Merge tag 'loongarch-6.1' of...

Merge tag 'loongarch-6.1' of git://git.kernel.org/pub/scm/linux/kernel/git/chenhuacai/linux-loongson

Pull LoongArch updates from Huacai Chen:

 - Use EXPLICIT_RELOCS (ABIv2.0)

 - Use generic BUG() handler

 - Refactor TLB/Cache operations

 - Add qspinlock support

 - Add perf events support

 - Add kexec/kdump support

 - Add BPF JIT support

 - Add ACPI-based laptop driver

 - Update the default config file

* tag 'loongarch-6.1' of git://git.kernel.org/pub/scm/linux/kernel/git/chenhuacai/linux-loongson: (25 commits)
  LoongArch: Update Loongson-3 default config file
  LoongArch: Add ACPI-based generic laptop driver
  LoongArch: Add BPF JIT support
  LoongArch: Add some instruction opcodes and formats
  LoongArch: Move {signed,unsigned}_imm_check() to inst.h
  LoongArch: Add kdump support
  LoongArch: Add kexec support
  LoongArch: Use generic BUG() handler
  LoongArch: Add SysRq-x (TLB Dump) support
  LoongArch: Add perf events support
  LoongArch: Add qspinlock support
  LoongArch: Use TLB for ioremap()
  LoongArch: Support access filter to /dev/mem interface
  LoongArch: Refactor cache probe and flush methods
  LoongArch: mm: Refactor TLB exception handlers
  LoongArch: Support R_LARCH_GOT_PC_{LO12,HI20} in modules
  LoongArch: Support PC-relative relocations in modules
  LoongArch: Define ELF relocation types added in ABIv2.0
  LoongArch: Adjust symbol addressing for AS_HAS_EXPLICIT_RELOCS
  LoongArch: Add Kconfig option AS_HAS_EXPLICIT_RELOCS
  ...

arch/loongarch/Kbuild

 obj-y += kernel/
 obj-y += mm/
+obj-y += net/
 obj-y += vdso/
 
 # for cleaning

arch/loongarch/Kconfig

@@ -50,6 +50,7 @@ config LOONGARCH
 	select ARCH_USE_BUILTIN_BSWAP
 	select ARCH_USE_CMPXCHG_LOCKREF
 	select ARCH_USE_QUEUED_RWLOCKS
+	select ARCH_USE_QUEUED_SPINLOCKS
 	select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT
 	select ARCH_WANT_LD_ORPHAN_WARN
 	select ARCH_WANTS_NO_INSTR
@@ -61,6 +62,7 @@ config LOONGARCH
 	select GENERIC_CPU_AUTOPROBE
 	select GENERIC_ENTRY
 	select GENERIC_GETTIMEOFDAY
+	select GENERIC_IOREMAP if !ARCH_IOREMAP
 	select GENERIC_IRQ_MULTI_HANDLER
 	select GENERIC_IRQ_PROBE
 	select GENERIC_IRQ_SHOW
@@ -69,6 +71,7 @@ config LOONGARCH
 	select GENERIC_LIB_CMPDI2
 	select GENERIC_LIB_LSHRDI3
 	select GENERIC_LIB_UCMPDI2
+	select GENERIC_LIB_DEVMEM_IS_ALLOWED
 	select GENERIC_PCI_IOMAP
 	select GENERIC_SCHED_CLOCK
 	select GENERIC_SMP_IDLE_THREAD
@@ -83,6 +86,7 @@ config LOONGARCH
 	select HAVE_CONTEXT_TRACKING_USER
 	select HAVE_DEBUG_STACKOVERFLOW
 	select HAVE_DMA_CONTIGUOUS
+	select HAVE_EBPF_JIT
 	select HAVE_EXIT_THREAD
 	select HAVE_FAST_GUP
 	select HAVE_GENERIC_VDSO
@@ -93,6 +97,8 @@ config LOONGARCH
 	select HAVE_NMI
 	select HAVE_PCI
 	select HAVE_PERF_EVENTS
+	select HAVE_PERF_REGS
+	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_RSEQ
 	select HAVE_SETUP_PER_CPU_AREA if NUMA
@@ -136,6 +142,14 @@ config CPU_HAS_PREFETCH
 	bool
 	default y
 
+config GENERIC_BUG
+	def_bool y
+	depends on BUG
+
+config GENERIC_BUG_RELATIVE_POINTERS
+	def_bool y
+	depends on GENERIC_BUG
+
 config GENERIC_CALIBRATE_DELAY
 	def_bool y
 
@@ -157,7 +171,7 @@ config STACKTRACE_SUPPORT
 	bool
 	default y
 
-# MACH_LOONGSON32 and MACH_LOONGSON64 are delibrately carried over from the
+# MACH_LOONGSON32 and MACH_LOONGSON64 are deliberately carried over from the
 # MIPS Loongson code, to preserve Loongson-specific code paths in drivers that
 # are shared between architectures, and specifically expecting the symbols.
 config MACH_LOONGSON32
@@ -166,6 +180,9 @@ config MACH_LOONGSON32
 config MACH_LOONGSON64
 	def_bool 64BIT
 
+config FIX_EARLYCON_MEM
+	def_bool y
+
 config PAGE_SIZE_4KB
 	bool
 
@@ -194,6 +211,9 @@ config SCHED_OMIT_FRAME_POINTER
 	bool
 	default y
 
+config AS_HAS_EXPLICIT_RELOCS
+	def_bool $(as-instr,x:pcalau12i \$t0$(comma)%pc_hi20(x))
+
 menu "Kernel type and options"
 
 source "kernel/Kconfig.hz"
@@ -399,6 +419,46 @@ config ARCH_FORCE_MAX_ORDER
 	  The page size is not necessarily 4KB.  Keep this in mind
 	  when choosing a value for this option.
 
+config ARCH_IOREMAP
+	bool "Enable LoongArch DMW-based ioremap()"
+	help
+	  We use generic TLB-based ioremap() by default since it has page
+	  protection support. However, you can enable LoongArch DMW-based
+	  ioremap() for better performance.
+
+config KEXEC
+	bool "Kexec system call"
+	select KEXEC_CORE
+	help
+	  kexec is a system call that implements the ability to shutdown your
+	  current kernel, and to start another kernel.  It is like a reboot
+	  but it is independent of the system firmware.   And like a reboot
+	  you can start any kernel with it, not just Linux.
+
+	  The name comes from the similarity to the exec system call.
+
+config CRASH_DUMP
+	bool "Build kdump crash kernel"
+	help
+	  Generate crash dump after being started by kexec. This should
+	  be normally only set in special crash dump kernels which are
+	  loaded in the main kernel with kexec-tools into a specially
+	  reserved region and then later executed after a crash by
+	  kdump/kexec.
+
+	  For more details see Documentation/admin-guide/kdump/kdump.rst
+
+config PHYSICAL_START
+	hex "Physical address where the kernel is loaded"
+	default "0x90000000a0000000"
+	depends on CRASH_DUMP
+	help
+	  This gives the XKPRANGE address where the kernel is loaded.
+	  If you plan to use kernel for capturing the crash dump change
+	  this value to start of the reserved region (the "X" value as
+	  specified in the "crashkernel=YM@XM" command line boot parameter
+	  passed to the panic-ed kernel).
+
 config SECCOMP
 	bool "Enable seccomp to safely compute untrusted bytecode"
 	depends on PROC_FS

arch/loongarch/Makefile

@@ -43,15 +43,37 @@ endif
 
 cflags-y			+= -G0 -pipe -msoft-float
 LDFLAGS_vmlinux			+= -G0 -static -n -nostdlib
+
+# When the assembler supports explicit relocation hint, we must use it.
+# GCC may have -mexplicit-relocs off by default if it was built with an old
+# assembler, so we force it via an option.
+#
+# When the assembler does not supports explicit relocation hint, we can't use
+# it.  Disable it if the compiler supports it.
+#
+# If you've seen "unknown reloc hint" message building the kernel and you are
+# now wondering why "-mexplicit-relocs" is not wrapped with cc-option: the
+# combination of a "new" assembler and "old" compiler is not supported.  Either
+# upgrade the compiler or downgrade the assembler.
+ifdef CONFIG_AS_HAS_EXPLICIT_RELOCS
+cflags-y			+= -mexplicit-relocs
+KBUILD_CFLAGS_KERNEL		+= -mdirect-extern-access
+else
+cflags-y			+= $(call cc-option,-mno-explicit-relocs)
 KBUILD_AFLAGS_KERNEL		+= -Wa,-mla-global-with-pcrel
 KBUILD_CFLAGS_KERNEL		+= -Wa,-mla-global-with-pcrel
 KBUILD_AFLAGS_MODULE		+= -Wa,-mla-global-with-abs
 KBUILD_CFLAGS_MODULE		+= -fplt -Wa,-mla-global-with-abs,-mla-local-with-abs
+endif
 
 cflags-y += -ffreestanding
 cflags-y += $(call cc-option, -mno-check-zero-division)
 
+ifndef CONFIG_PHYSICAL_START
 load-y		= 0x9000000000200000
+else
+load-y		= $(CONFIG_PHYSICAL_START)
+endif
 bootvars-y	= VMLINUX_LOAD_ADDRESS=$(load-y)
 
 drivers-$(CONFIG_PCI)		+= arch/loongarch/pci/

arch/loongarch/configs/loongson3_defconfig

@@ -4,6 +4,7 @@ CONFIG_POSIX_MQUEUE=y
 CONFIG_NO_HZ=y
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_BPF_SYSCALL=y
+CONFIG_BPF_JIT=y
 CONFIG_PREEMPT=y
 CONFIG_BSD_PROCESS_ACCT=y
 CONFIG_BSD_PROCESS_ACCT_V3=y
@@ -45,6 +46,7 @@ CONFIG_SMP=y
 CONFIG_HOTPLUG_CPU=y
 CONFIG_NR_CPUS=64
 CONFIG_NUMA=y
+CONFIG_KEXEC=y
 CONFIG_PAGE_SIZE_16KB=y
 CONFIG_HZ_250=y
 CONFIG_ACPI=y
@@ -55,6 +57,7 @@ CONFIG_ACPI_DOCK=y
 CONFIG_ACPI_IPMI=m
 CONFIG_ACPI_PCI_SLOT=y
 CONFIG_ACPI_HOTPLUG_MEMORY=y
+CONFIG_EFI_ZBOOT=y
 CONFIG_EFI_GENERIC_STUB_INITRD_CMDLINE_LOADER=y
 CONFIG_EFI_CAPSULE_LOADER=m
 CONFIG_EFI_TEST=m
@@ -65,6 +68,8 @@ CONFIG_MODULE_FORCE_UNLOAD=y
 CONFIG_MODVERSIONS=y
 CONFIG_BLK_DEV_THROTTLING=y
 CONFIG_PARTITION_ADVANCED=y
+CONFIG_BSD_DISKLABEL=y
+CONFIG_UNIXWARE_DISKLABEL=y
 CONFIG_IOSCHED_BFQ=y
 CONFIG_BFQ_GROUP_IOSCHED=y
 CONFIG_BINFMT_MISC=m
@@ -82,8 +87,11 @@ CONFIG_ZSMALLOC=m
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
+CONFIG_TLS=m
+CONFIG_TLS_DEVICE=y
 CONFIG_XFRM_USER=y
 CONFIG_NET_KEY=y
+CONFIG_XDP_SOCKETS=y
 CONFIG_INET=y
 CONFIG_IP_MULTICAST=y
 CONFIG_IP_ADVANCED_ROUTER=y
@@ -95,6 +103,7 @@ CONFIG_IP_PNP_DHCP=y
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_IP_PNP_RARP=y
 CONFIG_NET_IPIP=m
+CONFIG_NET_IPGRE_DEMUX=m
 CONFIG_IP_MROUTE=y
 CONFIG_INET_ESP=m
 CONFIG_INET_UDP_DIAG=y
@@ -102,6 +111,7 @@ CONFIG_TCP_CONG_ADVANCED=y
 CONFIG_TCP_CONG_BBR=m
 CONFIG_IPV6_ROUTER_PREF=y
 CONFIG_IPV6_ROUTE_INFO=y
+CONFIG_INET6_ESP=m
 CONFIG_IPV6_MROUTE=y
 CONFIG_NETWORK_PHY_TIMESTAMPING=y
 CONFIG_NETFILTER=y
@@ -112,10 +122,11 @@ CONFIG_NF_LOG_NETDEV=m
 CONFIG_NF_CONNTRACK_AMANDA=m
 CONFIG_NF_CONNTRACK_FTP=m
 CONFIG_NF_CONNTRACK_NETBIOS_NS=m
+CONFIG_NF_CONNTRACK_SNMP=m
+CONFIG_NF_CONNTRACK_PPTP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_CT_NETLINK=m
 CONFIG_NF_TABLES=m
-CONFIG_NFT_COUNTER=m
 CONFIG_NFT_CONNLIMIT=m
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
@@ -200,7 +211,6 @@ CONFIG_NF_TABLES_IPV4=y
 CONFIG_NFT_DUP_IPV4=m
 CONFIG_NFT_FIB_IPV4=m
 CONFIG_NF_TABLES_ARP=y
-CONFIG_NF_LOG_ARP=m
 CONFIG_IP_NF_IPTABLES=m
 CONFIG_IP_NF_MATCH_AH=m
 CONFIG_IP_NF_MATCH_ECN=m
@@ -254,10 +264,14 @@ CONFIG_BPFILTER=y
 CONFIG_IP_SCTP=m
 CONFIG_RDS=y
 CONFIG_L2TP=m
+CONFIG_L2TP_V3=y
+CONFIG_L2TP_IP=m
+CONFIG_L2TP_ETH=m
 CONFIG_BRIDGE=m
 CONFIG_VLAN_8021Q=m
 CONFIG_VLAN_8021Q_GVRP=y
 CONFIG_VLAN_8021Q_MVRP=y
+CONFIG_LLC2=m
 CONFIG_NET_SCHED=y
 CONFIG_NET_SCH_HTB=m
 CONFIG_NET_SCH_PRIO=m
@@ -282,9 +296,33 @@ CONFIG_VSOCKETS=m
 CONFIG_VIRTIO_VSOCKETS=m
 CONFIG_NETLINK_DIAG=y
 CONFIG_CGROUP_NET_PRIO=y
+CONFIG_BPF_STREAM_PARSER=y
 CONFIG_BT=m
+CONFIG_BT_RFCOMM=m
+CONFIG_BT_RFCOMM_TTY=y
+CONFIG_BT_BNEP=m
+CONFIG_BT_BNEP_MC_FILTER=y
+CONFIG_BT_BNEP_PROTO_FILTER=y
+CONFIG_BT_HIDP=m
+CONFIG_BT_HS=y
 CONFIG_BT_HCIBTUSB=m
-# CONFIG_BT_HCIBTUSB_BCM is not set
+CONFIG_BT_HCIBTUSB_AUTOSUSPEND=y
+CONFIG_BT_HCIBTUSB_MTK=y
+CONFIG_BT_HCIUART=m
+CONFIG_BT_HCIUART_BCSP=y
+CONFIG_BT_HCIUART_ATH3K=y
+CONFIG_BT_HCIUART_INTEL=y
+CONFIG_BT_HCIUART_AG6XX=y
+CONFIG_BT_HCIBCM203X=m
+CONFIG_BT_HCIBPA10X=m
+CONFIG_BT_HCIBFUSB=m
+CONFIG_BT_HCIDTL1=m
+CONFIG_BT_HCIBT3C=m
+CONFIG_BT_HCIBLUECARD=m
+CONFIG_BT_HCIVHCI=m
+CONFIG_BT_MRVL=m
+CONFIG_BT_ATH3K=m
+CONFIG_BT_VIRTIO=m
 CONFIG_CFG80211=m
 CONFIG_CFG80211_WEXT=y
 CONFIG_MAC80211=m
@@ -329,7 +367,6 @@ CONFIG_PARPORT_PC_FIFO=y
 CONFIG_ZRAM=m
 CONFIG_ZRAM_DEF_COMP_ZSTD=y
 CONFIG_BLK_DEV_LOOP=y
-CONFIG_BLK_DEV_CRYPTOLOOP=y
 CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_SIZE=8192
@@ -486,6 +523,7 @@ CONFIG_PPP_FILTER=y
 CONFIG_PPP_MPPE=m
 CONFIG_PPP_MULTILINK=y
 CONFIG_PPPOE=m
+CONFIG_PPTP=m
 CONFIG_PPPOL2TP=m
 CONFIG_PPP_ASYNC=m
 CONFIG_PPP_SYNC_TTY=m
@@ -505,7 +543,6 @@ CONFIG_ATH9K_HTC=m
 CONFIG_IWLWIFI=m
 CONFIG_IWLDVM=m
 CONFIG_IWLMVM=m
-CONFIG_IWLWIFI_BCAST_FILTERING=y
 CONFIG_HOSTAP=m
 CONFIG_MT7601U=m
 CONFIG_RT2X00=m
@@ -521,6 +558,14 @@ CONFIG_RTL8821AE=m
 CONFIG_RTL8192CU=m
 # CONFIG_RTLWIFI_DEBUG is not set
 CONFIG_RTL8XXXU=m
+CONFIG_RTW88=m
+CONFIG_RTW88_8822BE=m
+CONFIG_RTW88_8822CE=m
+CONFIG_RTW88_8723DE=m
+CONFIG_RTW88_8821CE=m
+CONFIG_RTW89=m
+CONFIG_RTW89_8852AE=m
+CONFIG_RTW89_8852CE=m
 CONFIG_ZD1211RW=m
 CONFIG_USB_NET_RNDIS_WLAN=m
 CONFIG_INPUT_MOUSEDEV=y
@@ -651,6 +696,11 @@ CONFIG_USB_SERIAL_FTDI_SIO=m
 CONFIG_USB_SERIAL_PL2303=m
 CONFIG_USB_SERIAL_OPTION=m
 CONFIG_USB_GADGET=y
+CONFIG_TYPEC=m
+CONFIG_TYPEC_TCPM=m
+CONFIG_TYPEC_TCPCI=m
+CONFIG_TYPEC_UCSI=m
+CONFIG_UCSI_ACPI=m
 CONFIG_INFINIBAND=m
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_EFI=y
@@ -688,7 +738,6 @@ CONFIG_COMEDI_NI_PCIDIO=m
 CONFIG_COMEDI_NI_PCIMIO=m
 CONFIG_STAGING=y
 CONFIG_R8188EU=m
-# CONFIG_88EU_AP_MODE is not set
 CONFIG_PM_DEVFREQ=y
 CONFIG_DEVFREQ_GOV_SIMPLE_ONDEMAND=y
 CONFIG_DEVFREQ_GOV_PERFORMANCE=y
@@ -772,14 +821,12 @@ CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
 CONFIG_CRYPTO_HMAC=y
 CONFIG_CRYPTO_VMAC=m
-CONFIG_CRYPTO_TGR192=m
 CONFIG_CRYPTO_WP512=m
 CONFIG_CRYPTO_ANUBIS=m
 CONFIG_CRYPTO_BLOWFISH=m
 CONFIG_CRYPTO_CAST5=m
 CONFIG_CRYPTO_CAST6=m
 CONFIG_CRYPTO_KHAZAD=m
-CONFIG_CRYPTO_SALSA20=m
 CONFIG_CRYPTO_SEED=m
 CONFIG_CRYPTO_SERPENT=m
 CONFIG_CRYPTO_TEA=m

arch/loongarch/include/asm/Kbuild

 # SPDX-License-Identifier: GPL-2.0
 generic-y += dma-contiguous.h
 generic-y += export.h
+generic-y += mcs_spinlock.h
 generic-y += parport.h
 generic-y += early_ioremap.h
 generic-y += qrwlock.h
-generic-y += qrwlock_types.h
-generic-y += spinlock.h
-generic-y += spinlock_types.h
+generic-y += qspinlock.h
 generic-y += rwsem.h
 generic-y += segment.h
 generic-y += user.h

arch/loongarch/include/asm/bootinfo.h

@@ -40,4 +40,9 @@ extern unsigned long fw_arg0, fw_arg1, fw_arg2;
 extern struct loongson_board_info b_info;
 extern struct loongson_system_configuration loongson_sysconf;
 
+static inline bool io_master(int cpu)
+{
+	return test_bit(cpu, &loongson_sysconf.cores_io_master);
+}
+
 #endif /* _ASM_BOOTINFO_H */

arch/loongarch/include/asm/bug.h

@@ -2,21 +2,59 @@
 #ifndef __ASM_BUG_H
 #define __ASM_BUG_H
 
-#include <linux/compiler.h>
+#include <asm/break.h>
+#include <linux/stringify.h>
+
+#ifndef CONFIG_DEBUG_BUGVERBOSE
+#define _BUGVERBOSE_LOCATION(file, line)
+#else
+#define __BUGVERBOSE_LOCATION(file, line)			\
+		.pushsection .rodata.str, "aMS", @progbits, 1;	\
+	10002:	.string file;					\
+		.popsection;					\
+								\
+		.long 10002b - .;				\
+		.short line;
+#define _BUGVERBOSE_LOCATION(file, line) __BUGVERBOSE_LOCATION(file, line)
+#endif
 
-#ifdef CONFIG_BUG
+#ifndef CONFIG_GENERIC_BUG
+#define __BUG_ENTRY(flags)
+#else
+#define __BUG_ENTRY(flags) 					\
+		.pushsection __bug_table, "aw";			\
+		.align 2;					\
+	10000:	.long 10001f - .;				\
+		_BUGVERBOSE_LOCATION(__FILE__, __LINE__)	\
+		.short flags; 					\
+		.popsection;					\
+	10001:
+#endif
 
-#include <asm/break.h>
+#define ASM_BUG_FLAGS(flags)					\
+	__BUG_ENTRY(flags)					\
+	break		BRK_BUG
 
-static inline void __noreturn BUG(void)
-{
-	__asm__ __volatile__("break %0" : : "i" (BRK_BUG));
-	unreachable();
-}
+#define ASM_BUG()	ASM_BUG_FLAGS(0)
 
-#define HAVE_ARCH_BUG
+#define __BUG_FLAGS(flags)					\
+	asm_inline volatile (__stringify(ASM_BUG_FLAGS(flags)));
 
-#endif
+#define __WARN_FLAGS(flags)					\
+do {								\
+	instrumentation_begin();				\
+	__BUG_FLAGS(BUGFLAG_WARNING|(flags));			\
+	instrumentation_end();					\
+} while (0)
+
+#define BUG()							\
+do {								\
+	instrumentation_begin();				\
+	__BUG_FLAGS(0);						\
+	unreachable();						\
+} while (0)
+
+#define HAVE_ARCH_BUG
 
 #include <asm-generic/bug.h>
 

arch/loongarch/include/asm/cacheflush.h

@@ -6,10 +6,33 @@
 #define _ASM_CACHEFLUSH_H
 
 #include <linux/mm.h>
-#include <asm/cpu-features.h>
+#include <asm/cpu-info.h>
 #include <asm/cacheops.h>
 
-extern void local_flush_icache_range(unsigned long start, unsigned long end);
+static inline bool cache_present(struct cache_desc *cdesc)
+{
+	return cdesc->flags & CACHE_PRESENT;
+}
+
+static inline bool cache_private(struct cache_desc *cdesc)
+{
+	return cdesc->flags & CACHE_PRIVATE;
+}
+
+static inline bool cache_inclusive(struct cache_desc *cdesc)
+{
+	return cdesc->flags & CACHE_INCLUSIVE;
+}
+
+static inline unsigned int cpu_last_level_cache_line_size(void)
+{
+	int cache_present = boot_cpu_data.cache_leaves_present;
+
+	return boot_cpu_data.cache_leaves[cache_present - 1].linesz;
+}
+
+asmlinkage void __flush_cache_all(void);
+void local_flush_icache_range(unsigned long start, unsigned long end);
 
 #define flush_icache_range	local_flush_icache_range
 #define flush_icache_user_range	local_flush_icache_range
@@ -35,44 +58,30 @@ extern void local_flush_icache_range(unsigned long start, unsigned long end);
 	:								\
 	: "i" (op), "ZC" (*(unsigned char *)(addr)))
 
-static inline void flush_icache_line_indexed(unsigned long addr)
-{
-	cache_op(Index_Invalidate_I, addr);
-}
-
-static inline void flush_dcache_line_indexed(unsigned long addr)
-{
-	cache_op(Index_Writeback_Inv_D, addr);
-}
-
-static inline void flush_vcache_line_indexed(unsigned long addr)
-{
-	cache_op(Index_Writeback_Inv_V, addr);
-}
-
-static inline void flush_scache_line_indexed(unsigned long addr)
-{
-	cache_op(Index_Writeback_Inv_S, addr);
-}
-
-static inline void flush_icache_line(unsigned long addr)
-{
-	cache_op(Hit_Invalidate_I, addr);
-}
-
-static inline void flush_dcache_line(unsigned long addr)
-{
-	cache_op(Hit_Writeback_Inv_D, addr);
-}
-
-static inline void flush_vcache_line(unsigned long addr)
-{
-	cache_op(Hit_Writeback_Inv_V, addr);
-}
-
-static inline void flush_scache_line(unsigned long addr)
+static inline void flush_cache_line(int leaf, unsigned long addr)
 {
-	cache_op(Hit_Writeback_Inv_S, addr);
+	switch (leaf) {
+	case Cache_LEAF0:
+		cache_op(Index_Writeback_Inv_LEAF0, addr);
+		break;
+	case Cache_LEAF1:
+		cache_op(Index_Writeback_Inv_LEAF1, addr);
+		break;
+	case Cache_LEAF2:
+		cache_op(Index_Writeback_Inv_LEAF2, addr);
+		break;
+	case Cache_LEAF3:
+		cache_op(Index_Writeback_Inv_LEAF3, addr);
+		break;
+	case Cache_LEAF4:
+		cache_op(Index_Writeback_Inv_LEAF4, addr);
+		break;
+	case Cache_LEAF5:
+		cache_op(Index_Writeback_Inv_LEAF5, addr);
+		break;
+	default:
+		break;
+	}
 }
 
 #include <asm-generic/cacheflush.h>

arch/loongarch/include/asm/cacheops.h

@@ -8,16 +8,18 @@
 #define __ASM_CACHEOPS_H
 
 /*
- * Most cache ops are split into a 2 bit field identifying the cache, and a 3
+ * Most cache ops are split into a 3 bit field identifying the cache, and a 2
  * bit field identifying the cache operation.
  */
-#define CacheOp_Cache			0x03
-#define CacheOp_Op			0x1c
+#define CacheOp_Cache			0x07
+#define CacheOp_Op			0x18
 
-#define Cache_I				0x00
-#define Cache_D				0x01
-#define Cache_V				0x02
-#define Cache_S				0x03
+#define Cache_LEAF0			0x00
+#define Cache_LEAF1			0x01
+#define Cache_LEAF2			0x02
+#define Cache_LEAF3			0x03
+#define Cache_LEAF4			0x04
+#define Cache_LEAF5			0x05
 
 #define Index_Invalidate		0x08
 #define Index_Writeback_Inv		0x08
@@ -25,13 +27,17 @@
 #define Hit_Writeback_Inv		0x10
 #define CacheOp_User_Defined		0x18
 
-#define Index_Invalidate_I		(Cache_I | Index_Invalidate)
-#define Index_Writeback_Inv_D		(Cache_D | Index_Writeback_Inv)
-#define Index_Writeback_Inv_V		(Cache_V | Index_Writeback_Inv)
-#define Index_Writeback_Inv_S		(Cache_S | Index_Writeback_Inv)
-#define Hit_Invalidate_I		(Cache_I | Hit_Invalidate)
-#define Hit_Writeback_Inv_D		(Cache_D | Hit_Writeback_Inv)
-#define Hit_Writeback_Inv_V		(Cache_V | Hit_Writeback_Inv)
-#define Hit_Writeback_Inv_S		(Cache_S | Hit_Writeback_Inv)
+#define Index_Writeback_Inv_LEAF0	(Cache_LEAF0 | Index_Writeback_Inv)
+#define Index_Writeback_Inv_LEAF1	(Cache_LEAF1 | Index_Writeback_Inv)
+#define Index_Writeback_Inv_LEAF2	(Cache_LEAF2 | Index_Writeback_Inv)
+#define Index_Writeback_Inv_LEAF3	(Cache_LEAF3 | Index_Writeback_Inv)
+#define Index_Writeback_Inv_LEAF4	(Cache_LEAF4 | Index_Writeback_Inv)
+#define Index_Writeback_Inv_LEAF5	(Cache_LEAF5 | Index_Writeback_Inv)
+#define Hit_Writeback_Inv_LEAF0		(Cache_LEAF0 | Hit_Writeback_Inv)
+#define Hit_Writeback_Inv_LEAF1		(Cache_LEAF1 | Hit_Writeback_Inv)
+#define Hit_Writeback_Inv_LEAF2		(Cache_LEAF2 | Hit_Writeback_Inv)
+#define Hit_Writeback_Inv_LEAF3		(Cache_LEAF3 | Hit_Writeback_Inv)
+#define Hit_Writeback_Inv_LEAF4		(Cache_LEAF4 | Hit_Writeback_Inv)
+#define Hit_Writeback_Inv_LEAF5		(Cache_LEAF5 | Hit_Writeback_Inv)
 
 #endif	/* __ASM_CACHEOPS_H */

arch/loongarch/include/asm/cmpxchg.h

@@ -61,8 +61,8 @@ static inline unsigned int __xchg_small(volatile void *ptr, unsigned int val,
 	return (old32 & mask) >> shift;
 }
 
-static inline unsigned long __xchg(volatile void *ptr, unsigned long x,
-				   int size)
+static __always_inline unsigned long
+__xchg(volatile void *ptr, unsigned long x, int size)
 {
 	switch (size) {
 	case 1:
@@ -159,8 +159,8 @@ static inline unsigned int __cmpxchg_small(volatile void *ptr, unsigned int old,
 	return (old32 & mask) >> shift;
 }
 
-static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
-				      unsigned long new, unsigned int size)
+static __always_inline unsigned long
+__cmpxchg(volatile void *ptr, unsigned long old, unsigned long new, unsigned int size)
 {
 	switch (size) {
 	case 1:

arch/loongarch/include/asm/cpu-features.h

@@ -19,11 +19,6 @@
 #define cpu_has_loongarch32		(cpu_data[0].isa_level & LOONGARCH_CPU_ISA_32BIT)
 #define cpu_has_loongarch64		(cpu_data[0].isa_level & LOONGARCH_CPU_ISA_64BIT)
 
-#define cpu_icache_line_size()		cpu_data[0].icache.linesz
-#define cpu_dcache_line_size()		cpu_data[0].dcache.linesz
-#define cpu_vcache_line_size()		cpu_data[0].vcache.linesz
-#define cpu_scache_line_size()		cpu_data[0].scache.linesz
-
 #ifdef CONFIG_32BIT
 # define cpu_has_64bits			(cpu_data[0].isa_level & LOONGARCH_CPU_ISA_64BIT)
 # define cpu_vabits			31

arch/loongarch/include/asm/cpu-info.h

@@ -10,18 +10,28 @@
 
 #include <asm/loongarch.h>
 
+/* cache_desc->flags */
+enum {
+	CACHE_PRESENT	= (1 << 0),
+	CACHE_PRIVATE	= (1 << 1),	/* core private cache */
+	CACHE_INCLUSIVE	= (1 << 2),	/* include the inner level caches */
+};
+
 /*
  * Descriptor for a cache
  */
 struct cache_desc {
-	unsigned int waysize;	/* Bytes per way */
+	unsigned char type;
+	unsigned char level;
 	unsigned short sets;	/* Number of lines per set */
 	unsigned char ways;	/* Number of ways */
 	unsigned char linesz;	/* Size of line in bytes */
-	unsigned char waybit;	/* Bits to select in a cache set */
 	unsigned char flags;	/* Flags describing cache properties */
 };
 
+#define CACHE_LEVEL_MAX		3
+#define CACHE_LEAVES_MAX	6
+
 struct cpuinfo_loongarch {
 	u64			asid_cache;
 	unsigned long		asid_mask;
@@ -40,11 +50,8 @@ struct cpuinfo_loongarch {
 	int			tlbsizemtlb;
 	int			tlbsizestlbsets;
 	int			tlbsizestlbways;
-	struct cache_desc	icache; /* Primary I-cache */
-	struct cache_desc	dcache; /* Primary D or combined I/D cache */
-	struct cache_desc	vcache; /* Victim cache, between pcache and scache */
-	struct cache_desc	scache; /* Secondary cache */
-	struct cache_desc	tcache; /* Tertiary/split secondary cache */
+	int			cache_leaves_present; /* number of cache_leaves[] elements */
+	struct cache_desc	cache_leaves[CACHE_LEAVES_MAX];
 	int			core;   /* physical core number in package */
 	int			package;/* physical package number */
 	int			vabits; /* Virtual Address size in bits */

arch/loongarch/include/asm/elf.h

@@ -74,6 +74,43 @@
 #define R_LARCH_SUB64				56
 #define R_LARCH_GNU_VTINHERIT			57
 #define R_LARCH_GNU_VTENTRY			58
+#define R_LARCH_B16				64
+#define R_LARCH_B21				65
+#define R_LARCH_B26				66
+#define R_LARCH_ABS_HI20			67
+#define R_LARCH_ABS_LO12			68
+#define R_LARCH_ABS64_LO20			69
+#define R_LARCH_ABS64_HI12			70
+#define R_LARCH_PCALA_HI20			71
+#define R_LARCH_PCALA_LO12			72
+#define R_LARCH_PCALA64_LO20			73
+#define R_LARCH_PCALA64_HI12			74
+#define R_LARCH_GOT_PC_HI20			75
+#define R_LARCH_GOT_PC_LO12			76
+#define R_LARCH_GOT64_PC_LO20			77
+#define R_LARCH_GOT64_PC_HI12			78
+#define R_LARCH_GOT_HI20			79
+#define R_LARCH_GOT_LO12			80
+#define R_LARCH_GOT64_LO20			81
+#define R_LARCH_GOT64_HI12			82
+#define R_LARCH_TLS_LE_HI20			83
+#define R_LARCH_TLS_LE_LO12			84
+#define R_LARCH_TLS_LE64_LO20			85
+#define R_LARCH_TLS_LE64_HI12			86
+#define R_LARCH_TLS_IE_PC_HI20			87
+#define R_LARCH_TLS_IE_PC_LO12			88
+#define R_LARCH_TLS_IE64_PC_LO20		89
+#define R_LARCH_TLS_IE64_PC_HI12		90
+#define R_LARCH_TLS_IE_HI20			91
+#define R_LARCH_TLS_IE_LO12			92
+#define R_LARCH_TLS_IE64_LO20			93
+#define R_LARCH_TLS_IE64_HI12			94
+#define R_LARCH_TLS_LD_PC_HI20			95
+#define R_LARCH_TLS_LD_HI20			96
+#define R_LARCH_TLS_GD_PC_HI20			97
+#define R_LARCH_TLS_GD_HI20			98
+#define R_LARCH_32_PCREL			99
+#define R_LARCH_RELAX				100
 
