diff options
Diffstat (limited to 'arch/riscv/include/asm')
45 files changed, 849 insertions, 285 deletions
diff --git a/arch/riscv/include/asm/Kbuild b/arch/riscv/include/asm/Kbuild index de13d5a234f8..bd5fc9403295 100644 --- a/arch/riscv/include/asm/Kbuild +++ b/arch/riscv/include/asm/Kbuild @@ -4,6 +4,7 @@ syscall-y += syscall_table_64.h generic-y += early_ioremap.h generic-y += flat.h +generic-y += fprobe.h generic-y += kvm_para.h generic-y += mmzone.h generic-y += mcs_spinlock.h diff --git a/arch/riscv/include/asm/alternative-macros.h b/arch/riscv/include/asm/alternative-macros.h index 721ec275ce57..231d777d936c 100644 --- a/arch/riscv/include/asm/alternative-macros.h +++ b/arch/riscv/include/asm/alternative-macros.h @@ -115,24 +115,19 @@ \old_c .endm -#define _ALTERNATIVE_CFG(old_c, ...) \ - ALTERNATIVE_CFG old_c - -#define _ALTERNATIVE_CFG_2(old_c, ...) \ - ALTERNATIVE_CFG old_c +#define __ALTERNATIVE_CFG(old_c, ...) ALTERNATIVE_CFG old_c +#define __ALTERNATIVE_CFG_2(old_c, ...) ALTERNATIVE_CFG old_c #else /* !__ASSEMBLY__ */ -#define __ALTERNATIVE_CFG(old_c) \ - old_c "\n" +#define __ALTERNATIVE_CFG(old_c, ...) old_c "\n" +#define __ALTERNATIVE_CFG_2(old_c, ...) old_c "\n" -#define _ALTERNATIVE_CFG(old_c, ...) \ - __ALTERNATIVE_CFG(old_c) +#endif /* __ASSEMBLY__ */ -#define _ALTERNATIVE_CFG_2(old_c, ...) \ - __ALTERNATIVE_CFG(old_c) +#define _ALTERNATIVE_CFG(old_c, ...) __ALTERNATIVE_CFG(old_c) +#define _ALTERNATIVE_CFG_2(old_c, ...) __ALTERNATIVE_CFG_2(old_c) -#endif /* __ASSEMBLY__ */ #endif /* CONFIG_RISCV_ALTERNATIVE */ /* diff --git a/arch/riscv/include/asm/arch_hweight.h b/arch/riscv/include/asm/arch_hweight.h index 613769b9cdc9..0e7cdbbec8ef 100644 --- a/arch/riscv/include/asm/arch_hweight.h +++ b/arch/riscv/include/asm/arch_hweight.h @@ -19,7 +19,7 @@ static __always_inline unsigned int __arch_hweight32(unsigned int w) { -#ifdef CONFIG_RISCV_ISA_ZBB +#if defined(CONFIG_RISCV_ISA_ZBB) && defined(CONFIG_TOOLCHAIN_HAS_ZBB) asm goto(ALTERNATIVE("j %l[legacy]", "nop", 0, RISCV_ISA_EXT_ZBB, 1) : : : : legacy); @@ -50,7 +50,7 @@ static inline unsigned int __arch_hweight8(unsigned int w) #if BITS_PER_LONG == 64 static __always_inline unsigned long __arch_hweight64(__u64 w) { -# ifdef CONFIG_RISCV_ISA_ZBB +#if defined(CONFIG_RISCV_ISA_ZBB) && defined(CONFIG_TOOLCHAIN_HAS_ZBB) asm goto(ALTERNATIVE("j %l[legacy]", "nop", 0, RISCV_ISA_EXT_ZBB, 1) : : : : legacy); @@ -64,7 +64,7 @@ static __always_inline unsigned long __arch_hweight64(__u64 w) return w; legacy: -# endif +#endif return __sw_hweight64(w); } #else /* BITS_PER_LONG == 64 */ diff --git a/arch/riscv/include/asm/asm-prototypes.h b/arch/riscv/include/asm/asm-prototypes.h index cd627ec289f1..bfc8ea5f9319 100644 --- a/arch/riscv/include/asm/asm-prototypes.h +++ b/arch/riscv/include/asm/asm-prototypes.h @@ -52,6 +52,8 @@ DECLARE_DO_ERROR_INFO(do_trap_ecall_s); DECLARE_DO_ERROR_INFO(do_trap_ecall_m); DECLARE_DO_ERROR_INFO(do_trap_break); +asmlinkage void ret_from_fork_kernel(void *fn_arg, int (*fn)(void *), struct pt_regs *regs); +asmlinkage void ret_from_fork_user(struct pt_regs *regs); asmlinkage void handle_bad_stack(struct pt_regs *regs); asmlinkage void do_page_fault(struct pt_regs *regs); asmlinkage void do_irq(struct pt_regs *regs); diff --git a/arch/riscv/include/asm/asm.h b/arch/riscv/include/asm/asm.h index 776354895b81..a8a2af6dfe9d 100644 --- a/arch/riscv/include/asm/asm.h +++ b/arch/riscv/include/asm/asm.h @@ -27,6 +27,7 @@ #define REG_ASM __REG_SEL(.dword, .word) #define SZREG __REG_SEL(8, 4) #define LGREG __REG_SEL(3, 2) +#define SRLI __REG_SEL(srliw, srli) #if __SIZEOF_POINTER__ == 8 #ifdef __ASSEMBLY__ diff --git a/arch/riscv/include/asm/bitops.h b/arch/riscv/include/asm/bitops.h index fae152ea0508..d59310f74c2b 100644 --- a/arch/riscv/include/asm/bitops.h +++ b/arch/riscv/include/asm/bitops.h @@ -15,7 +15,7 @@ #include <asm/barrier.h> #include <asm/bitsperlong.h> -#if !defined(CONFIG_RISCV_ISA_ZBB) || defined(NO_ALTERNATIVE) +#if !(defined(CONFIG_RISCV_ISA_ZBB) && defined(CONFIG_TOOLCHAIN_HAS_ZBB)) || defined(NO_ALTERNATIVE) #include <asm-generic/bitops/__ffs.h> #include <asm-generic/bitops/__fls.h> #include <asm-generic/bitops/ffs.h> @@ -175,7 +175,7 @@ legacy: variable_fls(x_); \ }) -#endif /* !defined(CONFIG_RISCV_ISA_ZBB) || defined(NO_ALTERNATIVE) */ +#endif /* !(defined(CONFIG_RISCV_ISA_ZBB) && defined(CONFIG_TOOLCHAIN_HAS_ZBB)) || defined(NO_ALTERNATIVE) */ #include <asm-generic/bitops/ffz.h> #include <asm-generic/bitops/fls64.h> @@ -226,9 +226,9 @@ legacy: * @nr: Bit to set * @addr: Address to count from * - * This operation may be reordered on other architectures than x86. + * This is an atomic fully-ordered operation (implied full memory barrier). */ -static inline int arch_test_and_set_bit(int nr, volatile unsigned long *addr) +static __always_inline int arch_test_and_set_bit(int nr, volatile unsigned long *addr) { return __test_and_op_bit(or, __NOP, nr, addr); } @@ -238,9 +238,9 @@ static inline int arch_test_and_set_bit(int nr, volatile unsigned long *addr) * @nr: Bit to clear * @addr: Address to count from * - * This operation can be reordered on other architectures other than x86. + * This is an atomic fully-ordered operation (implied full memory barrier). */ -static inline int arch_test_and_clear_bit(int nr, volatile unsigned long *addr) +static __always_inline int arch_test_and_clear_bit(int nr, volatile unsigned long *addr) { return __test_and_op_bit(and, __NOT, nr, addr); } @@ -253,7 +253,7 @@ static inline int arch_test_and_clear_bit(int nr, volatile unsigned long *addr) * This operation is atomic and cannot be reordered. * It also implies a memory barrier. */ -static inline int arch_test_and_change_bit(int nr, volatile unsigned long *addr) +static __always_inline int arch_test_and_change_bit(int nr, volatile unsigned long *addr) { return __test_and_op_bit(xor, __NOP, nr, addr); } @@ -270,7 +270,7 @@ static inline int arch_test_and_change_bit(int nr, volatile unsigned long *addr) * Note that @nr may be almost arbitrarily large; this function is not * restricted to acting on a single-word quantity. */ -static inline void arch_set_bit(int nr, volatile unsigned long *addr) +static __always_inline void arch_set_bit(int nr, volatile unsigned long *addr) { __op_bit(or, __NOP, nr, addr); } @@ -284,7 +284,7 @@ static inline void arch_set_bit(int nr, volatile unsigned long *addr) * on non x86 architectures, so if you are writing portable code, * make sure not to rely on its reordering guarantees. */ -static inline void arch_clear_bit(int nr, volatile unsigned long *addr) +static __always_inline void arch_clear_bit(int nr, volatile unsigned long *addr) { __op_bit(and, __NOT, nr, addr); } @@ -298,7 +298,7 @@ static inline void arch_clear_bit(int nr, volatile unsigned long *addr) * Note that @nr may be almost arbitrarily large; this function is not * restricted to acting on a single-word quantity. */ -static inline void arch_change_bit(int nr, volatile unsigned long *addr) +static __always_inline void arch_change_bit(int nr, volatile unsigned long *addr) { __op_bit(xor, __NOP, nr, addr); } @@ -311,7 +311,7 @@ static inline void arch_change_bit(int nr, volatile unsigned long *addr) * This operation is atomic and provides acquire barrier semantics. * It can be used to implement bit locks. */ -static inline int arch_test_and_set_bit_lock( +static __always_inline int arch_test_and_set_bit_lock( unsigned long nr, volatile unsigned long *addr) { return __test_and_op_bit_ord(or, __NOP, nr, addr, .aq); @@ -324,7 +324,7 @@ static inline int arch_test_and_set_bit_lock( * * This operation is atomic and provides release barrier semantics. */ -static inline void arch_clear_bit_unlock( +static __always_inline void arch_clear_bit_unlock( unsigned long nr, volatile unsigned long *addr) { __op_bit_ord(and, __NOT, nr, addr, .rl); @@ -345,13 +345,13 @@ static inline void arch_clear_bit_unlock( * non-atomic property here: it's a lot more instructions and we still have to * provide release semantics anyway. */ -static inline void arch___clear_bit_unlock( +static __always_inline void arch___clear_bit_unlock( unsigned long nr, volatile unsigned long *addr) { arch_clear_bit_unlock(nr, addr); } -static inline bool arch_xor_unlock_is_negative_byte(unsigned long mask, +static __always_inline bool arch_xor_unlock_is_negative_byte(unsigned long mask, volatile unsigned long *addr) { unsigned long res; diff --git a/arch/riscv/include/asm/bugs.h b/arch/riscv/include/asm/bugs.h new file mode 100644 index 000000000000..17ca0a947730 --- /dev/null +++ b/arch/riscv/include/asm/bugs.