Implement entity_id. Issue #155

This implements the 12 byte entity id as defined in
https://www.elastic.co/docs/reference/ecs/ecs-process#field-process-entity-id

We can't depend on dynamic linking of md or openssl, so include a standlone MIT
licensed sha256 implementation from https://github.com/ilvn/SHA256, they claim
to be formally verified, so that's something.

We now also have to link against resolv so we can get the base64 functions,
that's ok, beats already links against it. Musl doesn't have b64_ntop so we
include a replacement guarded by NO_B64.

This is a WIP as I want to make sure we compute the very same entity_id as
gosysinfo and friends.

Author: haesbaert

Makefile

@@ -43,6 +43,9 @@ CPPFLAGS?= -D_GNU_SOURCE
 ifndef SYSLIB
 CPPFLAGS+= -Iinclude/usr/include
 endif
+ifdef NO_B64
+CPPFLAGS+= -DNO_B64
+endif
 
 CDIAGFLAGS+= -Wall
 CDIAGFLAGS+= -Wextra
@@ -90,13 +93,15 @@ LIBQUARK_DEPS+= $(EEBPF_FILES) include
 endif
 LIBQUARK_DEPS:= $(filter-out manpages.h, $(LIBQUARK_DEPS))
 LIBQUARK_SRCS:=			\
+	base64.c		\
 	bpf_queue.c		\
 	btf.c			\
 	btfhub.c		\
 	compat.c		\
 	kprobe_queue.c		\
 	quark.c			\
-	qutil.c
+	qutil.c			\
+	sha256.c
 LIBQUARK_OBJS:= $(patsubst %.c,%.o,$(LIBQUARK_SRCS))
 LIBQUARK_STATIC:= libquark.a
 LIBQUARK_STATIC_BIG:= libquark_big.a
@@ -109,6 +114,11 @@ LIBQUARK_TARGET=$(LIBQUARK_STATIC)
 EXTRA_LDFLAGS+= -lbpf
 endif
 
+# for b64_ntop()
+ifndef NO_B64
+EXTRA_LDFLAGS+= -lresolv
+endif
+
 # ZLIB
 ZLIB_SRC:= zlib
 ZLIB_FILES:= $(shell find $(ZLIB_SRC) \(\
@@ -287,7 +297,7 @@ alpine: alpine-image clean-all
 	$(call msg,ALPINE-DOCKER-RUN,Dockerfile)
 	$(Q)$(DOCKER) run 				\
 		$(ALPINE_RUN_ARGS) $(SHELL)		\
-		-c "make -C $(PWD) all initramfs.gz EXTRA_LDFLAGS=-lfts"
+		-c "make -C $(PWD) all initramfs.gz EXTRA_LDFLAGS=-lfts NO_B64=y"
 
 alpine-image: clean-all
 	$(call msg,ALPINE-IMAGE,Dockerfile.alpine)

