path: root/components/safe_browsing_db/v4_get_hash_protocol_manager.h

// Copyright 2016 The Chromium Authors. All rights reserved.
// Use of this source code is governed by a BSD-style license that can be
// found in the LICENSE file.

#ifndef COMPONENTS_SAFE_BROWSING_DB_V4_GET_HASH_PROTOCOL_MANAGER_H_
#define COMPONENTS_SAFE_BROWSING_DB_V4_GET_HASH_PROTOCOL_MANAGER_H_

// A class that implements Chrome's interface with the SafeBrowsing V4 protocol.
//
// The V4GetHashProtocolManager handles formatting and making requests of, and
// handling responses from, Google's SafeBrowsing servers. The purpose of this
// class is to get full hash matches from the SB server for the given set of
// hash prefixes.

#include <string>
#include <vector>

#include "base/containers/hash_tables.h"
#include "base/gtest_prod_util.h"
#include "base/macros.h"
#include "base/memory/scoped_ptr.h"
#include "base/threading/non_thread_safe.h"
#include "base/time/time.h"
#include "base/timer/timer.h"
#include "components/safe_browsing_db/safebrowsing.pb.h"
#include "components/safe_browsing_db/util.h"
#include "net/url_request/url_fetcher_delegate.h"
#include "net/url_request/url_request_status.h"
#include "url/gurl.h"

namespace net {
class URLFetcher;
class URLRequestContextGetter;
}  // namespace net

namespace safe_browsing {

// Config passed to the constructor of a V4GetHashProtocolManager.
struct V4GetHashProtocolConfig {
  std::string client_name;
  std::string version;
  std::string key_param;
};

class V4GetHashProtocolManagerFactory;

class V4GetHashProtocolManager : public net::URLFetcherDelegate,
                                 public base::NonThreadSafe {
 public:
  // FullHashCallback is invoked when GetFullHashes completes.
  // Parameters:
  //   - The vector of full hash results. If empty, indicates that there
  //     were no matches, and that the resource is safe.
  //   - The negative cache duration of the result.
  typedef base::Callback<void(const std::vector<SBFullHashResult>&,
                              const base::TimeDelta&)>
      FullHashCallback;

  ~V4GetHashProtocolManager() override;

  // Makes the passed |factory| the factory used to instantiate
  // a V4GetHashProtocolManager. Useful for tests.
  static void RegisterFactory(V4GetHashProtocolManagerFactory* factory) {
    factory_ = factory;
  }

  // Create an instance of the safe browsing v4 protocol manager.
  static V4GetHashProtocolManager* Create(
      net::URLRequestContextGetter* request_context_getter,
      const V4GetHashProtocolConfig& config);

  // net::URLFetcherDelegate interface.
  void OnURLFetchComplete(const net::URLFetcher* source) override;

  // Retrieve the full hash for a set of prefixes, and invoke the callback
  // argument when the results are retrieved. The callback may be invoked
  // synchronously.
  virtual void GetFullHashes(const std::vector<SBPrefix>& prefixes,
                             const std::vector<PlatformType>& platforms,
                             ThreatType threat_type,
                             FullHashCallback callback);

  // Retrieve the full hash and API metadata for a set of prefixes, and invoke
  // the callback argument when the results are retrieved. The callback may be
  // invoked synchronously.
  virtual void GetFullHashesWithApis(const std::vector<SBPrefix>& prefixes,
                                     FullHashCallback callback);

  // Enumerate failures for histogramming purposes.  DO NOT CHANGE THE
  // ORDERING OF THESE VALUES.
  enum ResultType {
    // 200 response code means that the server recognized the hash
    // prefix.
    GET_HASH_STATUS_200 = 0,

    // Subset of successful responses where the response body wasn't parsable.
    GET_HASH_PARSE_ERROR = 1,

    // Gethash request failed (network error).
    GET_HASH_NETWORK_ERROR = 2,

    // Gethash request returned HTTP result code other than 200.
    GET_HASH_HTTP_ERROR = 3,

    // Gethash attempted during error backoff, no request sent.
    GET_HASH_BACKOFF_ERROR = 4,

    // Gethash attempted before min wait duration elapsed, no request sent.
    GET_HASH_MIN_WAIT_DURATION_ERROR = 5,

    // Memory space for histograms is determined by the max.  ALWAYS
    // ADD NEW VALUES BEFORE THIS ONE.
    GET_HASH_RESULT_MAX = 6
  };

  // Record a GetHash result.
  static void RecordGetHashResult(ResultType result_type);

  // Record HTTP response code when there's no error in fetching an HTTP
  // request, and the error code, when there is.
  // |metric_name| is the name of the UMA metric to record the response code or
  // error code against, |status| represents the status of the HTTP request, and
  // |response code| represents the HTTP response code received from the server.
  static void RecordHttpResponseOrErrorCode(const char* metric_name,
                                            const net::URLRequestStatus& status,
                                            int response_code);

 protected:
  // Constructs a V4GetHashProtocolManager that issues
  // network requests using |request_context_getter|.
  V4GetHashProtocolManager(net::URLRequestContextGetter* request_context_getter,
                           const V4GetHashProtocolConfig& config);

