Merge tag 'loongarch-6.6' of...

Merge tag 'loongarch-6.6' of git://git.kernel.org/pub/scm/linux/kernel/git/chenhuacai/linux-loongson

Pull LoongArch updates from Huacai Chen:

 - Allow usage of LSX/LASX in the kernel, and use them for
   SIMD-optimized RAID5/RAID6 routines

 - Add Loongson Binary Translation (LBT) extension support

 - Add basic KGDB & KDB support

 - Add building with kcov coverage

 - Add KFENCE (Kernel Electric-Fence) support

 - Add KASAN (Kernel Address Sanitizer) support

 - Some bug fixes and other small changes

 - Update the default config file

* tag 'loongarch-6.6' of git://git.kernel.org/pub/scm/linux/kernel/git/chenhuacai/linux-loongson: (25 commits)
  LoongArch: Update Loongson-3 default config file
  LoongArch: Add KASAN (Kernel Address Sanitizer) support
  LoongArch: Simplify the processing of jumping new kernel for KASLR
  kasan: Add (pmd|pud)_init for LoongArch zero_(pud|p4d)_populate process
  kasan: Add __HAVE_ARCH_SHADOW_MAP to support arch specific mapping
  LoongArch: Add KFENCE (Kernel Electric-Fence) support
  LoongArch: Get partial stack information when providing regs parameter
  LoongArch: mm: Add page table mapped mode support for virt_to_page()
  kfence: Defer the assignment of the local variable addr
  LoongArch: Allow building with kcov coverage
  LoongArch: Provide kaslr_offset() to get kernel offset
  LoongArch: Add basic KGDB & KDB support
  LoongArch: Add Loongson Binary Translation (LBT) extension support
  raid6: Add LoongArch SIMD recovery implementation
  raid6: Add LoongArch SIMD syndrome calculation
  LoongArch: Add SIMD-optimized XOR routines
  LoongArch: Allow usage of LSX/LASX in the kernel
  LoongArch: Define symbol 'fault' as a local label in fpu.S
  LoongArch: Adjust {copy, clear}_user exception handler behavior
  LoongArch: Use static defined zero page rather than allocated
  ...

Documentation/dev-tools/kasan.rst

@@ -41,8 +41,8 @@ Support
 Architectures
 ~~~~~~~~~~~~~
 
-Generic KASAN is supported on x86_64, arm, arm64, powerpc, riscv, s390, and
-xtensa, and the tag-based KASAN modes are supported only on arm64.
+Generic KASAN is supported on x86_64, arm, arm64, powerpc, riscv, s390, xtensa,
+and loongarch, and the tag-based KASAN modes are supported only on arm64.
 
 Compilers
 ~~~~~~~~~

Documentation/features/debug/KASAN/arch-support.txt

@@ -13,7 +13,7 @@
     |        csky: | TODO |
     |     hexagon: | TODO |
     |        ia64: | TODO |
-    |   loongarch: | TODO |
+    |   loongarch: |  ok  |
     |        m68k: | TODO |
     |  microblaze: | TODO |
     |        mips: | TODO |

Documentation/features/debug/kcov/arch-support.txt

@@ -13,7 +13,7 @@
     |        csky: | TODO |
     |     hexagon: | TODO |
     |        ia64: | TODO |
-    |   loongarch: | TODO |
+    |   loongarch: |  ok  |
     |        m68k: | TODO |
     |  microblaze: | TODO |
     |        mips: |  ok  |

Documentation/features/debug/kgdb/arch-support.txt

@@ -13,7 +13,7 @@
     |        csky: | TODO |
     |     hexagon: |  ok  |
     |        ia64: | TODO |
-    |   loongarch: | TODO |
+    |   loongarch: |  ok  |
     |        m68k: | TODO |
     |  microblaze: |  ok  |
     |        mips: |  ok  |

