OpenCloudOS-Kernel/arch/mips/kernel/ptrace.c

596 lines
14 KiB
C
Raw Normal View History

/*
* This file is subject to the terms and conditions of the GNU General Public
* License. See the file "COPYING" in the main directory of this archive
* for more details.
*
* Copyright (C) 1992 Ross Biro
* Copyright (C) Linus Torvalds
* Copyright (C) 1994, 95, 96, 97, 98, 2000 Ralf Baechle
* Copyright (C) 1996 David S. Miller
* Kevin D. Kissell, kevink@mips.com and Carsten Langgaard, carstenl@mips.com
* Copyright (C) 1999 MIPS Technologies, Inc.
* Copyright (C) 2000 Ulf Carlsson
*
* At this time Linux/MIPS64 only supports syscall tracing, even for 32-bit
* binaries.
*/
#include <linux/compiler.h>
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/mm.h>
#include <linux/errno.h>
#include <linux/ptrace.h>
#include <linux/smp.h>
#include <linux/user.h>
#include <linux/security.h>
#include <linux/audit.h>
#include <linux/seccomp.h>
#include <asm/byteorder.h>
#include <asm/cpu.h>
#include <asm/dsp.h>
#include <asm/fpu.h>
#include <asm/mipsregs.h>
#include <asm/mipsmtregs.h>
#include <asm/pgtable.h>
#include <asm/page.h>
#include <asm/uaccess.h>
#include <asm/bootinfo.h>
#include <asm/reg.h>
/*
* Called by kernel/ptrace.c when detaching..
*
* Make sure single step bits etc are not set.
*/
void ptrace_disable(struct task_struct *child)
{
/* Don't load the watchpoint registers for the ex-child. */
clear_tsk_thread_flag(child, TIF_LOAD_WATCH);
}
/*
* Read a general register set. We always use the 64-bit format, even
* for 32-bit kernels and for 32-bit processes on a 64-bit kernel.
* Registers are sign extended to fill the available space.
*/
int ptrace_getregs(struct task_struct *child, __s64 __user *data)
{
struct pt_regs *regs;
int i;
if (!access_ok(VERIFY_WRITE, data, 38 * 8))
return -EIO;
regs = task_pt_regs(child);
for (i = 0; i < 32; i++)
__put_user((long)regs->regs[i], data + i);
__put_user((long)regs->lo, data + EF_LO - EF_R0);
__put_user((long)regs->hi, data + EF_HI - EF_R0);
__put_user((long)regs->cp0_epc, data + EF_CP0_EPC - EF_R0);
__put_user((long)regs->cp0_badvaddr, data + EF_CP0_BADVADDR - EF_R0);
__put_user((long)regs->cp0_status, data + EF_CP0_STATUS - EF_R0);
__put_user((long)regs->cp0_cause, data + EF_CP0_CAUSE - EF_R0);
return 0;
}
/*
* Write a general register set. As for PTRACE_GETREGS, we always use
* the 64-bit format. On a 32-bit kernel only the lower order half
* (according to endianness) will be used.
*/
int ptrace_setregs(struct task_struct *child, __s64 __user *data)
{
struct pt_regs *regs;
int i;
if (!access_ok(VERIFY_READ, data, 38 * 8))
return -EIO;
regs = task_pt_regs(child);
for (i = 0; i < 32; i++)
__get_user(regs->regs[i], data + i);
__get_user(regs->lo, data + EF_LO - EF_R0);
__get_user(regs->hi, data + EF_HI - EF_R0);
__get_user(regs->cp0_epc, data + EF_CP0_EPC - EF_R0);
/* badvaddr, status, and cause may not be written. */
return 0;
}
int ptrace_getfpregs(struct task_struct *child, __u32 __user *data)
{
int i;
unsigned int tmp;
if (!access_ok(VERIFY_WRITE, data, 33 * 8))
return -EIO;
if (tsk_used_math(child)) {
fpureg_t *fregs = get_fpu_regs(child);
for (i = 0; i < 32; i++)
__put_user(fregs[i], i + (__u64 __user *) data);
} else {
for (i = 0; i < 32; i++)
__put_user((__u64) -1, i + (__u64 __user *) data);
}
__put_user(child->thread.fpu.fcr31, data + 64);
preempt_disable();
if (cpu_has_fpu) {
unsigned int flags;
if (cpu_has_mipsmt) {
unsigned int vpflags = dvpe();
flags = read_c0_status();
__enable_fpu();
__asm__ __volatile__("cfc1\t%0,$0" : "=r" (tmp));
write_c0_status(flags);
evpe(vpflags);
} else {
