diff options
Diffstat (limited to 'arch/powerpc/include')
310 files changed, 13796 insertions, 7461 deletions
diff --git a/arch/powerpc/include/asm/8xx_immap.h b/arch/powerpc/include/asm/8xx_immap.h index bdf0563ba423..f9cac46a95cb 100644 --- a/arch/powerpc/include/asm/8xx_immap.h +++ b/arch/powerpc/include/asm/8xx_immap.h @@ -560,5 +560,7 @@ typedef struct immap { cpm8xx_t im_cpm; /* Communication processor */ } immap_t; +extern immap_t __iomem *mpc8xx_immr; + #endif /* __IMMAP_8XX__ */ #endif /* __KERNEL__ */ diff --git a/arch/powerpc/include/asm/Kbuild b/arch/powerpc/include/asm/Kbuild index d0a23d0db863..61a8d5555cd7 100644 --- a/arch/powerpc/include/asm/Kbuild +++ b/arch/powerpc/include/asm/Kbuild @@ -1,14 +1,10 @@ # SPDX-License-Identifier: GPL-2.0 generated-y += syscall_table_32.h generated-y += syscall_table_64.h -generated-y += syscall_table_c32.h generated-y += syscall_table_spu.h -generic-y += div64.h -generic-y += dma-mapping.h -generic-y += export.h -generic-y += irq_regs.h -generic-y += local64.h +generic-y += agp.h +generic-y += kvm_types.h generic-y += mcs_spinlock.h -generic-y += preempt.h +generic-y += qrwlock.h generic-y += vtime.h generic-y += early_ioremap.h diff --git a/arch/powerpc/include/asm/agp.h b/arch/powerpc/include/asm/agp.h deleted file mode 100644 index b29b1186f819..000000000000 --- a/arch/powerpc/include/asm/agp.h +++ /dev/null @@ -1,19 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ASM_POWERPC_AGP_H -#define _ASM_POWERPC_AGP_H -#ifdef __KERNEL__ - -#include <asm/io.h> - -#define map_page_into_agp(page) -#define unmap_page_from_agp(page) -#define flush_agp_cache() mb() - -/* GATT allocation. Returns/accepts GATT kernel virtual address. */ -#define alloc_gatt_pages(order) \ - ((char *)__get_free_pages(GFP_KERNEL, (order))) -#define free_gatt_pages(table, order) \ - free_pages((unsigned long)(table), (order)) - -#endif /* __KERNEL__ */ -#endif /* _ASM_POWERPC_AGP_H */ diff --git a/arch/powerpc/include/asm/archrandom.h b/arch/powerpc/include/asm/archrandom.h index a09595f00cab..51b093f67528 100644 --- a/arch/powerpc/include/asm/archrandom.h +++ b/arch/powerpc/include/asm/archrandom.h @@ -2,57 +2,15 @@ #ifndef _ASM_POWERPC_ARCHRANDOM_H #define _ASM_POWERPC_ARCHRANDOM_H -#ifdef CONFIG_ARCH_RANDOM - -#include <asm/machdep.h> - -static inline int arch_get_random_long(unsigned long *v) -{ - return 0; -} - -static inline int arch_get_random_int(unsigned int *v) +static inline size_t __must_check arch_get_random_longs(unsigned long *v, size_t max_longs) { return 0; } -static inline int arch_get_random_seed_long(unsigned long *v) -{ - if (ppc_md.get_random_seed) - return ppc_md.get_random_seed(v); - - return 0; -} -static inline int arch_get_random_seed_int(unsigned int *v) -{ - unsigned long val; - int rc; - - rc = arch_get_random_seed_long(&val); - if (rc) - *v = val; - - return rc; -} - -static inline int arch_has_random(void) -{ - return 0; -} - -static inline int arch_has_random_seed(void) -{ - return !!ppc_md.get_random_seed; -} -#endif /* CONFIG_ARCH_RANDOM */ +size_t __must_check arch_get_random_seed_longs(unsigned long *v, size_t max_longs); #ifdef CONFIG_PPC_POWERNV -int powernv_hwrng_present(void); -int powernv_get_random_long(unsigned long *v); -int powernv_get_random_real_mode(unsigned long *v); -#else -static inline int powernv_hwrng_present(void) { return 0; } -static inline int powernv_get_random_real_mode(unsigned long *v) { return 0; } +int pnv_get_random_long(unsigned long *v); #endif #endif /* _ASM_POWERPC_ARCHRANDOM_H */ diff --git a/arch/powerpc/include/asm/asm-405.h b/arch/powerpc/include/asm/asm-405.h deleted file mode 100644 index 7270d3ae7c8e..000000000000 --- a/arch/powerpc/include/asm/asm-405.h +++ /dev/null @@ -1,19 +0,0 @@ -#ifndef _ASM_POWERPC_ASM_405_H -#define _ASM_POWERPC_ASM_405_H - -#include <asm/asm-const.h> - -#ifdef __KERNEL__ -#ifdef CONFIG_IBM405_ERR77 -/* Erratum #77 on the 405 means we need a sync or dcbt before every - * stwcx. The old ATOMIC_SYNC_FIX covered some but not all of this. - */ -#define PPC405_ERR77(ra,rb) stringify_in_c(dcbt ra, rb;) -#define PPC405_ERR77_SYNC stringify_in_c(sync;) -#else -#define PPC405_ERR77(ra,rb) -#define PPC405_ERR77_SYNC -#endif -#endif - -#endif /* _ASM_POWERPC_ASM_405_H */ diff --git a/arch/powerpc/include/asm/asm-compat.h b/arch/powerpc/include/asm/asm-compat.h index 19b70c5b5f18..2bc53c646ccd 100644 --- a/arch/powerpc/include/asm/asm-compat.h +++ b/arch/powerpc/include/asm/asm-compat.h @@ -17,10 +17,11 @@ #define PPC_LONG stringify_in_c(.8byte) #define PPC_LONG_ALIGN stringify_in_c(.balign 8) #define PPC_TLNEI stringify_in_c(tdnei) -#define PPC_LLARX(t, a, b, eh) PPC_LDARX(t, a, b, eh) +#define PPC_LLARX stringify_in_c(ldarx) #define PPC_STLCX stringify_in_c(stdcx.) #define PPC_CNTLZL stringify_in_c(cntlzd) #define PPC_MTOCRF(FXM, RS) MTOCRF((FXM), RS) +#define PPC_SRL stringify_in_c(srd) #define PPC_LR_STKOFF 16 #define PPC_MIN_STKFRM 112 @@ -50,10 +51,11 @@ #define PPC_LONG stringify_in_c(.long) #define PPC_LONG_ALIGN stringify_in_c(.balign 4) #define PPC_TLNEI stringify_in_c(twnei) -#define PPC_LLARX(t, a, b, eh) PPC_LWARX(t, a, b, eh) +#define PPC_LLARX stringify_in_c(lwarx) #define PPC_STLCX stringify_in_c(stwcx.) #define PPC_CNTLZL stringify_in_c(cntlzw) #define PPC_MTOCRF stringify_in_c(mtcrf) +#define PPC_SRL stringify_in_c(srw) #define PPC_LR_STKOFF 4 #define PPC_MIN_STKFRM 16 diff --git a/arch/powerpc/include/asm/asm-const.h b/arch/powerpc/include/asm/asm-const.h index 082c1538c562..bfb3c3534877 100644 --- a/arch/powerpc/include/asm/asm-const.h +++ b/arch/powerpc/include/asm/asm-const.h @@ -11,4 +11,5 @@ # define __ASM_CONST(x) x##UL # define ASM_CONST(x) __ASM_CONST(x) #endif + #endif /* _ASM_POWERPC_ASM_CONST_H */ diff --git a/arch/powerpc/include/asm/asm-prototypes.h b/arch/powerpc/include/asm/asm-prototypes.h index 983c0084fb3f..274bce76f5da 100644 --- a/arch/powerpc/include/asm/asm-prototypes.h +++ b/arch/powerpc/include/asm/asm-prototypes.h @@ -2,8 +2,9 @@ #ifndef _ASM_POWERPC_ASM_PROTOTYPES_H #define _ASM_POWERPC_ASM_PROTOTYPES_H /* - * This file is for prototypes of C functions that are only called - * from asm, and any associated variables. + * This file is for C prototypes of asm symbols that are EXPORTed. + * It allows the modversions logic to see their prototype and + * generate proper CRCs for them. * * Copyright 2016, Daniel Axtens, IBM Corporation. */ @@ -19,22 +20,6 @@ #include <uapi/asm/ucontext.h> -/* SMP */ -extern struct task_struct *current_set[NR_CPUS]; -extern struct task_struct *secondary_current; -void start_secondary(void *unused); - -/* kexec */ -struct paca_struct; -struct kimage; -extern struct paca_struct kexec_paca; -void kexec_copy_flush(struct kimage *image); - -/* pseries hcall tracing */ -extern struct static_key hcall_tracepoint_key; -void __trace_hcall_entry(unsigned long opcode, unsigned long *args); -void __trace_hcall_exit(long opcode, long retval, unsigned long *retbuf); - /* Ultravisor */ #if defined(CONFIG_PPC_POWERNV) || defined(CONFIG_PPC_SVM) long ucall_norets(unsigned long opcode, ...); @@ -50,82 +35,8 @@ int64_t __opal_call(int64_t a0, int64_t a1, int64_t a2, int64_t a3, int64_t a4, int64_t a5, int64_t a6, int64_t a7, int64_t opcode, uint64_t msr); -/* VMX copying */ -int enter_vmx_usercopy(void); -int exit_vmx_usercopy(void); -int enter_vmx_ops(void); -void *exit_vmx_ops(void *dest); - -/* Traps */ -long machine_check_early(struct pt_regs *regs); -long hmi_exception_realmode(struct pt_regs *regs); -void SMIException(struct pt_regs *regs); -void handle_hmi_exception(struct pt_regs *regs); -void instruction_breakpoint_exception(struct pt_regs *regs); -void RunModeException(struct pt_regs *regs); -void single_step_exception(struct pt_regs *regs); -void program_check_exception(struct pt_regs *regs); -void alignment_exception(struct pt_regs *regs); -void StackOverflow(struct pt_regs *regs); -void kernel_fp_unavailable_exception(struct pt_regs *regs); -void altivec_unavailable_exception(struct pt_regs *regs); -void vsx_unavailable_exception(struct pt_regs *regs); -void fp_unavailable_tm(struct pt_regs *regs); -void altivec_unavailable_tm(struct pt_regs *regs); -void vsx_unavailable_tm(struct pt_regs *regs); -void facility_unavailable_exception(struct pt_regs *regs); -void TAUException(struct pt_regs *regs); -void altivec_assist_exception(struct pt_regs *regs); -void unrecoverable_exception(struct pt_regs *regs); -void kernel_bad_stack(struct pt_regs *regs); -void system_reset_exception(struct pt_regs *regs); -void machine_check_exception(struct pt_regs *regs); -void emulation_assist_interrupt(struct pt_regs *regs); -long do_slb_fault(struct pt_regs *regs, unsigned long ea); -void do_bad_slb_fault(struct pt_regs *regs, unsigned long ea, long err); - -/* signals, syscalls and interrupts */ -long sys_swapcontext(struct ucontext __user *old_ctx, - struct ucontext __user *new_ctx, - long ctx_size); -#ifdef CONFIG_PPC32 -long sys_debug_setcontext(struct ucontext __user *ctx, - int ndbg, struct sig_dbg_op __user *dbg); -int -ppc_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, - struct __kernel_old_timeval __user *tvp); -unsigned long __init early_init(unsigned long dt_ptr); -void __init machine_init(u64 dt_ptr); -#endif - -long ppc_fadvise64_64(int fd, int advice, u32 offset_high, u32 offset_low, - u32 len_high, u32 len_low); -long sys_switch_endian(void); -notrace unsigned int __check_irq_replay(void); -void notrace restore_interrupts(void); - -/* ptrace */ -long do_syscall_trace_enter(struct pt_regs *regs); -void do_syscall_trace_leave(struct pt_regs *regs); - -/* process */ -void restore_math(struct pt_regs *regs); -void restore_tm_state(struct pt_regs *regs); - -/* prom_init (OpenFirmware) */ -unsigned long __init prom_init(unsigned long r3, unsigned long r4, - unsigned long pp, - unsigned long r6, unsigned long r7, - unsigned long kbase); - -/* setup */ -void __init early_setup(unsigned long dt_ptr); -void early_setup_secondary(void); - -/* time */ -void accumulate_stolen_time(void); - /* misc runtime */ +void enable_machine_check(void); extern u64 __bswapdi2(u64); extern s64 __lshrdi3(s64, int); extern s64 __ashldi3(s64, int); @@ -135,11 +46,6 @@ extern int __ucmpdi2(u64, u64); /* tracing */ void _mcount(void); -unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip, - unsigned long sp); - -void pnv_power9_force_smt4_catch(void); -void pnv_power9_force_smt4_release(void); /* Transaction memory related */ void tm_enable(void); @@ -150,16 +56,6 @@ struct kvm_vcpu; void _kvmppc_restore_tm_pr(struct kvm_vcpu *vcpu, u64 guest_msr); void _kvmppc_save_tm_pr(struct kvm_vcpu *vcpu, u64 guest_msr); -/* Patch sites */ -extern s32 patch__call_flush_count_cache; -extern s32 patch__flush_count_cache_return; -extern s32 patch__flush_link_stack_return; -extern s32 patch__call_kvm_flush_link_stack; -extern s32 patch__memset_nocache, patch__memcpy_nocache; - -extern long flush_count_cache; -extern long kvm_flush_link_stack; - #ifdef CONFIG_PPC_TRANSACTIONAL_MEM void kvmppc_save_tm_hv(struct kvm_vcpu *vcpu, u64 msr, bool preserve_nv); void kvmppc_restore_tm_hv(struct kvm_vcpu *vcpu, u64 msr, bool preserve_nv); @@ -170,12 +66,7 @@ static inline void kvmppc_restore_tm_hv(struct kvm_vcpu *vcpu, u64 msr, bool preserve_nv) { } #endif /* CONFIG_PPC_TRANSACTIONAL_MEM */ -void kvmhv_save_host_pmu(void); -void kvmhv_load_host_pmu(void); -void kvmhv_save_guest_pmu(struct kvm_vcpu *vcpu, bool pmu_in_use); -void kvmhv_load_guest_pmu(struct kvm_vcpu *vcpu); - -int __kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu); +void kvmppc_p9_enter_guest(struct kvm_vcpu *vcpu); long kvmppc_h_set_dabr(struct kvm_vcpu *vcpu, unsigned long dabr); long kvmppc_h_set_xdabr(struct kvm_vcpu *vcpu, unsigned long dabr, diff --git a/arch/powerpc/include/asm/asm.h b/arch/powerpc/include/asm/asm.h new file mode 100644 index 000000000000..86f46b604e9a --- /dev/null +++ b/arch/powerpc/include/asm/asm.h @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_POWERPC_ASM_H +#define _ASM_POWERPC_ASM_H + +#define _ASM_PTR " .long " + +#endif /* _ASM_POWERPC_ASM_H */ diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h index 31c231ea56b7..5bf6a4d49268 100644 --- a/arch/powerpc/include/asm/atomic.h +++ b/arch/powerpc/include/asm/atomic.h @@ -10,9 +10,7 @@ #include <linux/types.h> #include <asm/cmpxchg.h> #include <asm/barrier.h> -#include <asm/asm-405.h> - -#define ATOMIC_INIT(i) { (i) } +#include <asm/asm-const.h> /* * Since *_return_relaxed and {cmp}xchg_relaxed are implemented with @@ -25,182 +23,109 @@ #define __atomic_release_fence() \ __asm__ __volatile__(PPC_RELEASE_BARRIER "" : : : "memory") -static __inline__ int atomic_read(const atomic_t *v) +static __inline__ int arch_atomic_read(const atomic_t *v) { int t; - __asm__ __volatile__("lwz%U1%X1 %0,%1" : "=r"(t) : "m"(v->counter)); + /* -mprefixed can generate offsets beyond range, fall back hack */ + if (IS_ENABLED(CONFIG_PPC_KERNEL_PREFIXED)) + __asm__ __volatile__("lwz %0,0(%1)" : "=r"(t) : "b"(&v->counter)); + else + __asm__ __volatile__("lwz%U1%X1 %0,%1" : "=r"(t) : "m<>"(v->counter)); return t; } -static __inline__ void atomic_set(atomic_t *v, int i) +static __inline__ void arch_atomic_set(atomic_t *v, int i) { - __asm__ __volatile__("stw%U0%X0 %1,%0" : "=m"(v->counter) : "r"(i)); + /* -mprefixed can generate offsets beyond range, fall back hack */ + if (IS_ENABLED(CONFIG_PPC_KERNEL_PREFIXED)) + __asm__ __volatile__("stw %1,0(%2)" : "=m"(v->counter) : "r"(i), "b"(&v->counter)); + else + __asm__ __volatile__("stw%U0%X0 %1,%0" : "=m<>"(v->counter) : "r"(i)); } -#define ATOMIC_OP(op, asm_op) \ -static __inline__ void atomic_##op(int a, atomic_t *v) \ +#define ATOMIC_OP(op, asm_op, suffix, sign, ...) \ +static __inline__ void arch_atomic_##op(int a, atomic_t *v) \ { \ int t; \ \ __asm__ __volatile__( \ "1: lwarx %0,0,%3 # atomic_" #op "\n" \ - #asm_op " %0,%2,%0\n" \ - PPC405_ERR77(0,%3) \ + #asm_op "%I2" suffix " %0,%0,%2\n" \ " stwcx. %0,0,%3 \n" \ " bne- 1b\n" \ : "=&r" (t), "+m" (v->counter) \ - : "r" (a), "r" (&v->counter) \ - : "cc"); \ + : "r"#sign (a), "r" (&v->counter) \ + : "cc", ##__VA_ARGS__); \ } \ -#define ATOMIC_OP_RETURN_RELAXED(op, asm_op) \ -static inline int atomic_##op##_return_relaxed(int a, atomic_t *v) \ +#define ATOMIC_OP_RETURN_RELAXED(op, asm_op, suffix, sign, ...) \ +static inline int arch_atomic_##op##_return_relaxed(int a, atomic_t *v) \ { \ int t; \ \ __asm__ __volatile__( \ "1: lwarx %0,0,%3 # atomic_" #op "_return_relaxed\n" \ - #asm_op " %0,%2,%0\n" \ - PPC405_ERR77(0, %3) \ + #asm_op "%I2" suffix " %0,%0,%2\n" \ " stwcx. %0,0,%3\n" \ " bne- 1b\n" \ : "=&r" (t), "+m" (v->counter) \ - : "r" (a), "r" (&v->counter) \ - : "cc"); \ + : "r"#sign (a), "r" (&v->counter) \ + : "cc", ##__VA_ARGS__); \ \ return t; \ } -#define ATOMIC_FETCH_OP_RELAXED(op, asm_op) \ -static inline int atomic_fetch_##op##_relaxed(int a, atomic_t *v) \ +#define ATOMIC_FETCH_OP_RELAXED(op, asm_op, suffix, sign, ...) \ +static inline int arch_atomic_fetch_##op##_relaxed(int a, atomic_t *v) \ { \ int res, t; \ \ __asm__ __volatile__( \ "1: lwarx %0,0,%4 # atomic_fetch_" #op "_relaxed\n" \ - #asm_op " %1,%3,%0\n" \ - PPC405_ERR77(0, %4) \ + #asm_op "%I3" suffix " %1,%0,%3\n" \ " stwcx. %1,0,%4\n" \ " bne- 1b\n" \ : "=&r" (res), "=&r" (t), "+m" (v->counter) \ - : "r" (a), "r" (&v->counter) \ - : "cc"); \ + : "r"#sign (a), "r" (&v->counter) \ + : "cc", ##__VA_ARGS__); \ \ return res; \ } -#define ATOMIC_OPS(op, asm_op) \ - ATOMIC_OP(op, asm_op) \ - ATOMIC_OP_RETURN_RELAXED(op, asm_op) \ - ATOMIC_FETCH_OP_RELAXED(op, asm_op) +#define ATOMIC_OPS(op, asm_op, suffix, sign, ...) \ + ATOMIC_OP(op, asm_op, suffix, sign, ##__VA_ARGS__) \ + ATOMIC_OP_RETURN_RELAXED(op, asm_op, suffix, sign, ##__VA_ARGS__)\ + ATOMIC_FETCH_OP_RELAXED(op, asm_op, suffix, sign, ##__VA_ARGS__) -ATOMIC_OPS(add, add) -ATOMIC_OPS(sub, subf) +ATOMIC_OPS(add, add, "c", I, "xer") +ATOMIC_OPS(sub, sub, "c", I, "xer") -#define atomic_add_return_relaxed atomic_add_return_relaxed -#define atomic_sub_return_relaxed atomic_sub_return_relaxed +#define arch_atomic_add_return_relaxed arch_atomic_add_return_relaxed +#define arch_atomic_sub_return_relaxed arch_atomic_sub_return_relaxed -#define atomic_fetch_add_relaxed atomic_fetch_add_relaxed -#define atomic_fetch_sub_relaxed atomic_fetch_sub_relaxed +#define arch_atomic_fetch_add_relaxed arch_atomic_fetch_add_relaxed +#define arch_atomic_fetch_sub_relaxed arch_atomic_fetch_sub_relaxed #undef ATOMIC_OPS -#define ATOMIC_OPS(op, asm_op) \ - ATOMIC_OP(op, asm_op) \ - ATOMIC_FETCH_OP_RELAXED(op, asm_op) +#define ATOMIC_OPS(op, asm_op, suffix, sign) \ + ATOMIC_OP(op, asm_op, suffix, sign) \ + ATOMIC_FETCH_OP_RELAXED(op, asm_op, suffix, sign) -ATOMIC_OPS(and, and) -ATOMIC_OPS(or, or) -ATOMIC_OPS(xor, xor) +ATOMIC_OPS(and, and, ".", K) +ATOMIC_OPS(or, or, "", K) +ATOMIC_OPS(xor, xor, "", K) -#define atomic_fetch_and_relaxed atomic_fetch_and_relaxed -#define atomic_fetch_or_relaxed atomic_fetch_or_relaxed -#define atomic_fetch_xor_relaxed atomic_fetch_xor_relaxed +#define arch_atomic_fetch_and_relaxed arch_atomic_fetch_and_relaxed +#define arch_atomic_fetch_or_relaxed arch_atomic_fetch_or_relaxed +#define arch_atomic_fetch_xor_relaxed arch_atomic_fetch_xor_relaxed #undef ATOMIC_OPS #undef ATOMIC_FETCH_OP_RELAXED #undef ATOMIC_OP_RETURN_RELAXED #undef ATOMIC_OP -static __inline__ void atomic_inc(atomic_t *v) -{ - int t; - - __asm__ __volatile__( -"1: lwarx %0,0,%2 # atomic_inc\n\ - addic %0,%0,1\n" - PPC405_ERR77(0,%2) -" stwcx. %0,0,%2 \n\ - bne- 1b" - : "=&r" (t), "+m" (v->counter) - : "r" (&v->counter) - : "cc", "xer"); -} -#define atomic_inc atomic_inc - -static __inline__ int atomic_inc_return_relaxed(atomic_t *v) -{ - int t; - - __asm__ __volatile__( -"1: lwarx %0,0,%2 # atomic_inc_return_relaxed\n" -" addic %0,%0,1\n" - PPC405_ERR77(0, %2) -" stwcx. %0,0,%2\n" -" bne- 1b" - : "=&r" (t), "+m" (v->counter) - : "r" (&v->counter) - : "cc", "xer"); - - return t; -} - -static __inline__ void atomic_dec(atomic_t *v) -{ - int t; - - __asm__ __volatile__( -"1: lwarx %0,0,%2 # atomic_dec\n\ - addic %0,%0,-1\n" - PPC405_ERR77(0,%2)\ -" stwcx. %0,0,%2\n\ - bne- 1b" - : "=&r" (t), "+m" (v->counter) - : "r" (&v->counter) - : "cc", "xer"); -} -#define atomic_dec atomic_dec - -static __inline__ int atomic_dec_return_relaxed(atomic_t *v) -{ - int t; - - __asm__ __volatile__( -"1: lwarx %0,0,%2 # atomic_dec_return_relaxed\n" -" addic %0,%0,-1\n" - PPC405_ERR77(0, %2) -" stwcx. %0,0,%2\n" -" bne- 1b" - : "=&r" (t), "+m" (v->counter) - : "r" (&v->counter) - : "cc", "xer"); - - return t; -} - -#define atomic_inc_return_relaxed atomic_inc_return_relaxed -#define atomic_dec_return_relaxed atomic_dec_return_relaxed - -#define atomic_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n))) -#define atomic_cmpxchg_relaxed(v, o, n) \ - cmpxchg_relaxed(&((v)->counter), (o), (n)) -#define atomic_cmpxchg_acquire(v, o, n) \ - cmpxchg_acquire(&((v)->counter), (o), (n)) - -#define atomic_xchg(v, new) (xchg(&((v)->counter), new)) -#define atomic_xchg_relaxed(v, new) xchg_relaxed(&((v)->counter), (new)) - /** * atomic_fetch_add_unless - add unless the number is a given value * @v: pointer of type atomic_t @@ -210,7 +135,7 @@ static __inline__ int atomic_dec_return_relaxed(atomic_t *v) * Atomically adds @a to @v, so long as it was not @u. * Returns the old value of @v. */ -static __inline__ int atomic_fetch_add_unless(atomic_t *v, int a, int u) +static __inline__ int arch_atomic_fetch_add_unless(atomic_t *v, int a, int u) { int t; @@ -219,58 +144,26 @@ static __inline__ int atomic_fetch_add_unless(atomic_t *v, int a, int u) "1: lwarx %0,0,%1 # atomic_fetch_add_unless\n\ cmpw 0,%0,%3 \n\ beq 2f \n\ - add %0,%2,%0 \n" - PPC405_ERR77(0,%2) + add%I2c %0,%0,%2 \n" " stwcx. %0,0,%1 \n\ bne- 1b \n" PPC_ATOMIC_EXIT_BARRIER -" subf %0,%2,%0 \n\ +" sub%I2c %0,%0,%2 \n\ 2:" : "=&r" (t) - : "r" (&v->counter), "r" (a), "r" (u) - : "cc", "memory"); + : "r" (&v->counter), "rI" (a), "r" (u) + : "cc", "memory", "xer"); return t; } -#define atomic_fetch_add_unless atomic_fetch_add_unless - -/** - * atomic_inc_not_zero - increment unless the number is zero - * @v: pointer of type atomic_t - * - * Atomically increments @v by 1, so long as @v is non-zero. - * Returns non-zero if @v was non-zero, and zero otherwise. - */ -static __inline__ int atomic_inc_not_zero(atomic_t *v) -{ - int t1, t2; - - __asm__ __volatile__ ( - PPC_ATOMIC_ENTRY_BARRIER -"1: lwarx %0,0,%2 # atomic_inc_not_zero\n\ - cmpwi 0,%0,0\n\ - beq- 2f\n\ - addic %1,%0,1\n" - PPC405_ERR77(0,%2) -" stwcx. %1,0,%2\n\ - bne- 1b\n" - PPC_ATOMIC_EXIT_BARRIER - "\n\ -2:" - : "=&r" (t1), "=&r" (t2) - : "r" (&v->counter) - : "cc", "xer", "memory"); - - return t1; -} -#define atomic_inc_not_zero(v) atomic_inc_not_zero((v)) +#define arch_atomic_fetch_add_unless arch_atomic_fetch_add_unless /* * Atomically test *v and decrement if it is greater than 0. * The function returns the old value of *v minus 1, even if * the atomic variable, v, was not decremented. */ -static __inline__ int atomic_dec_if_positive(atomic_t *v) +static __inline__ int arch_atomic_dec_if_positive(atomic_t *v) { int t; @@ -280,7 +173,6 @@ static __inline__ int atomic_dec_if_positive(atomic_t *v) cmpwi %0,1\n\ addi %0,%0,-1\n\ blt- 2f\n" - PPC405_ERR77(0,%1) " stwcx. %0,0,%1\n\ bne- 1b" PPC_ATOMIC_EXIT_BARRIER @@ -291,28 +183,36 @@ static __inline__ int atomic_dec_if_positive(atomic_t *v) return t; } -#define atomic_dec_if_positive atomic_dec_if_positive +#define arch_atomic_dec_if_positive arch_atomic_dec_if_positive #ifdef __powerpc64__ #define ATOMIC64_INIT(i) { (i) } -static __inline__ s64 atomic64_read(const atomic64_t *v) +static __inline__ s64 arch_atomic64_read(const atomic64_t *v) { s64 t; - __asm__ __volatile__("ld%U1%X1 %0,%1" : "=r"(t) : "m"(v->counter)); + /* -mprefixed can generate offsets beyond range, fall back hack */ + if (IS_ENABLED(CONFIG_PPC_KERNEL_PREFIXED)) + __asm__ __volatile__("ld %0,0(%1)" : "=r"(t) : "b"(&v->counter)); + else + __asm__ __volatile__("ld%U1%X1 %0,%1" : "=r"(t) : "m<>"(v->counter)); return t; } -static __inline__ void atomic64_set(atomic64_t *v, s64 i) +static __inline__ void arch_atomic64_set(atomic64_t *v, s64 i) { - __asm__ __volatile__("std%U0%X0 %1,%0" : "=m"(v->counter) : "r"(i)); + /* -mprefixed can generate offsets beyond range, fall back hack */ + if (IS_ENABLED(CONFIG_PPC_KERNEL_PREFIXED)) + __asm__ __volatile__("std %1,0(%2)" : "=m"(v->counter) : "r"(i), "b"(&v->counter)); + else + __asm__ __volatile__("std%U0%X0 %1,%0" : "=m<>"(v->counter) : "r"(i)); } #define ATOMIC64_OP(op, asm_op) \ -static __inline__ void atomic64_##op(s64 a, atomic64_t *v) \ +static __inline__ void arch_atomic64_##op(s64 a, atomic64_t *v) \ { \ s64 t; \ \ @@ -328,7 +228,7 @@ static __inline__ void atomic64_##op(s64 a, atomic64_t *v) \ #define ATOMIC64_OP_RETURN_RELAXED(op, asm_op) \ static inline s64 \ -atomic64_##op##_return_relaxed(s64 a, atomic64_t *v) \ +arch_atomic64_##op##_return_relaxed(s64 a, atomic64_t *v) \ { \ s64 t; \ \ @@ -346,7 +246,7 @@ atomic64_##op##_return_relaxed(s64 a, atomic64_t *v) \ #define ATOMIC64_FETCH_OP_RELAXED(op, asm_op) \ static inline s64 \ -atomic64_fetch_##op##_relaxed(s64 a, atomic64_t *v) \ +arch_atomic64_fetch_##op##_relaxed(s64 a, atomic64_t *v) \ { \ s64 res, t; \ \ @@ -370,11 +270,11 @@ atomic64_fetch_##op##_relaxed(s64 a, atomic64_t *v) \ ATOMIC64_OPS(add, add) ATOMIC64_OPS(sub, subf) -#define atomic64_add_return_relaxed atomic64_add_return_relaxed -#define atomic64_sub_return_relaxed atomic64_sub_return_relaxed +#define arch_atomic64_add_return_relaxed arch_atomic64_add_return_relaxed +#define arch_atomic64_sub_return_relaxed arch_atomic64_sub_return_relaxed -#define atomic64_fetch_add_relaxed atomic64_fetch_add_relaxed -#define atomic64_fetch_sub_relaxed atomic64_fetch_sub_relaxed +#define arch_atomic64_fetch_add_relaxed arch_atomic64_fetch_add_relaxed +#define arch_atomic64_fetch_sub_relaxed arch_atomic64_fetch_sub_relaxed #undef ATOMIC64_OPS #define ATOMIC64_OPS(op, asm_op) \ @@ -385,16 +285,16 @@ ATOMIC64_OPS(and, and) ATOMIC64_OPS(or, or) ATOMIC64_OPS(xor, xor) -#define atomic64_fetch_and_relaxed atomic64_fetch_and_relaxed -#define atomic64_fetch_or_relaxed atomic64_fetch_or_relaxed -#define atomic64_fetch_xor_relaxed atomic64_fetch_xor_relaxed +#define arch_atomic64_fetch_and_relaxed arch_atomic64_fetch_and_relaxed +#define arch_atomic64_fetch_or_relaxed arch_atomic64_fetch_or_relaxed +#define arch_atomic64_fetch_xor_relaxed arch_atomic64_fetch_xor_relaxed #undef ATOPIC64_OPS #undef ATOMIC64_FETCH_OP_RELAXED #undef ATOMIC64_OP_RETURN_RELAXED #undef ATOMIC64_OP -static __inline__ void atomic64_inc(atomic64_t *v) +static __inline__ void arch_atomic64_inc(atomic64_t *v) { s64 t; @@ -407,9 +307,9 @@ static __inline__ void atomic64_inc(atomic64_t *v) : "r" (&v->counter) : "cc", "xer"); } -#define atomic64_inc atomic64_inc +#define arch_atomic64_inc arch_atomic64_inc -static __inline__ s64 atomic64_inc_return_relaxed(atomic64_t *v) +static __inline__ s64 arch_atomic64_inc_return_relaxed(atomic64_t *v) { s64 t; @@ -425,7 +325,7 @@ static __inline__ s64 atomic64_inc_return_relaxed(atomic64_t *v) return t; } -static __inline__ void atomic64_dec(atomic64_t *v) +static __inline__ void arch_atomic64_dec(atomic64_t *v) { s64 t; @@ -438,9 +338,9 @@ static __inline__ void atomic64_dec(atomic64_t *v) : "r" (&v->counter) : "cc", "xer"); } -#define atomic64_dec atomic64_dec +#define arch_atomic64_dec arch_atomic64_dec -static __inline__ s64 atomic64_dec_return_relaxed(atomic64_t *v) +static __inline__ s64 arch_atomic64_dec_return_relaxed(atomic64_t *v) { s64 t; @@ -456,14 +356,14 @@ static __inline__ s64 atomic64_dec_return_relaxed(atomic64_t *v) return t; } -#define atomic64_inc_return_relaxed atomic64_inc_return_relaxed -#define atomic64_dec_return_relaxed atomic64_dec_return_relaxed +#define arch_atomic64_inc_return_relaxed arch_atomic64_inc_return_relaxed +#define arch_atomic64_dec_return_relaxed arch_atomic64_dec_return_relaxed /* * Atomically test *v and decrement if it is greater than 0. * The function returns the old value of *v minus 1. */ -static __inline__ s64 atomic64_dec_if_positive(atomic64_t *v) +static __inline__ s64 arch_atomic64_dec_if_positive(atomic64_t *v) { s64 t; @@ -482,16 +382,7 @@ static __inline__ s64 atomic64_dec_if_positive(atomic64_t *v) return t; } -#define atomic64_dec_if_positive atomic64_dec_if_positive - -#define atomic64_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n))) -#define atomic64_cmpxchg_relaxed(v, o, n) \ - cmpxchg_relaxed(&((v)->counter), (o), (n)) -#define atomic64_cmpxchg_acquire(v, o, n) \ - cmpxchg_acquire(&((v)->counter), (o), (n)) - -#define atomic64_xchg(v, new) (xchg(&((v)->counter), new)) -#define atomic64_xchg_relaxed(v, new) xchg_relaxed(&((v)->counter), (new)) +#define arch_atomic64_dec_if_positive arch_atomic64_dec_if_positive /** * atomic64_fetch_add_unless - add unless the number is a given value @@ -502,7 +393,7 @@ static __inline__ s64 atomic64_dec_if_positive(atomic64_t *v) * Atomically adds @a to @v, so long as it was not @u. * Returns the old value of @v. */ -static __inline__ s64 atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u) +static __inline__ s64 arch_atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u) { s64 t; @@ -523,7 +414,7 @@ static __inline__ s64 atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u) return t; } -#define atomic64_fetch_add_unless atomic64_fetch_add_unless +#define arch_atomic64_fetch_add_unless arch_atomic64_fetch_add_unless /** * atomic_inc64_not_zero - increment unless the number is zero @@ -532,7 +423,7 @@ static __inline__ s64 atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u) * Atomically increments @v by 1, so long as @v is non-zero. * Returns non-zero if @v was non-zero, and zero otherwise. */ -static __inline__ int atomic64_inc_not_zero(atomic64_t *v) +static __inline__ int arch_atomic64_inc_not_zero(atomic64_t *v) { s64 t1, t2; @@ -553,7 +444,7 @@ static __inline__ int atomic64_inc_not_zero(atomic64_t *v) return t1 != 0; } -#define atomic64_inc_not_zero(v) atomic64_inc_not_zero((v)) +#define arch_atomic64_inc_not_zero(v) arch_atomic64_inc_not_zero((v)) #endif /* __powerpc64__ */ diff --git a/arch/powerpc/include/asm/barrier.h b/arch/powerpc/include/asm/barrier.h index fbe8df433019..b95b666f0374 100644 --- a/arch/powerpc/include/asm/barrier.h +++ b/arch/powerpc/include/asm/barrier.h @@ -7,6 +7,10 @@ #include <asm/asm-const.h> +#ifndef __ASSEMBLY__ +#include <asm/ppc-opcode.h> +#endif + /* * Memory barrier. * The sync instruction guarantees that all memory accesses initiated @@ -18,8 +22,6 @@ * mb() prevents loads and stores being reordered across this point. * rmb() prevents loads being reordered across this point. * wmb() prevents stores being reordered across this point. - * read_barrier_depends() prevents data-dependent loads being reordered - * across this point (nop on PPC). * * *mb() variants without smp_ prefix must order all types of memory * operations with one another. sync is the only instruction sufficient @@ -33,24 +35,28 @@ * However, on CPUs that don't support lwsync, lwsync actually maps to a * heavy-weight sync, so smp_wmb() can be a lighter-weight eieio. */ -#define mb() __asm__ __volatile__ ("sync" : : : "memory") -#define rmb() __asm__ __volatile__ ("sync" : : : "memory") -#define wmb() __asm__ __volatile__ ("sync" : : : "memory") +#define __mb() __asm__ __volatile__ ("sync" : : : "memory") +#define __rmb() __asm__ __volatile__ ("sync" : : : "memory") +#define __wmb() __asm__ __volatile__ ("sync" : : : "memory") /* The sub-arch has lwsync */ -#if defined(__powerpc64__) || defined(CONFIG_PPC_E500MC) +#if defined(CONFIG_PPC64) || defined(CONFIG_PPC_E500MC) # define SMPWMB LWSYNC +#elif defined(CONFIG_BOOKE) +# define SMPWMB mbar #else # define SMPWMB eieio #endif +/* clang defines this macro for a builtin, which will not work with runtime patching */ +#undef __lwsync #define __lwsync() __asm__ __volatile__ (stringify_in_c(LWSYNC) : : :"memory") -#define dma_rmb() __lwsync() -#define dma_wmb() __asm__ __volatile__ (stringify_in_c(SMPWMB) : : :"memory") +#define __dma_rmb() __lwsync() +#define __dma_wmb() __asm__ __volatile__ (stringify_in_c(SMPWMB) : : :"memory") #define __smp_lwsync() __lwsync() -#define __smp_mb() mb() +#define __smp_mb() __mb() #define __smp_rmb() __lwsync() #define __smp_wmb() __asm__ __volatile__ (stringify_in_c(SMPWMB) : : :"memory") @@ -80,7 +86,7 @@ do { \ #ifdef CONFIG_PPC_BOOK3S_64 #define NOSPEC_BARRIER_SLOT nop -#elif defined(CONFIG_PPC_FSL_BOOK3E) +#elif defined(CONFIG_PPC_E500) #define NOSPEC_BARRIER_SLOT nop; nop #endif @@ -99,6 +105,15 @@ do { \ #define barrier_nospec() #endif /* CONFIG_PPC_BARRIER_NOSPEC */ +/* + * pmem_wmb() ensures that all stores for which the modification + * are written to persistent storage by preceding dcbfps/dcbstps + * instructions have updated persistent storage before any data + * access or data transfer caused by subsequent instructions is + * initiated. + */ +#define pmem_wmb() __asm__ __volatile__(PPC_PHWSYNC ::: "memory") + #include <asm-generic/barrier.h> #endif /* _ASM_POWERPC_BARRIER_H */ diff --git a/arch/powerpc/include/asm/bitops.h b/arch/powerpc/include/asm/bitops.h index 28dcf8222943..671ecc6711e3 100644 --- a/arch/powerpc/include/asm/bitops.h +++ b/arch/powerpc/include/asm/bitops.h @@ -41,7 +41,6 @@ #include <linux/compiler.h> #include <asm/asm-compat.h> #include <asm/synch.h> -#include <asm/asm-405.h> /* PPC bit number conversion */ #define PPC_BITLSHIFT(be) (BITS_PER_LONG - 1 - (be)) @@ -71,21 +70,62 @@ static inline void fn(unsigned long mask, \ unsigned long *p = (unsigned long *)_p; \ __asm__ __volatile__ ( \ prefix \ -"1:" PPC_LLARX(%0,0,%3,0) "\n" \ - stringify_in_c(op) "%0,%0,%2\n" \ - PPC405_ERR77(0,%3) \ +"1:" PPC_LLARX "%0,0,%3,0\n" \ + #op "%I2 %0,%0,%2\n" \ PPC_STLCX "%0,0,%3\n" \ "bne- 1b\n" \ : "=&r" (old), "+m" (*p) \ - : "r" (mask), "r" (p) \ + : "rK" (mask), "r" (p) \ : "cc", "memory"); \ } DEFINE_BITOP(set_bits, or, "") -DEFINE_BITOP(clear_bits, andc, "") -DEFINE_BITOP(clear_bits_unlock, andc, PPC_RELEASE_BARRIER) DEFINE_BITOP(change_bits, xor, "") +static __always_inline bool is_rlwinm_mask_valid(unsigned long x) +{ + if (!x) + return false; + if (x & 1) + x = ~x; // make the mask non-wrapping + x += x & -x; // adding the low set bit results in at most one bit set + + return !(x & (x - 1)); +} + +#define DEFINE_CLROP(fn, prefix) \ +static inline void fn(unsigned long mask, volatile unsigned long *_p) \ +{ \ + unsigned long old; \ + unsigned long *p = (unsigned long *)_p; \ + \ + if (IS_ENABLED(CONFIG_PPC32) && \ + __builtin_constant_p(mask) && is_rlwinm_mask_valid(~mask)) {\ + asm volatile ( \ + prefix \ + "1:" "lwarx %0,0,%3\n" \ + "rlwinm %0,%0,0,%2\n" \ + "stwcx. %0,0,%3\n" \ + "bne- 1b\n" \ + : "=&r" (old), "+m" (*p) \ + : "n" (~mask), "r" (p) \ + : "cc", "memory"); \ + } else { \ + asm volatile ( \ + prefix \ + "1:" PPC_LLARX "%0,0,%3,0\n" \ + "andc %0,%0,%2\n" \ + PPC_STLCX "%0,0,%3\n" \ + "bne- 1b\n" \ + : "=&r" (old), "+m" (*p) \ + : "r" (mask), "r" (p) \ + : "cc", "memory"); \ + } \ +} + +DEFINE_CLROP(clear_bits, "") +DEFINE_CLROP(clear_bits_unlock, PPC_RELEASE_BARRIER) + static inline void arch_set_bit(int nr, volatile unsigned long *addr) { set_bits(BIT_MASK(nr), addr + BIT_WORD(nr)); @@ -117,14 +157,13 @@ static inline unsigned long fn( \ unsigned long *p = (unsigned long *)_p; \ __asm__ __volatile__ ( \ prefix \ -"1:" PPC_LLARX(%0,0,%3,eh) "\n" \ - stringify_in_c(op) "%1,%0,%2\n" \ - PPC405_ERR77(0,%3) \ +"1:" PPC_LLARX "%0,0,%3,%4\n" \ + #op "%I2 %1,%0,%2\n" \ PPC_STLCX "%1,0,%3\n" \ "bne- 1b\n" \ postfix \ : "=&r" (old), "=&r" (t) \ - : "r" (mask), "r" (p) \ + : "rK" (mask), "r" (p), "n" (eh) \ : "cc", "memory"); \ return (old & mask); \ } @@ -132,12 +171,43 @@ static inline unsigned long fn( \ DEFINE_TESTOP(test_and_set_bits, or, PPC_ATOMIC_ENTRY_BARRIER, PPC_ATOMIC_EXIT_BARRIER, 0) DEFINE_TESTOP(test_and_set_bits_lock, or, "", - PPC_ACQUIRE_BARRIER, 1) -DEFINE_TESTOP(test_and_clear_bits, andc, PPC_ATOMIC_ENTRY_BARRIER, - PPC_ATOMIC_EXIT_BARRIER, 0) + PPC_ACQUIRE_BARRIER, IS_ENABLED(CONFIG_PPC64)) DEFINE_TESTOP(test_and_change_bits, xor, PPC_ATOMIC_ENTRY_BARRIER, PPC_ATOMIC_EXIT_BARRIER, 0) +static inline unsigned long test_and_clear_bits(unsigned long mask, volatile unsigned long *_p) +{ + unsigned long old, t; + unsigned long *p = (unsigned long *)_p; + + if (IS_ENABLED(CONFIG_PPC32) && + __builtin_constant_p(mask) && is_rlwinm_mask_valid(~mask)) { + asm volatile ( + PPC_ATOMIC_ENTRY_BARRIER + "1:" "lwarx %0,0,%3\n" + "rlwinm %1,%0,0,%2\n" + "stwcx. %1,0,%3\n" + "bne- 1b\n" + PPC_ATOMIC_EXIT_BARRIER + : "=&r" (old), "=&r" (t) + : "n" (~mask), "r" (p) + : "cc", "memory"); + } else { + asm volatile ( + PPC_ATOMIC_ENTRY_BARRIER + "1:" PPC_LLARX "%0,0,%3,0\n" + "andc %1,%0,%2\n" + PPC_STLCX "%1,0,%3\n" + "bne- 1b\n" + PPC_ATOMIC_EXIT_BARRIER + : "=&r" (old), "=&r" (t) + : "r" (mask), "r" (p) + : "cc", "memory"); + } + + return (old & mask); +} + static inline int arch_test_and_set_bit(unsigned long nr, volatile unsigned long *addr) { @@ -163,36 +233,24 @@ static inline int arch_test_and_change_bit(unsigned long nr, return test_and_change_bits(BIT_MASK(nr), addr + BIT_WORD(nr)) != 0; } -#ifdef CONFIG_PPC64 -static inline unsigned long -clear_bit_unlock_return_word(int nr, volatile unsigned long *addr) +static inline bool arch_xor_unlock_is_negative_byte(unsigned long mask, + volatile unsigned long *p) { unsigned long old, t; - unsigned long *p = (unsigned long *)addr + BIT_WORD(nr); - unsigned long mask = BIT_MASK(nr); __asm__ __volatile__ ( PPC_RELEASE_BARRIER -"1:" PPC_LLARX(%0,0,%3,0) "\n" - "andc %1,%0,%2\n" - PPC405_ERR77(0,%3) +"1:" PPC_LLARX "%0,0,%3,0\n" + "xor %1,%0,%2\n" PPC_STLCX "%1,0,%3\n" "bne- 1b\n" : "=&r" (old), "=&r" (t) : "r" (mask), "r" (p) : "cc", "memory"); - return old; + return (old & BIT_MASK(7)) != 0; } - -/* - * This is a special function for mm/filemap.c - * Bit 7 corresponds to PG_waiters. - */ -#define arch_clear_bit_unlock_is_negative_byte(nr, addr) \ - (clear_bit_unlock_return_word(nr, addr) & BIT_MASK(7)) - -#endif /* CONFIG_PPC64 */ +#define arch_xor_unlock_is_negative_byte arch_xor_unlock_is_negative_byte #include <asm-generic/bitops/non-atomic.h> @@ -218,17 +276,36 @@ static inline void arch___clear_bit_unlock(int nr, volatile unsigned long *addr) * fls: find last (most-significant) bit set. * Note fls(0) = 0, fls(1) = 1, fls(0x80000000) = 32. */ -static inline int fls(unsigned int x) +static __always_inline int fls(unsigned int x) { - return 32 - __builtin_clz(x); + int lz; + + if (__builtin_constant_p(x)) + return x ? 32 - __builtin_clz(x) : 0; + asm("cntlzw %0,%1" : "=r" (lz) : "r" (x)); + return 32 - lz; } #include <asm-generic/bitops/builtin-__fls.h> -static inline int fls64(__u64 x) +/* + * 64-bit can do this using one cntlzd (count leading zeroes doubleword) + * instruction; for 32-bit we use the generic version, which does two + * 32-bit fls calls. + */ +#ifdef CONFIG_PPC64 +static __always_inline int fls64(__u64 x) { - return 64 - __builtin_clzll(x); + int lz; + + if (__builtin_constant_p(x)) + return x ? 64 - __builtin_clzll(x) : 0; + asm("cntlzd %0,%1" : "=r" (lz) : "r" (x)); + return 64 - lz; } +#else +#include <asm-generic/bitops/fls64.h> +#endif #ifdef CONFIG_PPC64 unsigned int __arch_hweight8(unsigned int w); @@ -240,8 +317,6 @@ unsigned long __arch_hweight64(__u64 w); #include <asm-generic/bitops/hweight.h> #endif -#include <asm-generic/bitops/find.h> - /* wrappers that deal with KASAN instrumentation */ #include <asm-generic/bitops/instrumented-atomic.h> #include <asm-generic/bitops/instrumented-lock.h> diff --git a/arch/powerpc/include/asm/book3s/32/hash.h b/arch/powerpc/include/asm/book3s/32/hash.h deleted file mode 100644 index 2a0a467d2985..000000000000 --- a/arch/powerpc/include/asm/book3s/32/hash.h +++ /dev/null @@ -1,45 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ASM_POWERPC_BOOK3S_32_HASH_H -#define _ASM_POWERPC_BOOK3S_32_HASH_H -#ifdef __KERNEL__ - -/* - * The "classic" 32-bit implementation of the PowerPC MMU uses a hash - * table containing PTEs, together with a set of 16 segment registers, - * to define the virtual to physical address mapping. - * - * We use the hash table as an extended TLB, i.e. a cache of currently - * active mappings. We maintain a two-level page table tree, much - * like that used by the i386, for the sake of the Linux memory - * management code. Low-level assembler code in hash_low_32.S - * (procedure hash_page) is responsible for extracting ptes from the - * tree and putting them into the hash table when necessary, and - * updating the accessed and modified bits in the page table tree. - */ - -#define _PAGE_PRESENT 0x001 /* software: pte contains a translation */ -#define _PAGE_HASHPTE 0x002 /* hash_page has made an HPTE for this pte */ -#define _PAGE_USER 0x004 /* usermode access allowed */ -#define _PAGE_GUARDED 0x008 /* G: prohibit speculative access */ -#define _PAGE_COHERENT 0x010 /* M: enforce memory coherence (SMP systems) */ -#define _PAGE_NO_CACHE 0x020 /* I: cache inhibit */ -#define _PAGE_WRITETHRU 0x040 /* W: cache write-through */ -#define _PAGE_DIRTY 0x080 /* C: page changed */ -#define _PAGE_ACCESSED 0x100 /* R: page referenced */ -#define _PAGE_EXEC 0x200 /* software: exec allowed */ -#define _PAGE_RW 0x400 /* software: user write access allowed */ -#define _PAGE_SPECIAL 0x800 /* software: Special page */ - -#ifdef CONFIG_PTE_64BIT -/* We never clear the high word of the pte */ -#define _PTE_NONE_MASK (0xffffffff00000000ULL | _PAGE_HASHPTE) -#else -#define _PTE_NONE_MASK _PAGE_HASHPTE -#endif - -#define _PMD_PRESENT 0 -#define _PMD_PRESENT_MASK (PAGE_MASK) -#define _PMD_BAD (~PAGE_MASK) - -#endif /* __KERNEL__ */ -#endif /* _ASM_POWERPC_BOOK3S_32_HASH_H */ diff --git a/arch/powerpc/include/asm/book3s/32/kup.h b/arch/powerpc/include/asm/book3s/32/kup.h index f9dc597b0b86..4e14a5427a63 100644 --- a/arch/powerpc/include/asm/book3s/32/kup.h +++ b/arch/powerpc/include/asm/book3s/32/kup.h @@ -2,141 +2,170 @@ #ifndef _ASM_POWERPC_BOOK3S_32_KUP_H #define _ASM_POWERPC_BOOK3S_32_KUP_H +#include <asm/bug.h> #include <asm/book3s/32/mmu-hash.h> +#include <asm/mmu.h> +#include <asm/synch.h> -#ifdef __ASSEMBLY__ - -.macro kuep_update_sr gpr1, gpr2 /* NEVER use r0 as gpr2 due to addis */ -101: mtsrin \gpr1, \gpr2 - addi \gpr1, \gpr1, 0x111 /* next VSID */ - rlwinm \gpr1, \gpr1, 0, 0xf0ffffff /* clear VSID overflow */ - addis \gpr2, \gpr2, 0x1000 /* address of next segment */ - bdnz 101b - isync -.endm - -.macro kuep_lock gpr1, gpr2 -#ifdef CONFIG_PPC_KUEP - li \gpr1, NUM_USER_SEGMENTS - li \gpr2, 0 - mtctr \gpr1 - mfsrin \gpr1, \gpr2 - oris \gpr1, \gpr1, SR_NX@h /* set Nx */ - kuep_update_sr \gpr1, \gpr2 -#endif -.endm - -.macro kuep_unlock gpr1, gpr2 -#ifdef CONFIG_PPC_KUEP - li \gpr1, NUM_USER_SEGMENTS - li \gpr2, 0 - mtctr \gpr1 - mfsrin \gpr1, \gpr2 - rlwinm \gpr1, \gpr1, 0, ~SR_NX /* Clear Nx */ - kuep_update_sr \gpr1, \gpr2 -#endif -.endm +#ifndef __ASSEMBLY__ #ifdef CONFIG_PPC_KUAP -.macro kuap_update_sr gpr1, gpr2, gpr3 /* NEVER use r0 as gpr2 due to addis */ -101: mtsrin \gpr1, \gpr2 - addi \gpr1, \gpr1, 0x111 /* next VSID */ - rlwinm \gpr1, \gpr1, 0, 0xf0ffffff /* clear VSID overflow */ - addis \gpr2, \gpr2, 0x1000 /* address of next segment */ - cmplw \gpr2, \gpr3 - blt- 101b - isync -.endm - -.macro kuap_save_and_lock sp, thread, gpr1, gpr2, gpr3 - lwz \gpr2, KUAP(\thread) - rlwinm. \gpr3, \gpr2, 28, 0xf0000000 - stw \gpr2, STACK_REGS_KUAP(\sp) - beq+ 102f - li \gpr1, 0 - stw \gpr1, KUAP(\thread) - mfsrin \gpr1, \gpr2 - oris \gpr1, \gpr1, SR_KS@h /* set Ks */ - kuap_update_sr \gpr1, \gpr2, \gpr3 -102: -.endm - -.macro kuap_restore sp, current, gpr1, gpr2, gpr3 - lwz \gpr2, STACK_REGS_KUAP(\sp) - rlwinm. \gpr3, \gpr2, 28, 0xf0000000 - stw \gpr2, THREAD + KUAP(\current) - beq+ 102f - mfsrin \gpr1, \gpr2 - rlwinm \gpr1, \gpr1, 0, ~SR_KS /* Clear Ks */ - kuap_update_sr \gpr1, \gpr2, \gpr3 -102: -.endm - -.macro kuap_check current, gpr -#ifdef CONFIG_PPC_KUAP_DEBUG - lwz \gpr2, KUAP(thread) -999: twnei \gpr, 0 - EMIT_BUG_ENTRY 999b, __FILE__, __LINE__, (BUGFLAG_WARNING | BUGFLAG_ONCE) -#endif -.endm +#include <linux/sched.h> -#endif /* CONFIG_PPC_KUAP */ +#define KUAP_NONE (~0UL) -#else /* !__ASSEMBLY__ */ +static __always_inline void kuap_lock_one(unsigned long addr) +{ + mtsr(mfsr(addr) | SR_KS, addr); + isync(); /* Context sync required after mtsr() */ +} -#ifdef CONFIG_PPC_KUAP +static __always_inline void kuap_unlock_one(unsigned long addr) +{ + mtsr(mfsr(addr) & ~SR_KS, addr); + isync(); /* Context sync required after mtsr() */ +} -#include <linux/sched.h> +static __always_inline void uaccess_begin_32s(unsigned long addr) +{ + unsigned long tmp; + + asm volatile(ASM_MMU_FTR_IFSET( + "mfsrin %0, %1;" + "rlwinm %0, %0, 0, %2;" + "mtsrin %0, %1;" + "isync", "", %3) + : "=&r"(tmp) + : "r"(addr), "i"(~SR_KS), "i"(MMU_FTR_KUAP) + : "memory"); +} -static inline void kuap_update_sr(u32 sr, u32 addr, u32 end) +static __always_inline void uaccess_end_32s(unsigned long addr) { - addr &= 0xf0000000; /* align addr to start of segment */ - barrier(); /* make sure thread.kuap is updated before playing with SRs */ - while (addr < end) { - mtsrin(sr, addr); - sr += 0x111; /* next VSID */ - sr &= 0xf0ffffff; /* clear VSID overflow */ - addr += 0x10000000; /* address of next segment */ - } - isync(); /* Context sync required after mtsrin() */ + unsigned long tmp; + + asm volatile(ASM_MMU_FTR_IFSET( + "mfsrin %0, %1;" + "oris %0, %0, %2;" + "mtsrin %0, %1;" + "isync", "", %3) + : "=&r"(tmp) + : "r"(addr), "i"(SR_KS >> 16), "i"(MMU_FTR_KUAP) + : "memory"); } -static inline void allow_user_access(void __user *to, const void __user *from, u32 size) +static __always_inline void __kuap_save_and_lock(struct pt_regs *regs) { - u32 addr, end; + unsigned long kuap = current->thread.kuap; - if (__builtin_constant_p(to) && to == NULL) + regs->kuap = kuap; + if (unlikely(kuap == KUAP_NONE)) return; - addr = (__force u32)to; + current->thread.kuap = KUAP_NONE; + kuap_lock_one(kuap); +} +#define __kuap_save_and_lock __kuap_save_and_lock + +static __always_inline void kuap_user_restore(struct pt_regs *regs) +{ +} - if (!addr || addr >= TASK_SIZE || !size) +static __always_inline void __kuap_kernel_restore(struct pt_regs *regs, unsigned long kuap) +{ + if (unlikely(kuap != KUAP_NONE)) { + current->thread.kuap = KUAP_NONE; + kuap_lock_one(kuap); + } + + if (likely(regs->kuap == KUAP_NONE)) return; - end = min(addr + size, TASK_SIZE); - current->thread.kuap = (addr & 0xf0000000) | ((((end - 1) >> 28) + 1) & 0xf); - kuap_update_sr(mfsrin(addr) & ~SR_KS, addr, end); /* Clear Ks */ + current->thread.kuap = regs->kuap; + + kuap_unlock_one(regs->kuap); } -static inline void prevent_user_access(void __user *to, const void __user *from, u32 size) +static __always_inline unsigned long __kuap_get_and_assert_locked(void) { - u32 addr = (__force u32)to; - u32 end = min(addr + size, TASK_SIZE); + unsigned long kuap = current->thread.kuap; + + WARN_ON_ONCE(IS_ENABLED(CONFIG_PPC_KUAP_DEBUG) && kuap != KUAP_NONE); + + return kuap; +} +#define __kuap_get_and_assert_locked __kuap_get_and_assert_locked - if (!addr || addr >= TASK_SIZE || !size) +static __always_inline void allow_user_access(void __user *to, const void __user *from, + u32 size, unsigned long dir) +{ + BUILD_BUG_ON(!__builtin_constant_p(dir)); + + if (!(dir & KUAP_WRITE)) return; - current->thread.kuap = 0; - kuap_update_sr(mfsrin(addr) | SR_KS, addr, end); /* set Ks */ + current->thread.kuap = (__force u32)to; + uaccess_begin_32s((__force u32)to); } -static inline bool bad_kuap_fault(struct pt_regs *regs, bool is_write) +static __always_inline void prevent_user_access(unsigned long dir) { + u32 kuap = current->thread.kuap; + + BUILD_BUG_ON(!__builtin_constant_p(dir)); + + if (!(dir & KUAP_WRITE)) + return; + + current->thread.kuap = KUAP_NONE; + uaccess_end_32s(kuap); +} + +static __always_inline unsigned long prevent_user_access_return(void) +{ + unsigned long flags = current->thread.kuap; + + if (flags != KUAP_NONE) { + current->thread.kuap = KUAP_NONE; + uaccess_end_32s(flags); + } + + return flags; +} + +static __always_inline void restore_user_access(unsigned long flags) +{ + if (flags != KUAP_NONE) { + current->thread.kuap = flags; + uaccess_begin_32s(flags); + } +} + +static __always_inline bool +__bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write) +{ + unsigned long kuap = regs->kuap; + if (!is_write) return false; + if (kuap == KUAP_NONE) + return true; + + /* + * If faulting address doesn't match unlocked segment, change segment. + * In case of unaligned store crossing two segments, emulate store. + */ + if ((kuap ^ address) & 0xf0000000) { + if (!(kuap & 0x0fffffff) && address > kuap - 4 && fix_alignment(regs)) { + regs_add_return_ip(regs, 4); + emulate_single_step(regs); + } else { + regs->kuap = address; + } + } - return WARN(!regs->kuap, "Bug: write fault blocked by segment registers !"); + return false; } #endif /* CONFIG_PPC_KUAP */ diff --git a/arch/powerpc/include/asm/book3s/32/mmu-hash.h b/arch/powerpc/include/asm/book3s/32/mmu-hash.h index 2e277ca0170f..78c6a5fde1d6 100644 --- a/arch/powerpc/include/asm/book3s/32/mmu-hash.h +++ b/arch/powerpc/include/asm/book3s/32/mmu-hash.h @@ -64,7 +64,92 @@ struct ppc_bat { #define SR_KP 0x20000000 /* User key */ #define SR_KS 0x40000000 /* Supervisor key */ -#ifndef __ASSEMBLY__ +#ifdef __ASSEMBLY__ + +#include <asm/asm-offsets.h> + +.macro uus_addi sr reg1 reg2 imm + .if NUM_USER_SEGMENTS > \sr + addi \reg1,\reg2,\imm + .endif +.endm + +.macro uus_mtsr sr reg1 + .if NUM_USER_SEGMENTS > \sr + mtsr \sr, \reg1 + .endif +.endm + +/* + * This isync() shouldn't be necessary as the kernel is not excepted to run + * any instruction in userspace soon after the update of segments and 'rfi' + * instruction is used to return to userspace, but hash based cores + * (at least G3) seem to exhibit a random behaviour when the 'isync' is not + * there. 603 cores don't have this behaviour so don't do the 'isync' as it + * saves several CPU cycles. + */ +.macro uus_isync +#ifdef CONFIG_PPC_BOOK3S_604 +BEGIN_MMU_FTR_SECTION + isync +END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE) +#endif +.endm + +.macro update_user_segments_by_4 tmp1 tmp2 tmp3 tmp4 + uus_addi 1, \tmp2, \tmp1, 0x111 + uus_addi 2, \tmp3, \tmp1, 0x222 + uus_addi 3, \tmp4, \tmp1, 0x333 + + uus_mtsr 0, \tmp1 + uus_mtsr 1, \tmp2 + uus_mtsr 2, \tmp3 + uus_mtsr 3, \tmp4 + + uus_addi 4, \tmp1, \tmp1, 0x444 + uus_addi 5, \tmp2, \tmp2, 0x444 + uus_addi 6, \tmp3, \tmp3, 0x444 + uus_addi 7, \tmp4, \tmp4, 0x444 + + uus_mtsr 4, \tmp1 + uus_mtsr 5, \tmp2 + uus_mtsr 6, \tmp3 + uus_mtsr 7, \tmp4 + + uus_addi 8, \tmp1, \tmp1, 0x444 + uus_addi 9, \tmp2, \tmp2, 0x444 + uus_addi 10, \tmp3, \tmp3, 0x444 + uus_addi 11, \tmp4, \tmp4, 0x444 + + uus_mtsr 8, \tmp1 + uus_mtsr 9, \tmp2 + uus_mtsr 10, \tmp3 + uus_mtsr 11, \tmp4 + + uus_addi 12, \tmp1, \tmp1, 0x444 + uus_addi 13, \tmp2, \tmp2, 0x444 + uus_addi 14, \tmp3, \tmp3, 0x444 + uus_addi 15, \tmp4, \tmp4, 0x444 + + uus_mtsr 12, \tmp1 + uus_mtsr 13, \tmp2 + uus_mtsr 14, \tmp3 + uus_mtsr 15, \tmp4 + + uus_isync +.endm + +#else + +/* + * This macro defines the mapping from contexts to VSIDs (virtual + * segment IDs). We use a skew on both the context and the high 4 bits + * of the 32-bit virtual address (the "effective segment ID") in order + * to spread out the entries in the MMU hash table. Note, if this + * function is changed then hash functions will have to be + * changed to correspond. + */ +#define CTX_TO_VSID(c, id) ((((c) * (897 * 16)) + (id * 0x111)) & 0xffffff) /* * Hardware Page Table Entry @@ -90,10 +175,16 @@ struct hash_pte { typedef struct { unsigned long id; - unsigned long vdso_base; + unsigned long sr0; + void __user *vdso; } mm_context_t; +#ifdef CONFIG_PPC_KUEP +#define INIT_MM_CONTEXT(mm) .context.sr0 = SR_NX +#endif + void update_bats(void); +static inline void cleanup_cpu_mmu_context(void) { } /* patch sites */ extern s32 patch__hash_page_A0, patch__hash_page_A1, patch__hash_page_A2; @@ -101,6 +192,39 @@ extern s32 patch__hash_page_B, patch__hash_page_C; extern s32 patch__flush_hash_A0, patch__flush_hash_A1, patch__flush_hash_A2; extern s32 patch__flush_hash_B; +#include <asm/reg.h> +#include <asm/task_size_32.h> + +static __always_inline void update_user_segment(u32 n, u32 val) +{ + if (n << 28 < TASK_SIZE) + mtsr(val + n * 0x111, n << 28); +} + +static __always_inline void update_user_segments(u32 val) +{ + val &= 0xf0ffffff; + + update_user_segment(0, val); + update_user_segment(1, val); + update_user_segment(2, val); + update_user_segment(3, val); + update_user_segment(4, val); + update_user_segment(5, val); + update_user_segment(6, val); + update_user_segment(7, val); + update_user_segment(8, val); + update_user_segment(9, val); + update_user_segment(10, val); + update_user_segment(11, val); + update_user_segment(12, val); + update_user_segment(13, val); + update_user_segment(14, val); + update_user_segment(15, val); +} + +int __init find_free_bat(void); +unsigned int bat_block_size(unsigned long base, unsigned long top); #endif /* !__ASSEMBLY__ */ /* We happily ignore the smaller BATs on 601, we don't actually use diff --git a/arch/powerpc/include/asm/book3s/32/pgalloc.h b/arch/powerpc/include/asm/book3s/32/pgalloc.h index 998317702630..dc5c039eb28e 100644 --- a/arch/powerpc/include/asm/book3s/32/pgalloc.h +++ b/arch/powerpc/include/asm/book3s/32/pgalloc.h @@ -49,7 +49,6 @@ static inline void pgtable_free(void *table, unsigned index_size) #define get_hugepd_cache_index(x) (x) -#ifdef CONFIG_SMP static inline void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift) { @@ -66,13 +65,6 @@ static inline void __tlb_remove_table(void *_table) pgtable_free(table, shift); } -#else -static inline void pgtable_free_tlb(struct mmu_gather *tlb, - void *table, int shift) -{ - pgtable_free(table, shift); -} -#endif static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table, unsigned long address) diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h index 0796533d37dd..52971ee30717 100644 --- a/arch/powerpc/include/asm/book3s/32/pgtable.h +++ b/arch/powerpc/include/asm/book3s/32/pgtable.h @@ -2,27 +2,52 @@ #ifndef _ASM_POWERPC_BOOK3S_32_PGTABLE_H #define _ASM_POWERPC_BOOK3S_32_PGTABLE_H -#define __ARCH_USE_5LEVEL_HACK #include <asm-generic/pgtable-nopmd.h> -#include <asm/book3s/32/hash.h> +/* + * The "classic" 32-bit implementation of the PowerPC MMU uses a hash + * table containing PTEs, together with a set of 16 segment registers, + * to define the virtual to physical address mapping. + * + * We use the hash table as an extended TLB, i.e. a cache of currently + * active mappings. We maintain a two-level page table tree, much + * like that used by the i386, for the sake of the Linux memory + * management code. Low-level assembler code in hash_low_32.S + * (procedure hash_page) is responsible for extracting ptes from the + * tree and putting them into the hash table when necessary, and + * updating the accessed and modified bits in the page table tree. + */ -/* And here we include common definitions */ +#define _PAGE_PRESENT 0x001 /* software: pte contains a translation */ +#define _PAGE_HASHPTE 0x002 /* hash_page has made an HPTE for this pte */ +#define _PAGE_READ 0x004 /* software: read access allowed */ +#define _PAGE_GUARDED 0x008 /* G: prohibit speculative access */ +#define _PAGE_COHERENT 0x010 /* M: enforce memory coherence (SMP systems) */ +#define _PAGE_NO_CACHE 0x020 /* I: cache inhibit */ +#define _PAGE_WRITETHRU 0x040 /* W: cache write-through */ +#define _PAGE_DIRTY 0x080 /* C: page changed */ +#define _PAGE_ACCESSED 0x100 /* R: page referenced */ +#define _PAGE_EXEC 0x200 /* software: exec allowed */ +#define _PAGE_WRITE 0x400 /* software: user write access allowed */ +#define _PAGE_SPECIAL 0x800 /* software: Special page */ -#define _PAGE_KERNEL_RO 0 -#define _PAGE_KERNEL_ROX (_PAGE_EXEC) -#define _PAGE_KERNEL_RW (_PAGE_DIRTY | _PAGE_RW) -#define _PAGE_KERNEL_RWX (_PAGE_DIRTY | _PAGE_RW | _PAGE_EXEC) +#ifdef CONFIG_PTE_64BIT +/* We never clear the high word of the pte */ +#define _PTE_NONE_MASK (0xffffffff00000000ULL | _PAGE_HASHPTE) +#else +#define _PTE_NONE_MASK _PAGE_HASHPTE +#endif -#define _PAGE_HPTEFLAGS _PAGE_HASHPTE +#define _PMD_PRESENT 0 +#define _PMD_PRESENT_MASK (PAGE_MASK) +#define _PMD_BAD (~PAGE_MASK) -#ifndef __ASSEMBLY__ +/* We borrow the _PAGE_READ bit to store the exclusive marker in swap PTEs. */ +#define _PAGE_SWP_EXCLUSIVE _PAGE_READ -static inline bool pte_user(pte_t pte) -{ - return pte_val(pte) & _PAGE_USER; -} -#endif /* __ASSEMBLY__ */ +/* And here we include common definitions */ + +#define _PAGE_HPTEFLAGS _PAGE_HASHPTE /* * Location of the PFN in the PTE. Most 32-bit platforms use the same @@ -37,8 +62,10 @@ static inline bool pte_user(pte_t pte) */ #ifdef CONFIG_PTE_64BIT #define PTE_RPN_MASK (~((1ULL << PTE_RPN_SHIFT) - 1)) +#define MAX_POSSIBLE_PHYSMEM_BITS 36 #else #define PTE_RPN_MASK (~((1UL << PTE_RPN_SHIFT) - 1)) +#define MAX_POSSIBLE_PHYSMEM_BITS 32 #endif /* @@ -57,49 +84,16 @@ static inline bool pte_user(pte_t pte) #define _PAGE_BASE_NC (_PAGE_PRESENT | _PAGE_ACCESSED) #define _PAGE_BASE (_PAGE_BASE_NC | _PAGE_COHERENT) -/* - * Permission masks used to generate the __P and __S table. - * - * Note:__pgprot is defined in arch/powerpc/include/asm/page.h - * - * Write permissions imply read permissions for now. - */ -#define PAGE_NONE __pgprot(_PAGE_BASE) -#define PAGE_SHARED __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RW) -#define PAGE_SHARED_X __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RW | _PAGE_EXEC) -#define PAGE_COPY __pgprot(_PAGE_BASE | _PAGE_USER) -#define PAGE_COPY_X __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_EXEC) -#define PAGE_READONLY __pgprot(_PAGE_BASE | _PAGE_USER) -#define PAGE_READONLY_X __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_EXEC) +#include <asm/pgtable-masks.h> /* Permission masks used for kernel mappings */ #define PAGE_KERNEL __pgprot(_PAGE_BASE | _PAGE_KERNEL_RW) #define PAGE_KERNEL_NC __pgprot(_PAGE_BASE_NC | _PAGE_KERNEL_RW | _PAGE_NO_CACHE) -#define PAGE_KERNEL_NCG __pgprot(_PAGE_BASE_NC | _PAGE_KERNEL_RW | \ - _PAGE_NO_CACHE | _PAGE_GUARDED) +#define PAGE_KERNEL_NCG __pgprot(_PAGE_BASE_NC | _PAGE_KERNEL_RW | _PAGE_NO_CACHE | _PAGE_GUARDED) #define PAGE_KERNEL_X __pgprot(_PAGE_BASE | _PAGE_KERNEL_RWX) #define PAGE_KERNEL_RO __pgprot(_PAGE_BASE | _PAGE_KERNEL_RO) #define PAGE_KERNEL_ROX __pgprot(_PAGE_BASE | _PAGE_KERNEL_ROX) -/* - * Protection used for kernel text. We want the debuggers to be able to - * set breakpoints anywhere, so don't write protect the kernel text - * on platforms where such control is possible. - */ -#if defined(CONFIG_KGDB) || defined(CONFIG_XMON) || defined(CONFIG_BDI_SWITCH) ||\ - defined(CONFIG_KPROBES) || defined(CONFIG_DYNAMIC_FTRACE) -#define PAGE_KERNEL_TEXT PAGE_KERNEL_X -#else -#define PAGE_KERNEL_TEXT PAGE_KERNEL_ROX -#endif - -/* Make modules code happy. We don't set RO yet */ -#define PAGE_KERNEL_EXEC PAGE_KERNEL_X - -/* Advertise special mapping type for AGP */ -#define PAGE_AGP (PAGE_KERNEL_NC) -#define HAVE_PAGE_AGP - #define PTE_INDEX_SIZE PTE_SHIFT #define PMD_INDEX_SIZE 0 #define PUD_INDEX_SIZE 0 @@ -113,6 +107,9 @@ static inline bool pte_user(pte_t pte) #define PMD_TABLE_SIZE 0 #define PUD_TABLE_SIZE 0 #define PGD_TABLE_SIZE (sizeof(pgd_t) << PGD_INDEX_SIZE) + +/* Bits to mask out from a PMD to get to the PTE page */ +#define PMD_MASKED_BITS (PTE_TABLE_SIZE - 1) #endif /* __ASSEMBLY__ */ #define PTRS_PER_PTE (1 << PTE_INDEX_SIZE) @@ -138,6 +135,7 @@ static inline bool pte_user(pte_t pte) #ifndef __ASSEMBLY__ int map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot); +void unmap_kernel_page(unsigned long va); #endif /* !__ASSEMBLY__ */ @@ -146,7 +144,14 @@ int map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot); * value (for now) on others, from where we can start layout kernel * virtual space that goes below PKMAP and FIXMAP */ -#include <asm/fixmap.h> + +#define FIXADDR_SIZE 0 +#ifdef CONFIG_KASAN +#include <asm/kasan.h> +#define FIXADDR_TOP (KASAN_SHADOW_START - PAGE_SIZE) +#else +#define FIXADDR_TOP ((unsigned long)(-PAGE_SIZE)) +#endif /* * ioremap_bot starts at that address. Early ioremaps move down from there, @@ -182,18 +187,16 @@ int map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot); */ #define VMALLOC_OFFSET (0x1000000) /* 16M */ -/* - * With CONFIG_STRICT_KERNEL_RWX, kernel segments are set NX. But when modules - * are used, NX cannot be set on VMALLOC space. So vmalloc VM space and linear - * memory shall not share segments. - */ -#if defined(CONFIG_STRICT_KERNEL_RWX) && defined(CONFIG_MODULES) -#define VMALLOC_START ((_ALIGN((long)high_memory, 256L << 20) + VMALLOC_OFFSET) & \ - ~(VMALLOC_OFFSET - 1)) -#else #define VMALLOC_START ((((long)high_memory + VMALLOC_OFFSET) & ~(VMALLOC_OFFSET-1))) -#endif + +#ifdef CONFIG_KASAN_VMALLOC +#define VMALLOC_END ALIGN_DOWN(ioremap_bot, PAGE_SIZE << KASAN_SHADOW_SCALE_SHIFT) +#else #define VMALLOC_END ioremap_bot +#endif + +#define MODULES_END ALIGN_DOWN(PAGE_OFFSET, SZ_256M) +#define MODULES_VADDR (MODULES_END - SZ_256M) #ifndef __ASSEMBLY__ #include <linux/sched.h> @@ -202,9 +205,6 @@ int map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot); /* Bits to mask out from a PGD to get to the PUD page */ #define PGD_MASKED_BITS 0 -#define pte_ERROR(e) \ - pr_err("%s:%d: bad pte %llx.\n", __FILE__, __LINE__, \ - (unsigned long long)pte_val(e)) #define pgd_ERROR(e) \ pr_err("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e)) /* @@ -213,7 +213,7 @@ int map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot); */ #define pte_clear(mm, addr, ptep) \ - do { pte_update(ptep, ~_PAGE_HASHPTE, 0); } while (0) + do { pte_update(mm, addr, ptep, ~_PAGE_HASHPTE, 0, 0); } while (0) #define pmd_none(pmd) (!pmd_val(pmd)) #define pmd_bad(pmd) (pmd_val(pmd) & _PMD_BAD) @@ -236,8 +236,14 @@ extern void add_hash_page(unsigned context, unsigned long va, unsigned long pmdval); /* Flush an entry from the TLB/hash table */ -extern void flush_hash_entry(struct mm_struct *mm, pte_t *ptep, - unsigned long address); +static inline void flush_hash_entry(struct mm_struct *mm, pte_t *ptep, unsigned long addr) +{ + if (mmu_has_feature(MMU_FTR_HPTE_TABLE)) { + unsigned long ptephys = __pa(ptep) & PAGE_MASK; + + flush_hash_pages(mm->context.id, addr, ptephys, 1); + } +} /* * PTE updates. This function is called whenever an existing @@ -248,84 +254,74 @@ extern void flush_hash_entry(struct mm_struct *mm, pte_t *ptep, * and the PTE may be either 32 or 64 bit wide. In the later case, * when using atomic updates, only the low part of the PTE is * accessed atomically. - * - * In addition, on 44x, we also maintain a global flag indicating - * that an executable user mapping was modified, which is needed - * to properly flush the virtually tagged instruction cache of - * those implementations. */ +static inline pte_basic_t pte_update(struct mm_struct *mm, unsigned long addr, pte_t *p, + unsigned long clr, unsigned long set, int huge) +{ + pte_basic_t old; + + if (mmu_has_feature(MMU_FTR_HPTE_TABLE)) { + unsigned long tmp; + + asm volatile( +#ifndef CONFIG_PTE_64BIT + "1: lwarx %0, 0, %3\n" + " andc %1, %0, %4\n" +#else + "1: lwarx %L0, 0, %3\n" + " lwz %0, -4(%3)\n" + " andc %1, %L0, %4\n" +#endif + " or %1, %1, %5\n" + " stwcx. %1, 0, %3\n" + " bne- 1b" + : "=&r" (old), "=&r" (tmp), "=m" (*p) #ifndef CONFIG_PTE_64BIT -static inline unsigned long pte_update(pte_t *p, - unsigned long clr, - unsigned long set) -{ - unsigned long old, tmp; - - __asm__ __volatile__("\ -1: lwarx %0,0,%3\n\ - andc %1,%0,%4\n\ - or %1,%1,%5\n" -" stwcx. %1,0,%3\n\ - bne- 1b" - : "=&r" (old), "=&r" (tmp), "=m" (*p) - : "r" (p), "r" (clr), "r" (set), "m" (*p) - : "cc" ); + : "r" (p), +#else + : "b" ((unsigned long)(p) + 4), +#endif + "r" (clr), "r" (set), "m" (*p) + : "cc" ); + } else { + old = pte_val(*p); - return old; -} -#else /* CONFIG_PTE_64BIT */ -static inline unsigned long long pte_update(pte_t *p, - unsigned long clr, - unsigned long set) -{ - unsigned long long old; - unsigned long tmp; - - __asm__ __volatile__("\ -1: lwarx %L0,0,%4\n\ - lwzx %0,0,%3\n\ - andc %1,%L0,%5\n\ - or %1,%1,%6\n" -" stwcx. %1,0,%4\n\ - bne- 1b" - : "=&r" (old), "=&r" (tmp), "=m" (*p) - : "r" (p), "r" ((unsigned long)(p) + 4), "r" (clr), "r" (set), "m" (*p) - : "cc" ); + *p = __pte((old & ~(pte_basic_t)clr) | set); + } return old; } -#endif /* CONFIG_PTE_64BIT */ /* * 2.6 calls this without flushing the TLB entry; this is wrong * for our hash-based implementation, we fix that up here. */ #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG -static inline int __ptep_test_and_clear_young(unsigned int context, unsigned long addr, pte_t *ptep) +static inline int __ptep_test_and_clear_young(struct mm_struct *mm, + unsigned long addr, pte_t *ptep) { unsigned long old; - old = pte_update(ptep, _PAGE_ACCESSED, 0); - if (old & _PAGE_HASHPTE) { - unsigned long ptephys = __pa(ptep) & PAGE_MASK; - flush_hash_pages(context, addr, ptephys, 1); - } + old = pte_update(mm, addr, ptep, _PAGE_ACCESSED, 0, 0); + if (old & _PAGE_HASHPTE) + flush_hash_entry(mm, ptep, addr); + return (old & _PAGE_ACCESSED) != 0; } #define ptep_test_and_clear_young(__vma, __addr, __ptep) \ - __ptep_test_and_clear_young((__vma)->vm_mm->context.id, __addr, __ptep) + __ptep_test_and_clear_young((__vma)->vm_mm, __addr, __ptep) #define __HAVE_ARCH_PTEP_GET_AND_CLEAR static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { - return __pte(pte_update(ptep, ~_PAGE_HASHPTE, 0)); + return __pte(pte_update(mm, addr, ptep, ~_PAGE_HASHPTE, 0, 0)); } #define __HAVE_ARCH_PTEP_SET_WRPROTECT static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { - pte_update(ptep, _PAGE_RW, 0); + pte_update(mm, addr, ptep, _PAGE_WRITE, 0, 0); } static inline void __ptep_set_access_flags(struct vm_area_struct *vma, @@ -336,7 +332,7 @@ static inline void __ptep_set_access_flags(struct vm_area_struct *vma, unsigned long set = pte_val(entry) & (_PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_RW | _PAGE_EXEC); - pte_update(ptep, 0, set); + pte_update(vma->vm_mm, address, ptep, 0, set, 0); flush_tlb_page(vma, address); } @@ -344,43 +340,56 @@ static inline void __ptep_set_access_flags(struct vm_area_struct *vma, #define __HAVE_ARCH_PTE_SAME #define pte_same(A,B) (((pte_val(A) ^ pte_val(B)) & ~_PAGE_HASHPTE) == 0) -#define pmd_page_vaddr(pmd) \ - ((unsigned long)__va(pmd_val(pmd) & ~(PTE_TABLE_SIZE - 1))) -#define pmd_page(pmd) \ - pfn_to_page(pmd_val(pmd) >> PAGE_SHIFT) - -/* to find an entry in a kernel page-table-directory */ -#define pgd_offset_k(address) pgd_offset(&init_mm, address) - -/* to find an entry in a page-table-directory */ -#define pgd_index(address) ((address) >> PGDIR_SHIFT) -#define pgd_offset(mm, address) ((mm)->pgd + pgd_index(address)) - -/* Find an entry in the third-level page table.. */ -#define pte_index(address) \ - (((address) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1)) -#define pte_offset_kernel(dir, addr) \ - ((pte_t *) pmd_page_vaddr(*(dir)) + pte_index(addr)) -#define pte_offset_map(dir, addr) \ - ((pte_t *)(kmap_atomic(pmd_page(*(dir))) + \ - (pmd_page_vaddr(*(dir)) & ~PAGE_MASK)) + pte_index(addr)) -#define pte_unmap(pte) kunmap_atomic(pte) +#define pmd_pfn(pmd) (pmd_val(pmd) >> PAGE_SHIFT) +#define pmd_page(pmd) pfn_to_page(pmd_pfn(pmd)) /* - * Encode and decode a swap entry. - * Note that the bits we use in a PTE for representing a swap entry - * must not include the _PAGE_PRESENT bit or the _PAGE_HASHPTE bit (if used). - * -- paulus + * Encode/decode swap entries and swap PTEs. Swap PTEs are all PTEs that + * are !pte_none() && !pte_present(). + * + * Format of swap PTEs (32bit PTEs): + * + * 1 1 1 1 1 1 1 1 1 2 2 2 2 2 2 2 2 2 2 3 3 + * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 + * <----------------- offset --------------------> < type -> E H P + * + * E is the exclusive marker that is not stored in swap entries. + * _PAGE_PRESENT (P) and __PAGE_HASHPTE (H) must be 0. + * + * For 64bit PTEs, the offset is extended by 32bit. */ #define __swp_type(entry) ((entry).val & 0x1f) #define __swp_offset(entry) ((entry).val >> 5) -#define __swp_entry(type, offset) ((swp_entry_t) { (type) | ((offset) << 5) }) +#define __swp_entry(type, offset) ((swp_entry_t) { ((type) & 0x1f) | ((offset) << 5) }) #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) >> 3 }) #define __swp_entry_to_pte(x) ((pte_t) { (x).val << 3 }) +static inline int pte_swp_exclusive(pte_t pte) +{ + return pte_val(pte) & _PAGE_SWP_EXCLUSIVE; +} + +static inline pte_t pte_swp_mkexclusive(pte_t pte) +{ + return __pte(pte_val(pte) | _PAGE_SWP_EXCLUSIVE); +} + +static inline pte_t pte_swp_clear_exclusive(pte_t pte) +{ + return __pte(pte_val(pte) & ~_PAGE_SWP_EXCLUSIVE); +} + /* Generic accessors to PTE bits */ -static inline int pte_write(pte_t pte) { return !!(pte_val(pte) & _PAGE_RW);} -static inline int pte_read(pte_t pte) { return 1; } +static inline bool pte_read(pte_t pte) +{ + return !!(pte_val(pte) & _PAGE_READ); +} + +static inline bool pte_write(pte_t pte) +{ + return !!(pte_val(pte) & _PAGE_WRITE); +} + static inline int pte_dirty(pte_t pte) { return !!(pte_val(pte) & _PAGE_DIRTY); } static inline int pte_young(pte_t pte) { return !!(pte_val(pte) & _PAGE_ACCESSED); } static inline int pte_special(pte_t pte) { return !!(pte_val(pte) & _PAGE_SPECIAL); } @@ -415,10 +424,10 @@ static inline bool pte_ci(pte_t pte) static inline bool pte_access_permitted(pte_t pte, bool write) { /* - * A read-only access is controlled by _PAGE_USER bit. - * We have _PAGE_READ set for WRITE and EXECUTE + * A read-only access is controlled by _PAGE_READ bit. + * We have _PAGE_READ set for WRITE */ - if (!pte_present(pte) || !pte_user(pte) || !pte_read(pte)) + if (!pte_present(pte) || !pte_read(pte)) return false; if (write && !pte_write(pte)) @@ -439,15 +448,10 @@ static inline pte_t pfn_pte(unsigned long pfn, pgprot_t pgprot) pgprot_val(pgprot)); } -static inline unsigned long pte_pfn(pte_t pte) -{ - return pte_val(pte) >> PTE_RPN_SHIFT; -} - /* Generic modifiers for PTE bits */ static inline pte_t pte_wrprotect(pte_t pte) { - return __pte(pte_val(pte) & ~_PAGE_RW); + return __pte(pte_val(pte) & ~_PAGE_WRITE); } static inline pte_t pte_exprotect(pte_t pte) @@ -475,8 +479,11 @@ static inline pte_t pte_mkpte(pte_t pte) return pte; } -static inline pte_t pte_mkwrite(pte_t pte) +static inline pte_t pte_mkwrite_novma(pte_t pte) { + /* + * write implies read, hence set both + */ return __pte(pte_val(pte) | _PAGE_RW); } @@ -500,16 +507,6 @@ static inline pte_t pte_mkhuge(pte_t pte) return pte; } -static inline pte_t pte_mkprivileged(pte_t pte) -{ - return __pte(pte_val(pte) & ~_PAGE_USER); -} - -static inline pte_t pte_mkuser(pte_t pte) -{ - return __pte(pte_val(pte) | _PAGE_USER); -} - static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) { return __pte((pte_val(pte) & _PAGE_CHG_MASK) | pgprot_val(newprot)); @@ -518,58 +515,43 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) /* This low level function performs the actual PTE insertion - * Setting the PTE depends on the MMU type and other factors. It's - * an horrible mess that I'm not going to try to clean up now but - * I'm keeping it in one place rather than spread around + * Setting the PTE depends on the MMU type and other factors. + * + * First case is 32-bit in UP mode with 32-bit PTEs, we need to preserve + * the _PAGE_HASHPTE bit since we may not have invalidated the previous + * translation in the hash yet (done in a subsequent flush_tlb_xxx()) + * and see we need to keep track that this PTE needs invalidating. + * + * Second case is 32-bit with 64-bit PTE. In this case, we + * can just store as long as we do the two halves in the right order + * with a barrier in between. This is possible because we take care, + * in the hash code, to pre-invalidate if the PTE was already hashed, + * which synchronizes us with any concurrent invalidation. + * In the percpu case, we fallback to the simple update preserving + * the hash bits (ie, same as the non-SMP case). + * + * Third case is 32-bit in SMP mode with 32-bit PTEs. We use the + * helper pte_update() which does an atomic update. We need to do that + * because a concurrent invalidation can clear _PAGE_HASHPTE. If it's a + * per-CPU PTE such as a kmap_atomic, we also do a simple update preserving + * the hash bits instead. */ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte, int percpu) { -#if defined(CONFIG_SMP) && !defined(CONFIG_PTE_64BIT) - /* First case is 32-bit Hash MMU in SMP mode with 32-bit PTEs. We use the - * helper pte_update() which does an atomic update. We need to do that - * because a concurrent invalidation can clear _PAGE_HASHPTE. If it's a - * per-CPU PTE such as a kmap_atomic, we do a simple update preserving - * the hash bits instead (ie, same as the non-SMP case) - */ - if (percpu) - *ptep = __pte((pte_val(*ptep) & _PAGE_HASHPTE) - | (pte_val(pte) & ~_PAGE_HASHPTE)); - else - pte_update(ptep, ~_PAGE_HASHPTE, pte_val(pte)); - -#elif defined(CONFIG_PTE_64BIT) - /* Second case is 32-bit with 64-bit PTE. In this case, we - * can just store as long as we do the two halves in the right order - * with a barrier in between. This is possible because we take care, - * in the hash code, to pre-invalidate if the PTE was already hashed, - * which synchronizes us with any concurrent invalidation. - * In the percpu case, we also fallback to the simple update preserving - * the hash bits - */ - if (percpu) { - *ptep = __pte((pte_val(*ptep) & _PAGE_HASHPTE) - | (pte_val(pte) & ~_PAGE_HASHPTE)); - return; + if ((!IS_ENABLED(CONFIG_SMP) && !IS_ENABLED(CONFIG_PTE_64BIT)) || percpu) { + *ptep = __pte((pte_val(*ptep) & _PAGE_HASHPTE) | + (pte_val(pte) & ~_PAGE_HASHPTE)); + } else if (IS_ENABLED(CONFIG_PTE_64BIT)) { + if (pte_val(*ptep) & _PAGE_HASHPTE) + flush_hash_entry(mm, ptep, addr); + + asm volatile("stw%X0 %2,%0; eieio; stw%X1 %L2,%1" : + "=m" (*ptep), "=m" (*((unsigned char *)ptep+4)) : + "r" (pte) : "memory"); + } else { + pte_update(mm, addr, ptep, ~_PAGE_HASHPTE, pte_val(pte), 0); } - if (pte_val(*ptep) & _PAGE_HASHPTE) - flush_hash_entry(mm, ptep, addr); - __asm__ __volatile__("\ - stw%U0%X0 %2,%0\n\ - eieio\n\ - stw%U0%X0 %L2,%1" - : "=m" (*ptep), "=m" (*((unsigned char *)ptep+4)) - : "r" (pte) : "memory"); - -#else - /* Third case is 32-bit hash table in UP mode, we need to preserve - * the _PAGE_HASHPTE bit since we may not have invalidated the previous - * translation in the hash yet (done in a subsequent flush_tlb_xxx()) - * and see we need to keep track that this PTE needs invalidating - */ - *ptep = __pte((pte_val(*ptep) & _PAGE_HASHPTE) - | (pte_val(pte) & ~_PAGE_HASHPTE)); -#endif } /* diff --git a/arch/powerpc/include/asm/book3s/32/tlbflush.h b/arch/powerpc/include/asm/book3s/32/tlbflush.h index 068085b709fb..e43534da5207 100644 --- a/arch/powerpc/include/asm/book3s/32/tlbflush.h +++ b/arch/powerpc/include/asm/book3s/32/tlbflush.h @@ -2,24 +2,90 @@ #ifndef _ASM_POWERPC_BOOK3S_32_TLBFLUSH_H #define _ASM_POWERPC_BOOK3S_32_TLBFLUSH_H +#include <linux/build_bug.h> + #define MMU_NO_CONTEXT (0) /* * TLB flushing for "classic" hash-MMU 32-bit CPUs, 6xx, 7xx, 7xxx */ -extern void flush_tlb_mm(struct mm_struct *mm); -extern void flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr); -extern void flush_tlb_page_nohash(struct vm_area_struct *vma, unsigned long addr); -extern void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, - unsigned long end); -extern void flush_tlb_kernel_range(unsigned long start, unsigned long end); +void hash__flush_tlb_mm(struct mm_struct *mm); +void hash__flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr); +void hash__flush_range(struct mm_struct *mm, unsigned long start, unsigned long end); + +#ifdef CONFIG_SMP +void _tlbie(unsigned long address); +#else +static inline void _tlbie(unsigned long address) +{ + asm volatile ("tlbie %0; sync" : : "r" (address) : "memory"); +} +#endif +void _tlbia(void); + +/* + * Called at the end of a mmu_gather operation to make sure the + * TLB flush is completely done. + */ +static inline void tlb_flush(struct mmu_gather *tlb) +{ + /* 603 needs to flush the whole TLB here since it doesn't use a hash table. */ + if (!mmu_has_feature(MMU_FTR_HPTE_TABLE)) + _tlbia(); +} + +static inline void flush_range(struct mm_struct *mm, unsigned long start, unsigned long end) +{ + start &= PAGE_MASK; + if (mmu_has_feature(MMU_FTR_HPTE_TABLE)) + hash__flush_range(mm, start, end); + else if (end - start <= PAGE_SIZE) + _tlbie(start); + else + _tlbia(); +} + +static inline void flush_tlb_mm(struct mm_struct *mm) +{ + if (mmu_has_feature(MMU_FTR_HPTE_TABLE)) + hash__flush_tlb_mm(mm); + else + _tlbia(); +} + +static inline void flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr) +{ + if (mmu_has_feature(MMU_FTR_HPTE_TABLE)) + hash__flush_tlb_page(vma, vmaddr); + else + _tlbie(vmaddr); +} + +static inline void +flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end) +{ + flush_range(vma->vm_mm, start, end); +} + +static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end) +{ + flush_range(&init_mm, start, end); +} + static inline void local_flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr) { flush_tlb_page(vma, vmaddr); } + +static inline void local_flush_tlb_page_psize(struct mm_struct *mm, + unsigned long vmaddr, int psize) +{ + flush_range(mm, vmaddr, vmaddr); +} + static inline void local_flush_tlb_mm(struct mm_struct *mm) { flush_tlb_mm(mm); } -#endif /* _ASM_POWERPC_TLBFLUSH_H */ +#endif /* _ASM_POWERPC_BOOK3S_32_TLBFLUSH_H */ diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h index 8fd8599c9395..6472b08fa1b0 100644 --- a/arch/powerpc/include/asm/book3s/64/hash-4k.h +++ b/arch/powerpc/include/asm/book3s/64/hash-4k.h @@ -13,20 +13,24 @@ */ #define MAX_EA_BITS_PER_CONTEXT 46 -#define REGION_SHIFT (MAX_EA_BITS_PER_CONTEXT - 2) /* - * Our page table limit us to 64TB. Hence for the kernel mapping, - * each MAP area is limited to 16 TB. - * The four map areas are: linear mapping, vmap, IO and vmemmap + * Our page table limit us to 64TB. For 64TB physical memory, we only need 64GB + * of vmemmap space. To better support sparse memory layout, we use 61TB + * linear map range, 1TB of vmalloc, 1TB of I/O and 1TB of vmememmap. */ +#define REGION_SHIFT (40) #define H_KERN_MAP_SIZE (ASM_CONST(1) << REGION_SHIFT) /* - * Define the address range of the kernel non-linear virtual area - * 16TB + * Limits the linear mapping range */ -#define H_KERN_VIRT_START ASM_CONST(0xc000100000000000) +#define H_MAX_PHYSMEM_BITS 46 + +/* + * Define the address range of the kernel non-linear virtual area (61TB) + */ +#define H_KERN_VIRT_START ASM_CONST(0xc0003d0000000000) #ifndef __ASSEMBLY__ #define H_PTE_TABLE_SIZE (sizeof(pte_t) << H_PTE_INDEX_SIZE) @@ -34,11 +38,11 @@ #define H_PUD_TABLE_SIZE (sizeof(pud_t) << H_PUD_INDEX_SIZE) #define H_PGD_TABLE_SIZE (sizeof(pgd_t) << H_PGD_INDEX_SIZE) -#define H_PAGE_F_GIX_SHIFT 53 -#define H_PAGE_F_SECOND _RPAGE_RPN44 /* HPTE is in 2ndary HPTEG */ -#define H_PAGE_F_GIX (_RPAGE_RPN43 | _RPAGE_RPN42 | _RPAGE_RPN41) -#define H_PAGE_BUSY _RPAGE_RSV1 /* software: PTE & hash are busy */ -#define H_PAGE_HASHPTE _RPAGE_RSV2 /* software: PTE & hash are busy */ +#define H_PAGE_F_GIX_SHIFT _PAGE_PA_MAX +#define H_PAGE_F_SECOND _RPAGE_PKEY_BIT0 /* HPTE is in 2ndary HPTEG */ +#define H_PAGE_F_GIX (_RPAGE_RPN43 | _RPAGE_RPN42 | _RPAGE_RPN41) +#define H_PAGE_BUSY _RPAGE_RSV1 +#define H_PAGE_HASHPTE _RPAGE_PKEY_BIT4 /* PTE flags to conserve for HPTE identification */ #define _PAGE_HPTEFLAGS (H_PAGE_BUSY | H_PAGE_HASHPTE | \ @@ -57,11 +61,12 @@ #define H_PMD_FRAG_NR (PAGE_SIZE >> H_PMD_FRAG_SIZE_SHIFT) /* memory key bits, only 8 keys supported */ -#define H_PTE_PKEY_BIT0 0 -#define H_PTE_PKEY_BIT1 0 -#define H_PTE_PKEY_BIT2 _RPAGE_RSV3 -#define H_PTE_PKEY_BIT3 _RPAGE_RSV4 -#define H_PTE_PKEY_BIT4 _RPAGE_RSV5 +#define H_PTE_PKEY_BIT4 0 +#define H_PTE_PKEY_BIT3 0 +#define H_PTE_PKEY_BIT2 _RPAGE_PKEY_BIT3 +#define H_PTE_PKEY_BIT1 _RPAGE_PKEY_BIT2 +#define H_PTE_PKEY_BIT0 _RPAGE_PKEY_BIT1 + /* * On all 4K setups, remap_4k_pfn() equates to remap_pfn_range() @@ -131,12 +136,6 @@ static inline int hash__pmd_trans_huge(pmd_t pmd) return 0; } -static inline int hash__pmd_same(pmd_t pmd_a, pmd_t pmd_b) -{ - BUG(); - return 0; -} - static inline pmd_t hash__pmd_mkhuge(pmd_t pmd) { BUG(); @@ -156,6 +155,12 @@ extern pmd_t hash__pmdp_huge_get_and_clear(struct mm_struct *mm, extern int hash__has_transparent_hugepage(void); #endif +static inline pmd_t hash__pmd_mkdevmap(pmd_t pmd) +{ + BUG(); + return pmd; +} + #endif /* !__ASSEMBLY__ */ #endif /* _ASM_POWERPC_BOOK3S_64_HASH_4K_H */ diff --git a/arch/powerpc/include/asm/book3s/64/hash-64k.h b/arch/powerpc/include/asm/book3s/64/hash-64k.h index d1d9177d9ebd..0bf6fd0bf42a 100644 --- a/arch/powerpc/include/asm/book3s/64/hash-64k.h +++ b/arch/powerpc/include/asm/book3s/64/hash-64k.h @@ -7,6 +7,19 @@ #define H_PUD_INDEX_SIZE 10 // size: 8B << 10 = 8KB, maps 2^10 x 16GB = 16TB #define H_PGD_INDEX_SIZE 8 // size: 8B << 8 = 2KB, maps 2^8 x 16TB = 4PB +/* + * If we store section details in page->flags we can't increase the MAX_PHYSMEM_BITS + * if we increase SECTIONS_WIDTH we will not store node details in page->flags and + * page_to_nid does a page->section->node lookup + * Hence only increase for VMEMMAP. Further depending on SPARSEMEM_EXTREME reduce + * memory requirements with large number of sections. + * 51 bits is the max physical real address on POWER9 + */ +#if defined(CONFIG_SPARSEMEM_VMEMMAP) && defined(CONFIG_SPARSEMEM_EXTREME) +#define H_MAX_PHYSMEM_BITS 51 +#else +#define H_MAX_PHYSMEM_BITS 46 +#endif /* * Each context is 512TB size. SLB miss for first context/default context @@ -32,15 +45,15 @@ */ #define H_PAGE_COMBO _RPAGE_RPN0 /* this is a combo 4k page */ #define H_PAGE_4K_PFN _RPAGE_RPN1 /* PFN is for a single 4k page */ -#define H_PAGE_BUSY _RPAGE_RPN44 /* software: PTE & hash are busy */ +#define H_PAGE_BUSY _RPAGE_RSV1 /* software: PTE & hash are busy */ #define H_PAGE_HASHPTE _RPAGE_RPN43 /* PTE has associated HPTE */ /* memory key bits. */ -#define H_PTE_PKEY_BIT0 _RPAGE_RSV1 -#define H_PTE_PKEY_BIT1 _RPAGE_RSV2 -#define H_PTE_PKEY_BIT2 _RPAGE_RSV3 -#define H_PTE_PKEY_BIT3 _RPAGE_RSV4 -#define H_PTE_PKEY_BIT4 _RPAGE_RSV5 +#define H_PTE_PKEY_BIT4 _RPAGE_PKEY_BIT4 +#define H_PTE_PKEY_BIT3 _RPAGE_PKEY_BIT3 +#define H_PTE_PKEY_BIT2 _RPAGE_PKEY_BIT2 +#define H_PTE_PKEY_BIT1 _RPAGE_PKEY_BIT1 +#define H_PTE_PKEY_BIT0 _RPAGE_PKEY_BIT0 /* * We need to differentiate between explicit huge page and THP huge @@ -246,15 +259,10 @@ static inline void mark_hpte_slot_valid(unsigned char *hpte_slot_array, */ static inline int hash__pmd_trans_huge(pmd_t pmd) { - return !!((pmd_val(pmd) & (_PAGE_PTE | H_PAGE_THP_HUGE)) == + return !!((pmd_val(pmd) & (_PAGE_PTE | H_PAGE_THP_HUGE | _PAGE_DEVMAP)) == (_PAGE_PTE | H_PAGE_THP_HUGE)); } -static inline int hash__pmd_same(pmd_t pmd_a, pmd_t pmd_b) -{ - return (((pmd_raw(pmd_a) ^ pmd_raw(pmd_b)) & ~cpu_to_be64(_PAGE_HPTEFLAGS)) == 0); -} - static inline pmd_t hash__pmd_mkhuge(pmd_t pmd) { return __pmd(pmd_val(pmd) | (_PAGE_PTE | H_PAGE_THP_HUGE)); @@ -272,6 +280,12 @@ extern pmd_t hash__pmdp_huge_get_and_clear(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp); extern int hash__has_transparent_hugepage(void); #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + +static inline pmd_t hash__pmd_mkdevmap(pmd_t pmd) +{ + return __pmd(pmd_val(pmd) | (_PAGE_PTE | H_PAGE_THP_HUGE | _PAGE_DEVMAP)); +} + #endif /* __ASSEMBLY__ */ #endif /* _ASM_POWERPC_BOOK3S_64_HASH_64K_H */ diff --git a/arch/powerpc/include/asm/book3s/64/hash-pkey.h b/arch/powerpc/include/asm/book3s/64/hash-pkey.h new file mode 100644 index 000000000000..6c5564c4fae4 --- /dev/null +++ b/arch/powerpc/include/asm/book3s/64/hash-pkey.h @@ -0,0 +1,45 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_POWERPC_BOOK3S_64_HASH_PKEY_H +#define _ASM_POWERPC_BOOK3S_64_HASH_PKEY_H + +/* We use key 3 for KERNEL */ +#define HASH_DEFAULT_KERNEL_KEY (HPTE_R_KEY_BIT0 | HPTE_R_KEY_BIT1) + +static inline u64 hash__vmflag_to_pte_pkey_bits(u64 vm_flags) +{ + return (((vm_flags & VM_PKEY_BIT0) ? H_PTE_PKEY_BIT0 : 0x0UL) | + ((vm_flags & VM_PKEY_BIT1) ? H_PTE_PKEY_BIT1 : 0x0UL) | + ((vm_flags & VM_PKEY_BIT2) ? H_PTE_PKEY_BIT2 : 0x0UL) | + ((vm_flags & VM_PKEY_BIT3) ? H_PTE_PKEY_BIT3 : 0x0UL) | + ((vm_flags & VM_PKEY_BIT4) ? H_PTE_PKEY_BIT4 : 0x0UL)); +} + +static inline u64 pte_to_hpte_pkey_bits(u64 pteflags, unsigned long flags) +{ + unsigned long pte_pkey; + + pte_pkey = (((pteflags & H_PTE_PKEY_BIT4) ? HPTE_R_KEY_BIT4 : 0x0UL) | + ((pteflags & H_PTE_PKEY_BIT3) ? HPTE_R_KEY_BIT3 : 0x0UL) | + ((pteflags & H_PTE_PKEY_BIT2) ? HPTE_R_KEY_BIT2 : 0x0UL) | + ((pteflags & H_PTE_PKEY_BIT1) ? HPTE_R_KEY_BIT1 : 0x0UL) | + ((pteflags & H_PTE_PKEY_BIT0) ? HPTE_R_KEY_BIT0 : 0x0UL)); + + if (mmu_has_feature(MMU_FTR_KUAP) || + mmu_has_feature(MMU_FTR_BOOK3S_KUEP)) { + if ((pte_pkey == 0) && (flags & HPTE_USE_KERNEL_KEY)) + return HASH_DEFAULT_KERNEL_KEY; + } + + return pte_pkey; +} + +static inline u16 hash__pte_to_pkey_bits(u64 pteflags) +{ + return (((pteflags & H_PTE_PKEY_BIT4) ? 0x10 : 0x0UL) | + ((pteflags & H_PTE_PKEY_BIT3) ? 0x8 : 0x0UL) | + ((pteflags & H_PTE_PKEY_BIT2) ? 0x4 : 0x0UL) | + ((pteflags & H_PTE_PKEY_BIT1) ? 0x2 : 0x0UL) | + ((pteflags & H_PTE_PKEY_BIT0) ? 0x1 : 0x0UL)); +} + +#endif diff --git a/arch/powerpc/include/asm/book3s/64/hash.h b/arch/powerpc/include/asm/book3s/64/hash.h index 2781ebf6add4..6e70ae511631 100644 --- a/arch/powerpc/include/asm/book3s/64/hash.h +++ b/arch/powerpc/include/asm/book3s/64/hash.h @@ -18,6 +18,10 @@ #include <asm/book3s/64/hash-4k.h> #endif +#define H_PTRS_PER_PTE (1 << H_PTE_INDEX_SIZE) +#define H_PTRS_PER_PMD (1 << H_PMD_INDEX_SIZE) +#define H_PTRS_PER_PUD (1 << H_PUD_INDEX_SIZE) + /* Bits to set in a PMD/PUD/PGD entry valid bit*/ #define HASH_PMD_VAL_BITS (0x8000000000000000UL) #define HASH_PUD_VAL_BITS (0x8000000000000000UL) @@ -99,10 +103,6 @@ * Defines the address of the vmemap area, in its own region on * hash table CPUs. */ -#ifdef CONFIG_PPC_MM_SLICES -#define HAVE_ARCH_UNMAPPED_AREA -#define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN -#endif /* CONFIG_PPC_MM_SLICES */ /* PTEIDX nibble */ #define _PTEIDX_SECONDARY 0x8 @@ -132,11 +132,25 @@ static inline int get_region_id(unsigned long ea) return region_id; } +static inline int hash__pmd_same(pmd_t pmd_a, pmd_t pmd_b) +{ + return (((pmd_raw(pmd_a) ^ pmd_raw(pmd_b)) & ~cpu_to_be64(_PAGE_HPTEFLAGS)) == 0); +} + #define hash__pmd_bad(pmd) (pmd_val(pmd) & H_PMD_BAD_BITS) + +/* + * pud comparison that will work with both pte and page table pointer. + */ +static inline int hash__pud_same(pud_t pud_a, pud_t pud_b) +{ + return (((pud_raw(pud_a) ^ pud_raw(pud_b)) & ~cpu_to_be64(_PAGE_HPTEFLAGS)) == 0); +} #define hash__pud_bad(pud) (pud_val(pud) & H_PUD_BAD_BITS) -static inline int hash__pgd_bad(pgd_t pgd) + +static inline int hash__p4d_bad(p4d_t p4d) { - return (pgd_val(pgd) == 0); + return (p4d_val(p4d) == 0); } #ifdef CONFIG_STRICT_KERNEL_RWX extern void hash__mark_rodata_ro(void); @@ -145,7 +159,7 @@ extern void hash__mark_initmem_nx(void); extern void hpte_need_flush(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned long pte, int huge); -extern unsigned long htab_convert_pte_flags(unsigned long pteflags); +unsigned long htab_convert_pte_flags(unsigned long pteflags, unsigned long flags); /* Atomic PTE updates */ static inline unsigned long hash__pte_update(struct mm_struct *mm, unsigned long addr, @@ -251,9 +265,12 @@ extern int __meminit hash__vmemmap_create_mapping(unsigned long start, extern void hash__vmemmap_remove_mapping(unsigned long start, unsigned long page_size); -int hash__create_section_mapping(unsigned long start, unsigned long end, int nid); +int hash__create_section_mapping(unsigned long start, unsigned long end, + int nid, pgprot_t prot); int hash__remove_section_mapping(unsigned long start, unsigned long end); +void hash__kernel_map_pages(struct page *page, int numpages, int enable); + #endif /* !__ASSEMBLY__ */ #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_BOOK3S_64_HASH_H */ diff --git a/arch/powerpc/include/asm/book3s/64/hugetlb.h b/arch/powerpc/include/asm/book3s/64/hugetlb.h index 12e150e615b7..aa1c67c8bfc8 100644 --- a/arch/powerpc/include/asm/book3s/64/hugetlb.h +++ b/arch/powerpc/include/asm/book3s/64/hugetlb.h @@ -1,6 +1,9 @@ /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_POWERPC_BOOK3S_64_HUGETLB_H #define _ASM_POWERPC_BOOK3S_64_HUGETLB_H + +#include <asm/firmware.h> + /* * For radix we want generic code to handle hugetlb. But then if we want * both hash and radix to be enabled together we need to workaround the @@ -8,10 +11,6 @@ */ void radix__flush_hugetlb_page(struct vm_area_struct *vma, unsigned long vmaddr); void radix__local_flush_hugetlb_page(struct vm_area_struct *vma, unsigned long vmaddr); -extern unsigned long -radix__hugetlb_get_unmapped_area(struct file *file, unsigned long addr, - unsigned long len, unsigned long pgoff, - unsigned long flags); extern void radix__huge_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, diff --git a/arch/powerpc/include/asm/book3s/64/kexec.h b/arch/powerpc/include/asm/book3s/64/kexec.h new file mode 100644 index 000000000000..df37a76c1e9f --- /dev/null +++ b/arch/powerpc/include/asm/book3s/64/kexec.h @@ -0,0 +1,33 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _ASM_POWERPC_BOOK3S_64_KEXEC_H_ +#define _ASM_POWERPC_BOOK3S_64_KEXEC_H_ + +#include <asm/plpar_wrappers.h> + +#define reset_sprs reset_sprs +static inline void reset_sprs(void) +{ + if (cpu_has_feature(CPU_FTR_ARCH_206)) { + mtspr(SPRN_AMR, 0); + mtspr(SPRN_UAMOR, 0); + } + + if (cpu_has_feature(CPU_FTR_ARCH_207S)) { + mtspr(SPRN_IAMR, 0); + if (cpu_has_feature(CPU_FTR_HVMODE)) + mtspr(SPRN_CIABR, 0); + else + plpar_set_ciabr(0); + } + + if (cpu_has_feature(CPU_FTR_ARCH_31)) { + mtspr(SPRN_DEXCR, 0); + mtspr(SPRN_HASHKEYR, 0); + } + + /* Do we need isync()? We are going via a kexec reset */ + isync(); +} + +#endif diff --git a/arch/powerpc/include/asm/book3s/64/kup-radix.h b/arch/powerpc/include/asm/book3s/64/kup-radix.h deleted file mode 100644 index f254de956d6a..000000000000 --- a/arch/powerpc/include/asm/book3s/64/kup-radix.h +++ /dev/null @@ -1,108 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ASM_POWERPC_BOOK3S_64_KUP_RADIX_H -#define _ASM_POWERPC_BOOK3S_64_KUP_RADIX_H - -#include <linux/const.h> - -#define AMR_KUAP_BLOCK_READ UL(0x4000000000000000) -#define AMR_KUAP_BLOCK_WRITE UL(0x8000000000000000) -#define AMR_KUAP_BLOCKED (AMR_KUAP_BLOCK_READ | AMR_KUAP_BLOCK_WRITE) -#define AMR_KUAP_SHIFT 62 - -#ifdef __ASSEMBLY__ - -.macro kuap_restore_amr gpr -#ifdef CONFIG_PPC_KUAP - BEGIN_MMU_FTR_SECTION_NESTED(67) - ld \gpr, STACK_REGS_KUAP(r1) - mtspr SPRN_AMR, \gpr - END_MMU_FTR_SECTION_NESTED_IFSET(MMU_FTR_RADIX_KUAP, 67) -#endif -.endm - -.macro kuap_check_amr gpr1, gpr2 -#ifdef CONFIG_PPC_KUAP_DEBUG - BEGIN_MMU_FTR_SECTION_NESTED(67) - mfspr \gpr1, SPRN_AMR - li \gpr2, (AMR_KUAP_BLOCKED >> AMR_KUAP_SHIFT) - sldi \gpr2, \gpr2, AMR_KUAP_SHIFT -999: tdne \gpr1, \gpr2 - EMIT_BUG_ENTRY 999b, __FILE__, __LINE__, (BUGFLAG_WARNING | BUGFLAG_ONCE) - END_MMU_FTR_SECTION_NESTED_IFSET(MMU_FTR_RADIX_KUAP, 67) -#endif -.endm - -.macro kuap_save_amr_and_lock gpr1, gpr2, use_cr, msr_pr_cr -#ifdef CONFIG_PPC_KUAP - BEGIN_MMU_FTR_SECTION_NESTED(67) - .ifnb \msr_pr_cr - bne \msr_pr_cr, 99f - .endif - mfspr \gpr1, SPRN_AMR - std \gpr1, STACK_REGS_KUAP(r1) - li \gpr2, (AMR_KUAP_BLOCKED >> AMR_KUAP_SHIFT) - sldi \gpr2, \gpr2, AMR_KUAP_SHIFT - cmpd \use_cr, \gpr1, \gpr2 - beq \use_cr, 99f - // We don't isync here because we very recently entered via rfid - mtspr SPRN_AMR, \gpr2 - isync -99: - END_MMU_FTR_SECTION_NESTED_IFSET(MMU_FTR_RADIX_KUAP, 67) -#endif -.endm - -#else /* !__ASSEMBLY__ */ - -#ifdef CONFIG_PPC_KUAP - -#include <asm/reg.h> - -/* - * We support individually allowing read or write, but we don't support nesting - * because that would require an expensive read/modify write of the AMR. - */ - -static inline void set_kuap(unsigned long value) -{ - if (!early_mmu_has_feature(MMU_FTR_RADIX_KUAP)) - return; - - /* - * ISA v3.0B says we need a CSI (Context Synchronising Instruction) both - * before and after the move to AMR. See table 6 on page 1134. - */ - isync(); - mtspr(SPRN_AMR, value); - isync(); -} - -static inline void allow_user_access(void __user *to, const void __user *from, - unsigned long size) -{ - // This is written so we can resolve to a single case at build time - if (__builtin_constant_p(to) && to == NULL) - set_kuap(AMR_KUAP_BLOCK_WRITE); - else if (__builtin_constant_p(from) && from == NULL) - set_kuap(AMR_KUAP_BLOCK_READ); - else - set_kuap(0); -} - -static inline void prevent_user_access(void __user *to, const void __user *from, - unsigned long size) -{ - set_kuap(AMR_KUAP_BLOCKED); -} - -static inline bool bad_kuap_fault(struct pt_regs *regs, bool is_write) -{ - return WARN(mmu_has_feature(MMU_FTR_RADIX_KUAP) && - (regs->kuap & (is_write ? AMR_KUAP_BLOCK_WRITE : AMR_KUAP_BLOCK_READ)), - "Bug: %s fault blocked by AMR!", is_write ? "Write" : "Read"); -} -#endif /* CONFIG_PPC_KUAP */ - -#endif /* __ASSEMBLY__ */ - -#endif /* _ASM_POWERPC_BOOK3S_64_KUP_RADIX_H */ diff --git a/arch/powerpc/include/asm/book3s/64/kup.h b/arch/powerpc/include/asm/book3s/64/kup.h new file mode 100644 index 000000000000..497a7bd31ecc --- /dev/null +++ b/arch/powerpc/include/asm/book3s/64/kup.h @@ -0,0 +1,418 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_POWERPC_BOOK3S_64_KUP_H +#define _ASM_POWERPC_BOOK3S_64_KUP_H + +#include <linux/const.h> +#include <asm/reg.h> + +#define AMR_KUAP_BLOCK_READ UL(0x5455555555555555) +#define AMR_KUAP_BLOCK_WRITE UL(0xa8aaaaaaaaaaaaaa) +#define AMR_KUEP_BLOCKED UL(0x5455555555555555) +#define AMR_KUAP_BLOCKED (AMR_KUAP_BLOCK_READ | AMR_KUAP_BLOCK_WRITE) + +#ifdef __ASSEMBLY__ + +.macro kuap_user_restore gpr1, gpr2 +#if defined(CONFIG_PPC_PKEY) + BEGIN_MMU_FTR_SECTION_NESTED(67) + b 100f // skip_restore_amr + END_MMU_FTR_SECTION_NESTED_IFCLR(MMU_FTR_PKEY, 67) + /* + * AMR and IAMR are going to be different when + * returning to userspace. + */ + ld \gpr1, STACK_REGS_AMR(r1) + + /* + * If kuap feature is not enabled, do the mtspr + * only if AMR value is different. + */ + BEGIN_MMU_FTR_SECTION_NESTED(68) + mfspr \gpr2, SPRN_AMR + cmpd \gpr1, \gpr2 + beq 99f + END_MMU_FTR_SECTION_NESTED_IFCLR(MMU_FTR_KUAP, 68) + + isync + mtspr SPRN_AMR, \gpr1 +99: + /* + * Restore IAMR only when returning to userspace + */ + ld \gpr1, STACK_REGS_IAMR(r1) + + /* + * If kuep feature is not enabled, do the mtspr + * only if IAMR value is different. + */ + BEGIN_MMU_FTR_SECTION_NESTED(69) + mfspr \gpr2, SPRN_IAMR + cmpd \gpr1, \gpr2 + beq 100f + END_MMU_FTR_SECTION_NESTED_IFCLR(MMU_FTR_BOOK3S_KUEP, 69) + + isync + mtspr SPRN_IAMR, \gpr1 + +100: //skip_restore_amr + /* No isync required, see kuap_user_restore() */ +#endif +.endm + +.macro kuap_kernel_restore gpr1, gpr2 +#if defined(CONFIG_PPC_PKEY) + + BEGIN_MMU_FTR_SECTION_NESTED(67) + /* + * AMR is going to be mostly the same since we are + * returning to the kernel. Compare and do a mtspr. + */ + ld \gpr2, STACK_REGS_AMR(r1) + mfspr \gpr1, SPRN_AMR + cmpd \gpr1, \gpr2 + beq 100f + isync + mtspr SPRN_AMR, \gpr2 + /* + * No isync required, see kuap_restore_amr() + * No need to restore IAMR when returning to kernel space. + */ +100: + END_MMU_FTR_SECTION_NESTED_IFSET(MMU_FTR_KUAP, 67) +#endif +.endm + +#ifdef CONFIG_PPC_KUAP +.macro kuap_check_amr gpr1, gpr2 +#ifdef CONFIG_PPC_KUAP_DEBUG + BEGIN_MMU_FTR_SECTION_NESTED(67) + mfspr \gpr1, SPRN_AMR + /* Prevent access to userspace using any key values */ + LOAD_REG_IMMEDIATE(\gpr2, AMR_KUAP_BLOCKED) +999: tdne \gpr1, \gpr2 + EMIT_WARN_ENTRY 999b, __FILE__, __LINE__, (BUGFLAG_WARNING | BUGFLAG_ONCE) + END_MMU_FTR_SECTION_NESTED_IFSET(MMU_FTR_KUAP, 67) +#endif +.endm +#endif + +/* + * if (pkey) { + * + * save AMR -> stack; + * if (kuap) { + * if (AMR != BLOCKED) + * KUAP_BLOCKED -> AMR; + * } + * if (from_user) { + * save IAMR -> stack; + * if (kuep) { + * KUEP_BLOCKED ->IAMR + * } + * } + * return; + * } + * + * if (kuap) { + * if (from_kernel) { + * save AMR -> stack; + * if (AMR != BLOCKED) + * KUAP_BLOCKED -> AMR; + * } + * + * } + */ +.macro kuap_save_amr_and_lock gpr1, gpr2, use_cr, msr_pr_cr +#if defined(CONFIG_PPC_PKEY) + + /* + * if both pkey and kuap is disabled, nothing to do + */ + BEGIN_MMU_FTR_SECTION_NESTED(68) + b 100f // skip_save_amr + END_MMU_FTR_SECTION_NESTED_IFCLR(MMU_FTR_PKEY | MMU_FTR_KUAP, 68) + + /* + * if pkey is disabled and we are entering from userspace + * don't do anything. + */ + BEGIN_MMU_FTR_SECTION_NESTED(67) + .ifnb \msr_pr_cr + /* + * Without pkey we are not changing AMR outside the kernel + * hence skip this completely. + */ + bne \msr_pr_cr, 100f // from userspace + .endif + END_MMU_FTR_SECTION_NESTED_IFCLR(MMU_FTR_PKEY, 67) + + /* + * pkey is enabled or pkey is disabled but entering from kernel + */ + mfspr \gpr1, SPRN_AMR + std \gpr1, STACK_REGS_AMR(r1) + + /* + * update kernel AMR with AMR_KUAP_BLOCKED only + * if KUAP feature is enabled + */ + BEGIN_MMU_FTR_SECTION_NESTED(69) + LOAD_REG_IMMEDIATE(\gpr2, AMR_KUAP_BLOCKED) + cmpd \use_cr, \gpr1, \gpr2 + beq \use_cr, 102f + /* + * We don't isync here because we very recently entered via an interrupt + */ + mtspr SPRN_AMR, \gpr2 + isync +102: + END_MMU_FTR_SECTION_NESTED_IFSET(MMU_FTR_KUAP, 69) + + /* + * if entering from kernel we don't need save IAMR + */ + .ifnb \msr_pr_cr + beq \msr_pr_cr, 100f // from kernel space + mfspr \gpr1, SPRN_IAMR + std \gpr1, STACK_REGS_IAMR(r1) + + /* + * update kernel IAMR with AMR_KUEP_BLOCKED only + * if KUEP feature is enabled + */ + BEGIN_MMU_FTR_SECTION_NESTED(70) + LOAD_REG_IMMEDIATE(\gpr2, AMR_KUEP_BLOCKED) + mtspr SPRN_IAMR, \gpr2 + isync + END_MMU_FTR_SECTION_NESTED_IFSET(MMU_FTR_BOOK3S_KUEP, 70) + .endif + +100: // skip_save_amr +#endif +.endm + +#else /* !__ASSEMBLY__ */ + +#include <linux/jump_label.h> +#include <linux/sched.h> + +DECLARE_STATIC_KEY_FALSE(uaccess_flush_key); + +#ifdef CONFIG_PPC_PKEY + +extern u64 __ro_after_init default_uamor; +extern u64 __ro_after_init default_amr; +extern u64 __ro_after_init default_iamr; + +#include <asm/mmu.h> +#include <asm/ptrace.h> + +/* usage of kthread_use_mm() should inherit the + * AMR value of the operating address space. But, the AMR value is + * thread-specific and we inherit the address space and not thread + * access restrictions. Because of this ignore AMR value when accessing + * userspace via kernel thread. + */ +static __always_inline u64 current_thread_amr(void) +{ + if (current->thread.regs) + return current->thread.regs->amr; + return default_amr; +} + +static __always_inline u64 current_thread_iamr(void) +{ + if (current->thread.regs) + return current->thread.regs->iamr; + return default_iamr; +} +#endif /* CONFIG_PPC_PKEY */ + +#ifdef CONFIG_PPC_KUAP + +static __always_inline void kuap_user_restore(struct pt_regs *regs) +{ + bool restore_amr = false, restore_iamr = false; + unsigned long amr, iamr; + + if (!mmu_has_feature(MMU_FTR_PKEY)) + return; + + if (!mmu_has_feature(MMU_FTR_KUAP)) { + amr = mfspr(SPRN_AMR); + if (amr != regs->amr) + restore_amr = true; + } else { + restore_amr = true; + } + + if (!mmu_has_feature(MMU_FTR_BOOK3S_KUEP)) { + iamr = mfspr(SPRN_IAMR); + if (iamr != regs->iamr) + restore_iamr = true; + } else { + restore_iamr = true; + } + + + if (restore_amr || restore_iamr) { + isync(); + if (restore_amr) + mtspr(SPRN_AMR, regs->amr); + if (restore_iamr) + mtspr(SPRN_IAMR, regs->iamr); + } + /* + * No isync required here because we are about to rfi + * back to previous context before any user accesses + * would be made, which is a CSI. + */ +} + +static __always_inline void __kuap_kernel_restore(struct pt_regs *regs, unsigned long amr) +{ + if (likely(regs->amr == amr)) + return; + + isync(); + mtspr(SPRN_AMR, regs->amr); + /* + * No isync required here because we are about to rfi + * back to previous context before any user accesses + * would be made, which is a CSI. + * + * No need to restore IAMR when returning to kernel space. + */ +} + +static __always_inline unsigned long __kuap_get_and_assert_locked(void) +{ + unsigned long amr = mfspr(SPRN_AMR); + + if (IS_ENABLED(CONFIG_PPC_KUAP_DEBUG)) /* kuap_check_amr() */ + WARN_ON_ONCE(amr != AMR_KUAP_BLOCKED); + return amr; +} +#define __kuap_get_and_assert_locked __kuap_get_and_assert_locked + +/* __kuap_lock() not required, book3s/64 does that in ASM */ + +/* + * We support individually allowing read or write, but we don't support nesting + * because that would require an expensive read/modify write of the AMR. + */ + +static __always_inline unsigned long get_kuap(void) +{ + /* + * We return AMR_KUAP_BLOCKED when we don't support KUAP because + * prevent_user_access_return needs to return AMR_KUAP_BLOCKED to + * cause restore_user_access to do a flush. + * + * This has no effect in terms of actually blocking things on hash, + * so it doesn't break anything. + */ + if (!mmu_has_feature(MMU_FTR_KUAP)) + return AMR_KUAP_BLOCKED; + + return mfspr(SPRN_AMR); +} + +static __always_inline void set_kuap(unsigned long value) +{ + if (!mmu_has_feature(MMU_FTR_KUAP)) + return; + + /* + * ISA v3.0B says we need a CSI (Context Synchronising Instruction) both + * before and after the move to AMR. See table 6 on page 1134. + */ + isync(); + mtspr(SPRN_AMR, value); + isync(); +} + +static __always_inline bool +__bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write) +{ + /* + * For radix this will be a storage protection fault (DSISR_PROTFAULT). + * For hash this will be a key fault (DSISR_KEYFAULT) + */ + /* + * We do have exception table entry, but accessing the + * userspace results in fault. This could be because we + * didn't unlock the AMR or access is denied by userspace + * using a key value that blocks access. We are only interested + * in catching the use case of accessing without unlocking + * the AMR. Hence check for BLOCK_WRITE/READ against AMR. + */ + if (is_write) { + return (regs->amr & AMR_KUAP_BLOCK_WRITE) == AMR_KUAP_BLOCK_WRITE; + } + return (regs->amr & AMR_KUAP_BLOCK_READ) == AMR_KUAP_BLOCK_READ; +} + +static __always_inline void allow_user_access(void __user *to, const void __user *from, + unsigned long size, unsigned long dir) +{ + unsigned long thread_amr = 0; + + // This is written so we can resolve to a single case at build time + BUILD_BUG_ON(!