From 158654a75940bf677f52567838036ef51b52c2c7 Mon Sep 17 00:00:00 2001
From: Lisa Overall <11458176+lisaoverall@users.noreply.github.com>
Date: Wed, 10 May 2023 20:37:44 -0400
Subject: [PATCH 01/10] WIP httpd demo

---
 examples/http/httpd/.dockerignore    |  3 ++
 examples/http/httpd/Dockerfile       | 69 ++++++++++++++++++++++++++++
 examples/http/httpd/example_httpd.sh | 10 ++++
 examples/http/httpd/harness_httpd.sh |  9 ++++
 4 files changed, 91 insertions(+)
 create mode 100644 examples/http/httpd/.dockerignore
 create mode 100644 examples/http/httpd/Dockerfile
 create mode 100755 examples/http/httpd/example_httpd.sh
 create mode 100755 examples/http/httpd/harness_httpd.sh

diff --git a/examples/http/httpd/.dockerignore b/examples/http/httpd/.dockerignore
new file mode 100644
index 00000000..1a60db3f
--- /dev/null
+++ b/examples/http/httpd/.dockerignore
@@ -0,0 +1,3 @@
+httpd
+example_httpd
+example_httpd.o
diff --git a/examples/http/httpd/Dockerfile b/examples/http/httpd/Dockerfile
new file mode 100644
index 00000000..04f9a2f3
--- /dev/null
+++ b/examples/http/httpd/Dockerfile
@@ -0,0 +1,69 @@
+# Create a separate image with the latest source
+FROM trailofbits/polytracker:latest
+LABEL org.opencontainers.image.authors="lisa.overall@trailofbits.com"
+
+RUN rm -rf /polytracker/examples/http/httpd && mkdir -p /polytracker/examples/http/httpd
+
+WORKDIR /polytracker/examples/http/httpd
+RUN git clone --branch 2.4.13 https://github.com/apache/httpd.git
+RUN apt update && apt install -y curl autoconf libtool-bin && rm -rf /var/lib/apt/lists/*
+# libapr1-dev libaprutil1-dev libpcre3-dev
+
+WORKDIR /polytracker/examples/http/httpd/httpd
+RUN mkdir -p srclib/apr srclib/apr-util srclib/pcre srclib/expat
+RUN curl https://archive.apache.org/dist/apr/apr-1.7.0.tar.gz -o apr-1.7.0.tar.gz \
+    && tar xfz apr-1.7.0.tar.gz -C srclib/apr --strip-components 1 \
+    && rm apr-1.7.0.tar.gz 
+RUN curl https://archive.apache.org/dist/apr/apr-util-1.6.1.tar.gz -o apr-util-1.6.1.tar.gz \
+    && tar xfz apr-util-1.6.1.tar.gz -C srclib/apr-util --strip-components 1 \
+    && rm apr-util-1.6.1.tar.gz
+RUN curl -L https://sourceforge.net/projects/pcre/files/pcre/8.39/pcre-8.39.tar.gz/download -o pcre-8.39.tar.gz \
+    && tar xfz pcre-8.39.tar.gz -C srclib/pcre --strip-components 1 \
+    && rm pcre-8.39.tar.gz
+RUN curl -L https://github.com/libexpat/libexpat/releases/download/R_2_4_7/expat-2.4.7.tar.gz -o expat-2.4.7.tar.gz \
+    && tar xfz expat-2.4.7.tar.gz -C srclib/expat --strip-components 1 \
+    && rm expat-2.4.7.tar.gz
+
+WORKDIR /polytracker/examples/http/httpd/httpd/srclib/pcre
+RUN polytracker build ./configure --disable-shared
+RUN polytracker build make
+# NOTE: no longer needed after --disable-shared
+RUN polytracker extract-bc -o ../../libpcre.bc .libs/libpcre.a
+
+WORKDIR /polytracker/examples/http/httpd/httpd/srclib/expat
+RUN polytracker build ./configure --disable-shared
+RUN polytracker build make
+# NOTE: no longer needed after --disable-shared
+RUN polytracker extract-bc -o ../../libexpat.bc  lib/.libs/libexpat.a
+
+# apr, apr-util are configured via httpd's configure script
+
+WORKDIR /polytracker/examples/http/httpd/httpd
+RUN polytracker build ./buildconf 
+# NOTE: CFLAGS reported unused during instrumentation
+RUN CFLAGS="-I$(pwd)/srclib/pcre -I$(pwd)/srclib/expat/lib" \
+LDFLAGS="-L$(pwd)/srclib/pcre/.libs -L$(pwd)/srclib/expat/lib/.libs" \
+    polytracker build ./configure --disable-shared --with-mpm=prefork --with-pcre=srclib/pcre/pcre-config --with-included-apr
+# NOTE: CFLAGS reported unused during instrumentation 
+RUN CFLAGS="-I$(pwd)/srclib/pcre -I$(pwd)/srclib/expat/lib" \
+LDFLAGS="-L$(pwd)/srclib/pcre/.libs -L$(pwd)/srclib/expat/lib/.libs" \ 
+    polytracker build make -j$((`nproc`+1))
+
+# NOTE: no longer needed after configuring dependencies with --disable-shared
+# RUN polytracker extract-bc -o httpd.bc httpd
+# RUN llvm-link -o httpd-linked.bc httpd.bc libpcre.bc libexpat.bc
+# RUN polytracker instrument-bc --taint --ftrace httpd-linked.bc -o instrumented.bc
+
+# TODO: fails here due to undefined references to getrandom()
+# RUN polytracker instrument-targets --taint --ftrace httpd
+
+# NOTE: no longer needed after configuring dependencies with --disable-shared
+# RUN polytracker lower-bc instrumented.bc -t httpd -o httpd.instrumented
+
+# RUN mv httpd.instrumented httpd_track
+
+COPY harness_httpd.sh /polytracker/examples/http/httpd/
+
+# Note, the /workdir directory is intended to be mounted at runtime
+VOLUME ["/workdir"]
+#WORKDIR /workdir
diff --git a/examples/http/httpd/example_httpd.sh b/examples/http/httpd/example_httpd.sh
new file mode 100755
index 00000000..73ca2313
--- /dev/null
+++ b/examples/http/httpd/example_httpd.sh
@@ -0,0 +1,10 @@
+#!/usr/bin/env bash
+
+if [[ "$(docker images -q trailofbits/polytracker 2>/dev/null)" == "" ]]; then
+	docker build -t trailofbits/polytracker -f ../../Dockerfile ../../
+fi
+if [[ "$(docker images -q trailofbits/polytracker-demo-http-httpd 2>/dev/null)" == "" ]]; then
+	docker build -t trailofbits/polytracker-demo-http-httpd .
+fi
+
+docker run --read-only -ti --rm -e POLYPATH="$1" --mount type=bind,source="$(pwd)",target=/workdir trailofbits/polytracker-demo-http-httpd:latest /polytracker/examples/http/httpd/harness_httpd.sh "$1"
diff --git a/examples/http/httpd/harness_httpd.sh b/examples/http/httpd/harness_httpd.sh
new file mode 100755
index 00000000..dced637d
--- /dev/null
+++ b/examples/http/httpd/harness_httpd.sh
@@ -0,0 +1,9 @@
+#!/usr/bin/env bash
+
+set -e
+
+httpd_track &
+APACHE_PID=$!
+# TODO: send request (in file - first command line arg) to httpd_track
+kill $APACHE_PID
+wait $APACHE_PID

