[security] transport.Controller{} and transport.Transport{} security and performance improvements (#564)

* cache transports in controller by privkey-generated pubkey, add retry logic to transport requests

Signed-off-by: kim <grufwub@gmail.com>

* update code comments, defer mutex unlocks

Signed-off-by: kim <grufwub@gmail.com>

* add count to 'performing request' log message

Signed-off-by: kim <grufwub@gmail.com>

* reduce repeated conversions of same url.URL object

Signed-off-by: kim <grufwub@gmail.com>

* move worker.Worker to concurrency subpackage, add WorkQueue type, limit transport http client use by WorkQueue

Signed-off-by: kim <grufwub@gmail.com>

* fix security advisories regarding max outgoing conns, max rsp body size

- implemented by a new httpclient.Client{} that wraps an underlying
  client with a queue to limit connections, and limit reader wrapping
  a response body with a configured maximum size
- update pub.HttpClient args passed around to be this new httpclient.Client{}

Signed-off-by: kim <grufwub@gmail.com>

* add httpclient tests, move ip validation to separate package + change mechanism

Signed-off-by: kim <grufwub@gmail.com>

* fix merge conflicts

Signed-off-by: kim <grufwub@gmail.com>

* use singular mutex in transport rather than separate signer mus

Signed-off-by: kim <grufwub@gmail.com>

* improved useragent string

Signed-off-by: kim <grufwub@gmail.com>

* add note regarding missing test

Signed-off-by: kim <grufwub@gmail.com>

* remove useragent field from transport (instead store in controller)

Signed-off-by: kim <grufwub@gmail.com>

* shutup linter

Signed-off-by: kim <grufwub@gmail.com>

* reset other signing headers on each loop iteration

Signed-off-by: kim <grufwub@gmail.com>

* respect request ctx during retry-backoff sleep period

Signed-off-by: kim <grufwub@gmail.com>

* use external pkg with docs explaining performance "hack"

Signed-off-by: kim <grufwub@gmail.com>

* use http package constants instead of string method literals

Signed-off-by: kim <grufwub@gmail.com>

* add license file headers

Signed-off-by: kim <grufwub@gmail.com>

* update code comment to match new func names

Signed-off-by: kim <grufwub@gmail.com>

* updates to user-agent string

Signed-off-by: kim <grufwub@gmail.com>

* update signed testrig models to fit with new transport logic (instead uses separate signer now)

Signed-off-by: kim <grufwub@gmail.com>

* fuck you linter

Signed-off-by: kim <grufwub@gmail.com>

1 files changed, 31 insertions, 8 deletions

diff --git a/internal/transport/dereference.go b/internal/transport/dereference.go
index 61d99c5c5..36157b673 100644
--- a/internal/transport/dereference.go
+++ b/internal/transport/dereference.go
@@ -20,32 +20,55 @@ package transport
 
 import (
 	"context"
+	"fmt"
+	"io/ioutil"
+	"net/http"
 	"net/url"
 
-	"github.com/sirupsen/logrus"
 	"github.com/spf13/viper"
 	"github.com/superseriousbusiness/gotosocial/internal/config"
 	"github.com/superseriousbusiness/gotosocial/internal/uris"
 )
 
 func (t *transport) Dereference(ctx context.Context, iri *url.URL) ([]byte, error) {
-	l := logrus.WithField("func", "Dereference")
-
 	// if the request is to us, we can shortcut for certain URIs rather than going through
 	// the normal request flow, thereby saving time and energy
 	if iri.Host == viper.GetString(config.Keys.Host) {
 		if uris.IsFollowersPath(iri) {
 			// the request is for followers of one of our accounts, which we can shortcut
-			return t.dereferenceFollowersShortcut(ctx, iri)
+			return t.controller.dereferenceLocalFollowers(ctx, iri)
 		}
 
 		if uris.IsUserPath(iri) {
 			// the request is for one of our accounts, which we can shortcut
-			return t.dereferenceUserShortcut(ctx, iri)
+			return t.controller.dereferenceLocalUser(ctx, iri)
 		}
 	}
 
-	// the request is either for a remote host or for us but we don't have a shortcut, so continue as normal
-	l.Debugf("performing GET to %s", iri.String())
-	return t.sigTransport.Dereference(ctx, iri)
+	// Build IRI just once
+	iriStr := iri.String()
+
+	// Prepare new HTTP request to endpoint
+	req, err := http.NewRequestWithContext(ctx, "GET", iriStr, nil)
+	if err != nil {
+		return nil, err
+	}
+	req.Header.Add("Accept", "application/ld+json; profile=\"https://www.w3.org/ns/activitystreams\"")
+	req.Header.Add("Accept-Charset", "utf-8")
+	req.Header.Add("User-Agent", t.controller.userAgent)
+	req.Header.Set("Host", iri.Host)
+
+	// Perform the HTTP request
+	rsp, err := t.GET(req)
+	if err != nil {
+		return nil, err
+	}
+	defer rsp.Body.Close()
+
+	// Check for an expected status code
+	if rsp.StatusCode != http.StatusOK {
+		return nil, fmt.Errorf("GET request to %s failed (%d): %s", iriStr, rsp.StatusCode, rsp.Status)
+	}
+
+	return ioutil.ReadAll(rsp.Body)
 }