sammccall updated this revision to Diff 508517. sammccall marked 4 inline comments as done. sammccall edited the summary of this revision. sammccall added a comment.
Address Dmitri's comments Update demo link Repository: rG LLVM Github Monorepo CHANGES SINCE LAST ACTION https://reviews.llvm.org/D146591/new/ https://reviews.llvm.org/D146591 Files: clang/include/clang/Analysis/FlowSensitive/Logger.h clang/lib/Analysis/FlowSensitive/CMakeLists.txt clang/lib/Analysis/FlowSensitive/DataflowAnalysisContext.cpp clang/lib/Analysis/FlowSensitive/HTMLLogger.cpp clang/lib/Analysis/FlowSensitive/HTMLLogger.css clang/lib/Analysis/FlowSensitive/HTMLLogger.html clang/lib/Analysis/FlowSensitive/HTMLLogger.js clang/unittests/Analysis/FlowSensitive/LoggerTest.cpp clang/utils/bundle_resources.py
Index: clang/utils/bundle_resources.py =================================================================== --- /dev/null +++ clang/utils/bundle_resources.py @@ -0,0 +1,29 @@ +#!/usr/bin/env python3 + +#===- bundle_resources.py - Generate string constants with file contents. === +# +# Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions. +# See https://llvm.org/LICENSE.txt for license information. +# SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception +# +#===----------------------------------------------------------------------=== + +# Usage: bundle-resources.py foo.inc a.js path/b.css ... +# Produces foo.inc containing: +# const char a_js[] = "..."; +# const char b_css[] = "..."; +import os +import sys + +outfile = sys.argv[1] +infiles = sys.argv[2:] + +with open(outfile, 'w') as out: + for filename in infiles: + varname = os.path.basename(filename).replace('.', '_') + out.write("const char " + varname + "[] = \n"); + # MSVC limits each chunk of string to 2k, so split by lines. + # The overall limit is 64k, which ought to be enough for anyone. + for line in open(filename).read().split('\n'): + out.write(' R"x(' + line + ')x" "\\n"\n' ) + out.write(' ;\n'); Index: clang/unittests/Analysis/FlowSensitive/LoggerTest.cpp =================================================================== --- clang/unittests/Analysis/FlowSensitive/LoggerTest.cpp +++ clang/unittests/Analysis/FlowSensitive/LoggerTest.cpp @@ -9,6 +9,7 @@ namespace clang::dataflow::test { namespace { +using testing::HasSubstr; struct TestLattice { int Elements = 0; @@ -83,19 +84,24 @@ void logText(llvm::StringRef Text) override { OS << Text << "\n"; } }; -TEST(LoggerTest, Sequence) { +AnalysisInputs<TestAnalysis> makeInputs() { const char *Code = R"cpp( int target(bool b, int p, int q) { return b ? p : q; } )cpp"; + static const std::vector<std::string> Args = { + "-fsyntax-only", "-fno-delayed-template-parsing", "-std=c++17"}; auto Inputs = AnalysisInputs<TestAnalysis>( Code, ast_matchers::hasName("target"), [](ASTContext &C, Environment &) { return TestAnalysis(C); }); - std::vector<std::string> Args = { - "-fsyntax-only", "-fno-delayed-template-parsing", "-std=c++17"}; Inputs.ASTBuildArgs = Args; + return Inputs; +} + +TEST(LoggerTest, Sequence) { + auto Inputs = makeInputs(); std::string Log; TestLogger Logger(Log); Inputs.BuiltinOptions.Log = &Logger; @@ -148,5 +154,29 @@ )"); } +TEST(LoggerTest, HTML) { + auto Inputs = makeInputs(); + std::vector<std::string> Logs; + auto Logger = Logger::html([&]() { + Logs.emplace_back(); + return std::make_unique<llvm::raw_string_ostream>(Logs.back()); + }); + Inputs.BuiltinOptions.Log = Logger.get(); + + ASSERT_THAT_ERROR(checkDataflow<TestAnalysis>(std::move(Inputs), + [](const AnalysisOutputs &) {}), + llvm::Succeeded()); + + // Simple smoke tests: we can't meaningfully test the behavior. + ASSERT_THAT(Logs, testing::SizeIs(1)); + EXPECT_THAT(Logs[0], HasSubstr("function updateSelection")) << "embeds JS"; + EXPECT_THAT(Logs[0], HasSubstr("html {")) << "embeds CSS"; + EXPECT_THAT(Logs[0], HasSubstr("b (ImplicitCastExpr")) << "has CFG elements"; + EXPECT_THAT(Logs[0], HasSubstr("\"B3:1_B3.1\":")) + << "has analysis point state"; + EXPECT_THAT(Logs[0], HasSubstr("transferBranch(0)")) << "has analysis logs"; + EXPECT_THAT(Logs[0], HasSubstr("LocToVal")) << "has built-in lattice dump"; +} + } // namespace } // namespace clang::dataflow::test Index: clang/lib/Analysis/FlowSensitive/HTMLLogger.js =================================================================== --- /dev/null +++ clang/lib/Analysis/FlowSensitive/HTMLLogger.js @@ -0,0 +1,210 @@ +//===-- HTMLLogger.js -----------------------------------------------------===// +// +// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions. +// See https://llvm.org/LICENSE.txt for license information. +// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception +// +//===----------------------------------------------------------------------===// + +// Based on selected objects, hide/show sections & populate data from templates. +// +// For example, if we the selection is {bb=BB4, elt=BB4.6 iter=BB4:2}: +// - show the "block" and "element" sections +// - re-render templates within these sections (if selection changed) +// - apply "bb-select" to items with class class "BB4", etc +let selection = {}; +function updateSelection(changes, data) { + Object.assign(selection, changes); + + data = Object.create(data); + data.selection = selection; + for (root of document.querySelectorAll('[data-selection]')) + updateSection(root, data); + + for (var k in changes) + applyClassIf(k + '-select', classSelector(changes[k])); +} + +// Given <section data-selection="x,y">: +// - hide section if selections x or y are null +// - re-render templates if x or y have changed +function updateSection(root, data) { + let changed = root.selection == null; + root.selection ||= {}; + for (key of root.dataset.selection.split(',')) { + if (!key) continue; + if (data.selection[key] != root.selection[key]) { + root.selection[key] = data.selection[key]; + changed = true; + } + if (data.selection[key] == null) { + root.hidden = true; + return; + } + } + root.hidden = false; + if (changed) { + for (tmpl of root.getElementsByTagName('template')) { + // Clear previously rendered template contents. + while (tmpl.nextSibling && tmpl.nextSibling.inflated) + tmpl.parentNode.removeChild(tmpl.nextSibling); + inflate(tmpl, data, tmpl.parentNode, tmpl.nextSibling); + } + } +} + +// Expands template `tmpl` based on input `data`: +// - interpolates {{expressions}} in text and attributes +// - <template> tags can modify expansion: if, for etc +// Outputs to `parent` element, inserting before `next`. +function inflate(tmpl, data, parent, next) { + // We use eval() as our expression language in templates! + // The templates are static and trusted. + let evalExpr = (expr, data) => eval('with (data) { ' + expr + ' }'); + let interpolate = (str, data) => + str.replace(/\{\{(.*?)\}\}/g, (_, expr) => evalExpr(expr, data)) + // Anything other than <template> tag: copy, interpolate, recursively inflate. + if (tmpl.nodeName != 'TEMPLATE') { + let clone = tmpl.cloneNode(); + clone.inflated = true; + if (clone instanceof Text) + clone.textContent = interpolate(clone.textContent, data); + if (clone instanceof Element) { + for (attr of clone.attributes) + attr.value = interpolate(attr.value, data); + for (c of tmpl.childNodes) + inflate(c, data, clone, /*next=*/null); + } + return parent.insertBefore(clone, next); + } + // <template> tag handling. Base case: recursively inflate. + function handle(data) { + for (c of tmpl.content.childNodes) + inflate(c, data, parent, next); + } + // Directives on <template> tags modify behavior. + const directives = { + // data-for="x in expr": expr is enumerable, bind x to each in turn + 'for': (nameInExpr, data, proceed) => { + let [name, expr] = nameInExpr.split(' in '); + let newData = Object.create(data); + let index = 0; + for (val of evalExpr(expr, data) || []) { + newData[name] = val; + newData[name + '_index'] = index++; + proceed(newData); + } + }, + // data-if="expr": only include contents if expression is truthy + 'if': (expr, data, proceed) => { if (evalExpr(expr, data)) proceed(data); }, + // data-let="x = expr": bind x to value of expr + 'let': (nameEqExpr, data, proceed) => { + let [name, expr] = nameEqExpr.split(' = '); + let newData = Object.create(data); + newData[name] = evalExpr(expr, data); + proceed(newData); + }, + } + // Compose directive handlers on top of the base handler. + for (let [dir, value] of Object.entries(tmpl.dataset).reverse()) { + if (dir in directives) { + let proceed = handle; + handle = (data) => directives[dir](value, data, proceed); + } + } + handle(data); +} + +// Handle a mouse event on a region containing selectable items. +// This might end up changing the hover state or the selection state. +// +// targetSelector describes what target HTML element is selectable. +// targetToID specifies how to determine the selection from it: +// hover: a function from target to the class name to highlight +// bb: a function from target to the basic-block name to select (BB4)A +// elt: a function from target to the CFG element name to select (BB4.5) +// iter: a function from target to the BB iteration to select (BB4:2) +// If an entry is missing, the selection is unmodified. +// If an entry is null, the selection is always cleared. +function mouseEventHandler(event, targetSelector, targetToID, data) { + var target = event.type == "mouseout" ? null : event.target.closest(targetSelector); + let selTarget = k => (target && targetToID[k]) ? targetToID[k](target) : null; + if (event.type == "click") { + let newSel = {}; + for (var k in targetToID) { + if (k == 'hover') continue; + let t = selTarget(k); + newSel[k] = t; + } + updateSelection(newSel, data); + } else if ("hover" in targetToID) { + applyClassIf("hover", classSelector(selTarget("hover"))); + } +} +function watch(rootSelector, targetSelector, targetToID, data) { + var root = document.querySelector(rootSelector); + for (event of ['mouseout', 'mousemove', 'click']) + root.addEventListener(event, e => mouseEventHandler(e, targetSelector, targetToID, data)); +} +function watchSelection(data) { + let lastIter = (bb) => `${bb}:${data.cfg[bb].iters}`; + watch('#code', '.c', { + hover: e => e.dataset.elt, + bb: e => e.dataset.bb, + elt: e => e.dataset.elt, + // If we're already viewing an iteration of this BB, stick with the same. + iter: e => (selection.iter && selection.bb == e.dataset.bb) ? selection.iter : lastIter(e.dataset.bb), + }, data); + watch('#cfg', '.bb', { + hover: e => e.id, + bb: e => e.id, + elt: e => e.id + ".0", + iter: e => lastIter(e.id), + }, data); + watch('#timeline', '.entry', { + hover: e => [e.id, e.dataset.bb], + bb: e => e.dataset.bb, + elt: e => e.dataset.bb + ".0", + iter: e => e.id, + }, data); + watch('#bb-elements', 'tr', { + hover: e => e.id, + elt: e => e.id, + }, data); + watch('#iterations', '.chooser', { + hover: e => e.dataset.iter, + iter: e => e.dataset.iter, + }, data); + updateSelection({}, data); +} +function applyClassIf(cls, query) { + document.querySelectorAll('.' + cls).forEach(elt => elt.classList.remove(cls)); + document.querySelectorAll(query).forEach(elt => elt.classList.add(cls)); +} +function classSelector(cls) { + if (cls == null) return null; + if (Array.isArray(cls)) return cls.map(classSelector).join(', '); + var escaped = cls.replace('.', '\\.').replace(':', '\\:'); + // don't require id="foo" class="foo" + return '.' + escaped + ", #" + escaped; +} + +// Add a stylesheet defining colors for n basic blocks. +function addBBColors(n) { + let sheet = new CSSStyleSheet(); + // hex values to subtract from fff to get a base color + options = [0x001, 0x010, 0x011, 0x100, 0x101, 0x110, 0x111]; + function color(hex) { + return "#" + hex.toString(16).padStart(3, "0"); + } + function add(selector, property, hex) { + sheet.insertRule(`${selector} { ${property}: ${color(hex)}; }`) + } + for (var i = 0; i < n; ++i) { + let opt = options[i%options.length]; + add(`.B${i}`, 'background-color', 0xfff - 2*opt); + add(`#B${i} polygon`, 'fill', 0xfff - 2*opt); + add(`#B${i} polygon`, 'stroke', 0x888 - 4*opt); + } + document.adoptedStyleSheets.push(sheet); +} Index: clang/lib/Analysis/FlowSensitive/HTMLLogger.html =================================================================== --- /dev/null +++ clang/lib/Analysis/FlowSensitive/HTMLLogger.html @@ -0,0 +1,66 @@ +<!doctype html> +<html> + +<head> +<?INJECT?> +</head> + +<body> + +<section id="timeline" data-selection=""> +<header>Timeline</header> +<template data-for="entry in timeline"> + <div id="{{entry.block}}:{{entry.iter}}" data-bb="{{entry.block}}" class="entry">{{entry.block}} ({{entry.iter}})</div> +</template> +</section> + +<section id="function" data-selection=""> +<header>Function</header> +<div id="code"></div> +<div id="cfg"></div> +</section> + +<section id="block" data-selection="bb"> +<header><template>Block {{selection.bb}}</template></header> +<div id="iterations"> + <template data-for="i in Array(cfg[selection.bb].iters).keys()"> + <a class="chooser {{selection.bb}}:{{i+1}}" data-iter="{{selection.bb}}:{{i+1}}">Iteration {{i+1}}</a> + </template> +</div> +<table id="bb-elements"> +<template data-for="elt in cfg[selection.bb].elements"> + <tr id="{{selection.bb}}.{{elt_index}}"> + <td class="{{selection.bb}}">{{selection.bb}}.{{elt_index}}</td> + <td>{{elt}}</td> + </tr> +</template> +</table> +</section> + +<section id="element" data-selection="iter,elt"> +<template data-let="state = states[selection.iter + '_' + selection.elt]"> +<header> + <template data-if="state.element == 0">{{state.block}} (iteration {{state.iter}}) initial state</template> + <template data-if="state.element != 0">Element {{selection.elt}} (iteration {{state.iter}})</template> +</header> +<template data-if="state.logs"> + <h2>Logs</h2> + <pre>{{state.logs}}</pre> +</template> +<h2>Built-in lattice</h2> +<pre>{{state.builtinLattice}}</pre> +</template> +</section> + +<script> +addBBColors(Object.keys(HTMLLoggerData.cfg).length); +watchSelection(HTMLLoggerData); +updateSelection({}, HTMLLoggerData); +// Copy code and cfg from <template>s into the body. +for (tmpl of