From 03587ac80b28ee66cf0a327d4dea8a6ea778b144 Mon Sep 17 00:00:00 2001
From: hbrodin <90325907+hbrodin@users.noreply.github.com>
Date: Thu, 11 May 2023 09:09:57 +0200
Subject: [PATCH 02/10] Instruct DFSan to discard getrandom. Allows the
 instrumetation of httpd to succeed.

---
 examples/http/httpd/Dockerfile           | 4 ++--
 polytracker/custom_abi/dfsan_abilist.txt | 2 ++
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/examples/http/httpd/Dockerfile b/examples/http/httpd/Dockerfile
index 04f9a2f3..6e523a08 100644
--- a/examples/http/httpd/Dockerfile
+++ b/examples/http/httpd/Dockerfile
@@ -55,12 +55,12 @@ LDFLAGS="-L$(pwd)/srclib/pcre/.libs -L$(pwd)/srclib/expat/lib/.libs" \
 # RUN polytracker instrument-bc --taint --ftrace httpd-linked.bc -o instrumented.bc
 
 # TODO: fails here due to undefined references to getrandom()
-# RUN polytracker instrument-targets --taint --ftrace httpd
+RUN polytracker instrument-targets --taint --ftrace httpd
 
 # NOTE: no longer needed after configuring dependencies with --disable-shared
 # RUN polytracker lower-bc instrumented.bc -t httpd -o httpd.instrumented
 
-# RUN mv httpd.instrumented httpd_track
+RUN mv httpd.instrumented httpd_track
 
 COPY harness_httpd.sh /polytracker/examples/http/httpd/
 
diff --git a/polytracker/custom_abi/dfsan_abilist.txt b/polytracker/custom_abi/dfsan_abilist.txt
index 6ddf8a97..a3c5b55c 100644
--- a/polytracker/custom_abi/dfsan_abilist.txt
+++ b/polytracker/custom_abi/dfsan_abilist.txt
@@ -25,6 +25,8 @@ fun:open=uninstrumented
 fun:open=custom
 fun:open64=uninstrumented
 fun:open64=custom
+fun:getrandom=uninstrumented
+fun:getrandom=discard
 
 
 ##########################################

From 5328c3ffa49dc6dfa4e8508d2ffc4154889b6767 Mon Sep 17 00:00:00 2001
From: Lisa Overall <11458176+lisaoverall@users.noreply.github.com>
Date: Thu, 11 May 2023 11:37:04 -0400
Subject: [PATCH 03/10] Supply required configuration and modules for
 bare-bones server, complete harness

---
 examples/http/httpd/Dockerfile       |  33 +--
 examples/http/httpd/README.md        |  29 ++
 examples/http/httpd/example_httpd.sh |   3 +-
 examples/http/httpd/harness_httpd.sh |  18 +-
 examples/http/httpd/httpd.conf       | 419 +++++++++++++++++++++++++++
 5 files changed, 473 insertions(+), 29 deletions(-)
 create mode 100644 examples/http/httpd/README.md
 create mode 100644 examples/http/httpd/httpd.conf

diff --git a/examples/http/httpd/Dockerfile b/examples/http/httpd/Dockerfile
index 6e523a08..7642d41b 100644
--- a/examples/http/httpd/Dockerfile
+++ b/examples/http/httpd/Dockerfile
@@ -1,4 +1,3 @@
-# Create a separate image with the latest source
 FROM trailofbits/polytracker:latest
 LABEL org.opencontainers.image.authors="lisa.overall@trailofbits.com"
 
@@ -6,8 +5,7 @@ RUN rm -rf /polytracker/examples/http/httpd && mkdir -p /polytracker/examples/ht
 
 WORKDIR /polytracker/examples/http/httpd
 RUN git clone --branch 2.4.13 https://github.com/apache/httpd.git
-RUN apt update && apt install -y curl autoconf libtool-bin && rm -rf /var/lib/apt/lists/*
-# libapr1-dev libaprutil1-dev libpcre3-dev
+RUN apt update && apt install -y netcat curl autoconf libtool-bin && rm -rf /var/lib/apt/lists/*
 
 WORKDIR /polytracker/examples/http/httpd/httpd
 RUN mkdir -p srclib/apr srclib/apr-util srclib/pcre srclib/expat
@@ -27,43 +25,32 @@ RUN curl -L https://github.com/libexpat/libexpat/releases/download/R_2_4_7/expat
 WORKDIR /polytracker/examples/http/httpd/httpd/srclib/pcre
 RUN polytracker build ./configure --disable-shared
 RUN polytracker build make
-# NOTE: no longer needed after --disable-shared
-RUN polytracker extract-bc -o ../../libpcre.bc .libs/libpcre.a
 
 WORKDIR /polytracker/examples/http/httpd/httpd/srclib/expat
 RUN polytracker build ./configure --disable-shared
 RUN polytracker build make
-# NOTE: no longer needed after --disable-shared
-RUN polytracker extract-bc -o ../../libexpat.bc  lib/.libs/libexpat.a
 
