#include <linux/user.h>
#include <linux/security.h>
#include <linux/audit.h>
+#include <linux/seccomp.h>
+#include <linux/signal.h>
#include <asm/uaccess.h>
#include <asm/pgtable.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), IOPL(12-13), IF(9).
+ * Also masks reserved bits (31-22, 15, 5, 3, 1).
+ */
+#define FLAG_MASK 0x00054dd5
/* set's the trap flag. */
#define TRAP_FLAG 0x100
*/
#define EFL_OFFSET ((EFL-2)*4-sizeof(struct pt_regs))
+static inline struct pt_regs *get_child_regs(struct task_struct *task)
+{
+ void *stack_top = (void *)task->thread.esp0;
+ return stack_top - 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.
return retval;
}
+#define LDT_SEGMENT 4
+
+static unsigned long convert_eip_to_linear(struct task_struct *child, struct pt_regs *regs)
+{
+ unsigned long addr, seg;
+
+ addr = regs->eip;
+ seg = regs->xcs & 0xffff;
+ if (regs->eflags & VM_MASK) {
+ addr = (addr & 0xffff) + (seg << 4);
+ return addr;
+ }
+
+ /*
+ * We'll assume that the code segments in the GDT
+ * are all zero-based. That is largely true: the
+ * TLS segments are used for data, and the PNPBIOS
+ * and APM bios ones we just ignore here.
+ */
+ if (seg & LDT_SEGMENT) {
+ u32 *desc;
+ unsigned long base;
+
+ down(&child->mm->context.sem);
+ desc = child->mm->context.ldt + (seg & ~7);
+ base = (desc[0] >> 16) | ((desc[1] & 0xff) << 16) | (desc[1] & 0xff000000);
+
+ /* 16-bit code segment? */
+ if (!((desc[1] >> 22) & 1))
+ addr &= 0xffff;
+ addr += base;
+ up(&child->mm->context.sem);
+ }
+ return addr;
+}
+
+static inline int is_at_popf(struct task_struct *child, struct pt_regs *regs)
+{
+ int i, copied;
+ unsigned char opcode[16];
+ 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:
+ return 1;
+ /* opcode and address size prefixes */
+ case 0x66: case 0x67:
+ continue;
+ /* irrelevant prefixes (segment overrides and repeats) */
+ case 0x26: case 0x2e:
+ case 0x36: case 0x3e:
+ case 0x64: case 0x65:
+ case 0xf0: case 0xf2: case 0xf3:
+ continue;
+
+ /*
+ * pushf: NOTE! We should probably not let
+ * the user see the TF bit being set. But
+ * it's more pain than it's worth to avoid
+ * it, and a debugger could emulate this
+ * all in user space if it _really_ cares.
+ */
+ case 0x9c:
+ default:
+ return 0;
+ }
+ }
+ return 0;
+}
+
static void set_singlestep(struct task_struct *child)
{
- long eflags;
+ struct pt_regs *regs = get_child_regs(child);
+ /*
+ * Always set TIF_SINGLESTEP - this guarantees that
+ * we single-step system calls etc.. This will also
+ * cause us to set TF when returning to user mode.
+ */
set_tsk_thread_flag(child, TIF_SINGLESTEP);
- eflags = get_stack_long(child, EFL_OFFSET);
- put_stack_long(child, EFL_OFFSET, eflags | TRAP_FLAG);
+
+ /*
+ * If TF was already set, don't do anything else
+ */
+ if (regs->eflags & TRAP_FLAG)
+ return;
+
+ /* Set TF on the kernel stack.. */
+ regs->eflags |= TRAP_FLAG;
+
+ /*
+ * ..but if TF is changed by the instruction we will trace,
+ * 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))
+ return;
+
child->ptrace |= PT_DTRACE;
}
static void clear_singlestep(struct task_struct *child)
{
- if (child->ptrace & PT_DTRACE) {
- long eflags;
+ /* Always clear TIF_SINGLESTEP... */
+ clear_tsk_thread_flag(child, TIF_SINGLESTEP);
- clear_tsk_thread_flag(child, TIF_SINGLESTEP);
- eflags = get_stack_long(child, EFL_OFFSET);
- put_stack_long(child, EFL_OFFSET, eflags & ~TRAP_FLAG);
+ /* But touch TF only if it was set by us.. */
+ if (child->ptrace & PT_DTRACE) {
+ struct pt_regs *regs = get_child_regs(child);
+ regs->eflags &= ~TRAP_FLAG;
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;
- if (!vx_check(vx_task_xid(child), VX_WATCH|VX_IDENT))
- goto out_tsk;
-
- 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. */
}
break;
+ case PTRACE_SYSEMU: /* continue and stop at next syscall, which will not be executed */
case PTRACE_SYSCALL: /* continue and stop at next (return from) syscall */
case PTRACE_CONT: /* restart after signal. */
ret = -EIO;
- if ((unsigned long) data > _NSIG)
