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 <paul.burton@imgtec.com>
Cc: linux-mips@linux-mips.org
Cc: Paul Burton <paul.burton@imgtec.com>
Patchwork: https://patchwork.linux-mips.org/patch/6154/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>

10 files changed, 209 insertions, 72 deletions

diff --git a/arch/mips/kernel/binfmt_elfo32.c b/arch/mips/kernel/binfmt_elfo32.c
index 202e581e6096..7faf5f2bee25 100644
--- a/arch/mips/kernel/binfmt_elfo32.c
+++ b/arch/mips/kernel/binfmt_elfo32.c
@@ -28,6 +28,18 @@ typedef double elf_fpreg_t;
 typedef elf_fpreg_t elf_fpregset_t[ELF_NFPREG];
 
 /*
+ * 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.
  */
 #define elf_check_arch(hdr)						\
@@ -44,6 +56,8 @@ typedef elf_fpreg_t elf_fpregset_t[ELF_NFPREG];
 	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;								\
 })
diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c
index c814287bdf5d..e2b2d2043701 100644
--- a/arch/mips/kernel/cpu-probe.c
+++ b/arch/mips/kernel/cpu-probe.c
@@ -112,7 +112,7 @@ static inline unsigned long cpu_get_fpu_id(void)
 	unsigned long tmp, fpu_id;
 
 	tmp = read_c0_status();
-	__enable_fpu();
+	__enable_fpu(FPU_AS_IS);
 	fpu_id = read_32bit_cp1_register(CP1_REVISION);
 	write_c0_status(tmp);
 	return fpu_id;
diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
index ddc76103e78c..747a6cfbb709 100644
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -60,9 +60,6 @@ void start_thread(struct pt_regs * regs, unsigned long pc, unsigned long sp)
 
 	/* New thread loses kernel privileges. */
 	status = regs->cp0_status & ~(ST0_CU0|ST0_CU1|ST0_FR|KU_MASK);
-#ifdef CONFIG_64BIT
-	status |= test_thread_flag(TIF_32BIT_REGS) ? 0 : ST0_FR;
-#endif
 	status |= KU_USER;
 	regs->cp0_status = status;
 	clear_used_math();
diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c
index b52e1d2b33e0..7da9b76db4d9 100644
--- a/arch/mips/kernel/ptrace.c
+++ b/arch/mips/kernel/ptrace.c
@@ -137,13 +137,13 @@ int ptrace_getfpregs(struct task_struct *child, __u32 __user *data)
 		if (cpu_has_mipsmt) {
 			unsigned int vpflags = dvpe();
 			flags = read_c0_status();
-			__enable_fpu();
+			__enable_fpu(FPU_AS_IS);
 			__asm__ __volatile__("cfc1\t%0,$0" : "=r" (tmp));
 			write_c0_status(flags);
 			evpe(vpflags);
 		} else {
 			flags = read_c0_status();
-			__enable_fpu();
+			__enable_fpu(FPU_AS_IS);
 			__asm__ __volatile__("cfc1\t%0,$0" : "=r" (tmp));
 			write_c0_status(flags);
 		}
@@ -408,6 +408,7 @@ long arch_ptrace(struct task_struct *child, long request,
 	/* Read the word at location addr in the USER area. */
 	case PTRACE_PEEKUSR: {
 		struct pt_regs *regs;
+		fpureg_t *fregs;
 		unsigned long tmp = 0;
 
 		regs = task_pt_regs(child);
@@ -418,26 +419,28 @@ long arch_ptrace(struct task_struct *child, long request,
 			tmp = regs->regs[addr];
 			break;
 		case FPR_BASE ... FPR_BASE + 31:
-			if (tsk_used_math(child)) {
-				fpureg_t *fregs = get_fpu_regs(child);
+			if (!tsk_used_math(child)) {
+				/* FP not yet used */
+				tmp = -1;
+				break;
+			}
+			fregs = get_fpu_regs(child);
 
