aboutsummaryrefslogtreecommitdiffstats
path: root/old/xenolinux-2.4.16-sparse/arch/xeno/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'old/xenolinux-2.4.16-sparse/arch/xeno/kernel')
-rw-r--r--old/xenolinux-2.4.16-sparse/arch/xeno/kernel/Makefile15
-rw-r--r--old/xenolinux-2.4.16-sparse/arch/xeno/kernel/entry.S717
-rw-r--r--old/xenolinux-2.4.16-sparse/arch/xeno/kernel/head.S67
-rw-r--r--old/xenolinux-2.4.16-sparse/arch/xeno/kernel/hypervisor.c118
-rw-r--r--old/xenolinux-2.4.16-sparse/arch/xeno/kernel/i386_ksyms.c144
-rw-r--r--old/xenolinux-2.4.16-sparse/arch/xeno/kernel/i387.c518
-rw-r--r--old/xenolinux-2.4.16-sparse/arch/xeno/kernel/init_task.c33
-rw-r--r--old/xenolinux-2.4.16-sparse/arch/xeno/kernel/ioport.c19
-rw-r--r--old/xenolinux-2.4.16-sparse/arch/xeno/kernel/irq.c1129
-rw-r--r--old/xenolinux-2.4.16-sparse/arch/xeno/kernel/ldt.c26
-rw-r--r--old/xenolinux-2.4.16-sparse/arch/xeno/kernel/process.c454
-rw-r--r--old/xenolinux-2.4.16-sparse/arch/xeno/kernel/ptrace.c463
-rw-r--r--old/xenolinux-2.4.16-sparse/arch/xeno/kernel/semaphore.c292
-rw-r--r--old/xenolinux-2.4.16-sparse/arch/xeno/kernel/setup.c996
-rw-r--r--old/xenolinux-2.4.16-sparse/arch/xeno/kernel/signal.c720
-rw-r--r--old/xenolinux-2.4.16-sparse/arch/xeno/kernel/sys_i386.c256
-rw-r--r--old/xenolinux-2.4.16-sparse/arch/xeno/kernel/time.c350
-rw-r--r--old/xenolinux-2.4.16-sparse/arch/xeno/kernel/traps.c567
18 files changed, 6884 insertions, 0 deletions
diff --git a/old/xenolinux-2.4.16-sparse/arch/xeno/kernel/Makefile b/old/xenolinux-2.4.16-sparse/arch/xeno/kernel/Makefile
new file mode 100644
index 0000000000..ea830e82b6
--- /dev/null
+++ b/old/xenolinux-2.4.16-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/old/xenolinux-2.4.16-sparse/arch/xeno/kernel/entry.S b/old/xenolinux-2.4.16-sparse/arch/xeno/kernel/entry.S
new file mode 100644
index 0000000000..b888ae7747
--- /dev/null
+++ b/old/xenolinux-2.4.16-sparse/arch/xeno/kernel/entry.S
@@ -0,0 +1,717 @@
+/*
+ * 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
+IF_MASK = 0x00000200
+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(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
+
+#if defined(CONFIG_KDB)
+ENTRY(kdb_call)
+ pushl %eax # save orig EAX
+ SAVE_ALL
+ pushl %esp # struct pt_regs
+ pushl $0 # error_code
+ pushl $7 # KDB_REASON_ENTRY
+ call SYMBOL_NAME(kdb)
+ addl $12,%esp # remove args
+ RESTORE_ALL
+#endif
+
+/*
+ * 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
+ xorl %eax,%eax
+ movl %eax,4(%esi) # need_resched and signals atomic test
+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 %eax,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 %eax,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
+ xorl %eax,%eax
+ movb CS(%esp),%cl
+ test $2,%cl # slow return to ring 2 or 3
+ jne ret_syscall_tests
+safesti:btsl %eax,4(%esi) # reenable event callbacks
+scrit: /**** START OF CRITICAL REGION ****/
+ cmpl %eax,(%esi)
+ jne 14f # process more events if necessary...
+ RESTORE_ALL
+14: btrl %eax,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 # cmpl %eax,(%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 # btrl %eax,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: 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
+
+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
+
+#if defined(CONFIG_KDB)
+ENTRY(page_fault_mca)
+ pushl %ecx
+ pushl %edx
+ pushl %eax
+ movl $473,%ecx
+ rdmsr
+ andl $0xfffffffe,%eax /* Disable last branch recording */
+ wrmsr
+ popl %eax
+ popl %edx
+ popl %ecx
+ pushl $ SYMBOL_NAME(do_page_fault)
+ jmp error_code
+#endif
+
+# 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 */
+
+ .rept NR_syscalls-(.-sys_call_table)/4
+ .long SYMBOL_NAME(sys_ni_syscall)
+ .endr
diff --git a/old/xenolinux-2.4.16-sparse/arch/xeno/kernel/head.S b/old/xenolinux-2.4.16-sparse/arch/xeno/kernel/head.S
new file mode 100644
index 0000000000..86a82b13dc
--- /dev/null
+++ b/old/xenolinux-2.4.16-sparse/arch/xeno/kernel/head.S
@@ -0,0 +1,67 @@
+
+.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 SHARED_INFO 4
+#define MOD_START 12
+#define MOD_LEN 16
+
+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. */
+ /* We need to copy shared_info early, so that sti/cli work */
+ mov SHARED_INFO(%esi),%eax
+ mov %eax,SYMBOL_NAME(HYPERVISOR_shared_info)
+ 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(cpu0_pte_quicklist)
+
+.org 0x2400
+ENTRY(cpu0_pgd_quicklist)
+
+.org 0x2800
+ENTRY(stext)
+ENTRY(_stext)
diff --git a/old/xenolinux-2.4.16-sparse/arch/xeno/kernel/hypervisor.c b/old/xenolinux-2.4.16-sparse/arch/xeno/kernel/hypervisor.c
new file mode 100644
index 0000000000..c49087173f
--- /dev/null
+++ b/old/xenolinux-2.4.16-sparse/arch/xeno/kernel/hypervisor.c
@@ -0,0 +1,118 @@
+/******************************************************************************
+ * 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>
+
+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 = shared->events_enable;
+ shared->events_enable = 0;
+ 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(). */
+ shared->events_enable = flags;
+ barrier();
+ }
+ while ( shared->events );
+}
+
+
+
+/*
+ * Define interface to generic handling in irq.c
+ */
+
+static unsigned int startup_hypervisor_event(unsigned int irq)
+{
+ set_bit(irq, &event_mask);
+ return 0;
+}
+
+static void shutdown_hypervisor_event(unsigned int irq)
+{
+ clear_bit(irq, &event_mask);
+}
+
+static void enable_hypervisor_event(unsigned int irq)
+{
+ set_bit(irq, &event_mask);
+}
+
+static void disable_hypervisor_event(unsigned int irq)
+{
+ clear_bit(irq, &event_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);
+ }
+}
+
+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/old/xenolinux-2.4.16-sparse/arch/xeno/kernel/i386_ksyms.c b/old/xenolinux-2.4.16-sparse/arch/xeno/kernel/i386_ksyms.c
new file mode 100644
index 0000000000..a35ef1cc8a
--- /dev/null
+++ b/old/xenolinux-2.4.16-sparse/arch/xeno/kernel/i386_ksyms.c
@@ -0,0 +1,144 @@
+#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>
+#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;
+
+#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
+
+//extern unsigned long get_cmos_time(void);
+
+/* platform dependent support */
+EXPORT_SYMBOL(boot_cpu_data);
+EXPORT_SYMBOL(MCA_bus);
+EXPORT_SYMBOL(__verify_write);
+EXPORT_SYMBOL(dump_thread);
+EXPORT_SYMBOL(dump_fpu);
+EXPORT_SYMBOL(dump_extended_fpu);
+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(get_cmos_time);
+EXPORT_SYMBOL(apm_info);
+
+#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(__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(simple_strtol);
+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);
+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_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_DEBUG_BUGVERBOSE
+EXPORT_SYMBOL(do_BUG);
+#endif
diff --git a/old/xenolinux-2.4.16-sparse/arch/xeno/kernel/i387.c b/old/xenolinux-2.4.16-sparse/arch/xeno/kernel/i387.c
new file mode 100644
index 0000000000..9b8dfb0581
--- /dev/null
+++ b/old/xenolinux-2.4.16-sparse/arch/xeno/kernel/i387.c
@@ -0,0 +1,518 @@
+/*
+ * linux/arch/i386/kernel/i387.c
+ *
+ * Copyright (C) 1994 Linus Torvalds
+ *
+ * Pentium III FXSR, SSE support
+ * General FPU state handling cleanups
+ * Gareth Hughes <gareth@valinux.com>, May 2000
+ */
+
+#include <linux/config.h>
+#include <linux/sched.h>
+#include <asm/processor.h>
+#include <asm/i387.h>
+#include <asm/math_emu.h>
+#include <asm/sigcontext.h>
+#include <asm/user.h>
+#include <asm/ptrace.h>
+#include <asm/uaccess.h>
+
+#define HAVE_HWFP 1
+
+/*
+ * The _current_ task is using the FPU for the first time
+ * so initialize it and set the mxcsr to its default
+ * value at reset if we support XMM instructions and then
+ * remeber the current task has used the FPU.
+ */
+void init_fpu(void)
+{
+ __asm__("fninit");
+ if ( cpu_has_xmm )
+ load_mxcsr(0x1f80);
+
+ current->used_math = 1;
+}
+
+/*
+ * FPU lazy state save handling.
+ */
+
+static inline void __save_init_fpu( struct task_struct *tsk )
+{
+ if ( cpu_has_fxsr ) {
+ asm volatile( "fxsave %0 ; fnclex"
+ : "=m" (tsk->thread.i387.fxsave) );
+ } else {
+ asm volatile( "fnsave %0 ; fwait"
+ : "=m" (tsk->thread.i387.fsave) );
+ }
+ tsk->flags &= ~PF_USEDFPU;
+}
+
+void save_init_fpu( struct task_struct *tsk )
+{
+ __save_init_fpu(tsk);
+ stts();
+}
+
+void kernel_fpu_begin(void)
+{
+ struct task_struct *tsk = current;
+
+ if (tsk->flags & PF_USEDFPU) {
+ __save_init_fpu(tsk);
+ return;
+ }
+ clts();
+}
+
+void restore_fpu( struct task_struct *tsk )
+{
+ if ( cpu_has_fxsr ) {
+ asm volatile( "fxrstor %0"
+ : : "m" (tsk->thread.i387.fxsave) );
+ } else {
+ asm volatile( "frstor %0"
+ : : "m" (tsk->thread.i387.fsave) );
+ }
+}
+
+/*
+ * FPU tag word conversions.