+ if (!valid_signal(data))
break;
- if (request == PTRACE_SYSCALL) {
+ if (request == PTRACE_SYSEMU) {
+ set_tsk_thread_flag(child, TIF_SYSCALL_EMU);
+ clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
+ } else if (request == PTRACE_SYSCALL) {
set_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
- }
- else {
+ clear_tsk_thread_flag(child, TIF_SYSCALL_EMU);
+ } else {
+ clear_tsk_thread_flag(child, TIF_SYSCALL_EMU);
clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
}
child->exit_code = data;
wake_up_process(child);
break;
+ case PTRACE_SYSEMU_SINGLESTEP: /* Same as SYSEMU, but singlestep if not syscall */
case PTRACE_SINGLESTEP: /* set the trap flag. */
ret = -EIO;
- if ((unsigned long) data > _NSIG)
+ if (!valid_signal(data))
break;
+
+ if (request == PTRACE_SYSEMU_SINGLESTEP)
+ set_tsk_thread_flag(child, TIF_SYSCALL_EMU);
+ else
+ clear_tsk_thread_flag(child, TIF_SYSCALL_EMU);
+
clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
set_singlestep(child);
child->exit_code = data;
break;
}
ret = 0;
- if (!child->used_math)
+ if (!tsk_used_math(child))
init_fpu(child);
get_fpregs((struct user_i387_struct __user *)data, child);
break;
ret = -EIO;
break;
}
- child->used_math = 1;
+ set_stopped_child_used_math(child);
set_fpregs(child, (struct user_i387_struct __user *)data);
ret = 0;
break;
ret = -EIO;
break;
}
- if (!child->used_math)
+ if (!tsk_used_math(child))
init_fpu(child);
ret = get_fpxregs((struct user_fxsr_struct __user *)data, child);
break;
ret = -EIO;
break;
}
- child->used_math = 1;
+ set_stopped_child_used_math(child);
ret = set_fpxregs(child, (struct user_fxsr_struct __user *)data);
break;
}
ret = ptrace_request(child, request, addr, data);
break;
}
-out_tsk:
- put_task_struct(child);
-out:
- unlock_kernel();
+ out_tsk:
return ret;
}
+void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs, int error_code)
+{
+ struct siginfo info;
+
+ tsk->thread.trap_no = 1;
+ tsk->thread.error_code = error_code;
+
+ memset(&info, 0, sizeof(info));
+ info.si_signo = SIGTRAP;
+ info.si_code = TRAP_BRKPT;
+
+ /* User-mode eip? */
+ info.si_addr = user_mode_vm(regs) ? (void __user *) regs->eip : NULL;
+
+ /* Send us the fakey SIGTRAP */
+ force_sig_info(SIGTRAP, &info, tsk);
+}
+
/* notification of system call entry/exit
* - triggered by current->work.syscall_trace
*/
__attribute__((regparm(3)))
-void do_syscall_trace(struct pt_regs *regs, int entryexit)
+int do_syscall_trace(struct pt_regs *regs, int entryexit)
{
+ 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 */
+ if (!entryexit)
+ secure_computing(regs->orig_eax);
+
if (unlikely(current->audit_context)) {
- if (!entryexit)
- audit_syscall_entry(current, regs->orig_eax,
- regs->ebx, regs->ecx,
- regs->edx, regs->esi);
- else
- audit_syscall_exit(current, regs->eax);
+ if (entryexit)
+ audit_syscall_exit(current, 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 (!test_thread_flag(TIF_SYSCALL_TRACE) &&
- !test_thread_flag(TIF_SINGLESTEP))
- return;
if (!(current->ptrace & PT_PTRACED))
- return;
+ goto out;
+
+ /* If a process stops on the 1st tracepoint with SYSCALL_TRACE
+ * and then is resumed with SYSEMU_SINGLESTEP, it will come in
+ * here. We have to check this and return */
+ if (is_sysemu && entryexit)
+ return 0;
+
+ /* Fake a debug trap */
+ if (is_singlestep)
+ send_sigtrap(current, regs, 0);
+
+ if (!test_thread_flag(TIF_SYSCALL_TRACE) && !is_sysemu)
+ 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) &&
- !test_thread_flag(TIF_SINGLESTEP) ? 0x80 : 0));
+ /* Note that the debugger could change the result of test_thread_flag!*/
+ ptrace_notify(SIGTRAP | ((current->ptrace & PT_TRACESYSGOOD) ? 0x80:0));
/*
* this isn't the same as continuing with a signal, but it will do
send_sig(current->exit_code, current, 1);
current->exit_code = 0;
}
+ ret = is_sysemu;
+out:
+ if (unlikely(current->audit_context) && !entryexit)
+ audit_syscall_entry(current, 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);
+ return 1;
}
git://git.onelab.eu / linux-2.6.git / blobdiff