riscv: Add support to no-FPU systems

This patchset adds an option, CONFIG_FPU, to enable/disable floating-
point support within the kernel.  The kernel's new behavior will be as
follows:

* with CONFIG_FPU=y
  All FPU codes are reserved.  If no FPU is found during booting, a
  global flag will be set, and those functions will be bypassed with
  condition check to that flag.

* with CONFIG_FPU=n
  No floating-point instructions in kernel and all related settings
  are excluded.

Signed-off-by: Palmer Dabbelt <palmer@sifive.com>

arch/riscv/Kconfig

@@ -210,6 +210,15 @@ config RISCV_BASE_PMU
 
 endmenu
 
+config FPU
+	bool "FPU support"
+	default y
+	help
+	  Say N here if you want to disable all floating-point related procedure
+	  in the kernel.
+
+	  If you don't know what to do here, say Y.
+
 endmenu
 
 menu "Kernel features"

arch/riscv/Makefile

@@ -26,7 +26,6 @@ ifeq ($(CONFIG_ARCH_RV64I),y)
 	KBUILD_CFLAGS += -mabi=lp64
 	KBUILD_AFLAGS += -mabi=lp64
 
-	KBUILD_MARCH = rv64im
 	KBUILD_LDFLAGS += -melf64lriscv
 else
 	BITS := 32
@@ -34,22 +33,20 @@ else
 
 	KBUILD_CFLAGS += -mabi=ilp32
 	KBUILD_AFLAGS += -mabi=ilp32
-	KBUILD_MARCH = rv32im
 	KBUILD_LDFLAGS += -melf32lriscv
 endif
 
 KBUILD_CFLAGS += -Wall
 
-ifeq ($(CONFIG_RISCV_ISA_A),y)
-	KBUILD_ARCH_A = a
-endif
-ifeq ($(CONFIG_RISCV_ISA_C),y)
-	KBUILD_ARCH_C = c
-endif
-
-KBUILD_AFLAGS += -march=$(KBUILD_MARCH)$(KBUILD_ARCH_A)fd$(KBUILD_ARCH_C)
+# ISA string setting
+riscv-march-$(CONFIG_ARCH_RV32I)	:= rv32im
+riscv-march-$(CONFIG_ARCH_RV64I)	:= rv64im
+riscv-march-$(CONFIG_RISCV_ISA_A)	:= $(riscv-march-y)a
+riscv-march-$(CONFIG_FPU)		:= $(riscv-march-y)fd
+riscv-march-$(CONFIG_RISCV_ISA_C)	:= $(riscv-march-y)c
+KBUILD_CFLAGS += -march=$(subst fd,,$(riscv-march-y))
+KBUILD_AFLAGS += -march=$(riscv-march-y)
 
-KBUILD_CFLAGS += -march=$(KBUILD_MARCH)$(KBUILD_ARCH_A)$(KBUILD_ARCH_C)
 KBUILD_CFLAGS += -mno-save-restore
 KBUILD_CFLAGS += -DCONFIG_PAGE_OFFSET=$(CONFIG_PAGE_OFFSET)
 

arch/riscv/include/asm/switch_to.h

@@ -18,6 +18,7 @@
 #include <asm/ptrace.h>
 #include <asm/csr.h>
 
+#ifdef CONFIG_FPU
 extern void __fstate_save(struct task_struct *save_to);
 extern void __fstate_restore(struct task_struct *restore_from);
 
@@ -55,6 +56,14 @@ static inline void __switch_to_aux(struct task_struct *prev,
 	fstate_restore(next, task_pt_regs(next));
 }
 
+extern bool has_fpu;
+#else
+#define has_fpu false
+#define fstate_save(task, regs) do { } while (0)
+#define fstate_restore(task, regs) do { } while (0)
+#define __switch_to_aux(__prev, __next) do { } while (0)
+#endif
+
 extern struct task_struct *__switch_to(struct task_struct *,
 				       struct task_struct *);
 
