Add experimental code behind a flag for Content Size Policy

content/browser/loader/loader_io_thread_notifier.cc

 // 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.
 
 #include "content/browser/loader/loader_io_thread_notifier.h"
 
 #include "content/browser/frame_host/render_frame_host_impl.h"
-#include "content/browser/loader/global_routing_id.h"
+#include "content/browser/loader/content_size_resource_handler.h"
 #include "content/browser/loader/resource_dispatcher_host_impl.h"
+#include "content/browser/web_contents/web_contents_impl.h"
 #include "content/public/browser/browser_thread.h"
+#include "content/public/browser/navigation_handle.h"
+#include "content/public/common/content_switches.h"
+#include "url/origin.h"
 
 namespace content {
 
 namespace {
 
 void NotifyRenderFrameDeletedOnIO(const GlobalFrameRoutingId& id) {
   ResourceDispatcherHostImpl* rdhi = ResourceDispatcherHostImpl::Get();
   if (rdhi)
     rdhi->OnRenderFrameDeleted(id);
 }
 
+class ContentSizeNavigationThrottle : public NavigationThrottle {
+ public:
+  ContentSizeNavigationThrottle(NavigationHandle* handle,
+                                LoaderIOThreadNotifier* notifier)
+      : NavigationThrottle(handle), notifier_(notifier) {}
+  ~ContentSizeNavigationThrottle() override {}
+
+  // NavigationThrottle:
+  NavigationThrottle::ThrottleCheckResult WillProcessResponse() override {
+    return notifier_->WillProcessNavigationResponse(navigation_handle());
+  }
+
+ private:
+  LoaderIOThreadNotifier* notifier_;
+
+  DISALLOW_COPY_AND_ASSIGN(ContentSizeNavigationThrottle);
+};
+
 }  // namespace
 
 LoaderIOThreadNotifier::LoaderIOThreadNotifier(WebContents* web_contents)
     : WebContentsObserver(web_contents) {}
 
 LoaderIOThreadNotifier::~LoaderIOThreadNotifier() {}
 
 void LoaderIOThreadNotifier::RenderFrameDeleted(
     RenderFrameHost* render_frame_host) {
   BrowserThread::PostTask(
       BrowserThread::IO, FROM_HERE,
       base::Bind(&NotifyRenderFrameDeletedOnIO,
                  static_cast<RenderFrameHostImpl*>(render_frame_host)
                      ->GetGlobalFrameRoutingId()));
 }
 
+// static
+NavigationThrottle* LoaderIOThreadNotifier::MaybeCreateThrottle(
+    NavigationHandle* handle) {
+  if (handle->IsInMainFrame())

[mmenke, 2016/08/02 18:02:11]

A main frame navigation is a navigation "in" a main frame, right?  (As opposed
to an iframe that's directly a child of the main frame being a navigation
directly *within* a main frame).

[Charlie Harrison, 2016/08/02 18:35:36]

Right. Now that you mention it, this is confusingly named :P.

+    return nullptr;
+  if (!base::CommandLine::ForCurrentProcess()->HasSwitch(
+          switches::kContentSizePolicy)) {
+    return nullptr;
+  }
+
+  LoaderIOThreadNotifier* notifier =
+      static_cast<WebContentsImpl*>(handle->GetWebContents())
+          ->loader_io_thread_notifier();
+  return new ContentSizeNavigationThrottle(handle, notifier);
+}
+
+// TODO(csharrison): This should be moved to ReadyToCommitNavigation once that
+// is available. This callback is incorrect for transfer navigations.
+NavigationThrottle::ThrottleCheckResult
+LoaderIOThreadNotifier::WillProcessNavigationResponse(
+    NavigationHandle* navigation_handle) {

[mmenke, 2016/08/02 18:02:11]

Do we really need a NavigationThrottle for this?  Is this the only way to learn
when a frame's frame_routing_id/frame_tree_node has changed or something?

Or is it too hard to stop a subnavigation through other APIs, and the
ResourceHandlers aren't good enough alone?

[Charlie Harrison, 2016/08/02 18:35:36]

So, actually I think I will remove the throttle. I added it so we can cancel
main resource loads before they commit, but clamy@ will soon add a
ReadyToCommitNavigation callback to WCO. With that I think we have what we need.

For context, we don't know the routing id of a navigation until it is ready to
commit. We *could* send the provisional routing id, but that seemed like too
much complication. I think for right now I will go off of DidFinishNavigation,
with a TODO to change it to ReadyToCommit.

+  const GURL& url = navigation_handle->GetURL();
+  // Only consider http/s or about:blank urls for blocking.

[mmenke, 2016/08/02 18:02:11]

Why do we care about about:blank?  Is there a spec?

[Charlie Harrison, 2016/08/02 18:35:36]

No spec yet :(

The only reason I added about:blank is because it's a common way to inject ads
into a page.

