MIPS: Fix build with binutils 2.24.51+

Starting with version 2.24.51.20140728 MIPS binutils complain loudly
about mixing soft-float and hard-float object files, leading to this
build failure since GCC is invoked with "-msoft-float" on MIPS:

{standard input}: Warning: .gnu_attribute 4,3 requires `softfloat'
  LD      arch/mips/alchemy/common/built-in.o
mipsel-softfloat-linux-gnu-ld: Warning: arch/mips/alchemy/common/built-in.o
 uses -msoft-float (set by arch/mips/alchemy/common/prom.o),
 arch/mips/alchemy/common/sleeper.o uses -mhard-float

To fix this, we detect if GAS is new enough to support "-msoft-float" command
option, and if it does, we can let GCC pass it to GAS;  but then we also need
to sprinkle the files which make use of floating point registers with the
necessary ".set hardfloat" directives.

Signed-off-by: Manuel Lauss <manuel.lauss@gmail.com>
Cc: Linux-MIPS <linux-mips@linux-mips.org>
Cc: Matthew Fortune <Matthew.Fortune@imgtec.com>
Cc: Markos Chandras <Markos.Chandras@imgtec.com>
Cc: Maciej W. Rozycki <macro@linux-mips.org>
Patchwork: https://patchwork.linux-mips.org/patch/8355/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>

14 files changed, 118 insertions, 17 deletions

diff --git a/arch/mips/Makefile b/arch/mips/Makefile
index 23cb94806fb..58076472bdd 100644
--- a/arch/mips/Makefile
+++ b/arch/mips/Makefile
@@ -93,6 +93,15 @@ LDFLAGS_vmlinux			+= -G 0 -static -n -nostdlib
 KBUILD_AFLAGS_MODULE		+= -mlong-calls
 KBUILD_CFLAGS_MODULE		+= -mlong-calls
 
+#
+# pass -msoft-float to GAS if it supports it.  However on newer binutils
+# (specifically newer than 2.24.51.20140728) we then also need to explicitly
+# set ".set hardfloat" in all files which manipulate floating point registers.
+#
+ifneq ($(call as-option,-Wa$(comma)-msoft-float,),)
+	cflags-y		+= -DGAS_HAS_SET_HARDFLOAT -Wa,-msoft-float
+endif
+
 cflags-y += -ffreestanding
 
 #
diff --git a/arch/mips/include/asm/asmmacro-32.h b/arch/mips/include/asm/asmmacro-32.h
index e38c2811d4e..cdac7b3eeaf 100644
--- a/arch/mips/include/asm/asmmacro-32.h
+++ b/arch/mips/include/asm/asmmacro-32.h
@@ -13,6 +13,8 @@
 #include <asm/mipsregs.h>
 
 	.macro	fpu_save_single thread tmp=t0
+	.set push
+	SET_HARDFLOAT
 	cfc1	\tmp,  fcr31
 	swc1	$f0,  THREAD_FPR0_LS64(\thread)
 	swc1	$f1,  THREAD_FPR1_LS64(\thread)
@@ -47,9 +49,12 @@
 	swc1	$f30, THREAD_FPR30_LS64(\thread)
 	swc1	$f31, THREAD_FPR31_LS64(\thread)
 	sw	\tmp, THREAD_FCR31(\thread)
+	.set pop
 	.endm
 
 	.macro	fpu_restore_single thread tmp=t0
+	.set push
+	SET_HARDFLOAT
 	lw	\tmp, THREAD_FCR31(\thread)
 	lwc1	$f0,  THREAD_FPR0_LS64(\thread)
 	lwc1	$f1,  THREAD_FPR1_LS64(\thread)
@@ -84,6 +89,7 @@
 	lwc1	$f30, THREAD_FPR30_LS64(\thread)
 	lwc1	$f31, THREAD_FPR31_LS64(\thread)
 	ctc1	\tmp, fcr31
+	.set pop
 	.endm
 
