diff options
Diffstat (limited to 'arch/loongarch/include')
100 files changed, 1823 insertions, 940 deletions
diff --git a/arch/loongarch/include/asm/Kbuild b/arch/loongarch/include/asm/Kbuild index 80ddb5edb845..7e92957baf6a 100644 --- a/arch/loongarch/include/asm/Kbuild +++ b/arch/loongarch/include/asm/Kbuild @@ -1,4 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 +syscall-y += syscall_table_32.h syscall-y += syscall_table_64.h generated-y += orc_hash.h @@ -9,6 +10,6 @@ generic-y += qrwlock.h generic-y += user.h generic-y += ioctl.h generic-y += mmzone.h +generic-y += ring_buffer.h generic-y += statfs.h -generic-y += param.h generic-y += text-patching.h diff --git a/arch/loongarch/include/asm/acenv.h b/arch/loongarch/include/asm/acenv.h index 52f298f7293b..483c955f2ae5 100644 --- a/arch/loongarch/include/asm/acenv.h +++ b/arch/loongarch/include/asm/acenv.h @@ -10,9 +10,8 @@ #ifndef _ASM_LOONGARCH_ACENV_H #define _ASM_LOONGARCH_ACENV_H -/* - * This header is required by ACPI core, but we have nothing to fill in - * right now. Will be updated later when needed. - */ +#ifdef CONFIG_ARCH_STRICT_ALIGN +#define ACPI_MISALIGNMENT_NOT_SUPPORTED +#endif /* CONFIG_ARCH_STRICT_ALIGN */ #endif /* _ASM_LOONGARCH_ACENV_H */ diff --git a/arch/loongarch/include/asm/acpi.h b/arch/loongarch/include/asm/acpi.h index 313f66f7913a..eda9d4d0a493 100644 --- a/arch/loongarch/include/asm/acpi.h +++ b/arch/loongarch/include/asm/acpi.h @@ -33,18 +33,13 @@ static inline bool acpi_has_cpu_in_madt(void) return true; } -#define MAX_CORE_PIC 256 +#define MAX_CORE_PIC 2048 extern struct list_head acpi_wakeup_device_list; extern struct acpi_madt_core_pic acpi_core_pic[MAX_CORE_PIC]; extern int __init parse_acpi_topology(void); -static inline u32 get_acpi_id_for_cpu(unsigned int cpu) -{ - return acpi_core_pic[cpu_logical_map(cpu)].processor_id; -} - #endif /* !CONFIG_ACPI */ #define ACPI_TABLE_UPGRADE_MAX_PHYS ARCH_LOW_ADDRESS_LIMIT diff --git a/arch/loongarch/include/asm/addrspace.h b/arch/loongarch/include/asm/addrspace.h index fe198b473f84..d6472cafb32c 100644 --- a/arch/loongarch/include/asm/addrspace.h +++ b/arch/loongarch/include/asm/addrspace.h @@ -18,12 +18,12 @@ /* * This gives the physical RAM offset. */ -#ifndef __ASSEMBLY__ +#ifndef __ASSEMBLER__ #ifndef PHYS_OFFSET #define PHYS_OFFSET _UL(0) #endif extern unsigned long vm_map_base; -#endif /* __ASSEMBLY__ */ +#endif /* __ASSEMBLER__ */ #ifndef IO_BASE #define IO_BASE CSR_DMW0_BASE @@ -38,11 +38,20 @@ extern unsigned long vm_map_base; #endif #ifndef WRITECOMBINE_BASE +#ifdef CONFIG_32BIT +#define WRITECOMBINE_BASE CSR_DMW0_BASE +#else #define WRITECOMBINE_BASE CSR_DMW2_BASE #endif +#endif +#ifdef CONFIG_32BIT +#define DMW_PABITS 29 +#define TO_PHYS_MASK ((_UL(1) << _UL(DMW_PABITS)) - 1) +#else #define DMW_PABITS 48 -#define TO_PHYS_MASK ((1ULL << DMW_PABITS) - 1) +#define TO_PHYS_MASK ((_ULL(1) << _ULL(DMW_PABITS)) - 1) +#endif /* * Memory above this physical address will be considered highmem. @@ -66,7 +75,7 @@ extern unsigned long vm_map_base; #define FIXADDR_TOP ((unsigned long)(long)(int)0xfffe0000) #endif -#ifdef __ASSEMBLY__ +#ifdef __ASSEMBLER__ #define _ATYPE_ #define _ATYPE32_ #define _ATYPE64_ @@ -85,7 +94,7 @@ extern unsigned long vm_map_base; /* * 32/64-bit LoongArch address spaces */ -#ifdef __ASSEMBLY__ +#ifdef __ASSEMBLER__ #define _ACAST32_ #define _ACAST64_ #else @@ -112,7 +121,11 @@ extern unsigned long vm_map_base; /* * Returns the physical address of a KPRANGEx / XKPRANGE address */ +#ifdef CONFIG_32BIT +#define PHYSADDR(a) ((_ACAST32_(a)) & TO_PHYS_MASK) +#else #define PHYSADDR(a) ((_ACAST64_(a)) & TO_PHYS_MASK) +#endif /* * On LoongArch, I/O ports mappring is following: diff --git a/arch/loongarch/include/asm/alternative-asm.h b/arch/loongarch/include/asm/alternative-asm.h index ff3d10ac393f..7dc29bd9b2f0 100644 --- a/arch/loongarch/include/asm/alternative-asm.h +++ b/arch/loongarch/include/asm/alternative-asm.h @@ -2,7 +2,7 @@ #ifndef _ASM_ALTERNATIVE_ASM_H #define _ASM_ALTERNATIVE_ASM_H -#ifdef __ASSEMBLY__ +#ifdef __ASSEMBLER__ #include <asm/asm.h> @@ -77,6 +77,6 @@ .previous .endm -#endif /* __ASSEMBLY__ */ +#endif /* __ASSEMBLER__ */ #endif /* _ASM_ALTERNATIVE_ASM_H */ diff --git a/arch/loongarch/include/asm/alternative.h b/arch/loongarch/include/asm/alternative.h index cee7b29785ab..b5bae21fb3c8 100644 --- a/arch/loongarch/include/asm/alternative.h +++ b/arch/loongarch/include/asm/alternative.h @@ -2,7 +2,7 @@ #ifndef _ASM_ALTERNATIVE_H #define _ASM_ALTERNATIVE_H -#ifndef __ASSEMBLY__ +#ifndef __ASSEMBLER__ #include <linux/types.h> #include <linux/stddef.h> @@ -106,6 +106,6 @@ extern void apply_alternatives(struct alt_instr *start, struct alt_instr *end); #define alternative_2(oldinstr, newinstr1, feature1, newinstr2, feature2) \ (asm volatile(ALTERNATIVE_2(oldinstr, newinstr1, feature1, newinstr2, feature2) ::: "memory")) -#endif /* __ASSEMBLY__ */ +#endif /* __ASSEMBLER__ */ #endif /* _ASM_ALTERNATIVE_H */ diff --git a/arch/loongarch/include/asm/asm-extable.h b/arch/loongarch/include/asm/asm-extable.h index df05005f2b80..d60bdf2e6377 100644 --- a/arch/loongarch/include/asm/asm-extable.h +++ b/arch/loongarch/include/asm/asm-extable.h @@ -7,7 +7,7 @@ #define EX_TYPE_UACCESS_ERR_ZERO 2 #define EX_TYPE_BPF 3 -#ifdef __ASSEMBLY__ +#ifdef __ASSEMBLER__ #define __ASM_EXTABLE_RAW(insn, fixup, type, data) \ .pushsection __ex_table, "a"; \ @@ -22,7 +22,7 @@ __ASM_EXTABLE_RAW(\insn, \fixup, EX_TYPE_FIXUP, 0) .endm -#else /* __ASSEMBLY__ */ +#else /* __ASSEMBLER__ */ #include <linux/bits.h> #include <linux/stringify.h> @@ -60,6 +60,6 @@ #define _ASM_EXTABLE_UACCESS_ERR(insn, fixup, err) \ _ASM_EXTABLE_UACCESS_ERR_ZERO(insn, fixup, err, zero) -#endif /* __ASSEMBLY__ */ +#endif /* __ASSEMBLER__ */ #endif /* __ASM_ASM_EXTABLE_H */ diff --git a/arch/loongarch/include/asm/asm-prototypes.h b/arch/loongarch/include/asm/asm-prototypes.h index 51f224bcfc65..de0c17f3f49c 100644 --- a/arch/loongarch/include/asm/asm-prototypes.h +++ b/arch/loongarch/include/asm/asm-prototypes.h @@ -12,3 +12,31 @@ __int128_t __ashlti3(__int128_t a, int b); __int128_t __ashrti3(__int128_t a, int b); __int128_t __lshrti3(__int128_t a, int b); #endif + +asmlinkage void noinstr __no_stack_protector ret_from_fork(struct task_struct *prev, + struct pt_regs *regs); + +asmlinkage void noinstr __no_stack_protector ret_from_kernel_thread(struct task_struct *prev, + struct pt_regs *regs, + int (*fn)(void *), + void *fn_arg); + +struct kvm_run; +struct kvm_vcpu; +struct loongarch_fpu; + +void kvm_exc_entry(void); +int kvm_enter_guest(struct kvm_run *run, struct kvm_vcpu *vcpu); + +void kvm_save_fpu(struct loongarch_fpu *fpu); +void kvm_restore_fpu(struct loongarch_fpu *fpu); + +#ifdef CONFIG_CPU_HAS_LSX +void kvm_save_lsx(struct loongarch_fpu *fpu); +void kvm_restore_lsx(struct loongarch_fpu *fpu); +#endif + +#ifdef CONFIG_CPU_HAS_LASX +void kvm_save_lasx(struct loongarch_fpu *fpu); +void kvm_restore_lasx(struct loongarch_fpu *fpu); +#endif diff --git a/arch/loongarch/include/asm/asm.h b/arch/loongarch/include/asm/asm.h index f591b3245def..719cab1a0ad8 100644 --- a/arch/loongarch/include/asm/asm.h +++ b/arch/loongarch/include/asm/asm.h @@ -72,11 +72,11 @@ #define INT_SUB sub.w #define INT_L ld.w #define INT_S st.w -#define INT_SLL slli.w +#define INT_SLLI slli.w #define INT_SLLV sll.w -#define INT_SRL srli.w +#define INT_SRLI srli.w #define INT_SRLV srl.w -#define INT_SRA srai.w +#define INT_SRAI srai.w #define INT_SRAV sra.w #endif @@ -86,11 +86,11 @@ #define INT_SUB sub.d #define INT_L ld.d #define INT_S st.d -#define INT_SLL slli.d +#define INT_SLLI slli.d #define INT_SLLV sll.d -#define INT_SRL srli.d +#define INT_SRLI srli.d #define INT_SRLV srl.d -#define INT_SRA srai.d +#define INT_SRAI srai.d #define INT_SRAV sra.d #endif @@ -100,17 +100,25 @@ #if (__SIZEOF_LONG__ == 4) #define LONG_ADD add.w #define LONG_ADDI addi.w +#define LONG_ALSL alsl.w +#define LONG_BSTRINS bstrins.w +#define LONG_BSTRPICK bstrpick.w #define LONG_SUB sub.w #define LONG_L ld.w +#define LONG_LI li.w +#define LONG_LPTR ld.w #define LONG_S st.w -#define LONG_SLL slli.w +#define LONG_SPTR st.w +#define LONG_SLLI slli.w #define LONG_SLLV sll.w -#define LONG_SRL srli.w +#define LONG_SRLI srli.w #define LONG_SRLV srl.w -#define LONG_SRA srai.w +#define LONG_SRAI srai.w #define LONG_SRAV sra.w +#define LONG_ROTR rotr.w +#define LONG_ROTRI rotri.w -#ifdef __ASSEMBLY__ +#ifdef __ASSEMBLER__ #define LONG .word #endif #define LONGSIZE 4 @@ -121,17 +129,25 @@ #if (__SIZEOF_LONG__ == 8) #define LONG_ADD add.d #define LONG_ADDI addi.d +#define LONG_ALSL alsl.d +#define LONG_BSTRINS bstrins.d +#define LONG_BSTRPICK bstrpick.d #define LONG_SUB sub.d #define LONG_L ld.d +#define LONG_LI li.d +#define LONG_LPTR ldptr.d #define LONG_S st.d -#define LONG_SLL slli.d +#define LONG_SPTR stptr.d +#define LONG_SLLI slli.d #define LONG_SLLV sll.d -#define LONG_SRL srli.d +#define LONG_SRLI srli.d #define LONG_SRLV srl.d -#define LONG_SRA srai.d +#define LONG_SRAI srai.d #define LONG_SRAV sra.d +#define LONG_ROTR rotr.d +#define LONG_ROTRI rotri.d -#ifdef __ASSEMBLY__ +#ifdef __ASSEMBLER__ #define LONG .dword #endif #define LONGSIZE 8 @@ -145,20 +161,27 @@ #if (__SIZEOF_POINTER__ == 4) #define PTR_ADD add.w #define PTR_ADDI addi.w +#define PTR_ALSL alsl.w +#define PTR_BSTRINS bstrins.w +#define PTR_BSTRPICK bstrpick.w #define PTR_SUB sub.w #define PTR_L ld.w -#define PTR_S st.w #define PTR_LI li.w -#define PTR_SLL slli.w +#define PTR_LPTR ld.w +#define PTR_S st.w +#define PTR_SPTR st.w +#define PTR_SLLI slli.w #define PTR_SLLV sll.w -#define PTR_SRL srli.w +#define PTR_SRLI srli.w #define PTR_SRLV srl.w -#define PTR_SRA srai.w +#define PTR_SRAI srai.w #define PTR_SRAV sra.w +#define PTR_ROTR rotr.w +#define PTR_ROTRI rotri.w #define PTR_SCALESHIFT 2 -#ifdef __ASSEMBLY__ +#ifdef __ASSEMBLER__ #define PTR .word #endif #define PTRSIZE 4 @@ -168,20 +191,27 @@ #if (__SIZEOF_POINTER__ == 8) #define PTR_ADD add.d #define PTR_ADDI addi.d +#define PTR_ALSL alsl.d +#define PTR_BSTRINS bstrins.d +#define PTR_BSTRPICK bstrpick.d #define PTR_SUB sub.d #define PTR_L ld.d -#define PTR_S st.d #define PTR_LI li.d -#define PTR_SLL slli.d +#define PTR_LPTR ldptr.d +#define PTR_S st.d +#define PTR_SPTR stptr.d +#define PTR_SLLI slli.d #define PTR_SLLV sll.d -#define PTR_SRL srli.d +#define PTR_SRLI srli.d #define PTR_SRLV srl.d -#define PTR_SRA srai.d +#define PTR_SRAI srai.d #define PTR_SRAV sra.d +#define PTR_ROTR rotr.d +#define PTR_ROTRI rotri.d #define PTR_SCALESHIFT 3 -#ifdef __ASSEMBLY__ +#ifdef __ASSEMBLER__ #define PTR .dword #endif #define PTRSIZE 8 @@ -190,10 +220,17 @@ /* Annotate a function as being unsuitable for kprobes. */ #ifdef CONFIG_KPROBES +#ifdef CONFIG_32BIT +#define _ASM_NOKPROBE(name) \ + .pushsection "_kprobe_blacklist", "aw"; \ + .long name; \ + .popsection +#else #define _ASM_NOKPROBE(name) \ .pushsection "_kprobe_blacklist", "aw"; \ .quad name; \ .popsection +#endif #else #define _ASM_NOKPROBE(name) #endif diff --git a/arch/loongarch/include/asm/asmmacro.h b/arch/loongarch/include/asm/asmmacro.h index 8d7f501b0a12..a648be5f723f 100644 --- a/arch/loongarch/include/asm/asmmacro.h +++ b/arch/loongarch/include/asm/asmmacro.h @@ -5,43 +5,55 @@ #ifndef _ASM_ASMMACRO_H #define _ASM_ASMMACRO_H +#include <linux/sizes.h> #include <asm/asm-offsets.h> #include <asm/regdef.h> #include <asm/fpregdef.h> #include <asm/loongarch.h> +#ifdef CONFIG_64BIT +#define TASK_STRUCT_OFFSET 0 +#else +#define TASK_STRUCT_OFFSET 2000 +#endif + .macro cpu_save_nonscratch thread - stptr.d s0, \thread, THREAD_REG23 - stptr.d s1, \thread, THREAD_REG24 - stptr.d s2, \thread, THREAD_REG25 - stptr.d s3, \thread, THREAD_REG26 - stptr.d s4, \thread, THREAD_REG27 - stptr.d s5, \thread, THREAD_REG28 - stptr.d s6, \thread, THREAD_REG29 - stptr.d s7, \thread, THREAD_REG30 - stptr.d s8, \thread, THREAD_REG31 - stptr.d sp, \thread, THREAD_REG03 - stptr.d fp, \thread, THREAD_REG22 + LONG_SPTR s0, \thread, (THREAD_REG23 - TASK_STRUCT_OFFSET) + LONG_SPTR s1, \thread, (THREAD_REG24 - TASK_STRUCT_OFFSET) + LONG_SPTR s2, \thread, (THREAD_REG25 - TASK_STRUCT_OFFSET) + LONG_SPTR s3, \thread, (THREAD_REG26 - TASK_STRUCT_OFFSET) + LONG_SPTR s4, \thread, (THREAD_REG27 - TASK_STRUCT_OFFSET) + LONG_SPTR s5, \thread, (THREAD_REG28 - TASK_STRUCT_OFFSET) + LONG_SPTR s6, \thread, (THREAD_REG29 - TASK_STRUCT_OFFSET) + LONG_SPTR s7, \thread, (THREAD_REG30 - TASK_STRUCT_OFFSET) + LONG_SPTR s8, \thread, (THREAD_REG31 - TASK_STRUCT_OFFSET) + LONG_SPTR ra, \thread, (THREAD_REG01 - TASK_STRUCT_OFFSET) + LONG_SPTR sp, \thread, (THREAD_REG03 - TASK_STRUCT_OFFSET) + LONG_SPTR fp, \thread, (THREAD_REG22 - TASK_STRUCT_OFFSET) .endm .macro cpu_restore_nonscratch thread - ldptr.d s0, \thread, THREAD_REG23 - ldptr.d s1, \thread, THREAD_REG24 - ldptr.d s2, \thread, THREAD_REG25 - ldptr.d s3, \thread, THREAD_REG26 - ldptr.d s4, \thread, THREAD_REG27 - ldptr.d s5, \thread, THREAD_REG28 - ldptr.d s6, \thread, THREAD_REG29 - ldptr.d s7, \thread, THREAD_REG30 - ldptr.d s8, \thread, THREAD_REG31 - ldptr.d ra, \thread, THREAD_REG01 - ldptr.d sp, \thread, THREAD_REG03 - ldptr.d fp, \thread, THREAD_REG22 + LONG_LPTR s0, \thread, (THREAD_REG23 - TASK_STRUCT_OFFSET) + LONG_LPTR s1, \thread, (THREAD_REG24 - TASK_STRUCT_OFFSET) + LONG_LPTR s2, \thread, (THREAD_REG25 - TASK_STRUCT_OFFSET) + LONG_LPTR s3, \thread, (THREAD_REG26 - TASK_STRUCT_OFFSET) + LONG_LPTR s4, \thread, (THREAD_REG27 - TASK_STRUCT_OFFSET) + LONG_LPTR s5, \thread, (THREAD_REG28 - TASK_STRUCT_OFFSET) + LONG_LPTR s6, \thread, (THREAD_REG29 - TASK_STRUCT_OFFSET) + LONG_LPTR s7, \thread, (THREAD_REG30 - TASK_STRUCT_OFFSET) + LONG_LPTR s8, \thread, (THREAD_REG31 - TASK_STRUCT_OFFSET) + LONG_LPTR ra, \thread, (THREAD_REG01 - TASK_STRUCT_OFFSET) + LONG_LPTR sp, \thread, (THREAD_REG03 - TASK_STRUCT_OFFSET) + LONG_LPTR fp, \thread, (THREAD_REG22 - TASK_STRUCT_OFFSET) .endm .macro fpu_save_csr thread tmp movfcsr2gr \tmp, fcsr0 +#ifdef CONFIG_32BIT + st.w \tmp, \thread, THREAD_FCSR +#else stptr.w \tmp, \thread, THREAD_FCSR +#endif #ifdef CONFIG_CPU_HAS_LBT /* TM bit is always 0 if LBT not supported */ andi \tmp, \tmp, FPU_CSR_TM @@ -56,7 +68,11 @@ .endm .macro fpu_restore_csr thread tmp0 tmp1 +#ifdef CONFIG_32BIT + ld.w \tmp0, \thread, THREAD_FCSR +#else ldptr.w \tmp0, \thread, THREAD_FCSR +#endif movgr2fcsr fcsr0, \tmp0 #ifdef CONFIG_CPU_HAS_LBT /* TM bit is always 0 if LBT not supported */ @@ -88,9 +104,52 @@ #endif .endm +#ifdef CONFIG_32BIT .macro fpu_save_cc thread tmp0 tmp1 movcf2gr \tmp0, $fcc0 - move \tmp1, \tmp0 + move \tmp1, \tmp0 + movcf2gr \tmp0, $fcc1 + bstrins.w \tmp1, \tmp0, 15, 8 + movcf2gr \tmp0, $fcc2 + bstrins.w \tmp1, \tmp0, 23, 16 + movcf2gr \tmp0, $fcc3 + bstrins.w \tmp1, \tmp0, 31, 24 + st.w \tmp1, \thread, THREAD_FCC + movcf2gr \tmp0, $fcc4 + move \tmp1, \tmp0 + movcf2gr \tmp0, $fcc5 + bstrins.w \tmp1, \tmp0, 15, 8 + movcf2gr \tmp0, $fcc6 + bstrins.w \tmp1, \tmp0, 23, 16 + movcf2gr \tmp0, $fcc7 + bstrins.w \tmp1, \tmp0, 31, 24 + st.w \tmp1, \thread, (THREAD_FCC + 4) + .endm + + .macro fpu_restore_cc thread tmp0 tmp1 + ld.w \tmp0, \thread, THREAD_FCC + bstrpick.w \tmp1, \tmp0, 7, 0 + movgr2cf $fcc0, \tmp1 + bstrpick.w \tmp1, \tmp0, 15, 8 + movgr2cf $fcc1, \tmp1 + bstrpick.w \tmp1, \tmp0, 23, 16 + movgr2cf $fcc2, \tmp1 + bstrpick.w \tmp1, \tmp0, 31, 24 + movgr2cf $fcc3, \tmp1 + ld.w \tmp0, \thread, (THREAD_FCC + 4) + bstrpick.w \tmp1, \tmp0, 7, 0 + movgr2cf $fcc4, \tmp1 + bstrpick.w \tmp1, \tmp0, 15, 8 + movgr2cf $fcc5, \tmp1 + bstrpick.w \tmp1, \tmp0, 23, 16 + movgr2cf $fcc6, \tmp1 + bstrpick.w \tmp1, \tmp0, 31, 24 + movgr2cf $fcc7, \tmp1 + .endm +#else + .macro fpu_save_cc thread tmp0 tmp1 + movcf2gr \tmp0, $fcc0 + move \tmp1, \tmp0 movcf2gr \tmp0, $fcc1 bstrins.d \tmp1, \tmp0, 15, 8 movcf2gr \tmp0, $fcc2 @@ -109,7 +168,7 @@ .endm .macro fpu_restore_cc thread tmp0 tmp1 - ldptr.d \tmp0, \thread, THREAD_FCC + ldptr.d \tmp0, \thread, THREAD_FCC bstrpick.d \tmp1, \tmp0, 7, 0 movgr2cf $fcc0, \tmp1 bstrpick.d \tmp1, \tmp0, 15, 8 @@ -127,6 +186,7 @@ bstrpick.d \tmp1, \tmp0, 63, 56 movgr2cf $fcc7, \tmp1 .endm +#endif .macro fpu_save_double thread tmp li.w \tmp, THREAD_FPR0 @@ -606,12 +666,14 @@ 766: lu12i.w \reg, 0 ori \reg, \reg, 0 +#ifdef CONFIG_64BIT lu32i.d \reg, 0 lu52i.d \reg, \reg, 0 +#endif .pushsection ".la_abs", "aw", %progbits - .p2align 3 - .dword 766b - .dword \sym + .p2align PTRLOG + PTR 766b + PTR \sym .popsection #endif .endm diff --git a/arch/loongarch/include/asm/atomic-amo.h b/arch/loongarch/include/asm/atomic-amo.h new file mode 100644 index 000000000000..d5efa5252d56 --- /dev/null +++ b/arch/loongarch/include/asm/atomic-amo.h @@ -0,0 +1,206 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Atomic operations (AMO). + * + * Copyright (C) 2020-2025 Loongson Technology Corporation Limited + */ + +#ifndef _ASM_ATOMIC_AMO_H +#define _ASM_ATOMIC_AMO_H + +#include <linux/types.h> +#include <asm/barrier.h> +#include <asm/cmpxchg.h> + +#define ATOMIC_OP(op, I, asm_op) \ +static inline void arch_atomic_##op(int i, atomic_t *v) \ +{ \ + __asm__ __volatile__( \ + "am"#asm_op".w" " $zero, %1, %0 \n" \ + : "+ZB" (v->counter) \ + : "r" (I) \ + : "memory"); \ +} + +#define ATOMIC_OP_RETURN(op, I, asm_op, c_op, mb, suffix) \ +static inline int arch_atomic_##op##_return##suffix(int i, atomic_t *v) \ +{ \ + int result; \ + \ + __asm__ __volatile__( \ + "am"#asm_op#mb".w" " %1, %2, %0 \n" \ + : "+ZB" (v->counter), "=&r" (result) \ + : "r" (I) \ + : "memory"); \ + \ + return result c_op I; \ +} + +#define ATOMIC_FETCH_OP(op, I, asm_op, mb, suffix) \ +static inline int arch_atomic_fetch_##op##suffix(int i, atomic_t *v) \ +{ \ + int result; \ + \ + __asm__ __volatile__( \ + "am"#asm_op#mb".w" " %1, %2, %0 \n" \ + : "+ZB" (v->counter), "=&r" (result) \ + : "r" (I) \ + : "memory"); \ + \ + return result; \ +} + +#define ATOMIC_OPS(op, I, asm_op, c_op) \ + ATOMIC_OP(op, I, asm_op) \ + ATOMIC_OP_RETURN(op, I, asm_op, c_op, _db, ) \ + ATOMIC_OP_RETURN(op, I, asm_op, c_op, , _relaxed) \ + ATOMIC_FETCH_OP(op, I, asm_op, _db, ) \ + ATOMIC_FETCH_OP(op, I, asm_op, , _relaxed) + +ATOMIC_OPS(add, i, add, +) +ATOMIC_OPS(sub, -i, add, +) + +#define arch_atomic_add_return arch_atomic_add_return +#define arch_atomic_add_return_acquire arch_atomic_add_return +#define arch_atomic_add_return_release arch_atomic_add_return +#define arch_atomic_add_return_relaxed arch_atomic_add_return_relaxed +#define arch_atomic_sub_return arch_atomic_sub_return +#define arch_atomic_sub_return_acquire arch_atomic_sub_return +#define arch_atomic_sub_return_release arch_atomic_sub_return +#define arch_atomic_sub_return_relaxed arch_atomic_sub_return_relaxed +#define arch_atomic_fetch_add arch_atomic_fetch_add +#define arch_atomic_fetch_add_acquire arch_atomic_fetch_add +#define arch_atomic_fetch_add_release arch_atomic_fetch_add +#define arch_atomic_fetch_add_relaxed arch_atomic_fetch_add_relaxed +#define arch_atomic_fetch_sub arch_atomic_fetch_sub +#define arch_atomic_fetch_sub_acquire arch_atomic_fetch_sub +#define arch_atomic_fetch_sub_release arch_atomic_fetch_sub +#define arch_atomic_fetch_sub_relaxed arch_atomic_fetch_sub_relaxed + +#undef ATOMIC_OPS + +#define ATOMIC_OPS(op, I, asm_op) \ + ATOMIC_OP(op, I, asm_op) \ + ATOMIC_FETCH_OP(op, I, asm_op, _db, ) \ + ATOMIC_FETCH_OP(op, I, asm_op, , _relaxed) + +ATOMIC_OPS(and, i, and) +ATOMIC_OPS(or, i, or) +ATOMIC_OPS(xor, i, xor) + +#define arch_atomic_fetch_and arch_atomic_fetch_and +#define arch_atomic_fetch_and_acquire arch_atomic_fetch_and +#define arch_atomic_fetch_and_release arch_atomic_fetch_and +#define arch_atomic_fetch_and_relaxed arch_atomic_fetch_and_relaxed +#define arch_atomic_fetch_or arch_atomic_fetch_or +#define arch_atomic_fetch_or_acquire arch_atomic_fetch_or +#define arch_atomic_fetch_or_release arch_atomic_fetch_or +#define arch_atomic_fetch_or_relaxed arch_atomic_fetch_or_relaxed +#define arch_atomic_fetch_xor arch_atomic_fetch_xor +#define arch_atomic_fetch_xor_acquire arch_atomic_fetch_xor +#define arch_atomic_fetch_xor_release arch_atomic_fetch_xor +#define arch_atomic_fetch_xor_relaxed arch_atomic_fetch_xor_relaxed + +#undef ATOMIC_OPS +#undef ATOMIC_FETCH_OP +#undef ATOMIC_OP_RETURN +#undef ATOMIC_OP + +#ifdef CONFIG_64BIT + +#define ATOMIC64_OP(op, I, asm_op) \ +static inline void arch_atomic64_##op(long i, atomic64_t *v) \ +{ \ + __asm__ __volatile__( \ + "am"#asm_op".d " " $zero, %1, %0 \n" \ + : "+ZB" (v->counter) \ + : "r" (I) \ + : "memory"); \ +} + +#define ATOMIC64_OP_RETURN(op, I, asm_op, c_op, mb, suffix) \ +static inline long arch_atomic64_##op##_return##suffix(long i, atomic64_t *v) \ +{ \ + long result; \ + __asm__ __volatile__( \ + "am"#asm_op#mb".d " " %1, %2, %0 \n" \ + : "+ZB" (v->counter), "=&r" (result) \ + : "r" (I) \ + : "memory"); \ + \ + return result c_op I; \ +} + +#define ATOMIC64_FETCH_OP(op, I, asm_op, mb, suffix) \ +static inline long arch_atomic64_fetch_##op##suffix(long i, atomic64_t *v) \ +{ \ + long result; \ + \ + __asm__ __volatile__( \ + "am"#asm_op#mb".d " " %1, %2, %0 \n" \ + : "+ZB" (v->counter), "=&r" (result) \ + : "r" (I) \ + : "memory"); \ + \ + return result; \ +} + +#define ATOMIC64_OPS(op, I, asm_op, c_op) \ + ATOMIC64_OP(op, I, asm_op) \ + ATOMIC64_OP_RETURN(op, I, asm_op, c_op, _db, ) \ + ATOMIC64_OP_RETURN(op, I, asm_op, c_op, , _relaxed) \ + ATOMIC64_FETCH_OP(op, I, asm_op, _db, ) \ + ATOMIC64_FETCH_OP(op, I, asm_op, , _relaxed) + +ATOMIC64_OPS(add, i, add, +) +ATOMIC64_OPS(sub, -i, add, +) + +#define arch_atomic64_add_return arch_atomic64_add_return +#define arch_atomic64_add_return_acquire arch_atomic64_add_return +#define arch_atomic64_add_return_release arch_atomic64_add_return +#define arch_atomic64_add_return_relaxed arch_atomic64_add_return_relaxed +#define arch_atomic64_sub_return arch_atomic64_sub_return +#define arch_atomic64_sub_return_acquire arch_atomic64_sub_return +#define arch_atomic64_sub_return_release arch_atomic64_sub_return +#define arch_atomic64_sub_return_relaxed arch_atomic64_sub_return_relaxed +#define arch_atomic64_fetch_add arch_atomic64_fetch_add +#define arch_atomic64_fetch_add_acquire arch_atomic64_fetch_add +#define arch_atomic64_fetch_add_release arch_atomic64_fetch_add +#define arch_atomic64_fetch_add_relaxed arch_atomic64_fetch_add_relaxed +#define arch_atomic64_fetch_sub arch_atomic64_fetch_sub +#define arch_atomic64_fetch_sub_acquire arch_atomic64_fetch_sub +#define arch_atomic64_fetch_sub_release arch_atomic64_fetch_sub +#define arch_atomic64_fetch_sub_relaxed arch_atomic64_fetch_sub_relaxed + +#undef ATOMIC64_OPS + +#define ATOMIC64_OPS(op, I, asm_op) \ + ATOMIC64_OP(op, I, asm_op) \ + ATOMIC64_FETCH_OP(op, I, asm_op, _db, ) \ + ATOMIC64_FETCH_OP(op, I, asm_op, , _relaxed) + +ATOMIC64_OPS(and, i, and) +ATOMIC64_OPS(or, i, or) +ATOMIC64_OPS(xor, i, xor) + +#define arch_atomic64_fetch_and arch_atomic64_fetch_and +#define arch_atomic64_fetch_and_acquire arch_atomic64_fetch_and +#define arch_atomic64_fetch_and_release arch_atomic64_fetch_and +#define arch_atomic64_fetch_and_relaxed arch_atomic64_fetch_and_relaxed +#define arch_atomic64_fetch_or arch_atomic64_fetch_or +#define arch_atomic64_fetch_or_acquire arch_atomic64_fetch_or +#define arch_atomic64_fetch_or_release arch_atomic64_fetch_or +#define arch_atomic64_fetch_or_relaxed arch_atomic64_fetch_or_relaxed +#define arch_atomic64_fetch_xor arch_atomic64_fetch_xor +#define arch_atomic64_fetch_xor_acquire arch_atomic64_fetch_xor +#define arch_atomic64_fetch_xor_release arch_atomic64_fetch_xor +#define arch_atomic64_fetch_xor_relaxed arch_atomic64_fetch_xor_relaxed + +#undef ATOMIC64_OPS +#undef ATOMIC64_FETCH_OP +#undef ATOMIC64_OP_RETURN +#undef ATOMIC64_OP + +#endif + +#endif /* _ASM_ATOMIC_AMO_H */ diff --git a/arch/loongarch/include/asm/atomic-llsc.h b/arch/loongarch/include/asm/atomic-llsc.h new file mode 100644 index 000000000000..3ce500c88272 --- /dev/null +++ b/arch/loongarch/include/asm/atomic-llsc.h @@ -0,0 +1,100 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Atomic operations (LLSC). + * + * Copyright (C) 2024-2025 Loongson Technology Corporation Limited + */ + +#ifndef _ASM_ATOMIC_LLSC_H +#define _ASM_ATOMIC_LLSC_H + +#include <linux/types.h> +#include <asm/barrier.h> +#include <asm/cmpxchg.h> + +#define ATOMIC_OP(op, I, asm_op) \ +static inline void arch_atomic_##op(int i, atomic_t *v) \ +{ \ + int temp; \ + \ + __asm__ __volatile__( \ + "1: ll.w %0, %1 #atomic_" #op " \n" \ + " " #asm_op " %0, %0, %2 \n" \ + " sc.w %0, %1 \n" \ + " beq %0, $r0, 1b \n" \ + :"=&r" (temp) , "+ZC"(v->counter) \ + :"r" (I) \ + ); \ +} + +#define ATOMIC_OP_RETURN(op, I, asm_op) \ +static inline int arch_atomic_##op##_return_relaxed(int i, atomic_t *v) \ +{ \ + int result, temp; \ + \ + __asm__ __volatile__( \ + "1: ll.w %1, %2 # atomic_" #op "_return \n" \ + " " #asm_op " %0, %1, %3 \n" \ + " sc.w %0, %2 \n" \ + " beq %0, $r0 ,1b \n" \ + " " #asm_op " %0, %1, %3 \n" \ + : "=&r" (result), "=&r" (temp), "+ZC"(v->counter) \ + : "r" (I)); \ + \ + return result; \ +} + +#define ATOMIC_FETCH_OP(op, I, asm_op) \ +static inline int arch_atomic_fetch_##op##_relaxed(int i, atomic_t *v) \ +{ \ + int result, temp; \ + \ + __asm__ __volatile__( \ + "1: ll.w %1, %2 # atomic_fetch_" #op " \n" \ + " " #asm_op " %0, %1, %3 \n" \ + " sc.w %0, %2 \n" \ + " beq %0, $r0 ,1b \n" \ + " add.w %0, %1 ,$r0 \n" \ + : "=&r" (result), "=&r" (temp), "+ZC" (v->counter) \ + : "r" (I)); \ + \ + return result; \ +} + +#define ATOMIC_OPS(op,I ,asm_op, c_op) \ + ATOMIC_OP(op, I, asm_op) \ + ATOMIC_OP_RETURN(op, I , asm_op) \ + ATOMIC_FETCH_OP(op, I, asm_op) + +ATOMIC_OPS(add, i , add.w ,+=) +ATOMIC_OPS(sub, -i , add.w ,+=) + +#define arch_atomic_add_return_relaxed arch_atomic_add_return_relaxed +#define arch_atomic_sub_return_relaxed arch_atomic_sub_return_relaxed +#define arch_atomic_fetch_add_relaxed arch_atomic_fetch_add_relaxed +#define arch_atomic_fetch_sub_relaxed arch_atomic_fetch_sub_relaxed + +#undef ATOMIC_OPS + +#define ATOMIC_OPS(op, I, asm_op) \ + ATOMIC_OP(op, I, asm_op) \ + ATOMIC_FETCH_OP(op, I, asm_op) + +ATOMIC_OPS(and, i, and) +ATOMIC_OPS(or, i, or) +ATOMIC_OPS(xor, i, xor) + +#define arch_atomic_fetch_and_relaxed arch_atomic_fetch_and_relaxed +#define arch_atomic_fetch_or_relaxed arch_atomic_fetch_or_relaxed +#define arch_atomic_fetch_xor_relaxed arch_atomic_fetch_xor_relaxed + +#undef ATOMIC_OPS +#undef ATOMIC_FETCH_OP +#undef ATOMIC_OP_RETURN +#undef ATOMIC_OP + +#ifdef CONFIG_64BIT +#error "64-bit LLSC atomic operations are not supported" +#endif + +#endif /* _ASM_ATOMIC_LLSC_H */ diff --git a/arch/loongarch/include/asm/atomic.h b/arch/loongarch/include/asm/atomic.h index c86f0ab922ec..444b9ddcd004 100644 --- a/arch/loongarch/include/asm/atomic.h +++ b/arch/loongarch/include/asm/atomic.h @@ -11,6 +11,16 @@ #include <asm/barrier.h> #include <asm/cmpxchg.h> +#ifdef CONFIG_CPU_HAS_AMO +#include <asm/atomic-amo.h> +#else +#include <asm/atomic-llsc.h> +#endif + +#ifdef CONFIG_GENERIC_ATOMIC64 +#include <asm-generic/atomic64.h> +#endif + #if __SIZEOF_LONG__ == 4 #define __LL "ll.w " #define __SC "sc.w " @@ -34,100 +44,6 @@ #define arch_atomic_read(v) READ_ONCE((v)->counter) #define arch_atomic_set(v, i) WRITE_ONCE((v)->counter, (i)) -#define ATOMIC_OP(op, I, asm_op) \ -static inline void arch_atomic_##op(int i, atomic_t *v) \ -{ \ - __asm__ __volatile__( \ - "am"#asm_op".w" " $zero, %1, %0 \n" \ - : "+ZB" (v->counter) \ - : "r" (I) \ - : "memory"); \ -} - -#define ATOMIC_OP_RETURN(op, I, asm_op, c_op, mb, suffix) \ -static inline int arch_atomic_##op##_return##suffix(int i, atomic_t *v) \ -{ \ - int result; \ - \ - __asm__ __volatile__( \ - "am"#asm_op#mb".w" " %1, %2, %0 \n" \ - : "+ZB" (v->counter), "=&r" (result) \ - : "r" (I) \ - : "memory"); \ - \ - return result c_op I; \ -} - -#define ATOMIC_FETCH_OP(op, I, asm_op, mb, suffix) \ -static inline int arch_atomic_fetch_##op##suffix(int i, atomic_t *v) \ -{ \ - int result; \ - \ - __asm__ __volatile__( \ - "am"#asm_op#mb".w" " %1, %2, %0 \n" \ - : "+ZB" (v->counter), "=&r" (result) \ - : "r" (I) \ - : "memory"); \ - \ - return result; \ -} - -#define ATOMIC_OPS(op, I, asm_op, c_op) \ - ATOMIC_OP(op, I, asm_op) \ - ATOMIC_OP_RETURN(op, I, asm_op, c_op, _db, ) \ - ATOMIC_OP_RETURN(op, I, asm_op, c_op, , _relaxed) \ - ATOMIC_FETCH_OP(op, I, asm_op, _db, ) \ - ATOMIC_FETCH_OP(op, I, asm_op, , _relaxed) - -ATOMIC_OPS(add, i, add, +) -ATOMIC_OPS(sub, -i, add, +) - -#define arch_atomic_add_return arch_atomic_add_return -#define arch_atomic_add_return_acquire arch_atomic_add_return -#define arch_atomic_add_return_release arch_atomic_add_return -#define arch_atomic_add_return_relaxed arch_atomic_add_return_relaxed -#define arch_atomic_sub_return arch_atomic_sub_return -#define arch_atomic_sub_return_acquire arch_atomic_sub_return -#define arch_atomic_sub_return_release arch_atomic_sub_return -#define arch_atomic_sub_return_relaxed arch_atomic_sub_return_relaxed -#define arch_atomic_fetch_add arch_atomic_fetch_add -#define arch_atomic_fetch_add_acquire arch_atomic_fetch_add -#define arch_atomic_fetch_add_release arch_atomic_fetch_add -#define arch_atomic_fetch_add_relaxed arch_atomic_fetch_add_relaxed -#define arch_atomic_fetch_sub arch_atomic_fetch_sub -#define arch_atomic_fetch_sub_acquire arch_atomic_fetch_sub -#define arch_atomic_fetch_sub_release arch_atomic_fetch_sub -#define arch_atomic_fetch_sub_relaxed arch_atomic_fetch_sub_relaxed - -#undef ATOMIC_OPS - -#define ATOMIC_OPS(op, I, asm_op) \ - ATOMIC_OP(op, I, asm_op) \ - ATOMIC_FETCH_OP(op, I, asm_op, _db, ) \ - ATOMIC_FETCH_OP(op, I, asm_op, , _relaxed) - -ATOMIC_OPS(and, i, and) -ATOMIC_OPS(or, i, or) -ATOMIC_OPS(xor, i, xor) - -#define arch_atomic_fetch_and arch_atomic_fetch_and -#define arch_atomic_fetch_and_acquire arch_atomic_fetch_and -#define arch_atomic_fetch_and_release arch_atomic_fetch_and -#define arch_atomic_fetch_and_relaxed arch_atomic_fetch_and_relaxed -#define arch_atomic_fetch_or arch_atomic_fetch_or -#define arch_atomic_fetch_or_acquire arch_atomic_fetch_or -#define arch_atomic_fetch_or_release arch_atomic_fetch_or -#define arch_atomic_fetch_or_relaxed arch_atomic_fetch_or_relaxed -#define arch_atomic_fetch_xor arch_atomic_fetch_xor -#define arch_atomic_fetch_xor_acquire arch_atomic_fetch_xor -#define arch_atomic_fetch_xor_release arch_atomic_fetch_xor -#define arch_atomic_fetch_xor_relaxed arch_atomic_fetch_xor_relaxed - -#undef ATOMIC_OPS -#undef ATOMIC_FETCH_OP -#undef ATOMIC_OP_RETURN -#undef ATOMIC_OP - static inline int arch_atomic_fetch_add_unless(atomic_t *v, int a, int u) { int prev, rc; @@ -194,99 +110,6 @@ static inline int arch_atomic_sub_if_positive(int i, atomic_t *v) #define arch_atomic64_read(v) READ_ONCE((v)->counter) #define arch_atomic64_set(v, i) WRITE_ONCE((v)->counter, (i)) -#define ATOMIC64_OP(op, I, asm_op) \ -static inline void arch_atomic64_##op(long i, atomic64_t *v) \ -{ \ - __asm__ __volatile__( \ - "am"#asm_op".d " " $zero, %1, %0 \n" \ - : "+ZB" (v->counter) \ - : "r" (I) \ - : "memory"); \ -} - -#define ATOMIC64_OP_RETURN(op, I, asm_op, c_op, mb, suffix) \ -static inline long arch_atomic64_##op##_return##suffix(long i, atomic64_t *v) \ -{ \ - long result; \ - __asm__ __volatile__( \ - "am"#asm_op#mb".d " " %1, %2, %0 \n" \ - : "+ZB" (v->counter), "=&r" (result) \ - : "r" (I) \ - : "memory"); \ - \ - return result c_op I; \ -} - -#define ATOMIC64_FETCH_OP(op, I, asm_op, mb, suffix) \ -static inline long arch_atomic64_fetch_##op##suffix(long i, atomic64_t *v) \ -{ \ - long result; \ - \ - __asm__ __volatile__( \ - "am"#asm_op#mb".d " " %1, %2, %0 \n" \ - : "+ZB" (v->counter), "=&r" (result) \ - : "r" (I) \ - : "memory"); \ - \ - return result; \ -} - -#define ATOMIC64_OPS(op, I, asm_op, c_op) \ - ATOMIC64_OP(op, I, asm_op) \ - ATOMIC64_OP_RETURN(op, I, asm_op, c_op, _db, ) \ - ATOMIC64_OP_RETURN(op, I, asm_op, c_op, , _relaxed) \ - ATOMIC64_FETCH_OP(op, I, asm_op, _db, ) \ - ATOMIC64_FETCH_OP(op, I, asm_op, , _relaxed) - -ATOMIC64_OPS(add, i, add, +) -ATOMIC64_OPS(sub, -i, add, +) - -#define arch_atomic64_add_return arch_atomic64_add_return -#define arch_atomic64_add_return_acquire arch_atomic64_add_return -#define arch_atomic64_add_return_release arch_atomic64_add_return -#define arch_atomic64_add_return_relaxed arch_atomic64_add_return_relaxed -#define arch_atomic64_sub_return arch_atomic64_sub_return -#define arch_atomic64_sub_return_acquire arch_atomic64_sub_return -#define arch_atomic64_sub_return_release arch_atomic64_sub_return -#define arch_atomic64_sub_return_relaxed arch_atomic64_sub_return_relaxed -#define arch_atomic64_fetch_add arch_atomic64_fetch_add -#define arch_atomic64_fetch_add_acquire arch_atomic64_fetch_add -#define arch_atomic64_fetch_add_release arch_atomic64_fetch_add -#define arch_atomic64_fetch_add_relaxed arch_atomic64_fetch_add_relaxed -#define arch_atomic64_fetch_sub arch_atomic64_fetch_sub -#define arch_atomic64_fetch_sub_acquire arch_atomic64_fetch_sub -#define arch_atomic64_fetch_sub_release arch_atomic64_fetch_sub -#define arch_atomic64_fetch_sub_relaxed arch_atomic64_fetch_sub_relaxed - -#undef ATOMIC64_OPS - -#define ATOMIC64_OPS(op, I, asm_op) \ - ATOMIC64_OP(op, I, asm_op) \ - ATOMIC64_FETCH_OP(op, I, asm_op, _db, ) \ - ATOMIC64_FETCH_OP(op, I, asm_op, , _relaxed) - -ATOMIC64_OPS(and, i, and) -ATOMIC64_OPS(or, i, or) -ATOMIC64_OPS(xor, i, xor) - -#define arch_atomic64_fetch_and arch_atomic64_fetch_and -#define arch_atomic64_fetch_and_acquire arch_atomic64_fetch_and -#define arch_atomic64_fetch_and_release arch_atomic64_fetch_and -#define arch_atomic64_fetch_and_relaxed arch_atomic64_fetch_and_relaxed -#define arch_atomic64_fetch_or arch_atomic64_fetch_or -#define arch_atomic64_fetch_or_acquire arch_atomic64_fetch_or -#define arch_atomic64_fetch_or_release arch_atomic64_fetch_or -#define arch_atomic64_fetch_or_relaxed arch_atomic64_fetch_or_relaxed -#define arch_atomic64_fetch_xor arch_atomic64_fetch_xor -#define arch_atomic64_fetch_xor_acquire arch_atomic64_fetch_xor -#define arch_atomic64_fetch_xor_release arch_atomic64_fetch_xor -#define arch_atomic64_fetch_xor_relaxed arch_atomic64_fetch_xor_relaxed - -#undef ATOMIC64_OPS -#undef ATOMIC64_FETCH_OP -#undef ATOMIC64_OP_RETURN -#undef ATOMIC64_OP - static inline long arch_atomic64_fetch_add_unless(atomic64_t *v, long a, long u) { long prev, rc; diff --git a/arch/loongarch/include/asm/bitops.h b/arch/loongarch/include/asm/bitops.h index 69e00f8d8034..411106bf9902 100644 --- a/arch/loongarch/include/asm/bitops.h +++ b/arch/loongarch/include/asm/bitops.h @@ -13,11 +13,22 @@ #include <asm/barrier.h> +#ifdef CONFIG_32BIT_REDUCED + +#include <asm-generic/bitops/ffs.h> +#include <asm-generic/bitops/fls.h> +#include <asm-generic/bitops/__ffs.h> +#include <asm-generic/bitops/__fls.h> + +#else /* CONFIG_32BIT_STANDARD || CONFIG_64BIT */ + #include <asm-generic/bitops/builtin-ffs.h> #include <asm-generic/bitops/builtin-fls.h> #include <asm-generic/bitops/builtin-__ffs.h> #include <asm-generic/bitops/builtin-__fls.h> +#endif + #include <asm-generic/bitops/ffz.h> #include <asm-generic/bitops/fls64.h> diff --git a/arch/loongarch/include/asm/bitrev.h b/arch/loongarch/include/asm/bitrev.h index 46f275b9cdf7..757738ea38d7 100644 --- a/arch/loongarch/include/asm/bitrev.h +++ b/arch/loongarch/include/asm/bitrev.h @@ -11,7 +11,7 @@ static __always_inline __attribute_const__ u32 __arch_bitrev32(u32 x) { u32 ret; - asm("bitrev.4b %0, %1" : "=r"(ret) : "r"(__swab32(x))); + asm("bitrev.w %0, %1" : "=r"(ret) : "r"(x)); return ret; } diff --git a/arch/loongarch/include/asm/bug.h b/arch/loongarch/include/asm/bug.h index f6f254f2c5db..d090a5bec5eb 100644 --- a/arch/loongarch/include/asm/bug.h +++ b/arch/loongarch/include/asm/bug.h @@ -11,7 +11,7 @@ #else #define __BUGVERBOSE_LOCATION(file, line) \ .pushsection .rodata.str, "aMS", @progbits, 1; \ - 10002: .string file; \ + 10002: .ascii file "\0"; \ .popsection; \ \ .long 10002b - .; \ @@ -20,39 +20,38 @@ #endif #ifndef CONFIG_GENERIC_BUG -#define __BUG_ENTRY(flags) +#define __BUG_ENTRY(cond_str, flags) #else -#define __BUG_ENTRY(flags) \ +#define __BUG_ENTRY(cond_str, flags) \ .pushsection __bug_table, "aw"; \ .align 2; \ 10000: .long 10001f - .; \ - _BUGVERBOSE_LOCATION(__FILE__, __LINE__) \ - .short flags; \ + _BUGVERBOSE_LOCATION(WARN_CONDITION_STR(cond_str) __FILE__, __LINE__) \ + .short flags; \ .popsection; \ 10001: #endif -#define ASM_BUG_FLAGS(flags) \ - __BUG_ENTRY(flags) \ +#define ASM_BUG_FLAGS(cond_str, flags) \ + __BUG_ENTRY(cond_str, flags) \ break BRK_BUG; -#define ASM_BUG() ASM_BUG_FLAGS(0) +#define ASM_BUG() ASM_BUG_FLAGS("", 0) -#define __BUG_FLAGS(flags, extra) \ - asm_inline volatile (__stringify(ASM_BUG_FLAGS(flags)) \ - extra); +#define __BUG_FLAGS(cond_str, flags, extra) \ + asm_inline volatile (__stringify(ASM_BUG_FLAGS(cond_str, flags)) extra); -#define __WARN_FLAGS(flags) \ +#define __WARN_FLAGS(cond_str, flags) \ do { \ instrumentation_begin(); \ - __BUG_FLAGS(BUGFLAG_WARNING|(flags), ANNOTATE_REACHABLE(10001b));\ + __BUG_FLAGS(cond_str, BUGFLAG_WARNING|(flags), ANNOTATE_REACHABLE(10001b));\ instrumentation_end(); \ } while (0) #define BUG() \ do { \ instrumentation_begin(); \ - __BUG_FLAGS(0, ""); \ + __BUG_FLAGS("", 0, ""); \ unreachable(); \ } while (0) diff --git a/arch/loongarch/include/asm/cache.h b/arch/loongarch/include/asm/cache.h index 1b6d09617199..aa622c754414 100644 --- a/arch/loongarch/include/asm/cache.h +++ b/arch/loongarch/include/asm/cache.h @@ -8,6 +8,8 @@ #define L1_CACHE_SHIFT CONFIG_L1_CACHE_SHIFT #define L1_CACHE_BYTES (1 << L1_CACHE_SHIFT) +#define ARCH_DMA_MINALIGN (16) + #define __read_mostly __section(".data..read_mostly") #endif /* _ASM_CACHE_H */ diff --git a/arch/loongarch/include/asm/cacheflush.h b/arch/loongarch/include/asm/cacheflush.h index f8754d08a31a..190651be9546 100644 --- a/arch/loongarch/include/asm/cacheflush.h +++ b/arch/loongarch/include/asm/cacheflush.h @@ -32,8 +32,22 @@ static inline unsigned int cpu_last_level_cache_line_size(void) } asmlinkage void __flush_cache_all(void); -void local_flush_icache_range(unsigned long start, unsigned long end); +/* + * LoongArch maintains ICache/DCache coherency by hardware, + * we just need "ibar" to avoid instruction hazard here. + */ +static inline void local_flush_icache_all(void) +{ + asm volatile ("ibar\t0\n"::); +} + +static inline void local_flush_icache_range(unsigned long start, unsigned long end) +{ + asm volatile ("ibar\t0\n"::); +} + +#define flush_icache_all local_flush_icache_all #define flush_icache_range local_flush_icache_range #define flush_icache_user_range local_flush_icache_range diff --git a/arch/loongarch/include/asm/checksum.h b/arch/loongarch/include/asm/checksum.h index cabbf6af44c4..cc2754e0aa25 100644 --- a/arch/loongarch/include/asm/checksum.h +++ b/arch/loongarch/include/asm/checksum.h @@ -9,6 +9,8 @@ #include <linux/bitops.h> #include <linux/in6.h> +#ifdef CONFIG_64BIT + #define _HAVE_ARCH_IPV6_CSUM __sum16 csum_ipv6_magic(const struct in6_addr *saddr, const struct in6_addr *daddr, @@ -61,6 +63,8 @@ static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl) extern unsigned int do_csum(const unsigned char *buff, int len); #define do_csum do_csum +#endif + #include <asm-generic/checksum.h> #endif /* __ASM_CHECKSUM_H */ diff --git a/arch/loongarch/include/asm/cmpxchg.h b/arch/loongarch/include/asm/cmpxchg.h index 979fde61bba8..909f9274fe71 100644 --- a/arch/loongarch/include/asm/cmpxchg.h +++ b/arch/loongarch/include/asm/cmpxchg.h @@ -8,18 +8,35 @@ #include <linux/bits.h> #include <linux/build_bug.h> #include <asm/barrier.h> +#include <asm/cpu-features.h> -#define __xchg_asm(amswap_db, m, val) \ +#define __xchg_amo_asm(amswap_db, m, val) \ ({ \ - __typeof(val) __ret; \ + __typeof(val) __ret; \ \ - __asm__ __volatile__ ( \ - " "amswap_db" %1, %z2, %0 \n" \ - : "+ZB" (*m), "=&r" (__ret) \ - : "Jr" (val) \ - : "memory"); \ + __asm__ __volatile__ ( \ + " "amswap_db" %1, %z2, %0 \n" \ + : "+ZB" (*m), "=&r" (__ret) \ + : "Jr" (val) \ + : "memory"); \ \ - __ret; \ + __ret; \ +}) + +#define __xchg_llsc_asm(ld, st, m, val) \ +({ \ + __typeof(val) __ret, __tmp; \ + \ + asm volatile ( \ + "1: ll.w %0, %3 \n" \ + " move %1, %z4 \n" \ + " sc.w %1, %2 \n" \ + " beqz %1, 1b \n" \ + : "=&r" (__ret), "=&r" (__tmp), "=ZC" (*m) \ + : "ZC" (*m), "Jr" (val) \ + : "memory"); \ + \ + __ret; \ }) static inline unsigned int __xchg_small(volatile void *ptr, unsigned int val, @@ -67,13 +84,23 @@ __arch_xchg(volatile void *ptr, unsigned long x, int size) switch (size) { case 1: case 2: - return __xchg_small(ptr, x, size); + return __xchg_small((volatile void *)ptr, x, size); case 4: - return __xchg_asm("amswap_db.w", (volatile u32 *)ptr, (u32)x); +#ifdef CONFIG_CPU_HAS_AMO + return __xchg_amo_asm("amswap_db.w", (volatile u32 *)ptr, (u32)x); +#else + return __xchg_llsc_asm("ll.w", "sc.w", (volatile u32 *)ptr, (u32)x); +#endif /* CONFIG_CPU_HAS_AMO */ +#ifdef CONFIG_64BIT case 8: - return __xchg_asm("amswap_db.d", (volatile u64 *)ptr, (u64)x); +#ifdef CONFIG_CPU_HAS_AMO + return __xchg_amo_asm("amswap_db.d", (volatile u64 *)ptr, (u64)x); +#else + return __xchg_llsc_asm("ll.d", "sc.d", (volatile u64 *)ptr, (u64)x); +#endif /* CONFIG_CPU_HAS_AMO */ +#endif /* CONFIG_64BIT */ default: BUILD_BUG(); @@ -210,6 +237,64 @@ __cmpxchg(volatile void *ptr, unsigned long old, unsigned long new, unsigned int BUILD_BUG_ON(sizeof(*(ptr)) != 8); \ arch_cmpxchg((ptr), (o), (n)); \ }) + +#ifdef CONFIG_AS_HAS_SCQ_EXTENSION + +union __u128_halves { + u128 full; + struct { + u64 low; + u64 high; + }; +}; + +#define system_has_cmpxchg128() cpu_opt(LOONGARCH_CPU_SCQ) + +#define __arch_cmpxchg128(ptr, old, new, llsc_mb) \ +({ \ + union __u128_halves __old, __new, __ret; \ + volatile u64 *__ptr = (volatile u64 *)(ptr); \ + \ + __old.full = (old); \ + __new.full = (new); \ + \ + __asm__ __volatile__( \ + "1: ll.d %0, %3 # 128-bit cmpxchg low \n" \ + llsc_mb \ + " ld.d %1, %4 # 128-bit cmpxchg high \n" \ + " move $t0, %0 \n" \ + " move $t1, %1 \n" \ + " bne %0, %z5, 2f \n" \ + " bne %1, %z6, 2f \n" \ + " move $t0, %z7 \n" \ + " move $t1, %z8 \n" \ + "2: sc.q $t0, $t1, %2 \n" \ + " beqz $t0, 1b \n" \ + llsc_mb \ + : "=&r" (__ret.low), "=&r" (__ret.high) \ + : "r" (__ptr), \ + "ZC" (__ptr[0]), "m" (__ptr[1]), \ + "Jr" (__old.low), "Jr" (__old.high), \ + "Jr" (__new.low), "Jr" (__new.high) \ + : "t0", "t1", "memory"); \ + \ + __ret.full; \ +}) + +#define arch_cmpxchg128(ptr, o, n) \ +({ \ + BUILD_BUG_ON(sizeof(*(ptr)) != 16); \ + __arch_cmpxchg128(ptr, o, n, __WEAK_LLSC_MB); \ +}) + +#define arch_cmpxchg128_local(ptr, o, n) \ +({ \ + BUILD_BUG_ON(sizeof(*(ptr)) != 16); \ + __arch_cmpxchg128(ptr, o, n, ""); \ +}) + +#endif /* CONFIG_AS_HAS_SCQ_EXTENSION */ + #else #include <asm-generic/cmpxchg-local.h> #define arch_cmpxchg64_local(ptr, o, n) __generic_cmpxchg64_local((ptr), (o), (n)) diff --git a/arch/loongarch/include/asm/cpu-features.h b/arch/loongarch/include/asm/cpu-features.h index fc83bb32f9f0..62059c5551b9 100644 --- a/arch/loongarch/include/asm/cpu-features.h +++ b/arch/loongarch/include/asm/cpu-features.h @@ -20,16 +20,13 @@ #define cpu_has_loongarch64 (cpu_data[0].isa_level & LOONGARCH_CPU_ISA_64BIT) #ifdef CONFIG_32BIT -# define cpu_has_64bits (cpu_data[0].isa_level & LOONGARCH_CPU_ISA_64BIT) # define cpu_vabits 31 # define cpu_pabits 31 #endif #ifdef CONFIG_64BIT -# define cpu_has_64bits 1 # define cpu_vabits cpu_data[0].vabits # define cpu_pabits cpu_data[0].pabits -# define __NEED_ADDRBITS_PROBE #endif /* @@ -38,6 +35,8 @@ */ #define cpu_has_cpucfg cpu_opt(LOONGARCH_CPU_CPUCFG) #define cpu_has_lam cpu_opt(LOONGARCH_CPU_LAM) +#define cpu_has_lam_bh cpu_opt(LOONGARCH_CPU_LAM_BH) +#define cpu_has_scq cpu_opt(LOONGARCH_CPU_SCQ) #define cpu_has_ual cpu_opt(LOONGARCH_CPU_UAL) #define cpu_has_fpu cpu_opt(LOONGARCH_CPU_FPU) #define cpu_has_lsx cpu_opt(LOONGARCH_CPU_LSX) @@ -67,6 +66,8 @@ #define cpu_has_hypervisor cpu_opt(LOONGARCH_CPU_HYPERVISOR) #define cpu_has_ptw cpu_opt(LOONGARCH_CPU_PTW) #define cpu_has_lspw cpu_opt(LOONGARCH_CPU_LSPW) +#define cpu_has_msgint cpu_opt(LOONGARCH_CPU_MSGINT) #define cpu_has_avecint cpu_opt(LOONGARCH_CPU_AVECINT) +#define cpu_has_redirectint cpu_opt(LOONGARCH_CPU_REDIRECTINT) #endif /* __ASM_CPU_FEATURES_H */ diff --git a/arch/loongarch/include/asm/cpu.h b/arch/loongarch/include/asm/cpu.h index 98cf4d7b4b0a..91b96938861e 100644 --- a/arch/loongarch/include/asm/cpu.h +++ b/arch/loongarch/include/asm/cpu.h @@ -46,7 +46,7 @@ #define PRID_PRODUCT_MASK 0x0fff -#if !defined(__ASSEMBLY__) +#if !defined(__ASSEMBLER__) enum cpu_type_enum { CPU_UNKNOWN, @@ -55,7 +55,28 @@ enum cpu_type_enum { CPU_LAST }; -#endif /* !__ASSEMBLY */ +static inline char *id_to_core_name(unsigned int id) +{ + if ((id & PRID_COMP_MASK) != PRID_COMP_LOONGSON) + return "Unknown"; + + switch (id & PRID_SERIES_MASK) { + case PRID_SERIES_LA132: + return "LA132"; + case PRID_SERIES_LA264: + return "LA264"; + case PRID_SERIES_LA364: + return "LA364"; + case PRID_SERIES_LA464: + return "LA464"; + case PRID_SERIES_LA664: + return "LA664"; + default: + return "Unknown"; + } +} + +#endif /* !__ASSEMBLER__ */ /* * ISA Level encodings @@ -74,37 +95,43 @@ enum cpu_type_enum { */ #define CPU_FEATURE_CPUCFG 0 /* CPU has CPUCFG */ #define CPU_FEATURE_LAM 1 /* CPU has Atomic instructions */ -#define CPU_FEATURE_UAL 2 /* CPU supports unaligned access */ -#define CPU_FEATURE_FPU 3 /* CPU has FPU */ -#define CPU_FEATURE_LSX 4 /* CPU has LSX (128-bit SIMD) */ -#define CPU_FEATURE_LASX 5 /* CPU has LASX (256-bit SIMD) */ -#define CPU_FEATURE_CRC32 6 /* CPU has CRC32 instructions */ -#define CPU_FEATURE_COMPLEX 7 /* CPU has Complex instructions */ -#define CPU_FEATURE_CRYPTO 8 /* CPU has Crypto instructions */ -#define CPU_FEATURE_LVZ 9 /* CPU has Virtualization extension */ -#define CPU_FEATURE_LBT_X86 10 /* CPU has X86 Binary Translation */ -#define CPU_FEATURE_LBT_ARM 11 /* CPU has ARM Binary Translation */ -#define CPU_FEATURE_LBT_MIPS 12 /* CPU has MIPS Binary Translation */ -#define CPU_FEATURE_TLB 13 /* CPU has TLB */ -#define CPU_FEATURE_CSR 14 /* CPU has CSR */ -#define CPU_FEATURE_IOCSR 15 /* CPU has IOCSR */ -#define CPU_FEATURE_WATCH 16 /* CPU has watchpoint registers */ -#define CPU_FEATURE_VINT 17 /* CPU has vectored interrupts */ -#define CPU_FEATURE_CSRIPI 18 /* CPU has CSR-IPI */ -#define CPU_FEATURE_EXTIOI 19 /* CPU has EXT-IOI */ -#define CPU_FEATURE_PREFETCH 20 /* CPU has prefetch instructions */ -#define CPU_FEATURE_PMP 21 /* CPU has perfermance counter */ -#define CPU_FEATURE_SCALEFREQ 22 /* CPU supports cpufreq scaling */ -#define CPU_FEATURE_FLATMODE 23 /* CPU has flat mode */ -#define CPU_FEATURE_EIODECODE 24 /* CPU has EXTIOI interrupt pin decode mode */ -#define CPU_FEATURE_GUESTID 25 /* CPU has GuestID feature */ -#define CPU_FEATURE_HYPERVISOR 26 /* CPU has hypervisor (running in VM) */ -#define CPU_FEATURE_PTW 27 /* CPU has hardware page table walker */ -#define CPU_FEATURE_LSPW 28 /* CPU has LSPW (lddir/ldpte instructions) */ -#define CPU_FEATURE_AVECINT 29 /* CPU has AVEC interrupt */ +#define CPU_FEATURE_LAM_BH 2 /* CPU has AM{SWAP/ADD}[_DB].{B/H} instructions */ +#define CPU_FEATURE_SCQ 3 /* CPU has SC.Q instruction */ +#define CPU_FEATURE_UAL 4 /* CPU supports unaligned access */ +#define CPU_FEATURE_FPU 5 /* CPU has FPU */ +#define CPU_FEATURE_LSX 6 /* CPU has LSX (128-bit SIMD) */ +#define CPU_FEATURE_LASX 7 /* CPU has LASX (256-bit SIMD) */ +#define CPU_FEATURE_CRC32 8 /* CPU has CRC32 instructions */ +#define CPU_FEATURE_COMPLEX 9 /* CPU has Complex instructions */ +#define CPU_FEATURE_CRYPTO 10 /* CPU has Crypto instructions */ +#define CPU_FEATURE_LVZ 11 /* CPU has Virtualization extension */ +#define CPU_FEATURE_LBT_X86 12 /* CPU has X86 Binary Translation */ +#define CPU_FEATURE_LBT_ARM 13 /* CPU has ARM Binary Translation */ +#define CPU_FEATURE_LBT_MIPS 14 /* CPU has MIPS Binary Translation */ +#define CPU_FEATURE_TLB 15 /* CPU has TLB */ +#define CPU_FEATURE_CSR 16 /* CPU has CSR */ +#define CPU_FEATURE_IOCSR 17 /* CPU has IOCSR */ +#define CPU_FEATURE_WATCH 18 /* CPU has watchpoint registers */ +#define CPU_FEATURE_VINT 19 /* CPU has vectored interrupts */ +#define CPU_FEATURE_CSRIPI 20 /* CPU has CSR-IPI */ +#define CPU_FEATURE_EXTIOI 21 /* CPU has EXT-IOI */ +#define CPU_FEATURE_PREFETCH 22 /* CPU has prefetch instructions */ +#define CPU_FEATURE_PMP 23 /* CPU has perfermance counter */ +#define CPU_FEATURE_SCALEFREQ 24 /* CPU supports cpufreq scaling */ +#define CPU_FEATURE_FLATMODE 25 /* CPU has flat mode */ +#define CPU_FEATURE_EIODECODE 26 /* CPU has EXTIOI interrupt pin decode mode */ +#define CPU_FEATURE_GUESTID 27 /* CPU has GuestID feature */ +#define CPU_FEATURE_HYPERVISOR 28 /* CPU has hypervisor (running in VM) */ +#define CPU_FEATURE_PTW 29 /* CPU has hardware page table walker */ +#define CPU_FEATURE_LSPW 30 /* CPU has LSPW (lddir/ldpte instructions) */ +#define CPU_FEATURE_MSGINT 31 /* CPU has MSG interrupt */ +#define CPU_FEATURE_AVECINT 32 /* CPU has AVEC interrupt */ +#define CPU_FEATURE_REDIRECTINT 33 /* CPU has interrupt remapping */ #define LOONGARCH_CPU_CPUCFG BIT_ULL(CPU_FEATURE_CPUCFG) #define LOONGARCH_CPU_LAM BIT_ULL(CPU_FEATURE_LAM) +#define LOONGARCH_CPU_LAM_BH BIT_ULL(CPU_FEATURE_LAM_BH) +#define LOONGARCH_CPU_SCQ BIT_ULL(CPU_FEATURE_SCQ) #define LOONGARCH_CPU_UAL BIT_ULL(CPU_FEATURE_UAL) #define LOONGARCH_CPU_FPU BIT_ULL(CPU_FEATURE_FPU) #define LOONGARCH_CPU_LSX BIT_ULL(CPU_FEATURE_LSX) @@ -132,6 +159,8 @@ enum cpu_type_enum { #define LOONGARCH_CPU_HYPERVISOR BIT_ULL(CPU_FEATURE_HYPERVISOR) #define LOONGARCH_CPU_PTW BIT_ULL(CPU_FEATURE_PTW) #define LOONGARCH_CPU_LSPW BIT_ULL(CPU_FEATURE_LSPW) +#define LOONGARCH_CPU_MSGINT BIT_ULL(CPU_FEATURE_MSGINT) #define LOONGARCH_CPU_AVECINT BIT_ULL(CPU_FEATURE_AVECINT) +#define LOONGARCH_CPU_REDIRECTINT BIT_ULL(CPU_FEATURE_REDIRECTINT) #endif /* _ASM_CPU_H */ diff --git a/arch/loongarch/include/asm/dmi.h b/arch/loongarch/include/asm/dmi.h index 605493417753..11bb3c8a7179 100644 --- a/arch/loongarch/include/asm/dmi.h +++ b/arch/loongarch/include/asm/dmi.h @@ -12,7 +12,7 @@ #define dmi_early_unmap(x, l) dmi_unmap(x) #define dmi_alloc(l) memblock_alloc(l, PAGE_SIZE) -static inline void *dmi_remap(u64 phys_addr, unsigned long size) +static inline void *dmi_remap(phys_addr_t phys_addr, unsigned long size) { return ((void *)TO_CACHE(phys_addr)); } diff --git a/arch/loongarch/include/asm/efi.h b/arch/loongarch/include/asm/efi.h index eddc8e79b3fa..1ad764b18c3e 100644 --- a/arch/loongarch/include/asm/efi.h +++ b/arch/loongarch/include/asm/efi.h @@ -30,6 +30,8 @@ static inline unsigned long efi_get_kimg_min_align(void) return SZ_2M; } -#define EFI_KIMG_PREFERRED_ADDRESS PHYSADDR(VMLINUX_LOAD_ADDRESS) +unsigned long efi_get_kimg_kaslr_address(void); + +#define EFI_KIMG_PREFERRED_ADDRESS efi_get_kimg_kaslr_address() #endif /* _ASM_LOONGARCH_EFI_H */ diff --git a/arch/loongarch/include/asm/elf.h b/arch/loongarch/include/asm/elf.h index f16bd42456e4..912c50cdd6b7 100644 --- a/arch/loongarch/include/asm/elf.h +++ b/arch/loongarch/include/asm/elf.h @@ -120,6 +120,36 @@ #define R_LARCH_ADD_ULEB128 107 #define R_LARCH_SUB_ULEB128 108 #define R_LARCH_64_PCREL 109 +#define R_LARCH_CALL36 110 +#define R_LARCH_TLS_DESC_PC_HI20 111 +#define R_LARCH_TLS_DESC_PC_LO12 112 +#define R_LARCH_TLS_DESC64_PC_LO20 113 +#define R_LARCH_TLS_DESC64_PC_HI12 114 +#define R_LARCH_TLS_DESC_HI20 115 +#define R_LARCH_TLS_DESC_LO12 116 +#define R_LARCH_TLS_DESC64_LO20 117 +#define R_LARCH_TLS_DESC64_HI12 118 +#define R_LARCH_TLS_DESC_LD 119 +#define R_LARCH_TLS_DESC_CALL 120 +#define R_LARCH_TLS_LE_HI20_R 121 +#define R_LARCH_TLS_LE_ADD_R 122 +#define R_LARCH_TLS_LE_LO12_R 123 +#define R_LARCH_TLS_LD_PCREL20_S2 124 +#define R_LARCH_TLS_GD_PCREL20_S2 125 +#define R_LARCH_TLS_DESC_PCREL20_S2 126 +#define R_LARCH_CALL30 127 +#define R_LARCH_PCADD_HI20 128 +#define R_LARCH_PCADD_LO12 129 +#define R_LARCH_GOT_PCADD_HI20 130 +#define R_LARCH_GOT_PCADD_LO12 131 +#define R_LARCH_TLS_IE_PCADD_HI20 132 +#define R_LARCH_TLS_IE_PCADD_LO12 133 +#define R_LARCH_TLS_LD_PCADD_HI20 134 +#define R_LARCH_TLS_LD_PCADD_LO12 135 +#define R_LARCH_TLS_GD_PCADD_HI20 136 +#define R_LARCH_TLS_GD_PCADD_LO12 137 +#define R_LARCH_TLS_DESC_PCADD_HI20 138 +#define R_LARCH_TLS_DESC_PCADD_LO12 139 #ifndef ELF_ARCH @@ -156,6 +186,7 @@ typedef elf_greg_t elf_gregset_t[ELF_NGREG]; typedef double elf_fpreg_t; typedef elf_fpreg_t elf_fpregset_t[ELF_NFPREG]; +void loongarch_dump_regs32(u32 *uregs, const struct pt_regs *regs); void loongarch_dump_regs64(u64 *uregs, const struct pt_regs *regs); #ifdef CONFIG_32BIT diff --git a/arch/loongarch/include/asm/entry-common.h b/arch/loongarch/include/asm/entry-common.h index 0fe2a098ded9..099132980dc9 100644 --- a/arch/loongarch/include/asm/entry-common.h +++ b/arch/loongarch/include/asm/entry-common.h @@ -2,12 +2,6 @@ #ifndef ARCH_LOONGARCH_ENTRY_COMMON_H #define ARCH_LOONGARCH_ENTRY_COMMON_H -#include <linux/sched.h> -#include <linux/processor.h> - -static inline bool on_thread_stack(void) -{ - return !(((unsigned long)(current->stack) ^ current_stack_pointer) & ~(THREAD_SIZE - 1)); -} +#include <asm/stacktrace.h> /* For on_thread_stack() */ #endif diff --git a/arch/loongarch/include/asm/fixmap.h b/arch/loongarch/include/asm/fixmap.h index d2e55ae55bb9..dce2da6ba787 100644 --- a/arch/loongarch/include/asm/fixmap.h +++ b/arch/loongarch/include/asm/fixmap.h @@ -8,10 +8,19 @@ #ifndef _ASM_FIXMAP_H #define _ASM_FIXMAP_H +#ifdef CONFIG_HIGHMEM +#include <linux/threads.h> +#include <asm/kmap_size.h> +#endif + #define NR_FIX_BTMAPS 64 enum fixed_addresses { FIX_HOLE, +#ifdef CONFIG_HIGHMEM + FIX_KMAP_BEGIN, + FIX_KMAP_END = FIX_KMAP_BEGIN + (KM_MAX_IDX * NR_CPUS) - 1, +#endif FIX_EARLYCON_MEM_BASE, __end_of_fixed_addresses }; @@ -25,4 +34,9 @@ extern void __set_fixmap(enum fixed_addresses idx, #include <asm-generic/fixmap.h> +/* + * Called from pagetable_init() + */ +extern void fixrange_init(unsigned long start, unsigned long end, pgd_t *pgd_base); + #endif diff --git a/arch/loongarch/include/asm/fpu.h b/arch/loongarch/include/asm/fpu.h index 3177674228f8..45514f314664 100644 --- a/arch/loongarch/include/asm/fpu.h +++ b/arch/loongarch/include/asm/fpu.h @@ -22,22 +22,29 @@ struct sigcontext; #define kernel_fpu_available() cpu_has_fpu -extern void kernel_fpu_begin(void); -extern void kernel_fpu_end(void); - -extern void _init_fpu(unsigned int); -extern void _save_fp(struct loongarch_fpu *); -extern void _restore_fp(struct loongarch_fpu *); - -extern void _save_lsx(struct loongarch_fpu *fpu); -extern void _restore_lsx(struct loongarch_fpu *fpu); -extern void _init_lsx_upper(void); -extern void _restore_lsx_upper(struct loongarch_fpu *fpu); - -extern void _save_lasx(struct loongarch_fpu *fpu); -extern void _restore_lasx(struct loongarch_fpu *fpu); -extern void _init_lasx_upper(void); -extern void _restore_lasx_upper(struct loongarch_fpu *fpu); + +void kernel_fpu_begin(void); +void kernel_fpu_end(void); + +asmlinkage void _init_fpu(unsigned int); +asmlinkage void _save_fp(struct loongarch_fpu *); +asmlinkage void _restore_fp(struct loongarch_fpu *); +asmlinkage int _save_fp_context(void __user *fpregs, void __user *fcc, void __user *csr); +asmlinkage int _restore_fp_context(void __user *fpregs, void __user *fcc, void __user *csr); + +asmlinkage void _save_lsx(struct loongarch_fpu *fpu); +asmlinkage void _restore_lsx(struct loongarch_fpu *fpu); +asmlinkage void _init_lsx_upper(void); +asmlinkage void _restore_lsx_upper(struct loongarch_fpu *fpu); +asmlinkage int _save_lsx_context(void __user *fpregs, void __user *fcc, void __user *fcsr); +asmlinkage int _restore_lsx_context(void __user *fpregs, void __user *fcc, void __user *fcsr); + +asmlinkage void _save_lasx(struct loongarch_fpu *fpu); +asmlinkage void _restore_lasx(struct loongarch_fpu *fpu); +asmlinkage void _init_lasx_upper(void); +asmlinkage void _restore_lasx_upper(struct loongarch_fpu *fpu); +asmlinkage int _save_lasx_context(void __user *fpregs, void __user *fcc, void __user *fcsr); +asmlinkage int _restore_lasx_context(void __user *fpregs, void __user *fcc, void __user *fcsr); static inline void enable_lsx(void); static inline void disable_lsx(void); diff --git a/arch/loongarch/include/asm/ftrace.h b/arch/loongarch/include/asm/ftrace.h index 6e0a99763a9a..f4caaf764f9e 100644 --- a/arch/loongarch/include/asm/ftrace.h +++ b/arch/loongarch/include/asm/ftrace.h @@ -14,7 +14,7 @@ #define MCOUNT_INSN_SIZE 4 /* sizeof mcount call */ -#ifndef __ASSEMBLY__ +#ifndef __ASSEMBLER__ #ifndef CONFIG_DYNAMIC_FTRACE @@ -84,7 +84,7 @@ __arch_ftrace_set_direct_caller(struct pt_regs *regs, unsigned long addr) #endif -#endif /* __ASSEMBLY__ */ +#endif /* __ASSEMBLER__ */ #endif /* CONFIG_FUNCTION_TRACER */ diff --git a/arch/loongarch/include/asm/gpr-num.h b/arch/loongarch/include/asm/gpr-num.h index 996038da806d..af95b941f48b 100644 --- a/arch/loongarch/include/asm/gpr-num.h +++ b/arch/loongarch/include/asm/gpr-num.h @@ -2,7 +2,7 @@ #ifndef __ASM_GPR_NUM_H #define __ASM_GPR_NUM_H -#ifdef __ASSEMBLY__ +#ifdef __ASSEMBLER__ .equ .L__gpr_num_zero, 0 .irp num,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31 @@ -25,7 +25,7 @@ .equ .L__gpr_num_$s\num, 23 + \num .endr -#else /* __ASSEMBLY__ */ +#else /* __ASSEMBLER__ */ #define __DEFINE_ASM_GPR_NUMS \ " .equ .L__gpr_num_zero, 0\n" \ @@ -47,6 +47,6 @@ " .equ .L__gpr_num_$s\\num, 23 + \\num\n" \ " .endr\n" \ -#endif /* __ASSEMBLY__ */ +#endif /* __ASSEMBLER__ */ #endif /* __ASM_GPR_NUM_H */ diff --git a/arch/loongarch/include/asm/highmem.h b/arch/loongarch/include/asm/highmem.h new file mode 100644 index 000000000000..e6d7a662d340 --- /dev/null +++ b/arch/loongarch/include/asm/highmem.h @@ -0,0 +1,43 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * highmem.h: virtual kernel memory mappings for high memory + * + * Used in CONFIG_HIGHMEM systems for memory pages which + * are not addressable by direct kernel virtual addresses. + * + * Copyright (C) 2025 Loongson Technology Corporation Limited + */ +#ifndef _ASM_HIGHMEM_H +#define _ASM_HIGHMEM_H + +#ifdef __KERNEL__ + +#include <asm/kmap_size.h> + +#ifndef __ASSEMBLER__ + +extern pte_t *pkmap_page_table; + +#define ARCH_HAS_KMAP_FLUSH_TLB +void kmap_flush_tlb(unsigned long addr); + +#endif /* !__ASSEMBLER__ */ + +/* + * Right now we initialize only a single pte table. It can be extended + * easily, subsequent pte tables have to be allocated in one physical + * chunk of RAM. + */ +#define LAST_PKMAP 1024 +#define LAST_PKMAP_MASK (LAST_PKMAP - 1) +#define PKMAP_NR(virt) ((virt - PKMAP_BASE) >> PAGE_SHIFT) +#define PKMAP_ADDR(nr) (PKMAP_BASE + ((nr) << PAGE_SHIFT)) + +#define flush_cache_kmaps() do {} while (0) + +#define arch_kmap_local_post_map(vaddr, pteval) local_flush_tlb_one(vaddr) +#define arch_kmap_local_post_unmap(vaddr) local_flush_tlb_one(vaddr) + +#endif /* __KERNEL__ */ + +#endif /* _ASM_HIGHMEM_H */ diff --git a/arch/loongarch/include/asm/hugetlb.h b/arch/loongarch/include/asm/hugetlb.h index 4dc4b3e04225..ab68b594f889 100644 --- a/arch/loongarch/include/asm/hugetlb.h +++ b/arch/loongarch/include/asm/hugetlb.h @@ -10,20 +10,6 @@ uint64_t pmd_to_entrylo(unsigned long pmd_val); -#define __HAVE_ARCH_PREPARE_HUGEPAGE_RANGE -static inline int prepare_hugepage_range(struct file *file, - unsigned long addr, - unsigned long len) -{ - unsigned long task_size = STACK_TOP; - - if (len > task_size) - return -ENOMEM; - if (task_size - len < addr) - return -EINVAL; - return 0; -} - #define __HAVE_ARCH_HUGE_PTE_CLEAR static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned long sz) diff --git a/arch/loongarch/include/asm/hw_breakpoint.h b/arch/loongarch/include/asm/hw_breakpoint.h index 13b2462f3d8c..5faa97a87a9e 100644 --- a/arch/loongarch/include/asm/hw_breakpoint.h +++ b/arch/loongarch/include/asm/hw_breakpoint.h @@ -134,13 +134,13 @@ static inline void hw_breakpoint_thread_switch(struct task_struct *next) /* Determine number of BRP registers available. */ static inline int get_num_brps(void) { - return csr_read64(LOONGARCH_CSR_FWPC) & CSR_FWPC_NUM; + return csr_read32(LOONGARCH_CSR_FWPC) & CSR_FWPC_NUM; } /* Determine number of WRP registers available. */ static inline int get_num_wrps(void) { - return csr_read64(LOONGARCH_CSR_MWPC) & CSR_MWPC_NUM; + return csr_read32(LOONGARCH_CSR_MWPC) & CSR_MWPC_NUM; } #endif /* __KERNEL__ */ diff --git a/arch/loongarch/include/asm/image.h b/arch/loongarch/include/asm/image.h new file mode 100644 index 000000000000..cab981cdb72a --- /dev/null +++ b/arch/loongarch/include/asm/image.h @@ -0,0 +1,52 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * LoongArch binary image header for EFI(PE/COFF) format. + * + * Author: Youling Tang <tangyouling@kylinos.cn> + * Copyright (C) 2025 KylinSoft Corporation. + */ + +#ifndef __ASM_IMAGE_H +#define __ASM_IMAGE_H + +#ifndef __ASSEMBLER__ + +/** + * struct loongarch_image_header + * + * @dos_sig: Optional PE format 'MZ' signature. + * @padding_1: Reserved. + * @kernel_entry: Kernel image entry pointer. + * @kernel_asize: An estimated size of the memory image size in LSB byte order. + * @text_offset: The image load offset in LSB byte order. + * @padding_2: Reserved. + * @pe_header: Optional offset to a PE format header. + **/ + +struct loongarch_image_header { + uint8_t dos_sig[2]; + uint16_t padding_1[3]; + uint64_t kernel_entry; + uint64_t kernel_asize; + uint64_t text_offset; + uint32_t