Add scripts/coccinelle/deref_null.cocci

Add a Coccinelle file to identify the dereferences of NULL variables

This semantic patch identifies when a variable is known to be NULL
after a test, but it is still dereferenced later.

Signed-off-by: Nicolas Palix <npalix@diku.dk>
Signed-off-by: Julia Lawall <julia@diku.dk>
Signed-off-by: Michal Marek <mmarek@suse.cz>

1 files changed, 293 insertions, 0 deletions

diff --git a/scripts/coccinelle/deref_null.cocci b/scripts/coccinelle/deref_null.cocci
new file mode 100644
index 0000000..9969d76
--- /dev/null
+++ b/scripts/coccinelle/deref_null.cocci
@@ -0,0 +1,293 @@
+///
+/// A variable is dereference under a NULL test.
+/// Even though it is know to be NULL.
+///
+// Confidence: Moderate
+// Copyright: (C) 2010 Nicolas Palix, DIKU.  GPLv2.
+// Copyright: (C) 2010 Julia Lawall, DIKU.  GPLv2.
+// Copyright: (C) 2010 Gilles Muller, INRIA/LiP6.  GPLv2.
+// URL: http://coccinelle.lip6.fr/
+// Comments: -I ... -all_includes can give more complete results
+// Options:
+
+virtual context
+virtual patch
+virtual org
+virtual report
+
+@initialize:python depends on !context && patch && !org && !report@
+
+import sys
+print >> sys.stderr, "This semantic patch does not support the 'patch' mode."
+
+@depends on patch@
+@@
+
+this_rule_should_never_matches();
+
+@ifm depends on !patch@
+expression *E;
+statement S1,S2;
+position p1;
+@@
+
+if@p1 ((E == NULL && ...) || ...) S1 else S2
+
+// The following two rules are separate, because both can match a single
+// expression in different ways
+@pr1 depends on !patch expression@
+expression *ifm.E;
+identifier f;
+position p1;
+@@
+
+ (E != NULL && ...) ? <+...E->f@p1...+> : ...
+
+@pr2 depends on !patch expression@
+expression *ifm.E;
+identifier f;
+position p2;
+@@
+
+(
+  (E != NULL) && ... && <+...E->f@p2...+>
+|
+  (E == NULL) || ... || <+...E->f@p2...+>
+|
+ sizeof(<+...E->f@p2...+>)
+)
+
+// For org and report modes
+
+@r depends on !context && !patch && (org || report) exists@
+expression subE <= ifm.E;
+expression *ifm.E;
+expression E1,E2;
+identifier f;
+statement S1,S2,S3,S4;
+iterator iter;
+position p!={pr1.p1,pr2.p2};
+position ifm.p1;
+@@
+
+if@p1 ((E == NULL && ...) || ...)
+{
+  ... when != if (...) S1 else S2
+(
+ iter(subE,...) S4 // no use
+|
+ list_remove_head(E2,subE,...)
+|
+ subE = E1
+|
+ for(subE = E1;...;...) S4
+|
+ subE++
+|
+ ++subE
+|
+ --subE
+|
+ subE--
+|
+ &subE
+|
+ E->f@p // bad use
+)
+  ... when any
+  return ...;
+}
+else S3
+
+@script:python depends on !context && !patch && !org && report@
+p << r.p;
+p1 << ifm.p1;
+x << ifm.E;
+@@
+
+msg="ERROR: %s is NULL but dereferenced." % (x)
+coccilib.report.print_report(p[0], msg)
+cocci.include_match(False)
+
+@script:python depends on !context && !patch && org && !report@
+p << r.p;
+p1 << ifm.p1;
+x << ifm.E;
+@@
+
+msg="ERROR: %s is NULL but dereferenced." % (x)