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Interface for managing mitigations for riscv vulnerabilities. + * + * Copyright (C) 2024 Rivos Inc. + */ + +#ifndef __ASM_BUGS_H +#define __ASM_BUGS_H + +/* Watch out, ordering is important here. */ +enum mitigation_state { + UNAFFECTED, + MITIGATED, + VULNERABLE, +}; + +void ghostwrite_set_vulnerable(void); +bool ghostwrite_enable_mitigation(void); +enum mitigation_state ghostwrite_get_state(void); + +#endif /* __ASM_BUGS_H */ diff --git a/arch/riscv/include/asm/cacheflush.h b/arch/riscv/include/asm/cacheflush.h index 8de73f91bfa3..b59ffeb668d6 100644 --- a/arch/riscv/include/asm/cacheflush.h +++ b/arch/riscv/include/asm/cacheflush.h @@ -34,11 +34,6 @@ static inline void flush_dcache_page(struct page *page) flush_dcache_folio(page_folio(page)); } -/* - * RISC-V doesn't have an instruction to flush parts of the instruction cache, - * so instead we just flush the whole thing. - */ -#define flush_icache_range(start, end) flush_icache_all() #define flush_icache_user_page(vma, pg, addr, len) \ do { \ if (vma->vm_flags & VM_EXEC) \ @@ -78,6 +73,16 @@ void flush_icache_mm(struct mm_struct *mm, bool local); #endif /* CONFIG_SMP */ +/* + * RISC-V doesn't have an instruction to flush parts of the instruction cache, + * so instead we just flush the whole thing. + */ +#define flush_icache_range flush_icache_range +static inline void flush_icache_range(unsigned long start, unsigned long end) +{ + flush_icache_all(); +} + extern unsigned int riscv_cbom_block_size; extern unsigned int riscv_cboz_block_size; void riscv_init_cbo_blocksizes(void); diff --git a/arch/riscv/include/asm/checksum.h b/arch/riscv/include/asm/checksum.h index 88e6f1499e88..da378856f1d5 100644 --- a/arch/riscv/include/asm/checksum.h +++ b/arch/riscv/include/asm/checksum.h @@ -49,8 +49,7 @@ static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl) * ZBB only saves three instructions on 32-bit and five on 64-bit so not * worth checking if supported without Alternatives. */ - if (IS_ENABLED(CONFIG_RISCV_ISA_ZBB) && - IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) { + if (IS_ENABLED(CONFIG_RISCV_ISA_ZBB) && IS_ENABLED(CONFIG_TOOLCHAIN_HAS_ZBB)) { unsigned long fold_temp; asm goto(ALTERNATIVE("j %l[no_zbb]", "nop", 0, diff --git a/arch/riscv/include/asm/cmpxchg.h b/arch/riscv/include/asm/cmpxchg.h index 4cadc56220fe..2ec119eb147b 100644 --- a/arch/riscv/include/asm/cmpxchg.h +++ b/arch/riscv/include/asm/cmpxchg.h @@ -231,7 +231,7 @@ __arch_cmpxchg(".w", ".w" sc_sfx, ".w" cas_sfx, \ sc_prepend, sc_append, \ cas_prepend, cas_append, \ - __ret, __ptr, (long), __old, __new); \ + __ret, __ptr, (long)(int)(long), __old, __new); \ break; \ case 8: \ __arch_cmpxchg(".d", ".d" sc_sfx, ".d" cas_sfx, \ @@ -365,16 +365,48 @@ static __always_inline void __cmpwait(volatile void *ptr, { unsigned long tmp; + u32 *__ptr32b; + ulong __s, __val, __mask; + asm goto(ALTERNATIVE("j %l[no_zawrs]", "nop", 0, RISCV_ISA_EXT_ZAWRS, 1) : : : : no_zawrs); switch (size) { case 1: - fallthrough; + __ptr32b = (u32 *)((ulong)(ptr) & ~0x3); + __s = ((ulong)(ptr) & 0x3) * BITS_PER_BYTE; + __val = val << __s; + __mask = 0xff << __s; + + asm volatile( + " lr.w %0, %1\n" + " and %0, %0, %3\n" + " xor %0, %0, %2\n" + " bnez %0, 1f\n" + ZAWRS_WRS_NTO "\n" + "1:" + : "=&r" (tmp), "+A" (*(__ptr32b)) + : "r" (__val), "r" (__mask) + : "memory"); + break; case 2: - /* RISC-V doesn't have lr instructions on byte and half-word. */ - goto no_zawrs; + __ptr32b = (u32 *)((ulong)(ptr) & ~0x3); + __s = ((ulong)(ptr) & 0x2) * BITS_PER_BYTE; + __val = val << __s; + __mask = 0xffff << __s; + + asm volatile( + " lr.w %0, %1\n" + " and %0, %0, %3\n" + " xor %0, %0, %2\n" + " bnez %0, 1f\n" + ZAWRS_WRS_NTO "\n" + "1:" + : "=&r" (tmp), "+A" (*(__ptr32b)) + : "r" (__val), "r" (__mask) + : "memory"); + break; case 4: asm volatile( " lr.w %0, %1\n" diff --git a/arch/riscv/include/asm/cpufeature.h b/arch/riscv/include/asm/cpufeature.h index 4bd054c54c21..f56b409361fb 100644 --- a/arch/riscv/include/asm/cpufeature.h +++ b/arch/riscv/include/asm/cpufeature.h @@ -34,6 +34,8 @@ DECLARE_PER_CPU(struct riscv_cpuinfo, riscv_cpuinfo); /* Per-cpu ISA extensions. */ extern struct riscv_isainfo hart_isa[NR_CPUS]; +extern u32 thead_vlenb_of; + void __init riscv_user_isa_enable(void); #define _RISCV_ISA_EXT_DATA(_name, _id, _subset_exts, _subset_exts_size, _validate) { \ @@ -54,6 +56,9 @@ void __init riscv_user_isa_enable(void); #define __RISCV_ISA_EXT_BUNDLE(_name, _bundled_exts) \ _RISCV_ISA_EXT_DATA(_name, RISCV_ISA_EXT_INVALID, _bundled_exts, \ ARRAY_SIZE(_bundled_exts), NULL) +#define __RISCV_ISA_EXT_BUNDLE_VALIDATE(_name, _bundled_exts, _validate) \ + _RISCV_ISA_EXT_DATA(_name, RISCV_ISA_EXT_INVALID, _bundled_exts, \ + ARRAY_SIZE(_bundled_exts), _validate) /* Used to declare extensions that are a superset of other extensions (Zvbb for instance) */ #define __RISCV_ISA_EXT_SUPERSET(_name, _id, _sub_exts) \ @@ -61,7 +66,7 @@ void __init riscv_user_isa_enable(void); #define __RISCV_ISA_EXT_SUPERSET_VALIDATE(_name, _id, _sub_exts, _validate) \ _RISCV_ISA_EXT_DATA(_name, _id, _sub_exts, ARRAY_SIZE(_sub_exts), _validate) -bool check_unaligned_access_emulated_all_cpus(void); +bool __init check_unaligned_access_emulated_all_cpus(void); #if defined(CONFIG_RISCV_SCALAR_MISALIGNED) void check_unaligned_access_emulated(struct work_struct *work __always_unused); void unaligned_emulation_finish(void); @@ -74,7 +79,7 @@ static inline bool unaligned_ctl_available(void) } #endif -bool check_vector_unaligned_access_emulated_all_cpus(void); +bool __init check_vector_unaligned_access_emulated_all_cpus(void); #if defined(CONFIG_RISCV_VECTOR_MISALIGNED) void check_vector_unaligned_access_emulated(struct work_struct *work __always_unused); DECLARE_PER_CPU(long, vector_misaligned_access); diff --git a/arch/riscv/include/asm/csr.h b/arch/riscv/include/asm/csr.h index 37bdea65bbd8..6fed42e37705 100644 --- a/arch/riscv/include/asm/csr.h +++ b/arch/riscv/include/asm/csr.h @@ -30,6 +30,12 @@ #define SR_VS_CLEAN _AC(0x00000400, UL) #define SR_VS_DIRTY _AC(0x00000600, UL) +#define SR_VS_THEAD _AC(0x01800000, UL) /* xtheadvector Status */ +#define SR_VS_OFF_THEAD _AC(0x00000000, UL) +#define SR_VS_INITIAL_THEAD _AC(0x00800000, UL) +#define SR_VS_CLEAN_THEAD _AC(0x01000000, UL) +#define SR_VS_DIRTY_THEAD _AC(0x01800000, UL) + #define SR_XS _AC(0x00018000, UL) /* Extension Status */ #define SR_XS_OFF _AC(0x00000000, UL) #define SR_XS_INITIAL _AC(0x00008000, UL) @@ -315,6 +321,15 @@ #define CSR_STIMECMP 0x14D #define CSR_STIMECMPH 0x15D +/* xtheadvector symbolic CSR names */ +#define CSR_VXSAT 0x9 +#define CSR_VXRM 0xa + +/* xtheadvector CSR masks */ +#define CSR_VXRM_MASK 3 +#define CSR_VXRM_SHIFT 1 +#define CSR_VXSAT_MASK 1 + /* Supervisor-Level Window to Indirectly Accessed Registers (AIA) */ #define CSR_SISELECT 0x150 #define CSR_SIREG 0x151 diff --git a/arch/riscv/include/asm/errata_list.h b/arch/riscv/include/asm/errata_list.h index 7c8a71a526a3..6e426ed7919a 100644 --- a/arch/riscv/include/asm/errata_list.h +++ b/arch/riscv/include/asm/errata_list.h @@ -25,7 +25,8 @@ #ifdef CONFIG_ERRATA_THEAD #define ERRATA_THEAD_MAE 0 #define ERRATA_THEAD_PMU 1 -#define ERRATA_THEAD_NUMBER 2 +#define ERRATA_THEAD_GHOSTWRITE 2 +#define ERRATA_THEAD_NUMBER 3 #endif #ifdef __ASSEMBLY__ diff --git a/arch/riscv/include/asm/ftrace.h b/arch/riscv/include/asm/ftrace.h index 3d66437a1029..d627f63ee289 100644 --- a/arch/riscv/include/asm/ftrace.h +++ b/arch/riscv/include/asm/ftrace.h @@ -79,7 +79,6 @@ struct dyn_arch_ftrace { #define AUIPC_RA (0x00000097) #define JALR_T0 (0x000282e7) #define AUIPC_T0 (0x00000297) -#define NOP4 (0x00000013) #define to_jalr_t0(offset) \ (((offset & JALR_OFFSET_MASK) << JALR_SHIFT) | JALR_T0) @@ -92,7 +91,7 @@ struct dyn_arch_ftrace { #define make_call_t0(caller, callee, call) \ do { \ unsigned int offset = \ - (unsigned long) callee - (unsigned long) caller; \ + (unsigned long) (callee) - (unsigned long) (caller); \ call[0] = to_auipc_t0(offset); \ call[1] = to_jalr_t0(offset); \ } while (0) @@ -108,7 +107,7 @@ do { \ #define make_call_ra(caller, callee, call) \ do { \ unsigned int offset = \ - (unsigned long) callee - (unsigned long) caller; \ + (unsigned long) (callee) - (unsigned long) (caller); \ call[0] = to_auipc_ra(offset); \ call[1] = to_jalr_ra(offset); \ } while (0) @@ -168,6 +167,11 @@ static __always_inline unsigned long ftrace_regs_get_stack_pointer(const struct return arch_ftrace_regs(fregs)->sp; } +static __always_inline unsigned long ftrace_regs_get_frame_pointer(const struct ftrace_regs *fregs) +{ + return arch_ftrace_regs(fregs)->s0; +} + static __always_inline unsigned long ftrace_regs_get_argument(struct ftrace_regs *fregs, unsigned int n) { @@ -181,6 +185,11 @@ static __always_inline unsigned long ftrace_regs_get_return_value(const struct f return arch_ftrace_regs(fregs)->a0; } +static __always_inline unsigned long ftrace_regs_get_return_address(const struct ftrace_regs *fregs) +{ + return arch_ftrace_regs(fregs)->ra; +} + static __always_inline void ftrace_regs_set_return_value(struct ftrace_regs *fregs, unsigned long ret) { @@ -192,6 +201,20 @@ static __always_inline void ftrace_override_function_with_return(struct ftrace_r arch_ftrace_regs(fregs)->epc = arch_ftrace_regs(fregs)->ra; } +static __always_inline struct pt_regs * +ftrace_partial_regs(const struct ftrace_regs *fregs, struct pt_regs *regs) +{ + struct __arch_ftrace_regs *afregs = arch_ftrace_regs(fregs); + + memcpy(®s->a_regs, afregs->args, sizeof(afregs->args)); + regs->epc = afregs->epc; + regs->ra = afregs->ra; + regs->sp = afregs->sp; + regs->s0 = afregs->s0; + regs->t1 = afregs->t1; + return regs; +} + int ftrace_regs_query_register_offset(const char *name); void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, @@ -208,25 +231,4 @@ static inline void arch_ftrace_set_direct_caller(struct ftrace_regs *fregs, unsi #endif /* CONFIG_DYNAMIC_FTRACE */ -#ifndef __ASSEMBLY__ -#ifdef CONFIG_FUNCTION_GRAPH_TRACER -struct fgraph_ret_regs { - unsigned long a1; - unsigned long a0; - unsigned long s0; - unsigned long ra; -}; - -static inline unsigned long fgraph_ret_regs_return_value(struct fgraph_ret_regs *ret_regs) -{ - return ret_regs->a0; -} - -static inline unsigned long fgraph_ret_regs_frame_pointer(struct fgraph_ret_regs *ret_regs) -{ - return ret_regs->s0; -} -#endif /* ifdef CONFIG_FUNCTION_GRAPH_TRACER */ -#endif - #endif /* _ASM_RISCV_FTRACE_H */ diff --git a/arch/riscv/include/asm/futex.h b/arch/riscv/include/asm/futex.h index fc8130f995c1..90c86b115e00 100644 --- a/arch/riscv/include/asm/futex.h +++ b/arch/riscv/include/asm/futex.h @@ -85,7 +85,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, __enable_user_access(); __asm__ __volatile__ ( - "1: lr.w.aqrl %[v],%[u] \n" + "1: lr.w %[v],%[u] \n" " bne %[v],%z[ov],3f \n" "2: sc.w.aqrl %[t],%z[nv],%[u] \n" " bnez %[t],1b \n" @@ -93,7 +93,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, _ASM_EXTABLE_UACCESS_ERR(1b, 3b, %[r]) \ _ASM_EXTABLE_UACCESS_ERR(2b, 3b, %[r]) \ : [r] "+r" (ret), [v] "=&r" (val), [u] "+m" (*uaddr), [t] "=&r" (tmp) - : [ov] "Jr" (oldval), [nv] "Jr" (newval) + : [ov] "Jr" ((long)(int)oldval), [nv] "Jr" (newval) : "memory"); __disable_user_access(); diff --git a/arch/riscv/include/asm/hugetlb.h b/arch/riscv/include/asm/hugetlb.h index faf3624d8057..446126497768 100644 --- a/arch/riscv/include/asm/hugetlb.h +++ b/arch/riscv/include/asm/hugetlb.h @@ -28,7 +28,8 @@ void set_huge_pte_at(struct mm_struct *mm, #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR pte_t huge_ptep_get_and_clear(struct mm_struct *mm, - unsigned long addr, pte_t *ptep); + unsigned long addr, pte_t *ptep, + unsigned long sz); #define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH pte_t huge_ptep_clear_flush(struct vm_area_struct *vma, diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h index 869da082252a..e3cbf203cdde 100644 --- a/arch/riscv/include/asm/hwcap.h +++ b/arch/riscv/include/asm/hwcap.h @@ -100,6 +100,11 @@ #define RISCV_ISA_EXT_ZICCRSE 91 #define RISCV_ISA_EXT_SVADE 92 #define RISCV_ISA_EXT_SVADU 93 +#define RISCV_ISA_EXT_ZFBFMIN 94 +#define RISCV_ISA_EXT_ZVFBFMIN 95 +#define RISCV_ISA_EXT_ZVFBFWMA 96 +#define RISCV_ISA_EXT_ZAAMO 97 +#define RISCV_ISA_EXT_ZALRSC 98 #define RISCV_ISA_EXT_XLINUXENVCFG 127 diff --git a/arch/riscv/include/asm/hwprobe.h b/arch/riscv/include/asm/hwprobe.h index 1ce1df6d0ff3..1f690fea0e03 100644 --- a/arch/riscv/include/asm/hwprobe.h +++ b/arch/riscv/include/asm/hwprobe.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* - * Copyright 2023 Rivos, Inc + * Copyright 2023-2024 Rivos, Inc */ #ifndef _ASM_HWPROBE_H @@ -8,7 +8,7 @@ #include <uapi/asm/hwprobe.h> -#define RISCV_HWPROBE_MAX_KEY 10 +#define RISCV_HWPROBE_MAX_KEY 12 static inline bool riscv_hwprobe_key_is_valid(__s64 key) { @@ -21,6 +21,7 @@ static inline bool hwprobe_key_is_bitmask(__s64 key) case RISCV_HWPROBE_KEY_BASE_BEHAVIOR: case RISCV_HWPROBE_KEY_IMA_EXT_0: case RISCV_HWPROBE_KEY_CPUPERF_0: + case RISCV_HWPROBE_KEY_VENDOR_EXT_THEAD_0: return true; } diff --git a/arch/riscv/include/asm/insn-def.h b/arch/riscv/include/asm/insn-def.h index 9a913010cdd9..71060a2f838e 100644 --- a/arch/riscv/include/asm/insn-def.h +++ b/arch/riscv/include/asm/insn-def.h @@ -199,5 +199,8 @@ #define RISCV_PAUSE ".4byte 0x100000f" #define ZAWRS_WRS_NTO ".4byte 0x00d00073" #define ZAWRS_WRS_STO ".4byte 0x01d00073" +#define RISCV_NOP4 ".4byte 0x00000013" + +#define RISCV_INSN_NOP4 _AC(0x00000013, U) #endif /* __ASM_INSN_DEF_H */ diff --git a/arch/riscv/include/asm/io.h b/arch/riscv/include/asm/io.h index 1c5c641075d2..a0e51840b9db 100644 --- a/arch/riscv/include/asm/io.h +++ b/arch/riscv/include/asm/io.h @@ -136,8 +136,8 @@ __io_writes_outs(outs, u64, q, __io_pbr(), __io_paw()) #include <asm-generic/io.h> #ifdef CONFIG_MMU -#define arch_memremap_wb(addr, size) \ - ((__force void *)ioremap_prot((addr), (size), _PAGE_KERNEL)) +#define arch_memremap_wb(addr, size, flags) \ + ((__force void *)ioremap_prot((addr), (size), __pgprot(_PAGE_KERNEL))) #endif #endif /* _ASM_RISCV_IO_H */ diff --git a/arch/riscv/include/asm/kgdb.h b/arch/riscv/include/asm/kgdb.h index 46677daf708b..cc11c4544cff 100644 --- a/arch/riscv/include/asm/kgdb.h +++ b/arch/riscv/include/asm/kgdb.h @@ -19,16 +19,9 @@ #ifndef __ASSEMBLY__ +void arch_kgdb_breakpoint(void); extern unsigned long kgdb_compiled_break; -static inline void arch_kgdb_breakpoint(void) -{ - asm(".global kgdb_compiled_break\n" - ".option norvc\n" - "kgdb_compiled_break: ebreak\n" - ".option rvc\n"); -} - #endif /* !