 # apr, apr-util are configured via httpd's configure script
 
 WORKDIR /polytracker/examples/http/httpd/httpd
 RUN polytracker build ./buildconf 
-# NOTE: CFLAGS reported unused during instrumentation
 RUN CFLAGS="-I$(pwd)/srclib/pcre -I$(pwd)/srclib/expat/lib" \
-LDFLAGS="-L$(pwd)/srclib/pcre/.libs -L$(pwd)/srclib/expat/lib/.libs" \
-    polytracker build ./configure --disable-shared --with-mpm=prefork --with-pcre=srclib/pcre/pcre-config --with-included-apr
-# NOTE: CFLAGS reported unused during instrumentation 
+    LDFLAGS="-L$(pwd)/srclib/pcre/.libs -L$(pwd)/srclib/expat/lib/.libs" \
+    polytracker build ./configure --disable-shared --with-mpm=prefork --with-pcre=srclib/pcre/pcre-config --with-included-apr \
+    --enable-mods-static='authz_core unixd'
 RUN CFLAGS="-I$(pwd)/srclib/pcre -I$(pwd)/srclib/expat/lib" \
-LDFLAGS="-L$(pwd)/srclib/pcre/.libs -L$(pwd)/srclib/expat/lib/.libs" \ 
+    LDFLAGS="-L$(pwd)/srclib/pcre/.libs -L$(pwd)/srclib/expat/lib/.libs" \ 
     polytracker build make -j$((`nproc`+1))
 
-# NOTE: no longer needed after configuring dependencies with --disable-shared
-# RUN polytracker extract-bc -o httpd.bc httpd
-# RUN llvm-link -o httpd-linked.bc httpd.bc libpcre.bc libexpat.bc
-# RUN polytracker instrument-bc --taint --ftrace httpd-linked.bc -o instrumented.bc
-
-# TODO: fails here due to undefined references to getrandom()
 RUN polytracker instrument-targets --taint --ftrace httpd
-
-# NOTE: no longer needed after configuring dependencies with --disable-shared
-# RUN polytracker lower-bc instrumented.bc -t httpd -o httpd.instrumented
-
 RUN mv httpd.instrumented httpd_track
+# overwrite binary to be installed with our polytracker-instrumented version 
+RUN cp httpd_track httpd  
+RUN polytracker build make install
 
 COPY harness_httpd.sh /polytracker/examples/http/httpd/
+COPY httpd.conf /usr/local/apache2/conf/
 
 # Note, the /workdir directory is intended to be mounted at runtime
 VOLUME ["/workdir"]
-#WORKDIR /workdir
+WORKDIR /workdir
diff --git a/examples/http/httpd/README.md b/examples/http/httpd/README.md
new file mode 100644
index 00000000..737d74fd
--- /dev/null
+++ b/examples/http/httpd/README.md
@@ -0,0 +1,29 @@
+# Polytracker demo: Apache httpd 
+
+## Quickstart
+```
+cd /path/to/polytracker/examples/http/httpd
+./example_httpd.sh foo.txt
+```
+where `foo.txt` contains the raw text of an HTTP request.
+
+## Notes on instrumentation
+In order to enable polytracker instrumentation, we statically compile httpd, its dependencies, and its modules.
+
+The default build includes the following statically compiled modules:
+```
+$ ./httpd -l
+Compiled in modules:
+  core.c
+  mod_authz_core.c
+  mod_so.c
+  http_core.c
+  prefork.c
+  mod_unixd.c
+```
+
+In order to enable additional modules, modify the Dockerfile to include additional `--enable-MODULE=static`
+or `--enable-modules-static=MODULE-LIST` directives during the final `./configure` command. 
+(see the [httpd configruation documenation](https://httpd.apache.org/docs/2.4/programs/configure.html) for further details).
+You may also need to modify the `httpd.conf` file in this directory (which is copied to `/usr/local/apache2/conf/httpd.conf` in the container), and potentially add module configuration files to 
+the `/usr/local/apache2/conf/extra` directory.
diff --git a/examples/http/httpd/example_httpd.sh b/examples/http/httpd/example_httpd.sh
index 73ca2313..27acaca0 100755
--- a/examples/http/httpd/example_httpd.sh
+++ b/examples/http/httpd/example_httpd.sh
@@ -7,4 +7,5 @@ if [[ "$(docker images -q trailofbits/polytracker-demo-http-httpd 2>/dev/null)"
 	docker build -t trailofbits/polytracker-demo-http-httpd .
 fi
 
-docker run --read-only -ti --rm -e POLYPATH="$1" --mount type=bind,source="$(pwd)",target=/workdir trailofbits/polytracker-demo-http-httpd:latest /polytracker/examples/http/httpd/harness_httpd.sh "$1"
+# NOTE: cannot pass --read-only because httpd needs to be able to write to /usr/local/apache2/logs/error_log
+docker run -ti --rm -e POLYPATH="$1" --mount type=bind,source="$(pwd)",target=/workdir trailofbits/polytracker-demo-http-httpd:latest /polytracker/examples/http/httpd/harness_httpd.sh "$1"
diff --git a/examples/http/httpd/harness_httpd.sh b/examples/http/httpd/harness_httpd.sh
index dced637d..0caec897 100755
--- a/examples/http/httpd/harness_httpd.sh
+++ b/examples/http/httpd/harness_httpd.sh
@@ -2,8 +2,16 @@
 