+ */
+
+static inline unsigned short twd_i387_to_fxsr( unsigned short twd )
+{
+ unsigned int tmp; /* to avoid 16 bit prefixes in the code */
+
+ /* Transform each pair of bits into 01 (valid) or 00 (empty) */
+ tmp = ~twd;
+ tmp = (tmp | (tmp>>1)) & 0x5555; /* 0V0V0V0V0V0V0V0V */
+ /* and move the valid bits to the lower byte. */
+ tmp = (tmp | (tmp >> 1)) & 0x3333; /* 00VV00VV00VV00VV */
+ tmp = (tmp | (tmp >> 2)) & 0x0f0f; /* 0000VVVV0000VVVV */
+ tmp = (tmp | (tmp >> 4)) & 0x00ff; /* 00000000VVVVVVVV */
+ return tmp;
+}
+
+static inline unsigned long twd_fxsr_to_i387( struct i387_fxsave_struct *fxsave )
+{
+ struct _fpxreg *st = NULL;
+ unsigned long twd = (unsigned long) fxsave->twd;
+ unsigned long tag;
+ unsigned long ret = 0xffff0000;
+ int i;
+
+#define FPREG_ADDR(f, n) ((char *)&(f)->st_space + (n) * 16);
+
+ for ( i = 0 ; i < 8 ; i++ ) {
+ if ( twd & 0x1 ) {
+ st = (struct _fpxreg *) FPREG_ADDR( fxsave, i );
+
+ switch ( st->exponent & 0x7fff ) {
+ case 0x7fff:
+ tag = 2; /* Special */
+ break;
+ case 0x0000:
+ if ( !st->significand[0] &&
+ !st->significand[1] &&
+ !st->significand[2] &&
+ !st->significand[3] ) {
+ tag = 1; /* Zero */
+ } else {
+ tag = 2; /* Special */
+ }
+ break;
+ default:
+ if ( st->significand[3] & 0x8000 ) {
+ tag = 0; /* Valid */
+ } else {
+ tag = 2; /* Special */
+ }
+ break;
+ }
+ } else {
+ tag = 3; /* Empty */
+ }
+ ret |= (tag << (2 * i));
+ twd = twd >> 1;
+ }
+ return ret;
+}
+
+/*
+ * FPU state interaction.
+ */
+
+unsigned short get_fpu_cwd( struct task_struct *tsk )
+{
+ if ( cpu_has_fxsr ) {
+ return tsk->thread.i387.fxsave.cwd;
+ } else {
+ return (unsigned short)tsk->thread.i387.fsave.cwd;
+ }
+}
+
+unsigned short get_fpu_swd( struct task_struct *tsk )
+{
+ if ( cpu_has_fxsr ) {
+ return tsk->thread.i387.fxsave.swd;
+ } else {
+ return (unsigned short)tsk->thread.i387.fsave.swd;
+ }
+}
+
+unsigned short get_fpu_twd( struct task_struct *tsk )
+{
+ if ( cpu_has_fxsr ) {
+ return tsk->thread.i387.fxsave.twd;
+ } else {
+ return (unsigned short)tsk->thread.i387.fsave.twd;
+ }
+}
+
+unsigned short get_fpu_mxcsr( struct task_struct *tsk )
+{
+ if ( cpu_has_xmm ) {
+ return tsk->thread.i387.fxsave.mxcsr;
+ } else {
+ return 0x1f80;
+ }
+}
+
+void set_fpu_cwd( struct task_struct *tsk, unsigned short cwd )
+{
+ if ( cpu_has_fxsr ) {
+ tsk->thread.i387.fxsave.cwd = cwd;
+ } else {
+ tsk->thread.i387.fsave.cwd = ((long)cwd | 0xffff0000);
+ }
+}
+
+void set_fpu_swd( struct task_struct *tsk, unsigned short swd )
+{
+ if ( cpu_has_fxsr ) {
+ tsk->thread.i387.fxsave.swd = swd;
+ } else {
+ tsk->thread.i387.fsave.swd = ((long)swd | 0xffff0000);
+ }
+}
+
+void set_fpu_twd( struct task_struct *tsk, unsigned short twd )
+{
+ if ( cpu_has_fxsr ) {
+ tsk->thread.i387.fxsave.twd = twd_i387_to_fxsr(twd);
+ } else {
+ tsk->thread.i387.fsave.twd = ((long)twd | 0xffff0000);
+ }
+}
+
+void set_fpu_mxcsr( struct task_struct *tsk, unsigned short mxcsr )
+{
+ if ( cpu_has_xmm ) {
+ tsk->thread.i387.fxsave.mxcsr = (mxcsr & 0xffbf);
+ }
+}
+
+/*
+ * FXSR floating point environment conversions.
+ */
+
+static inline int convert_fxsr_to_user( struct _fpstate *buf,
+ struct i387_fxsave_struct *fxsave )
+{
+ unsigned long env[7];
+ struct _fpreg *to;
+ struct _fpxreg *from;
+ int i;
+
+ env[0] = (unsigned long)fxsave->cwd | 0xffff0000;
+ env[1] = (unsigned long)fxsave->swd | 0xffff0000;
+ env[2] = twd_fxsr_to_i387(fxsave);
+ env[3] = fxsave->fip;
+ env[4] = fxsave->fcs | ((unsigned long)fxsave->fop << 16);
+ env[5] = fxsave->foo;
+ env[6] = fxsave->fos;
+
+ if ( __copy_to_user( buf, env, 7 * sizeof(unsigned long) ) )
+ return 1;
+
+ to = &buf->_st[0];
+ from = (struct _fpxreg *) &fxsave->st_space[0];
+ for ( i = 0 ; i < 8 ; i++, to++, from++ ) {
+ if ( __copy_to_user( to, from, sizeof(*to) ) )
+ return 1;
+ }
+ return 0;
+}
+
+static inline int convert_fxsr_from_user( struct i387_fxsave_struct *fxsave,
+ struct _fpstate *buf )
+{
+ unsigned long env[7];
+ struct _fpxreg *to;
+ struct _fpreg *from;
+ int i;
+
+ if ( __copy_from_user( env, buf, 7 * sizeof(long) ) )
+ return 1;
+
+ fxsave->cwd = (unsigned short)(env[0] & 0xffff);
+ fxsave->swd = (unsigned short)(env[1] & 0xffff);
+ fxsave->twd = twd_i387_to_fxsr((unsigned short)(env[2] & 0xffff));
+ fxsave->fip = env[3];
+ fxsave->fop = (unsigned short)((env[4] & 0xffff0000) >> 16);
+ fxsave->fcs = (env[4] & 0xffff);
+ fxsave->foo = env[5];
+ fxsave->fos = env[6];
+
+ to = (struct _fpxreg *) &fxsave->st_space[0];
+ from = &buf->_st[0];
+ for ( i = 0 ; i < 8 ; i++, to++, from++ ) {
+ if ( __copy_from_user( to, from, sizeof(*from) ) )
+ return 1;
+ }
+ return 0;
+}
+
+/*
+ * Signal frame handlers.
+ */
+
+static inline int save_i387_fsave( struct _fpstate *buf )
+{
+ struct task_struct *tsk = current;
+
+ unlazy_fpu( tsk );
+ tsk->thread.i387.fsave.status = tsk->thread.i387.fsave.swd;
+ if ( __copy_to_user( buf, &tsk->thread.i387.fsave,
+ sizeof(struct i387_fsave_struct) ) )
+ return -1;
+ return 1;
+}
+
+static inline int save_i387_fxsave( struct _fpstate *buf )
+{
+ struct task_struct *tsk = current;
+ int err = 0;
+
+ unlazy_fpu( tsk );
+
+ if ( convert_fxsr_to_user( buf, &tsk->thread.i387.fxsave ) )
+ return -1;
+
+ err |= __put_user( tsk->thread.i387.fxsave.swd, &buf->status );
+ err |= __put_user( X86_FXSR_MAGIC, &buf->magic );
+ if ( err )
+ return -1;
+
+ if ( __copy_to_user( &buf->_fxsr_env[0], &tsk->thread.i387.fxsave,
+ sizeof(struct i387_fxsave_struct) ) )
+ return -1;
+ return 1;
+}
+
+int save_i387( struct _fpstate *buf )
+{
+ if ( !current->used_math )
+ return 0;
+
+ /* This will cause a "finit" to be triggered by the next
+ * attempted FPU operation by the 'current' process.
+ */
+ current->used_math = 0;
+
+ if ( HAVE_HWFP ) {
+ if ( cpu_has_fxsr ) {
+ return save_i387_fxsave( buf );
+ } else {
+ return save_i387_fsave( buf );
+ }
+ } else {
+ return save_i387_soft( &current->thread.i387.soft, buf );
+ }
+}
+
+static inline int restore_i387_fsave( struct _fpstate *buf )
+{
+ struct task_struct *tsk = current;
+ clear_fpu( tsk );
+ return __copy_from_user( &tsk->thread.i387.fsave, buf,
+ sizeof(struct i387_fsave_struct) );
+}
+
+static inline int restore_i387_fxsave( struct _fpstate *buf )
+{
+ struct task_struct *tsk = current;
+ clear_fpu( tsk );
+ if ( __copy_from_user( &tsk->thread.i387.fxsave, &buf->_fxsr_env[0],
+ sizeof(struct i387_fxsave_struct) ) )
+ return 1;
+ /* mxcsr bit 6 and 31-16 must be zero for security reasons */
+ tsk->thread.i387.fxsave.mxcsr &= 0xffbf;
+ return convert_fxsr_from_user( &tsk->thread.i387.fxsave, buf );
+}
+
+int restore_i387( struct _fpstate *buf )
+{
+ int err;
+
+ if ( HAVE_HWFP ) {
+ if ( cpu_has_fxsr ) {
+ err = restore_i387_fxsave( buf );
+ } else {
+ err = restore_i387_fsave( buf );
+ }
+ } else {
+ err = restore_i387_soft( &current->thread.i387.soft, buf );
+ }
+ current->used_math = 1;
+ return err;
+}
+
+/*
+ * ptrace request handlers.
