Makefile + hash.h: remove PPC_SHA1 implementation

Remove the PPC_SHA1 implementation added in a6ef3518f9 ([PATCH] PPC
assembly implementation of SHA1, 2005-04-22). When this was added
Apple consumer hardware used the PPC architecture, and the
implementation was intended to improve SHA-1 speed there.

Since it was added we've moved to using sha1collisiondetection by
default, and anyone wanting hard-rolled non-DC SHA-1 implementation
can use OpenSSL's via the OPENSSL_SHA1 knob.

The PPC_SHA1 originally originally targeted 32 bit PPC, and later the
64 bit PPC 970 (a.k.a. Apple PowerPC G5). See 926172c5e4 (block-sha1:
improve code on large-register-set machines, 2009-08-10) for a
reference about the performance on G5 (a comment in block-sha1/sha1.c
being removed here).

I can't get it to do anything but segfault on both the BE and LE POWER
machines in the GCC compile farm[1]. Anyone who's concerned about
performance on PPC these days is likely to be using the IBM POWER
processors.

There have been proposals to entirely remove non-sha1collisiondetection
implementations from the tree[2]. I think per [3] that would be a bit
overzealous. I.e. there are various set-ups git's speed is going to be
more important than the relatively implausible SHA-1 collision attack,
or where such attacks are entirely mitigated by other means (e.g. by
incoming objects being checked with DC_SHA1).

But that really doesn't apply to PPC_SHA1 in particular, which seems
to have outlived its usefulness.

As this gets rid of the only in-tree *.S assembly file we can remove
the small bits of logic from the Makefile needed to build objects
from *.S (as opposed to *.c)

The code being removed here was also throwing warnings with the
"-pedantic" flag, it could have been fixed as 544d93bc3b (block-sha1:
remove use of obsolete x86 assembly, 2022-03-10) did for block-sha1/*,
but as noted above let's remove it instead.

1. https://cfarm.tetaneutral.net/machines/list/
   Tested on gcc{110,112,135,203}, a mixture of POWER [789] ppc64 and
   ppc64le. All segfault in anything needing object
   hashing (e.g. t/t1007-hash-object.sh) when compiled with
   PPC_SHA1=Y.
2. https://lore.kernel.org/git/20200223223758.120941-1-mh@glandium.org/
3. https://lore.kernel.org/git/20200224044732.GK1018190@coredump.intra.peff.net/

Acked-by: brian m. carlson" <sandals@crustytoothpaste.net>
Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

INSTALL

@@ -135,8 +135,7 @@ Issues of note:
 
 	  By default, git uses OpenSSL for SHA1 but it will use its own
 	  library (inspired by Mozilla's) with either NO_OPENSSL or
-	  BLK_SHA1.  Also included is a version optimized for PowerPC
+	  BLK_SHA1.
-	  (PPC_SHA1).
 
 	- "libcurl" library is used for fetching and pushing
 	  repositories over http:// or https://, as well as by

Makefile

@@ -155,9 +155,6 @@ include shared.mak
 # Define BLK_SHA1 environment variable to make use of the bundled
 # optimized C SHA1 routine.
 #
-# Define PPC_SHA1 environment variable when running make to make use of
-# a bundled SHA1 routine optimized for PowerPC.
-#
 # Define DC_SHA1 to unconditionally enable the collision-detecting sha1
 # algorithm. This is slower, but may detect attempted collision attacks.
 # Takes priority over other *_SHA1 knobs.
@@ -1802,6 +1799,10 @@ ifdef APPLE_COMMON_CRYPTO
 	SHA1_MAX_BLOCK_SIZE = 1024L*1024L*1024L
 endif
 
+ifdef PPC_SHA1
+$(error the PPC_SHA1 flag has been removed along with the PowerPC-specific SHA-1 implementation.)
+endif
+
 ifdef OPENSSL_SHA1
 	EXTLIBS += $(LIB_4_CRYPTO)
 	BASIC_CFLAGS += -DSHA1_OPENSSL
@@ -1810,10 +1811,6 @@ ifdef BLK_SHA1
 	LIB_OBJS += block-sha1/sha1.o
 	BASIC_CFLAGS += -DSHA1_BLK
 else
-ifdef PPC_SHA1
-	LIB_OBJS += ppc/sha1.o ppc/sha1ppc.o
-	BASIC_CFLAGS += -DSHA1_PPC
-else
 ifdef APPLE_COMMON_CRYPTO
 	COMPAT_CFLAGS += -DCOMMON_DIGEST_FOR_OPENSSL
 	BASIC_CFLAGS += -DSHA1_APPLE
@@ -1847,7 +1844,6 @@ endif
 endif
 endif
 endif
-endif
 
 ifdef OPENSSL_SHA256
 	EXTLIBS += $(LIB_4_CRYPTO)
@@ -2594,14 +2590,10 @@ missing_compdb_dir =
 compdb_args =
 endif
 