 set -e
 
-httpd_track &
-APACHE_PID=$!
-# TODO: send request (in file - first command line arg) to httpd_track
-kill $APACHE_PID
-wait $APACHE_PID
+APACHE_ROOT=/usr/local/apache2
+$APACHE_ROOT/bin/apachectl -k start
+
+# send request (from text file - first command line arg) to instrumented httpd
+nc localhost 80 <"$1"
+
+# alternatively:
+# APACHE_PID=$(cat /usr/local/apache2/logs/httpd.pid)
+# kill $APACHE_PID
+# wait $APACHE_PID
+
+# alternatively: graceful-stop, in which currently open connections are not aborted
+$APACHE_ROOT/bin/apachectl -k stop
diff --git a/examples/http/httpd/httpd.conf b/examples/http/httpd/httpd.conf
new file mode 100644
index 00000000..4b18e597
--- /dev/null
+++ b/examples/http/httpd/httpd.conf
@@ -0,0 +1,419 @@
+#
+# This is the main Apache HTTP server configuration file.  It contains the
+# configuration directives that give the server its instructions.
+# See <URL:http://httpd.apache.org/docs/2.4/> for detailed information.
+# In particular, see 
+# <URL:http://httpd.apache.org/docs/2.4/mod/directives.html>
+# for a discussion of each configuration directive.
+#
+# Do NOT simply read the instructions in here without understanding
+# what they do.  They're here only as hints or reminders.  If you are unsure
+# consult the online docs. You have been warned.  
+#
+# Configuration and logfile names: If the filenames you specify for many
+# of the server's control files begin with "/" (or "drive:/" for Win32), the
+# server will use that explicit path.  If the filenames do *not* begin
+# with "/", the value of ServerRoot is prepended -- so "logs/access_log"
+# with ServerRoot set to "/usr/local/apache2" will be interpreted by the
+# server as "/usr/local/apache2/logs/access_log", whereas "/logs/access_log" 
+# will be interpreted as '/logs/access_log'.
+
+#
+# ServerRoot: The top of the directory tree under which the server's
+# configuration, error, and log files are kept.
+#
+# Do not add a slash at the end of the directory path.  If you point
+# ServerRoot at a non-local disk, be sure to specify a local disk on the
+# Mutex directive, if file-based mutexes are used.  If you wish to share the
+# same ServerRoot for multiple httpd daemons, you will need to change at
+# least PidFile.
+#
+ServerRoot /usr/local/apache2 
+
+#
+# Mutex: Allows you to set the mutex mechanism and mutex file directory
+# for individual mutexes, or change the global defaults
+#
+# Uncomment and change the directory if mutexes are file-based and the default
+# mutex file directory is not on a local disk or is not appropriate for some
+# other reason.
+#
+# Mutex default:logs
+
+#
+# Listen: Allows you to bind Apache to specific IP addresses and/or
+# ports, instead of the default. See also the <VirtualHost>
+# directive.
+#
+# Change this to Listen on specific IP addresses as shown below to 
+# prevent Apache from glomming onto all bound IP addresses.
+#
+Listen 127.0.0.1:80 
+
+#
+# Dynamic Shared Object (DSO) Support
+#
+# To be able to use the functionality of a module which was built as a DSO you
+# have to place corresponding `LoadModule' lines at this location so the
+# directives contained in it are actually available _before_ they are used.
+# Statically compiled modules (those listed by `httpd -l') do not need
+# to be loaded here.
+#
+# Example:
+# LoadModule foo_module modules/mod_foo.so
+#
+# @@LoadModule@@
+
+<IfModule unixd_module>
+#
+# If you wish httpd to run as a different user or group, you must run
+# httpd as root initially and it will switch.  
+#
+# User/Group: The name (or #number) of the user/group to run httpd as.
+# It is usually good practice to create a dedicated user and group for
+# running httpd, as with most system services.
+#
+User daemon
+Group daemon
+
+</IfModule>
+
+# 'Main' server configuration
+#
+# The directives in this section set up the values used by the 'main'
+# server, which responds to any requests that aren't handled by a
+# <VirtualHost> definition.  These values also provide defaults for
+# any <VirtualHost> containers you may define later in the file.
+#
+# All of these directives may appear inside <VirtualHost> containers,
+# in which case these default settings will be overridden for the
+# virtual host being defined.
+#
+
+#
+# ServerAdmin: Your address, where problems with the server should be
+# e-mailed.  This address appears on some server-generated pages, such
+# as error documents.  e.g. admin@your-domain.com
+#
+ServerAdmin you@example.com
+
+#
+# ServerName gives the name and port that the server uses to identify itself.
+# This can often be determined automatically, but we recommend you specify
+# it explicitly to prevent problems during startup.
+#
+# If your host doesn't have a registered DNS name, enter its IP address here.
+#
+ServerName localhost
+
+#
+# Deny access to the entirety of your server's filesystem. You must
+# explicitly permit access to web content directories in other 
+# <Directory> blocks below.
+#
+<Directory />
+    AllowOverride none
+    Require all denied
+</Directory>
+
+#
+# Note that from this point forward you must specifically allow
+# particular features to be enabled - so if something's not working as
+# you might expect, make sure that you have specifically enabled it
+# below.
+#
+
+#
+# DocumentRoot: The directory out of which you will serve your
+# documents. By default, all requests are taken from this directory, but
+# symbolic links and aliases may be used to point to other locations.
+#
+DocumentRoot "/usr/local/apache2/htdocs"
+<Directory "/usr/local/apache2/htdocs">
+    #
+    # Possible values for the Options directive are "None", "All",
+    # or any combination of:
+    #   Indexes Includes FollowSymLinks SymLinksifOwnerMatch ExecCGI MultiViews
+    #
+    # Note that "MultiViews" must be named *explicitly* --- "Options All"
+    # doesn't give it to you.
+    #
+    # The Options directive is both complicated and important.  Please see
+    # http://httpd.apache.org/docs/2.4/mod/core.html#options
+    # for more information.
+    #
+    Options Indexes FollowSymLinks
+
+    #
+    # AllowOverride controls what directives may be placed in .htaccess files.
+    # It can be "All", "None", or any combination of the keywords:
+    #   AllowOverride FileInfo AuthConfig Limit
+    #
+    AllowOverride None
+
+    #
+    # Controls who can get stuff from this server.
+    #
+    Require all granted
+</Directory>
+
+#
+# DirectoryIndex: sets the file that Apache will serve if a directory
+# is requested.
+#
+<IfModule dir_module>
+    DirectoryIndex index.html
+</IfModule>
+
+#
+# The following lines prevent .htaccess and .htpasswd files from being 
+# viewed by Web clients. 
+#
+<Files ".ht*">
+    Require all denied
+</Files>
+
+#
+# ErrorLog: The location of the error log file.
+# If you do not specify an ErrorLog directive within a <VirtualHost>
+# container, error messages relating to that virtual host will be
+# logged here.  If you *do* define an error logfile for a <VirtualHost>
+# container, that host's errors will be logged there and not here.
+#
+ErrorLog "logs/error_log"
+
+#
+# LogLevel: Control the number of messages logged to the error_log.
+# Possible values include: debug, info, notice, warn, error, crit,
+# alert, emerg.
+#
+LogLevel warn
+
+<IfModule log_config_module>
+    #
+    # The following directives define some format nicknames for use with