 	.macro	cpu_save_nonscratch thread
diff --git a/arch/mips/include/asm/asmmacro.h b/arch/mips/include/asm/asmmacro.h
index cd9a98bc8f6..6caf8766b80 100644
--- a/arch/mips/include/asm/asmmacro.h
+++ b/arch/mips/include/asm/asmmacro.h
@@ -57,6 +57,8 @@
 #endif /* CONFIG_CPU_MIPSR2 */
 
 	.macro	fpu_save_16even thread tmp=t0
+	.set	push
+	SET_HARDFLOAT
 	cfc1	\tmp, fcr31
 	sdc1	$f0,  THREAD_FPR0_LS64(\thread)
 	sdc1	$f2,  THREAD_FPR2_LS64(\thread)
@@ -75,11 +77,13 @@
 	sdc1	$f28, THREAD_FPR28_LS64(\thread)
 	sdc1	$f30, THREAD_FPR30_LS64(\thread)
 	sw	\tmp, THREAD_FCR31(\thread)
+	.set	pop
 	.endm
 
 	.macro	fpu_save_16odd thread
 	.set	push
 	.set	mips64r2
+	SET_HARDFLOAT
 	sdc1	$f1,  THREAD_FPR1_LS64(\thread)
 	sdc1	$f3,  THREAD_FPR3_LS64(\thread)
 	sdc1	$f5,  THREAD_FPR5_LS64(\thread)
@@ -110,6 +114,8 @@
 	.endm
 
 	.macro	fpu_restore_16even thread tmp=t0
+	.set	push
+	SET_HARDFLOAT
 	lw	\tmp, THREAD_FCR31(\thread)
 	ldc1	$f0,  THREAD_FPR0_LS64(\thread)
 	ldc1	$f2,  THREAD_FPR2_LS64(\thread)
@@ -133,6 +139,7 @@
 	.macro	fpu_restore_16odd thread
 	.set	push
 	.set	mips64r2
+	SET_HARDFLOAT
 	ldc1	$f1,  THREAD_FPR1_LS64(\thread)
 	ldc1	$f3,  THREAD_FPR3_LS64(\thread)
 	ldc1	$f5,  THREAD_FPR5_LS64(\thread)
@@ -277,6 +284,7 @@
 	.macro	cfcmsa	rd, cs
 	.set	push
 	.set	noat
+	SET_HARDFLOAT
 	.insn
 	.word	CFC_MSA_INSN | (\cs << 11)
 	move	\rd, $1
@@ -286,6 +294,7 @@
 	.macro	ctcmsa	cd, rs
 	.set	push
 	.set	noat
+	SET_HARDFLOAT
 	move	$1, \rs
 	.word	CTC_MSA_INSN | (\cd << 6)
 	.set	pop
@@ -294,6 +303,7 @@
 	.macro	ld_d	wd, off, base
 	.set	push
 	.set	noat
+	SET_HARDFLOAT
 	add	$1, \base, \off
 	.word	LDD_MSA_INSN | (\wd << 6)
 	.set	pop
@@ -302,6 +312,7 @@
 	.macro	st_d	wd, off, base
 	.set	push
 	.set	noat
+	SET_HARDFLOAT
 	add	$1, \base, \off
 	.word	STD_MSA_INSN | (\wd << 6)
 	.set	pop
@@ -310,6 +321,7 @@
 	.macro	copy_u_w	rd, ws, n
 	.set	push
 	.set	noat
+	SET_HARDFLOAT
 	.insn
 	.word	COPY_UW_MSA_INSN | (\n << 16) | (\ws << 11)
 	/* move triggers an assembler bug... */
@@ -320,6 +332,7 @@
 	.macro	copy_u_d	rd, ws, n
 	.set	push
 	.set	noat
+	SET_HARDFLOAT
 	.insn
 	.word	COPY_UD_MSA_INSN | (\n << 16) | (\ws << 11)
 	/* move triggers an assembler bug... */
@@ -330,6 +343,7 @@
 	.macro	insert_w	wd, n, rs
 	.set	push
 	.set	noat
+	SET_HARDFLOAT
 	/* move triggers an assembler bug... */
 	or	$1, \rs, zero
 	.word	INSERT_W_MSA_INSN | (\n << 16) | (\wd << 6)
@@ -339,6 +353,7 @@
 	.macro	insert_d	wd, n, rs
 	.set	push
 	.set	noat
+	SET_HARDFLOAT
 	/* move triggers an assembler bug... */
 	or	$1, \rs, zero
 	.word	INSERT_D_MSA_INSN | (\n << 16) | (\wd << 6)
@@ -381,6 +396,7 @@
 	st_d	31, THREAD_FPR31, \thread
 	.set	push
 	.set	noat
+	SET_HARDFLOAT
 	cfcmsa	$1, MSA_CSR
 	sw	$1, THREAD_MSA_CSR(\thread)
 	.set	pop
@@ -389,6 +405,7 @@
 	.macro	msa_restore_all	thread
 	.set	push
 	.set	noat
+	SET_HARDFLOAT
 	lw	$1, THREAD_MSA_CSR(\thread)
 	ctcmsa	MSA_CSR, $1
 	.set	pop
@@ -441,6 +458,7 @@
 	.macro	msa_init_all_upper
 	.set	push
 	.set	noat
+	SET_HARDFLOAT
 	not	$1, zero
 	msa_init_upper	0
 	.set	pop
diff --git a/arch/mips/include/asm/fpregdef.h b/arch/mips/include/asm/fpregdef.h
index 429481f9028..f184ba08853 100644
--- a/arch/mips/include/asm/fpregdef.h
+++ b/arch/mips/include/asm/fpregdef.h
@@ -14,6 +14,20 @@
 
