nds32: support denormalized result through FP emulator

Currently, the nds32 FPU dose not support the arithmetic of denormalized
number. When the nds32 FPU finds the result of the instruction is a
denormlized number, the nds32 FPU considers it to be an underflow condition
and rounds the result to an appropriate number. It may causes some loss
of precision. This commit proposes a solution to re-execute the
instruction by the FPU emulator to enhance the precision. To transfer
calculations from user space to kernel space, this feature will enable
the underflow exception trap by default. Enabling this feature may cause
some side effects:
  1. Performance loss due to extra FPU exception
  2. Need another scheme to control real underflow trap
       A new parameter, UDF_trap, which is belong to FPU context is used
     to control underflow trap.

User can configure this feature via CONFIG_SUPPORT_DENORMAL_ARITHMETIC

Signed-off-by: Vincent Chen <vincentc@andestech.com>
Acked-by: Greentime Hu <greentime@andestech.com>
Signed-off-by: Greentime Hu <greentime@andestech.com>

7 files changed, 54 insertions, 0 deletions

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
index 9b1107b58e23..019f1bcfc5ee 100644
--- a/arch/nds32/include/asm/fpu.h
+++ b/arch/nds32/include/asm/fpu.h
@@ -28,7 +28,18 @@ extern int do_fpuemu(struct pt_regs *regs, struct fpu_struct *fpu);
 #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;
 
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 1257a78e3ae1..58afc416473e 100644
--- a/arch/nds32/include/uapi/asm/sigcontext.h
+++ b/arch/nds32/include/uapi/asm/sigcontext.h
@@ -12,6 +12,15 @@
 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 {
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)