sanchayanmaity/minix
1
0
Fork 0
Code Issues Pull requests Packages Projects Releases Wiki Activity
minix/kernel/arch/i386/mpx.S
Ben Gras 2f892aca91 kernel fpu context switching: fix race condition 
There seems to have been a broken assumption in the fpu context
restoring code.  It restores the context of the running process, without
guarantee that the current process is the one that will be scheduled.
This caused fpu saving for a different process to be triggered without
fpu hardware being enabled, causing an fpu exception in the kernel. This
practically only shows up with DEBUG_RACE on. Fix my thruby+me.

The fix
 . is to only set the fpu-in-use-by-this-process flag in the
   exception handler, and then take care of fpu restoring when
   actually returning to userspace

And the patch
 . translates fpu saving and restoring to c in arch_system.c,
   getting rid of a juicy chunk of assembly
 . makes osfxsr_feature private to arch_system.c
 . removes most of the arch dependent code from do_sigsend
2010-06-03 11:32:22 +00:00

673 lines
16 KiB
ArmAsm
Raw Blame History

/*
* This file is part of the lowest layer of the MINIX kernel. (The other part
* is "proc.c".) The lowest layer does process switching and message handling.
* Furthermore it contains the assembler startup code for Minix and the 32-bit
* interrupt handlers. It cooperates with the code in "start.c" to set up a
* good environment for main().
*
* Kernel is entered either because of kernel-calls, ipc-calls, interrupts or
* exceptions. TSS is set so that the kernel stack is loaded. The user cotext is
* saved to the proc table and the handler of the event is called. Once the
* handler is done, switch_to_user() function is called to pick a new process,
* finish what needs to be done for the next process to run, sets its context
* and switch to userspace.
*
* For communication with the boot monitor at startup time some constant
* data are compiled into the beginning of the text segment. This facilitates
* reading the data at the start of the boot process, since only the first
* sector of the file needs to be read.
*
* Some data storage is also allocated at the end of this file. This data
* will be at the start of the data segment of the kernel and will be read
* and modified by the boot monitor before the kernel starts.
*/
#include "kernel/kernel.h" /* configures the kernel */
/* sections */
#include <machine/vm.h>
#ifdef __ACK__
.text
begtext:
#ifdef __ACK__
.rom
#else
.data
#endif
begrom:
.data
begdata:
.bss
begbss:
#endif
#include <minix/config.h>
#include <minix/const.h>
#include <minix/com.h>
#include <machine/interrupt.h>
#include "archconst.h"
#include "kernel/const.h"
#include "kernel/proc.h"
#include "sconst.h"
/* Selected 386 tss offsets. */
#define TSS3_S_SP0 4
/*
* Exported functions
* Note: in assembly language the .define statement applied to a function name
* is loosely equivalent to a prototype in C code -- it makes it possible to
* link to an entity declared in the assembly code but does not create
* the entity.