 #include <asm/sgidefs.h>
 
+/*
+ * starting with binutils 2.24.51.20140729, MIPS binutils warn about mixing
+ * hardfloat and softfloat object files.  The kernel build uses soft-float by
+ * default, so we also need to pass -msoft-float along to GAS if it supports it.
+ * But this in turn causes assembler errors in files which access hardfloat
+ * registers.  We detect if GAS supports "-msoft-float" in the Makefile and
+ * explicitly put ".set hardfloat" where floating point registers are touched.
+ */
+#ifdef GAS_HAS_SET_HARDFLOAT
+#define SET_HARDFLOAT .set hardfloat
+#else
+#define SET_HARDFLOAT
+#endif
+
 #if _MIPS_SIM == _MIPS_SIM_ABI32
 
 /*
diff --git a/arch/mips/include/asm/fpu.h b/arch/mips/include/asm/fpu.h
index 4d0aeda6839..dd562414cd5 100644
--- a/arch/mips/include/asm/fpu.h
+++ b/arch/mips/include/asm/fpu.h
@@ -145,8 +145,8 @@ static inline void lose_fpu(int save)
 	if (is_msa_enabled()) {
 		if (save) {
 			save_msa(current);
-			asm volatile("cfc1 %0, $31"
-				: "=r"(current->thread.fpu.fcr31));
+			current->thread.fpu.fcr31 =
+					read_32bit_cp1_register(CP1_STATUS);
 		}
 		disable_msa();
 		clear_thread_flag(TIF_USEDMSA);
diff --git a/arch/mips/include/asm/mipsregs.h b/arch/mips/include/asm/mipsregs.h
index cf3b580c3df..b46cd220a01 100644
--- a/arch/mips/include/asm/mipsregs.h
+++ b/arch/mips/include/asm/mipsregs.h
@@ -1324,7 +1324,7 @@ do {									\
 /*
  * Macros to access the floating point coprocessor control registers
  */
-#define read_32bit_cp1_register(source)					\
+#define _read_32bit_cp1_register(source, gas_hardfloat)			\
 ({									\
 	int __res;							\
 									\
@@ -1334,12 +1334,21 @@ do {									\
 	"	# gas fails to assemble cfc1 for some archs,	\n"	\
 	"	# like Octeon.					\n"	\
 	"	.set	mips1					\n"	\
+	"	"STR(gas_hardfloat)"				\n"	\
 	"	cfc1	%0,"STR(source)"			\n"	\
 	"	.set	pop					\n"	\
 	: "=r" (__res));						\
 	__res;								\
 })
 