__builtin_constant_p(dir)); + + if (mmu_has_feature(MMU_FTR_PKEY)) + thread_amr = current_thread_amr(); + + if (dir == KUAP_READ) + set_kuap(thread_amr | AMR_KUAP_BLOCK_WRITE); + else if (dir == KUAP_WRITE) + set_kuap(thread_amr | AMR_KUAP_BLOCK_READ); + else if (dir == KUAP_READ_WRITE) + set_kuap(thread_amr); + else + BUILD_BUG(); +} + +#else /* CONFIG_PPC_KUAP */ + +static __always_inline unsigned long get_kuap(void) +{ + return AMR_KUAP_BLOCKED; +} + +static __always_inline void set_kuap(unsigned long value) { } + +static __always_inline void allow_user_access(void __user *to, const void __user *from, + unsigned long size, unsigned long dir) +{ } + +#endif /* !CONFIG_PPC_KUAP */ + +static __always_inline void prevent_user_access(unsigned long dir) +{ + set_kuap(AMR_KUAP_BLOCKED); + if (static_branch_unlikely(&uaccess_flush_key)) + do_uaccess_flush(); +} + +static __always_inline unsigned long prevent_user_access_return(void) +{ + unsigned long flags = get_kuap(); + + set_kuap(AMR_KUAP_BLOCKED); + if (static_branch_unlikely(&uaccess_flush_key)) + do_uaccess_flush(); + + return flags; +} + +static __always_inline void restore_user_access(unsigned long flags) +{ + set_kuap(flags); + if (static_branch_unlikely(&uaccess_flush_key) && flags == AMR_KUAP_BLOCKED) + do_uaccess_flush(); +} +#endif /* __ASSEMBLY__ */ + +#endif /* _ASM_POWERPC_BOOK3S_64_KUP_H */ diff --git a/arch/powerpc/include/asm/book3s/64/mmu-hash.h b/arch/powerpc/include/asm/book3s/64/mmu-hash.h index 15b75005bc34..1c4eebbc69c9 100644 --- a/arch/powerpc/include/asm/book3s/64/mmu-hash.h +++ b/arch/powerpc/include/asm/book3s/64/mmu-hash.h @@ -18,7 +18,7 @@ * complete pgtable.h but only a portion of it. */ #include <asm/book3s/64/pgtable.h> -#include <asm/bug.h> +#include <asm/book3s/64/slice.h> #include <asm/task_size_64.h> #include <asm/cpu_has_feature.h> @@ -86,8 +86,8 @@ #define HPTE_R_PP0 ASM_CONST(0x8000000000000000) #define HPTE_R_TS ASM_CONST(0x4000000000000000) #define HPTE_R_KEY_HI ASM_CONST(0x3000000000000000) -#define HPTE_R_KEY_BIT0 ASM_CONST(0x2000000000000000) -#define HPTE_R_KEY_BIT1 ASM_CONST(0x1000000000000000) +#define HPTE_R_KEY_BIT4 ASM_CONST(0x2000000000000000) +#define HPTE_R_KEY_BIT3 ASM_CONST(0x1000000000000000) #define HPTE_R_RPN_SHIFT 12 #define HPTE_R_RPN ASM_CONST(0x0ffffffffffff000) #define HPTE_R_RPN_3_0 ASM_CONST(0x01fffffffffff000) @@ -103,8 +103,8 @@ #define HPTE_R_R ASM_CONST(0x0000000000000100) #define HPTE_R_KEY_LO ASM_CONST(0x0000000000000e00) #define HPTE_R_KEY_BIT2 ASM_CONST(0x0000000000000800) -#define HPTE_R_KEY_BIT3 ASM_CONST(0x0000000000000400) -#define HPTE_R_KEY_BIT4 ASM_CONST(0x0000000000000200) +#define HPTE_R_KEY_BIT1 ASM_CONST(0x0000000000000400) +#define HPTE_R_KEY_BIT0 ASM_CONST(0x0000000000000200) #define HPTE_R_KEY (HPTE_R_KEY_LO | HPTE_R_KEY_HI) #define HPTE_V_1TB_SEG ASM_CONST(0x4000000000000000) @@ -452,7 +452,10 @@ static inline unsigned long hpt_hash(unsigned long vpn, #define HPTE_LOCAL_UPDATE 0x1 #define HPTE_NOHPTE_UPDATE 0x2 +#define HPTE_USE_KERNEL_KEY 0x4 +long hpte_insert_repeating(unsigned long hash, unsigned long vpn, unsigned long pa, + unsigned long rlags, unsigned long vflags, int psize, int ssize); extern int __hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid, pte_t *ptep, unsigned long trap, unsigned long flags, int ssize, int subpage_prot); @@ -466,6 +469,8 @@ extern int hash_page_mm(struct mm_struct *mm, unsigned long ea, unsigned long flags); extern int hash_page(unsigned long ea, unsigned long access, unsigned long trap, unsigned long dsisr); +void low_hash_fault(struct pt_regs *regs, unsigned long address, int rc); +int __hash_page(unsigned long trap, unsigned long ea, unsigned long dsisr, unsigned long msr); int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid, pte_t *ptep, unsigned long trap, unsigned long flags, int ssize, unsigned int shift, unsigned int mmu_psize); @@ -519,7 +524,14 @@ void slb_save_contents(struct slb_entry *slb_ptr); void slb_dump_contents(struct slb_entry *slb_ptr); extern void slb_vmalloc_update(void); -extern void slb_set_size(u16 size); +void preload_new_slb_context(unsigned long start, unsigned long sp); + +#ifdef CONFIG_PPC_64S_HASH_MMU +void slb_set_size(u16 size); +#else +static inline void slb_set_size(u16 size) { } +#endif + #endif /* __ASSEMBLY__ */ /* @@ -577,8 +589,8 @@ extern void slb_set_size(u16 size); * For vmalloc and memmap, we use just one context with 512TB. With 64 byte * struct page size, we need ony 32 TB in memmap for 2PB (51 bits (MAX_PHYSMEM_BITS)). */ -#if (MAX_PHYSMEM_BITS > MAX_EA_BITS_PER_CONTEXT) -#define MAX_KERNEL_CTX_CNT (1UL << (MAX_PHYSMEM_BITS - MAX_EA_BITS_PER_CONTEXT)) +#if (H_MAX_PHYSMEM_BITS > MAX_EA_BITS_PER_CONTEXT) +#define MAX_KERNEL_CTX_CNT (1UL << (H_MAX_PHYSMEM_BITS - MAX_EA_BITS_PER_CONTEXT)) #else #define MAX_KERNEL_CTX_CNT 1 #endif @@ -600,8 +612,11 @@ extern void slb_set_size(u16 size); * */ #define MAX_USER_CONTEXT ((ASM_CONST(1) << CONTEXT_BITS) - 2) + +// The + 2 accounts for INVALID_REGION and 1 more to avoid overlap with kernel #define MIN_USER_CONTEXT (MAX_KERNEL_CTX_CNT + MAX_VMALLOC_CTX_CNT + \ - MAX_IO_CTX_CNT + MAX_VMEMMAP_CTX_CNT) + MAX_IO_CTX_CNT + MAX_VMEMMAP_CTX_CNT + 2) + /* * For platforms that support on 65bit VA we limit the context bits */ @@ -790,7 +805,7 @@ static inline unsigned long get_vsid(unsigned long context, unsigned long ea, } /* - * For kernel space, we use context ids as below + * For kernel space, we use context ids as * below. Range is 512TB per context. * * 0x00001 - [ 0xc000000000000000 - 0xc001ffffffffffff] @@ -839,6 +854,32 @@ static inline unsigned long get_kernel_vsid(unsigned long ea, int ssize) unsigned htab_shift_for_mem_size(unsigned long mem_size); -#endif /* __ASSEMBLY__ */ +enum slb_index { + LINEAR_INDEX = 0, /* Kernel linear map (0xc000000000000000) */ + KSTACK_INDEX = 1, /* Kernel stack map */ +}; + +#define slb_esid_mask(ssize) \ + (((ssize) == MMU_SEGSIZE_256M) ? ESID_MASK : ESID_MASK_1T) +static inline unsigned long mk_esid_data(unsigned long ea, int ssize, + enum slb_index index) +{ + return (ea & slb_esid_mask(ssize)) | SLB_ESID_V | index; +} + +static inline unsigned long __mk_vsid_data(unsigned long vsid, int ssize, + unsigned long flags) +{ + return (vsid << slb_vsid_shift(ssize)) | flags | + ((unsigned long)ssize << SLB_VSID_SSIZE_SHIFT); +} + +static inline unsigned long mk_vsid_data(unsigned long ea, int ssize, + unsigned long flags) +{ + return __mk_vsid_data(get_kernel_vsid(ea, ssize), ssize, flags); +} + +#endif /* __ASSEMBLY__ */ #endif /* _ASM_POWERPC_BOOK3S_64_MMU_HASH_H_ */ diff --git a/arch/powerpc/include/asm/book3s/64/mmu.h b/arch/powerpc/include/asm/book3s/64/mmu.h index bb3deb76c951..fedbc5d38191 100644 --- a/arch/powerpc/include/asm/book3s/64/mmu.h +++ b/arch/powerpc/include/asm/book3s/64/mmu.h @@ -19,6 +19,7 @@ struct mmu_psize_def { int penc[MMU_PAGE_COUNT]; /* HPTE encoding */ unsigned int tlbiel; /* tlbiel supported for that page size */ unsigned long avpnm; /* bits to mask out in AVPN in the HPTE */ + unsigned long h_rpt_pgsize; /* H_RPT_INVALIDATE page size encoding */ union { unsigned long sllp; /* SLB L||LP (exact mask to use in slbmte) */ unsigned long ap; /* Ap encoding used by PowerISA 3.0 */ @@ -27,21 +28,6 @@ struct mmu_psize_def { extern struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT]; #endif /* __ASSEMBLY__ */ -/* - * If we store section details in page->flags we can't increase the MAX_PHYSMEM_BITS - * if we increase SECTIONS_WIDTH we will not store node details in page->flags and - * page_to_nid does a page->section->node lookup - * Hence only increase for VMEMMAP. Further depending on SPARSEMEM_EXTREME reduce - * memory requirements with large number of sections. - * 51 bits is the max physical real address on POWER9 - */ -#if defined(CONFIG_SPARSEMEM_VMEMMAP) && defined(CONFIG_SPARSEMEM_EXTREME) && \ - defined(CONFIG_PPC_64K_PAGES) -#define MAX_PHYSMEM_BITS 51 -#else -#define MAX_PHYSMEM_BITS 46 -#endif - /* 64-bit classic hash table MMU */ #include <asm/book3s/64/mmu-hash.h> @@ -76,19 +62,22 @@ extern struct patb_entry *partition_tb; #define PRTS_MASK 0x1f /* process table size field */ #define PRTB_MASK 0x0ffffffffffff000UL +/* Number of supported LPID bits */ +extern unsigned int mmu_lpid_bits; + /* Number of supported PID bits */ extern unsigned int mmu_pid_bits; /* Base PID to allocate from */ extern unsigned int mmu_base_pid; +extern unsigned long __ro_after_init memory_block_size; + #define PRTB_SIZE_SHIFT (mmu_pid_bits + 4) #define PRTB_ENTRIES (1ul << mmu_pid_bits) -/* - * Power9 currently only support 64K partition table size. - */ -#define PATB_SIZE_SHIFT 16 +#define PATB_SIZE_SHIFT (mmu_lpid_bits + 4) +#define PATB_ENTRIES (1ul << mmu_lpid_bits) typedef unsigned long mm_context_id_t; struct spinlock; @@ -107,7 +96,9 @@ typedef struct { * from EA and new context ids to build the new VAs. */ mm_context_id_t id; +#ifdef CONFIG_PPC_64S_HASH_MMU mm_context_id_t extended_id[TASK_SIZE_USER64/TASK_CONTEXT_SIZE]; +#endif }; /* Number of bits in the mm_cpumask */ @@ -116,9 +107,14 @@ typedef struct { /* Number of users of the external (Nest) MMU */ atomic_t copros; + /* Number of user space windows opened in process mm_context */ + atomic_t vas_windows; + +#ifdef CONFIG_PPC_64S_HASH_MMU struct hash_mm_context *hash_context; +#endif - unsigned long vdso_base; + void __user *vdso; /* * pagetable fragment support */ @@ -139,6 +135,7 @@ typedef struct { #endif } mm_context_t; +#ifdef CONFIG_PPC_64S_HASH_MMU static inline u16 mm_ctx_user_psize(mm_context_t *ctx) { return ctx->hash_context->user_psize; @@ -196,19 +193,32 @@ static inline struct subpage_prot_table *mm_ctx_subpage_prot(mm_context_t *ctx) /* * The current system page and segment sizes */ -extern int mmu_linear_psize; extern int mmu_virtual_psize; extern int mmu_vmalloc_psize; -extern int mmu_vmemmap_psize; extern int mmu_io_psize; +#else /* CONFIG_PPC_64S_HASH_MMU */ +#ifdef CONFIG_PPC_64K_PAGES +#define mmu_virtual_psize MMU_PAGE_64K +#else +#define mmu_virtual_psize MMU_PAGE_4K +#endif +#endif +extern int mmu_linear_psize; +extern int mmu_vmemmap_psize; /* MMU initialization */ void mmu_early_init_devtree(void); void hash__early_init_devtree(void); void radix__early_init_devtree(void); +#ifdef CONFIG_PPC_PKEY +void pkey_early_init_devtree(void); +#else +static inline void pkey_early_init_devtree(void) {} +#endif + extern void hash__early_init_mmu(void); extern void radix__early_init_mmu(void); -static inline void early_init_mmu(void) +static inline void __init early_init_mmu(void) { if (radix_enabled()) return radix__early_init_mmu(); @@ -225,24 +235,38 @@ static inline void early_init_mmu_secondary(void) extern void hash__setup_initial_memory_limit(phys_addr_t first_memblock_base, phys_addr_t first_memblock_size); -extern void radix__setup_initial_memory_limit(phys_addr_t first_memblock_base, - phys_addr_t first_memblock_size); static inline void setup_initial_memory_limit(phys_addr_t first_memblock_base, phys_addr_t first_memblock_size) { - if (early_radix_enabled()) - return radix__setup_initial_memory_limit(first_memblock_base, - first_memblock_size); - return hash__setup_initial_memory_limit(first_memblock_base, - first_memblock_size); + /* + * Hash has more strict restrictions. At this point we don't + * know which translations we will pick. Hence go with hash + * restrictions. + */ + if (!early_radix_enabled()) + hash__setup_initial_memory_limit(first_memblock_base, + first_memblock_size); } #ifdef CONFIG_PPC_PSERIES -extern void radix_init_pseries(void); +void __init radix_init_pseries(void); #else -static inline void radix_init_pseries(void) { }; +static inline void radix_init_pseries(void) { } #endif +#ifdef CONFIG_HOTPLUG_CPU +#define arch_clear_mm_cpumask_cpu(cpu, mm) \ + do { \ + if (cpumask_test_cpu(cpu, mm_cpumask(mm))) { \ + dec_mm_active_cpus(mm); \ + cpumask_clear_cpu(cpu, mm_cpumask(mm)); \ + } \ + } while (0) + +void cleanup_cpu_mmu_context(void); +#endif + +#ifdef CONFIG_PPC_64S_HASH_MMU static inline int get_user_context(mm_context_t *ctx, unsigned long ea) { int index = ea >> MAX_EA_BITS_PER_CONTEXT; @@ -262,6 +286,7 @@ static inline unsigned long get_user_vsid(mm_context_t *ctx, return get_vsid(context, ea, ssize); } +#endif #endif /* __ASSEMBLY__ */ #endif /* _ASM_POWERPC_BOOK3S_64_MMU_H_ */ diff --git a/arch/powerpc/include/asm/book3s/64/pgalloc.h b/arch/powerpc/include/asm/book3s/64/pgalloc.h index f6968c811026..dd2cff53a111 100644 --- a/arch/powerpc/include/asm/book3s/64/pgalloc.h +++ b/arch/powerpc/include/asm/book3s/64/pgalloc.h @@ -19,9 +19,7 @@ extern struct vmemmap_backing *vmemmap_list; extern pmd_t *pmd_fragment_alloc(struct mm_struct *, unsigned long); extern void pmd_fragment_free(unsigned long *); extern void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift); -#ifdef CONFIG_SMP extern void __tlb_remove_table(void *_table); -#endif void pte_frag_destroy(void *pte_frag); static inline pgd_t *radix__pgd_alloc(struct mm_struct *mm) @@ -87,9 +85,9 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) kmem_cache_free(PGT_CACHE(PGD_INDEX_SIZE), pgd); } -static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *pud) +static inline void p4d_populate(struct mm_struct *mm, p4d_t *pgd, pud_t *pud) { - *pgd = __pgd(__pgtable_ptr_val(pud) | PGD_VAL_BITS); + *pgd = __p4d(__pgtable_ptr_val(pud) | PGD_VAL_BITS); } static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr) @@ -109,9 +107,25 @@ static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr) return pud; } +static inline void __pud_free(pud_t *pud) +{ + struct page *page = virt_to_page(pud); + + /* + * Early pud pages allocated via memblock allocator + * can't be directly freed to slab. KFENCE pages have + * both reserved and slab flags set so need to be freed + * kmem_cache_free. + */ + if (PageReserved(page) && !PageSlab(page)) + free_reserved_page(page); + else + kmem_cache_free(PGT_CACHE(PUD_CACHE_INDEX), pud); +} + static inline void pud_free(struct mm_struct *mm, pud_t *pud) { - kmem_cache_free(PGT_CACHE(PUD_CACHE_INDEX), pud); + return __pud_free(pud); } static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) diff --git a/arch/powerpc/include/asm/book3s/64/pgtable-4k.h b/arch/powerpc/include/asm/book3s/64/pgtable-4k.h index 4e697bc2f4cd..48f21820afe2 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable-4k.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable-4k.h @@ -26,16 +26,6 @@ static inline int pud_huge(pud_t pud) return 0; } -static inline int pgd_huge(pgd_t pgd) -{ - /* - * leaf pte for huge page - */ - if (radix_enabled()) - return !!(pgd_raw(pgd) & cpu_to_be64(_PAGE_PTE)); - return 0; -} -#define pgd_huge pgd_huge /* * With radix , we have hugepage ptes in the pud and pmd entries. We don't * need to setup hugepage directory for them. Our pte and page directory format diff --git a/arch/powerpc/include/asm/book3s/64/pgtable-64k.h b/arch/powerpc/include/asm/book3s/64/pgtable-64k.h index 34d1018896b3..2fce3498b000 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable-64k.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable-64k.h @@ -30,15 +30,6 @@ static inline int pud_huge(pud_t pud) return !!(pud_raw(pud) & cpu_to_be64(_PAGE_PTE)); } -static inline int pgd_huge(pgd_t pgd) -{ - /* - * leaf pte for huge page - */ - return !!(pgd_raw(pgd) & cpu_to_be64(_PAGE_PTE)); -} -#define pgd_huge pgd_huge - /* * With 64k page size, we have hugepage ptes in the pgd and pmd entries. We don't * need to setup hugepage directory for them. Our pte and page directory format diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index b01624e5c467..927d585652bc 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -2,23 +2,21 @@ #ifndef _ASM_POWERPC_BOOK3S_64_PGTABLE_H_ #define _ASM_POWERPC_BOOK3S_64_PGTABLE_H_ -#include <asm-generic/5level-fixup.h> +#include <asm-generic/pgtable-nop4d.h> #ifndef __ASSEMBLY__ #include <linux/mmdebug.h> #include <linux/bug.h> +#include <linux/sizes.h> #endif /* * Common bits between hash and Radix page table */ -#define _PAGE_BIT_SWAP_TYPE 0 #define _PAGE_EXEC 0x00001 /* execute permission */ #define _PAGE_WRITE 0x00002 /* write access allowed */ #define _PAGE_READ 0x00004 /* read access allowed */ -#define _PAGE_RW (_PAGE_READ | _PAGE_WRITE) -#define _PAGE_RWX (_PAGE_READ | _PAGE_WRITE | _PAGE_EXEC) #define _PAGE_PRIVILEGED 0x00008 /* kernel access only */ #define _PAGE_SAO 0x00010 /* Strong access order */ #define _PAGE_NON_IDEMPOTENT 0x00020 /* non idempotent memory */ @@ -32,11 +30,13 @@ #define _RPAGE_SW1 0x00800 #define _RPAGE_SW2 0x00400 #define _RPAGE_SW3 0x00200 -#define _RPAGE_RSV1 0x1000000000000000UL -#define _RPAGE_RSV2 0x0800000000000000UL -#define _RPAGE_RSV3 0x0400000000000000UL -#define _RPAGE_RSV4 0x0200000000000000UL -#define _RPAGE_RSV5 0x00040UL +#define _RPAGE_RSV1 0x00040UL + +#define _RPAGE_PKEY_BIT4 0x1000000000000000UL +#define _RPAGE_PKEY_BIT3 0x0800000000000000UL +#define _RPAGE_PKEY_BIT2 0x0400000000000000UL +#define _RPAGE_PKEY_BIT1 0x0200000000000000UL +#define _RPAGE_PKEY_BIT0 0x0100000000000000UL #define _PAGE_PTE 0x4000000000000000UL /* distinguishes PTEs from pointers */ #define _PAGE_PRESENT 0x8000000000000000UL /* pte contains a translation */ @@ -58,13 +58,12 @@ */ #define _RPAGE_RPN0 0x01000 #define _RPAGE_RPN1 0x02000 -#define _RPAGE_RPN44 0x0100000000000000UL #define _RPAGE_RPN43 0x0080000000000000UL #define _RPAGE_RPN42 0x0040000000000000UL #define _RPAGE_RPN41 0x0020000000000000UL /* Max physical address bit as per radix table */ -#define _RPAGE_PA_MAX 57 +#define _RPAGE_PA_MAX 56 /* * Max physical address bit we will use for now. @@ -103,6 +102,7 @@ * and every thing below PAGE_SHIFT; */ #define PTE_RPN_MASK (((1UL << _PAGE_PA_MAX) - 1) & (PAGE_MASK)) +#define PTE_RPN_SHIFT PAGE_SHIFT /* * set of bits not changed in pmd_modify. Even though we have hash specific bits * in here, on radix we expect them to be zero. @@ -115,8 +115,8 @@ */ #define _PAGE_KERNEL_RW (_PAGE_PRIVILEGED | _PAGE_RW | _PAGE_DIRTY) #define _PAGE_KERNEL_RO (_PAGE_PRIVILEGED | _PAGE_READ) -#define _PAGE_KERNEL_RWX (_PAGE_PRIVILEGED | _PAGE_DIRTY | \ - _PAGE_RW | _PAGE_EXEC) +#define _PAGE_KERNEL_ROX (_PAGE_PRIVILEGED | _PAGE_READ | _PAGE_EXEC) +#define _PAGE_KERNEL_RWX (_PAGE_PRIVILEGED | _PAGE_DIRTY | _PAGE_RW | _PAGE_EXEC) /* * _PAGE_CHG_MASK masks of bits that are to be preserved across * pgprot changes @@ -125,8 +125,6 @@ _PAGE_ACCESSED | _PAGE_SPECIAL | _PAGE_PTE | \ _PAGE_SOFT_DIRTY | _PAGE_DEVMAP) -#define H_PTE_PKEY (H_PTE_PKEY_BIT0 | H_PTE_PKEY_BIT1 | H_PTE_PKEY_BIT2 | \ - H_PTE_PKEY_BIT3 | H_PTE_PKEY_BIT4) /* * We define 2 sets of base prot bits, one for basic pages (ie, * cacheable kernel and user pages) and one for non cacheable @@ -136,48 +134,16 @@ #define _PAGE_BASE_NC (_PAGE_PRESENT | _PAGE_ACCESSED) #define _PAGE_BASE (_PAGE_BASE_NC) -/* Permission masks used to generate the __P and __S table, - * - * Note:__pgprot is defined in arch/powerpc/include/asm/page.h - * - * Write permissions imply read permissions for now (we could make write-only - * pages on BookE but we don't bother for now). Execute permission control is - * possible on platforms that define _PAGE_EXEC - */ -#define PAGE_NONE __pgprot(_PAGE_BASE | _PAGE_PRIVILEGED) -#define PAGE_SHARED __pgprot(_PAGE_BASE | _PAGE_RW) -#define PAGE_SHARED_X __pgprot(_PAGE_BASE | _PAGE_RW | _PAGE_EXEC) -#define PAGE_COPY __pgprot(_PAGE_BASE | _PAGE_READ) -#define PAGE_COPY_X __pgprot(_PAGE_BASE | _PAGE_READ | _PAGE_EXEC) -#define PAGE_READONLY __pgprot(_PAGE_BASE | _PAGE_READ) -#define PAGE_READONLY_X __pgprot(_PAGE_BASE | _PAGE_READ | _PAGE_EXEC) +#include <asm/pgtable-masks.h> /* Permission masks used for kernel mappings */ #define PAGE_KERNEL __pgprot(_PAGE_BASE | _PAGE_KERNEL_RW) -#define PAGE_KERNEL_NC __pgprot(_PAGE_BASE_NC | _PAGE_KERNEL_RW | \ - _PAGE_TOLERANT) -#define PAGE_KERNEL_NCG __pgprot(_PAGE_BASE_NC | _PAGE_KERNEL_RW | \ - _PAGE_NON_IDEMPOTENT) +#define PAGE_KERNEL_NC __pgprot(_PAGE_BASE_NC | _PAGE_KERNEL_RW | _PAGE_TOLERANT) +#define PAGE_KERNEL_NCG __pgprot(_PAGE_BASE_NC | _PAGE_KERNEL_RW | _PAGE_NON_IDEMPOTENT) #define PAGE_KERNEL_X __pgprot(_PAGE_BASE | _PAGE_KERNEL_RWX) #define PAGE_KERNEL_RO __pgprot(_PAGE_BASE | _PAGE_KERNEL_RO) #define PAGE_KERNEL_ROX __pgprot(_PAGE_BASE | _PAGE_KERNEL_ROX) -/* - * Protection used for kernel text. We want the debuggers to be able to - * set breakpoints anywhere, so don't write protect the kernel text - * on platforms where such control is possible. - */ -#if defined(CONFIG_KGDB) || defined(CONFIG_XMON) || defined(CONFIG_BDI_SWITCH) || \ - defined(CONFIG_KPROBES) || defined(CONFIG_DYNAMIC_FTRACE) -#define PAGE_KERNEL_TEXT PAGE_KERNEL_X -#else -#define PAGE_KERNEL_TEXT PAGE_KERNEL_ROX -#endif - -/* Make modules code happy. We don't set RO yet */ -#define PAGE_KERNEL_EXEC PAGE_KERNEL_X -#define PAGE_AGP (PAGE_KERNEL_NC) - #ifndef __ASSEMBLY__ /* * page table defines @@ -231,6 +197,12 @@ extern unsigned long __pmd_frag_size_shift; #define PTRS_PER_PUD (1 << PUD_INDEX_SIZE) #define PTRS_PER_PGD (1 << PGD_INDEX_SIZE) +#define MAX_PTRS_PER_PTE ((H_PTRS_PER_PTE > R_PTRS_PER_PTE) ? H_PTRS_PER_PTE : R_PTRS_PER_PTE) +#define MAX_PTRS_PER_PMD ((H_PTRS_PER_PMD > R_PTRS_PER_PMD) ? H_PTRS_PER_PMD : R_PTRS_PER_PMD) +#define MAX_PTRS_PER_PUD ((H_PTRS_PER_PUD > R_PTRS_PER_PUD) ? H_PTRS_PER_PUD : R_PTRS_PER_PUD) +#define MAX_PTRS_PER_PGD (1 << (H_PGD_INDEX_SIZE > RADIX_PGD_INDEX_SIZE ? \ + H_PGD_INDEX_SIZE : RADIX_PGD_INDEX_SIZE)) + /* PMD_SHIFT determines what a second-level page table entry can map */ #define PMD_SHIFT (PAGE_SHIFT + PTE_INDEX_SIZE) #define PMD_SIZE (1UL << PMD_SHIFT) @@ -251,7 +223,7 @@ extern unsigned long __pmd_frag_size_shift; /* Bits to mask out from a PUD to get to the PMD page */ #define PUD_MASKED_BITS 0xc0000000000000ffUL /* Bits to mask out from a PGD to get to the PUD page */ -#define PGD_MASKED_BITS 0xc0000000000000ffUL +#define P4D_MASKED_BITS 0xc0000000000000ffUL /* * Used as an indicator for rcu callback functions @@ -295,6 +267,13 @@ extern unsigned long pci_io_base; #include <asm/book3s/64/hash.h> #include <asm/book3s/64/radix.h> +#if H_MAX_PHYSMEM_BITS > R_MAX_PHYSMEM_BITS +#define MAX_PHYSMEM_BITS H_MAX_PHYSMEM_BITS +#else +#define MAX_PHYSMEM_BITS R_MAX_PHYSMEM_BITS +#endif + + #ifdef CONFIG_PPC_64K_PAGES #include <asm/book3s/64/pgtable-64k.h> #else @@ -317,10 +296,9 @@ extern unsigned long pci_io_base; #define PHB_IO_END (KERN_IO_START + FULL_IO_SIZE) #define IOREMAP_BASE (PHB_IO_END) #define IOREMAP_START (ioremap_bot) -#define IOREMAP_END (KERN_IO_END) - -/* Advertise special mapping type for AGP */ -#define HAVE_PAGE_AGP +#define IOREMAP_END (KERN_IO_END - FIXADDR_SIZE) +#define FIXADDR_SIZE SZ_32M +#define FIXADDR_TOP (IOREMAP_END + FIXADDR_SIZE) #ifndef __ASSEMBLY__ @@ -382,40 +360,34 @@ static inline int __ptep_test_and_clear_young(struct mm_struct *mm, #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG #define ptep_test_and_clear_young(__vma, __addr, __ptep) \ ({ \ - int __r; \ - __r = __ptep_test_and_clear_young((__vma)->vm_mm, __addr, __ptep); \ - __r; \ + __ptep_test_and_clear_young((__vma)->vm_mm, __addr, __ptep); \ }) -static inline int __pte_write(pte_t pte) -{ - return !!(pte_raw(pte) & cpu_to_be64(_PAGE_WRITE)); -} +/* + * On Book3S CPUs, clearing the accessed bit without a TLB flush + * doesn't cause data corruption. [ It could cause incorrect + * page aging and the (mistaken) reclaim of hot pages, but the + * chance of that should be relatively low. ] + * + * So as a performance optimization don't flush the TLB when + * clearing the accessed bit, it will eventually be flushed by + * a context switch or a VM operation anyway. [ In the rare + * event of it not getting flushed for a long time the delay + * shouldn't really matter because there's no real memory + * pressure for swapout to react to. ] + * + * Note: this optimisation also exists in pte_needs_flush() and + * huge_pmd_needs_flush(). + */ +#define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH +#define ptep_clear_flush_young ptep_test_and_clear_young -#ifdef CONFIG_NUMA_BALANCING -#define pte_savedwrite pte_savedwrite -static inline bool pte_savedwrite(pte_t pte) -{ - /* - * Saved write ptes are prot none ptes that doesn't have - * privileged bit sit. We mark prot none as one which has - * present and pviliged bit set and RWX cleared. To mark - * protnone which used to have _PAGE_WRITE set we clear - * the privileged bit. - */ - return !(pte_raw(pte) & cpu_to_be64(_PAGE_RWX | _PAGE_PRIVILEGED)); -} -#else -#define pte_savedwrite pte_savedwrite -static inline bool pte_savedwrite(pte_t pte) -{ - return false; -} -#endif +#define __HAVE_ARCH_PMDP_CLEAR_YOUNG_FLUSH +#define pmdp_clear_flush_young pmdp_test_and_clear_young static inline int pte_write(pte_t pte) { - return __pte_write(pte) || pte_savedwrite(pte); + return !!(pte_raw(pte) & cpu_to_be64(_PAGE_WRITE)); } static inline int pte_read(pte_t pte) @@ -427,24 +399,16 @@ static inline int pte_read(pte_t pte) static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { - if (__pte_write(*ptep)) + if (pte_write(*ptep)) pte_update(mm, addr, ptep, _PAGE_WRITE, 0, 0); - else if (unlikely(pte_savedwrite(*ptep))) - pte_update(mm, addr, ptep, 0, _PAGE_PRIVILEGED, 0); } #define __HAVE_ARCH_HUGE_PTEP_SET_WRPROTECT static inline void huge_ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { - /* - * We should not find protnone for hugetlb, but this complete the - * interface. - */ - if (__pte_write(*ptep)) + if (pte_write(*ptep)) pte_update(mm, addr, ptep, _PAGE_WRITE, 0, 1); - else if (unlikely(pte_savedwrite(*ptep))) - pte_update(mm, addr, ptep, 0, _PAGE_PRIVILEGED, 1); } #define __HAVE_ARCH_PTEP_GET_AND_CLEAR @@ -521,38 +485,14 @@ static inline int pte_protnone(pte_t pte) return (pte_raw(pte) & cpu_to_be64(_PAGE_PRESENT | _PAGE_PTE | _PAGE_RWX)) == cpu_to_be64(_PAGE_PRESENT | _PAGE_PTE); } +#endif /* CONFIG_NUMA_BALANCING */ -#define pte_mk_savedwrite pte_mk_savedwrite -static inline pte_t pte_mk_savedwrite(pte_t pte) +static inline bool pte_hw_valid(pte_t pte) { - /* - * Used by Autonuma subsystem to preserve the write bit - * while marking the pte PROT_NONE. Only allow this - * on PROT_NONE pte - */ - VM_BUG_ON((pte_raw(pte) & cpu_to_be64(_PAGE_PRESENT | _PAGE_RWX | _PAGE_PRIVILEGED)) != - cpu_to_be64(_PAGE_PRESENT | _PAGE_PRIVILEGED)); - return __pte_raw(pte_raw(pte) & cpu_to_be64(~_PAGE_PRIVILEGED)); + return (pte_raw(pte) & cpu_to_be64(_PAGE_PRESENT | _PAGE_PTE)) == + cpu_to_be64(_PAGE_PRESENT | _PAGE_PTE); } -#define pte_clear_savedwrite pte_clear_savedwrite -static inline pte_t pte_clear_savedwrite(pte_t pte) -{ - /* - * Used by KSM subsystem to make a protnone pte readonly. - */ - VM_BUG_ON(!pte_protnone(pte)); - return __pte_raw(pte_raw(pte) | cpu_to_be64(_PAGE_PRIVILEGED)); -} -#else -#define pte_clear_savedwrite pte_clear_savedwrite -static inline pte_t pte_clear_savedwrite(pte_t pte) -{ - VM_WARN_ON(1); - return __pte_raw(pte_raw(pte) & cpu_to_be64(~_PAGE_WRITE)); -} -#endif /* CONFIG_NUMA_BALANCING */ - static inline int pte_present(pte_t pte) { /* @@ -561,12 +501,11 @@ static inline int pte_present(pte_t pte) * invalid during ptep_set_access_flags. Hence we look for _PAGE_INVALID * if we find _PAGE_PRESENT cleared. */ - return !!(pte_raw(pte) & cpu_to_be64(_PAGE_PRESENT | _PAGE_INVALID)); -} -static inline bool pte_hw_valid(pte_t pte) -{ - return !!(pte_raw(pte) & cpu_to_be64(_PAGE_PRESENT)); + if (pte_hw_valid(pte)) + return true; + return (pte_raw(pte) & cpu_to_be64(_PAGE_INVALID | _PAGE_PTE)) == + cpu_to_be64(_PAGE_INVALID | _PAGE_PTE); } #ifdef CONFIG_PPC_MEM_KEYS @@ -587,8 +526,8 @@ static inline bool pte_user(pte_t pte) static inline bool pte_access_permitted(pte_t pte, bool write) { /* - * _PAGE_READ is needed for any access and will be - * cleared for PROT_NONE + * _PAGE_READ is needed for any access and will be cleared for + * PROT_NONE. Execute-only mapping via PROT_EXEC also returns false. */ if (!pte_present(pte) || !pte_user(pte) || !pte_read(pte)) return false; @@ -611,19 +550,12 @@ static inline pte_t pfn_pte(unsigned long pfn, pgprot_t pgprot) VM_BUG_ON(pfn >> (64 - PAGE_SHIFT)); VM_BUG_ON((pfn << PAGE_SHIFT) & ~PTE_RPN_MASK); - return __pte(((pte_basic_t)pfn << PAGE_SHIFT) | pgprot_val(pgprot)); -} - -static inline unsigned long pte_pfn(pte_t pte) -{ - return (pte_val(pte) & PTE_RPN_MASK) >> PAGE_SHIFT; + return __pte(((pte_basic_t)pfn << PAGE_SHIFT) | pgprot_val(pgprot) | _PAGE_PTE); } /* Generic modifiers for PTE bits */ static inline pte_t pte_wrprotect(pte_t pte) { - if (unlikely(pte_savedwrite(pte))) - return pte_clear_savedwrite(pte); return __pte_raw(pte_raw(pte) & cpu_to_be64(~_PAGE_WRITE)); } @@ -647,12 +579,7 @@ static inline pte_t pte_mkexec(pte_t pte) return __pte_raw(pte_raw(pte) | cpu_to_be64(_PAGE_EXEC)); } -static inline pte_t pte_mkpte(pte_t pte) -{ - return __pte_raw(pte_raw(pte) | cpu_to_be64(_PAGE_PTE)); -} - -static inline pte_t pte_mkwrite(pte_t pte) +static inline pte_t pte_mkwrite_novma(pte_t pte) { /* * write implies read, hence set both @@ -685,16 +612,6 @@ static inline pte_t pte_mkdevmap(pte_t pte) return __pte_raw(pte_raw(pte) | cpu_to_be64(_PAGE_SPECIAL | _PAGE_DEVMAP)); } -static inline pte_t pte_mkprivileged(pte_t pte) -{ - return __pte_raw(pte_raw(pte) | cpu_to_be64(_PAGE_PRIVILEGED)); -} - -static inline pte_t pte_mkuser(pte_t pte) -{ - return __pte_raw(pte_raw(pte) & cpu_to_be64(~_PAGE_PRIVILEGED)); -} - /* * This is potentially called with a pmd as the argument, in which case it's not * safe to check _PAGE_DEVMAP unless we also confirm that _PAGE_PTE is set. @@ -703,7 +620,7 @@ static inline pte_t pte_mkuser(pte_t pte) */ static inline int pte_devmap(pte_t pte) { - u64 mask = cpu_to_be64(_PAGE_DEVMAP | _PAGE_PTE); + __be64 mask = cpu_to_be64(_PAGE_DEVMAP | _PAGE_PTE); return (pte_raw(pte) & mask) == mask; } @@ -722,17 +639,17 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) * Don't have overlapping bits with _PAGE_HPTEFLAGS \ * We filter HPTEFLAGS on set_pte. \ */ \ - BUILD_BUG_ON(_PAGE_HPTEFLAGS & (0x1f << _PAGE_BIT_SWAP_TYPE)); \ + BUILD_BUG_ON(_PAGE_HPTEFLAGS & SWP_TYPE_MASK); \ BUILD_BUG_ON(_PAGE_HPTEFLAGS & _PAGE_SWP_SOFT_DIRTY); \ + BUILD_BUG_ON(_PAGE_HPTEFLAGS & _PAGE_SWP_EXCLUSIVE); \ } while (0) #define SWP_TYPE_BITS 5 -#define __swp_type(x) (((x).val >> _PAGE_BIT_SWAP_TYPE) \ - & ((1UL << SWP_TYPE_BITS) - 1)) +#define SWP_TYPE_MASK ((1UL << SWP_TYPE_BITS) - 1) +#define __swp_type(x) ((x).val & SWP_TYPE_MASK) #define __swp_offset(x) (((x).val & PTE_RPN_MASK) >> PAGE_SHIFT) #define __swp_entry(type, offset) ((swp_entry_t) { \ - ((type) << _PAGE_BIT_SWAP_TYPE) \ - | (((offset) << PAGE_SHIFT) & PTE_RPN_MASK)}) + (type) | (((offset) << PAGE_SHIFT) & PTE_RPN_MASK)}) /* * swp_entry_t must be independent of pte bits. We build a swp_entry_t from * swap type and offset we get from swap and convert that to pte to find a @@ -745,11 +662,13 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) #define __swp_entry_to_pmd(x) (pte_pmd(__swp_entry_to_pte(x))) #ifdef CONFIG_MEM_SOFT_DIRTY -#define _PAGE_SWP_SOFT_DIRTY (1UL << (SWP_TYPE_BITS + _PAGE_BIT_SWAP_TYPE)) +#define _PAGE_SWP_SOFT_DIRTY _PAGE_SOFT_DIRTY #else #define _PAGE_SWP_SOFT_DIRTY 0UL #endif /* CONFIG_MEM_SOFT_DIRTY */ +#define _PAGE_SWP_EXCLUSIVE _PAGE_NON_IDEMPOTENT + #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY static inline pte_t pte_swp_mksoft_dirty(pte_t pte) { @@ -767,6 +686,21 @@ static inline pte_t pte_swp_clear_soft_dirty(pte_t pte) } #endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */ +static inline pte_t pte_swp_mkexclusive(pte_t pte) +{ + return __pte_raw(pte_raw(pte) | cpu_to_be64(_PAGE_SWP_EXCLUSIVE)); +} + +static inline int pte_swp_exclusive(pte_t pte) +{ + return !!(pte_raw(pte) & cpu_to_be64(_PAGE_SWP_EXCLUSIVE)); +} + +static inline pte_t pte_swp_clear_exclusive(pte_t pte) +{ + return __pte_raw(pte_raw(pte) & cpu_to_be64(~_PAGE_SWP_EXCLUSIVE)); +} + static inline bool check_pte_access(unsigned long access, unsigned long ptev) { /* @@ -815,6 +749,14 @@ static inline int pte_none(pte_t pte) static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte, int percpu) { + + VM_WARN_ON(!(pte_raw(pte) & cpu_to_be64(_PAGE_PTE))); + /* + * Keep the _PAGE_PTE added till we are sure we handle _PAGE_PTE + * in all the callers. + */ + pte = __pte_raw(pte_raw(pte) | cpu_to_be64(_PAGE_PTE)); + if (radix_enabled()) return radix__set_pte_at(mm, addr, ptep, pte, percpu); return hash__set_pte_at(mm, addr, ptep, pte, percpu); @@ -862,6 +804,13 @@ static inline bool pte_ci(pte_t pte) static inline void pmd_clear(pmd_t *pmdp) { + if (IS_ENABLED(CONFIG_DEBUG_VM) && !radix_enabled()) { + /* + * Don't use this if we can possibly have a hash page table + * entry mapping this. + */ + WARN_ON((pmd_val(*pmdp) & (H_PAGE_HASHPTE | _PAGE_PTE)) == (H_PAGE_HASHPTE | _PAGE_PTE)); + } *pmdp = __pmd(0); } @@ -910,6 +859,13 @@ static inline int pmd_bad(pmd_t pmd) static inline void pud_clear(pud_t *pudp) { + if (IS_ENABLED(CONFIG_DEBUG_VM) && !radix_enabled()) { + /* + * Don't use this if we can possibly have a hash page table + * entry mapping this. + */ + WARN_ON((pud_val(*pudp) & (H_PAGE_HASHPTE | _PAGE_PTE)) == (H_PAGE_HASHPTE | _PAGE_PTE)); + } *pudp = __pud(0); } @@ -934,8 +890,29 @@ static inline pud_t pte_pud(pte_t pte) { return __pud_raw(pte_raw(pte)); } + +static inline pte_t *pudp_ptep(pud_t *pud) +{ + return (pte_t *)pud; +} + +#define pud_pfn(pud) pte_pfn(pud_pte(pud)) +#define pud_dirty(pud) pte_dirty(pud_pte(pud)) +#define pud_young(pud) pte_young(pud_pte(pud)) +#define pud_mkold(pud) pte_pud(pte_mkold(pud_pte(pud))) +#define pud_wrprotect(pud) pte_pud(pte_wrprotect(pud_pte(pud))) +#define pud_mkdirty(pud) pte_pud(pte_mkdirty(pud_pte(pud))) +#define pud_mkclean(pud) pte_pud(pte_mkclean(pud_pte(pud))) +#define pud_mkyoung(pud) pte_pud(pte_mkyoung(pud_pte(pud))) +#define pud_mkwrite(pud) pte_pud(pte_mkwrite_novma(pud_pte(pud))) #define pud_write(pud) pte_write(pud_pte(pud)) +#ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY +#define pud_soft_dirty(pmd) pte_soft_dirty(pud_pte(pud)) +#define pud_mksoft_dirty(pmd) pte_pud(pte_mksoft_dirty(pud_pte(pud))) +#define pud_clear_soft_dirty(pmd) pte_pud(pte_clear_soft_dirty(pud_pte(pud))) +#endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */ + static inline int pud_bad(pud_t pud) { if (radix_enabled()) @@ -949,84 +926,67 @@ static inline bool pud_access_permitted(pud_t pud, bool write) return pte_access_permitted(pud_pte(pud), write); } -#define pgd_write(pgd) pte_write(pgd_pte(pgd)) +#define __p4d_raw(x) ((p4d_t) { __pgd_raw(x) }) +static inline __be64 p4d_raw(p4d_t x) +{ + return pgd_raw(x.pgd); +} + +#define p4d_write(p4d) pte_write(p4d_pte(p4d)) -static inline void pgd_clear(pgd_t *pgdp) +static inline void p4d_clear(p4d_t *p4dp) { - *pgdp = __pgd(0); + *p4dp = __p4d(0); } -static inline int pgd_none(pgd_t pgd) +static inline int p4d_none(p4d_t p4d) { - return !pgd_raw(pgd); + return !p4d_raw(p4d); } -static inline int pgd_present(pgd_t pgd) +static inline int p4d_present(p4d_t p4d) { - return !!(pgd_raw(pgd) & cpu_to_be64(_PAGE_PRESENT)); + return !!(p4d_raw(p4d) & cpu_to_be64(_PAGE_PRESENT)); } -static inline pte_t pgd_pte(pgd_t pgd) +static inline pte_t p4d_pte(p4d_t p4d) { - return __pte_raw(pgd_raw(pgd)); + return __pte_raw(p4d_raw(p4d)); } -static inline pgd_t pte_pgd(pte_t pte) +static inline p4d_t pte_p4d(pte_t pte) { - return __pgd_raw(pte_raw(pte)); + return __p4d_raw(pte_raw(pte)); } -static inline int pgd_bad(pgd_t pgd) +static inline int p4d_bad(p4d_t p4d) { if (radix_enabled()) - return radix__pgd_bad(pgd); - return hash__pgd_bad(pgd); + return radix__p4d_bad(p4d); + return hash__p4d_bad(p4d); } -#define pgd_access_permitted pgd_access_permitted -static inline bool pgd_access_permitted(pgd_t pgd, bool write) +#define p4d_access_permitted p4d_access_permitted +static inline bool p4d_access_permitted(p4d_t p4d, bool write) { - return pte_access_permitted(pgd_pte(pgd), write); + return pte_access_permitted(p4d_pte(p4d), write); } -extern struct page *pgd_page(pgd_t pgd); +extern struct page *p4d_page(p4d_t p4d); /* Pointers in the page table tree are physical addresses */ #define __pgtable_ptr_val(ptr) __pa(ptr) -#define pmd_page_vaddr(pmd) __va(pmd_val(pmd) & ~PMD_MASKED_BITS) -#define pud_page_vaddr(pud) __va(pud_val(pud) & ~PUD_MASKED_BITS) -#define pgd_page_vaddr(pgd) __va(pgd_val(pgd) & ~PGD_MASKED_BITS) - -#define pgd_index(address) (((address) >> (PGDIR_SHIFT)) & (PTRS_PER_PGD - 1)) -#define pud_index(address) (((address) >> (PUD_SHIFT)) & (PTRS_PER_PUD - 1)) -#define pmd_index(address) (((address) >> (PMD_SHIFT)) & (PTRS_PER_PMD - 1)) -#define pte_index(address) (((address) >> (PAGE_SHIFT)) & (PTRS_PER_PTE - 1)) - -/* - * Find an entry in a page-table-directory. We combine the address region - * (the high order N bits) and the pgd portion of the address. - */ - -#define pgd_offset(mm, address) ((mm)->pgd + pgd_index(address)) - -#define pud_offset(pgdp, addr) \ - (((pud_t *) pgd_page_vaddr(*(pgdp))) + pud_index(addr)) -#define pmd_offset(pudp,addr) \ - (((pmd_t *) pud_page_vaddr(*(pudp))) + pmd_index(addr)) -#define pte_offset_kernel(dir,addr) \ - (((pte_t *) pmd_page_vaddr(*(dir))) + pte_index(addr)) - -#define pte_offset_map(dir,addr) pte_offset_kernel((dir), (addr)) - -static inline void pte_unmap(pte_t *pte) { } +static inline pud_t *p4d_pgtable(p4d_t p4d) +{ + return (pud_t *)__va(p4d_val(p4d) & ~P4D_MASKED_BITS); +} -/* to find an entry in a kernel page-table-directory */ -/* This now only contains the vmalloc pages */ -#define pgd_offset_k(address) pgd_offset(&init_mm, address) +static inline pmd_t *pud_pgtable(pud_t pud) +{ + return (pmd_t *)__va(pud_val(pud) & ~PUD_MASKED_BITS); +} -#define pte_ERROR(e) \ - pr_err("%s:%d: bad pte %08lx.\n", __FILE__, __LINE__, pte_val(e)) #define pmd_ERROR(e) \ pr_err("%s:%d: bad pmd %08lx.\n", __FILE__, __LINE__, pmd_val(e)) #define pud_ERROR(e) \ @@ -1046,6 +1006,8 @@ static inline int map_kernel_page(unsigned long ea, unsigned long pa, pgprot_t p return hash__map_kernel_page(ea, pa, prot); } +void unmap_kernel_page(unsigned long va); + static inline int __meminit vmemmap_create_mapping(unsigned long start, unsigned long page_size, unsigned long phys) @@ -1065,6 +1027,16 @@ static inline void vmemmap_remove_mapping(unsigned long start, } #endif +#if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_KFENCE) +static inline void __kernel_map_pages(struct page *page, int numpages, int enable) +{ + if (radix_enabled()) + radix__kernel_map_pages(page, numpages, enable); + else + hash__kernel_map_pages(page, numpages, enable); +} +#endif + static inline pte_t pmd_pte(pmd_t pmd) { return __pte_raw(pmd_raw(pmd)); @@ -1087,9 +1059,7 @@ static inline pte_t *pmdp_ptep(pmd_t *pmd) #define pmd_mkdirty(pmd) pte_pmd(pte_mkdirty(pmd_pte(pmd))) #define pmd_mkclean(pmd) pte_pmd(pte_mkclean(pmd_pte(pmd))) #define pmd_mkyoung(pmd) pte_pmd(pte_mkyoung(pmd_pte(pmd))) -#define pmd_mkwrite(pmd) pte_pmd(pte_mkwrite(pmd_pte(pmd))) -#define pmd_mk_savedwrite(pmd) pte_pmd(pte_mk_savedwrite(pmd_pte(pmd))) -#define pmd_clear_savedwrite(pmd) pte_pmd(pte_clear_savedwrite(pmd_pte(pmd))) +#define pmd_mkwrite_novma(pmd) pte_pmd(pte_mkwrite_novma(pmd_pte(pmd))) #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY #define pmd_soft_dirty(pmd) pte_soft_dirty(pmd_pte(pmd)) @@ -1111,8 +1081,6 @@ static inline int pmd_protnone(pmd_t pmd) #endif /* CONFIG_NUMA_BALANCING */ #define pmd_write(pmd) pte_write(pmd_pte(pmd)) -#define __pmd_write(pmd) __pte_write(pmd_pte(pmd)) -#define pmd_savedwrite(pmd) pte_savedwrite(pmd_pte(pmd)) #define pmd_access_permitted pmd_access_permitted static inline bool pmd_access_permitted(pmd_t pmd, bool write) @@ -1135,12 +1103,24 @@ static inline bool pmd_access_permitted(pmd_t pmd, bool write) #ifdef CONFIG_TRANSPARENT_HUGEPAGE extern pmd_t pfn_pmd(unsigned long pfn, pgprot_t pgprot); +extern pud_t pfn_pud(unsigned long pfn, pgprot_t pgprot); extern pmd_t mk_pmd(struct page *page, pgprot_t pgprot); extern pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot); extern void set_pmd_at(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, pmd_t pmd); -extern void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr, - pmd_t *pmd); +extern void set_pud_at(struct mm_struct *mm, unsigned long addr, + pud_t *pudp, pud_t pud); + +static inline void update_mmu_cache_pmd(struct vm_area_struct *vma, + unsigned long addr, pmd_t *pmd) +{ +} + +static inline void update_mmu_cache_pud(struct vm_area_struct *vma, + unsigned long addr, pud_t *pud) +{ +} + extern int hash__has_transparent_hugepage(void); static inline int has_transparent_hugepage(void) { @@ -1150,6 +1130,14 @@ static inline int has_transparent_hugepage(void) } #define has_transparent_hugepage has_transparent_hugepage +static inline int has_transparent_pud_hugepage(void) +{ + if (radix_enabled()) + return radix__has_transparent_pud_hugepage(); + return 0; +} +#define has_transparent_pud_hugepage has_transparent_pud_hugepage + static inline unsigned long pmd_hugepage_update(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, unsigned long clr, unsigned long set) @@ -1159,6 +1147,16 @@ pmd_hugepage_update(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, return hash__pmd_hugepage_update(mm, addr, pmdp, clr, set); } +static inline unsigned long +pud_hugepage_update(struct mm_struct *mm, unsigned long addr, pud_t *pudp, + unsigned long clr, unsigned long set) +{ + if (radix_enabled()) + return radix__pud_hugepage_update(mm, addr, pudp, clr, set); + BUG(); + return pud_val(*pudp); +} + /* * returns true for pmd migration entries, THP, devmap, hugetlb * But compile time dependent on THP config @@ -1168,10 +1166,11 @@ static inline int pmd_large(pmd_t pmd) return !!(pmd_raw(pmd) & cpu_to_be64(_PAGE_PTE)); } -static inline pmd_t pmd_mknotpresent(pmd_t pmd) +static inline int pud_large(pud_t pud) { - return __pmd(pmd_val(pmd) & ~_PAGE_PRESENT); + return !!(pud_raw(pud) & cpu_to_be64(_PAGE_PTE)); } + /* * For radix we should always find H_PAGE_HASHPTE zero. Hence * the below will work for radix too @@ -1187,14 +1186,31 @@ static inline int __pmdp_test_and_clear_young(struct mm_struct *mm, return ((old & _PAGE_ACCESSED) != 0); } +static inline int __pudp_test_and_clear_young(struct mm_struct *mm, + unsigned long addr, pud_t *pudp) +{ + unsigned long old; + + if ((pud_raw(*pudp) & cpu_to_be64(_PAGE_ACCESSED | H_PAGE_HASHPTE)) == 0) + return 0; + old = pud_hugepage_update(mm, addr, pudp, _PAGE_ACCESSED, 0); + return ((old & _PAGE_ACCESSED) != 0); +} + #define __HAVE_ARCH_PMDP_SET_WRPROTECT static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp) { - if (__pmd_write((*pmdp))) + if (pmd_write(*pmdp)) pmd_hugepage_update(mm, addr, pmdp, _PAGE_WRITE, 0); - else if (unlikely(pmd_savedwrite(*pmdp))) - pmd_hugepage_update(mm, addr, pmdp, 0, _PAGE_PRIVILEGED); +} + +#define __HAVE_ARCH_PUDP_SET_WRPROTECT +static inline void pudp_set_wrprotect(struct mm_struct *mm, unsigned long addr, + pud_t *pudp) +{ + if (pud_write(*pudp)) + pud_hugepage_update(mm, addr, pudp, _PAGE_WRITE, 0); } /* @@ -1206,7 +1222,7 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long addr, * should return true. * We should not call this on a hugetlb entry. We should check for HugeTLB * entry using vma->vm_flags - * The page table walk rule is explained in Documentation/vm/transhuge.rst + * The page table walk rule is explained in Documentation/mm/transhuge.rst */ static inline int pmd_trans_huge(pmd_t pmd) { @@ -1218,6 +1234,17 @@ static inline int pmd_trans_huge(pmd_t pmd) return hash__pmd_trans_huge(pmd); } +static inline int pud_trans_huge(pud_t pud) +{ + if (!pud_present(pud)) + return false; + + if (radix_enabled()) + return radix__pud_trans_huge(pud); + return 0; +} + + #define __HAVE_ARCH_PMD_SAME static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b) { @@ -1226,21 +1253,73 @@ static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b) return hash__pmd_same(pmd_a, pmd_b); } -static inline pmd_t pmd_mkhuge(pmd_t pmd) +#define pud_same pud_same +static inline int pud_same(pud_t pud_a, pud_t pud_b) +{ + if (radix_enabled()) + return radix__pud_same(pud_a, pud_b); + return hash__pud_same(pud_a, pud_b); +} + + +static inline pmd_t __pmd_mkhuge(pmd_t pmd) { if (radix_enabled()) return radix__pmd_mkhuge(pmd); return hash__pmd_mkhuge(pmd); } +static inline pud_t __pud_mkhuge(pud_t pud) +{ + if (radix_enabled()) + return radix__pud_mkhuge(pud); + BUG(); + return pud; +} + +/* + * pfn_pmd return a pmd_t that can be used as pmd pte entry. + */ +static inline pmd_t pmd_mkhuge(pmd_t pmd) +{ +#ifdef CONFIG_DEBUG_VM + if (radix_enabled()) + WARN_ON((pmd_raw(pmd) & cpu_to_be64(_PAGE_PTE)) == 0); + else + WARN_ON((pmd_raw(pmd) & cpu_to_be64(_PAGE_PTE | H_PAGE_THP_HUGE)) != + cpu_to_be64(_PAGE_PTE | H_PAGE_THP_HUGE)); +#endif + return pmd; +} + +static inline pud_t pud_mkhuge(pud_t pud) +{ +#ifdef CONFIG_DEBUG_VM + if (radix_enabled()) + WARN_ON((pud_raw(pud) & cpu_to_be64(_PAGE_PTE)) == 0); + else + WARN_ON(1); +#endif + return pud; +} + + #define __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS extern int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, pmd_t entry, int dirty); +#define __HAVE_ARCH_PUDP_SET_ACCESS_FLAGS +extern int pudp_set_access_flags(struct vm_area_struct *vma, + unsigned long address, pud_t *pudp, + pud_t entry, int dirty); #define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG extern int pmdp_test_and_clear_young(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp); +#define __HAVE_ARCH_PUDP_TEST_AND_CLEAR_YOUNG +extern int pudp_test_and_clear_young(struct vm_area_struct *vma, + unsigned long address, pud_t *pudp); + #define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, @@ -1251,6 +1330,16 @@ static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, return hash__pmdp_huge_get_and_clear(mm, addr, pmdp); } +#define __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR +static inline pud_t pudp_huge_get_and_clear(struct mm_struct *mm, + unsigned long addr, pud_t *pudp) +{ + if (radix_enabled()) + return radix__pudp_huge_get_and_clear(mm, addr, pudp); + BUG(); + return *pudp; +} + static inline pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { @@ -1260,6 +1349,16 @@ static inline pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, } #define pmdp_collapse_flush pmdp_collapse_flush +#define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR_FULL +pmd_t pmdp_huge_get_and_clear_full(struct vm_area_struct *vma, + unsigned long addr, + pmd_t *pmdp, int full); + +#define __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR_FULL +pud_t pudp_huge_get_and_clear_full(struct vm_area_struct *vma, + unsigned long addr, + pud_t *pudp, int full); + #define __HAVE_ARCH_PGTABLE_DEPOSIT static inline void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, pgtable_t pgtable) @@ -1303,7 +1402,17 @@ extern void serialize_against_pte_lookup(struct mm_struct *mm); static inline pmd_t pmd_mkdevmap(pmd_t pmd) { - return __pmd(pmd_val(pmd) | (_PAGE_PTE | _PAGE_DEVMAP)); + if (radix_enabled()) + return radix__pmd_mkdevmap(pmd); + return hash__pmd_mkdevmap(pmd); +} + +static inline pud_t pud_mkdevmap(pud_t pud) +{ + if (radix_enabled()) + return radix__pud_mkdevmap(pud); + BUG(); + return pud; } static inline int pmd_devmap(pmd_t pmd) @@ -1313,7 +1422,7 @@ static inline int pmd_devmap(pmd_t pmd) static inline int pud_devmap(pud_t pud) { - return 0; + return pte_devmap(pud_pte(pud)); } static inline int pgd_devmap(pgd_t pgd) @@ -1322,16 +1431,6 @@ static inline int pgd_devmap(pgd_t pgd) } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ -static inline int pud_pfn(pud_t pud) -{ - /* - * Currently all calls to pud_pfn() are gated around a pud_devmap() - * check so this should never be used. If it grows another user we - * want to know about it. - */ - BUILD_BUG(); - return 0; -} #define __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION pte_t ptep_modify_prot_start(struct vm_area_struct *, unsigned long, pte_t *); void ptep_modify_prot_commit(struct vm_area_struct *, unsigned long, @@ -1355,22 +1454,18 @@ static inline bool is_pte_rw_upgrade(unsigned long old_val, unsigned long new_va * Like pmd_huge() and pmd_large(), but works regardless of config options */ #define pmd_is_leaf pmd_is_leaf +#define pmd_leaf pmd_is_leaf static inline bool pmd_is_leaf(pmd_t pmd) { return !!(pmd_raw(pmd) & cpu_to_be64(_PAGE_PTE)); } #define pud_is_leaf pud_is_leaf +#define pud_leaf pud_is_leaf static inline bool pud_is_leaf(pud_t pud) { return !!(pud_raw(pud) & cpu_to_be64(_PAGE_PTE)); } -#define pgd_is_leaf pgd_is_leaf -static inline bool pgd_is_leaf(pgd_t pgd) -{ - return !!(pgd_raw(pgd) & cpu_to_be64(_PAGE_PTE)); -} - #endif /* __ASSEMBLY__ */ #endif /* _ASM_POWERPC_BOOK3S_64_PGTABLE_H_ */ diff --git a/arch/powerpc/include/asm/book3s/64/pkeys.h b/arch/powerpc/include/asm/book3s/64/pkeys.h new file mode 100644 index 000000000000..5b178139f3c0 --- /dev/null +++ b/arch/powerpc/include/asm/book3s/64/pkeys.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ + +#ifndef _ASM_POWERPC_BOOK3S_64_PKEYS_H +#define _ASM_POWERPC_BOOK3S_64_PKEYS_H + +#include <asm/book3s/64/hash-pkey.h> + +static inline u64 vmflag_to_pte_pkey_bits(u64 vm_flags) +{ + if (!mmu_has_feature(MMU_FTR_PKEY)) + return 0x0UL; + + if (radix_enabled()) + BUG(); + return hash__vmflag_to_pte_pkey_bits(vm_flags); +} + +static inline u16 pte_to_pkey_bits(u64 pteflags) +{ + if (radix_enabled()) + BUG(); + return hash__pte_to_pkey_bits(pteflags); +} + +#endif /*_ASM_POWERPC_KEYS_H */ diff --git a/arch/powerpc/include/asm/book3s/64/radix-4k.h b/arch/powerpc/include/asm/book3s/64/radix-4k.h index d5f5ab73dc7f..035ceecd6d67 100644 --- a/arch/powerpc/include/asm/book3s/64/radix-4k.h +++ b/arch/powerpc/include/asm/book3s/64/radix-4k.h @@ -11,7 +11,7 @@ #define RADIX_PGD_INDEX_SIZE 13 // size: 8B << 13 = 64KB, maps 2^13 x 512GB = 4PB /* - * One fragment per per page + * One fragment per page */ #define RADIX_PTE_FRAG_SIZE_SHIFT (RADIX_PTE_INDEX_SIZE + 3) #define RADIX_PTE_FRAG_NR (PAGE_SIZE >> RADIX_PTE_FRAG_SIZE_SHIFT) diff --git a/arch/powerpc/include/asm/book3s/64/radix.h b/arch/powerpc/include/asm/book3s/64/radix.h index d97db3ad9aae..357e23a403d3 100644 --- a/arch/powerpc/include/asm/book3s/64/radix.h +++ b/arch/powerpc/include/asm/book3s/64/radix.h @@ -30,11 +30,16 @@ /* Don't have anything in the reserved bits and leaf bits */ #define RADIX_PMD_BAD_BITS 0x60000000000000e0UL #define RADIX_PUD_BAD_BITS 0x60000000000000e0UL -#define RADIX_PGD_BAD_BITS 0x60000000000000e0UL +#define RADIX_P4D_BAD_BITS 0x60000000000000e0UL #define RADIX_PMD_SHIFT (PAGE_SHIFT + RADIX_PTE_INDEX_SIZE) #define RADIX_PUD_SHIFT (RADIX_PMD_SHIFT + RADIX_PMD_INDEX_SIZE) #define RADIX_PGD_SHIFT (RADIX_PUD_SHIFT + RADIX_PUD_INDEX_SIZE) + +#define R_PTRS_PER_PTE (1 << RADIX_PTE_INDEX_SIZE) +#define R_PTRS_PER_PMD (1 << RADIX_PMD_INDEX_SIZE) +#define R_PTRS_PER_PUD (1 << RADIX_PUD_INDEX_SIZE) + /* * Size of EA range mapped by our pagetables. */ @@ -68,11 +73,11 @@ * * * 3rd quadrant expanded: - * +------------------------------+ - * | | + * +------------------------------+ Highest address (0xc010000000000000) + * +------------------------------+ KASAN shadow end (0xc00fc00000000000) * | | * | | - * +------------------------------+ Kernel vmemmap end (0xc010000000000000) + * +------------------------------+ Kernel vmemmap end/shadow start (0xc00e000000000000) * | | * | 512TB | * | | @@ -91,6 +96,23 @@ * +------------------------------+ Kernel linear (0xc.....) */ +/* For the sizes of the shadow area, see kasan.h */ + +/* + * If we store section details in page->flags we can't increase the MAX_PHYSMEM_BITS + * if we increase SECTIONS_WIDTH we will not store node details in page->flags and + * page_to_nid does a page->section->node lookup + * Hence only increase for VMEMMAP. Further depending on SPARSEMEM_EXTREME reduce + * memory requirements with large number of sections. + * 51 bits is the max physical real address on POWER9 + */ + +#if defined(CONFIG_SPARSEMEM_VMEMMAP) && defined(CONFIG_SPARSEMEM_EXTREME) +#define R_MAX_PHYSMEM_BITS 51 +#else +#define R_MAX_PHYSMEM_BITS 46 +#endif + #define RADIX_KERN_VIRT_START ASM_CONST(0xc008000000000000) /* * 49 = MAX_EA_BITS_PER_CONTEXT (hash specific). To make sure we pick @@ -206,8 +228,10 @@ static inline void radix__set_pte_at(struct mm_struct *mm, unsigned long addr, * from ptesync, it should probably go into update_mmu_cache, rather * than set_pte_at (which is used to set ptes unrelated to faults). * - * Spurious faults to vmalloc region are not tolerated, so there is - * a ptesync in flush_cache_vmap. + * Spurious faults from the kernel memory are not tolerated, so there + * is a ptesync in flush_cache_vmap, and __map_kernel_page() follows + * the pte update sequence from ISA Book III 6.10 Translation Table + * Update Synchronization Requirements. */ } @@ -226,10 +250,14 @@ static inline int radix__pud_bad(pud_t pud) return !!(pud_val(pud) & RADIX_PUD_BAD_BITS); } +static inline int radix__pud_same(pud_t pud_a, pud_t pud_b) +{ + return ((pud_raw(pud_a) ^ pud_raw(pud_b)) == 0); +} -static inline int radix__pgd_bad(pgd_t pgd) +static inline int radix__p4d_bad(p4d_t p4d) { - return !!(pgd_val(pgd) & RADIX_PGD_BAD_BITS); + return !!(p4d_val(p4d) & RADIX_P4D_BAD_BITS); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE @@ -244,9 +272,22 @@ static inline pmd_t radix__pmd_mkhuge(pmd_t pmd) return __pmd(pmd_val(pmd) | _PAGE_PTE); } +static inline int radix__pud_trans_huge(pud_t pud) +{ + return (pud_val(pud) & (_PAGE_PTE | _PAGE_DEVMAP)) == _PAGE_PTE; +} + +static inline pud_t radix__pud_mkhuge(pud_t pud) +{ + return __pud(pud_val(pud) | _PAGE_PTE); +} + extern unsigned long radix__pmd_hugepage_update(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, unsigned long clr, unsigned long set); +extern unsigned long radix__pud_hugepage_update(struct mm_struct *mm, unsigned long addr, + pud_t *pudp, unsigned long clr, + unsigned long set); extern pmd_t radix__pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp); extern void radix__pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, @@ -254,6 +295,9 @@ extern void radix__pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, extern pgtable_t radix__pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp); extern pmd_t radix__pmdp_huge_get_and_clear(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp); +pud_t radix__pudp_huge_get_and_clear(struct mm_struct *mm, + unsigned long addr, pud_t *pudp); + static inline int radix__has_transparent_hugepage(void) { /* For radix 2M at PMD level means thp */ @@ -261,11 +305,35 @@ static inline int radix__has_transparent_hugepage(void) return 1; return 0; } + +static inline int radix__has_transparent_pud_hugepage(void) +{ + /* For radix 1G at PUD level means pud hugepage support */ + if (mmu_psize_defs[MMU_PAGE_1G].shift == PUD_SHIFT) + return 1; + return 0; +} #endif +static inline pmd_t radix__pmd_mkdevmap(pmd_t pmd) +{ + return __pmd(pmd_val(pmd) | (_PAGE_PTE | _PAGE_DEVMAP)); +} + +static inline pud_t radix__pud_mkdevmap(pud_t pud) +{ + return __pud(pud_val(pud) | (_PAGE_PTE | _PAGE_DEVMAP)); +} + +struct vmem_altmap; +struct dev_pagemap; extern int __meminit radix__vmemmap_create_mapping(unsigned long start, unsigned long page_size, unsigned long phys); +int __meminit radix__vmemmap_populate(unsigned long start, unsigned long end, + int node, struct vmem_altmap *altmap); +void __ref radix__vmemmap_free(unsigned long start, unsigned long end, + struct vmem_altmap *altmap); extern void radix__vmemmap_remove_mapping(unsigned long start, unsigned long page_size); @@ -289,8 +357,22 @@ static inline unsigned long radix__get_tree_size(void) } #ifdef CONFIG_MEMORY_HOTPLUG -int radix__create_section_mapping(unsigned long start, unsigned long end, int nid); +int radix__create_section_mapping(unsigned long start, unsigned long end, + int nid, pgprot_t prot); int radix__remove_section_mapping(unsigned long start, unsigned long end); #endif /* CONFIG_MEMORY_HOTPLUG */ + +void radix__kernel_map_pages(struct page *page, int numpages, int enable); + +#ifdef CONFIG_ARCH_WANT_OPTIMIZE_DAX_VMEMMAP +#define vmemmap_can_optimize vmemmap_can_optimize +bool vmemmap_can_optimize(struct vmem_altmap *altmap, struct dev_pagemap *pgmap); +#endif + +#define vmemmap_populate_compound_pages vmemmap_populate_compound_pages +int __meminit vmemmap_populate_compound_pages(unsigned long start_pfn, + unsigned long start, + unsigned long end, int node, + struct dev_pagemap *pgmap); #endif /* __ASSEMBLY__ */ #endif diff --git a/arch/powerpc/include/asm/book3s/64/slice.h b/arch/powerpc/include/asm/book3s/64/slice.h index f0d3194ba41b..5fbe18544cbd 100644 --- a/arch/powerpc/include/asm/book3s/64/slice.h +++ b/arch/powerpc/include/asm/book3s/64/slice.h @@ -2,6 +2,16 @@ #ifndef _ASM_POWERPC_BOOK3S_64_SLICE_H #define _ASM_POWERPC_BOOK3S_64_SLICE_H +#ifndef __ASSEMBLY__ + +#ifdef CONFIG_PPC_64S_HASH_MMU +#ifdef CONFIG_HUGETLB_PAGE +#define HAVE_ARCH_HUGETLB_UNMAPPED_AREA +#endif +#define HAVE_ARCH_UNMAPPED_AREA +#define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN +#endif + #define SLICE_LOW_SHIFT 28 #define SLICE_LOW_TOP (0x100000000ul) #define SLICE_NUM_LOW (SLICE_LOW_TOP >> SLICE_LOW_SHIFT) @@ -13,4 +23,20 @@ #define SLB_ADDR_LIMIT_DEFAULT DEFAULT_MAP_WINDOW_USER64 +struct mm_struct; + +unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len, + unsigned long flags, unsigned int psize, + int topdown); + +unsigned int get_slice_psize(struct mm_struct *mm, unsigned long addr); + +void slice_set_range_psize(struct mm_struct *mm, unsigned long start, + unsigned long len, unsigned int psize); + +void slice_init_new_context_exec(struct mm_struct *mm); +void slice_setup_new_exec(void); + +#endif /* __ASSEMBLY__ */ + #endif /* _ASM_POWERPC_BOOK3S_64_SLICE_H */ diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-hash.h b/arch/powerpc/include/asm/book3s/64/tlbflush-hash.h index 64d02a704bcb..146287d9580f 100644 --- a/arch/powerpc/include/asm/book3s/64/tlbflush-hash.h +++ b/arch/powerpc/include/asm/book3s/64/tlbflush-hash.h @@ -32,6 +32,11 @@ static inline void arch_enter_lazy_mmu_mode(void) if (radix_enabled()) return; + /* + * apply_to_page_range can call us this preempt enabled when + * operating on kernel page tables. + */ + preempt_disable(); batch = this_cpu_ptr(&ppc64_tlb_batch); batch->active = 1; } @@ -47,6 +52,7 @@ static inline void arch_leave_lazy_mmu_mode(void) if (batch->index) __flush_tlb_pending(batch); batch->active = 0; + preempt_enable(); } #define arch_flush_lazy_mmu_mode() do {} while (0) @@ -59,62 +65,15 @@ extern void flush_hash_range(unsigned long number, int local); extern void flush_hash_hugepage(unsigned long vsid, unsigned long addr, pmd_t *pmdp, unsigned int psize, int ssize, unsigned long flags); -static inline void hash__local_flush_tlb_mm(struct mm_struct *mm) -{ -} - -static inline void hash__flush_tlb_mm(struct mm_struct *mm) -{ -} - -static inline void hash__local_flush_all_mm(struct mm_struct *mm) -{ - /* - * There's no Page Walk Cache for hash, so what is needed is - * the same as flush_tlb_mm(), which doesn't really make sense - * with hash. So the only thing we could do is flush the - * entire LPID! Punt for now, as it's not being used. - */ - WARN_ON_ONCE(1); -} - -static inline void hash__flush_all_mm(struct mm_struct *mm) -{ - /* - * There's no Page Walk Cache for hash, so what is needed is - * the same as flush_tlb_mm(), which doesn't really make sense - * with hash. So the only thing we could do is flush the - * entire LPID! Punt for now, as it's not being used. - */ - WARN_ON_ONCE(1); -} - -static inline void hash__local_flush_tlb_page(struct vm_area_struct *vma, - unsigned long vmaddr) -{ -} - -static inline void hash__flush_tlb_page(struct vm_area_struct *vma, - unsigned long vmaddr) -{ -} - -static inline void hash__flush_tlb_range(struct vm_area_struct *vma, - unsigned long start, unsigned long end) -{ -} - -static inline void hash__flush_tlb_kernel_range(unsigned long start, - unsigned long end) -{ -} - struct mmu_gather; extern void hash__tlb_flush(struct mmu_gather *tlb); + +#ifdef CONFIG_PPC_64S_HASH_MMU /* Private function for use by PCI IO mapping code */ -extern void __flush_hash_table_range(struct mm_struct *mm, unsigned long start, - unsigned long end); -extern void flush_tlb_pmd_range(struct mm_struct *mm, pmd_t *pmd, - unsigned long addr); +extern void __flush_hash_table_range(unsigned long start, unsigned long end); +void flush_hash_table_pmd_range(struct mm_struct *mm, pmd_t *pmd, unsigned long addr); +#else +static inline void __flush_hash_table_range(unsigned long start, unsigned long end) { } +#endif #endif /* _ASM_POWERPC_BOOK3S_64_TLBFLUSH_HASH_H */ diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h index ca8db193ae38..a38542259fab 100644 --- a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h +++ b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h @@ -2,10 +2,29 @@ #ifndef _ASM_POWERPC_TLBFLUSH_RADIX_H #define _ASM_POWERPC_TLBFLUSH_RADIX_H +#include <asm/hvcall.h> + +#define RIC_FLUSH_TLB 0 +#define RIC_FLUSH_PWC 1 +#define RIC_FLUSH_ALL 2 + struct vm_area_struct; struct mm_struct; struct mmu_gather; +static inline u64 psize_to_rpti_pgsize(unsigned long psize) +{ + if (psize == MMU_PAGE_4K) + return H_RPTI_PAGE_4K; + if (psize == MMU_PAGE_64K) + return H_RPTI_PAGE_64K; + if (psize == MMU_PAGE_2M) + return H_RPTI_PAGE_2M; + if (psize == MMU_PAGE_1G) + return H_RPTI_PAGE_1G; + return H_RPTI_PAGE_ALL; +} + static inline int mmu_get_ap(int psize) { return mmu_psize_defs[psize].ap; @@ -20,7 +39,7 @@ extern void radix__flush_pwc_lpid(unsigned int lpid); extern void radix__flush_all_lpid(unsigned int lpid); extern void radix__flush_all_lpid_guest(unsigned int lpid); #else -static inline void radix__tlbiel_all(unsigned int action) { WARN_ON(1); }; +static inline void radix__tlbiel_all(unsigned int action) { WARN_ON(1); } static inline void radix__flush_tlb_lpid_page(unsigned int lpid, unsigned long addr, unsigned long page_size) @@ -45,8 +64,12 @@ extern void radix__flush_hugetlb_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); extern void radix__flush_tlb_range_psize(struct mm_struct *mm, unsigned long start, unsigned long end, int psize); +void radix__flush_tlb_pwc_range_psize(struct mm_struct *mm, unsigned long start, + unsigned long end, int psize); extern void radix__flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); +extern void radix__flush_pud_tlb_range(struct vm_area_struct *vma, + unsigned long start, unsigned long end); extern void radix__flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); extern void radix__flush_tlb_kernel_range(unsigned long start, unsigned long end); diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush.h b/arch/powerpc/include/asm/book3s/64/tlbflush.h index dcb5c3839d2f..fd642b729775 100644 --- a/arch/powerpc/include/asm/book3s/64/tlbflush.h +++ b/arch/powerpc/include/asm/book3s/64/tlbflush.h @@ -5,6 +5,7 @@ #define MMU_NO_CONTEXT ~0UL #include <linux/mm_types.h> +#include <linux/mmu_notifier.h> #include <asm/book3s/64/tlbflush-hash.h> #include <asm/book3s/64/tlbflush-radix.h> @@ -14,7 +15,6 @@ enum { TLB_INVAL_SCOPE_LPID = 1, /* invalidate TLBs for current LPID */ }; -#ifdef CONFIG_PPC_NATIVE static inline void tlbiel_all(void) { /* @@ -30,9 +30,6 @@ static inline void tlbiel_all(void) else hash__tlbiel_all(TLB_INVAL_SCOPE_GLOBAL); } -#else -static inline void tlbiel_all(void) { BUG(); }; -#endif static inline void tlbiel_all_lpid(bool radix) { @@ -51,8 +48,15 @@ static inline void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end) { if (radix_enabled()) - return radix__flush_pmd_tlb_range(vma, start, end); - return hash__flush_tlb_range(vma, start, end); + radix__flush_pmd_tlb_range(vma, start, end); +} + +#define __HAVE_ARCH_FLUSH_PUD_TLB_RANGE +static inline void flush_pud_tlb_range(struct vm_area_struct *vma, + unsigned long start, unsigned long end) +{ + if (radix_enabled()) + radix__flush_pud_tlb_range(vma, start, end); } #define __HAVE_ARCH_FLUSH_HUGETLB_TLB_RANGE @@ -61,91 +65,154 @@ static inline void flush_hugetlb_tlb_range(struct vm_area_struct *vma, unsigned long end) { if (radix_enabled()) - return radix__flush_hugetlb_tlb_range(vma, start, end); - return hash__flush_tlb_range(vma, start, end); + radix__flush_hugetlb_tlb_range(vma, start, end); } static inline void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end) { if (radix_enabled()) - return radix__flush_tlb_range(vma, start, end); - return hash__flush_tlb_range(vma, start, end); + radix__flush_tlb_range(vma, start, end); } static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end) { if (radix_enabled()) - return radix__flush_tlb_kernel_range(start, end); - return hash__flush_tlb_kernel_range(start, end); + radix__flush_tlb_kernel_range(start, end); } static inline void local_flush_tlb_mm(struct mm_struct *mm) { if (radix_enabled()) - return radix__local_flush_tlb_mm(mm); - return hash__local_flush_tlb_mm(mm); + radix__local_flush_tlb_mm(mm); } static inline void local_flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr) { if (radix_enabled()) - return radix__local_flush_tlb_page(vma, vmaddr); - return hash__local_flush_tlb_page(vma, vmaddr); + radix__local_flush_tlb_page(vma, vmaddr); } -static inline void local_flush_all_mm(struct mm_struct *mm) +static inline void local_flush_tlb_page_psize(struct mm_struct *mm, + unsigned long vmaddr, int psize) { if (radix_enabled()) - return radix__local_flush_all_mm(mm); - return hash__local_flush_all_mm(mm); + radix__local_flush_tlb_page_psize(mm, vmaddr, psize); } static inline void tlb_flush(struct mmu_gather *tlb) { if (radix_enabled()) - return radix__tlb_flush(tlb); - return hash__tlb_flush(tlb); + radix__tlb_flush(tlb); + else + hash__tlb_flush(tlb); } #ifdef CONFIG_SMP static inline void flush_tlb_mm(struct mm_struct *mm) { if (radix_enabled()) - return radix__flush_tlb_mm(mm); - return hash__flush_tlb_mm(mm); + radix__flush_tlb_mm(mm); } static inline void flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr) { if (radix_enabled()) - return radix__flush_tlb_page(vma, vmaddr); - return hash__flush_tlb_page(vma, vmaddr); -} - -static inline void flush_all_mm(struct mm_struct *mm) -{ - if (radix_enabled()) - return radix__flush_all_mm(mm); - return hash__flush_all_mm(mm); + radix__flush_tlb_page(vma, vmaddr); } #else #define flush_tlb_mm(mm) local_flush_tlb_mm(mm) #define flush_tlb_page(vma, addr) local_flush_tlb_page(vma, addr) -#define flush_all_mm(mm) local_flush_all_mm(mm) #endif /* CONFIG_SMP */ #define flush_tlb_fix_spurious_fault flush_tlb_fix_spurious_fault static inline void flush_tlb_fix_spurious_fault(struct vm_area_struct *vma, - unsigned long address) + unsigned long address, + pte_t *ptep) +{ + /* + * Book3S 64 does not require spurious fault flushes because the PTE + * must be re-fetched in case of an access permission problem. So the + * only reason for a spurious fault should be concurrent modification + * to the PTE, in which case the PTE will eventually be re-fetched by + * the MMU when it attempts the access again. + * + * See: Power ISA Version 3.1B, 6.10.1.2 Modifying a Translation Table + * Entry, Setting a Reference or Change Bit or Upgrading Access + * Authority (PTE Subject to Atomic Hardware Updates): + * + * "If the only change being made to a valid PTE that is subject to + * atomic hardware updates is to set the Reference or Change bit to + * 1 or to upgrade access authority, a simpler sequence suffices + * because the translation hardware will refetch the PTE if an + * access is attempted for which the only problems were reference + * and/or change bits needing to be set or insufficient access + * authority." + * + * The nest MMU in POWER9 does not perform this PTE re-fetch, but + * it avoids the spurious fault problem by flushing the TLB before + * upgrading PTE permissions, see radix__ptep_set_access_flags. + */ +} + +static inline bool __pte_flags_need_flush(unsigned long oldval, + unsigned long newval) +{ + unsigned long delta = oldval ^ newval; + + /* + * The return value of this function doesn't matter for hash, + * ptep_modify_prot_start() does a pte_update() which does or schedules + * any necessary hash table update and flush. + */ + if (!radix_enabled()) + return true; + + /* + * We do not expect kernel mappings or non-PTEs or not-present PTEs. + */ + VM_WARN_ON_ONCE(oldval & _PAGE_PRIVILEGED); + VM_WARN_ON_ONCE(newval & _PAGE_PRIVILEGED); + VM_WARN_ON_ONCE(!(oldval & _PAGE_PTE)); + VM_WARN_ON_ONCE(!(newval & _PAGE_PTE)); + VM_WARN_ON_ONCE(!(oldval & _PAGE_PRESENT)); + VM_WARN_ON_ONCE(!(newval & _PAGE_PRESENT)); + + /* + * Must flush on any change except READ, WRITE, EXEC, DIRTY, ACCESSED. + * + * In theory, some changed software bits could be tolerated, in + * practice those should rarely if ever matter. + */ + + if (delta & ~(_PAGE_RWX | _PAGE_DIRTY | _PAGE_ACCESSED)) + return true; + + /* + * If any of the above was present in old but cleared in new, flush. + * With the exception of _PAGE_ACCESSED, don't worry about flushing + * if that was cleared (see the comment in ptep_clear_flush_young()). + */ + if ((delta & ~_PAGE_ACCESSED) & oldval) + return true; + + return false; +} + +static inline bool pte_needs_flush(pte_t oldpte, pte_t newpte) +{ + return __pte_flags_need_flush(pte_val(oldpte), pte_val(newpte)); +} +#define pte_needs_flush pte_needs_flush + +static inline bool huge_pmd_needs_flush(pmd_t oldpmd, pmd_t newpmd) { - /* See ptep_set_access_flags comment */ - if (atomic_read(&vma->vm_mm->context.copros) > 0) - flush_tlb_page(vma, address); + return __pte_flags_need_flush(pmd_val(oldpmd), pmd_val(newpmd)); } +#define huge_pmd_needs_flush huge_pmd_needs_flush extern bool tlbie_capable; extern bool tlbie_enabled; diff --git a/arch/powerpc/include/asm/book3s/pgtable.h b/arch/powerpc/include/asm/book3s/pgtable.h index 0e1263455d73..f42d68c6b314 100644 --- a/arch/powerpc/include/asm/book3s/pgtable.h +++ b/arch/powerpc/include/asm/book3s/pgtable.h @@ -8,34 +8,4 @@ #include <asm/book3s/32/pgtable.h> #endif -#define FIRST_USER_ADDRESS 0UL -#ifndef __ASSEMBLY__ -/* Insert a PTE, top-level function is out of line. It uses an inline - * low level function in the respective pgtable-* files - */ -extern void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, - pte_t pte); - - -#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS -extern int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address, - pte_t *ptep, pte_t entry, int dirty); - -struct file; -extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, - unsigned long size, pgprot_t vma_prot); -#define __HAVE_PHYS_MEM_ACCESS_PROT - -/* - * This gets called at the end of handling a page fault, when - * the kernel has put a new PTE into the page table for the process. - * We use it to ensure coherency between the i-cache and d-cache - * for the page which has just been mapped in. - * On machines which use an MMU hash table, we use this to put a - * corresponding HPTE into the hash table ahead of time, instead of - * waiting for the inevitable extra hash-table miss exception. - */ -void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep); - -#endif /* __ASSEMBLY__ */ #endif diff --git a/arch/powerpc/include/asm/bpf_perf_event.h b/arch/powerpc/include/asm/bpf_perf_event.h new file mode 100644 index 000000000000..e8a7b4ffb58c --- /dev/null +++ b/arch/powerpc/include/asm/bpf_perf_event.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_POWERPC_BPF_PERF_EVENT_H +#define _ASM_POWERPC_BPF_PERF_EVENT_H + +#include <asm/ptrace.h> + +typedef struct user_pt_regs bpf_user_pt_regs_t; + +#endif /* _ASM_POWERPC_BPF_PERF_EVENT_H */ diff --git a/arch/powerpc/include/asm/btext.h b/arch/powerpc/include/asm/btext.h index 461b0f193864..860f8868f11e 100644 --- a/arch/powerpc/include/asm/btext.h +++ b/arch/powerpc/include/asm/btext.h @@ -23,12 +23,12 @@ extern void btext_unmap(void); extern void btext_drawchar(char c); extern void btext_drawstring(const char *str); -extern void btext_drawhex(unsigned long v); -extern void btext_drawtext(const char *c, unsigned int len); +void __init btext_drawhex(unsigned long v); +void __init btext_drawtext(const char *c, unsigned int len); -extern void btext_clearscreen(void); -extern void btext_flushscreen(void); -extern void btext_flushline(void); +void __init btext_clearscreen(void); +void __init btext_flushscreen(void); +void __init btext_flushline(void); #endif /* __KERNEL__ */ #endif /* __PPC_BTEXT_H */ diff --git a/arch/powerpc/include/asm/bug.h b/arch/powerpc/include/asm/bug.h index 338f36cd9934..1db485aacbd9 100644 --- a/arch/powerpc/include/asm/bug.h +++ b/arch/powerpc/include/asm/bug.h @@ -12,7 +12,8 @@ #ifdef CONFIG_DEBUG_BUGVERBOSE .macro EMIT_BUG_ENTRY addr,file,line,flags .section __bug_table,"aw" -5001: PPC_LONG \addr, 5002f +5001: .4byte \addr - . + .4byte 5002f - . .short \line, \flags .org 5001b+BUG_ENTRY_SIZE .previous @@ -23,7 +24,7 @@ #else .macro EMIT_BUG_ENTRY addr,file,line,flags .section __bug_table,"aw" -5001: PPC_LONG \addr +5001: .4byte \addr - . .short \flags .org 5001b+BUG_ENTRY_SIZE .previous @@ -36,15 +37,16 @@ #ifdef CONFIG_DEBUG_BUGVERBOSE #define _EMIT_BUG_ENTRY \ ".section __bug_table,\"aw\"\n" \ - "2:\t" PPC_LONG "1b, %0\n" \ - "\t.short %1, %2\n" \ + "2: .4byte 1b - .\n" \ + " .4byte %0 - .\n" \ + " .short %1, %2\n" \ ".org 2b+%3\n" \ ".previous\n" #else #define _EMIT_BUG_ENTRY \ ".section __bug_table,\"aw\"\n" \ - "2:\t" PPC_LONG "1b\n" \ - "\t.short %2\n" \ + "2: .4byte 1b - .\n" \ + " .short %2\n" \ ".org 2b+%3\n" \ ".previous\n" #endif @@ -68,7 +70,11 @@ BUG_ENTRY("twi 31, 0, 0", 0); \ unreachable(); \ } while (0) +#define HAVE_ARCH_BUG + +#define __WARN_FLAGS(flags) BUG_ENTRY("twi 31, 0, 0", BUGFLAG_WARNING | (flags)) +#ifdef CONFIG_PPC64 #define BUG_ON(x) do { \ if (__builtin_constant_p(x)) { \ if (x) \ @@ -78,8 +84,6 @@ } \ } while (0) -#define __WARN_FLAGS(flags) BUG_ENTRY("twi 31, 0, 0", BUGFLAG_WARNING | (flags)) - #define WARN_ON(x) ({ \ int __ret_warn_on = !!(x); \ if (__builtin_constant_p(__ret_warn_on)) { \ @@ -93,9 +97,10 @@ unlikely(__ret_warn_on); \ }) -#define HAVE_ARCH_BUG #define HAVE_ARCH_BUG_ON #define HAVE_ARCH_WARN_ON +#endif + #endif /* __ASSEMBLY __ */ #else #ifdef __ASSEMBLY__ @@ -106,16 +111,20 @@ #endif #endif /* CONFIG_BUG */ +#define EMIT_WARN_ENTRY EMIT_BUG_ENTRY + #include <asm-generic/bug.h> #ifndef __ASSEMBLY__ struct pt_regs; -extern int do_page_fault(struct pt_regs *, unsigned long, unsigned long); -extern void bad_page_fault(struct pt_regs *, unsigned long, int); +void hash__do_page_fault(struct pt_regs *); +void bad_page_fault(struct pt_regs *, int); +void emulate_single_step(struct pt_regs *regs); extern void _exception(int, struct pt_regs *, int, unsigned long); extern void _exception_pkey(struct pt_regs *, unsigned long, int); extern void die(const char *, struct pt_regs *, long); +void die_mce(const char *str, struct pt_regs *regs, long err); extern bool die_will_crash(void); extern void panic_flush_kmsg_start(void); extern void panic_flush_kmsg_end(void); diff --git a/arch/powerpc/include/asm/bugs.h b/arch/powerpc/include/asm/bugs.h deleted file mode 100644 index 01b8f6ca4dbb..000000000000 --- a/arch/powerpc/include/asm/bugs.h +++ /dev/null @@ -1,15 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -#ifndef _ASM_POWERPC_BUGS_H -#define _ASM_POWERPC_BUGS_H - -/* - */ - -/* - * This file is included by 'init/main.c' to check for - * architecture-dependent bugs. - */ - -static inline void check_bugs(void) { } - -#endif /* _ASM_POWERPC_BUGS_H */ diff --git a/arch/powerpc/include/asm/cache.h b/arch/powerpc/include/asm/cache.h index 72b81015cebe..69232231d270 100644 --- a/arch/powerpc/include/asm/cache.h +++ b/arch/powerpc/include/asm/cache.h @@ -6,7 +6,7 @@ /* bytes per L1 cache line */ -#if defined(CONFIG_PPC_8xx) || defined(CONFIG_403GCX) +#if defined(CONFIG_PPC_8xx) #define L1_CACHE_SHIFT 4 #define MAX_COPY_PREFETCH 1 #define IFETCH_ALIGN_SHIFT 2 @@ -33,6 +33,10 @@ #define IFETCH_ALIGN_BYTES (1 << IFETCH_ALIGN_SHIFT) +#ifdef CONFIG_NOT_COHERENT_CACHE +#define ARCH_DMA_MINALIGN L1_CACHE_BYTES +#endif + #if !defined(__ASSEMBLY__) #ifdef CONFIG_PPC64 @@ -97,7 +101,7 @@ static inline u32 l1_icache_bytes(void) #endif -#define __read_mostly __attribute__((__section__(".data..read_mostly"))) +#define __read_mostly __section(".data..read_mostly") #ifdef CONFIG_PPC_BOOK3S_32 extern long _get_L2CR(void); diff --git a/arch/powerpc/include/asm/cacheflush.h b/arch/powerpc/include/asm/cacheflush.h index 4a1c9f0200e1..ef7d2de33b89 100644 --- a/arch/powerpc/include/asm/cacheflush.h +++ b/arch/powerpc/include/asm/cacheflush.h @@ -4,22 +4,15 @@ #ifndef _ASM_POWERPC_CACHEFLUSH_H #define _ASM_POWERPC_CACHEFLUSH_H -#ifdef __KERNEL__ - #include <linux/mm.h> #include <asm/cputable.h> +#include <asm/cpu_has_feature.h> /* - * No cache flushing is required when address mappings are changed, - * because the caches on PowerPCs are physically addressed. + * This flag is used to indicate that the page pointed to by a pte is clean + * and does not require cleaning before returning it to the user. */ -#define flush_cache_all() do { } while (0) -#define flush_cache_mm(mm) do { } while (0) -#define flush_cache_dup_mm(mm) do { } while (0) -#define flush_cache_range(vma, start, end) do { } while (0) -#define flush_cache_page(vma, vmaddr, pfn) do { } while (0) -#define flush_icache_page(vma, page) do { } while (0) -#define flush_cache_vunmap(start, end) do { } while (0) +#define PG_dcache_clean PG_arch_1 #ifdef CONFIG_PPC_BOOK3S_64 /* @@ -33,21 +26,38 @@ static inline void flush_cache_vmap(unsigned long start, unsigned long end) { asm volatile("ptesync" ::: "memory"); } -#else -static inline void flush_cache_vmap(unsigned long start, unsigned long end) { } -#endif +#define flush_cache_vmap flush_cache_vmap +#endif /* CONFIG_PPC_BOOK3S_64 */ #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 -extern void flush_dcache_page(struct page *page); -#define flush_dcache_mmap_lock(mapping) do { } while (0) -#define flush_dcache_mmap_unlock(mapping) do { } while (0) +/* + * This is called when a page has been modified by the kernel. + * It just marks the page as not i-cache clean. We do the i-cache + * flush later when the page is given to a user process, if necessary. + */ +static inline void flush_dcache_folio(struct folio *folio) +{ + if (cpu_has_feature(CPU_FTR_COHERENT_ICACHE)) + return; + /* avoid an atomic op if possible */ + if (test_bit(PG_dcache_clean, &folio->flags)) + clear_bit(PG_dcache_clean, &folio->flags); +} +#define flush_dcache_folio flush_dcache_folio + +static inline void flush_dcache_page(struct page *page) +{ + flush_dcache_folio(page_folio(page)); +} void flush_icache_range(unsigned long start, unsigned long stop); -extern void flush_icache_user_range(struct vm_area_struct *vma, - struct page *page, unsigned long addr, - int len); -extern void flush_dcache_icache_page(struct page *page); -void __flush_dcache_icache(void *page); +#define flush_icache_range flush_icache_range + +void flush_icache_user_page(struct vm_area_struct *vma, struct page *page, + unsigned long addr, int len); +#define flush_icache_user_page flush_icache_user_page + +void flush_dcache_icache_folio(struct folio *folio); /** * flush_dcache_range(): Write any modified data cache blocks out to memory and @@ -65,17 +75,13 @@ static inline void flush_dcache_range(unsigned long start, unsigned long stop) unsigned long size = stop - (unsigned long)addr + (bytes - 1); unsigned long i; - if (IS_ENABLED(CONFIG_PPC64)) { + if (IS_ENABLED(CONFIG_PPC64)) mb(); /* sync */ - isync(); - } for (i = 0; i < size >> shift; i++, addr += bytes) dcbf(addr); mb(); /* sync */ - if (IS_ENABLED(CONFIG_PPC64)) - isync(); } /* @@ -115,14 +121,16 @@ static inline void invalidate_dcache_range(unsigned long start, mb(); /* sync */ } -#define copy_to_user_page(vma, page, vaddr, dst, src, len) \ - do { \ - memcpy(dst, src, len); \ - flush_icache_user_range(vma, page, vaddr, len); \ - } while (0) -#define copy_from_user_page(vma, page, vaddr, dst, src, len) \ - memcpy(dst, src, len) +#ifdef CONFIG_4xx +static inline void flush_instruction_cache(void) +{ + iccci((void *)KERNELBASE); + isync(); +} +#else +void flush_instruction_cache(void); +#endif -#endif /* __KERNEL__ */ +#include <asm-generic/cacheflush.h> #endif /* _ASM_POWERPC_CACHEFLUSH_H */ diff --git a/arch/powerpc/include/asm/checksum.h b/arch/powerpc/include/asm/checksum.h index 9cce06194dcc..4b573a3b7e17 100644 --- a/arch/powerpc/include/asm/checksum.h +++ b/arch/powerpc/include/asm/checksum.h @@ -18,19 +18,18 @@ * Like csum_partial, this must be called with even lengths, * except for the last fragment. */ -extern __wsum csum_partial_copy_generic(const void *src, void *dst, - int len, __wsum sum, - int *src_err, int *dst_err); +extern __wsum csum_partial_copy_generic(const void *src, void *dst, int len); #define _HAVE_ARCH_COPY_AND_CSUM_FROM_USER extern __wsum csum_and_copy_from_user(const void __user *src, void *dst, - int len, __wsum sum, int *err_ptr); + int len); #define HAVE_CSUM_COPY_USER extern __wsum csum_and_copy_to_user(const void *src, void __user *dst, - int len, __wsum sum, int *err_ptr); + int len); -#define csum_partial_copy_nocheck(src, dst, len, sum) \ - csum_partial_copy_generic((src), (dst), (len), (sum), NULL, NULL) +#define _HAVE_ARCH_CSUM_AND_COPY +#define csum_partial_copy_nocheck(src, dst, len) \ + csum_partial_copy_generic((src), (dst), (len)) /* @@ -39,14 +38,15 @@ extern __wsum csum_and_copy_to_user(const void *src, void __user *dst, */ static inline __sum16 csum_fold(__wsum sum) { - unsigned int tmp; - - /* swap the two 16-bit halves of sum */ - __asm__("rlwinm %0,%1,16,0,31" : "=r" (tmp) : "r" (sum)); - /* if there is a carry from adding the two 16-bit halves, - it will carry from the lower half into the upper half, - giving us the correct sum in the upper half. */ - return (__force __sum16)(~((__force u32)sum + tmp) >> 16); + u32 tmp = (__force u32)sum; + + /* + * swap the two 16-bit halves of sum + * if there is a carry from adding the two 16-bit halves, + * it will carry from the lower half into the upper half, + * giving us the correct sum in the upper half. + */ + return (__force __sum16)(~(tmp + rol32(tmp, 16)) >> 16); } static inline u32 from64to32(u64 x) @@ -92,20 +92,19 @@ static inline __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr, __u32 len, } #define HAVE_ARCH_CSUM_ADD -static inline __wsum csum_add(__wsum csum, __wsum addend) +static __always_inline __wsum csum_add(__wsum csum, __wsum addend) { #ifdef __powerpc64__ u64 res = (__force u64)csum; -#endif + + res += (__force u64)addend; + return (__force __wsum)((u32)res + (res >> 32)); +#else if (__builtin_constant_p(csum) && csum == 0) return addend; if (__builtin_constant_p(addend) && addend == 0) return csum; -#ifdef __powerpc64__ - res += (__force u64)addend; - return (__force __wsum)((u32)res + (res >> 32)); -#else asm("addc %0,%0,%1;" "addze %0,%0;" : "+r" (csum) : "r" (addend) : "xer"); @@ -113,6 +112,13 @@ static inline __wsum csum_add(__wsum csum, __wsum addend) #endif } +#define HAVE_ARCH_CSUM_SHIFT +static __always_inline __wsum csum_shift(__wsum sum, int offset) +{ + /* rotate sum to align it with a 16b boundary */ + return (__force __wsum)rol32((__force u32)sum, (offset & 1) << 3); +} + /* * This is a version of ip_compute_csum() optimized for IP headers, * which always checksum on 4 octet boundaries. ihl is the number @@ -164,7 +170,7 @@ static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl) */ __wsum __csum_partial(const void *buff, int len, __wsum sum); -static inline __wsum csum_partial(const void *buff, int len, __wsum sum) +static __always_inline __wsum csum_partial(const void *buff, int len, __wsum sum) { if (__builtin_constant_p(len) && len <= 16 && (len & 1) == 0) { if (len == 2) diff --git a/arch/powerpc/include/asm/clocksource.h b/arch/powerpc/include/asm/clocksource.h new file mode 100644 index 000000000000..0a26ef13a34a --- /dev/null +++ b/arch/powerpc/include/asm/clocksource.h @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_POWERPC_CLOCKSOURCE_H +#define _ASM_POWERPC_CLOCKSOURCE_H + +#include <asm/vdso/clocksource.h> + +#endif /* _ASM_POWERPC_CLOCKSOURCE_H */ diff --git a/arch/powerpc/include/asm/cmpxchg.h b/arch/powerpc/include/asm/cmpxchg.h index 27183871eb3b..dbb50c06f0bf 100644 --- a/arch/powerpc/include/asm/cmpxchg.h +++ b/arch/powerpc/include/asm/cmpxchg.h @@ -6,7 +6,6 @@ #include <linux/compiler.h> #include <asm/synch.h> #include <linux/bug.h> -#include <asm/asm-405.h> #ifdef __BIG_ENDIAN #define BITOFF_CAL(size, off) ((sizeof(u32) - size - off) * BITS_PER_BYTE) @@ -29,7 +28,6 @@ static inline u32 __xchg_##type##sfx(volatile void *p, u32 val) \ "1: lwarx %0,0,%3\n" \ " andc %1,%0,%5\n" \ " or %1,%1,%4\n" \ - PPC405_ERR77(0,%3) \ " stwcx. %1,0,%3\n" \ " bne- 1b\n" \ : "=&r" (prev), "=&r" (tmp), "+m" (*(u32*)p) \ @@ -60,7 +58,6 @@ u32 __cmpxchg_##type##sfx(volatile void *p, u32 old, u32 new) \ " bne- 2f\n" \ " andc %1,%0,%6\n" \ " or %1,%1,%5\n" \ - PPC405_ERR77(0,%3) \ " stwcx. %1,0,%3\n" \ " bne- 1b\n" \ br2 \ @@ -80,10 +77,76 @@ u32 __cmpxchg_##type##sfx(volatile void *p, u32 old, u32 new) \ * the previous value stored there. */ +#ifndef CONFIG_PPC_HAS_LBARX_LHARX XCHG_GEN(u8, _local, "memory"); XCHG_GEN(u8, _relaxed, "cc"); XCHG_GEN(u16, _local, "memory"); XCHG_GEN(u16, _relaxed, "cc"); +#else +static __always_inline unsigned long +__xchg_u8_local(volatile void *p, unsigned long val) +{ + unsigned long prev; + + __asm__ __volatile__( +"1: lbarx %0,0,%2 # __xchg_u8_local\n" +" stbcx. %3,0,%2 \n" +" bne- 1b" + : "=&r" (prev), "+m" (*(volatile unsigned char *)p) + : "r" (p), "r" (val) + : "cc", "memory"); + + return prev; +} + +static __always_inline unsigned long +__xchg_u8_relaxed(u8 *p, unsigned long val) +{ + unsigned long prev; + + __asm__ __volatile__( +"1: lbarx %0,0,%2 # __xchg_u8_relaxed\n" +" stbcx. %3,0,%2\n" +" bne- 1b" + : "=&r" (prev), "+m" (*p) + : "r" (p), "r" (val) + : "cc"); + + return prev; +} + +static __always_inline unsigned long +__xchg_u16_local(volatile void *p, unsigned long val) +{ + unsigned long prev; + + __asm__ __volatile__( +"1: lharx %0,0,%2 # __xchg_u16_local\n" +" sthcx. %3,0,%2\n" +" bne- 1b" + : "=&r" (prev), "+m" (*(volatile unsigned short *)p) + : "r" (p), "r" (val) + : "cc", "memory"); + + return prev; +} + +static __always_inline unsigned long +__xchg_u16_relaxed(u16 *p, unsigned long val) +{ + unsigned long prev; + + __asm__ __volatile__( +"1: lharx %0,0,%2 # __xchg_u16_relaxed\n" +" sthcx. %3,0,%2\n" +" bne- 1b" + : "=&r" (prev), "+m" (*p) + : "r" (p), "r" (val) + : "cc"); + + return prev; +} +#endif static __always_inline unsigned long __xchg_u32_local(volatile void *p, unsigned long val) @@ -92,7 +155,6 @@ __xchg_u32_local(volatile void *p, unsigned long val) __asm__ __volatile__( "1: lwarx %0,0,%2 \n" - PPC405_ERR77(0,%2) " stwcx. %3,0,%2 \n\ bne- 1b" : "=&r" (prev), "+m" (*(volatile unsigned int *)p) @@ -109,7 +171,6 @@ __xchg_u32_relaxed(u32 *p, unsigned long val) __asm__ __volatile__( "1: lwarx %0,0,%2\n" - PPC405_ERR77(0, %2) " stwcx. %3,0,%2\n" " bne- 1b" : "=&r" (prev), "+m" (*p) @@ -127,7 +188,6 @@ __xchg_u64_local(volatile void *p, unsigned long val) __asm__ __volatile__( "1: ldarx %0,0,%2 \n" - PPC405_ERR77(0,%2) " stdcx. %3,0,%2 \n\ bne- 1b" : "=&r" (prev), "+m" (*(volatile unsigned long *)p) @@ -144,7 +204,6 @@ __xchg_u64_relaxed(u64 *p, unsigned long val) __asm__ __volatile__( "1: ldarx %0,0,%2\n" - PPC405_ERR77(0, %2) " stdcx. %3,0,%2\n" " bne- 1b" : "=&r" (prev), "+m" (*p) @@ -170,7 +229,7 @@ __xchg_local(void *ptr, unsigned long x, unsigned int size) return __xchg_u64_local(ptr, x); #endif } - BUILD_BUG_ON_MSG(1, "Unsupported size for __xchg"); + BUILD_BUG_ON_MSG(1, "Unsupported size for __xchg_local"); return x; } @@ -189,27 +248,28 @@ __xchg_relaxed(void *ptr, unsigned long x, unsigned int size) return __xchg_u64_relaxed(ptr, x); #endif } - BUILD_BUG_ON_MSG(1, "Unsupported size for __xchg_local"); + BUILD_BUG_ON_MSG(1, "Unsupported size for __xchg_relaxed"); return x; } -#define xchg_local(ptr,x) \ +#define arch_xchg_local(ptr,x) \ ({ \ __typeof__(*(ptr)) _x_ = (x); \ (__typeof__(*(ptr))) __xchg_local((ptr), \ (unsigned long)_x_, sizeof(*(ptr))); \ }) -#define xchg_relaxed(ptr, x) \ +#define arch_xchg_relaxed(ptr, x) \ ({ \ __typeof__(*(ptr)) _x_ = (x); \ (__typeof__(*(ptr))) __xchg_relaxed((ptr), \ (unsigned long)_x_, sizeof(*(ptr))); \ }) + /* * Compare and exchange - if *p == old, set it to new, * and return the old value of *p. */ - +#ifndef CONFIG_PPC_HAS_LBARX_LHARX CMPXCHG_GEN(u8, , PPC_ATOMIC_ENTRY_BARRIER, PPC_ATOMIC_EXIT_BARRIER, "memory"); CMPXCHG_GEN(u8, _local, , , "memory"); CMPXCHG_GEN(u8, _acquire, , PPC_ACQUIRE_BARRIER, "memory"); @@ -218,6 +278,168 @@ CMPXCHG_GEN(u16, , PPC_ATOMIC_ENTRY_BARRIER, PPC_ATOMIC_EXIT_BARRIER, "memory"); CMPXCHG_GEN(u16, _local, , , "memory"); CMPXCHG_GEN(u16, _acquire, , PPC_ACQUIRE_BARRIER, "memory"); CMPXCHG_GEN(u16, _relaxed, , , "cc"); +#else +static __always_inline unsigned long +__cmpxchg_u8(volatile unsigned char *p, unsigned long old, unsigned long new) +{ + unsigned int prev; + + __asm__ __volatile__ ( + PPC_ATOMIC_ENTRY_BARRIER +"1: lbarx %0,0,%2 # __cmpxchg_u8\n" +" cmpw 0,%0,%3\n" +" bne- 2f\n" +" stbcx. %4,0,%2\n" +" bne- 1b" + PPC_ATOMIC_EXIT_BARRIER + "\n\ +2:" + : "=&r" (prev), "+m" (*p) + : "r" (p), "r" (old), "r" (new) + : "cc", "memory"); + + return prev; +} + +static __always_inline unsigned long +__cmpxchg_u8_local(volatile unsigned char *p, unsigned long old, + unsigned long new) +{ + unsigned int prev; + + __asm__ __volatile__ ( +"1: lbarx %0,0,%2 # __cmpxchg_u8_local\n" +" cmpw 0,%0,%3\n" +" bne- 2f\n" +" stbcx. %4,0,%2\n" +" bne- 1b\n" +"2:" + : "=&r" (prev), "+m" (*p) + : "r" (p), "r" (old), "r" (new) + : "cc", "memory"); + + return prev; +} + +static __always_inline unsigned long +__cmpxchg_u8_relaxed(u8 *p, unsigned long old, unsigned long new) +{ + unsigned long prev; + + __asm__ __volatile__ ( +"1: lbarx %0,0,%2 # __cmpxchg_u8_relaxed\n" +" cmpw 0,%0,%3\n" +" bne- 2f\n" +" stbcx. %4,0,%2\n" +" bne- 1b\n" +"2:" + : "=&r" (prev), "+m" (*p) + : "r" (p), "r" (old), "r" (new) + : "cc"); + + return prev; +} + +static __always_inline unsigned long +__cmpxchg_u8_acquire(u8 *p, unsigned long old, unsigned long new) +{ + unsigned long prev; + + __asm__ __volatile__ ( +"1: lbarx %0,0,%2 # __cmpxchg_u8_acquire\n" +" cmpw 0,%0,%3\n" +" bne- 2f\n" +" stbcx. %4,0,%2\n" +" bne- 1b\n" + PPC_ACQUIRE_BARRIER +"2:" + : "=&r" (prev), "+m" (*p) + : "r" (p), "r" (old), "r" (new) + : "cc", "memory"); + + return prev; +} + +static __always_inline unsigned long +__cmpxchg_u16(volatile unsigned short *p, unsigned long old, unsigned long new) +{ + unsigned int prev; + + __asm__ __volatile__ ( + PPC_ATOMIC_ENTRY_BARRIER +"1: lharx %0,0,%2 # __cmpxchg_u16\n" +" cmpw 0,%0,%3\n" +" bne- 2f\n" +" sthcx. %4,0,%2\n" +" bne- 1b\n" + PPC_ATOMIC_EXIT_BARRIER +"2:" + : "=&r" (prev), "+m" (*p) + : "r" (p), "r" (old), "r" (new) + : "cc", "memory"); + + return prev; +} + +static __always_inline unsigned long +__cmpxchg_u16_local(volatile unsigned short *p, unsigned long old, + unsigned long new) +{ + unsigned int prev; + + __asm__ __volatile__ ( +"1: lharx %0,0,%2 # __cmpxchg_u16_local\n" +" cmpw 0,%0,%3\n" +" bne- 2f\n" +" sthcx. %4,0,%2\n" +" bne- 1b" +"2:" + : "=&r" (prev), "+m" (*p) + : "r" (p), "r" (old), "r" (new) + : "cc", "memory"); + + return prev; +} + +static __always_inline unsigned long +__cmpxchg_u16_relaxed(u16 *p, unsigned long old, unsigned long new) +{ + unsigned long prev; + + __asm__ __volatile__ ( +"1: lharx %0,0,%2 # __cmpxchg_u16_relaxed\n" +" cmpw 0,%0,%3\n" +" bne- 2f\n" +" sthcx. %4,0,%2\n" +" bne- 1b\n" +"2:" + : "=&r" (prev), "+m" (*p) + : "r" (p), "r" (old), "r" (new) + : "cc"); + + return prev; +} + +static __always_inline unsigned long +__cmpxchg_u16_acquire(u16 *p, unsigned long old, unsigned long new) +{ + unsigned long prev; + + __asm__ __volatile__ ( +"1: lharx %0,0,%2 # __cmpxchg_u16_acquire\n" +" cmpw 0,%0,%3\n" +" bne- 2f\n" +" sthcx. %4,0,%2\n" +" bne- 1b\n" + PPC_ACQUIRE_BARRIER +"2:" + : "=&r" (prev), "+m" (*p) + : "r" (p), "r" (old), "r" (new) + : "cc", "memory"); + + return prev; +} +#endif static __always_inline unsigned long __cmpxchg_u32(volatile unsigned int *p, unsigned long old, unsigned long new) @@ -229,7 +451,6 @@ __cmpxchg_u32(volatile unsigned int *p, unsigned long old, unsigned long new) "1: lwarx %0,0,%2 # __cmpxchg_u32\n\ cmpw 0,%0,%3\n\ bne- 2f\n" - PPC405_ERR77(0,%2) " stwcx. %4,0,%2\n\ bne- 1b" PPC_ATOMIC_EXIT_BARRIER @@ -252,7 +473,6 @@ __cmpxchg_u32_local(volatile unsigned int *p, unsigned long old, "1: lwarx %0,0,%2 # __cmpxchg_u32\n\ cmpw 0,%0,%3\n\ bne- 2f\n" - PPC405_ERR77(0,%2) " stwcx. %4,0,%2\n\ bne- 1b" "\n\ @@ -273,7 +493,6 @@ __cmpxchg_u32_relaxed(u32 *p, unsigned long old, unsigned long new) "1: lwarx %0,0,%2 # __cmpxchg_u32_relaxed\n" " cmpw 0,%0,%3\n" " bne- 2f\n" - PPC405_ERR77(0, %2) " stwcx. %4,0,%2\n" " bne- 1b\n" "2:" @@ -301,7 +520,6 @@ __cmpxchg_u32_acquire(u32 *p, unsigned long old, unsigned long new) "1: lwarx %0,0,%2 # __cmpxchg_u32_acquire\n" " cmpw 0,%0,%3\n" " bne- 2f\n" - PPC405_ERR77(0, %2) " stwcx. %4,0,%2\n" " bne- 1b\n" PPC_ACQUIRE_BARRIER @@ -478,7 +696,7 @@ __cmpxchg_acquire(void *ptr, unsigned long old, unsigned long new, BUILD_BUG_ON_MSG(1, "Unsupported size for __cmpxchg_acquire"); return old; } -#define cmpxchg(ptr, o, n) \ +#define arch_cmpxchg(ptr, o, n) \ ({ \ __typeof__(*(ptr)) _o_ = (o); \ __typeof__(*(ptr)) _n_ = (n); \ @@ -487,7 +705,7 @@ __cmpxchg_acquire(void *ptr, unsigned long old, unsigned long new, }) -#define cmpxchg_local(ptr, o, n) \ +#define arch_cmpxchg_local(ptr, o, n) \ ({ \ __typeof__(*(ptr)) _o_ = (o); \ __typeof__(*(ptr)) _n_ = (n); \ @@ -495,7 +713,7 @@ __cmpxchg_acquire(void *ptr, unsigned long old, unsigned long new, (unsigned long)_n_, sizeof(*(ptr))); \ }) -#define cmpxchg_relaxed(ptr, o, n) \ +#define arch_cmpxchg_relaxed(ptr, o, n) \ ({ \ __typeof__(*(ptr)) _o_ = (o); \ __typeof__(*(ptr)) _n_ = (n); \ @@ -504,7 +722,7 @@ __cmpxchg_acquire(void *ptr, unsigned long old, unsigned long new, sizeof(*(ptr))); \ }) -#define cmpxchg_acquire(ptr, o, n) \ +#define arch_cmpxchg_acquire(ptr, o, n) \ ({ \ __typeof__(*(ptr)) _o_ = (o); \ __typeof__(*(ptr)) _n_ = (n); \ @@ -513,29 +731,29 @@ __cmpxchg_acquire(void *ptr, unsigned long old, unsigned long new, sizeof(*(ptr))); \ }) #ifdef CONFIG_PPC64 -#define cmpxchg64(ptr, o, n) \ +#define arch_cmpxchg64(ptr, o, n) \ ({ \ BUILD_BUG_ON(sizeof(*(ptr)) != 8); \ - cmpxchg((ptr), (o), (n)); \ + arch_cmpxchg((ptr), (o), (n)); \ }) -#define cmpxchg64_local(ptr, o, n) \ +#define arch_cmpxchg64_local(ptr, o, n) \ ({ \ BUILD_BUG_ON(sizeof(*(ptr)) != 8); \ - cmpxchg_local((ptr), (o), (n)); \ + arch_cmpxchg_local((ptr), (o), (n)); \ }) -#define cmpxchg64_relaxed(ptr, o, n) \ +#define arch_cmpxchg64_relaxed(ptr, o, n) \ ({ \ BUILD_BUG_ON(sizeof(*(ptr)) != 8); \ - cmpxchg_relaxed((ptr), (o), (n)); \ + arch_cmpxchg_relaxed((ptr), (o), (n)); \ }) -#define cmpxchg64_acquire(ptr, o, n) \ +#define arch_cmpxchg64_acquire(ptr, o, n) \ ({ \ BUILD_BUG_ON(sizeof(*(ptr)) != 8); \ - cmpxchg_acquire((ptr), (o), (n)); \ + arch_cmpxchg_acquire((ptr), (o), (n)); \ }) #else #include <asm-generic/cmpxchg-local.h> -#define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n)) +#define arch_cmpxchg64_local(ptr, o, n) __generic_cmpxchg64_local((ptr), (o), (n)) #endif #endif /* __KERNEL__ */ diff --git a/arch/powerpc/include/asm/code-patching.h b/arch/powerpc/include/asm/code-patching.h index 898b54262881..0e29ccf903d0 100644 --- a/arch/powerpc/include/asm/code-patching.h +++ b/arch/powerpc/include/asm/code-patching.h @@ -11,6 +11,7 @@ #include <linux/string.h> #include <linux/kallsyms.h> #include <asm/asm-compat.h> +#include <asm/inst.h> /* Flags for create_branch: * "b" == create_branch(addr, target, 0); @@ -21,34 +22,79 @@ #define BRANCH_SET_LINK 0x1 #define BRANCH_ABSOLUTE 0x2 -bool is_offset_in_branch_range(long offset); -unsigned int create_branch(const unsigned int *addr, - unsigned long target, int flags); -unsigned int create_cond_branch(const unsigned int *addr, - unsigned long target, int flags); -int patch_branch(unsigned int *addr, unsigned long target, int flags); -int patch_instruction(unsigned int *addr, unsigned int instr); -int raw_patch_instruction(unsigned int *addr, unsigned int instr); +/* + * Powerpc branch instruction is : + * + * 0 6 30 31 + * +---------+----------------+---+---+ + * | opcode | LI |AA |LK | + * +---------+----------------+---+---+ + * Where AA = 0 and LK = 0 + * + * LI is a signed 24 bits integer. The real branch offset is computed + * by: imm32 = SignExtend(LI:'0b00', 32); + * + * So the maximum forward branch should be: + * (0x007fffff << 2) = 0x01fffffc = 0x1fffffc + * The maximum backward branch should be: + * (0xff800000 << 2) = 0xfe000000 = -0x2000000 + */ +static inline bool is_offset_in_branch_range(long offset) +{ + return (offset >= -0x2000000 && offset <= 0x1fffffc && !(offset & 0x3)); +} + +static inline bool is_offset_in_cond_branch_range(long offset) +{ + return offset >= -0x8000 && offset <= 0x7fff && !