-ASM_SRC := $(wildcard $(OBJECTS:o=S))
+C_OBJ := $(OBJECTS)
-ASM_OBJ := $(ASM_SRC:S=o)
-C_OBJ := $(filter-out $(ASM_OBJ),$(OBJECTS))
 
 $(C_OBJ): %.o: %.c GIT-CFLAGS $(missing_dep_dirs) $(missing_compdb_dir)
 	$(QUIET_CC)$(CC) -o $*.o -c $(dep_args) $(compdb_args) $(ALL_CFLAGS) $(EXTRA_CPPFLAGS) $<
-$(ASM_OBJ): %.o: %.S GIT-CFLAGS $(missing_dep_dirs) $(missing_compdb_dir)
-	$(QUIET_CC)$(CC) -o $*.o -c $(dep_args) $(compdb_args) $(ALL_CFLAGS) $(EXTRA_CPPFLAGS) $<
 
 %.s: %.c GIT-CFLAGS FORCE
 	$(QUIET_CC)$(CC) -o $@ -S $(ALL_CFLAGS) $(EXTRA_CPPFLAGS) $<

block-sha1/sha1.c

@@ -28,10 +28,6 @@
  * try to do the silly "optimize away loads" part because it won't
  * see what the value will be).
  *
- * Ben Herrenschmidt reports that on PPC, the C version comes close
- * to the optimized asm with this (ie on PPC you don't want that
- * 'volatile', since there are lots of registers).
- *
  * On ARM we get the best code generation by forcing a full memory barrier
  * between each SHA_ROUND, otherwise gcc happily get wild with spilling and
  * the stack frame size simply explode and performance goes down the drain.

configure.ac

@@ -237,9 +237,6 @@ AC_MSG_NOTICE([CHECKS for site configuration])
 # tests.  These tests take up a significant amount of the total test time
 # but are not needed unless you plan to talk to SVN repos.
 #
-# Define PPC_SHA1 environment variable when running make to make use of
-# a bundled SHA1 routine optimized for PowerPC.
-#
 # Define NO_OPENSSL environment variable if you do not have OpenSSL.
 #
 # Define OPENSSLDIR=/foo/bar if your openssl header and library files are in

hash.h

@@ -4,9 +4,7 @@
 #include "git-compat-util.h"
 #include "repository.h"
 
-#if defined(SHA1_PPC)
+#if defined(SHA1_APPLE)
-#include "ppc/sha1.h"
-#elif defined(SHA1_APPLE)
 #include <CommonCrypto/CommonDigest.h>
 #elif defined(SHA1_OPENSSL)
 #include <openssl/sha.h>
@@ -32,7 +30,7 @@
  * platform's underlying implementation of SHA-1; could be OpenSSL,
  * blk_SHA, Apple CommonCrypto, etc...  Note that the relevant
  * SHA-1 header may have already defined platform_SHA_CTX for our
- * own implementations like block-sha1 and ppc-sha1, so we list
+ * own implementations like block-sha1, so we list
  * the default for OpenSSL compatible SHA-1 implementations here.
  */
 #define platform_SHA_CTX	SHA_CTX

