diff options
Diffstat (limited to 'arch/loongarch')
30 files changed, 277 insertions, 427 deletions
diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig index b57daee98b89..62b5b07fa4e1 100644 --- a/arch/loongarch/Kconfig +++ b/arch/loongarch/Kconfig @@ -69,7 +69,6 @@ config LOONGARCH select GENERIC_TIME_VSYSCALL select GPIOLIB select HAVE_ARCH_AUDITSYSCALL - select HAVE_ARCH_COMPILER_H select HAVE_ARCH_MMAP_RND_BITS if MMU select HAVE_ARCH_SECCOMP_FILTER select HAVE_ARCH_TRACEHOOK diff --git a/arch/loongarch/include/asm/asmmacro.h b/arch/loongarch/include/asm/asmmacro.h index a1a04083bd67..be037a40580d 100644 --- a/arch/loongarch/include/asm/asmmacro.h +++ b/arch/loongarch/include/asm/asmmacro.h @@ -274,16 +274,4 @@ nor \dst, \src, zero .endm -.macro bgt r0 r1 label - blt \r1, \r0, \label -.endm - -.macro bltz r0 label - blt \r0, zero, \label -.endm - -.macro bgez r0 label - bge \r0, zero, \label -.endm - #endif /* _ASM_ASMMACRO_H */ diff --git a/arch/loongarch/include/asm/atomic.h b/arch/loongarch/include/asm/atomic.h index 979367ad4e2c..6b9aca9ab6e9 100644 --- a/arch/loongarch/include/asm/atomic.h +++ b/arch/loongarch/include/asm/atomic.h @@ -10,7 +10,6 @@ #include <linux/types.h> #include <asm/barrier.h> #include <asm/cmpxchg.h> -#include <asm/compiler.h> #if __SIZEOF_LONG__ == 4 #define __LL "ll.w " @@ -157,27 +156,25 @@ static inline int arch_atomic_sub_if_positive(int i, atomic_t *v) __asm__ __volatile__( "1: ll.w %1, %2 # atomic_sub_if_positive\n" " addi.w %0, %1, %3 \n" - " or %1, %0, $zero \n" - " blt %0, $zero, 2f \n" + " move %1, %0 \n" + " bltz %0, 2f \n" " sc.w %1, %2 \n" - " beq $zero, %1, 1b \n" + " beqz %1, 1b \n" "2: \n" __WEAK_LLSC_MB - : "=&r" (result), "=&r" (temp), - "+" GCC_OFF_SMALL_ASM() (v->counter) + : "=&r" (result), "=&r" (temp), "+ZC" (v->counter) : "I" (-i)); } else { __asm__ __volatile__( "1: ll.w %1, %2 # atomic_sub_if_positive\n" " sub.w %0, %1, %3 \n" - " or %1, %0, $zero \n" - " blt %0, $zero, 2f \n" + " move %1, %0 \n" + " bltz %0, 2f \n" " sc.w %1, %2 \n" - " beq $zero, %1, 1b \n" + " beqz %1, 1b \n" "2: \n" __WEAK_LLSC_MB - : "=&r" (result), "=&r" (temp), - "+" GCC_OFF_SMALL_ASM() (v->counter) + : "=&r" (result), "=&r" (temp), "+ZC" (v->counter) : "r" (i)); } @@ -320,27 +317,25 @@ static inline long arch_atomic64_sub_if_positive(long i, atomic64_t *v) __asm__ __volatile__( "1: ll.d %1, %2 # atomic64_sub_if_positive \n" " addi.d %0, %1, %3 \n" - " or %1, %0, $zero \n" - " blt %0, $zero, 2f \n" + " move %1, %0 \n" + " bltz %0, 2f \n" " sc.d %1, %2 \n" - " beq %1, $zero, 1b \n" + " beqz %1, 1b \n" "2: \n" __WEAK_LLSC_MB - : "=&r" (result), "=&r" (temp), - "+" GCC_OFF_SMALL_ASM() (v->counter) + : "=&r" (result), "=&r" (temp), "+ZC" (v->counter) : "I" (-i)); } else { __asm__ __volatile__( "1: ll.d %1, %2 # atomic64_sub_if_positive \n" " sub.d %0, %1, %3 \n" - " or %1, %0, $zero \n" - " blt %0, $zero, 2f \n" + " move %1, %0 \n" + " bltz %0, 2f \n" " sc.d %1, %2 \n" - " beq %1, $zero, 1b \n" + " beqz %1, 1b \n" "2: \n" __WEAK_LLSC_MB - : "=&r" (result), "=&r" (temp), - "+" GCC_OFF_SMALL_ASM() (v->counter) + : "=&r" (result), "=&r" (temp), "+ZC" (v->counter) : "r" (i)); } diff --git a/arch/loongarch/include/asm/barrier.h b/arch/loongarch/include/asm/barrier.h index b6517eeeb141..cda977675854 100644 --- a/arch/loongarch/include/asm/barrier.h +++ b/arch/loongarch/include/asm/barrier.h @@ -48,9 +48,9 @@ static inline unsigned long array_index_mask_nospec(unsigned long index, __asm__ __volatile__( "sltu %0, %1, %2\n\t" #if (__SIZEOF_LONG__ == 4) - "sub.w %0, $r0, %0\n\t" + "sub.w %0, $zero, %0\n\t" #elif (__SIZEOF_LONG__ == 8) - "sub.d %0, $r0, %0\n\t" + "sub.d %0, $zero, %0\n\t" #endif : "=r" (mask) : "r" (index), "r" (size) diff --git a/arch/loongarch/include/asm/cmpxchg.h b/arch/loongarch/include/asm/cmpxchg.h index 75b3a4478652..0a9b0fac1eee 100644 --- a/arch/loongarch/include/asm/cmpxchg.h +++ b/arch/loongarch/include/asm/cmpxchg.h @@ -55,9 +55,9 @@ static inline unsigned long __xchg(volatile void *ptr, unsigned long x, __asm__ __volatile__( \ "1: " ld " %0, %2 # __cmpxchg_asm \n" \ " bne %0, %z3, 2f \n" \ - " or $t0, %z4, $zero \n" \ + " move $t0, %z4 \n" \ " " st " $t0, %1 \n" \ - " beq $zero, $t0, 1b \n" \ + " beqz $t0, 1b \n" \ "2: \n" \ __WEAK_LLSC_MB \ : "=&r" (__ret), "=ZB"(*m) \ diff --git a/arch/loongarch/include/asm/compiler.h b/arch/loongarch/include/asm/compiler.h deleted file mode 100644 index 657cebe70ace..000000000000 --- a/arch/loongarch/include/asm/compiler.h +++ /dev/null @@ -1,15 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Copyright (C) 2020-2022 Loongson Technology Corporation Limited - */ -#ifndef _ASM_COMPILER_H -#define _ASM_COMPILER_H - -#define GCC_OFF_SMALL_ASM() "ZC" - -#define LOONGARCH_ISA_LEVEL "loongarch" -#define LOONGARCH_ISA_ARCH_LEVEL "arch=loongarch" -#define LOONGARCH_ISA_LEVEL_RAW loongarch -#define LOONGARCH_ISA_ARCH_LEVEL_RAW LOONGARCH_ISA_LEVEL_RAW - -#endif /* _ASM_COMPILER_H */ diff --git a/arch/loongarch/include/asm/elf.h b/arch/loongarch/include/asm/elf.h index f3960b18a90e..5f3ff4781fda 100644 --- a/arch/loongarch/include/asm/elf.h +++ b/arch/loongarch/include/asm/elf.h @@ -288,8 +288,6 @@ struct arch_elf_state { .interp_fp_abi = LOONGARCH_ABI_FP_ANY, \ } -#define