uretprobes: Return probe entry, prepare_uretprobe()

When a uprobe with return probe consumer is hit, prepare_uretprobe()
function is invoked. It creates return_instance, hijacks return address
and replaces it with the trampoline.

* Return instances are kept as stack per uprobed task.
* Return instance is chained, when the original return address is
  trampoline's page vaddr (e.g. recursive call of the probed function).

Signed-off-by: Anton Arapov <anton@redhat.com>
Acked-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Oleg Nesterov <oleg@redhat.com>

diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h
index 5c8d3290df41bf0944b1651f5ac24d085881437a..b0507f24eeb050bd74a7c0114535550b1bed7f82 100644 (file)
--- a/include/linux/uprobes.h
+++ b/include/linux/uprobes.h
@@ -71,6 +71,7 @@ struct uprobe_task {
        enum uprobe_task_state          state;
        struct arch_uprobe_task         autask;
 
+       struct return_instance          *return_instances;
        struct uprobe                   *active_uprobe;
 
        unsigned long                   xol_vaddr;

diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index d345b7c6cb2dce5d435fece4474def421c1bfe88..3798947b3b58cdc4d97ac4398f71d2175865d284 100644 (file)
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -75,6 +75,15 @@ struct uprobe {
        struct arch_uprobe      arch;
 };
 
+struct return_instance {
+       struct uprobe           *uprobe;
+       unsigned long           func;
+       unsigned long           orig_ret_vaddr; /* original return address */
+       bool                    chained;        /* true, if instance is nested */
+
+       struct return_instance  *next;          /* keep as stack */
+};
+
 /*
  * valid_vma: Verify if the specified vma is an executable vma
  * Relax restrictions while unregistering: vm_flags might have
@@ -1317,6 +1326,7 @@ unsigned long __weak uprobe_get_swbp_addr(struct pt_regs *regs)
 void uprobe_free_utask(struct task_struct *t)
 {
        struct uprobe_task *utask = t->utask;
+       struct return_instance *ri, *tmp;
 
        if (!utask)
                return;
@@ -1324,6 +1334,15 @@ void uprobe_free_utask(struct task_struct *t)
        if (utask->active_uprobe)
                put_uprobe(utask->active_uprobe);
 
+       ri = utask->return_instances;
+       while (ri) {
+               tmp = ri;
+               ri = ri->next;
+
+               put_uprobe(tmp->uprobe);
+               kfree(tmp);
+       }
+
        xol_free_insn_slot(t);
        kfree(utask);
        t->utask = NULL;
@@ -1371,6 +1390,65 @@ static unsigned long get_trampoline_vaddr(void)
        return trampoline_vaddr;
 }
 
+static void prepare_uretprobe(struct uprobe *uprobe, struct pt_regs *regs)
+{
+       struct return_instance *ri;
+       struct uprobe_task *utask;
+       unsigned long orig_ret_vaddr, trampoline_vaddr;
+       bool chained = false;
+
+       if (!get_xol_area())
+               return;
+
+       utask = get_utask();
+       if (!utask)
+               return;
+
+       ri = kzalloc(sizeof(struct return_instance), GFP_KERNEL);
+       if (!ri)
+               goto fail;
+
+       trampoline_vaddr = get_trampoline_vaddr();
+       orig_ret_vaddr = arch_uretprobe_hijack_return_addr(trampoline_vaddr, regs);
+       if (orig_ret_vaddr == -1)
+               goto fail;
+
+       /*
+        * We don't want to keep trampoline address in stack, rather keep the
+        * original return address of first caller thru all the consequent
+        * instances. This also makes breakpoint unwrapping easier.
+        */
+       if (orig_ret_vaddr == trampoline_vaddr) {
+               if (!utask->return_instances) {
+                       /*
+                        * This situation is not possible. Likely we have an
+                        * attack from user-space.
+                        */
+                       pr_warn("uprobe: unable to set uretprobe pid/tgid=%d/%d\n",
+                                               current->pid, current->tgid);
+                       goto fail;
+               }
+
+               chained = true;
+               orig_ret_vaddr = utask->return_instances->orig_ret_vaddr;
+       }
+
+       atomic_inc(&uprobe->ref);
+       ri->uprobe = uprobe;
+       ri->func = instruction_pointer(regs);
+       ri->orig_ret_vaddr = orig_ret_vaddr;
+       ri->chained = chained;
+
+       /* add instance to the stack */
+       ri->next = utask->return_instances;
+       utask->return_instances = ri;
+
+       return;
+
+ fail:
+       kfree(ri);
+}
+
 /* Prepare to single-step probed instruction out of line. */
 static int
 pre_ssout(struct uprobe *uprobe, struct pt_regs *regs, unsigned long bp_vaddr)
@@ -1527,6 +1605,7 @@ static void handler_chain(struct uprobe *uprobe, struct pt_regs *regs)
 {
        struct uprobe_consumer *uc;
        int remove = UPROBE_HANDLER_REMOVE;
+       bool need_prep = false; /* prepare return uprobe, when needed */
 
        down_read(&uprobe->register_rwsem);
        for (uc = uprobe->consumers; uc; uc = uc->next) {
@@ -1537,9 +1616,16 @@ static void handler_chain(struct uprobe *uprobe, struct pt_regs *regs)
                        WARN(rc & ~UPROBE_HANDLER_MASK,
                                "bad rc=0x%x from %pf()\n", rc, uc->handler);
                }
+
+               if (uc->ret_handler)
+                       need_prep = true;
+
                remove &= rc;
        }
 
+       if (need_prep && !remove)
+               prepare_uretprobe(uprobe, regs); /* put bp at return */
+
        if (remove && uprobe->consumers) {
                WARN_ON(!uprobe_is_active(uprobe));
                unapply_uprobe(uprobe, current->mm);
@@ -1658,7 +1744,11 @@ void uprobe_notify_resume(struct pt_regs *regs)
  */
 int uprobe_pre_sstep_notifier(struct pt_regs *regs)
 {
-       if (!current->mm || !test_bit(MMF_HAS_UPROBES, &current->mm->flags))
+       if (!current->mm)
+               return 0;
+
+       if (!test_bit(MMF_HAS_UPROBES, &current->mm->flags) &&
+           (!current->utask || !current->utask->return_instances))
                return 0;
 
        set_thread_flag(TIF_UPROBE);