base64.c

@@ -0,0 +1,307 @@
+/*	$OpenBSD: base64.c,v 1.5 2006/10/21 09:55:03 otto Exp $	*/
+
+/*
+ * Copyright (c) 1996 by Internet Software Consortium.
+ *
+ * Permission to use, copy, modify, and distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND INTERNET SOFTWARE CONSORTIUM DISCLAIMS
+ * ALL WARRANTIES WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES
+ * OF MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL INTERNET SOFTWARE
+ * CONSORTIUM BE LIABLE FOR ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL
+ * DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR
+ * PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS
+ * ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS
+ * SOFTWARE.
+ */
+
+/*
+ * Portions Copyright (c) 1995 by International Business Machines, Inc.
+ *
+ * International Business Machines, Inc. (hereinafter called IBM) grants
+ * permission under its copyrights to use, copy, modify, and distribute this
+ * Software with or without fee, provided that the above copyright notice and
+ * all paragraphs of this notice appear in all copies, and that the name of IBM
+ * not be used in connection with the marketing of any product incorporating
+ * the Software or modifications thereof, without specific, written prior
+ * permission.
+ *
+ * To the extent it has a right to do so, IBM grants an immunity from suit
+ * under its patents, if any, for the use, sale or manufacture of products to
+ * the extent that such products are used for performing Domain Name System
+ * dynamic updates in TCP/IP networks by means of the Software.  No immunity is
+ * granted for any product per se or for any other function of any product.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", AND IBM DISCLAIMS ALL WARRANTIES,
+ * INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
+ * PARTICULAR PURPOSE.  IN NO EVENT SHALL IBM BE LIABLE FOR ANY SPECIAL,
+ * DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER ARISING
+ * OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE, EVEN
+ * IF IBM IS APPRISED OF THE POSSIBILITY OF SUCH DAMAGES.
+ */
+
+/* OPENBSD ORIGINAL: lib/libc/net/base64.c */
+
+#ifdef NO_B64
+
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+
+#include <ctype.h>
+#include <stdio.h>
+
+#include <stdlib.h>
+#include <string.h>
+
+#include "compat.h"
+
+static const char Base64[] =
+	"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/";
+static const char Pad64 = '=';
+
+/* (From RFC1521 and draft-ietf-dnssec-secext-03.txt)
+   The following encoding technique is taken from RFC 1521 by Borenstein
+   and Freed.  It is reproduced here in a slightly edited form for
+   convenience.
+
+   A 65-character subset of US-ASCII is used, enabling 6 bits to be
+   represented per printable character. (The extra 65th character, "=",
+   is used to signify a special processing function.)
+
+   The encoding process represents 24-bit groups of input bits as output
+   strings of 4 encoded characters. Proceeding from left to right, a
+   24-bit input group is formed by concatenating 3 8-bit input groups.
+   These 24 bits are then treated as 4 concatenated 6-bit groups, each
+   of which is translated into a single digit in the base64 alphabet.
+
+   Each 6-bit group is used as an index into an array of 64 printable
+   characters. The character referenced by the index is placed in the
+   output string.
+
+                         Table 1: The Base64 Alphabet
+
+      Value Encoding  Value Encoding  Value Encoding  Value Encoding
+          0 A            17 R            34 i            51 z
+          1 B            18 S            35 j            52 0
+          2 C            19 T            36 k            53 1
+          3 D            20 U            37 l            54 2
+          4 E            21 V            38 m            55 3
+          5 F            22 W            39 n            56 4
+          6 G            23 X            40 o            57 5
+          7 H            24 Y            41 p            58 6
+          8 I            25 Z            42 q            59 7
+          9 J            26 a            43 r            60 8
+         10 K            27 b            44 s            61 9
+         11 L            28 c            45 t            62 +
+         12 M            29 d            46 u            63 /
+         13 N            30 e            47 v
+         14 O            31 f            48 w         (pad) =
+         15 P            32 g            49 x
+         16 Q            33 h            50 y
+
+   Special processing is performed if fewer than 24 bits are available
+   at the end of the data being encoded.  A full encoding quantum is
+   always completed at the end of a quantity.  When fewer than 24 input
+   bits are available in an input group, zero bits are added (on the
+   right) to form an integral number of 6-bit groups.  Padding at the
+   end of the data is performed using the '=' character.
+
+   Since all base64 input is an integral number of octets, only the
+         -------------------------------------------------                       
+   following cases can arise:
+   
+       (1) the final quantum of encoding input is an integral
+           multiple of 24 bits; here, the final unit of encoded
+	   output will be an integral multiple of 4 characters
