apache · my-ship-it · Jul 3, 2023 · Jul 3, 2023
diff --git a/concourse/scripts/dumpdb.bash b/concourse/scripts/dumpdb.bash
@@ -7,6 +7,8 @@ INSTALL_DIR=${INSTALL_DIR:-/usr/local/cloudberry-db-devel}
 source $INSTALL_DIR/greenplum_path.sh
 source ./gpdb_src/gpAux/gpdemo/gpdemo-env.sh
 
+# ignore ERR trap
+gpstop -qa || :
 gpstart -a
 sleep 60
 ./gpdb_src/concourse/scripts/ic_start_fts_once.bash

diff --git a/contrib/bloom/blinsert.c b/contrib/bloom/blinsert.c
@@ -176,6 +176,8 @@ blbuildempty(Relation index)
 	 * XLOG_DBASE_CREATE or XLOG_TBLSPC_CREATE record.  Therefore, we need
 	 * this even when wal_level=minimal.
 	 */
+	PageEncryptInplace(metapage, INIT_FORKNUM,
+					   BLOOM_METAPAGE_BLKNO);
 	PageSetChecksumInplace(metapage, BLOOM_METAPAGE_BLKNO);
 	smgrwrite(index->rd_smgr, INIT_FORKNUM, BLOOM_METAPAGE_BLKNO,
 			  (char *) metapage, true);

diff --git a/contrib/bloom/blscan.c b/contrib/bloom/blscan.c
@@ -97,7 +97,7 @@ blgetbitmap(IndexScanDesc scan, Node **bmNodeP)
 	if (*bmNodeP == NULL)
 	{
 		/* XXX should we use less than work_mem for this? */
-		tbm = tbm_create(work_mem * 1024L, NULL);
+		tbm = tbm_create(work_mem * 1024L, scan->dsa);
 		*bmNodeP = (Node *) tbm;
 	}
 	else if (!IsA(*bmNodeP, TIDBitmap))

diff --git a/deploy/cbdb_deploy.sh b/deploy/cbdb_deploy.sh
@@ -55,7 +55,7 @@ function cbdb_build() {
 
     #do compile configuration
     echo "[CBDB build] start to init configuraiton for code compile..."
-    CFLAGS=-O0 CXXFLAGS='-O0 -std=c++14' ./configure --prefix=${install_dir}/cbdb --enable-debug --enable-cassert --enable-tap-tests --with-gssapi --with-libxml --with-quicklz --with-pythonsrc-ext
+    CFLAGS=-O0 CXXFLAGS='-O0 -std=c++14' ./configure --prefix=${install_dir}/cbdb --enable-debug --enable-cassert --enable-tap-tests --with-gssapi --with-libxml --with-quicklz --with-pythonsrc-ext --with-openssl
 
     #do compile
     echo "[CBDB build] start to compile binary file..."

diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml
@@ -1542,19 +1542,31 @@ include_dir 'conf.d'
         mechanism is used.
        </para>
        <para>
-        The command must print the passphrase to the standard output and exit
-        with code 0.  In the parameter value, <literal>%p</literal> is
-        replaced by a prompt string.  (Write <literal>%%</literal> for a
-        literal <literal>%</literal>.)  Note that the prompt string will
-        probably contain whitespace, so be sure to quote adequately.  A single
-        newline is stripped from the end of the output if present.
+        The command must print the passphrase to the standard output
+        and exit with code 0.  It can prompt from the terminal if
+        <option>--authprompt</option> is used.  In the parameter
+        value, <literal>%R</literal> is replaced by a file descriptor
+        number opened to the terminal that started the server.  A file
+        descriptor is only available if enabled at server start via
+        <option>-R</option>.  If <literal>%R</literal> is specified and
+        no file descriptor is available, the server will not start.  Value
+        <literal>%p</literal> is replaced by a pre-defined prompt string.
+        (Write <literal>%%</literal> for a literal <literal>%</literal>.)
+        Note that the prompt string will probably contain whitespace,
+        so be sure to quote its use adequately.  Newlines are stripped
+        from the end of the output if present.
        </para>
+
        <para>
-        The command does not actually have to prompt the user for a
-        passphrase.  It can read it from a file, obtain it from a keychain
-        facility, or similar.  It is up to the user to make sure the chosen
-        mechanism is adequately secure.
+        Sample scripts can be found in
+        <filename>$SHAREDIR/auth_commands</filename>,
+        where <literal>$SHAREDIR</literal> means the
+        <productname>PostgreSQL</productname> installation's shared-data
+        directory, often <filename>/usr/local/share/postgresql</filename>
+        (use <command>pg_config --sharedir</command> to determine it if
+        you're not sure).
        </para>
+
        <para>
         This parameter can only be set in the <filename>postgresql.conf</filename>
         file or on the server command line.
@@ -1576,10 +1588,12 @@ include_dir 'conf.d'
         parameter is off (the default), then
         <varname>ssl_passphrase_command</varname> will be ignored during a
         reload and the SSL configuration will not be reloaded if a passphrase
-        is needed.  That setting is appropriate for a command that requires a
-        TTY for prompting, which might not be available when the server is
-        running.  Setting this parameter to on might be appropriate if the
-        passphrase is obtained from a file, for example.
+        is needed.  This setting is appropriate for a command that requires a
+        terminal for prompting, which will likely not be available when the server is
+        running.  (<option>--authprompt</option> closes the terminal file
+        descriptor soon after server start.)   Setting this parameter on
+        might be appropriate, for example, if the passphrase is obtained
+        from a file.
        </para>
        <para>
         This parameter can only be set in the <filename>postgresql.conf</filename>
@@ -2775,7 +2789,7 @@ include_dir 'conf.d'
         Note that changing <varname>wal_level</varname> to
         <literal>minimal</literal> makes any base backups taken before
         unavailable for archive recovery and standby server, which may
-        lead to data loss.
+        lead to data loss. Cluster file encryption also does not support.
        </para>
        <para>
         In <literal>logical</literal> level, the same information is logged as
@@ -3129,9 +3143,10 @@ include_dir 'conf.d'
        </para>
 