+    # a CustomLog directive (see below).
+    #
+    LogFormat "%h %l %u %t \"%r\" %>s %b \"%{Referer}i\" \"%{User-Agent}i\"" combined
+    LogFormat "%h %l %u %t \"%r\" %>s %b" common
+
+    <IfModule logio_module>
+      # You need to enable mod_logio.c to use %I and %O
+      LogFormat "%h %l %u %t \"%r\" %>s %b \"%{Referer}i\" \"%{User-Agent}i\" %I %O" combinedio
+    </IfModule>
+
+    #
+    # The location and format of the access logfile (Common Logfile Format).
+    # If you do not define any access logfiles within a <VirtualHost>
+    # container, they will be logged here.  Contrariwise, if you *do*
+    # define per-<VirtualHost> access logfiles, transactions will be
+    # logged therein and *not* in this file.
+    #
+    CustomLog "logs/access_log" common
+
+    #
+    # If you prefer a logfile with access, agent, and referer information
+    # (Combined Logfile Format) you can use the following directive.
+    #
+    #CustomLog "logs/access_log" combined
+</IfModule>
+
+<IfModule alias_module>
+    #
+    # Redirect: Allows you to tell clients about documents that used to 
+    # exist in your server's namespace, but do not anymore. The client 
+    # will make a new request for the document at its new location.
+    # Example:
+    # Redirect permanent /foo http://www.example.com/bar
+
+    #
+    # Alias: Maps web paths into filesystem paths and is used to
+    # access content that does not live under the DocumentRoot.
+    # Example:
+    # Alias /webpath /full/filesystem/path
+    #
+    # If you include a trailing / on /webpath then the server will
+    # require it to be present in the URL.  You will also likely
+    # need to provide a <Directory> section to allow access to
+    # the filesystem path.
+
+    #
+    # ScriptAlias: This controls which directories contain server scripts. 
+    # ScriptAliases are essentially the same as Aliases, except that
+    # documents in the target directory are treated as applications and
+    # run by the server when requested rather than as documents sent to the
+    # client.  The same rules about trailing "/" apply to ScriptAlias
+    # directives as to Alias.
+    #
+    ScriptAlias /cgi-bin/ "/usr/local/apache2/cgi-bin/"
+
+</IfModule>
+
+<IfModule cgid_module>
+    #
+    # ScriptSock: On threaded servers, designate the path to the UNIX
+    # socket used to communicate with the CGI daemon of mod_cgid.
+    #
+    #Scriptsock cgisock
+</IfModule>
+
+#
+# "/usr/local/apache2/cgi-bin" should be changed to whatever your ScriptAliased
+# CGI directory exists, if you have that configured.
+#
+<Directory "/usr/local/apache2/cgi-bin">
+    AllowOverride None
+    Options None
+    Require all granted
+</Directory>
+
+<IfModule mime_module>
+    #
+    # TypesConfig points to the file containing the list of mappings from
+    # filename extension to MIME-type.
+    #
+    TypesConfig conf/mime.types
+
+    #
+    # AddType allows you to add to or override the MIME configuration
+    # file specified in TypesConfig for specific file types.
+    #
+    #AddType application/x-gzip .tgz
+    #
+    # AddEncoding allows you to have certain browsers uncompress
+    # information on the fly. Note: Not all browsers support this.
+    #
+    #AddEncoding x-compress .Z
+    #AddEncoding x-gzip .gz .tgz
+    #
+    # If the AddEncoding directives above are commented-out, then you
+    # probably should define those extensions to indicate media types:
+    #
+    AddType application/x-compress .Z
+    AddType application/x-gzip .gz .tgz
+
+    #
+    # AddHandler allows you to map certain file extensions to "handlers":
+    # actions unrelated to filetype. These can be either built into the server
+    # or added with the Action directive (see below)
+    #
+    # To use CGI scripts outside of ScriptAliased directories:
+    # (You will also need to add "ExecCGI" to the "Options" directive.)
+    #
+    #AddHandler cgi-script .cgi
+
+    # For type maps (negotiated resources):
+    #AddHandler type-map var
+
+    #
+    # Filters allow you to process content before it is sent to the client.
+    #
+    # To parse .shtml files for server-side includes (SSI):
+    # (You will also need to add "Includes" to the "Options" directive.)
+    #
+    #AddType text/html .shtml
+    #AddOutputFilter INCLUDES .shtml
+</IfModule>
+
+#
+# The mod_mime_magic module allows the server to use various hints from the
+# contents of the file itself to determine its type.  The MIMEMagicFile
+# directive tells the module where the hint definitions are located.
+#
+#MIMEMagicFile conf/magic
+
+#
+# Customizable error responses come in three flavors:
+# 1) plain text 2) local redirects 3) external redirects
+#
+# Some examples:
+#ErrorDocument 500 "The server made a boo boo."
+#ErrorDocument 404 /missing.html
+#ErrorDocument 404 "/cgi-bin/missing_handler.pl"
+#ErrorDocument 402 http://www.example.com/subscription_info.html
+#
+
+#
+# MaxRanges: Maximum number of Ranges in a request before
+# returning the entire resource, or one of the special
+# values 'default', 'none' or 'unlimited'.
+# Default setting is to accept 200 Ranges.
+#MaxRanges unlimited
+
+#
+# EnableMMAP and EnableSendfile: On systems that support it, 
+# memory-mapping or the sendfile syscall may be used to deliver
+# files.  This usually improves server performance, but must
+# be turned off when serving from networked-mounted 
+# filesystems or if support for these functions is otherwise
+# broken on your system.
+# Defaults: EnableMMAP On, EnableSendfile Off
+#
+#EnableMMAP off
+#EnableSendfile on
+
+# Supplemental configuration
+#
+# The configuration files in the conf/extra/ directory can be 
+# included to add extra features or to modify the default configuration of 
+# the server, or you may simply copy their contents here and change as 
+# necessary.
+
+# Server-pool management (MPM specific)
+#Include conf/extra/httpd-mpm.conf
+
+# Multi-language error messages
+#Include conf/extra/httpd-multilang-errordoc.conf
+
+# Fancy directory listings
+#Include conf/extra/httpd-autoindex.conf
+
+# Language settings
+#Include conf/extra/httpd-languages.conf
+
+# User home directories
+#Include conf/extra/httpd-userdir.conf
+
+# Real-time info on requests and configuration
+#Include conf/extra/httpd-info.conf
+
+# Virtual hosts
+#Include conf/extra/httpd-vhosts.conf
+
+# Local access to the Apache HTTP Server Manual
+#Include conf/extra/httpd-manual.conf
+
+# Distributed authoring and versioning (WebDAV)
+#Include conf/extra/httpd-dav.conf
+
+# Various default settings
+#Include conf/extra/httpd-default.conf
+
+# Configure mod_proxy_html to understand HTML4/XHTML1
+<IfModule proxy_html_module>
+Include conf/extra/proxy-html.conf
+</IfModule>
+
+# Secure (SSL/TLS) connections
+#Include conf/extra/httpd-ssl.conf
+#
+# Note: The following must must be present to support
+#       starting without SSL on platforms with no /dev/random equivalent
+#       but a statically compiled-in mod_ssl.
+#
+<IfModule ssl_module>
+SSLRandomSeed startup builtin
+SSLRandomSeed connect builtin
+</IfModule>
+#
+# uncomment out the below to deal with user agents that deliberately
+# violate open standards by misusing DNT (DNT *must* be a specific
+# end-user choice)
+#
+#<IfModule setenvif_module>
+#BrowserMatch "MSIE 10.0;" bad_DNT
+#</IfModule>
+#<IfModule headers_module>
+#RequestHeader unset DNT env=bad_DNT
+#</IfModule>
+