+#ifdef GAS_HAS_SET_HARDFLOAT
+#define read_32bit_cp1_register(source)					\
+	_read_32bit_cp1_register(source, .set hardfloat)
+#else
+#define read_32bit_cp1_register(source)					\
+	_read_32bit_cp1_register(source, )
+#endif
+
 #ifdef HAVE_AS_DSP
 #define rddsp(mask)							\
 ({									\
diff --git a/arch/mips/kernel/branch.c b/arch/mips/kernel/branch.c
index 7b2df224f04..4d7d99d601c 100644
--- a/arch/mips/kernel/branch.c
+++ b/arch/mips/kernel/branch.c
@@ -144,7 +144,7 @@ int __mm_isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn,
 		case mm_bc1t_op:
 			preempt_disable();
 			if (is_fpu_owner())
-				asm volatile("cfc1\t%0,$31" : "=r" (fcr31));
+			        fcr31 = read_32bit_cp1_register(CP1_STATUS);
 			else
 				fcr31 = current->thread.fpu.fcr31;
 			preempt_enable();
@@ -562,11 +562,7 @@ int __compute_return_epc_for_insn(struct pt_regs *regs,
 	case cop1_op:
 		preempt_disable();
 		if (is_fpu_owner())
-			asm volatile(
-				".set push\n"
-				"\t.set mips1\n"
-				"\tcfc1\t%0,$31\n"
-				"\t.set pop" : "=r" (fcr31));
+		        fcr31 = read_32bit_cp1_register(CP1_STATUS);
 		else
 			fcr31 = current->thread.fpu.fcr31;
 		preempt_enable();
diff --git a/arch/mips/kernel/genex.S b/arch/mips/kernel/genex.S
index ac35e12cb1f..a5e26dd9059 100644
--- a/arch/mips/kernel/genex.S
+++ b/arch/mips/kernel/genex.S
@@ -358,6 +358,7 @@ NESTED(nmi_handler, PT_SIZE, sp)
 	.set	push
 	/* gas fails to assemble cfc1 for some archs (octeon).*/ \
 	.set	mips1
+	SET_HARDFLOAT
 	cfc1	a1, fcr31
 	li	a2, ~(0x3f << 12)
 	and	a2, a1
diff --git a/arch/mips/kernel/r2300_fpu.S b/arch/mips/kernel/r2300_fpu.S
index f31063dbdae..5ce3b746ced 100644
--- a/arch/mips/kernel/r2300_fpu.S
+++ b/arch/mips/kernel/r2300_fpu.S
@@ -28,6 +28,8 @@
 	.set	mips1
 	/* Save floating point context */
 LEAF(_save_fp_context)
+	.set	push
+	SET_HARDFLOAT
 	li	v0, 0					# assume success
 	cfc1	t1,fcr31
 	EX(swc1 $f0,(SC_FPREGS+0)(a0))
@@ -65,6 +67,7 @@ LEAF(_save_fp_context)
 	EX(sw	t1,(SC_FPC_CSR)(a0))
 	cfc1	t0,$0				# implementation/version
 	jr	ra
+	.set	pop
 	.set	nomacro
 	 EX(sw	t0,(SC_FPC_EIR)(a0))
 	.set	macro
@@ -80,6 +83,8 @@ LEAF(_save_fp_context)
  * stack frame which might have been changed by the user.
  */
 LEAF(_restore_fp_context)
+	.set	push
+	SET_HARDFLOAT
 	li	v0, 0					# assume success
 	EX(lw t0,(SC_FPC_CSR)(a0))
 	EX(lwc1 $f0,(SC_FPREGS+0)(a0))
@@ -116,6 +121,7 @@ LEAF(_restore_fp_context)
 	EX(lwc1 $f31,(SC_FPREGS+248)(a0))
 	jr	ra
 	 ctc1	t0,fcr31
+	.set	pop
 	END(_restore_fp_context)
 	.set	reorder
 
diff --git a/arch/mips/kernel/r2300_switch.S b/arch/mips/kernel/r2300_switch.S
index 20b7b040e76..435ea652f5f 100644
--- a/arch/mips/kernel/r2300_switch.S
+++ b/arch/mips/kernel/r2300_switch.S
@@ -120,6 +120,9 @@ LEAF(_restore_fp)
 