 #ifndef ELF_ARCH
 

arch/loongarch/include/asm/fixmap.h

@@ -10,4 +10,19 @@
 
 #define NR_FIX_BTMAPS 64
 
+enum fixed_addresses {
+	FIX_HOLE,
+	FIX_EARLYCON_MEM_BASE,
+	__end_of_fixed_addresses
+};
+
+#define FIXADDR_SIZE	(__end_of_fixed_addresses << PAGE_SHIFT)
+#define FIXADDR_START	(FIXADDR_TOP - FIXADDR_SIZE)
+#define FIXMAP_PAGE_IO	PAGE_KERNEL_SUC
+
+extern void __set_fixmap(enum fixed_addresses idx,
+			 phys_addr_t phys, pgprot_t flags);
+
+#include <asm-generic/fixmap.h>
+
 #endif

arch/loongarch/include/asm/inst.h

@@ -8,6 +8,8 @@
 #include <linux/types.h>
 #include <asm/asm.h>
 
+#define INSN_BREAK		0x002a0000
+
 #define ADDR_IMMMASK_LU52ID	0xFFF0000000000000
 #define ADDR_IMMMASK_LU32ID	0x000FFFFF00000000
 #define ADDR_IMMMASK_ADDU16ID	0x00000000FFFF0000
@@ -18,9 +20,16 @@
 
 #define ADDR_IMM(addr, INSN)	((addr & ADDR_IMMMASK_##INSN) >> ADDR_IMMSHIFT_##INSN)
 
+enum reg0i26_op {
+	b_op		= 0x14,
+	bl_op		= 0x15,
+};
+
 enum reg1i20_op {
 	lu12iw_op	= 0x0a,
 	lu32id_op	= 0x0b,
+	pcaddu12i_op	= 0x0e,
+	pcaddu18i_op	= 0x0f,
 };
 
 enum reg1i21_op {
@@ -28,10 +37,34 @@ enum reg1i21_op {
 	bnez_op		= 0x11,
 };
 
+enum reg2_op {
+	revb2h_op	= 0x0c,
+	revb4h_op	= 0x0d,
+	revb2w_op	= 0x0e,
+	revbd_op	= 0x0f,
+	revh2w_op	= 0x10,
+	revhd_op	= 0x11,
+};
+
+enum reg2i5_op {
+	slliw_op	= 0x81,
+	srliw_op	= 0x89,
+	sraiw_op	= 0x91,
+};
+
+enum reg2i6_op {
+	sllid_op	= 0x41,
+	srlid_op	= 0x45,
+	sraid_op	= 0x49,
+};
+
 enum reg2i12_op {
 	addiw_op	= 0x0a,
 	addid_op	= 0x0b,
 	lu52id_op	= 0x0c,
+	andi_op		= 0x0d,
+	ori_op		= 0x0e,
+	xori_op		= 0x0f,
 	ldb_op		= 0xa0,
 	ldh_op		= 0xa1,
 	ldw_op		= 0xa2,
@@ -40,6 +73,20 @@ enum reg2i12_op {
 	sth_op		= 0xa5,
 	stw_op		= 0xa6,
 	std_op		= 0xa7,
+	ldbu_op		= 0xa8,
+	ldhu_op		= 0xa9,
+	ldwu_op		= 0xaa,
+};
+
+enum reg2i14_op {
+	llw_op		= 0x20,
+	scw_op		= 0x21,
+	lld_op		= 0x22,
+	scd_op		= 0x23,
+	ldptrw_op	= 0x24,
+	stptrw_op	= 0x25,
+	ldptrd_op	= 0x26,
+	stptrd_op	= 0x27,
 };
 
 enum reg2i16_op {
@@ -52,6 +99,71 @@ enum reg2i16_op {
 	bgeu_op		= 0x1b,
 };
 
+enum reg2bstrd_op {
+	bstrinsd_op	= 0x2,
+	bstrpickd_op	= 0x3,
+};
+
+enum reg3_op {
+	addw_op		= 0x20,
+	addd_op		= 0x21,
+	subw_op		= 0x22,
+	subd_op		= 0x23,
+	nor_op		= 0x28,
+	and_op		= 0x29,
+	or_op		= 0x2a,
+	xor_op		= 0x2b,
+	orn_op		= 0x2c,
+	andn_op		= 0x2d,
+	sllw_op		= 0x2e,
+	srlw_op		= 0x2f,
+	sraw_op		= 0x30,
+	slld_op		= 0x31,
+	srld_op		= 0x32,
+	srad_op		= 0x33,
+	mulw_op		= 0x38,
+	mulhw_op	= 0x39,
+	mulhwu_op	= 0x3a,
+	muld_op		= 0x3b,
+	mulhd_op	= 0x3c,
+	mulhdu_op	= 0x3d,
+	divw_op		= 0x40,
+	modw_op		= 0x41,
+	divwu_op	= 0x42,
+	modwu_op	= 0x43,
+	divd_op		= 0x44,
+	modd_op		= 0x45,
+	divdu_op	= 0x46,
+	moddu_op	= 0x47,
+	ldxb_op		= 0x7000,
+	ldxh_op		= 0x7008,
+	ldxw_op		= 0x7010,
+	ldxd_op		= 0x7018,
+	stxb_op		= 0x7020,
+	stxh_op		= 0x7028,
+	stxw_op		= 0x7030,
+	stxd_op		= 0x7038,
+	ldxbu_op	= 0x7040,
+	ldxhu_op	= 0x7048,
+	ldxwu_op	= 0x7050,
+	amswapw_op	= 0x70c0,
+	amswapd_op	= 0x70c1,
+	amaddw_op	= 0x70c2,
+	amaddd_op	= 0x70c3,
+	amandw_op	= 0x70c4,
+	amandd_op	= 0x70c5,
+	amorw_op	= 0x70c6,
+	amord_op	= 0x70c7,
+	amxorw_op	= 0x70c8,
+	amxord_op	= 0x70c9,
+};
+
+enum reg3sa2_op {
+	alslw_op	= 0x02,
+	alslwu_op	= 0x03,
+	alsld_op	= 0x16,
+};
+
 struct reg0i26_format {
 	unsigned int immediate_h : 10;
 	unsigned int immediate_l : 16;
@@ -71,6 +183,26 @@ struct reg1i21_format {
 	unsigned int opcode : 6;
 };
 
+struct reg2_format {
+	unsigned int rd : 5;
+	unsigned int rj : 5;
+	unsigned int opcode : 22;
+};
+
+struct reg2i5_format {
+	unsigned int rd : 5;
+	unsigned int rj : 5;
+	unsigned int immediate : 5;
+	unsigned int opcode : 17;
+};
+
+struct reg2i6_format {
+	unsigned int rd : 5;
+	unsigned int rj : 5;
+	unsigned int immediate : 6;
+	unsigned int opcode : 16;
+};
+
 struct reg2i12_format {
 	unsigned int rd : 5;
 	unsigned int rj : 5;
@@ -78,6 +210,13 @@ struct reg2i12_format {
 	unsigned int opcode : 10;
 };
 
+struct reg2i14_format {
+	unsigned int rd : 5;
+	unsigned int rj : 5;
+	unsigned int immediate : 14;
+	unsigned int opcode : 8;
+};
+
 struct reg2i16_format {
 	unsigned int rd : 5;
 	unsigned int rj : 5;
@@ -85,13 +224,43 @@ struct reg2i16_format {
 	unsigned int opcode : 6;
 };
 
+struct reg2bstrd_format {
+	unsigned int rd : 5;
+	unsigned int rj : 5;
+	unsigned int lsbd : 6;
+	unsigned int msbd : 6;
+	unsigned int opcode : 10;
+};
+
+struct reg3_format {
+	unsigned int rd : 5;
+	unsigned int rj : 5;
+	unsigned int rk : 5;
+	unsigned int opcode : 17;
+};
+
+struct reg3sa2_format {
+	unsigned int rd : 5;
+	unsigned int rj : 5;
+	unsigned int rk : 5;
+	unsigned int immediate : 2;
+	unsigned int opcode : 15;
+};
+
 union loongarch_instruction {
 	unsigned int word;
-	struct reg0i26_format reg0i26_format;
-	struct reg1i20_format reg1i20_format;
-	struct reg1i21_format reg1i21_format;
-	struct reg2i12_format reg2i12_format;
-	struct reg2i16_format reg2i16_format;
+	struct reg0i26_format	reg0i26_format;
+	struct reg1i20_format	reg1i20_format;
+	struct reg1i21_format	reg1i21_format;
+	struct reg2_format	reg2_format;
+	struct reg2i5_format	reg2i5_format;
+	struct reg2i6_format	reg2i6_format;
+	struct reg2i12_format	reg2i12_format;
+	struct reg2i14_format	reg2i14_format;
+	struct reg2i16_format	reg2i16_format;
+	struct reg2bstrd_format	reg2bstrd_format;
+	struct reg3_format	reg3_format;
+	struct reg3sa2_format	reg3sa2_format;
 };
 
 #define LOONGARCH_INSN_SIZE	sizeof(union loongarch_instruction)
@@ -166,4 +335,235 @@ u32 larch_insn_gen_lu32id(enum loongarch_gpr rd, int imm);
 u32 larch_insn_gen_lu52id(enum loongarch_gpr rd, enum loongarch_gpr rj, int imm);
 u32 larch_insn_gen_jirl(enum loongarch_gpr rd, enum loongarch_gpr rj, unsigned long pc, unsigned long dest);
 
+static inline bool signed_imm_check(long val, unsigned int bit)
+{
+	return -(1L << (bit - 1)) <= val && val < (1L << (bit - 1));
+}
+
+static inline bool unsigned_imm_check(unsigned long val, unsigned int bit)
+{
+	return val < (1UL << bit);
+}
+
+#define DEF_EMIT_REG0I26_FORMAT(NAME, OP)				\
+static inline void emit_##NAME(union loongarch_instruction *insn,	\
+			       int offset)				\
+{									\
+	unsigned int immediate_l, immediate_h;				\
+									\
+	immediate_l = offset & 0xffff;					\
+	offset >>= 16;							\
+	immediate_h = offset & 0x3ff;					\
+									\
+	insn->reg0i26_format.opcode = OP;				\
+	insn->reg0i26_format.immediate_l = immediate_l;			\
+	insn->reg0i26_format.immediate_h = immediate_h;			\
+}
+
+DEF_EMIT_REG0I26_FORMAT(b, b_op)
+
+#define DEF_EMIT_REG1I20_FORMAT(NAME, OP)				\
+static inline void emit_##NAME(union loongarch_instruction *insn,	\
+			       enum loongarch_gpr rd, int imm)		\
+{									\
+	insn->reg1i20_format.opcode = OP;				\
+	insn->reg1i20_format.immediate = imm;				\
+	insn->reg1i20_format.rd = rd;					\
+}
+
+DEF_EMIT_REG1I20_FORMAT(lu12iw, lu12iw_op)
+DEF_EMIT_REG1I20_FORMAT(lu32id, lu32id_op)
+DEF_EMIT_REG1I20_FORMAT(pcaddu18i, pcaddu18i_op)
+
+#define DEF_EMIT_REG2_FORMAT(NAME, OP)					\
+static inline void emit_##NAME(union loongarch_instruction *insn,	\
+			       enum loongarch_gpr rd,			\
+			       enum loongarch_gpr rj)			\
+{									\
+	insn->reg2_format.opcode = OP;					\
+	insn->reg2_format.rd = rd;					\
+	insn->reg2_format.rj = rj;					\
+}
+
+DEF_EMIT_REG2_FORMAT(revb2h, revb2h_op)
+DEF_EMIT_REG2_FORMAT(revb2w, revb2w_op)
+DEF_EMIT_REG2_FORMAT(revbd, revbd_op)
+
+#define DEF_EMIT_REG2I5_FORMAT(NAME, OP)				\
+static inline void emit_##NAME(union loongarch_instruction *insn,	\
+			       enum loongarch_gpr rd,			\
+			       enum loongarch_gpr rj,			\
+			       int imm)					\
+{									\
+	insn->reg2i5_format.opcode = OP;				\
+	insn->reg2i5_format.immediate = imm;				\
+	insn->reg2i5_format.rd = rd;					\
+	insn->reg2i5_format.rj = rj;					\
+}
+
+DEF_EMIT_REG2I5_FORMAT(slliw, slliw_op)
+DEF_EMIT_REG2I5_FORMAT(srliw, srliw_op)
+DEF_EMIT_REG2I5_FORMAT(sraiw, sraiw_op)
+
+#define DEF_EMIT_REG2I6_FORMAT(NAME, OP)				\
+static inline void emit_##NAME(union loongarch_instruction *insn,	\
+			       enum loongarch_gpr rd,			\
+			       enum loongarch_gpr rj,			\
+			       int imm)					\
+{									\
+	insn->reg2i6_format.opcode = OP;				\
+	insn->reg2i6_format.immediate = imm;				\
+	insn->reg2i6_format.rd = rd;					\
+	insn->reg2i6_format.rj = rj;					\
+}
+
+DEF_EMIT_REG2I6_FORMAT(sllid, sllid_op)
+DEF_EMIT_REG2I6_FORMAT(srlid, srlid_op)
+DEF_EMIT_REG2I6_FORMAT(sraid, sraid_op)
+
+#define DEF_EMIT_REG2I12_FORMAT(NAME, OP)				\
+static inline void emit_##NAME(union loongarch_instruction *insn,	\
+			       enum loongarch_gpr rd,			\
+			       enum loongarch_gpr rj,			\
+			       int imm)					\
+{									\
+	insn->reg2i12_format.opcode = OP;				\
+	insn->reg2i12_format.immediate = imm;				\
+	insn->reg2i12_format.rd = rd;					\
+	insn->reg2i12_format.rj = rj;					\
+}
+
+DEF_EMIT_REG2I12_FORMAT(addiw, addiw_op)
+DEF_EMIT_REG2I12_FORMAT(addid, addid_op)
+DEF_EMIT_REG2I12_FORMAT(lu52id, lu52id_op)
+DEF_EMIT_REG2I12_FORMAT(andi, andi_op)
+DEF_EMIT_REG2I12_FORMAT(ori, ori_op)
+DEF_EMIT_REG2I12_FORMAT(xori, xori_op)
+DEF_EMIT_REG2I12_FORMAT(ldbu, ldbu_op)
+DEF_EMIT_REG2I12_FORMAT(ldhu, ldhu_op)
+DEF_EMIT_REG2I12_FORMAT(ldwu, ldwu_op)
+DEF_EMIT_REG2I12_FORMAT(ldd, ldd_op)
+DEF_EMIT_REG2I12_FORMAT(stb, stb_op)
+DEF_EMIT_REG2I12_FORMAT(sth, sth_op)
+DEF_EMIT_REG2I12_FORMAT(stw, stw_op)
+DEF_EMIT_REG2I12_FORMAT(std, std_op)
+
+#define DEF_EMIT_REG2I14_FORMAT(NAME, OP)				\
+static inline void emit_##NAME(union loongarch_instruction *insn,	\
+			       enum loongarch_gpr rd,			\
+			       enum loongarch_gpr rj,			\
+			       int imm)					\
+{									\
+	insn->reg2i14_format.opcode = OP;				\
+	insn->reg2i14_format.immediate = imm;				\
+	insn->reg2i14_format.rd = rd;					\
+	insn->reg2i14_format.rj = rj;					\
+}
+
+DEF_EMIT_REG2I14_FORMAT(llw, llw_op)
+DEF_EMIT_REG2I14_FORMAT(scw, scw_op)
+DEF_EMIT_REG2I14_FORMAT(lld, lld_op)
+DEF_EMIT_REG2I14_FORMAT(scd, scd_op)
+DEF_EMIT_REG2I14_FORMAT(ldptrw, ldptrw_op)
+DEF_EMIT_REG2I14_FORMAT(stptrw, stptrw_op)
+DEF_EMIT_REG2I14_FORMAT(ldptrd, ldptrd_op)
+DEF_EMIT_REG2I14_FORMAT(stptrd, stptrd_op)
+
+#define DEF_EMIT_REG2I16_FORMAT(NAME, OP)				\
+static inline void emit_##NAME(union loongarch_instruction *insn,	\
+			       enum loongarch_gpr rj,			\
+			       enum loongarch_gpr rd,			\
+			       int offset)				\
+{									\
+	insn->reg2i16_format.opcode = OP;				\
+	insn->reg2i16_format.immediate = offset;			\
+	insn->reg2i16_format.rj = rj;					\
+	insn->reg2i16_format.rd = rd;					\
+}
+
+DEF_EMIT_REG2I16_FORMAT(beq, beq_op)
+DEF_EMIT_REG2I16_FORMAT(bne, bne_op)
+DEF_EMIT_REG2I16_FORMAT(blt, blt_op)
+DEF_EMIT_REG2I16_FORMAT(bge, bge_op)
+DEF_EMIT_REG2I16_FORMAT(bltu, bltu_op)
+DEF_EMIT_REG2I16_FORMAT(bgeu, bgeu_op)
+DEF_EMIT_REG2I16_FORMAT(jirl, jirl_op)
+
+#define DEF_EMIT_REG2BSTRD_FORMAT(NAME, OP)				\
+static inline void emit_##NAME(union loongarch_instruction *insn,	\
+			       enum loongarch_gpr rd,			\
+			       enum loongarch_gpr rj,			\
+			       int msbd,				\
+			       int lsbd)				\
+{									\
+	insn->reg2bstrd_format.opcode = OP;				\
+	insn->reg2bstrd_format.msbd = msbd;				\
+	insn->reg2bstrd_format.lsbd = lsbd;				\
+	insn->reg2bstrd_format.rj = rj;					\
+	insn->reg2bstrd_format.rd = rd;					\
+}
+
+DEF_EMIT_REG2BSTRD_FORMAT(bstrpickd, bstrpickd_op)
+
+#define DEF_EMIT_REG3_FORMAT(NAME, OP)					\
+static inline void emit_##NAME(union loongarch_instruction *insn,	\
+			       enum loongarch_gpr rd,			\
+			       enum loongarch_gpr rj,			\
+			       enum loongarch_gpr rk)			\
+{									\
+	insn->reg3_format.opcode = OP;					\
+	insn->reg3_format.rd = rd;					\
+	insn->reg3_format.rj = rj;					\
+	insn->reg3_format.rk = rk;					\
+}
+
+DEF_EMIT_REG3_FORMAT(addd, addd_op)
+DEF_EMIT_REG3_FORMAT(subd, subd_op)
+DEF_EMIT_REG3_FORMAT(muld, muld_op)
+DEF_EMIT_REG3_FORMAT(divdu, divdu_op)
+DEF_EMIT_REG3_FORMAT(moddu, moddu_op)
+DEF_EMIT_REG3_FORMAT(and, and_op)
+DEF_EMIT_REG3_FORMAT(or, or_op)
+DEF_EMIT_REG3_FORMAT(xor, xor_op)
+DEF_EMIT_REG3_FORMAT(sllw, sllw_op)
+DEF_EMIT_REG3_FORMAT(slld, slld_op)
+DEF_EMIT_REG3_FORMAT(srlw, srlw_op)
+DEF_EMIT_REG3_FORMAT(srld, srld_op)
+DEF_EMIT_REG3_FORMAT(sraw, sraw_op)
+DEF_EMIT_REG3_FORMAT(srad, srad_op)
+DEF_EMIT_REG3_FORMAT(ldxbu, ldxbu_op)
+DEF_EMIT_REG3_FORMAT(ldxhu, ldxhu_op)
+DEF_EMIT_REG3_FORMAT(ldxwu, ldxwu_op)
+DEF_EMIT_REG3_FORMAT(ldxd, ldxd_op)
+DEF_EMIT_REG3_FORMAT(stxb, stxb_op)
+DEF_EMIT_REG3_FORMAT(stxh, stxh_op)
+DEF_EMIT_REG3_FORMAT(stxw, stxw_op)
+DEF_EMIT_REG3_FORMAT(stxd, stxd_op)
+DEF_EMIT_REG3_FORMAT(amaddw, amaddw_op)
+DEF_EMIT_REG3_FORMAT(amaddd, amaddd_op)
+DEF_EMIT_REG3_FORMAT(amandw, amandw_op)
+DEF_EMIT_REG3_FORMAT(amandd, amandd_op)
+DEF_EMIT_REG3_FORMAT(amorw, amorw_op)
+DEF_EMIT_REG3_FORMAT(amord, amord_op)
+DEF_EMIT_REG3_FORMAT(amxorw, amxorw_op)
+DEF_EMIT_REG3_FORMAT(amxord, amxord_op)
+DEF_EMIT_REG3_FORMAT(amswapw, amswapw_op)
+DEF_EMIT_REG3_FORMAT(amswapd, amswapd_op)
+
+#define DEF_EMIT_REG3SA2_FORMAT(NAME, OP)				\
+static inline void emit_##NAME(union loongarch_instruction *insn,	\
+			       enum loongarch_gpr rd,			\
+			       enum loongarch_gpr rj,			\
+			       enum loongarch_gpr rk,			\
+			       int imm)					\
+{									\
+	insn->reg3sa2_format.opcode = OP;				\
+	insn->reg3sa2_format.immediate = imm;				\
+	insn->reg3sa2_format.rd = rd;					\
+	insn->reg3sa2_format.rj = rj;					\
+	insn->reg3sa2_format.rk = rk;					\
+}
+
+DEF_EMIT_REG3SA2_FORMAT(alsld, alsld_op)
+
 #endif /* _ASM_INST_H */

arch/loongarch/include/asm/io.h

@@ -27,71 +27,38 @@ extern void __init early_iounmap(void __iomem *addr, unsigned long size);
 #define early_memremap early_ioremap
 #define early_memunmap early_iounmap
 
+#ifdef CONFIG_ARCH_IOREMAP
+
 static inline void __iomem *ioremap_prot(phys_addr_t offset, unsigned long size,
 					 unsigned long prot_val)
 {
-	if (prot_val == _CACHE_CC)
+	if (prot_val & _CACHE_CC)
 		return (void __iomem *)(unsigned long)(CACHE_BASE + offset);
 	else
 		return (void __iomem *)(unsigned long)(UNCACHE_BASE + offset);
 }
 
-/*
- * ioremap -   map bus memory into CPU space
- * @offset:    bus address of the memory
- * @size:      size of the resource to map
- *
- * ioremap performs a platform specific sequence of operations to
- * make bus memory CPU accessible via the readb/readw/readl/writeb/
- * writew/writel functions and the other mmio helpers. The returned
- * address is not guaranteed to be usable directly as a virtual
- * address.
- */
-#define ioremap(offset, size)					\
-	ioremap_prot((offset), (size), _CACHE_SUC)
+#define ioremap(offset, size)		\
+	ioremap_prot((offset), (size), pgprot_val(PAGE_KERNEL_SUC))
 
-/*
- * ioremap_wc - map bus memory into CPU space
- * @offset:     bus address of the memory
- * @size:       size of the resource to map
- *
- * ioremap_wc performs a platform specific sequence of operations to
- * make bus memory CPU accessible via the readb/readw/readl/writeb/
- * writew/writel functions and the other mmio helpers. The returned
- * address is not guaranteed to be usable directly as a virtual
- * address.
- *
- * This version of ioremap ensures that the memory is marked uncachable
- * but accelerated by means of write-combining feature. It is specifically
- * useful for PCIe prefetchable windows, which may vastly improve a
- * communications performance. If it was determined on boot stage, what
- * CPU CCA doesn't support WUC, the method shall fall-back to the
- * _CACHE_SUC option (see cpu_probe() method).
- */
-#define ioremap_wc(offset, size)				\
-	ioremap_prot((offset), (size), _CACHE_WUC)
+#define iounmap(addr) 			((void)(addr))
+
+#endif
 
 /*
- * ioremap_cache -  map bus memory into CPU space
- * @offset:	    bus address of the memory
- * @size:	    size of the resource to map
+ * On LoongArch, ioremap() has two variants, ioremap_wc() and ioremap_cache().
+ * They map bus memory into CPU space, the mapped memory is marked uncachable
+ * (_CACHE_SUC), uncachable but accelerated by write-combine (_CACHE_WUC) and
+ * cachable (_CACHE_CC) respectively for CPU access.
  *
- * ioremap_cache performs a platform specific sequence of operations to
- * make bus memory CPU accessible via the readb/readw/readl/writeb/
- * writew/writel functions and the other mmio helpers. The returned
- * address is not guaranteed to be usable directly as a virtual
- * address.
- *
- * This version of ioremap ensures that the memory is marked cachable by
- * the CPU.  Also enables full write-combining.	 Useful for some
- * memory-like regions on I/O busses.
+ * @offset:    bus address of the memory
+ * @size:      size of the resource to map
  */
-#define ioremap_cache(offset, size)				\
-	ioremap_prot((offset), (size), _CACHE_CC)
+#define ioremap_wc(offset, size)	\
+	ioremap_prot((offset), (size), pgprot_val(PAGE_KERNEL_WUC))
 
-static inline void iounmap(const volatile void __iomem *addr)
-{
-}
+#define ioremap_cache(offset, size)	\
+	ioremap_prot((offset), (size), pgprot_val(PAGE_KERNEL))
 
 #define mmiowb() asm volatile ("dbar 0" ::: "memory")
 
@@ -107,4 +74,8 @@ extern void __memcpy_fromio(void *to, const volatile void __iomem *from, size_t
 
 #include <asm-generic/io.h>
 
+#define ARCH_HAS_VALID_PHYS_ADDR_RANGE
+extern int valid_phys_addr_range(phys_addr_t addr, size_t size);
+extern int valid_mmap_phys_addr_range(unsigned long pfn, size_t size);
+
 #endif /* _ASM_IO_H */

arch/loongarch/include/asm/kexec.h

+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * kexec.h for kexec
+ *
+ * Copyright (C) 2022 Loongson Technology Corporation Limited
+ */
+
+#ifndef _ASM_KEXEC_H
+#define _ASM_KEXEC_H
+
+#include <asm/stacktrace.h>
+#include <asm/page.h>
+
+/* Maximum physical address we can use pages from */
+#define KEXEC_SOURCE_MEMORY_LIMIT (-1UL)
+/* Maximum address we can reach in physical address mode */
+#define KEXEC_DESTINATION_MEMORY_LIMIT (-1UL)
+ /* Maximum address we can use for the control code buffer */
+#define KEXEC_CONTROL_MEMORY_LIMIT (-1UL)
+
+/* Reserve a page for the control code buffer */
+#define KEXEC_CONTROL_PAGE_SIZE PAGE_SIZE
+
+/* The native architecture */
+#define KEXEC_ARCH KEXEC_ARCH_LOONGARCH
+
+static inline void crash_setup_regs(struct pt_regs *newregs,
+				    struct pt_regs *oldregs)
+{
+	if (oldregs)
+		memcpy(newregs, oldregs, sizeof(*newregs));
+	else
+		prepare_frametrace(newregs);
+}
+
+#define ARCH_HAS_KIMAGE_ARCH
+
+struct kimage_arch {
+	unsigned long efi_boot;
+	unsigned long cmdline_ptr;
+	unsigned long systable_ptr;
+};
+
+typedef void (*do_kexec_t)(unsigned long efi_boot,
+			   unsigned long cmdline_ptr,
+			   unsigned long systable_ptr,
+			   unsigned long start_addr,
+			   unsigned long first_ind_entry);
+
+struct kimage;
+extern const unsigned char relocate_new_kernel[];
+extern const size_t relocate_new_kernel_size;
+extern void kexec_reboot(void);
+
+#ifdef CONFIG_SMP
+extern atomic_t kexec_ready_to_reboot;
+extern const unsigned char kexec_smp_wait[];
+#endif
+
+#endif /* !_ASM_KEXEC_H */

arch/loongarch/include/asm/loongarch.h

@@ -187,36 +187,15 @@ static inline u32 read_cpucfg(u32 reg)
 #define  CPUCFG16_L3_DINCL		BIT(16)
 
 #define LOONGARCH_CPUCFG17		0x11
-#define  CPUCFG17_L1I_WAYS_M		GENMASK(15, 0)
-#define  CPUCFG17_L1I_SETS_M		GENMASK(23, 16)
-#define  CPUCFG17_L1I_SIZE_M		GENMASK(30, 24)
-#define  CPUCFG17_L1I_WAYS		0
-#define  CPUCFG17_L1I_SETS		16
-#define  CPUCFG17_L1I_SIZE		24
-
 #define LOONGARCH_CPUCFG18		0x12
-#define  CPUCFG18_L1D_WAYS_M		GENMASK(15, 0)
-#define  CPUCFG18_L1D_SETS_M		GENMASK(23, 16)
-#define  CPUCFG18_L1D_SIZE_M		GENMASK(30, 24)
-#define  CPUCFG18_L1D_WAYS		0
-#define  CPUCFG18_L1D_SETS		16
-#define  CPUCFG18_L1D_SIZE		24
-
 #define LOONGARCH_CPUCFG19		0x13
-#define  CPUCFG19_L2_WAYS_M		GENMASK(15, 0)
-#define  CPUCFG19_L2_SETS_M		GENMASK(23, 16)
-#define  CPUCFG19_L2_SIZE_M		GENMASK(30, 24)
-#define  CPUCFG19_L2_WAYS		0
-#define  CPUCFG19_L2_SETS		16
-#define  CPUCFG19_L2_SIZE		24
-
 #define LOONGARCH_CPUCFG20		0x14
-#define  CPUCFG20_L3_WAYS_M		GENMASK(15, 0)
-#define  CPUCFG20_L3_SETS_M		GENMASK(23, 16)
-#define  CPUCFG20_L3_SIZE_M		GENMASK(30, 24)
-#define  CPUCFG20_L3_WAYS		0
-#define  CPUCFG20_L3_SETS		16
-#define  CPUCFG20_L3_SIZE		24
+#define  CPUCFG_CACHE_WAYS_M		GENMASK(15, 0)
+#define  CPUCFG_CACHE_SETS_M		GENMASK(23, 16)
+#define  CPUCFG_CACHE_LSIZE_M		GENMASK(30, 24)
+#define  CPUCFG_CACHE_WAYS	 	0
+#define  CPUCFG_CACHE_SETS		16
+#define  CPUCFG_CACHE_LSIZE		24
 
 #define LOONGARCH_CPUCFG48		0x30
 #define  CPUCFG48_MCSR_LCK		BIT(0)

arch/loongarch/include/asm/module.h

@@ -17,10 +17,15 @@ struct mod_section {
 };
 
 struct mod_arch_specific {
+	struct mod_section got;
 	struct mod_section plt;
 	struct mod_section plt_idx;
 };
 
+struct got_entry {
+	Elf_Addr symbol_addr;
+};
+
 struct plt_entry {
 	u32 inst_lu12iw;
 	u32 inst_lu32id;
@@ -29,10 +34,16 @@ struct plt_entry {
 };
 
 struct plt_idx_entry {
-	unsigned long symbol_addr;
+	Elf_Addr symbol_addr;
 };
 
-Elf_Addr module_emit_plt_entry(struct module *mod, unsigned long val);
+Elf_Addr module_emit_got_entry(struct module *mod, Elf_Addr val);
+Elf_Addr module_emit_plt_entry(struct module *mod, Elf_Addr val);
+
+static inline struct got_entry emit_got_entry(Elf_Addr val)
+{
+	return (struct got_entry) { val };
+}
 
 static inline struct plt_entry emit_plt_entry(unsigned long val)
 {
@@ -77,4 +88,16 @@ static inline struct plt_entry *get_plt_entry(unsigned long val,
 	return plt + plt_idx;
 }
 
+static inline struct got_entry *get_got_entry(Elf_Addr val,
+					      const struct mod_section *sec)
+{
+	struct got_entry *got = (struct got_entry *)sec->shdr->sh_addr;
+	int i;
+
+	for (i = 0; i < sec->num_entries; i++)
+		if (got[i].symbol_addr == val)
+			return &got[i];
+	return NULL;
+}
+
 #endif /* _ASM_MODULE_H */

arch/loongarch/include/asm/module.lds.h

@@ -2,6 +2,7 @@
 /* Copyright (C) 2020-2022 Loongson Technology Corporation Limited */
 SECTIONS {
 	. = ALIGN(4);
+	.got : { BYTE(0) }
 	.plt : { BYTE(0) }
 	.plt.idx : { BYTE(0) }
 }

arch/loongarch/include/asm/percpu.h

@@ -8,6 +8,15 @@
 #include <asm/cmpxchg.h>
 #include <asm/loongarch.h>
 
+/*
+ * The "address" (in fact, offset from $r21) of a per-CPU variable is close to
+ * the loading address of main kernel image, but far from where the modules are
+ * loaded. Tell the compiler this fact when using explicit relocs.
+ */
+#if defined(MODULE) && defined(CONFIG_AS_HAS_EXPLICIT_RELOCS)
+#define PER_CPU_ATTRIBUTES    __attribute__((model("extreme")))
+#endif
+
 /* Use r21 for fast access */
 register unsigned long __my_cpu_offset __asm__("$r21");
 

arch/loongarch/include/asm/perf_event.h

@@ -6,5 +6,7 @@
 
 #ifndef __LOONGARCH_PERF_EVENT_H__
 #define __LOONGARCH_PERF_EVENT_H__
-/* Nothing to show here; the file is required by linux/perf_event.h. */
+
+#define perf_arch_bpf_user_pt_regs(regs) (struct user_pt_regs *)regs
+
 #endif /* __LOONGARCH_PERF_EVENT_H__ */

arch/loongarch/include/asm/pgtable-bits.h

@@ -83,8 +83,11 @@
 				 _PAGE_GLOBAL | _PAGE_KERN |  _CACHE_SUC)
 #define PAGE_KERNEL_WUC __pgprot(_PAGE_PRESENT | __READABLE | __WRITEABLE | \
 				 _PAGE_GLOBAL | _PAGE_KERN |  _CACHE_WUC)
+
 #ifndef __ASSEMBLY__
 