flags = read_c0_status();
__enable_fpu();
__asm__ __volatile__("cfc1\t%0,$0" : "=r" (tmp));
write_c0_status(flags);
}
} else {
tmp = 0;
}
preempt_enable();
__put_user(tmp, data + 65);
return 0;
}
int ptrace_setfpregs(struct task_struct *child, __u32 __user *data)
{
fpureg_t *fregs;
int i;
if (!access_ok(VERIFY_READ, data, 33 * 8))
return -EIO;
fregs = get_fpu_regs(child);
for (i = 0; i < 32; i++)
__get_user(fregs[i], i + (__u64 __user *) data);
__get_user(child->thread.fpu.fcr31, data + 64);
/* FIR may not be written. */
return 0;
}
int ptrace_get_watch_regs(struct task_struct *child,
struct pt_watch_regs __user *addr)
{
enum pt_watch_style style;
int i;
if (!cpu_has_watch || current_cpu_data.watch_reg_use_cnt == 0)
return -EIO;
if (!access_ok(VERIFY_WRITE, addr, sizeof(struct pt_watch_regs)))
return -EIO;
#ifdef CONFIG_32BIT
style = pt_watch_style_mips32;
#define WATCH_STYLE mips32
#else
style = pt_watch_style_mips64;
#define WATCH_STYLE mips64
#endif
__put_user(style, &addr->style);
__put_user(current_cpu_data.watch_reg_use_cnt,
&addr->WATCH_STYLE.num_valid);
for (i = 0; i < current_cpu_data.watch_reg_use_cnt; i++) {
__put_user(child->thread.watch.mips3264.watchlo[i],
&addr->WATCH_STYLE.watchlo[i]);
__put_user(child->thread.watch.mips3264.watchhi[i] & 0xfff,
&addr->WATCH_STYLE.watchhi[i]);
__put_user(current_cpu_data.watch_reg_masks[i],
&addr->WATCH_STYLE.watch_masks[i]);
}
for (; i < 8; i++) {
__put_user(0, &addr->WATCH_STYLE.watchlo[i]);
__put_user(0, &addr->WATCH_STYLE.watchhi[i]);
__put_user(0, &addr->WATCH_STYLE.watch_masks[i]);
}
return 0;
}
int ptrace_set_watch_regs(struct task_struct *child,
struct pt_watch_regs __user *addr)
{
int i;
int watch_active = 0;
unsigned long lt[NUM_WATCH_REGS];
u16 ht[NUM_WATCH_REGS];
if (!cpu_has_watch || current_cpu_data.watch_reg_use_cnt == 0)
return -EIO;
if (!access_ok(VERIFY_READ, addr, sizeof(struct pt_watch_regs)))
return -EIO;
/* Check the values. */
for (i = 0; i < current_cpu_data.watch_reg_use_cnt; i++) {
__get_user(lt[i], &addr->WATCH_STYLE.watchlo[i]);
#ifdef CONFIG_32BIT
if (lt[i] & __UA_LIMIT)
return -EINVAL;
#else
if (test_tsk_thread_flag(child, TIF_32BIT_ADDR)) {
if (lt[i] & 0xffffffff80000000UL)
return -EINVAL;
} else {
if (lt[i] & __UA_LIMIT)
return -EINVAL;
}
#endif
__get_user(ht[i], &addr->WATCH_STYLE.watchhi[i]);
if (ht[i] & ~0xff8)
return -EINVAL;
}
/* Install them. */
for (i = 0; i < current_cpu_data.watch_reg_use_cnt; i++) {
if (lt[i] & 7)
watch_active = 1;
child->thread.watch.mips3264.watchlo[i] = lt[i];
/* Set the G bit. */
child->thread.watch.mips3264.watchhi[i] = ht[i];
}
if (watch_active)
set_tsk_thread_flag(child, TIF_LOAD_WATCH);
else
clear_tsk_thread_flag(child, TIF_LOAD_WATCH);
return 0;
}
long arch_ptrace(struct task_struct *child, long request,
unsigned long addr, unsigned long data)
{
int ret;
void __user *addrp = (void __user *) addr;
void __user *datavp = (void __user *) data;
unsigned long __user *datalp = (void __user *) data;
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:
ret = generic_ptrace_peekdata(child, addr, data);
break;
/* Read the word at location addr in the USER area. */
case PTRACE_PEEKUSR: {
struct pt_regs *regs;
unsigned long tmp = 0;
regs = task_pt_regs(child);
ret = 0; /* Default return value. */
switch (addr) {
case 0 ... 31:
tmp = regs->regs[addr];
break;
case FPR_BASE ... FPR_BASE + 31:
if (tsk_used_math(child)) {
fpureg_t *fregs = get_fpu_regs(child);
#ifdef CONFIG_32BIT
/*
* The odd registers are actually the high
* order bits of the values stored in the even
* registers - unless we're using r2k_switch.S.
