MIPS: Support for 64-bit FP with O32 binaries

CPUs implementing MIPS32 R2 may include a 64-bit FPU, just as MIPS64 CPUs
do. In order to preserve backwards compatibility a 64-bit FPU will act
like a 32-bit FPU (by accessing doubles from the least significant 32
bits of an even-odd pair of FP registers) when the Status.FR bit is
zero, again just like a mips64 CPU. The standard O32 ABI is defined
expecting a 32-bit FPU, however recent toolchains support use of a
64-bit FPU from an O32 MIPS32 executable. When an ELF executable is
built to use a 64-bit FPU a new flag (EF_MIPS_FP64) is set in the ELF
header.

With this patch the kernel will check the EF_MIPS_FP64 flag when
executing an O32 binary, and set Status.FR accordingly. The addition
of O32 64-bit FP support lessens the opportunity for optimisation in
the FPU emulator, so a CONFIG_MIPS_O32_FP64_SUPPORT Kconfig option is
introduced to allow this support to be disabled for those that don't
require it.

Inspired by an earlier patch by Leonid Yegoshin, but implemented more
cleanly & correctly.

Signed-off-by: Paul Burton <[email protected]>
Cc: [email protected]
Cc: Paul Burton <[email protected]>
Patchwork: https://patchwork.linux-mips.org/patch/6154/
Signed-off-by: Ralf Baechle <[email protected]>

Author: paulburton

arch/mips/Kconfig

@@ -2335,6 +2335,23 @@ config CC_STACKPROTECTOR
 
 	  This feature requires gcc version 4.2 or above.
 
+config MIPS_O32_FP64_SUPPORT
+	bool "Support for O32 binaries using 64-bit FP"
+	depends on 32BIT || MIPS32_O32
+	default y
+	help
+	  When this is enabled, the kernel will support use of 64-bit floating
+	  point registers with binaries using the O32 ABI along with the
+	  EF_MIPS_FP64 ELF header flag (typically built with -mfp64). On
+	  32-bit MIPS systems this support is at the cost of increasing the
+	  size and complexity of the compiled FPU emulator. Thus if you are
+	  running a MIPS32 system and know that none of your userland binaries
+	  will require 64-bit floating point, you may wish to reduce the size
+	  of your kernel & potentially improve FP emulation performance by
+	  saying N here.
+
+	  If unsure, say Y.
+
 config USE_OF
 	bool
 	select OF

arch/mips/include/asm/asmmacro-32.h

@@ -12,27 +12,6 @@
 #include <asm/fpregdef.h>
 #include <asm/mipsregs.h>
 
-	.macro	fpu_save_double thread status tmp1=t0
-	cfc1	\tmp1,  fcr31
-	sdc1	$f0,  THREAD_FPR0(\thread)
-	sdc1	$f2,  THREAD_FPR2(\thread)
-	sdc1	$f4,  THREAD_FPR4(\thread)
-	sdc1	$f6,  THREAD_FPR6(\thread)
-	sdc1	$f8,  THREAD_FPR8(\thread)
-	sdc1	$f10, THREAD_FPR10(\thread)
-	sdc1	$f12, THREAD_FPR12(\thread)
-	sdc1	$f14, THREAD_FPR14(\thread)
-	sdc1	$f16, THREAD_FPR16(\thread)
-	sdc1	$f18, THREAD_FPR18(\thread)
-	sdc1	$f20, THREAD_FPR20(\thread)
-	sdc1	$f22, THREAD_FPR22(\thread)
-	sdc1	$f24, THREAD_FPR24(\thread)
-	sdc1	$f26, THREAD_FPR26(\thread)
-	sdc1	$f28, THREAD_FPR28(\thread)
-	sdc1	$f30, THREAD_FPR30(\thread)
-	sw	\tmp1, THREAD_FCR31(\thread)
-	.endm
-
 	.macro	fpu_save_single thread tmp=t0
 	cfc1	\tmp,  fcr31
 	swc1	$f0,  THREAD_FPR0(\thread)
@@ -70,27 +49,6 @@
 	sw	\tmp, THREAD_FCR31(\thread)
 	.endm
 