        <para>
-        If data checksums are enabled, hint bit updates are always WAL-logged
-        and this setting is ignored. You can use this setting to test how much
-        extra WAL-logging would occur if your database had data checksums
+        If data checksums or cluster file encryption is enabled,
+        hint bit updates are always WAL-logged and this setting is
+        ignored. You can use this setting to test how much extra
+        WAL-logging would occur if your database had data checksums
         enabled.
        </para>
 
@@ -8048,6 +8063,64 @@ COPY postgres_log FROM '/full/path/to/logfile.csv' WITH csv;
     </variablelist>
    </sect1>
 
+   <sect1 id="runtime-config-encryption">
+    <title>Cluster File Encryption</title>
+
+    <variablelist>
+     <varlistentry id="guc-cluster-key-command" xreflabel="cluster_key_command">
+      <term><varname>cluster_key_command</varname> (<type>string</type>)
+      <indexterm>
+       <primary><varname>cluster_key_command</varname> configuration parameter</primary>
+      </indexterm>
+      </term>
+      <listitem>
+       <para>
+        This option specifies an external command to obtain the cluster-level
+        key for cluster file encryption during server initialization and
+        server start.
+       </para>
+       <para>
+        The command must print the cluster key to the standard
+        output as 64 hexadecimal characters, and exit with code 0.
+        The command can prompt for the passphrase or PIN from the
+        terminal if <option>--authprompt</option> is used.  In the
+        parameter value, <literal>%R</literal> is replaced by a file
+        descriptor number opened to the terminal that started the server.
+        A file descriptor is only available if enabled at server start
+        via <option>-R</option>.  If <literal>%R</literal> is specified
+        and no file descriptor is available, the server will not start.
+        Value <literal>%p</literal> is replaced by a pre-defined
+        prompt string.  Value <literal>%d</literal> is replaced by the
+        directory containing the keys;  this is useful if the command
+        must create files with the keys, e.g., to store a cluster-level
+        key encrypted by a key stored in a hardware security module.
+        (Write <literal>%%</literal> for a literal <literal>%</literal>.)
+        Note that the prompt string will probably contain whitespace,
+        so be sure to quote its use adequately.  Newlines are stripped
+        from the end of the output if present.
+       </para>
+
+       <para>
+        Sample script can be found in
+        <filename>$SHAREDIR/auth_commands</filename>,
+        where <literal>$SHAREDIR</literal> means the
+        <productname>PostgreSQL</productname> installation's shared-data
+        directory, often <filename>/usr/local/share/postgresql</filename>
+        (use <command>pg_config --sharedir</command> to determine it if
+        you're not sure).
+       </para>
+
+       <para>
+        This parameter can only be set by
+        <application>initdb</application>, in the
+        <filename>postgresql.conf</filename> file, or on the server
+        command line.
+       </para>
+      </listitem>
+     </varlistentry>
+    </variablelist>
+   </sect1>
+
    <sect1 id="runtime-config-client">
     <title>Client Connection Defaults</title>
 
@@ -10068,6 +10141,22 @@ dynamic_library_path = 'C:\tools\postgresql;H:\my_project\lib;$libdir'
       </listitem>
      </varlistentry>
 