Documentation/translations/zh_CN/dev-tools/kasan.rst

@@ -42,7 +42,7 @@ KASAN有三种模式:
 体系架构
 ~~~~~~~~
 
-在x86_64、arm、arm64、powerpc、riscv、s390和xtensa上支持通用KASAN，
+在x86_64、arm、arm64、powerpc、riscv、s390、xtensa和loongarch上支持通用KASAN，
 而基于标签的KASAN模式只在arm64上支持。
 
 编译器

arch/loongarch/Kconfig

@@ -8,11 +8,13 @@ config LOONGARCH
 	select ACPI_PPTT if ACPI
 	select ACPI_SYSTEM_POWER_STATES_SUPPORT	if ACPI
 	select ARCH_BINFMT_ELF_STATE
+	select ARCH_DISABLE_KASAN_INLINE
 	select ARCH_ENABLE_MEMORY_HOTPLUG
 	select ARCH_ENABLE_MEMORY_HOTREMOVE
 	select ARCH_HAS_ACPI_TABLE_UPGRADE	if ACPI
 	select ARCH_HAS_CPU_FINALIZE_INIT
 	select ARCH_HAS_FORTIFY_SOURCE
+	select ARCH_HAS_KCOV
 	select ARCH_HAS_NMI_SAFE_THIS_CPU_OPS
 	select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
 	select ARCH_HAS_PTE_SPECIAL
@@ -91,6 +93,9 @@ config LOONGARCH
 	select HAVE_ARCH_AUDITSYSCALL
 	select HAVE_ARCH_JUMP_LABEL
 	select HAVE_ARCH_JUMP_LABEL_RELATIVE
+	select HAVE_ARCH_KASAN
+	select HAVE_ARCH_KFENCE
+	select HAVE_ARCH_KGDB if PERF_EVENTS
 	select HAVE_ARCH_MMAP_RND_BITS if MMU
 	select HAVE_ARCH_SECCOMP_FILTER
 	select HAVE_ARCH_TRACEHOOK
@@ -115,6 +120,7 @@ config LOONGARCH
 	select HAVE_FUNCTION_GRAPH_RETVAL if HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FUNCTION_TRACER
+	select HAVE_GCC_PLUGINS
 	select HAVE_GENERIC_VDSO
 	select HAVE_HW_BREAKPOINT if PERF_EVENTS
 	select HAVE_IOREMAP_PROT
@@ -254,6 +260,9 @@ config AS_HAS_LSX_EXTENSION
 config AS_HAS_LASX_EXTENSION
 	def_bool $(as-instr,xvld \$xr0$(comma)\$a0$(comma)0)
 
+config AS_HAS_LBT_EXTENSION
+	def_bool $(as-instr,movscr2gr \$a0$(comma)\$scr0)
+
 menu "Kernel type and options"
 
 source "kernel/Kconfig.hz"
@@ -534,6 +543,18 @@ config CPU_HAS_LASX
 
 	  If unsure, say Y.
 
+config CPU_HAS_LBT
+	bool "Support for the Loongson Binary Translation Extension"
+	depends on AS_HAS_LBT_EXTENSION
+	help
+	  Loongson Binary Translation (LBT) introduces 4 scratch registers (SCR0
+	  to SCR3), x86/ARM eflags (eflags) and x87 fpu stack pointer (ftop).
+	  Enabling this option allows the kernel to allocate and switch registers
+	  specific to LBT.
+
+	  If you want to use this feature, such as the Loongson Architecture
+	  Translator (LAT), say Y.
+
 config CPU_HAS_PREFETCH
 	bool
 	default y
@@ -638,6 +659,11 @@ config ARCH_MMAP_RND_BITS_MAX
 config ARCH_SUPPORTS_UPROBES
 	def_bool y
 
+config KASAN_SHADOW_OFFSET
+	hex
+	default 0x0
+	depends on KASAN
+
 menu "Power management options"
 
 config ARCH_SUSPEND_POSSIBLE

arch/loongarch/Makefile

@@ -84,7 +84,10 @@ LDFLAGS_vmlinux			+= -static -pie --no-dynamic-linker -z notext
 endif
 
 cflags-y += $(call cc-option, -mno-check-zero-division)
+
+ifndef CONFIG_KASAN
 cflags-y += -fno-builtin-memcpy -fno-builtin-memmove -fno-builtin-memset
+endif
 
 load-y		= 0x9000000000200000
 bootvars-y	= VMLINUX_LOAD_ADDRESS=$(load-y)

arch/loongarch/configs/loongson3_defconfig

@@ -30,7 +30,6 @@ CONFIG_NAMESPACES=y
 CONFIG_USER_NS=y
 CONFIG_CHECKPOINT_RESTORE=y
 CONFIG_SCHED_AUTOGROUP=y
-CONFIG_SYSFS_DEPRECATED=y
 CONFIG_RELAY=y
 CONFIG_BLK_DEV_INITRD=y
 CONFIG_EXPERT=y
@@ -47,8 +46,12 @@ CONFIG_SMP=y
 CONFIG_HOTPLUG_CPU=y
 CONFIG_NR_CPUS=64
 CONFIG_NUMA=y
+CONFIG_CPU_HAS_FPU=y
+CONFIG_CPU_HAS_LSX=y
+CONFIG_CPU_HAS_LASX=y
 CONFIG_KEXEC=y
 CONFIG_CRASH_DUMP=y
+CONFIG_RANDOMIZE_BASE=y
 CONFIG_SUSPEND=y
 CONFIG_HIBERNATION=y
 CONFIG_ACPI=y
@@ -63,6 +66,7 @@ CONFIG_EFI_ZBOOT=y
 CONFIG_EFI_GENERIC_STUB_INITRD_CMDLINE_LOADER=y
 CONFIG_EFI_CAPSULE_LOADER=m
 CONFIG_EFI_TEST=m
+CONFIG_JUMP_LABEL=y
 CONFIG_MODULES=y
 CONFIG_MODULE_FORCE_LOAD=y
 CONFIG_MODULE_UNLOAD=y
@@ -108,7 +112,12 @@ CONFIG_IP_PNP_BOOTP=y
 CONFIG_IP_PNP_RARP=y
 CONFIG_NET_IPIP=m
 CONFIG_NET_IPGRE_DEMUX=m
+CONFIG_NET_IPGRE=m
+CONFIG_NET_IPGRE_BROADCAST=y
 CONFIG_IP_MROUTE=y
+CONFIG_IP_MROUTE_MULTIPLE_TABLES=y
+CONFIG_IP_PIMSM_V1=y
+CONFIG_IP_PIMSM_V2=y
 CONFIG_INET_ESP=m
 CONFIG_INET_UDP_DIAG=y
 CONFIG_TCP_CONG_ADVANCED=y
@@ -137,7 +146,6 @@ CONFIG_NFT_MASQ=m
 CONFIG_NFT_REDIR=m
 CONFIG_NFT_NAT=m
 CONFIG_NFT_TUNNEL=m
-CONFIG_NFT_OBJREF=m
 CONFIG_NFT_QUEUE=m
 CONFIG_NFT_QUOTA=m
 CONFIG_NFT_REJECT=m
@@ -208,7 +216,11 @@ CONFIG_IP_VS=m
 CONFIG_IP_VS_IPV6=y
 CONFIG_IP_VS_PROTO_TCP=y
 CONFIG_IP_VS_PROTO_UDP=y
+CONFIG_IP_VS_PROTO_ESP=y
+CONFIG_IP_VS_PROTO_AH=y
+CONFIG_IP_VS_PROTO_SCTP=y
 CONFIG_IP_VS_RR=m
+CONFIG_IP_VS_WRR=m