-	.macro	fpu_restore_double thread status tmp=t0
-	lw	\tmp, THREAD_FCR31(\thread)
-	ldc1	$f0,  THREAD_FPR0(\thread)
-	ldc1	$f2,  THREAD_FPR2(\thread)
-	ldc1	$f4,  THREAD_FPR4(\thread)
-	ldc1	$f6,  THREAD_FPR6(\thread)
-	ldc1	$f8,  THREAD_FPR8(\thread)
-	ldc1	$f10, THREAD_FPR10(\thread)
-	ldc1	$f12, THREAD_FPR12(\thread)
-	ldc1	$f14, THREAD_FPR14(\thread)
-	ldc1	$f16, THREAD_FPR16(\thread)
-	ldc1	$f18, THREAD_FPR18(\thread)
-	ldc1	$f20, THREAD_FPR20(\thread)
-	ldc1	$f22, THREAD_FPR22(\thread)
-	ldc1	$f24, THREAD_FPR24(\thread)
-	ldc1	$f26, THREAD_FPR26(\thread)
-	ldc1	$f28, THREAD_FPR28(\thread)
-	ldc1	$f30, THREAD_FPR30(\thread)
-	ctc1	\tmp, fcr31
-	.endm
-
 	.macro	fpu_restore_single thread tmp=t0
 	lw	\tmp, THREAD_FCR31(\thread)
 	lwc1	$f0,  THREAD_FPR0(\thread)