*/
.globl _restore_user_context
.globl _reload_cr3
.globl _divide_error
.globl _single_step_exception
.globl _nmi
.globl _breakpoint_exception
.globl _overflow
.globl _bounds_check
.globl _inval_opcode
.globl _copr_not_available
.globl _double_fault
.globl _copr_seg_overrun
.globl _inval_tss
.globl _segment_not_present
.globl _stack_exception
.globl _general_protection
.globl _page_fault
.globl _copr_error
.globl _alignment_check
.globl _machine_check
.globl _simd_exception
.globl _params_size
.globl _params_offset
.globl _mon_ds
.globl _switch_to_user
.globl _save_fpu
.globl _hwint00 /* handlers for hardware interrupts */
.globl _hwint01
.globl _hwint02
.globl _hwint03
.globl _hwint04
.globl _hwint05
.globl _hwint06
.globl _hwint07
.globl _hwint08
.globl _hwint09
.globl _hwint10
.globl _hwint11
.globl _hwint12
.globl _hwint13
.globl _hwint14
.globl _hwint15
/* Exported variables. */
.globl begbss
.globl begdata
.text
/*===========================================================================*/
/* MINIX */
/*===========================================================================*/
.globl MINIX
MINIX:
/* this is the entry point for the MINIX kernel */
jmp over_flags /* skip over the next few bytes */
.short CLICK_SHIFT /* for the monitor: memory granularity */
flags:
/* boot monitor flags:
* call in 386 mode, make bss, make stack,
* load high, don't patch, will return,
* uses generic INT, memory vector,
* new boot code return
*/
.short 0x01FD
nop /* extra byte to sync up disassembler */
over_flags:
/* Set up a C stack frame on the monitor stack. (The monitor sets cs and ds */
/* right. The ss descriptor still references the monitor data segment.) */
movzwl %sp, %esp /* monitor stack is a 16 bit stack */
push %ebp
mov %esp, %ebp
push %esi
push %edi
cmp $0, 4(%ebp) /* monitor return vector is */
je noret /* nonzero if return possible */
incl _mon_return
noret:
movl %esp, _mon_sp /* save stack pointer for later return */
/* Copy the monitor global descriptor table to the address space of kernel and */
/* switch over to it. Prot_init() can then update it with immediate effect. */
sgdt _gdt+GDT_SELECTOR /* get the monitor gdtr */
movl _gdt+GDT_SELECTOR+2, %esi /* absolute address of GDT */
mov $_gdt, %ebx /* address of kernel GDT */
mov $8*8, %ecx /* copying eight descriptors */
copygdt:
movb %es:(%esi), %al
movb %al, (%ebx)
inc %esi
inc %ebx
loop copygdt
movl _gdt+DS_SELECTOR+2, %eax /* base of kernel data */
and $0x00FFFFFF, %eax /* only 24 bits */
add $_gdt, %eax /* eax = vir2phys(gdt) */
movl %eax, _gdt+GDT_SELECTOR+2 /* set base of GDT */
lgdt _gdt+GDT_SELECTOR /* switch over to kernel GDT */
/* Locate boot parameters, set up kernel segment registers and stack. */
mov 8(%ebp), %ebx /* boot parameters offset */
mov 12(%ebp), %edx /* boot parameters length */
mov 16(%ebp), %eax /* address of a.out headers */
movl %eax, _aout
mov %ds, %ax /* kernel data */
mov %ax, %es
mov %ax, %fs
mov %ax, %gs
mov %ax, %ss
mov $_k_boot_stktop, %esp /* set sp to point to the top of kernel stack */
/* Save boot parameters into these global variables for i386 code */
movl %edx, _params_size
movl %ebx, _params_offset
movl $SS_SELECTOR, _mon_ds
/* Call C startup code to set up a proper environment to run main(). */
push %edx
push %ebx
push $SS_SELECTOR
push $DS_SELECTOR
push $CS_SELECTOR
call _cstart /* cstart(cs, ds, mds, parmoff, parmlen) */
add $5*4, %esp
/* Reload gdtr, idtr and the segment registers to global descriptor table set */
/* up by prot_init(). */
lgdt _gdt+GDT_SELECTOR
lidt _gdt+IDT_SELECTOR
ljmp $CS_SELECTOR, $csinit
csinit:
movw $DS_SELECTOR, %ax
mov %ax, %ds
mov %ax, %es
mov %ax, %fs
mov %ax, %gs
mov %ax, %ss
movw $TSS_SELECTOR, %ax /* no other TSS is used */
