* [PATCH v2 1/5] nds32: nds32 FPU port
2018-10-11 2:20 [PATCH v2 0/5] nds32 FPU port Vincent Chen
@ 2018-10-11 2:20 ` Vincent Chen
2018-10-11 7:30 ` Arnd Bergmann
2018-10-11 2:20 ` [PATCH v2 2/5] nds32: Support FP emulation Vincent Chen
` (3 subsequent siblings)
4 siblings, 1 reply; 9+ messages in thread
From: Vincent Chen @ 2018-10-11 2:20 UTC (permalink / raw)
To: green.hu, linux-kernel, arnd, deanbo422; +Cc: Vincent Chen
This commit contains basic components for nds32 FPU support such as
FPU exception handler and context switch for FPU register.
Signed-off-by: Vincent Chen <vincentc@andestech.com>
---
arch/nds32/Kconfig | 1 +
arch/nds32/Kconfig.cpu | 22 +++
arch/nds32/Makefile | 10 ++
arch/nds32/include/asm/bitfield.h | 15 ++
arch/nds32/include/asm/fpu.h | 116 ++++++++++++++++
arch/nds32/include/asm/processor.h | 7 +
arch/nds32/include/uapi/asm/sigcontext.h | 5 +
arch/nds32/kernel/Makefile | 9 ++
arch/nds32/kernel/ex-entry.S | 9 ++
arch/nds32/kernel/ex-exit.S | 8 +-
arch/nds32/kernel/ex-scall.S | 8 +-
arch/nds32/kernel/fpu.c | 219 ++++++++++++++++++++++++++++++
arch/nds32/kernel/process.c | 64 ++++++++-
arch/nds32/kernel/setup.c | 5 +
arch/nds32/kernel/signal.c | 68 +++++++++-
arch/nds32/kernel/traps.c | 16 ++
16 files changed, 571 insertions(+), 11 deletions(-)
create mode 100644 arch/nds32/include/asm/fpu.h
create mode 100644 arch/nds32/kernel/fpu.c
diff --git a/arch/nds32/Kconfig b/arch/nds32/Kconfig
index 7068f34..4f4a580 100644
--- a/arch/nds32/Kconfig
+++ b/arch/nds32/Kconfig
@@ -29,6 +29,7 @@ config NDS32
select HANDLE_DOMAIN_IRQ
select HAVE_ARCH_TRACEHOOK
select HAVE_DEBUG_KMEMLEAK
+ select HAVE_EXIT_THREAD
select HAVE_MEMBLOCK
select HAVE_REGS_AND_STACK_ACCESS_API
select IRQ_DOMAIN
diff --git a/arch/nds32/Kconfig.cpu b/arch/nds32/Kconfig.cpu
index b8c8984..7ee4e19 100644
--- a/arch/nds32/Kconfig.cpu
+++ b/arch/nds32/Kconfig.cpu
@@ -7,6 +7,28 @@ config CPU_LITTLE_ENDIAN
bool "Little endian"
default y
+config FPU
+ bool "FPU support"
+ default n
+ help
+ If FPU ISA is used in user space, this configure shall be Y to make
+ the fpu context switch and fpu exception handler is enabled in kernel.
+ Lazy FPU is the default scheme for fpu context switch. If user wants
+ to disable Lazy FPU scheme, please enable CONFIG_UNLAZY_FPU.
+
+ If no FPU ISA is used in user space, say N.
+
+config UNLAZY_FPU
+ bool "Unlazy FPU support"
+ depends on FPU
+ default n
+ help
+ Say Y here to disable lazy FPU scheme. Disable lazy FPU scheme causes
+ some performance loss because the fpu register are loaded and stored
+ in each context switch.
+
+ For nomal case, say N.
+
config HWZOL
bool "hardware zero overhead loop support"
depends on CPU_D10 || CPU_D15
diff --git a/arch/nds32/Makefile b/arch/nds32/Makefile
index 3509fac..599ee62 100644
--- a/arch/nds32/Makefile
+++ b/arch/nds32/Makefile
@@ -5,9 +5,19 @@ KBUILD_DEFCONFIG := defconfig
comma = ,
+
ifdef CONFIG_FUNCTION_TRACER
arch-y += -malways-save-lp -mno-relax
endif
+ifdef CONFIG_FPU
+arch-y += \
+ $(shell $(CC) -E -dM -xc /dev/null | \
+ grep -o -m1 NDS32_EXT_FPU_SP | \
+ sed -e 's/NDS32_EXT_FPU_SP/-mno-ext-fpu-sp -mfloat-abi=soft/') \
+ $(shell $(CC) -E -dM -xc /dev/null | \
+ grep -o -m1 NDS32_EXT_FPU_DP | \
+ sed -e 's/NDS32_EXT_FPU_DP/-mno-ext-fpu-dp -mfloat-abi=soft/')
+endif
KBUILD_CFLAGS += $(call cc-option, -mno-sched-prolog-epilog)
KBUILD_CFLAGS += -mcmodel=large
diff --git a/arch/nds32/include/asm/bitfield.h b/arch/nds32/include/asm/bitfield.h
index 8e84fc3..bbb1c08 100644
--- a/arch/nds32/include/asm/bitfield.h
+++ b/arch/nds32/include/asm/bitfield.h
@@ -251,6 +251,11 @@
#define ITYPE_mskSTYPE ( 0xF << ITYPE_offSTYPE )
#define ITYPE_mskCPID ( 0x3 << ITYPE_offCPID )
+/* Additional definitions for FPU coprocessor in ITYPE register */
+#define FPU_DISABLE_EXCEPTION (0x1 << ITYPE_offSTYPE)
+#define FPU_EXCEPTION (0x2 << ITYPE_offSTYPE)
+#define FPU_CPID 0 /* The Co-Processor ID of FPU is 0 */
+
#define NDS32_VECTOR_mskNONEXCEPTION 0x78
#define NDS32_VECTOR_offEXCEPTION 8
#define NDS32_VECTOR_offINTERRUPT 9
@@ -926,6 +931,7 @@
#define FPCSR_mskDNIT ( 0x1 << FPCSR_offDNIT )
#define FPCSR_mskRIT ( 0x1 << FPCSR_offRIT )
#define FPCSR_mskALL (FPCSR_mskIVO | FPCSR_mskDBZ | FPCSR_mskOVF | FPCSR_mskUDF | FPCSR_mskIEX)
+#define FPCSR_mskALLE_NO_UDFE (FPCSR_mskIVOE | FPCSR_mskDBZE | FPCSR_mskOVFE | FPCSR_mskIEXE)
#define FPCSR_mskALLE (FPCSR_mskIVOE | FPCSR_mskDBZE | FPCSR_mskOVFE | FPCSR_mskUDFE | FPCSR_mskIEXE)
#define FPCSR_mskALLT (FPCSR_mskIVOT | FPCSR_mskDBZT | FPCSR_mskOVFT | FPCSR_mskUDFT | FPCSR_mskIEXT |FPCSR_mskDNIT | FPCSR_mskRIT)
@@ -946,6 +952,15 @@
#define FPCFG_mskIMVER ( 0x1F << FPCFG_offIMVER )
#define FPCFG_mskAVER ( 0x1F << FPCFG_offAVER )
+/* 8 Single precision or 4 double precision registers are available */
+#define SP8_DP4_reg 0
+/* 16 Single precision or 8 double precision registers are available */
+#define SP16_DP8_reg 1
+/* 32 Single precision or 16 double precision registers are available */
+#define SP32_DP16_reg 2
+/* 32 Single precision or 32 double precision registers are available */
+#define SP32_DP32_reg 3
+
/******************************************************************************
* fucpr: FUCOP_CTL (FPU and Coprocessor Enable Control Register)
*****************************************************************************/
diff --git a/arch/nds32/include/asm/fpu.h b/arch/nds32/include/asm/fpu.h
new file mode 100644
index 0000000..3132400
--- /dev/null
+++ b/arch/nds32/include/asm/fpu.h
@@ -0,0 +1,116 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2005-2018 Andes Technology Corporation */
+
+#ifndef __ASM_NDS32_FPU_H
+#define __ASM_NDS32_FPU_H
+
+#if IS_ENABLED(CONFIG_FPU)
+#ifndef __ASSEMBLY__
+#include <linux/sched/task_stack.h>
+#include <linux/preempt.h>
+#include <asm/ptrace.h>
+
+extern void save_fpu(struct task_struct *__tsk);
+extern void fpload(const struct fpu_struct *fpregs);
+extern bool do_fpu_exception(unsigned int subtype, struct pt_regs *regs);
+
+#define test_tsk_fpu(regs) (regs->fucop_ctl & FUCOP_CTL_mskCP0EN)
+
+/*
+ * Initially load the FPU with signalling NANS. This bit pattern
+ * has the property that no matter whether considered as single or as
+ * double precision, it still represents a signalling NAN.
