Merge tag 'nds32-for-linus-4.21' of git://git.kernel.org/pub/scm/linux/kernel/git/greentime/linux

Pull nds32 updates from Greentime Hu:

 - Perf support

 - Power management support

 - FPU support

 - Hardware prefetcher support

 - Build error fixed

 - Performance enhancement

* tag 'nds32-for-linus-4.21' of git://git.kernel.org/pub/scm/linux/kernel/git/greentime/linux:
  nds32: support hardware prefetcher
  nds32: Fix the items of hwcap_str ordering issue.
  math-emu/soft-fp.h: (_FP_ROUND_ZERO) cast 0 to void to fix warning
  math-emu/op-2.h: Use statement expressions to prevent negative constant shift
  nds32: support denormalized result through FP emulator
  nds32: Support FP emulation
  nds32: nds32 FPU port
  nds32: Remove duplicated include from pm.c
  nds32: Power management for nds32
  nds32: Add document for NDS32 PMU.
  nds32: Add perf call-graph support.
  nds32: Perf porting
  nds32: Fix bug in bitfield.h
  nds32: Fix gcc 8.0 compiler option incompatible.
  nds32: Fill all TLB entries with kernel image mapping
  nds32: Remove the redundant assignment

17 files changed, 956 insertions, 2 deletions

diff --git a/arch/nds32/include/asm/Kbuild b/arch/nds32/include/asm/Kbuild
index dbc4e5422550..f81b633d5379 100644
--- a/arch/nds32/include/asm/Kbuild
+++ b/arch/nds32/include/asm/Kbuild
@@ -36,6 +36,7 @@ generic-y += kprobes.h
 generic-y += kvm_para.h
 generic-y += limits.h
 generic-y += local.h
+generic-y += local64.h
 generic-y += mm-arch-hooks.h
 generic-y += mman.h
 generic-y += parport.h
diff --git a/arch/nds32/include/asm/bitfield.h b/arch/nds32/include/asm/bitfield.h
index 8e84fc385b94..7414fcbbab4e 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 of ITYPE register for FPU */
+#define FPU_DISABLE_EXCEPTION	(0x1  << ITYPE_offSTYPE)
+#define FPU_EXCEPTION		(0x2  << ITYPE_offSTYPE)
+#define FPU_CPID		0	/* FPU Co-Processor ID is 0 */
+
 #define NDS32_VECTOR_mskNONEXCEPTION	0x78
 #define NDS32_VECTOR_offEXCEPTION	8
 #define NDS32_VECTOR_offINTERRUPT	9
@@ -692,8 +697,8 @@
 #define PFM_CTL_offKU1		13	/* Enable user mode event counting for PFMC1 */
 #define PFM_CTL_offKU2		14	/* Enable user mode event counting for PFMC2 */
 #define PFM_CTL_offSEL0		15	/* The event selection for PFMC0 */
-#define PFM_CTL_offSEL1		21	/* The event selection for PFMC1 */
-#define PFM_CTL_offSEL2		27	/* The event selection for PFMC2 */
+#define PFM_CTL_offSEL1		16	/* The event selection for PFMC1 */
+#define PFM_CTL_offSEL2		22	/* The event selection for PFMC2 */
 /* bit 28:31 reserved */
 
 #define PFM_CTL_mskEN0		( 0x01  << PFM_CTL_offEN0 )
@@ -735,14 +740,20 @@
 #define N13MISC_CTL_offRTP	1	/* Disable Return Target Predictor */
 #define N13MISC_CTL_offPTEPF	2	/* Disable HPTWK L2 PTE pefetch */
 #define N13MISC_CTL_offSP_SHADOW_EN	4	/* Enable shadow stack pointers */
+#define MISC_CTL_offHWPRE      11      /* Enable HardWare PREFETCH */
 /* bit 6, 9:31 reserved */
 
 #define N13MISC_CTL_makBTB	( 0x1  << N13MISC_CTL_offBTB )
 #define N13MISC_CTL_makRTP	( 0x1  << N13MISC_CTL_offRTP )
 #define N13MISC_CTL_makPTEPF	( 0x1  << N13MISC_CTL_offPTEPF )
 #define N13MISC_CTL_makSP_SHADOW_EN	( 0x1  << N13MISC_CTL_offSP_SHADOW_EN )
+#define MISC_CTL_makHWPRE_EN     ( 0x1  << MISC_CTL_offHWPRE )
 
+#ifdef CONFIG_HW_PRE
+#define MISC_init	(N13MISC_CTL_makBTB|N13MISC_CTL_makRTP|N13MISC_CTL_makSP_SHADOW_EN|MISC_CTL_makHWPRE_EN)
+#else
 #define MISC_init	(N13MISC_CTL_makBTB|N13MISC_CTL_makRTP|N13MISC_CTL_makSP_SHADOW_EN)
+#endif
 