(offset & 0x3); +} + +static inline int create_branch(ppc_inst_t *instr, const u32 *addr, + unsigned long target, int flags) +{ + long offset; + + *instr = ppc_inst(0); + offset = target; + if (! (flags & BRANCH_ABSOLUTE)) + offset = offset - (unsigned long)addr; + + /* Check we can represent the target in the instruction format */ + if (!is_offset_in_branch_range(offset)) + return 1; + + /* Mask out the flags and target, so they don't step on each other. */ + *instr = ppc_inst(0x48000000 | (flags & 0x3) | (offset & 0x03FFFFFC)); + + return 0; +} + +int create_cond_branch(ppc_inst_t *instr, const u32 *addr, + unsigned long target, int flags); +int patch_branch(u32 *addr, unsigned long target, int flags); +int patch_instruction(u32 *addr, ppc_inst_t instr); +int raw_patch_instruction(u32 *addr, ppc_inst_t instr); +int patch_instructions(u32 *addr, u32 *code, size_t len, bool repeat_instr); static inline unsigned long patch_site_addr(s32 *site) { return (unsigned long)site + *site; } -static inline int patch_instruction_site(s32 *site, unsigned int instr) +static inline int patch_instruction_site(s32 *site, ppc_inst_t instr) { - return patch_instruction((unsigned int *)patch_site_addr(site), instr); + return patch_instruction((u32 *)patch_site_addr(site), instr); } static inline int patch_branch_site(s32 *site, unsigned long target, int flags) { - return patch_branch((unsigned int *)patch_site_addr(site), target, flags); + return patch_branch((u32 *)patch_site_addr(site), target, flags); } static inline int modify_instruction(unsigned int *addr, unsigned int clr, unsigned int set) { - return patch_instruction(addr, (*addr & ~clr) | set); + return patch_instruction(addr, ppc_inst((*addr & ~clr) | set)); } static inline int modify_instruction_site(s32 *site, unsigned int clr, unsigned int set) @@ -56,29 +102,36 @@ static inline int modify_instruction_site(s32 *site, unsigned int clr, unsigned return modify_instruction((unsigned int *)patch_site_addr(site), clr, set); } -int instr_is_relative_branch(unsigned int instr); -int instr_is_relative_link_branch(unsigned int instr); -int instr_is_branch_to_addr(const unsigned int *instr, unsigned long addr); -unsigned long branch_target(const unsigned int *instr); -unsigned int translate_branch(const unsigned int *dest, - const unsigned int *src); -extern bool is_conditional_branch(unsigned int instr); -#ifdef CONFIG_PPC_BOOK3E_64 -void __patch_exception(int exc, unsigned long addr); -#define patch_exception(exc, name) do { \ - extern unsigned int name; \ - __patch_exception((exc), (unsigned long)&name); \ -} while (0) -#endif +static inline unsigned int branch_opcode(ppc_inst_t instr) +{ + return ppc_inst_primary_opcode(instr) & 0x3F; +} + +static inline int instr_is_branch_iform(ppc_inst_t instr) +{ + return branch_opcode(instr) == 18; +} + +static inline int instr_is_branch_bform(ppc_inst_t instr) +{ + return branch_opcode(instr) == 16; +} + +int instr_is_relative_branch(ppc_inst_t instr); +int instr_is_relative_link_branch(ppc_inst_t instr); +unsigned long branch_target(const u32 *instr); +int translate_branch(ppc_inst_t *instr, const u32 *dest, const u32 *src); +bool is_conditional_branch(ppc_inst_t instr); #define OP_RT_RA_MASK 0xffff0000UL -#define LIS_R2 0x3c020000UL -#define ADDIS_R2_R12 0x3c4c0000UL -#define ADDI_R2_R2 0x38420000UL +#define LIS_R2 (PPC_RAW_LIS(_R2, 0)) +#define ADDIS_R2_R12 (PPC_RAW_ADDIS(_R2, _R12, 0)) +#define ADDI_R2_R2 (PPC_RAW_ADDI(_R2, _R2, 0)) + static inline unsigned long ppc_function_entry(void *func) { -#ifdef PPC64_ELF_ABI_v2 +#ifdef CONFIG_PPC64_ELF_ABI_V2 u32 *insn = func; /* @@ -103,13 +156,13 @@ static inline unsigned long ppc_function_entry(void *func) return (unsigned long)(insn + 2); else return (unsigned long)func; -#elif defined(PPC64_ELF_ABI_v1) +#elif defined(CONFIG_PPC64_ELF_ABI_V1) /* * On PPC64 ABIv1 the function pointer actually points to the * function's descriptor. The first entry in the descriptor is the * address of the function text. */ - return ((func_descr_t *)func)->entry; + return ((struct func_desc *)func)->addr; #else return (unsigned long)func; #endif @@ -117,7 +170,7 @@ static inline unsigned long ppc_function_entry(void *func) static inline unsigned long ppc_global_function_entry(void *func) { -#ifdef PPC64_ELF_ABI_v2 +#ifdef CONFIG_PPC64_ELF_ABI_V2 /* PPC64 ABIv2 the global entry point is at the address */ return (unsigned long)func; #else @@ -134,7 +187,7 @@ static inline unsigned long ppc_global_function_entry(void *func) static inline unsigned long ppc_kallsyms_lookup_name(const char *name) { unsigned long addr; -#ifdef PPC64_ELF_ABI_v1 +#ifdef CONFIG_PPC64_ELF_ABI_V1 /* check for dot variant */ char dot_name[1 + KSYM_NAME_LEN]; bool dot_appended = false; @@ -155,7 +208,7 @@ static inline unsigned long ppc_kallsyms_lookup_name(const char *name) if (!addr && dot_appended) /* Let's try the original non-dot symbol lookup */ addr = kallsyms_lookup_name(name); -#elif defined(PPC64_ELF_ABI_v2) +#elif defined(CONFIG_PPC64_ELF_ABI_V2) addr = kallsyms_lookup_name(name); if (addr) addr = ppc_function_entry((void *)addr); @@ -165,25 +218,21 @@ static inline unsigned long ppc_kallsyms_lookup_name(const char *name) return addr; } -#ifdef CONFIG_PPC64 /* * Some instruction encodings commonly used in dynamic ftracing * and function live patching. */ /* This must match the definition of STK_GOT in <asm/ppc_asm.h> */ -#ifdef PPC64_ELF_ABI_v2 +#ifdef CONFIG_PPC64_ELF_ABI_V2 #define R2_STACK_OFFSET 24 #else #define R2_STACK_OFFSET 40 #endif -#define PPC_INST_LD_TOC (PPC_INST_LD | ___PPC_RT(__REG_R2) | \ - ___PPC_RA(__REG_R1) | R2_STACK_OFFSET) +#define PPC_INST_LD_TOC PPC_RAW_LD(_R2, _R1, R2_STACK_OFFSET) /* usually preceded by a mflr r0 */ -#define PPC_INST_STD_LR (PPC_INST_STD | ___PPC_RS(__REG_R0) | \ - ___PPC_RA(__REG_R1) | PPC_LR_STKOFF) -#endif /* CONFIG_PPC64 */ +#define PPC_INST_STD_LR PPC_RAW_STD(_R0, _R1, PPC_LR_STKOFF) #endif /* _ASM_POWERPC_CODE_PATCHING_H */ diff --git a/arch/powerpc/include/asm/compat.h b/arch/powerpc/include/asm/compat.h index 74d0db511099..dda4091fd012 100644 --- a/arch/powerpc/include/asm/compat.h +++ b/arch/powerpc/include/asm/compat.h @@ -8,27 +8,20 @@ #include <linux/types.h> #include <linux/sched.h> +#define compat_ipc_pid_t compat_ipc_pid_t +typedef u16 compat_ipc_pid_t; + +#define compat_ipc64_perm compat_ipc64_perm + #include <asm-generic/compat.h> -#define COMPAT_USER_HZ 100 #ifdef __BIG_ENDIAN__ #define COMPAT_UTS_MACHINE "ppc\0\0" #else #define COMPAT_UTS_MACHINE "ppcle\0\0" #endif -typedef u32 __compat_uid_t; -typedef u32 __compat_gid_t; -typedef u32 __compat_uid32_t; -typedef u32 __compat_gid32_t; -typedef u32 compat_mode_t; -typedef u32 compat_dev_t; typedef s16 compat_nlink_t; -typedef u16 compat_ipc_pid_t; -typedef u32 compat_caddr_t; -typedef __kernel_fsid_t compat_fsid_t; -typedef s64 compat_s64; -typedef u64 compat_u64; struct compat_stat { compat_dev_t st_dev; @@ -50,85 +43,6 @@ struct compat_stat { u32 __unused4[2]; }; -struct compat_flock { - short l_type; - short l_whence; - compat_off_t l_start; - compat_off_t l_len; - compat_pid_t l_pid; -}; - -#define F_GETLK64 12 /* using 'struct flock64' */ -#define F_SETLK64 13 -#define F_SETLKW64 14 - -struct compat_flock64 { - short l_type; - short l_whence; - compat_loff_t l_start; - compat_loff_t l_len; - compat_pid_t l_pid; -}; - -struct compat_statfs { - int f_type; - int f_bsize; - int f_blocks; - int f_bfree; - int f_bavail; - int f_files; - int f_ffree; - compat_fsid_t f_fsid; - int f_namelen; /* SunOS ignores this field. */ - int f_frsize; - int f_flags; - int f_spare[4]; -}; - -#define COMPAT_RLIM_INFINITY 0xffffffff - -typedef u32 compat_old_sigset_t; - -#define _COMPAT_NSIG 64 -#define _COMPAT_NSIG_BPW 32 - -typedef u32 compat_sigset_word; - -#define COMPAT_OFF_T_MAX 0x7fffffff - -/* - * A pointer passed in from user mode. This should not - * be used for syscall parameters, just declare them - * as pointers because the syscall entry code will have - * appropriately converted them already. - */ - -static inline void __user *compat_ptr(compat_uptr_t uptr) -{ - return (void __user *)(unsigned long)uptr; -} - -static inline compat_uptr_t ptr_to_compat(void __user *uptr) -{ - return (u32)(unsigned long)uptr; -} - -static inline void __user *arch_compat_alloc_user_space(long len) -{ - struct pt_regs *regs = current->thread.regs; - unsigned long usp = regs->gpr[1]; - - /* - * We can't access below the stack pointer in the 32bit ABI and - * can access 288 bytes in the 64bit big-endian ABI, - * or 512 bytes with the new ELFv2 little-endian ABI. - */ - if (!is_32bit_task()) - usp -= USER_REDZONE_SIZE; - - return (void __user *) (usp - len); -} - /* * ipc64_perm is actually 32/64bit clean but since the compat layer refers to * it we may as well define it. diff --git a/arch/powerpc/include/asm/context_tracking.h b/arch/powerpc/include/asm/context_tracking.h index f2682b28b050..4b63931c49e0 100644 --- a/arch/powerpc/include/asm/context_tracking.h +++ b/arch/powerpc/include/asm/context_tracking.h @@ -2,7 +2,7 @@ #ifndef _ASM_POWERPC_CONTEXT_TRACKING_H #define _ASM_POWERPC_CONTEXT_TRACKING_H -#ifdef CONFIG_CONTEXT_TRACKING +#ifdef CONFIG_CONTEXT_TRACKING_USER #define SCHEDULE_USER bl schedule_user #else #define SCHEDULE_USER bl schedule diff --git a/arch/powerpc/include/asm/cpm.h b/arch/powerpc/include/asm/cpm.h index 4c24ea8209bb..ce483b0f8a4d 100644 --- a/arch/powerpc/include/asm/cpm.h +++ b/arch/powerpc/include/asm/cpm.h @@ -1,171 +1 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __CPM_H -#define __CPM_H - -#include <linux/compiler.h> -#include <linux/types.h> -#include <linux/errno.h> -#include <linux/of.h> -#include <soc/fsl/qe/qe.h> - -/* - * SPI Parameter RAM common to QE and CPM. - */ -struct spi_pram { - __be16 rbase; /* Rx Buffer descriptor base address */ - __be16 tbase; /* Tx Buffer descriptor base address */ - u8 rfcr; /* Rx function code */ - u8 tfcr; /* Tx function code */ - __be16 mrblr; /* Max receive buffer length */ - __be32 rstate; /* Internal */ - __be32 rdp; /* Internal */ - __be16 rbptr; /* Internal */ - __be16 rbc; /* Internal */ - __be32 rxtmp; /* Internal */ - __be32 tstate; /* Internal */ - __be32 tdp; /* Internal */ - __be16 tbptr; /* Internal */ - __be16 tbc; /* Internal */ - __be32 txtmp; /* Internal */ - __be32 res; /* Tx temp. */ - __be16 rpbase; /* Relocation pointer (CPM1 only) */ - __be16 res1; /* Reserved */ -}; - -/* - * USB Controller pram common to QE and CPM. - */ -struct usb_ctlr { - u8 usb_usmod; - u8 usb_usadr; - u8 usb_uscom; - u8 res1[1]; - __be16 usb_usep[4]; - u8 res2[4]; - __be16 usb_usber; - u8 res3[2]; - __be16 usb_usbmr; - u8 res4[1]; - u8 usb_usbs; - /* Fields down below are QE-only */ - __be16 usb_ussft; - u8 res5[2]; - __be16 usb_usfrn; - u8 res6[0x22]; -} __attribute__ ((packed)); - -/* - * Function code bits, usually generic to devices. - */ -#ifdef CONFIG_CPM1 -#define CPMFCR_GBL ((u_char)0x00) /* Flag doesn't exist in CPM1 */ -#define CPMFCR_TC2 ((u_char)0x00) /* Flag doesn't exist in CPM1 */ -#define CPMFCR_DTB ((u_char)0x00) /* Flag doesn't exist in CPM1 */ -#define CPMFCR_BDB ((u_char)0x00) /* Flag doesn't exist in CPM1 */ -#else -#define CPMFCR_GBL ((u_char)0x20) /* Set memory snooping */ -#define CPMFCR_TC2 ((u_char)0x04) /* Transfer code 2 value */ -#define CPMFCR_DTB ((u_char)0x02) /* Use local bus for data when set */ -#define CPMFCR_BDB ((u_char)0x01) /* Use local bus for BD when set */ -#endif -#define CPMFCR_EB ((u_char)0x10) /* Set big endian byte order */ - -/* Opcodes common to CPM1 and CPM2 -*/ -#define CPM_CR_INIT_TRX ((ushort)0x0000) -#define CPM_CR_INIT_RX ((ushort)0x0001) -#define CPM_CR_INIT_TX ((ushort)0x0002) -#define CPM_CR_HUNT_MODE ((ushort)0x0003) -#define CPM_CR_STOP_TX ((ushort)0x0004) -#define CPM_CR_GRA_STOP_TX ((ushort)0x0005) -#define CPM_CR_RESTART_TX ((ushort)0x0006) -#define CPM_CR_CLOSE_RX_BD ((ushort)0x0007) -#define CPM_CR_SET_GADDR ((ushort)0x0008) -#define CPM_CR_SET_TIMER ((ushort)0x0008) -#define CPM_CR_STOP_IDMA ((ushort)0x000b) - -/* Buffer descriptors used by many of the CPM protocols. */ -typedef struct cpm_buf_desc { - ushort cbd_sc; /* Status and Control */ - ushort cbd_datlen; /* Data length in buffer */ - uint cbd_bufaddr; /* Buffer address in host memory */ -} cbd_t; - -/* Buffer descriptor control/status used by serial - */ - -#define BD_SC_EMPTY (0x8000) /* Receive is empty */ -#define BD_SC_READY (0x8000) /* Transmit is ready */ -#define BD_SC_WRAP (0x2000) /* Last buffer descriptor */ -#define BD_SC_INTRPT (0x1000) /* Interrupt on change */ -#define BD_SC_LAST (0x0800) /* Last buffer in frame */ -#define BD_SC_TC (0x0400) /* Transmit CRC */ -#define BD_SC_CM (0x0200) /* Continuous mode */ -#define BD_SC_ID (0x0100) /* Rec'd too many idles */ -#define BD_SC_P (0x0100) /* xmt preamble */ -#define BD_SC_BR (0x0020) /* Break received */ -#define BD_SC_FR (0x0010) /* Framing error */ -#define BD_SC_PR (0x0008) /* Parity error */ -#define BD_SC_NAK (0x0004) /* NAK - did not respond */ -#define BD_SC_OV (0x0002) /* Overrun */ -#define BD_SC_UN (0x0002) /* Underrun */ -#define BD_SC_CD (0x0001) /* */ -#define BD_SC_CL (0x0001) /* Collision */ - -/* Buffer descriptor control/status used by Ethernet receive. - * Common to SCC and FCC. - */ -#define BD_ENET_RX_EMPTY (0x8000) -#define BD_ENET_RX_WRAP (0x2000) -#define BD_ENET_RX_INTR (0x1000) -#define BD_ENET_RX_LAST (0x0800) -#define BD_ENET_RX_FIRST (0x0400) -#define BD_ENET_RX_MISS (0x0100) -#define BD_ENET_RX_BC (0x0080) /* FCC Only */ -#define BD_ENET_RX_MC (0x0040) /* FCC Only */ -#define BD_ENET_RX_LG (0x0020) -#define BD_ENET_RX_NO (0x0010) -#define BD_ENET_RX_SH (0x0008) -#define BD_ENET_RX_CR (0x0004) -#define BD_ENET_RX_OV (0x0002) -#define BD_ENET_RX_CL (0x0001) -#define BD_ENET_RX_STATS (0x01ff) /* All status bits */ - -/* Buffer descriptor control/status used by Ethernet transmit. - * Common to SCC and FCC. - */ -#define BD_ENET_TX_READY (0x8000) -#define BD_ENET_TX_PAD (0x4000) -#define BD_ENET_TX_WRAP (0x2000) -#define BD_ENET_TX_INTR (0x1000) -#define BD_ENET_TX_LAST (0x0800) -#define BD_ENET_TX_TC (0x0400) -#define BD_ENET_TX_DEF (0x0200) -#define BD_ENET_TX_HB (0x0100) -#define BD_ENET_TX_LC (0x0080) -#define BD_ENET_TX_RL (0x0040) -#define BD_ENET_TX_RCMASK (0x003c) -#define BD_ENET_TX_UN (0x0002) -#define BD_ENET_TX_CSL (0x0001) -#define BD_ENET_TX_STATS (0x03ff) /* All status bits */ - -/* Buffer descriptor control/status used by Transparent mode SCC. - */ -#define BD_SCC_TX_LAST (0x0800) - -/* Buffer descriptor control/status used by I2C. - */ -#define BD_I2C_START (0x0400) - -#ifdef CONFIG_CPM -int cpm_command(u32 command, u8 opcode); -#else -static inline int cpm_command(u32 command, u8 opcode) -{ - return -ENOSYS; -} -#endif /* CONFIG_CPM */ - -int cpm2_gpiochip_add32(struct device *dev); - -#endif +#include <soc/fsl/cpm.h> diff --git a/arch/powerpc/include/asm/cpm1.h b/arch/powerpc/include/asm/cpm1.h index a116fe931789..e3c6969853ef 100644 --- a/arch/powerpc/include/asm/cpm1.h +++ b/arch/powerpc/include/asm/cpm1.h @@ -49,11 +49,6 @@ */ extern cpm8xx_t __iomem *cpmp; /* Pointer to comm processor */ -#define cpm_dpalloc cpm_muram_alloc -#define cpm_dpfree cpm_muram_free -#define cpm_dpram_addr cpm_muram_addr -#define cpm_dpram_phys cpm_muram_dma - extern void cpm_setbrg(uint brg, uint rate); extern void __init cpm_load_patch(cpm8xx_t *cp); @@ -68,6 +63,7 @@ extern void cpm_reset(void); #define PROFF_SPI ((uint)0x0180) #define PROFF_SCC3 ((uint)0x0200) #define PROFF_SMC1 ((uint)0x0280) +#define PROFF_DSP1 ((uint)0x02c0) #define PROFF_SCC4 ((uint)0x0300) #define PROFF_SMC2 ((uint)0x0380) diff --git a/arch/powerpc/include/asm/cpm2.h b/arch/powerpc/include/asm/cpm2.h index 2211b934ecb4..a22acc36eb9b 100644 --- a/arch/powerpc/include/asm/cpm2.h +++ b/arch/powerpc/include/asm/cpm2.h @@ -87,10 +87,6 @@ */ extern cpm_cpm2_t __iomem *cpmp; /* Pointer to comm processor */ -#define cpm_dpalloc cpm_muram_alloc -#define cpm_dpfree cpm_muram_free -#define cpm_dpram_addr cpm_muram_addr - extern void cpm2_reset(void); /* Baud rate generators. @@ -594,7 +590,7 @@ typedef struct fcc_enet { uint fen_p256c; /* Total packets 256 < bytes <= 511 */ uint fen_p512c; /* Total packets 512 < bytes <= 1023 */ uint fen_p1024c; /* Total packets 1024 < bytes <= 1518 */ - uint fen_cambuf; /* Internal CAM buffer poiner */ + uint fen_cambuf; /* Internal CAM buffer pointer */ ushort fen_rfthr; /* Received frames threshold */ ushort fen_rfcnt; /* Received frames count */ } fcc_enet_t; @@ -1080,6 +1076,9 @@ typedef struct im_idma { #define FCC2_MEM_OFFSET FCC_MEM_OFFSET(1) #define FCC3_MEM_OFFSET FCC_MEM_OFFSET(2) +/* Pipeline Maximum Depth */ +#define MPC82XX_BCR_PLDP 0x00800000 + /* Clocks and GRG's */ enum cpm_clk_dir { @@ -1133,8 +1132,8 @@ enum cpm_clk { CPM_CLK_DUMMY }; -extern int cpm2_clk_setup(enum cpm_clk_target target, int clock, int mode); -extern int cpm2_smc_clk_setup(enum cpm_clk_target target, int clock); +int __init cpm2_clk_setup(enum cpm_clk_target target, int clock, int mode); +int __init cpm2_smc_clk_setup(enum cpm_clk_target target, int clock); #define CPM_PIN_INPUT 0 #define CPM_PIN_OUTPUT 1 @@ -1143,7 +1142,7 @@ extern int cpm2_smc_clk_setup(enum cpm_clk_target target, int clock); #define CPM_PIN_GPIO 4 #define CPM_PIN_OPENDRAIN 8 -void cpm2_set_pin(int port, int pin, int flags); +void __init cpm2_set_pin(int port, int pin, int flags); #endif /* __CPM2__ */ #endif /* __KERNEL__ */ diff --git a/arch/powerpc/include/asm/cpu_has_feature.h b/arch/powerpc/include/asm/cpu_has_feature.h index 7897d16e0990..727d4b321937 100644 --- a/arch/powerpc/include/asm/cpu_has_feature.h +++ b/arch/powerpc/include/asm/cpu_has_feature.h @@ -7,7 +7,7 @@ #include <linux/bug.h> #include <asm/cputable.h> -static inline bool early_cpu_has_feature(unsigned long feature) +static __always_inline bool early_cpu_has_feature(unsigned long feature) { return !!((CPU_FTRS_ALWAYS & feature) || (CPU_FTRS_POSSIBLE & cur_cpu_spec->cpu_features & feature)); @@ -46,7 +46,7 @@ static __always_inline bool cpu_has_feature(unsigned long feature) return static_branch_likely(&cpu_feature_keys[i]); } #else -static inline bool cpu_has_feature(unsigned long feature) +static __always_inline bool cpu_has_feature(unsigned long feature) { return early_cpu_has_feature(feature); } diff --git a/arch/powerpc/include/asm/cpu_setup.h b/arch/powerpc/include/asm/cpu_setup.h new file mode 100644 index 000000000000..30e2fe389502 --- /dev/null +++ b/arch/powerpc/include/asm/cpu_setup.h @@ -0,0 +1,49 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (C) 2020 IBM Corporation + */ + +#ifndef _ASM_POWERPC_CPU_SETUP_H +#define _ASM_POWERPC_CPU_SETUP_H +void __setup_cpu_power7(unsigned long offset, struct cpu_spec *spec); +void __setup_cpu_power8(unsigned long offset, struct cpu_spec *spec); +void __setup_cpu_power9(unsigned long offset, struct cpu_spec *spec); +void __setup_cpu_power10(unsigned long offset, struct cpu_spec *spec); +void __restore_cpu_power7(void); +void __restore_cpu_power8(void); +void __restore_cpu_power9(void); +void __restore_cpu_power10(void); + +void __setup_cpu_e500v1(unsigned long offset, struct cpu_spec *spec); +void __setup_cpu_e500v2(unsigned long offset, struct cpu_spec *spec); +void __setup_cpu_e500mc(unsigned long offset, struct cpu_spec *spec); +void __setup_cpu_440ep(unsigned long offset, struct cpu_spec *spec); +void __setup_cpu_440epx(unsigned long offset, struct cpu_spec *spec); +void __setup_cpu_440gx(unsigned long offset, struct cpu_spec *spec); +void __setup_cpu_440grx(unsigned long offset, struct cpu_spec *spec); +void __setup_cpu_440spe(unsigned long offset, struct cpu_spec *spec); +void __setup_cpu_440x5(unsigned long offset, struct cpu_spec *spec); +void __setup_cpu_460ex(unsigned long offset, struct cpu_spec *spec); +void __setup_cpu_460gt(unsigned long offset, struct cpu_spec *spec); +void __setup_cpu_460sx(unsigned long offset, struct cpu_spec *spec); +void __setup_cpu_apm821xx(unsigned long offset, struct cpu_spec *spec); +void __setup_cpu_603(unsigned long offset, struct cpu_spec *spec); +void __setup_cpu_604(unsigned long offset, struct cpu_spec *spec); +void __setup_cpu_750(unsigned long offset, struct cpu_spec *spec); +void __setup_cpu_750cx(unsigned long offset, struct cpu_spec *spec); +void __setup_cpu_750fx(unsigned long offset, struct cpu_spec *spec); +void __setup_cpu_7400(unsigned long offset, struct cpu_spec *spec); +void __setup_cpu_7410(unsigned long offset, struct cpu_spec *spec); +void __setup_cpu_745x(unsigned long offset, struct cpu_spec *spec); + +void __setup_cpu_ppc970(unsigned long offset, struct cpu_spec *spec); +void __setup_cpu_ppc970MP(unsigned long offset, struct cpu_spec *spec); +void __setup_cpu_pa6t(unsigned long offset, struct cpu_spec *spec); +void __restore_cpu_pa6t(void); +void __restore_cpu_ppc970(void); + +void __setup_cpu_e5500(unsigned long offset, struct cpu_spec *spec); +void __setup_cpu_e6500(unsigned long offset, struct cpu_spec *spec); +void __restore_cpu_e5500(void); +void __restore_cpu_e6500(void); +#endif /* _ASM_POWERPC_CPU_SETUP_H */ diff --git a/arch/powerpc/include/asm/cpufeature.h b/arch/powerpc/include/asm/cpufeature.h index f6f790a90367..2dcc66225e7f 100644 --- a/arch/powerpc/include/asm/cpufeature.h +++ b/arch/powerpc/include/asm/cpufeature.h @@ -22,6 +22,7 @@ */ #define PPC_MODULE_FEATURE_VEC_CRYPTO (32 + ilog2(PPC_FEATURE2_VEC_CRYPTO)) +#define PPC_MODULE_FEATURE_P10 (32 + ilog2(PPC_FEATURE2_ARCH_3_1)) #define cpu_feature(x) (x) diff --git a/arch/powerpc/include/asm/cpuidle.h b/arch/powerpc/include/asm/cpuidle.h index 9844b3ded187..0cce5dc7fb1c 100644 --- a/arch/powerpc/include/asm/cpuidle.h +++ b/arch/powerpc/include/asm/cpuidle.h @@ -85,7 +85,7 @@ extern struct pnv_idle_states_t *pnv_idle_states; extern int nr_pnv_idle_states; unsigned long pnv_cpu_offline(unsigned int cpu); -int validate_psscr_val_mask(u64 *psscr_val, u64 *psscr_mask, u32 flags); +int __init validate_psscr_val_mask(u64 *psscr_val, u64 *psscr_mask, u32 flags); static inline void report_invalid_psscr_val(u64 psscr_val, int err) { switch (err) { diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h index cf00ff0d121d..8765d5158324 100644 --- a/arch/powerpc/include/asm/cputable.h +++ b/arch/powerpc/include/asm/cputable.h @@ -17,16 +17,6 @@ struct cpu_spec; typedef void (*cpu_setup_t)(unsigned long offset, struct cpu_spec* spec); typedef void (*cpu_restore_t)(void); -enum powerpc_oprofile_type { - PPC_OPROFILE_INVALID = 0, - PPC_OPROFILE_RS64 = 1, - PPC_OPROFILE_POWER4 = 2, - PPC_OPROFILE_G4 = 3, - PPC_OPROFILE_FSL_EMB = 4, - PPC_OPROFILE_CELL = 5, - PPC_OPROFILE_PA6T = 6, -}; - enum powerpc_pmc_type { PPC_PMC_DEFAULT = 0, PPC_PMC_IBM = 1, @@ -41,7 +31,6 @@ extern int machine_check_4xx(struct pt_regs *regs); extern int machine_check_440A(struct pt_regs *regs); extern int machine_check_e500mc(struct pt_regs *regs); extern int machine_check_e500(struct pt_regs *regs); -extern int machine_check_e200(struct pt_regs *regs); extern int machine_check_47x(struct pt_regs *regs); int machine_check_8xx(struct pt_regs *regs); int machine_check_83xx(struct pt_regs *regs); @@ -81,19 +70,6 @@ struct cpu_spec { /* Used to restore cpu setup on secondary processors and at resume */ cpu_restore_t cpu_restore; - /* Used by oprofile userspace to select the right counters */ - char *oprofile_cpu_type; - - /* Processor specific oprofile operations */ - enum powerpc_oprofile_type oprofile_type; - - /* Bit locations inside the mmcra change */ - unsigned long oprofile_mmcra_sihv; - unsigned long oprofile_mmcra_sipr; - - /* Bits to clear during an oprofile exception */ - unsigned long oprofile_mmcra_clear; - /* Name of processor class, for the ELF AT_PLATFORM entry */ char *platform; @@ -137,7 +113,7 @@ static inline void cpu_feature_keys_init(void) { } #define CPU_FTR_DBELL ASM_CONST(0x00000004) #define CPU_FTR_CAN_NAP ASM_CONST(0x00000008) #define CPU_FTR_DEBUG_LVL_EXC ASM_CONST(0x00000010) -#define CPU_FTR_NODSISRALIGN ASM_CONST(0x00000020) +// ASM_CONST(0x00000020) Free #define CPU_FTR_FPU_UNAVAILABLE ASM_CONST(0x00000040) #define CPU_FTR_LWSYNC ASM_CONST(0x00000080) #define CPU_FTR_NOEXECUTE ASM_CONST(0x00000100) @@ -165,6 +141,7 @@ static inline void cpu_feature_keys_init(void) { } #else /* CONFIG_PPC32 */ /* Define these to 0 for the sake of tests in common code */ #define CPU_FTR_PPC_LE (0) +#define CPU_FTR_SPE (0) #endif /* @@ -198,7 +175,7 @@ static inline void cpu_feature_keys_init(void) { } #define CPU_FTR_STCX_CHECKS_ADDRESS LONG_ASM_CONST(0x0000000080000000) #define CPU_FTR_POPCNTB LONG_ASM_CONST(0x0000000100000000) #define CPU_FTR_POPCNTD LONG_ASM_CONST(0x0000000200000000) -#define CPU_FTR_PKEY LONG_ASM_CONST(0x0000000400000000) +/* LONG_ASM_CONST(0x0000000400000000) Free */ #define CPU_FTR_VMX_COPY LONG_ASM_CONST(0x0000000800000000) #define CPU_FTR_TM LONG_ASM_CONST(0x0000001000000000) #define CPU_FTR_CFAR LONG_ASM_CONST(0x0000002000000000) @@ -212,12 +189,14 @@ static inline void cpu_feature_keys_init(void) { } #define CPU_FTR_P9_TLBIE_STQ_BUG LONG_ASM_CONST(0x0000400000000000) #define CPU_FTR_P9_TIDR LONG_ASM_CONST(0x0000800000000000) #define CPU_FTR_P9_TLBIE_ERAT_BUG LONG_ASM_CONST(0x0001000000000000) +#define CPU_FTR_P9_RADIX_PREFETCH_BUG LONG_ASM_CONST(0x0002000000000000) +#define CPU_FTR_ARCH_31 LONG_ASM_CONST(0x0004000000000000) +#define CPU_FTR_DAWR1 LONG_ASM_CONST(0x0008000000000000) +#define CPU_FTR_DEXCR_NPHIE LONG_ASM_CONST(0x0010000000000000) #ifndef __ASSEMBLY__ -#define CPU_FTR_PPCAS_ARCH_V2 (CPU_FTR_NOEXECUTE | CPU_FTR_NODSISRALIGN) - -#define MMU_FTR_PPCAS_ARCH_V2 (MMU_FTR_TLBIEL | MMU_FTR_16M_PAGE) +#define CPU_FTR_PPCAS_ARCH_V2 (CPU_FTR_NOEXECUTE) /* We only set the altivec features if the kernel was compiled with altivec * support @@ -273,7 +252,7 @@ static inline void cpu_feature_keys_init(void) { } * This is also required by 52xx family. */ #if defined(CONFIG_SMP) || defined(CONFIG_MPC10X_BRIDGE) \ - || defined(CONFIG_PPC_83xx) || defined(CONFIG_8260) \ + || defined(CONFIG_PPC_83xx) || defined(CONFIG_PPC_82xx) \ || defined(CONFIG_PPC_MPC52xx) #define CPU_FTR_COMMON CPU_FTR_NEED_COHERENT #else @@ -291,8 +270,6 @@ static inline void cpu_feature_keys_init(void) { } #define CPU_FTR_MAYBE_CAN_NAP 0 #endif -#define CPU_FTRS_PPC601 (CPU_FTR_COMMON | \ - CPU_FTR_COHERENT_ICACHE) #define CPU_FTRS_603 (CPU_FTR_COMMON | CPU_FTR_MAYBE_CAN_DOZE | \ CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_PPC_LE | CPU_FTR_NOEXECUTE) #define CPU_FTRS_604 (CPU_FTR_COMMON | CPU_FTR_PPC_LE) @@ -367,7 +344,7 @@ static inline void cpu_feature_keys_init(void) { } CPU_FTR_PPC_LE | CPU_FTR_NEED_PAIRED_STWCX) #define CPU_FTRS_82XX (CPU_FTR_COMMON | CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_NOEXECUTE) #define CPU_FTRS_G2_LE (CPU_FTR_COMMON | CPU_FTR_MAYBE_CAN_DOZE | \ - CPU_FTR_MAYBE_CAN_NAP) + CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_NOEXECUTE) #define CPU_FTRS_E300 (CPU_FTR_MAYBE_CAN_DOZE | \ CPU_FTR_MAYBE_CAN_NAP | \ CPU_FTR_COMMON | CPU_FTR_NOEXECUTE) @@ -376,38 +353,33 @@ static inline void cpu_feature_keys_init(void) { } CPU_FTR_COMMON | CPU_FTR_FPU_UNAVAILABLE | CPU_FTR_NOEXECUTE) #define CPU_FTRS_CLASSIC32 (CPU_FTR_COMMON) #define CPU_FTRS_8XX (CPU_FTR_NOEXECUTE) -#define CPU_FTRS_40X (CPU_FTR_NODSISRALIGN | CPU_FTR_NOEXECUTE) -#define CPU_FTRS_44X (CPU_FTR_NODSISRALIGN | CPU_FTR_NOEXECUTE) -#define CPU_FTRS_440x6 (CPU_FTR_NODSISRALIGN | CPU_FTR_NOEXECUTE | \ +#define CPU_FTRS_40X (CPU_FTR_NOEXECUTE) +#define CPU_FTRS_44X (CPU_FTR_NOEXECUTE) +#define CPU_FTRS_440x6 (CPU_FTR_NOEXECUTE | \ CPU_FTR_INDEXED_DCR) #define CPU_FTRS_47X (CPU_FTRS_440x6) -#define CPU_FTRS_E200 (CPU_FTR_SPE_COMP | \ - CPU_FTR_NODSISRALIGN | CPU_FTR_COHERENT_ICACHE | \ - CPU_FTR_NOEXECUTE | \ - CPU_FTR_DEBUG_LVL_EXC) #define CPU_FTRS_E500 (CPU_FTR_MAYBE_CAN_DOZE | \ - CPU_FTR_SPE_COMP | CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_NODSISRALIGN | \ + CPU_FTR_SPE_COMP | CPU_FTR_MAYBE_CAN_NAP | \ CPU_FTR_NOEXECUTE) #define CPU_FTRS_E500_2 (CPU_FTR_MAYBE_CAN_DOZE | \ CPU_FTR_SPE_COMP | CPU_FTR_MAYBE_CAN_NAP | \ - CPU_FTR_NODSISRALIGN | CPU_FTR_NOEXECUTE) -#define CPU_FTRS_E500MC (CPU_FTR_NODSISRALIGN | \ + CPU_FTR_NOEXECUTE) +#define CPU_FTRS_E500MC ( \ CPU_FTR_LWSYNC | CPU_FTR_NOEXECUTE | \ CPU_FTR_DBELL | CPU_FTR_DEBUG_LVL_EXC | CPU_FTR_EMB_HV) /* * e5500/e6500 erratum A-006958 is a timebase bug that can use the * same workaround as CPU_FTR_CELL_TB_BUG. */ -#define CPU_FTRS_E5500 (CPU_FTR_NODSISRALIGN | \ +#define CPU_FTRS_E5500 ( \ CPU_FTR_LWSYNC | CPU_FTR_NOEXECUTE | \ CPU_FTR_DBELL | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \ CPU_FTR_DEBUG_LVL_EXC | CPU_FTR_EMB_HV | CPU_FTR_CELL_TB_BUG) -#define CPU_FTRS_E6500 (CPU_FTR_NODSISRALIGN | \ +#define CPU_FTRS_E6500 ( \ CPU_FTR_LWSYNC | CPU_FTR_NOEXECUTE | \ CPU_FTR_DBELL | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \ CPU_FTR_DEBUG_LVL_EXC | CPU_FTR_EMB_HV | CPU_FTR_ALTIVEC_COMP | \ CPU_FTR_CELL_TB_BUG | CPU_FTR_SMT) -#define CPU_FTRS_GENERIC_32 (CPU_FTR_COMMON | CPU_FTR_NODSISRALIGN) /* 64-bit CPUs */ #define CPU_FTRS_PPC970 (CPU_FTR_LWSYNC | \ @@ -436,7 +408,7 @@ static inline void cpu_feature_keys_init(void) { } CPU_FTR_DSCR | CPU_FTR_SAO | CPU_FTR_ASYM_SMT | \ CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \ CPU_FTR_CFAR | CPU_FTR_HVMODE | \ - CPU_FTR_VMX_COPY | CPU_FTR_HAS_PPR | CPU_FTR_DABRX | CPU_FTR_PKEY) + CPU_FTR_VMX_COPY | CPU_FTR_HAS_PPR | CPU_FTR_DABRX ) #define CPU_FTRS_POWER8 (CPU_FTR_LWSYNC | \ CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | CPU_FTR_ARCH_206 |\ CPU_FTR_MMCRA | CPU_FTR_SMT | \ @@ -446,7 +418,7 @@ static inline void cpu_feature_keys_init(void) { } CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \ CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \ CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_DAWR | \ - CPU_FTR_ARCH_207S | CPU_FTR_TM_COMP | CPU_FTR_PKEY) + CPU_FTR_ARCH_207S | CPU_FTR_TM_COMP ) #define CPU_FTRS_POWER8E (CPU_FTRS_POWER8 | CPU_FTR_PMAO_BUG) #define CPU_FTRS_POWER9 (CPU_FTR_LWSYNC | \ CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | CPU_FTR_ARCH_206 |\ @@ -457,13 +429,31 @@ static inline void cpu_feature_keys_init(void) { } CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \ CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \ CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_ARCH_207S | \ - CPU_FTR_TM_COMP | CPU_FTR_ARCH_300 | CPU_FTR_PKEY | \ - CPU_FTR_P9_TLBIE_STQ_BUG | CPU_FTR_P9_TLBIE_ERAT_BUG | CPU_FTR_P9_TIDR) -#define CPU_FTRS_POWER9_DD2_0 CPU_FTRS_POWER9 -#define CPU_FTRS_POWER9_DD2_1 (CPU_FTRS_POWER9 | CPU_FTR_POWER9_DD2_1) + CPU_FTR_TM_COMP | CPU_FTR_ARCH_300 | CPU_FTR_P9_TLBIE_STQ_BUG | \ + CPU_FTR_P9_TLBIE_ERAT_BUG | CPU_FTR_P9_TIDR) +#define CPU_FTRS_POWER9_DD2_0 (CPU_FTRS_POWER9 | CPU_FTR_P9_RADIX_PREFETCH_BUG) +#define CPU_FTRS_POWER9_DD2_1 (CPU_FTRS_POWER9 | \ + CPU_FTR_P9_RADIX_PREFETCH_BUG | \ + CPU_FTR_POWER9_DD2_1) #define CPU_FTRS_POWER9_DD2_2 (CPU_FTRS_POWER9 | CPU_FTR_POWER9_DD2_1 | \ CPU_FTR_P9_TM_HV_ASSIST | \ CPU_FTR_P9_TM_XER_SO_BUG) +#define CPU_FTRS_POWER9_DD2_3 (CPU_FTRS_POWER9 | CPU_FTR_POWER9_DD2_1 | \ + CPU_FTR_P9_TM_HV_ASSIST | \ + CPU_FTR_P9_TM_XER_SO_BUG | \ + CPU_FTR_DAWR) +#define CPU_FTRS_POWER10 (CPU_FTR_LWSYNC | \ + CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | CPU_FTR_ARCH_206 |\ + CPU_FTR_MMCRA | CPU_FTR_SMT | \ + CPU_FTR_COHERENT_ICACHE | \ + CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \ + CPU_FTR_DSCR | CPU_FTR_SAO | \ + CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \ + CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \ + CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_ARCH_207S | \ + CPU_FTR_ARCH_300 | CPU_FTR_ARCH_31 | \ + CPU_FTR_DAWR | CPU_FTR_DAWR1 | \ + CPU_FTR_DEXCR_NPHIE) #define CPU_FTRS_CELL (CPU_FTR_LWSYNC | \ CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \ CPU_FTR_ALTIVEC_COMP | CPU_FTR_MMCRA | CPU_FTR_SMT | \ @@ -474,41 +464,42 @@ static inline void cpu_feature_keys_init(void) { } CPU_FTR_PURR | CPU_FTR_REAL_LE | CPU_FTR_DABRX) #define CPU_FTRS_COMPATIBLE (CPU_FTR_PPCAS_ARCH_V2) -#ifdef __powerpc64__ -#ifdef CONFIG_PPC_BOOK3E +#ifdef CONFIG_PPC64 +#ifdef CONFIG_PPC_BOOK3E_64 #define CPU_FTRS_POSSIBLE (CPU_FTRS_E6500 | CPU_FTRS_E5500) #else #ifdef CONFIG_CPU_LITTLE_ENDIAN #define CPU_FTRS_POSSIBLE \ (CPU_FTRS_POWER7 | CPU_FTRS_POWER8E | CPU_FTRS_POWER8 | \ CPU_FTR_ALTIVEC_COMP | CPU_FTR_VSX_COMP | CPU_FTRS_POWER9 | \ - CPU_FTRS_POWER9_DD2_1 | CPU_FTRS_POWER9_DD2_2) + CPU_FTRS_POWER9_DD2_1 | CPU_FTRS_POWER9_DD2_2 | \ + CPU_FTRS_POWER9_DD2_3 | CPU_FTRS_POWER10) #else #define CPU_FTRS_POSSIBLE \ (CPU_FTRS_PPC970 | CPU_FTRS_POWER5 | \ CPU_FTRS_POWER6 | CPU_FTRS_POWER7 | CPU_FTRS_POWER8E | \ CPU_FTRS_POWER8 | CPU_FTRS_CELL | CPU_FTRS_PA6T | \ CPU_FTR_VSX_COMP | CPU_FTR_ALTIVEC_COMP | CPU_FTRS_POWER9 | \ - CPU_FTRS_POWER9_DD2_1 | CPU_FTRS_POWER9_DD2_2) + CPU_FTRS_POWER9_DD2_1 | CPU_FTRS_POWER9_DD2_2 | \ + CPU_FTRS_POWER9_DD2_3 | CPU_FTRS_POWER10) #endif /* CONFIG_CPU_LITTLE_ENDIAN */ #endif #else enum { CPU_FTRS_POSSIBLE = -#ifdef CONFIG_PPC_BOOK3S_601 - CPU_FTRS_PPC601 | -#elif defined(CONFIG_PPC_BOOK3S_32) - CPU_FTRS_PPC601 | CPU_FTRS_603 | CPU_FTRS_604 | CPU_FTRS_740_NOTAU | +#ifdef CONFIG_PPC_BOOK3S_604 + CPU_FTRS_604 | CPU_FTRS_740_NOTAU | CPU_FTRS_740 | CPU_FTRS_750 | CPU_FTRS_750FX1 | CPU_FTRS_750FX2 | CPU_FTRS_750FX | CPU_FTRS_750GX | CPU_FTRS_7400_NOTAU | CPU_FTRS_7400 | CPU_FTRS_7450_20 | CPU_FTRS_7450_21 | CPU_FTRS_7450_23 | CPU_FTRS_7455_1 | CPU_FTRS_7455_20 | CPU_FTRS_7455 | CPU_FTRS_7447_10 | - CPU_FTRS_7447 | CPU_FTRS_7447A | CPU_FTRS_82XX | - CPU_FTRS_G2_LE | CPU_FTRS_E300 | CPU_FTRS_E300C2 | + CPU_FTRS_7447 | CPU_FTRS_7447A | CPU_FTRS_CLASSIC32 | -#else - CPU_FTRS_GENERIC_32 | +#endif +#ifdef CONFIG_PPC_BOOK3S_603 + CPU_FTRS_603 | CPU_FTRS_82XX | + CPU_FTRS_G2_LE | CPU_FTRS_E300 | CPU_FTRS_E300C2 | #endif #ifdef CONFIG_PPC_8xx CPU_FTRS_8XX | @@ -516,16 +507,12 @@ enum { #ifdef CONFIG_40x CPU_FTRS_40X | #endif -#ifdef CONFIG_44x - CPU_FTRS_44X | CPU_FTRS_440x6 | -#endif #ifdef CONFIG_PPC_47x CPU_FTRS_47X | CPU_FTR_476_DD2 | +#elif defined(CONFIG_44x) + CPU_FTRS_44X | CPU_FTRS_440x6 | #endif -#ifdef CONFIG_E200 - CPU_FTRS_E200 | -#endif -#ifdef CONFIG_E500 +#ifdef CONFIG_PPC_E500 CPU_FTRS_E500 | CPU_FTRS_E500_2 | #endif #ifdef CONFIG_PPC_E500MC @@ -535,8 +522,8 @@ enum { }; #endif /* __powerpc64__ */ -#ifdef __powerpc64__ -#ifdef CONFIG_PPC_BOOK3E +#ifdef CONFIG_PPC64 +#ifdef CONFIG_PPC_BOOK3E_64 #define CPU_FTRS_ALWAYS (CPU_FTRS_E6500 & CPU_FTRS_E5500) #else @@ -544,7 +531,6 @@ enum { #define CPU_FTRS_DT_CPU_BASE \ (CPU_FTR_LWSYNC | \ CPU_FTR_FPU_UNAVAILABLE | \ - CPU_FTR_NODSISRALIGN | \ CPU_FTR_NOEXECUTE | \ CPU_FTR_COHERENT_ICACHE | \ CPU_FTR_STCX_CHECKS_ADDRESS | \ @@ -560,33 +546,34 @@ enum { #define CPU_FTRS_ALWAYS \ (CPU_FTRS_POSSIBLE & ~CPU_FTR_HVMODE & CPU_FTRS_POWER7 & \ CPU_FTRS_POWER8E & CPU_FTRS_POWER8 & CPU_FTRS_POWER9 & \ - CPU_FTRS_POWER9_DD2_1 & CPU_FTRS_DT_CPU_BASE) + CPU_FTRS_POWER9_DD2_1 & CPU_FTRS_POWER9_DD2_2 & \ + CPU_FTRS_POWER10 & CPU_FTRS_DT_CPU_BASE) #else #define CPU_FTRS_ALWAYS \ (CPU_FTRS_PPC970 & CPU_FTRS_POWER5 & \ CPU_FTRS_POWER6 & CPU_FTRS_POWER7 & CPU_FTRS_CELL & \ CPU_FTRS_PA6T & CPU_FTRS_POWER8 & CPU_FTRS_POWER8E & \ ~CPU_FTR_HVMODE & CPU_FTRS_POSSIBLE & CPU_FTRS_POWER9 & \ - CPU_FTRS_POWER9_DD2_1 & CPU_FTRS_DT_CPU_BASE) + CPU_FTRS_POWER9_DD2_1 & CPU_FTRS_POWER9_DD2_2 & \ + CPU_FTRS_POWER10 & CPU_FTRS_DT_CPU_BASE) #endif /* CONFIG_CPU_LITTLE_ENDIAN */ #endif #else enum { CPU_FTRS_ALWAYS = -#ifdef CONFIG_PPC_BOOK3S_601 - CPU_FTRS_PPC601 & -#elif defined(CONFIG_PPC_BOOK3S_32) - CPU_FTRS_603 & CPU_FTRS_604 & CPU_FTRS_740_NOTAU & +#ifdef CONFIG_PPC_BOOK3S_604 + CPU_FTRS_604 & CPU_FTRS_740_NOTAU & CPU_FTRS_740 & CPU_FTRS_750 & CPU_FTRS_750FX1 & CPU_FTRS_750FX2 & CPU_FTRS_750FX & CPU_FTRS_750GX & CPU_FTRS_7400_NOTAU & CPU_FTRS_7400 & CPU_FTRS_7450_20 & CPU_FTRS_7450_21 & CPU_FTRS_7450_23 & CPU_FTRS_7455_1 & CPU_FTRS_7455_20 & CPU_FTRS_7455 & CPU_FTRS_7447_10 & - CPU_FTRS_7447 & CPU_FTRS_7447A & CPU_FTRS_82XX & - CPU_FTRS_G2_LE & CPU_FTRS_E300 & CPU_FTRS_E300C2 & + CPU_FTRS_7447 & CPU_FTRS_7447A & CPU_FTRS_CLASSIC32 & -#else - CPU_FTRS_GENERIC_32 & +#endif +#ifdef CONFIG_PPC_BOOK3S_603 + CPU_FTRS_603 & CPU_FTRS_82XX & + CPU_FTRS_G2_LE & CPU_FTRS_E300 & CPU_FTRS_E300C2 & #endif #ifdef CONFIG_PPC_8xx CPU_FTRS_8XX & @@ -594,13 +581,12 @@ enum { #ifdef CONFIG_40x CPU_FTRS_40X & #endif -#ifdef CONFIG_44x +#ifdef CONFIG_PPC_47x + CPU_FTRS_47X & +#elif defined(CONFIG_44x) CPU_FTRS_44X & CPU_FTRS_440x6 & #endif -#ifdef CONFIG_E200 - CPU_FTRS_E200 & -#endif -#ifdef CONFIG_E500 +#ifdef CONFIG_PPC_E500 CPU_FTRS_E500 & CPU_FTRS_E500_2 & #endif #ifdef CONFIG_PPC_E500MC @@ -611,7 +597,12 @@ enum { }; #endif /* __powerpc64__ */ -#define HBP_NUM 1 +/* + * Maximum number of hw breakpoint supported on powerpc. Number of + * breakpoints supported by actual hw might be less than this, which + * is decided at run time in nr_wp_slots(). + */ +#define HBP_NUM_MAX 2 #endif /* !__ASSEMBLY__ */ diff --git a/arch/powerpc/include/asm/cputhreads.h b/arch/powerpc/include/asm/cputhreads.h index deb99fd6e060..f26c430f3982 100644 --- a/arch/powerpc/include/asm/cputhreads.h +++ b/arch/powerpc/include/asm/cputhreads.h @@ -23,7 +23,6 @@ extern int threads_per_core; extern int threads_per_subcore; extern int threads_shift; -extern bool has_big_cores; extern cpumask_t threads_core_mask; #else #define threads_per_core 1 @@ -33,44 +32,11 @@ extern cpumask_t threads_core_mask; #define threads_core_mask (*get_cpu_mask(0)) #endif -/* cpu_thread_mask_to_cores - Return a cpumask of one per cores - * hit by the argument - * - * @threads: a cpumask of online threads - * - * This function returns a cpumask which will have one online cpu's - * bit set for each core that has at least one thread set in the argument. - * - * This can typically be used for things like IPI for tlb invalidations - * since those need to be done only once per core/TLB - */ -static inline cpumask_t cpu_thread_mask_to_cores(const struct cpumask *threads) -{ - cpumask_t tmp, res; - int i, cpu; - - cpumask_clear(&res); - for (i = 0; i < NR_CPUS; i += threads_per_core) { - cpumask_shift_left(&tmp, &threads_core_mask, i); - if (cpumask_intersects(threads, &tmp)) { - cpu = cpumask_next_and(-1, &tmp, cpu_online_mask); - if (cpu < nr_cpu_ids) - cpumask_set_cpu(cpu, &res); - } - } - return res; -} - static inline int cpu_nr_cores(void) { return nr_cpu_ids >> threads_shift; } -static inline cpumask_t cpu_online_cores_map(void) -{ - return cpu_thread_mask_to_cores(cpu_online_mask); -} - #ifdef CONFIG_SMP int cpu_core_index_of_thread(int cpu); int cpu_first_thread_of_core(int core); @@ -99,6 +65,36 @@ static inline int cpu_last_thread_sibling(int cpu) return cpu | (threads_per_core - 1); } +/* + * tlb_thread_siblings are siblings which share a TLB. This is not + * architected, is not something a hypervisor could emulate and a future + * CPU may change behaviour even in compat mode, so this should only be + * used on PowerNV, and only with care. + */ +static inline int cpu_first_tlb_thread_sibling(int cpu) +{ + if (cpu_has_feature(CPU_FTR_ARCH_300) && (threads_per_core == 8)) + return cpu & ~0x6; /* Big Core */ + else + return cpu_first_thread_sibling(cpu); +} + +static inline int cpu_last_tlb_thread_sibling(int cpu) +{ + if (cpu_has_feature(CPU_FTR_ARCH_300) && (threads_per_core == 8)) + return cpu | 0x6; /* Big Core */ + else + return cpu_last_thread_sibling(cpu); +} + +static inline int cpu_tlb_thread_sibling_step(void) +{ + if (cpu_has_feature(CPU_FTR_ARCH_300) && (threads_per_core == 8)) + return 2; /* Big Core */ + else + return 1; +} + static inline u32 get_tensr(void) { #ifdef CONFIG_BOOKE diff --git a/arch/powerpc/include/asm/cputime.h b/arch/powerpc/include/asm/cputime.h index 2431b4ada2fa..4961fb38e438 100644 --- a/arch/powerpc/include/asm/cputime.h +++ b/arch/powerpc/include/asm/cputime.h @@ -19,22 +19,10 @@ #include <asm/div64.h> #include <asm/time.h> #include <asm/param.h> - -typedef u64 __nocast cputime_t; -typedef u64 __nocast cputime64_t; - -#define cmpxchg_cputime(ptr, old, new) cmpxchg(ptr, old, new) +#include <asm/firmware.h> #ifdef __KERNEL__ -/* - * Convert cputime <-> microseconds - */ -extern u64 __cputime_usec_factor; - -static inline unsigned long cputime_to_usecs(const cputime_t ct) -{ - return mulhdu((__force u64) ct, __cputime_usec_factor); -} +#define cputime_to_nsecs(cputime) tb_to_ns(cputime) /* * PPC64 uses PACA which is task independent for storing accounting data while @@ -43,9 +31,12 @@ static inline unsigned long cputime_to_usecs(const cputime_t ct) */ #ifdef CONFIG_PPC64 #define get_accounting(tsk) (&get_paca()->accounting) +#define raw_get_accounting(tsk) (&local_paca->accounting) static inline void arch_vtime_task_switch(struct task_struct *tsk) { } + #else #define get_accounting(tsk) (&task_thread_info(tsk)->accounting) +#define raw_get_accounting(tsk) get_accounting(tsk) /* * Called from the context switch with interrupts disabled, to charge all * accumulated times to the current process, and to prepare accounting on @@ -60,6 +51,50 @@ static inline void arch_vtime_task_switch(struct task_struct *prev) } #endif +/* + * account_cpu_user_entry/exit runs "unreconciled", so can't trace, + * can't use get_paca() + */ +static notrace inline void account_cpu_user_entry(void) +{ + unsigned long tb = mftb(); + struct cpu_accounting_data *acct = raw_get_accounting(current); + + acct->utime += (tb - acct->starttime_user); + acct->starttime = tb; +} + +static notrace inline void account_cpu_user_exit(void) +{ + unsigned long tb = mftb(); + struct cpu_accounting_data *acct = raw_get_accounting(current); + + acct->stime += (tb - acct->starttime); + acct->starttime_user = tb; +} + +static notrace inline void account_stolen_time(void) +{ +#ifdef CONFIG_PPC_SPLPAR + if (firmware_has_feature(FW_FEATURE_SPLPAR)) { + struct lppaca *lp = local_paca->lppaca_ptr; + + if (unlikely(local_paca->dtl_ridx != be64_to_cpu(lp->dtl_idx))) + pseries_accumulate_stolen_time(); + } +#endif +} + #endif /* __KERNEL__ */ +#else /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ +static inline void account_cpu_user_entry(void) +{ +} +static inline void account_cpu_user_exit(void) +{ +} +static notrace inline void account_stolen_time(void) +{ +} #endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ #endif /* __POWERPC_CPUTIME_H */ diff --git a/arch/powerpc/include/asm/crashdump-ppc64.h b/arch/powerpc/include/asm/crashdump-ppc64.h new file mode 100644 index 000000000000..68d9717cc5ee --- /dev/null +++ b/arch/powerpc/include/asm/crashdump-ppc64.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef _ASM_POWERPC_CRASHDUMP_PPC64_H +#define _ASM_POWERPC_CRASHDUMP_PPC64_H + +/* + * Backup region - first 64KB of System RAM + * + * If ever the below macros are to be changed, please be judicious. + * The implicit assumptions are: + * - start, end & size are less than UINT32_MAX. + * - start & size are at least 8 byte aligned. + * + * For implementation details: arch/powerpc/purgatory/trampoline_64.S + */ +#define BACKUP_SRC_START 0 +#define BACKUP_SRC_END 0xffff +#define BACKUP_SRC_SIZE (BACKUP_SRC_END - BACKUP_SRC_START + 1) + +#endif /* __ASM_POWERPC_CRASHDUMP_PPC64_H */ diff --git a/arch/powerpc/include/asm/dbell.h b/arch/powerpc/include/asm/dbell.h index 4ce6808deed3..3e9da22a2779 100644 --- a/arch/powerpc/include/asm/dbell.h +++ b/arch/powerpc/include/asm/dbell.h @@ -11,8 +11,10 @@ #include <linux/smp.h> #include <linux/threads.h> +#include <asm/cputhreads.h> #include <asm/ppc-opcode.h> #include <asm/feature-fixups.h> +#include <asm/kvm_ppc.h> #define PPC_DBELL_MSG_BRDCAST (0x04000000) #define PPC_DBELL_TYPE(x) (((x) & 0xf) << (63-36)) @@ -87,9 +89,6 @@ static inline void ppc_msgsync(void) #endif /* CONFIG_PPC_BOOK3S */ -extern void doorbell_global_ipi(int cpu); -extern void doorbell_core_ipi(int cpu); -extern int doorbell_try_core_ipi(int cpu); extern void doorbell_exception(struct pt_regs *regs); static inline void ppc_msgsnd(enum ppc_dbell type, u32 flags, u32 tag) @@ -100,4 +99,63 @@ static inline void ppc_msgsnd(enum ppc_dbell type, u32 flags, u32 tag) _ppc_msgsnd(msg); } +#ifdef CONFIG_SMP + +/* + * Doorbells must only be used if CPU_FTR_DBELL is available. + * msgsnd is used in HV, and msgsndp is used in !HV. + * + * These should be used by platform code that is aware of restrictions. + * Other arch code should use ->cause_ipi. + * + * doorbell_global_ipi() sends a dbell to any target CPU. + * Must be used only by architectures that address msgsnd target + * by PIR/get_hard_smp_processor_id. + */ +static inline void doorbell_global_ipi(int cpu) +{ + u32 tag = get_hard_smp_processor_id(cpu); + + kvmppc_set_host_ipi(cpu); + /* Order previous accesses vs. msgsnd, which is treated as a store */ + ppc_msgsnd_sync(); + ppc_msgsnd(PPC_DBELL_MSGTYPE, 0, tag); +} + +/* + * doorbell_core_ipi() sends a dbell to a target CPU in the same core. + * Must be used only by architectures that address msgsnd target + * by TIR/cpu_thread_in_core. + */ +static inline void doorbell_core_ipi(int cpu) +{ + u32 tag = cpu_thread_in_core(cpu); + + kvmppc_set_host_ipi(cpu); + /* Order previous accesses vs. msgsnd, which is treated as a store */ + ppc_msgsnd_sync(); + ppc_msgsnd(PPC_DBELL_MSGTYPE, 0, tag); +} + +/* + * Attempt to cause a core doorbell if destination is on the same core. + * Returns 1 on success, 0 on failure. + */ +static inline int doorbell_try_core_ipi(int cpu) +{ + int this_cpu = get_cpu(); + int ret = 0; + + if (cpumask_test_cpu(cpu, cpu_sibling_mask(this_cpu))) { + doorbell_core_ipi(cpu); + ret = 1; + } + + put_cpu(); + + return ret; +} + +#endif /* CONFIG_SMP */ + #endif /* _ASM_POWERPC_DBELL_H */ diff --git a/arch/powerpc/include/asm/dcr-native.h b/arch/powerpc/include/asm/dcr-native.h index 7141ccea8c94..a92059964579 100644 --- a/arch/powerpc/include/asm/dcr-native.h +++ b/arch/powerpc/include/asm/dcr-native.h @@ -53,8 +53,8 @@ static inline void mtdcrx(unsigned int reg, unsigned int val) #define mfdcr(rn) \ ({unsigned int rval; \ if (__builtin_constant_p(rn) && rn < 1024) \ - asm volatile("mfdcr %0," __stringify(rn) \ - : "=r" (rval)); \ + asm volatile("mfdcr %0, %1" : "=r" (rval) \ + : "n" (rn)); \ else if (likely(cpu_has_feature(CPU_FTR_INDEXED_DCR))) \ rval = mfdcrx(rn); \ else \ @@ -64,8 +64,8 @@ static inline void mtdcrx(unsigned int reg, unsigned int val) #define mtdcr(rn, v) \ do { \ if (__builtin_constant_p(rn) && rn < 1024) \ - asm volatile("mtdcr " __stringify(rn) ",%0" \ - : : "r" (v)); \ + asm volatile("mtdcr %0, %1" \ + : : "n" (rn), "r" (v)); \ else if (likely(cpu_has_feature(CPU_FTR_INDEXED_DCR))) \ mtdcrx(rn, v); \ else \ diff --git a/arch/powerpc/include/asm/debug.h b/arch/powerpc/include/asm/debug.h index 7756026b95ca..51c744608f37 100644 --- a/arch/powerpc/include/asm/debug.h +++ b/arch/powerpc/include/asm/debug.h @@ -45,15 +45,13 @@ static inline int debugger_break_match(struct pt_regs *regs) { return 0; } static inline int debugger_fault_handler(struct pt_regs *regs) { return 0; } #endif -void __set_breakpoint(struct arch_hw_breakpoint *brk); +void __set_breakpoint(int nr, struct arch_hw_breakpoint *brk); +void suspend_breakpoints(void); +void restore_breakpoints(void); bool ppc_breakpoint_available(void); #ifdef CONFIG_PPC_ADV_DEBUG_REGS extern void do_send_trap(struct pt_regs *regs, unsigned long address, unsigned long error_code, int brkpt); -#else - -extern void do_break(struct pt_regs *regs, unsigned long address, - unsigned long error_code); #endif #endif /* _ASM_POWERPC_DEBUG_H */ diff --git a/arch/powerpc/include/asm/debugfs.h b/arch/powerpc/include/asm/debugfs.h deleted file mode 100644 index 2c5c48571d75..000000000000 --- a/arch/powerpc/include/asm/debugfs.h +++ /dev/null @@ -1,13 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -#ifndef _ASM_POWERPC_DEBUGFS_H -#define _ASM_POWERPC_DEBUGFS_H - -/* - * Copyright 2017, Michael Ellerman, IBM Corporation. - */ - -#include <linux/debugfs.h> - -extern struct dentry *powerpc_debugfs_root; - -#endif /* _ASM_POWERPC_DEBUGFS_H */ diff --git a/arch/powerpc/include/asm/delay.h b/arch/powerpc/include/asm/delay.h index 66963f7d3e64..51bb8c1476c7 100644 --- a/arch/powerpc/include/asm/delay.h +++ b/arch/powerpc/include/asm/delay.h @@ -54,7 +54,7 @@ extern void udelay(unsigned long usecs); ({ \ typeof(condition) __ret; \ unsigned long __loops = tb_ticks_per_usec * timeout; \ - unsigned long __start = get_tbl(); \ + unsigned long __start = mftb(); \ \ if (delay) { \ while (!(__ret = (condition)) && \ diff --git a/arch/powerpc/include/asm/device.h b/arch/powerpc/include/asm/device.h index 266542769e4b..47ed639f3b8f 100644 --- a/arch/powerpc/include/asm/device.h +++ b/arch/powerpc/include/asm/device.h @@ -19,11 +19,6 @@ struct iommu_table; */ struct dev_archdata { /* - * Set to %true if the dma_iommu_ops are requested to use a direct - * window instead of dynamically mapping memory. - */ - bool iommu_bypass : 1; - /* * These two used to be a union. However, with the hybrid ops we need * both so here we store both a DMA offset for direct mappings and * an iommu_table for remapped DMA. @@ -34,9 +29,6 @@ struct dev_archdata { struct iommu_table *iommu_table_base; #endif -#ifdef CONFIG_IOMMU_API - void *iommu_domain; -#endif #ifdef CONFIG_PPC64 struct pci_dn *pci_data; #endif @@ -49,10 +41,18 @@ struct dev_archdata { #ifdef CONFIG_CXL_BASE struct cxl_context *cxl_ctx; #endif +#ifdef CONFIG_PCI_IOV + void *iov_data; +#endif }; struct pdev_archdata { u64 dma_mask; + /* + * Pointer to nvdimm_pmu structure, to handle the unregistering + * of pmu device + */ + void *priv; }; #endif /* _ASM_POWERPC_DEVICE_H */ diff --git a/arch/powerpc/include/asm/dma-direct.h b/arch/powerpc/include/asm/dma-direct.h index abc154d784b0..128304cbee1d 100644 --- a/arch/powerpc/include/asm/dma-direct.h +++ b/arch/powerpc/include/asm/dma-direct.h @@ -2,12 +2,12 @@ #ifndef ASM_POWERPC_DMA_DIRECT_H #define ASM_POWERPC_DMA_DIRECT_H 1 -static inline dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr) +static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr) { return paddr + dev->archdata.dma_offset; } -static inline phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr) +static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr) { return daddr - dev->archdata.dma_offset; } diff --git a/arch/powerpc/include/asm/dma.h b/arch/powerpc/include/asm/dma.h index 1b4f0254868f..d97c66d9ae34 100644 --- a/arch/powerpc/include/asm/dma.h +++ b/arch/powerpc/include/asm/dma.h @@ -151,10 +151,9 @@ #define DMA2_EXT_REG 0x4D6 #ifndef __powerpc64__ - /* in arch/ppc/kernel/setup.c -- Cort */ + /* in arch/powerpc/kernel/setup_32.c -- Cort */ extern unsigned int DMA_MODE_WRITE; extern unsigned int DMA_MODE_READ; - extern unsigned long ISA_DMA_THRESHOLD; #else #define DMA_MODE_READ 0x44 /* I/O to memory, no autoinit, increment, single mode */ #define DMA_MODE_WRITE 0x48 /* memory to I/O, no autoinit, increment, single mode */ @@ -341,11 +340,5 @@ extern int request_dma(unsigned int dmanr, const char *device_id); /* release it again */ extern void free_dma(unsigned int dmanr); -#ifdef CONFIG_PCI -extern int isa_dma_bridge_buggy; -#else -#define isa_dma_bridge_buggy (0) -#endif - #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_DMA_H */ diff --git a/arch/powerpc/include/asm/drmem.h b/arch/powerpc/include/asm/drmem.h index 3d76e1c388c2..13bf6dee8e2d 100644 --- a/arch/powerpc/include/asm/drmem.h +++ b/arch/powerpc/include/asm/drmem.h @@ -8,31 +8,47 @@ #ifndef _ASM_POWERPC_LMB_H #define _ASM_POWERPC_LMB_H +#include <linux/sched.h> + struct drmem_lmb { u64 base_addr; u32 drc_index; u32 aa_index; u32 flags; -#ifdef CONFIG_MEMORY_HOTPLUG - int nid; -#endif }; struct drmem_lmb_info { struct drmem_lmb *lmbs; int n_lmbs; - u32 lmb_size; + u64 lmb_size; }; +struct device_node; +struct property; + extern struct drmem_lmb_info *drmem_info; +static inline struct drmem_lmb *drmem_lmb_next(struct drmem_lmb *lmb, + const struct drmem_lmb *start) +{ + /* + * DLPAR code paths can take several milliseconds per element + * when interacting with firmware. Ensure that we don't + * unfairly monopolize the CPU. + */ + if (((++lmb - start) % 16) == 0) + cond_resched(); + + return lmb; +} + #define for_each_drmem_lmb_in_range(lmb, start, end) \ - for ((lmb) = (start); (lmb) <= (end); (lmb)++) + for ((lmb) = (start); (lmb) < (end); lmb = drmem_lmb_next(lmb, start)) #define for_each_drmem_lmb(lmb) \ for_each_drmem_lmb_in_range((lmb), \ &drmem_info->lmbs[0], \ - &drmem_info->lmbs[drmem_info->n_lmbs - 1]) + &drmem_info->lmbs[drmem_info->n_lmbs]) /* * The of_drconf_cell_v1 struct defines the layout of the LMB data @@ -65,8 +81,9 @@ struct of_drconf_cell_v2 { #define DRCONF_MEM_ASSIGNED 0x00000008 #define DRCONF_MEM_AI_INVALID 0x00000040 #define DRCONF_MEM_RESERVED 0x00000080 +#define DRCONF_MEM_HOTREMOVABLE 0x00000100 -static inline u32 drmem_lmb_size(void) +static inline u64 drmem_lmb_size(void) { return drmem_info->lmb_size; } @@ -89,13 +106,15 @@ static inline bool drmem_lmb_reserved(struct drmem_lmb *lmb) } u64 drmem_lmb_memory_max(void); -void __init walk_drmem_lmbs(struct device_node *dn, - void (*func)(struct drmem_lmb *, const __be32 **)); +int walk_drmem_lmbs(struct device_node *dn, void *data, + int (*func)(struct drmem_lmb *, const __be32 **, void *)); int drmem_update_dt(void); #ifdef CONFIG_PPC_PSERIES -void __init walk_drmem_lmbs_early(unsigned long node, - void (*func)(struct drmem_lmb *, const __be32 **)); +int __init +walk_drmem_lmbs_early(unsigned long node, void *data, + int (*func)(struct drmem_lmb *, const __be32 **, void *)); +void drmem_update_lmbs(struct property *prop); #endif static inline void invalidate_lmb_associativity_index(struct drmem_lmb *lmb) @@ -103,22 +122,4 @@ static inline void invalidate_lmb_associativity_index(struct drmem_lmb *lmb) lmb->aa_index = 0xffffffff; } -#ifdef CONFIG_MEMORY_HOTPLUG -static inline void lmb_set_nid(struct drmem_lmb *lmb) -{ - lmb->nid = memory_add_physaddr_to_nid(lmb->base_addr); -} -static inline void lmb_clear_nid(struct drmem_lmb *lmb) -{ - lmb->nid = -1; -} -#else -static inline void lmb_set_nid(struct drmem_lmb *lmb) -{ -} -static inline void lmb_clear_nid(struct drmem_lmb *lmb) -{ -} -#endif - #endif /* _ASM_POWERPC_LMB_H */ diff --git a/arch/powerpc/include/asm/dtl.h b/arch/powerpc/include/asm/dtl.h new file mode 100644 index 000000000000..d6f43d149f8d --- /dev/null +++ b/arch/powerpc/include/asm/dtl.h @@ -0,0 +1,43 @@ +#ifndef _ASM_POWERPC_DTL_H +#define _ASM_POWERPC_DTL_H + +#include <asm/lppaca.h> +#include <linux/spinlock_types.h> + +/* + * Layout of entries in the hypervisor's dispatch trace log buffer. + */ +struct dtl_entry { + u8 dispatch_reason; + u8 preempt_reason; + __be16 processor_id; + __be32 enqueue_to_dispatch_time; + __be32 ready_to_enqueue_time; + __be32 waiting_to_ready_time; + __be64 timebase; + __be64 fault_addr; + __be64 srr0; + __be64 srr1; +}; + +#define DISPATCH_LOG_BYTES 4096 /* bytes per cpu */ +#define N_DISPATCH_LOG (DISPATCH_LOG_BYTES / sizeof(struct dtl_entry)) + +/* + * Dispatch trace log event enable mask: + * 0x1: voluntary virtual processor waits + * 0x2: time-slice preempts + * 0x4: virtual partition memory page faults + */ +#define DTL_LOG_CEDE 0x1 +#define DTL_LOG_PREEMPT 0x2 +#define DTL_LOG_FAULT 0x4 +#define DTL_LOG_ALL (DTL_LOG_CEDE | DTL_LOG_PREEMPT | DTL_LOG_FAULT) + +extern struct kmem_cache *dtl_cache; +extern rwlock_t dtl_access_lock; + +extern void register_dtl_buffer(int cpu); +extern void alloc_dtl_buffers(unsigned long *time_limit); + +#endif /* _ASM_POWERPC_DTL_H */ diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h index 6f9b2a12540a..514dd056c2c8 100644 --- a/arch/powerpc/include/asm/eeh.h +++ b/arch/powerpc/include/asm/eeh.h @@ -27,7 +27,6 @@ struct pci_dn; #define EEH_FORCE_DISABLED 0x02 /* EEH disabled */ #define EEH_PROBE_MODE_DEV 0x04 /* From PCI device */ #define EEH_PROBE_MODE_DEVTREE 0x08 /* From device tree */ -#define EEH_VALID_PE_ZERO 0x10 /* PE#0 is valid */ #define EEH_ENABLE_IO_FOR_LOG 0x20 /* Enable IO for log */ #define EEH_EARLY_DUMP_LOG 0x40 /* Dump log immediately */ @@ -74,7 +73,6 @@ struct pci_dn; struct eeh_pe { int type; /* PE type: PHB/Bus/Device */ int state; /* PE EEH dependent mode */ - int config_addr; /* Traditional PCI address */ int addr; /* PE configuration address */ struct pci_controller *phb; /* Associated PHB */ struct pci_bus *bus; /* Top PCI bus for bus PE */ @@ -133,7 +131,6 @@ static inline bool eeh_pe_passed(struct eeh_pe *pe) struct eeh_dev { int mode; /* EEH mode */ - int class_code; /* Class code of the device */ int bdfn; /* bdfn of device (for cfg ops) */ struct pci_controller *controller; int pe_config_addr; /* PE config address */ @@ -148,7 +145,10 @@ struct eeh_dev { struct pci_dn *pdn; /* Associated PCI device node */ struct pci_dev *pdev; /* Associated PCI device */ bool in_error; /* Error flag for edev */ + + /* VF specific properties */ struct pci_dev *physfn; /* Associated SRIOV PF */ + int vf_index; /* Index of this VF */ }; /* "fmt" must be a simple literal string */ @@ -214,21 +214,19 @@ enum { struct eeh_ops { char *name; - int (*init)(void); - void* (*probe)(struct pci_dn *pdn, void *data); + struct eeh_dev *(*probe)(struct pci_dev *pdev); int (*set_option)(struct eeh_pe *pe, int option); - int (*get_pe_addr)(struct eeh_pe *pe); int (*get_state)(struct eeh_pe *pe, int *delay); int (*reset)(struct eeh_pe *pe, int option); int (*get_log)(struct eeh_pe *pe, int severity, char *drv_log, unsigned long len); int (*configure_bridge)(struct eeh_pe *pe); int (*err_inject)(struct eeh_pe *pe, int type, int func, unsigned long addr, unsigned long mask); - int (*read_config)(struct pci_dn *pdn, int where, int size, u32 *val); - int (*write_config)(struct pci_dn *pdn, int where, int size, u32 val); + int (*read_config)(struct eeh_dev *edev, int where, int size, u32 *val); + int (*write_config)(struct eeh_dev *edev, int where, int size, u32 val); int (*next_error)(struct eeh_pe **pe); - int (*restore_config)(struct pci_dn *pdn); - int (*notify_resume)(struct pci_dn *pdn); + int (*restore_config)(struct eeh_dev *edev); + int (*notify_resume)(struct eeh_dev *edev); }; extern int eeh_subsystem_flags; @@ -280,10 +278,9 @@ int eeh_phb_pe_create(struct pci_controller *phb); int eeh_wait_state(struct eeh_pe *pe, int max_wait); struct eeh_pe *eeh_phb_pe_get(struct pci_controller *phb); struct eeh_pe *eeh_pe_next(struct eeh_pe *pe, struct eeh_pe *root); -struct eeh_pe *eeh_pe_get(struct pci_controller *phb, - int pe_no, int config_addr); -int eeh_add_to_parent_pe(struct eeh_dev *edev); -int eeh_rmv_from_parent_pe(struct eeh_dev *edev); +struct eeh_pe *eeh_pe_get(struct pci_controller *phb, int pe_no); +int eeh_pe_tree_insert(struct eeh_dev *edev, struct eeh_pe *new_pe_parent); +int eeh_pe_tree_remove(struct eeh_dev *edev); void eeh_pe_update_time_stamp(struct eeh_pe *pe); void *eeh_pe_traverse(struct eeh_pe *root, eeh_pe_traverse_func fn, void *flag); @@ -293,19 +290,12 @@ void eeh_pe_restore_bars(struct eeh_pe *pe); const char *eeh_pe_loc_get(struct eeh_pe *pe); struct pci_bus *eeh_pe_bus_get(struct eeh_pe *pe); -struct eeh_dev *eeh_dev_init(struct pci_dn *pdn); -void eeh_dev_phb_init_dynamic(struct pci_controller *phb); void eeh_show_enabled(void); -int __init eeh_ops_register(struct eeh_ops *ops); -int __exit eeh_ops_unregister(const char *name); +int __init eeh_init(struct eeh_ops *ops); int eeh_check_failure(const volatile void __iomem *token); int eeh_dev_check_failure(struct eeh_dev *edev); void eeh_addr_cache_init(void); -void eeh_add_device_early(struct pci_dn *); -void eeh_add_device_tree_early(struct pci_dn *); -void eeh_add_device_late(struct pci_dev *); -void eeh_add_device_tree_late(struct pci_bus *); -void eeh_add_sysfs_files(struct pci_bus *); +void eeh_probe_device(struct pci_dev *pdev); void eeh_remove_device(struct pci_dev *); int eeh_unfreeze_pe(struct eeh_pe *pe); int eeh_pe_reset_and_recover(struct eeh_pe *pe); @@ -318,7 +308,6 @@ int eeh_pe_reset(struct eeh_pe *pe, int option, bool include_passed); int eeh_pe_configure(struct eeh_pe *pe); int eeh_pe_inject_err(struct eeh_pe *pe, int type, int func, unsigned long addr, unsigned long mask); -int eeh_restore_vf_config(struct pci_dn *pdn); /** * EEH_POSSIBLE_ERROR() -- test for possible MMIO failure. @@ -344,13 +333,6 @@ static inline bool eeh_enabled(void) static inline void eeh_show_enabled(void) { } -static inline void *eeh_dev_init(struct pci_dn *pdn, void *data) -{ - return NULL; -} - -static inline void eeh_dev_phb_init_dynamic(struct pci_controller *phb) { } - static inline int eeh_check_failure(const volatile void __iomem *token) { return 0; @@ -360,22 +342,19 @@ static inline int eeh_check_failure(const volatile void __iomem *token) static inline void eeh_addr_cache_init(void) { } -static inline void eeh_add_device_early(struct pci_dn *pdn) { } - -static inline void eeh_add_device_tree_early(struct pci_dn *pdn) { } - -static inline void eeh_add_device_late(struct pci_dev *dev) { } - -static inline void eeh_add_device_tree_late(struct pci_bus *bus) { } - -static inline void eeh_add_sysfs_files(struct pci_bus *bus) { } +static inline void eeh_probe_device(struct pci_dev *dev) { } static inline void eeh_remove_device(struct pci_dev *dev) { } #define EEH_POSSIBLE_ERROR(val, type) (0) #define EEH_IO_ERROR_VALUE(size) (-1UL) +static inline int eeh_phb_pe_create(struct pci_controller *phb) { return 0; } #endif /* CONFIG_EEH */ +#if defined(CONFIG_PPC_PSERIES) && defined(CONFIG_EEH) +void pseries_eeh_init_edev_recursive(struct pci_dn *pdn); +#endif + #ifdef CONFIG_PPC64 /* * MMIO read/write operations with EEH support. @@ -475,7 +454,7 @@ static inline void eeh_readsl(const volatile void __iomem *addr, void * buf, } -void eeh_cache_debugfs_init(void); +void __init eeh_cache_debugfs_init(void); #endif /* CONFIG_PPC64 */ #endif /* __KERNEL__ */ diff --git a/arch/powerpc/include/asm/elf.h b/arch/powerpc/include/asm/elf.h index 57c229a86f08..79f1c480b5eb 100644 --- a/arch/powerpc/include/asm/elf.h +++ b/arch/powerpc/include/asm/elf.h @@ -53,8 +53,6 @@ static inline void ppc_elf_core_copy_regs(elf_gregset_t elf_regs, } #define ELF_CORE_COPY_REGS(gregs, regs) ppc_elf_core_copy_regs(gregs, regs); -typedef elf_vrregset_t elf_fpxregset_t; - /* ELF_HWCAP yields a mask that user programs can use to figure out what instruction set this cpu supports. This could be done in userspace, but it's not easy, and we've already done it here. */ @@ -162,7 +160,7 @@ extern int arch_setup_additional_pages(struct linux_binprm *bprm, * even if DLINFO_ARCH_ITEMS goes to zero or is undefined. * update AT_VECTOR_SIZE_ARCH if the number of NEW_AUX_ENT entries changes */ -#define ARCH_DLINFO \ +#define COMMON_ARCH_DLINFO \ do { \ /* Handle glibc compatibility. */ \ NEW_AUX_ENT(AT_IGNOREPPC, AT_IGNOREPPC); \ @@ -170,12 +168,30 @@ do { \ /* Cache size items */ \ NEW_AUX_ENT(AT_DCACHEBSIZE, dcache_bsize); \ NEW_AUX_ENT(AT_ICACHEBSIZE, icache_bsize); \ - NEW_AUX_ENT(AT_UCACHEBSIZE, ucache_bsize); \ - VDSO_AUX_ENT(AT_SYSINFO_EHDR, current->mm->context.vdso_base); \ + NEW_AUX_ENT(AT_UCACHEBSIZE, 0); \ + VDSO_AUX_ENT(AT_SYSINFO_EHDR, (unsigned long)current->mm->context.vdso);\ ARCH_DLINFO_CACHE_GEOMETRY; \ } while (0) +#define ARCH_DLINFO \ +do { \ + COMMON_ARCH_DLINFO; \ + NEW_AUX_ENT(AT_MINSIGSTKSZ, get_min_sigframe_size()); \ +} while (0) + +#define COMPAT_ARCH_DLINFO \ +do { \ + COMMON_ARCH_DLINFO; \ + NEW_AUX_ENT(AT_MINSIGSTKSZ, get_min_sigframe_size_compat()); \ +} while (0) + /* Relocate the kernel image to @final_address */ void relocate(unsigned long final_address); +struct func_desc { + unsigned long addr; + unsigned long toc; + unsigned long env; +}; + #endif /* _ASM_POWERPC_ELF_H */ diff --git a/arch/powerpc/include/asm/epapr_hcalls.h b/arch/powerpc/include/asm/epapr_hcalls.h index d3a7e36f1402..cdf3c6df5123 100644 --- a/arch/powerpc/include/asm/epapr_hcalls.h +++ b/arch/powerpc/include/asm/epapr_hcalls.h @@ -37,7 +37,7 @@ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. */ -/* A "hypercall" is an "sc 1" instruction. This header file file provides C +/* A "hypercall" is an "sc 1" instruction. This header file provides C * wrapper functions for the ePAPR hypervisor interface. It is inteded * for use by Linux device drivers and other operating systems. * @@ -65,7 +65,7 @@ * but the gcc inline assembly syntax does not allow us to specify registers * on the clobber list that are also on the input/output list. Therefore, * the lists of clobbered registers depends on the number of register - * parmeters ("+r" and "=r") passed to the hypercall. + * parameters ("+r" and "=r") passed to the hypercall. * * Each assembly block should use one of the HCALL_CLOBBERSx macros. As a * general rule, 'x' is the number of parameters passed to the assembly @@ -246,7 +246,7 @@ static inline unsigned int ev_int_get_mask(unsigned int interrupt, * ev_int_eoi - signal the end of interrupt processing * @interrupt: the interrupt number * - * This function signals the end of processing for the the specified + * This function signals the end of processing for the specified * interrupt, which must be the interrupt currently in service. By * definition, this is also the highest-priority interrupt. * diff --git a/arch/powerpc/include/asm/exception-64e.h b/arch/powerpc/include/asm/exception-64e.h index 54a98ef7d7fe..b1ef1e92c34a 100644 --- a/arch/powerpc/include/asm/exception-64e.h +++ b/arch/powerpc/include/asm/exception-64e.h @@ -66,14 +66,7 @@ #define EX_TLB_SRR0 (10 * 8) #define EX_TLB_SRR1 (11 * 8) #define EX_TLB_R7 (12 * 8) -#ifdef CONFIG_BOOK3E_MMU_TLB_STATS -#define EX_TLB_R8 (13 * 8) -#define EX_TLB_R9 (14 * 8) -#define EX_TLB_LR (15 * 8) -#define EX_TLB_SIZE (16 * 8) -#else #define EX_TLB_SIZE (13 * 8) -#endif #define START_EXCEPTION(label) \ .globl exc_##label##_book3e; \ @@ -110,8 +103,7 @@ exc_##label##_book3e: std r11,EX_TLB_R12(r12); \ mtspr SPRN_SPRG_TLB_EXFRAME,r14; \ std r15,EX_TLB_SRR1(r12); \ - std r16,EX_TLB_SRR0(r12); \ - TLB_MISS_PROLOG_STATS + std r16,EX_TLB_SRR0(r12); /* And these are the matching epilogs that restores things * @@ -143,7 +135,6 @@ exc_##label##_book3e: mtspr SPRN_SRR0,r15; \ ld r15,EX_TLB_R15(r12); \ mtspr SPRN_SRR1,r16; \ - TLB_MISS_RESTORE_STATS \ ld r16,EX_TLB_R16(r12); \ ld r12,EX_TLB_R12(r12); \ @@ -158,53 +149,19 @@ exc_##label##_book3e: addi r11,r13,PACA_EXTLB; \ TLB_MISS_RESTORE(r11) -#ifdef CONFIG_BOOK3E_MMU_TLB_STATS -#define TLB_MISS_PROLOG_STATS \ - mflr r10; \ - std r8,EX_TLB_R8(r12); \ - std r9,EX_TLB_R9(r12); \ - std r10,EX_TLB_LR(r12); -#define TLB_MISS_RESTORE_STATS \ - ld r16,EX_TLB_LR(r12); \ - ld r9,EX_TLB_R9(r12); \ - ld r8,EX_TLB_R8(r12); \ - mtlr r16; -#define TLB_MISS_STATS_D(name) \ - addi r9,r13,MMSTAT_DSTATS+name; \ - bl tlb_stat_inc; -#define TLB_MISS_STATS_I(name) \ - addi r9,r13,MMSTAT_ISTATS+name; \ - bl tlb_stat_inc; -#define TLB_MISS_STATS_X(name) \ - ld r8,PACA_EXTLB+EX_TLB_ESR(r13); \ - cmpdi cr2,r8,-1; \ - beq cr2,61f; \ - addi r9,r13,MMSTAT_DSTATS+name; \ - b 62f; \ -61: addi r9,r13,MMSTAT_ISTATS+name; \ -62: bl tlb_stat_inc; -#define TLB_MISS_STATS_SAVE_INFO \ - std r14,EX_TLB_ESR(r12); /* save ESR */ -#define TLB_MISS_STATS_SAVE_INFO_BOLTED \ - std r14,PACA_EXTLB+EX_TLB_ESR(r13); /* save ESR */ -#else -#define TLB_MISS_PROLOG_STATS -#define TLB_MISS_RESTORE_STATS -#define TLB_MISS_PROLOG_STATS_BOLTED -#define TLB_MISS_RESTORE_STATS_BOLTED -#define TLB_MISS_STATS_D(name) -#define TLB_MISS_STATS_I(name) -#define TLB_MISS_STATS_X(name) -#define TLB_MISS_STATS_Y(name) -#define TLB_MISS_STATS_SAVE_INFO -#define TLB_MISS_STATS_SAVE_INFO_BOLTED +#ifndef __ASSEMBLY__ +extern unsigned int interrupt_base_book3e; #endif #define SET_IVOR(vector_number, vector_offset) \ LOAD_REG_ADDR(r3,interrupt_base_book3e);\ ori r3,r3,vector_offset@l; \ mtspr SPRN_IVOR##vector_number,r3; - +/* + * powerpc relies on return from interrupt/syscall being context synchronising + * (which rfi is) to support ARCH_HAS_MEMBARRIER_SYNC_CORE without additional + * synchronisation instructions. + */ #define RFI_TO_KERNEL \ rfi diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h index 33f4f72eb035..bb6f78fcf981 100644 --- a/arch/powerpc/include/asm/exception-64s.h +++ b/arch/powerpc/include/asm/exception-64s.h @@ -33,11 +33,20 @@ #include <asm/feature-fixups.h> /* PACA save area size in u64 units (exgen, exmc, etc) */ -#if defined(CONFIG_RELOCATABLE) #define EX_SIZE 10 -#else -#define EX_SIZE 9 -#endif + +/* PACA save area offsets */ +#define EX_R9 0 +#define EX_R10 8 +#define EX_R11 16 +#define EX_R12 24 +#define EX_R13 32 +#define EX_DAR 40 +#define EX_DSISR 48 +#define EX_CCR 52 +#define EX_CFAR 56 +#define EX_PPR 64 +#define EX_CTR 72 /* * maximum recursive depth of MCE exceptions @@ -61,17 +70,45 @@ nop; \ nop +#define ENTRY_FLUSH_SLOT \ + ENTRY_FLUSH_FIXUP_SECTION; \ + nop; \ + nop; \ + nop; + +#define SCV_ENTRY_FLUSH_SLOT \ + SCV_ENTRY_FLUSH_FIXUP_SECTION; \ + nop; \ + nop; \ + nop; + /* * r10 must be free to use, r13 must be paca */ #define INTERRUPT_TO_KERNEL \ - STF_ENTRY_BARRIER_SLOT + STF_ENTRY_BARRIER_SLOT; \ + ENTRY_FLUSH_SLOT + +/* + * r10, ctr must be free to use, r13 must be paca + */ +#define SCV_INTERRUPT_TO_KERNEL \ + STF_ENTRY_BARRIER_SLOT; \ + SCV_ENTRY_FLUSH_SLOT /* * Macros for annotating the expected destination of (h)rfid * * The nop instructions allow us to insert one or more instructions to flush the * L1-D cache when returning to userspace or a guest. + * + * powerpc relies on return from interrupt/syscall being context synchronising + * (which hrfid, rfid, and rfscv are) to support ARCH_HAS_MEMBARRIER_SYNC_CORE + * without additional synchronisation instructions. + * + * soft-masked interrupt replay does not include a context-synchronising rfid, + * but those always return to kernel, the sync is only required when returning + * to user. */ #define RFI_FLUSH_SLOT \ RFI_FLUSH_FIXUP_SECTION; \ @@ -127,6 +164,15 @@ hrfid; \ b hrfi_flush_fallback +#define RFSCV_TO_USER \ + STF_EXIT_BARRIER_SLOT; \ + RFI_FLUSH_SLOT; \ + RFSCV; \ + b rfscv_flush_fallback + +#else /* __ASSEMBLY__ */ +/* Prototype for function defined in exceptions-64s.S */ +void do_uaccess_flush(void); #endif /* __ASSEMBLY__ */ #endif /* _ASM_POWERPC_EXCEPTION_H */ diff --git a/arch/powerpc/include/asm/extable.h b/arch/powerpc/include/asm/extable.h index eb91b2d2935a..26ce2e5c0fa8 100644 --- a/arch/powerpc/include/asm/extable.h +++ b/arch/powerpc/include/asm/extable.h @@ -17,6 +17,8 @@ #define ARCH_HAS_RELATIVE_EXTABLE +#ifndef __ASSEMBLY__ + struct exception_table_entry { int insn; int fixup; @@ -28,3 +30,15 @@ static inline unsigned long extable_fixup(const struct exception_table_entry *x) } #endif + +/* + * Helper macro for exception table entries + */ +#define EX_TABLE(_fault, _target) \ + stringify_in_c(.section __ex_table,"a";)\ + stringify_in_c(.balign 4;) \ + stringify_in_c(.long (_fault) - . ;) \ + stringify_in_c(.long (_target) - . ;) \ + stringify_in_c(.previous) + +#endif diff --git a/arch/powerpc/include/asm/fadump-internal.h b/arch/powerpc/include/asm/fadump-internal.h index c814a2b55389..27f9e11eda28 100644 --- a/arch/powerpc/include/asm/fadump-internal.h +++ b/arch/powerpc/include/asm/fadump-internal.h @@ -19,11 +19,6 @@ #define memblock_num_regions(memblock_type) (memblock.memblock_type.cnt) -/* Alignment per CMA requirement. */ -#define FADUMP_CMA_ALIGNMENT (PAGE_SIZE << \ - max_t(unsigned long, MAX_ORDER - 1, \ - pageblock_order)) - /* FAD commands */ #define FADUMP_REGISTER 1 #define FADUMP_UNREGISTER 2 @@ -55,7 +50,7 @@ struct fadump_crash_info_header { u64 elfcorehdr_addr; u32 crashing_cpu; struct pt_regs regs; - struct cpumask online_mask; + struct cpumask cpu_mask; }; struct fadump_memory_range { @@ -64,12 +59,14 @@ struct fadump_memory_range { }; /* fadump memory ranges info */ +#define RNG_NAME_SZ 16 struct fadump_mrange_info { - char name[16]; + char name[RNG_NAME_SZ]; struct fadump_memory_range *mem_ranges; u32 mem_ranges_sz; u32 mem_range_cnt; u32 max_mem_ranges; + bool is_static; }; /* Platform specific callback functions */ @@ -135,10 +132,10 @@ struct fadump_ops { }; /* Helper functions */ -s32 fadump_setup_cpu_notes_buf(u32 num_cpus); +s32 __init fadump_setup_cpu_notes_buf(u32 num_cpus); void fadump_free_cpu_notes_buf(void); -u32 *fadump_regs_to_elf_notes(u32 *buf, struct pt_regs *regs); -void fadump_update_elfcore_header(char *bufp); +u32 *__init fadump_regs_to_elf_notes(u32 *buf, struct pt_regs *regs); +void __init fadump_update_elfcore_header(char *bufp); bool is_fadump_boot_mem_contiguous(void); bool is_fadump_reserved_mem_contiguous(void); diff --git a/arch/powerpc/include/asm/fb.h b/arch/powerpc/include/asm/fb.h index 6541ab77c5b9..c0c5d1df7ad1 100644 --- a/arch/powerpc/include/asm/fb.h +++ b/arch/powerpc/include/asm/fb.h @@ -2,21 +2,16 @@ #ifndef _ASM_FB_H_ #define _ASM_FB_H_ -#include <linux/fb.h> -#include <linux/fs.h> #include <asm/page.h> -static inline void fb_pgprotect(struct file *file, struct vm_area_struct *vma, - unsigned long off) +static inline pgprot_t pgprot_framebuffer(pgprot_t prot, + unsigned long vm_start, unsigned long vm_end, + unsigned long offset) { - vma->vm_page_prot = phys_mem_access_prot(file, off >> PAGE_SHIFT, - vma->vm_end - vma->vm_start, - vma->vm_page_prot); + return __phys_mem_access_prot(PHYS_PFN(offset), vm_end - vm_start, prot); } +#define pgprot_framebuffer pgprot_framebuffer -static inline int fb_is_primary_device(struct fb_info *info) -{ - return 0; -} +#include <asm-generic/fb.h> #endif /* _ASM_FB_H_ */ diff --git a/arch/powerpc/include/asm/feature-fixups.h b/arch/powerpc/include/asm/feature-fixups.h index b0af97add751..77824bd289a3 100644 --- a/arch/powerpc/include/asm/feature-fixups.h +++ b/arch/powerpc/include/asm/feature-fixups.h @@ -36,6 +36,24 @@ label##2: \ .align 2; \ label##3: + +#ifndef CONFIG_CC_IS_CLANG +#define CHECK_ALT_SIZE(else_size, body_size) \ + .ifgt (else_size) - (body_size); \ + .error "Feature section else case larger than body"; \ + .endif; +#else +/* + * If we use the ifgt syntax above, clang's assembler complains about the + * expression being non-absolute when the code appears in an inline assembly + * statement. + * As a workaround use an .org directive that has no effect if the else case + * instructions are smaller than the body, but fails otherwise. + */ +#define CHECK_ALT_SIZE(else_size, body_size) \ + .org . + ((else_size) > (body_size)); +#endif + #define MAKE_FTR_SECTION_ENTRY(msk, val, label, sect) \ label##4: \ .popsection; \ @@ -48,9 +66,7 @@ label##5: \ FTR_ENTRY_OFFSET label##2b-label##5b; \ FTR_ENTRY_OFFSET label##3b-label##5b; \ FTR_ENTRY_OFFSET label##4b-label##5b; \ - .ifgt (label##4b- label##3b)-(label##2b- label##1b); \ - .error "Feature section else case larger than body"; \ - .endif; \ + CHECK_ALT_SIZE((label##4b-label##3b), (label##2b-label##1b)); \ .popsection; @@ -100,6 +116,9 @@ label##5: \ #define END_MMU_FTR_SECTION_NESTED_IFSET(msk, label) \ END_MMU_FTR_SECTION_NESTED((msk), (msk), label) +#define END_MMU_FTR_SECTION_NESTED_IFCLR(msk, label) \ + END_MMU_FTR_SECTION_NESTED((msk), 0, label) + #define END_MMU_FTR_SECTION_IFSET(msk) END_MMU_FTR_SECTION((msk), (msk)) #define END_MMU_FTR_SECTION_IFCLR(msk) END_MMU_FTR_SECTION((msk), 0) @@ -205,6 +224,30 @@ label##3: \ FTR_ENTRY_OFFSET 955b-956b; \ .popsection; +#define UACCESS_FLUSH_FIXUP_SECTION \ +959: \ + .pushsection __uaccess_flush_fixup,"a"; \ + .align 2; \ +960: \ + FTR_ENTRY_OFFSET 959b-960b; \ + .popsection; + +#define ENTRY_FLUSH_FIXUP_SECTION \ +957: \ + .pushsection __entry_flush_fixup,"a"; \ + .align 2; \ +958: \ + FTR_ENTRY_OFFSET 957b-958b; \ + .popsection; + +#define SCV_ENTRY_FLUSH_FIXUP_SECTION \ +957: \ + .pushsection __scv_entry_flush_fixup,"a"; \ + .align 2; \ +958: \ + FTR_ENTRY_OFFSET 957b-958b; \ + .popsection; + #define RFI_FLUSH_FIXUP_SECTION \ 951: \ .pushsection __rfi_flush_fixup,"a"; \ @@ -237,13 +280,19 @@ label##3: \ #include <linux/types.h> extern long stf_barrier_fallback; +extern long entry_flush_fallback; +extern long scv_entry_flush_fallback; extern long __start___stf_entry_barrier_fixup, __stop___stf_entry_barrier_fixup; extern long __start___stf_exit_barrier_fixup, __stop___stf_exit_barrier_fixup; +extern long __start___uaccess_flush_fixup, __stop___uaccess_flush_fixup; +extern long __start___entry_flush_fixup, __stop___entry_flush_fixup; +extern long __start___scv_entry_flush_fixup, __stop___scv_entry_flush_fixup; extern long __start___rfi_flush_fixup, __stop___rfi_flush_fixup; extern long __start___barrier_nospec_fixup, __stop___barrier_nospec_fixup; extern long __start__btb_flush_fixup, __stop__btb_flush_fixup; void apply_feature_fixups(void); +void update_mmu_feature_fixups(unsigned long mask); void setup_feature_keys(void); #endif diff --git a/arch/powerpc/include/asm/firmware.h b/arch/powerpc/include/asm/firmware.h index b3e214a97f3a..69ae9cf57d50 100644 --- a/arch/powerpc/include/asm/firmware.h +++ b/arch/powerpc/include/asm/firmware.h @@ -33,7 +33,7 @@ #define FW_FEATURE_LLAN ASM_CONST(0x0000000000010000) #define FW_FEATURE_BULK_REMOVE ASM_CONST(0x0000000000020000) #define FW_FEATURE_XDABR ASM_CONST(0x0000000000040000) -#define FW_FEATURE_MULTITCE ASM_CONST(0x0000000000080000) +#define FW_FEATURE_PUT_TCE_IND ASM_CONST(0x0000000000080000) #define FW_FEATURE_SPLPAR ASM_CONST(0x0000000000100000) #define FW_FEATURE_LPAR ASM_CONST(0x0000000000400000) #define FW_FEATURE_PS3_LV1 ASM_CONST(0x0000000000800000) @@ -44,13 +44,19 @@ #define FW_FEATURE_OPAL ASM_CONST(0x0000000010000000) #define FW_FEATURE_SET_MODE ASM_CONST(0x0000000040000000) #define FW_FEATURE_BEST_ENERGY ASM_CONST(0x0000000080000000) -#define FW_FEATURE_TYPE1_AFFINITY ASM_CONST(0x0000000100000000) +#define FW_FEATURE_FORM1_AFFINITY ASM_CONST(0x0000000100000000) #define FW_FEATURE_PRRN ASM_CONST(0x0000000200000000) #define FW_FEATURE_DRMEM_V2 ASM_CONST(0x0000000400000000) #define FW_FEATURE_DRC_INFO ASM_CONST(0x0000000800000000) #define FW_FEATURE_BLOCK_REMOVE ASM_CONST(0x0000001000000000) #define FW_FEATURE_PAPR_SCM ASM_CONST(0x0000002000000000) #define FW_FEATURE_ULTRAVISOR ASM_CONST(0x0000004000000000) +#define FW_FEATURE_STUFF_TCE ASM_CONST(0x0000008000000000) +#define FW_FEATURE_RPT_INVALIDATE ASM_CONST(0x0000010000000000) +#define FW_FEATURE_FORM2_AFFINITY ASM_CONST(0x0000020000000000) +#define FW_FEATURE_ENERGY_SCALE_INFO ASM_CONST(0x0000040000000000) +#define FW_FEATURE_WATCHDOG ASM_CONST(0x0000080000000000) +#define FW_FEATURE_PLPKS ASM_CONST(0x0000100000000000) #ifndef __ASSEMBLY__ @@ -63,13 +69,17 @@ enum { FW_FEATURE_MIGRATE | FW_FEATURE_PERFMON | FW_FEATURE_CRQ | FW_FEATURE_VIO | FW_FEATURE_RDMA | FW_FEATURE_LLAN | FW_FEATURE_BULK_REMOVE | FW_FEATURE_XDABR | - FW_FEATURE_MULTITCE | FW_FEATURE_SPLPAR | FW_FEATURE_LPAR | + FW_FEATURE_PUT_TCE_IND | FW_FEATURE_STUFF_TCE | + FW_FEATURE_SPLPAR | FW_FEATURE_LPAR | FW_FEATURE_CMO | FW_FEATURE_VPHN | FW_FEATURE_XCMO | FW_FEATURE_SET_MODE | FW_FEATURE_BEST_ENERGY | - FW_FEATURE_TYPE1_AFFINITY | FW_FEATURE_PRRN | + FW_FEATURE_FORM1_AFFINITY | FW_FEATURE_PRRN | FW_FEATURE_HPT_RESIZE | FW_FEATURE_DRMEM_V2 | FW_FEATURE_DRC_INFO | FW_FEATURE_BLOCK_REMOVE | - FW_FEATURE_PAPR_SCM | FW_FEATURE_ULTRAVISOR, + FW_FEATURE_PAPR_SCM | FW_FEATURE_ULTRAVISOR | + FW_FEATURE_RPT_INVALIDATE | FW_FEATURE_FORM2_AFFINITY | + FW_FEATURE_ENERGY_SCALE_INFO | FW_FEATURE_WATCHDOG | + FW_FEATURE_PLPKS, FW_FEATURE_PSERIES_ALWAYS = 0, FW_FEATURE_POWERNV_POSSIBLE = FW_FEATURE_OPAL | FW_FEATURE_ULTRAVISOR, FW_FEATURE_POWERNV_ALWAYS = 0, @@ -87,7 +97,7 @@ enum { #ifdef CONFIG_PPC_PS3 FW_FEATURE_PS3_POSSIBLE | #endif -#ifdef CONFIG_PPC_NATIVE +#ifdef CONFIG_PPC_HASH_MMU_NATIVE FW_FEATURE_NATIVE_ALWAYS | #endif 0, @@ -101,7 +111,7 @@ enum { #ifdef CONFIG_PPC_PS3 FW_FEATURE_PS3_ALWAYS & #endif -#ifdef CONFIG_PPC_NATIVE +#ifdef CONFIG_PPC_HASH_MMU_NATIVE FW_FEATURE_NATIVE_ALWAYS & #endif FW_FEATURE_POSSIBLE, @@ -126,13 +136,14 @@ extern void machine_check_fwnmi(void); /* This is true if we are using the firmware NMI handler (typically LPAR) */ extern int fwnmi_active; +extern int ibm_nmi_interlock_token; extern unsigned int __start___fw_ftr_fixup, __stop___fw_ftr_fixup; #ifdef CONFIG_PPC_PSERIES void pseries_probe_fw_features(void); #else -static inline void pseries_probe_fw_features(void) { }; +static inline void pseries_probe_fw_features(void) { } #endif #endif /* __ASSEMBLY__ */ diff --git a/arch/powerpc/include/asm/fixmap.h b/arch/powerpc/include/asm/fixmap.h index 2ef155a3c821..f9068dd8dfce 100644 --- a/arch/powerpc/include/asm/fixmap.h +++ b/arch/powerpc/include/asm/fixmap.h @@ -16,18 +16,11 @@ #ifndef __ASSEMBLY__ #include <linux/sizes.h> +#include <linux/pgtable.h> #include <asm/page.h> -#include <asm/pgtable.h> #ifdef CONFIG_HIGHMEM #include <linux/threads.h> -#include <asm/kmap_types.h> -#endif - -#ifdef CONFIG_KASAN -#include <asm/kasan.h> -#define FIXADDR_TOP (KASAN_SHADOW_START - PAGE_SIZE) -#else -#define FIXADDR_TOP ((unsigned long)(-PAGE_SIZE)) +#include <asm/kmap_size.h> #endif /* @@ -50,12 +43,13 @@ */ enum fixed_addresses { FIX_HOLE, +#ifdef CONFIG_PPC32 /* reserve the top 128K for early debugging purposes */ FIX_EARLY_DEBUG_TOP = FIX_HOLE, - FIX_EARLY_DEBUG_BASE = FIX_EARLY_DEBUG_TOP+((128*1024)/PAGE_SIZE)-1, + FIX_EARLY_DEBUG_BASE = FIX_EARLY_DEBUG_TOP+(ALIGN(SZ_128K, PAGE_SIZE)/PAGE_SIZE)-1, #ifdef CONFIG_HIGHMEM FIX_KMAP_BEGIN, /* reserved pte's for temporary kernel mappings */ - FIX_KMAP_END = FIX_KMAP_BEGIN+(KM_TYPE_NR*NR_CPUS)-1, + FIX_KMAP_END = FIX_KMAP_BEGIN + (KM_MAX_IDX * NR_CPUS) - 1, #endif #ifdef CONFIG_PPC_8xx /* For IMMR we need an aligned 512K area */ @@ -72,6 +66,7 @@ enum fixed_addresses { FIX_IMMR_SIZE, #endif /* FIX_PCIE_MCFG, */ +#endif /* CONFIG_PPC32 */ __end_of_permanent_fixed_addresses, #define NR_FIX_BTMAPS (SZ_256K / PAGE_SIZE) @@ -86,6 +81,10 @@ enum fixed_addresses { #define __FIXADDR_SIZE (__end_of_fixed_addresses << PAGE_SHIFT) #define FIXADDR_START (FIXADDR_TOP - __FIXADDR_SIZE) +#define FIXMAP_ALIGNED_SIZE (ALIGN(FIXADDR_TOP, PGDIR_SIZE) - \ + ALIGN_DOWN(FIXADDR_START, PGDIR_SIZE)) +#define FIXMAP_PTE_SIZE (FIXMAP_ALIGNED_SIZE / PGDIR_SIZE * PTE_TABLE_SIZE) + #define FIXMAP_PAGE_NOCACHE PAGE_KERNEL_NCG #define FIXMAP_PAGE_IO PAGE_KERNEL_NCG @@ -94,15 +93,23 @@ enum fixed_addresses { static inline void __set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t flags) { + BUILD_BUG_ON(IS_ENABLED(CONFIG_PPC64) && __FIXADDR_SIZE > FIXADDR_SIZE); + if (__builtin_constant_p(idx)) BUILD_BUG_ON(idx >= __end_of_fixed_addresses); else if (WARN_ON(idx >= __end_of_fixed_addresses)) return; - - map_kernel_page(__fix_to_virt(idx), phys, flags); + if (pgprot_val(flags)) + map_kernel_page(__fix_to_virt(idx), phys, flags); + else + unmap_kernel_page(__fix_to_virt(idx)); } #define __early_set_fixmap __set_fixmap +#ifdef CONFIG_PPC_8xx +#define VIRT_IMMR_BASE (__fix_to_virt(FIX_IMMR_BASE)) +#endif + #endif /* !__ASSEMBLY__ */ #endif diff --git a/arch/powerpc/include/asm/floppy.h b/arch/powerpc/include/asm/floppy.h index 167c44b58848..f8ce178b43b7 100644 --- a/arch/powerpc/include/asm/floppy.h +++ b/arch/powerpc/include/asm/floppy.h @@ -13,8 +13,8 @@ #include <asm/machdep.h> -#define fd_inb(port) inb_p(port) -#define fd_outb(value,port) outb_p(value,port) +#define fd_inb(base, reg) inb_p((base) + (reg)) +#define fd_outb(value, base, reg) outb_p(value, (base) + (reg)) #define fd_enable_dma() enable_dma(FLOPPY_DMA) #define fd_disable_dma() fd_ops->_disable_dma(FLOPPY_DMA) @@ -61,21 +61,22 @@ static irqreturn_t floppy_hardint(int irq, void *dev_id) st = 1; for (lcount=virtual_dma_count, lptr=virtual_dma_addr; lcount; lcount--, lptr++) { - st=inb(virtual_dma_port+4) & 0xa0 ; - if (st != 0xa0) + st = inb(virtual_dma_port + FD_STATUS); + st &= STATUS_DMA | STATUS_READY; + if (st != (STATUS_DMA | STATUS_READY)) break; if (virtual_dma_mode) - outb_p(*lptr, virtual_dma_port+5); + outb_p(*lptr, virtual_dma_port + FD_DATA); else - *lptr = inb_p(virtual_dma_port+5); + *lptr = inb_p(virtual_dma_port + FD_DATA); } virtual_dma_count = lcount; virtual_dma_addr = lptr; - st = inb(virtual_dma_port+4); + st = inb(virtual_dma_port + FD_STATUS); - if (st == 0x20) + if (st == STATUS_DMA) return IRQ_HANDLED; - if (!(st & 0x20)) { + if (!(st & STATUS_DMA)) { virtual_dma_residue += virtual_dma_count; virtual_dma_count=0; doing_vdma = 0; @@ -133,17 +134,19 @@ static int hard_dma_setup(char *addr, unsigned long size, int mode, int io) int dir; doing_vdma = 0; - dir = (mode == DMA_MODE_READ) ? PCI_DMA_FROMDEVICE : PCI_DMA_TODEVICE; + dir = (mode == DMA_MODE_READ) ? DMA_FROM_DEVICE : DMA_TO_DEVICE; if (bus_addr && (addr != prev_addr || size != prev_size || dir != prev_dir)) { /* different from last time -- unmap prev */ - pci_unmap_single(isa_bridge_pcidev, bus_addr, prev_size, prev_dir); + dma_unmap_single(&isa_bridge_pcidev->dev, bus_addr, prev_size, + prev_dir); bus_addr = 0; } if (!bus_addr) /* need to map it */ - bus_addr = pci_map_single(isa_bridge_pcidev, addr, size, dir); + bus_addr = dma_map_single(&isa_bridge_pcidev->dev, addr, size, + dir); /* remember this one as prev */ prev_addr = addr; diff --git a/arch/powerpc/include/asm/fs_pd.h b/arch/powerpc/include/asm/fs_pd.h deleted file mode 100644 index 8def56ec05c6..000000000000 --- a/arch/powerpc/include/asm/fs_pd.h +++ /dev/null @@ -1,49 +0,0 @@ -/* - * Platform information definitions. - * - * 2006 (c) MontaVista Software, Inc. - * Vitaly Bordug <vbordug@ru.mvista.com> - * - * This file is licensed under the terms of the GNU General Public License - * version 2. This program is licensed "as is" without any warranty of any - * kind, whether express or implied. - */ - -#ifndef FS_PD_H -#define FS_PD_H -#include <sysdev/fsl_soc.h> -#include <asm/time.h> - -#ifdef CONFIG_CPM2 -#include <asm/cpm2.h> - -#if defined(CONFIG_8260) -#include <asm/mpc8260.h> -#endif - -#define cpm2_map(member) (&cpm2_immr->member) -#define cpm2_map_size(member, size) (&cpm2_immr->member) -#define cpm2_unmap(addr) do {} while(0) -#endif - -#ifdef CONFIG_PPC_8xx -#include <asm/8xx_immap.h> - -extern immap_t __iomem *mpc8xx_immr; - -#define immr_map(member) (&mpc8xx_immr->member) -#define immr_map_size(member, size) (&mpc8xx_immr->member) -#define immr_unmap(addr) do {} while (0) -#endif - -static inline int uart_baudrate(void) -{ - return get_baudrate(); -} - -static inline int uart_clock(void) -{ - return ppc_proc_freq; -} - -#endif diff --git a/arch/powerpc/include/asm/fsl_85xx_cache_sram.h b/arch/powerpc/include/asm/fsl_85xx_cache_sram.h deleted file mode 100644 index 0235a0447baa..000000000000 --- a/arch/powerpc/include/asm/fsl_85xx_cache_sram.h +++ /dev/null @@ -1,35 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * Copyright 2009 Freescale Semiconductor, Inc. - * - * Cache SRAM handling for QorIQ platform - * - * Author: Vivek Mahajan <vivek.mahajan@freescale.com> - - * This file is derived from the original work done - * by Sylvain Munaut for the Bestcomm SRAM allocator. - */ - -#ifndef __ASM_POWERPC_FSL_85XX_CACHE_SRAM_H__ -#define __ASM_POWERPC_FSL_85XX_CACHE_SRAM_H__ - -#include <asm/rheap.h> -#include <linux/spinlock.h> - -/* - * Cache-SRAM - */ - -struct mpc85xx_cache_sram { - phys_addr_t base_phys; - void *base_virt; - unsigned int size; - rh_info_t *rh; - spinlock_t lock; -}; - -extern void mpc85xx_cache_sram_free(void *ptr); -extern void *mpc85xx_cache_sram_alloc(unsigned int size, - phys_addr_t *phys, unsigned int align); - -#endif /* __AMS_POWERPC_FSL_85XX_CACHE_SRAM_H__ */ diff --git a/arch/powerpc/include/asm/fsl_pamu_stash.h b/arch/powerpc/include/asm/fsl_pamu_stash.h index 30a31ad2123d..c0fbadb70b5d 100644 --- a/arch/powerpc/include/asm/fsl_pamu_stash.h +++ b/arch/powerpc/include/asm/fsl_pamu_stash.h @@ -7,6 +7,8 @@ #ifndef __FSL_PAMU_STASH_H #define __FSL_PAMU_STASH_H +struct iommu_domain; + /* cache stash targets */ enum pamu_stash_target { PAMU_ATTR_CACHE_L1 = 1, @@ -14,14 +16,6 @@ enum pamu_stash_target { PAMU_ATTR_CACHE_L3, }; -/* - * This attribute allows configuring stashig specific parameters - * in the PAMU hardware. - */ - -struct pamu_stash_attribute { - u32 cpu; /* cpu number */ - u32 cache; /* cache to stash to: L1,L2,L3 */ -}; +int fsl_pamu_configure_l1_stash(struct iommu_domain *domain, u32 cpu); #endif /* __FSL_PAMU_STASH_H */ diff --git a/arch/powerpc/include/asm/ftrace.h b/arch/powerpc/include/asm/ftrace.h index f54a08a2cd70..1ebd2ca97f12 100644 --- a/arch/powerpc/include/asm/ftrace.h +++ b/arch/powerpc/include/asm/ftrace.h @@ -10,55 +10,80 @@ #define HAVE_FUNCTION_GRAPH_RET_ADDR_PTR -#ifdef __ASSEMBLY__ - -/* Based off of objdump optput from glibc */ - -#define MCOUNT_SAVE_FRAME \ - stwu r1,-48(r1); \ - stw r3, 12(r1); \ - stw r4, 16(r1); \ - stw r5, 20(r1); \ - stw r6, 24(r1); \ - mflr r3; \ - lwz r4, 52(r1); \ - mfcr r5; \ - stw r7, 28(r1); \ - stw r8, 32(r1); \ - stw r9, 36(r1); \ - stw r10,40(r1); \ - stw r3, 44(r1); \ - stw r5, 8(r1) - -#define MCOUNT_RESTORE_FRAME \ - lwz r6, 8(r1); \ - lwz r0, 44(r1); \ - lwz r3, 12(r1); \ - mtctr r0; \ - lwz r4, 16(r1); \ - mtcr r6; \ - lwz r5, 20(r1); \ - lwz r6, 24(r1); \ - lwz r0, 52(r1); \ - lwz r7, 28(r1); \ - lwz r8, 32(r1); \ - mtlr r0; \ - lwz r9, 36(r1); \ - lwz r10,40(r1); \ - addi r1, r1, 48 - -#else /* !__ASSEMBLY__ */ +/* Ignore unused weak functions which will have larger offsets */ +#if defined(CONFIG_MPROFILE_KERNEL) || defined(CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY) +#define FTRACE_MCOUNT_MAX_OFFSET 16 +#elif defined(CONFIG_PPC32) +#define FTRACE_MCOUNT_MAX_OFFSET 8 +#endif + +#ifndef __ASSEMBLY__ extern void _mcount(void); static inline unsigned long ftrace_call_adjust(unsigned long addr) { - /* reloction of mcount call site is the same as the address */ - return addr; + if (IS_ENABLED(CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY)) + addr += MCOUNT_INSN_SIZE; + + return addr; } +unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip, + unsigned long sp); + +struct module; +struct dyn_ftrace; struct dyn_arch_ftrace { struct module *mod; }; + +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS +#define ftrace_need_init_nop() (true) +int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec); +#define ftrace_init_nop ftrace_init_nop + +struct ftrace_regs { + struct pt_regs regs; +}; + +static __always_inline struct pt_regs *arch_ftrace_get_regs(struct ftrace_regs *fregs) +{ + /* We clear regs.msr in ftrace_call */ + return fregs->regs.msr ? &fregs->regs : NULL; +} + +static __always_inline void +ftrace_regs_set_instruction_pointer(struct ftrace_regs *fregs, + unsigned long ip) +{ + regs_set_return_ip(&fregs->regs, ip); +} + +static __always_inline unsigned long +ftrace_regs_get_instruction_pointer(struct ftrace_regs *fregs) +{ + return instruction_pointer(&fregs->regs); +} + +#define ftrace_regs_get_argument(fregs, n) \ + regs_get_kernel_argument(&(fregs)->regs, n) +#define ftrace_regs_get_stack_pointer(fregs) \ + kernel_stack_pointer(&(fregs)->regs) +#define ftrace_regs_return_value(fregs) \ + regs_return_value(&(fregs)->regs) +#define ftrace_regs_set_return_value(fregs, ret) \ + regs_set_return_value(&(fregs)->regs, ret) +#define ftrace_override_function_with_return(fregs) \ + override_function_with_return(&(fregs)->regs) +#define ftrace_regs_query_register_offset(name) \ + regs_query_register_offset(name) + +struct ftrace_ops; + +#define ftrace_graph_func ftrace_graph_func +void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct ftrace_regs *fregs); +#endif #endif /* __ASSEMBLY__ */ #ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS @@ -74,17 +99,6 @@ struct dyn_arch_ftrace { * those. */ #define ARCH_HAS_SYSCALL_MATCH_SYM_NAME -#ifdef PPC64_ELF_ABI_v1 -static inline bool arch_syscall_match_sym_name(const char *sym, const char *name) -{ - /* We need to skip past the initial dot, and the __se_sys alias */ - return !strcmp(sym + 1, name) || - (!strncmp(sym, ".__se_sys", 9) && !strcmp(sym + 6, name)) || - (!strncmp(sym, ".ppc_", 5) && !strcmp(sym + 5, name + 4)) || - (!strncmp(sym, ".ppc32_", 7) && !strcmp(sym + 7, name + 4)) || - (!strncmp(sym, ".ppc64_", 7) && !strcmp(sym + 7, name + 4)); -} -#else static inline bool arch_syscall_match_sym_name(const char *sym, const char *name) { return !strcmp(sym, name) || @@ -93,10 +107,9 @@ static inline bool arch_syscall_match_sym_name(const char *sym, const char *name (!strncmp(sym, "ppc32_", 6) && !strcmp(sym + 6, name + 4)) || (!strncmp(sym, "ppc64_", 6) && !strcmp(sym + 6, name + 4)); } -#endif /* PPC64_ELF_ABI_v1 */ #endif /* CONFIG_FTRACE_SYSCALLS */ -#ifdef CONFIG_PPC64 +#if defined(CONFIG_PPC64) && defined(CONFIG_FUNCTION_TRACER) #include <asm/paca.h> static inline void this_cpu_disable_ftrace(void) @@ -108,10 +121,30 @@ static inline void this_cpu_enable_ftrace(void) { get_paca()->ftrace_enabled = 1; } + +/* Disable ftrace on this CPU if possible (may not be implemented) */ +static inline void this_cpu_set_ftrace_enabled(u8 ftrace_enabled) +{ + get_paca()->ftrace_enabled = ftrace_enabled; +} + +static inline u8 this_cpu_get_ftrace_enabled(void) +{ + return get_paca()->ftrace_enabled; +} #else /* CONFIG_PPC64 */ static inline void this_cpu_disable_ftrace(void) { } static inline void this_cpu_enable_ftrace(void) { } +static inline void this_cpu_set_ftrace_enabled(u8 ftrace_enabled) { } +static inline u8 this_cpu_get_ftrace_enabled(void) { return 1; } #endif /* CONFIG_PPC64 */ + +#ifdef CONFIG_FUNCTION_TRACER +extern unsigned int ftrace_tramp_text[], ftrace_tramp_init[]; +void ftrace_free_init_tramp(void); +#else +static inline void ftrace_free_init_tramp(void) { } +#endif #endif /* !