Received: by 2002:a05:6a11:4021:0:0:0:0 with SMTP id ky33csp3692671pxb; Sun, 26 Sep 2021 23:56:38 -0700 (PDT) X-Google-Smtp-Source: ABdhPJwS2unjqsZ7NMPdvcm2ZcndjqMvOJ/kYoSUvTnb3WSF8lP2F+oVpxooXGH4swYUgko+UgXA X-Received: by 2002:aa7:9282:0:b0:3e2:800a:b423 with SMTP id j2-20020aa79282000000b003e2800ab423mr22206608pfa.21.1632725798531; Sun, 26 Sep 2021 23:56:38 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1632725798; cv=none; d=google.com; s=arc-20160816; b=EfC697daDIStiV6vENyNeBlbOo1rdMQJjU9AkiyejizqYwYy+g1c7CgmuNK/9Jry7b euuR/PXqmYNUgDX0klfBzm1hbPGA91h750/HDdN7QUNsGbB2zmtFTb5M8H/2cmSaj4DL XPwdOsy+JxplXE4QgpwMVb/Q0KXQBZeGQl+UzOocZhQ+AtJ55wKQnCF9K+QEibyDqlu5 h77l+XsUh2lWCcFvybgoSuvuXElfx2LqC4y798XV1X0DWtbR/L1omHkqm5XvOSJ6eoAf OdyrZaUlvujUSSVH2thruojA7F5l7V4XJTe+nuh8cr8EvdtTOs60Thz6WMqwWa7O8eCZ jdMg== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=list-id:precedence:content-transfer-encoding:mime-version :references:in-reply-to:message-id:date:subject:cc:to:from; bh=UeT6suSwpw3nIxvBWTRzMrQyiUkEVaCK7tw9K7Z9I9U=; b=QtC3MoLPJuCwjEGReO1/O7dQpbqYYVYrxsuGzAHT2XKu6Wt/7Xc5My2IIxxQtdkfqo 9RxL1+Z6UlTM2/p41y+XSIrFftdE1yUXi4lxYYdQLaCq+kJSXat8fOqI0LI8TZw98JYB jg6l71Q0k+GEwOhORB8aKW7eEQFi16/Idc5P8gqwp0lVzKhn65du0diLqulqxAf1vu5j cgQGNaW2MvxceTmTOkl7YbNpomA2NH40n7YWAdQnguNNr61uWpi5gAVBC/5rkmcvz+cy Mal58obF26IBavRn7pcjUc2Gm0KVtQ2D3dpwg6W3lLfRjwpcj/P93W7h4poVKSSof1tB uW0Q== ARC-Authentication-Results: i=1; mx.google.com; spf=pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) smtp.mailfrom=linux-kernel-owner@vger.kernel.org Return-Path: Received: from vger.kernel.org (vger.kernel.org. [23.128.96.18]) by mx.google.com with ESMTP id a64si18861081pge.604.2021.09.26.23.56.26; Sun, 26 Sep 2021 23:56:38 -0700 (PDT) Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18; Authentication-Results: mx.google.com; spf=pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) smtp.mailfrom=linux-kernel-owner@vger.kernel.org Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S233143AbhI0G4F (ORCPT + 99 others); Mon, 27 Sep 2021 02:56:05 -0400 Received: from mail.kernel.org ([198.145.29.99]:44534 "EHLO mail.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S233067AbhI0G4E (ORCPT ); Mon, 27 Sep 2021 02:56:04 -0400 Received: by mail.kernel.org (Postfix) with ESMTPSA id 4D5C561041; Mon, 27 Sep 2021 06:54:23 +0000 (UTC) From: Huacai Chen To: Arnd Bergmann , Andy Lutomirski , Thomas Gleixner , Peter Zijlstra , Andrew Morton , David Airlie , Jonathan Corbet , Linus Torvalds Cc: linux-arch@vger.kernel.org, linux-doc@vger.kernel.org, linux-kernel@vger.kernel.org, Xuefeng Li , Yanteng Si , Huacai Chen , Jiaxun Yang , Huacai Chen Subject: [PATCH V4 17/22] LoongArch: Add some library functions Date: Mon, 27 Sep 2021 14:42:54 +0800 Message-Id: <20210927064300.624279-18-chenhuacai@loongson.cn> X-Mailer: git-send-email 2.27.0 In-Reply-To: <20210927064300.624279-1-chenhuacai@loongson.cn> References: <20210927064300.624279-1-chenhuacai@loongson.cn> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org This patch adds some library functions for LoongArch, including: delay, memset, memcpy, memmove, copy_user, strncpy_user, strnlen_user and tlb dump functions. Signed-off-by: Huacai Chen --- arch/loongarch/include/asm/delay.h | 26 +++++++ arch/loongarch/include/asm/string.h | 17 +++++ arch/loongarch/lib/clear_user.S | 43 +++++++++++ arch/loongarch/lib/copy_user.S | 47 ++++++++++++ arch/loongarch/lib/delay.c | 43 +++++++++++ arch/loongarch/lib/dump_tlb.c | 111 ++++++++++++++++++++++++++++ arch/loongarch/lib/memcpy.S | 32 ++++++++ arch/loongarch/lib/memmove.S | 45 +++++++++++ arch/loongarch/lib/memset.S | 30 ++++++++ 9 files changed, 394 insertions(+) create mode 100644 arch/loongarch/include/asm/delay.h create mode 100644 arch/loongarch/include/asm/string.h create mode 100644 arch/loongarch/lib/clear_user.S create mode 100644 arch/loongarch/lib/copy_user.S create mode 100644 arch/loongarch/lib/delay.c create mode 100644 arch/loongarch/lib/dump_tlb.c create mode 100644 arch/loongarch/lib/memcpy.S create mode 100644 arch/loongarch/lib/memmove.S create mode 100644 arch/loongarch/lib/memset.S diff --git a/arch/loongarch/include/asm/delay.h b/arch/loongarch/include/asm/delay.h new file mode 100644 index 000000000000..717227c1c79d --- /dev/null +++ b/arch/loongarch/include/asm/delay.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2020-2021 Loongson Technology Corporation Limited + */ +#ifndef _ASM_DELAY_H +#define _ASM_DELAY_H + +#include + +extern void __delay(unsigned long loops); +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 */ diff --git a/arch/loongarch/include/asm/string.h b/arch/loongarch/include/asm/string.h new file mode 100644 index 000000000000..21e9e0a58194 --- /dev/null +++ b/arch/loongarch/include/asm/string.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2020-2021 Loongson Technology Corporation Limited + */ +#ifndef _ASM_STRING_H +#define _ASM_STRING_H + +#define __HAVE_ARCH_MEMSET +extern void *memset(void *__s, int __c, size_t __count); + +#define __HAVE_ARCH_MEMCPY +extern void *memcpy(void *__to, __const__ void *__from, size_t __n); + +#define __HAVE_ARCH_MEMMOVE +extern void *memmove(void *__dest, __const__ void *__src, size_t __n); + +#endif /* _ASM_STRING_H */ diff --git a/arch/loongarch/lib/clear_user.S b/arch/loongarch/lib/clear_user.S new file mode 100644 index 000000000000..97b9998360cc --- /dev/null +++ b/arch/loongarch/lib/clear_user.S @@ -0,0 +1,43 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2020-2021 Loongson Technology Corporation Limited + */ + +#include +#include +#include +#include + +.macro fixup_ex from, to, offset, fix +.if \fix + .section .fixup, "ax" +\to: addi.d v0, 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 v0, a1 + jr ra + + fixup_ex 1, 3, 0, 1 +SYM_FUNC_END(__clear_user) + +EXPORT_SYMBOL(__clear_user) diff --git a/arch/loongarch/lib/copy_user.S b/arch/loongarch/lib/copy_user.S new file mode 100644 index 000000000000..b814efd9cbd2 --- /dev/null +++ b/arch/loongarch/lib/copy_user.S @@ -0,0 +1,47 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2020-2021 Loongson Technology Corporation Limited + */ + +#include +#include +#include +#include + +.macro fixup_ex from, to, offset, fix +.if \fix + .section .fixup, "ax" +\to: addi.d v0, 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 v0, a2 + jr ra + + fixup_ex 1, 4, 0, 1 + fixup_ex 2, 4, 0, 0 +SYM_FUNC_END(__copy_user) + +EXPORT_SYMBOL(__copy_user) diff --git a/arch/loongarch/lib/delay.c b/arch/loongarch/lib/delay.c new file mode 100644 index 000000000000..cf22f0899a9a --- /dev/null +++ b/arch/loongarch/lib/delay.c @@ -0,0 +1,43 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2020-2021 Loongson Technology Corporation Limited + */ +#include +#include +#include +#include + +#include +#include + +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); diff --git