From f9a48028fcfcf72b900cddce047230678b21c8d7 Mon Sep 17 00:00:00 2001
From: Lisa Overall <11458176+lisaoverall@users.noreply.github.com>
Date: Mon, 15 May 2023 07:51:59 -0400
Subject: [PATCH 04/10] Harness robust to HTTP requests located anywhere on
 host file system

---
 examples/http/httpd/example_httpd.sh | 23 ++++++++++++++++++++++-
 1 file changed, 22 insertions(+), 1 deletion(-)

diff --git a/examples/http/httpd/example_httpd.sh b/examples/http/httpd/example_httpd.sh
index 27acaca0..767f77db 100755
--- a/examples/http/httpd/example_httpd.sh
+++ b/examples/http/httpd/example_httpd.sh
@@ -1,5 +1,11 @@
 #!/usr/bin/env bash
 
+if [[ -z "$1" ]]; then
+	echo "Error: no arguments supplied"
+	echo "Usage: ./example_httpd.sh /path/to/raw_http_request"
+	exit 1
+fi
+
 if [[ "$(docker images -q trailofbits/polytracker 2>/dev/null)" == "" ]]; then
 	docker build -t trailofbits/polytracker -f ../../Dockerfile ../../
 fi
@@ -7,5 +13,20 @@ if [[ "$(docker images -q trailofbits/polytracker-demo-http-httpd 2>/dev/null)"
 	docker build -t trailofbits/polytracker-demo-http-httpd .
 fi
 
+HOST_PATH=$(realpath $1)
+HOST_DIR=$(dirname "$HOST_PATH")
+
 # NOTE: cannot pass --read-only because httpd needs to be able to write to /usr/local/apache2/logs/error_log
-docker run -ti --rm -e POLYPATH="$1" --mount type=bind,source="$(pwd)",target=/workdir trailofbits/polytracker-demo-http-httpd:latest /polytracker/examples/http/httpd/harness_httpd.sh "$1"
+
+# mount the file if it's not already in /workdir
+SCRIPT_DIR=$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" &>/dev/null && pwd)
+if [[ "$HOST_DIR" == "$SCRIPT_DIR" ]]; then
+	docker run -ti --rm -e POLYPATH="$1" -e POLYDB="$1.tdag" \
+		--mount type=bind,source="$(pwd)",target=/workdir trailofbits/polytracker-demo-http-httpd:latest \
+		/polytracker/examples/http/httpd/harness_httpd.sh "$1"
+else
+	CONTAINER_PATH=/workdir/$(basename "$1")
+	docker run -ti --rm -v "$HOST_PATH":"$CONTAINER_PATH" -e POLYPATH="$CONTAINER_PATH" -e POLYDB="$CONTAINER_PATH.tdag" \
+		--mount type=bind,source="$(pwd)",target=/workdir trailofbits/polytracker-demo-http-httpd:latest \
+		/polytracker/examples/http/httpd/harness_httpd.sh "$CONTAINER_PATH"
+fi

From 65fba32a2d12b6f641649bb2bbdef7f35b3a7c9a Mon Sep 17 00:00:00 2001
From: Lisa Overall <11458176+lisaoverall@users.noreply.github.com>
Date: Mon, 15 May 2023 10:34:21 -0400
Subject: [PATCH 05/10] Use bind mount instead of named volume so docker cleans
 up appropriately

---
 examples/http/httpd/Dockerfile       |  4 ++--
 examples/http/httpd/example_httpd.sh | 11 +++++++----
 2 files changed, 9 insertions(+), 6 deletions(-)

diff --git a/examples/http/httpd/Dockerfile b/examples/http/httpd/Dockerfile
index 7642d41b..8c250356 100644
--- a/examples/http/httpd/Dockerfile
+++ b/examples/http/httpd/Dockerfile
@@ -51,6 +51,6 @@ RUN polytracker build make install
 COPY harness_httpd.sh /polytracker/examples/http/httpd/
 COPY httpd.conf /usr/local/apache2/conf/
 
-# Note, the /workdir directory is intended to be mounted at runtime
-VOLUME ["/workdir"]
+# Note, the /workdir and /testcase directories are intended to be mounted at runtime
+VOLUME ["/workdir", "/testcase"]
 WORKDIR /workdir
diff --git a/examples/http/httpd/example_httpd.sh b/examples/http/httpd/example_httpd.sh
index 767f77db..3aaf69da 100755
--- a/examples/http/httpd/example_httpd.sh
+++ b/examples/http/httpd/example_httpd.sh
@@ -13,7 +13,8 @@ if [[ "$(docker images -q trailofbits/polytracker-demo-http-httpd 2>/dev/null)"
 	docker build -t trailofbits/polytracker-demo-http-httpd .
 fi
 
-HOST_PATH=$(realpath $1)
+HOST_PATH=$(realpath "$1")
+BASENAME=$(basename "$HOST_PATH")
 HOST_DIR=$(dirname "$HOST_PATH")
 
 # NOTE: cannot pass --read-only because httpd needs to be able to write to /usr/local/apache2/logs/error_log
@@ -25,8 +26,10 @@ if [[ "$HOST_DIR" == "$SCRIPT_DIR" ]]; then
 		--mount type=bind,source="$(pwd)",target=/workdir trailofbits/polytracker-demo-http-httpd:latest \
 		/polytracker/examples/http/httpd/harness_httpd.sh "$1"
 else
-	CONTAINER_PATH=/workdir/$(basename "$1")
-	docker run -ti --rm -v "$HOST_PATH":"$CONTAINER_PATH" -e POLYPATH="$CONTAINER_PATH" -e POLYDB="$CONTAINER_PATH.tdag" \
-		--mount type=bind,source="$(pwd)",target=/workdir trailofbits/polytracker-demo-http-httpd:latest \
+	CONTAINER_PATH=/testcase/"$BASENAME"
+	docker run -ti --rm -e POLYPATH="$CONTAINER_PATH" -e POLYDB=/workdir/"$BASENAME".tdag \
+		--mount type=bind,source="$(pwd)",target=/workdir \
+		--mount type=bind,source="$HOST_PATH",target="$CONTAINER_PATH" \
+		trailofbits/polytracker-demo-http-httpd:latest \
 		/polytracker/examples/http/httpd/harness_httpd.sh "$CONTAINER_PATH"
 fi