 #define FPU_DEFAULT  0x00000000
 
+	.set push
+	SET_HARDFLOAT
+
 LEAF(_init_fpu)
 	mfc0	t0, CP0_STATUS
 	li	t1, ST0_CU1
@@ -165,3 +168,5 @@ LEAF(_init_fpu)
 	mtc1	t0, $f31
 	jr	ra
 	END(_init_fpu)
+
+	.set pop
diff --git a/arch/mips/kernel/r4k_fpu.S b/arch/mips/kernel/r4k_fpu.S
index 8352523568e..6c160c67984 100644
--- a/arch/mips/kernel/r4k_fpu.S
+++ b/arch/mips/kernel/r4k_fpu.S
@@ -19,8 +19,12 @@
 #include <asm/asm-offsets.h>
 #include <asm/regdef.h>
 
+/* preprocessor replaces the fp in ".set fp=64" with $30 otherwise */
+#undef fp
+
 	.macro	EX insn, reg, src
 	.set	push
+	SET_HARDFLOAT
 	.set	nomacro
 .ex\@:	\insn	\reg, \src
 	.set	pop
@@ -33,12 +37,17 @@
 	.set	arch=r4000
 
 LEAF(_save_fp_context)
+	.set	push
+	SET_HARDFLOAT
 	cfc1	t1, fcr31
+	.set	pop
 
 #if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPS32_R2)
 	.set	push
+	SET_HARDFLOAT
 #ifdef CONFIG_CPU_MIPS32_R2
-	.set	mips64r2
+	.set	mips32r2
+	.set	fp=64
 	mfc0	t0, CP0_STATUS
 	sll	t0, t0, 5
 	bgez	t0, 1f			# skip storing odd if FR=0
@@ -64,6 +73,8 @@ LEAF(_save_fp_context)
 1:	.set	pop
 #endif
 
+	.set push
+	SET_HARDFLOAT
 	/* Store the 16 even double precision registers */
 	EX	sdc1 $f0, SC_FPREGS+0(a0)
 	EX	sdc1 $f2, SC_FPREGS+16(a0)
@@ -84,11 +95,14 @@ LEAF(_save_fp_context)
 	EX	sw t1, SC_FPC_CSR(a0)
 	jr	ra
 	 li	v0, 0					# success
+	.set pop
 	END(_save_fp_context)
 
 #ifdef CONFIG_MIPS32_COMPAT
 	/* Save 32-bit process floating point context */
 LEAF(_save_fp_context32)
+	.set push
+	SET_HARDFLOAT
 	cfc1	t1, fcr31
 
 	mfc0	t0, CP0_STATUS
@@ -134,6 +148,7 @@ LEAF(_save_fp_context32)
 	EX	sw t1, SC32_FPC_CSR(a0)
 	cfc1	t0, $0				# implementation/version
 	EX	sw t0, SC32_FPC_EIR(a0)
+	.set pop
 
 	jr	ra
 	 li	v0, 0					# success
@@ -150,8 +165,10 @@ LEAF(_restore_fp_context)
 
 #if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPS32_R2)
 	.set	push
+	SET_HARDFLOAT
 #ifdef CONFIG_CPU_MIPS32_R2
-	.set	mips64r2
+	.set	mips32r2
+	.set	fp=64
 	mfc0	t0, CP0_STATUS
 	sll	t0, t0, 5
 	bgez	t0, 1f			# skip loading odd if FR=0
@@ -175,6 +192,8 @@ LEAF(_restore_fp_context)
 	EX	ldc1 $f31, SC_FPREGS+248(a0)
 1:	.set pop
 #endif
+	.set push
+	SET_HARDFLOAT
 	EX	ldc1 $f0, SC_FPREGS+0(a0)
 	EX	ldc1 $f2, SC_FPREGS+16(a0)
 	EX	ldc1 $f4, SC_FPREGS+32(a0)
@@ -192,6 +211,7 @@ LEAF(_restore_fp_context)
 	EX	ldc1 $f28, SC_FPREGS+224(a0)
 	EX	ldc1 $f30, SC_FPREGS+240(a0)
 	ctc1	t1, fcr31
+	.set pop
 	jr	ra
 	 li	v0, 0					# success
 	END(_restore_fp_context)
@@ -199,6 +219,8 @@ LEAF(_restore_fp_context)
 #ifdef CONFIG_MIPS32_COMPAT
 LEAF(_restore_fp_context32)
 	/* Restore an o32 sigcontext.  */
+	.set push
+	SET_HARDFLOAT
 	EX	lw t1, SC32_FPC_CSR(a0)
 