 /******************************************************************************
  * PRUSR_ACC_CTL (Privileged Resource User Access Control Registers)
@@ -926,6 +937,7 @@
 #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 +958,15 @@
 #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/elf.h b/arch/nds32/include/asm/elf.h
index f5f9cf7e0544..95f3ea253e4c 100644
--- a/arch/nds32/include/asm/elf.h
+++ b/arch/nds32/include/asm/elf.h
@@ -9,6 +9,7 @@
  */
 
 #include <asm/ptrace.h>
+#include <asm/fpu.h>
 
 typedef unsigned long elf_greg_t;
 typedef unsigned long elf_freg_t[3];
@@ -159,8 +160,18 @@ struct elf32_hdr;
 
 #endif
 
+
+#if IS_ENABLED(CONFIG_FPU)
+#define FPU_AUX_ENT	NEW_AUX_ENT(AT_FPUCW, FPCSR_INIT)
+#else
+#define FPU_AUX_ENT	NEW_AUX_ENT(AT_IGNORE, 0)
+#endif
+
 #define ARCH_DLINFO						\
 do {								\
+	/* Optional FPU initialization */			\
+	FPU_AUX_ENT;						\
+								\
 	NEW_AUX_ENT(AT_SYSINFO_EHDR,				\
 		    (elf_addr_t)current->mm->context.vdso);	\
 } while (0)
diff --git a/arch/nds32/include/asm/fpu.h b/arch/nds32/include/asm/fpu.h
new file mode 100644
index 000000000000..019f1bcfc5ee
--- /dev/null
+++ b/arch/nds32/include/asm/fpu.h
@@ -0,0 +1,126 @@
+/* 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 bool has_fpu;
+
+extern void save_fpu(struct task_struct *__tsk);
+extern void load_fpu(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)
+
+/*
+ * 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
+
+#if IS_ENABLED(CONFIG_SUPPORT_DENORMAL_ARITHMETIC)
+/*
+ * Denormalized number is unsupported by nds32 FPU. Hence the operation
+ * is treated as underflow cases when the final result is a denormalized
+ * number. To enhance precision, underflow exception trap should be
+ * enabled by default and kerenl will re-execute it by fpu emulator
+ * when getting underflow exception.
+ */
+#define FPCSR_INIT  FPCSR_mskUDFE
+#else
+#define FPCSR_INIT  0x0UL
+#endif
+
+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_LAZY_FPU)
+	if (last_task_used_math == current) {
+		last_task_used_math = NULL;
+#else
+	if (test_tsk_fpu(task_pt_regs(current))) {
+#endif
+		save_fpu(current);
+	}
+	disable_ptreg_fpu(task_pt_regs(current));
+	preempt_enable();
+}
+
+static inline void own_fpu(void)
+{
+	preempt_disable();
+#if IS_ENABLED(CONFIG_LAZY_FPU)
+	if (last_task_used_math != current) {
+		if (last_task_used_math != NULL)
+			save_fpu(last_task_used_math);
+		load_fpu(&current->thread.fpu);
+		last_task_used_math = current;
+	}
+#else
+	if (!test_tsk_fpu(task_pt_regs(current))) {
+		load_fpu(&current->thread.fpu);
+	}
+#endif
+	enable_ptreg_fpu(task_pt_regs(current));
+	preempt_enable();
+}
+
+#if !IS_ENABLED(CONFIG_LAZY_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_LAZY_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/fpuemu.h b/arch/nds32/include/asm/fpuemu.h
new file mode 100644
index 000000000000..c4bd0c7faa75
--- /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 000000000000..1e4b86a90a48
--- /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/perf_event.h b/arch/nds32/include/asm/perf_event.h
new file mode 100644
index 000000000000..fcdff02acc14
--- /dev/null
+++ b/arch/nds32/include/asm/perf_event.h
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2008-2018 Andes Technology Corporation */
+
+#ifndef __ASM_PERF_EVENT_H
+#define __ASM_PERF_EVENT_H
+
+/*
+ * This file is request by Perf,
+ * please refer to tools/perf/design.txt for more details
+ */
+struct pt_regs;
+unsigned long perf_instruction_pointer(struct pt_regs *regs);
+unsigned long perf_misc_flags(struct pt_regs *regs);
+#define perf_misc_flags(regs)   perf_misc_flags(regs)
