Merge tag 'loongarch-6.4' of...

Merge tag 'loongarch-6.4' of git://git.kernel.org/pub/scm/linux/kernel/git/chenhuacai/linux-loongson

Pull LoongArch updates from Huacai Chen:

 - Better backtraces for humanization

 - Relay BCE exceptions to userland as SIGSEGV

 - Provide kernel fpu functions

 - Optimize memory ops (memset/memcpy/memmove)

 - Optimize checksum and crc32(c) calculation

 - Add ARCH_HAS_FORTIFY_SOURCE selection

 - Add function error injection support

 - Add ftrace with direct call support

 - Add basic perf tools support

* tag 'loongarch-6.4' of git://git.kernel.org/pub/scm/linux/kernel/git/chenhuacai/linux-loongson: (24 commits)
  tools/perf: Add basic support for LoongArch
  LoongArch: ftrace: Add direct call trampoline samples support
  LoongArch: ftrace: Add direct call support
  LoongArch: ftrace: Implement ftrace_find_callable_addr() to simplify code
  LoongArch: ftrace: Fix build error if DYNAMIC_FTRACE_WITH_REGS is not set
  LoongArch: ftrace: Abstract DYNAMIC_FTRACE_WITH_ARGS accesses
  LoongArch: Add support for function error injection
  LoongArch: Add ARCH_HAS_FORTIFY_SOURCE selection
  LoongArch: crypto: Add crc32 and crc32c hw acceleration
  LoongArch: Add checksum optimization for 64-bit system
  LoongArch: Optimize memory ops (memset/memcpy/memmove)
  LoongArch: Provide kernel fpu functions
  LoongArch: Relay BCE exceptions to userland as SIGSEGV with si_code=SEGV_BNDERR
  LoongArch: Tweak the BADV and CPUCFG.PRID lines in show_regs()
  LoongArch: Humanize the ESTAT line when showing registers
  LoongArch: Humanize the ECFG line when showing registers
  LoongArch: Humanize the EUEN line when showing registers
  LoongArch: Humanize the PRMD line when showing registers
  LoongArch: Humanize the CRMD line when showing registers
  LoongArch: Fix format of CSR lines during show_regs()
  ...

arch/loongarch/Kconfig

@@ -10,6 +10,7 @@ config LOONGARCH
 	select ARCH_ENABLE_MEMORY_HOTPLUG
 	select ARCH_ENABLE_MEMORY_HOTREMOVE
 	select ARCH_HAS_ACPI_TABLE_UPGRADE	if ACPI
+	select ARCH_HAS_FORTIFY_SOURCE
 	select ARCH_HAS_NMI_SAFE_THIS_CPU_OPS
 	select ARCH_HAS_PTE_SPECIAL
 	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
@@ -93,6 +94,7 @@ config LOONGARCH
 	select HAVE_DMA_CONTIGUOUS
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_DYNAMIC_FTRACE_WITH_ARGS
+	select HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
 	select HAVE_DYNAMIC_FTRACE_WITH_REGS
 	select HAVE_EBPF_JIT
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS if !ARCH_STRICT_ALIGN
@@ -100,6 +102,7 @@ config LOONGARCH
 	select HAVE_FAST_GUP
 	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_FUNCTION_ARG_ACCESS_API
+	select HAVE_FUNCTION_ERROR_INJECTION
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FUNCTION_TRACER
 	select HAVE_GENERIC_VDSO
@@ -118,6 +121,8 @@ config LOONGARCH
 	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_RSEQ
+	select HAVE_SAMPLE_FTRACE_DIRECT
+	select HAVE_SAMPLE_FTRACE_DIRECT_MULTI
 	select HAVE_SETUP_PER_CPU_AREA if NUMA
 	select HAVE_STACKPROTECTOR
 	select HAVE_SYSCALL_TRACEPOINTS

arch/loongarch/Makefile

@@ -115,6 +115,8 @@ endif
 libs-y += arch/loongarch/lib/
 libs-$(CONFIG_EFI_STUB) += $(objtree)/drivers/firmware/efi/libstub/lib.a
 
+drivers-y		+= arch/loongarch/crypto/
+
 # suspend and hibernation support
 drivers-$(CONFIG_PM)	+= arch/loongarch/power/
 

arch/loongarch/crypto/Kconfig

+# SPDX-License-Identifier: GPL-2.0
+
+menu "Accelerated Cryptographic Algorithms for CPU (loongarch)"
+
+config CRYPTO_CRC32_LOONGARCH
+	tristate "CRC32c and CRC32"
+	select CRC32
+	select CRYPTO_HASH
+	help
+	  CRC32c and CRC32 CRC algorithms
+
+	  Architecture: LoongArch with CRC32 instructions
+
+endmenu

arch/loongarch/crypto/Makefile

+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for LoongArch crypto files..
+#
+
+obj-$(CONFIG_CRYPTO_CRC32_LOONGARCH) += crc32-loongarch.o

arch/loongarch/crypto/crc32-loongarch.c

+// SPDX-License-Identifier: GPL-2.0
+/*
+ * crc32.c - CRC32 and CRC32C using LoongArch crc* instructions
+ *
+ * Module based on mips/crypto/crc32-mips.c
+ *
+ * Copyright (C) 2014 Linaro Ltd <yazen.ghannam@linaro.org>
+ * Copyright (C) 2018 MIPS Tech, LLC
+ * Copyright (C) 2020-2023 Loongson Technology Corporation Limited
+ */
+
+#include <linux/module.h>
+#include <crypto/internal/hash.h>
+
+#include <asm/cpu-features.h>
+#include <asm/unaligned.h>
+
+#define _CRC32(crc, value, size, type)			\
+do {							\
+	__asm__ __volatile__(				\
+		#type ".w." #size ".w" " %0, %1, %0\n\t"\
+		: "+r" (crc)				\
+		: "r" (value)				\
+		: "memory");				\
+} while (0)
+
+#define CRC32(crc, value, size)		_CRC32(crc, value, size, crc)
+#define CRC32C(crc, value, size)	_CRC32(crc, value, size, crcc)
+
+static u32 crc32_loongarch_hw(u32 crc_, const u8 *p, unsigned int len)
+{
+	u32 crc = crc_;
+
+	while (len >= sizeof(u64)) {
+		u64 value = get_unaligned_le64(p);
+
+		CRC32(crc, value, d);
+		p += sizeof(u64);
+		len -= sizeof(u64);
+	}
+
+	if (len & sizeof(u32)) {
+		u32 value = get_unaligned_le32(p);
+
+		CRC32(crc, value, w);
+		p += sizeof(u32);
+		len -= sizeof(u32);
+	}
+
+	if (len & sizeof(u16)) {
+		u16 value = get_unaligned_le16(p);
+
+		CRC32(crc, value, h);
+		p += sizeof(u16);
+	}
+
+	if (len & sizeof(u8)) {
+		u8 value = *p++;
+
+		CRC32(crc, value, b);
+	}
+
+	return crc;
+}
+
+static u32 crc32c_loongarch_hw(u32 crc_, const u8 *p, unsigned int len)
+{
+	u32 crc = crc_;
+
+	while (len >= sizeof(u64)) {
+		u64 value = get_unaligned_le64(p);
+
+		CRC32C(crc, value, d);
+		p += sizeof(u64);
+		len -= sizeof(u64);
+	}
+
+	if (len & sizeof(u32)) {
+		u32 value = get_unaligned_le32(p);
+
+		CRC32C(crc, value, w);
+		p += sizeof(u32);
+		len -= sizeof(u32);
+	}
+
+	if (len & sizeof(u16)) {
+		u16 value = get_unaligned_le16(p);
+
+		CRC32C(crc, value, h);
+		p += sizeof(u16);
+	}
+
+	if (len & sizeof(u8)) {
+		u8 value = *p++;
+
+		CRC32C(crc, value, b);
+	}
+
+	return crc;
+}
+
+#define CHKSUM_BLOCK_SIZE	1
+#define CHKSUM_DIGEST_SIZE	4
+
+struct chksum_ctx {
+	u32 key;
+};
+
+struct chksum_desc_ctx {
+	u32 crc;
+};
+
+static int chksum_init(struct shash_desc *desc)
+{
+	struct chksum_ctx *mctx = crypto_shash_ctx(desc->tfm);
+	struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
+
+	ctx->crc = mctx->key;
+
+	return 0;
+}
+
+/*
+ * Setting the seed allows arbitrary accumulators and flexible XOR policy
+ * If your algorithm starts with ~0, then XOR with ~0 before you set the seed.
+ */
+static int chksum_setkey(struct crypto_shash *tfm, const u8 *key, unsigned int keylen)
+{
+	struct chksum_ctx *mctx = crypto_shash_ctx(tfm);
+
+	if (keylen != sizeof(mctx->key))
+		return -EINVAL;
+
+	mctx->key = get_unaligned_le32(key);
+
+	return 0;
+}
+
+static int chksum_update(struct shash_desc *desc, const u8 *data, unsigned int length)
+{
+	struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
+
+	ctx->crc = crc32_loongarch_hw(ctx->crc, data, length);
+	return 0;
+}
+
+static int chksumc_update(struct shash_desc *desc, const u8 *data, unsigned int length)
+{
+	struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
+
+	ctx->crc = crc32c_loongarch_hw(ctx->crc, data, length);
+	return 0;
+}
+
+static int chksum_final(struct shash_desc *desc, u8 *out)
+{
+	struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
+
+	put_unaligned_le32(ctx->crc, out);
+	return 0;
+}
+
+static int chksumc_final(struct shash_desc *desc, u8 *out)
+{
+	struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
+
+	put_unaligned_le32(~ctx->crc, out);
+	return 0;
+}
+
+static int __chksum_finup(u32 crc, const u8 *data, unsigned int len, u8 *out)
+{
+	put_unaligned_le32(crc32_loongarch_hw(crc, data, len), out);
+	return 0;
+}
+
+static int __chksumc_finup(u32 crc, const u8 *data, unsigned int len, u8 *out)
+{
+	put_unaligned_le32(~crc32c_loongarch_hw(crc, data, len), out);
+	return 0;
+}
+
+static int chksum_finup(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out)
+{
+	struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
+
+	return __chksum_finup(ctx->crc, data, len, out);
+}
+
+static int chksumc_finup(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out)
+{
+	struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
+
+	return __chksumc_finup(ctx->crc, data, len, out);
+}
+
+static int chksum_digest(struct shash_desc *desc, const u8 *data, unsigned int length, u8 *out)
+{
+	struct chksum_ctx *mctx = crypto_shash_ctx(desc->tfm);
+
+	return __chksum_finup(mctx->key, data, length, out);
+}
+
+static int chksumc_digest(struct shash_desc *desc, const u8 *data, unsigned int length, u8 *out)
+{
+	struct chksum_ctx *mctx = crypto_shash_ctx(desc->tfm);
+
+	return __chksumc_finup(mctx->key, data, length, out);
+}
+
+static int chksum_cra_init(struct crypto_tfm *tfm)
+{
+	struct chksum_ctx *mctx = crypto_tfm_ctx(tfm);
+
+	mctx->key = 0;
+	return 0;
+}
+
+static int chksumc_cra_init(struct crypto_tfm *tfm)
+{
+	struct chksum_ctx *mctx = crypto_tfm_ctx(tfm);
+
+	mctx->key = ~0;
+	return 0;
+}
+
+static struct shash_alg crc32_alg = {
+	.digestsize		=	CHKSUM_DIGEST_SIZE,
+	.setkey			=	chksum_setkey,
+	.init			=	chksum_init,
+	.update			=	chksum_update,
+	.final			=	chksum_final,
+	.finup			=	chksum_finup,
+	.digest			=	chksum_digest,
+	.descsize		=	sizeof(struct chksum_desc_ctx),
+	.base			=	{
+		.cra_name		=	"crc32",
+		.cra_driver_name	=	"crc32-loongarch",
+		.cra_priority		=	300,
+		.cra_flags		=	CRYPTO_ALG_OPTIONAL_KEY,
+		.cra_blocksize		=	CHKSUM_BLOCK_SIZE,
+		.cra_alignmask		=	0,
+		.cra_ctxsize		=	sizeof(struct chksum_ctx),
+		.cra_module		=	THIS_MODULE,
+		.cra_init		=	chksum_cra_init,
+	}
+};
+
+static struct shash_alg crc32c_alg = {
+	.digestsize		=	CHKSUM_DIGEST_SIZE,
+	.setkey			=	chksum_setkey,
+	.init			=	chksum_init,
+	.update			=	chksumc_update,
+	.final			=	chksumc_final,
+	.finup			=	chksumc_finup,
+	.digest			=	chksumc_digest,
+	.descsize		=	sizeof(struct chksum_desc_ctx),
+	.base			=	{
+		.cra_name		=	"crc32c",
+		.cra_driver_name	=	"crc32c-loongarch",
+		.cra_priority		=	300,
+		.cra_flags		=	CRYPTO_ALG_OPTIONAL_KEY,
+		.cra_blocksize		=	CHKSUM_BLOCK_SIZE,
+		.cra_alignmask		=	0,
+		.cra_ctxsize		=	sizeof(struct chksum_ctx),
+		.cra_module		=	THIS_MODULE,
+		.cra_init		=	chksumc_cra_init,
+	}
+};
+
+static int __init crc32_mod_init(void)
+{
+	int err;
+
+	if (!cpu_has(CPU_FEATURE_CRC32))
+		return 0;
+
+	err = crypto_register_shash(&crc32_alg);
+	if (err)
+		return err;
+
+	err = crypto_register_shash(&crc32c_alg);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+static void __exit crc32_mod_exit(void)
+{
+	if (!cpu_has(CPU_FEATURE_CRC32))
+		return;
+
+	crypto_unregister_shash(&crc32_alg);
+	crypto_unregister_shash(&crc32c_alg);
+}
+
+module_init(crc32_mod_init);
+module_exit(crc32_mod_exit);
+
+MODULE_AUTHOR("Min Zhou <zhoumin@loongson.cn>");
+MODULE_AUTHOR("Huacai Chen <chenhuacai@loongson.cn>");
+MODULE_DESCRIPTION("CRC32 and CRC32C using LoongArch crc* instructions");
+MODULE_LICENSE("GPL v2");