__ASSEMBLY__ */ #endif /* _ASM_POWERPC_FTRACE */ diff --git a/arch/powerpc/include/asm/futex.h b/arch/powerpc/include/asm/futex.h index eea28ca679db..b3001f8b2c1e 100644 --- a/arch/powerpc/include/asm/futex.h +++ b/arch/powerpc/include/asm/futex.h @@ -8,14 +8,12 @@ #include <linux/uaccess.h> #include <asm/errno.h> #include <asm/synch.h> -#include <asm/asm-405.h> #define __futex_atomic_op(insn, ret, oldval, uaddr, oparg) \ __asm__ __volatile ( \ PPC_ATOMIC_ENTRY_BARRIER \ "1: lwarx %0,0,%2\n" \ insn \ - PPC405_ERR77(0, %2) \ "2: stwcx. %1,0,%2\n" \ "bne- 1b\n" \ PPC_ATOMIC_EXIT_BARRIER \ @@ -35,8 +33,8 @@ static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval, { int oldval = 0, ret; - allow_write_to_user(uaddr, sizeof(*uaddr)); - pagefault_disable(); + if (!user_access_begin(uaddr, sizeof(u32))) + return -EFAULT; switch (op) { case FUTEX_OP_SET: @@ -57,12 +55,10 @@ static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval, default: ret = -ENOSYS; } - - pagefault_enable(); + user_access_end(); *oval = oldval; - prevent_write_to_user(uaddr, sizeof(*uaddr)); return ret; } @@ -73,16 +69,14 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, int ret = 0; u32 prev; - if (!access_ok(uaddr, sizeof(u32))) + if (!user_access_begin(uaddr, sizeof(u32))) return -EFAULT; - allow_write_to_user(uaddr, sizeof(*uaddr)); __asm__ __volatile__ ( PPC_ATOMIC_ENTRY_BARRIER "1: lwarx %1,0,%3 # futex_atomic_cmpxchg_inatomic\n\ cmpw 0,%1,%4\n\ bne- 3f\n" - PPC405_ERR77(0,%3) "2: stwcx. %5,0,%3\n\ bne- 1b\n" PPC_ATOMIC_EXIT_BARRIER @@ -96,8 +90,10 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, : "r" (uaddr), "r" (oldval), "r" (newval), "i" (-EFAULT) : "cc", "memory"); + user_access_end(); + *uval = prev; - prevent_write_to_user(uaddr, sizeof(*uaddr)); + return ret; } diff --git a/arch/powerpc/include/asm/guest-state-buffer.h b/arch/powerpc/include/asm/guest-state-buffer.h new file mode 100644 index 000000000000..808149f31576 --- /dev/null +++ b/arch/powerpc/include/asm/guest-state-buffer.h @@ -0,0 +1,995 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Interface based on include/net/netlink.h + */ +#ifndef _ASM_POWERPC_GUEST_STATE_BUFFER_H +#define _ASM_POWERPC_GUEST_STATE_BUFFER_H + +#include "asm/hvcall.h" +#include <linux/gfp.h> +#include <linux/bitmap.h> +#include <asm/plpar_wrappers.h> + +/************************************************************************** + * Guest State Buffer Constants + **************************************************************************/ +/* Element without a value and any length */ +#define KVMPPC_GSID_BLANK 0x0000 +/* Size required for the L0's internal VCPU representation */ +#define KVMPPC_GSID_HOST_STATE_SIZE 0x0001 + /* Minimum size for the H_GUEST_RUN_VCPU output buffer */ +#define KVMPPC_GSID_RUN_OUTPUT_MIN_SIZE 0x0002 + /* "Logical" PVR value as defined in the PAPR */ +#define KVMPPC_GSID_LOGICAL_PVR 0x0003 + /* L0 relative timebase offset */ +#define KVMPPC_GSID_TB_OFFSET 0x0004 + /* Partition Scoped Page Table Info */ +#define KVMPPC_GSID_PARTITION_TABLE 0x0005 + /* Process Table Info */ +#define KVMPPC_GSID_PROCESS_TABLE 0x0006 + +/* H_GUEST_RUN_VCPU input buffer Info */ +#define KVMPPC_GSID_RUN_INPUT 0x0C00 +/* H_GUEST_RUN_VCPU output buffer Info */ +#define KVMPPC_GSID_RUN_OUTPUT 0x0C01 +#define KVMPPC_GSID_VPA 0x0C02 + +#define KVMPPC_GSID_GPR(x) (0x1000 + (x)) +#define KVMPPC_GSID_HDEC_EXPIRY_TB 0x1020 +#define KVMPPC_GSID_NIA 0x1021 +#define KVMPPC_GSID_MSR 0x1022 +#define KVMPPC_GSID_LR 0x1023 +#define KVMPPC_GSID_XER 0x1024 +#define KVMPPC_GSID_CTR 0x1025 +#define KVMPPC_GSID_CFAR 0x1026 +#define KVMPPC_GSID_SRR0 0x1027 +#define KVMPPC_GSID_SRR1 0x1028 +#define KVMPPC_GSID_DAR 0x1029 +#define KVMPPC_GSID_DEC_EXPIRY_TB 0x102A +#define KVMPPC_GSID_VTB 0x102B +#define KVMPPC_GSID_LPCR 0x102C +#define KVMPPC_GSID_HFSCR 0x102D +#define KVMPPC_GSID_FSCR 0x102E +#define KVMPPC_GSID_FPSCR 0x102F +#define KVMPPC_GSID_DAWR0 0x1030 +#define KVMPPC_GSID_DAWR1 0x1031 +#define KVMPPC_GSID_CIABR 0x1032 +#define KVMPPC_GSID_PURR 0x1033 +#define KVMPPC_GSID_SPURR 0x1034 +#define KVMPPC_GSID_IC 0x1035 +#define KVMPPC_GSID_SPRG0 0x1036 +#define KVMPPC_GSID_SPRG1 0x1037 +#define KVMPPC_GSID_SPRG2 0x1038 +#define KVMPPC_GSID_SPRG3 0x1039 +#define KVMPPC_GSID_PPR 0x103A +#define KVMPPC_GSID_MMCR(x) (0x103B + (x)) +#define KVMPPC_GSID_MMCRA 0x103F +#define KVMPPC_GSID_SIER(x) (0x1040 + (x)) +#define KVMPPC_GSID_BESCR 0x1043 +#define KVMPPC_GSID_EBBHR 0x1044 +#define KVMPPC_GSID_EBBRR 0x1045 +#define KVMPPC_GSID_AMR 0x1046 +#define KVMPPC_GSID_IAMR 0x1047 +#define KVMPPC_GSID_AMOR 0x1048 +#define KVMPPC_GSID_UAMOR 0x1049 +#define KVMPPC_GSID_SDAR 0x104A +#define KVMPPC_GSID_SIAR 0x104B +#define KVMPPC_GSID_DSCR 0x104C +#define KVMPPC_GSID_TAR 0x104D +#define KVMPPC_GSID_DEXCR 0x104E +#define KVMPPC_GSID_HDEXCR 0x104F +#define KVMPPC_GSID_HASHKEYR 0x1050 +#define KVMPPC_GSID_HASHPKEYR 0x1051 +#define KVMPPC_GSID_CTRL 0x1052 + +#define KVMPPC_GSID_CR 0x2000 +#define KVMPPC_GSID_PIDR 0x2001 +#define KVMPPC_GSID_DSISR 0x2002 +#define KVMPPC_GSID_VSCR 0x2003 +#define KVMPPC_GSID_VRSAVE 0x2004 +#define KVMPPC_GSID_DAWRX0 0x2005 +#define KVMPPC_GSID_DAWRX1 0x2006 +#define KVMPPC_GSID_PMC(x) (0x2007 + (x)) +#define KVMPPC_GSID_WORT 0x200D +#define KVMPPC_GSID_PSPB 0x200E + +#define KVMPPC_GSID_VSRS(x) (0x3000 + (x)) + +#define KVMPPC_GSID_HDAR 0xF000 +#define KVMPPC_GSID_HDSISR 0xF001 +#define KVMPPC_GSID_HEIR 0xF002 +#define KVMPPC_GSID_ASDR 0xF003 + +#define KVMPPC_GSE_GUESTWIDE_START KVMPPC_GSID_BLANK +#define KVMPPC_GSE_GUESTWIDE_END KVMPPC_GSID_PROCESS_TABLE +#define KVMPPC_GSE_GUESTWIDE_COUNT \ + (KVMPPC_GSE_GUESTWIDE_END - KVMPPC_GSE_GUESTWIDE_START + 1) + +#define KVMPPC_GSE_META_START KVMPPC_GSID_RUN_INPUT +#define KVMPPC_GSE_META_END KVMPPC_GSID_VPA +#define KVMPPC_GSE_META_COUNT (KVMPPC_GSE_META_END - KVMPPC_GSE_META_START + 1) + +#define KVMPPC_GSE_DW_REGS_START KVMPPC_GSID_GPR(0) +#define KVMPPC_GSE_DW_REGS_END KVMPPC_GSID_CTRL +#define KVMPPC_GSE_DW_REGS_COUNT \ + (KVMPPC_GSE_DW_REGS_END - KVMPPC_GSE_DW_REGS_START + 1) + +#define KVMPPC_GSE_W_REGS_START KVMPPC_GSID_CR +#define KVMPPC_GSE_W_REGS_END KVMPPC_GSID_PSPB +#define KVMPPC_GSE_W_REGS_COUNT \ + (KVMPPC_GSE_W_REGS_END - KVMPPC_GSE_W_REGS_START + 1) + +#define KVMPPC_GSE_VSRS_START KVMPPC_GSID_VSRS(0) +#define KVMPPC_GSE_VSRS_END KVMPPC_GSID_VSRS(63) +#define KVMPPC_GSE_VSRS_COUNT (KVMPPC_GSE_VSRS_END - KVMPPC_GSE_VSRS_START + 1) + +#define KVMPPC_GSE_INTR_REGS_START KVMPPC_GSID_HDAR +#define KVMPPC_GSE_INTR_REGS_END KVMPPC_GSID_ASDR +#define KVMPPC_GSE_INTR_REGS_COUNT \ + (KVMPPC_GSE_INTR_REGS_END - KVMPPC_GSE_INTR_REGS_START + 1) + +#define KVMPPC_GSE_IDEN_COUNT \ + (KVMPPC_GSE_GUESTWIDE_COUNT + KVMPPC_GSE_META_COUNT + \ + KVMPPC_GSE_DW_REGS_COUNT + KVMPPC_GSE_W_REGS_COUNT + \ + KVMPPC_GSE_VSRS_COUNT + KVMPPC_GSE_INTR_REGS_COUNT) + +/** + * Ranges of guest state buffer elements + */ +enum { + KVMPPC_GS_CLASS_GUESTWIDE = 0x01, + KVMPPC_GS_CLASS_META = 0x02, + KVMPPC_GS_CLASS_DWORD_REG = 0x04, + KVMPPC_GS_CLASS_WORD_REG = 0x08, + KVMPPC_GS_CLASS_VECTOR = 0x10, + KVMPPC_GS_CLASS_INTR = 0x20, +}; + +/** + * Types of guest state buffer elements + */ +enum { + KVMPPC_GSE_BE32, + KVMPPC_GSE_BE64, + KVMPPC_GSE_VEC128, + KVMPPC_GSE_PARTITION_TABLE, + KVMPPC_GSE_PROCESS_TABLE, + KVMPPC_GSE_BUFFER, + __KVMPPC_GSE_TYPE_MAX, +}; + +/** + * Flags for guest state elements + */ +enum { + KVMPPC_GS_FLAGS_WIDE = 0x01, +}; + +/** + * struct kvmppc_gs_part_table - deserialized partition table information + * element + * @address: start of the partition table + * @ea_bits: number of bits in the effective address + * @gpd_size: root page directory size + */ +struct kvmppc_gs_part_table { + u64 address; + u64 ea_bits; + u64 gpd_size; +}; + +/** + * struct kvmppc_gs_proc_table - deserialized process table information element + * @address: start of the process table + * @gpd_size: process table size + */ +struct kvmppc_gs_proc_table { + u64 address; + u64 gpd_size; +}; + +/** + * struct kvmppc_gs_buff_info - deserialized meta guest state buffer information + * @address: start of the guest state buffer + * @size: size of the guest state buffer + */ +struct kvmppc_gs_buff_info { + u64 address; + u64 size; +}; + +/** + * struct kvmppc_gs_header - serialized guest state buffer header + * @nelem: count of guest state elements in the buffer + * @data: start of the stream of elements in the buffer + */ +struct kvmppc_gs_header { + __be32 nelems; + char data[]; +} __packed; + +/** + * struct kvmppc_gs_elem - serialized guest state buffer element + * @iden: Guest State ID + * @len: length of data + * @data: the guest state buffer element's value + */ +struct kvmppc_gs_elem { + __be16 iden; + __be16 len; + char data[]; +} __packed; + +/** + * struct kvmppc_gs_buff - a guest state buffer with metadata. + * @capacity: total length of the buffer + * @len: current length of the elements and header + * @guest_id: guest id associated with the buffer + * @vcpu_id: vcpu_id associated with the buffer + * @hdr: the serialised guest state buffer + */ +struct kvmppc_gs_buff { + size_t capacity; + size_t len; + unsigned long guest_id; + unsigned long vcpu_id; + struct kvmppc_gs_header *hdr; +}; + +/** + * struct kvmppc_gs_bitmap - a bitmap for element ids + * @bitmap: a bitmap large enough for all Guest State IDs + */ +struct kvmppc_gs_bitmap { + /* private: */ + DECLARE_BITMAP(bitmap, KVMPPC_GSE_IDEN_COUNT); +}; + +/** + * struct kvmppc_gs_parser - a map of element ids to locations in a buffer + * @iterator: bitmap used for iterating + * @gses: contains the pointers to elements + * + * A guest state parser is used for deserialising a guest state buffer. + * Given a buffer, it then allows looking up guest state elements using + * a guest state id. + */ +struct kvmppc_gs_parser { + /* private: */ + struct kvmppc_gs_bitmap iterator; + struct kvmppc_gs_elem *gses[KVMPPC_GSE_IDEN_COUNT]; +}; + +enum { + GSM_GUEST_WIDE = 0x1, + GSM_SEND = 0x2, + GSM_RECEIVE = 0x4, + GSM_GSB_OWNER = 0x8, +}; + +struct kvmppc_gs_msg; + +/** + * struct kvmppc_gs_msg_ops - guest state message behavior + * @get_size: maximum size required for the message data + * @fill_info: serializes to the guest state buffer format + * @refresh_info: dserializes from the guest state buffer format + */ +struct kvmppc_gs_msg_ops { + size_t (*get_size)(struct kvmppc_gs_msg *gsm); + int (*fill_info)(struct kvmppc_gs_buff *gsb, struct kvmppc_gs_msg *gsm); + int (*refresh_info)(struct kvmppc_gs_msg *gsm, + struct kvmppc_gs_buff *gsb); +}; + +/** + * struct kvmppc_gs_msg - a guest state message + * @bitmap: the guest state ids that should be included + * @ops: modify message behavior for reading and writing to buffers + * @flags: guest wide or thread wide + * @data: location where buffer data will be written to or from. + * + * A guest state message is allows flexibility in sending in receiving data + * in a guest state buffer format. + */ +struct kvmppc_gs_msg { + struct kvmppc_gs_bitmap bitmap; + struct kvmppc_gs_msg_ops *ops; + unsigned long flags; + void *data; +}; + +/************************************************************************** + * Guest State IDs + **************************************************************************/ + +u16 kvmppc_gsid_size(u16 iden); +unsigned long kvmppc_gsid_flags(u16 iden); +u64 kvmppc_gsid_mask(u16 iden); + +/************************************************************************** + * Guest State Buffers + **************************************************************************/ +struct kvmppc_gs_buff *kvmppc_gsb_new(size_t size, unsigned long guest_id, + unsigned long vcpu_id, gfp_t flags); +void kvmppc_gsb_free(struct kvmppc_gs_buff *gsb); +void *kvmppc_gsb_put(struct kvmppc_gs_buff *gsb, size_t size); +int kvmppc_gsb_send(struct kvmppc_gs_buff *gsb, unsigned long flags); +int kvmppc_gsb_recv(struct kvmppc_gs_buff *gsb, unsigned long flags); + +/** + * kvmppc_gsb_header() - the header of a guest state buffer + * @gsb: guest state buffer + * + * Returns a pointer to the buffer header. + */ +static inline struct kvmppc_gs_header * +kvmppc_gsb_header(struct kvmppc_gs_buff *gsb) +{ + return gsb->hdr; +} + +/** + * kvmppc_gsb_data() - the elements of a guest state buffer + * @gsb: guest state buffer + * + * Returns a pointer to the first element of the buffer data. + */ +static inline struct kvmppc_gs_elem *kvmppc_gsb_data(struct kvmppc_gs_buff *gsb) +{ + return (struct kvmppc_gs_elem *)kvmppc_gsb_header(gsb)->data; +} + +/** + * kvmppc_gsb_len() - the current length of a guest state buffer + * @gsb: guest state buffer + * + * Returns the length including the header of a buffer. + */ +static inline size_t kvmppc_gsb_len(struct kvmppc_gs_buff *gsb) +{ + return gsb->len; +} + +/** + * kvmppc_gsb_capacity() - the capacity of a guest state buffer + * @gsb: guest state buffer + * + * Returns the capacity of a buffer. + */ +static inline size_t kvmppc_gsb_capacity(struct kvmppc_gs_buff *gsb) +{ + return gsb->capacity; +} + +/** + * kvmppc_gsb_paddress() - the physical address of buffer + * @gsb: guest state buffer + * + * Returns the physical address of the buffer. + */ +static inline u64 kvmppc_gsb_paddress(struct kvmppc_gs_buff *gsb) +{ + return __pa(kvmppc_gsb_header(gsb)); +} + +/** + * kvmppc_gsb_nelems() - the number of elements in a buffer + * @gsb: guest state buffer + * + * Returns the number of elements in a buffer + */ +static inline u32 kvmppc_gsb_nelems(struct kvmppc_gs_buff *gsb) +{ + return be32_to_cpu(kvmppc_gsb_header(gsb)->nelems); +} + +/** + * kvmppc_gsb_reset() - empty a guest state buffer + * @gsb: guest state buffer + * + * Reset the number of elements and length of buffer to empty. + */ +static inline void kvmppc_gsb_reset(struct kvmppc_gs_buff *gsb) +{ + kvmppc_gsb_header(gsb)->nelems = cpu_to_be32(0); + gsb->len = sizeof(struct kvmppc_gs_header); +} + +/** + * kvmppc_gsb_data_len() - the length of a buffer excluding the header + * @gsb: guest state buffer + * + * Returns the length of a buffer excluding the header + */ +static inline size_t kvmppc_gsb_data_len(struct kvmppc_gs_buff *gsb) +{ + return gsb->len - sizeof(struct kvmppc_gs_header); +} + +/** + * kvmppc_gsb_data_cap() - the capacity of a buffer excluding the header + * @gsb: guest state buffer + * + * Returns the capacity of a buffer excluding the header + */ +static inline size_t kvmppc_gsb_data_cap(struct kvmppc_gs_buff *gsb) +{ + return gsb->capacity - sizeof(struct kvmppc_gs_header); +} + +/** + * kvmppc_gsb_for_each_elem - iterate over the elements in a buffer + * @i: loop counter + * @pos: set to current element + * @gsb: guest state buffer + * @rem: initialized to buffer capacity, holds bytes currently remaining in + * stream + */ +#define kvmppc_gsb_for_each_elem(i, pos, gsb, rem) \ + kvmppc_gse_for_each_elem(i, kvmppc_gsb_nelems(gsb), pos, \ + kvmppc_gsb_data(gsb), \ + kvmppc_gsb_data_cap(gsb), rem) + +/************************************************************************** + * Guest State Elements + **************************************************************************/ + +/** + * kvmppc_gse_iden() - guest state ID of element + * @gse: guest state element + * + * Return the guest state ID in host endianness. + */ +static inline u16 kvmppc_gse_iden(const struct kvmppc_gs_elem *gse) +{ + return be16_to_cpu(gse->iden); +} + +/** + * kvmppc_gse_len() - length of guest state element data + * @gse: guest state element + * + * Returns the length of guest state element data + */ +static inline u16 kvmppc_gse_len(const struct kvmppc_gs_elem *gse) +{ + return be16_to_cpu(gse->len); +} + +/** + * kvmppc_gse_total_len() - total length of guest state element + * @gse: guest state element + * + * Returns the length of the data plus the ID and size header. + */ +static inline u16 kvmppc_gse_total_len(const struct kvmppc_gs_elem *gse) +{ + return be16_to_cpu(gse->len) + sizeof(*gse); +} + +/** + * kvmppc_gse_total_size() - space needed for a given data length + * @size: data length + * + * Returns size plus the space needed for the ID and size header. + */ +static inline u16 kvmppc_gse_total_size(u16 size) +{ + return sizeof(struct kvmppc_gs_elem) + size; +} + +/** + * kvmppc_gse_data() - pointer to data of a guest state element + * @gse: guest state element + * + * Returns a pointer to the beginning of guest state element data. + */ +static inline void *kvmppc_gse_data(const struct kvmppc_gs_elem *gse) +{ + return (void *)gse->data; +} + +/** + * kvmppc_gse_ok() - checks space exists for guest state element + * @gse: guest state element + * @remaining: bytes of space remaining + * + * Returns true if the guest state element can fit in remaining space. + */ +static inline bool kvmppc_gse_ok(const struct kvmppc_gs_elem *gse, + int remaining) +{ + return remaining >= kvmppc_gse_total_len(gse); +} + +/** + * kvmppc_gse_next() - iterate to the next guest state element in a stream + * @gse: stream of guest state elements + * @remaining: length of the guest element stream + * + * Returns the next guest state element in a stream of elements. The length of + * the stream is updated in remaining. + */ +static inline struct kvmppc_gs_elem * +kvmppc_gse_next(const struct kvmppc_gs_elem *gse, int *remaining) +{ + int len = sizeof(*gse) + kvmppc_gse_len(gse); + + *remaining -= len; + return (struct kvmppc_gs_elem *)(gse->data + kvmppc_gse_len(gse)); +} + +/** + * kvmppc_gse_for_each_elem - iterate over a stream of guest state elements + * @i: loop counter + * @max: number of elements + * @pos: set to current element + * @head: head of elements + * @len: length of the stream + * @rem: initialized to len, holds bytes currently remaining elements + */ +#define kvmppc_gse_for_each_elem(i, max, pos, head, len, rem) \ + for (i = 0, pos = head, rem = len; kvmppc_gse_ok(pos, rem) && i < max; \ + pos = kvmppc_gse_next(pos, &(rem)), i++) + +int __kvmppc_gse_put(struct kvmppc_gs_buff *gsb, u16 iden, u16 size, + const void *data); +int kvmppc_gse_parse(struct kvmppc_gs_parser *gsp, struct kvmppc_gs_buff *gsb); + +/** + * kvmppc_gse_put_be32() - add a be32 guest state element to a buffer + * @gsb: guest state buffer to add element to + * @iden: guest state ID + * @val: big endian value + */ +static inline int kvmppc_gse_put_be32(struct kvmppc_gs_buff *gsb, u16 iden, + __be32 val) +{ + __be32 tmp; + + tmp = val; + return __kvmppc_gse_put(gsb, iden, sizeof(__be32), &tmp); +} + +/** + * kvmppc_gse_put_u32() - add a host endian 32bit int guest state element to a + * buffer + * @gsb: guest state buffer to add element to + * @iden: guest state ID + * @val: host endian value + */ +static inline int kvmppc_gse_put_u32(struct kvmppc_gs_buff *gsb, u16 iden, + u32 val) +{ + __be32 tmp; + + val &= kvmppc_gsid_mask(iden); + tmp = cpu_to_be32(val); + return kvmppc_gse_put_be32(gsb, iden, tmp); +} + +/** + * kvmppc_gse_put_be64() - add a be64 guest state element to a buffer + * @gsb: guest state buffer to add element to + * @iden: guest state ID + * @val: big endian value + */ +static inline int kvmppc_gse_put_be64(struct kvmppc_gs_buff *gsb, u16 iden, + __be64 val) +{ + __be64 tmp; + + tmp = val; + return __kvmppc_gse_put(gsb, iden, sizeof(__be64), &tmp); +} + +/** + * kvmppc_gse_put_u64() - add a host endian 64bit guest state element to a + * buffer + * @gsb: guest state buffer to add element to + * @iden: guest state ID + * @val: host endian value + */ +static inline int kvmppc_gse_put_u64(struct kvmppc_gs_buff *gsb, u16 iden, + u64 val) +{ + __be64 tmp; + + val &= kvmppc_gsid_mask(iden); + tmp = cpu_to_be64(val); + return kvmppc_gse_put_be64(gsb, iden, tmp); +} + +/** + * __kvmppc_gse_put_reg() - add a register type guest state element to a buffer + * @gsb: guest state buffer to add element to + * @iden: guest state ID + * @val: host endian value + * + * Adds a register type guest state element. Uses the guest state ID for + * determining the length of the guest element. If the guest state ID has + * bits that can not be set they will be cleared. + */ +static inline int __kvmppc_gse_put_reg(struct kvmppc_gs_buff *gsb, u16 iden, + u64 val) +{ + val &= kvmppc_gsid_mask(iden); + if (kvmppc_gsid_size(iden) == sizeof(u64)) + return kvmppc_gse_put_u64(gsb, iden, val); + + if (kvmppc_gsid_size(iden) == sizeof(u32)) { + u32 tmp; + + tmp = (u32)val; + if (tmp != val) + return -EINVAL; + + return kvmppc_gse_put_u32(gsb, iden, tmp); + } + return -EINVAL; +} + +/** + * kvmppc_gse_put_vector128() - add a vector guest state element to a buffer + * @gsb: guest state buffer to add element to + * @iden: guest state ID + * @val: 16 byte vector value + */ +static inline int kvmppc_gse_put_vector128(struct kvmppc_gs_buff *gsb, u16 iden, + vector128 *val) +{ + __be64 tmp[2] = { 0 }; + union { + __vector128 v; + u64 dw[2]; + } u; + + u.v = *val; + tmp[0] = cpu_to_be64(u.dw[TS_FPROFFSET]); +#ifdef CONFIG_VSX + tmp[1] = cpu_to_be64(u.dw[TS_VSRLOWOFFSET]); +#endif + return __kvmppc_gse_put(gsb, iden, sizeof(tmp), &tmp); +} + +/** + * kvmppc_gse_put_part_table() - add a partition table guest state element to a + * buffer + * @gsb: guest state buffer to add element to + * @iden: guest state ID + * @val: partition table value + */ +static inline int kvmppc_gse_put_part_table(struct kvmppc_gs_buff *gsb, + u16 iden, + struct kvmppc_gs_part_table val) +{ + __be64 tmp[3]; + + tmp[0] = cpu_to_be64(val.address); + tmp[1] = cpu_to_be64(val.ea_bits); + tmp[2] = cpu_to_be64(val.gpd_size); + return __kvmppc_gse_put(gsb, KVMPPC_GSID_PARTITION_TABLE, sizeof(tmp), + &tmp); +} + +/** + * kvmppc_gse_put_proc_table() - add a process table guest state element to a + * buffer + * @gsb: guest state buffer to add element to + * @iden: guest state ID + * @val: process table value + */ +static inline int kvmppc_gse_put_proc_table(struct kvmppc_gs_buff *gsb, + u16 iden, + struct kvmppc_gs_proc_table val) +{ + __be64 tmp[2]; + + tmp[0] = cpu_to_be64(val.address); + tmp[1] = cpu_to_be64(val.gpd_size); + return __kvmppc_gse_put(gsb, KVMPPC_GSID_PROCESS_TABLE, sizeof(tmp), + &tmp); +} + +/** + * kvmppc_gse_put_buff_info() - adds a GSB description guest state element to a + * buffer + * @gsb: guest state buffer to add element to + * @iden: guest state ID + * @val: guest state buffer description value + */ +static inline int kvmppc_gse_put_buff_info(struct kvmppc_gs_buff *gsb, u16 iden, + struct kvmppc_gs_buff_info val) +{ + __be64 tmp[2]; + + tmp[0] = cpu_to_be64(val.address); + tmp[1] = cpu_to_be64(val.size); + return __kvmppc_gse_put(gsb, iden, sizeof(tmp), &tmp); +} + +int __kvmppc_gse_put(struct kvmppc_gs_buff *gsb, u16 iden, u16 size, + const void *data); + +/** + * kvmppc_gse_get_be32() - return the data of a be32 element + * @gse: guest state element + */ +static inline __be32 kvmppc_gse_get_be32(const struct kvmppc_gs_elem *gse) +{ + if (WARN_ON(kvmppc_gse_len(gse) != sizeof(__be32))) + return 0; + return *(__be32 *)kvmppc_gse_data(gse); +} + +/** + * kvmppc_gse_get_u32() - return the data of a be32 element in host endianness + * @gse: guest state element + */ +static inline u32 kvmppc_gse_get_u32(const struct kvmppc_gs_elem *gse) +{ + return be32_to_cpu(kvmppc_gse_get_be32(gse)); +} + +/** + * kvmppc_gse_get_be64() - return the data of a be64 element + * @gse: guest state element + */ +static inline __be64 kvmppc_gse_get_be64(const struct kvmppc_gs_elem *gse) +{ + if (WARN_ON(kvmppc_gse_len(gse) != sizeof(__be64))) + return 0; + return *(__be64 *)kvmppc_gse_data(gse); +} + +/** + * kvmppc_gse_get_u64() - return the data of a be64 element in host endianness + * @gse: guest state element + */ +static inline u64 kvmppc_gse_get_u64(const struct kvmppc_gs_elem *gse) +{ + return be64_to_cpu(kvmppc_gse_get_be64(gse)); +} + +/** + * kvmppc_gse_get_vector128() - return the data of a vector element + * @gse: guest state element + */ +static inline void kvmppc_gse_get_vector128(const struct kvmppc_gs_elem *gse, + vector128 *v) +{ + union { + __vector128 v; + u64 dw[2]; + } u = { 0 }; + __be64 *src; + + if (WARN_ON(kvmppc_gse_len(gse) != sizeof(__vector128))) + *v = u.v; + + src = (__be64 *)kvmppc_gse_data(gse); + u.dw[TS_FPROFFSET] = be64_to_cpu(src[0]); +#ifdef CONFIG_VSX + u.dw[TS_VSRLOWOFFSET] = be64_to_cpu(src[1]); +#endif + *v = u.v; +} + +/************************************************************************** + * Guest State Bitmap + **************************************************************************/ + +bool kvmppc_gsbm_test(struct kvmppc_gs_bitmap *gsbm, u16 iden); +void kvmppc_gsbm_set(struct kvmppc_gs_bitmap *gsbm, u16 iden); +void kvmppc_gsbm_clear(struct kvmppc_gs_bitmap *gsbm, u16 iden); +u16 kvmppc_gsbm_next(struct kvmppc_gs_bitmap *gsbm, u16 prev); + +/** + * kvmppc_gsbm_zero - zero the entire bitmap + * @gsbm: guest state buffer bitmap + */ +static inline void kvmppc_gsbm_zero(struct kvmppc_gs_bitmap *gsbm) +{ + bitmap_zero(gsbm->bitmap, KVMPPC_GSE_IDEN_COUNT); +} + +/** + * kvmppc_gsbm_fill - fill the entire bitmap + * @gsbm: guest state buffer bitmap + */ +static inline void kvmppc_gsbm_fill(struct kvmppc_gs_bitmap *gsbm) +{ + bitmap_fill(gsbm->bitmap, KVMPPC_GSE_IDEN_COUNT); + clear_bit(0, gsbm->bitmap); +} + +/** + * kvmppc_gsbm_for_each - iterate the present guest state IDs + * @gsbm: guest state buffer bitmap + * @iden: current guest state ID + */ +#define kvmppc_gsbm_for_each(gsbm, iden) \ + for (iden = kvmppc_gsbm_next(gsbm, 0); iden != 0; \ + iden = kvmppc_gsbm_next(gsbm, iden)) + +/************************************************************************** + * Guest State Parser + **************************************************************************/ + +void kvmppc_gsp_insert(struct kvmppc_gs_parser *gsp, u16 iden, + struct kvmppc_gs_elem *gse); +struct kvmppc_gs_elem *kvmppc_gsp_lookup(struct kvmppc_gs_parser *gsp, + u16 iden); + +/** + * kvmppc_gsp_for_each - iterate the <guest state IDs, guest state element> + * pairs + * @gsp: guest state buffer bitmap + * @iden: current guest state ID + * @gse: guest state element + */ +#define kvmppc_gsp_for_each(gsp, iden, gse) \ + for (iden = kvmppc_gsbm_next(&(gsp)->iterator, 0), \ + gse = kvmppc_gsp_lookup((gsp), iden); \ + iden != 0; iden = kvmppc_gsbm_next(&(gsp)->iterator, iden), \ + gse = kvmppc_gsp_lookup((gsp), iden)) + +/************************************************************************** + * Guest State Message + **************************************************************************/ + +/** + * kvmppc_gsm_for_each - iterate the guest state IDs included in a guest state + * message + * @gsp: guest state buffer bitmap + * @iden: current guest state ID + * @gse: guest state element + */ +#define kvmppc_gsm_for_each(gsm, iden) \ + for (iden = kvmppc_gsbm_next(&gsm->bitmap, 0); iden != 0; \ + iden = kvmppc_gsbm_next(&gsm->bitmap, iden)) + +int kvmppc_gsm_init(struct kvmppc_gs_msg *mgs, struct kvmppc_gs_msg_ops *ops, + void *data, unsigned long flags); + +struct kvmppc_gs_msg *kvmppc_gsm_new(struct kvmppc_gs_msg_ops *ops, void *data, + unsigned long flags, gfp_t gfp_flags); +void kvmppc_gsm_free(struct kvmppc_gs_msg *gsm); +size_t kvmppc_gsm_size(struct kvmppc_gs_msg *gsm); +int kvmppc_gsm_fill_info(struct kvmppc_gs_msg *gsm, struct kvmppc_gs_buff *gsb); +int kvmppc_gsm_refresh_info(struct kvmppc_gs_msg *gsm, + struct kvmppc_gs_buff *gsb); + +/** + * kvmppc_gsm_include - indicate a guest state ID should be included when + * serializing + * @gsm: guest state message + * @iden: guest state ID + */ +static inline void kvmppc_gsm_include(struct kvmppc_gs_msg *gsm, u16 iden) +{ + kvmppc_gsbm_set(&gsm->bitmap, iden); +} + +/** + * kvmppc_gsm_includes - check if a guest state ID will be included when + * serializing + * @gsm: guest state message + * @iden: guest state ID + */ +static inline bool kvmppc_gsm_includes(struct kvmppc_gs_msg *gsm, u16 iden) +{ + return kvmppc_gsbm_test(&gsm->bitmap, iden); +} + +/** + * kvmppc_gsm_includes - indicate all guest state IDs should be included when + * serializing + * @gsm: guest state message + * @iden: guest state ID + */ +static inline void kvmppc_gsm_include_all(struct kvmppc_gs_msg *gsm) +{ + kvmppc_gsbm_fill(&gsm->bitmap); +} + +/** + * kvmppc_gsm_include - clear the guest state IDs that should be included when + * serializing + * @gsm: guest state message + */ +static inline void kvmppc_gsm_reset(struct kvmppc_gs_msg *gsm) +{ + kvmppc_gsbm_zero(&gsm->bitmap); +} + +/** + * kvmppc_gsb_receive_data - flexibly update values from a guest state buffer + * @gsb: guest state buffer + * @gsm: guest state message + * + * Requests updated values for the guest state values included in the guest + * state message. The guest state message will then deserialize the guest state + * buffer. + */ +static inline int kvmppc_gsb_receive_data(struct kvmppc_gs_buff *gsb, + struct kvmppc_gs_msg *gsm) +{ + int rc; + + kvmppc_gsb_reset(gsb); + rc = kvmppc_gsm_fill_info(gsm, gsb); + if (rc < 0) + return rc; + + rc = kvmppc_gsb_recv(gsb, gsm->flags); + if (rc < 0) + return rc; + + rc = kvmppc_gsm_refresh_info(gsm, gsb); + if (rc < 0) + return rc; + return 0; +} + +/** + * kvmppc_gsb_recv - receive a single guest state ID + * @gsb: guest state buffer + * @gsm: guest state message + * @iden: guest state identity + */ +static inline int kvmppc_gsb_receive_datum(struct kvmppc_gs_buff *gsb, + struct kvmppc_gs_msg *gsm, u16 iden) +{ + int rc; + + kvmppc_gsm_include(gsm, iden); + rc = kvmppc_gsb_receive_data(gsb, gsm); + if (rc < 0) + return rc; + kvmppc_gsm_reset(gsm); + return 0; +} + +/** + * kvmppc_gsb_send_data - flexibly send values from a guest state buffer + * @gsb: guest state buffer + * @gsm: guest state message + * + * Sends the guest state values included in the guest state message. + */ +static inline int kvmppc_gsb_send_data(struct kvmppc_gs_buff *gsb, + struct kvmppc_gs_msg *gsm) +{ + int rc; + + kvmppc_gsb_reset(gsb); + rc = kvmppc_gsm_fill_info(gsm, gsb); + if (rc < 0) + return rc; + rc = kvmppc_gsb_send(gsb, gsm->flags); + + return rc; +} + +/** + * kvmppc_gsb_recv - send a single guest state ID + * @gsb: guest state buffer + * @gsm: guest state message + * @iden: guest state identity + */ +static inline int kvmppc_gsb_send_datum(struct kvmppc_gs_buff *gsb, + struct kvmppc_gs_msg *gsm, u16 iden) +{ + int rc; + + kvmppc_gsm_include(gsm, iden); + rc = kvmppc_gsb_send_data(gsb, gsm); + if (rc < 0) + return rc; + kvmppc_gsm_reset(gsm); + return 0; +} + +#endif /* _ASM_POWERPC_GUEST_STATE_BUFFER_H */ diff --git a/arch/powerpc/include/asm/hardirq.h b/arch/powerpc/include/asm/hardirq.h index f1e9067bd5ac..f133b5930ae1 100644 --- a/arch/powerpc/include/asm/hardirq.h +++ b/arch/powerpc/include/asm/hardirq.h @@ -13,7 +13,6 @@ typedef struct { unsigned int pmu_irqs; unsigned int mce_exceptions; unsigned int spurious_irqs; - unsigned int hmi_exceptions; unsigned int sreset_irqs; #ifdef CONFIG_PPC_WATCHDOG unsigned int soft_nmi_irqs; diff --git a/arch/powerpc/include/asm/head-64.h b/arch/powerpc/include/asm/head-64.h index 2dabcf668292..d73153b0275d 100644 --- a/arch/powerpc/include/asm/head-64.h +++ b/arch/powerpc/include/asm/head-64.h @@ -16,7 +16,7 @@ .section ".head.data.\name\()","a",@progbits .endm .macro use_ftsec name - .section ".head.text.\name\()" + .section ".head.text.\name\()","ax",@progbits .endm /* @@ -98,13 +98,9 @@ start_text: . = sname##_len; #define USE_FIXED_SECTION(sname) \ - fs_label = start_##sname; \ - fs_start = sname##_start; \ use_ftsec sname; #define USE_TEXT_SECTION() \ - fs_label = start_text; \ - fs_start = text_start; \ .text #define CLOSE_FIXED_SECTION(sname) \ @@ -128,7 +124,7 @@ name: .if ((start) % (size) != 0); \ .error "Fixed section exception vector misalignment"; \ .endif; \ - .if ((size) != 0x20) && ((size) != 0x80) && ((size) != 0x100); \ + .if ((size) != 0x20) && ((size) != 0x80) && ((size) != 0x100) && ((size) != 0x1000); \ .error "Fixed section exception vector bad size"; \ .endif; \ .if (start) < sname##_start; \ @@ -161,13 +157,15 @@ name: * - ABS_ADDR is used to find the absolute address of any symbol, from within * a fixed section. */ -#define DEFINE_FIXED_SYMBOL(label) \ - label##_absolute = (label - fs_label + fs_start) +// define label as being _in_ sname +#define DEFINE_FIXED_SYMBOL(label, sname) \ + label##_absolute = (label - start_ ## sname + sname ## _start) #define FIXED_SYMBOL_ABS_ADDR(label) \ (label##_absolute) -#define ABS_ADDR(label) (label - fs_label + fs_start) +// find label from _within_ sname +#define ABS_ADDR(label, sname) (label - start_ ## sname + sname ## _start) #endif /* __ASSEMBLY__ */ diff --git a/arch/powerpc/include/asm/highmem.h b/arch/powerpc/include/asm/highmem.h index a4b65b186ec6..c0fcd1bbdba9 100644 --- a/arch/powerpc/include/asm/highmem.h +++ b/arch/powerpc/include/asm/highmem.h @@ -24,13 +24,10 @@ #ifdef __KERNEL__ #include <linux/interrupt.h> -#include <asm/kmap_types.h> #include <asm/cacheflush.h> #include <asm/page.h> #include <asm/fixmap.h> -extern pte_t *kmap_pte; -extern pgprot_t kmap_prot; extern pte_t *pkmap_page_table; /* @@ -59,35 +56,15 @@ extern pte_t *pkmap_page_table; #define PKMAP_NR(virt) ((virt-PKMAP_BASE) >> PAGE_SHIFT) #define PKMAP_ADDR(nr) (PKMAP_BASE + ((nr) << PAGE_SHIFT)) -extern void *kmap_high(struct page *page); -extern void kunmap_high(struct page *page); -extern void *kmap_atomic_prot(struct page *page, pgprot_t prot); -extern void __kunmap_atomic(void *kvaddr); - -static inline void *kmap(struct page *page) -{ - might_sleep(); - if (!PageHighMem(page)) - return page_address(page); - return kmap_high(page); -} - -static inline void kunmap(struct page *page) -{ - BUG_ON(in_interrupt()); - if (!PageHighMem(page)) - return; - kunmap_high(page); -} - -static inline void *kmap_atomic(struct page *page) -{ - return kmap_atomic_prot(page, kmap_prot); -} - - #define flush_cache_kmaps() flush_cache_all() +#define arch_kmap_local_set_pte(mm, vaddr, ptep, ptev) \ + __set_pte_at(mm, vaddr, ptep, ptev, 1) +#define arch_kmap_local_post_map(vaddr, pteval) \ + local_flush_tlb_page(NULL, vaddr) +#define arch_kmap_local_post_unmap(vaddr) \ + local_flush_tlb_page(NULL, vaddr) + #endif /* __KERNEL__ */ #endif /* _ASM_HIGHMEM_H */ diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h index bd6504c28c2f..ea71f7245a63 100644 --- a/arch/powerpc/include/asm/hugetlb.h +++ b/arch/powerpc/include/asm/hugetlb.h @@ -7,17 +7,15 @@ #ifdef CONFIG_PPC_BOOK3S_64 #include <asm/book3s/64/hugetlb.h> -#elif defined(CONFIG_PPC_FSL_BOOK3E) -#include <asm/nohash/hugetlb-book3e.h> +#elif defined(CONFIG_PPC_E500) +#include <asm/nohash/hugetlb-e500.h> #elif defined(CONFIG_PPC_8xx) #include <asm/nohash/32/hugetlb-8xx.h> #endif /* CONFIG_PPC_BOOK3S_64 */ extern bool hugetlb_disabled; -void hugetlbpage_init_default(void); - -void flush_dcache_icache_hugepage(struct page *page); +void __init hugetlbpage_init_defaultsize(void); int slice_is_hugepage_only_range(struct mm_struct *mm, unsigned long addr, unsigned long len); @@ -26,10 +24,11 @@ static inline int is_hugepage_only_range(struct mm_struct *mm, unsigned long addr, unsigned long len) { - if (IS_ENABLED(CONFIG_PPC_MM_SLICES) && !radix_enabled()) + if (IS_ENABLED(CONFIG_PPC_64S_HASH_MMU) && !radix_enabled()) return slice_is_hugepage_only_range(mm, addr, len); return 0; } +#define is_hugepage_only_range is_hugepage_only_range #define __HAVE_ARCH_HUGETLB_FREE_PGD_RANGE void hugetlb_free_pgd_range(struct mmu_gather *tlb, unsigned long addr, @@ -40,19 +39,18 @@ void hugetlb_free_pgd_range(struct mmu_gather *tlb, unsigned long addr, static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { -#ifdef CONFIG_PPC64 return __pte(pte_update(mm, addr, ptep, ~0UL, 0, 1)); -#else - return __pte(pte_update(ptep, ~0UL, 0)); -#endif } #define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH -static inline void huge_ptep_clear_flush(struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep) +static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep) { - huge_ptep_get_and_clear(vma->vm_mm, addr, ptep); + pte_t pte; + + pte = huge_ptep_get_and_clear(vma->vm_mm, addr, ptep); flush_hugetlb_page(vma, addr); + return pte; } #define __HAVE_ARCH_HUGE_PTEP_SET_ACCESS_FLAGS @@ -60,10 +58,7 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t pte, int dirty); -static inline void arch_clear_hugepage_flags(struct page *page) -{ -} - +void gigantic_hugetlb_cma_reserve(void) __init; #include <asm-generic/hugetlb.h> #else /* ! CONFIG_HUGETLB_PAGE */ @@ -78,6 +73,15 @@ static inline pte_t *hugepte_offset(hugepd_t hpd, unsigned long addr, { return NULL; } + + +static inline void __init gigantic_hugetlb_cma_reserve(void) +{ +} + +static inline void __init hugetlbpage_init_defaultsize(void) +{ +} #endif /* CONFIG_HUGETLB_PAGE */ #endif /* _ASM_POWERPC_HUGETLB_H */ diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h index 13bd870609c3..a41e542ba94d 100644 --- a/arch/powerpc/include/asm/hvcall.h +++ b/arch/powerpc/include/asm/hvcall.h @@ -79,6 +79,7 @@ #define H_NOT_ENOUGH_RESOURCES -44 #define H_R_STATE -45 #define H_RESCINDED -46 +#define H_ABORTED -54 #define H_P2 -55 #define H_P3 -56 #define H_P4 -57 @@ -87,6 +88,7 @@ #define H_P7 -60 #define H_P8 -61 #define H_P9 -62 +#define H_NOOP -63 #define H_TOO_BIG -64 #define H_UNSUPPORTED -67 #define H_OVERLAP -68 @@ -97,6 +99,19 @@ #define H_OP_MODE -73 #define H_COP_HW -74 #define H_STATE -75 +#define H_IN_USE -77 + +#define H_INVALID_ELEMENT_ID -79 +#define H_INVALID_ELEMENT_SIZE -80 +#define H_INVALID_ELEMENT_VALUE -81 +#define H_INPUT_BUFFER_NOT_DEFINED -82 +#define H_INPUT_BUFFER_TOO_SMALL -83 +#define H_OUTPUT_BUFFER_NOT_DEFINED -84 +#define H_OUTPUT_BUFFER_TOO_SMALL -85 +#define H_PARTITION_PAGE_TABLE_NOT_DEFINED -86 +#define H_GUEST_VCPU_STATE_NOT_HV_OWNED -87 + + #define H_UNSUPPORTED_FLAG_START -256 #define H_UNSUPPORTED_FLAG_END -511 #define H_MULTI_THREADS_ACTIVE -9005 @@ -155,6 +170,14 @@ #define H_VASI_RESUMED 5 #define H_VASI_COMPLETED 6 +/* VASI signal codes. Only the Cancel code is valid for H_VASI_SIGNAL. */ +#define H_VASI_SIGNAL_CANCEL 1 +#define H_VASI_SIGNAL_ABORT 2 +#define H_VASI_SIGNAL_SUSPEND 3 +#define H_VASI_SIGNAL_COMPLETE 4 +#define H_VASI_SIGNAL_ENABLE 5 +#define H_VASI_SIGNAL_FAILOVER 6 + /* Each control block has to be on a 4K boundary */ #define H_CB_ALIGNMENT 4096 @@ -237,7 +260,7 @@ #define H_CREATE_RPT 0x1A4 #define H_REMOVE_RPT 0x1A8 #define H_REGISTER_RPAGES 0x1AC -#define H_DISABLE_AND_GETC 0x1B0 +#define H_DISABLE_AND_GET 0x1B0 #define H_ERROR_DATA 0x1B4 #define H_GET_HCA_INFO 0x1B8 #define H_GET_PERF_COUNT 0x1BC @@ -261,6 +284,7 @@ #define H_ADD_CONN 0x284 #define H_DEL_CONN 0x288 #define H_JOIN 0x298 +#define H_VASI_SIGNAL 0x2A0 #define H_VASI_STATE 0x2A4 #define H_VIOCTL 0x2A8 #define H_ENABLE_CRQ 0x2B0 @@ -285,6 +309,13 @@ #define H_RESIZE_HPT_COMMIT 0x370 #define H_REGISTER_PROC_TBL 0x37C #define H_SIGNAL_SYS_RESET 0x380 +#define H_ALLOCATE_VAS_WINDOW 0x388 +#define H_MODIFY_VAS_WINDOW 0x38C +#define H_DEALLOCATE_VAS_WINDOW 0x390 +#define H_QUERY_VAS_WINDOW 0x394 +#define H_QUERY_VAS_CAPABILITIES 0x398 +#define H_QUERY_NX_CAPABILITIES 0x39C +#define H_GET_NX_FAULT 0x3A0 #define H_INT_GET_SOURCE_INFO 0x3A8 #define H_INT_SET_SOURCE_CONFIG 0x3AC #define H_INT_GET_SOURCE_CONFIG 0x3B0 @@ -305,7 +336,29 @@ #define H_SCM_UNBIND_ALL 0x3FC #define H_SCM_HEALTH 0x400 #define H_SCM_PERFORMANCE_STATS 0x418 -#define MAX_HCALL_OPCODE H_SCM_PERFORMANCE_STATS +#define H_PKS_GET_CONFIG 0x41C +#define H_PKS_SET_PASSWORD 0x420 +#define H_PKS_GEN_PASSWORD 0x424 +#define H_PKS_WRITE_OBJECT 0x42C +#define H_PKS_GEN_KEY 0x430 +#define H_PKS_READ_OBJECT 0x434 +#define H_PKS_REMOVE_OBJECT 0x438 +#define H_PKS_CONFIRM_OBJECT_FLUSHED 0x43C +#define H_RPT_INVALIDATE 0x448 +#define H_SCM_FLUSH 0x44C +#define H_GET_ENERGY_SCALE_INFO 0x450 +#define H_PKS_SIGNED_UPDATE 0x454 +#define H_WATCHDOG 0x45C +#define H_GUEST_GET_CAPABILITIES 0x460 +#define H_GUEST_SET_CAPABILITIES 0x464 +#define H_GUEST_CREATE 0x470 +#define H_GUEST_CREATE_VCPU 0x474 +#define H_GUEST_GET_STATE 0x478 +#define H_GUEST_SET_STATE 0x47C +#define H_GUEST_RUN_VCPU 0x480 +#define H_GUEST_COPY_MEMORY 0x484 +#define H_GUEST_DELETE 0x488 +#define MAX_HCALL_OPCODE H_GUEST_DELETE /* Scope args for H_SCM_UNBIND_ALL */ #define H_UNBIND_SCOPE_ALL (0x1) @@ -331,6 +384,14 @@ /* Platform specific hcalls, used by KVM */ #define H_RTAS 0xf000 +/* + * Platform specific hcalls, used by QEMU/SLOF. These are ignored by + * KVM and only kept here so we can identify them during tracing. + */ +#define H_LOGICAL_MEMOP 0xF001 +#define H_CAS 0XF002 +#define H_UPDATE_DT 0XF003 + /* "Platform specific hcalls", provided by PHYP */ #define H_GET_24X7_CATALOG_PAGE 0xF078 #define H_GET_24X7_DATA 0xF07C @@ -350,12 +411,14 @@ #define H_SVM_PAGE_OUT 0xEF04 #define H_SVM_INIT_START 0xEF08 #define H_SVM_INIT_DONE 0xEF0C +#define H_SVM_INIT_ABORT 0xEF14 /* Values for 2nd argument to H_SET_MODE */ #define H_SET_MODE_RESOURCE_SET_CIABR 1 -#define H_SET_MODE_RESOURCE_SET_DAWR 2 +#define H_SET_MODE_RESOURCE_SET_DAWR0 2 #define H_SET_MODE_RESOURCE_ADDR_TRANS_MODE 3 #define H_SET_MODE_RESOURCE_LE 4 +#define H_SET_MODE_RESOURCE_SET_DAWR1 5 /* Values for argument to H_SIGNAL_SYS_RESET */ #define H_SIGNAL_SYS_RESET_ALL -1 @@ -372,11 +435,17 @@ #define H_CPU_CHAR_THREAD_RECONFIG_CTRL (1ull << 57) // IBM bit 6 #define H_CPU_CHAR_COUNT_CACHE_DISABLED (1ull << 56) // IBM bit 7 #define H_CPU_CHAR_BCCTR_FLUSH_ASSIST (1ull << 54) // IBM bit 9 +#define H_CPU_CHAR_BCCTR_LINK_FLUSH_ASSIST (1ull << 52) // IBM bit 11 #define H_CPU_BEHAV_FAVOUR_SECURITY (1ull << 63) // IBM bit 0 #define H_CPU_BEHAV_L1D_FLUSH_PR (1ull << 62) // IBM bit 1 #define H_CPU_BEHAV_BNDS_CHK_SPEC_BAR (1ull << 61) // IBM bit 2 +#define H_CPU_BEHAV_FAVOUR_SECURITY_H (1ull << 60) // IBM bit 3 #define H_CPU_BEHAV_FLUSH_COUNT_CACHE (1ull << 58) // IBM bit 5 +#define H_CPU_BEHAV_FLUSH_LINK_STACK (1ull << 57) // IBM bit 6 +#define H_CPU_BEHAV_NO_L1D_FLUSH_ENTRY (1ull << 56) // IBM bit 7 +#define H_CPU_BEHAV_NO_L1D_FLUSH_UACCESS (1ull << 55) // IBM bit 8 +#define H_CPU_BEHAV_NO_STF_BARRIER (1ull << 54) // IBM bit 9 /* Flag values used in H_REGISTER_PROC_TBL hcall */ #define PROC_TABLE_OP_MASK 0x18 @@ -388,6 +457,46 @@ #define PROC_TABLE_RADIX 0x04 #define PROC_TABLE_GTSE 0x01 +/* + * Defines for + * H_RPT_INVALIDATE - Invalidate RPT translation lookaside information. + */ + +/* Type of translation to invalidate (type) */ +#define H_RPTI_TYPE_NESTED 0x0001 /* Invalidate nested guest partition-scope */ +#define H_RPTI_TYPE_TLB 0x0002 /* Invalidate TLB */ +#define H_RPTI_TYPE_PWC 0x0004 /* Invalidate Page Walk Cache */ +/* Invalidate caching of Process Table Entries if H_RPTI_TYPE_NESTED is clear */ +#define H_RPTI_TYPE_PRT 0x0008 +/* Invalidate caching of Partition Table Entries if H_RPTI_TYPE_NESTED is set */ +#define H_RPTI_TYPE_PAT 0x0008 +#define H_RPTI_TYPE_ALL (H_RPTI_TYPE_TLB | H_RPTI_TYPE_PWC | \ + H_RPTI_TYPE_PRT) +#define H_RPTI_TYPE_NESTED_ALL (H_RPTI_TYPE_TLB | H_RPTI_TYPE_PWC | \ + H_RPTI_TYPE_PAT) + +/* Invalidation targets (target) */ +#define H_RPTI_TARGET_CMMU 0x01 /* All virtual processors in the partition */ +#define H_RPTI_TARGET_CMMU_LOCAL 0x02 /* Current virtual processor */ +/* All nest/accelerator agents in use by the partition */ +#define H_RPTI_TARGET_NMMU 0x04 + +/* Page size mask (page sizes) */ +#define H_RPTI_PAGE_4K 0x01 +#define H_RPTI_PAGE_64K 0x02 +#define H_RPTI_PAGE_2M 0x04 +#define H_RPTI_PAGE_1G 0x08 +#define H_RPTI_PAGE_ALL (-1UL) + +/* Flags for H_GUEST_{S,G}_STATE */ +#define H_GUEST_FLAGS_WIDE (1UL<<(63-0)) + +/* Flag values used for H_{S,G}SET_GUEST_CAPABILITIES */ +#define H_GUEST_CAP_COPY_MEM (1UL<<(63-0)) +#define H_GUEST_CAP_POWER9 (1UL<<(63-1)) +#define H_GUEST_CAP_POWER10 (1UL<<(63-2)) +#define H_GUEST_CAP_BITMAP2 (1UL<<(63-63)) + #ifndef __ASSEMBLY__ #include <linux/types.h> @@ -401,6 +510,9 @@ */ long plpar_hcall_norets(unsigned long opcode, ...); +/* Variant which does not do hcall tracing */ +long plpar_hcall_norets_notrace(unsigned long opcode, ...); + /** * plpar_hcall: - Make a pseries hypervisor call * @opcode: The hypervisor call to make. @@ -440,6 +552,11 @@ long plpar_hcall_raw(unsigned long opcode, unsigned long *retbuf, ...); long plpar_hcall9(unsigned long opcode, unsigned long *retbuf, ...); long plpar_hcall9_raw(unsigned long opcode, unsigned long *retbuf, ...); +/* pseries hcall tracing */ +extern struct static_key hcall_tracepoint_key; +void __trace_hcall_entry(unsigned long opcode, unsigned long *args); +void __trace_hcall_exit(long opcode, long retval, unsigned long *retbuf); + struct hvcall_mpp_data { unsigned long entitled_mem; unsigned long mapped_mem; @@ -490,9 +607,12 @@ struct h_cpu_char_result { u64 behaviour; }; -/* Register state for entering a nested guest with H_ENTER_NESTED */ +/* + * Register state for entering a nested guest with H_ENTER_NESTED. + * New member must be added at the end. + */ struct hv_guest_state { - u64 version; /* version of this structure layout */ + u64 version; /* version of this structure layout, must be first */ u32 lpid; u32 vcpu_token; /* These registers are hypervisor privileged (at least for writing) */ @@ -521,10 +641,62 @@ struct hv_guest_state { u64 pidr; u64 cfar; u64 ppr; + /* Version 1 ends here */ + u64 dawr1; + u64 dawrx1; + /* Version 2 ends here */ }; /* Latest version of hv_guest_state structure */ -#define HV_GUEST_STATE_VERSION 1 +#define HV_GUEST_STATE_VERSION 2 + +static inline int hv_guest_state_size(unsigned int version) +{ + switch (version) { + case 1: + return offsetofend(struct hv_guest_state, ppr); + case 2: + return offsetofend(struct hv_guest_state, dawrx1); + default: + return -1; + } +} + +/* + * From the document "H_GetPerformanceCounterInfo Interface" v1.07 + * + * H_GET_PERF_COUNTER_INFO argument + */ +struct hv_get_perf_counter_info_params { + __be32 counter_request; /* I */ + __be32 starting_index; /* IO */ + __be16 secondary_index; /* IO */ + __be16 returned_values; /* O */ + __be32 detail_rc; /* O, only needed when called via *_norets() */ + + /* + * O, size each of counter_value element in bytes, only set for version + * >= 0x3 + */ + __be16 cv_element_size; + + /* I, 0 (zero) for versions < 0x3 */ + __u8 counter_info_version_in; + + /* O, 0 (zero) if version < 0x3. Must be set to 0 when making hcall */ + __u8 counter_info_version_out; + __u8 reserved[0xC]; + __u8 counter_value[]; +} __packed; + +#define HGPCI_REQ_BUFFER_SIZE 4096 +#define HGPCI_MAX_DATA_BYTES \ + (HGPCI_REQ_BUFFER_SIZE - sizeof(struct hv_get_perf_counter_info_params)) + +struct hv_gpci_request_buffer { + struct hv_get_perf_counter_info_params params; + uint8_t bytes[HGPCI_MAX_DATA_BYTES]; +} __packed; #endif /* __ASSEMBLY__ */ #endif /* __KERNEL__ */ diff --git a/arch/powerpc/include/asm/hvconsole.h b/arch/powerpc/include/asm/hvconsole.h index 999ed5ac9053..d841a97010a0 100644 --- a/arch/powerpc/include/asm/hvconsole.h +++ b/arch/powerpc/include/asm/hvconsole.h @@ -21,8 +21,11 @@ * Vio firmware always attempts to fetch MAX_VIO_GET_CHARS chars. The 'count' * parm is included to conform to put_chars() function pointer template */ -extern int hvc_get_chars(uint32_t vtermno, char *buf, int count); -extern int hvc_put_chars(uint32_t vtermno, const char *buf, int count); +extern ssize_t hvc_get_chars(uint32_t vtermno, u8 *buf, size_t count); +extern ssize_t hvc_put_chars(uint32_t vtermno, const u8 *buf, size_t count); + +/* Provided by HVC VIO */ +void hvc_vio_init_early(void); #endif /* __KERNEL__ */ #endif /* _PPC64_HVCONSOLE_H */ diff --git a/arch/powerpc/include/asm/hvsi.h b/arch/powerpc/include/asm/hvsi.h index 464a7519ed64..9058edcb632b 100644 --- a/arch/powerpc/include/asm/hvsi.h +++ b/arch/powerpc/include/asm/hvsi.h @@ -64,7 +64,7 @@ struct hvsi_priv { unsigned int inbuf_len; /* data in input buffer */ unsigned char inbuf[HVSI_INBUF_SIZE]; unsigned int inbuf_cur; /* Cursor in input buffer */ - unsigned int inbuf_pktlen; /* packet length from cursor */ + size_t inbuf_pktlen; /* packet length from cursor */ atomic_t seqno; /* packet sequence number */ unsigned int opened:1; /* driver opened */ unsigned int established:1; /* protocol established */ @@ -72,24 +72,26 @@ struct hvsi_priv { unsigned int mctrl_update:1; /* modem control updated */ unsigned short mctrl; /* modem control */ struct tty_struct *tty; /* tty structure */ - int (*get_chars)(uint32_t termno, char *buf, int count); - int (*put_chars)(uint32_t termno, const char *buf, int count); + ssize_t (*get_chars)(uint32_t termno, u8 *buf, size_t count); + ssize_t (*put_chars)(uint32_t termno, const u8 *buf, size_t count); uint32_t termno; }; /* hvsi lib functions */ struct hvc_struct; extern void hvsilib_init(struct hvsi_priv *pv, - int (*get_chars)(uint32_t termno, char *buf, int count), - int (*put_chars)(uint32_t termno, const char *buf, - int count), + ssize_t (*get_chars)(uint32_t termno, u8 *buf, + size_t count), + ssize_t (*put_chars)(uint32_t termno, const u8 *buf, + size_t count), int termno, int is_console); extern int hvsilib_open(struct hvsi_priv *pv, struct hvc_struct *hp); extern void hvsilib_close(struct hvsi_priv *pv, struct hvc_struct *hp); extern int hvsilib_read_mctrl(struct hvsi_priv *pv); extern int hvsilib_write_mctrl(struct hvsi_priv *pv, int dtr); extern void hvsilib_establish(struct hvsi_priv *pv); -extern int hvsilib_get_chars(struct hvsi_priv *pv, char *buf, int count); -extern int hvsilib_put_chars(struct hvsi_priv *pv, const char *buf, int count); +extern ssize_t hvsilib_get_chars(struct hvsi_priv *pv, u8 *buf, size_t count); +extern ssize_t hvsilib_put_chars(struct hvsi_priv *pv, const u8 *buf, + size_t count); #endif /* _HVSI_H */ diff --git a/arch/powerpc/include/asm/hw_breakpoint.h b/arch/powerpc/include/asm/hw_breakpoint.h index 27ac6f5d2891..66db0147d5b4 100644 --- a/arch/powerpc/include/asm/hw_breakpoint.h +++ b/arch/powerpc/include/asm/hw_breakpoint.h @@ -9,15 +9,19 @@ #ifndef _PPC_BOOK3S_64_HW_BREAKPOINT_H #define _PPC_BOOK3S_64_HW_BREAKPOINT_H +#include <asm/cpu_has_feature.h> + #ifdef __KERNEL__ struct arch_hw_breakpoint { unsigned long address; u16 type; u16 len; /* length of the target data symbol */ u16 hw_len; /* length programmed in hw */ + u8 flags; + bool perf_single_step; /* temporarily uninstalled for a perf single step */ }; -/* Note: Don't change the the first 6 bits below as they are in the same order +/* Note: Don't change the first 6 bits below as they are in the same order * as the dabr and dabrx. */ #define HW_BRK_TYPE_READ 0x01 @@ -34,11 +38,31 @@ struct arch_hw_breakpoint { #define HW_BRK_TYPE_PRIV_ALL (HW_BRK_TYPE_USER | HW_BRK_TYPE_KERNEL | \ HW_BRK_TYPE_HYP) -#define HW_BREAKPOINT_ALIGN 0x7 +#define HW_BRK_FLAG_DISABLED 0x1 + +/* Minimum granularity */ +#ifdef CONFIG_PPC_8xx +#define HW_BREAKPOINT_SIZE 0x4 +#else +#define HW_BREAKPOINT_SIZE 0x8 +#endif +#define HW_BREAKPOINT_SIZE_QUADWORD 0x10 #define DABR_MAX_LEN 8 #define DAWR_MAX_LEN 512 +static inline int nr_wp_slots(void) +{ + return cpu_has_feature(CPU_FTR_DAWR1) ? 2 : 1; +} + +bool wp_check_constraints(struct pt_regs *regs, ppc_inst_t instr, + unsigned long ea, int type, int size, + struct arch_hw_breakpoint *info); + +void wp_get_instr_detail(struct pt_regs *regs, ppc_inst_t *instr, + int *type, int *size, unsigned long *ea); + #ifdef CONFIG_HAVE_HW_BREAKPOINT #include <linux/kdebug.h> #include <asm/reg.h> @@ -60,7 +84,6 @@ extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused, unsigned long val, void *data); int arch_install_hw_breakpoint(struct perf_event *bp); void arch_uninstall_hw_breakpoint(struct perf_event *bp); -void arch_unregister_hw_breakpoint(struct perf_event *bp); void hw_breakpoint_pmu_read(struct perf_event *bp); extern void flush_ptrace_hw_breakpoint(struct task_struct *tsk); @@ -69,14 +92,14 @@ extern void ptrace_triggered(struct perf_event *bp, struct perf_sample_data *data, struct pt_regs *regs); static inline void hw_breakpoint_disable(void) { - struct arch_hw_breakpoint brk; - - brk.address = 0; - brk.type = 0; - brk.len = 0; - brk.hw_len = 0; - if (ppc_breakpoint_available()) - __set_breakpoint(&brk); + int i; + struct arch_hw_breakpoint null_brk = {0}; + + if (!ppc_breakpoint_available()) + return; + + for (i = 0; i < nr_wp_slots(); i++) + __set_breakpoint(i, &null_brk); } extern void thread_change_pc(struct task_struct *tsk, struct pt_regs *regs); int hw_breakpoint_handler(struct die_args *args); @@ -95,10 +118,10 @@ static inline bool dawr_enabled(void) { return dawr_force_enable; } -int set_dawr(struct arch_hw_breakpoint *brk); +int set_dawr(int nr, struct arch_hw_breakpoint *brk); #else static inline bool dawr_enabled(void) { return false; } -static inline int set_dawr(struct arch_hw_breakpoint *brk) { return -1; } +static inline int set_dawr(int nr, struct arch_hw_breakpoint *brk) { return -1; } #endif #endif /* __KERNEL__ */ diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h index e3a905e3d573..317659fdeacf 100644 --- a/arch/powerpc/include/asm/hw_irq.h +++ b/arch/powerpc/include/asm/hw_irq.h @@ -18,27 +18,39 @@ * PACA flags in paca->irq_happened. * * This bits are set when interrupts occur while soft-disabled - * and allow a proper replay. Additionally, PACA_IRQ_HARD_DIS - * is set whenever we manually hard disable. + * and allow a proper replay. + * + * The PACA_IRQ_HARD_DIS is set whenever we hard disable. It is almost + * always in synch with the MSR[EE] state, except: + * - A window in interrupt entry, where hardware disables MSR[EE] and that + * must be "reconciled" with the soft mask state. + * - NMI interrupts that hit in awkward places, until they fix the state. + * - When local irqs are being enabled and state is being fixed up. + * - When returning from an interrupt there are some windows where this + * can become out of synch, but gets fixed before the RFI or before + * executing the next user instruction (see arch/powerpc/kernel/interrupt.c). */ #define PACA_IRQ_HARD_DIS 0x01 #define PACA_IRQ_DBELL 0x02 #define PACA_IRQ_EE 0x04 #define PACA_IRQ_DEC 0x08 /* Or FIT */ -#define PACA_IRQ_EE_EDGE 0x10 /* BookE only */ -#define PACA_IRQ_HMI 0x20 -#define PACA_IRQ_PMI 0x40 +#define PACA_IRQ_HMI 0x10 +#define PACA_IRQ_PMI 0x20 +#define PACA_IRQ_REPLAYING 0x40 /* * Some soft-masked interrupts must be hard masked until they are replayed * (e.g., because the soft-masked handler does not clear the exception). + * Interrupt replay itself must remain hard masked too. */ #ifdef CONFIG_PPC_BOOK3S -#define PACA_IRQ_MUST_HARD_MASK (PACA_IRQ_EE|PACA_IRQ_PMI) +#define PACA_IRQ_MUST_HARD_MASK (PACA_IRQ_EE|PACA_IRQ_PMI|PACA_IRQ_REPLAYING) #else -#define PACA_IRQ_MUST_HARD_MASK (PACA_IRQ_EE) +#define PACA_IRQ_MUST_HARD_MASK (PACA_IRQ_EE|PACA_IRQ_REPLAYING) #endif +#endif /* CONFIG_PPC64 */ + /* * flags for paca->irq_soft_mask */ @@ -47,18 +59,56 @@ #define IRQS_PMI_DISABLED 2 #define IRQS_ALL_DISABLED (IRQS_DISABLED | IRQS_PMI_DISABLED) -#endif /* CONFIG_PPC64 */ - #ifndef __ASSEMBLY__ -extern void replay_system_reset(void); -extern void __replay_interrupt(unsigned int vector); +static inline void __hard_irq_enable(void) +{ + if (IS_ENABLED(CONFIG_BOOKE_OR_40x)) + wrtee(MSR_EE); + else if (IS_ENABLED(CONFIG_PPC_8xx)) + wrtspr(SPRN_EIE); + else if (IS_ENABLED(CONFIG_PPC_BOOK3S_64)) + __mtmsrd(MSR_EE | MSR_RI, 1); + else + mtmsr(mfmsr() | MSR_EE); +} -extern void timer_interrupt(struct pt_regs *); -extern void timer_broadcast_interrupt(void); -extern void performance_monitor_exception(struct pt_regs *regs); -extern void WatchdogException(struct pt_regs *regs); -extern void unknown_exception(struct pt_regs *regs); +static inline void __hard_irq_disable(void) +{ + if (IS_ENABLED(CONFIG_BOOKE_OR_40x)) + wrtee(0); + else if (IS_ENABLED(CONFIG_PPC_8xx)) + wrtspr(SPRN_EID); + else if (IS_ENABLED(CONFIG_PPC_BOOK3S_64)) + __mtmsrd(MSR_RI, 1); + else + mtmsr(mfmsr() & ~MSR_EE); +} + +static inline void __hard_EE_RI_disable(void) +{ + if (IS_ENABLED(CONFIG_BOOKE_OR_40x)) + wrtee(0); + else if (IS_ENABLED(CONFIG_PPC_8xx)) + wrtspr(SPRN_NRI); + else if (IS_ENABLED(CONFIG_PPC_BOOK3S_64)) + __mtmsrd(0, 1); + else + mtmsr(mfmsr() & ~(MSR_EE | MSR_RI)); +} + +static inline void __hard_RI_enable(void) +{ + if (IS_ENABLED(CONFIG_BOOKE_OR_40x)) + return; + + if (IS_ENABLED(CONFIG_PPC_8xx)) + wrtspr(SPRN_EID); + else if (IS_ENABLED(CONFIG_PPC_BOOK3S_64)) + __mtmsrd(MSR_RI, 1); + else + mtmsr(mfmsr() | MSR_RI); +} #ifdef CONFIG_PPC64 #include <asm/paca.h> @@ -82,7 +132,6 @@ static inline notrace unsigned long irq_soft_mask_return(void) */ static inline notrace void irq_soft_mask_set(unsigned long mask) { -#ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG /* * The irq mask must always include the STD bit if any are set. * @@ -97,8 +146,8 @@ static inline notrace void irq_soft_mask_set(unsigned long mask) * unmasks to be replayed, among other things. For now, take * the simple approach. */ - WARN_ON(mask && !(mask & IRQS_DISABLED)); -#endif + if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) + WARN_ON(mask && !(mask & IRQS_DISABLED)); asm volatile( "stb %0,%1(13)" @@ -110,36 +159,27 @@ static inline notrace void irq_soft_mask_set(unsigned long mask) static inline notrace unsigned long irq_soft_mask_set_return(unsigned long mask) { - unsigned long flags; + unsigned long flags = irq_soft_mask_return(); -#ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG - WARN_ON(mask && !(mask & IRQS_DISABLED)); -#endif - - asm volatile( - "lbz %0,%1(13); stb %2,%1(13)" - : "=&r" (flags) - : "i" (offsetof(struct paca_struct, irq_soft_mask)), - "r" (mask) - : "memory"); + irq_soft_mask_set(mask); return flags; } static inline notrace unsigned long irq_soft_mask_or_return(unsigned long mask) { - unsigned long flags, tmp; + unsigned long flags = irq_soft_mask_return(); - asm volatile( - "lbz %0,%2(13); or %1,%0,%3; stb %1,%2(13)" - : "=&r" (flags), "=r" (tmp) - : "i" (offsetof(struct paca_struct, irq_soft_mask)), - "r" (mask) - : "memory"); + irq_soft_mask_set(flags | mask); -#ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG - WARN_ON((mask | flags) && !((mask | flags) & IRQS_DISABLED)); -#endif + return flags; +} + +static inline notrace unsigned long irq_soft_mask_andc_return(unsigned long mask) +{ + unsigned long flags = irq_soft_mask_return(); + + irq_soft_mask_set(flags & ~mask); return flags; } @@ -163,7 +203,7 @@ static inline void arch_local_irq_enable(void) static inline unsigned long arch_local_irq_save(void) { - return irq_soft_mask_set_return(IRQS_DISABLED); + return irq_soft_mask_or_return(IRQS_DISABLED); } static inline bool arch_irqs_disabled_flags(unsigned long flags) @@ -176,6 +216,42 @@ static inline bool arch_irqs_disabled(void) return arch_irqs_disabled_flags(arch_local_save_flags()); } +static inline void set_pmi_irq_pending(void) +{ + /* + * Invoked from PMU callback functions to set PMI bit in the paca. + * This has to be called with irq's disabled (via hard_irq_disable()). + */ + if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) + WARN_ON_ONCE(mfmsr() & MSR_EE); + + get_paca()->irq_happened |= PACA_IRQ_PMI; +} + +static inline void clear_pmi_irq_pending(void) +{ + /* + * Invoked from PMU callback functions to clear the pending PMI bit + * in the paca. + */ + if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) + WARN_ON_ONCE(mfmsr() & MSR_EE); + + get_paca()->irq_happened &= ~PACA_IRQ_PMI; +} + +static inline bool pmi_irq_pending(void) +{ + /* + * Invoked from PMU callback functions to check if there is a pending + * PMI bit in the paca. + */ + if (get_paca()->irq_happened & PACA_IRQ_PMI) + return true; + + return false; +} + #ifdef CONFIG_PPC_BOOK3S /* * To support disabling and enabling of irq with PMI, set of @@ -200,17 +276,14 @@ static inline bool arch_irqs_disabled(void) #define powerpc_local_irq_pmu_save(flags) \ do { \ raw_local_irq_pmu_save(flags); \ - trace_hardirqs_off(); \ + if (!raw_irqs_disabled_flags(flags)) \ + trace_hardirqs_off(); \ } while(0) #define powerpc_local_irq_pmu_restore(flags) \ do { \ - if (raw_irqs_disabled_flags(flags)) { \ - raw_local_irq_pmu_restore(flags); \ - trace_hardirqs_off(); \ - } else { \ + if (!raw_irqs_disabled_flags(flags)) \ trace_hardirqs_on(); \ - raw_local_irq_pmu_restore(flags); \ - } \ + raw_local_irq_pmu_restore(flags); \ } while(0) #else #define powerpc_local_irq_pmu_save(flags) \ @@ -225,44 +298,99 @@ static inline bool arch_irqs_disabled(void) #endif /* CONFIG_PPC_BOOK3S */ -#ifdef CONFIG_PPC_BOOK3E -#define __hard_irq_enable() wrtee(MSR_EE) -#define __hard_irq_disable() wrtee(0) -#else -#define __hard_irq_enable() __mtmsrd(MSR_EE|MSR_RI, 1) -#define __hard_irq_disable() __mtmsrd(MSR_RI, 1) -#endif - #define hard_irq_disable() do { \ unsigned long flags; \ __hard_irq_disable(); \ flags = irq_soft_mask_set_return(IRQS_ALL_DISABLED); \ local_paca->irq_happened |= PACA_IRQ_HARD_DIS; \ if (!arch_irqs_disabled_flags(flags)) { \ - asm ("stdx %%r1, 0, %1 ;" \ - : "=m" (local_paca->saved_r1) \ - : "b" (&local_paca->saved_r1)); \ + asm volatile("std%X0 %1,%0" : "=m" (local_paca->saved_r1) \ + : "r" (current_stack_pointer)); \ trace_hardirqs_off(); \ } \ } while(0) +static inline bool __lazy_irq_pending(u8 irq_happened) +{ + return !!(irq_happened & ~PACA_IRQ_HARD_DIS); +} + +/* + * Check if a lazy IRQ is pending. Should be called with IRQs hard disabled. + */ static inline bool lazy_irq_pending(void) { - return !!(get_paca()->irq_happened & ~PACA_IRQ_HARD_DIS); + return __lazy_irq_pending(get_paca()->irq_happened); } /* - * This is called by asynchronous interrupts to conditionally - * re-enable hard interrupts after having cleared the source - * of the interrupt. They are kept disabled if there is a different - * soft-masked interrupt pending that requires hard masking. + * Check if a lazy IRQ is pending, with no debugging checks. + * Should be called with IRQs hard disabled. + * For use in RI disabled code or other constrained situations. */ -static inline void may_hard_irq_enable(void) +static inline bool lazy_irq_pending_nocheck(void) { - if (!(get_paca()->irq_happened & PACA_IRQ_MUST_HARD_MASK)) { - get_paca()->irq_happened &= ~PACA_IRQ_HARD_DIS; - __hard_irq_enable(); + return __lazy_irq_pending(local_paca->irq_happened); +} + +bool power_pmu_wants_prompt_pmi(void); + +/* + * This is called by asynchronous interrupts to check whether to + * conditionally re-enable hard interrupts after having cleared + * the source of the interrupt. They are kept disabled if there + * is a different soft-masked interrupt pending that requires hard + * masking. + */ +static inline bool should_hard_irq_enable(struct pt_regs *regs) +{ + if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) { + WARN_ON(irq_soft_mask_return() != IRQS_ALL_DISABLED); + WARN_ON(!(get_paca()->irq_happened & PACA_IRQ_HARD_DIS)); + WARN_ON(mfmsr() & MSR_EE); } + + if (!IS_ENABLED(CONFIG_PERF_EVENTS)) + return false; + /* + * If the PMU is not running, there is not much reason to enable + * MSR[EE] in irq handlers because any interrupts would just be + * soft-masked. + * + * TODO: Add test for 64e + */ + if (IS_ENABLED(CONFIG_PPC_BOOK3S_64)) { + if (!power_pmu_wants_prompt_pmi()) + return false; + /* + * If PMIs are disabled then IRQs should be disabled as well, + * so we shouldn't see this condition, check for it just in + * case because we are about to enable PMIs. + */ + if (WARN_ON_ONCE(regs->softe & IRQS_PMI_DISABLED)) + return false; + } + + if (get_paca()->irq_happened & PACA_IRQ_MUST_HARD_MASK) + return false; + + return true; +} + +/* + * Do the hard enabling, only call this if should_hard_irq_enable is true. + * This allows PMI interrupts to profile irq handlers. + */ +static inline void do_hard_irq_enable(void) +{ + /* + * Asynch interrupts come in with IRQS_ALL_DISABLED, + * PACA_IRQ_HARD_DIS, and MSR[EE]=0. + */ + if (IS_ENABLED(CONFIG_PPC_BOOK3S_64)) + irq_soft_mask_andc_return(IRQS_PMI_DISABLED); + get_paca()->irq_happened &= ~PACA_IRQ_HARD_DIS; + __hard_irq_enable(); } static inline bool arch_irq_disabled_regs(struct pt_regs *regs) @@ -278,8 +406,17 @@ extern void irq_set_pending_from_srr1(unsigned long srr1); extern void force_external_irq_replay(void); +static inline void irq_soft_mask_regs_set_state(struct pt_regs *regs, unsigned long val) +{ + regs->softe = val; +} #else /* CONFIG_PPC64 */ +static inline notrace unsigned long irq_soft_mask_return(void) +{ + return 0; +} + static inline unsigned long arch_local_save_flags(void) { return mfmsr(); @@ -309,22 +446,12 @@ static inline unsigned long arch_local_irq_save(void) static inline void arch_local_irq_disable(void) { - if (IS_ENABLED(CONFIG_BOOKE)) - wrtee(0); - else if (IS_ENABLED(CONFIG_PPC_8xx)) - wrtspr(SPRN_EID); - else - mtmsr(mfmsr() & ~MSR_EE); + __hard_irq_disable(); } static inline void arch_local_irq_enable(void) { - if (IS_ENABLED(CONFIG_BOOKE)) - wrtee(MSR_EE); - else if (IS_ENABLED(CONFIG_PPC_8xx)) - wrtspr(SPRN_EIE); - else - mtmsr(mfmsr() | MSR_EE); + __hard_irq_enable(); } static inline bool arch_irqs_disabled_flags(unsigned long flags) @@ -344,17 +471,50 @@ static inline bool arch_irq_disabled_regs(struct pt_regs *regs) return !(regs->msr & MSR_EE); } -static inline void may_hard_irq_enable(void) { } +static __always_inline bool should_hard_irq_enable(struct pt_regs *regs) +{ + return false; +} + +static inline void do_hard_irq_enable(void) +{ + BUILD_BUG(); +} + +static inline void clear_pmi_irq_pending(void) { } +static inline void set_pmi_irq_pending(void) { } +static inline bool pmi_irq_pending(void) { return false; } +static inline void irq_soft_mask_regs_set_state(struct pt_regs *regs, unsigned long val) +{ +} #endif /* CONFIG_PPC64 */ -#define ARCH_IRQ_INIT_FLAGS IRQ_NOREQUEST +static inline unsigned long mtmsr_isync_irqsafe(unsigned long msr) +{ +#ifdef CONFIG_PPC64 + if (arch_irqs_disabled()) { + /* + * With soft-masking, MSR[EE] can change from 1 to 0 + * asynchronously when irqs are disabled, and we don't want to + * set MSR[EE] back to 1 here if that has happened. A race-free + * way to do this is ensure EE is already 0. Another way it + * could be done is with a RESTART_TABLE handler, but that's + * probably overkill here. + */ + msr &= ~MSR_EE; + mtmsr_isync(msr); + irq_soft_mask_set(IRQS_ALL_DISABLED); + local_paca->irq_happened |= PACA_IRQ_HARD_DIS; + } else +#endif + mtmsr_isync(msr); -/* - * interrupt-retrigger: should we handle this via lost interrupts and IPIs - * or should we not care like we do now ? --BenH. - */ -struct irq_chip; + return msr; +} + + +#define ARCH_IRQ_INIT_FLAGS IRQ_NOREQUEST #endif /* __ASSEMBLY__ */ #endif /* __KERNEL__ */ diff --git a/arch/powerpc/include/asm/hydra.h b/arch/powerpc/include/asm/hydra.h index b3b0f2d020f0..d024447283a0 100644 --- a/arch/powerpc/include/asm/hydra.h +++ b/arch/powerpc/include/asm/hydra.h @@ -10,7 +10,7 @@ * * © Copyright 1995 Apple Computer, Inc. All rights reserved. * - * It's available online from http://www.cpu.lu/~mlan/ftp/MacTech.pdf + * It's available online from https://www.cpu.lu/~mlan/ftp/MacTech.pdf * You can obtain paper copies of this book from computer bookstores or by * writing Morgan Kaufmann Publishers, Inc., 340 Pine Street, Sixth Floor, San * Francisco, CA 94104. Reference ISBN 1-55860-393-X. @@ -94,8 +94,6 @@ extern volatile struct Hydra __iomem *Hydra; #define HYDRA_INT_EXT7 18 /* Power Off Request */ #define HYDRA_INT_SPARE 19 -extern int hydra_init(void); - #endif /* __KERNEL__ */ #endif /* _ASMPPC_HYDRA_H */ diff --git a/arch/powerpc/include/asm/i8259.h b/arch/powerpc/include/asm/i8259.h index d7f08ae49e12..75481d363cd8 100644 --- a/arch/powerpc/include/asm/i8259.h +++ b/arch/powerpc/include/asm/i8259.h @@ -7,7 +7,7 @@ extern void i8259_init(struct device_node *node, unsigned long intack_addr); extern unsigned int i8259_irq(void); -extern struct irq_domain *i8259_get_host(void); +struct irq_domain *__init i8259_get_host(void); #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_I8259_H */ diff --git a/arch/powerpc/include/asm/ibmebus.h b/arch/powerpc/include/asm/ibmebus.h index 088f95b2e14f..6f33253a364a 100644 --- a/arch/powerpc/include/asm/ibmebus.h +++ b/arch/powerpc/include/asm/ibmebus.h @@ -46,6 +46,8 @@ #include <linux/of_device.h> #include <linux/of_platform.h> +struct platform_driver; + extern struct bus_type ibmebus_bus_type; int ibmebus_register_driver(struct platform_driver *drv); diff --git a/arch/powerpc/include/asm/icswx.h b/arch/powerpc/include/asm/icswx.h index 9872f85d356f..f6599ccb3012 100644 --- a/arch/powerpc/include/asm/icswx.h +++ b/arch/powerpc/include/asm/icswx.h @@ -77,6 +77,8 @@ struct coprocessor_completion_block { #define CSB_CC_CHAIN (37) #define CSB_CC_SEQUENCE (38) #define CSB_CC_HW (39) +/* P9 DD2 NX Workbook 3.2 (Table 4-36): Address translation fault */ +#define CSB_CC_FAULT_ADDRESS (250) #define CSB_SIZE (0x10) #define CSB_ALIGN CSB_SIZE @@ -108,6 +110,17 @@ struct data_descriptor_entry { __be64 address; } __packed __aligned(DDE_ALIGN); +/* 4.3.2 NX-stamped Fault CRB */ + +#define NX_STAMP_ALIGN (0x10) + +struct nx_fault_stamp { + __be64 fault_storage_addr; + __be16 reserved; + __u8 flags; + __u8 fault_status; + __be32 pswid; +} __packed __aligned(NX_STAMP_ALIGN); /* Chapter 6.5.2 Coprocessor-Request Block (CRB) */ @@ -135,11 +148,15 @@ struct coprocessor_request_block { struct coprocessor_completion_block ccb; - u8 reserved[48]; + union { + struct nx_fault_stamp nx; + u8 reserved[16]; + } stamp; - struct coprocessor_status_block csb; -} __packed __aligned(CRB_ALIGN); + u8 reserved[32]; + struct coprocessor_status_block csb; +} __aligned(128); /* RFC02167 Initiate Coprocessor Instructions document * Chapter 8.2.1.1.1 RS @@ -170,6 +187,9 @@ static inline int icswx(__be32 ccw, struct coprocessor_request_block *crb) __be64 ccw_reg = ccw; u32 cr; + /* NB: the same structures are used by VAS-NX */ + BUILD_BUG_ON(sizeof(*crb) != 128); + __asm__ __volatile__( PPC_ICSWX(%1,0,%2) "\n" "mfcr %0\n" diff --git a/arch/powerpc/include/asm/ide.h b/arch/powerpc/include/asm/ide.h deleted file mode 100644 index ce87a4441ca3..000000000000 --- a/arch/powerpc/include/asm/ide.h +++ /dev/null @@ -1,18 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Copyright (C) 1994-1996 Linus Torvalds & authors - * - * This file contains the powerpc architecture specific IDE code. - */ -#ifndef _ASM_POWERPC_IDE_H -#define _ASM_POWERPC_IDE_H - -#include <linux/compiler.h> -#include <asm/io.h> - -#define __ide_mm_insw(p, a, c) readsw((void __iomem *)(p), (a), (c)) -#define __ide_mm_insl(p, a, c) readsl((void __iomem *)(p), (a), (c)) -#define __ide_mm_outsw(p, a, c) writesw((void __iomem *)(p), (a), (c)) -#define __ide_mm_outsl(p, a, c) writesl((void __iomem *)(p), (a), (c)) - -#endif /* _ASM_POWERPC_IDE_H */ diff --git a/arch/powerpc/include/asm/idle.h b/arch/powerpc/include/asm/idle.h new file mode 100644 index 000000000000..00f360667391 --- /dev/null +++ b/arch/powerpc/include/asm/idle.h @@ -0,0 +1,93 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _ASM_POWERPC_IDLE_H +#define _ASM_POWERPC_IDLE_H +#include <asm/runlatch.h> +#include <asm/paca.h> + +#ifdef CONFIG_PPC_PSERIES +DECLARE_PER_CPU(u64, idle_spurr_cycles); +DECLARE_PER_CPU(u64, idle_entry_purr_snap); +DECLARE_PER_CPU(u64, idle_entry_spurr_snap); + +static __always_inline void snapshot_purr_idle_entry(void) +{ + *this_cpu_ptr(&idle_entry_purr_snap) = mfspr(SPRN_PURR); +} + +static __always_inline void snapshot_spurr_idle_entry(void) +{ + *this_cpu_ptr(&idle_entry_spurr_snap) = mfspr(SPRN_SPURR); +} + +static __always_inline void update_idle_purr_accounting(void) +{ + u64 wait_cycles; + u64 in_purr = *this_cpu_ptr(&idle_entry_purr_snap); + + wait_cycles = be64_to_cpu(get_lppaca()->wait_state_cycles); + wait_cycles += mfspr(SPRN_PURR) - in_purr; + get_lppaca()->wait_state_cycles = cpu_to_be64(wait_cycles); +} + +static __always_inline void update_idle_spurr_accounting(void) +{ + u64 *idle_spurr_cycles_ptr = this_cpu_ptr(&idle_spurr_cycles); + u64 in_spurr = *this_cpu_ptr(&idle_entry_spurr_snap); + + *idle_spurr_cycles_ptr += mfspr(SPRN_SPURR) - in_spurr; +} + +static __always_inline void pseries_idle_prolog(void) +{ + ppc64_runlatch_off(); + snapshot_purr_idle_entry(); + snapshot_spurr_idle_entry(); + /* + * Indicate to the HV that we are idle. Now would be + * a good time to find other work to dispatch. + */ + get_lppaca()->idle = 1; +} + +static __always_inline void pseries_idle_epilog(void) +{ + update_idle_purr_accounting(); + update_idle_spurr_accounting(); + get_lppaca()->idle = 0; + ppc64_runlatch_on(); +} + +static inline u64 read_this_idle_purr(void) +{ + /* + * If we are reading from an idle context, update the + * idle-purr cycles corresponding to the last idle period. + * Since the idle context is not yet over, take a fresh + * snapshot of the idle-purr. + */ + if (unlikely(get_lppaca()->idle == 1)) { + update_idle_purr_accounting(); + snapshot_purr_idle_entry(); + } + + return be64_to_cpu(get_lppaca()->wait_state_cycles); +} + +static inline u64 read_this_idle_spurr(void) +{ + /* + * If we are reading from an idle context, update the + * idle-spurr cycles corresponding to the last idle period. + * Since the idle context is not yet over, take a fresh + * snapshot of the idle-spurr. + */ + if (get_lppaca()->idle == 1) { + update_idle_spurr_accounting(); + snapshot_spurr_idle_entry(); + } + + return *this_cpu_ptr(&idle_spurr_cycles); +} + +#endif /* CONFIG_PPC_PSERIES */ +#endif diff --git a/arch/powerpc/include/asm/ima.h b/arch/powerpc/include/asm/ima.h deleted file mode 100644 index ead488cf3981..000000000000 --- a/arch/powerpc/include/asm/ima.h +++ /dev/null @@ -1,30 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ASM_POWERPC_IMA_H -#define _ASM_POWERPC_IMA_H - -struct kimage; - -int ima_get_kexec_buffer(void **addr, size_t *size); -int ima_free_kexec_buffer(void); - -#ifdef CONFIG_IMA -void remove_ima_buffer(void *fdt, int chosen_node); -#else -static inline void remove_ima_buffer(void *fdt, int chosen_node) {} -#endif - -#ifdef CONFIG_IMA_KEXEC -int arch_ima_add_kexec_buffer(struct kimage *image, unsigned long load_addr, - size_t size); - -int setup_ima_buffer(const struct kimage *image, void *fdt, int chosen_node); -#else -static inline int setup_ima_buffer(const struct kimage *image, void *fdt, - int chosen_node) -{ - remove_ima_buffer(fdt, chosen_node); - return 0; -} -#endif /* CONFIG_IMA_KEXEC */ - -#endif /* _ASM_POWERPC_IMA_H */ diff --git a/arch/powerpc/include/asm/imc-pmu.h b/arch/powerpc/include/asm/imc-pmu.h index 4da4fcba0684..a656635df386 100644 --- a/arch/powerpc/include/asm/imc-pmu.h +++ b/arch/powerpc/include/asm/imc-pmu.h @@ -74,14 +74,14 @@ struct imc_events { * The following is the data structure to hold trace imc data. */ struct trace_imc_data { - u64 tb1; - u64 ip; - u64 val; - u64 cpmc1; - u64 cpmc2; - u64 cpmc3; - u64 cpmc4; - u64 tb2; + __be64 tb1; + __be64 ip; + __be64 val; + __be64 cpmc1; + __be64 cpmc2; + __be64 cpmc3; + __be64 cpmc4; + __be64 tb2; }; /* Event attribute array index */ @@ -99,6 +99,11 @@ struct trace_imc_data { */ #define IMC_TRACE_RECORD_TB1_MASK 0x3ffffffffffULL +/* + * Bit 0:1 in third DW of IMC trace record + * specifies the MSR[HV PR] values. + */ +#define IMC_TRACE_RECORD_VAL_HVPR(x) ((x) >> 62) /* * Device tree parser code detects IMC pmu support and @@ -132,7 +137,7 @@ struct imc_pmu { * are inited. */ struct imc_pmu_ref { - struct mutex lock; + spinlock_t lock; unsigned int id; int refc; }; diff --git a/arch/powerpc/include/asm/inst.h b/arch/powerpc/include/asm/inst.h new file mode 100644 index 000000000000..684d3f453282 --- /dev/null +++ b/arch/powerpc/include/asm/inst.h @@ -0,0 +1,170 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _ASM_POWERPC_INST_H +#define _ASM_POWERPC_INST_H + +#include <asm/ppc-opcode.h> +#include <asm/reg.h> +#include <asm/disassemble.h> +#include <asm/uaccess.h> + +#define ___get_user_instr(gu_op, dest, ptr) \ +({ \ + long __gui_ret; \ + u32 __user *__gui_ptr = (u32 __user *)ptr; \ + ppc_inst_t __gui_inst; \ + unsigned int __prefix, __suffix; \ + \ + __chk_user_ptr(ptr); \ + __gui_ret = gu_op(__prefix, __gui_ptr); \ + if (__gui_ret == 0) { \ + if (IS_ENABLED(CONFIG_PPC64) && (__prefix >> 26) == OP_PREFIX) { \ + __gui_ret = gu_op(__suffix, __gui_ptr + 1); \ + __gui_inst = ppc_inst_prefix(__prefix, __suffix); \ + } else { \ + __gui_inst = ppc_inst(__prefix); \ + } \ + if (__gui_ret == 0) \ + (dest) = __gui_inst; \ + } \ + __gui_ret; \ +}) + +#define get_user_instr(x, ptr) ___get_user_instr(get_user, x, ptr) + +#define __get_user_instr(x, ptr) ___get_user_instr(__get_user, x, ptr) + +/* + * Instruction data type for POWER + */ + +#if defined(CONFIG_PPC64) || defined(__CHECKER__) +static inline u32 ppc_inst_val(ppc_inst_t x) +{ + return x.val; +} + +#define ppc_inst(x) ((ppc_inst_t){ .val = (x) }) + +#else +static inline u32 ppc_inst_val(ppc_inst_t x) +{ + return x; +} +#define ppc_inst(x) (x) +#endif + +static inline int ppc_inst_primary_opcode(ppc_inst_t x) +{ + return ppc_inst_val(x) >> 26; +} + +#ifdef CONFIG_PPC64 +#define ppc_inst_prefix(x, y) ((ppc_inst_t){ .val = (x), .suffix = (y) }) + +static inline u32 ppc_inst_suffix(ppc_inst_t x) +{ + return x.suffix; +} + +#else +#define ppc_inst_prefix(x, y) ((void)y, ppc_inst(x)) + +static inline u32 ppc_inst_suffix(ppc_inst_t x) +{ + return 0; +} + +#endif /* CONFIG_PPC64 */ + +static inline ppc_inst_t ppc_inst_read(const u32 *ptr) +{ + if (IS_ENABLED(CONFIG_PPC64) && (*ptr >> 26) == OP_PREFIX) + return ppc_inst_prefix(*ptr, *(ptr + 1)); + else + return ppc_inst(*ptr); +} + +static inline bool ppc_inst_prefixed(ppc_inst_t x) +{ + return IS_ENABLED(CONFIG_PPC64) && ppc_inst_primary_opcode(x) == OP_PREFIX; +} + +static inline ppc_inst_t ppc_inst_swab(ppc_inst_t x) +{ + return ppc_inst_prefix(swab32(ppc_inst_val(x)), swab32(ppc_inst_suffix(x))); +} + +static inline bool ppc_inst_equal(ppc_inst_t x, ppc_inst_t y) +{ + if (ppc_inst_val(x) != ppc_inst_val(y)) + return false; + if (!ppc_inst_prefixed(x)) + return true; + return ppc_inst_suffix(x) == ppc_inst_suffix(y); +} + +static inline int ppc_inst_len(ppc_inst_t x) +{ + return ppc_inst_prefixed(x) ? 8 : 4; +} + +/* + * Return the address of the next instruction, if the instruction @value was + * located at @location. + */ +static inline u32 *ppc_inst_next(u32 *location, u32 *value) +{ + ppc_inst_t tmp; + + tmp = ppc_inst_read(value); + + return (void *)location + ppc_inst_len(tmp); +} + +static inline unsigned long ppc_inst_as_ulong(ppc_inst_t x) +{ + if (IS_ENABLED(CONFIG_PPC32)) + return ppc_inst_val(x); + else if (IS_ENABLED(CONFIG_CPU_LITTLE_ENDIAN)) + return (u64)ppc_inst_suffix(x) << 32 | ppc_inst_val(x); + else + return (u64)ppc_inst_val(x) << 32 | ppc_inst_suffix(x); +} + +static inline void ppc_inst_write(u32 *ptr, ppc_inst_t x) +{ + if (!ppc_inst_prefixed(x)) + *ptr = ppc_inst_val(x); + else + *(u64 *)ptr = ppc_inst_as_ulong(x); +} + +static inline int __copy_inst_from_kernel_nofault(ppc_inst_t *inst, u32 *src) +{ + unsigned int val, suffix; + +/* See https://github.com/ClangBuiltLinux/linux/issues/1521 */ +#if defined(CONFIG_CC_IS_CLANG) && CONFIG_CLANG_VERSION < 140000 + val = suffix = 0; +#endif + __get_kernel_nofault(&val, src, u32, Efault); + if (IS_ENABLED(CONFIG_PPC64) && get_op(val) == OP_PREFIX) { + __get_kernel_nofault(&suffix, src + 1, u32, Efault); + *inst = ppc_inst_prefix(val, suffix); + } else { + *inst = ppc_inst(val); + } + return 0; +Efault: + return -EFAULT; +} + +static inline int copy_inst_from_kernel_nofault(ppc_inst_t *inst, u32 *src) +{ + if (unlikely(!is_kernel_addr((unsigned long)src))) + return -ERANGE; + + return __copy_inst_from_kernel_nofault(inst, src); +} + +#endif /* _ASM_POWERPC_INST_H */ diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h new file mode 100644 index 000000000000..a4196ab1d016 --- /dev/null +++ b/arch/powerpc/include/asm/interrupt.h @@ -0,0 +1,670 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _ASM_POWERPC_INTERRUPT_H +#define _ASM_POWERPC_INTERRUPT_H + +/* BookE/4xx */ +#define INTERRUPT_CRITICAL_INPUT 0x100 + +/* BookE */ +#define INTERRUPT_DEBUG 0xd00 +#ifdef CONFIG_BOOKE +#define INTERRUPT_PERFMON 0x260 +#define INTERRUPT_DOORBELL 0x280 +#endif + +/* BookS/4xx/8xx */ +#define INTERRUPT_MACHINE_CHECK 0x200 + +/* BookS/8xx */ +#define INTERRUPT_SYSTEM_RESET 0x100 + +/* BookS */ +#define INTERRUPT_DATA_SEGMENT 0x380 +#define INTERRUPT_INST_SEGMENT 0x480 +#define INTERRUPT_TRACE 0xd00 +#define INTERRUPT_H_DATA_STORAGE 0xe00 +#define INTERRUPT_HMI 0xe60 +#define INTERRUPT_H_FAC_UNAVAIL 0xf80 +#ifdef CONFIG_PPC_BOOK3S +#define INTERRUPT_DOORBELL 0xa00 +#define INTERRUPT_PERFMON 0xf00 +#define INTERRUPT_ALTIVEC_UNAVAIL 0xf20 +#endif + +/* BookE/BookS/4xx/8xx */ +#define INTERRUPT_DATA_STORAGE 0x300 +#define INTERRUPT_INST_STORAGE 0x400 +#define INTERRUPT_EXTERNAL 0x500 +#define INTERRUPT_ALIGNMENT 0x600 +#define INTERRUPT_PROGRAM 0x700 +#define INTERRUPT_SYSCALL 0xc00 +#define INTERRUPT_TRACE 0xd00 + +/* BookE/BookS/44x */ +#define INTERRUPT_FP_UNAVAIL 0x800 + +/* BookE/BookS/44x/8xx */ +#define INTERRUPT_DECREMENTER 0x900 + +#ifndef INTERRUPT_PERFMON +#define INTERRUPT_PERFMON 0x0 +#endif + +/* 8xx */ +#define INTERRUPT_SOFT_EMU_8xx 0x1000 +#define INTERRUPT_INST_TLB_MISS_8xx 0x1100 +#define INTERRUPT_DATA_TLB_MISS_8xx 0x1200 +#define INTERRUPT_INST_TLB_ERROR_8xx 0x1300 +#define INTERRUPT_DATA_TLB_ERROR_8xx 0x1400 +#define INTERRUPT_DATA_BREAKPOINT_8xx 0x1c00 +#define INTERRUPT_INST_BREAKPOINT_8xx 0x1d00 + +/* 603 */ +#define INTERRUPT_INST_TLB_MISS_603 0x1000 +#define INTERRUPT_DATA_LOAD_TLB_MISS_603 0x1100 +#define INTERRUPT_DATA_STORE_TLB_MISS_603 0x1200 + +#ifndef __ASSEMBLY__ + +#include <linux/context_tracking.h> +#include <linux/hardirq.h> +#include <asm/cputime.h> +#include <asm/firmware.h> +#include <asm/ftrace.h> +#include <asm/kprobes.h> +#include <asm/runlatch.h> + +#ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG +/* + * WARN/BUG is handled with a program interrupt so minimise checks here to + * avoid recursion and maximise the chance of getting the first oops handled. + */ +#define INT_SOFT_MASK_BUG_ON(regs, cond) \ +do { \ + if ((user_mode(regs) || (TRAP(regs) != INTERRUPT_PROGRAM))) \ + BUG_ON(cond); \ +} while (0) +#else +#define INT_SOFT_MASK_BUG_ON(regs, cond) +#endif + +#ifdef CONFIG_PPC_BOOK3S_64 +extern char __end_soft_masked[]; +bool search_kernel_soft_mask_table(unsigned long addr); +unsigned long search_kernel_restart_table(unsigned long addr); + +DECLARE_STATIC_KEY_FALSE(interrupt_exit_not_reentrant); + +static inline bool is_implicit_soft_masked(struct pt_regs *regs) +{ + if (regs->msr & MSR_PR) + return false; + + if (regs->nip >= (unsigned long)__end_soft_masked) + return false; + + return search_kernel_soft_mask_table(regs->nip); +} + +static inline void srr_regs_clobbered(void) +{ + local_paca->srr_valid = 0; + local_paca->hsrr_valid = 0; +} +#else +static inline unsigned long search_kernel_restart_table(unsigned long addr) +{ + return 0; +} + +static inline bool is_implicit_soft_masked(struct pt_regs *regs) +{ + return false; +} + +static inline void srr_regs_clobbered(void) +{ +} +#endif + +static inline void nap_adjust_return(struct pt_regs *regs) +{ +#ifdef CONFIG_PPC_970_NAP + if (unlikely(test_thread_local_flags(_TLF_NAPPING))) { + /* Can avoid a test-and-clear because NMIs do not call this */ + clear_thread_local_flags(_TLF_NAPPING); + regs_set_return_ip(regs, (unsigned long)power4_idle_nap_return); + } +#endif +} + +static inline void booke_restore_dbcr0(void) +{ +#ifdef CONFIG_PPC_ADV_DEBUG_REGS + unsigned long dbcr0 = current->thread.debug.dbcr0; + + if (IS_ENABLED(CONFIG_PPC32) && unlikely(dbcr0 & DBCR0_IDM)) { + mtspr(SPRN_DBSR, -1); + mtspr(SPRN_DBCR0, global_dbcr0[smp_processor_id()]); + } +#endif +} + +static inline void interrupt_enter_prepare(struct pt_regs *regs) +{ +#ifdef CONFIG_PPC64 + irq_soft_mask_set(IRQS_ALL_DISABLED); + + /* + * If the interrupt was taken with HARD_DIS clear, then enable MSR[EE]. + * Asynchronous interrupts get here with HARD_DIS set (see below), so + * this enables MSR[EE] for synchronous interrupts. IRQs remain + * soft-masked. The interrupt handler may later call + * interrupt_cond_local_irq_enable() to achieve a regular process + * context. + */ + if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS)) { + INT_SOFT_MASK_BUG_ON(regs, !(regs->msr & MSR_EE)); + __hard_irq_enable(); + } else { + __hard_RI_enable(); + } + /* Enable MSR[RI] early, to support kernel SLB and hash faults */ +#endif + + if (!arch_irq_disabled_regs(regs)) + trace_hardirqs_off(); + + if (user_mode(regs)) { + kuap_lock(); + CT_WARN_ON(ct_state() != CONTEXT_USER); + user_exit_irqoff(); + + account_cpu_user_entry(); + account_stolen_time(); + } else { + kuap_save_and_lock(regs); + /* + * CT_WARN_ON comes here via program_check_exception, + * so avoid recursion. + */ + if (TRAP(regs) != INTERRUPT_PROGRAM) + CT_WARN_ON(ct_state() != CONTEXT_KERNEL && + ct_state() != CONTEXT_IDLE); + INT_SOFT_MASK_BUG_ON(regs, is_implicit_soft_masked(regs)); + INT_SOFT_MASK_BUG_ON(regs, arch_irq_disabled_regs(regs) && + search_kernel_restart_table(regs->nip)); + } + INT_SOFT_MASK_BUG_ON(regs, !arch_irq_disabled_regs(regs) && + !(regs->msr & MSR_EE)); + + booke_restore_dbcr0(); +} + +/* + * Care should be taken to note that interrupt_exit_prepare and + * interrupt_async_exit_prepare do not necessarily return immediately to + * regs context (e.g., if regs is usermode, we don't necessarily return to + * user mode). Other interrupts might be taken between here and return, + * context switch / preemption may occur in the exit path after this, or a + * signal may be delivered, etc. + * + * The real interrupt exit code is platform specific, e.g., + * interrupt_exit_user_prepare / interrupt_exit_kernel_prepare for 64s. + * + * However interrupt_nmi_exit_prepare does return directly to regs, because + * NMIs do not do "exit work" or replay soft-masked interrupts. + */ +static inline void interrupt_exit_prepare(struct pt_regs *regs) +{ +} + +static inline void interrupt_async_enter_prepare(struct pt_regs *regs) +{ +#ifdef CONFIG_PPC64 + /* Ensure interrupt_enter_prepare does not enable MSR[EE] */ + local_paca->irq_happened |= PACA_IRQ_HARD_DIS; +#endif + interrupt_enter_prepare(regs); +#ifdef CONFIG_PPC_BOOK3S_64 + /* + * RI=1 is set by interrupt_enter_prepare, so this thread flags access + * has to come afterward (it can cause SLB faults). + */ + if (cpu_has_feature(CPU_FTR_CTRL) && + !test_thread_local_flags(_TLF_RUNLATCH)) + __ppc64_runlatch_on(); +#endif + irq_enter(); +} + +static inline void interrupt_async_exit_prepare(struct pt_regs *regs) +{ + /* + * Adjust at exit so the main handler sees the true NIA. This must + * come before irq_exit() because irq_exit can enable interrupts, and + * if another interrupt is taken before nap_adjust_return has run + * here, then that interrupt would return directly to idle nap return. + */ + nap_adjust_return(regs); + + irq_exit(); + interrupt_exit_prepare(regs); +} + +struct interrupt_nmi_state { +#ifdef CONFIG_PPC64 + u8 irq_soft_mask; + u8 irq_happened; + u8 ftrace_enabled; + u64 softe; +#endif +}; + +static inline bool nmi_disables_ftrace(struct pt_regs *regs) +{ + /* Allow DEC and PMI to be traced when they are soft-NMI */ + if (IS_ENABLED(CONFIG_PPC_BOOK3S_64)) { + if (TRAP(regs) == INTERRUPT_DECREMENTER) + return false; + if (TRAP(regs) == INTERRUPT_PERFMON) + return false; + } + if (IS_ENABLED(CONFIG_PPC_BOOK3E_64)) { + if (TRAP(regs) == INTERRUPT_PERFMON) + return false; + } + + return true; +} + +static inline void interrupt_nmi_enter_prepare(struct pt_regs *regs, struct interrupt_nmi_state *state) +{ +#ifdef CONFIG_PPC64 + state->irq_soft_mask = local_paca->irq_soft_mask; + state->irq_happened = local_paca->irq_happened; + state->softe = regs->softe; + + /* + * Set IRQS_ALL_DISABLED unconditionally so irqs_disabled() does + * the right thing, and set IRQ_HARD_DIS. We do not want to reconcile + * because that goes through irq tracing which we don't want in NMI. + */ + local_paca->irq_soft_mask = IRQS_ALL_DISABLED; + local_paca->irq_happened |= PACA_IRQ_HARD_DIS; + + if (!(regs->msr & MSR_EE) || is_implicit_soft_masked(regs)) { + /* + * Adjust regs->softe to be soft-masked if it had not been + * reconcied (e.g., interrupt entry with MSR[EE]=0 but softe + * not yet set disabled), or if it was in an implicit soft + * masked state. This makes arch_irq_disabled_regs(regs) + * behave as expected. + */ + regs->softe = IRQS_ALL_DISABLED; + } + + __hard_RI_enable(); + + /* Don't do any per-CPU operations until interrupt state is fixed */ + + if (nmi_disables_ftrace(regs)) { + state->ftrace_enabled = this_cpu_get_ftrace_enabled(); + this_cpu_set_ftrace_enabled(0); + } +#endif + + /* If data relocations are enabled, it's safe to use nmi_enter() */ + if (mfmsr() & MSR_DR) { + nmi_enter(); + return; + } + + /* + * But do not use nmi_enter() for pseries hash guest taking a real-mode + * NMI because not everything it touches is within the RMA limit. + */ + if (IS_ENABLED(CONFIG_PPC_BOOK3S_64) && + firmware_has_feature(FW_FEATURE_LPAR) && + !radix_enabled()) + return; + + /* + * Likewise, don't use it if we have some form of instrumentation (like + * KASAN shadow) that is not safe to access in real mode (even on radix) + */ + if (IS_ENABLED(CONFIG_KASAN)) + return; + + /* Otherwise, it should be safe to call it */ + nmi_enter(); +} + +static inline void interrupt_nmi_exit_prepare(struct pt_regs *regs, struct interrupt_nmi_state *state) +{ + if (mfmsr() & MSR_DR) { + // nmi_exit if relocations are on + nmi_exit(); + } else if (IS_ENABLED(CONFIG_PPC_BOOK3S_64) && + firmware_has_feature(FW_FEATURE_LPAR) && + !radix_enabled()) { + // no nmi_exit for a pseries hash guest taking a real mode exception + } else if (IS_ENABLED(CONFIG_KASAN)) { + // no nmi_exit for KASAN in real mode + } else { + nmi_exit(); + } + + /* + * nmi does not call nap_adjust_return because nmi should not create + * new work to do (must use irq_work for that). + */ + +#ifdef CONFIG_PPC64 +#ifdef CONFIG_PPC_BOOK3S + if (arch_irq_disabled_regs(regs)) { + unsigned long rst = search_kernel_restart_table(regs->nip); + if (rst) + regs_set_return_ip(regs, rst); + } +#endif + + if (nmi_disables_ftrace(regs)) + this_cpu_set_ftrace_enabled(state->ftrace_enabled); + + /* Check we didn't change the pending interrupt mask. */ + WARN_ON_ONCE((state->irq_happened | PACA_IRQ_HARD_DIS) != local_paca->irq_happened); + regs->softe = state->softe; + local_paca->irq_happened = state->irq_happened; + local_paca->irq_soft_mask = state->irq_soft_mask; +#endif +} + +/* + * Don't use noinstr here like x86, but rather add NOKPROBE_SYMBOL to each + * function definition. The reason for this is the noinstr section is placed + * after the main text section, i.e., very far away from the interrupt entry + * asm. That creates problems with fitting linker stubs when building large + * kernels. + */ +#define interrupt_handler __visible noinline notrace __no_kcsan __no_sanitize_address + +/** + * DECLARE_INTERRUPT_HANDLER_RAW - Declare raw interrupt handler function + * @func: Function name of the entry point + * @returns: Returns a value back to asm caller + */ +#define DECLARE_INTERRUPT_HANDLER_RAW(func) \ + __visible long func(struct pt_regs *regs) + +/** + * DEFINE_INTERRUPT_HANDLER_RAW - Define raw interrupt handler function + * @func: Function name of the entry point + * @returns: Returns a value back to asm caller + * + * @func is called from ASM entry code. + * + * This is a plain function which does no tracing, reconciling, etc. + * The macro is written so it acts as function definition. Append the + * body with a pair of curly brackets. + * + * raw interrupt handlers must not enable or disable interrupts, or + * schedule, tracing and instrumentation (ftrace, lockdep, etc) would + * not be advisable either, although may be possible in a pinch, the + * trace will look odd at least. + * + * A raw handler may call one of the other interrupt handler functions + * to be converted into that interrupt context without these restrictions. + * + * On PPC64, _RAW handlers may return with fast_interrupt_return. + * + * Specific handlers may have additional restrictions. + */ +#define DEFINE_INTERRUPT_HANDLER_RAW(func) \ +static __always_inline __no_sanitize_address __no_kcsan long \ +____##func(struct pt_regs *regs); \ + \ +interrupt_handler long func(struct pt_regs *regs) \ +{ \ + long ret; \ + \ + __hard_RI_enable(); \ + \ + ret = ____##func (regs); \ + \ + return ret; \ +} \ +NOKPROBE_SYMBOL(func); \ + \ +static __always_inline __no_sanitize_address __no_kcsan long \ +____##func(struct pt_regs *regs) + +/** + * DECLARE_INTERRUPT_HANDLER - Declare synchronous interrupt handler function + * @func: Function name of the entry point + */ +#define DECLARE_INTERRUPT_HANDLER(func) \ + __visible void func(struct pt_regs *regs) + +/** + * DEFINE_INTERRUPT_HANDLER - Define synchronous interrupt handler function + * @func: Function name of the entry point + * + * @func is called from ASM entry code. + * + * The macro is written so it acts as function definition. Append the + * body with a pair of curly brackets. + */ +#define DEFINE_INTERRUPT_HANDLER(func) \ +static __always_inline void ____##func(struct pt_regs *regs); \ + \ +interrupt_handler void func(struct pt_regs *regs) \ +{ \ + interrupt_enter_prepare(regs); \ + \ + ____##func (regs); \ + \ + interrupt_exit_prepare(regs); \ +} \ +NOKPROBE_SYMBOL(func); \ + \ +static __always_inline void ____##func(struct pt_regs *regs) + +/** + * DECLARE_INTERRUPT_HANDLER_RET - Declare synchronous interrupt handler function + * @func: Function name of the entry point + * @returns: Returns a value back to asm caller + */ +#define DECLARE_INTERRUPT_HANDLER_RET(func) \ + __visible long func(struct pt_regs *regs) + +/** + * DEFINE_INTERRUPT_HANDLER_RET - Define synchronous interrupt handler function + * @func: Function name of the entry point + * @returns: Returns a value back to asm caller + * + * @func is called from ASM entry code. + * + * The macro is written so it acts as function definition. Append the + * body with a pair of curly brackets. + */ +#define DEFINE_INTERRUPT_HANDLER_RET(func) \ +static __always_inline long ____##func(struct pt_regs *regs); \ + \ +interrupt_handler long func(struct pt_regs *regs) \ +{ \ + long ret; \ + \ + interrupt_enter_prepare(regs); \ + \ + ret = ____##func (regs); \ + \ + interrupt_exit_prepare(regs); \ + \ + return ret; \ +} \ +NOKPROBE_SYMBOL(func); \ + \ +static __always_inline long ____##func(struct pt_regs *regs) + +/** + * DECLARE_INTERRUPT_HANDLER_ASYNC - Declare asynchronous interrupt handler function + * @func: Function name of the entry point + */ +#define DECLARE_INTERRUPT_HANDLER_ASYNC(func) \ + __visible void func(struct pt_regs *regs) + +/** + * DEFINE_INTERRUPT_HANDLER_ASYNC - Define asynchronous interrupt handler function + * @func: Function name of the entry point + * + * @func is called from ASM entry code. + * + * The macro is written so it acts as function definition. Append the + * body with a pair of curly brackets. + */ +#define DEFINE_INTERRUPT_HANDLER_ASYNC(func) \ +static __always_inline void ____##func(struct pt_regs *regs); \ + \ +interrupt_handler void func(struct pt_regs *regs) \ +{ \ + interrupt_async_enter_prepare(regs); \ + \ + ____##func (regs); \ + \ + interrupt_async_exit_prepare(regs); \ +} \ +NOKPROBE_SYMBOL(func); \ + \ +static __always_inline void ____##func(struct pt_regs *regs) + +/** + * DECLARE_INTERRUPT_HANDLER_NMI - Declare NMI interrupt handler function + * @func: Function name of the entry point + * @returns: Returns a value back to asm caller + */ +#define DECLARE_INTERRUPT_HANDLER_NMI(func) \ + __visible long func(struct pt_regs *regs) + +/** + * DEFINE_INTERRUPT_HANDLER_NMI - Define NMI interrupt handler function + * @func: Function name of the entry point + * @returns: Returns a value back to asm caller + * + * @func is called from ASM entry code. + * + * The macro is written so it acts as function definition. Append the + * body with a pair of curly brackets. + */ +#define DEFINE_INTERRUPT_HANDLER_NMI(func) \ +static __always_inline __no_sanitize_address __no_kcsan long \ +____##func(struct pt_regs *regs); \ + \ +interrupt_handler long func(struct pt_regs *regs) \ +{ \ + struct interrupt_nmi_state state; \ + long ret; \ + \ + interrupt_nmi_enter_prepare(regs, &state); \ + \ + ret = ____##func (regs); \ + \ + interrupt_nmi_exit_prepare(regs, &state); \ + \ + return ret; \ +} \ +NOKPROBE_SYMBOL(func); \ + \ +static __always_inline __no_sanitize_address __no_kcsan long \ +____##func(struct pt_regs *regs) + + +/* Interrupt handlers */ +/* kernel/traps.c */ +DECLARE_INTERRUPT_HANDLER_NMI(system_reset_exception); +#ifdef CONFIG_PPC_BOOK3S_64 +DECLARE_INTERRUPT_HANDLER_RAW(machine_check_early_boot); +DECLARE_INTERRUPT_HANDLER_ASYNC(machine_check_exception_async); +#endif +DECLARE_INTERRUPT_HANDLER_NMI(machine_check_exception); +DECLARE_INTERRUPT_HANDLER(SMIException); +DECLARE_INTERRUPT_HANDLER(handle_hmi_exception); +DECLARE_INTERRUPT_HANDLER(unknown_exception); +DECLARE_INTERRUPT_HANDLER_ASYNC(unknown_async_exception); +DECLARE_INTERRUPT_HANDLER_NMI(unknown_nmi_exception); +DECLARE_INTERRUPT_HANDLER(instruction_breakpoint_exception); +DECLARE_INTERRUPT_HANDLER(RunModeException); +DECLARE_INTERRUPT_HANDLER(single_step_exception); +DECLARE_INTERRUPT_HANDLER(program_check_exception); +DECLARE_INTERRUPT_HANDLER(emulation_assist_interrupt); +DECLARE_INTERRUPT_HANDLER(alignment_exception); +DECLARE_INTERRUPT_HANDLER(StackOverflow); +DECLARE_INTERRUPT_HANDLER(stack_overflow_exception); +DECLARE_INTERRUPT_HANDLER(kernel_fp_unavailable_exception); +DECLARE_INTERRUPT_HANDLER(altivec_unavailable_exception); +DECLARE_INTERRUPT_HANDLER(vsx_unavailable_exception); +DECLARE_INTERRUPT_HANDLER(facility_unavailable_exception); +DECLARE_INTERRUPT_HANDLER(fp_unavailable_tm); +DECLARE_INTERRUPT_HANDLER(altivec_unavailable_tm); +DECLARE_INTERRUPT_HANDLER(vsx_unavailable_tm); +DECLARE_INTERRUPT_HANDLER_NMI(performance_monitor_exception_nmi); +DECLARE_INTERRUPT_HANDLER_ASYNC(performance_monitor_exception_async); +DECLARE_INTERRUPT_HANDLER_RAW(performance_monitor_exception); +DECLARE_INTERRUPT_HANDLER(DebugException); +DECLARE_INTERRUPT_HANDLER(altivec_assist_exception); +DECLARE_INTERRUPT_HANDLER(CacheLockingException); +DECLARE_INTERRUPT_HANDLER(SPEFloatingPointException); +DECLARE_INTERRUPT_HANDLER(SPEFloatingPointRoundException); +DECLARE_INTERRUPT_HANDLER_NMI(WatchdogException); +DECLARE_INTERRUPT_HANDLER(kernel_bad_stack); + +/* slb.c */ +DECLARE_INTERRUPT_HANDLER_RAW(do_slb_fault); +DECLARE_INTERRUPT_HANDLER(do_bad_segment_interrupt); + +/* hash_utils.c */ +DECLARE_INTERRUPT_HANDLER(do_hash_fault); + +/* fault.c */ +DECLARE_INTERRUPT_HANDLER(do_page_fault); +DECLARE_INTERRUPT_HANDLER(do_bad_page_fault_segv); + +/* process.c */ +DECLARE_INTERRUPT_HANDLER(do_break); + +/* time.c */ +DECLARE_INTERRUPT_HANDLER_ASYNC(timer_interrupt); + +/* mce.c */ +DECLARE_INTERRUPT_HANDLER_NMI(machine_check_early); +DECLARE_INTERRUPT_HANDLER_NMI(hmi_exception_realmode); + +DECLARE_INTERRUPT_HANDLER_ASYNC(TAUException); + +/* irq.c */ +DECLARE_INTERRUPT_HANDLER_ASYNC(do_IRQ); + +void __noreturn unrecoverable_exception(struct pt_regs *regs); + +void replay_system_reset(void); +void replay_soft_interrupts(void); + +static inline void interrupt_cond_local_irq_enable(struct pt_regs *regs) +{ + if (!arch_irq_disabled_regs(regs)) + local_irq_enable(); +} + +long system_call_exception(struct pt_regs *regs, unsigned long r0); +notrace unsigned long syscall_exit_prepare(unsigned long r3, struct pt_regs *regs, long scv); +notrace unsigned long interrupt_exit_user_prepare(struct pt_regs *regs); +notrace unsigned long interrupt_exit_kernel_prepare(struct pt_regs *regs); +#ifdef CONFIG_PPC64 +unsigned long syscall_exit_restart(unsigned long r3, struct pt_regs *regs); +unsigned long interrupt_exit_user_restart(struct pt_regs *regs); +unsigned long interrupt_exit_kernel_restart(struct pt_regs *regs); +#endif + +#endif /* __ASSEMBLY__ */ + +#endif /* _ASM_POWERPC_INTERRUPT_H */ diff --git a/arch/powerpc/include/asm/io.h b/arch/powerpc/include/asm/io.h index a63ec938636d..08c550ed49be 100644 --- a/arch/powerpc/include/asm/io.h +++ b/arch/powerpc/include/asm/io.h @@ -3,11 +3,6 @@ #define _ASM_POWERPC_IO_H #ifdef __KERNEL__ -#define ARCH_HAS_IOREMAP_WC -#ifdef CONFIG_PPC32 -#define ARCH_HAS_IOREMAP_WT -#endif - /* */ @@ -33,14 +28,10 @@ extern struct pci_dev *isa_bridge_pcidev; #include <asm/delay.h> #include <asm/mmiowb.h> #include <asm/mmu.h> -#include <asm/ppc_asm.h> -#include <asm/pgtable.h> #define SIO_CONFIG_RA 0x398 #define SIO_CONFIG_RD 0x399 -#define SLOW_DOWN_IO - /* 32 bits uses slightly different variables for the various IO * bases. Most of this file only uses _IO_BASE though which we * define properly based on the platform @@ -101,6 +92,42 @@ extern bool isa_io_special; * */ +/* -mprefixed can generate offsets beyond range, fall back hack */ +#ifdef CONFIG_PPC_KERNEL_PREFIXED +#define DEF_MMIO_IN_X(name, size, insn) \ +static inline u##size name(const volatile u##size __iomem *addr) \ +{ \ + u##size ret; \ + __asm__ __volatile__("sync;"#insn" %0,0,%1;twi 0,%0,0;isync" \ + : "=r" (ret) : "r" (addr) : "memory"); \ + return ret; \ +} + +#define DEF_MMIO_OUT_X(name, size, insn) \ +static inline void name(volatile u##size __iomem *addr, u##size val) \ +{ \ + __asm__ __volatile__("sync;"#insn" %1,0,%0" \ + : : "r" (addr), "r" (val) : "memory"); \ + mmiowb_set_pending(); \ +} + +#define DEF_MMIO_IN_D(name, size, insn) \ +static inline u##size name(const volatile u##size __iomem *addr) \ +{ \ + u##size ret; \ + __asm__ __volatile__("sync;"#insn" %0,0(%1);twi 0,%0,0;isync"\ + : "=r" (ret) : "b" (addr) : "memory"); \ + return ret; \ +} + +#define DEF_MMIO_OUT_D(name, size, insn) \ +static inline void name(volatile u##size __iomem *addr, u##size val) \ +{ \ + __asm__ __volatile__("sync;"#insn" %1,0(%0)" \ + : : "b" (addr), "r" (val) : "memory"); \ + mmiowb_set_pending(); \ +} +#else #define DEF_MMIO_IN_X(name, size, insn) \ static inline u##size name(const volatile u##size __iomem *addr) \ { \ @@ -123,7 +150,7 @@ static inline u##size name(const volatile u##size __iomem *addr) \ { \ u##size ret; \ __asm__ __volatile__("sync;"#insn"%U1%X1 %0,%1;twi 0,%0,0;isync"\ - : "=r" (ret) : "m" (*addr) : "memory"); \ + : "=r" (ret) : "m<>" (*addr) : "memory"); \ return ret; \ } @@ -131,9 +158,10 @@ static inline u##size name(const volatile u##size __iomem *addr) \ static inline void name(volatile u##size __iomem *addr, u##size val) \ { \ __asm__ __volatile__("sync;"#insn"%U0%X0 %1,%0" \ - : "=m" (*addr) : "r" (val) : "memory"); \ + : "=m<>" (*addr) : "r" (val) : "memory"); \ mmiowb_set_pending(); \ } +#endif DEF_MMIO_IN_D(in_8, 8, lbz); DEF_MMIO_OUT_D(out_8, 8, stb); @@ -303,41 +331,56 @@ static inline unsigned char __raw_readb(const volatile void __iomem *addr) { return *(volatile unsigned char __force *)PCI_FIX_ADDR(addr); } +#define __raw_readb __raw_readb + static inline unsigned short __raw_readw(const volatile void __iomem *addr) { return *(volatile unsigned short __force *)PCI_FIX_ADDR(addr); } +#define __raw_readw __raw_readw + static inline unsigned int __raw_readl(const volatile void __iomem *addr) { return *(volatile unsigned int __force *)PCI_FIX_ADDR(addr); } +#define __raw_readl __raw_readl + static inline void __raw_writeb(unsigned char v, volatile void __iomem *addr) { *(volatile unsigned char __force *)PCI_FIX_ADDR(addr) = v; } +#define __raw_writeb __raw_writeb + static inline void __raw_writew(unsigned short v, volatile void __iomem *addr) { *(volatile unsigned short __force *)PCI_FIX_ADDR(addr) = v; } +#define __raw_writew __raw_writew + static inline void __raw_writel(unsigned int v, volatile void __iomem *addr) { *(volatile unsigned int __force *)PCI_FIX_ADDR(addr) = v; } +#define __raw_writel __raw_writel #ifdef __powerpc64__ static inline unsigned long __raw_readq(const volatile void __iomem *addr) { return *(volatile unsigned long __force *)PCI_FIX_ADDR(addr); } +#define __raw_readq __raw_readq + static inline void __raw_writeq(unsigned long v, volatile void __iomem *addr) { *(volatile unsigned long __force *)PCI_FIX_ADDR(addr) = v; } +#define __raw_writeq __raw_writeq static inline void __raw_writeq_be(unsigned long v, volatile void __iomem *addr) { __raw_writeq((__force unsigned long)cpu_to_be64(v), addr); } +#define __raw_writeq_be __raw_writeq_be /* * Real mode versions of the above. Those instructions are only supposed @@ -345,25 +388,37 @@ static inline void __raw_writeq_be(unsigned long v, volatile void __iomem *addr) */ static inline void __raw_rm_writeb(u8 val, volatile void __iomem *paddr) { - __asm__ __volatile__("stbcix %0,0,%1" + __asm__ __volatile__(".machine push; \ + .machine power6; \ + stbcix %0,0,%1; \ + .machine pop;" : : "r" (val), "r" (paddr) : "memory"); } static inline void __raw_rm_writew(u16 val, volatile void __iomem *paddr) { - __asm__ __volatile__("sthcix %0,0,%1" + __asm__ __volatile__(".machine push; \ + .machine power6; \ + sthcix %0,0,%1; \ + .machine pop;" : : "r" (val), "r" (paddr) : "memory"); } static inline void __raw_rm_writel(u32 val, volatile void __iomem *paddr) { - __asm__ __volatile__("stwcix %0,0,%1" + __asm__ __volatile__(".machine push; \ + .machine power6; \ + stwcix %0,0,%1; \ + .machine pop;" : : "r" (val), "r" (paddr) : "memory"); } static inline void __raw_rm_writeq(u64 val, volatile void __iomem *paddr) { - __asm__ __volatile__("stdcix %0,0,%1" + __asm__ __volatile__(".machine push; \ + .machine power6; \ + stdcix %0,0,%1; \ + .machine pop;" : : "r" (val), "r" (paddr) : "memory"); } @@ -375,7 +430,10 @@ static inline void __raw_rm_writeq_be(u64 val, volatile void __iomem *paddr) static inline u8 __raw_rm_readb(volatile void __iomem *paddr) { u8 ret; - __asm__ __volatile__("lbzcix %0,0, %1" + __asm__ __volatile__(".machine push; \ + .machine power6; \ + lbzcix %0,0, %1; \ + .machine pop;" : "=r" (ret) : "r" (paddr) : "memory"); return ret; } @@ -383,7 +441,10 @@ static inline u8 __raw_rm_readb(volatile void __iomem *paddr) static inline u16 __raw_rm_readw(volatile void __iomem *paddr) { u16 ret; - __asm__ __volatile__("lhzcix %0,0, %1" + __asm__ __volatile__(".machine push; \ + .machine power6; \ + lhzcix %0,0, %1; \ + .machine pop;" : "=r" (ret) : "r" (paddr) : "memory"); return ret; } @@ -391,7 +452,10 @@ static inline u16 __raw_rm_readw(volatile void __iomem *paddr) static inline u32 __raw_rm_readl(volatile void __iomem *paddr) { u32 ret; - __asm__ __volatile__("lwzcix %0,0, %1" + __asm__ __volatile__(".machine push; \ + .machine power6; \ + lwzcix %0,0, %1; \ + .machine pop;" : "=r" (ret) : "r" (paddr) : "memory"); return ret; } @@ -399,7 +463,10 @@ static inline u32 __raw_rm_readl(volatile void __iomem *paddr) static inline u64 __raw_rm_readq(volatile void __iomem *paddr) { u64 ret; - __asm__ __volatile__("ldcix %0,0, %1" + __asm__ __volatile__(".machine push; \ + .machine power6; \ + ldcix %0,0, %1; \ + .machine pop;" : "=r" (ret) : "r" (paddr) : "memory"); return ret; } @@ -610,21 +677,37 @@ static inline void name at \ /* Some drivers check for the presence of readq & writeq with * a #ifdef, so we make them happy here. */ +#define readb readb +#define readw readw +#define readl readl +#define writeb writeb +#define writew writew +#define writel writel +#define readsb readsb +#define readsw readsw +#define readsl readsl +#define writesb writesb +#define writesw writesw +#define writesl writesl +#define inb inb +#define inw inw +#define inl inl +#define outb outb +#define outw outw +#define outl outl +#define insb insb +#define insw insw +#define insl insl +#define outsb outsb +#define outsw outsw +#define outsl outsl #ifdef __powerpc64__ #define readq readq #define writeq writeq #endif - -/* - * Convert a physical pointer to a virtual kernel pointer for /dev/mem - * access - */ -#define xlate_dev_mem_ptr(p) __va(p) - -/* - * Convert a virtual cached pointer to an uncached pointer - */ -#define xlate_dev_kmem_ptr(p) p +#define memset_io memset_io +#define memcpy_fromio memcpy_fromio +#define memcpy_toio memcpy_toio /* * We don't do relaxed operations yet, at least not with this semantic @@ -638,7 +721,104 @@ static inline void name at \ #define writel_relaxed(v, addr) writel(v, addr) #define writeq_relaxed(v, addr) writeq(v, addr) -#include <asm-generic/iomap.h> +#ifndef CONFIG_GENERIC_IOMAP +/* + * Here comes the implementation of the IOMAP interfaces. + */ +static inline unsigned int ioread16be(const void __iomem *addr) +{ + return readw_be(addr); +} +#define ioread16be ioread16be + +static inline unsigned int ioread32be(const void __iomem *addr) +{ + return readl_be(addr); +} +#define ioread32be ioread32be + +#ifdef __powerpc64__ +static inline u64 ioread64_lo_hi(const void __iomem *addr) +{ + return readq(addr); +} +#define ioread64_lo_hi ioread64_lo_hi + +static inline u64 ioread64_hi_lo(const void __iomem *addr) +{ + return readq(addr); +} +#define ioread64_hi_lo ioread64_hi_lo + +static inline u64 ioread64be(const void __iomem *addr) +{ + return readq_be(addr); +} +#define ioread64be ioread64be + +static inline u64 ioread64be_lo_hi(const void __iomem *addr) +{ + return readq_be(addr); +} +#define ioread64be_lo_hi ioread64be_lo_hi + +static inline u64 ioread64be_hi_lo(const void __iomem *addr) +{ + return readq_be(addr); +} +#define ioread64be_hi_lo ioread64be_hi_lo +#endif /* __powerpc64__ */ + +static inline void iowrite16be(u16 val, void __iomem *addr) +{ + writew_be(val, addr); +} +#define iowrite16be iowrite16be + +static inline void iowrite32be(u32 val, void __iomem *addr) +{ + writel_be(val, addr); +} +#define iowrite32be iowrite32be + +#ifdef __powerpc64__ +static inline void iowrite64_lo_hi(u64 val, void __iomem *addr) +{ + writeq(val, addr); +} +#define iowrite64_lo_hi iowrite64_lo_hi + +static inline void iowrite64_hi_lo(u64 val, void __iomem *addr) +{ + writeq(val, addr); +} +#define iowrite64_hi_lo iowrite64_hi_lo + +static inline void iowrite64be(u64 val, void __iomem *addr) +{ + writeq_be(val, addr); +} +#define iowrite64be iowrite64be + +static inline void iowrite64be_lo_hi(u64 val, void __iomem *addr) +{ + writeq_be(val, addr); +} +#define iowrite64be_lo_hi iowrite64be_lo_hi + +static inline void iowrite64be_hi_lo(u64 val, void __iomem *addr) +{ + writeq_be(val, addr); +} +#define iowrite64be_hi_lo iowrite64be_hi_lo +#endif /* __powerpc64__ */ + +struct pci_dev; +void pci_iounmap(struct pci_dev *dev, void __iomem *addr); +#define pci_iounmap pci_iounmap +void __iomem *ioport_map(unsigned long port, unsigned int len); +#define ioport_map ioport_map +#endif static inline void iosync(void) { @@ -671,7 +851,6 @@ static inline void iosync(void) #define IO_SPACE_LIMIT ~(0UL) - /** * ioremap - map bus memory into CPU space * @address: bus address of the memory @@ -691,8 +870,6 @@ static inline void iosync(void) * * ioremap_prot allows to specify the page flags as an argument and can * also be hooked by the platform via ppc_md. * - * * ioremap_nocache is identical to ioremap - * * * ioremap_wc enables write combining * * * ioremap_wt enables write through @@ -701,39 +878,35 @@ static inline void iosync(void) * * * iounmap undoes such a mapping and can be hooked * - * * __ioremap_at (and the pending __iounmap_at) are low level functions to - * create hand-made mappings for use only by the PCI code and cannot - * currently be hooked. Must be page aligned. - * * * __ioremap_caller is the same as above but takes an explicit caller * reference rather than using __builtin_return_address(0) * */ extern void __iomem *ioremap(phys_addr_t address, unsigned long size); -extern void __iomem *ioremap_prot(phys_addr_t address, unsigned long size, - unsigned long flags); +#define ioremap ioremap +#define ioremap_prot ioremap_prot extern void __iomem *ioremap_wc(phys_addr_t address, unsigned long size); +#define ioremap_wc ioremap_wc + +#ifdef CONFIG_PPC32 void __iomem *ioremap_wt(phys_addr_t address, unsigned long size); +#define ioremap_wt ioremap_wt +#endif + void __iomem *ioremap_coherent(phys_addr_t address, unsigned long size); -#define ioremap_nocache(addr, size) ioremap((addr), (size)) -#define ioremap_uc(addr, size) ioremap((addr), (size)) #define ioremap_cache(addr, size) \ ioremap_prot((addr), (size), pgprot_val(PAGE_KERNEL)) -extern void iounmap(volatile void __iomem *addr); +#define iounmap iounmap + +void __iomem *ioremap_phb(phys_addr_t paddr, unsigned long size); int early_ioremap_range(unsigned long ea, phys_addr_t pa, unsigned long size, pgprot_t prot); -void __iomem *do_ioremap(phys_addr_t pa, phys_addr_t offset, unsigned long size, - pgprot_t prot, void *caller); extern void __iomem *__ioremap_caller(phys_addr_t, unsigned long size, pgprot_t prot, void *caller); -extern void __iomem * __ioremap_at(phys_addr_t pa, void *ea, - unsigned long size, pgprot_t prot); -extern void __iounmap_at(void *ea, unsigned long size); - /* * When CONFIG_PPC_INDIRECT_PIO is set, we use the generic iomap implementation * which needs some additional definitions here. They basically allow PIO @@ -770,12 +943,13 @@ extern void __iounmap_at(void *ea, unsigned long size); * almost all conceivable cases a device driver should not be using * this function */ -static inline unsigned long virt_to_phys(volatile void * address) +static inline unsigned long virt_to_phys(const volatile void * address) { WARN_ON(IS_ENABLED(CONFIG_DEBUG_VIRTUAL) && !virt_addr_valid(address)); return __pa((unsigned long)address); } +#define virt_to_phys virt_to_phys /** * phys_to_virt - map physical address to virtual @@ -793,6 +967,7 @@ static inline void * phys_to_virt(unsigned long address) { return (void *)__va(address); } +#define phys_to_virt phys_to_virt /* * Change "struct page" to physical address. @@ -820,6 +995,7 @@ static inline unsigned long virt_to_bus(volatile void * address) return 0; return __pa(address) + PCI_DRAM_OFFSET; } +#define virt_to_bus virt_to_bus static inline void * bus_to_virt(unsigned long address) { @@ -827,8 +1003,7 @@ static inline void * bus_to_virt(unsigned long address) return NULL; return __va(address - PCI_DRAM_OFFSET); } - -#define page_to_bus(page) (page_to_phys(page) + PCI_DRAM_OFFSET) +#define bus_to_virt bus_to_virt #endif /* CONFIG_PPC32 */ @@ -865,6 +1040,8 @@ static inline void * bus_to_virt(unsigned long address) #define clrsetbits_8(addr, clear, set) clrsetbits(8, addr, clear, set) +#include <asm-generic/io.h> + #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_IO_H */ diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h index 350101e11ddb..026695943550 100644 --- a/arch/powerpc/include/asm/iommu.h +++ b/arch/powerpc/include/asm/iommu.h @@ -12,7 +12,7 @@ #include <linux/compiler.h> #include <linux/spinlock.h> #include <linux/device.h> -#include <linux/dma-mapping.h> +#include <linux/dma-map-ops.h> #include <linux/bitops.h> #include <asm/machdep.h> #include <asm/types.h> @@ -22,11 +22,14 @@ #define IOMMU_PAGE_SHIFT_4K 12 #define IOMMU_PAGE_SIZE_4K (ASM_CONST(1) << IOMMU_PAGE_SHIFT_4K) #define IOMMU_PAGE_MASK_4K (~((1 << IOMMU_PAGE_SHIFT_4K) - 1)) -#define IOMMU_PAGE_ALIGN_4K(addr) _ALIGN_UP(addr, IOMMU_PAGE_SIZE_4K) +#define IOMMU_PAGE_ALIGN_4K(addr) ALIGN(addr, IOMMU_PAGE_SIZE_4K) #define IOMMU_PAGE_SIZE(tblptr) (ASM_CONST(1) << (tblptr)->it_page_shift) #define IOMMU_PAGE_MASK(tblptr) (~((1 << (tblptr)->it_page_shift) - 1)) -#define IOMMU_PAGE_ALIGN(addr, tblptr) _ALIGN_UP(addr, IOMMU_PAGE_SIZE(tblptr)) +#define IOMMU_PAGE_ALIGN(addr, tblptr) ALIGN(addr, IOMMU_PAGE_SIZE(tblptr)) + +#define DIRECT64_PROPNAME "linux,direct64-ddr-window-info" +#define DMA64_PROPNAME "linux,dma64-ddr-window-info" /* Boot time flags */ extern int iommu_is_off; @@ -51,13 +54,11 @@ struct iommu_table_ops { int (*xchg_no_kill)(struct iommu_table *tbl, long index, unsigned long *hpa, - enum dma_data_direction *direction, - bool realmode); + enum dma_data_direction *direction); void (*tce_kill)(struct iommu_table *tbl, unsigned long index, - unsigned long pages, - bool realmode); + unsigned long pages); __be64 *(*useraddrptr)(struct iommu_table *tbl, long index, bool alloc); #endif @@ -154,6 +155,7 @@ extern int iommu_tce_table_put(struct iommu_table *tbl); */ extern struct iommu_table *iommu_init_table(struct iommu_table *tbl, int nid, unsigned long res_start, unsigned long res_end); +bool iommu_table_in_use(struct iommu_table *tbl); #define IOMMU_TABLE_GROUP_MAX_TABLES 2 @@ -176,7 +178,7 @@ struct iommu_table_group_ops { long (*unset_window)(struct iommu_table_group *table_group, int num); /* Switch ownership from platform code to external user (e.g. VFIO) */ - void (*take_ownership)(struct iommu_table_group *table_group); + long (*take_ownership)(struct iommu_table_group *table_group); /* Switch ownership from external user (e.g. VFIO) back to core */ void (*release_ownership)(struct iommu_table_group *table_group); }; @@ -206,7 +208,6 @@ extern void iommu_register_group(struct iommu_table_group *table_group, int pci_domain_number, unsigned long pe_num); extern int iommu_add_device(struct iommu_table_group *table_group, struct device *dev); -extern void iommu_del_device(struct device *dev); extern long iommu_tce_xchg(struct mm_struct *mm, struct iommu_table *tbl, unsigned long entry, unsigned long *hpa, enum dma_data_direction *direction); @@ -216,6 +217,8 @@ extern long iommu_tce_xchg_no_kill(struct mm_struct *mm, enum dma_data_direction *direction); extern void iommu_tce_kill(struct iommu_table *tbl, unsigned long entry, unsigned long pages); + +extern struct iommu_table_group_ops spapr_tce_table_group_ops; #else static inline void iommu_register_group(struct iommu_table_group *table_group, int pci_domain_number, @@ -228,10 +231,6 @@ static inline int iommu_add_device(struct iommu_table_group *table_group, { return 0; } - -static inline void iommu_del_device(struct device *dev) -{ -} #endif /* !CONFIG_IOMMU_API */ u64 dma_iommu_get_required_mask(struct device *dev); @@ -274,17 +273,11 @@ extern void iommu_unmap_page(struct iommu_table *tbl, dma_addr_t dma_handle, size_t size, enum dma_data_direction direction, unsigned long attrs); -extern void iommu_init_early_pSeries(void); +void __init iommu_init_early_pSeries(void); extern void iommu_init_early_dart(struct pci_controller_ops *controller_ops); extern void iommu_init_early_pasemi(void); #if defined(CONFIG_PPC64) && defined(CONFIG_PM) -static inline void iommu_save(void) -{ - if (ppc_md.iommu_save) - ppc_md.iommu_save(); -} - static inline void iommu_restore(void) { if (ppc_md.iommu_restore) @@ -310,8 +303,6 @@ extern int iommu_tce_check_gpa(unsigned long page_shift, iommu_tce_check_gpa((tbl)->it_page_shift, (gpa))) extern void iommu_flush_tce(struct iommu_table *tbl); -extern int iommu_take_ownership(struct iommu_table *tbl); -extern void iommu_release_ownership(struct iommu_table *tbl); extern enum dma_data_direction iommu_tce_direction(unsigned long tce); extern unsigned long iommu_direction_to_tce_perm(enum dma_data_direction dir); diff --git a/arch/powerpc/include/asm/ipic.h b/arch/powerpc/include/asm/ipic.h index 0524df31a7e6..b47ca7dc7199 100644 --- a/arch/powerpc/include/asm/ipic.h +++ b/arch/powerpc/include/asm/ipic.h @@ -65,7 +65,7 @@ enum ipic_mcp_irq { IPIC_MCP_MU = 7, }; -extern void ipic_set_default_priority(void); +void __init ipic_set_default_priority(void); extern u32 ipic_get_mcp_status(void); extern void ipic_clear_mcp_status(u32 mask); diff --git a/arch/powerpc/include/asm/irq.h b/arch/powerpc/include/asm/irq.h index 814dfab7e392..ba1a5974e714 100644 --- a/arch/powerpc/include/asm/irq.h +++ b/arch/powerpc/include/asm/irq.h @@ -6,7 +6,6 @@ /* */ -#include <linux/irqdomain.h> #include <linux/threads.h> #include <linux/list.h> #include <linux/radix-tree.h> @@ -17,14 +16,11 @@ extern atomic_t ppc_n_lost_interrupts; -/* This number is used when no interrupt has been assigned */ -#define NO_IRQ (0) - /* Total number of virq in the platform */ #define NR_IRQS CONFIG_NR_IRQS -/* Same thing, used by the generic IRQ code */ -#define NR_IRQS_LEGACY NUM_ISA_INTERRUPTS +/* Number of irqs reserved for a legacy isa controller */ +#define NR_IRQS_LEGACY 16 extern irq_hw_number_t virq_to_hw(unsigned int virq); @@ -35,12 +31,9 @@ static __inline__ int irq_canonicalize(int irq) extern int distribute_irqs; -struct irqaction; struct pt_regs; -#define __ARCH_HAS_DO_SOFTIRQ - -#if defined(CONFIG_BOOKE) || defined(CONFIG_40x) +#ifdef CONFIG_BOOKE_OR_40x /* * Per-cpu stacks for handling critical, debug and machine check * level interrupts. @@ -56,13 +49,15 @@ extern void *mcheckirq_ctx[NR_CPUS]; extern void *hardirq_ctx[NR_CPUS]; extern void *softirq_ctx[NR_CPUS]; -void call_do_softirq(void *sp); -void call_do_irq(struct pt_regs *regs, void *sp); -extern void do_IRQ(struct pt_regs *regs); -extern void __init init_IRQ(void); -extern void __do_irq(struct pt_regs *regs); +void __do_IRQ(struct pt_regs *regs); int irq_choose_cpu(const struct cpumask *mask); +#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_NMI_IPI) +extern void arch_trigger_cpumask_backtrace(const cpumask_t *mask, + int exclude_cpu); +#define arch_trigger_cpumask_backtrace arch_trigger_cpumask_backtrace +#endif + #endif /* _ASM_IRQ_H */ #endif /* __KERNEL__ */ diff --git a/arch/powerpc/include/asm/irq_work.h b/arch/powerpc/include/asm/irq_work.h index b8b0be8f1a07..c6d3078bd8c3 100644 --- a/arch/powerpc/include/asm/irq_work.h +++ b/arch/powerpc/include/asm/irq_work.h @@ -6,6 +6,5 @@ static inline bool arch_irq_work_has_interrupt(void) { return true; } -extern void arch_irq_work_raise(void); #endif /* _ASM_POWERPC_IRQ_WORK_H */ diff --git a/arch/powerpc/include/asm/irqflags.h b/arch/powerpc/include/asm/irqflags.h index 1a6c1ce17735..47d46712928a 100644 --- a/arch/powerpc/include/asm/irqflags.h +++ b/arch/powerpc/include/asm/irqflags.h @@ -11,64 +11,6 @@ */ #include <asm/hw_irq.h> -#else -#ifdef CONFIG_TRACE_IRQFLAGS -#ifdef CONFIG_IRQSOFF_TRACER -/* - * Since the ftrace irqsoff latency trace checks CALLER_ADDR1, - * which is the stack frame here, we need to force a stack frame - * in case we came from user space. - */ -#define TRACE_WITH_FRAME_BUFFER(func) \ - mflr r0; \ - stdu r1, -STACK_FRAME_OVERHEAD(r1); \ - std r0, 16(r1); \ - stdu r1, -STACK_FRAME_OVERHEAD(r1); \ - bl func; \ - ld r1, 0(r1); \ - ld r1, 0(r1); -#else -#define TRACE_WITH_FRAME_BUFFER(func) \ - bl func; -#endif - -/* - * These are calls to C code, so the caller must be prepared for volatiles to - * be clobbered. - */ -#define TRACE_ENABLE_INTS TRACE_WITH_FRAME_BUFFER(trace_hardirqs_on) -#define TRACE_DISABLE_INTS TRACE_WITH_FRAME_BUFFER(trace_hardirqs_off) - -/* - * This is used by assembly code to soft-disable interrupts first and - * reconcile irq state. - * - * NB: This may call C code, so the caller must be prepared for volatiles to - * be clobbered. - */ -#define RECONCILE_IRQ_STATE(__rA, __rB) \ - lbz __rA,PACAIRQSOFTMASK(r13); \ - lbz __rB,PACAIRQHAPPENED(r13); \ - andi. __rA,__rA,IRQS_DISABLED; \ - li __rA,IRQS_DISABLED; \ - ori __rB,__rB,PACA_IRQ_HARD_DIS; \ - stb __rB,PACAIRQHAPPENED(r13); \ - bne 44f; \ - stb __rA,PACAIRQSOFTMASK(r13); \ - TRACE_DISABLE_INTS; \ -44: - -#else -#define TRACE_ENABLE_INTS -#define TRACE_DISABLE_INTS - -#define RECONCILE_IRQ_STATE(__rA, __rB) \ - lbz __rA,PACAIRQHAPPENED(r13); \ - li __rB,IRQS_DISABLED; \ - ori __rA,__rA,PACA_IRQ_HARD_DIS; \ - stb __rB,PACAIRQSOFTMASK(r13); \ - stb __rA,PACAIRQHAPPENED(r13) -#endif #endif #endif diff --git a/arch/powerpc/include/asm/jump_label.h b/arch/powerpc/include/asm/jump_label.h index 09297ec9fa52..93ce3ec25387 100644 --- a/arch/powerpc/include/asm/jump_label.h +++ b/arch/powerpc/include/asm/jump_label.h @@ -20,7 +20,8 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool bran asm_volatile_goto("1:\n\t" "nop # arch_static_branch\n\t" ".pushsection __jump_table, \"aw\"\n\t" - JUMP_ENTRY_TYPE "1b, %l[l_yes], %c0\n\t" + ".long 1b - ., %l[l_yes] - .