+ */
+
+#define sNAN64 0xFFFFFFFFFFFFFFFFULL
+#define sNAN32 0xFFFFFFFFUL
+
+#define FPCSR_INIT 0x0UL
+
+extern const struct fpu_struct init_fpuregs;
+
+static inline void disable_ptreg_fpu(struct pt_regs *regs)
+{
+ regs->fucop_ctl &= ~FUCOP_CTL_mskCP0EN;
+}
+
+static inline void enable_ptreg_fpu(struct pt_regs *regs)
+{
+ regs->fucop_ctl |= FUCOP_CTL_mskCP0EN;
+}
+
+static inline void enable_fpu(void)
+{
+ unsigned long fucop_ctl;
+
+ fucop_ctl = __nds32__mfsr(NDS32_SR_FUCOP_CTL) | FUCOP_CTL_mskCP0EN;
+ __nds32__mtsr(fucop_ctl, NDS32_SR_FUCOP_CTL);
+ __nds32__isb();
+}
+
+static inline void disable_fpu(void)
+{
+ unsigned long fucop_ctl;
+
+ fucop_ctl = __nds32__mfsr(NDS32_SR_FUCOP_CTL) & ~FUCOP_CTL_mskCP0EN;
+ __nds32__mtsr(fucop_ctl, NDS32_SR_FUCOP_CTL);
+ __nds32__isb();
+}
+
+static inline void lose_fpu(void)
+{
+ preempt_disable();
+#if !IS_ENABLED(CONFIG_UNLAZY_FPU)
+ if (last_task_used_math == current) {
+#else
+ if (test_tsk_fpu(task_pt_regs(current))) {
+#endif
+ save_fpu(current);
+#if !IS_ENABLED(CONFIG_UNLAZY_FPU)
+ last_task_used_math = NULL;
+#endif
+ }
+ disable_ptreg_fpu(task_pt_regs(current));
+ preempt_enable();
+}
+
+static inline void own_fpu(void)
+{
+ preempt_disable();
+#if !IS_ENABLED(CONFIG_UNLAZY_FPU)
+ if (last_task_used_math != current) {
+#else
+ if (!test_tsk_fpu(task_pt_regs(current))) {
+#endif
+#if IS_ENABLED(CONFIG_UNLAZY_FPU)
+ fpload(¤t->thread.fpu);
+#else
+ if (last_task_used_math != NULL)
+ save_fpu(last_task_used_math);
+ fpload(¤t->thread.fpu);
+ last_task_used_math = current;
+#endif
+ }
+ enable_ptreg_fpu(task_pt_regs(current));
+ preempt_enable();
+}
+
+#if IS_ENABLED(CONFIG_UNLAZY_FPU)
+static inline void unlazy_fpu(struct task_struct *tsk)
+{
+ preempt_disable();
+ if (test_tsk_fpu(task_pt_regs(tsk)))
+ save_fpu(tsk);
+ preempt_enable();
+}
+#endif /* CONFIG_UNLAZY_FPU */
+static inline void clear_fpu(struct pt_regs *regs)
+{
+ preempt_disable();
+ if (test_tsk_fpu(regs))
+ disable_ptreg_fpu(regs);
+ preempt_enable();
+}
+#endif /* CONFIG_FPU */
+#endif /* __ASSEMBLY__ */
+#endif /* __ASM_NDS32_FPU_H */
diff --git a/arch/nds32/include/asm/processor.h b/arch/nds32/include/asm/processor.h
index 9c83caf..bf935d8 100644
--- a/arch/nds32/include/asm/processor.h
+++ b/arch/nds32/include/asm/processor.h
@@ -41,6 +41,8 @@ struct thread_struct {
unsigned long address;
unsigned long trap_no;
unsigned long error_code;
+
+ struct fpu_struct fpu;
};
#define INIT_THREAD { }
@@ -78,6 +80,11 @@ struct thread_struct {
/* Free all resources held by a thread. */
#define release_thread(thread) do { } while(0)
+#if IS_ENABLED(CONFIG_FPU)
+#if !IS_ENABLED(CONFIG_UNLAZU_FPU)
+extern struct task_struct *last_task_used_math;
+#endif
+#endif
/* Prepare to copy thread state - unlazy all lazy status */
#define prepare_to_copy(tsk) do { } while (0)
diff --git a/arch/nds32/include/uapi/asm/sigcontext.h b/arch/nds32/include/uapi/asm/sigcontext.h
index 00567b2..1257a78 100644
--- a/arch/nds32/include/uapi/asm/sigcontext.h
+++ b/arch/nds32/include/uapi/asm/sigcontext.h
@@ -9,6 +9,10 @@
* before the signal handler was invoked. Note: only add new entries
* to the end of the structure.
*/
+struct fpu_struct {
+ unsigned long long fd_regs[32];
+ unsigned long fpcsr;
+};
struct zol_struct {
unsigned long nds32_lc; /* $LC */
@@ -54,6 +58,7 @@ struct sigcontext {
unsigned long fault_address;
unsigned long used_math_flag;
/* FPU Registers */
+ struct fpu_struct fpu;
struct zol_struct zol;
};
diff --git a/arch/nds32/kernel/Makefile b/arch/nds32/kernel/Makefile
index 27cded3..42eb5b2 100644
--- a/arch/nds32/kernel/Makefile
+++ b/arch/nds32/kernel/Makefile
@@ -14,11 +14,20 @@ obj-y := ex-entry.o ex-exit.o ex-scall.o irq.o \
obj-$(CONFIG_MODULES) += nds32_ksyms.o module.o
obj-$(CONFIG_STACKTRACE) += stacktrace.o
+obj-$(CONFIG_FPU) += fpu.o
obj-$(CONFIG_OF) += devtree.o
obj-$(CONFIG_CACHE_L2) += atl2c.o
extra-y := head.o vmlinux.lds
+CFLAGS_fpu.o += \
+ $(shell $(CC) -E -dM -xc /dev/null | \
+ grep -o -m1 NDS32_EXT_FPU_SP | \
+ sed -e 's/NDS32_EXT_FPU_SP/-mext-fpu-sp/') \
+ $(shell $(CC) -E -dM -xc /dev/null | \
+ grep -o -m1 NDS32_EXT_FPU_DP | \
+ sed -e 's/NDS32_EXT_FPU_DP/-mext-fpu-dp/')
+
obj-y += vdso/
diff --git a/arch/nds32/kernel/ex-entry.S b/arch/nds32/kernel/ex-entry.S
index 21a1440..97d3430 100644
--- a/arch/nds32/kernel/ex-entry.S
+++ b/arch/nds32/kernel/ex-entry.S
@@ -18,9 +18,18 @@
.macro save_user_regs
+#if defined(CONFIG_FPU)
+ mfsr $p0, $FUCOP_CTL
+ smw.adm $p0, [$sp], $p0, #0x1
+ bclr $p0, $p0, #FUCOP_CTL_offCP0EN
+ mtsr $p0, $FUCOP_CTL
+ /* move $SP to the bottom of pt_regs */
+ addi $sp, $sp, -FUCOP_CTL_OFFSET
+#else
smw.adm $sp, [$sp], $sp, #0x1
/* move $SP to the bottom of pt_regs */
addi $sp, $sp, -OSP_OFFSET
+#endif
/* push $r0 ~ $r25 */
smw.bim $r0, [$sp], $r25
diff --git a/arch/nds32/kernel/ex-exit.S b/arch/nds32/kernel/ex-exit.S
index f00af92..304267e 100644
--- a/arch/nds32/kernel/ex-exit.S
+++ b/arch/nds32/kernel/ex-exit.S
@@ -22,10 +22,14 @@
.macro restore_user_regs_first
setgie.d
isb
-
+#if defined(CONFIG_FPU)
+ addi $sp, $sp, OSP_OFFSET
+ lmw.adm $r12, [$sp], $r25, #0x0
+ mtsr $r25, $FUCOP_CTL
+#else
addi $sp, $sp, FUCOP_CTL_OFFSET
-
lmw.adm $r12, [$sp], $r24, #0x0
+#endif
mtsr $r12, $SP_USR
mtsr $r13, $IPC
#ifdef CONFIG_HWZOL
diff --git a/arch/nds32/kernel/ex-scall.S b/arch/nds32/kernel/ex-scall.S
index 36aa87e..3b4993d 100644
--- a/arch/nds32/kernel/ex-scall.S
+++ b/arch/nds32/kernel/ex-scall.S
@@ -19,11 +19,13 @@ ENTRY(__switch_to)
la $p0, __entry_task
sw $r1, [$p0]
- move $p1, $r0
- addi $p1, $p1, #THREAD_CPU_CONTEXT
+ addi $p1, $r0, #THREAD_CPU_CONTEXT
smw.bi $r6, [$p1], $r14, #0xb ! push r6~r14, fp, lp, sp
move $r25, $r1
- addi $r1, $r1, #THREAD_CPU_CONTEXT
+#if defined(CONFIG_FPU)
+ call _switch
+#endif
+ addi $r1, $r25, #THREAD_CPU_CONTEXT
lmw.bi $r6, [$r1], $r14, #0xb ! pop r6~r14, fp, lp, sp
ret
diff --git a/arch/nds32/kernel/fpu.c b/arch/nds32/kernel/fpu.c
new file mode 100644
index 0000000..7353746
--- /dev/null
+++ b/arch/nds32/kernel/fpu.c
@@ -0,0 +1,219 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2005-2018 Andes Technology Corporation
+
+#include <linux/sched.h>
+#include <linux/signal.h>
+#include <linux/sched/signal.h>
+#include <asm/processor.h>
+#include <asm/user.h>
+#include <asm/io.h>
+#include <asm/bitfield.h>
+#include <asm/fpu.h>
+
+const struct fpu_struct init_fpuregs = {
+ .fd_regs = {[0 ... 31] = sNAN64},
+ .fpcsr = FPCSR_INIT
+};
+
+void save_fpu(struct task_struct *tsk)
+{
+ unsigned int fpcfg, fpcsr;
+
+ enable_fpu();
+ fpcfg = ((__nds32__fmfcfg() & FPCFG_mskFREG) >> FPCFG_offFREG);
+ switch (fpcfg) {
+ case SP32_DP32_reg:
+ asm volatile ("fsdi $fd31, [%0+0xf8]\n\t"
+ "fsdi $fd30, [%0+0xf0]\n\t"
+ "fsdi $fd29, [%0+0xe8]\n\t"
+ "fsdi $fd28, [%0+0xe0]\n\t"
+ "fsdi $fd27, [%0+0xd8]\n\t"
+ "fsdi $fd26, [%0+0xd0]\n\t"
+ "fsdi $fd25, [%0+0xc8]\n\t"
+ "fsdi $fd24, [%0+0xc0]\n\t"
+ "fsdi $fd23, [%0+0xb8]\n\t"
+ "fsdi $fd22, [%0+0xb0]\n\t"
+ "fsdi $fd21, [%0+0xa8]\n\t"
