50e2064049
This commit removes all traces of Minix segments (the text/data/stack memory map abstraction in the kernel) and significance of Intel segments (hardware segments like CS, DS that add offsets to all addressing before page table translation). This ultimately simplifies the memory layout and addressing and makes the same layout possible on non-Intel architectures. There are only two types of addresses in the world now: virtual and physical; even the kernel and processes have the same virtual address space. Kernel and user processes can be distinguished at a glance as processes won't use 0xF0000000 and above. No static pre-allocated memory sizes exist any more. Changes to booting: . The pre_init.c leaves the kernel and modules exactly as they were left by the bootloader in physical memory . The kernel starts running using physical addressing, loaded at a fixed location given in its linker script by the bootloader. All code and data in this phase are linked to this fixed low location. . It makes a bootstrap pagetable to map itself to a fixed high location (also in linker script) and jumps to the high address. All code and data then use this high addressing. . All code/data symbols linked at the low addresses is prefixed by an objcopy step with __k_unpaged_*, so that that code cannot reference highly-linked symbols (which aren't valid yet) or vice versa (symbols that aren't valid any more). . The two addressing modes are separated in the linker script by collecting the unpaged_*.o objects and linking them with low addresses, and linking the rest high. Some objects are linked twice, once low and once high. . The bootstrap phase passes a lot of information (e.g. free memory list, physical location of the modules, etc.) using the kinfo struct. . After this bootstrap the low-linked part is freed. . The kernel maps in VM into the bootstrap page table so that VM can begin executing. Its first job is to make page tables for all other boot processes. So VM runs before RS, and RS gets a fully dynamic, VM-managed address space. VM gets its privilege info from RS as usual but that happens after RS starts running. . Both the kernel loading VM and VM organizing boot processes happen using the libexec logic. This removes the last reason for VM to still know much about exec() and vm/exec.c is gone. Further Implementation: . All segments are based at 0 and have a 4 GB limit. . The kernel is mapped in at the top of the virtual address space so as not to constrain the user processes. . Processes do not use segments from the LDT at all; there are no segments in the LDT any more, so no LLDT is needed. . The Minix segments T/D/S are gone and so none of the user-space or in-kernel copy functions use them. The copy functions use a process endpoint of NONE to realize it's a physical address, virtual otherwise. . The umap call only makes sense to translate a virtual address to a physical address now. . Segments-related calls like newmap and alloc_segments are gone. . All segments-related translation in VM is gone (vir2map etc). . Initialization in VM is simpler as no moving around is necessary. . VM and all other boot processes can be linked wherever they wish and will be mapped in at the right location by the kernel and VM respectively. Other changes: . The multiboot code is less special: it does not use mb_print for its diagnostics any more but uses printf() as normal, saving the output into the diagnostics buffer, only printing to the screen using the direct print functions if a panic() occurs. . The multiboot code uses the flexible 'free memory map list' style to receive the list of free memory if available. . The kernel determines the memory layout of the processes to a degree: it tells VM where the kernel starts and ends and where the kernel wants the top of the process to be. VM then uses this entire range, i.e. the stack is right at the top, and mmap()ped bits of memory are placed below that downwards, and the break grows upwards. Other Consequences: . Every process gets its own page table as address spaces can't be separated any more by segments. . As all segments are 0-based, there is no distinction between virtual and linear addresses, nor between userspace and kernel addresses. . Less work is done when context switching, leading to a net performance increase. (8% faster on my machine for 'make servers'.) . The layout and configuration of the GDT makes sysenter and syscall possible.
