LoongArch: Add some library functions

mainline inclusion
from mainline-v5.19-rc1
commit 559671e0
category: feature
bugzilla: https://gitee.com/openeuler/kernel/issues/I5OHOB
CVE: NA

--------------------------------

Add some library functions for LoongArch, including: delay, memset,
memcpy, memmove, copy_user, strncpy_user, strnlen_user and tlb dump
functions.
Reviewed-by: NWANG Xuerui <git@xen0n.name>
Reviewed-by: NJiaxun Yang <jiaxun.yang@flygoat.com>
Signed-off-by: NHuacai Chen <chenhuacai@loongson.cn>

arch/loongarch/include/asm/delay.h

+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2020-2022 Loongson Technology Corporation Limited
+ */
+#ifndef _ASM_DELAY_H
+#define _ASM_DELAY_H
+
+#include <linux/param.h>
+
+extern void __delay(unsigned long cycles);
+extern void __ndelay(unsigned long ns);
+extern void __udelay(unsigned long us);
+
+#define ndelay(ns) __ndelay(ns)
+#define udelay(us) __udelay(us)
+
+/* make sure "usecs *= ..." in udelay do not overflow. */
+#if HZ >= 1000
+#define MAX_UDELAY_MS	1
+#elif HZ <= 200
+#define MAX_UDELAY_MS	5
+#else
+#define MAX_UDELAY_MS	(1000 / HZ)
+#endif
+
+#endif /* _ASM_DELAY_H */

arch/loongarch/include/asm/string.h

+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2020-2022 Loongson Technology Corporation Limited
+ */
+#ifndef _ASM_STRING_H
+#define _ASM_STRING_H
+
+extern void *memset(void *__s, int __c, size_t __count);
+extern void *memcpy(void *__to, __const__ void *__from, size_t __n);
+extern void *memmove(void *__dest, __const__ void *__src, size_t __n);
+
+#endif /* _ASM_STRING_H */

arch/loongarch/lib/Makefile

@@ -3,4 +3,4 @@
 # Makefile for LoongArch-specific library files.
 #
 
-lib-y	+= delay.o clear_user.o copy_user.o dump_tlb.o
+lib-y	+= delay.o clear_user.o strnlen_user.o strncpy_user.o copy_user.o dump_tlb.o

arch/loongarch/lib/clear_user.S

+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2020-2022 Loongson Technology Corporation Limited
+ */
+
+#include <asm/asm.h>
+#include <asm/asmmacro.h>
+#include <asm/export.h>
+#include <asm/regdef.h>
+
+.macro fixup_ex from, to, offset, fix
+.if \fix
+	.section .fixup, "ax"
+\to:	addi.d	a0, a1, \offset
+	jr	ra
+	.previous
+.endif
+	.section __ex_table, "a"
+	PTR	\from\()b, \to\()b
+	.previous
+.endm
+
+/*
+ * unsigned long __clear_user(void *addr, size_t size)
+ *
+ * a0: addr
+ * a1: size
+ */
+SYM_FUNC_START(__clear_user)
+	beqz	a1, 2f
+
+1:	st.b	zero, a0, 0
+	addi.d	a0, a0, 1
+	addi.d	a1, a1, -1
+	bgt	a1, zero, 1b
+
+2:	move	a0, a1
+	jr	ra
+
+	fixup_ex 1, 3, 0, 1
+SYM_FUNC_END(__clear_user)
+
+EXPORT_SYMBOL(__clear_user)

arch/loongarch/lib/copy_user.S

+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2020-2022 Loongson Technology Corporation Limited
+ */
+
+#include <asm/asm.h>
+#include <asm/asmmacro.h>
+#include <asm/export.h>
+#include <asm/regdef.h>
+
+.macro fixup_ex from, to, offset, fix
+.if \fix
+	.section .fixup, "ax"
+\to:	addi.d	a0, a2, \offset
+	jr	ra
+	.previous
+.endif
+	.section __ex_table, "a"
+	PTR	\from\()b, \to\()b
+	.previous
+.endm
+
+/*
+ * unsigned long __copy_user(void *to, const void *from, size_t n)
+ *
+ * a0: to
+ * a1: from
+ * a2: n
+ */
+SYM_FUNC_START(__copy_user)
+	beqz	a2, 3f
+
+1:	ld.b	t0, a1, 0
+2:	st.b	t0, a0, 0
+	addi.d	a0, a0, 1
+	addi.d	a1, a1, 1
+	addi.d	a2, a2, -1
+	bgt	a2, zero, 1b
+
+3:	move	a0, a2
+	jr	ra
+
+	fixup_ex 1, 4, 0, 1
+	fixup_ex 2, 4, 0, 0
+SYM_FUNC_END(__copy_user)
+
+EXPORT_SYMBOL(__copy_user)

