1 files changed, 88 insertions, 0 deletions

diff --git a/arch/x86_64/kernel/ptrace.c b/arch/x86_64/kernel/ptrace.c
index 002237c3b6a2..c7011675007d 100644
--- a/arch/x86_64/kernel/ptrace.c
+++ b/arch/x86_64/kernel/ptrace.c
@@ -86,6 +86,84 @@ static inline long put_stack_long(struct task_struct *task, int offset,
         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);
@@ -106,6 +184,16 @@ static void set_singlestep(struct task_struct *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;
 }