From 8aaf5d60aa0b3ddb05e117f52c0e30ec246b7aad Mon Sep 17 00:00:00 2001
From: Dmitry Vyukov <dvyukov@google.com>
Date: Fri, 17 Jan 2025 10:39:49 +0100
Subject: tools/syz-declextract: support function scopes

Extract info about function scopes formed by switch'es on function arguments.
For example if we have:

void foo(..., int cmd, ...)
{
  ...
  switch (cmd) {
  case FOO:
    ... block 1 ...
  case BAR:
    ... block 2 ...
  }
  ...
}

We record that any data flow within block 1 is only relevant
when foo's arg cmd has value FOO, similarly for block 2 and BAR.

This allows to do 3 things:
1. Locate ioctl commands that are switched on within transitively
   called functions.
2. Infer return value for each ioctl command.
3. Infer argument type when it's not specified in _IO macro.

This will also allow to infer other multiplexed syscalls.

Descriptions generated on Linux commit c4b9570cfb63501.
---
 pkg/declextract/typing.go | 69 +++++++++++++++++++++++++++++++++++++++++------
 1 file changed, 61 insertions(+), 8 deletions(-)

(limited to 'pkg/declextract/typing.go')

diff --git a/pkg/declextract/typing.go b/pkg/declextract/typing.go
index 7de22474d..f29f8e950 100644
--- a/pkg/declextract/typing.go
+++ b/pkg/declextract/typing.go
@@ -94,6 +94,8 @@ const maxTraversalDepth = 18
 
 type typingNode struct {
 	id    string
+	fn    *Function
+	arg   int
 	flows [2]map[*typingNode]bool
 }
 
@@ -104,14 +106,16 @@ const (
 
 func (ctx *context) processTypingFacts() {
 	for _, fn := range ctx.Functions {
-		for _, fact := range fn.Facts {
-			src := ctx.canonicalNode(fn, fact.Src)
-			dst := ctx.canonicalNode(fn, fact.Dst)
-			if src == nil || dst == nil {
-				continue
+		for _, scope := range fn.Scopes {
+			for _, fact := range scope.Facts {
+				src := ctx.canonicalNode(fn, fact.Src)
+				dst := ctx.canonicalNode(fn, fact.Dst)
+				if src == nil || dst == nil {
+					continue
+				}
+				src.flows[flowTo][dst] = true
+				dst.flows[flowFrom][src] = true
 			}
-			src.flows[flowTo][dst] = true
-			dst.flows[flowFrom][src] = true
 		}
 	}
 }
@@ -142,8 +146,14 @@ func (ctx *context) canonicalNode(fn *Function, ent *TypingEntity) *typingNode {
 	if n != nil {
 		return n
 	}
+	arg := -1
+	if ent.Argument != nil {
+		arg = ent.Argument.Arg
+	}
 	n = &typingNode{
-		id: fullID,
+		id:  fullID,
+		fn:  fn,
+		arg: arg,
 	}
 	for i := range n.flows {
 		n.flows[i] = make(map[*typingNode]bool)
@@ -266,3 +276,46 @@ func flowString(path []*typingNode, flowType int) string {
 	}
 	return w.String()
 }
+
+func (ctx *context) inferCommandVariants(name, file string, arg int) []string {
+	ctx.trace("inferring %v:arg%v variants", name, arg)
+	fn := ctx.findFunc(name, file)
+	if fn == nil {
+		return nil
+	}
+	var variants []string
+	n := fn.facts[fmt.Sprintf("arg%v", arg)]
+	if n == nil {
+		ctx.collectCommandVariants(fn, arg, &variants)
+	} else {
+		visited := make(map[*typingNode]bool)
+		ctx.walkCommandVariants(n, &variants, visited, 0)
+	}
+	return sortAndDedupSlice(variants)
+}
+
+func (ctx *context) collectCommandVariants(fn *Function, arg int, variants *[]string) {
+	var values []string
+	for _, scope := range fn.Scopes {
+		if scope.Arg == arg {
+			values = append(values, scope.Values...)
+		}
+	}
+	if len(values) != 0 {
+		ctx.trace("  function %v:arg%v implements: %v", fn.Name, arg, values)
+		*variants = append(*variants, values...)
+	}
+}
+
+func (ctx *context) walkCommandVariants(n *typingNode, variants *[]string, visited map[*typingNode]bool, depth int) {
+	if visited[n] || depth >= 10 {
+		return
+	}
+	visited[n] = true
+	if n.arg >= 0 {
+		ctx.collectCommandVariants(n.fn, n.arg, variants)
+	}
+	for e := range n.flows[flowTo] {
+		ctx.walkCommandVariants(e, variants, visited, depth+1)
+	}
+}
-- 
cgit mrf-deployment