Add initial support for DataFlowSanitizer

Adds initial support for DataFlowSanitizer to the Rust compiler. It
currently supports `-Zsanitizer-dataflow-abilist`. Additional options
for it can be passed to LLVM command line argument processor via LLVM
arguments using `llvm-args` codegen option (e.g.,
`-Cllvm-args=-dfsan-combine-pointer-labels-on-load=false`).

7 files changed, 42 insertions, 7 deletions

diff --git a/src/bootstrap/configure.py b/src/bootstrap/configure.py
index d34c19a47e3..8b65e8ff9c3 100755
--- a/src/bootstrap/configure.py
+++ b/src/bootstrap/configure.py
@@ -48,7 +48,7 @@ o("codegen-tests", "rust.codegen-tests", "run the tests/codegen tests")
 o("ninja", "llvm.ninja", "build LLVM using the Ninja generator (for MSVC, requires building in the correct environment)")
 o("locked-deps", "build.locked-deps", "force Cargo.lock to be up to date")
 o("vendor", "build.vendor", "enable usage of vendored Rust crates")
-o("sanitizers", "build.sanitizers", "build the sanitizer runtimes (asan, lsan, msan, tsan, hwasan)")
+o("sanitizers", "build.sanitizers", "build the sanitizer runtimes (asan, dfsan, lsan, msan, tsan, hwasan)")
 o("dist-src", "rust.dist-src", "when building tarballs enables building a source tarball")
 o("cargo-native-static", "build.cargo-native-static", "static native libraries in cargo")
 o("profiler", "build.profiler", "build the profiler runtime")
diff --git a/src/bootstrap/download-ci-llvm-stamp b/src/bootstrap/download-ci-llvm-stamp
index 9998fe2f5db..bd1f9699c3c 100644
--- a/src/bootstrap/download-ci-llvm-stamp
+++ b/src/bootstrap/download-ci-llvm-stamp
@@ -1,4 +1,4 @@
 Change this file to make users of the `download-ci-llvm` configuration download
 a new version of LLVM from CI, even if the LLVM submodule hasn’t changed.
 
-Last change is for: https://github.com/rust-lang/rust/pull/116881
+Last change is for: https://github.com/rust-lang/rust/pull/120761
diff --git a/src/bootstrap/src/core/build_steps/llvm.rs b/src/bootstrap/src/core/build_steps/llvm.rs
index 0681289a94f..701bd585eee 100644
--- a/src/bootstrap/src/core/build_steps/llvm.rs
+++ b/src/bootstrap/src/core/build_steps/llvm.rs
@@ -1088,7 +1088,7 @@ fn supported_sanitizers(
         "x86_64-unknown-illumos" => common_libs("illumos", "x86_64", &["asan"]),
         "x86_64-pc-solaris" => common_libs("solaris", "x86_64", &["asan"]),
         "x86_64-unknown-linux-gnu" => {
-            common_libs("linux", "x86_64", &["asan", "lsan", "msan", "safestack", "tsan"])
+            common_libs("linux", "x86_64", &["asan", "dfsan", "lsan", "msan", "safestack", "tsan"])
         }
         "x86_64-unknown-linux-musl" => {
             common_libs("linux", "x86_64", &["asan", "lsan", "msan", "tsan"])
diff --git a/src/doc/unstable-book/src/compiler-flags/sanitizer.md b/src/doc/unstable-book/src/compiler-flags/sanitizer.md
index 523617eb3e1..c8fd154a00e 100644
--- a/src/doc/unstable-book/src/compiler-flags/sanitizer.md
+++ b/src/doc/unstable-book/src/compiler-flags/sanitizer.md
@@ -29,6 +29,8 @@ This feature allows for use of one of following sanitizers:
 * Those that apart from testing, may be used in production:
   * [ControlFlowIntegrity](#controlflowintegrity) LLVM Control Flow Integrity
     (CFI) provides forward-edge control flow protection.
+  * [DataFlowSanitizer](#dataflowsanitizer) a generic dynamic data flow analysis
+    framework.
   * [KernelControlFlowIntegrity](#kernelcontrolflowintegrity) LLVM Kernel
     Control Flow Integrity (KCFI) provides forward-edge control flow protection
     for operating systems kernels.
@@ -39,14 +41,21 @@ This feature allows for use of one of following sanitizers:
   * [ShadowCallStack](#shadowcallstack) provides backward-edge control flow
     protection (aarch64 only).
 
-To enable a sanitizer compile with `-Zsanitizer=address`,`-Zsanitizer=cfi`,
-`-Zsanitizer=hwaddress`, `-Zsanitizer=leak`, `-Zsanitizer=memory`,
-`-Zsanitizer=memtag`, `-Zsanitizer=shadow-call-stack`, or `-Zsanitizer=thread`.
-You might also need the `--target` and `build-std` flags. Example:
+To enable a sanitizer compile with `-Zsanitizer=address`, `-Zsanitizer=cfi`,
+`-Zsanitizer=dataflow`,`-Zsanitizer=hwaddress`, `-Zsanitizer=leak`,
+`-Zsanitizer=memory`, `-Zsanitizer=memtag`, `-Zsanitizer=shadow-call-stack`, or
+`-Zsanitizer=thread`. You might also need the `--target` and `build-std` flags.
+
+Example:
 ```shell
 $ RUSTFLAGS=-Zsanitizer=address cargo build -Zbuild-std --target x86_64-unknown-linux-gnu
 ```
 
+Additional options for sanitizers can be passed to LLVM command line argument
+processor via LLVM arguments using `llvm-args` codegen option (e.g.,
+`-Cllvm-args=-dfsan-combine-pointer-labels-on-load=false`). See the sanitizer
+documentation for more information about additional options.
+
 # AddressSanitizer
 
 AddressSanitizer is a memory error detector. It can detect the following types
@@ -639,6 +648,21 @@ LLVM KCFI is supported on the following targets:
 See the [Clang KernelControlFlowIntegrity documentation][clang-kcfi] for more
 details.
 