__ASSEMBLY__ */ #define DBG_REG_ZERO "zero" diff --git a/arch/riscv/include/asm/kvm_aia.h b/arch/riscv/include/asm/kvm_aia.h index 1f37b600ca47..3b643b9efc07 100644 --- a/arch/riscv/include/asm/kvm_aia.h +++ b/arch/riscv/include/asm/kvm_aia.h @@ -63,9 +63,6 @@ struct kvm_vcpu_aia { /* CPU AIA CSR context of Guest VCPU */ struct kvm_vcpu_aia_csr guest_csr; - /* CPU AIA CSR context upon Guest VCPU reset */ - struct kvm_vcpu_aia_csr guest_reset_csr; - /* Guest physical address of IMSIC for this VCPU */ gpa_t imsic_addr; diff --git a/arch/riscv/include/asm/kvm_host.h b/arch/riscv/include/asm/kvm_host.h index 35eab6e0f4ae..85cfebc32e4c 100644 --- a/arch/riscv/include/asm/kvm_host.h +++ b/arch/riscv/include/asm/kvm_host.h @@ -87,6 +87,11 @@ struct kvm_vcpu_stat { u64 csr_exit_kernel; u64 signal_exits; u64 exits; + u64 instr_illegal_exits; + u64 load_misaligned_exits; + u64 store_misaligned_exits; + u64 load_access_exits; + u64 store_access_exits; }; struct kvm_arch_memory_slot { @@ -114,6 +119,9 @@ struct kvm_arch { /* AIA Guest/VM context */ struct kvm_aia aia; + + /* KVM_CAP_RISCV_MP_STATE_RESET */ + bool mp_state_reset; }; struct kvm_cpu_trap { @@ -188,6 +196,12 @@ struct kvm_vcpu_smstateen_csr { unsigned long sstateen0; }; +struct kvm_vcpu_reset_state { + spinlock_t lock; + unsigned long pc; + unsigned long a1; +}; + struct kvm_vcpu_arch { /* VCPU ran at least once */ bool ran_atleast_once; @@ -222,12 +236,8 @@ struct kvm_vcpu_arch { /* CPU Smstateen CSR context of Guest VCPU */ struct kvm_vcpu_smstateen_csr smstateen_csr; - /* CPU context upon Guest VCPU reset */ - struct kvm_cpu_context guest_reset_context; - spinlock_t reset_cntx_lock; - - /* CPU CSR context upon Guest VCPU reset */ - struct kvm_vcpu_csr guest_reset_csr; + /* CPU reset state of Guest VCPU */ + struct kvm_vcpu_reset_state reset_state; /* * VCPU interrupts @@ -296,8 +306,6 @@ static inline bool kvm_arch_pmi_in_guest(struct kvm_vcpu *vcpu) return IS_ENABLED(CONFIG_GUEST_PERF_EVENTS) && !!vcpu; } -static inline void kvm_arch_sync_events(struct kvm *kvm) {} - #define KVM_RISCV_GSTAGE_TLB_MIN_ORDER 12 void kvm_riscv_local_hfence_gvma_vmid_gpa(unsigned long vmid, diff --git a/arch/riscv/include/asm/kvm_vcpu_sbi.h b/arch/riscv/include/asm/kvm_vcpu_sbi.h index b96705258cf9..439ab2b3534f 100644 --- a/arch/riscv/include/asm/kvm_vcpu_sbi.h +++ b/arch/riscv/include/asm/kvm_vcpu_sbi.h @@ -55,6 +55,9 @@ void kvm_riscv_vcpu_sbi_forward(struct kvm_vcpu *vcpu, struct kvm_run *run); void kvm_riscv_vcpu_sbi_system_reset(struct kvm_vcpu *vcpu, struct kvm_run *run, u32 type, u64 flags); +void kvm_riscv_vcpu_sbi_request_reset(struct kvm_vcpu *vcpu, + unsigned long pc, unsigned long a1); +void kvm_riscv_vcpu_sbi_load_reset_state(struct kvm_vcpu *vcpu); int kvm_riscv_vcpu_sbi_return(struct kvm_vcpu *vcpu, struct kvm_run *run); int kvm_riscv_vcpu_set_reg_sbi_ext(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg); @@ -85,6 +88,7 @@ extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_rfence; extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_srst; extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_hsm; extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_dbcn; +extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_susp; extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_sta; extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_experimental; extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_vendor; diff --git a/arch/riscv/include/asm/kvm_vcpu_vector.h b/arch/riscv/include/asm/kvm_vcpu_vector.h index 27f5bccdd8b0..57a798a4cb0d 100644 --- a/arch/riscv/include/asm/kvm_vcpu_vector.h +++ b/arch/riscv/include/asm/kvm_vcpu_vector.h @@ -33,8 +33,7 @@ void kvm_riscv_vcpu_guest_vector_restore(struct kvm_cpu_context *cntx, unsigned long *isa); void kvm_riscv_vcpu_host_vector_save(struct kvm_cpu_context *cntx); void kvm_riscv_vcpu_host_vector_restore(struct kvm_cpu_context *cntx); -int kvm_riscv_vcpu_alloc_vector_context(struct kvm_vcpu *vcpu, - struct kvm_cpu_context *cntx); +int kvm_riscv_vcpu_alloc_vector_context(struct kvm_vcpu *vcpu); void kvm_riscv_vcpu_free_vector_context(struct kvm_vcpu *vcpu); #else @@ -62,8 +61,7 @@ static inline void kvm_riscv_vcpu_host_vector_restore(struct kvm_cpu_context *cn { } -static inline int kvm_riscv_vcpu_alloc_vector_context(struct kvm_vcpu *vcpu, - struct kvm_cpu_context *cntx) +static inline int kvm_riscv_vcpu_alloc_vector_context(struct kvm_vcpu *vcpu) { return 0; } diff --git a/arch/riscv/include/asm/page.h b/arch/riscv/include/asm/page.h index 125f5ecd9565..572a141ddecd 100644 --- a/arch/riscv/include/asm/page.h +++ b/arch/riscv/include/asm/page.h @@ -24,21 +24,22 @@ * When not using MMU this corresponds to the first free page in * physical memory (aligned on a page boundary). */ -#ifdef CONFIG_64BIT #ifdef CONFIG_MMU -#define PAGE_OFFSET kernel_map.page_offset -#else -#define PAGE_OFFSET _AC(CONFIG_PAGE_OFFSET, UL) -#endif -/* - * By default, CONFIG_PAGE_OFFSET value corresponds to SV57 address space so - * define the PAGE_OFFSET value for SV48 and SV39. - */ +#ifdef CONFIG_64BIT +#define PAGE_OFFSET_L5 _AC(0xff60000000000000, UL) #define PAGE_OFFSET_L4 _AC(0xffffaf8000000000, UL) #define PAGE_OFFSET_L3 _AC(0xffffffd600000000, UL) +#ifdef CONFIG_XIP_KERNEL +#define PAGE_OFFSET PAGE_OFFSET_L3 #else -#define PAGE_OFFSET _AC(CONFIG_PAGE_OFFSET, UL) +#define PAGE_OFFSET kernel_map.page_offset +#endif /* CONFIG_XIP_KERNEL */ +#else +#define PAGE_OFFSET _AC(0xc0000000, UL) #endif /* CONFIG_64BIT */ +#else +#define PAGE_OFFSET ((unsigned long)phys_ram_base) +#endif /* CONFIG_MMU */ #ifndef __ASSEMBLY__ @@ -95,14 +96,9 @@ typedef struct page *pgtable_t; #define MIN_MEMBLOCK_ADDR 0 #endif -#ifdef CONFIG_MMU #define ARCH_PFN_OFFSET (PFN_DOWN((unsigned long)phys_ram_base)) -#else -#define ARCH_PFN_OFFSET (PAGE_OFFSET >> PAGE_SHIFT) -#endif /* CONFIG_MMU */ struct kernel_mapping { - unsigned long page_offset; unsigned long virt_addr; unsigned long virt_offset; uintptr_t phys_addr; @@ -116,6 +112,7 @@ struct kernel_mapping { uintptr_t xiprom; uintptr_t xiprom_sz; #else + unsigned long page_offset; unsigned long va_kernel_pa_offset; #endif }; diff --git a/arch/riscv/include/asm/pgalloc.h b/arch/riscv/include/asm/pgalloc.h index f52264304f77..770ce18a7328 100644 --- a/arch/riscv/include/asm/pgalloc.h +++ b/arch/riscv/include/asm/pgalloc.h @@ -12,18 +12,9 @@ #include <asm/tlb.h> #ifdef CONFIG_MMU -#define __HAVE_ARCH_PUD_ALLOC_ONE #define __HAVE_ARCH_PUD_FREE #include <asm-generic/pgalloc.h> -static inline void riscv_tlb_remove_ptdesc(struct mmu_gather *tlb, void *pt) -{ - if (riscv_use_sbi_for_rfence()) - tlb_remove_ptdesc(tlb, pt); - else - tlb_remove_page_ptdesc(tlb, pt); -} - static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, pte_t *pte) { @@ -88,15 +79,6 @@ static inline void pgd_populate_safe(struct mm_struct *mm, pgd_t *pgd, } } -#define pud_alloc_one pud_alloc_one -static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr) -{ - if (pgtable_l4_enabled) - return __pud_alloc_one(mm, addr); - - return NULL; -} - #define pud_free pud_free static inline void pud_free(struct mm_struct *mm, pud_t *pud) { @@ -107,46 +89,15 @@ static inline void pud_free(struct mm_struct *mm, pud_t *pud) static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud, unsigned long addr) { - if (pgtable_l4_enabled) { - struct ptdesc *ptdesc = virt_to_ptdesc(pud); - - pagetable_pud_dtor(ptdesc); - riscv_tlb_remove_ptdesc(tlb, ptdesc); - } -} - -#define p4d_alloc_one p4d_alloc_one -static inline p4d_t *p4d_alloc_one(struct mm_struct *mm, unsigned long addr) -{ - if (pgtable_l5_enabled) { - gfp_t gfp = GFP_PGTABLE_USER; - - if (mm == &init_mm) - gfp = GFP_PGTABLE_KERNEL; - return (p4d_t *)get_zeroed_page(gfp); - } - - return NULL; -} - -static inline void __p4d_free(struct mm_struct *mm, p4d_t *p4d) -{ - BUG_ON((unsigned long)p4d & (PAGE_SIZE-1)); - free_page((unsigned long)p4d); -} - -#define p4d_free p4d_free -static inline void p4d_free(struct mm_struct *mm, p4d_t *p4d) -{ - if (pgtable_l5_enabled) - __p4d_free(mm, p4d); + if (pgtable_l4_enabled) + tlb_remove_ptdesc(tlb, virt_to_ptdesc(pud)); } static inline void __p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d, unsigned long addr) { if (pgtable_l5_enabled) - riscv_tlb_remove_ptdesc(tlb, virt_to_ptdesc(p4d)); + tlb_remove_ptdesc(tlb, virt_to_ptdesc(p4d)); } #endif /* __PAGETABLE_PMD_FOLDED */ @@ -161,9 +112,8 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm) { pgd_t *pgd; - pgd = (pgd_t *)__get_free_page(GFP_KERNEL); + pgd = __pgd_alloc(mm, 0); if (likely(pgd != NULL)) { - memset(pgd, 0, USER_PTRS_PER_PGD * sizeof(pgd_t)); /* Copy kernel mappings */ sync_kernel_mappings(pgd); } @@ -175,10 +125,7 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm) static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd, unsigned long addr) { - struct ptdesc *ptdesc = virt_to_ptdesc(pmd); - - pagetable_pmd_dtor(ptdesc); - riscv_tlb_remove_ptdesc(tlb, ptdesc); + tlb_remove_ptdesc(tlb, virt_to_ptdesc(pmd)); } #endif /* __PAGETABLE_PMD_FOLDED */ @@ -186,10 +133,7 @@ static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd, static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte, unsigned long addr) { - struct ptdesc *ptdesc = page_ptdesc(pte); - - pagetable_pte_dtor(ptdesc); - riscv_tlb_remove_ptdesc(tlb, ptdesc); + tlb_remove_ptdesc(tlb, page_ptdesc(pte)); } #endif /* CONFIG_MMU */ diff --git a/arch/riscv/include/asm/pgtable-64.h b/arch/riscv/include/asm/pgtable-64.h index 0897dd99ab8d..188fadc1c21f 100644 --- a/arch/riscv/include/asm/pgtable-64.h +++ b/arch/riscv/include/asm/pgtable-64.h @@ -262,8 +262,6 @@ static inline unsigned long _pmd_pfn(pmd_t pmd) return __page_val_to_pfn(pmd_val(pmd)); } -#define mk_pmd(page, prot) pfn_pmd(page_to_pfn(page), prot) - #define pmd_ERROR(e) \ pr_err("%s:%d: bad pmd %016lx.