 CONFIG_IP_VS_NFCT=y
 CONFIG_NF_TABLES_IPV4=y
 CONFIG_NFT_DUP_IPV4=m
@@ -227,7 +239,6 @@ CONFIG_IP_NF_TARGET_MASQUERADE=m
 CONFIG_IP_NF_TARGET_NETMAP=m
 CONFIG_IP_NF_TARGET_REDIRECT=m
 CONFIG_IP_NF_MANGLE=m
-CONFIG_IP_NF_TARGET_CLUSTERIP=m
 CONFIG_IP_NF_TARGET_ECN=m
 CONFIG_IP_NF_TARGET_TTL=m
 CONFIG_IP_NF_RAW=m
@@ -363,6 +374,8 @@ CONFIG_MTD_CFI_AMDSTD=m
 CONFIG_MTD_CFI_STAA=m
 CONFIG_MTD_RAM=m
 CONFIG_MTD_ROM=m
+CONFIG_MTD_UBI=m
+CONFIG_MTD_UBI_BLOCK=y
 CONFIG_PARPORT=y
 CONFIG_PARPORT_PC=y
 CONFIG_PARPORT_SERIAL=y
@@ -370,6 +383,7 @@ CONFIG_PARPORT_PC_FIFO=y
 CONFIG_ZRAM=m
 CONFIG_ZRAM_DEF_COMP_ZSTD=y
 CONFIG_BLK_DEV_LOOP=y
+CONFIG_BLK_DEV_DRBD=m
 CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_SIZE=8192
@@ -516,6 +530,8 @@ CONFIG_STMMAC_ETH=y
 # CONFIG_NET_VENDOR_TEHUTI is not set
 # CONFIG_NET_VENDOR_TI is not set
 # CONFIG_NET_VENDOR_VIA is not set
+CONFIG_NGBE=y
+CONFIG_TXGBE=y
 # CONFIG_NET_VENDOR_WIZNET is not set
 # CONFIG_NET_VENDOR_XILINX is not set
 CONFIG_PPP=m
@@ -602,9 +618,15 @@ CONFIG_HW_RANDOM_VIRTIO=m
 CONFIG_I2C_CHARDEV=y
 CONFIG_I2C_PIIX4=y
 CONFIG_I2C_GPIO=y
+CONFIG_I2C_LS2X=y
 CONFIG_SPI=y
+CONFIG_SPI_LOONGSON_PCI=m
+CONFIG_SPI_LOONGSON_PLATFORM=m
+CONFIG_PINCTRL=y
+CONFIG_PINCTRL_LOONGSON2=y
 CONFIG_GPIO_SYSFS=y
 CONFIG_GPIO_LOONGSON=y
+CONFIG_GPIO_LOONGSON_64BIT=y
 CONFIG_POWER_RESET=y
 CONFIG_POWER_RESET_RESTART=y
 CONFIG_POWER_RESET_SYSCON=y
@@ -614,6 +636,7 @@ CONFIG_SENSORS_LM75=m
 CONFIG_SENSORS_LM93=m
 CONFIG_SENSORS_W83795=m
 CONFIG_SENSORS_W83627HF=m
+CONFIG_LOONGSON2_THERMAL=m
 CONFIG_RC_CORE=m
 CONFIG_LIRC=y
 CONFIG_RC_DECODERS=y
@@ -643,6 +666,7 @@ CONFIG_DRM_AMDGPU_USERPTR=y
 CONFIG_DRM_AST=y
 CONFIG_DRM_QXL=m
 CONFIG_DRM_VIRTIO_GPU=m
+CONFIG_DRM_LOONGSON=y
 CONFIG_FB=y
 CONFIG_FB_EFI=y
 CONFIG_FB_RADEON=y
@@ -712,6 +736,7 @@ CONFIG_UCSI_ACPI=m
 CONFIG_INFINIBAND=m
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_EFI=y
+CONFIG_RTC_DRV_LOONGSON=y
 CONFIG_DMADEVICES=y
 CONFIG_UIO=m
 CONFIG_UIO_PDRV_GENIRQ=m
@@ -745,7 +770,9 @@ CONFIG_COMEDI_NI_LABPC_PCI=m
 CONFIG_COMEDI_NI_PCIDIO=m
 CONFIG_COMEDI_NI_PCIMIO=m
 CONFIG_STAGING=y
-CONFIG_R8188EU=m
+CONFIG_COMMON_CLK_LOONGSON2=y
+CONFIG_LOONGSON2_GUTS=y
+CONFIG_LOONGSON2_PM=y
 CONFIG_PM_DEVFREQ=y
 CONFIG_DEVFREQ_GOV_SIMPLE_ONDEMAND=y
 CONFIG_DEVFREQ_GOV_PERFORMANCE=y
@@ -759,10 +786,17 @@ CONFIG_EXT2_FS_SECURITY=y
 CONFIG_EXT3_FS=y
 CONFIG_EXT3_FS_POSIX_ACL=y
 CONFIG_EXT3_FS_SECURITY=y
+CONFIG_JFS_FS=m
+CONFIG_JFS_POSIX_ACL=y
+CONFIG_JFS_SECURITY=y
 CONFIG_XFS_FS=y
 CONFIG_XFS_QUOTA=y
 CONFIG_XFS_POSIX_ACL=y
+CONFIG_GFS2_FS=m
+CONFIG_GFS2_FS_LOCKING_DLM=y
+CONFIG_OCFS2_FS=m
 CONFIG_BTRFS_FS=y
+CONFIG_BTRFS_FS_POSIX_ACL=y
 CONFIG_FANOTIFY=y
 CONFIG_FANOTIFY_ACCESS_PERMISSIONS=y
 CONFIG_QUOTA=y
@@ -771,11 +805,14 @@ CONFIG_QFMT_V1=m
 CONFIG_QFMT_V2=m
 CONFIG_AUTOFS_FS=y
 CONFIG_FUSE_FS=m
+CONFIG_CUSE=m
+CONFIG_VIRTIO_FS=m
 CONFIG_OVERLAY_FS=y
 CONFIG_OVERLAY_FS_INDEX=y
 CONFIG_OVERLAY_FS_XINO_AUTO=y
 CONFIG_OVERLAY_FS_METACOPY=y
 CONFIG_FSCACHE=y
+CONFIG_CACHEFILES=m
 CONFIG_ISO9660_FS=y
 CONFIG_JOLIET=y
 CONFIG_ZISOFS=y
@@ -784,19 +821,42 @@ CONFIG_MSDOS_FS=m
 CONFIG_VFAT_FS=m
 CONFIG_FAT_DEFAULT_CODEPAGE=936
 CONFIG_FAT_DEFAULT_IOCHARSET="gb2312"
+CONFIG_EXFAT_FS=m
+CONFIG_NTFS3_FS=m
+CONFIG_NTFS3_64BIT_CLUSTER=y
+CONFIG_NTFS3_LZX_XPRESS=y
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
 CONFIG_TMPFS_POSIX_ACL=y
 CONFIG_HUGETLBFS=y
 CONFIG_CONFIGFS_FS=y
+CONFIG_ORANGEFS_FS=m
+CONFIG_ECRYPT_FS=m
+CONFIG_ECRYPT_FS_MESSAGING=y
 CONFIG_HFS_FS=m
 CONFIG_HFSPLUS_FS=m
+CONFIG_UBIFS_FS=m
+CONFIG_UBIFS_FS_ADVANCED_COMPR=y
 CONFIG_CRAMFS=m
 CONFIG_SQUASHFS=y
 CONFIG_SQUASHFS_XATTR=y
 CONFIG_SQUASHFS_LZ4=y
 CONFIG_SQUASHFS_LZO=y
 CONFIG_SQUASHFS_XZ=y
+CONFIG_MINIX_FS=m
+CONFIG_ROMFS_FS=m
+CONFIG_PSTORE=m
+CONFIG_PSTORE_LZO_COMPRESS=m
+CONFIG_PSTORE_LZ4_COMPRESS=m
+CONFIG_PSTORE_LZ4HC_COMPRESS=m
+CONFIG_PSTORE_842_COMPRESS=y
+CONFIG_PSTORE_ZSTD_COMPRESS=y
+CONFIG_PSTORE_ZSTD_COMPRESS_DEFAULT=y
+CONFIG_SYSV_FS=m
+CONFIG_UFS_FS=m
+CONFIG_EROFS_FS=m
+CONFIG_EROFS_FS_ZIP_LZMA=y
+CONFIG_EROFS_FS_PCPU_KTHREAD=y
 CONFIG_NFS_FS=y
 CONFIG_NFS_V3_ACL=y
 CONFIG_NFS_V4=y
@@ -807,6 +867,10 @@ CONFIG_NFSD=y
 CONFIG_NFSD_V3_ACL=y
 CONFIG_NFSD_V4=y
 CONFIG_NFSD_BLOCKLAYOUT=y
+CONFIG_CEPH_FS=m
+CONFIG_CEPH_FSCACHE=y
+CONFIG_CEPH_FS_POSIX_ACL=y
+CONFIG_CEPH_FS_SECURITY_LABEL=y