elf_read_implies_exec(ex, exec_stk) (exec_stk == EXSTACK_DEFAULT) - extern int arch_elf_pt_proc(void *ehdr, void *phdr, struct file *elf, bool is_interp, struct arch_elf_state *state); diff --git a/arch/loongarch/include/asm/futex.h b/arch/loongarch/include/asm/futex.h index 9de8231694ec..feb6658c84ff 100644 --- a/arch/loongarch/include/asm/futex.h +++ b/arch/loongarch/include/asm/futex.h @@ -8,7 +8,6 @@ #include <linux/futex.h> #include <linux/uaccess.h> #include <asm/barrier.h> -#include <asm/compiler.h> #include <asm/errno.h> #define __futex_atomic_op(insn, ret, oldval, uaddr, oparg) \ @@ -17,7 +16,7 @@ "1: ll.w %1, %4 # __futex_atomic_op\n" \ " " insn " \n" \ "2: sc.w $t0, %2 \n" \ - " beq $t0, $zero, 1b \n" \ + " beqz $t0, 1b \n" \ "3: \n" \ " .section .fixup,\"ax\" \n" \ "4: li.w %0, %6 \n" \ @@ -82,9 +81,9 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, u32 oldval, u32 newv "# futex_atomic_cmpxchg_inatomic \n" "1: ll.w %1, %3 \n" " bne %1, %z4, 3f \n" - " or $t0, %z5, $zero \n" + " move $t0, %z5 \n" "2: sc.w $t0, %2 \n" - " beq $zero, $t0, 1b \n" + " beqz $t0, 1b \n" "3: \n" __WEAK_LLSC_MB " .section .fixup,\"ax\" \n" @@ -95,8 +94,8 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, u32 oldval, u32 newv " "__UA_ADDR "\t1b, 4b \n" " "__UA_ADDR "\t2b, 4b \n" " .previous \n" - : "+r" (ret), "=&r" (val), "=" GCC_OFF_SMALL_ASM() (*uaddr) - : GCC_OFF_SMALL_ASM() (*uaddr), "Jr" (oldval), "Jr" (newval), + : "+r" (ret), "=&r" (val), "=ZC" (*uaddr) + : "ZC" (*uaddr), "Jr" (oldval), "Jr" (newval), "i" (-EFAULT) : "memory", "t0"); diff --git a/arch/loongarch/include/asm/irqflags.h b/arch/loongarch/include/asm/irqflags.h index 52121cd791fe..319a8c616f1f 100644 --- a/arch/loongarch/include/asm/irqflags.h +++ b/arch/loongarch/include/asm/irqflags.h @@ -9,7 +9,6 @@ #include <linux/compiler.h> #include <linux/stringify.h> -#include <asm/compiler.h> #include <asm/loongarch.h> static inline void arch_local_irq_enable(void) diff --git a/arch/loongarch/include/asm/local.h b/arch/loongarch/include/asm/local.h index 2052a2267337..65fbbae9fc4d 100644 --- a/arch/loongarch/include/asm/local.h +++ b/arch/loongarch/include/asm/local.h @@ -9,7 +9,6 @@ #include <linux/bitops.h> #include <linux/atomic.h> #include <asm/cmpxchg.h> -#include <asm/compiler.h> typedef struct { atomic_long_t a; diff --git a/arch/loongarch/include/asm/loongson.h b/arch/loongarch/include/asm/loongson.h index 6a8038725ba7..6e8f6972ceb6 100644 --- a/arch/loongarch/include/asm/loongson.h +++ b/arch/loongarch/include/asm/loongson.h @@ -39,18 +39,6 @@ extern const struct plat_smp_ops loongson3_smp_ops; #define MAX_PACKAGES 16 -/* Chip Config register of each physical cpu package */ -extern u64 loongson_chipcfg[MAX_PACKAGES]; -#define LOONGSON_CHIPCFG(id) (*(volatile u32 *)(loongson_chipcfg[id])) - -/* Chip Temperature register of each physical cpu package */ -extern u64 loongson_chiptemp[MAX_PACKAGES]; -#define LOONGSON_CHIPTEMP(id) (*(volatile u32 *)(loongson_chiptemp[id])) - -/* Freq Control register of each physical cpu package */ -extern u64 loongson_freqctrl[MAX_PACKAGES]; -#define LOONGSON_FREQCTRL(id) (*(volatile u32 *)(loongson_freqctrl[id])) - #define xconf_readl(addr) readl(addr) #define xconf_readq(addr) readq(addr) @@ -58,7 +46,7 @@ static inline void xconf_writel(u32 val, volatile void __iomem *addr) { asm volatile ( " st.w %[v], %[hw], 0 \n" - " ld.b $r0, %[hw], 0 \n" + " ld.b $zero, %[hw], 0 \n" : : [hw] "r" (addr), [v] "r" (val) ); @@ -68,7 +56,7 @@ static inline void xconf_writeq(u64 val64, volatile void __iomem *addr) { asm volatile ( " st.d %[v], %[hw], 0 \n" - " ld.b $r0, %[hw], 0 \n" + " ld.b $zero, %[hw], 0 \n" : : [hw] "r" (addr), [v] "r" (val64) ); diff --git a/arch/loongarch/include/asm/stacktrace.h b/arch/loongarch/include/asm/stacktrace.h index 26483e396ad1..6b5c2a7aa706 100644 --- a/arch/loongarch/include/asm/stacktrace.h +++ b/arch/loongarch/include/asm/stacktrace.h @@ -23,13 +23,13 @@ static __always_inline void prepare_frametrace(struct pt_regs *regs) { __asm__ __volatile__( - /* Save $r1 */ + /* Save $ra */ STORE_ONE_REG(1) - /* Use $r1 to save PC */ - "pcaddi $r1, 0\n\t" - STR_LONG_S " $r1, %0\n\t" - /* Restore $r1 */ - STR_LONG_L " $r1, %1, "STR_LONGSIZE"\n\t" + /* Use $ra to save PC */ + "pcaddi $ra, 0\n\t" + STR_LONG_S " $ra, %0\n\t" + /* Restore $ra */ + STR_LONG_L " $ra, %1, "STR_LONGSIZE"\n\t" STORE_ONE_REG(2) STORE_ONE_REG(3) STORE_ONE_REG(4) diff --git a/arch/loongarch/include/asm/thread_info.h b/arch/loongarch/include/asm/thread_info.h index 99beb11c2fa8..b7dd9f19a5a9 100644 --- a/arch/loongarch/include/asm/thread_info.h +++ b/arch/loongarch/include/asm/thread_info.h @@ -44,14 +44,14 @@ struct thread_info { } /* How to get the thread information struct from C. */ -register struct thread_info *__current_thread_info __asm__("$r2"); +register struct thread_info *__current_thread_info __asm__("$tp"); static inline struct thread_info *current_thread_info(void) { return __current_thread_info; } -register unsigned long current_stack_pointer __asm__("$r3"); +register unsigned long current_stack_pointer __asm__("$sp"); #endif /* !