+#define _PAGE_IOREMAP		pgprot_val(PAGE_KERNEL_SUC)
+
 #define pgprot_noncached pgprot_noncached
 
 static inline pgprot_t pgprot_noncached(pgprot_t _prot)

arch/loongarch/include/asm/setup.h

@@ -13,7 +13,9 @@
 
 extern unsigned long eentry;
 extern unsigned long tlbrentry;
+extern void tlb_init(int cpu);
 extern void cpu_cache_init(void);
+extern void cache_error_setup(void);
 extern void per_cpu_trap_init(int cpu);
 extern void set_handler(unsigned long offset, void *addr, unsigned long len);
 extern void set_merr_handler(unsigned long offset, void *addr, unsigned long len);

arch/loongarch/include/asm/spinlock.h

+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2020-2022 Loongson Technology Corporation Limited
+ */
+#ifndef _ASM_SPINLOCK_H
+#define _ASM_SPINLOCK_H
+
+#include <asm/processor.h>
+#include <asm/qspinlock.h>
+#include <asm/qrwlock.h>
+
+#endif /* _ASM_SPINLOCK_H */

arch/loongarch/include/asm/spinlock_types.h

+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2020-2022 Loongson Technology Corporation Limited
+ */
+#ifndef _ASM_SPINLOCK_TYPES_H
+#define _ASM_SPINLOCK_TYPES_H
+
+#include <asm-generic/qspinlock_types.h>
+#include <asm-generic/qrwlock_types.h>
+
+#endif

arch/loongarch/include/uapi/asm/bpf_perf_event.h

+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI__ASM_BPF_PERF_EVENT_H__
+#define _UAPI__ASM_BPF_PERF_EVENT_H__
+
+#include <linux/ptrace.h>
+
+typedef struct user_pt_regs bpf_user_pt_regs_t;
+
+#endif /* _UAPI__ASM_BPF_PERF_EVENT_H__ */

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 */

arch/loongarch/kernel/Makefile

@@ -23,7 +23,14 @@ obj-$(CONFIG_SMP)		+= smp.o
 
 obj-$(CONFIG_NUMA)		+= numa.o
 
+obj-$(CONFIG_MAGIC_SYSRQ)	+= sysrq.o
+
+obj-$(CONFIG_KEXEC)		+= machine_kexec.o relocate_kernel.o
+obj-$(CONFIG_CRASH_DUMP)	+= crash_dump.o
+
 obj-$(CONFIG_UNWINDER_GUESS)	+= unwind_guess.o
 obj-$(CONFIG_UNWINDER_PROLOGUE) += unwind_prologue.o
 
+obj-$(CONFIG_PERF_EVENTS)	+= perf_event.o perf_regs.o
+
 CPPFLAGS_vmlinux.lds		:= $(KBUILD_CFLAGS)

arch/loongarch/kernel/cacheinfo.c

@@ -5,73 +5,34 @@
  * Copyright (C) 2020-2022 Loongson Technology Corporation Limited
  */
 #include <linux/cacheinfo.h>
+#include <linux/topology.h>
 #include <asm/bootinfo.h>
 #include <asm/cpu-info.h>
 
-/* Populates leaf and increments to next leaf */
-#define populate_cache(cache, leaf, c_level, c_type)		\
-do {								\
-	leaf->type = c_type;					\
-	leaf->level = c_level;					\
-	leaf->coherency_line_size = c->cache.linesz;		\
-	leaf->number_of_sets = c->cache.sets;			\
-	leaf->ways_of_associativity = c->cache.ways;		\
-	leaf->size = c->cache.linesz * c->cache.sets *		\
-		c->cache.ways;					\
-	if (leaf->level > 2)					\
-		leaf->size *= nodes_per_package;		\
-	leaf++;							\
-} while (0)
-
 int init_cache_level(unsigned int cpu)
 {
-	struct cpuinfo_loongarch *c = &current_cpu_data;
+	int cache_present = current_cpu_data.cache_leaves_present;
 	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
-	int levels = 0, leaves = 0;
-
-	/*
-	 * If Dcache is not set, we assume the cache structures
-	 * are not properly initialized.
-	 */
-	if (c->dcache.waysize)
-		levels += 1;
-	else
-		return -ENOENT;
-
-
-	leaves += (c->icache.waysize) ? 2 : 1;
-
-	if (c->vcache.waysize) {
-		levels++;
-		leaves++;
-	}
 
-	if (c->scache.waysize) {
-		levels++;
-		leaves++;
-	}
+	this_cpu_ci->num_levels =
+		current_cpu_data.cache_leaves[cache_present - 1].level;
+	this_cpu_ci->num_leaves = cache_present;
 
-	if (c->tcache.waysize) {
-		levels++;
-		leaves++;
-	}
-
-	this_cpu_ci->num_levels = levels;
-	this_cpu_ci->num_leaves = leaves;
 	return 0;
 }
 
 static inline bool cache_leaves_are_shared(struct cacheinfo *this_leaf,
 					   struct cacheinfo *sib_leaf)
 {
-	return !((this_leaf->level == 1) || (this_leaf->level == 2));
+	return (!(*(unsigned char *)(this_leaf->priv) & CACHE_PRIVATE)
+		&& !(*(unsigned char *)(sib_leaf->priv) & CACHE_PRIVATE));
 }
 
 static void cache_cpumap_setup(unsigned int cpu)
 {
-	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
-	struct cacheinfo *this_leaf, *sib_leaf;
 	unsigned int index;
+	struct cacheinfo *this_leaf, *sib_leaf;
+	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
 
 	for (index = 0; index < this_cpu_ci->num_leaves; index++) {
 		unsigned int i;
@@ -85,8 +46,10 @@ static void cache_cpumap_setup(unsigned int cpu)
 		for_each_online_cpu(i) {
 			struct cpu_cacheinfo *sib_cpu_ci = get_cpu_cacheinfo(i);
 
-			if (i == cpu || !sib_cpu_ci->info_list)
-				continue;/* skip if itself or no cacheinfo */
+			if (i == cpu || !sib_cpu_ci->info_list ||
+				(cpu_to_node(i) != cpu_to_node(cpu)))
+				continue;
+
 			sib_leaf = sib_cpu_ci->info_list + index;
 			if (cache_leaves_are_shared(this_leaf, sib_leaf)) {
 				cpumask_set_cpu(cpu, &sib_leaf->shared_cpu_map);
@@ -98,31 +61,24 @@ static void cache_cpumap_setup(unsigned int cpu)
 
 int populate_cache_leaves(unsigned int cpu)
 {
-	int level = 1, nodes_per_package = 1;
-	struct cpuinfo_loongarch *c = &current_cpu_data;
+	int i, cache_present = current_cpu_data.cache_leaves_present;
 	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
 	struct cacheinfo *this_leaf = this_cpu_ci->info_list;
-
-	if (loongson_sysconf.nr_nodes > 1)
-		nodes_per_package = loongson_sysconf.cores_per_package
-					/ loongson_sysconf.cores_per_node;
-
-	if (c->icache.waysize) {
-		populate_cache(dcache, this_leaf, level, CACHE_TYPE_DATA);
-		populate_cache(icache, this_leaf, level++, CACHE_TYPE_INST);
-	} else {
-		populate_cache(dcache, this_leaf, level++, CACHE_TYPE_UNIFIED);
+	struct cache_desc *cd, *cdesc = current_cpu_data.cache_leaves;
+
+	for (i = 0; i < cache_present; i++) {
+		cd = cdesc + i;
+
+		this_leaf->type = cd->type;
+		this_leaf->level = cd->level;
+		this_leaf->coherency_line_size = cd->linesz;
+		this_leaf->number_of_sets = cd->sets;
+		this_leaf->ways_of_associativity = cd->ways;
+		this_leaf->size = cd->linesz * cd->sets * cd->ways;
+		this_leaf->priv = &cd->flags;
+		this_leaf++;
 	}
 
-	if (c->vcache.waysize)
-		populate_cache(vcache, this_leaf, level++, CACHE_TYPE_UNIFIED);
-
-	if (c->scache.waysize)
-		populate_cache(scache, this_leaf, level++, CACHE_TYPE_UNIFIED);
-
-	if (c->tcache.waysize)
-		populate_cache(tcache, this_leaf, level++, CACHE_TYPE_UNIFIED);
-
 	cache_cpumap_setup(cpu);
 	this_cpu_ci->cpu_map_populated = true;
 

arch/loongarch/kernel/cpu-probe.c

@@ -187,7 +187,9 @@ static inline void cpu_probe_loongson(struct cpuinfo_loongarch *c, unsigned int
 	uint64_t *vendor = (void *)(&cpu_full_name[VENDOR_OFFSET]);
 	uint64_t *cpuname = (void *)(&cpu_full_name[CPUNAME_OFFSET]);
 
-	__cpu_full_name[cpu] = cpu_full_name;
+	if (!__cpu_full_name[cpu])
+		__cpu_full_name[cpu] = cpu_full_name;
+
 	*vendor = iocsr_read64(LOONGARCH_IOCSR_VENDOR);
 	*cpuname = iocsr_read64(LOONGARCH_IOCSR_CPUNAME);
 

arch/loongarch/kernel/crash_dump.c

+// SPDX-License-Identifier: GPL-2.0
+#include <linux/crash_dump.h>
+#include <linux/io.h>
+#include <linux/uio.h>
+
+ssize_t copy_oldmem_page(struct iov_iter *iter, unsigned long pfn,
+			 size_t csize, unsigned long offset)
+{
+	void *vaddr;
+
+	if (!csize)
+		return 0;
+
+	vaddr = memremap(__pfn_to_phys(pfn), PAGE_SIZE, MEMREMAP_WB);
+	if (!vaddr)
+		return -ENOMEM;
+
+	csize = copy_to_iter(vaddr + offset, csize, iter);
+
+	memunmap(vaddr);
+
+	return csize;
+}

arch/loongarch/kernel/head.S

@@ -8,6 +8,7 @@
 #include <asm/addrspace.h>
 #include <asm/asm.h>
 #include <asm/asmmacro.h>
+#include <asm/bug.h>
 #include <asm/regdef.h>
 #include <asm/loongarch.h>
 #include <asm/stackframe.h>
@@ -20,7 +21,11 @@
 
 _head:
 	.word	MZ_MAGIC		/* "MZ", MS-DOS header */
-	.org	0x3c			/* 0x04 ~ 0x3b reserved */
+	.org	0x8
+	.dword	kernel_entry		/* Kernel entry point */
+	.dword	_end - _text		/* Kernel image effective size */
+	.quad	0			/* Kernel image load offset from start of RAM */
+	.org	0x3c			/* 0x20 ~ 0x3b reserved */
 	.long	pe_header - _head	/* Offset to the PE header */
 
 pe_header:
@@ -57,19 +62,19 @@ SYM_CODE_START(kernel_entry)			# kernel entry point
 	li.w		t0, 0x00		# FPE=0, SXE=0, ASXE=0, BTE=0
 	csrwr		t0, LOONGARCH_CSR_EUEN
 
-	la		t0, __bss_start		# clear .bss
+	la.pcrel	t0, __bss_start		# clear .bss
 	st.d		zero, t0, 0
-	la		t1, __bss_stop - LONGSIZE
+	la.pcrel	t1, __bss_stop - LONGSIZE
 1:
 	addi.d		t0, t0, LONGSIZE
 	st.d		zero, t0, 0
 	bne		t0, t1, 1b
 
-	la		t0, fw_arg0
+	la.pcrel	t0, fw_arg0
 	st.d		a0, t0, 0		# firmware arguments
-	la		t0, fw_arg1
+	la.pcrel	t0, fw_arg1
 	st.d		a1, t0, 0
-	la		t0, fw_arg2
+	la.pcrel	t0, fw_arg2
 	st.d		a2, t0, 0
 
 	/* KSave3 used for percpu base, initialized as 0 */
@@ -77,7 +82,7 @@ SYM_CODE_START(kernel_entry)			# kernel entry point
 	/* GPR21 used for percpu base (runtime), initialized as 0 */
 	move		u0, zero
 
-	la		tp, init_thread_union
+	la.pcrel	tp, init_thread_union
 	/* Set the SP after an empty pt_regs.  */
 	PTR_LI		sp, (_THREAD_SIZE - 32 - PT_SIZE)
 	PTR_ADD		sp, sp, tp
@@ -85,6 +90,7 @@ SYM_CODE_START(kernel_entry)			# kernel entry point
 	PTR_ADDI	sp, sp, -4 * SZREG	# init stack pointer
 
 	bl		start_kernel
+	ASM_BUG()
 
 SYM_CODE_END(kernel_entry)
 
@@ -116,6 +122,8 @@ SYM_CODE_START(smpboot_entry)
 	ld.d		tp, t0, CPU_BOOT_TINFO
 
 	bl		start_secondary
+	ASM_BUG()
+
 SYM_CODE_END(smpboot_entry)
 
 #endif /* CONFIG_SMP */

arch/loongarch/kernel/machine_kexec.c

+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * machine_kexec.c for kexec
+ *
+ * Copyright (C) 2022 Loongson Technology Corporation Limited
+ */
+#include <linux/compiler.h>
+#include <linux/cpu.h>
+#include <linux/kexec.h>
+#include <linux/crash_dump.h>
+#include <linux/delay.h>
+#include <linux/irq.h>
+#include <linux/libfdt.h>
+#include <linux/mm.h>
+#include <linux/of_fdt.h>
+#include <linux/reboot.h>
+#include <linux/sched.h>
+#include <linux/sched/task_stack.h>
+
+#include <asm/bootinfo.h>
+#include <asm/cacheflush.h>
+#include <asm/page.h>
+
+/* 0x100000 ~ 0x200000 is safe */
+#define KEXEC_CONTROL_CODE	TO_CACHE(0x100000UL)
+#define KEXEC_CMDLINE_ADDR	TO_CACHE(0x108000UL)
+
+static unsigned long reboot_code_buffer;
+static cpumask_t cpus_in_crash = CPU_MASK_NONE;
+
+#ifdef CONFIG_SMP
+static void (*relocated_kexec_smp_wait)(void *);
+atomic_t kexec_ready_to_reboot = ATOMIC_INIT(0);
+#endif
+
+static unsigned long efi_boot;
+static unsigned long cmdline_ptr;
+static unsigned long systable_ptr;
+static unsigned long start_addr;
+static unsigned long first_ind_entry;
+
+static void kexec_image_info(const struct kimage *kimage)
+{
+	unsigned long i;
+
+	pr_debug("kexec kimage info:\n");
+	pr_debug("\ttype:        %d\n", kimage->type);
+	pr_debug("\tstart:       %lx\n", kimage->start);
+	pr_debug("\thead:        %lx\n", kimage->head);
+	pr_debug("\tnr_segments: %lu\n", kimage->nr_segments);
+
+	for (i = 0; i < kimage->nr_segments; i++) {
+		pr_debug("\t    segment[%lu]: %016lx - %016lx", i,
+			kimage->segment[i].mem,
+			kimage->segment[i].mem + kimage->segment[i].memsz);
+		pr_debug("\t\t0x%lx bytes, %lu pages\n",
+			(unsigned long)kimage->segment[i].memsz,
+			(unsigned long)kimage->segment[i].memsz /  PAGE_SIZE);
+	}
+}
+
+int machine_kexec_prepare(struct kimage *kimage)
+{
+	int i;
+	char *bootloader = "kexec";
+	void *cmdline_ptr = (void *)KEXEC_CMDLINE_ADDR;
+
+	kexec_image_info(kimage);
+
+	kimage->arch.efi_boot = fw_arg0;
+	kimage->arch.systable_ptr = fw_arg2;
+
+	/* Find the command line */
+	for (i = 0; i < kimage->nr_segments; i++) {
+		if (!strncmp(bootloader, (char __user *)kimage->segment[i].buf, strlen(bootloader))) {
+			if (!copy_from_user(cmdline_ptr, kimage->segment[i].buf, COMMAND_LINE_SIZE))
+				kimage->arch.cmdline_ptr = (unsigned long)cmdline_ptr;
+			break;
+		}
+	}
+
+	if (!kimage->arch.cmdline_ptr) {
+		pr_err("Command line not included in the provided image\n");
+		return -EINVAL;
+	}
+
+	/* kexec/kdump need a safe page to save reboot_code_buffer */
+	kimage->control_code_page = virt_to_page((void *)KEXEC_CONTROL_CODE);
+
+	reboot_code_buffer = (unsigned long)page_address(kimage->control_code_page);
+	memcpy((void *)reboot_code_buffer, relocate_new_kernel, relocate_new_kernel_size);
+
+#ifdef CONFIG_SMP
+	/* All secondary cpus now may jump to kexec_smp_wait cycle */
+	relocated_kexec_smp_wait = reboot_code_buffer + (void *)(kexec_smp_wait - relocate_new_kernel);
+#endif
+
+	return 0;
+}
+
+void machine_kexec_cleanup(struct kimage *kimage)
+{
+}
+
+void kexec_reboot(void)
+{
+	do_kexec_t do_kexec = NULL;
+
+	/*
+	 * We know we were online, and there will be no incoming IPIs at
+	 * this point. Mark online again before rebooting so that the crash
+	 * analysis tool will see us correctly.
+	 */
+	set_cpu_online(smp_processor_id(), true);
+
+	/* Ensure remote CPUs observe that we're online before rebooting. */
+	smp_mb__after_atomic();
+
+	/*
+	 * Make sure we get correct instructions written by the
+	 * machine_kexec_prepare() CPU.
+	 */
+	__asm__ __volatile__ ("\tibar 0\n"::);
+
+#ifdef CONFIG_SMP
+	/* All secondary cpus go to kexec_smp_wait */
+	if (smp_processor_id() > 0) {
+		relocated_kexec_smp_wait(NULL);
+		unreachable();
+	}
+#endif
+
+	do_kexec = (void *)reboot_code_buffer;
+	do_kexec(efi_boot, cmdline_ptr, systable_ptr, start_addr, first_ind_entry);
+
+	unreachable();
+}
+
+
+#ifdef CONFIG_SMP
+static void kexec_shutdown_secondary(void *regs)
+{
+	int cpu = smp_processor_id();
+
+	if (!cpu_online(cpu))
+		return;
+
+	/* We won't be sent IPIs any more. */
+	set_cpu_online(cpu, false);
+
+	local_irq_disable();
+	while (!atomic_read(&kexec_ready_to_reboot))
+		cpu_relax();
+
+	kexec_reboot();
+}
+
+static void crash_shutdown_secondary(void *passed_regs)
+{
+	int cpu = smp_processor_id();
+	struct pt_regs *regs = passed_regs;
+
+	/*
+	 * If we are passed registers, use those. Otherwise get the
+	 * regs from the last interrupt, which should be correct, as
+	 * we are in an interrupt. But if the regs are not there,
+	 * pull them from the top of the stack. They are probably
+	 * wrong, but we need something to keep from crashing again.
+	 */
+	if (!regs)
+		regs = get_irq_regs();
+	if (!regs)
+		regs = task_pt_regs(current);
+
+	if (!cpu_online(cpu))
+		return;
+
+	/* We won't be sent IPIs any more. */
+	set_cpu_online(cpu, false);
+
+	local_irq_disable();
+	if (!cpumask_test_cpu(cpu, &cpus_in_crash))
+		crash_save_cpu(regs, cpu);
+	cpumask_set_cpu(cpu, &cpus_in_crash);
+
+	while (!atomic_read(&kexec_ready_to_reboot))
+		cpu_relax();
+
+	kexec_reboot();
+}
+
+void crash_smp_send_stop(void)
+{
+	unsigned int ncpus;
+	unsigned long timeout;
+	static int cpus_stopped;
+
+	/*
+	 * This function can be called twice in panic path, but obviously
+	 * we should execute this only once.
+	 */
+	if (cpus_stopped)
+		return;
+
+	cpus_stopped = 1;
+
+	 /* Excluding the panic cpu */
+	ncpus = num_online_cpus() - 1;
+
+	smp_call_function(crash_shutdown_secondary, NULL, 0);
+	smp_wmb();
+
+	/*
+	 * The crash CPU sends an IPI and wait for other CPUs to
+	 * respond. Delay of at least 10 seconds.
+	 */
+	timeout = MSEC_PER_SEC * 10;
+	pr_emerg("Sending IPI to other cpus...\n");
+	while ((cpumask_weight(&cpus_in_crash) < ncpus) && timeout--) {
+		mdelay(1);
+		cpu_relax();
+	}
+}
+#endif /* defined(CONFIG_SMP) */
+
+void machine_shutdown(void)
+{
+	int cpu;
+
+	/* All CPUs go to reboot_code_buffer */
+	for_each_possible_cpu(cpu)
+		if (!cpu_online(cpu))
+			cpu_device_up(get_cpu_device(cpu));
+
+#ifdef CONFIG_SMP
+	smp_call_function(kexec_shutdown_secondary, NULL, 0);
+#endif
+}
+
+void machine_crash_shutdown(struct pt_regs *regs)
+{
+	int crashing_cpu;
+
+	local_irq_disable();
+
+	crashing_cpu = smp_processor_id();
+	crash_save_cpu(regs, crashing_cpu);
+
+#ifdef CONFIG_SMP
+	crash_smp_send_stop();
+#endif
+	cpumask_set_cpu(crashing_cpu, &cpus_in_crash);
+
+	pr_info("Starting crashdump kernel...\n");
+}
+
+void machine_kexec(struct kimage *image)
+{
+	unsigned long entry, *ptr;
+	struct kimage_arch *internal = &image->arch;
+
+	efi_boot = internal->efi_boot;
+	cmdline_ptr = internal->cmdline_ptr;
+	systable_ptr = internal->systable_ptr;
+
+	start_addr = (unsigned long)phys_to_virt(image->start);
+
+	first_ind_entry = (image->type == KEXEC_TYPE_DEFAULT) ?
+		(unsigned long)phys_to_virt(image->head & PAGE_MASK) : 0;
+
+	/*
+	 * The generic kexec code builds a page list with physical
+	 * addresses. they are directly accessible through XKPRANGE
+	 * hence the phys_to_virt() call.
+	 */
+	for (ptr = &image->head; (entry = *ptr) && !(entry & IND_DONE);
+	     ptr = (entry & IND_INDIRECTION) ?
+	       phys_to_virt(entry & PAGE_MASK) : ptr + 1) {
+		if (*ptr & IND_SOURCE || *ptr & IND_INDIRECTION ||
+		    *ptr & IND_DESTINATION)
+			*ptr = (unsigned long) phys_to_virt(*ptr);
+	}
+
+	/* Mark offline before disabling local irq. */
+	set_cpu_online(smp_processor_id(), false);
+
+	/* We do not want to be bothered. */
+	local_irq_disable();
+
+	pr_notice("EFI boot flag 0x%lx\n", efi_boot);
+	pr_notice("Command line at 0x%lx\n", cmdline_ptr);
+	pr_notice("System table at 0x%lx\n", systable_ptr);
+	pr_notice("We will call new kernel at 0x%lx\n", start_addr);
+	pr_notice("Bye ...\n");
+
+	/* Make reboot code buffer available to the boot CPU. */
+	flush_cache_all();
+
+#ifdef CONFIG_SMP
+	atomic_set(&kexec_ready_to_reboot, 1);
+#endif
+
+	kexec_reboot();
+}

arch/loongarch/kernel/mem.c

@@ -58,7 +58,4 @@ void __init memblock_init(void)
 	/* Reserve the kernel text/data/bss */
 	memblock_reserve(__pa_symbol(&_text),
 			 __pa_symbol(&_end) - __pa_symbol(&_text));
-
-	/* Reserve the initrd */
-	reserve_initrd_mem();
 }

arch/loongarch/kernel/module-sections.c

@@ -7,7 +7,33 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 
-Elf_Addr module_emit_plt_entry(struct module *mod, unsigned long val)
+Elf_Addr module_emit_got_entry(struct module *mod, Elf_Addr val)
+{
+	struct mod_section *got_sec = &mod->arch.got;
+	int i = got_sec->num_entries;
+	struct got_entry *got = get_got_entry(val, got_sec);
+
+	if (got)
+		return (Elf_Addr)got;
+
+	/* There is no GOT entry for val yet, create a new one. */
+	got = (struct got_entry *)got_sec->shdr->sh_addr;
+	got[i] = emit_got_entry(val);
+
+	got_sec->num_entries++;
+	if (got_sec->num_entries > got_sec->max_entries) {
+		/*
+		 * This may happen when the module contains a GOT_HI20 without
+		 * a paired GOT_LO12. Such a module is broken, reject it.
+		 */
+		pr_err("%s: module contains bad GOT relocation\n", mod->name);
+		return 0;
+	}
+
+	return (Elf_Addr)&got[i];
+}
+
+Elf_Addr module_emit_plt_entry(struct module *mod, Elf_Addr val)
 {
 	int nr;
 	struct mod_section *plt_sec = &mod->arch.plt;
@@ -50,15 +76,25 @@ static bool duplicate_rela(const Elf_Rela *rela, int idx)
 	return false;
 }
 
-static void count_max_entries(Elf_Rela *relas, int num, unsigned int *plts)
+static void count_max_entries(Elf_Rela *relas, int num,
+			      unsigned int *plts, unsigned int *gots)
 {
 	unsigned int i, type;
 
 	for (i = 0; i < num; i++) {
 		type = ELF_R_TYPE(relas[i].r_info);
-		if (type == R_LARCH_SOP_PUSH_PLT_PCREL) {
+		switch (type) {
+		case R_LARCH_SOP_PUSH_PLT_PCREL:
+		case R_LARCH_B26:
 			if (!duplicate_rela(relas, i))
 				(*plts)++;
+			break;
+		case R_LARCH_GOT_PC_HI20:
+			if (!duplicate_rela(relas, i))
+				(*gots)++;
+			break;
+		default:
+			break; /* Do nothing. */
 		}
 	}
 }
@@ -66,18 +102,24 @@ static void count_max_entries(Elf_Rela *relas, int num, unsigned int *plts)
 int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
 			      char *secstrings, struct module *mod)
 {
-	unsigned int i, num_plts = 0;
+	unsigned int i, num_plts = 0, num_gots = 0;
 
 	/*
 	 * Find the empty .plt sections.
 	 */
 	for (i = 0; i < ehdr->e_shnum; i++) {
-		if (!strcmp(secstrings + sechdrs[i].sh_name, ".plt"))
+		if (!strcmp(secstrings + sechdrs[i].sh_name, ".got"))
+			mod->arch.got.shdr = sechdrs + i;
+		else if (!strcmp(secstrings + sechdrs[i].sh_name, ".plt"))
 			mod->arch.plt.shdr = sechdrs + i;
 		else if (!strcmp(secstrings + sechdrs[i].sh_name, ".plt.idx"))
 			mod->arch.plt_idx.shdr = sechdrs + i;
 	}
 
+	if (!mod->arch.got.shdr) {
+		pr_err("%s: module GOT section(s) missing\n", mod->name);
+		return -ENOEXEC;
+	}
 	if (!mod->arch.plt.shdr) {
 		pr_err("%s: module PLT section(s) missing\n", mod->name);
 		return -ENOEXEC;
@@ -100,9 +142,16 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
 		if (!(dst_sec->sh_flags & SHF_EXECINSTR))
 			continue;
 
-		count_max_entries(relas, num_rela, &num_plts);
+		count_max_entries(relas, num_rela, &num_plts, &num_gots);
 	}
 
+	mod->arch.got.shdr->sh_type = SHT_NOBITS;
+	mod->arch.got.shdr->sh_flags = SHF_ALLOC;
+	mod->arch.got.shdr->sh_addralign = L1_CACHE_BYTES;
+	mod->arch.got.shdr->sh_size = (num_gots + 1) * sizeof(struct got_entry);
+	mod->arch.got.num_entries = 0;
+	mod->arch.got.max_entries = num_gots;
+
 	mod->arch.plt.shdr->sh_type = SHT_NOBITS;
 	mod->arch.plt.shdr->sh_flags = SHF_EXECINSTR | SHF_ALLOC;
 	mod->arch.plt.shdr->sh_addralign = L1_CACHE_BYTES;

arch/loongarch/kernel/module.c

@@ -18,16 +18,6 @@
 #include <linux/string.h>
 #include <linux/kernel.h>
 
-static inline bool signed_imm_check(long val, unsigned int bit)
-{
-	return -(1L << (bit - 1)) <= val && val < (1L << (bit - 1));
-}
-
-static inline bool unsigned_imm_check(unsigned long val, unsigned int bit)
-{
-	return val < (1UL << bit);
-}
-
 static int rela_stack_push(s64 stack_value, s64 *rela_stack, size_t *rela_stack_top)
 {
 	if (*rela_stack_top >= RELA_STACK_DEPTH)
@@ -281,6 +271,96 @@ static int apply_r_larch_add_sub(struct module *mod, u32 *location, Elf_Addr v,
 	}
 }
 
+static int apply_r_larch_b26(struct module *mod, u32 *location, Elf_Addr v,
+			s64 *rela_stack, size_t *rela_stack_top, unsigned int type)
+{
+	ptrdiff_t offset = (void *)v - (void *)location;
+	union loongarch_instruction *insn = (union loongarch_instruction *)location;
+
+	if (offset >= SZ_128M)
+		v = module_emit_plt_entry(mod, v);
+
+	if (offset < -SZ_128M)
+		v = module_emit_plt_entry(mod, v);
+
+	offset = (void *)v - (void *)location;
+
+	if (offset & 3) {
+		pr_err("module %s: jump offset = 0x%llx unaligned! dangerous R_LARCH_B26 (%u) relocation\n",
+				mod->name, (long long)offset, type);
+		return -ENOEXEC;
+	}
+
+	if (!signed_imm_check(offset, 28)) {
+		pr_err("module %s: jump offset = 0x%llx overflow! dangerous R_LARCH_B26 (%u) relocation\n",
+				mod->name, (long long)offset, type);
+		return -ENOEXEC;
+	}
+
+	offset >>= 2;
+	insn->reg0i26_format.immediate_l = offset & 0xffff;
+	insn->reg0i26_format.immediate_h = (offset >> 16) & 0x3ff;
+
+	return 0;
+}
+
+static int apply_r_larch_pcala(struct module *mod, u32 *location, Elf_Addr v,
+			s64 *rela_stack, size_t *rela_stack_top, unsigned int type)
+{
+	union loongarch_instruction *insn = (union loongarch_instruction *)location;
+	/* Use s32 for a sign-extension deliberately. */
+	s32 offset_hi20 = (void *)((v + 0x800) & ~0xfff) -
+			  (void *)((Elf_Addr)location & ~0xfff);
+	Elf_Addr anchor = (((Elf_Addr)location) & ~0xfff) + offset_hi20;
+	ptrdiff_t offset_rem = (void *)v - (void *)anchor;
+
+	switch (type) {
+	case R_LARCH_PCALA_LO12:
+		insn->reg2i12_format.immediate = v & 0xfff;
+		break;
+	case R_LARCH_PCALA_HI20:
+		v = offset_hi20 >> 12;
+		insn->reg1i20_format.immediate = v & 0xfffff;
+		break;
+	case R_LARCH_PCALA64_LO20:
+		v = offset_rem >> 32;
+		insn->reg1i20_format.immediate = v & 0xfffff;
+		break;
+	case R_LARCH_PCALA64_HI12:
+		v = offset_rem >> 52;
+		insn->reg2i12_format.immediate = v & 0xfff;
+		break;
+	default:
+		pr_err("%s: Unsupport relocation type %u\n", mod->name, type);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int apply_r_larch_got_pc(struct module *mod, u32 *location, Elf_Addr v,
+			s64 *rela_stack, size_t *rela_stack_top, unsigned int type)
+{
+	Elf_Addr got = module_emit_got_entry(mod, v);
+
+	if (!got)
+		return -EINVAL;
+
+	switch (type) {
+	case R_LARCH_GOT_PC_LO12:
+		type = R_LARCH_PCALA_LO12;
+		break;
+	case R_LARCH_GOT_PC_HI20:
+		type = R_LARCH_PCALA_HI20;
+		break;
+	default:
+		pr_err("%s: Unsupport relocation type %u\n", mod->name, type);
+		return -EINVAL;
+	}
+
+	return apply_r_larch_pcala(mod, location, got, rela_stack, rela_stack_top, type);
+}
+
 /*
  * reloc_handlers_rela() - Apply a particular relocation to a module
  * @mod: the module to apply the reloc to
@@ -296,7 +376,7 @@ typedef int (*reloc_rela_handler)(struct module *mod, u32 *location, Elf_Addr v,
 
 /* The handlers for known reloc types */
 static reloc_rela_handler reloc_rela_handlers[] = {
-	[R_LARCH_NONE ... R_LARCH_SUB64]		     = apply_r_larch_error,
+	[R_LARCH_NONE ... R_LARCH_RELAX]		     = apply_r_larch_error,
 