*/
if (addr & 1)
tmp = (unsigned long) (fregs[((addr & ~1) - 32)] >> 32);
else
tmp = (unsigned long) (fregs[(addr - 32)] & 0xffffffff);
#endif
#ifdef CONFIG_64BIT
tmp = fregs[addr - FPR_BASE];
#endif
} else {
tmp = -1; /* FP not yet used */
}
break;
case PC:
tmp = regs->cp0_epc;
break;
case CAUSE:
tmp = regs->cp0_cause;
break;
case BADVADDR:
tmp = regs->cp0_badvaddr;
break;
case MMHI:
tmp = regs->hi;
break;
case MMLO:
tmp = regs->lo;
break;
#ifdef CONFIG_CPU_HAS_SMARTMIPS
case ACX:
tmp = regs->acx;
break;
#endif
case FPC_CSR:
tmp = child->thread.fpu.fcr31;
break;
case FPC_EIR: { /* implementation / version register */
unsigned int flags;
#ifdef CONFIG_MIPS_MT_SMTC
unsigned long irqflags;
unsigned int mtflags;
#endif /* CONFIG_MIPS_MT_SMTC */
preempt_disable();
if (!cpu_has_fpu) {
preempt_enable();
break;
}
#ifdef CONFIG_MIPS_MT_SMTC
/* Read-modify-write of Status must be atomic */
local_irq_save(irqflags);
mtflags = dmt();
#endif /* CONFIG_MIPS_MT_SMTC */
if (cpu_has_mipsmt) {
unsigned int vpflags = dvpe();
flags = read_c0_status();
__enable_fpu();
__asm__ __volatile__("cfc1\t%0,$0": "=r" (tmp));
write_c0_status(flags);
evpe(vpflags);
} else {
flags = read_c0_status();
__enable_fpu();
__asm__ __volatile__("cfc1\t%0,$0": "=r" (tmp));
write_c0_status(flags);
}
#ifdef CONFIG_MIPS_MT_SMTC
emt(mtflags);
local_irq_restore(irqflags);
#endif /* CONFIG_MIPS_MT_SMTC */
preempt_enable();
break;
}
case DSP_BASE ... DSP_BASE + 5: {
dspreg_t *dregs;
if (!cpu_has_dsp) {
tmp = 0;
ret = -EIO;
goto out;
}
dregs = __get_dsp_regs(child);
tmp = (unsigned long) (dregs[addr - DSP_BASE]);
break;
}
case DSP_CONTROL:
if (!cpu_has_dsp) {
tmp = 0;
ret = -EIO;
goto out;
}
tmp = child->thread.dsp.dspcontrol;
break;
default:
tmp = 0;
ret = -EIO;
goto out;
}
ret = put_user(tmp, datalp);
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 = generic_ptrace_pokedata(child, addr, data);
break;
case PTRACE_POKEUSR: {
struct pt_regs *regs;
ret = 0;
regs = task_pt_regs(child);
switch (addr) {
case 0 ... 31:
regs->regs[addr] = data;
break;
case FPR_BASE ... FPR_BASE + 31: {
fpureg_t *fregs = get_fpu_regs(child);
if (!tsk_used_math(child)) {
/* FP not yet used */
memset(&child->thread.fpu, ~0,
sizeof(child->thread.fpu));
child->thread.fpu.fcr31 = 0;
}
#ifdef CONFIG_32BIT
/*
* The odd registers are actually the high order bits
* of the values stored in the even registers - unless
* we're using r2k_switch.S.