+ "fsdi $fd20, [%0+0xa0]\n\t"
+ "fsdi $fd19, [%0+0x98]\n\t"
+ "fsdi $fd18, [%0+0x90]\n\t"
+ "fsdi $fd17, [%0+0x88]\n\t"
+ "fsdi $fd16, [%0+0x80]\n\t"
+ : /* no output */
+ : "r" (&tsk->thread.fpu)
+ : "memory");
+ /* fall through */
+ case SP32_DP16_reg:
+ asm volatile ("fsdi $fd15, [%0+0x78]\n\t"
+ "fsdi $fd14, [%0+0x70]\n\t"
+ "fsdi $fd13, [%0+0x68]\n\t"
+ "fsdi $fd12, [%0+0x60]\n\t"
+ "fsdi $fd11, [%0+0x58]\n\t"
+ "fsdi $fd10, [%0+0x50]\n\t"
+ "fsdi $fd9, [%0+0x48]\n\t"
+ "fsdi $fd8, [%0+0x40]\n\t"
+ : /* no output */
+ : "r" (&tsk->thread.fpu)
+ : "memory");
+ /* fall through */
+ case SP16_DP8_reg:
+ asm volatile ("fsdi $fd7, [%0+0x38]\n\t"
+ "fsdi $fd6, [%0+0x30]\n\t"
+ "fsdi $fd5, [%0+0x28]\n\t"
+ "fsdi $fd4, [%0+0x20]\n\t"
+ : /* no output */
+ : "r" (&tsk->thread.fpu)
+ : "memory");
+ /* fall through */
+ case SP8_DP4_reg:
+ asm volatile ("fsdi $fd3, [%1+0x18]\n\t"
+ "fsdi $fd2, [%1+0x10]\n\t"
+ "fsdi $fd1, [%1+0x8]\n\t"
+ "fsdi $fd0, [%1+0x0]\n\t"
+ "fmfcsr %0\n\t"
+ "swi %0, [%1+0x100]\n\t"
+ : "=&r" (fpcsr)
+ : "r"(&tsk->thread.fpu)
+ : "memory");
+ }
+ disable_fpu();
+}
+
+void fpload(const struct fpu_struct *fpregs)
+{
+ unsigned int fpcfg, fpcsr;
+
+ enable_fpu();
+ fpcfg = ((__nds32__fmfcfg() & FPCFG_mskFREG) >> FPCFG_offFREG);
+ switch (fpcfg) {
+ case SP32_DP32_reg:
+ asm volatile ("fldi $fd31, [%0+0xf8]\n\t"
+ "fldi $fd30, [%0+0xf0]\n\t"
+ "fldi $fd29, [%0+0xe8]\n\t"
+ "fldi $fd28, [%0+0xe0]\n\t"
+ "fldi $fd27, [%0+0xd8]\n\t"
+ "fldi $fd26, [%0+0xd0]\n\t"
+ "fldi $fd25, [%0+0xc8]\n\t"
+ "fldi $fd24, [%0+0xc0]\n\t"
+ "fldi $fd23, [%0+0xb8]\n\t"
+ "fldi $fd22, [%0+0xb0]\n\t"
+ "fldi $fd21, [%0+0xa8]\n\t"
+ "fldi $fd20, [%0+0xa0]\n\t"
+ "fldi $fd19, [%0+0x98]\n\t"
+ "fldi $fd18, [%0+0x90]\n\t"
+ "fldi $fd17, [%0+0x88]\n\t"
+ "fldi $fd16, [%0+0x80]\n\t"
+ : /* no output */
+ : "r" (fpregs));
+ /* fall through */
+ case SP32_DP16_reg:
+ asm volatile ("fldi $fd15, [%0+0x78]\n\t"
+ "fldi $fd14, [%0+0x70]\n\t"
+ "fldi $fd13, [%0+0x68]\n\t"
+ "fldi $fd12, [%0+0x60]\n\t"
+ "fldi $fd11, [%0+0x58]\n\t"
+ "fldi $fd10, [%0+0x50]\n\t"
+ "fldi $fd9, [%0+0x48]\n\t"
+ "fldi $fd8, [%0+0x40]\n\t"
+ : /* no output */
+ : "r" (fpregs));
+ /* fall through */
+ case SP16_DP8_reg:
+ asm volatile ("fldi $fd7, [%0+0x38]\n\t"
+ "fldi $fd6, [%0+0x30]\n\t"
+ "fldi $fd5, [%0+0x28]\n\t"
+ "fldi $fd4, [%0+0x20]\n\t"
+ : /* no output */
+ : "r" (fpregs));
+ /* fall through */
+ case SP8_DP4_reg:
+ asm volatile ("fldi $fd3, [%1+0x18]\n\t"
+ "fldi $fd2, [%1+0x10]\n\t"
+ "fldi $fd1, [%1+0x8]\n\t"
+ "fldi $fd0, [%1+0x0]\n\t"
+ "lwi %0, [%1+0x100]\n\t"
+ "fmtcsr %0\n\t":"=&r" (fpcsr)
+ : "r"(fpregs));
+ }
+ disable_fpu();
+}
+
+inline void do_fpu_context_switch(struct pt_regs *regs)
+{
+ /* Enable to use FPU. */
+
+ if (!user_mode(regs)) {
+ pr_err("BUG: FPU is used in kernel mode.\n");
+ BUG();
+ return;
+ }
+
+ enable_ptreg_fpu(regs);
+#ifndef CONFIG_UNLAZY_FPU //Lazy FPU is used
+ if (last_task_used_math == current)
+ return;
+ if (last_task_used_math != NULL)
+ /* Other processes fpu state, save away */
+ save_fpu(last_task_used_math);
+ last_task_used_math = current;
+#endif
+ if (used_math()) {
+ fpload(¤t->thread.fpu);
+ } else {
+ /* First time FPU user. */
+ fpload(&init_fpuregs);
+ set_used_math();
+ }
+
+}
+
+inline void fill_sigfpe_signo(unsigned int fpcsr, int *signo)
+{
+ if (fpcsr & FPCSR_mskOVFT)
+ *signo = FPE_FLTOVF;
+ else if (fpcsr & FPCSR_mskUDFT)
+ *signo = FPE_FLTUND;
+ else if (fpcsr & FPCSR_mskIVOT)
+ *signo = FPE_FLTINV;
+ else if (fpcsr & FPCSR_mskDBZT)
+ *signo = FPE_FLTDIV;
+ else if (fpcsr & FPCSR_mskIEXT)
+ *signo = FPE_FLTRES;
+}
+
+inline void handle_fpu_exception(struct pt_regs *regs)
+{
+ unsigned int fpcsr;
+ int si_code = 0, si_signo = SIGFPE;
+
+ lose_fpu();
+ fpcsr = current->thread.fpu.fpcsr;
+
+ if (fpcsr & FPCSR_mskRIT) {
+ if (!user_mode(regs))
+ do_exit(SIGILL);
+ si_signo = SIGILL;
+ show_regs(regs);
+ si_code = ILL_COPROC;
+ } else
+ fill_sigfpe_signo(fpcsr, &si_code);
+ force_sig_fault(si_signo, si_code,
+ (void __user *)instruction_pointer(regs), current);
+}
+
+bool do_fpu_exception(unsigned int subtype, struct pt_regs *regs)
+{
+ int done = true;
+ /* Coprocessor disabled exception */
+ if (subtype == FPU_DISABLE_EXCEPTION) {
+ preempt_disable();
+ do_fpu_context_switch(regs);
+ preempt_enable();
+ }
+ /* Coprocessor exception such as underflow and overflow */
+ else if (subtype == FPU_EXCEPTION)
+ handle_fpu_exception(regs);
+ else
+ done = false;
+ return done;
+}
diff --git a/arch/nds32/kernel/process.c b/arch/nds32/kernel/process.c
index 65fda98..4841e32 100644
--- a/arch/nds32/kernel/process.c
+++ b/arch/nds32/kernel/process.c
@@ -9,15 +9,16 @@
#include <linux/uaccess.h>
#include <asm/elf.h>
#include <asm/proc-fns.h>
+#include <asm/fpu.h>
#include <linux/ptrace.h>
#include <linux/reboot.h>
-extern void setup_mm_for_reboot(char mode);
-#ifdef CONFIG_PROC_FS
-struct proc_dir_entry *proc_dir_cpu;
-EXPORT_SYMBOL(proc_dir_cpu);
+#if !IS_ENABLED(CONFIG_UNLAZY_FPU)
+struct task_struct *last_task_used_math;
#endif
+extern void setup_mm_for_reboot(char mode);
+
extern inline void arch_reset(char mode)
{
if (mode == 's') {
@@ -125,15 +126,31 @@ void show_regs(struct pt_regs *regs)
EXPORT_SYMBOL(show_regs);
+void exit_thread(struct task_struct *tsk)
+{
+#if defined(CONFIG_FPU) && !defined(CONFIG_UNLAZY_FPU)
+ if (last_task_used_math == tsk)
+ last_task_used_math = NULL;
+#endif
+}
+
void flush_thread(void)
{
+#if defined(CONFIG_FPU)
+ clear_fpu(task_pt_regs(current));
+ clear_used_math();
+# ifndef CONFIG_UNLAZY_FPU
+ if (last_task_used_math == current)
+ last_task_used_math = NULL;
+# endif
+#endif
}
DEFINE_PER_CPU(struct task_struct *, __entry_task);
asmlinkage void ret_from_fork(void) __asm__("ret_from_fork");
int copy_thread(unsigned long clone_flags, unsigned long stack_start,
- unsigned long stk_sz, struct task_struct *p)
+ unsigned long stk_sz, struct task_struct *p)
{
struct pt_regs *childregs = task_pt_regs(p);
@@ -159,6 +176,22 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start,
p->thread.cpu_context.pc = (unsigned long)ret_from_fork;
p->thread.cpu_context.sp = (unsigned long)childregs;
+#if IS_ENABLED(CONFIG_FPU)
+ if (used_math()) {
+# if IS_ENABLED(CONFIG_UNLAZY_FPU)
+ unlazy_fpu(current);
+# else
+ preempt_disable();
+ if (last_task_used_math == current)
+ save_fpu(current);
+ preempt_enable();
+# endif
+ p->thread.fpu = current->thread.fpu;
+ clear_fpu(task_pt_regs(p));
+ set_stopped_child_used_math(p);
+ }
+#endif
+
#ifdef CONFIG_HWZOL
childregs->lb = 0;
childregs->le = 0;
@@ -168,12 +201,33 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start,
return 0;
}
+#if IS_ENABLED(CONFIG_FPU)
+struct task_struct *_switch(struct task_struct *prev, struct task_struct *next)
+{
+#if IS_ENABLED(CONFIG_UNLAZY_FPU)
+ unlazy_fpu(prev);
+#endif
+ if (!(next->flags & PF_KTHREAD))
+ clear_fpu(task_pt_regs(next));
+ return prev;
+}
+#endif
+
/*
* fill in the fpe structure for a core dump...