 	[R_LARCH_NONE]					     = apply_r_larch_none,
 	[R_LARCH_32]					     = apply_r_larch_32,
@@ -310,6 +390,9 @@ static reloc_rela_handler reloc_rela_handlers[] = {
 	[R_LARCH_SOP_SUB ... R_LARCH_SOP_IF_ELSE] 	     = apply_r_larch_sop,
 	[R_LARCH_SOP_POP_32_S_10_5 ... R_LARCH_SOP_POP_32_U] = apply_r_larch_sop_imm_field,
 	[R_LARCH_ADD32 ... R_LARCH_SUB64]		     = apply_r_larch_add_sub,
+	[R_LARCH_B26]					     = apply_r_larch_b26,
+	[R_LARCH_PCALA_HI20...R_LARCH_PCALA64_HI12]	     = apply_r_larch_pcala,
+	[R_LARCH_GOT_PC_HI20...R_LARCH_GOT_PC_LO12]	     = apply_r_larch_got_pc,
 };
 
 int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab,

arch/loongarch/kernel/perf_event.c

+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Linux performance counter support for LoongArch.
+ *
+ * Copyright (C) 2022 Loongson Technology Corporation Limited
+ *
+ * Derived from MIPS:
+ * Copyright (C) 2010 MIPS Technologies, Inc.
+ * Copyright (C) 2011 Cavium Networks, Inc.
+ * Author: Deng-Cheng Zhu
+ */
+
+#include <linux/cpumask.h>
+#include <linux/interrupt.h>
+#include <linux/smp.h>
+#include <linux/kernel.h>
+#include <linux/perf_event.h>
+#include <linux/uaccess.h>
+#include <linux/sched/task_stack.h>
+
+#include <asm/irq.h>
+#include <asm/irq_regs.h>
+#include <asm/stacktrace.h>
+#include <asm/unwind.h>
+
+/*
+ * Get the return address for a single stackframe and return a pointer to the
+ * next frame tail.
+ */
+static unsigned long
+user_backtrace(struct perf_callchain_entry_ctx *entry, unsigned long fp)
+{
+	unsigned long err;
+	unsigned long __user *user_frame_tail;
+	struct stack_frame buftail;
+
+	user_frame_tail = (unsigned long __user *)(fp - sizeof(struct stack_frame));
+
+	/* Also check accessibility of one struct frame_tail beyond */
+	if (!access_ok(user_frame_tail, sizeof(buftail)))
+		return 0;
+
+	pagefault_disable();
+	err = __copy_from_user_inatomic(&buftail, user_frame_tail, sizeof(buftail));
+	pagefault_enable();
+
+	if (err || (unsigned long)user_frame_tail >= buftail.fp)
+		return 0;
+
+	perf_callchain_store(entry, buftail.ra);
+
+	return buftail.fp;
+}
+
+void perf_callchain_user(struct perf_callchain_entry_ctx *entry,
+			 struct pt_regs *regs)
+{
+	unsigned long fp;
+
+	if (perf_guest_state()) {
+		/* We don't support guest os callchain now */
+		return;
+	}
+
+	perf_callchain_store(entry, regs->csr_era);
+
+	fp = regs->regs[22];
+
+	while (entry->nr < entry->max_stack && fp && !((unsigned long)fp & 0xf))
+		fp = user_backtrace(entry, fp);
+}
+
+void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
+			   struct pt_regs *regs)
+{
+	struct unwind_state state;
+	unsigned long addr;
+
+	for (unwind_start(&state, current, regs);
+	      !unwind_done(&state); unwind_next_frame(&state)) {
+		addr = unwind_get_return_address(&state);
+		if (!addr || perf_callchain_store(entry, addr))
+			return;
+	}
+}
+
+#define LOONGARCH_MAX_HWEVENTS 32
+
+struct cpu_hw_events {
+	/* Array of events on this cpu. */
+	struct perf_event	*events[LOONGARCH_MAX_HWEVENTS];
+
+	/*
+	 * Set the bit (indexed by the counter number) when the counter
+	 * is used for an event.
+	 */
+	unsigned long		used_mask[BITS_TO_LONGS(LOONGARCH_MAX_HWEVENTS)];
+
+	/*
+	 * Software copy of the control register for each performance counter.
+	 */
+	unsigned int		saved_ctrl[LOONGARCH_MAX_HWEVENTS];
+};
+static DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events) = {
+	.saved_ctrl = {0},
+};
+
+/* The description of LoongArch performance events. */
+struct loongarch_perf_event {
+	unsigned int event_id;
+};
+
+static struct loongarch_perf_event raw_event;
+static DEFINE_MUTEX(raw_event_mutex);
+
+#define C(x) PERF_COUNT_HW_CACHE_##x
+#define HW_OP_UNSUPPORTED		0xffffffff
+#define CACHE_OP_UNSUPPORTED		0xffffffff
+
+#define PERF_MAP_ALL_UNSUPPORTED					\
+	[0 ... PERF_COUNT_HW_MAX - 1] = {HW_OP_UNSUPPORTED}
+
+#define PERF_CACHE_MAP_ALL_UNSUPPORTED					\
+[0 ... C(MAX) - 1] = {							\
+	[0 ... C(OP_MAX) - 1] = {					\
+		[0 ... C(RESULT_MAX) - 1] = {CACHE_OP_UNSUPPORTED},	\
+	},								\
+}
+
+struct loongarch_pmu {
+	u64		max_period;
+	u64		valid_count;
+	u64		overflow;
+	const char	*name;
+	unsigned int	num_counters;
+	u64		(*read_counter)(unsigned int idx);
+	void		(*write_counter)(unsigned int idx, u64 val);
+	const struct loongarch_perf_event *(*map_raw_event)(u64 config);
+	const struct loongarch_perf_event (*general_event_map)[PERF_COUNT_HW_MAX];
+	const struct loongarch_perf_event (*cache_event_map)
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX];
+};
+
+static struct loongarch_pmu loongarch_pmu;
+
+#define M_PERFCTL_EVENT(event)	(event & CSR_PERFCTRL_EVENT)
+
+#define M_PERFCTL_COUNT_EVENT_WHENEVER	(CSR_PERFCTRL_PLV0 |	\
+					CSR_PERFCTRL_PLV1 |	\
+					CSR_PERFCTRL_PLV2 |	\
+					CSR_PERFCTRL_PLV3 |	\
+					CSR_PERFCTRL_IE)
+
+#define M_PERFCTL_CONFIG_MASK		0x1f0000
+
+static void pause_local_counters(void);
+static void resume_local_counters(void);
+
+static u64 loongarch_pmu_read_counter(unsigned int idx)
+{
+	u64 val = -1;
+
+	switch (idx) {
+	case 0:
+		val = read_csr_perfcntr0();
+		break;
+	case 1:
+		val = read_csr_perfcntr1();
+		break;
+	case 2:
+		val = read_csr_perfcntr2();
+		break;
+	case 3:
+		val = read_csr_perfcntr3();
+		break;
+	default:
+		WARN_ONCE(1, "Invalid performance counter number (%d)\n", idx);
+		return 0;
+	}
+
+	return val;
+}
+
+static void loongarch_pmu_write_counter(unsigned int idx, u64 val)
+{
+	switch (idx) {
+	case 0:
+		write_csr_perfcntr0(val);
+		return;
+	case 1:
+		write_csr_perfcntr1(val);
+		return;
+	case 2:
+		write_csr_perfcntr2(val);
+		return;
+	case 3:
+		write_csr_perfcntr3(val);
+		return;
+	default:
+		WARN_ONCE(1, "Invalid performance counter number (%d)\n", idx);
+		return;
+	}
+}
+
+static unsigned int loongarch_pmu_read_control(unsigned int idx)
+{
+	unsigned int val = -1;
+
+	switch (idx) {
+	case 0:
+		val = read_csr_perfctrl0();
+		break;
+	case 1:
+		val = read_csr_perfctrl1();
+		break;
+	case 2:
+		val = read_csr_perfctrl2();
+		break;
+	case 3:
+		val = read_csr_perfctrl3();
+		break;
+	default:
+		WARN_ONCE(1, "Invalid performance counter number (%d)\n", idx);
+		return 0;
+	}
+
+	return val;
+}
+
+static void loongarch_pmu_write_control(unsigned int idx, unsigned int val)
+{
+	switch (idx) {
+	case 0:
+		write_csr_perfctrl0(val);
+		return;
+	case 1:
+		write_csr_perfctrl1(val);
+		return;
+	case 2:
+		write_csr_perfctrl2(val);
+		return;
+	case 3:
+		write_csr_perfctrl3(val);
+		return;
+	default:
+		WARN_ONCE(1, "Invalid performance counter number (%d)\n", idx);
+		return;
+	}
+}
+
+static int loongarch_pmu_alloc_counter(struct cpu_hw_events *cpuc, struct hw_perf_event *hwc)
+{
+	int i;
+
+	for (i = 0; i < loongarch_pmu.num_counters; i++) {
+		if (!test_and_set_bit(i, cpuc->used_mask))
+			return i;
+	}
+
+	return -EAGAIN;
+}
+
+static void loongarch_pmu_enable_event(struct hw_perf_event *evt, int idx)
+{
+	unsigned int cpu;
+	struct perf_event *event = container_of(evt, struct perf_event, hw);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
+	WARN_ON(idx < 0 || idx >= loongarch_pmu.num_counters);
+
+	/* Make sure interrupt enabled. */
+	cpuc->saved_ctrl[idx] = M_PERFCTL_EVENT(evt->event_base & 0xff) |
+		(evt->config_base & M_PERFCTL_CONFIG_MASK) | CSR_PERFCTRL_IE;
+
+	cpu = (event->cpu >= 0) ? event->cpu : smp_processor_id();
+
+	/*
+	 * We do not actually let the counter run. Leave it until start().
+	 */
+	pr_debug("Enabling perf counter for CPU%d\n", cpu);
+}
+
+static void loongarch_pmu_disable_event(int idx)
+{
+	unsigned long flags;
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
+	WARN_ON(idx < 0 || idx >= loongarch_pmu.num_counters);
+
+	local_irq_save(flags);
+	cpuc->saved_ctrl[idx] = loongarch_pmu_read_control(idx) &
+		~M_PERFCTL_COUNT_EVENT_WHENEVER;
+	loongarch_pmu_write_control(idx, cpuc->saved_ctrl[idx]);
+	local_irq_restore(flags);
+}
+
+static int loongarch_pmu_event_set_period(struct perf_event *event,
+				    struct hw_perf_event *hwc,
+				    int idx)
+{
+	int ret = 0;
+	u64 left = local64_read(&hwc->period_left);
+	u64 period = hwc->sample_period;
+
+	if (unlikely((left + period) & (1ULL << 63))) {
+		/* left underflowed by more than period. */
+		left = period;
+		local64_set(&hwc->period_left, left);
+		hwc->last_period = period;
+		ret = 1;
+	} else	if (unlikely((left + period) <= period)) {
+		/* left underflowed by less than period. */
+		left += period;
+		local64_set(&hwc->period_left, left);
+		hwc->last_period = period;
+		ret = 1;
+	}
+
+	if (left > loongarch_pmu.max_period) {
+		left = loongarch_pmu.max_period;
+		local64_set(&hwc->period_left, left);
+	}
+
+	local64_set(&hwc->prev_count, loongarch_pmu.overflow - left);
+
+	loongarch_pmu.write_counter(idx, loongarch_pmu.overflow - left);
+
+	perf_event_update_userpage(event);
+
+	return ret;
+}
+
+static void loongarch_pmu_event_update(struct perf_event *event,
+				 struct hw_perf_event *hwc,
+				 int idx)
+{
+	u64 delta;
+	u64 prev_raw_count, new_raw_count;
+
+again:
+	prev_raw_count = local64_read(&hwc->prev_count);
+	new_raw_count = loongarch_pmu.read_counter(idx);
+
+	if (local64_cmpxchg(&hwc->prev_count, prev_raw_count,
+				new_raw_count) != prev_raw_count)
+		goto again;
+
+	delta = new_raw_count - prev_raw_count;
+
+	local64_add(delta, &event->count);
+	local64_sub(delta, &hwc->period_left);
+}
+
+static void loongarch_pmu_start(struct perf_event *event, int flags)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	if (flags & PERF_EF_RELOAD)
+		WARN_ON_ONCE(!(hwc->state & PERF_HES_UPTODATE));
+
+	hwc->state = 0;
+
+	/* Set the period for the event. */
+	loongarch_pmu_event_set_period(event, hwc, hwc->idx);
+
+	/* Enable the event. */
+	loongarch_pmu_enable_event(hwc, hwc->idx);
+}
+
+static void loongarch_pmu_stop(struct perf_event *event, int flags)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	if (!(hwc->state & PERF_HES_STOPPED)) {
+		/* We are working on a local event. */
+		loongarch_pmu_disable_event(hwc->idx);
+		barrier();
+		loongarch_pmu_event_update(event, hwc, hwc->idx);
+		hwc->state |= PERF_HES_STOPPED | PERF_HES_UPTODATE;
+	}
+}
+
+static int loongarch_pmu_add(struct perf_event *event, int flags)
+{
+	int idx, err = 0;
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	struct hw_perf_event *hwc = &event->hw;
+
+	perf_pmu_disable(event->pmu);
+
+	/* To look for a free counter for this event. */
+	idx = loongarch_pmu_alloc_counter(cpuc, hwc);
+	if (idx < 0) {
+		err = idx;
+		goto out;
+	}
+
+	/*
+	 * If there is an event in the counter we are going to use then
+	 * make sure it is disabled.
+	 */
+	event->hw.idx = idx;
+	loongarch_pmu_disable_event(idx);
+	cpuc->events[idx] = event;
+
+	hwc->state = PERF_HES_STOPPED | PERF_HES_UPTODATE;
+	if (flags & PERF_EF_START)
+		loongarch_pmu_start(event, PERF_EF_RELOAD);
+
+	/* Propagate our changes to the userspace mapping. */
+	perf_event_update_userpage(event);
+
+out:
+	perf_pmu_enable(event->pmu);
+	return err;
+}
+
+static void loongarch_pmu_del(struct perf_event *event, int flags)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	struct hw_perf_event *hwc = &event->hw;
+	int idx = hwc->idx;
+
+	WARN_ON(idx < 0 || idx >= loongarch_pmu.num_counters);
+
+	loongarch_pmu_stop(event, PERF_EF_UPDATE);
+	cpuc->events[idx] = NULL;
+	clear_bit(idx, cpuc->used_mask);
+
+	perf_event_update_userpage(event);
+}
+
+static void loongarch_pmu_read(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	/* Don't read disabled counters! */
+	if (hwc->idx < 0)
+		return;
+
+	loongarch_pmu_event_update(event, hwc, hwc->idx);
+}
+
+static void loongarch_pmu_enable(struct pmu *pmu)
+{
+	resume_local_counters();
+}
+
+static void loongarch_pmu_disable(struct pmu *pmu)
+{
+	pause_local_counters();
+}
+
+static DEFINE_MUTEX(pmu_reserve_mutex);
+static atomic_t active_events = ATOMIC_INIT(0);
+
+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 -EINVAL;
+}
+
+static void reset_counters(void *arg);
+static int __hw_perf_event_init(struct perf_event *event);
+
+static void hw_perf_event_destroy(struct perf_event *event)
+{
+	if (atomic_dec_and_mutex_lock(&active_events, &pmu_reserve_mutex)) {
+		on_each_cpu(reset_counters, NULL, 1);
+		free_irq(get_pmc_irq(), &loongarch_pmu);
+		mutex_unlock(&pmu_reserve_mutex);
+	}
+}
+
+static void handle_associated_event(struct cpu_hw_events *cpuc, int idx,
+			struct perf_sample_data *data, struct pt_regs *regs)
+{
+	struct perf_event *event = cpuc->events[idx];
+	struct hw_perf_event *hwc = &event->hw;
+
+	loongarch_pmu_event_update(event, hwc, idx);
+	data->period = event->hw.last_period;
+	if (!loongarch_pmu_event_set_period(event, hwc, idx))
+		return;
+
+	if (perf_event_overflow(event, data, regs))
+		loongarch_pmu_disable_event(idx);
+}
+
+static irqreturn_t pmu_handle_irq(int irq, void *dev)
+{
+	int n;
+	int handled = IRQ_NONE;
+	uint64_t counter;
+	struct pt_regs *regs;
+	struct perf_sample_data data;
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
+	/*
+	 * First we pause the local counters, so that when we are locked
+	 * here, the counters are all paused. When it gets locked due to
+	 * perf_disable(), the timer interrupt handler will be delayed.
+	 *
+	 * See also loongarch_pmu_start().
+	 */
+	pause_local_counters();
+
+	regs = get_irq_regs();
+
+	perf_sample_data_init(&data, 0, 0);
+
+	for (n = 0; n < loongarch_pmu.num_counters; n++) {
+		if (test_bit(n, cpuc->used_mask)) {
+			counter = loongarch_pmu.read_counter(n);
+			if (counter & loongarch_pmu.overflow) {
+				handle_associated_event(cpuc, n, &data, regs);
+				handled = IRQ_HANDLED;
+			}
+		}
+	}
+
+	resume_local_counters();
+
+	/*
+	 * Do all the work for the pending perf events. We can do this
+	 * in here because the performance counter interrupt is a regular
+	 * interrupt, not NMI.
+	 */
+	if (handled == IRQ_HANDLED)
+		irq_work_run();
+
+	return handled;
+}
+
+static int loongarch_pmu_event_init(struct perf_event *event)
+{
+	int r, irq;
+	unsigned long flags;
+
+	/* does not support taken branch sampling */
+	if (has_branch_stack(event))
+		return -EOPNOTSUPP;
+
+	switch (event->attr.type) {
+	case PERF_TYPE_RAW:
+	case PERF_TYPE_HARDWARE:
+	case PERF_TYPE_HW_CACHE:
+		break;
+
+	default:
+		/* Init it to avoid false validate_group */
+		event->hw.event_base = 0xffffffff;
+		return -ENOENT;
+	}
+
+	if (event->cpu >= 0 && !cpu_online(event->cpu))
+		return -ENODEV;
+
+	irq = get_pmc_irq();
+	flags = IRQF_PERCPU | IRQF_NOBALANCING | IRQF_NO_THREAD | IRQF_NO_SUSPEND | IRQF_SHARED;
+	if (!atomic_inc_not_zero(&active_events)) {
+		mutex_lock(&pmu_reserve_mutex);
+		if (atomic_read(&active_events) == 0) {
+			r = request_irq(irq, pmu_handle_irq, flags, "Perf_PMU", &loongarch_pmu);
+			if (r < 0) {
+				mutex_unlock(&pmu_reserve_mutex);
+				pr_warn("PMU IRQ request failed\n");
+				return -ENODEV;
+			}
+		}
+		atomic_inc(&active_events);
+		mutex_unlock(&pmu_reserve_mutex);
+	}
+
+	return __hw_perf_event_init(event);
+}
+
+static struct pmu pmu = {
+	.pmu_enable	= loongarch_pmu_enable,
+	.pmu_disable	= loongarch_pmu_disable,
+	.event_init	= loongarch_pmu_event_init,
+	.add		= loongarch_pmu_add,
+	.del		= loongarch_pmu_del,
+	.start		= loongarch_pmu_start,
+	.stop		= loongarch_pmu_stop,
+	.read		= loongarch_pmu_read,
+};
+
+static unsigned int loongarch_pmu_perf_event_encode(const struct loongarch_perf_event *pev)
+{
+	return (pev->event_id & 0xff);
+}
+
+static const struct loongarch_perf_event *loongarch_pmu_map_general_event(int idx)
+{
+	const struct loongarch_perf_event *pev;
+
+	pev = &(*loongarch_pmu.general_event_map)[idx];
+
+	if (pev->event_id == HW_OP_UNSUPPORTED)
+		return ERR_PTR(-ENOENT);
+
+	return pev;
+}
+
+static const struct loongarch_perf_event *loongarch_pmu_map_cache_event(u64 config)
+{
+	unsigned int cache_type, cache_op, cache_result;
+	const struct loongarch_perf_event *pev;
+
+	cache_type = (config >> 0) & 0xff;
+	if (cache_type >= PERF_COUNT_HW_CACHE_MAX)
+		return ERR_PTR(-EINVAL);
+
+	cache_op = (config >> 8) & 0xff;
+	if (cache_op >= PERF_COUNT_HW_CACHE_OP_MAX)
+		return ERR_PTR(-EINVAL);
+
+	cache_result = (config >> 16) & 0xff;
+	if (cache_result >= PERF_COUNT_HW_CACHE_RESULT_MAX)
+		return ERR_PTR(-EINVAL);
+
+	pev = &((*loongarch_pmu.cache_event_map)
+					[cache_type]
+					[cache_op]
+					[cache_result]);
+
+	if (pev->event_id == CACHE_OP_UNSUPPORTED)
+		return ERR_PTR(-ENOENT);
+
+	return pev;
+}
+
+static int validate_group(struct perf_event *event)
+{
+	struct cpu_hw_events fake_cpuc;
+	struct perf_event *sibling, *leader = event->group_leader;
+
+	memset(&fake_cpuc, 0, sizeof(fake_cpuc));
+
+	if (loongarch_pmu_alloc_counter(&fake_cpuc, &leader->hw) < 0)
+		return -EINVAL;
+
+	for_each_sibling_event(sibling, leader) {
+		if (loongarch_pmu_alloc_counter(&fake_cpuc, &sibling->hw) < 0)
+			return -EINVAL;
+	}
+
+	if (loongarch_pmu_alloc_counter(&fake_cpuc, &event->hw) < 0)
+		return -EINVAL;
+
+	return 0;
+}
+
+static void reset_counters(void *arg)
+{
+	int n;
+	int counters = loongarch_pmu.num_counters;
+
+	for (n = 0; n < counters; n++) {
+		loongarch_pmu_write_control(n, 0);
+		loongarch_pmu.write_counter(n, 0);
+	}
+}
+
+static const struct loongarch_perf_event loongson_event_map[PERF_COUNT_HW_MAX] = {
+	PERF_MAP_ALL_UNSUPPORTED,
+	[PERF_COUNT_HW_CPU_CYCLES] = { 0x00 },
+	[PERF_COUNT_HW_INSTRUCTIONS] = { 0x01 },
+	[PERF_COUNT_HW_CACHE_REFERENCES] = { 0x08 },
+	[PERF_COUNT_HW_CACHE_MISSES] = { 0x09 },
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = { 0x02 },
+	[PERF_COUNT_HW_BRANCH_MISSES] = { 0x03 },
+};
+
+static const struct loongarch_perf_event loongson_cache_map
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+PERF_CACHE_MAP_ALL_UNSUPPORTED,
+[C(L1D)] = {
+	/*
+	 * Like some other architectures (e.g. ARM), the performance
+	 * counters don't differentiate between read and write
+	 * accesses/misses, so this isn't strictly correct, but it's the
+	 * best we can do. Writes and reads get combined.
+	 */
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)]	= { 0x8 },
+		[C(RESULT_MISS)]	= { 0x9 },
+	},
+	[C(OP_WRITE)] = {
+		[C(RESULT_ACCESS)]	= { 0x8 },
+		[C(RESULT_MISS)]	= { 0x9 },
+	},
+	[C(OP_PREFETCH)] = {
+		[C(RESULT_ACCESS)]	= { 0xaa },
+		[C(RESULT_MISS)]	= { 0xa9 },
+	},
+},
+[C(L1I)] = {
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)]	= { 0x6 },
+		[C(RESULT_MISS)]	= { 0x7 },
+	},
+},
+[C(LL)] = {
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)]	= { 0xc },
+		[C(RESULT_MISS)]	= { 0xd },
+	},
+	[C(OP_WRITE)] = {
+		[C(RESULT_ACCESS)]	= { 0xc },
+		[C(RESULT_MISS)]	= { 0xd },
+	},
+},
+[C(ITLB)] = {
+	[C(OP_READ)] = {
+		[C(RESULT_MISS)]    = { 0x3b },
+	},
+},
+[C(DTLB)] = {
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)]	= { 0x4 },
+		[C(RESULT_MISS)]	= { 0x3c },
+	},
+	[C(OP_WRITE)] = {
+		[C(RESULT_ACCESS)]	= { 0x4 },
+		[C(RESULT_MISS)]	= { 0x3c },
+	},
+},
+[C(BPU)] = {
+	/* Using the same code for *HW_BRANCH* */
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)]  = { 0x02 },
+		[C(RESULT_MISS)]    = { 0x03 },
+	},
+},
+};
+
+static int __hw_perf_event_init(struct perf_event *event)
+{
+	int err;
+	struct hw_perf_event *hwc = &event->hw;
+	struct perf_event_attr *attr = &event->attr;
+	const struct loongarch_perf_event *pev;
+
+	/* Returning LoongArch event descriptor for generic perf event. */
+	if (PERF_TYPE_HARDWARE == event->attr.type) {
+		if (event->attr.config >= PERF_COUNT_HW_MAX)
+			return -EINVAL;
+		pev = loongarch_pmu_map_general_event(event->attr.config);
+	} else if (PERF_TYPE_HW_CACHE == event->attr.type) {
+		pev = loongarch_pmu_map_cache_event(event->attr.config);
+	} else if (PERF_TYPE_RAW == event->attr.type) {
+		/* We are working on the global raw event. */
+		mutex_lock(&raw_event_mutex);
+		pev = loongarch_pmu.map_raw_event(event->attr.config);
+	} else {
+		/* The event type is not (yet) supported. */
+		return -EOPNOTSUPP;
+	}
+
+	if (IS_ERR(pev)) {
+		if (PERF_TYPE_RAW == event->attr.type)
+			mutex_unlock(&raw_event_mutex);
+		return PTR_ERR(pev);
+	}
+
+	/*
+	 * We allow max flexibility on how each individual counter shared
+	 * by the single CPU operates (the mode exclusion and the range).
+	 */
+	hwc->config_base = CSR_PERFCTRL_IE;
+
+	hwc->event_base = loongarch_pmu_perf_event_encode(pev);
+	if (PERF_TYPE_RAW == event->attr.type)
+		mutex_unlock(&raw_event_mutex);
+
+	if (!attr->exclude_user) {
+		hwc->config_base |= CSR_PERFCTRL_PLV3;
+		hwc->config_base |= CSR_PERFCTRL_PLV2;
+	}
+	if (!attr->exclude_kernel) {
+		hwc->config_base |= CSR_PERFCTRL_PLV0;
+	}
+	if (!attr->exclude_hv) {
+		hwc->config_base |= CSR_PERFCTRL_PLV1;
+	}
+
+	hwc->config_base &= M_PERFCTL_CONFIG_MASK;
+	/*
+	 * The event can belong to another cpu. We do not assign a local
+	 * counter for it for now.
+	 */
+	hwc->idx = -1;
+	hwc->config = 0;
+
+	if (!hwc->sample_period) {
+		hwc->sample_period  = loongarch_pmu.max_period;
+		hwc->last_period    = hwc->sample_period;
+		local64_set(&hwc->period_left, hwc->sample_period);
+	}
+
+	err = 0;
+	if (event->group_leader != event)
+		err = validate_group(event);
+
+	event->destroy = hw_perf_event_destroy;
+
+	if (err)
+		event->destroy(event);
+
+	return err;
+}
+
+static void pause_local_counters(void)
+{
+	unsigned long flags;
+	int ctr = loongarch_pmu.num_counters;
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
+	local_irq_save(flags);
+	do {
+		ctr--;
+		cpuc->saved_ctrl[ctr] = loongarch_pmu_read_control(ctr);
+		loongarch_pmu_write_control(ctr, cpuc->saved_ctrl[ctr] &
+					 ~M_PERFCTL_COUNT_EVENT_WHENEVER);
+	} while (ctr > 0);
+	local_irq_restore(flags);
+}
+
+static void resume_local_counters(void)
+{
+	int ctr = loongarch_pmu.num_counters;
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
+	do {
+		ctr--;
+		loongarch_pmu_write_control(ctr, cpuc->saved_ctrl[ctr]);
+	} while (ctr > 0);
+}
+
+static const struct loongarch_perf_event *loongarch_pmu_map_raw_event(u64 config)
+{
+	raw_event.event_id = config & 0xff;
+
+	return &raw_event;
+}
+
+static int __init init_hw_perf_events(void)
+{
+	int counters;
+
+	if (!cpu_has_pmp)
+		return -ENODEV;
+
+	pr_info("Performance counters: ");
+	counters = ((read_cpucfg(LOONGARCH_CPUCFG6) & CPUCFG6_PMNUM) >> 4) + 1;
+
+	loongarch_pmu.num_counters = counters;
+	loongarch_pmu.max_period = (1ULL << 63) - 1;
+	loongarch_pmu.valid_count = (1ULL << 63) - 1;
+	loongarch_pmu.overflow = 1ULL << 63;
+	loongarch_pmu.name = "loongarch/loongson64";
+	loongarch_pmu.read_counter = loongarch_pmu_read_counter;
+	loongarch_pmu.write_counter = loongarch_pmu_write_counter;
+	loongarch_pmu.map_raw_event = loongarch_pmu_map_raw_event;
+	loongarch_pmu.general_event_map = &loongson_event_map;
+	loongarch_pmu.cache_event_map = &loongson_cache_map;
+
+	on_each_cpu(reset_counters, NULL, 1);
+
+	pr_cont("%s PMU enabled, %d %d-bit counters available to each CPU.\n",
+			loongarch_pmu.name, counters, 64);
+
+	perf_pmu_register(&pmu, "cpu", PERF_TYPE_RAW);
+
+	return 0;
+}
+early_initcall(init_hw_perf_events);

arch/loongarch/kernel/perf_regs.c

+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2022 Loongson Technology Corporation Limited
+ *
+ * Derived from MIPS:
+ * Copyright (C) 2013 Cavium, Inc.
+ */
+
+#include <linux/perf_event.h>
+
+#include <asm/ptrace.h>
+
+#ifdef CONFIG_32BIT
+u64 perf_reg_abi(struct task_struct *tsk)
+{
+	return PERF_SAMPLE_REGS_ABI_32;
+}
+#else /* Must be CONFIG_64BIT */
+u64 perf_reg_abi(struct task_struct *tsk)
+{
+	if (test_tsk_thread_flag(tsk, TIF_32BIT_REGS))
+		return PERF_SAMPLE_REGS_ABI_32;
+	else
+		return PERF_SAMPLE_REGS_ABI_64;
+}
+#endif /* CONFIG_32BIT */
+
+int perf_reg_validate(u64 mask)
+{
+	if (!mask)
+		return -EINVAL;
+	if (mask & ~((1ull << PERF_REG_LOONGARCH_MAX) - 1))
+		return -EINVAL;
+	return 0;
+}
+
+u64 perf_reg_value(struct pt_regs *regs, int idx)
+{
+	if (WARN_ON_ONCE((u32)idx >= PERF_REG_LOONGARCH_MAX))
+		return 0;
+
+	if ((u32)idx == PERF_REG_LOONGARCH_PC)
+		return regs->csr_era;
+
+	return regs->regs[idx];
+}
+
+void perf_get_regs_user(struct perf_regs *regs_user,
+			struct pt_regs *regs)
+{
+	regs_user->regs = task_pt_regs(current);
+	regs_user->abi = perf_reg_abi(current);
+}

arch/loongarch/kernel/relocate_kernel.S

+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * relocate_kernel.S for kexec
+ *
+ * Copyright (C) 2022 Loongson Technology Corporation Limited
+ */
+
+#include <linux/kexec.h>
+
+#include <asm/asm.h>
+#include <asm/asmmacro.h>
+#include <asm/regdef.h>
+#include <asm/loongarch.h>
+#include <asm/stackframe.h>
+#include <asm/addrspace.h>
+
+SYM_CODE_START(relocate_new_kernel)
+	/*
+	 * a0: EFI boot flag for the new kernel
+	 * a1: Command line pointer for the new kernel
+	 * a2: System table pointer for the new kernel
+	 * a3: Start address to jump to after relocation
+	 * a4: Pointer to the current indirection page entry
+	 */
+	move		s0, a4
+
+	/*
+	 * In case of a kdump/crash kernel, the indirection page is not
+	 * populated as the kernel is directly copied to a reserved location
+	 */
+	beqz		s0, done
+
+process_entry:
+	PTR_L		s1, s0, 0
+	PTR_ADDI	s0, s0, SZREG
+
+	/* destination page */
+	andi		s2, s1, IND_DESTINATION
+	beqz		s2, 1f
+	li.w		t0, ~0x1
+	and		s3, s1, t0	/* store destination addr in s3 */
+	b		process_entry
+
+1:
+	/* indirection page, update s0	*/
+	andi		s2, s1, IND_INDIRECTION
+	beqz		s2, 1f
+	li.w		t0, ~0x2
+	and		s0, s1, t0
+	b		process_entry
+
+1:
+	/* done page */
+	andi		s2, s1, IND_DONE
+	beqz		s2, 1f
+	b		done
+
+1:
+	/* source page */
+	andi		s2, s1, IND_SOURCE
+	beqz		s2, process_entry
+	li.w		t0, ~0x8
+	and		s1, s1, t0
+	li.w		s5, (1 << _PAGE_SHIFT) / SZREG
+
+copy_word:
+	/* copy page word by word */
+	REG_L		s4, s1, 0
+	REG_S		s4, s3, 0
+	PTR_ADDI	s3, s3, SZREG
+	PTR_ADDI	s1, s1, SZREG
+	LONG_ADDI	s5, s5, -1
+	beqz		s5, process_entry
+	b		copy_word
+	b		process_entry
+
+done:
+	ibar		0
+	dbar		0
+
+	/*
+	 * Jump to the new kernel,
+	 * make sure the values of a0, a1, a2 and a3 are not changed.
+	 */
+	jr		a3
+SYM_CODE_END(relocate_new_kernel)
+
+#ifdef CONFIG_SMP
+/*
+ * Other CPUs should wait until code is relocated and
+ * then start at the entry point from LOONGARCH_IOCSR_MBUF0.
+ */
+SYM_CODE_START(kexec_smp_wait)
+1:	li.w		t0, 0x100			/* wait for init loop */
+2:	addi.w		t0, t0, -1			/* limit mailbox access */
+	bnez		t0, 2b
+	li.w		t1, LOONGARCH_IOCSR_MBUF0
+	iocsrrd.w	s0, t1				/* check PC as an indicator */
+	beqz		s0, 1b
+	iocsrrd.d	s0, t1				/* get PC via mailbox */
+
+	li.d		t0, CACHE_BASE
+	or		s0, s0, t0			/* s0 = TO_CACHE(s0) */
+	jr		s0				/* jump to initial PC */
+SYM_CODE_END(kexec_smp_wait)
+#endif
+
+relocate_new_kernel_end:
+
+SYM_DATA_START(relocate_new_kernel_size)
+	PTR		relocate_new_kernel_end - relocate_new_kernel
+SYM_DATA_END(relocate_new_kernel_size)

arch/loongarch/kernel/setup.c

@@ -19,6 +19,8 @@
 #include <linux/memblock.h>
 #include <linux/initrd.h>
 #include <linux/ioport.h>
+#include <linux/kexec.h>
+#include <linux/crash_dump.h>
 #include <linux/root_dev.h>
 #include <linux/console.h>
 #include <linux/pfn.h>
@@ -185,8 +187,70 @@ static int __init early_parse_mem(char *p)
 }
 early_param("mem", early_parse_mem);
 
+static void __init arch_reserve_vmcore(void)
+{
+#ifdef CONFIG_PROC_VMCORE
+	u64 i;
+	phys_addr_t start, end;
+
+	if (!is_kdump_kernel())
+		return;
+
+	if (!elfcorehdr_size) {
+		for_each_mem_range(i, &start, &end) {
+			if (elfcorehdr_addr >= start && elfcorehdr_addr < end) {
+				/*
+				 * Reserve from the elf core header to the end of
+				 * the memory segment, that should all be kdump
+				 * reserved memory.
+				 */
+				elfcorehdr_size = end - elfcorehdr_addr;
+				break;
+			}
+		}
+	}
+
+	if (memblock_is_region_reserved(elfcorehdr_addr, elfcorehdr_size)) {
+		pr_warn("elfcorehdr is overlapped\n");
+		return;
+	}
+
+	memblock_reserve(elfcorehdr_addr, elfcorehdr_size);
+
+	pr_info("Reserving %llu KiB of memory at 0x%llx for elfcorehdr\n",
+		elfcorehdr_size >> 10, elfcorehdr_addr);
+#endif
+}
+
+static void __init arch_parse_crashkernel(void)
+{
+#ifdef CONFIG_KEXEC
+	int ret;
+	unsigned long long start;
+	unsigned long long total_mem;
+	unsigned long long crash_base, crash_size;
+
+	total_mem = memblock_phys_mem_size();
+	ret = parse_crashkernel(boot_command_line, total_mem, &crash_size, &crash_base);
+	if (ret < 0 || crash_size <= 0)
+		return;
+
+	start = memblock_phys_alloc_range(crash_size, 1, crash_base, crash_base + crash_size);
+	if (start != crash_base) {
+		pr_warn("Invalid memory region reserved for crash kernel\n");
+		return;
+	}
+
+	crashk_res.start = crash_base;
+	crashk_res.end	 = crash_base + crash_size - 1;
+#endif
+}
+
 void __init platform_init(void)
 {
+	arch_reserve_vmcore();
+	arch_parse_crashkernel();
+
 #ifdef CONFIG_ACPI_TABLE_UPGRADE
 	acpi_table_upgrade();
 #endif
@@ -289,6 +353,15 @@ static void __init resource_init(void)
 		request_resource(res, &data_resource);
 		request_resource(res, &bss_resource);
 	}
+
+#ifdef CONFIG_KEXEC
+	if (crashk_res.start < crashk_res.end) {
+		insert_resource(&iomem_resource, &crashk_res);
+		pr_info("Reserving %ldMB of memory at %ldMB for crashkernel\n",
+			(unsigned long)((crashk_res.end - crashk_res.start + 1) >> 20),
+			(unsigned long)(crashk_res.start  >> 20));
+	}
+#endif
 }
 
 static int __init reserve_memblock_reserved_regions(void)
@@ -348,10 +421,11 @@ void __init setup_arch(char **cmdline_p)
 	init_environ();
 	efi_init();
 	memblock_init();
+	pagetable_init();
 	parse_early_param();
+	reserve_initrd_mem();
 
 	platform_init();
-	pagetable_init();
 	arch_mem_init(cmdline_p);
 
 	resource_init();

arch/loongarch/kernel/smp.c

@@ -240,11 +240,6 @@ void loongson3_smp_finish(void)
 
