALL( __write_lock_failed(rwlock_t *rw)); +extern void FASTCALL( __read_lock_failed(rwlock_t *rw)); +#endif + +#if defined(CONFIG_BLK_DEV_IDE) || defined(CONFIG_BLK_DEV_HD) || defined(CONFIG_BLK_DEV_IDE_MODULE) || defined(CONFIG_BLK_DEV_HD_MODULE) +extern struct drive_info_struct drive_info; +EXPORT_SYMBOL(drive_info); +#endif + +// XXX extern unsigned long get_cmos_time(void); + +/* platform dependent support */ +EXPORT_SYMBOL(boot_cpu_data); +EXPORT_SYMBOL(dump_thread); +EXPORT_SYMBOL(dump_fpu); +EXPORT_SYMBOL(dump_extended_fpu); +EXPORT_SYMBOL(__ioremap); +EXPORT_SYMBOL(iounmap); +EXPORT_SYMBOL(enable_irq); +EXPORT_SYMBOL(disable_irq); +EXPORT_SYMBOL(disable_irq_nosync); +EXPORT_SYMBOL(probe_irq_mask); +EXPORT_SYMBOL(kernel_thread); +EXPORT_SYMBOL(pm_idle); +EXPORT_SYMBOL(pm_power_off); +EXPORT_SYMBOL(apm_info); +//EXPORT_SYMBOL(gdt); +EXPORT_SYMBOL(empty_zero_page); + +#ifdef CONFIG_DEBUG_IOVIRT +EXPORT_SYMBOL(__io_virt_debug); +#endif + +EXPORT_SYMBOL_NOVERS(__down_failed); +EXPORT_SYMBOL_NOVERS(__down_failed_interruptible); +EXPORT_SYMBOL_NOVERS(__down_failed_trylock); +EXPORT_SYMBOL_NOVERS(__up_wakeup); +/* Networking helper routines. */ +EXPORT_SYMBOL(csum_partial_copy_generic); +/* Delay loops */ +EXPORT_SYMBOL(__ndelay); +EXPORT_SYMBOL(__udelay); +EXPORT_SYMBOL(__delay); +EXPORT_SYMBOL(__const_udelay); + +EXPORT_SYMBOL_NOVERS(__get_user_1); +EXPORT_SYMBOL_NOVERS(__get_user_2); +EXPORT_SYMBOL_NOVERS(__get_user_4); + +EXPORT_SYMBOL(strtok); +EXPORT_SYMBOL(strpbrk); +EXPORT_SYMBOL(strstr); + +EXPORT_SYMBOL(strncpy_from_user); +EXPORT_SYMBOL(__strncpy_from_user); +EXPORT_SYMBOL(clear_user); +EXPORT_SYMBOL(__clear_user); +EXPORT_SYMBOL(__generic_copy_from_user); +EXPORT_SYMBOL(__generic_copy_to_user); +EXPORT_SYMBOL(strnlen_user); + +#ifdef CONFIG_X86_USE_3DNOW +EXPORT_SYMBOL(_mmx_memcpy); +EXPORT_SYMBOL(mmx_clear_page); +EXPORT_SYMBOL(mmx_copy_page); +#endif + +#ifdef CONFIG_SMP +EXPORT_SYMBOL(cpu_data); +EXPORT_SYMBOL(kernel_flag_cacheline); +EXPORT_SYMBOL(smp_num_cpus); +EXPORT_SYMBOL(cpu_online_map); +EXPORT_SYMBOL_NOVERS(__write_lock_failed); +EXPORT_SYMBOL_NOVERS(__read_lock_failed); + +/* Global SMP irq stuff */ +EXPORT_SYMBOL(synchronize_irq); +EXPORT_SYMBOL(global_irq_holder); +EXPORT_SYMBOL(__global_cli); +EXPORT_SYMBOL(__global_sti); +EXPORT_SYMBOL(__global_save_flags); +EXPORT_SYMBOL(__global_restore_flags); +EXPORT_SYMBOL(smp_call_function); + +/* TLB flushing */ +EXPORT_SYMBOL(flush_tlb_page); +#endif + +#ifdef CONFIG_X86_IO_APIC +EXPORT_SYMBOL(IO_APIC_get_PCI_irq_vector); +#endif + +#ifdef CONFIG_VT +EXPORT_SYMBOL(screen_info); +#endif + +EXPORT_SYMBOL(get_wchan); + +EXPORT_SYMBOL(rtc_lock); + +#undef memcpy +#undef memset +extern void * memset(void *,int,__kernel_size_t); +extern void * memcpy(void *,const void *,__kernel_size_t); +EXPORT_SYMBOL_NOVERS(memcpy); +EXPORT_SYMBOL_NOVERS(memset); + +#ifdef CONFIG_HAVE_DEC_LOCK +EXPORT_SYMBOL(atomic_dec_and_lock); +#endif + +#ifdef CONFIG_MULTIQUAD +EXPORT_SYMBOL(xquad_portio); +#endif + +#include <asm/xeno_proc.h> +EXPORT_SYMBOL(create_xeno_proc_entry); +EXPORT_SYMBOL(remove_xeno_proc_entry); + +EXPORT_SYMBOL(do_hypervisor_callback); +EXPORT_SYMBOL(HYPERVISOR_shared_info); diff --git a/xenolinux-2.4.24-sparse/arch/xeno/kernel/ioport.c b/xenolinux-2.4.24-sparse/arch/xeno/kernel/ioport.c new file mode 100644 index 0000000000..ed6dbbc3c5 --- /dev/null +++ b/xenolinux-2.4.24-sparse/arch/xeno/kernel/ioport.c @@ -0,0 +1,48 @@ +#include <linux/sched.h> +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/types.h> +#include <linux/stddef.h> +#include <asm/hypervisor-ifs/dom0_ops.h> + + +asmlinkage int sys_iopl(unsigned int new_io_pl) +{ + unsigned int old_io_pl = current->thread.io_pl; + dom0_op_t op; + + if ( !(start_info.flags & SIF_PRIVILEGED) ) + return -EPERM; + + if ( new_io_pl > 3 ) + return -EINVAL; + + /* Need "raw I/O" privileges for direct port access. */ + if ( (new_io_pl > old_io_pl) && !capable(CAP_SYS_RAWIO) ) + return -EPERM; + + /* Maintain OS privileges even if user attempts to relinquish them. */ + if ( (new_io_pl == 0) && (start_info.flags & SIF_PRIVILEGED) ) + new_io_pl = 1; + + /* Change our version of the privilege levels. */ + current->thread.io_pl = new_io_pl; + + /* Force the change at ring 0. */ + op.cmd = DOM0_IOPL; + op.u.iopl.domain = start_info.dom_id; + op.u.iopl.iopl = new_io_pl; + HYPERVISOR_dom0_op(&op); + + return 0; +} + + +asmlinkage int sys_ioperm(unsigned long from, unsigned long num, int turn_on) +{ + printk(KERN_INFO "ioperm not fully supported - %s\n", + turn_on ? "set iopl to 3" : "ignore resource release"); + return turn_on ? sys_iopl(3) : 0; +} + + diff --git a/xenolinux-2.4.24-sparse/arch/xeno/kernel/irq.c b/xenolinux-2.4.24-sparse/arch/xeno/kernel/irq.c new file mode 100644 index 0000000000..c88e976125 --- /dev/null +++ b/xenolinux-2.4.24-sparse/arch/xeno/kernel/irq.c @@ -0,0 +1,1137 @@ +/* + * linux/arch/i386/kernel/irq.c + * + * Copyright (C) 1992, 1998 Linus Torvalds, Ingo Molnar + * + * This file contains the code used by various IRQ handling routines: + * asking for different IRQ's should be done through these routines + * instead of just grabbing them. Thus setups with different IRQ numbers + * shouldn't result in any weird surprises, and installing new handlers + * should be easier. + */ + +/* + * (mostly architecture independent, will move to kernel/irq.c in 2.5.) + * + * IRQs are in fact implemented a bit like signal handlers for the kernel. + * Naturally it's not a 1:1 relation, but there are similarities. + */ + +#include <linux/config.h> +#include <linux/ptrace.h> +#include <linux/errno.h> +#include <linux/signal.h> +#include <linux/sched.h> +#include <linux/ioport.h> +#include <linux/interrupt.h> +#include <linux/timex.h> +#include <linux/slab.h> +#include <linux/random.h> +#include <linux/smp_lock.h> +#include <linux/init.h> +#include <linux/kernel_stat.h> +#include <linux/irq.h> +#include <linux/proc_fs.h> +#include <linux/seq_file.h> + +#include <asm/atomic.h> +#include <asm/io.h> +#include <asm/smp.h> +#include <asm/system.h> +#include <asm/bitops.h> +#include <asm/uaccess.h> +#include <asm/pgalloc.h> +#include <asm/delay.h> +#include <asm/desc.h> +#include <asm/irq.h> + + + +/* + * Linux has a controller-independent x86 interrupt architecture. + * every controller has a 'controller-template', that is used + * by the main code to do the right thing. Each driver-visible + * interrupt source is transparently wired to the apropriate + * controller. Thus drivers need not be aware of the + * interrupt-controller. + * + * Various interrupt controllers we handle: 8259 PIC, SMP IO-APIC, + * PIIX4's internal 8259 PIC and SGI's Visual Workstation Cobalt (IO-)APIC. + * (IO-APICs assumed to be messaging to Pentium local-APICs) + * + * the code is designed to be easily extended with new/different + * interrupt controllers, without having to do assembly magic. + */ + +/* + * Controller mappings for all interrupt sources: + */ +irq_desc_t irq_desc[NR_IRQS] __cacheline_aligned = + { [0 ... NR_IRQS-1] = { 0, &no_irq_type, NULL, 0, SPIN_LOCK_UNLOCKED}}; + +static void register_irq_proc (unsigned int irq); + +/* + * Special irq handlers. + */ + +void no_action(int cpl, void *dev_id, struct pt_regs *regs) { } + +/* + * Generic no controller code + */ + +static void enable_none(unsigned int irq) { } +static unsigned int startup_none(unsigned int irq) { return 0; } +static void disable_none(unsigned int irq) { } +static void ack_none(unsigned int irq) +{ + printk("unexpected IRQ trap at vector %02x\n", irq); +} + +/* startup is the same as "enable", shutdown is same as "disable" */ +#define shutdown_none disable_none +#define end_none enable_none + +struct hw_interrupt_type no_irq_type = { + "none", + startup_none, + shutdown_none, + enable_none, + disable_none, + ack_none, + end_none +}; + +atomic_t irq_err_count; +#ifdef CONFIG_X86_IO_APIC +#ifdef APIC_MISMATCH_DEBUG +atomic_t irq_mis_count; +#endif +#endif + +/* + * Generic, controller-independent functions: + */ + +int show_interrupts(struct seq_file *p, void *v) +{ + int i, j; + struct irqaction * action; + + seq_printf(p, " "); + for (j=0; j<smp_num_cpus; j++) + seq_printf(p, "CPU%d ",j); + seq_putc(p,'\n'); + + for (i = 0 ; i < NR_IRQS ; i++) { + action = irq_desc[i].action; + if (!action) + continue; + seq_printf(p, "%3d: ",i); +#ifndef CONFIG_SMP + seq_printf(p, "%10u ", kstat_irqs(i)); +#else + for (j = 0; j < smp_num_cpus; j++) + seq_printf(p, "%10u ", + kstat.irqs[cpu_logical_map(j)][i]); +#endif + seq_printf(p, " %14s", irq_desc[i].handler->typename); + seq_printf(p, " %s", action->name); + + for (action=action->next; action; action = action->next) + seq_printf(p, ", %s", action->name); + seq_putc(p,'\n'); + } + seq_printf(p, "NMI: "); + for (j = 0; j < smp_num_cpus; j++) + seq_printf(p, "%10u ", + nmi_count(cpu_logical_map(j))); + seq_printf(p, "\n"); +#if CONFIG_X86_LOCAL_APIC + seq_printf(p, "LOC: "); + for (j = 0; j < smp_num_cpus; j++) + seq_printf(p, "%10u ", + apic_timer_irqs[cpu_logical_map(j)]); + seq_printf(p, "\n"); +#endif + seq_printf(p, "ERR: %10u\n", atomic_read(&irq_err_count)); +#ifdef CONFIG_X86_IO_APIC +#ifdef APIC_MISMATCH_DEBUG + seq_printf(p, "MIS: %10u\n", atomic_read(&irq_mis_count)); +#endif +#endif + + return 0; +} + + +/* + * Global interrupt locks for SMP. Allow interrupts to come in on any + * CPU, yet make cli/sti act globally to protect critical regions.. + */ + +#ifdef CONFIG_SMP +unsigned char global_irq_holder = NO_PROC_ID; +unsigned volatile long global_irq_lock; /* pendantic: long for set_bit --RR */ + +extern void show_stack(unsigned long* esp); + +static void show(char * str) +{ + int i; + int cpu = smp_processor_id(); + + printk("\n%s, CPU %d:\n", str, cpu); + printk("irq: %d [",irqs_running()); + for(i=0;i < smp_num_cpus;i++) + printk(" %d",local_irq_count(i)); + printk(" ]\nbh: %d [",spin_is_locked(&global_bh_lock) ? 1 : 0); + for(i=0;i < smp_num_cpus;i++) + printk(" %d",local_bh_count(i)); + + printk(" ]\nStack dumps:"); + for(i = 0; i < smp_num_cpus; i++) { + unsigned long esp; + if (i == cpu) + continue; + printk("\nCPU %d:",i); + esp = init_tss[i].esp0; + if (!esp) { + /* tss->esp0 is set to NULL in cpu_init(), + * it's initialized when the cpu returns to user + * space. -- manfreds + */ + printk(" <unknown> "); + continue; + } + esp &= ~(THREAD_SIZE-1); + esp += sizeof(struct task_struct); + show_stack((void*)esp); + } + printk("\nCPU %d:",cpu); + show_stack(NULL); + printk("\n"); +} + +#define MAXCOUNT 100000000 + +/* + * I had a lockup scenario where a tight loop doing + * spin_unlock()/spin_lock() on CPU#1 was racing with + * spin_lock() on CPU#0. CPU#0 should have noticed spin_unlock(), but + * apparently the spin_unlock() information did not make it + * through to CPU#0 ... nasty, is this by design, do we have to limit + * 'memory update oscillation frequency' artificially like here? + * + * Such 'high frequency update' races can be avoided by careful design, but + * some of our major constructs like spinlocks use similar techniques, + * it would be nice to clarify this issue. Set this define to 0 if you + * want to check whether your system freezes. I suspect the delay done + * by SYNC_OTHER_CORES() is in correlation with 'snooping latency', but + * i thought that such things are guaranteed by design, since we use + * the 'LOCK' prefix. + */ +#define SUSPECTED_CPU_OR_CHIPSET_BUG_WORKAROUND 0 + +#if SUSPECTED_CPU_OR_CHIPSET_BUG_WORKAROUND +# define SYNC_OTHER_CORES(x) udelay(x+1) +#else +/* + * We have to allow irqs to arrive between __sti and __cli + */ +# define SYNC_OTHER_CORES(x) __asm__ __volatile__ ("nop") +#endif + +static inline void wait_on_irq(int cpu) +{ + int count = MAXCOUNT; + + for (;;) { + + /* + * Wait until all interrupts are gone. Wait + * for bottom half handlers unless we're + * already executing in one.. + */ + if (!irqs_running()) + if (local_bh_count(cpu) || !spin_is_locked(&global_bh_lock)) + break; + + /* Duh, we have to loop. Release the lock to avoid deadlocks */ + clear_bit(0,&global_irq_lock); + + for (;;) { + if (!--count) { + show("wait_on_irq"); + count = ~0; + } + __sti(); + SYNC_OTHER_CORES(cpu); + __cli(); + if (irqs_running()) + continue; + if (global_irq_lock) + continue; + if (!local_bh_count(cpu) && spin_is_locked(&global_bh_lock)) + continue; + if (!test_and_set_bit(0,&global_irq_lock)) + break; + } + } +} + +/* + * This is called when we want to synchronize with + * interrupts. We may for example tell a device to + * stop sending interrupts: but to make sure there + * are no interrupts that are executing on another + * CPU we need to call this function. + */ +void synchronize_irq(void) +{ + if (irqs_running()) { + /* Stupid approach */ + cli(); + sti(); + } +} + +static inline void get_irqlock(int cpu) +{ + if (test_and_set_bit(0,&global_irq_lock)) { + /* do we already hold the lock? */ + if ((unsigned char) cpu == global_irq_holder) + return; + /* Uhhuh.. Somebody else got it. Wait.. */ + do { + do { + rep_nop(); + } while (test_bit(0,&global_irq_lock)); + } while (test_and_set_bit(0,&global_irq_lock)); + } + /* + * We also to make sure that nobody else is running + * in an interrupt context. + */ + wait_on_irq(cpu); + + /* + * Ok, finally.. + */ + global_irq_holder = cpu; +} + +void __global_cli(void) +{ + panic("__global_cli"); +} + +void __global_sti(void) +{ + panic("__global_sti"); +} + +/* + * SMP flags value to restore to: + * 0 - global cli + * 1 - global sti + * 2 - local cli + * 3 - local sti + */ +unsigned long __global_save_flags(void) +{ + panic("__global_save_flags"); +} + +void __global_restore_flags(unsigned long flags) +{ + panic("__global_restore_flags"); +} + +#endif + +/* + * This should really return information about whether + * we should do bottom half handling etc. Right now we + * end up _always_ checking the bottom half, which is a + * waste of time and is not what some drivers would + * prefer. + */ +int handle_IRQ_event(unsigned int irq, struct pt_regs * regs, struct irqaction * action) +{ + int status; + int cpu = smp_processor_id(); + + irq_enter(cpu, irq); + + status = 1; /* Force the "do bottom halves" bit */ + + if (!(action->flags & SA_INTERRUPT)) + __sti(); + + do { + status |= action->flags; + action->handler(irq, action->dev_id, regs); + action = action->next; + } while (action); + if (status & SA_SAMPLE_RANDOM) + add_interrupt_randomness(irq); + __cli(); + + irq_exit(cpu, irq); + + return status; +} + +/* + * Generic enable/disable code: this just calls + * down into the PIC-specific version for the actual + * hardware disable after having gotten the irq + * controller lock. + */ + +/** + * disable_irq_nosync - disable an irq without waiting + * @irq: Interrupt to disable + * + * Disable the selected interrupt line. Disables and Enables are + * nested. + * Unlike disable_irq(), this function does not ensure existing + * instances of the IRQ handler have completed before returning. + * + * This function may be called from IRQ context. + */ + +inline void disable_irq_nosync(unsigned int irq) +{ + irq_desc_t *desc = irq_desc + irq; + unsigned long flags; + + spin_lock_irqsave(&desc->lock, flags); + if (!desc->depth++) { + desc->status |= IRQ_DISABLED; + desc->handler->disable(irq); + } + spin_unlock_irqrestore(&desc->lock, flags); +} + +/** + * disable_irq - disable an irq and wait for completion + * @irq: Interrupt to disable + * + * Disable the selected interrupt line. Enables and Disables are + * nested. + * This function waits for any pending IRQ handlers for this interrupt + * to complete before returning. If you use this function while + * holding a resource the IRQ handler may need you will deadlock. + * + * This function may be called - with care - from IRQ context. + */ + +void disable_irq(unsigned int irq) +{ + disable_irq_nosync(irq); + + if (!local_irq_count(smp_processor_id())) { + do { + barrier(); + cpu_relax(); + } while (irq_desc[irq].status & IRQ_INPROGRESS); + } +} + +/** + * enable_irq - enable handling of an irq + * @irq: Interrupt to enable + * + * Undoes the effect of one call to disable_irq(). If this + * matches the last disable, processing of interrupts on this + * IRQ line is re-enabled. + * + * This function may be called from IRQ context. + */ + +void enable_irq(unsigned int irq) +{ + irq_desc_t *desc = irq_desc + irq; + unsigned long flags; + + spin_lock_irqsave(&desc->lock, flags); + switch (desc->depth) { + case 1: { + unsigned int status = desc->status & ~IRQ_DISABLED; + desc->status = status; + if ((status & (IRQ_PENDING | IRQ_REPLAY)) == IRQ_PENDING) { + desc->status = status | IRQ_REPLAY; + hw_resend_irq(desc->handler,irq); + } + desc->handler->enable(irq); + /* fall-through */ + } + default: + desc->depth--; + break; + case 0: + printk("enable_irq(%u) unbalanced from %p\n", irq, + __builtin_return_address(0)); + } + spin_unlock_irqrestore(&desc->lock, flags); +} + +/* + * do_IRQ handles all normal device IRQ's (the special + * SMP cross-CPU interrupts have their own specific + * handlers). + */ +asmlinkage unsigned int do_IRQ(int irq, struct pt_regs *regs) +{ + /* + * We ack quickly, we don't want the irq controller + * thinking we're snobs just because some other CPU has + * disabled global interrupts (we have already done the + * INT_ACK cycles, it's too late to try to pretend to the + * controller that we aren't taking the interrupt). + * + * 0 return value means that this irq is already being + * handled by some other CPU. (or is disabled) + */ + int cpu = smp_processor_id(); + irq_desc_t *desc = irq_desc + irq; + struct irqaction * action; + unsigned int status; +#ifdef CONFIG_DEBUG_STACKOVERFLOW + long esp; + + /* Debugging check for stack overflow: is there less than 1KB free? */ + __asm__ __volatile__("andl %%esp,%0" : "=r" (esp) : "0" (8191)); + if (unlikely(esp < (sizeof(struct task_struct) + 1024))) { + extern void show_stack(unsigned long *); + + printk("do_IRQ: stack overflow: %ld\n", + esp - sizeof(struct task_struct)); + __asm__ __volatile__("movl %%esp,%0" : "=r" (esp)); + show_stack((void *)esp); + } +#endif + + kstat.irqs[cpu][irq]++; + spin_lock(&desc->lock); + desc->handler->ack(irq); + /* + REPLAY is when Linux resends an IRQ that was dropped earlier + WAITING is used by probe to mark irqs that are being tested + */ + status = desc->status & ~(IRQ_REPLAY | IRQ_WAITING); + status |= IRQ_PENDING; /* we _want_ to handle it */ + + /* + * If the IRQ is disabled for whatever reason, we cannot + * use the action we have. + */ + action = NULL; + if (!