ppc/sha1.c

@@ -1,72 +0,0 @@
-/*
- * SHA-1 implementation.
- *
- * Copyright (C) 2005 Paul Mackerras <paulus@samba.org>
- *
- * This version assumes we are running on a big-endian machine.
- * It calls an external sha1_core() to process blocks of 64 bytes.
- */
-#include <stdio.h>
-#include <string.h>
-#include "sha1.h"
-
-void ppc_sha1_core(uint32_t *hash, const unsigned char *p,
-		   unsigned int nblocks);
-
-int ppc_SHA1_Init(ppc_SHA_CTX *c)
-{
-	c->hash[0] = 0x67452301;
-	c->hash[1] = 0xEFCDAB89;
-	c->hash[2] = 0x98BADCFE;
-	c->hash[3] = 0x10325476;
-	c->hash[4] = 0xC3D2E1F0;
-	c->len = 0;
-	c->cnt = 0;
-	return 0;
-}
-
-int ppc_SHA1_Update(ppc_SHA_CTX *c, const void *ptr, unsigned long n)
-{
-	unsigned long nb;
-	const unsigned char *p = ptr;
-
-	c->len += (uint64_t) n << 3;
-	while (n != 0) {
-		if (c->cnt || n < 64) {
-			nb = 64 - c->cnt;
-			if (nb > n)
-				nb = n;
-			memcpy(&c->buf.b[c->cnt], p, nb);
-			if ((c->cnt += nb) == 64) {
-				ppc_sha1_core(c->hash, c->buf.b, 1);
-				c->cnt = 0;
-			}
-		} else {
-			nb = n >> 6;
-			ppc_sha1_core(c->hash, p, nb);
-			nb <<= 6;
-		}
-		n -= nb;
-		p += nb;
-	}
-	return 0;
-}
-
-int ppc_SHA1_Final(unsigned char *hash, ppc_SHA_CTX *c)
-{
-	unsigned int cnt = c->cnt;
-
-	c->buf.b[cnt++] = 0x80;
-	if (cnt > 56) {
-		if (cnt < 64)
-			memset(&c->buf.b[cnt], 0, 64 - cnt);
-		ppc_sha1_core(c->hash, c->buf.b, 1);
-		cnt = 0;
-	}
-	if (cnt < 56)
-		memset(&c->buf.b[cnt], 0, 56 - cnt);
-	c->buf.l[7] = c->len;
-	ppc_sha1_core(c->hash, c->buf.b, 1);
-	memcpy(hash, c->hash, 20);
-	return 0;
-}

ppc/sha1.h

@@ -1,25 +0,0 @@
-/*
- * SHA-1 implementation.
- *
- * Copyright (C) 2005 Paul Mackerras <paulus@samba.org>
- */
-#include <stdint.h>
-
-typedef struct {
-	uint32_t hash[5];
-	uint32_t cnt;
-	uint64_t len;
-	union {
-		unsigned char b[64];
-		uint64_t l[8];
-	} buf;
-} ppc_SHA_CTX;
-
-int ppc_SHA1_Init(ppc_SHA_CTX *c);
-int ppc_SHA1_Update(ppc_SHA_CTX *c, const void *p, unsigned long n);
-int ppc_SHA1_Final(unsigned char *hash, ppc_SHA_CTX *c);
-
-#define platform_SHA_CTX	ppc_SHA_CTX
-#define platform_SHA1_Init	ppc_SHA1_Init
-#define platform_SHA1_Update	ppc_SHA1_Update
-#define platform_SHA1_Final	ppc_SHA1_Final