\n", __FILE__, __LINE__, pmd_val(e)) diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 050fdc49b5ad..f19240fd018e 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -12,7 +12,11 @@ #include <asm/pgtable-bits.h> #ifndef CONFIG_MMU -#define KERNEL_LINK_ADDR PAGE_OFFSET +#ifdef CONFIG_RELOCATABLE +#define KERNEL_LINK_ADDR UL(0) +#else +#define KERNEL_LINK_ADDR _AC(CONFIG_PHYS_RAM_BASE, UL) +#endif #define KERN_VIRT_SIZE (UL(-1)) #else @@ -339,7 +343,13 @@ static inline pte_t pfn_pte(unsigned long pfn, pgprot_t prot) return __pte((pfn << _PAGE_PFN_SHIFT) | prot_val); } -#define mk_pte(page, prot) pfn_pte(page_to_pfn(page), prot) +#define pte_pgprot pte_pgprot +static inline pgprot_t pte_pgprot(pte_t pte) +{ + unsigned long pfn = pte_pfn(pte); + + return __pgprot(pte_val(pfn_pte(pfn, __pgprot(0))) ^ pte_val(pte)); +} static inline int pte_present(pte_t pte) { @@ -674,6 +684,11 @@ static inline pmd_t pte_pmd(pte_t pte) return __pmd(pte_val(pte)); } +static inline pud_t pte_pud(pte_t pte) +{ + return __pud(pte_val(pte)); +} + static inline pmd_t pmd_mkhuge(pmd_t pmd) { return pmd; @@ -699,6 +714,18 @@ static inline unsigned long pud_pfn(pud_t pud) return ((__pud_to_phys(pud) & PUD_MASK) >> PAGE_SHIFT); } +#define pmd_pgprot pmd_pgprot +static inline pgprot_t pmd_pgprot(pmd_t pmd) +{ + return pte_pgprot(pmd_pte(pmd)); +} + +#define pud_pgprot pud_pgprot +static inline pgprot_t pud_pgprot(pud_t pud) +{ + return pte_pgprot(pud_pte(pud)); +} + static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) { return pte_pmd(pte_modify(pmd_pte(pmd), newprot)); @@ -768,6 +795,30 @@ static inline pmd_t pmd_mkdevmap(pmd_t pmd) return pte_pmd(pte_mkdevmap(pmd_pte(pmd))); } +#ifdef CONFIG_ARCH_SUPPORTS_PMD_PFNMAP +static inline bool pmd_special(pmd_t pmd) +{ + return pte_special(pmd_pte(pmd)); +} + +static inline pmd_t pmd_mkspecial(pmd_t pmd) +{ + return pte_pmd(pte_mkspecial(pmd_pte(pmd))); +} +#endif + +#ifdef CONFIG_ARCH_SUPPORTS_PUD_PFNMAP +static inline bool pud_special(pud_t pud) +{ + return pte_special(pud_pte(pud)); +} + +static inline pud_t pud_mkspecial(pud_t pud) +{ + return pte_pud(pte_mkspecial(pud_pte(pud))); +} +#endif + static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, pmd_t pmd) { diff --git a/arch/riscv/include/asm/ptrace.h b/arch/riscv/include/asm/ptrace.h index b5b0adcc85c1..2910231977cb 100644 --- a/arch/riscv/include/asm/ptrace.h +++ b/arch/riscv/include/asm/ptrace.h @@ -23,14 +23,16 @@ struct pt_regs { unsigned long t2; unsigned long s0; unsigned long s1; - unsigned long a0; - unsigned long a1; - unsigned long a2; - unsigned long a3; - unsigned long a4; - unsigned long a5; - unsigned long a6; - unsigned long a7; + struct_group(a_regs, + unsigned long a0; + unsigned long a1; + unsigned long a2; + unsigned long a3; + unsigned long a4; + unsigned long a5; + unsigned long a6; + unsigned long a7; + ); unsigned long s2; unsigned long s3; unsigned long s4; diff --git a/arch/riscv/include/asm/runtime-const.h b/arch/riscv/include/asm/runtime-const.h new file mode 100644 index 000000000000..451fd76b8811 --- /dev/null +++ b/arch/riscv/include/asm/runtime-const.h @@ -0,0 +1,268 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_RISCV_RUNTIME_CONST_H +#define _ASM_RISCV_RUNTIME_CONST_H + +#include <asm/asm.h> +#include <asm/alternative.h> +#include <asm/cacheflush.h> +#include <asm/insn-def.h> +#include <linux/memory.h> +#include <asm/text-patching.h> + +#include <linux/uaccess.h> + +#ifdef CONFIG_32BIT +#define runtime_const_ptr(sym) \ +({ \ + typeof(sym) __ret; \ + asm_inline(".option push\n\t" \ + ".option norvc\n\t" \ + "1:\t" \ + "lui %[__ret],0x89abd\n\t" \ + "addi %[__ret],%[__ret],-0x211\n\t" \ + ".option pop\n\t" \ + ".pushsection runtime_ptr_" #sym ",\"a\"\n\t" \ + ".long 1b - .\n\t" \ + ".popsection" \ + : [__ret] "=r" (__ret)); \ + __ret; \ +}) +#else +/* + * Loading 64-bit constants into a register from immediates is a non-trivial + * task on riscv64. To get it somewhat performant, load 32 bits into two + * different registers and then combine the results. + * + * If the processor supports the Zbkb extension, we can combine the final + * "slli,slli,srli,add" into the single "pack" instruction. If the processor + * doesn't support Zbkb but does support the Zbb extension, we can + * combine the final "slli,srli,add" into one instruction "add.uw". + */ +#define RISCV_RUNTIME_CONST_64_PREAMBLE \ + ".option push\n\t" \ + ".option norvc\n\t" \ + "1:\t" \ + "lui %[__ret],0x89abd\n\t" \ + "lui %[__tmp],0x1234\n\t" \ + "addiw %[__ret],%[__ret],-0x211\n\t" \ + "addiw %[__tmp],%[__tmp],0x567\n\t" \ + +#define RISCV_RUNTIME_CONST_64_BASE \ + "slli %[__tmp],%[__tmp],32\n\t" \ + "slli %[__ret],%[__ret],32\n\t" \ + "srli %[__ret],%[__ret],32\n\t" \ + "add %[__ret],%[__ret],%[__tmp]\n\t" \ + +#define RISCV_RUNTIME_CONST_64_ZBA \ + ".option push\n\t" \ + ".option arch,+zba\n\t" \ + ".option norvc\n\t" \ + "slli %[__tmp],%[__tmp],32\n\t" \ + "add.uw %[__ret],%[__ret],%[__tmp]\n\t" \ + "nop\n\t" \ + "nop\n\t" \ + ".option pop\n\t" \ + +#define RISCV_RUNTIME_CONST_64_ZBKB \ + ".option push\n\t" \ + ".option arch,+zbkb\n\t" \ + ".option norvc\n\t" \ + "pack %[__ret],%[__ret],%[__tmp]\n\t" \ + "nop\n\t" \ + "nop\n\t" \ + "nop\n\t" \ + ".option pop\n\t" \ + +#define RISCV_RUNTIME_CONST_64_POSTAMBLE(sym) \ + ".option pop\n\t" \ + ".pushsection runtime_ptr_" #sym ",\"a\"\n\t" \ + ".long 1b - .\n\t" \ + ".popsection" \ + +#if defined(CONFIG_RISCV_ISA_ZBA) && defined(CONFIG_TOOLCHAIN_HAS_ZBA) \ + && defined(CONFIG_RISCV_ISA_ZBKB) +#define runtime_const_ptr(sym) \ +({ \ + typeof(sym) __ret, __tmp; \ + asm_inline(RISCV_RUNTIME_CONST_64_PREAMBLE \ + ALTERNATIVE_2( \ + RISCV_RUNTIME_CONST_64_BASE, \ + RISCV_RUNTIME_CONST_64_ZBA, \ + 0, RISCV_ISA_EXT_ZBA, 1, \ + RISCV_RUNTIME_CONST_64_ZBKB, \ + 0, RISCV_ISA_EXT_ZBKB, 1 \ + ) \ + RISCV_RUNTIME_CONST_64_POSTAMBLE(sym) \ + : [__ret] "=r" (__ret), [__tmp] "=r" (__tmp)); \ + __ret; \ +}) +#elif defined(CONFIG_RISCV_ISA_ZBA) && defined(CONFIG_TOOLCHAIN_HAS_ZBA) +#define runtime_const_ptr(sym) \ +({ \ + typeof(sym) __ret, __tmp; \ + asm_inline(RISCV_RUNTIME_CONST_64_PREAMBLE \ + ALTERNATIVE( \ + RISCV_RUNTIME_CONST_64_BASE, \ + RISCV_RUNTIME_CONST_64_ZBA, \ + 0, RISCV_ISA_EXT_ZBA, 1 \ + ) \ + RISCV_RUNTIME_CONST_64_POSTAMBLE(sym) \ + : [__ret] "=r" (__ret), [__tmp] "=r" (__tmp)); \ + __ret; \ +}) +#elif defined(CONFIG_RISCV_ISA_ZBKB) +#define runtime_const_ptr(sym) \ +({ \ + typeof(sym) __ret, __tmp; \ + asm_inline(RISCV_RUNTIME_CONST_64_PREAMBLE \ + ALTERNATIVE( \ + RISCV_RUNTIME_CONST_64_BASE, \ + RISCV_RUNTIME_CONST_64_ZBKB, \ + 0, RISCV_ISA_EXT_ZBKB, 1 \ + ) \ + RISCV_RUNTIME_CONST_64_POSTAMBLE(sym) \ + : [__ret] "=r" (__ret), [__tmp] "=r" (__tmp)); \ + __ret; \ +}) +#else +#define runtime_const_ptr(sym) \ +({ \ + typeof(sym) __ret, __tmp; \ + asm_inline(RISCV_RUNTIME_CONST_64_PREAMBLE \ + RISCV_RUNTIME_CONST_64_BASE \ + RISCV_RUNTIME_CONST_64_POSTAMBLE(sym) \ + : [__ret] "=r" (__ret), [__tmp] "=r" (__tmp)); \ + __ret; \ +}) +#endif +#endif + +#define runtime_const_shift_right_32(val, sym) \ +({ \ + u32 __ret; \ + asm_inline(".option push\n\t" \ + ".option norvc\n\t" \ + "1:\t" \ + SRLI " %[__ret],%[__val],12\n\t" \ + ".option pop\n\t" \ + ".pushsection runtime_shift_" #sym ",\"a\"\n\t" \ + ".long 1b - .