 #ifdef CONFIG_32BIT
+			if (test_thread_flag(TIF_32BIT_FPREGS)) {
 				/*
 				 * The odd registers are actually the high
 				 * order bits of the values stored in the even
 				 * registers - unless we're using r2k_switch.S.
 				 */
 				if (addr & 1)
-					tmp = (unsigned long) (fregs[((addr & ~1) - 32)] >> 32);
+					tmp = fregs[(addr & ~1) - 32] >> 32;
 				else
-					tmp = (unsigned long) (fregs[(addr - 32)] & 0xffffffff);
-#endif
-#ifdef CONFIG_64BIT
-				tmp = fregs[addr - FPR_BASE];
-#endif
-			} else {
-				tmp = -1;	/* FP not yet used  */
+					tmp = fregs[addr - 32];
+				break;
 			}
+#endif
+			tmp = fregs[addr - FPR_BASE];
 			break;
 		case PC:
 			tmp = regs->cp0_epc;
@@ -483,13 +486,13 @@ long arch_ptrace(struct task_struct *child, long request,
 			if (cpu_has_mipsmt) {
 				unsigned int vpflags = dvpe();
 				flags = read_c0_status();
-				__enable_fpu();
+				__enable_fpu(FPU_AS_IS);
 				__asm__ __volatile__("cfc1\t%0,$0": "=r" (tmp));
 				write_c0_status(flags);
 				evpe(vpflags);
 			} else {
 				flags = read_c0_status();
-				__enable_fpu();
+				__enable_fpu(FPU_AS_IS);
 				__asm__ __volatile__("cfc1\t%0,$0": "=r" (tmp));
 				write_c0_status(flags);
 			}
@@ -554,22 +557,25 @@ long arch_ptrace(struct task_struct *child, long request,
 				child->thread.fpu.fcr31 = 0;
 			}
 #ifdef CONFIG_32BIT
-			/*
-			 * The odd registers are actually the high order bits
-			 * of the values stored in the even registers - unless
-			 * we're using r2k_switch.S.
-			 */
-			if (addr & 1) {
-				fregs[(addr & ~1) - FPR_BASE] &= 0xffffffff;
-				fregs[(addr & ~1) - FPR_BASE] |= ((unsigned long long) data) << 32;
-			} else {
-				fregs[addr - FPR_BASE] &= ~0xffffffffLL;
-				fregs[addr - FPR_BASE] |= data;
+			if (test_thread_flag(TIF_32BIT_FPREGS)) {
+				/*
+				 * The odd registers are actually the high
+				 * order bits of the values stored in the even
+				 * registers - unless we're using r2k_switch.S.
+				 */
+				if (addr & 1) {
+					fregs[(addr & ~1) - FPR_BASE] &=
+						0xffffffff;
+					fregs[(addr & ~1) - FPR_BASE] |=
+						((u64)data) << 32;
+				} else {
+					fregs[addr - FPR_BASE] &= ~0xffffffffLL;
+					fregs[addr - FPR_BASE] |= data;
+				}
+				break;
 			}
 #endif
-#ifdef CONFIG_64BIT
 			fregs[addr - FPR_BASE] = data;
-#endif
 			break;
 		}
 		case PC:
diff --git a/arch/mips/kernel/ptrace32.c b/arch/mips/kernel/ptrace32.c
index 9486055ba660..b8aa2dd5b00b 100644
--- a/arch/mips/kernel/ptrace32.c
+++ b/arch/mips/kernel/ptrace32.c
@@ -80,6 +80,7 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
 	/* Read the word at location addr in the USER area. */
 	case PTRACE_PEEKUSR: {
 		struct pt_regs *regs;
+		fpureg_t *fregs;
 		unsigned int tmp;
 