(status & (IRQ_DISABLED | IRQ_INPROGRESS))) { + action = desc->action; + status &= ~IRQ_PENDING; /* we commit to handling */ + status |= IRQ_INPROGRESS; /* we are handling it */ + } + desc->status = status; + + /* + * If there is no IRQ handler or it was disabled, exit early. + Since we set PENDING, if another processor is handling + a different instance of this same irq, the other processor + will take care of it. + */ + if (!action) + goto out; + + /* + * Edge triggered interrupts need to remember + * pending events. + * This applies to any hw interrupts that allow a second + * instance of the same irq to arrive while we are in do_IRQ + * or in the handler. But the code here only handles the _second_ + * instance of the irq, not the third or fourth. So it is mostly + * useful for irq hardware that does not mask cleanly in an + * SMP environment. + */ + for (;;) { + spin_unlock(&desc->lock); + handle_IRQ_event(irq, regs, action); + spin_lock(&desc->lock); + + if (!(desc->status & IRQ_PENDING)) + break; + desc->status &= ~IRQ_PENDING; + } + desc->status &= ~IRQ_INPROGRESS; +out: + /* + * The ->end() handler has to deal with interrupts which got + * disabled while the handler was running. + */ + desc->handler->end(irq); + spin_unlock(&desc->lock); + + if (softirq_pending(cpu)) + do_softirq(); + return 1; +} + +/** + * request_irq - allocate an interrupt line + * @irq: Interrupt line to allocate + * @handler: Function to be called when the IRQ occurs + * @irqflags: Interrupt type flags + * @devname: An ascii name for the claiming device + * @dev_id: A cookie passed back to the handler function + * + * This call allocates interrupt resources and enables the + * interrupt line and IRQ handling. From the point this + * call is made your handler function may be invoked. Since + * your handler function must clear any interrupt the board + * raises, you must take care both to initialise your hardware + * and to set up the interrupt handler in the right order. + * + * Dev_id must be globally unique. Normally the address of the + * device data structure is used as the cookie. Since the handler + * receives this value it makes sense to use it. + * + * If your interrupt is shared you must pass a non NULL dev_id + * as this is required when freeing the interrupt. + * + * Flags: + * + * SA_SHIRQ Interrupt is shared + * + * SA_INTERRUPT Disable local interrupts while processing + * + * SA_SAMPLE_RANDOM The interrupt can be used for entropy + * + */ + +int request_irq(unsigned int irq, + void (*handler)(int, void *, struct pt_regs *), + unsigned long irqflags, + const char * devname, + void *dev_id) +{ + int retval; + struct irqaction * action; + +#if 1 + /* + * Sanity-check: shared interrupts should REALLY pass in + * a real dev-ID, otherwise we'll have trouble later trying + * to figure out which interrupt is which (messes up the + * interrupt freeing logic etc). + */ + if (irqflags & SA_SHIRQ) { + if (!dev_id) + printk("Bad boy: %s (at 0x%x) called us without a dev_id!\n", devname, (&irq)[-1]); + } +#endif + + if (irq >= NR_IRQS) + return -EINVAL; + if (!handler) + return -EINVAL; + + action = (struct irqaction *) + kmalloc(sizeof(struct irqaction), GFP_KERNEL); + if (!action) + return -ENOMEM; + + action->handler = handler; + action->flags = irqflags; + action->mask = 0; + action->name = devname; + action->next = NULL; + action->dev_id = dev_id; + + retval = setup_irq(irq, action); + if (retval) + kfree(action); + return retval; +} + +/** + * free_irq - free an interrupt + * @irq: Interrupt line to free + * @dev_id: Device identity to free + * + * Remove an interrupt handler. The handler is removed and if the + * interrupt line is no longer in use by any driver it is disabled. + * On a shared IRQ the caller must ensure the interrupt is disabled + * on the card it drives before calling this function. The function + * does not return until any executing interrupts for this IRQ + * have completed. + * + * This function may be called from interrupt context. + * + * Bugs: Attempting to free an irq in a handler for the same irq hangs + * the machine. + */ + +void free_irq(unsigned int irq, void *dev_id) +{ + irq_desc_t *desc; + struct irqaction **p; + unsigned long flags; + + if (irq >= NR_IRQS) + return; + + desc = irq_desc + irq; + spin_lock_irqsave(&desc->lock,flags); + p = &desc->action; + for (;;) { + struct irqaction * action = *p; + if (action) { + struct irqaction **pp = p; + p = &action->next; + if (action->dev_id != dev_id) + continue; + + /* Found it - now remove it from the list of entries */ + *pp = action->next; + if (!desc->action) { + desc->status |= IRQ_DISABLED; + desc->handler->shutdown(irq); + } + spin_unlock_irqrestore(&desc->lock,flags); + +#ifdef CONFIG_SMP + /* Wait to make sure it's not being used on another CPU */ + while (desc->status & IRQ_INPROGRESS) { + barrier(); + cpu_relax(); + } +#endif + kfree(action); + return; + } + printk("Trying to free free IRQ%d\n",irq); + spin_unlock_irqrestore(&desc->lock,flags); + return; + } +} + +/* + * IRQ autodetection code.. + * + * This depends on the fact that any interrupt that + * comes in on to an unassigned handler will get stuck + * with "IRQ_WAITING" cleared and the interrupt + * disabled. + */ + +static DECLARE_MUTEX(probe_sem); + +/** + * probe_irq_on - begin an interrupt autodetect + * + * Commence probing for an interrupt. The interrupts are scanned + * and a mask of potential interrupt lines is returned. + * + */ + +unsigned long probe_irq_on(void) +{ + unsigned int i; + irq_desc_t *desc; + unsigned long val; + unsigned long delay; + + down(&probe_sem); + /* + * something may have generated an irq long ago and we want to + * flush such a longstanding irq before considering it as spurious. + */ + for (i = NR_IRQS-1; i > 0; i--) { + desc = irq_desc + i; + + spin_lock_irq(&desc->lock); + if (!irq_desc[i].action) + irq_desc[i].handler->startup(i); + spin_unlock_irq(&desc->lock); + } + + /* Wait for longstanding interrupts to trigger. */ + for (delay = jiffies + HZ/50; time_after(delay, jiffies); ) + /* about 20ms delay */ synchronize_irq(); + + /* + * enable any unassigned irqs + * (we must startup again here because if a longstanding irq + * happened in the previous stage, it may have masked itself) + */ + for (i = NR_IRQS-1; i > 0; i--) { + desc = irq_desc + i; + + spin_lock_irq(&desc->lock); + if (!desc->action) { + desc->status |= IRQ_AUTODETECT | IRQ_WAITING; + if (desc->handler->startup(i)) + desc->status |= IRQ_PENDING; + } + spin_unlock_irq(&desc->lock); + } + + /* + * Wait for spurious interrupts to trigger + */ + for (delay = jiffies + HZ/10; time_after(delay, jiffies); ) + /* about 100ms delay */ synchronize_irq(); + + /* + * Now filter out any obviously spurious interrupts + */ + val = 0; + for (i = 0; i < NR_IRQS; i++) { + irq_desc_t *desc = irq_desc + i; + unsigned int status; + + spin_lock_irq(&desc->lock); + status = desc->status; + + if (status & IRQ_AUTODETECT) { + /* It triggered already - consider it spurious. */ + if (!(status & IRQ_WAITING)) { + desc->status = status & ~IRQ_AUTODETECT; + desc->handler->shutdown(i); + } else + if (i < 32) + val |= 1 << i; + } + spin_unlock_irq(&desc->lock); + } + + return val; +} + +/* + * Return a mask of triggered interrupts (this + * can handle only legacy ISA interrupts). + */ + +/** + * probe_irq_mask - scan a bitmap of interrupt lines + * @val: mask of interrupts to consider + * + * Scan the ISA bus interrupt lines and return a bitmap of + * active interrupts. The interrupt probe logic state is then + * returned to its previous value. + * + * Note: we need to scan all the irq's even though we will + * only return ISA irq numbers - just so that we reset them + * all to a known state. + */ +unsigned int probe_irq_mask(unsigned long val) +{ + int i; + unsigned int mask; + + mask = 0; + for (i = 0; i < NR_IRQS; i++) { + irq_desc_t *desc = irq_desc + i; + unsigned int status; + + spin_lock_irq(&desc->lock); + status = desc->status; + + if (status & IRQ_AUTODETECT) { + if (i < 16 && !(status & IRQ_WAITING)) + mask |= 1 << i; + + desc->status = status & ~IRQ_AUTODETECT; + desc->handler->shutdown(i); + } + spin_unlock_irq(&desc->lock); + } + up(&probe_sem); + + return mask & val; +} + +/* + * Return the one interrupt that triggered (this can + * handle any interrupt source). + */ + +/** + * probe_irq_off - end an interrupt autodetect + * @val: mask of potential interrupts (unused) + * + * Scans the unused interrupt lines and returns the line which + * appears to have triggered the interrupt. If no interrupt was + * found then zero is returned. If more than one interrupt is + * found then minus the first candidate is returned to indicate + * their is doubt. + * + * The interrupt probe logic state is returned to its previous + * value. + * + * BUGS: When used in a module (which arguably shouldnt happen) + * nothing prevents two IRQ probe callers from overlapping. The + * results of this are non-optimal. + */ + +int probe_irq_off(unsigned long val) +{ + int i, irq_found, nr_irqs; + + nr_irqs = 0; + irq_found = 0; + for (i = 0; i < NR_IRQS; i++) { + irq_desc_t *desc = irq_desc + i; + unsigned int status; + + spin_lock_irq(&desc->lock); + status = desc->status; + + if (status & IRQ_AUTODETECT) { + if (!(status & IRQ_WAITING)) { + if (!nr_irqs) + irq_found = i; + nr_irqs++; + } + desc->status = status & ~IRQ_AUTODETECT; + desc->handler->shutdown(i); + } + spin_unlock_irq(&desc->lock); + } + up(&probe_sem); + + if (nr_irqs > 1) + irq_found = -irq_found; + return irq_found; +} + +/* this was setup_x86_irq but it seems pretty generic */ +int setup_irq(unsigned int irq, struct irqaction * new) +{ + int shared = 0; + unsigned long flags; + struct irqaction *old, **p; + irq_desc_t *desc = irq_desc + irq; + + /* + * Some drivers like serial.c use request_irq() heavily, + * so we have to be careful not to interfere with a + * running system. + */ + if (new->flags & SA_SAMPLE_RANDOM) { + /* + * This function might sleep, we want to call it first, + * outside of the atomic block. + * Yes, this might clear the entropy pool if the wrong + * driver is attempted to be loaded, without actually + * installing a new handler, but is this really a problem, + * only the sysadmin is able to do this. + */ + rand_initialize_irq(irq); + } + + /* + * The following block of code has to be executed atomically + */ + spin_lock_irqsave(&desc->lock,flags); + p = &desc->action; + if ((old = *p) != NULL) { + /* Can't share interrupts unless both agree to */ + if (!(old->flags & new->flags & SA_SHIRQ)) { + spin_unlock_irqrestore(&desc->lock,flags); + return -EBUSY; + } + + /* add new interrupt at end of irq queue */ + do { + p = &old->next; + old = *p; + } while (old); + shared = 1; + } + + *p = new; + + if (!shared) { + desc->depth = 0; + desc->status &= ~(IRQ_DISABLED | IRQ_AUTODETECT | IRQ_WAITING | IRQ_INPROGRESS); + desc->handler->startup(irq); + } + spin_unlock_irqrestore(&desc->lock,flags); + + register_irq_proc(irq); + return 0; +} + +static struct proc_dir_entry * root_irq_dir; +static struct proc_dir_entry * irq_dir [NR_IRQS]; + +#define HEX_DIGITS 8 + +static unsigned int parse_hex_value (const char *buffer, + unsigned long count, unsigned long *ret) +{ + unsigned char hexnum [HEX_DIGITS]; + unsigned long value; + int i; + + if (!count) + return -EINVAL; + if (count > HEX_DIGITS) + count = HEX_DIGITS; + if (copy_from_user(hexnum, buffer, count)) + return -EFAULT; + + /* + * Parse the first 8 characters as a hex string, any non-hex char + * is end-of-string. '00e1', 'e1', '00E1', 'E1' are all the same. + */ + value = 0; + + for (i = 0; i < count; i++) { + unsigned int c = hexnum[i]; + + switch (c) { + case '0' ... '9': c -= '0'; break; + case 'a' ... 'f': c -= 'a'-10; break; + case 'A' ... 'F': c -= 'A'-10; break; + default: + goto out; + } + value = (value << 4) | c; + } +out: + *ret = value; + return 0; +} + +#if CONFIG_SMP + +static struct proc_dir_entry * smp_affinity_entry [NR_IRQS]; + +static unsigned long irq_affinity [NR_IRQS] = { [0 ... NR_IRQS-1] = ~0UL }; +static int irq_affinity_read_proc (char *page, char **start, off_t off, + int count, int *eof, void *data) +{ + if (count < HEX_DIGITS+1) + return -EINVAL; + return sprintf (page, "%08lx\n", irq_affinity[(long)data]); +} + +static int irq_affinity_write_proc (struct file *file, const char *buffer, + unsigned long count, void *data) +{ + int irq = (long) data, full_count = count, err; + unsigned long new_value; + + if (!irq_desc[irq].handler->set_affinity) + return -EIO; + + err = parse_hex_value(buffer, count, &new_value); + + /* + * Do not allow disabling IRQs completely - it's a too easy + * way to make the system unusable accidentally :-) At least + * one online CPU still has to be targeted. + */ + if (!