summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
Diffstat
-rw-r--r--arch/nds32/Kconfig.cpu13
-rw-r--r--arch/nds32/include/asm/elf.h11
-rw-r--r--arch/nds32/include/asm/fpu.h11
-rw-r--r--arch/nds32/include/asm/syscalls.h1
-rw-r--r--arch/nds32/include/uapi/asm/auxvec.h7
-rw-r--r--arch/nds32/include/uapi/asm/sigcontext.h9
-rw-r--r--arch/nds32/include/uapi/asm/udftrap.h13
-rw-r--r--arch/nds32/include/uapi/asm/unistd.h2
-rw-r--r--arch/nds32/kernel/fpu.c25
-rw-r--r--arch/nds32/kernel/sys_nds32.c32
-rw-r--r--arch/nds32/math-emu/fpuemu.c5
11 files changed, 125 insertions, 4 deletions
diff --git a/arch/nds32/Kconfig.cpu b/arch/nds32/Kconfig.cpu
index bb06a1b7eef0..6482ed877f97 100644
--- a/arch/nds32/Kconfig.cpu
+++ b/arch/nds32/Kconfig.cpu
@@ -28,6 +28,19 @@ config LAZY_FPU
For nomal case, say Y.
+config SUPPORT_DENORMAL_ARITHMETIC
+ bool "Denormal arithmetic support"
+ depends on FPU
+ default n
+ help
+ Say Y here to enable arithmetic of denormalized number. Enabling
+ this feature can enhance the precision for tininess number.
+ However, performance loss in float pointe calculations is
+ possibly significant due to additional FPU exception.
+
+ If the calculated tolerance for tininess number is not critical,
+ say N to prevent performance loss.
+
config HWZOL
bool "hardware zero overhead loop support"
depends on CPU_D10 || CPU_D15
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)
diff --git a/arch/nds32/kernel/fpu.c b/arch/nds32/kernel/fpu.c
index 2942df6f93e6..fddd40c7a16f 100644
--- a/arch/nds32/kernel/fpu.c
+++ b/arch/nds32/kernel/fpu.c
@@ -12,7 +12,10 @@
const struct fpu_struct init_fpuregs = {
.fd_regs = {[0 ... 31] = sNAN64},
- .fpcsr = FPCSR_INIT
+ .fpcsr = FPCSR_INIT,
+#if IS_ENABLED(CONFIG_SUPPORT_DENORMAL_ARITHMETIC)
+ .UDF_trap = 0
+#endif
};
void save_fpu(struct task_struct *tsk)
@@ -174,6 +177,9 @@ inline void do_fpu_context_switch(struct pt_regs *regs)
} else {
/* First time FPU user. */
load_fpu(&init_fpuregs);
+#if IS_ENABLED(CONFIG_SUPPORT_DENORMAL_ARITHMETIC)
+ current->thread.fpu.UDF_trap = init_fpuregs.UDF_trap;
+#endif
set_used_math();
}
@@ -183,10 +189,12 @@ inline void fill_sigfpe_signo(unsigned int fpcsr, int *signo)
{
if (fpcsr & FPCSR_mskOVFT)
*signo = FPE_FLTOVF;
- else if (fpcsr & FPCSR_mskIVOT)
- *signo = FPE_FLTINV;
+#ifndef CONFIG_SUPPORT_DENORMAL_ARITHMETIC
else if (fpcsr & FPCSR_mskUDFT)
*signo = FPE_FLTUND;
+#endif
+ else if (fpcsr & FPCSR_mskIVOT)
+ *signo = FPE_FLTINV;
else if (fpcsr & FPCSR_mskDBZT)
*signo = FPE_FLTDIV;
else if (fpcsr & FPCSR_mskIEXT)
@@ -197,11 +205,20 @@ inline void handle_fpu_exception(struct pt_regs *regs)
{
unsigned int fpcsr;
int si_code = 0, si_signo = SIGFPE;
+#if IS_ENABLED(CONFIG_SUPPORT_DENORMAL_ARITHMETIC)
+ unsigned long redo_except = FPCSR_mskDNIT|FPCSR_mskUDFT;
+#else
+ unsigned long redo_except = FPCSR_mskDNIT;
+#endif
lose_fpu();
fpcsr = current->thread.fpu.fpcsr;
- if (fpcsr & FPCSR_mskDNIT) {
+ if (fpcsr & redo_except) {
+#if IS_ENABLED(CONFIG_SUPPORT_DENORMAL_ARITHMETIC)
+ if (fpcsr & FPCSR_mskUDFT)
+ current->thread.fpu.fpcsr &= ~FPCSR_mskIEX;
+#endif
si_signo = do_fpuemu(regs, &current->thread.fpu);
fpcsr = current->thread.fpu.fpcsr;
if (!si_signo)
diff --git a/arch/nds32/kernel/sys_nds32.c b/arch/nds32/kernel/sys_nds32.c
index 9de93ab4c52b..0835277636ce 100644
--- a/arch/nds32/kernel/sys_nds32.c
+++ b/arch/nds32/kernel/sys_nds32.c
@@ -6,6 +6,8 @@
#include <asm/cachectl.h>
#include <asm/proc-fns.h>
+#include <asm/udftrap.h>
+#include <asm/fpu.h>
SYSCALL_DEFINE6(mmap2, unsigned long, addr, unsigned long, len,
unsigned long, prot, unsigned long, flags,
@@ -48,3 +50,33 @@ SYSCALL_DEFINE3(cacheflush, unsigned int, start, unsigned int, end, int, cache)
return 0;
}
+
+SYSCALL_DEFINE1(udftrap, int, option)
+{
+#if IS_ENABLED(CONFIG_SUPPORT_DENORMAL_ARITHMETIC)
+ int old_udftrap;
+
+ if (!used_math()) {
+ load_fpu(&init_fpuregs);
+ current->thread.fpu.UDF_trap = init_fpuregs.UDF_trap;
+ set_used_math();
+ }
+
+ old_udftrap = current->thread.fpu.UDF_trap;
+ switch (option) {
+ case DISABLE_UDFTRAP:
+ current->thread.fpu.UDF_trap = 0;
+ break;
+ case ENABLE_UDFTRAP:
+ current->thread.fpu.UDF_trap = FPCSR_mskUDFE;
+ break;
+ case GET_UDFTRAP:
+ break;
+ default:
+ return -EINVAL;
+ }
+ return old_udftrap;
+#else
+ return -ENOTSUPP;
+#endif
+}
diff --git a/arch/nds32/math-emu/fpuemu.c b/arch/nds32/math-emu/fpuemu.c
index 2a01333d6e5f..75cf1643fa78 100644
--- a/arch/nds32/math-emu/fpuemu.c
+++ b/arch/nds32/math-emu/fpuemu.c
@@ -304,7 +304,12 @@ static int fpu_emu(struct fpu_struct *fpu_reg, unsigned long insn)
/*
* If an exception is required, generate a tidy SIGFPE exception.
*/
+#if IS_ENABLED(CONFIG_SUPPORT_DENORMAL_ARITHMETIC)
+ if (((fpu_reg->fpcsr << 5) & fpu_reg->fpcsr & FPCSR_mskALLE_NO_UDFE) ||
+ ((fpu_reg->fpcsr & FPCSR_mskUDF) && (fpu_reg->UDF_trap)))
+#else
if ((fpu_reg->fpcsr << 5) & fpu_reg->fpcsr & FPCSR_mskALLE)
+#endif
return SIGFPE;
return 0;
}
generated by cgit (git 2.34.1) at 2024-05-23 14:05:05 +0000