arch/mips/include/asm/asmmacro-64.h

@@ -13,102 +13,6 @@
 #include <asm/fpregdef.h>
 #include <asm/mipsregs.h>
 
-	.macro	fpu_save_16even thread tmp=t0
-	cfc1	\tmp, fcr31
-	sdc1	$f0,  THREAD_FPR0(\thread)
-	sdc1	$f2,  THREAD_FPR2(\thread)
-	sdc1	$f4,  THREAD_FPR4(\thread)
-	sdc1	$f6,  THREAD_FPR6(\thread)
-	sdc1	$f8,  THREAD_FPR8(\thread)
-	sdc1	$f10, THREAD_FPR10(\thread)
-	sdc1	$f12, THREAD_FPR12(\thread)
-	sdc1	$f14, THREAD_FPR14(\thread)
-	sdc1	$f16, THREAD_FPR16(\thread)
-	sdc1	$f18, THREAD_FPR18(\thread)
-	sdc1	$f20, THREAD_FPR20(\thread)
-	sdc1	$f22, THREAD_FPR22(\thread)
-	sdc1	$f24, THREAD_FPR24(\thread)
-	sdc1	$f26, THREAD_FPR26(\thread)
-	sdc1	$f28, THREAD_FPR28(\thread)
-	sdc1	$f30, THREAD_FPR30(\thread)
-	sw	\tmp, THREAD_FCR31(\thread)
-	.endm
-
-	.macro	fpu_save_16odd thread
-	sdc1	$f1,  THREAD_FPR1(\thread)
-	sdc1	$f3,  THREAD_FPR3(\thread)
-	sdc1	$f5,  THREAD_FPR5(\thread)
-	sdc1	$f7,  THREAD_FPR7(\thread)
-	sdc1	$f9,  THREAD_FPR9(\thread)
-	sdc1	$f11, THREAD_FPR11(\thread)
-	sdc1	$f13, THREAD_FPR13(\thread)
-	sdc1	$f15, THREAD_FPR15(\thread)
-	sdc1	$f17, THREAD_FPR17(\thread)
-	sdc1	$f19, THREAD_FPR19(\thread)
-	sdc1	$f21, THREAD_FPR21(\thread)
-	sdc1	$f23, THREAD_FPR23(\thread)
-	sdc1	$f25, THREAD_FPR25(\thread)
-	sdc1	$f27, THREAD_FPR27(\thread)
-	sdc1	$f29, THREAD_FPR29(\thread)
-	sdc1	$f31, THREAD_FPR31(\thread)
-	.endm
-
-	.macro	fpu_save_double thread status tmp
-	sll	\tmp, \status, 5
-	bgez	\tmp, 2f
-	fpu_save_16odd \thread
-2:
-	fpu_save_16even \thread \tmp
-	.endm
-
-	.macro	fpu_restore_16even thread tmp=t0
-	lw	\tmp, THREAD_FCR31(\thread)
-	ldc1	$f0,  THREAD_FPR0(\thread)
-	ldc1	$f2,  THREAD_FPR2(\thread)
-	ldc1	$f4,  THREAD_FPR4(\thread)
-	ldc1	$f6,  THREAD_FPR6(\thread)
-	ldc1	$f8,  THREAD_FPR8(\thread)
-	ldc1	$f10, THREAD_FPR10(\thread)
-	ldc1	$f12, THREAD_FPR12(\thread)
-	ldc1	$f14, THREAD_FPR14(\thread)
-	ldc1	$f16, THREAD_FPR16(\thread)
-	ldc1	$f18, THREAD_FPR18(\thread)
-	ldc1	$f20, THREAD_FPR20(\thread)
-	ldc1	$f22, THREAD_FPR22(\thread)
-	ldc1	$f24, THREAD_FPR24(\thread)
-	ldc1	$f26, THREAD_FPR26(\thread)
-	ldc1	$f28, THREAD_FPR28(\thread)
-	ldc1	$f30, THREAD_FPR30(\thread)
-	ctc1	\tmp, fcr31
-	.endm
-
-	.macro	fpu_restore_16odd thread
-	ldc1	$f1,  THREAD_FPR1(\thread)
-	ldc1	$f3,  THREAD_FPR3(\thread)
-	ldc1	$f5,  THREAD_FPR5(\thread)
-	ldc1	$f7,  THREAD_FPR7(\thread)
-	ldc1	$f9,  THREAD_FPR9(\thread)
-	ldc1	$f11, THREAD_FPR11(\thread)
-	ldc1	$f13, THREAD_FPR13(\thread)
-	ldc1	$f15, THREAD_FPR15(\thread)
-	ldc1	$f17, THREAD_FPR17(\thread)
-	ldc1	$f19, THREAD_FPR19(\thread)
-	ldc1	$f21, THREAD_FPR21(\thread)
-	ldc1	$f23, THREAD_FPR23(\thread)
-	ldc1	$f25, THREAD_FPR25(\thread)
-	ldc1	$f27, THREAD_FPR27(\thread)
-	ldc1	$f29, THREAD_FPR29(\thread)
-	ldc1	$f31, THREAD_FPR31(\thread)
-	.endm
-
-	.macro	fpu_restore_double thread status tmp
-	sll	\tmp, \status, 5
-	bgez	\tmp, 1f				# 16 register mode?
-
-	fpu_restore_16odd \thread
-1:	fpu_restore_16even \thread \tmp
-	.endm
-
 	.macro	cpu_save_nonscratch thread
 	LONG_S	s0, THREAD_REG16(\thread)
 	LONG_S	s1, THREAD_REG17(\thread)