arch/loongarch/include/asm/checksum.h

+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2016 ARM Ltd.
+ * Copyright (C) 2023 Loongson Technology Corporation Limited
+ */
+#ifndef __ASM_CHECKSUM_H
+#define __ASM_CHECKSUM_H
+
+#include <linux/bitops.h>
+#include <linux/in6.h>
+
+#define _HAVE_ARCH_IPV6_CSUM
+__sum16 csum_ipv6_magic(const struct in6_addr *saddr,
+			const struct in6_addr *daddr,
+			__u32 len, __u8 proto, __wsum sum);
+
+/*
+ * turns a 32-bit partial checksum (e.g. from csum_partial) into a
+ * 1's complement 16-bit checksum.
+ */
+static inline __sum16 csum_fold(__wsum sum)
+{
+	u32 tmp = (__force u32)sum;
+
+	/*
+	 * swap the two 16-bit halves of sum
+	 * if there is a carry from adding the two 16-bit halves,
+	 * it will carry from the lower half into the upper half,
+	 * giving us the correct sum in the upper half.
+	 */
+	return (__force __sum16)(~(tmp + rol32(tmp, 16)) >> 16);
+}
+#define csum_fold csum_fold
+
+/*
+ * This is a version of ip_compute_csum() optimized for IP headers,
+ * which always checksum on 4 octet boundaries.  ihl is the number
+ * of 32-bit words and is always >= 5.
+ */
+static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
+{
+	u64 sum;
+	__uint128_t tmp;
+	int n = ihl; /* we want it signed */
+
+	tmp = *(const __uint128_t *)iph;
+	iph += 16;
+	n -= 4;
+	tmp += ((tmp >> 64) | (tmp << 64));
+	sum = tmp >> 64;
+	do {
+		sum += *(const u32 *)iph;
+		iph += 4;
+	} while (--n > 0);
+
+	sum += ror64(sum, 32);
+	return csum_fold((__force __wsum)(sum >> 32));
+}
+#define ip_fast_csum ip_fast_csum
+
+extern unsigned int do_csum(const unsigned char *buff, int len);
+#define do_csum do_csum
+
+#include <asm-generic/checksum.h>
+
+#endif	/* __ASM_CHECKSUM_H */

arch/loongarch/include/asm/fpu.h

@@ -21,6 +21,9 @@
 
 struct sigcontext;
 
+extern void kernel_fpu_begin(void);
+extern void kernel_fpu_end(void);
+
 extern void _init_fpu(unsigned int);
 extern void _save_fp(struct loongarch_fpu *);
 extern void _restore_fp(struct loongarch_fpu *);

arch/loongarch/include/asm/ftrace.h

@@ -54,9 +54,46 @@ static __always_inline struct pt_regs *arch_ftrace_get_regs(struct ftrace_regs *
 	return &fregs->regs;
 }
 
+static __always_inline unsigned long
+ftrace_regs_get_instruction_pointer(struct ftrace_regs *fregs)
+{
+	return instruction_pointer(&fregs->regs);
+}
+
+static __always_inline void
+ftrace_regs_set_instruction_pointer(struct ftrace_regs *fregs, unsigned long ip)
+{
+	regs_set_return_value(&fregs->regs, ip);
+}
+
+#define ftrace_regs_get_argument(fregs, n) \
+	regs_get_kernel_argument(&(fregs)->regs, n)
+#define ftrace_regs_get_stack_pointer(fregs) \
+	kernel_stack_pointer(&(fregs)->regs)
+#define ftrace_regs_return_value(fregs) \
+	regs_return_value(&(fregs)->regs)
+#define ftrace_regs_set_return_value(fregs, ret) \
+	regs_set_return_value(&(fregs)->regs, ret)
+#define ftrace_override_function_with_return(fregs) \
+	override_function_with_return(&(fregs)->regs)
+#define ftrace_regs_query_register_offset(name) \
+	regs_query_register_offset(name)
+
 #define ftrace_graph_func ftrace_graph_func
 void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
 		       struct ftrace_ops *op, struct ftrace_regs *fregs);
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
+static inline void
+__arch_ftrace_set_direct_caller(struct pt_regs *regs, unsigned long addr)
+{
+	regs->regs[13] = addr;	/* t1 */
+}
+
+#define arch_ftrace_set_direct_caller(fregs, addr) \
+	__arch_ftrace_set_direct_caller(&(fregs)->regs, addr)
+#endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */
+
 #endif
 
 #endif /* __ASSEMBLY__ */

arch/loongarch/include/asm/inst.h

@@ -121,6 +121,8 @@ enum reg2bstrd_op {
 };
 
 enum reg3_op {
+	asrtle_op	= 0x02,
+	asrtgt_op	= 0x03,
 	addw_op		= 0x20,
 	addd_op		= 0x21,
 	subw_op		= 0x22,
@@ -176,6 +178,30 @@ enum reg3_op {
 	amord_op	= 0x70c7,
 	amxorw_op	= 0x70c8,
 	amxord_op	= 0x70c9,
+	fldgts_op	= 0x70e8,
+	fldgtd_op	= 0x70e9,
+	fldles_op	= 0x70ea,
+	fldled_op	= 0x70eb,
+	fstgts_op	= 0x70ec,
+	fstgtd_op	= 0x70ed,
+	fstles_op	= 0x70ee,
+	fstled_op	= 0x70ef,
+	ldgtb_op	= 0x70f0,
+	ldgth_op	= 0x70f1,
+	ldgtw_op	= 0x70f2,
+	ldgtd_op	= 0x70f3,
+	ldleb_op	= 0x70f4,
+	ldleh_op	= 0x70f5,
+	ldlew_op	= 0x70f6,
+	ldled_op	= 0x70f7,
+	stgtb_op	= 0x70f8,
+	stgth_op	= 0x70f9,
+	stgtw_op	= 0x70fa,
+	stgtd_op	= 0x70fb,
+	stleb_op	= 0x70fc,
+	stleh_op	= 0x70fd,
+	stlew_op	= 0x70fe,
+	stled_op	= 0x70ff,
 };
 
 enum reg3sa2_op {

arch/loongarch/include/asm/loongarch.h

@@ -311,8 +311,8 @@ static __always_inline void iocsr_write64(u64 val, u32 reg)
 #define  CSR_ECFG_VS_WIDTH		3
 #define  CSR_ECFG_VS			(_ULCAST_(0x7) << CSR_ECFG_VS_SHIFT)
 #define  CSR_ECFG_IM_SHIFT		0
-#define  CSR_ECFG_IM_WIDTH		13
-#define  CSR_ECFG_IM			(_ULCAST_(0x1fff) << CSR_ECFG_IM_SHIFT)
+#define  CSR_ECFG_IM_WIDTH		14
+#define  CSR_ECFG_IM			(_ULCAST_(0x3fff) << CSR_ECFG_IM_SHIFT)
 
 #define LOONGARCH_CSR_ESTAT		0x5	/* Exception status */
 #define  CSR_ESTAT_ESUBCODE_SHIFT	22
@@ -322,8 +322,8 @@ static __always_inline void iocsr_write64(u64 val, u32 reg)
 #define  CSR_ESTAT_EXC_WIDTH		6
 #define  CSR_ESTAT_EXC			(_ULCAST_(0x3f) << CSR_ESTAT_EXC_SHIFT)
 #define  CSR_ESTAT_IS_SHIFT		0
-#define  CSR_ESTAT_IS_WIDTH		15
-#define  CSR_ESTAT_IS			(_ULCAST_(0x7fff) << CSR_ESTAT_IS_SHIFT)
+#define  CSR_ESTAT_IS_WIDTH		14
+#define  CSR_ESTAT_IS			(_ULCAST_(0x3fff) << CSR_ESTAT_IS_SHIFT)
 
 #define LOONGARCH_CSR_ERA		0x6	/* ERA */
 
@@ -1090,7 +1090,7 @@ static __always_inline void iocsr_write64(u64 val, u32 reg)
 #define ECFGF_IPI		(_ULCAST_(1) << ECFGB_IPI)
 #define ECFGF(hwirq)		(_ULCAST_(1) << hwirq)
 
-#define ESTATF_IP		0x00001fff
+#define ESTATF_IP		0x00003fff
 
 #define LOONGARCH_IOCSR_FEATURES	0x8
 #define  IOCSRF_TEMP			BIT_ULL(0)
@@ -1397,7 +1397,7 @@ __BUILD_CSR_OP(tlbidx)
 	#define EXSUBCODE_ADEF		0	/* Fetch Instruction */
 	#define EXSUBCODE_ADEM		1	/* Access Memory*/
 #define EXCCODE_ALE		9	/* Unalign Access */
-#define EXCCODE_OOB		10	/* Out of bounds */
+#define EXCCODE_BCE		10	/* Bounds Check Error */
 #define EXCCODE_SYS		11	/* System call */
 #define EXCCODE_BP		12	/* Breakpoint */
 #define EXCCODE_INE		13	/* Inst. Not Exist */
@@ -1408,33 +1408,38 @@ __BUILD_CSR_OP(tlbidx)
 #define EXCCODE_FPE		18	/* Floating Point Exception */
 	#define EXCSUBCODE_FPE		0	/* Floating Point Exception */
 	#define EXCSUBCODE_VFPE		1	/* Vector Exception */
-#define EXCCODE_WATCH		19	/* Watch address reference */
+#define EXCCODE_WATCH		19	/* WatchPoint Exception */
+	#define EXCSUBCODE_WPEF		0	/* ... on Instruction Fetch */
+	#define EXCSUBCODE_WPEM		1	/* ... on Memory Accesses */
 #define EXCCODE_BTDIS		20	/* Binary Trans. Disabled */
 #define EXCCODE_BTE		21	/* Binary Trans. Exception */
-#define EXCCODE_PSI		22	/* Guest Privileged Error */
-#define EXCCODE_HYP		23	/* Hypercall */
+#define EXCCODE_GSPR		22	/* Guest Privileged Error */
+#define EXCCODE_HVC		23	/* Hypercall */
 #define EXCCODE_GCM		24	/* Guest CSR modified */
 	#define EXCSUBCODE_GCSC		0	/* Software caused */
 	#define EXCSUBCODE_GCHC		1	/* Hardware caused */
 #define EXCCODE_SE		25	/* Security */
 
+/* Interrupt numbers */
+#define INT_SWI0	0	/* Software Interrupts */
+#define INT_SWI1	1
+#define INT_HWI0	2	/* Hardware Interrupts */
+#define INT_HWI1	3
+#define INT_HWI2	4
+#define INT_HWI3	5
+#define INT_HWI4	6
+#define INT_HWI5	7
+#define INT_HWI6	8
+#define INT_HWI7	9
+#define INT_PCOV	10	/* Performance Counter Overflow */
+#define INT_TI		11	/* Timer */
+#define INT_IPI		12
+#define INT_NMI		13
+
+/* ExcCodes corresponding to interrupts */
+#define EXCCODE_INT_NUM		(INT_NMI + 1)
 #define EXCCODE_INT_START	64
-#define EXCCODE_SIP0        64
-#define EXCCODE_SIP1        65
-#define EXCCODE_IP0         66
-#define EXCCODE_IP1         67
-#define EXCCODE_IP2         68
-#define EXCCODE_IP3         69
-#define EXCCODE_IP4         70
-#define EXCCODE_IP5         71
-#define EXCCODE_IP6         72
-#define EXCCODE_IP7         73
-#define EXCCODE_PMC         74 /* Performance Counter */
-#define EXCCODE_TIMER       75
-#define EXCCODE_IPI         76
-#define EXCCODE_NMI         77
-#define EXCCODE_INT_END     78
-#define EXCCODE_INT_NUM	    (EXCCODE_INT_END - EXCCODE_INT_START)
+#define EXCCODE_INT_END		(EXCCODE_INT_START + EXCCODE_INT_NUM - 1)
 
 /* FPU register names */
 #define LOONGARCH_FCSR0	$r0

arch/loongarch/include/asm/ptrace.h

@@ -154,6 +154,11 @@ static inline long regs_return_value(struct pt_regs *regs)
 	return regs->regs[4];
 }
 
+static inline void regs_set_return_value(struct pt_regs *regs, unsigned long val)
+{
+	regs->regs[4] = val;
+}
+
 #define instruction_pointer(regs) ((regs)->csr_era)
 #define profile_pc(regs) instruction_pointer(regs)
 

arch/loongarch/kernel/Makefile

@@ -13,7 +13,7 @@ obj-y		+= head.o cpu-probe.o cacheinfo.o env.o setup.o entry.o genex.o \
 obj-$(CONFIG_ACPI)		+= acpi.o
 obj-$(CONFIG_EFI) 		+= efi.o
 
-obj-$(CONFIG_CPU_HAS_FPU)	+= fpu.o
+obj-$(CONFIG_CPU_HAS_FPU)	+= fpu.o kfpu.o
 
 obj-$(CONFIG_ARCH_STRICT_ALIGN)	+= unaligned.o
 

arch/loongarch/kernel/ftrace_dyn.c

@@ -30,19 +30,12 @@ static int ftrace_modify_code(unsigned long pc, u32 old, u32 new, bool validate)
 	return 0;
 }
 
-#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
-
 #ifdef CONFIG_MODULES
-static inline int __get_mod(struct module **mod, unsigned long addr)
+static bool reachable_by_bl(unsigned long addr, unsigned long pc)
 {
-	preempt_disable();
-	*mod = __module_text_address(addr);
-	preempt_enable();
+	long offset = (long)addr - (long)pc;
 