 		regs = task_pt_regs(child);
@@ -90,21 +91,25 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
 			tmp = regs->regs[addr];
 			break;
 		case FPR_BASE ... FPR_BASE + 31:
-			if (tsk_used_math(child)) {
-				fpureg_t *fregs = get_fpu_regs(child);
-
+			if (!tsk_used_math(child)) {
+				/* FP not yet used */
+				tmp = -1;
+				break;
+			}
+			fregs = get_fpu_regs(child);
+			if (test_thread_flag(TIF_32BIT_FPREGS)) {
 				/*
 				 * The odd registers are actually the high
 				 * order bits of the values stored in the even
 				 * registers - unless we're using r2k_switch.S.
 				 */
 				if (addr & 1)
-					tmp = (unsigned long) (fregs[((addr & ~1) - 32)] >> 32);
+					tmp = fregs[(addr & ~1) - 32] >> 32;
 				else
-					tmp = (unsigned long) (fregs[(addr - 32)] & 0xffffffff);
-			} else {
-				tmp = -1;	/* FP not yet used  */
+					tmp = fregs[addr - 32];
+				break;
 			}
+			tmp = fregs[addr - FPR_BASE];
 			break;
 		case PC:
 			tmp = regs->cp0_epc;
@@ -147,13 +152,13 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
 			if (cpu_has_mipsmt) {
 				unsigned int vpflags = dvpe();
 				flags = read_c0_status();
-				__enable_fpu();
+				__enable_fpu(FPU_AS_IS);
 				__asm__ __volatile__("cfc1\t%0,$0": "=r" (tmp));
 				write_c0_status(flags);
 				evpe(vpflags);
 			} else {
 				flags = read_c0_status();
-				__enable_fpu();
+				__enable_fpu(FPU_AS_IS);
 				__asm__ __volatile__("cfc1\t%0,$0": "=r" (tmp));
 				write_c0_status(flags);
 			}
@@ -236,20 +241,24 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
 				       sizeof(child->thread.fpu));
 				child->thread.fpu.fcr31 = 0;
 			}
-			/*
-			 * The odd registers are actually the high order bits
-			 * of the values stored in the even registers - unless
-			 * we're using r2k_switch.S.
-			 */
-			if (addr & 1) {
-				fregs[(addr & ~1) - FPR_BASE] &= 0xffffffff;
-				fregs[(addr & ~1) - FPR_BASE] |= ((unsigned long long) data) << 32;
-			} else {
-				fregs[addr - FPR_BASE] &= ~0xffffffffLL;
-				/* Must cast, lest sign extension fill upper
-				   bits!  */
-				fregs[addr - FPR_BASE] |= (unsigned int)data;
+			if (test_thread_flag(TIF_32BIT_FPREGS)) {
+				/*
+				 * The odd registers are actually the high
+				 * order bits of the values stored in the even
+				 * registers - unless we're using r2k_switch.S.
+				 */
+				if (addr & 1) {
+					fregs[(addr & ~1) - FPR_BASE] &=
+						0xffffffff;
+					fregs[(addr & ~1) - FPR_BASE] |=
+						((u64)data) << 32;
+				} else {
+					fregs[addr - FPR_BASE] &= ~0xffffffffLL;
+					fregs[addr - FPR_BASE] |= data;
+				}
+				break;
 			}
+			fregs[addr - FPR_BASE] = data;
 			break;
 		}
 		case PC:
diff --git a/arch/mips/kernel/r4k_fpu.S b/arch/mips/kernel/r4k_fpu.S
index 55ffe149dae9..253b2fb52026 100644
--- a/arch/mips/kernel/r4k_fpu.S
+++ b/arch/mips/kernel/r4k_fpu.S
@@ -35,7 +35,15 @@
 LEAF(_save_fp_context)
 	cfc1	t1, fcr31
 
-#ifdef CONFIG_64BIT
+#if defined(CONFIG_64BIT) || defined(CONFIG_MIPS32_R2)
+	.set	push
+#ifdef CONFIG_MIPS32_R2
+	.set	mips64r2
+	mfc0	t0, CP0_STATUS
+	sll	t0, t0, 5
+	bgez	t0, 1f			# skip storing odd if FR=0
+	 nop
+#endif
 	/* Store the 16 odd double precision registers */
 	EX	sdc1 $f1, SC_FPREGS+8(a0)
 	EX	sdc1 $f3, SC_FPREGS+24(a0)
@@ -53,6 +61,7 @@ LEAF(_save_fp_context)
 	EX	sdc1 $f27, SC_FPREGS+216(a0)
 	EX	sdc1 $f29, SC_FPREGS+232(a0)
 	EX	sdc1 $f31, SC_FPREGS+248(a0)
+1:	.set	pop
 #endif
 
