Merge branch 'master' into connect-ir-dataflow-models

This commit is contained in:
Robert Marsh
2020-02-03 11:06:45 -08:00
167 changed files with 5839 additions and 565 deletions

View File

@@ -258,14 +258,7 @@ class FormatLiteral extends Literal {
* Gets the position in the string at which the nth conversion specifier
* starts.
*/
int getConvSpecOffset(int n) {
n = 0 and result = this.getFormat().indexOf("%", 0, 0)
or
n > 0 and
exists(int p |
n = p + 1 and result = this.getFormat().indexOf("%", 0, this.getConvSpecOffset(p) + 2)
)
}
int getConvSpecOffset(int n) { result = this.getFormat().indexOf("%", n, 0) }
/*
* Each of these predicates gets a regular expressions to match each individual

View File

@@ -21,31 +21,19 @@ private predicate predictableInstruction(Instruction instr) {
predictableInstruction(instr.(UnaryInstruction).getUnary())
}
private DataFlow::Node getNodeForSource(Expr source) {
isUserInput(source, _) and
(
result = DataFlow::exprNode(source)
or
result = DataFlow::definitionByReferenceNode(source)
)
}
private class DefaultTaintTrackingCfg extends DataFlow::Configuration {
DefaultTaintTrackingCfg() { this = "DefaultTaintTrackingCfg" }
override predicate isSource(DataFlow::Node source) {
exists(CallInstruction ci, WriteSideEffectInstruction wsei |
userInputArgument(ci.getConvertedResultExpression(), wsei.getIndex()) and
source.asInstruction() = wsei and
wsei.getPrimaryInstruction() = ci
)
or
userInputReturned(source.asExpr())
or
isUserInput(source.asExpr(), _)
or
source.asExpr() instanceof EnvironmentRead
or
source
.asInstruction()
.(LoadInstruction)
.getSourceAddress()
.(VariableAddressInstruction)
.getASTVariable()
.hasName("argv") and
source.asInstruction().getEnclosingFunction().hasGlobalName("main")
}
override predicate isSource(DataFlow::Node source) { source = getNodeForSource(_) }
override predicate isSink(DataFlow::Node sink) { any() }
@@ -59,7 +47,7 @@ private class DefaultTaintTrackingCfg extends DataFlow::Configuration {
private class ToGlobalVarTaintTrackingCfg extends DataFlow::Configuration {
ToGlobalVarTaintTrackingCfg() { this = "GlobalVarTaintTrackingCfg" }
override predicate isSource(DataFlow::Node source) { isUserInput(source.asExpr(), _) }
override predicate isSource(DataFlow::Node source) { source = getNodeForSource(_) }
override predicate isSink(DataFlow::Node sink) {
exists(GlobalOrNamespaceVariable gv | writesVariable(sink.asInstruction(), gv))
@@ -163,6 +151,22 @@ private predicate instructionTaintStep(Instruction i1, Instruction i2) {
// from `a`.
i2.(PointerAddInstruction).getLeft() = i1
or
// Until we have from through indirections across calls, we'll take flow out
// of the parameter and into its indirection.
exists(IRFunction f, Parameter parameter |
i1 = getInitializeParameter(f, parameter) and
i2 = getInitializeIndirection(f, parameter)
)
or
// Until we have flow through indirections across calls, we'll take flow out
// of the indirection and into the argument.
// When we get proper flow through indirections across calls, this code can be
// moved to `adjusedSink` or possibly into the `DataFlow::ExprNode` class.
exists(ReadSideEffectInstruction read |
read.getAnOperand().(SideEffectOperand).getAnyDef() = i1 and
read.getArgumentDef() = i2
)
or
// Flow from argument to return value
i2 =
any(CallInstruction call |
@@ -188,6 +192,33 @@ private predicate instructionTaintStep(Instruction i1, Instruction i2) {
)
}
pragma[noinline]
private InitializeIndirectionInstruction getInitializeIndirection(IRFunction f, Parameter p) {
result.getParameter() = p and
result.getEnclosingIRFunction() = f
}
pragma[noinline]
private InitializeParameterInstruction getInitializeParameter(IRFunction f, Parameter p) {
result.getParameter() = p and
result.getEnclosingIRFunction() = f
}
/**
* Get an instruction that goes into argument `argumentIndex` of `call`. This
* can be either directly or through one pointer indirection.
*/
private Instruction getACallArgumentOrIndirection(CallInstruction call, int argumentIndex) {
result = call.getPositionalArgument(argumentIndex)
or
exists(ReadSideEffectInstruction readSE |
// TODO: why are read side effect operands imprecise?
result = readSE.getSideEffectOperand().getAnyDef() and
readSE.getPrimaryInstruction() = call and
readSE.getIndex() = argumentIndex
)
}
private predicate modelTaintToParameter(Function f, int parameterIn, int parameterOut) {
exists(FunctionInput modelIn, FunctionOutput modelOut |
(
@@ -270,31 +301,11 @@ private Element adjustedSink(DataFlow::Node sink) {
// For compatibility, send flow into a `NotExpr` even if it's part of a
// short-circuiting condition and thus might get skipped.
result.(NotExpr).getOperand() = sink.asExpr()
or
// For compatibility, send flow from argument read side effects to their
// corresponding argument expression
exists(IndirectReadSideEffectInstruction read |
read.getAnOperand().(SideEffectOperand).getAnyDef() = sink.asInstruction() and
read.getArgumentDef().getUnconvertedResultExpression() = result
)
or
exists(BufferReadSideEffectInstruction read |
read.getAnOperand().(SideEffectOperand).getAnyDef() = sink.asInstruction() and
read.getArgumentDef().getUnconvertedResultExpression() = result
)
or
exists(SizedBufferReadSideEffectInstruction read |
read.getAnOperand().(SideEffectOperand).getAnyDef() = sink.asInstruction() and
read.getArgumentDef().getUnconvertedResultExpression() = result
)
}
predicate tainted(Expr source, Element tainted) {
exists(DefaultTaintTrackingCfg cfg, DataFlow::Node sink |
cfg.hasFlow(DataFlow::exprNode(source), sink)
or
cfg.hasFlow(DataFlow::definitionByReferenceNode(source), sink)
|
cfg.hasFlow(getNodeForSource(source), sink) and
tainted = adjustedSink(sink)
)
}
@@ -307,7 +318,7 @@ predicate taintedIncludingGlobalVars(Expr source, Element tainted, string global
ToGlobalVarTaintTrackingCfg toCfg, FromGlobalVarTaintTrackingCfg fromCfg, DataFlow::Node store,
GlobalOrNamespaceVariable global, DataFlow::Node load, DataFlow::Node sink
|
toCfg.hasFlow(DataFlow::exprNode(source), store) and
toCfg.hasFlow(getNodeForSource(source), store) and
store
.asInstruction()
.(StoreInstruction)