\n\t" + JUMP_ENTRY_TYPE "%c0 - .\n\t" ".popsection \n\t" : : "i" (&((char *)key)[branch]) : : l_yes); @@ -34,7 +35,8 @@ static __always_inline bool arch_static_branch_jump(struct static_key *key, bool asm_volatile_goto("1:\n\t" "b %l[l_yes] # arch_static_branch_jump\n\t" ".pushsection __jump_table, \"aw\"\n\t" - JUMP_ENTRY_TYPE "1b, %l[l_yes], %c0\n\t" + ".long 1b - ., %l[l_yes] - .\n\t" + JUMP_ENTRY_TYPE "%c0 - .\n\t" ".popsection \n\t" : : "i" (&((char *)key)[branch]) : : l_yes); @@ -43,23 +45,12 @@ l_yes: return true; } -#ifdef CONFIG_PPC64 -typedef u64 jump_label_t; -#else -typedef u32 jump_label_t; -#endif - -struct jump_entry { - jump_label_t code; - jump_label_t target; - jump_label_t key; -}; - #else #define ARCH_STATIC_BRANCH(LABEL, KEY) \ 1098: nop; \ .pushsection __jump_table, "aw"; \ - FTR_ENTRY_LONG 1098b, LABEL, KEY; \ + .long 1098b - ., LABEL - .; \ + FTR_ENTRY_LONG KEY - .; \ .popsection #endif diff --git a/arch/powerpc/include/asm/kasan.h b/arch/powerpc/include/asm/kasan.h index 296e51c2f066..365d2720097c 100644 --- a/arch/powerpc/include/asm/kasan.h +++ b/arch/powerpc/include/asm/kasan.h @@ -2,7 +2,7 @@ #ifndef __ASM_KASAN_H #define __ASM_KASAN_H -#ifdef CONFIG_KASAN +#if defined(CONFIG_KASAN) && !defined(CONFIG_CC_HAS_KASAN_MEMINTRINSIC_PREFIX) #define _GLOBAL_KASAN(fn) _GLOBAL(__##fn) #define _GLOBAL_TOC_KASAN(fn) _GLOBAL_TOC(__##fn) #define EXPORT_SYMBOL_KASAN(fn) EXPORT_SYMBOL(__##fn) @@ -15,26 +15,70 @@ #ifndef __ASSEMBLY__ #include <asm/page.h> +#include <linux/sizes.h> #define KASAN_SHADOW_SCALE_SHIFT 3 +#if defined(CONFIG_MODULES) && defined(CONFIG_PPC32) +#define KASAN_KERN_START ALIGN_DOWN(PAGE_OFFSET - SZ_256M, SZ_256M) +#else +#define KASAN_KERN_START PAGE_OFFSET +#endif + #define KASAN_SHADOW_START (KASAN_SHADOW_OFFSET + \ - (PAGE_OFFSET >> KASAN_SHADOW_SCALE_SHIFT)) + (KASAN_KERN_START >> KASAN_SHADOW_SCALE_SHIFT)) #define KASAN_SHADOW_OFFSET ASM_CONST(CONFIG_KASAN_SHADOW_OFFSET) -#define KASAN_SHADOW_END 0UL +#ifdef CONFIG_PPC32 +#define KASAN_SHADOW_END (-(-KASAN_SHADOW_START >> KASAN_SHADOW_SCALE_SHIFT)) +#elif defined(CONFIG_PPC_BOOK3S_64) +/* + * The shadow ends before the highest accessible address + * because we don't need a shadow for the shadow. Instead: + * c00e000000000000 << 3 + a80e000000000000 = c00fc00000000000 + */ +#define KASAN_SHADOW_END 0xc00fc00000000000UL -#define KASAN_SHADOW_SIZE (KASAN_SHADOW_END - KASAN_SHADOW_START) +#else + +/* + * The shadow ends before the highest accessible address + * because we don't need a shadow for the shadow. + * But it doesn't hurt to have a shadow for the shadow, + * keep shadow end aligned eases things. + */ +#define KASAN_SHADOW_END 0xc000200000000000UL + +#endif #ifdef CONFIG_KASAN +#ifdef CONFIG_PPC_BOOK3S_64 +DECLARE_STATIC_KEY_FALSE(powerpc_kasan_enabled_key); + +static __always_inline bool kasan_arch_is_ready(void) +{ + if (static_branch_likely(&powerpc_kasan_enabled_key)) + return true; + return false; +} + +#define kasan_arch_is_ready kasan_arch_is_ready +#endif + void kasan_early_init(void); void kasan_mmu_init(void); void kasan_init(void); +void kasan_late_init(void); #else static inline void kasan_init(void) { } static inline void kasan_mmu_init(void) { } +static inline void kasan_late_init(void) { } #endif +void kasan_update_early_region(unsigned long k_start, unsigned long k_end, pte_t pte); +int kasan_init_shadow_page_tables(unsigned long k_start, unsigned long k_end); +int kasan_init_region(void *start, size_t size); + #endif /* __ASSEMBLY */ #endif diff --git a/arch/powerpc/include/asm/kexec.h b/arch/powerpc/include/asm/kexec.h index c68476818753..e1b43aa12175 100644 --- a/arch/powerpc/include/asm/kexec.h +++ b/arch/powerpc/include/asm/kexec.h @@ -3,7 +3,7 @@ #define _ASM_POWERPC_KEXEC_H #ifdef __KERNEL__ -#if defined(CONFIG_FSL_BOOKE) || defined(CONFIG_44x) +#if defined(CONFIG_PPC_85xx) || defined(CONFIG_44x) /* * On FSL-BookE we setup a 1:1 mapping which covers the first 2GiB of memory @@ -79,13 +79,13 @@ extern int crash_wake_offline; struct kimage; struct pt_regs; extern void default_machine_kexec(struct kimage *image); -extern int default_machine_kexec_prepare(struct kimage *image); extern void default_machine_crash_shutdown(struct pt_regs *regs); extern int crash_shutdown_register(crash_shutdown_t handler); extern int crash_shutdown_unregister(crash_shutdown_t handler); +extern void crash_kexec_prepare(void); extern void crash_kexec_secondary(struct pt_regs *regs); -extern int overlaps_crashkernel(unsigned long start, unsigned long size); +int __init overlaps_crashkernel(unsigned long start, unsigned long size); extern void reserve_crashkernel(void); extern void machine_kexec_mask_interrupts(void); @@ -97,25 +97,59 @@ static inline bool kdump_in_progress(void) void relocate_new_kernel(unsigned long indirection_page, unsigned long reboot_code_buffer, unsigned long start_address) __noreturn; +void kexec_copy_flush(struct kimage *image); + +#if defined(CONFIG_CRASH_DUMP) +bool is_kdump_kernel(void); +#define is_kdump_kernel is_kdump_kernel +#if defined(CONFIG_PPC_RTAS) +void crash_free_reserved_phys_range(unsigned long begin, unsigned long end); +#define crash_free_reserved_phys_range crash_free_reserved_phys_range +#endif /* CONFIG_PPC_RTAS */ +#endif /* CONFIG_CRASH_DUMP */ + #ifdef CONFIG_KEXEC_FILE extern const struct kexec_file_ops kexec_elf64_ops; -#ifdef CONFIG_IMA_KEXEC #define ARCH_HAS_KIMAGE_ARCH struct kimage_arch { - phys_addr_t ima_buffer_addr; - size_t ima_buffer_size; + struct crash_mem *exclude_ranges; + + unsigned long backup_start; + void *backup_buf; + void *fdt; }; -#endif +char *setup_kdump_cmdline(struct kimage *image, char *cmdline, + unsigned long cmdline_len); int setup_purgatory(struct kimage *image, const void *slave_code, const void *fdt, unsigned long kernel_load_addr, unsigned long fdt_load_addr); -int setup_new_fdt(const struct kimage *image, void *fdt, - unsigned long initrd_load_addr, unsigned long initrd_len, - const char *cmdline); -int delete_fdt_mem_rsv(void *fdt, unsigned long start, unsigned long size); + +#ifdef CONFIG_PPC64 +struct kexec_buf; + +int arch_kexec_kernel_image_probe(struct kimage *image, void *buf, unsigned long buf_len); +#define arch_kexec_kernel_image_probe arch_kexec_kernel_image_probe + +int arch_kimage_file_post_load_cleanup(struct kimage *image); +#define arch_kimage_file_post_load_cleanup arch_kimage_file_post_load_cleanup + +int arch_kexec_locate_mem_hole(struct kexec_buf *kbuf); +#define arch_kexec_locate_mem_hole arch_kexec_locate_mem_hole + +int load_crashdump_segments_ppc64(struct kimage *image, + struct kexec_buf *kbuf); +int setup_purgatory_ppc64(struct kimage *image, const void *slave_code, + const void *fdt, unsigned long kernel_load_addr, + unsigned long fdt_load_addr); +unsigned int kexec_extra_fdt_size_ppc64(struct kimage *image); +int setup_new_fdt_ppc64(const struct kimage *image, void *fdt, + unsigned long initrd_load_addr, + unsigned long initrd_len, const char *cmdline); +#endif /* CONFIG_PPC64 */ + #endif /* CONFIG_KEXEC_FILE */ #else /* !CONFIG_KEXEC_CORE */ @@ -150,6 +184,18 @@ static inline void crash_send_ipi(void (*crash_ipi_callback)(struct pt_regs *)) } #endif /* CONFIG_KEXEC_CORE */ + +#ifdef CONFIG_PPC_BOOK3S_64 +#include <asm/book3s/64/kexec.h> +#endif + +#ifndef reset_sprs +#define reset_sprs reset_sprs +static inline void reset_sprs(void) +{ +} +#endif + #endif /* ! __ASSEMBLY__ */ #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_KEXEC_H */ diff --git a/arch/powerpc/include/asm/kexec_ranges.h b/arch/powerpc/include/asm/kexec_ranges.h new file mode 100644 index 000000000000..f83866a19e87 --- /dev/null +++ b/arch/powerpc/include/asm/kexec_ranges.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef _ASM_POWERPC_KEXEC_RANGES_H +#define _ASM_POWERPC_KEXEC_RANGES_H + +#define MEM_RANGE_CHUNK_SZ 2048 /* Memory ranges size chunk */ + +void sort_memory_ranges(struct crash_mem *mrngs, bool merge); +struct crash_mem *realloc_mem_ranges(struct crash_mem **mem_ranges); +int add_mem_range(struct crash_mem **mem_ranges, u64 base, u64 size); +int add_tce_mem_ranges(struct crash_mem **mem_ranges); +int add_initrd_mem_range(struct crash_mem **mem_ranges); +#ifdef CONFIG_PPC_64S_HASH_MMU +int add_htab_mem_range(struct crash_mem **mem_ranges); +#else +static inline int add_htab_mem_range(struct crash_mem **mem_ranges) +{ + return 0; +} +#endif +int add_kernel_mem_range(struct crash_mem **mem_ranges); +int add_rtas_mem_range(struct crash_mem **mem_ranges); +int add_opal_mem_range(struct crash_mem **mem_ranges); +int add_reserved_mem_ranges(struct crash_mem **mem_ranges); + +#endif /* _ASM_POWERPC_KEXEC_RANGES_H */ diff --git a/arch/powerpc/include/asm/kfence.h b/arch/powerpc/include/asm/kfence.h new file mode 100644 index 000000000000..424ceef82ae6 --- /dev/null +++ b/arch/powerpc/include/asm/kfence.h @@ -0,0 +1,48 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * powerpc KFENCE support. + * + * Copyright (C) 2020 CS GROUP France + */ + +#ifndef __ASM_POWERPC_KFENCE_H +#define __ASM_POWERPC_KFENCE_H + +#include <linux/mm.h> +#include <asm/pgtable.h> + +#ifdef CONFIG_PPC64_ELF_ABI_V1 +#define ARCH_FUNC_PREFIX "." +#endif + +static inline bool arch_kfence_init_pool(void) +{ + return true; +} + +#ifdef CONFIG_PPC64 +static inline bool kfence_protect_page(unsigned long addr, bool protect) +{ + struct page *page = virt_to_page((void *)addr); + + __kernel_map_pages(page, 1, !protect); + + return true; +} +#else +static inline bool kfence_protect_page(unsigned long addr, bool protect) +{ + pte_t *kpte = virt_to_kpte(addr); + + if (protect) { + pte_update(&init_mm, addr, kpte, _PAGE_PRESENT, 0, 0); + flush_tlb_kernel_range(addr, addr + PAGE_SIZE); + } else { + pte_update(&init_mm, addr, kpte, 0, _PAGE_PRESENT, 0); + } + + return true; +} +#endif + +#endif /* __ASM_POWERPC_KFENCE_H */ diff --git a/arch/powerpc/include/asm/kgdb.h b/arch/powerpc/include/asm/kgdb.h index a9e098a3b881..715c18b75334 100644 --- a/arch/powerpc/include/asm/kgdb.h +++ b/arch/powerpc/include/asm/kgdb.h @@ -52,7 +52,7 @@ static inline void arch_kgdb_breakpoint(void) /* On non-E500 family PPC32 we determine the size by picking the last * register we need, but on E500 we skip sections so we list what we * need to store, and add it up. */ -#ifndef CONFIG_E500 +#ifndef CONFIG_PPC_E500 #define MAXREG (PT_FPSCR+1) #else /* 32 GPRs (8 bytes), nip, msr, ccr, link, ctr, xer, acc (8 bytes), spefscr*/ diff --git a/arch/powerpc/include/asm/kmap_types.h b/arch/powerpc/include/asm/kmap_types.h deleted file mode 100644 index c8fa182d48c8..000000000000 --- a/arch/powerpc/include/asm/kmap_types.h +++ /dev/null @@ -1,13 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -#ifndef _ASM_POWERPC_KMAP_TYPES_H -#define _ASM_POWERPC_KMAP_TYPES_H - -#ifdef __KERNEL__ - -/* - */ - -#define KM_TYPE_NR 16 - -#endif /* __KERNEL__ */ -#endif /* _ASM_POWERPC_KMAP_TYPES_H */ diff --git a/arch/powerpc/include/asm/kprobes.h b/arch/powerpc/include/asm/kprobes.h index 66b3f2983b22..4525a9c68260 100644 --- a/arch/powerpc/include/asm/kprobes.h +++ b/arch/powerpc/include/asm/kprobes.h @@ -29,7 +29,7 @@ struct pt_regs; struct kprobe; -typedef ppc_opcode_t kprobe_opcode_t; +typedef u32 kprobe_opcode_t; extern kprobe_opcode_t optinsn_slot; @@ -43,7 +43,7 @@ extern kprobe_opcode_t optprobe_template_ret[]; extern kprobe_opcode_t optprobe_template_end[]; /* Fixed instruction size for powerpc */ -#define MAX_INSN_SIZE 1 +#define MAX_INSN_SIZE 2 #define MAX_OPTIMIZED_LENGTH sizeof(kprobe_opcode_t) /* 4 bytes */ #define MAX_OPTINSN_SIZE (optprobe_template_end - optprobe_template_entry) #define RELATIVEJUMP_SIZE sizeof(kprobe_opcode_t) /* 4 bytes */ @@ -51,7 +51,7 @@ extern kprobe_opcode_t optprobe_template_end[]; #define flush_insn_slot(p) do { } while (0) #define kretprobe_blacklist_size 0 -void kretprobe_trampoline(void); +void __kretprobe_trampoline(void); extern void arch_remove_kprobe(struct kprobe *p); /* Architecture specific copy of original instruction */ @@ -84,8 +84,6 @@ struct arch_optimized_insn { kprobe_opcode_t *insn; }; -extern int kprobe_exceptions_notify(struct notifier_block *self, - unsigned long val, void *data); extern int kprobe_fault_handler(struct pt_regs *regs, int trapnr); extern int kprobe_handler(struct pt_regs *regs); extern int kprobe_post_handler(struct pt_regs *regs); diff --git a/arch/powerpc/include/asm/kup.h b/arch/powerpc/include/asm/kup.h index 5b5e39643a27..ad7e8c5aec3f 100644 --- a/arch/powerpc/include/asm/kup.h +++ b/arch/powerpc/include/asm/kup.h @@ -2,72 +2,185 @@ #ifndef _ASM_POWERPC_KUP_H_ #define _ASM_POWERPC_KUP_H_ -#ifdef CONFIG_PPC64 -#include <asm/book3s/64/kup-radix.h> +#define KUAP_READ 1 +#define KUAP_WRITE 2 +#define KUAP_READ_WRITE (KUAP_READ | KUAP_WRITE) + +#ifndef __ASSEMBLY__ +#include <linux/types.h> + +static __always_inline bool kuap_is_disabled(void); +#endif + +#ifdef CONFIG_PPC_BOOK3S_64 +#include <asm/book3s/64/kup.h> #endif + #ifdef CONFIG_PPC_8xx #include <asm/nohash/32/kup-8xx.h> #endif + +#ifdef CONFIG_BOOKE_OR_40x +#include <asm/nohash/kup-booke.h> +#endif + #ifdef CONFIG_PPC_BOOK3S_32 #include <asm/book3s/32/kup.h> #endif #ifdef __ASSEMBLY__ #ifndef CONFIG_PPC_KUAP -.macro kuap_save_and_lock sp, thread, gpr1, gpr2, gpr3 -.endm - -.macro kuap_restore sp, current, gpr1, gpr2, gpr3 -.endm - -.macro kuap_check current, gpr +.macro kuap_check_amr gpr1, gpr2 .endm #endif #else /* !__ASSEMBLY__ */ -#include <asm/pgtable.h> +extern bool disable_kuep; +extern bool disable_kuap; -void setup_kup(void); +#include <linux/pgtable.h> -#ifdef CONFIG_PPC_KUEP +void setup_kup(void); void setup_kuep(bool disabled); -#else -static inline void setup_kuep(bool disabled) { } -#endif /* CONFIG_PPC_KUEP */ #ifdef CONFIG_PPC_KUAP void setup_kuap(bool disabled); + +static __always_inline bool kuap_is_disabled(void) +{ + return !mmu_has_feature(MMU_FTR_KUAP); +} #else static inline void setup_kuap(bool disabled) { } -static inline void allow_user_access(void __user *to, const void __user *from, - unsigned long size) { } -static inline void prevent_user_access(void __user *to, const void __user *from, - unsigned long size) { } -static inline bool bad_kuap_fault(struct pt_regs *regs, bool is_write) { return false; } + +static __always_inline bool kuap_is_disabled(void) { return true; } + +static __always_inline bool +__bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write) +{ + return false; +} + +static __always_inline void kuap_user_restore(struct pt_regs *regs) { } +static __always_inline void __kuap_kernel_restore(struct pt_regs *regs, unsigned long amr) { } + +/* + * book3s/64/kup-radix.h defines these functions for the !KUAP case to flush + * the L1D cache after user accesses. Only include the empty stubs for other + * platforms. + */ +#ifndef CONFIG_PPC_BOOK3S_64 +static __always_inline void allow_user_access(void __user *to, const void __user *from, + unsigned long size, unsigned long dir) { } +static __always_inline void prevent_user_access(unsigned long dir) { } +static __always_inline unsigned long prevent_user_access_return(void) { return 0UL; } +static __always_inline void restore_user_access(unsigned long flags) { } +#endif /* CONFIG_PPC_BOOK3S_64 */ #endif /* CONFIG_PPC_KUAP */ -static inline void allow_read_from_user(const void __user *from, unsigned long size) +static __always_inline bool +bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write) +{ + if (kuap_is_disabled()) + return false; + + return __bad_kuap_fault(regs, address, is_write); +} + +static __always_inline void kuap_lock(void) +{ +#ifdef __kuap_lock + if (kuap_is_disabled()) + return; + + __kuap_lock(); +#endif +} + +static __always_inline void kuap_save_and_lock(struct pt_regs *regs) +{ +#ifdef __kuap_save_and_lock + if (kuap_is_disabled()) + return; + + __kuap_save_and_lock(regs); +#endif +} + +static __always_inline void kuap_kernel_restore(struct pt_regs *regs, unsigned long amr) +{ + if (kuap_is_disabled()) + return; + + __kuap_kernel_restore(regs, amr); +} + +static __always_inline unsigned long kuap_get_and_assert_locked(void) +{ +#ifdef __kuap_get_and_assert_locked + if (!kuap_is_disabled()) + return __kuap_get_and_assert_locked(); +#endif + return 0; +} + +static __always_inline void kuap_assert_locked(void) +{ + if (IS_ENABLED(CONFIG_PPC_KUAP_DEBUG)) + kuap_get_and_assert_locked(); +} + +static __always_inline void allow_read_from_user(const void __user *from, unsigned long size) +{ + barrier_nospec(); + allow_user_access(NULL, from, size, KUAP_READ); +} + +static __always_inline void allow_write_to_user(void __user *to, unsigned long size) +{ + allow_user_access(to, NULL, size, KUAP_WRITE); +} + +static __always_inline void allow_read_write_user(void __user *to, const void __user *from, + unsigned long size) +{ + barrier_nospec(); + allow_user_access(to, from, size, KUAP_READ_WRITE); +} + +static __always_inline void prevent_read_from_user(const void __user *from, unsigned long size) +{ + prevent_user_access(KUAP_READ); +} + +static __always_inline void prevent_write_to_user(void __user *to, unsigned long size) +{ + prevent_user_access(KUAP_WRITE); +} + +static __always_inline void prevent_read_write_user(void __user *to, const void __user *from, + unsigned long size) { - allow_user_access(NULL, from, size); + prevent_user_access(KUAP_READ_WRITE); } -static inline void allow_write_to_user(void __user *to, unsigned long size) +static __always_inline void prevent_current_access_user(void) { - allow_user_access(to, NULL, size); + prevent_user_access(KUAP_READ_WRITE); } -static inline void prevent_read_from_user(const void __user *from, unsigned long size) +static __always_inline void prevent_current_read_from_user(void) { - prevent_user_access(NULL, from, size); + prevent_user_access(KUAP_READ); } -static inline void prevent_write_to_user(void __user *to, unsigned long size) +static __always_inline void prevent_current_write_to_user(void) { - prevent_user_access(to, NULL, size); + prevent_user_access(KUAP_WRITE); } #endif /* !__ASSEMBLY__ */ -#endif /* _ASM_POWERPC_KUP_H_ */ +#endif /* _ASM_POWERPC_KUAP_H_ */ diff --git a/arch/powerpc/include/asm/kvm_asm.h b/arch/powerpc/include/asm/kvm_asm.h index 635fb154b33f..d68d71987d5c 100644 --- a/arch/powerpc/include/asm/kvm_asm.h +++ b/arch/powerpc/include/asm/kvm_asm.h @@ -79,6 +79,7 @@ #define BOOK3S_INTERRUPT_FP_UNAVAIL 0x800 #define BOOK3S_INTERRUPT_DECREMENTER 0x900 #define BOOK3S_INTERRUPT_HV_DECREMENTER 0x980 +#define BOOK3S_INTERRUPT_NESTED_HV_DECREMENTER 0x1980 #define BOOK3S_INTERRUPT_DOORBELL 0xa00 #define BOOK3S_INTERRUPT_SYSCALL 0xc00 #define BOOK3S_INTERRUPT_TRACE 0xd00 @@ -147,7 +148,11 @@ #define KVM_GUEST_MODE_SKIP 2 #define KVM_GUEST_MODE_GUEST_HV 3 #define KVM_GUEST_MODE_HOST_HV 4 +#define KVM_GUEST_MODE_HV_P9 5 /* ISA >= v3.0 path */ #define KVM_INST_FETCH_FAILED -1 +/* Extract PO and XOP opcode fields */ +#define PO_XOP_OPCODE_MASK 0xfc0007fe + #endif /* __POWERPC_KVM_ASM_H__ */ diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h index 506e4df2d730..3e1e2a698c9e 100644 --- a/arch/powerpc/include/asm/kvm_book3s.h +++ b/arch/powerpc/include/asm/kvm_book3s.h @@ -12,6 +12,7 @@ #include <linux/types.h> #include <linux/kvm_host.h> #include <asm/kvm_book3s_asm.h> +#include <asm/guest-state-buffer.h> struct kvmppc_bat { u64 raw; @@ -78,7 +79,7 @@ struct kvmppc_vcore { struct kvm_vcpu *runnable_threads[MAX_SMT_THREADS]; struct list_head preempt_list; spinlock_t lock; - struct swait_queue_head wq; + struct rcuwait wait; spinlock_t stoltb_lock; /* protects stolen_tb and preempt_tb */ u64 stolen_tb; u64 preempt_tb; @@ -155,12 +156,11 @@ extern void kvmppc_mmu_unmap_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *pte) extern int kvmppc_mmu_map_segment(struct kvm_vcpu *vcpu, ulong eaddr); extern void kvmppc_mmu_flush_segment(struct kvm_vcpu *vcpu, ulong eaddr, ulong seg_size); extern void kvmppc_mmu_flush_segments(struct kvm_vcpu *vcpu); -extern int kvmppc_book3s_hv_page_fault(struct kvm_run *run, - struct kvm_vcpu *vcpu, unsigned long addr, - unsigned long status); +extern int kvmppc_book3s_hv_page_fault(struct kvm_vcpu *vcpu, + unsigned long addr, unsigned long status); extern long kvmppc_hv_find_lock_hpte(struct kvm *kvm, gva_t eaddr, unsigned long slb_v, unsigned long valid); -extern int kvmppc_hv_emulate_mmio(struct kvm_run *run, struct kvm_vcpu *vcpu, +extern int kvmppc_hv_emulate_mmio(struct kvm_vcpu *vcpu, unsigned long gpa, gva_t ea, int is_store); extern void kvmppc_mmu_hpte_cache_map(struct kvm_vcpu *vcpu, struct hpte_cache *pte); @@ -174,8 +174,7 @@ extern void kvmppc_mmu_hpte_sysexit(void); extern int kvmppc_mmu_hv_init(void); extern int kvmppc_book3s_hcall_implemented(struct kvm *kvm, unsigned long hc); -extern int kvmppc_book3s_radix_page_fault(struct kvm_run *run, - struct kvm_vcpu *vcpu, +extern int kvmppc_book3s_radix_page_fault(struct kvm_vcpu *vcpu, unsigned long ea, unsigned long dsisr); extern unsigned long __kvmhv_copy_tofrom_guest_radix(int lpid, int pid, gva_t eaddr, void *to, void *from, @@ -193,14 +192,14 @@ extern int kvmppc_mmu_radix_translate_table(struct kvm_vcpu *vcpu, gva_t eaddr, extern int kvmppc_mmu_radix_xlate(struct kvm_vcpu *vcpu, gva_t eaddr, struct kvmppc_pte *gpte, bool data, bool iswrite); extern void kvmppc_radix_tlbie_page(struct kvm *kvm, unsigned long addr, - unsigned int pshift, unsigned int lpid); + unsigned int pshift, u64 lpid); extern void kvmppc_unmap_pte(struct kvm *kvm, pte_t *pte, unsigned long gpa, unsigned int shift, const struct kvm_memory_slot *memslot, - unsigned int lpid); -extern bool kvmppc_hv_handle_set_rc(struct kvm *kvm, pgd_t *pgtable, + u64 lpid); +extern bool kvmppc_hv_handle_set_rc(struct kvm *kvm, bool nested, bool writing, unsigned long gpa, - unsigned int lpid); + u64 lpid); extern int kvmppc_book3s_instantiate_page(struct kvm_vcpu *vcpu, unsigned long gpa, struct kvm_memory_slot *memslot, @@ -209,15 +208,15 @@ extern int kvmppc_book3s_instantiate_page(struct kvm_vcpu *vcpu, extern int kvmppc_init_vm_radix(struct kvm *kvm); extern void kvmppc_free_radix(struct kvm *kvm); extern void kvmppc_free_pgtable_radix(struct kvm *kvm, pgd_t *pgd, - unsigned int lpid); + u64 lpid); extern int kvmppc_radix_init(void); extern void kvmppc_radix_exit(void); -extern int kvm_unmap_radix(struct kvm *kvm, struct kvm_memory_slot *memslot, - unsigned long gfn); -extern int kvm_age_radix(struct kvm *kvm, struct kvm_memory_slot *memslot, - unsigned long gfn); -extern int kvm_test_age_radix(struct kvm *kvm, struct kvm_memory_slot *memslot, - unsigned long gfn); +extern void kvm_unmap_radix(struct kvm *kvm, struct kvm_memory_slot *memslot, + unsigned long gfn); +extern bool kvm_age_radix(struct kvm *kvm, struct kvm_memory_slot *memslot, + unsigned long gfn); +extern bool kvm_test_age_radix(struct kvm *kvm, struct kvm_memory_slot *memslot, + unsigned long gfn); extern long kvmppc_hv_get_dirty_log_radix(struct kvm *kvm, struct kvm_memory_slot *memslot, unsigned long *map); extern void kvmppc_radix_flush_memslot(struct kvm *kvm, @@ -234,7 +233,7 @@ extern void kvmppc_trigger_fac_interrupt(struct kvm_vcpu *vcpu, ulong fac); extern void kvmppc_set_bat(struct kvm_vcpu *vcpu, struct kvmppc_bat *bat, bool upper, u32 val); extern void kvmppc_giveup_ext(struct kvm_vcpu *vcpu, ulong msr); -extern int kvmppc_emulate_paired_single(struct kvm_run *run, struct kvm_vcpu *vcpu); +extern int kvmppc_emulate_paired_single(struct kvm_vcpu *vcpu); extern kvm_pfn_t kvmppc_gpa_to_pfn(struct kvm_vcpu *vcpu, gpa_t gpa, bool writing, bool *writable); extern void kvmppc_add_revmap_chain(struct kvm *kvm, struct revmap_entry *rev, @@ -260,6 +259,8 @@ extern long kvmppc_hv_get_dirty_log_hpt(struct kvm *kvm, extern void kvmppc_harvest_vpa_dirty(struct kvmppc_vpa *vpa, struct kvm_memory_slot *memslot, unsigned long *map); +extern unsigned long kvmppc_filter_lpcr_hv(struct kvm *kvm, + unsigned long lpcr); extern void kvmppc_update_lpcr(struct kvm *kvm, unsigned long lpcr, unsigned long mask); extern void kvmppc_set_fscr(struct kvm_vcpu *vcpu, u64 fscr); @@ -279,6 +280,10 @@ extern int kvmppc_hcall_impl_hv_realmode(unsigned long cmd); extern void kvmppc_copy_to_svcpu(struct kvm_vcpu *vcpu); extern void kvmppc_copy_from_svcpu(struct kvm_vcpu *vcpu); +long kvmppc_read_intr(void); +void kvmppc_set_msr_hv(struct kvm_vcpu *vcpu, u64 msr); +void kvmppc_inject_interrupt_hv(struct kvm_vcpu *vcpu, int vec, u64 srr1_flags); + #ifdef CONFIG_PPC_TRANSACTIONAL_MEM void kvmppc_save_tm_pr(struct kvm_vcpu *vcpu); void kvmppc_restore_tm_pr(struct kvm_vcpu *vcpu); @@ -291,24 +296,92 @@ static inline void kvmppc_save_tm_sprs(struct kvm_vcpu *vcpu) {} static inline void kvmppc_restore_tm_sprs(struct kvm_vcpu *vcpu) {} #endif +extern unsigned long nested_capabilities; long kvmhv_nested_init(void); void kvmhv_nested_exit(void); void kvmhv_vm_nested_init(struct kvm *kvm); long kvmhv_set_partition_table(struct kvm_vcpu *vcpu); long kvmhv_copy_tofrom_guest_nested(struct kvm_vcpu *vcpu); -void kvmhv_set_ptbl_entry(unsigned int lpid, u64 dw0, u64 dw1); +void kvmhv_flush_lpid(u64 lpid); +void kvmhv_set_ptbl_entry(u64 lpid, u64 dw0, u64 dw1); void kvmhv_release_all_nested(struct kvm *kvm); long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu); long kvmhv_do_nested_tlbie(struct kvm_vcpu *vcpu); -int kvmhv_run_single_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu, +long do_h_rpt_invalidate_pat(struct kvm_vcpu *vcpu, unsigned long lpid, + unsigned long type, unsigned long pg_sizes, + unsigned long start, unsigned long end); +int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpcr); void kvmhv_save_hv_regs(struct kvm_vcpu *vcpu, struct hv_guest_state *hr); void kvmhv_restore_hv_return_state(struct kvm_vcpu *vcpu, struct hv_guest_state *hr); -long int kvmhv_nested_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu); +long int kvmhv_nested_page_fault(struct kvm_vcpu *vcpu); void kvmppc_giveup_fac(struct kvm_vcpu *vcpu, ulong fac); + +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE + +extern struct static_key_false __kvmhv_is_nestedv2; + +static inline bool kvmhv_is_nestedv2(void) +{ + return static_branch_unlikely(&__kvmhv_is_nestedv2); +} + +static inline bool kvmhv_is_nestedv1(void) +{ + return !static_branch_likely(&__kvmhv_is_nestedv2); +} + +#else + +static inline bool kvmhv_is_nestedv2(void) +{ + return false; +} + +static inline bool kvmhv_is_nestedv1(void) +{ + return false; +} + +#endif + +int __kvmhv_nestedv2_reload_ptregs(struct kvm_vcpu *vcpu, struct pt_regs *regs); +int __kvmhv_nestedv2_mark_dirty_ptregs(struct kvm_vcpu *vcpu, struct pt_regs *regs); +int __kvmhv_nestedv2_mark_dirty(struct kvm_vcpu *vcpu, u16 iden); +int __kvmhv_nestedv2_cached_reload(struct kvm_vcpu *vcpu, u16 iden); + +static inline int kvmhv_nestedv2_reload_ptregs(struct kvm_vcpu *vcpu, + struct pt_regs *regs) +{ + if (kvmhv_is_nestedv2()) + return __kvmhv_nestedv2_reload_ptregs(vcpu, regs); + return 0; +} +static inline int kvmhv_nestedv2_mark_dirty_ptregs(struct kvm_vcpu *vcpu, + struct pt_regs *regs) +{ + if (kvmhv_is_nestedv2()) + return __kvmhv_nestedv2_mark_dirty_ptregs(vcpu, regs); + return 0; +} + +static inline int kvmhv_nestedv2_mark_dirty(struct kvm_vcpu *vcpu, u16 iden) +{ + if (kvmhv_is_nestedv2()) + return __kvmhv_nestedv2_mark_dirty(vcpu, iden); + return 0; +} + +static inline int kvmhv_nestedv2_cached_reload(struct kvm_vcpu *vcpu, u16 iden) +{ + if (kvmhv_is_nestedv2()) + return __kvmhv_nestedv2_cached_reload(vcpu, iden); + return 0; +} + extern int kvm_irq_bypass; static inline struct kvmppc_vcpu_book3s *to_book3s(struct kvm_vcpu *vcpu) @@ -328,60 +401,72 @@ static inline struct kvmppc_vcpu_book3s *to_book3s(struct kvm_vcpu *vcpu) static inline void kvmppc_set_gpr(struct kvm_vcpu *vcpu, int num, ulong val) { vcpu->arch.regs.gpr[num] = val; + kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_GPR(num)); } static inline ulong kvmppc_get_gpr(struct kvm_vcpu *vcpu, int num) { + WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, KVMPPC_GSID_GPR(num)) < 0); return vcpu->arch.regs.gpr[num]; } static inline void kvmppc_set_cr(struct kvm_vcpu *vcpu, u32 val) { vcpu->arch.regs.ccr = val; + kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_CR); } static inline u32 kvmppc_get_cr(struct kvm_vcpu *vcpu) { + WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, KVMPPC_GSID_CR) < 0); return vcpu->arch.regs.ccr; } static inline void kvmppc_set_xer(struct kvm_vcpu *vcpu, ulong val) { vcpu->arch.regs.xer = val; + kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_XER); } static inline ulong kvmppc_get_xer(struct kvm_vcpu *vcpu) { + WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, KVMPPC_GSID_XER) < 0); return vcpu->arch.regs.xer; } static inline void kvmppc_set_ctr(struct kvm_vcpu *vcpu, ulong val) { vcpu->arch.regs.ctr = val; + kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_CTR); } static inline ulong kvmppc_get_ctr(struct kvm_vcpu *vcpu) { + WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, KVMPPC_GSID_CTR) < 0); return vcpu->arch.regs.ctr; } static inline void kvmppc_set_lr(struct kvm_vcpu *vcpu, ulong val) { vcpu->arch.regs.link = val; + kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_LR); } static inline ulong kvmppc_get_lr(struct kvm_vcpu *vcpu) { + WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, KVMPPC_GSID_LR) < 0); return vcpu->arch.regs.link; } static inline void kvmppc_set_pc(struct kvm_vcpu *vcpu, ulong val) { vcpu->arch.regs.nip = val; + kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_NIA); } static inline ulong kvmppc_get_pc(struct kvm_vcpu *vcpu) { + WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, KVMPPC_GSID_NIA) < 0); return vcpu->arch.regs.nip; } @@ -396,6 +481,146 @@ static inline ulong kvmppc_get_fault_dar(struct kvm_vcpu *vcpu) return vcpu->arch.fault_dar; } +static inline u64 kvmppc_get_fpr(struct kvm_vcpu *vcpu, int i) +{ + WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, KVMPPC_GSID_VSRS(i)) < 0); + return vcpu->arch.fp.fpr[i][TS_FPROFFSET]; +} + +static inline void kvmppc_set_fpr(struct kvm_vcpu *vcpu, int i, u64 val) +{ + vcpu->arch.fp.fpr[i][TS_FPROFFSET] = val; + kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_VSRS(i)); +} + +static inline u64 kvmppc_get_fpscr(struct kvm_vcpu *vcpu) +{ + WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, KVMPPC_GSID_FPSCR) < 0); + return vcpu->arch.fp.fpscr; +} + +static inline void kvmppc_set_fpscr(struct kvm_vcpu *vcpu, u64 val) +{ + vcpu->arch.fp.fpscr = val; + kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_FPSCR); +} + + +static inline u64 kvmppc_get_vsx_fpr(struct kvm_vcpu *vcpu, int i, int j) +{ + WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, KVMPPC_GSID_VSRS(i)) < 0); + return vcpu->arch.fp.fpr[i][j]; +} + +static inline void kvmppc_set_vsx_fpr(struct kvm_vcpu *vcpu, int i, int j, + u64 val) +{ + vcpu->arch.fp.fpr[i][j] = val; + kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_VSRS(i)); +} + +#ifdef CONFIG_ALTIVEC +static inline void kvmppc_get_vsx_vr(struct kvm_vcpu *vcpu, int i, vector128 *v) +{ + WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, KVMPPC_GSID_VSRS(32 + i)) < 0); + *v = vcpu->arch.vr.vr[i]; +} + +static inline void kvmppc_set_vsx_vr(struct kvm_vcpu *vcpu, int i, + vector128 *val) +{ + vcpu->arch.vr.vr[i] = *val; + kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_VSRS(32 + i)); +} + +static inline u32 kvmppc_get_vscr(struct kvm_vcpu *vcpu) +{ + WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, KVMPPC_GSID_VSCR) < 0); + return vcpu->arch.vr.vscr.u[3]; +} + +static inline void kvmppc_set_vscr(struct kvm_vcpu *vcpu, u32 val) +{ + vcpu->arch.vr.vscr.u[3] = val; + kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_VSCR); +} +#endif + +#define KVMPPC_BOOK3S_VCPU_ACCESSOR_SET(reg, size, iden) \ +static inline void kvmppc_set_##reg(struct kvm_vcpu *vcpu, u##size val) \ +{ \ + \ + vcpu->arch.reg = val; \ + kvmhv_nestedv2_mark_dirty(vcpu, iden); \ +} + +#define KVMPPC_BOOK3S_VCPU_ACCESSOR_GET(reg, size, iden) \ +static inline u##size kvmppc_get_##reg(struct kvm_vcpu *vcpu) \ +{ \ + WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, iden) < 0); \ + return vcpu->arch.reg; \ +} + +#define KVMPPC_BOOK3S_VCPU_ACCESSOR(reg, size, iden) \ + KVMPPC_BOOK3S_VCPU_ACCESSOR_SET(reg, size, iden) \ + KVMPPC_BOOK3S_VCPU_ACCESSOR_GET(reg, size, iden) \ + +KVMPPC_BOOK3S_VCPU_ACCESSOR(pid, 32, KVMPPC_GSID_PIDR) +KVMPPC_BOOK3S_VCPU_ACCESSOR(tar, 64, KVMPPC_GSID_TAR) +KVMPPC_BOOK3S_VCPU_ACCESSOR(ebbhr, 64, KVMPPC_GSID_EBBHR) +KVMPPC_BOOK3S_VCPU_ACCESSOR(ebbrr, 64, KVMPPC_GSID_EBBRR) +KVMPPC_BOOK3S_VCPU_ACCESSOR(bescr, 64, KVMPPC_GSID_BESCR) +KVMPPC_BOOK3S_VCPU_ACCESSOR(ic, 64, KVMPPC_GSID_IC) +KVMPPC_BOOK3S_VCPU_ACCESSOR(vrsave, 64, KVMPPC_GSID_VRSAVE) + + +#define KVMPPC_BOOK3S_VCORE_ACCESSOR_SET(reg, size, iden) \ +static inline void kvmppc_set_##reg(struct kvm_vcpu *vcpu, u##size val) \ +{ \ + vcpu->arch.vcore->reg = val; \ + kvmhv_nestedv2_mark_dirty(vcpu, iden); \ +} + +#define KVMPPC_BOOK3S_VCORE_ACCESSOR_GET(reg, size, iden) \ +static inline u##size kvmppc_get_##reg(struct kvm_vcpu *vcpu) \ +{ \ + WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, iden) < 0); \ + return vcpu->arch.vcore->reg; \ +} + +#define KVMPPC_BOOK3S_VCORE_ACCESSOR(reg, size, iden) \ + KVMPPC_BOOK3S_VCORE_ACCESSOR_SET(reg, size, iden) \ + KVMPPC_BOOK3S_VCORE_ACCESSOR_GET(reg, size, iden) \ + + +KVMPPC_BOOK3S_VCORE_ACCESSOR(vtb, 64, KVMPPC_GSID_VTB) +KVMPPC_BOOK3S_VCORE_ACCESSOR_GET(arch_compat, 32, KVMPPC_GSID_LOGICAL_PVR) +KVMPPC_BOOK3S_VCORE_ACCESSOR_GET(lpcr, 64, KVMPPC_GSID_LPCR) +KVMPPC_BOOK3S_VCORE_ACCESSOR_SET(tb_offset, 64, KVMPPC_GSID_TB_OFFSET) + +static inline u64 kvmppc_get_tb_offset(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.vcore->tb_offset; +} + +static inline u64 kvmppc_get_dec_expires(struct kvm_vcpu *vcpu) +{ + WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, KVMPPC_GSID_DEC_EXPIRY_TB) < 0); + return vcpu->arch.dec_expires; +} + +static inline void kvmppc_set_dec_expires(struct kvm_vcpu *vcpu, u64 val) +{ + vcpu->arch.dec_expires = val; + kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_DEC_EXPIRY_TB); +} + +/* Expiry time of vcpu DEC relative to host TB */ +static inline u64 kvmppc_dec_expires_host_tb(struct kvm_vcpu *vcpu) +{ + return kvmppc_get_dec_expires(vcpu) - kvmppc_get_tb_offset(vcpu); +} + static inline bool is_kvmppc_resume_guest(int r) { return (r == RESUME_GUEST || r == RESUME_GUEST_NV); @@ -424,7 +649,7 @@ extern int kvmppc_h_logical_ci_store(struct kvm_vcpu *vcpu); #define SPLIT_HACK_OFFS 0xfb000000 /* - * This packs a VCPU ID from the [0..KVM_MAX_VCPU_ID) space down to the + * This packs a VCPU ID from the [0..KVM_MAX_VCPU_IDS) space down to the * [0..KVM_MAX_VCPUS) space, using knowledge of the guest's core stride * (but not its actual threading mode, which is not available) to avoid * collisions. diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h index 04b2b927bb5a..d8729ec81ca0 100644 --- a/arch/powerpc/include/asm/kvm_book3s_64.h +++ b/arch/powerpc/include/asm/kvm_book3s_64.h @@ -14,18 +14,7 @@ #include <asm/book3s/64/mmu-hash.h> #include <asm/cpu_has_feature.h> #include <asm/ppc-opcode.h> - -#ifdef CONFIG_PPC_PSERIES -static inline bool kvmhv_on_pseries(void) -{ - return !cpu_has_feature(CPU_FTR_HVMODE); -} -#else -static inline bool kvmhv_on_pseries(void) -{ - return false; -} -#endif +#include <asm/pte-walk.h> /* * Structure for a nested guest, that is, for a guest that is managed by @@ -42,7 +31,6 @@ struct kvm_nested_guest { struct mutex tlb_lock; /* serialize page faults and tlbies */ struct kvm_nested_guest *next; cpumask_t need_tlb_flush; - cpumask_t cpu_in_guest; short prev_cpu[NR_CPUS]; u8 radix; /* is this nested guest radix */ }; @@ -152,10 +140,20 @@ static inline bool kvmhv_vcpu_is_radix(struct kvm_vcpu *vcpu) return radix; } +unsigned long kvmppc_msr_hard_disable_set_facilities(struct kvm_vcpu *vcpu, unsigned long msr); + +int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpcr, u64 *tb); + #define KVM_DEFAULT_HPT_ORDER 24 /* 16MB HPT by default */ #endif /* + * Invalid HDSISR value which is used to indicate when HW has not set the reg. + * Used to work around an errata. + */ +#define HDSISR_CANARY 0x7fff + +/* * We use a lock bit in HPTE dword 0 to synchronize updates and * accesses to each HPTE, and another bit to indicate non-present * HPTEs. @@ -368,6 +366,10 @@ static inline unsigned long compute_tlbie_rb(unsigned long v, unsigned long r, rb |= 1; /* L field */ rb |= r & 0xff000 & ((1ul << a_pgshift) - 1); /* LP field */ } + /* + * This sets both bits of the B field in the PTE. 0b1x values are + * reserved, but those will have been filtered by kvmppc_do_h_enter. + */ rb |= (v >> HPTE_V_SSIZE_SHIFT) << 8; /* B field */ return rb; } @@ -434,7 +436,7 @@ static inline pte_t kvmppc_read_update_linux_pte(pte_t *ptep, int writing) continue; } /* If pte is not present return None */ - if (unlikely(!(pte_val(old_pte) & _PAGE_PRESENT))) + if (unlikely(!pte_present(old_pte))) return __pte(0); new_pte = pte_mkyoung(old_pte); @@ -622,7 +624,7 @@ static inline void copy_to_checkpoint(struct kvm_vcpu *vcpu) extern int kvmppc_create_pte(struct kvm *kvm, pgd_t *pgtable, pte_t pte, unsigned long gpa, unsigned int level, - unsigned long mmu_seq, unsigned int lpid, + unsigned long mmu_seq, u64 lpid, unsigned long *rmapp, struct rmap_nested **n_rmap); extern void kvmhv_insert_nest_rmap(struct kvm *kvm, unsigned long *rmapp, struct rmap_nested **n_rmap); @@ -634,6 +636,54 @@ extern void kvmhv_remove_nest_rmap_range(struct kvm *kvm, unsigned long gpa, unsigned long hpa, unsigned long nbytes); +static inline pte_t * +find_kvm_secondary_pte_unlocked(struct kvm *kvm, unsigned long ea, + unsigned *hshift) +{ + pte_t *pte; + + pte = __find_linux_pte(kvm->arch.pgtable, ea, NULL, hshift); + return pte; +} + +static inline pte_t *find_kvm_secondary_pte(struct kvm *kvm, unsigned long ea, + unsigned *hshift) +{ + pte_t *pte; + + VM_WARN(!spin_is_locked(&kvm->mmu_lock), + "%s called with kvm mmu_lock not held \n", __func__); + pte = __find_linux_pte(kvm->arch.pgtable, ea, NULL, hshift); + + return pte; +} + +static inline pte_t *find_kvm_host_pte(struct kvm *kvm, unsigned long mmu_seq, + unsigned long ea, unsigned *hshift) +{ + pte_t *pte; + + VM_WARN(!spin_is_locked(&kvm->mmu_lock), + "%s called with kvm mmu_lock not held \n", __func__); + + if (mmu_invalidate_retry(kvm, mmu_seq)) + return NULL; + + pte = __find_linux_pte(kvm->mm->pgd, ea, NULL, hshift); + + return pte; +} + +extern pte_t *find_kvm_nested_guest_pte(struct kvm *kvm, unsigned long lpid, + unsigned long ea, unsigned *hshift); + +int kvmhv_nestedv2_vcpu_create(struct kvm_vcpu *vcpu, struct kvmhv_nestedv2_io *io); +void kvmhv_nestedv2_vcpu_free(struct kvm_vcpu *vcpu, struct kvmhv_nestedv2_io *io); +int kvmhv_nestedv2_flush_vcpu(struct kvm_vcpu *vcpu, u64 time_limit); +int kvmhv_nestedv2_set_ptbl_entry(unsigned long lpid, u64 dw0, u64 dw1); +int kvmhv_nestedv2_parse_output(struct kvm_vcpu *vcpu); +int kvmhv_nestedv2_set_vpa(struct kvm_vcpu *vcpu, unsigned long vpa); + #endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */ #endif /* __ASM_KVM_BOOK3S_64_H__ */ diff --git a/arch/powerpc/include/asm/kvm_book3s_asm.h b/arch/powerpc/include/asm/kvm_book3s_asm.h index 45704f2716e2..a36797938620 100644 --- a/arch/powerpc/include/asm/kvm_book3s_asm.h +++ b/arch/powerpc/include/asm/kvm_book3s_asm.h @@ -14,9 +14,6 @@ #define XICS_MFRR 0xc #define XICS_IPI 2 /* interrupt source # for IPIs */ -/* LPIDs we support with this build -- runtime limit may be lower */ -#define KVMPPC_NR_LPIDS (LPID_RSVD + 1) - /* Maximum number of threads per physical core */ #define MAX_SMT_THREADS 8 @@ -74,16 +71,6 @@ struct kvm_split_mode { u8 do_nap; u8 napped[MAX_SMT_THREADS]; struct kvmppc_vcore *vc[MAX_SUBCORES]; - /* Bits for changing lpcr on P9 */ - unsigned long lpcr_req; - unsigned long lpidr_req; - unsigned long host_lpcr; - u32 do_set; - u32 do_restore; - union { - u32 allphases; - u8 phase[4]; - } lpcr_sync; }; /* @@ -110,7 +97,6 @@ struct kvmppc_host_state { u8 hwthread_state; u8 host_ipi; u8 ptid; /* thread number within subcore when split */ - u8 tid; /* thread number within whole core */ u8 fake_suspend; struct kvm_vcpu *kvm_vcpu; struct kvmppc_vcore *kvm_vcore; diff --git a/arch/powerpc/include/asm/kvm_book3s_uvmem.h b/arch/powerpc/include/asm/kvm_book3s_uvmem.h index 50204e228f16..0a6319448cb6 100644 --- a/arch/powerpc/include/asm/kvm_book3s_uvmem.h +++ b/arch/powerpc/include/asm/kvm_book3s_uvmem.h @@ -5,6 +5,7 @@ #ifdef CONFIG_PPC_UV int kvmppc_uvmem_init(void); void kvmppc_uvmem_free(void); +bool kvmppc_uvmem_available(void); int kvmppc_uvmem_slot_init(struct kvm *kvm, const struct kvm_memory_slot *slot); void kvmppc_uvmem_slot_free(struct kvm *kvm, const struct kvm_memory_slot *slot); @@ -19,8 +20,13 @@ unsigned long kvmppc_h_svm_page_out(struct kvm *kvm, unsigned long kvmppc_h_svm_init_start(struct kvm *kvm); unsigned long kvmppc_h_svm_init_done(struct kvm *kvm); int kvmppc_send_page_to_uv(struct kvm *kvm, unsigned long gfn); +unsigned long kvmppc_h_svm_init_abort(struct kvm *kvm); void kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *free, - struct kvm *kvm); + struct kvm *kvm, bool skip_page_out); +int kvmppc_uvmem_memslot_create(struct kvm *kvm, + const struct kvm_memory_slot *new); +void kvmppc_uvmem_memslot_delete(struct kvm *kvm, + const struct kvm_memory_slot *old); #else static inline int kvmppc_uvmem_init(void) { @@ -29,6 +35,11 @@ static inline int kvmppc_uvmem_init(void) static inline void kvmppc_uvmem_free(void) { } +static inline bool kvmppc_uvmem_available(void) +{ + return false; +} + static inline int kvmppc_uvmem_slot_init(struct kvm *kvm, const struct kvm_memory_slot *slot) { @@ -62,6 +73,11 @@ static inline unsigned long kvmppc_h_svm_init_done(struct kvm *kvm) return H_UNSUPPORTED; } +static inline unsigned long kvmppc_h_svm_init_abort(struct kvm *kvm) +{ + return H_UNSUPPORTED; +} + static inline int kvmppc_send_page_to_uv(struct kvm *kvm, unsigned long gfn) { return -EFAULT; @@ -69,6 +85,16 @@ static inline int kvmppc_send_page_to_uv(struct kvm *kvm, unsigned long gfn) static inline void kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *free, - struct kvm *kvm) { } + struct kvm *kvm, bool skip_page_out) { } + +static inline int kvmppc_uvmem_memslot_create(struct kvm *kvm, + const struct kvm_memory_slot *new) +{ + return H_UNSUPPORTED; +} + +static inline void kvmppc_uvmem_memslot_delete(struct kvm *kvm, + const struct kvm_memory_slot *old) { } + #endif /* CONFIG_PPC_UV */ #endif /* __ASM_KVM_BOOK3S_UVMEM_H__ */ diff --git a/arch/powerpc/include/asm/kvm_booke.h b/arch/powerpc/include/asm/kvm_booke.h index 310ba48d13f0..7c3291aa8922 100644 --- a/arch/powerpc/include/asm/kvm_booke.h +++ b/arch/powerpc/include/asm/kvm_booke.h @@ -89,10 +89,22 @@ static inline ulong kvmppc_get_pc(struct kvm_vcpu *vcpu) return vcpu->arch.regs.nip; } +static inline void kvmppc_set_fpr(struct kvm_vcpu *vcpu, int i, u64 val) +{ + vcpu->arch.fp.fpr[i][TS_FPROFFSET] = val; +} + +static inline u64 kvmppc_get_fpr(struct kvm_vcpu *vcpu, int i) +{ + return vcpu->arch.fp.fpr[i][TS_FPROFFSET]; +} + +#ifdef CONFIG_BOOKE static inline ulong kvmppc_get_fault_dar(struct kvm_vcpu *vcpu) { return vcpu->arch.fault_dear; } +#endif static inline bool kvmppc_supports_magic_page(struct kvm_vcpu *vcpu) { diff --git a/arch/powerpc/include/asm/kvm_guest.h b/arch/powerpc/include/asm/kvm_guest.h new file mode 100644 index 000000000000..68e499abdb24 --- /dev/null +++ b/arch/powerpc/include/asm/kvm_guest.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2020 IBM Corporation + */ + +#ifndef _ASM_POWERPC_KVM_GUEST_H_ +#define _ASM_POWERPC_KVM_GUEST_H_ + +#if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_KVM_GUEST) +#include <linux/jump_label.h> + +DECLARE_STATIC_KEY_FALSE(kvm_guest); + +static inline bool is_kvm_guest(void) +{ + return static_branch_unlikely(&kvm_guest); +} + +int __init check_kvm_guest(void); +#else +static inline bool is_kvm_guest(void) { return false; } +static inline int check_kvm_guest(void) { return 0; } +#endif + +#endif /* _ASM_POWERPC_KVM_GUEST_H_ */ diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 0a398f2321c2..8abac532146e 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -25,20 +25,27 @@ #include <asm/cacheflush.h> #include <asm/hvcall.h> #include <asm/mce.h> +#include <asm/guest-state-buffer.h> + +#define __KVM_HAVE_ARCH_VCPU_DEBUGFS #define KVM_MAX_VCPUS NR_CPUS #define KVM_MAX_VCORES NR_CPUS -#define KVM_USER_MEM_SLOTS 512 #include <asm/cputhreads.h> #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE #include <asm/kvm_book3s_asm.h> /* for MAX_SMT_THREADS */ -#define KVM_MAX_VCPU_ID (MAX_SMT_THREADS * KVM_MAX_VCORES) -#define KVM_MAX_NESTED_GUESTS KVMPPC_NR_LPIDS +#define KVM_MAX_VCPU_IDS (MAX_SMT_THREADS * KVM_MAX_VCORES) + +/* + * Limit the nested partition table to 4096 entries (because that's what + * hardware supports). Both guest and host use this value. + */ +#define KVM_MAX_NESTED_GUESTS_SHIFT 12 #else -#define KVM_MAX_VCPU_ID KVM_MAX_VCPUS +#define KVM_MAX_VCPU_IDS KVM_MAX_VCPUS #endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */ #define __KVM_HAVE_ARCH_INTC_INITIALIZED @@ -52,17 +59,10 @@ /* PPC-specific vcpu->requests bit members */ #define KVM_REQ_WATCHDOG KVM_ARCH_REQ(0) #define KVM_REQ_EPR_EXIT KVM_ARCH_REQ(1) +#define KVM_REQ_PENDING_TIMER KVM_ARCH_REQ(2) #include <linux/mmu_notifier.h> -#define KVM_ARCH_WANT_MMU_NOTIFIER - -extern int kvm_unmap_hva_range(struct kvm *kvm, - unsigned long start, unsigned long end); -extern int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end); -extern int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); -extern int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); - #define HPTEG_CACHE_NUM (1 << 15) #define HPTEG_HASH_BITS_PTE 13 #define HPTEG_HASH_BITS_PTE_LONG 12 @@ -87,12 +87,13 @@ struct kvmppc_book3s_shadow_vcpu; struct kvm_nested_guest; struct kvm_vm_stat { - ulong remote_tlb_flush; - ulong num_2M_pages; - ulong num_1G_pages; + struct kvm_vm_stat_generic generic; + u64 num_2M_pages; + u64 num_1G_pages; }; struct kvm_vcpu_stat { + struct kvm_vcpu_stat_generic generic; u64 sum_exits; u64 mmio_exits; u64 signal_exits; @@ -108,14 +109,7 @@ struct kvm_vcpu_stat { u64 emulated_inst_exits; u64 dec_exits; u64 ext_intr_exits; - u64 halt_poll_success_ns; - u64 halt_poll_fail_ns; - u64 halt_wait_ns; - u64 halt_successful_poll; - u64 halt_attempted_poll; u64 halt_successful_wait; - u64 halt_poll_invalid; - u64 halt_wakeup; u64 dbell_exits; u64 gdbell_exits; u64 ld; @@ -202,7 +196,7 @@ struct kvmppc_spapr_tce_table { u64 size; /* window size in pages */ struct list_head iommu_tables; struct mutex alloc_lock; - struct page *pages[0]; + struct page *pages[]; }; /* XICS components, defined in book3s_xics.c */ @@ -278,9 +272,10 @@ struct kvm_resize_hpt; /* Flag values for kvm_arch.secure_guest */ #define KVMPPC_SECURE_INIT_START 0x1 /* H_SVM_INIT_START has been called */ #define KVMPPC_SECURE_INIT_DONE 0x2 /* H_SVM_INIT_DONE completed */ +#define KVMPPC_SECURE_INIT_ABORT 0x4 /* H_SVM_INIT_ABORT issued */ struct kvm_arch { - unsigned int lpid; + u64 lpid; unsigned int smt_mode; /* # vcpus per virtual core */ unsigned int emul_smt_mode; /* emualted SMT mode, on P9 */ #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE @@ -298,17 +293,14 @@ struct kvm_arch { u32 online_vcores; atomic_t hpte_mod_interest; cpumask_t need_tlb_flush; - cpumask_t cpu_in_guest; u8 radix; u8 fwnmi_enabled; u8 secure_guest; - bool threads_indep; + u8 svm_enabled; bool nested_enable; + bool dawr1_enabled; pgd_t *pgtable; u64 process_table; - struct dentry *debugfs_dir; - struct dentry *htab_dentry; - struct dentry *radix_dentry; struct kvm_resize_hpt *resize_hpt; /* protected by kvm->lock */ #endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */ #ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE @@ -325,6 +317,7 @@ struct kvm_arch { #endif #ifdef CONFIG_KVM_XICS struct kvmppc_xics *xics; + struct kvmppc_xics *xics_device; struct kvmppc_xive *xive; /* Current XIVE device in use */ struct { struct kvmppc_xive *native; @@ -338,8 +331,7 @@ struct kvm_arch { struct list_head uvmem_pfns; struct mutex mmu_setup_lock; /* nests inside vcpu mutexes */ u64 l1_ptcr; - int max_nested_lpid; - struct kvm_nested_guest *nested_guests[KVM_MAX_NESTED_GUESTS]; + struct idr kvm_nested_guest_idr; /* This array can grow quite large, keep it at the end */ struct kvmppc_vcore *vcores[KVM_MAX_VCORES]; #endif @@ -450,7 +442,7 @@ struct kvmppc_passthru_irqmap { }; #endif -# ifdef CONFIG_PPC_FSL_BOOK3E +# ifdef CONFIG_PPC_E500 #define KVMPPC_BOOKE_IAC_NUM 2 #define KVMPPC_BOOKE_DAC_NUM 2 # else @@ -516,6 +508,23 @@ union xive_tma_w01 { __be64 w01; }; + /* Nestedv2 H_GUEST_RUN_VCPU configuration */ +struct kvmhv_nestedv2_config { + struct kvmppc_gs_buff_info vcpu_run_output_cfg; + struct kvmppc_gs_buff_info vcpu_run_input_cfg; + u64 vcpu_run_output_size; +}; + + /* Nestedv2 L1<->L0 communication state */ +struct kvmhv_nestedv2_io { + struct kvmhv_nestedv2_config cfg; + struct kvmppc_gs_buff *vcpu_run_output; + struct kvmppc_gs_buff *vcpu_run_input; + struct kvmppc_gs_msg *vcpu_message; + struct kvmppc_gs_msg *vcore_message; + struct kvmppc_gs_bitmap valids; +}; + struct kvm_vcpu_arch { ulong host_stack; u32 host_pid; @@ -530,7 +539,11 @@ struct kvm_vcpu_arch { struct kvmppc_book3s_shadow_vcpu *shadow_vcpu; #endif - struct pt_regs regs; + /* + * This is passed along to the HV via H_ENTER_NESTED. Align to + * prevent it crossing a real 4K page. + */ + struct pt_regs regs __aligned(512); struct thread_fp_state fp; @@ -582,12 +595,18 @@ struct kvm_vcpu_arch { u32 ctrl; u32 dabrx; ulong dabr; - ulong dawr; - ulong dawrx; + ulong dawr0; + ulong dawrx0; + ulong dawr1; + ulong dawrx1; ulong ciabr; ulong cfar; ulong ppr; u32 pspb; + u8 load_ebb; +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + u8 load_tm; +#endif ulong fscr; ulong shadow_fscr; ulong ebbhr; @@ -637,12 +656,14 @@ struct kvm_vcpu_arch { u32 ccr1; u32 dbsr; - u64 mmcr[5]; + u64 mmcr[4]; /* MMCR0, MMCR1, MMCR2, MMCR3 */ + u64 mmcra; + u64 mmcrs; u32 pmc[8]; u32 spmc[2]; u64 siar; u64 sdar; - u64 sier; + u64 sier[3]; #ifdef CONFIG_PPC_TRANSACTIONAL_MEM u64 tfhar; u64 texasr; @@ -677,14 +698,18 @@ struct kvm_vcpu_arch { u64 timing_min_duration[__NUMBER_OF_KVM_EXIT_TYPES]; u64 timing_max_duration[__NUMBER_OF_KVM_EXIT_TYPES]; u64 timing_last_exit; - struct dentry *debugfs_exit_timing; #endif #ifdef CONFIG_PPC_BOOK3S ulong fault_dar; u32 fault_dsisr; unsigned long intr_msr; - ulong fault_gpa; /* guest real address of page fault (POWER9) */ + /* + * POWER9 and later: fault_gpa contains the guest real address of page + * fault for a radix guest, or segment descriptor (equivalent to result + * from slbmfev of SLB entry that translated the EA) for hash guests. + */ + ulong fault_gpa; #endif #ifdef CONFIG_BOOKE @@ -743,15 +768,16 @@ struct kvm_vcpu_arch { struct hrtimer dec_timer; u64 dec_jiffies; - u64 dec_expires; + u64 dec_expires; /* Relative to guest timebase. */ unsigned long pending_exceptions; u8 ceded; u8 prodded; u8 doorbell_request; u8 irq_pending; /* Used by XIVE to signal pending guest irqs */ - u32 last_inst; + unsigned long last_inst; - struct swait_queue_head *wqp; + struct rcuwait wait; + struct rcuwait *waitp; struct kvmppc_vcore *vcore; int ret; int trap; @@ -795,7 +821,6 @@ struct kvm_vcpu_arch { struct mmio_hpte_cache_entry *pgfault_cache; struct task_struct *run_task; - struct kvm_run *kvm_run; spinlock_t vpa_update_lock; struct kvmppc_vpa vpa; @@ -809,27 +834,39 @@ struct kvm_vcpu_arch { u64 busy_stolen; u64 busy_preempt; - u32 emul_inst; + u64 emul_inst; u32 online; + u64 hfscr_permitted; /* A mask of permitted HFSCR facilities */ + /* For support of nested guests */ struct kvm_nested_guest *nested; + u64 nested_hfscr; /* HFSCR that the L1 requested for the nested guest */ u32 nested_vcpu_id; gpa_t nested_io_gpr; + /* For nested APIv2 guests*/ + struct kvmhv_nestedv2_io nestedv2_io; #endif #ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING struct kvmhv_tb_accumulator *cur_activity; /* What we're timing */ u64 cur_tb_start; /* when it started */ +#ifdef CONFIG_KVM_BOOK3S_HV_P9_TIMING + struct kvmhv_tb_accumulator vcpu_entry; + struct kvmhv_tb_accumulator vcpu_exit; + struct kvmhv_tb_accumulator in_guest; + struct kvmhv_tb_accumulator hcall; + struct kvmhv_tb_accumulator pg_fault; + struct kvmhv_tb_accumulator guest_entry; + struct kvmhv_tb_accumulator guest_exit; +#else struct kvmhv_tb_accumulator rm_entry; /* real-mode entry code */ struct kvmhv_tb_accumulator rm_intr; /* real-mode intr handling */ struct kvmhv_tb_accumulator rm_exit; /* real-mode exit code */ struct kvmhv_tb_accumulator guest_time; /* guest execution */ struct kvmhv_tb_accumulator cede_time; /* time napping inside guest */ - - struct dentry *debugfs_dir; - struct dentry *debugfs_timings; +#endif #endif /* CONFIG_KVM_BOOK3S_HV_EXIT_TIMING */ }; @@ -857,15 +894,11 @@ struct kvm_vcpu_arch { #define __KVM_HAVE_ARCH_WQP #define __KVM_HAVE_CREATE_DEVICE -static inline void kvm_arch_hardware_disable(void) {} -static inline void kvm_arch_hardware_unsetup(void) {} static inline void kvm_arch_sync_events(struct kvm *kvm) {} static inline void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) {} static inline void kvm_arch_flush_shadow_all(struct kvm *kvm) {} static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {} -static inline void kvm_arch_exit(void) {} static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) {} static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) {} -static inline void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) {} #endif /* __POWERPC_KVM_HOST_H__ */ diff --git a/arch/powerpc/include/asm/kvm_para.h b/arch/powerpc/include/asm/kvm_para.h index 9c1f6b4b9bbf..abe1b5e82547 100644 --- a/arch/powerpc/include/asm/kvm_para.h +++ b/arch/powerpc/include/asm/kvm_para.h @@ -8,35 +8,15 @@ #ifndef __POWERPC_KVM_PARA_H__ #define __POWERPC_KVM_PARA_H__ -#include <uapi/asm/kvm_para.h> - -#ifdef CONFIG_KVM_GUEST - -#include <linux/of.h> - -static inline int kvm_para_available(void) -{ - struct device_node *hyper_node; - - hyper_node = of_find_node_by_path("/hypervisor"); - if (!hyper_node) - return 0; +#include <asm/kvm_guest.h> - if (!of_device_is_compatible(hyper_node, "linux,kvm")) - return 0; - - return 1; -} - -#else +#include <uapi/asm/kvm_para.h> static inline int kvm_para_available(void) { - return 0; + return IS_ENABLED(CONFIG_KVM_GUEST) && is_kvm_guest(); } -#endif - static inline unsigned int kvm_arch_para_features(void) { unsigned long r; diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index 3d2f871241a8..3281215097cc 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -28,6 +28,7 @@ #include <asm/xive.h> #include <asm/cpu_has_feature.h> #endif +#include <asm/inst.h> /* * KVMPPC_INST_SW_BREAKPOINT is debug Instruction @@ -58,42 +59,42 @@ enum xlate_readwrite { XLATE_WRITE /* check for write permissions */ }; -extern int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu); -extern int __kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu); +extern int kvmppc_vcpu_run(struct kvm_vcpu *vcpu); +extern int __kvmppc_vcpu_run(struct kvm_vcpu *vcpu); extern void kvmppc_handler_highmem(void); extern void kvmppc_dump_vcpu(struct kvm_vcpu *vcpu); -extern int kvmppc_handle_load(struct kvm_run *run, struct kvm_vcpu *vcpu, +extern int kvmppc_handle_load(struct kvm_vcpu *vcpu, unsigned int rt, unsigned int bytes, int is_default_endian); -extern int kvmppc_handle_loads(struct kvm_run *run, struct kvm_vcpu *vcpu, +extern int kvmppc_handle_loads(struct kvm_vcpu *vcpu, unsigned int rt, unsigned int bytes, int is_default_endian); -extern int kvmppc_handle_vsx_load(struct kvm_run *run, struct kvm_vcpu *vcpu, +extern int kvmppc_handle_vsx_load(struct kvm_vcpu *vcpu, unsigned int rt, unsigned int bytes, int is_default_endian, int mmio_sign_extend); -extern int kvmppc_handle_vmx_load(struct kvm_run *run, struct kvm_vcpu *vcpu, +extern int kvmppc_handle_vmx_load(struct kvm_vcpu *vcpu, unsigned int rt, unsigned int bytes, int is_default_endian); -extern int kvmppc_handle_vmx_store(struct kvm_run *run, struct kvm_vcpu *vcpu, +extern int kvmppc_handle_vmx_store(struct kvm_vcpu *vcpu, unsigned int rs, unsigned int bytes, int is_default_endian); -extern int kvmppc_handle_store(struct kvm_run *run, struct kvm_vcpu *vcpu, +extern int kvmppc_handle_store(struct kvm_vcpu *vcpu, u64 val, unsigned int bytes, int is_default_endian); -extern int kvmppc_handle_vsx_store(struct kvm_run *run, struct kvm_vcpu *vcpu, +extern int kvmppc_handle_vsx_store(struct kvm_vcpu *vcpu, int rs, unsigned int bytes, int is_default_endian); extern int kvmppc_load_last_inst(struct kvm_vcpu *vcpu, - enum instruction_fetch_type type, u32 *inst); + enum instruction_fetch_type type, + unsigned long *inst); extern int kvmppc_ld(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr, bool data); extern int kvmppc_st(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr, bool data); -extern int kvmppc_emulate_instruction(struct kvm_run *run, - struct kvm_vcpu *vcpu); +extern int kvmppc_emulate_instruction(struct kvm_vcpu *vcpu); extern int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu); -extern int kvmppc_emulate_mmio(struct kvm_run *run, struct kvm_vcpu *vcpu); +extern int kvmppc_emulate_mmio(struct kvm_vcpu *vcpu); extern void kvmppc_emulate_dec(struct kvm_vcpu *vcpu); extern u32 kvmppc_get_dec(struct kvm_vcpu *vcpu, u64 tb); extern void kvmppc_decrementer_func(struct kvm_vcpu *vcpu); @@ -105,10 +106,7 @@ extern void kvmppc_subarch_vcpu_uninit(struct kvm_vcpu *vcpu); extern void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 gvaddr, gpa_t gpaddr, unsigned int gtlb_idx); -extern void kvmppc_mmu_priv_switch(struct kvm_vcpu *vcpu, int usermode); extern void kvmppc_mmu_switch_pid(struct kvm_vcpu *vcpu, u32 pid); -extern void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu); -extern int kvmppc_mmu_init(struct kvm_vcpu *vcpu); extern int kvmppc_mmu_dtlb_index(struct kvm_vcpu *vcpu, gva_t eaddr); extern int kvmppc_mmu_itlb_index(struct kvm_vcpu *vcpu, gva_t eaddr); extern gpa_t kvmppc_mmu_xlate(struct kvm_vcpu *vcpu, unsigned int gtlb_index, @@ -119,11 +117,9 @@ extern int kvmppc_xlate(struct kvm_vcpu *vcpu, ulong eaddr, enum xlate_instdata xlid, enum xlate_readwrite xlrw, struct kvmppc_pte *pte); -extern struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, - unsigned int id); +extern int kvmppc_core_vcpu_create(struct kvm_vcpu *vcpu); extern void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu); extern int kvmppc_core_vcpu_setup(struct kvm_vcpu *vcpu); -extern int kvmppc_core_check_processor_compat(void); extern int kvmppc_core_vcpu_translate(struct kvm_vcpu *vcpu, struct kvm_translation *tr); @@ -132,41 +128,48 @@ extern void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu); extern int kvmppc_core_prepare_to_enter(struct kvm_vcpu *vcpu); extern int kvmppc_core_pending_dec(struct kvm_vcpu *vcpu); -extern void kvmppc_core_queue_machine_check(struct kvm_vcpu *vcpu, ulong flags); -extern void kvmppc_core_queue_program(struct kvm_vcpu *vcpu, ulong flags); -extern void kvmppc_core_queue_fpunavail(struct kvm_vcpu *vcpu); -extern void kvmppc_core_queue_vec_unavail(struct kvm_vcpu *vcpu); -extern void kvmppc_core_queue_vsx_unavail(struct kvm_vcpu *vcpu); + +extern void kvmppc_core_queue_machine_check(struct kvm_vcpu *vcpu, + ulong srr1_flags); +extern void kvmppc_core_queue_syscall(struct kvm_vcpu *vcpu); +extern void kvmppc_core_queue_program(struct kvm_vcpu *vcpu, + ulong srr1_flags); +extern void kvmppc_core_queue_fpunavail(struct kvm_vcpu *vcpu, + ulong srr1_flags); +extern void kvmppc_core_queue_vec_unavail(struct kvm_vcpu *vcpu, + ulong srr1_flags); +extern void kvmppc_core_queue_vsx_unavail(struct kvm_vcpu *vcpu, + ulong srr1_flags); extern void kvmppc_core_queue_dec(struct kvm_vcpu *vcpu); extern void kvmppc_core_dequeue_dec(struct kvm_vcpu *vcpu); extern void kvmppc_core_queue_external(struct kvm_vcpu *vcpu, struct kvm_interrupt *irq); extern void kvmppc_core_dequeue_external(struct kvm_vcpu *vcpu); -extern void kvmppc_core_queue_dtlb_miss(struct kvm_vcpu *vcpu, ulong dear_flags, +extern void kvmppc_core_queue_dtlb_miss(struct kvm_vcpu *vcpu, + ulong dear_flags, ulong esr_flags); extern void kvmppc_core_queue_data_storage(struct kvm_vcpu *vcpu, - ulong dear_flags, - ulong esr_flags); + ulong srr1_flags, + ulong dar, + ulong dsisr); extern void kvmppc_core_queue_itlb_miss(struct kvm_vcpu *vcpu); extern void kvmppc_core_queue_inst_storage(struct kvm_vcpu *vcpu, - ulong esr_flags); + ulong srr1_flags); + extern void kvmppc_core_flush_tlb(struct kvm_vcpu *vcpu); extern int kvmppc_core_check_requests(struct kvm_vcpu *vcpu); extern int kvmppc_booke_init(void); extern void kvmppc_booke_exit(void); -extern void kvmppc_core_destroy_mmu(struct kvm_vcpu *vcpu); extern int kvmppc_kvm_pv(struct kvm_vcpu *vcpu); extern void kvmppc_map_magic(struct kvm_vcpu *vcpu); extern int kvmppc_allocate_hpt(struct kvm_hpt_info *info, u32 order); extern void kvmppc_set_hpt(struct kvm *kvm, struct kvm_hpt_info *info); -extern long kvmppc_alloc_reset_hpt(struct kvm *kvm, int order); +extern int kvmppc_alloc_reset_hpt(struct kvm *kvm, int order); extern void kvmppc_free_hpt(struct kvm_hpt_info *info); extern void kvmppc_rmap_reset(struct kvm *kvm); -extern long kvmppc_prepare_vrma(struct kvm *kvm, - struct kvm_userspace_memory_region *mem); extern void kvmppc_map_vrma(struct kvm_vcpu *vcpu, struct kvm_memory_slot *memslot, unsigned long porder); extern int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu); @@ -178,10 +181,8 @@ extern int kvmppc_switch_mmu_to_hpt(struct kvm *kvm); extern int kvmppc_switch_mmu_to_radix(struct kvm *kvm); extern void kvmppc_setup_partition_table(struct kvm *kvm); -extern long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm, +extern int kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm, struct kvm_create_spapr_tce_64 *args); -extern struct kvmppc_spapr_tce_table *kvmppc_find_table( - struct kvm *kvm, unsigned long liobn); #define kvmppc_ioba_validate(stt, ioba, npages) \ (iommu_tce_check_ioba((stt)->page_shift, (stt)->offset, \ (stt)->size, (ioba), (npages)) ? \ @@ -201,17 +202,13 @@ extern void kvm_free_hpt_cma(struct page *page, unsigned long nr_pages); extern int kvmppc_core_init_vm(struct kvm *kvm); extern void kvmppc_core_destroy_vm(struct kvm *kvm); extern void kvmppc_core_free_memslot(struct kvm *kvm, - struct kvm_memory_slot *free, - struct kvm_memory_slot *dont); -extern int kvmppc_core_create_memslot(struct kvm *kvm, - struct kvm_memory_slot *slot, - unsigned long npages); + struct kvm_memory_slot *slot); extern int kvmppc_core_prepare_memory_region(struct kvm *kvm, - struct kvm_memory_slot *memslot, - const struct kvm_userspace_memory_region *mem); -extern void kvmppc_core_commit_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem, const struct kvm_memory_slot *old, + struct kvm_memory_slot *new, + enum kvm_mr_change change); +extern void kvmppc_core_commit_memory_region(struct kvm *kvm, + struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change); extern int kvm_vm_ioctl_get_smmu_info(struct kvm *kvm, @@ -225,10 +222,10 @@ extern void kvmppc_bookehv_exit(void); extern int kvmppc_prepare_to_enter(struct kvm_vcpu *vcpu); extern int kvm_vm_ioctl_get_htab_fd(struct kvm *kvm, struct kvm_get_htab_fd *); -extern long kvm_vm_ioctl_resize_hpt_prepare(struct kvm *kvm, - struct kvm_ppc_resize_hpt *rhpt); -extern long kvm_vm_ioctl_resize_hpt_commit(struct kvm *kvm, +extern int kvm_vm_ioctl_resize_hpt_prepare(struct kvm *kvm, struct kvm_ppc_resize_hpt *rhpt); +extern int kvm_vm_ioctl_resize_hpt_commit(struct kvm *kvm, + struct kvm_ppc_resize_hpt *rhpt); int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, struct kvm_interrupt *irq); @@ -273,40 +270,35 @@ struct kvmppc_ops { void (*vcpu_put)(struct kvm_vcpu *vcpu); void (*inject_interrupt)(struct kvm_vcpu *vcpu, int vec, u64 srr1_flags); void (*set_msr)(struct kvm_vcpu *vcpu, u64 msr); - int (*vcpu_run)(struct kvm_run *run, struct kvm_vcpu *vcpu); - struct kvm_vcpu *(*vcpu_create)(struct kvm *kvm, unsigned int id); + int (*vcpu_run)(struct kvm_vcpu *vcpu); + int (*vcpu_create)(struct kvm_vcpu *vcpu); void (*vcpu_free)(struct kvm_vcpu *vcpu); int (*check_requests)(struct kvm_vcpu *vcpu); int (*get_dirty_log)(struct kvm *kvm, struct kvm_dirty_log *log); void (*flush_memslot)(struct kvm *kvm, struct kvm_memory_slot *memslot); int (*prepare_memory_region)(struct kvm *kvm, - struct kvm_memory_slot *memslot, - const struct kvm_userspace_memory_region *mem); - void (*commit_memory_region)(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem, const struct kvm_memory_slot *old, + struct kvm_memory_slot *new, + enum kvm_mr_change change); + void (*commit_memory_region)(struct kvm *kvm, + struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change); - int (*unmap_hva_range)(struct kvm *kvm, unsigned long start, - unsigned long end); - int (*age_hva)(struct kvm *kvm, unsigned long start, unsigned long end); - int (*test_age_hva)(struct kvm *kvm, unsigned long hva); - void (*set_spte_hva)(struct kvm *kvm, unsigned long hva, pte_t pte); - void (*mmu_destroy)(struct kvm_vcpu *vcpu); - void (*free_memslot)(struct kvm_memory_slot *free, - struct kvm_memory_slot *dont); - int (*create_memslot)(struct kvm_memory_slot *slot, - unsigned long npages); + bool (*unmap_gfn_range)(struct kvm *kvm, struct kvm_gfn_range *range); + bool (*age_gfn)(struct kvm *kvm, struct kvm_gfn_range *range); + bool (*test_age_gfn)(struct kvm *kvm, struct kvm_gfn_range *range); + bool (*set_spte_gfn)(struct kvm *kvm, struct kvm_gfn_range *range); + void (*free_memslot)(struct kvm_memory_slot *slot); int (*init_vm)(struct kvm *kvm); void (*destroy_vm)(struct kvm *kvm); int (*get_smmu_info)(struct kvm *kvm, struct kvm_ppc_smmu_info *info); - int (*emulate_op)(struct kvm_run *run, struct kvm_vcpu *vcpu, + int (*emulate_op)(struct kvm_vcpu *vcpu, unsigned int inst, int *advance); int (*emulate_mtspr)(struct kvm_vcpu *vcpu, int sprn, ulong spr_val); int (*emulate_mfspr)(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val); void (*fast_vcpu_kick)(struct kvm_vcpu *vcpu); - long (*arch_vm_ioctl)(struct file *filp, unsigned int ioctl, - unsigned long arg); + int (*arch_vm_ioctl)(struct file *filp, unsigned int ioctl, + unsigned long arg); int (*hcall_implemented)(unsigned long hcall); int (*irq_bypass_add_producer)(struct irq_bypass_consumer *, struct irq_bypass_producer *); @@ -322,14 +314,19 @@ struct kvmppc_ops { int size); int (*store_to_eaddr)(struct kvm_vcpu *vcpu, ulong *eaddr, void *ptr, int size); + int (*enable_svm)(struct kvm *kvm); int (*svm_off)(struct kvm *kvm); + int (*enable_dawr1)(struct kvm *kvm); + bool (*hash_v3_possible)(void); + int (*create_vm_debugfs)(struct kvm *kvm); + int (*create_vcpu_debugfs)(struct kvm_vcpu *vcpu, struct dentry *debugfs_dentry); }; extern struct kvmppc_ops *kvmppc_hv_ops; extern struct kvmppc_ops *kvmppc_pr_ops; static inline int kvmppc_get_last_inst(struct kvm_vcpu *vcpu, - enum instruction_fetch_type type, u32 *inst) + enum instruction_fetch_type type, ppc_inst_t *inst) { int ret = EMULATE_DONE; u32 fetched_inst; @@ -340,15 +337,30 @@ static inline int kvmppc_get_last_inst(struct kvm_vcpu *vcpu, ret = kvmppc_load_last_inst(vcpu, type, &vcpu->arch.last_inst); /* Write fetch_failed unswapped if the fetch failed */ - if (ret == EMULATE_DONE) - fetched_inst = kvmppc_need_byteswap(vcpu) ? - swab32(vcpu->arch.last_inst) : - vcpu->arch.last_inst; - else - fetched_inst = vcpu->arch.last_inst; + if (ret != EMULATE_DONE) { + *inst = ppc_inst(KVM_INST_FETCH_FAILED); + return ret; + } - *inst = fetched_inst; - return ret; +#ifdef CONFIG_PPC64 + /* Is this a prefixed instruction? */ + if ((vcpu->arch.last_inst >> 32) != 0) { + u32 prefix = vcpu->arch.last_inst >> 32; + u32 suffix = vcpu->arch.last_inst; + if (kvmppc_need_byteswap(vcpu)) { + prefix = swab32(prefix); + suffix = swab32(suffix); + } + *inst = ppc_inst_prefix(prefix, suffix); + return EMULATE_DONE; + } +#endif + + fetched_inst = kvmppc_need_byteswap(vcpu) ? + swab32(vcpu->arch.last_inst) : + vcpu->arch.last_inst; + *inst = ppc_inst(fetched_inst); + return EMULATE_DONE; } static inline bool is_kvmppc_hv_enabled(struct kvm *kvm) @@ -536,12 +548,12 @@ static inline void kvmppc_set_host_ipi(int cpu) * pairs with the barrier in kvmppc_clear_host_ipi() */ smp_mb(); - paca_ptrs[cpu]->kvm_hstate.host_ipi = 1; + WRITE_ONCE(paca_ptrs[cpu]->kvm_hstate.host_ipi, 1); } static inline void kvmppc_clear_host_ipi(int cpu) { - paca_ptrs[cpu]->kvm_hstate.host_ipi = 0; + WRITE_ONCE(paca_ptrs[cpu]->kvm_hstate.host_ipi, 0); /* * order clearing of host_ipi flag vs. processing of IPI messages * @@ -559,8 +571,7 @@ extern void kvm_hv_vm_activated(void); extern void kvm_hv_vm_deactivated(void); extern bool kvm_hv_mode_active(void); -extern void kvmppc_check_need_tlb_flush(struct kvm *kvm, int pcpu, - struct kvm_nested_guest *nested); +extern void kvmppc_check_need_tlb_flush(struct kvm *kvm, int pcpu); #else static inline void __init kvm_cma_reserve(void) @@ -594,6 +605,54 @@ static inline bool kvm_hv_mode_active(void) { return false; } #endif +#ifdef CONFIG_PPC_PSERIES +static inline bool kvmhv_on_pseries(void) +{ + return !cpu_has_feature(CPU_FTR_HVMODE); +} +#else +static inline bool kvmhv_on_pseries(void) +{ + return false; +} + +#endif + +#ifndef CONFIG_PPC_BOOK3S + +static inline bool kvmhv_is_nestedv2(void) +{ + return false; +} + +static inline bool kvmhv_is_nestedv1(void) +{ + return false; +} + +static inline int kvmhv_nestedv2_reload_ptregs(struct kvm_vcpu *vcpu, + struct pt_regs *regs) +{ + return 0; +} +static inline int kvmhv_nestedv2_mark_dirty_ptregs(struct kvm_vcpu *vcpu, + struct pt_regs *regs) +{ + return 0; +} + +static inline int kvmhv_nestedv2_mark_dirty(struct kvm_vcpu *vcpu, u16 iden) +{ + return 0; +} + +static inline int kvmhv_nestedv2_cached_reload(struct kvm_vcpu *vcpu, u16 iden) +{ + return 0; +} + +#endif + #ifdef CONFIG_KVM_XICS static inline int kvmppc_xics_enabled(struct kvm_vcpu *vcpu) { @@ -614,6 +673,7 @@ extern void kvmppc_free_pimap(struct kvm *kvm); extern int kvmppc_xics_rm_complete(struct kvm_vcpu *vcpu, u32 hcall); extern void kvmppc_xics_free_icp(struct kvm_vcpu *vcpu); extern int kvmppc_xics_hcall(struct kvm_vcpu *vcpu, u32 cmd); +extern int kvmppc_xive_xics_hcall(struct kvm_vcpu *vcpu, u32 req); extern u64 kvmppc_xics_get_icp(struct kvm_vcpu *vcpu); extern int kvmppc_xics_set_icp(struct kvm_vcpu *vcpu, u64 icpval); extern int kvmppc_xics_connect_vcpu(struct kvm_device *dev, @@ -636,9 +696,9 @@ extern int h_ipi_redirect; static inline struct kvmppc_passthru_irqmap *kvmppc_get_passthru_irqmap( struct kvm *kvm) { return NULL; } -static inline void kvmppc_alloc_host_rm_ops(void) {}; -static inline void kvmppc_free_host_rm_ops(void) {}; -static inline void kvmppc_free_pimap(struct kvm *kvm) {}; +static inline void kvmppc_alloc_host_rm_ops(void) {} +static inline void kvmppc_free_host_rm_ops(void) {} +static inline void kvmppc_free_pimap(struct kvm *kvm) {} static inline int kvmppc_xics_rm_complete(struct kvm_vcpu *vcpu, u32 hcall) { return 0; } static inline int kvmppc_xics_enabled(struct kvm_vcpu *vcpu) @@ -646,6 +706,8 @@ static inline int kvmppc_xics_enabled(struct kvm_vcpu *vcpu) static inline void kvmppc_xics_free_icp(struct kvm_vcpu *vcpu) { } static inline int kvmppc_xics_hcall(struct kvm_vcpu *vcpu, u32 cmd) { return 0; } +static inline int kvmppc_xive_xics_hcall(struct kvm_vcpu *vcpu, u32 req) + { return 0; } #endif #ifdef CONFIG_KVM_XIVE @@ -663,22 +725,22 @@ extern int kvmppc_xive_get_xive(struct kvm *kvm, u32 irq, u32 *server, u32 *priority); extern int kvmppc_xive_int_on(struct kvm *kvm, u32 irq); extern int kvmppc_xive_int_off(struct kvm *kvm, u32 irq); -extern void kvmppc_xive_init_module(void); -extern void kvmppc_xive_exit_module(void); extern int kvmppc_xive_connect_vcpu(struct kvm_device *dev, struct kvm_vcpu *vcpu, u32 cpu); extern void kvmppc_xive_cleanup_vcpu(struct kvm_vcpu *vcpu); extern int kvmppc_xive_set_mapped(struct kvm *kvm, unsigned long guest_irq, - struct irq_desc *host_desc); + unsigned long host_irq); extern int kvmppc_xive_clr_mapped(struct kvm *kvm, unsigned long guest_irq, - struct irq_desc *host_desc); + unsigned long host_irq); extern u64 kvmppc_xive_get_icp(struct kvm_vcpu *vcpu); extern int kvmppc_xive_set_icp(struct kvm_vcpu *vcpu, u64 icpval); extern int kvmppc_xive_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level, bool line_status); extern void kvmppc_xive_push_vcpu(struct kvm_vcpu *vcpu); +extern void kvmppc_xive_pull_vcpu(struct kvm_vcpu *vcpu); +extern bool kvmppc_xive_rearm_escalation(struct kvm_vcpu *vcpu); static inline int kvmppc_xive_enabled(struct kvm_vcpu *vcpu) { @@ -688,8 +750,6 @@ static inline int kvmppc_xive_enabled(struct kvm_vcpu *vcpu) extern int kvmppc_xive_native_connect_vcpu(struct kvm_device *dev, struct kvm_vcpu *vcpu, u32 cpu); extern void kvmppc_xive_native_cleanup_vcpu(struct kvm_vcpu *vcpu); -extern void kvmppc_xive_native_init_module(void); -extern void kvmppc_xive_native_exit_module(void); extern int kvmppc_xive_native_get_vp(struct kvm_vcpu *vcpu, union kvmppc_one_reg *val); extern int kvmppc_xive_native_set_vp(struct kvm_vcpu *vcpu, @@ -703,8 +763,6 @@ static inline int kvmppc_xive_get_xive(struct kvm *kvm, u32 irq, u32 *server, u32 *priority) { return -1; } static inline int kvmppc_xive_int_on(struct kvm *kvm, u32 irq) { return -1; } static inline int kvmppc_xive_int_off(struct kvm *kvm, u32 irq) { return -1; } -static inline void kvmppc_xive_init_module(void) { } -static inline void kvmppc_xive_exit_module(void) { } static inline int kvmppc_xive_connect_vcpu(struct kvm_device *dev, struct kvm_vcpu *vcpu, u32 cpu) { return -EBUSY; } @@ -719,14 +777,14 @@ static inline int kvmppc_xive_set_icp(struct kvm_vcpu *vcpu, u64 icpval) { retur static inline int kvmppc_xive_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level, bool line_status) { return -ENODEV; } static inline void kvmppc_xive_push_vcpu(struct kvm_vcpu *vcpu) { } +static inline void kvmppc_xive_pull_vcpu(struct kvm_vcpu *vcpu) { } +static inline bool kvmppc_xive_rearm_escalation(struct kvm_vcpu *vcpu) { return true; } static inline int kvmppc_xive_enabled(struct kvm_vcpu *vcpu) { return 0; } static inline int kvmppc_xive_native_connect_vcpu(struct kvm_device *dev, struct kvm_vcpu *vcpu, u32 cpu) { return -EBUSY; } static inline void kvmppc_xive_native_cleanup_vcpu(struct kvm_vcpu *vcpu) { } -static inline void kvmppc_xive_native_init_module(void) { } -static inline void kvmppc_xive_native_exit_module(void) { } static inline int kvmppc_xive_native_get_vp(struct kvm_vcpu *vcpu, union kvmppc_one_reg *val) { return 0; } @@ -762,20 +820,20 @@ long kvmppc_rm_h_stuff_tce(struct kvm_vcpu *vcpu, unsigned long tce_value, unsigned long npages); long int kvmppc_rm_h_confer(struct kvm_vcpu *vcpu, int target, unsigned int yield_count); -long kvmppc_h_random(struct kvm_vcpu *vcpu); +long kvmppc_rm_h_random(struct kvm_vcpu *vcpu); void kvmhv_commence_exit(int trap); void kvmppc_realmode_machine_check(struct kvm_vcpu *vcpu); void kvmppc_subcore_enter_guest(void); void kvmppc_subcore_exit_guest(void); long kvmppc_realmode_hmi_handler(void); +long kvmppc_p9_realmode_hmi_handler(struct kvm_vcpu *vcpu); long kvmppc_h_enter(struct kvm_vcpu *vcpu, unsigned long flags, long pte_index, unsigned long pteh, unsigned long ptel); long kvmppc_h_remove(struct kvm_vcpu *vcpu, unsigned long flags, unsigned long pte_index, unsigned long avpn); long kvmppc_h_bulk_remove(struct kvm_vcpu *vcpu); long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags, - unsigned long pte_index, unsigned long avpn, - unsigned long va); + unsigned long pte_index, unsigned long avpn); long kvmppc_h_read(struct kvm_vcpu *vcpu, unsigned long flags, unsigned long pte_index); long kvmppc_h_clear_ref(struct kvm_vcpu *vcpu, unsigned long flags, @@ -786,13 +844,6 @@ long kvmppc_rm_h_page_init(struct kvm_vcpu *vcpu, unsigned long flags, unsigned long dest, unsigned long src); long kvmppc_hpte_hv_fault(struct kvm_vcpu *vcpu, unsigned long addr, unsigned long slb_v, unsigned int status, bool data); -unsigned long kvmppc_rm_h_xirr(struct kvm_vcpu *vcpu); -unsigned long kvmppc_rm_h_xirr_x(struct kvm_vcpu *vcpu); -unsigned long kvmppc_rm_h_ipoll(struct kvm_vcpu *vcpu, unsigned long server); -int kvmppc_rm_h_ipi(struct kvm_vcpu *vcpu, unsigned long server, - unsigned long mfrr); -int kvmppc_rm_h_cppr(struct kvm_vcpu *vcpu, unsigned long cppr); -int kvmppc_rm_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr); void kvmppc_guest_entry_inject_int(struct kvm_vcpu *vcpu); /* @@ -874,13 +925,12 @@ int kvm_vcpu_ioctl_dirty_tlb(struct kvm_vcpu *vcpu, struct kvm_dirty_tlb *cfg); long kvmppc_alloc_lpid(void); -void kvmppc_claim_lpid(long lpid); void kvmppc_free_lpid(long lpid); void kvmppc_init_lpid(unsigned long nr_lpids); static inline void kvmppc_mmu_flush_icache(kvm_pfn_t pfn) { - struct page *page; + struct folio *folio; /* * We can only access pages that the kernel maps * as memory. Bail out for unmapped ones. @@ -889,10 +939,10 @@ static inline void kvmppc_mmu_flush_icache(kvm_pfn_t pfn) return; /* Clear i-cache for new pages */ - page = pfn_to_page(pfn); - if (!test_bit(PG_arch_1, &page->flags)) { - flush_dcache_icache_page(page); - set_bit(PG_arch_1, &page->flags); + folio = page_folio(pfn_to_page(pfn)); + if (!test_bit(PG_dcache_clean, &folio->flags)) { + flush_dcache_icache_folio(folio); + set_bit(PG_dcache_clean, &folio->flags); } } @@ -913,79 +963,85 @@ static inline bool kvmppc_shared_big_endian(struct kvm_vcpu *vcpu) #endif } -#define SPRNG_WRAPPER_GET(reg, bookehv_spr) \ +#define KVMPPC_BOOKE_HV_SPRNG_ACCESSOR_GET(reg, bookehv_spr) \ static inline ulong kvmppc_get_##reg(struct kvm_vcpu *vcpu) \ { \ return mfspr(bookehv_spr); \ } \ -#define SPRNG_WRAPPER_SET(reg, bookehv_spr) \ +#define KVMPPC_BOOKE_HV_SPRNG_ACCESSOR_SET(reg, bookehv_spr) \ static inline void kvmppc_set_##reg(struct kvm_vcpu *vcpu, ulong val) \ { \ mtspr(bookehv_spr, val); \ } \ -#define SHARED_WRAPPER_GET(reg, size) \ +#define KVMPPC_VCPU_SHARED_REGS_ACCESSOR_GET(reg, size, iden) \ static inline u##size kvmppc_get_##reg(struct kvm_vcpu *vcpu) \ { \ + if (iden) \ + WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, iden) < 0); \ if (kvmppc_shared_big_endian(vcpu)) \ - return be##size##_to_cpu(vcpu->arch.shared->reg); \ + return be##size##_to_cpu((__be##size __force)vcpu->arch.shared->reg); \ else \ - return le##size##_to_cpu(vcpu->arch.shared->reg); \ + return le##size##_to_cpu((__le##size __force)vcpu->arch.shared->reg); \ } \ -#define SHARED_WRAPPER_SET(reg, size) \ +#define KVMPPC_VCPU_SHARED_REGS_ACCESSOR_SET(reg, size, iden) \ static inline void kvmppc_set_##reg(struct kvm_vcpu *vcpu, u##size val) \ { \ if (kvmppc_shared_big_endian(vcpu)) \ - vcpu->arch.shared->reg = cpu_to_be##size(val); \ + vcpu->arch.shared->reg = (u##size __force)cpu_to_be##size(val); \ else \ - vcpu->arch.shared->reg = cpu_to_le##size(val); \ + vcpu->arch.shared->reg = (u##size __force)cpu_to_le##size(val); \ + \ + if (iden) \ + kvmhv_nestedv2_mark_dirty(vcpu, iden); \ } \ -#define SHARED_WRAPPER(reg, size) \ - SHARED_WRAPPER_GET(reg, size) \ - SHARED_WRAPPER_SET(reg, size) \ +#define KVMPPC_VCPU_SHARED_REGS_ACCESSOR(reg, size, iden) \ + KVMPPC_VCPU_SHARED_REGS_ACCESSOR_GET(reg, size, iden) \ + KVMPPC_VCPU_SHARED_REGS_ACCESSOR_SET(reg, size, iden) \ -#define SPRNG_WRAPPER(reg, bookehv_spr) \ - SPRNG_WRAPPER_GET(reg, bookehv_spr) \ - SPRNG_WRAPPER_SET(reg, bookehv_spr) \ +#define KVMPPC_BOOKE_HV_SPRNG_ACCESSOR(reg, bookehv_spr) \ + KVMPPC_BOOKE_HV_SPRNG_ACCESSOR_GET(reg, bookehv_spr) \ + KVMPPC_BOOKE_HV_SPRNG_ACCESSOR_SET(reg, bookehv_spr) \ #ifdef CONFIG_KVM_BOOKE_HV -#define SHARED_SPRNG_WRAPPER(reg, size, bookehv_spr) \ - SPRNG_WRAPPER(reg, bookehv_spr) \ +#define KVMPPC_BOOKE_HV_SPRNG_OR_VCPU_SHARED_REGS_ACCESSOR(reg, size, bookehv_spr, iden) \ + KVMPPC_BOOKE_HV_SPRNG_ACCESSOR(reg, bookehv_spr) \ #else -#define SHARED_SPRNG_WRAPPER(reg, size, bookehv_spr) \ - SHARED_WRAPPER(reg, size) \ +#define KVMPPC_BOOKE_HV_SPRNG_OR_VCPU_SHARED_REGS_ACCESSOR(reg, size, bookehv_spr, iden) \ + KVMPPC_VCPU_SHARED_REGS_ACCESSOR(reg, size, iden) \ #endif -SHARED_WRAPPER(critical, 64) -SHARED_SPRNG_WRAPPER(sprg0, 64, SPRN_GSPRG0) -SHARED_SPRNG_WRAPPER(sprg1, 64, SPRN_GSPRG1) -SHARED_SPRNG_WRAPPER(sprg2, 64, SPRN_GSPRG2) -SHARED_SPRNG_WRAPPER(sprg3, 64, SPRN_GSPRG3) -SHARED_SPRNG_WRAPPER(srr0, 64, SPRN_GSRR0) -SHARED_SPRNG_WRAPPER(srr1, 64, SPRN_GSRR1) -SHARED_SPRNG_WRAPPER(dar, 64, SPRN_GDEAR) -SHARED_SPRNG_WRAPPER(esr, 64, SPRN_GESR) -SHARED_WRAPPER_GET(msr, 64) +KVMPPC_VCPU_SHARED_REGS_ACCESSOR(critical, 64, 0) +KVMPPC_BOOKE_HV_SPRNG_OR_VCPU_SHARED_REGS_ACCESSOR(sprg0, 64, SPRN_GSPRG0, KVMPPC_GSID_SPRG0) +KVMPPC_BOOKE_HV_SPRNG_OR_VCPU_SHARED_REGS_ACCESSOR(sprg1, 64, SPRN_GSPRG1, KVMPPC_GSID_SPRG1) +KVMPPC_BOOKE_HV_SPRNG_OR_VCPU_SHARED_REGS_ACCESSOR(sprg2, 64, SPRN_GSPRG2, KVMPPC_GSID_SPRG2) +KVMPPC_BOOKE_HV_SPRNG_OR_VCPU_SHARED_REGS_ACCESSOR(sprg3, 64, SPRN_GSPRG3, KVMPPC_GSID_SPRG3) +KVMPPC_BOOKE_HV_SPRNG_OR_VCPU_SHARED_REGS_ACCESSOR(srr0, 64, SPRN_GSRR0, KVMPPC_GSID_SRR0) +KVMPPC_BOOKE_HV_SPRNG_OR_VCPU_SHARED_REGS_ACCESSOR(srr1, 64, SPRN_GSRR1, KVMPPC_GSID_SRR1) +KVMPPC_BOOKE_HV_SPRNG_OR_VCPU_SHARED_REGS_ACCESSOR(dar, 64, SPRN_GDEAR, KVMPPC_GSID_DAR) +KVMPPC_BOOKE_HV_SPRNG_OR_VCPU_SHARED_REGS_ACCESSOR(esr, 64, SPRN_GESR, 0) +KVMPPC_VCPU_SHARED_REGS_ACCESSOR_GET(msr, 64, KVMPPC_GSID_MSR) static inline void kvmppc_set_msr_fast(struct kvm_vcpu *vcpu, u64 val) { if (kvmppc_shared_big_endian(vcpu)) vcpu->arch.shared->msr = cpu_to_be64(val); else vcpu->arch.shared->msr = cpu_to_le64(val); + kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_MSR); } -SHARED_WRAPPER(dsisr, 32) -SHARED_WRAPPER(int_pending, 32) -SHARED_WRAPPER(sprg4, 64) -SHARED_WRAPPER(sprg5, 64) -SHARED_WRAPPER(sprg6, 64) -SHARED_WRAPPER(sprg7, 64) +KVMPPC_VCPU_SHARED_REGS_ACCESSOR(dsisr, 32, KVMPPC_GSID_DSISR) +KVMPPC_VCPU_SHARED_REGS_ACCESSOR(int_pending, 32, 0) +KVMPPC_VCPU_SHARED_REGS_ACCESSOR(sprg4, 64, 0) +KVMPPC_VCPU_SHARED_REGS_ACCESSOR(sprg5, 64, 0) +KVMPPC_VCPU_SHARED_REGS_ACCESSOR(sprg6, 64, 0) +KVMPPC_VCPU_SHARED_REGS_ACCESSOR(sprg7, 64, 0) static inline u32 kvmppc_get_sr(struct kvm_vcpu *vcpu, int nr) { @@ -1025,6 +1081,18 @@ static inline void kvmppc_fix_ee_before_entry(void) #endif } +static inline void kvmppc_fix_ee_after_exit(void) +{ +#ifdef CONFIG_PPC64 + /* Only need to enable IRQs by hard enabling them after this */ + local_paca->irq_happened = PACA_IRQ_HARD_DIS; + irq_soft_mask_set(IRQS_ALL_DISABLED); +#endif + + trace_hardirqs_off(); +} + + static inline ulong kvmppc_get_ea_indexed(struct kvm_vcpu *vcpu, int ra, int rb) { ulong ea; diff --git a/arch/powerpc/include/asm/linkage.h b/arch/powerpc/include/asm/linkage.h index 1f00d2891d69..b71b9582e754 100644 --- a/arch/powerpc/include/asm/linkage.h +++ b/arch/powerpc/include/asm/linkage.h @@ -4,7 +4,7 @@ #include <asm/types.h> -#ifdef PPC64_ELF_ABI_v1 +#ifdef CONFIG_PPC64_ELF_ABI_V1 #define cond_syscall(x) \ asm ("\t.weak " #x "\n\t.set " #x ", sys_ni_syscall\n" \ "\t.weak ." #x "\n\t.set ." #x ", .sys_ni_syscall\n") diff --git a/arch/powerpc/include/asm/livepatch.h b/arch/powerpc/include/asm/livepatch.h index 4a3d5d25fed5..d044a1fd4f44 100644 --- a/arch/powerpc/include/asm/livepatch.h +++ b/arch/powerpc/include/asm/livepatch.h @@ -7,26 +7,10 @@ #ifndef _ASM_POWERPC_LIVEPATCH_H #define _ASM_POWERPC_LIVEPATCH_H -#include <linux/module.h> -#include <linux/ftrace.h> +#include <linux/sched.h> #include <linux/sched/task_stack.h> -#ifdef CONFIG_LIVEPATCH -static inline void klp_arch_set_pc(struct pt_regs *regs, unsigned long ip) -{ - regs->nip = ip; -} - -#define klp_get_ftrace_location klp_get_ftrace_location -static inline unsigned long klp_get_ftrace_location(unsigned long faddr) -{ - /* - * Live patch works only with -mprofile-kernel on PPC. In this case, - * the ftrace location is always within the first 16 bytes. - */ - return ftrace_location_range(faddr, faddr + 16); -} - +#ifdef CONFIG_LIVEPATCH_64 static inline void klp_init_thread_info(struct task_struct *p) { /* + 1 to account for STACK_END_MAGIC */ @@ -34,6 +18,6 @@ static inline void klp_init_thread_info(struct task_struct *p) } #else static inline void klp_init_thread_info(struct task_struct *p) { } -#endif /* CONFIG_LIVEPATCH */ +#endif #endif /* _ASM_POWERPC_LIVEPATCH_H */ diff --git a/arch/powerpc/include/asm/local.h b/arch/powerpc/include/asm/local.h index bc4bd19b7fc2..ec6ced6d7ced 100644 --- a/arch/powerpc/include/asm/local.h +++ b/arch/powerpc/include/asm/local.h @@ -90,6 +90,17 @@ static __inline__ long local_cmpxchg(local_t *l, long o, long n) return t; } +static __inline__ bool local_try_cmpxchg(local_t *l, long *po, long n) +{ + long o = *po, r; + + r = local_cmpxchg(l, o, n); + if (unlikely(r != o)) + *po = r; + + return likely(r == o); +} + static __inline__ long local_xchg(local_t *l, long n) { long t; @@ -104,23 +115,23 @@ static __inline__ long local_xchg(local_t *l, long n) } /** - * local_add_unless - add unless the number is a given value + * local_add_unless - add unless the number is already a given value * @l: pointer of type local_t * @a: the amount to add to v... * @u: ...unless v is equal to u. * - * Atomically adds @a to @l, so long as it was not @u. - * Returns non-zero if @l was not @u, and zero otherwise. + * Atomically adds @a to @l, if @v was not already @u. + * Returns true if the addition was done. */ -static __inline__ int local_add_unless(local_t *l, long a, long u) +static __inline__ bool local_add_unless(local_t *l, long a, long u) { unsigned long flags; - int ret = 0; + bool ret = false; powerpc_local_irq_pmu_save(flags); if (l->v != u) { l->v += a; - ret = 1; + ret = true; } powerpc_local_irq_pmu_restore(flags); diff --git a/arch/powerpc/include/asm/lppaca.h b/arch/powerpc/include/asm/lppaca.h index 3b4b305796ae..61ec2447dabf 100644 --- a/arch/powerpc/include/asm/lppaca.h +++ b/arch/powerpc/include/asm/lppaca.h @@ -6,28 +6,6 @@ #ifndef _ASM_POWERPC_LPPACA_H #define _ASM_POWERPC_LPPACA_H -/* - * The below VPHN macros are outside the __KERNEL__ check since these are - * used for compiling the vphn selftest in userspace - */ - -/* The H_HOME_NODE_ASSOCIATIVITY h_call returns 6 64-bit registers. */ -#define VPHN_REGISTER_COUNT 6 - -/* - * 6 64-bit registers unpacked into up to 24 be32 associativity values. To - * form the complete property we have to add the length in the first cell. - */ -#define VPHN_ASSOC_BUFSIZE (VPHN_REGISTER_COUNT*sizeof(u64)/sizeof(u16) + 1) - -/* - * The H_HOME_NODE_ASSOCIATIVITY hcall takes two values for flags: - * 1 for retrieving associativity information for a guest cpu - * 2 for retrieving associativity information for a host/hypervisor cpu - */ -#define VPHN_FLAG_VCPU 1 -#define VPHN_FLAG_PCPU 2 - #ifdef __KERNEL__ /* @@ -42,10 +20,10 @@ */ #include <linux/cache.h> #include <linux/threads.h> -#include <linux/spinlock_types.h> #include <asm/types.h> #include <asm/mmu.h> #include <asm/firmware.h> +#include <asm/paca.h> /* * The lppaca is the "virtual processor area" registered with the hypervisor, @@ -105,14 +83,18 @@ struct lppaca { volatile __be32 dispersion_count; /* dispatch changed physical cpu */ volatile __be64 cmo_faults; /* CMO page fault count */ volatile __be64 cmo_fault_time; /* CMO page fault time */ - u8 reserved10[104]; + u8 reserved10[64]; /* [S]PURR expropriated/donated */ + volatile __be64 enqueue_dispatch_tb; /* Total TB enqueue->dispatch */ + volatile __be64 ready_enqueue_tb; /* Total TB ready->enqueue */ + volatile __be64 wait_ready_tb; /* Total TB wait->ready */ + u8 reserved11[16]; /* cacheline 4-5 */ __be32 page_ins; /* CMO Hint - # page ins by OS */ - u8 reserved11[148]; + u8 reserved12[148]; volatile __be64 dtl_idx; /* Dispatch Trace Log head index */ - u8 reserved12[96]; + u8 reserved13[96]; } ____cacheline_aligned; #define lppaca_of(cpu) (*paca_ptrs[cpu]->lppaca_ptr) @@ -124,13 +106,23 @@ struct lppaca { */ #define LPPACA_OLD_SHARED_PROC 2 -static inline bool lppaca_shared_proc(struct lppaca *l) +#ifdef CONFIG_PPC_PSERIES +/* + * All CPUs should have the same shared proc value, so directly access the PACA + * to avoid false positives from DEBUG_PREEMPT. + */ +static inline bool lppaca_shared_proc(void) { + struct lppaca *l = local_paca->lppaca_ptr; + if (!firmware_has_feature(FW_FEATURE_SPLPAR)) return false; return !!