| 1 | /* |
| 2 | * Copyright (C) 2011 Google, Inc. All rights reserved. |
| 3 | * Copyright (C) 2016 Apple Inc. All rights reserved. |
| 4 | * |
| 5 | * Redistribution and use in source and binary forms, with or without |
| 6 | * modification, are permitted provided that the following conditions |
| 7 | * are met: |
| 8 | * 1. Redistributions of source code must retain the above copyright |
| 9 | * notice, this list of conditions and the following disclaimer. |
| 10 | * 2. Redistributions in binary form must reproduce the above copyright |
| 11 | * notice, this list of conditions and the following disclaimer in the |
| 12 | * documentation and/or other materials provided with the distribution. |
| 13 | * |
| 14 | * THIS SOFTWARE IS PROVIDED BY GOOGLE INC. ``AS IS'' AND ANY |
| 15 | * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE |
| 16 | * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR |
| 17 | * PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL APPLE INC. OR |
| 18 | * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, |
| 19 | * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, |
| 20 | * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR |
| 21 | * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY |
| 22 | * OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT |
| 23 | * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE |
| 24 | * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. |
| 25 | */ |
| 26 | |
| 27 | #include "config.h" |
| 28 | #include "ContentSecurityPolicySourceList.h" |
| 29 | |
| 30 | #include "ContentSecurityPolicy.h" |
| 31 | #include "ContentSecurityPolicyDirectiveNames.h" |
| 32 | #include "ParsingUtilities.h" |
| 33 | #include "TextEncoding.h" |
| 34 | #include <wtf/ASCIICType.h> |
| 35 | #include <wtf/NeverDestroyed.h> |
| 36 | #include <wtf/URL.h> |
| 37 | #include <wtf/text/Base64.h> |
| 38 | |
| 39 | namespace WebCore { |
| 40 | |
| 41 | static bool isCSPDirectiveName(const String& name) |
| 42 | { |
| 43 | return equalIgnoringASCIICase(name, ContentSecurityPolicyDirectiveNames::baseURI) |
| 44 | || equalIgnoringASCIICase(name, ContentSecurityPolicyDirectiveNames::connectSrc) |
| 45 | || equalIgnoringASCIICase(name, ContentSecurityPolicyDirectiveNames::defaultSrc) |
| 46 | || equalIgnoringASCIICase(name, ContentSecurityPolicyDirectiveNames::fontSrc) |
| 47 | || equalIgnoringASCIICase(name, ContentSecurityPolicyDirectiveNames::formAction) |
| 48 | || equalIgnoringASCIICase(name, ContentSecurityPolicyDirectiveNames::frameSrc) |
| 49 | || equalIgnoringASCIICase(name, ContentSecurityPolicyDirectiveNames::imgSrc) |
| 50 | || equalIgnoringASCIICase(name, ContentSecurityPolicyDirectiveNames::mediaSrc) |
| 51 | || equalIgnoringASCIICase(name, ContentSecurityPolicyDirectiveNames::objectSrc) |
| 52 | || equalIgnoringASCIICase(name, ContentSecurityPolicyDirectiveNames::pluginTypes) |
| 53 | || equalIgnoringASCIICase(name, ContentSecurityPolicyDirectiveNames::reportURI) |
| 54 | || equalIgnoringASCIICase(name, ContentSecurityPolicyDirectiveNames::sandbox) |
| 55 | || equalIgnoringASCIICase(name, ContentSecurityPolicyDirectiveNames::scriptSrc) |
| 56 | || equalIgnoringASCIICase(name, ContentSecurityPolicyDirectiveNames::styleSrc); |
| 57 | } |
| 58 | |
| 59 | static bool isSourceCharacter(UChar c) |
| 60 | { |
| 61 | return !isASCIISpace(c); |
| 62 | } |
| 63 | |
| 64 | static bool isHostCharacter(UChar c) |
| 65 | { |
| 66 | return isASCIIAlphanumeric(c) || c == '-'; |
| 67 | } |
| 68 | |
| 69 | static bool isPathComponentCharacter(UChar c) |
| 70 | { |
| 71 | return c != '?' && c != '#'; |
| 72 | } |
| 73 | |