a/arch/loongarch/lib/dump_tlb.c b/arch/loongarch/lib/dump_tlb.c new file mode 100644 index 000000000000..21b55681a726 --- /dev/null +++ b/arch/loongarch/lib/dump_tlb.c @@ -0,0 +1,111 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2020-2021 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 +#include + +#include +#include +#include +#include + +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*lx\n", field, read_csr_entryhi()); + pr_info("EntryLo0 : %0*lx\n", field, read_csr_entrylo0()); + pr_info("EntryLo1 : %0*lx\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(¤t_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); + + /* RI/XI are in awkward places, so mask them off separately */ + pa = entrylo0 & ~(ENTRYLO_RI | ENTRYLO_XI); + pa = pa & PAGE_MASK; + pr_cont("\n\t["); + pr_cont("ri=%d xi=%d ", + (entrylo0 & ENTRYLO_RI) ? 1 : 0, + (entrylo0 & ENTRYLO_XI) ? 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); + /* RI/XI are in awkward places, so mask them off separately */ + pa = entrylo1 & ~(ENTRYLO_RI | ENTRYLO_XI); + pa = pa & PAGE_MASK; + pr_cont("ri=%d xi=%d ", + (entrylo1 & ENTRYLO_RI) ? 1 : 0, + (entrylo1 & ENTRYLO_XI) ? 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); +} diff --git a/arch/loongarch/lib/memcpy.S b/arch/loongarch/lib/memcpy.S new file mode 100644 index 000000000000..e94899d99624 --- /dev/null +++ b/arch/loongarch/lib/memcpy.S @@ -0,0 +1,32 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2020-2021 Loongson Technology Corporation Limited + */ + +#include +#include +#include + +/* + * void *memcpy(void *dst, const void *src, size_t n) + * + * a0: dst + * a1: src + * a2: n + */ +SYM_FUNC_START(memcpy) + move a3, a0 + beqz a2, 2f + +1: ld.b t0, a1, 0 + st.b t0, a0, 0 + addi.d a0, a0, 1 + addi.d a1, a1, 1 + addi.d a2, a2, -1 + bgt a2, zero, 1b + +2: move v0, a3 + jr ra +SYM_FUNC_END(memcpy) + +EXPORT_SYMBOL(memcpy) diff --git a/arch/loongarch/lib/memmove.S b/arch/loongarch/lib/memmove.S new file mode 100644 index 000000000000..f55d8dcd09dd --- /dev/null +++ b/arch/loongarch/lib/memmove.S @@ -0,0 +1,45 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2020-2021 Loongson Technology Corporation Limited + */ + +#include +#include +#include + +/* + * void *rmemcpy(void *dst, const void *src, size_t n) + * + * a0: dst + * a1: src + * a2: n + */ +SYM_FUNC_START(rmemcpy) + move a3, a0 + beqz a2, 2f + + add.d a0, a0, a2 + add.d a1, a1, a2 + +1: ld.b t0, a1, -1 + st.b t0, a0, -1 + addi.d a0, a0, -1 + addi.d a1, a1, -1 + addi.d a2, a2, -1 + bgt a2, zero, 1b + +2: move v0, a3 + jr ra +SYM_FUNC_END(rmemcpy) + +SYM_FUNC_START(memmove) + blt a0, a1, 1f /* dst < src, memcpy */ + blt a1, a0, 2f /* src < dst, rmemcpy */ + jr ra /* dst == src, return */ + +1: b memcpy + +2: b rmemcpy +SYM_FUNC_END(memmove) + +EXPORT_SYMBOL(memmove) diff --git a/arch/loongarch/lib/memset.S b/arch/loongarch/lib/memset.S new file mode 100644 index 000000000000..f599017e68fd --- /dev/null +++ b/arch/loongarch/lib/memset.S @@ -0,0 +1,30 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2020-2021 Loongson Technology Corporation Limited + */ + +#include +#include +#include + +/* + * void *memset(void *s, int c, size_t n) + * + * a0: s + * a1: c + * a2: n + */ +SYM_FUNC_START(memset) + move a3, a0 + beqz a2, 2f + +1: st.b a1, a0, 0 + addi.d a0, a0, 1 + addi.d a2, a2, -1 + bgt a2, zero, 1b + +2: move v0, a3 + jr ra +SYM_FUNC_END(memset) + +EXPORT_SYMBOL(memset) -- 2.27.0