+
+#endif
diff --git a/arch/nds32/include/asm/pmu.h b/arch/nds32/include/asm/pmu.h
new file mode 100644
index 000000000000..e1ac0b0b8bcf
--- /dev/null
+++ b/arch/nds32/include/asm/pmu.h
@@ -0,0 +1,386 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2008-2018 Andes Technology Corporation */
+
+#ifndef __ASM_PMU_H
+#define __ASM_PMU_H
+
+#include <linux/interrupt.h>
+#include <linux/perf_event.h>
+#include <asm/unistd.h>
+#include <asm/bitfield.h>
+
+/* Has special meaning for perf core implementation */
+#define HW_OP_UNSUPPORTED		0x0
+#define C(_x)				PERF_COUNT_HW_CACHE_##_x
+#define CACHE_OP_UNSUPPORTED		0x0
+
+/* Enough for both software and hardware defined events */
+#define SOFTWARE_EVENT_MASK		0xFF
+
+#define PFM_OFFSET_MAGIC_0		2	/* DO NOT START FROM 0 */
+#define PFM_OFFSET_MAGIC_1		(PFM_OFFSET_MAGIC_0 + 36)
+#define PFM_OFFSET_MAGIC_2		(PFM_OFFSET_MAGIC_1 + 36)
+
+enum { PFMC0, PFMC1, PFMC2, MAX_COUNTERS };
+
+u32 PFM_CTL_OVF[3] = { PFM_CTL_mskOVF0, PFM_CTL_mskOVF1,
+		       PFM_CTL_mskOVF2 };
+u32 PFM_CTL_EN[3] = { PFM_CTL_mskEN0, PFM_CTL_mskEN1,
+		      PFM_CTL_mskEN2 };
+u32 PFM_CTL_OFFSEL[3] = { PFM_CTL_offSEL0, PFM_CTL_offSEL1,
+			  PFM_CTL_offSEL2 };
+u32 PFM_CTL_IE[3] = { PFM_CTL_mskIE0, PFM_CTL_mskIE1, PFM_CTL_mskIE2 };
+u32 PFM_CTL_KS[3] = { PFM_CTL_mskKS0, PFM_CTL_mskKS1, PFM_CTL_mskKS2 };
+u32 PFM_CTL_KU[3] = { PFM_CTL_mskKU0, PFM_CTL_mskKU1, PFM_CTL_mskKU2 };
+u32 PFM_CTL_SEL[3] = { PFM_CTL_mskSEL0, PFM_CTL_mskSEL1, PFM_CTL_mskSEL2 };
+/*
+ * Perf Events' indices
+ */
+#define NDS32_IDX_CYCLE_COUNTER			0
+#define NDS32_IDX_COUNTER0			1
+#define NDS32_IDX_COUNTER1			2
+
+/* The events for a given PMU register set. */
+struct pmu_hw_events {
+	/*
+	 * The events that are active on the PMU for the given index.
+	 */
+	struct perf_event *events[MAX_COUNTERS];
+
+	/*
+	 * A 1 bit for an index indicates that the counter is being used for
+	 * an event. A 0 means that the counter can be used.
+	 */
+	unsigned long used_mask[BITS_TO_LONGS(MAX_COUNTERS)];
+
+	/*
+	 * Hardware lock to serialize accesses to PMU registers. Needed for the
+	 * read/modify/write sequences.
+	 */
+	raw_spinlock_t pmu_lock;
+};
+
+struct nds32_pmu {
+	struct pmu pmu;
+	cpumask_t active_irqs;
+	char *name;
+	 irqreturn_t (*handle_irq)(int irq_num, void *dev);
+	void (*enable)(struct perf_event *event);
+	void (*disable)(struct perf_event *event);
+	int (*get_event_idx)(struct pmu_hw_events *hw_events,
+			     struct perf_event *event);
+	int (*set_event_filter)(struct hw_perf_event *evt,
+				struct perf_event_attr *attr);
+	u32 (*read_counter)(struct perf_event *event);
+	void (*write_counter)(struct perf_event *event, u32 val);
+	void (*start)(struct nds32_pmu *nds32_pmu);
+	void (*stop)(struct nds32_pmu *nds32_pmu);
+	void (*reset)(void *data);
+	int (*request_irq)(struct nds32_pmu *nds32_pmu, irq_handler_t handler);
+	void (*free_irq)(struct nds32_pmu *nds32_pmu);
+	int (*map_event)(struct perf_event *event);
+	int num_events;
+	atomic_t active_events;
+	u64 max_period;
+	struct platform_device *plat_device;
+	struct pmu_hw_events *(*get_hw_events)(void);
+};
+
+#define to_nds32_pmu(p)			(container_of(p, struct nds32_pmu, pmu))
+
+int nds32_pmu_register(struct nds32_pmu *nds32_pmu, int type);
+
+u64 nds32_pmu_event_update(struct perf_event *event);
+
+int nds32_pmu_event_set_period(struct perf_event *event);
+
+/*
+ * Common NDS32 SPAv3 event types
+ *
+ * Note: An implementation may not be able to count all of these events
+ * but the encodings are considered to be `reserved' in the case that
+ * they are not available.
+ *