 #ifdef CONFIG_HOTPLUG_CPU
 
-static bool io_master(int cpu)
-{
-	return test_bit(cpu, &loongson_sysconf.cores_io_master);
-}
-
 int loongson3_cpu_disable(void)
 {
 	unsigned long flags;

arch/loongarch/kernel/sysrq.c

+// SPDX-License-Identifier: GPL-2.0
+/*
+ * LoongArch specific sysrq operations.
+ *
+ * Copyright (C) 2020-2022 Loongson Technology Corporation Limited
+ */
+#include <linux/init.h>
+#include <linux/smp.h>
+#include <linux/spinlock.h>
+#include <linux/sysrq.h>
+#include <linux/workqueue.h>
+
+#include <asm/cpu-features.h>
+#include <asm/tlb.h>
+
+/*
+ * Dump TLB entries on all CPUs.
+ */
+
+static DEFINE_SPINLOCK(show_lock);
+
+static void sysrq_tlbdump_single(void *dummy)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&show_lock, flags);
+
+	pr_info("CPU%d:\n", smp_processor_id());
+	dump_tlb_regs();
+	pr_info("\n");
+	dump_tlb_all();
+	pr_info("\n");
+
+	spin_unlock_irqrestore(&show_lock, flags);
+}
+
+#ifdef CONFIG_SMP
+static void sysrq_tlbdump_othercpus(struct work_struct *dummy)
+{
+	smp_call_function(sysrq_tlbdump_single, NULL, 0);
+}
+
+static DECLARE_WORK(sysrq_tlbdump, sysrq_tlbdump_othercpus);
+#endif
+
+static void sysrq_handle_tlbdump(int key)
+{
+	sysrq_tlbdump_single(NULL);
+#ifdef CONFIG_SMP
+	schedule_work(&sysrq_tlbdump);
+#endif
+}
+
+static struct sysrq_key_op sysrq_tlbdump_op = {
+	.handler        = sysrq_handle_tlbdump,
+	.help_msg       = "show-tlbs(x)",
+	.action_msg     = "Show TLB entries",
+	.enable_mask	= SYSRQ_ENABLE_DUMP,
+};
+
+static int __init loongarch_sysrq_init(void)
+{
+	return register_sysrq_key('x', &sysrq_tlbdump_op);
+}
+arch_initcall(loongarch_sysrq_init);

arch/loongarch/kernel/topology.c

@@ -5,6 +5,7 @@
 #include <linux/node.h>
 #include <linux/nodemask.h>
 #include <linux/percpu.h>
+#include <asm/bootinfo.h>
 
 static DEFINE_PER_CPU(struct cpu, cpu_devices);
 
@@ -40,7 +41,7 @@ static int __init topology_init(void)
 	for_each_present_cpu(i) {
 		struct cpu *c = &per_cpu(cpu_devices, i);
 
-		c->hotpluggable = !!i;
+		c->hotpluggable = !io_master(i);
 		ret = register_cpu(c, i);
 		if (ret < 0)
 			pr_warn("topology_init: register_cpu %d failed (%d)\n", i, ret);

arch/loongarch/kernel/traps.c

@@ -10,6 +10,7 @@
 #include <linux/entry-common.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
+#include <linux/kexec.h>
 #include <linux/module.h>
 #include <linux/extable.h>
 #include <linux/mm.h>
@@ -246,6 +247,9 @@ void __noreturn die(const char *str, struct pt_regs *regs)
 
 	oops_exit();
 
+	if (regs && kexec_should_crash(current))
+		crash_kexec(regs);
+
 	if (in_interrupt())
 		panic("Fatal exception in interrupt");
 
@@ -374,6 +378,29 @@ asmlinkage void noinstr do_ale(struct pt_regs *regs)
 	irqentry_exit(regs, state);
 }
 
+#ifdef CONFIG_GENERIC_BUG
+int is_valid_bugaddr(unsigned long addr)
+{
+	return 1;
+}
+#endif /* CONFIG_GENERIC_BUG */
+
+static void bug_handler(struct pt_regs *regs)
+{
+	switch (report_bug(regs->csr_era, regs)) {
+	case BUG_TRAP_TYPE_BUG:
+	case BUG_TRAP_TYPE_NONE:
+		die_if_kernel("Oops - BUG", regs);
+		force_sig(SIGTRAP);
+		break;
+
+	case BUG_TRAP_TYPE_WARN:
+		/* Skip the BUG instruction and continue */
+		regs->csr_era += LOONGARCH_INSN_SIZE;
+		break;
+	}
+}
+
 asmlinkage void noinstr do_bp(struct pt_regs *regs)
 {
 	bool user = user_mode(regs);
@@ -427,8 +454,7 @@ asmlinkage void noinstr do_bp(struct pt_regs *regs)
 
 	switch (bcode) {
 	case BRK_BUG:
-		die_if_kernel("Kernel bug detected", regs);
-		force_sig(SIGTRAP);
+		bug_handler(regs);
 		break;
 	case BRK_DIVZERO:
 		die_if_kernel("Break instruction in kernel code", regs);
@@ -620,9 +646,6 @@ asmlinkage void noinstr do_vint(struct pt_regs *regs, unsigned long sp)
 	irqentry_exit(regs, state);
 }
 
-extern void tlb_init(int cpu);
-extern void cache_error_setup(void);
-
 unsigned long eentry;
 unsigned long tlbrentry;
 

arch/loongarch/kernel/vmlinux.lds.S

@@ -55,6 +55,10 @@ SECTIONS
 
 	EXCEPTION_TABLE(16)
 
+	.got : ALIGN(16) { *(.got) }
+	.plt : ALIGN(16) { *(.plt) }
+	.got.plt : ALIGN(16) { *(.got.plt) }
+
 	. = ALIGN(PECOFF_SEGMENT_ALIGN);
 	__init_begin = .;
 	__inittext_begin = .;

arch/loongarch/mm/cache.c

@@ -6,8 +6,8 @@
  * Copyright (C) 1994 - 2003, 06, 07 by Ralf Baechle (ralf@linux-mips.org)
  * Copyright (C) 2007 MIPS Technologies, Inc.
  */
+#include <linux/cacheinfo.h>
 #include <linux/export.h>
-#include <linux/fcntl.h>
 #include <linux/fs.h>
 #include <linux/highmem.h>
 #include <linux/kernel.h>
@@ -16,14 +16,21 @@
 #include <linux/sched.h>
 #include <linux/syscalls.h>
 
+#include <asm/bootinfo.h>
 #include <asm/cacheflush.h>
 #include <asm/cpu.h>
 #include <asm/cpu-features.h>
-#include <asm/dma.h>
 #include <asm/loongarch.h>
+#include <asm/numa.h>
 #include <asm/processor.h>
 #include <asm/setup.h>
 
+void cache_error_setup(void)
+{
+	extern char __weak except_vec_cex;
+	set_merr_handler(0x0, &except_vec_cex, 0x80);
+}
+
 /*
  * LoongArch maintains ICache/DCache coherency by hardware,
  * we just need "ibar" to avoid instruction hazard here.
@@ -34,109 +41,121 @@ void local_flush_icache_range(unsigned long start, unsigned long end)
 }
 EXPORT_SYMBOL(local_flush_icache_range);
 
-void cache_error_setup(void)
-{
-	extern char __weak except_vec_cex;
-	set_merr_handler(0x0, &except_vec_cex, 0x80);
-}
-
-static unsigned long icache_size __read_mostly;
-static unsigned long dcache_size __read_mostly;
-static unsigned long vcache_size __read_mostly;
-static unsigned long scache_size __read_mostly;
-
-static char *way_string[] = { NULL, "direct mapped", "2-way",
-	"3-way", "4-way", "5-way", "6-way", "7-way", "8-way",
-	"9-way", "10-way", "11-way", "12-way",
-	"13-way", "14-way", "15-way", "16-way",
-};
-
-static void probe_pcache(void)
+static void flush_cache_leaf(unsigned int leaf)
 {
-	struct cpuinfo_loongarch *c = &current_cpu_data;
-	unsigned int lsize, sets, ways;
-	unsigned int config;
-
-	config = read_cpucfg(LOONGARCH_CPUCFG17);
-	lsize = 1 << ((config & CPUCFG17_L1I_SIZE_M) >> CPUCFG17_L1I_SIZE);
-	sets  = 1 << ((config & CPUCFG17_L1I_SETS_M) >> CPUCFG17_L1I_SETS);
-	ways  = ((config & CPUCFG17_L1I_WAYS_M) >> CPUCFG17_L1I_WAYS) + 1;
-
-	c->icache.linesz = lsize;
-	c->icache.sets = sets;
-	c->icache.ways = ways;
-	icache_size = sets * ways * lsize;
-	c->icache.waysize = icache_size / c->icache.ways;
-
-	config = read_cpucfg(LOONGARCH_CPUCFG18);
-	lsize = 1 << ((config & CPUCFG18_L1D_SIZE_M) >> CPUCFG18_L1D_SIZE);
-	sets  = 1 << ((config & CPUCFG18_L1D_SETS_M) >> CPUCFG18_L1D_SETS);
-	ways  = ((config & CPUCFG18_L1D_WAYS_M) >> CPUCFG18_L1D_WAYS) + 1;
-
-	c->dcache.linesz = lsize;
-	c->dcache.sets = sets;
-	c->dcache.ways = ways;
-	dcache_size = sets * ways * lsize;
-	c->dcache.waysize = dcache_size / c->dcache.ways;
-
-	c->options |= LOONGARCH_CPU_PREFETCH;
-
-	pr_info("Primary instruction cache %ldkB, %s, %s, linesize %d bytes.\n",
-		icache_size >> 10, way_string[c->icache.ways], "VIPT", c->icache.linesz);
-
-	pr_info("Primary data cache %ldkB, %s, %s, %s, linesize %d bytes\n",
-		dcache_size >> 10, way_string[c->dcache.ways], "VIPT", "no aliases", c->dcache.linesz);
+	int i, j, nr_nodes;
+	uint64_t addr = CSR_DMW0_BASE;
+	struct cache_desc *cdesc = current_cpu_data.cache_leaves + leaf;
+
+	nr_nodes = cache_private(cdesc) ? 1 : loongson_sysconf.nr_nodes;
+
+	do {
+		for (i = 0; i < cdesc->sets; i++) {
+			for (j = 0; j < cdesc->ways; j++) {
+				flush_cache_line(leaf, addr);
+				addr++;
+			}
+
+			addr -= cdesc->ways;
+			addr += cdesc->linesz;
+		}
+		addr += (1ULL << NODE_ADDRSPACE_SHIFT);
+	} while (--nr_nodes > 0);
 }
 
-static void probe_vcache(void)
+asmlinkage __visible void __flush_cache_all(void)
 {
-	struct cpuinfo_loongarch *c = &current_cpu_data;
-	unsigned int lsize, sets, ways;
-	unsigned int config;
-
-	config = read_cpucfg(LOONGARCH_CPUCFG19);
-	lsize = 1 << ((config & CPUCFG19_L2_SIZE_M) >> CPUCFG19_L2_SIZE);
-	sets  = 1 << ((config & CPUCFG19_L2_SETS_M) >> CPUCFG19_L2_SETS);
-	ways  = ((config & CPUCFG19_L2_WAYS_M) >> CPUCFG19_L2_WAYS) + 1;
-
-	c->vcache.linesz = lsize;
-	c->vcache.sets = sets;
-	c->vcache.ways = ways;
-	vcache_size = lsize * sets * ways;
-	c->vcache.waysize = vcache_size / c->vcache.ways;
-
-	pr_info("Unified victim cache %ldkB %s, linesize %d bytes.\n",
-		vcache_size >> 10, way_string[c->vcache.ways], c->vcache.linesz);
+	int leaf;
+	struct cache_desc *cdesc = current_cpu_data.cache_leaves;
+	unsigned int cache_present = current_cpu_data.cache_leaves_present;
+
+	leaf = cache_present - 1;
+	if (cache_inclusive(cdesc + leaf)) {
+		flush_cache_leaf(leaf);
+		return;
+	}
+
+	for (leaf = 0; leaf < cache_present; leaf++)
+		flush_cache_leaf(leaf);
 }
 
-static void probe_scache(void)
-{
-	struct cpuinfo_loongarch *c = &current_cpu_data;
-	unsigned int lsize, sets, ways;
-	unsigned int config;
-
-	config = read_cpucfg(LOONGARCH_CPUCFG20);
-	lsize = 1 << ((config & CPUCFG20_L3_SIZE_M) >> CPUCFG20_L3_SIZE);
-	sets  = 1 << ((config & CPUCFG20_L3_SETS_M) >> CPUCFG20_L3_SETS);
-	ways  = ((config & CPUCFG20_L3_WAYS_M) >> CPUCFG20_L3_WAYS) + 1;
-
-	c->scache.linesz = lsize;
-	c->scache.sets = sets;
-	c->scache.ways = ways;
-	/* 4 cores. scaches are shared */
-	scache_size = lsize * sets * ways;
-	c->scache.waysize = scache_size / c->scache.ways;
-
-	pr_info("Unified secondary cache %ldkB %s, linesize %d bytes.\n",
-		scache_size >> 10, way_string[c->scache.ways], c->scache.linesz);
-}
+#define L1IUPRE		(1 << 0)
+#define L1IUUNIFY	(1 << 1)
+#define L1DPRE		(1 << 2)
+
+#define LXIUPRE		(1 << 0)
+#define LXIUUNIFY	(1 << 1)
+#define LXIUPRIV	(1 << 2)
+#define LXIUINCL	(1 << 3)
+#define LXDPRE		(1 << 4)
+#define LXDPRIV		(1 << 5)
+#define LXDINCL		(1 << 6)
+
+#define populate_cache_properties(cfg0, cdesc, level, leaf)				\
+do {											\
+	unsigned int cfg1;								\
+											\
+	cfg1 = read_cpucfg(LOONGARCH_CPUCFG17 + leaf);					\
+	if (level == 1)	{								\
+		cdesc->flags |= CACHE_PRIVATE;						\
+	} else {									\
+		if (cfg0 & LXIUPRIV)							\
+			cdesc->flags |= CACHE_PRIVATE;					\
+		if (cfg0 & LXIUINCL)							\
+			cdesc->flags |= CACHE_INCLUSIVE;				\
+	}										\
+	cdesc->level = level;								\
+	cdesc->flags |= CACHE_PRESENT;							\
+	cdesc->ways = ((cfg1 & CPUCFG_CACHE_WAYS_M) >> CPUCFG_CACHE_WAYS) + 1;		\
+	cdesc->sets = 1 << ((cfg1 & CPUCFG_CACHE_SETS_M) >> CPUCFG_CACHE_SETS);		\
+	cdesc->linesz = 1 << ((cfg1 & CPUCFG_CACHE_LSIZE_M) >> CPUCFG_CACHE_LSIZE);	\
+	cdesc++; leaf++;								\
+} while (0)
 
 void cpu_cache_init(void)
 {
-	probe_pcache();
-	probe_vcache();
-	probe_scache();
-
+	unsigned int leaf = 0, level = 1;
+	unsigned int config = read_cpucfg(LOONGARCH_CPUCFG16);
+	struct cache_desc *cdesc = current_cpu_data.cache_leaves;
+
+	if (config & L1IUPRE) {
+		if (config & L1IUUNIFY)
+			cdesc->type = CACHE_TYPE_UNIFIED;
+		else
+			cdesc->type = CACHE_TYPE_INST;
+		populate_cache_properties(config, cdesc, level, leaf);
+	}
+
+	if (config & L1DPRE) {
+		cdesc->type = CACHE_TYPE_DATA;
+		populate_cache_properties(config, cdesc, level, leaf);
+	}
+
+	config = config >> 3;
+	for (level = 2; level <= CACHE_LEVEL_MAX; level++) {
+		if (!config)
+			break;
+
+		if (config & LXIUPRE) {
+			if (config & LXIUUNIFY)
+				cdesc->type = CACHE_TYPE_UNIFIED;
+			else
+				cdesc->type = CACHE_TYPE_INST;
+			populate_cache_properties(config, cdesc, level, leaf);
+		}
+
+		if (config & LXDPRE) {
+			cdesc->type = CACHE_TYPE_DATA;
+			populate_cache_properties(config, cdesc, level, leaf);
+		}
+
+		config = config >> 7;
+	}
+
+	BUG_ON(leaf > CACHE_LEAVES_MAX);
+
+	current_cpu_data.cache_leaves_present = leaf;
+	current_cpu_data.options |= LOONGARCH_CPU_PREFETCH;
 	shm_align_mask = PAGE_SIZE - 1;
 }
 

arch/loongarch/mm/init.c

@@ -152,6 +152,70 @@ EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid);
 #endif
 #endif
 
+static pte_t *fixmap_pte(unsigned long addr)
+{
+	pgd_t *pgd;
+	p4d_t *p4d;
+	pud_t *pud;
+	pmd_t *pmd;
+
+	pgd = pgd_offset_k(addr);
+	p4d = p4d_offset(pgd, addr);
+
+	if (pgd_none(*pgd)) {
+		pud_t *new __maybe_unused;
+
+		new = memblock_alloc_low(PAGE_SIZE, PAGE_SIZE);
+		pgd_populate(&init_mm, pgd, new);
+#ifndef __PAGETABLE_PUD_FOLDED
+		pud_init((unsigned long)new, (unsigned long)invalid_pmd_table);
+#endif
+	}
+
+	pud = pud_offset(p4d, addr);
+	if (pud_none(*pud)) {
+		pmd_t *new __maybe_unused;
+
+		new = memblock_alloc_low(PAGE_SIZE, PAGE_SIZE);
+		pud_populate(&init_mm, pud, new);
+#ifndef __PAGETABLE_PMD_FOLDED
+		pmd_init((unsigned long)new, (unsigned long)invalid_pte_table);
+#endif
+	}
+
+	pmd = pmd_offset(pud, addr);
+	if (pmd_none(*pmd)) {
+		pte_t *new __maybe_unused;
+
+		new = memblock_alloc_low(PAGE_SIZE, PAGE_SIZE);
+		pmd_populate_kernel(&init_mm, pmd, new);
+	}
+
+	return pte_offset_kernel(pmd, addr);
+}
+
+void __init __set_fixmap(enum fixed_addresses idx,
+			       phys_addr_t phys, pgprot_t flags)
+{
+	unsigned long addr = __fix_to_virt(idx);
+	pte_t *ptep;
+
+	BUG_ON(idx <= FIX_HOLE || idx >= __end_of_fixed_addresses);
+
+	ptep = fixmap_pte(addr);
+	if (!pte_none(*ptep)) {
+		pte_ERROR(*ptep);
+		return;
+	}
+
+	if (pgprot_val(flags))
+		set_pte(ptep, pfn_pte(phys >> PAGE_SHIFT, flags));
+	else {
+		pte_clear(&init_mm, addr, ptep);
+		flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
+	}
+}
+
 /*
  * Align swapper_pg_dir in to 64K, allows its address to be loaded
  * with a single LUI instruction in the TLB handlers.  If we used

arch/loongarch/mm/mmap.c

@@ -3,6 +3,8 @@
  * Copyright (C) 2020-2022 Loongson Technology Corporation Limited
  */
 #include <linux/export.h>
+#include <linux/io.h>
+#include <linux/memblock.h>
 #include <linux/mm.h>
 #include <linux/mman.h>
 
@@ -116,3 +118,30 @@ int __virt_addr_valid(volatile void *kaddr)
 	return pfn_valid(PFN_DOWN(PHYSADDR(kaddr)));
 }
 EXPORT_SYMBOL_GPL(__virt_addr_valid);
+
+/*
+ * You really shouldn't be using read() or write() on /dev/mem.  This might go
+ * away in the future.
+ */
+int valid_phys_addr_range(phys_addr_t addr, size_t size)
+{
+	/*
+	 * Check whether addr is covered by a memory region without the
+	 * MEMBLOCK_NOMAP attribute, and whether that region covers the
+	 * entire range. In theory, this could lead to false negatives
+	 * if the range is covered by distinct but adjacent memory regions
+	 * that only differ in other attributes. However, few of such
+	 * attributes have been defined, and it is debatable whether it
+	 * follows that /dev/mem read() calls should be able traverse
+	 * such boundaries.
+	 */
+	return memblock_is_region_memory(addr, size) && memblock_is_map_memory(addr);
+}
+
+/*
+ * Do not allow /dev/mem mappings beyond the supported physical range.
+ */
+int valid_mmap_phys_addr_range(unsigned long pfn, size_t size)
+{
+	return !(((pfn << PAGE_SHIFT) + size) & ~(GENMASK_ULL(cpu_pabits, 0)));
+}

arch/loongarch/mm/tlb.c

@@ -258,7 +258,7 @@ extern long exception_handlers[VECSIZE * 128 / sizeof(long)];
 void setup_tlb_handler(int cpu)
 {
 	setup_ptwalker();
-	output_pgtable_bits_defines();
+	local_flush_tlb_all();
 
 	/* The tlb handlers are generated only once */
 	if (cpu == 0) {
@@ -301,6 +301,7 @@ void tlb_init(int cpu)
 	write_csr_pagesize(PS_DEFAULT_SIZE);
 	write_csr_stlbpgsize(PS_DEFAULT_SIZE);
 	write_csr_tlbrefill_pagesize(PS_DEFAULT_SIZE);
+
 	setup_tlb_handler(cpu);
-	local_flush_tlb_all();
+	output_pgtable_bits_defines();
 }

arch/loongarch/mm/tlbex.S

@@ -10,15 +10,20 @@
 #include <asm/regdef.h>
 #include <asm/stackframe.h>
 
+#define PTRS_PER_PGD_BITS	(PAGE_SHIFT - 3)
+#define PTRS_PER_PUD_BITS	(PAGE_SHIFT - 3)
+#define PTRS_PER_PMD_BITS	(PAGE_SHIFT - 3)
+#define PTRS_PER_PTE_BITS	(PAGE_SHIFT - 3)
+
 	.macro tlb_do_page_fault, write
 	SYM_FUNC_START(tlb_do_page_fault_\write)
 	SAVE_ALL
-	csrrd	a2, LOONGARCH_CSR_BADV
-	move	a0, sp
-	REG_S	a2, sp, PT_BVADDR
-	li.w	a1, \write
-	la.abs	t0, do_page_fault
-	jirl	ra, t0, 0
+	csrrd		a2, LOONGARCH_CSR_BADV
+	move		a0, sp
+	REG_S		a2, sp, PT_BVADDR
+	li.w		a1, \write
+	la.abs		t0, do_page_fault
+	jirl		ra, t0, 0
 	RESTORE_ALL_AND_RET
 	SYM_FUNC_END(tlb_do_page_fault_\write)
 	.endm
@@ -29,133 +34,115 @@
 SYM_FUNC_START(handle_tlb_protect)
 	BACKUP_T0T1
 	SAVE_ALL
-	move	a0, sp
-	move	a1, zero
-	csrrd	a2, LOONGARCH_CSR_BADV
-	REG_S	a2, sp, PT_BVADDR
-	la.abs	t0, do_page_fault
-	jirl	ra, t0, 0
+	move		a0, sp
+	move		a1, zero
+	csrrd		a2, LOONGARCH_CSR_BADV
+	REG_S		a2, sp, PT_BVADDR
+	la.abs		t0, do_page_fault
+	jirl		ra, t0, 0
 	RESTORE_ALL_AND_RET
 SYM_FUNC_END(handle_tlb_protect)
 
 SYM_FUNC_START(handle_tlb_load)
-	csrwr	t0, EXCEPTION_KS0
-	csrwr	t1, EXCEPTION_KS1
-	csrwr	ra, EXCEPTION_KS2
+	csrwr		t0, EXCEPTION_KS0
+	csrwr		t1, EXCEPTION_KS1
+	csrwr		ra, EXCEPTION_KS2
 
 	/*
 	 * The vmalloc handling is not in the hotpath.
 	 */
-	csrrd	t0, LOONGARCH_CSR_BADV
-	bltz	t0, vmalloc_load
-	csrrd	t1, LOONGARCH_CSR_PGDL
+	csrrd		t0, LOONGARCH_CSR_BADV
+	bltz		t0, vmalloc_load
+	csrrd		t1, LOONGARCH_CSR_PGDL
 
 vmalloc_done_load:
 	/* Get PGD offset in bytes */
-	srli.d	t0, t0, PGDIR_SHIFT
-	andi	t0, t0, (PTRS_PER_PGD - 1)
-	slli.d	t0, t0, 3
-	add.d	t1, t1, t0
+	bstrpick.d	ra, t0, PTRS_PER_PGD_BITS + PGDIR_SHIFT - 1, PGDIR_SHIFT
+	alsl.d		t1, ra, t1, 3
 #if CONFIG_PGTABLE_LEVELS > 3
-	csrrd	t0, LOONGARCH_CSR_BADV
-	ld.d	t1, t1, 0
-	srli.d	t0, t0, PUD_SHIFT
-	andi	t0, t0, (PTRS_PER_PUD - 1)
-	slli.d	t0, t0, 3
-	add.d	t1, t1, t0
+	ld.d		t1, t1, 0
+	bstrpick.d	ra, t0, PTRS_PER_PUD_BITS + PUD_SHIFT - 1, PUD_SHIFT
+	alsl.d		t1, ra, t1, 3
 #endif
 #if CONFIG_PGTABLE_LEVELS > 2
-	csrrd	t0, LOONGARCH_CSR_BADV
-	ld.d	t1, t1, 0
-	srli.d	t0, t0, PMD_SHIFT
-	andi	t0, t0, (PTRS_PER_PMD - 1)
-	slli.d	t0, t0, 3
-	add.d	t1, t1, t0
+	ld.d		t1, t1, 0
+	bstrpick.d	ra, t0, PTRS_PER_PMD_BITS + PMD_SHIFT - 1, PMD_SHIFT
+	alsl.d		t1, ra, t1, 3
 #endif
-	ld.d	ra, t1, 0
+	ld.d		ra, t1, 0
 
 	/*
 	 * For huge tlb entries, pmde doesn't contain an address but
 	 * instead contains the tlb pte. Check the PAGE_HUGE bit and
 	 * see if we need to jump to huge tlb processing.
 	 */
-	andi	t0, ra, _PAGE_HUGE
-	bnez	t0, tlb_huge_update_load
+	rotri.d		ra, ra, _PAGE_HUGE_SHIFT + 1
+	bltz		ra, tlb_huge_update_load
 
-	csrrd	t0, LOONGARCH_CSR_BADV
-	srli.d	t0, t0, PAGE_SHIFT
-	andi	t0, t0, (PTRS_PER_PTE - 1)
-	slli.d	t0, t0, _PTE_T_LOG2
-	add.d	t1, ra, t0
+	rotri.d		ra, ra, 64 - (_PAGE_HUGE_SHIFT + 1)
+	bstrpick.d	t0, t0, PTRS_PER_PTE_BITS + PAGE_SHIFT - 1, PAGE_SHIFT
+	alsl.d		t1, t0, ra, _PTE_T_LOG2
 
 #ifdef CONFIG_SMP
 smp_pgtable_change_load:
-#endif
-#ifdef CONFIG_SMP
-	ll.d	t0, t1, 0
+	ll.d		t0, t1, 0
 #else
-	ld.d	t0, t1, 0
+	ld.d		t0, t1, 0
 #endif
-	tlbsrch
-
-	srli.d	ra, t0, _PAGE_PRESENT_SHIFT
-	andi	ra, ra, 1
-	beqz	ra, nopage_tlb_load
+	andi		ra, t0, _PAGE_PRESENT
+	beqz		ra, nopage_tlb_load
 
-	ori	t0, t0, _PAGE_VALID
+	ori		t0, t0, _PAGE_VALID
 #ifdef CONFIG_SMP
-	sc.d	t0, t1, 0
-	beqz	t0, smp_pgtable_change_load
+	sc.d		t0, t1, 0
+	beqz		t0, smp_pgtable_change_load
 #else
-	st.d	t0, t1, 0
+	st.d		t0, t1, 0
 #endif
-	ori	t1, t1, 8
-	xori	t1, t1, 8
-	ld.d	t0, t1, 0
-	ld.d	t1, t1, 8
-	csrwr	t0, LOONGARCH_CSR_TLBELO0
-	csrwr	t1, LOONGARCH_CSR_TLBELO1
+	tlbsrch
+	bstrins.d	t1, zero, 3, 3
+	ld.d		t0, t1, 0
+	ld.d		t1, t1, 8
+	csrwr		t0, LOONGARCH_CSR_TLBELO0
+	csrwr		t1, LOONGARCH_CSR_TLBELO1
 	tlbwr
-leave_load:
-	csrrd	t0, EXCEPTION_KS0
-	csrrd	t1, EXCEPTION_KS1
-	csrrd	ra, EXCEPTION_KS2
+
+	csrrd		t0, EXCEPTION_KS0
+	csrrd		t1, EXCEPTION_KS1
+	csrrd		ra, EXCEPTION_KS2
 	ertn
+
 #ifdef CONFIG_64BIT
 vmalloc_load:
-	la.abs	t1, swapper_pg_dir
-	b	vmalloc_done_load
+	la.abs		t1, swapper_pg_dir
+	b		vmalloc_done_load
 #endif
 
-	/*
-	 * This is the entry point when build_tlbchange_handler_head
-	 * spots a huge page.
-	 */
+	/* This is the entry point of a huge page. */
 tlb_huge_update_load:
 #ifdef CONFIG_SMP
-	ll.d	t0, t1, 0
-#else
-	ld.d	t0, t1, 0
+	ll.d		ra, t1, 0
 #endif
-	srli.d	ra, t0, _PAGE_PRESENT_SHIFT
-	andi	ra, ra, 1
-	beqz	ra, nopage_tlb_load
-	tlbsrch
+	andi		t0, ra, _PAGE_PRESENT
+	beqz		t0, nopage_tlb_load
 
-	ori	t0, t0, _PAGE_VALID
 #ifdef CONFIG_SMP
-	sc.d	t0, t1, 0
-	beqz	t0, tlb_huge_update_load
-	ld.d	t0, t1, 0
+	ori		t0, ra, _PAGE_VALID
+	sc.d		t0, t1, 0
+	beqz		t0, tlb_huge_update_load
+	ori		t0, ra, _PAGE_VALID
 #else
-	st.d	t0, t1, 0
+	rotri.d		ra, ra, 64 - (_PAGE_HUGE_SHIFT + 1)
+	ori		t0, ra, _PAGE_VALID
+	st.d		t0, t1, 0
 #endif
+	tlbsrch
 	addu16i.d	t1, zero, -(CSR_TLBIDX_EHINV >> 16)
 	addi.d		ra, t1, 0
 	csrxchg		ra, t1, LOONGARCH_CSR_TLBIDX
 	tlbwr
 
-	csrxchg	zero, t1, LOONGARCH_CSR_TLBIDX
+	csrxchg		zero, t1, LOONGARCH_CSR_TLBIDX
 
 	/*
 	 * A huge PTE describes an area the size of the
@@ -167,21 +154,20 @@ tlb_huge_update_load:
 	 * address space.
 	 */
 	/* Huge page: Move Global bit */
-	xori	t0, t0, _PAGE_HUGE
-	lu12i.w	t1, _PAGE_HGLOBAL >> 12
-	and	t1, t0, t1
-	srli.d	t1, t1, (_PAGE_HGLOBAL_SHIFT - _PAGE_GLOBAL_SHIFT)
-	or	t0, t0, t1
+	xori		t0, t0, _PAGE_HUGE
+	lu12i.w		t1, _PAGE_HGLOBAL >> 12
+	and		t1, t0, t1
+	srli.d		t1, t1, (_PAGE_HGLOBAL_SHIFT - _PAGE_GLOBAL_SHIFT)
+	or		t0, t0, t1
 
-	addi.d	ra, t0, 0
-	csrwr	t0, LOONGARCH_CSR_TLBELO0
-	addi.d	t0, ra, 0
+	move		ra, t0
+	csrwr		ra, LOONGARCH_CSR_TLBELO0
 
 	/* Convert to entrylo1 */
-	addi.d	t1, zero, 1
-	slli.d	t1, t1, (HPAGE_SHIFT - 1)
-	add.d	t0, t0, t1
-	csrwr	t0, LOONGARCH_CSR_TLBELO1
+	addi.d		t1, zero, 1
+	slli.d		t1, t1, (HPAGE_SHIFT - 1)
+	add.d		t0, t0, t1
+	csrwr		t0, LOONGARCH_CSR_TLBELO1
 
 	/* Set huge page tlb entry size */
 	addu16i.d	t0, zero, (CSR_TLBIDX_PS >> 16)
@@ -194,136 +180,120 @@ tlb_huge_update_load:
 	addu16i.d	t1, zero, (PS_DEFAULT_SIZE << (CSR_TLBIDX_PS_SHIFT - 16))
 	csrxchg		t1, t0, LOONGARCH_CSR_TLBIDX
 
+	csrrd		t0, EXCEPTION_KS0
+	csrrd		t1, EXCEPTION_KS1
+	csrrd		ra, EXCEPTION_KS2
+	ertn
+
 nopage_tlb_load:
-	dbar	0
-	csrrd	ra, EXCEPTION_KS2
-	la.abs	t0, tlb_do_page_fault_0
-	jr	t0
+	dbar		0
+	csrrd		ra, EXCEPTION_KS2
+	la.abs		t0, tlb_do_page_fault_0
+	jr		t0
 SYM_FUNC_END(handle_tlb_load)
 
 SYM_FUNC_START(handle_tlb_store)
-	csrwr	t0, EXCEPTION_KS0
-	csrwr	t1, EXCEPTION_KS1
-	csrwr	ra, EXCEPTION_KS2
+	csrwr		t0, EXCEPTION_KS0
+	csrwr		t1, EXCEPTION_KS1
+	csrwr		ra, EXCEPTION_KS2
 