| 74 | static bool isSchemeContinuationCharacter(UChar c) |
| 75 | { |
| 76 | return isASCIIAlphanumeric(c) || c == '+' || c == '-' || c == '.'; |
| 77 | } |
| 78 | |
| 79 | static bool isNotColonOrSlash(UChar c) |
| 80 | { |
| 81 | return c != ':' && c != '/'; |
| 82 | } |
| 83 | |
| 84 | static bool isSourceListNone(const String& value) |
| 85 | { |
| 86 | auto characters = StringView(value).upconvertedCharacters(); |
| 87 | const UChar* begin = characters; |
| 88 | const UChar* end = characters + value.length(); |
| 89 | skipWhile<UChar, isASCIISpace>(begin, end); |
| 90 | |
| 91 | const UChar* position = begin; |
| 92 | skipWhile<UChar, isSourceCharacter>(position, end); |
| 93 | if (!equalLettersIgnoringASCIICase(begin, position - begin, "'none'" )) |
| 94 | return false; |
| 95 | |
| 96 | skipWhile<UChar, isASCIISpace>(position, end); |
| 97 | if (position != end) |
| 98 | return false; |
| 99 | |
| 100 | return true; |
| 101 | } |
| 102 | |
| 103 | ContentSecurityPolicySourceList::ContentSecurityPolicySourceList(const ContentSecurityPolicy& policy, const String& directiveName) |
| 104 | : m_policy(policy) |
| 105 | , m_directiveName(directiveName) |
| 106 | { |
| 107 | } |
| 108 | |
| 109 | void ContentSecurityPolicySourceList::parse(const String& value) |
| 110 | { |
| 111 | if (isSourceListNone(value)) { |
| 112 | m_isNone = true; |
| 113 | return; |
| 114 | } |
| 115 | auto characters = StringView(value).upconvertedCharacters(); |
| 116 | parse(characters, characters + value.length()); |
| 117 | } |
| 118 | |
| 119 | bool ContentSecurityPolicySourceList::isProtocolAllowedByStar(const URL& url) const |
| 120 | { |
| 121 | if (m_policy.allowContentSecurityPolicySourceStarToMatchAnyProtocol()) |
| 122 | return true; |
| 123 | |
| 124 | // Although not allowed by the Content Security Policy Level 3 spec., we allow a data URL to match |
| 125 | // "img-src *" and either a data URL or blob URL to match "media-src *" for web compatibility. |
| 126 | bool isAllowed = url.protocolIsInHTTPFamily() || url.protocolIs("ws" ) || url.protocolIs("wss" ) || m_policy.protocolMatchesSelf(url); |
| 127 | if (equalIgnoringASCIICase(m_directiveName, ContentSecurityPolicyDirectiveNames::imgSrc)) |
| 128 | isAllowed |= url.protocolIsData(); |
| 129 | else if (equalIgnoringASCIICase(m_directiveName, ContentSecurityPolicyDirectiveNames::mediaSrc)) |
| 130 | isAllowed |= url.protocolIsData() || url.protocolIsBlob(); |
| 131 | return isAllowed; |
| 132 | } |
| 133 | |
| 134 | bool ContentSecurityPolicySourceList::matches(const URL& url, bool didReceiveRedirectResponse) const |
| 135 | { |
| 136 | if (m_allowStar && isProtocolAllowedByStar(url)) |
| 137 | return true; |
| 138 | |
| 139 | if (m_allowSelf && m_policy.urlMatchesSelf(url)) |
| 140 | return true; |
| 141 | |
| 142 | for (auto& entry : m_list) { |
| 143 | if (entry.matches(url, didReceiveRedirectResponse)) |
| 144 | return true; |
| 145 | } |
| 146 | |
| 147 | return false; |
| 148 | } |
| 149 | |
| 150 | bool ContentSecurityPolicySourceList::matches(const ContentSecurityPolicyHash& hash) const |
| 151 | { |
| 152 | return m_hashes.contains(hash); |
| 153 | } |
| 154 | |
| 155 | bool ContentSecurityPolicySourceList::matches(const String& nonce) const |
| 156 | { |
| 157 | return m_nonces.contains(nonce); |
| 158 | } |
| 159 | |
| 160 | // source-list = *WSP [ source *( 1*WSP source ) *WSP ] |
| 161 | // / *WSP "'none'" *WSP |
| 162 | // |
| 163 | void ContentSecurityPolicySourceList::parse(const UChar* begin, const UChar* end) |
| 164 | { |
| 165 | const UChar* position = begin; |
| 166 | |
| 167 | while (position < end) { |
| 168 | skipWhile<UChar, isASCIISpace>(position, end); |