+ * SEL_TOTAL_CYCLES will add an offset is due to ZERO is defined as
+ * NOT_SUPPORTED EVENT mapping in generic perf code.
+ * You will need to deal it in the event writing implementation.
+ */
+enum spav3_counter_0_perf_types {
+	SPAV3_0_SEL_BASE = -1 + PFM_OFFSET_MAGIC_0,	/* counting symbol */
+	SPAV3_0_SEL_TOTAL_CYCLES = 0 + PFM_OFFSET_MAGIC_0,
+	SPAV3_0_SEL_COMPLETED_INSTRUCTION = 1 + PFM_OFFSET_MAGIC_0,
+	SPAV3_0_SEL_LAST	/* counting symbol */
+};
+
+enum spav3_counter_1_perf_types {
+	SPAV3_1_SEL_BASE = -1 + PFM_OFFSET_MAGIC_1,	/* counting symbol */
+	SPAV3_1_SEL_TOTAL_CYCLES = 0 + PFM_OFFSET_MAGIC_1,
+	SPAV3_1_SEL_COMPLETED_INSTRUCTION = 1 + PFM_OFFSET_MAGIC_1,
+	SPAV3_1_SEL_CONDITIONAL_BRANCH = 2 + PFM_OFFSET_MAGIC_1,
+	SPAV3_1_SEL_TAKEN_CONDITIONAL_BRANCH = 3 + PFM_OFFSET_MAGIC_1,
+	SPAV3_1_SEL_PREFETCH_INSTRUCTION = 4 + PFM_OFFSET_MAGIC_1,
+	SPAV3_1_SEL_RET_INST = 5 + PFM_OFFSET_MAGIC_1,
+	SPAV3_1_SEL_JR_INST = 6 + PFM_OFFSET_MAGIC_1,
+	SPAV3_1_SEL_JAL_JRAL_INST = 7 + PFM_OFFSET_MAGIC_1,
+	SPAV3_1_SEL_NOP_INST = 8 + PFM_OFFSET_MAGIC_1,
+	SPAV3_1_SEL_SCW_INST = 9 + PFM_OFFSET_MAGIC_1,
+	SPAV3_1_SEL_ISB_DSB_INST = 10 + PFM_OFFSET_MAGIC_1,
+	SPAV3_1_SEL_CCTL_INST = 11 + PFM_OFFSET_MAGIC_1,
+	SPAV3_1_SEL_TAKEN_INTERRUPTS = 12 + PFM_OFFSET_MAGIC_1,
+	SPAV3_1_SEL_LOADS_COMPLETED = 13 + PFM_OFFSET_MAGIC_1,
+	SPAV3_1_SEL_UITLB_ACCESS = 14 + PFM_OFFSET_MAGIC_1,
+	SPAV3_1_SEL_UDTLB_ACCESS = 15 + PFM_OFFSET_MAGIC_1,
+	SPAV3_1_SEL_MTLB_ACCESS = 16 + PFM_OFFSET_MAGIC_1,
+	SPAV3_1_SEL_CODE_CACHE_ACCESS = 17 + PFM_OFFSET_MAGIC_1,
+	SPAV3_1_SEL_DATA_DEPENDENCY_STALL_CYCLES = 18 + PFM_OFFSET_MAGIC_1,
+	SPAV3_1_SEL_DATA_CACHE_MISS_STALL_CYCLES = 19 + PFM_OFFSET_MAGIC_1,
+	SPAV3_1_SEL_DATA_CACHE_ACCESS = 20 + PFM_OFFSET_MAGIC_1,
+	SPAV3_1_SEL_DATA_CACHE_MISS = 21 + PFM_OFFSET_MAGIC_1,
+	SPAV3_1_SEL_LOAD_DATA_CACHE_ACCESS = 22 + PFM_OFFSET_MAGIC_1,
+	SPAV3_1_SEL_STORE_DATA_CACHE_ACCESS = 23 + PFM_OFFSET_MAGIC_1,
+	SPAV3_1_SEL_ILM_ACCESS = 24 + PFM_OFFSET_MAGIC_1,
+	SPAV3_1_SEL_LSU_BIU_CYCLES = 25 + PFM_OFFSET_MAGIC_1,
+	SPAV3_1_SEL_HPTWK_BIU_CYCLES = 26 + PFM_OFFSET_MAGIC_1,
+	SPAV3_1_SEL_DMA_BIU_CYCLES = 27 + PFM_OFFSET_MAGIC_1,
+	SPAV3_1_SEL_CODE_CACHE_FILL_BIU_CYCLES = 28 + PFM_OFFSET_MAGIC_1,
+	SPAV3_1_SEL_LEGAL_UNALIGN_DCACHE_ACCESS = 29 + PFM_OFFSET_MAGIC_1,
+	SPAV3_1_SEL_PUSH25 = 30 + PFM_OFFSET_MAGIC_1,
+	SPAV3_1_SEL_SYSCALLS_INST = 31 + PFM_OFFSET_MAGIC_1,
+	SPAV3_1_SEL_LAST	/* counting symbol */
+};
+
+enum spav3_counter_2_perf_types {
+	SPAV3_2_SEL_BASE = -1 + PFM_OFFSET_MAGIC_2,	/* counting symbol */
+	SPAV3_2_SEL_TOTAL_CYCLES = 0 + PFM_OFFSET_MAGIC_2,
+	SPAV3_2_SEL_COMPLETED_INSTRUCTION = 1 + PFM_OFFSET_MAGIC_2,
+	SPAV3_2_SEL_CONDITIONAL_BRANCH_MISPREDICT = 2 + PFM_OFFSET_MAGIC_2,
+	SPAV3_2_SEL_TAKEN_CONDITIONAL_BRANCH_MISPREDICT =
+	    3 + PFM_OFFSET_MAGIC_2,
+	SPAV3_2_SEL_PREFETCH_INSTRUCTION_CACHE_HIT = 4 + PFM_OFFSET_MAGIC_2,
+	SPAV3_1_SEL_RET_MISPREDICT = 5 + PFM_OFFSET_MAGIC_2,
+	SPAV3_1_SEL_IMMEDIATE_J_INST = 6 + PFM_OFFSET_MAGIC_2,
+	SPAV3_1_SEL_MULTIPLY_INST = 7 + PFM_OFFSET_MAGIC_2,
+	SPAV3_1_SEL_16_BIT_INST = 8 + PFM_OFFSET_MAGIC_2,
+	SPAV3_1_SEL_FAILED_SCW_INST = 9 + PFM_OFFSET_MAGIC_2,
+	SPAV3_1_SEL_LD_AFTER_ST_CONFLICT_REPLAYS = 10 + PFM_OFFSET_MAGIC_2,
+	SPAV3_1_SEL_TAKEN_EXCEPTIONS = 12 + PFM_OFFSET_MAGIC_2,
+	SPAV3_1_SEL_STORES_COMPLETED = 13 + PFM_OFFSET_MAGIC_2,
+	SPAV3_2_SEL_UITLB_MISS = 14 + PFM_OFFSET_MAGIC_2,
+	SPAV3_2_SEL_UDTLB_MISS = 15 + PFM_OFFSET_MAGIC_2,
+	SPAV3_2_SEL_MTLB_MISS = 16 + PFM_OFFSET_MAGIC_2,
+	SPAV3_2_SEL_CODE_CACHE_MISS = 17 + PFM_OFFSET_MAGIC_2,
+	SPAV3_1_SEL_EMPTY_INST_QUEUE_STALL_CYCLES = 18 + PFM_OFFSET_MAGIC_2,