*/
int dump_fpu(struct pt_regs *regs, elf_fpregset_t * fpu)
{
int fpvalid = 0;
+#if IS_ENABLED(CONFIG_FPU)
+ struct task_struct *tsk = current;
+
+ fpvalid = tsk_used_math(tsk);
+ if (fpvalid) {
+ lose_fpu();
+ memcpy(fpu, &tsk->thread.fpu, sizeof(*fpu));
+ }
+#endif
return fpvalid;
}
diff --git a/arch/nds32/kernel/setup.c b/arch/nds32/kernel/setup.c
index 63a1a5e..9e97e9a 100644
--- a/arch/nds32/kernel/setup.c
+++ b/arch/nds32/kernel/setup.c
@@ -16,6 +16,7 @@
#include <asm/proc-fns.h>
#include <asm/cache_info.h>
#include <asm/elf.h>
+#include <asm/fpu.h>
#include <nds32_intrinsic.h>
#define HWCAP_MFUSR_PC 0x000001
@@ -137,6 +138,10 @@ static void __init dump_cpu_info(int cpu)
(aliasing_num - 1) << PAGE_SHIFT;
}
#endif
+#ifdef CONFIG_FPU
+ /* Disable fpu and enable when it is used. */
+ disable_fpu();
+#endif
}
static void __init setup_cpuinfo(void)
diff --git a/arch/nds32/kernel/signal.c b/arch/nds32/kernel/signal.c
index 5d01f6e..ecf859f 100644
--- a/arch/nds32/kernel/signal.c
+++ b/arch/nds32/kernel/signal.c
@@ -12,6 +12,7 @@
#include <asm/cacheflush.h>
#include <asm/ucontext.h>
#include <asm/unistd.h>
+#include <asm/fpu.h>
#include <asm/ptrace.h>
#include <asm/vdso.h>
@@ -20,6 +21,66 @@ struct rt_sigframe {
struct siginfo info;
struct ucontext uc;
};
+#if IS_ENABLED(CONFIG_FPU)
+static inline int restore_sigcontext_fpu(struct pt_regs *regs,
+ struct sigcontext __user *sc)
+{
+ struct task_struct *tsk = current;
+ unsigned long used_math_flag;
+ int ret = 0;
+
+ if (!(__nds32__mfsr(NDS32_SR_FUCOP_EXIST) & FUCOP_EXIST_mskCP0ISFPU))
+ return 0;
+
+ __get_user_error(used_math_flag, &sc->used_math_flag, ret);
+
+ if (!used_math_flag)
+ return 0;
+
+ set_used_math();
+
+#if IS_ENABLED(CONFIG_UNLAZY_FPU)
+ clear_fpu(regs);
+#else
+ preempt_disable();
+ if (current == last_task_used_math) {
+ last_task_used_math = NULL;
+ disable_ptreg_fpu(regs);
+ }
+ preempt_enable();
+#endif
+
+ return __copy_from_user(&tsk->thread.fpu, &sc->fpu,
+ sizeof(struct fpu_struct));
+}
+
+static inline int setup_sigcontext_fpu(struct pt_regs *regs,
+ struct sigcontext __user *sc)
+{
+ struct task_struct *tsk = current;
+ int ret = 0;
+
+ if (!(__nds32__mfsr(NDS32_SR_FUCOP_EXIST) & FUCOP_EXIST_mskCP0ISFPU))
+ return 0;
+
+ if (!used_math())
+ return 0;
+
+ __put_user_error(used_math(), &sc->used_math_flag, ret);
+
+ preempt_disable();
+#if IS_ENABLED(CONFIG_UNLAZY_FPU)
+ unlazy_fpu(tsk);
+#else
+ if (last_task_used_math == tsk)
+ save_fpu(last_task_used_math);
+#endif
+ ret = __copy_to_user(&sc->fpu, &tsk->thread.fpu,
+ sizeof(struct fpu_struct));
+ preempt_enable();
+ return ret;
+}
+#endif
static int restore_sigframe(struct pt_regs *regs,
struct rt_sigframe __user * sf)
@@ -69,7 +130,9 @@ static int restore_sigframe(struct pt_regs *regs,
__get_user_error(regs->le, &sf->uc.uc_mcontext.zol.nds32_le, err);
__get_user_error(regs->lb, &sf->uc.uc_mcontext.zol.nds32_lb, err);
#endif
-
+#if IS_ENABLED(CONFIG_FPU)
+ err |= restore_sigcontext_fpu(regs, &sf->uc.uc_mcontext);
+#endif
/*
* Avoid sys_rt_sigreturn() restarting.
*/
@@ -153,6 +216,9 @@ asmlinkage long sys_rt_sigreturn(struct pt_regs *regs)
__put_user_error(regs->le, &sf->uc.uc_mcontext.zol.nds32_le, err);
__put_user_error(regs->lb, &sf->uc.uc_mcontext.zol.nds32_lb, err);
#endif
+#if IS_ENABLED(CONFIG_FPU)
+ err |= setup_sigcontext_fpu(regs, &sf->uc.uc_mcontext);
+#endif
__put_user_error(current->thread.trap_no, &sf->uc.uc_mcontext.trap_no,
err);
diff --git a/arch/nds32/kernel/traps.c b/arch/nds32/kernel/traps.c
index 1496aab..5aa7c17 100644
--- a/arch/nds32/kernel/traps.c
+++ b/arch/nds32/kernel/traps.c
@@ -12,6 +12,7 @@
#include <asm/proc-fns.h>
#include <asm/unistd.h>
+#include <asm/fpu.h>
#include <linux/ptrace.h>
#include <nds32_intrinsic.h>
@@ -357,6 +358,21 @@ void do_dispatch_general(unsigned long entry, unsigned long addr,
} else if (type == ETYPE_RESERVED_INSTRUCTION) {
/* Reserved instruction */
do_revinsn(regs);
+ } else if (type == ETYPE_COPROCESSOR) {
+ /* Coprocessor */
+#if IS_ENABLED(CONFIG_FPU)
+ unsigned int fucop_exist = __nds32__mfsr(NDS32_SR_FUCOP_EXIST);
+ unsigned int cpid = ((itype & ITYPE_mskCPID) >> ITYPE_offCPID);
+
+ if ((cpid == FPU_CPID) &&
+ (fucop_exist & FUCOP_EXIST_mskCP0ISFPU)) {
+ unsigned int subtype = (itype & ITYPE_mskSTYPE);
+
+ if (true == do_fpu_exception(subtype, regs))
+ return;
+ }
+#endif
+ unhandled_exceptions(entry, addr, type, regs);
} else if (type == ETYPE_TRAP && swid == SWID_RAISE_INTERRUPT_LEVEL) {
/* trap, used on v3 EDM target debugging workaround */
/*
--
1.7.1
^ permalink raw reply related [flat|nested] 9+ messages in thread
* [PATCH v2 2/5] nds32: Support FP emulation
2018-10-11 2:20 [PATCH v2 0/5] nds32 FPU port Vincent Chen
2018-10-11 2:20 ` [PATCH v2 1/5] nds32: " Vincent Chen
@ 2018-10-11 2:20 ` Vincent Chen
2018-10-11 2:20 ` [PATCH v2 3/5] nds32: support denormalized result through FP emulator Vincent Chen
` (2 subsequent siblings)
4 siblings, 0 replies; 9+ messages in thread
From: Vincent Chen @ 2018-10-11 2:20 UTC (permalink / raw)
To: green.hu, linux-kernel, arnd, deanbo422; +Cc: Vincent Chen
Andes FPU hardware does not support denormalized number handling.
From Andes FPU spec, FPU generates a denorm input to require kernel
to deal with this instrution operation when encountering a denormalized
operand. Hence an emulator for nds32 FPU ISA in kernel is needed to
satisfy the requirement.
Signed-off-by: Vincent Chen <vincentc@andestech.com>
---
arch/nds32/Makefile | 1 +
arch/nds32/include/asm/fpu.h | 1 +
arch/nds32/include/asm/fpuemu.h | 32 +++
arch/nds32/include/asm/nds32_fpu_inst.h | 109 ++++++++++
arch/nds32/include/asm/sfp-machine.h | 158 ++++++++++++++
arch/nds32/kernel/fpu.c | 31 +++-
arch/nds32/math-emu/Makefile | 7 +
arch/nds32/math-emu/faddd.c | 24 ++
arch/nds32/math-emu/fadds.c | 24 ++
arch/nds32/math-emu/fcmpd.c | 24 ++
arch/nds32/math-emu/fcmps.c | 24 ++
arch/nds32/math-emu/fd2s.c | 22 ++
arch/nds32/math-emu/fdivd.c | 27 +++
arch/nds32/math-emu/fdivs.c | 26 +++
arch/nds32/math-emu/fmuld.c | 23 ++
arch/nds32/math-emu/fmuls.c | 23 ++
arch/nds32/math-emu/fnegd.c | 21 ++
arch/nds32/math-emu/fnegs.c | 21 ++
arch/nds32/math-emu/fpuemu.c | 361 +++++++++++++++++++++++++++++++
arch/nds32/math-emu/fs2d.c | 23 ++
arch/nds32/math-emu/fsqrtd.c | 21 ++
arch/nds32/math-emu/fsqrts.c | 21 ++
arch/nds32/math-emu/fsubd.c | 27 +++
arch/nds32/math-emu/fsubs.c | 27 +++
24 files changed, 1073 insertions(+), 5 deletions(-)
create mode 100644 arch/nds32/include/asm/fpuemu.h
create mode 100644 arch/nds32/include/asm/nds32_fpu_inst.h
create mode 100644 arch/nds32/include/asm/sfp-machine.h
create mode 100644 arch/nds32/math-emu/Makefile
create mode 100644 arch/nds32/math-emu/faddd.c
create mode 100644 arch/nds32/math-emu/fadds.c
create mode 100644 arch/nds32/math-emu/fcmpd.c
create mode 100644 arch/nds32/math-emu/fcmps.c
create mode 100644 arch/nds32/math-emu/fd2s.c
create mode 100644 arch/nds32/math-emu/fdivd.c
create mode 100644 arch/nds32/math-emu/fdivs.c
create mode 100644 arch/nds32/math-emu/fmuld.c
create mode 100644 arch/nds32/math-emu/fmuls.c
create mode 100644 arch/nds32/math-emu/fnegd.c
create mode 100644 arch/nds32/math-emu/fnegs.c
create mode 100644 arch/nds32/math-emu/fpuemu.c
create mode 100644 arch/nds32/math-emu/fs2d.c
create mode 100644 arch/nds32/math-emu/fsqrtd.c
create mode 100644 arch/nds32/math-emu/fsqrts.c
create mode 100644 arch/nds32/math-emu/fsubd.c
create mode 100644 arch/nds32/math-emu/fsubs.c
diff --git a/arch/nds32/Makefile b/arch/nds32/Makefile
index 599ee62..e034e30 100644
--- a/arch/nds32/Makefile
+++ b/arch/nds32/Makefile
@@ -36,6 +36,7 @@ export TEXTADDR
# If we have a machine-specific directory, then include it in the build.
core-y += arch/nds32/kernel/ arch/nds32/mm/
+core-$(CONFIG_FPU) += arch/nds32/math-emu/
libs-y += arch/nds32/lib/
ifneq '$(CONFIG_NDS32_BUILTIN_DTB)' '""'
diff --git a/arch/nds32/include/asm/fpu.h b/arch/nds32/include/asm/fpu.h
index 3132400..10df5f0 100644
--- a/arch/nds32/include/asm/fpu.h
+++ b/arch/nds32/include/asm/fpu.h
@@ -13,6 +13,7 @@
extern void save_fpu(struct task_struct *__tsk);
extern void fpload(const struct fpu_struct *fpregs);
extern bool do_fpu_exception(unsigned int subtype, struct pt_regs *regs);
+extern int do_fpuemu(struct pt_regs *regs, struct fpu_struct *fpu);
#define test_tsk_fpu(regs) (regs->fucop_ctl & FUCOP_CTL_mskCP0EN)
diff --git a/arch/nds32/include/asm/fpuemu.h b/arch/nds32/include/asm/fpuemu.h
new file mode 100644
index 0000000..c4bd0c7
--- /dev/null
+++ b/arch/nds32/include/asm/fpuemu.h
@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2005-2018 Andes Technology Corporation */
+
+#ifndef __ARCH_NDS32_FPUEMU_H
+#define __ARCH_NDS32_FPUEMU_H
+
+/*
+ * single precision
+ */
+
+void fadds(void *ft, void *fa, void *fb);
+void fsubs(void *ft, void *fa, void *fb);
+void fmuls(void *ft, void *fa, void *fb);
+void fdivs(void *ft, void *fa, void *fb);
+void fs2d(void *ft, void *fa);
+void fsqrts(void *ft, void *fa);
+void fnegs(void *ft, void *fa);
+int fcmps(void *ft, void *fa, void *fb, int cop);
+
+/*
+ * double precision
+ */
+void faddd(void *ft, void *fa, void *fb);
+void fsubd(void *ft, void *fa, void *fb);
+void fmuld(void *ft, void *fa, void *fb);
+void fdivd(void *ft, void *fa, void *fb);
+void fsqrtd(void *ft, void *fa);
+void fd2s(void *ft, void *fa);
+void fnegd(void *ft, void *fa);
+int fcmpd(void *ft, void *fa, void *fb, int cop);
+
+#endif /* __ARCH_NDS32_FPUEMU_H */
diff --git a/arch/nds32/include/asm/nds32_fpu_inst.h b/arch/nds32/include/asm/nds32_fpu_inst.h
new file mode 100644
index 0000000..1e4b86a
--- /dev/null
+++ b/arch/nds32/include/asm/nds32_fpu_inst.h
@@ -0,0 +1,109 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2005-2018 Andes Technology Corporation */
+
+#ifndef __NDS32_FPU_INST_H
+#define __NDS32_FPU_INST_H
+
+#define cop0_op 0x35
+
+/*
+ * COP0 field of opcodes.