ppc/sha1ppc.S

@@ -1,224 +0,0 @@
-/*
- * SHA-1 implementation for PowerPC.
- *
- * Copyright (C) 2005 Paul Mackerras <paulus@samba.org>
- */
-
-/*
- * PowerPC calling convention:
- * %r0 - volatile temp
- * %r1 - stack pointer.
- * %r2 - reserved
- * %r3-%r12 - Incoming arguments & return values; volatile.
- * %r13-%r31 - Callee-save registers
- * %lr - Return address, volatile
- * %ctr - volatile
- *
- * Register usage in this routine:
- * %r0 - temp
- * %r3 - argument (pointer to 5 words of SHA state)
- * %r4 - argument (pointer to data to hash)
- * %r5 - Constant K in SHA round (initially number of blocks to hash)
- * %r6-%r10 - Working copies of SHA variables A..E (actually E..A order)
- * %r11-%r26 - Data being hashed W[].
- * %r27-%r31 - Previous copies of A..E, for final add back.
- * %ctr - loop count
- */
-
-
-/*
- * We roll the registers for A, B, C, D, E around on each
- * iteration; E on iteration t is D on iteration t+1, and so on.
- * We use registers 6 - 10 for this.  (Registers 27 - 31 hold
- * the previous values.)
- */
-#define RA(t)	(((t)+4)%5+6)
-#define RB(t)	(((t)+3)%5+6)
-#define RC(t)	(((t)+2)%5+6)
-#define RD(t)	(((t)+1)%5+6)
-#define RE(t)	(((t)+0)%5+6)
-
-/* We use registers 11 - 26 for the W values */
-#define W(t)	((t)%16+11)
-
-/* Register 5 is used for the constant k */
-
-/*
- * The basic SHA-1 round function is:
- * E += ROTL(A,5) + F(B,C,D) + W[i] + K;  B = ROTL(B,30)
- * Then the variables are renamed: (A,B,C,D,E) = (E,A,B,C,D).
- *
- * Every 20 rounds, the function F() and the constant K changes:
- * - 20 rounds of f0(b,c,d) = "bit wise b ? c : d" =  (^b & d) + (b & c)
- * - 20 rounds of f1(b,c,d) = b^c^d = (b^d)^c
- * - 20 rounds of f2(b,c,d) = majority(b,c,d) = (b&d) + ((b^d)&c)
- * - 20 more rounds of f1(b,c,d)
- *
- * These are all scheduled for near-optimal performance on a G4.
- * The G4 is a 3-issue out-of-order machine with 3 ALUs, but it can only
- * *consider* starting the oldest 3 instructions per cycle.  So to get
- * maximum performance out of it, you have to treat it as an in-order
- * machine.  Which means interleaving the computation round t with the
- * computation of W[t+4].
- *
- * The first 16 rounds use W values loaded directly from memory, while the
- * remaining 64 use values computed from those first 16.  We preload
- * 4 values before starting, so there are three kinds of rounds:
- * - The first 12 (all f0) also load the W values from memory.
- * - The next 64 compute W(i+4) in parallel. 8*f0, 20*f1, 20*f2, 16*f1.
- * - The last 4 (all f1) do not do anything with W.
- *
- * Therefore, we have 6 different round functions:
- * STEPD0_LOAD(t,s) - Perform round t and load W(s).  s < 16
- * STEPD0_UPDATE(t,s) - Perform round t and compute W(s).  s >= 16.
- * STEPD1_UPDATE(t,s)
- * STEPD2_UPDATE(t,s)
- * STEPD1(t) - Perform round t with no load or update.
- *
- * The G5 is more fully out-of-order, and can find the parallelism
- * by itself.  The big limit is that it has a 2-cycle ALU latency, so
- * even though it's 2-way, the code has to be scheduled as if it's
- * 4-way, which can be a limit.  To help it, we try to schedule the
- * read of RA(t) as late as possible so it doesn't stall waiting for
- * the previous round's RE(t-1), and we try to rotate RB(t) as early
- * as possible while reading RC(t) (= RB(t-1)) as late as possible.
- */
-
-/* the initial loads. */
-#define LOADW(s) \
-	lwz	W(s),(s)*4(%r4)
-
-/*
- * Perform a step with F0, and load W(s).  Uses W(s) as a temporary
- * before loading it.
- * This is actually 10 instructions, which is an awkward fit.
- * It can execute grouped as listed, or delayed one instruction.
- * (If delayed two instructions, there is a stall before the start of the
- * second line.)  Thus, two iterations take 7 cycles, 3.5 cycles per round.
- */
-#define STEPD0_LOAD(t,s) \