From a5a0466f3021b3213544451b4577a24ad2f25211 Mon Sep 17 00:00:00 2001
From: Lisa Overall <11458176+lisaoverall@users.noreply.github.com>
Date: Tue, 16 May 2023 14:14:05 -0400
Subject: [PATCH 06/10] Instrument accept4, non-standard Linux extension used
 in httpd

---
 polytracker/src/taint_sources/taint_sources.cpp | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/polytracker/src/taint_sources/taint_sources.cpp b/polytracker/src/taint_sources/taint_sources.cpp
index 4d4ea846..34e3bc81 100644
--- a/polytracker/src/taint_sources/taint_sources.cpp
+++ b/polytracker/src/taint_sources/taint_sources.cpp
@@ -466,6 +466,23 @@ EXT_C_FUNC int __dfsw_accept(int socket, struct sockaddr *address,
   return client_socket;
 }
 
+EXT_C_FUNC int __dfsw_accept4(int socket, struct sockaddr *address,
+                             socklen_t *address_len, int flags, 
+                             dfsan_label socket_label,
+                             dfsan_label address_label,
+                             dfsan_label address_len_label,
+                             dfsan_label *ret_label) {
+  int client_socket = accept4(socket, address, address_len, flags);
+  if (client_socket >= 0) {
+    if (auto name = connect_name(client_socket); name) {
+      get_polytracker_tdag().open_file(client_socket, *name);
+    }
+  }
+
+  *ret_label = 0;
+  return client_socket;
+}
+
 EXT_C_FUNC int __dfsw_connect(int socket, const struct sockaddr *address,
                               socklen_t address_len, dfsan_label socket_label,
                               dfsan_label address_label,

From 7c041c2445032bba8553253b549c7a552fa91c86 Mon Sep 17 00:00:00 2001
From: hbrodin <90325907+hbrodin@users.noreply.github.com>
Date: Tue, 16 May 2023 21:55:09 +0200
Subject: [PATCH 07/10] Tiny changes to instrument accept4 correctly

---
 polytracker/custom_abi/dfsan_abilist.txt        | 1 +
 polytracker/src/taint_sources/taint_sources.cpp | 1 +
 2 files changed, 2 insertions(+)

diff --git a/polytracker/custom_abi/dfsan_abilist.txt b/polytracker/custom_abi/dfsan_abilist.txt
index a3c5b55c..62176f43 100644
--- a/polytracker/custom_abi/dfsan_abilist.txt
+++ b/polytracker/custom_abi/dfsan_abilist.txt
@@ -1687,6 +1687,7 @@ fun:abs=functional
 fun:accept=uninstrumented
 fun:accept=custom
 fun:accept4=uninstrumented
+fun:accept4=custom
 fun:access=uninstrumented
 fun:acct=uninstrumented
 fun:acos=uninstrumented
diff --git a/polytracker/src/taint_sources/taint_sources.cpp b/polytracker/src/taint_sources/taint_sources.cpp
index 34e3bc81..fba84587 100644
--- a/polytracker/src/taint_sources/taint_sources.cpp
+++ b/polytracker/src/taint_sources/taint_sources.cpp
@@ -471,6 +471,7 @@ EXT_C_FUNC int __dfsw_accept4(int socket, struct sockaddr *address,
                              dfsan_label socket_label,
                              dfsan_label address_label,
                              dfsan_label address_len_label,
+                             dfsan_label flags_label,
                              dfsan_label *ret_label) {
   int client_socket = accept4(socket, address, address_len, flags);
   if (client_socket >= 0) {

From deffb5b355d90b683e3413aaa0bda713dea6b00c Mon Sep 17 00:00:00 2001
From: Lisa Overall <11458176+lisaoverall@users.noreply.github.com>
Date: Wed, 17 May 2023 11:16:49 -0400
Subject: [PATCH 08/10] Harness modifications to address console- and
 timing-related issues

---
 examples/http/httpd/harness_httpd.sh | 17 ++++++++++-------
 1 file changed, 10 insertions(+), 7 deletions(-)

diff --git a/examples/http/httpd/harness_httpd.sh b/examples/http/httpd/harness_httpd.sh
index 0caec897..0dc79873 100755
--- a/examples/http/httpd/harness_httpd.sh
+++ b/examples/http/httpd/harness_httpd.sh
@@ -3,15 +3,18 @@
 set -e
 
 APACHE_ROOT=/usr/local/apache2
-$APACHE_ROOT/bin/apachectl -k start
+$APACHE_ROOT/bin/apachectl -X &
+# needed for server initialization in single-worker mode
+sleep 10
 
 # send request (from text file - first command line arg) to instrumented httpd
 nc localhost 80 <"$1"
 
-# alternatively:
-# APACHE_PID=$(cat /usr/local/apache2/logs/httpd.pid)
-# kill $APACHE_PID
-# wait $APACHE_PID
+APACHE_PID=$(cat /usr/local/apache2/logs/httpd.pid)
+kill "$APACHE_PID"
+wait
 
-# alternatively: graceful-stop, in which currently open connections are not aborted
-$APACHE_ROOT/bin/apachectl -k stop
+# Oddly, these cause issues with TDAG production and does not include socket fds among TDAG sources
+# but only when run from the same terminal
+# $APACHE_ROOT/bin/apachectl stop
+# $APACHE_ROOT/bin/apachectl graceful-stop

From a807ce3952a2a725b5c4213c99c8bb54d7f091f4 Mon Sep 17 00:00:00 2001
From: Lisa Overall <11458176+lisaoverall@users.noreply.github.com>
Date: Wed, 13 Sep 2023 10:44:06 -0400
Subject: [PATCH 09/10] Helper scripts to produce TDAGs for a collection of
 requests under every instrumented HTTP parser

---
 examples/http/faw_tdag_pairs.sh |  6 +++++
 examples/http/tdag_pairs.sh     | 39 +++++++++++++++++++++++++++++++++
 2 files changed, 45 insertions(+)
 create mode 100755 examples/http/faw_tdag_pairs.sh
 create mode 100755 examples/http/tdag_pairs.sh