+ */
+
+static inline int get_fpregs_fsave( struct user_i387_struct *buf,
+ struct task_struct *tsk )
+{
+ return __copy_to_user( buf, &tsk->thread.i387.fsave,
+ sizeof(struct user_i387_struct) );
+}
+
+static inline int get_fpregs_fxsave( struct user_i387_struct *buf,
+ struct task_struct *tsk )
+{
+ return convert_fxsr_to_user( (struct _fpstate *)buf,
+ &tsk->thread.i387.fxsave );
+}
+
+int get_fpregs( struct user_i387_struct *buf, struct task_struct *tsk )
+{
+ if ( HAVE_HWFP ) {
+ if ( cpu_has_fxsr ) {
+ return get_fpregs_fxsave( buf, tsk );
+ } else {
+ return get_fpregs_fsave( buf, tsk );
+ }
+ } else {
+ return save_i387_soft( &tsk->thread.i387.soft,
+ (struct _fpstate *)buf );
+ }
+}
+
+static inline int set_fpregs_fsave( struct task_struct *tsk,
+ struct user_i387_struct *buf )
+{
+ return __copy_from_user( &tsk->thread.i387.fsave, buf,
+ sizeof(struct user_i387_struct) );
+}
+
+static inline int set_fpregs_fxsave( struct task_struct *tsk,
+ struct user_i387_struct *buf )
+{
+ return convert_fxsr_from_user( &tsk->thread.i387.fxsave,
+ (struct _fpstate *)buf );
+}
+
+int set_fpregs( struct task_struct *tsk, struct user_i387_struct *buf )
+{
+ if ( HAVE_HWFP ) {
+ if ( cpu_has_fxsr ) {
+ return set_fpregs_fxsave( tsk, buf );
+ } else {
+ return set_fpregs_fsave( tsk, buf );
+ }
+ } else {
+ return restore_i387_soft( &tsk->thread.i387.soft,
+ (struct _fpstate *)buf );
+ }
+}
+
+int get_fpxregs( struct user_fxsr_struct *buf, struct task_struct *tsk )
+{
+ if ( cpu_has_fxsr ) {
+ if (__copy_to_user( (void *)buf, &tsk->thread.i387.fxsave,
+ sizeof(struct user_fxsr_struct) ))
+ return -EFAULT;
+ return 0;
+ } else {
+ return -EIO;
+ }
+}
+
+int set_fpxregs( struct task_struct *tsk, struct user_fxsr_struct *buf )
+{
+ if ( cpu_has_fxsr ) {
+ __copy_from_user( &tsk->thread.i387.fxsave, (void *)buf,
+ sizeof(struct user_fxsr_struct) );
+ /* mxcsr bit 6 and 31-16 must be zero for security reasons */
+ tsk->thread.i387.fxsave.mxcsr &= 0xffbf;
+ return 0;
+ } else {
+ return -EIO;
+ }
+}
+
+/*
+ * FPU state for core dumps.
+ */
+
+static inline void copy_fpu_fsave( struct task_struct *tsk,
+ struct user_i387_struct *fpu )
+{
+ memcpy( fpu, &tsk->thread.i387.fsave,
+ sizeof(struct user_i387_struct) );
+}
+
+static inline void copy_fpu_fxsave( struct task_struct *tsk,
+ struct user_i387_struct *fpu )
+{
+ unsigned short *to;
+ unsigned short *from;
+ int i;
+
+ memcpy( fpu, &tsk->thread.i387.fxsave, 7 * sizeof(long) );
+
+ to = (unsigned short *)&fpu->st_space[0];
+ from = (unsigned short *)&tsk->thread.i387.fxsave.st_space[0];
+ for ( i = 0 ; i < 8 ; i++, to += 5, from += 8 ) {
+ memcpy( to, from, 5 * sizeof(unsigned short) );
+ }
+}
+
+int dump_fpu( struct pt_regs *regs, struct user_i387_struct *fpu )
+{
+ int fpvalid;
+ struct task_struct *tsk = current;
+
+ fpvalid = tsk->used_math;
+ if ( fpvalid ) {
+ unlazy_fpu( tsk );
+ if ( cpu_has_fxsr ) {
+ copy_fpu_fxsave( tsk, fpu );
+ } else {
+ copy_fpu_fsave( tsk, fpu );
+ }
+ }
+
+ return fpvalid;
+}
+
+int dump_extended_fpu( struct pt_regs *regs, struct user_fxsr_struct *fpu )
+{
+ int fpvalid;
+ struct task_struct *tsk = current;
+
+ fpvalid = tsk->used_math && cpu_has_fxsr;
+ if ( fpvalid ) {
+ unlazy_fpu( tsk );
+ memcpy( fpu, &tsk->thread.i387.fxsave,
+ sizeof(struct user_fxsr_struct) );
+ }
+
+ return fpvalid;
+}
diff --git a/old/xenolinux-2.4.16-sparse/arch/xeno/kernel/init_task.c b/old/xenolinux-2.4.16-sparse/arch/xeno/kernel/init_task.c
new file mode 100644
index 0000000000..7779809ef2
--- /dev/null
+++ b/old/xenolinux-2.4.16-sparse/arch/xeno/kernel/init_task.c
@@ -0,0 +1,33 @@
+#include <linux/mm.h>
+#include <linux/sched.h>
+#include <linux/init.h>
+
+#include <asm/uaccess.h>
+#include <asm/pgtable.h>
+#include <asm/desc.h>
+
+static struct fs_struct init_fs = INIT_FS;
+static struct files_struct init_files = INIT_FILES;
+static struct signal_struct init_signals = INIT_SIGNALS;
+struct mm_struct init_mm = INIT_MM(init_mm);
+
+/*
+ * Initial task structure.
+ *
+ * We need to make sure that this is 8192-byte aligned due to the
+ * way process stacks are handled. This is done by having a special
+ * "init_task" linker map entry..
+ */
+union task_union init_task_union
+ __attribute__((__section__(".data.init_task"))) =
+ { INIT_TASK(init_task_union.task) };
+
+/*
+ * per-CPU TSS segments. Threads are completely 'soft' on Linux,
+ * no more per-task TSS's. The TSS size is kept cacheline-aligned
+ * so they are allowed to end up in the .data.cacheline_aligned
+ * section. Since TSS's are completely CPU-local, we want them
+ * on exact cacheline boundaries, to eliminate cacheline ping-pong.
+ */
+struct tss_struct init_tss[NR_CPUS] __cacheline_aligned = { [0 ... NR_CPUS-1] = INIT_TSS };
+
diff --git a/old/xenolinux-2.4.16-sparse/arch/xeno/kernel/ioport.c b/old/xenolinux-2.4.16-sparse/arch/xeno/kernel/ioport.c
new file mode 100644
index 0000000000..6bce25aec0
--- /dev/null
+++ b/old/xenolinux-2.4.16-sparse/arch/xeno/kernel/ioport.c
@@ -0,0 +1,19 @@
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/types.h>
+#include <linux/stddef.h>
+
+
+asmlinkage int sys_ioperm(unsigned long from, unsigned long num, int turn_on)
+{
+ /* No IO permission! */
+ return -EPERM;
+}
+
+
+asmlinkage int sys_iopl(unsigned long unused)
+{
+ /* The hypervisor won't allow it! */
+ return -EPERM;
+}
diff --git a/old/xenolinux-2.4.16-sparse/arch/xeno/kernel/irq.c b/old/xenolinux-2.4.16-sparse/arch/xeno/kernel/irq.c
new file mode 100644
index 0000000000..7c855904ae
--- /dev/null
+++ b/old/xenolinux-2.4.16-sparse/arch/xeno/kernel/irq.c
@@ -0,0 +1,1129 @@
+/*
+ * 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/kdb.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 get_irq_list(char *buf)
+{
+ int i, j;
+ struct irqaction * action;
+ char *p = buf;
+
+ p += sprintf(p, " ");
+ for (j=0; j<smp_num_cpus; j++)
+ p += sprintf(p, "CPU%d ",j);
+ *p++ = '\n';
+
+ for (i = 0 ; i < NR_IRQS ; i++) {
+ action = irq_desc[i].action;
+ if (!action)
+ continue;
+ p += sprintf(p, "%3d: ",i);
+#ifndef CONFIG_SMP
+ p += sprintf(p, "%10u ", kstat_irqs(i));
+#else
+ for (j = 0; j < smp_num_cpus; j++)
+ p += sprintf(p, "%10u ",
+ kstat.irqs[cpu_logical_map(j)][i]);
+#endif
+ p += sprintf(p, " %14s", irq_desc[i].handler->typename);
+ p += sprintf(p, " %s", action->name);
+
+ for (action=action->next; action; action = action->next)
+ p += sprintf(p, ", %s", action->name);
+ *p++ = '\n';
+ }
+ p += sprintf(p, "NMI: ");
+ for (j = 0; j < smp_num_cpus; j++)
+ p += sprintf(p, "%10u ",
+ nmi_count(cpu_logical_map(j)));
+ p += sprintf(p, "\n");
+#if CONFIG_X86_LOCAL_APIC
+ p += sprintf(p, "LOC: ");
+ for (j = 0; j < smp_num_cpus; j++)
+ p += sprintf(p, "%10u ",
+ apic_timer_irqs[cpu_logical_map(j)]);
+ p += sprintf(p, "\n");
+#endif
+ p += sprintf(p, "ERR: %10u\n", atomic_read(&irq_err_count));
+#ifdef CONFIG_X86_IO_APIC
+#ifdef APIC_MISMATCH_DEBUG
+ p += sprintf(p, "MIS: %10u\n", atomic_read(&irq_mis_count));
+#endif
+#endif
+ return p - buf;
+}
+
+
+/*
+ * 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)
+{
+#ifdef CONFIG_KDB
+ static int kdb_rate;
+ if (KDB_IS_RUNNING() && kdb_rate++ < 10)
+ kdb_printf("Warning: get_irqlock on cpu %d while kdb is running, may hang\n", smp_processor_id());
+#endif /* CONFIG_KDB */
+ 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;
+
+ 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);
+ 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/old/xenolinux-2.4.16-sparse/arch/xeno/kernel/ldt.c b/old/xenolinux-2.4.16-sparse/arch/xeno/kernel/ldt.c
new file mode 100644
index 0000000000..6c93943036
--- /dev/null
+++ b/old/xenolinux-2.4.16-sparse/arch/xeno/kernel/ldt.c
@@ -0,0 +1,26 @@
+/*
+ * 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>
+
+/*
+ * XXX KAF (28/7/02): This stuff is only used for DOS emulation, and is
+ * the default way of finding current TCB in linuxthreads. Supporting
+ * table update svia the hypervisor is feasible, but a hassle: for now,
+ * recompiling linuxthreads is the most sensible option.