@@ -62,7 +71,8 @@ extern struct task_struct *__switch_to(struct task_struct *,
 do {							\
 	struct task_struct *__prev = (prev);		\
 	struct task_struct *__next = (next);		\
-	__switch_to_aux(__prev, __next);		\
+	if (has_fpu)					\
+		__switch_to_aux(__prev, __next);	\
 	((last) = __switch_to(__prev, __next));		\
 } while (0)
 

arch/riscv/kernel/Makefile

@@ -31,6 +31,7 @@ obj-y	+= vdso/
 
 CFLAGS_setup.o := -mcmodel=medany
 
+obj-$(CONFIG_FPU)		+= fpu.o
 obj-$(CONFIG_SMP)		+= smpboot.o
 obj-$(CONFIG_SMP)		+= smp.o
 obj-$(CONFIG_MODULES)		+= module.o

arch/riscv/kernel/cpufeature.c

@@ -22,6 +22,9 @@
 #include <asm/hwcap.h>
 
 unsigned long elf_hwcap __read_mostly;
+#ifdef CONFIG_FPU
+bool has_fpu __read_mostly;
+#endif
 
 void riscv_fill_hwcap(void)
 {
@@ -65,4 +68,9 @@ void riscv_fill_hwcap(void)
 	}
 
 	pr_info("elf_hwcap is 0x%lx", elf_hwcap);
+
+#ifdef CONFIG_FPU
+	if (elf_hwcap & (COMPAT_HWCAP_ISA_F | COMPAT_HWCAP_ISA_D))
+		has_fpu = true;
+#endif
 }

arch/riscv/kernel/entry.S

@@ -357,93 +357,6 @@ ENTRY(__switch_to)
 	ret
 ENDPROC(__switch_to)
 
-ENTRY(__fstate_save)
-	li  a2,  TASK_THREAD_F0
-	add a0, a0, a2
-	li t1, SR_FS
-	csrs sstatus, t1
-	frcsr t0
-	fsd f0,  TASK_THREAD_F0_F0(a0)
-	fsd f1,  TASK_THREAD_F1_F0(a0)
-	fsd f2,  TASK_THREAD_F2_F0(a0)
-	fsd f3,  TASK_THREAD_F3_F0(a0)
-	fsd f4,  TASK_THREAD_F4_F0(a0)
-	fsd f5,  TASK_THREAD_F5_F0(a0)
-	fsd f6,  TASK_THREAD_F6_F0(a0)
-	fsd f7,  TASK_THREAD_F7_F0(a0)
-	fsd f8,  TASK_THREAD_F8_F0(a0)
-	fsd f9,  TASK_THREAD_F9_F0(a0)
-	fsd f10, TASK_THREAD_F10_F0(a0)
-	fsd f11, TASK_THREAD_F11_F0(a0)
-	fsd f12, TASK_THREAD_F12_F0(a0)
-	fsd f13, TASK_THREAD_F13_F0(a0)
-	fsd f14, TASK_THREAD_F14_F0(a0)
-	fsd f15, TASK_THREAD_F15_F0(a0)
-	fsd f16, TASK_THREAD_F16_F0(a0)
-	fsd f17, TASK_THREAD_F17_F0(a0)
-	fsd f18, TASK_THREAD_F18_F0(a0)
-	fsd f19, TASK_THREAD_F19_F0(a0)