arch/mips/include/asm/asmmacro.h

@@ -62,6 +62,113 @@
 	.endm
 #endif /* CONFIG_MIPS_MT_SMTC */
 
+	.macro	fpu_save_16even thread tmp=t0
+	cfc1	\tmp, fcr31
+	sdc1	$f0,  THREAD_FPR0(\thread)
+	sdc1	$f2,  THREAD_FPR2(\thread)
+	sdc1	$f4,  THREAD_FPR4(\thread)
+	sdc1	$f6,  THREAD_FPR6(\thread)
+	sdc1	$f8,  THREAD_FPR8(\thread)
+	sdc1	$f10, THREAD_FPR10(\thread)
+	sdc1	$f12, THREAD_FPR12(\thread)
+	sdc1	$f14, THREAD_FPR14(\thread)
+	sdc1	$f16, THREAD_FPR16(\thread)
+	sdc1	$f18, THREAD_FPR18(\thread)
+	sdc1	$f20, THREAD_FPR20(\thread)
+	sdc1	$f22, THREAD_FPR22(\thread)
+	sdc1	$f24, THREAD_FPR24(\thread)
+	sdc1	$f26, THREAD_FPR26(\thread)
+	sdc1	$f28, THREAD_FPR28(\thread)
+	sdc1	$f30, THREAD_FPR30(\thread)
+	sw	\tmp, THREAD_FCR31(\thread)
+	.endm
+
+	.macro	fpu_save_16odd thread
+	.set	push
+	.set	mips64r2
+	sdc1	$f1,  THREAD_FPR1(\thread)
+	sdc1	$f3,  THREAD_FPR3(\thread)
+	sdc1	$f5,  THREAD_FPR5(\thread)
+	sdc1	$f7,  THREAD_FPR7(\thread)
+	sdc1	$f9,  THREAD_FPR9(\thread)
+	sdc1	$f11, THREAD_FPR11(\thread)
+	sdc1	$f13, THREAD_FPR13(\thread)
+	sdc1	$f15, THREAD_FPR15(\thread)
+	sdc1	$f17, THREAD_FPR17(\thread)
+	sdc1	$f19, THREAD_FPR19(\thread)
+	sdc1	$f21, THREAD_FPR21(\thread)
+	sdc1	$f23, THREAD_FPR23(\thread)
+	sdc1	$f25, THREAD_FPR25(\thread)
+	sdc1	$f27, THREAD_FPR27(\thread)
+	sdc1	$f29, THREAD_FPR29(\thread)
+	sdc1	$f31, THREAD_FPR31(\thread)
+	.set	pop
+	.endm
+
+	.macro	fpu_save_double thread status tmp
+#if defined(CONFIG_MIPS64) || defined(CONFIG_CPU_MIPS32_R2)
+	sll	\tmp, \status, 5
+	bgez	\tmp, 10f
+	fpu_save_16odd \thread
+10:
+#endif
+	fpu_save_16even \thread \tmp
+	.endm
+
+	.macro	fpu_restore_16even thread tmp=t0
+	lw	\tmp, THREAD_FCR31(\thread)
+	ldc1	$f0,  THREAD_FPR0(\thread)
+	ldc1	$f2,  THREAD_FPR2(\thread)
+	ldc1	$f4,  THREAD_FPR4(\thread)
+	ldc1	$f6,  THREAD_FPR6(\thread)
+	ldc1	$f8,  THREAD_FPR8(\thread)
+	ldc1	$f10, THREAD_FPR10(\thread)
+	ldc1	$f12, THREAD_FPR12(\thread)
+	ldc1	$f14, THREAD_FPR14(\thread)
+	ldc1	$f16, THREAD_FPR16(\thread)
+	ldc1	$f18, THREAD_FPR18(\thread)
+	ldc1	$f20, THREAD_FPR20(\thread)
+	ldc1	$f22, THREAD_FPR22(\thread)
+	ldc1	$f24, THREAD_FPR24(\thread)
+	ldc1	$f26, THREAD_FPR26(\thread)
+	ldc1	$f28, THREAD_FPR28(\thread)
+	ldc1	$f30, THREAD_FPR30(\thread)
+	ctc1	\tmp, fcr31
+	.endm
+
+	.macro	fpu_restore_16odd thread
+	.set	push
+	.set	mips64r2
+	ldc1	$f1,  THREAD_FPR1(\thread)
+	ldc1	$f3,  THREAD_FPR3(\thread)
+	ldc1	$f5,  THREAD_FPR5(\thread)
+	ldc1	$f7,  THREAD_FPR7(\thread)
+	ldc1	$f9,  THREAD_FPR9(\thread)
+	ldc1	$f11, THREAD_FPR11(\thread)
+	ldc1	$f13, THREAD_FPR13(\thread)
+	ldc1	$f15, THREAD_FPR15(\thread)
+	ldc1	$f17, THREAD_FPR17(\thread)
+	ldc1	$f19, THREAD_FPR19(\thread)
+	ldc1	$f21, THREAD_FPR21(\thread)
+	ldc1	$f23, THREAD_FPR23(\thread)
+	ldc1	$f25, THREAD_FPR25(\thread)
+	ldc1	$f27, THREAD_FPR27(\thread)
+	ldc1	$f29, THREAD_FPR29(\thread)
+	ldc1	$f31, THREAD_FPR31(\thread)
+	.set	pop
+	.endm
+
+	.macro	fpu_restore_double thread status tmp
+#if defined(CONFIG_MIPS64) || defined(CONFIG_CPU_MIPS32_R2)
+	sll	\tmp, \status, 5
+	bgez	\tmp, 10f				# 16 register mode?
+
+	fpu_restore_16odd \thread
+10:
+#endif
+	fpu_restore_16even \thread \tmp
+	.endm
+
 /*
  * Temporary until all gas have MT ASE support
  */