+msg_safe=msg.replace("[","@(").replace("]",")")
+cocci.print_main(msg_safe,p)
+cocci.include_match(False)
+
+@s depends on !context && !patch && (org || report) exists@
+expression subE <= ifm.E;
+expression *ifm.E;
+expression E1,E2;
+identifier f;
+statement S1,S2,S3,S4;
+iterator iter;
+position p!={pr1.p1,pr2.p2};
+position ifm.p1;
+@@
+
+if@p1 ((E == NULL && ...) || ...)
+{
+  ... when != if (...) S1 else S2
+(
+ iter(subE,...) S4 // no use
+|
+ list_remove_head(E2,subE,...)
+|
+ subE = E1
+|
+ for(subE = E1;...;...) S4
+|
+ subE++
+|
+ ++subE
+|
+ --subE
+|
+ subE--
+|
+ &subE
+|
+ E->f@p // bad use
+)
+  ... when any
+}
+else S3
+
+@script:python depends on !context && !patch && !org && report@
+p << s.p;
+p1 << ifm.p1;
+x << ifm.E;
+@@
+
+msg="ERROR: %s is NULL but dereferenced." % (x)
+coccilib.report.print_report(p[0], msg)
+
+@script:python depends on !context && !patch && org && !report@
+p << s.p;
+p1 << ifm.p1;
+x << ifm.E;
+@@
+
+msg="ERROR: %s is NULL but dereferenced." % (x)
+msg_safe=msg.replace("[","@(").replace("]",")")
+cocci.print_main(msg_safe,p)
+
+// For context mode
+
+@depends on context && !patch && !org && !report exists@
+expression subE <= ifm.E;
+expression *ifm.E;
+expression E1,E2;
+identifier f;
+statement S1,S2,S3,S4;
+iterator iter;
+position p!={pr1.p1,pr2.p2};
+position ifm.p1;
+@@
+
+if@p1 ((E == NULL && ...) || ...)
+{
+  ... when != if (...) S1 else S2
+(
+ iter(subE,...) S4 // no use
+|
+ list_remove_head(E2,subE,...)
+|
+ subE = E1
+|
+ for(subE = E1;...;...) S4
+|
+ subE++
+|
+ ++subE
+|
+ --subE
+|
+ subE--
+|
+ &subE
+|
+* E->f@p // bad use
+)
+  ... when any
+  return ...;
+}
+else S3
+
+// The following three rules are duplicates of ifm, pr1 and pr2 respectively.
+// It is need because the previous rule as already made a "change".
+
+@ifm1 depends on !patch@
+expression *E;
+statement S1,S2;
+position p1;
+@@
+
+if@p1 ((E == NULL && ...) || ...) S1 else S2
+
+@pr11 depends on !patch expression@
+expression *ifm1.E;
+identifier f;
+position p1;
+@@
+
+ (E != NULL && ...) ? <+...E->f@p1...+> : ...
+
+@pr12 depends on !patch expression@
+expression *ifm1.E;
+identifier f;
+position p2;
+@@
+
+(
+  (E != NULL) && ... && <+...E->f@p2...+>
+|
+  (E == NULL) || ... || <+...E->f@p2...+>
+|
+ sizeof(<+...E->f@p2...+>)
+)
+
+@depends on context && !patch && !org && !report exists@
+expression subE <= ifm1.E;
+expression *ifm1.E;
+expression E1,E2;
+identifier f;
+statement S1,S2,S3,S4;
+iterator iter;
+position p!={pr11.p1,pr12.p2};
+position ifm1.p1;
+@@
+
+if@p1 ((E == NULL && ...) || ...)
+{
+  ... when != if (...) S1 else S2
+(
+ iter(subE,...) S4 // no use
+|
+ list_remove_head(E2,subE,...)
+|
+ subE = E1
+|
+ for(subE = E1;...;...) S4
+|
+ subE++
+|
+ ++subE
+|
+ --subE
+|
+ subE--
+|
+ &subE
+|
+* E->f@p // bad use
+)
+  ... when any
+}
+else S3