 	/*
 	 * The vmalloc handling is not in the hotpath.
 	 */
-	csrrd	t0, LOONGARCH_CSR_BADV
-	bltz	t0, vmalloc_store
-	csrrd	t1, LOONGARCH_CSR_PGDL
+	csrrd		t0, LOONGARCH_CSR_BADV
+	bltz		t0, vmalloc_store
+	csrrd		t1, LOONGARCH_CSR_PGDL
 
 vmalloc_done_store:
 	/* Get PGD offset in bytes */
-	srli.d	t0, t0, PGDIR_SHIFT
-	andi	t0, t0, (PTRS_PER_PGD - 1)
-	slli.d	t0, t0, 3
-	add.d	t1, t1, t0
-
+	bstrpick.d	ra, t0, PTRS_PER_PGD_BITS + PGDIR_SHIFT - 1, PGDIR_SHIFT
+	alsl.d		t1, ra, t1, 3
 #if CONFIG_PGTABLE_LEVELS > 3
-	csrrd	t0, LOONGARCH_CSR_BADV
-	ld.d	t1, t1, 0
-	srli.d	t0, t0, PUD_SHIFT
-	andi	t0, t0, (PTRS_PER_PUD - 1)
-	slli.d	t0, t0, 3
-	add.d	t1, t1, t0
+	ld.d		t1, t1, 0
+	bstrpick.d	ra, t0, PTRS_PER_PUD_BITS + PUD_SHIFT - 1, PUD_SHIFT
+	alsl.d		t1, ra, t1, 3
 #endif
 #if CONFIG_PGTABLE_LEVELS > 2
-	csrrd	t0, LOONGARCH_CSR_BADV
-	ld.d	t1, t1, 0
-	srli.d	t0, t0, PMD_SHIFT
-	andi	t0, t0, (PTRS_PER_PMD - 1)
-	slli.d	t0, t0, 3
-	add.d	t1, t1, t0
+	ld.d		t1, t1, 0
+	bstrpick.d	ra, t0, PTRS_PER_PMD_BITS + PMD_SHIFT - 1, PMD_SHIFT
+	alsl.d		t1, ra, t1, 3
 #endif
-	ld.d	ra, t1, 0
+	ld.d		ra, t1, 0
 
 	/*
 	 * For huge tlb entries, pmde doesn't contain an address but
 	 * instead contains the tlb pte. Check the PAGE_HUGE bit and
 	 * see if we need to jump to huge tlb processing.
 	 */
-	andi	t0, ra, _PAGE_HUGE
-	bnez	t0, tlb_huge_update_store
+	rotri.d		ra, ra, _PAGE_HUGE_SHIFT + 1
+	bltz		ra, tlb_huge_update_store
 
-	csrrd	t0, LOONGARCH_CSR_BADV
-	srli.d	t0, t0, PAGE_SHIFT
-	andi	t0, t0, (PTRS_PER_PTE - 1)
-	slli.d	t0, t0, _PTE_T_LOG2
-	add.d	t1, ra, t0
+	rotri.d		ra, ra, 64 - (_PAGE_HUGE_SHIFT + 1)
+	bstrpick.d	t0, t0, PTRS_PER_PTE_BITS + PAGE_SHIFT - 1, PAGE_SHIFT
+	alsl.d		t1, t0, ra, _PTE_T_LOG2
 
 #ifdef CONFIG_SMP
 smp_pgtable_change_store:
-#endif
-#ifdef CONFIG_SMP
-	ll.d	t0, t1, 0
+	ll.d		t0, t1, 0
 #else
-	ld.d	t0, t1, 0
+	ld.d		t0, t1, 0
 #endif
-	tlbsrch
-
-	srli.d	ra, t0, _PAGE_PRESENT_SHIFT
-	andi	ra, ra, ((_PAGE_PRESENT | _PAGE_WRITE) >> _PAGE_PRESENT_SHIFT)
-	xori	ra, ra, ((_PAGE_PRESENT | _PAGE_WRITE) >> _PAGE_PRESENT_SHIFT)
-	bnez	ra, nopage_tlb_store
+	andi		ra, t0, _PAGE_PRESENT | _PAGE_WRITE
+	xori		ra, ra, _PAGE_PRESENT | _PAGE_WRITE
+	bnez		ra, nopage_tlb_store
 
-	ori	t0, t0, (_PAGE_VALID | _PAGE_DIRTY | _PAGE_MODIFIED)
+	ori		t0, t0, (_PAGE_VALID | _PAGE_DIRTY | _PAGE_MODIFIED)
 #ifdef CONFIG_SMP
-	sc.d	t0, t1, 0
-	beqz	t0, smp_pgtable_change_store
+	sc.d		t0, t1, 0
+	beqz		t0, smp_pgtable_change_store
 #else
-	st.d	t0, t1, 0
+	st.d		t0, t1, 0
 #endif
-
-	ori	t1, t1, 8
-	xori	t1, t1, 8
-	ld.d	t0, t1, 0
-	ld.d	t1, t1, 8
-	csrwr	t0, LOONGARCH_CSR_TLBELO0
-	csrwr	t1, LOONGARCH_CSR_TLBELO1
+	tlbsrch
+	bstrins.d	t1, zero, 3, 3
+	ld.d		t0, t1, 0
+	ld.d		t1, t1, 8
+	csrwr		t0, LOONGARCH_CSR_TLBELO0
+	csrwr		t1, LOONGARCH_CSR_TLBELO1
 	tlbwr
-leave_store:
-	csrrd	t0, EXCEPTION_KS0
-	csrrd	t1, EXCEPTION_KS1
-	csrrd	ra, EXCEPTION_KS2
+
+	csrrd		t0, EXCEPTION_KS0
+	csrrd		t1, EXCEPTION_KS1
+	csrrd		ra, EXCEPTION_KS2
 	ertn
+
 #ifdef CONFIG_64BIT
 vmalloc_store:
-	la.abs	t1, swapper_pg_dir
-	b	vmalloc_done_store
+	la.abs		t1, swapper_pg_dir
+	b		vmalloc_done_store
 #endif
 
-	/*
-	 * This is the entry point when build_tlbchange_handler_head
-	 * spots a huge page.
-	 */
+	/* This is the entry point of a huge page. */
 tlb_huge_update_store:
 #ifdef CONFIG_SMP
-	ll.d	t0, t1, 0
-#else
-	ld.d	t0, t1, 0
+	ll.d		ra, t1, 0
 #endif
-	srli.d	ra, t0, _PAGE_PRESENT_SHIFT
-	andi	ra, ra, ((_PAGE_PRESENT | _PAGE_WRITE) >> _PAGE_PRESENT_SHIFT)
-	xori	ra, ra, ((_PAGE_PRESENT | _PAGE_WRITE) >> _PAGE_PRESENT_SHIFT)
-	bnez	ra, nopage_tlb_store
-
-	tlbsrch
-	ori	t0, t0, (_PAGE_VALID | _PAGE_DIRTY | _PAGE_MODIFIED)
+	andi		t0, ra, _PAGE_PRESENT | _PAGE_WRITE
+	xori		t0, t0, _PAGE_PRESENT | _PAGE_WRITE
+	bnez		t0, nopage_tlb_store
 
 #ifdef CONFIG_SMP
-	sc.d	t0, t1, 0
-	beqz	t0, tlb_huge_update_store
-	ld.d	t0, t1, 0
+	ori		t0, ra, (_PAGE_VALID | _PAGE_DIRTY | _PAGE_MODIFIED)
+	sc.d		t0, t1, 0
+	beqz		t0, tlb_huge_update_store
+	ori		t0, ra, (_PAGE_VALID | _PAGE_DIRTY | _PAGE_MODIFIED)
 #else
-	st.d	t0, t1, 0
+	rotri.d		ra, ra, 64 - (_PAGE_HUGE_SHIFT + 1)
+	ori		t0, ra, (_PAGE_VALID | _PAGE_DIRTY | _PAGE_MODIFIED)
+	st.d		t0, t1, 0
 #endif
+	tlbsrch
 	addu16i.d	t1, zero, -(CSR_TLBIDX_EHINV >> 16)
 	addi.d		ra, t1, 0
 	csrxchg		ra, t1, LOONGARCH_CSR_TLBIDX
 	tlbwr
 
-	csrxchg	zero, t1, LOONGARCH_CSR_TLBIDX
+	csrxchg		zero, t1, LOONGARCH_CSR_TLBIDX
 	/*
 	 * A huge PTE describes an area the size of the
 	 * configured huge page size. This is twice the
@@ -334,21 +304,20 @@ tlb_huge_update_store:
 	 * address space.
 	 */
 	/* Huge page: Move Global bit */
-	xori	t0, t0, _PAGE_HUGE
-	lu12i.w	t1, _PAGE_HGLOBAL >> 12
-	and	t1, t0, t1
-	srli.d	t1, t1, (_PAGE_HGLOBAL_SHIFT - _PAGE_GLOBAL_SHIFT)
-	or	t0, t0, t1
+	xori		t0, t0, _PAGE_HUGE
+	lu12i.w		t1, _PAGE_HGLOBAL >> 12
+	and		t1, t0, t1
+	srli.d		t1, t1, (_PAGE_HGLOBAL_SHIFT - _PAGE_GLOBAL_SHIFT)
+	or		t0, t0, t1
 
-	addi.d	ra, t0, 0
-	csrwr	t0, LOONGARCH_CSR_TLBELO0
-	addi.d	t0, ra, 0
+	move		ra, t0
+	csrwr		ra, LOONGARCH_CSR_TLBELO0
 
 	/* Convert to entrylo1 */
-	addi.d	t1, zero, 1
-	slli.d	t1, t1, (HPAGE_SHIFT - 1)
-	add.d	t0, t0, t1
-	csrwr	t0, LOONGARCH_CSR_TLBELO1
+	addi.d		t1, zero, 1
+	slli.d		t1, t1, (HPAGE_SHIFT - 1)
+	add.d		t0, t0, t1
+	csrwr		t0, LOONGARCH_CSR_TLBELO1
 
 	/* Set huge page tlb entry size */
 	addu16i.d	t0, zero, (CSR_TLBIDX_PS >> 16)
@@ -362,126 +331,110 @@ tlb_huge_update_store:
 	addu16i.d	t1, zero, (PS_DEFAULT_SIZE << (CSR_TLBIDX_PS_SHIFT - 16))
 	csrxchg		t1, t0, LOONGARCH_CSR_TLBIDX
 
+	csrrd		t0, EXCEPTION_KS0
+	csrrd		t1, EXCEPTION_KS1
+	csrrd		ra, EXCEPTION_KS2
+	ertn
+
 nopage_tlb_store:
-	dbar	0
-	csrrd	ra, EXCEPTION_KS2
-	la.abs	t0, tlb_do_page_fault_1
-	jr	t0
+	dbar		0
+	csrrd		ra, EXCEPTION_KS2
+	la.abs		t0, tlb_do_page_fault_1
+	jr		t0
 SYM_FUNC_END(handle_tlb_store)
 
 SYM_FUNC_START(handle_tlb_modify)
-	csrwr	t0, EXCEPTION_KS0
-	csrwr	t1, EXCEPTION_KS1
-	csrwr	ra, EXCEPTION_KS2
+	csrwr		t0, EXCEPTION_KS0
+	csrwr		t1, EXCEPTION_KS1
+	csrwr		ra, EXCEPTION_KS2
 
 	/*
 	 * The vmalloc handling is not in the hotpath.
 	 */
-	csrrd	t0, LOONGARCH_CSR_BADV
-	bltz	t0, vmalloc_modify
-	csrrd	t1, LOONGARCH_CSR_PGDL
+	csrrd		t0, LOONGARCH_CSR_BADV
+	bltz		t0, vmalloc_modify
+	csrrd		t1, LOONGARCH_CSR_PGDL
 
 vmalloc_done_modify:
 	/* Get PGD offset in bytes */
-	srli.d	t0, t0, PGDIR_SHIFT
-	andi	t0, t0, (PTRS_PER_PGD - 1)
-	slli.d	t0, t0, 3
-	add.d	t1, t1, t0
+	bstrpick.d	ra, t0, PTRS_PER_PGD_BITS + PGDIR_SHIFT - 1, PGDIR_SHIFT
+	alsl.d		t1, ra, t1, 3
 #if CONFIG_PGTABLE_LEVELS > 3
-	csrrd	t0, LOONGARCH_CSR_BADV
-	ld.d	t1, t1, 0
-	srli.d	t0, t0, PUD_SHIFT
-	andi	t0, t0, (PTRS_PER_PUD - 1)
-	slli.d	t0, t0, 3
-	add.d	t1, t1, t0
+	ld.d		t1, t1, 0
+	bstrpick.d	ra, t0, PTRS_PER_PUD_BITS + PUD_SHIFT - 1, PUD_SHIFT
+	alsl.d		t1, ra, t1, 3
 #endif
 #if CONFIG_PGTABLE_LEVELS > 2
-	csrrd	t0, LOONGARCH_CSR_BADV
-	ld.d	t1, t1, 0
-	srli.d	t0, t0, PMD_SHIFT
-	andi	t0, t0, (PTRS_PER_PMD - 1)
-	slli.d	t0, t0, 3
-	add.d	t1, t1, t0
+	ld.d		t1, t1, 0
+	bstrpick.d	ra, t0, PTRS_PER_PMD_BITS + PMD_SHIFT - 1, PMD_SHIFT
+	alsl.d		t1, ra, t1, 3
 #endif
-	ld.d	ra, t1, 0
+	ld.d		ra, t1, 0
 
 	/*
 	 * For huge tlb entries, pmde doesn't contain an address but
 	 * instead contains the tlb pte. Check the PAGE_HUGE bit and
 	 * see if we need to jump to huge tlb processing.
 	 */
-	andi	t0, ra, _PAGE_HUGE
-	bnez	t0, tlb_huge_update_modify
+	rotri.d		ra, ra, _PAGE_HUGE_SHIFT + 1
+	bltz		ra, tlb_huge_update_modify
 
-	csrrd	t0, LOONGARCH_CSR_BADV
-	srli.d	t0, t0, PAGE_SHIFT
-	andi	t0, t0, (PTRS_PER_PTE - 1)
-	slli.d	t0, t0, _PTE_T_LOG2
-	add.d	t1, ra, t0
+	rotri.d		ra, ra, 64 - (_PAGE_HUGE_SHIFT + 1)
+	bstrpick.d	t0, t0, PTRS_PER_PTE_BITS + PAGE_SHIFT - 1, PAGE_SHIFT
+	alsl.d		t1, t0, ra, _PTE_T_LOG2
 
 #ifdef CONFIG_SMP
 smp_pgtable_change_modify:
-#endif
-#ifdef CONFIG_SMP
-	ll.d	t0, t1, 0
+	ll.d		t0, t1, 0
 #else
-	ld.d	t0, t1, 0
+	ld.d		t0, t1, 0
 #endif
-	tlbsrch
-
-	srli.d	ra, t0, _PAGE_WRITE_SHIFT
-	andi	ra, ra, 1
-	beqz	ra, nopage_tlb_modify
+	andi		ra, t0, _PAGE_WRITE
+	beqz		ra, nopage_tlb_modify
 
-	ori	t0, t0, (_PAGE_VALID | _PAGE_DIRTY | _PAGE_MODIFIED)
+	ori		t0, t0, (_PAGE_VALID | _PAGE_DIRTY | _PAGE_MODIFIED)
 #ifdef CONFIG_SMP
-	sc.d	t0, t1, 0
-	beqz	t0, smp_pgtable_change_modify
+	sc.d		t0, t1, 0
+	beqz		t0, smp_pgtable_change_modify
 #else
-	st.d	t0, t1, 0
+	st.d		t0, t1, 0
 #endif
-	ori	t1, t1, 8
-	xori	t1, t1, 8
-	ld.d	t0, t1, 0
-	ld.d	t1, t1, 8
-	csrwr	t0, LOONGARCH_CSR_TLBELO0
-	csrwr	t1, LOONGARCH_CSR_TLBELO1
+	tlbsrch
+	bstrins.d	t1, zero, 3, 3
+	ld.d		t0, t1, 0
+	ld.d		t1, t1, 8
+	csrwr		t0, LOONGARCH_CSR_TLBELO0
+	csrwr		t1, LOONGARCH_CSR_TLBELO1
 	tlbwr
-leave_modify:
-	csrrd	t0, EXCEPTION_KS0
-	csrrd	t1, EXCEPTION_KS1
-	csrrd	ra, EXCEPTION_KS2
+
+	csrrd		t0, EXCEPTION_KS0
+	csrrd		t1, EXCEPTION_KS1
+	csrrd		ra, EXCEPTION_KS2
 	ertn
+
 #ifdef CONFIG_64BIT
 vmalloc_modify:
-	la.abs	t1, swapper_pg_dir
-	b	vmalloc_done_modify
+	la.abs		t1, swapper_pg_dir
+	b		vmalloc_done_modify
 #endif
 
-	/*
-	 * This is the entry point when
-	 * build_tlbchange_handler_head spots a huge page.
-	 */
+	/* This is the entry point of a huge page. */
 tlb_huge_update_modify:
 #ifdef CONFIG_SMP
-	ll.d	t0, t1, 0
-#else
-	ld.d	t0, t1, 0
+	ll.d		ra, t1, 0
 #endif
-
-	srli.d	ra, t0, _PAGE_WRITE_SHIFT
-	andi	ra, ra, 1
-	beqz	ra, nopage_tlb_modify
-
-	tlbsrch
-	ori	t0, t0, (_PAGE_VALID | _PAGE_DIRTY | _PAGE_MODIFIED)
+	andi		t0, ra, _PAGE_WRITE
+	beqz		t0, nopage_tlb_modify
 
 #ifdef CONFIG_SMP
-	sc.d	t0, t1, 0
-	beqz	t0, tlb_huge_update_modify
-	ld.d	t0, t1, 0
+	ori		t0, ra, (_PAGE_VALID | _PAGE_DIRTY | _PAGE_MODIFIED)
+	sc.d		t0, t1, 0
+	beqz		t0, tlb_huge_update_modify
+	ori		t0, ra, (_PAGE_VALID | _PAGE_DIRTY | _PAGE_MODIFIED)
 #else
-	st.d	t0, t1, 0
+	rotri.d		ra, ra, 64 - (_PAGE_HUGE_SHIFT + 1)
+	ori		t0, ra, (_PAGE_VALID | _PAGE_DIRTY | _PAGE_MODIFIED)
+	st.d		t0, t1, 0
 #endif
 	/*
 	 * A huge PTE describes an area the size of the
@@ -493,21 +446,20 @@ tlb_huge_update_modify:
 	 * address space.
 	 */
 	/* Huge page: Move Global bit */
-	xori	t0, t0, _PAGE_HUGE
-	lu12i.w	t1, _PAGE_HGLOBAL >> 12
-	and	t1, t0, t1
-	srli.d	t1, t1, (_PAGE_HGLOBAL_SHIFT - _PAGE_GLOBAL_SHIFT)
-	or	t0, t0, t1
+	xori		t0, t0, _PAGE_HUGE
+	lu12i.w		t1, _PAGE_HGLOBAL >> 12
+	and		t1, t0, t1
+	srli.d		t1, t1, (_PAGE_HGLOBAL_SHIFT - _PAGE_GLOBAL_SHIFT)
+	or		t0, t0, t1
 
-	addi.d	ra, t0, 0
-	csrwr	t0, LOONGARCH_CSR_TLBELO0
-	addi.d	t0, ra, 0
+	move		ra, t0
+	csrwr		ra, LOONGARCH_CSR_TLBELO0
 
 	/* Convert to entrylo1 */
-	addi.d	t1, zero, 1
-	slli.d	t1, t1, (HPAGE_SHIFT - 1)
-	add.d	t0, t0, t1
-	csrwr	t0, LOONGARCH_CSR_TLBELO1
+	addi.d		t1, zero, 1
+	slli.d		t1, t1, (HPAGE_SHIFT - 1)
+	add.d		t0, t0, t1
+	csrwr		t0, LOONGARCH_CSR_TLBELO1
 
 	/* Set huge page tlb entry size */
 	addu16i.d	t0, zero, (CSR_TLBIDX_PS >> 16)
@@ -521,26 +473,31 @@ tlb_huge_update_modify:
 	addu16i.d	t1, zero, (PS_DEFAULT_SIZE << (CSR_TLBIDX_PS_SHIFT - 16))
 	csrxchg		t1, t0, LOONGARCH_CSR_TLBIDX
 
+	csrrd		t0, EXCEPTION_KS0
+	csrrd		t1, EXCEPTION_KS1
+	csrrd		ra, EXCEPTION_KS2
+	ertn
+
 nopage_tlb_modify:
-	dbar	0
-	csrrd	ra, EXCEPTION_KS2
-	la.abs	t0, tlb_do_page_fault_1
-	jr	t0
+	dbar		0
+	csrrd		ra, EXCEPTION_KS2
+	la.abs		t0, tlb_do_page_fault_1
+	jr		t0
 SYM_FUNC_END(handle_tlb_modify)
 
 SYM_FUNC_START(handle_tlb_refill)
-	csrwr	t0, LOONGARCH_CSR_TLBRSAVE
-	csrrd	t0, LOONGARCH_CSR_PGD
-	lddir	t0, t0, 3
+	csrwr		t0, LOONGARCH_CSR_TLBRSAVE
+	csrrd		t0, LOONGARCH_CSR_PGD
+	lddir		t0, t0, 3
 #if CONFIG_PGTABLE_LEVELS > 3
-	lddir	t0, t0, 2
+	lddir		t0, t0, 2
 #endif
 #if CONFIG_PGTABLE_LEVELS > 2
-	lddir	t0, t0, 1
+	lddir		t0, t0, 1
 #endif
-	ldpte	t0, 0
-	ldpte	t0, 1
+	ldpte		t0, 0
+	ldpte		t0, 1
 	tlbfill
-	csrrd	t0, LOONGARCH_CSR_TLBRSAVE
+	csrrd		t0, LOONGARCH_CSR_TLBRSAVE
 	ertn
 SYM_FUNC_END(handle_tlb_refill)

arch/loongarch/net/Makefile

+# SPDX-License-Identifier: GPL-2.0-only
+#
+# Makefile for arch/loongarch/net
+#
+# Copyright (C) 2022 Loongson Technology Corporation Limited
+#
+obj-$(CONFIG_BPF_JIT) += bpf_jit.o