arch/loongarch/lib/delay.c

+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2020-2022 Loongson Technology Corporation Limited
+ */
+#include <linux/delay.h>
+#include <linux/export.h>
+#include <linux/smp.h>
+#include <linux/timex.h>
+
+#include <asm/compiler.h>
+#include <asm/processor.h>
+
+void __delay(unsigned long cycles)
+{
+	u64 t0 = get_cycles();
+
+	while ((unsigned long)(get_cycles() - t0) < cycles)
+		cpu_relax();
+}
+EXPORT_SYMBOL(__delay);
+
+/*
+ * Division by multiplication: you don't have to worry about
+ * loss of precision.
+ *
+ * Use only for very small delays ( < 1 msec).	Should probably use a
+ * lookup table, really, as the multiplications take much too long with
+ * short delays.  This is a "reasonable" implementation, though (and the
+ * first constant multiplications gets optimized away if the delay is
+ * a constant)
+ */
+
+void __udelay(unsigned long us)
+{
+	__delay((us * 0x000010c7ull * HZ * lpj_fine) >> 32);
+}
+EXPORT_SYMBOL(__udelay);
+
+void __ndelay(unsigned long ns)
+{
+	__delay((ns * 0x00000005ull * HZ * lpj_fine) >> 32);
+}
+EXPORT_SYMBOL(__ndelay);

arch/loongarch/lib/dump_tlb.c

+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2020-2022 Loongson Technology Corporation Limited
+ *
+ * Derived from MIPS:
+ * Copyright (C) 1994, 1995 by Waldorf Electronics, written by Ralf Baechle.
+ * Copyright (C) 1999 by Silicon Graphics, Inc.
+ */
+#include <linux/kernel.h>
+#include <linux/mm.h>
+
+#include <asm/loongarch.h>
+#include <asm/page.h>
+#include <asm/pgtable.h>
+#include <asm/tlb.h>
+
+void dump_tlb_regs(void)
+{
+	const int field = 2 * sizeof(unsigned long);
+
+	pr_info("Index    : %0x\n", read_csr_tlbidx());
+	pr_info("PageSize : %0x\n", read_csr_pagesize());
+	pr_info("EntryHi  : %0*llx\n", field, read_csr_entryhi());
+	pr_info("EntryLo0 : %0*llx\n", field, read_csr_entrylo0());
+	pr_info("EntryLo1 : %0*llx\n", field, read_csr_entrylo1());
+}
+
+static void dump_tlb(int first, int last)
+{
+	unsigned long s_entryhi, entryhi, asid;
+	unsigned long long entrylo0, entrylo1, pa;
+	unsigned int index;
+	unsigned int s_index, s_asid;
+	unsigned int pagesize, c0, c1, i;
+	unsigned long asidmask = cpu_asid_mask(&current_cpu_data);
+	int pwidth = 11;
+	int vwidth = 11;
+	int asidwidth = DIV_ROUND_UP(ilog2(asidmask) + 1, 4);
+
+	s_entryhi = read_csr_entryhi();
+	s_index = read_csr_tlbidx();
+	s_asid = read_csr_asid();
+
+	for (i = first; i <= last; i++) {
+		write_csr_index(i);
+		tlb_read();
+		pagesize = read_csr_pagesize();
+		entryhi	 = read_csr_entryhi();
+		entrylo0 = read_csr_entrylo0();
+		entrylo1 = read_csr_entrylo1();
+		index = read_csr_tlbidx();
+		asid = read_csr_asid();
+
+		/* EHINV bit marks entire entry as invalid */
+		if (index & CSR_TLBIDX_EHINV)
+			continue;
+		/*
+		 * ASID takes effect in absence of G (global) bit.
+		 */
+		if (!((entrylo0 | entrylo1) & ENTRYLO_G) &&
+		    asid != s_asid)
+			continue;
+
+		/*
+		 * Only print entries in use
+		 */
+		pr_info("Index: %2d pgsize=%x ", i, (1 << pagesize));
+
+		c0 = (entrylo0 & ENTRYLO_C) >> ENTRYLO_C_SHIFT;
+		c1 = (entrylo1 & ENTRYLO_C) >> ENTRYLO_C_SHIFT;
+
+		pr_cont("va=%0*lx asid=%0*lx",
+			vwidth, (entryhi & ~0x1fffUL), asidwidth, asid & asidmask);
+
+		/* NR/NX are in awkward places, so mask them off separately */
+		pa = entrylo0 & ~(ENTRYLO_NR | ENTRYLO_NX);
+		pa = pa & PAGE_MASK;
+		pr_cont("\n\t[");
+		pr_cont("ri=%d xi=%d ",
+			(entrylo0 & ENTRYLO_NR) ? 1 : 0,
+			(entrylo0 & ENTRYLO_NX) ? 1 : 0);
+		pr_cont("pa=%0*llx c=%d d=%d v=%d g=%d plv=%lld] [",
+			pwidth, pa, c0,
+			(entrylo0 & ENTRYLO_D) ? 1 : 0,
+			(entrylo0 & ENTRYLO_V) ? 1 : 0,
+			(entrylo0 & ENTRYLO_G) ? 1 : 0,
+			(entrylo0 & ENTRYLO_PLV) >> ENTRYLO_PLV_SHIFT);
+		/* NR/NX are in awkward places, so mask them off separately */
+		pa = entrylo1 & ~(ENTRYLO_NR | ENTRYLO_NX);
+		pa = pa & PAGE_MASK;
+		pr_cont("ri=%d xi=%d ",
+			(entrylo1 & ENTRYLO_NR) ? 1 : 0,
+			(entrylo1 & ENTRYLO_NX) ? 1 : 0);
+		pr_cont("pa=%0*llx c=%d d=%d v=%d g=%d plv=%lld]\n",
+			pwidth, pa, c1,
+			(entrylo1 & ENTRYLO_D) ? 1 : 0,
+			(entrylo1 & ENTRYLO_V) ? 1 : 0,
+			(entrylo1 & ENTRYLO_G) ? 1 : 0,
+			(entrylo1 & ENTRYLO_PLV) >> ENTRYLO_PLV_SHIFT);
+	}
+	pr_info("\n");
+
+	write_csr_entryhi(s_entryhi);
+	write_csr_tlbidx(s_index);
+	write_csr_asid(s_asid);
+}
+
+void dump_tlb_all(void)
+{
+	dump_tlb(0, current_cpu_data.tlbsize - 1);
+}