+     <varlistentry id="guc-file-encryption-method" xreflabel="file_encryption_method">
+      <term><varname>file_encryption_method</varname> (<type>boolean</type>)
+      <indexterm>
+       <primary>Cluster file encryption method</primary>
+      </indexterm>
+      </term>
+      <listitem>
+       <para>
+        Reports the cluster file
+        encryption method.  See <xref
+        linkend="app-initdb-cluster-key-command"/> for more
+        information.
+       </para>
+      </listitem>
+     </varlistentry>
+
      <varlistentry id="guc-data-directory-mode" xreflabel="data_directory_mode">
       <term><varname>data_directory_mode</varname> (<type>integer</type>)
       <indexterm>

diff --git a/doc/src/sgml/database-encryption.sgml b/doc/src/sgml/database-encryption.sgml
@@ -0,0 +1,149 @@
+<!-- doc/src/sgml/database-encryption.sgml -->
+
+<chapter id="cluster-file-encryption">
+ <title>Cluster File Encryption</title>
+
+ <indexterm zone="cluster-file-encryption">
+  <primary>Cluster File Encryption</primary>
+ </indexterm>
+
+ <para>
+  The purpose of cluster file encryption is to prevent users with read
+  access on the directories used to store database files and write-ahead
+  log files from being able to access the data stored in those files.
+  For example, when using cluster file encryption, users who have read
+  access to the cluster directories for backup purposes will not be able
+  to decrypt the data stored in these files.  Read-only access for a group
+  of users can be enabled using the <application>initdb</application>
+  <option>--allow-group-access</option> option.  Cluster file encryption
+  also provides data-at-rest security, protecting users from data loss
+  should the physical storage media be stolen or improperly erased before
+  disposal.
+ </para>
+
+ <para>
+  Cluster file encryption does not protect against unauthorized file
+  system writes.  Such writes can allow data decryption if used to weaken
+  the system's security and the weakened system is later supplied with
+  the externally-stored cluster encryption key.  This also does not always
+  detect if users with write access remove or modify database files.
+ </para>
+
+ <para>
+  This also does not protect against users who have read access to database
+  process memory because all in-memory data pages and data encryption keys
+  are stored unencrypted in memory.  Therefore, an attacker who is able
+  to read memory can read the data encryption keys and decrypt the entire
+  cluster.  The Postgres operating system user and the operating system
+  administrator, e.g., the <literal>root</literal> user, have such access.
+ </para>
+
+ <sect1 id="cluster-encryption-keys">
+  <title>Keys</title>
+
+  <para>
+   Cluster file encryption uses two levels of encryption &mdash; an upper
+   key which encrypts lower-level keys.  The upper-level key is often
+   referred to as a Key Encryption Key (<acronym>KEK</acronym>).  This key
+   is <emphasis>not</emphasis> stored in the file system, but provided at
+   <command>initdb</command> time and each time the server is started.  This
+   key can be easily changed via <command>pg_alterckey</command> without
+   requiring any changes to the the data files or <command>WAL</command>
+   files.
+  </para>
+
+  <para>
+   The lower level keys are data encryption keys, specifically for relations
+   and <acronym>WAL</acronym>.  The relation key is used to encrypt database
+   heap and index files.  The WAL key is used to encrypt write-ahead log
+   (WAL) files.  Two different keys are used so that primary and standby
+   servers can use different relation keys, but the same WAL key, so that
+   these keys can (in a future release) be rotated by switching the
+   primary to the standby and then changing the WAL key.  Eventually,
+   encryption will be able to added to non-encrypted clusters by creating
+   encrypted replicas and switching over to them.
+  </para>
+
+  <para>
+   Postgres stores the data encryption (lower-level) keys in the data
+   directory encrypted (wrapped) by key encryption (upper-level) key.
+   Though the data encryption keys technically exist in the file system,
+   the key encryption key does not, so the data encryption keys are
+   securely stored.  Data encryption keys are used to security encrypt
+   other database files.
+  </para>
+ </sect1>
+
+ <sect1 id="cluster-encryption-initialization">
+  <title>Initialization</title>
+
+  <para>
+   Cluster file encryption is enabled when
+   <productname>PostgreSQL</productname> is built
+   with <literal>--with-openssl</literal> and <xref
+   linkend="app-initdb-cluster-key-command"/> is specified
+   during <command>initdb</command>.  The cluster key
+   provided by the <option>--cluster-key-command</option>
+   option during <command>initdb</command> and the one generated
+   by <xref linkend="guc-cluster-key-command"/> in the
+   <filename>postgresql.conf</filename> must match for the database
+   cluster to start. Note that the cluster key command
+   passed to <command>initdb</command> must return a key of
+   64 hexadecimal characters. For example:
+<programlisting>
+initdb -D dbname --cluster-key-command='ckey_passphrase.sh'
+</programlisting>
+   Cluster file encryption does not support a <varname>wal_level</varname>
+   of <literal>minimal</literal>.
+  </para>
+ </sect1>
+
+ <sect1 id="cluster-encryption-operation">
+  <title>Operation</title>
+
+  <para>
+   During the <command>initdb</command> process, if
+   <option>--cluster-key-command</option> is specified, two data-level
+   encryption keys are created.   These two keys are then encrypted with
+   the key encryption key (KEK) supplied by the cluster key command before
+   being stored in the database directory.  The key or passphrase that
+   derives the key must be supplied from the terminal or stored in a
+   trusted key store, such as key vault software or a hardware security
+   module.
+  </para>
+
+  <para>
+   If the <productname>PostgreSQL</productname> server has
+   been initialized to require a cluster key, each time the
+   server starts the <filename>postgresql.conf</filename>
+   <varname>cluster_key_command</varname> command will be executed
+   and the cluster key retrieved.  The data encryption keys in the
+   <filename>pg_cryptokeys</filename> directory will then be decrypted
+   using the supplied key and integrity-checked to ensure it matches the
+   initdb-supplied key.  (If this check fails, the server will refuse
+   to start.)  The cluster encryption key will then be removed from
+   system memory.  The decrypted data encryption keys will remain in
+   shared memory until the server is stopped.
+  </para>
+
+  <para>
+   The data encryption keys are randomly generated and can be 128, 192,
+   or 256-bits in length, depending on whether <literal>AES128</literal>,
+   <literal>AES192</literal>, or <literal>AES256</literal> is specified.
+   They are encrypted by the key encryption key (KEK) using Advanced
+   Encryption Standard (<acronym>AES256</acronym>) encryption in Key
+   Wrap Padded Mode, which also provides KEK authentication;  see <ulink
+   url="https://tools.ietf.org/html/rfc5649">RFC 5649</ulink>. While
+   128-bit encryption is sufficient for most sites, 256-bit encryption
+   is thought to be more immune to future quantum cryptographic attacks.
+  </para>
+
+  <para>.
+   If you prefer to create the random keys on your own, you can create
+   a empty directory with a <filename>pg_cryptokeys/live</filename>
+   subdirectory, generate the keys there using your tools. and use the
+   <command>initdb</command> <option>--copy-encryption-keys</option>
+   to copy those keys into the newly-created  cluster.
+  </para>
+ </sect1>
+</chapter>
diff --git a/doc/src/sgml/filelist.sgml b/doc/src/sgml/filelist.sgml
@@ -49,6 +49,7 @@
 <!ENTITY wal           SYSTEM "wal.sgml">
 <!ENTITY logical-replication    SYSTEM "logical-replication.sgml">
 <!ENTITY jit    SYSTEM "jit.sgml">
+<!ENTITY database-encryption SYSTEM "database-encryption.sgml">
 