 	/* Store the 16 even double precision registers */
@@ -82,7 +91,31 @@ LEAF(_save_fp_context)
 LEAF(_save_fp_context32)
 	cfc1	t1, fcr31
 
-	EX	sdc1 $f0, SC32_FPREGS+0(a0)
+	mfc0	t0, CP0_STATUS
+	sll	t0, t0, 5
+	bgez	t0, 1f			# skip storing odd if FR=0
+	 nop
+
+	/* Store the 16 odd double precision registers */
+	EX      sdc1 $f1, SC32_FPREGS+8(a0)
+	EX      sdc1 $f3, SC32_FPREGS+24(a0)
+	EX      sdc1 $f5, SC32_FPREGS+40(a0)
+	EX      sdc1 $f7, SC32_FPREGS+56(a0)
+	EX      sdc1 $f9, SC32_FPREGS+72(a0)
+	EX      sdc1 $f11, SC32_FPREGS+88(a0)
+	EX      sdc1 $f13, SC32_FPREGS+104(a0)
+	EX      sdc1 $f15, SC32_FPREGS+120(a0)
+	EX      sdc1 $f17, SC32_FPREGS+136(a0)
+	EX      sdc1 $f19, SC32_FPREGS+152(a0)
+	EX      sdc1 $f21, SC32_FPREGS+168(a0)
+	EX      sdc1 $f23, SC32_FPREGS+184(a0)
+	EX      sdc1 $f25, SC32_FPREGS+200(a0)
+	EX      sdc1 $f27, SC32_FPREGS+216(a0)
+	EX      sdc1 $f29, SC32_FPREGS+232(a0)
+	EX      sdc1 $f31, SC32_FPREGS+248(a0)
+
+	/* Store the 16 even double precision registers */
+1:	EX	sdc1 $f0, SC32_FPREGS+0(a0)
 	EX	sdc1 $f2, SC32_FPREGS+16(a0)
 	EX	sdc1 $f4, SC32_FPREGS+32(a0)
 	EX	sdc1 $f6, SC32_FPREGS+48(a0)
@@ -114,7 +147,16 @@ LEAF(_save_fp_context32)
  */
 LEAF(_restore_fp_context)
 	EX	lw t0, SC_FPC_CSR(a0)
-#ifdef CONFIG_64BIT
+
+#if defined(CONFIG_64BIT) || defined(CONFIG_MIPS32_R2)
+	.set	push
+#ifdef CONFIG_MIPS32_R2
+	.set	mips64r2
+	mfc0	t0, CP0_STATUS
+	sll	t0, t0, 5
+	bgez	t0, 1f			# skip loading odd if FR=0
+	 nop
+#endif
 	EX	ldc1 $f1, SC_FPREGS+8(a0)
 	EX	ldc1 $f3, SC_FPREGS+24(a0)
 	EX	ldc1 $f5, SC_FPREGS+40(a0)
@@ -131,6 +173,7 @@ LEAF(_restore_fp_context)
 	EX	ldc1 $f27, SC_FPREGS+216(a0)
 	EX	ldc1 $f29, SC_FPREGS+232(a0)
 	EX	ldc1 $f31, SC_FPREGS+248(a0)
+1:	.set pop
 #endif
 	EX	ldc1 $f0, SC_FPREGS+0(a0)
 	EX	ldc1 $f2, SC_FPREGS+16(a0)
@@ -157,7 +200,30 @@ LEAF(_restore_fp_context)
 LEAF(_restore_fp_context32)
 	/* Restore an o32 sigcontext.  */
 	EX	lw t0, SC32_FPC_CSR(a0)
-	EX	ldc1 $f0, SC32_FPREGS+0(a0)
+
+	mfc0	t0, CP0_STATUS
+	sll	t0, t0, 5
+	bgez	t0, 1f			# skip loading odd if FR=0
+	 nop
+
+	EX      ldc1 $f1, SC32_FPREGS+8(a0)
+	EX      ldc1 $f3, SC32_FPREGS+24(a0)
+	EX      ldc1 $f5, SC32_FPREGS+40(a0)
+	EX      ldc1 $f7, SC32_FPREGS+56(a0)
+	EX      ldc1 $f9, SC32_FPREGS+72(a0)
+	EX      ldc1 $f11, SC32_FPREGS+88(a0)
+	EX      ldc1 $f13, SC32_FPREGS+104(a0)
+	EX      ldc1 $f15, SC32_FPREGS+120(a0)
+	EX      ldc1 $f17, SC32_FPREGS+136(a0)