padding_2[7]; + uint32_t pe_header; +}; + +/* + * loongarch_header_check_dos_sig - Helper to check the header + * + * Returns true (non-zero) if 'MZ' signature is found. + */ + +static inline int loongarch_header_check_dos_sig(const struct loongarch_image_header *h) +{ + if (!h) + return 0; + + return (h->dos_sig[0] == 'M' && h->dos_sig[1] == 'Z'); +} + +#endif /* __ASSEMBLER__ */ + +#endif /* __ASM_IMAGE_H */ diff --git a/arch/loongarch/include/asm/inst.h b/arch/loongarch/include/asm/inst.h index 3089785ca97e..76b723590023 100644 --- a/arch/loongarch/include/asm/inst.h +++ b/arch/loongarch/include/asm/inst.h @@ -36,6 +36,7 @@ enum reg0i15_op { break_op = 0x54, + dbar_op = 0x70e4, }; enum reg0i26_op { @@ -77,6 +78,10 @@ enum reg2_op { iocsrwrh_op = 0x19205, iocsrwrw_op = 0x19206, iocsrwrd_op = 0x19207, + llacqw_op = 0xe15e0, + screlw_op = 0xe15e1, + llacqd_op = 0xe15e2, + screld_op = 0xe15e3, }; enum reg2i5_op { @@ -189,6 +194,11 @@ enum reg3_op { fldxd_op = 0x7068, fstxs_op = 0x7070, fstxd_op = 0x7078, + scq_op = 0x70ae, + amswapb_op = 0x70b8, + amswaph_op = 0x70b9, + amaddb_op = 0x70ba, + amaddh_op = 0x70bb, amswapw_op = 0x70c0, amswapd_op = 0x70c1, amaddw_op = 0x70c2, @@ -433,8 +443,10 @@ static inline bool is_branch_ins(union loongarch_instruction *ip) static inline bool is_ra_save_ins(union loongarch_instruction *ip) { - /* st.d $ra, $sp, offset */ - return ip->reg2i12_format.opcode == std_op && + const u32 opcode = IS_ENABLED(CONFIG_32BIT) ? stw_op : std_op; + + /* st.w / st.d $ra, $sp, offset */ + return ip->reg2i12_format.opcode == opcode && ip->reg2i12_format.rj == LOONGARCH_GPR_SP && ip->reg2i12_format.rd == LOONGARCH_GPR_RA && !is_imm12_negative(ip->reg2i12_format.immediate); @@ -442,8 +454,10 @@ static inline bool is_ra_save_ins(union loongarch_instruction *ip) static inline bool is_stack_alloc_ins(union loongarch_instruction *ip) { - /* addi.d $sp, $sp, -imm */ - return ip->reg2i12_format.opcode == addid_op && + const u32 opcode = IS_ENABLED(CONFIG_32BIT) ? addiw_op : addid_op; + + /* addi.w / addi.d $sp, $sp, -imm */ + return ip->reg2i12_format.opcode == opcode && ip->reg2i12_format.rj == LOONGARCH_GPR_SP && ip->reg2i12_format.rd == LOONGARCH_GPR_SP && is_imm12_negative(ip->reg2i12_format.immediate); @@ -497,6 +511,7 @@ void arch_simulate_insn(union loongarch_instruction insn, struct pt_regs *regs); int larch_insn_read(void *addr, u32 *insnp); int larch_insn_write(void *addr, u32 insn); int larch_insn_patch_text(void *addr, u32 insn); +int larch_insn_text_copy(void *dst, void *src, size_t len); u32 larch_insn_gen_nop(void); u32 larch_insn_gen_b(unsigned long pc, unsigned long dest); @@ -510,6 +525,8 @@ u32 larch_insn_gen_move(enum loongarch_gpr rd, enum loongarch_gpr rj); u32 larch_insn_gen_lu12iw(enum loongarch_gpr rd, int imm); 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_beq(enum loongarch_gpr rd, enum loongarch_gpr rj, int imm); +u32 larch_insn_gen_bne(enum loongarch_gpr rd, enum loongarch_gpr rj, int imm); u32 larch_insn_gen_jirl(enum loongarch_gpr rd, enum loongarch_gpr rj, int imm); static inline bool signed_imm_check(long val, unsigned int bit) @@ -531,6 +548,7 @@ static inline void emit_##NAME(union loongarch_instruction *insn, \ } DEF_EMIT_REG0I15_FORMAT(break, break_op) +DEF_EMIT_REG0I15_FORMAT(dbar, dbar_op) /* like emit_break(imm) but returns a constant expression */ #define __emit_break(imm) ((u32)((imm) | (break_op << 15))) @@ -751,6 +769,8 @@ 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(amaddb, amaddb_op) +DEF_EMIT_REG3_FORMAT(amaddh, amaddh_op) DEF_EMIT_REG3_FORMAT(amaddw, amaddw_op) DEF_EMIT_REG3_FORMAT(amaddd, amaddd_op) DEF_EMIT_REG3_FORMAT(amandw, amandw_op) @@ -759,6 +779,8 @@ 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(amswapb, amswapb_op) +DEF_EMIT_REG3_FORMAT(amswaph, amswaph_op) DEF_EMIT_REG3_FORMAT(amswapw, amswapw_op) DEF_EMIT_REG3_FORMAT(amswapd, amswapd_op) diff --git a/arch/loongarch/include/asm/io.h b/arch/loongarch/include/asm/io.h index e77a56eaf906..0130185e0349 100644 --- a/arch/loongarch/include/asm/io.h +++ b/arch/loongarch/include/asm/io.h @@ -14,7 +14,7 @@ #include <asm/pgtable-bits.h> #include <asm/string.h> -extern void __init __iomem *early_ioremap(u64 phys_addr, unsigned long size); +extern void __init __iomem *early_ioremap(phys_addr_t phys_addr, unsigned long size); extern void __init early_iounmap(void __iomem *addr, unsigned long size); #define early_memremap early_ioremap @@ -23,9 +23,12 @@ extern void __init early_iounmap(void __iomem *addr, unsigned long size); #ifdef CONFIG_ARCH_IOREMAP static inline void __iomem *ioremap_prot(phys_addr_t offset, unsigned long size, - unsigned long prot_val) + pgprot_t prot) { - switch (prot_val & _CACHE_MASK) { + if (offset > TO_PHYS_MASK) + return NULL; + + switch (pgprot_val(prot) & _CACHE_MASK) { case _CACHE_CC: return (void __iomem *)(unsigned long)(CACHE_BASE + offset); case _CACHE_SUC: @@ -38,7 +41,7 @@ static inline void __iomem *ioremap_prot(phys_addr_t offset, unsigned long size, } #define ioremap(offset, size) \ - ioremap_prot((offset), (size), pgprot_val(PAGE_KERNEL_SUC)) + ioremap_prot((offset), (size), PAGE_KERNEL_SUC) #define iounmap(addr) ((void)(addr)) @@ -55,10 +58,10 @@ static inline void __iomem *ioremap_prot(phys_addr_t offset, unsigned long size, */ #define ioremap_wc(offset, size) \ ioremap_prot((offset), (size), \ - pgprot_val(wc_enabled ? PAGE_KERNEL_WUC : PAGE_KERNEL_SUC)) + wc_enabled ? PAGE_KERNEL_WUC : PAGE_KERNEL_SUC) #define ioremap_cache(offset, size) \ - ioremap_prot((offset), (size), pgprot_val(PAGE_KERNEL)) + ioremap_prot((offset), (size), PAGE_KERNEL) #define mmiowb() wmb() diff --git a/arch/loongarch/include/asm/irq.h b/arch/loongarch/include/asm/irq.h index a0ca84da8541..537add26daf4 100644 --- a/arch/loongarch/include/asm/irq.h +++ b/arch/loongarch/include/asm/irq.h @@ -48,12 +48,23 @@ void spurious_interrupt(void); */ #define NR_VECTORS 256 #define NR_LEGACY_VECTORS 16 -#define IRQ_MATRIX_BITS NR_VECTORS + +#define AVEC_IRQ_SHIFT 4 +#define AVEC_IRQ_BIT 8 +#define AVEC_IRQ_MASK GENMASK(AVEC_IRQ_BIT - 1, 0) +#define AVEC_CPU_SHIFT 12 +#define AVEC_CPU_BIT 16 +#define AVEC_CPU_MASK GENMASK(AVEC_CPU_BIT - 1, 0) #define arch_trigger_cpumask_backtrace arch_trigger_cpumask_backtrace void arch_trigger_cpumask_backtrace(const struct cpumask *mask, int exclude_cpu); -#define MAX_IO_PICS 2 +#ifdef CONFIG_32BIT +#define MAX_IO_PICS 1 +#else +#define MAX_IO_PICS 8 +#endif + #define NR_IRQS (64 + NR_VECTORS * (NR_CPUS + MAX_IO_PICS)) struct acpi_vector_group { diff --git a/arch/loongarch/include/asm/irq_work.h b/arch/loongarch/include/asm/irq_work.h index d63076e9160d..63aee0335d1a 100644 --- a/arch/loongarch/include/asm/irq_work.h +++ b/arch/loongarch/include/asm/irq_work.h @@ -4,7 +4,7 @@ static inline bool arch_irq_work_has_interrupt(void) { - return IS_ENABLED(CONFIG_SMP); + return IS_ENABLED(CONFIG_SMP) && cpu_opt(LOONGARCH_CPU_CSRIPI); } #endif /* _ASM_LOONGARCH_IRQ_WORK_H */ diff --git a/arch/loongarch/include/asm/irqflags.h b/arch/loongarch/include/asm/irqflags.h index 319a8c616f1f..620163628a7f 100644 --- a/arch/loongarch/include/asm/irqflags.h +++ b/arch/loongarch/include/asm/irqflags.h @@ -5,7 +5,7 @@ #ifndef _ASM_IRQFLAGS_H #define _ASM_IRQFLAGS_H -#ifndef __ASSEMBLY__ +#ifndef __ASSEMBLER__ #include <linux/compiler.h> #include <linux/stringify.h> @@ -14,40 +14,48 @@ static inline void arch_local_irq_enable(void) { u32 flags = CSR_CRMD_IE; + register u32 mask asm("t0") = CSR_CRMD_IE; + __asm__ __volatile__( "csrxchg %[val], %[mask], %[reg]\n\t" : [val] "+r" (flags) - : [mask] "r" (CSR_CRMD_IE), [reg] "i" (LOONGARCH_CSR_CRMD) + : [mask] "r" (mask), [reg] "i" (LOONGARCH_CSR_CRMD) : "memory"); } static inline void arch_local_irq_disable(void) { u32 flags = 0; + register u32 mask asm("t0") = CSR_CRMD_IE; + __asm__ __volatile__( "csrxchg %[val], %[mask], %[reg]\n\t" : [val] "+r" (flags) - : [mask] "r" (CSR_CRMD_IE), [reg] "i" (LOONGARCH_CSR_CRMD) + : [mask] "r" (mask), [reg] "i" (LOONGARCH_CSR_CRMD) : "memory"); } static inline unsigned long arch_local_irq_save(void) { u32 flags = 0; + register u32 mask asm("t0") = CSR_CRMD_IE; + __asm__ __volatile__( "csrxchg %[val], %[mask], %[reg]\n\t" : [val] "+r" (flags) - : [mask] "r" (CSR_CRMD_IE), [reg] "i" (LOONGARCH_CSR_CRMD) + : [mask] "r" (mask), [reg] "i" (LOONGARCH_CSR_CRMD) : "memory"); return flags; } static inline void arch_local_irq_restore(unsigned long flags) { + register u32 mask asm("t0") = CSR_CRMD_IE; + __asm__ __volatile__( "csrxchg %[val], %[mask], %[reg]\n\t" : [val] "+r" (flags) - : [mask] "r" (CSR_CRMD_IE), [reg] "i" (LOONGARCH_CSR_CRMD) + : [mask] "r" (mask), [reg] "i" (LOONGARCH_CSR_CRMD) : "memory"); } @@ -72,6 +80,6 @@ static inline int arch_irqs_disabled(void) return arch_irqs_disabled_flags(arch_local_save_flags()); } -#endif /* #ifndef __ASSEMBLY__ */ +#endif /* #ifndef __ASSEMBLER__ */ #endif /* _ASM_IRQFLAGS_H */ diff --git a/arch/loongarch/include/asm/jump_label.h b/arch/loongarch/include/asm/jump_label.h index 8a924bd69d19..7ef4ae3abf08 100644 --- a/arch/loongarch/include/asm/jump_label.h +++ b/arch/loongarch/include/asm/jump_label.h @@ -7,18 +7,28 @@ #ifndef __ASM_JUMP_LABEL_H #define __ASM_JUMP_LABEL_H -#ifndef __ASSEMBLY__ +#ifndef __ASSEMBLER__ #include <linux/types.h> +#include <linux/stringify.h> +#include <asm/asm.h> + +#define HAVE_JUMP_LABEL_BATCH #define JUMP_LABEL_NOP_SIZE 4 +#ifdef CONFIG_32BIT +#define JUMP_LABEL_TYPE ".long " +#else +#define JUMP_LABEL_TYPE ".quad " +#endif + /* This macro is also expanded on the Rust side. */ #define JUMP_TABLE_ENTRY(key, label) \ ".pushsection __jump_table, \"aw\" \n\t" \ - ".align 3 \n\t" \ + ".align " __stringify(PTRLOG) " \n\t" \ ".long 1b - ., " label " - . \n\t" \ - ".quad " key " - . \n\t" \ + JUMP_LABEL_TYPE key " - . \n\t" \ ".popsection \n\t" #define ARCH_STATIC_BRANCH_ASM(key, label) \ @@ -50,5 +60,5 @@ l_yes: return true; } -#endif /* __ASSEMBLY__ */ +#endif /* __ASSEMBLER__ */ #endif /* __ASM_JUMP_LABEL_H */ diff --git a/arch/loongarch/include/asm/kasan.h b/arch/loongarch/include/asm/kasan.h index 7f52bd31b9d4..0e50e5b5e056 100644 --- a/arch/loongarch/include/asm/kasan.h +++ b/arch/loongarch/include/asm/kasan.h @@ -2,7 +2,7 @@ #ifndef __ASM_KASAN_H #define __ASM_KASAN_H -#ifndef __ASSEMBLY__ +#ifndef __ASSEMBLER__ #include <linux/linkage.h> #include <linux/mmzone.h> @@ -66,7 +66,6 @@ #define XKPRANGE_WC_SHADOW_OFFSET (KASAN_SHADOW_START + XKPRANGE_WC_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_mem_to_shadow kasan_mem_to_shadow @@ -75,12 +74,6 @@ void *kasan_mem_to_shadow(const void *addr); #define kasan_shadow_to_mem kasan_shadow_to_mem const void *kasan_shadow_to_mem(const void *shadow_addr); -#define kasan_arch_is_ready kasan_arch_is_ready -static __always_inline bool kasan_arch_is_ready(void) -{ - return !kasan_early_stage; -} - #define addr_has_metadata addr_has_metadata static __always_inline bool addr_has_metadata(const void *addr) { diff --git a/arch/loongarch/include/asm/kexec.h b/arch/loongarch/include/asm/kexec.h index cf95cd3eb2de..209fa43222e1 100644 --- a/arch/loongarch/include/asm/kexec.h +++ b/arch/loongarch/include/asm/kexec.h @@ -41,6 +41,18 @@ struct kimage_arch { unsigned long systable_ptr; }; +#ifdef CONFIG_KEXEC_FILE +extern const struct kexec_file_ops kexec_efi_ops; +extern const struct kexec_file_ops kexec_elf_ops; + +int arch_kimage_file_post_load_cleanup(struct kimage *image); +#define arch_kimage_file_post_load_cleanup arch_kimage_file_post_load_cleanup + +extern int load_other_segments(struct kimage *image, + unsigned long kernel_load_addr, unsigned long kernel_size, + char *initrd, unsigned long initrd_len, char *cmdline, unsigned long cmdline_len); +#endif + typedef void (*do_kexec_t)(unsigned long efi_boot, unsigned long cmdline_ptr, unsigned long systable_ptr, diff --git a/arch/loongarch/include/asm/kvm_dmsintc.h b/arch/loongarch/include/asm/kvm_dmsintc.h new file mode 100644 index 000000000000..5a71b9ccbe78 --- /dev/null +++ b/arch/loongarch/include/asm/kvm_dmsintc.h @@ -0,0 +1,27 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2025 Loongson Technology Corporation Limited + */ + +#ifndef __ASM_KVM_DMSINTC_H +#define __ASM_KVM_DMSINTC_H + +#include <linux/kvm_types.h> + +struct loongarch_dmsintc { + struct kvm *kvm; + uint64_t msg_addr_base; + uint64_t msg_addr_size; + uint32_t cpu_mask; +}; + +struct dmsintc_state { + atomic64_t vector_map[4]; +}; + +int kvm_loongarch_register_dmsintc_device(void); +void dmsintc_inject_irq(struct kvm_vcpu *vcpu); +int dmsintc_set_irq(struct kvm *kvm, u64 addr, int data, int level); +int dmsintc_deliver_msi_to_vcpu(struct kvm *kvm, struct kvm_vcpu *vcpu, u32 vector, int level); + +#endif diff --git a/arch/loongarch/include/asm/kvm_eiointc.h b/arch/loongarch/include/asm/kvm_eiointc.h index a3a40aba8acf..8b7a2fa3f7f8 100644 --- a/arch/loongarch/include/asm/kvm_eiointc.h +++ b/arch/loongarch/include/asm/kvm_eiointc.h @@ -10,10 +10,7 @@ #define EIOINTC_IRQS 256 #define EIOINTC_ROUTE_MAX_VCPUS 256 -#define EIOINTC_IRQS_U8_NUMS (EIOINTC_IRQS / 8) -#define EIOINTC_IRQS_U16_NUMS (EIOINTC_IRQS_U8_NUMS / 2) -#define EIOINTC_IRQS_U32_NUMS (EIOINTC_IRQS_U8_NUMS / 4) -#define EIOINTC_IRQS_U64_NUMS (EIOINTC_IRQS_U8_NUMS / 8) +#define EIOINTC_IRQS_U64_NUMS (EIOINTC_IRQS / 64) /* map to ipnum per 32 irqs */ #define EIOINTC_IRQS_NODETYPE_COUNT 16 @@ -64,54 +61,18 @@ struct loongarch_eiointc { uint32_t status; /* hardware state */ - union nodetype { - u64 reg_u64[EIOINTC_IRQS_NODETYPE_COUNT / 4]; - u32 reg_u32[EIOINTC_IRQS_NODETYPE_COUNT / 2]; - u16 reg_u16[EIOINTC_IRQS_NODETYPE_COUNT]; - u8 reg_u8[EIOINTC_IRQS_NODETYPE_COUNT * 2]; - } nodetype; + u64 nodetype[EIOINTC_IRQS_NODETYPE_COUNT / 4]; /* one bit shows the state of one irq */ - union bounce { - u64 reg_u64[EIOINTC_IRQS_U64_NUMS]; - u32 reg_u32[EIOINTC_IRQS_U32_NUMS]; - u16 reg_u16[EIOINTC_IRQS_U16_NUMS]; - u8 reg_u8[EIOINTC_IRQS_U8_NUMS]; - } bounce; - - union isr { - u64 reg_u64[EIOINTC_IRQS_U64_NUMS]; - u32 reg_u32[EIOINTC_IRQS_U32_NUMS]; - u16 reg_u16[EIOINTC_IRQS_U16_NUMS]; - u8 reg_u8[EIOINTC_IRQS_U8_NUMS]; - } isr; - union coreisr { - u64 reg_u64[EIOINTC_ROUTE_MAX_VCPUS][EIOINTC_IRQS_U64_NUMS]; - u32 reg_u32[EIOINTC_ROUTE_MAX_VCPUS][EIOINTC_IRQS_U32_NUMS]; - u16 reg_u16[EIOINTC_ROUTE_MAX_VCPUS][EIOINTC_IRQS_U16_NUMS]; - u8 reg_u8[EIOINTC_ROUTE_MAX_VCPUS][EIOINTC_IRQS_U8_NUMS]; - } coreisr; - union enable { - u64 reg_u64[EIOINTC_IRQS_U64_NUMS]; - u32 reg_u32[EIOINTC_IRQS_U32_NUMS]; - u16 reg_u16[EIOINTC_IRQS_U16_NUMS]; - u8 reg_u8[EIOINTC_IRQS_U8_NUMS]; - } enable; + u64 bounce[EIOINTC_IRQS_U64_NUMS]; + u64 isr[EIOINTC_IRQS_U64_NUMS]; + u64 coreisr[EIOINTC_ROUTE_MAX_VCPUS][EIOINTC_IRQS_U64_NUMS]; + u64 enable[EIOINTC_IRQS_U64_NUMS]; /* use one byte to config ipmap for 32 irqs at once */ - union ipmap { - u64 reg_u64; - u32 reg_u32[EIOINTC_IRQS_U32_NUMS / 4]; - u16 reg_u16[EIOINTC_IRQS_U16_NUMS / 4]; - u8 reg_u8[EIOINTC_IRQS_U8_NUMS / 4]; - } ipmap; + u64 ipmap; /* use one byte to config coremap for one irq */ - union coremap { - u64 reg_u64[EIOINTC_IRQS / 8]; - u32 reg_u32[EIOINTC_IRQS / 4]; - u16 reg_u16[EIOINTC_IRQS / 2]; - u8 reg_u8[EIOINTC_IRQS]; - } coremap; + u64 coremap[EIOINTC_IRQS / 8]; DECLARE_BITMAP(sw_coreisr[EIOINTC_ROUTE_MAX_VCPUS][LOONGSON_IP_NUM], EIOINTC_IRQS); uint8_t sw_coremap[EIOINTC_IRQS]; diff --git a/arch/loongarch/include/asm/kvm_host.h b/arch/loongarch/include/asm/kvm_host.h index 590982cd986e..776bc487a705 100644 --- a/arch/loongarch/include/asm/kvm_host.h +++ b/arch/loongarch/include/asm/kvm_host.h @@ -12,6 +12,7 @@ #include <linux/kvm.h> #include <linux/kvm_types.h> #include <linux/mutex.h> +#include <linux/perf_event.h> #include <linux/spinlock.h> #include <linux/threads.h> #include <linux/types.h> @@ -19,6 +20,7 @@ #include <asm/inst.h> #include <asm/kvm_mmu.h> #include <asm/kvm_ipi.h> +#include <asm/kvm_dmsintc.h> #include <asm/kvm_eiointc.h> #include <asm/kvm_pch_pic.h> #include <asm/loongarch.h> @@ -36,6 +38,7 @@ #define KVM_REQ_TLB_FLUSH_GPA KVM_ARCH_REQ(0) #define KVM_REQ_STEAL_UPDATE KVM_ARCH_REQ(1) #define KVM_REQ_PMU KVM_ARCH_REQ(2) +#define KVM_REQ_AUX_LOAD KVM_ARCH_REQ(3) #define KVM_GUESTDBG_SW_BP_MASK \ (KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_SW_BP) @@ -49,12 +52,6 @@ struct kvm_vm_stat { struct kvm_vm_stat_generic generic; u64 pages; u64 hugepages; - u64 ipi_read_exits; - u64 ipi_write_exits; - u64 eiointc_read_exits; - u64 eiointc_write_exits; - u64 pch_pic_read_exits; - u64 pch_pic_write_exits; }; struct kvm_vcpu_stat { @@ -64,6 +61,12 @@ struct kvm_vcpu_stat { u64 cpucfg_exits; u64 signal_exits; u64 hypercall_exits; + u64 ipi_read_exits; + u64 ipi_write_exits; + u64 eiointc_read_exits; + u64 eiointc_write_exits; + u64 pch_pic_read_exits; + u64 pch_pic_write_exits; }; #define KVM_MEM_HUGEPAGE_CAPABLE (1UL << 0) @@ -84,7 +87,6 @@ struct kvm_context { struct kvm_world_switch { int (*exc_entry)(void); int (*enter_guest)(struct kvm_run *run, struct kvm_vcpu *vcpu); - unsigned long page_order; }; #define MAX_PGTABLE_LEVELS 4 @@ -125,10 +127,13 @@ struct kvm_arch { struct kvm_phyid_map *phyid_map; /* Enabled PV features */ unsigned long pv_features; + /* Supported KVM features */ + unsigned long kvm_features; s64 time_offset; struct kvm_context __percpu *vmcs; struct loongarch_ipi *ipi; + struct loongarch_dmsintc *dmsintc; struct loongarch_eiointc *eiointc; struct loongarch_pch_pic *pch_pic; }; @@ -161,6 +166,7 @@ enum emulation_result { #define LOONGARCH_PV_FEAT_UPDATED BIT_ULL(63) #define LOONGARCH_PV_FEAT_MASK (BIT(KVM_FEATURE_IPI) | \ + BIT(KVM_FEATURE_PREEMPT) | \ BIT(KVM_FEATURE_STEAL_TIME) | \ BIT(KVM_FEATURE_USER_HCALL) | \ BIT(KVM_FEATURE_VIRT_EXTIOI)) @@ -176,6 +182,9 @@ struct kvm_vcpu_arch { /* Pointers stored here for easy accessing from assembly code */ int (*handle_exit)(struct kvm_run *run, struct kvm_vcpu *vcpu); + /* GPA (=HVA) of PGD for secondary mmu */ + unsigned long kvm_pgd; + /* Host registers preserved across guest mode execution */ unsigned long host_sp; unsigned long host_tp; @@ -194,6 +203,7 @@ struct kvm_vcpu_arch { /* Which auxiliary state is loaded (KVM_LARCH_*) */ unsigned int aux_inuse; + unsigned int aux_ldtype; /* FPU state */ struct loongarch_fpu fpu FPU_ALIGN; @@ -238,6 +248,7 @@ struct kvm_vcpu_arch { struct kvm_mp_state mp_state; /* ipi state */ struct ipi_state ipi_state; + struct dmsintc_state dmsintc_state; /* cpucfg */ u32 cpucfg[KVM_MAX_CPUCFG_REGS]; @@ -246,6 +257,7 @@ struct kvm_vcpu_arch { u64 guest_addr; u64 last_steal; struct gfn_to_hva_cache cache; + u8 preempted; } st; }; @@ -259,6 +271,11 @@ static inline void writel_sw_gcsr(struct loongarch_csrs *csr, int reg, unsigned csr->csrs[reg] = val; } +static inline bool kvm_guest_has_msgint(struct kvm_vcpu_arch *arch) +{ + return arch->cpucfg[1] & CPUCFG1_MSGINT; +} + static inline bool kvm_guest_has_fpu(struct kvm_vcpu_arch *arch) { return arch->cpucfg[2] & CPUCFG2_FP; @@ -289,13 +306,21 @@ static inline int kvm_get_pmu_num(struct kvm_vcpu_arch *arch) return (arch->cpucfg[6] & CPUCFG6_PMNUM) >> CPUCFG6_PMNUM_SHIFT; } +/* Check whether KVM support this feature (VMM may disable it) */ +static inline bool kvm_vm_support(struct kvm_arch *arch, int feature) +{ + return !!