(new_value & cpu_online_map)) + return -EINVAL; + + irq_affinity[irq] = new_value; + irq_desc[irq].handler->set_affinity(irq, new_value); + + return full_count; +} + +#endif + +static int prof_cpu_mask_read_proc (char *page, char **start, off_t off, + int count, int *eof, void *data) +{ + unsigned long *mask = (unsigned long *) data; + if (count < HEX_DIGITS+1) + return -EINVAL; + return sprintf (page, "%08lx\n", *mask); +} + +static int prof_cpu_mask_write_proc (struct file *file, const char *buffer, + unsigned long count, void *data) +{ + unsigned long *mask = (unsigned long *) data, full_count = count, err; + unsigned long new_value; + + err = parse_hex_value(buffer, count, &new_value); + if (err) + return err; + + *mask = new_value; + return full_count; +} + +#define MAX_NAMELEN 10 + +static void register_irq_proc (unsigned int irq) +{ + char name [MAX_NAMELEN]; + + if (!root_irq_dir || (irq_desc[irq].handler == &no_irq_type) || + irq_dir[irq]) + return; + + memset(name, 0, MAX_NAMELEN); + sprintf(name, "%d", irq); + + /* create /proc/irq/1234 */ + irq_dir[irq] = proc_mkdir(name, root_irq_dir); + +#if CONFIG_SMP + { + struct proc_dir_entry *entry; + + /* create /proc/irq/1234/smp_affinity */ + entry = create_proc_entry("smp_affinity", 0600, irq_dir[irq]); + + if (entry) { + entry->nlink = 1; + entry->data = (void *)(long)irq; + entry->read_proc = irq_affinity_read_proc; + entry->write_proc = irq_affinity_write_proc; + } + + smp_affinity_entry[irq] = entry; + } +#endif +} + +unsigned long prof_cpu_mask = -1; + +void init_irq_proc (void) +{ + struct proc_dir_entry *entry; + int i; + + /* create /proc/irq */ + root_irq_dir = proc_mkdir("irq", 0); + + /* create /proc/irq/prof_cpu_mask */ + entry = create_proc_entry("prof_cpu_mask", 0600, root_irq_dir); + + if (!entry) + return; + + entry->nlink = 1; + entry->data = (void *)&prof_cpu_mask; + entry->read_proc = prof_cpu_mask_read_proc; + entry->write_proc = prof_cpu_mask_write_proc; + + /* + * Create entries for all existing IRQs. + */ + for (i = 0; i < NR_IRQS; i++) + register_irq_proc(i); +} + diff --git a/xenolinux-2.4.24-sparse/arch/xeno/kernel/ldt.c b/xenolinux-2.4.24-sparse/arch/xeno/kernel/ldt.c new file mode 100644 index 0000000000..501ce94484 --- /dev/null +++ b/xenolinux-2.4.24-sparse/arch/xeno/kernel/ldt.c @@ -0,0 +1,182 @@ +/* + * linux/kernel/ldt.c + * + * Copyright (C) 1992 Krishna Balasubramanian and Linus Torvalds + * Copyright (C) 1999 Ingo Molnar <mingo@redhat.com> + */ + +#include <linux/errno.h> +#include <linux/sched.h> +#include <linux/string.h> +#include <linux/mm.h> +#include <linux/smp.h> +#include <linux/smp_lock.h> +#include <linux/vmalloc.h> + +#include <asm/uaccess.h> +#include <asm/system.h> +#include <asm/ldt.h> +#include <asm/desc.h> + +/* + * read_ldt() is not really atomic - this is not a problem since + * synchronization of reads and writes done to the LDT has to be + * assured by user-space anyway. Writes are atomic, to protect + * the security checks done on new descriptors. + */ +static int read_ldt(void * ptr, unsigned long bytecount) +{ + int err; + unsigned long size; + struct mm_struct * mm = current->mm; + + err = 0; + if (!mm->context.segments) + goto out; + + size = LDT_ENTRIES*LDT_ENTRY_SIZE; + if (size > bytecount) + size = bytecount; + + err = size; + if (copy_to_user(ptr, mm->context.segments, size)) + err = -EFAULT; + out: + return err; +} + +static int read_default_ldt(void * ptr, unsigned long bytecount) +{ + int err; + unsigned long size; + void *address; + + err = 0; + address = &default_ldt[0]; + size = sizeof(struct desc_struct); + if (size > bytecount) + size = bytecount; + + err = size; + if (copy_to_user(ptr, address, size)) + err = -EFAULT; + + return err; +} + +static int write_ldt(void * ptr, unsigned long bytecount, int oldmode) +{ + struct mm_struct * mm = current->mm; + __u32 entry_1, entry_2, *lp; + unsigned long phys_lp, max_limit; + int error; + struct modify_ldt_ldt_s ldt_info; + + error = -EINVAL; + if (bytecount != sizeof(ldt_info)) + goto out; + error = -EFAULT; + if (copy_from_user(&ldt_info, ptr, sizeof(ldt_info))) + goto out; + + error = -EINVAL; + if (ldt_info.entry_number >= LDT_ENTRIES) + goto out; + if (ldt_info.contents == 3) { + if (oldmode) + goto out; + if (ldt_info.seg_not_present == 0) + goto out; + } + + /* + * This makes our tests for overlap with Xen space easier. There's no good + * reason to have a user segment starting this high anyway. + */ + if (ldt_info.base_addr >= PAGE_OFFSET) + goto out; + + down_write(&mm->mmap_sem); + if (!mm->context.segments) { + void * segments = vmalloc(LDT_ENTRIES*LDT_ENTRY_SIZE); + error = -ENOMEM; + if (!segments) + goto out_unlock; + memset(segments, 0, LDT_ENTRIES*LDT_ENTRY_SIZE); + make_pages_readonly(segments, (LDT_ENTRIES*LDT_ENTRY_SIZE)/PAGE_SIZE); + wmb(); + mm->context.segments = segments; + mm->context.cpuvalid = 1UL << smp_processor_id(); + load_LDT(mm); + flush_page_update_queue(); + } + + lp = (__u32 *)((ldt_info.entry_number<<3) + (char *)mm->context.segments); + phys_lp = arbitrary_virt_to_phys(lp); + + /* Allow LDTs to be cleared by the user. */ + if (ldt_info.base_addr == 0 && ldt_info.limit == 0) { + if (oldmode || + (ldt_info.contents == 0 && + ldt_info.read_exec_only == 1 && + ldt_info.seg_32bit == 0 && + ldt_info.limit_in_pages == 0 && + ldt_info.seg_not_present == 1 && + ldt_info.useable == 0 )) { + entry_1 = 0; + entry_2 = 0; + goto install; + } + } + + max_limit = HYPERVISOR_VIRT_START - ldt_info.base_addr; + if ( ldt_info.limit_in_pages ) + max_limit >>= PAGE_SHIFT; + max_limit--; + if ( (ldt_info.limit & 0xfffff) > (max_limit & 0xfffff) ) + ldt_info.limit = max_limit; + + entry_1 = ((ldt_info.base_addr & 0x0000ffff) << 16) | + (ldt_info.limit & 0x0ffff); + entry_2 = (ldt_info.base_addr & 0xff000000) | + ((ldt_info.base_addr & 0x00ff0000) >> 16) | + (ldt_info.limit & 0xf0000) | + ((ldt_info.read_exec_only ^ 1) << 9) | + (ldt_info.contents << 10) | + ((ldt_info.seg_not_present ^ 1) << 15) | + (ldt_info.seg_32bit << 22) | + (ldt_info.limit_in_pages << 23) | + 0x7000; + if (!oldmode) + entry_2 |= (ldt_info.useable << 20); + + /* Install the new entry ... */ + install: + error = HYPERVISOR_update_descriptor(phys_lp, entry_1, entry_2); + + out_unlock: + up_write(&mm->mmap_sem); + out: + return error; +} + +asmlinkage int sys_modify_ldt(int func, void *ptr, unsigned long bytecount) +{ + int ret = -ENOSYS; + + switch (func) { + case 0: + ret = read_ldt(ptr, bytecount); + break; + case 1: + ret = write_ldt(ptr, bytecount, 1); + break; + case 2: + ret = read_default_ldt(ptr, bytecount); + break; + case 0x11: + ret = write_ldt(ptr, bytecount, 0); + break; + } + return ret; +} diff --git a/xenolinux-2.4.24-sparse/arch/xeno/kernel/process.c b/xenolinux-2.4.24-sparse/arch/xeno/kernel/process.c new file mode 100644 index 0000000000..3b17c7326c --- /dev/null +++ b/xenolinux-2.4.24-sparse/arch/xeno/kernel/process.c @@ -0,0 +1,489 @@ +/* + * linux/arch/i386/kernel/process.c + * + * Copyright (C) 1995 Linus Torvalds + * + * Pentium III FXSR, SSE support + * Gareth Hughes <gareth@valinux.com>, May 2000 + */ + +/* + * This file handles the architecture-dependent parts of process handling.. + */ + +#define __KERNEL_SYSCALLS__ +#include <stdarg.h> + +#include <linux/errno.h> +#include <linux/sched.h> +#include <linux/kernel.h> +#include <linux/mm.h> +#include <linux/smp.h> +#include <linux/smp_lock.h> +#include <linux/stddef.h> +#include <linux/unistd.h> +#include <linux/ptrace.h> +#include <linux/slab.h> +#include <linux/vmalloc.h> +#include <linux/user.h> +#include <linux/a.out.h> +#include <linux/interrupt.h> +#include <linux/config.h> +#include <linux/delay.h> +#include <linux/reboot.h> +#include <linux/init.h> +#include <linux/mc146818rtc.h> + +#include <asm/uaccess.h> +#include <asm/pgtable.h> +#include <asm/system.h> +#include <asm/io.h> +#include <asm/ldt.h> +#include <asm/processor.h> +#include <asm/i387.h> +#include <asm/desc.h> +#include <asm/mmu_context.h> +#include <asm/multicall.h> +#include <asm/hypervisor-ifs/dom0_ops.h> + +#include <linux/irq.h> + +asmlinkage void ret_from_fork(void) __asm__("ret_from_fork"); + +int hlt_counter; + +/* + * Powermanagement idle function, if any.. + */ +void (*pm_idle)(void); + +/* + * Power off function, if any + */ +void (*pm_power_off)(void); + +void disable_hlt(void) +{ + hlt_counter++; +} + +void enable_hlt(void) +{ + hlt_counter--; +} + +/* + * The idle thread. There's no useful work to be + * done, so just try to conserve power and have a + * low exit latency (ie sit in a loop waiting for + * somebody to say that they'd like to reschedule) + */ +void cpu_idle (void) +{ + /* endless idle loop with no priority at all */ + init_idle(); + current->nice = 20; + current->counter = -100; + + while (1) { + while (!current->need_resched) + HYPERVISOR_yield(); + schedule(); + check_pgt_cache(); + } +} + +void machine_restart(char * __unused) +{ + HYPERVISOR_exit(); +} + +void machine_halt(void) +{ + HYPERVISOR_exit(); +} + +void machine_power_off(void) +{ + HYPERVISOR_exit(); +} + +extern void show_trace(unsigned long* esp); + +void show_regs(struct pt_regs * regs) +{ + printk("\n"); + printk("Pid: %d, comm: %20s\n", current->pid, current->comm); + printk("EIP: %04x:[<%08lx>] CPU: %d",0xffff & regs->xcs,regs->eip, smp_processor_id()); + if (regs->xcs & 2) + printk(" ESP: %04x:%08lx",0xffff & regs->xss,regs->esp); + printk(" EFLAGS: %08lx %s\n",regs->eflags, print_tainted()); + printk("EAX: %08lx EBX: %08lx ECX: %08lx EDX: %08lx\n", + regs->eax,regs->ebx,regs->ecx,regs->edx); + printk("ESI: %08lx EDI: %08lx EBP: %08lx", + regs->esi, regs->edi, regs->ebp); + printk(" DS: %04x ES: %04x\n", + 0xffff & regs->xds,0xffff & regs->xes); + + show_trace(®s->esp); +} + +/* + * No need to lock the MM as we are the last user + */ +void release_segments(struct mm_struct *mm) +{ + void * ldt = mm->context.segments; + + /* + * free the LDT + */ + if (ldt) { + mm->context.segments = NULL; + clear_LDT(); + make_pages_writeable(ldt, (LDT_ENTRIES*LDT_ENTRY_SIZE)/PAGE_SIZE); + flush_page_update_queue(); + vfree(ldt); + } +} + +/* + * Create a kernel thread + */ +int arch_kernel_thread(int (*fn)(void *), void * arg, unsigned long flags) +{ + long retval, d0; + + __asm__ __volatile__( + "movl %%esp,%%esi\n\t" + "int $0x80\n\t" /* Linux/i386 system call */ + "cmpl %%esp,%%esi\n\t" /* child or parent? */ + "je 1f\n\t" /* parent - jump */ + /* Load the argument into eax, and push it. That way, it does + * not matter whether the called function is compiled with + * -mregparm or not. */ + "movl %4,%%eax\n\t" + "pushl %%eax\n\t" + "call *%5\n\t" /* call fn */ + "movl %3,%0\n\t" /* exit */ + "int $0x80\n" + "1:\t" + :"=&a" (retval), "=&S" (d0) + :"0" (__NR_clone), "i" (__NR_exit), + "r" (arg), "r" (fn), + "b" (flags | CLONE_VM) + : "memory"); + + return retval; +} + +/* + * Free current thread data structures etc.. + */ +void exit_thread(void) +{ + /* nothing to do ... */ +} + +void flush_thread(void) +{ + struct task_struct *tsk = current; + + memset(tsk->thread.debugreg, 0, sizeof(unsigned long)*8); + + /* + * Forget coprocessor state.. + */ + clear_fpu(tsk); + tsk->used_math = 0; +} + +void release_thread(struct task_struct *dead_task) +{ + if (dead_task->mm) { + void * ldt = dead_task->mm->context.segments; + + // temporary debugging check + if (ldt) { + printk("WARNING: dead process %8s still has LDT? <%p>\n", + dead_task->comm, ldt); + BUG(); + } + } +} + +/* + * we do not have to muck with descriptors here, that is + * done in switch_mm() as needed. + */ +void copy_segments(struct task_struct *p, struct mm_struct *new_mm) +{ + struct mm_struct * old_mm; + void *old_ldt, *ldt; + + ldt = NULL; + old_mm = current->mm; + if (old_mm && (old_ldt = old_mm->context.segments) != NULL) { + /* + * Completely new LDT, we initialize it from the parent: + */ + ldt = vmalloc(LDT_ENTRIES*LDT_ENTRY_SIZE); + if ( ldt == NULL ) + { + printk(KERN_WARNING "ldt allocation failed\n"); + } + else + { + memcpy(ldt, old_ldt, LDT_ENTRIES*LDT_ENTRY_SIZE); + make_pages_readonly(ldt, (LDT_ENTRIES*LDT_ENTRY_SIZE)/PAGE_SIZE); + } + } + new_mm->context.segments = ldt; + new_mm->context.cpuvalid = ~0UL; /* valid on all CPU's - they can't have stale data */ +} + +/* + * Save a segment. + */ +#define savesegment(seg,value) \ + asm volatile("movl %%" #seg ",%0":"=m" (*(int *)&(value))) + +int copy_thread(int nr, unsigned long clone_flags, unsigned long esp, + unsigned long unused, + struct task_struct * p, struct pt_regs * regs) +{ + struct pt_regs * childregs; + unsigned long eflags; + + childregs = ((struct pt_regs *) (THREAD_SIZE + (unsigned long) p)) - 1; + struct_cpy(childregs, regs); + childregs->eax = 0; + childregs->esp = esp; + + p->thread.esp = (unsigned long) childregs; + p->thread.esp0 = (unsigned long) (childregs+1); + + p->thread.eip = (unsigned long) ret_from_fork; + + savesegment(fs,p->thread.fs); + savesegment(gs,p->thread.gs); + + unlazy_fpu(current); + struct_cpy(&p->thread.i387, ¤t->thread.i387); + + + __asm__ __volatile__ ( "pushfl; popl %0" : "=r" (eflags) : ); + p->thread.io_pl = (eflags >> 12) & 3; + + return 0; +} + +/* + * fill in the user structure for a core dump.. + */ +void dump_thread(struct pt_regs * regs, struct user * dump) +{ + int i; + +/* changed the size calculations - should hopefully work better. lbt */ + dump->magic = CMAGIC; + dump->start_code = 0; + dump->start_stack = regs->esp & ~(PAGE_SIZE - 1); + dump->u_tsize = ((unsigned long) current->mm->end_code) >> PAGE_SHIFT; + dump->u_dsize = ((unsigned long) (current->mm->brk + (PAGE_SIZE-1))) >> PAGE_SHIFT; + dump->u_dsize -= dump->u_tsize; + dump->u_ssize = 0; + for (i = 0; i < 8; i++) + dump->u_debugreg[i] = current->thread.debugreg[i]; + + if (dump->start_stack < TASK_SIZE) + dump->u_ssize = ((unsigned long) (TASK_SIZE - dump->start_stack)) >> PAGE_SHIFT; + + dump->regs.ebx = regs->ebx; + dump->regs.ecx = regs->ecx; + dump->regs.edx = regs->edx; + dump->regs.esi = regs->esi; + dump->regs.edi = regs->edi; + dump->regs.ebp = regs->ebp; + dump->regs.eax = regs->eax; + dump->regs.ds = regs->xds; + dump->regs.es = regs->xes; + savesegment(fs,dump->regs.fs); + savesegment(gs,dump->regs.gs); + dump->regs.orig_eax = regs->orig_eax; + dump->regs.eip = regs->eip; + dump->regs.cs = regs->xcs; + dump->regs.eflags = regs->eflags; + dump->regs.esp = regs->esp; + dump->regs.ss = regs->xss; + + dump->u_fpvalid = dump_fpu (regs, &dump->i387); +} + +/* + * switch_to(x,yn) should switch tasks from x to y. + * + * We fsave/fwait so that an exception goes off at the right time + * (as a call from the fsave or fwait in effect) rather than to + * the wrong process. Lazy FP saving no longer makes any sense + * with modern CPU's, and this simplifies a lot of things (SMP + * and UP become the same). + * + * NOTE! We used to use the x86 hardware context switching. The + * reason for not using it any more becomes apparent when you + * try to recover gracefully from saved state that is no longer + * valid (stale segment register values in particular). With the + * hardware task-switch, there is no way to fix up bad state in + * a reasonable manner. + * + * The fact that Intel documents the hardware task-switching to + * be slow is a fairly red herring - this code is not noticeably + * faster. However, there _is_ some room for improvement here, + * so the performance issues may eventually be a valid point. + * More important, however, is the fact that this allows us much + * more flexibility. + */ +void __switch_to(struct task_struct *prev_p, struct task_struct *next_p) +{ + struct thread_struct *next = &next_p->thread; + + __cli(); + + MULTICALL_flush_page_update_queue(); + + /* + * This is basically 'unlazy_fpu', except that we queue a multicall to + * indicate FPU task switch, rather than synchronously trapping to Xen. + */ + if ( prev_p->flags & PF_USEDFPU ) + { + if ( cpu_has_fxsr ) + asm volatile( "fxsave %0 ; fnclex" + : "=m" (prev_p->thread.i387.fxsave) ); + else + asm volatile( "fnsave %0 ; fwait" + : "=m" (prev_p->thread.i387.fsave) ); + prev_p->flags &= ~PF_USEDFPU; + queue_multicall0(__HYPERVISOR_fpu_taskswitch); + } + + queue_multicall2(__HYPERVISOR_stack_switch, __KERNEL_DS, next->esp0); + if ( start_info.flags & SIF_PRIVILEGED ) + { + dom0_op_t op; + op.cmd = DOM0_IOPL; + op.u.iopl.domain = start_info.dom_id; + op.u.iopl.iopl = next->io_pl; + queue_multicall1(__HYPERVISOR_dom0_op, (unsigned long)&op); + } + + /* EXECUTE ALL TASK SWITCH XEN SYSCALLS AT THIS POINT. */ + execute_multicall_list(); + __sti(); + + /* + * Restore %fs and %gs. + */ + loadsegment(fs, next->fs); + loadsegment(gs, next->gs); + + /* + * Now maybe reload the debug registers + */ + if ( next->debugreg[7] != 0 ) + { + HYPERVISOR_set_debugreg(0, next->debugreg[0]); + HYPERVISOR_set_debugreg(1, next->debugreg[1]); + HYPERVISOR_set_debugreg(2, next->debugreg[2]); + HYPERVISOR_set_debugreg(3, next->debugreg[3]); + /* no 4 and 5 */ + HYPERVISOR_set_debugreg(6, next->debugreg[6]); + HYPERVISOR_set_debugreg(7, next->debugreg[7]); + } +} + +asmlinkage int sys_fork(struct pt_regs regs) +{ + return do_fork(SIGCHLD, regs.esp, ®s, 0); +} + +asmlinkage int sys_clone(struct pt_regs regs) +{ + unsigned long clone_flags; + unsigned long newsp; + + clone_flags = regs.ebx; + newsp = regs.ecx; + if (!newsp) + newsp = regs.esp; + return do_fork(clone_flags, newsp, ®s, 0); +} + +/* + * This is trivial, and on the face of it looks like it + * could equally well be done in user mode. + * + * Not so, for quite unobvious reasons - register pressure. + * In user mode vfork() cannot have a stack frame, and if + * done by calling the "clone()" system call directly, you + * do not have enough call-clobbered registers to hold all + * the information you need. + */ +asmlinkage int sys_vfork(struct pt_regs regs) +{ + return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, regs.esp, ®s, 0); +} + +/* + * sys_execve() executes a new program. + */ +asmlinkage int sys_execve(struct pt_regs regs) +{ + int