-	if (WARN_ON(!(*mod)))
-		return -EINVAL;
-
-	return 0;
+	return offset >= -SZ_128M && offset < SZ_128M;
 }
 
 static struct plt_entry *get_ftrace_plt(struct module *mod, unsigned long addr)
@@ -58,51 +51,88 @@ static struct plt_entry *get_ftrace_plt(struct module *mod, unsigned long addr)
 	return NULL;
 }
 
-static unsigned long get_plt_addr(struct module *mod, unsigned long addr)
+/*
+ * Find the address the callsite must branch to in order to reach '*addr'.
+ *
+ * Due to the limited range of 'bl' instruction, modules may be placed too far
+ * away to branch directly and we must use a PLT.
+ *
+ * Returns true when '*addr' contains a reachable target address, or has been
+ * modified to contain a PLT address. Returns false otherwise.
+ */
+static bool ftrace_find_callable_addr(struct dyn_ftrace *rec, struct module *mod, unsigned long *addr)
 {
+	unsigned long pc = rec->ip + LOONGARCH_INSN_SIZE;
 	struct plt_entry *plt;
 
-	plt = get_ftrace_plt(mod, addr);
+	/*
+	 * If a custom trampoline is unreachable, rely on the ftrace_regs_caller
+	 * trampoline which knows how to indirectly reach that trampoline through
+	 * ops->direct_call.
+	 */
+	if (*addr != FTRACE_ADDR && *addr != FTRACE_REGS_ADDR && !reachable_by_bl(*addr, pc))
+		*addr = FTRACE_REGS_ADDR;
+
+	/*
+	 * When the target is within range of the 'bl' instruction, use 'addr'
+	 * as-is and branch to that directly.
+	 */
+	if (reachable_by_bl(*addr, pc))
+		return true;
+
+	/*
+	 * 'mod' is only set at module load time, but if we end up
+	 * dealing with an out-of-range condition, we can assume it
+	 * is due to a module being loaded far away from the kernel.
+	 *
+	 * NOTE: __module_text_address() must be called with preemption
+	 * disabled, but we can rely on ftrace_lock to ensure that 'mod'
+	 * retains its validity throughout the remainder of this code.
+	 */
+	if (!mod) {
+		preempt_disable();
+		mod = __module_text_address(pc);
+		preempt_enable();
+	}
+
+	if (WARN_ON(!mod))
+		return false;
+
+	plt = get_ftrace_plt(mod, *addr);
 	if (!plt) {
-		pr_err("ftrace: no module PLT for %ps\n", (void *)addr);
-		return -EINVAL;
+		pr_err("ftrace: no module PLT for %ps\n", (void *)*addr);
+		return false;
 	}
 
-	return (unsigned long)plt;
+	*addr = (unsigned long)plt;
+	return true;
+}
+#else /* !CONFIG_MODULES */
+static bool ftrace_find_callable_addr(struct dyn_ftrace *rec, struct module *mod, unsigned long *addr)
+{
+	return true;
 }
 #endif
 
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
 int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, unsigned long addr)
 {
 	u32 old, new;
 	unsigned long pc;
-	long offset __maybe_unused;
 
 	pc = rec->ip + LOONGARCH_INSN_SIZE;
 
-#ifdef CONFIG_MODULES
-	offset = (long)pc - (long)addr;
-
-	if (offset < -SZ_128M || offset >= SZ_128M) {
-		int ret;
-		struct module *mod;
-
-		ret = __get_mod(&mod, pc);
-		if (ret)
-			return ret;
-
-		addr = get_plt_addr(mod, addr);
+	if (!ftrace_find_callable_addr(rec, NULL, &addr))
+		return -EINVAL;
 
-		old_addr = get_plt_addr(mod, old_addr);
-	}
-#endif
+	if (!ftrace_find_callable_addr(rec, NULL, &old_addr))
+		return -EINVAL;
 
 	new = larch_insn_gen_bl(pc, addr);
 	old = larch_insn_gen_bl(pc, old_addr);
 
 	return ftrace_modify_code(pc, old, new, true);
 }
-
 #endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
 
 int ftrace_update_ftrace_func(ftrace_func_t func)
@@ -153,24 +183,11 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 {
 	u32 old, new;
 	unsigned long pc;
-	long offset __maybe_unused;
 
 	pc = rec->ip + LOONGARCH_INSN_SIZE;
 
-#ifdef CONFIG_MODULES
-	offset = (long)pc - (long)addr;
-
-	if (offset < -SZ_128M || offset >= SZ_128M) {
-		int ret;
-		struct module *mod;
-
-		ret = __get_mod(&mod, pc);
-		if (ret)
-			return ret;
-
-		addr = get_plt_addr(mod, addr);
-	}
-#endif
+	if (!ftrace_find_callable_addr(rec, NULL, &addr))
+		return -EINVAL;
 
 	old = larch_insn_gen_nop();
 	new = larch_insn_gen_bl(pc, addr);
@@ -182,24 +199,11 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, unsigned long ad
 {
 	u32 old, new;
 	unsigned long pc;
-	long offset __maybe_unused;
 
 	pc = rec->ip + LOONGARCH_INSN_SIZE;
 
-#ifdef CONFIG_MODULES
-	offset = (long)pc - (long)addr;
-
-	if (offset < -SZ_128M || offset >= SZ_128M) {
-		int ret;
-		struct module *mod;
-
-		ret = __get_mod(&mod, pc);
-		if (ret)
-			return ret;
-
-		addr = get_plt_addr(mod, addr);
-	}
-#endif
+	if (!ftrace_find_callable_addr(rec, NULL, &addr))
+		return -EINVAL;
 
 	new = larch_insn_gen_nop();
 	old = larch_insn_gen_bl(pc, addr);

arch/loongarch/kernel/genex.S

@@ -82,6 +82,7 @@ SYM_FUNC_END(except_vec_cex)
 
 	BUILD_HANDLER ade ade badv
 	BUILD_HANDLER ale ale badv
+	BUILD_HANDLER bce bce none
 	BUILD_HANDLER bp bp none
 	BUILD_HANDLER fpe fpe fcsr
 	BUILD_HANDLER fpu fpu none

arch/loongarch/kernel/irq.c

@@ -92,7 +92,7 @@ static int __init get_ipi_irq(void)
 	struct irq_domain *d = irq_find_matching_fwnode(cpuintc_handle, DOMAIN_BUS_ANY);
 
 	if (d)
-		return irq_create_mapping(d, EXCCODE_IPI - EXCCODE_INT_START);
+		return irq_create_mapping(d, INT_IPI);
 
 	return -EINVAL;
 }

arch/loongarch/kernel/kfpu.c

+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2023 Loongson Technology Corporation Limited
+ */
+
+#include <linux/cpu.h>
+#include <linux/init.h>
+#include <asm/fpu.h>
+#include <asm/smp.h>
+
+static DEFINE_PER_CPU(bool, in_kernel_fpu);
+
+void kernel_fpu_begin(void)
+{
+	preempt_disable();
+
+	WARN_ON(this_cpu_read(in_kernel_fpu));
+
+	this_cpu_write(in_kernel_fpu, true);
+
+	if (!is_fpu_owner())
+		enable_fpu();
+	else
+		_save_fp(&current->thread.fpu);
+
+	write_fcsr(LOONGARCH_FCSR0, 0);
+}
+EXPORT_SYMBOL_GPL(kernel_fpu_begin);
+
+void kernel_fpu_end(void)
+{
+	WARN_ON(!this_cpu_read(in_kernel_fpu));
+
+	if (!is_fpu_owner())
+		disable_fpu();
+	else
+		_restore_fp(&current->thread.fpu);
+
+	this_cpu_write(in_kernel_fpu, false);
+
+	preempt_enable();
+}
+EXPORT_SYMBOL_GPL(kernel_fpu_end);

arch/loongarch/kernel/mcount_dyn.S

@@ -42,7 +42,6 @@
 	.if \allregs
 	PTR_S		tp, sp, PT_R2
 	PTR_S		t0, sp, PT_R12
-	PTR_S		t1, sp, PT_R13
 	PTR_S		t2, sp, PT_R14
 	PTR_S		t3, sp, PT_R15
 	PTR_S		t4, sp, PT_R16
@@ -64,6 +63,8 @@
 	PTR_S		zero, sp, PT_R0
 	.endif
 	PTR_S		ra, sp, PT_ERA /* Save trace function ra at PT_ERA */
+	move		t1, zero
+	PTR_S		t1, sp, PT_R13
 	PTR_ADDI	t8, sp, PT_SIZE
 	PTR_S		t8, sp, PT_R3
 	.endm
@@ -104,8 +105,12 @@ ftrace_common_return:
 	PTR_L		a7, sp, PT_R11
 	PTR_L		fp, sp, PT_R22
 	PTR_L		t0, sp, PT_ERA
+	PTR_L		t1, sp, PT_R13
 	PTR_ADDI	sp, sp, PT_SIZE
+	bnez		t1, .Ldirect
 	jr		t0
+.Ldirect:
+	jr		t1
 SYM_CODE_END(ftrace_common)
 
 SYM_CODE_START(ftrace_caller)
@@ -147,3 +152,9 @@ SYM_CODE_START(return_to_handler)
 	jr		ra
 SYM_CODE_END(return_to_handler)
 #endif
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
+SYM_CODE_START(ftrace_stub_direct_tramp)
+	jr		t0
+SYM_CODE_END(ftrace_stub_direct_tramp)
+#endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */

arch/loongarch/kernel/perf_event.c

@@ -461,7 +461,7 @@ static int get_pmc_irq(void)
 	struct irq_domain *d = irq_find_matching_fwnode(cpuintc_handle, DOMAIN_BUS_ANY);
 
 	if (d)
-		return irq_create_mapping(d, EXCCODE_PMC - EXCCODE_INT_START);
+		return irq_create_mapping(d, INT_PCOV);
 
 	return -EINVAL;
 }

arch/loongarch/kernel/time.c

@@ -133,7 +133,7 @@ static int get_timer_irq(void)
 	struct irq_domain *d = irq_find_matching_fwnode(cpuintc_handle, DOMAIN_BUS_ANY);
 
 	if (d)
-		return irq_create_mapping(d, EXCCODE_TIMER - EXCCODE_INT_START);
+		return irq_create_mapping(d, INT_TI);
 
 	return -EINVAL;
 }

arch/loongarch/lib/Makefile

@@ -4,4 +4,6 @@
 #
 
 lib-y	+= delay.o memset.o memcpy.o memmove.o \
-	   clear_user.o copy_user.o dump_tlb.o unaligned.o
+	   clear_user.o copy_user.o csum.o dump_tlb.o unaligned.o
+
+obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o

arch/loongarch/lib/clear_user.S

@@ -13,7 +13,14 @@
 
 .irp to, 0, 1, 2, 3, 4, 5, 6, 7
 .L_fixup_handle_\to\():
-	addi.d	a0, a1, (\to) * (-8)
+	sub.d	a0, a2, a0
+	addi.d	a0, a0, (\to) * (-8)
+	jr	ra
+.endr
+
+.irp to, 0, 2, 4
+.L_fixup_handle_s\to\():
+	addi.d	a0, a1, -\to
 	jr	ra
 .endr
 
@@ -44,7 +51,7 @@ SYM_FUNC_START(__clear_user_generic)
 2:	move	a0, a1
 	jr	ra
 
-	_asm_extable 1b, .L_fixup_handle_0
+	_asm_extable 1b, .L_fixup_handle_s0
 SYM_FUNC_END(__clear_user_generic)
 
 /*
@@ -54,12 +61,21 @@ SYM_FUNC_END(__clear_user_generic)
  * a1: size
  */
 SYM_FUNC_START(__clear_user_fast)
-	beqz	a1, 10f
+	sltui	t0, a1, 9
+	bnez	t0, .Lsmall
 
-	ori	a2, zero, 64
-	blt	a1, a2, 9f
+	add.d	a2, a0, a1
+0:	st.d	zero, a0, 0
+
+	/* align up address */
+	addi.d	a0, a0, 8
+	bstrins.d	a0, zero, 2, 0
+
+	addi.d	a3, a2, -64
+	bgeu	a0, a3, .Llt64
 
 	/* set 64 bytes at a time */
+.Lloop64:
 1:	st.d	zero, a0, 0
 2:	st.d	zero, a0, 8
 3:	st.d	zero, a0, 16
@@ -68,24 +84,95 @@ SYM_FUNC_START(__clear_user_fast)
 6:	st.d	zero, a0, 40
 7:	st.d	zero, a0, 48
 8:	st.d	zero, a0, 56
-
 	addi.d	a0, a0, 64
-	addi.d	a1, a1, -64
-	bge	a1, a2, 1b
-
-	beqz	a1, 10f
+	bltu	a0, a3, .Lloop64
 
 	/* set the remaining bytes */
-9:	st.b	zero, a0, 0
-	addi.d	a0, a0, 1
-	addi.d	a1, a1, -1
-	bgt	a1, zero, 9b
+.Llt64:
+	addi.d	a3, a2, -32
+	bgeu	a0, a3, .Llt32
+9:	st.d	zero, a0, 0
+10:	st.d	zero, a0, 8
+11:	st.d	zero, a0, 16
+12:	st.d	zero, a0, 24
+	addi.d	a0, a0, 32
+
+.Llt32:
+	addi.d	a3, a2, -16
+	bgeu	a0, a3, .Llt16
+13:	st.d	zero, a0, 0
+14:	st.d	zero, a0, 8
+	addi.d	a0, a0, 16
+
+.Llt16:
+	addi.d	a3, a2, -8
+	bgeu	a0, a3, .Llt8
+15:	st.d	zero, a0, 0
+
+.Llt8:
+16:	st.d	zero, a2, -8
 