document.querySelectorAll('template[data-copy]')) + document.getElementById(tmpl.dataset.copy).replaceChildren( + ...tmpl.content.cloneNode(/*deep=*/true).childNodes); +</script> + +</body> +</html> Index: clang/lib/Analysis/FlowSensitive/HTMLLogger.css =================================================================== --- /dev/null +++ clang/lib/Analysis/FlowSensitive/HTMLLogger.css @@ -0,0 +1,118 @@ +/*===-- HTMLLogger.css ----------------------------------------------------=== +* +* Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions. +* See https://llvm.org/LICENSE.txt for license information. +* SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception +* +*===----------------------------------------------------------------------===*/ +html { font-family: sans-serif; } +body { margin: 0; display: flex; justify-content: left; } +body > * { box-sizing: border-box; } +body > section { + border: 1px solid black; + min-width: 20em; + overflow: auto; + max-height: 100vh; +} +section header { + background-color: #008; + color: white; + font-weight: bold; + font-size: large; +} +section h2 { + font-size: medium; + margin-bottom: 0.5em; + padding-top: 0.5em; + border-top: 1px solid #aaa; +} +#timeline { + min-width: 0; +} +#timeline .entry.hover { + background-color: #aaa; +} +#timeline .entry.iter-select { + background-color: #aac; +} + +#bb-elements { + font-family: monospace; + font-size: x-small; + border-collapse: collapse; +} +#bb-elements td:nth-child(1) { + text-align: right; + width: 4em; + border-right: 1px solid #008; + padding: 0.3em 0.5em; + + font-weight: bold; + color: #888; +}; +#bb-elements tr.hover { + background-color: #abc; +} +#bb-elements tr.elt-select { + background-color: #acf; +} +#iterations { + display: flex; +} +#iterations .chooser { + flex-grow: 1; + text-align: center; +} +#iterations .chooser:not(.iter-select).hover { + background-color: #aaa; +} +#iterations .iter-select { + font-weight: bold; + background-color: #ccc; +} +#iterations .chooser:not(.iter-select) { + text-decoration: underline; + color: blue; +} + +code.filename { + font-weight: bold; + color: black; + background-color: #ccc; + display: block; + text-align: center; +} +code.line { + display: block; + white-space: pre; +} +code.line:before { /* line numbers */ + content: attr(data-line); + display: inline-block; + width: 2em; + text-align: right; + padding-right: 2px; + background-color: #ccc; + border-right: 1px solid #888; + margin-right: 8px; +} +code.line:has(.bb-select):before { + border-right: 4px solid black; + margin-right: 5px; +} +.c.hover, .bb.hover { + filter: saturate(200%) brightness(90%); +} +.c.elt-select { + box-shadow: inset 0 -4px 2px -2px #a00; +} +.bb.bb-select polygon { + stroke-width: 4px; + filter: brightness(70%) saturate(150%); +} +.bb { user-select: none; } +.bb polygon { fill: white; } +#cfg { + position: relative; + margin-left: 0.5em; +} Index: clang/lib/Analysis/FlowSensitive/HTMLLogger.cpp =================================================================== --- /dev/null +++ clang/lib/Analysis/FlowSensitive/HTMLLogger.cpp @@ -0,0 +1,460 @@ +//===-- HTMLLogger.cpp ----------------------------------------------------===// +// +// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions. +// See https://llvm.org/LICENSE.txt for license information. +// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception +// +//===----------------------------------------------------------------------===// +// +// This file implements the HTML logger. Given a directory dir/, we write +// dir/0.html for the first analysis, etc. +// These files contain a visualization that allows inspecting the CFG and the +// state of the analysis at each point. +// Static assets (HTMLLogger.js, HTMLLogger.css) and SVG graphs etc are embedded +// so each output file is self-contained. +// +// VIEWS +// +// The timeline and function view are always shown. These allow selecting basic +// blocks, statements within them, and processing iterations (BBs are visited +// multiple times when e.g. loops are involved). +// These are written directly into the HTML body. +// +// There are also listings of particular basic blocks, and dumps of the state +// at particular analysis points (i.e. BB2 iteration 3 statement 2). +// These are only shown when the relevant BB/analysis point is *selected*. +// +// DATA AND TEMPLATES +// +// The HTML proper is mostly static. +// The analysis data is in a JSON object HTMLLoggerData which is embedded as +// a <script> in the <head>. +// This gets rendered into DOM by a simple template processor which substitutes +// the data into <template> tags embedded in the HTML. (see inflate() in JS). +// +// SELECTION +// +// This is the only