 CONFIG_CIFS=m
 # CONFIG_CIFS_DEBUG is not set
 CONFIG_9P_FS=y
@@ -814,6 +878,7 @@ CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_CODEPAGE_936=y
 CONFIG_NLS_ASCII=y
 CONFIG_NLS_UTF8=y
+CONFIG_DLM=m
 CONFIG_KEY_DH_OPERATIONS=y
 CONFIG_SECURITY=y
 CONFIG_SECURITY_SELINUX=y
@@ -847,6 +912,7 @@ CONFIG_CRYPTO_USER_API_HASH=m
 CONFIG_CRYPTO_USER_API_SKCIPHER=m
 CONFIG_CRYPTO_USER_API_RNG=m
 CONFIG_CRYPTO_USER_API_AEAD=m
+CONFIG_CRYPTO_CRC32_LOONGARCH=m
 CONFIG_CRYPTO_DEV_VIRTIO=m
 CONFIG_PRINTK_TIME=y
 CONFIG_STRIP_ASM_SYMS=y

arch/loongarch/include/asm/asm-prototypes.h

 /* SPDX-License-Identifier: GPL-2.0 */
 #include <linux/uaccess.h>
 #include <asm/fpu.h>
+#include <asm/lbt.h>
 #include <asm/mmu_context.h>
 #include <asm/page.h>
 #include <asm/ftrace.h>

arch/loongarch/include/asm/asmmacro.h

@@ -10,113 +10,6 @@
 #include <asm/fpregdef.h>
 #include <asm/loongarch.h>
 
-	.macro	parse_v var val
-	\var	= \val
-	.endm
-
-	.macro	parse_r var r
-	\var	= -1
-	.ifc	\r, $r0
-	\var	= 0
-	.endif
-	.ifc	\r, $r1
-	\var	= 1
-	.endif
-	.ifc	\r, $r2
-	\var	= 2
-	.endif
-	.ifc	\r, $r3
-	\var	= 3
-	.endif
-	.ifc	\r, $r4
-	\var	= 4
-	.endif
-	.ifc	\r, $r5
-	\var	= 5
-	.endif
-	.ifc	\r, $r6
-	\var	= 6
-	.endif
-	.ifc	\r, $r7
-	\var	= 7
-	.endif
-	.ifc	\r, $r8
-	\var	= 8
-	.endif
-	.ifc	\r, $r9
-	\var	= 9
-	.endif
-	.ifc	\r, $r10
-	\var	= 10
-	.endif
-	.ifc	\r, $r11
-	\var	= 11
-	.endif
-	.ifc	\r, $r12
-	\var	= 12
-	.endif
-	.ifc	\r, $r13
-	\var	= 13
-	.endif
-	.ifc	\r, $r14
-	\var	= 14
-	.endif
-	.ifc	\r, $r15
-	\var	= 15
-	.endif
-	.ifc	\r, $r16
-	\var	= 16
-	.endif
-	.ifc	\r, $r17
-	\var	= 17
-	.endif
-	.ifc	\r, $r18
-	\var	= 18
-	.endif
-	.ifc	\r, $r19
-	\var	= 19
-	.endif
-	.ifc	\r, $r20
-	\var	= 20
-	.endif
-	.ifc	\r, $r21
-	\var	= 21
-	.endif
-	.ifc	\r, $r22
-	\var	= 22
-	.endif
-	.ifc	\r, $r23
-	\var	= 23
-	.endif
-	.ifc	\r, $r24
-	\var	= 24
-	.endif
-	.ifc	\r, $r25
-	\var	= 25
-	.endif
-	.ifc	\r, $r26
-	\var	= 26
-	.endif
-	.ifc	\r, $r27
-	\var	= 27
-	.endif
-	.ifc	\r, $r28
-	\var	= 28
-	.endif
-	.ifc	\r, $r29
-	\var	= 29
-	.endif
-	.ifc	\r, $r30
-	\var	= 30
-	.endif
-	.ifc	\r, $r31
-	\var	= 31
-	.endif
-	.iflt	\var
-	.error	"Unable to parse register name \r"
-	.endif
-	.endm
-
 	.macro	cpu_save_nonscratch thread
 	stptr.d	s0, \thread, THREAD_REG23
 	stptr.d	s1, \thread, THREAD_REG24
@@ -148,12 +41,51 @@
 
 	.macro fpu_save_csr thread tmp
 	movfcsr2gr	\tmp, fcsr0
-	stptr.w	\tmp, \thread, THREAD_FCSR
+	stptr.w		\tmp, \thread, THREAD_FCSR
+#ifdef CONFIG_CPU_HAS_LBT
+	/* TM bit is always 0 if LBT not supported */
+	andi		\tmp, \tmp, FPU_CSR_TM
+	beqz		\tmp, 1f
+	/* Save FTOP */
+	x86mftop	\tmp
+	stptr.w		\tmp, \thread, THREAD_FTOP
+	/* Turn off TM to ensure the order of FPR in memory independent of TM */
+	x86clrtm
+1:
+#endif
 	.endm
 
-	.macro fpu_restore_csr thread tmp
-	ldptr.w	\tmp, \thread, THREAD_FCSR
-	movgr2fcsr	fcsr0, \tmp
+	.macro fpu_restore_csr thread tmp0 tmp1
+	ldptr.w		\tmp0, \thread, THREAD_FCSR
+	movgr2fcsr	fcsr0, \tmp0
+#ifdef CONFIG_CPU_HAS_LBT
+	/* TM bit is always 0 if LBT not supported */
+	andi		\tmp0, \tmp0, FPU_CSR_TM
+	beqz		\tmp0, 2f
+	/* Restore FTOP */
+	ldptr.w		\tmp0, \thread, THREAD_FTOP
+	andi		\tmp0, \tmp0, 0x7
+	la.pcrel	\tmp1, 1f
+	alsl.d		\tmp1, \tmp0, \tmp1, 3
+	jr		\tmp1
+1:
+	x86mttop	0
+	b	2f
+	x86mttop	1
+	b	2f
+	x86mttop	2
+	b	2f
+	x86mttop	3
+	b	2f
+	x86mttop	4
+	b	2f
+	x86mttop	5
+	b	2f
+	x86mttop	6
+	b	2f
+	x86mttop	7
+2:
+#endif
 	.endm
 
 	.macro fpu_save_cc thread tmp0 tmp1
@@ -353,7 +285,7 @@
 	.macro	lsx_restore_all	thread tmp0 tmp1
 	lsx_restore_data	\thread, \tmp0
 	fpu_restore_cc		\thread, \tmp0, \tmp1
-	fpu_restore_csr		\thread, \tmp0
+	fpu_restore_csr		\thread, \tmp0, \tmp1
 	.endm
 
 	.macro	lsx_save_upper vd base tmp off
@@ -563,7 +495,7 @@
 	.macro	lasx_restore_all thread tmp0 tmp1
 	lasx_restore_data	\thread, \tmp0
 	fpu_restore_cc		\thread, \tmp0, \tmp1
-	fpu_restore_csr		\thread, \tmp0
+	fpu_restore_csr		\thread, \tmp0, \tmp1
 	.endm
 
 	.macro	lasx_save_upper xd base tmp off

arch/loongarch/include/asm/kasan.h

+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_KASAN_H
+#define __ASM_KASAN_H
+
+#ifndef __ASSEMBLY__
+
+#include <linux/linkage.h>
+#include <linux/mmzone.h>
+#include <asm/addrspace.h>
+#include <asm/io.h>
+#include <asm/pgtable.h>
+
+#define __HAVE_ARCH_SHADOW_MAP
+
