[PATCH] kprobes: fix broken fault handling for x86_64

Provide proper kprobes fault handling, if a user-specified pre/post handlers
tries to access user address space, through copy_from_user(), get_user() etc.

The user-specified fault handler gets called only if the fault occurs while
executing user-specified handlers.  In such a case user-specified handler is
allowed to fix it first, later if the user-specifed fault handler does not fix
it, we try to fix it by calling fix_exception().

The user-specified handler will not be called if the fault happens when single
stepping the original instruction, instead we reset the current probe and
allow the system page fault handler to fix it up.

Signed-off-by: Prasanna S Panchamukhi <prasanna@in.ibm.com>
Cc: Andi Kleen <ak@muc.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

1 files changed, 55 insertions, 7 deletions

diff --git a/arch/x86_64/kernel/kprobes.c b/arch/x86_64/kernel/kprobes.c
index 218e015c3195..accbff3fec49 100644
--- a/arch/x86_64/kernel/kprobes.c
+++ b/arch/x86_64/kernel/kprobes.c
@@ -37,10 +37,12 @@
 #include <linux/string.h>
 #include <linux/slab.h>
 #include <linux/preempt.h>
+#include <linux/module.h>
 
 #include <asm/cacheflush.h>
 #include <asm/pgtable.h>
 #include <asm/kdebug.h>
+#include <asm/uaccess.h>
 
 void jprobe_return_end(void);
 static void __kprobes arch_copy_kprobe(struct kprobe *p);
@@ -578,16 +580,62 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr)
 {
         struct kprobe *cur = kprobe_running();
         struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+        const struct exception_table_entry *fixup;
 
-        if (cur->fault_handler && cur->fault_handler(cur, regs, trapnr))
-                return 1;
-
-        if (kcb->kprobe_status & KPROBE_HIT_SS) {
-                resume_execution(cur, regs, kcb);
+        switch(kcb->kprobe_status) {
+        case KPROBE_HIT_SS:
+        case KPROBE_REENTER:
+                /*
+                 * We are here because the instruction being single
+                 * stepped caused a page fault. We reset the current
+                 * kprobe and the rip points back to the probe address
+                 * and allow the page fault handler to continue as a
+                 * normal page fault.
+                 */
+                regs->rip = (unsigned long)cur->addr;
                 regs->eflags |= kcb->kprobe_old_rflags;
-
-                reset_current_kprobe();
+                if (kcb->kprobe_status == KPROBE_REENTER)
+                        restore_previous_kprobe(kcb);
+                else
+                        reset_current_kprobe();
                 preempt_enable_no_resched();
+                break;
+        case KPROBE_HIT_ACTIVE:
+        case KPROBE_HIT_SSDONE:
+                /*
+                 * We increment the nmissed count for accounting,
+                 * we can also use npre/npostfault count for accouting
+                 * these specific fault cases.
+                 */
+                kprobes_inc_nmissed_count(cur);
+
+                /*
+                 * We come here because instructions in the pre/post
+                 * handler caused the page_fault, this could happen
+                 * if handler tries to access user space by
+                 * copy_from_user(), get_user() etc. Let the
+                 * user-specified handler try to fix it first.
+                 */
+                if (cur->fault_handler && cur->fault_handler(cur, regs, trapnr))
+                        return 1;
+
+                /*
+                 * In case the user-specified fault handler returned
+                 * zero, try to fix up.
+                 */
+                fixup = search_exception_tables(regs->rip);
+                if (fixup) {
+                        regs->rip = fixup->fixup;
+                        return 1;
+                }
+
+                /*
+                 * fixup() could not handle it,
+                 * Let do_page_fault() fix it.
+                 */
+                break;
+        default:
+                break;
         }
         return 0;
 }