error; + char * filename; + + filename = getname((char *) regs.ebx); + error = PTR_ERR(filename); + if (IS_ERR(filename)) + goto out; + error = do_execve(filename, (char **) regs.ecx, (char **) regs.edx, ®s); + if (error == 0) + current->ptrace &= ~PT_DTRACE; + putname(filename); + out: + return error; +} + +/* + * These bracket the sleeping functions.. + */ +extern void scheduling_functions_start_here(void); +extern void scheduling_functions_end_here(void); +#define first_sched ((unsigned long) scheduling_functions_start_here) +#define last_sched ((unsigned long) scheduling_functions_end_here) + +unsigned long get_wchan(struct task_struct *p) +{ + unsigned long ebp, esp, eip; + unsigned long stack_page; + int count = 0; + if (!p || p == current || p->state == TASK_RUNNING) + return 0; + stack_page = (unsigned long)p; + esp = p->thread.esp; + if (!stack_page || esp < stack_page || esp > 8188+stack_page) + return 0; + /* include/asm-i386/system.h:switch_to() pushes ebp last. */ + ebp = *(unsigned long *) esp; + do { + if (ebp < stack_page || ebp > 8184+stack_page) + return 0; + eip = *(unsigned long *) (ebp+4); + if (eip < first_sched || eip >= last_sched) + return eip; + ebp = *(unsigned long *) ebp; + } while (count++ < 16); + return 0; +} +#undef last_sched +#undef first_sched diff --git a/xenolinux-2.4.24-sparse/arch/xeno/kernel/setup.c b/xenolinux-2.4.24-sparse/arch/xeno/kernel/setup.c new file mode 100644 index 0000000000..be70b26ce3 --- /dev/null +++ b/xenolinux-2.4.24-sparse/arch/xeno/kernel/setup.c @@ -0,0 +1,1215 @@ +/* + * linux/arch/i386/kernel/setup.c + * + * Copyright (C) 1995 Linus Torvalds + */ + +/* + * This file handles the architecture-dependent parts of initialization + */ + +#include <linux/errno.h> +#include <linux/sched.h> +#include <linux/kernel.h> +#include <linux/mm.h> +#include <linux/stddef.h> +#include <linux/unistd.h> +#include <linux/ptrace.h> +#include <linux/slab.h> +#include <linux/user.h> +#include <linux/a.out.h> +#include <linux/tty.h> +#include <linux/ioport.h> +#include <linux/delay.h> +#include <linux/config.h> +#include <linux/init.h> +#include <linux/apm_bios.h> +#ifdef CONFIG_BLK_DEV_RAM +#include <linux/blk.h> +#endif +#include <linux/highmem.h> +#include <linux/bootmem.h> +#include <linux/seq_file.h> +#include <asm/processor.h> +#include <linux/console.h> +#include <linux/module.h> +#include <asm/mtrr.h> +#include <asm/uaccess.h> +#include <asm/system.h> +#include <asm/io.h> +#include <asm/smp.h> +#include <asm/msr.h> +#include <asm/desc.h> +#include <asm/dma.h> +#include <asm/mpspec.h> +#include <asm/mmu_context.h> +#include <asm/hypervisor.h> +#include <asm/hypervisor-ifs/dom0_ops.h> +#include <linux/netdevice.h> +#include <linux/rtnetlink.h> +#include <linux/tqueue.h> + +/* + * Point at the empty zero page to start with. We map the real shared_info + * page as soon as fixmap is up and running. + */ +shared_info_t *HYPERVISOR_shared_info = (shared_info_t *)empty_zero_page; + +unsigned long *phys_to_machine_mapping; + +/* + * Machine setup.. + */ + +char ignore_irq13; /* set if exception 16 works */ +struct cpuinfo_x86 boot_cpu_data = { 0, 0, 0, 0, -1, 1, 0, 0, -1 }; + +unsigned long mmu_cr4_features; +//EXPORT_SYMBOL(mmu_cr4_features); + +unsigned char * vgacon_mmap; + +/* + * Bus types .. + */ +#ifdef CONFIG_EISA +int EISA_bus; +#endif +int MCA_bus; + +/* for MCA, but anyone else can use it if they want */ +unsigned int machine_id; +unsigned int machine_submodel_id; +unsigned int BIOS_revision; +unsigned int mca_pentium_flag; + +/* For PCI or other memory-mapped resources */ +unsigned long pci_mem_start = 0x10000000; + +/* + * Setup options + */ +struct drive_info_struct { char dummy[32]; } drive_info; +struct screen_info screen_info; +struct apm_info apm_info; +struct sys_desc_table_struct { + unsigned short length; + unsigned char table[0]; +}; + +unsigned char aux_device_present; + +extern int root_mountflags; +extern char _text, _etext, _edata, _end; + +int enable_acpi_smp_table; + +/* Raw start-of-day parameters from the hypervisor. */ +union start_info_union start_info_union; + +#define COMMAND_LINE_SIZE 256 +static char command_line[COMMAND_LINE_SIZE]; +char saved_command_line[COMMAND_LINE_SIZE]; + +static void __init parse_mem_cmdline (char ** cmdline_p) +{ + char c = ' ', *to = command_line, *from = saved_command_line; + int len = 0; + + /* Save unparsed command line copy for /proc/cmdline */ + memcpy(saved_command_line, start_info.cmd_line, COMMAND_LINE_SIZE); + saved_command_line[COMMAND_LINE_SIZE-1] = '\0'; + + for (;;) { + /* + * "mem=nopentium" disables the 4MB page tables. + * "mem=XXX[kKmM]" defines a memory region from HIGH_MEM + * to <mem>, overriding the bios size. + * "mem=XXX[KkmM]@XXX[KkmM]" defines a memory region from + * <start> to <start>+<mem>, overriding the bios size. + */ + if (c == ' ' && !memcmp(from, "mem=", 4)) { + if (to != command_line) + to--; + if (!memcmp(from+4, "nopentium", 9)) { + from += 9+4; + } else if (!memcmp(from+4, "exactmap", 8)) { + from += 8+4; + } else { + (void)memparse(from+4, &from); + if (*from == '@') + (void)memparse(from+1, &from); + } + } + + c = *(from++); + if (!c) + break; + if (COMMAND_LINE_SIZE <= ++len) + break; + *(to++) = c; + } + *to = '\0'; + *cmdline_p = command_line; +} + +void __init setup_arch(char **cmdline_p) +{ + unsigned long bootmap_size, start_pfn, max_low_pfn; + unsigned long i; + + extern void hypervisor_callback(void); + extern void failsafe_callback(void); + + extern unsigned long cpu0_pte_quicklist[]; + extern unsigned long cpu0_pgd_quicklist[]; + + HYPERVISOR_set_callbacks( + __KERNEL_CS, (unsigned long)hypervisor_callback, + __KERNEL_CS, (unsigned long)failsafe_callback); + + boot_cpu_data.pgd_quick = cpu0_pgd_quicklist; + boot_cpu_data.pte_quick = cpu0_pte_quicklist; + + ROOT_DEV = MKDEV(RAMDISK_MAJOR,0); + memset(&drive_info, 0, sizeof(drive_info)); + memset(&screen_info, 0, sizeof(screen_info)); + + /* This is drawn from a dump from vgacon:startup in standard Linux. */ + screen_info.orig_video_mode = 3; + screen_info.orig_video_isVGA = 1; + screen_info.orig_video_lines = 25; + screen_info.orig_video_cols = 80; + screen_info.orig_video_ega_bx = 3; + screen_info.orig_video_points = 16; + + memset(&apm_info.bios, 0, sizeof(apm_info.bios)); + aux_device_present = 0; +#ifdef CONFIG_BLK_DEV_RAM + rd_image_start = 0; + rd_prompt = 0; + rd_doload = 0; +#endif + + root_mountflags &= ~MS_RDONLY; + init_mm.start_code = (unsigned long) &_text; + init_mm.end_code = (unsigned long) &_etext; + init_mm.end_data = (unsigned long) &_edata; + init_mm.brk = (unsigned long) &_end; + + parse_mem_cmdline(cmdline_p); + +#define PFN_UP(x) (((x) + PAGE_SIZE-1) >> PAGE_SHIFT) +#define PFN_DOWN(x) ((x) >> PAGE_SHIFT) +#define PFN_PHYS(x) ((x) << PAGE_SHIFT) + +/* + * 128MB for vmalloc and initrd + */ +#define VMALLOC_RESERVE (unsigned long)(128 << 20) +#define MAXMEM (unsigned long)(HYPERVISOR_VIRT_START-PAGE_OFFSET-VMALLOC_RESERVE) +#define MAXMEM_PFN PFN_DOWN(MAXMEM) +#define MAX_NONPAE_PFN (1 << 20) + + /* + * partially used pages are not usable - thus + * we are rounding upwards: + */ +#ifdef CONFIG_BLK_DEV_INITRD + if ( start_info.mod_start ) + start_pfn = PFN_UP(__pa(start_info.mod_start + start_info.mod_len)); + else +#endif + start_pfn = PFN_UP(__pa(&_end)); + max_pfn = start_info.nr_pages; + + /* + * Determine low and high memory ranges: + */ + max_low_pfn = max_pfn; + if (max_low_pfn > MAXMEM_PFN) { + max_low_pfn = MAXMEM_PFN; +#ifndef CONFIG_HIGHMEM + /* Maximum memory usable is what is directly addressable */ + printk(KERN_WARNING "Warning only %ldMB will be used.\n", + MAXMEM>>20); + if (max_pfn > MAX_NONPAE_PFN) + printk(KERN_WARNING "Use a PAE enabled kernel.\n"); + else + printk(KERN_WARNING "Use a HIGHMEM enabled kernel.\n"); +#else /* !CONFIG_HIGHMEM */ +#ifndef CONFIG_X86_PAE + if (max_pfn > MAX_NONPAE_PFN) { + max_pfn = MAX_NONPAE_PFN; + printk(KERN_WARNING "Warning only 4GB will be used.\n"); + printk(KERN_WARNING "Use a PAE enabled kernel.\n"); + } +#endif /* !CONFIG_X86_PAE */ +#endif /* !CONFIG_HIGHMEM */ + } + +#ifdef CONFIG_HIGHMEM + highstart_pfn = highend_pfn = max_pfn; + if (max_pfn > MAXMEM_PFN) { + highstart_pfn = MAXMEM_PFN; + printk(KERN_NOTICE "%ldMB HIGHMEM available.\n", + pages_to_mb(highend_pfn - highstart_pfn)); + } +#endif + + /* + * Initialize the boot-time allocator, and free up all RAM. + * Then reserve space for OS image, and the bootmem bitmap. + */ + bootmap_size = init_bootmem(start_pfn, max_low_pfn); + free_bootmem(0, PFN_PHYS(max_low_pfn)); + reserve_bootmem(0, PFN_PHYS(start_pfn) + bootmap_size + PAGE_SIZE-1); + + /* Now reserve space for the hypervisor-provided page tables. */ + { + unsigned long *pgd = (unsigned long *)start_info.pt_base; + unsigned long pte; + int i; + reserve_bootmem(__pa(pgd), PAGE_SIZE); + for ( i = 0; i < (HYPERVISOR_VIRT_START>>22); i++ ) + { + unsigned long pgde = *pgd++; + if ( !(pgde & 1) ) continue; + pte = machine_to_phys(pgde & PAGE_MASK); + reserve_bootmem(pte, PAGE_SIZE); + } + } + cur_pgd = init_mm.pgd = (pgd_t *)start_info.pt_base; + + /* Now initialise the physical->machine mapping table. */ + phys_to_machine_mapping = alloc_bootmem(max_pfn * sizeof(unsigned long)); + for ( i = 0; i < max_pfn; i++ ) + { + unsigned long pgde, *ppte; + unsigned long pfn = i + (PAGE_OFFSET >> PAGE_SHIFT); + pgde = *((unsigned long *)start_info.pt_base + (pfn >> 10)); + ppte = (unsigned long *)machine_to_phys(pgde & PAGE_MASK) + (pfn&1023); + phys_to_machine_mapping[i] = + (*(unsigned long *)__va(ppte)) >> PAGE_SHIFT; + } + +#ifdef CONFIG_BLK_DEV_INITRD + if (start_info.mod_start) { + if ((__pa(start_info.mod_start) + start_info.mod_len) <= + (max_low_pfn << PAGE_SHIFT)) { + initrd_start = start_info.mod_start; + initrd_end = initrd_start + start_info.mod_len; + initrd_below_start_ok = 1; + } + else { + printk(KERN_ERR "initrd extends beyond end of memory " + "(0x%08lx > 0x%08lx)\ndisabling initrd\n", + __pa(start_info.mod_start) + start_info.mod_len, + max_low_pfn << PAGE_SHIFT); + initrd_start = 0; + } + } +#endif + + paging_init(); + + /* We are privileged guest os - should have IO privileges. */ + if ( start_info.flags & SIF_PRIVILEGED ) + { + dom0_op_t op; + op.cmd = DOM0_IOPL; + op.u.iopl.domain = start_info.dom_id; + op.u.iopl.iopl = 1; + if( HYPERVISOR_dom0_op(&op) != 0 ) + panic("Unable to obtain IOPL, despite being SIF_PRIVILEGED"); + current->thread.io_pl = 1; + } + + if(start_info.flags & SIF_CONSOLE) + { + if( !(start_info.flags & SIF_PRIVILEGED) ) + panic("Xen granted us console access but not privileged status"); + +#if defined(CONFIG_VT) +#if defined(CONFIG_VGA_CONSOLE) + conswitchp = &vga_con; +#elif defined(CONFIG_DUMMY_CONSOLE) + conswitchp = &dummy_con; +#endif +#endif + } +} + +static int cachesize_override __initdata = -1; +static int __init cachesize_setup(char *str) +{ + get_option (&str, &cachesize_override); + return 1; +} +__setup("cachesize=", cachesize_setup); + + +static int __init get_model_name(struct cpuinfo_x86 *c) +{ + unsigned int *v; + char *p, *q; + + if (cpuid_eax(0x80000000) < 0x80000004) + return 0; + + v = (unsigned int *) c->x86_model_id; + cpuid(0x80000002, &v[0], &v[1], &v[2], &v[3]); + cpuid(0x80000003, &v[4], &v[5], &v[6], &v[7]); + cpuid(0x80000004, &v[8], &v[9], &v[10], &v[11]); + c->x86_model_id[48] = 0; + + /* Intel chips right-justify this string for some dumb reason; + undo that brain damage */ + p = q = &c->x86_model_id[0]; + while ( *p == ' ' ) + p++; + if ( p != q ) { + while ( *p ) + *q++ = *p++; + while ( q <= &c->x86_model_id[48] ) + *q++ = '\0'; /* Zero-pad the rest */ + } + + return 1; +} + + +static void __init display_cacheinfo(struct cpuinfo_x86 *c) +{ + unsigned int n, dummy, ecx, edx, l2size; + + n = cpuid_eax(0x80000000); + + if (n >= 0x80000005) { + cpuid(0x80000005, &dummy, &dummy, &ecx, &edx); + printk(KERN_INFO "CPU: L1 I Cache: %dK (%d bytes/line), D cache %dK (%d bytes/line)\n", + edx>>24, edx&0xFF, ecx>>24, ecx&0xFF); + c->x86_cache_size=(ecx>>24)+(edx>>24); + } + + if (n < 0x80000006) /* Some chips just has a large L1. */ + return; + + ecx = cpuid_ecx(0x80000006); + l2size = ecx >> 16; + + /* AMD errata T13 (order #21922) */ + if ((c->x86_vendor == X86_VENDOR_AMD) && (c->x86 == 6)) { + if (c->x86_model == 3 && c->x86_mask == 0) /* Duron Rev A0 */ + l2size = 64; + if (c->x86_model == 4 && + (c->x86_mask==0 || c->x86_mask==1)) /* Tbird rev A1/A2 */ + l2size = 256; + } + + /* Intel PIII Tualatin. This comes in two flavours. + * One has 256kb of cache, the other 512. We have no way + * to determine which, so we use a boottime override + * for the 512kb model, and assume 256 otherwise. + */ + if ((c->x86_vendor == X86_VENDOR_INTEL) && (c->x86 == 6) && + (c->x86_model == 11) && (l2size == 0)) + l2size = 256; + + if (c->x86_vendor == X86_VENDOR_CENTAUR) { + /* VIA C3 CPUs (670-68F) need further shifting. */ + if ((c->x86 == 6) && + ((c->x86_model == 7) || (c->x86_model == 8))) { + l2size >>= 8; + } + + /* VIA also screwed up Nehemiah stepping 1, and made + it return '65KB' instead of '64KB' + - Note, it seems this may only be in engineering samples. */ + if ((c->x86==6) && (c->x86_model==9) && + (c->x86_mask==1) && (l2size==65)) + l2size -= 1; + } + + /* Allow user to override all this if necessary. */ + if (cachesize_override != -1) + l2size = cachesize_override; + + if ( l2size == 0 ) + return; /* Again, no L2 cache is possible */ + + c->x86_cache_size = l2size; + + printk(KERN_INFO "CPU: L2 Cache: %dK (%d bytes/line)\n", + l2size, ecx & 0xFF); +} + + +static int __init init_amd(struct cpuinfo_x86 *c) +{ + int r; + + /* Bit 31 in normal CPUID used for nonstandard 3DNow ID; + 3DNow is IDd by bit 31 in extended CPUID (1*32+31) anyway */ + clear_bit(0*32+31, &c->x86_capability); + + r = get_model_name(c); + + switch(c->x86) + { + case 6: /* An Athlon/Duron. We can trust the BIOS probably */ + break; + default: + panic("Unsupported AMD processor\n"); + } + + display_cacheinfo(c); + return r; +} + + +static void __init init_intel(struct cpuinfo_x86 *c) +{ + char *p = NULL; + unsigned int l1i = 0, l1d = 0, l2 = 0, l3 = 0; /* Cache sizes */ + + if (c->cpuid_level > 1) { + /* supports eax=2 call */ + int i, j, n; + int regs[4]; + unsigned char *dp = (unsigned char *)regs; + + /* Number of times to iterate */ + n = cpuid_eax(2) & 0xFF; + + for ( i = 0 ; i < n ; i++ ) { + cpuid(2, ®s[0], ®s[1], ®s[2], ®s[3]); + + /* If bit 31 is set, this is an unknown format */ + for ( j = 0 ; j < 3 ; j++ ) { + if ( regs[j] < 0 ) regs[j] = 0; + } + + /* Byte 0 is level count, not a descriptor */ + for ( j = 1 ; j < 16 ; j++ ) { + unsigned char des = dp[j]; + unsigned char dl, dh; + unsigned int cs; + + dh = des >> 4; + dl = des & 0x0F; + + /* Black magic... */ + + switch ( dh ) + { + case 0: + switch ( dl ) { + case 6: + /* L1 I cache */ + l1i += 8; + break; + case 8: + /* L1 I cache */ + l1i += 16; + break; + case 10: + /* L1 D cache */ + l1d += 8; + break; + case 12: + /* L1 D cache */ + l1d += 16; + break; + default:; + /* TLB, or unknown */ + } + break; + case 2: + if ( dl ) { + /* L3 cache */ + cs = (dl-1) << 9; + l3 += cs; + } + break; + case 4: + if ( c->x86 > 6 && dl ) { + /* P4 family */ + /* L3 cache */ + cs = 128 << (dl-1); + l3 += cs; + break; + } + /* else same as 8 - fall through */ + case 8: + if ( dl ) { + /* L2 cache */ + cs = 128 << (dl-1); + l2 += cs; + } + break; + case 6: + if (dl > 5) { + /* L1 D cache */ + cs = 8<<(dl-6); + l1d += cs; + } + break; + case 7: + if ( dl >= 8 ) + { + /* L2 cache */ + cs = 64<<(dl-8); + l2 += cs; + } else { + /* L0 I cache, count as L1 */ + cs = dl ? (16 << (dl-1)) : 12; + l1i += cs; + } + break; + default: + /* TLB, or something else we don't know about */ + break; + } + } + } + if ( l1i || l1d ) + printk(KERN_INFO "CPU: L1 I cache: %dK, L1 D cache: %dK\n", + l1i, l1d); + if ( l2 ) + printk(KERN_INFO "CPU: L2 cache: %dK\n", l2); + if ( l3 ) + printk(KERN_INFO "CPU: L3 cache: %dK\n", l3); + + /* + * This assumes the L3 cache is shared; it typically lives in + * the northbridge. The L1 caches are included by the L2 + * cache, and so should not be included for the purpose of + * SMP switching weights. + */ + c->x86_cache_size = l2 ? l2 : (l1i+l1d); + } + + /* SEP CPUID bug: Pentium Pro reports SEP but doesn't have it */ + if ( c->x86 == 6 && c->x86_model < 3 && c->x86_mask < 3 ) + clear_bit(X86_FEATURE_SEP, &c->x86_capability); + + /* Names for the Pentium II/Celeron