ltr %ax
push $0 /* set flags to known good state */
popf /* esp, clear nested task and int enable */
jmp _main /* main() */
/*===========================================================================*/
/* interrupt handlers */
/* interrupt handlers for 386 32-bit protected mode */
/*===========================================================================*/
#define PIC_IRQ_HANDLER(irq) \
push $irq ;\
call _irq_handle /* intr_handle(irq_handlers[irq]) */ ;\
add $4, %esp ;
/*===========================================================================*/
/* hwint00 - 07 */
/*===========================================================================*/
/* Note this is a macro, it just looks like a subroutine. */
#define hwint_master(irq) \
TEST_INT_IN_KERNEL(4, 0f) ;\
\
SAVE_PROCESS_CTX(0) ;\
push %ebp ;\
movl $0, %ebp /* for stack trace */ ;\
call _context_stop ;\
add $4, %esp ;\
PIC_IRQ_HANDLER(irq) ;\
movb $END_OF_INT, %al ;\
outb $INT_CTL /* reenable interrupts in master pic */ ;\
jmp _switch_to_user ;\
\
0: \
pusha ;\
call _context_stop_idle ;\
PIC_IRQ_HANDLER(irq) ;\
movb $END_OF_INT, %al ;\
outb $INT_CTL /* reenable interrupts in master pic */ ;\
CLEAR_IF(10*4(%esp)) ;\
popa ;\
iret ;
/* Each of these entry points is an expansion of the hwint_master macro */
.balign 16
_hwint00:
/* Interrupt routine for irq 0 (the clock). */
hwint_master(0)
.balign 16
_hwint01:
/* Interrupt routine for irq 1 (keyboard) */
hwint_master(1)
.balign 16
_hwint02:
/* Interrupt routine for irq 2 (cascade!) */
hwint_master(2)
.balign 16
_hwint03:
/* Interrupt routine for irq 3 (second serial) */
hwint_master(3)
.balign 16
_hwint04:
/* Interrupt routine for irq 4 (first serial) */
hwint_master(4)
.balign 16
_hwint05:
/* Interrupt routine for irq 5 (XT winchester) */
hwint_master(5)
.balign 16
_hwint06:
/* Interrupt routine for irq 6 (floppy) */
hwint_master(6)
.balign 16
_hwint07:
/* Interrupt routine for irq 7 (printer) */
hwint_master(7)
/*===========================================================================*/
/* hwint08 - 15 */
/*===========================================================================*/
/* Note this is a macro, it just looks like a subroutine. */
#define hwint_slave(irq) \
TEST_INT_IN_KERNEL(4, 0f) ;\
\
SAVE_PROCESS_CTX(0) ;\
push %ebp ;\
movl $0, %ebp /* for stack trace */ ;\
call _context_stop ;\
add $4, %esp ;\
PIC_IRQ_HANDLER(irq) ;\
movb $END_OF_INT, %al ;\
outb $INT_CTL /* reenable interrupts in master pic */ ;\
outb $INT2_CTL /* reenable slave 8259 */ ;\
jmp _switch_to_user ;\
\
0: \
pusha ;\
call _context_stop_idle ;\
PIC_IRQ_HANDLER(irq) ;\
movb $END_OF_INT, %al ;\
outb $INT_CTL /* reenable interrupts in master pic */ ;\
outb $INT2_CTL /* reenable slave 8259 */ ;\
CLEAR_IF(10*4(%esp)) ;\
popa ;\
iret ;
/* Each of these entry points is an expansion of the hwint_slave macro */
.balign 16
_hwint08:
/* Interrupt routine for irq 8 (realtime clock) */
hwint_slave(8)
.balign 16
_hwint09:
/* Interrupt routine for irq 9 (irq 2 redirected) */
hwint_slave(9)
.balign 16
_hwint10:
/* Interrupt routine for irq 10 */
hwint_slave(10)
.balign 16
_hwint11:
/* Interrupt routine for irq 11 */
hwint_slave(11)
.balign 16
_hwint12:
/* Interrupt routine for irq 12 */
hwint_slave(12)
.balign 16
_hwint13:
/* Interrupt routine for irq 13 (FPU exception) */
hwint_slave(13)
.balign 16
_hwint14:
/* Interrupt routine for irq 14 (AT winchester) */
hwint_slave(14)
.balign 16
_hwint15:
/* Interrupt routine for irq 15 */
hwint_slave(15)
/*
* IPC is only from a process to kernel
*/
.balign 16
.globl _ipc_entry
_ipc_entry:
SAVE_PROCESS_CTX(0)
/* save the pointer to the current process */
push %ebp
/*
* pass the syscall arguments from userspace to the handler.
