nds32: Avoid IEX status being incorrectly modified

In order for kernel to capture each denormalized output, the UDF
trapping enable bit is always raised in $fpcsr. Because underflow case will
issue not an underflow exception but also an inexact exception, it causes
that the IEX, IEX cumulative exception, flag in $fpcsr to be raised in each
denormalized output handling. To make the emulation transparent to the
user, the emulator needs to clear the IEX flag in $fpcsr if the result is a
denormalized number. However, if the IEX flag has been raised before this
floating point emulation, this cleanup may be incorrect. To avoid the IEX
flags in $fpcsr be raised in each denormalized output handling, the IEX
trap shall be always enabled.

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, 38 insertions, 25 deletions

diff --git a/arch/nds32/include/asm/bitfield.h b/arch/nds32/include/asm/bitfield.h
index e75212c76b20..b02a58e71f80 100644
--- a/arch/nds32/include/asm/bitfield.h
+++ b/arch/nds32/include/asm/bitfield.h
@@ -937,7 +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_NO_UDF_IEXE (FPCSR_mskIVOE | FPCSR_mskDBZE | FPCSR_mskOVFE)
 #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)
 
diff --git a/arch/nds32/include/asm/fpu.h b/arch/nds32/include/asm/fpu.h
index 019f1bcfc5ee..8294ed4aaa2c 100644
--- a/arch/nds32/include/asm/fpu.h
+++ b/arch/nds32/include/asm/fpu.h
@@ -36,7 +36,7 @@ extern int do_fpuemu(struct pt_regs *regs, struct fpu_struct *fpu);
  * enabled by default and kerenl will re-execute it by fpu emulator
  * when getting underflow exception.
  */
-#define FPCSR_INIT  FPCSR_mskUDFE
+#define FPCSR_INIT  (FPCSR_mskUDFE | FPCSR_mskIEXE)
 #else
 #define FPCSR_INIT  0x0UL
 #endif
diff --git a/arch/nds32/include/asm/syscalls.h b/arch/nds32/include/asm/syscalls.h
index f3b16f602cb5..4e7216082a67 100644
--- a/arch/nds32/include/asm/syscalls.h
+++ b/arch/nds32/include/asm/syscalls.h
@@ -7,7 +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);
+asmlinkage long sys_fp_udfiex_crtl(int cmd, int act);
 
 #include <asm-generic/syscalls.h>
 
diff --git a/arch/nds32/include/uapi/asm/fp_udfiex_crtl.h b/arch/nds32/include/uapi/asm/fp_udfiex_crtl.h
new file mode 100644
index 000000000000..d54a5d6c6538
--- /dev/null
+++ b/arch/nds32/include/uapi/asm/fp_udfiex_crtl.h
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2005-2019 Andes Technology Corporation */
+#ifndef	_FP_UDF_IEX_CRTL_H
+#define	_FP_UDF_IEX_CRTL_H
+
+/*
+ * The cmd list of sys_fp_udfiex_crtl()
+ */
+/* Disable UDF or IEX trap based on the content of parameter act */
+#define DISABLE_UDF_IEX_TRAP	0
+/* Enable UDF or IEX trap based on the content of parameter act */
+#define ENABLE_UDF_IEX_TRAP	1
+/* Get current status of UDF and IEX trap */
+#define GET_UDF_IEX_TRAP	2
+
+#endif /* _FP_UDF_IEX_CRTL_H */
diff --git a/arch/nds32/include/uapi/asm/sigcontext.h b/arch/nds32/include/uapi/asm/sigcontext.h
index 628ff6b75825..dc89af7ddcc3 100644
--- a/arch/nds32/include/uapi/asm/sigcontext.h
+++ b/arch/nds32/include/uapi/asm/sigcontext.h
@@ -13,14 +13,24 @@ 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.
+	 * When CONFIG_SUPPORT_DENORMAL_ARITHMETIC is defined, kernel prevents
+	 * hardware from treating the denormalized output as an underflow case
+	 * and rounding it to a normal number. Hence kernel enables the UDF and
+	 * IEX trap in the fpcsr register to step in the calculation.
+	 * However, the UDF and IEX trap enable bit in $fpcsr also lose
+	 * their use.
+	 *
+	 * UDF_IEX_trap replaces the feature of UDF and IEX trap enable bit in
+	 * $fpcsr to control the trap of underflow and inexact. The bit filed
+	 * of UDF_IEX_trap is the same as $fpcsr, 10th bit is used to enable UDF
+	 * exception trapping and 11th bit is used to enable IEX exception
+	 * trapping.
+	 *
+	 * UDF_IEX_trap is only modified through fp_udfiex_crtl syscall.
+	 * Therefore, UDF_IEX_trap needn't be saved and restored in each
+	 * context switch.
 	 */
-	unsigned long UDF_trap;
+	unsigned long UDF_IEX_trap;
 };
 
 struct zol_struct {
diff --git a/arch/nds32/include/uapi/asm/udftrap.h b/arch/nds32/include/uapi/asm/udftrap.h
deleted file mode 100644
index 433f79d679c0..000000000000
--- a/arch/nds32/include/uapi/asm/udftrap.h
+++ /dev/null
@@ -1,13 +0,0 @@
-/* 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 c691735017ed..a0b2f7b9c0f2 100644
--- a/arch/nds32/include/uapi/asm/unistd.h
+++ b/arch/nds32/include/uapi/asm/unistd.h
@@ -11,6 +11,6 @@
 
 /* Additional NDS32 specific syscalls. */
 #define __NR_cacheflush		(__NR_arch_specific_syscall)
-#define __NR_udftrap		(__NR_arch_specific_syscall + 1)
+#define __NR_fp_udfiex_crtl	(__NR_arch_specific_syscall + 1)
 __SYSCALL(__NR_cacheflush, sys_cacheflush)
-__SYSCALL(__NR_udftrap, sys_udftrap)
+__SYSCALL(__NR_fp_udfiex_crtl, sys_fp_udfiex_crtl)