+# DataFlowSanitizer
+
+DataFlowSanitizer is a generalised dynamic data flow analysis.
+
+Unlike other Sanitizer tools, this tool is not designed to detect a specific
+class of bugs on its own. Instead, it provides a generic dynamic data flow
+analysis framework to be used by clients to help detect application-specific
+issues within their own code.
+
+DataFlowSanitizer is supported on the following targets:
+
+* `x86_64-unknown-linux-gnu`
+
+See the [Clang DataFlowSanitizer documentation][clang-dataflow] for more details.
+
 # KernelAddressSanitizer
 
 KernelAddressSanitizer (KASAN) is a freestanding version of AddressSanitizer
@@ -849,6 +873,7 @@ Sanitizers produce symbolized stacktraces when llvm-symbolizer binary is in `PAT
 * [Sanitizers project page](https://github.com/google/sanitizers/wiki/)
 * [AddressSanitizer in Clang][clang-asan]
 * [ControlFlowIntegrity in Clang][clang-cfi]
+* [DataFlowSanitizer in Clang][clang-dataflow]
 * [HWAddressSanitizer in Clang][clang-hwasan]
 * [Linux Kernel's KernelAddressSanitizer documentation][linux-kasan]
 * [LeakSanitizer in Clang][clang-lsan]
@@ -858,6 +883,7 @@ Sanitizers produce symbolized stacktraces when llvm-symbolizer binary is in `PAT
 
 [clang-asan]: https://clang.llvm.org/docs/AddressSanitizer.html
 [clang-cfi]: https://clang.llvm.org/docs/ControlFlowIntegrity.html
+[clang-dataflow]: https://clang.llvm.org/docs/DataFlowSanitizer.html
 [clang-hwasan]: https://clang.llvm.org/docs/HardwareAssistedAddressSanitizerDesign.html
 [clang-kcfi]: https://clang.llvm.org/docs/ControlFlowIntegrity.html#fsanitize-kcfi
 [clang-lsan]: https://clang.llvm.org/docs/LeakSanitizer.html
diff --git a/src/tools/compiletest/src/common.rs b/src/tools/compiletest/src/common.rs
index 49f1226e2cc..bfe6c959e7c 100644
--- a/src/tools/compiletest/src/common.rs
+++ b/src/tools/compiletest/src/common.rs
@@ -156,6 +156,7 @@ impl PanicStrategy {
 pub enum Sanitizer {
     Address,
     Cfi,
+    Dataflow,
     Kcfi,
     KernelAddress,
     Leak,
diff --git a/src/tools/compiletest/src/header/needs.rs b/src/tools/compiletest/src/header/needs.rs
index 9b22b2112a8..39786588150 100644
--- a/src/tools/compiletest/src/header/needs.rs
+++ b/src/tools/compiletest/src/header/needs.rs
@@ -30,6 +30,11 @@ pub(super) fn handle_needs(
             ignore_reason: "ignored on targets without CFI sanitizer",
         },
         Need {
+            name: "needs-sanitizer-dataflow",
+            condition: cache.sanitizer_dataflow,
+            ignore_reason: "ignored on targets without dataflow sanitizer",
+        },
+        Need {
             name: "needs-sanitizer-kcfi",
             condition: cache.sanitizer_kcfi,
             ignore_reason: "ignored on targets without kernel CFI sanitizer",
@@ -190,6 +195,7 @@ pub(super) struct CachedNeedsConditions {
     sanitizer_support: bool,
     sanitizer_address: bool,
     sanitizer_cfi: bool,
+    sanitizer_dataflow: bool,
     sanitizer_kcfi: bool,
     sanitizer_kasan: bool,
     sanitizer_leak: bool,
@@ -229,6 +235,7 @@ impl CachedNeedsConditions {
             sanitizer_support: std::env::var_os("RUSTC_SANITIZER_SUPPORT").is_some(),
             sanitizer_address: sanitizers.contains(&Sanitizer::Address),
             sanitizer_cfi: sanitizers.contains(&Sanitizer::Cfi),
+            sanitizer_dataflow: sanitizers.contains(&Sanitizer::Dataflow),
             sanitizer_kcfi: sanitizers.contains(&Sanitizer::Kcfi),
             sanitizer_kasan: sanitizers.contains(&Sanitizer::KernelAddress),
             sanitizer_leak: sanitizers.contains(&Sanitizer::Leak),
diff --git a/src/tools/tidy/src/ui_tests.rs b/src/tools/tidy/src/ui_tests.rs
index 920fe16a9fc..8899a55b2df 100644
--- a/src/tools/tidy/src/ui_tests.rs
+++ b/src/tools/tidy/src/ui_tests.rs
@@ -43,6 +43,7 @@ const EXTENSION_EXCEPTION_PATHS: &[&str] = &[
     "tests/ui/macros/syntax-extension-source-utils-files/includeme.fragment", // more include
     "tests/ui/proc-macro/auxiliary/included-file.txt", // more include
     "tests/ui/invalid/foo.natvis.xml", // sample debugger visualizer
+    "tests/ui/sanitizer/dataflow-abilist.txt", // dataflow sanitizer ABI list file
     "tests/ui/shell-argfiles/shell-argfiles.args", // passing args via a file
     "tests/ui/shell-argfiles/shell-argfiles-badquotes.args", // passing args via a file
     "tests/ui/shell-argfiles/shell-argfiles-via-argfile-shell.args", // passing args via a file