(l->__old_status & LPPACA_OLD_SHARED_PROC); } +#define get_lppaca() (get_paca()->lppaca_ptr) +#endif + /* * SLB shadow buffer structure as defined in the PAPR. The save_area * contains adjacent ESID and VSID pairs for each shadowed SLB. The @@ -146,51 +138,6 @@ struct slb_shadow { } save_area[SLB_NUM_BOLTED]; } ____cacheline_aligned; -/* - * Layout of entries in the hypervisor's dispatch trace log buffer. - */ -struct dtl_entry { - u8 dispatch_reason; - u8 preempt_reason; - __be16 processor_id; - __be32 enqueue_to_dispatch_time; - __be32 ready_to_enqueue_time; - __be32 waiting_to_ready_time; - __be64 timebase; - __be64 fault_addr; - __be64 srr0; - __be64 srr1; -}; - -#define DISPATCH_LOG_BYTES 4096 /* bytes per cpu */ -#define N_DISPATCH_LOG (DISPATCH_LOG_BYTES / sizeof(struct dtl_entry)) - -/* - * Dispatch trace log event enable mask: - * 0x1: voluntary virtual processor waits - * 0x2: time-slice preempts - * 0x4: virtual partition memory page faults - */ -#define DTL_LOG_CEDE 0x1 -#define DTL_LOG_PREEMPT 0x2 -#define DTL_LOG_FAULT 0x4 -#define DTL_LOG_ALL (DTL_LOG_CEDE | DTL_LOG_PREEMPT | DTL_LOG_FAULT) - -extern struct kmem_cache *dtl_cache; -extern rwlock_t dtl_access_lock; - -/* - * When CONFIG_VIRT_CPU_ACCOUNTING_NATIVE = y, the cpu accounting code controls - * reading from the dispatch trace log. If other code wants to consume - * DTL entries, it can set this pointer to a function that will get - * called once for each DTL entry that gets processed. - */ -extern void (*dtl_consumer)(struct dtl_entry *entry, u64 index); - -extern void register_dtl_buffer(int cpu); -extern void alloc_dtl_buffers(unsigned long *time_limit); -extern long hcall_vphn(unsigned long cpu, u64 flags, __be32 *associativity); - #endif /* CONFIG_PPC_BOOK3S */ #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_LPPACA_H */ diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h index 7bcb64444a39..d31a5ec1550d 100644 --- a/arch/powerpc/include/asm/machdep.h +++ b/arch/powerpc/include/asm/machdep.h @@ -3,20 +3,14 @@ #define _ASM_POWERPC_MACHDEP_H #ifdef __KERNEL__ +#include <linux/compiler.h> #include <linux/seq_file.h> #include <linux/init.h> #include <linux/dma-mapping.h> #include <linux/export.h> -#include <asm/setup.h> - -/* We export this macro for external modules like Alsa to know if - * ppc_md.feature_call is implemented or not - */ -#define CONFIG_PPC_HAS_FEATURE_CALLS - struct pt_regs; -struct pci_bus; +struct pci_bus; struct device_node; struct iommu_table; struct rtc_time; @@ -26,13 +20,13 @@ struct kimage; struct pci_host_bridge; struct machdep_calls { - char *name; + const char *name; + const char *compatible; #ifdef CONFIG_PPC64 #ifdef CONFIG_PM - void (*iommu_save)(void); void (*iommu_restore)(void); #endif -#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE +#ifdef CONFIG_MEMORY_HOTPLUG unsigned long (*memory_block_size)(void); #endif #endif /* CONFIG_PPC64 */ @@ -43,7 +37,6 @@ struct machdep_calls { void (*setup_arch)(void); /* Optional, may be NULL */ /* Optional, may be NULL. */ void (*show_cpuinfo)(struct seq_file *m); - void (*show_percpuinfo)(struct seq_file *m, int i); /* Returns the current operating frequency of "cpu" in Hz */ unsigned long (*get_proc_freq)(unsigned int cpu); @@ -59,21 +52,21 @@ struct machdep_calls { int (*pcibios_root_bridge_prepare)(struct pci_host_bridge *bridge); + /* finds all the pci_controllers present at boot */ + void (*discover_phbs)(void); + /* To setup PHBs when using automatic OF platform driver for PCI */ int (*pci_setup_phb)(struct pci_controller *host); void __noreturn (*restart)(char *cmd); void __noreturn (*halt)(void); void (*panic)(char *str); - void (*cpu_die)(void); long (*time_init)(void); /* Optional, may be NULL */ int (*set_rtc_time)(struct rtc_time *); void (*get_rtc_time)(struct rtc_time *); time64_t (*get_boot_time)(void); - unsigned char (*rtc_read_val)(int addr); - void (*rtc_write_val)(int addr, unsigned char val); void (*calibrate_decr)(void); @@ -85,8 +78,8 @@ struct machdep_calls { unsigned char (*nvram_read_val)(int addr); void (*nvram_write_val)(int addr, unsigned char val); ssize_t (*nvram_write)(char *buf, size_t count, loff_t *index); - ssize_t (*nvram_read)(char *buf, size_t count, loff_t *index); - ssize_t (*nvram_size)(void); + ssize_t (*nvram_read)(char *buf, size_t count, loff_t *index); + ssize_t (*nvram_size)(void); void (*nvram_sync)(void); /* Exception handlers */ @@ -101,18 +94,19 @@ struct machdep_calls { /* Called during machine check exception to retrive fixup address. */ bool (*mce_check_early_recovery)(struct pt_regs *regs); + void (*machine_check_log_err)(void); + /* Motherboard/chipset features. This is a kind of general purpose * hook used to control some machine specific features (like reset * lines, chip power control, etc...). */ long (*feature_call)(unsigned int feature, ...); - /* Get legacy PCI/IDE interrupt mapping */ + /* Get legacy PCI/IDE interrupt mapping */ int (*pci_get_legacy_ide_irq)(struct pci_dev *dev, int channel); - + /* Get access protection for /dev/mem */ - pgprot_t (*phys_mem_access_prot)(struct file *file, - unsigned long pfn, + pgprot_t (*phys_mem_access_prot)(unsigned long pfn, unsigned long size, pgprot_t vma_prot); @@ -131,7 +125,7 @@ struct machdep_calls { unsigned long dabrx); /* Set DAWR for this platform, leave empty for default implementation */ - int (*set_dawr)(unsigned long dawr, + int (*set_dawr)(int nr, unsigned long dawr, unsigned long dawrx); #ifdef CONFIG_PPC32 /* XXX for now */ @@ -139,8 +133,6 @@ struct machdep_calls { May be NULL. */ void (*init)(void); - void (*kgdb_map_scc)(void); - /* * optional PCI "hooks" */ @@ -185,13 +177,6 @@ struct machdep_calls { #ifdef CONFIG_KEXEC_CORE void (*kexec_cpu_down)(int crash_shutdown, int secondary); - /* Called to do what every setup is needed on image and the - * reboot code buffer. Returns 0 on success. - * Provide your own (maybe dummy) implementation if your platform - * claims to support kexec. - */ - int (*machine_kexec_prepare)(struct kimage *image); - /* Called to perform the _real_ kexec. * Do NOT allocate memory or fail here. We are past the point of * no return. @@ -208,24 +193,18 @@ struct machdep_calls { void (*suspend_disable_irqs)(void); void (*suspend_enable_irqs)(void); #endif - int (*suspend_disable_cpu)(void); #ifdef CONFIG_ARCH_CPU_PROBE_RELEASE ssize_t (*cpu_probe)(const char *, size_t); ssize_t (*cpu_release)(const char *, size_t); #endif -#ifdef CONFIG_ARCH_RANDOM int (*get_random_seed)(unsigned long *v); -#endif }; extern void e500_idle(void); extern void power4_idle(void); -extern void power7_idle(void); -extern void power9_idle(void); extern void ppc6xx_idle(void); -extern void book3e_idle(void); /* * ppc_md contains a copy of the machine description structure for the @@ -235,36 +214,24 @@ extern void book3e_idle(void); extern struct machdep_calls ppc_md; extern struct machdep_calls *machine_id; -#define __machine_desc __attribute__ ((__section__ (".machine.desc"))) +#define __machine_desc __section(".machine.desc") #define define_machine(name) \ extern struct machdep_calls mach_##name; \ EXPORT_SYMBOL(mach_##name); \ struct machdep_calls mach_##name __machine_desc = -#define machine_is(name) \ - ({ \ - extern struct machdep_calls mach_##name \ - __attribute__((weak)); \ - machine_id == &mach_##name; \ - }) - -extern void probe_machine(void); +static inline bool __machine_is(const struct machdep_calls *md) +{ + WARN_ON(!machine_id); // complain if used before probe_machine() + return machine_id == md; +} -#ifdef CONFIG_PPC_PMAC -/* - * Power macintoshes have either a CUDA, PMU or SMU controlling - * system reset, power, NVRAM, RTC. - */ -typedef enum sys_ctrler_kind { - SYS_CTRLER_UNKNOWN = 0, - SYS_CTRLER_CUDA = 1, - SYS_CTRLER_PMU = 2, - SYS_CTRLER_SMU = 3, -} sys_ctrler_t; -extern sys_ctrler_t sys_ctrler; - -#endif /* CONFIG_PPC_PMAC */ +#define machine_is(name) \ + ({ \ + extern struct machdep_calls mach_##name __weak; \ + __machine_is(&mach_##name); \ + }) static inline void log_error(char *buf, unsigned int err_type, int fatal) { diff --git a/arch/powerpc/include/asm/macio.h b/arch/powerpc/include/asm/macio.h index ff5fd82d9ff0..3a07c62973aa 100644 --- a/arch/powerpc/include/asm/macio.h +++ b/arch/powerpc/include/asm/macio.h @@ -3,7 +3,8 @@ #define __MACIO_ASIC_H__ #ifdef __KERNEL__ -#include <linux/of_device.h> +#include <linux/of.h> +#include <linux/platform_device.h> extern struct bus_type macio_bus_type; diff --git a/arch/powerpc/include/asm/mce.h b/arch/powerpc/include/asm/mce.h index 6a6ddaabdb34..c9f0936bd3c9 100644 --- a/arch/powerpc/include/asm/mce.h +++ b/arch/powerpc/include/asm/mce.h @@ -86,6 +86,7 @@ enum MCE_TlbErrorType { enum MCE_UserErrorType { MCE_USER_ERROR_INDETERMINATE = 0, MCE_USER_ERROR_TLBIE = 1, + MCE_USER_ERROR_SCV = 2, }; enum MCE_RaErrorType { @@ -203,12 +204,26 @@ struct mce_error_info { bool ignore_event; }; -#define MAX_MC_EVT 100 +#define MAX_MC_EVT 10 + +struct mce_info { + int mce_nest_count; + struct machine_check_event mce_event[MAX_MC_EVT]; + /* Queue for delayed MCE events. */ + int mce_queue_count; + struct machine_check_event mce_event_queue[MAX_MC_EVT]; + /* Queue for delayed MCE UE events. */ + int mce_ue_count; + struct machine_check_event mce_ue_event_queue[MAX_MC_EVT]; +}; /* Release flags for get_mce_event() */ #define MCE_EVENT_RELEASE true #define MCE_EVENT_DONTRELEASE false +struct pt_regs; +struct notifier_block; + extern void save_mce_event(struct pt_regs *regs, long handled, struct mce_error_info *mce_err, uint64_t nip, uint64_t addr, uint64_t phys_addr); @@ -218,7 +233,36 @@ extern void machine_check_queue_event(void); extern void machine_check_print_event_info(struct machine_check_event *evt, bool user_mode, bool in_guest); unsigned long addr_to_pfn(struct pt_regs *regs, unsigned long addr); +extern void mce_common_process_ue(struct pt_regs *regs, + struct mce_error_info *mce_err); +void mce_irq_work_queue(void); +int mce_register_notifier(struct notifier_block *nb); +int mce_unregister_notifier(struct notifier_block *nb); + +#ifdef CONFIG_PPC_BOOK3S_64 +void mce_run_irq_context_handlers(void); +#else +static inline void mce_run_irq_context_handlers(void) { }; +#endif /* CONFIG_PPC_BOOK3S_64 */ + +#ifdef CONFIG_PPC_BOOK3S_64 +void set_mce_pending_irq_work(void); +void clear_mce_pending_irq_work(void); +#endif /* CONFIG_PPC_BOOK3S_64 */ + #ifdef CONFIG_PPC_BOOK3S_64 void flush_and_reload_slb(void); +void flush_erat(void); +long __machine_check_early_realmode_p7(struct pt_regs *regs); +long __machine_check_early_realmode_p8(struct pt_regs *regs); +long __machine_check_early_realmode_p9(struct pt_regs *regs); +long __machine_check_early_realmode_p10(struct pt_regs *regs); #endif /* CONFIG_PPC_BOOK3S_64 */ + +#ifdef CONFIG_PPC_BOOK3S_64 +void mce_init(void); +#else +static inline void mce_init(void) { }; +#endif /* CONFIG_PPC_BOOK3S_64 */ + #endif /* __ASM_PPC64_MCE_H__ */ diff --git a/arch/powerpc/include/asm/mem_encrypt.h b/arch/powerpc/include/asm/mem_encrypt.h index ba9dab07c1be..2f26b8fc8d29 100644 --- a/arch/powerpc/include/asm/mem_encrypt.h +++ b/arch/powerpc/include/asm/mem_encrypt.h @@ -10,11 +10,6 @@ #include <asm/svm.h> -static inline bool mem_encrypt_active(void) -{ - return is_secure_guest(); -} - static inline bool force_dma_unencrypted(struct device *dev) { return is_secure_guest(); diff --git a/arch/powerpc/include/asm/membarrier.h b/arch/powerpc/include/asm/membarrier.h index 6e20bb5c74ea..de7f79157918 100644 --- a/arch/powerpc/include/asm/membarrier.h +++ b/arch/powerpc/include/asm/membarrier.h @@ -12,7 +12,8 @@ static inline void membarrier_arch_switch_mm(struct mm_struct *prev, * when switching from userspace to kernel is not needed after * store to rq->curr. */ - if (likely(!(atomic_read(&next->membarrier_state) & + if (IS_ENABLED(CONFIG_SMP) && + likely(!(atomic_read(&next->membarrier_state) & (MEMBARRIER_STATE_PRIVATE_EXPEDITED | MEMBARRIER_STATE_GLOBAL_EXPEDITED)) || !prev)) return; diff --git a/arch/powerpc/include/asm/mm-arch-hooks.h b/arch/powerpc/include/asm/mm-arch-hooks.h deleted file mode 100644 index dce274be824a..000000000000 --- a/arch/powerpc/include/asm/mm-arch-hooks.h +++ /dev/null @@ -1,25 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Architecture specific mm hooks - * - * Copyright (C) 2015, IBM Corporation - * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com> - */ - -#ifndef _ASM_POWERPC_MM_ARCH_HOOKS_H -#define _ASM_POWERPC_MM_ARCH_HOOKS_H - -static inline void arch_remap(struct mm_struct *mm, - unsigned long old_start, unsigned long old_end, - unsigned long new_start, unsigned long new_end) -{ - /* - * mremap() doesn't allow moving multiple vmas so we can limit the - * check to old_start == vdso_base. - */ - if (old_start == mm->context.vdso_base) - mm->context.vdso_base = new_start; -} -#define arch_remap arch_remap - -#endif /* _ASM_POWERPC_MM_ARCH_HOOKS_H */ diff --git a/arch/powerpc/include/asm/mman.h b/arch/powerpc/include/asm/mman.h index d610c2e07b28..17a77d47ed6d 100644 --- a/arch/powerpc/include/asm/mman.h +++ b/arch/powerpc/include/asm/mman.h @@ -12,11 +12,8 @@ #include <linux/mm.h> #include <linux/pkeys.h> #include <asm/cpu_has_feature.h> +#include <asm/firmware.h> -/* - * This file is included by linux/mman.h, so we can't use cacl_vm_prot_bits() - * here. How important is the optimization? - */ static inline unsigned long arch_calc_vm_prot_bits(unsigned long prot, unsigned long pkey) { @@ -28,24 +25,17 @@ static inline unsigned long arch_calc_vm_prot_bits(unsigned long prot, } #define arch_calc_vm_prot_bits(prot, pkey) arch_calc_vm_prot_bits(prot, pkey) -static inline pgprot_t arch_vm_get_page_prot(unsigned long vm_flags) -{ -#ifdef CONFIG_PPC_MEM_KEYS - return (vm_flags & VM_SAO) ? - __pgprot(_PAGE_SAO | vmflag_to_pte_pkey_bits(vm_flags)) : - __pgprot(0 | vmflag_to_pte_pkey_bits(vm_flags)); -#else - return (vm_flags & VM_SAO) ? __pgprot(_PAGE_SAO) : __pgprot(0); -#endif -} -#define arch_vm_get_page_prot(vm_flags) arch_vm_get_page_prot(vm_flags) - static inline bool arch_validate_prot(unsigned long prot, unsigned long addr) { if (prot & ~(PROT_READ | PROT_WRITE | PROT_EXEC | PROT_SEM | PROT_SAO)) return false; - if ((prot & PROT_SAO) && !cpu_has_feature(CPU_FTR_SAO)) - return false; + if (prot & PROT_SAO) { + if (!cpu_has_feature(CPU_FTR_SAO)) + return false; + if (firmware_has_feature(FW_FEATURE_LPAR) && + !IS_ENABLED(CONFIG_PPC_PROT_SAO_LPAR)) + return false; + } return true; } #define arch_validate_prot arch_validate_prot diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h index 0699cfeeb8c9..d8b7e246a32f 100644 --- a/arch/powerpc/include/asm/mmu.h +++ b/arch/powerpc/include/asm/mmu.h @@ -29,6 +29,28 @@ */ /* + * Supports KUAP feature + * key 0 controlling userspace addresses on radix + * Key 3 on hash + */ +#define MMU_FTR_KUAP ASM_CONST(0x00000200) + +/* + * Supports KUEP feature + * key 0 controlling userspace addresses on radix + * Key 3 on hash + */ +#define MMU_FTR_BOOK3S_KUEP ASM_CONST(0x00000400) + +/* + * Support for memory protection keys. + */ +#define MMU_FTR_PKEY ASM_CONST(0x00000800) + +/* Guest Translation Shootdown Enable */ +#define MMU_FTR_GTSE ASM_CONST(0x00001000) + +/* * Support for 68 bit VA space. We added that from ISA 2.05 */ #define MMU_FTR_68_BIT_VA ASM_CONST(0x00002000) @@ -74,15 +96,6 @@ */ #define MMU_FTR_NEED_DTLB_SW_LRU ASM_CONST(0x00200000) -/* Enable use of TLB reservation. Processor should support tlbsrx. - * instruction and MAS0[WQ]. - */ -#define MMU_FTR_USE_TLBRSRV ASM_CONST(0x00800000) - -/* Use paired MAS registers (MAS7||MAS3, etc.) - */ -#define MMU_FTR_USE_PAIRED_MAS ASM_CONST(0x01000000) - /* Doesn't support the B bit (1T segment) in SLBIE */ #define MMU_FTR_NO_SLBIE_B ASM_CONST(0x02000000) @@ -107,14 +120,11 @@ */ #define MMU_FTR_1T_SEGMENT ASM_CONST(0x40000000) -/* - * Supports KUAP (key 0 controlling userspace addresses) on radix - */ -#define MMU_FTR_RADIX_KUAP ASM_CONST(0x80000000) +// NX paste RMA reject in DSI +#define MMU_FTR_NX_DSI ASM_CONST(0x80000000) /* MMU feature bit sets for various CPUs */ -#define MMU_FTRS_DEFAULT_HPTE_ARCH_V2 \ - MMU_FTR_HPTE_TABLE | MMU_FTR_PPCAS_ARCH_V2 +#define MMU_FTRS_DEFAULT_HPTE_ARCH_V2 (MMU_FTR_HPTE_TABLE | MMU_FTR_TLBIEL | MMU_FTR_16M_PAGE) #define MMU_FTRS_POWER MMU_FTRS_DEFAULT_HPTE_ARCH_V2 #define MMU_FTRS_PPC970 MMU_FTRS_POWER | MMU_FTR_TLBIE_CROP_VA #define MMU_FTRS_POWER5 MMU_FTRS_POWER | MMU_FTR_LOCKLESS_TLBIE @@ -122,6 +132,7 @@ #define MMU_FTRS_POWER7 MMU_FTRS_POWER6 #define MMU_FTRS_POWER8 MMU_FTRS_POWER6 #define MMU_FTRS_POWER9 MMU_FTRS_POWER6 +#define MMU_FTRS_POWER10 MMU_FTRS_POWER6 #define MMU_FTRS_CELL MMU_FTRS_DEFAULT_HPTE_ARCH_V2 | \ MMU_FTR_CI_LARGE_PAGE #define MMU_FTRS_PA6T MMU_FTRS_DEFAULT_HPTE_ARCH_V2 | \ @@ -133,14 +144,9 @@ typedef pte_t *pgtable_t; -#ifdef CONFIG_PPC_FSL_BOOK3E -#include <asm/percpu.h> -DECLARE_PER_CPU(int, next_tlbcam_idx); -#endif - enum { MMU_FTRS_POSSIBLE = -#ifdef CONFIG_PPC_BOOK3S +#if defined(CONFIG_PPC_BOOK3S_604) MMU_FTR_HPTE_TABLE | #endif #ifdef CONFIG_PPC_8xx @@ -149,38 +155,80 @@ enum { #ifdef CONFIG_40x MMU_FTR_TYPE_40x | #endif -#ifdef CONFIG_44x +#ifdef CONFIG_PPC_47x + MMU_FTR_TYPE_47x | MMU_FTR_USE_TLBIVAX_BCAST | MMU_FTR_LOCK_BCAST_INVAL | +#elif defined(CONFIG_44x) MMU_FTR_TYPE_44x | #endif -#if defined(CONFIG_E200) || defined(CONFIG_E500) +#ifdef CONFIG_PPC_E500 MMU_FTR_TYPE_FSL_E | MMU_FTR_BIG_PHYS | MMU_FTR_USE_TLBILX | #endif -#ifdef CONFIG_PPC_47x - MMU_FTR_TYPE_47x | MMU_FTR_USE_TLBIVAX_BCAST | MMU_FTR_LOCK_BCAST_INVAL | -#endif #ifdef CONFIG_PPC_BOOK3S_32 - MMU_FTR_USE_HIGH_BATS | MMU_FTR_NEED_DTLB_SW_LRU | + MMU_FTR_USE_HIGH_BATS | #endif -#ifdef CONFIG_PPC_BOOK3E_64 - MMU_FTR_USE_TLBRSRV | MMU_FTR_USE_PAIRED_MAS | +#ifdef CONFIG_PPC_83xx + MMU_FTR_NEED_DTLB_SW_LRU | #endif #ifdef CONFIG_PPC_BOOK3S_64 + MMU_FTR_KERNEL_RO | +#ifdef CONFIG_PPC_64S_HASH_MMU MMU_FTR_NO_SLBIE_B | MMU_FTR_16M_PAGE | MMU_FTR_TLBIEL | MMU_FTR_LOCKLESS_TLBIE | MMU_FTR_CI_LARGE_PAGE | MMU_FTR_1T_SEGMENT | MMU_FTR_TLBIE_CROP_VA | - MMU_FTR_KERNEL_RO | MMU_FTR_68_BIT_VA | + MMU_FTR_68_BIT_VA | MMU_FTR_HPTE_TABLE | #endif #ifdef CONFIG_PPC_RADIX_MMU MMU_FTR_TYPE_RADIX | + MMU_FTR_GTSE | MMU_FTR_NX_DSI | +#endif /* CONFIG_PPC_RADIX_MMU */ +#endif #ifdef CONFIG_PPC_KUAP - MMU_FTR_RADIX_KUAP | + MMU_FTR_KUAP | #endif /* CONFIG_PPC_KUAP */ -#endif /* CONFIG_PPC_RADIX_MMU */ +#ifdef CONFIG_PPC_MEM_KEYS + MMU_FTR_PKEY | +#endif +#ifdef CONFIG_PPC_KUEP + MMU_FTR_BOOK3S_KUEP | +#endif /* CONFIG_PPC_KUAP */ + 0, }; -static inline bool early_mmu_has_feature(unsigned long feature) +#if defined(CONFIG_PPC_BOOK3S_604) && !defined(CONFIG_PPC_BOOK3S_603) +#define MMU_FTRS_ALWAYS MMU_FTR_HPTE_TABLE +#endif +#ifdef CONFIG_PPC_8xx +#define MMU_FTRS_ALWAYS MMU_FTR_TYPE_8xx +#endif +#ifdef CONFIG_40x +#define MMU_FTRS_ALWAYS MMU_FTR_TYPE_40x +#endif +#ifdef CONFIG_PPC_47x +#define MMU_FTRS_ALWAYS MMU_FTR_TYPE_47x +#elif defined(CONFIG_44x) +#define MMU_FTRS_ALWAYS MMU_FTR_TYPE_44x +#endif +#ifdef CONFIG_PPC_E500 +#define MMU_FTRS_ALWAYS MMU_FTR_TYPE_FSL_E +#endif + +/* BOOK3S_64 options */ +#if defined(CONFIG_PPC_RADIX_MMU) && !defined(CONFIG_PPC_64S_HASH_MMU) +#define MMU_FTRS_ALWAYS MMU_FTR_TYPE_RADIX +#elif !defined(CONFIG_PPC_RADIX_MMU) && defined(CONFIG_PPC_64S_HASH_MMU) +#define MMU_FTRS_ALWAYS MMU_FTR_HPTE_TABLE +#endif + +#ifndef MMU_FTRS_ALWAYS +#define MMU_FTRS_ALWAYS 0 +#endif + +static __always_inline bool early_mmu_has_feature(unsigned long feature) { + if (MMU_FTRS_ALWAYS & feature) + return true; + return !!(MMU_FTRS_POSSIBLE & cur_cpu_spec->mmu_features & feature); } @@ -209,6 +257,9 @@ static __always_inline bool mmu_has_feature(unsigned long feature) } #endif + if (MMU_FTRS_ALWAYS & feature) + return true; + if (!(MMU_FTRS_POSSIBLE & feature)) return false; @@ -231,7 +282,7 @@ static inline void mmu_feature_keys_init(void) } -static inline bool mmu_has_feature(unsigned long feature) +static __always_inline bool mmu_has_feature(unsigned long feature) { return early_mmu_has_feature(feature); } @@ -269,36 +320,15 @@ static inline void assert_pte_locked(struct mm_struct *mm, unsigned long addr) } #endif /* !CONFIG_DEBUG_VM */ -#ifdef CONFIG_PPC_RADIX_MMU -static inline bool radix_enabled(void) +static __always_inline bool radix_enabled(void) { return mmu_has_feature(MMU_FTR_TYPE_RADIX); } -static inline bool early_radix_enabled(void) +static __always_inline bool early_radix_enabled(void) { return early_mmu_has_feature(MMU_FTR_TYPE_RADIX); } -#else -static inline bool radix_enabled(void) -{ - return false; -} - -static inline bool early_radix_enabled(void) -{ - return false; -} -#endif - -#ifdef CONFIG_PPC_MEM_KEYS -extern u16 get_mm_addr_key(struct mm_struct *mm, unsigned long address); -#else -static inline u16 get_mm_addr_key(struct mm_struct *mm, unsigned long address) -{ - return 0; -} -#endif /* CONFIG_PPC_MEM_KEYS */ #ifdef CONFIG_STRICT_KERNEL_RWX static inline bool strict_kernel_rwx_enabled(void) @@ -311,6 +341,11 @@ static inline bool strict_kernel_rwx_enabled(void) return false; } #endif + +static inline bool strict_module_rwx_enabled(void) +{ + return IS_ENABLED(CONFIG_STRICT_MODULE_RWX) && strict_kernel_rwx_enabled(); +} #endif /* !__ASSEMBLY__ */ /* The kernel use the constants below to index in the page sizes array. @@ -364,6 +399,8 @@ extern void setup_initial_memory_limit(phys_addr_t first_memblock_base, phys_addr_t first_memblock_size); static inline void mmu_early_init_devtree(void) { } +static inline void pkey_early_init_devtree(void) {} + extern void *abatron_pteptrs[2]; #endif /* __ASSEMBLY__ */ #endif @@ -375,5 +412,9 @@ extern void *abatron_pteptrs[2]; #include <asm/nohash/mmu.h> #endif +#if defined(CONFIG_FA_DUMP) || defined(CONFIG_PRESERVE_FA_DUMP) +#define __HAVE_ARCH_RESERVED_KERNEL_PAGES +#endif + #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_MMU_H_ */ diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h index 58efca934311..37bffa0f7918 100644 --- a/arch/powerpc/include/asm/mmu_context.h +++ b/arch/powerpc/include/asm/mmu_context.h @@ -14,12 +14,13 @@ /* * Most if the context management is out of line */ +#define init_new_context init_new_context extern int init_new_context(struct task_struct *tsk, struct mm_struct *mm); +#define destroy_context destroy_context extern void destroy_context(struct mm_struct *mm); #ifdef CONFIG_SPAPR_TCE_IOMMU struct mm_iommu_table_group_mem_t; -extern int isolate_lru_page(struct page *page); /* from internal.h */ extern bool mm_iommu_preregistered(struct mm_struct *mm); extern long mm_iommu_new(struct mm_struct *mm, unsigned long ua, unsigned long entries, @@ -30,18 +31,12 @@ extern long mm_iommu_newdev(struct mm_struct *mm, unsigned long ua, extern long mm_iommu_put(struct mm_struct *mm, struct mm_iommu_table_group_mem_t *mem); extern void mm_iommu_init(struct mm_struct *mm); -extern void mm_iommu_cleanup(struct mm_struct *mm); extern struct mm_iommu_table_group_mem_t *mm_iommu_lookup(struct mm_struct *mm, unsigned long ua, unsigned long size); -extern struct mm_iommu_table_group_mem_t *mm_iommu_lookup_rm( - struct mm_struct *mm, unsigned long ua, unsigned long size); extern struct mm_iommu_table_group_mem_t *mm_iommu_get(struct mm_struct *mm, unsigned long ua, unsigned long entries); extern long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem, unsigned long ua, unsigned int pageshift, unsigned long *hpa); -extern long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem, - unsigned long ua, unsigned int pageshift, unsigned long *hpa); -extern void mm_iommu_ua_mark_dirty_rm(struct mm_struct *mm, unsigned long ua); extern bool mm_iommu_is_devmem(struct mm_struct *mm, unsigned long hpa, unsigned int pageshift, unsigned long *size); extern long mm_iommu_mapped_inc(struct mm_iommu_table_group_mem_t *mem); @@ -55,7 +50,6 @@ static inline bool mm_iommu_is_devmem(struct mm_struct *mm, unsigned long hpa, static inline void mm_iommu_init(struct mm_struct *mm) { } #endif extern void switch_slb(struct task_struct *tsk, struct mm_struct *mm); -extern void set_context(unsigned long id, pgd_t *pgd); #ifdef CONFIG_PPC_BOOK3S_64 extern void radix__switch_mmu_context(struct mm_struct *prev, @@ -70,10 +64,11 @@ static inline void switch_mmu_context(struct mm_struct *prev, } extern int hash__alloc_context_id(void); -extern void hash__reserve_context_id(int id); +void __init hash__reserve_context_id(int id); extern void __destroy_context(int context_id); static inline void mmu_context_init(void) { } +#ifdef CONFIG_PPC_64S_HASH_MMU static inline int alloc_extended_context(struct mm_struct *mm, unsigned long ea) { @@ -99,6 +94,7 @@ static inline bool need_extra_context(struct mm_struct *mm, unsigned long ea) return true; return false; } +#endif #else extern void switch_mmu_context(struct mm_struct *prev, struct mm_struct *next, @@ -120,13 +116,6 @@ static inline bool need_extra_context(struct mm_struct *mm, unsigned long ea) } #endif -#if defined(CONFIG_KVM_BOOK3S_HV_POSSIBLE) && defined(CONFIG_PPC_RADIX_MMU) -extern void radix_kvm_prefetch_workaround(struct mm_struct *mm); -#else -static inline void radix_kvm_prefetch_workaround(struct mm_struct *mm) { } -#endif - -extern void switch_cop(struct mm_struct *next); extern int use_cop(unsigned long acop, struct mm_struct *mm); extern void drop_cop(unsigned long acop, struct mm_struct *mm); @@ -138,6 +127,7 @@ static inline void inc_mm_active_cpus(struct mm_struct *mm) static inline void dec_mm_active_cpus(struct mm_struct *mm) { + VM_WARN_ON_ONCE(atomic_read(&mm->context.active_cpus) <= 0); atomic_dec(&mm->context.active_cpus); } @@ -162,8 +152,8 @@ static inline void mm_context_remove_copro(struct mm_struct *mm) * nMMU and/or PSL need to be cleaned up. * * Both the 'copros' and 'active_cpus' counts are looked at in - * flush_all_mm() to determine the scope (local/global) of the - * TLBIs, so we need to flush first before decrementing + * radix__flush_all_mm() to determine the scope (local/global) + * of the TLBIs, so we need to flush first before decrementing * 'copros'. If this API is used by several callers for the * same context, it can lead to over-flushing. It's hopefully * not common enough to be a problem. @@ -175,7 +165,7 @@ static inline void mm_context_remove_copro(struct mm_struct *mm) * in-between. */ if (radix_enabled()) { - flush_all_mm(mm); + radix__flush_all_mm(mm); c = atomic_dec_if_positive(&mm->context.copros); /* Detect imbalance between add and remove */ @@ -185,6 +175,34 @@ static inline void mm_context_remove_copro(struct mm_struct *mm) dec_mm_active_cpus(mm); } } + +/* + * vas_windows counter shows number of open windows in the mm + * context. During context switch, use this counter to clear the + * foreign real address mapping (CP_ABORT) for the thread / process + * that intend to use COPY/PASTE. When a process closes all windows, + * disable CP_ABORT which is expensive to run. + * + * For user context, register a copro so that TLBIs are seen by the + * nest MMU. mm_context_add/remove_vas_window() are used only for user + * space windows. + */ +static inline void mm_context_add_vas_window(struct mm_struct *mm) +{ + atomic_inc(&mm->context.vas_windows); + mm_context_add_copro(mm); +} + +static inline void mm_context_remove_vas_window(struct mm_struct *mm) +{ + int v; + + mm_context_remove_copro(mm); + v = atomic_dec_if_positive(&mm->context.vas_windows); + + /* Detect imbalance between add and remove */ + WARN_ON(v < 0); +} #else static inline void inc_mm_active_cpus(struct mm_struct *mm) { } static inline void dec_mm_active_cpus(struct mm_struct *mm) { } @@ -192,6 +210,18 @@ static inline void mm_context_add_copro(struct mm_struct *mm) { } static inline void mm_context_remove_copro(struct mm_struct *mm) { } #endif +#if defined(CONFIG_KVM_BOOK3S_HV_POSSIBLE) && defined(CONFIG_PPC_RADIX_MMU) +void do_h_rpt_invalidate_prt(unsigned long pid, unsigned long lpid, + unsigned long type, unsigned long pg_sizes, + unsigned long start, unsigned long end); +#else +static inline void do_h_rpt_invalidate_prt(unsigned long pid, + unsigned long lpid, + unsigned long type, + unsigned long pg_sizes, + unsigned long start, + unsigned long end) { } +#endif extern void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk); @@ -207,40 +237,36 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, } #define switch_mm_irqs_off switch_mm_irqs_off - -#define deactivate_mm(tsk,mm) do { } while (0) - /* * After we have set current->mm to a new value, this activates * the context for the new mm so we see the new mappings. */ +#define activate_mm activate_mm static inline void activate_mm(struct mm_struct *prev, struct mm_struct *next) { - switch_mm(prev, next, current); + switch_mm_irqs_off(prev, next, current); } /* We don't currently use enter_lazy_tlb() for anything */ +#ifdef CONFIG_PPC_BOOK3E_64 +#define enter_lazy_tlb enter_lazy_tlb static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk) { /* 64-bit Book3E keeps track of current PGD in the PACA */ -#ifdef CONFIG_PPC_BOOK3E_64 get_paca()->pgd = NULL; -#endif } +#endif extern void arch_exit_mmap(struct mm_struct *mm); static inline void arch_unmap(struct mm_struct *mm, unsigned long start, unsigned long end) { - if (start <= mm->context.vdso_base && mm->context.vdso_base < end) - mm->context.vdso_base = 0; -} + unsigned long vdso_base = (unsigned long)mm->context.vdso; -static inline void arch_bprm_mm_init(struct mm_struct *mm, - struct vm_area_struct *vma) -{ + if (start <= vdso_base && vdso_base < end) + mm->context.vdso = NULL; } #ifdef CONFIG_PPC_MEM_KEYS @@ -256,12 +282,9 @@ static inline bool arch_vma_access_permitted(struct vm_area_struct *vma, } #define pkey_mm_init(mm) -#define thread_pkey_regs_save(thread) -#define thread_pkey_regs_restore(new_thread, old_thread) -#define thread_pkey_regs_init(thread) #define arch_dup_pkeys(oldmm, mm) -static inline u64 pte_to_hpte_pkey_bits(u64 pteflags) +static inline u64 pte_to_hpte_pkey_bits(u64 pteflags, unsigned long flags) { return 0x0UL; } @@ -275,5 +298,7 @@ static inline int arch_dup_mmap(struct mm_struct *oldmm, return 0; } +#include <asm-generic/mmu_context.h> + #endif /* __KERNEL__ */ #endif /* __ASM_POWERPC_MMU_CONTEXT_H */ diff --git a/arch/powerpc/include/asm/mmzone.h b/arch/powerpc/include/asm/mmzone.h index 91c69ff53a8a..da827d2d0866 100644 --- a/arch/powerpc/include/asm/mmzone.h +++ b/arch/powerpc/include/asm/mmzone.h @@ -18,7 +18,7 @@ * flags field of the struct page */ -#ifdef CONFIG_NEED_MULTIPLE_NODES +#ifdef CONFIG_NUMA extern struct pglist_data *node_data[]; /* @@ -41,10 +41,7 @@ u64 memory_hotplug_max(void); #else #define memory_hotplug_max() memblock_end_of_DRAM() -#endif /* CONFIG_NEED_MULTIPLE_NODES */ -#ifdef CONFIG_FA_DUMP -#define __HAVE_ARCH_RESERVED_KERNEL_PAGES -#endif +#endif /* CONFIG_NUMA */ #endif /* __KERNEL__ */ #endif /* _ASM_MMZONE_H_ */ diff --git a/arch/powerpc/include/asm/module.h b/arch/powerpc/include/asm/module.h index 356658711a86..a8e2e8339fb7 100644 --- a/arch/powerpc/include/asm/module.h +++ b/arch/powerpc/include/asm/module.h @@ -3,28 +3,10 @@ #define _ASM_POWERPC_MODULE_H #ifdef __KERNEL__ -/* - */ - #include <linux/list.h> #include <asm/bug.h> #include <asm-generic/module.h> - -#ifdef CONFIG_MPROFILE_KERNEL -#define MODULE_ARCH_VERMAGIC_FTRACE "mprofile-kernel " -#else -#define MODULE_ARCH_VERMAGIC_FTRACE "" -#endif - -#ifdef CONFIG_RELOCATABLE -#define MODULE_ARCH_VERMAGIC_RELOCATABLE "relocatable " -#else -#define MODULE_ARCH_VERMAGIC_RELOCATABLE "" -#endif - -#define MODULE_ARCH_VERMAGIC MODULE_ARCH_VERMAGIC_FTRACE MODULE_ARCH_VERMAGIC_RELOCATABLE - #ifndef __powerpc64__ /* * Thanks to Paul M for explaining this. @@ -45,8 +27,13 @@ struct ppc_plt_entry { struct mod_arch_specific { #ifdef __powerpc64__ unsigned int stubs_section; /* Index of stubs section in module */ +#ifdef CONFIG_PPC_KERNEL_PCREL + unsigned int got_section; /* What section is the GOT? */ + unsigned int pcpu_section; /* .data..percpu section */ +#else unsigned int toc_section; /* What section is the TOC? */ bool toc_fixed; /* Have we fixed up .TOC.? */ +#endif /* For module function descriptor dereference */ unsigned long start_opd; @@ -59,10 +46,8 @@ struct mod_arch_specific { #ifdef CONFIG_DYNAMIC_FTRACE unsigned long tramp; -#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS unsigned long tramp_regs; #endif -#endif /* List of BUG addresses, source line numbers and filenames */ struct list_head bug_list; @@ -72,12 +57,15 @@ struct mod_arch_specific { /* * Select ELF headers. - * Make empty section for module_frob_arch_sections to expand. + * Make empty sections for module_frob_arch_sections to expand. */ #ifdef __powerpc64__ # ifdef MODULE asm(".section .stubs,\"ax\",@nobits; .align 3; .previous"); +# ifdef CONFIG_PPC_KERNEL_PCREL + asm(".section .mygot,\"a\",@nobits; .align 3; .previous"); +# endif # endif #else # ifdef MODULE @@ -87,15 +75,8 @@ struct mod_arch_specific { #endif #ifdef CONFIG_DYNAMIC_FTRACE -# ifdef MODULE - asm(".section .ftrace.tramp,\"ax\",@nobits; .align 3; .previous"); -# endif /* MODULE */ -#endif - int module_trampoline_target(struct module *mod, unsigned long trampoline, unsigned long *target); - -#ifdef CONFIG_DYNAMIC_FTRACE int module_finalize_ftrace(struct module *mod, const Elf_Shdr *sechdrs); #else static inline int module_finalize_ftrace(struct module *mod, const Elf_Shdr *sechdrs) diff --git a/arch/powerpc/include/asm/module.lds.h b/arch/powerpc/include/asm/module.lds.h new file mode 100644 index 000000000000..cea5dc124be4 --- /dev/null +++ b/arch/powerpc/include/asm/module.lds.h @@ -0,0 +1,8 @@ +/* Force alignment of .toc section. */ +SECTIONS +{ + .toc 0 : ALIGN(256) + { + *(.got .toc) + } +} diff --git a/arch/powerpc/include/asm/mpc52xx.h b/arch/powerpc/include/asm/mpc52xx.h index ce1e0aabaa64..01ae6c351e50 100644 --- a/arch/powerpc/include/asm/mpc52xx.h +++ b/arch/powerpc/include/asm/mpc52xx.h @@ -15,7 +15,6 @@ #ifndef __ASSEMBLY__ #include <asm/types.h> -#include <asm/prom.h> #include <asm/mpc5xxx.h> #endif /* __ASSEMBLY__ */ @@ -268,13 +267,14 @@ struct mpc52xx_intr { #ifndef __ASSEMBLY__ +struct device_node; + /* mpc52xx_common.c */ extern void mpc5200_setup_xlb_arbiter(void); extern void mpc52xx_declare_of_platform_devices(void); extern int mpc5200_psc_ac97_gpio_reset(int psc_number); extern void mpc52xx_map_common_devices(void); extern int mpc52xx_set_psc_clkdiv(int psc_id, int clkdiv); -extern unsigned int mpc52xx_get_xtal_freq(struct device_node *node); extern void __noreturn mpc52xx_restart(char *cmd); /* mpc52xx_gpt.c */ @@ -285,47 +285,6 @@ extern int mpc52xx_gpt_start_timer(struct mpc52xx_gpt_priv *gpt, u64 period, extern u64 mpc52xx_gpt_timer_period(struct mpc52xx_gpt_priv *gpt); extern int mpc52xx_gpt_stop_timer(struct mpc52xx_gpt_priv *gpt); -/* mpc52xx_lpbfifo.c */ -#define MPC52XX_LPBFIFO_FLAG_READ (0) -#define MPC52XX_LPBFIFO_FLAG_WRITE (1<<0) -#define MPC52XX_LPBFIFO_FLAG_NO_INCREMENT (1<<1) -#define MPC52XX_LPBFIFO_FLAG_NO_DMA (1<<2) -#define MPC52XX_LPBFIFO_FLAG_POLL_DMA (1<<3) - -struct mpc52xx_lpbfifo_request { - struct list_head list; - - /* localplus bus address */ - unsigned int cs; - size_t offset; - - /* Memory address */ - void *data; - phys_addr_t data_phys; - - /* Details of transfer */ - size_t size; - size_t pos; /* current position of transfer */ - int flags; - int defer_xfer_start; - - /* What to do when finished */ - void (*callback)(struct mpc52xx_lpbfifo_request *); - - void *priv; /* Driver private data */ - - /* statistics */ - int irq_count; - int irq_ticks; - u8 last_byte; - int buffer_not_done_cnt; -}; - -extern int mpc52xx_lpbfifo_submit(struct mpc52xx_lpbfifo_request *req); -extern void mpc52xx_lpbfifo_abort(struct mpc52xx_lpbfifo_request *req); -extern void mpc52xx_lpbfifo_poll(void); -extern int mpc52xx_lpbfifo_start_xfer(struct mpc52xx_lpbfifo_request *req); - /* mpc52xx_pic.c */ extern void mpc52xx_init_irq(void); extern unsigned int mpc52xx_get_irq(void); diff --git a/arch/powerpc/include/asm/mpc5xxx.h b/arch/powerpc/include/asm/mpc5xxx.h index 2f60f5c5461b..44db26380435 100644 --- a/arch/powerpc/include/asm/mpc5xxx.h +++ b/arch/powerpc/include/asm/mpc5xxx.h @@ -11,7 +11,14 @@ #ifndef __ASM_POWERPC_MPC5xxx_H__ #define __ASM_POWERPC_MPC5xxx_H__ -extern unsigned long mpc5xxx_get_bus_frequency(struct device_node *node); +#include <linux/property.h> + +unsigned long mpc5xxx_fwnode_get_bus_frequency(struct fwnode_handle *fwnode); + +static inline unsigned long mpc5xxx_get_bus_frequency(struct device *dev) +{ + return mpc5xxx_fwnode_get_bus_frequency(dev_fwnode(dev)); +} #endif /* __ASM_POWERPC_MPC5xxx_H__ */ diff --git a/arch/powerpc/include/asm/mpc8260.h b/arch/powerpc/include/asm/mpc8260.h deleted file mode 100644 index fd8c5707425b..000000000000 --- a/arch/powerpc/include/asm/mpc8260.h +++ /dev/null @@ -1,26 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Since there are many different boards and no standard configuration, - * we have a unique include file for each. Rather than change every - * file that has to include MPC8260 configuration, they all include - * this one and the configuration switching is done here. - */ -#ifdef __KERNEL__ -#ifndef __ASM_POWERPC_MPC8260_H__ -#define __ASM_POWERPC_MPC8260_H__ - -#define MPC82XX_BCR_PLDP 0x00800000 /* Pipeline Maximum Depth */ - -#ifdef CONFIG_8260 - -#if defined(CONFIG_PQ2ADS) || defined (CONFIG_PQ2FADS) -#include <platforms/82xx/pq2ads.h> -#endif - -#ifdef CONFIG_PCI_8260 -#include <platforms/82xx/m82xx_pci.h> -#endif - -#endif /* CONFIG_8260 */ -#endif /* !__ASM_POWERPC_MPC8260_H__ */ -#endif /* __KERNEL__ */ diff --git a/arch/powerpc/include/asm/mpic.h b/arch/powerpc/include/asm/mpic.h index 0abf2e7fd222..58353c5bd3fb 100644 --- a/arch/powerpc/include/asm/mpic.h +++ b/arch/powerpc/include/asm/mpic.h @@ -472,7 +472,7 @@ extern int mpic_cpu_get_priority(void); extern void mpic_cpu_set_priority(int prio); /* Request IPIs on primary mpic */ -extern void mpic_request_ipis(void); +void __init mpic_request_ipis(void); /* Send a message (IPI) to a given target (cpu number or MSG_*) */ void smp_mpic_message_pass(int target, int msg); diff --git a/arch/powerpc/include/asm/nmi.h b/arch/powerpc/include/asm/nmi.h index 84b4cfe73edd..49a75340c3e0 100644 --- a/arch/powerpc/include/asm/nmi.h +++ b/arch/powerpc/include/asm/nmi.h @@ -3,15 +3,10 @@ #define _ASM_NMI_H #ifdef CONFIG_PPC_WATCHDOG -extern void arch_touch_nmi_watchdog(void); +long soft_nmi_interrupt(struct pt_regs *regs); +void watchdog_hardlockup_set_timeout_pct(u64 pct); #else -static inline void arch_touch_nmi_watchdog(void) {} -#endif - -#if defined(CONFIG_NMI_IPI) && defined(CONFIG_STACKTRACE) -extern void arch_trigger_cpumask_backtrace(const cpumask_t *mask, - bool exclude_self); -#define arch_trigger_cpumask_backtrace arch_trigger_cpumask_backtrace +static inline void watchdog_hardlockup_set_timeout_pct(u64 pct) {} #endif extern void hv_nmi_check_nonrecoverable(struct pt_regs *regs); diff --git a/arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h b/arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h index a46616937d20..92df40c6cc6b 100644 --- a/arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h +++ b/arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h @@ -13,13 +13,13 @@ static inline pte_t *hugepd_page(hugepd_t hpd) static inline unsigned int hugepd_shift(hugepd_t hpd) { - return ((hpd_val(hpd) & _PMD_PAGE_MASK) >> 1) + 17; + return PAGE_SHIFT_8M; } static inline pte_t *hugepte_offset(hugepd_t hpd, unsigned long addr, unsigned int pdshift) { - unsigned long idx = (addr & ((1UL << pdshift) - 1)) >> PAGE_SHIFT; + unsigned long idx = (addr & (SZ_4M - 1)) >> PAGE_SHIFT; return hugepd_page(hpd) + idx; } @@ -32,8 +32,12 @@ static inline void flush_hugetlb_page(struct vm_area_struct *vma, static inline void hugepd_populate(hugepd_t *hpdp, pte_t *new, unsigned int pshift) { - *hpdp = __hugepd(__pa(new) | _PMD_USER | _PMD_PRESENT | - (pshift == PAGE_SHIFT_8M ? _PMD_PAGE_8M : _PMD_PAGE_512K)); + *hpdp = __hugepd(__pa(new) | _PMD_USER | _PMD_PRESENT | _PMD_PAGE_8M); +} + +static inline void hugepd_populate_kernel(hugepd_t *hpdp, pte_t *new, unsigned int pshift) +{ + *hpdp = __hugepd(__pa(new) | _PMD_PRESENT | _PMD_PAGE_8M); } static inline int check_and_get_huge_psize(int shift) @@ -41,4 +45,38 @@ static inline int check_and_get_huge_psize(int shift) return shift_to_mmu_psize(shift); } +#define __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT +void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, + pte_t pte, unsigned long sz); + +#define __HAVE_ARCH_HUGE_PTE_CLEAR +static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, unsigned long sz) +{ + pte_update(mm, addr, ptep, ~0UL, 0, 1); +} + +#define __HAVE_ARCH_HUGE_PTEP_SET_WRPROTECT +static inline void huge_ptep_set_wrprotect(struct mm_struct *mm, + unsigned long addr, pte_t *ptep) +{ + unsigned long clr = ~pte_val(pte_wrprotect(__pte(~0))); + unsigned long set = pte_val(pte_wrprotect(__pte(0))); + + pte_update(mm, addr, ptep, clr, set, 1); +} + +#ifdef CONFIG_PPC_4K_PAGES +static inline pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags) +{ + size_t size = 1UL << shift; + + if (size == SZ_16K) + return __pte(pte_val(entry) | _PAGE_SPS); + else + return __pte(pte_val(entry) | _PAGE_SPS | _PAGE_HUGE); +} +#define arch_make_huge_pte arch_make_huge_pte +#endif + #endif /* _ASM_POWERPC_NOHASH_32_HUGETLB_8XX_H */ diff --git a/arch/powerpc/include/asm/nohash/32/kup-8xx.h b/arch/powerpc/include/asm/nohash/32/kup-8xx.h index 1006a427e99c..46bc5925e5fd 100644 --- a/arch/powerpc/include/asm/nohash/32/kup-8xx.h +++ b/arch/powerpc/include/asm/nohash/32/kup-8xx.h @@ -7,49 +7,79 @@ #ifdef CONFIG_PPC_KUAP -#ifdef __ASSEMBLY__ +#ifndef __ASSEMBLY__ -.macro kuap_save_and_lock sp, thread, gpr1, gpr2, gpr3 - lis \gpr2, MD_APG_KUAP@h /* only APG0 and APG1 are used */ - mfspr \gpr1, SPRN_MD_AP - mtspr SPRN_MD_AP, \gpr2 - stw \gpr1, STACK_REGS_KUAP(\sp) -.endm +#include <asm/reg.h> + +static __always_inline void __kuap_save_and_lock(struct pt_regs *regs) +{ + regs->kuap = mfspr(SPRN_MD_AP); + mtspr(SPRN_MD_AP, MD_APG_KUAP); +} +#define __kuap_save_and_lock __kuap_save_and_lock + +static __always_inline void kuap_user_restore(struct pt_regs *regs) +{ +} -.macro kuap_restore sp, current, gpr1, gpr2, gpr3 - lwz \gpr1, STACK_REGS_KUAP(\sp) - mtspr SPRN_MD_AP, \gpr1 -.endm +static __always_inline void __kuap_kernel_restore(struct pt_regs *regs, unsigned long kuap) +{ + mtspr(SPRN_MD_AP, regs->kuap); +} -.macro kuap_check current, gpr #ifdef CONFIG_PPC_KUAP_DEBUG - mfspr \gpr, SPRN_MD_AP - rlwinm \gpr, \gpr, 16, 0xffff -999: twnei \gpr, MD_APG_KUAP@h - EMIT_BUG_ENTRY 999b, __FILE__, __LINE__, (BUGFLAG_WARNING | BUGFLAG_ONCE) +static __always_inline unsigned long __kuap_get_and_assert_locked(void) +{ + WARN_ON_ONCE(mfspr(SPRN_MD_AP) >> 16 != MD_APG_KUAP >> 16); + + return 0; +} +#define __kuap_get_and_assert_locked __kuap_get_and_assert_locked #endif -.endm -#else /* !__ASSEMBLY__ */ +static __always_inline void uaccess_begin_8xx(unsigned long val) +{ + asm(ASM_MMU_FTR_IFSET("mtspr %0, %1", "", %2) : : + "i"(SPRN_MD_AP), "r"(val), "i"(MMU_FTR_KUAP) : "memory"); +} + +static __always_inline void uaccess_end_8xx(void) +{ + asm(ASM_MMU_FTR_IFSET("mtspr %0, %1", "", %2) : : + "i"(SPRN_MD_AP), "r"(MD_APG_KUAP), "i"(MMU_FTR_KUAP) : "memory"); +} -#include <asm/reg.h> +static __always_inline void allow_user_access(void __user *to, const void __user *from, + unsigned long size, unsigned long dir) +{ + uaccess_begin_8xx(MD_APG_INIT); +} -static inline void allow_user_access(void __user *to, const void __user *from, - unsigned long size) +static __always_inline void prevent_user_access(unsigned long dir) { - mtspr(SPRN_MD_AP, MD_APG_INIT); + uaccess_end_8xx(); } -static inline void prevent_user_access(void __user *to, const void __user *from, - unsigned long size) +static __always_inline unsigned long prevent_user_access_return(void) { - mtspr(SPRN_MD_AP, MD_APG_KUAP); + unsigned long flags; + + flags = mfspr(SPRN_MD_AP); + + uaccess_end_8xx(); + + return flags; +} + +static __always_inline void restore_user_access(unsigned long flags) +{ + uaccess_begin_8xx(flags); } -static inline bool bad_kuap_fault(struct pt_regs *regs, bool is_write) +static __always_inline bool +__bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write) { - return WARN(!((regs->kuap ^ MD_APG_KUAP) & 0xf0000000), - "Bug: fault blocked by AP register !"); + return !((regs->kuap ^ MD_APG_KUAP) & 0xff000000); } #endif /* !__ASSEMBLY__ */ diff --git a/arch/powerpc/include/asm/nohash/32/mmu-40x.h b/arch/powerpc/include/asm/nohash/32/mmu-40x.h index 74f4edb5916e..8a8f13a22cf4 100644 --- a/arch/powerpc/include/asm/nohash/32/mmu-40x.h +++ b/arch/powerpc/include/asm/nohash/32/mmu-40x.h @@ -57,7 +57,7 @@ typedef struct { unsigned int id; unsigned int active; - unsigned long vdso_base; + void __user *vdso; } mm_context_t; #endif /* !__ASSEMBLY__ */ diff --git a/arch/powerpc/include/asm/nohash/32/mmu-44x.h b/arch/powerpc/include/asm/nohash/32/mmu-44x.h index 28aa3b339c5e..2d92a39d8f2e 100644 --- a/arch/powerpc/include/asm/nohash/32/mmu-44x.h +++ b/arch/powerpc/include/asm/nohash/32/mmu-44x.h @@ -108,7 +108,7 @@ extern unsigned int tlb_44x_index; typedef struct { unsigned int id; unsigned int active; - unsigned long vdso_base; + void __user *vdso; } mm_context_t; /* patch sites */ diff --git a/arch/powerpc/include/asm/nohash/32/mmu-8xx.h b/arch/powerpc/include/asm/nohash/32/mmu-8xx.h index 76af5b0cb16e..141d82e249a8 100644 --- a/arch/powerpc/include/asm/nohash/32/mmu-8xx.h +++ b/arch/powerpc/include/asm/nohash/32/mmu-8xx.h @@ -19,7 +19,6 @@ #define MI_RSV4I 0x08000000 /* Reserve 4 TLB entries */ #define MI_PPCS 0x02000000 /* Use MI_RPN prob/priv state */ #define MI_IDXMASK 0x00001f00 /* TLB index to be loaded */ -#define MI_RESETVAL 0x00000000 /* Value of register at reset */ /* These are the Ks and Kp from the PowerPC books. For proper operation, * Ks = 0, Kp = 1. @@ -34,19 +33,16 @@ * respectively NA for All or X for Supervisor and no access for User. * Then we use the APG to say whether accesses are according to Page rules or * "all Supervisor" rules (Access to all) - * Therefore, we define 2 APG groups. lsb is _PMD_USER - * 0 => Kernel => 01 (all accesses performed according to page definition) - * 1 => User => 00 (all accesses performed as supervisor iaw page definition) - * 2-16 => NA => 11 (all accesses performed as user iaw page definition) + * _PAGE_ACCESSED is also managed via APG. When _PAGE_ACCESSED is not set, say + * "all User" rules, that will lead to NA for all. + * Therefore, we define 4 APG groups. lsb is _PAGE_ACCESSED + * 0 => Kernel => 11 (all accesses performed according as user iaw page definition) + * 1 => Kernel+Accessed => 01 (all accesses performed according to page definition) + * 2 => User => 11 (all accesses performed according as user iaw page definition) + * 3 => User+Accessed => 10 (all accesses performed according to swaped page definition) for KUEP + * 4-15 => Not Used */ -#define MI_APG_INIT 0x4fffffff - -/* - * 0 => Kernel => 01 (all accesses performed according to page definition) - * 1 => User => 10 (all accesses performed according to swaped page definition) - * 2-16 => NA => 11 (all accesses performed as user iaw page definition) - */ -#define MI_APG_KUEP 0x6fffffff +#define MI_APG_INIT 0xde000000 /* The effective page number register. When read, contains the information * about the last instruction TLB miss. When MI_RPN is written, bits in @@ -95,7 +91,6 @@ #define MD_TWAM 0x04000000 /* Use 4K page hardware assist */ #define MD_PPCS 0x02000000 /* Use MI_RPN prob/priv state */ #define MD_IDXMASK 0x00001f00 /* TLB index to be loaded */ -#define MD_RESETVAL 0x04000000 /* Value of register at reset */ #define SPRN_M_CASID 793 /* Address space ID (context) to match */ #define MC_ASIDMASK 0x0000000f /* Bits used for ASID value */ @@ -108,25 +103,9 @@ #define MD_Ks 0x80000000 /* Should not be set */ #define MD_Kp 0x40000000 /* Should always be set */ -/* - * All pages' PP data bits are set to either 000 or 011 or 001, which means - * respectively RW for Supervisor and no access for User, or RO for - * Supervisor and no access for user and NA for ALL. - * Then we use the APG to say whether accesses are according to Page rules or - * "all Supervisor" rules (Access to all) - * Therefore, we define 2 APG groups. lsb is _PMD_USER - * 0 => Kernel => 01 (all accesses performed according to page definition) - * 1 => User => 00 (all accesses performed as supervisor iaw page definition) - * 2-16 => NA => 11 (all accesses performed as user iaw page definition) - */ -#define MD_APG_INIT 0x4fffffff - -/* - * 0 => No user => 01 (all accesses performed according to page definition) - * 1 => User => 10 (all accesses performed according to swaped page definition) - * 2-16 => NA => 11 (all accesses performed as user iaw page definition) - */ -#define MD_APG_KUAP 0x6fffffff +/* See explanation above at the definition of MI_APG_INIT */ +#define MD_APG_INIT 0xdc000000 +#define MD_APG_KUAP 0xde000000 /* The effective page number register. When read, contains the information * about the last instruction TLB miss. When MD_RPN is written, bits in @@ -178,12 +157,6 @@ */ #define SPRN_M_TW 799 -#ifdef CONFIG_PPC_MM_SLICES -#include <asm/nohash/32/slice.h> -#define SLICE_ARRAY_SIZE (1 << (32 - SLICE_LOW_SHIFT - 1)) -#define LOW_SLICE_ARRAY_SZ SLICE_ARRAY_SIZE -#endif - #if defined(CONFIG_PPC_4K_PAGES) #define mmu_virtual_psize MMU_PAGE_4K #elif defined(CONFIG_PPC_16K_PAGES) @@ -197,77 +170,24 @@ #define mmu_linear_psize MMU_PAGE_8M +#define MODULES_VADDR (PAGE_OFFSET - SZ_256M) +#define MODULES_END PAGE_OFFSET + #ifndef __ASSEMBLY__ #include <linux/mmdebug.h> +#include <linux/sizes.h> -struct slice_mask { - u64 low_slices; - DECLARE_BITMAP(high_slices, 0); -}; +void mmu_pin_tlb(unsigned long top, bool readonly); typedef struct { unsigned int id; unsigned int active; - unsigned long vdso_base; -#ifdef CONFIG_PPC_MM_SLICES - u16 user_psize; /* page size index */ - unsigned char low_slices_psize[SLICE_ARRAY_SIZE]; - unsigned char high_slices_psize[0]; - unsigned long slb_addr_limit; - struct slice_mask mask_base_psize; /* 4k or 16k */ - struct slice_mask mask_512k; - struct slice_mask mask_8m; -#endif + void __user *vdso; void *pte_frag; } mm_context_t; -#ifdef CONFIG_PPC_MM_SLICES -static inline u16 mm_ctx_user_psize(mm_context_t *ctx) -{ - return ctx->user_psize; -} - -static inline void mm_ctx_set_user_psize(mm_context_t *ctx, u16 user_psize) -{ - ctx->user_psize = user_psize; -} - -static inline unsigned char *mm_ctx_low_slices(mm_context_t *ctx) -{ - return ctx->low_slices_psize; -} - -static inline unsigned char *mm_ctx_high_slices(mm_context_t *ctx) -{ - return ctx->high_slices_psize; -} - -static inline unsigned long mm_ctx_slb_addr_limit(mm_context_t *ctx) -{ - return ctx->slb_addr_limit; -} - -static inline void mm_ctx_set_slb_addr_limit(mm_context_t *ctx, unsigned long limit) -{ - ctx->slb_addr_limit = limit; -} - -static inline struct slice_mask *slice_mask_for_size(mm_context_t *ctx, int psize) -{ - if (psize == MMU_PAGE_512K) - return &ctx->mask_512k; - if (psize == MMU_PAGE_8M) - return &ctx->mask_8m; - - BUG_ON(psize != mmu_virtual_psize); - - return &ctx->mask_base_psize; -} -#endif /* CONFIG_PPC_MM_SLICE */ - #define PHYS_IMMR_BASE (mfspr(SPRN_IMMR) & 0xfff80000) -#define VIRT_IMMR_BASE (__fix_to_virt(FIX_IMMR_BASE)) /* Page size definitions, common between 32 and 64-bit * @@ -303,14 +223,50 @@ static inline unsigned int mmu_psize_to_shift(unsigned int mmu_psize) BUG(); } -/* patch sites */ -extern s32 patch__itlbmiss_linmem_top, patch__itlbmiss_linmem_top8; -extern s32 patch__dtlbmiss_linmem_top, patch__dtlbmiss_immr_jmp; -extern s32 patch__fixupdar_linmem_top; -extern s32 patch__dtlbmiss_romem_top, patch__dtlbmiss_romem_top8; +static inline bool arch_vmap_try_size(unsigned long addr, unsigned long end, u64 pfn, + unsigned int max_page_shift, unsigned long size) +{ + if (end - addr < size) + return false; + + if ((1UL << max_page_shift) < size) + return false; + + if (!IS_ALIGNED(addr, size)) + return false; + + if (!IS_ALIGNED(PFN_PHYS(pfn), size)) + return false; -extern s32 patch__itlbmiss_exit_1, patch__itlbmiss_exit_2; -extern s32 patch__dtlbmiss_exit_1, patch__dtlbmiss_exit_2, patch__dtlbmiss_exit_3; + return true; +} + +static inline unsigned long arch_vmap_pte_range_map_size(unsigned long addr, unsigned long end, + u64 pfn, unsigned int max_page_shift) +{ + if (arch_vmap_try_size(addr, end, pfn, max_page_shift, SZ_512K)) + return SZ_512K; + if (PAGE_SIZE == SZ_16K) + return SZ_16K; + if (arch_vmap_try_size(addr, end, pfn, max_page_shift, SZ_16K)) + return SZ_16K; + return PAGE_SIZE; +} +#define arch_vmap_pte_range_map_size arch_vmap_pte_range_map_size + +static inline int arch_vmap_pte_supported_shift(unsigned long size) +{ + if (size >= SZ_512K) + return 19; + else if (size >= SZ_16K) + return 14; + else + return PAGE_SHIFT; +} +#define arch_vmap_pte_supported_shift arch_vmap_pte_supported_shift + +/* patch sites */ +extern s32 patch__itlbmiss_exit_1, patch__dtlbmiss_exit_1; extern s32 patch__itlbmiss_perf, patch__dtlbmiss_perf; #endif /* !__ASSEMBLY__ */ diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h index 552b96eef0c8..9164a9e41b02 100644 --- a/arch/powerpc/include/asm/nohash/32/pgtable.h +++ b/arch/powerpc/include/asm/nohash/32/pgtable.h @@ -2,18 +2,12 @@ #ifndef _ASM_POWERPC_NOHASH_32_PGTABLE_H #define _ASM_POWERPC_NOHASH_32_PGTABLE_H -#define __ARCH_USE_5LEVEL_HACK #include <asm-generic/pgtable-nopmd.h> #ifndef __ASSEMBLY__ #include <linux/sched.h> #include <linux/threads.h> #include <asm/mmu.h> /* For sub-arch specific PPC_PIN_SIZE */ -#include <asm/asm-405.h> - -#ifdef CONFIG_44x -extern int icache_44x_need_flush; -#endif #endif /* __ASSEMBLY__ */ @@ -30,6 +24,8 @@ extern int icache_44x_need_flush; #define PMD_TABLE_SIZE 0 #define PUD_TABLE_SIZE 0 #define PGD_TABLE_SIZE (sizeof(pgd_t) << PGD_INDEX_SIZE) + +#define PMD_MASKED_BITS (PTE_TABLE_SIZE - 1) #endif /* __ASSEMBLY__ */ #define PTRS_PER_PTE (1 << PTE_INDEX_SIZE) @@ -54,27 +50,23 @@ extern int icache_44x_need_flush; #define PGD_MASKED_BITS 0 #define USER_PTRS_PER_PGD (TASK_SIZE / PGDIR_SIZE) -#define FIRST_USER_ADDRESS 0UL -#define pte_ERROR(e) \ - pr_err("%s:%d: bad pte %llx.\n", __FILE__, __LINE__, \ - (unsigned long long)pte_val(e)) #define pgd_ERROR(e) \ pr_err("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e)) -#ifndef __ASSEMBLY__ - -int map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot); - -#endif /* !__ASSEMBLY__ */ - - /* * This is the bottom of the PKMAP area with HIGHMEM or an arbitrary * value (for now) on others, from where we can start layout kernel * virtual space that goes below PKMAP and FIXMAP */ -#include <asm/fixmap.h> + +#define FIXADDR_SIZE 0 +#ifdef CONFIG_KASAN +#include <asm/kasan.h> +#define FIXADDR_TOP (KASAN_SHADOW_START - PAGE_SIZE) +#else +#define FIXADDR_TOP ((unsigned long)(-PAGE_SIZE)) +#endif /* * ioremap_bot starts at that address. Early ioremaps move down from there, @@ -110,11 +102,16 @@ int map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot); */ #define VMALLOC_OFFSET (0x1000000) /* 16M */ #ifdef PPC_PIN_SIZE -#define VMALLOC_START (((_ALIGN((long)high_memory, PPC_PIN_SIZE) + VMALLOC_OFFSET) & ~(VMALLOC_OFFSET-1))) +#define VMALLOC_START (((ALIGN((long)high_memory, PPC_PIN_SIZE) + VMALLOC_OFFSET) & ~(VMALLOC_OFFSET-1))) #else #define VMALLOC_START ((((long)high_memory + VMALLOC_OFFSET) & ~(VMALLOC_OFFSET-1))) #endif + +#ifdef CONFIG_KASAN_VMALLOC +#define VMALLOC_END ALIGN_DOWN(ioremap_bot, PAGE_SIZE << KASAN_SHADOW_SCALE_SHIFT) +#else #define VMALLOC_END ioremap_bot +#endif /* * Bits in a linux-style PTE. These match the bits in the @@ -125,10 +122,10 @@ int map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot); #include <asm/nohash/32/pte-40x.h> #elif defined(CONFIG_44x) #include <asm/nohash/32/pte-44x.h> -#elif defined(CONFIG_FSL_BOOKE) && defined(CONFIG_PTE_64BIT) -#include <asm/nohash/pte-book3e.h> -#elif defined(CONFIG_FSL_BOOKE) -#include <asm/nohash/32/pte-fsl-booke.h> +#elif defined(CONFIG_PPC_85xx) && defined(CONFIG_PTE_64BIT) +#include <asm/nohash/pte-e500.h> +#elif defined(CONFIG_PPC_85xx) +#include <asm/nohash/32/pte-85xx.h> #elif defined(CONFIG_PPC_8xx) #include <asm/nohash/32/pte-8xx.h> #endif @@ -146,52 +143,16 @@ int map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot); * The mask covered by the RPN must be a ULL on 32-bit platforms with * 64-bit PTEs. */ -#if defined(CONFIG_PPC32) && defined(CONFIG_PTE_64BIT) +#ifdef CONFIG_PTE_64BIT #define PTE_RPN_MASK (~((1ULL << PTE_RPN_SHIFT) - 1)) +#define MAX_POSSIBLE_PHYSMEM_BITS 36 #else #define PTE_RPN_MASK (~((1UL << PTE_RPN_SHIFT) - 1)) +#define MAX_POSSIBLE_PHYSMEM_BITS 32 #endif -/* - * _PAGE_CHG_MASK masks of bits that are to be preserved across - * pgprot changes. - */ -#define _PAGE_CHG_MASK (PTE_RPN_MASK | _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_SPECIAL) - #ifndef __ASSEMBLY__ -#define pte_clear(mm, addr, ptep) \ - do { pte_update(ptep, ~0, 0); } while (0) - -#ifndef pte_mkwrite -static inline pte_t pte_mkwrite(pte_t pte) -{ - return __pte(pte_val(pte) | _PAGE_RW); -} -#endif - -static inline pte_t pte_mkdirty(pte_t pte) -{ - return __pte(pte_val(pte) | _PAGE_DIRTY); -} - -static inline pte_t pte_mkyoung(pte_t pte) -{ - return __pte(pte_val(pte) | _PAGE_ACCESSED); -} - -#ifndef pte_wrprotect -static inline pte_t pte_wrprotect(pte_t pte) -{ - return __pte(pte_val(pte) & ~_PAGE_RW); -} -#endif - -static inline pte_t pte_mkexec(pte_t pte) -{ - return __pte(pte_val(pte) | _PAGE_EXEC); -} - #define pmd_none(pmd) (!pmd_val(pmd)) #define pmd_bad(pmd) (pmd_val(pmd) & _PMD_BAD) #define pmd_present(pmd) (pmd_val(pmd) & _PMD_PRESENT_MASK) @@ -200,141 +161,6 @@ static inline void pmd_clear(pmd_t *pmdp) *pmdp = __pmd(0); } - - -/* - * PTE updates. This function is called whenever an existing - * valid PTE is updated. This does -not- include set_pte_at() - * which nowadays only sets a new PTE. - * - * Depending on the type of MMU, we may need to use atomic updates - * and the PTE may be either 32 or 64 bit wide. In the later case, - * when using atomic updates, only the low part of the PTE is - * accessed atomically. - * - * In addition, on 44x, we also maintain a global flag indicating - * that an executable user mapping was modified, which is needed - * to properly flush the virtually tagged instruction cache of - * those implementations. - */ -#ifndef CONFIG_PTE_64BIT -static inline unsigned long pte_update(pte_t *p, - unsigned long clr, - unsigned long set) -{ -#ifdef PTE_ATOMIC_UPDATES - unsigned long old, tmp; - - __asm__ __volatile__("\ -1: lwarx %0,0,%3\n\ - andc %1,%0,%4\n\ - or %1,%1,%5\n" - PPC405_ERR77(0,%3) -" stwcx. %1,0,%3\n\ - bne- 1b" - : "=&r" (old), "=&r" (tmp), "=m" (*p) - : "r" (p), "r" (clr), "r" (set), "m" (*p) - : "cc" ); -#else /* PTE_ATOMIC_UPDATES */ - unsigned long old = pte_val(*p); - unsigned long new = (old & ~clr) | set; - -#if defined(CONFIG_PPC_8xx) && defined(CONFIG_PPC_16K_PAGES) - p->pte = p->pte1 = p->pte2 = p->pte3 = new; -#else - *p = __pte(new); -#endif -#endif /* !PTE_ATOMIC_UPDATES */ - -#ifdef CONFIG_44x - if ((old & _PAGE_USER) && (old & _PAGE_EXEC)) - icache_44x_need_flush = 1; -#endif - return old; -} -#else /* CONFIG_PTE_64BIT */ -static inline unsigned long long pte_update(pte_t *p, - unsigned long clr, - unsigned long set) -{ -#ifdef PTE_ATOMIC_UPDATES - unsigned long long old; - unsigned long tmp; - - __asm__ __volatile__("\ -1: lwarx %L0,0,%4\n\ - lwzx %0,0,%3\n\ - andc %1,%L0,%5\n\ - or %1,%1,%6\n" - PPC405_ERR77(0,%3) -" stwcx. %1,0,%4\n\ - bne- 1b" - : "=&r" (old), "=&r" (tmp), "=m" (*p) - : "r" (p), "r" ((unsigned long)(p) + 4), "r" (clr), "r" (set), "m" (*p) - : "cc" ); -#else /* PTE_ATOMIC_UPDATES */ - unsigned long long old = pte_val(*p); - *p = __pte((old & ~(unsigned long long)clr) | set); -#endif /* !PTE_ATOMIC_UPDATES */ - -#ifdef CONFIG_44x - if ((old & _PAGE_USER) && (old & _PAGE_EXEC)) - icache_44x_need_flush = 1; -#endif - return old; -} -#endif /* CONFIG_PTE_64BIT */ - -#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG -static inline int __ptep_test_and_clear_young(unsigned int context, unsigned long addr, pte_t *ptep) -{ - unsigned long old; - old = pte_update(ptep, _PAGE_ACCESSED, 0); - return (old & _PAGE_ACCESSED) != 0; -} -#define ptep_test_and_clear_young(__vma, __addr, __ptep) \ - __ptep_test_and_clear_young((__vma)->vm_mm->context.id, __addr, __ptep) - -#define __HAVE_ARCH_PTEP_GET_AND_CLEAR -static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, - pte_t *ptep) -{ - return __pte(pte_update(ptep, ~0, 0)); -} - -#define __HAVE_ARCH_PTEP_SET_WRPROTECT -static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, - pte_t *ptep) -{ - unsigned long clr = ~pte_val(pte_wrprotect(__pte(~0))); - unsigned long set = pte_val(pte_wrprotect(__pte(0))); - - pte_update(ptep, clr, set); -} - -static inline void __ptep_set_access_flags(struct vm_area_struct *vma, - pte_t *ptep, pte_t entry, - unsigned long address, - int psize) -{ - pte_t pte_set = pte_mkyoung(pte_mkdirty(pte_mkwrite(pte_mkexec(__pte(0))))); - pte_t pte_clr = pte_mkyoung(pte_mkdirty(pte_mkwrite(pte_mkexec(__pte(~0))))); - unsigned long set = pte_val(entry) & pte_val(pte_set); - unsigned long clr = ~pte_val(entry) & ~pte_val(pte_clr); - - pte_update(ptep, clr, set); - - flush_tlb_page(vma, address); -} - -static inline int pte_young(pte_t pte) -{ - return pte_val(pte) & _PAGE_ACCESSED; -} - -#define __HAVE_ARCH_PTE_SAME -#define pte_same(A,B) ((pte_val(A) ^ pte_val(B)) == 0) - /* * Note that on Book E processors, the pmd contains the kernel virtual * (lowmem) address of the pte page. The physical address is less useful @@ -343,47 +169,38 @@ static inline int pte_young(pte_t pte) * of the pte page. -- paulus */ #ifndef CONFIG_BOOKE -#define pmd_page_vaddr(pmd) \ - ((unsigned long)__va(pmd_val(pmd) & ~(PTE_TABLE_SIZE - 1))) -#define pmd_page(pmd) \ - pfn_to_page(pmd_val(pmd) >> PAGE_SHIFT) +#define pmd_pfn(pmd) (pmd_val(pmd) >> PAGE_SHIFT) #else #define pmd_page_vaddr(pmd) \ - ((unsigned long)(pmd_val(pmd) & ~(PTE_TABLE_SIZE - 1))) -#define pmd_page(pmd) \ - pfn_to_page((__pa(pmd_val(pmd)) >> PAGE_SHIFT)) + ((const void *)(pmd_val(pmd) & ~(PTE_TABLE_SIZE - 1))) +#define pmd_pfn(pmd) (__pa(pmd_val(pmd)) >> PAGE_SHIFT) #endif -/* to find an entry in a kernel page-table-directory */ -#define pgd_offset_k(address) pgd_offset(&init_mm, address) - -/* to find an entry in a page-table-directory */ -#define pgd_index(address) ((address) >> PGDIR_SHIFT) -#define pgd_offset(mm, address) ((mm)->pgd + pgd_index(address)) - -/* Find an entry in the third-level page table.. */ -#define pte_index(address) \ - (((address) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1)) -#define pte_offset_kernel(dir, addr) \ - (pmd_bad(*(dir)) ? NULL : (pte_t *)pmd_page_vaddr(*(dir)) + \ - pte_index(addr)) -#define pte_offset_map(dir, addr) \ - ((pte_t *)(kmap_atomic(pmd_page(*(dir))) + \ - (pmd_page_vaddr(*(dir)) & ~PAGE_MASK)) + pte_index(addr)) -#define pte_unmap(pte) kunmap_atomic(pte) +#define pmd_page(pmd) pfn_to_page(pmd_pfn(pmd)) /* - * Encode and decode a swap entry. - * Note that the bits we use in a PTE for representing a swap entry - * must not include the _PAGE_PRESENT bit. - * -- paulus + * Encode/decode swap entries and swap PTEs. Swap PTEs are all PTEs that + * are !pte_none() && !pte_present(). + * + * Format of swap PTEs (32bit PTEs): + * + * 1 1 1 1 1 1 1 1 1 2 2 2 2 2 2 2 2 2 2 3 3 + * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 + * <------------------ offset -------------------> < type -> E 0 0 + * + * E is the exclusive marker that is not stored in swap entries. + * + * For 64bit PTEs, the offset is extended by 32bit. */ #define __swp_type(entry) ((entry).val & 0x1f) #define __swp_offset(entry) ((entry).val >> 5) -#define __swp_entry(type, offset) ((swp_entry_t) { (type) | ((offset) << 5) }) +#define __swp_entry(type, offset) ((swp_entry_t) { ((type) & 0x1f) | ((offset) << 5) }) #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) >> 3 }) #define __swp_entry_to_pte(x) ((pte_t) { (x).val << 3 }) +/* We borrow LSB 2 to store the exclusive marker in swap PTEs. */ +#define _PAGE_SWP_EXCLUSIVE 0x000004 + #endif /* !__ASSEMBLY__ */ #endif /* __ASM_POWERPC_NOHASH_32_PGTABLE_H */ diff --git a/arch/powerpc/include/asm/nohash/32/pte-40x.h b/arch/powerpc/include/asm/nohash/32/pte-40x.h index 12c6811e344b..d759cfd74754 100644 --- a/arch/powerpc/include/asm/nohash/32/pte-40x.h +++ b/arch/powerpc/include/asm/nohash/32/pte-40x.h @@ -27,9 +27,9 @@ * of the 16 available. Bit 24-26 of the TLB are cleared in the TLB * miss handler. Bit 27 is PAGE_USER, thus selecting the correct * zone. - * - PRESENT *must* be in the bottom two bits because swap cache - * entries use the top 30 bits. Because 40x doesn't support SMP - * anyway, M is irrelevant so we borrow it for PAGE_PRESENT. Bit 30 + * - PRESENT *must* be in the bottom two bits because swap PTEs + * use the top 30 bits. Because 40x doesn't support SMP anyway, M is + * irrelevant so we borrow it for PAGE_PRESENT. Bit 30 * is cleared in the TLB miss handler before the TLB entry is loaded. * - All other bits of the PTE are loaded into TLBLO without * modification, leaving us only the bits 20, 21, 24, 25, 26, 30 for @@ -42,11 +42,10 @@ #define _PAGE_PRESENT 0x002 /* software: PTE contains a translation */ #define _PAGE_NO_CACHE 0x004 /* I: caching is inhibited */ #define _PAGE_WRITETHRU 0x008 /* W: caching is write-through */ -#define _PAGE_USER 0x010 /* matches one of the zone permission bits */ +#define _PAGE_READ 0x010 /* software: read permission */ #define _PAGE_SPECIAL 0x020 /* software: Special page */ -#define _PAGE_RW 0x040 /* software: Writes permitted */ #define _PAGE_DIRTY 0x080 /* software: dirty page */ -#define _PAGE_HWWRITE 0x100 /* hardware: Dirty & RW, set in exception */ +#define _PAGE_WRITE 0x100 /* hardware: WR, anded with dirty in exception */ #define _PAGE_EXEC 0x200 /* hardware: EX permission */ #define _PAGE_ACCESSED 0x400 /* software: R: page referenced */ @@ -56,11 +55,6 @@ /* cache related flags non existing on 40x */ #define _PAGE_COHERENT 0 -#define _PAGE_KERNEL_RO 0 -#define _PAGE_KERNEL_ROX _PAGE_EXEC -#define _PAGE_KERNEL_RW (_PAGE_DIRTY | _PAGE_RW | _PAGE_HWWRITE) -#define _PAGE_KERNEL_RWX (_PAGE_DIRTY | _PAGE_RW | _PAGE_HWWRITE | _PAGE_EXEC) - #define _PMD_PRESENT 0x400 /* PMD points to page of PTEs */ #define _PMD_PRESENT_MASK _PMD_PRESENT #define _PMD_BAD 0x802 @@ -70,36 +64,10 @@ #define _PTE_NONE_MASK 0 -/* Until my rework is finished, 40x still needs atomic PTE updates */ -#define PTE_ATOMIC_UPDATES 1 - #define _PAGE_BASE_NC (_PAGE_PRESENT | _PAGE_ACCESSED) #define _PAGE_BASE (_PAGE_BASE_NC) -/* Permission masks used to generate the __P and __S table */ -#define PAGE_NONE __pgprot(_PAGE_BASE) -#define PAGE_SHARED __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RW) -#define PAGE_SHARED_X __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RW | _PAGE_EXEC) -#define PAGE_COPY __pgprot(_PAGE_BASE | _PAGE_USER) -#define PAGE_COPY_X __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_EXEC) -#define PAGE_READONLY __pgprot(_PAGE_BASE | _PAGE_USER) -#define PAGE_READONLY_X __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_EXEC) - -#ifndef __ASSEMBLY__ -static inline pte_t pte_wrprotect(pte_t pte) -{ - return __pte(pte_val(pte) & ~(_PAGE_RW | _PAGE_HWWRITE)); -} - -#define pte_wrprotect pte_wrprotect - -static inline pte_t pte_mkclean(pte_t pte) -{ - return __pte(pte_val(pte) & ~(_PAGE_DIRTY | _PAGE_HWWRITE)); -} - -#define pte_mkclean pte_mkclean -#endif +#include <asm/pgtable-masks.h> #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_NOHASH_32_PTE_40x_H */ diff --git a/arch/powerpc/include/asm/nohash/32/pte-44x.h b/arch/powerpc/include/asm/nohash/32/pte-44x.h index 78bc304f750e..851813725237 100644 --- a/arch/powerpc/include/asm/nohash/32/pte-44x.h +++ b/arch/powerpc/include/asm/nohash/32/pte-44x.h @@ -56,29 +56,19 @@ * above bits. Note that the bit values are CPU specific, not architecture * specific. * - * The kernel PTE entry holds an arch-dependent swp_entry structure under - * certain situations. In other words, in such situations some portion of - * the PTE bits are used as a swp_entry. In the PPC implementation, the - * 3-24th LSB are shared with swp_entry, however the 0-2nd three LSB still - * hold protection values. That means the three protection bits are - * reserved for both PTE and SWAP entry at the most significant three - * LSBs. - * - * There are three protection bits available for SWAP entry: - * _PAGE_PRESENT - * _PAGE_HASHPTE (if HW has) - * - * So those three bits have to be inside of 0-2nd LSB of PTE. - * + * The kernel PTE entry can be an ordinary PTE mapping a page or a special swap + * PTE. In case of a swap PTE, LSB 2-24 are used to store information regarding + * the swap entry. However LSB 0-1 still hold protection values, for example, + * to distinguish swap PTEs from ordinary PTEs, and must be used with care. */ #define _PAGE_PRESENT 0x00000001 /* S: PTE valid */ -#define _PAGE_RW 0x00000002 /* S: Write permission */ +#define _PAGE_WRITE 0x00000002 /* S: Write permission */ #define _PAGE_EXEC 0x00000004 /* H: Execute permission */ -#define _PAGE_ACCESSED 0x00000008 /* S: Page referenced */ +#define _PAGE_READ 0x00000008 /* S: Read permission */ #define _PAGE_DIRTY 0x00000010 /* S: Page dirty */ #define _PAGE_SPECIAL 0x00000020 /* S: Special page */ -#define _PAGE_USER 0x00000040 /* S: User page */ +#define _PAGE_ACCESSED 0x00000040 /* S: Page referenced */ #define _PAGE_ENDIAN 0x00000080 /* H: E bit */ #define _PAGE_GUARDED 0x00000100 /* H: G bit */ #define _PAGE_COHERENT 0x00000200 /* H: M bit */ @@ -88,11 +78,6 @@ /* No page size encoding in the linux PTE */ #define _PAGE_PSIZE 0 -#define _PAGE_KERNEL_RO 0 -#define _PAGE_KERNEL_ROX _PAGE_EXEC -#define _PAGE_KERNEL_RW (_PAGE_DIRTY | _PAGE_RW) -#define _PAGE_KERNEL_RWX (_PAGE_DIRTY | _PAGE_RW | _PAGE_EXEC) - /* TODO: Add large page lowmem mapping support */ #define _PMD_PRESENT 0 #define _PMD_PRESENT_MASK (PAGE_MASK) @@ -115,14 +100,7 @@ #define _PAGE_BASE (_PAGE_BASE_NC) #endif -/* Permission masks used to generate the __P and __S table */ -#define PAGE_NONE __pgprot(_PAGE_BASE) -#define PAGE_SHARED __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RW) -#define PAGE_SHARED_X __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RW | _PAGE_EXEC) -#define PAGE_COPY __pgprot(_PAGE_BASE | _PAGE_USER) -#define PAGE_COPY_X __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_EXEC) -#define PAGE_READONLY __pgprot(_PAGE_BASE | _PAGE_USER) -#define PAGE_READONLY_X __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_EXEC) +#include <asm/pgtable-masks.h> #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_NOHASH_32_PTE_44x_H */ diff --git a/arch/powerpc/include/asm/nohash/32/pte-fsl-booke.h b/arch/powerpc/include/asm/nohash/32/pte-85xx.h index 0fc1bd42bb3e..653a342d3b25 100644 --- a/arch/powerpc/include/asm/nohash/32/pte-fsl-booke.h +++ b/arch/powerpc/include/asm/nohash/32/pte-85xx.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ASM_POWERPC_NOHASH_32_PTE_FSL_BOOKE_H -#define _ASM_POWERPC_NOHASH_32_PTE_FSL_BOOKE_H +#ifndef _ASM_POWERPC_NOHASH_32_PTE_85xx_H +#define _ASM_POWERPC_NOHASH_32_PTE_85xx_H #ifdef __KERNEL__ /* PTE bit definitions for Freescale BookE SW loaded TLB MMU based @@ -11,15 +11,15 @@ 32 33 34 35 36 ... 50 51 52 53 54 55 56 57 58 59 60 61 62 63 RPN...................... 0 0 U0 U1 U2 U3 UX SX UW SW UR SR - - PRESENT *must* be in the bottom three bits because swap cache - entries use the top 29 bits. + - PRESENT *must* be in the bottom two bits because swap PTEs use + the top 30 bits. */ /* Definitions for FSL Book-E Cores */ -#define _PAGE_PRESENT 0x00001 /* S: PTE contains a translation */ -#define _PAGE_USER 0x00002 /* S: User page (maps to UR) */ -#define _PAGE_RW 0x00004 /* S: Write permission (SW) */ +#define _PAGE_READ 0x00001 /* H: Read permission (SR) */ +#define _PAGE_PRESENT 0x00002 /* S: PTE contains a translation */ +#define _PAGE_WRITE 0x00004 /* S: Write permission (SW) */ #define _PAGE_DIRTY 0x00008 /* S: Page dirty */ #define _PAGE_EXEC 0x00010 /* H: SX permission */ #define _PAGE_ACCESSED 0x00020 /* S: Page referenced */ @@ -31,11 +31,6 @@ #define _PAGE_WRITETHRU 0x00400 /* H: W bit */ #define _PAGE_SPECIAL 0x00800 /* S: Special page */ -#define _PAGE_KERNEL_RO 0 -#define _PAGE_KERNEL_ROX _PAGE_EXEC -#define _PAGE_KERNEL_RW (_PAGE_DIRTY | _PAGE_RW) -#define _PAGE_KERNEL_RWX (_PAGE_DIRTY | _PAGE_RW | _PAGE_EXEC) - /* No page size encoding in the linux PTE */ #define _PAGE_PSIZE 0 @@ -61,14 +56,7 @@ #define _PAGE_BASE (_PAGE_BASE_NC) #endif -/* Permission masks used to generate the __P and __S table */ -#define PAGE_NONE __pgprot(_PAGE_BASE) -#define PAGE_SHARED __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RW) -#define PAGE_SHARED_X __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RW | _PAGE_EXEC) -#define PAGE_COPY __pgprot(_PAGE_BASE | _PAGE_USER) -#define PAGE_COPY_X __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_EXEC) -#define PAGE_READONLY __pgprot(_PAGE_BASE | _PAGE_USER) -#define PAGE_READONLY_X __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_EXEC) +#include <asm/pgtable-masks.h> #endif /* __KERNEL__ */ -#endif /* _ASM_POWERPC_NOHASH_32_PTE_FSL_BOOKE_H */ +#endif /* _ASM_POWERPC_NOHASH_32_PTE_FSL_85xx_H */ diff --git a/arch/powerpc/include/asm/nohash/32/pte-8xx.h b/arch/powerpc/include/asm/nohash/32/pte-8xx.h index c9e4b2d90f65..137dc3c84e45 100644 --- a/arch/powerpc/include/asm/nohash/32/pte-8xx.h +++ b/arch/powerpc/include/asm/nohash/32/pte-8xx.h @@ -39,13 +39,20 @@ * into the TLB. */ #define _PAGE_GUARDED 0x0010 /* Copied to L1 G entry in DTLB */ -#define _PAGE_SPECIAL 0x0020 /* SW entry */ +#define _PAGE_ACCESSED 0x0020 /* Copied to L1 APG 1 entry in I/DTLB */ #define _PAGE_EXEC 0x0040 /* Copied to PP (bit 21) in ITLB */ -#define _PAGE_ACCESSED 0x0080 /* software: page referenced */ +#define _PAGE_SPECIAL 0x0080 /* SW entry */ #define _PAGE_NA 0x0200 /* Supervisor NA, User no access */ #define _PAGE_RO 0x0600 /* Supervisor RO, User no access */ +#define _PAGE_HUGE 0x0800 /* Copied to L1 PS bit 29 */ + +#define _PAGE_NAX (_PAGE_NA | _PAGE_EXEC) +#define _PAGE_ROX (_PAGE_RO | _PAGE_EXEC) +#define _PAGE_RW 0 +#define _PAGE_RWX _PAGE_EXEC + /* cache related flags non existing on 8xx */ #define _PAGE_COHERENT 0 #define _PAGE_WRITETHRU 0 @@ -57,11 +64,12 @@ #define _PMD_PRESENT 0x0001 #define _PMD_PRESENT_MASK _PMD_PRESENT -#define _PMD_BAD 0x0fd0 +#define _PMD_BAD 0x0f90 #define _PMD_PAGE_MASK 0x000c #define _PMD_PAGE_8M 0x000c #define _PMD_PAGE_512K 0x0004 -#define _PMD_USER 0x0020 /* APG 1 */ +#define _PMD_ACCESSED 0x0020 /* APG 1 */ +#define _PMD_USER 0x0040 /* APG 2 */ #define _PTE_NONE_MASK 0 @@ -74,14 +82,7 @@ #define _PAGE_BASE_NC (_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_PSIZE) #define _PAGE_BASE (_PAGE_BASE_NC) -/* Permission masks used to generate the __P and __S table */ -#define PAGE_NONE __pgprot(_PAGE_BASE | _PAGE_NA) -#define PAGE_SHARED __pgprot(_PAGE_BASE) -#define PAGE_SHARED_X __pgprot(_PAGE_BASE | _PAGE_EXEC) -#define PAGE_COPY __pgprot(_PAGE_BASE | _PAGE_RO) -#define PAGE_COPY_X __pgprot(_PAGE_BASE | _PAGE_RO | _PAGE_EXEC) -#define PAGE_READONLY __pgprot(_PAGE_BASE | _PAGE_RO) -#define PAGE_READONLY_X __pgprot(_PAGE_BASE | _PAGE_RO | _PAGE_EXEC) +#include <asm/pgtable-masks.h> #ifndef __ASSEMBLY__ static inline pte_t pte_wrprotect(pte_t pte) @@ -91,6 +92,13 @@ static inline pte_t pte_wrprotect(pte_t pte) #define pte_wrprotect pte_wrprotect +static inline int pte_read(pte_t pte) +{ + return (pte_val(pte) & _PAGE_RO) != _PAGE_NA; +} + +#define pte_read pte_read + static inline int pte_write(pte_t pte) { return !(pte_val(pte) & _PAGE_RO); @@ -98,40 +106,121 @@ static inline int pte_write(pte_t pte) #define pte_write pte_write -static inline pte_t pte_mkwrite(pte_t pte) +static inline pte_t pte_mkwrite_novma(pte_t pte) { return __pte(pte_val(pte) & ~_PAGE_RO); } -#define pte_mkwrite pte_mkwrite +#define pte_mkwrite_novma pte_mkwrite_novma -static inline bool pte_user(pte_t pte) +static inline pte_t pte_mkhuge(pte_t pte) { - return !(pte_val(pte) & _PAGE_SH); + return __pte(pte_val(pte) | _PAGE_SPS | _PAGE_HUGE); } -#define pte_user pte_user +#define pte_mkhuge pte_mkhuge + +static inline pte_basic_t pte_update(struct mm_struct *mm, unsigned long addr, pte_t *p, + unsigned long clr, unsigned long set, int huge); -static inline pte_t pte_mkprivileged(pte_t pte) +static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { - return __pte(pte_val(pte) | _PAGE_SH); + pte_update(mm, addr, ptep, 0, _PAGE_RO, 0); } +#define ptep_set_wrprotect ptep_set_wrprotect + +static inline void __ptep_set_access_flags(struct vm_area_struct *vma, pte_t *ptep, + pte_t entry, unsigned long address, int psize) +{ + unsigned long set = pte_val(entry) & (_PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_EXEC); + unsigned long clr = ~pte_val(entry) & _PAGE_RO; + int huge = psize > mmu_virtual_psize ? 1 : 0; + + pte_update(vma->vm_mm, address, ptep, clr, set, huge); -#define pte_mkprivileged pte_mkprivileged + flush_tlb_page(vma, address); +} +#define __ptep_set_access_flags __ptep_set_access_flags -static inline pte_t pte_mkuser(pte_t pte) +static inline unsigned long pgd_leaf_size(pgd_t pgd) { - return __pte(pte_val(pte) & ~_PAGE_SH); + if (pgd_val(pgd) & _PMD_PAGE_8M) + return SZ_8M; + return SZ_4M; } -#define pte_mkuser pte_mkuser +#define pgd_leaf_size pgd_leaf_size -static inline pte_t pte_mkhuge(pte_t pte) +static inline unsigned long pte_leaf_size(pte_t pte) { - return __pte(pte_val(pte) | _PAGE_SPS); + pte_basic_t val = pte_val(pte); + + if (val & _PAGE_HUGE) + return SZ_512K; + if (val & _PAGE_SPS) + return SZ_16K; + return SZ_4K; } -#define pte_mkhuge pte_mkhuge +#define pte_leaf_size pte_leaf_size + +/* + * On the 8xx, the page tables are a bit special. For 16k pages, we have + * 4 identical entries. For 512k pages, we have 128 entries as if it was + * 4k pages, but they are flagged as 512k pages for the hardware. + * For other page sizes, we have a single entry in the table. + */ +static pmd_t *pmd_off(struct mm_struct *mm, unsigned long addr); +static int hugepd_ok(hugepd_t hpd); + +static inline int number_of_cells_per_pte(pmd_t *pmd, pte_basic_t val, int huge) +{ + if (!huge) + return PAGE_SIZE / SZ_4K; + else if (hugepd_ok(*((hugepd_t *)pmd))) + return 1; + else if (IS_ENABLED(CONFIG_PPC_4K_PAGES) && !(val & _PAGE_HUGE)) + return SZ_16K / SZ_4K; + else + return SZ_512K / SZ_4K; +} + +static inline pte_basic_t pte_update(struct mm_struct *mm, unsigned long addr, pte_t *p, + unsigned long clr, unsigned long set, int huge) +{ + pte_basic_t *entry = (pte_basic_t *)p; + pte_basic_t old = pte_val(*p); + pte_basic_t new = (old & ~(pte_basic_t)clr) | set; + int num, i; + pmd_t *pmd = pmd_off(mm, addr); + + num = number_of_cells_per_pte(pmd, new, huge); + + for (i = 0; i < num; i += PAGE_SIZE / SZ_4K, new += PAGE_SIZE) { + *entry++ = new; + if (IS_ENABLED(CONFIG_PPC_16K_PAGES) && num != 1) { + *entry++ = new; + *entry++ = new; + *entry++ = new; + } + } + + return old; +} + +#define pte_update pte_update + +#ifdef CONFIG_PPC_16K_PAGES +#define ptep_get ptep_get +static inline pte_t ptep_get(pte_t *ptep) +{ + pte_basic_t val = READ_ONCE(ptep->pte); + pte_t pte = {val, val, val, val}; + + return pte; +} +#endif /* CONFIG_PPC_16K_PAGES */ + #endif #endif /* __KERNEL__ */ diff --git a/arch/powerpc/include/asm/nohash/32/slice.h b/arch/powerpc/include/asm/nohash/32/slice.h deleted file mode 100644 index 39eb0154ae2d..000000000000 --- a/arch/powerpc/include/asm/nohash/32/slice.h +++ /dev/null @@ -1,20 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ASM_POWERPC_NOHASH_32_SLICE_H -#define _ASM_POWERPC_NOHASH_32_SLICE_H - -#ifdef CONFIG_PPC_MM_SLICES - -#define SLICE_LOW_SHIFT 26 /* 64 slices */ -#define SLICE_LOW_TOP (0x100000000ull) -#define SLICE_NUM_LOW (SLICE_LOW_TOP >> SLICE_LOW_SHIFT) -#define GET_LOW_SLICE_INDEX(addr) ((addr) >> SLICE_LOW_SHIFT) - -#define SLICE_HIGH_SHIFT 0 -#define SLICE_NUM_HIGH 0ul -#define GET_HIGH_SLICE_INDEX(addr) (addr & 0) - -#define SLB_ADDR_LIMIT_DEFAULT DEFAULT_MAP_WINDOW - -#endif /* CONFIG_PPC_MM_SLICES */ - -#endif /* _ASM_POWERPC_NOHASH_32_SLICE_H */ diff --git a/arch/powerpc/include/asm/nohash/64/pgalloc.h b/arch/powerpc/include/asm/nohash/64/pgalloc.h index b9534a793293..e50b211becb3 100644 --- a/arch/powerpc/include/asm/nohash/64/pgalloc.h +++ b/arch/powerpc/include/asm/nohash/64/pgalloc.h @@ -15,7 +15,10 @@ struct vmemmap_backing { }; extern struct vmemmap_backing *vmemmap_list; -#define pgd_populate(MM, PGD, PUD) pgd_set(PGD, (unsigned long)PUD) +static inline void p4d_populate(struct mm_struct *mm, p4d_t *p4d, pud_t *pud) +{ + p4d_set(p4d, (unsigned long)pud); +} static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr) { diff --git a/arch/powerpc/include/asm/nohash/64/pgtable-4k.h b/arch/powerpc/include/asm/nohash/64/pgtable-4k.h index c40ec32b8194..10f5cf444d72 100644 --- a/arch/powerpc/include/asm/nohash/64/pgtable-4k.h +++ b/arch/powerpc/include/asm/nohash/64/pgtable-4k.h @@ -2,7 +2,7 @@ #ifndef _ASM_POWERPC_NOHASH_64_PGTABLE_4K_H #define _ASM_POWERPC_NOHASH_64_PGTABLE_4K_H -#include <asm-generic/5level-fixup.h> +#include <asm-generic/pgtable-nop4d.h> /* * Entries per page directory level. The PTE level must use a 64b record @@ -45,42 +45,42 @@ #define PMD_MASKED_BITS 0 /* Bits to mask out from a PUD to get to the PMD page */ #define PUD_MASKED_BITS 0 -/* Bits to mask out from a PGD to get to the PUD page */ -#define PGD_MASKED_BITS 0 +/* Bits to mask out from a P4D to get to the PUD page */ +#define P4D_MASKED_BITS 0 /* * 4-level page tables related bits */ -#define pgd_none(pgd) (!pgd_val(pgd)) -#define pgd_bad(pgd) (pgd_val(pgd) == 0) -#define pgd_present(pgd) (pgd_val(pgd) != 0) -#define pgd_page_vaddr(pgd) (pgd_val(pgd) & ~PGD_MASKED_BITS) +#define p4d_none(p4d) (!p4d_val(p4d)) +#define p4d_bad(p4d) (p4d_val(p4d) == 0) +#define p4d_present(p4d) (p4d_val(p4d) != 0) #ifndef __ASSEMBLY__ -static inline void pgd_clear(pgd_t *pgdp) +static inline pud_t *p4d_pgtable(p4d_t p4d) { - *pgdp = __pgd(0); + return (pud_t *) (p4d_val(p4d) & ~P4D_MASKED_BITS); } -static inline pte_t pgd_pte(pgd_t pgd) +static inline void p4d_clear(p4d_t *p4dp) { - return __pte(pgd_val(pgd)); + *p4dp = __p4d(0); } -static inline pgd_t pte_pgd(pte_t pte) +static inline pte_t p4d_pte(p4d_t p4d) { - return __pgd(pte_val(pte)); + return __pte(p4d_val(p4d)); } -extern struct page *pgd_page(pgd_t pgd); -#endif /* !__ASSEMBLY__ */ +static inline p4d_t pte_p4d(pte_t pte) +{ + return __p4d(pte_val(pte)); +} +extern struct page *p4d_page(p4d_t p4d); -#define pud_offset(pgdp, addr) \ - (((pud_t *) pgd_page_vaddr(*(pgdp))) + \ - (((addr) >> PUD_SHIFT) & (PTRS_PER_PUD - 1))) +#endif /* !__ASSEMBLY__ */ #define pud_ERROR(e) \ pr_err("%s:%d: bad pud %08lx.\n", __FILE__, __LINE__, pud_val(e)) diff --git a/arch/powerpc/include/asm/nohash/64/pgtable.h b/arch/powerpc/include/asm/nohash/64/pgtable.h index 9a33b8bd842d..2202c78730e8 100644 --- a/arch/powerpc/include/asm/nohash/64/pgtable.h +++ b/arch/powerpc/include/asm/nohash/64/pgtable.h @@ -6,12 +6,12 @@ * the ppc64 non-hashed page table. */ +#include <linux/sizes.h> + #include <asm/nohash/64/pgtable-4k.h> #include <asm/barrier.h> #include <asm/asm-const.h> -#define FIRST_USER_ADDRESS 0UL - /* * Size of EA range mapped by our pagetables. */ @@ -25,7 +25,7 @@ /* * Define the address range of the kernel non-linear virtual area */ -#define KERN_VIRT_START ASM_CONST(0x8000000000000000) +#define KERN_VIRT_START ASM_CONST(0xc000100000000000) #define KERN_VIRT_SIZE ASM_CONST(0x0000100000000000) /* @@ -38,15 +38,16 @@ #define VMALLOC_END (VMALLOC_START + VMALLOC_SIZE) /* - * The second half of the kernel virtual space is used for IO mappings, + * The third quarter of the kernel virtual space is used for IO mappings, * it's itself carved into the PIO region (ISA and PHB IO space) and * the ioremap space * * ISA_IO_BASE = KERN_IO_START, 64K reserved area * PHB_IO_BASE = ISA_IO_BASE + 64K to ISA_IO_BASE + 2G, PHB IO spaces - * IOREMAP_BASE = ISA_IO_BASE + 2G to VMALLOC_START + PGTABLE_RANGE + * IOREMAP_BASE = ISA_IO_BASE + 2G to KERN_IO_START + KERN_IO_SIZE */ #define KERN_IO_START (KERN_VIRT_START + (KERN_VIRT_SIZE >> 1)) +#define KERN_IO_SIZE (KERN_VIRT_SIZE >> 2) #define FULL_IO_SIZE 0x80000000ul #define ISA_IO_BASE (KERN_IO_START) #define ISA_IO_END (KERN_IO_START + 0x10000ul) @@ -54,19 +55,9 @@ #define PHB_IO_END (KERN_IO_START + FULL_IO_SIZE) #define IOREMAP_BASE (PHB_IO_END) #define IOREMAP_START (ioremap_bot) -#define IOREMAP_END (KERN_VIRT_START + KERN_VIRT_SIZE) - - -/* - * Region IDs - */ -#define REGION_SHIFT 60UL -#define REGION_MASK (0xfUL << REGION_SHIFT) -#define REGION_ID(ea) (((unsigned long)(ea)) >> REGION_SHIFT) - -#define VMALLOC_REGION_ID (REGION_ID(VMALLOC_START)) -#define KERNEL_REGION_ID (REGION_ID(PAGE_OFFSET)) -#define USER_REGION_ID (0UL) +#define IOREMAP_END (KERN_IO_START + KERN_IO_SIZE - FIXADDR_SIZE) +#define FIXADDR_SIZE SZ_32M +#define FIXADDR_TOP (IOREMAP_END + FIXADDR_SIZE) /* * Defines the address of the vmemap area, in its own region on @@ -80,48 +71,15 @@ /* * Include the PTE bits definitions */ -#include <asm/nohash/pte-book3e.h> - -#define _PAGE_SAO 0 +#include <asm/nohash/pte-e500.h> #define PTE_RPN_MASK (~((1UL << PTE_RPN_SHIFT) - 1)) -/* - * _PAGE_CHG_MASK masks of bits that are to be preserved across - * pgprot changes. - */ -#define _PAGE_CHG_MASK (PTE_RPN_MASK | _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_SPECIAL) - #define H_PAGE_4K_PFN 0 #ifndef __ASSEMBLY__ /* pte_clear moved to later in this file */ -static inline pte_t pte_mkwrite(pte_t pte) -{ - return __pte(pte_val(pte) | _PAGE_RW); -} - -static inline pte_t pte_mkdirty(pte_t pte) -{ - return __pte(pte_val(pte) | _PAGE_DIRTY); -} - -static inline pte_t pte_mkyoung(pte_t pte) -{ - return __pte(pte_val(pte) | _PAGE_ACCESSED); -} - -static inline pte_t pte_wrprotect(pte_t pte) -{ - return __pte(pte_val(pte) & ~_PAGE_RW); -} - -static inline pte_t pte_mkexec(pte_t pte) -{ - return __pte(pte_val(pte) | _PAGE_EXEC); -} - #define PMD_BAD_BITS (PTE_TABLE_SIZE-1) #define PUD_BAD_BITS (PMD_TABLE_SIZE-1) @@ -144,8 +102,9 @@ static inline pte_t pmd_pte(pmd_t pmd) #define pmd_bad(pmd) (!is_kernel_addr(pmd_val(pmd)) \ || (pmd_val(pmd) & PMD_BAD_BITS)) #define pmd_present(pmd) (!pmd_none(pmd)) -#define pmd_page_vaddr(pmd) (pmd_val(pmd) & ~PMD_MASKED_BITS) +#define pmd_page_vaddr(pmd) ((const void *)(pmd_val(pmd) & ~PMD_MASKED_BITS)) extern struct page *pmd_page(pmd_t pmd); +#define pmd_pfn(pmd) (page_to_pfn(pmd_page(pmd))) static inline void pud_set(pud_t *pudp, unsigned long val) { @@ -161,7 +120,11 @@ static inline void pud_clear(pud_t *pudp) #define pud_bad(pud) (!is_kernel_addr(pud_val(pud)) \ || (pud_val(pud) & PUD_BAD_BITS)) #define pud_present(pud) (pud_val(pud) != 0) -#define pud_page_vaddr(pud) (pud_val(pud) & ~PUD_MASKED_BITS) + +static inline pmd_t *pud_pgtable(pud_t pud) +{ + return (pmd_t *)(pud_val(pud) & ~PUD_MASKED_BITS); +} extern struct page *pud_page(pud_t pud); @@ -175,192 +138,77 @@ static inline pud_t pte_pud(pte_t pte) return __pud(pte_val(pte)); } #define pud_write(pud) pte_write(pud_pte(pud)) -#define pgd_write(pgd) pte_write(pgd_pte(pgd)) - -static inline void pgd_set(pgd_t *pgdp, unsigned long val) -{ - *pgdp = __pgd(val); -} - -/* - * Find an entry in a page-table-directory. We combine the address region - * (the high order N bits) and the pgd portion of the address. - */ -#define pgd_index(address) (((address) >> (PGDIR_SHIFT)) & (PTRS_PER_PGD - 1)) - -#define pgd_offset(mm, address) ((mm)->pgd + pgd_index(address)) - -#define pmd_offset(pudp,addr) \ - (((pmd_t *) pud_page_vaddr(*(pudp))) + (((addr) >> PMD_SHIFT) & (PTRS_PER_PMD - 1))) +#define p4d_write(pgd) pte_write(p4d_pte(p4d)) -#define pte_offset_kernel(dir,addr) \ - (((pte_t *) pmd_page_vaddr(*(dir))) + (((addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))) - -#define pte_offset_map(dir,addr) pte_offset_kernel((dir), (addr)) - -static inline void pte_unmap(pte_t *pte) { } - -/* to find an entry in a kernel page-table-directory */ -/* This now only contains the vmalloc pages */ -#define pgd_offset_k(address) pgd_offset(&init_mm, address) - -/* Atomic PTE updates */ -static inline unsigned long pte_update(struct mm_struct *mm, - unsigned long addr, - pte_t *ptep, unsigned long clr, - unsigned long set, - int huge) -{ -#ifdef PTE_ATOMIC_UPDATES - unsigned long old, tmp; - - __asm__ __volatile__( - "1: ldarx %0,0,%3 # pte_update\n\ - andc %1,%0,%4 \n\ - or %1,%1,%6\n\ - stdcx. %1,0,%3 \n\ - bne- 1b" - : "=&r" (old), "=&r" (tmp), "=m" (*ptep) - : "r" (ptep), "r" (clr), "m" (*ptep), "r" (set) - : "cc" ); -#else - unsigned long old = pte_val(*ptep); - *ptep = __pte((old & ~clr) | set); -#endif - /* huge pages use the old page table lock */ - if (!huge) - assert_pte_locked(mm, addr); - - return old; -} - -static inline int pte_young(pte_t pte) +static inline void p4d_set(p4d_t *p4dp, unsigned long val) { - return pte_val(pte) & _PAGE_ACCESSED; -} - -static inline int __ptep_test_and_clear_young(struct mm_struct *mm, - unsigned long addr, pte_t *ptep) -{ - unsigned long old; - - if (pte_young(*ptep)) - return 0; - old = pte_update(mm, addr, ptep, _PAGE_ACCESSED, 0, 0); - return (old & _PAGE_ACCESSED) != 0; -} -#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG -#define ptep_test_and_clear_young(__vma, __addr, __ptep) \ -({ \ - int __r; \ - __r = __ptep_test_and_clear_young((__vma)->vm_mm, __addr, __ptep); \ - __r; \ -}) - -#define __HAVE_ARCH_PTEP_SET_WRPROTECT -static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, - pte_t *ptep) -{ - - if ((pte_val(*ptep) & _PAGE_RW) == 0) - return; - - pte_update(mm, addr, ptep, _PAGE_RW, 0, 0); + *p4dp = __p4d(val); } #define __HAVE_ARCH_HUGE_PTEP_SET_WRPROTECT static inline void huge_ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { - if ((pte_val(*ptep) & _PAGE_RW) == 0) - return; - - pte_update(mm, addr, ptep, _PAGE_RW, 0, 1); + pte_update(mm, addr, ptep, _PAGE_WRITE, 0, 1); } #define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH #define ptep_clear_flush_young(__vma, __address, __ptep) \ ({ \ - int __young = __ptep_test_and_clear_young((__vma)->vm_mm, __address, \ - __ptep); \ + int __young = ptep_test_and_clear_young(__vma, __address, __ptep);\ __young; \ }) -#define __HAVE_ARCH_PTEP_GET_AND_CLEAR -static inline pte_t ptep_get_and_clear(struct mm_struct *mm, - unsigned long addr, pte_t *ptep) -{ - unsigned long old = pte_update(mm, addr, ptep, ~0UL, 0, 0); - return __pte(old); -} - -static inline void pte_clear(struct mm_struct *mm, unsigned long addr, - pte_t * ptep) -{ - pte_update(mm, addr, ptep, ~0UL, 0, 0); -} - - -/* Set the dirty and/or accessed bits atomically in a linux PTE */ -static inline void __ptep_set_access_flags(struct vm_area_struct *vma, - pte_t *ptep, pte_t entry, - unsigned long address, - int psize) -{ - unsigned long bits = pte_val(entry) & - (_PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_RW | _PAGE_EXEC); - -#ifdef PTE_ATOMIC_UPDATES - unsigned long old, tmp; - - __asm__ __volatile__( - "1: ldarx %0,0,%4\n\ - or %0,%3,%0\n\ - stdcx. %0,0,%4\n\ - bne- 1b" - :"=&r" (old), "=&r" (tmp), "=m" (*ptep) - :"r" (bits), "r" (ptep), "m" (*ptep) - :"cc"); -#else - unsigned long old = pte_val(*ptep); - *ptep = __pte(old | bits); -#endif - - flush_tlb_page(vma, address); -} - -#define __HAVE_ARCH_PTE_SAME -#define pte_same(A,B) ((pte_val(A) ^ pte_val(B)) == 0) - -#define pte_ERROR(e) \ - pr_err("%s:%d: bad pte %08lx.\n", __FILE__, __LINE__, pte_val(e)) #define pmd_ERROR(e) \ pr_err("%s:%d: bad pmd %08lx.\n", __FILE__, __LINE__, pmd_val(e)) #define pgd_ERROR(e) \ pr_err("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e)) -/* Encode and de-code a swap entry */ +/* + * Encode/decode swap entries and swap PTEs. Swap PTEs are all PTEs that + * are !pte_none() && !pte_present(). + * + * Format of swap PTEs: + * + * 1 1 1 1 1 1 1 1 1 2 2 2 2 2 2 2 2 2 2 3 3 + * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 + * <-------------------------- offset ---------------------------- + * + * 3 3 3 3 3 3 3 3 4 4 4 4 4 4 4 4 4 4 5 5 5 5 5 5 5 5 5 5 6 6 6 6 + * 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 + * --------------> <----------- zero ------------> E < type -> 0 0 + * + * E is the exclusive marker that is not stored in swap entries. + */ #define MAX_SWAPFILES_CHECK() do { \ BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS); \ } while (0) #define SWP_TYPE_BITS 5 -#define __swp_type(x) (((x).val >> _PAGE_BIT_SWAP_TYPE) \ +#define __swp_type(x) (((x).val >> 2) \ & ((1UL << SWP_TYPE_BITS) - 1)) #define __swp_offset(x) ((x).val >> PTE_RPN_SHIFT) #define __swp_entry(type, offset) ((swp_entry_t) { \ - ((type) << _PAGE_BIT_SWAP_TYPE) \ + (((type) & 0x1f) << 2) \ | ((offset) << PTE_RPN_SHIFT) }) #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val((pte)) }) #define __swp_entry_to_pte(x) __pte((x).val) -int map_kernel_page(unsigned long ea, unsigned long pa, pgprot_t prot); +/* We borrow MSB 56 (LSB 7) to store the exclusive marker in swap PTEs. */ +#define _PAGE_SWP_EXCLUSIVE 0x80 + extern int __meminit vmemmap_create_mapping(unsigned long start, unsigned long page_size, unsigned long phys); extern void vmemmap_remove_mapping(unsigned long start, unsigned long page_size); +void __patch_exception(int exc, unsigned long addr); +#define patch_exception(exc, name) do { \ + extern unsigned int name; \ + __patch_exception((exc), (unsigned long)&name); \ +} while (0) + #endif /* __ASSEMBLY__ */ #endif /* _ASM_POWERPC_NOHASH_64_PGTABLE_H */ diff --git a/arch/powerpc/include/asm/nohash/hugetlb-book3e.h b/arch/powerpc/include/asm/nohash/hugetlb-e500.h index ecd8694cb229..8f04ad20e040 100644 --- a/arch/powerpc/include/asm/nohash/hugetlb-book3e.h +++ b/arch/powerpc/include/asm/nohash/hugetlb-e500.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ASM_POWERPC_NOHASH_HUGETLB_BOOK3E_H -#define _ASM_POWERPC_NOHASH_HUGETLB_BOOK3E_H +#ifndef _ASM_POWERPC_NOHASH_HUGETLB_E500_H +#define _ASM_POWERPC_NOHASH_HUGETLB_E500_H static inline pte_t *hugepd_page(hugepd_t hpd) { @@ -30,7 +30,7 @@ void flush_hugetlb_page(struct vm_area_struct *vma, unsigned long vmaddr); static inline void hugepd_populate(hugepd_t *hpdp, pte_t *new, unsigned int pshift) { - /* We use the old format for PPC_FSL_BOOK3E */ + /* We use the old format for PPC_E500 */ *hpdp = __hugepd(((unsigned long)new & ~PD_HUGE) | pshift); } @@ -42,4 +42,4 @@ static inline int check_and_get_huge_psize(int shift) return shift_to_mmu_psize(shift); } -#endif /* _ASM_POWERPC_NOHASH_HUGETLB_BOOK3E_H */ +#endif /* _ASM_POWERPC_NOHASH_HUGETLB_E500_H */ diff --git a/arch/powerpc/include/asm/nohash/kup-booke.h b/arch/powerpc/include/asm/nohash/kup-booke.h new file mode 100644 index 000000000000..0c7c3258134c --- /dev/null +++ b/arch/powerpc/include/asm/nohash/kup-booke.h @@ -0,0 +1,112 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_POWERPC_KUP_BOOKE_H_ +#define _ASM_POWERPC_KUP_BOOKE_H_ + +#include <asm/bug.h> +#include <asm/mmu.h> + +#ifdef CONFIG_PPC_KUAP + +#ifdef __ASSEMBLY__ + +.macro kuap_check_amr gpr1, gpr2 +.endm + +#else + +#include <linux/sched.h> + +#include <asm/reg.h> + +static __always_inline void __kuap_lock(void) +{ + mtspr(SPRN_PID, 0); + isync(); +} +#define __kuap_lock __kuap_lock + +static __always_inline void __kuap_save_and_lock(struct pt_regs *regs) +{ + regs->kuap = mfspr(SPRN_PID); + mtspr(SPRN_PID, 0); + isync(); +} +#define __kuap_save_and_lock __kuap_save_and_lock + +static __always_inline void kuap_user_restore(struct pt_regs *regs) +{ + if (kuap_is_disabled()) + return; + + mtspr(SPRN_PID, current->thread.pid); + + /* Context synchronisation is performed by rfi */ +} + +static __always_inline void __kuap_kernel_restore(struct pt_regs *regs, unsigned long kuap) +{ + if (regs->kuap) + mtspr(SPRN_PID, current->thread.pid); + + /* Context synchronisation is performed by rfi */ +} + +#ifdef CONFIG_PPC_KUAP_DEBUG +static __always_inline unsigned long __kuap_get_and_assert_locked(void) +{ + WARN_ON_ONCE(mfspr(SPRN_PID)); + + return 0; +} +#define __kuap_get_and_assert_locked __kuap_get_and_assert_locked +#endif + +static __always_inline void uaccess_begin_booke(unsigned long val) +{ + asm(ASM_MMU_FTR_IFSET("mtspr %0, %1; isync", "", %2) : : + "i"(SPRN_PID), "r"(val), "i"(MMU_FTR_KUAP) : "memory"); +} + +static __always_inline void uaccess_end_booke(void) +{ + asm(ASM_MMU_FTR_IFSET("mtspr %0, %1; isync", "", %2) : : + "i"(SPRN_PID), "r"(0), "i"(MMU_FTR_KUAP) : "memory"); +} + +static __always_inline void allow_user_access(void __user *to, const void __user *from, + unsigned long size, unsigned long dir) +{ + uaccess_begin_booke(current->thread.pid); +} + +static __always_inline void prevent_user_access(unsigned long dir) +{ + uaccess_end_booke(); +} + +static __always_inline unsigned long prevent_user_access_return(void) +{ + unsigned long flags = mfspr(SPRN_PID); + + uaccess_end_booke(); + + return flags; +} + +static __always_inline void restore_user_access(unsigned long flags) +{ + if (flags) + uaccess_begin_booke(current->thread.pid); +} + +static __always_inline bool +__bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write) +{ + return !regs->kuap; +} + +#endif /* !__ASSEMBLY__ */ + +#endif /* CONFIG_PPC_KUAP */ + +#endif /* _ASM_POWERPC_KUP_BOOKE_H_ */ diff --git a/arch/powerpc/include/asm/nohash/mmu-book3e.h b/arch/powerpc/include/asm/nohash/mmu-e500.h index b41004664312..6ddced0415cb 100644 --- a/arch/powerpc/include/asm/nohash/mmu-book3e.h +++ b/arch/powerpc/include/asm/nohash/mmu-e500.h @@ -238,7 +238,7 @@ extern unsigned int tlbcam_index; typedef struct { unsigned int id; unsigned int active; - unsigned long vdso_base; + void __user *vdso; } mm_context_t; /* Page size definitions, common between 32 and 64-bit @@ -319,6 +319,9 @@ extern int book3e_htw_mode; #endif +#include <asm/percpu.h> +DECLARE_PER_CPU(int, next_tlbcam_idx); + #endif /* !__ASSEMBLY__ */ #endif /* _ASM_POWERPC_MMU_BOOK3E_H_ */ diff --git a/arch/powerpc/include/asm/nohash/mmu.h b/arch/powerpc/include/asm/nohash/mmu.h index edc793e5f08f..e264be219fdb 100644 --- a/arch/powerpc/include/asm/nohash/mmu.h +++ b/arch/powerpc/include/asm/nohash/mmu.h @@ -8,9 +8,9 @@ #elif defined(CONFIG_44x) /* 44x-style software loaded TLB */ #include <asm/nohash/32/mmu-44x.h> -#elif defined(CONFIG_PPC_BOOK3E_MMU) +#elif defined(CONFIG_PPC_E500) /* Freescale Book-E software loaded TLB or Book-3e (ISA 2.06+) MMU */ -#include <asm/nohash/mmu-book3e.h> +#include <asm/nohash/mmu-e500.h> #elif defined (CONFIG_PPC_8xx) /* Motorola/Freescale 8xx software loaded TLB */ #include <asm/nohash/32/mmu-8xx.h> diff --git a/arch/powerpc/include/asm/nohash/pgalloc.h b/arch/powerpc/include/asm/nohash/pgalloc.h index 332b13b4ecdb..4b62376318e1 100644 --- a/arch/powerpc/include/asm/nohash/pgalloc.h +++ b/arch/powerpc/include/asm/nohash/pgalloc.h @@ -15,7 +15,7 @@ static inline void tlb_flush_pgtable(struct mmu_gather *tlb, { } -#endif /* !CONFIG_PPC_BOOK3E */ +#endif /* !CONFIG_PPC_BOOK3E_64 */ static inline pgd_t *pgd_alloc(struct mm_struct *mm) { @@ -46,7 +46,6 @@ static inline void pgtable_free(void *table, int shift) #define get_hugepd_cache_index(x) (x) -#ifdef CONFIG_SMP static inline void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift) { unsigned long pgf = (unsigned long)table; @@ -64,13 +63,6 @@ static inline void __tlb_remove_table(void *_table) pgtable_free(table, shift); } -#else -static inline void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift) -{ - pgtable_free(table, shift); -} -#endif - static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table, unsigned long address) { diff --git a/arch/powerpc/include/asm/nohash/pgtable.h b/arch/powerpc/include/asm/nohash/pgtable.h index 7fed9dc0f147..427db14292c9 100644 --- a/arch/powerpc/include/asm/nohash/pgtable.h +++ b/arch/powerpc/include/asm/nohash/pgtable.h @@ -2,50 +2,163 @@ #ifndef _ASM_POWERPC_NOHASH_PGTABLE_H #define _ASM_POWERPC_NOHASH_PGTABLE_H +#ifndef __ASSEMBLY__ +static inline pte_basic_t pte_update(struct mm_struct *mm, unsigned long addr, pte_t *p, + unsigned long clr, unsigned long set, int huge); +#endif + #if defined(CONFIG_PPC64) #include <asm/nohash/64/pgtable.h> #else #include <asm/nohash/32/pgtable.h> #endif +/* + * _PAGE_CHG_MASK masks of bits that are to be preserved across + * pgprot changes. + */ +#define _PAGE_CHG_MASK (PTE_RPN_MASK | _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_SPECIAL) + /* Permission masks used for kernel mappings */ #define PAGE_KERNEL __pgprot(_PAGE_BASE | _PAGE_KERNEL_RW) #define PAGE_KERNEL_NC __pgprot(_PAGE_BASE_NC | _PAGE_KERNEL_RW | _PAGE_NO_CACHE) -#define PAGE_KERNEL_NCG __pgprot(_PAGE_BASE_NC | _PAGE_KERNEL_RW | \ - _PAGE_NO_CACHE | _PAGE_GUARDED) +#define PAGE_KERNEL_NCG __pgprot(_PAGE_BASE_NC | _PAGE_KERNEL_RW | _PAGE_NO_CACHE | _PAGE_GUARDED) #define PAGE_KERNEL_X __pgprot(_PAGE_BASE | _PAGE_KERNEL_RWX) #define PAGE_KERNEL_RO __pgprot(_PAGE_BASE | _PAGE_KERNEL_RO) #define PAGE_KERNEL_ROX __pgprot(_PAGE_BASE | _PAGE_KERNEL_ROX) +#ifndef __ASSEMBLY__ + +extern int icache_44x_need_flush; + /* - * Protection used for kernel text. We want the debuggers to be able to - * set breakpoints anywhere, so don't write protect the kernel text - * on platforms where such control is possible. + * PTE updates. This function is called whenever an existing + * valid PTE is updated. This does -not- include set_pte_at() + * which nowadays only sets a new PTE. + * + * Depending on the type of MMU, we may need to use atomic updates + * and the PTE may be either 32 or 64 bit wide. In the later case, + * when using atomic updates, only the low part of the PTE is + * accessed atomically. + * + * In addition, on 44x, we also maintain a global flag indicating + * that an executable user mapping was modified, which is needed + * to properly flush the virtually tagged instruction cache of + * those implementations. */ -#if defined(CONFIG_KGDB) || defined(CONFIG_XMON) || defined(CONFIG_BDI_SWITCH) ||\ - defined(CONFIG_KPROBES) || defined(CONFIG_DYNAMIC_FTRACE) -#define PAGE_KERNEL_TEXT PAGE_KERNEL_X -#else -#define PAGE_KERNEL_TEXT PAGE_KERNEL_ROX +#ifndef pte_update +static inline pte_basic_t pte_update(struct mm_struct *mm, unsigned long addr, pte_t *p, + unsigned long clr, unsigned long set, int huge) +{ + pte_basic_t old = pte_val(*p); + pte_basic_t new = (old & ~(pte_basic_t)clr) | set; + + if (new == old) + return old; + + *p = __pte(new); + + if (IS_ENABLED(CONFIG_44x) && !is_kernel_addr(addr) && (old & _PAGE_EXEC)) + icache_44x_need_flush = 1; + + /* huge pages use the old page table lock */ + if (!huge) + assert_pte_locked(mm, addr); + + return old; +} #endif -/* Make modules code happy. We don't set RO yet */ -#define PAGE_KERNEL_EXEC PAGE_KERNEL_X +static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep) +{ + unsigned long old; -/* Advertise special mapping type for AGP */ -#define PAGE_AGP (PAGE_KERNEL_NC) -#define HAVE_PAGE_AGP + old = pte_update(vma->vm_mm, addr, ptep, _PAGE_ACCESSED, 0, 0); -#ifndef __ASSEMBLY__ + return (old & _PAGE_ACCESSED) != 0; +} +#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG + +#ifndef ptep_set_wrprotect +static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, + pte_t *ptep) +{ + pte_update(mm, addr, ptep, _PAGE_WRITE, 0, 0); +} +#endif +#define __HAVE_ARCH_PTEP_SET_WRPROTECT + +static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, + pte_t *ptep) +{ + return __pte(pte_update(mm, addr, ptep, ~0UL, 0, 0)); +} +#define __HAVE_ARCH_PTEP_GET_AND_CLEAR + +static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) +{ + pte_update(mm, addr, ptep, ~0UL, 0, 0); +} + +/* Set the dirty and/or accessed bits atomically in a linux PTE */ +#ifndef __ptep_set_access_flags +static inline void __ptep_set_access_flags(struct vm_area_struct *vma, + pte_t *ptep, pte_t entry, + unsigned long address, + int psize) +{ + unsigned long set = pte_val(entry) & + (_PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_RW | _PAGE_EXEC); + int huge = psize > mmu_virtual_psize ? 