+#define KASAN_SHADOW_SCALE_SHIFT 3
+#define KASAN_SHADOW_OFFSET	_AC(CONFIG_KASAN_SHADOW_OFFSET, UL)
+
+#define XRANGE_SHIFT (48)
+
+/* Valid address length */
+#define XRANGE_SHADOW_SHIFT	(PGDIR_SHIFT + PAGE_SHIFT - 3)
+/* Used for taking out the valid address */
+#define XRANGE_SHADOW_MASK	GENMASK_ULL(XRANGE_SHADOW_SHIFT - 1, 0)
+/* One segment whole address space size */
+#define XRANGE_SIZE		(XRANGE_SHADOW_MASK + 1)
+
+/* 64-bit segment value. */
+#define XKPRANGE_UC_SEG		(0x8000)
+#define XKPRANGE_CC_SEG		(0x9000)
+#define XKVRANGE_VC_SEG		(0xffff)
+
+/* Cached */
+#define XKPRANGE_CC_START		CACHE_BASE
+#define XKPRANGE_CC_SIZE		XRANGE_SIZE
+#define XKPRANGE_CC_KASAN_OFFSET	(0)
+#define XKPRANGE_CC_SHADOW_SIZE		(XKPRANGE_CC_SIZE >> KASAN_SHADOW_SCALE_SHIFT)
+#define XKPRANGE_CC_SHADOW_END		(XKPRANGE_CC_KASAN_OFFSET + XKPRANGE_CC_SHADOW_SIZE)
+
+/* UnCached */
+#define XKPRANGE_UC_START		UNCACHE_BASE
+#define XKPRANGE_UC_SIZE		XRANGE_SIZE
+#define XKPRANGE_UC_KASAN_OFFSET	XKPRANGE_CC_SHADOW_END
+#define XKPRANGE_UC_SHADOW_SIZE		(XKPRANGE_UC_SIZE >> KASAN_SHADOW_SCALE_SHIFT)
+#define XKPRANGE_UC_SHADOW_END		(XKPRANGE_UC_KASAN_OFFSET + XKPRANGE_UC_SHADOW_SIZE)
+
+/* VMALLOC (Cached or UnCached)  */
+#define XKVRANGE_VC_START		MODULES_VADDR
+#define XKVRANGE_VC_SIZE		round_up(KFENCE_AREA_END - MODULES_VADDR + 1, PGDIR_SIZE)
+#define XKVRANGE_VC_KASAN_OFFSET	XKPRANGE_UC_SHADOW_END
+#define XKVRANGE_VC_SHADOW_SIZE		(XKVRANGE_VC_SIZE >> KASAN_SHADOW_SCALE_SHIFT)
+#define XKVRANGE_VC_SHADOW_END		(XKVRANGE_VC_KASAN_OFFSET + XKVRANGE_VC_SHADOW_SIZE)
+
+/* KAsan shadow memory start right after vmalloc. */
+#define KASAN_SHADOW_START		round_up(KFENCE_AREA_END, PGDIR_SIZE)
+#define KASAN_SHADOW_SIZE		(XKVRANGE_VC_SHADOW_END - XKPRANGE_CC_KASAN_OFFSET)
+#define KASAN_SHADOW_END		round_up(KASAN_SHADOW_START + KASAN_SHADOW_SIZE, PGDIR_SIZE)
+
+#define XKPRANGE_CC_SHADOW_OFFSET	(KASAN_SHADOW_START + XKPRANGE_CC_KASAN_OFFSET)
+#define XKPRANGE_UC_SHADOW_OFFSET	(KASAN_SHADOW_START + XKPRANGE_UC_KASAN_OFFSET)
+#define XKVRANGE_VC_SHADOW_OFFSET	(KASAN_SHADOW_START + XKVRANGE_VC_KASAN_OFFSET)
+
+extern bool kasan_early_stage;
+extern unsigned char kasan_early_shadow_page[PAGE_SIZE];
+
+#define kasan_arch_is_ready kasan_arch_is_ready
+static __always_inline bool kasan_arch_is_ready(void)
+{
+	return !kasan_early_stage;
+}
+
+static inline void *kasan_mem_to_shadow(const void *addr)
+{
+	if (!kasan_arch_is_ready()) {
+		return (void *)(kasan_early_shadow_page);
+	} else {
+		unsigned long maddr = (unsigned long)addr;
+		unsigned long xrange = (maddr >> XRANGE_SHIFT) & 0xffff;
+		unsigned long offset = 0;
+
+		maddr &= XRANGE_SHADOW_MASK;
+		switch (xrange) {
+		case XKPRANGE_CC_SEG:
+			offset = XKPRANGE_CC_SHADOW_OFFSET;
+			break;
+		case XKPRANGE_UC_SEG:
+			offset = XKPRANGE_UC_SHADOW_OFFSET;
+			break;
+		case XKVRANGE_VC_SEG:
+			offset = XKVRANGE_VC_SHADOW_OFFSET;
+			break;
+		default:
+			WARN_ON(1);
+			return NULL;
+		}
+
+		return (void *)((maddr >> KASAN_SHADOW_SCALE_SHIFT) + offset);
+	}
+}
+
+static inline const void *kasan_shadow_to_mem(const void *shadow_addr)
+{
+	unsigned long addr = (unsigned long)shadow_addr;
+
+	if (unlikely(addr > KASAN_SHADOW_END) ||
+		unlikely(addr < KASAN_SHADOW_START)) {
+		WARN_ON(1);
+		return NULL;
+	}
+
+	if (addr >= XKVRANGE_VC_SHADOW_OFFSET)
+		return (void *)(((addr - XKVRANGE_VC_SHADOW_OFFSET) << KASAN_SHADOW_SCALE_SHIFT) + XKVRANGE_VC_START);
+	else if (addr >= XKPRANGE_UC_SHADOW_OFFSET)
+		return (void *)(((addr - XKPRANGE_UC_SHADOW_OFFSET) << KASAN_SHADOW_SCALE_SHIFT) + XKPRANGE_UC_START);
+	else if (addr >= XKPRANGE_CC_SHADOW_OFFSET)
+		return (void *)(((addr - XKPRANGE_CC_SHADOW_OFFSET) << KASAN_SHADOW_SCALE_SHIFT) + XKPRANGE_CC_START);
+	else {
+		WARN_ON(1);
+		return NULL;
+	}
+}
+
+void kasan_init(void);
+asmlinkage void kasan_early_init(void);
+
+#endif
+#endif

arch/loongarch/include/asm/kfence.h

+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * KFENCE support for LoongArch.
+ *
+ * Author: Enze Li <lienze@kylinos.cn>
+ * Copyright (C) 2022-2023 KylinSoft Corporation.
+ */
+
+#ifndef _ASM_LOONGARCH_KFENCE_H
+#define _ASM_LOONGARCH_KFENCE_H
+
+#include <linux/kfence.h>
+#include <asm/pgtable.h>
+#include <asm/tlb.h>
+
+static inline bool arch_kfence_init_pool(void)
+{
+	int err;