arch/mips/include/asm/elf.h

@@ -36,6 +36,7 @@
 #define EF_MIPS_ABI2		0x00000020
 #define EF_MIPS_OPTIONS_FIRST	0x00000080
 #define EF_MIPS_32BITMODE	0x00000100
+#define EF_MIPS_FP64		0x00000200
 #define EF_MIPS_ABI		0x0000f000
 #define EF_MIPS_ARCH		0xf0000000
 
@@ -175,6 +176,18 @@ typedef elf_fpreg_t elf_fpregset_t[ELF_NFPREG];
 
 #ifdef CONFIG_32BIT
 
+/*
+ * In order to be sure that we don't attempt to execute an O32 binary which
+ * requires 64 bit FP (FR=1) on a system which does not support it we refuse
+ * to execute any binary which has bits specified by the following macro set
+ * in its ELF header flags.
+ */
+#ifdef CONFIG_MIPS_O32_FP64_SUPPORT
+# define __MIPS_O32_FP64_MUST_BE_ZERO	0
+#else
+# define __MIPS_O32_FP64_MUST_BE_ZERO	EF_MIPS_FP64
+#endif
+
 /*
  * This is used to ensure we don't load something for the wrong architecture.
  */
@@ -191,6 +204,8 @@ typedef elf_fpreg_t elf_fpregset_t[ELF_NFPREG];
 		__res = 0;						\
 	if (((__h->e_flags & EF_MIPS_ABI) != 0) &&			\
 	    ((__h->e_flags & EF_MIPS_ABI) != EF_MIPS_ABI_O32))		\
+		__res = 0;						\
+	if (__h->e_flags & __MIPS_O32_FP64_MUST_BE_ZERO)		\
 		__res = 0;						\
 									\
 	__res;								\
@@ -249,6 +264,11 @@ extern struct mips_abi mips_abi_n32;
 
 #define SET_PERSONALITY(ex)						\
 do {									\
+	if ((ex).e_flags & EF_MIPS_FP64)				\
+		clear_thread_flag(TIF_32BIT_FPREGS);			\
+	else								\
+		set_thread_flag(TIF_32BIT_FPREGS);			\
+									\
 	if (personality(current->personality) != PER_LINUX)		\
 		set_personality(PER_LINUX);				\
 									\
@@ -271,14 +291,18 @@ do {									\
 #endif
 
 #ifdef CONFIG_MIPS32_O32
-#define __SET_PERSONALITY32_O32()					\
+#define __SET_PERSONALITY32_O32(ex)					\
 	do {								\
 		set_thread_flag(TIF_32BIT_REGS);			\
 		set_thread_flag(TIF_32BIT_ADDR);			\
+									\
+		if (!((ex).e_flags & EF_MIPS_FP64))			\
+			set_thread_flag(TIF_32BIT_FPREGS);		\
+									\
 		current->thread.abi = &mips_abi_32;			\
 	} while (0)
 #else
-#define __SET_PERSONALITY32_O32()					\
+#define __SET_PERSONALITY32_O32(ex)					\
 	do { } while (0)
 #endif
 
@@ -289,7 +313,7 @@ do {									\
 	     ((ex).e_flags & EF_MIPS_ABI) == 0)				\
 		__SET_PERSONALITY32_N32();				\
 	else								\
-		__SET_PERSONALITY32_O32();				\
+		__SET_PERSONALITY32_O32(ex);                            \
 } while (0)
 #else
 #define __SET_PERSONALITY32(ex) do { } while (0)
@@ -300,6 +324,7 @@ do {									\
 	unsigned int p;							\
 									\
 	clear_thread_flag(TIF_32BIT_REGS);				\
+	clear_thread_flag(TIF_32BIT_FPREGS);				\
 	clear_thread_flag(TIF_32BIT_ADDR);				\
 									\
 	if ((ex).e_ident[EI_CLASS] == ELFCLASS32)			\