 	/* return */
-10:	move	a0, a1
+	move	a0, zero
+	jr	ra
+
+	.align	4
+.Lsmall:
+	pcaddi	t0, 4
+	slli.d	a2, a1, 4
+	add.d	t0, t0, a2
+	jr	t0
+
+	.align	4
+	move	a0, zero
+	jr	ra
+
+	.align	4
+17:	st.b	zero, a0, 0
+	move	a0, zero
+	jr	ra
+
+	.align	4
+18:	st.h	zero, a0, 0
+	move	a0, zero
+	jr	ra
+
+	.align	4
+19:	st.h	zero, a0, 0
+20:	st.b	zero, a0, 2
+	move	a0, zero
+	jr	ra
+
+	.align	4
+21:	st.w	zero, a0, 0
+	move	a0, zero
+	jr	ra
+
+	.align	4
+22:	st.w	zero, a0, 0
+23:	st.b	zero, a0, 4
+	move	a0, zero
+	jr	ra
+
+	.align	4
+24:	st.w	zero, a0, 0
+25:	st.h	zero, a0, 4
+	move	a0, zero
+	jr	ra
+
+	.align	4
+26:	st.w	zero, a0, 0
+27:	st.w	zero, a0, 3
+	move	a0, zero
+	jr	ra
+
+	.align	4
+28:	st.d	zero, a0, 0
+	move	a0, zero
 	jr	ra
 
 	/* fixup and ex_table */
+	_asm_extable 0b, .L_fixup_handle_0
 	_asm_extable 1b, .L_fixup_handle_0
 	_asm_extable 2b, .L_fixup_handle_1
 	_asm_extable 3b, .L_fixup_handle_2
@@ -95,4 +182,23 @@ SYM_FUNC_START(__clear_user_fast)
 	_asm_extable 7b, .L_fixup_handle_6
 	_asm_extable 8b, .L_fixup_handle_7
 	_asm_extable 9b, .L_fixup_handle_0
+	_asm_extable 10b, .L_fixup_handle_1
+	_asm_extable 11b, .L_fixup_handle_2
+	_asm_extable 12b, .L_fixup_handle_3
+	_asm_extable 13b, .L_fixup_handle_0
+	_asm_extable 14b, .L_fixup_handle_1
+	_asm_extable 15b, .L_fixup_handle_0
+	_asm_extable 16b, .L_fixup_handle_1
+	_asm_extable 17b, .L_fixup_handle_s0
+	_asm_extable 18b, .L_fixup_handle_s0
+	_asm_extable 19b, .L_fixup_handle_s0
+	_asm_extable 20b, .L_fixup_handle_s2
+	_asm_extable 21b, .L_fixup_handle_s0
+	_asm_extable 22b, .L_fixup_handle_s0
+	_asm_extable 23b, .L_fixup_handle_s4
+	_asm_extable 24b, .L_fixup_handle_s0
+	_asm_extable 25b, .L_fixup_handle_s4
+	_asm_extable 26b, .L_fixup_handle_s0
+	_asm_extable 27b, .L_fixup_handle_s4
+	_asm_extable 28b, .L_fixup_handle_s0
 SYM_FUNC_END(__clear_user_fast)

arch/loongarch/lib/copy_user.S

@@ -13,7 +13,14 @@
 
 .irp to, 0, 1, 2, 3, 4, 5, 6, 7
 .L_fixup_handle_\to\():
-	addi.d	a0, a2, (\to) * (-8)
+	sub.d	a0, a2, a0
+	addi.d	a0, a0, (\to) * (-8)
+	jr	ra
+.endr
+
+.irp to, 0, 2, 4
+.L_fixup_handle_s\to\():
+	addi.d	a0, a2, -\to
 	jr	ra
 .endr
 
@@ -47,8 +54,8 @@ SYM_FUNC_START(__copy_user_generic)
 3:	move	a0, a2
 	jr	ra
 
-	_asm_extable 1b, .L_fixup_handle_0
-	_asm_extable 2b, .L_fixup_handle_0
+	_asm_extable 1b, .L_fixup_handle_s0
+	_asm_extable 2b, .L_fixup_handle_s0
 SYM_FUNC_END(__copy_user_generic)
 
 /*
@@ -59,65 +66,209 @@ SYM_FUNC_END(__copy_user_generic)
  * a2: n
  */
 SYM_FUNC_START(__copy_user_fast)
-	beqz	a2, 19f
+	sltui	t0, a2, 9
+	bnez	t0, .Lsmall
 
-	ori	a3, zero, 64
-	blt	a2, a3, 17f
+	add.d	a3, a1, a2
+	add.d	a2, a0, a2
+0:	ld.d	t0, a1, 0
+1:	st.d	t0, a0, 0
 
-	/* copy 64 bytes at a time */
-1:	ld.d	t0, a1, 0
-2:	ld.d	t1, a1, 8
-3:	ld.d	t2, a1, 16
-4:	ld.d	t3, a1, 24
-5:	ld.d	t4, a1, 32
-6:	ld.d	t5, a1, 40
-7:	ld.d	t6, a1, 48
-8:	ld.d	t7, a1, 56
-9:	st.d	t0, a0, 0
-10:	st.d	t1, a0, 8
-11:	st.d	t2, a0, 16
-12:	st.d	t3, a0, 24
-13:	st.d	t4, a0, 32
-14:	st.d	t5, a0, 40
-15:	st.d	t6, a0, 48
-16:	st.d	t7, a0, 56
+	/* align up destination address */
+	andi	t1, a0, 7
+	sub.d	t0, zero, t1
+	addi.d	t0, t0, 8
+	add.d	a1, a1, t0
+	add.d	a0, a0, t0
 
-	addi.d	a0, a0, 64
-	addi.d	a1, a1, 64
-	addi.d	a2, a2, -64
-	bge	a2, a3, 1b
+	addi.d	a4, a3, -64
+	bgeu	a1, a4, .Llt64
 
-	beqz	a2, 19f
+	/* copy 64 bytes at a time */
+.Lloop64:
+2:	ld.d	t0, a1, 0
+3:	ld.d	t1, a1, 8
+4:	ld.d	t2, a1, 16
+5:	ld.d	t3, a1, 24
+6:	ld.d	t4, a1, 32
+7:	ld.d	t5, a1, 40
+8:	ld.d	t6, a1, 48
+9:	ld.d	t7, a1, 56
+	addi.d	a1, a1, 64
+10:	st.d	t0, a0, 0
+11:	st.d	t1, a0, 8
+12:	st.d	t2, a0, 16
+13:	st.d	t3, a0, 24
+14:	st.d	t4, a0, 32
+15:	st.d	t5, a0, 40
+16:	st.d	t6, a0, 48
+17:	st.d	t7, a0, 56
+	addi.d	a0, a0, 64
+	bltu	a1, a4, .Lloop64
 
 	/* copy the remaining bytes */
-17:	ld.b	t0, a1, 0
-18:	st.b	t0, a0, 0
-	addi.d	a0, a0, 1
-	addi.d	a1, a1, 1
-	addi.d	a2, a2, -1
-	bgt	a2, zero, 17b
+.Llt64:
+	addi.d	a4, a3, -32
+	bgeu	a1, a4, .Llt32
+18:	ld.d	t0, a1, 0
+19:	ld.d	t1, a1, 8
+20:	ld.d	t2, a1, 16
+21:	ld.d	t3, a1, 24
+	addi.d	a1, a1, 32
+22:	st.d	t0, a0, 0
+23:	st.d	t1, a0, 8
+24:	st.d	t2, a0, 16
+25:	st.d	t3, a0, 24
+	addi.d	a0, a0, 32
+
+.Llt32:
+	addi.d	a4, a3, -16
+	bgeu	a1, a4, .Llt16
+26:	ld.d	t0, a1, 0
+27:	ld.d	t1, a1, 8
+	addi.d	a1, a1, 16
+28:	st.d	t0, a0, 0
+29:	st.d	t1, a0, 8
+	addi.d	a0, a0, 16
+
+.Llt16:
+	addi.d	a4, a3, -8
+	bgeu	a1, a4, .Llt8
+30:	ld.d	t0, a1, 0
+31:	st.d	t0, a0, 0
+
+.Llt8:
+32:	ld.d	t0, a3, -8
+33:	st.d	t0, a2, -8
 
 	/* return */
-19:	move	a0, a2
+	move	a0, zero
+	jr	ra
+
+	.align	5
+.Lsmall:
+	pcaddi	t0, 8
+	slli.d	a3, a2, 5
+	add.d	t0, t0, a3
+	jr	t0
+
+	.align	5
+	move	a0, zero
+	jr	ra
+
+	.align	5
+34:	ld.b	t0, a1, 0
+35:	st.b	t0, a0, 0
+	move	a0, zero
+	jr	ra
+
+	.align	5
+36:	ld.h	t0, a1, 0
+37:	st.h	t0, a0, 0
+	move	a0, zero
+	jr	ra
+
+	.align	5
+38:	ld.h	t0, a1, 0
+39:	ld.b	t1, a1, 2
+40:	st.h	t0, a0, 0
+41:	st.b	t1, a0, 2
+	move	a0, zero
+	jr	ra
+
+	.align	5
+42:	ld.w	t0, a1, 0
+43:	st.w	t0, a0, 0
+	move	a0, zero
+	jr	ra
+
+	.align	5
+44:	ld.w	t0, a1, 0
+45:	ld.b	t1, a1, 4
+46:	st.w	t0, a0, 0
+47:	st.b	t1, a0, 4
+	move	a0, zero
+	jr	ra
+
+	.align	5
+48:	ld.w	t0, a1, 0
+49:	ld.h	t1, a1, 4
+50:	st.w	t0, a0, 0
+51:	st.h	t1, a0, 4
+	move	a0, zero
+	jr	ra
+
+	.align	5
+52:	ld.w	t0, a1, 0
+53:	ld.w	t1, a1, 3
+54:	st.w	t0, a0, 0
+55:	st.w	t1, a0, 3
+	move	a0, zero
+	jr	ra
+
+	.align	5
+56:	ld.d	t0, a1, 0
+57:	st.d	t0, a0, 0
+	move	a0, zero
 	jr	ra
 
 	/* fixup and ex_table */
+	_asm_extable 0b, .L_fixup_handle_0
 	_asm_extable 1b, .L_fixup_handle_0
-	_asm_extable 2b, .L_fixup_handle_1
-	_asm_extable 3b, .L_fixup_handle_2
-	_asm_extable 4b, .L_fixup_handle_3
-	_asm_extable 5b, .L_fixup_handle_4
-	_asm_extable 6b, .L_fixup_handle_5
-	_asm_extable 7b, .L_fixup_handle_6
-	_asm_extable 8b, .L_fixup_handle_7
+	_asm_extable 2b, .L_fixup_handle_0
+	_asm_extable 3b, .L_fixup_handle_0
+	_asm_extable 4b, .L_fixup_handle_0
+	_asm_extable 5b, .L_fixup_handle_0
+	_asm_extable 6b, .L_fixup_handle_0
+	_asm_extable 7b, .L_fixup_handle_0
+	_asm_extable 8b, .L_fixup_handle_0
 	_asm_extable 9b, .L_fixup_handle_0
-	_asm_extable 10b, .L_fixup_handle_1
-	_asm_extable 11b, .L_fixup_handle_2
-	_asm_extable 12b, .L_fixup_handle_3
-	_asm_extable 13b, .L_fixup_handle_4
-	_asm_extable 14b, .L_fixup_handle_5
-	_asm_extable 15b, .L_fixup_handle_6
-	_asm_extable 16b, .L_fixup_handle_7
-	_asm_extable 17b, .L_fixup_handle_0
+	_asm_extable 10b, .L_fixup_handle_0
+	_asm_extable 11b, .L_fixup_handle_1
+	_asm_extable 12b, .L_fixup_handle_2
+	_asm_extable 13b, .L_fixup_handle_3
+	_asm_extable 14b, .L_fixup_handle_4
+	_asm_extable 15b, .L_fixup_handle_5
+	_asm_extable 16b, .L_fixup_handle_6
+	_asm_extable 17b, .L_fixup_handle_7
 	_asm_extable 18b, .L_fixup_handle_0
+	_asm_extable 19b, .L_fixup_handle_0
+	_asm_extable 20b, .L_fixup_handle_0
+	_asm_extable 21b, .L_fixup_handle_0
+	_asm_extable 22b, .L_fixup_handle_0
+	_asm_extable 23b, .L_fixup_handle_1
+	_asm_extable 24b, .L_fixup_handle_2
+	_asm_extable 25b, .L_fixup_handle_3
+	_asm_extable 26b, .L_fixup_handle_0
+	_asm_extable 27b, .L_fixup_handle_0
+	_asm_extable 28b, .L_fixup_handle_0
+	_asm_extable 29b, .L_fixup_handle_1
+	_asm_extable 30b, .L_fixup_handle_0
+	_asm_extable 31b, .L_fixup_handle_0
+	_asm_extable 32b, .L_fixup_handle_0
+	_asm_extable 33b, .L_fixup_handle_1
+	_asm_extable 34b, .L_fixup_handle_s0
+	_asm_extable 35b, .L_fixup_handle_s0
+	_asm_extable 36b, .L_fixup_handle_s0
+	_asm_extable 37b, .L_fixup_handle_s0
+	_asm_extable 38b, .L_fixup_handle_s0
+	_asm_extable 39b, .L_fixup_handle_s0
+	_asm_extable 40b, .L_fixup_handle_s0
+	_asm_extable 41b, .L_fixup_handle_s2
+	_asm_extable 42b, .L_fixup_handle_s0
+	_asm_extable 43b, .L_fixup_handle_s0
+	_asm_extable 44b, .L_fixup_handle_s0
+	_asm_extable 45b, .L_fixup_handle_s0
+	_asm_extable 46b, .L_fixup_handle_s0
+	_asm_extable 47b, .L_fixup_handle_s4
+	_asm_extable 48b, .L_fixup_handle_s0
+	_asm_extable 49b, .L_fixup_handle_s0
+	_asm_extable 50b, .L_fixup_handle_s0
+	_asm_extable 51b, .L_fixup_handle_s4
+	_asm_extable 52b, .L_fixup_handle_s0
+	_asm_extable 53b, .L_fixup_handle_s0
+	_asm_extable 54b, .L_fixup_handle_s0
+	_asm_extable 55b, .L_fixup_handle_s4
+	_asm_extable 56b, .L_fixup_handle_s0
+	_asm_extable 57b, .L_fixup_handle_s0
 SYM_FUNC_END(__copy_user_fast)