__ASSEMBLY__ */ diff --git a/arch/loongarch/include/asm/uaccess.h b/arch/loongarch/include/asm/uaccess.h index 217c6a3727b1..2b44edc604a2 100644 --- a/arch/loongarch/include/asm/uaccess.h +++ b/arch/loongarch/include/asm/uaccess.h @@ -162,7 +162,7 @@ do { \ "2: \n" \ " .section .fixup,\"ax\" \n" \ "3: li.w %0, %3 \n" \ - " or %1, $r0, $r0 \n" \ + " move %1, $zero \n" \ " b 2b \n" \ " .previous \n" \ " .section __ex_table,\"a\" \n" \ diff --git a/arch/loongarch/kernel/cacheinfo.c b/arch/loongarch/kernel/cacheinfo.c index b38f5489d094..4662b06269f4 100644 --- a/arch/loongarch/kernel/cacheinfo.c +++ b/arch/loongarch/kernel/cacheinfo.c @@ -4,8 +4,9 @@ * * Copyright (C) 2020-2022 Loongson Technology Corporation Limited */ -#include <asm/cpu-info.h> #include <linux/cacheinfo.h> +#include <asm/bootinfo.h> +#include <asm/cpu-info.h> /* Populates leaf and increments to next leaf */ #define populate_cache(cache, leaf, c_level, c_type) \ @@ -17,6 +18,8 @@ do { \ leaf->ways_of_associativity = c->cache.ways; \ leaf->size = c->cache.linesz * c->cache.sets * \ c->cache.ways; \ + if (leaf->level > 2) \ + leaf->size *= nodes_per_package; \ leaf++; \ } while (0) @@ -95,11 +98,15 @@ static void cache_cpumap_setup(unsigned int cpu) int populate_cache_leaves(unsigned int cpu) { - int level = 1; + int level = 1, nodes_per_package = 1; struct cpuinfo_loongarch *c = ¤t_cpu_data; struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu); struct cacheinfo *this_leaf = this_cpu_ci->info_list; + if (loongson_sysconf.nr_nodes > 1) + nodes_per_package = loongson_sysconf.cores_per_package + / loongson_sysconf.cores_per_node; + if (c->icache.waysize) { populate_cache(dcache, this_leaf, level, CACHE_TYPE_DATA); populate_cache(icache, this_leaf, level++, CACHE_TYPE_INST); diff --git a/arch/loongarch/kernel/entry.S b/arch/loongarch/kernel/entry.S index d5b3dbcf5425..d53b631c9022 100644 --- a/arch/loongarch/kernel/entry.S +++ b/arch/loongarch/kernel/entry.S @@ -27,7 +27,7 @@ SYM_FUNC_START(handle_syscall) addi.d sp, sp, -PT_SIZE cfi_st t2, PT_R3 - cfi_rel_offset sp, PT_R3 + cfi_rel_offset sp, PT_R3 st.d zero, sp, PT_R0 csrrd t2, LOONGARCH_CSR_PRMD st.d t2, sp, PT_PRMD @@ -50,7 +50,7 @@ SYM_FUNC_START(handle_syscall) cfi_st a7, PT_R11 csrrd ra, LOONGARCH_CSR_ERA st.d ra, sp, PT_ERA - cfi_rel_offset ra, PT_ERA + cfi_rel_offset ra, PT_ERA cfi_st tp, PT_R2 cfi_st u0, PT_R21 diff --git a/arch/loongarch/kernel/env.c b/arch/loongarch/kernel/env.c index 467946ecf451..82b478a5c665 100644 --- a/arch/loongarch/kernel/env.c +++ b/arch/loongarch/kernel/env.c @@ -17,21 +17,6 @@ u64 efi_system_table; struct loongson_system_configuration loongson_sysconf; EXPORT_SYMBOL(loongson_sysconf); -u64 loongson_chipcfg[MAX_PACKAGES]; -u64 loongson_chiptemp[MAX_PACKAGES]; -u64 loongson_freqctrl[MAX_PACKAGES]; -unsigned long long smp_group[MAX_PACKAGES]; - -static void __init register_addrs_set(u64 *registers, const u64 addr, int num) -{ - u64 i; - - for (i = 0; i < num; i++) { - *registers = (i << 44) | addr; - registers++; - } -} - void __init init_environ(void) { int efi_boot = fw_arg0; @@ -50,11 +35,6 @@ void __init init_environ(void) efi_memmap_init_early(&data); memblock_reserve(data.phys_map & PAGE_MASK, PAGE_ALIGN(data.size + (data.phys_map & ~PAGE_MASK))); - - register_addrs_set(smp_group, TO_UNCACHE(0x1fe01000), 16); - register_addrs_set(loongson_chipcfg, TO_UNCACHE(0x1fe00180), 16); - register_addrs_set(loongson_chiptemp, TO_UNCACHE(0x1fe0019c), 16); - register_addrs_set(loongson_freqctrl, TO_UNCACHE(0x1fe001d0), 16); } static int __init init_cpu_fullname(void) diff --git a/arch/loongarch/kernel/fpu.S b/arch/loongarch/kernel/fpu.S index a631a7137667..576b3370a296 100644 --- a/arch/loongarch/kernel/fpu.S +++ b/arch/loongarch/kernel/fpu.S @@ -27,78 +27,78 @@ .endm .macro sc_save_fp base - EX fst.d $f0, \base, (0 * FPU_REG_WIDTH) - EX fst.d $f1, \base, (1 * FPU_REG_WIDTH) - EX fst.d $f2, \base, (2 * FPU_REG_WIDTH) - EX fst.d $f3, \base, (3 * FPU_REG_WIDTH) - EX fst.d $f4, \base, (4 * FPU_REG_WIDTH) - EX fst.d $f5, \base, (5 * FPU_REG_WIDTH) - EX fst.d $f6, \base, (6 * FPU_REG_WIDTH) - EX fst.d $f7, \base, (7 * FPU_REG_WIDTH) - EX fst.d $f8, \base, (8 * FPU_REG_WIDTH) - EX fst.d $f9, \base, (9 * FPU_REG_WIDTH) - EX fst.d $f10, \base, (10 * FPU_REG_WIDTH) - EX fst.d $f11, \base, (11 * FPU_REG_WIDTH) - EX fst.d $f12, \base, (12 * FPU_REG_WIDTH) - EX fst.d $f13, \base, (13 * FPU_REG_WIDTH) - EX fst.d $f14, \base, (14 * FPU_REG_WIDTH) - EX fst.d $f15, \base, (15 * FPU_REG_WIDTH) - EX fst.d $f16, \base, (16 * FPU_REG_WIDTH) - EX fst.d $f17, \base, (17 * FPU_REG_WIDTH) - EX fst.d $f18, \base, (18 * FPU_REG_WIDTH) - EX fst.d $f19, \base, (19 * FPU_REG_WIDTH) - EX fst.d $f20, \base, (20 * FPU_REG_WIDTH) - EX fst.d $f21, \base, (21 * FPU_REG_WIDTH) - EX fst.d $f22, \base, (22 * FPU_REG_WIDTH) - EX fst.d $f23, \base, (23 * FPU_REG_WIDTH) - EX fst.d $f24, \base, (24 * FPU_REG_WIDTH) - EX fst.d $f25, \base, (25 * FPU_REG_WIDTH) - EX fst.d $f26, \base, (26 * FPU_REG_WIDTH) - EX fst.d $f27, \base, (27 * FPU_REG_WIDTH) - EX fst.d $f28, \base, (28 * FPU_REG_WIDTH) - EX fst.d $f29, \base, (29 * FPU_REG_WIDTH) - EX fst.d $f30, \base, (30 * FPU_REG_WIDTH) - EX fst.d $f31, \base, (31 * FPU_REG_WIDTH) + EX fst.d $f0, \base, (0 * FPU_REG_WIDTH) + EX fst.d $f1, \base, (1 * FPU_REG_WIDTH) + EX fst.d $f2, \base, (2 * FPU_REG_WIDTH) + EX fst.d $f3, \base, (3 * FPU_REG_WIDTH) + EX fst.d $f4, \base, (4 * FPU_REG_WIDTH) + EX fst.d $f5, \base, (5 * FPU_REG_WIDTH) + EX fst.d $f6, \base, (6 * FPU_REG_WIDTH) + EX fst.d $f7, \base, (7 * FPU_REG_WIDTH) + EX fst.d $f8, \base, (8 * FPU_REG_WIDTH) + EX fst.d $f9, \base, (9 * FPU_REG_WIDTH) + EX fst.d $f10, \base, (10 * FPU_REG_WIDTH) + EX fst.d $f11, \base, (11 * FPU_REG_WIDTH) + EX fst.d $f12, \base, (12 * FPU_REG_WIDTH) + EX fst.d $f13, \base, (13 * FPU_REG_WIDTH) + EX fst.d $f14, \base, (14 * FPU_REG_WIDTH) + EX fst.d $f15, \base, (15 * FPU_REG_WIDTH) + EX fst.d $f16, \base, (16 * FPU_REG_WIDTH) + EX fst.d $f17, \base, (17 * FPU_REG_WIDTH) + EX fst.d $f18, \base, (18 * FPU_REG_WIDTH) + EX fst.d $f19, \base, (19 * FPU_REG_WIDTH) + EX fst.d $f20, \base, (20 * FPU_REG_WIDTH) + EX fst.d $f21, \base, (21 * FPU_REG_WIDTH) + EX fst.d $f22, \base, (22 * FPU_REG_WIDTH) + EX fst.d $f23, \base, (23 * FPU_REG_WIDTH) + EX fst.d $f24, \base, (24 * FPU_REG_WIDTH) + EX fst.d $f25, \base, (25 * FPU_REG_WIDTH) + EX fst.d $f26, \base, (26 * FPU_REG_WIDTH) + EX fst.d $f27, \base, (27 * FPU_REG_WIDTH) + EX fst.d $f28, \base, (28 * FPU_REG_WIDTH) + EX fst.d $f29, \base, (29 * FPU_REG_WIDTH) + EX fst.d $f30, \base, (30 * FPU_REG_WIDTH) + EX fst.d $f31, \base, (31 * FPU_REG_WIDTH) .endm .macro sc_restore_fp base - EX fld.d $f0, \base, (0 * FPU_REG_WIDTH) - EX fld.d $f1, \base, (1 * FPU_REG_WIDTH) - EX fld.d $f2, \base, (2 * FPU_REG_WIDTH) - EX fld.d $f3, \base, (3 * FPU_REG_WIDTH) - EX fld.d $f4, \base, (4 * FPU_REG_WIDTH) - EX fld.d $f5, \base, (5 * FPU_REG_WIDTH) - EX fld.d $f6, \base, (6 * FPU_REG_WIDTH) - EX fld.d $f7, \base, (7 * FPU_REG_WIDTH) - EX fld.d $f8, \base, (8 * FPU_REG_WIDTH) - EX fld.d $f9, \base, (9 * FPU_REG_WIDTH) - EX fld.d $f10, \base, (10 * FPU_REG_WIDTH) - EX fld.d $f11, \base, (11 * FPU_REG_WIDTH) - EX fld.d $f12, \base, (12 * FPU_REG_WIDTH) - EX fld.d $f13, \base, (13 * FPU_REG_WIDTH) - EX fld.d $f14, \base, (14 * FPU_REG_WIDTH) - EX fld.d $f15, \base, (15 * FPU_REG_WIDTH) - EX fld.d $f16, \base, (16 * FPU_REG_WIDTH) - EX fld.d $f17, \base, (17 * FPU_REG_WIDTH) - EX fld.d $f18, \base, (18 * FPU_REG_WIDTH) - EX fld.d $f19, \base, (19 * FPU_REG_WIDTH) - EX fld.d $f20, \base, (20 * FPU_REG_WIDTH) - EX fld.d $f21, \base, (21 * FPU_REG_WIDTH) - EX fld.d $f22, \base, (22 * FPU_REG_WIDTH) - EX fld.d $f23, \base, (23 * FPU_REG_WIDTH) - EX fld.d $f24, \base, (24 * FPU_REG_WIDTH) - EX fld.d $f25, \base, (25 * FPU_REG_WIDTH) - EX fld.d $f26, \base, (26 * FPU_REG_WIDTH) - EX fld.d $f27, \base, (27 * FPU_REG_WIDTH) - EX fld.d $f28, \base, (28 * FPU_REG_WIDTH) - EX fld.d $f29, \base, (29 * FPU_REG_WIDTH) - EX fld.d $f30, \base, (30 * FPU_REG_WIDTH) - EX fld.d $f31, \base, (31 * FPU_REG_WIDTH) + EX fld.d $f0, \base, (0 * FPU_REG_WIDTH) + EX fld.d $f1, \base, (1 * FPU_REG_WIDTH) + EX fld.d $f2, \base, (2 * FPU_REG_WIDTH) + EX fld.d $f3, \base, (3 * FPU_REG_WIDTH) + EX fld.d $f4, \base, (4 * FPU_REG_WIDTH) + EX fld.d $f5, \base, (5 * FPU_REG_WIDTH) + EX fld.d $f6, \base, (6 * FPU_REG_WIDTH) + EX fld.d $f7, \base, (7 * FPU_REG_WIDTH) + EX fld.d $f8, \base, (8 * FPU_REG_WIDTH) + EX fld.d $f9, \base, (9 * FPU_REG_WIDTH) + EX fld.d $f10, \base, (10 * FPU_REG_WIDTH) + EX fld.d $f11, \base, (11 * FPU_REG_WIDTH) + EX fld.d $f12, \base, (12 * FPU_REG_WIDTH) + EX fld.d $f13, \base, (13 * FPU_REG_WIDTH) + EX fld.d $f14, \base, (14 * FPU_REG_WIDTH) + EX fld.d $f15, \base, (15 * FPU_REG_WIDTH) + EX fld.d $f16, \base, (16 * FPU_REG_WIDTH) + EX fld.d $f17, \base, (17 * FPU_REG_WIDTH) + EX fld.d $f18, \base, (18 * FPU_REG_WIDTH) + EX fld.d $f19, \base, (19 * FPU_REG_WIDTH) + EX fld.d $f20, \base, (20 * FPU_REG_WIDTH) + EX fld.d $f21, \base, (21 * FPU_REG_WIDTH) + EX fld.d $f22, \base, (22 * FPU_REG_WIDTH) + EX fld.d $f23, \base, (23 * FPU_REG_WIDTH) + EX fld.d $f24, \base, (24 * FPU_REG_WIDTH) + EX fld.d $f25, \base, (25 * FPU_REG_WIDTH) + EX fld.d $f26, \base, (26 * FPU_REG_WIDTH) + EX fld.d $f27, \base, (27 * FPU_REG_WIDTH) + EX fld.d $f28, \base, (28 * FPU_REG_WIDTH) + EX fld.d $f29, \base, (29 * FPU_REG_WIDTH) + EX fld.d $f30, \base, (30 * FPU_REG_WIDTH) + EX fld.d $f31, \base, (31 * FPU_REG_WIDTH) .endm .macro sc_save_fcc base, tmp0, tmp1 movcf2gr \tmp0, $fcc0 - move \tmp1, \tmp0 + move \tmp1, \tmp0 movcf2gr \tmp0, $fcc1 bstrins.d \tmp1, \tmp0, 15, 8 movcf2gr \tmp0, $fcc2 @@ -113,11 +113,11 @@ bstrins.d \tmp1, \tmp0, 55, 48 movcf2gr \tmp0, $fcc7 bstrins.d \tmp1, \tmp0, 63, 56 - EX st.d \tmp1, \base, 0 + EX st.d \tmp1, \base, 0 .endm .macro sc_restore_fcc base, tmp0, tmp1 - EX ld.d \tmp0, \base, 0 + EX ld.d \tmp0, \base, 0 bstrpick.d \tmp1, \tmp0, 7, 0 movgr2cf $fcc0, \tmp1 bstrpick.d \tmp1, \tmp0, 15, 8 @@ -138,11 +138,11 @@ .macro sc_save_fcsr base, tmp0 movfcsr2gr \tmp0, fcsr0 - EX st.w \tmp0, \base, 0 + EX st.w \tmp0, \base, 0 .endm .macro sc_restore_fcsr base, tmp0 - EX ld.w \tmp0, \base, 0 + EX ld.w \tmp0, \base, 0 movgr2fcsr fcsr0, \tmp0 .endm @@ -151,9 +151,9 @@ */ SYM_FUNC_START(_save_fp) fpu_save_csr a0 t1 - fpu_save_double a0 t1 # clobbers t1 + fpu_save_double a0 t1 # clobbers t1 fpu_save_cc a0 t1 t2 # clobbers t1, t2 - jirl zero, ra, 0 + jr ra SYM_FUNC_END(_save_fp) EXPORT_SYMBOL(_save_fp) @@ -161,10 +161,10 @@ EXPORT_SYMBOL(_save_fp) * Restore a thread's fp context. */ SYM_FUNC_START(_restore_fp) - fpu_restore_double a0 t1 # clobbers t1 - fpu_restore_csr a0 t1 - fpu_restore_cc a0 t1 t2 # clobbers t1, t2 - jirl zero, ra, 0 + fpu_restore_double a0 t1 # clobbers t1 + fpu_restore_csr a0 t1 + fpu_restore_cc a0 t1 t2 # clobbers t1, t2 + jr ra SYM_FUNC_END(_restore_fp) /* @@ -216,7 +216,7 @@ SYM_FUNC_START(_init_fpu) movgr2fr.d $f30, t1 movgr2fr.d $f31, t1 - jirl zero, ra, 0 + jr ra SYM_FUNC_END(_init_fpu) /* @@ -225,11 +225,11 @@ SYM_FUNC_END(_init_fpu) * a2: fcsr */ SYM_FUNC_START(_save_fp_context) - sc_save_fcc a1 t1 t2 - sc_save_fcsr a2 t1 - sc_save_fp a0 - li.w a0, 0 # success - jirl zero, ra, 0 + sc_save_fcc a1 t1 t2 + sc_save_fcsr a2 t1 + sc_save_fp a0 + li.w a0, 0 # success + jr ra SYM_FUNC_END(_save_fp_context) /* @@ -238,14 +238,14 @@ SYM_FUNC_END(_save_fp_context) * a2: fcsr */ SYM_FUNC_START(_restore_fp_context) - sc_restore_fp a0 - sc_restore_fcc a1 t1 t2 - sc_restore_fcsr a2 t1 - li.w a0, 0 # success - jirl zero, ra, 0 + sc_restore_fp a0 + sc_restore_fcc a1 t1 t2 + sc_restore_fcsr a2 t1 + li.w a0, 0 # success + jr ra SYM_FUNC_END(_restore_fp_context) SYM_FUNC_START(fault) li.w a0, -EFAULT # failure - jirl zero, ra, 0 + jr ra SYM_FUNC_END(fault) diff --git a/arch/loongarch/kernel/genex.S b/arch/loongarch/kernel/genex.S index 93496852b3cc..75e5be807a0d 100644 --- a/arch/loongarch/kernel/genex.S +++ b/arch/loongarch/kernel/genex.S @@ -28,23 +28,23 @@ SYM_FUNC_START(__arch_cpu_idle) nop idle 0 /* end of rollback region */ -1: jirl zero, ra, 0 +1: jr ra SYM_FUNC_END(__arch_cpu_idle) SYM_FUNC_START(handle_vint) BACKUP_T0T1 SAVE_ALL la.abs t1, __arch_cpu_idle - LONG_L t0, sp, PT_ERA + LONG_L t0, sp, PT_ERA /* 32 byte rollback region */ ori t0, t0, 0x1f xori t0, t0, 0x1f bne t0, t1, 1f - LONG_S t0, sp, PT_ERA + LONG_S t0, sp, PT_ERA 1: move a0, sp move a1, sp la.abs t0, do_vint - jirl ra, t0, 0 + jirl ra, t0, 0 RESTORE_ALL_AND_RET SYM_FUNC_END(handle_vint) @@ -72,7 +72,7 @@ SYM_FUNC_END(except_vec_cex) build_prep_\prep move a0, sp la.abs t0, do_\handler - jirl ra, t0, 0 + jirl ra, t0, 0 RESTORE_ALL_AND_RET SYM_FUNC_END(handle_\exception) .endm @@ -91,5 +91,5 @@ SYM_FUNC_END(except_vec_cex) SYM_FUNC_START(handle_sys) la.abs t0, handle_syscall - jirl zero, t0, 0 + jr t0 SYM_FUNC_END(handle_sys) diff --git a/arch/loongarch/kernel/head.S b/arch/loongarch/kernel/head.S index d01e62dd414f..7062cdf0e33e 100644 --- a/arch/loongarch/kernel/head.S +++ b/arch/loongarch/kernel/head.S @@ -32,7 +32,7 @@ SYM_CODE_START(kernel_entry) # kernel entry point /* We might not get launched at the address the kernel is linked to, so we jump there. */ la.abs t0, 0f - jirl zero, t0, 0 + jr t0 0: la t0, __bss_start # clear .bss st.d zero, t0, 0 @@ -50,7 +50,7 @@ SYM_CODE_START(kernel_entry) # kernel entry point /* KSave3 used for percpu base, initialized as 0 */ csrwr zero, PERCPU_BASE_KS /* GPR21 used for percpu base (runtime), initialized as 0 */ - or u0, zero, zero + move u0, zero la tp, init_thread_union /* Set the SP after an empty pt_regs. */ @@ -85,8 +85,8 @@ SYM_CODE_START(smpboot_entry) ld.d sp, t0, CPU_BOOT_STACK ld.d tp, t0, CPU_BOOT_TINFO - la.abs t0, 0f - jirl zero, t0, 0 + la.abs t0, 0f + jr t0 0: bl start_secondary SYM_CODE_END(smpboot_entry) diff --git a/arch/loongarch/kernel/ptrace.c b/arch/loongarch/kernel/ptrace.c index e6ab87948e1d..dc2b82ea894c 100644 --- a/arch/loongarch/kernel/ptrace.c +++ b/arch/loongarch/kernel/ptrace.c @@ -193,7 +193,7 @@ static int fpr_set(struct task_struct *target, const void *kbuf, const void __user *ubuf) { const int fcc_start = NUM_FPU_REGS * sizeof(elf_fpreg_t); - const int fcc_end = fcc_start + sizeof(u64); + const int fcsr_start = fcc_start + sizeof(u64); int err; BUG_ON(count % sizeof(elf_fpreg_t)); @@ -209,10 +209,12 @@ static int fpr_set(struct task_struct *target, if (err) return err; - if (count > 0) - err |= user_regset_copyin(&pos, &count, &kbuf, &ubuf, - &target->thread.fpu.fcc, - fcc_start, fcc_end); + err |= user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.fpu.fcc, fcc_start, + fcc_start + sizeof(u64)); + err |= user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.fpu.fcsr, fcsr_start, + fcsr_start + sizeof(u32)); return err; } diff --git a/arch/loongarch/kernel/reset.c b/arch/loongarch/kernel/reset.c index 2b86469e4718..800c965a17ea 100644 --- a/arch/loongarch/kernel/reset.c +++ b/arch/loongarch/kernel/reset.c @@ -13,7 +13,6 @@ #include <linux/console.h> #include <acpi/reboot.h> -#include <asm/compiler.h> #include <asm/idle.h> #include <asm/loongarch.h> #include <asm/reboot.h> diff --git a/arch/loongarch/kernel/setup.c b/arch/loongarch/kernel/setup.c index c74860b53375..8f5c2f9a1a83 100644 --- a/arch/loongarch/kernel/setup.c +++ b/arch/loongarch/kernel/setup.c @@ -126,7 +126,7 @@ static void __init parse_bios_table(const struct dmi_header *dm) char *dmi_data = (char *)dm; bios_extern = *(dmi_data + SMBIOS_BIOSEXTERN_OFFSET); - b_info.bios_size = *(dmi_data + SMBIOS_BIOSSIZE_OFFSET); + b_info.bios_size = (*(dmi_data + SMBIOS_BIOSSIZE_OFFSET) + 1) << 6; if (bios_extern & LOONGSON_EFI_ENABLE) set_bit(EFI_BOOT, &efi.flags); diff --git a/arch/loongarch/kernel/smp.c b/arch/loongarch/kernel/smp.c index 73cec62504fb..09743103d9b3 100644 --- a/arch/loongarch/kernel/smp.c +++ b/arch/loongarch/kernel/smp.c @@ -278,116 +278,29 @@ void loongson3_cpu_die(unsigned