*/
if (addr & 1) {
fregs[(addr & ~1) - FPR_BASE] &= 0xffffffff;
fregs[(addr & ~1) - FPR_BASE] |= ((unsigned long long) data) << 32;
} else {
fregs[addr - FPR_BASE] &= ~0xffffffffLL;
fregs[addr - FPR_BASE] |= data;
}
#endif
#ifdef CONFIG_64BIT
fregs[addr - FPR_BASE] = data;
#endif
break;
}
case PC:
regs->cp0_epc = data;
break;
case MMHI:
regs->hi = data;
break;
case MMLO:
regs->lo = data;
break;
#ifdef CONFIG_CPU_HAS_SMARTMIPS
case ACX:
regs->acx = data;
break;
#endif
case FPC_CSR:
child->thread.fpu.fcr31 = data;
break;
case DSP_BASE ... DSP_BASE + 5: {
dspreg_t *dregs;
if (!cpu_has_dsp) {
ret = -EIO;
break;
}
dregs = __get_dsp_regs(child);
dregs[addr - DSP_BASE] = data;
break;
}
case DSP_CONTROL:
if (!cpu_has_dsp) {
ret = -EIO;
break;
}
child->thread.dsp.dspcontrol = data;
break;
default:
/* The rest are not allowed. */
ret = -EIO;
break;
}
break;
}
case PTRACE_GETREGS:
ret = ptrace_getregs(child, datavp);
break;
case PTRACE_SETREGS:
ret = ptrace_setregs(child, datavp);
break;
case PTRACE_GETFPREGS:
ret = ptrace_getfpregs(child, datavp);
break;
case PTRACE_SETFPREGS:
ret = ptrace_setfpregs(child, datavp);
break;
case PTRACE_GET_THREAD_AREA:
ret = put_user(task_thread_info(child)->tp_value, datalp);
break;
case PTRACE_GET_WATCH_REGS:
ret = ptrace_get_watch_regs(child, addrp);
break;
case PTRACE_SET_WATCH_REGS:
ret = ptrace_set_watch_regs(child, addrp);
break;
default:
ret = ptrace_request(child, request, addr, data);
break;
}
out:
return ret;
}
static inline int audit_arch(void)
{
int arch = EM_MIPS;
#ifdef CONFIG_64BIT
arch |= __AUDIT_ARCH_64BIT;
#endif
#if defined(__LITTLE_ENDIAN)
arch |= __AUDIT_ARCH_LE;
#endif
return arch;
}
/*
* Notification of system call entry/exit
* - triggered by current->work.syscall_trace
*/
asmlinkage void syscall_trace_enter(struct pt_regs *regs)
{
/* do the secure computing check first */
secure_computing_strict(regs->regs[2]);
if (!(current->ptrace & PT_PTRACED))
goto out;
if (!test_thread_flag(TIF_SYSCALL_TRACE))
goto out;
/* The 0x80 provides a way for the tracing parent to distinguish
between a syscall stop and SIGTRAP delivery */
ptrace_notify(SIGTRAP | ((current->ptrace & PT_TRACESYSGOOD) ?
0x80 : 0));
/*
* 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;
}
out:
audit_syscall_entry(audit_arch(), regs->regs[2],
regs->regs[4], regs->regs[5],
regs->regs[6], regs->regs[7]);
}
/*
* Notification of system call entry/exit
* - triggered by current->work.syscall_trace
*/
asmlinkage void syscall_trace_leave(struct pt_regs *regs)
{
Audit: push audit success and retcode into arch ptrace.h The audit system previously expected arches calling to audit_syscall_exit to supply as arguments if the syscall was a success and what the return code was. Audit also provides a helper AUDITSC_RESULT which was supposed to simplify things by converting from negative retcodes to an audit internal magic value stating success or failure. This helper was wrong and could indicate that a valid pointer returned to userspace was a failed syscall. The fix is to fix the layering foolishness. We now pass audit_syscall_exit a struct pt_reg and it in turns calls back into arch code to collect the return value and to determine if the syscall was a success or failure. We also define a generic is_syscall_success() macro which determines success/failure based on if the value is < -MAX_ERRNO. This works for arches like x86 which do not use a separate mechanism to indicate syscall failure. We make both the is_syscall_success() and regs_return_value() static inlines instead of macros. The reason is because the audit function must take a void* for the regs. (uml calls theirs struct uml_pt_regs instead of just struct pt_regs so audit_syscall_exit can't take a struct pt_regs). Since the audit function takes a void* we need to use static inlines to cast it back to the arch correct structure to dereference it. The other major change is that on some arches, like ia64, MIPS and ppc, we change regs_return_value() to give us the negative value on syscall failure. THE only other user of this macro, kretprobe_example.c, won't notice and it makes the value signed consistently for the audit functions across all archs. In arch/sh/kernel/ptrace_64.c I see that we were using regs[9] in the old audit code as the return value. But the ptrace_64.h code defined the macro regs_return_value() as regs[3]. I have no idea which one is correct, but this patch now uses the regs_return_value() function, so it now uses regs[3]. For powerpc we previously used regs->result but now use the regs_return_value() function which uses regs->gprs[3]. regs->gprs[3] is always positive so the regs_return_value(), much like ia64 makes it negative before calling the audit code when appropriate. Signed-off-by: Eric Paris <eparis@redhat.com> Acked-by: H. Peter Anvin <hpa@zytor.com> [for x86 portion] Acked-by: Tony Luck <tony.luck@intel.com> [for ia64] Acked-by: Richard Weinberger <richard@nod.at> [for uml] Acked-by: David S. Miller <davem@davemloft.net> [for sparc] Acked-by: Ralf Baechle <ralf@linux-mips.org> [for mips] Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> [for ppc]
2012-01-04 03:23:06 +08:00
audit_syscall_exit(regs);
if (!(current->ptrace & PT_PTRACED))
return;
if (!test_thread_flag(TIF_SYSCALL_TRACE))
return;
/* The 0x80 provides a way for the tracing parent to distinguish
between a syscall stop and SIGTRAP delivery */
ptrace_notify(SIGTRAP | ((current->ptrace & PT_TRACESYSGOOD) ?
0x80 : 0));
/*
* 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;
}
}