+ *
+ * Oh, this may become an issue depending on what JVM we use for
+ * running the xeno-daemon.
+ */
+
+asmlinkage int sys_modify_ldt(int func, void *ptr, unsigned long bytecount)
+{
+ return -ENOSYS;
+}
diff --git a/old/xenolinux-2.4.16-sparse/arch/xeno/kernel/process.c b/old/xenolinux-2.4.16-sparse/arch/xeno/kernel/process.c
new file mode 100644
index 0000000000..87c52056f6
--- /dev/null
+++ b/old/xenolinux-2.4.16-sparse/arch/xeno/kernel/process.c
@@ -0,0 +1,454 @@
+/*
+ * 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 <linux/kdb.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 <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_do_sched_op(NULL);
+ 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(&regs->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();
+ vfree(ldt);
+ }
+}
+
+/*
+ * Create a kernel thread
+ */
+int 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)
+ printk(KERN_WARNING "ldt allocation failed\n");
+ else
+ memcpy(ldt, old_ldt, LDT_ENTRIES*LDT_ENTRY_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;
+
+ 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, &current->thread.i387);
+
+ 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 *prev = &prev_p->thread,
+ *next = &next_p->thread;
+
+ unlazy_fpu(prev_p);
+
+ HYPERVISOR_stack_and_ldt_switch(__KERNEL_DS, next->esp0, 0);
+
+ /*
+ * Save away %fs and %gs. No need to save %es and %ds, as
+ * those are always kernel segments while inside the kernel.
+ */
+ asm volatile("movl %%fs,%0":"=m" (*(int *)&prev->fs));
+ asm volatile("movl %%gs,%0":"=m" (*(int *)&prev->gs));
+
+ /*
+ * 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, &regs, 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, &regs, 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, &regs, 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, &regs);
+ 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/old/xenolinux-2.4.16-sparse/arch/xeno/kernel/ptrace.c b/old/xenolinux-2.4.16-sparse/arch/xeno/kernel/ptrace.c
new file mode 100644
index 0000000000..0fe86897fb
--- /dev/null
+++ b/old/xenolinux-2.4.16-sparse/arch/xeno/kernel/ptrace.c
@@ -0,0 +1,463 @@
+/* ptrace.c */
+/* By Ross Biro 1/23/92 */
+/*
+ * Pentium III FXSR, SSE support
+ * Gareth Hughes <gareth@valinux.com>, May 2000
+ */
+
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/smp.h>
+#include <linux/smp_lock.h>
+#include <linux/errno.h>
+#include <linux/ptrace.h>
+#include <linux/user.h>
+
+#include <asm/uaccess.h>
+#include <asm/pgtable.h>
+#include <asm/system.h>
+#include <asm/processor.h>
+#include <asm/i387.h>
+#include <asm/debugreg.h>
+
+/*
+ * does not yet catch signals sent when the child dies.
+ * in exit.c or in signal.c.
+ */
+
+/* determines which flags the user has access to. */
+/* 1 = access 0 = no access */
+#define FLAG_MASK 0x00044dd5
+
+/* set's the trap flag. */
+#define TRAP_FLAG 0x100
+
+/*
+ * Offset of eflags on child stack..
+ */
+#define EFL_OFFSET ((EFL-2)*4-sizeof(struct pt_regs))
+
+/*
+ * this routine will get a word off of the processes privileged stack.
+ * the offset is how far from the base addr as stored in the TSS.
+ * this routine assumes that all the privileged stacks are in our
+ * data space.
+ */
+static inline int get_stack_long(struct task_struct *task, int offset)
+{
+ unsigned char *stack;
+
+ stack = (unsigned char *)task->thread.esp0;
+ stack += offset;
+ return (*((int *)stack));
+}
+
+/*
+ * this routine will put a word on the processes privileged stack.
+ * the offset is how far from the base addr as stored in the TSS.
+ * this routine assumes that all the privileged stacks are in our
+ * data space.
+ */
+static inline int put_stack_long(struct task_struct *task, int offset,
+ unsigned long data)
+{
+ unsigned char * stack;
+
+ stack = (unsigned char *) task->thread.esp0;
+ stack += offset;
+ *(unsigned long *) stack = data;
+ return 0;
+}
+
+static int putreg(struct task_struct *child,
+ unsigned long regno, unsigned long value)
+{
+ switch (regno >> 2) {
+ case FS:
+ if (value && (value & 3) != 3)
+ return -EIO;
+ child->thread.fs = value;
+ return 0;
+ case GS:
+ if (value && (value & 3) != 3)
+ return -EIO;
+ child->thread.gs = value;
+ return 0;
+ case DS:
+ case ES:
+ if (value && (value & 3) != 3)
+ return -EIO;
+ value &= 0xffff;
+ break;
+ case SS:
+ case CS:
+ if ((value & 3) != 3)
+ return -EIO;
+ value &= 0xffff;
+ break;
+ case EFL:
+ value &= FLAG_MASK;
+ value |= get_stack_long(child, EFL_OFFSET) & ~FLAG_MASK;
+ break;
+ }
+ if (regno > GS*4)
+ regno -= 2*4;
+ put_stack_long(child, regno - sizeof(struct pt_regs), value);
+ return 0;
+}
+
+static unsigned long getreg(struct task_struct *child,
+ unsigned long regno)
+{
+ unsigned long retval = ~0UL;
+
+ switch (regno >> 2) {
+ case FS:
+ retval = child->thread.fs;
+ break;
+ case GS:
+ retval = child->thread.gs;
+ break;
+ case DS:
+ case ES:
+ case SS:
+ case CS:
+ retval = 0xffff;
+ /* fall through */
+ default:
+ if (regno > GS*4)
+ regno -= 2*4;
+ regno = regno - sizeof(struct pt_regs);
+ retval &= get_stack_long(child, regno);
+ }
+ return retval;
+}
+
+/*
+ * Called by kernel/ptrace.c when detaching..
+ *
+ * Make sure the single step bit is not set.
+ */
+void ptrace_disable(struct task_struct *child)
+{
+ long tmp;
+
+ tmp = get_stack_long(child, EFL_OFFSET) & ~TRAP_FLAG;
+ put_stack_long(child, EFL_OFFSET, tmp);
+}
+
+asmlinkage int sys_ptrace(long request, long pid, long addr, long data)
+{
+ struct task_struct *child;
+ struct user * dummy = NULL;
+ int i, ret;
+
+ lock_kernel();
+ ret = -EPERM;
+ if (request == PTRACE_TRACEME) {
+ /* are we already being traced? */
+ if (current->ptrace & PT_PTRACED)
+ goto out;
+ /* set the ptrace bit in the process flags. */
+ current->ptrace |= PT_PTRACED;
+ ret = 0;
+ goto out;
+ }
+ ret = -ESRCH;
+ read_lock(&tasklist_lock);
+ child = find_task_by_pid(pid);
+ if (child)
+ get_task_struct(child);
+ read_unlock(&tasklist_lock);
+ if (!child)
+ goto out;
+
+ ret = -EPERM;
+ if (pid == 1) /* you may not mess with init */
+ goto out_tsk;
+
+ if (request == PTRACE_ATTACH) {
+ ret = ptrace_attach(child);
+ goto out_tsk;
+ }
+
+ ret = ptrace_check_attach(child, request == PTRACE_KILL);
+ if (ret < 0)
+ goto out_tsk;
+
+ switch (request) {
+ /* when I and D space are separate, these will need to be fixed. */
+ case PTRACE_PEEKTEXT: /* read word at location addr. */
+ case PTRACE_PEEKDATA: {
+ unsigned long tmp;
+ int copied;
+
+ copied = access_process_vm(child, addr, &tmp, sizeof(tmp), 0);
+ ret = -EIO;
+ if (copied != sizeof(tmp))
+ break;
+ ret = put_user(tmp,(unsigned long *) data);
+ break;
+ }
+
+ /* read the word at location addr in the USER area. */
+ case PTRACE_PEEKUSR: {
+ unsigned long tmp;
+
+ ret = -EIO;
+ if ((addr & 3) || addr < 0 ||
+ addr > sizeof(struct user) - 3)
+ break;
+
+ tmp = 0; /* Default return condition */
+ if(addr < FRAME_SIZE*sizeof(long))
+ tmp = getreg(child, addr);
+ if(addr >= (long) &dummy->u_debugreg[0] &&
+ addr <= (long) &dummy->u_debugreg[7]){
+ addr -= (long) &dummy->u_debugreg[0];
+ addr = addr >> 2;
+ tmp = child->thread.debugreg[addr];
+ }
+ ret = put_user(tmp,(unsigned long *) data);
+ break;
+ }
+
+ /* when I and D space are separate, this will have to be fixed. */
+ case PTRACE_POKETEXT: /* write the word at location addr. */
+ case PTRACE_POKEDATA:
+ ret = 0;
+ if (access_process_vm(child, addr, &data, sizeof(data), 1) == sizeof(data))
+ break;
+ ret = -EIO;
+ break;
+
+ case PTRACE_POKEUSR: /* write the word at location addr in the USER area */
+ ret = -EIO;
+ if ((addr & 3) || addr < 0 ||
+ addr > sizeof(struct user) - 3)
+ break;
+
+ if (addr < FRAME_SIZE*sizeof(long)) {
+ ret = putreg(child, addr, data);
+ break;
+ }
+ /* We need to be very careful here. We implicitly
+ want to modify a portion of the task_struct, and we
+ have to be selective about what portions we allow someone
+ to modify. */
+
+ ret = -EIO;
+ if(addr >= (long) &dummy->u_debugreg[0] &&
+ addr <= (long) &dummy->u_debugreg[7]){
+
+ if(addr == (long) &dummy->u_debugreg[4]) break;
+ if(addr == (long) &dummy->u_debugreg[5]) break;
+ if(addr < (long) &dummy->u_debugreg[4] &&
+ ((unsigned long) data) >= TASK_SIZE-3) break;
+
+ if(addr == (long) &dummy->u_debugreg[7]) {
+ data &= ~DR_CONTROL_RESERVED;
+ for(i=0; i<4; i++)
+ if ((0x5f54 >> ((data >> (16 + 4*i)) & 0xf)) & 1)
+ goto out_tsk;
+ }
+
+ addr -= (long) &dummy->u_debugreg;
+ addr = addr >> 2;
+ child->thread.debugreg[addr] = data;
+ ret = 0;
+ }
+ break;
+
+ case PTRACE_SYSCALL: /* continue and stop at next (return from) syscall */
+ case PTRACE_CONT: { /* restart after signal. */
+ long tmp;
+
+ ret = -EIO;
+ if ((unsigned long) data > _NSIG)
+ break;
+ if (request == PTRACE_SYSCALL)
+ child->ptrace |= PT_TRACESYS;
+ else
+ child->ptrace &= ~PT_TRACESYS;
+ child->exit_code = data;
+ /* make sure the single step bit is not set. */
+ tmp = get_stack_long(child, EFL_OFFSET) & ~TRAP_FLAG;
+ put_stack_long(child, EFL_OFFSET,tmp);
+ wake_up_process(child);
+ ret = 0;
+ break;
+ }
+
+/*
+ * make the child exit. Best I can do is send it a sigkill.