int cpu) mb(); } -/* - * The target CPU should go to XKPRANGE (uncached area) and flush - * ICache/DCache/VCache before the control CPU can safely disable its clock. - */ -static void loongson3_play_dead(int *state_addr) +void play_dead(void) { - register int val; - register void *addr; + register uint64_t addr; register void (*init_fn)(void); - __asm__ __volatile__( - " li.d %[addr], 0x8000000000000000\n" - "1: cacop 0x8, %[addr], 0 \n" /* flush ICache */ - " cacop 0x8, %[addr], 1 \n" - " cacop 0x8, %[addr], 2 \n" - " cacop 0x8, %[addr], 3 \n" - " cacop 0x9, %[addr], 0 \n" /* flush DCache */ - " cacop 0x9, %[addr], 1 \n" - " cacop 0x9, %[addr], 2 \n" - " cacop 0x9, %[addr], 3 \n" - " addi.w %[sets], %[sets], -1 \n" - " addi.d %[addr], %[addr], 0x40 \n" - " bnez %[sets], 1b \n" - " li.d %[addr], 0x8000000000000000\n" - "2: cacop 0xa, %[addr], 0 \n" /* flush VCache */ - " cacop 0xa, %[addr], 1 \n" - " cacop 0xa, %[addr], 2 \n" - " cacop 0xa, %[addr], 3 \n" - " cacop 0xa, %[addr], 4 \n" - " cacop 0xa, %[addr], 5 \n" - " cacop 0xa, %[addr], 6 \n" - " cacop 0xa, %[addr], 7 \n" - " cacop 0xa, %[addr], 8 \n" - " cacop 0xa, %[addr], 9 \n" - " cacop 0xa, %[addr], 10 \n" - " cacop 0xa, %[addr], 11 \n" - " cacop 0xa, %[addr], 12 \n" - " cacop 0xa, %[addr], 13 \n" - " cacop 0xa, %[addr], 14 \n" - " cacop 0xa, %[addr], 15 \n" - " addi.w %[vsets], %[vsets], -1 \n" - " addi.d %[addr], %[addr], 0x40 \n" - " bnez %[vsets], 2b \n" - " li.w %[val], 0x7 \n" /* *state_addr = CPU_DEAD; */ - " st.w %[val], %[state_addr], 0 \n" - " dbar 0 \n" - " cacop 0x11, %[state_addr], 0 \n" /* flush entry of *state_addr */ - : [addr] "=&r" (addr), [val] "=&r" (val) - : [state_addr] "r" (state_addr), - [sets] "r" (cpu_data[smp_processor_id()].dcache.sets), - [vsets] "r" (cpu_data[smp_processor_id()].vcache.sets)); - + idle_task_exit(); local_irq_enable(); - change_csr_ecfg(ECFG0_IM, ECFGF_IPI); + set_csr_ecfg(ECFGF_IPI); + __this_cpu_write(cpu_state, CPU_DEAD); + + __smp_mb(); + do { + __asm__ __volatile__("idle 0\n\t"); + addr = iocsr_read64(LOONGARCH_IOCSR_MBUF0); + } while (addr == 0); - __asm__ __volatile__( - " idle 0 \n" - " li.w $t0, 0x1020 \n" - " iocsrrd.d %[init_fn], $t0 \n" /* Get init PC */ - : [init_fn] "=&r" (addr) - : /* No Input */ - : "a0"); - init_fn = __va(addr); + init_fn = (void *)TO_CACHE(addr); + iocsr_write32(0xffffffff, LOONGARCH_IOCSR_IPI_CLEAR); init_fn(); unreachable(); } -void play_dead(void) -{ - int *state_addr; - unsigned int cpu = smp_processor_id(); - void (*play_dead_uncached)(int *s); - - idle_task_exit(); - play_dead_uncached = (void *)TO_UNCACHE(__pa((unsigned long)loongson3_play_dead)); - state_addr = &per_cpu(cpu_state, cpu); - mb(); - play_dead_uncached(state_addr); -} - -static int loongson3_enable_clock(unsigned int cpu) -{ - uint64_t core_id = cpu_data[cpu].core; - uint64_t package_id = cpu_data[cpu].package; - - LOONGSON_FREQCTRL(package_id) |= 1 << (core_id * 4 + 3); - - return 0; -} - -static int loongson3_disable_clock(unsigned int cpu) -{ - uint64_t core_id = cpu_data[cpu].core; - uint64_t package_id = cpu_data[cpu].package; - - LOONGSON_FREQCTRL(package_id) &= ~(1 << (core_id * 4 + 3)); - - return 0; -} - -static int register_loongson3_notifier(void) -{ - return cpuhp_setup_state_nocalls(CPUHP_LOONGARCH_SOC_PREPARE, - "loongarch/loongson:prepare", - loongson3_enable_clock, - loongson3_disable_clock); -} -early_initcall(register_loongson3_notifier); - #endif /* diff --git a/arch/loongarch/kernel/switch.S b/arch/loongarch/kernel/switch.S index 53e2fa8e580e..37e84ac8ffc2 100644 --- a/arch/loongarch/kernel/switch.S +++ b/arch/loongarch/kernel/switch.S @@ -24,8 +24,8 @@ SYM_FUNC_START(__switch_to) move tp, a2 cpu_restore_nonscratch a1 - li.w t0, _THREAD_SIZE - 32 - PTR_ADD t0, t0, tp + li.w t0, _THREAD_SIZE - 32 + PTR_ADD t0, t0, tp set_saved_sp t0, t1, t2 ldptr.d t1, a1, THREAD_CSRPRMD diff --git a/arch/loongarch/lib/clear_user.S b/arch/loongarch/lib/clear_user.S index 25d9be5fbb19..16ba2b8dd68a 100644 --- a/arch/loongarch/lib/clear_user.S +++ b/arch/loongarch/lib/clear_user.S @@ -32,7 +32,7 @@ SYM_FUNC_START(__clear_user) 1: st.b zero, a0, 0 addi.d a0, a0, 1 addi.d a1, a1, -1 - bgt a1, zero, 1b + bgtz a1, 1b 2: move a0, a1 jr ra diff --git a/arch/loongarch/lib/copy_user.S b/arch/loongarch/lib/copy_user.S index 9ae507f851b5..97d20327a69e 100644 --- a/arch/loongarch/lib/copy_user.S +++ b/arch/loongarch/lib/copy_user.S @@ -35,7 +35,7 @@ SYM_FUNC_START(__copy_user) addi.d a0, a0, 1 addi.d a1, a1, 1 addi.d a2, a2, -1 - bgt a2, zero, 1b + bgtz a2, 1b 3: move a0, a2 jr ra diff --git a/arch/loongarch/lib/delay.c b/arch/loongarch/lib/delay.c index 5d856694fcfe..831d4761f385 100644 --- a/arch/loongarch/lib/delay.c +++ b/arch/loongarch/lib/delay.c @@ -7,7 +7,6 @@ #include <linux/smp.h> #include <linux/timex.h> -#include <asm/compiler.h> #include <asm/processor.h> void __delay(unsigned long cycles) diff --git a/arch/loongarch/mm/page.S b/arch/loongarch/mm/page.S index ddc78ab33c7b..4c874a7af0ad 100644 --- a/arch/loongarch/mm/page.S +++ b/arch/loongarch/mm/page.S @@ -10,75 +10,75 @@ .align 5 SYM_FUNC_START(clear_page) - lu12i.w t0, 1 << (PAGE_SHIFT - 12) - add.d t0, t0, a0 + lu12i.w t0, 1 << (PAGE_SHIFT - 12) + add.d t0, t0, a0 1: - st.d zero, a0, 0 - st.d