\n\t" \ + ".popsection" \ + : [__ret] "=r" (__ret) \ + : [__val] "r" (val)); \ + __ret; \ +}) + +#define runtime_const_init(type, sym) do { \ + extern s32 __start_runtime_##type##_##sym[]; \ + extern s32 __stop_runtime_##type##_##sym[]; \ + \ + runtime_const_fixup(__runtime_fixup_##type, \ + (unsigned long)(sym), \ + __start_runtime_##type##_##sym, \ + __stop_runtime_##type##_##sym); \ +} while (0) + +static inline void __runtime_fixup_caches(void *where, unsigned int insns) +{ + /* On riscv there are currently only cache-wide flushes so va is ignored. */ + __always_unused uintptr_t va = (uintptr_t)where; + + flush_icache_range(va, va + 4 * insns); +} + +/* + * The 32-bit immediate is stored in a lui+addi pairing. + * lui holds the upper 20 bits of the immediate in the first 20 bits of the instruction. + * addi holds the lower 12 bits of the immediate in the first 12 bits of the instruction. + */ +static inline void __runtime_fixup_32(__le16 *lui_parcel, __le16 *addi_parcel, unsigned int val) +{ + unsigned int lower_immediate, upper_immediate; + u32 lui_insn, addi_insn, addi_insn_mask; + __le32 lui_res, addi_res; + + /* Mask out upper 12 bit of addi */ + addi_insn_mask = 0x000fffff; + + lui_insn = (u32)le16_to_cpu(lui_parcel[0]) | (u32)le16_to_cpu(lui_parcel[1]) << 16; + addi_insn = (u32)le16_to_cpu(addi_parcel[0]) | (u32)le16_to_cpu(addi_parcel[1]) << 16; + + lower_immediate = sign_extend32(val, 11); + upper_immediate = (val - lower_immediate); + + if (upper_immediate & 0xfffff000) { + /* replace upper 20 bits of lui with upper immediate */ + lui_insn &= 0x00000fff; + lui_insn |= upper_immediate & 0xfffff000; + } else { + /* replace lui with nop if immediate is small enough to fit in addi */ + lui_insn = RISCV_INSN_NOP4; + /* + * lui is being skipped, so do a load instead of an add. A load + * is performed by adding with the x0 register. Setting rs to + * zero with the following mask will accomplish this goal. + */ + addi_insn_mask &= 0x07fff; + } + + if (lower_immediate & 0x00000fff) { + /* replace upper 12 bits of addi with lower 12 bits of val */ + addi_insn &= addi_insn_mask; + addi_insn |= (lower_immediate & 0x00000fff) << 20; + } else { + /* replace addi with nop if lower_immediate is empty */ + addi_insn = RISCV_INSN_NOP4; + } + + addi_res = cpu_to_le32(addi_insn); + lui_res = cpu_to_le32(lui_insn); + mutex_lock(&text_mutex); + patch_insn_write(addi_parcel, &addi_res, sizeof(addi_res)); + patch_insn_write(lui_parcel, &lui_res, sizeof(lui_res)); + mutex_unlock(&text_mutex); +} + +static inline void __runtime_fixup_ptr(void *where, unsigned long val) +{ +#ifdef CONFIG_32BIT + __runtime_fixup_32(where, where + 4, val); + __runtime_fixup_caches(where, 2); +#else + __runtime_fixup_32(where, where + 8, val); + __runtime_fixup_32(where + 4, where + 12, val >> 32); + __runtime_fixup_caches(where, 4); +#endif +} + +/* + * Replace the least significant 5 bits of the srli/srliw immediate that is + * located at bits 20-24 + */ +static inline void __runtime_fixup_shift(void *where, unsigned long val) +{ + __le16 *parcel = where; + __le32 res; + u32 insn; + + insn = (u32)le16_to_cpu(parcel[0]) | (u32)le16_to_cpu(parcel[1]) << 16; + + insn &= 0xfe0fffff; + insn |= (val & 0b11111) << 20; + + res = cpu_to_le32(insn); + mutex_lock(&text_mutex); + patch_text_nosync(where, &res, sizeof(insn)); + mutex_unlock(&text_mutex); +} + +static inline void runtime_const_fixup(void (*fn)(void *, unsigned long), + unsigned long val, s32 *start, s32 *end) +{ + while (start < end) { + fn(*start + (void *)start, val); + start++; + } +} + +#endif /* _ASM_RISCV_RUNTIME_CONST_H */ diff --git a/arch/riscv/include/asm/suspend.h b/arch/riscv/include/asm/suspend.h index 4ffb022b097f..dc5782b5fbad 100644 --- a/arch/riscv/include/asm/suspend.h +++ b/arch/riscv/include/asm/suspend.h @@ -18,6 +18,10 @@ struct suspend_context { unsigned long ie; #ifdef CONFIG_MMU unsigned long satp; + unsigned long stimecmp; +#if __riscv_xlen < 64 + unsigned long stimecmph; +#endif #endif }; diff --git a/arch/riscv/include/asm/switch_to.h b/arch/riscv/include/asm/switch_to.h index 94e33216b2d9..0e71eb82f920 100644 --- a/arch/riscv/include/asm/switch_to.h +++ b/arch/riscv/include/asm/switch_to.h @@ -117,7 +117,7 @@ do { \ __set_prev_cpu(__prev->thread); \ if (has_fpu()) \ __switch_to_fpu(__prev, __next); \ - if (has_vector()) \ + if (has_vector() || has_xtheadvector()) \ __switch_to_vector(__prev, __next); \ if (switch_to_should_flush_icache(__next)) \ local_flush_icache_all(); \ diff --git a/arch/riscv/include/asm/syscall.h b/arch/riscv/include/asm/syscall.h index 121fff429dce..34313387f977 100644 --- a/arch/riscv/include/asm/syscall.h +++ b/arch/riscv/include/asm/syscall.h @@ -30,6 +30,13 @@ static inline int syscall_get_nr(struct task_struct *task, return regs->a7; } +static inline void syscall_set_nr(struct task_struct *task, + struct pt_regs *regs, + int nr) +{ + regs->a7 = nr; +} + static inline void syscall_rollback(struct task_struct *task, struct pt_regs *regs) { @@ -62,8 +69,23 @@ static inline void syscall_get_arguments(struct task_struct *task, unsigned long *args) { args[0] = regs->orig_a0; - args++; - memcpy(args, ®s->a1, 5 * sizeof(args[0])); + args[1] = regs->a1; + args[2] = regs->a2; + args[3] = regs->a3; + args[4] = regs->a4; + args[5] = regs->a5; +} + +static inline void syscall_set_arguments(struct task_struct *task, + struct pt_regs *regs, + const unsigned long *args) +{ + regs->orig_a0 = args[0]; + regs->a1 = args[1]; + regs->a2 = args[2]; + regs->a3 = args[3]; + regs->a4 = args[4]; + regs->a5 = args[5]; } static inline int syscall_get_arch(struct task_struct *task) diff --git a/arch/riscv/include/asm/tlb.h b/arch/riscv/include/asm/tlb.h index 1f6c38420d8e..50b63b5c15bd 100644 --- a/arch/riscv/include/asm/tlb.h +++ b/arch/riscv/include/asm/tlb.h @@ -10,24 +10,6 @@ struct mmu_gather; static void tlb_flush(struct mmu_gather *tlb); -#ifdef CONFIG_MMU -#include <linux/swap.h> - -/* - * While riscv platforms with riscv_ipi_for_rfence as true require an IPI to - * perform TLB shootdown, some platforms with riscv_ipi_for_rfence as false use - * SBI to perform TLB shootdown. To keep software pagetable walkers safe in this - * case we switch to RCU based table free (MMU_GATHER_RCU_TABLE_FREE). See the - * comment below 'ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE' in include/asm-generic/tlb.h - * for more details. - */ -static inline void __tlb_remove_table(void *table) -{ - free_page_and_swap_cache(table); -} - -#endif /* CONFIG_MMU */ - #define tlb_flush tlb_flush #include <asm-generic/tlb.h> diff --git a/arch/riscv/include/asm/tlbflush.h b/arch/riscv/include/asm/tlbflush.h index 72e559934952..ce0dd0fed764 100644 --- a/arch/riscv/include/asm/tlbflush.h +++ b/arch/riscv/include/asm/tlbflush.h @@ -60,8 +60,7 @@ void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start, bool arch_tlbbatch_should_defer(struct mm_struct *mm); void arch_tlbbatch_add_pending(struct arch_tlbflush_unmap_batch *batch, - struct mm_struct *mm, - unsigned long uaddr); + struct mm_struct *mm, unsigned long start, unsigned long end); void arch_flush_tlb_batched_pending(struct mm_struct *mm); void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch); diff --git a/arch/riscv/include/asm/vdso.h b/arch/riscv/include/asm/vdso.h index f891478829a5..c130d8100232 100644 --- a/arch/riscv/include/asm/vdso.h +++ b/arch/riscv/include/asm/vdso.h @@ -14,7 +14,7 @@ */ #ifdef CONFIG_MMU -#define __VVAR_PAGES 2 +#define __VDSO_PAGES 4 #ifndef __ASSEMBLY__ #include <generated/vdso-offsets.h> diff --git a/arch/riscv/include/asm/vdso/time_data.h b/arch/riscv/include/asm/vdso/arch_data.h index dfa65228999b..da57a3786f7a 100644 --- a/arch/riscv/include/asm/vdso/time_data.h +++ b/arch/riscv/include/asm/vdso/arch_data.h @@ -1,12 +1,12 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __RISCV_ASM_VDSO_TIME_DATA_H -#define __RISCV_ASM_VDSO_TIME_DATA_H +#ifndef __RISCV_ASM_VDSO_ARCH_DATA_H +#define __RISCV_ASM_VDSO_ARCH_DATA_H #include <linux/types.h> #include <vdso/datapage.h> #include <asm/hwprobe.h> -struct arch_vdso_time_data { +struct vdso_arch_data { /* Stash static answers