real interactive mechanism. +// +// At any given time, there are several named selections, e.g.: +// bb: B2 (basic block 0 is selected) +// elt: B2.4 (statement 4 is selected) +// iter: B2:1 (iteration 1 of the basic block is selected) +// hover: B3 (hovering over basic block 3) +// +// The selection is updated by mouse events: hover by moving the mouse and +// others by clicking. Elements that are click targets generally have attributes +// (id or data-foo) that define what they should select. +// See watchSelection() in JS for the exact logic. +// +// When the "bb" selection is set to "B2": +// - sections <section data-selection="bb"> get shown +// - templates under such sections get re-rendered +// - elements with class/id "B2" get class "bb-select" +// +//===----------------------------------------------------------------------===// + +#include "clang/Analysis/FlowSensitive/ControlFlowContext.h" +#include "clang/Analysis/FlowSensitive/DebugSupport.h" +#include "clang/Analysis/FlowSensitive/Logger.h" +#include "clang/Analysis/FlowSensitive/TypeErasedDataflowAnalysis.h" +#include "clang/Analysis/FlowSensitive/Value.h" +#include "clang/Basic/SourceManager.h" +#include "clang/Lex/Lexer.h" +#include "llvm/ADT/DenseMap.h" +#include "llvm/ADT/ScopeExit.h" +#include "llvm/Support/Error.h" +#include "llvm/Support/FormatVariadic.h" +#include "llvm/Support/JSON.h" +#include "llvm/Support/Program.h" +#include "llvm/Support/raw_ostream.h" +// Defines assets: HTMLLogger_{html_js,css} +#include "HTMLLogger.inc" + +namespace clang::dataflow { +namespace { + +void escape(char C, llvm::raw_ostream &OS) { + switch (C) { + case '<': + OS << "<"; + break; + case '&': + OS << "&"; + break; + case '"': + OS << """; + break; + case '\'': + OS << "'"; + break; + default: + OS << C; + break; + } +} +void escape(llvm::StringRef S, llvm::raw_ostream &OS) { + for (char C : S) + escape(C, OS); +} +// Render a graphviz graph specification to SVG using the `dot` tool. +llvm::Expected<std::string> renderSVG(llvm::StringRef DotGraph); + +using StreamFactory = std::function<std::unique_ptr<llvm::raw_ostream>()>; + +class HTMLLogger : public Logger { + StreamFactory Streams; + std::unique_ptr<llvm::raw_ostream> OS; + std::optional<llvm::json::OStream> JOS; + + const ControlFlowContext *CFG; + // Timeline of iterations of CFG block visitation. + std::vector<std::pair<const CFGBlock *, unsigned>> Iters; + // Number of times each CFG block has been seen. + llvm::DenseMap<const CFGBlock *, unsigned> BlockIters; + // The messages logged in the current context but not yet written. + std::string ContextLogs; + // The number of elements we have visited within the current CFG block. + unsigned ElementIndex; + +public: + explicit HTMLLogger(StreamFactory Streams) : Streams(std::move(Streams)) {} + void beginAnalysis(const ControlFlowContext &CFG, + TypeErasedDataflowAnalysis &A) override { + OS = Streams(); + this->CFG = &CFG; + *OS << llvm::StringRef(HTMLLogger_html).split("<?INJECT?>").first; + *OS << "<style>" << HTMLLogger_css << "</style>\n"; + *OS << "<script>" << HTMLLogger_js << "</script>\n"; + + writeCode(); + writeCFG(); + + *OS << "<script>var HTMLLoggerData = \n"; + JOS.emplace(*OS, /*Indent=*/2); + JOS->objectBegin(); + JOS->attributeBegin("states"); + JOS->objectBegin(); + } + // Between beginAnalysis() and endAnalysis() we write all the states for + // particular analysis points into the `timeline` array. + void endAnalysis() override { + JOS->objectEnd(); + JOS->attributeEnd(); + + JOS->attributeArray("timeline", [&] { + for (const auto &E : Iters) { + JOS->object([&] { + JOS->attribute("block", blockID(E.first->getBlockID())); + JOS->attribute("iter", E.second); + }); + } + }); + JOS->attributeObject("cfg", [&] { + for (const auto &E : BlockIters) + writeBlock(*E.first, E.second); + }); + + JOS->objectEnd(); + JOS.reset(); + *OS << ";\n</script>\n"; + *OS << llvm::StringRef(HTMLLogger_html).split("<?INJECT?>").second; + } + + void enterBlock(const CFGBlock &B) override { + Iters.emplace_back(&B, ++BlockIters[&B]); + ElementIndex = 0; + } + void enterElement(const CFGElement &E) override { + ++ElementIndex; + } + + static std::string blockID(unsigned Block) { + return llvm::formatv("B{0}", Block); + } + static std::string eltID(unsigned Block, unsigned Element) { + return llvm::formatv("B{0}.{1}", Block, Element); + } + static std::string iterID(unsigned Block, unsigned Iter) { + return llvm::formatv("B{0}:{1}", Block, Iter); + } + static std::string elementIterID(unsigned Block, unsigned Iter, + unsigned Element) { + return llvm::formatv("B{0}:{1}_B{0}.