 private:
  FRIEND_TEST_ALL_PREFIXES(SafeBrowsingV4GetHashProtocolManagerTest,
                           TestGetHashUrl);
  FRIEND_TEST_ALL_PREFIXES(SafeBrowsingV4GetHashProtocolManagerTest,
                           TestGetHashRequest);
  FRIEND_TEST_ALL_PREFIXES(SafeBrowsingV4GetHashProtocolManagerTest,
                           TestParseHashResponse);
  FRIEND_TEST_ALL_PREFIXES(SafeBrowsingV4GetHashProtocolManagerTest,
                           TestParseHashResponseWrongThreatEntryType);
  FRIEND_TEST_ALL_PREFIXES(SafeBrowsingV4GetHashProtocolManagerTest,
                           TestParseHashResponseSocialEngineeringThreatType);
  FRIEND_TEST_ALL_PREFIXES(SafeBrowsingV4GetHashProtocolManagerTest,
                           TestParseHashResponseNonPermissionMetadata);
  FRIEND_TEST_ALL_PREFIXES(SafeBrowsingV4GetHashProtocolManagerTest,
                           TestParseHashResponseInconsistentThreatTypes);
  FRIEND_TEST_ALL_PREFIXES(SafeBrowsingV4GetHashProtocolManagerTest,
                           TestGetHashBackOffTimes);
  FRIEND_TEST_ALL_PREFIXES(SafeBrowsingV4GetHashProtocolManagerTest,
                           TestGetHashErrorHandlingOK);
  FRIEND_TEST_ALL_PREFIXES(SafeBrowsingV4GetHashProtocolManagerTest,
                           TestGetHashErrorHandlingNetwork);
  FRIEND_TEST_ALL_PREFIXES(SafeBrowsingV4GetHashProtocolManagerTest,
                           TestGetHashErrorHandlingResponseCode);
  friend class V4GetHashProtocolManagerFactoryImpl;

  // Generates GetHashWithApis Pver4 request URL for retrieving full hashes.
  // |request_base64| is the serialized FindFullHashesRequest protocol buffer
  // encoded in base 64.
  GURL GetHashUrl(const std::string& request_base64) const;

  // Fills a FindFullHashesRequest protocol buffer for a request.
  // Returns the serialized and base 64 encoded request as a string.
  std::string GetHashRequest(const std::vector<SBPrefix>& prefixes,
                             const std::vector<PlatformType>& platforms,
                             ThreatType threat_type);

  // Composes a URL using |prefix|, |method| (e.g.: encodedFullHashes).
  // |request_base64|, |client_id|, |version| and |key_param|. |prefix|
  // should contain the entire url prefix including scheme, host and path.
  static std::string ComposePver4Url(const std::string& prefix,
                                     const std::string& method,
                                     const std::string& request_base64,
                                     const std::string& client_id,
                                     const std::string& version,
                                     const std::string& key_param);

  // Parses a FindFullHashesResponse protocol buffer and fills the results in
  // |full_hashes| and |negative_cache_duration|. |data| is a serialized
  // FindFullHashes protocol buffer. |negative_cache_duration| is the duration
  // to cache the response for entities that did not match the threat list.
  // Returns true if parsing is successful, false otherwise.
  bool ParseHashResponse(const std::string& data_base64,
                         std::vector<SBFullHashResult>* full_hashes,
                         base::TimeDelta* negative_cache_duration);

  // Worker function for calculating the GetHash backoff times.
  // |multiplier| is doubled for each consecutive error after the
  // first, and |error_count| is incremented with each call.
  static base::TimeDelta GetNextBackOffInterval(size_t* error_count,
                                                size_t* multiplier);

  // Resets the gethash error counter and multiplier.
  void ResetGetHashErrors();

  // Updates internal state for each GetHash response error, assuming that
  // the current time is |now|.
  void HandleGetHashError(const base::Time& now);

 private:
  // Map of GetHash requests to parameters which created it.
  typedef base::hash_map<const net::URLFetcher*, FullHashCallback> HashRequests;

  // The factory that controls the creation of V4GetHashProtocolManager.
  // This is used by tests.
  static V4GetHashProtocolManagerFactory* factory_;

  // Current active request (in case we need to cancel) for updates or chunks
  // from the SafeBrowsing service. We can only have one of these outstanding
  // at any given time unlike GetHash requests, which are tracked separately.
  scoped_ptr<net::URLFetcher> request_;

  // The number of HTTP response errors since the the last successful HTTP
  // response, used for request backoff timing.
  size_t gethash_error_count_;

  // Multiplier for the backoff error after the second.
  size_t gethash_back_off_mult_;

  HashRequests hash_requests_;

  // For v4, the next gethash time is set to the backoff time is the last
  // response was an error, or the minimum wait time if the last response was
  // successful.
  base::Time next_gethash_time_;

  // Current product version sent in each request.
  std::string version_;

  // The safe browsing client name sent in each request.
  std::string client_name_;

  // The Google API key.
  std::string key_param_;

  // The context we use to issue network requests.
  scoped_refptr<net::URLRequestContextGetter> request_context_getter_;

  // ID for URLFetchers for testing.
  int url_fetcher_id_;

  DISALLOW_COPY_AND_ASSIGN(V4GetHashProtocolManager);
};

// Interface of a factory to create V4GetHashProtocolManager.  Useful for tests.
class V4GetHashProtocolManagerFactory {
 public:
  V4GetHashProtocolManagerFactory() {}
  virtual ~V4GetHashProtocolManagerFactory() {}
  virtual V4GetHashProtocolManager* CreateProtocolManager(
      net::URLRequestContextGetter* request_context_getter,
      const V4GetHashProtocolConfig& config) = 0;

 private:
  DISALLOW_COPY_AND_ASSIGN(V4GetHashProtocolManagerFactory);
};

}  // namespace safe_browsing

#endif  // COMPONENTS_SAFE_BROWSING_DB_V4_GET_HASH_PROTOCOL_MANAGER_H_