-	fsd f20, TASK_THREAD_F20_F0(a0)
-	fsd f21, TASK_THREAD_F21_F0(a0)
-	fsd f22, TASK_THREAD_F22_F0(a0)
-	fsd f23, TASK_THREAD_F23_F0(a0)
-	fsd f24, TASK_THREAD_F24_F0(a0)
-	fsd f25, TASK_THREAD_F25_F0(a0)
-	fsd f26, TASK_THREAD_F26_F0(a0)
-	fsd f27, TASK_THREAD_F27_F0(a0)
-	fsd f28, TASK_THREAD_F28_F0(a0)
-	fsd f29, TASK_THREAD_F29_F0(a0)
-	fsd f30, TASK_THREAD_F30_F0(a0)
-	fsd f31, TASK_THREAD_F31_F0(a0)
-	sw t0, TASK_THREAD_FCSR_F0(a0)
-	csrc sstatus, t1
-	ret
-ENDPROC(__fstate_save)
-
-ENTRY(__fstate_restore)
-	li  a2,  TASK_THREAD_F0
-	add a0, a0, a2
-	li t1, SR_FS
-	lw t0, TASK_THREAD_FCSR_F0(a0)
-	csrs sstatus, t1
-	fld f0,  TASK_THREAD_F0_F0(a0)
-	fld f1,  TASK_THREAD_F1_F0(a0)
-	fld f2,  TASK_THREAD_F2_F0(a0)
-	fld f3,  TASK_THREAD_F3_F0(a0)
-	fld f4,  TASK_THREAD_F4_F0(a0)
-	fld f5,  TASK_THREAD_F5_F0(a0)
-	fld f6,  TASK_THREAD_F6_F0(a0)
-	fld f7,  TASK_THREAD_F7_F0(a0)
-	fld f8,  TASK_THREAD_F8_F0(a0)
-	fld f9,  TASK_THREAD_F9_F0(a0)
-	fld f10, TASK_THREAD_F10_F0(a0)
-	fld f11, TASK_THREAD_F11_F0(a0)
-	fld f12, TASK_THREAD_F12_F0(a0)
-	fld f13, TASK_THREAD_F13_F0(a0)
-	fld f14, TASK_THREAD_F14_F0(a0)
-	fld f15, TASK_THREAD_F15_F0(a0)
-	fld f16, TASK_THREAD_F16_F0(a0)
-	fld f17, TASK_THREAD_F17_F0(a0)
-	fld f18, TASK_THREAD_F18_F0(a0)
-	fld f19, TASK_THREAD_F19_F0(a0)
-	fld f20, TASK_THREAD_F20_F0(a0)
-	fld f21, TASK_THREAD_F21_F0(a0)
-	fld f22, TASK_THREAD_F22_F0(a0)
-	fld f23, TASK_THREAD_F23_F0(a0)
-	fld f24, TASK_THREAD_F24_F0(a0)
-	fld f25, TASK_THREAD_F25_F0(a0)
-	fld f26, TASK_THREAD_F26_F0(a0)
-	fld f27, TASK_THREAD_F27_F0(a0)
-	fld f28, TASK_THREAD_F28_F0(a0)
-	fld f29, TASK_THREAD_F29_F0(a0)
-	fld f30, TASK_THREAD_F30_F0(a0)
-	fld f31, TASK_THREAD_F31_F0(a0)
-	fscsr t0
-	csrc sstatus, t1
-	ret
-ENDPROC(__fstate_restore)
-
-
 	.section ".rodata"
 	/* Exception vector table */
 ENTRY(excp_vect_table)