arch/loongarch/net/bpf_jit.c

+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * BPF JIT compiler for LoongArch
+ *
+ * Copyright (C) 2022 Loongson Technology Corporation Limited
+ */
+#include "bpf_jit.h"
+
+#define REG_TCC		LOONGARCH_GPR_A6
+#define TCC_SAVED	LOONGARCH_GPR_S5
+
+#define SAVE_RA		BIT(0)
+#define SAVE_TCC	BIT(1)
+
+static const int regmap[] = {
+	/* return value from in-kernel function, and exit value for eBPF program */
+	[BPF_REG_0] = LOONGARCH_GPR_A5,
+	/* arguments from eBPF program to in-kernel function */
+	[BPF_REG_1] = LOONGARCH_GPR_A0,
+	[BPF_REG_2] = LOONGARCH_GPR_A1,
+	[BPF_REG_3] = LOONGARCH_GPR_A2,
+	[BPF_REG_4] = LOONGARCH_GPR_A3,
+	[BPF_REG_5] = LOONGARCH_GPR_A4,
+	/* callee saved registers that in-kernel function will preserve */
+	[BPF_REG_6] = LOONGARCH_GPR_S0,
+	[BPF_REG_7] = LOONGARCH_GPR_S1,
+	[BPF_REG_8] = LOONGARCH_GPR_S2,
+	[BPF_REG_9] = LOONGARCH_GPR_S3,
+	/* read-only frame pointer to access stack */
+	[BPF_REG_FP] = LOONGARCH_GPR_S4,
+	/* temporary register for blinding constants */
+	[BPF_REG_AX] = LOONGARCH_GPR_T0,
+};
+
+static void mark_call(struct jit_ctx *ctx)
+{
+	ctx->flags |= SAVE_RA;
+}
+
+static void mark_tail_call(struct jit_ctx *ctx)
+{
+	ctx->flags |= SAVE_TCC;
+}
+
+static bool seen_call(struct jit_ctx *ctx)
+{
+	return (ctx->flags & SAVE_RA);
+}
+
+static bool seen_tail_call(struct jit_ctx *ctx)
+{
+	return (ctx->flags & SAVE_TCC);
+}
+
+static u8 tail_call_reg(struct jit_ctx *ctx)
+{
+	if (seen_call(ctx))
+		return TCC_SAVED;
+
+	return REG_TCC;
+}
+
+/*
+ * eBPF prog stack layout:
+ *
+ *                                        high
+ * original $sp ------------> +-------------------------+ <--LOONGARCH_GPR_FP
+ *                            |           $ra           |
+ *                            +-------------------------+
+ *                            |           $fp           |
+ *                            +-------------------------+
+ *                            |           $s0           |
+ *                            +-------------------------+
+ *                            |           $s1           |
+ *                            +-------------------------+
+ *                            |           $s2           |
+ *                            +-------------------------+
+ *                            |           $s3           |
+ *                            +-------------------------+
+ *                            |           $s4           |
+ *                            +-------------------------+
+ *                            |           $s5           |
+ *                            +-------------------------+ <--BPF_REG_FP
+ *                            |  prog->aux->stack_depth |
+ *                            |        (optional)       |
+ * current $sp -------------> +-------------------------+
+ *                                        low
+ */
+static void build_prologue(struct jit_ctx *ctx)
+{
+	int stack_adjust = 0, store_offset, bpf_stack_adjust;
+
+	bpf_stack_adjust = round_up(ctx->prog->aux->stack_depth, 16);
+
+	/* To store ra, fp, s0, s1, s2, s3, s4 and s5. */
+	stack_adjust += sizeof(long) * 8;
+
+	stack_adjust = round_up(stack_adjust, 16);
+	stack_adjust += bpf_stack_adjust;
+
+	/*
+	 * First instruction initializes the tail call count (TCC).
+	 * On tail call we skip this instruction, and the TCC is
+	 * passed in REG_TCC from the caller.
+	 */
+	emit_insn(ctx, addid, REG_TCC, LOONGARCH_GPR_ZERO, MAX_TAIL_CALL_CNT);
+
+	emit_insn(ctx, addid, LOONGARCH_GPR_SP, LOONGARCH_GPR_SP, -stack_adjust);
+
+	store_offset = stack_adjust - sizeof(long);
+	emit_insn(ctx, std, LOONGARCH_GPR_RA, LOONGARCH_GPR_SP, store_offset);
+
+	store_offset -= sizeof(long);
+	emit_insn(ctx, std, LOONGARCH_GPR_FP, LOONGARCH_GPR_SP, store_offset);
+
+	store_offset -= sizeof(long);
+	emit_insn(ctx, std, LOONGARCH_GPR_S0, LOONGARCH_GPR_SP, store_offset);
+
+	store_offset -= sizeof(long);
+	emit_insn(ctx, std, LOONGARCH_GPR_S1, LOONGARCH_GPR_SP, store_offset);
+
+	store_offset -= sizeof(long);
+	emit_insn(ctx, std, LOONGARCH_GPR_S2, LOONGARCH_GPR_SP, store_offset);
+
+	store_offset -= sizeof(long);
+	emit_insn(ctx, std, LOONGARCH_GPR_S3, LOONGARCH_GPR_SP, store_offset);
+
+	store_offset -= sizeof(long);
+	emit_insn(ctx, std, LOONGARCH_GPR_S4, LOONGARCH_GPR_SP, store_offset);
+
+	store_offset -= sizeof(long);
+	emit_insn(ctx, std, LOONGARCH_GPR_S5, LOONGARCH_GPR_SP, store_offset);
+
+	emit_insn(ctx, addid, LOONGARCH_GPR_FP, LOONGARCH_GPR_SP, stack_adjust);
+
+	if (bpf_stack_adjust)
+		emit_insn(ctx, addid, regmap[BPF_REG_FP], LOONGARCH_GPR_SP, bpf_stack_adjust);
+
+	/*
+	 * Program contains calls and tail calls, so REG_TCC need
+	 * to be saved across calls.
+	 */
+	if (seen_tail_call(ctx) && seen_call(ctx))
+		move_reg(ctx, TCC_SAVED, REG_TCC);
+
+	ctx->stack_size = stack_adjust;
+}
+
+static void __build_epilogue(struct jit_ctx *ctx, bool is_tail_call)
+{
+	int stack_adjust = ctx->stack_size;
+	int load_offset;
+
+	load_offset = stack_adjust - sizeof(long);
+	emit_insn(ctx, ldd, LOONGARCH_GPR_RA, LOONGARCH_GPR_SP, load_offset);
+
+	load_offset -= sizeof(long);
+	emit_insn(ctx, ldd, LOONGARCH_GPR_FP, LOONGARCH_GPR_SP, load_offset);
+
+	load_offset -= sizeof(long);
+	emit_insn(ctx, ldd, LOONGARCH_GPR_S0, LOONGARCH_GPR_SP, load_offset);
+
+	load_offset -= sizeof(long);
+	emit_insn(ctx, ldd, LOONGARCH_GPR_S1, LOONGARCH_GPR_SP, load_offset);
+
+	load_offset -= sizeof(long);
+	emit_insn(ctx, ldd, LOONGARCH_GPR_S2, LOONGARCH_GPR_SP, load_offset);
+
+	load_offset -= sizeof(long);
+	emit_insn(ctx, ldd, LOONGARCH_GPR_S3, LOONGARCH_GPR_SP, load_offset);
+
+	load_offset -= sizeof(long);
+	emit_insn(ctx, ldd, LOONGARCH_GPR_S4, LOONGARCH_GPR_SP, load_offset);
+
+	load_offset -= sizeof(long);
+	emit_insn(ctx, ldd, LOONGARCH_GPR_S5, LOONGARCH_GPR_SP, load_offset);
+
+	emit_insn(ctx, addid, LOONGARCH_GPR_SP, LOONGARCH_GPR_SP, stack_adjust);
+
+	if (!is_tail_call) {
+		/* Set return value */
+		move_reg(ctx, LOONGARCH_GPR_A0, regmap[BPF_REG_0]);
+		/* Return to the caller */
+		emit_insn(ctx, jirl, LOONGARCH_GPR_RA, LOONGARCH_GPR_ZERO, 0);
+	} else {
+		/*
+		 * Call the next bpf prog and skip the first instruction
+		 * of TCC initialization.
+		 */
+		emit_insn(ctx, jirl, LOONGARCH_GPR_T3, LOONGARCH_GPR_ZERO, 1);
+	}
+}
+
+static void build_epilogue(struct jit_ctx *ctx)
+{
+	__build_epilogue(ctx, false);
+}
+
+bool bpf_jit_supports_kfunc_call(void)
+{
+	return true;
+}
+
+/* initialized on the first pass of build_body() */
+static int out_offset = -1;
+static int emit_bpf_tail_call(struct jit_ctx *ctx)
+{
+	int off;
+	u8 tcc = tail_call_reg(ctx);
+	u8 a1 = LOONGARCH_GPR_A1;
+	u8 a2 = LOONGARCH_GPR_A2;
+	u8 t1 = LOONGARCH_GPR_T1;
+	u8 t2 = LOONGARCH_GPR_T2;
+	u8 t3 = LOONGARCH_GPR_T3;
+	const int idx0 = ctx->idx;
+
+#define cur_offset (ctx->idx - idx0)
+#define jmp_offset (out_offset - (cur_offset))
+
+	/*
+	 * a0: &ctx
+	 * a1: &array
+	 * a2: index
+	 *
+	 * if (index >= array->map.max_entries)
+	 *	 goto out;
+	 */
+	off = offsetof(struct bpf_array, map.max_entries);
+	emit_insn(ctx, ldwu, t1, a1, off);
+	/* bgeu $a2, $t1, jmp_offset */
+	if (emit_tailcall_jmp(ctx, BPF_JGE, a2, t1, jmp_offset) < 0)
+		goto toofar;
+
+	/*
+	 * if (--TCC < 0)
+	 *	 goto out;
+	 */
+	emit_insn(ctx, addid, REG_TCC, tcc, -1);
+	if (emit_tailcall_jmp(ctx, BPF_JSLT, REG_TCC, LOONGARCH_GPR_ZERO, jmp_offset) < 0)
+		goto toofar;
+
+	/*
+	 * prog = array->ptrs[index];
+	 * if (!prog)
+	 *	 goto out;
+	 */
+	emit_insn(ctx, alsld, t2, a2, a1, 2);
+	off = offsetof(struct bpf_array, ptrs);
+	emit_insn(ctx, ldd, t2, t2, off);
+	/* beq $t2, $zero, jmp_offset */
+	if (emit_tailcall_jmp(ctx, BPF_JEQ, t2, LOONGARCH_GPR_ZERO, jmp_offset) < 0)
+		goto toofar;
+
+	/* goto *(prog->bpf_func + 4); */
+	off = offsetof(struct bpf_prog, bpf_func);
+	emit_insn(ctx, ldd, t3, t2, off);
+	__build_epilogue(ctx, true);
+
+	/* out: */
+	if (out_offset == -1)
+		out_offset = cur_offset;
+	if (cur_offset != out_offset) {
+		pr_err_once("tail_call out_offset = %d, expected %d!\n",
+			    cur_offset, out_offset);
+		return -1;
+	}
+
+	return 0;
+
+toofar:
+	pr_info_once("tail_call: jump too far\n");
+	return -1;
+#undef cur_offset
+#undef jmp_offset
+}
+
+static void emit_atomic(const struct bpf_insn *insn, struct jit_ctx *ctx)
+{
+	const u8 t1 = LOONGARCH_GPR_T1;
+	const u8 t2 = LOONGARCH_GPR_T2;
+	const u8 t3 = LOONGARCH_GPR_T3;
+	const u8 src = regmap[insn->src_reg];
+	const u8 dst = regmap[insn->dst_reg];
+	const s16 off = insn->off;
+	const s32 imm = insn->imm;
+	const bool isdw = BPF_SIZE(insn->code) == BPF_DW;
+
+	move_imm(ctx, t1, off, false);
+	emit_insn(ctx, addd, t1, dst, t1);
+	move_reg(ctx, t3, src);
+
+	switch (imm) {
+	/* lock *(size *)(dst + off) <op>= src */
+	case BPF_ADD:
+		if (isdw)
+			emit_insn(ctx, amaddd, t2, t1, src);
+		else
+			emit_insn(ctx, amaddw, t2, t1, src);
+		break;
+	case BPF_AND:
+		if (isdw)
+			emit_insn(ctx, amandd, t2, t1, src);
+		else
+			emit_insn(ctx, amandw, t2, t1, src);
+		break;
+	case BPF_OR:
+		if (isdw)
+			emit_insn(ctx, amord, t2, t1, src);
+		else
+			emit_insn(ctx, amorw, t2, t1, src);
+		break;
+	case BPF_XOR:
+		if (isdw)
+			emit_insn(ctx, amxord, t2, t1, src);
+		else
+			emit_insn(ctx, amxorw, t2, t1, src);
+		break;
+	/* src = atomic_fetch_<op>(dst + off, src) */
+	case BPF_ADD | BPF_FETCH:
+		if (isdw) {
+			emit_insn(ctx, amaddd, src, t1, t3);
+		} else {
+			emit_insn(ctx, amaddw, src, t1, t3);
+			emit_zext_32(ctx, src, true);
+		}
+		break;
+	case BPF_AND | BPF_FETCH:
+		if (isdw) {
+			emit_insn(ctx, amandd, src, t1, t3);
+		} else {
+			emit_insn(ctx, amandw, src, t1, t3);
+			emit_zext_32(ctx, src, true);
+		}
+		break;
+	case BPF_OR | BPF_FETCH:
+		if (isdw) {
+			emit_insn(ctx, amord, src, t1, t3);
+		} else {
+			emit_insn(ctx, amorw, src, t1, t3);
+			emit_zext_32(ctx, src, true);
+		}
+		break;
+	case BPF_XOR | BPF_FETCH:
+		if (isdw) {
+			emit_insn(ctx, amxord, src, t1, t3);
+		} else {
+			emit_insn(ctx, amxorw, src, t1, t3);
+			emit_zext_32(ctx, src, true);
+		}
+		break;
+	/* src = atomic_xchg(dst + off, src); */
+	case BPF_XCHG:
+		if (isdw) {
+			emit_insn(ctx, amswapd, src, t1, t3);
+		} else {
+			emit_insn(ctx, amswapw, src, t1, t3);
+			emit_zext_32(ctx, src, true);
+		}
+		break;
+	/* r0 = atomic_cmpxchg(dst + off, r0, src); */
+	case BPF_CMPXCHG:
+		u8 r0 = regmap[BPF_REG_0];
+
+		move_reg(ctx, t2, r0);
+		if (isdw) {
+			emit_insn(ctx, lld, r0, t1, 0);
+			emit_insn(ctx, bne, t2, r0, 4);
+			move_reg(ctx, t3, src);
+			emit_insn(ctx, scd, t3, t1, 0);
+			emit_insn(ctx, beq, t3, LOONGARCH_GPR_ZERO, -4);
+		} else {
+			emit_insn(ctx, llw, r0, t1, 0);
+			emit_zext_32(ctx, t2, true);
+			emit_zext_32(ctx, r0, true);
+			emit_insn(ctx, bne, t2, r0, 4);
+			move_reg(ctx, t3, src);
+			emit_insn(ctx, scw, t3, t1, 0);
+			emit_insn(ctx, beq, t3, LOONGARCH_GPR_ZERO, -6);
+			emit_zext_32(ctx, r0, true);
+		}
+		break;
+	}
+}
+
+static bool is_signed_bpf_cond(u8 cond)
+{
+	return cond == BPF_JSGT || cond == BPF_JSLT ||
+	       cond == BPF_JSGE || cond == BPF_JSLE;
+}
+
+static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool extra_pass)
+{
+	const bool is32 = BPF_CLASS(insn->code) == BPF_ALU ||
+			  BPF_CLASS(insn->code) == BPF_JMP32;
+	const u8 code = insn->code;
+	const u8 cond = BPF_OP(code);
+	const u8 t1 = LOONGARCH_GPR_T1;
+	const u8 t2 = LOONGARCH_GPR_T2;
+	const u8 src = regmap[insn->src_reg];
+	const u8 dst = regmap[insn->dst_reg];
+	const s16 off = insn->off;
+	const s32 imm = insn->imm;
+	int jmp_offset;
+	int i = insn - ctx->prog->insnsi;
+
+	switch (code) {
+	/* dst = src */
+	case BPF_ALU | BPF_MOV | BPF_X:
+	case BPF_ALU64 | BPF_MOV | BPF_X:
+		move_reg(ctx, dst, src);
+		emit_zext_32(ctx, dst, is32);
+		break;
+
+	/* dst = imm */
+	case BPF_ALU | BPF_MOV | BPF_K:
+	case BPF_ALU64 | BPF_MOV | BPF_K:
+		move_imm(ctx, dst, imm, is32);
+		break;
+
+	/* dst = dst + src */
+	case BPF_ALU | BPF_ADD | BPF_X:
+	case BPF_ALU64 | BPF_ADD | BPF_X:
+		emit_insn(ctx, addd, dst, dst, src);
+		emit_zext_32(ctx, dst, is32);
+		break;
+
+	/* dst = dst + imm */
+	case BPF_ALU | BPF_ADD | BPF_K:
+	case BPF_ALU64 | BPF_ADD | BPF_K:
+		if (is_signed_imm12(imm)) {
+			emit_insn(ctx, addid, dst, dst, imm);
+		} else {
+			move_imm(ctx, t1, imm, is32);
+			emit_insn(ctx, addd, dst, dst, t1);
+		}
+		emit_zext_32(ctx, dst, is32);
+		break;
+
+	/* dst = dst - src */
+	case BPF_ALU | BPF_SUB | BPF_X:
+	case BPF_ALU64 | BPF_SUB | BPF_X:
+		emit_insn(ctx, subd, dst, dst, src);
+		emit_zext_32(ctx, dst, is32);
+		break;
+
+	/* dst = dst - imm */
+	case BPF_ALU | BPF_SUB | BPF_K:
+	case BPF_ALU64 | BPF_SUB | BPF_K:
+		if (is_signed_imm12(-imm)) {
+			emit_insn(ctx, addid, dst, dst, -imm);
+		} else {
+			move_imm(ctx, t1, imm, is32);
+			emit_insn(ctx, subd, dst, dst, t1);
+		}
+		emit_zext_32(ctx, dst, is32);
+		break;
+
+	/* dst = dst * src */
+	case BPF_ALU | BPF_MUL | BPF_X:
+	case BPF_ALU64 | BPF_MUL | BPF_X:
+		emit_insn(ctx, muld, dst, dst, src);
+		emit_zext_32(ctx, dst, is32);
+		break;
+
+	/* dst = dst * imm */
+	case BPF_ALU | BPF_MUL | BPF_K:
+	case BPF_ALU64 | BPF_MUL | BPF_K:
+		move_imm(ctx, t1, imm, is32);
+		emit_insn(ctx, muld, dst, dst, t1);
+		emit_zext_32(ctx, dst, is32);
+		break;
+
+	/* dst = dst / src */
+	case BPF_ALU | BPF_DIV | BPF_X:
+	case BPF_ALU64 | BPF_DIV | BPF_X:
+		emit_zext_32(ctx, dst, is32);
+		move_reg(ctx, t1, src);
+		emit_zext_32(ctx, t1, is32);
+		emit_insn(ctx, divdu, dst, dst, t1);
+		emit_zext_32(ctx, dst, is32);
+		break;
+
+	/* dst = dst / imm */
+	case BPF_ALU | BPF_DIV | BPF_K:
+	case BPF_ALU64 | BPF_DIV | BPF_K:
+		move_imm(ctx, t1, imm, is32);
+		emit_zext_32(ctx, dst, is32);
+		emit_insn(ctx, divdu, dst, dst, t1);
+		emit_zext_32(ctx, dst, is32);
+		break;
+
+	/* dst = dst % src */
+	case BPF_ALU | BPF_MOD | BPF_X:
+	case BPF_ALU64 | BPF_MOD | BPF_X:
+		emit_zext_32(ctx, dst, is32);
+		move_reg(ctx, t1, src);
+		emit_zext_32(ctx, t1, is32);
+		emit_insn(ctx, moddu, dst, dst, t1);
+		emit_zext_32(ctx, dst, is32);
+		break;
+
+	/* dst = dst % imm */
+	case BPF_ALU | BPF_MOD | BPF_K:
+	case BPF_ALU64 | BPF_MOD | BPF_K:
+		move_imm(ctx, t1, imm, is32);
+		emit_zext_32(ctx, dst, is32);
+		emit_insn(ctx, moddu, dst, dst, t1);
+		emit_zext_32(ctx, dst, is32);
+		break;
+
+	/* dst = -dst */
+	case BPF_ALU | BPF_NEG:
+	case BPF_ALU64 | BPF_NEG:
+		move_imm(ctx, t1, imm, is32);
+		emit_insn(ctx, subd, dst, LOONGARCH_GPR_ZERO, dst);
+		emit_zext_32(ctx, dst, is32);
+		break;
+
+	/* dst = dst & src */
+	case BPF_ALU | BPF_AND | BPF_X:
+	case BPF_ALU64 | BPF_AND | BPF_X:
+		emit_insn(ctx, and, dst, dst, src);
+		emit_zext_32(ctx, dst, is32);
+		break;
+
+	/* dst = dst & imm */
+	case BPF_ALU | BPF_AND | BPF_K:
+	case BPF_ALU64 | BPF_AND | BPF_K:
+		if (is_unsigned_imm12(imm)) {
+			emit_insn(ctx, andi, dst, dst, imm);
+		} else {
+			move_imm(ctx, t1, imm, is32);
+			emit_insn(ctx, and, dst, dst, t1);
+		}
+		emit_zext_32(ctx, dst, is32);
+		break;
+
+	/* dst = dst | src */
+	case BPF_ALU | BPF_OR | BPF_X:
+	case BPF_ALU64 | BPF_OR | BPF_X:
+		emit_insn(ctx, or, dst, dst, src);
+		emit_zext_32(ctx, dst, is32);
+		break;
+
+	/* dst = dst | imm */
+	case BPF_ALU | BPF_OR | BPF_K:
+	case BPF_ALU64 | BPF_OR | BPF_K:
+		if (is_unsigned_imm12(imm)) {
+			emit_insn(ctx, ori, dst, dst, imm);
+		} else {
+			move_imm(ctx, t1, imm, is32);
+			emit_insn(ctx, or, dst, dst, t1);
+		}
+		emit_zext_32(ctx, dst, is32);
+		break;
+
+	/* dst = dst ^ src */
+	case BPF_ALU | BPF_XOR | BPF_X:
+	case BPF_ALU64 | BPF_XOR | BPF_X:
+		emit_insn(ctx, xor, dst, dst, src);
+		emit_zext_32(ctx, dst, is32);
+		break;
+
+	/* dst = dst ^ imm */
+	case BPF_ALU | BPF_XOR | BPF_K:
+	case BPF_ALU64 | BPF_XOR | BPF_K:
+		if (is_unsigned_imm12(imm)) {
+			emit_insn(ctx, xori, dst, dst, imm);
+		} else {
+			move_imm(ctx, t1, imm, is32);
+			emit_insn(ctx, xor, dst, dst, t1);
+		}
+		emit_zext_32(ctx, dst, is32);
+		break;
+
+	/* dst = dst << src (logical) */
+	case BPF_ALU | BPF_LSH | BPF_X:
+		emit_insn(ctx, sllw, dst, dst, src);
+		emit_zext_32(ctx, dst, is32);
+		break;
+
+	case BPF_ALU64 | BPF_LSH | BPF_X:
+		emit_insn(ctx, slld, dst, dst, src);
+		break;
+
+	/* dst = dst << imm (logical) */
+	case BPF_ALU | BPF_LSH | BPF_K:
+		emit_insn(ctx, slliw, dst, dst, imm);
+		emit_zext_32(ctx, dst, is32);
+		break;
+
+	case BPF_ALU64 | BPF_LSH | BPF_K:
+		emit_insn(ctx, sllid, dst, dst, imm);
+		break;
+
+	/* dst = dst >> src (logical) */
+	case BPF_ALU | BPF_RSH | BPF_X:
+		emit_insn(ctx, srlw, dst, dst, src);
+		emit_zext_32(ctx, dst, is32);
+		break;
+
+	case BPF_ALU64 | BPF_RSH | BPF_X:
+		emit_insn(ctx, srld, dst, dst, src);
+		break;
+
+	/* dst = dst >> imm (logical) */
+	case BPF_ALU | BPF_RSH | BPF_K:
+		emit_insn(ctx, srliw, dst, dst, imm);
+		emit_zext_32(ctx, dst, is32);
+		break;
+
+	case BPF_ALU64 | BPF_RSH | BPF_K:
+		emit_insn(ctx, srlid, dst, dst, imm);
+		break;
+
+	/* dst = dst >> src (arithmetic) */
+	case BPF_ALU | BPF_ARSH | BPF_X:
+		emit_insn(ctx, sraw, dst, dst, src);
+		emit_zext_32(ctx, dst, is32);
+		break;
+
+	case BPF_ALU64 | BPF_ARSH | BPF_X:
+		emit_insn(ctx, srad, dst, dst, src);
+		break;
+
+	/* dst = dst >> imm (arithmetic) */
+	case BPF_ALU | BPF_ARSH | BPF_K:
+		emit_insn(ctx, sraiw, dst, dst, imm);
+		emit_zext_32(ctx, dst, is32);
+		break;
+
+	case BPF_ALU64 | BPF_ARSH | BPF_K:
+		emit_insn(ctx, sraid, dst, dst, imm);
+		break;
+
+	/* dst = BSWAP##imm(dst) */
+	case BPF_ALU | BPF_END | BPF_FROM_LE:
+		switch (imm) {
+		case 16:
+			/* zero-extend 16 bits into 64 bits */
+			emit_insn(ctx, bstrpickd, dst, dst, 15, 0);
+			break;
+		case 32:
+			/* zero-extend 32 bits into 64 bits */
+			emit_zext_32(ctx, dst, is32);
+			break;
+		case 64:
+			/* do nothing */
+			break;
+		}
+		break;
+
+	case BPF_ALU | BPF_END | BPF_FROM_BE:
+		switch (imm) {
+		case 16:
+			emit_insn(ctx, revb2h, dst, dst);
+			/* zero-extend 16 bits into 64 bits */
+			emit_insn(ctx, bstrpickd, dst, dst, 15, 0);
+			break;
+		case 32:
+			emit_insn(ctx, revb2w, dst, dst);
+			/* zero-extend 32 bits into 64 bits */
+			emit_zext_32(ctx, dst, is32);
+			break;
+		case 64:
+			emit_insn(ctx, revbd, dst, dst);
+			break;
+		}
+		break;
+
+	/* PC += off if dst cond src */
+	case BPF_JMP | BPF_JEQ | BPF_X:
+	case BPF_JMP | BPF_JNE | BPF_X:
+	case BPF_JMP | BPF_JGT | BPF_X:
+	case BPF_JMP | BPF_JGE | BPF_X:
+	case BPF_JMP | BPF_JLT | BPF_X:
+	case BPF_JMP | BPF_JLE | BPF_X:
+	case BPF_JMP | BPF_JSGT | BPF_X:
+	case BPF_JMP | BPF_JSGE | BPF_X:
+	case BPF_JMP | BPF_JSLT | BPF_X:
+	case BPF_JMP | BPF_JSLE | BPF_X:
+	case BPF_JMP32 | BPF_JEQ | BPF_X:
+	case BPF_JMP32 | BPF_JNE | BPF_X:
+	case BPF_JMP32 | BPF_JGT | BPF_X:
+	case BPF_JMP32 | BPF_JGE | BPF_X:
+	case BPF_JMP32 | BPF_JLT | BPF_X:
+	case BPF_JMP32 | BPF_JLE | BPF_X:
+	case BPF_JMP32 | BPF_JSGT | BPF_X:
+	case BPF_JMP32 | BPF_JSGE | BPF_X:
+	case BPF_JMP32 | BPF_JSLT | BPF_X:
+	case BPF_JMP32 | BPF_JSLE | BPF_X:
+		jmp_offset = bpf2la_offset(i, off, ctx);
+		move_reg(ctx, t1, dst);
+		move_reg(ctx, t2, src);
+		if (is_signed_bpf_cond(BPF_OP(code))) {
+			emit_sext_32(ctx, t1, is32);
+			emit_sext_32(ctx, t2, is32);
+		} else {
+			emit_zext_32(ctx, t1, is32);
+			emit_zext_32(ctx, t2, is32);
+		}
+		if (emit_cond_jmp(ctx, cond, t1, t2, jmp_offset) < 0)
+			goto toofar;
+		break;
+
+	/* PC += off if dst cond imm */
+	case BPF_JMP | BPF_JEQ | BPF_K:
+	case BPF_JMP | BPF_JNE | BPF_K:
+	case BPF_JMP | BPF_JGT | BPF_K:
+	case BPF_JMP | BPF_JGE | BPF_K:
+	case BPF_JMP | BPF_JLT | BPF_K:
+	case BPF_JMP | BPF_JLE | BPF_K:
+	case BPF_JMP | BPF_JSGT | BPF_K:
+	case BPF_JMP | BPF_JSGE | BPF_K:
+	case BPF_JMP | BPF_JSLT | BPF_K:
+	case BPF_JMP | BPF_JSLE | BPF_K:
+	case BPF_JMP32 | BPF_JEQ | BPF_K:
+	case BPF_JMP32 | BPF_JNE | BPF_K:
+	case BPF_JMP32 | BPF_JGT | BPF_K:
+	case BPF_JMP32 | BPF_JGE | BPF_K:
+	case BPF_JMP32 | BPF_JLT | BPF_K:
+	case BPF_JMP32 | BPF_JLE | BPF_K:
+	case BPF_JMP32 | BPF_JSGT | BPF_K:
+	case BPF_JMP32 | BPF_JSGE | BPF_K:
+	case BPF_JMP32 | BPF_JSLT | BPF_K:
+	case BPF_JMP32 | BPF_JSLE | BPF_K:
+		u8 t7 = -1;
+		jmp_offset = bpf2la_offset(i, off, ctx);
+		if (imm) {
+			move_imm(ctx, t1, imm, false);
+			t7 = t1;
+		} else {
+			/* If imm is 0, simply use zero register. */
+			t7 = LOONGARCH_GPR_ZERO;
+		}
+		move_reg(ctx, t2, dst);
+		if (is_signed_bpf_cond(BPF_OP(code))) {
+			emit_sext_32(ctx, t7, is32);
+			emit_sext_32(ctx, t2, is32);
+		} else {
+			emit_zext_32(ctx, t7, is32);
+			emit_zext_32(ctx, t2, is32);
+		}
+		if (emit_cond_jmp(ctx, cond, t2, t7, jmp_offset) < 0)
+			goto toofar;
+		break;
+
+	/* PC += off if dst & src */
+	case BPF_JMP | BPF_JSET | BPF_X:
+	case BPF_JMP32 | BPF_JSET | BPF_X:
+		jmp_offset = bpf2la_offset(i, off, ctx);
+		emit_insn(ctx, and, t1, dst, src);
+		emit_zext_32(ctx, t1, is32);
+		if (emit_cond_jmp(ctx, cond, t1, LOONGARCH_GPR_ZERO, jmp_offset) < 0)
+			goto toofar;
+		break;
+
+	/* PC += off if dst & imm */
+	case BPF_JMP | BPF_JSET | BPF_K:
+	case BPF_JMP32 | BPF_JSET | BPF_K:
+		jmp_offset = bpf2la_offset(i, off, ctx);
+		move_imm(ctx, t1, imm, is32);
+		emit_insn(ctx, and, t1, dst, t1);
+		emit_zext_32(ctx, t1, is32);
+		if (emit_cond_jmp(ctx, cond, t1, LOONGARCH_GPR_ZERO, jmp_offset) < 0)
+			goto toofar;
+		break;
+
+	/* PC += off */
+	case BPF_JMP | BPF_JA:
+		jmp_offset = bpf2la_offset(i, off, ctx);
+		if (emit_uncond_jmp(ctx, jmp_offset) < 0)
+			goto toofar;
+		break;
+
+	/* function call */
+	case BPF_JMP | BPF_CALL:
+		int ret;
+		u64 func_addr;
+		bool func_addr_fixed;
+
+		mark_call(ctx);
+		ret = bpf_jit_get_func_addr(ctx->prog, insn, extra_pass,
+					    &func_addr, &func_addr_fixed);
+		if (ret < 0)
+			return ret;
+
+		move_imm(ctx, t1, func_addr, is32);
+		emit_insn(ctx, jirl, t1, LOONGARCH_GPR_RA, 0);
+		move_reg(ctx, regmap[BPF_REG_0], LOONGARCH_GPR_A0);
+		break;
+
+	/* tail call */
+	case BPF_JMP | BPF_TAIL_CALL:
+		mark_tail_call(ctx);
+		if (emit_bpf_tail_call(ctx) < 0)
+			return -EINVAL;
+		break;
+
+	/* function return */
+	case BPF_JMP | BPF_EXIT:
+		emit_sext_32(ctx, regmap[BPF_REG_0], true);
+
+		if (i == ctx->prog->len - 1)
+			break;
+
+		jmp_offset = epilogue_offset(ctx);
+		if (emit_uncond_jmp(ctx, jmp_offset) < 0)
+			goto toofar;
+		break;
+
+	/* dst = imm64 */
+	case BPF_LD | BPF_IMM | BPF_DW:
+		u64 imm64 = (u64)(insn + 1)->imm << 32 | (u32)insn->imm;
+
+		move_imm(ctx, dst, imm64, is32);
+		return 1;
+
+	/* dst = *(size *)(src + off) */
+	case BPF_LDX | BPF_MEM | BPF_B:
+	case BPF_LDX | BPF_MEM | BPF_H:
+	case BPF_LDX | BPF_MEM | BPF_W:
+	case BPF_LDX | BPF_MEM | BPF_DW:
+		switch (BPF_SIZE(code)) {
+		case BPF_B:
+			if (is_signed_imm12(off)) {
+				emit_insn(ctx, ldbu, dst, src, off);
+			} else {
+				move_imm(ctx, t1, off, is32);
+				emit_insn(ctx, ldxbu, dst, src, t1);
+			}
+			break;
+		case BPF_H:
+			if (is_signed_imm12(off)) {
+				emit_insn(ctx, ldhu, dst, src, off);
+			} else {
+				move_imm(ctx, t1, off, is32);
+				emit_insn(ctx, ldxhu, dst, src, t1);
+			}
+			break;
+		case BPF_W:
+			if (is_signed_imm12(off)) {
+				emit_insn(ctx, ldwu, dst, src, off);
+			} else if (is_signed_imm14(off)) {
+				emit_insn(ctx, ldptrw, dst, src, off);
+			} else {
+				move_imm(ctx, t1, off, is32);
+				emit_insn(ctx, ldxwu, dst, src, t1);
+			}
+			break;
+		case BPF_DW:
+			if (is_signed_imm12(off)) {
+				emit_insn(ctx, ldd, dst, src, off);
+			} else if (is_signed_imm14(off)) {
+				emit_insn(ctx, ldptrd, dst, src, off);
+			} else {
+				move_imm(ctx, t1, off, is32);
+				emit_insn(ctx, ldxd, dst, src, t1);
+			}
+			break;
+		}
+		break;
+
+	/* *(size *)(dst + off) = imm */
+	case BPF_ST | BPF_MEM | BPF_B:
+	case BPF_ST | BPF_MEM | BPF_H:
+	case BPF_ST | BPF_MEM | BPF_W:
+	case BPF_ST | BPF_MEM | BPF_DW:
+		switch (BPF_SIZE(code)) {
+		case BPF_B:
+			move_imm(ctx, t1, imm, is32);
+			if (is_signed_imm12(off)) {
+				emit_insn(ctx, stb, t1, dst, off);
+			} else {
+				move_imm(ctx, t2, off, is32);
+				emit_insn(ctx, stxb, t1, dst, t2);
+			}
+			break;
+		case BPF_H:
+			move_imm(ctx, t1, imm, is32);
+			if (is_signed_imm12(off)) {
+				emit_insn(ctx, sth, t1, dst, off);
+			} else {
+				move_imm(ctx, t2, off, is32);
+				emit_insn(ctx, stxh, t1, dst, t2);
+			}
+			break;
+		case BPF_W:
+			move_imm(ctx, t1, imm, is32);
+			if (is_signed_imm12(off)) {
+				emit_insn(ctx, stw, t1, dst, off);
+			} else if (is_signed_imm14(off)) {
+				emit_insn(ctx, stptrw, t1, dst, off);
+			} else {
+				move_imm(ctx, t2, off, is32);
+				emit_insn(ctx, stxw, t1, dst, t2);
+			}
+			break;
+		case BPF_DW:
+			move_imm(ctx, t1, imm, is32);
+			if (is_signed_imm12(off)) {
+				emit_insn(ctx, std, t1, dst, off);
+			} else if (is_signed_imm14(off)) {
+				emit_insn(ctx, stptrd, t1, dst, off);
+			} else {
+				move_imm(ctx, t2, off, is32);
+				emit_insn(ctx, stxd, t1, dst, t2);
+			}
+			break;
+		}
+		break;
+
+	/* *(size *)(dst + off) = src */
+	case BPF_STX | BPF_MEM | BPF_B:
+	case BPF_STX | BPF_MEM | BPF_H:
+	case BPF_STX | BPF_MEM | BPF_W:
+	case BPF_STX | BPF_MEM | BPF_DW:
+		switch (BPF_SIZE(code)) {
+		case BPF_B:
+			if (is_signed_imm12(off)) {
+				emit_insn(ctx, stb, src, dst, off);
+			} else {
+				move_imm(ctx, t1, off, is32);
+				emit_insn(ctx, stxb, src, dst, t1);
+			}
+			break;
+		case BPF_H:
+			if (is_signed_imm12(off)) {
+				emit_insn(ctx, sth, src, dst, off);
+			} else {
+				move_imm(ctx, t1, off, is32);
+				emit_insn(ctx, stxh, src, dst, t1);
+			}
+			break;
+		case BPF_W:
+			if (is_signed_imm12(off)) {
+				emit_insn(ctx, stw, src, dst, off);
+			} else if (is_signed_imm14(off)) {
+				emit_insn(ctx, stptrw, src, dst, off);
+			} else {
+				move_imm(ctx, t1, off, is32);
+				emit_insn(ctx, stxw, src, dst, t1);
+			}
+			break;
+		case BPF_DW:
+			if (is_signed_imm12(off)) {
+				emit_insn(ctx, std, src, dst, off);
+			} else if (is_signed_imm14(off)) {
+				emit_insn(ctx, stptrd, src, dst, off);
+			} else {
+				move_imm(ctx, t1, off, is32);
+				emit_insn(ctx, stxd, src, dst, t1);
+			}
+			break;
+		}
+		break;
+
+	case BPF_STX | BPF_ATOMIC | BPF_W:
+	case BPF_STX | BPF_ATOMIC | BPF_DW:
+		emit_atomic(insn, ctx);
+		break;
+
+	default:
+		pr_err("bpf_jit: unknown opcode %02x\n", code);
+		return -EINVAL;
+	}
+
+	return 0;
+
+toofar:
+	pr_info_once("bpf_jit: opcode %02x, jump too far\n", code);
+	return -E2BIG;
+}
+
+static int build_body(struct jit_ctx *ctx, bool extra_pass)
+{
+	int i;
+	const struct bpf_prog *prog = ctx->prog;
+
+	for (i = 0; i < prog->len; i++) {
+		const struct bpf_insn *insn = &prog->insnsi[i];
+		int ret;
+
+		if (ctx->image == NULL)
+			ctx->offset[i] = ctx->idx;
+
+		ret = build_insn(insn, ctx, extra_pass);
+		if (ret > 0) {
+			i++;
+			if (ctx->image == NULL)
+				ctx->offset[i] = ctx->idx;
+			continue;
+		}
+		if (ret)
+			return ret;
+	}
+
+	if (ctx->image == NULL)
+		ctx->offset[i] = ctx->idx;
+
+	return 0;
+}
+
+/* Fill space with break instructions */
+static void jit_fill_hole(void *area, unsigned int size)
+{
+	u32 *ptr;
+
+	/* We are guaranteed to have aligned memory */
+	for (ptr = area; size >= sizeof(u32); size -= sizeof(u32))
+		*ptr++ = INSN_BREAK;
+}
+
+static int validate_code(struct jit_ctx *ctx)
+{
+	int i;
+	union loongarch_instruction insn;
+
+	for (i = 0; i < ctx->idx; i++) {
+		insn = ctx->image[i];
+		/* Check INSN_BREAK */
+		if (insn.word == INSN_BREAK)
+			return -1;
+	}
+
+	return 0;
+}
+
+struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
+{
+	bool tmp_blinded = false, extra_pass = false;
+	u8 *image_ptr;
+	int image_size;
+	struct jit_ctx ctx;
+	struct jit_data *jit_data;
+	struct bpf_binary_header *header;
+	struct bpf_prog *tmp, *orig_prog = prog;
+
+	/*
+	 * If BPF JIT was not enabled then we must fall back to
+	 * the interpreter.
+	 */
+	if (!prog->jit_requested)
+		return orig_prog;
+
+	tmp = bpf_jit_blind_constants(prog);
+	/*
+	 * If blinding was requested and we failed during blinding,
+	 * we must fall back to the interpreter. Otherwise, we save
+	 * the new JITed code.
+	 */
+	if (IS_ERR(tmp))
+		return orig_prog;
+
+	if (tmp != prog) {
+		tmp_blinded = true;
+		prog = tmp;
+	}
+
+	jit_data = prog->aux->jit_data;
+	if (!jit_data) {
+		jit_data = kzalloc(sizeof(*jit_data), GFP_KERNEL);
+		if (!jit_data) {
+			prog = orig_prog;
+			goto out;
+		}
+		prog->aux->jit_data = jit_data;
+	}
+	if (jit_data->ctx.offset) {
+		ctx = jit_data->ctx;
+		image_ptr = jit_data->image;
+		header = jit_data->header;
+		extra_pass = true;
+		image_size = sizeof(u32) * ctx.idx;
+		goto skip_init_ctx;
+	}
+
+	memset(&ctx, 0, sizeof(ctx));
+	ctx.prog = prog;
+
+	ctx.offset = kvcalloc(prog->len + 1, sizeof(u32), GFP_KERNEL);
+	if (ctx.offset == NULL) {
+		prog = orig_prog;
+		goto out_offset;
+	}
+
+	/* 1. Initial fake pass to compute ctx->idx and set ctx->flags */
+	build_prologue(&ctx);
+	if (build_body(&ctx, extra_pass)) {
+		prog = orig_prog;
+		goto out_offset;
+	}
+	ctx.epilogue_offset = ctx.idx;
+	build_epilogue(&ctx);
+
+	/* Now we know the actual image size.
+	 * As each LoongArch instruction is of length 32bit,
+	 * we are translating number of JITed intructions into
+	 * the size required to store these JITed code.
+	 */
+	image_size = sizeof(u32) * ctx.idx;
+	/* Now we know the size of the structure to make */
+	header = bpf_jit_binary_alloc(image_size, &image_ptr,
+				      sizeof(u32), jit_fill_hole);
+	if (header == NULL) {
+		prog = orig_prog;
+		goto out_offset;
+	}
+
+	/* 2. Now, the actual pass to generate final JIT code */
+	ctx.image = (union loongarch_instruction *)image_ptr;
+
+skip_init_ctx:
+	ctx.idx = 0;
+
+	build_prologue(&ctx);
+	if (build_body(&ctx, extra_pass)) {
+		bpf_jit_binary_free(header);
+		prog = orig_prog;
+		goto out_offset;
+	}
+	build_epilogue(&ctx);
+
+	/* 3. Extra pass to validate JITed code */
+	if (validate_code(&ctx)) {
+		bpf_jit_binary_free(header);
+		prog = orig_prog;
+		goto out_offset;
+	}
+
+	/* And we're done */
+	if (bpf_jit_enable > 1)
+		bpf_jit_dump(prog->len, image_size, 2, ctx.image);
+
+	/* Update the icache */
+	flush_icache_range((unsigned long)header, (unsigned long)(ctx.image + ctx.idx));
+
+	if (!prog->is_func || extra_pass) {
+		if (extra_pass && ctx.idx != jit_data->ctx.idx) {
+			pr_err_once("multi-func JIT bug %d != %d\n",
+				    ctx.idx, jit_data->ctx.idx);
+			bpf_jit_binary_free(header);
+			prog->bpf_func = NULL;
+			prog->jited = 0;
+			prog->jited_len = 0;
+			goto out_offset;
+		}
+		bpf_jit_binary_lock_ro(header);
+	} else {
+		jit_data->ctx = ctx;
+		jit_data->image = image_ptr;
+		jit_data->header = header;
+	}
+	prog->jited = 1;
+	prog->jited_len = image_size;
+	prog->bpf_func = (void *)ctx.image;
+
+	if (!prog->is_func || extra_pass) {
+		int i;
+
+		/* offset[prog->len] is the size of program */
+		for (i = 0; i <= prog->len; i++)
+			ctx.offset[i] *= LOONGARCH_INSN_SIZE;
+		bpf_prog_fill_jited_linfo(prog, ctx.offset + 1);
+
+out_offset:
+		kvfree(ctx.offset);
+		kfree(jit_data);
+		prog->aux->jit_data = NULL;
+	}
+
+out:
+	if (tmp_blinded)
+		bpf_jit_prog_release_other(prog, prog == orig_prog ? tmp : orig_prog);
+
+	out_offset = -1;
+
+	return prog;
+}