+ * perhaps it should be put in the status that it wants to
+ * exit.
+ */
+ case PTRACE_KILL: {
+ long tmp;
+
+ ret = 0;
+ if (child->state == TASK_ZOMBIE) /* already dead */
+ break;
+ child->exit_code = SIGKILL;
+ /* make sure the single step bit is not set. */
+ tmp = get_stack_long(child, EFL_OFFSET) & ~TRAP_FLAG;
+ put_stack_long(child, EFL_OFFSET, tmp);
+ wake_up_process(child);
+ break;
+ }
+
+ case PTRACE_SINGLESTEP: { /* set the trap flag. */
+ long tmp;
+
+ ret = -EIO;
+ if ((unsigned long) data > _NSIG)
+ break;
+ child->ptrace &= ~PT_TRACESYS;
+ if ((child->ptrace & PT_DTRACE) == 0) {
+ /* Spurious delayed TF traps may occur */
+ child->ptrace |= PT_DTRACE;
+ }
+ tmp = get_stack_long(child, EFL_OFFSET) | TRAP_FLAG;
+ put_stack_long(child, EFL_OFFSET, tmp);
+ child->exit_code = data;
+ /* give it a chance to run. */
+ wake_up_process(child);
+ ret = 0;
+ break;
+ }
+
+ case PTRACE_DETACH:
+ /* detach a process that was attached. */
+ ret = ptrace_detach(child, data);
+ break;
+
+ case PTRACE_GETREGS: { /* Get all gp regs from the child. */
+ if (!access_ok(VERIFY_WRITE, (unsigned *)data, FRAME_SIZE*sizeof(long))) {
+ ret = -EIO;
+ break;
+ }
+ for ( i = 0; i < FRAME_SIZE*sizeof(long); i += sizeof(long) ) {
+ __put_user(getreg(child, i),(unsigned long *) data);
+ data += sizeof(long);
+ }
+ ret = 0;
+ break;
+ }
+
+ case PTRACE_SETREGS: { /* Set all gp regs in the child. */
+ unsigned long tmp;
+ if (!access_ok(VERIFY_READ, (unsigned *)data, FRAME_SIZE*sizeof(long))) {
+ ret = -EIO;
+ break;
+ }
+ for ( i = 0; i < FRAME_SIZE*sizeof(long); i += sizeof(long) ) {
+ __get_user(tmp, (unsigned long *) data);
+ putreg(child, i, tmp);
+ data += sizeof(long);
+ }
+ ret = 0;
+ break;
+ }
+
+ case PTRACE_GETFPREGS: { /* Get the child FPU state. */
+ if (!access_ok(VERIFY_WRITE, (unsigned *)data,
+ sizeof(struct user_i387_struct))) {
+ ret = -EIO;
+ break;
+ }
+ ret = 0;
+ if ( !child->used_math ) {
+ /* Simulate an empty FPU. */
+ set_fpu_cwd(child, 0x037f);
+ set_fpu_swd(child, 0x0000);
+ set_fpu_twd(child, 0xffff);
+ }
+ get_fpregs((struct user_i387_struct *)data, child);
+ break;
+ }
+
+ case PTRACE_SETFPREGS: { /* Set the child FPU state. */
+ if (!access_ok(VERIFY_READ, (unsigned *)data,
+ sizeof(struct user_i387_struct))) {
+ ret = -EIO;
+ break;
+ }
+ child->used_math = 1;
+ set_fpregs(child, (struct user_i387_struct *)data);
+ ret = 0;
+ break;
+ }
+
+ case PTRACE_GETFPXREGS: { /* Get the child extended FPU state. */
+ if (!access_ok(VERIFY_WRITE, (unsigned *)data,
+ sizeof(struct user_fxsr_struct))) {
+ ret = -EIO;
+ break;
+ }
+ if ( !child->used_math ) {
+ /* Simulate an empty FPU. */
+ set_fpu_cwd(child, 0x037f);
+ set_fpu_swd(child, 0x0000);
+ set_fpu_twd(child, 0xffff);
+ set_fpu_mxcsr(child, 0x1f80);
+ }
+ ret = get_fpxregs((struct user_fxsr_struct *)data, child);
+ break;
+ }
+
+ case PTRACE_SETFPXREGS: { /* Set the child extended FPU state. */
+ if (!access_ok(VERIFY_READ, (unsigned *)data,
+ sizeof(struct user_fxsr_struct))) {
+ ret = -EIO;
+ break;
+ }
+ child->used_math = 1;
+ ret = set_fpxregs(child, (struct user_fxsr_struct *)data);
+ break;
+ }
+
+ case PTRACE_SETOPTIONS: {
+ if (data & PTRACE_O_TRACESYSGOOD)
+ child->ptrace |= PT_TRACESYSGOOD;
+ else
+ child->ptrace &= ~PT_TRACESYSGOOD;
+ ret = 0;
+ break;
+ }
+
+ default:
+ ret = -EIO;
+ break;
+ }
+out_tsk:
+ free_task_struct(child);
+out:
+ unlock_kernel();
+ return ret;
+}
+
+asmlinkage void syscall_trace(void)
+{
+ if ((current->ptrace & (PT_PTRACED|PT_TRACESYS)) !=
+ (PT_PTRACED|PT_TRACESYS))
+ return;
+ /* the 0x80 provides a way for the tracing parent to distinguish
+ between a syscall stop and SIGTRAP delivery */
+ current->exit_code = SIGTRAP | ((current->ptrace & PT_TRACESYSGOOD)
+ ? 0x80 : 0);
+ current->state = TASK_STOPPED;
+ notify_parent(current, SIGCHLD);
+ schedule();
+ /*
+ * this isn't the same as continuing with a signal, but it will do
+ * for normal use. strace only continues with a signal if the
+ * stopping signal is not SIGTRAP. -brl
+ */
+ if (current->exit_code) {
+ send_sig(current->exit_code, current, 1);
+ current->exit_code = 0;
+ }
+}
diff --git a/old/xenolinux-2.4.16-sparse/arch/xeno/kernel/semaphore.c b/old/xenolinux-2.4.16-sparse/arch/xeno/kernel/semaphore.c
new file mode 100644
index 0000000000..08ff686f1e
--- /dev/null
+++ b/old/xenolinux-2.4.16-sparse/arch/xeno/kernel/semaphore.c
@@ -0,0 +1,292 @@
+/*
+ * i386 semaphore implementation.
+ *
+ * (C) Copyright 1999 Linus Torvalds
+ *
+ * Portions Copyright 1999 Red Hat, Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * rw semaphores implemented November 1999 by Benjamin LaHaise <bcrl@redhat.com>
+ */
+#include <linux/config.h>
+#include <linux/sched.h>
+#include <asm/semaphore.h>
+
+/*
+ * Semaphores are implemented using a two-way counter:
+ * The "count" variable is decremented for each process
+ * that tries to acquire the semaphore, while the "sleeping"
+ * variable is a count of such acquires.
+ *
+ * Notably, the inline "up()" and "down()" functions can
+ * efficiently test if they need to do any extra work (up
+ * needs to do something only if count was negative before
+ * the increment operation.
+ *
+ * "sleeping" and the contention routine ordering is
+ * protected by the semaphore spinlock.
+ *
+ * Note that these functions are only called when there is
+ * contention on the lock, and as such all this is the
+ * "non-critical" part of the whole semaphore business. The
+ * critical part is the inline stuff in <asm/semaphore.h>
+ * where we want to avoid any extra jumps and calls.
+ */
+
+/*
+ * Logic:
+ * - only on a boundary condition do we need to care. When we go
+ * from a negative count to a non-negative, we wake people up.
+ * - when we go from a non-negative count to a negative do we
+ * (a) synchronize with the "sleeper" count and (b) make sure
+ * that we're on the wakeup list before we synchronize so that
+ * we cannot lose wakeup events.
+ */
+
+void __up(struct semaphore *sem)
+{
+ wake_up(&sem->wait);
+}
+
+static spinlock_t semaphore_lock = SPIN_LOCK_UNLOCKED;
+
+void __down(struct semaphore * sem)
+{
+ struct task_struct *tsk = current;
+ DECLARE_WAITQUEUE(wait, tsk);
+ tsk->state = TASK_UNINTERRUPTIBLE;
+ add_wait_queue_exclusive(&sem->wait, &wait);
+
+ spin_lock_irq(&semaphore_lock);
+ sem->sleepers++;
+ for (;;) {
+ int sleepers = sem->sleepers;
+
+ /*
+ * Add "everybody else" into it. They aren't
+ * playing, because we own the spinlock.