+ */
+#define fs1_op 0x0
+#define fs2_op 0x4
+#define fd1_op 0x8
+#define fd2_op 0xc
+
+/*
+ * FS1 opcode.
+ */
+enum fs1 {
+ fadds_op, fsubs_op, fcpynss_op, fcpyss_op,
+ fmadds_op, fmsubs_op, fcmovns_op, fcmovzs_op,
+ fnmadds_op, fnmsubs_op,
+ fmuls_op = 0xc, fdivs_op,
+ fs1_f2op_op = 0xf
+};
+
+/*
+ * FS1/F2OP opcode.
+ */
+enum fs1_f2 {
+ fs2d_op, fsqrts_op,
+ fui2s_op = 0x8, fsi2s_op = 0xc,
+ fs2ui_op = 0x10, fs2ui_z_op = 0x14,
+ fs2si_op = 0x18, fs2si_z_op = 0x1c
+};
+
+/*
+ * FS2 opcode.
+ */
+enum fs2 {
+ fcmpeqs_op, fcmpeqs_e_op, fcmplts_op, fcmplts_e_op,
+ fcmples_op, fcmples_e_op, fcmpuns_op, fcmpuns_e_op
+};
+
+/*
+ * FD1 opcode.
+ */
+enum fd1 {
+ faddd_op, fsubd_op, fcpynsd_op, fcpysd_op,
+ fmaddd_op, fmsubd_op, fcmovnd_op, fcmovzd_op,
+ fnmaddd_op, fnmsubd_op,
+ fmuld_op = 0xc, fdivd_op, fd1_f2op_op = 0xf
+};
+
+/*
+ * FD1/F2OP opcode.
+ */
+enum fd1_f2 {
+ fd2s_op, fsqrtd_op,
+ fui2d_op = 0x8, fsi2d_op = 0xc,
+ fd2ui_op = 0x10, fd2ui_z_op = 0x14,
+ fd2si_op = 0x18, fd2si_z_op = 0x1c
+};
+
+/*
+ * FD2 opcode.
+ */
+enum fd2 {
+ fcmpeqd_op, fcmpeqd_e_op, fcmpltd_op, fcmpltd_e_op,
+ fcmpled_op, fcmpled_e_op, fcmpund_op, fcmpund_e_op
+};
+
+#define NDS32Insn(x) x
+
+#define I_OPCODE_off 25
+#define NDS32Insn_OPCODE(x) (NDS32Insn(x) >> I_OPCODE_off)
+
+#define I_OPCODE_offRt 20
+#define I_OPCODE_mskRt (0x1fUL << I_OPCODE_offRt)
+#define NDS32Insn_OPCODE_Rt(x) \
+ ((NDS32Insn(x) & I_OPCODE_mskRt) >> I_OPCODE_offRt)
+
+#define I_OPCODE_offRa 15
+#define I_OPCODE_mskRa (0x1fUL << I_OPCODE_offRa)
+#define NDS32Insn_OPCODE_Ra(x) \
+ ((NDS32Insn(x) & I_OPCODE_mskRa) >> I_OPCODE_offRa)
+
+#define I_OPCODE_offRb 10
+#define I_OPCODE_mskRb (0x1fUL << I_OPCODE_offRb)
+#define NDS32Insn_OPCODE_Rb(x) \
+ ((NDS32Insn(x) & I_OPCODE_mskRb) >> I_OPCODE_offRb)
+
+#define I_OPCODE_offbit1014 10
+#define I_OPCODE_mskbit1014 (0x1fUL << I_OPCODE_offbit1014)
+#define NDS32Insn_OPCODE_BIT1014(x) \
+ ((NDS32Insn(x) & I_OPCODE_mskbit1014) >> I_OPCODE_offbit1014)
+
+#define I_OPCODE_offbit69 6
+#define I_OPCODE_mskbit69 (0xfUL << I_OPCODE_offbit69)
+#define NDS32Insn_OPCODE_BIT69(x) \
+ ((NDS32Insn(x) & I_OPCODE_mskbit69) >> I_OPCODE_offbit69)
+
+#define I_OPCODE_offCOP0 0
+#define I_OPCODE_mskCOP0 (0x3fUL << I_OPCODE_offCOP0)
+#define NDS32Insn_OPCODE_COP0(x) \
+ ((NDS32Insn(x) & I_OPCODE_mskCOP0) >> I_OPCODE_offCOP0)
+
+#endif /* __NDS32_FPU_INST_H */
diff --git a/arch/nds32/include/asm/sfp-machine.h b/arch/nds32/include/asm/sfp-machine.h
new file mode 100644
index 0000000..b1a5caa
--- /dev/null
+++ b/arch/nds32/include/asm/sfp-machine.h
@@ -0,0 +1,158 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2005-2018 Andes Technology Corporation */
+
+#include <asm/bitfield.h>
+
+#define _FP_W_TYPE_SIZE 32
+#define _FP_W_TYPE unsigned long
+#define _FP_WS_TYPE signed long
+#define _FP_I_TYPE long
+
+#define __ll_B ((UWtype) 1 << (W_TYPE_SIZE / 2))
+#define __ll_lowpart(t) ((UWtype) (t) & (__ll_B - 1))
+#define __ll_highpart(t) ((UWtype) (t) >> (W_TYPE_SIZE / 2))
+
+#define _FP_MUL_MEAT_S(R, X, Y) \
+ _FP_MUL_MEAT_1_wide(_FP_WFRACBITS_S, R, X, Y, umul_ppmm)
+#define _FP_MUL_MEAT_D(R, X, Y) \
+ _FP_MUL_MEAT_2_wide(_FP_WFRACBITS_D, R, X, Y, umul_ppmm)
+#define _FP_MUL_MEAT_Q(R, X, Y) \
+ _FP_MUL_MEAT_4_wide(_FP_WFRACBITS_Q, R, X, Y, umul_ppmm)
+
+#define _FP_MUL_MEAT_DW_S(R, X, Y) \
+ _FP_MUL_MEAT_DW_1_wide(_FP_WFRACBITS_S, R, X, Y, umul_ppmm)
+#define _FP_MUL_MEAT_DW_D(R, X, Y) \
+ _FP_MUL_MEAT_DW_2_wide(_FP_WFRACBITS_D, R, X, Y, umul_ppmm)
+
+#define _FP_DIV_MEAT_S(R, X, Y) _FP_DIV_MEAT_1_udiv_norm(S, R, X, Y)
+#define _FP_DIV_MEAT_D(R, X, Y) _FP_DIV_MEAT_2_udiv(D, R, X, Y)
+
+#define _FP_NANFRAC_S ((_FP_QNANBIT_S << 1) - 1)
+#define _FP_NANFRAC_D ((_FP_QNANBIT_D << 1) - 1), -1
+#define _FP_NANFRAC_Q ((_FP_QNANBIT_Q << 1) - 1), -1, -1, -1
+#define _FP_NANSIGN_S 0
+#define _FP_NANSIGN_D 0
+#define _FP_NANSIGN_Q 0
+
+#define _FP_KEEPNANFRACP 1
+#define _FP_QNANNEGATEDP 0
+
+#define _FP_CHOOSENAN(fs, wc, R, X, Y, OP) \
+do { \
+ if ((_FP_FRAC_HIGH_RAW_##fs(X) & _FP_QNANBIT_##fs) \
+ && !(_FP_FRAC_HIGH_RAW_##fs(Y) & _FP_QNANBIT_##fs)) { \
+ R##_s = Y##_s; \
+ _FP_FRAC_COPY_##wc(R, Y); \
+ } else { \
+ R##_s = X##_s; \
+ _FP_FRAC_COPY_##wc(R, X); \
+ } \
+ R##_c = FP_CLS_NAN; \
+} while (0)
+
+#define __FPU_FPCSR (current->thread.fpu.fpcsr)
+
+/* Obtain the current rounding mode. */
+#define FP_ROUNDMODE \
+({ \
+ __FPU_FPCSR & FPCSR_mskRM; \
+})
+
+#define FP_RND_NEAREST 0
+#define FP_RND_PINF 1
+#define FP_RND_MINF 2
+#define FP_RND_ZERO 3
+
+#define FP_EX_INVALID FPCSR_mskIVO
+#define FP_EX_DIVZERO FPCSR_mskDBZ
+#define FP_EX_OVERFLOW FPCSR_mskOVF
+#define FP_EX_UNDERFLOW FPCSR_mskUDF
+#define FP_EX_INEXACT FPCSR_mskIEX
+
+#define SF_CEQ 2
+#define SF_CLT 1
+#define SF_CGT 3
+#define SF_CUN 4
+
+#include <asm/byteorder.h>
+
+#ifdef __BIG_ENDIAN__
+#define __BYTE_ORDER __BIG_ENDIAN
+#define __LITTLE_ENDIAN 0
+#else
+#define __BYTE_ORDER __LITTLE_ENDIAN
+#define __BIG_ENDIAN 0
+#endif
+
+#define abort() do { } while (0)
+#define umul_ppmm(w1, w0, u, v) \
+do { \
+ UWtype __x0, __x1, __x2, __x3; \
+ UHWtype __ul, __vl, __uh, __vh; \
+ \
+ __ul = __ll_lowpart(u); \
+ __uh = __ll_highpart(u); \
+ __vl = __ll_lowpart(v); \
+ __vh = __ll_highpart(v); \
+ \
+ __x0 = (UWtype) __ul * __vl; \
+ __x1 = (UWtype) __ul * __vh; \
+ __x2 = (UWtype) __uh * __vl; \
+ __x3 = (UWtype) __uh * __vh; \
+ \
+ __x1 += __ll_highpart(__x0); \
+ __x1 += __x2; \
+ if (__x1 < __x2) \
+ __x3 += __ll_B; \
+ \
+ (w1) = __x3 + __ll_highpart(__x1); \
+ (w0) = __ll_lowpart(__x1) * __ll_B + __ll_lowpart(__x0); \
+} while (0)
+
+#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
+do { \
+ UWtype __x; \
+ __x = (al) + (bl); \
+ (sh) = (ah) + (bh) + (__x < (al)); \