199 lines
5.7 KiB
C
199 lines
5.7 KiB
C
/* The kernel call implemented in this file:
|
|
* m_type: SYS_TRACE
|
|
*
|
|
* The parameters for this kernel call are:
|
|
* m2_i1: CTL_ENDPT process that is traced
|
|
* m2_i2: CTL_REQUEST trace request
|
|
* m2_l1: CTL_ADDRESS address at traced process' space
|
|
* m2_l2: CTL_DATA data to be written or returned here
|
|
*/
|
|
|
|
#include "kernel/system.h"
|
|
#include <sys/ptrace.h>
|
|
|
|
#if USE_TRACE
|
|
|
|
/*==========================================================================*
|
|
* do_trace *
|
|
*==========================================================================*/
|
|
int do_trace(struct proc * caller, message * m_ptr)
|
|
{
|
|
/* Handle the debugging commands supported by the ptrace system call
|
|
* The commands are:
|
|
* T_STOP stop the process
|
|
* T_OK enable tracing by parent for this process
|
|
* T_GETINS return value from instruction space
|
|
* T_GETDATA return value from data space
|
|
* T_GETUSER return value from user process table
|
|
* T_SETINS set value in instruction space
|
|
* T_SETDATA set value in data space
|
|
* T_SETUSER set value in user process table
|
|
* T_RESUME resume execution
|
|
* T_EXIT exit
|
|
* T_STEP set trace bit
|
|
* T_SYSCALL trace system call
|
|
* T_ATTACH attach to an existing process
|
|
* T_DETACH detach from a traced process
|
|
* T_SETOPT set trace options
|
|
* T_GETRANGE get range of values
|
|
* T_SETRANGE set range of values
|
|
*
|
|
* The T_OK, T_ATTACH, T_EXIT, and T_SETOPT commands are handled completely by
|
|
* the process manager. T_GETRANGE and T_SETRANGE use sys_vircopy(). All others
|
|
* come here.
|
|
*/
|
|
|
|
register struct proc *rp;
|
|
vir_bytes tr_addr = (vir_bytes) m_ptr->CTL_ADDRESS;
|
|
long tr_data = m_ptr->CTL_DATA;
|
|
int tr_request = m_ptr->CTL_REQUEST;
|
|
int tr_proc_nr_e = m_ptr->CTL_ENDPT, tr_proc_nr;
|
|
unsigned char ub;
|
|
int i;
|
|
|
|
#define COPYTOPROC(addr, myaddr, length) { \
|
|
struct vir_addr fromaddr, toaddr; \
|
|
int r; \
|
|
fromaddr.proc_nr_e = KERNEL; \
|
|
toaddr.proc_nr_e = tr_proc_nr_e; \
|
|
fromaddr.offset = (myaddr); \
|
|
toaddr.offset = (addr); \
|
|
if((r=virtual_copy_vmcheck(caller, &fromaddr, \
|
|
&toaddr, length)) != OK) { \
|
|
printf("Can't copy in sys_trace: %d\n", r);\
|
|
return r;\
|
|
} \
|
|
}
|
|
|
|
#define COPYFROMPROC(addr, myaddr, length) { \
|
|
struct vir_addr fromaddr, toaddr; \
|
|
int r; \
|
|
fromaddr.proc_nr_e = tr_proc_nr_e; \
|
|
toaddr.proc_nr_e = KERNEL; \
|
|
fromaddr.offset = (addr); \
|
|
toaddr.offset = (myaddr); \
|
|
if((r=virtual_copy_vmcheck(caller, &fromaddr, \
|
|
&toaddr, length)) != OK) { \
|
|
printf("Can't copy in sys_trace: %d\n", r);\
|
|
return r;\
|
|
} \
|
|
}
|
|
|
|
if(!isokendpt(tr_proc_nr_e, &tr_proc_nr)) return(EINVAL);
|
|
if (iskerneln(tr_proc_nr)) return(EPERM);
|
|
|
|
rp = proc_addr(tr_proc_nr);
|
|
if (isemptyp(rp)) return(EINVAL);
|
|
switch (tr_request) {
|
|
case T_STOP: /* stop process */
|
|
RTS_SET(rp, RTS_P_STOP);
|
|
rp->p_reg.psw &= ~TRACEBIT; /* clear trace bit */
|
|
rp->p_misc_flags &= ~MF_SC_TRACE; /* clear syscall trace flag */
|
|
return(OK);
|
|
|
|
case T_GETINS: /* return value from instruction space */
|
|
COPYFROMPROC(tr_addr, (vir_bytes) &tr_data, sizeof(long));
|
|
m_ptr->CTL_DATA = tr_data;
|
|
break;
|
|
|
|
case T_GETDATA: /* return value from data space */
|
|
COPYFROMPROC(tr_addr, (vir_bytes) &tr_data, sizeof(long));
|
|
m_ptr->CTL_DATA= tr_data;
|
|
break;
|
|
|
|
case T_GETUSER: /* return value from process table */
|
|
if ((tr_addr & (sizeof(long) - 1)) != 0) return(EFAULT);
|
|
|
|
if (tr_addr <= sizeof(struct proc) - sizeof(long)) {
|
|
m_ptr->CTL_DATA = *(long *) ((char *) rp + (int) tr_addr);
|
|
break;
|
|
}
|
|
|
|
/* The process's proc struct is followed by its priv struct.