(arch->kvm_features & BIT_ULL(feature)); +} + +bool kvm_arch_pmi_in_guest(struct kvm_vcpu *vcpu); + /* Debug: dump vcpu state */ int kvm_arch_vcpu_dump_regs(struct kvm_vcpu *vcpu); /* MMU handling */ void kvm_flush_tlb_all(void); void kvm_flush_tlb_gpa(struct kvm_vcpu *vcpu, unsigned long gpa); -int kvm_handle_mm_fault(struct kvm_vcpu *vcpu, unsigned long badv, bool write); +int kvm_handle_mm_fault(struct kvm_vcpu *vcpu, unsigned long badv, bool write, int ecode); int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end, bool blockable); int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end); @@ -320,7 +345,6 @@ static inline bool kvm_is_ifetch_fault(struct kvm_vcpu_arch *arch) /* Misc */ static inline void kvm_arch_hardware_unsetup(void) {} -static inline void kvm_arch_sync_events(struct kvm *kvm) {} static inline void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) {} static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) {} static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) {} @@ -334,8 +358,6 @@ void kvm_exc_entry(void); int kvm_enter_guest(struct kvm_run *run, struct kvm_vcpu *vcpu); extern unsigned long vpid_mask; -extern const unsigned long kvm_exception_size; -extern const unsigned long kvm_enter_guest_size; extern struct kvm_world_switch *kvm_loongarch_ops; #define SW_GCSR (1 << 0) diff --git a/arch/loongarch/include/asm/kvm_mmu.h b/arch/loongarch/include/asm/kvm_mmu.h index 099bafc6f797..e36cc7e8ed20 100644 --- a/arch/loongarch/include/asm/kvm_mmu.h +++ b/arch/loongarch/include/asm/kvm_mmu.h @@ -16,6 +16,13 @@ */ #define KVM_MMU_CACHE_MIN_PAGES (CONFIG_PGTABLE_LEVELS - 1) +/* + * _PAGE_MODIFIED is a SW pte bit, it records page ever written on host + * kernel, on secondary MMU it records the page writeable attribute, in + * order for fast path handling. + */ +#define KVM_PAGE_WRITEABLE _PAGE_MODIFIED + #define _KVM_FLUSH_PGTABLE 0x1 #define _KVM_HAS_PGMASK 0x2 #define kvm_pfn_pte(pfn, prot) (((pfn) << PFN_PTE_SHIFT) | pgprot_val(prot)) @@ -52,10 +59,10 @@ static inline void kvm_set_pte(kvm_pte_t *ptep, kvm_pte_t val) WRITE_ONCE(*ptep, val); } -static inline int kvm_pte_write(kvm_pte_t pte) { return pte & _PAGE_WRITE; } -static inline int kvm_pte_dirty(kvm_pte_t pte) { return pte & _PAGE_DIRTY; } static inline int kvm_pte_young(kvm_pte_t pte) { return pte & _PAGE_ACCESSED; } static inline int kvm_pte_huge(kvm_pte_t pte) { return pte & _PAGE_HUGE; } +static inline int kvm_pte_dirty(kvm_pte_t pte) { return pte & __WRITEABLE; } +static inline int kvm_pte_writeable(kvm_pte_t pte) { return pte & KVM_PAGE_WRITEABLE; } static inline kvm_pte_t kvm_pte_mkyoung(kvm_pte_t pte) { @@ -69,12 +76,12 @@ static inline kvm_pte_t kvm_pte_mkold(kvm_pte_t pte) static inline kvm_pte_t kvm_pte_mkdirty(kvm_pte_t pte) { - return pte | _PAGE_DIRTY; + return pte | __WRITEABLE; } static inline kvm_pte_t kvm_pte_mkclean(kvm_pte_t pte) { - return pte & ~_PAGE_DIRTY; + return pte & ~__WRITEABLE; } static inline kvm_pte_t kvm_pte_mkhuge(kvm_pte_t pte) @@ -87,6 +94,11 @@ static inline kvm_pte_t kvm_pte_mksmall(kvm_pte_t pte) return pte & ~_PAGE_HUGE; } +static inline kvm_pte_t kvm_pte_mkwriteable(kvm_pte_t pte) +{ + return pte | KVM_PAGE_WRITEABLE; +} + static inline int kvm_need_flush(kvm_ptw_ctx *ctx) { return ctx->flag & _KVM_FLUSH_PGTABLE; diff --git a/arch/loongarch/include/asm/kvm_para.h b/arch/loongarch/include/asm/kvm_para.h index 3e4b397f423f..fb17ba0fa101 100644 --- a/arch/loongarch/include/asm/kvm_para.h +++ b/arch/loongarch/include/asm/kvm_para.h @@ -37,8 +37,10 @@ struct kvm_steal_time { __u64 steal; __u32 version; __u32 flags; - __u32 pad[12]; + __u8 preempted; + __u8 pad[47]; }; +#define KVM_VCPU_PREEMPTED (1 << 0) /* * Hypercall interface for KVM hypervisor diff --git a/arch/loongarch/include/asm/kvm_pch_pic.h b/arch/loongarch/include/asm/kvm_pch_pic.h index e6df6a4c1c70..e74b3b742634 100644 --- a/arch/loongarch/include/asm/kvm_pch_pic.h +++ b/arch/loongarch/include/asm/kvm_pch_pic.h @@ -34,13 +34,26 @@ #define PCH_PIC_INT_ISR_END 0x3af #define PCH_PIC_POLARITY_START 0x3e0 #define PCH_PIC_POLARITY_END 0x3e7 -#define PCH_PIC_INT_ID_VAL 0x7000000UL +#define PCH_PIC_INT_ID_VAL 0x7UL #define PCH_PIC_INT_ID_VER 0x1UL +union pch_pic_id { + struct { + uint8_t reserved_0[3]; + uint8_t id; + uint8_t version; + uint8_t reserved_1; + uint8_t irq_num; + uint8_t reserved_2; + } desc; + uint64_t data; +}; + struct loongarch_pch_pic { spinlock_t lock; struct kvm *kvm; struct kvm_io_device device; + union pch_pic_id id; uint64_t mask; /* 1:disable irq, 0:enable irq */ uint64_t htmsi_en; /* 1:msi */ uint64_t edge; /* 1:edge triggered, 0:level triggered */ @@ -55,8 +68,9 @@ struct loongarch_pch_pic { uint64_t pch_pic_base; }; +struct kvm_kernel_irq_routing_entry; int kvm_loongarch_register_pch_pic_device(void); void pch_pic_set_irq(struct loongarch_pch_pic *s, int irq, int level); -void pch_msi_set_irq(struct kvm *kvm, int irq, int level); +int pch_msi_set_irq(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e, int level); #endif /* __ASM_KVM_PCH_PIC_H */ diff --git a/arch/loongarch/include/asm/kvm_vcpu.h b/arch/loongarch/include/asm/kvm_vcpu.h index 2c349f961bfb..3784ab4ccdb5 100644 --- a/arch/loongarch/include/asm/kvm_vcpu.h +++ b/arch/loongarch/include/asm/kvm_vcpu.h @@ -15,6 +15,7 @@ #define CPU_PMU (_ULCAST_(1) << 10) #define CPU_TIMER (_ULCAST_(1) << 11) #define CPU_IPI (_ULCAST_(1) << 12) +#define CPU_AVEC (_ULCAST_(1) << 14) /* Controlled by 0x52 guest exception VIP aligned to estat bit 5~12 */ #define CPU_IP0 (_ULCAST_(1)) @@ -37,7 +38,7 @@ #define KVM_LOONGSON_IRQ_NUM_MASK 0xffff typedef union loongarch_instruction larch_inst; -typedef int (*exit_handle_fn)(struct kvm_vcpu *); +typedef int (*exit_handle_fn)(struct kvm_vcpu *, int); int kvm_emu_mmio_read(struct kvm_vcpu *vcpu, larch_inst inst); int kvm_emu_mmio_write(struct kvm_vcpu *vcpu, larch_inst inst); diff --git a/arch/loongarch/include/asm/lbt.h b/arch/loongarch/include/asm/lbt.h index e671978bf552..38566574e562 100644 --- a/arch/loongarch/include/asm/lbt.h +++ b/arch/loongarch/include/asm/lbt.h @@ -12,9 +12,13 @@ #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 *); +asmlinkage void _init_lbt(void); +asmlinkage void _save_lbt(struct loongarch_lbt *); +asmlinkage void _restore_lbt(struct loongarch_lbt *); +asmlinkage int _save_lbt_context(void __user *regs, void __user *eflags); +asmlinkage int _restore_lbt_context(void __user *regs, void __user *eflags); +asmlinkage int _save_ftop_context(void __user *ftop); +asmlinkage int _restore_ftop_context(void __user *ftop); static inline int is_lbt_enabled(void) { diff --git a/arch/loongarch/include/asm/linkage.h b/arch/loongarch/include/asm/linkage.h index e2eca1a25b4e..ae937d1708b2 100644 --- a/arch/loongarch/include/asm/linkage.h +++ b/arch/loongarch/include/asm/linkage.h @@ -41,4 +41,40 @@ .cfi_endproc; \ SYM_END(name, SYM_T_NONE) +/* + * This is for the signal handler trampoline, which is used as the return + * address of the signal handlers in userspace instead of called normally. + * The long standing libgcc bug https://gcc.gnu.org/PR124050 requires a + * nop between .cfi_startproc and the actual address of the trampoline, so + * we cannot simply use SYM_FUNC_START. + * + * This wrapper also contains all the .cfi_* directives for recovering + * the content of the GPRs and the "return address" (where the rt_sigreturn + * syscall will jump to), assuming there is a struct rt_sigframe (where + * a struct sigcontext containing those information we need to recover) at + * $sp. The "DWARF for the LoongArch(TM) Architecture" manual states + * column 0 is for $zero, but it does not make too much sense to + * save/restore the hardware zero register. Repurpose this column here + * for the return address (here it's not the content of $ra we cannot use + * the default column 3). + */ +#define SYM_SIGFUNC_START(name) \ + .cfi_startproc; \ + .cfi_signal_frame; \ + .cfi_def_cfa 3, RT_SIGFRAME_SC; \ + .cfi_return_column 0; \ + .cfi_offset 0, SC_PC; \ + \ + .irp num, 1, 2, 3, 4, 5, 6, 7, 8, \ + 9, 10, 11, 12, 13, 14, 15, 16, \ + 17, 18, 19, 20, 21, 22, 23, 24, \ + 25, 26, 27, 28, 29, 30, 31; \ + .cfi_offset \num, SC_REGS + \num * 8; \ + .endr; \ + \ + nop; \ + SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN) + +#define SYM_SIGFUNC_END(name) SYM_FUNC_END(name) + #endif diff --git a/arch/loongarch/include/asm/local.h b/arch/loongarch/include/asm/local.h index f53ea653af76..2d118b1a060e 100644 --- a/arch/loongarch/include/asm/local.h +++ b/arch/loongarch/include/asm/local.h @@ -8,6 +8,7 @@ #include <linux/percpu.h> #include <linux/bitops.h> #include <linux/atomic.h> +#include <asm/asm.h> #include <asm/cmpxchg.h> typedef struct { @@ -27,6 +28,7 @@ typedef struct { /* * Same as above, but return the result value */ +#ifdef CONFIG_CPU_HAS_AMO static inline long local_add_return(long i, local_t *l) { unsigned long result; @@ -55,6 +57,41 @@ static inline long local_sub_return(long i, local_t *l) return result; } +#else +static inline long local_add_return(long i, local_t *l) +{ + unsigned long result, temp; + + __asm__ __volatile__( + "1:" __LL "%1, %2 # local_add_return \n" + __stringify(LONG_ADD) " %0, %1, %3 \n" + __SC "%0, %2 \n" + " beq %0, $r0, 1b \n" + __stringify(LONG_ADD) " %0, %1, %3 \n" + : "=&r" (result), "=&r" (temp), "=ZC" (l->a.counter) + : "r" (i), "ZC" (l->a.counter) + : "memory"); + + return result; +} + +static inline long local_sub_return(long i, local_t *l) +{ + unsigned long result, temp; + + __asm__ __volatile__( + "1:" __LL "%1, %2 # local_sub_return \n" + __stringify(LONG_SUB) " %0, %1, %3 \n" + __SC "%0, %2 \n" + " beq %0, $r0, 1b \n" + __stringify(LONG_SUB) " %0, %1, %3 \n" + : "=&r" (result), "=&r" (temp), "=ZC" (l->a.counter) + : "r" (i), "ZC" (l->a.counter) + : "memory"); + + return result; +} +#endif static inline long local_cmpxchg(local_t *l, long old, long new) { diff --git a/arch/loongarch/include/asm/loongarch.h b/arch/loongarch/include/asm/loongarch.h index 52651aa0e583..2a6bc99177d8 100644 --- a/arch/loongarch/include/asm/loongarch.h +++ b/arch/loongarch/include/asm/loongarch.h @@ -9,15 +9,15 @@ #include <linux/linkage.h> #include <linux/types.h> -#ifndef __ASSEMBLY__ +#ifndef __ASSEMBLER__ #include <larchintrin.h> /* CPUCFG */ #define read_cpucfg(reg) __cpucfg(reg) -#endif /* !__ASSEMBLY__ */ +#endif /* !__ASSEMBLER__ */ -#ifdef __ASSEMBLY__ +#ifdef __ASSEMBLER__ /* LoongArch Registers */ #define REG_ZERO 0x0 @@ -53,7 +53,7 @@ #define REG_S7 0x1e #define REG_S8 0x1f -#endif /* __ASSEMBLY__ */ +#endif /* __ASSEMBLER__ */ /* Bit fields for CPUCFG registers */ #define LOONGARCH_CPUCFG0 0x0 @@ -94,6 +94,12 @@ #define CPUCFG2_LSPW BIT(21) #define CPUCFG2_LAM BIT(22) #define CPUCFG2_PTW BIT(24) +#define CPUCFG2_FRECIPE BIT(25) +#define CPUCFG2_DIV32 BIT(26) +#define CPUCFG2_LAM_BH BIT(27) +#define CPUCFG2_LAMCAS BIT(28) +#define CPUCFG2_LLACQ_SCREL BIT(29) +#define CPUCFG2_SCQ BIT(30) #define LOONGARCH_CPUCFG3 0x3 #define CPUCFG3_CCDMA BIT(0) @@ -108,6 +114,7 @@ #define CPUCFG3_SPW_HG_HF BIT(11) #define CPUCFG3_RVA BIT(12) #define CPUCFG3_RVAMAX GENMASK(16, 13) +#define CPUCFG3_DBAR_HINTS BIT(17) #define CPUCFG3_ALDORDER_CAP BIT(18) /* All address load ordered, capability */ #define CPUCFG3_ASTORDER_CAP BIT(19) /* All address store ordered, capability */ #define CPUCFG3_ALDORDER_STA BIT(20) /* All address load ordered, status */ @@ -128,6 +135,7 @@ #define CPUCFG6_PMNUM GENMASK(7, 4) #define CPUCFG6_PMNUM_SHIFT 4 #define CPUCFG6_PMBITS GENMASK(13, 8) +#define CPUCFG6_PMBITS_SHIFT 8 #define CPUCFG6_UPM BIT(14) #define LOONGARCH_CPUCFG16 0x10 @@ -171,7 +179,7 @@ * SW emulation for KVM hypervirsor, see arch/loongarch/include/uapi/asm/kvm_para.h */ -#ifndef __ASSEMBLY__ +#ifndef __ASSEMBLER__ /* CSR */ #define csr_read32(reg) __csrrd_w(reg) @@ -181,13 +189,23 @@ #define csr_xchg32(val, mask, reg) __csrxchg_w(val, mask, reg) #define csr_xchg64(val, mask, reg) __csrxchg_d(val, mask, reg) +#ifdef CONFIG_32BIT +#define csr_read(reg) csr_read32(reg) +#define csr_write(val, reg) csr_write32(val, reg) +#define csr_xchg(val, mask, reg) csr_xchg32(val, mask, reg) +#else +#define csr_read(reg) csr_read64(reg) +#define csr_write(val, reg) csr_write64(val, reg) +#define csr_xchg(val, mask, reg) csr_xchg64(val, mask, reg) +#endif + /* IOCSR */ #define iocsr_read32(reg) __iocsrrd_w(reg) #define iocsr_read64(reg) __iocsrrd_d(reg) #define iocsr_write32(val, reg) __iocsrwr_w(val, reg) #define iocsr_write64(val, reg) __iocsrwr_d(val, reg) -#endif /* !__ASSEMBLY__ */ +#endif /* !__ASSEMBLER__ */ /* CSR register number */ @@ -411,8 +429,8 @@ /* Config CSR registers */ #define LOONGARCH_CSR_CPUID 0x20 /* CPU core id */ -#define CSR_CPUID_COREID_WIDTH 9 -#define CSR_CPUID_COREID _ULCAST_(0x1ff) +#define CSR_CPUID_COREID_WIDTH 11 +#define CSR_CPUID_COREID _ULCAST_(0x7ff) #define LOONGARCH_CSR_PRCFG1 0x21 /* Config1 */ #define CSR_CONF1_VSMAX_SHIFT 12 @@ -451,6 +469,13 @@ #define LOONGARCH_CSR_KS6 0x36 #define LOONGARCH_CSR_KS7 0x37 #define LOONGARCH_CSR_KS8 0x38 +#define LOONGARCH_CSR_KS9 0x39 +#define LOONGARCH_CSR_KS10 0x3a +#define LOONGARCH_CSR_KS11 0x3b +#define LOONGARCH_CSR_KS12 0x3c +#define LOONGARCH_CSR_KS13 0x3d +#define LOONGARCH_CSR_KS14 0x3e +#define LOONGARCH_CSR_KS15 0x3f /* Exception allocated KS0, KS1 and KS2 statically */ #define EXCEPTION_KS0 LOONGARCH_CSR_KS0 @@ -503,6 +528,8 @@ #define CSR_GCFG_GPERF_SHIFT 24 #define CSR_GCFG_GPERF_WIDTH 3 #define CSR_GCFG_GPERF (_ULCAST_(0x7) << CSR_GCFG_GPERF_SHIFT) +#define CSR_GCFG_GPMP_SHIFT 23 +#define CSR_GCFG_GPMP (_ULCAST_(0x1) << CSR_GCFG_GPMP_SHIFT) #define CSR_GCFG_GCI_SHIFT 20 #define CSR_GCFG_GCI_WIDTH 2 #define CSR_GCFG_GCI (_ULCAST_(0x3) << CSR_GCFG_GCI_SHIFT) @@ -663,6 +690,7 @@ #define LOONGARCH_CSR_ISR3 0xa3 #define LOONGARCH_CSR_IRR 0xa4 +#define LOONGARCH_CSR_IPR 0xa5 #define LOONGARCH_CSR_PRID 0xc0 @@ -894,6 +922,26 @@ #define LOONGARCH_CSR_DMWIN3 0x183 /* 64 direct map win3: MEM */ /* Direct Map window 0/1/2/3 */ + +#ifdef CONFIG_32BIT + +#define CSR_DMW0_PLV0 (1 << 0) +#define CSR_DMW0_VSEG (0x4) +#define CSR_DMW0_BASE (CSR_DMW0_VSEG << DMW_PABITS) +#define CSR_DMW0_INIT (CSR_DMW0_BASE | CSR_DMW0_PLV0) + +#define CSR_DMW1_PLV0 (1 << 0) +#define CSR_DMW1_MAT (1 << 4) +#define CSR_DMW1_VSEG (0x5) +#define CSR_DMW1_BASE (CSR_DMW1_VSEG << DMW_PABITS) +#define CSR_DMW1_INIT (CSR_DMW1_BASE | CSR_DMW1_MAT | CSR_DMW1_PLV0) + +#define CSR_DMW2_INIT 0x0 + +#define CSR_DMW3_INIT 0x0 + +#else + #define CSR_DMW0_PLV0 _CONST64_(1 << 0) #define CSR_DMW0_VSEG _CONST64_(0x8000) #define CSR_DMW0_BASE (CSR_DMW0_VSEG << DMW_PABITS) @@ -913,6 +961,8 @@ #define CSR_DMW3_INIT 0x0 +#endif + /* Performance Counter registers */ #define LOONGARCH_CSR_PERFCTRL0 0x200 /* 32 perf event 0 config */ #define LOONGARCH_CSR_PERFCNTR0 0x201 /* 64 perf event 0 count value */ @@ -1130,6 +1180,7 @@ #define IOCSRF_FLATMODE BIT_ULL(10) #define IOCSRF_VM BIT_ULL(11) #define IOCSRF_AVEC BIT_ULL(15) +#define IOCSRF_REDIRECT BIT_ULL(16) #define LOONGARCH_IOCSR_VENDOR 0x10 @@ -1195,9 +1246,37 @@ #define LOONGARCH_IOCSR_EXTIOI_ROUTE_BASE 0x1c00 #define IOCSR_EXTIOI_VECTOR_NUM 256 -#ifndef __ASSEMBLY__ +#ifndef __ASSEMBLER__ + +#ifdef CONFIG_32BIT -static __always_inline u64 drdtime(void) +static __always_inline u32 rdtime_h(void) +{ + u32 val = 0; + + __asm__ __volatile__( + "rdtimeh.w %0, $zero\n\t" + : "=r"(val) + : + ); + return val; +} + +static __always_inline u32 rdtime_l(void) +{ + u32 val = 0; + + __asm__ __volatile__( + "rdtimel.w %0, $zero\n\t" + : "=r"(val) + : + ); + return val; +} + +#else + +static __always_inline u64 rdtime_d(void) { u64 val = 0; @@ -1209,11 +1288,14 @@ static __always_inline u64 drdtime(void) return val; } +#endif + static inline unsigned int get_csr_cpuid(void) { return csr_read32(LOONGARCH_CSR_CPUID); } +#ifdef CONFIG_64BIT static inline void csr_any_send(unsigned int addr, unsigned int data, unsigned int data_mask, unsigned int cpu) { @@ -1225,6 +1307,7 @@ static inline void csr_any_send(unsigned int addr, unsigned int data, val |= ((uint64_t)data << IOCSR_ANY_SEND_BUF_SHIFT); iocsr_write64(val, LOONGARCH_IOCSR_ANY_SEND); } +#endif static inline unsigned int read_csr_excode(void) { @@ -1248,22 +1331,22 @@ static inline void write_csr_pagesize(unsigned int size) static inline unsigned int read_csr_tlbrefill_pagesize(void) { - return (csr_read64(LOONGARCH_CSR_TLBREHI) & CSR_TLBREHI_PS) >> CSR_TLBREHI_PS_SHIFT; + return (csr_read(LOONGARCH_CSR_TLBREHI) & CSR_TLBREHI_PS) >> CSR_TLBREHI_PS_SHIFT; } static inline void write_csr_tlbrefill_pagesize(unsigned int size) { - csr_xchg64(size << CSR_TLBREHI_PS_SHIFT, CSR_TLBREHI_PS, LOONGARCH_CSR_TLBREHI); + csr_xchg(size << CSR_TLBREHI_PS_SHIFT, CSR_TLBREHI_PS, LOONGARCH_CSR_TLBREHI); } #define read_csr_asid() csr_read32(LOONGARCH_CSR_ASID) #define write_csr_asid(val) csr_write32(val, LOONGARCH_CSR_ASID) -#define read_csr_entryhi() csr_read64(LOONGARCH_CSR_TLBEHI) -#define write_csr_entryhi(val) csr_write64(val, LOONGARCH_CSR_TLBEHI) -#define read_csr_entrylo0() csr_read64(LOONGARCH_CSR_TLBELO0) -#define write_csr_entrylo0(val) csr_write64(val, LOONGARCH_CSR_TLBELO0) -#define read_csr_entrylo1() csr_read64(LOONGARCH_CSR_TLBELO1) -#define write_csr_entrylo1(val) csr_write64(val, LOONGARCH_CSR_TLBELO1) +#define read_csr_entryhi() csr_read(LOONGARCH_CSR_TLBEHI) +#define write_csr_entryhi(val) csr_write(val, LOONGARCH_CSR_TLBEHI) +#define read_csr_entrylo0() csr_read(LOONGARCH_CSR_TLBELO0) +#define write_csr_entrylo0(val) csr_write(val, LOONGARCH_CSR_TLBELO0) +#define read_csr_entrylo1() csr_read(LOONGARCH_CSR_TLBELO1) +#define write_csr_entrylo1(val) csr_write(val, LOONGARCH_CSR_TLBELO1) #define read_csr_ecfg() csr_read32(LOONGARCH_CSR_ECFG) #define write_csr_ecfg(val) csr_write32(val, LOONGARCH_CSR_ECFG) #define read_csr_estat() csr_read32(LOONGARCH_CSR_ESTAT) @@ -1273,20 +1356,20 @@ static inline void write_csr_tlbrefill_pagesize(unsigned int size) #define read_csr_euen() csr_read32(LOONGARCH_CSR_EUEN) #define write_csr_euen(val) csr_write32(val, LOONGARCH_CSR_EUEN) #define read_csr_cpuid() csr_read32(LOONGARCH_CSR_CPUID) -#define read_csr_prcfg1() csr_read64(LOONGARCH_CSR_PRCFG1) -#define write_csr_prcfg1(val) csr_write64(val, LOONGARCH_CSR_PRCFG1) -#define read_csr_prcfg2() csr_read64(LOONGARCH_CSR_PRCFG2) -#define write_csr_prcfg2(val) csr_write64(val, LOONGARCH_CSR_PRCFG2) -#define read_csr_prcfg3() csr_read64(LOONGARCH_CSR_PRCFG3) -#define write_csr_prcfg3(val) csr_write64(val, LOONGARCH_CSR_PRCFG3) +#define read_csr_prcfg1() csr_read(LOONGARCH_CSR_PRCFG1) +#define write_csr_prcfg1(val) csr_write(val, LOONGARCH_CSR_PRCFG1) +#define read_csr_prcfg2() csr_read(LOONGARCH_CSR_PRCFG2) +#define write_csr_prcfg2(val) csr_write(val, LOONGARCH_CSR_PRCFG2) +#define read_csr_prcfg3() csr_read(LOONGARCH_CSR_PRCFG3) +#define write_csr_prcfg3(val) csr_write(val, LOONGARCH_CSR_PRCFG3) #define read_csr_stlbpgsize() csr_read32(LOONGARCH_CSR_STLBPGSIZE) #define write_csr_stlbpgsize(val) csr_write32(val, LOONGARCH_CSR_STLBPGSIZE) #define read_csr_rvacfg() csr_read32(LOONGARCH_CSR_RVACFG) #define write_csr_rvacfg(val) csr_write32(val, LOONGARCH_CSR_RVACFG) #define write_csr_tintclear(val) csr_write32(val, LOONGARCH_CSR_TINTCLR) -#define read_csr_impctl1() csr_read64(LOONGARCH_CSR_IMPCTL1) -#define write_csr_impctl1(val) csr_write64(val, LOONGARCH_CSR_IMPCTL1) -#define write_csr_impctl2(val) csr_write64(val, LOONGARCH_CSR_IMPCTL2) +#define read_csr_impctl1() csr_read(LOONGARCH_CSR_IMPCTL1) +#define write_csr_impctl1(val) csr_write(val, LOONGARCH_CSR_IMPCTL1) +#define write_csr_impctl2(val) csr_write(val, LOONGARCH_CSR_IMPCTL2) #define read_csr_perfctrl0() csr_read64(LOONGARCH_CSR_PERFCTRL0) #define read_csr_perfcntr0() csr_read64(LOONGARCH_CSR_PERFCNTR0) @@ -1357,7 +1440,7 @@ __BUILD_CSR_OP(tlbidx) #define clear_csr_estat(val) \ csr_xchg32(~(val), val, LOONGARCH_CSR_ESTAT) -#endif /* __ASSEMBLY__ */ +#endif /* __ASSEMBLER__ */ /* Generic EntryLo bit definitions */ #define ENTRYLO_V (_ULCAST_(1) << 0) @@ -1367,8 +1450,10 @@ __BUILD_CSR_OP(tlbidx) #define ENTRYLO_C_SHIFT 4 #define ENTRYLO_C (_ULCAST_(3) << ENTRYLO_C_SHIFT) #define ENTRYLO_G (_ULCAST_(1) << 6) +#ifdef CONFIG_64BIT #define ENTRYLO_NR (_ULCAST_(1) << 61) #define ENTRYLO_NX (_ULCAST_(1) << 62) +#endif /* Values for PageSize register */ #define PS_4K 0x0000000c diff --git a/arch/loongarch/include/asm/module.h b/arch/loongarch/include/asm/module.h index f33f3fd32ecc..d56a968273de 100644 --- a/arch/loongarch/include/asm/module.h +++ b/arch/loongarch/include/asm/module.h @@ -38,8 +38,10 @@ struct got_entry { struct plt_entry { u32 inst_lu12iw; +#ifdef CONFIG_64BIT u32 inst_lu32id; u32 inst_lu52id; +#endif u32 inst_jirl; }; @@ -57,6 +59,14 @@ static inline struct got_entry emit_got_entry(Elf_Addr val) static inline struct plt_entry emit_plt_entry(unsigned long val) { +#ifdef CONFIG_32BIT + u32 lu12iw, jirl; + + lu12iw = larch_insn_gen_lu12iw(LOONGARCH_GPR_T1, ADDR_IMM(val, LU12IW)); + jirl = larch_insn_gen_jirl(0, LOONGARCH_GPR_T1, ADDR_IMM(val, ORI)); + + return (struct plt_entry) { lu12iw, jirl }; +#else u32 lu12iw, lu32id, lu52id, jirl; lu12iw = larch_insn_gen_lu12iw(LOONGARCH_GPR_T1, ADDR_IMM(val, LU12IW)); @@ -65,6 +75,7 @@ static inline struct plt_entry emit_plt_entry(unsigned long val) jirl = larch_insn_gen_jirl(0, LOONGARCH_GPR_T1, ADDR_IMM(val, ORI)); return (struct plt_entry) { lu12iw, lu32id, lu52id, jirl }; +#endif } static inline struct plt_idx_entry emit_plt_idx_entry(unsigned long val) diff --git a/arch/loongarch/include/asm/numa.h b/arch/loongarch/include/asm/numa.h index b5f9de9f102e..bbf9f70bd25f 100644 --- a/arch/loongarch/include/asm/numa.h +++ b/arch/loongarch/include/asm/numa.h @@ -22,20 +22,6 @@ extern int numa_off; extern s16 __cpuid_to_node[CONFIG_NR_CPUS]; extern nodemask_t numa_nodes_parsed __initdata; -struct numa_memblk { - u64 start; - u64 end; - int nid; -}; - -#define NR_NODE_MEMBLKS (MAX_NUMNODES*2) -struct numa_meminfo { - int nr_blks; - struct numa_memblk blk[NR_NODE_MEMBLKS]; -}; - -extern int __init numa_add_memblk(int nodeid, u64 start, u64 end); - extern void __init early_numa_add_cpu(int cpuid, s16 node); extern void numa_add_cpu(unsigned int cpu); extern void numa_remove_cpu(unsigned int cpu); diff --git a/arch/loongarch/include/asm/orc_types.h b/arch/loongarch/include/asm/orc_types.h index caf1f71a1057..d5fa98d1d177 100644 --- a/arch/loongarch/include/asm/orc_types.h +++ b/arch/loongarch/include/asm/orc_types.h @@ -34,7 +34,7 @@ #define ORC_TYPE_REGS 3 #define ORC_TYPE_REGS_PARTIAL 4 -#ifndef __ASSEMBLY__ +#ifndef __ASSEMBLER__ /* * This struct is more or less a vastly simplified version of the DWARF Call * Frame Information standard. It contains only the necessary parts of DWARF @@ -53,6 +53,6 @@ struct orc_entry { unsigned int type:3; unsigned int signal:1; }; -#endif /* __ASSEMBLY__ */ +#endif /* __ASSEMBLER__ */ #endif /* _ORC_TYPES_H */ diff --git a/arch/loongarch/include/asm/page.h b/arch/loongarch/include/asm/page.h index 7368f12b7cb1..b9d61f7c032c 100644 --- a/arch/loongarch/include/asm/page.h +++ b/arch/loongarch/include/asm/page.h @@ -10,12 +10,12 @@ #include <vdso/page.h> -#define HPAGE_SHIFT (PAGE_SHIFT + PAGE_SHIFT - 3) +#define HPAGE_SHIFT (PAGE_SHIFT + PAGE_SHIFT - PTRLOG) #define HPAGE_SIZE (_AC(1, UL) << HPAGE_SHIFT) #define HPAGE_MASK (~(HPAGE_SIZE - 1)) #define HUGETLB_PAGE_ORDER (HPAGE_SHIFT - PAGE_SHIFT) -#ifndef __ASSEMBLY__ +#ifndef __ASSEMBLER__ #include <linux/kernel.h> #include <linux/pfn.h> @@ -30,17 +30,12 @@ extern void clear_page(void *page); extern void copy_page(void *to, void *from); -#define clear_user_page(page, vaddr, pg) clear_page(page) #define copy_user_page(to, from, vaddr, pg) copy_page(to, from) extern unsigned long shm_align_mask; struct page; struct vm_area_struct; -void copy_user_highpage(struct page *to, struct page *from, - unsigned long vaddr, struct vm_area_struct *vma); - -#define __HAVE_ARCH_COPY_USER_HIGHPAGE typedef struct { unsigned long pte; } pte_t; #define pte_val(x) ((x).pte) @@ -105,11 +100,11 @@ struct page *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)) -#define VM_DATA_DEFAULT_FLAGS VM_DATA_FLAGS_TSK_EXEC +#define VMA_DATA_DEFAULT_FLAGS VMA_DATA_FLAGS_TSK_EXEC #include <asm-generic/memory_model.h> #include <asm-generic/getorder.h> -#endif /* !