View File

@@ -21,14 +21,18 @@
| defaulttainttracking.cpp:22:20:22:25 | call to getenv | defaulttainttracking.cpp:22:8:22:33 | (const char *)... |
| defaulttainttracking.cpp:22:20:22:25 | call to getenv | defaulttainttracking.cpp:22:20:22:25 | call to getenv |
| defaulttainttracking.cpp:22:20:22:25 | call to getenv | defaulttainttracking.cpp:22:20:22:32 | (const char *)... |
| defaulttainttracking.cpp:22:20:22:25 | call to getenv | defaulttainttracking.cpp:24:8:24:10 | (const char *)... |
| defaulttainttracking.cpp:22:20:22:25 | call to getenv | defaulttainttracking.cpp:24:8:24:10 | array to pointer conversion |
| defaulttainttracking.cpp:22:20:22:25 | call to getenv | defaulttainttracking.cpp:24:8:24:10 | buf |
| defaulttainttracking.cpp:22:20:22:25 | call to getenv | test_diff.cpp:1:11:1:20 | p#0 |
| defaulttainttracking.cpp:38:25:38:30 | call to getenv | defaulttainttracking.cpp:31:40:31:53 | dotted_address |
| defaulttainttracking.cpp:38:25:38:30 | call to getenv | defaulttainttracking.cpp:32:11:32:26 | p#0 |
| defaulttainttracking.cpp:38:25:38:30 | call to getenv | defaulttainttracking.cpp:38:11:38:21 | env_pointer |
| defaulttainttracking.cpp:38:25:38:30 | call to getenv | defaulttainttracking.cpp:38:25:38:30 | call to getenv |
| defaulttainttracking.cpp:38:25:38:30 | call to getenv | defaulttainttracking.cpp:38:25:38:37 | (void *)... |
| defaulttainttracking.cpp:38:25:38:30 | call to getenv | defaulttainttracking.cpp:39:22:39:22 | a |
| defaulttainttracking.cpp:38:25:38:30 | call to getenv | defaulttainttracking.cpp:39:26:39:34 | call to inet_addr |
| defaulttainttracking.cpp:38:25:38:30 | call to getenv | defaulttainttracking.cpp:39:36:39:61 | (const char *)... |
| defaulttainttracking.cpp:38:25:38:30 | call to getenv | defaulttainttracking.cpp:39:50:39:61 | & ... |
| defaulttainttracking.cpp:38:25:38:30 | call to getenv | defaulttainttracking.cpp:40:10:40:10 | a |
| defaulttainttracking.cpp:64:10:64:15 | call to getenv | defaulttainttracking.cpp:9:11:9:20 | p#0 |

View File

@@ -5,8 +5,8 @@
| defaulttainttracking.cpp:22:20:22:25 | call to getenv | defaulttainttracking.cpp:3:21:3:22 | s1 | AST only |
| defaulttainttracking.cpp:22:20:22:25 | call to getenv | defaulttainttracking.cpp:21:8:21:10 | buf | AST only |
| defaulttainttracking.cpp:22:20:22:25 | call to getenv | defaulttainttracking.cpp:22:15:22:17 | buf | AST only |
| defaulttainttracking.cpp:38:25:38:30 | call to getenv | defaulttainttracking.cpp:31:40:31:53 | dotted_address | AST only |
| defaulttainttracking.cpp:38:25:38:30 | call to getenv | defaulttainttracking.cpp:39:36:39:61 | (const char *)... | AST only |
| defaulttainttracking.cpp:22:20:22:25 | call to getenv | defaulttainttracking.cpp:24:8:24:10 | (const char *)... | IR only |
| defaulttainttracking.cpp:22:20:22:25 | call to getenv | defaulttainttracking.cpp:24:8:24:10 | array to pointer conversion | IR only |
| defaulttainttracking.cpp:38:25:38:30 | call to getenv | defaulttainttracking.cpp:39:51:39:61 | env_pointer | AST only |
| defaulttainttracking.cpp:64:10:64:15 | call to getenv | defaulttainttracking.cpp:52:24:52:24 | p | IR only |
| defaulttainttracking.cpp:88:18:88:23 | call to getenv | defaulttainttracking.cpp:9:11:9:20 | p#0 | IR only |