|
|
* The alignment here should be unnecessary, but better safe..
|
|
*/
|
|
i = sizeof(long) - 1;
|
|
tr_addr -= (sizeof(struct proc) + i) & ~i;
|
|
|
|
if (tr_addr > sizeof(struct priv) - sizeof(long)) return(EFAULT);
|
|
|
|
m_ptr->CTL_DATA = *(long *) ((char *) rp->p_priv + (int) tr_addr);
|
|
break;
|
|
|
|
case T_SETINS: /* set value in instruction space */
|
|
COPYTOPROC(tr_addr, (vir_bytes) &tr_data, sizeof(long));
|
|
m_ptr->CTL_DATA = 0;
|
|
break;
|
|
|
|
case T_SETDATA: /* set value in data space */
|
|
COPYTOPROC(tr_addr, (vir_bytes) &tr_data, sizeof(long));
|
|
m_ptr->CTL_DATA = 0;
|
|
break;
|
|
|
|
case T_SETUSER: /* set value in process table */
|
|
if ((tr_addr & (sizeof(reg_t) - 1)) != 0 ||
|
|
tr_addr > sizeof(struct stackframe_s) - sizeof(reg_t))
|
|
return(EFAULT);
|
|
i = (int) tr_addr;
|
|
#if (_MINIX_CHIP == _CHIP_INTEL)
|
|
/* Altering segment registers might crash the kernel when it
|
|
* tries to load them prior to restarting a process, so do
|
|
* not allow it.
|
|
*/
|
|
if (i == (int) &((struct proc *) 0)->p_reg.cs ||
|
|
i == (int) &((struct proc *) 0)->p_reg.ds ||
|
|
i == (int) &((struct proc *) 0)->p_reg.es ||
|
|
#if _WORD_SIZE == 4
|
|
i == (int) &((struct proc *) 0)->p_reg.gs ||
|
|
i == (int) &((struct proc *) 0)->p_reg.fs ||
|
|
#endif
|
|
i == (int) &((struct proc *) 0)->p_reg.ss)
|
|
return(EFAULT);
|
|
#endif
|
|
if (i == (int) &((struct proc *) 0)->p_reg.psw)
|
|
/* only selected bits are changeable */
|
|
SETPSW(rp, tr_data);
|
|
else
|
|
*(reg_t *) ((char *) &rp->p_reg + i) = (reg_t) tr_data;
|
|
m_ptr->CTL_DATA = 0;
|
|
break;
|
|
|
|
case T_DETACH: /* detach tracer */
|
|
rp->p_misc_flags &= ~MF_SC_ACTIVE;
|
|
|
|
/* fall through */
|
|
case T_RESUME: /* resume execution */
|
|
RTS_UNSET(rp, RTS_P_STOP);
|
|
m_ptr->CTL_DATA = 0;
|
|
break;
|
|
|
|
case T_STEP: /* set trace bit */
|
|
rp->p_reg.psw |= TRACEBIT;
|
|
RTS_UNSET(rp, RTS_P_STOP);
|
|
m_ptr->CTL_DATA = 0;
|
|
break;
|
|
|
|
case T_SYSCALL: /* trace system call */
|
|
rp->p_misc_flags |= MF_SC_TRACE;
|
|
RTS_UNSET(rp, RTS_P_STOP);
|
|
m_ptr->CTL_DATA = 0;
|
|
break;
|
|
|
|
case T_READB_INS: /* get value from instruction space */
|
|
COPYFROMPROC(tr_addr, (vir_bytes) &ub, 1);
|
|
m_ptr->CTL_DATA = ub;
|
|
break;
|
|
|
|
case T_WRITEB_INS: /* set value in instruction space */
|
|
ub = (unsigned char) (tr_data & 0xff);
|
|
COPYTOPROC(tr_addr, (vir_bytes) &ub, 1);
|
|
m_ptr->CTL_DATA = 0;
|
|
break;
|
|
|
|
default:
|
|
return(EINVAL);
|
|
}
|
|
return(OK);
|
|
}
|
|
|
|
#endif /* USE_TRACE */
|