diff --git a/examples/http/faw_tdag_pairs.sh b/examples/http/faw_tdag_pairs.sh
new file mode 100755
index 00000000..c9943dc1
--- /dev/null
+++ b/examples/http/faw_tdag_pairs.sh
@@ -0,0 +1,6 @@
+#!/usr/bin/env bash
+
+FAW_DIR="$1"
+./tdag_pairs.sh "$FAW_DIR"/cves
+./tdag_pairs.sh "$FAW_DIR"/handcrafted
+./tdag_pairs.sh "$FAW_DIR"/portswigger
diff --git a/examples/http/tdag_pairs.sh b/examples/http/tdag_pairs.sh
new file mode 100755
index 00000000..a2bc1674
--- /dev/null
+++ b/examples/http/tdag_pairs.sh
@@ -0,0 +1,39 @@
+#!/usr/bin/env bash
+
+set -e
+
+if [[ -z "$1" ]]; then
+	echo "USAGE: ./tdag_pairs.sh /path/to/dir/with/raw_http_test_cases"
+	exit 1
+fi
+
+if [[ ! -d "$1" ]]; then
+	echo "ERROR: directory does not exist"
+	exit 2
+fi
+
+mkdir -p results
+for file in "$1"/*; do
+	TEST_CASE=$(basename "$file")
+	if [[ ! -d results/"$TEST_CASE" ]]; then
+		mkdir -p results/"$TEST_CASE"
+
+		# Could do this more elegantly by iterating over directories and excluding non-test-case dirs,
+		# e.g. via [[ $PARSER =~ ^(results)$ ]] && continue
+		# but there's a bunch of hidden directories with various code artifacts,
+		# which would be harder to maintain and could vary for different users
+		parser_array=("picohttpparser" "httpd")
+		for PARSER in "${parser_array[@]}"; do
+			echo "Producing TDAG for test case $TEST_CASE with parser $PARSER"
+
+			# NOTE: if the instrumented process crashes, continue as long as we get a tdag
+			"$PARSER"/example_"$PARSER".sh "$file" || true
+			# TODO: use `polytracker compress` command once integrated
+			docker run --read-only -ti --rm --mount type=bind,source="$(pwd)",target=/workdir trailofbits/polytracker:latest \
+				python3 /polytracker/examples/analysis/ubet/compress_tdag.py -i "$TEST_CASE".tdag -o "$TEST_CASE".tdag."$PARSER".compress
+			mv "$TEST_CASE".tdag."$PARSER".compress results/"$TEST_CASE"
+			rm "$TEST_CASE".tdag
+		done
+
+	fi
+done

From 0973781b1913d4566b72a1263d44641ee1f454cd Mon Sep 17 00:00:00 2001
From: Lisa Overall <11458176+lisaoverall@users.noreply.github.com>
Date: Wed, 13 Sep 2023 17:34:29 -0400
Subject: [PATCH 10/10] Configure httpd listening port via Docker environment
 variables

---
 examples/http/faw_tdag_pairs.sh      |  6 ++++++
 examples/http/httpd/example_httpd.sh | 16 ++++++++++++++--
 examples/http/httpd/harness_httpd.sh | 12 ++++++++++--
 3 files changed, 30 insertions(+), 4 deletions(-)

diff --git a/examples/http/faw_tdag_pairs.sh b/examples/http/faw_tdag_pairs.sh
index c9943dc1..f1d55775 100755
--- a/examples/http/faw_tdag_pairs.sh
+++ b/examples/http/faw_tdag_pairs.sh
@@ -1,5 +1,11 @@
 #!/usr/bin/env bash
 
+if [[ -z "$1" ]]; then
+	echo "Error: no arguments supplied"
+	echo "Usage: ./example_httpd.sh /path/to/FAW/test_files/http"
+	exit 1
+fi
+
 FAW_DIR="$1"
 ./tdag_pairs.sh "$FAW_DIR"/cves
 ./tdag_pairs.sh "$FAW_DIR"/handcrafted
diff --git a/examples/http/httpd/example_httpd.sh b/examples/http/httpd/example_httpd.sh
index 3aaf69da..7bf2d1dc 100755
--- a/examples/http/httpd/example_httpd.sh
+++ b/examples/http/httpd/example_httpd.sh
@@ -2,10 +2,22 @@
 
 if [[ -z "$1" ]]; then
 	echo "Error: no arguments supplied"
-	echo "Usage: ./example_httpd.sh /path/to/raw_http_request"
+	echo "Usage: ./example_httpd.sh /path/to/raw_http_request [httpd_port]"
 	exit 1
 fi
 
+if [[ -z "$2" ]]; then
+	APACHE_PORT=80
+else
+	re='^[0-9]+$'
+	if ! [[ "$2" =~ $re ]] || [[ $2 -eq 0 ]] || [[ $2 -gt 65535 ]]; then
+		echo "Error: invalid httpd_port - must be positive integer in range 1-65535"
+		exit 1
+	else
+		APACHE_PORT="$2"
+	fi
+fi
+
 if [[ "$(docker images -q trailofbits/polytracker 2>/dev/null)" == "" ]]; then
 	docker build -t trailofbits/polytracker -f ../../Dockerfile ../../
 fi
@@ -27,7 +39,7 @@ if [[ "$HOST_DIR" == "$SCRIPT_DIR" ]]; then
 		/polytracker/examples/http/httpd/harness_httpd.sh "$1"
 else
 	CONTAINER_PATH=/testcase/"$BASENAME"
-	docker run -ti --rm -e POLYPATH="$CONTAINER_PATH" -e POLYDB=/workdir/"$BASENAME".tdag \
+	docker run -ti --rm -e POLYPATH="$CONTAINER_PATH" -e POLYDB=/workdir/"$BASENAME".tdag -e APACHE_PORT="$APACHE_PORT" \
 		--mount type=bind,source="$(pwd)",target=/workdir \
 		--mount type=bind,source="$HOST_PATH",target="$CONTAINER_PATH" \
 		trailofbits/polytracker-demo-http-httpd:latest \
diff --git a/examples/http/httpd/harness_httpd.sh b/examples/http/httpd/harness_httpd.sh
index 0dc79873..8cd05f9b 100755
--- a/examples/http/httpd/harness_httpd.sh
+++ b/examples/http/httpd/harness_httpd.sh
@@ -3,14 +3,22 @@
 set -e
 
 APACHE_ROOT=/usr/local/apache2
+
+# NB: this should be set via Docker if used with example_httpd.sh
+if [[ -z "${APACHE_PORT}" ]]; then
+	APACHE_PORT=80
+else
+	sed -i 's/:80/:'"$APACHE_PORT"'/g' "$APACHE_ROOT"/conf/httpd.conf
+fi
+
 $APACHE_ROOT/bin/apachectl -X &
 # needed for server initialization in single-worker mode
 sleep 10
 
 # send request (from text file - first command line arg) to instrumented httpd
-nc localhost 80 <"$1"
+nc localhost "$APACHE_PORT" <"$1"
 
-APACHE_PID=$(cat /usr/local/apache2/logs/httpd.pid)
+APACHE_PID=$(cat "$APACHE_ROOT"/logs/httpd.pid)
 kill "$APACHE_PID"
 wait