processors + detectable only by also checking the cache size. + Dixon is NOT a Celeron. */ + if (c->x86 == 6) { + switch (c->x86_model) { + case 5: + if (l2 == 0) + p = "Celeron (Covington)"; + if (l2 == 256) + p = "Mobile Pentium II (Dixon)"; + break; + + case 6: + if (l2 == 128) + p = "Celeron (Mendocino)"; + break; + + case 8: + if (l2 == 128) + p = "Celeron (Coppermine)"; + break; + } + } + + if ( p ) + strcpy(c->x86_model_id, p); +} + +void __init get_cpu_vendor(struct cpuinfo_x86 *c) +{ + char *v = c->x86_vendor_id; + + if (!strcmp(v, "GenuineIntel")) + c->x86_vendor = X86_VENDOR_INTEL; + else if (!strcmp(v, "AuthenticAMD")) + c->x86_vendor = X86_VENDOR_AMD; + else + c->x86_vendor = X86_VENDOR_UNKNOWN; +} + +struct cpu_model_info { + int vendor; + int family; + char *model_names[16]; +}; + +/* Naming convention should be: <Name> [(<Codename>)] */ +/* This table only is used unless init_<vendor>() below doesn't set it; */ +/* in particular, if CPUID levels 0x80000002..4 are supported, this isn't used */ +static struct cpu_model_info cpu_models[] __initdata = { + { X86_VENDOR_INTEL, 6, + { "Pentium Pro A-step", "Pentium Pro", NULL, "Pentium II (Klamath)", + NULL, "Pentium II (Deschutes)", "Mobile Pentium II", + "Pentium III (Katmai)", "Pentium III (Coppermine)", NULL, + "Pentium III (Cascades)", NULL, NULL, NULL, NULL }}, + { X86_VENDOR_AMD, 6, /* Is this this really necessary?? */ + { "Athlon", "Athlon", + "Athlon", NULL, "Athlon", NULL, + NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL }} +}; + +/* Look up CPU names by table lookup. */ +static char __init *table_lookup_model(struct cpuinfo_x86 *c) +{ + struct cpu_model_info *info = cpu_models; + int i; + + if ( c->x86_model >= 16 ) + return NULL; /* Range check */ + + for ( i = 0 ; i < sizeof(cpu_models)/sizeof(struct cpu_model_info) ; i++ ) { + if ( info->vendor == c->x86_vendor && + info->family == c->x86 ) { + return info->model_names[c->x86_model]; + } + info++; + } + return NULL; /* Not found */ +} + + + +/* Standard macro to see if a specific flag is changeable */ +static inline int flag_is_changeable_p(u32 flag) +{ + u32 f1, f2; + + asm("pushfl\n\t" + "pushfl\n\t" + "popl %0\n\t" + "movl %0,%1\n\t" + "xorl %2,%0\n\t" + "pushl %0\n\t" + "popfl\n\t" + "pushfl\n\t" + "popl %0\n\t" + "popfl\n\t" + : "=&r" (f1), "=&r" (f2) + : "ir" (flag)); + + return ((f1^f2) & flag) != 0; +} + + +/* Probe for the CPUID instruction */ +static int __init have_cpuid_p(void) +{ + return flag_is_changeable_p(X86_EFLAGS_ID); +} + + + +#if defined(CONFIG_EDD) || defined(CONFIG_EDD_MODULE) +unsigned char eddnr; +struct edd_info edd[EDDMAXNR]; +/** + * copy_edd() - Copy the BIOS EDD information + * from empty_zero_page into a safe place. + * + */ +static inline void copy_edd(void) +{ + eddnr = EDD_NR; + memcpy(edd, EDD_BUF, sizeof(edd)); +} +#else +static inline void copy_edd(void) {} +#endif + +/* + * This does the hard work of actually picking apart the CPU stuff... + */ +void __init identify_cpu(struct cpuinfo_x86 *c) +{ + int junk, i; + u32 xlvl, tfms; + + c->loops_per_jiffy = loops_per_jiffy; + c->x86_cache_size = -1; + c->x86_vendor = X86_VENDOR_UNKNOWN; + c->cpuid_level = -1; /* CPUID not detected */ + c->x86_model = c->x86_mask = 0; /* So far unknown... */ + c->x86_vendor_id[0] = '\0'; /* Unset */ + c->x86_model_id[0] = '\0'; /* Unset */ + memset(&c->x86_capability, 0, sizeof c->x86_capability); + c->hard_math = 1; + + if ( !have_cpuid_p() ) { + panic("Processor must support CPUID\n"); + } else { + /* CPU does have CPUID */ + + /* Get vendor name */ + cpuid(0x00000000, &c->cpuid_level, + (int *)&c->x86_vendor_id[0], + (int *)&c->x86_vendor_id[8], + (int *)&c->x86_vendor_id[4]); + + get_cpu_vendor(c); + /* Initialize the standard set of capabilities */ + /* Note that the vendor-specific code below might override */ + + /* Intel-defined flags: level 0x00000001 */ + if ( c->cpuid_level >= 0x00000001 ) { + u32 capability, excap; + cpuid(0x00000001, &tfms, &junk, &excap, &capability); + c->x86_capability[0] = capability; + c->x86_capability[4] = excap; + c->x86 = (tfms >> 8) & 15; + c->x86_model = (tfms >> 4) & 15; + if (c->x86 == 0xf) { + c->x86 += (tfms >> 20) & 0xff; + c->x86_model += ((tfms >> 16) & 0xF) << 4; + } + c->x86_mask = tfms & 15; + } else { + /* Have CPUID level 0 only - unheard of */ + c->x86 = 4; + } + + /* AMD-defined flags: level 0x80000001 */ + xlvl = cpuid_eax(0x80000000); + if ( (xlvl & 0xffff0000) == 0x80000000 ) { + if ( xlvl >= 0x80000001 ) + c->x86_capability[1] = cpuid_edx(0x80000001); + if ( xlvl >= 0x80000004 ) + get_model_name(c); /* Default name */ + } + + /* Transmeta-defined flags: level 0x80860001 */ + xlvl = cpuid_eax(0x80860000); + if ( (xlvl & 0xffff0000) == 0x80860000 ) { + if ( xlvl >= 0x80860001 ) + c->x86_capability[2] = cpuid_edx(0x80860001); + } + } + + printk(KERN_DEBUG "CPU: Before vendor init, caps: %08x %08x %08x, vendor = %d\n", + c->x86_capability[0], + c->x86_capability[1], + c->x86_capability[2], + c->x86_vendor); + + /* + * Vendor-specific initialization. In this section we + * canonicalize the feature flags, meaning if there are + * features a certain CPU supports which CPUID doesn't + * tell us, CPUID claiming incorrect flags, or other bugs, + * we handle them here. + * + * At the end of this section, c->x86_capability better + * indicate the features this CPU genuinely supports! + */ + switch ( c->x86_vendor ) { + case X86_VENDOR_AMD: + init_amd(c); + break; + + case X86_VENDOR_INTEL: + init_intel(c); + break; + + default: + panic("Unsupported CPU vendor\n"); + } + + printk(KERN_DEBUG "CPU: After vendor init, caps: %08x %08x %08x %08x\n", + c->x86_capability[0], + c->x86_capability[1], + c->x86_capability[2], + c->x86_capability[3]); + + + /* If the model name is still unset, do table lookup. */ + if ( !c->x86_model_id[0] ) { + char *p; + p = table_lookup_model(c); + if ( p ) + strcpy(c->x86_model_id, p); + else + /* Last resort... */ + sprintf(c->x86_model_id, "%02x/%02x", + c->x86_vendor, c->x86_model); + } + + /* Now the feature flags better reflect actual CPU features! */ + + printk(KERN_DEBUG "CPU: After generic, caps: %08x %08x %08x %08x\n", + c->x86_capability[0], + c->x86_capability[1], + c->x86_capability[2], + c->x86_capability[3]); + + /* + * On SMP, boot_cpu_data holds the common feature set between + * all CPUs; so make sure that we indicate which features are + * common between the CPUs. The first time this routine gets + * executed, c == &boot_cpu_data. + */ + if ( c != &boot_cpu_data ) { + /* AND the already accumulated flags with these */ + for ( i = 0 ; i < NCAPINTS ; i++ ) + boot_cpu_data.x86_capability[i] &= c->x86_capability[i]; + } + + printk(KERN_DEBUG "CPU: Common caps: %08x %08x %08x %08x\n", + boot_cpu_data.x86_capability[0], + boot_cpu_data.x86_capability[1], + boot_cpu_data.x86_capability[2], + boot_cpu_data.x86_capability[3]); +} + + +/* These need to match <asm/processor.h> */ +static char *cpu_vendor_names[] __initdata = { + "Intel", "Cyrix", "AMD", "UMC", "NexGen", "Centaur", "Rise", "Transmeta" }; + + +void __init print_cpu_info(struct cpuinfo_x86 *c) +{ + char *vendor = NULL; + + if (c->x86_vendor < sizeof(cpu_vendor_names)/sizeof(char *)) + vendor = cpu_vendor_names[c->x86_vendor]; + else if (c->cpuid_level >= 0) + vendor = c->x86_vendor_id; + + if (vendor && strncmp(c->x86_model_id, vendor, strlen(vendor))) + printk("%s ", vendor); + + if (!c->x86_model_id[0]) + printk("%d86", c->x86); + else + printk("%s", c->x86_model_id); + + if (c->x86_mask || c->cpuid_level >= 0) + printk(" stepping %02x\n", c->x86_mask); + else + printk("\n"); +} + +/* + * Get CPU information for use by the procfs. + */ +static int show_cpuinfo(struct seq_file *m, void *v) +{ + /* + * These flag bits must match the definitions in <asm/cpufeature.h>. + * NULL means this bit is undefined or reserved; either way it doesn't + * have meaning as far as Linux is concerned. Note that it's important + * to realize there is a difference between this table and CPUID -- if + * applications want to get the raw CPUID data, they should access + * /dev/cpu/<cpu_nr>/cpuid instead. + */ + static char *x86_cap_flags[] = { + /* Intel-defined */ + "fpu", "vme", "de", "pse", "tsc", "msr", "pae", "mce", + "cx8", "apic", NULL, "sep", "mtrr", "pge", "mca", "cmov", + "pat", "pse36", "pn", "clflush", NULL, "dts", "acpi", "mmx", + "fxsr", "sse", "sse2", "ss", "ht", "tm", "ia64", "pbe", + + /* AMD-defined */ + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, "syscall", NULL, NULL, NULL, NULL, + NULL, NULL, NULL, "mp", NULL, NULL, "mmxext", NULL, + NULL, NULL, NULL, NULL, NULL, "lm", "3dnowext", "3dnow", + + /* Transmeta-defined */ + "recovery", "longrun", NULL, "lrti", NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + + /* Other (Linux-defined) */ + "cxmmx", "k6_mtrr", "cyrix_arr", "centaur_mcr", + NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + + /* Intel-defined (#2) */ + "pni", NULL, NULL, "monitor", "ds_cpl", NULL, NULL, "tm2", + "est", NULL, "cid", NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + + /* VIA/Cyrix/Centaur-defined */ + NULL, NULL, "xstore", NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + + }; + struct cpuinfo_x86 *c = v; + int i, n = c - cpu_data; + int fpu_exception; + +#ifdef CONFIG_SMP + if (!(cpu_online_map & (1<<n))) + return 0; +#endif + seq_printf(m, "processor\t: %d\n" + "vendor_id\t: %s\n" + "cpu family\t: %d\n" + "model\t\t: %d\n" + "model name\t: %s\n", + n, + c->x86_vendor_id[0] ? c->x86_vendor_id : "unknown", + c->x86, + c->x86_model, + c->x86_model_id[0] ? c->x86_model_id : "unknown"); + + if (c->x86_mask || c->cpuid_level >= 0) + seq_printf(m, "stepping\t: %d\n", c->x86_mask); + else + seq_printf(m, "stepping\t: unknown\n"); + + if ( test_bit(X86_FEATURE_TSC, &c->x86_capability) ) { + seq_printf(m, "cpu MHz\t\t: %lu.%03lu\n", + cpu_khz / 1000, (cpu_khz % 1000)); + } + + /* Cache size */ + if (c->x86_cache_size >= 0) + seq_printf(m, "cache size\t: %d KB\n", c->x86_cache_size); + + /* We use exception 16 if we have hardware math and we've either seen it or the CPU claims it is internal */ + fpu_exception = c->hard_math && (ignore_irq13 || cpu_has_fpu); + seq_printf(m, "fdiv_bug\t: %s\n" + "hlt_bug\t\t: %s\n" + "f00f_bug\t: %s\n" + "coma_bug\t: %s\n" + "fpu\t\t: %s\n" + "fpu_exception\t: %s\n" + "cpuid level\t: %d\n" + "wp\t\t: %s\n" + "flags\t\t:", + c->fdiv_bug ? "yes" : "no", + c->hlt_works_ok ? "no" : "yes", + c->f00f_bug ? "yes" : "no", + c->coma_bug ? "yes" : "no", + c->hard_math ? "yes" : "no", + fpu_exception ? "yes" : "no", + c->cpuid_level, + c->wp_works_ok ? "yes" : "no"); + + for ( i = 0 ; i < 32*NCAPINTS ; i++ ) + if ( test_bit(i, &c->x86_capability) && + x86_cap_flags[i] != NULL ) + seq_printf(m, " %s", x86_cap_flags[i]); + + seq_printf(m, "\nbogomips\t: %lu.%02lu\n\n", + c->loops_per_jiffy/(500000/HZ), + (c->loops_per_jiffy/(5000/HZ)) % 100); + return 0; +} + +static void *c_start(struct seq_file *m, loff_t *pos) +{ + return *pos < NR_CPUS ? cpu_data + *pos : NULL; +} +static void *c_next(struct seq_file *m, void *v, loff_t *pos) +{ + ++*pos; + return c_start(m, pos); +} +static void c_stop(struct seq_file *m, void *v) +{ +} +struct seq_operations cpuinfo_op = { + start: c_start, + next: c_next, + stop: c_stop, + show: show_cpuinfo, +}; + +unsigned long cpu_initialized __initdata = 0; + +/* + * cpu_init() initializes state that is per-CPU. Some data is already + * initialized (naturally) in the bootstrap process, such as the GDT + * and IDT. We reload them nevertheless, this function acts as a + * 'CPU state barrier', nothing should get across. + */ +void __init cpu_init (void) +{ + int nr = smp_processor_id(); + + if (test_and_set_bit(nr, &cpu_initialized)) { + printk(KERN_WARNING "CPU#%d already initialized!\n", nr); + for (;;) __sti(); + } + printk(KERN_INFO "Initializing CPU#%d\n", nr); + + /* + * set up and load the per-CPU TSS and LDT + */ + atomic_inc(&init_mm.mm_count); + current->active_mm = &init_mm; + if(current->mm) + BUG(); + enter_lazy_tlb(&init_mm, current, nr); + + HYPERVISOR_stack_switch(__KERNEL_DS, current->thread.esp0); + + load_LDT(&init_mm); + flush_page_update_queue(); + + /* Force FPU initialization. */ + current->flags &= ~PF_USEDFPU; + current->used_math = 0; + stts(); +} + + +/****************************************************************************** + * Time-to-die callback handling. + */ + +static void die_irq(int irq, void *unused, struct pt_regs *regs) +{ + extern void ctrl_alt_del(void); + ctrl_alt_del(); +} + +static int __init setup_die_event(void) +{ + (void)request_irq(_EVENT_DIE, die_irq, 0, "die", NULL); + return 0; +} + +__initcall(setup_die_event); + + +/****************************************************************************** + * Stop/pickle callback handling. + */ + +#include <asm/suspend.h> + +static void stop_task(void *unused) +{ + /* Hmmm... a cleaner interface to suspend/resume blkdevs would be nice. */ + extern void blkdev_suspend(void); + extern void blkdev_resume(void); + + unsigned long *pfn_to_mfn_frame_list = NULL; + suspend_record_t *suspend_record = NULL; + struct net_device *dev; + char name[6]; + int i, j; + + if ( (pfn_to_mfn_frame_list = (unsigned long *)__get_free_page(GFP_KERNEL)) + == NULL ) + goto out; + if ( (suspend_record = (suspend_record_t *)__get_free_page(GFP_KERNEL)) + == NULL ) + goto out; + + suspend_record->pfn_to_mfn_frame_list = + virt_to_machine(pfn_to_mfn_frame_list) >> PAGE_SHIFT; + suspend_record->nr_pfns = max_pfn; + + j = 0; + for ( i = 0; i < max_pfn; i += (PAGE_SIZE / sizeof(unsigned long)) ) + pfn_to_mfn_frame_list[j++] = + virt_to_machine(&phys_to_machine_mapping[i]) >> PAGE_SHIFT; + + /* + * NB. This is /not/ a full dev_close() as that loses route information! + * Instead we do essentialy the same as dev_close() but without notifying + * various registered subsystems about the NETDEV_DOWN event. + */ + rtnl_lock(); + for ( i = 0; i < 10; i++ ) + { + sprintf(name, "eth%d", i); + if ( ((dev = __dev_get_by_name(name)) != NULL) && + (dev->flags & IFF_UP) ) + { + dev_deactivate(dev); + clear_bit(__LINK_STATE_START, &dev->state); + if ( dev->stop != NULL ) + dev->stop(dev); + dev->flags &= ~IFF_UP; + } + } + rtnl_unlock(); + + blkdev_suspend(); + + __cli(); + + HYPERVISOR_shared_info = (shared_info_t *)empty_zero_page; + clear_fixmap(FIX_SHARED_INFO); + + memcpy(&suspend_record->resume_info, &start_info, sizeof(start_info)); + + HYPERVISOR_stop(virt_to_machine(suspend_record) >> PAGE_SHIFT); + + memcpy(&start_info, &suspend_record->resume_info, sizeof(start_info)); + + set_fixmap(FIX_SHARED_INFO, start_info.shared_info); + HYPERVISOR_shared_info = (shared_info_t *)fix_to_virt(FIX_SHARED_INFO); + memset(empty_zero_page, 0, PAGE_SIZE); + + __sti(); + + blkdev_resume(); + + /* + * We now do the opposite of the network suspend code. Basically it's + * dev_open() but without notifying anyone about NETDEV_UP. + */ + rtnl_lock(); + for ( i = 0; i < 10; i++ ) + { + sprintf(name, "eth%d", i); + if ( ((dev = __dev_get_by_name(name)) != NULL) && + !