arch/loongarch/lib/csum.c

+// SPDX-License-Identifier: GPL-2.0-only
+// Copyright (C) 2019-2020 Arm Ltd.
+
+#include <linux/compiler.h>
+#include <linux/kasan-checks.h>
+#include <linux/kernel.h>
+
+#include <net/checksum.h>
+
+static u64 accumulate(u64 sum, u64 data)
+{
+	sum += data;
+	if (sum < data)
+		sum += 1;
+	return sum;
+}
+
+/*
+ * We over-read the buffer and this makes KASAN unhappy. Instead, disable
+ * instrumentation and call kasan explicitly.
+ */
+unsigned int __no_sanitize_address do_csum(const unsigned char *buff, int len)
+{
+	unsigned int offset, shift, sum;
+	const u64 *ptr;
+	u64 data, sum64 = 0;
+
+	if (unlikely(len == 0))
+		return 0;
+
+	offset = (unsigned long)buff & 7;
+	/*
+	 * This is to all intents and purposes safe, since rounding down cannot
+	 * result in a different page or cache line being accessed, and @buff
+	 * should absolutely not be pointing to anything read-sensitive. We do,
+	 * however, have to be careful not to piss off KASAN, which means using
+	 * unchecked reads to accommodate the head and tail, for which we'll
+	 * compensate with an explicit check up-front.
+	 */
+	kasan_check_read(buff, len);
+	ptr = (u64 *)(buff - offset);
+	len = len + offset - 8;
+
+	/*
+	 * Head: zero out any excess leading bytes. Shifting back by the same
+	 * amount should be at least as fast as any other way of handling the
+	 * odd/even alignment, and means we can ignore it until the very end.
+	 */
+	shift = offset * 8;
+	data = *ptr++;
+	data = (data >> shift) << shift;
+
+	/*
+	 * Body: straightforward aligned loads from here on (the paired loads
+	 * underlying the quadword type still only need dword alignment). The
+	 * main loop strictly excludes the tail, so the second loop will always
+	 * run at least once.
+	 */
+	while (unlikely(len > 64)) {
+		__uint128_t tmp1, tmp2, tmp3, tmp4;
+
+		tmp1 = *(__uint128_t *)ptr;
+		tmp2 = *(__uint128_t *)(ptr + 2);
+		tmp3 = *(__uint128_t *)(ptr + 4);
+		tmp4 = *(__uint128_t *)(ptr + 6);
+
+		len -= 64;
+		ptr += 8;
+
+		/* This is the "don't dump the carry flag into a GPR" idiom */
+		tmp1 += (tmp1 >> 64) | (tmp1 << 64);
+		tmp2 += (tmp2 >> 64) | (tmp2 << 64);
+		tmp3 += (tmp3 >> 64) | (tmp3 << 64);
+		tmp4 += (tmp4 >> 64) | (tmp4 << 64);
+		tmp1 = ((tmp1 >> 64) << 64) | (tmp2 >> 64);
+		tmp1 += (tmp1 >> 64) | (tmp1 << 64);
+		tmp3 = ((tmp3 >> 64) << 64) | (tmp4 >> 64);
+		tmp3 += (tmp3 >> 64) | (tmp3 << 64);
+		tmp1 = ((tmp1 >> 64) << 64) | (tmp3 >> 64);
+		tmp1 += (tmp1 >> 64) | (tmp1 << 64);
+		tmp1 = ((tmp1 >> 64) << 64) | sum64;
+		tmp1 += (tmp1 >> 64) | (tmp1 << 64);
+		sum64 = tmp1 >> 64;
+	}
+	while (len > 8) {
+		__uint128_t tmp;
+
+		sum64 = accumulate(sum64, data);
+		tmp = *(__uint128_t *)ptr;
+
+		len -= 16;
+		ptr += 2;
+
+		data = tmp >> 64;
+		sum64 = accumulate(sum64, tmp);
+	}
+	if (len > 0) {
+		sum64 = accumulate(sum64, data);
+		data = *ptr;
+		len -= 8;
+	}
+	/*
+	 * Tail: zero any over-read bytes similarly to the head, again
+	 * preserving odd/even alignment.
+	 */
+	shift = len * -8;
+	data = (data << shift) >> shift;
+	sum64 = accumulate(sum64, data);
+
+	/* Finally, folding */
+	sum64 += (sum64 >> 32) | (sum64 << 32);
+	sum = sum64 >> 32;
+	sum += (sum >> 16) | (sum << 16);
+	if (offset & 1)
+		return (u16)swab32(sum);
+
+	return sum >> 16;
+}
+
+__sum16 csum_ipv6_magic(const struct in6_addr *saddr,
+			const struct in6_addr *daddr,
+			__u32 len, __u8 proto, __wsum csum)
+{
+	__uint128_t src, dst;
+	u64 sum = (__force u64)csum;
+
+	src = *(const __uint128_t *)saddr->s6_addr;
+	dst = *(const __uint128_t *)daddr->s6_addr;
+
+	sum += (__force u32)htonl(len);
+	sum += (u32)proto << 24;
+	src += (src >> 64) | (src << 64);
+	dst += (dst >> 64) | (dst << 64);
+
+	sum = accumulate(sum, src >> 64);
+	sum = accumulate(sum, dst >> 64);
+
+	sum += ((sum >> 32) | (sum << 32));
+	return csum_fold((__force __wsum)(sum >> 32));
+}
+EXPORT_SYMBOL(csum_ipv6_magic);

arch/loongarch/lib/error-inject.c

+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/error-injection.h>
+#include <linux/kprobes.h>
+
+void override_function_with_return(struct pt_regs *regs)
+{
+	instruction_pointer_set(regs, regs->regs[1]);
+}
+NOKPROBE_SYMBOL(override_function_with_return);

arch/loongarch/lib/memcpy.S

@@ -44,6 +44,66 @@ SYM_FUNC_START(__memcpy_generic)
 SYM_FUNC_END(__memcpy_generic)
 _ASM_NOKPROBE(__memcpy_generic)
 
+	.align	5
+SYM_FUNC_START_NOALIGN(__memcpy_small)
+	pcaddi	t0, 8
+	slli.d	a2, a2, 5
+	add.d	t0, t0, a2
+	jr	t0
+
+	.align	5
+0:	jr	ra
+
+	.align	5
+1:	ld.b	t0, a1, 0
+	st.b	t0, a0, 0
+	jr	ra
+
+	.align	5
+2:	ld.h	t0, a1, 0
+	st.h	t0, a0, 0
+	jr	ra
+
+	.align	5
+3:	ld.h	t0, a1, 0
+	ld.b	t1, a1, 2
+	st.h	t0, a0, 0
+	st.b	t1, a0, 2
+	jr	ra
+
+	.align	5
+4:	ld.w	t0, a1, 0
+	st.w	t0, a0, 0
+	jr	ra
+
+	.align	5
+5:	ld.w	t0, a1, 0
+	ld.b	t1, a1, 4
+	st.w	t0, a0, 0
+	st.b	t1, a0, 4
+	jr	ra
+
+	.align	5
+6:	ld.w	t0, a1, 0
+	ld.h	t1, a1, 4
+	st.w	t0, a0, 0
+	st.h	t1, a0, 4
+	jr	ra
+
+	.align	5
+7:	ld.w	t0, a1, 0
+	ld.w	t1, a1, 3
+	st.w	t0, a0, 0
+	st.w	t1, a0, 3
+	jr	ra
+
+	.align	5
+8:	ld.d	t0, a1, 0
+	st.d	t0, a0, 0
+	jr	ra
+SYM_FUNC_END(__memcpy_small)
+_ASM_NOKPROBE(__memcpy_small)
+
 /*
  * void *__memcpy_fast(void *dst, const void *src, size_t n)
  *
@@ -52,14 +112,27 @@ _ASM_NOKPROBE(__memcpy_generic)
  * a2: n
  */
 SYM_FUNC_START(__memcpy_fast)
-	move	a3, a0
-	beqz	a2, 3f
+	sltui	t0, a2, 9
+	bnez	t0, __memcpy_small
+
+	add.d	a3, a1, a2
+	add.d	a2, a0, a2
+	ld.d	a6, a1, 0
+	ld.d	a7, a3, -8
+
+	/* align up destination address */
+	andi	t1, a0, 7
+	sub.d	t0, zero, t1
+	addi.d	t0, t0, 8
+	add.d	a1, a1, t0
+	add.d	a5, a0, t0
 
-	ori	a4, zero, 64
-	blt	a2, a4, 2f
+	addi.d	a4, a3, -64
+	bgeu	a1, a4, .Llt64
 
 	/* copy 64 bytes at a time */
-1:	ld.d	t0, a1, 0
+.Lloop64:
+	ld.d	t0, a1, 0
 	ld.d	t1, a1, 8
 	ld.d	t2, a1, 16
 	ld.d	t3, a1, 24
@@ -67,32 +140,54 @@ SYM_FUNC_START(__memcpy_fast)
 	ld.d	t5, a1, 40
 	ld.d	t6, a1, 48
 	ld.d	t7, a1, 56
-	st.d	t0, a0, 0
-	st.d	t1, a0, 8
-	st.d	t2, a0, 16
-	st.d	t3, a0, 24
-	st.d	t4, a0, 32
-	st.d	t5, a0, 40
-	st.d	t6, a0, 48
-	st.d	t7, a0, 56
-
-	addi.d	a0, a0, 64
 	addi.d	a1, a1, 64
-	addi.d	a2, a2, -64
-	bge	a2, a4, 1b
-
-	beqz	a2, 3f
+	st.d	t0, a5, 0
+	st.d	t1, a5, 8
+	st.d	t2, a5, 16
+	st.d	t3, a5, 24
+	st.d	t4, a5, 32
+	st.d	t5, a5, 40
+	st.d	t6, a5, 48
+	st.d	t7, a5, 56
+	addi.d	a5, a5, 64
+	bltu	a1, a4, .Lloop64
 
 	/* copy the remaining bytes */
-2:	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, 2b
+.Llt64:
+	addi.d	a4, a3, -32
+	bgeu	a1, a4, .Llt32
+	ld.d	t0, a1, 0
+	ld.d	t1, a1, 8
+	ld.d	t2, a1, 16
+	ld.d	t3, a1, 24
+	addi.d	a1, a1, 32
+	st.d	t0, a5, 0
+	st.d	t1, a5, 8
+	st.d	t2, a5, 16
+	st.d	t3, a5, 24
+	addi.d	a5, a5, 32
+
+.Llt32:
+	addi.d	a4, a3, -16
+	bgeu	a1, a4, .Llt16
+	ld.d	t0, a1, 0
+	ld.d	t1, a1, 8
+	addi.d	a1, a1, 16
+	st.d	t0, a5, 0
+	st.d	t1, a5, 8
+	addi.d	a5, a5, 16
+
+.Llt16:
+	addi.d	a4, a3, -8
+	bgeu	a1, a4, .Llt8
+	ld.d	t0, a1, 0
+	st.d	t0, a5, 0
+
+.Llt8:
+	st.d	a6, a0, 0
+	st.d	a7, a2, -8
 
 	/* return */
-3:	move	a0, a3
 	jr	ra
 SYM_FUNC_END(__memcpy_fast)
 _ASM_NOKPROBE(__memcpy_fast)

arch/loongarch/lib/memmove.S

@@ -11,23 +11,9 @@
 #include <asm/regdef.h>
 
 SYM_FUNC_START(memmove)
-	blt	a0, a1, 1f	/* dst < src, memcpy */
-	blt	a1, a0, 3f	/* src < dst, rmemcpy */
+	blt	a0, a1, memcpy	/* dst < src, memcpy */
+	blt	a1, a0, rmemcpy	/* src < dst, rmemcpy */
 	jr	ra		/* dst == src, return */
-
-	/* if (src - dst) < 64, copy 1 byte at a time */
-1:	ori	a3, zero, 64
-	sub.d	t0, a1, a0
-	blt	t0, a3, 2f
-	b	memcpy
-2:	b	__memcpy_generic
-
-	/* if (dst - src) < 64, copy 1 byte at a time */
-3:	ori	a3, zero, 64
-	sub.d	t0, a0, a1
-	blt	t0, a3, 4f
-	b	rmemcpy
-4:	b	__rmemcpy_generic
 SYM_FUNC_END(memmove)
 _ASM_NOKPROBE(memmove)
 
@@ -76,50 +62,80 @@ _ASM_NOKPROBE(__rmemcpy_generic)
  * a2: n
  */
 SYM_FUNC_START(__rmemcpy_fast)
-	move	a3, a0
-	beqz	a2, 3f
+	sltui	t0, a2, 9
+	bnez	t0, __memcpy_small
 
-	add.d	a0, a0, a2
-	add.d	a1, a1, a2
+	add.d	a3, a1, a2
+	add.d	a2, a0, a2
+	ld.d	a6, a1, 0
+	ld.d	a7, a3, -8
+
+	/* align up destination address */
+	andi	t1, a2, 7
+	sub.d	a3, a3, t1
+	sub.d	a5, a2, t1
 