+  if (!url.SchemeIsHTTPOrHTTPS() &&
+      url.spec().compare(url::kAboutBlankURL) != 0) {
+    return NavigationThrottle::PROCEED;
+  }
+
+  if (web_contents()->GetLastCommittedURL().SchemeIs("chrome"))
+    return NavigationThrottle::PROCEED;
+
+  // TODO(csharrison): Navigations to about:blank are not counted as
+  // same-origin.
+  if (url::Origin(web_contents()->GetLastCommittedURL())
+          .IsSameOriginWith(url::Origin(url))) {
+    return NavigationThrottle::PROCEED;
+  }
+
+  std::string policy_string =
+      base::CommandLine::ForCurrentProcess()->GetSwitchValueASCII(
+          switches::kContentSizePolicy);

[mmenke, 2016/08/05 17:18:17]

Why are we getting this as a command line string...This is supposed to come from
an iframe parameter, I assume?

[Charlie Harrison, 2016/08/08 14:04:38]

Yes. We wanted to land an experiment that just applies a blanket policy to all
cross origin subframes while the API of the spec is worked out. I imagine the
final interface will end up having the ContentSizeFrameCounter be a mojo
interface that the renderer talks to when it sees that an iframe has a max-size
attribute. Then we will add frames to the size map in the mojo callback. 

+  int content_size = 0;
+  base::StringToInt(policy_string, &content_size);

[mmenke, 2016/08/05 17:16:27]

Should we be using int64_t here, or even uint64_t?

[mmenke, 2016/08/05 17:18:17]

Oh, and I don't think anyone will be setting a limit over 2 GB, but seems like
we may as well support it.

[Charlie Harrison, 2016/08/08 14:04:38]

Yeah why not. Changing it to uint64_t sgtm. I had everything as int to keep
static_casting to a minimum in the resource handler.

+
+  RenderFrameHostImpl* rfh = static_cast<RenderFrameHostImpl*>(
+      navigation_handle->GetRenderFrameHost());
+  FrameSize* frame_size = AddNewFrame(rfh->frame_tree_node(), content_size);
+  if (frame_size->content_left < INT_MAX) {
+    BrowserThread::PostTask(
+        BrowserThread::IO, FROM_HERE,
+        base::Bind(&LoaderIOThreadNotifier::NotifyFrameHasLimit,
+                   rfh->GetGlobalFrameRoutingId(), frame_size->content_left));
+  }
+  return frame_size->content_left <= 0 ? NavigationThrottle::CANCEL
+                                       : NavigationThrottle::PROCEED;
+}
+
+void LoaderIOThreadNotifier::RenderFrameCreated(
+    RenderFrameHost* render_frame_host) {

[mmenke, 2016/08/05 17:16:27]

This doesn't do anything.

[Charlie Harrison, 2016/08/08 14:04:38]

Sorry about that. Removed.

+}
+
+// static
+// This method iterates through all LoaderIOThreadNotifiers, and calls
+// UpdateDataAccounting on them with updates from the IO thread.
+void LoaderIOThreadNotifier::UpdateGlobalDataAccounting(
+    std::unique_ptr<std::map<GlobalFrameRoutingId, int>> updates) {
+  DCHECK_CURRENTLY_ON(BrowserThread::UI);
+  DCHECK(updates);
+  std::map<LoaderIOThreadNotifier*, std::map<GlobalFrameRoutingId, int>>
+      per_notifier_map;
+  for (const auto& it : *updates) {
+    RenderFrameHostImpl* rfh = RenderFrameHostImpl::FromID(
+        it.first.child_id, it.first.frame_routing_id);
+    WebContents* contents = WebContents::FromRenderFrameHost(rfh);

[mmenke, 2016/08/02 18:02:11]

By creating and killing iframes, and then re-requesting resources that are now
in the cache, could a renderer bypass this stuff?  It would, admittedly, have to
be very precise about the timing.

[Charlie Harrison, 2016/08/02 18:35:37]

No, because we count bytes for resources loaded from the cache.

+    if (!contents)
+      continue;
+    LoaderIOThreadNotifier* notifier =
+        static_cast<WebContentsImpl*>(contents)->loader_io_thread_notifier();
+    per_notifier_map[notifier][it.first] = it.second;

[mmenke, 2016/08/02 18:02:11]

+=?  We can have multiple notifications for the same frame...I assume that's the
whole reason there are two loops here, and we don't call UpdateDataAccounting
here?

[Charlie Harrison, 2016/08/02 18:35:37]

Acknowledged. Think you're right.

[Charlie Harrison, 2016/08/08 14:04:39]

Done.