+ */
+ if (!atomic_add_negative(sleepers - 1, &sem->count)) {
+ sem->sleepers = 0;
+ break;
+ }
+ sem->sleepers = 1; /* us - see -1 above */
+ spin_unlock_irq(&semaphore_lock);
+
+ schedule();
+ tsk->state = TASK_UNINTERRUPTIBLE;
+ spin_lock_irq(&semaphore_lock);
+ }
+ spin_unlock_irq(&semaphore_lock);
+ remove_wait_queue(&sem->wait, &wait);
+ tsk->state = TASK_RUNNING;
+ wake_up(&sem->wait);
+}
+
+int __down_interruptible(struct semaphore * sem)
+{
+ int retval = 0;
+ struct task_struct *tsk = current;
+ DECLARE_WAITQUEUE(wait, tsk);
+ tsk->state = TASK_INTERRUPTIBLE;
+ add_wait_queue_exclusive(&sem->wait, &wait);
+
+ spin_lock_irq(&semaphore_lock);
+ sem->sleepers ++;
+ for (;;) {
+ int sleepers = sem->sleepers;
+
+ /*
+ * With signals pending, this turns into
+ * the trylock failure case - we won't be
+ * sleeping, and we* can't get the lock as
+ * it has contention. Just correct the count
+ * and exit.
+ */
+ if (signal_pending(current)) {
+ retval = -EINTR;
+ sem->sleepers = 0;
+ atomic_add(sleepers, &sem->count);
+ break;
+ }
+
+ /*
+ * Add "everybody else" into it. They aren't
+ * playing, because we own the spinlock. The
+ * "-1" is because we're still hoping to get
+ * the lock.
+ */
+ if (!atomic_add_negative(sleepers - 1, &sem->count)) {
+ sem->sleepers = 0;
+ break;
+ }
+ sem->sleepers = 1; /* us - see -1 above */
+ spin_unlock_irq(&semaphore_lock);
+
+ schedule();
+ tsk->state = TASK_INTERRUPTIBLE;
+ spin_lock_irq(&semaphore_lock);
+ }
+ spin_unlock_irq(&semaphore_lock);
+ tsk->state = TASK_RUNNING;
+ remove_wait_queue(&sem->wait, &wait);
+ wake_up(&sem->wait);
+ return retval;
+}
+
+/*
+ * Trylock failed - make sure we correct for
+ * having decremented the count.
+ *
+ * We could have done the trylock with a
+ * single "cmpxchg" without failure cases,
+ * but then it wouldn't work on a 386.
+ */
+int __down_trylock(struct semaphore * sem)
+{
+ int sleepers;
+ unsigned long flags;
+
+ spin_lock_irqsave(&semaphore_lock, flags);
+ sleepers = sem->sleepers + 1;
+ sem->sleepers = 0;
+
+ /*
+ * Add "everybody else" and us into it. They aren't
+ * playing, because we own the spinlock.
+ */
+ if (!atomic_add_negative(sleepers, &sem->count))
+ wake_up(&sem->wait);
+
+ spin_unlock_irqrestore(&semaphore_lock, flags);
+ return 1;
+}
+
+
+/*
+ * The semaphore operations have a special calling sequence that
+ * allow us to do a simpler in-line version of them. These routines
+ * need to convert that sequence back into the C sequence when
+ * there is contention on the semaphore.
+ *
+ * %ecx contains the semaphore pointer on entry. Save the C-clobbered
+ * registers (%eax, %edx and %ecx) except %eax when used as a return
+ * value..
+ */
+asm(
+".text\n"
+".align 4\n"
+".globl __down_failed\n"
+"__down_failed:\n\t"
+#if defined(CONFIG_FRAME_POINTER)
+ "pushl %ebp\n\t"
+ "movl %esp,%ebp\n\t"
+#endif
+ "pushl %eax\n\t"
+ "pushl %edx\n\t"
+ "pushl %ecx\n\t"
+ "call __down\n\t"
+ "popl %ecx\n\t"
+ "popl %edx\n\t"
+ "popl %eax\n\t"
+#if defined(CONFIG_FRAME_POINTER)
+ "movl %ebp,%esp\n\t"
+ "popl %ebp\n\t"
+#endif
+ "ret"
+);
+
+asm(
+".text\n"
+".align 4\n"
+".globl __down_failed_interruptible\n"
+"__down_failed_interruptible:\n\t"
+#if defined(CONFIG_FRAME_POINTER)
+ "pushl %ebp\n\t"
+ "movl %esp,%ebp\n\t"
+#endif
+ "pushl %edx\n\t"
+ "pushl %ecx\n\t"
+ "call __down_interruptible\n\t"
+ "popl %ecx\n\t"
+ "popl %edx\n\t"
+#if defined(CONFIG_FRAME_POINTER)
+ "movl %ebp,%esp\n\t"
+ "popl %ebp\n\t"
+#endif
+ "ret"
+);
+
+asm(
+".text\n"
+".align 4\n"
+".globl __down_failed_trylock\n"
+"__down_failed_trylock:\n\t"
+#if defined(CONFIG_FRAME_POINTER)
+ "pushl %ebp\n\t"
+ "movl %esp,%ebp\n\t"
+#endif
+ "pushl %edx\n\t"
+ "pushl %ecx\n\t"
+ "call __down_trylock\n\t"
+ "popl %ecx\n\t"
+ "popl %edx\n\t"
+#if defined(CONFIG_FRAME_POINTER)
+ "movl %ebp,%esp\n\t"
+ "popl %ebp\n\t"
+#endif
+ "ret"
+);
+
+asm(
+".text\n"
+".align 4\n"
+".globl __up_wakeup\n"
+"__up_wakeup:\n\t"
+ "pushl %eax\n\t"
+ "pushl %edx\n\t"
+ "pushl %ecx\n\t"
+ "call __up\n\t"
+ "popl %ecx\n\t"
+ "popl %edx\n\t"
+ "popl %eax\n\t"
+ "ret"
+);
+
+/*
+ * rw spinlock fallbacks
+ */
+#if defined(CONFIG_SMP)
+asm(
+"
+.align 4
+.globl __write_lock_failed
+__write_lock_failed:
+ " LOCK "addl $" RW_LOCK_BIAS_STR ",(%eax)
+1: rep; nop
+ cmpl $" RW_LOCK_BIAS_STR ",(%eax)
+ jne 1b
+
+ " LOCK "subl $" RW_LOCK_BIAS_STR ",(%eax)
+ jnz __write_lock_failed
+ ret
+
+
+.align 4
+.globl __read_lock_failed
+__read_lock_failed:
+ lock ; incl (%eax)
+1: rep; nop
+ cmpl $1,(%eax)
+ js 1b
+
+ lock ; decl (%eax)
+ js __read_lock_failed
+ ret
+"
+);
+#endif
diff --git a/old/xenolinux-2.4.16-sparse/arch/xeno/kernel/setup.c b/old/xenolinux-2.4.16-sparse/arch/xeno/kernel/setup.c
new file mode 100644
index 0000000000..979deacf5a
--- /dev/null
+++ b/old/xenolinux-2.4.16-sparse/arch/xeno/kernel/setup.c
@@ -0,0 +1,996 @@
+/*
+ * 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 <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>
+
+shared_info_t *HYPERVISOR_shared_info;
+
+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;
+
+/*
+ * 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 start_pfn, max_pfn, max_low_pfn;
+ unsigned long bootmap_size;
+ 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_shared_info->event_address =
+ (unsigned long)hypervisor_callback;
+ HYPERVISOR_shared_info->failsafe_address =
+ (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));
+ 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();
+}
+
+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;
+
+ /* VIA C3 CPUs (670-68F) need further shifting. */
+ if (c->x86_vendor == X86_VENDOR_CENTAUR && (c->x86 == 6) &&
+ ((c->x86_model == 7) || (c->x86_model == 8))) {
+ l2size = l2size >> 8;
+ }
+
+ /* 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, &regs[0], &regs[1], &regs[2], &regs[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);
+}
+
+
+
+/*
+ * 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 ) {
+ cpuid(0x00000001, &tfms, &junk, &junk,
+ &c->x86_capability[0]);
+ c->x86 = (tfms >> 8) & 15;
+ c->x86_model = (tfms >> 4) & 15;
+ 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", NULL, "tm", "ia64", NULL,
+
+ /* AMD-defined */
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, "syscall", NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, 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,
+ };
+ 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_and_ldt_switch(__KERNEL_DS, current->thread.esp0, 0);
+
+ /* Force FPU initialization. */
+ current->flags &= ~PF_USEDFPU;
+ current->used_math = 0;
+ stts();
+}
+
+
+/******************************************************************************
+ * Time-to-die callback handling.
+ */
+
+static void time_to_die(int irq, void *unused, struct pt_regs *regs)
+{
+ extern void ctrl_alt_del(void);
+ ctrl_alt_del();
+}
+
+static int __init setup_death_event(void)
+{
+ (void)request_irq(_EVENT_DIE, time_to_die, 0, "die", NULL);
+ return 0;
+}
+
+__initcall(setup_death_event);
diff --git a/old/xenolinux-2.4.16-sparse/arch/xeno/kernel/signal.c b/old/xenolinux-2.4.16-sparse/arch/xeno/kernel/signal.c
new file mode 100644
index 0000000000..a23cec1dea
--- /dev/null
+++ b/old/xenolinux-2.4.16-sparse/arch/xeno/kernel/signal.c
@@ -0,0 +1,720 @@
+/*
+ * 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(&current->sigmask_lock);
+ saveset = current->blocked;
+ siginitset(&current->blocked, mask);
+ recalc_sigpending(current);
+ spin_unlock_irq(&current->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(&current->sigmask_lock);
+ saveset = current->blocked;
+ current->blocked = newset;
+ recalc_sigpending(current);
+ spin_unlock_irq(&current->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(&current->sigmask_lock);
+ current->blocked = set;
+ recalc_sigpending(current);
+ spin_unlock_irq(&current->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(&current->sigmask_lock);
+ current->blocked = set;
+ recalc_sigpending(current);
+ spin_unlock_irq(&current->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(&current->sigmask_lock);
+ sigorsets(&current->blocked,&current->blocked,&ka->sa.sa_mask);
+ sigaddset(&current->blocked,sig);
+ recalc_sigpending(current);
+ spin_unlock_irq(&current->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 = &current->blocked;
+
+ for (;;) {
+ unsigned long signr;
+
+ spin_lock_irq(&current->sigmask_lock);
+ signr = dequeue_signal(&current->blocked, &info);
+ spin_unlock_irq(&current->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(&current->blocked, signr)) {
+ send_sig_info(signr, &info, current);
+ continue;
+ }
+ }
+
+ ka = &current->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:
+ 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:
+ sigaddset(&current->pending.signal, signr);
+ recalc_sigpending(current);
+ current->flags |= PF_SIGNALED;
+ do_exit(exit_code);
+ /* 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/old/xenolinux-2.4.16-sparse/arch/xeno/kernel/sys_i386.c b/old/xenolinux-2.4.16-sparse/arch/xeno/kernel/sys_i386.c
new file mode 100644
index 0000000000..5fd6910b9c
--- /dev/null
+++ b/old/xenolinux-2.4.16-sparse/arch/xeno/kernel/sys_i386.c
@@ -0,0 +1,256 @@
+/*
+ * linux/arch/i386/kernel/sys_i386.c
+ *
+ * This file contains various random system calls that
+ * have a non-standard calling sequence on the Linux/i386
+ * platform.