 	mfc0	t0, CP0_STATUS
@@ -242,6 +264,7 @@ LEAF(_restore_fp_context32)
 	ctc1	t1, fcr31
 	jr	ra
 	 li	v0, 0					# success
+	.set pop
 	END(_restore_fp_context32)
 #endif
 
diff --git a/arch/mips/kernel/r4k_switch.S b/arch/mips/kernel/r4k_switch.S
index 4c4ec181242..64591e67187 100644
--- a/arch/mips/kernel/r4k_switch.S
+++ b/arch/mips/kernel/r4k_switch.S
@@ -22,6 +22,9 @@
 
 #include <asm/asmmacro.h>
 
+/* preprocessor replaces the fp in ".set fp=64" with $30 otherwise */
+#undef fp
+
 /*
  * Offset to the current process status flags, the first 32 bytes of the
  * stack are not used.
@@ -65,8 +68,12 @@
 	bgtz	a3, 1f
 
 	/* Save 128b MSA vector context + scalar FP control & status. */
+	.set push
+	SET_HARDFLOAT
 	cfc1	t1, fcr31
 	msa_save_all	a0
+	.set pop	/* SET_HARDFLOAT */
+
 	sw	t1, THREAD_FCR31(a0)
 	b	2f
 
@@ -161,6 +168,9 @@ LEAF(_init_msa_upper)
 
 #define FPU_DEFAULT  0x00000000
 
+	.set push
+	SET_HARDFLOAT
+
 LEAF(_init_fpu)
 	mfc0	t0, CP0_STATUS
 	li	t1, ST0_CU1
@@ -232,7 +242,8 @@ LEAF(_init_fpu)
 
 #ifdef CONFIG_CPU_MIPS32_R2
 	.set    push
-	.set    mips64r2
+	.set    mips32r2
+	.set	fp=64
 	sll     t0, t0, 5			# is Status.FR set?
 	bgez    t0, 1f				# no: skip setting upper 32b
 
@@ -291,3 +302,5 @@ LEAF(_init_fpu)
 #endif
 	jr	ra
 	END(_init_fpu)
+
+	.set pop	/* SET_HARDFLOAT */
diff --git a/arch/mips/kernel/r6000_fpu.S b/arch/mips/kernel/r6000_fpu.S
index da0fbe46d83..47077380c15 100644
--- a/arch/mips/kernel/r6000_fpu.S
+++ b/arch/mips/kernel/r6000_fpu.S
@@ -18,6 +18,9 @@
 
 	.set	noreorder
 	.set	mips2
+	.set	push
+	SET_HARDFLOAT
+
 	/* Save floating point context */
 	LEAF(_save_fp_context)
 	mfc0	t0,CP0_STATUS
@@ -85,3 +88,5 @@
 1:	jr	ra
 	 nop
 	END(_restore_fp_context)
+
+	.set pop	/* SET_HARDFLOAT */
diff --git a/arch/mips/math-emu/cp1emu.c b/arch/mips/math-emu/cp1emu.c
index 51a0fde4bec..cac529a405b 100644
--- a/arch/mips/math-emu/cp1emu.c
+++ b/arch/mips/math-emu/cp1emu.c
@@ -584,11 +584,7 @@ static int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn,
 		if (insn.i_format.rs == bc_op) {
 			preempt_disable();
 			if (is_fpu_owner())
-				asm volatile(
-					".set push\n"
-					"\t.set mips1\n"
-					"\tcfc1\t%0,$31\n"
-					"\t.set pop" : "=r" (fcr31));
+			        fcr31 = read_32bit_cp1_register(CP1_STATUS);
 			else
 				fcr31 = current->thread.fpu.fcr31;
 			preempt_enable();