-	ori	a4, zero, 64
-	blt	a2, a4, 2f
+	addi.d	a4, a1, 64
+	bgeu	a4, a3, .Llt64
 
 	/* copy 64 bytes at a time */
-1:	ld.d	t0, a1, -8
-	ld.d	t1, a1, -16
-	ld.d	t2, a1, -24
-	ld.d	t3, a1, -32
-	ld.d	t4, a1, -40
-	ld.d	t5, a1, -48
-	ld.d	t6, a1, -56
-	ld.d	t7, a1, -64
-	st.d	t0, a0, -8
-	st.d	t1, a0, -16
-	st.d	t2, a0, -24
-	st.d	t3, a0, -32
-	st.d	t4, a0, -40
-	st.d	t5, a0, -48
-	st.d	t6, a0, -56
-	st.d	t7, a0, -64
-
-	addi.d	a0, a0, -64
-	addi.d	a1, a1, -64
-	addi.d	a2, a2, -64
-	bge	a2, a4, 1b
-
-	beqz	a2, 3f
+.Lloop64:
+	ld.d	t0, a3, -8
+	ld.d	t1, a3, -16
+	ld.d	t2, a3, -24
+	ld.d	t3, a3, -32
+	ld.d	t4, a3, -40
+	ld.d	t5, a3, -48
+	ld.d	t6, a3, -56
+	ld.d	t7, a3, -64
+	addi.d	a3, a3, -64
+	st.d	t0, a5, -8
+	st.d	t1, a5, -16
+	st.d	t2, a5, -24
+	st.d	t3, a5, -32
+	st.d	t4, a5, -40
+	st.d	t5, a5, -48
+	st.d	t6, a5, -56
+	st.d	t7, a5, -64
+	addi.d	a5, a5, -64
+	bltu	a4, a3, .Lloop64
 
 	/* copy the remaining bytes */
-2:	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, 2b
+.Llt64:
+	addi.d	a4, a1, 32
+	bgeu	a4, a3, .Llt32
+	ld.d	t0, a3, -8
+	ld.d	t1, a3, -16
+	ld.d	t2, a3, -24
+	ld.d	t3, a3, -32
+	addi.d	a3, a3, -32
+	st.d	t0, a5, -8
+	st.d	t1, a5, -16
+	st.d	t2, a5, -24
+	st.d	t3, a5, -32
+	addi.d	a5, a5, -32
+
+.Llt32:
+	addi.d	a4, a1, 16
+	bgeu	a4, a3, .Llt16
+	ld.d	t0, a3, -8
+	ld.d	t1, a3, -16
+	addi.d	a3, a3, -16
+	st.d	t0, a5, -8
+	st.d	t1, a5, -16
+	addi.d	a5, a5, -16
+
+.Llt16:
+	addi.d	a4, a1, 8
+	bgeu	a4, a3, .Llt8
+	ld.d	t0, a3, -8
+	st.d	t0, a5, -8
+
+.Llt8:
+	st.d	a6, a0, 0
+	st.d	a7, a2, -8
 
 	/* return */
-3:	move	a0, a3
 	jr	ra
 SYM_FUNC_END(__rmemcpy_fast)
 _ASM_NOKPROBE(__rmemcpy_fast)

arch/loongarch/lib/memset.S

@@ -56,39 +56,107 @@ _ASM_NOKPROBE(__memset_generic)
  * a2: n
  */
 SYM_FUNC_START(__memset_fast)
-	move	a3, a0
-	beqz	a2, 3f
-
-	ori	a4, zero, 64
-	blt	a2, a4, 2f
-
 	/* fill a1 to 64 bits */
 	fill_to_64 a1
 
-	/* set 64 bytes at a time */
-1:	st.d	a1, a0, 0
-	st.d	a1, a0, 8
-	st.d	a1, a0, 16
-	st.d	a1, a0, 24
-	st.d	a1, a0, 32
-	st.d	a1, a0, 40
-	st.d	a1, a0, 48
-	st.d	a1, a0, 56
+	sltui	t0, a2, 9
+	bnez	t0, .Lsmall
 
-	addi.d	a0, a0, 64
-	addi.d	a2, a2, -64
-	bge	a2, a4, 1b
+	add.d	a2, a0, a2
+	st.d	a1, a0, 0
 
-	beqz	a2, 3f
+	/* align up address */
+	addi.d	a3, a0, 8
+	bstrins.d	a3, zero, 2, 0
+
+	addi.d	a4, a2, -64
+	bgeu	a3, a4, .Llt64
+
+	/* set 64 bytes at a time */
+.Lloop64:
+	st.d	a1, a3, 0
+	st.d	a1, a3, 8
+	st.d	a1, a3, 16
+	st.d	a1, a3, 24
+	st.d	a1, a3, 32
+	st.d	a1, a3, 40
+	st.d	a1, a3, 48
+	st.d	a1, a3, 56
+	addi.d	a3, a3, 64
+	bltu	a3, a4, .Lloop64
 
 	/* set the remaining bytes */
-2:	st.b	a1, a0, 0
-	addi.d	a0, a0, 1
-	addi.d	a2, a2, -1
-	bgt	a2, zero, 2b
+.Llt64:
+	addi.d	a4, a2, -32
+	bgeu	a3, a4, .Llt32
+	st.d	a1, a3, 0
+	st.d	a1, a3, 8
+	st.d	a1, a3, 16
+	st.d	a1, a3, 24
+	addi.d	a3, a3, 32
+
+.Llt32:
+	addi.d	a4, a2, -16
+	bgeu	a3, a4, .Llt16
+	st.d	a1, a3, 0
+	st.d	a1, a3, 8
+	addi.d	a3, a3, 16
+
+.Llt16:
+	addi.d	a4, a2, -8
+	bgeu	a3, a4, .Llt8
+	st.d	a1, a3, 0
+
+.Llt8:
+	st.d	a1, a2, -8
 
 	/* return */
-3:	move	a0, a3
+	jr	ra
+
+	.align	4
+.Lsmall:
+	pcaddi	t0, 4
+	slli.d	a2, a2, 4
+	add.d	t0, t0, a2
+	jr	t0
+
+	.align	4
+0:	jr	ra
+
+	.align	4
+1:	st.b	a1, a0, 0
+	jr	ra
+
+	.align	4
+2:	st.h	a1, a0, 0
+	jr	ra
+
+	.align	4
+3:	st.h	a1, a0, 0
+	st.b	a1, a0, 2
+	jr	ra
+
+	.align	4
+4:	st.w	a1, a0, 0
+	jr	ra
+
+	.align	4
+5:	st.w	a1, a0, 0
+	st.b	a1, a0, 4
+	jr	ra
+
+	.align	4
+6:	st.w	a1, a0, 0
+	st.h	a1, a0, 4
+	jr	ra
+
+	.align	4
+7:	st.w	a1, a0, 0
+	st.w	a1, a0, 3
+	jr	ra
+
+	.align	4
+8:	st.d	a1, a0, 0
 	jr	ra
 SYM_FUNC_END(__memset_fast)
 _ASM_NOKPROBE(__memset_fast)

crypto/Kconfig

@@ -1395,6 +1395,9 @@ endif
 if ARM64
 source "arch/arm64/crypto/Kconfig"
 endif
+if LOONGARCH
+source "arch/loongarch/crypto/Kconfig"
+endif
 if MIPS
 source "arch/mips/crypto/Kconfig"
 endif

samples/ftrace/ftrace-direct-modify.c

@@ -96,6 +96,40 @@ asm (
 
 #endif /* CONFIG_S390 */
 
+#ifdef CONFIG_LOONGARCH
+
+asm (
+"	.pushsection    .text, \"ax\", @progbits\n"
+"	.type		my_tramp1, @function\n"
+"	.globl		my_tramp1\n"
+"   my_tramp1:\n"
+"	addi.d	$sp, $sp, -16\n"
+"	st.d	$t0, $sp, 0\n"
+"	st.d	$ra, $sp, 8\n"
+"	bl	my_direct_func1\n"
+"	ld.d	$t0, $sp, 0\n"
+"	ld.d	$ra, $sp, 8\n"
+"	addi.d	$sp, $sp, 16\n"
+"	jr	$t0\n"
+"	.size		my_tramp1, .-my_tramp1\n"
+
+"	.type		my_tramp2, @function\n"
+"	.globl		my_tramp2\n"
+"   my_tramp2:\n"
+"	addi.d	$sp, $sp, -16\n"
+"	st.d	$t0, $sp, 0\n"
+"	st.d	$ra, $sp, 8\n"
+"	bl	my_direct_func2\n"
+"	ld.d	$t0, $sp, 0\n"
+"	ld.d	$ra, $sp, 8\n"
+"	addi.d	$sp, $sp, 16\n"
+"	jr	$t0\n"
+"	.size		my_tramp2, .-my_tramp2\n"
+"	.popsection\n"
+);
+
+#endif /* CONFIG_LOONGARCH */
+
 static struct ftrace_ops direct;
 
 static unsigned long my_tramp = (unsigned long)my_tramp1;

samples/ftrace/ftrace-direct-multi-modify.c

@@ -103,6 +103,47 @@ asm (
 
 #endif /* CONFIG_S390 */
 
+#ifdef CONFIG_LOONGARCH
+#include <asm/asm.h>
+
+asm (
+"	.pushsection    .text, \"ax\", @progbits\n"
+"	.type		my_tramp1, @function\n"
+"	.globl		my_tramp1\n"
+"   my_tramp1:\n"
+"	addi.d	$sp, $sp, -32\n"
+"	st.d	$a0, $sp, 0\n"
+"	st.d	$t0, $sp, 8\n"
+"	st.d	$ra, $sp, 16\n"
+"	move	$a0, $t0\n"
+"	bl	my_direct_func1\n"
+"	ld.d	$a0, $sp, 0\n"
+"	ld.d	$t0, $sp, 8\n"
+"	ld.d	$ra, $sp, 16\n"
+"	addi.d	$sp, $sp, 32\n"
+"	jr	$t0\n"
+"	.size		my_tramp1, .-my_tramp1\n"
+
+"	.type		my_tramp2, @function\n"
+"	.globl		my_tramp2\n"
+"   my_tramp2:\n"
+"	addi.d	$sp, $sp, -32\n"
+"	st.d	$a0, $sp, 0\n"
+"	st.d	$t0, $sp, 8\n"
+"	st.d	$ra, $sp, 16\n"
+"	move	$a0, $t0\n"
+"	bl	my_direct_func2\n"
+"	ld.d	$a0, $sp, 0\n"
+"	ld.d	$t0, $sp, 8\n"
+"	ld.d	$ra, $sp, 16\n"
+"	addi.d	$sp, $sp, 32\n"
+"	jr	$t0\n"
+"	.size		my_tramp2, .-my_tramp2\n"
+"	.popsection\n"
+);
+
+#endif /* CONFIG_LOONGARCH */
+
 static unsigned long my_tramp = (unsigned long)my_tramp1;
 static unsigned long tramps[2] = {
 	(unsigned long)my_tramp1,

samples/ftrace/ftrace-direct-multi.c

@@ -66,6 +66,31 @@ asm (
 
 #endif /* CONFIG_S390 */
 
+#ifdef CONFIG_LOONGARCH
+
+#include <asm/asm.h>
+asm (
+"	.pushsection	.text, \"ax\", @progbits\n"
+"	.type		my_tramp, @function\n"
+"	.globl		my_tramp\n"
+"   my_tramp:\n"
+"	addi.d	$sp, $sp, -32\n"
+"	st.d	$a0, $sp, 0\n"
+"	st.d	$t0, $sp, 8\n"
+"	st.d	$ra, $sp, 16\n"
+"	move	$a0, $t0\n"
+"	bl	my_direct_func\n"
+"	ld.d	$a0, $sp, 0\n"
+"	ld.d	$t0, $sp, 8\n"
+"	ld.d	$ra, $sp, 16\n"
+"	addi.d	$sp, $sp, 32\n"
+"	jr	$t0\n"
+"	.size		my_tramp, .-my_tramp\n"
+"	.popsection\n"
+);
+
+#endif /* CONFIG_LOONGARCH */
+
 static struct ftrace_ops direct;
 
 static int __init ftrace_direct_multi_init(void)

samples/ftrace/ftrace-direct-too.c

@@ -70,6 +70,33 @@ asm (
 
 #endif /* CONFIG_S390 */
 
+#ifdef CONFIG_LOONGARCH
+
+asm (
+"	.pushsection	.text, \"ax\", @progbits\n"
+"	.type		my_tramp, @function\n"
+"	.globl		my_tramp\n"
+"   my_tramp:\n"
+"	addi.d	$sp, $sp, -48\n"
+"	st.d	$a0, $sp, 0\n"
+"	st.d	$a1, $sp, 8\n"
+"	st.d	$a2, $sp, 16\n"
+"	st.d	$t0, $sp, 24\n"
+"	st.d	$ra, $sp, 32\n"
+"	bl	my_direct_func\n"
+"	ld.d	$a0, $sp, 0\n"
+"	ld.d	$a1, $sp, 8\n"
+"	ld.d	$a2, $sp, 16\n"
+"	ld.d	$t0, $sp, 24\n"
+"	ld.d	$ra, $sp, 32\n"
+"	addi.d	$sp, $sp, 48\n"
+"	jr	$t0\n"
+"	.size		my_tramp, .-my_tramp\n"
+"	.popsection\n"
+);
+
+#endif /* CONFIG_LOONGARCH */
+
 static struct ftrace_ops direct;
 
 static int __init ftrace_direct_init(void)

samples/ftrace/ftrace-direct.c

@@ -63,6 +63,29 @@ asm (
 
 #endif /* CONFIG_S390 */
 
+#ifdef CONFIG_LOONGARCH
+
+asm (
+"	.pushsection	.text, \"ax\", @progbits\n"
+"	.type		my_tramp, @function\n"
+"	.globl		my_tramp\n"
+"   my_tramp:\n"
+"	addi.d	$sp, $sp, -32\n"
+"	st.d	$a0, $sp, 0\n"
+"	st.d	$t0, $sp, 8\n"
+"	st.d	$ra, $sp, 16\n"
+"	bl	my_direct_func\n"
+"	ld.d	$a0, $sp, 0\n"
+"	ld.d	$t0, $sp, 8\n"
+"	ld.d	$ra, $sp, 16\n"
+"	addi.d	$sp, $sp, 32\n"
+"	jr	$t0\n"
+"	.size		my_tramp, .-my_tramp\n"
+"	.popsection\n"
+);
+
+#endif /* CONFIG_LOONGARCH */
+
 static struct ftrace_ops direct;
 