+	SPAV3_1_SEL_DATA_WRITE_BACK = 19 + PFM_OFFSET_MAGIC_2,
+	SPAV3_2_SEL_DATA_CACHE_MISS = 21 + PFM_OFFSET_MAGIC_2,
+	SPAV3_2_SEL_LOAD_DATA_CACHE_MISS = 22 + PFM_OFFSET_MAGIC_2,
+	SPAV3_2_SEL_STORE_DATA_CACHE_MISS = 23 + PFM_OFFSET_MAGIC_2,
+	SPAV3_1_SEL_DLM_ACCESS = 24 + PFM_OFFSET_MAGIC_2,
+	SPAV3_1_SEL_LSU_BIU_REQUEST = 25 + PFM_OFFSET_MAGIC_2,
+	SPAV3_1_SEL_HPTWK_BIU_REQUEST = 26 + PFM_OFFSET_MAGIC_2,
+	SPAV3_1_SEL_DMA_BIU_REQUEST = 27 + PFM_OFFSET_MAGIC_2,
+	SPAV3_1_SEL_CODE_CACHE_FILL_BIU_REQUEST = 28 + PFM_OFFSET_MAGIC_2,
+	SPAV3_1_SEL_EXTERNAL_EVENTS = 29 + PFM_OFFSET_MAGIC_2,
+	SPAV3_1_SEL_POP25 = 30 + PFM_OFFSET_MAGIC_2,
+	SPAV3_2_SEL_LAST	/* counting symbol */
+};
+
+/* Get converted event counter index */
+static inline int get_converted_event_idx(unsigned long event)
+{
+	int idx;
+
+	if ((event) > SPAV3_0_SEL_BASE && event < SPAV3_0_SEL_LAST) {
+		idx = 0;
+	} else if ((event) > SPAV3_1_SEL_BASE && event < SPAV3_1_SEL_LAST) {
+		idx = 1;
+	} else if ((event) > SPAV3_2_SEL_BASE && event < SPAV3_2_SEL_LAST) {
+		idx = 2;
+	} else {
+		pr_err("GET_CONVERTED_EVENT_IDX PFM counter range error\n");
+		return -EPERM;
+	}
+
+	return idx;
+}
+
+/* Get converted hardware event number */
+static inline u32 get_converted_evet_hw_num(u32 event)
+{
+	if (event > SPAV3_0_SEL_BASE && event < SPAV3_0_SEL_LAST)
+		event -= PFM_OFFSET_MAGIC_0;
+	else if (event > SPAV3_1_SEL_BASE && event < SPAV3_1_SEL_LAST)
+		event -= PFM_OFFSET_MAGIC_1;
+	else if (event > SPAV3_2_SEL_BASE && event < SPAV3_2_SEL_LAST)
+		event -= PFM_OFFSET_MAGIC_2;
+	else if (event != 0)
+		pr_err("GET_CONVERTED_EVENT_HW_NUM PFM counter range error\n");
+
+	return event;
+}
+
+/*
+ * NDS32 HW events mapping
+ *
+ * The hardware events that we support. We do support cache operations but
+ * we have harvard caches and no way to combine instruction and data
+ * accesses/misses in hardware.
+ */
+static const unsigned int nds32_pfm_perf_map[PERF_COUNT_HW_MAX] = {
+	[PERF_COUNT_HW_CPU_CYCLES] = SPAV3_0_SEL_TOTAL_CYCLES,
+	[PERF_COUNT_HW_INSTRUCTIONS] = SPAV3_1_SEL_COMPLETED_INSTRUCTION,
+	[PERF_COUNT_HW_CACHE_REFERENCES] = SPAV3_1_SEL_DATA_CACHE_ACCESS,
+	[PERF_COUNT_HW_CACHE_MISSES] = SPAV3_2_SEL_DATA_CACHE_MISS,
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = HW_OP_UNSUPPORTED,
+	[PERF_COUNT_HW_BRANCH_MISSES] = HW_OP_UNSUPPORTED,
+	[PERF_COUNT_HW_BUS_CYCLES] = HW_OP_UNSUPPORTED,
+	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = HW_OP_UNSUPPORTED,
+	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = HW_OP_UNSUPPORTED,
+	[PERF_COUNT_HW_REF_CPU_CYCLES] = HW_OP_UNSUPPORTED
+};
+
+static const unsigned int nds32_pfm_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
+	[PERF_COUNT_HW_CACHE_OP_MAX]
+	[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+	[C(L1D)] = {
+		    [C(OP_READ)] = {
+				    [C(RESULT_ACCESS)] =
+				    SPAV3_1_SEL_LOAD_DATA_CACHE_ACCESS,
+				    [C(RESULT_MISS)] =
+				    SPAV3_2_SEL_LOAD_DATA_CACHE_MISS,
+				    },
+		    [C(OP_WRITE)] = {
+				     [C(RESULT_ACCESS)] =
+				     SPAV3_1_SEL_STORE_DATA_CACHE_ACCESS,
+				     [C(RESULT_MISS)] =
+				     SPAV3_2_SEL_STORE_DATA_CACHE_MISS,
+				     },
+		    [C(OP_PREFETCH)] = {
+					[C(RESULT_ACCESS)] =
+						CACHE_OP_UNSUPPORTED,
+					[C(RESULT_MISS)] =
+						CACHE_OP_UNSUPPORTED,
+					},
+		    },
+	[C(L1I)] = {
+		    [C(OP_READ)] = {
+				    [C(RESULT_ACCESS)] =
+				    SPAV3_1_SEL_CODE_CACHE_ACCESS,
+				    [C(RESULT_MISS)] =
+				    SPAV3_2_SEL_CODE_CACHE_MISS,
+				    },
+		    [C(OP_WRITE)] = {
+				     [C(RESULT_ACCESS)] =
+				     SPAV3_1_SEL_CODE_CACHE_ACCESS,
+				     [C(RESULT_MISS)] =
+				     SPAV3_2_SEL_CODE_CACHE_MISS,