 <!-- programmer's guide -->
 <!ENTITY bgworker   SYSTEM "bgworker.sgml">

diff --git a/doc/src/sgml/installation.sgml b/doc/src/sgml/installation.sgml
@@ -1004,7 +1004,7 @@ build-postgresql:
        <listitem>
         <para>
          Build with support for <acronym>SSL</acronym> (encrypted)
-         connections. The only <replaceable>LIBRARY</replaceable>
+         connections and cluster file encryption.  The only <replaceable>LIBRARY</replaceable>
          supported is <option>openssl</option>. This requires the
          <productname>OpenSSL</productname> package to be installed.
          <filename>configure</filename> will check for the required

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
@@ -1318,6 +1318,19 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
       <entry><literal>DataFileWrite</literal></entry>
       <entry>Waiting for a write to a relation data file.</entry>
      </row>
+     <row>
+      <entry><literal>KeyFileRead</literal></entry>
+      <entry>Waiting for a read of the wrapped data encryption keys.</entry>
+     </row>
+     <row>
+      <entry><literal>KeyFileWrite</literal></entry>
+      <entry>Waiting for a write of the wrapped data encryption keys.</entry>
+     </row>
+     <row>
+      <entry><literal>KeyFileSync</literal></entry>
+      <entry>Waiting for changes to the wrapped data encryption keys to reach
+       durable storage.</entry>
+     </row>
      <row>
       <entry><literal>LockFileAddToDataDirRead</literal></entry>
       <entry>Waiting for a read while adding a line to the data directory lock