#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>
* in exit.c or in signal.c.
*/
-/* determines which flags the user has access to. */
-/* 1 = access 0 = no access */
-#define FLAG_MASK 0x00044dd5
+/*
+ * Determines which flags the user has access to [1 = access, 0 = no access].
+ * Prohibits changing ID(21), VIP(20), VIF(19), VM(17), NT(14), IOPL(12-13), IF(9).
+ * Also masks reserved bits (31-22, 15, 5, 3, 1).
+ */
+#define FLAG_MASK 0x00050dd5
/* 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))
+#define EFL_OFFSET offsetof(struct pt_regs, eflags)
static inline struct pt_regs *get_child_regs(struct task_struct *task)
{
}
/*
- * 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
+ * This routine will get a word off of the processes privileged stack.
+ * the offset is bytes into the pt_regs structure on the stack.
+ * 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 = (unsigned char *)task->thread.esp0 - sizeof(struct pt_regs);
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
+ * This routine will put a word on the processes privileged stack.
+ * the offset is bytes into the pt_regs structure on the stack.
+ * 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 char * stack;
- stack = (unsigned char *) task->thread.esp0;
+ stack = (unsigned char *)task->thread.esp0 - sizeof(struct pt_regs);
stack += offset;
*(unsigned long *) stack = data;
return 0;
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;
return 0;
case DS:
case ES:
+ case FS:
if (value && (value & 3) != 3)
return -EIO;
value &= 0xffff;
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);
+ if (regno > FS*4)
+ regno -= 1*4;
+ put_stack_long(child, regno, value);
return 0;
}
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 FS:
case SS:
case CS:
retval = 0xffff;
/* fall through */
default:
- if (regno > GS*4)
- regno -= 2*4;
- regno = regno - sizeof(struct pt_regs);
+ if (regno > FS*4)
+ regno -= 1*4;
retval &= get_stack_long(child, regno);
}
return retval;
return addr;
}
-static inline int is_at_popf(struct task_struct *child, struct pt_regs *regs)
+static inline int is_setting_trap_flag(struct task_struct *child, struct pt_regs *regs)
{
int i, copied;
- unsigned char opcode[16];
+ unsigned char opcode[15];
unsigned long addr = convert_eip_to_linear(child, regs);
copied = access_process_vm(child, addr, opcode, sizeof(opcode), 0);
for (i = 0; i < copied; i++) {
switch (opcode[i]) {
- /* popf */
- case 0x9d:
+ /* popf and iret */
+ case 0x9d: case 0xcf:
return 1;
/* opcode and address size prefixes */
case 0x66: case 0x67:
* don't mark it as being "us" that set it, so that we
* won't clear it by hand later.
*/
- if (is_at_popf(child, regs))
+ if (is_setting_trap_flag(child, regs))
return;
child->ptrace |= PT_DTRACE;
void ptrace_disable(struct task_struct *child)
{
clear_singlestep(child);
+ clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
+ clear_tsk_thread_flag(child, TIF_SYSCALL_EMU);
}
/*
return 0;
}
-asmlinkage int sys_ptrace(long request, long pid, long addr, long data)
+long arch_ptrace(struct task_struct *child, long request, long addr, long data)
{
- struct task_struct *child;
struct user * dummy = NULL;
int i, ret;
unsigned long __user *datap = (unsigned long __user *)data;
- lock_kernel();
- ret = -EPERM;
- if (request == PTRACE_TRACEME) {
- /* are we already being traced? */
- if (current->ptrace & PT_PTRACED)
- goto out;
- ret = security_ptrace(current->parent, current);
- if (ret)
- 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, datap);
+ case PTRACE_PEEKDATA:
+ ret = generic_ptrace_peekdata(child, addr, data);
break;
- }
/* read the word at location addr in the USER area. */
case PTRACE_PEEKUSR: {
/* 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;
+ ret = generic_ptrace_pokedata(child, addr, data);
break;
case PTRACE_POKEUSR: /* write the word at location addr in the USER area */
for(i=0; i<4; i++)
if ((0x5f54 >> ((data >> (16 + 4*i)) & 0xf)) & 1)
goto out_tsk;
+ if (data)
+ set_tsk_thread_flag(child, TIF_DEBUG);
+ else
+ clear_tsk_thread_flag(child, TIF_DEBUG);
}
-
addr -= (long) &dummy->u_debugreg;
addr = addr >> 2;
child->thread.debugreg[addr] = data;
ret = ptrace_request(child, request, addr, data);
break;
}
-out_tsk:
- put_task_struct(child);
-out:
- unlock_kernel();
+ out_tsk:
return ret;
}
__attribute__((regparm(3)))
int do_syscall_trace(struct pt_regs *regs, int entryexit)
{
- int is_sysemu = test_thread_flag(TIF_SYSCALL_EMU), ret = 0;
- /* With TIF_SYSCALL_EMU set we want to ignore TIF_SINGLESTEP */
+ int is_sysemu = test_thread_flag(TIF_SYSCALL_EMU);
+ /*
+ * With TIF_SYSCALL_EMU set we want to ignore TIF_SINGLESTEP for syscall
+ * interception
+ */
int is_singlestep = !is_sysemu && test_thread_flag(TIF_SINGLESTEP);
+ int ret = 0;
/* do the secure computing check first */
- secure_computing(regs->orig_eax);
-
- if (unlikely(current->audit_context) && entryexit)
- audit_syscall_exit(current, AUDITSC_RESULT(regs->eax), regs->eax);
+ if (!entryexit)
+ secure_computing(regs->orig_eax);
+
+ if (unlikely(current->audit_context)) {
+ if (entryexit)
+ audit_syscall_exit(AUDITSC_RESULT(regs->eax),
+ regs->eax);
+ /* Debug traps, when using PTRACE_SINGLESTEP, must be sent only
+ * on the syscall exit path. Normally, when TIF_SYSCALL_AUDIT is
+ * not used, entry.S will call us only on syscall exit, not
+ * entry; so when TIF_SYSCALL_AUDIT is used we must avoid
+ * calling send_sigtrap() on syscall entry.
+ *
+ * Note that when PTRACE_SYSEMU_SINGLESTEP is used,
+ * is_singlestep is false, despite his name, so we will still do
+ * the correct thing.
+ */
+ else if (is_singlestep)
+ goto out;
+ }
if (!(current->ptrace & PT_PTRACED))
goto out;
/* the 0x80 provides a way for the tracing parent to distinguish
between a syscall stop and SIGTRAP delivery */
/* Note that the debugger could change the result of test_thread_flag!*/
- ptrace_notify(SIGTRAP | ((current->ptrace & PT_TRACESYSGOOD) ? 0x80 : 0));
+ ptrace_notify(SIGTRAP | ((current->ptrace & PT_TRACESYSGOOD) ? 0x80:0));
/*
* this isn't the same as continuing with a signal, but it will do
current->exit_code = 0;
}
ret = is_sysemu;
- out:
+out:
if (unlikely(current->audit_context) && !entryexit)
- audit_syscall_entry(current, AUDIT_ARCH_I386, regs->orig_eax,
+ audit_syscall_entry(AUDIT_ARCH_I386, regs->orig_eax,
regs->ebx, regs->ecx, regs->edx, regs->esi);
if (ret == 0)
return 0;
regs->orig_eax = -1; /* force skip of syscall restarting */
if (unlikely(current->audit_context))
- audit_syscall_exit(current, AUDITSC_RESULT(regs->eax), regs->eax);
+ audit_syscall_exit(AUDITSC_RESULT(regs->eax), regs->eax);
return 1;
}