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()
  ...

6 files changed, 168 insertions, 26 deletions

diff --git a/arch/loongarch/include/asm/checksum.h b/arch/loongarch/include/asm/checksum.h
new file mode 100644
index 000000000000..cabbf6af44c4
--- /dev/null
+++ b/arch/loongarch/include/asm/checksum.h
@@ -0,0 +1,66 @@
+/* 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 */
diff --git a/arch/loongarch/include/asm/fpu.h b/arch/loongarch/include/asm/fpu.h
index 358b254d9c1d..192f8e35d912 100644
--- a/arch/loongarch/include/asm/fpu.h
+++ b/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 *);
diff --git a/arch/loongarch/include/asm/ftrace.h b/arch/loongarch/include/asm/ftrace.h
index 3418d32d4fc7..23e2ba78dcb0 100644
--- a/arch/loongarch/include/asm/ftrace.h
+++ b/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__ */
diff --git a/arch/loongarch/include/asm/inst.h b/arch/loongarch/include/asm/inst.h
index a04fe755d719..b09887ffcd15 100644
--- a/arch/loongarch/include/asm/inst.h
+++ b/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 {
diff --git a/arch/loongarch/include/asm/loongarch.h b/arch/loongarch/include/asm/loongarch.h
index 83da5d29e2d1..b3323ab5b78d 100644
--- a/arch/loongarch/include/asm/loongarch.h
+++ b/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 */
 
-#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)
+/* 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_INT_END		(EXCCODE_INT_START + EXCCODE_INT_NUM - 1)
 
 /* FPU register names */
 #define LOONGARCH_FCSR0	$r0
diff --git a/arch/loongarch/include/asm/ptrace.h b/arch/loongarch/include/asm/ptrace.h
index d761db943335..35f0958163ac 100644
--- a/arch/loongarch/include/asm/ptrace.h
+++ b/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)