#include <linux/security.h>
#include <linux/audit.h>
#include <linux/seccomp.h>
+#include <linux/signal.h>
#include <asm/uaccess.h>
#include <asm/pgtable.h>
return 0;
}
+#define LDT_SEGMENT 4
+
+unsigned long convert_rip_to_linear(struct task_struct *child, struct pt_regs *regs)
+{
+ unsigned long addr, seg;
+
+ addr = regs->rip;
+ seg = regs->cs & 0xffff;
+
+ /*
+ * 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 int is_at_popf(struct task_struct *child, struct pt_regs *regs)
+{
+ int i, copied;
+ unsigned char opcode[16];
+ unsigned long addr = convert_rip_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;
+
+ /* CHECKME: 64 65 */
+
+ /* 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;
+
+ /* REX prefixes */
+ case 0x40 ... 0x4f:
+ continue;
+
+ /* CHECKME: f0, f2, f3 */
+
+ /*
+ * 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)
{
struct pt_regs *regs = get_child_regs(child);
/* 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.
+ *
+ * AK: this is not enough, LAHF and IRET can change TF in user space too.
+ */
+ if (is_at_popf(child, regs))
+ return;
+
child->ptrace |= PT_DTRACE;
}
value &= 0xffff;
return 0;
case offsetof(struct user_regs_struct,fs_base):
- if (!((value >> 48) == 0 || (value >> 48) == 0xffff))
- return -EIO;
+ if (value >= TASK_SIZE_OF(child))
+ return -EIO;
child->thread.fs = value;
return 0;
case offsetof(struct user_regs_struct,gs_base):
- if (!((value >> 48) == 0 || (value >> 48) == 0xffff))
- return -EIO;
+ if (value >= TASK_SIZE_OF(child))
+ return -EIO;
child->thread.gs = value;
return 0;
case offsetof(struct user_regs_struct, eflags):
return -EIO;
value &= 0xffff;
break;
+ case offsetof(struct user_regs_struct, rip):
+ /* Check if the new RIP address is canonical */
+ if (value >= TASK_SIZE_OF(child))
+ return -EIO;
+ break;
}
put_stack_long(child, regno - sizeof(struct pt_regs), value);
return 0;
break;
switch (addr) {
- case 0 ... sizeof(struct user_regs_struct):
+ case 0 ... sizeof(struct user_regs_struct) - sizeof(long):
tmp = getreg(child, addr);
break;
case offsetof(struct user, u_debugreg[0]):
break;
case PTRACE_POKEUSR: /* write the word at location addr in the USER area */
+ {
+ int dsize = test_tsk_thread_flag(child, TIF_IA32) ? 3 : 7;
ret = -EIO;
if ((addr & 7) ||
addr > sizeof(struct user) - 7)
break;
switch (addr) {
- case 0 ... sizeof(struct user_regs_struct):
+ case 0 ... sizeof(struct user_regs_struct) - sizeof(long):
ret = putreg(child, addr, data);
break;
/* Disallows to set a breakpoint into the vsyscall */
case offsetof(struct user, u_debugreg[0]):
- if (data >= TASK_SIZE-7) break;
+ if (data >= TASK_SIZE_OF(child) - dsize) break;
child->thread.debugreg0 = data;
ret = 0;
break;
case offsetof(struct user, u_debugreg[1]):
- if (data >= TASK_SIZE-7) break;
+ if (data >= TASK_SIZE_OF(child) - dsize) break;
child->thread.debugreg1 = data;
ret = 0;
break;
case offsetof(struct user, u_debugreg[2]):
- if (data >= TASK_SIZE-7) break;
+ if (data >= TASK_SIZE_OF(child) - dsize) break;
child->thread.debugreg2 = data;
ret = 0;
break;
case offsetof(struct user, u_debugreg[3]):
- if (data >= TASK_SIZE-7) break;
+ if (data >= TASK_SIZE_OF(child) - dsize) break;
child->thread.debugreg3 = data;
ret = 0;
break;
break;
}
break;
+ }
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)
set_tsk_thread_flag(child,TIF_SYSCALL_TRACE);
case PTRACE_SINGLESTEP: /* set the trap flag. */
ret = -EIO;
- if ((unsigned long) data > _NSIG)
+ if (!valid_signal(data))
break;
clear_tsk_thread_flag(child,TIF_SYSCALL_TRACE);
set_singlestep(child);
/* do the secure computing check first */
secure_computing(regs->orig_rax);
- if (unlikely(current->audit_context))
- audit_syscall_entry(current, regs->orig_rax,
- regs->rdi, regs->rsi,
- regs->rdx, regs->r10);
-
if (test_thread_flag(TIF_SYSCALL_TRACE)
&& (current->ptrace & PT_PTRACED))
syscall_trace(regs);
+
+ if (unlikely(current->audit_context)) {
+ if (test_thread_flag(TIF_IA32)) {
+ audit_syscall_entry(current, AUDIT_ARCH_I386,
+ regs->orig_rax,
+ regs->rbx, regs->rcx,
+ regs->rdx, regs->rsi);
+ } else {
+ audit_syscall_entry(current, AUDIT_ARCH_X86_64,
+ regs->orig_rax,
+ regs->rdi, regs->rsi,
+ regs->rdx, regs->r10);
+ }
+ }
}
asmlinkage void syscall_trace_leave(struct pt_regs *regs)
{
if (unlikely(current->audit_context))
- audit_syscall_exit(current, regs->rax);
+ audit_syscall_exit(current, AUDITSC_RESULT(regs->rax), regs->rax);
if ((test_thread_flag(TIF_SYSCALL_TRACE)
|| test_thread_flag(TIF_SINGLESTEP))