+ (sl) = __x; \
+} while (0)
+
+#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
+do { \
+ UWtype __x; \
+ __x = (al) - (bl); \
+ (sh) = (ah) - (bh) - (__x > (al)); \
+ (sl) = __x; \
+} while (0)
+
+#define udiv_qrnnd(q, r, n1, n0, d) \
+do { \
+ UWtype __d1, __d0, __q1, __q0, __r1, __r0, __m; \
+ __d1 = __ll_highpart(d); \
+ __d0 = __ll_lowpart(d); \
+ \
+ __r1 = (n1) % __d1; \
+ __q1 = (n1) / __d1; \
+ __m = (UWtype) __q1 * __d0; \
+ __r1 = __r1 * __ll_B | __ll_highpart(n0); \
+ if (__r1 < __m) { \
+ __q1--, __r1 += (d); \
+ if (__r1 >= (d)) \
+ if (__r1 < __m) \
+ __q1--, __r1 += (d); \
+ } \
+ __r1 -= __m; \
+ __r0 = __r1 % __d1; \
+ __q0 = __r1 / __d1; \
+ __m = (UWtype) __q0 * __d0; \
+ __r0 = __r0 * __ll_B | __ll_lowpart(n0); \
+ if (__r0 < __m) { \
+ __q0--, __r0 += (d); \
+ if (__r0 >= (d)) \
+ if (__r0 < __m) \
+ __q0--, __r0 += (d); \
+ } \
+ __r0 -= __m; \
+ (q) = (UWtype) __q1 * __ll_B | __q0; \
+ (r) = __r0; \
+} while (0)
diff --git a/arch/nds32/kernel/fpu.c b/arch/nds32/kernel/fpu.c
index 7353746..75f611b 100644
--- a/arch/nds32/kernel/fpu.c
+++ b/arch/nds32/kernel/fpu.c
@@ -171,10 +171,10 @@ inline void fill_sigfpe_signo(unsigned int fpcsr, int *signo)
{
if (fpcsr & FPCSR_mskOVFT)
*signo = FPE_FLTOVF;
- else if (fpcsr & FPCSR_mskUDFT)
- *signo = FPE_FLTUND;
else if (fpcsr & FPCSR_mskIVOT)
*signo = FPE_FLTINV;
+ else if (fpcsr & FPCSR_mskUDFT)
+ *signo = FPE_FLTUND;
else if (fpcsr & FPCSR_mskDBZT)
*signo = FPE_FLTDIV;
else if (fpcsr & FPCSR_mskIEXT)
@@ -189,16 +189,37 @@ inline void handle_fpu_exception(struct pt_regs *regs)
lose_fpu();
fpcsr = current->thread.fpu.fpcsr;
- if (fpcsr & FPCSR_mskRIT) {
+ if (fpcsr & FPCSR_mskDNIT) {
+ si_signo = do_fpuemu(regs, ¤t->thread.fpu);
+ fpcsr = current->thread.fpu.fpcsr;
+ if (!si_signo)
+ goto done;
+ } else if (fpcsr & FPCSR_mskRIT) {
if (!user_mode(regs))
do_exit(SIGILL);
si_signo = SIGILL;
+ }
+
+
+ switch (si_signo) {
+ case SIGFPE:
+ fill_sigfpe_signo(fpcsr, &si_code);
+ break;
+ case SIGILL:
show_regs(regs);
si_code = ILL_COPROC;
- } else
- fill_sigfpe_signo(fpcsr, &si_code);
+ break;
+ case SIGBUS:
+ si_code = BUS_ADRERR;
+ break;
+ default:
+ break;
+ }
+
force_sig_fault(si_signo, si_code,
(void __user *)instruction_pointer(regs), current);
+done:
+ own_fpu();
}
bool do_fpu_exception(unsigned int subtype, struct pt_regs *regs)
diff --git a/arch/nds32/math-emu/Makefile b/arch/nds32/math-emu/Makefile
new file mode 100644
index 0000000..947fe0c
--- /dev/null
+++ b/arch/nds32/math-emu/Makefile
@@ -0,0 +1,7 @@
+#
+# Makefile for the Linux/nds32 kernel FPU emulation.
+#
+
+obj-y := fpuemu.o \
+ fdivd.o fmuld.o fsubd.o faddd.o fs2d.o fsqrtd.o fcmpd.o fnegs.o \
+ fdivs.o fmuls.o fsubs.o fadds.o fd2s.o fsqrts.o fcmps.o fnegd.o
diff --git a/arch/nds32/math-emu/faddd.c b/arch/nds32/math-emu/faddd.c
new file mode 100644
index 0000000..f7fd4e3
--- /dev/null
+++ b/arch/nds32/math-emu/faddd.c
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2005-2018 Andes Technology Corporation
+#include <linux/uaccess.h>
+
+#include <asm/sfp-machine.h>
+#include <math-emu/soft-fp.h>
+#include <math-emu/double.h>
+void faddd(void *ft, void *fa, void *fb)
+{
+ FP_DECL_D(A);
+ FP_DECL_D(B);
+ FP_DECL_D(R);
+ FP_DECL_EX;
+
+ FP_UNPACK_DP(A, fa);
+ FP_UNPACK_DP(B, fb);
+
+ FP_ADD_D(R, A, B);
+
+ FP_PACK_DP(ft, R);
+
+ __FPU_FPCSR |= FP_CUR_EXCEPTIONS;
+
+}
diff --git a/arch/nds32/math-emu/fadds.c b/arch/nds32/math-emu/fadds.c
new file mode 100644
index 0000000..f5af6ca
--- /dev/null
+++ b/arch/nds32/math-emu/fadds.c
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2005-2018 Andes Technology Corporation
+#include <linux/uaccess.h>
+
+#include <asm/sfp-machine.h>
+#include <math-emu/soft-fp.h>
+#include <math-emu/single.h>
+void fadds(void *ft, void *fa, void *fb)
+{
+ FP_DECL_S(A);
+ FP_DECL_S(B);
+ FP_DECL_S(R);
+ FP_DECL_EX;
+
+ FP_UNPACK_SP(A, fa);
+ FP_UNPACK_SP(B, fb);
+
+ FP_ADD_S(R, A, B);
+
+ FP_PACK_SP(ft, R);
+
+ __FPU_FPCSR |= FP_CUR_EXCEPTIONS;
+
+}
diff --git a/arch/nds32/math-emu/fcmpd.c b/arch/nds32/math-emu/fcmpd.c
new file mode 100644
index 0000000..0ea225a
--- /dev/null
+++ b/arch/nds32/math-emu/fcmpd.c
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2005-2018 Andes Technology Corporation
+#include <asm/sfp-machine.h>
+#include <math-emu/soft-fp.h>
+#include <math-emu/double.h>
+int fcmpd(void *ft, void *fa, void *fb, int cmpop)
+{
+ FP_DECL_D(A);
+ FP_DECL_D(B);
+ FP_DECL_EX;
+ long cmp;
+
+ FP_UNPACK_DP(A, fa);
+ FP_UNPACK_DP(B, fb);
+
+ FP_CMP_D(cmp, A, B, SF_CUN);
+ cmp += 2;
+ if (cmp == SF_CGT)
+ *(long *)ft = 0;
+ else
+ *(long *)ft = (cmp & cmpop) ? 1 : 0;
+
+ return 0;
+}
diff --git a/arch/nds32/math-emu/fcmps.c b/arch/nds32/math-emu/fcmps.c
new file mode 100644
index 0000000..6814807
--- /dev/null
+++ b/arch/nds32/math-emu/fcmps.c
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2005-2018 Andes Technology Corporation
+#include <asm/sfp-machine.h>
+#include <math-emu/soft-fp.h>
+#include <math-emu/single.h>
+int fcmps(void *ft, void *fa, void *fb, int cmpop)
+{
+ FP_DECL_S(A);
+ FP_DECL_S(B);
+ FP_DECL_EX;
+ long cmp;
+
+ FP_UNPACK_SP(A, fa);
+ FP_UNPACK_SP(B, fb);
+
+ FP_CMP_S(cmp, A, B, SF_CUN);
+ cmp += 2;
+ if (cmp == SF_CGT)
+ *(int *)ft = 0x0;
+ else
+ *(int *)ft = (cmp & cmpop) ? 0x1 : 0x0;
+
+ return 0;
+}
diff --git a/arch/nds32/math-emu/fd2s.c b/arch/nds32/math-emu/fd2s.c
new file mode 100644
index 0000000..1328371
--- /dev/null
+++ b/arch/nds32/math-emu/fd2s.c
@@ -0,0 +1,22 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2005-2018 Andes Technology Corporation
+#include <linux/uaccess.h>
+
+#include <asm/sfp-machine.h>
+#include <math-emu/double.h>
+#include <math-emu/single.h>
+#include <math-emu/soft-fp.h>