 static int __init ftrace_direct_init(void)

tools/arch/loongarch/include/uapi/asm/perf_regs.h

+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _ASM_LOONGARCH_PERF_REGS_H
+#define _ASM_LOONGARCH_PERF_REGS_H
+
+enum perf_event_loongarch_regs {
+	PERF_REG_LOONGARCH_PC,
+	PERF_REG_LOONGARCH_R1,
+	PERF_REG_LOONGARCH_R2,
+	PERF_REG_LOONGARCH_R3,
+	PERF_REG_LOONGARCH_R4,
+	PERF_REG_LOONGARCH_R5,
+	PERF_REG_LOONGARCH_R6,
+	PERF_REG_LOONGARCH_R7,
+	PERF_REG_LOONGARCH_R8,
+	PERF_REG_LOONGARCH_R9,
+	PERF_REG_LOONGARCH_R10,
+	PERF_REG_LOONGARCH_R11,
+	PERF_REG_LOONGARCH_R12,
+	PERF_REG_LOONGARCH_R13,
+	PERF_REG_LOONGARCH_R14,
+	PERF_REG_LOONGARCH_R15,
+	PERF_REG_LOONGARCH_R16,
+	PERF_REG_LOONGARCH_R17,
+	PERF_REG_LOONGARCH_R18,
+	PERF_REG_LOONGARCH_R19,
+	PERF_REG_LOONGARCH_R20,
+	PERF_REG_LOONGARCH_R21,
+	PERF_REG_LOONGARCH_R22,
+	PERF_REG_LOONGARCH_R23,
+	PERF_REG_LOONGARCH_R24,
+	PERF_REG_LOONGARCH_R25,
+	PERF_REG_LOONGARCH_R26,
+	PERF_REG_LOONGARCH_R27,
+	PERF_REG_LOONGARCH_R28,
+	PERF_REG_LOONGARCH_R29,
+	PERF_REG_LOONGARCH_R30,
+	PERF_REG_LOONGARCH_R31,
+	PERF_REG_LOONGARCH_MAX,
+};
+#endif /* _ASM_LOONGARCH_PERF_REGS_H */

tools/arch/loongarch/include/uapi/asm/unistd.h

+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Copyright (C) 2020-2023 Loongson Technology Corporation Limited
+ */
+
+#define __ARCH_WANT_SYS_CLONE
+#define __ARCH_WANT_SYS_CLONE3
+
+#include <asm-generic/unistd.h>

tools/perf/Makefile.config

@@ -38,7 +38,7 @@ ifneq ($(NO_SYSCALL_TABLE),1)
       NO_SYSCALL_TABLE := 0
     endif
   else
-    ifeq ($(SRCARCH),$(filter $(SRCARCH),powerpc arm64 s390 mips))
+    ifeq ($(SRCARCH),$(filter $(SRCARCH),powerpc arm64 s390 mips loongarch))
       NO_SYSCALL_TABLE := 0
     endif
   endif
@@ -80,6 +80,12 @@ ifeq ($(SRCARCH),arm64)
   LIBUNWIND_LIBS = -lunwind -lunwind-aarch64
 endif
 
+ifeq ($(SRCARCH),loongarch)
+  NO_PERF_REGS := 0
+  CFLAGS += -I$(OUTPUT)arch/loongarch/include/generated
+  LIBUNWIND_LIBS = -lunwind -lunwind-loongarch64
+endif
+
 ifeq ($(SRCARCH),riscv)
   NO_PERF_REGS := 0
 endif
@@ -107,7 +113,7 @@ endif
 # Disable it on all other architectures in case libdw unwind
 # support is detected in system. Add supported architectures
 # to the check.
-ifneq ($(SRCARCH),$(filter $(SRCARCH),x86 arm arm64 powerpc s390 csky riscv))
+ifneq ($(SRCARCH),$(filter $(SRCARCH),x86 arm arm64 powerpc s390 csky riscv loongarch))
   NO_LIBDW_DWARF_UNWIND := 1
 endif
 
@@ -129,7 +135,7 @@ endef
 ifdef LIBUNWIND_DIR
   LIBUNWIND_CFLAGS  = -I$(LIBUNWIND_DIR)/include
   LIBUNWIND_LDFLAGS = -L$(LIBUNWIND_DIR)/lib
-  LIBUNWIND_ARCHS = x86 x86_64 arm aarch64 debug-frame-arm debug-frame-aarch64
+  LIBUNWIND_ARCHS = x86 x86_64 arm aarch64 debug-frame-arm debug-frame-aarch64 loongarch
   $(foreach libunwind_arch,$(LIBUNWIND_ARCHS),$(call libunwind_arch_set_flags,$(libunwind_arch)))
 endif
 

tools/perf/arch/loongarch/Build

+perf-y += util/

tools/perf/arch/loongarch/Makefile

+# SPDX-License-Identifier: GPL-2.0
+ifndef NO_DWARF
+PERF_HAVE_DWARF_REGS := 1
+endif
+PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1
+PERF_HAVE_JITDUMP := 1
+
+#
+# Syscall table generation for perf
+#
+
+out    := $(OUTPUT)arch/loongarch/include/generated/asm
+header := $(out)/syscalls.c
+incpath := $(srctree)/tools
+sysdef := $(srctree)/tools/arch/loongarch/include/uapi/asm/unistd.h
+sysprf := $(srctree)/tools/perf/arch/loongarch/entry/syscalls/
+systbl := $(sysprf)/mksyscalltbl
+
+# Create output directory if not already present
+_dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)')
+
+$(header): $(sysdef) $(systbl)
+	$(Q)$(SHELL) '$(systbl)' '$(CC)' '$(HOSTCC)' $(incpath) $(sysdef) > $@
+
+clean::
+	$(call QUIET_CLEAN, loongarch) $(RM) $(header)
+
+archheaders: $(header)

tools/perf/arch/loongarch/annotate/instructions.c

+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Perf annotate functions.
+ *
+ * Copyright (C) 2020-2023 Loongson Technology Corporation Limited
+ */
+
+static
+struct ins_ops *loongarch__associate_ins_ops(struct arch *arch, const char *name)
+{
+	struct ins_ops *ops = NULL;
+
+	if (!strncmp(name, "beqz", 4) ||
+	    !strncmp(name, "bnez", 4) ||
+	    !strncmp(name, "beq", 3) ||
+	    !strncmp(name, "bne", 3) ||
+	    !strncmp(name, "blt", 3) ||
+	    !strncmp(name, "bge", 3) ||
+	    !strncmp(name, "bltu", 4) ||
+	    !strncmp(name, "bgeu", 4) ||
+	    !strncmp(name, "bl", 2))
+		ops = &call_ops;
+	else if (!strncmp(name, "jirl", 4))
+		ops = &ret_ops;
+	else if (name[0] == 'b')
+		ops = &jump_ops;
+	else
+		return NULL;
+
+	arch__associate_ins_ops(arch, name, ops);
+
+	return ops;
+}
+
+static
+int loongarch__annotate_init(struct arch *arch, char *cpuid __maybe_unused)
+{
+	if (!arch->initialized) {
+		arch->associate_instruction_ops = loongarch__associate_ins_ops;
+		arch->initialized = true;
+		arch->objdump.comment_char = '#';
+	}
+
+	return 0;
+}

tools/perf/arch/loongarch/entry/syscalls/mksyscalltbl

+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+#
+# Generate system call table for perf. Derived from
+# powerpc script.
+#
+# Author(s):  Ming Wang <wangming01@loongson.cn>
+# Author(s):  Huacai Chen <chenhuacai@loongson.cn>
+# Copyright (C) 2020-2023 Loongson Technology Corporation Limited
+
+gcc=$1
+hostcc=$2
+incpath=$3
+input=$4
+
+if ! test -r $input; then
+	echo "Could not read input file" >&2
+	exit 1
+fi
+
+create_table_from_c()
+{
+	local sc nr last_sc
+
+	create_table_exe=`mktemp ${TMPDIR:-/tmp}/create-table-XXXXXX`
+
+	{
+
+	cat <<-_EoHEADER
+		#include <stdio.h>
+		#include "$input"
+		int main(int argc, char *argv[])
+		{
+	_EoHEADER
+
+	while read sc nr; do
+		printf "%s\n" "	printf(\"\\t[%d] = \\\"$sc\\\",\\n\", $nr);"
+		last_sc=$nr
+	done
+
+	printf "%s\n" "	printf(\"#define SYSCALLTBL_LOONGARCH_MAX_ID %d\\n\", $last_sc);"
+	printf "}\n"
+
+	} | $hostcc -I $incpath/include/uapi -o $create_table_exe -x c -
+
+	$create_table_exe
+
+	rm -f $create_table_exe
+}
+
+create_table()
+{
+	echo "static const char *syscalltbl_loongarch[] = {"
+	create_table_from_c
+	echo "};"
+}
+
+$gcc -E -dM -x c  -I $incpath/include/uapi $input	       \
+	|sed -ne 's/^#define __NR_//p' \
+	|sort -t' ' -k2 -n \
+	|create_table

tools/perf/arch/loongarch/include/dwarf-regs-table.h

+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * dwarf-regs-table.h : Mapping of DWARF debug register numbers into
+ * register names.
+ *
+ * Copyright (C) 2020-2023 Loongson Technology Corporation Limited
+ */
+
+#ifdef DEFINE_DWARF_REGSTR_TABLE
+static const char * const loongarch_regstr_tbl[] = {
+	"%r0", "%r1", "%r2", "%r3", "%r4", "%r5", "%r6", "%r7",
+	"%r8", "%r9", "%r10", "%r11", "%r12", "%r13", "%r14", "%r15",
+	"%r16", "%r17", "%r18", "%r19", "%r20", "%r21", "%r22", "%r23",
+	"%r24", "%r25", "%r26", "%r27", "%r28", "%r29", "%r30", "%r31",
+};
+#endif

tools/perf/arch/loongarch/include/perf_regs.h

+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef ARCH_PERF_REGS_H
+#define ARCH_PERF_REGS_H
+
+#include <stdlib.h>
+#include <linux/types.h>
+#include <asm/perf_regs.h>
+
+#define PERF_REGS_MAX PERF_REG_LOONGARCH_MAX
+#define PERF_REG_IP PERF_REG_LOONGARCH_PC
+#define PERF_REG_SP PERF_REG_LOONGARCH_R3
+
+#define PERF_REGS_MASK ((1ULL << PERF_REG_LOONGARCH_MAX) - 1)
+
+#endif /* ARCH_PERF_REGS_H */

tools/perf/arch/loongarch/util/Build

+perf-y += perf_regs.o
+
+perf-$(CONFIG_DWARF)     += dwarf-regs.o
+perf-$(CONFIG_LOCAL_LIBUNWIND) += unwind-libunwind.o
+perf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o

tools/perf/arch/loongarch/util/dwarf-regs.c

+// SPDX-License-Identifier: GPL-2.0
+/*
+ * dwarf-regs.c : Mapping of DWARF debug register numbers into register names.
+ *
+ * Copyright (C) 2020-2023 Loongson Technology Corporation Limited
+ */
+
+#include <stdio.h>
+#include <errno.h> /* for EINVAL */
+#include <string.h> /* for strcmp */
+#include <dwarf-regs.h>
+
+struct pt_regs_dwarfnum {
+	const char *name;
+	unsigned int dwarfnum;
+};
+
+static struct pt_regs_dwarfnum loongarch_gpr_table[] = {
+	{"%r0", 0}, {"%r1", 1}, {"%r2", 2}, {"%r3", 3},
+	{"%r4", 4}, {"%r5", 5}, {"%r6", 6}, {"%r7", 7},
+	{"%r8", 8}, {"%r9", 9}, {"%r10", 10}, {"%r11", 11},
+	{"%r12", 12}, {"%r13", 13}, {"%r14", 14}, {"%r15", 15},
+	{"%r16", 16}, {"%r17", 17}, {"%r18", 18}, {"%r19", 19},
+	{"%r20", 20}, {"%r21", 21}, {"%r22", 22}, {"%r23", 23},
+	{"%r24", 24}, {"%r25", 25}, {"%r26", 26}, {"%r27", 27},
+	{"%r28", 28}, {"%r29", 29}, {"%r30", 30}, {"%r31", 31},
+	{NULL, 0}
+};
+
+const char *get_arch_regstr(unsigned int n)
+{
+	n %= 32;
+	return loongarch_gpr_table[n].name;
+}
+
+int regs_query_register_offset(const char *name)
+{
+	const struct pt_regs_dwarfnum *roff;
+
+	for (roff = loongarch_gpr_table; roff->name != NULL; roff++)
+		if (!strcmp(roff->name, name))
+			return roff->dwarfnum;
+	return -EINVAL;
+}

tools/perf/arch/loongarch/util/perf_regs.c

+// SPDX-License-Identifier: GPL-2.0
+#include "../../../util/perf_regs.h"
+
+const struct sample_reg sample_reg_masks[] = {
+	SMPL_REG_END
+};