arch/riscv/kernel/fpu.S

@@ -0,0 +1,106 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ * Copyright (C) 2017 SiFive
+ *
+ *   This program 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, version 2.
+ *
+ *   This program 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.
+ */
+
+#include <linux/linkage.h>
+
+#include <asm/asm.h>
+#include <asm/csr.h>
+#include <asm/asm-offsets.h>
+
+ENTRY(__fstate_save)
+	li  a2,  TASK_THREAD_F0
+	add a0, a0, a2
+	li t1, SR_FS
+	csrs sstatus, t1
+	frcsr t0
+	fsd f0,  TASK_THREAD_F0_F0(a0)
+	fsd f1,  TASK_THREAD_F1_F0(a0)
+	fsd f2,  TASK_THREAD_F2_F0(a0)
+	fsd f3,  TASK_THREAD_F3_F0(a0)
+	fsd f4,  TASK_THREAD_F4_F0(a0)
+	fsd f5,  TASK_THREAD_F5_F0(a0)
+	fsd f6,  TASK_THREAD_F6_F0(a0)
+	fsd f7,  TASK_THREAD_F7_F0(a0)
+	fsd f8,  TASK_THREAD_F8_F0(a0)
+	fsd f9,  TASK_THREAD_F9_F0(a0)
+	fsd f10, TASK_THREAD_F10_F0(a0)
+	fsd f11, TASK_THREAD_F11_F0(a0)
+	fsd f12, TASK_THREAD_F12_F0(a0)
+	fsd f13, TASK_THREAD_F13_F0(a0)
+	fsd f14, TASK_THREAD_F14_F0(a0)
+	fsd f15, TASK_THREAD_F15_F0(a0)
+	fsd f16, TASK_THREAD_F16_F0(a0)
+	fsd f17, TASK_THREAD_F17_F0(a0)
+	fsd f18, TASK_THREAD_F18_F0(a0)
+	fsd f19, TASK_THREAD_F19_F0(a0)
+	fsd f20, TASK_THREAD_F20_F0(a0)
+	fsd f21, TASK_THREAD_F21_F0(a0)
+	fsd f22, TASK_THREAD_F22_F0(a0)
+	fsd f23, TASK_THREAD_F23_F0(a0)
+	fsd f24, TASK_THREAD_F24_F0(a0)
+	fsd f25, TASK_THREAD_F25_F0(a0)
+	fsd f26, TASK_THREAD_F26_F0(a0)
+	fsd f27, TASK_THREAD_F27_F0(a0)
+	fsd f28, TASK_THREAD_F28_F0(a0)
+	fsd f29, TASK_THREAD_F29_F0(a0)
+	fsd f30, TASK_THREAD_F30_F0(a0)
+	fsd f31, TASK_THREAD_F31_F0(a0)
+	sw t0, TASK_THREAD_FCSR_F0(a0)
+	csrc sstatus, t1
+	ret
+ENDPROC(__fstate_save)
+
+ENTRY(__fstate_restore)
+	li  a2,  TASK_THREAD_F0
+	add a0, a0, a2
+	li t1, SR_FS
+	lw t0, TASK_THREAD_FCSR_F0(a0)
+	csrs sstatus, t1
+	fld f0,  TASK_THREAD_F0_F0(a0)
+	fld f1,  TASK_THREAD_F1_F0(a0)
+	fld f2,  TASK_THREAD_F2_F0(a0)
+	fld f3,  TASK_THREAD_F3_F0(a0)
+	fld f4,  TASK_THREAD_F4_F0(a0)
+	fld f5,  TASK_THREAD_F5_F0(a0)
+	fld f6,  TASK_THREAD_F6_F0(a0)
+	fld f7,  TASK_THREAD_F7_F0(a0)
+	fld f8,  TASK_THREAD_F8_F0(a0)
+	fld f9,  TASK_THREAD_F9_F0(a0)
+	fld f10, TASK_THREAD_F10_F0(a0)
+	fld f11, TASK_THREAD_F11_F0(a0)
+	fld f12, TASK_THREAD_F12_F0(a0)
+	fld f13, TASK_THREAD_F13_F0(a0)
+	fld f14, TASK_THREAD_F14_F0(a0)
+	fld f15, TASK_THREAD_F15_F0(a0)
+	fld f16, TASK_THREAD_F16_F0(a0)
+	fld f17, TASK_THREAD_F17_F0(a0)
+	fld f18, TASK_THREAD_F18_F0(a0)
+	fld f19, TASK_THREAD_F19_F0(a0)
+	fld f20, TASK_THREAD_F20_F0(a0)
+	fld f21, TASK_THREAD_F21_F0(a0)
+	fld f22, TASK_THREAD_F22_F0(a0)
+	fld f23, TASK_THREAD_F23_F0(a0)
+	fld f24, TASK_THREAD_F24_F0(a0)
+	fld f25, TASK_THREAD_F25_F0(a0)
+	fld f26, TASK_THREAD_F26_F0(a0)
+	fld f27, TASK_THREAD_F27_F0(a0)
+	fld f28, TASK_THREAD_F28_F0(a0)
+	fld f29, TASK_THREAD_F29_F0(a0)
+	fld f30, TASK_THREAD_F30_F0(a0)
+	fld f31, TASK_THREAD_F31_F0(a0)
+	fscsr t0
+	csrc sstatus, t1
+	ret
+ENDPROC(__fstate_restore)

arch/riscv/kernel/process.c

@@ -76,7 +76,9 @@ void show_regs(struct pt_regs *regs)
 void start_thread(struct pt_regs *regs, unsigned long pc,
 	unsigned long sp)
 {
-	regs->sstatus = SR_SPIE /* User mode, irqs on */ | SR_FS_INITIAL;
+	regs->sstatus = SR_SPIE;
+	if (has_fpu)
+		regs->sstatus |= SR_FS_INITIAL;
 	regs->sepc = pc;
 	regs->sp = sp;
 	set_fs(USER_DS);
@@ -84,12 +86,14 @@ void start_thread(struct pt_regs *regs, unsigned long pc,
 
 void flush_thread(void)
 {
+#ifdef CONFIG_FPU
 	/*
 	 * Reset FPU context
 	 *	frm: round to nearest, ties to even (IEEE default)
 	 *	fflags: accrued exceptions cleared
 	 */
 	memset(&current->thread.fstate, 0, sizeof(current->thread.fstate));
+#endif
 }
 
 int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)

arch/riscv/kernel/signal.c

@@ -37,45 +37,69 @@ struct rt_sigframe {
 	struct ucontext uc;
 };
 