| 169 | if (position == end) |
| 170 | return; |
| 171 | |
| 172 | const UChar* beginSource = position; |
| 173 | skipWhile<UChar, isSourceCharacter>(position, end); |
| 174 | |
| 175 | String scheme, host, path; |
| 176 | Optional<uint16_t> port; |
| 177 | bool hostHasWildcard = false; |
| 178 | bool portHasWildcard = false; |
| 179 | |
| 180 | if (parseNonceSource(beginSource, position)) |
| 181 | continue; |
| 182 | |
| 183 | if (parseHashSource(beginSource, position)) |
| 184 | continue; |
| 185 | |
| 186 | if (parseSource(beginSource, position, scheme, host, port, path, hostHasWildcard, portHasWildcard)) { |
| 187 | // Wildcard hosts and keyword sources ('self', 'unsafe-inline', |
| 188 | // etc.) aren't stored in m_list, but as attributes on the source |
| 189 | // list itself. |
| 190 | if (scheme.isEmpty() && host.isEmpty()) |
| 191 | continue; |
| 192 | if (isCSPDirectiveName(host)) |
| 193 | m_policy.reportDirectiveAsSourceExpression(m_directiveName, host); |
| 194 | m_list.append(ContentSecurityPolicySource(m_policy, scheme, host, port, path, hostHasWildcard, portHasWildcard)); |
| 195 | } else |
| 196 | m_policy.reportInvalidSourceExpression(m_directiveName, String(beginSource, position - beginSource)); |
| 197 | |
| 198 | ASSERT(position == end || isASCIISpace(*position)); |
| 199 | } |
| 200 | |
| 201 | m_list.shrinkToFit(); |
| 202 | } |
| 203 | |
| 204 | // source = scheme ":" |
| 205 | // / ( [ scheme "://" ] host [ port ] [ path ] ) |
| 206 | // / "'self'" |
| 207 | // |
| 208 | bool ContentSecurityPolicySourceList::parseSource(const UChar* begin, const UChar* end, String& scheme, String& host, Optional<uint16_t>& port, String& path, bool& hostHasWildcard, bool& portHasWildcard) |
| 209 | { |
| 210 | if (begin == end) |
| 211 | return false; |
| 212 | |
| 213 | if (equalLettersIgnoringASCIICase(begin, end - begin, "'none'" )) |
| 214 | return false; |
| 215 | |
| 216 | if (end - begin == 1 && *begin == '*') { |
| 217 | m_allowStar = true; |
| 218 | return true; |
| 219 | } |
| 220 | |
| 221 | if (equalLettersIgnoringASCIICase(begin, end - begin, "'self'" )) { |
| 222 | m_allowSelf = true; |
| 223 | return true; |
| 224 | } |
| 225 | |
| 226 | if (equalLettersIgnoringASCIICase(begin, end - begin, "'unsafe-inline'" )) { |
| 227 | m_allowInline = true; |
| 228 | return true; |
| 229 | } |
| 230 | |
| 231 | if (equalLettersIgnoringASCIICase(begin, end - begin, "'unsafe-eval'" )) { |
| 232 | m_allowEval = true; |
| 233 | return true; |
| 234 | } |
| 235 | |
| 236 | const UChar* position = begin; |
| 237 | const UChar* beginHost = begin; |
| 238 | const UChar* beginPath = end; |
| 239 | const UChar* beginPort = nullptr; |
| 240 | |
| 241 | skipWhile<UChar, isNotColonOrSlash>(position, end); |
| 242 | |
| 243 | if (position == end) { |
| 244 | // host |
| 245 | // ^ |
| 246 | return parseHost(beginHost, position, host, hostHasWildcard); |
| 247 | } |
| 248 | |
| 249 | if (position < end && *position == '/') { |
| 250 | // host/path || host/ || / |
| 251 | // ^ ^ ^ |
| 252 | return parseHost(beginHost, position, host, hostHasWildcard) && parsePath(position, end, path); |
| 253 | } |
| 254 | |
| 255 | if (position < end && *position == ':') { |
| 256 | if (end - position == 1) { |
| 257 | // scheme: |
| 258 | // ^ |
| 259 | return parseScheme(begin, position, scheme); |
| 260 | } |
| 261 | |
| 262 | if (position[1] == '/') { |
| 263 | // scheme://host || scheme:// |
| 264 | // ^ ^ |
| 265 | if (!parseScheme(begin, position, scheme) |
| 266 | || !skipExactly<UChar>(position, end, ':') |
| 267 | || !skipExactly<UChar>(position, end, '/') |
| 268 | || !skipExactly<UChar>(position, end, '/')) |