+	   with no "=" padding,
+       (2) the final quantum of encoding input is exactly 8 bits;
+           here, the final unit of encoded output will be two
+	   characters followed by two "=" padding characters, or
+       (3) the final quantum of encoding input is exactly 16 bits;
+           here, the final unit of encoded output will be three
+	   characters followed by one "=" padding character.
+   */
+
+int
+b64_ntop(u_char const *src, size_t srclength, char *target, size_t targsize)
+{
+	size_t datalength = 0;
+	u_char input[3];
+	u_char output[4];
+	u_int i;
+
+	while (2 < srclength) {
+		input[0] = *src++;
+		input[1] = *src++;
+		input[2] = *src++;
+		srclength -= 3;
+
+		output[0] = input[0] >> 2;
+		output[1] = ((input[0] & 0x03) << 4) + (input[1] >> 4);
+		output[2] = ((input[1] & 0x0f) << 2) + (input[2] >> 6);
+		output[3] = input[2] & 0x3f;
+
+		if (datalength + 4 > targsize)
+			return (-1);
+		target[datalength++] = Base64[output[0]];
+		target[datalength++] = Base64[output[1]];
+		target[datalength++] = Base64[output[2]];
+		target[datalength++] = Base64[output[3]];
+	}
+    
+	/* Now we worry about padding. */
+	if (0 != srclength) {
+		/* Get what's left. */
+		input[0] = input[1] = input[2] = '\0';
+		for (i = 0; i < srclength; i++)
+			input[i] = *src++;
+	
+		output[0] = input[0] >> 2;
+		output[1] = ((input[0] & 0x03) << 4) + (input[1] >> 4);
+		output[2] = ((input[1] & 0x0f) << 2) + (input[2] >> 6);
+
+		if (datalength + 4 > targsize)
+			return (-1);
+		target[datalength++] = Base64[output[0]];
+		target[datalength++] = Base64[output[1]];
+		if (srclength == 1)
+			target[datalength++] = Pad64;
+		else
+			target[datalength++] = Base64[output[2]];
+		target[datalength++] = Pad64;
+	}
+	if (datalength >= targsize)
+		return (-1);
+	target[datalength] = '\0';	/* Returned value doesn't count \0. */
+	return (datalength);
+}
+
+/* skips all whitespace anywhere.
+   converts characters, four at a time, starting at (or after)
+   src from base - 64 numbers into three 8 bit bytes in the target area.
+   it returns the number of data bytes stored at the target, or -1 on error.
+ */
+
+int
+b64_pton(char const *src, u_char *target, size_t targsize)
+{
+	u_int tarindex, state;
+	int ch;
+	char *pos;
+
+	state = 0;
+	tarindex = 0;
+
+	while ((ch = *src++) != '\0') {
+		if (isspace(ch))	/* Skip whitespace anywhere. */
+			continue;
+
+		if (ch == Pad64)
+			break;
+
+		pos = strchr(Base64, ch);
+		if (pos == 0)		/* A non-base64 character. */
+			return (-1);
+
+		switch (state) {
+		case 0:
+			if (target) {
+				if (tarindex >= targsize)
+					return (-1);
+				target[tarindex] = (pos - Base64) << 2;
+			}
+			state = 1;
+			break;
+		case 1:
+			if (target) {
+				if (tarindex + 1 >= targsize)
+					return (-1);
+				target[tarindex]   |=  (pos - Base64) >> 4;
+				target[tarindex+1]  = ((pos - Base64) & 0x0f)
+							<< 4 ;
+			}
+			tarindex++;
+			state = 2;
+			break;
+		case 2:
+			if (target) {
+				if (tarindex + 1 >= targsize)
+					return (-1);
+				target[tarindex]   |=  (pos - Base64) >> 2;
+				target[tarindex+1]  = ((pos - Base64) & 0x03)
+							<< 6;
+			}
+			tarindex++;
+			state = 3;
+			break;
+		case 3:
+			if (target) {
+				if (tarindex >= targsize)
+					return (-1);
+				target[tarindex] |= (pos - Base64);
+			}
+			tarindex++;
+			state = 0;
+			break;
+		}
+	}
+
+	/*
+	 * We are done decoding Base-64 chars.  Let's see if we ended
+	 * on a byte boundary, and/or with erroneous trailing characters.
+	 */
+
+	if (ch == Pad64) {		/* We got a pad char. */
+		ch = *src++;		/* Skip it, get next. */
+		switch (state) {
+		case 0:		/* Invalid = in first position */
+		case 1:		/* Invalid = in second position */
+			return (-1);
+
+		case 2:		/* Valid, means one byte of info */
+			/* Skip any number of spaces. */
+			for (; ch != '\0'; ch = *src++)
+				if (!isspace(ch))
+					break;
+			/* Make sure there is another trailing = sign. */
+			if (ch != Pad64)
+				return (-1);
+			ch = *src++;		/* Skip the = */
+			/* Fall through to "single trailing =" case. */
+			/* FALLTHROUGH */
+
+		case 3:		/* Valid, means two bytes of info */
+			/*
+			 * We know this char is an =.  Is there anything but
+			 * whitespace after it?
+			 */
+			for (; ch != '\0'; ch = *src++)
+				if (!isspace(ch))
+					return (-1);
+
+			/*
+			 * Now make sure for cases 2 and 3 that the "extra"
+			 * bits that slopped past the last full byte were
+			 * zeros.  If we don't check them, they become a
+			 * subliminal channel.
+			 */
+			if (target && target[tarindex] != 0)
+				return (-1);
+		}
+	} else {
+		/*
+		 * We ended by seeing the end of the string.  Make sure we
+		 * have no partial bytes lying around.
+		 */
+		if (state != 0)
+			return (-1);
+	}
+
+	return (tarindex);
+}
+
+#endif /* NO_B64 */

compat.h

@@ -70,4 +70,21 @@ long long	strtonum(const char *, long long, long long, const char **);
  */
 void		sshbuf_dump_data(const void *, size_t, FILE *);
 
+/*
+ * Musl
+ */
+#ifdef NO_B64
+int b64_ntop(u_char const *src, size_t srclength, char *target,
+    size_t targsize);
+int b64_pton(char const *src, u_char *target, size_t targsize);
+#else
+#include <resolv.h>
+#endif /* NO_B64 */
+
+/*
+ * Linkining with the one billion versions of openssl is a pain, we need sha256
+ * for a dozen bytes only.
+ */
+#include "sha256.h"
+
 #endif	/* _COMPAT_H */