+				     },
+		    [C(OP_PREFETCH)] = {
+					[C(RESULT_ACCESS)] =
+					CACHE_OP_UNSUPPORTED,
+					[C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+					},
+		    },
+	/* TODO: L2CC */
+	[C(LL)] = {
+		   [C(OP_READ)] = {
+				   [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+				   [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+				   },
+		   [C(OP_WRITE)] = {
+				    [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+				    [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+				    },
+		   [C(OP_PREFETCH)] = {
+				       [C(RESULT_ACCESS)] =
+				       CACHE_OP_UNSUPPORTED,
+				       [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+				       },
+		   },
+	/* NDS32 PMU does not support TLB read/write hit/miss,
+	 * However, it can count access/miss, which mixed with read and write.
+	 * Therefore, only READ counter will use it.
+	 * We do as possible as we can.
+	 */
+	[C(DTLB)] = {
+		     [C(OP_READ)] = {
+				     [C(RESULT_ACCESS)] =
+					SPAV3_1_SEL_UDTLB_ACCESS,
+				     [C(RESULT_MISS)] =
+					SPAV3_2_SEL_UDTLB_MISS,
+				     },
+		     [C(OP_WRITE)] = {
+				      [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+				      [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+				      },
+		     [C(OP_PREFETCH)] = {
+					 [C(RESULT_ACCESS)] =
+					 CACHE_OP_UNSUPPORTED,
+					 [C(RESULT_MISS)] =
+					 CACHE_OP_UNSUPPORTED,
+					 },
+		     },
+	[C(ITLB)] = {
+		     [C(OP_READ)] = {
+				     [C(RESULT_ACCESS)] =
+					SPAV3_1_SEL_UITLB_ACCESS,
+				     [C(RESULT_MISS)] =
+					SPAV3_2_SEL_UITLB_MISS,
+				     },
+		     [C(OP_WRITE)] = {
+				      [C(RESULT_ACCESS)] =
+					CACHE_OP_UNSUPPORTED,
+				      [C(RESULT_MISS)] =
+					CACHE_OP_UNSUPPORTED,
+				      },
+		     [C(OP_PREFETCH)] = {
+					 [C(RESULT_ACCESS)] =
+						CACHE_OP_UNSUPPORTED,
+					 [C(RESULT_MISS)] =
+						CACHE_OP_UNSUPPORTED,
+					 },
+		     },
+	[C(BPU)] = {		/* What is BPU? */
+		    [C(OP_READ)] = {
+				    [C(RESULT_ACCESS)] =
+					CACHE_OP_UNSUPPORTED,
+				    [C(RESULT_MISS)] =
+					CACHE_OP_UNSUPPORTED,
+				    },
+		    [C(OP_WRITE)] = {
+				     [C(RESULT_ACCESS)] =
+					CACHE_OP_UNSUPPORTED,
+				     [C(RESULT_MISS)] =
+					CACHE_OP_UNSUPPORTED,
+				     },
+		    [C(OP_PREFETCH)] = {
+					[C(RESULT_ACCESS)] =
+						CACHE_OP_UNSUPPORTED,
+					[C(RESULT_MISS)] =
+						CACHE_OP_UNSUPPORTED,
+					},
+		    },
+	[C(NODE)] = {		/* What is NODE? */
+		     [C(OP_READ)] = {
+				     [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+				     [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+				     },
+		     [C(OP_WRITE)] = {
+				      [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+				      [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+				      },
+		     [C(OP_PREFETCH)] = {
+					 [C(RESULT_ACCESS)] =
+						CACHE_OP_UNSUPPORTED,
+					 [C(RESULT_MISS)] =
+						CACHE_OP_UNSUPPORTED,
+					 },
+		     },
+};
+
+int nds32_pmu_map_event(struct perf_event *event,
+			const unsigned int (*event_map)[PERF_COUNT_HW_MAX],
+			const unsigned int (*cache_map)[PERF_COUNT_HW_CACHE_MAX]
+			[PERF_COUNT_HW_CACHE_OP_MAX]
+			[PERF_COUNT_HW_CACHE_RESULT_MAX], u32 raw_event_mask);
+
+#endif /* __ASM_PMU_H */
diff --git a/arch/nds32/include/asm/processor.h b/arch/nds32/include/asm/processor.h
index c2660f566bac..72024f8bc129 100644
--- a/arch/nds32/include/asm/processor.h
+++ b/arch/nds32/include/asm/processor.h
@@ -35,6 +35,8 @@ struct thread_struct {
 	unsigned long address;
 	unsigned long trap_no;
 	unsigned long error_code;
+
+	struct fpu_struct fpu;
 };
 
