[PATCH v7 22/34] Import integer multiplication from the CM0 library

[Daniel Engel <gnu@danielengel.com>]

gcc/libgcc/ChangeLog:
2022-10-09 Daniel Engel <gnu@danielengel.com>

	* config/arm/eabi/lmul.S: New file for __muldi3(), __mulsidi3(), and
	 __umulsidi3().
	* config/arm/lib1funcs.S: #eabi/lmul.S (v6m only).
	* config/arm/t-elf: Add the new objects to LIB1ASMFUNCS.
---
 libgcc/config/arm/eabi/lmul.S | 218 ++++++++++++++++++++++++++++++++++
 libgcc/config/arm/lib1funcs.S |   1 +
 libgcc/config/arm/t-elf       |  13 +-
 3 files changed, 230 insertions(+), 2 deletions(-)
 create mode 100644 libgcc/config/arm/eabi/lmul.S

diff --git a/libgcc/config/arm/eabi/lmul.S b/libgcc/config/arm/eabi/lmul.S
new file mode 100644
index 00000000000..377e571bf09
--- /dev/null
+++ b/libgcc/config/arm/eabi/lmul.S
@@ -0,0 +1,218 @@
+/* lmul.S: Thumb-1 optimized 64-bit integer multiplication
+
+   Copyright (C) 2018-2022 Free Software Foundation, Inc.
+   Contributed by Daniel Engel, Senva Inc (gnu@danielengel.com)
+
+   This file is free software; you can redistribute it and/or modify it
+   under the terms of the GNU General Public License as published by the
+   Free Software Foundation; either version 3, or (at your option) any
+   later version.
+
+   This file is distributed in the hope that it will be useful, but
+   WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+   General Public License for more details.
+
+   Under Section 7 of GPL version 3, you are granted additional
+   permissions described in the GCC Runtime Library Exception, version
+   3.1, as published by the Free Software Foundation.
+
+   You should have received a copy of the GNU General Public License and
+   a copy of the GCC Runtime Library Exception along with this program;
+   see the files COPYING3 and COPYING.RUNTIME respectively.  If not, see
+   <http://www.gnu.org/licenses/>.  */
+
+
+#ifdef L_muldi3
+
+// long long __aeabi_lmul(long long, long long)
+// Returns the least significant 64 bits of a 64 bit multiplication.
+// Expects the two multiplicands in $r1:$r0 and $r3:$r2.
+// Returns the product in $r1:$r0 (does not distinguish signed types).
+// Uses $r4 and $r5 as scratch space.
+// Same parent section as __umulsidi3() to keep tail call branch within range.
+FUNC_START_SECTION muldi3 .text.sorted.libgcc.lmul.muldi3
+
+#ifndef __symbian__
+  FUNC_ALIAS aeabi_lmul muldi3
+#endif
+
+    CFI_START_FUNCTION
+
+        // $r1:$r0 = 0xDDDDCCCCBBBBAAAA
+        // $r3:$r2 = 0xZZZZYYYYXXXXWWWW
+
+        // The following operations that only affect the upper 64 bits
+        //  can be safely discarded:
+        //   DDDD * ZZZZ
+        //   DDDD * YYYY
+        //   DDDD * XXXX
+        //   CCCC * ZZZZ
+        //   CCCC * YYYY
+        //   BBBB * ZZZZ
+
+        // MAYBE: Test for multiply by ZERO on implementations with a 32-cycle
+        //  'muls' instruction, and skip over the operation in that case.
+
+        // (0xDDDDCCCC * 0xXXXXWWWW), free $r1
+        muls    xxh,    yyl
+
+        // (0xZZZZYYYY * 0xBBBBAAAA), free $r3
+        muls    yyh,    xxl
+        adds    yyh,    xxh
+
+        // Put the parameters in the correct form for umulsidi3().
+        movs    xxh,    yyl
+        b       LLSYM(__mul_overflow)
+
+    CFI_END_FUNCTION
+FUNC_END muldi3
+
+#ifndef __symbian__
+  FUNC_END aeabi_lmul
+#endif
+
+#endif /* L_muldi3 */
+
+
+// The following implementation of __umulsidi3() integrates with __muldi3()
+//  above to allow the fast tail call while still preserving the extra
+//  hi-shifted bits of the result.  However, these extra bits add a few
+//  instructions not otherwise required when using only __umulsidi3().
+// Therefore, this block configures __umulsidi3() for compilation twice.
+// The first version is a minimal standalone implementation, and the second
+//  version adds the hi bits of __muldi3().  The standalone version must
+//  be declared WEAK, so that the combined version can supersede it and
+//  provide both symbols in programs that multiply long doubles.
+// This means '_umulsidi3' should appear before '_muldi3' in LIB1ASMFUNCS.
+#if defined(L_muldi3) || defined(L_umulsidi3)
+
+#ifdef L_umulsidi3
+// unsigned long long __umulsidi3(unsigned int, unsigned int)
+// Returns all 64 bits of a 32 bit multiplication.
+// Expects the two multiplicands in $r0 and $r1.
+// Returns the product in $r1:$r0.
+// Uses $r3, $r4 and $ip as scratch space.
+WEAK_START_SECTION umulsidi3 .text.sorted.libgcc.lmul.umulsidi3
+    CFI_START_FUNCTION
+
+#else /* L_muldi3 */
+FUNC_ENTRY umulsidi3
+    CFI_START_FUNCTION
+
+        // 32x32 multiply with 64 bit result.
+        // Expand the multiply into 4 parts, since muls only returns 32 bits.
+        //         (a16h * b16h / 2^32)
+        //       + (a16h * b16l / 2^48) + (a16l * b16h / 2^48)
+        //       + (a16l * b16l / 2^64)
+
+        // MAYBE: Test for multiply by 0 on implementations with a 32-cycle
+        //  'muls' instruction, and skip over the operation in that case.
+
+        eors    yyh,    yyh
+
+    LLSYM(__mul_overflow):
+        mov     ip,     yyh
+
+#endif /* !L_muldi3 */
+
+        // a16h * b16h
+        lsrs    r2,     xxl,    #16
+        lsrs    r3,     xxh,    #16
+        muls    r2,     r3
+
+      #ifdef L_muldi3
+        add     ip,     r2
+      #else
+        mov     ip,     r2
+      #endif
+
+        // a16l * b16h; save a16h first!
+        lsrs    r2,     xxl,    #16
+    #if (__ARM_ARCH >= 6)
+        uxth    xxl,    xxl
+    #else /* __ARM_ARCH < 6 */
+        lsls    xxl,    #16
+        lsrs    xxl,    #16
+    #endif
+        muls    r3,     xxl
+
+        // a16l * b16l
+    #if (__ARM_ARCH >= 6)
+        uxth    xxh,    xxh
+    #else /* __ARM_ARCH < 6 */
+        lsls    xxh,    #16
+        lsrs    xxh,    #16
+    #endif
+        muls    xxl,    xxh
+
+        // a16h * b16l
+        muls    xxh,    r2
+
+        // Distribute intermediate results.
+        eors    r2,     r2
+        adds    xxh,    r3
+        adcs    r2,     r2
+        lsls    r3,     xxh,    #16
+        lsrs    xxh,    #16
+        lsls    r2,     #16
+        adds    xxl,    r3
+        adcs    xxh,    r2
+
+        // Add in the high bits.
+        add     xxh,     ip
+
+        RET
+
+    CFI_END_FUNCTION
+FUNC_END umulsidi3
+
+#endif /* L_muldi3 || L_umulsidi3 */
+
+
+#ifdef L_mulsidi3
+
+// long long mulsidi3(int, int)
+// Returns all 64 bits of a 32 bit signed multiplication.
+// Expects the two multiplicands in $r0 and $r1.
+// Returns the product in $r1:$r0.
+// Uses $r3, $r4 and $rT as scratch space.
+FUNC_START_SECTION mulsidi3 .text.sorted.libgcc.lmul.mulsidi3
+    CFI_START_FUNCTION
+
+        // Push registers for function call.
+        push    { rT, lr }
+                .cfi_remember_state
+                .cfi_adjust_cfa_offset 8
+                .cfi_rel_offset rT, 0
+                .cfi_rel_offset lr, 4
+
+        // Save signs of the arguments.
+        asrs    r3,     r0,     #31
+        asrs    rT,     r1,     #31
+
+        // Absolute value of the arguments.
+        eors    r0,     r3
+        eors    r1,     rT
+        subs    r0,     r3
+        subs    r1,     rT
+
+        // Save sign of the result.
+        eors    rT,     r3
+
+        bl      SYM(__umulsidi3) __PLT__
+
+        // Apply sign of the result.
+        eors    xxl,     rT
+        eors    xxh,     rT
+        subs    xxl,     rT
+        sbcs    xxh,     rT
+
+        pop     { rT, pc }
+                .cfi_restore_state
+
+    CFI_END_FUNCTION
+FUNC_END mulsidi3
+
+#endif /* L_mulsidi3 */
+
diff --git a/libgcc/config/arm/lib1funcs.S b/libgcc/config/arm/lib1funcs.S
index 51fb32e38aa..e828d53d732 100644
--- a/libgcc/config/arm/lib1funcs.S
+++ b/libgcc/config/arm/lib1funcs.S
@@ -1578,6 +1578,7 @@ LSYM(Lover12):
 #define PEDANTIC_DIV0 (1)
 #include "eabi/idiv.S"
 #include "eabi/ldiv.S"
+#include "eabi/lmul.S"
 #endif /* NOT_ISA_TARGET_32BIT */
 