| 269 | return false; |
| 270 | if (position == end) |
| 271 | return false; |
| 272 | beginHost = position; |
| 273 | skipWhile<UChar, isNotColonOrSlash>(position, end); |
| 274 | } |
| 275 | |
| 276 | if (position < end && *position == ':') { |
| 277 | // host:port || scheme://host:port |
| 278 | // ^ ^ |
| 279 | beginPort = position; |
| 280 | skipUntil<UChar>(position, end, '/'); |
| 281 | } |
| 282 | } |
| 283 | |
| 284 | if (position < end && *position == '/') { |
| 285 | // scheme://host/path || scheme://host:port/path |
| 286 | // ^ ^ |
| 287 | if (position == beginHost) |
| 288 | return false; |
| 289 | |
| 290 | beginPath = position; |
| 291 | } |
| 292 | |
| 293 | if (!parseHost(beginHost, beginPort ? beginPort : beginPath, host, hostHasWildcard)) |
| 294 | return false; |
| 295 | |
| 296 | if (!beginPort) |
| 297 | port = WTF::nullopt; |
| 298 | else { |
| 299 | if (!parsePort(beginPort, beginPath, port, portHasWildcard)) |
| 300 | return false; |
| 301 | } |
| 302 | |
| 303 | if (beginPath != end) { |
| 304 | if (!parsePath(beginPath, end, path)) |
| 305 | return false; |
| 306 | } |
| 307 | |
| 308 | return true; |
| 309 | } |
| 310 | |
| 311 | // ; <scheme> production from RFC 3986 |
| 312 | // scheme = ALPHA *( ALPHA / DIGIT / "+" / "-" / "." ) |
| 313 | // |
| 314 | bool ContentSecurityPolicySourceList::parseScheme(const UChar* begin, const UChar* end, String& scheme) |
| 315 | { |
| 316 | ASSERT(begin <= end); |
| 317 | ASSERT(scheme.isEmpty()); |
| 318 | |
| 319 | if (begin == end) |
| 320 | return false; |
| 321 | |
| 322 | const UChar* position = begin; |
| 323 | |
| 324 | if (!skipExactly<UChar, isASCIIAlpha>(position, end)) |
| 325 | return false; |
| 326 | |
| 327 | skipWhile<UChar, isSchemeContinuationCharacter>(position, end); |
| 328 | |
| 329 | if (position != end) |
| 330 | return false; |
| 331 | |
| 332 | scheme = String(begin, end - begin); |
| 333 | return true; |
| 334 | } |
| 335 | |
| 336 | // host = [ "*." ] 1*host-char *( "." 1*host-char ) |
| 337 | // / "*" |
| 338 | // host-char = ALPHA / DIGIT / "-" |
| 339 | // |
| 340 | bool ContentSecurityPolicySourceList::parseHost(const UChar* begin, const UChar* end, String& host, bool& hostHasWildcard) |
| 341 | { |
| 342 | ASSERT(begin <= end); |
| 343 | ASSERT(host.isEmpty()); |
| 344 | ASSERT(!hostHasWildcard); |
| 345 | |
| 346 | if (begin == end) |
| 347 | return false; |
| 348 | |
| 349 | const UChar* position = begin; |
| 350 | |
| 351 | if (skipExactly<UChar>(position, end, '*')) { |
| 352 | hostHasWildcard = true; |
| 353 | |
| 354 | if (position == end) |
| 355 | return true; |
| 356 | |
| 357 | if (!skipExactly<UChar>(position, end, '.')) |
| 358 | return false; |
| 359 | } |
| 360 | |
| 361 | const UChar* hostBegin = position; |
| 362 | |
| 363 | while (position < end) { |
| 364 | if (!skipExactly<UChar, isHostCharacter>(position, end)) |
| 365 | return false; |
| 366 | |
| 367 | skipWhile<UChar, isHostCharacter>(position, end); |
| 368 | |
| 369 | if (position < end && !skipExactly<UChar>(position, end, '.')) |
| 370 | return false; |
| 371 | } |
| 372 | |
| 373 | ASSERT(position == end); |
| 374 | host = String(hostBegin, end - hostBegin); |
| 375 | return true; |
| 376 | } |
| 377 | |
| 378 | bool ContentSecurityPolicySourceList::parsePath(const UChar* begin, const UChar* end, String& path) |
| 379 | { |
| 380 | ASSERT(begin <= end); |
| 381 | ASSERT(path.isEmpty()); |
| 382 | |
| 383 | const UChar* position = begin; |
| 384 | skipWhile<UChar, isPathComponentCharacter>(position, end); |
| 385 | // path/to/file.js?query=string || path/to/file.js#anchor |
| 386 | // ^ ^ |
