x86: single-step over "popf" without corrupting state.

This still leaves "pushf" able to see that somebody is
single-stepping us, but that is at least something you
can work around.

arch/i386/kernel/ptrace.c

@@ -144,6 +144,79 @@ static unsigned long getreg(struct task_struct *child,
 	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)
 {
 	struct pt_regs *regs = get_child_regs(child);
@@ -161,8 +234,17 @@ static void set_singlestep(struct task_struct *child)
 	if (regs->eflags & TRAP_FLAG)
 		return;
 
-	/* Set TF on the kernel stack, and set the flag to say so */
+	/* 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;
 }