+	EX      ldc1 $f19, SC32_FPREGS+152(a0)
+	EX      ldc1 $f21, SC32_FPREGS+168(a0)
+	EX      ldc1 $f23, SC32_FPREGS+184(a0)
+	EX      ldc1 $f25, SC32_FPREGS+200(a0)
+	EX      ldc1 $f27, SC32_FPREGS+216(a0)
+	EX      ldc1 $f29, SC32_FPREGS+232(a0)
+	EX      ldc1 $f31, SC32_FPREGS+248(a0)
+
+1:	EX	ldc1 $f0, SC32_FPREGS+0(a0)
 	EX	ldc1 $f2, SC32_FPREGS+16(a0)
 	EX	ldc1 $f4, SC32_FPREGS+32(a0)
 	EX	ldc1 $f6, SC32_FPREGS+48(a0)
diff --git a/arch/mips/kernel/r4k_switch.S b/arch/mips/kernel/r4k_switch.S
index 078de5eaca8f..cc78dd9a17c7 100644
--- a/arch/mips/kernel/r4k_switch.S
+++ b/arch/mips/kernel/r4k_switch.S
@@ -123,7 +123,7 @@
  * Save a thread's fp context.
  */
 LEAF(_save_fp)
-#ifdef CONFIG_64BIT
+#if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPS32_R2)
 	mfc0	t0, CP0_STATUS
 #endif
 	fpu_save_double a0 t0 t1		# clobbers t1
@@ -134,7 +134,7 @@ LEAF(_save_fp)
  * Restore a thread's fp context.
  */
 LEAF(_restore_fp)
-#ifdef CONFIG_64BIT
+#if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPS32_R2)
 	mfc0	t0, CP0_STATUS
 #endif
 	fpu_restore_double a0 t0 t1		# clobbers t1
@@ -228,6 +228,47 @@ LEAF(_init_fpu)
 	mtc1	t1, $f29
 	mtc1	t1, $f30
 	mtc1	t1, $f31
+
+#ifdef CONFIG_CPU_MIPS32_R2
+	.set    push
+	.set    mips64r2
+	sll     t0, t0, 5			# is Status.FR set?
+	bgez    t0, 1f				# no: skip setting upper 32b
+
+	mthc1   t1, $f0
+	mthc1   t1, $f1
+	mthc1   t1, $f2
+	mthc1   t1, $f3
+	mthc1   t1, $f4
+	mthc1   t1, $f5
+	mthc1   t1, $f6
+	mthc1   t1, $f7
+	mthc1   t1, $f8
+	mthc1   t1, $f9
+	mthc1   t1, $f10
+	mthc1   t1, $f11
+	mthc1   t1, $f12
+	mthc1   t1, $f13
+	mthc1   t1, $f14
+	mthc1   t1, $f15
+	mthc1   t1, $f16
+	mthc1   t1, $f17
+	mthc1   t1, $f18
+	mthc1   t1, $f19
+	mthc1   t1, $f20
+	mthc1   t1, $f21
+	mthc1   t1, $f22
+	mthc1   t1, $f23
+	mthc1   t1, $f24
+	mthc1   t1, $f25
+	mthc1   t1, $f26
+	mthc1   t1, $f27
+	mthc1   t1, $f28
+	mthc1   t1, $f29
+	mthc1   t1, $f30
+	mthc1   t1, $f31
+1:	.set    pop
+#endif /* CONFIG_CPU_MIPS32_R2 */
 #else
 	.set	mips3
 	dmtc1	t1, $f0
diff --git a/arch/mips/kernel/signal.c b/arch/mips/kernel/signal.c
index 2f285abc76d5..5199563c4403 100644
--- a/arch/mips/kernel/signal.c
+++ b/arch/mips/kernel/signal.c
@@ -71,8 +71,9 @@ static int protected_save_fp_context(struct sigcontext __user *sc)
 	int err;
 	while (1) {
 		lock_fpu_owner();
-		own_fpu_inatomic(1);
-		err = save_fp_context(sc); /* this might fail */
+		err = own_fpu_inatomic(1);
+		if (!err)