tools/perf/arch/loongarch/util/unwind-libdw.c

+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2020-2023 Loongson Technology Corporation Limited */
+
+#include <elfutils/libdwfl.h>
+#include "../../util/unwind-libdw.h"
+#include "../../util/perf_regs.h"
+#include "../../util/sample.h"
+
+bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg)
+{
+	struct unwind_info *ui = arg;
+	struct regs_dump *user_regs = &ui->sample->user_regs;
+	Dwarf_Word dwarf_regs[PERF_REG_LOONGARCH_MAX];
+
+#define REG(r) ({							\
+	Dwarf_Word val = 0;						\
+	perf_reg_value(&val, user_regs, PERF_REG_LOONGARCH_##r);	\
+	val;								\
+})
+
+	dwarf_regs[0]  = 0;
+	dwarf_regs[1]  = REG(R1);
+	dwarf_regs[2]  = REG(R2);
+	dwarf_regs[3]  = REG(R3);
+	dwarf_regs[4]  = REG(R4);
+	dwarf_regs[5]  = REG(R5);
+	dwarf_regs[6]  = REG(R6);
+	dwarf_regs[7]  = REG(R7);
+	dwarf_regs[8]  = REG(R8);
+	dwarf_regs[9]  = REG(R9);
+	dwarf_regs[10] = REG(R10);
+	dwarf_regs[11] = REG(R11);
+	dwarf_regs[12] = REG(R12);
+	dwarf_regs[13] = REG(R13);
+	dwarf_regs[14] = REG(R14);
+	dwarf_regs[15] = REG(R15);
+	dwarf_regs[16] = REG(R16);
+	dwarf_regs[17] = REG(R17);
+	dwarf_regs[18] = REG(R18);
+	dwarf_regs[19] = REG(R19);
+	dwarf_regs[20] = REG(R20);
+	dwarf_regs[21] = REG(R21);
+	dwarf_regs[22] = REG(R22);
+	dwarf_regs[23] = REG(R23);
+	dwarf_regs[24] = REG(R24);
+	dwarf_regs[25] = REG(R25);
+	dwarf_regs[26] = REG(R26);
+	dwarf_regs[27] = REG(R27);
+	dwarf_regs[28] = REG(R28);
+	dwarf_regs[29] = REG(R29);
+	dwarf_regs[30] = REG(R30);
+	dwarf_regs[31] = REG(R31);
+	dwfl_thread_state_register_pc(thread, REG(PC));
+
+	return dwfl_thread_state_registers(thread, 0, PERF_REG_LOONGARCH_MAX, dwarf_regs);
+}

tools/perf/arch/loongarch/util/unwind-libunwind.c

+// SPDX-License-Identifier: GPL-2.0
+
+#include <errno.h>
+#include <libunwind.h>
+#include "perf_regs.h"
+#include "../../util/unwind.h"
+#include "util/debug.h"
+
+int libunwind__arch_reg_id(int regnum)
+{
+	switch (regnum) {
+	case UNW_LOONGARCH64_R1:
+		return PERF_REG_LOONGARCH_R1;
+	case UNW_LOONGARCH64_R2:
+		return PERF_REG_LOONGARCH_R2;
+	case UNW_LOONGARCH64_R3:
+		return PERF_REG_LOONGARCH_R3;
+	case UNW_LOONGARCH64_R4:
+		return PERF_REG_LOONGARCH_R4;
+	case UNW_LOONGARCH64_R5:
+		return PERF_REG_LOONGARCH_R5;
+	case UNW_LOONGARCH64_R6:
+		return PERF_REG_LOONGARCH_R6;
+	case UNW_LOONGARCH64_R7:
+		return PERF_REG_LOONGARCH_R7;
+	case UNW_LOONGARCH64_R8:
+		return PERF_REG_LOONGARCH_R8;
+	case UNW_LOONGARCH64_R9:
+		return PERF_REG_LOONGARCH_R9;
+	case UNW_LOONGARCH64_R10:
+		return PERF_REG_LOONGARCH_R10;
+	case UNW_LOONGARCH64_R11:
+		return PERF_REG_LOONGARCH_R11;
+	case UNW_LOONGARCH64_R12:
+		return PERF_REG_LOONGARCH_R12;
+	case UNW_LOONGARCH64_R13:
+		return PERF_REG_LOONGARCH_R13;
+	case UNW_LOONGARCH64_R14:
+		return PERF_REG_LOONGARCH_R14;
+	case UNW_LOONGARCH64_R15:
+		return PERF_REG_LOONGARCH_R15;
+	case UNW_LOONGARCH64_R16:
+		return PERF_REG_LOONGARCH_R16;
+	case UNW_LOONGARCH64_R17:
+		return PERF_REG_LOONGARCH_R17;
+	case UNW_LOONGARCH64_R18:
+		return PERF_REG_LOONGARCH_R18;
+	case UNW_LOONGARCH64_R19:
+		return PERF_REG_LOONGARCH_R19;
+	case UNW_LOONGARCH64_R20:
+		return PERF_REG_LOONGARCH_R20;
+	case UNW_LOONGARCH64_R21:
+		return PERF_REG_LOONGARCH_R21;
+	case UNW_LOONGARCH64_R22:
+		return PERF_REG_LOONGARCH_R22;
+	case UNW_LOONGARCH64_R23:
+		return PERF_REG_LOONGARCH_R23;
+	case UNW_LOONGARCH64_R24:
+		return PERF_REG_LOONGARCH_R24;
+	case UNW_LOONGARCH64_R25:
+		return PERF_REG_LOONGARCH_R25;
+	case UNW_LOONGARCH64_R26:
+		return PERF_REG_LOONGARCH_R26;
+	case UNW_LOONGARCH64_R27:
+		return PERF_REG_LOONGARCH_R27;
+	case UNW_LOONGARCH64_R28:
+		return PERF_REG_LOONGARCH_R28;
+	case UNW_LOONGARCH64_R29:
+		return PERF_REG_LOONGARCH_R29;
+	case UNW_LOONGARCH64_R30:
+		return PERF_REG_LOONGARCH_R30;
+	case UNW_LOONGARCH64_R31:
+		return PERF_REG_LOONGARCH_R31;
+	case UNW_LOONGARCH64_PC:
+		return PERF_REG_LOONGARCH_PC;
+	default:
+		pr_err("unwind: invalid reg id %d\n", regnum);
+		return -EINVAL;
+	}
+
+	return -EINVAL;
+}

tools/perf/check-headers.sh

@@ -40,6 +40,7 @@ arch/x86/lib/x86-opcode-map.txt
 arch/x86/tools/gen-insn-attr-x86.awk
 arch/arm/include/uapi/asm/perf_regs.h
 arch/arm64/include/uapi/asm/perf_regs.h
+arch/loongarch/include/uapi/asm/perf_regs.h
 arch/mips/include/uapi/asm/perf_regs.h
 arch/powerpc/include/uapi/asm/perf_regs.h
 arch/s390/include/uapi/asm/perf_regs.h

tools/perf/util/annotate.c

@@ -149,6 +149,7 @@ static int arch__associate_ins_ops(struct arch* arch, const char *name, struct i
 #include "arch/arm/annotate/instructions.c"
 #include "arch/arm64/annotate/instructions.c"
 #include "arch/csky/annotate/instructions.c"
+#include "arch/loongarch/annotate/instructions.c"
 #include "arch/mips/annotate/instructions.c"
 #include "arch/x86/annotate/instructions.c"
 #include "arch/powerpc/annotate/instructions.c"
@@ -211,6 +212,13 @@ static struct arch architectures[] = {
 			.comment_char = '#',
 		},
 	},
+	{
+		.name = "loongarch",
+		.init = loongarch__annotate_init,
+		.objdump = {
+			.comment_char = '#',
+		},
+	},
 };
 
 static void ins__delete(struct ins_operands *ops)

tools/perf/util/dwarf-regs.c

@@ -14,6 +14,10 @@
 #define EM_AARCH64	183  /* ARM 64 bit */
 #endif
 
+#ifndef EM_LOONGARCH
+#define EM_LOONGARCH	258 /* LoongArch */
+#endif
+
 /* Define const char * {arch}_register_tbl[] */
 #define DEFINE_DWARF_REGSTR_TABLE
 #include "../arch/x86/include/dwarf-regs-table.h"
@@ -25,6 +29,7 @@
 #include "../arch/sparc/include/dwarf-regs-table.h"
 #include "../arch/xtensa/include/dwarf-regs-table.h"
 #include "../arch/mips/include/dwarf-regs-table.h"
+#include "../arch/loongarch/include/dwarf-regs-table.h"
 
 #define __get_dwarf_regstr(tbl, n) (((n) < ARRAY_SIZE(tbl)) ? (tbl)[(n)] : NULL)
 
@@ -56,6 +61,8 @@ const char *get_dwarf_regstr(unsigned int n, unsigned int machine)
 		return __get_dwarf_regstr(xtensa_regstr_tbl, n);
 	case EM_MIPS:
 		return __get_dwarf_regstr(mips_regstr_tbl, n);
+	case EM_LOONGARCH:
+		return __get_dwarf_regstr(loongarch_regstr_tbl, n);
 	default:
 		pr_err("ELF MACHINE %x is not supported.\n", machine);
 	}

tools/perf/util/env.c

@@ -435,6 +435,8 @@ static const char *normalize_arch(char *arch)
 		return "mips";
 	if (!strncmp(arch, "sh", 2) && isdigit(arch[2]))
 		return "sh";
+	if (!strncmp(arch, "loongarch", 9))
+		return "loongarch";
 
 	return arch;
 }

tools/perf/util/genelf.h

@@ -43,6 +43,9 @@ int jit_add_debug_info(Elf *e, uint64_t code_addr, void *debug, int nr_debug_ent
 #elif defined(__riscv) && __riscv_xlen == 64
 #define GEN_ELF_ARCH	EM_RISCV
 #define GEN_ELF_CLASS	ELFCLASS64
+#elif defined(__loongarch__)
+#define GEN_ELF_ARCH	EM_LOONGARCH
+#define GEN_ELF_CLASS	ELFCLASS64
 #else
 #error "unsupported architecture"
 #endif

tools/perf/util/perf_regs.c

@@ -28,6 +28,7 @@ uint64_t __weak arch__user_reg_mask(void)
 
 #include "../../arch/arm/include/uapi/asm/perf_regs.h"
 #include "../../arch/csky/include/uapi/asm/perf_regs.h"
+#include "../../arch/loongarch/include/uapi/asm/perf_regs.h"
 #include "../../arch/mips/include/uapi/asm/perf_regs.h"
 #include "../../arch/powerpc/include/uapi/asm/perf_regs.h"
 #include "../../arch/riscv/include/uapi/asm/perf_regs.h"
@@ -236,6 +237,79 @@ static const char *__perf_reg_name_csky(int id)
 	return NULL;
 }
 
+static inline const char *__perf_reg_name_loongarch(int id)
+{
+	switch (id) {
+	case PERF_REG_LOONGARCH_PC:
+		return "PC";
+	case PERF_REG_LOONGARCH_R1:
+		return "%r1";
+	case PERF_REG_LOONGARCH_R2:
+		return "%r2";
+	case PERF_REG_LOONGARCH_R3:
+		return "%r3";
+	case PERF_REG_LOONGARCH_R4:
+		return "%r4";
+	case PERF_REG_LOONGARCH_R5:
+		return "%r5";
+	case PERF_REG_LOONGARCH_R6:
+		return "%r6";
+	case PERF_REG_LOONGARCH_R7:
+		return "%r7";
+	case PERF_REG_LOONGARCH_R8:
+		return "%r8";
+	case PERF_REG_LOONGARCH_R9:
+		return "%r9";
+	case PERF_REG_LOONGARCH_R10:
+		return "%r10";
+	case PERF_REG_LOONGARCH_R11:
+		return "%r11";
+	case PERF_REG_LOONGARCH_R12:
+		return "%r12";
+	case PERF_REG_LOONGARCH_R13:
+		return "%r13";
+	case PERF_REG_LOONGARCH_R14:
+		return "%r14";
+	case PERF_REG_LOONGARCH_R15:
+		return "%r15";
+	case PERF_REG_LOONGARCH_R16:
+		return "%r16";
+	case PERF_REG_LOONGARCH_R17:
+		return "%r17";
+	case PERF_REG_LOONGARCH_R18:
+		return "%r18";
+	case PERF_REG_LOONGARCH_R19:
+		return "%r19";
+	case PERF_REG_LOONGARCH_R20:
+		return "%r20";
+	case PERF_REG_LOONGARCH_R21:
+		return "%r21";
+	case PERF_REG_LOONGARCH_R22:
+		return "%r22";
+	case PERF_REG_LOONGARCH_R23:
+		return "%r23";
+	case PERF_REG_LOONGARCH_R24:
+		return "%r24";
+	case PERF_REG_LOONGARCH_R25:
+		return "%r25";
+	case PERF_REG_LOONGARCH_R26:
+		return "%r26";
+	case PERF_REG_LOONGARCH_R27:
+		return "%r27";
+	case PERF_REG_LOONGARCH_R28:
+		return "%r28";
+	case PERF_REG_LOONGARCH_R29:
+		return "%r29";
+	case PERF_REG_LOONGARCH_R30:
+		return "%r30";
+	case PERF_REG_LOONGARCH_R31:
+		return "%r31";
+	default:
+		break;
+	}
+	return NULL;
+}
+
 static const char *__perf_reg_name_mips(int id)
 {
 	switch (id) {
@@ -670,6 +744,8 @@ const char *perf_reg_name(int id, const char *arch)
 
 	if (!strcmp(arch, "csky"))
 		reg_name = __perf_reg_name_csky(id);
+	else if (!strcmp(arch, "loongarch"))
+		reg_name = __perf_reg_name_loongarch(id);
 	else if (!strcmp(arch, "mips"))
 		reg_name = __perf_reg_name_mips(id);
 	else if (!strcmp(arch, "powerpc"))

tools/perf/util/syscalltbl.c

@@ -38,6 +38,10 @@ static const char **syscalltbl_native = syscalltbl_arm64;
 #include <asm/syscalls_n64.c>
 const int syscalltbl_native_max_id = SYSCALLTBL_MIPS_N64_MAX_ID;
 static const char **syscalltbl_native = syscalltbl_mips_n64;
+#elif defined(__loongarch__)
+#include <asm/syscalls.c>
+const int syscalltbl_native_max_id = SYSCALLTBL_LOONGARCH_MAX_ID;
+static const char **syscalltbl_native = syscalltbl_loongarch;
 #endif
 
 struct syscall {