* SAVE_PROCESS_CTX() does not clobber these registers, they are still
* set as the userspace have set them
*/
push %ebx
push %eax
push %ecx
/* stop user process cycles */
push %ebp
/* for stack trace */
movl $0, %ebp
call _context_stop
add $4, %esp
call _do_ipc
/* restore the current process pointer and save the return value */
add $3 * 4, %esp
pop %esi
mov %eax, AXREG(%esi)
jmp _switch_to_user
/*
* kernel call is only from a process to kernel
*/
.balign 16
.globl _kernel_call_entry
_kernel_call_entry:
SAVE_PROCESS_CTX(0)
/* save the pointer to the current process */
push %ebp
/*
* pass the syscall arguments from userspace to the handler.
* SAVE_PROCESS_CTX() does not clobber these registers, they are still
* set as the userspace have set them
*/
push %eax
/* stop user process cycles */
push %ebp
/* for stack trace */
movl $0, %ebp
call _context_stop
add $4, %esp
call _kernel_call
/* restore the current process pointer and save the return value */
add $8, %esp
jmp _switch_to_user
.balign 16
/*
* called by the exception interrupt vectors. If the exception does not push
* errorcode, we assume that the vector handler pushed 0 instead. Next pushed
* thing is the vector number. From this point on we can continue as if every
* exception pushes an error code
*/
exception_entry:
/*
* check if it is a nested trap by comparing the saved code segment
* descriptor with the kernel CS first
*/
TEST_INT_IN_KERNEL(12, exception_entry_nested)
exception_entry_from_user:
SAVE_PROCESS_CTX(8)
/* stop user process cycles */
push %ebp
/* for stack trace clear %ebp */
movl $0, %ebp
call _context_stop
add $4, %esp
/*
* push a pointer to the interrupt state pushed by the cpu and the
* vector number pushed by the vector handler just before calling
* exception_entry and call the exception handler.
*/
push %esp
push $0 /* it's not a nested exception */
call _exception_handler
jmp _switch_to_user
exception_entry_nested:
pusha
mov %esp, %eax
add $(8 * 4), %eax
push %eax
pushl $1 /* it's a nested exception */
call _exception_handler
add $8, %esp
popa
/* clear the error code and the exception number */
add $8, %esp
/* resume execution at the point of exception */
iret
/*===========================================================================*/
/* restart */
/*===========================================================================*/
_restore_user_context:
mov 4(%esp), %ebp /* will assume P_STACKBASE == 0 */
/* reconstruct the stack for iret */
movl SSREG(%ebp), %eax
push %eax
movl SPREG(%ebp), %eax
push %eax
movl PSWREG(%ebp), %eax
push %eax
movl CSREG(%ebp), %eax
push %eax
movl PCREG(%ebp), %eax
push %eax
RESTORE_GP_REGS(%ebp)
RESTORE_SEGS(%ebp)
movl %ss:BPREG(%ebp), %ebp
iret /* continue process */
/*===========================================================================*/
/* exception handlers */
/*===========================================================================*/
#define EXCEPTION_ERR_CODE(vector) \
push $vector ;\
jmp exception_entry
#define EXCEPTION_NO_ERR_CODE(vector) \
pushl $0 ;\
EXCEPTION_ERR_CODE(vector)
_divide_error:
EXCEPTION_NO_ERR_CODE(DIVIDE_VECTOR)
_single_step_exception:
EXCEPTION_NO_ERR_CODE(DEBUG_VECTOR)
_nmi:
#ifndef CONFIG_WATCHDOG
EXCEPTION_NO_ERR_CODE(NMI_VECTOR)
#else
/*
* We have to be very careful as this interrupt can occur anytime. On
* the other hand, if it interrupts a user process, we will resume the
* same process which makes things a little simpler. We know that we are
* already on kernel stack whenever it happened and we can be
* conservative and save everything as we don't need to be extremely
* efficient as the interrupt is infrequent and some overhead is already
* expected.