+			err = save_fp_context(sc); /* this might fail */
 		unlock_fpu_owner();
 		if (likely(!err))
 			break;
@@ -91,8 +92,9 @@ static int protected_restore_fp_context(struct sigcontext __user *sc)
 	int err, tmp __maybe_unused;
 	while (1) {
 		lock_fpu_owner();
-		own_fpu_inatomic(0);
-		err = restore_fp_context(sc); /* this might fail */
+		err = own_fpu_inatomic(0);
+		if (!err)
+			err = restore_fp_context(sc); /* this might fail */
 		unlock_fpu_owner();
 		if (likely(!err))
 			break;
diff --git a/arch/mips/kernel/signal32.c b/arch/mips/kernel/signal32.c
index 1905a419aa46..3d60f7750fa8 100644
--- a/arch/mips/kernel/signal32.c
+++ b/arch/mips/kernel/signal32.c
@@ -85,8 +85,9 @@ static int protected_save_fp_context32(struct sigcontext32 __user *sc)
 	int err;
 	while (1) {
 		lock_fpu_owner();
-		own_fpu_inatomic(1);
-		err = save_fp_context32(sc); /* this might fail */
+		err = own_fpu_inatomic(1);
+		if (!err)
+			err = save_fp_context32(sc); /* this might fail */
 		unlock_fpu_owner();
 		if (likely(!err))
 			break;
@@ -105,8 +106,9 @@ static int protected_restore_fp_context32(struct sigcontext32 __user *sc)
 	int err, tmp __maybe_unused;
 	while (1) {
 		lock_fpu_owner();
-		own_fpu_inatomic(0);
-		err = restore_fp_context32(sc); /* this might fail */
+		err = own_fpu_inatomic(0);
+		if (!err)
+			err = restore_fp_context32(sc); /* this might fail */
 		unlock_fpu_owner();
 		if (likely(!err))
 			break;
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index f9c8746be8d6..f40f688276c2 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -1080,7 +1080,7 @@ asmlinkage void do_cpu(struct pt_regs *regs)
 	unsigned long old_epc, old31;
 	unsigned int opcode;
 	unsigned int cpid;
-	int status;
+	int status, err;
 	unsigned long __maybe_unused flags;
 
 	prev_state = exception_enter();
@@ -1153,19 +1153,19 @@ asmlinkage void do_cpu(struct pt_regs *regs)
 
 	case 1:
 		if (used_math())	/* Using the FPU again.	 */
-			own_fpu(1);
+			err = own_fpu(1);
 		else {			/* First time FPU user.	 */
-			init_fpu();
+			err = init_fpu();
 			set_used_math();
 		}
 
-		if (!raw_cpu_has_fpu) {
+		if (!raw_cpu_has_fpu || err) {
 			int sig;
 			void __user *fault_addr = NULL;
 			sig = fpu_emulator_cop1Handler(regs,
 						       &current->thread.fpu,
 						       0, &fault_addr);
-			if (!process_fpemu_return(sig, fault_addr))
+			if (!process_fpemu_return(sig, fault_addr) && !err)
 				mt_ase_fp_affinity();
 		}