+	char *kfence_pool = __kfence_pool;
+	struct vm_struct *area;
+
+	area = __get_vm_area_caller(KFENCE_POOL_SIZE, VM_IOREMAP,
+				    KFENCE_AREA_START, KFENCE_AREA_END,
+				    __builtin_return_address(0));
+	if (!area)
+		return false;
+
+	__kfence_pool = (char *)area->addr;
+	err = ioremap_page_range((unsigned long)__kfence_pool,
+				 (unsigned long)__kfence_pool + KFENCE_POOL_SIZE,
+				 virt_to_phys((void *)kfence_pool), PAGE_KERNEL);
+	if (err) {
+		free_vm_area(area);
+		__kfence_pool = kfence_pool;
+		return false;
+	}
+
+	return true;
+}
+
+/* Protect the given page and flush TLB. */
+static inline bool kfence_protect_page(unsigned long addr, bool protect)
+{
+	pte_t *pte = virt_to_kpte(addr);
+
+	if (WARN_ON(!pte) || pte_none(*pte))
+		return false;
+
+	if (protect)
+		set_pte(pte, __pte(pte_val(*pte) & ~(_PAGE_VALID | _PAGE_PRESENT)));
+	else
+		set_pte(pte, __pte(pte_val(*pte) | (_PAGE_VALID | _PAGE_PRESENT)));
+
+	preempt_disable();
+	local_flush_tlb_one(addr);
+	preempt_enable();
+
+	return true;
+}
+
+#endif /* _ASM_LOONGARCH_KFENCE_H */

arch/loongarch/include/asm/kgdb.h

+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2023 Loongson Technology Corporation Limited
+ */
+
+#ifndef _ASM_LOONGARCH_KGDB_H
+#define _ASM_LOONGARCH_KGDB_H
+
+#define GDB_SIZEOF_REG		sizeof(u64)
+
+/* gdb remote procotol expects the following register layout. */
+
+/*
+ * General purpose registers:
+ *     r0-r31: 64 bit
+ *     orig_a0: 64 bit
+ *     pc : 64 bit
+ *     csr_badvaddr: 64 bit
+ */
+#define DBG_PT_REGS_BASE	0
+#define DBG_PT_REGS_NUM		35
+#define DBG_PT_REGS_END		(DBG_PT_REGS_BASE + DBG_PT_REGS_NUM - 1)
+
+/*
+ * Floating point registers:
+ *     f0-f31: 64 bit
+ */
+#define DBG_FPR_BASE		(DBG_PT_REGS_END + 1)
+#define DBG_FPR_NUM		32
+#define DBG_FPR_END		(DBG_FPR_BASE + DBG_FPR_NUM - 1)
+
+/*
+ * Condition Flag registers:
+ *     fcc0-fcc8: 8 bit
+ */
+#define DBG_FCC_BASE		(DBG_FPR_END + 1)
+#define DBG_FCC_NUM		8
+#define DBG_FCC_END		(DBG_FCC_BASE + DBG_FCC_NUM - 1)
+
+/*
+ * Floating-point Control and Status registers:
+ *     fcsr: 32 bit
+ */
+#define DBG_FCSR_NUM		1
+#define DBG_FCSR		(DBG_FCC_END + 1)
+
+#define DBG_MAX_REG_NUM		(DBG_FCSR + 1)
+
+/*
+ * Size of I/O buffer for gdb packet.
+ * considering to hold all register contents, size is set
+ */
+#define BUFMAX			2048
+
+/*
+ * Number of bytes required for gdb_regs buffer.
+ * PT_REGS and FPR: 8 bytes; FCSR: 4 bytes; FCC: 1 bytes.
+ * GDB fails to connect for size beyond this with error
+ * "'g' packet reply is too long"
+ */
+#define NUMREGBYTES		((DBG_PT_REGS_NUM + DBG_FPR_NUM) * GDB_SIZEOF_REG + DBG_FCC_NUM * 1 + DBG_FCSR_NUM * 4)
+
+#define BREAK_INSTR_SIZE	4
+#define CACHE_FLUSH_IS_SAFE	0
+
+/* Register numbers of various important registers. */
+enum dbg_loongarch_regnum {
+	DBG_LOONGARCH_ZERO = 0,
+	DBG_LOONGARCH_RA,
+	DBG_LOONGARCH_TP,
+	DBG_LOONGARCH_SP,
+	DBG_LOONGARCH_A0,
+	DBG_LOONGARCH_FP = 22,
+	DBG_LOONGARCH_S0,
+	DBG_LOONGARCH_S1,
+	DBG_LOONGARCH_S2,
+	DBG_LOONGARCH_S3,
+	DBG_LOONGARCH_S4,
+	DBG_LOONGARCH_S5,
+	DBG_LOONGARCH_S6,
+	DBG_LOONGARCH_S7,
+	DBG_LOONGARCH_S8,
+	DBG_LOONGARCH_ORIG_A0,
+	DBG_LOONGARCH_PC,
+	DBG_LOONGARCH_BADV
+};
+
+void kgdb_breakinst(void);
+void arch_kgdb_breakpoint(void);
+
+#ifdef CONFIG_KGDB
+bool kgdb_breakpoint_handler(struct pt_regs *regs);
+#else /* !CONFIG_KGDB */
+static inline bool kgdb_breakpoint_handler(struct pt_regs *regs) { return false; }
+#endif /* CONFIG_KGDB */
+
+#endif /* __ASM_KGDB_H_ */

arch/loongarch/include/asm/lbt.h

+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Author: Qi Hu <huqi@loongson.cn>
+ *         Huacai Chen <chenhuacai@loongson.cn>
+ * Copyright (C) 2020-2023 Loongson Technology Corporation Limited
+ */
+#ifndef _ASM_LBT_H
+#define _ASM_LBT_H
+
+#include <asm/cpu.h>
+#include <asm/current.h>
+#include <asm/loongarch.h>
+#include <asm/processor.h>
+
+extern void _init_lbt(void);
+extern void _save_lbt(struct loongarch_lbt *);
+extern void _restore_lbt(struct loongarch_lbt *);
+
+static inline int is_lbt_enabled(void)
+{
+	if (!cpu_has_lbt)
+		return 0;
+
+	return (csr_read32(LOONGARCH_CSR_EUEN) & CSR_EUEN_LBTEN) ?
+		1 : 0;
+}
+
+static inline int is_lbt_owner(void)
+{
+	return test_thread_flag(TIF_USEDLBT);
+}
+
+#ifdef CONFIG_CPU_HAS_LBT
+
+static inline void enable_lbt(void)
+{
+	if (cpu_has_lbt)