(dev->flags & IFF_UP) ) + { + set_bit(__LINK_STATE_START, &dev->state); + if ( (dev->open == NULL) || (dev->open(dev) == 0) ) + { + dev->flags |= IFF_UP; + dev_activate(dev); + } + else + { + clear_bit(__LINK_STATE_START, &dev->state); + } + } + } + rtnl_unlock(); + + out: + if ( pfn_to_mfn_frame_list != NULL ) + free_page((unsigned long)pfn_to_mfn_frame_list); + if ( suspend_record != NULL ) + free_page((unsigned long)suspend_record); +} + +static struct tq_struct stop_tq; + +static void stop_irq(int irq, void *unused, struct pt_regs *regs) +{ + stop_tq.routine = stop_task; + schedule_task(&stop_tq); +} + +static int __init setup_stop_event(void) +{ + (void)request_irq(_EVENT_STOP, stop_irq, 0, "stop", NULL); + return 0; +} + +__initcall(setup_stop_event); + diff --git a/xenolinux-2.4.24-sparse/arch/xeno/kernel/signal.c b/xenolinux-2.4.24-sparse/arch/xeno/kernel/signal.c new file mode 100644 index 0000000000..f646c5c0ca --- /dev/null +++ b/xenolinux-2.4.24-sparse/arch/xeno/kernel/signal.c @@ -0,0 +1,717 @@ +/* + * linux/arch/i386/kernel/signal.c + * + * Copyright (C) 1991, 1992 Linus Torvalds + * + * 1997-11-28 Modified for POSIX.1b signals by Richard Henderson + * 2000-06-20 Pentium III FXSR, SSE support by Gareth Hughes + */ + +#include <linux/sched.h> +#include <linux/mm.h> +#include <linux/smp.h> +#include <linux/smp_lock.h> +#include <linux/kernel.h> +#include <linux/signal.h> +#include <linux/errno.h> +#include <linux/wait.h> +#include <linux/ptrace.h> +#include <linux/unistd.h> +#include <linux/stddef.h> +#include <linux/tty.h> +#include <linux/personality.h> +#include <asm/ucontext.h> +#include <asm/uaccess.h> +#include <asm/i387.h> + +#define DEBUG_SIG 0 + +#define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP))) + +int FASTCALL(do_signal(struct pt_regs *regs, sigset_t *oldset)); + +int copy_siginfo_to_user(siginfo_t *to, siginfo_t *from) +{ + if (!access_ok (VERIFY_WRITE, to, sizeof(siginfo_t))) + return -EFAULT; + if (from->si_code < 0) + return __copy_to_user(to, from, sizeof(siginfo_t)); + else { + int err; + + /* If you change siginfo_t structure, please be sure + this code is fixed accordingly. + It should never copy any pad contained in the structure + to avoid security leaks, but must copy the generic + 3 ints plus the relevant union member. */ + err = __put_user(from->si_signo, &to->si_signo); + err |= __put_user(from->si_errno, &to->si_errno); + err |= __put_user((short)from->si_code, &to->si_code); + /* First 32bits of unions are always present. */ + err |= __put_user(from->si_pid, &to->si_pid); + switch (from->si_code >> 16) { + case __SI_FAULT >> 16: + break; + case __SI_CHLD >> 16: + err |= __put_user(from->si_utime, &to->si_utime); + err |= __put_user(from->si_stime, &to->si_stime); + err |= __put_user(from->si_status, &to->si_status); + default: + err |= __put_user(from->si_uid, &to->si_uid); + break; + /* case __SI_RT: This is not generated by the kernel as of now. */ + } + return err; + } +} + +/* + * Atomically swap in the new signal mask, and wait for a signal. + */ +asmlinkage int +sys_sigsuspend(int history0, int history1, old_sigset_t mask) +{ + struct pt_regs * regs = (struct pt_regs *) &history0; + sigset_t saveset; + + mask &= _BLOCKABLE; + spin_lock_irq(¤t->sigmask_lock); + saveset = current->blocked; + siginitset(¤t->blocked, mask); + recalc_sigpending(current); + spin_unlock_irq(¤t->sigmask_lock); + + regs->eax = -EINTR; + while (1) { + current->state = TASK_INTERRUPTIBLE; + schedule(); + if (do_signal(regs, &saveset)) + return -EINTR; + } +} + +asmlinkage int +sys_rt_sigsuspend(sigset_t *unewset, size_t sigsetsize) +{ + struct pt_regs * regs = (struct pt_regs *) &unewset; + sigset_t saveset, newset; + + /* XXX: Don't preclude handling different sized sigset_t's. */ + if (sigsetsize != sizeof(sigset_t)) + return -EINVAL; + + if (copy_from_user(&newset, unewset, sizeof(newset))) + return -EFAULT; + sigdelsetmask(&newset, ~_BLOCKABLE); + + spin_lock_irq(¤t->sigmask_lock); + saveset = current->blocked; + current->blocked = newset; + recalc_sigpending(current); + spin_unlock_irq(¤t->sigmask_lock); + + regs->eax = -EINTR; + while (1) { + current->state = TASK_INTERRUPTIBLE; + schedule(); + if (do_signal(regs, &saveset)) + return -EINTR; + } +} + +asmlinkage int +sys_sigaction(int sig, const struct old_sigaction *act, + struct old_sigaction *oact) +{ + struct k_sigaction new_ka, old_ka; + int ret; + + if (act) { + old_sigset_t mask; + if (verify_area(VERIFY_READ, act, sizeof(*act)) || + __get_user(new_ka.sa.sa_handler, &act->sa_handler) || + __get_user(new_ka.sa.sa_restorer, &act->sa_restorer)) + return -EFAULT; + __get_user(new_ka.sa.sa_flags, &act->sa_flags); + __get_user(mask, &act->sa_mask); + siginitset(&new_ka.sa.sa_mask, mask); + } + + ret = do_sigaction(sig, act ? &new_ka : NULL, oact ? &old_ka : NULL); + + if (!ret && oact) { + if (verify_area(VERIFY_WRITE, oact, sizeof(*oact)) || + __put_user(old_ka.sa.sa_handler, &oact->sa_handler) || + __put_user(old_ka.sa.sa_restorer, &oact->sa_restorer)) + return -EFAULT; + __put_user(old_ka.sa.sa_flags, &oact->sa_flags); + __put_user(old_ka.sa.sa_mask.sig[0], &oact->sa_mask); + } + + return ret; +} + +asmlinkage int +sys_sigaltstack(const stack_t *uss, stack_t *uoss) +{ + struct pt_regs *regs = (struct pt_regs *) &uss; + return do_sigaltstack(uss, uoss, regs->esp); +} + + +/* + * Do a signal return; undo the signal stack. + */ + +struct sigframe +{ + char *pretcode; + int sig; + struct sigcontext sc; + struct _fpstate fpstate; + unsigned long extramask[_NSIG_WORDS-1]; + char retcode[8]; +}; + +struct rt_sigframe +{ + char *pretcode; + int sig; + struct siginfo *pinfo; + void *puc; + struct siginfo info; + struct ucontext uc; + struct _fpstate fpstate; + char retcode[8]; +}; + +static int +restore_sigcontext(struct pt_regs *regs, struct sigcontext *sc, int *peax) +{ + unsigned int err = 0; + +#define COPY(x) err |= __get_user(regs->x, &sc->x) + +#define COPY_SEG(seg) \ + { unsigned short tmp; \ + err |= __get_user(tmp, &sc->seg); \ + regs->x##seg = tmp; } + +#define COPY_SEG_STRICT(seg) \ + { unsigned short tmp; \ + err |= __get_user(tmp, &sc->seg); \ + regs->x##seg = tmp|3; } + +#define GET_SEG(seg) \ + { unsigned short tmp; \ + err |= __get_user(tmp, &sc->seg); \ + loadsegment(seg,tmp); } + + GET_SEG(gs); + GET_SEG(fs); + COPY_SEG(es); + COPY_SEG(ds); + COPY(edi); + COPY(esi); + COPY(ebp); + COPY(esp); + COPY(ebx); + COPY(edx); + COPY(ecx); + COPY(eip); + COPY_SEG_STRICT(cs); + COPY_SEG_STRICT(ss); + + { + unsigned int tmpflags; + err |= __get_user(tmpflags, &sc->eflags); + regs->eflags = (regs->eflags & ~0x40DD5) | (tmpflags & 0x40DD5); + regs->orig_eax = -1; /* disable syscall checks */ + } + + { + struct _fpstate * buf; + err |= __get_user(buf, &sc->fpstate); + if (buf) { + if (verify_area(VERIFY_READ, buf, sizeof(*buf))) + goto badframe; + err |= restore_i387(buf); + } + } + + err |= __get_user(*peax, &sc->eax); + return err; + +badframe: + return 1; +} + +asmlinkage int sys_sigreturn(unsigned long __unused) +{ + struct pt_regs *regs = (struct pt_regs *) &__unused; + struct sigframe *frame = (struct sigframe *)(regs->esp - 8); + sigset_t set; + int eax; + + if (verify_area(VERIFY_READ, frame, sizeof(*frame))) + goto badframe; + if (__get_user(set.sig[0], &frame->sc.oldmask) + || (_NSIG_WORDS > 1 + && __copy_from_user(&set.sig[1], &frame->extramask, + sizeof(frame->extramask)))) + goto badframe; + + sigdelsetmask(&set, ~_BLOCKABLE); + spin_lock_irq(¤t->sigmask_lock); + current->blocked = set; + recalc_sigpending(current); + spin_unlock_irq(¤t->sigmask_lock); + + if (restore_sigcontext(regs, &frame->sc, &eax)) + goto badframe; + return eax; + +badframe: + force_sig(SIGSEGV, current); + return 0; +} + +asmlinkage int sys_rt_sigreturn(unsigned long __unused) +{ + struct pt_regs *regs = (struct pt_regs *) &__unused; + struct rt_sigframe *frame = (struct rt_sigframe *)(regs->esp - 4); + sigset_t set; + stack_t st; + int eax; + + if (verify_area(VERIFY_READ, frame, sizeof(*frame))) + goto badframe; + if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set))) + goto badframe; + + sigdelsetmask(&set, ~_BLOCKABLE); + spin_lock_irq(¤t->sigmask_lock); + current->blocked = set; + recalc_sigpending(current); + spin_unlock_irq(¤t->sigmask_lock); + + if (restore_sigcontext(regs, &frame->uc.uc_mcontext, &eax)) + goto badframe; + + if (__copy_from_user(&st, &frame->uc.uc_stack, sizeof(st))) + goto badframe; + /* It is more difficult to avoid calling this function than to + call it and ignore errors. */ + do_sigaltstack(&st, NULL, regs->esp); + + return eax; + +badframe: + force_sig(SIGSEGV, current); + return 0; +} + +/* + * Set up a signal frame. + */ + +static int +setup_sigcontext(struct sigcontext *sc, struct _fpstate *fpstate, + struct pt_regs *regs, unsigned long mask) +{ + int tmp, err = 0; + + tmp = 0; + __asm__("movl %%gs,%0" : "=r"(tmp): "0"(tmp)); + err |= __put_user(tmp, (unsigned int *)&sc->gs); + __asm__("movl %%fs,%0" : "=r"(tmp): "0"(tmp)); + err |= __put_user(tmp, (unsigned int *)&sc->fs); + + err |= __put_user(regs->xes, (unsigned int *)&sc->es); + err |= __put_user(regs->xds, (unsigned int *)&sc->ds); + err |= __put_user(regs->edi, &sc->edi); + err |= __put_user(regs->esi, &sc->esi); + err |= __put_user(regs->ebp, &sc->ebp); + err |= __put_user(regs->esp, &sc->esp); + err |= __put_user(regs->ebx, &sc->ebx); + err |= __put_user(regs->edx, &sc->edx); + err |= __put_user(regs->ecx, &sc->ecx); + err |= __put_user(regs->eax, &sc->eax); + err |= __put_user(current->thread.trap_no, &sc->trapno); + err |= __put_user(current->thread.error_code, &sc->err); + err |= __put_user(regs->eip, &sc->eip); + err |= __put_user(regs->xcs, (unsigned int *)&sc->cs); + err |= __put_user(regs->eflags, &sc->eflags); + err |= __put_user(regs->esp, &sc->esp_at_signal); + err |= __put_user(regs->xss, (unsigned int *)&sc->ss); + + tmp = save_i387(fpstate); + if (tmp < 0) + err = 1; + else + err |= __put_user(tmp ? fpstate : NULL, &sc->fpstate); + + /* non-iBCS2 extensions.. */ + err |= __put_user(mask, &sc->oldmask); + err |= __put_user(current->thread.cr2, &sc->cr2); + + return err; +} + +/* + * Determine which stack to use.. + */ +static inline void * +get_sigframe(struct k_sigaction *ka, struct pt_regs * regs, size_t frame_size) +{ + unsigned long esp; + + /* Default to using normal stack */ + esp = regs->esp; + + /* This is the X/Open sanctioned signal stack switching. */ + if (ka->sa.sa_flags & SA_ONSTACK) { + if (sas_ss_flags(esp) == 0) + esp = current->sas_ss_sp + current->sas_ss_size; + } + + /* This is the legacy signal stack switching. */ + else if ((regs->xss & 0xffff) != __USER_DS && + !(ka->sa.sa_flags & SA_RESTORER) && + ka->sa.sa_restorer) { + esp = (unsigned long) ka->sa.sa_restorer; + } + + return (void *)((esp - frame_size) & -8ul); +} + +static void setup_frame(int sig, struct k_sigaction *ka, + sigset_t *set, struct pt_regs * regs) +{ + struct sigframe *frame; + int err = 0; + + frame = get_sigframe(ka, regs, sizeof(*frame)); + + if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame))) + goto give_sigsegv; + + err |= __put_user((current->exec_domain + && current->exec_domain->signal_invmap + && sig < 32 + ? current->exec_domain->signal_invmap[sig] + : sig), + &frame->sig); + if (err) + goto give_sigsegv; + + err |= setup_sigcontext(&frame->sc, &frame->fpstate, regs, set->sig[0]); + if (err) + goto give_sigsegv; + + if (_NSIG_WORDS > 1) { + err |= __copy_to_user(frame->extramask, &set->sig[1], + sizeof(frame->extramask)); + } + if (err) + goto give_sigsegv; + + /* Set up to return from userspace. If provided, use a stub + already in userspace. */ + if (ka->sa.sa_flags & SA_RESTORER) { + err |= __put_user(ka->sa.sa_restorer, &frame->pretcode); + } else { + err |= __put_user(frame->retcode, &frame->pretcode); + /* This is popl %eax ; movl $,%eax ; int $0x80 */ + err |= __put_user(0xb858, (short *)(frame->retcode+0)); + err |= __put_user(__NR_sigreturn, (int *)(frame->retcode+2)); + err |= __put_user(0x80cd, (short *)(frame->retcode+6)); + } + + if (err) + goto give_sigsegv; + + /* Set up registers for signal handler */ + regs->esp = (unsigned long) frame; + regs->eip = (unsigned long) ka->sa.sa_handler; + + set_fs(USER_DS); + regs->xds = __USER_DS; + regs->xes = __USER_DS; + regs->xss = __USER_DS; + regs->xcs = __USER_CS; + regs->eflags &= ~TF_MASK; + +#if DEBUG_SIG + printk("SIG deliver (%s:%d): sp=%p pc=%p ra=%p\n", + current->comm, current->pid, frame, regs->eip, frame->pretcode); +#endif + + return; + +give_sigsegv: + if (sig == SIGSEGV) + ka->sa.sa_handler = SIG_DFL; + force_sig(SIGSEGV, current); +} + +static void setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, + sigset_t *set, struct pt_regs * regs) +{ + struct rt_sigframe *frame; + int err = 0; + + frame = get_sigframe(ka, regs, sizeof(*frame)); + + if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame))) + goto give_sigsegv; + + err |= __put_user((current->exec_domain + && current->exec_domain->signal_invmap + && sig < 32 + ? current->exec_domain->signal_invmap[sig] + : sig), + &frame->sig); + err |= __put_user(&frame->info, &frame->pinfo); + err |= __put_user(&frame->uc, &frame->puc); + err |= copy_siginfo_to_user(&frame->info, info); + if (err) + goto give_sigsegv; + + /* Create the ucontext. */ + err |= __put_user(0, &frame->uc.uc_flags); + err |= __put_user(0, &frame->uc.uc_link); + err |= __put_user(current->sas_ss_sp, &frame->uc.uc_stack.ss_sp); + err |= __put_user(sas_ss_flags(regs->esp), + &frame->uc.uc_stack.ss_flags); + err |= __put_user(current->sas_ss_size, &frame->uc.uc_stack.ss_size); + err |= setup_sigcontext(&frame->uc.uc_mcontext, &frame->fpstate, + regs, set->sig[0]); + err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)); + if (err) + goto give_sigsegv; + + /* Set up to return from userspace. If provided, use a stub + already in userspace. */ + if (ka->sa.sa_flags & SA_RESTORER) { + err |= __put_user(ka->sa.sa_restorer, &frame->pretcode); + } else { + err |= __put_user(frame->retcode, &frame->pretcode); + /* This is movl $,%eax ; int $0x80 */ + err |= __put_user(0xb8, (char *)(frame->retcode+0)); + err |= __put_user(__NR_rt_sigreturn, (int *)(frame->retcode+1)); + err |= __put_user(0x80cd, (short *)(frame->retcode+5)); + } + + if (err) + goto give_sigsegv; + + /* Set up registers for signal handler */ + regs->esp = (unsigned long) frame; + regs->eip = (unsigned long) ka->sa.sa_handler; + + set_fs(USER_DS); + regs->xds = __USER_DS; + regs->xes = __USER_DS; + regs->xss = __USER_DS; + regs->xcs = __USER_CS; + regs->eflags &= ~TF_MASK; + +#if DEBUG_SIG + printk("SIG deliver (%s:%d): sp=%p pc=%p ra=%p\n", + current->comm, current->pid, frame, regs->eip, frame->pretcode); +#endif + + return; + +give_sigsegv: + if (sig == SIGSEGV) + ka->sa.sa_handler = SIG_DFL; + force_sig(SIGSEGV, current); +} + +/* + * OK, we're invoking a handler + */ + +static void +handle_signal(unsigned long sig, struct k_sigaction *ka, + siginfo_t *info, sigset_t *oldset, struct pt_regs * regs) +{ + /* Are we from a system call? */ + if (regs->orig_eax >= 0) { + /* If so, check system call restarting.. */ + switch (regs->eax) { + case -ERESTARTNOHAND: + regs->eax = -EINTR; + break; + + case -ERESTARTSYS: + if (!(ka->sa.sa_flags & SA_RESTART)) { + regs->eax = -EINTR; + break; + } + /* fallthrough */ + case -ERESTARTNOINTR: + regs->eax = regs->orig_eax; + regs->eip -= 2; + } + } + + /* Set up the stack frame */ + if (ka->sa.sa_flags & SA_SIGINFO) + setup_rt_frame(sig, ka, info, oldset, regs); + else + setup_frame(sig, ka, oldset, regs); + + if (ka->sa.sa_flags & SA_ONESHOT) + ka->sa.sa_handler = SIG_DFL; + + if (!(ka->sa.sa_flags & SA_NODEFER)) { + spin_lock_irq(¤t->sigmask_lock); + sigorsets(¤t->blocked,¤t->blocked,&ka->sa.sa_mask); + sigaddset(¤t->blocked,sig); + recalc_sigpending(current); + spin_unlock_irq(¤t->sigmask_lock); + } +} + +/* + * Note that 'init' is a special process: it doesn't get signals it doesn't + * want to handle. Thus you cannot kill init even with a SIGKILL even by + * mistake. + */ +int do_signal(struct pt_regs *regs, sigset_t *oldset) +{ + siginfo_t info; + struct k_sigaction *ka; + + /* + * We want the common case to go fast, which + * is why we may in certain cases get here from + * kernel mode. Just return without doing anything + * if so. + */ + if ((regs->xcs & 2) != 2) + return 1; + + if (!oldset) + oldset = ¤t->blocked; + + for (;;) { + unsigned long signr; + + spin_lock_irq(¤t->sigmask_lock); + signr = dequeue_signal(¤t->blocked, &info); + spin_unlock_irq(¤t->sigmask_lock); + + if (!signr) + break; + + if ((current->ptrace & PT_PTRACED) && signr != SIGKILL) { + /* Let the debugger run. */ + current->exit_code = signr; + current->state = TASK_STOPPED; + notify_parent(current, SIGCHLD); + schedule(); + + /* We're back. Did the debugger cancel the sig? */ + if (!(signr = current->exit_code)) + continue; + current->exit_code = 0; + + /* The debugger continued. Ignore SIGSTOP. */ + if (signr == SIGSTOP) + continue; + + /* Update the siginfo structure. Is this good? */ + if (signr != info.si_signo) { + info.si_signo = signr; + info.si_errno = 0; + info.si_code = SI_USER; + info.si_pid = current->p_pptr->pid; + info.si_uid = current->p_pptr->uid; + } + + /* If the (new) signal is now blocked, requeue it. */ + if (sigismember(¤t->blocked, signr)) { + send_sig_info(signr, &info, current); + continue; + } + } + + ka = ¤t->sig->action[signr-1]; + if (ka->sa.sa_handler == SIG_IGN) { + if (signr != SIGCHLD) + continue; + /* Check for SIGCHLD: it's special. */ + while (sys_wait4(-1, NULL, WNOHANG, NULL) > 0) + /* nothing */; + continue; + } + + if (ka->sa.sa_handler == SIG_DFL) { + int exit_code = signr; + + /* Init gets no signals it doesn't want. */ + if (current->pid == 1) + continue; + + switch (signr) { + case SIGCONT: case SIGCHLD: case SIGWINCH: case SIGURG: + continue; + + case SIGTSTP: case SIGTTIN: case SIGTTOU: + if (is_orphaned_pgrp(current->pgrp)) + continue; + /* FALLTHRU */ + + case SIGSTOP: { + struct signal_struct *sig; + current->state = TASK_STOPPED; + current->exit_code = signr; + sig = current->p_pptr->sig; + if (sig && !