From 5d60778fa0dc07e8ece7fbb8cf0f4f924c3d35bf Mon Sep 17 00:00:00 2001
From: Mats Kindahl <mats@kindahl.net>
Date: Sun, 29 Dec 2024 20:23:25 +0100
Subject: [PATCH 5/7] Semantic patch for palloc_array and palloc_object

Macros were added to the palloc API in commit 2016055a92f to improve
type-safety, but very few instances were replaced. This adds a cocci script to
do that replacement. The semantic patch deliberately do not replace instances
where the type of the variable and the type used in the macro does not match.
---
 cocci/palloc_array.cocci | 157 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 157 insertions(+)
 create mode 100644 cocci/palloc_array.cocci

diff --git a/cocci/palloc_array.cocci b/cocci/palloc_array.cocci
new file mode 100644
index 00000000000..aeeab74c3a9
--- /dev/null
+++ b/cocci/palloc_array.cocci
@@ -0,0 +1,157 @@
+// Since PG16 there are array versions of common palloc operations, so
+// we can use those instead.
+//
+// We ignore cases where we have a anonymous struct and also when the
+// type of the variable being assigned to is different from the
+// inferred type.
+//
+// Options: --no-includes --include-headers
+
+virtual patch
+virtual report
+virtual context
+
+// These rules (soN) are needed to rewrite types of the form
+// sizeof(T[C]) to C * sizeof(T) since Cocci cannot (currently) handle
+// it.
+@initialize:python@
+@@
+import re
+
+CRE = re.compile(r'(.*)\s+\[\s+(\d+)\s+\]$')
+
+def is_array_type(s):
+    mre = CRE.match(s)
+    return (mre is not None)
+
+@so1 depends on patch@
+type T : script:python() {  is_array_type(T) };
+@@
+palloc(sizeof(T))
+
+@script:python so2 depends on patch@
+T << so1.T;
+T2;
+E;
+@@
+mre = CRE.match(T)
+coccinelle.T2 = cocci.make_type(mre.group(1))
+coccinelle.E = cocci.make_expr(mre.group(2))
+
+@depends on patch@
+type so1.T;
+type so2.T2;
+expression so2.E;
+@@
+- palloc(sizeof(T))
++ palloc(E * sizeof(T2))
+
+@r1 depends on report || context@
+type T !~ "^struct {";
+expression E;
+position p;
+idexpression T *I;
+identifier alloc = {palloc0, palloc};
+@@
+* I = alloc@p(E * sizeof(T))
+
+@script:python depends on report@
+p << r1.p;
+alloc << r1.alloc;
+@@
+coccilib.report.print_report(p[0], f"this {alloc} can be replaced with {alloc}_array")
+
+@depends on patch@
+type T !~ "^struct {";
+expression E;
+T *P;
+idexpression T* I;
+constant C;
+identifier alloc = {palloc0, palloc};
+fresh identifier alloc_array = alloc ## "_array";
+@@
+(
+- I = (T*) alloc(E * sizeof( \( *P \| P[C] \) ))
++ I = alloc_array(T, E)
+|
+- I = (T*) alloc(E * sizeof(T))
++ I = alloc_array(T, E)
+|
+- I = alloc(E * sizeof( \( *P \| P[C] \) ))
++ I = alloc_array(T, E)
+|
+- I = alloc(E * sizeof(T))
++ I = alloc_array(T, E)
+)
+
+@r3 depends on report || context@
+type T !~ "^struct {";
+expression E;
+idexpression T *P;
+idexpression T *I;
+position p;
+@@
+* I = repalloc@p(P, E * sizeof(T))
+
+@script:python depends on report@
+p << r3.p;
+@@
+coccilib.report.print_report(p[0], "this repalloc can be replaced with repalloc_array")
+
+@depends on patch@
+type T !~ "^struct {";
+expression E;
+idexpression T *P1;
+idexpression T *P2;
+idexpression T *I;
+constant C;
+@@
+(
+- I = (T*) repalloc(P1, E * sizeof( \( *P2 \| P2[C] \) ))
++ I = repalloc_array(P1, T, E)
+|
+- I = (T*) repalloc(P1, E * sizeof(T))
++ I = repalloc_array(P1, T, E)
+|
+- I = repalloc(P1, E * sizeof( \( *P2 \| P2[C] \) ))
++ I = repalloc_array(P1, T, E)
+|
+- I = repalloc(P1, E * sizeof(T))
++ I = repalloc_array(P1, T, E)
+)
+
+@r4 depends on report || context@
+type T !~ "^struct {";
+position p;
+idexpression T* I;
+identifier alloc = {palloc, palloc0};
+@@
+* I = alloc@p(sizeof(T))
+
+@script:python depends on report@
+p << r4.p;
+alloc << r4.alloc;
+@@
+coccilib.report.print_report(p[0], f"this {alloc} can be replaced with {alloc}_object")
+
+@depends on patch@
+type T !~ "^struct {";
+T* P;
+idexpression T *I;
+constant C;
+identifier alloc = {palloc, palloc0};
+fresh identifier alloc_object = alloc ## "_object";
+@@
+(
+- I = (T*) alloc(sizeof( \( *P \| P[C] \) ))
++ I = alloc_object(T)
+|
+- I = (T*) alloc(sizeof(T))
++ I = alloc_object(T)
+|
+- I = alloc(sizeof( \( *P \| P[C] \) ))
++ I = alloc_object(T)
+|
+- I = alloc(sizeof(T))
++ I = alloc_object(T)
+)
-- 
2.43.0