 /* ------------------------------------------------------------------------ */
diff --git a/libgcc/config/arm/t-elf b/libgcc/config/arm/t-elf
index 4d430325fa1..eb1acd8d5a2 100644
--- a/libgcc/config/arm/t-elf
+++ b/libgcc/config/arm/t-elf
@@ -27,6 +27,13 @@ LIB1ASMFUNCS += \
 	_paritysi2 \
 	_popcountsi2 \
 
+ifeq (__ARM_ARCH_ISA_THUMB 1,$(ARM_ISA)$(THUMB1_ISA))
+# Group 0B: WEAK overridable function objects built for v6m only.
+LIB1ASMFUNCS += \
+	_muldi3 \
+	
+endif
+
 
 # Group 1: Integer function objects.
 LIB1ASMFUNCS += \
@@ -51,11 +58,13 @@ LIB1ASMFUNCS += \
 
 
 ifeq (__ARM_ARCH_ISA_THUMB 1,$(ARM_ISA)$(THUMB1_ISA))
-# Group 1B: Integer functions built for v6m only.
+# Group 1B: Integer function objects built for v6m only.
 LIB1ASMFUNCS += \
 	_divdi3 \
 	_udivdi3 \
-
+	_mulsidi3 \
+	_umulsidi3 \
+	
 endif
 
 
-- 
2.34.1