__ASSEMBLY__ */ +#endif /* !__ASSEMBLER__ */ #endif /* _ASM_PAGE_H */ diff --git a/arch/loongarch/include/asm/paravirt.h b/arch/loongarch/include/asm/paravirt.h index 3f4323603e6a..acae1c5e5f88 100644 --- a/arch/loongarch/include/asm/paravirt.h +++ b/arch/loongarch/include/asm/paravirt.h @@ -4,18 +4,11 @@ #ifdef CONFIG_PARAVIRT -#include <linux/static_call_types.h> -struct static_key; -extern struct static_key paravirt_steal_enabled; -extern struct static_key paravirt_steal_rq_enabled; +#include <linux/jump_label.h> -u64 dummy_steal_clock(int cpu); -DECLARE_STATIC_CALL(pv_steal_clock, dummy_steal_clock); - -static inline u64 paravirt_steal_clock(int cpu) -{ - return static_call(pv_steal_clock)(cpu); -} +DECLARE_STATIC_KEY_FALSE(virt_preempt_key); +DECLARE_STATIC_KEY_FALSE(virt_spin_lock_key); +DECLARE_PER_CPU(struct kvm_steal_time, steal_time); int __init pv_ipi_init(void); int __init pv_time_init(void); diff --git a/arch/loongarch/include/asm/paravirt_api_clock.h b/arch/loongarch/include/asm/paravirt_api_clock.h deleted file mode 100644 index 65ac7cee0dad..000000000000 --- a/arch/loongarch/include/asm/paravirt_api_clock.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm/paravirt.h> diff --git a/arch/loongarch/include/asm/percpu.h b/arch/loongarch/include/asm/percpu.h index 87be9b14e9da..583f2466262f 100644 --- a/arch/loongarch/include/asm/percpu.h +++ b/arch/loongarch/include/asm/percpu.h @@ -13,7 +13,7 @@ * 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) +#if defined(MODULE) && defined(CONFIG_AS_HAS_EXPLICIT_RELOCS) && defined(CONFIG_64BIT) # if __has_attribute(model) # define PER_CPU_ATTRIBUTES __attribute__((model("extreme"))) # else @@ -27,7 +27,7 @@ register unsigned long __my_cpu_offset __asm__("$r21"); static inline void set_my_cpu_offset(unsigned long off) { __my_cpu_offset = off; - csr_write64(off, PERCPU_BASE_KS); + csr_write(off, PERCPU_BASE_KS); } #define __my_cpu_offset \ @@ -36,6 +36,8 @@ static inline void set_my_cpu_offset(unsigned long off) __my_cpu_offset; \ }) +#ifdef CONFIG_CPU_HAS_AMO + #define PERCPU_OP(op, asm_op, c_op) \ static __always_inline unsigned long __percpu_##op(void *ptr, \ unsigned long val, int size) \ @@ -68,25 +70,9 @@ PERCPU_OP(and, and, &) PERCPU_OP(or, or, |) #undef PERCPU_OP -static __always_inline unsigned long __percpu_xchg(void *ptr, unsigned long val, int size) -{ - switch (size) { - case 1: - case 2: - return __xchg_small((volatile void *)ptr, val, size); - - case 4: - return __xchg_asm("amswap.w", (volatile u32 *)ptr, (u32)val); - - case 8: - return __xchg_asm("amswap.d", (volatile u64 *)ptr, (u64)val); +#endif - default: - BUILD_BUG(); - } - - return 0; -} +#ifdef CONFIG_64BIT #define __pcpu_op_1(op) op ".b " #define __pcpu_op_2(op) op ".h " @@ -115,6 +101,10 @@ do { \ : "memory"); \ } while (0) +#endif + +#define __percpu_xchg __arch_xchg + /* this_cpu_cmpxchg */ #define _protect_cmpxchg_local(pcp, o, n) \ ({ \ @@ -135,6 +125,8 @@ do { \ __retval; \ }) +#ifdef CONFIG_CPU_HAS_AMO + #define _percpu_add(pcp, val) \ _pcp_protect(__percpu_add, pcp, val) @@ -146,9 +138,6 @@ do { \ #define _percpu_or(pcp, val) \ _pcp_protect(__percpu_or, pcp, val) -#define _percpu_xchg(pcp, val) ((typeof(pcp)) \ - _pcp_protect(__percpu_xchg, pcp, (unsigned long)(val))) - #define this_cpu_add_4(pcp, val) _percpu_add(pcp, val) #define this_cpu_add_8(pcp, val) _percpu_add(pcp, val) @@ -161,6 +150,10 @@ do { \ #define this_cpu_or_4(pcp, val) _percpu_or(pcp, val) #define this_cpu_or_8(pcp, val) _percpu_or(pcp, val) +#endif + +#ifdef CONFIG_64BIT + #define this_cpu_read_1(pcp) _percpu_read(1, pcp) #define this_cpu_read_2(pcp) _percpu_read(2, pcp) #define this_cpu_read_4(pcp) _percpu_read(4, pcp) @@ -171,6 +164,11 @@ do { \ #define this_cpu_write_4(pcp, val) _percpu_write(4, pcp, val) #define this_cpu_write_8(pcp, val) _percpu_write(8, pcp, val) +#endif + +#define _percpu_xchg(pcp, val) ((typeof(pcp)) \ + _pcp_protect(__percpu_xchg, pcp, (unsigned long)(val))) + #define this_cpu_xchg_1(pcp, val) _percpu_xchg(pcp, val) #define this_cpu_xchg_2(pcp, val) _percpu_xchg(pcp, val) #define this_cpu_xchg_4(pcp, val) _percpu_xchg(pcp, val) diff --git a/arch/loongarch/include/asm/pgalloc.h b/arch/loongarch/include/asm/pgalloc.h index 7211dff8c969..248f62d0b590 100644 --- a/arch/loongarch/include/asm/pgalloc.h +++ b/arch/loongarch/include/asm/pgalloc.h @@ -55,11 +55,7 @@ static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm) return pte; } -#define __pte_free_tlb(tlb, pte, address) \ -do { \ - pagetable_dtor(page_ptdesc(pte)); \ - tlb_remove_page_ptdesc((tlb), page_ptdesc(pte)); \ -} while (0) +#define __pte_free_tlb(tlb, pte, address) tlb_remove_ptdesc((tlb), page_ptdesc(pte)) #ifndef __PAGETABLE_PMD_FOLDED @@ -72,7 +68,7 @@ static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address) if (!ptdesc) return NULL; - if (!pagetable_pmd_ctor(ptdesc)) { + if (!pagetable_pmd_ctor(mm, ptdesc)) { pagetable_free(ptdesc); return NULL; } @@ -82,7 +78,7 @@ static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address) return pmd; } -#define __pmd_free_tlb(tlb, x, addr) pmd_free((tlb)->mm, x) +#define __pmd_free_tlb(tlb, x, addr) tlb_remove_ptdesc((tlb), virt_to_ptdesc(x)) #endif @@ -91,7 +87,7 @@ static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address) static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address) { pud_t *pud; - struct ptdesc *ptdesc = pagetable_alloc(GFP_KERNEL & ~__GFP_HIGHMEM, 0); + struct ptdesc *ptdesc = pagetable_alloc(GFP_KERNEL, 0); if (!ptdesc) return NULL; @@ -102,7 +98,7 @@ static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address) return pud; } -#define __pud_free_tlb(tlb, x, addr) pud_free((tlb)->mm, x) +#define __pud_free_tlb(tlb, x, addr) tlb_remove_ptdesc((tlb), virt_to_ptdesc(x)) #endif /* __PAGETABLE_PUD_FOLDED */ diff --git a/arch/loongarch/include/asm/pgtable-bits.h b/arch/loongarch/include/asm/pgtable-bits.h index 45bfc65a0c9f..b565573cd82e 100644 --- a/arch/loongarch/include/asm/pgtable-bits.h +++ b/arch/loongarch/include/asm/pgtable-bits.h @@ -6,6 +6,26 @@ #define _ASM_PGTABLE_BITS_H /* Page table bits */ + +#ifdef CONFIG_32BIT +#define _PAGE_VALID_SHIFT 0 +#define _PAGE_ACCESSED_SHIFT 0 /* Reuse Valid for Accessed */ +#define _PAGE_DIRTY_SHIFT 1 +#define _PAGE_PLV_SHIFT 2 /* 2~3, two bits */ +#define _CACHE_SHIFT 4 /* 4~5, two bits */ +#define _PAGE_GLOBAL_SHIFT 6 +#define _PAGE_HUGE_SHIFT 6 /* HUGE is a PMD bit */ +#define _PAGE_PRESENT_SHIFT 7 +#define _PAGE_PFN_SHIFT 8 +#define _PAGE_HGLOBAL_SHIFT 12 /* HGlobal is a PMD bit */ +#define _PAGE_SWP_EXCLUSIVE_SHIFT 13 +#define _PAGE_PFN_END_SHIFT 28 +#define _PAGE_WRITE_SHIFT 29 +#define _PAGE_MODIFIED_SHIFT 30 +#define _PAGE_PRESENT_INVALID_SHIFT 31 +#endif + +#ifdef CONFIG_64BIT #define _PAGE_VALID_SHIFT 0 #define _PAGE_ACCESSED_SHIFT 0 /* Reuse Valid for Accessed */ #define _PAGE_DIRTY_SHIFT 1 @@ -18,15 +38,15 @@ #define _PAGE_MODIFIED_SHIFT 9 #define _PAGE_PROTNONE_SHIFT 10 #define _PAGE_SPECIAL_SHIFT 11 -#define _PAGE_HGLOBAL_SHIFT 12 /* HGlobal is a PMD bit */ #define _PAGE_PFN_SHIFT 12 +#define _PAGE_HGLOBAL_SHIFT 12 /* HGlobal is a PMD bit */ #define _PAGE_SWP_EXCLUSIVE_SHIFT 23 #define _PAGE_PFN_END_SHIFT 48 -#define _PAGE_DEVMAP_SHIFT 59 #define _PAGE_PRESENT_INVALID_SHIFT 60 #define _PAGE_NO_READ_SHIFT 61 #define _PAGE_NO_EXEC_SHIFT 62 #define _PAGE_RPLV_SHIFT 63 +#endif /* Used by software */ #define _PAGE_PRESENT (_ULCAST_(1) << _PAGE_PRESENT_SHIFT) @@ -34,11 +54,15 @@ #define _PAGE_WRITE (_ULCAST_(1) << _PAGE_WRITE_SHIFT) #define _PAGE_ACCESSED (_ULCAST_(1) << _PAGE_ACCESSED_SHIFT) #define _PAGE_MODIFIED (_ULCAST_(1) << _PAGE_MODIFIED_SHIFT) +#ifdef CONFIG_32BIT +#define _PAGE_PROTNONE 0 +#define _PAGE_SPECIAL 0 +#else #define _PAGE_PROTNONE (_ULCAST_(1) << _PAGE_PROTNONE_SHIFT) #define _PAGE_SPECIAL (_ULCAST_(1) << _PAGE_SPECIAL_SHIFT) -#define _PAGE_DEVMAP (_ULCAST_(1) << _PAGE_DEVMAP_SHIFT) +#endif -/* We borrow bit 23 to store the exclusive marker in swap PTEs. */ +/* We borrow bit 13/23 to store the exclusive marker in swap PTEs. */ #define _PAGE_SWP_EXCLUSIVE (_ULCAST_(1) << _PAGE_SWP_EXCLUSIVE_SHIFT) /* Used by TLB hardware (placed in EntryLo*) */ @@ -48,9 +72,15 @@ #define _PAGE_GLOBAL (_ULCAST_(1) << _PAGE_GLOBAL_SHIFT) #define _PAGE_HUGE (_ULCAST_(1) << _PAGE_HUGE_SHIFT) #define _PAGE_HGLOBAL (_ULCAST_(1) << _PAGE_HGLOBAL_SHIFT) +#ifdef CONFIG_32BIT +#define _PAGE_NO_READ 0 +#define _PAGE_NO_EXEC 0 +#define _PAGE_RPLV 0 +#else #define _PAGE_NO_READ (_ULCAST_(1) << _PAGE_NO_READ_SHIFT) #define _PAGE_NO_EXEC (_ULCAST_(1) << _PAGE_NO_EXEC_SHIFT) #define _PAGE_RPLV (_ULCAST_(1) << _PAGE_RPLV_SHIFT) +#endif #define _CACHE_MASK (_ULCAST_(3) << _CACHE_SHIFT) #define PFN_PTE_SHIFT (PAGE_SHIFT - 12 + _PAGE_PFN_SHIFT) @@ -76,8 +106,8 @@ #define __READABLE (_PAGE_VALID) #define __WRITEABLE (_PAGE_DIRTY | _PAGE_WRITE) -#define _PAGE_CHG_MASK (_PAGE_MODIFIED | _PAGE_SPECIAL | _PAGE_DEVMAP | _PFN_MASK | _CACHE_MASK | _PAGE_PLV) -#define _HPAGE_CHG_MASK (_PAGE_MODIFIED | _PAGE_SPECIAL | _PAGE_DEVMAP | _PFN_MASK | _CACHE_MASK | _PAGE_PLV | _PAGE_HUGE) +#define _PAGE_CHG_MASK (_PAGE_MODIFIED | _PAGE_SPECIAL | _PFN_MASK | _CACHE_MASK | _PAGE_PLV) +#define _HPAGE_CHG_MASK (_PAGE_MODIFIED | _PAGE_SPECIAL | _PFN_MASK | _CACHE_MASK | _PAGE_PLV | _PAGE_HUGE) #define PAGE_NONE __pgprot(_PAGE_PROTNONE | _PAGE_NO_READ | \ _PAGE_USER | _CACHE_CC) @@ -92,7 +122,7 @@ #define PAGE_KERNEL_WUC __pgprot(_PAGE_PRESENT | __READABLE | __WRITEABLE | \ _PAGE_GLOBAL | _PAGE_KERN | _CACHE_WUC) -#ifndef __ASSEMBLY__ +#ifndef __ASSEMBLER__ #define _PAGE_IOREMAP pgprot_val(PAGE_KERNEL_SUC) @@ -127,6 +157,6 @@ static inline pgprot_t pgprot_writecombine(pgprot_t _prot) return __pgprot(prot); } -#endif /* !__ASSEMBLY__ */ +#endif /* !__ASSEMBLER__ */ #endif /* _ASM_PGTABLE_BITS_H */ diff --git a/arch/loongarch/include/asm/pgtable.h b/arch/loongarch/include/asm/pgtable.h index da346733a1da..2a0b63ae421f 100644 --- a/arch/loongarch/include/asm/pgtable.h +++ b/arch/loongarch/include/asm/pgtable.h @@ -11,6 +11,7 @@ #include <linux/compiler.h> #include <asm/addrspace.h> +#include <asm/asm.h> #include <asm/page.h> #include <asm/pgtable-bits.h> @@ -22,40 +23,52 @@ #include <asm-generic/pgtable-nop4d.h> #endif +#ifdef CONFIG_HIGHMEM +#include <asm/highmem.h> +#endif + #if CONFIG_PGTABLE_LEVELS == 2 -#define PGDIR_SHIFT (PAGE_SHIFT + (PAGE_SHIFT - 3)) +#define PGDIR_SHIFT (PAGE_SHIFT + (PAGE_SHIFT - PTRLOG)) #elif CONFIG_PGTABLE_LEVELS == 3 -#define PMD_SHIFT (PAGE_SHIFT + (PAGE_SHIFT - 3)) +#define PMD_SHIFT (PAGE_SHIFT + (PAGE_SHIFT - PTRLOG)) #define PMD_SIZE (1UL << PMD_SHIFT) #define PMD_MASK (~(PMD_SIZE-1)) -#define PGDIR_SHIFT (PMD_SHIFT + (PAGE_SHIFT - 3)) +#define PGDIR_SHIFT (PMD_SHIFT + (PAGE_SHIFT - PTRLOG)) #elif CONFIG_PGTABLE_LEVELS == 4 -#define PMD_SHIFT (PAGE_SHIFT + (PAGE_SHIFT - 3)) +#define PMD_SHIFT (PAGE_SHIFT + (PAGE_SHIFT - PTRLOG)) #define PMD_SIZE (1UL << PMD_SHIFT) #define PMD_MASK (~(PMD_SIZE-1)) -#define PUD_SHIFT (PMD_SHIFT + (PAGE_SHIFT - 3)) +#define PUD_SHIFT (PMD_SHIFT + (PAGE_SHIFT - PTRLOG)) #define PUD_SIZE (1UL << PUD_SHIFT) #define PUD_MASK (~(PUD_SIZE-1)) -#define PGDIR_SHIFT (PUD_SHIFT + (PAGE_SHIFT - 3)) +#define PGDIR_SHIFT (PUD_SHIFT + (PAGE_SHIFT - PTRLOG)) #endif #define PGDIR_SIZE (1UL << PGDIR_SHIFT) #define PGDIR_MASK (~(PGDIR_SIZE-1)) -#define VA_BITS (PGDIR_SHIFT + (PAGE_SHIFT - 3)) +#ifdef CONFIG_32BIT +#define VA_BITS 32 +#else +#define VA_BITS (PGDIR_SHIFT + (PAGE_SHIFT - PTRLOG)) +#endif -#define PTRS_PER_PGD (PAGE_SIZE >> 3) +#define PTRS_PER_PGD (PAGE_SIZE >> PTRLOG) #if CONFIG_PGTABLE_LEVELS > 3 -#define PTRS_PER_PUD (PAGE_SIZE >> 3) +#define PTRS_PER_PUD (PAGE_SIZE >> PTRLOG) #endif #if CONFIG_PGTABLE_LEVELS > 2 -#define PTRS_PER_PMD (PAGE_SIZE >> 3) +#define PTRS_PER_PMD (PAGE_SIZE >> PTRLOG) #endif -#define PTRS_PER_PTE (PAGE_SIZE >> 3) +#define PTRS_PER_PTE (PAGE_SIZE >> PTRLOG) +#ifdef CONFIG_32BIT +#define USER_PTRS_PER_PGD (TASK_SIZE / PGDIR_SIZE) +#else #define USER_PTRS_PER_PGD ((TASK_SIZE64 / PGDIR_SIZE)?(TASK_SIZE64 / PGDIR_SIZE):1) +#endif -#ifndef __ASSEMBLY__ +#ifndef __ASSEMBLER__ #include <linux/mm_types.h> #include <linux/mmzone.h> @@ -65,20 +78,23 @@ struct mm_struct; struct vm_area_struct; -/* - * ZERO_PAGE is a global shared page that is always zero; used - * for zero-mapped memory areas etc.. - */ +#ifdef CONFIG_32BIT -extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]; +#define VMALLOC_START (vm_map_base + PCI_IOSIZE + (2 * PAGE_SIZE)) -#define ZERO_PAGE(vaddr) virt_to_page(empty_zero_page) +#ifdef CONFIG_HIGHMEM +#define VMALLOC_END (PKMAP_BASE - (2 * PAGE_SIZE)) +#else +#define VMALLOC_END (FIXADDR_START - (2 * PAGE_SIZE)) +#endif + +#define PKMAP_BASE (PKMAP_END - (PAGE_SIZE * LAST_PKMAP)) +#define PKMAP_END ((FIXADDR_START) & ~((LAST_PKMAP << PAGE_SHIFT)-1)) + +#endif + +#ifdef CONFIG_64BIT -/* - * TLB refill handlers may also map the vmalloc area into xkvrange. - * Avoid the first couple of pages so NULL pointer dereferences will - * still reliably trap. - */ #define MODULES_VADDR (vm_map_base + PCI_IOSIZE + (2 * PAGE_SIZE)) #define MODULES_END (MODULES_VADDR + SZ_256M) @@ -100,12 +116,15 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]; 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_ALIGN max(PMD_SIZE, MAX_FOLIO_VMEMMAP_ALIGN) +#define vmemmap ((struct page *)(ALIGN(VMALLOC_END, VMEMMAP_ALIGN))) #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) +#endif + #define ptep_get(ptep) READ_ONCE(*(ptep)) #define pmdp_get(pmdp) READ_ONCE(*(pmdp)) @@ -255,7 +274,6 @@ static inline void pmd_clear(pmd_t *pmdp) #define pmd_page_vaddr(pmd) pmd_val(pmd) -extern pmd_t mk_pmd(struct page *page, pgprot_t prot); extern void set_pmd_at(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, pmd_t pmd); #define pte_page(x) pfn_to_page(pte_pfn(x)) @@ -278,7 +296,16 @@ extern void kernel_pte_init(void *addr); * Encode/decode swap entries and swap PTEs. Swap PTEs are all PTEs that * are !pte_none() && !pte_present(). * - * Format of swap PTEs: + * Format of 32bit swap PTEs: + * + * 3 3 2 2 2 2 2 2 2 2 2 2 1 1 1 1 1 1 1 1 1 1 + * 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 + * <------------ offset -------------> E <- type -> <-- zeroes --> + * + * E is the exclusive marker that is not stored in swap entries. + * The zero'ed bits include _PAGE_PRESENT. + * + * Format of 64bit swap PTEs: * * 6 6 6 6 5 5 5 5 5 5 5 5 5 5 4 4 4 4 4 4 4 4 4 4 3 3 3 3 3 3 3 3 * 3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 @@ -291,18 +318,29 @@ extern void kernel_pte_init(void *addr); * E is the exclusive marker that is not stored in swap entries. * The zero'ed bits include _PAGE_PRESENT and _PAGE_PROTNONE. */ + +#define __SWP_TYPE_BITS (IS_ENABLED(CONFIG_32BIT) ? 5 : 7) +#define __SWP_TYPE_MASK ((1UL << __SWP_TYPE_BITS) - 1) +#define __SWP_TYPE_SHIFT (IS_ENABLED(CONFIG_32BIT) ? 8 : 16) +#define __SWP_OFFSET_SHIFT (__SWP_TYPE_BITS + __SWP_TYPE_SHIFT + 1) + static inline pte_t mk_swap_pte(unsigned long type, unsigned long offset) -{ pte_t pte; pte_val(pte) = ((type & 0x7f) << 16) | (offset << 24); return pte; } +{ + pte_t pte; + pte_val(pte) = ((type & __SWP_TYPE_MASK) << __SWP_TYPE_SHIFT) | (offset << __SWP_OFFSET_SHIFT); + return pte; +} -#define __swp_type(x) (((x).val >> 16) & 0x7f) -#define __swp_offset(x) ((x).val >> 24) +#define __swp_type(x) (((x).val >> __SWP_TYPE_SHIFT) & __SWP_TYPE_MASK) +#define __swp_offset(x) ((x).val >> __SWP_OFFSET_SHIFT) #define __swp_entry(type, offset) ((swp_entry_t) { pte_val(mk_swap_pte((type), (offset))) }) + +#define __swp_entry_to_pte(x) __pte((x).val) +#define __swp_entry_to_pmd(x) __pmd((x).val | _PAGE_HUGE) #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) }) -#define __swp_entry_to_pte(x) ((pte_t) { (x).val }) #define __pmd_to_swp_entry(pmd) ((swp_entry_t) { pmd_val(pmd) }) -#define __swp_entry_to_pmd(x) ((pmd_t) { (x).val | _PAGE_HUGE }) -static inline int pte_swp_exclusive(pte_t pte) +static inline bool pte_swp_exclusive(pte_t pte) { return pte_val(pte) & _PAGE_SWP_EXCLUSIVE; } @@ -319,8 +357,6 @@ static inline pte_t pte_swp_clear_exclusive(pte_t pte) return pte; } -extern void paging_init(void); - #define pte_none(pte) (!(pte_val(pte) & ~_PAGE_GLOBAL)) #define pte_present(pte) (pte_val(pte) & (_PAGE_PRESENT | _PAGE_PROTNONE)) #define pte_no_exec(pte) (pte_val(pte) & _PAGE_NO_EXEC) @@ -410,9 +446,6 @@ static inline int pte_special(pte_t pte) { return pte_val(pte) & _PAGE_SPECIAL; static inline pte_t pte_mkspecial(pte_t pte) { pte_val(pte) |= _PAGE_SPECIAL; return pte; } #endif /* CONFIG_ARCH_HAS_PTE_SPECIAL */ -static inline int pte_devmap(pte_t pte) { return !!(pte_val(pte) & _PAGE_DEVMAP); } -static inline pte_t pte_mkdevmap(pte_t pte) { pte_val(pte) |= _PAGE_DEVMAP; return pte; } - #define pte_accessible pte_accessible static inline unsigned long pte_accessible(struct mm_struct *mm, pte_t a) { @@ -426,14 +459,11 @@ static inline unsigned long pte_accessible(struct mm_struct *mm, pte_t a) return false; } -/* - * Conversion functions: convert a page and protection to a page entry, - * and a page entry and page directory to the page they refer to. - */ -#define mk_pte(page, pgprot) pfn_pte(page_to_pfn(page), (pgprot)) - static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) { + if (pte_val(pte) & _PAGE_DIRTY) + pte_val(pte) |= _PAGE_MODIFIED; + return __pte((pte_val(pte) & _PAGE_CHG_MASK) | (pgprot_val(newprot) & ~_PAGE_CHG_MASK)); } @@ -547,17 +577,6 @@ static inline pmd_t pmd_mkyoung(pmd_t pmd) return pmd; } -static inline int pmd_devmap(pmd_t pmd) -{ - return !!