linux_dsm_epyc7002/arch/um/kernel/ptrace.c
Eric Paris d7e7528bcd 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]
2012-01-17 16:16:56 -05:00

212 lines
4.7 KiB
C

/*
* Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
* Licensed under the GPL
*/
#include "linux/audit.h"
#include "linux/ptrace.h"
#include "linux/sched.h"
#include "asm/uaccess.h"
#include "skas_ptrace.h"
void user_enable_single_step(struct task_struct *child)
{
child->ptrace |= PT_DTRACE;
child->thread.singlestep_syscall = 0;
#ifdef SUBARCH_SET_SINGLESTEPPING
SUBARCH_SET_SINGLESTEPPING(child, 1);
#endif
}
void user_disable_single_step(struct task_struct *child)
{
child->ptrace &= ~PT_DTRACE;
child->thread.singlestep_syscall = 0;
#ifdef SUBARCH_SET_SINGLESTEPPING
SUBARCH_SET_SINGLESTEPPING(child, 0);
#endif
}
/*
* Called by kernel/ptrace.c when detaching..
*/
void ptrace_disable(struct task_struct *child)
{
user_disable_single_step(child);
}
extern int peek_user(struct task_struct * child, long addr, long data);
extern int poke_user(struct task_struct * child, long addr, long data);
long arch_ptrace(struct task_struct *child, long request,
unsigned long addr, unsigned long data)
{
int i, ret;
unsigned long __user *p = (void __user *)data;
void __user *vp = p;
switch (request) {
/* read the word at location addr in the USER area. */
case PTRACE_PEEKUSR:
ret = peek_user(child, addr, data);
break;
/* write the word at location addr in the USER area */
case PTRACE_POKEUSR:
ret = poke_user(child, addr, data);
break;
case PTRACE_SYSEMU:
case PTRACE_SYSEMU_SINGLESTEP:
ret = -EIO;
break;
#ifdef PTRACE_GETREGS
case PTRACE_GETREGS: { /* Get all gp regs from the child. */
if (!access_ok(VERIFY_WRITE, p, MAX_REG_OFFSET)) {
ret = -EIO;
break;
}
for ( i = 0; i < MAX_REG_OFFSET; i += sizeof(long) ) {
__put_user(getreg(child, i), p);
p++;
}
ret = 0;
break;
}
#endif
#ifdef PTRACE_SETREGS
case PTRACE_SETREGS: { /* Set all gp regs in the child. */
unsigned long tmp = 0;
if (!access_ok(VERIFY_READ, p, MAX_REG_OFFSET)) {
ret = -EIO;
break;
}
for ( i = 0; i < MAX_REG_OFFSET; i += sizeof(long) ) {
__get_user(tmp, p);
putreg(child, i, tmp);
p++;
}
ret = 0;
break;
}
#endif
case PTRACE_GET_THREAD_AREA:
ret = ptrace_get_thread_area(child, addr, vp);
break;
case PTRACE_SET_THREAD_AREA:
ret = ptrace_set_thread_area(child, addr, vp);
break;
case PTRACE_FAULTINFO: {
/*
* Take the info from thread->arch->faultinfo,
* but transfer max. sizeof(struct ptrace_faultinfo).
* On i386, ptrace_faultinfo is smaller!
*/
ret = copy_to_user(p, &child->thread.arch.faultinfo,
sizeof(struct ptrace_faultinfo)) ?
-EIO : 0;
break;
}
#ifdef PTRACE_LDT
case PTRACE_LDT: {
struct ptrace_ldt ldt;
if (copy_from_user(&ldt, p, sizeof(ldt))) {
ret = -EIO;
break;
}
/*
* This one is confusing, so just punt and return -EIO for
* now
*/
ret = -EIO;
break;
}
#endif
default:
ret = ptrace_request(child, request, addr, data);
if (ret == -EIO)
ret = subarch_ptrace(child, request, addr, data);
break;
}
return ret;
}
static void send_sigtrap(struct task_struct *tsk, struct uml_pt_regs *regs,
int error_code)
{
struct siginfo info;
memset(&info, 0, sizeof(info));
info.si_signo = SIGTRAP;
info.si_code = TRAP_BRKPT;
/* User-mode eip? */
info.si_addr = UPT_IS_USER(regs) ? (void __user *) UPT_IP(regs) : NULL;
/* Send us the fake SIGTRAP */
force_sig_info(SIGTRAP, &info, tsk);
}
/*
* XXX Check PT_DTRACE vs TIF_SINGLESTEP for singlestepping check and
* PT_PTRACED vs TIF_SYSCALL_TRACE for syscall tracing check
*/
void syscall_trace(struct uml_pt_regs *regs, int entryexit)
{
int is_singlestep = (current->ptrace & PT_DTRACE) && entryexit;
int tracesysgood;
if (unlikely(current->audit_context)) {
if (!entryexit)
audit_syscall_entry(HOST_AUDIT_ARCH,
UPT_SYSCALL_NR(regs),
UPT_SYSCALL_ARG1(regs),
UPT_SYSCALL_ARG2(regs),
UPT_SYSCALL_ARG3(regs),
UPT_SYSCALL_ARG4(regs));
else
audit_syscall_exit(regs);
}
/* Fake a debug trap */
if (is_singlestep)
send_sigtrap(current, regs, 0);
if (!test_thread_flag(TIF_SYSCALL_TRACE))
return;
if (!(current->ptrace & PT_PTRACED))
return;
/*
* the 0x80 provides a way for the tracing parent to distinguish
* between a syscall stop and SIGTRAP delivery
*/
tracesysgood = (current->ptrace & PT_TRACESYSGOOD);
ptrace_notify(SIGTRAP | (tracesysgood ? 0x80 : 0));
if (entryexit) /* force do_signal() --> is_syscall() */
set_thread_flag(TIF_SIGPENDING);
/*
* 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;
}
}