+void fd2s(void *ft, void *fa)
+{
+ FP_DECL_D(A);
+ FP_DECL_S(R);
+ FP_DECL_EX;
+
+ FP_UNPACK_DP(A, fa);
+
+ FP_CONV(S, D, 1, 2, R, A);
+
+ FP_PACK_SP(ft, R);
+
+ __FPU_FPCSR |= FP_CUR_EXCEPTIONS;
+}
diff --git a/arch/nds32/math-emu/fdivd.c b/arch/nds32/math-emu/fdivd.c
new file mode 100644
index 0000000..458e7e9
--- /dev/null
+++ b/arch/nds32/math-emu/fdivd.c
@@ -0,0 +1,27 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2005-2018 Andes Technology Corporation
+
+#include <linux/uaccess.h>
+#include <asm/sfp-machine.h>
+#include <math-emu/soft-fp.h>
+#include <math-emu/double.h>
+
+void fdivd(void *ft, void *fa, void *fb)
+{
+ FP_DECL_D(A);
+ FP_DECL_D(B);
+ FP_DECL_D(R);
+ FP_DECL_EX;
+
+ FP_UNPACK_DP(A, fa);
+ FP_UNPACK_DP(B, fb);
+
+ if (B_c == FP_CLS_ZERO && A_c != FP_CLS_ZERO)
+ FP_SET_EXCEPTION(FP_EX_DIVZERO);
+
+ FP_DIV_D(R, A, B);
+
+ FP_PACK_DP(ft, R);
+
+ __FPU_FPCSR |= FP_CUR_EXCEPTIONS;
+}
diff --git a/arch/nds32/math-emu/fdivs.c b/arch/nds32/math-emu/fdivs.c
new file mode 100644
index 0000000..c7d2021
--- /dev/null
+++ b/arch/nds32/math-emu/fdivs.c
@@ -0,0 +1,26 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2005-2018 Andes Technology Corporation
+#include <linux/uaccess.h>
+
+#include <asm/sfp-machine.h>
+#include <math-emu/soft-fp.h>
+#include <math-emu/single.h>
+void fdivs(void *ft, void *fa, void *fb)
+{
+ FP_DECL_S(A);
+ FP_DECL_S(B);
+ FP_DECL_S(R);
+ FP_DECL_EX;
+
+ FP_UNPACK_SP(A, fa);
+ FP_UNPACK_SP(B, fb);
+
+ if (B_c == FP_CLS_ZERO && A_c != FP_CLS_ZERO)
+ FP_SET_EXCEPTION(FP_EX_DIVZERO);
+
+ FP_DIV_S(R, A, B);
+
+ FP_PACK_SP(ft, R);
+
+ __FPU_FPCSR |= FP_CUR_EXCEPTIONS;
+}
diff --git a/arch/nds32/math-emu/fmuld.c b/arch/nds32/math-emu/fmuld.c
new file mode 100644
index 0000000..f3c77a4
--- /dev/null
+++ b/arch/nds32/math-emu/fmuld.c
@@ -0,0 +1,23 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2005-2018 Andes Technology Corporation
+#include <linux/uaccess.h>
+
+#include <asm/sfp-machine.h>
+#include <math-emu/soft-fp.h>
+#include <math-emu/double.h>
+void fmuld(void *ft, void *fa, void *fb)
+{
+ FP_DECL_D(A);
+ FP_DECL_D(B);
+ FP_DECL_D(R);
+ FP_DECL_EX;
+
+ FP_UNPACK_DP(A, fa);
+ FP_UNPACK_DP(B, fb);
+
+ FP_MUL_D(R, A, B);
+
+ FP_PACK_DP(ft, R);
+
+ __FPU_FPCSR |= FP_CUR_EXCEPTIONS;
+}
diff --git a/arch/nds32/math-emu/fmuls.c b/arch/nds32/math-emu/fmuls.c
new file mode 100644
index 0000000..cf150df
--- /dev/null
+++ b/arch/nds32/math-emu/fmuls.c
@@ -0,0 +1,23 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2005-2018 Andes Technology Corporation
+#include <linux/uaccess.h>
+
+#include <asm/sfp-machine.h>
+#include <math-emu/soft-fp.h>
+#include <math-emu/single.h>
+void fmuls(void *ft, void *fa, void *fb)
+{
+ FP_DECL_S(A);
+ FP_DECL_S(B);
+ FP_DECL_S(R);
+ FP_DECL_EX;
+
+ FP_UNPACK_SP(A, fa);
+ FP_UNPACK_SP(B, fb);
+
+ FP_MUL_S(R, A, B);
+
+ FP_PACK_SP(ft, R);
+
+ __FPU_FPCSR |= FP_CUR_EXCEPTIONS;
+}
diff --git a/arch/nds32/math-emu/fnegd.c b/arch/nds32/math-emu/fnegd.c
new file mode 100644
index 0000000..de7ea6a
--- /dev/null
+++ b/arch/nds32/math-emu/fnegd.c
@@ -0,0 +1,21 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2005-2018 Andes Technology Corporation
+#include <linux/uaccess.h>
+
+#include <asm/sfp-machine.h>
+#include <math-emu/soft-fp.h>
+#include <math-emu/double.h>
+void fnegd(void *ft, void *fa)
+{
+ FP_DECL_D(A);
+ FP_DECL_D(R);
+ FP_DECL_EX;
+
+ FP_UNPACK_DP(A, fa);
+
+ FP_NEG_D(R, A);
+
+ FP_PACK_DP(ft, R);
+
+ __FPU_FPCSR |= FP_CUR_EXCEPTIONS;
+}
diff --git a/arch/nds32/math-emu/fnegs.c b/arch/nds32/math-emu/fnegs.c
new file mode 100644
index 0000000..07270b3
--- /dev/null
+++ b/arch/nds32/math-emu/fnegs.c
@@ -0,0 +1,21 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2005-2018 Andes Technology Corporation
+#include <linux/uaccess.h>
+
+#include <asm/sfp-machine.h>
+#include <math-emu/soft-fp.h>
+#include <math-emu/single.h>
+void fnegs(void *ft, void *fa)
+{
+ FP_DECL_S(A);
+ FP_DECL_S(R);
+ FP_DECL_EX;
+
+ FP_UNPACK_SP(A, fa);
+
+ FP_NEG_S(R, A);
+
+ FP_PACK_SP(ft, R);
+
+ __FPU_FPCSR |= FP_CUR_EXCEPTIONS;
+}
diff --git a/arch/nds32/math-emu/fpuemu.c b/arch/nds32/math-emu/fpuemu.c
new file mode 100644
index 0000000..4d88135
--- /dev/null
+++ b/arch/nds32/math-emu/fpuemu.c
@@ -0,0 +1,361 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2005-2018 Andes Technology Corporation
+
+#include <asm/bitfield.h>
+#include <asm/uaccess.h>
+#include <asm/sfp-machine.h>
+#include <asm/fpuemu.h>
+#include <asm/nds32_fpu_inst.h>
+
+#define DPFROMREG(dp, x) (dp = (void *)((unsigned long *)fpu_reg + 2*x))
+#ifdef __NDS32_EL__
+#define SPFROMREG(sp, x)\
+ ((sp) = (void *)((unsigned long *)fpu_reg + (x^1)))
+#else
+#define SPFROMREG(sp, x) ((sp) = (void *)((unsigned long *)fpu_reg + x))
+#endif
+
+#define DEF3OP(name, p, f1, f2) \
+void fpemu_##name##p(void *ft, void *fa, void *fb) \
+{ \
+ f1(fa, fa, fb); \
+ f2(ft, ft, fa); \
+}
+
+#define DEF3OPNEG(name, p, f1, f2, f3) \
+void fpemu_##name##p(void *ft, void *fa, void *fb) \
+{ \
+ f1(fa, fa, fb); \
+ f2(ft, ft, fa); \
+ f3(ft, ft); \
+}
+DEF3OP(fmadd, s, fmuls, fadds);
+DEF3OP(fmsub, s, fmuls, fsubs);
+DEF3OP(fmadd, d, fmuld, faddd);
+DEF3OP(fmsub, d, fmuld, fsubd);
+DEF3OPNEG(fnmadd, s, fmuls, fadds, fnegs);
+DEF3OPNEG(fnmsub, s, fmuls, fsubs, fnegs);
+DEF3OPNEG(fnmadd, d, fmuld, faddd, fnegd);
+DEF3OPNEG(fnmsub, d, fmuld, fsubd, fnegd);
+
+static const unsigned char cmptab[8] = {
+ SF_CEQ,
+ SF_CEQ,
+ SF_CLT,
+ SF_CLT,
+ SF_CLT | SF_CEQ,
+ SF_CLT | SF_CEQ,
+ SF_CUN,
+ SF_CUN
+};
+
+enum ARGTYPE {
+ S1S = 1,
+ S2S,
+ S1D,
+ CS,
+ D1D,
+ D2D,
+ D1S,
+ CD
+};
+union func_t {
+ void (*t)(void *ft, void *fa, void *fb);
+ void (*b)(void *ft, void *fa);
+};
+/*
+ * Emulate a single FPU arithmetic instruction.