+  }
+  for (const auto& it : per_notifier_map) {
+    it.first->UpdateDataAccounting(it.second);
+  }
+}
+
+LoaderIOThreadNotifier::FrameSize* LoaderIOThreadNotifier::AddNewFrame(
+    FrameTreeNode* node,
+    int limit) {
+  FrameSize* frame_size = GetEffectiveLimit(node);
+  // No need to add this to the map if a parent frame has a lower limit.
+  if (!frame_size || frame_size->content_left > limit) {
+    FrameSize* size = &frame_tree_node_sizes_[node->frame_tree_node_id()];

[mmenke, 2016/08/02 18:02:11]

Half this code uses frame_tree_node_ids, half uses child_id/route_id.  Could we
standardize on one or the other?  Is there a 1-to-1 correspondence between the
two?  If I navigate a frame, do both stay the same (At least in a non-OOPIF
world)?

[Charlie Harrison, 2016/08/02 18:35:37]

*sigh* that's one of the complications here.

frame_tree_node_ids stay constant in a frame, regardless of OOPIF, cross process
navigation, anything. This means that our data accounting needs to use them for
the "golden" source of truth for per-frame accounting, otherwise an iframe could
just continually navigate cross process and reset its counts (and play a bit
more video, etc.).

The problem is that frame_tree_node_id is a UI thread thing, and routing id is
known on the IO thread. frame_tree_node_id is known on the IO thread for
navigations (post PlzNavigate), but that's it.

Possibly, we could add them wholesale to ResourceRequestInfoImpl, but I'm not
sure if other owners would be okay with that.

+    size->content_limit = limit;
+    size->content_left = limit;
+    return size;
+  }
+  return frame_size;
+}
+
+// This method walks the frame tree and returns the FrameSize of the frame with
+// the lowest limit. This is the effective bytes limit of |node|.
+LoaderIOThreadNotifier::FrameSize*
+LoaderIOThreadNotifier::GetEffectiveLimit(FrameTreeNode* node) {
+  FrameSize* frame_size = nullptr;
+  FrameTreeNode* current_node = node;
+  while (current_node) {
+    std::map<int, FrameSize>::iterator size_it =
+        frame_tree_node_sizes_.find(current_node->frame_tree_node_id());
+    if (size_it != frame_tree_node_sizes_.end() &&
+        (!frame_size ||
+         size_it->second.content_left < frame_size->content_left)) {
+      frame_size = &size_it->second;
+    }
+    current_node = current_node->parent();
+  }
+  return frame_size;
+}
+
+void LoaderIOThreadNotifier::UpdateDataAccounting(
+    std::map<GlobalFrameRoutingId, int> updates) {
+  std::unique_ptr<std::set<GlobalFrameRoutingId>> frames_over_limit(
+      new std::set<GlobalFrameRoutingId>);
+  for (const auto& it : updates) {
+    RenderFrameHostImpl* rfh = static_cast<RenderFrameHostImpl*>(
+        RenderFrameHost::FromID(it.first.child_id, it.first.frame_routing_id));
+    FrameSize* frame_size = GetEffectiveLimit(rfh->frame_tree_node());
+    DCHECK(frame_size);
+    frame_size->content_left -= it.second;

[mmenke, 2016/08/02 18:02:12]

This should update the content_left value of all frame_sizes that
GetEffectiveLimit goes through.

Just consider a subframe A with children B and C.  A has a limit of 10k, C a
limit of 5k.  B downloads 4k, which it subtracts from the 5k limit, but not the
10k limit.  C then downalods 8k.  It just checks this against the 10k limit
(Which the 4k was not subtracted from), and violates the limit.  It would be
easy to exploit this.

[Charlie Harrison, 2016/08/02 18:35:36]

I think you mixed up B and C in your example, but I understand the point. This
is a necessary change.

[Charlie Harrison, 2016/08/08 14:04:39]

Done.

+    if (frame_size->content_left <= 0)
+      frames_over_limit->insert(it.first);
+  }
+  if (!frames_over_limit->empty()) {
+    BrowserThread::PostTask(
+        BrowserThread::IO, FROM_HERE,
+        base::Bind(&LoaderIOThreadNotifier::NotifyFramesWentOverSizeLimits,
+                   base::Passed(std::move(frames_over_limit))));
+  }
+}
+
+// static
+void LoaderIOThreadNotifier::NotifyFramesWentOverSizeLimits(
+    std::unique_ptr<std::set<GlobalFrameRoutingId>> frames) {
+  DCHECK_CURRENTLY_ON(BrowserThread::IO);
+  ResourceDispatcherHostImpl* rdh = ResourceDispatcherHostImpl::Get();
+  if (rdh && rdh->content_size_manager()) {
+    rdh->content_size_manager()->FramesWentOverSizeLimits(std::move(frames));
+  }
+}
+
+// static
+void LoaderIOThreadNotifier::NotifyFrameHasLimit(
+    const GlobalFrameRoutingId& frame,
+    int limit) {
+  DCHECK_CURRENTLY_ON(BrowserThread::IO);
+  ResourceDispatcherHostImpl* rdh = ResourceDispatcherHostImpl::Get();
+  if (rdh && rdh->content_size_manager()) {
+    rdh->content_size_manager()->FrameHasSizeLimit(frame, limit);
+  }
+}
+
 }  // namespace content