 #define INIT_THREAD  {	}
@@ -72,6 +74,11 @@ struct task_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/asm/sfp-machine.h b/arch/nds32/include/asm/sfp-machine.h
new file mode 100644
index 000000000000..b1a5caa332b5
--- /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/include/asm/stacktrace.h b/arch/nds32/include/asm/stacktrace.h
new file mode 100644
index 000000000000..6bf7c777bda4
--- /dev/null
+++ b/arch/nds32/include/asm/stacktrace.h
@@ -0,0 +1,39 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2008-2018 Andes Technology Corporation */
+
+#ifndef __ASM_STACKTRACE_H
+#define __ASM_STACKTRACE_H
+
+/* Kernel callchain */
+struct stackframe {
+	unsigned long fp;
+	unsigned long sp;
+	unsigned long lp;
+};
+
+/*
+ * struct frame_tail: User callchain
+ * IMPORTANT:
+ * This struct is used for call-stack walking,
+ * the order and types matters.
+ * Do not use array, it only stores sizeof(pointer)
+ *
+ * The details can refer to arch/arm/kernel/perf_event.c
+ */
+struct frame_tail {
+	unsigned long stack_fp;
+	unsigned long stack_lp;
+};
+
+/* For User callchain with optimize for size */
+struct frame_tail_opt_size {
+	unsigned long stack_r6;
+	unsigned long stack_fp;
+	unsigned long stack_gp;
+	unsigned long stack_lp;
+};
+
+extern void
+get_real_ret_addr(unsigned long *addr, struct task_struct *tsk, int *graph);
+
+#endif /* __ASM_STACKTRACE_H */
diff --git a/arch/nds32/include/asm/suspend.h b/arch/nds32/include/asm/suspend.h
new file mode 100644
index 000000000000..6ed2418af1ac
--- /dev/null
+++ b/arch/nds32/include/asm/suspend.h
@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+// Copyright (C) 2008-2017 Andes Technology Corporation
+
+#ifndef __ASM_NDS32_SUSPEND_H
+#define __ASM_NDS32_SUSPEND_H
+
+extern void suspend2ram(void);
+extern void cpu_resume(void);
+extern unsigned long wake_mask;
+
+#endif
diff --git a/arch/nds32/include/asm/syscalls.h b/arch/nds32/include/asm/syscalls.h
index 78778ecff60c..da32101b455d 100644
--- a/arch/nds32/include/asm/syscalls.h
+++ b/arch/nds32/include/asm/syscalls.h
@@ -7,6 +7,7 @@
 asmlinkage long sys_cacheflush(unsigned long addr, unsigned long len, unsigned int op);
 asmlinkage long sys_fadvise64_64_wrapper(int fd, int advice, loff_t offset, loff_t len);
 asmlinkage long sys_rt_sigreturn_wrapper(void);
+asmlinkage long sys_udftrap(int option);
 