(pmd_val(pmd) & _PAGE_DEVMAP); -} - -static inline pmd_t pmd_mkdevmap(pmd_t pmd) -{ - pmd_val(pmd) |= _PAGE_DEVMAP; - return pmd; -} - static inline struct page *pmd_page(pmd_t pmd) { if (pmd_trans_huge(pmd)) @@ -568,9 +587,11 @@ static inline struct page *pmd_page(pmd_t pmd) static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) { - pmd_val(pmd) = (pmd_val(pmd) & _HPAGE_CHG_MASK) | - (pgprot_val(newprot) & ~_HPAGE_CHG_MASK); - return pmd; + if (pmd_val(pmd) & _PAGE_DIRTY) + pmd_val(pmd) |= _PAGE_MODIFIED; + + return __pmd((pmd_val(pmd) & _HPAGE_CHG_MASK) | + (pgprot_val(newprot) & ~_HPAGE_CHG_MASK)); } static inline pmd_t pmd_mkinvalid(pmd_t pmd) @@ -613,11 +634,6 @@ static inline long pmd_protnone(pmd_t pmd) #define pmd_leaf(pmd) ((pmd_val(pmd) & _PAGE_HUGE) != 0) #define pud_leaf(pud) ((pud_val(pud) & _PAGE_HUGE) != 0) -#ifdef CONFIG_TRANSPARENT_HUGEPAGE -#define pud_devmap(pud) (0) -#define pgd_devmap(pgd) (0) -#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ - /* * We provide our own get_unmapped area to cope with the virtual aliasing * constraints placed on us by the cache architecture. @@ -625,6 +641,6 @@ static inline long pmd_protnone(pmd_t pmd) #define HAVE_ARCH_UNMAPPED_AREA #define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN -#endif /* !__ASSEMBLY__ */ +#endif /* !__ASSEMBLER__ */ #endif /* _ASM_PGTABLE_H */ diff --git a/arch/loongarch/include/asm/prefetch.h b/arch/loongarch/include/asm/prefetch.h index 1672262a5e2e..0b168cdaae9a 100644 --- a/arch/loongarch/include/asm/prefetch.h +++ b/arch/loongarch/include/asm/prefetch.h @@ -8,7 +8,7 @@ #define Pref_Load 0 #define Pref_Store 8 -#ifdef __ASSEMBLY__ +#ifdef __ASSEMBLER__ .macro __pref hint addr #ifdef CONFIG_CPU_HAS_PREFETCH diff --git a/arch/loongarch/include/asm/processor.h b/arch/loongarch/include/asm/processor.h index c3bc44b5f5b3..ce8b953f8c79 100644 --- a/arch/loongarch/include/asm/processor.h +++ b/arch/loongarch/include/asm/processor.h @@ -80,10 +80,10 @@ BUILD_FPR_ACCESS(32) BUILD_FPR_ACCESS(64) struct loongarch_fpu { + union fpureg fpr[NUM_FPU_REGS]; uint64_t fcc; /* 8x8 */ uint32_t fcsr; uint32_t ftop; - union fpureg fpr[NUM_FPU_REGS]; }; struct loongarch_lbt { diff --git a/arch/loongarch/include/asm/ptrace.h b/arch/loongarch/include/asm/ptrace.h index f3ddaed9ef7f..e5d21e836d99 100644 --- a/arch/loongarch/include/asm/ptrace.h +++ b/arch/loongarch/include/asm/ptrace.h @@ -33,9 +33,9 @@ struct pt_regs { unsigned long __last[]; } __aligned(8); -static inline int regs_irqs_disabled(struct pt_regs *regs) +static __always_inline bool regs_irqs_disabled(struct pt_regs *regs) { - return arch_irqs_disabled_flags(regs->csr_prmd); + return !(regs->csr_prmd & CSR_PRMD_PIE); } static inline unsigned long kernel_stack_pointer(struct pt_regs *regs) @@ -55,7 +55,7 @@ static inline void instruction_pointer_set(struct pt_regs *regs, unsigned long v /* Query offset/name of register from its name/offset */ extern int regs_query_register_offset(const char *name); -#define MAX_REG_OFFSET (offsetof(struct pt_regs, __last)) +#define MAX_REG_OFFSET (offsetof(struct pt_regs, __last) - sizeof(unsigned long)) /** * regs_get_register() - get register value from its offset diff --git a/arch/loongarch/include/asm/qspinlock.h b/arch/loongarch/include/asm/qspinlock.h index e76d3aa1e1eb..fbfc6be82f26 100644 --- a/arch/loongarch/include/asm/qspinlock.h +++ b/arch/loongarch/include/asm/qspinlock.h @@ -2,12 +2,11 @@ #ifndef _ASM_LOONGARCH_QSPINLOCK_H #define _ASM_LOONGARCH_QSPINLOCK_H -#include <linux/jump_label.h> +#include <asm/kvm_para.h> +#include <asm/paravirt.h> #ifdef CONFIG_PARAVIRT -DECLARE_STATIC_KEY_FALSE(virt_spin_lock_key); - #define virt_spin_lock virt_spin_lock static inline bool virt_spin_lock(struct qspinlock *lock) @@ -34,6 +33,26 @@ __retry: return true; } +/* + * Macro is better than inline function here + * With macro, parameter cpu is parsed only when it is used. + * With inline function, parameter cpu is parsed even though it is not used. + * This may cause cache line thrashing across NUMA nodes. + */ +#define vcpu_is_preempted(cpu) \ +({ \ + bool __val; \ + \ + if (!static_branch_unlikely(&virt_preempt_key)) \ + __val = false; \ + else { \ + struct kvm_steal_time *src; \ + src = &per_cpu(steal_time, cpu); \ + __val = !!(READ_ONCE(src->preempted) & KVM_VCPU_PREEMPTED); \ + } \ + __val; \ +}) + #endif /* CONFIG_PARAVIRT */ #include <asm-generic/qspinlock.h> diff --git a/arch/loongarch/include/asm/setup.h b/arch/loongarch/include/asm/setup.h index 3c2fb16b11b6..f81375e5e89c 100644 --- a/arch/loongarch/include/asm/setup.h +++ b/arch/loongarch/include/asm/setup.h @@ -7,6 +7,7 @@ #define _LOONGARCH_SETUP_H #include <linux/types.h> +#include <linux/threads.h> #include <asm/sections.h> #include <uapi/asm/setup.h> @@ -14,6 +15,8 @@ extern unsigned long eentry; extern unsigned long tlbrentry; +extern unsigned long pcpu_handlers[NR_CPUS]; +extern long exception_handlers[VECSIZE * 128 / sizeof(long)]; extern char init_command_line[COMMAND_LINE_SIZE]; extern void tlb_init(int cpu); extern void cpu_cache_init(void); diff --git a/arch/loongarch/include/asm/sigframe.h b/arch/loongarch/include/asm/sigframe.h new file mode 100644 index 000000000000..109298b8d7e0 --- /dev/null +++ b/arch/loongarch/include/asm/sigframe.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ + +#include <asm/siginfo.h> +#include <asm/ucontext.h> + +struct rt_sigframe { + struct siginfo rs_info; + struct ucontext rs_uctx; +}; diff --git a/arch/loongarch/include/asm/smp.h b/arch/loongarch/include/asm/smp.h index b87d1d5e5890..3a47f52959a8 100644 --- a/arch/loongarch/include/asm/smp.h +++ b/arch/loongarch/include/asm/smp.h @@ -25,6 +25,7 @@ extern int smp_num_siblings; extern int num_processors; extern int disabled_cpus; extern cpumask_t cpu_sibling_map[]; +extern cpumask_t cpu_llc_shared_map[]; extern cpumask_t cpu_core_map[]; extern cpumask_t cpu_foreign_map[]; @@ -38,7 +39,7 @@ int loongson_cpu_disable(void); void loongson_cpu_die(unsigned int cpu); #endif -static inline void plat_smp_setup(void) +static inline void __init plat_smp_setup(void) { loongson_smp_setup(); } diff --git a/arch/loongarch/include/asm/sparsemem.h b/arch/loongarch/include/asm/sparsemem.h index 8d4af6aff8a8..4501efac1a87 100644 --- a/arch/loongarch/include/asm/sparsemem.h +++ b/arch/loongarch/include/asm/sparsemem.h @@ -21,11 +21,6 @@ #define VMEMMAP_SIZE 0 /* 1, For FLATMEM; 2, For SPARSEMEM without VMEMMAP. */ #endif -#ifdef CONFIG_MEMORY_HOTPLUG -int memory_add_physaddr_to_nid(u64 addr); -#define memory_add_physaddr_to_nid memory_add_physaddr_to_nid -#endif - #define INIT_MEMBLOCK_RESERVED_REGIONS (INIT_MEMBLOCK_REGIONS + NR_CPUS) #endif /* _LOONGARCH_SPARSEMEM_H */ diff --git a/arch/loongarch/include/asm/stackframe.h b/arch/loongarch/include/asm/stackframe.h index 66736837085b..ecc8e50fffa8 100644 --- a/arch/loongarch/include/asm/stackframe.h +++ b/arch/loongarch/include/asm/stackframe.h @@ -38,25 +38,51 @@ cfi_restore \reg \offset \docfi .endm + .macro SETUP_TWINS temp + pcaddi t0, 0 + PTR_LI t1, ~TO_PHYS_MASK + and t0, t0, t1 + ori t0, t0, (1 << 4 | 1) + csrwr t0, LOONGARCH_CSR_DMWIN0 + PTR_LI t0, CSR_DMW1_INIT + csrwr t0, LOONGARCH_CSR_DMWIN1 + .endm + + .macro SETUP_MODES temp + /* Enable PG */ + li.w \temp, 0xb0 # PLV=0, IE=0, PG=1 + csrwr \temp, LOONGARCH_CSR_CRMD + li.w \temp, 0x04 # PLV=0, PIE=1, PWE=0 + csrwr \temp, LOONGARCH_CSR_PRMD + li.w \temp, 0x00 # FPE=0, SXE=0, ASXE=0, BTE=0 + csrwr \temp, LOONGARCH_CSR_EUEN + .endm + .macro SETUP_DMWINS temp - li.d \temp, CSR_DMW0_INIT # WUC, PLV0, 0x8000 xxxx xxxx xxxx + PTR_LI \temp, CSR_DMW0_INIT # SUC, PLV0, LA32: 0x8xxx xxxx, LA64: 0x8000 xxxx xxxx xxxx csrwr \temp, LOONGARCH_CSR_DMWIN0 - li.d \temp, CSR_DMW1_INIT # CAC, PLV0, 0x9000 xxxx xxxx xxxx + PTR_LI \temp, CSR_DMW1_INIT # CAC, PLV0, LA32: 0xaxxx xxxx, LA64: 0x9000 xxxx xxxx xxxx csrwr \temp, LOONGARCH_CSR_DMWIN1 - li.d \temp, CSR_DMW2_INIT # WUC, PLV0, 0xa000 xxxx xxxx xxxx + PTR_LI \temp, CSR_DMW2_INIT # WUC, PLV0, LA32: unavailable, LA64: 0xa000 xxxx xxxx xxxx csrwr \temp, LOONGARCH_CSR_DMWIN2 - li.d \temp, CSR_DMW3_INIT # 0x0, unused + PTR_LI \temp, CSR_DMW3_INIT # 0x0, unused csrwr \temp, LOONGARCH_CSR_DMWIN3 .endm /* Jump to the runtime virtual address. */ .macro JUMP_VIRT_ADDR temp1 temp2 - li.d \temp1, CACHE_BASE + PTR_LI \temp1, CACHE_BASE pcaddi \temp2, 0 - bstrins.d \temp1, \temp2, (DMW_PABITS - 1), 0 + PTR_BSTRINS \temp1, \temp2, (DMW_PABITS - 1), 0 jirl zero, \temp1, 0xc .endm + .macro STACKLEAK_ERASE +#ifdef CONFIG_KSTACK_ERASE + bl stackleak_erase_on_task_stack +#endif + .endm + .macro BACKUP_T0T1 csrwr t0, EXCEPTION_KS0 csrwr t1, EXCEPTION_KS1 @@ -165,7 +191,7 @@ andi t0, t0, 0x3 /* extract pplv bit */ beqz t0, 9f - li.d tp, ~_THREAD_MASK + LONG_LI tp, ~_THREAD_MASK and tp, tp, sp cfi_st u0, PT_R21, \docfi csrrd u0, PERCPU_BASE_KS diff --git a/arch/loongarch/include/asm/stackprotector.h b/arch/loongarch/include/asm/stackprotector.h index a1a965751a7b..42f6c3f69115 100644 --- a/arch/loongarch/include/asm/stackprotector.h +++ b/arch/loongarch/include/asm/stackprotector.h @@ -12,9 +12,6 @@ #ifndef _ASM_STACKPROTECTOR_H #define _ASM_STACKPROTECTOR_H -#include <linux/random.h> -#include <linux/version.h> - extern unsigned long __stack_chk_guard; /* @@ -25,11 +22,7 @@ extern unsigned long __stack_chk_guard; */ static __always_inline void boot_init_stack_canary(void) { - unsigned long canary; - - /* Try to get a semi random initial value. */ - get_random_bytes(&canary, sizeof(canary)); - canary ^= LINUX_VERSION_CODE; + unsigned long canary = get_random_canary(); current->stack_canary = canary; __stack_chk_guard = current->stack_canary; diff --git a/arch/loongarch/include/asm/stacktrace.h b/arch/loongarch/include/asm/stacktrace.h index f23adb15f418..5c8be156567c 100644 --- a/arch/loongarch/include/asm/stacktrace.h +++ b/arch/loongarch/include/asm/stacktrace.h @@ -8,6 +8,7 @@ #include <asm/asm.h> #include <asm/ptrace.h> #include <asm/loongarch.h> +#include <asm/unwind_hints.h> #include <linux/stringify.h> enum stack_type { @@ -30,6 +31,11 @@ bool in_irq_stack(unsigned long stack, struct stack_info *info); bool in_task_stack(unsigned long stack, struct task_struct *task, struct stack_info *info); int get_stack_info(unsigned long stack, struct task_struct *task, struct stack_info *info); +static __always_inline bool on_thread_stack(void) +{ + return !(((unsigned long)(current->stack) ^ current_stack_pointer) & ~(THREAD_SIZE - 1)); +} + #define STR_LONG_L __stringify(LONG_L) #define STR_LONG_S __stringify(LONG_S) #define STR_LONGSIZE __stringify(LONGSIZE) @@ -43,6 +49,7 @@ int get_stack_info(unsigned long stack, struct task_struct *task, struct stack_i static __always_inline void prepare_frametrace(struct pt_regs *regs) { __asm__ __volatile__( + UNWIND_HINT_SAVE /* Save $ra */ STORE_ONE_REG(1) /* Use $ra to save PC */ @@ -80,6 +87,7 @@ static __always_inline void prepare_frametrace(struct pt_regs *regs) STORE_ONE_REG(29) STORE_ONE_REG(30) STORE_ONE_REG(31) + UNWIND_HINT_RESTORE : "=m" (regs->csr_era) : "r" (regs->regs) : "memory"); diff --git a/arch/loongarch/include/asm/string.h b/arch/loongarch/include/asm/string.h index 5bb5a90d2681..bfa3fd879c7f 100644 --- a/arch/loongarch/include/asm/string.h +++ b/arch/loongarch/include/asm/string.h @@ -5,6 +5,7 @@ #ifndef _ASM_STRING_H #define _ASM_STRING_H +#ifdef CONFIG_64BIT #define __HAVE_ARCH_MEMSET extern void *memset(void *__s, int __c, size_t __count); extern void *__memset(void *__s, int __c, size_t __count); @@ -16,6 +17,7 @@ extern void *__memcpy(void *__to, __const__ void *__from, size_t __n); #define __HAVE_ARCH_MEMMOVE extern void *memmove(void *__dest, __const__ void *__src, size_t __n); extern void *__memmove(void *__dest, __const__ void *__src, size_t __n); +#endif #if defined(CONFIG_KASAN) && !defined(__SANITIZE_ADDRESS__) diff --git a/arch/loongarch/include/asm/syscall.h b/arch/loongarch/include/asm/syscall.h index e286dc58476e..df8ea223c77b 100644 --- a/arch/loongarch/include/asm/syscall.h +++ b/arch/loongarch/include/asm/syscall.h @@ -26,6 +26,13 @@ static inline long syscall_get_nr(struct task_struct *task, return regs->regs[11]; } +static inline void syscall_set_nr(struct task_struct *task, + struct pt_regs *regs, + int nr) +{ + regs->regs[11] = nr; +} + static inline void syscall_rollback(struct task_struct *task, struct pt_regs *regs) { @@ -61,9 +68,21 @@ static inline void syscall_get_arguments(struct task_struct *task, memcpy(&args[1], ®s->regs[5], 5 * sizeof(long)); } +static inline void syscall_set_arguments(struct task_struct *task, + struct pt_regs *regs, + unsigned long *args) +{ + regs->orig_a0 = args[0]; + memcpy(®s->regs[5], &args[1], 5 * sizeof(long)); +} + static inline int syscall_get_arch(struct task_struct *task) { +#ifdef CONFIG_32BIT + return AUDIT_ARCH_LOONGARCH32; +#else return AUDIT_ARCH_LOONGARCH64; +#endif } static inline bool arch_syscall_is_vdso_sigreturn(struct pt_regs *regs) diff --git a/arch/loongarch/include/asm/thread_info.h b/arch/loongarch/include/asm/thread_info.h index 4f5a9441754e..4d7117fcdc78 100644 --- a/arch/loongarch/include/asm/thread_info.h +++ b/arch/loongarch/include/asm/thread_info.h @@ -10,7 +10,7 @@ #ifdef __KERNEL__ -#ifndef __ASSEMBLY__ +#ifndef __ASSEMBLER__ #include <asm/processor.h> @@ -53,7 +53,7 @@ static inline struct thread_info *current_thread_info(void) register unsigned long current_stack_pointer __asm__("$sp"); -#endif /* !__ASSEMBLY__ */ +#endif /* !__ASSEMBLER__ */ /* thread information allocation */ #define THREAD_SIZE SZ_16K @@ -65,50 +65,42 @@ register unsigned long current_stack_pointer __asm__("$sp"); * access * - pending work-to-be-done flags are in LSW * - other flags in MSW + * + * Tell the generic TIF infrastructure which special bits loongarch supports */ -#define TIF_NEED_RESCHED 0 /* rescheduling necessary */ -#define TIF_NEED_RESCHED_LAZY 1 /* lazy rescheduling necessary */ -#define TIF_SIGPENDING 2 /* signal pending */ -#define TIF_NOTIFY_RESUME 3 /* callback before returning to user */ -#define TIF_NOTIFY_SIGNAL 4 /* signal notifications exist */ -#define TIF_RESTORE_SIGMASK 5 /* restore signal mask in do_signal() */ -#define TIF_NOHZ 6 /* in adaptive nohz mode */ -#define TIF_UPROBE 7 /* breakpointed or singlestepping */ -#define TIF_USEDFPU 8 /* FPU was used by this task this quantum (SMP) */ -#define TIF_USEDSIMD 9 /* SIMD has been used this quantum */ -#define TIF_MEMDIE 10 /* is terminating due to OOM killer */ -#define TIF_FIXADE 11 /* Fix address errors in software */ -#define TIF_LOGADE 12 /* Log address errors to syslog */ -#define TIF_32BIT_REGS 13 /* 32-bit general purpose registers */ -#define TIF_32BIT_ADDR 14 /* 32-bit address space */ -#define TIF_LOAD_WATCH 15 /* If set, load watch registers */ -#define TIF_SINGLESTEP 16 /* Single Step */ -#define TIF_LSX_CTX_LIVE 17 /* LSX context must be preserved */ -#define TIF_LASX_CTX_LIVE 18 /* LASX context must be preserved */ -#define TIF_USEDLBT 19 /* LBT was used by this task this quantum (SMP) */ -#define TIF_LBT_CTX_LIVE 20 /* LBT context must be preserved */ -#define TIF_PATCH_PENDING 21 /* pending live patching update */ +#define HAVE_TIF_NEED_RESCHED_LAZY +#define HAVE_TIF_RESTORE_SIGMASK + +#include <asm-generic/thread_info_tif.h> + +/* Architecture specific bits */ +#define TIF_NOHZ 16 /* in adaptive nohz mode */ +#define TIF_USEDFPU 17 /* FPU was used by this task this quantum (SMP) */ +#define TIF_USEDSIMD 18 /* SIMD has been used this quantum */ +#define TIF_FIXADE 19 /* Fix address errors in software */ +#define TIF_LOGADE 20 /* Log address errors to syslog */ +#define TIF_32BIT_REGS 21 /* 32-bit general purpose registers */ +#define TIF_32BIT_ADDR 22 /* 32-bit address space */ +#define TIF_LOAD_WATCH 23 /* If set, load watch registers */ +#define TIF_SINGLESTEP 24 /* Single Step */ +#define TIF_LSX_CTX_LIVE 25 /* LSX context must be preserved */ +#define TIF_LASX_CTX_LIVE 26 /* LASX context must be preserved */ +#define TIF_USEDLBT 27 /* LBT was used by this task this quantum (SMP) */ +#define TIF_LBT_CTX_LIVE 28 /* LBT context must be preserved */ -#define _TIF_NEED_RESCHED (1<<TIF_NEED_RESCHED) -#define _TIF_NEED_RESCHED_LAZY (1<<TIF_NEED_RESCHED_LAZY) -#define _TIF_SIGPENDING (1<<TIF_SIGPENDING) -#define _TIF_NOTIFY_RESUME (1<<TIF_NOTIFY_RESUME) -#define _TIF_NOTIFY_SIGNAL (1<<TIF_NOTIFY_SIGNAL) -#define _TIF_NOHZ (1<<TIF_NOHZ) -#define _TIF_UPROBE (1<<TIF_UPROBE) -#define _TIF_USEDFPU (1<<TIF_USEDFPU) -#define _TIF_USEDSIMD (1<<TIF_USEDSIMD) -#define _TIF_FIXADE (1<<TIF_FIXADE) -#define _TIF_LOGADE (1<<TIF_LOGADE) -#define _TIF_32BIT_REGS (1<<TIF_32BIT_REGS) -#define _TIF_32BIT_ADDR (1<<TIF_32BIT_ADDR) -#define _TIF_LOAD_WATCH (1<<TIF_LOAD_WATCH) -#define _TIF_SINGLESTEP (1<<TIF_SINGLESTEP) -#define _TIF_LSX_CTX_LIVE (1<<TIF_LSX_CTX_LIVE) -#define _TIF_LASX_CTX_LIVE (1<<TIF_LASX_CTX_LIVE) -#define _TIF_USEDLBT (1<<TIF_USEDLBT) -#define _TIF_LBT_CTX_LIVE (1<<TIF_LBT_CTX_LIVE) -#define _TIF_PATCH_PENDING (1<<TIF_PATCH_PENDING) +#define _TIF_NOHZ BIT(TIF_NOHZ) +#define _TIF_USEDFPU BIT(TIF_USEDFPU) +#define _TIF_USEDSIMD BIT(TIF_USEDSIMD) +#define _TIF_FIXADE BIT(TIF_FIXADE) +#define _TIF_LOGADE BIT(TIF_LOGADE) +#define _TIF_32BIT_REGS BIT(TIF_32BIT_REGS) +#define _TIF_32BIT_ADDR BIT(TIF_32BIT_ADDR) +#define _TIF_LOAD_WATCH BIT(TIF_LOAD_WATCH) +#define _TIF_SINGLESTEP BIT(TIF_SINGLESTEP) +#define _TIF_LSX_CTX_LIVE BIT(TIF_LSX_CTX_LIVE) +#define _TIF_LASX_CTX_LIVE BIT(TIF_LASX_CTX_LIVE) +#define _TIF_USEDLBT BIT(TIF_USEDLBT) +#define _TIF_LBT_CTX_LIVE BIT(TIF_LBT_CTX_LIVE) #endif /* __KERNEL__ */ #endif /* _ASM_THREAD_INFO_H */ diff --git a/arch/loongarch/include/asm/timex.h b/arch/loongarch/include/asm/timex.h index fb41e9e7a222..9ea52fad9690 100644 --- a/arch/loongarch/include/asm/timex.h +++ b/arch/loongarch/include/asm/timex.h @@ -18,7 +18,38 @@ typedef unsigned long cycles_t; static inline cycles_t get_cycles(void) { - return drdtime(); +#ifdef CONFIG_32BIT + return rdtime_l(); +#else + return rdtime_d(); +#endif +} + +#ifdef CONFIG_32BIT + +#define get_cycles_hi get_cycles_hi + +static inline cycles_t get_cycles_hi(void) +{ + return rdtime_h(); +} + +#endif + +static inline u64 get_cycles64(void) +{ +#ifdef CONFIG_32BIT + u32 hi, lo; + + do { + hi = rdtime_h(); + lo = rdtime_l(); + } while (hi != rdtime_h()); + + return ((u64)hi << 32) | lo; +#else + return rdtime_d(); +#endif } #endif /* __KERNEL__ */ diff --git a/arch/loongarch/include/asm/topology.h b/arch/loongarch/include/asm/topology.h index 50273c9187d0..6b79d6183085 100644 --- a/arch/loongarch/include/asm/topology.h +++ b/arch/loongarch/include/asm/topology.h @@ -12,24 +12,29 @@ extern cpumask_t cpus_on_node[]; -#define cpumask_of_node(node) (&cpus_on_node[node]) +#define cpumask_of_node(node) ((node) == NUMA_NO_NODE ? cpu_all_mask : &cpus_on_node[node]) struct pci_bus; extern int pcibus_to_node(struct pci_bus *); #define cpumask_of_pcibus(bus) (cpu_online_mask) -extern unsigned char node_distances[MAX_NUMNODES][MAX_NUMNODES]; - -void numa_set_distance(int from, int to, int distance); - -#define node_distance(from, to) (node_distances[(from)][(to)]) +int __node_distance(int from, int to); +#define node_distance(from, to) __node_distance(from, to) #else #define pcibus_to_node(bus) 0 #endif #ifdef CONFIG_SMP +/* + * Return cpus that shares the last level cache. + */ +static inline const struct cpumask *cpu_coregroup_mask(int cpu) +{ + return &cpu_llc_shared_map[cpu]; +} + #define topology_physical_package_id(cpu) (cpu_data[cpu].package) #define topology_core_id(cpu) (cpu_data[cpu].core) #define topology_core_cpumask(cpu) (&cpu_core_map[cpu]) diff --git a/arch/loongarch/include/asm/types.h b/arch/loongarch/include/asm/types.h index baf15a0dcf8b..0edd731f3d6a 100644 --- a/arch/loongarch/include/asm/types.h +++ b/arch/loongarch/include/asm/types.h @@ -8,7 +8,7 @@ #include <asm-generic/int-ll64.h> #include <uapi/asm/types.h> -#ifdef __ASSEMBLY__ +#ifdef __ASSEMBLER__ #define _ULCAST_ #define _U64CAST_ #else diff --git a/arch/loongarch/include/asm/uaccess.h b/arch/loongarch/include/asm/uaccess.h index 0d22991ae430..438269313e78 100644 --- a/arch/loongarch/include/asm/uaccess.h +++ b/arch/loongarch/include/asm/uaccess.h @@ -19,10 +19,16 @@ #include <asm/asm-extable.h> #include <asm-generic/access_ok.h> +#define __LSW 0 +#define __MSW 1 + extern u64 __ua_limit; -#define __UA_ADDR ".dword" +#ifdef CONFIG_64BIT #define __UA_LIMIT __ua_limit +#else +#define __UA_LIMIT 0x80000000UL +#endif /* * get_user: - Get a simple variable from user space. @@ -126,6 +132,7 @@ extern u64 __ua_limit; * * Returns zero on success, or -EFAULT on error. */ + #define __put_user(x, ptr) \ ({ \ int __pu_err = 0; \ @@ -146,7 +153,7 @@ do { \ case 1: __get_data_asm(val, "ld.b", ptr); break; \ case 2: __get_data_asm(val, "ld.h", ptr); break; \ case 4: __get_data_asm(val, "ld.w", ptr); break; \ - case 8: __get_data_asm(val, "ld.d", ptr); break; \ + case 8: __get_data_asm_8(val, ptr); break; \ default: BUILD_BUG(); break; \ } \ } while (0) @@ -167,13 +174,39 @@ do { \ (val) = (__typeof__(*(ptr))) __gu_tmp; \ } +#ifdef CONFIG_64BIT +#define __get_data_asm_8(val, ptr) \ + __get_data_asm(val, "ld.d", ptr) +#else /* !CONFIG_64BIT */ +#define __get_data_asm_8(val, ptr) \ +{ \ + u32 __lo, __hi; \ + u32 __user *__ptr = (u32 __user *)(ptr); \ + \ + __asm__ __volatile__ ( \ + "1:\n" \ + " ld.w %1, %3 \n" \ + "2:\n" \ + " ld.w %2, %4 \n" \ + "3:\n" \ + _ASM_EXTABLE_UACCESS_ERR_ZERO(1b, 3b, %0, %1) \ + _ASM_EXTABLE_UACCESS_ERR_ZERO(2b, 3b, %0, %1) \ + : "+r" (__gu_err), "=&r" (__lo), "=r" (__hi) \ + : "m" (__ptr[__LSW]), "m" (__ptr[__MSW])); \ + if (__gu_err) \ + __hi = 0; \ + (val) = (__typeof__(val))((__typeof__((val)-(val))) \ + ((((u64)__hi << 32) | __lo))); \ +} +#endif /* CONFIG_64BIT */ + #define __put_user_common(ptr, size) \ do { \ switch (size) { \ case 1: __put_data_asm("st.b", ptr); break; \ case 2: __put_data_asm("st.h", ptr); break; \ case 4: __put_data_asm("st.w", ptr); break; \ - case 8: __put_data_asm("st.d", ptr); break; \ + case 8: __put_data_asm_8(ptr); break; \ default: BUILD_BUG(); break; \ } \ } while (0) @@ -190,14 +223,43 @@ do { \ : "Jr" (__pu_val)); \ } +#ifdef CONFIG_64BIT +#define __put_data_asm_8(ptr) \ + __put_data_asm("st.d", ptr) +#else /* !CONFIG_64BIT */ +#define __put_data_asm_8(ptr) \ +{ \ + u32 __user *__ptr = (u32 __user *)(ptr); \ + u64 __x = (__typeof__((__pu_val)-(__pu_val)))(__pu_val); \ + \ + __asm__ __volatile__ ( \ + "1:\n" \ + " st.w %z3, %1 \n" \ + "2:\n" \ + " st.w %z4, %2 \n" \ + "3:\n" \ + _ASM_EXTABLE_UACCESS_ERR(1b, 3b, %0) \ + _ASM_EXTABLE_UACCESS_ERR(2b, 3b, %0) \ + : "+r" (__pu_err), \ + "=m" (__ptr[__LSW]), \ + "=m" (__ptr[__MSW]) \ + : "rJ" (__x), "rJ" (__x >> 32)); \ +} +#endif /* CONFIG_64BIT */ + #define __get_kernel_nofault(dst, src, type, err_label) \ do { \ int __gu_err = 0; \ \ __get_kernel_common(*((type *)(dst)), sizeof(type), \ (__force type *)(src)); \ - if (unlikely(__gu_err)) \ + if (unlikely(__gu_err)) { \ + pr_info("%s: memory access failed, ecode 0x%x\n", \ + __func__, read_csr_excode()); \ + pr_info("%s: the caller is %pS\n", \ + __func__, __builtin_return_address(0)); \ goto err_label; \ + } \ } while (0) #define __put_kernel_nofault(dst, src, type, err_label) \ @@ -207,8 +269,13 @@ do { \ \ __pu_val = *(__force type *)(src); \ __put_kernel_common(((type *)(dst)), sizeof(type)); \ - if (unlikely(__pu_err)) \ + if (unlikely(__pu_err)) { \ + pr_info("%s: memory access failed, ecode 0x%x\n", \ + __func__, read_csr_excode()); \ + pr_info("%s: the caller is %pS\n", \ + __func__, __builtin_return_address(0)); \ goto err_label; \ + } \ } while (0) extern unsigned long __copy_user(void *to, const void *from, __kernel_size_t n); diff --git a/arch/loongarch/include/asm/unistd.h b/arch/loongarch/include/asm/unistd.h index e2c0f3d86c7b..e7649c158248 100644 --- a/arch/loongarch/include/asm/unistd.h +++ b/arch/loongarch/include/asm/unistd.h @@ -10,5 +10,6 @@ #define __ARCH_WANT_NEW_STAT #define __ARCH_WANT_SYS_CLONE +#define __ARCH_WANT_MEMFD_SECRET #define NR_syscalls (__NR_syscalls) diff --git a/arch/loongarch/include/asm/unwind_hints.h b/arch/loongarch/include/asm/unwind_hints.h index a01086ad9dde..16c7f7e465a0 100644 --- a/arch/loongarch/include/asm/unwind_hints.h +++ b/arch/loongarch/include/asm/unwind_hints.h @@ -5,7 +5,7 @@ #include <linux/objtool.h> #include <asm/orc_types.h> -#ifdef __ASSEMBLY__ +#ifdef __ASSEMBLER__ .macro UNWIND_HINT_UNDEFINED UNWIND_HINT type=UNWIND_HINT_TYPE_UNDEFINED @@ -23,6 +23,14 @@ UNWIND_HINT sp_reg=ORC_REG_SP type=UNWIND_HINT_TYPE_CALL .endm -#endif /* __ASSEMBLY__ */ +#else /* !__ASSEMBLER__ */ + +#define UNWIND_HINT_SAVE \ + UNWIND_HINT(UNWIND_HINT_TYPE_SAVE, 0, 0, 0) + +#define UNWIND_HINT_RESTORE \ + UNWIND_HINT(UNWIND_HINT_TYPE_RESTORE, 0, 0, 0) + +#endif /* !__ASSEMBLER__ */ #endif /* _ASM_LOONGARCH_UNWIND_HINTS_H */ diff --git a/arch/loongarch/include/asm/uprobes.h b/arch/loongarch/include/asm/uprobes.h index 99a0d198927f..025fc3f0a102 100644 --- a/arch/loongarch/include/asm/uprobes.h +++ b/arch/loongarch/include/asm/uprobes.h @@ -15,7 +15,6 @@ typedef u32 uprobe_opcode_t; #define UPROBE_XOLBP_INSN __emit_break(BRK_UPROBE_XOLBP) struct arch_uprobe { - unsigned long resume_era; u32 insn[2]; u32 ixol[2]; bool simulate; diff --git a/arch/loongarch/include/asm/vdso.h b/arch/loongarch/include/asm/vdso.h index d3ba35eb23e7..f72ec79e2dde 100644 --- a/arch/loongarch/include/asm/vdso.h +++ b/arch/loongarch/include/asm/vdso.h @@ -31,7 +31,6 @@ struct loongarch_vdso_info { unsigned long size; unsigned long offset_sigreturn; struct vm_special_mapping code_mapping; - struct vm_special_mapping data_mapping; }; extern struct loongarch_vdso_info vdso_info; diff --git a/arch/loongarch/include/asm/vdso/arch_data.h b/arch/loongarch/include/asm/vdso/arch_data.h new file mode 100644 index 000000000000..395ec223bcbe --- /dev/null +++ b/arch/loongarch/include/asm/vdso/arch_data.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Author: Huacai Chen <chenhuacai@loongson.cn> + * Copyright (C) 2020-2022 Loongson Technology Corporation Limited + */ + +#ifndef _VDSO_ARCH_DATA_H +#define _VDSO_ARCH_DATA_H + +#ifndef __ASSEMBLER__ + +#include <asm/asm.h> +#include <asm/vdso.h> + +struct vdso_pcpu_data { + u32 node; +} ____cacheline_aligned_in_smp; + +struct vdso_arch_data { + struct vdso_pcpu_data pdata[NR_CPUS]; +}; + +#endif /* __ASSEMBLER__ */ + +#endif diff --git a/arch/loongarch/include/asm/vdso/getrandom.h b/arch/loongarch/include/asm/vdso/getrandom.h index e80f3c4ac748..2ff05003c6e7 100644 --- a/arch/loongarch/include/asm/vdso/getrandom.h +++ b/arch/loongarch/include/asm/vdso/getrandom.h @@ -5,7 +5,7 @@ #ifndef __ASM_VDSO_GETRANDOM_H #define __ASM_VDSO_GETRANDOM_H -#ifndef __ASSEMBLY__ +#ifndef __ASSEMBLER__ #include <asm/unistd.h> #include <asm/vdso/vdso.h> @@ -20,7 +20,7 @@ static __always_inline ssize_t getrandom_syscall(void *_buffer, size_t _len, uns asm volatile( " syscall 0\n" - : "+r" (ret) + : "=r" (ret) : "r" (nr), "r" (buffer), "r" (len), "r" (flags) : "$t0", "$t1", "$t2", "$t3", "$t4", "$t5", "$t6", "$t7", "$t8", "memory"); @@ -28,11 +28,6 @@ static __always_inline ssize_t getrandom_syscall(void *_buffer, size_t _len, uns return ret; } -static __always_inline const struct vdso_rng_data *__arch_get_vdso_rng_data(void) -{ - return &_loongarch_data.rng_data; -} - -#endif /* !__ASSEMBLY__ */ +#endif /* !__ASSEMBLER__ */ #endif /* __ASM_VDSO_GETRANDOM_H */ diff --git a/arch/loongarch/include/asm/vdso/gettimeofday.h b/arch/loongarch/include/asm/vdso/gettimeofday.h index 7eb3f041af76..18ba403e1ed9 100644 --- a/arch/loongarch/include/asm/vdso/gettimeofday.h +++ b/arch/loongarch/include/asm/vdso/gettimeofday.h @@ -7,11 +7,13 @@ #ifndef __ASM_VDSO_GETTIMEOFDAY_H #define __ASM_VDSO_GETTIMEOFDAY_H -#ifndef __ASSEMBLY__ +#ifndef __ASSEMBLER__ #include <asm/unistd.h> #include <asm/vdso/vdso.h> +#ifdef CONFIG_GENERIC_GETTIMEOFDAY + #define VDSO_HAS_CLOCK_GETRES 1 static __always_inline long gettimeofday_fallback( @@ -25,7 +27,7 @@ static __always_inline long gettimeofday_fallback( asm volatile( " syscall 0\n" - : "+r" (ret) + : "=r" (ret) : "r" (nr), "r" (tv), "r" (tz) : "$t0", "$t1", "$t2", "$t3", "$t4", "$t5", "$t6", "$t7", "$t8", "memory"); @@ -44,7 +46,7 @@ static __always_inline long clock_gettime_fallback( asm volatile( " syscall 0\n" - : "+r" (ret) + : "=r" (ret) : "r" (nr), "r" (clkid), "r" (ts) : "$t0", "$t1", "$t2", "$t3", "$t4", "$t5", "$t6", "$t7", "$t8", "memory"); @@ -63,7 +65,7 @@ static __always_inline int clock_getres_fallback( asm volatile( " syscall 0\n" - : "+r" (ret) + : "=r" (ret) : "r" (nr), "r" (clkid), "r" (ts) : "$t0", "$t1", "$t2", "$t3", "$t4", "$t5", "$t6", "$t7", "$t8", "memory"); @@ -72,7 +74,7 @@ static __always_inline int clock_getres_fallback( } static __always_inline u64 __arch_get_hw_counter(s32 clock_mode, - const struct vdso_data *vd) + const struct vdso_time_data *vd) { uint64_t count; @@ -83,24 +85,8 @@ static __always_inline u64 __arch_get_hw_counter(s32 clock_mode, return count; } -static inline bool loongarch_vdso_hres_capable(void) -{ - return true; -} -#define __arch_vdso_hres_capable loongarch_vdso_hres_capable - -static __always_inline const struct vdso_data *__arch_get_vdso_data(void) -{ - return _vdso_data; -} +#endif /* CONFIG_GENERIC_GETTIMEOFDAY */ -#ifdef CONFIG_TIME_NS -static __always_inline -const struct vdso_data *__arch_get_timens_vdso_data(const struct vdso_data *vd) -{ - return _timens_data; -} -#endif -#endif /* !__ASSEMBLY__ */ +#endif /* !__ASSEMBLER__ */ #endif /* __ASM_VDSO_GETTIMEOFDAY_H */ diff --git a/arch/loongarch/include/asm/vdso/processor.h b/arch/loongarch/include/asm/vdso/processor.h index ef5770b343a0..1e255373b0b8 100644 --- a/arch/loongarch/include/asm/vdso/processor.h +++ b/arch/loongarch/include/asm/vdso/processor.h @@ -5,10 +5,10 @@ #ifndef __ASM_VDSO_PROCESSOR_H #define __ASM_VDSO_PROCESSOR_H -#ifndef __ASSEMBLY__ +#ifndef __ASSEMBLER__ #define cpu_relax() barrier() -#endif /* __ASSEMBLY__ */ +#endif /* __ASSEMBLER__ */ #endif /* __ASM_VDSO_PROCESSOR_H */ diff --git a/arch/loongarch/include/asm/vdso/vdso.h b/arch/loongarch/include/asm/vdso/vdso.h index 1c183a9b2115..04bd2d452876 100644 --- a/arch/loongarch/include/asm/vdso/vdso.h +++ b/arch/loongarch/include/asm/vdso/vdso.h @@ -7,49 +7,15 @@ #ifndef _ASM_VDSO_VDSO_H #define _ASM_VDSO_VDSO_H -#ifndef __ASSEMBLY__ +#ifndef __ASSEMBLER__ #include <asm/asm.h> #include <asm/page.h> #include <asm/vdso.h> +#include <vdso/datapage.h> -struct vdso_pcpu_data { - u32 node; -} ____cacheline_aligned_in_smp; +#define VVAR_SIZE (VDSO_NR_PAGES << PAGE_SHIFT) -struct loongarch_vdso_data { - struct vdso_pcpu_data pdata[NR_CPUS]; - struct vdso_rng_data rng_data; -}; - -/* - * The layout of vvar: - * - * high - * +---------------------+--------------------------+ - * | loongarch vdso data | LOONGARCH_VDSO_DATA_SIZE | - * +---------------------+--------------------------+ - * | time-ns vdso data | PAGE_SIZE | - * +---------------------+--------------------------+ - * | generic vdso data | PAGE_SIZE | - * +---------------------+--------------------------+ - * low - */ -#define LOONGARCH_VDSO_DATA_SIZE PAGE_ALIGN(sizeof(struct loongarch_vdso_data)) -#define LOONGARCH_VDSO_DATA_PAGES (LOONGARCH_VDSO_DATA_SIZE >> PAGE_SHIFT) - -enum vvar_pages { - VVAR_GENERIC_PAGE_OFFSET, - VVAR_TIMENS_PAGE_OFFSET, - VVAR_LOONGARCH_PAGES_START, - VVAR_LOONGARCH_PAGES_END = VVAR_LOONGARCH_PAGES_START + LOONGARCH_VDSO_DATA_PAGES - 1, - VVAR_NR_PAGES, -}; - -#define VVAR_SIZE (VVAR_NR_PAGES << PAGE_SHIFT) - -extern struct loongarch_vdso_data _loongarch_data __attribute__((visibility("hidden"))); - -#endif /* __ASSEMBLY__ */ +#endif /* __ASSEMBLER__ */ #endif diff --git a/arch/loongarch/include/asm/vdso/vsyscall.h b/arch/loongarch/include/asm/vdso/vsyscall.h index 8987e951d0a9..558eb9dfda52 100644 --- a/arch/loongarch/include/asm/vdso/vsyscall.h +++ b/arch/loongarch/include/asm/vdso/vsyscall.h @@ -2,30 +2,13 @@ #ifndef __ASM_VDSO_VSYSCALL_H #define __ASM_VDSO_VSYSCALL_H -#ifndef __ASSEMBLY__ +#ifndef __ASSEMBLER__ #include <vdso/datapage.h> -extern struct vdso_data *vdso_data; -extern struct vdso_rng_data *vdso_rng_data; - -static __always_inline -struct vdso_data *__loongarch_get_k_vdso_data(void) -{ - return vdso_data; -} -#define __arch_get_k_vdso_data __loongarch_get_k_vdso_data - -static __always_inline -struct vdso_rng_data *__loongarch_get_k_vdso_rng_data(void) -{ - return vdso_rng_data; -} -#define __arch_get_k_vdso_rng_data __loongarch_get_k_vdso_rng_data - /* The asm-generic header needs to be included after the definitions above */ #include <asm-generic/vdso/vsyscall.h> -#endif /* !__ASSEMBLY__ */ +#endif /* !__ASSEMBLER__ */ #endif /* __ASM_VDSO_VSYSCALL_H */ diff --git a/arch/loongarch/include/asm/xor.h b/arch/loongarch/include/asm/xor.h deleted file mode 100644 index 12467fffee46..000000000000 --- a/arch/loongarch/include/asm/xor.h +++ /dev/null @@ -1,68 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * Copyright (C) 2023 WANG Xuerui <git@xen0n.name> - */ -#ifndef _ASM_LOONGARCH_XOR_H -#define _ASM_LOONGARCH_XOR_H - -#include <asm/cpu-features.h> -#include <asm/xor_simd.h> - -#ifdef CONFIG_CPU_HAS_LSX -static struct xor_block_template xor_block_lsx = { - .name = "lsx", - .do_2 = xor_lsx_2, - .do_3 = xor_lsx_3, - .do_4 = xor_lsx_4, - .do_5 = xor_lsx_5, -}; - -#define XOR_SPEED_LSX() \ - do { \ - if (cpu_has_lsx) \ - xor_speed(&xor_block_lsx); \ - } while (0) -#else /* CONFIG_CPU_HAS_LSX */ -#define XOR_SPEED_LSX() -#endif /* CONFIG_CPU_HAS_LSX */ - -#ifdef CONFIG_CPU_HAS_LASX -static struct xor_block_template xor_block_lasx = { - .name = "lasx", - .do_2 = xor_lasx_2, - .do_3 = xor_lasx_3, - .do_4 = xor_lasx_4, - .do_5 = xor_lasx_5, -}; - -#define XOR_SPEED_LASX() \ - do { \ - if (cpu_has_lasx) \ - xor_speed(&xor_block_lasx); \ - } while (0) -#else /* CONFIG_CPU_HAS_LASX */ -#define XOR_SPEED_LASX() -#endif /* CONFIG_CPU_HAS_LASX */ - -/* - * For grins, also test the generic routines. - * - * More importantly: it cannot be ruled out at this point of time, that some - * future (maybe reduced) models could run the vector algorithms slower than - * the scalar ones, maybe for errata or micro-op reasons. It may be - * appropriate to revisit this after one or two more uarch generations. - */ -#include <asm-generic/xor.h> - -#undef XOR_TRY_TEMPLATES -#define XOR_TRY_TEMPLATES \ -do { \ - xor_speed(&xor_block_8regs); \ - xor_speed(&xor_block_8regs_p); \ - xor_speed(&xor_block_32regs); \ - xor_speed(&xor_block_32regs_p); \ - XOR_SPEED_LSX(); \ - XOR_SPEED_LASX(); \ -} while (0) - -#endif /* _ASM_LOONGARCH_XOR_H */ diff --git a/arch/loongarch/include/asm/xor_simd.h b/arch/loongarch/include/asm/xor_simd.h deleted file mode 100644 index 471b96332f38..000000000000 --- a/arch/loongarch/include/asm/xor_simd.h +++ /dev/null @@ -1,34 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * Copyright (C) 2023 WANG Xuerui <git@xen0n.name> - */ -#ifndef _ASM_LOONGARCH_XOR_SIMD_H -#define _ASM_LOONGARCH_XOR_SIMD_H - -#ifdef CONFIG_CPU_HAS_LSX -void xor_lsx_2(unsigned long bytes, unsigned long * __restrict p1, - const unsigned long * __restrict p2); -void xor_lsx_3(unsigned long bytes, unsigned long * __restrict p1, - const unsigned long * __restrict p2, const unsigned long * __restrict p3); -void xor_lsx_4(unsigned long bytes, unsigned long * __restrict p1, - const unsigned long * __restrict p2, const unsigned long * __restrict p3, - const unsigned long * __restrict p4); -void xor_lsx_5(unsigned long bytes, unsigned long * __restrict p1, - const unsigned long * __restrict p2, const unsigned long * __restrict p3, - const unsigned long * __restrict p4, const unsigned long * __restrict p5); -#endif /* CONFIG_CPU_HAS_LSX */ - -#ifdef CONFIG_CPU_HAS_LASX -void xor_lasx_2(unsigned long bytes, unsigned long * __restrict p1, - const unsigned long * __restrict p2); -void xor_lasx_3(unsigned long bytes, unsigned long * __restrict p1, - const unsigned long * __restrict p2, const unsigned long * __restrict p3); -void xor_lasx_4(unsigned long bytes, unsigned long * __restrict p1, - const unsigned long * __restrict p2, const unsigned long * __restrict p3, - const unsigned long * __restrict p4); -void xor_lasx_5(unsigned long bytes, unsigned long * __restrict p1, - const unsigned long * __restrict p2, const unsigned long * __restrict p3, - const unsigned long * __restrict p4, const unsigned long * __restrict p5); -#endif /* CONFIG_CPU_HAS_LASX */ - -#endif /* _ASM_LOONGARCH_XOR_SIMD_H */ diff --git a/arch/loongarch/include/uapi/asm/Kbuild b/arch/loongarch/include/uapi/asm/Kbuild index 517761419999..89ac01faa5ae 100644 --- a/arch/loongarch/include/uapi/asm/Kbuild +++ b/arch/loongarch/include/uapi/asm/Kbuild @@ -1,2 +1,3 @@ # SPDX-License-Identifier: GPL-2.0 +syscall-y += unistd_32.h syscall-y += unistd_64.h diff --git a/arch/loongarch/include/uapi/asm/hwcap.h b/arch/loongarch/include/uapi/asm/hwcap.h index 2b34e56cfa9e..90e96113ba51 100644 --- a/arch/loongarch/include/uapi/asm/hwcap.h +++ b/arch/loongarch/include/uapi/asm/hwcap.h @@ -18,5 +18,7 @@ #define HWCAP_LOONGARCH_LBT_MIPS (1 << 12) #define HWCAP_LOONGARCH_PTW (1 << 13) #define HWCAP_LOONGARCH_LSPW (1 << 14) +#define HWCAP_LOONGARCH_SCQ (1 << 15) +#define HWCAP_LOONGARCH_LAM_BH (1 << 16) #endif /* _UAPI_ASM_HWCAP_H */ diff --git a/arch/loongarch/include/uapi/asm/kvm.h b/arch/loongarch/include/uapi/asm/kvm.h index 5f354f5c6847..cd0b5c11ca9c 100644 --- a/arch/loongarch/include/uapi/asm/kvm.h +++ b/arch/loongarch/include/uapi/asm/kvm.h @@ -103,6 +103,9 @@ struct kvm_fpu { #define KVM_LOONGARCH_VM_FEAT_PMU 5 #define KVM_LOONGARCH_VM_FEAT_PV_IPI 6 #define KVM_LOONGARCH_VM_FEAT_PV_STEALTIME 7 +#define KVM_LOONGARCH_VM_FEAT_PTW 8 +#define KVM_LOONGARCH_VM_FEAT_MSGINT 9 +#define KVM_LOONGARCH_VM_FEAT_PV_PREEMPT 10 /* Device Control API on vcpu fd */ #define KVM_LOONGARCH_VCPU_CPUCFG 0 @@ -152,4 +155,8 @@ struct kvm_iocsr_entry { #define KVM_DEV_LOONGARCH_PCH_PIC_GRP_CTRL 0x40000006 #define KVM_DEV_LOONGARCH_PCH_PIC_CTRL_INIT 0 +#define KVM_DEV_LOONGARCH_DMSINTC_GRP_CTRL 0x40000007 +#define KVM_DEV_LOONGARCH_DMSINTC_MSG_ADDR_BASE 0x0 +#define KVM_DEV_LOONGARCH_DMSINTC_MSG_ADDR_SIZE 0x1 + #endif /* __UAPI_ASM_LOONGARCH_KVM_H */ diff --git a/arch/loongarch/include/uapi/asm/kvm_para.h b/arch/loongarch/include/uapi/asm/kvm_para.h index 76d802ef01ce..d28cbcadd276 100644 --- a/arch/loongarch/include/uapi/asm/kvm_para.h +++ b/arch/loongarch/include/uapi/asm/kvm_para.h @@ -15,6 +15,7 @@ #define CPUCFG_KVM_FEATURE (CPUCFG_KVM_BASE + 4) #define KVM_FEATURE_IPI 1 #define KVM_FEATURE_STEAL_TIME 2 +#define KVM_FEATURE_PREEMPT 3 /* BIT 24 - 31 are features configurable by user space vmm */ #define KVM_FEATURE_VIRT_EXTIOI 24 #define KVM_FEATURE_USER_HCALL 25 diff --git a/arch/loongarch/include/uapi/asm/ptrace.h b/arch/loongarch/include/uapi/asm/ptrace.h index aafb3cd9e943..b35c794323bc 100644 --- a/arch/loongarch/include/uapi/asm/ptrace.h +++ b/arch/loongarch/include/uapi/asm/ptrace.h @@ -10,10 +10,6 @@ #include <linux/types.h> -#ifndef __KERNEL__ -#include <stdint.h> -#endif - /* * For PTRACE_{POKE,PEEK}USR. 0 - 31 are GPRs, * 32 is syscall's original ARG0, 33 is PC, 34 is BADVADDR. @@ -41,44 +37,54 @@ struct user_pt_regs { } __attribute__((aligned(8))); struct user_fp_state { - uint64_t fpr[32]; - uint64_t fcc; - uint32_t fcsr; + __u64 fpr[32]; + __u64 fcc; + __u32 fcsr; }; struct user_lsx_state { /* 32 registers, 128 bits width per register. */ - uint64_t vregs[32*2]; + __u64 vregs[32*2]; }; struct user_lasx_state { /* 32 registers, 256 bits width per register. */ - uint64_t vregs[32*4]; + __u64 vregs[32*4]; }; struct user_lbt_state { - uint64_t scr[4]; - uint32_t eflags; - uint32_t ftop; + __u64 scr[4]; + __u32 eflags; + __u32 ftop; }; struct user_watch_state { - uint64_t dbg_info; + __u64 dbg_info; struct { - uint64_t addr; - uint64_t mask; - uint32_t ctrl; - uint32_t pad; +#if __BITS_PER_LONG == 32 + __u32 addr; + __u32 mask; +#else + __u64 addr; + __u64 mask; +#endif + __u32 ctrl; + __u32 pad; } dbg_regs[8]; }; struct user_watch_state_v2 { - uint64_t dbg_info; + __u64 dbg_info; struct { - uint64_t addr; - uint64_t mask; - uint32_t ctrl; - uint32_t pad; +#if __BITS_PER_LONG == 32 + __u32 addr; + __u32 mask; +#else + __u64 addr; + __u64 mask; +#endif + __u32 ctrl; + __u32 pad; } dbg_regs[14]; }; diff --git a/arch/loongarch/include/uapi/asm/setup.h b/arch/loongarch/include/uapi/asm/setup.h new file mode 100644 index 000000000000..d46363ce3e02 --- /dev/null +++ b/arch/loongarch/include/uapi/asm/setup.h @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ + +#ifndef _UAPI_ASM_LOONGARCH_SETUP_H +#define _UAPI_ASM_LOONGARCH_SETUP_H + +#define COMMAND_LINE_SIZE 4096 + +#endif /* _UAPI_ASM_LOONGARCH_SETUP_H */ diff --git a/arch/loongarch/include/uapi/asm/unistd.h b/arch/loongarch/include/uapi/asm/unistd.h index 1f01980f9c94..e19c7f2f9f87 100644 --- a/arch/loongarch/include/uapi/asm/unistd.h +++ b/arch/loongarch/include/uapi/asm/unistd.h @@ -1,3 +1,9 @@ /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#include <asm/bitsperlong.h> + +#if __BITS_PER_LONG == 32 +#include <asm/unistd_32.h> +#else #include <asm/unistd_64.h> +#endif |