{2}", Block, Iter, Element); + } + + // Write the analysis state associated with a particular analysis point. + // FIXME: this dump is fairly opaque. We should show: + // - values associated with the current Stmt + // - values associated with its children + // - meaningful names for values + // - which boolean values are implied true/false by the flow condition + void recordState(TypeErasedDataflowAnalysisState &State) override { + unsigned Block = Iters.back().first->getBlockID(); + unsigned Iter = Iters.back().second; + JOS->attributeObject(elementIterID(Block, Iter, ElementIndex), [&] { + JOS->attribute("block", blockID(Block)); + JOS->attribute("iter", Iter); + JOS->attribute("element", ElementIndex); + if (!ContextLogs.empty()) { + JOS->attribute("logs", ContextLogs); + ContextLogs.clear(); + } + { + std::string BuiltinLattice; + llvm::raw_string_ostream BuiltinLatticeS(BuiltinLattice); + State.Env.dump(BuiltinLatticeS); + JOS->attribute("builtinLattice", BuiltinLattice); + } + }); + } + void blockConverged() override { logText("Block converged"); } + + void logText(llvm::StringRef S) override { + ContextLogs.append(S.begin(), S.end()); + ContextLogs.push_back('\n'); + } + +private: + // Write the CFG block details. + // Currently this is just the list of elements in execution order. + // FIXME: an AST dump would be a useful view, too. + void writeBlock(const CFGBlock &B, unsigned Iters) { + JOS->attributeObject(blockID(B.getBlockID()), [&] { + JOS->attribute("iters", Iters); + JOS->attributeArray("elements", [&] { + for (const auto &Elt : B.Elements) { + std::string Dump; + llvm::raw_string_ostream DumpS(Dump); + Elt.dumpToStream(DumpS); + JOS->value(Dump); + } + }); + }); + } + + // Write the code of function being examined. + // We want to overlay the code with <span>s that mark which BB particular + // tokens are associated with, and even which BB element (so that clicking + // can select the right element). + void writeCode() { + if (!CFG->getDecl()) + return; + const auto &AST = CFG->getDecl()->getASTContext(); + bool Invalid = false; + + // Extract the source code from the original file. + // Pretty-printing from the AST would probably be nicer (no macros or + // indentation to worry about), but we need the boundaries of particular + // AST nodes and the printer doesn't provide this. + auto Range = clang::Lexer::makeFileCharRange( + CharSourceRange::getTokenRange(CFG->getDecl()->getSourceRange()), + AST.getSourceManager(), AST.getLangOpts()); + if (Range.isInvalid()) + return; + llvm::StringRef Code = clang::Lexer::getSourceText( + Range, AST.getSourceManager(), AST.getLangOpts(), &Invalid); + if (Invalid) + return; + + static constexpr unsigned Missing = -1; + // TokenInfo stores the BB and set of elements that a token is part of. + struct TokenInfo { + // The basic block this is part of. + // This is the BB of the stmt with the smallest containing range. + unsigned BB = Missing; + unsigned BBPriority = 0; + // The most specific stmt this is part of (smallest range). + unsigned Elt = Missing; + unsigned EltPriority = 0; + // All stmts this is part of. + SmallVector<unsigned> Elts; + + // Mark this token as being part of BB.Elt. + // RangeLen is the character length of the element's range, used to + // distinguish inner vs outer statements. + // For example in `a==0`, token "a" is part of the stmts "a" and "a==0". + // However "a" has a smaller range, so is more specific. Clicking on the + // token "a" should select the stmt "a". + void assign(unsigned BB, unsigned Elt, unsigned RangeLen) { + // A worse BB (larger range) => ignore. + if (this->BB != Missing && BB != this->BB && BBPriority <= RangeLen) + return; + if (BB != this->BB) { + this->BB = BB; + Elts.clear(); + BBPriority = RangeLen; + } + BBPriority = std::min(BBPriority, RangeLen); + Elts.push_back(Elt); + if (this->Elt == Missing || EltPriority > RangeLen) + this->Elt = Elt; + } + bool operator==(const TokenInfo &Other) const { + return std::tie(BB, Elt, Elts) == + std::tie(Other.BB, Other.Elt, Other.Elts); + } + // Write the attributes for the <span> on this token. + void write(llvm::raw_ostream &OS) const { + OS << "class='c"; + if (BB != Missing) + OS << " " << blockID(BB); + for (unsigned Elt : Elts) + OS << " " << eltID(BB, Elt); + OS << "'"; + + if (Elt != Missing) + OS << " data-elt='" << eltID(BB, Elt) << "'"; + if (BB != Missing) + OS << " data-bb='" << blockID(BB) << "'"; + } + }; + + // Construct one TokenInfo per character in a flat array. + // This is inefficient (chars in a token all have the same info) but simple. + std::vector<TokenInfo> State(Code.size()); + for (const auto *Block : CFG->getCFG()) { + unsigned EltIndex = 0; + for (const auto& Elt : *Block) { + ++EltIndex; + if (const auto S = Elt.getAs<CFGStmt>()) { + auto EltRange = clang::Lexer::makeFileCharRange( + CharSourceRange::getTokenRange(S->getStmt()->getSourceRange()), + AST.getSourceManager(), AST.getLangOpts()); + if (EltRange.isInvalid()) + continue; + if (EltRange.getBegin() < Range.getBegin() || + EltRange.getEnd() >= Range.getEnd() || + EltRange.getEnd() < Range.getBegin() || + EltRange.getEnd() >= Range.getEnd()) + continue; + unsigned Off = EltRange.getBegin().getRawEncoding() - + Range.getBegin().getRawEncoding(); + unsigned Len = EltRange.getEnd().getRawEncoding() - + EltRange.getBegin().getRawEncoding(); + for (unsigned I = 0; I < Len; ++I) + State[Off + I].assign(Block->getBlockID(), EltIndex, Len); + } + } + } + + // Finally, write the code with the correct <span>s. + unsigned Line = + AST.getSourceManager().getSpellingLineNumber(Range.getBegin()); + *OS << "<template data-copy='code'>\n"; + *OS << "<code class='filename'>"; + escape(AST.getSourceManager().getFilename(Range.getBegin()), *OS); + *OS << "</code>"; + *OS << "<code class='line' data-line='" << Line++ << "'>"; + for (unsigned I = 0; I < Code.size(); ++I) { + // Don't actually write a <span> around each character, only break spans + // when the TokenInfo changes. + bool NeedOpen = I == 0 || !(State[I] == State[I-1]); + bool NeedClose = I + 1 == Code.size() || !(State[I] == State[I + 1]); + if (NeedOpen) { + *OS << "<span "; + State[I].write(*OS); + *OS << ">"; + } + if (Code[I] == '\n') + *OS << "</code>\n<code class='line' data-line='" << Line++ << "'>"; + else + escape(Code[I], *OS); + if (NeedClose) *OS << "</span>"; + } + *OS << "</code>\n"; + *OS << "</template>"; + } + + // Write the CFG diagram, a graph of basic blocks. + // Laying out graphs is hard, so we construct a graphviz description and shell + // out to `dot` to turn it into an SVG. + void writeCFG() { + *OS << "<template data-copy='cfg'>\n"; + if (auto SVG = renderSVG(buildCFGDot(CFG->getCFG()))) + *OS << *SVG; + else + *OS << "Can't draw CFG: " << toString(SVG.takeError()); + *OS << "</template>\n"; + } + + // Produce a graphviz description of a CFG. + static std::string buildCFGDot(const clang::CFG &CFG) { + std::string Graph; + llvm::raw_string_ostream GraphS(Graph); + // Graphviz likes to add unhelpful tooltips everywhere, " " suppresses. + GraphS << R"(digraph { + tooltip=" " + node[class=bb, shape=square, fontname="sans-serif", tooltip=" "] + edge[tooltip = " "] +)"; + for (unsigned I = 0; I < CFG.getNumBlockIDs(); ++I) + GraphS << " " << blockID(I) << " [id=" << blockID(I) << "]\n"; + for (const auto *Block : CFG) { + for (const auto &Succ : Block->succs()) { + GraphS << " " << blockID(Block->getBlockID()) << " -> " + << blockID(Succ.getReachableBlock()->getBlockID()) << "\n"; + } + } + GraphS << "}\n"; + return Graph; + } +}; + +// Nothing interesting here, just subprocess/temp-file plumbing. +llvm::Expected<std::string> renderSVG(llvm::StringRef DotGraph) { + auto Dot = llvm::sys::findProgramByName("dot"); + if (!Dot) + return llvm::createStringError(Dot.getError(), + "Can't draw CFG: 'dot' not found on PATH"); + + // Create input and output files for `dot` subprocess. + // (We create the output file as empty, to reserve the temp filename). + llvm::SmallString<256> Input, Output; + int InputFD; + if (auto EC = llvm::sys::fs::createTemporaryFile("analysis", ".dot", InputFD, + Input)) + return llvm::createStringError(EC, "failed to create `dot` temp input"); + llvm::raw_fd_ostream(InputFD, /*shouldClose=*/true) << DotGraph; + auto DeleteInput = + llvm::make_scope_exit([&] { llvm::sys::fs::remove(Input); }); + if (auto EC = llvm::sys::fs::createTemporaryFile("analysis", ".svg", Output)) + return llvm::createStringError(EC, "failed to create `dot` temp output"); + auto DeleteOutput = + llvm::make_scope_exit([&] { llvm::sys::fs::remove(Output); }); + + std::vector<std::optional<llvm::StringRef>> Redirects = { + Input, Output, + /*stderr=*/std::nullopt}; + std::string ErrMsg; + int Code = llvm::sys::ExecuteAndWait( + *Dot, {"dot", "-Tsvg"}, /*Env=*/std::nullopt, Redirects, + /*SecondsToWait=*/0, /*MemoryLimit=*/0, &ErrMsg); + if (!ErrMsg.empty()) + return llvm::createStringError(llvm::inconvertibleErrorCode(), + "'dot' failed: " + ErrMsg); + if (Code != 0) + return llvm::createStringError(llvm::inconvertibleErrorCode(), + "'dot' failed (" + llvm::Twine(Code) + ")"); + + auto Buf = llvm::MemoryBuffer::getFile(Output); + if (!Buf) + return llvm::createStringError(Buf.getError(), "Can't read `dot` output"); + + // Output has <?xml> prefix we don't want. Skip to <svg> tag. + llvm::StringRef Result = Buf.get()->getBuffer(); + auto Pos = Result.find("<svg"); + if (Pos == llvm::StringRef::npos) + return llvm::createStringError(llvm::inconvertibleErrorCode(), + "Can't