zero, a0, 8 - st.d zero, a0, 16 - st.d zero, a0, 24 - st.d zero, a0, 32 - st.d zero, a0, 40 - st.d zero, a0, 48 - st.d zero, a0, 56 - addi.d a0, a0, 128 - st.d zero, a0, -64 - st.d zero, a0, -56 - st.d zero, a0, -48 - st.d zero, a0, -40 - st.d zero, a0, -32 - st.d zero, a0, -24 - st.d zero, a0, -16 - st.d zero, a0, -8 - bne t0, a0, 1b + st.d zero, a0, 0 + st.d zero, a0, 8 + st.d zero, a0, 16 + st.d zero, a0, 24 + st.d zero, a0, 32 + st.d zero, a0, 40 + st.d zero, a0, 48 + st.d zero, a0, 56 + addi.d a0, a0, 128 + st.d zero, a0, -64 + st.d zero, a0, -56 + st.d zero, a0, -48 + st.d zero, a0, -40 + st.d zero, a0, -32 + st.d zero, a0, -24 + st.d zero, a0, -16 + st.d zero, a0, -8 + bne t0, a0, 1b - jirl $r0, ra, 0 + jr ra SYM_FUNC_END(clear_page) EXPORT_SYMBOL(clear_page) .align 5 SYM_FUNC_START(copy_page) - lu12i.w t8, 1 << (PAGE_SHIFT - 12) - add.d t8, t8, a0 + lu12i.w t8, 1 << (PAGE_SHIFT - 12) + add.d t8, t8, a0 1: - ld.d t0, a1, 0 - ld.d t1, a1, 8 - ld.d t2, a1, 16 - ld.d t3, a1, 24 - ld.d t4, a1, 32 - ld.d t5, a1, 40 - ld.d t6, a1, 48 - ld.d t7, a1, 56 + ld.d t0, a1, 0 + ld.d t1, a1, 8 + ld.d t2, a1, 16 + ld.d t3, a1, 24 + ld.d t4, a1, 32 + ld.d t5, a1, 40 + ld.d t6, a1, 48 + ld.d t7, a1, 56 - st.d t0, a0, 0 - st.d t1, a0, 8 - ld.d t0, a1, 64 - ld.d t1, a1, 72 - st.d t2, a0, 16 - st.d t3, a0, 24 - ld.d t2, a1, 80 - ld.d t3, a1, 88 - st.d t4, a0, 32 - st.d t5, a0, 40 - ld.d t4, a1, 96 - ld.d t5, a1, 104 - st.d t6, a0, 48 - st.d t7, a0, 56 - ld.d t6, a1, 112 - ld.d t7, a1, 120 - addi.d a0, a0, 128 - addi.d a1, a1, 128 + st.d t0, a0, 0 + st.d t1, a0, 8 + ld.d t0, a1, 64 + ld.d t1, a1, 72 + st.d t2, a0, 16 + st.d t3, a0, 24 + ld.d t2, a1, 80 + ld.d t3, a1, 88 + st.d t4, a0, 32 + st.d t5, a0, 40 + ld.d t4, a1, 96 + ld.d t5, a1, 104 + st.d t6, a0, 48 + st.d t7, a0, 56 + ld.d t6, a1, 112 + ld.d t7, a1, 120 + addi.d a0, a0, 128 + addi.d a1, a1, 128 - st.d t0, a0, -64 - st.d t1, a0, -56 - st.d t2, a0, -48 - st.d t3, a0, -40 - st.d t4, a0, -32 - st.d t5, a0, -24 - st.d t6, a0, -16 - st.d t7, a0, -8 + st.d t0, a0, -64 + st.d t1, a0, -56 + st.d t2, a0, -48 + st.d t3, a0, -40 + st.d t4, a0, -32 + st.d t5, a0, -24 + st.d t6, a0, -16 + st.d t7, a0, -8 - bne t8, a0, 1b - jirl $r0, ra, 0 + bne t8, a0, 1b + jr ra SYM_FUNC_END(copy_page) EXPORT_SYMBOL(copy_page) diff --git a/arch/loongarch/mm/tlbex.S b/arch/loongarch/mm/tlbex.S index 7eee40271577..de19fa2d7f0d 100644 --- a/arch/loongarch/mm/tlbex.S +++ b/arch/loongarch/mm/tlbex.S @@ -18,7 +18,7 @@ REG_S a2, sp, PT_BVADDR li.w a1, \write la.abs t0, do_page_fault - jirl ra, t0, 0 + jirl ra, t0, 0 RESTORE_ALL_AND_RET SYM_FUNC_END(tlb_do_page_fault_\write) .endm @@ -34,7 +34,7 @@ SYM_FUNC_START(handle_tlb_protect) csrrd a2, LOONGARCH_CSR_BADV REG_S a2, sp, PT_BVADDR la.abs t0, do_page_fault - jirl ra, t0, 0 + jirl ra, t0, 0 RESTORE_ALL_AND_RET SYM_FUNC_END(handle_tlb_protect) @@ -47,7 +47,7 @@ SYM_FUNC_START(handle_tlb_load) * The vmalloc handling is not in the hotpath. */ csrrd t0, LOONGARCH_CSR_BADV - blt t0, $r0, vmalloc_load + bltz t0, vmalloc_load csrrd t1, LOONGARCH_CSR_PGDL vmalloc_done_load: @@ -80,7 +80,7 @@ vmalloc_done_load: * see if we need to jump to huge tlb processing. */ andi t0, ra, _PAGE_HUGE - bne t0, $r0, tlb_huge_update_load + bnez t0, tlb_huge_update_load csrrd t0, LOONGARCH_CSR_BADV srli.d t0, t0, (PAGE_SHIFT + PTE_ORDER) @@ -100,12 +100,12 @@ smp_pgtable_change_load: srli.d ra, t0, _PAGE_PRESENT_SHIFT andi ra, ra, 1 - beq ra, $r0, nopage_tlb_load + beqz ra, nopage_tlb_load ori t0, t0, _PAGE_VALID #ifdef CONFIG_SMP sc.d t0, t1, 0 - beq t0, $r0, smp_pgtable_change_load + beqz t0, smp_pgtable_change_load #else st.d t0, t1, 0 #endif @@ -139,23 +139,23 @@ tlb_huge_update_load: #endif srli.d ra, t0, _PAGE_PRESENT_SHIFT andi ra, ra, 1 - beq ra, $r0, nopage_tlb_load + beqz ra, nopage_tlb_load tlbsrch ori t0, t0, _PAGE_VALID #ifdef CONFIG_SMP sc.d t0, t1, 0 - beq t0, $r0, tlb_huge_update_load + beqz t0, tlb_huge_update_load ld.d t0, t1, 0 #else st.d t0, t1, 0 #endif - addu16i.d t1, $r0, -(CSR_TLBIDX_EHINV >> 16) - addi.d ra, t1, 0 - csrxchg ra, t1, LOONGARCH_CSR_TLBIDX + addu16i.d t1, zero, -(CSR_TLBIDX_EHINV >> 16) + addi.d ra, t1, 0 + csrxchg ra, t1, LOONGARCH_CSR_TLBIDX tlbwr - csrxchg $r0, t1, LOONGARCH_CSR_TLBIDX + csrxchg zero, t1, LOONGARCH_CSR_TLBIDX /* * A huge PTE describes an area the size of the @@ -178,27 +178,27 @@ tlb_huge_update_load: addi.d t0, ra, 0 /* Convert to entrylo1 */ - addi.d t1, $r0, 1 + addi.d t1, zero, 1 slli.d t1, t1, (HPAGE_SHIFT - 1) add.d t0, t0, t1 csrwr t0, LOONGARCH_CSR_TLBELO1 /* Set huge page tlb entry size */ - addu16i.d t0, $r0, (CSR_TLBIDX_PS >> 16) - addu16i.d t1, $r0, (PS_HUGE_SIZE << (CSR_TLBIDX_PS_SHIFT - 16)) + addu16i.d t0, zero, (CSR_TLBIDX_PS >> 16) + addu16i.d t1, zero, (PS_HUGE_SIZE << (CSR_TLBIDX_PS_SHIFT - 16)) csrxchg t1, t0, LOONGARCH_CSR_TLBIDX tlbfill - addu16i.d t0, $r0, (CSR_TLBIDX_PS >> 16) - addu16i.d t1, $r0, (PS_DEFAULT_SIZE << (CSR_TLBIDX_PS_SHIFT - 16)) + addu16i.d t0, zero, (CSR_TLBIDX_PS >> 16) + addu16i.d t1, zero, (PS_DEFAULT_SIZE << (CSR_TLBIDX_PS_SHIFT - 16)) csrxchg t1, t0, LOONGARCH_CSR_TLBIDX nopage_tlb_load: dbar 0 csrrd ra, EXCEPTION_KS2 la.abs t0, tlb_do_page_fault_0 - jirl $r0, t0, 0 + jr t0 SYM_FUNC_END(handle_tlb_load) SYM_FUNC_START(handle_tlb_store) @@ -210,7 +210,7 @@ SYM_FUNC_START(handle_tlb_store) * The vmalloc handling is not in the hotpath. */ csrrd t0, LOONGARCH_CSR_BADV - blt t0, $r0, vmalloc_store + bltz t0, vmalloc_store csrrd t1, LOONGARCH_CSR_PGDL vmalloc_done_store: @@ -244,7 +244,7 @@ vmalloc_done_store: * see if we need to jump to huge tlb processing. */ andi t0, ra, _PAGE_HUGE - bne t0, $r0, tlb_huge_update_store + bnez t0, tlb_huge_update_store csrrd t0, LOONGARCH_CSR_BADV srli.d t0, t0, (PAGE_SHIFT + PTE_ORDER) @@ -265,12 +265,12 @@ smp_pgtable_change_store: srli.d ra, t0, _PAGE_PRESENT_SHIFT andi ra, ra, ((_PAGE_PRESENT | _PAGE_WRITE) >> _PAGE_PRESENT_SHIFT) xori ra, ra, ((_PAGE_PRESENT | _PAGE_WRITE) >> _PAGE_PRESENT_SHIFT) - bne ra, $r0, nopage_tlb_store + bnez ra, nopage_tlb_store ori t0, t0, (_PAGE_VALID | _PAGE_DIRTY | _PAGE_MODIFIED) #ifdef CONFIG_SMP sc.d t0, t1, 0 - beq t0, $r0, smp_pgtable_change_store + beqz t0, smp_pgtable_change_store #else st.d t0, t1, 0 #endif @@ -306,24 +306,24 @@ tlb_huge_update_store: srli.d ra, t0, _PAGE_PRESENT_SHIFT andi ra, ra, ((_PAGE_PRESENT | _PAGE_WRITE) >> _PAGE_PRESENT_SHIFT) xori ra, ra, ((_PAGE_PRESENT | _PAGE_WRITE) >> _PAGE_PRESENT_SHIFT) - bne ra, $r0, nopage_tlb_store + bnez ra, nopage_tlb_store tlbsrch ori t0, t0, (_PAGE_VALID | _PAGE_DIRTY | _PAGE_MODIFIED) #ifdef CONFIG_SMP sc.d t0, t1, 0 - beq t0, $r0, tlb_huge_update_store + beqz t0, tlb_huge_update_store ld.d t0, t1, 0 #else st.d t0, t1, 0 #endif - addu16i.d t1, $r0, -(CSR_TLBIDX_EHINV >> 16) - addi.d ra, t1, 0 - csrxchg ra, t1, LOONGARCH_CSR_TLBIDX + addu16i.d t1, zero, -(CSR_TLBIDX_EHINV >> 16) + addi.d ra, t1, 0 + csrxchg ra, t1, LOONGARCH_CSR_TLBIDX tlbwr - csrxchg $r0, t1, LOONGARCH_CSR_TLBIDX + csrxchg zero, t1, LOONGARCH_CSR_TLBIDX /* * A huge PTE describes an area the size of the * configured huge page size. This is twice the @@ -345,28 +345,28 @@ tlb_huge_update_store: addi.d t0, ra, 0 /* Convert to entrylo1 */ - addi.d t1, $r0, 1 + addi.d t1, zero, 1 slli.d t1, t1, (HPAGE_SHIFT - 1) add.d t0, t0, t1 csrwr t0, LOONGARCH_CSR_TLBELO1 /* Set huge page tlb entry size */ - addu16i.d t0, $r0, (CSR_TLBIDX_PS >> 16) - addu16i.d t1, $r0, (PS_HUGE_SIZE << (CSR_TLBIDX_PS_SHIFT - 16)) + addu16i.d t0, zero, (CSR_TLBIDX_PS >> 16) + addu16i.d t1, zero, (PS_HUGE_SIZE << (CSR_TLBIDX_PS_SHIFT - 16)) csrxchg t1, t0, LOONGARCH_CSR_TLBIDX tlbfill /* Reset default page size */ - addu16i.d t0, $r0, (CSR_TLBIDX_PS >> 16) - addu16i.d t1, $r0, (PS_DEFAULT_SIZE << (CSR_TLBIDX_PS_SHIFT - 16)) + addu16i.d t0, zero, (CSR_TLBIDX_PS >> 16) + addu16i.d t1, zero, (PS_DEFAULT_SIZE << (CSR_TLBIDX_PS_SHIFT - 16)) csrxchg t1, t0, LOONGARCH_CSR_TLBIDX nopage_tlb_store: dbar 0 csrrd ra, EXCEPTION_KS2 la.abs t0, tlb_do_page_fault_1 - jirl $r0, t0, 0 + jr t0 SYM_FUNC_END(handle_tlb_store) SYM_FUNC_START(handle_tlb_modify) @@ -378,7 +378,7 @@ SYM_FUNC_START(handle_tlb_modify) * The vmalloc handling is not in the hotpath. */ csrrd t0, LOONGARCH_CSR_BADV - blt t0, $r0, vmalloc_modify + bltz t0, vmalloc_modify csrrd t1, LOONGARCH_CSR_PGDL vmalloc_done_modify: @@ -411,7 +411,7 @@ vmalloc_done_modify: * see if we need to jump to huge tlb processing. */ andi t0, ra, _PAGE_HUGE - bne t0, $r0, tlb_huge_update_modify + bnez t0, tlb_huge_update_modify csrrd t0, LOONGARCH_CSR_BADV srli.d t0, t0, (PAGE_SHIFT + PTE_ORDER) @@ -431,12 +431,12 @@ smp_pgtable_change_modify: srli.d ra, t0, _PAGE_WRITE_SHIFT andi ra, ra, 1 - beq ra, $r0, nopage_tlb_modify + beqz ra, nopage_tlb_modify ori t0, t0, (_PAGE_VALID | _PAGE_DIRTY | _PAGE_MODIFIED) #ifdef CONFIG_SMP sc.d t0, t1, 0 - beq t0, $r0, smp_pgtable_change_modify + beqz t0, smp_pgtable_change_modify #else st.d t0, t1, 0 #endif @@ -454,7 +454,7 @@ leave_modify: ertn #ifdef CONFIG_64BIT vmalloc_modify: - la.abs t1, swapper_pg_dir + la.abs t1, swapper_pg_dir b vmalloc_done_modify #endif @@ -471,14 +471,14 @@ tlb_huge_update_modify: srli.d ra, t0, _PAGE_WRITE_SHIFT andi ra, ra, 1 - beq ra, $r0, nopage_tlb_modify + beqz ra, nopage_tlb_modify tlbsrch ori t0, t0, (_PAGE_VALID | _PAGE_DIRTY | _PAGE_MODIFIED) #ifdef CONFIG_SMP sc.d t0, t1, 0 - beq t0, $r0, tlb_huge_update_modify + beqz t0, tlb_huge_update_modify ld.d t0, t1, 0 #else st.d t0, t1, 0 @@ -504,28 +504,28 @@ tlb_huge_update_modify: addi.d t0, ra, 0 /* Convert to entrylo1 */ - addi.d t1, $r0, 1 + addi.d t1, zero, 1 slli.d t1, t1, (HPAGE_SHIFT - 1) add.d t0, t0, t1 csrwr t0, LOONGARCH_CSR_TLBELO1 /* Set huge page tlb entry size */ - addu16i.d t0, $r0, (CSR_TLBIDX_PS >> 16) - addu16i.d t1, $r0, (PS_HUGE_SIZE << (CSR_TLBIDX_PS_SHIFT - 16)) - csrxchg t1, t0, LOONGARCH_CSR_TLBIDX + addu16i.d t0, zero, (CSR_TLBIDX_PS >> 16) + addu16i.d t1, zero, (PS_HUGE_SIZE << (CSR_TLBIDX_PS_SHIFT - 16)) + csrxchg t1, t0, LOONGARCH_CSR_TLBIDX tlbwr /* Reset default page size */ - addu16i.d t0, $r0, (CSR_TLBIDX_PS >> 16) - addu16i.d t1, $r0, (PS_DEFAULT_SIZE << (CSR_TLBIDX_PS_SHIFT - 16)) - csrxchg t1, t0, LOONGARCH_CSR_TLBIDX + addu16i.d t0, zero, (CSR_TLBIDX_PS >> 16) + addu16i.d t1, zero, (PS_DEFAULT_SIZE << (CSR_TLBIDX_PS_SHIFT - 16)) + csrxchg t1, t0, LOONGARCH_CSR_TLBIDX nopage_tlb_modify: dbar 0 csrrd ra, EXCEPTION_KS2 la.abs t0, tlb_do_page_fault_1 - jirl $r0, t0, 0 + jr t0 SYM_FUNC_END(handle_tlb_modify) SYM_FUNC_START(handle_tlb_refill) |