+ */
+
+#include <linux/errno.h>
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/smp.h>
+#include <linux/smp_lock.h>
+#include <linux/sem.h>
+#include <linux/msg.h>
+#include <linux/shm.h>
+#include <linux/stat.h>
+#include <linux/mman.h>
+#include <linux/file.h>
+#include <linux/utsname.h>
+
+#include <asm/uaccess.h>
+#include <asm/ipc.h>
+
+/*
+ * sys_pipe() is the normal C calling standard for creating
+ * a pipe. It's not the way Unix traditionally does this, though.
+ */
+asmlinkage int sys_pipe(unsigned long * fildes)
+{
+ int fd[2];
+ int error;
+
+ error = do_pipe(fd);
+ if (!error) {
+ if (copy_to_user(fildes, fd, 2*sizeof(int)))
+ error = -EFAULT;
+ }
+ return error;
+}
+
+/* common code for old and new mmaps */
+static inline long do_mmap2(
+ unsigned long addr, unsigned long len,
+ unsigned long prot, unsigned long flags,
+ unsigned long fd, unsigned long pgoff)
+{
+ int error = -EBADF;
+ struct file * file = NULL;
+
+ flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE);
+ if (!(flags & MAP_ANONYMOUS)) {
+ file = fget(fd);
+ if (!file)
+ goto out;
+ }
+
+ down_write(&current->mm->mmap_sem);
+ error = do_mmap_pgoff(file, addr, len, prot, flags, pgoff);
+ up_write(&current->mm->mmap_sem);
+
+ if (file)
+ fput(file);
+out:
+ return error;
+}
+
+asmlinkage long sys_mmap2(unsigned long addr, unsigned long len,
+ unsigned long prot, unsigned long flags,
+ unsigned long fd, unsigned long pgoff)
+{
+ return do_mmap2(addr, len, prot, flags, fd, pgoff);
+}
+
+/*
+ * Perform the select(nd, in, out, ex, tv) and mmap() system
+ * calls. Linux/i386 didn't use to be able to handle more than
+ * 4 system call parameters, so these system calls used a memory
+ * block for parameter passing..
+ */
+
+struct mmap_arg_struct {
+ unsigned long addr;
+ unsigned long len;
+ unsigned long prot;
+ unsigned long flags;
+ unsigned long fd;
+ unsigned long offset;
+};
+
+asmlinkage int old_mmap(struct mmap_arg_struct *arg)
+{
+ struct mmap_arg_struct a;
+ int err = -EFAULT;
+
+ if (copy_from_user(&a, arg, sizeof(a)))
+ goto out;
+
+ err = -EINVAL;
+ if (a.offset & ~PAGE_MASK)
+ goto out;
+
+ err = do_mmap2(a.addr, a.len, a.prot, a.flags, a.fd, a.offset >> PAGE_SHIFT);
+out:
+ return err;
+}
+
+
+extern asmlinkage int sys_select(int, fd_set *, fd_set *, fd_set *, struct timeval *);
+
+struct sel_arg_struct {
+ unsigned long n;
+ fd_set *inp, *outp, *exp;
+ struct timeval *tvp;
+};
+
+asmlinkage int old_select(struct sel_arg_struct *arg)
+{
+ struct sel_arg_struct a;
+
+ if (copy_from_user(&a, arg, sizeof(a)))
+ return -EFAULT;
+ /* sys_select() does the appropriate kernel locking */
+ return sys_select(a.n, a.inp, a.outp, a.exp, a.tvp);
+}
+
+/*
+ * sys_ipc() is the de-multiplexer for the SysV IPC calls..
+ *
+ * This is really horribly ugly.
+ */
+asmlinkage int sys_ipc (uint call, int first, int second,
+ int third, void *ptr, long fifth)
+{
+ int version, ret;
+
+ version = call >> 16; /* hack for backward compatibility */
+ call &= 0xffff;
+
+ switch (call) {
+ case SEMOP:
+ return sys_semop (first, (struct sembuf *)ptr, second);
+ case SEMGET:
+ return sys_semget (first, second, third);
+ case SEMCTL: {
+ union semun fourth;
+ if (!ptr)
+ return -EINVAL;
+ if (get_user(fourth.__pad, (void **) ptr))
+ return -EFAULT;
+ return sys_semctl (first, second, third, fourth);
+ }
+
+ case MSGSND:
+ return sys_msgsnd (first, (struct msgbuf *) ptr,
+ second, third);
+ case MSGRCV:
+ switch (version) {
+ case 0: {
+ struct ipc_kludge tmp;
+ if (!ptr)
+ return -EINVAL;
+
+ if (copy_from_user(&tmp,
+ (struct ipc_kludge *) ptr,
+ sizeof (tmp)))
+ return -EFAULT;
+ return sys_msgrcv (first, tmp.msgp, second,
+ tmp.msgtyp, third);
+ }
+ default:
+ return sys_msgrcv (first,
+ (struct msgbuf *) ptr,
+ second, fifth, third);
+ }
+ case MSGGET:
+ return sys_msgget ((key_t) first, second);
+ case MSGCTL:
+ return sys_msgctl (first, second, (struct msqid_ds *) ptr);
+
+ case SHMAT:
+ switch (version) {
+ default: {
+ ulong raddr;
+ ret = sys_shmat (first, (char *) ptr, second, &raddr);
+ if (ret)
+ return ret;
+ return put_user (raddr, (ulong *) third);
+ }
+ case 1: /* iBCS2 emulator entry point */
+ if (!segment_eq(get_fs(), get_ds()))
+ return -EINVAL;
+ return sys_shmat (first, (char *) ptr, second, (ulong *) third);
+ }
+ case SHMDT:
+ return sys_shmdt ((char *)ptr);
+ case SHMGET:
+ return sys_shmget (first, second, third);
+ case SHMCTL:
+ return sys_shmctl (first, second,
+ (struct shmid_ds *) ptr);
+ default:
+ return -EINVAL;
+ }
+}
+
+/*
+ * Old cruft
+ */
+asmlinkage int sys_uname(struct old_utsname * name)
+{
+ int err;
+ if (!name)
+ return -EFAULT;
+ down_read(&uts_sem);
+ err=copy_to_user(name, &system_utsname, sizeof (*name));
+ up_read(&uts_sem);
+ return err?-EFAULT:0;
+}
+
+asmlinkage int sys_olduname(struct oldold_utsname * name)
+{
+ int error;
+
+ if (!name)
+ return -EFAULT;
+ if (!access_ok(VERIFY_WRITE,name,sizeof(struct oldold_utsname)))
+ return -EFAULT;
+
+ down_read(&uts_sem);
+
+ error = __copy_to_user(&name->sysname,&system_utsname.sysname,__OLD_UTS_LEN);
+ error |= __put_user(0,name->sysname+__OLD_UTS_LEN);
+ error |= __copy_to_user(&name->nodename,&system_utsname.nodename,__OLD_UTS_LEN);
+ error |= __put_user(0,name->nodename+__OLD_UTS_LEN);
+ error |= __copy_to_user(&name->release,&system_utsname.release,__OLD_UTS_LEN);
+ error |= __put_user(0,name->release+__OLD_UTS_LEN);
+ error |= __copy_to_user(&name->version,&system_utsname.version,__OLD_UTS_LEN);
+ error |= __put_user(0,name->version+__OLD_UTS_LEN);
+ error |= __copy_to_user(&name->machine,&system_utsname.machine,__OLD_UTS_LEN);
+ error |= __put_user(0,name->machine+__OLD_UTS_LEN);
+
+ up_read(&uts_sem);
+
+ error = error ? -EFAULT : 0;
+
+ return error;
+}
+
+asmlinkage int sys_pause(void)
+{
+ current->state = TASK_INTERRUPTIBLE;
+ schedule();
+ return -ERESTARTNOHAND;
+}
+
diff --git a/old/xenolinux-2.4.16-sparse/arch/xeno/kernel/time.c b/old/xenolinux-2.4.16-sparse/arch/xeno/kernel/time.c
new file mode 100644
index 0000000000..eb5757cdc2
--- /dev/null
+++ b/old/xenolinux-2.4.16-sparse/arch/xeno/kernel/time.c
@@ -0,0 +1,350 @@
+/* -*- Mode:C; c-basic-offset:4; tab-width:4 -*-
+ ****************************************************************************
+ * (C) 2002 - Rolf Neugebauer - Intel Research Cambridge
+ ****************************************************************************
+ *
+ * File: arch.xeno/time.c
+ * Author: Rolf Neugebauer
+ * Changes:
+ *
+ * Date: Nov 2002
+ *
+ * Environment: XenoLinux
+ * Description: Interface with Hypervisor to get correct notion of time
+ * Currently supports Systemtime and WallClock time.
+ *
+ * (This has hardly any resemblence with the Linux code but left the
+ * copyright notice anyway. Ignore the comments in the copyright notice.)
+ ****************************************************************************
+ * $Id: c-insert.c,v 1.7 2002/11/08 16:04:34 rn Exp $
+ ****************************************************************************
+ */
+
+/*
+ * 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 <linux/kernel.h>
+#include <linux/interrupt.h>
+#include <linux/time.h>
+#include <linux/init.h>
+#include <linux/smp.h>
+#include <linux/irq.h>
+
+#undef XENO_TIME_DEBUG /* adds sanity checks and periodic printouts */
+
+spinlock_t rtc_lock = SPIN_LOCK_UNLOCKED;
+extern rwlock_t xtime_lock;
+
+unsigned long cpu_khz; /* get this from Xen, used elsewhere */
+static spinlock_t hyp_stime_lock = SPIN_LOCK_UNLOCKED;
+static spinlock_t hyp_wctime_lock = SPIN_LOCK_UNLOCKED;
+
+static u32 st_scale_f;
+static u32 st_scale_i;
+static u32 shadow_st_pcc;
+static s64 shadow_st;
+
+/*
+ * System time.