 #include <asm-generic/syscalls.h>
 
diff --git a/arch/nds32/include/uapi/asm/auxvec.h b/arch/nds32/include/uapi/asm/auxvec.h
index 56043ce4972f..2d3213f5e595 100644
--- a/arch/nds32/include/uapi/asm/auxvec.h
+++ b/arch/nds32/include/uapi/asm/auxvec.h
@@ -4,6 +4,13 @@
 #ifndef __ASM_AUXVEC_H
 #define __ASM_AUXVEC_H
 
+/*
+ * This entry gives some information about the FPU initialization
+ * performed by the kernel.
+ */
+#define AT_FPUCW	18	/* Used FPU control word.  */
+
+
 /* VDSO location */
 #define AT_SYSINFO_EHDR	33
 
diff --git a/arch/nds32/include/uapi/asm/sigcontext.h b/arch/nds32/include/uapi/asm/sigcontext.h
index 00567b237b0c..58afc416473e 100644
--- a/arch/nds32/include/uapi/asm/sigcontext.h
+++ b/arch/nds32/include/uapi/asm/sigcontext.h
@@ -9,6 +9,19 @@
  * 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;
+	/*
+	 * UDF_trap is used to recognize whether underflow trap is enabled
+	 * or not. When UDF_trap == 1, this process will be traped and then
+	 * get a SIGFPE signal when encountering an underflow exception.
+	 * UDF_trap is only modified through setfputrap syscall. Therefore,
+	 * UDF_trap needn't be saved or loaded to context in each context
+	 * switch.
+	 */
+	unsigned long UDF_trap;
+};
 
 struct zol_struct {
 	unsigned long nds32_lc;	/* $LC */
@@ -54,6 +67,7 @@ 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/include/uapi/asm/udftrap.h b/arch/nds32/include/uapi/asm/udftrap.h
new file mode 100644
index 000000000000..433f79d679c0
--- /dev/null
+++ b/arch/nds32/include/uapi/asm/udftrap.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2005-2018 Andes Technology Corporation */
+#ifndef	_ASM_SETFPUTRAP
+#define	_ASM_SETFPUTRAP
+
+/*
+ * Options for setfputrap system call
+ */
+#define	DISABLE_UDFTRAP	0	/* disable underflow exception trap */
+#define	ENABLE_UDFTRAP	1	/* enable undeflos exception trap */
+#define	GET_UDFTRAP	2	/* only get undeflos exception trap status */
+
+#endif /* _ASM_CACHECTL */
diff --git a/arch/nds32/include/uapi/asm/unistd.h b/arch/nds32/include/uapi/asm/unistd.h
index 603e826e0449..c2c3a3e34083 100644
--- a/arch/nds32/include/uapi/asm/unistd.h
+++ b/arch/nds32/include/uapi/asm/unistd.h
@@ -9,4 +9,6 @@
 
 /* Additional NDS32 specific syscalls. */
 #define __NR_cacheflush		(__NR_arch_specific_syscall)
+#define __NR_udftrap		(__NR_arch_specific_syscall + 1)
 __SYSCALL(__NR_cacheflush, sys_cacheflush)
+__SYSCALL(__NR_udftrap, sys_udftrap)