-add RE(t),RE(t),W(t); andc   %r0,RD(t),RB(t);  and    W(s),RC(t),RB(t); \
-add RE(t),RE(t),%r0;  rotlwi %r0,RA(t),5;      rotlwi RB(t),RB(t),30;   \
-add RE(t),RE(t),W(s); add    %r0,%r0,%r5;      lwz    W(s),(s)*4(%r4);  \
-add RE(t),RE(t),%r0
-
-/*
- * This is likewise awkward, 13 instructions.  However, it can also
- * execute starting with 2 out of 3 possible moduli, so it does 2 rounds
- * in 9 cycles, 4.5 cycles/round.
- */
-#define STEPD0_UPDATE(t,s,loadk...) \
-add RE(t),RE(t),W(t); andc   %r0,RD(t),RB(t); xor    W(s),W((s)-16),W((s)-3); \
-add RE(t),RE(t),%r0;  and    %r0,RC(t),RB(t); xor    W(s),W(s),W((s)-8);      \
-add RE(t),RE(t),%r0;  rotlwi %r0,RA(t),5;     xor    W(s),W(s),W((s)-14);     \
-add RE(t),RE(t),%r5;  loadk; rotlwi RB(t),RB(t),30;  rotlwi W(s),W(s),1;     \
-add RE(t),RE(t),%r0
-
-/* Nicely optimal.  Conveniently, also the most common. */
-#define STEPD1_UPDATE(t,s,loadk...) \
-add RE(t),RE(t),W(t); xor    %r0,RD(t),RB(t); xor    W(s),W((s)-16),W((s)-3); \
-add RE(t),RE(t),%r5;  loadk; xor %r0,%r0,RC(t);  xor W(s),W(s),W((s)-8);      \
-add RE(t),RE(t),%r0;  rotlwi %r0,RA(t),5;     xor    W(s),W(s),W((s)-14);     \
-add RE(t),RE(t),%r0;  rotlwi RB(t),RB(t),30;  rotlwi W(s),W(s),1
-
-/*
- * The naked version, no UPDATE, for the last 4 rounds.  3 cycles per.
- * We could use W(s) as a temp register, but we don't need it.
- */
-#define STEPD1(t) \
-                        add   RE(t),RE(t),W(t); xor    %r0,RD(t),RB(t); \
-rotlwi RB(t),RB(t),30;  add   RE(t),RE(t),%r5;  xor    %r0,%r0,RC(t);   \
-add    RE(t),RE(t),%r0; rotlwi %r0,RA(t),5;     /* spare slot */        \
-add    RE(t),RE(t),%r0
-
-/*
- * 14 instructions, 5 cycles per.  The majority function is a bit
- * awkward to compute.  This can execute with a 1-instruction delay,
- * but it causes a 2-instruction delay, which triggers a stall.
- */
-#define STEPD2_UPDATE(t,s,loadk...) \
-add RE(t),RE(t),W(t); and    %r0,RD(t),RB(t); xor    W(s),W((s)-16),W((s)-3); \
-add RE(t),RE(t),%r0;  xor    %r0,RD(t),RB(t); xor    W(s),W(s),W((s)-8);      \
-add RE(t),RE(t),%r5;  loadk; and %r0,%r0,RC(t);  xor W(s),W(s),W((s)-14);     \
-add RE(t),RE(t),%r0;  rotlwi %r0,RA(t),5;     rotlwi W(s),W(s),1;             \
-add RE(t),RE(t),%r0;  rotlwi RB(t),RB(t),30
-
-#define STEP0_LOAD4(t,s)		\
-	STEPD0_LOAD(t,s);		\
-	STEPD0_LOAD((t+1),(s)+1);	\
-	STEPD0_LOAD((t)+2,(s)+2);	\
-	STEPD0_LOAD((t)+3,(s)+3)
-
-#define STEPUP4(fn, t, s, loadk...)		\
-	STEP##fn##_UPDATE(t,s,);		\
-	STEP##fn##_UPDATE((t)+1,(s)+1,);	\
-	STEP##fn##_UPDATE((t)+2,(s)+2,);	\
-	STEP##fn##_UPDATE((t)+3,(s)+3,loadk)
-
-#define STEPUP20(fn, t, s, loadk...)	\
-	STEPUP4(fn, t, s,);		\
-	STEPUP4(fn, (t)+4, (s)+4,);	\
-	STEPUP4(fn, (t)+8, (s)+8,);	\
-	STEPUP4(fn, (t)+12, (s)+12,);	\
-	STEPUP4(fn, (t)+16, (s)+16, loadk)
-
-	.globl	ppc_sha1_core
-ppc_sha1_core:
-	stwu	%r1,-80(%r1)
-	stmw	%r13,4(%r1)
-
-	/* Load up A - E */
-	lmw	%r27,0(%r3)
-
-	mtctr	%r5
-
-1:
-	LOADW(0)
-	lis	%r5,0x5a82
-	mr	RE(0),%r31
-	LOADW(1)
-	mr	RD(0),%r30
-	mr	RC(0),%r29
-	LOADW(2)
-	ori	%r5,%r5,0x7999	/* K0-19 */
-	mr	RB(0),%r28
-	LOADW(3)
-	mr	RA(0),%r27
-
-	STEP0_LOAD4(0, 4)
-	STEP0_LOAD4(4, 8)
-	STEP0_LOAD4(8, 12)
-	STEPUP4(D0, 12, 16,)
-	STEPUP4(D0, 16, 20, lis %r5,0x6ed9)
-
-	ori	%r5,%r5,0xeba1	/* K20-39 */
-	STEPUP20(D1, 20, 24, lis %r5,0x8f1b)
-
-	ori	%r5,%r5,0xbcdc	/* K40-59 */
-	STEPUP20(D2, 40, 44, lis %r5,0xca62)
-
-	ori	%r5,%r5,0xc1d6	/* K60-79 */
-	STEPUP4(D1, 60, 64,)
-	STEPUP4(D1, 64, 68,)
-	STEPUP4(D1, 68, 72,)
-	STEPUP4(D1, 72, 76,)
-	addi	%r4,%r4,64
-	STEPD1(76)
-	STEPD1(77)
-	STEPD1(78)
-	STEPD1(79)
-
-	/* Add results to original values */
-	add	%r31,%r31,RE(0)
-	add	%r30,%r30,RD(0)
-	add	%r29,%r29,RC(0)
-	add	%r28,%r28,RB(0)
-	add	%r27,%r27,RA(0)
-
-	bdnz	1b
-
-	/* Save final hash, restore registers, and return */
-	stmw	%r27,0(%r3)
-	lmw	%r13,4(%r1)
-	addi	%r1,%r1,80
-	blr