+ * Although the rest of the Linux kernel doesn't know about this, we
+ * we use it to extrapolate passage of wallclock time.
+ * We need to read the values from the shared info page "atomically"
+ * and use the cycle counter value as the "version" number. Clashes
+ * should be very rare.
+ */
+static inline long long get_s_time(void)
+{
+ unsigned long flags;
+ u32 delta_tsc, low, pcc;
+ u64 delta;
+ s64 now;
+
+ spin_lock_irqsave(&hyp_stime_lock, flags);
+
+ while ((pcc = HYPERVISOR_shared_info->st_timestamp) != shadow_st_pcc)
+ {
+ barrier();
+ shadow_st_pcc = pcc;
+ shadow_st = HYPERVISOR_shared_info->system_time;
+ barrier();
+ }
+
+ now = shadow_st;
+ /* only use bottom 32bits of TSC. This should be sufficient */
+ rdtscl(low);
+ delta_tsc = low - pcc;
+ delta = ((u64)delta_tsc * st_scale_f);
+ delta >>= 32;
+ delta += ((u64)delta_tsc * st_scale_i);
+
+ spin_unlock_irqrestore(&hyp_time_lock, flags);
+
+ return now + delta;
+
+}
+#define NOW() ((long long)get_s_time())
+
+/*
+ * Wallclock time.
+ * Based on what the hypervisor tells us, extrapolated using system time.
+ * Again need to read a number of values from the shared page "atomically".
+ * this time using a version number.
+ */
+static u32 shadow_wc_version=0;
+static long shadow_tv_sec;
+static long shadow_tv_usec;
+static long long shadow_wc_timestamp;
+void do_gettimeofday(struct timeval *tv)
+{
+ unsigned long flags;
+ long usec, sec;
+ u32 version;
+ u64 now;
+
+ spin_lock_irqsave(&hyp_wctime_lock, flags);
+
+ while ((version = HYPERVISOR_shared_info->wc_version)!= shadow_wc_version)
+ {
+ barrier();
+ shadow_wc_version = version;
+ shadow_tv_sec = HYPERVISOR_shared_info->tv_sec;
+ shadow_tv_usec = HYPERVISOR_shared_info->tv_usec;
+ shadow_wc_timestamp = HYPERVISOR_shared_info->wc_timestamp;
+ barrier();
+ }
+
+ now = NOW();
+ usec = ((unsigned long)(now-shadow_wc_timestamp))/1000;
+ sec = shadow_tv_sec;
+ usec += shadow_tv_usec;
+
+ while ( usec >= 1000000 )
+ {
+ usec -= 1000000;
+ sec++;
+ }
+
+ tv->tv_sec = sec;
+ tv->tv_usec = usec;
+
+ spin_unlock_irqrestore(&hyp_time_lock, flags);
+
+#ifdef XENO_TIME_DEBUG
+ {
+ static long long old_now=0;
+ static long long wct=0, old_wct=0;
+
+ /* This debug code checks if time increase over two subsequent calls */
+ wct=(((long long)sec) * 1000000) + usec;
+ /* wall clock time going backwards */
+ if ((wct < old_wct) ) {
+ printk("Urgh1: wc diff=%6ld, usec = %ld (0x%lX)\n",
+ (long)(wct-old_wct), usec, usec);
+ printk(" st diff=%lld cur st=0x%016llX old st=0x%016llX\n",
+ now-old_now, now, old_now);
+ }
+
+ /* system time going backwards */
+ if (now<=old_now) {
+ printk("Urgh2: st diff=%lld cur st=0x%016llX old st=0x%016llX\n",
+ now-old_now, now, old_now);
+ }
+ old_wct = wct;
+ old_now = now;
+ }
+#endif
+
+}
+
+void do_settimeofday(struct timeval *tv)
+{
+/* XXX RN: should do something special here for dom0 */
+#if 0
+ write_lock_irq(&xtime_lock);
+ /*
+ * This is revolting. We need to set "xtime" correctly. However, the
+ * value in this location is the value at the most recent update of
+ * wall time. Discover what correction gettimeofday() would have
+ * made, and then undo it!
+ */
+ tv->tv_usec -= do_gettimeoffset();
+ tv->tv_usec -= (jiffies - wall_jiffies) * (1000000 / HZ);
+
+ while ( tv->tv_usec < 0 )
+ {
+ tv->tv_usec += 1000000;
+ tv->tv_sec--;
+ }
+
+ xtime = *tv;
+ time_adjust = 0; /* stop active adjtime() */
+ time_status |= STA_UNSYNC;
+ time_maxerror = NTP_PHASE_LIMIT;
+ time_esterror = NTP_PHASE_LIMIT;
+ write_unlock_irq(&xtime_lock);
+#endif
+}
+
+
+/*
+ * Timer ISR.
+ * Unlike normal Linux these don't come in at a fixed rate of HZ.
+ * In here we wrok out how often it should have been called and then call
+ * the architecture independent part (do_timer()) the appropriate number of
+ * times. A bit of a nasty hack, to keep the "other" notion of wallclock time
+ * happy.
+ */
+static long long us_per_tick=1000000/HZ;
+static long long last_irq;
+static inline void do_timer_interrupt(int irq, void *dev_id,
+ struct pt_regs *regs)
+{
+ struct timeval tv;
+ long long time, delta;
+
+#ifdef XENO_TIME_DEBUG
+ static u32 foo_count = 0;
+ foo_count++;
+ if (foo_count>= 1000) {
+ s64 n = NOW();
+ struct timeval tv;
+ do_gettimeofday(&tv);
+ printk("0x%08X%08X %ld:%ld\n",
+ (u32)(n>>32), (u32)n, tv.tv_sec, tv.tv_usec);
+ foo_count = 0;
+ }
+#endif
+ /*
+ * The next bit really sucks:
+ * Linux not only uses do_gettimeofday() to keep a notion of
+ * wallclock time, but also maintains the xtime struct and jiffies.
+ * (Even worse some userland code accesses this via the sys_time()
+ * system call)
+ * Unfortunately, xtime is maintain in the architecture independent
+ * part of the timer ISR (./kernel/timer.c sic!). So, although we have
+ * perfectly valid notion of wallclock time from the hypervisor we here
+ * fake missed timer interrupts so that the arch independent part of
+ * the Timer ISR updates jiffies for us *and* once the bh gets run
+ * updates xtime accordingly. Yuck!
+ */
+
+ /* work out the number of jiffies past and update them */
+ do_gettimeofday(&tv);
+ time = (((long long)tv.tv_sec) * 1000000) + tv.tv_usec;
+ delta = time - last_irq;
+ if (delta <= 0) {
+ printk ("Timer ISR: Time went backwards: %lld\n", delta);
+ return;
+ }
+ while (delta >= us_per_tick) {
+ do_timer(regs);
+ delta -= us_per_tick;
+ last_irq += us_per_tick;
+ }
+
+#if 0
+ if (!user_mode(regs))
+ x86_do_profile(regs->eip);
+#endif
+}
+
+static void timer_interrupt(int irq, void *dev_id, struct pt_regs *regs)
+{
+ write_lock(&xtime_lock);
+ 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_freq = HYPERVISOR_shared_info->cpu_freq;
+ u64 scale;
+
+ do_get_fast_time = do_gettimeofday;
+
+ cpu_khz = (u32)cpu_freq/1000;
+ printk("Xen reported: %lu.%03lu MHz processor.\n",
+ cpu_khz / 1000, cpu_khz % 1000);
+
+ /*
+ * calculate systemtime scaling factor
+ * XXX RN: have to cast cpu_freq to u32 limits it to 4.29 GHz.
+ * Get a better do_div!
+ */
+ scale = 1000000000LL << 32;
+ do_div(scale,(u32)cpu_freq);
+ st_scale_f = scale & 0xffffffff;
+ st_scale_i = scale >> 32;
+ printk("System Time scale: %X %X\n",st_scale_i, st_scale_f);
+
+ do_gettimeofday(&xtime);
+ last_irq = (((long long)xtime.tv_sec) * 1000000) + xtime.tv_usec;
+
+ setup_irq(TIMER_IRQ, &irq_timer);
+
+ /*
+ * Start ticker. Note that timing runs of wall clock, not virtual
+ * 'domain' time. This means that clock sshould run at the correct
+ * rate. For things like scheduling, it's not clear whether it
+ * matters which sort of time we use.
+ * XXX RN: unimplemented.
+ */
+
+ rdtscll(alarm);
+#if 0
+ alarm += (1000/HZ)*HYPERVISOR_shared_info->ticks_per_ms;
+ HYPERVISOR_shared_info->wall_timeout = alarm;
+ HYPERVISOR_shared_info->domain_timeout = ~0ULL;
+#endif
+ clear_bit(_EVENT_TIMER, &HYPERVISOR_shared_info->events);
+}
diff --git a/old/xenolinux-2.4.16-sparse/arch/xeno/kernel/traps.c b/old/xenolinux-2.4.16-sparse/arch/xeno/kernel/traps.c
new file mode 100644
index 0000000000..c274928ae9
--- /dev/null
+++ b/old/xenolinux-2.4.16-sparse/arch/xeno/kernel/traps.c
@@ -0,0 +1,567 @@
+/*
+ * 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 <linux/kdb.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 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 i;
+ int in_kernel = 1;
+ unsigned long esp;
+ unsigned short ss;
+
+ esp = (unsigned long) (&regs->esp);
+ ss = __KERNEL_DS;
+ if (regs->xcs & 2) {
+ in_kernel = 0;
+ esp = regs->esp;
+ ss = regs->xss & 0xffff;
+ }
+ printk("CPU: %d\nEIP: %04x:[<%08lx>] %s\nEFLAGS: %08lx\n",
+ smp_processor_id(), 0xffff & regs->xcs, regs->eip, print_tainted(), regs->eflags);
+ 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 esp: %08lx\n",
+ regs->esi, regs->edi, regs->ebp, esp);
+ printk("ds: %04x es: %04x ss: %04x\n",
+ regs->xds & 0xffff, regs->xes & 0xffff, ss);
+ printk("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("\nStack: ");
+ show_stack((unsigned long*)esp);
+
+#if 0
+ printk("\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(" Bad EIP value.");
+ break;
+ }
+ printk("%02x ", c);
+ }
+#endif
+ }
+ printk("\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 (!(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 & 3) == 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() */
+}
+
+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);
+ cpu_init();
+}