to the hwprobe queries when all CPUs are selected. */ __u64 all_cpu_hwprobe_values[RISCV_HWPROBE_MAX_KEY + 1]; @@ -14,4 +14,4 @@ struct arch_vdso_time_data { __u8 homogeneous_cpus; }; -#endif /* __RISCV_ASM_VDSO_TIME_DATA_H */ +#endif /* __RISCV_ASM_VDSO_ARCH_DATA_H */ diff --git a/arch/riscv/include/asm/vdso/gettimeofday.h b/arch/riscv/include/asm/vdso/gettimeofday.h index ba3283cf7acc..29164f84f93c 100644 --- a/arch/riscv/include/asm/vdso/gettimeofday.h +++ b/arch/riscv/include/asm/vdso/gettimeofday.h @@ -69,7 +69,7 @@ int clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts) #endif /* CONFIG_GENERIC_TIME_VSYSCALL */ static __always_inline u64 __arch_get_hw_counter(s32 clock_mode, - const struct vdso_data *vd) + const struct vdso_time_data *vd) { /* * The purpose of csr_read(CSR_TIME) is to trap the system into @@ -79,18 +79,6 @@ static __always_inline u64 __arch_get_hw_counter(s32 clock_mode, return csr_read(CSR_TIME); } -static __always_inline const struct vdso_data *__arch_get_vdso_data(void) -{ - return _vdso_data; -} - -#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 /* __ASM_VDSO_GETTIMEOFDAY_H */ diff --git a/arch/riscv/include/asm/vdso/vsyscall.h b/arch/riscv/include/asm/vdso/vsyscall.h index e8a9c4b53c0c..1140b54b4bc8 100644 --- a/arch/riscv/include/asm/vdso/vsyscall.h +++ b/arch/riscv/include/asm/vdso/vsyscall.h @@ -6,15 +6,6 @@ #include <vdso/datapage.h> -extern struct vdso_data *vdso_data; - -static __always_inline struct vdso_data *__riscv_get_k_vdso_data(void) -{ - return vdso_data; -} - -#define __arch_get_k_vdso_data __riscv_get_k_vdso_data - /* The asm-generic header needs to be included after the definitions above */ #include <asm-generic/vdso/vsyscall.h> diff --git a/arch/riscv/include/asm/vector.h b/arch/riscv/include/asm/vector.h index c7c023afbacd..e8a83f55be2b 100644 --- a/arch/riscv/include/asm/vector.h +++ b/arch/riscv/include/asm/vector.h @@ -18,6 +18,27 @@ #include <asm/cpufeature.h> #include <asm/csr.h> #include <asm/asm.h> +#include <asm/vendorid_list.h> +#include <asm/vendor_extensions.h> +#include <asm/vendor_extensions/thead.h> + +#define __riscv_v_vstate_or(_val, TYPE) ({ \ + typeof(_val) _res = _val; \ + if (has_xtheadvector()) \ + _res = (_res & ~SR_VS_THEAD) | SR_VS_##TYPE##_THEAD; \ + else \ + _res = (_res & ~SR_VS) | SR_VS_##TYPE; \ + _res; \ +}) + +#define __riscv_v_vstate_check(_val, TYPE) ({ \ + bool _res; \ + if (has_xtheadvector()) \ + _res = ((_val) & SR_VS_THEAD) == SR_VS_##TYPE##_THEAD; \ + else \ + _res = ((_val) & SR_VS) == SR_VS_##TYPE; \ + _res; \ +}) extern unsigned long riscv_v_vsize; int riscv_v_setup_vsize(void); @@ -41,39 +62,62 @@ static __always_inline bool has_vector(void) return riscv_has_extension_unlikely(RISCV_ISA_EXT_ZVE32X); } +static __always_inline bool has_xtheadvector_no_alternatives(void) +{ + if (IS_ENABLED(CONFIG_RISCV_ISA_XTHEADVECTOR)) + return riscv_isa_vendor_extension_available(THEAD_VENDOR_ID, XTHEADVECTOR); + else + return false; +} + +static __always_inline bool has_xtheadvector(void) +{ + if (IS_ENABLED(CONFIG_RISCV_ISA_XTHEADVECTOR)) + return riscv_has_vendor_extension_unlikely(THEAD_VENDOR_ID, + RISCV_ISA_VENDOR_EXT_XTHEADVECTOR); + else + return false; +} + static inline void __riscv_v_vstate_clean(struct pt_regs *regs) { - regs->status = (regs->status & ~SR_VS) | SR_VS_CLEAN; + regs->status = __riscv_v_vstate_or(regs->status, CLEAN); } static inline void __riscv_v_vstate_dirty(struct pt_regs *regs) { - regs->status = (regs->status & ~SR_VS) | SR_VS_DIRTY; + regs->status = __riscv_v_vstate_or(regs->status, DIRTY); } static inline void riscv_v_vstate_off(struct pt_regs *regs) { - regs->status = (regs->status & ~SR_VS) | SR_VS_OFF; + regs->status = __riscv_v_vstate_or(regs->status, OFF); } static inline void riscv_v_vstate_on(struct pt_regs *regs) { - regs->status = (regs->status & ~SR_VS) | SR_VS_INITIAL; + regs->status = __riscv_v_vstate_or(regs->status, INITIAL); } static inline bool riscv_v_vstate_query(struct pt_regs *regs) { - return (regs->status & SR_VS) != 0; + return !__riscv_v_vstate_check(regs->status, OFF); } static __always_inline void riscv_v_enable(void) { - csr_set(CSR_SSTATUS, SR_VS); + if (has_xtheadvector()) + csr_set(CSR_SSTATUS, SR_VS_THEAD); + else + csr_set(CSR_SSTATUS, SR_VS); } static __always_inline void riscv_v_disable(void) { - csr_clear(CSR_SSTATUS, SR_VS); + if (has_xtheadvector()) + csr_clear(CSR_SSTATUS, SR_VS_THEAD); + else + csr_clear(CSR_SSTATUS, SR_VS); } static __always_inline void __vstate_csr_save(struct __riscv_v_ext_state *dest) @@ -82,10 +126,36 @@ static __always_inline void __vstate_csr_save(struct __riscv_v_ext_state *dest) "csrr %0, " __stringify(CSR_VSTART) "\n\t" "csrr %1, " __stringify(CSR_VTYPE) "\n\t" "csrr %2, " __stringify(CSR_VL) "\n\t" - "csrr %3, " __stringify(CSR_VCSR) "\n\t" - "csrr %4, " __stringify(CSR_VLENB) "\n\t" : "=r" (dest->vstart), "=r" (dest->vtype), "=r" (dest->vl), - "=r" (dest->vcsr), "=r" (dest->vlenb) : :); + "=r" (dest->vcsr) : :); + + if (has_xtheadvector()) { + unsigned long status; + + /* + * CSR_VCSR is defined as + * [2:1] - vxrm[1:0] + * [0] - vxsat + * The earlier vector spec implemented by T-Head uses separate + * registers for the same bit-elements, so just combine those + * into the existing output field. + * + * Additionally T-Head cores need FS to be enabled when accessing + * the VXRM and VXSAT CSRs, otherwise ending in illegal instructions. + * Though the cores do not implement the VXRM and VXSAT fields in the + * FCSR CSR that vector-0.7.1 specifies. + */ + status = csr_read_set(CSR_STATUS, SR_FS_DIRTY); + dest->vcsr = csr_read(CSR_VXSAT) | csr_read(CSR_VXRM) << CSR_VXRM_SHIFT; + + dest->vlenb = riscv_v_vsize / 32; + + if ((status & SR_FS) != SR_FS_DIRTY) + csr_write(CSR_STATUS, status); + } else { + dest->vcsr = csr_read(CSR_VCSR); + dest->vlenb = csr_read(CSR_VLENB); + } } static __always_inline void __vstate_csr_restore(struct __riscv_v_ext_state *src) @@ -96,9 +166,25 @@ static __always_inline void __vstate_csr_restore(struct __riscv_v_ext_state *src "vsetvl x0, %2, %1\n\t" ".option pop\n\t" "csrw " __stringify(CSR_VSTART) ", %0\n\t" - "csrw " __stringify(CSR_VCSR) ", %3\n\t" - : : "r" (src->vstart), "r" (src->vtype), "r" (src->vl), - "r" (src->vcsr) :); + : : "r" (src->vstart), "r" (src->vtype), "r" (src->vl)); + + if (has_xtheadvector()) { + unsigned long status = csr_read(CSR_SSTATUS); + + /* + * Similar to __vstate_csr_save above, restore values for the + * separate VXRM and VXSAT CSRs from the vcsr variable. + */ + status = csr_read_set(CSR_STATUS, SR_FS_DIRTY); + + csr_write(CSR_VXRM, (src->vcsr >> CSR_VXRM_SHIFT) & CSR_VXRM_MASK); + csr_write(CSR_VXSAT, src->vcsr & CSR_VXSAT_MASK); + + if ((status & SR_FS) != SR_FS_DIRTY) + csr_write(CSR_STATUS, status); + } else { + csr_write(CSR_VCSR, src->vcsr); + } } static inline void __riscv_v_vstate_save(struct __riscv_v_ext_state *save_to, @@ -108,19 +194,33 @@ static inline void __riscv_v_vstate_save(struct __riscv_v_ext_state *save_to, riscv_v_enable(); __vstate_csr_save(save_to); - asm volatile ( - ".option push\n\t" - ".option arch, +zve32x\n\t" - "vsetvli %0, x0, e8, m8, ta, ma\n\t" - "vse8.v v0, (%1)\n\t" - "add %1, %1, %0\n\t" - "vse8.v v8, (%1)\n\t" - "add %1, %1, %0\n\t" - "vse8.v v16, (%1)\n\t" - "add %1, %1, %0\n\t" - "vse8.v v24, (%1)\n\t" - ".option pop\n\t" - : "=&r" (vl) : "r" (datap) : "memory"); + if (has_xtheadvector()) { + asm volatile ( + "mv t0, %0\n\t" + THEAD_VSETVLI_T4X0E8M8D1 + THEAD_VSB_V_V0T0 + "add t0, t0, t4\n\t" + THEAD_VSB_V_V0T0 + "add t0, t0, t4\n\t" + THEAD_VSB_V_V0T0 + "add t0, t0, t4\n\t" + THEAD_VSB_V_V0T0 + : : "r" (datap) : "memory", "t0", "t4"); + } else { + asm volatile ( + ".option push\n\t" + ".option arch, +zve32x\n\t" + "vsetvli %0, x0, e8, m8, ta, ma\n\t" + "vse8.v v0, (%1)\n\t" + "add %1, %1, %0\n\t" + "vse8.v v8, (%1)\n\t" + "add %1, %1, %0\n\t" + "vse8.v v16, (%1)\n\t" + "add %1, %1, %0\n\t" + "vse8.v v24, (%1)\n\t" + ".option pop\n\t" + : "=&r" (vl) : "r" (datap) : "memory"); + } riscv_v_disable(); } @@ -130,19 +230,33 @@ static inline void __riscv_v_vstate_restore(struct __riscv_v_ext_state *restore_ unsigned long vl; riscv_v_enable(); - asm volatile ( - ".option push\n\t" - ".option arch, +zve32x\n\t" - "vsetvli %0, x0, e8, m8, ta, ma\n\t" - "vle8.v v0, (%1)\n\t" - "add %1, %1, %0\n\t" - "vle8.v v8, (%1)\n\t" - "add %1, %1, %0\n\t" - "vle8.v v16, (%1)\n\t" - "add %1, %1, %0\n\t" - "vle8.v v24, (%1)\n\t" - ".option pop\n\t" - : "=&r" (vl) : "r" (datap) : "memory"); + if (has_xtheadvector()) { + asm volatile ( + "mv t0, %0\n\t" + THEAD_VSETVLI_T4X0E8M8D1 + THEAD_VLB_V_V0T0 + "add t0, t0, t4\n\t" + THEAD_VLB_V_V0T0 + "add t0, t0, t4\n\t" + THEAD_VLB_V_V0T0 + "add t0, t0, t4\n\t" + THEAD_VLB_V_V0T0 + : : "r" (datap) : "memory", "t0", "t4"); + } else { + asm volatile ( + ".option push\n\t" + ".option arch, +zve32x\n\t" + "vsetvli %0, x0, e8, m8, ta, ma\n\t" + "vle8.v v0, (%1)\n\t" + "add %1, %1, %0\n\t" + "vle8.v v8, (%1)\n\t" + "add %1, %1, %0\n\t" + "vle8.v v16, (%1)\n\t" + "add %1, %1, %0\n\t" + "vle8.v v24, (%1)\n\t" + ".option pop\n\t" + : "=&r" (vl) : "r" (datap) : "memory"); + } __vstate_csr_restore(restore_from); riscv_v_disable(); } @@ -152,33 +266,41 @@ static inline void __riscv_v_vstate_discard(void) unsigned long vl, vtype_inval = 1UL << (BITS_PER_LONG - 1); riscv_v_enable(); + if (has_xtheadvector()) + asm volatile (THEAD_VSETVLI_T4X0E8M8D1 : : : "t4"); + else + asm volatile ( + ".option push\n\t" + ".option arch, +zve32x\n\t" + "vsetvli %0, x0, e8, m8, ta, ma\n\t" + ".option pop\n\t": "=&r" (vl)); + asm volatile ( ".option push\n\t" ".option arch, +zve32x\n\t" - "vsetvli %0, x0, e8, m8, ta, ma\n\t" "vmv.v.i v0, -1\n\t" "vmv.v.i v8, -1\n\t" "vmv.v.i v16, -1\n\t" "vmv.v.i v24, -1\n\t" "vsetvl %0, x0, %1\n\t" ".option pop\n\t" - : "=&r" (vl) : "r" (vtype_inval) : "memory"); + : "=&r" (vl) : "r" (vtype_inval)); + riscv_v_disable(); } static inline void riscv_v_vstate_discard(struct pt_regs *regs) { - if ((regs->status & SR_VS) == SR_VS_OFF) - return; - - __riscv_v_vstate_discard(); - __riscv_v_vstate_dirty(regs); + if (riscv_v_vstate_query(regs)) { + __riscv_v_vstate_discard(); + __riscv_v_vstate_dirty(regs); + } } static inline void riscv_v_vstate_save(struct __riscv_v_ext_state *vstate, struct pt_regs *regs) { - if ((regs->status & SR_VS) == SR_VS_DIRTY) { + if (__riscv_v_vstate_check(regs->status, DIRTY)) { __riscv_v_vstate_save(vstate, vstate->datap); __riscv_v_vstate_clean(regs); } @@ -187,7 +309,7 @@ static inline void riscv_v_vstate_save(struct __riscv_v_ext_state *vstate, static inline void riscv_v_vstate_restore(struct __riscv_v_ext_state *vstate, struct pt_regs *regs) { - if ((regs->status & SR_VS) != SR_VS_OFF) { + if (riscv_v_vstate_query(regs)) { __riscv_v_vstate_restore(vstate, vstate->datap); __riscv_v_vstate_clean(regs); } @@ -196,7 +318,7 @@ static inline void riscv_v_vstate_restore(struct __riscv_v_ext_state *vstate, static inline void riscv_v_vstate_set_restore(struct task_struct *task, struct pt_regs *regs) { - if ((regs->status & SR_VS) != SR_VS_OFF) { + if (riscv_v_vstate_query(regs)) { set_tsk_thread_flag(task, TIF_RISCV_V_DEFER_RESTORE); riscv_v_vstate_on(regs); } @@ -270,6 +392,8 @@ struct pt_regs; static inline int riscv_v_setup_vsize(void) { return -EOPNOTSUPP; } static __always_inline bool has_vector(void) { return false; } static __always_inline bool insn_is_vector(u32 insn_buf) { return false; } +static __always_inline bool has_xtheadvector_no_alternatives(void) { return false; } +static __always_inline bool has_xtheadvector(void) { return false; } static inline bool riscv_v_first_use_handler(struct pt_regs *regs) { return false; } static inline bool riscv_v_vstate_query(struct pt_regs *regs) { return false; } static inline bool riscv_v_vstate_ctrl_user_allowed(void) { return false; } diff --git a/arch/riscv/include/asm/vendor_extensions/thead.h b/arch/riscv/include/asm/vendor_extensions/thead.h new file mode 100644 index 000000000000..e85c75b3b340 --- /dev/null +++ b/arch/riscv/include/asm/vendor_extensions/thead.h @@ -0,0 +1,47 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_RISCV_VENDOR_EXTENSIONS_THEAD_H +#define _ASM_RISCV_VENDOR_EXTENSIONS_THEAD_H + +#include <asm/vendor_extensions.h> + +#include <linux/types.h> + +/* + * Extension keys must be strictly less than RISCV_ISA_VENDOR_EXT_MAX. + */ +#define RISCV_ISA_VENDOR_EXT_XTHEADVECTOR 0 + +extern struct riscv_isa_vendor_ext_data_list riscv_isa_vendor_ext_list_thead; + +#ifdef CONFIG_RISCV_ISA_VENDOR_EXT_THEAD +void disable_xtheadvector(void); +#else +static inline void disable_xtheadvector(void) { } +#endif + +/* Extension specific helpers */ + +/* + * Vector 0.7.1 as used for example on T-Head Xuantie cores, uses an older + * encoding for vsetvli (ta, ma vs. d1), so provide an instruction for + * vsetvli t4, x0, e8, m8, d1 + */ +#define THEAD_VSETVLI_T4X0E8M8D1 ".long 0x00307ed7\n\t" + +/* + * While in theory, the vector-0.7.1 vsb.v and vlb.v result in the same + * encoding as the standard vse8.v and vle8.v, compilers seem to optimize + * the call resulting in a different encoding and then using a value for + * the "mop" field that is not part of vector-0.7.1 + * So encode specific variants for vstate_save and _restore. + */ +#define THEAD_VSB_V_V0T0 ".long 0x02028027\n\t" +#define THEAD_VSB_V_V8T0 ".long 0x02028427\n\t" +#define THEAD_VSB_V_V16T0 ".long 0x02028827\n\t" +#define THEAD_VSB_V_V24T0 ".long 0x02028c27\n\t" +#define THEAD_VLB_V_V0T0 ".long 0x012028007\n\t" +#define THEAD_VLB_V_V8T0 ".long 0x012028407\n\t" +#define THEAD_VLB_V_V16T0 ".long 0x012028807\n\t" +#define THEAD_VLB_V_V24T0 ".long 0x012028c07\n\t" + +#endif diff --git a/arch/riscv/include/asm/vendor_extensions/thead_hwprobe.h b/arch/riscv/include/asm/vendor_extensions/thead_hwprobe.h new file mode 100644 index 000000000000..65a9c5612466 --- /dev/null +++ b/arch/riscv/include/asm/vendor_extensions/thead_hwprobe.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_RISCV_VENDOR_EXTENSIONS_THEAD_HWPROBE_H +#define _ASM_RISCV_VENDOR_EXTENSIONS_THEAD_HWPROBE_H + +#include <linux/cpumask.h> + +#include <uapi/asm/hwprobe.h> + +#ifdef CONFIG_RISCV_ISA_VENDOR_EXT_THEAD +void hwprobe_isa_vendor_ext_thead_0(struct riscv_hwprobe *pair, const struct cpumask *cpus); +#else +static inline void hwprobe_isa_vendor_ext_thead_0(struct riscv_hwprobe *pair, + const struct cpumask *cpus) +{ + pair->value = 0; +} +#endif + +#endif diff --git a/arch/riscv/include/asm/vendor_extensions/vendor_hwprobe.h b/arch/riscv/include/asm/vendor_extensions/vendor_hwprobe.h new file mode 100644 index 000000000000..6b9293e984a9 --- /dev/null +++ b/arch/riscv/include/asm/vendor_extensions/vendor_hwprobe.h @@ -0,0 +1,37 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright 2024 Rivos, Inc + */ + +#ifndef _ASM_RISCV_SYS_HWPROBE_H +#define _ASM_RISCV_SYS_HWPROBE_H + +#include <asm/cpufeature.h> + +#define VENDOR_EXT_KEY(ext) \ + do { \ + if (__riscv_isa_extension_available(isainfo->isa, RISCV_ISA_VENDOR_EXT_##ext)) \ + pair->value |= RISCV_HWPROBE_VENDOR_EXT_##ext; \ + else \ + missing |= RISCV_HWPROBE_VENDOR_EXT_##ext; \ + } while (false) + +/* + * Loop through and record extensions that 1) anyone has, and 2) anyone + * doesn't have. + * + * _extension_checks is an arbitrary C block to set the values of pair->value + * and missing. It should be filled with VENDOR_EXT_KEY expressions. + */ +#define VENDOR_EXTENSION_SUPPORTED(pair, cpus, per_hart_vendor_bitmap, _extension_checks) \ + do { \ + int cpu; \ + u64 missing = 0; \ + for_each_cpu(cpu, (cpus)) { \ + struct riscv_isavendorinfo *isainfo = &(per_hart_vendor_bitmap)[cpu]; \ + _extension_checks \ + } \ + (pair)->value &= ~missing; \ + } while (false) \ + +#endif /* _ASM_RISCV_SYS_HWPROBE_H */ diff --git a/arch/riscv/include/asm/vendorid_list.h b/arch/riscv/include/asm/vendorid_list.h index 2f2bb0c84f9a..a5150cdf34d8 100644 --- a/arch/riscv/include/asm/vendorid_list.h +++ b/arch/riscv/include/asm/vendorid_list.h @@ -6,6 +6,7 @@ #define ASM_VENDOR_LIST_H #define ANDES_VENDOR_ID 0x31e +#define MICROCHIP_VENDOR_ID 0x029 #define SIFIVE_VENDOR_ID 0x489 #define THEAD_VENDOR_ID 0x5b7 |