arch/loongarch/lib/strncpy_user.S

+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2020-2021 Loongson Technology Corporation Limited
+ */
+#include <linux/errno.h>
+#include <asm/asm.h>
+#include <asm/asmmacro.h>
+#include <asm/export.h>
+#include <asm/regdef.h>
+
+/*
+ * long __strncpy_from_user(char *to, const char *from, long len)
+ *
+ * a0: to
+ * a1: from
+ * a2: len
+ */
+SYM_FUNC_START(__strncpy_from_user)
+	move	a3, zero
+
+1:	ld.b	t0, a1, 0
+	st.b	t0, a0, 0
+	addi.d	a0, a0, 1
+	addi.d	a1, a1, 1
+	beqz	t0, 2f
+
+	addi.d	a3, a3, 1
+	blt	a3, a2, 1b
+
+	/*
+	 * return len if the entire buffer filled,
+	 * return strlen else
+	 */
+2:	move	a0, a3
+	jr	ra
+
+	.section .fixup, "ax"
+	/* return -EFAULT if exception before terminator */
+3:	li.w	a0, -EFAULT
+	jr	ra
+	.previous
+
+	.section __ex_table, "a"
+	PTR	1b, 3b
+	.previous
+SYM_FUNC_END(__strncpy_from_user)
+
+EXPORT_SYMBOL(__strncpy_from_user)

arch/loongarch/lib/strnlen_user.S

+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2020-2021 Loongson Technology Corporation Limited
+ */
+#include <asm/asm.h>
+#include <asm/asmmacro.h>
+#include <asm/export.h>
+#include <asm/regdef.h>
+
+/*
+ * long __strnlen_user(const char *s, long n)
+ *
+ * a0: s
+ * a1: n
+ */
+SYM_FUNC_START(__strnlen_user)
+	move	a2, zero
+
+1:	ld.b	t0, a0, 0
+	addi.d	a0, a0, 1
+	addi.d	a2, a2, 1
+	beqz	t0, 2f
+
+	bge	a1, a2, 1b
+
+	/*
+	 * return the size of a string including the ending NUL character
+	 * up to a maximum of n
+	 */
+2:	move	a0, a2
+	jr	ra
+
+	.section .fixup, "ax"
+	/* return 0 in case of error */
+3:	move	a0, zero
+	jr	ra
+	.previous
+
+	.section __ex_table, "a"
+	PTR	1b, 3b
+	.previous
+SYM_FUNC_END(__strnlen_user)
+
+EXPORT_SYMBOL(__strnlen_user)