+ */
+static int fpu_emu(struct fpu_struct *fpu_reg, unsigned long insn)
+{
+ int rfmt; /* resulting format */
+ union func_t func;
+ int ftype = 0;
+
+ switch (rfmt = NDS32Insn_OPCODE_COP0(insn)) {
+ case fs1_op:{
+ switch (NDS32Insn_OPCODE_BIT69(insn)) {
+ case fadds_op:
+ func.t = fadds;
+ ftype = S2S;
+ break;
+ case fsubs_op:
+ func.t = fsubs;
+ ftype = S2S;
+ break;
+ case fmadds_op:
+ func.t = fpemu_fmadds;
+ ftype = S2S;
+ break;
+ case fmsubs_op:
+ func.t = fpemu_fmsubs;
+ ftype = S2S;
+ break;
+ case fnmadds_op:
+ func.t = fpemu_fnmadds;
+ ftype = S2S;
+ break;
+ case fnmsubs_op:
+ func.t = fpemu_fnmsubs;
+ ftype = S2S;
+ break;
+ case fmuls_op:
+ func.t = fmuls;
+ ftype = S2S;
+ break;
+ case fdivs_op:
+ func.t = fdivs;
+ ftype = S2S;
+ break;
+ case fs1_f2op_op:
+ switch (NDS32Insn_OPCODE_BIT1014(insn)) {
+ case fs2d_op:
+ func.b = fs2d;
+ ftype = S1D;
+ break;
+ case fsqrts_op:
+ func.b = fsqrts;
+ ftype = S1S;
+ break;
+ default:
+ return SIGILL;
+ }
+ break;
+ default:
+ return SIGILL;
+ }
+ break;
+ }
+ case fs2_op:
+ switch (NDS32Insn_OPCODE_BIT69(insn)) {
+ case fcmpeqs_op:
+ case fcmpeqs_e_op:
+ case fcmplts_op:
+ case fcmplts_e_op:
+ case fcmples_op:
+ case fcmples_e_op:
+ case fcmpuns_op:
+ case fcmpuns_e_op:
+ ftype = CS;
+ break;
+ default:
+ return SIGILL;
+ }
+ break;
+ case fd1_op:{
+ switch (NDS32Insn_OPCODE_BIT69(insn)) {
+ case faddd_op:
+ func.t = faddd;
+ ftype = D2D;
+ break;
+ case fsubd_op:
+ func.t = fsubd;
+ ftype = D2D;
+ break;
+ case fmaddd_op:
+ func.t = fpemu_fmaddd;
+ ftype = D2D;
+ break;
+ case fmsubd_op:
+ func.t = fpemu_fmsubd;
+ ftype = D2D;
+ break;
+ case fnmaddd_op:
+ func.t = fpemu_fnmaddd;
+ ftype = D2D;
+ break;
+ case fnmsubd_op:
+ func.t = fpemu_fnmsubd;
+ ftype = D2D;
+ break;
+ case fmuld_op:
+ func.t = fmuld;
+ ftype = D2D;
+ break;
+ case fdivd_op:
+ func.t = fdivd;
+ ftype = D2D;
+ break;
+ case fd1_f2op_op:
+ switch (NDS32Insn_OPCODE_BIT1014(insn)) {
+ case fd2s_op:
+ func.b = fd2s;
+ ftype = D1S;
+ break;
+ case fsqrtd_op:
+ func.b = fsqrtd;
+ ftype = D1D;
+ break;
+ default:
+ return SIGILL;
+ }
+ break;
+ default:
+ return SIGILL;
+
+ }
+ break;
+ }
+
+ case fd2_op:
+ switch (NDS32Insn_OPCODE_BIT69(insn)) {
+ case fcmpeqd_op:
+ case fcmpeqd_e_op:
+ case fcmpltd_op:
+ case fcmpltd_e_op:
+ case fcmpled_op:
+ case fcmpled_e_op:
+ case fcmpund_op:
+ case fcmpund_e_op:
+ ftype = CD;
+ break;
+ default:
+ return SIGILL;
+ }
+ break;
+
+ default:
+ return SIGILL;
+ }
+
+ switch (ftype) {
+ case S1S:{
+ void *ft, *fa;
+
+ SPFROMREG(ft, NDS32Insn_OPCODE_Rt(insn));
+ SPFROMREG(fa, NDS32Insn_OPCODE_Ra(insn));
+ func.b(ft, fa);
+ break;
+ }
+ case S2S:{
+ void *ft, *fa, *fb;
+
+ SPFROMREG(ft, NDS32Insn_OPCODE_Rt(insn));
+ SPFROMREG(fa, NDS32Insn_OPCODE_Ra(insn));
+ SPFROMREG(fb, NDS32Insn_OPCODE_Rb(insn));
+ func.t(ft, fa, fb);
+ break;
+ }
+ case S1D:{
+ void *ft, *fa;
+
+ DPFROMREG(ft, NDS32Insn_OPCODE_Rt(insn));
+ SPFROMREG(fa, NDS32Insn_OPCODE_Ra(insn));
+ func.b(ft, fa);
+ break;
+ }
+ case CS:{
+ unsigned int cmpop = NDS32Insn_OPCODE_BIT69(insn);
+ void *ft, *fa, *fb;
+
+ SPFROMREG(ft, NDS32Insn_OPCODE_Rt(insn));
+ SPFROMREG(fa, NDS32Insn_OPCODE_Ra(insn));
+ SPFROMREG(fb, NDS32Insn_OPCODE_Rb(insn));
+ if (cmpop < 0x8) {
+ cmpop = cmptab[cmpop];
+ fcmps(ft, fa, fb, cmpop);
+ } else
+ return SIGILL;
+ break;
+ }
+ case D1D:{
+ void *ft, *fa;
+
+ DPFROMREG(ft, NDS32Insn_OPCODE_Rt(insn));
+ DPFROMREG(fa, NDS32Insn_OPCODE_Ra(insn));
+ func.b(ft, fa);
+ break;
+ }
+ case D2D:{
+ void *ft, *fa, *fb;
+
+ DPFROMREG(ft, NDS32Insn_OPCODE_Rt(insn));
+ DPFROMREG(fa, NDS32Insn_OPCODE_Ra(insn));
+ DPFROMREG(fb, NDS32Insn_OPCODE_Rb(insn));
+ func.t(ft, fa, fb);
+ break;
+ }
+ case D1S:{
+ void *ft, *fa;
+
+ SPFROMREG(ft, NDS32Insn_OPCODE_Rt(insn));
+ DPFROMREG(fa, NDS32Insn_OPCODE_Ra(insn));
+ func.b(ft, fa);
+ break;
+ }
+ case CD:{
+ unsigned int cmpop = NDS32Insn_OPCODE_BIT69(insn);
+ void *ft, *fa, *fb;
+
+ SPFROMREG(ft, NDS32Insn_OPCODE_Rt(insn));
+ DPFROMREG(fa, NDS32Insn_OPCODE_Ra(insn));
+ DPFROMREG(fb, NDS32Insn_OPCODE_Rb(insn));
+ if (cmpop < 0x8) {
+ cmpop = cmptab[cmpop];
+ fcmpd(ft, fa, fb, cmpop);
+ } else
+ return SIGILL;
+ break;
+ }
+ default:
+ return SIGILL;
+ }
+
+ /*
+ * If an exception is required, generate a tidy SIGFPE exception.
+ */
+ if ((fpu_reg->fpcsr << 5) & fpu_reg->fpcsr & FPCSR_mskALLE)
+ return SIGFPE;
+ return 0;
+}
+
+
+int do_fpuemu(struct pt_regs *regs, struct fpu_struct *fpu)
+{
+ unsigned long insn = 0, addr = regs->ipc;
+ unsigned long emulpc, contpc;
+ unsigned char *pc = (void *)&insn;
+ char c;
+ int i = 0;
+
+ for (i = 0; i < 4; i++) {
+ if (__get_user(c, (unsigned char *)addr++))
+ return SIGBUS;
+ *pc++ = c;
+ }
+
+ insn = be32_to_cpu(insn);
+
+ emulpc = regs->ipc;
+ contpc = regs->ipc + 4;
+
+ switch (NDS32Insn_OPCODE(insn)) {
+ case cop0_op:
+ switch (NDS32Insn_OPCODE_COP0(insn)) {
+
+ case fs1_op:
+ case fs2_op:
+ case fd1_op:
+ case fd2_op:
+ {
+ /* Do fpu emulation */
+ int sig = fpu_emu(fpu, insn);
+
+ if (sig)
+ return sig;
+ }
+ break;
+
+ default:
+ return SIGILL;
+ }
+ break;
+ default:
+ return SIGILL;
+ }
+
+ /* we did it !! */
+ regs->ipc = contpc;
+
+ return 0;
+}
diff --git a/arch/nds32/math-emu/fs2d.c b/arch/nds32/math-emu/fs2d.c
new file mode 100644
index 0000000..0e8db90
--- /dev/null
+++ b/arch/nds32/math-emu/fs2d.c
@@ -0,0 +1,23 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2005-2018 Andes Technology Corporation
+
+#include <linux/uaccess.h>
+#include <asm/sfp-machine.h>
+#include <math-emu/double.h>
+#include <math-emu/single.h>
+#include <math-emu/soft-fp.h>
+
+void fs2d(void *ft, void *fa)
+{
+ FP_DECL_S(A);
+ FP_DECL_D(R);
+ FP_DECL_EX;
+
+ FP_UNPACK_SP(A, fa);
+
+ FP_CONV(D, S, 2, 1, R, A);
+
+ FP_PACK_DP(ft, R);
+
+ __FPU_FPCSR |= FP_CUR_EXCEPTIONS;
+}
diff --git a/arch/nds32/math-emu/fsqrtd.c b/arch/nds32/math-emu/fsqrtd.c
new file mode 100644
index 0000000..c3a8dbd
--- /dev/null
+++ b/arch/nds32/math-emu/fsqrtd.c
@@ -0,0 +1,21 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2005-2018 Andes Technology Corporation
+
+#include <linux/uaccess.h>
+#include <asm/sfp-machine.h>
+#include <math-emu/soft-fp.h>
+#include <math-emu/double.h>
+void fsqrtd(void *ft, void *fa)
+{
+ FP_DECL_D(A);
+ FP_DECL_D(R);
+ FP_DECL_EX;
+
+ FP_UNPACK_DP(A, fa);
+
+ FP_SQRT_D(R, A);
+
+ FP_PACK_DP(ft, R);
+
+ __FPU_FPCSR |= FP_CUR_EXCEPTIONS;
+}
diff --git a/arch/nds32/math-emu/fsqrts.c b/arch/nds32/math-emu/fsqrts.c
new file mode 100644
index 0000000..4c6f94b
--- /dev/null
+++ b/arch/nds32/math-emu/fsqrts.c
@@ -0,0 +1,21 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2005-2018 Andes Technology Corporation
+
+#include <linux/uaccess.h>
+#include <asm/sfp-machine.h>
+#include <math-emu/soft-fp.h>
+#include <math-emu/single.h>
+void fsqrts(void *ft, void *fa)
+{
+ FP_DECL_S(A);
+ FP_DECL_S(R);
+ FP_DECL_EX;
+
+ FP_UNPACK_SP(A, fa);
+
+ FP_SQRT_S(R, A);
+
+ FP_PACK_SP(ft, R);
+
+ __FPU_FPCSR |= FP_CUR_EXCEPTIONS;
+}
diff --git a/arch/nds32/math-emu/fsubd.c b/arch/nds32/math-emu/fsubd.c
new file mode 100644
index 0000000..81b6a0d
--- /dev/null
+++ b/arch/nds32/math-emu/fsubd.c
@@ -0,0 +1,27 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2005-2018 Andes Technology Corporation
+#include <linux/uaccess.h>
+
+#include <asm/sfp-machine.h>
+#include <math-emu/soft-fp.h>
+#include <math-emu/double.h>
+void fsubd(void *ft, void *fa, void *fb)
+{
+
+ FP_DECL_D(A);
+ FP_DECL_D(B);
+ FP_DECL_D(R);
+ FP_DECL_EX;
+
+ FP_UNPACK_DP(A, fa);
+ FP_UNPACK_DP(B, fb);
+
+ if (B_c != FP_CLS_NAN)
+ B_s ^= 1;
+
+ FP_ADD_D(R, A, B);
+
+ FP_PACK_DP(ft, R);
+
+ __FPU_FPCSR |= FP_CUR_EXCEPTIONS;
+}
diff --git a/arch/nds32/math-emu/fsubs.c b/arch/nds32/math-emu/fsubs.c
new file mode 100644
index 0000000..61ddd97
--- /dev/null
+++ b/arch/nds32/math-emu/fsubs.c
@@ -0,0 +1,27 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2005-2018 Andes Technology Corporation
+#include <linux/uaccess.h>
+
+#include <asm/sfp-machine.h>
+#include <math-emu/soft-fp.h>
+#include <math-emu/single.h>
+void fsubs(void *ft, void *fa, void *fb)
+{
+
+ FP_DECL_S(A);
+ FP_DECL_S(B);
+ FP_DECL_S(R);
+ FP_DECL_EX;
+
+ FP_UNPACK_SP(A, fa);
+ FP_UNPACK_SP(B, fb);
+
+ if (B_c != FP_CLS_NAN)
+ B_s ^= 1;
+
+ FP_ADD_S(R, A, B);
+
+ FP_PACK_SP(ft, R);
+
+ __FPU_FPCSR |= FP_CUR_EXCEPTIONS;
+}
--
1.7.1
^ permalink raw reply related [flat|nested] 9+ messages in thread