find <svg> tag in `dot` output"); + return Result.substr(Pos).str(); +} + +} // namespace + +std::unique_ptr<Logger> +Logger::html(std::function<std::unique_ptr<llvm::raw_ostream>()> Streams) { + return std::make_unique<HTMLLogger>(std::move(Streams)); +} + +} // namespace clang::dataflow Index: clang/lib/Analysis/FlowSensitive/DataflowAnalysisContext.cpp =================================================================== --- clang/lib/Analysis/FlowSensitive/DataflowAnalysisContext.cpp +++ clang/lib/Analysis/FlowSensitive/DataflowAnalysisContext.cpp @@ -20,14 +20,17 @@ #include "llvm/ADT/SetOperations.h" #include "llvm/Support/CommandLine.h" #include "llvm/Support/Debug.h" +#include "llvm/Support/FileSystem.h" +#include "llvm/Support/Path.h" #include <cassert> #include <memory> #include <utility> -static llvm::cl::opt<std::string> - DataflowLog("dataflow-log", llvm::cl::Hidden, llvm::cl::ValueOptional, - llvm::cl::desc("Emit log of dataflow analysis. With no arg, " - "writes textual log to stderr.")); +static llvm::cl::opt<std::string> DataflowLog( + "dataflow-log", llvm::cl::Hidden, llvm::cl::ValueOptional, + llvm::cl::desc("Emit log of dataflow analysis. With no arg, writes textual " + "log to stderr. With an arg, writes HTML logs under the " + "specified directory (one per analyzed function).")); namespace clang { namespace dataflow { @@ -382,6 +385,34 @@ return nullptr; } +static std::unique_ptr<Logger> makeLoggerFromCommandLine() { + if (DataflowLog.empty()) + return Logger::textual(llvm::errs()); + + llvm::StringRef Dir = DataflowLog; + if (auto EC = llvm::sys::fs::create_directories(Dir)) + llvm::errs() << "Failed to create log dir: " << EC.message() << "\n"; + // All analysis runs within a process will log to the same directory. + // Share a counter so they don't all overwrite each other's 0.html. + // (Don't share a logger, it's not threadsafe). + static std::atomic<unsigned> Counter = {0}; + auto StreamFactory = + [Dir(Dir.str())]() mutable -> std::unique_ptr<llvm::raw_ostream> { + llvm::SmallString<256> File(Dir); + llvm::sys::path::append(File, + std::to_string(Counter.fetch_add(1)) + ".html"); + std::error_code EC; + auto OS = std::make_unique<llvm::raw_fd_ostream>(File, EC); + if (EC) { + llvm::errs() << "Failed to create log " << File << ": " << EC.message() + << "\n"; + return std::make_unique<llvm::raw_null_ostream>(); + } + return OS; + }; + return Logger::html(std::move(StreamFactory)); +} + DataflowAnalysisContext::DataflowAnalysisContext(std::unique_ptr<Solver> S, Options Opts) : S(std::move(S)), TrueVal(createAtomicBoolValue()), @@ -392,7 +423,7 @@ // based tools. if (Opts.Log == nullptr) { if (DataflowLog.getNumOccurrences() > 0) { - LogOwner = Logger::textual(llvm::errs()); + LogOwner = makeLoggerFromCommandLine(); this->Opts.Log = LogOwner.get(); // FIXME: if the flag is given a value, write an HTML log to a file. } else { Index: clang/lib/Analysis/FlowSensitive/CMakeLists.txt =================================================================== --- clang/lib/Analysis/FlowSensitive/CMakeLists.txt +++ clang/lib/Analysis/FlowSensitive/CMakeLists.txt @@ -2,6 +2,7 @@ ControlFlowContext.cpp DataflowAnalysisContext.cpp DataflowEnvironment.cpp + HTMLLogger.cpp Logger.cpp Transfer.cpp TypeErasedDataflowAnalysis.cpp @@ -16,3 +17,14 @@ ) add_subdirectory(Models) + +add_custom_command(OUTPUT HTMLLogger.inc + COMMAND "${Python3_EXECUTABLE}" ${CLANG_SOURCE_DIR}/utils/bundle_resources.py + ${CMAKE_CURRENT_BINARY_DIR}/HTMLLogger.inc + HTMLLogger.html HTMLLogger.css HTMLLogger.js + WORKING_DIRECTORY ${CMAKE_CURRENT_SOURCE_DIR} + COMMENT "Bundling HTMLLogger resources" + DEPENDS ${CLANG_SOURCE_DIR}/utils/bundle_resources.py HTMLLogger.html HTMLLogger.css HTMLLogger.js + VERBATIM) +add_custom_target(clangAnalysisFlowSensitiveResources DEPENDS HTMLLogger.inc) +add_dependencies(clangAnalysisFlowSensitive clangAnalysisFlowSensitiveResources) Index: clang/include/clang/Analysis/FlowSensitive/Logger.h =================================================================== --- clang/include/clang/Analysis/FlowSensitive/Logger.h +++ clang/include/clang/Analysis/FlowSensitive/Logger.h @@ -31,6 +31,10 @@ /// A logger that simply writes messages to the specified ostream in real /// time. static std::unique_ptr<Logger> textual(llvm::raw_ostream &); + /// A logger that builds an HTML UI to inspect the analysis results. + /// Each function's analysis is written to a stream obtained from the factory. + static std::unique_ptr<Logger> + html(std::function<std::unique_ptr<llvm::raw_ostream>()>); virtual ~Logger() = default;
_______________________________________________ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