+		csr_xchg32(CSR_EUEN_LBTEN, CSR_EUEN_LBTEN, LOONGARCH_CSR_EUEN);
+}
+
+static inline void disable_lbt(void)
+{
+	if (cpu_has_lbt)
+		csr_xchg32(0, CSR_EUEN_LBTEN, LOONGARCH_CSR_EUEN);
+}
+
+static inline void __own_lbt(void)
+{
+	enable_lbt();
+	set_thread_flag(TIF_USEDLBT);
+	KSTK_EUEN(current) |= CSR_EUEN_LBTEN;
+}
+
+static inline void own_lbt_inatomic(int restore)
+{
+	if (cpu_has_lbt && !is_lbt_owner()) {
+		__own_lbt();
+		if (restore)
+			_restore_lbt(&current->thread.lbt);
+	}
+}
+
+static inline void own_lbt(int restore)
+{
+	preempt_disable();
+	own_lbt_inatomic(restore);
+	preempt_enable();
+}
+
+static inline void lose_lbt_inatomic(int save, struct task_struct *tsk)
+{
+	if (cpu_has_lbt && is_lbt_owner()) {
+		if (save)
+			_save_lbt(&tsk->thread.lbt);
+
+		disable_lbt();
+		clear_tsk_thread_flag(tsk, TIF_USEDLBT);
+	}
+	KSTK_EUEN(tsk) &= ~(CSR_EUEN_LBTEN);
+}
+
+static inline void lose_lbt(int save)
+{
+	preempt_disable();
+	lose_lbt_inatomic(save, current);
+	preempt_enable();
+}
+
+static inline void init_lbt(void)
+{
+	__own_lbt();
+	_init_lbt();
+}
+#else
+static inline void own_lbt_inatomic(int restore) {}
+static inline void lose_lbt_inatomic(int save, struct task_struct *tsk) {}
+static inline void init_lbt(void) {}
+static inline void lose_lbt(int save) {}
+#endif
+
+static inline int thread_lbt_context_live(void)
+{
+	if (!cpu_has_lbt)
+		return 0;
+
+	return test_thread_flag(TIF_LBT_CTX_LIVE);
+}
+
+#endif /* _ASM_LBT_H */

arch/loongarch/include/asm/loongarch.h

@@ -12,49 +12,6 @@
 #ifndef __ASSEMBLY__
 #include <larchintrin.h>
 
-/*
- * parse_r var, r - Helper assembler macro for parsing register names.
- *
- * This converts the register name in $n form provided in \r to the
- * corresponding register number, which is assigned to the variable \var. It is
- * needed to allow explicit encoding of instructions in inline assembly where
- * registers are chosen by the compiler in $n form, allowing us to avoid using
- * fixed register numbers.
- *
- * It also allows newer instructions (not implemented by the assembler) to be
- * transparently implemented using assembler macros, instead of needing separate
- * cases depending on toolchain support.
- *
- * Simple usage example:
- * __asm__ __volatile__("parse_r addr, %0\n\t"
- *			"#invtlb op, 0, %0\n\t"
- *			".word ((0x6498000) | (addr << 10) | (0 << 5) | op)"
- *			: "=r" (status);
- */
-
-/* Match an individual register number and assign to \var */
-#define _IFC_REG(n)				\
-	".ifc	\\r, $r" #n "\n\t"		\
-	"\\var	= " #n "\n\t"			\
-	".endif\n\t"
-
-__asm__(".macro	parse_r var r\n\t"
-	"\\var	= -1\n\t"
-	_IFC_REG(0)  _IFC_REG(1)  _IFC_REG(2)  _IFC_REG(3)
-	_IFC_REG(4)  _IFC_REG(5)  _IFC_REG(6)  _IFC_REG(7)
-	_IFC_REG(8)  _IFC_REG(9)  _IFC_REG(10) _IFC_REG(11)
-	_IFC_REG(12) _IFC_REG(13) _IFC_REG(14) _IFC_REG(15)
-	_IFC_REG(16) _IFC_REG(17) _IFC_REG(18) _IFC_REG(19)
-	_IFC_REG(20) _IFC_REG(21) _IFC_REG(22) _IFC_REG(23)
-	_IFC_REG(24) _IFC_REG(25) _IFC_REG(26) _IFC_REG(27)
-	_IFC_REG(28) _IFC_REG(29) _IFC_REG(30) _IFC_REG(31)
-	".iflt	\\var\n\t"
-	".error	\"Unable to parse register name \\r\"\n\t"
-	".endif\n\t"
-	".endm");
-
-#undef _IFC_REG
-
 /* CPUCFG */
 #define read_cpucfg(reg) __cpucfg(reg)
 
@@ -1453,6 +1410,10 @@ __BUILD_CSR_OP(tlbidx)
 #define FPU_CSR_RU	0x200	/* towards +Infinity */
 #define FPU_CSR_RD	0x300	/* towards -Infinity */
 
+/* Bit 6 of FPU Status Register specify the LBT TOP simulation mode */
+#define FPU_CSR_TM_SHIFT	0x6
+#define FPU_CSR_TM		(_ULCAST_(1) << FPU_CSR_TM_SHIFT)
+
 #define read_fcsr(source)	\
 ({	\
 	unsigned int __res;	\

arch/loongarch/include/asm/mmzone.h

@@ -13,6 +13,4 @@ extern struct pglist_data *node_data[];
 
 #define NODE_DATA(nid)	(node_data[(nid)])
 
-extern void setup_zero_pages(void);
-
 #endif /* _ASM_MMZONE_H_ */

arch/loongarch/include/asm/page.h

@@ -84,7 +84,12 @@ typedef struct { unsigned long pgprot; } pgprot_t;
 #define sym_to_pfn(x)		__phys_to_pfn(__pa_symbol(x))
 
 #define virt_to_pfn(kaddr)	PFN_DOWN(PHYSADDR(kaddr))
-#define virt_to_page(kaddr)	pfn_to_page(virt_to_pfn(kaddr))
+
+#define virt_to_page(kaddr)								\
+({											\
+	(likely((unsigned long)kaddr < vm_map_base)) ?					\
+	dmw_virt_to_page((unsigned long)kaddr) : tlb_virt_to_page((unsigned long)kaddr);\
+})
 
 extern int __virt_addr_valid(volatile void *kaddr);