arch/loongarch/net/bpf_jit.h

+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * BPF JIT compiler for LoongArch
+ *
+ * Copyright (C) 2022 Loongson Technology Corporation Limited
+ */
+#include <linux/bpf.h>
+#include <linux/filter.h>
+#include <asm/cacheflush.h>
+#include <asm/inst.h>
+
+struct jit_ctx {
+	const struct bpf_prog *prog;
+	unsigned int idx;
+	unsigned int flags;
+	unsigned int epilogue_offset;
+	u32 *offset;
+	union loongarch_instruction *image;
+	u32 stack_size;
+};
+
+struct jit_data {
+	struct bpf_binary_header *header;
+	u8 *image;
+	struct jit_ctx ctx;
+};
+
+#define emit_insn(ctx, func, ...)						\
+do {										\
+	if (ctx->image != NULL) {						\
+		union loongarch_instruction *insn = &ctx->image[ctx->idx];	\
+		emit_##func(insn, ##__VA_ARGS__);				\
+	}									\
+	ctx->idx++;								\
+} while (0)
+
+#define is_signed_imm12(val)	signed_imm_check(val, 12)
+#define is_signed_imm14(val)	signed_imm_check(val, 14)
+#define is_signed_imm16(val)	signed_imm_check(val, 16)
+#define is_signed_imm26(val)	signed_imm_check(val, 26)
+#define is_signed_imm32(val)	signed_imm_check(val, 32)
+#define is_signed_imm52(val)	signed_imm_check(val, 52)
+#define is_unsigned_imm12(val)	unsigned_imm_check(val, 12)
+
+static inline int bpf2la_offset(int bpf_insn, int off, const struct jit_ctx *ctx)
+{
+	/* BPF JMP offset is relative to the next instruction */
+	bpf_insn++;
+	/*
+	 * Whereas LoongArch branch instructions encode the offset
+	 * from the branch itself, so we must subtract 1 from the
+	 * instruction offset.
+	 */
+	return (ctx->offset[bpf_insn + off] - (ctx->offset[bpf_insn] - 1));
+}
+
+static inline int epilogue_offset(const struct jit_ctx *ctx)
+{
+	int from = ctx->idx;
+	int to = ctx->epilogue_offset;
+
+	return (to - from);
+}
+
+/* Zero-extend 32 bits into 64 bits */
+static inline void emit_zext_32(struct jit_ctx *ctx, enum loongarch_gpr reg, bool is32)
+{
+	if (!is32)
+		return;
+
+	emit_insn(ctx, lu32id, reg, 0);
+}
+
+/* Signed-extend 32 bits into 64 bits */
+static inline void emit_sext_32(struct jit_ctx *ctx, enum loongarch_gpr reg, bool is32)
+{
+	if (!is32)
+		return;
+
+	emit_insn(ctx, addiw, reg, reg, 0);
+}
+
+static inline void move_imm(struct jit_ctx *ctx, enum loongarch_gpr rd, long imm, bool is32)
+{
+	long imm_11_0, imm_31_12, imm_51_32, imm_63_52, imm_51_0, imm_51_31;
+
+	/* or rd, $zero, $zero */
+	if (imm == 0) {
+		emit_insn(ctx, or, rd, LOONGARCH_GPR_ZERO, LOONGARCH_GPR_ZERO);
+		return;
+	}
+
+	/* addiw rd, $zero, imm_11_0 */
+	if (is_signed_imm12(imm)) {
+		emit_insn(ctx, addiw, rd, LOONGARCH_GPR_ZERO, imm);
+		goto zext;
+	}
+
+	/* ori rd, $zero, imm_11_0 */
+	if (is_unsigned_imm12(imm)) {
+		emit_insn(ctx, ori, rd, LOONGARCH_GPR_ZERO, imm);
+		goto zext;
+	}
+
+	/* lu52id rd, $zero, imm_63_52 */
+	imm_63_52 = (imm >> 52) & 0xfff;
+	imm_51_0 = imm & 0xfffffffffffff;
+	if (imm_63_52 != 0 && imm_51_0 == 0) {
+		emit_insn(ctx, lu52id, rd, LOONGARCH_GPR_ZERO, imm_63_52);
+		return;
+	}
+
+	/* lu12iw rd, imm_31_12 */
+	imm_31_12 = (imm >> 12) & 0xfffff;
+	emit_insn(ctx, lu12iw, rd, imm_31_12);
+
+	/* ori rd, rd, imm_11_0 */
+	imm_11_0 = imm & 0xfff;
+	if (imm_11_0 != 0)
+		emit_insn(ctx, ori, rd, rd, imm_11_0);
+
+	if (!is_signed_imm32(imm)) {
+		if (imm_51_0 != 0) {
+			/*
+			 * If bit[51:31] is all 0 or all 1,
+			 * it means bit[51:32] is sign extended by lu12iw,
+			 * no need to call lu32id to do a new filled operation.
+			 */
+			imm_51_31 = (imm >> 31) & 0x1fffff;
+			if (imm_51_31 != 0 || imm_51_31 != 0x1fffff) {
+				/* lu32id rd, imm_51_32 */
+				imm_51_32 = (imm >> 32) & 0xfffff;
+				emit_insn(ctx, lu32id, rd, imm_51_32);
+			}
+		}
+
+		/* lu52id rd, rd, imm_63_52 */
+		if (!is_signed_imm52(imm))
+			emit_insn(ctx, lu52id, rd, rd, imm_63_52);
+	}
+
+zext:
+	emit_zext_32(ctx, rd, is32);
+}
+
+static inline void move_reg(struct jit_ctx *ctx, enum loongarch_gpr rd,
+			    enum loongarch_gpr rj)
+{
+	emit_insn(ctx, or, rd, rj, LOONGARCH_GPR_ZERO);
+}
+
+static inline int invert_jmp_cond(u8 cond)
+{
+	switch (cond) {
+	case BPF_JEQ:
+		return BPF_JNE;
+	case BPF_JNE:
+	case BPF_JSET:
+		return BPF_JEQ;
+	case BPF_JGT:
+		return BPF_JLE;
+	case BPF_JGE:
+		return BPF_JLT;
+	case BPF_JLT:
+		return BPF_JGE;
+	case BPF_JLE:
+		return BPF_JGT;
+	case BPF_JSGT:
+		return BPF_JSLE;
+	case BPF_JSGE:
+		return BPF_JSLT;
+	case BPF_JSLT:
+		return BPF_JSGE;
+	case BPF_JSLE:
+		return BPF_JSGT;
+	}
+	return -1;
+}
+
+static inline void cond_jmp_offset(struct jit_ctx *ctx, u8 cond, enum loongarch_gpr rj,
+				   enum loongarch_gpr rd, int jmp_offset)
+{
+	switch (cond) {
+	case BPF_JEQ:
+		/* PC += jmp_offset if rj == rd */
+		emit_insn(ctx, beq, rj, rd, jmp_offset);
+		return;
+	case BPF_JNE:
+	case BPF_JSET:
+		/* PC += jmp_offset if rj != rd */
+		emit_insn(ctx, bne, rj, rd, jmp_offset);
+		return;
+	case BPF_JGT:
+		/* PC += jmp_offset if rj > rd (unsigned) */
+		emit_insn(ctx, bltu, rd, rj, jmp_offset);
+		return;
+	case BPF_JLT:
+		/* PC += jmp_offset if rj < rd (unsigned) */
+		emit_insn(ctx, bltu, rj, rd, jmp_offset);
+		return;
+	case BPF_JGE:
+		/* PC += jmp_offset if rj >= rd (unsigned) */
+		emit_insn(ctx, bgeu, rj, rd, jmp_offset);
+		return;
+	case BPF_JLE:
+		/* PC += jmp_offset if rj <= rd (unsigned) */
+		emit_insn(ctx, bgeu, rd, rj, jmp_offset);
+		return;
+	case BPF_JSGT:
+		/* PC += jmp_offset if rj > rd (signed) */
+		emit_insn(ctx, blt, rd, rj, jmp_offset);
+		return;
+	case BPF_JSLT:
+		/* PC += jmp_offset if rj < rd (signed) */
+		emit_insn(ctx, blt, rj, rd, jmp_offset);
+		return;
+	case BPF_JSGE:
+		/* PC += jmp_offset if rj >= rd (signed) */
+		emit_insn(ctx, bge, rj, rd, jmp_offset);
+		return;
+	case BPF_JSLE:
+		/* PC += jmp_offset if rj <= rd (signed) */
+		emit_insn(ctx, bge, rd, rj, jmp_offset);
+		return;
+	}
+}
+
+static inline void cond_jmp_offs26(struct jit_ctx *ctx, u8 cond, enum loongarch_gpr rj,
+				   enum loongarch_gpr rd, int jmp_offset)
+{
+	cond = invert_jmp_cond(cond);
+	cond_jmp_offset(ctx, cond, rj, rd, 2);
+	emit_insn(ctx, b, jmp_offset);
+}
+
+static inline void uncond_jmp_offs26(struct jit_ctx *ctx, int jmp_offset)
+{
+	emit_insn(ctx, b, jmp_offset);
+}
+
+static inline int emit_cond_jmp(struct jit_ctx *ctx, u8 cond, enum loongarch_gpr rj,
+				enum loongarch_gpr rd, int jmp_offset)
+{
+	/*
+	 * A large PC-relative jump offset may overflow the immediate field of
+	 * the native conditional branch instruction, triggering a conversion
+	 * to use an absolute jump instead, this jump sequence is particularly
+	 * nasty. For now, use cond_jmp_offs26() directly to keep it simple.
+	 * In the future, maybe we can add support for far branching, the branch
+	 * relaxation requires more than two passes to converge, the code seems
+	 * too complex to understand, not quite sure whether it is necessary and
+	 * worth the extra pain. Anyway, just leave it as it is to enhance code
+	 * readability now.
+	 */
+	if (is_signed_imm26(jmp_offset)) {
+		cond_jmp_offs26(ctx, cond, rj, rd, jmp_offset);
+		return 0;
+	}
+
+	return -EINVAL;
+}
+
+static inline int emit_uncond_jmp(struct jit_ctx *ctx, int jmp_offset)
+{
+	if (is_signed_imm26(jmp_offset)) {
+		uncond_jmp_offs26(ctx, jmp_offset);
+		return 0;
+	}
+
+	return -EINVAL;
+}
+
+static inline int emit_tailcall_jmp(struct jit_ctx *ctx, u8 cond, enum loongarch_gpr rj,
+				    enum loongarch_gpr rd, int jmp_offset)
+{
+	if (is_signed_imm16(jmp_offset)) {
+		cond_jmp_offset(ctx, cond, rj, rd, jmp_offset);
+		return 0;
+	}
+
+	return -EINVAL;
+}

arch/loongarch/pci/acpi.c

@@ -82,6 +82,69 @@ static int acpi_prepare_root_resources(struct acpi_pci_root_info *ci)
 	return 0;
 }
 
+/*
+ * Create a PCI config space window
+ *  - reserve mem region
+ *  - alloc struct pci_config_window with space for all mappings
+ *  - ioremap the config space
+ */
+static struct pci_config_window *arch_pci_ecam_create(struct device *dev,
+		struct resource *cfgres, struct resource *busr, const struct pci_ecam_ops *ops)
+{
+	int bsz, bus_range, err;
+	struct resource *conflict;
+	struct pci_config_window *cfg;
+
+	if (busr->start > busr->end)
+		return ERR_PTR(-EINVAL);
+
+	cfg = kzalloc(sizeof(*cfg), GFP_KERNEL);
+	if (!cfg)
+		return ERR_PTR(-ENOMEM);
+
+	cfg->parent = dev;
+	cfg->ops = ops;
+	cfg->busr.start = busr->start;
+	cfg->busr.end = busr->end;
+	cfg->busr.flags = IORESOURCE_BUS;
+	bus_range = resource_size(cfgres) >> ops->bus_shift;
+
+	bsz = 1 << ops->bus_shift;
+
+	cfg->res.start = cfgres->start;
+	cfg->res.end = cfgres->end;
+	cfg->res.flags = IORESOURCE_MEM | IORESOURCE_BUSY;
+	cfg->res.name = "PCI ECAM";
+
+	conflict = request_resource_conflict(&iomem_resource, &cfg->res);
+	if (conflict) {
+		err = -EBUSY;
+		dev_err(dev, "can't claim ECAM area %pR: address conflict with %s %pR\n",
+			&cfg->res, conflict->name, conflict);
+		goto err_exit;
+	}
+
+	cfg->win = pci_remap_cfgspace(cfgres->start, bus_range * bsz);
+	if (!cfg->win)
+		goto err_exit_iomap;
+
+	if (ops->init) {
+		err = ops->init(cfg);
+		if (err)
+			goto err_exit;
+	}
+	dev_info(dev, "ECAM at %pR for %pR\n", &cfg->res, &cfg->busr);
+
+	return cfg;
+
+err_exit_iomap:
+	err = -ENOMEM;
+	dev_err(dev, "ECAM ioremap failed\n");
+err_exit:
+	pci_ecam_free(cfg);
+	return ERR_PTR(err);
+}
+
 /*
  * Lookup the bus range for the domain in MCFG, and set up config space
  * mapping.
@@ -106,11 +169,16 @@ pci_acpi_setup_ecam_mapping(struct acpi_pci_root *root)
 
 	bus_shift = ecam_ops->bus_shift ? : 20;
 
-	cfgres.start = root->mcfg_addr + (bus_res->start << bus_shift);
-	cfgres.end = cfgres.start + (resource_size(bus_res) << bus_shift) - 1;
-	cfgres.flags = IORESOURCE_MEM;
+	if (bus_shift == 20)
+		cfg = pci_ecam_create(dev, &cfgres, bus_res, ecam_ops);
+	else {
+		cfgres.start = root->mcfg_addr + (bus_res->start << bus_shift);
+		cfgres.end = cfgres.start + (resource_size(bus_res) << bus_shift) - 1;
+		cfgres.end |= BIT(28) + (((PCI_CFG_SPACE_EXP_SIZE - 1) & 0xf00) << 16);
+		cfgres.flags = IORESOURCE_MEM;
+		cfg = arch_pci_ecam_create(dev, &cfgres, bus_res, ecam_ops);
+	}
 
-	cfg = pci_ecam_create(dev, &cfgres, bus_res, ecam_ops);
 	if (IS_ERR(cfg)) {
 		dev_err(dev, "%04x:%pR error %ld mapping ECAM\n", seg, bus_res, PTR_ERR(cfg));
 		return NULL;

arch/loongarch/pci/pci.c

@@ -9,6 +9,7 @@
 #include <linux/types.h>
 #include <linux/pci.h>
 #include <linux/vgaarb.h>
+#include <asm/cacheflush.h>
 #include <asm/loongson.h>
 
 #define PCI_DEVICE_ID_LOONGSON_HOST     0x7a00
@@ -45,12 +46,10 @@ static int __init pcibios_init(void)
 	unsigned int lsize;
 
 	/*
-	 * Set PCI cacheline size to that of the highest level in the
+	 * Set PCI cacheline size to that of the last level in the
 	 * cache hierarchy.
 	 */
-	lsize = cpu_dcache_line_size();
-	lsize = cpu_vcache_line_size() ? : lsize;
-	lsize = cpu_scache_line_size() ? : lsize;
+	lsize = cpu_last_level_cache_line_size();
 
 	BUG_ON(!lsize);
 

drivers/platform/Kconfig

@@ -3,6 +3,8 @@ if MIPS
 source "drivers/platform/mips/Kconfig"
 endif
 
+source "drivers/platform/loongarch/Kconfig"
+
 source "drivers/platform/goldfish/Kconfig"
 
 source "drivers/platform/chrome/Kconfig"

drivers/platform/Makefile

@@ -4,6 +4,7 @@
 #
 
 obj-$(CONFIG_X86)		+= x86/
+obj-$(CONFIG_LOONGARCH)		+= loongarch/
 obj-$(CONFIG_MELLANOX_PLATFORM)	+= mellanox/
 obj-$(CONFIG_MIPS)		+= mips/
 obj-$(CONFIG_OLPC_EC)		+= olpc/

drivers/platform/loongarch/Kconfig

+#
+# LoongArch Platform Specific Drivers
+#
+
+menuconfig LOONGARCH_PLATFORM_DEVICES
+	bool "LoongArch Platform Specific Device Drivers"
+	default y
+	depends on LOONGARCH
+	help
+	  Say Y here to get to see options for device drivers of various
+	  LoongArch platforms, including vendor-specific laptop/desktop
+	  extension and hardware monitor drivers. This option itself does
+	  not add any kernel code.
+
+	  If you say N, all options in this submenu will be skipped and disabled.
+
+if LOONGARCH_PLATFORM_DEVICES
+
+config LOONGSON_LAPTOP
+	tristate "Generic Loongson-3 Laptop Driver"
+	depends on ACPI
+	depends on BACKLIGHT_CLASS_DEVICE
+	depends on INPUT
+	depends on MACH_LOONGSON64
+	select ACPI_VIDEO
+	select INPUT_SPARSEKMAP
+	default y
+	help
+	  ACPI-based Loongson-3 family laptops generic driver.
+
+endif # LOONGARCH_PLATFORM_DEVICES

drivers/platform/loongarch/Makefile

+obj-$(CONFIG_LOONGSON_LAPTOP) += loongson-laptop.o

drivers/platform/loongarch/loongson-laptop.c

+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  Generic Loongson processor based LAPTOP/ALL-IN-ONE driver
+ *
+ *  Jianmin Lv <lvjianmin@loongson.cn>
+ *  Huacai Chen <chenhuacai@loongson.cn>
+ *
+ * Copyright (C) 2022 Loongson Technology Corporation Limited
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/acpi.h>
+#include <linux/backlight.h>
+#include <linux/device.h>
+#include <linux/input.h>
+#include <linux/input/sparse-keymap.h>
+#include <linux/platform_device.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <acpi/video.h>
+
+/* 1. Driver-wide structs and misc. variables */
+
+/* ACPI HIDs */
+#define LOONGSON_ACPI_EC_HID	"PNP0C09"
+#define LOONGSON_ACPI_HKEY_HID	"LOON0000"
+
+#define ACPI_LAPTOP_NAME "loongson-laptop"
+#define ACPI_LAPTOP_ACPI_EVENT_PREFIX "loongson"
+
+#define MAX_ACPI_ARGS			3
+#define GENERIC_HOTKEY_MAP_MAX		64
+
+#define GENERIC_EVENT_TYPE_OFF		12
+#define GENERIC_EVENT_TYPE_MASK		0xF000
+#define GENERIC_EVENT_CODE_MASK		0x0FFF
+
+struct generic_sub_driver {
+	u32 type;
+	char *name;
+	acpi_handle *handle;
+	struct acpi_device *device;
+	struct platform_driver *driver;
+	int (*init)(struct generic_sub_driver *sub_driver);
+	void (*notify)(struct generic_sub_driver *sub_driver, u32 event);
+	u8 acpi_notify_installed;
+};
+
+static u32 input_device_registered;
+static struct input_dev *generic_inputdev;
+
+static acpi_handle hotkey_handle;
+static struct key_entry hotkey_keycode_map[GENERIC_HOTKEY_MAP_MAX];
+
+int loongson_laptop_turn_on_backlight(void);
+int loongson_laptop_turn_off_backlight(void);
+static int loongson_laptop_backlight_update(struct backlight_device *bd);
+
+/* 2. ACPI Helpers and device model */
+
+static int acpi_evalf(acpi_handle handle, int *res, char *method, char *fmt, ...)
+{
+	char res_type;
+	char *fmt0 = fmt;
+	va_list ap;
+	int success, quiet;
+	acpi_status status;
+	struct acpi_object_list params;
+	struct acpi_buffer result, *resultp;
+	union acpi_object in_objs[MAX_ACPI_ARGS], out_obj;
+
+	if (!*fmt) {
+		pr_err("acpi_evalf() called with empty format\n");
+		return 0;
+	}
+
+	if (*fmt == 'q') {
+		quiet = 1;
+		fmt++;
+	} else
+		quiet = 0;
+
+	res_type = *(fmt++);
+
+	params.count = 0;
+	params.pointer = &in_objs[0];
+
+	va_start(ap, fmt);
+	while (*fmt) {
+		char c = *(fmt++);
+		switch (c) {
+		case 'd':	/* int */
+			in_objs[params.count].integer.value = va_arg(ap, int);
+			in_objs[params.count++].type = ACPI_TYPE_INTEGER;
+			break;
+			/* add more types as needed */
+		default:
+			pr_err("acpi_evalf() called with invalid format character '%c'\n", c);
+			va_end(ap);
+			return 0;
+		}
+	}
+	va_end(ap);
+
+	if (res_type != 'v') {
+		result.length = sizeof(out_obj);
+		result.pointer = &out_obj;
+		resultp = &result;
+	} else
+		resultp = NULL;
+
+	status = acpi_evaluate_object(handle, method, &params, resultp);
+
+	switch (res_type) {
+	case 'd':		/* int */
+		success = (status == AE_OK && out_obj.type == ACPI_TYPE_INTEGER);
+		if (success && res)
+			*res = out_obj.integer.value;
+		break;
+	case 'v':		/* void */
+		success = status == AE_OK;
+		break;
+		/* add more types as needed */
+	default:
+		pr_err("acpi_evalf() called with invalid format character '%c'\n", res_type);
+		return 0;
+	}
+
+	if (!success && !quiet)
+		pr_err("acpi_evalf(%s, %s, ...) failed: %s\n",
+		       method, fmt0, acpi_format_exception(status));
+
+	return success;
+}
+
+static int hotkey_status_get(int *status)
+{
+	if (!acpi_evalf(hotkey_handle, status, "GSWS", "d"))
+		return -EIO;
+
+	return 0;
+}
+
+static void dispatch_acpi_notify(acpi_handle handle, u32 event, void *data)
+{
+	struct generic_sub_driver *sub_driver = data;
+
+	if (!sub_driver || !sub_driver->notify)
+		return;
+	sub_driver->notify(sub_driver, event);
+}
+
+static int __init setup_acpi_notify(struct generic_sub_driver *sub_driver)
+{
+	acpi_status status;
+
+	if (!*sub_driver->handle)
+		return 0;
+
+	sub_driver->device = acpi_fetch_acpi_dev(*sub_driver->handle);
+	if (!sub_driver->device) {
+		pr_err("acpi_fetch_acpi_dev(%s) failed\n", sub_driver->name);
+		return -ENODEV;
+	}
+
+	sub_driver->device->driver_data = sub_driver;
+	sprintf(acpi_device_class(sub_driver->device), "%s/%s",
+		ACPI_LAPTOP_ACPI_EVENT_PREFIX, sub_driver->name);
+
+	status = acpi_install_notify_handler(*sub_driver->handle,
+			sub_driver->type, dispatch_acpi_notify, sub_driver);
+	if (ACPI_FAILURE(status)) {
+		if (status == AE_ALREADY_EXISTS) {
+			pr_notice("Another device driver is already "
+				  "handling %s events\n", sub_driver->name);
+		} else {
+			pr_err("acpi_install_notify_handler(%s) failed: %s\n",
+			       sub_driver->name, acpi_format_exception(status));
+		}
+		return -ENODEV;
+	}
+	sub_driver->acpi_notify_installed = 1;
+
+	return 0;
+}
+
+static int loongson_hotkey_suspend(struct device *dev)
+{
+	return 0;
+}
+
+static int loongson_hotkey_resume(struct device *dev)
+{
+	int status = 0;
+	struct key_entry ke;
+	struct backlight_device *bd;
+
+	/*
+	 * Only if the firmware supports SW_LID event model, we can handle the
+	 * event. This is for the consideration of development board without EC.
+	 */
+	if (test_bit(SW_LID, generic_inputdev->swbit)) {
+		if (hotkey_status_get(&status) < 0)
+			return -EIO;
+		/*
+		 * The input device sw element records the last lid status.
+		 * When the system is awakened by other wake-up sources,
+		 * the lid event will also be reported. The judgment of
+		 * adding SW_LID bit which in sw element can avoid this
+		 * case.
+		 *
+		 * Input system will drop lid event when current lid event
+		 * value and last lid status in the same. So laptop driver
+		 * doesn't report repeated events.
+		 *
+		 * Lid status is generally 0, but hardware exception is
+		 * considered. So add lid status confirmation.
+		 */
+		if (test_bit(SW_LID, generic_inputdev->sw) && !(status & (1 << SW_LID))) {
+			ke.type = KE_SW;
+			ke.sw.value = (u8)status;
+			ke.sw.code = SW_LID;
+			sparse_keymap_report_entry(generic_inputdev, &ke, 1, true);
+		}
+	}
+
+	bd = backlight_device_get_by_type(BACKLIGHT_PLATFORM);
+	if (bd) {
+		loongson_laptop_backlight_update(bd) ?
+		pr_warn("Loongson_backlight: resume brightness failed") :
+		pr_info("Loongson_backlight: resume brightness %d\n", bd->props.brightness);
+	}
+
+	return 0;
+}
+
+static DEFINE_SIMPLE_DEV_PM_OPS(loongson_hotkey_pm,
+		loongson_hotkey_suspend, loongson_hotkey_resume);
+
+static int loongson_hotkey_probe(struct platform_device *pdev)
+{
+	hotkey_handle = ACPI_HANDLE(&pdev->dev);
+
+	if (!hotkey_handle)
+		return -ENODEV;
+
+	return 0;
+}
+
+static const struct acpi_device_id loongson_device_ids[] = {
+	{LOONGSON_ACPI_HKEY_HID, 0},
+	{"", 0},
+};
+MODULE_DEVICE_TABLE(acpi, loongson_device_ids);
+
+static struct platform_driver loongson_hotkey_driver = {
+	.probe		= loongson_hotkey_probe,
+	.driver		= {
+		.name	= "loongson-hotkey",
+		.owner	= THIS_MODULE,
+		.pm	= pm_ptr(&loongson_hotkey_pm),
+		.acpi_match_table = loongson_device_ids,
+	},
+};
+
+static int hotkey_map(void)
+{
+	u32 index;
+	acpi_status status;
+	struct acpi_buffer buf;
+	union acpi_object *pack;
+
+	buf.length = ACPI_ALLOCATE_BUFFER;
+	status = acpi_evaluate_object_typed(hotkey_handle, "KMAP", NULL, &buf, ACPI_TYPE_PACKAGE);
+	if (status != AE_OK) {
+		pr_err("ACPI exception: %s\n", acpi_format_exception(status));
+		return -1;
+	}
+	pack = buf.pointer;
+	for (index = 0; index < pack->package.count; index++) {
+		union acpi_object *element, *sub_pack;
+
+		sub_pack = &pack->package.elements[index];
+
+		element = &sub_pack->package.elements[0];
+		hotkey_keycode_map[index].type = element->integer.value;
+		element = &sub_pack->package.elements[1];
+		hotkey_keycode_map[index].code = element->integer.value;
+		element = &sub_pack->package.elements[2];
+		hotkey_keycode_map[index].keycode = element->integer.value;
+	}
+
+	return 0;
+}
+
+static int hotkey_backlight_set(bool enable)
+{
+	if (!acpi_evalf(hotkey_handle, NULL, "VCBL", "vd", enable ? 1 : 0))
+		return -EIO;
+
+	return 0;
+}
+
+static int ec_get_brightness(void)
+{
+	int status = 0;
+
+	if (!hotkey_handle)
+		return -ENXIO;
+
+	if (!acpi_evalf(hotkey_handle, &status, "ECBG", "d"))
+		return -EIO;
+
+	return status;
+}
+
+static int ec_set_brightness(int level)
+{
+
+	int ret = 0;
+
+	if (!hotkey_handle)
+		return -ENXIO;
+
+	if (!acpi_evalf(hotkey_handle, NULL, "ECBS", "vd", level))
+		ret = -EIO;
+
+	return ret;
+}
+
+static int ec_backlight_level(u8 level)
+{
+	int status = 0;
+
+	if (!hotkey_handle)
+		return -ENXIO;
+
+	if (!acpi_evalf(hotkey_handle, &status, "ECLL", "d"))
+		return -EIO;
+
+	if ((status < 0) || (level > status))
+		return status;
+
+	if (!acpi_evalf(hotkey_handle, &status, "ECSL", "d"))
+		return -EIO;
+
+	if ((status < 0) || (level < status))
+		return status;
+
+	return level;
+}
+
+static int loongson_laptop_backlight_update(struct backlight_device *bd)
+{
+	int lvl = ec_backlight_level(bd->props.brightness);
+
+	if (lvl < 0)
+		return -EIO;
+	if (ec_set_brightness(lvl))
+		return -EIO;
+
+	return 0;
+}
+
+static int loongson_laptop_get_brightness(struct backlight_device *bd)
+{
+	int level;
+
+	level = ec_get_brightness();
+	if (level < 0)
+		return -EIO;
+
+	return level;
+}
+
+static const struct backlight_ops backlight_laptop_ops = {
+	.update_status = loongson_laptop_backlight_update,
+	.get_brightness = loongson_laptop_get_brightness,
+};
+
+static int laptop_backlight_register(void)
+{
+	int status = 0;
+	struct backlight_properties props;
+
+	memset(&props, 0, sizeof(props));
+
+	if (!acpi_evalf(hotkey_handle, &status, "ECLL", "d"))
+		return -EIO;
+
+	props.brightness = 1;
+	props.max_brightness = status;
+	props.type = BACKLIGHT_PLATFORM;
+
+	backlight_device_register("loongson_laptop",
+				NULL, NULL, &backlight_laptop_ops, &props);
+
+	return 0;
+}
+
+int loongson_laptop_turn_on_backlight(void)
+{
+	int status;
+	union acpi_object arg0 = { ACPI_TYPE_INTEGER };
+	struct acpi_object_list args = { 1, &arg0 };
+
+	arg0.integer.value = 1;
+	status = acpi_evaluate_object(NULL, "\\BLSW", &args, NULL);
+	if (ACPI_FAILURE(status)) {
+		pr_info("Loongson lvds error: 0x%x\n", status);
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
+int loongson_laptop_turn_off_backlight(void)
+{
+	int status;
+	union acpi_object arg0 = { ACPI_TYPE_INTEGER };
+	struct acpi_object_list args = { 1, &arg0 };
+
+	arg0.integer.value = 0;
+	status = acpi_evaluate_object(NULL, "\\BLSW", &args, NULL);
+	if (ACPI_FAILURE(status)) {
+		pr_info("Loongson lvds error: 0x%x\n", status);
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
+static int __init event_init(struct generic_sub_driver *sub_driver)
+{
+	int ret;
+
+	ret = hotkey_map();
+	if (ret < 0) {
+		pr_err("Failed to parse keymap from DSDT\n");
+		return ret;
+	}
+
+	ret = sparse_keymap_setup(generic_inputdev, hotkey_keycode_map, NULL);
+	if (ret < 0) {
+		pr_err("Failed to setup input device keymap\n");
+		input_free_device(generic_inputdev);
+
+		return ret;
+	}
+
+	/*
+	 * This hotkey driver handle backlight event when
+	 * acpi_video_get_backlight_type() gets acpi_backlight_vendor
+	 */
+	if (acpi_video_get_backlight_type() == acpi_backlight_vendor)
+		hotkey_backlight_set(true);
+	else
+		hotkey_backlight_set(false);
+
+	pr_info("ACPI: enabling firmware HKEY event interface...\n");
+
+	return ret;
+}
+
+static void event_notify(struct generic_sub_driver *sub_driver, u32 event)
+{
+	int type, scan_code;
+	struct key_entry *ke = NULL;
+
+	scan_code = event & GENERIC_EVENT_CODE_MASK;
+	type = (event & GENERIC_EVENT_TYPE_MASK) >> GENERIC_EVENT_TYPE_OFF;
+	ke = sparse_keymap_entry_from_scancode(generic_inputdev, scan_code);
+	if (ke) {
+		if (type == KE_SW) {
+			int status = 0;
+
+			if (hotkey_status_get(&status) < 0)
+				return;
+
+			ke->sw.value = !!(status & (1 << ke->sw.code));
+		}
+		sparse_keymap_report_entry(generic_inputdev, ke, 1, true);
+	}
+}
+
+/* 3. Infrastructure */
+
+static void generic_subdriver_exit(struct generic_sub_driver *sub_driver);
+
+static int __init generic_subdriver_init(struct generic_sub_driver *sub_driver)
+{
+	int ret;
+
+	if (!sub_driver || !sub_driver->driver)
+		return -EINVAL;
+
+	ret = platform_driver_register(sub_driver->driver);
+	if (ret)
+		return -EINVAL;
+
+	if (sub_driver->init)
+		sub_driver->init(sub_driver);
+
+	if (sub_driver->notify) {
+		ret = setup_acpi_notify(sub_driver);
+		if (ret == -ENODEV) {
+			ret = 0;
+			goto err_out;
+		}
+		if (ret < 0)
+			goto err_out;
+	}
+
+	return 0;
+
+err_out:
+	generic_subdriver_exit(sub_driver);
+	return (ret < 0) ? ret : 0;
+}
+
+static void generic_subdriver_exit(struct generic_sub_driver *sub_driver)
+{
+
+	if (sub_driver->acpi_notify_installed) {
+		acpi_remove_notify_handler(*sub_driver->handle,
+					   sub_driver->type, dispatch_acpi_notify);
+		sub_driver->acpi_notify_installed = 0;
+	}
+	platform_driver_unregister(sub_driver->driver);
+}
+
+static struct generic_sub_driver generic_sub_drivers[] __refdata = {
+	{
+		.name = "hotkey",
+		.init = event_init,
+		.notify = event_notify,
+		.handle = &hotkey_handle,
+		.type = ACPI_DEVICE_NOTIFY,
+		.driver = &loongson_hotkey_driver,
+	},
+};
+
+static int __init generic_acpi_laptop_init(void)
+{
+	bool ec_found;
+	int i, ret, status;
+
+	if (acpi_disabled)
+		return -ENODEV;
+
+	/* The EC device is required */
+	ec_found = acpi_dev_found(LOONGSON_ACPI_EC_HID);
+	if (!ec_found)
+		return -ENODEV;
+
+	/* Enable SCI for EC */
+	acpi_write_bit_register(ACPI_BITREG_SCI_ENABLE, 1);
+
+	generic_inputdev = input_allocate_device();
+	if (!generic_inputdev) {
+		pr_err("Unable to allocate input device\n");
+		return -ENOMEM;
+	}
+
+	/* Prepare input device, but don't register */
+	generic_inputdev->name =
+		"Loongson Generic Laptop/All-in-One Extra Buttons";
+	generic_inputdev->phys = ACPI_LAPTOP_NAME "/input0";
+	generic_inputdev->id.bustype = BUS_HOST;
+	generic_inputdev->dev.parent = NULL;
+
+	/* Init subdrivers */
+	for (i = 0; i < ARRAY_SIZE(generic_sub_drivers); i++) {
+		ret = generic_subdriver_init(&generic_sub_drivers[i]);
+		if (ret < 0) {
+			input_free_device(generic_inputdev);
+			while (--i >= 0)
+				generic_subdriver_exit(&generic_sub_drivers[i]);
+			return ret;
+		}
+	}
+
+	ret = input_register_device(generic_inputdev);
+	if (ret < 0) {
+		input_free_device(generic_inputdev);
+		while (--i >= 0)
+			generic_subdriver_exit(&generic_sub_drivers[i]);
+		pr_err("Unable to register input device\n");
+		return ret;
+	}
+
+	input_device_registered = 1;
+
+	if (acpi_evalf(hotkey_handle, &status, "ECBG", "d")) {
+		pr_info("Loongson Laptop used, init brightness is 0x%x\n", status);
+		ret = laptop_backlight_register();
+		if (ret < 0)
+			pr_err("Loongson Laptop: laptop-backlight device register failed\n");
+	}
+
+	return 0;
+}
+
+static void __exit generic_acpi_laptop_exit(void)
+{
+	if (generic_inputdev) {
+		if (input_device_registered)
+			input_unregister_device(generic_inputdev);
+		else
+			input_free_device(generic_inputdev);
+	}
+}
+
+module_init(generic_acpi_laptop_init);
+module_exit(generic_acpi_laptop_exit);
+
+MODULE_AUTHOR("Jianmin Lv <lvjianmin@loongson.cn>");
+MODULE_AUTHOR("Huacai Chen <chenhuacai@loongson.cn>");
+MODULE_DESCRIPTION("Loongson Laptop/All-in-One ACPI Driver");
+MODULE_LICENSE("GPL");