-static long restore_d_state(struct pt_regs *regs,
-	struct __riscv_d_ext_state __user *state)
+#ifdef CONFIG_FPU
+static long restore_fp_state(struct pt_regs *regs,
+			     union __riscv_fp_state *sc_fpregs)
 {
 	long err;
+	struct __riscv_d_ext_state __user *state = &sc_fpregs->d;
+	size_t i;
+
 	err = __copy_from_user(&current->thread.fstate, state, sizeof(*state));
-	if (likely(!err))
-		fstate_restore(current, regs);
+	if (unlikely(err))
+		return err;
+
+	fstate_restore(current, regs);
+
+	/* We support no other extension state at this time. */
+	for (i = 0; i < ARRAY_SIZE(sc_fpregs->q.reserved); i++) {
+		u32 value;
+
+		err = __get_user(value, &sc_fpregs->q.reserved[i]);
+		if (unlikely(err))
+			break;
+		if (value != 0)
+			return -EINVAL;
+	}
+
 	return err;
 }
 
-static long save_d_state(struct pt_regs *regs,
-	struct __riscv_d_ext_state __user *state)
+static long save_fp_state(struct pt_regs *regs,
+			  union __riscv_fp_state *sc_fpregs)
 {
+	long err;
+	struct __riscv_d_ext_state __user *state = &sc_fpregs->d;
+	size_t i;
+
 	fstate_save(current, regs);
-	return __copy_to_user(state, &current->thread.fstate, sizeof(*state));
+	err = __copy_to_user(state, &current->thread.fstate, sizeof(*state));
+	if (unlikely(err))
+		return err;
+
+	/* We support no other extension state at this time. */
+	for (i = 0; i < ARRAY_SIZE(sc_fpregs->q.reserved); i++) {
+		err = __put_user(0, &sc_fpregs->q.reserved[i]);
+		if (unlikely(err))
+			break;
+	}
+
+	return err;
 }
+#else
+#define save_fp_state(task, regs) (0)
+#define restore_fp_state(task, regs) (0)
+#endif
 
 static long restore_sigcontext(struct pt_regs *regs,
 	struct sigcontext __user *sc)
 {
 	long err;
-	size_t i;
 	/* sc_regs is structured the same as the start of pt_regs */
 	err = __copy_from_user(regs, &sc->sc_regs, sizeof(sc->sc_regs));
-	if (unlikely(err))
-		return err;
 	/* Restore the floating-point state. */
-	err = restore_d_state(regs, &sc->sc_fpregs.d);
-	if (unlikely(err))
-		return err;
-	/* We support no other extension state at this time. */
-	for (i = 0; i < ARRAY_SIZE(sc->sc_fpregs.q.reserved); i++) {
-		u32 value;
-		err = __get_user(value, &sc->sc_fpregs.q.reserved[i]);
-		if (unlikely(err))
-			break;
-		if (value != 0)
-			return -EINVAL;
-	}
+	if (has_fpu)
+		err |= restore_fp_state(regs, &sc->sc_fpregs);
 	return err;
 }
 
@@ -124,14 +148,11 @@ static long setup_sigcontext(struct rt_sigframe __user *frame,
 {
 	struct sigcontext __user *sc = &frame->uc.uc_mcontext;
 	long err;
-	size_t i;
 	/* sc_regs is structured the same as the start of pt_regs */
 	err = __copy_to_user(&sc->sc_regs, regs, sizeof(sc->sc_regs));
 	/* Save the floating-point state. */
-	err |= save_d_state(regs, &sc->sc_fpregs.d);
-	/* We support no other extension state at this time. */
-	for (i = 0; i < ARRAY_SIZE(sc->sc_fpregs.q.reserved); i++)
-		err |= __put_user(0, &sc->sc_fpregs.q.reserved[i]);
+	if (has_fpu)
+		err |= save_fp_state(regs, &sc->sc_fpregs);
 	return err;
 }