 #define virt_addr_valid(kaddr)	__virt_addr_valid((volatile void *)(kaddr))

arch/loongarch/include/asm/pgalloc.h

@@ -94,4 +94,5 @@ static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address)
 
 #endif /* __PAGETABLE_PUD_FOLDED */
 
+extern pte_t * __init populate_kernel_pte(unsigned long addr);
 #endif /* _ASM_PGALLOC_H */

arch/loongarch/include/asm/pgtable.h

@@ -70,12 +70,9 @@ struct vm_area_struct;
  * for zero-mapped memory areas etc..
  */
 
-extern unsigned long empty_zero_page;
-extern unsigned long zero_page_mask;
+extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
 
-#define ZERO_PAGE(vaddr) \
-	(virt_to_page((void *)(empty_zero_page + (((unsigned long)(vaddr)) & zero_page_mask))))
-#define __HAVE_COLOR_ZERO_PAGE
+#define ZERO_PAGE(vaddr)	virt_to_page(empty_zero_page)
 
 /*
  * TLB refill handlers may also map the vmalloc area into xkvrange.
@@ -85,14 +82,30 @@ extern unsigned long zero_page_mask;
 #define MODULES_VADDR	(vm_map_base + PCI_IOSIZE + (2 * PAGE_SIZE))
 #define MODULES_END	(MODULES_VADDR + SZ_256M)
 
+#ifdef CONFIG_KFENCE
+#define KFENCE_AREA_SIZE	(((CONFIG_KFENCE_NUM_OBJECTS + 1) * 2 + 2) * PAGE_SIZE)
+#else
+#define KFENCE_AREA_SIZE	0
+#endif
+
 #define VMALLOC_START	MODULES_END
+
+#ifndef CONFIG_KASAN
 #define VMALLOC_END	\
 	(vm_map_base +	\
-	 min(PTRS_PER_PGD * PTRS_PER_PUD * PTRS_PER_PMD * PTRS_PER_PTE * PAGE_SIZE, (1UL << cpu_vabits)) - PMD_SIZE - VMEMMAP_SIZE)
+	 min(PTRS_PER_PGD * PTRS_PER_PUD * PTRS_PER_PMD * PTRS_PER_PTE * PAGE_SIZE, (1UL << cpu_vabits)) - PMD_SIZE - VMEMMAP_SIZE - KFENCE_AREA_SIZE)
+#else
+#define VMALLOC_END	\
+	(vm_map_base +	\
+	 min(PTRS_PER_PGD * PTRS_PER_PUD * PTRS_PER_PMD * PTRS_PER_PTE * PAGE_SIZE, (1UL << cpu_vabits) / 2) - PMD_SIZE - VMEMMAP_SIZE - KFENCE_AREA_SIZE)
+#endif
 
 #define vmemmap		((struct page *)((VMALLOC_END + PMD_SIZE) & PMD_MASK))
 #define VMEMMAP_END	((unsigned long)vmemmap + VMEMMAP_SIZE - 1)
 
+#define KFENCE_AREA_START	(VMEMMAP_END + 1)
+#define KFENCE_AREA_END		(KFENCE_AREA_START + KFENCE_AREA_SIZE - 1)
+
 #define pte_ERROR(e) \
 	pr_err("%s:%d: bad pte %016lx.\n", __FILE__, __LINE__, pte_val(e))
 #ifndef __PAGETABLE_PMD_FOLDED
@@ -350,6 +363,9 @@ static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *pt
 extern pgd_t swapper_pg_dir[];
 extern pgd_t invalid_pg_dir[];
 
+struct page *dmw_virt_to_page(unsigned long kaddr);
+struct page *tlb_virt_to_page(unsigned long kaddr);
+
 /*
  * The following only work if pte_present() is true.
  * Undefined behaviour if not..
@@ -596,6 +612,9 @@ static inline long pmd_protnone(pmd_t pmd)
 }
 #endif /* CONFIG_NUMA_BALANCING */
 
+#define pmd_leaf(pmd)		((pmd_val(pmd) & _PAGE_HUGE) != 0)
+#define pud_leaf(pud)		((pud_val(pud) & _PAGE_HUGE) != 0)
+
 /*
  * We provide our own get_unmapped area to cope with the virtual aliasing
  * constraints placed on us by the cache architecture.

arch/loongarch/include/asm/processor.h

@@ -80,11 +80,22 @@ BUILD_FPR_ACCESS(32)
 BUILD_FPR_ACCESS(64)
 
 struct loongarch_fpu {
-	unsigned int	fcsr;
 	uint64_t	fcc;	/* 8x8 */
+	uint32_t	fcsr;
+	uint32_t	ftop;
 	union fpureg	fpr[NUM_FPU_REGS];
 };
 
+struct loongarch_lbt {
+	/* Scratch registers */
+	unsigned long scr0;
+	unsigned long scr1;
+	unsigned long scr2;
+	unsigned long scr3;
+	/* Eflags register */
+	unsigned long eflags;
+};
+
 #define INIT_CPUMASK { \
 	{0,} \
 }
@@ -113,15 +124,6 @@ struct thread_struct {
 	unsigned long csr_ecfg;
 	unsigned long csr_badvaddr;	/* Last user fault */
 
-	/* Scratch registers */
-	unsigned long scr0;
-	unsigned long scr1;
-	unsigned long scr2;
-	unsigned long scr3;
-
-	/* Eflags register */
-	unsigned long eflags;
-
 	/* Other stuff associated with the thread. */
 	unsigned long trap_nr;
 	unsigned long error_code;
@@ -133,6 +135,7 @@ struct thread_struct {
 	 * context because they are conditionally copied at fork().
 	 */
 	struct loongarch_fpu fpu FPU_ALIGN;
+	struct loongarch_lbt lbt; /* Also conditionally copied */
 
 	/* Hardware breakpoints pinned to this task. */
 	struct perf_event *hbp_break[LOONGARCH_MAX_BRP];
@@ -174,8 +177,9 @@ struct thread_struct {
 	 * FPU & vector registers				\
 	 */							\
 	.fpu			= {				\
-		.fcsr		= 0,				\
 		.fcc		= 0,				\
+		.fcsr		= 0,				\
+		.ftop		= 0,				\
 		.fpr		= {{{0,},},},			\
 	},							\
 	.hbp_break		= {0},				\