(sig->action[SIGCHLD-1].sa.sa_flags & SA_NOCLDSTOP)) + notify_parent(current, SIGCHLD); + schedule(); + continue; + } + + case SIGQUIT: case SIGILL: case SIGTRAP: + case SIGABRT: case SIGFPE: case SIGSEGV: + case SIGBUS: case SIGSYS: case SIGXCPU: case SIGXFSZ: + if (do_coredump(signr, regs)) + exit_code |= 0x80; + /* FALLTHRU */ + + default: + sig_exit(signr, exit_code, &info); + /* NOTREACHED */ + } + } + + /* Reenable any watchpoints before delivering the + * signal to user space. The processor register will + * have been cleared if the watchpoint triggered + * inside the kernel. + */ + if ( current->thread.debugreg[7] != 0 ) + HYPERVISOR_set_debugreg(7, current->thread.debugreg[7]); + + /* Whee! Actually deliver the signal. */ + handle_signal(signr, ka, &info, oldset, regs); + return 1; + } + + /* Did we come from a system call? */ + if (regs->orig_eax >= 0) { + /* Restart the system call - no handlers present */ + if (regs->eax == -ERESTARTNOHAND || + regs->eax == -ERESTARTSYS || + regs->eax == -ERESTARTNOINTR) { + regs->eax = regs->orig_eax; + regs->eip -= 2; + } + } + return 0; +} diff --git a/xenolinux-2.4.24-sparse/arch/xeno/kernel/time.c b/xenolinux-2.4.24-sparse/arch/xeno/kernel/time.c new file mode 100644 index 0000000000..1944e63c1c --- /dev/null +++ b/xenolinux-2.4.24-sparse/arch/xeno/kernel/time.c @@ -0,0 +1,526 @@ +/* -*- Mode:C; c-basic-offset:4; tab-width:4 -*- + **************************************************************************** + * (C) 2002-2003 - Rolf Neugebauer - Intel Research Cambridge + * (C) 2002-2003 - Keir Fraser - University of Cambridge + **************************************************************************** + * + * File: arch/xeno/kernel/time.c + * Author: Rolf Neugebauer and Keir Fraser + * + * Description: Interface with Xen to get correct notion of time + */ + +/* + * linux/arch/i386/kernel/time.c + * + * Copyright (C) 1991, 1992, 1995 Linus Torvalds + * + * This file contains the PC-specific time handling details: + * reading the RTC at bootup, etc.. + * 1994-07-02 Alan Modra + * fixed set_rtc_mmss, fixed time.year for >= 2000, new mktime + * 1995-03-26 Markus Kuhn + * fixed 500 ms bug at call to set_rtc_mmss, fixed DS12887 + * precision CMOS clock update + * 1996-05-03 Ingo Molnar + * fixed time warps in do_[slow|fast]_gettimeoffset() + * 1997-09-10 Updated NTP code according to technical memorandum Jan '96 + * "A Kernel Model for Precision Timekeeping" by Dave Mills + * 1998-09-05 (Various) + * More robust do_fast_gettimeoffset() algorithm implemented + * (works with APM, Cyrix 6x86MX and Centaur C6), + * monotonic gettimeofday() with fast_get_timeoffset(), + * drift-proof precision TSC calibration on boot + * (C. Scott Ananian <cananian@alumni.princeton.edu>, Andrew D. + * Balsa <andrebalsa@altern.org>, Philip Gladstone <philip@raptor.com>; + * ported from 2.0.35 Jumbo-9 by Michael Krause <m.krause@tu-harburg.de>). + * 1998-12-16 Andrea Arcangeli + * Fixed Jumbo-9 code in 2.1.131: do_gettimeofday was missing 1 jiffy + * because was not accounting lost_ticks. + * 1998-12-24 Copyright (C) 1998 Andrea Arcangeli + * Fixed a xtime SMP race (we need the xtime_lock rw spinlock to + * serialize accesses to xtime/lost_ticks). + */ + +#include <asm/smp.h> +#include <asm/irq.h> +#include <asm/msr.h> +#include <asm/delay.h> +#include <asm/mpspec.h> +#include <asm/uaccess.h> +#include <asm/processor.h> + +#include <asm/div64.h> +#include <asm/hypervisor.h> +#include <asm/hypervisor-ifs/dom0_ops.h> + +#include <linux/mc146818rtc.h> +#include <linux/kernel.h> +#include <linux/interrupt.h> +#include <linux/time.h> +#include <linux/init.h> +#include <linux/smp.h> +#include <linux/irq.h> +#include <linux/sysctl.h> + +spinlock_t rtc_lock = SPIN_LOCK_UNLOCKED; +extern rwlock_t xtime_lock; +extern unsigned long wall_jiffies; + +unsigned long cpu_khz; /* get this from Xen, used elsewhere */ + +static unsigned int rdtsc_bitshift; +static u32 st_scale_f; /* convert ticks -> usecs */ +static u32 st_scale_i; /* convert ticks -> usecs */ + +/* These are peridically updated in shared_info, and then copied here. */ +static u32 shadow_tsc_stamp; +static s64 shadow_system_time; +static u32 shadow_time_version; +static struct timeval shadow_tv; + +/* + * We use this to ensure that gettimeofday() is monotonically increasing. We + * only break this guarantee if the wall clock jumps backwards "a long way". + */ +static struct timeval last_seen_tv = {0,0}; + +#ifdef CONFIG_XENO_PRIV +/* Periodically propagate synchronised time base to the RTC and to Xen. */ +static long last_update_to_rtc, last_update_to_xen; +#endif + +/* Periodically take synchronised time base from Xen, if we need it. */ +static long last_update_from_xen; + +static u64 processed_system_time; + +#define HANDLE_USEC_UNDERFLOW(_tv) \ + do { \ + while ( (_tv).tv_usec < 0 ) \ + { \ + (_tv).tv_usec += 1000000; \ + (_tv).tv_sec--; \ + } \ + } while ( 0 ) +#define HANDLE_USEC_OVERFLOW(_tv) \ + do { \ + while ( (_tv).tv_usec >= 1000000 ) \ + { \ + (_tv).tv_usec -= 1000000; \ + (_tv).tv_sec++; \ + } \ + } while ( 0 ) + + +/* Does this guest OS track Xen time, or set its wall clock independently? */ +static int independent_wallclock = 0; +static int __init __independent_wallclock(char *str) +{ + independent_wallclock = 1; + return 1; +} +__setup("independent_wallclock", __independent_wallclock); + + +#ifdef CONFIG_XENO_PRIV +/* + * In order to set the CMOS clock precisely, set_rtc_mmss has to be + * called 500 ms after the second nowtime has started, because when + * nowtime is written into the registers of the CMOS clock, it will + * jump to the next second precisely 500 ms later. Check the Motorola + * MC146818A or Dallas DS12887 data sheet for details. + * + * BUG: This routine does not handle hour overflow properly; it just + * sets the minutes. Usually you'll only notice that after reboot! + */ +static int set_rtc_mmss(unsigned long nowtime) +{ + int retval = 0; + int real_seconds, real_minutes, cmos_minutes; + unsigned char save_control, save_freq_select; + + /* gets recalled with irq locally disabled */ + spin_lock(&rtc_lock); + save_control = CMOS_READ(RTC_CONTROL); + CMOS_WRITE((save_control|RTC_SET), RTC_CONTROL); + + save_freq_select = CMOS_READ(RTC_FREQ_SELECT); + CMOS_WRITE((save_freq_select|RTC_DIV_RESET2), RTC_FREQ_SELECT); + + cmos_minutes = CMOS_READ(RTC_MINUTES); + if ( !(save_control & RTC_DM_BINARY) || RTC_ALWAYS_BCD ) + BCD_TO_BIN(cmos_minutes); + + /* + * since we're only adjusting minutes and seconds, don't interfere with + * hour overflow. This avoids messing with unknown time zones but requires + * your RTC not to be off by more than 15 minutes + */ + real_seconds = nowtime % 60; + real_minutes = nowtime / 60; + if ( ((abs(real_minutes - cmos_minutes) + 15)/30) & 1 ) + real_minutes += 30; /* correct for half hour time zone */ + real_minutes %= 60; + + if ( abs(real_minutes - cmos_minutes) < 30 ) + { + if ( !(save_control & RTC_DM_BINARY) || RTC_ALWAYS_BCD ) + { + BIN_TO_BCD(real_seconds); + BIN_TO_BCD(real_minutes); + } + CMOS_WRITE(real_seconds,RTC_SECONDS); + CMOS_WRITE(real_minutes,RTC_MINUTES); + } + else + { + printk(KERN_WARNING + "set_rtc_mmss: can't update from %d to %d\n", + cmos_minutes, real_minutes); + retval = -1; + } + + /* The following flags have to be released exactly in this order, + * otherwise the DS12887 (popular MC146818A clone with integrated + * battery and quartz) will not reset the oscillator and will not + * update precisely 500 ms later. You won't find this mentioned in + * the Dallas Semiconductor data sheets, but who believes data + * sheets anyway ... -- Markus Kuhn + */ + CMOS_WRITE(save_control, RTC_CONTROL); + CMOS_WRITE(save_freq_select, RTC_FREQ_SELECT); + spin_unlock(&rtc_lock); + + return retval; +} +#endif + + +/* Must be called with the xtime_lock held for writing. */ +static void get_time_values_from_xen(void) +{ + do { + shadow_time_version = HYPERVISOR_shared_info->time_version2; + rmb(); + shadow_tv.tv_sec = HYPERVISOR_shared_info->wc_sec; + shadow_tv.tv_usec = HYPERVISOR_shared_info->wc_usec; + shadow_tsc_stamp = HYPERVISOR_shared_info->tsc_timestamp; + shadow_system_time = HYPERVISOR_shared_info->system_time; + rmb(); + } + while ( shadow_time_version != HYPERVISOR_shared_info->time_version1 ); +} + +#define TIME_VALUES_UP_TO_DATE \ + (shadow_time_version == HYPERVISOR_shared_info->time_version2) + + +static inline unsigned long get_time_delta_usecs(void) +{ + s32 delta_tsc; + u32 low; + u64 delta, tsc; + + rdtscll(tsc); + low = (u32)(tsc >> rdtsc_bitshift); + delta_tsc = (s32)(low - shadow_tsc_stamp); + if ( unlikely(delta_tsc < 0) ) delta_tsc = 0; + delta = ((u64)delta_tsc * st_scale_f); + delta >>= 32; + delta += ((u64)delta_tsc * st_scale_i); + + return (unsigned long)delta; +} + + +void do_gettimeofday(struct timeval *tv) +{ + unsigned long flags, lost; + struct timeval _tv; + + again: + read_lock_irqsave(&xtime_lock, flags); + + _tv.tv_usec = get_time_delta_usecs(); + if ( (lost = (jiffies - wall_jiffies)) != 0 ) + _tv.tv_usec += lost * (1000000 / HZ); + _tv.tv_sec = xtime.tv_sec; + _tv.tv_usec += xtime.tv_usec; + + if ( unlikely(!TIME_VALUES_UP_TO_DATE) ) + { + /* + * We may have blocked for a long time, rendering our calculations + * invalid (e.g. the time delta may have overflowed). Detect that + * and recalculate with fresh values. + */ + read_unlock_irqrestore(&xtime_lock, flags); + write_lock_irqsave(&xtime_lock, flags); + get_time_values_from_xen(); + write_unlock_irqrestore(&xtime_lock, flags); + goto again; + } + + HANDLE_USEC_OVERFLOW(_tv); + + /* Ensure that time-of-day is monotonically increasing. */ + if ( (_tv.tv_sec < last_seen_tv.tv_sec) || + ((_tv.tv_sec == last_seen_tv.tv_sec) && + (_tv.tv_usec < last_seen_tv.tv_usec)) ) + _tv = last_seen_tv; + last_seen_tv = _tv; + + read_unlock_irqrestore(&xtime_lock, flags); + + *tv = _tv; +} + +void do_settimeofday(struct timeval *tv) +{ + struct timeval newtv; + + if ( !independent_wallclock && (start_info.dom_id != 0) ) + return; + + write_lock_irq(&xtime_lock); + + /* + * Ensure we don't get blocked for a long time so that our time delta + * overflows. If that were to happen then our shadow time values would + * be stale, so we can retry with fresh ones. + */ + again: + tv->tv_usec -= get_time_delta_usecs(); + if ( unlikely(!TIME_VALUES_UP_TO_DATE) ) + { + get_time_values_from_xen(); + goto again; + } + + HANDLE_USEC_UNDERFLOW(*tv); + + newtv = *tv; + + tv->tv_usec -= (jiffies - wall_jiffies) * (1000000 / HZ); + HANDLE_USEC_UNDERFLOW(*tv); + + xtime = *tv; + time_adjust = 0; /* stop active adjtime() */ + time_status |= STA_UNSYNC; + time_maxerror = NTP_PHASE_LIMIT; + time_esterror = NTP_PHASE_LIMIT; + + /* Reset all our running time counts. They make no sense now. */ + last_seen_tv.tv_sec = 0; + last_update_from_xen = 0; + +#ifdef CONFIG_XENO_PRIV + if ( start_info.dom_id == 0 ) + { + dom0_op_t op; + last_update_to_rtc = last_update_to_xen = 0; + op.cmd = DOM0_SETTIME; + op.u.settime.secs = newtv.tv_sec; + op.u.settime.usecs = newtv.tv_usec; + op.u.settime.system_time = shadow_system_time; + write_unlock_irq(&xtime_lock); + HYPERVISOR_dom0_op(&op); + } + else +#endif + { + write_unlock_irq(&xtime_lock); + } +} + +asmlinkage long sys_stime(int *tptr) +{ + int value; + struct timeval tv; + + if ( !capable(CAP_SYS_TIME) ) + return -EPERM; + + if ( get_user(value, tptr) ) + return -EFAULT; + + tv.tv_sec = value; + tv.tv_usec = 0; + + do_settimeofday(&tv); + + return 0; +} + +#define NS_PER_TICK (1000000000ULL/HZ) +static inline void do_timer_interrupt(int irq, void *dev_id, + struct pt_regs *regs) +{ + s64 delta; + long sec_diff; + + get_time_values_from_xen(); + + if ( (delta = (s64)(shadow_system_time - processed_system_time)) < 0 ) + { + printk("Timer ISR: Time went backwards: %lld\n", delta); + return; + } + + while ( delta >= NS_PER_TICK ) + { + do_timer(regs); + delta -= NS_PER_TICK; + processed_system_time += NS_PER_TICK; + } + + /* + * Take synchronised time from Xen once a minute if we're not + * synchronised ourselves, and we haven't chosen to keep an independent + * time base. + */ + if ( !independent_wallclock && + ((time_status & STA_UNSYNC) != 0) && + (xtime.tv_sec > (last_update_from_xen + 60)) ) + { + /* Adjust shadow timeval for jiffies that haven't updated xtime yet. */ + shadow_tv.tv_usec -= (jiffies - wall_jiffies) * (1000000/HZ); + HANDLE_USEC_UNDERFLOW(shadow_tv); + + /* + * Reset our running time counts if they are invalidated by a warp + * backwards of more than 500ms. + */ + sec_diff = xtime.tv_sec - shadow_tv.tv_sec; + if ( unlikely(abs(sec_diff) > 1) || + unlikely(((sec_diff * 1000000) + + xtime.tv_usec - shadow_tv.tv_usec) > 500000) ) + { + last_update_to_rtc = last_update_to_xen = 0; + last_seen_tv.tv_sec = 0; + } + + /* Update our unsynchronised xtime appropriately. */ + xtime = shadow_tv; + + last_update_from_xen = xtime.tv_sec; + } + +#ifdef CONFIG_XENO_PRIV + if ( (start_info.dom_id == 0) && ((time_status & STA_UNSYNC) == 0) ) + { + /* Send synchronised time to Xen approximately every minute. */ + if ( xtime.tv_sec > (last_update_to_xen + 60) ) + { + dom0_op_t op; + struct timeval tv = xtime; + + tv.tv_usec += (jiffies - wall_jiffies) * (1000000/HZ); + HANDLE_USEC_OVERFLOW(tv); + + op.cmd = DOM0_SETTIME; + op.u.settime.secs = tv.tv_sec; + op.u.settime.usecs = tv.tv_usec; + op.u.settime.system_time = shadow_system_time; + HYPERVISOR_dom0_op(&op); + + last_update_to_xen = xtime.tv_sec; + } + + /* + * If we have an externally synchronized Linux clock, then update CMOS + * clock accordingly every ~11 minutes. Set_rtc_mmss() has to be called + * as close as possible to 500 ms before the new second starts. + */ + if ( (xtime.tv_sec > (last_update_to_rtc + 660)) && + (xtime.tv_usec >= (500000 - ((unsigned) tick) / 2)) && + (xtime.tv_usec <= (500000 + ((unsigned) tick) / 2)) ) + { + if ( set_rtc_mmss(xtime.tv_sec) == 0 ) + last_update_to_rtc = xtime.tv_sec; + else + last_update_to_rtc = xtime.tv_sec - 600; + } + } +#endif +} + +static void timer_interrupt(int irq, void *dev_id, struct pt_regs *regs) +{ + write_lock(&xtime_lock); + while ( !TIME_VALUES_UP_TO_DATE ) + do_timer_interrupt(irq, NULL, regs); + write_unlock(&xtime_lock); +} + +static struct irqaction irq_timer = { + timer_interrupt, + SA_INTERRUPT, + 0, + "timer", + NULL, + NULL +}; + +void __init time_init(void) +{ + unsigned long long alarm; + u64 __cpu_khz, cpu_freq, scale, scale2; + + __cpu_khz = HYPERVISOR_shared_info->cpu_freq; + do_div(__cpu_khz, 1000); + cpu_khz = (u32)__cpu_khz; + printk("Xen reported: %lu.%03lu MHz processor.