*/
/*
* save the important registers. We don't save %cs and %ss and they are
* saved and restored by CPU
*/
pushw %ds
pushw %es
pushw %fs
pushw %gs
pusha
/*
* We cannot be sure about the state of the kernel segment register,
* however, we always set %ds and %es to the same as %ss
*/
mov %ss, %si
mov %si, %ds
mov %si, %es
push %esp
call _nmi_watchdog_handler
add $4, %esp
/* restore all the important registers as they were before the trap */
popa
popw %gs
popw %fs
popw %es
popw %ds
iret
#endif
_breakpoint_exception:
EXCEPTION_NO_ERR_CODE(BREAKPOINT_VECTOR)
_overflow:
EXCEPTION_NO_ERR_CODE(OVERFLOW_VECTOR)
_bounds_check:
EXCEPTION_NO_ERR_CODE(BOUNDS_VECTOR)
_inval_opcode:
EXCEPTION_NO_ERR_CODE(INVAL_OP_VECTOR)
_copr_not_available:
TEST_INT_IN_KERNEL(4, copr_not_available_in_kernel)
cld /* set direction flag to a known value */
SAVE_PROCESS_CTX_NON_LAZY(0)
/* stop user process cycles */
push %ebp
mov $0, %ebp
call _context_stop
pop %ebp
lea P_MISC_FLAGS(%ebp), %ebx
orw $MF_USED_FPU, (%ebx)
mov $0, %ebp
jmp _switch_to_user
copr_not_available_in_kernel:
pushl $0
pushl $COPROC_NOT_VECTOR
jmp exception_entry_nested
_double_fault:
EXCEPTION_ERR_CODE(DOUBLE_FAULT_VECTOR)
_copr_seg_overrun:
EXCEPTION_NO_ERR_CODE(COPROC_SEG_VECTOR)
_inval_tss:
EXCEPTION_ERR_CODE(INVAL_TSS_VECTOR)
_segment_not_present:
EXCEPTION_ERR_CODE(SEG_NOT_VECTOR)
_stack_exception:
EXCEPTION_ERR_CODE(STACK_FAULT_VECTOR)
_general_protection:
EXCEPTION_ERR_CODE(PROTECTION_VECTOR)
_page_fault:
EXCEPTION_ERR_CODE(PAGE_FAULT_VECTOR)
_copr_error:
EXCEPTION_NO_ERR_CODE(COPROC_ERR_VECTOR)
_alignment_check:
EXCEPTION_NO_ERR_CODE(ALIGNMENT_CHECK_VECTOR)
_machine_check:
EXCEPTION_NO_ERR_CODE(MACHINE_CHECK_VECTOR)
_simd_exception:
EXCEPTION_NO_ERR_CODE(SIMD_EXCEPTION_VECTOR)
/*===========================================================================*/
/* reload_cr3 */
/*===========================================================================*/
/* PUBLIC void reload_cr3(void); */
_reload_cr3:
push %ebp
mov %esp, %ebp
mov %cr3, %eax
mov %eax, %cr3
pop %ebp
ret
/*===========================================================================*/
/* data */
/*===========================================================================*/
#ifdef __ACK__
.rom /* Before the string table please */
#else
.data
#endif
.short 0x526F /* this must be the first data entry (magic #) */
.bss
/*
* the kernel stack
*/
.globl _k_boot_stktop
k_boot_stack:
.space 4096 /* kernel stack */ /* FIXME use macro here */
_k_boot_stktop: /* top of kernel stack */
Reference in a new issue View git blame Copy permalink