| 387 | if (position < end) |
| 388 | m_policy.reportInvalidPathCharacter(m_directiveName, String(begin, end - begin), *position); |
| 389 | |
| 390 | path = decodeURLEscapeSequences(String(begin, position - begin)); |
| 391 | |
| 392 | ASSERT(position <= end); |
| 393 | ASSERT(position == end || (*position == '#' || *position == '?')); |
| 394 | return true; |
| 395 | } |
| 396 | |
| 397 | // port = ":" ( 1*DIGIT / "*" ) |
| 398 | // |
| 399 | bool ContentSecurityPolicySourceList::parsePort(const UChar* begin, const UChar* end, Optional<uint16_t>& port, bool& portHasWildcard) |
| 400 | { |
| 401 | ASSERT(begin <= end); |
| 402 | ASSERT(!port); |
| 403 | ASSERT(!portHasWildcard); |
| 404 | |
| 405 | if (!skipExactly<UChar>(begin, end, ':')) |
| 406 | ASSERT_NOT_REACHED(); |
| 407 | |
| 408 | if (begin == end) |
| 409 | return false; |
| 410 | |
| 411 | if (end - begin == 1 && *begin == '*') { |
| 412 | port = WTF::nullopt; |
| 413 | portHasWildcard = true; |
| 414 | return true; |
| 415 | } |
| 416 | |
| 417 | const UChar* position = begin; |
| 418 | skipWhile<UChar, isASCIIDigit>(position, end); |
| 419 | |
| 420 | if (position != end) |
| 421 | return false; |
| 422 | |
| 423 | bool ok; |
| 424 | int portInt = charactersToIntStrict(begin, end - begin, &ok); |
| 425 | if (portInt < 0 || portInt > std::numeric_limits<uint16_t>::max()) |
| 426 | return false; |
| 427 | port = portInt; |
| 428 | return ok; |
| 429 | } |
| 430 | |
| 431 | // Match Blink's behavior of allowing an equal sign to appear anywhere in the value of the nonce |
| 432 | // even though this does not match the behavior of Content Security Policy Level 3 spec., |
| 433 | // <https://w3c.github.io/webappsec-csp/> (29 February 2016). |
| 434 | static bool isNonceCharacter(UChar c) |
| 435 | { |
| 436 | return isBase64OrBase64URLCharacter(c) || c == '='; |
| 437 | } |
| 438 | |
| 439 | // nonce-source = "'nonce-" nonce-value "'" |
| 440 | // nonce-value = base64-value |
| 441 | bool ContentSecurityPolicySourceList::parseNonceSource(const UChar* begin, const UChar* end) |
| 442 | { |
| 443 | const unsigned noncePrefixLength = 7; |
| 444 | if (!StringView(begin, end - begin).startsWithIgnoringASCIICase("'nonce-" )) |
| 445 | return false; |
| 446 | const UChar* position = begin + noncePrefixLength; |
| 447 | const UChar* beginNonceValue = position; |
| 448 | skipWhile<UChar, isNonceCharacter>(position, end); |
| 449 | if (position >= end || position == beginNonceValue || *position != '\'') |
| 450 | return false; |
| 451 | m_nonces.add(String(beginNonceValue, position - beginNonceValue)); |
| 452 | return true; |
| 453 | } |
| 454 | |
| 455 | // hash-source = "'" hash-algorithm "-" base64-value "'" |
| 456 | // hash-algorithm = "sha256" / "sha384" / "sha512" |
| 457 | // base64-value = 1*( ALPHA / DIGIT / "+" / "/" / "-" / "_" )*2( "=" ) |
| 458 | bool ContentSecurityPolicySourceList::parseHashSource(const UChar* begin, const UChar* end) |
| 459 | { |
| 460 | if (begin == end) |
| 461 | return false; |
| 462 | |
| 463 | const UChar* position = begin; |
| 464 | if (!skipExactly<UChar>(position, end, '\'')) |
| 465 | return false; |
| 466 | |
| 467 | auto digest = parseCryptographicDigest(position, end); |
| 468 | if (!digest) |
| 469 | return false; |
| 470 | |
| 471 | if (position >= end || *position != '\'') |
| 472 | return false; |
| 473 | |
| 474 | if (digest->value.size() > ContentSecurityPolicyHash::maximumDigestLength) |
| 475 | return false; |
| 476 | |
| 477 | m_hashAlgorithmsUsed.add(digest->algorithm); |
| 478 | m_hashes.add(WTFMove(*digest)); |
| 479 | return true; |
| 480 | } |
| 481 | |
| 482 | } // namespace WebCore |
| 483 | |