\n", + cpu_khz / 1000, cpu_khz % 1000); + + xtime.tv_sec = HYPERVISOR_shared_info->wc_sec; + xtime.tv_usec = HYPERVISOR_shared_info->wc_usec; + processed_system_time = shadow_system_time; + + rdtsc_bitshift = HYPERVISOR_shared_info->rdtsc_bitshift; + cpu_freq = HYPERVISOR_shared_info->cpu_freq; + + scale = 1000000LL << (32 + rdtsc_bitshift); + do_div(scale, (u32)cpu_freq); + + if ( (cpu_freq >> 32) != 0 ) + { + scale2 = 1000000LL << rdtsc_bitshift; + do_div(scale2, (u32)(cpu_freq>>32)); + scale += scale2; + } + + st_scale_f = scale & 0xffffffff; + st_scale_i = scale >> 32; + + get_time_values_from_xen(); + processed_system_time = shadow_system_time; + + setup_irq(TIMER_IRQ, &irq_timer); + + rdtscll(alarm); + + clear_bit(_EVENT_TIMER, &HYPERVISOR_shared_info->events); +} + + +/* + * /proc/sys/xeno: This really belongs in another file. It can stay here for + * now however. + */ +static ctl_table xeno_subtable[] = { + {1, "independent_wallclock", &independent_wallclock, + sizeof(independent_wallclock), 0644, NULL, proc_dointvec}, + {0} +}; +static ctl_table xeno_table[] = { + {123, "xeno", NULL, 0, 0555, xeno_subtable}, + {0} +}; +static int __init xeno_sysctl_init(void) +{ + (void)register_sysctl_table(xeno_table, 0); + return 0; +} +__initcall(xeno_sysctl_init); diff --git a/xenolinux-2.4.24-sparse/arch/xeno/kernel/traps.c b/xenolinux-2.4.24-sparse/arch/xeno/kernel/traps.c new file mode 100644 index 0000000000..cb45e1c278 --- /dev/null +++ b/xenolinux-2.4.24-sparse/arch/xeno/kernel/traps.c @@ -0,0 +1,620 @@ +/* + * linux/arch/i386/traps.c + * + * Copyright (C) 1991, 1992 Linus Torvalds + * + * Pentium III FXSR, SSE support + * Gareth Hughes <gareth@valinux.com>, May 2000 + */ + +/* + * 'Traps.c' handles hardware traps and faults after we have saved some + * state in 'asm.s'. + */ +#include <linux/config.h> +#include <linux/sched.h> +#include <linux/kernel.h> +#include <linux/string.h> +#include <linux/errno.h> +#include <linux/ptrace.h> +#include <linux/timer.h> +#include <linux/mm.h> +#include <linux/init.h> +#include <linux/delay.h> +#include <linux/spinlock.h> +#include <linux/interrupt.h> +#include <linux/highmem.h> + +#include <asm/system.h> +#include <asm/uaccess.h> +#include <asm/io.h> +#include <asm/atomic.h> +#include <asm/debugreg.h> +#include <asm/desc.h> +#include <asm/i387.h> + +#include <asm/smp.h> +#include <asm/pgalloc.h> + +#include <asm/hypervisor.h> + +#include <linux/irq.h> +#include <linux/module.h> + +asmlinkage int system_call(void); +asmlinkage void lcall7(void); +asmlinkage void lcall27(void); + +asmlinkage void divide_error(void); +asmlinkage void debug(void); +asmlinkage void int3(void); +asmlinkage void overflow(void); +asmlinkage void bounds(void); +asmlinkage void invalid_op(void); +asmlinkage void device_not_available(void); +asmlinkage void double_fault(void); +asmlinkage void coprocessor_segment_overrun(void); +asmlinkage void invalid_TSS(void); +asmlinkage void segment_not_present(void); +asmlinkage void stack_segment(void); +asmlinkage void general_protection(void); +asmlinkage void page_fault(void); +asmlinkage void coprocessor_error(void); +asmlinkage void simd_coprocessor_error(void); +asmlinkage void alignment_check(void); +asmlinkage void spurious_interrupt_bug(void); +asmlinkage void machine_check(void); + +int kstack_depth_to_print = 24; + + +/* + * If the address is either in the .text section of the + * kernel, or in the vmalloc'ed module regions, it *may* + * be the address of a calling routine + */ + +#ifdef CONFIG_MODULES + +extern struct module *module_list; +extern struct module kernel_module; + +static inline int kernel_text_address(unsigned long addr) +{ + int retval = 0; + struct module *mod; + + if (addr >= (unsigned long) &_stext && + addr <= (unsigned long) &_etext) + return 1; + + for (mod = module_list; mod != &kernel_module; mod = mod->next) { + /* mod_bound tests for addr being inside the vmalloc'ed + * module area. Of course it'd be better to test only + * for the .text subset... */ + if (mod_bound(addr, 0, mod)) { + retval = 1; + break; + } + } + + return retval; +} + +#else + +static inline int kernel_text_address(unsigned long addr) +{ + return (addr >= (unsigned long) &_stext && + addr <= (unsigned long) &_etext); +} + +#endif + +void show_trace(unsigned long * stack) +{ + int i; + unsigned long addr; + + if (!stack) + stack = (unsigned long*)&stack; + + printk("Call Trace: "); + i = 1; + while (((long) stack & (THREAD_SIZE-1)) != 0) { + addr = *stack++; + if (kernel_text_address(addr)) { + if (i && ((i % 6) == 0)) + printk("\n "); + printk("[<%08lx>] ", addr); + i++; + } + } + printk("\n"); +} + +void show_trace_task(struct task_struct *tsk) +{ + unsigned long esp = tsk->thread.esp; + + /* User space on another CPU? */ + if ((esp ^ (unsigned long)tsk) & (PAGE_MASK<<1)) + return; + show_trace((unsigned long *)esp); +} + +void show_stack(unsigned long * esp) +{ + unsigned long *stack; + int i; + + // debugging aid: "show_stack(NULL);" prints the + // back trace for this cpu. + + if(esp==NULL) + esp=(unsigned long*)&esp; + + stack = esp; + for(i=0; i < kstack_depth_to_print; i++) { + if (((long) stack & (THREAD_SIZE-1)) == 0) + break; + if (i && ((i % 8) == 0)) + printk("\n "); + printk("%08lx ", *stack++); + } + printk("\n"); + show_trace(esp); +} + +void show_registers(struct pt_regs *regs) +{ + int in_kernel = 1; + unsigned long esp; + unsigned short ss; + + esp = (unsigned long) (®s->esp); + ss = __KERNEL_DS; + if (regs->xcs & 2) { + in_kernel = 0; + esp = regs->esp; + ss = regs->xss & 0xffff; + } + printk(KERN_ALERT "CPU: %d\n", smp_processor_id() ); + printk(KERN_ALERT "EIP: %04x:[<%08lx>] %s\n", + 0xffff & regs->xcs, regs->eip, print_tainted()); + printk(KERN_ALERT "EFLAGS: %08lx\n",regs->eflags); + printk(KERN_ALERT "eax: %08lx ebx: %08lx ecx: %08lx edx: %08lx\n", + regs->eax, regs->ebx, regs->ecx, regs->edx); + printk(KERN_ALERT "esi: %08lx edi: %08lx ebp: %08lx esp: %08lx\n", + regs->esi, regs->edi, regs->ebp, esp); + printk(KERN_ALERT "ds: %04x es: %04x ss: %04x\n", + regs->xds & 0xffff, regs->xes & 0xffff, ss); + printk(KERN_ALERT "Process %s (pid: %d, stackpage=%08lx)", + current->comm, current->pid, 4096+(unsigned long)current); + /* + * When in-kernel, we also print out the stack and code at the + * time of the fault.. + */ + if (in_kernel) { + + printk(KERN_ALERT "\nStack: "); + show_stack((unsigned long*)esp); + +#if 0 + { + int i; + printk(KERN_ALERT "\nCode: "); + if(regs->eip < PAGE_OFFSET) + goto bad; + + for(i=0;i<20;i++) + { + unsigned char c; + if(__get_user(c, &((unsigned char*)regs->eip)[i])) { +bad: + printk(KERN_ALERT " Bad EIP value."); + break; + } + printk("%02x ", c); + } + } +#endif + } + printk(KERN_ALERT "\n"); +} + +spinlock_t die_lock = SPIN_LOCK_UNLOCKED; + +void die(const char * str, struct pt_regs * regs, long err) +{ + console_verbose(); + spin_lock_irq(&die_lock); + bust_spinlocks(1); + printk("%s: %04lx\n", str, err & 0xffff); + show_registers(regs); + bust_spinlocks(0); + spin_unlock_irq(&die_lock); + do_exit(SIGSEGV); +} + +static inline void die_if_kernel(const char * str, struct pt_regs * regs, long err) +{ + if (!(2 & regs->xcs)) + die(str, regs, err); +} + + +static void inline do_trap(int trapnr, int signr, char *str, + struct pt_regs * regs, long error_code, + siginfo_t *info) +{ + if (!(regs->xcs & 2)) + goto kernel_trap; + + /*trap_signal:*/ { + struct task_struct *tsk = current; + tsk->thread.error_code = error_code; + tsk->thread.trap_no = trapnr; + if (info) + force_sig_info(signr, info, tsk); + else + force_sig(signr, tsk); + return; + } + + kernel_trap: { + unsigned long fixup = search_exception_table(regs->eip); + if (fixup) + regs->eip = fixup; + else + die(str, regs, error_code); + return; + } +} + +#define DO_ERROR(trapnr, signr, str, name) \ +asmlinkage void do_##name(struct pt_regs * regs, long error_code) \ +{ \ + do_trap(trapnr, signr, str, regs, error_code, NULL); \ +} + +#define DO_ERROR_INFO(trapnr, signr, str, name, sicode, siaddr) \ +asmlinkage void do_##name(struct pt_regs * regs, long error_code) \ +{ \ + siginfo_t info; \ + info.si_signo = signr; \ + info.si_errno = 0; \ + info.si_code = sicode; \ + info.si_addr = (void *)siaddr; \ + do_trap(trapnr, signr, str, regs, error_code, &info); \ +} + +DO_ERROR_INFO( 0, SIGFPE, "divide error", divide_error, FPE_INTDIV, regs->eip) +DO_ERROR( 3, SIGTRAP, "int3", int3) +DO_ERROR( 4, SIGSEGV, "overflow", overflow) +DO_ERROR( 5, SIGSEGV, "bounds", bounds) +DO_ERROR_INFO( 6, SIGILL, "invalid operand", invalid_op, ILL_ILLOPN, regs->eip) +DO_ERROR( 7, SIGSEGV, "device not available", device_not_available) +DO_ERROR( 8, SIGSEGV, "double fault", double_fault) +DO_ERROR( 9, SIGFPE, "coprocessor segment overrun", coprocessor_segment_overrun) +DO_ERROR(10, SIGSEGV, "invalid TSS", invalid_TSS) +DO_ERROR(11, SIGBUS, "segment not present", segment_not_present) +DO_ERROR(12, SIGBUS, "stack segment", stack_segment) +DO_ERROR_INFO(17, SIGBUS, "alignment check", alignment_check, BUS_ADRALN, 0) +DO_ERROR(18, SIGBUS, "machine check", machine_check) + +asmlinkage void do_general_protection(struct pt_regs * regs, long error_code) +{ + /* + * If we trapped on an LDT access then ensure that the default_ldt is + * loaded, if nothing else. We load default_ldt lazily because LDT + * switching costs time and many applications don't need it. + */ + if ( unlikely((error_code & 6) == 4) ) + { + unsigned long ldt; + flush_page_update_queue(); /* ensure LDTR is up to date */ + __asm__ __volatile__ ( "sldt %0" : "=r" (ldt) ); + if ( likely(ldt == 0) ) + { + queue_set_ldt((unsigned long)&default_ldt[0], 5); + flush_page_update_queue(); + return; + } + } + + if (!(regs->xcs & 2)) + goto gp_in_kernel; + + current->thread.error_code = error_code; + current->thread.trap_no = 13; + force_sig(SIGSEGV, current); + return; + +gp_in_kernel: + { + unsigned long fixup; + fixup = search_exception_table(regs->eip); + if (fixup) { + regs->eip = fixup; + return; + } + die("general protection fault", regs, error_code); + } +} + + +asmlinkage void do_debug(struct pt_regs * regs, long error_code) +{ + unsigned int condition; + struct task_struct *tsk = current; + siginfo_t info; + + condition = HYPERVISOR_get_debugreg(6); + + /* Mask out spurious debug traps due to lazy DR7 setting */ + if (condition & (DR_TRAP0|DR_TRAP1|DR_TRAP2|DR_TRAP3)) { + if (!tsk->thread.debugreg[7]) + goto clear_dr7; + } + + /* Save debug status register where ptrace can see it */ + tsk->thread.debugreg[6] = condition; + + /* Mask out spurious TF errors due to lazy TF clearing */ + if (condition & DR_STEP) { + /* + * The TF error should be masked out only if the current + * process is not traced and if the TRAP flag has been set + * previously by a tracing process (condition detected by + * the PT_DTRACE flag); remember that the i386 TRAP flag + * can be modified by the process itself in user mode, + * allowing programs to debug themselves without the ptrace() + * interface. + */ + if ((tsk->ptrace & (PT_DTRACE|PT_PTRACED)) == PT_DTRACE) + goto clear_TF; + } + + /* Ok, finally something we can handle */ + tsk->thread.trap_no = 1; + tsk->thread.error_code = error_code; + info.si_signo = SIGTRAP; + info.si_errno = 0; + info.si_code = TRAP_BRKPT; + + /* If this is a kernel mode trap, save the user PC on entry to + * the kernel, that's what the debugger can make sense of. + */ + info.si_addr = ((regs->xcs & 2) == 0) ? (void *)tsk->thread.eip : + (void *)regs->eip; + force_sig_info(SIGTRAP, &info, tsk); + + /* Disable additional traps. They'll be re-enabled when + * the signal is delivered. + */ + clear_dr7: + HYPERVISOR_set_debugreg(7, 0); + return; + + clear_TF: + regs->eflags &= ~TF_MASK; + return; +} + + +/* + * Note that we play around with the 'TS' bit in an attempt to get + * the correct behaviour even in the presence of the asynchronous + * IRQ13 behaviour + */ +void math_error(void *eip) +{ + struct task_struct * task; + siginfo_t info; + unsigned short cwd, swd; + + /* + * Save the info for the exception handler and clear the error. + */ + task = current; + save_init_fpu(task); + task->thread.trap_no = 16; + task->thread.error_code = 0; + info.si_signo = SIGFPE; + info.si_errno = 0; + info.si_code = __SI_FAULT; + info.si_addr = eip; + /* + * (~cwd & swd) will mask out exceptions that are not set to unmasked + * status. 0x3f is the exception bits in these regs, 0x200 is the + * C1 reg you need in case of a stack fault, 0x040 is the stack + * fault bit. We should only be taking one exception at a time, + * so if this combination doesn't produce any single exception, + * then we have a bad program that isn't syncronizing its FPU usage + * and it will suffer the consequences since we won't be able to + * fully reproduce the context of the exception + */ + cwd = get_fpu_cwd(task); + swd = get_fpu_swd(task); + switch (((~cwd) & swd & 0x3f) | (swd & 0x240)) { + case 0x000: + default: + break; + case 0x001: /* Invalid Op */ + case 0x040: /* Stack Fault */ + case 0x240: /* Stack Fault | Direction */ + info.si_code = FPE_FLTINV; + break; + case 0x002: /* Denormalize */ + case 0x010: /* Underflow */ + info.si_code = FPE_FLTUND; + break; + case 0x004: /* Zero Divide */ + info.si_code = FPE_FLTDIV; + break; + case 0x008: /* Overflow */ + info.si_code = FPE_FLTOVF; + break; + case 0x020: /* Precision */ + info.si_code = FPE_FLTRES; + break; + } + force_sig_info(SIGFPE, &info, task); +} + +asmlinkage void do_coprocessor_error(struct pt_regs * regs, long error_code) +{ + ignore_irq13 = 1; + math_error((void *)regs->eip); +} + +void simd_math_error(void *eip) +{ + struct task_struct * task; + siginfo_t info; + unsigned short mxcsr; + + /* + * Save the info for the exception handler and clear the error. + */ + task = current; + save_init_fpu(task); + task->thread.trap_no = 19; + task->thread.error_code = 0; + info.si_signo = SIGFPE; + info.si_errno = 0; + info.si_code = __SI_FAULT; + info.si_addr = eip; + /* + * The SIMD FPU exceptions are handled a little differently, as there + * is only a single status/control register. Thus, to determine which + * unmasked exception was caught we must mask the exception mask bits + * at 0x1f80, and then use these to mask the exception bits at 0x3f. + */ + mxcsr = get_fpu_mxcsr(task); + switch (~((mxcsr & 0x1f80) >> 7) & (mxcsr & 0x3f)) { + case 0x000: + default: + break; + case 0x001: /* Invalid Op */ + info.si_code = FPE_FLTINV; + break; + case 0x002: /* Denormalize */ + case 0x010: /* Underflow */ + info.si_code = FPE_FLTUND; + break; + case 0x004: /* Zero Divide */ + info.si_code = FPE_FLTDIV; + break; + case 0x008: /* Overflow */ + info.si_code = FPE_FLTOVF; + break; + case 0x020: /* Precision */ + info.si_code = FPE_FLTRES; + break; + } + force_sig_info(SIGFPE, &info, task); +} + +asmlinkage void do_simd_coprocessor_error(struct pt_regs * regs, + long error_code) +{ + if (cpu_has_xmm) { + /* Handle SIMD FPU exceptions on PIII+ processors. */ + ignore_irq13 = 1; + simd_math_error((void *)regs->eip); + } else { + die_if_kernel("cache flush denied", regs, error_code); + current->thread.trap_no = 19; + current->thread.error_code = error_code; + force_sig(SIGSEGV, current); + } +} + +asmlinkage void do_spurious_interrupt_bug(struct pt_regs * regs, + long error_code) +{ +} + +/* + * 'math_state_restore()' saves the current math information in the + * old math state array, and gets the new ones from the current task + * + * Careful.. There are problems with IBM-designed IRQ13 behaviour. + * Don't touch unless you *really* know how it works. + */ +asmlinkage void math_state_restore(struct pt_regs regs) +{ + if (current->used_math) { + restore_fpu(current); + } else { + init_fpu(); + } + current->flags |= PF_USEDFPU; /* So we fnsave on switch_to() */ +} + + +#define _set_gate(gate_addr,type,dpl,addr) \ +do { \ + int __d0, __d1; \ + __asm__ __volatile__ ("movw %%dx,%%ax\n\t" \ + "movw %4,%%dx\n\t" \ + "movl %%eax,%0\n\t" \ + "movl %%edx,%1" \ + :"=m" (*((long *) (gate_addr))), \ + "=m" (*(1+(long *) (gate_addr))), "=&a" (__d0), "=&d" (__d1) \ + :"i" ((short) (0x8000+(dpl<<13)+(type<<8))), \ + "3" ((char *) (addr)),"2" (__KERNEL_CS << 16)); \ +} while (0) + +static void __init set_call_gate(void *a, void *addr) +{ + _set_gate(a,12,3,addr); +} + + +/* NB. All these are "trap gates" (i.e. events_mask isn't cleared). */ +static trap_info_t trap_table[] = { + { 0, 0, __KERNEL_CS, (unsigned long)divide_error }, + { 1, 0, __KERNEL_CS, (unsigned long)debug }, + { 3, 3, __KERNEL_CS, (unsigned long)int3 }, + { 4, 3, __KERNEL_CS, (unsigned long)overflow }, + { 5, 3, __KERNEL_CS, (unsigned long)bounds }, + { 6, 0, __KERNEL_CS, (unsigned long)invalid_op }, + { 7, 0, __KERNEL_CS, (unsigned long)device_not_available }, + { 8, 0, __KERNEL_CS, (unsigned long)double_fault }, + { 9, 0, __KERNEL_CS, (unsigned long)coprocessor_segment_overrun }, + { 10, 0, __KERNEL_CS, (unsigned long)invalid_TSS }, + { 11, 0, __KERNEL_CS, (unsigned long)segment_not_present }, + { 12, 0, __KERNEL_CS, (unsigned long)stack_segment }, + { 13, 0, __KERNEL_CS, (unsigned long)general_protection }, + { 14, 0, __KERNEL_CS, (unsigned long)page_fault }, + { 15, 0, __KERNEL_CS, (unsigned long)spurious_interrupt_bug }, + { 16, 0, __KERNEL_CS, (unsigned long)coprocessor_error }, + { 17, 0, __KERNEL_CS, (unsigned long)alignment_check }, + { 18, 0, __KERNEL_CS, (unsigned long)machine_check }, + { 19, 0, __KERNEL_CS, (unsigned long)simd_coprocessor_error }, + { SYSCALL_VECTOR, + 3, __KERNEL_CS, (unsigned long)system_call }, + { 0, 0, 0, 0 } +}; + + + +void __init trap_init(void) +{ + HYPERVISOR_set_trap_table(trap_table); + HYPERVISOR_set_fast_trap(SYSCALL_VECTOR); + + /* + * The default LDT is a single-entry callgate to lcall7 for iBCS and a + * callgate to lcall27 for Solaris/x86 binaries. + */ + clear_page(&default_ldt[0]); + set_call_gate(&default_ldt[0],lcall7); + set_call_gate(&default_ldt[4],lcall27); + __make_page_readonly(&default_ldt[0]); + + cpu_init(); +} |