1 : 0; + + pte_update(vma->vm_mm, address, ptep, 0, set, huge); + + flush_tlb_page(vma, address); +} +#endif /* Generic accessors to PTE bits */ +#ifndef pte_mkwrite_novma +static inline pte_t pte_mkwrite_novma(pte_t pte) +{ + /* + * write implies read, hence set both + */ + return __pte(pte_val(pte) | _PAGE_RW); +} +#endif + +static inline pte_t pte_mkdirty(pte_t pte) +{ + return __pte(pte_val(pte) | _PAGE_DIRTY); +} + +static inline pte_t pte_mkyoung(pte_t pte) +{ + return __pte(pte_val(pte) | _PAGE_ACCESSED); +} + +#ifndef pte_wrprotect +static inline pte_t pte_wrprotect(pte_t pte) +{ + return __pte(pte_val(pte) & ~_PAGE_WRITE); +} +#endif + +#ifndef pte_mkexec +static inline pte_t pte_mkexec(pte_t pte) +{ + return __pte(pte_val(pte) | _PAGE_EXEC); +} +#endif + #ifndef pte_write static inline int pte_write(pte_t pte) { - return pte_val(pte) & _PAGE_RW; + return pte_val(pte) & _PAGE_WRITE; } #endif -static inline int pte_read(pte_t pte) { return 1; } static inline int pte_dirty(pte_t pte) { return pte_val(pte) & _PAGE_DIRTY; } static inline int pte_special(pte_t pte) { return pte_val(pte) & _PAGE_SPECIAL; } static inline int pte_none(pte_t pte) { return (pte_val(pte) & ~_PTE_NONE_MASK) == 0; } @@ -53,23 +166,6 @@ static inline bool pte_hashpte(pte_t pte) { return false; } static inline bool pte_ci(pte_t pte) { return pte_val(pte) & _PAGE_NO_CACHE; } static inline bool pte_exec(pte_t pte) { return pte_val(pte) & _PAGE_EXEC; } -#ifdef CONFIG_NUMA_BALANCING -/* - * These work without NUMA balancing but the kernel does not care. See the - * comment in include/asm-generic/pgtable.h . On powerpc, this will only - * work for user pages and always return true for kernel pages. - */ -static inline int pte_protnone(pte_t pte) -{ - return pte_present(pte) && !pte_user(pte); -} - -static inline int pmd_protnone(pmd_t pmd) -{ - return pte_protnone(pmd_pte(pmd)); -} -#endif /* CONFIG_NUMA_BALANCING */ - static inline int pte_present(pte_t pte) { return pte_val(pte) & _PAGE_PRESENT; @@ -80,15 +176,20 @@ static inline bool pte_hw_valid(pte_t pte) return pte_val(pte) & _PAGE_PRESENT; } +static inline int pte_young(pte_t pte) +{ + return pte_val(pte) & _PAGE_ACCESSED; +} + /* - * Don't just check for any non zero bits in __PAGE_USER, since for book3e + * Don't just check for any non zero bits in __PAGE_READ, since for book3e * and PTE_64BIT, PAGE_KERNEL_X contains _PAGE_BAP_SR which is also in - * _PAGE_USER. Need to explicitly match _PAGE_BAP_UR bit in that case too. + * _PAGE_READ. Need to explicitly match _PAGE_BAP_UR bit in that case too. */ -#ifndef pte_user -static inline bool pte_user(pte_t pte) +#ifndef pte_read +static inline bool pte_read(pte_t pte) { - return (pte_val(pte) & _PAGE_USER) == _PAGE_USER; + return (pte_val(pte) & _PAGE_READ) == _PAGE_READ; } #endif @@ -100,10 +201,10 @@ static inline bool pte_user(pte_t pte) static inline bool pte_access_permitted(pte_t pte, bool write) { /* - * A read-only access is controlled by _PAGE_USER bit. - * We have _PAGE_READ set for WRITE and EXECUTE + * A read-only access is controlled by _PAGE_READ bit. + * We have _PAGE_READ set for WRITE */ - if (!pte_present(pte) || !pte_user(pte) || !pte_read(pte)) + if (!pte_present(pte) || !pte_read(pte)) return false; if (write && !pte_write(pte)) @@ -121,8 +222,6 @@ static inline bool pte_access_permitted(pte_t pte, bool write) static inline pte_t pfn_pte(unsigned long pfn, pgprot_t pgprot) { return __pte(((pte_basic_t)(pfn) << PTE_RPN_SHIFT) | pgprot_val(pgprot)); } -static inline unsigned long pte_pfn(pte_t pte) { - return pte_val(pte) >> PTE_RPN_SHIFT; } /* Generic modifiers for PTE bits */ static inline pte_t pte_exprotect(pte_t pte) @@ -130,23 +229,16 @@ static inline pte_t pte_exprotect(pte_t pte) return __pte(pte_val(pte) & ~_PAGE_EXEC); } -#ifndef pte_mkclean static inline pte_t pte_mkclean(pte_t pte) { return __pte(pte_val(pte) & ~_PAGE_DIRTY); } -#endif static inline pte_t pte_mkold(pte_t pte) { return __pte(pte_val(pte) & ~_PAGE_ACCESSED); } -static inline pte_t pte_mkpte(pte_t pte) -{ - return pte; -} - static inline pte_t pte_mkspecial(pte_t pte) { return __pte(pte_val(pte) | _PAGE_SPECIAL); @@ -159,30 +251,25 @@ static inline pte_t pte_mkhuge(pte_t pte) } #endif -#ifndef pte_mkprivileged -static inline pte_t pte_mkprivileged(pte_t pte) +static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) { - return __pte(pte_val(pte) & ~_PAGE_USER); + return __pte((pte_val(pte) & _PAGE_CHG_MASK) | pgprot_val(newprot)); } -#endif -#ifndef pte_mkuser -static inline pte_t pte_mkuser(pte_t pte) +static inline int pte_swp_exclusive(pte_t pte) { - return __pte(pte_val(pte) | _PAGE_USER); + return pte_val(pte) & _PAGE_SWP_EXCLUSIVE; } -#endif -static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) +static inline pte_t pte_swp_mkexclusive(pte_t pte) { - return __pte((pte_val(pte) & _PAGE_CHG_MASK) | pgprot_val(newprot)); + return __pte(pte_val(pte) | _PAGE_SWP_EXCLUSIVE); } -/* Insert a PTE, top-level function is out of line. It uses an inline - * low level function in the respective pgtable-* files - */ -extern void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, - pte_t pte); +static inline pte_t pte_swp_clear_exclusive(pte_t pte) +{ + return __pte(pte_val(pte) & ~_PAGE_SWP_EXCLUSIVE); +} /* This low level function performs the actual PTE insertion * Setting the PTE depends on the MMU type and other factors. It's @@ -199,9 +286,9 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr, */ if (IS_ENABLED(CONFIG_PPC32) && IS_ENABLED(CONFIG_PTE_64BIT) && !percpu) { __asm__ __volatile__("\ - stw%U0%X0 %2,%0\n\ - eieio\n\ - stw%U0%X0 %L2,%1" + stw%X0 %2,%0\n\ + mbar\n\ + stw%X1 %L2,%1" : "=m" (*ptep), "=m" (*((unsigned char *)ptep+4)) : "r" (pte) : "memory"); return; @@ -210,7 +297,7 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr, * cases, and 32-bit non-hash with 32-bit PTEs. */ #if defined(CONFIG_PPC_8xx) && defined(CONFIG_PPC_16K_PAGES) - ptep->pte = ptep->pte1 = ptep->pte2 = ptep->pte3 = pte_val(pte); + ptep->pte3 = ptep->pte2 = ptep->pte1 = ptep->pte = pte_val(pte); #else *ptep = pte; #endif @@ -225,11 +312,6 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr, mb(); } - -#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS -extern int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address, - pte_t *ptep, pte_t entry, int dirty); - /* * Macro to mark a page protection value as "uncacheable". */ @@ -258,16 +340,11 @@ extern int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long addre #define pgprot_writecombine pgprot_noncached_wc -struct file; -extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, - unsigned long size, pgprot_t vma_prot); -#define __HAVE_PHYS_MEM_ACCESS_PROT - #ifdef CONFIG_HUGETLB_PAGE static inline int hugepd_ok(hugepd_t hpd) { #ifdef CONFIG_PPC_8xx - return ((hpd_val(hpd) & 0x4) != 0); + return ((hpd_val(hpd) & _PMD_PAGE_MASK) == _PMD_PAGE_8M); #else /* We clear the top bit to indicate hugepd */ return (hpd_val(hpd) && (hpd_val(hpd) & PD_HUGE) == 0); @@ -284,27 +361,11 @@ static inline int pud_huge(pud_t pud) return 0; } -static inline int pgd_huge(pgd_t pgd) -{ - return 0; -} -#define pgd_huge pgd_huge - #define is_hugepd(hpd) (hugepd_ok(hpd)) #endif -/* - * This gets called at the end of handling a page fault, when - * the kernel has put a new PTE into the page table for the process. - * We use it to ensure coherency between the i-cache and d-cache - * for the page which has just been mapped in. - */ -#if defined(CONFIG_PPC_FSL_BOOK3E) && defined(CONFIG_HUGETLB_PAGE) -void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep); -#else -static inline -void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) {} -#endif +int map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot); +void unmap_kernel_page(unsigned long va); #endif /* __ASSEMBLY__ */ #endif diff --git a/arch/powerpc/include/asm/nohash/pte-book3e.h b/arch/powerpc/include/asm/nohash/pte-e500.h index 813918f40765..f516f0b5b7a8 100644 --- a/arch/powerpc/include/asm/nohash/pte-book3e.h +++ b/arch/powerpc/include/asm/nohash/pte-e500.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ASM_POWERPC_NOHASH_PTE_BOOK3E_H -#define _ASM_POWERPC_NOHASH_PTE_BOOK3E_H +#ifndef _ASM_POWERPC_NOHASH_PTE_E500_H +#define _ASM_POWERPC_NOHASH_PTE_E500_H #ifdef __KERNEL__ /* PTE bit definitions for processors compliant to the Book3E @@ -12,7 +12,6 @@ /* Architected bits */ #define _PAGE_PRESENT 0x000001 /* software: pte contains a translation */ #define _PAGE_SW1 0x000002 -#define _PAGE_BIT_SWAP_TYPE 2 #define _PAGE_BAP_SR 0x000004 #define _PAGE_BAP_UR 0x000008 #define _PAGE_BAP_SW 0x000010 @@ -48,14 +47,21 @@ #define _PAGE_WRITETHRU 0x800000 /* W: cache write-through */ /* "Higher level" linux bit combinations */ -#define _PAGE_EXEC _PAGE_BAP_UX /* .. and was cache cleaned */ -#define _PAGE_RW (_PAGE_BAP_SW | _PAGE_BAP_UW) /* User write permission */ +#define _PAGE_EXEC (_PAGE_BAP_SX | _PAGE_BAP_UX) /* .. and was cache cleaned */ +#define _PAGE_READ (_PAGE_BAP_SR | _PAGE_BAP_UR) /* User read permission */ +#define _PAGE_WRITE (_PAGE_BAP_SW | _PAGE_BAP_UW) /* User write permission */ + #define _PAGE_KERNEL_RW (_PAGE_BAP_SW | _PAGE_BAP_SR | _PAGE_DIRTY) #define _PAGE_KERNEL_RO (_PAGE_BAP_SR) #define _PAGE_KERNEL_RWX (_PAGE_BAP_SW | _PAGE_BAP_SR | _PAGE_DIRTY | _PAGE_BAP_SX) #define _PAGE_KERNEL_ROX (_PAGE_BAP_SR | _PAGE_BAP_SX) -#define _PAGE_USER (_PAGE_BAP_UR | _PAGE_BAP_SR) /* Can be read */ -#define _PAGE_PRIVILEGED (_PAGE_BAP_SR) + +#define _PAGE_NA 0 +#define _PAGE_NAX _PAGE_BAP_UX +#define _PAGE_RO _PAGE_READ +#define _PAGE_ROX (_PAGE_READ | _PAGE_BAP_UX) +#define _PAGE_RW (_PAGE_READ | _PAGE_WRITE) +#define _PAGE_RWX (_PAGE_READ | _PAGE_WRITE | _PAGE_BAP_UX) #define _PAGE_SPECIAL _PAGE_SW0 @@ -90,30 +96,16 @@ #define _PAGE_BASE (_PAGE_BASE_NC) #endif -/* Permission masks used to generate the __P and __S table */ -#define PAGE_NONE __pgprot(_PAGE_BASE) -#define PAGE_SHARED __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RW) -#define PAGE_SHARED_X __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RW | _PAGE_EXEC) -#define PAGE_COPY __pgprot(_PAGE_BASE | _PAGE_USER) -#define PAGE_COPY_X __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_EXEC) -#define PAGE_READONLY __pgprot(_PAGE_BASE | _PAGE_USER) -#define PAGE_READONLY_X __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_EXEC) +#include <asm/pgtable-masks.h> #ifndef __ASSEMBLY__ -static inline pte_t pte_mkprivileged(pte_t pte) -{ - return __pte((pte_val(pte) & ~_PAGE_USER) | _PAGE_PRIVILEGED); -} - -#define pte_mkprivileged pte_mkprivileged - -static inline pte_t pte_mkuser(pte_t pte) +static inline pte_t pte_mkexec(pte_t pte) { - return __pte((pte_val(pte) & ~_PAGE_PRIVILEGED) | _PAGE_USER); + return __pte((pte_val(pte) & ~_PAGE_BAP_SX) | _PAGE_BAP_UX); } +#define pte_mkexec pte_mkexec -#define pte_mkuser pte_mkuser #endif /* __ASSEMBLY__ */ #endif /* __KERNEL__ */ -#endif /* _ASM_POWERPC_NOHASH_PTE_BOOK3E_H */ +#endif /* _ASM_POWERPC_NOHASH_PTE_E500_H */ diff --git a/arch/powerpc/include/asm/nohash/tlbflush.h b/arch/powerpc/include/asm/nohash/tlbflush.h index b1d8fec29169..9a2cf83ea4f1 100644 --- a/arch/powerpc/include/asm/nohash/tlbflush.h +++ b/arch/powerpc/include/asm/nohash/tlbflush.h @@ -10,7 +10,6 @@ * - local_flush_tlb_mm(mm, full) flushes the specified mm context on * the local processor * - local_flush_tlb_page(vma, vmaddr) flushes one page on the local processor - * - flush_tlb_page_nohash(vma, vmaddr) flushes one page if SW loaded TLB * - flush_tlb_range(vma, start, end) flushes a range of pages * - flush_tlb_kernel_range(start, end) flushes a range of kernel pages * @@ -19,7 +18,7 @@ /* * TLB flushing for software loaded TLB chips * - * TODO: (CONFIG_FSL_BOOKE) determine if flush_tlb_range & + * TODO: (CONFIG_PPC_85xx) determine if flush_tlb_range & * flush_tlb_kernel_range are best implemented as tlbia vs * specific tlbie's */ @@ -31,13 +30,45 @@ struct mm_struct; extern void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); -extern void flush_tlb_kernel_range(unsigned long start, unsigned long end); +#ifdef CONFIG_PPC_8xx +static inline void local_flush_tlb_mm(struct mm_struct *mm) +{ + unsigned int pid = READ_ONCE(mm->context.id); + + if (pid != MMU_NO_CONTEXT) + asm volatile ("sync; tlbia; isync" : : : "memory"); +} + +static inline void local_flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr) +{ + asm volatile ("tlbie %0; sync" : : "r" (vmaddr) : "memory"); +} + +static inline void local_flush_tlb_page_psize(struct mm_struct *mm, + unsigned long vmaddr, int psize) +{ + asm volatile ("tlbie %0; sync" : : "r" (vmaddr) : "memory"); +} + +static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end) +{ + start &= PAGE_MASK; + + if (end - start <= PAGE_SIZE) + asm volatile ("tlbie %0; sync" : : "r" (start) : "memory"); + else + asm volatile ("sync; tlbia; isync" : : : "memory"); +} +#else +extern void flush_tlb_kernel_range(unsigned long start, unsigned long end); extern void local_flush_tlb_mm(struct mm_struct *mm); extern void local_flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr); +void local_flush_tlb_page_psize(struct mm_struct *mm, unsigned long vmaddr, int psize); extern void __local_flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr, int tsize, int ind); +#endif #ifdef CONFIG_SMP extern void flush_tlb_mm(struct mm_struct *mm); diff --git a/arch/powerpc/include/asm/opal-api.h b/arch/powerpc/include/asm/opal-api.h index c1f25a760eb1..a2bc4b95e703 100644 --- a/arch/powerpc/include/asm/opal-api.h +++ b/arch/powerpc/include/asm/opal-api.h @@ -1067,6 +1067,7 @@ enum { OPAL_REBOOT_PLATFORM_ERROR = 1, OPAL_REBOOT_FULL_IPL = 2, OPAL_REBOOT_MPIPL = 3, + OPAL_REBOOT_FAST = 4, }; /* Argument to OPAL_PCI_TCE_KILL */ @@ -1090,9 +1091,10 @@ enum { OPAL_XIVE_IRQ_TRIGGER_PAGE = 0x00000001, OPAL_XIVE_IRQ_STORE_EOI = 0x00000002, OPAL_XIVE_IRQ_LSI = 0x00000004, - OPAL_XIVE_IRQ_SHIFT_BUG = 0x00000008, - OPAL_XIVE_IRQ_MASK_VIA_FW = 0x00000010, - OPAL_XIVE_IRQ_EOI_VIA_FW = 0x00000020, + OPAL_XIVE_IRQ_SHIFT_BUG = 0x00000008, /* P9 DD1.0 workaround */ + OPAL_XIVE_IRQ_MASK_VIA_FW = 0x00000010, /* P9 DD1.0 workaround */ + OPAL_XIVE_IRQ_EOI_VIA_FW = 0x00000020, /* P9 DD1.0 workaround */ + OPAL_XIVE_IRQ_STORE_EOI2 = 0x00000040, }; /* Flags for OPAL_XIVE_GET/SET_QUEUE_INFO */ diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h index 9986ac34b8e2..af304e6cb486 100644 --- a/arch/powerpc/include/asm/opal.h +++ b/arch/powerpc/include/asm/opal.h @@ -28,9 +28,6 @@ extern struct device_node *opal_node; /* API functions */ int64_t opal_invalid_call(void); -int64_t opal_npu_destroy_context(uint64_t phb_id, uint64_t pid, uint64_t bdf); -int64_t opal_npu_init_context(uint64_t phb_id, int pasid, uint64_t msr, - uint64_t bdf); int64_t opal_npu_map_lpar(uint64_t phb_id, uint64_t bdf, uint64_t lparid, uint64_t lpcr); int64_t opal_npu_spa_setup(uint64_t phb_id, uint32_t bdfn, @@ -115,9 +112,6 @@ int64_t opal_pci_set_pe(uint64_t phb_id, uint64_t pe_number, uint64_t bus_dev_fu uint8_t pe_action); int64_t opal_pci_set_peltv(uint64_t phb_id, uint32_t parent_pe, uint32_t child_pe, uint8_t state); -int64_t opal_pci_set_mve(uint64_t phb_id, uint32_t mve_number, uint32_t pe_number); -int64_t opal_pci_set_mve_enable(uint64_t phb_id, uint32_t mve_number, - uint32_t state); int64_t opal_pci_get_xive_reissue(uint64_t phb_id, uint32_t xive_number, uint8_t *p_bit, uint8_t *q_bit); int64_t opal_pci_set_xive_reissue(uint64_t phb_id, uint32_t xive_number, @@ -233,7 +227,7 @@ int64_t opal_pci_set_power_state(uint64_t async_token, uint64_t id, uint64_t data); int64_t opal_pci_poll2(uint64_t id, uint64_t data); -int64_t opal_int_get_xirr(uint32_t *out_xirr, bool just_poll); +int64_t opal_int_get_xirr(__be32 *out_xirr, bool just_poll); int64_t opal_int_set_cppr(uint8_t cppr); int64_t opal_int_eoi(uint32_t xirr); int64_t opal_int_set_mfrr(uint32_t cpu, uint8_t mfrr); @@ -307,7 +301,7 @@ int opal_secvar_enqueue_update(const char *key, uint64_t key_len, u8 *data, s64 opal_mpipl_update(enum opal_mpipl_ops op, u64 src, u64 dest, u64 size); s64 opal_mpipl_register_tag(enum opal_mpipl_tags tag, u64 addr); -s64 opal_mpipl_query_tag(enum opal_mpipl_tags tag, u64 *addr); +s64 opal_mpipl_query_tag(enum opal_mpipl_tags tag, __be64 *addr); s64 opal_signal_system_reset(s32 cpu); s64 opal_quiesce(u64 shutdown_type, s32 cpu); @@ -317,26 +311,22 @@ extern int early_init_dt_scan_opal(unsigned long node, const char *uname, int depth, void *data); extern int early_init_dt_scan_recoverable_ranges(unsigned long node, const char *uname, int depth, void *data); -extern void opal_configure_cores(void); +void __init opal_configure_cores(void); -extern int opal_get_chars(uint32_t vtermno, char *buf, int count); -extern int opal_put_chars(uint32_t vtermno, const char *buf, int total_len); -extern int opal_put_chars_atomic(uint32_t vtermno, const char *buf, int total_len); +extern ssize_t opal_get_chars(uint32_t vtermno, u8 *buf, size_t count); +extern ssize_t opal_put_chars(uint32_t vtermno, const u8 *buf, + size_t total_len); +extern ssize_t opal_put_chars_atomic(uint32_t vtermno, const u8 *buf, + size_t total_len); extern int opal_flush_chars(uint32_t vtermno, bool wait); extern int opal_flush_console(uint32_t vtermno); extern void hvc_opal_init_early(void); -extern int opal_notifier_register(struct notifier_block *nb); -extern int opal_notifier_unregister(struct notifier_block *nb); - extern int opal_message_notifier_register(enum opal_msg_type msg_type, struct notifier_block *nb); extern int opal_message_notifier_unregister(enum opal_msg_type msg_type, struct notifier_block *nb); -extern void opal_notifier_enable(void); -extern void opal_notifier_disable(void); -extern void opal_notifier_update_evt(uint64_t evt_mask, uint64_t evt_val); extern int opal_async_get_token_interruptible(void); extern int opal_async_release_token(int token); diff --git a/arch/powerpc/include/asm/oprofile_impl.h b/arch/powerpc/include/asm/oprofile_impl.h deleted file mode 100644 index 2a166c297f97..000000000000 --- a/arch/powerpc/include/asm/oprofile_impl.h +++ /dev/null @@ -1,135 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * Copyright (C) 2004 Anton Blanchard <anton@au.ibm.com>, IBM - * - * Based on alpha version. - */ - -#ifndef _ASM_POWERPC_OPROFILE_IMPL_H -#define _ASM_POWERPC_OPROFILE_IMPL_H -#ifdef __KERNEL__ - -#define OP_MAX_COUNTER 8 - -/* Per-counter configuration as set via oprofilefs. */ -struct op_counter_config { - unsigned long enabled; - unsigned long event; - unsigned long count; - /* Classic doesn't support per-counter user/kernel selection */ - unsigned long kernel; - unsigned long user; - unsigned long unit_mask; -}; - -/* System-wide configuration as set via oprofilefs. */ -struct op_system_config { -#ifdef CONFIG_PPC64 - unsigned long mmcr0; - unsigned long mmcr1; - unsigned long mmcra; -#ifdef CONFIG_OPROFILE_CELL - /* Register for oprofile user tool to check cell kernel profiling - * support. - */ - unsigned long cell_support; -#endif -#endif - unsigned long enable_kernel; - unsigned long enable_user; -}; - -/* Per-arch configuration */ -struct op_powerpc_model { - int (*reg_setup) (struct op_counter_config *, - struct op_system_config *, - int num_counters); - int (*cpu_setup) (struct op_counter_config *); - int (*start) (struct op_counter_config *); - int (*global_start) (struct op_counter_config *); - void (*stop) (void); - void (*global_stop) (void); - int (*sync_start)(void); - int (*sync_stop)(void); - void (*handle_interrupt) (struct pt_regs *, - struct op_counter_config *); - int num_counters; -}; - -extern struct op_powerpc_model op_model_fsl_emb; -extern struct op_powerpc_model op_model_power4; -extern struct op_powerpc_model op_model_7450; -extern struct op_powerpc_model op_model_cell; -extern struct op_powerpc_model op_model_pa6t; - - -/* All the classic PPC parts use these */ -static inline unsigned int classic_ctr_read(unsigned int i) -{ - switch(i) { - case 0: - return mfspr(SPRN_PMC1); - case 1: - return mfspr(SPRN_PMC2); - case 2: - return mfspr(SPRN_PMC3); - case 3: - return mfspr(SPRN_PMC4); - case 4: - return mfspr(SPRN_PMC5); - case 5: - return mfspr(SPRN_PMC6); - -/* No PPC32 chip has more than 6 so far */ -#ifdef CONFIG_PPC64 - case 6: - return mfspr(SPRN_PMC7); - case 7: - return mfspr(SPRN_PMC8); -#endif - default: - return 0; - } -} - -static inline void classic_ctr_write(unsigned int i, unsigned int val) -{ - switch(i) { - case 0: - mtspr(SPRN_PMC1, val); - break; - case 1: - mtspr(SPRN_PMC2, val); - break; - case 2: - mtspr(SPRN_PMC3, val); - break; - case 3: - mtspr(SPRN_PMC4, val); - break; - case 4: - mtspr(SPRN_PMC5, val); - break; - case 5: - mtspr(SPRN_PMC6, val); - break; - -/* No PPC32 chip has more than 6, yet */ -#ifdef CONFIG_PPC64 - case 6: - mtspr(SPRN_PMC7, val); - break; - case 7: - mtspr(SPRN_PMC8, val); - break; -#endif - default: - break; - } -} - - -extern void op_powerpc_backtrace(struct pt_regs * const regs, unsigned int depth); - -#endif /* __KERNEL__ */ -#endif /* _ASM_POWERPC_OPROFILE_IMPL_H */ diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h index e3cc9eb9204d..e667d455ecb4 100644 --- a/arch/powerpc/include/asm/paca.h +++ b/arch/powerpc/include/asm/paca.h @@ -12,12 +12,12 @@ #ifdef CONFIG_PPC64 +#include <linux/cache.h> #include <linux/string.h> #include <asm/types.h> -#include <asm/lppaca.h> #include <asm/mmu.h> #include <asm/page.h> -#ifdef CONFIG_PPC_BOOK3E +#ifdef CONFIG_PPC_BOOK3E_64 #include <asm/exception-64e.h> #else #include <asm/exception-64s.h> @@ -29,6 +29,7 @@ #include <asm/hmi.h> #include <asm/cpuidle.h> #include <asm/atomic.h> +#include <asm/mce.h> #include <asm-generic/mmiowb_types.h> @@ -45,13 +46,11 @@ extern unsigned int debug_smp_processor_id(void); /* from linux/smp.h */ #define get_paca() local_paca #endif -#ifdef CONFIG_PPC_PSERIES -#define get_lppaca() (get_paca()->lppaca_ptr) -#endif - #define get_slb_shadow() (get_paca()->slb_shadow_ptr) struct task_struct; +struct rtas_args; +struct lppaca; /* * Defines the layout of the paca. @@ -85,7 +84,9 @@ struct paca_struct { u16 lock_token; /* Constant 0x8000, used in locks */ #endif +#ifndef CONFIG_PPC_KERNEL_PCREL u64 kernel_toc; /* Kernel TOC address */ +#endif u64 kernelbase; /* Base address of kernel */ u64 kernel_msr; /* MSR while running in kernel */ void *emergency_sp; /* pointer to emergency stack */ @@ -95,7 +96,9 @@ struct paca_struct { /* this becomes non-zero. */ u8 kexec_state; /* set when kexec down has irqs off */ #ifdef CONFIG_PPC_BOOK3S_64 +#ifdef CONFIG_PPC_64S_HASH_MMU struct slb_shadow *slb_shadow_ptr; +#endif struct dtl_entry *dispatch_log; struct dtl_entry *dispatch_log_end; #endif @@ -107,8 +110,8 @@ struct paca_struct { */ /* used for most interrupts/exceptions */ u64 exgen[EX_SIZE] __attribute__((aligned(0x80))); - u64 exslb[EX_SIZE]; /* used for SLB/segment table misses - * on the linear mapping */ + +#ifdef CONFIG_PPC_64S_HASH_MMU /* SLB related definitions */ u16 vmalloc_sllp; u8 slb_cache_ptr; @@ -119,9 +122,10 @@ struct paca_struct { u32 slb_used_bitmap; /* Bitmaps for first 32 SLB entries. */ u32 slb_kern_bitmap; u32 slb_cache[SLB_CACHE_ENTRIES]; +#endif #endif /* CONFIG_PPC_BOOK3S_64 */ -#ifdef CONFIG_PPC_BOOK3E +#ifdef CONFIG_PPC_BOOK3E_64 u64 exgen[8] __aligned(0x40); /* Keep pgd in the same cacheline as the start of extlb */ pgd_t *pgd __aligned(0x40); /* Current PGD */ @@ -145,18 +149,11 @@ struct paca_struct { void *dbg_kstack; struct tlb_core_data tcd; -#endif /* CONFIG_PPC_BOOK3E */ +#endif /* CONFIG_PPC_BOOK3E_64 */ -#ifdef CONFIG_PPC_BOOK3S - mm_context_id_t mm_ctx_id; -#ifdef CONFIG_PPC_MM_SLICES +#ifdef CONFIG_PPC_64S_HASH_MMU unsigned char mm_ctx_low_slices_psize[BITS_PER_LONG / BITS_PER_BYTE]; unsigned char mm_ctx_high_slices_psize[SLICE_ARRAY_SIZE]; - unsigned long mm_ctx_slb_addr_limit; -#else - u16 mm_ctx_user_psize; - u16 mm_ctx_sllp; -#endif #endif /* @@ -166,9 +163,16 @@ struct paca_struct { u64 kstack; /* Saved Kernel stack addr */ u64 saved_r1; /* r1 save for RTAS calls or PM or EE=0 */ u64 saved_msr; /* MSR saved here by enter_rtas */ -#ifdef CONFIG_PPC_BOOK3E +#ifdef CONFIG_PPC64 + u64 exit_save_r1; /* Syscall/interrupt R1 save */ +#endif +#ifdef CONFIG_PPC_BOOK3E_64 u16 trap_save; /* Used when bad stack is encountered */ #endif +#ifdef CONFIG_PPC_BOOK3S_64 + u8 hsrr_valid; /* HSRRs set for HRFID */ + u8 srr_valid; /* SRRs set for RFID */ +#endif u8 irq_soft_mask; /* mask for irq soft masking */ u8 irq_happened; /* irq happened while soft-disabled */ u8 irq_work_pending; /* IRQ_WORK interrupt while soft-disable */ @@ -183,6 +187,7 @@ struct paca_struct { #ifdef CONFIG_PPC_POWERNV /* PowerNV idle fields */ /* PNV_CORE_IDLE_* bits, all siblings work on thread 0 paca */ + unsigned long idle_lock; /* A value of 1 means acquired */ unsigned long idle_state; union { /* P7/P8 specific fields */ @@ -224,6 +229,7 @@ struct paca_struct { u16 in_mce; u8 hmi_event_available; /* HMI event is available */ u8 hmi_p9_special_emu; /* HMI P9 special emulation */ + u32 hmi_irqs; /* HMI irq stat */ #endif u8 ftrace_enabled; /* Hard disable ftrace */ @@ -260,9 +266,11 @@ struct paca_struct { #endif /* CONFIG_PPC_PSERIES */ #ifdef CONFIG_PPC_BOOK3S_64 +#ifdef CONFIG_PPC_64S_HASH_MMU /* Capture SLB related old contents in MCE handler. */ struct slb_entry *mce_faulty_slbs; u16 slb_save_cache_ptr; +#endif #endif /* CONFIG_PPC_BOOK3S_64 */ #ifdef CONFIG_STACKPROTECTOR unsigned long canary; @@ -270,6 +278,10 @@ struct paca_struct { #ifdef CONFIG_MMIOWB struct mmiowb_state mmiowb_state; #endif +#ifdef CONFIG_PPC_BOOK3S_64 + struct mce_info *mce_info; + u8 mce_pending_irq_work; +#endif /* CONFIG_PPC_BOOK3S_64 */ } ____cacheline_aligned; extern void copy_mm_to_paca(struct mm_struct *mm); @@ -282,9 +294,8 @@ extern void free_unused_pacas(void); #else /* CONFIG_PPC64 */ -static inline void allocate_paca_ptrs(void) { }; -static inline void allocate_paca(int cpu) { }; -static inline void free_unused_pacas(void) { }; +static inline void allocate_paca(int cpu) { } +static inline void free_unused_pacas(void) { } #endif /* CONFIG_PPC64 */ diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h index 7f1fd41e3065..e5fcc79b5bfb 100644 --- a/arch/powerpc/include/asm/page.h +++ b/arch/powerpc/include/asm/page.h @@ -9,6 +9,7 @@ #ifndef __ASSEMBLY__ #include <linux/types.h> #include <linux/kernel.h> +#include <linux/bug.h> #else #include <asm/types.h> #endif @@ -31,7 +32,7 @@ extern unsigned int hpage_shift; #define HPAGE_SHIFT hpage_shift #elif defined(CONFIG_PPC_8xx) #define HPAGE_SHIFT 19 /* 512k pages */ -#elif defined(CONFIG_PPC_FSL_BOOK3E) +#elif defined(CONFIG_PPC_E500) #define HPAGE_SHIFT 22 /* 4M pages */ #endif #define HPAGE_SIZE ((1UL) << HPAGE_SHIFT) @@ -117,22 +118,7 @@ extern long long virt_phys_offset; #ifdef CONFIG_FLATMEM #define ARCH_PFN_OFFSET ((unsigned long)(MEMORY_START >> PAGE_SHIFT)) -#ifndef __ASSEMBLY__ -extern unsigned long max_mapnr; -static inline bool pfn_valid(unsigned long pfn) -{ - unsigned long min_pfn = ARCH_PFN_OFFSET; - - return pfn >= min_pfn && pfn < max_mapnr; -} #endif -#endif - -#define virt_to_pfn(kaddr) (__pa(kaddr) >> PAGE_SHIFT) -#define virt_to_page(kaddr) pfn_to_page(virt_to_pfn(kaddr)) -#define pfn_to_kaddr(pfn) __va((pfn) << PAGE_SHIFT) - -#define virt_addr_valid(kaddr) pfn_valid(virt_to_pfn(kaddr)) /* * On Book-E parts we need __va to parse the device tree and we can't @@ -209,9 +195,12 @@ static inline bool pfn_valid(unsigned long pfn) */ #if defined(CONFIG_PPC32) && defined(CONFIG_BOOKE) #define __va(x) ((void *)(unsigned long)((phys_addr_t)(x) + VIRT_PHYS_OFFSET)) -#define __pa(x) ((unsigned long)(x) - VIRT_PHYS_OFFSET) +#define __pa(x) ((phys_addr_t)(unsigned long)(x) - VIRT_PHYS_OFFSET) #else #ifdef CONFIG_PPC64 + +#define VIRTUAL_WARN_ON(x) WARN_ON(IS_ENABLED(CONFIG_DEBUG_VIRTUAL) && (x)) + /* * gcc miscompiles (unsigned long)(&static_var) - PAGE_OFFSET * with -mcmodel=medium, so we use & and | instead of - and + on 64-bit. @@ -219,13 +208,13 @@ static inline bool pfn_valid(unsigned long pfn) */ #define __va(x) \ ({ \ - VIRTUAL_BUG_ON((unsigned long)(x) >= PAGE_OFFSET); \ + VIRTUAL_WARN_ON((unsigned long)(x) >= PAGE_OFFSET); \ (void *)(unsigned long)((phys_addr_t)(x) | PAGE_OFFSET); \ }) #define __pa(x) \ ({ \ - VIRTUAL_BUG_ON((unsigned long)(x) < PAGE_OFFSET); \ + VIRTUAL_WARN_ON((unsigned long)(x) < PAGE_OFFSET); \ (unsigned long)(x) & 0x0fffffffffffffffUL; \ }) @@ -235,18 +224,32 @@ static inline bool pfn_valid(unsigned long pfn) #endif #endif +#ifndef __ASSEMBLY__ +static inline unsigned long virt_to_pfn(const void *kaddr) +{ + return __pa(kaddr) >> PAGE_SHIFT; +} + +static inline const void *pfn_to_kaddr(unsigned long pfn) +{ + return __va(pfn << PAGE_SHIFT); +} +#endif + +#define virt_to_page(kaddr) pfn_to_page(virt_to_pfn(kaddr)) +#define virt_addr_valid(vaddr) ({ \ + unsigned long _addr = (unsigned long)vaddr; \ + _addr >= PAGE_OFFSET && _addr < (unsigned long)high_memory && \ + pfn_valid(virt_to_pfn((void *)_addr)); \ +}) + /* * Unfortunately the PLT is in the BSS in the PPC32 ELF ABI, * and needs to be executable. This means the whole heap ends * up being executable. */ -#define VM_DATA_DEFAULT_FLAGS32 \ - (((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0) | \ - VM_READ | VM_WRITE | \ - VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) - -#define VM_DATA_DEFAULT_FLAGS64 (VM_READ | VM_WRITE | \ - VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) +#define VM_DATA_DEFAULT_FLAGS32 VM_DATA_FLAGS_TSK_EXEC +#define VM_DATA_DEFAULT_FLAGS64 VM_DATA_FLAGS_NON_EXEC #ifdef __powerpc64__ #include <asm/page_64.h> @@ -254,21 +257,16 @@ static inline bool pfn_valid(unsigned long pfn) #include <asm/page_32.h> #endif -/* align addr on a size boundary - adjust address up/down if needed */ -#define _ALIGN_UP(addr, size) __ALIGN_KERNEL(addr, size) -#define _ALIGN_DOWN(addr, size) ((addr)&(~((typeof(addr))(size)-1))) - -/* align addr on a size boundary - adjust address up if needed */ -#define _ALIGN(addr,size) _ALIGN_UP(addr,size) - /* * Don't compare things with KERNELBASE or PAGE_OFFSET to test for * "kernelness", use is_kernel_addr() - it should do what you want. */ #ifdef CONFIG_PPC_BOOK3E_64 #define is_kernel_addr(x) ((x) >= 0x8000000000000000ul) -#else +#elif defined(CONFIG_PPC_BOOK3S_64) #define is_kernel_addr(x) ((x) >= PAGE_OFFSET) +#else +#define is_kernel_addr(x) ((x) >= TASK_SIZE) #endif #ifndef CONFIG_PPC_BOOK3S_64 @@ -295,8 +293,13 @@ static inline bool pfn_valid(unsigned long pfn) /* * Some number of bits at the level of the page table that points to * a hugepte are used to encode the size. This masks those bits. + * On 8xx, HW assistance requires 4k alignment for the hugepte. */ +#ifdef CONFIG_PPC_8xx +#define HUGEPD_SHIFT_MASK 0xfff +#else #define HUGEPD_SHIFT_MASK 0x3f +#endif #ifndef __ASSEMBLY__ @@ -306,12 +309,6 @@ static inline bool pfn_valid(unsigned long pfn) #include <asm/pgtable-types.h> #endif - -#ifndef CONFIG_HUGETLB_PAGE -#define is_hugepd(pdep) (0) -#define pgd_huge(pgd) (0) -#endif /* CONFIG_HUGETLB_PAGE */ - struct page; extern void clear_user_page(void *page, unsigned long vaddr, struct page *pg); extern void copy_user_page(void *to, void *from, unsigned long vaddr, @@ -334,6 +331,5 @@ static inline unsigned long kaslr_offset(void) #include <asm-generic/memory_model.h> #endif /* __ASSEMBLY__ */ -#include <asm/slice.h> #endif /* _ASM_POWERPC_PAGE_H */ diff --git a/arch/powerpc/include/asm/page_32.h b/arch/powerpc/include/asm/page_32.h index d64dfe3ac712..b9ac9e3a771c 100644 --- a/arch/powerpc/include/asm/page_32.h +++ b/arch/powerpc/include/asm/page_32.h @@ -12,16 +12,6 @@ #define VM_DATA_DEFAULT_FLAGS VM_DATA_DEFAULT_FLAGS32 -#ifdef CONFIG_NOT_COHERENT_CACHE -#define ARCH_DMA_MINALIGN L1_CACHE_BYTES -#endif - -#ifdef CONFIG_PTE_64BIT -#define PTE_FLAGS_OFFSET 4 /* offset of PTE flags, in bytes */ -#else -#define PTE_FLAGS_OFFSET 0 -#endif - #if defined(CONFIG_PPC_256K_PAGES) || \ (defined(CONFIG_PPC_8xx) && defined(CONFIG_PPC_16K_PAGES)) #define PTE_SHIFT (PAGE_SHIFT - PTE_T_LOG2 - 2) /* 1/4 of a page */ diff --git a/arch/powerpc/include/asm/page_64.h b/arch/powerpc/include/asm/page_64.h index 5962797f784a..79a9b7c6a132 100644 --- a/arch/powerpc/include/asm/page_64.h +++ b/arch/powerpc/include/asm/page_64.h @@ -94,11 +94,8 @@ extern u64 ppc64_pft_size; * stack by default, so in the absence of a PT_GNU_STACK program header * we turn execute permission off. */ -#define VM_STACK_DEFAULT_FLAGS32 (VM_READ | VM_WRITE | VM_EXEC | \ - VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) - -#define VM_STACK_DEFAULT_FLAGS64 (VM_READ | VM_WRITE | \ - VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) +#define VM_STACK_DEFAULT_FLAGS32 VM_DATA_FLAGS_EXEC +#define VM_STACK_DEFAULT_FLAGS64 VM_DATA_FLAGS_NON_EXEC #define VM_STACK_DEFAULT_FLAGS \ (is_32bit_task() ? \ diff --git a/arch/powerpc/include/asm/papr-sysparm.h b/arch/powerpc/include/asm/papr-sysparm.h new file mode 100644 index 000000000000..0dbbff59101d --- /dev/null +++ b/arch/powerpc/include/asm/papr-sysparm.h @@ -0,0 +1,43 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef _ASM_POWERPC_PAPR_SYSPARM_H +#define _ASM_POWERPC_PAPR_SYSPARM_H + +#include <uapi/asm/papr-sysparm.h> + +typedef struct { + u32 token; +} papr_sysparm_t; + +#define mk_papr_sysparm(x_) ((papr_sysparm_t){ .token = x_, }) + +/* + * Derived from the "Defined Parameters" table in PAPR 7.3.16 System + * Parameters Option. Where the spec says "characteristics", we use + * "attrs" in the symbolic names to keep them from getting too + * unwieldy. + */ +#define PAPR_SYSPARM_SHARED_PROC_LPAR_ATTRS mk_papr_sysparm(20) +#define PAPR_SYSPARM_PROC_MODULE_INFO mk_papr_sysparm(43) +#define PAPR_SYSPARM_COOP_MEM_OVERCOMMIT_ATTRS mk_papr_sysparm(44) +#define PAPR_SYSPARM_TLB_BLOCK_INVALIDATE_ATTRS mk_papr_sysparm(50) +#define PAPR_SYSPARM_LPAR_NAME mk_papr_sysparm(55) + +/** + * struct papr_sysparm_buf - RTAS work area layout for system parameter functions. + * + * This is the memory layout of the buffers passed to/from + * ibm,get-system-parameter and ibm,set-system-parameter. It is + * distinct from the papr_sysparm_io_block structure that is passed + * between user space and the kernel. + */ +struct papr_sysparm_buf { + __be16 len; + char val[PAPR_SYSPARM_MAX_OUTPUT]; +}; + +struct papr_sysparm_buf *papr_sysparm_buf_alloc(void); +void papr_sysparm_buf_free(struct papr_sysparm_buf *buf); +int papr_sysparm_set(papr_sysparm_t param, const struct papr_sysparm_buf *buf); +int papr_sysparm_get(papr_sysparm_t param, struct papr_sysparm_buf *buf); + +#endif /* _ASM_POWERPC_PAPR_SYSPARM_H */ diff --git a/arch/powerpc/include/asm/paravirt.h b/arch/powerpc/include/asm/paravirt.h new file mode 100644 index 000000000000..b78b82d66057 --- /dev/null +++ b/arch/powerpc/include/asm/paravirt.h @@ -0,0 +1,223 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _ASM_POWERPC_PARAVIRT_H +#define _ASM_POWERPC_PARAVIRT_H + +#include <linux/jump_label.h> +#include <asm/smp.h> +#ifdef CONFIG_PPC64 +#include <asm/paca.h> +#include <asm/lppaca.h> +#include <asm/hvcall.h> +#endif + +#ifdef CONFIG_PPC_SPLPAR +#include <linux/smp.h> +#include <asm/kvm_guest.h> +#include <asm/cputhreads.h> + +DECLARE_STATIC_KEY_FALSE(shared_processor); + +static inline bool is_shared_processor(void) +{ + return static_branch_unlikely(&shared_processor); +} + +#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING +extern struct static_key paravirt_steal_enabled; +extern struct static_key paravirt_steal_rq_enabled; + +u64 pseries_paravirt_steal_clock(int cpu); + +static inline u64 paravirt_steal_clock(int cpu) +{ + return pseries_paravirt_steal_clock(cpu); +} +#endif + +/* If bit 0 is set, the cpu has been ceded, conferred, or preempted */ +static inline u32 yield_count_of(int cpu) +{ + __be32 yield_count = READ_ONCE(lppaca_of(cpu).yield_count); + return be32_to_cpu(yield_count); +} + +/* + * Spinlock code confers and prods, so don't trace the hcalls because the + * tracing code takes spinlocks which can cause recursion deadlocks. + * + * These calls are made while the lock is not held: the lock slowpath yields if + * it can not acquire the lock, and unlock slow path might prod if a waiter has + * yielded). So this may not be a problem for simple spin locks because the + * tracing does not technically recurse on the lock, but we avoid it anyway. + * + * However the queued spin lock contended path is more strictly ordered: the + * H_CONFER hcall is made after the task has queued itself on the lock, so then + * recursing on that lock will cause the task to then queue up again behind the + * first instance (or worse: queued spinlocks use tricks that assume a context + * never waits on more than one spinlock, so such recursion may cause random + * corruption in the lock code). + */ +static inline void yield_to_preempted(int cpu, u32 yield_count) +{ + plpar_hcall_norets_notrace(H_CONFER, get_hard_smp_processor_id(cpu), yield_count); +} + +static inline void prod_cpu(int cpu) +{ + plpar_hcall_norets_notrace(H_PROD, get_hard_smp_processor_id(cpu)); +} + +static inline void yield_to_any(void) +{ + plpar_hcall_norets_notrace(H_CONFER, -1, 0); +} + +static inline bool is_vcpu_idle(int vcpu) +{ + return lppaca_of(vcpu).idle; +} + +static inline bool vcpu_is_dispatched(int vcpu) +{ + /* + * This is the yield_count. An "odd" value (low bit on) means that + * the processor is yielded (either because of an OS yield or a + * hypervisor preempt). An even value implies that the processor is + * currently executing. + */ + return (!(yield_count_of(vcpu) & 1)); +} +#else +static inline bool is_shared_processor(void) +{ + return false; +} + +static inline u32 yield_count_of(int cpu) +{ + return 0; +} + +extern void ___bad_yield_to_preempted(void); +static inline void yield_to_preempted(int cpu, u32 yield_count) +{ + ___bad_yield_to_preempted(); /* This would be a bug */ +} + +extern void ___bad_yield_to_any(void); +static inline void yield_to_any(void) +{ + ___bad_yield_to_any(); /* This would be a bug */ +} + +extern void ___bad_prod_cpu(void); +static inline void prod_cpu(int cpu) +{ + ___bad_prod_cpu(); /* This would be a bug */ +} + +static inline bool is_vcpu_idle(int vcpu) +{ + return false; +} +static inline bool vcpu_is_dispatched(int vcpu) +{ + return true; +} +#endif + +#define vcpu_is_preempted vcpu_is_preempted +static inline bool vcpu_is_preempted(int cpu) +{ + /* + * The dispatch/yield bit alone is an imperfect indicator of + * whether the hypervisor has dispatched @cpu to run on a physical + * processor. When it is clear, @cpu is definitely not preempted. + * But when it is set, it means only that it *might* be, subject to + * other conditions. So we check other properties of the VM and + * @cpu first, resorting to the yield count last. + */ + + /* + * Hypervisor preemption isn't possible in dedicated processor + * mode by definition. + */ + if (!is_shared_processor()) + return false; + + /* + * If the hypervisor has dispatched the target CPU on a physical + * processor, then the target CPU is definitely not preempted. + */ + if (vcpu_is_dispatched(cpu)) + return false; + + /* + * if the target CPU is not dispatched and the guest OS + * has not marked the CPU idle, then it is hypervisor preempted. + */ + if (!is_vcpu_idle(cpu)) + return true; + +#ifdef CONFIG_PPC_SPLPAR + if (!is_kvm_guest()) { + int first_cpu, i; + + /* + * The result of vcpu_is_preempted() is used in a + * speculative way, and is always subject to invalidation + * by events internal and external to Linux. While we can + * be called in preemptable context (in the Linux sense), + * we're not accessing per-cpu resources in a way that can + * race destructively with Linux scheduler preemption and + * migration, and callers can tolerate the potential for + * error introduced by sampling the CPU index without + * pinning the task to it. So it is permissible to use + * raw_smp_processor_id() here to defeat the preempt debug + * warnings that can arise from using smp_processor_id() + * in arbitrary contexts. + */ + first_cpu = cpu_first_thread_sibling(raw_smp_processor_id()); + + /* + * The PowerVM hypervisor dispatches VMs on a whole core + * basis. So we know that a thread sibling of the executing CPU + * cannot have been preempted by the hypervisor, even if it + * has called H_CONFER, which will set the yield bit. + */ + if (cpu_first_thread_sibling(cpu) == first_cpu) + return false; + + /* + * The specific target CPU was marked by guest OS as idle, but + * then also check all other cpus in the core for PowerVM + * because it does core scheduling and one of the vcpu + * of the core getting preempted by hypervisor implies + * other vcpus can also be considered preempted. + */ + first_cpu = cpu_first_thread_sibling(cpu); + for (i = first_cpu; i < first_cpu + threads_per_core; i++) { + if (i == cpu) + continue; + if (vcpu_is_dispatched(i)) + return false; + if (!is_vcpu_idle(i)) + return true; + } + } +#endif + + /* + * None of the threads in target CPU's core are running but none of + * them were preempted too. Hence assume the target CPU to be + * non-preempted. + */ + return false; +} + +static inline bool pv_is_native_spin_unlock(void) +{ + return !is_shared_processor(); +} + +#endif /* _ASM_POWERPC_PARAVIRT_H */ diff --git a/arch/powerpc/include/asm/paravirt_api_clock.h b/arch/powerpc/include/asm/paravirt_api_clock.h new file mode 100644 index 000000000000..d25ca7ac57c7 --- /dev/null +++ b/arch/powerpc/include/asm/paravirt_api_clock.h @@ -0,0 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <asm/paravirt.h> diff --git a/arch/powerpc/include/asm/parport.h b/arch/powerpc/include/asm/parport.h index 8abfb8f7c33d..42cc321ed754 100644 --- a/arch/powerpc/include/asm/parport.h +++ b/arch/powerpc/include/asm/parport.h @@ -11,7 +11,7 @@ #define _ASM_POWERPC_PARPORT_H #ifdef __KERNEL__ -#include <asm/prom.h> +#include <linux/of_irq.h> static int parport_pc_find_nonpci_ports (int autoirq, int autodma) { diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h index ea6ec65970ef..2aa3a091ef20 100644 --- a/arch/powerpc/include/asm/pci-bridge.h +++ b/arch/powerpc/include/asm/pci-bridge.h @@ -8,6 +8,7 @@ #include <linux/list.h> #include <linux/ioport.h> #include <linux/numa.h> +#include <linux/iommu.h> struct device_node; @@ -44,6 +45,9 @@ struct pci_controller_ops { #endif void (*shutdown)(struct pci_controller *hose); + + struct iommu_group *(*device_group)(struct pci_controller *hose, + struct pci_dev *pdev); }; /* @@ -66,7 +70,7 @@ struct pci_controller { void __iomem *io_base_virt; #ifdef CONFIG_PPC64 - void *io_base_alloc; + void __iomem *io_base_alloc; #endif resource_size_t io_base_phys; resource_size_t pci_io_size; @@ -126,7 +130,14 @@ struct pci_controller { #endif /* CONFIG_PPC64 */ void *private_data; - struct npu *npu; + + /* IRQ domain hierarchy */ + struct irq_domain *dev_domain; + struct irq_domain *msi_domain; + struct fwnode_handle *fwnode; + + /* iommu_ops support */ + struct iommu_device iommu; }; /* These are used for config access before all the PCI probing @@ -166,11 +177,17 @@ static inline struct pci_controller *pci_bus_to_host(const struct pci_bus *bus) return bus->sysdata; } -#ifndef CONFIG_PPC64 - +#ifdef CONFIG_PPC_PMAC extern int pci_device_from_OF_node(struct device_node *node, u8 *bus, u8 *devfn); +#endif +#ifndef CONFIG_PPC64 + +#ifdef CONFIG_PPC_PCI_OF_BUS_MAP extern void pci_create_OF_bus_map(void); +#else +static inline void pci_create_OF_bus_map(void) {} +#endif #else /* CONFIG_PPC64 */ @@ -202,7 +219,6 @@ struct pci_dn { #define IODA_INVALID_PE 0xFFFFFFFF unsigned int pe_number; #ifdef CONFIG_PCI_IOV - int vf_index; /* VF index in the PF */ u16 vfs_expanded; /* number of VFs IOV BAR expanded */ u16 num_vfs; /* number of VFs enabled*/ unsigned int *pe_num_map; /* PE# for the first VF PE or array */ @@ -223,21 +239,14 @@ struct pci_dn { extern struct pci_dn *pci_get_pdn_by_devfn(struct pci_bus *bus, int devfn); extern struct pci_dn *pci_get_pdn(struct pci_dev *pdev); -extern struct pci_dn *add_dev_pci_data(struct pci_dev *pdev); -extern void remove_dev_pci_data(struct pci_dev *pdev); extern struct pci_dn *pci_add_device_node_info(struct pci_controller *hose, struct device_node *dn); extern void pci_remove_device_node_info(struct device_node *dn); -static inline int pci_device_from_OF_node(struct device_node *np, - u8 *bus, u8 *devfn) -{ - if (!PCI_DN(np)) - return -ENODEV; - *bus = PCI_DN(np)->busno; - *devfn = PCI_DN(np)->devfn; - return 0; -} +#ifdef CONFIG_PCI_IOV +struct pci_dn *add_sriov_vf_pdns(struct pci_dev *pdev); +void remove_sriov_vf_pdns(struct pci_dev *pdev); +#endif #if defined(CONFIG_EEH) static inline struct eeh_dev *pdn_to_eeh_dev(struct pci_dn *pdn) diff --git a/arch/powerpc/include/asm/pci.h b/arch/powerpc/include/asm/pci.h index 327567b8f7d6..46a9c4491ed0 100644 --- a/arch/powerpc/include/asm/pci.h +++ b/arch/powerpc/include/asm/pci.h @@ -9,12 +9,11 @@ #include <linux/types.h> #include <linux/slab.h> #include <linux/string.h> -#include <linux/dma-mapping.h> +#include <linux/dma-map-ops.h> #include <linux/scatterlist.h> #include <asm/machdep.h> #include <asm/io.h> -#include <asm/prom.h> #include <asm/pci-bridge.h> /* Return values for pci_controller_ops.probe_mode function */ @@ -39,7 +38,6 @@ #define pcibios_assign_all_busses() \ (pci_has_flag(PCI_REASSIGN_ALL_BUS)) -#define HAVE_ARCH_PCI_GET_LEGACY_IDE_IRQ static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel) { if (ppc_md.pci_get_legacy_ide_irq) @@ -48,7 +46,7 @@ static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel) } #ifdef CONFIG_PCI -extern void set_pci_dma_ops(const struct dma_map_ops *dma_ops); +void __init set_pci_dma_ops(const struct dma_map_ops *dma_ops); #else /* CONFIG_PCI */ #define set_pci_dma_ops(d) #endif @@ -84,7 +82,8 @@ extern int pci_legacy_write(struct pci_bus *bus, loff_t port, u32 val, extern int pci_mmap_legacy_page_range(struct pci_bus *bus, struct vm_area_struct *vma, enum pci_mmap_state mmap_state); - +extern void pci_adjust_legacy_attr(struct pci_bus *bus, + enum pci_mmap_state mmap_type); #define HAVE_PCI_LEGACY 1 extern void pcibios_claim_one_bus(struct pci_bus *b); @@ -106,25 +105,15 @@ extern void of_scan_pci_bridge(struct pci_dev *dev); extern void of_scan_bus(struct device_node *node, struct pci_bus *bus); extern void of_rescan_bus(struct device_node *node, struct pci_bus *bus); -struct file; -extern pgprot_t pci_phys_mem_access_prot(struct file *file, - unsigned long pfn, +extern pgprot_t pci_phys_mem_access_prot(unsigned long pfn, unsigned long size, pgprot_t prot); extern resource_size_t pcibios_io_space_offset(struct pci_controller *hose); -extern void pcibios_setup_bus_devices(struct pci_bus *bus); extern void pcibios_setup_bus_self(struct pci_bus *bus); extern void pcibios_setup_phb_io_space(struct pci_controller *hose); extern void pcibios_scan_phb(struct pci_controller *hose); #endif /* __KERNEL__ */ -extern struct pci_dev *pnv_pci_get_gpu_dev(struct pci_dev *npdev); -extern struct pci_dev *pnv_pci_get_npu_dev(struct pci_dev *gpdev, int index); -extern int pnv_npu2_init(struct pci_controller *hose); -extern int pnv_npu2_map_lpar_dev(struct pci_dev *gpdev, unsigned int lparid, - unsigned long msr); -extern int pnv_npu2_unmap_lpar_dev(struct pci_dev *gpdev); - #endif /* __ASM_POWERPC_PCI_H */ diff --git a/arch/powerpc/include/asm/percpu.h b/arch/powerpc/include/asm/percpu.h index dce863a7635c..8e5b7d0b851c 100644 --- a/arch/powerpc/include/asm/percpu.h +++ b/arch/powerpc/include/asm/percpu.h @@ -10,8 +10,6 @@ #ifdef CONFIG_SMP -#include <asm/paca.h> - #define __my_cpu_offset local_paca->data_offset #endif /* CONFIG_SMP */ @@ -19,4 +17,6 @@ #include <asm-generic/percpu.h> +#include <asm/paca.h> + #endif /* _ASM_POWERPC_PERCPU_H_ */ diff --git a/arch/powerpc/include/asm/perf_event.h b/arch/powerpc/include/asm/perf_event.h index 7426d7a90e1e..164e910bf654 100644 --- a/arch/powerpc/include/asm/perf_event.h +++ b/arch/powerpc/include/asm/perf_event.h @@ -12,6 +12,9 @@ #ifdef CONFIG_PPC_PERF_CTRS #include <asm/perf_event_server.h> +#else +static inline bool is_sier_available(void) { return false; } +static inline unsigned long get_pmcs_ext_regs(int idx) { return 0; } #endif #ifdef CONFIG_FSL_EMB_PERF_EVENT @@ -32,10 +35,14 @@ do { \ (regs)->result = 0; \ (regs)->nip = __ip; \ - (regs)->gpr[1] = current_stack_pointer(); \ + (regs)->gpr[1] = current_stack_frame(); \ asm volatile("mfmsr %0" : "=r" ((regs)->msr)); \ } while (0) /* To support perf_regs sier update */ extern bool is_sier_available(void); +extern unsigned long get_pmcs_ext_regs(int idx); +/* To define perf extended regs mask value */ +extern u64 PERF_REG_EXTENDED_MASK; +#define PERF_REG_EXTENDED_MASK PERF_REG_EXTENDED_MASK #endif diff --git a/arch/powerpc/include/asm/perf_event_server.h b/arch/powerpc/include/asm/perf_event_server.h index 3e9703f44c7c..e2221d29fdf9 100644 --- a/arch/powerpc/include/asm/perf_event_server.h +++ b/arch/powerpc/include/asm/perf_event_server.h @@ -17,6 +17,13 @@ struct perf_event; +struct mmcr_regs { + unsigned long mmcr0; + unsigned long mmcr1; + unsigned long mmcr2; + unsigned long mmcra; + unsigned long mmcr3; +}; /* * This struct provides the constants and functions needed to * describe the PMU on a particular POWER-family CPU. @@ -28,26 +35,26 @@ struct power_pmu { unsigned long add_fields; unsigned long test_adder; int (*compute_mmcr)(u64 events[], int n_ev, - unsigned int hwc[], unsigned long mmcr[], - struct perf_event *pevents[]); + unsigned int hwc[], struct mmcr_regs *mmcr, + struct perf_event *pevents[], u32 flags); int (*get_constraint)(u64 event_id, unsigned long *mskp, - unsigned long *valp); + unsigned long *valp, u64 event_config1); int (*get_alternatives)(u64 event_id, unsigned int flags, u64 alt[]); void (*get_mem_data_src)(union perf_mem_data_src *dsrc, u32 flags, struct pt_regs *regs); - void (*get_mem_weight)(u64 *weight); + void (*get_mem_weight)(u64 *weight, u64 type); unsigned long group_constraint_mask; unsigned long group_constraint_val; u64 (*bhrb_filter_map)(u64 branch_sample_type); void (*config_bhrb)(u64 pmu_bhrb_filter); - void (*disable_pmc)(unsigned int pmc, unsigned long mmcr[]); + void (*disable_pmc)(unsigned int pmc, struct mmcr_regs *mmcr); int (*limited_pmc_event)(u64 event_id); u32 flags; const struct attribute_group **attr_groups; int n_generic; int *generic_events; - int (*cache_events)[PERF_COUNT_HW_CACHE_MAX] + u64 (*cache_events)[PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] [PERF_COUNT_HW_CACHE_RESULT_MAX]; @@ -55,6 +62,17 @@ struct power_pmu { int *blacklist_ev; /* BHRB entries in the PMU */ int bhrb_nr; + /* + * set this flag with `PERF_PMU_CAP_EXTENDED_REGS` if + * the pmu supports extended perf regs capability + */ + int capabilities; + /* + * Function to check event code for values which are + * reserved. Function takes struct perf_event as input, + * since event code could be spread in attr.config* + */ + int (*check_attr_config)(struct perf_event *ev); }; /* @@ -69,6 +87,9 @@ struct power_pmu { #define PPMU_HAS_SIER 0x00000040 /* Has SIER */ #define PPMU_ARCH_207S 0x00000080 /* PMC is architecture v2.07S */ #define PPMU_NO_SIAR 0x00000100 /* Do not use SIAR */ +#define PPMU_ARCH_31 0x00000200 /* Has MMCR3, SIER2 and SIER3 */ +#define PPMU_P10_DD1 0x00000400 /* Is power10 DD1 processor version */ +#define PPMU_HAS_ATTR_CONFIG1 0x00000800 /* Using config1 attribute */ /* * Values for flags to get_alternatives() @@ -77,7 +98,7 @@ struct power_pmu { #define PPMU_LIMITED_PMC_REQD 2 /* have to put this on a limited PMC */ #define PPMU_ONLY_COUNT_RUN 4 /* only counting in run state */ -extern int register_power_pmu(struct power_pmu *); +int __init register_power_pmu(struct power_pmu *pmu); struct pt_regs; extern unsigned long perf_misc_flags(struct pt_regs *regs); diff --git a/arch/powerpc/include/asm/pgalloc.h b/arch/powerpc/include/asm/pgalloc.h index 6dd78a2dc03a..3a971e2a8c73 100644 --- a/arch/powerpc/include/asm/pgalloc.h +++ b/arch/powerpc/include/asm/pgalloc.h @@ -45,6 +45,10 @@ static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage) pte_fragment_free((unsigned long *)ptepage, 0); } +/* arch use pte_free_defer() implementation in arch/powerpc/mm/pgtable-frag.c */ +#define pte_free_defer pte_free_defer +void pte_free_defer(struct mm_struct *mm, pgtable_t pgtable); + /* * Functions that deal with pagetables that could be at any level of * the table need to be passed an "index_size" so they know how to @@ -70,9 +74,4 @@ extern struct kmem_cache *pgtable_cache[]; #include <asm/nohash/pgalloc.h> #endif -static inline pgtable_t pmd_pgtable(pmd_t pmd) -{ - return (pgtable_t)pmd_page_vaddr(pmd); -} - #endif /* _ASM_POWERPC_PGALLOC_H */ diff --git a/arch/powerpc/include/asm/pgtable-be-types.h b/arch/powerpc/include/asm/pgtable-be-types.h index b169bbf95fcb..82633200b500 100644 --- a/arch/powerpc/include/asm/pgtable-be-types.h +++ b/arch/powerpc/include/asm/pgtable-be-types.h @@ -101,6 +101,7 @@ static inline bool pmd_xchg(pmd_t *pmdp, pmd_t old, pmd_t new) return pmd_raw(old) == prev; } +#ifdef CONFIG_ARCH_HAS_HUGEPD typedef struct { __be64 pdbe; } hugepd_t; #define __hugepd(x) ((hugepd_t) { cpu_to_be64(x) }) @@ -108,5 +109,6 @@ static inline unsigned long hpd_val(hugepd_t x) { return be64_to_cpu(x.pdbe); } +#endif #endif /* _ASM_POWERPC_PGTABLE_BE_TYPES_H */ diff --git a/arch/powerpc/include/asm/pgtable-masks.h b/arch/powerpc/include/asm/pgtable-masks.h new file mode 100644 index 000000000000..6e8e2db26a5a --- /dev/null +++ b/arch/powerpc/include/asm/pgtable-masks.h @@ -0,0 +1,32 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_POWERPC_PGTABLE_MASKS_H +#define _ASM_POWERPC_PGTABLE_MASKS_H + +#ifndef _PAGE_NA +#define _PAGE_NA 0 +#define _PAGE_NAX _PAGE_EXEC +#define _PAGE_RO _PAGE_READ +#define _PAGE_ROX (_PAGE_READ | _PAGE_EXEC) +#define _PAGE_RW (_PAGE_READ | _PAGE_WRITE) +#define _PAGE_RWX (_PAGE_READ | _PAGE_WRITE | _PAGE_EXEC) +#endif + +/* Permission flags for kernel mappings */ +#ifndef _PAGE_KERNEL_RO +#define _PAGE_KERNEL_RO _PAGE_RO +#define _PAGE_KERNEL_ROX _PAGE_ROX +#define _PAGE_KERNEL_RW (_PAGE_RW | _PAGE_DIRTY) +#define _PAGE_KERNEL_RWX (_PAGE_RWX | _PAGE_DIRTY) +#endif + +/* Permission masks used to generate the __P and __S table */ +#define PAGE_NONE __pgprot(_PAGE_BASE | _PAGE_NA) +#define PAGE_EXECONLY_X __pgprot(_PAGE_BASE | _PAGE_NAX) +#define PAGE_SHARED __pgprot(_PAGE_BASE | _PAGE_RW) +#define PAGE_SHARED_X __pgprot(_PAGE_BASE | _PAGE_RWX) +#define PAGE_COPY __pgprot(_PAGE_BASE | _PAGE_RO) +#define PAGE_COPY_X __pgprot(_PAGE_BASE | _PAGE_ROX) +#define PAGE_READONLY __pgprot(_PAGE_BASE | _PAGE_RO) +#define PAGE_READONLY_X __pgprot(_PAGE_BASE | _PAGE_ROX) + +#endif /* _ASM_POWERPC_PGTABLE_MASKS_H */ diff --git a/arch/powerpc/include/asm/pgtable-types.h b/arch/powerpc/include/asm/pgtable-types.h index d11b4c61d686..082c85cc09b1 100644 --- a/arch/powerpc/include/asm/pgtable-types.h +++ b/arch/powerpc/include/asm/pgtable-types.h @@ -2,17 +2,33 @@ #ifndef _ASM_POWERPC_PGTABLE_TYPES_H #define _ASM_POWERPC_PGTABLE_TYPES_H +#if defined(__CHECKER__) || !defined(CONFIG_PPC32) +#define STRICT_MM_TYPECHECKS +#endif + /* PTE level */ #if defined(CONFIG_PPC_8xx) && defined(CONFIG_PPC_16K_PAGES) typedef struct { pte_basic_t pte, pte1, pte2, pte3; } pte_t; -#else +#elif defined(STRICT_MM_TYPECHECKS) typedef struct { pte_basic_t pte; } pte_t; +#else +typedef pte_basic_t pte_t; #endif + +#if defined(STRICT_MM_TYPECHECKS) || \ + (defined(CONFIG_PPC_8xx) && defined(CONFIG_PPC_16K_PAGES)) #define __pte(x) ((pte_t) { (x) }) static inline pte_basic_t pte_val(pte_t x) { return x.pte; } +#else +#define __pte(x) ((pte_t)(x)) +static inline pte_basic_t pte_val(pte_t x) +{ + return x; +} +#endif /* PMD level */ #ifdef CONFIG_PPC64 @@ -67,11 +83,13 @@ static inline bool pte_xchg(pte_t *ptep, pte_t old, pte_t new) } #endif +#ifdef CONFIG_ARCH_HAS_HUGEPD typedef struct { unsigned long pd; } hugepd_t; #define __hugepd(x) ((hugepd_t) { (x) }) static inline unsigned long hpd_val(hugepd_t x) { return x.pd; } +#endif #endif /* _ASM_POWERPC_PGTABLE_TYPES_H */ diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h index 0e4ec8cc37b7..9224f23065ff 100644 --- a/arch/powerpc/include/asm/pgtable.h +++ b/arch/powerpc/include/asm/pgtable.h @@ -20,32 +20,46 @@ struct mm_struct; #include <asm/nohash/pgtable.h> #endif /* !CONFIG_PPC_BOOK3S */ -/* Note due to the way vm flags are laid out, the bits are XWR */ -#define __P000 PAGE_NONE -#define __P001 PAGE_READONLY -#define __P010 PAGE_COPY -#define __P011 PAGE_COPY -#define __P100 PAGE_READONLY_X -#define __P101 PAGE_READONLY_X -#define __P110 PAGE_COPY_X -#define __P111 PAGE_COPY_X - -#define __S000 PAGE_NONE -#define __S001 PAGE_READONLY -#define __S010 PAGE_SHARED -#define __S011 PAGE_SHARED -#define __S100 PAGE_READONLY_X -#define __S101 PAGE_READONLY_X -#define __S110 PAGE_SHARED_X -#define __S111 PAGE_SHARED_X +/* + * Protection used for kernel text. We want the debuggers to be able to + * set breakpoints anywhere, so don't write protect the kernel text + * on platforms where such control is possible. + */ +#if defined(CONFIG_KGDB) || defined(CONFIG_XMON) || defined(CONFIG_BDI_SWITCH) || \ + defined(CONFIG_KPROBES) || defined(CONFIG_DYNAMIC_FTRACE) +#define PAGE_KERNEL_TEXT PAGE_KERNEL_X +#else +#define PAGE_KERNEL_TEXT PAGE_KERNEL_ROX +#endif + +/* Make modules code happy. We don't set RO yet */ +#define PAGE_KERNEL_EXEC PAGE_KERNEL_X + +/* Advertise special mapping type for AGP */ +#define PAGE_AGP (PAGE_KERNEL_NC) +#define HAVE_PAGE_AGP #ifndef __ASSEMBLY__ -#include <asm/tlbflush.h> +void set_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, + pte_t pte, unsigned int nr); +#define set_ptes set_ptes +#define update_mmu_cache(vma, addr, ptep) \ + update_mmu_cache_range(NULL, vma, addr, ptep, 1) + +#ifndef MAX_PTRS_PER_PGD +#define MAX_PTRS_PER_PGD PTRS_PER_PGD +#endif /* Keep these as a macros to avoid include dependency mess */ #define pte_page(x) pfn_to_page(pte_pfn(x)) #define mk_pte(page, pgprot) pfn_pte(page_to_pfn(page), (pgprot)) + +static inline unsigned long pte_pfn(pte_t pte) +{ + return (pte_val(pte) & PTE_RPN_MASK) >> PTE_RPN_SHIFT; +} + /* * Select all bits except the pfn */ @@ -57,6 +71,19 @@ static inline pgprot_t pte_pgprot(pte_t pte) return __pgprot(pte_flags); } +static inline pgprot_t pgprot_nx(pgprot_t prot) +{ + return pte_pgprot(pte_exprotect(__pte(pgprot_val(prot)))); +} +#define pgprot_nx pgprot_nx + +#ifndef pmd_page_vaddr +static inline const void *pmd_page_vaddr(pmd_t pmd) +{ + return __va(pmd_val(pmd) & ~PMD_MASKED_BITS); +} +#define pmd_page_vaddr pmd_page_vaddr +#endif /* * ZERO_PAGE is a global shared page that is always zero: used * for zero-mapped memory areas etc.. @@ -67,17 +94,10 @@ extern unsigned long empty_zero_page[]; extern pgd_t swapper_pg_dir[]; extern void paging_init(void); +void poking_init(void); extern unsigned long ioremap_bot; - -/* - * kern_addr_valid is intended to indicate whether an address is a valid - * kernel address. Most 32-bit archs define it as always true (like this) - * but most 64-bit archs actually perform a test. What should we do here? - */ -#define kern_addr_valid(addr) (1) - -#include <asm-generic/pgtable.h> +extern const pgprot_t protection_map[16]; #ifndef CONFIG_TRANSPARENT_HUGEPAGE #define pmd_large(pmd) 0 @@ -88,17 +108,48 @@ unsigned long vmalloc_to_phys(void *vmalloc_addr); void pgtable_cache_add(unsigned int shift); +pte_t *early_pte_alloc_kernel(pmd_t *pmdp, unsigned long va); + #if defined(CONFIG_STRICT_KERNEL_RWX) || defined(CONFIG_PPC32) void mark_initmem_nx(void); #else static inline void mark_initmem_nx(void) { } #endif -#ifdef CONFIG_PPC_DEBUG_WX -void ptdump_check_wx(void); -#else -static inline void ptdump_check_wx(void) { } -#endif +#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS +int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address, + pte_t *ptep, pte_t entry, int dirty); + +pgprot_t __phys_mem_access_prot(unsigned long pfn, unsigned long size, + pgprot_t vma_prot); + +struct file; +static inline pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, + unsigned long size, pgprot_t vma_prot) +{ + return __phys_mem_access_prot(pfn, size, vma_prot); +} +#define __HAVE_PHYS_MEM_ACCESS_PROT + +void __update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep); + +/* + * This gets called at the end of handling a page fault, when + * the kernel has put a new PTE into the page table for the process. + * We use it to ensure coherency between the i-cache and d-cache + * for the page which has just been mapped in. + * On machines which use an MMU hash table, we use this to put a + * corresponding HPTE into the hash table ahead of time, instead of + * waiting for the inevitable extra hash-table miss exception. + */ +static inline void update_mmu_cache_range(struct vm_fault *vmf, + struct vm_area_struct *vma, unsigned long address, + pte_t *ptep, unsigned int nr) +{ + if ((mmu_has_feature(MMU_FTR_HPTE_TABLE) && !radix_enabled()) || + (IS_ENABLED(CONFIG_PPC_E500) && IS_ENABLED(CONFIG_HUGETLB_PAGE))) + __update_mmu_cache(vma, address, ptep); +} /* * When used, PTE_FRAG_NR is defined in subarch pgtable.h @@ -145,22 +196,45 @@ static inline bool pud_is_leaf(pud_t pud) } #endif -#ifndef pgd_is_leaf -#define pgd_is_leaf pgd_is_leaf -static inline bool pgd_is_leaf(pgd_t pgd) +#ifndef p4d_is_leaf +#define p4d_is_leaf p4d_is_leaf +static inline bool p4d_is_leaf(p4d_t p4d) { return false; } #endif -#ifdef CONFIG_PPC64 -#define is_ioremap_addr is_ioremap_addr -static inline bool is_ioremap_addr(const void *x) +#define pmd_pgtable pmd_pgtable +static inline pgtable_t pmd_pgtable(pmd_t pmd) { - unsigned long addr = (unsigned long)x; + return (pgtable_t)pmd_page_vaddr(pmd); +} - return addr >= IOREMAP_BASE && addr < IOREMAP_END; +#ifdef CONFIG_PPC64 +int __meminit vmemmap_populated(unsigned long vmemmap_addr, int vmemmap_map_size); +bool altmap_cross_boundary(struct vmem_altmap *altmap, unsigned long start, + unsigned long page_size); +/* + * mm/memory_hotplug.c:mhp_supports_memmap_on_memory goes into details + * some of the restrictions. We don't check for PMD_SIZE because our + * vmemmap allocation code can fallback correctly. The pageblock + * alignment requirement is met using altmap->reserve blocks. + */ +#define arch_supports_memmap_on_memory arch_supports_memmap_on_memory +static inline bool arch_supports_memmap_on_memory(unsigned long vmemmap_size) +{ + if (!radix_enabled()) + return false; + /* + * With 4K page size and 2M PMD_SIZE, we can align + * things better with memory block size value + * starting from 128MB. Hence align things with PMD_SIZE. + */ + if (IS_ENABLED(CONFIG_PPC_4K_PAGES)) + return IS_ALIGNED(vmemmap_size, PMD_SIZE); + return true; } + #endif /* CONFIG_PPC64 */ #endif /* __ASSEMBLY__ */ diff --git a/arch/powerpc/include/asm/pkeys.h b/arch/powerpc/include/asm/pkeys.h index 20ebf153c871..59a2c7dbc78f 100644 --- a/arch/powerpc/include/asm/pkeys.h +++ b/arch/powerpc/include/asm/pkeys.h @@ -11,9 +11,7 @@ #include <linux/jump_label.h> #include <asm/firmware.h> -DECLARE_STATIC_KEY_TRUE(pkey_disabled); -extern int pkeys_total; /* total pkeys as per device tree */ -extern u32 initial_allocation_mask; /* bits set for the initially allocated keys */ +extern int num_pkey; extern u32 reserved_allocation_mask; /* bits set for reserved keys */ #define ARCH_VM_PKEY_FLAGS (VM_PKEY_BIT0 | VM_PKEY_BIT1 | VM_PKEY_BIT2 | \ @@ -25,48 +23,28 @@ extern u32 reserved_allocation_mask; /* bits set for reserved keys */ PKEY_DISABLE_WRITE | \ PKEY_DISABLE_EXECUTE) +#ifdef CONFIG_PPC_BOOK3S_64 +#include <asm/book3s/64/pkeys.h> +#else +#error "Not supported" +#endif + + static inline u64 pkey_to_vmflag_bits(u16 pkey) { return (((u64)pkey << VM_PKEY_SHIFT) & ARCH_VM_PKEY_FLAGS); } -static inline u64 vmflag_to_pte_pkey_bits(u64 vm_flags) -{ - if (static_branch_likely(&pkey_disabled)) - return 0x0UL; - - return (((vm_flags & VM_PKEY_BIT0) ? H_PTE_PKEY_BIT4 : 0x0UL) | - ((vm_flags & VM_PKEY_BIT1) ? H_PTE_PKEY_BIT3 : 0x0UL) | - ((vm_flags & VM_PKEY_BIT2) ? H_PTE_PKEY_BIT2 : 0x0UL) | - ((vm_flags & VM_PKEY_BIT3) ? H_PTE_PKEY_BIT1 : 0x0UL) | - ((vm_flags & VM_PKEY_BIT4) ? H_PTE_PKEY_BIT0 : 0x0UL)); -} - static inline int vma_pkey(struct vm_area_struct *vma) { - if (static_branch_likely(&pkey_disabled)) + if (!mmu_has_feature(MMU_FTR_PKEY)) return 0; return (vma->vm_flags & ARCH_VM_PKEY_FLAGS) >> VM_PKEY_SHIFT; } -#define arch_max_pkey() pkeys_total - -static inline u64 pte_to_hpte_pkey_bits(u64 pteflags) +static inline int arch_max_pkey(void) { - return (((pteflags & H_PTE_PKEY_BIT0) ? HPTE_R_KEY_BIT0 : 0x0UL) | - ((pteflags & H_PTE_PKEY_BIT1) ? HPTE_R_KEY_BIT1 : 0x0UL) | - ((pteflags & H_PTE_PKEY_BIT2) ? HPTE_R_KEY_BIT2 : 0x0UL) | - ((pteflags & H_PTE_PKEY_BIT3) ? HPTE_R_KEY_BIT3 : 0x0UL) | - ((pteflags & H_PTE_PKEY_BIT4) ? HPTE_R_KEY_BIT4 : 0x0UL)); -} - -static inline u16 pte_to_pkey_bits(u64 pteflags) -{ - return (((pteflags & H_PTE_PKEY_BIT0) ? 0x10 : 0x0UL) | - ((pteflags & H_PTE_PKEY_BIT1) ? 0x8 : 0x0UL) | - ((pteflags & H_PTE_PKEY_BIT2) ? 0x4 : 0x0UL) | - ((pteflags & H_PTE_PKEY_BIT3) ? 0x2 : 0x0UL) | - ((pteflags & H_PTE_PKEY_BIT4) ? 0x1 : 0x0UL)); + return num_pkey; } #define pkey_alloc_mask(pkey) (0x1 << pkey) @@ -101,7 +79,7 @@ static inline bool mm_pkey_is_allocated(struct mm_struct *mm, int pkey) /* * Returns a positive, 5-bit key on success, or -1 on failure. - * Relies on the mmap_sem to protect against concurrency in mm_pkey_alloc() and + * Relies on the mmap_lock to protect against concurrency in mm_pkey_alloc() and * mm_pkey_free(). */ static inline int mm_pkey_alloc(struct mm_struct *mm) @@ -114,9 +92,8 @@ static inline int mm_pkey_alloc(struct mm_struct *mm) u32 all_pkeys_mask = (u32)(~(0x0)); int ret; - if (static_branch_likely(&pkey_disabled)) + if (!mmu_has_feature(MMU_FTR_PKEY)) return -1; - /* * Are we out of pkeys? We must handle this specially because ffz() * behavior is undefined if there are no zeros. @@ -132,7 +109,7 @@ static inline int mm_pkey_alloc(struct mm_struct *mm) static inline int mm_pkey_free(struct mm_struct *mm, int pkey) { - if (static_branch_likely(&pkey_disabled)) + if (!mmu_has_feature(MMU_FTR_PKEY)) return -1; if (!mm_pkey_is_allocated(mm, pkey)) @@ -147,21 +124,13 @@ static inline int mm_pkey_free(struct mm_struct *mm, int pkey) * Try to dedicate one of the protection keys to be used as an * execute-only protection key. */ -extern int __execute_only_pkey(struct mm_struct *mm); -static inline int execute_only_pkey(struct mm_struct *mm) -{ - if (static_branch_likely(&pkey_disabled)) - return -1; - - return __execute_only_pkey(mm); -} - +extern int execute_only_pkey(struct mm_struct *mm); extern int __arch_override_mprotect_pkey(struct vm_area_struct *vma, int prot, int pkey); static inline int arch_override_mprotect_pkey(struct vm_area_struct *vma, int prot, int pkey) { - if (static_branch_likely(&pkey_disabled)) + if (!mmu_has_feature(MMU_FTR_PKEY)) return 0; /* @@ -179,7 +148,7 @@ extern int __arch_set_user_pkey_access(struct task_struct *tsk, int pkey, static inline int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, unsigned long init_val) { - if (static_branch_likely(&pkey_disabled)) + if (!mmu_has_feature(MMU_FTR_PKEY)) return -EINVAL; /* @@ -196,14 +165,8 @@ static inline int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, static inline bool arch_pkeys_enabled(void) { - return !static_branch_likely(&pkey_disabled); + return mmu_has_feature(MMU_FTR_PKEY); } extern void pkey_mm_init(struct mm_struct *mm); -extern bool arch_supports_pkeys(int cap); -extern unsigned int arch_usable_pkeys(void); -extern void thread_pkey_regs_save(struct thread_struct *thread); -extern void thread_pkey_regs_restore(struct thread_struct *new_thread, - struct thread_struct *old_thread); -extern void thread_pkey_regs_init(struct thread_struct *thread); #endif /*_ASM_POWERPC_KEYS_H */ diff --git a/arch/powerpc/include/asm/plpar_wrappers.h b/arch/powerpc/include/asm/plpar_wrappers.h index 4497c8afb573..b3ee44a40c2f 100644 --- a/arch/powerpc/include/asm/plpar_wrappers.h +++ b/arch/powerpc/include/asm/plpar_wrappers.h @@ -6,9 +6,11 @@ #include <linux/string.h> #include <linux/irqflags.h> +#include <linux/delay.h> #include <asm/hvcall.h> #include <asm/paca.h> +#include <asm/lppaca.h> #include <asm/page.h> static inline long poll_pending(void) @@ -28,7 +30,11 @@ static inline void set_cede_latency_hint(u8 latency_hint) static inline long cede_processor(void) { - return plpar_hcall_norets(H_CEDE); + /* + * We cannot call tracepoints inside RCU idle regions which + * means we must not trace H_CEDE. + */ + return plpar_hcall_norets_notrace(H_CEDE); } static inline long extended_cede_processor(unsigned long latency_hint) @@ -39,11 +45,10 @@ static inline long extended_cede_processor(unsigned long latency_hint) set_cede_latency_hint(latency_hint); rc = cede_processor(); -#ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG + /* Ensure that H_CEDE returns with IRQs on */ - if (WARN_ON(!(mfmsr() & MSR_EE))) + if (WARN_ON(IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG) && !(mfmsr() & MSR_EE))) __hard_irq_enable(); -#endif set_cede_latency_hint(old_latency_hint); @@ -312,7 +317,12 @@ static inline long plpar_set_ciabr(unsigned long ciabr) static inline long plpar_set_watchpoint0(unsigned long dawr0, unsigned long dawrx0) { - return plpar_set_mode(0, H_SET_MODE_RESOURCE_SET_DAWR, dawr0, dawrx0); + return plpar_set_mode(0, H_SET_MODE_RESOURCE_SET_DAWR0, dawr0, dawrx0); +} + +static inline long plpar_set_watchpoint1(unsigned long dawr1, unsigned long dawrx1) +{ + return plpar_set_mode(0, H_SET_MODE_RESOURCE_SET_DAWR1, dawr1, dawrx1); } static inline long plpar_signal_sys_reset(long cpu) @@ -334,6 +344,257 @@ static inline long plpar_get_cpu_characteristics(struct h_cpu_char_result *p) return rc; } +static inline long plpar_guest_create(unsigned long flags, unsigned long *guest_id) +{ + unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; + unsigned long token; + long rc; + + token = -1UL; + do { + rc = plpar_hcall(H_GUEST_CREATE, retbuf, flags, token); + if (rc == H_SUCCESS) + *guest_id = retbuf[0]; + + if (rc == H_BUSY) { + token = retbuf[0]; + cond_resched(); + } + + if (H_IS_LONG_BUSY(rc)) { + token = retbuf[0]; + msleep(get_longbusy_msecs(rc)); + rc = H_BUSY; + } + + } while (rc == H_BUSY); + + return rc; +} + +static inline long plpar_guest_create_vcpu(unsigned long flags, + unsigned long guest_id, + unsigned long vcpu_id) +{ + long rc; + + do { + rc = plpar_hcall_norets(H_GUEST_CREATE_VCPU, 0, guest_id, vcpu_id); + + if (rc == H_BUSY) + cond_resched(); + + if (H_IS_LONG_BUSY(rc)) { + msleep(get_longbusy_msecs(rc)); + rc = H_BUSY; + } + + } while (rc == H_BUSY); + + return rc; +} + +static inline long plpar_guest_set_state(unsigned long flags, + unsigned long guest_id, + unsigned long vcpu_id, + unsigned long data_buffer, + unsigned long data_size, + unsigned long *failed_index) +{ + unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; + long rc; + + while (true) { + rc = plpar_hcall(H_GUEST_SET_STATE, retbuf, flags, guest_id, + vcpu_id, data_buffer, data_size); + + if (rc == H_BUSY) { + cpu_relax(); + continue; + } + + if (H_IS_LONG_BUSY(rc)) { + mdelay(get_longbusy_msecs(rc)); + continue; + } + + if (rc == H_INVALID_ELEMENT_ID) + *failed_index = retbuf[0]; + else if (rc == H_INVALID_ELEMENT_SIZE) + *failed_index = retbuf[0]; + else if (rc == H_INVALID_ELEMENT_VALUE) + *failed_index = retbuf[0]; + + break; + } + + return rc; +} + +static inline long plpar_guest_get_state(unsigned long flags, + unsigned long guest_id, + unsigned long vcpu_id, + unsigned long data_buffer, + unsigned long data_size, + unsigned long *failed_index) +{ + unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; + long rc; + + while (true) { + rc = plpar_hcall(H_GUEST_GET_STATE, retbuf, flags, guest_id, + vcpu_id, data_buffer, data_size); + + if (rc == H_BUSY) { + cpu_relax(); + continue; + } + + if (H_IS_LONG_BUSY(rc)) { + mdelay(get_longbusy_msecs(rc)); + continue; + } + + if (rc == H_INVALID_ELEMENT_ID) + *failed_index = retbuf[0]; + else if (rc == H_INVALID_ELEMENT_SIZE) + *failed_index = retbuf[0]; + else if (rc == H_INVALID_ELEMENT_VALUE) + *failed_index = retbuf[0]; + + break; + } + + return rc; +} + +static inline long plpar_guest_run_vcpu(unsigned long flags, unsigned long guest_id, + unsigned long vcpu_id, int *trap, + unsigned long *failed_index) +{ + unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; + long rc; + + rc = plpar_hcall(H_GUEST_RUN_VCPU, retbuf, flags, guest_id, vcpu_id); + if (rc == H_SUCCESS) + *trap = retbuf[0]; + else if (rc == H_INVALID_ELEMENT_ID) + *failed_index = retbuf[0]; + else if (rc == H_INVALID_ELEMENT_SIZE) + *failed_index = retbuf[0]; + else if (rc == H_INVALID_ELEMENT_VALUE) + *failed_index = retbuf[0]; + + return rc; +} + +static inline long plpar_guest_delete(unsigned long flags, u64 guest_id) +{ + long rc; + + do { + rc = plpar_hcall_norets(H_GUEST_DELETE, flags, guest_id); + if (rc == H_BUSY) + cond_resched(); + + if (H_IS_LONG_BUSY(rc)) { + msleep(get_longbusy_msecs(rc)); + rc = H_BUSY; + } + + } while (rc == H_BUSY); + + return rc; +} + +static inline long plpar_guest_set_capabilities(unsigned long flags, + unsigned long capabilities) +{ + unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; + long rc; + + do { + rc = plpar_hcall(H_GUEST_SET_CAPABILITIES, retbuf, flags, capabilities); + if (rc == H_BUSY) + cond_resched(); + + if (H_IS_LONG_BUSY(rc)) { + msleep(get_longbusy_msecs(rc)); + rc = H_BUSY; + } + } while (rc == H_BUSY); + + return rc; +} + +static inline long plpar_guest_get_capabilities(unsigned long flags, + unsigned long *capabilities) +{ + unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; + long rc; + + do { + rc = plpar_hcall(H_GUEST_GET_CAPABILITIES, retbuf, flags); + if (rc == H_BUSY) + cond_resched(); + + if (H_IS_LONG_BUSY(rc)) { + msleep(get_longbusy_msecs(rc)); + rc = H_BUSY; + } + } while (rc == H_BUSY); + + if (rc == H_SUCCESS) + *capabilities = retbuf[0]; + + return rc; +} + +/* + * Wrapper to H_RPT_INVALIDATE hcall that handles return values appropriately + * + * - Returns H_SUCCESS on success + * - For H_BUSY return value, we retry the hcall. + * - For any other hcall failures, attempt a full flush once before + * resorting to BUG(). + * + * Note: This hcall is expected to fail only very rarely. The correct + * error recovery of killing the process/guest will be eventually + * needed. + */ +static inline long pseries_rpt_invalidate(u64 pid, u64 target, u64 type, + u64 page_sizes, u64 start, u64 end) +{ + long rc; + unsigned long all; + + while (true) { + rc = plpar_hcall_norets(H_RPT_INVALIDATE, pid, target, type, + page_sizes, start, end); + if (rc == H_BUSY) { + cpu_relax(); + continue; + } else if (rc == H_SUCCESS) + return rc; + + /* Flush request failed, try with a full flush once */ + if (type & H_RPTI_TYPE_NESTED) + all = H_RPTI_TYPE_NESTED | H_RPTI_TYPE_NESTED_ALL; + else + all = H_RPTI_TYPE_ALL; +retry: + rc = plpar_hcall_norets(H_RPT_INVALIDATE, pid, target, + all, page_sizes, 0, -1UL); + if (rc == H_BUSY) { + cpu_relax(); + goto retry; + } else if (rc == H_SUCCESS) + return rc; + + BUG(); + } +} + #else /* !CONFIG_PPC_PSERIES */ static inline long plpar_set_ciabr(unsigned long ciabr) @@ -346,6 +607,69 @@ static inline long plpar_pte_read_4(unsigned long flags, unsigned long ptex, { return 0; } + +static inline long pseries_rpt_invalidate(u64 pid, u64 target, u64 type, + u64 page_sizes, u64 start, u64 end) +{ + return 0; +} + +static inline long plpar_guest_create_vcpu(unsigned long flags, + unsigned long guest_id, + unsigned long vcpu_id) +{ + return 0; +} + +static inline long plpar_guest_get_state(unsigned long flags, + unsigned long guest_id, + unsigned long vcpu_id, + unsigned long data_buffer, + unsigned long data_size, + unsigned long *failed_index) +{ + return 0; +} + +static inline long plpar_guest_set_state(unsigned long flags, + unsigned long guest_id, + unsigned long vcpu_id, + unsigned long data_buffer, + unsigned long data_size, + unsigned long *failed_index) +{ + return 0; +} + +static inline long plpar_guest_run_vcpu(unsigned long flags, unsigned long guest_id, + unsigned long vcpu_id, int *trap, + unsigned long *failed_index) +{ + return 0; +} + +static inline long plpar_guest_create(unsigned long flags, unsigned long *guest_id) +{ + return 0; +} + +static inline long plpar_guest_delete(unsigned long flags, u64 guest_id) +{ + return 0; +} + +static inline long plpar_guest_get_capabilities(unsigned long flags, + unsigned long *capabilities) +{ + return 0; +} + +static inline long plpar_guest_set_capabilities(unsigned long flags, + unsigned long capabilities) +{ + return 0; +} + #endif /* CONFIG_PPC_PSERIES */ #endif /* _ASM_POWERPC_PLPAR_WRAPPERS_H */ diff --git a/arch/powerpc/include/asm/plpks.h b/arch/powerpc/include/asm/plpks.h new file mode 100644 index 000000000000..23b77027c916 --- /dev/null +++ b/arch/powerpc/include/asm/plpks.h @@ -0,0 +1,195 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2022 IBM Corporation + * Author: Nayna Jain <nayna@linux.ibm.com> + * + * Platform keystore for pseries LPAR(PLPKS). + */ + +#ifndef _ASM_POWERPC_PLPKS_H +#define _ASM_POWERPC_PLPKS_H + +#ifdef CONFIG_PSERIES_PLPKS + +#include <linux/types.h> +#include <linux/list.h> + +// Object policy flags from supported_policies +#define PLPKS_OSSECBOOTAUDIT PPC_BIT32(1) // OS secure boot must be audit/enforce +#define PLPKS_OSSECBOOTENFORCE PPC_BIT32(2) // OS secure boot must be enforce +#define PLPKS_PWSET PPC_BIT32(3) // No access without password set +#define PLPKS_WORLDREADABLE PPC_BIT32(4) // Readable without authentication +#define PLPKS_IMMUTABLE PPC_BIT32(5) // Once written, object cannot be removed +#define PLPKS_TRANSIENT PPC_BIT32(6) // Object does not persist through reboot +#define PLPKS_SIGNEDUPDATE PPC_BIT32(7) // Object can only be modified by signed updates +#define PLPKS_HVPROVISIONED PPC_BIT32(28) // Hypervisor has provisioned this object + +// Signature algorithm flags from signed_update_algorithms +#define PLPKS_ALG_RSA2048 PPC_BIT(0) +#define PLPKS_ALG_RSA4096 PPC_BIT(1) + +// Object label OS metadata flags +#define PLPKS_VAR_LINUX 0x02 +#define PLPKS_VAR_COMMON 0x04 + +// Flags for which consumer owns an object is owned by +#define PLPKS_FW_OWNER 0x1 +#define PLPKS_BOOTLOADER_OWNER 0x2 +#define PLPKS_OS_OWNER 0x3 + +// Flags for label metadata fields +#define PLPKS_LABEL_VERSION 0 +#define PLPKS_MAX_LABEL_ATTR_SIZE 16 +#define PLPKS_MAX_NAME_SIZE 239 +#define PLPKS_MAX_DATA_SIZE 4000 + +// Timeouts for PLPKS operations +#define PLPKS_MAX_TIMEOUT 5000 // msec +#define PLPKS_FLUSH_SLEEP 10 // msec +#define PLPKS_FLUSH_SLEEP_RANGE 400 + +struct plpks_var { + char *component; + u8 *name; + u8 *data; + u32 policy; + u16 namelen; + u16 datalen; + u8 os; +}; + +struct plpks_var_name { + u8 *name; + u16 namelen; +}; + +struct plpks_var_name_list { + u32 varcount; + struct plpks_var_name varlist[]; +}; + +/** + * Updates the authenticated variable. It expects NULL as the component. + */ +int plpks_signed_update_var(struct plpks_var *var, u64 flags); + +/** + * Writes the specified var and its data to PKS. + * Any caller of PKS driver should present a valid component type for + * their variable. + */ +int plpks_write_var(struct plpks_var var); + +/** + * Removes the specified var and its data from PKS. + */ +int plpks_remove_var(char *component, u8 varos, + struct plpks_var_name vname); + +/** + * Returns the data for the specified os variable. + * + * Caller must allocate a buffer in var->data with length in var->datalen. + * If no buffer is provided, var->datalen will be populated with the object's + * size. + */ +int plpks_read_os_var(struct plpks_var *var); + +/** + * Returns the data for the specified firmware variable. + * + * Caller must allocate a buffer in var->data with length in var->datalen. + * If no buffer is provided, var->datalen will be populated with the object's + * size. + */ +int plpks_read_fw_var(struct plpks_var *var); + +/** + * Returns the data for the specified bootloader variable. + * + * Caller must allocate a buffer in var->data with length in var->datalen. + * If no buffer is provided, var->datalen will be populated with the object's + * size. + */ +int plpks_read_bootloader_var(struct plpks_var *var); + +/** + * Returns if PKS is available on this LPAR. + */ +bool plpks_is_available(void); + +/** + * Returns version of the Platform KeyStore. + */ +u8 plpks_get_version(void); + +/** + * Returns hypervisor storage overhead per object, not including the size of + * the object or label. Only valid for config version >= 2 + */ +u16 plpks_get_objoverhead(void); + +/** + * Returns maximum password size. Must be >= 32 bytes + */ +u16 plpks_get_maxpwsize(void); + +/** + * Returns maximum object size supported by Platform KeyStore. + */ +u16 plpks_get_maxobjectsize(void); + +/** + * Returns maximum object label size supported by Platform KeyStore. + */ +u16 plpks_get_maxobjectlabelsize(void); + +/** + * Returns total size of the configured Platform KeyStore. + */ +u32 plpks_get_totalsize(void); + +/** + * Returns used space from the total size of the Platform KeyStore. + */ +u32 plpks_get_usedspace(void); + +/** + * Returns bitmask of policies supported by the hypervisor. + */ +u32 plpks_get_supportedpolicies(void); + +/** + * Returns maximum byte size of a single object supported by the hypervisor. + * Only valid for config version >= 3 + */ +u32 plpks_get_maxlargeobjectsize(void); + +/** + * Returns bitmask of signature algorithms supported for signed updates. + * Only valid for config version >= 3 + */ +u64 plpks_get_signedupdatealgorithms(void); + +/** + * Returns the length of the PLPKS password in bytes. + */ +u16 plpks_get_passwordlen(void); + +/** + * Called in early init to retrieve and clear the PLPKS password from the DT. + */ +void plpks_early_init_devtree(void); + +/** + * Populates the FDT with the PLPKS password to prepare for kexec. + */ +int plpks_populate_fdt(void *fdt); +#else // CONFIG_PSERIES_PLPKS +static inline bool plpks_is_available(void) { return false; } +static inline u16 plpks_get_passwordlen(void) { BUILD_BUG(); } +static inline void plpks_early_init_devtree(void) { } +static inline int plpks_populate_fdt(void *fdt) { BUILD_BUG(); } +#endif // CONFIG_PSERIES_PLPKS + +#endif // _ASM_POWERPC_PLPKS_H diff --git a/arch/powerpc/include/asm/pmac_feature.h b/arch/powerpc/include/asm/pmac_feature.h index e08e829261b6..2495866f2e97 100644 --- a/arch/powerpc/include/asm/pmac_feature.h +++ b/arch/powerpc/include/asm/pmac_feature.h @@ -401,5 +401,17 @@ extern u32 __iomem *uninorth_base; */ extern int pmac_get_uninorth_variant(void); +/* + * Power macintoshes have either a CUDA, PMU or SMU controlling + * system reset, power, NVRAM, RTC. + */ +typedef enum sys_ctrler_kind { + SYS_CTRLER_UNKNOWN = 0, + SYS_CTRLER_CUDA = 1, + SYS_CTRLER_PMU = 2, + SYS_CTRLER_SMU = 3, +} sys_ctrler_t; +extern sys_ctrler_t sys_ctrler; + #endif /* __ASM_POWERPC_PMAC_FEATURE_H */ #endif /* __KERNEL__ */ diff --git a/arch/powerpc/include/asm/pmc.h b/arch/powerpc/include/asm/pmc.h index c6bbe9778d3c..3c09109e708e 100644 --- a/arch/powerpc/include/asm/pmc.h +++ b/arch/powerpc/include/asm/pmc.h @@ -34,6 +34,13 @@ static inline void ppc_set_pmu_inuse(int inuse) #endif } +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE +static inline int ppc_get_pmu_inuse(void) +{ + return get_paca()->pmcregs_in_use; +} +#endif + extern void power4_enable_pmcs(void); #else /* CONFIG_PPC64 */ diff --git a/arch/powerpc/include/asm/pnv-ocxl.h b/arch/powerpc/include/asm/pnv-ocxl.h index 7de82647e761..9acd1fbf1197 100644 --- a/arch/powerpc/include/asm/pnv-ocxl.h +++ b/arch/powerpc/include/asm/pnv-ocxl.h @@ -3,34 +3,83 @@ #ifndef _ASM_PNV_OCXL_H #define _ASM_PNV_OCXL_H +#include <linux/bitfield.h> #include <linux/pci.h> #define PNV_OCXL_TL_MAX_TEMPLATE 63 #define PNV_OCXL_TL_BITS_PER_RATE 4 #define PNV_OCXL_TL_RATE_BUF_SIZE ((PNV_OCXL_TL_MAX_TEMPLATE+1) * PNV_OCXL_TL_BITS_PER_RATE / 8) -extern int pnv_ocxl_get_actag(struct pci_dev *dev, u16 *base, u16 *enabled, - u16 *supported); -extern int pnv_ocxl_get_pasid_count(struct pci_dev *dev, int *count); +#define PNV_OCXL_ATSD_TIMEOUT 1 -extern int pnv_ocxl_get_tl_cap(struct pci_dev *dev, long *cap, - char *rate_buf, int rate_buf_size); -extern int pnv_ocxl_set_tl_conf(struct pci_dev *dev, long cap, - uint64_t rate_buf_phys, int rate_buf_size); +/* TLB Management Instructions */ +#define PNV_OCXL_ATSD_LNCH 0x00 +/* Radix Invalidate */ +#define PNV_OCXL_ATSD_LNCH_R PPC_BIT(0) +/* Radix Invalidation Control + * 0b00 Just invalidate TLB. + * 0b01 Invalidate just Page Walk Cache. + * 0b10 Invalidate TLB, Page Walk Cache, and any + * caching of Partition and Process Table Entries. + */ +#define PNV_OCXL_ATSD_LNCH_RIC PPC_BITMASK(1, 2) +/* Number and Page Size of translations to be invalidated */ +#define PNV_OCXL_ATSD_LNCH_LP PPC_BITMASK(3, 10) +/* Invalidation Criteria + * 0b00 Invalidate just the target VA. + * 0b01 Invalidate matching PID. + */ +#define PNV_OCXL_ATSD_LNCH_IS PPC_BITMASK(11, 12) +/* 0b1: Process Scope, 0b0: Partition Scope */ +#define PNV_OCXL_ATSD_LNCH_PRS PPC_BIT(13) +/* Invalidation Flag */ +#define PNV_OCXL_ATSD_LNCH_B PPC_BIT(14) +/* Actual Page Size to be invalidated + * 000 4KB + * 101 64KB + * 001 2MB + * 010 1GB + */ +#define PNV_OCXL_ATSD_LNCH_AP PPC_BITMASK(15, 17) +/* Defines the large page select + * L=0b0 for 4KB pages + * L=0b1 for large pages) + */ +#define PNV_OCXL_ATSD_LNCH_L PPC_BIT(18) +/* Process ID */ +#define PNV_OCXL_ATSD_LNCH_PID PPC_BITMASK(19, 38) +/* NoFlush – Assumed to be 0b0 */ +#define PNV_OCXL_ATSD_LNCH_F PPC_BIT(39) +#define PNV_OCXL_ATSD_LNCH_OCAPI_SLBI PPC_BIT(40) +#define PNV_OCXL_ATSD_LNCH_OCAPI_SINGLETON PPC_BIT(41) +#define PNV_OCXL_ATSD_AVA 0x08 +#define PNV_OCXL_ATSD_AVA_AVA PPC_BITMASK(0, 51) +#define PNV_OCXL_ATSD_STAT 0x10 + +int pnv_ocxl_get_actag(struct pci_dev *dev, u16 *base, u16 *enabled, u16 *supported); +int pnv_ocxl_get_pasid_count(struct pci_dev *dev, int *count); -extern int pnv_ocxl_get_xsl_irq(struct pci_dev *dev, int *hwirq); -extern void pnv_ocxl_unmap_xsl_regs(void __iomem *dsisr, void __iomem *dar, - void __iomem *tfc, void __iomem *pe_handle); -extern int pnv_ocxl_map_xsl_regs(struct pci_dev *dev, void __iomem **dsisr, - void __iomem **dar, void __iomem **tfc, - void __iomem **pe_handle); +int pnv_ocxl_get_tl_cap(struct pci_dev *dev, long *cap, + char *rate_buf, int rate_buf_size); +int pnv_ocxl_set_tl_conf(struct pci_dev *dev, long cap, + uint64_t rate_buf_phys, int rate_buf_size); -extern int pnv_ocxl_spa_setup(struct pci_dev *dev, void *spa_mem, int PE_mask, - void **platform_data); -extern void pnv_ocxl_spa_release(void *platform_data); -extern int pnv_ocxl_spa_remove_pe_from_cache(void *platform_data, int pe_handle); +int pnv_ocxl_get_xsl_irq(struct pci_dev *dev, int *hwirq); +void pnv_ocxl_unmap_xsl_regs(void __iomem *dsisr, void __iomem *dar, + void __iomem *tfc, void __iomem *pe_handle); +int pnv_ocxl_map_xsl_regs(struct pci_dev *dev, void __iomem **dsisr, + void __iomem **dar, void __iomem **tfc, + void __iomem **pe_handle); -extern int pnv_ocxl_alloc_xive_irq(u32 *irq, u64 *trigger_addr); -extern void pnv_ocxl_free_xive_irq(u32 irq); +int pnv_ocxl_spa_setup(struct pci_dev *dev, void *spa_mem, int PE_mask, void **platform_data); +void pnv_ocxl_spa_release(void *platform_data); +int pnv_ocxl_spa_remove_pe_from_cache(void *platform_data, int pe_handle); +int pnv_ocxl_map_lpar(struct pci_dev *dev, uint64_t lparid, + uint64_t lpcr, void __iomem **arva); +void pnv_ocxl_unmap_lpar(void __iomem *arva); +void pnv_ocxl_tlb_invalidate(void __iomem *arva, + unsigned long pid, + unsigned long addr, + unsigned long page_size); #endif /* _ASM_PNV_OCXL_H */ diff --git a/arch/powerpc/include/asm/pnv-pci.h b/arch/powerpc/include/asm/pnv-pci.h index edcb1fc50aeb..8afc92860dbb 100644 --- a/arch/powerpc/include/asm/pnv-pci.h +++ b/arch/powerpc/include/asm/pnv-pci.h @@ -9,12 +9,14 @@ #include <linux/pci.h> #include <linux/pci_hotplug.h> #include <linux/irq.h> +#include <linux/of.h> #include <misc/cxl-base.h> #include <asm/opal-api.h> #define PCI_SLOT_ID_PREFIX (1UL << 63) #define PCI_SLOT_ID(phb_id, bdfn) \ (PCI_SLOT_ID_PREFIX | ((uint64_t)(bdfn) << 16) | (phb_id)) +#define PCI_PHB_SLOT_ID(phb_id) (phb_id) extern int pnv_pci_get_slot_id(struct device_node *np, uint64_t *id); extern int pnv_pci_get_device_tree(uint32_t phandle, void *buf, uint64_t len); @@ -32,7 +34,7 @@ int pnv_cxl_alloc_hwirqs(struct pci_dev *dev, int num); void pnv_cxl_release_hwirqs(struct pci_dev *dev, int hwirq, int num); int pnv_cxl_get_irq_count(struct pci_dev *dev); struct device_node *pnv_pci_get_phb_node(struct pci_dev *dev); -int64_t pnv_opal_pci_msi_eoi(struct irq_chip *chip, unsigned int hw_irq); +int64_t pnv_opal_pci_msi_eoi(struct irq_data *d); bool is_pnv_opal_msi(struct irq_chip *chip); #ifdef CONFIG_CXL_BASE diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h index c1df75edde44..005601243dda 100644 --- a/arch/powerpc/include/asm/ppc-opcode.h +++ b/arch/powerpc/include/asm/ppc-opcode.h @@ -76,9 +76,111 @@ #define __REGA0_R30 30 #define __REGA0_R31 31 +/* For use with PPC_RAW_() macros */ +#define _R0 0 +#define _R1 1 +#define _R2 2 +#define _R3 3 +#define _R4 4 +#define _R5 5 +#define _R6 6 +#define _R7 7 +#define _R8 8 +#define _R9 9 +#define _R10 10 +#define _R11 11 +#define _R12 12 +#define _R13 13 +#define _R14 14 +#define _R15 15 +#define _R16 16 +#define _R17 17 +#define _R18 18 +#define _R19 19 +#define _R20 20 +#define _R21 21 +#define _R22 22 +#define _R23 23 +#define _R24 24 +#define _R25 25 +#define _R26 26 +#define _R27 27 +#define _R28 28 +#define _R29 29 +#define _R30 30 +#define _R31 31 + +#define IMM_L(i) ((uintptr_t)(i) & 0xffff) +#define IMM_DS(i) ((uintptr_t)(i) & 0xfffc) +#define IMM_DQ(i) ((uintptr_t)(i) & 0xfff0) +#define IMM_D0(i) (((uintptr_t)(i) >> 16) & 0x3ffff) +#define IMM_D1(i) IMM_L(i) + +/* + * 16-bit immediate helper macros: HA() is for use with sign-extending instrs + * (e.g. LD, ADDI). If the bottom 16 bits is "-ve", add another bit into the + * top half to negate the effect (i.e. 0xffff + 1 = 0x(1)0000). + * + * XXX: should these mask out possible sign bits? + */ +#define IMM_H(i) ((uintptr_t)(i)>>16) +#define IMM_HA(i) (((uintptr_t)(i)>>16) + \ + (((uintptr_t)(i) & 0x8000) >> 15)) + +/* + * 18-bit immediate helper for prefix 18-bit upper immediate si0 field. + */ +#define IMM_H18(i) (((uintptr_t)(i)>>16) & 0x3ffff) + + /* opcode and xopcode for instructions */ -#define OP_TRAP 3 -#define OP_TRAP_64 2 +#define OP_PREFIX 1 +#define OP_TRAP_64 2 +#define OP_TRAP 3 +#define OP_SC 17 +#define OP_19 19 +#define OP_31 31 +#define OP_LWZ 32 +#define OP_LWZU 33 +#define OP_LBZ 34 +#define OP_LBZU 35 +#define OP_STW 36 +#define OP_STWU 37 +#define OP_STB 38 +#define OP_STBU 39 +#define OP_LHZ 40 +#define OP_LHZU 41 +#define OP_LHA 42 +#define OP_LHAU 43 +#define OP_STH 44 +#define OP_STHU 45 +#define OP_LMW 46 +#define OP_STMW 47 +#define OP_LFS 48 +#define OP_LFSU 49 +#define OP_LFD 50 +#define OP_LFDU 51 +#define OP_STFS 52 +#define OP_STFSU 53 +#define OP_STFD 54 +#define OP_STFDU 55 +#define OP_LQ 56 +#define OP_LD 58 +#define OP_STD 62 + +#define OP_19_XOP_RFID 18 +#define OP_19_XOP_RFMCI 38 +#define OP_19_XOP_RFDI 39 +#define OP_19_XOP_RFI 50 +#define OP_19_XOP_RFCI 51 +#define OP_19_XOP_RFSCV 82 +#define OP_19_XOP_HRFID 274 +#define OP_19_XOP_URFID 306 +#define OP_19_XOP_STOP 370 +#define OP_19_XOP_DOZE 402 +#define OP_19_XOP_NAP 434 +#define OP_19_XOP_SLEEP 466 +#define OP_19_XOP_RVWINKLE 498 #define OP_31_XOP_TRAP 4 #define OP_31_XOP_LDX 21 @@ -100,6 +202,8 @@ #define OP_31_XOP_LHZUX 311 #define OP_31_XOP_MSGSNDP 142 #define OP_31_XOP_MSGCLRP 174 +#define OP_31_XOP_MTMSR 146 +#define OP_31_XOP_MTMSRD 178 #define OP_31_XOP_TLBIE 306 #define OP_31_XOP_MFSPR 339 #define OP_31_XOP_LWAX 341 @@ -118,6 +222,7 @@ #define OP_31_XOP_STFSX 663 #define OP_31_XOP_STFSUX 695 #define OP_31_XOP_STFDX 727 +#define OP_31_XOP_HASHCHK 754 #define OP_31_XOP_STFDUX 759 #define OP_31_XOP_LHBRX 790 #define OP_31_XOP_LFIWAX 855 @@ -158,91 +263,30 @@ /* VMX Vector Store Instructions */ #define OP_31_XOP_STVX 231 -#define OP_31 31 -#define OP_LWZ 32 -#define OP_STFS 52 -#define OP_STFSU 53 -#define OP_STFD 54 -#define OP_STFDU 55 -#define OP_LD 58 -#define OP_LWZU 33 -#define OP_LBZ 34 -#define OP_LBZU 35 -#define OP_STW 36 -#define OP_STWU 37 -#define OP_STD 62 -#define OP_STB 38 -#define OP_STBU 39 -#define OP_LHZ 40 -#define OP_LHZU 41 -#define OP_LHA 42 -#define OP_LHAU 43 -#define OP_STH 44 -#define OP_STHU 45 -#define OP_LMW 46 -#define OP_STMW 47 -#define OP_LFS 48 -#define OP_LFSU 49 -#define OP_LFD 50 -#define OP_LFDU 51 -#define OP_STFS 52 -#define OP_STFSU 53 -#define OP_STFD 54 -#define OP_STFDU 55 -#define OP_LQ 56 - /* sorted alphabetically */ -#define PPC_INST_BHRBE 0x7c00025c -#define PPC_INST_CLRBHRB 0x7c00035c +#define PPC_INST_BCCTR_FLUSH 0x4c400420 #define PPC_INST_COPY 0x7c20060c -#define PPC_INST_CP_ABORT 0x7c00068c -#define PPC_INST_DARN 0x7c0005e6 #define PPC_INST_DCBA 0x7c0005ec #define PPC_INST_DCBA_MASK 0xfc0007fe -#define PPC_INST_DCBAL 0x7c2005ec -#define PPC_INST_DCBZL 0x7c2007ec -#define PPC_INST_ICBT 0x7c00002c -#define PPC_INST_ICSWX 0x7c00032d -#define PPC_INST_ICSWEPX 0x7c00076d +#define PPC_INST_DSSALL 0x7e00066c #define PPC_INST_ISEL 0x7c00001e #define PPC_INST_ISEL_MASK 0xfc00003e -#define PPC_INST_LDARX 0x7c0000a8 -#define PPC_INST_STDCX 0x7c0001ad -#define PPC_INST_LQARX 0x7c000228 -#define PPC_INST_STQCX 0x7c00016d #define PPC_INST_LSWI 0x7c0004aa #define PPC_INST_LSWX 0x7c00042a -#define PPC_INST_LWARX 0x7c000028 -#define PPC_INST_STWCX 0x7c00012d #define PPC_INST_LWSYNC 0x7c2004ac #define PPC_INST_SYNC 0x7c0004ac #define PPC_INST_SYNC_MASK 0xfc0007fe -#define PPC_INST_ISYNC 0x4c00012c -#define PPC_INST_LXVD2X 0x7c000698 #define PPC_INST_MCRXR 0x7c000400 #define PPC_INST_MCRXR_MASK 0xfc0007fe #define PPC_INST_MFSPR_PVR 0x7c1f42a6 #define PPC_INST_MFSPR_PVR_MASK 0xfc1ffffe -#define PPC_INST_MFTMR 0x7c0002dc -#define PPC_INST_MSGSND 0x7c00019c -#define PPC_INST_MSGCLR 0x7c0001dc -#define PPC_INST_MSGSYNC 0x7c0006ec -#define PPC_INST_MSGSNDP 0x7c00011c -#define PPC_INST_MSGCLRP 0x7c00015c #define PPC_INST_MTMSRD 0x7c000164 -#define PPC_INST_MTTMR 0x7c0003dc -#define PPC_INST_NOP 0x60000000 #define PPC_INST_PASTE 0x7c20070d +#define PPC_INST_PASTE_MASK 0xfc2007ff #define PPC_INST_POPCNTB 0x7c0000f4 #define PPC_INST_POPCNTB_MASK 0xfc0007fe -#define PPC_INST_POPCNTD 0x7c0003f4 -#define PPC_INST_POPCNTW 0x7c0002f4 #define PPC_INST_RFEBB 0x4c000124 -#define PPC_INST_RFCI 0x4c000066 -#define PPC_INST_RFDI 0x4c00004e #define PPC_INST_RFID 0x4c000024 -#define PPC_INST_RFMCI 0x4c00004c -#define PPC_INST_MFSPR 0x7c0002a6 #define PPC_INST_MFSPR_DSCR 0x7c1102a6 #define PPC_INST_MFSPR_DSCR_MASK 0xfc1ffffe #define PPC_INST_MTSPR_DSCR 0x7c1103a6 @@ -251,131 +295,28 @@ #define PPC_INST_MFSPR_DSCR_USER_MASK 0xfc1ffffe #define PPC_INST_MTSPR_DSCR_USER 0x7c0303a6 #define PPC_INST_MTSPR_DSCR_USER_MASK 0xfc1ffffe -#define PPC_INST_MFVSRD 0x7c000066 -#define PPC_INST_MTVSRD 0x7c000166 -#define PPC_INST_SC 0x44000002 -#define PPC_INST_SLBFEE 0x7c0007a7 -#define PPC_INST_SLBIA 0x7c0003e4 - #define PPC_INST_STRING 0x7c00042a #define PPC_INST_STRING_MASK 0xfc0007fe #define PPC_INST_STRING_GEN_MASK 0xfc00067e - #define PPC_INST_STSWI 0x7c0005aa #define PPC_INST_STSWX 0x7c00052a -#define PPC_INST_STXVD2X 0x7c000798 -#define PPC_INST_TLBIE 0x7c000264 -#define PPC_INST_TLBIEL 0x7c000224 -#define PPC_INST_TLBILX 0x7c000024 -#define PPC_INST_WAIT 0x7c00007c -#define PPC_INST_TLBIVAX 0x7c000624 -#define PPC_INST_TLBSRX_DOT 0x7c0006a5 -#define PPC_INST_VPMSUMW 0x10000488 -#define PPC_INST_VPMSUMD 0x100004c8 -#define PPC_INST_VPERMXOR 0x1000002d -#define PPC_INST_XXLOR 0xf0000490 -#define PPC_INST_XXSWAPD 0xf0000250 -#define PPC_INST_XVCPSGNDP 0xf0000780 #define PPC_INST_TRECHKPT 0x7c0007dd #define PPC_INST_TRECLAIM 0x7c00075d -#define PPC_INST_TABORT 0x7c00071d #define PPC_INST_TSR 0x7c0005dd - -#define PPC_INST_NAP 0x4c000364 -#define PPC_INST_SLEEP 0x4c0003a4 -#define PPC_INST_WINKLE 0x4c0003e4 - -#define PPC_INST_STOP 0x4c0002e4 - -/* A2 specific instructions */ -#define PPC_INST_ERATWE 0x7c0001a6 -#define PPC_INST_ERATRE 0x7c000166 -#define PPC_INST_ERATILX 0x7c000066 -#define PPC_INST_ERATIVAX 0x7c000666 -#define PPC_INST_ERATSX 0x7c000126 -#define PPC_INST_ERATSX_DOT 0x7c000127 - -/* Misc instructions for BPF compiler */ -#define PPC_INST_LBZ 0x88000000 -#define PPC_INST_LD 0xe8000000 -#define PPC_INST_LDX 0x7c00002a -#define PPC_INST_LHZ 0xa0000000 -#define PPC_INST_LWZ 0x80000000 -#define PPC_INST_LHBRX 0x7c00062c -#define PPC_INST_LDBRX 0x7c000428 -#define PPC_INST_STB 0x98000000 -#define PPC_INST_STH 0xb0000000 -#define PPC_INST_STD 0xf8000000 -#define PPC_INST_STDX 0x7c00012a -#define PPC_INST_STDU 0xf8000001 -#define PPC_INST_STW 0x90000000 -#define PPC_INST_STWU 0x94000000 -#define PPC_INST_MFLR 0x7c0802a6 -#define PPC_INST_MTLR 0x7c0803a6 -#define PPC_INST_MTCTR 0x7c0903a6 -#define PPC_INST_CMPWI 0x2c000000 -#define PPC_INST_CMPDI 0x2c200000 -#define PPC_INST_CMPW 0x7c000000 -#define PPC_INST_CMPD 0x7c200000 -#define PPC_INST_CMPLW 0x7c000040 -#define PPC_INST_CMPLD 0x7c200040 -#define PPC_INST_CMPLWI 0x28000000 -#define PPC_INST_CMPLDI 0x28200000 -#define PPC_INST_ADDI 0x38000000 -#define PPC_INST_ADDIS 0x3c000000 -#define PPC_INST_ADD 0x7c000214 -#define PPC_INST_ADDC 0x7c000014 -#define PPC_INST_SUB 0x7c000050 -#define PPC_INST_BLR 0x4e800020 -#define PPC_INST_BLRL 0x4e800021 -#define PPC_INST_BCTR 0x4e800420 -#define PPC_INST_MULLD 0x7c0001d2 -#define PPC_INST_MULLW 0x7c0001d6 -#define PPC_INST_MULHWU 0x7c000016 -#define PPC_INST_MULLI 0x1c000000 -#define PPC_INST_MADDHD 0x10000030 -#define PPC_INST_MADDHDU 0x10000031 -#define PPC_INST_MADDLD 0x10000033 -#define PPC_INST_DIVWU 0x7c000396 -#define PPC_INST_DIVD 0x7c0003d2 -#define PPC_INST_DIVDU 0x7c000392 -#define PPC_INST_RLWINM 0x54000000 -#define PPC_INST_RLWINM_DOT 0x54000001 -#define PPC_INST_RLWIMI 0x50000000 -#define PPC_INST_RLDICL 0x78000000 -#define PPC_INST_RLDICR 0x78000004 -#define PPC_INST_SLW 0x7c000030 -#define PPC_INST_SLD 0x7c000036 -#define PPC_INST_SRW 0x7c000430 -#define PPC_INST_SRAW 0x7c000630 -#define PPC_INST_SRAWI 0x7c000670 -#define PPC_INST_SRD 0x7c000436 -#define PPC_INST_SRAD 0x7c000634 -#define PPC_INST_SRADI 0x7c000674 -#define PPC_INST_AND 0x7c000038 -#define PPC_INST_ANDDOT 0x7c000039 -#define PPC_INST_OR 0x7c000378 -#define PPC_INST_XOR 0x7c000278 -#define PPC_INST_ANDI 0x70000000 -#define PPC_INST_ORI 0x60000000 -#define PPC_INST_ORIS 0x64000000 -#define PPC_INST_XORI 0x68000000 -#define PPC_INST_XORIS 0x6c000000 -#define PPC_INST_NEG 0x7c0000d0 -#define PPC_INST_EXTSW 0x7c0007b4 -#define PPC_INST_BRANCH 0x48000000 #define PPC_INST_BRANCH_COND 0x40800000 -#define PPC_INST_LBZCIX 0x7c0006aa -#define PPC_INST_STBCIX 0x7c0007aa -#define PPC_INST_LWZX 0x7c00002e -#define PPC_INST_LFSX 0x7c00042e -#define PPC_INST_STFSX 0x7c00052e -#define PPC_INST_LFDX 0x7c0004ae -#define PPC_INST_STFDX 0x7c0005ae -#define PPC_INST_LVX 0x7c0000ce -#define PPC_INST_STVX 0x7c0001ce -#define PPC_INST_VCMPEQUD 0x100000c7 -#define PPC_INST_VCMPEQUB 0x10000006 + +/* Prefixes */ +#define PPC_INST_LFS 0xc0000000 +#define PPC_INST_STFS 0xd0000000 +#define PPC_INST_LFD 0xc8000000 +#define PPC_INST_STFD 0xd8000000 +#define PPC_PREFIX_MLS 0x06000000 +#define PPC_PREFIX_8LS 0x04000000 + +/* Prefixed instructions */ +#define PPC_INST_PADDI 0x38000000 +#define PPC_INST_PLD 0xe4000000 +#define PPC_INST_PSTD 0xf4000000 /* macros to insert fields into opcodes */ #define ___PPC_RA(a) (((a) & 0x1f) << 16) @@ -395,7 +336,10 @@ #define __PPC_XB(b) ((((b) & 0x1f) << 11) | (((b) & 0x20) >> 4)) #define __PPC_XS(s) ((((s) & 0x1f) << 21) | (((s) & 0x20) >> 5)) #define __PPC_XT(s) __PPC_XS(s) +#define __PPC_XSP(s) ((((s) & 0x1e) | (((s) >> 5) & 0x1)) << 21) +#define __PPC_XTP(s) __PPC_XSP(s) #define __PPC_T_TLB(t) (((t) & 0x3) << 21) +#define __PPC_PL(p) (((p) & 0x3) << 16) #define __PPC_WC(w) (((w) & 0x3) << 21) #define __PPC_WS(w) (((w) & 0x1f) << 11) #define __PPC_SH(s) __PPC_WS(s) @@ -408,6 +352,8 @@ #define __PPC_CT(t) (((t) & 0x0f) << 21) #define __PPC_SPR(r) ((((r) & 0x1f) << 16) | ((((r) >> 5) & 0x1f) << 11)) #define __PPC_RC21 (0x1 << 10) +#define __PPC_PRFX_R(r) (((r) & 0x1) << 20) +#define __PPC_EH(eh) (((eh) & 0x1) << 0) /* * Both low and high 16 bits are added as SIGNED additions, so if low 16 bits @@ -417,186 +363,326 @@ #define PPC_LO(v) ((v) & 0xffff) #define PPC_HI(v) (((v) >> 16) & 0xffff) #define PPC_HA(v) PPC_HI((v) + 0x8000) +#define PPC_HIGHER(v) (((v) >> 32) & 0xffff) +#define PPC_HIGHEST(v) (((v) >> 48) & 0xffff) + +/* LI Field */ +#define PPC_LI_MASK 0x03fffffc +#define PPC_LI(v) ((v) & PPC_LI_MASK) + +/* Base instruction encoding */ +#define PPC_RAW_CP_ABORT (0x7c00068c) +#define PPC_RAW_COPY(a, b) (PPC_INST_COPY | ___PPC_RA(a) | ___PPC_RB(b)) +#define PPC_RAW_DARN(t, l) (0x7c0005e6 | ___PPC_RT(t) | (((l) & 0x3) << 16)) +#define PPC_RAW_DCBAL(a, b) (0x7c2005ec | __PPC_RA(a) | __PPC_RB(b)) +#define PPC_RAW_DCBZL(a, b) (0x7c2007ec | __PPC_RA(a) | __PPC_RB(b)) +#define PPC_RAW_LQARX(t, a, b, eh) (0x7c000228 | ___PPC_RT(t) | ___PPC_RA(a) | ___PPC_RB(b) | __PPC_EH(eh)) +#define PPC_RAW_LDARX(t, a, b, eh) (0x7c0000a8 | ___PPC_RT(t) | ___PPC_RA(a) | ___PPC_RB(b) | __PPC_EH(eh)) +#define PPC_RAW_LWARX(t, a, b, eh) (0x7c000028 | ___PPC_RT(t) | ___PPC_RA(a) | ___PPC_RB(b) | __PPC_EH(eh)) +#define PPC_RAW_PHWSYNC (0x7c8004ac) +#define PPC_RAW_PLWSYNC (0x7ca004ac) +#define PPC_RAW_STQCX(t, a, b) (0x7c00016d | ___PPC_RT(t) | ___PPC_RA(a) | ___PPC_RB(b)) +#define PPC_RAW_MADDHD(t, a, b, c) (0x10000030 | ___PPC_RT(t) | ___PPC_RA(a) | ___PPC_RB(b) | ___PPC_RC(c)) +#define PPC_RAW_MADDHDU(t, a, b, c) (0x10000031 | ___PPC_RT(t) | ___PPC_RA(a) | ___PPC_RB(b) | ___PPC_RC(c)) +#define PPC_RAW_MADDLD(t, a, b, c) (0x10000033 | ___PPC_RT(t) | ___PPC_RA(a) | ___PPC_RB(b) | ___PPC_RC(c)) +#define PPC_RAW_MSGSND(b) (0x7c00019c | ___PPC_RB(b)) +#define PPC_RAW_MSGSYNC (0x7c0006ec) +#define PPC_RAW_MSGCLR(b) (0x7c0001dc | ___PPC_RB(b)) +#define PPC_RAW_MSGSNDP(b) (0x7c00011c | ___PPC_RB(b)) +#define PPC_RAW_MSGCLRP(b) (0x7c00015c | ___PPC_RB(b)) +#define PPC_RAW_PASTE(a, b) (0x7c20070d | ___PPC_RA(a) | ___PPC_RB(b)) +#define PPC_RAW_POPCNTB(a, s) (PPC_INST_POPCNTB | __PPC_RA(a) | __PPC_RS(s)) +#define PPC_RAW_POPCNTD(a, s) (0x7c0003f4 | __PPC_RA(a) | __PPC_RS(s)) +#define PPC_RAW_POPCNTW(a, s) (0x7c0002f4 | __PPC_RA(a) | __PPC_RS(s)) +#define PPC_RAW_RFCI (0x4c000066) +#define PPC_RAW_RFDI (0x4c00004e) +#define PPC_RAW_RFMCI (0x4c00004c) +#define PPC_RAW_TLBILX_LPID (0x7c000024) +#define PPC_RAW_TLBILX(t, a, b) (0x7c000024 | __PPC_T_TLB(t) | __PPC_RA0(a) | __PPC_RB(b)) +#define PPC_RAW_WAIT_v203 (0x7c00007c) +#define PPC_RAW_WAIT(w, p) (0x7c00003c | __PPC_WC(w) | __PPC_PL(p)) +#define PPC_RAW_TLBIE(lp, a) (0x7c000264 | ___PPC_RB(a) | ___PPC_RS(lp)) +#define PPC_RAW_TLBIE_5(rb, rs, ric, prs, r) \ + (0x7c000264 | ___PPC_RB(rb) | ___PPC_RS(rs) | ___PPC_RIC(ric) | ___PPC_PRS(prs) | ___PPC_R(r)) +#define PPC_RAW_TLBIEL(rb, rs, ric, prs, r) \ + (0x7c000224 | ___PPC_RB(rb) | ___PPC_RS(rs) | ___PPC_RIC(ric) | ___PPC_PRS(prs) | ___PPC_R(r)) +#define PPC_RAW_TLBIEL_v205(rb, l) (0x7c000224 | ___PPC_RB(rb) | (l << 21)) +#define PPC_RAW_TLBSRX_DOT(a, b) (0x7c0006a5 | __PPC_RA0(a) | __PPC_RB(b)) +#define PPC_RAW_TLBIVAX(a, b) (0x7c000624 | __PPC_RA0(a) | __PPC_RB(b)) +#define PPC_RAW_ERATWE(s, a, w) (0x7c0001a6 | __PPC_RS(s) | __PPC_RA(a) | __PPC_WS(w)) +#define PPC_RAW_ERATRE(s, a, w) (0x7c000166 | __PPC_RS(s) | __PPC_RA(a) | __PPC_WS(w)) +#define PPC_RAW_ERATILX(t, a, b) (0x7c000066 | __PPC_T_TLB(t) | __PPC_RA0(a) | __PPC_RB(b)) +#define PPC_RAW_ERATIVAX(s, a, b) (0x7c000666 | __PPC_RS(s) | __PPC_RA0(a) | __PPC_RB(b)) +#define PPC_RAW_ERATSX(t, a, w) (0x7c000126 | __PPC_RS(t) | __PPC_RA0(a) | __PPC_RB(b)) +#define PPC_RAW_ERATSX_DOT(t, a, w) (0x7c000127 | __PPC_RS(t) | __PPC_RA0(a) | __PPC_RB(b)) +#define PPC_RAW_SLBFEE_DOT(t, b) (0x7c0007a7 | __PPC_RT(t) | __PPC_RB(b)) +#define __PPC_RAW_SLBFEE_DOT(t, b) (0x7c0007a7 | ___PPC_RT(t) | ___PPC_RB(b)) +#define PPC_RAW_ICBT(c, a, b) (0x7c00002c | __PPC_CT(c) | __PPC_RA0(a) | __PPC_RB(b)) +#define PPC_RAW_LBZCIX(t, a, b) (0x7c0006aa | __PPC_RT(t) | __PPC_RA(a) | __PPC_RB(b)) +#define PPC_RAW_STBCIX(s, a, b) (0x7c0007aa | __PPC_RS(s) | __PPC_RA(a) | __PPC_RB(b)) +#define PPC_RAW_DCBFPS(a, b) (0x7c0000ac | ___PPC_RA(a) | ___PPC_RB(b) | (4 << 21)) +#define PPC_RAW_DCBSTPS(a, b) (0x7c0000ac | ___PPC_RA(a) | ___PPC_RB(b) | (6 << 21)) +#define PPC_RAW_SC() (0x44000002) +#define PPC_RAW_SYNC() (0x7c0004ac) +#define PPC_RAW_ISYNC() (0x4c00012c) /* - * Only use the larx hint bit on 64bit CPUs. e500v1/v2 based CPUs will treat a - * larx with EH set as an illegal instruction. + * Define what the VSX XX1 form instructions will look like, then add + * the 128 bit load store instructions based on that. */ -#ifdef CONFIG_PPC64 -#define __PPC_EH(eh) (((eh) & 0x1) << 0) -#else -#define __PPC_EH(eh) 0 -#endif +#define VSX_XX1(s, a, b) (__PPC_XS(s) | __PPC_RA(a) | __PPC_RB(b)) +#define VSX_XX3(t, a, b) (__PPC_XT(t) | __PPC_XA(a) | __PPC_XB(b)) +#define PPC_RAW_STXVD2X(s, a, b) (0x7c000798 | VSX_XX1((s), a, b)) +#define PPC_RAW_LXVD2X(s, a, b) (0x7c000698 | VSX_XX1((s), a, b)) +#define PPC_RAW_MFVRD(a, t) (0x7c000066 | VSX_XX1((t) + 32, a, R0)) +#define PPC_RAW_MTVRD(t, a) (0x7c000166 | VSX_XX1((t) + 32, a, R0)) +#define PPC_RAW_VPMSUMW(t, a, b) (0x10000488 | VSX_XX3((t), a, b)) +#define PPC_RAW_VPMSUMD(t, a, b) (0x100004c8 | VSX_XX3((t), a, b)) +#define PPC_RAW_XXLOR(t, a, b) (0xf0000490 | VSX_XX3((t), a, b)) +#define PPC_RAW_XXSWAPD(t, a) (0xf0000250 | VSX_XX3((t), a, a)) +#define PPC_RAW_XVCPSGNDP(t, a, b) ((0xf0000780 | VSX_XX3((t), (a), (b)))) +#define PPC_RAW_VPERMXOR(vrt, vra, vrb, vrc) \ + ((0x1000002d | ___PPC_RT(vrt) | ___PPC_RA(vra) | ___PPC_RB(vrb) | (((vrc) & 0x1f) << 6))) +#define PPC_RAW_LXVP(xtp, a, i) (0x18000000 | __PPC_XTP(xtp) | ___PPC_RA(a) | IMM_DQ(i)) +#define PPC_RAW_STXVP(xsp, a, i) (0x18000001 | __PPC_XSP(xsp) | ___PPC_RA(a) | IMM_DQ(i)) +#define PPC_RAW_LXVPX(xtp, a, b) (0x7c00029a | __PPC_XTP(xtp) | ___PPC_RA(a) | ___PPC_RB(b)) +#define PPC_RAW_STXVPX(xsp, a, b) (0x7c00039a | __PPC_XSP(xsp) | ___PPC_RA(a) | ___PPC_RB(b)) +#define PPC_RAW_PLXVP_P(xtp, i, a, pr) (PPC_PREFIX_8LS | __PPC_PRFX_R(pr) | IMM_D0(i)) +#define PPC_RAW_PLXVP_S(xtp, i, a, pr) (0xe8000000 | __PPC_XTP(xtp) | ___PPC_RA(a) | IMM_D1(i)) +#define PPC_RAW_PSTXVP_P(xsp, i, a, pr) (PPC_PREFIX_8LS | __PPC_PRFX_R(pr) | IMM_D0(i)) +#define PPC_RAW_PSTXVP_S(xsp, i, a, pr) (0xf8000000 | __PPC_XSP(xsp) | ___PPC_RA(a) | IMM_D1(i)) +#define PPC_RAW_NAP (0x4c000364) +#define PPC_RAW_SLEEP (0x4c0003a4) +#define PPC_RAW_WINKLE (0x4c0003e4) +#define PPC_RAW_STOP (0x4c0002e4) +#define PPC_RAW_CLRBHRB (0x7c00035c) +#define PPC_RAW_MFBHRBE(r, n) (0x7c00025c | __PPC_RT(r) | (((n) & 0x3ff) << 11)) +#define PPC_RAW_TRECHKPT (PPC_INST_TRECHKPT) +#define PPC_RAW_TRECLAIM(r) (PPC_INST_TRECLAIM | __PPC_RA(r)) +#define PPC_RAW_TABORT(r) (0x7c00071d | __PPC_RA(r)) +#define TMRN(x) ((((x) & 0x1f) << 16) | (((x) & 0x3e0) << 6)) +#define PPC_RAW_MTTMR(tmr, r) (0x7c0003dc | TMRN(tmr) | ___PPC_RS(r)) +#define PPC_RAW_MFTMR(tmr, r) (0x7c0002dc | TMRN(tmr) | ___PPC_RT(r)) +#define PPC_RAW_ICSWX(s, a, b) (0x7c00032d | ___PPC_RS(s) | ___PPC_RA(a) | ___PPC_RB(b)) +#define PPC_RAW_ICSWEPX(s, a, b) (0x7c00076d | ___PPC_RS(s) | ___PPC_RA(a) | ___PPC_RB(b)) +#define PPC_RAW_SLBIA(IH) (0x7c0003e4 | (((IH) & 0x7) << 21)) +#define PPC_RAW_VCMPEQUD_RC(vrt, vra, vrb) \ + (0x100000c7 | ___PPC_RT(vrt) | ___PPC_RA(vra) | ___PPC_RB(vrb) | __PPC_RC21) +#define PPC_RAW_VCMPEQUB_RC(vrt, vra, vrb) \ + (0x10000006 | ___PPC_RT(vrt) | ___PPC_RA(vra) | ___PPC_RB(vrb) | __PPC_RC21) +#define PPC_RAW_LD(r, base, i) (0xe8000000 | ___PPC_RT(r) | ___PPC_RA(base) | IMM_DS(i)) +#define PPC_RAW_LWZ(r, base, i) (0x80000000 | ___PPC_RT(r) | ___PPC_RA(base) | IMM_L(i)) +#define PPC_RAW_LWZX(t, a, b) (0x7c00002e | ___PPC_RT(t) | ___PPC_RA(a) | ___PPC_RB(b)) +#define PPC_RAW_STD(r, base, i) (0xf8000000 | ___PPC_RS(r) | ___PPC_RA(base) | IMM_DS(i)) +#define PPC_RAW_STDCX(s, a, b) (0x7c0001ad | ___PPC_RS(s) | ___PPC_RA(a) | ___PPC_RB(b)) +#define PPC_RAW_LFSX(t, a, b) (0x7c00042e | ___PPC_RT(t) | ___PPC_RA(a) | ___PPC_RB(b)) +#define PPC_RAW_STFSX(s, a, b) (0x7c00052e | ___PPC_RS(s) | ___PPC_RA(a) | ___PPC_RB(b)) +#define PPC_RAW_LFDX(t, a, b) (0x7c0004ae | ___PPC_RT(t) | ___PPC_RA(a) | ___PPC_RB(b)) +#define PPC_RAW_STFDX(s, a, b) (0x7c0005ae | ___PPC_RS(s) | ___PPC_RA(a) | ___PPC_RB(b)) +#define PPC_RAW_LVX(t, a, b) (0x7c0000ce | ___PPC_RT(t) | ___PPC_RA(a) | ___PPC_RB(b)) +#define PPC_RAW_STVX(s, a, b) (0x7c0001ce | ___PPC_RS(s) | ___PPC_RA(a) | ___PPC_RB(b)) +#define PPC_RAW_ADDE(t, a, b) (0x7c000114 | ___PPC_RT(t) | ___PPC_RA(a) | ___PPC_RB(b)) +#define PPC_RAW_ADDZE(t, a) (0x7c000194 | ___PPC_RT(t) | ___PPC_RA(a)) +#define PPC_RAW_ADDME(t, a) (0x7c0001d4 | ___PPC_RT(t) | ___PPC_RA(a)) +#define PPC_RAW_ADD(t, a, b) (0x7c000214 | ___PPC_RT(t) | ___PPC_RA(a) | ___PPC_RB(b)) +#define PPC_RAW_ADD_DOT(t, a, b) (0x7c000214 | ___PPC_RT(t) | ___PPC_RA(a) | ___PPC_RB(b) | 0x1) +#define PPC_RAW_ADDC(t, a, b) (0x7c000014 | ___PPC_RT(t) | ___PPC_RA(a) | ___PPC_RB(b)) +#define PPC_RAW_ADDC_DOT(t, a, b) (0x7c000014 | ___PPC_RT(t) | ___PPC_RA(a) | ___PPC_RB(b) | 0x1) +#define PPC_RAW_NOP() PPC_RAW_ORI(0, 0, 0) +#define PPC_RAW_BLR() (0x4e800020) +#define PPC_RAW_BLRL() (0x4e800021) +#define PPC_RAW_MTLR(r) (0x7c0803a6 | ___PPC_RT(r)) +#define PPC_RAW_MFLR(t) (0x7c0802a6 | ___PPC_RT(t)) +#define PPC_RAW_BCTR() (0x4e800420) +#define PPC_RAW_BCTRL() (0x4e800421) +#define PPC_RAW_MTCTR(r) (0x7c0903a6 | ___PPC_RT(r)) +#define PPC_RAW_ADDI(d, a, i) (0x38000000 | ___PPC_RT(d) | ___PPC_RA(a) | IMM_L(i)) +#define PPC_RAW_LI(r, i) PPC_RAW_ADDI(r, 0, i) +#define PPC_RAW_ADDIS(d, a, i) (0x3c000000 | ___PPC_RT(d) | ___PPC_RA(a) | IMM_L(i)) +#define PPC_RAW_ADDIC(d, a, i) (0x30000000 | ___PPC_RT(d) | ___PPC_RA(a) | IMM_L(i)) +#define PPC_RAW_ADDIC_DOT(d, a, i) (0x34000000 | ___PPC_RT(d) | ___PPC_RA(a) | IMM_L(i)) +#define PPC_RAW_LIS(r, i) PPC_RAW_ADDIS(r, 0, i) +#define PPC_RAW_STDX(r, base, b) (0x7c00012a | ___PPC_RS(r) | ___PPC_RA(base) | ___PPC_RB(b)) +#define PPC_RAW_STDU(r, base, i) (0xf8000001 | ___PPC_RS(r) | ___PPC_RA(base) | ((i) & 0xfffc)) +#define PPC_RAW_STW(r, base, i) (0x90000000 | ___PPC_RS(r) | ___PPC_RA(base) | IMM_L(i)) +#define PPC_RAW_STWU(r, base, i) (0x94000000 | ___PPC_RS(r) | ___PPC_RA(base) | IMM_L(i)) +#define PPC_RAW_STH(r, base, i) (0xb0000000 | ___PPC_RS(r) | ___PPC_RA(base) | IMM_L(i)) +#define PPC_RAW_STB(r, base, i) (0x98000000 | ___PPC_RS(r) | ___PPC_RA(base) | IMM_L(i)) +#define PPC_RAW_LBZ(r, base, i) (0x88000000 | ___PPC_RT(r) | ___PPC_RA(base) | IMM_L(i)) +#define PPC_RAW_LDX(r, base, b) (0x7c00002a | ___PPC_RT(r) | ___PPC_RA(base) | ___PPC_RB(b)) +#define PPC_RAW_LHZ(r, base, i) (0xa0000000 | ___PPC_RT(r) | ___PPC_RA(base) | IMM_L(i)) +#define PPC_RAW_LHBRX(r, base, b) (0x7c00062c | ___PPC_RT(r) | ___PPC_RA(base) | ___PPC_RB(b)) +#define PPC_RAW_LWBRX(r, base, b) (0x7c00042c | ___PPC_RT(r) | ___PPC_RA(base) | ___PPC_RB(b)) +#define PPC_RAW_LDBRX(r, base, b) (0x7c000428 | ___PPC_RT(r) | ___PPC_RA(base) | ___PPC_RB(b)) +#define PPC_RAW_STWCX(s, a, b) (0x7c00012d | ___PPC_RS(s) | ___PPC_RA(a) | ___PPC_RB(b)) +#define PPC_RAW_CMPWI(a, i) (0x2c000000 | ___PPC_RA(a) | IMM_L(i)) +#define PPC_RAW_CMPDI(a, i) (0x2c200000 | ___PPC_RA(a) | IMM_L(i)) +#define PPC_RAW_CMPW(a, b) (0x7c000000 | ___PPC_RA(a) | ___PPC_RB(b)) +#define PPC_RAW_CMPD(a, b) (0x7c200000 | ___PPC_RA(a) | ___PPC_RB(b)) +#define PPC_RAW_CMPLWI(a, i) (0x28000000 | ___PPC_RA(a) | IMM_L(i)) +#define PPC_RAW_CMPLDI(a, i) (0x28200000 | ___PPC_RA(a) | IMM_L(i)) +#define PPC_RAW_CMPLW(a, b) (0x7c000040 | ___PPC_RA(a) | ___PPC_RB(b)) +#define PPC_RAW_CMPLD(a, b) (0x7c200040 | ___PPC_RA(a) | ___PPC_RB(b)) +#define PPC_RAW_SUB(d, a, b) (0x7c000050 | ___PPC_RT(d) | ___PPC_RB(a) | ___PPC_RA(b)) +#define PPC_RAW_SUBFC(d, a, b) (0x7c000010 | ___PPC_RT(d) | ___PPC_RA(a) | ___PPC_RB(b)) +#define PPC_RAW_SUBFE(d, a, b) (0x7c000110 | ___PPC_RT(d) | ___PPC_RA(a) | ___PPC_RB(b)) +#define PPC_RAW_SUBFIC(d, a, i) (0x20000000 | ___PPC_RT(d) | ___PPC_RA(a) | IMM_L(i)) +#define PPC_RAW_SUBFZE(d, a) (0x7c000190 | ___PPC_RT(d) | ___PPC_RA(a)) +#define PPC_RAW_MULD(d, a, b) (0x7c0001d2 | ___PPC_RT(d) | ___PPC_RA(a) | ___PPC_RB(b)) +#define PPC_RAW_MULW(d, a, b) (0x7c0001d6 | ___PPC_RT(d) | ___PPC_RA(a) | ___PPC_RB(b)) +#define PPC_RAW_MULHWU(d, a, b) (0x7c000016 | ___PPC_RT(d) | ___PPC_RA(a) | ___PPC_RB(b)) +#define PPC_RAW_MULI(d, a, i) (0x1c000000 | ___PPC_RT(d) | ___PPC_RA(a) | IMM_L(i)) +#define PPC_RAW_DIVWU(d, a, b) (0x7c000396 | ___PPC_RT(d) | ___PPC_RA(a) | ___PPC_RB(b)) +#define PPC_RAW_DIVDU(d, a, b) (0x7c000392 | ___PPC_RT(d) | ___PPC_RA(a) | ___PPC_RB(b)) +#define PPC_RAW_DIVDE(t, a, b) (0x7c000352 | ___PPC_RT(t) | ___PPC_RA(a) | ___PPC_RB(b)) +#define PPC_RAW_DIVDE_DOT(t, a, b) (0x7c000352 | ___PPC_RT(t) | ___PPC_RA(a) | ___PPC_RB(b) | 0x1) +#define PPC_RAW_DIVDEU(t, a, b) (0x7c000312 | ___PPC_RT(t) | ___PPC_RA(a) | ___PPC_RB(b)) +#define PPC_RAW_DIVDEU_DOT(t, a, b) (0x7c000312 | ___PPC_RT(t) | ___PPC_RA(a) | ___PPC_RB(b) | 0x1) +#define PPC_RAW_AND(d, a, b) (0x7c000038 | ___PPC_RA(d) | ___PPC_RS(a) | ___PPC_RB(b)) +#define PPC_RAW_ANDI(d, a, i) (0x70000000 | ___PPC_RA(d) | ___PPC_RS(a) | IMM_L(i)) +#define PPC_RAW_ANDIS(d, a, i) (0x74000000 | ___PPC_RA(d) | ___PPC_RS(a) | IMM_L(i)) +#define PPC_RAW_AND_DOT(d, a, b) (0x7c000039 | ___PPC_RA(d) | ___PPC_RS(a) | ___PPC_RB(b)) +#define PPC_RAW_OR(d, a, b) (0x7c000378 | ___PPC_RA(d) | ___PPC_RS(a) | ___PPC_RB(b)) +#define PPC_RAW_MR(d, a) PPC_RAW_OR(d, a, a) +#define PPC_RAW_ORI(d, a, i) (0x60000000 | ___PPC_RA(d) | ___PPC_RS(a) | IMM_L(i)) +#define PPC_RAW_ORIS(d, a, i) (0x64000000 | ___PPC_RA(d) | ___PPC_RS(a) | IMM_L(i)) +#define PPC_RAW_NOR(d, a, b) (0x7c0000f8 | ___PPC_RA(d) | ___PPC_RS(a) | ___PPC_RB(b)) +#define PPC_RAW_XOR(d, a, b) (0x7c000278 | ___PPC_RA(d) | ___PPC_RS(a) | ___PPC_RB(b)) +#define PPC_RAW_XORI(d, a, i) (0x68000000 | ___PPC_RA(d) | ___PPC_RS(a) | IMM_L(i)) +#define PPC_RAW_XORIS(d, a, i) (0x6c000000 | ___PPC_RA(d) | ___PPC_RS(a) | IMM_L(i)) +#define PPC_RAW_EXTSW(d, a) (0x7c0007b4 | ___PPC_RA(d) | ___PPC_RS(a)) +#define PPC_RAW_SLW(d, a, s) (0x7c000030 | ___PPC_RA(d) | ___PPC_RS(a) | ___PPC_RB(s)) +#define PPC_RAW_SLD(d, a, s) (0x7c000036 | ___PPC_RA(d) | ___PPC_RS(a) | ___PPC_RB(s)) +#define PPC_RAW_SRW(d, a, s) (0x7c000430 | ___PPC_RA(d) | ___PPC_RS(a) | ___PPC_RB(s)) +#define PPC_RAW_SRAW(d, a, s) (0x7c000630 | ___PPC_RA(d) | ___PPC_RS(a) | ___PPC_RB(s)) +#define PPC_RAW_SRAWI(d, a, i) (0x7c000670 | ___PPC_RA(d) | ___PPC_RS(a) | __PPC_SH(i)) +#define PPC_RAW_SRD(d, a, s) (0x7c000436 | ___PPC_RA(d) | ___PPC_RS(a) | ___PPC_RB(s)) +#define PPC_RAW_SRAD(d, a, s) (0x7c000634 | ___PPC_RA(d) | ___PPC_RS(a) | ___PPC_RB(s)) +#define PPC_RAW_SRADI(d, a, i) (0x7c000674 | ___PPC_RA(d) | ___PPC_RS(a) | __PPC_SH64(i)) +#define PPC_RAW_RLWINM(d, a, i, mb, me) (0x54000000 | ___PPC_RA(d) | ___PPC_RS(a) | __PPC_SH(i) | __PPC_MB(mb) | __PPC_ME(me)) +#define PPC_RAW_RLWINM_DOT(d, a, i, mb, me) \ + (0x54000001 | ___PPC_RA(d) | ___PPC_RS(a) | __PPC_SH(i) | __PPC_MB(mb) | __PPC_ME(me)) +#define PPC_RAW_RLWIMI(d, a, i, mb, me) (0x50000000 | ___PPC_RA(d) | ___PPC_RS(a) | __PPC_SH(i) | __PPC_MB(mb) | __PPC_ME(me)) +#define PPC_RAW_RLDICL(d, a, i, mb) (0x78000000 | ___PPC_RA(d) | ___PPC_RS(a) | __PPC_SH64(i) | __PPC_MB64(mb)) +#define PPC_RAW_RLDICR(d, a, i, me) (0x78000004 | ___PPC_RA(d) | ___PPC_RS(a) | __PPC_SH64(i) | __PPC_ME64(me)) + +/* slwi = rlwinm Rx, Ry, n, 0, 31-n */ +#define PPC_RAW_SLWI(d, a, i) PPC_RAW_RLWINM(d, a, i, 0, 31-(i)) +/* srwi = rlwinm Rx, Ry, 32-n, n, 31 */ +#define PPC_RAW_SRWI(d, a, i) PPC_RAW_RLWINM(d, a, 32-(i), i, 31) +/* sldi = rldicr Rx, Ry, n, 63-n */ +#define PPC_RAW_SLDI(d, a, i) PPC_RAW_RLDICR(d, a, i, 63-(i)) +/* sldi = rldicl Rx, Ry, 64-n, n */ +#define PPC_RAW_SRDI(d, a, i) PPC_RAW_RLDICL(d, a, 64-(i), i) + +#define PPC_RAW_NEG(d, a) (0x7c0000d0 | ___PPC_RT(d) | ___PPC_RA(a)) + +#define PPC_RAW_MFSPR(d, spr) (0x7c0002a6 | ___PPC_RT(d) | __PPC_SPR(spr)) +#define PPC_RAW_MTSPR(spr, d) (0x7c0003a6 | ___PPC_RS(d) | __PPC_SPR(spr)) +#define PPC_RAW_EIEIO() (0x7c0006ac) + +#define PPC_RAW_BRANCH(offset) (0x48000000 | PPC_LI(offset)) +#define PPC_RAW_BL(offset) (0x48000001 | PPC_LI(offset)) +#define PPC_RAW_TW(t0, a, b) (0x7c000008 | ___PPC_RS(t0) | ___PPC_RA(a) | ___PPC_RB(b)) +#define PPC_RAW_TRAP() PPC_RAW_TW(31, 0, 0) +#define PPC_RAW_SETB(t, bfa) (0x7c000100 | ___PPC_RT(t) | ___PPC_RA((bfa) << 2)) /* Deal with instructions that older assemblers aren't aware of */ -#define PPC_CP_ABORT stringify_in_c(.long PPC_INST_CP_ABORT) -#define PPC_COPY(a, b) stringify_in_c(.long PPC_INST_COPY | \ - ___PPC_RA(a) | ___PPC_RB(b)) -#define PPC_DARN(t, l) stringify_in_c(.long PPC_INST_DARN | \ - ___PPC_RT(t) | \ - (((l) & 0x3) << 16)) -#define PPC_DCBAL(a, b) stringify_in_c(.long PPC_INST_DCBAL | \ - __PPC_RA(a) | __PPC_RB(b)) -#define PPC_DCBZL(a, b) stringify_in_c(.long PPC_INST_DCBZL | \ - __PPC_RA(a) | __PPC_RB(b)) -#define PPC_LQARX(t, a, b, eh) stringify_in_c(.long PPC_INST_LQARX | \ - ___PPC_RT(t) | ___PPC_RA(a) | \ - ___PPC_RB(b) | __PPC_EH(eh)) -#define PPC_LDARX(t, a, b, eh) stringify_in_c(.long PPC_INST_LDARX | \ - ___PPC_RT(t) | ___PPC_RA(a) | \ - ___PPC_RB(b) | __PPC_EH(eh)) -#define PPC_LWARX(t, a, b, eh) stringify_in_c(.long PPC_INST_LWARX | \ - ___PPC_RT(t) | ___PPC_RA(a) | \ - ___PPC_RB(b) | __PPC_EH(eh)) -#define PPC_STQCX(t, a, b) stringify_in_c(.long PPC_INST_STQCX | \ - ___PPC_RT(t) | ___PPC_RA(a) | \ - ___PPC_RB(b)) -#define PPC_MADDHD(t, a, b, c) stringify_in_c(.long PPC_INST_MADDHD | \ - ___PPC_RT(t) | ___PPC_RA(a) | \ - ___PPC_RB(b) | ___PPC_RC(c)) -#define PPC_MADDHDU(t, a, b, c) stringify_in_c(.long PPC_INST_MADDHDU | \ - ___PPC_RT(t) | ___PPC_RA(a) | \ - ___PPC_RB(b) | ___PPC_RC(c)) -#define PPC_MADDLD(t, a, b, c) stringify_in_c(.long PPC_INST_MADDLD | \ - ___PPC_RT(t) | ___PPC_RA(a) | \ - ___PPC_RB(b) | ___PPC_RC(c)) -#define PPC_MSGSND(b) stringify_in_c(.long PPC_INST_MSGSND | \ - ___PPC_RB(b)) -#define PPC_MSGSYNC stringify_in_c(.long PPC_INST_MSGSYNC) -#define PPC_MSGCLR(b) stringify_in_c(.long PPC_INST_MSGCLR | \ - ___PPC_RB(b)) -#define PPC_MSGSNDP(b) stringify_in_c(.long PPC_INST_MSGSNDP | \ - ___PPC_RB(b)) -#define PPC_MSGCLRP(b) stringify_in_c(.long PPC_INST_MSGCLRP | \ - ___PPC_RB(b)) -#define PPC_PASTE(a, b) stringify_in_c(.long PPC_INST_PASTE | \ - ___PPC_RA(a) | ___PPC_RB(b)) -#define PPC_POPCNTB(a, s) stringify_in_c(.long PPC_INST_POPCNTB | \ - __PPC_RA(a) | __PPC_RS(s)) -#define PPC_POPCNTD(a, s) stringify_in_c(.long PPC_INST_POPCNTD | \ - __PPC_RA(a) | __PPC_RS(s)) -#define PPC_POPCNTW(a, s) stringify_in_c(.long PPC_INST_POPCNTW | \ - __PPC_RA(a) | __PPC_RS(s)) -#define PPC_RFCI stringify_in_c(.long PPC_INST_RFCI) -#define PPC_RFDI stringify_in_c(.long PPC_INST_RFDI) -#define PPC_RFMCI stringify_in_c(.long PPC_INST_RFMCI) -#define PPC_TLBILX(t, a, b) stringify_in_c(.long PPC_INST_TLBILX | \ - __PPC_T_TLB(t) | __PPC_RA0(a) | __PPC_RB(b)) +#define PPC_BCCTR_FLUSH stringify_in_c(.long PPC_INST_BCCTR_FLUSH) +#define PPC_CP_ABORT stringify_in_c(.long PPC_RAW_CP_ABORT) +#define PPC_COPY(a, b) stringify_in_c(.long PPC_RAW_COPY(a, b)) +#define PPC_DARN(t, l) stringify_in_c(.long PPC_RAW_DARN(t, l)) +#define PPC_DCBAL(a, b) stringify_in_c(.long PPC_RAW_DCBAL(a, b)) +#define PPC_DCBZL(a, b) stringify_in_c(.long PPC_RAW_DCBZL(a, b)) +#define PPC_DIVDE(t, a, b) stringify_in_c(.long PPC_RAW_DIVDE(t, a, b)) +#define PPC_DIVDEU(t, a, b) stringify_in_c(.long PPC_RAW_DIVDEU(t, a, b)) +#define PPC_DSSALL stringify_in_c(.long PPC_INST_DSSALL) +#define PPC_LQARX(t, a, b, eh) stringify_in_c(.long PPC_RAW_LQARX(t, a, b, eh)) +#define PPC_STQCX(t, a, b) stringify_in_c(.long PPC_RAW_STQCX(t, a, b)) +#define PPC_MADDHD(t, a, b, c) stringify_in_c(.long PPC_RAW_MADDHD(t, a, b, c)) +#define PPC_MADDHDU(t, a, b, c) stringify_in_c(.long PPC_RAW_MADDHDU(t, a, b, c)) +#define PPC_MADDLD(t, a, b, c) stringify_in_c(.long PPC_RAW_MADDLD(t, a, b, c)) +#define PPC_MSGSND(b) stringify_in_c(.long PPC_RAW_MSGSND(b)) +#define PPC_MSGSYNC stringify_in_c(.long PPC_RAW_MSGSYNC) +#define PPC_MSGCLR(b) stringify_in_c(.long PPC_RAW_MSGCLR(b)) +#define PPC_MSGSNDP(b) stringify_in_c(.long PPC_RAW_MSGSNDP(b)) +#define PPC_MSGCLRP(b) stringify_in_c(.long PPC_RAW_MSGCLRP(b)) +#define PPC_PASTE(a, b) stringify_in_c(.long PPC_RAW_PASTE(a, b)) +#define PPC_POPCNTB(a, s) stringify_in_c(.long PPC_RAW_POPCNTB(a, s)) +#define PPC_POPCNTD(a, s) stringify_in_c(.long PPC_RAW_POPCNTD(a, s)) +#define PPC_POPCNTW(a, s) stringify_in_c(.long PPC_RAW_POPCNTW(a, s)) +#define PPC_RFCI stringify_in_c(.long PPC_RAW_RFCI) +#define PPC_RFDI stringify_in_c(.long PPC_RAW_RFDI) +#define PPC_RFMCI stringify_in_c(.long PPC_RAW_RFMCI) +#define PPC_TLBILX(t, a, b) stringify_in_c(.long PPC_RAW_TLBILX(t, a, b)) #define PPC_TLBILX_ALL(a, b) PPC_TLBILX(0, a, b) #define PPC_TLBILX_PID(a, b) PPC_TLBILX(1, a, b) +#define PPC_TLBILX_LPID stringify_in_c(.long PPC_RAW_TLBILX_LPID) #define PPC_TLBILX_VA(a, b) PPC_TLBILX(3, a, b) -#define PPC_WAIT(w) stringify_in_c(.long PPC_INST_WAIT | \ - __PPC_WC(w)) -#define PPC_TLBIE(lp,a) stringify_in_c(.long PPC_INST_TLBIE | \ - ___PPC_RB(a) | ___PPC_RS(lp)) -#define PPC_TLBIE_5(rb,rs,ric,prs,r) \ - stringify_in_c(.long PPC_INST_TLBIE | \ - ___PPC_RB(rb) | ___PPC_RS(rs) | \ - ___PPC_RIC(ric) | ___PPC_PRS(prs) | \ - ___PPC_R(r)) +#define PPC_WAIT_v203 stringify_in_c(.long PPC_RAW_WAIT_v203) +#define PPC_WAIT(w, p) stringify_in_c(.long PPC_RAW_WAIT(w, p)) +#define PPC_TLBIE(lp, a) stringify_in_c(.long PPC_RAW_TLBIE(lp, a)) +#define PPC_TLBIE_5(rb, rs, ric, prs, r) \ + stringify_in_c(.long PPC_RAW_TLBIE_5(rb, rs, ric, prs, r)) #define PPC_TLBIEL(rb,rs,ric,prs,r) \ - stringify_in_c(.long PPC_INST_TLBIEL | \ - ___PPC_RB(rb) | ___PPC_RS(rs) | \ - ___PPC_RIC(ric) | ___PPC_PRS(prs) | \ - ___PPC_R(r)) -#define PPC_TLBSRX_DOT(a,b) stringify_in_c(.long PPC_INST_TLBSRX_DOT | \ - __PPC_RA0(a) | __PPC_RB(b)) -#define PPC_TLBIVAX(a,b) stringify_in_c(.long PPC_INST_TLBIVAX | \ - __PPC_RA0(a) | __PPC_RB(b)) - -#define PPC_ERATWE(s, a, w) stringify_in_c(.long PPC_INST_ERATWE | \ - __PPC_RS(s) | __PPC_RA(a) | __PPC_WS(w)) -#define PPC_ERATRE(s, a, w) stringify_in_c(.long PPC_INST_ERATRE | \ - __PPC_RS(s) | __PPC_RA(a) | __PPC_WS(w)) -#define PPC_ERATILX(t, a, b) stringify_in_c(.long PPC_INST_ERATILX | \ - __PPC_T_TLB(t) | __PPC_RA0(a) | \ - __PPC_RB(b)) -#define PPC_ERATIVAX(s, a, b) stringify_in_c(.long PPC_INST_ERATIVAX | \ - __PPC_RS(s) | __PPC_RA0(a) | __PPC_RB(b)) -#define PPC_ERATSX(t, a, w) stringify_in_c(.long PPC_INST_ERATSX | \ - __PPC_RS(t) | __PPC_RA0(a) | __PPC_RB(b)) -#define PPC_ERATSX_DOT(t, a, w) stringify_in_c(.long PPC_INST_ERATSX_DOT | \ - __PPC_RS(t) | __PPC_RA0(a) | __PPC_RB(b)) -#define PPC_SLBFEE_DOT(t, b) stringify_in_c(.long PPC_INST_SLBFEE | \ - __PPC_RT(t) | __PPC_RB(b)) -#define __PPC_SLBFEE_DOT(t, b) stringify_in_c(.long PPC_INST_SLBFEE | \ - ___PPC_RT(t) | ___PPC_RB(b)) -#define PPC_ICBT(c,a,b) stringify_in_c(.long PPC_INST_ICBT | \ - __PPC_CT(c) | __PPC_RA0(a) | __PPC_RB(b)) + stringify_in_c(.long PPC_RAW_TLBIEL(rb, rs, ric, prs, r)) +#define PPC_TLBIEL_v205(rb, l) stringify_in_c(.long PPC_RAW_TLBIEL_v205(rb, l)) +#define PPC_TLBSRX_DOT(a, b) stringify_in_c(.long PPC_RAW_TLBSRX_DOT(a, b)) +#define PPC_TLBIVAX(a, b) stringify_in_c(.long PPC_RAW_TLBIVAX(a, b)) + +#define PPC_ERATWE(s, a, w) stringify_in_c(.long PPC_RAW_ERATWE(s, a, w)) +#define PPC_ERATRE(s, a, w) stringify_in_c(.long PPC_RAW_ERATRE(a, a, w)) +#define PPC_ERATILX(t, a, b) stringify_in_c(.long PPC_RAW_ERATILX(t, a, b)) +#define PPC_ERATIVAX(s, a, b) stringify_in_c(.long PPC_RAW_ERATIVAX(s, a, b)) +#define PPC_ERATSX(t, a, w) stringify_in_c(.long PPC_RAW_ERATSX(t, a, w)) +#define PPC_ERATSX_DOT(t, a, w) stringify_in_c(.long PPC_RAW_ERATSX_DOT(t, a, w)) +#define PPC_SLBFEE_DOT(t, b) stringify_in_c(.long PPC_RAW_SLBFEE_DOT(t, b)) +#define __PPC_SLBFEE_DOT(t, b) stringify_in_c(.long __PPC_RAW_SLBFEE_DOT(t, b)) +#define PPC_ICBT(c, a, b) stringify_in_c(.long PPC_RAW_ICBT(c, a, b)) /* PASemi instructions */ -#define LBZCIX(t,a,b) stringify_in_c(.long PPC_INST_LBZCIX | \ - __PPC_RT(t) | __PPC_RA(a) | __PPC_RB(b)) -#define STBCIX(s,a,b) stringify_in_c(.long PPC_INST_STBCIX | \ - __PPC_RS(s) | __PPC_RA(a) | __PPC_RB(b)) - -/* - * Define what the VSX XX1 form instructions will look like, then add - * the 128 bit load store instructions based on that. - */ -#define VSX_XX1(s, a, b) (__PPC_XS(s) | __PPC_RA(a) | __PPC_RB(b)) -#define VSX_XX3(t, a, b) (__PPC_XT(t) | __PPC_XA(a) | __PPC_XB(b)) -#define STXVD2X(s, a, b) stringify_in_c(.long PPC_INST_STXVD2X | \ - VSX_XX1((s), a, b)) -#define LXVD2X(s, a, b) stringify_in_c(.long PPC_INST_LXVD2X | \ - VSX_XX1((s), a, b)) -#define MFVRD(a, t) stringify_in_c(.long PPC_INST_MFVSRD | \ - VSX_XX1((t)+32, a, R0)) -#define MTVRD(t, a) stringify_in_c(.long PPC_INST_MTVSRD | \ - VSX_XX1((t)+32, a, R0)) -#define VPMSUMW(t, a, b) stringify_in_c(.long PPC_INST_VPMSUMW | \ - VSX_XX3((t), a, b)) -#define VPMSUMD(t, a, b) stringify_in_c(.long PPC_INST_VPMSUMD | \ - VSX_XX3((t), a, b)) -#define XXLOR(t, a, b) stringify_in_c(.long PPC_INST_XXLOR | \ - VSX_XX3((t), a, b)) -#define XXSWAPD(t, a) stringify_in_c(.long PPC_INST_XXSWAPD | \ - VSX_XX3((t), a, a)) -#define XVCPSGNDP(t, a, b) stringify_in_c(.long (PPC_INST_XVCPSGNDP | \ - VSX_XX3((t), (a), (b)))) +#define LBZCIX(t, a, b) stringify_in_c(.long PPC_RAW_LBZCIX(t, a, b)) +#define STBCIX(s, a, b) stringify_in_c(.long PPC_RAW_STBCIX(s, a, b)) +#define PPC_DCBFPS(a, b) stringify_in_c(.long PPC_RAW_DCBFPS(a, b)) +#define PPC_DCBSTPS(a, b) stringify_in_c(.long PPC_RAW_DCBSTPS(a, b)) +#define PPC_PHWSYNC stringify_in_c(.long PPC_RAW_PHWSYNC) +#define PPC_PLWSYNC stringify_in_c(.long PPC_RAW_PLWSYNC) +#define STXVD2X(s, a, b) stringify_in_c(.long PPC_RAW_STXVD2X(s, a, b)) +#define LXVD2X(s, a, b) stringify_in_c(.long PPC_RAW_LXVD2X(s, a, b)) +#define MFVRD(a, t) stringify_in_c(.long PPC_RAW_MFVRD(a, t)) +#define MTVRD(t, a) stringify_in_c(.long PPC_RAW_MTVRD(t, a)) +#define VPMSUMW(t, a, b) stringify_in_c(.long PPC_RAW_VPMSUMW(t, a, b)) +#define VPMSUMD(t, a, b) stringify_in_c(.long PPC_RAW_VPMSUMD(t, a, b)) +#define XXLOR(t, a, b) stringify_in_c(.long PPC_RAW_XXLOR(t, a, b)) +#define XXSWAPD(t, a) stringify_in_c(.long PPC_RAW_XXSWAPD(t, a)) +#define XVCPSGNDP(t, a, b) stringify_in_c(.long (PPC_RAW_XVCPSGNDP(t, a, b))) #define VPERMXOR(vrt, vra, vrb, vrc) \ - stringify_in_c(.long (PPC_INST_VPERMXOR | \ - ___PPC_RT(vrt) | ___PPC_RA(vra) | \ - ___PPC_RB(vrb) | (((vrc) & 0x1f) << 6))) + stringify_in_c(.long (PPC_RAW_VPERMXOR(vrt, vra, vrb, vrc))) -#define PPC_NAP stringify_in_c(.long PPC_INST_NAP) -#define PPC_SLEEP stringify_in_c(.long PPC_INST_SLEEP) -#define PPC_WINKLE stringify_in_c(.long PPC_INST_WINKLE) +#define PPC_NAP stringify_in_c(.long PPC_RAW_NAP) +#define PPC_SLEEP stringify_in_c(.long PPC_RAW_SLEEP) +#define PPC_WINKLE stringify_in_c(.long PPC_RAW_WINKLE) -#define PPC_STOP stringify_in_c(.long PPC_INST_STOP) +#define PPC_STOP stringify_in_c(.long PPC_RAW_STOP) /* BHRB instructions */ -#define PPC_CLRBHRB stringify_in_c(.long PPC_INST_CLRBHRB) -#define PPC_MFBHRBE(r, n) stringify_in_c(.long PPC_INST_BHRBE | \ - __PPC_RT(r) | \ - (((n) & 0x3ff) << 11)) +#define PPC_CLRBHRB stringify_in_c(.long PPC_RAW_CLRBHRB) +#define PPC_MFBHRBE(r, n) stringify_in_c(.long PPC_RAW_MFBHRBE(r, n)) /* Transactional memory instructions */ -#define TRECHKPT stringify_in_c(.long PPC_INST_TRECHKPT) -#define TRECLAIM(r) stringify_in_c(.long PPC_INST_TRECLAIM \ - | __PPC_RA(r)) -#define TABORT(r) stringify_in_c(.long PPC_INST_TABORT \ - | __PPC_RA(r)) +#define TRECHKPT stringify_in_c(.long PPC_RAW_TRECHKPT) +#define TRECLAIM(r) stringify_in_c(.long PPC_RAW_TRECLAIM(r)) +#define TABORT(r) stringify_in_c(.long PPC_RAW_TABORT(r)) /* book3e thread control instructions */ -#define TMRN(x) ((((x) & 0x1f) << 16) | (((x) & 0x3e0) << 6)) -#define MTTMR(tmr, r) stringify_in_c(.long PPC_INST_MTTMR | \ - TMRN(tmr) | ___PPC_RS(r)) -#define MFTMR(tmr, r) stringify_in_c(.long PPC_INST_MFTMR | \ - TMRN(tmr) | ___PPC_RT(r)) +#define MTTMR(tmr, r) stringify_in_c(.long PPC_RAW_MTTMR(tmr, r)) +#define MFTMR(tmr, r) stringify_in_c(.long PPC_RAW_MFTMR(tmr, r)) /* Coprocessor instructions */ -#define PPC_ICSWX(s, a, b) stringify_in_c(.long PPC_INST_ICSWX | \ - ___PPC_RS(s) | \ - ___PPC_RA(a) | \ - ___PPC_RB(b)) -#define PPC_ICSWEPX(s, a, b) stringify_in_c(.long PPC_INST_ICSWEPX | \ - ___PPC_RS(s) | \ - ___PPC_RA(a) | \ - ___PPC_RB(b)) - -#define PPC_SLBIA(IH) stringify_in_c(.long PPC_INST_SLBIA | \ - ((IH & 0x7) << 21)) +#define PPC_ICSWX(s, a, b) stringify_in_c(.long PPC_RAW_ICSWX(s, a, b)) +#define PPC_ICSWEPX(s, a, b) stringify_in_c(.long PPC_RAW_ICSWEPX(s, a, b)) + +#define PPC_SLBIA(IH) stringify_in_c(.long PPC_RAW_SLBIA(IH)) /* * These may only be used on ISA v3.0 or later (aka. CPU_FTR_ARCH_300, radix @@ -608,12 +694,8 @@ #define PPC_RADIX_INVALIDATE_ERAT_USER PPC_SLBIA(3) #define PPC_RADIX_INVALIDATE_ERAT_GUEST PPC_SLBIA(6) -#define VCMPEQUD_RC(vrt, vra, vrb) stringify_in_c(.long PPC_INST_VCMPEQUD | \ - ___PPC_RT(vrt) | ___PPC_RA(vra) | \ - ___PPC_RB(vrb) | __PPC_RC21) +#define VCMPEQUD_RC(vrt, vra, vrb) stringify_in_c(.long PPC_RAW_VCMPEQUD_RC(vrt, vra, vrb)) -#define VCMPEQUB_RC(vrt, vra, vrb) stringify_in_c(.long PPC_INST_VCMPEQUB | \ - ___PPC_RT(vrt) | ___PPC_RA(vra) | \ - ___PPC_RB(vrb) | __PPC_RC21) +#define VCMPEQUB_RC(vrt, vra, vrb) stringify_in_c(.long PPC_RAW_VCMPEQUB_RC(vrt, vra, vrb)) #endif /* _ASM_POWERPC_PPC_OPCODE_H */ diff --git a/arch/powerpc/include/asm/ppc-pci.h b/arch/powerpc/include/asm/ppc-pci.h index 7f4be5a05eb3..ce2b1b5eebdd 100644 --- a/arch/powerpc/include/asm/ppc-pci.h +++ b/arch/powerpc/include/asm/ppc-pci.h @@ -13,10 +13,6 @@ extern unsigned long isa_io_base; -extern void pci_setup_phb_io(struct pci_controller *hose, int primary); -extern void pci_setup_phb_io_dynamic(struct pci_controller *hose, int primary); - - extern struct list_head hose_list; extern struct pci_dev *isa_bridge_pcidev; /* may be NULL if no ISA bus */ @@ -32,9 +28,6 @@ struct pci_dn; void *pci_traverse_device_nodes(struct device_node *start, void *(*fn)(struct device_node *, void *), void *data); -void *traverse_pci_dn(struct pci_dn *root, - void *(*fn)(struct pci_dn *, void *), - void *data); extern void pci_devs_phb_init_dynamic(struct pci_controller *phb); /* From rtas_pci.h */ @@ -42,6 +35,9 @@ extern void init_pci_config_tokens (void); extern unsigned long get_phb_buid (struct device_node *); extern int rtas_setup_phb(struct pci_controller *phb); +int rtas_pci_dn_read_config(struct pci_dn *pdn, int where, int size, u32 *val); +int rtas_pci_dn_write_config(struct pci_dn *pdn, int where, int size, u32 val); + #ifdef CONFIG_EEH void eeh_addr_cache_insert_dev(struct pci_dev *dev); @@ -51,8 +47,6 @@ void eeh_slot_error_detail(struct eeh_pe *pe, int severity); int eeh_pci_enable(struct eeh_pe *pe, int function); int eeh_pe_reset_full(struct eeh_pe *pe, bool include_passed); void eeh_save_bars(struct eeh_dev *edev); -int rtas_write_config(struct pci_dn *, int where, int size, u32 val); -int rtas_read_config(struct pci_dn *, int where, int size, u32 *val); void eeh_pe_state_mark(struct eeh_pe *pe, int state); void eeh_pe_mark_isolated(struct eeh_pe *pe); void eeh_pe_state_clear(struct eeh_pe *pe, int state, bool include_passed); @@ -62,18 +56,21 @@ void eeh_pe_dev_mode_mark(struct eeh_pe *pe, int mode); void eeh_sysfs_add_device(struct pci_dev *pdev); void eeh_sysfs_remove_device(struct pci_dev *pdev); -static inline const char *eeh_driver_name(struct pci_dev *pdev) -{ - return (pdev && pdev->driver) ? pdev->driver->name : "<null>"; -} - #endif /* CONFIG_EEH */ +#ifdef CONFIG_FSL_ULI1575 +void __init uli_init(void); +#endif /* CONFIG_FSL_ULI1575 */ + #define PCI_BUSNO(bdfn) ((bdfn >> 8) & 0xff) #else /* CONFIG_PCI */ static inline void init_pci_config_tokens(void) { } #endif /* !CONFIG_PCI */ +#if !defined(CONFIG_PCI) || !defined(CONFIG_FSL_ULI1575) +static inline void __init uli_init(void) {} +#endif /* !defined(CONFIG_PCI) || !defined(CONFIG_FSL_ULI1575) */ + #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_PPC_PCI_H */ diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h index 6b03dff61a05..e7792aa13510 100644 --- a/arch/powerpc/include/asm/ppc_asm.h +++ b/arch/powerpc/include/asm/ppc_asm.h @@ -10,89 +10,88 @@ #include <asm/ppc-opcode.h> #include <asm/firmware.h> #include <asm/feature-fixups.h> +#include <asm/extable.h> #ifdef __ASSEMBLY__ #define SZL (BITS_PER_LONG/8) /* - * Stuff for accurate CPU time accounting. - * These macros handle transitions between user and system state - * in exception entry and exit and accumulate time to the - * user_time and system_time fields in the paca. + * This expands to a sequence of operations with reg incrementing from + * start to end inclusive, of this form: + * + * op reg, (offset + (width * reg))(base) + * + * Note that offset is not the offset of the first operation unless start + * is zero (or width is zero). */ +.macro OP_REGS op, width, start, end, base, offset + .Lreg=\start + .rept (\end - \start + 1) + \op .Lreg, \offset + \width * .Lreg(\base) + .Lreg=.Lreg+1 + .endr +.endm -#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE -#define ACCOUNT_CPU_USER_ENTRY(ptr, ra, rb) -#define ACCOUNT_CPU_USER_EXIT(ptr, ra, rb) -#define ACCOUNT_STOLEN_TIME -#else -#define ACCOUNT_CPU_USER_ENTRY(ptr, ra, rb) \ - MFTB(ra); /* get timebase */ \ - PPC_LL rb, ACCOUNT_STARTTIME_USER(ptr); \ - PPC_STL ra, ACCOUNT_STARTTIME(ptr); \ - subf rb,rb,ra; /* subtract start value */ \ - PPC_LL ra, ACCOUNT_USER_TIME(ptr); \ - add ra,ra,rb; /* add on to user time */ \ - PPC_STL ra, ACCOUNT_USER_TIME(ptr); \ - -#define ACCOUNT_CPU_USER_EXIT(ptr, ra, rb) \ - MFTB(ra); /* get timebase */ \ - PPC_LL rb, ACCOUNT_STARTTIME(ptr); \ - PPC_STL ra, ACCOUNT_STARTTIME_USER(ptr); \ - subf rb,rb,ra; /* subtract start value */ \ - PPC_LL ra, ACCOUNT_SYSTEM_TIME(ptr); \ - add ra,ra,rb; /* add on to system time */ \ - PPC_STL ra, ACCOUNT_SYSTEM_TIME(ptr) - -#ifdef CONFIG_PPC_SPLPAR -#define ACCOUNT_STOLEN_TIME \ -BEGIN_FW_FTR_SECTION; \ - beq 33f; \ - /* from user - see if there are any DTL entries to process */ \ - ld r10,PACALPPACAPTR(r13); /* get ptr to VPA */ \ - ld r11,PACA_DTL_RIDX(r13); /* get log read index */ \ - addi r10,r10,LPPACA_DTLIDX; \ - LDX_BE r10,0,r10; /* get log write index */ \ - cmpd cr1,r11,r10; \ - beq+ cr1,33f; \ - bl accumulate_stolen_time; \ - ld r12,_MSR(r1); \ - andi. r10,r12,MSR_PR; /* Restore cr0 (coming from user) */ \ -33: \ -END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR) - -#else /* CONFIG_PPC_SPLPAR */ -#define ACCOUNT_STOLEN_TIME - -#endif /* CONFIG_PPC_SPLPAR */ - -#endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ +/* + * This expands to a sequence of register clears for regs start to end + * inclusive, of the form: + * + * li rN, 0 + */ +.macro ZEROIZE_REGS start, end + .Lreg=\start + .rept (\end - \start + 1) + li .Lreg, 0 + .Lreg=.Lreg+1 + .endr +.endm /* * Macros for storing registers into and loading registers from * exception frames. */ #ifdef __powerpc64__ -#define SAVE_GPR(n, base) std n,GPR0+8*(n)(base) -#define REST_GPR(n, base) ld n,GPR0+8*(n)(base) -#define SAVE_NVGPRS(base) SAVE_8GPRS(14, base); SAVE_10GPRS(22, base) -#define REST_NVGPRS(base) REST_8GPRS(14, base); REST_10GPRS(22, base) +#define SAVE_GPRS(start, end, base) OP_REGS std, 8, start, end, base, GPR0 +#define REST_GPRS(start, end, base) OP_REGS ld, 8, start, end, base, GPR0 +#define SAVE_NVGPRS(base) SAVE_GPRS(14, 31, base) +#define REST_NVGPRS(base) REST_GPRS(14, 31, base) #else -#define SAVE_GPR(n, base) stw n,GPR0+4*(n)(base) -#define REST_GPR(n, base) lwz n,GPR0+4*(n)(base) -#define SAVE_NVGPRS(base) stmw 13, GPR0+4*13(base) -#define REST_NVGPRS(base) lmw 13, GPR0+4*13(base) +#define SAVE_GPRS(start, end, base) OP_REGS stw, 4, start, end, base, GPR0 +#define REST_GPRS(start, end, base) OP_REGS lwz, 4, start, end, base, GPR0 +#define SAVE_NVGPRS(base) SAVE_GPRS(13, 31, base) +#define REST_NVGPRS(base) REST_GPRS(13, 31, base) #endif -#define SAVE_2GPRS(n, base) SAVE_GPR(n, base); SAVE_GPR(n+1, base) -#define SAVE_4GPRS(n, base) SAVE_2GPRS(n, base); SAVE_2GPRS(n+2, base) -#define SAVE_8GPRS(n, base) SAVE_4GPRS(n, base); SAVE_4GPRS(n+4, base) -#define SAVE_10GPRS(n, base) SAVE_8GPRS(n, base); SAVE_2GPRS(n+8, base) -#define REST_2GPRS(n, base) REST_GPR(n, base); REST_GPR(n+1, base) -#define REST_4GPRS(n, base) REST_2GPRS(n, base); REST_2GPRS(n+2, base) -#define REST_8GPRS(n, base) REST_4GPRS(n, base); REST_4GPRS(n+4, base) -#define REST_10GPRS(n, base) REST_8GPRS(n, base); REST_2GPRS(n+8, base) +#define ZEROIZE_GPRS(start, end) ZEROIZE_REGS start, end +#ifdef __powerpc64__ +#define ZEROIZE_NVGPRS() ZEROIZE_GPRS(14, 31) +#else +#define ZEROIZE_NVGPRS() ZEROIZE_GPRS(13, 31) +#endif +#define ZEROIZE_GPR(n) ZEROIZE_GPRS(n, n) + +#define SAVE_GPR(n, base) SAVE_GPRS(n, n, base) +#define REST_GPR(n, base) REST_GPRS(n, n, base) + +/* macros for handling user register sanitisation */ +#ifdef CONFIG_INTERRUPT_SANITIZE_REGISTERS +#define SANITIZE_SYSCALL_GPRS() ZEROIZE_GPR(0); \ + ZEROIZE_GPRS(5, 12); \ + ZEROIZE_NVGPRS() +#define SANITIZE_GPR(n) ZEROIZE_GPR(n) +#define SANITIZE_GPRS(start, end) ZEROIZE_GPRS(start, end) +#define SANITIZE_NVGPRS() ZEROIZE_NVGPRS() +#define SANITIZE_RESTORE_NVGPRS() REST_NVGPRS(r1) +#define HANDLER_RESTORE_NVGPRS() +#else +#define SANITIZE_SYSCALL_GPRS() +#define SANITIZE_GPR(n) +#define SANITIZE_GPRS(start, end) +#define SANITIZE_NVGPRS() +#define SANITIZE_RESTORE_NVGPRS() +#define HANDLER_RESTORE_NVGPRS() REST_NVGPRS(r1) +#endif /* CONFIG_INTERRUPT_SANITIZE_REGISTERS */ #define SAVE_FPR(n, base) stfd n,8*TS_FPRWIDTH*(n)(base) #define SAVE_2FPRS(n, base) SAVE_FPR(n, base); SAVE_FPR(n+1, base) @@ -180,13 +179,27 @@ END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR) #define VCPU_GPR(n) __VCPU_GPR(__REG_##n) #ifdef __KERNEL__ -#ifdef CONFIG_PPC64 + +/* + * Used to name C functions called from asm + */ +#ifdef CONFIG_PPC_KERNEL_PCREL +#define CFUNC(name) name@notoc +#else +#define CFUNC(name) name +#endif + +/* + * We use __powerpc64__ here because we want the compat VDSO to use the 32-bit + * version below in the else case of the ifdef. + */ +#ifdef __powerpc64__ #define STACKFRAMESIZE 256 #define __STK_REG(i) (112 + ((i)-14)*8) #define STK_REG(i) __STK_REG(__REG_##i) -#ifdef PPC64_ELF_ABI_v2 +#ifdef CONFIG_PPC64_ELF_ABI_V2 #define STK_GOT 24 #define __STK_PARAM(i) (32 + ((i)-3)*8) #else @@ -195,7 +208,7 @@ END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR) #endif #define STK_PARAM(i) __STK_PARAM(__REG_##i) -#ifdef PPC64_ELF_ABI_v2 +#ifdef CONFIG_PPC64_ELF_ABI_V2 #define _GLOBAL(name) \ .align 2 ; \ @@ -203,6 +216,9 @@ END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR) .globl name; \ name: +#ifdef CONFIG_PPC_KERNEL_PCREL +#define _GLOBAL_TOC _GLOBAL +#else #define _GLOBAL_TOC(name) \ .align 2 ; \ .type name,@function; \ @@ -211,6 +227,7 @@ name: \ 0: addis r2,r12,(.TOC.-0b)@ha; \ addi r2,r2,(.TOC.-0b)@l; \ .localentry name,.-name +#endif #define DOTSYM(a) a @@ -240,17 +257,14 @@ GLUE(.,name): #else /* 32-bit */ -#define _ENTRY(n) \ - .globl n; \ -n: - #define _GLOBAL(n) \ - .stabs __stringify(n:F-1),N_FUN,0,0,n;\ .globl n; \ n: #define _GLOBAL_TOC(name) _GLOBAL(name) +#define DOTSYM(a) a + #endif /* @@ -306,7 +320,7 @@ n: /* Be careful, this will clobber the lr register. */ #define LOAD_REG_ADDR_PIC(reg, name) \ - bl 0f; \ + bcl 20,31,$+4; \ 0: mflr reg; \ addis reg,reg,(name - 0b)@ha; \ addi reg,reg,(name - 0b)@l; @@ -345,6 +359,17 @@ n: #ifdef __powerpc64__ +#ifdef CONFIG_PPC_KERNEL_PCREL +#define __LOAD_PACA_TOC(reg) \ + li reg,-1 +#else +#define __LOAD_PACA_TOC(reg) \ + ld reg,PACATOC(r13) +#endif + +#define LOAD_PACA_TOC() \ + __LOAD_PACA_TOC(r2) + #define LOAD_REG_IMMEDIATE(reg, expr) __LOAD_REG_IMMEDIATE reg, expr #define LOAD_REG_IMMEDIATE_SYM(reg, tmp, expr) \ @@ -354,8 +379,26 @@ n: ori reg, reg, (expr)@l; \ rldimi reg, tmp, 32, 0 +#ifdef CONFIG_PPC_KERNEL_PCREL +#define LOAD_REG_ADDR(reg,name) \ + pla reg,name@pcrel + +#else #define LOAD_REG_ADDR(reg,name) \ - ld reg,name@got(r2) + addis reg,r2,name@toc@ha; \ + addi reg,reg,name@toc@l +#endif + +#ifdef CONFIG_PPC_BOOK3E_64 +/* + * This is used in register-constrained interrupt handlers. Not to be used + * by BOOK3S. ld complains with "got/toc optimization is not supported" if r2 + * is not used for the TOC offset, so use @got(tocreg). If the interrupt + * handlers saved r2 instead, LOAD_REG_ADDR could be used. + */ +#define LOAD_REG_ADDR_ALTTOC(reg,tocreg,name) \ + ld reg,name@got(tocreg) +#endif #define LOAD_REG_ADDRBASE(reg,name) LOAD_REG_ADDR(reg,name) #define ADDROFF(name) 0 @@ -363,6 +406,15 @@ n: /* offsets for stack frame layout */ #define LRSAVE 16 +/* + * GCC stack frames follow a different pattern on 32 vs 64. This can be used + * to make asm frames be consistent with C. + */ +#define PPC_CREATE_STACK_FRAME(size) \ + mflr r0; \ + std r0,16(r1); \ + stdu r1,-(size)(r1) + #else /* 32-bit */ #define LOAD_REG_IMMEDIATE(reg, expr) __LOAD_REG_IMMEDIATE_32 reg, expr @@ -379,20 +431,15 @@ n: /* offsets for stack frame layout */ #define LRSAVE 4 -#endif +#define PPC_CREATE_STACK_FRAME(size) \ + stwu r1,-(size)(r1); \ + mflr r0; \ + stw r0,(size+4)(r1) -/* various errata or part fixups */ -#ifdef CONFIG_PPC601_SYNC_FIX -#define SYNC sync; isync -#define SYNC_601 sync -#define ISYNC_601 isync -#else -#define SYNC -#define SYNC_601 -#define ISYNC_601 #endif -#if defined(CONFIG_PPC_CELL) || defined(CONFIG_PPC_FSL_BOOK3E) +/* various errata or part fixups */ +#if defined(CONFIG_PPC_CELL) || defined(CONFIG_PPC_E500) #define MFTB(dest) \ 90: mfspr dest, SPRN_TBRL; \ BEGIN_FTR_SECTION_NESTED(96); \ @@ -411,8 +458,7 @@ END_FTR_SECTION_NESTED(CPU_FTR_CELL_TB_BUG, CPU_FTR_CELL_TB_BUG, 96) #define MFTBU(dest) mfspr dest, SPRN_TBRU #endif -/* tlbsync is not implemented on 601 */ -#if !defined(CONFIG_SMP) || defined(CONFIG_PPC_BOOK3S_601) +#ifndef CONFIG_SMP #define TLBSYNC #else #define TLBSYNC tlbsync; sync @@ -506,15 +552,9 @@ END_FTR_SECTION_NESTED(CPU_FTR_CELL_TB_BUG, CPU_FTR_CELL_TB_BUG, 96) #endif #ifdef CONFIG_PPC_BOOK3S_64 -#define RFI rfid #define MTMSRD(r) mtmsrd r #define MTMSR_EERI(reg) mtmsrd reg,1 #else -#ifndef CONFIG_40x -#define RFI rfi -#else -#define RFI rfi; b . /* Prevent prefetch past rfi */ -#endif #define MTMSRD(r) mtmsr r #define MTMSR_EERI(reg) mtmsr reg #endif @@ -749,11 +789,7 @@ END_FTR_SECTION_NESTED(CPU_FTR_CELL_TB_BUG, CPU_FTR_CELL_TB_BUG, 96) #define evr30 30 #define evr31 31 -/* some stab codes */ -#define N_FUN 36 -#define N_RSYM 64 -#define N_SLINE 68 -#define N_SO 100 +#define RFSCV .long 0x4c0000a4 /* * Create an endian fixup trampoline @@ -770,11 +806,11 @@ END_FTR_SECTION_NESTED(CPU_FTR_CELL_TB_BUG, CPU_FTR_CELL_TB_BUG, 96) * kernel is built for. */ -#ifdef CONFIG_PPC_BOOK3E +#ifdef CONFIG_PPC_BOOK3E_64 #define FIXUP_ENDIAN #else /* - * This version may be used in in HV or non-HV context. + * This version may be used in HV or non-HV context. * MSR[EE] must be disabled. */ #define FIXUP_ENDIAN \ @@ -810,21 +846,26 @@ END_FTR_SECTION_NESTED(CPU_FTR_CELL_TB_BUG, CPU_FTR_CELL_TB_BUG, 96) .long 0x2402004c; /* hrfid */ \ 191: -#endif /* !CONFIG_PPC_BOOK3E */ +#endif /* !CONFIG_PPC_BOOK3E_64 */ #endif /* __ASSEMBLY__ */ -/* - * Helper macro for exception table entries - */ -#define EX_TABLE(_fault, _target) \ - stringify_in_c(.section __ex_table,"a";)\ - stringify_in_c(.balign 4;) \ - stringify_in_c(.long (_fault) - . ;) \ - stringify_in_c(.long (_target) - . ;) \ +#define SOFT_MASK_TABLE(_start, _end) \ + stringify_in_c(.section __soft_mask_table,"a";)\ + stringify_in_c(.balign 8;) \ + stringify_in_c(.llong (_start);) \ + stringify_in_c(.llong (_end);) \ stringify_in_c(.previous) -#ifdef CONFIG_PPC_FSL_BOOK3E +#define RESTART_TABLE(_start, _end, _target) \ + stringify_in_c(.section __restart_table,"a";)\ + stringify_in_c(.balign 8;) \ + stringify_in_c(.llong (_start);) \ + stringify_in_c(.llong (_end);) \ + stringify_in_c(.llong (_target);) \ + stringify_in_c(.previous) + +#ifdef CONFIG_PPC_E500 #define BTB_FLUSH(reg) \ lis reg,BUCSR_INIT@h; \ ori reg,reg,BUCSR_INIT@l; \ @@ -832,6 +873,14 @@ END_FTR_SECTION_NESTED(CPU_FTR_CELL_TB_BUG, CPU_FTR_CELL_TB_BUG, 96) isync; #else #define BTB_FLUSH(reg) -#endif /* CONFIG_PPC_FSL_BOOK3E */ +#endif /* CONFIG_PPC_E500 */ + +#if defined(CONFIG_PPC64_ELF_ABI_V1) +#define STACK_FRAME_PARAMS 48 +#elif defined(CONFIG_PPC64_ELF_ABI_V2) +#define STACK_FRAME_PARAMS 32 +#elif defined(CONFIG_PPC32) +#define STACK_FRAME_PARAMS 8 +#endif #endif /* _ASM_POWERPC_PPC_ASM_H */ diff --git a/arch/powerpc/include/asm/probes.h b/arch/powerpc/include/asm/probes.h index 84dd1addd434..e77a2ed7d938 100644 --- a/arch/powerpc/include/asm/probes.h +++ b/arch/powerpc/include/asm/probes.h @@ -8,9 +8,10 @@ * Copyright IBM Corporation, 2012 */ #include <linux/types.h> +#include <asm/disassemble.h> +#include <asm/ppc-opcode.h> -typedef u32 ppc_opcode_t; -#define BREAKPOINT_INSTRUCTION 0x7fe00008 /* trap */ +#define BREAKPOINT_INSTRUCTION PPC_RAW_TRAP() /* trap */ /* Trap definitions per ISA */ #define IS_TW(instr) (((instr) & 0xfc0007fe) == 0x7c000008) @@ -31,17 +32,52 @@ typedef u32 ppc_opcode_t; #define MSR_SINGLESTEP (MSR_SE) #endif +static inline bool can_single_step(u32 inst) +{ + switch (get_op(inst)) { + case OP_TRAP_64: return false; + case OP_TRAP: return false; + case OP_SC: return false; + case OP_19: + switch (get_xop(inst)) { + case OP_19_XOP_RFID: return false; + case OP_19_XOP_RFMCI: return false; + case OP_19_XOP_RFDI: return false; + case OP_19_XOP_RFI: return false; + case OP_19_XOP_RFCI: return false; + case OP_19_XOP_RFSCV: return false; + case OP_19_XOP_HRFID: return false; + case OP_19_XOP_URFID: return false; + case OP_19_XOP_STOP: return false; + case OP_19_XOP_DOZE: return false; + case OP_19_XOP_NAP: return false; + case OP_19_XOP_SLEEP: return false; + case OP_19_XOP_RVWINKLE: return false; + } + break; + case OP_31: + switch (get_xop(inst)) { + case OP_31_XOP_TRAP: return false; + case OP_31_XOP_TRAP_64: return false; + case OP_31_XOP_MTMSR: return false; + case OP_31_XOP_MTMSRD: return false; + } + break; + } + return true; +} + /* Enable single stepping for the current task */ static inline void enable_single_step(struct pt_regs *regs) { - regs->msr |= MSR_SINGLESTEP; + regs_set_return_msr(regs, regs->msr | MSR_SINGLESTEP); #ifdef CONFIG_PPC_ADV_DEBUG_REGS /* * We turn off Critical Input Exception(CE) to ensure that the single * step will be for the instruction we have the probe on; if we don't, * it is possible we'd get the single step reported for CE. */ - regs->msr &= ~MSR_CE; + regs_set_return_msr(regs, regs->msr & ~MSR_CE); mtspr(SPRN_DBCR0, mfspr(SPRN_DBCR0) | DBCR0_IC | DBCR0_IDM); #ifdef CONFIG_PPC_47x isync(); diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index a9993e7a443b..b2c51d337e60 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -6,6 +6,8 @@ * Copyright (C) 2001 PPC 64 Team, IBM Corp */ +#include <vdso/processor.h> + #include <asm/reg.h> #ifdef CONFIG_VSX @@ -63,14 +65,6 @@ extern int _chrp_type; #endif /* defined(__KERNEL__) && defined(CONFIG_PPC32) */ -/* Macros for adjusting thread priority (hardware multi-threading) */ -#define HMT_very_low() asm volatile("or 31,31,31 # very low priority") -#define HMT_low() asm volatile("or 1,1,1 # low priority") -#define HMT_medium_low() asm volatile("or 6,6,6 # medium low priority") -#define HMT_medium() asm volatile("or 2,2,2 # medium priority") -#define HMT_medium_high() asm volatile("or 5,5,5 # medium high priority") -#define HMT_high() asm volatile("or 3,3,3 # high priority") - #ifdef __KERNEL__ #ifdef CONFIG_PPC64 @@ -81,11 +75,6 @@ extern int _chrp_type; struct task_struct; void start_thread(struct pt_regs *regs, unsigned long fdptr, unsigned long sp); -void release_thread(struct task_struct *); - -typedef struct { - unsigned long seg; -} mm_segment_t; #define TS_FPR(i) fp_state.fpr[i][TS_FPROFFSET] #define TS_CKFPR(i) ckfp_state.fpr[i][TS_FPROFFSET] @@ -148,36 +137,43 @@ struct thread_struct { unsigned long ksp_vsid; #endif struct pt_regs *regs; /* Pointer to saved register state */ - mm_segment_t addr_limit; /* for get_fs() validation */ #ifdef CONFIG_BOOKE /* BookE base exception scratch space; align on cacheline */ unsigned long normsave[8] ____cacheline_aligned; #endif #ifdef CONFIG_PPC32 void *pgdir; /* root of page-table tree */ - unsigned long ksp_limit; /* if ksp <= ksp_limit stack overflow */ #ifdef CONFIG_PPC_RTAS unsigned long rtas_sp; /* stack pointer for when in RTAS */ #endif -#endif #if defined(CONFIG_PPC_BOOK3S_32) && defined(CONFIG_PPC_KUAP) unsigned long kuap; /* opened segments for user access */ #endif + unsigned long srr0; + unsigned long srr1; + unsigned long dar; + unsigned long dsisr; +#ifdef CONFIG_PPC_BOOK3S_32 + unsigned long r0, r3, r4, r5, r6, r8, r9, r11; + unsigned long lr, ctr; + unsigned long sr0; +#endif +#endif /* CONFIG_PPC32 */ +#if defined(CONFIG_BOOKE_OR_40x) && defined(CONFIG_PPC_KUAP) + unsigned long pid; /* value written in PID reg. at interrupt exit */ +#endif /* Debug Registers */ struct debug_reg debug; +#ifdef CONFIG_PPC_FPU_REGS struct thread_fp_state fp_state; struct thread_fp_state *fp_save_area; +#endif int fpexc_mode; /* floating-point exception mode */ unsigned int align_ctl; /* alignment handling control */ #ifdef CONFIG_HAVE_HW_BREAKPOINT - struct perf_event *ptrace_bps[HBP_NUM]; - /* - * Helps identify source of single-step exception and subsequent - * hw-breakpoint enablement - */ - struct perf_event *last_hit_ubp; + struct perf_event *ptrace_bps[HBP_NUM_MAX]; #endif /* CONFIG_HAVE_HW_BREAKPOINT */ - struct arch_hw_breakpoint hw_brk; /* info on the hardware breakpoint */ + struct arch_hw_breakpoint hw_brk[HBP_NUM_MAX]; /* hardware breakpoint info */ unsigned long trap_nr; /* last trap # on this thread */ u8 load_slb; /* Ages out SLB preload cache entries */ u8 load_fp; @@ -193,8 +189,10 @@ struct thread_struct { int used_vsr; /* set if process has used VSX */ #endif /* CONFIG_VSX */ #ifdef CONFIG_SPE - unsigned long evr[32]; /* upper 32-bits of SPE regs */ - u64 acc; /* Accumulator */ + struct_group(spe, + unsigned long evr[32]; /* upper 32-bits of SPE regs */ + u64 acc; /* Accumulator */ + ); unsigned long spefscr; /* SPE & eFP status */ unsigned long spefscr_last; /* SPEFSCR value on last prctl call or trap return */ @@ -210,6 +208,7 @@ struct thread_struct { unsigned long tm_tar; unsigned long tm_ppr; unsigned long tm_dscr; + unsigned long tm_amr; /* * Checkpointed FP and VSX 0-31 register set. @@ -224,11 +223,6 @@ struct thread_struct { struct thread_vr_state ckvr_state; /* Checkpointed VR state */ unsigned long ckvrsave; /* Checkpointed VRSAVE */ #endif /* CONFIG_PPC_TRANSACTIONAL_MEM */ -#ifdef CONFIG_PPC_MEM_KEYS - unsigned long amr; - unsigned long iamr; - unsigned long uamor; -#endif #ifdef CONFIG_KVM_BOOK3S_32_HANDLER void* kvm_shadow_vcpu; /* KVM internal data */ #endif /* CONFIG_KVM_BOOK3S_32_HANDLER */ @@ -262,7 +256,11 @@ struct thread_struct { unsigned mmcr0; unsigned used_ebb; - unsigned int used_vas; + unsigned long mmcr3; + unsigned long sier2; + unsigned long sier3; + unsigned long hashkeyr; + #endif }; @@ -279,28 +277,39 @@ struct thread_struct { #define SPEFSCR_INIT #endif -#ifdef CONFIG_PPC32 +#ifdef CONFIG_PPC_BOOK3S_32 +#define SR0_INIT .sr0 = IS_ENABLED(CONFIG_PPC_KUEP) ? SR_NX : 0, +#else +#define SR0_INIT +#endif + +#if defined(CONFIG_PPC_BOOK3S_32) && defined(CONFIG_PPC_KUAP) +#define INIT_THREAD { \ + .ksp = INIT_SP, \ + .pgdir = swapper_pg_dir, \ + .kuap = ~0UL, /* KUAP_NONE */ \ + .fpexc_mode = MSR_FE0 | MSR_FE1, \ + SPEFSCR_INIT \ + SR0_INIT \ +} +#elif defined(CONFIG_PPC32) #define INIT_THREAD { \ .ksp = INIT_SP, \ - .ksp_limit = INIT_SP_LIMIT, \ - .addr_limit = KERNEL_DS, \ .pgdir = swapper_pg_dir, \ .fpexc_mode = MSR_FE0 | MSR_FE1, \ SPEFSCR_INIT \ + SR0_INIT \ } #else #define INIT_THREAD { \ .ksp = INIT_SP, \ - .regs = (struct pt_regs *)INIT_SP - 1, /* XXX bogus, I think */ \ - .addr_limit = KERNEL_DS, \ .fpexc_mode = 0, \ - .fscr = FSCR_TAR | FSCR_EBB \ } #endif -#define task_pt_regs(tsk) ((struct pt_regs *)(tsk)->thread.regs) +#define task_pt_regs(tsk) ((tsk)->thread.regs) -unsigned long get_wchan(struct task_struct *p); +unsigned long __get_wchan(struct task_struct *p); #define KSTK_EIP(tsk) ((tsk)->thread.regs? (tsk)->thread.regs->nip: 0) #define KSTK_ESP(tsk) ((tsk)->thread.regs? (tsk)->thread.regs->gpr[1]: 0) @@ -340,39 +349,45 @@ static inline unsigned long __pack_fe01(unsigned int fpmode) } #ifdef CONFIG_PPC64 -#define cpu_relax() do { HMT_low(); HMT_medium(); barrier(); } while (0) - -#define spin_begin() HMT_low() -#define spin_cpu_relax() barrier() +#define spin_begin() \ + asm volatile(ASM_FTR_IFCLR( \ + "or 1,1,1", /* HMT_LOW */ \ + "nop", /* v3.1 uses pause_short in cpu_relax instead */ \ + %0) :: "i" (CPU_FTR_ARCH_31) : "memory") -#define spin_end() HMT_medium() +#define spin_cpu_relax() \ + asm volatile(ASM_FTR_IFCLR( \ + "nop", /* Before v3.1 use priority nops in spin_begin/end */ \ + PPC_WAIT(2, 0), /* aka pause_short */ \ + %0) :: "i" (CPU_FTR_ARCH_31) : "memory") -#define spin_until_cond(cond) \ -do { \ - if (unlikely(!(cond))) { \ - spin_begin(); \ - do { \ - spin_cpu_relax(); \ - } while (!(cond)); \ - spin_end(); \ - } \ -} while (0) +#define spin_end() \ + asm volatile(ASM_FTR_IFCLR( \ + "or 2,2,2", /* HMT_MEDIUM */ \ + "nop", \ + %0) :: "i" (CPU_FTR_ARCH_31) : "memory") -#else -#define cpu_relax() barrier() #endif -/* Check that a certain kernel stack pointer is valid in task_struct p */ -int validate_sp(unsigned long sp, struct task_struct *p, - unsigned long nbytes); +/* + * Check that a certain kernel stack pointer is a valid (minimum sized) + * stack frame in task_struct p. + */ +int validate_sp(unsigned long sp, struct task_struct *p); + +/* + * validate the stack frame of a particular minimum size, used for when we are + * looking at a certain object in the stack beyond the minimum. + */ +int validate_sp_size(unsigned long sp, struct task_struct *p, + unsigned long nbytes); /* * Prefetch macros. */ #define ARCH_HAS_PREFETCH #define ARCH_HAS_PREFETCHW -#define ARCH_HAS_SPINLOCK_PREFETCH static inline void prefetch(const void *x) { @@ -390,28 +405,14 @@ static inline void prefetchw(const void *x) __asm__ __volatile__ ("dcbtst 0,%0" : : "r" (x)); } -#define spin_lock_prefetch(x) prefetchw(x) - -#define HAVE_ARCH_PICK_MMAP_LAYOUT - -#ifdef CONFIG_PPC64 -static inline unsigned long get_clean_sp(unsigned long sp, int is_32) -{ - if (is_32) - return sp & 0x0ffffffffUL; - return sp; -} -#else -static inline unsigned long get_clean_sp(unsigned long sp, int is_32) -{ - return sp; -} -#endif - /* asm stubs */ extern unsigned long isa300_idle_stop_noloss(unsigned long psscr_val); extern unsigned long isa300_idle_stop_mayloss(unsigned long psscr_val); extern unsigned long isa206_idle_insn_mayloss(unsigned long type); +#ifdef CONFIG_PPC_970_NAP +extern void power4_idle_nap(void); +void power4_idle_nap_return(void); +#endif extern unsigned long cpuidle_disable; enum idle_boot_override {IDLE_NO_OVERRIDE = 0, IDLE_POWERSAVE_OFF}; @@ -419,16 +420,12 @@ enum idle_boot_override {IDLE_NO_OVERRIDE = 0, IDLE_POWERSAVE_OFF}; extern int powersave_nap; /* set if nap mode can be used in idle loop */ extern void power7_idle_type(unsigned long type); -extern void power9_idle_type(unsigned long stop_psscr_val, +extern void arch300_idle_type(unsigned long stop_psscr_val, unsigned long stop_psscr_mask); +void pnv_power9_force_smt4_catch(void); +void pnv_power9_force_smt4_release(void); -extern void flush_instruction_cache(void); -extern void hard_reset_now(void); -extern void poweroff_now(void); extern int fix_alignment(struct pt_regs *); -extern void cvt_fd(float *from, double *to); -extern void cvt_df(double *from, float *to); -extern void _nmask_and_or_msr(unsigned long nmask, unsigned long or_val); #ifdef CONFIG_PPC64 /* @@ -441,6 +438,16 @@ extern void _nmask_and_or_msr(unsigned long nmask, unsigned long or_val); #define NET_IP_ALIGN 0 #endif +int do_mathemu(struct pt_regs *regs); +int do_spe_mathemu(struct pt_regs *regs); +int speround_handler(struct pt_regs *regs); + +/* VMX copying */ +int enter_vmx_usercopy(void); +int exit_vmx_usercopy(void); +int enter_vmx_ops(void); +void *exit_vmx_ops(void *dest); + #endif /* __KERNEL__ */ #endif /* __ASSEMBLY__ */ #endif /* _ASM_POWERPC_PROCESSOR_H */ diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h index 94e3fd54f2c8..c0107d8ddd8c 100644 --- a/arch/powerpc/include/asm/prom.h +++ b/arch/powerpc/include/asm/prom.h @@ -12,15 +12,10 @@ * Updates for PPC64 by Peter Bergner & David Engebretsen, IBM Corp. */ #include <linux/types.h> -#include <asm/irq.h> -#include <linux/atomic.h> +#include <asm/firmware.h> -/* These includes should be removed once implicit includes are cleaned up. */ -#include <linux/of.h> -#include <linux/of_fdt.h> -#include <linux/of_address.h> -#include <linux/of_irq.h> -#include <linux/platform_device.h> +struct device_node; +struct property; #define OF_DT_BEGIN_NODE 0x1 /* Start of node, full name */ #define OF_DT_END_NODE 0x2 /* End node */ @@ -90,6 +85,7 @@ struct of_drc_info { extern int of_read_drc_info_cell(struct property **prop, const __be32 **curval, struct of_drc_info *data); +extern unsigned int boot_cpu_node_count; /* * There are two methods for telling firmware what our capabilities are. @@ -117,6 +113,7 @@ extern int of_read_drc_info_cell(struct property **prop, #define OV1_PPC_2_07 0x01 /* set if we support PowerPC 2.07 */ #define OV1_PPC_3_00 0x80 /* set if we support PowerPC 3.00 */ +#define OV1_PPC_3_1 0x40 /* set if we support PowerPC 3.1 */ /* Option vector 2: Open Firmware options supported */ #define OV2_REAL_MODE 0x20 /* set if we want OF in real mode */ @@ -146,8 +143,9 @@ extern int of_read_drc_info_cell(struct property **prop, #define OV5_MSI 0x0201 /* PCIe/MSI support */ #define OV5_CMO 0x0480 /* Cooperative Memory Overcommitment */ #define OV5_XCMO 0x0440 /* Page Coalescing */ -#define OV5_TYPE1_AFFINITY 0x0580 /* Type 1 NUMA affinity */ +#define OV5_FORM1_AFFINITY 0x0580 /* FORM1 NUMA affinity */ #define OV5_PRRN 0x0540 /* Platform Resource Reassignment */ +#define OV5_FORM2_AFFINITY 0x0520 /* Form2 NUMA affinity */ #define OV5_HP_EVT 0x0604 /* Hot Plug Event support */ #define OV5_RESIZE_HPT 0x0601 /* Hash Page Table resizing */ #define OV5_PFO_HW_RNG 0x1180 /* PFO Random Number Generator */ diff --git a/arch/powerpc/include/asm/ps3.h b/arch/powerpc/include/asm/ps3.h index cb89e4bf55ce..d13d8fdc3411 100644 --- a/arch/powerpc/include/asm/ps3.h +++ b/arch/powerpc/include/asm/ps3.h @@ -71,6 +71,7 @@ struct ps3_dma_region_ops; * @bus_addr: The 'translated' bus address of the region. * @len: The length in bytes of the region. * @offset: The offset from the start of memory of the region. + * @dma_mask: Device dma_mask. * @ioid: The IOID of the device who owns this region * @chunk_list: Opaque variable used by the ioc page manager. * @region_ops: struct ps3_dma_region_ops - dma region operations @@ -85,6 +86,7 @@ struct ps3_dma_region { enum ps3_dma_region_type region_type; unsigned long len; unsigned long offset; + u64 dma_mask; /* driver variables (set by ps3_dma_region_create) */ unsigned long bus_addr; @@ -232,7 +234,7 @@ enum lv1_result { static inline const char* ps3_result(int result) { -#if defined(DEBUG) || defined(PS3_VERBOSE_RESULT) +#if defined(DEBUG) || defined(PS3_VERBOSE_RESULT) || defined(CONFIG_PS3_VERBOSE_RESULT) switch (result) { case LV1_SUCCESS: return "LV1_SUCCESS (0)"; @@ -378,8 +380,8 @@ struct ps3_system_bus_driver { enum ps3_match_sub_id match_sub_id; struct device_driver core; int (*probe)(struct ps3_system_bus_device *); - int (*remove)(struct ps3_system_bus_device *); - int (*shutdown)(struct ps3_system_bus_device *); + void (*remove)(struct ps3_system_bus_device *); + void (*shutdown)(struct ps3_system_bus_device *); /* int (*suspend)(struct ps3_system_bus_device *, pm_message_t); */ /* int (*resume)(struct ps3_system_bus_device *); */ }; @@ -394,7 +396,7 @@ static inline struct ps3_system_bus_driver *ps3_drv_to_system_bus_drv( return container_of(_drv, struct ps3_system_bus_driver, core); } static inline struct ps3_system_bus_device *ps3_dev_to_system_bus_dev( - struct device *_dev) + const struct device *_dev) { return container_of(_dev, struct ps3_system_bus_device, core); } @@ -423,10 +425,6 @@ static inline void *ps3_system_bus_get_drvdata( return dev_get_drvdata(&dev->core); } -/* These two need global scope for get_arch_dma_ops(). */ - -extern struct bus_type ps3_system_bus_type; - /* system manager */ struct ps3_sys_manager_ops { @@ -516,4 +514,10 @@ u64 ps3_get_spe_id(void *arg); void ps3_early_mm_init(void); +#ifdef CONFIG_PPC_EARLY_DEBUG_PS3GELIC +void udbg_shutdown_ps3gelic(void); +#else +static inline void udbg_shutdown_ps3gelic(void) {} +#endif + #endif diff --git a/arch/powerpc/include/asm/ps3av.h b/arch/powerpc/include/asm/ps3av.h index 82db78fc169d..c8b0f2ffcd35 100644 --- a/arch/powerpc/include/asm/ps3av.h +++ b/arch/powerpc/include/asm/ps3av.h @@ -726,6 +726,4 @@ extern int ps3av_video_mode2res(u32, u32 *, u32 *); extern int ps3av_video_mute(int); extern int ps3av_audio_mute(int); extern int ps3av_audio_mute_analog(int); -extern int ps3av_dev_open(void); -extern int ps3av_dev_close(void); #endif /* _ASM_POWERPC_PS3AV_H_ */ diff --git a/arch/powerpc/include/asm/pte-walk.h b/arch/powerpc/include/asm/pte-walk.h index 33fa5dd8ee6a..73c22c579a79 100644 --- a/arch/powerpc/include/asm/pte-walk.h +++ b/arch/powerpc/include/asm/pte-walk.h @@ -31,29 +31,33 @@ static inline pte_t *find_init_mm_pte(unsigned long ea, unsigned *hshift) pgd_t *pgdir = init_mm.pgd; return __find_linux_pte(pgdir, ea, NULL, hshift); } + /* - * This is what we should always use. Any other lockless page table lookup needs - * careful audit against THP split. + * Convert a kernel vmap virtual address (vmalloc or ioremap space) to a + * physical address, without taking locks. This can be used in real-mode. */ -static inline pte_t *find_current_mm_pte(pgd_t *pgdir, unsigned long ea, - bool *is_thp, unsigned *hshift) +static inline phys_addr_t ppc_find_vmap_phys(unsigned long addr) { - pte_t *pte; - - VM_WARN(!arch_irqs_disabled(), "%s called with irq enabled\n", __func__); - VM_WARN(pgdir != current->mm->pgd, - "%s lock less page table lookup called on wrong mm\n", __func__); - pte = __find_linux_pte(pgdir, ea, is_thp, hshift); + pte_t *ptep; + phys_addr_t pa; + int hugepage_shift; -#if defined(CONFIG_DEBUG_VM) && \ - !(defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)) /* - * We should not find huge page if these configs are not enabled. + * init_mm does not free page tables, and does not do THP. It may + * have huge pages from huge vmalloc / ioremap etc. */ - if (hshift) - WARN_ON(*hshift); -#endif - return pte; + ptep = find_init_mm_pte(addr, &hugepage_shift); + if (WARN_ON(!ptep)) + return 0; + + pa = PFN_PHYS(pte_pfn(*ptep)); + + if (!hugepage_shift) + hugepage_shift = PAGE_SHIFT; + + pa |= addr & ((1ul << hugepage_shift) - 1); + + return pa; } #endif /* _ASM_POWERPC_PTE_WALK_H */ diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h index ee3ada66deb5..ea8f91fbc62f 100644 --- a/arch/powerpc/include/asm/ptrace.h +++ b/arch/powerpc/include/asm/ptrace.h @@ -19,8 +19,10 @@ #ifndef _ASM_POWERPC_PTRACE_H #define _ASM_POWERPC_PTRACE_H +#include <linux/err.h> #include <uapi/asm/ptrace.h> #include <asm/asm-const.h> +#include <asm/reg.h> #ifndef __ASSEMBLY__ struct pt_regs @@ -42,26 +44,66 @@ struct pt_regs unsigned long mq; #endif unsigned long trap; - unsigned long dar; - unsigned long dsisr; + union { + unsigned long dar; + unsigned long dear; + }; + union { + unsigned long dsisr; + unsigned long esr; + }; unsigned long result; }; }; - +#if defined(CONFIG_PPC64) || defined(CONFIG_PPC_KUAP) union { struct { #ifdef CONFIG_PPC64 unsigned long ppr; + unsigned long exit_result; #endif + union { #ifdef CONFIG_PPC_KUAP - unsigned long kuap; + unsigned long kuap; +#endif +#ifdef CONFIG_PPC_PKEY + unsigned long amr; +#endif + }; +#ifdef CONFIG_PPC_PKEY + unsigned long iamr; #endif }; - unsigned long __pad[2]; /* Maintain 16 byte interrupt stack alignment */ + unsigned long __pad[4]; /* Maintain 16 byte interrupt stack alignment */ + }; +#endif +#if defined(CONFIG_PPC32) && defined(CONFIG_BOOKE) + struct { /* Must be a multiple of 16 bytes */ + unsigned long mas0; + unsigned long mas1; + unsigned long mas2; + unsigned long mas3; + unsigned long mas6; + unsigned long mas7; + unsigned long srr0; + unsigned long srr1; + unsigned long csrr0; + unsigned long csrr1; + unsigned long dsrr0; + unsigned long dsrr1; }; +#endif }; #endif + +// Always displays as "REGS" in memory dumps +#ifdef CONFIG_CPU_BIG_ENDIAN +#define STACK_FRAME_REGS_MARKER ASM_CONST(0x52454753) +#else +#define STACK_FRAME_REGS_MARKER ASM_CONST(0x53474552) +#endif + #ifdef __powerpc64__ /* @@ -76,17 +118,27 @@ struct pt_regs #define USER_REDZONE_SIZE 512 #define KERNEL_REDZONE_SIZE 288 -#define STACK_FRAME_OVERHEAD 112 /* size of minimum stack frame */ #define STACK_FRAME_LR_SAVE 2 /* Location of LR in stack frame */ -#define STACK_FRAME_REGS_MARKER ASM_CONST(0x7265677368657265) -#define STACK_INT_FRAME_SIZE (sizeof(struct pt_regs) + \ - STACK_FRAME_OVERHEAD + KERNEL_REDZONE_SIZE) -#define STACK_FRAME_MARKER 12 -#ifdef PPC64_ELF_ABI_v2 +#ifdef CONFIG_PPC64_ELF_ABI_V2 #define STACK_FRAME_MIN_SIZE 32 +#define STACK_USER_INT_FRAME_SIZE (sizeof(struct pt_regs) + STACK_FRAME_MIN_SIZE + 16) +#define STACK_INT_FRAME_REGS (STACK_FRAME_MIN_SIZE + 16) +#define STACK_INT_FRAME_MARKER STACK_FRAME_MIN_SIZE +#define STACK_SWITCH_FRAME_SIZE (sizeof(struct pt_regs) + STACK_FRAME_MIN_SIZE + 16) +#define STACK_SWITCH_FRAME_REGS (STACK_FRAME_MIN_SIZE + 16) #else -#define STACK_FRAME_MIN_SIZE STACK_FRAME_OVERHEAD +/* + * The ELFv1 ABI specifies 48 bytes plus a minimum 64 byte parameter save + * area. This parameter area is not used by calls to C from interrupt entry, + * so the second from last one of those is used for the frame marker. + */ +#define STACK_FRAME_MIN_SIZE 112 +#define STACK_USER_INT_FRAME_SIZE (sizeof(struct pt_regs) + STACK_FRAME_MIN_SIZE) +#define STACK_INT_FRAME_REGS STACK_FRAME_MIN_SIZE +#define STACK_INT_FRAME_MARKER (STACK_FRAME_MIN_SIZE - 16) +#define STACK_SWITCH_FRAME_SIZE (sizeof(struct pt_regs) + STACK_FRAME_MIN_SIZE) +#define STACK_SWITCH_FRAME_REGS STACK_FRAME_MIN_SIZE #endif /* Size of dummy stack frame allocated when calling signal handler. */ @@ -97,19 +149,58 @@ struct pt_regs #define USER_REDZONE_SIZE 0 #define KERNEL_REDZONE_SIZE 0 -#define STACK_FRAME_OVERHEAD 16 /* size of minimum stack frame */ +#define STACK_FRAME_MIN_SIZE 16 #define STACK_FRAME_LR_SAVE 1 /* Location of LR in stack frame */ -#define STACK_FRAME_REGS_MARKER ASM_CONST(0x72656773) -#define STACK_INT_FRAME_SIZE (sizeof(struct pt_regs) + STACK_FRAME_OVERHEAD) -#define STACK_FRAME_MARKER 2 -#define STACK_FRAME_MIN_SIZE STACK_FRAME_OVERHEAD +#define STACK_USER_INT_FRAME_SIZE (sizeof(struct pt_regs) + STACK_FRAME_MIN_SIZE) +#define STACK_INT_FRAME_REGS STACK_FRAME_MIN_SIZE +#define STACK_INT_FRAME_MARKER (STACK_FRAME_MIN_SIZE - 8) +#define STACK_SWITCH_FRAME_SIZE (sizeof(struct pt_regs) + STACK_FRAME_MIN_SIZE) +#define STACK_SWITCH_FRAME_REGS STACK_FRAME_MIN_SIZE /* Size of stack frame allocated when calling signal handler. */ #define __SIGNAL_FRAMESIZE 64 #endif /* __powerpc64__ */ +#define STACK_INT_FRAME_SIZE (KERNEL_REDZONE_SIZE + STACK_USER_INT_FRAME_SIZE) +#define STACK_INT_FRAME_MARKER_LONGS (STACK_INT_FRAME_MARKER/sizeof(long)) + #ifndef __ASSEMBLY__ +#include <asm/paca.h> + +#ifdef CONFIG_SMP +extern unsigned long profile_pc(struct pt_regs *regs); +#else +#define profile_pc(regs) instruction_pointer(regs) +#endif + +long do_syscall_trace_enter(struct pt_regs *regs); +void do_syscall_trace_leave(struct pt_regs *regs); + +static inline void set_return_regs_changed(void) +{ +#ifdef CONFIG_PPC_BOOK3S_64 + WRITE_ONCE(local_paca->hsrr_valid, 0); + WRITE_ONCE(local_paca->srr_valid, 0); +#endif +} + +static inline void regs_set_return_ip(struct pt_regs *regs, unsigned long ip) +{ + regs->nip = ip; + set_return_regs_changed(); +} + +static inline void regs_set_return_msr(struct pt_regs *regs, unsigned long msr) +{ + regs->msr = msr; + set_return_regs_changed(); +} + +static inline void regs_add_return_ip(struct pt_regs *regs, long offset) +{ + regs_set_return_ip(regs, regs->nip + offset); +} static inline unsigned long instruction_pointer(struct pt_regs *regs) { @@ -119,7 +210,7 @@ static inline unsigned long instruction_pointer(struct pt_regs *regs) static inline void instruction_pointer_set(struct pt_regs *regs, unsigned long val) { - regs->nip = val; + regs_set_return_ip(regs, val); } static inline unsigned long user_stack_pointer(struct pt_regs *regs) @@ -132,20 +223,80 @@ static inline unsigned long frame_pointer(struct pt_regs *regs) return 0; } -#ifdef CONFIG_SMP -extern unsigned long profile_pc(struct pt_regs *regs); +#define user_mode(regs) (((regs)->msr & MSR_PR) != 0) + +#define force_successful_syscall_return() \ + do { \ + set_thread_flag(TIF_NOERROR); \ + } while(0) + +#define current_pt_regs() \ + ((struct pt_regs *)((unsigned long)task_stack_page(current) + THREAD_SIZE) - 1) + +/* + * The 4 low bits (0xf) are available as flags to overload the trap word, + * because interrupt vectors have minimum alignment of 0x10. TRAP_FLAGS_MASK + * must cover the bits used as flags, including bit 0 which is used as the + * "norestart" bit. + */ +#ifdef __powerpc64__ +#define TRAP_FLAGS_MASK 0x1 #else -#define profile_pc(regs) instruction_pointer(regs) -#endif +/* + * On 4xx we use bit 1 in the trap word to indicate whether the exception + * is a critical exception (1 means it is). + */ +#define TRAP_FLAGS_MASK 0xf +#define IS_CRITICAL_EXC(regs) (((regs)->trap & 2) != 0) +#define IS_MCHECK_EXC(regs) (((regs)->trap & 4) != 0) +#define IS_DEBUG_EXC(regs) (((regs)->trap & 8) != 0) +#endif /* __powerpc64__ */ +#define TRAP(regs) ((regs)->trap & ~TRAP_FLAGS_MASK) + +static __always_inline void set_trap(struct pt_regs *regs, unsigned long val) +{ + regs->trap = (regs->trap & TRAP_FLAGS_MASK) | (val & ~TRAP_FLAGS_MASK); +} + +static inline bool trap_is_scv(struct pt_regs *regs) +{ + return (IS_ENABLED(CONFIG_PPC_BOOK3S_64) && TRAP(regs) == 0x3000); +} + +static inline bool trap_is_unsupported_scv(struct pt_regs *regs) +{ + return IS_ENABLED(CONFIG_PPC_BOOK3S_64) && TRAP(regs) == 0x7ff0; +} + +static inline bool trap_is_syscall(struct pt_regs *regs) +{ + return (trap_is_scv(regs) || TRAP(regs) == 0xc00); +} + +static inline bool trap_norestart(struct pt_regs *regs) +{ + return regs->trap & 0x1; +} + +static __always_inline void set_trap_norestart(struct pt_regs *regs) +{ + regs->trap |= 0x1; +} #define kernel_stack_pointer(regs) ((regs)->gpr[1]) static inline int is_syscall_success(struct pt_regs *regs) { - return !(regs->ccr & 0x10000000); + if (trap_is_scv(regs)) + return !IS_ERR_VALUE((unsigned long)regs->gpr[3]); + else + return !(regs->ccr & 0x10000000); } static inline long regs_return_value(struct pt_regs *regs) { + if (trap_is_scv(regs)) + return regs->gpr[3]; + if (is_syscall_success(regs)) return regs->gpr[3]; else @@ -157,57 +308,30 @@ static inline void regs_set_return_value(struct pt_regs *regs, unsigned long rc) regs->gpr[3] = rc; } -#ifdef __powerpc64__ -#define user_mode(regs) ((((regs)->msr) >> MSR_PR_LG) & 0x1) -#else -#define user_mode(regs) (((regs)->msr & MSR_PR) != 0) -#endif +static inline bool cpu_has_msr_ri(void) +{ + return !IS_ENABLED(CONFIG_BOOKE_OR_40x); +} -#define force_successful_syscall_return() \ - do { \ - set_thread_flag(TIF_NOERROR); \ - } while(0) +static inline bool regs_is_unrecoverable(struct pt_regs *regs) +{ + return unlikely(cpu_has_msr_ri() && !(regs->msr & MSR_RI)); +} -struct task_struct; -extern int ptrace_get_reg(struct task_struct *task, int regno, - unsigned long *data); -extern int ptrace_put_reg(struct task_struct *task, int regno, - unsigned long data); +static inline void regs_set_recoverable(struct pt_regs *regs) +{ + if (cpu_has_msr_ri()) + regs_set_return_msr(regs, regs->msr | MSR_RI); +} -#define current_pt_regs() \ - ((struct pt_regs *)((unsigned long)task_stack_page(current) + THREAD_SIZE) - 1) -/* - * We use the least-significant bit of the trap field to indicate - * whether we have saved the full set of registers, or only a - * partial set. A 1 there means the partial set. - * On 4xx we use the next bit to indicate whether the exception - * is a critical exception (1 means it is). - */ -#define FULL_REGS(regs) (((regs)->trap & 1) == 0) -#ifndef __powerpc64__ -#define IS_CRITICAL_EXC(regs) (((regs)->trap & 2) != 0) -#define IS_MCHECK_EXC(regs) (((regs)->trap & 4) != 0) -#define IS_DEBUG_EXC(regs) (((regs)->trap & 8) != 0) -#endif /* ! __powerpc64__ */ -#define TRAP(regs) ((regs)->trap & ~0xF) -#ifdef __powerpc64__ -#define NV_REG_POISON 0xdeadbeefdeadbeefUL -#define CHECK_FULL_REGS(regs) BUG_ON(regs->trap & 1) -#else -#define NV_REG_POISON 0xdeadbeef -#define CHECK_FULL_REGS(regs) \ -do { \ - if ((regs)->trap & 1) \ - printk(KERN_CRIT "%s: partial register set\n", __func__); \ -} while (0) -#endif /* __powerpc64__ */ +static inline void regs_set_unrecoverable(struct pt_regs *regs) +{ + if (cpu_has_msr_ri()) + regs_set_return_msr(regs, regs->msr & ~MSR_RI); +} #define arch_has_single_step() (1) -#ifndef CONFIG_BOOK3S_601 #define arch_has_block_step() (true) -#else -#define arch_has_block_step() (false) -#endif #define ARCH_HAS_USER_SINGLE_STEP_REPORT /* @@ -273,9 +397,28 @@ static inline unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, return 0; } +/** + * regs_get_kernel_argument() - get Nth function argument in kernel + * @regs: pt_regs of that context + * @n: function argument number (start from 0) + * + * We support up to 8 arguments and assume they are sent in through the GPRs. + * This will fail for fp/vector arguments, but those aren't usually found in + * kernel code. This is expected to be called from kprobes or ftrace with regs. + */ +static inline unsigned long regs_get_kernel_argument(struct pt_regs *regs, unsigned int n) +{ +#define NR_REG_ARGUMENTS 8 + if (n < NR_REG_ARGUMENTS) + return regs_get_register(regs, offsetof(struct pt_regs, gpr[3 + n])); + return 0; +} + #endif /* __ASSEMBLY__ */ #ifndef __powerpc64__ +/* We need PT_SOFTE defined at all time to avoid #ifdefs */ +#define PT_SOFTE PT_MQ #else /* __powerpc64__ */ #define PT_FPSCR32 (PT_FPR0 + 2*32 + 1) /* each FP reg occupies 2 32-bit userspace slots */ #define PT_VR0_32 164 /* each Vector reg occupies 4 slots in 32-bit */ diff --git a/arch/powerpc/include/asm/qspinlock.h b/arch/powerpc/include/asm/qspinlock.h new file mode 100644 index 000000000000..28a53fb69b38 --- /dev/null +++ b/arch/powerpc/include/asm/qspinlock.h @@ -0,0 +1,174 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_POWERPC_QSPINLOCK_H +#define _ASM_POWERPC_QSPINLOCK_H + +#include <linux/compiler.h> +#include <asm/qspinlock_types.h> +#include <asm/paravirt.h> + +#ifdef CONFIG_PPC64 +/* + * Use the EH=1 hint for accesses that result in the lock being acquired. + * The hardware is supposed to optimise this pattern by holding the lock + * cacheline longer, and releasing when a store to the same memory (the + * unlock) is performed. + */ +#define _Q_SPIN_EH_HINT 1 +#else +#define _Q_SPIN_EH_HINT 0 +#endif + +/* + * The trylock itself may steal. This makes trylocks slightly stronger, and + * makes locks slightly more efficient when stealing. + * + * This is compile-time, so if true then there may always be stealers, so the + * nosteal paths become unused. + */ +#define _Q_SPIN_TRY_LOCK_STEAL 1 + +/* + * Put a speculation barrier after testing the lock/node and finding it + * busy. Try to prevent pointless speculation in slow paths. + * + * Slows down the lockstorm microbenchmark with no stealing, where locking + * is purely FIFO through the queue. May have more benefit in real workload + * where speculating into the wrong place could have a greater cost. + */ +#define _Q_SPIN_SPEC_BARRIER 0 + +#ifdef CONFIG_PPC64 +/* + * Execute a miso instruction after passing the MCS lock ownership to the + * queue head. Miso is intended to make stores visible to other CPUs sooner. + * + * This seems to make the lockstorm microbenchmark nospin test go slightly + * faster on POWER10, but disable for now. + */ +#define _Q_SPIN_MISO 0 +#else +#define _Q_SPIN_MISO 0 +#endif + +#ifdef CONFIG_PPC64 +/* + * This executes miso after an unlock of the lock word, having ownership + * pass to the next CPU sooner. This will slow the uncontended path to some + * degree. Not evidence it helps yet. + */ +#define _Q_SPIN_MISO_UNLOCK 0 +#else +#define _Q_SPIN_MISO_UNLOCK 0 +#endif + +/* + * Seems to slow down lockstorm microbenchmark, suspect queue node just + * has to become shared again right afterwards when its waiter spins on + * the lock field. + */ +#define _Q_SPIN_PREFETCH_NEXT 0 + +static __always_inline int queued_spin_is_locked(struct qspinlock *lock) +{ + return READ_ONCE(lock->val); +} + +static __always_inline int queued_spin_value_unlocked(struct qspinlock lock) +{ + return !lock.val; +} + +static __always_inline int queued_spin_is_contended(struct qspinlock *lock) +{ + return !!(READ_ONCE(lock->val) & _Q_TAIL_CPU_MASK); +} + +static __always_inline u32 queued_spin_encode_locked_val(void) +{ + /* XXX: make this use lock value in paca like simple spinlocks? */ + return _Q_LOCKED_VAL | (smp_processor_id() << _Q_OWNER_CPU_OFFSET); +} + +static __always_inline int __queued_spin_trylock_nosteal(struct qspinlock *lock) +{ + u32 new = queued_spin_encode_locked_val(); + u32 prev; + + /* Trylock succeeds only when unlocked and no queued nodes */ + asm volatile( +"1: lwarx %0,0,%1,%3 # __queued_spin_trylock_nosteal \n" +" cmpwi 0,%0,0 \n" +" bne- 2f \n" +" stwcx. %2,0,%1 \n" +" bne- 1b \n" +"\t" PPC_ACQUIRE_BARRIER " \n" +"2: \n" + : "=&r" (prev) + : "r" (&lock->val), "r" (new), + "i" (_Q_SPIN_EH_HINT) + : "cr0", "memory"); + + return likely(prev == 0); +} + +static __always_inline int __queued_spin_trylock_steal(struct qspinlock *lock) +{ + u32 new = queued_spin_encode_locked_val(); + u32 prev, tmp; + + /* Trylock may get ahead of queued nodes if it finds unlocked */ + asm volatile( +"1: lwarx %0,0,%2,%5 # __queued_spin_trylock_steal \n" +" andc. %1,%0,%4 \n" +" bne- 2f \n" +" and %1,%0,%4 \n" +" or %1,%1,%3 \n" +" stwcx. %1,0,%2 \n" +" bne- 1b \n" +"\t" PPC_ACQUIRE_BARRIER " \n" +"2: \n" + : "=&r" (prev), "=&r" (tmp) + : "r" (&lock->val), "r" (new), "r" (_Q_TAIL_CPU_MASK), + "i" (_Q_SPIN_EH_HINT) + : "cr0", "memory"); + + return likely(!(prev & ~_Q_TAIL_CPU_MASK)); +} + +static __always_inline int queued_spin_trylock(struct qspinlock *lock) +{ + if (!_Q_SPIN_TRY_LOCK_STEAL) + return __queued_spin_trylock_nosteal(lock); + else + return __queued_spin_trylock_steal(lock); +} + +void queued_spin_lock_slowpath(struct qspinlock *lock); + +static __always_inline void queued_spin_lock(struct qspinlock *lock) +{ + if (!queued_spin_trylock(lock)) + queued_spin_lock_slowpath(lock); +} + +static inline void queued_spin_unlock(struct qspinlock *lock) +{ + smp_store_release(&lock->locked, 0); + if (_Q_SPIN_MISO_UNLOCK) + asm volatile("miso" ::: "memory"); +} + +#define arch_spin_is_locked(l) queued_spin_is_locked(l) +#define arch_spin_is_contended(l) queued_spin_is_contended(l) +#define arch_spin_value_unlocked(l) queued_spin_value_unlocked(l) +#define arch_spin_lock(l) queued_spin_lock(l) +#define arch_spin_trylock(l) queued_spin_trylock(l) +#define arch_spin_unlock(l) queued_spin_unlock(l) + +#ifdef CONFIG_PARAVIRT_SPINLOCKS +void pv_spinlocks_init(void); +#else +static inline void pv_spinlocks_init(void) { } +#endif + +#endif /* _ASM_POWERPC_QSPINLOCK_H */ diff --git a/arch/powerpc/include/asm/qspinlock_types.h b/arch/powerpc/include/asm/qspinlock_types.h new file mode 100644 index 000000000000..4766a7aa03cb --- /dev/null +++ b/arch/powerpc/include/asm/qspinlock_types.h @@ -0,0 +1,72 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _ASM_POWERPC_QSPINLOCK_TYPES_H +#define _ASM_POWERPC_QSPINLOCK_TYPES_H + +#include <linux/types.h> +#include <asm/byteorder.h> + +typedef struct qspinlock { + union { + u32 val; + +#ifdef __LITTLE_ENDIAN + struct { + u16 locked; + u8 reserved[2]; + }; +#else + struct { + u8 reserved[2]; + u16 locked; + }; +#endif + }; +} arch_spinlock_t; + +#define __ARCH_SPIN_LOCK_UNLOCKED { { .val = 0 } } + +/* + * Bitfields in the lock word: + * + * 0: locked bit + * 1-14: lock holder cpu + * 15: lock owner or queuer vcpus observed to be preempted bit + * 16: must queue bit + * 17-31: tail cpu (+1) + */ +#define _Q_SET_MASK(type) (((1U << _Q_ ## type ## _BITS) - 1)\ + << _Q_ ## type ## _OFFSET) +/* 0x00000001 */ +#define _Q_LOCKED_OFFSET 0 +#define _Q_LOCKED_BITS 1 +#define _Q_LOCKED_VAL (1U << _Q_LOCKED_OFFSET) + +/* 0x00007ffe */ +#define _Q_OWNER_CPU_OFFSET 1 +#define _Q_OWNER_CPU_BITS 14 +#define _Q_OWNER_CPU_MASK _Q_SET_MASK(OWNER_CPU) + +#if CONFIG_NR_CPUS > (1U << _Q_OWNER_CPU_BITS) +#error "qspinlock does not support such large CONFIG_NR_CPUS" +#endif + +/* 0x00008000 */ +#define _Q_SLEEPY_OFFSET 15 +#define _Q_SLEEPY_BITS 1 +#define _Q_SLEEPY_VAL (1U << _Q_SLEEPY_OFFSET) + +/* 0x00010000 */ +#define _Q_MUST_Q_OFFSET 16 +#define _Q_MUST_Q_BITS 1 +#define _Q_MUST_Q_VAL (1U << _Q_MUST_Q_OFFSET) + +/* 0xfffe0000 */ +#define _Q_TAIL_CPU_OFFSET 17 +#define _Q_TAIL_CPU_BITS 15 +#define _Q_TAIL_CPU_MASK _Q_SET_MASK(TAIL_CPU) + +#if CONFIG_NR_CPUS >= (1U << _Q_TAIL_CPU_BITS) +#error "qspinlock does not support such large CONFIG_NR_CPUS" +#endif + +#endif /* _ASM_POWERPC_QSPINLOCK_TYPES_H */ diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index 1aa46dff0957..7fd09f25452d 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -12,14 +12,15 @@ #ifdef __KERNEL__ #include <linux/stringify.h> +#include <linux/const.h> #include <asm/cputable.h> #include <asm/asm-const.h> #include <asm/feature-fixups.h> /* Pickup Book E specific registers. */ -#if defined(CONFIG_BOOKE) || defined(CONFIG_40x) +#ifdef CONFIG_BOOKE_OR_40x #include <asm/reg_booke.h> -#endif /* CONFIG_BOOKE || CONFIG_40x */ +#endif #ifdef CONFIG_FSL_EMB_PERFMON #include <asm/reg_fsl_emb.h> @@ -28,7 +29,6 @@ #include <asm/reg_8xx.h> #define MSR_SF_LG 63 /* Enable 64 bit mode */ -#define MSR_ISF_LG 61 /* Interrupt 64b mode valid on 630 */ #define MSR_HV_LG 60 /* Hypervisor state */ #define MSR_TS_T_LG 34 /* Trans Mem state: Transactional */ #define MSR_TS_S_LG 33 /* Trans Mem state: Suspended */ @@ -68,13 +68,11 @@ #ifdef CONFIG_PPC64 #define MSR_SF __MASK(MSR_SF_LG) /* Enable 64 bit mode */ -#define MSR_ISF __MASK(MSR_ISF_LG) /* Interrupt 64b mode valid on 630 */ #define MSR_HV __MASK(MSR_HV_LG) /* Hypervisor state */ #define MSR_S __MASK(MSR_S_LG) /* Secure state */ #else /* so tests for these bits fail on 32-bit */ #define MSR_SF 0 -#define MSR_ISF 0 #define MSR_HV 0 #define MSR_S 0 #endif @@ -126,14 +124,14 @@ #ifdef CONFIG_PPC_TRANSACTIONAL_MEM #define MSR_TM_ACTIVE(x) (((x) & MSR_TS_MASK) != 0) /* Transaction active? */ #else -#define MSR_TM_ACTIVE(x) 0 +#define MSR_TM_ACTIVE(x) ((void)(x), 0) #endif #if defined(CONFIG_PPC_BOOK3S_64) #define MSR_64BIT MSR_SF /* Server variant */ -#define __MSR (MSR_ME | MSR_RI | MSR_IR | MSR_DR | MSR_ISF |MSR_HV) +#define __MSR (MSR_ME | MSR_RI | MSR_IR | MSR_DR | MSR_HV) #ifdef __BIG_ENDIAN__ #define MSR_ __MSR #define MSR_IDLE (MSR_ME | MSR_SF | MSR_HV) @@ -283,14 +281,16 @@ #define CTRL_CT1 0x40000000 /* thread 1 */ #define CTRL_TE 0x00c00000 /* thread enable */ #define CTRL_RUNLATCH 0x1 -#define SPRN_DAWR 0xB4 +#define SPRN_DAWR0 0xB4 +#define SPRN_DAWR1 0xB5 #define SPRN_RPR 0xBA /* Relative Priority Register */ #define SPRN_CIABR 0xBB #define CIABR_PRIV 0x3 #define CIABR_PRIV_USER 1 #define CIABR_PRIV_SUPER 2 #define CIABR_PRIV_HYPER 3 -#define SPRN_DAWRX 0xBC +#define SPRN_DAWRX0 0xBC +#define SPRN_DAWRX1 0xBD #define DAWRX_USER __MASK(0) #define DAWRX_KERNEL __MASK(1) #define DAWRX_HYP __MASK(2) @@ -382,9 +382,17 @@ #define SPRN_HIOR 0x137 /* 970 Hypervisor interrupt offset */ #define SPRN_RMOR 0x138 /* Real mode offset register */ #define SPRN_HRMOR 0x139 /* Real mode offset register */ -#define SPRN_HSRR0 0x13A /* Hypervisor Save/Restore 0 */ -#define SPRN_HSRR1 0x13B /* Hypervisor Save/Restore 1 */ +#define SPRN_HDEXCR_RO 0x1C7 /* Hypervisor DEXCR (non-privileged, readonly) */ +#define SPRN_HASHKEYR 0x1D4 /* Non-privileged hashst/hashchk key register */ +#define SPRN_HDEXCR 0x1D7 /* Hypervisor dynamic execution control register */ +#define SPRN_DEXCR_RO 0x32C /* DEXCR (non-privileged, readonly) */ #define SPRN_ASDR 0x330 /* Access segment descriptor register */ +#define SPRN_DEXCR 0x33C /* Dynamic execution control register */ +#define DEXCR_PR_SBHE 0x80000000UL /* 0: Speculative Branch Hint Enable */ +#define DEXCR_PR_IBRTPD 0x10000000UL /* 3: Indirect Branch Recurrent Target Prediction Disable */ +#define DEXCR_PR_SRAPD 0x08000000UL /* 4: Subroutine Return Address Prediction Disable */ +#define DEXCR_PR_NPHIE 0x04000000UL /* 5: Non-Privileged Hash Instruction Enable */ +#define DEXCR_INIT DEXCR_PR_NPHIE /* Fixed DEXCR value to initialise all CPUs with */ #define SPRN_IC 0x350 /* Virtual Instruction Count */ #define SPRN_VTB 0x351 /* Virtual Time Base */ #define SPRN_LDBAR 0x352 /* LD Base Address Register */ @@ -393,10 +401,12 @@ #define SPRN_PMMAR 0x356 /* Power Management Memory Activity Register */ #define SPRN_PSSCR 0x357 /* Processor Stop Status and Control Register (ISA 3.0) */ #define SPRN_PSSCR_PR 0x337 /* PSSCR ISA 3.0, privileged mode access */ +#define SPRN_TRIG2 0x372 #define SPRN_PMCR 0x374 /* Power Management Control Register */ #define SPRN_RWMR 0x375 /* Region-Weighting Mode Register */ /* HFSCR and FSCR bit numbers are the same */ +#define FSCR_PREFIX_LG 13 /* Enable Prefix Instructions */ #define FSCR_SCV_LG 12 /* Enable System Call Vectored */ #define FSCR_MSGP_LG 10 /* Enable MSGP */ #define FSCR_TAR_LG 8 /* Enable Target Address Register */ @@ -408,11 +418,14 @@ #define FSCR_VECVSX_LG 1 /* Enable VMX/VSX */ #define FSCR_FP_LG 0 /* Enable Floating Point */ #define SPRN_FSCR 0x099 /* Facility Status & Control Register */ +#define FSCR_PREFIX __MASK(FSCR_PREFIX_LG) #define FSCR_SCV __MASK(FSCR_SCV_LG) #define FSCR_TAR __MASK(FSCR_TAR_LG) #define FSCR_EBB __MASK(FSCR_EBB_LG) #define FSCR_DSCR __MASK(FSCR_DSCR_LG) +#define FSCR_INTR_CAUSE (ASM_CONST(0xFF) << 56) /* interrupt cause */ #define SPRN_HFSCR 0xbe /* HV=1 Facility Status & Control Register */ +#define HFSCR_PREFIX __MASK(FSCR_PREFIX_LG) #define HFSCR_MSGP __MASK(FSCR_MSGP_LG) #define HFSCR_TAR __MASK(FSCR_TAR_LG) #define HFSCR_EBB __MASK(FSCR_EBB_LG) @@ -422,7 +435,7 @@ #define HFSCR_DSCR __MASK(FSCR_DSCR_LG) #define HFSCR_VECVSX __MASK(FSCR_VECVSX_LG) #define HFSCR_FP __MASK(FSCR_FP_LG) -#define HFSCR_INTR_CAUSE (ASM_CONST(0xFF) << 56) /* interrupt cause */ +#define HFSCR_INTR_CAUSE FSCR_INTR_CAUSE #define SPRN_TAR 0x32f /* Target Address Register */ #define SPRN_LPCR 0x13E /* LPAR Control Register */ #define LPCR_VPM0 ASM_CONST(0x8000000000000000) @@ -438,6 +451,7 @@ #define LPCR_VRMA_LP1 ASM_CONST(0x0000800000000000) #define LPCR_RMLS 0x1C000000 /* Implementation dependent RMO limit sel */ #define LPCR_RMLS_SH 26 +#define LPCR_HAIL ASM_CONST(0x0000000004000000) /* HV AIL (ISAv3.1) */ #define LPCR_ILE ASM_CONST(0x0000000002000000) /* !HV irqs set MSR:LE */ #define LPCR_AIL ASM_CONST(0x0000000001800000) /* Alternate interrupt location */ #define LPCR_AIL_0 ASM_CONST(0x0000000000000000) /* MMU off exception offset 0x0 */ @@ -468,7 +482,6 @@ #ifndef SPRN_LPID #define SPRN_LPID 0x13F /* Logical Partition Identifier */ #endif -#define LPID_RSVD 0x3ff /* Reserved LPID for partn switching */ #define SPRN_HMER 0x150 /* Hypervisor maintenance exception reg */ #define HMER_DEBUG_TRIG (1ul << (63 - 17)) /* Debug trigger */ #define SPRN_HMEER 0x151 /* Hyp maintenance exception enable reg */ @@ -476,16 +489,18 @@ #define PCR_VEC_DIS (__MASK(63-0)) /* Vec. disable (bit NA since POWER8) */ #define PCR_VSX_DIS (__MASK(63-1)) /* VSX disable (bit NA since POWER8) */ #define PCR_TM_DIS (__MASK(63-2)) /* Trans. memory disable (POWER8) */ -#define PCR_HIGH_BITS (PCR_VEC_DIS | PCR_VSX_DIS | PCR_TM_DIS) +#define PCR_MMA_DIS (__MASK(63-3)) /* Matrix-Multiply Accelerator */ +#define PCR_HIGH_BITS (PCR_MMA_DIS | PCR_VEC_DIS | PCR_VSX_DIS | PCR_TM_DIS) /* * These bits are used in the function kvmppc_set_arch_compat() to specify and * determine both the compatibility level which we want to emulate and the * compatibility level which the host is capable of emulating. */ +#define PCR_ARCH_300 0x10 /* Architecture 3.00 */ #define PCR_ARCH_207 0x8 /* Architecture 2.07 */ #define PCR_ARCH_206 0x4 /* Architecture 2.06 */ #define PCR_ARCH_205 0x2 /* Architecture 2.05 */ -#define PCR_LOW_BITS (PCR_ARCH_207 | PCR_ARCH_206 | PCR_ARCH_205) +#define PCR_LOW_BITS (PCR_ARCH_207 | PCR_ARCH_206 | PCR_ARCH_205 | PCR_ARCH_300) #define PCR_MASK ~(PCR_HIGH_BITS | PCR_LOW_BITS) /* PCR Reserved Bits */ #define SPRN_HEIR 0x153 /* Hypervisor Emulated Instruction Register */ #define SPRN_TLBINDEXR 0x154 /* P7 TLB control register */ @@ -512,6 +527,8 @@ #define SPRN_TSCR 0x399 /* Thread Switch Control Register */ #define SPRN_DEC 0x016 /* Decrement Register */ +#define SPRN_PIT 0x3DB /* Programmable Interval Timer (40x/BOOKE) */ + #define SPRN_DER 0x095 /* Debug Enable Register */ #define DER_RSTE 0x40000000 /* Reset Interrupt */ #define DER_CHSTPE 0x20000000 /* Check Stop */ @@ -759,7 +776,7 @@ #endif #define SRR1_ISI_NOPT 0x40000000 /* ISI: Not found in hash */ -#define SRR1_ISI_N_OR_G 0x10000000 /* ISI: Access is no-exec or G */ +#define SRR1_ISI_N_G_OR_CIP 0x10000000 /* ISI: Access is no-exec or G or CI for a prefixed instruction */ #define SRR1_ISI_PROT 0x08000000 /* ISI: Other protection fault */ #define SRR1_WAKEMASK 0x00380000 /* reason for wakeup */ #define SRR1_WAKEMASK_P8 0x003c0000 /* reason for wakeup on POWER8 and 9 */ @@ -786,6 +803,8 @@ #define SRR1_PROGADDR 0x00010000 /* SRR0 contains subsequent addr */ #define SRR1_MCE_MCP 0x00080000 /* Machine check signal caused interrupt */ +#define SRR1_BOUNDARY 0x10000000 /* Prefixed instruction crosses 64-byte boundary */ +#define SRR1_PREFIXED 0x20000000 /* Exception caused by prefixed instruction */ #define SPRN_HSRR0 0x13A /* Save/Restore Register 0 */ #define SPRN_HSRR1 0x13B /* Save/Restore Register 1 */ @@ -806,7 +825,7 @@ #define THRM1_TIN (1 << 31) #define THRM1_TIV (1 << 30) #define THRM1_THRES(x) ((x&0x7f)<<23) -#define THRM3_SITV(x) ((x&0x3fff)<<1) +#define THRM3_SITV(x) ((x & 0x1fff) << 1) #define THRM1_TID (1<<2) #define THRM1_TIE (1<<1) #define THRM1_V (1<<0) @@ -851,6 +870,7 @@ #define MMCR0_BHRBA 0x00200000UL /* BHRB Access allowed in userspace */ #define MMCR0_EBE 0x00100000UL /* Event based branch enable */ #define MMCR0_PMCC 0x000c0000UL /* PMC control */ +#define MMCR0_PMCCEXT ASM_CONST(0x00000200) /* PMCCEXT control */ #define MMCR0_PMCC_U6 0x00080000UL /* PMC1-6 are R/W by user (PR) */ #define MMCR0_PMC1CE 0x00008000UL /* PMC1 count enable*/ #define MMCR0_PMCjCE ASM_CONST(0x00004000) /* PMCj count enable*/ @@ -867,7 +887,9 @@ #define MMCR0_FCHV 0x00000001UL /* freeze conditions in hypervisor mode */ #define SPRN_MMCR1 798 #define SPRN_MMCR2 785 +#define SPRN_MMCR3 754 #define SPRN_UMMCR2 769 +#define SPRN_UMMCR3 738 #define SPRN_MMCRA 0x312 #define MMCRA_SDSYNC 0x80000000UL /* SDAR synced with SIAR */ #define MMCRA_SDAR_DCACHE_MISS 0x40000000UL @@ -877,6 +899,7 @@ #define MMCRA_SLOT 0x07000000UL /* SLOT bits (37-39) */ #define MMCRA_SLOT_SHIFT 24 #define MMCRA_SAMPLE_ENABLE 0x00000001UL /* enable sampling */ +#define MMCRA_BHRB_DISABLE _UL(0x2000000000) // BHRB disable bit for ISA v3.1 #define POWER6_MMCRA_SDSYNC 0x0000080000000000ULL /* SDAR/SIAR synced */ #define POWER6_MMCRA_SIHV 0x0000040000000000ULL #define POWER6_MMCRA_SIPR 0x0000020000000000ULL @@ -909,6 +932,10 @@ #define SIER_SIHV 0x1000000 /* Sampled MSR_HV */ #define SIER_SIAR_VALID 0x0400000 /* SIAR contents valid */ #define SIER_SDAR_VALID 0x0200000 /* SDAR contents valid */ +#define SPRN_SIER2 752 +#define SPRN_SIER3 753 +#define SPRN_USIER2 736 +#define SPRN_USIER3 737 #define SPRN_SIAR 796 #define SPRN_SDAR 797 #define SPRN_TACR 888 @@ -1183,7 +1210,7 @@ #ifdef CONFIG_PPC_BOOK3S_32 #define SPRN_SPRG_SCRATCH0 SPRN_SPRG0 #define SPRN_SPRG_SCRATCH1 SPRN_SPRG1 -#define SPRN_SPRG_PGDIR SPRN_SPRG2 +#define SPRN_SPRG_SCRATCH2 SPRN_SPRG2 #define SPRN_SPRG_603_LRU SPRN_SPRG4 #endif @@ -1212,14 +1239,9 @@ #define SPRN_SPRG_WSCRATCH_MC SPRN_SPRG1 #define SPRN_SPRG_RSCRATCH4 SPRN_SPRG7R #define SPRN_SPRG_WSCRATCH4 SPRN_SPRG7W -#ifdef CONFIG_E200 -#define SPRN_SPRG_RSCRATCH_DBG SPRN_SPRG6R -#define SPRN_SPRG_WSCRATCH_DBG SPRN_SPRG6W -#else #define SPRN_SPRG_RSCRATCH_DBG SPRN_SPRG9 #define SPRN_SPRG_WSCRATCH_DBG SPRN_SPRG9 #endif -#endif #ifdef CONFIG_PPC_8xx #define SPRN_SPRG_SCRATCH0 SPRN_SPRG0 @@ -1297,6 +1319,11 @@ #define PVR_VER_E500MC 0x8023 #define PVR_VER_E5500 0x8024 #define PVR_VER_E6500 0x8040 +#define PVR_VER_7450 0x8000 +#define PVR_VER_7455 0x8001 +#define PVR_VER_7447 0x8002 +#define PVR_VER_7447A 0x8003 +#define PVR_VER_7448 0x8004 /* * For the 8xx processors, all of them report the same PVR family for @@ -1334,7 +1361,9 @@ #define PVR_POWER8E 0x004B #define PVR_POWER8NVL 0x004C #define PVR_POWER8 0x004D +#define PVR_HX_C2000 0x0066 #define PVR_POWER9 0x004E +#define PVR_POWER10 0x0080 #define PVR_BE 0x0070 #define PVR_PA6T 0x0090 @@ -1345,9 +1374,22 @@ #define PVR_ARCH_206p 0x0f100003 #define PVR_ARCH_207 0x0f000004 #define PVR_ARCH_300 0x0f000005 +#define PVR_ARCH_31 0x0f000006 /* Macros for setting and retrieving special purpose registers */ #ifndef __ASSEMBLY__ + +#if defined(CONFIG_PPC64) || defined(__CHECKER__) +typedef struct { + u32 val; +#ifdef CONFIG_PPC64 + u32 suffix; +#endif +} __packed ppc_inst_t; +#else +typedef u32 ppc_inst_t; +#endif + #define mfmsr() ({unsigned long rval; \ asm volatile("mfmsr %0" : "=r" (rval) : \ : "memory"); rval;}) @@ -1360,6 +1402,7 @@ #define mtmsr(v) asm volatile("mtmsr %0" : \ : "r" ((unsigned long)(v)) \ : "memory") +#define __mtmsrd(v, l) BUILD_BUG() #define __MTMSR "mtmsr" #endif @@ -1372,13 +1415,10 @@ static inline void mtmsr_isync(unsigned long val) #define mfspr(rn) ({unsigned long rval; \ asm volatile("mfspr %0," __stringify(rn) \ : "=r" (rval)); rval;}) -#ifndef mtspr #define mtspr(rn, v) asm volatile("mtspr " __stringify(rn) ",%0" : \ : "r" ((unsigned long)(v)) \ : "memory") -#endif -#define wrtspr(rn) asm volatile("mtspr " __stringify(rn) ",0" : \ - : : "memory") +#define wrtspr(rn) asm volatile("mtspr " __stringify(rn) ",2" : : : "memory") static inline void wrtee(unsigned long val) { @@ -1397,58 +1437,31 @@ static inline void msr_check_and_clear(unsigned long bits) __msr_check_and_clear(bits); } -#ifdef __powerpc64__ -#if defined(CONFIG_PPC_CELL) || defined(CONFIG_PPC_FSL_BOOK3E) -#define mftb() ({unsigned long rval; \ - asm volatile( \ - "90: mfspr %0, %2;\n" \ - ASM_FTR_IFSET( \ - "97: cmpwi %0,0;\n" \ - " beq- 90b;\n", "", %1) \ - : "=r" (rval) \ - : "i" (CPU_FTR_CELL_TB_BUG), "i" (SPRN_TBRL) : "cr0"); \ - rval;}) -#else -#define mftb() ({unsigned long rval; \ - asm volatile("mfspr %0, %1" : \ - "=r" (rval) : "i" (SPRN_TBRL)); rval;}) -#endif /* !CONFIG_PPC_CELL */ - -#else /* __powerpc64__ */ - -#if defined(CONFIG_PPC_8xx) -#define mftbl() ({unsigned long rval; \ - asm volatile("mftbl %0" : "=r" (rval)); rval;}) -#define mftbu() ({unsigned long rval; \ - asm volatile("mftbu %0" : "=r" (rval)); rval;}) -#else -#define mftbl() ({unsigned long rval; \ - asm volatile("mfspr %0, %1" : "=r" (rval) : \ - "i" (SPRN_TBRL)); rval;}) -#define mftbu() ({unsigned long rval; \ - asm volatile("mfspr %0, %1" : "=r" (rval) : \ - "i" (SPRN_TBRU)); rval;}) -#endif -#define mftb() mftbl() -#endif /* !__powerpc64__ */ +#ifdef CONFIG_PPC32 +static inline u32 mfsr(u32 idx) +{ + u32 val; -#define mttbl(v) asm volatile("mttbl %0":: "r"(v)) -#define mttbu(v) asm volatile("mttbu %0":: "r"(v)) + if (__builtin_constant_p(idx)) + asm volatile("mfsr %0, %1" : "=r" (val): "i" (idx >> 28)); + else + asm volatile("mfsrin %0, %1" : "=r" (val): "r" (idx)); -#ifdef CONFIG_PPC32 -#define mfsrin(v) ({unsigned int rval; \ - asm volatile("mfsrin %0,%1" : "=r" (rval) : "r" (v)); \ - rval;}) + return val; +} -static inline void mtsrin(u32 val, u32 idx) +static inline void mtsr(u32 val, u32 idx) { - asm volatile("mtsrin %0, %1" : : "r" (val), "r" (idx)); + if (__builtin_constant_p(idx)) + asm volatile("mtsr %1, %0" : : "r" (val), "i" (idx >> 28)); + else + asm volatile("mtsrin %0, %1" : : "r" (val), "r" (idx)); } #endif -#define proc_trap() asm volatile("trap") +extern unsigned long current_stack_frame(void); -extern unsigned long current_stack_pointer(void); +register unsigned long current_stack_pointer asm("r1"); extern unsigned long scom970_read(unsigned int address); extern void scom970_write(unsigned int address, unsigned long value); @@ -1456,16 +1469,6 @@ extern void scom970_write(unsigned int address, unsigned long value); struct pt_regs; extern void ppc_save_regs(struct pt_regs *regs); - -static inline void update_power8_hid0(unsigned long hid0) -{ - /* - * The HID0 update on Power8 should at the very least be - * preceded by a a SYNC instruction followed by an ISYNC - * instruction - */ - asm volatile("sync; mtspr %0,%1; isync":: "i"(SPRN_HID0), "r"(hid0)); -} #endif /* __ASSEMBLY__ */ #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_REG_H */ diff --git a/arch/powerpc/include/asm/reg_8xx.h b/arch/powerpc/include/asm/reg_8xx.h index 07df35ee8cbc..299ee7be0f67 100644 --- a/arch/powerpc/include/asm/reg_8xx.h +++ b/arch/powerpc/include/asm/reg_8xx.h @@ -35,7 +35,21 @@ #define SPRN_CMPE 152 #define SPRN_CMPF 153 #define SPRN_LCTRL1 156 +#define LCTRL1_CTE_GT 0xc0000000 +#define LCTRL1_CTF_LT 0x14000000 +#define LCTRL1_CRWE_RW 0x00000000 +#define LCTRL1_CRWE_RO 0x00040000 +#define LCTRL1_CRWE_WO 0x000c0000 +#define LCTRL1_CRWF_RW 0x00000000 +#define LCTRL1_CRWF_RO 0x00010000 +#define LCTRL1_CRWF_WO 0x00030000 #define SPRN_LCTRL2 157 +#define LCTRL2_LW0EN 0x80000000 +#define LCTRL2_LW0LA_E 0x00000000 +#define LCTRL2_LW0LA_F 0x04000000 +#define LCTRL2_LW0LA_EandF 0x08000000 +#define LCTRL2_LW0LADC 0x02000000 +#define LCTRL2_SLW0EN 0x00000002 #ifdef CONFIG_PPC_8xx #define SPRN_ICTRL 158 #endif diff --git a/arch/powerpc/include/asm/reg_a2.h b/arch/powerpc/include/asm/reg_a2.h deleted file mode 100644 index 74fba29e9491..000000000000 --- a/arch/powerpc/include/asm/reg_a2.h +++ /dev/null @@ -1,154 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * Register definitions specific to the A2 core - * - * Copyright (C) 2008 Ben. Herrenschmidt (benh@kernel.crashing.org), IBM Corp. - */ - -#ifndef __ASM_POWERPC_REG_A2_H__ -#define __ASM_POWERPC_REG_A2_H__ - -#include <asm/asm-const.h> - -#define SPRN_TENSR 0x1b5 -#define SPRN_TENS 0x1b6 /* Thread ENable Set */ -#define SPRN_TENC 0x1b7 /* Thread ENable Clear */ - -#define SPRN_A2_CCR0 0x3f0 /* Core Configuration Register 0 */ -#define SPRN_A2_CCR1 0x3f1 /* Core Configuration Register 1 */ -#define SPRN_A2_CCR2 0x3f2 /* Core Configuration Register 2 */ -#define SPRN_MMUCR0 0x3fc /* MMU Control Register 0 */ -#define SPRN_MMUCR1 0x3fd /* MMU Control Register 1 */ -#define SPRN_MMUCR2 0x3fe /* MMU Control Register 2 */ -#define SPRN_MMUCR3 0x3ff /* MMU Control Register 3 */ - -#define SPRN_IAR 0x372 - -#define SPRN_IUCR0 0x3f3 -#define IUCR0_ICBI_ACK 0x1000 - -#define SPRN_XUCR0 0x3f6 /* Execution Unit Config Register 0 */ - -#define A2_IERAT_SIZE 16 -#define A2_DERAT_SIZE 32 - -/* A2 MMUCR0 bits */ -#define MMUCR0_ECL 0x80000000 /* Extended Class for TLB fills */ -#define MMUCR0_TID_NZ 0x40000000 /* TID is non-zero */ -#define MMUCR0_TS 0x10000000 /* Translation space for TLB fills */ -#define MMUCR0_TGS 0x20000000 /* Guest space for TLB fills */ -#define MMUCR0_TLBSEL 0x0c000000 /* TLB or ERAT target for TLB fills */ -#define MMUCR0_TLBSEL_U 0x00000000 /* TLBSEL = UTLB */ -#define MMUCR0_TLBSEL_I 0x08000000 /* TLBSEL = I-ERAT */ -#define MMUCR0_TLBSEL_D 0x0c000000 /* TLBSEL = D-ERAT */ -#define MMUCR0_LOCKSRSH 0x02000000 /* Use TLB lock on tlbsx. */ -#define MMUCR0_TID_MASK 0x000000ff /* TID field */ - -/* A2 MMUCR1 bits */ -#define MMUCR1_IRRE 0x80000000 /* I-ERAT round robin enable */ -#define MMUCR1_DRRE 0x40000000 /* D-ERAT round robin enable */ -#define MMUCR1_REE 0x20000000 /* Reference Exception Enable*/ -#define MMUCR1_CEE 0x10000000 /* Change exception enable */ -#define MMUCR1_CSINV_ALL 0x00000000 /* Inval ERAT on all CS evts */ -#define MMUCR1_CSINV_NISYNC 0x04000000 /* Inval ERAT on all ex isync*/ -#define MMUCR1_CSINV_NEVER 0x0c000000 /* Don't inval ERAT on CS */ -#define MMUCR1_ICTID 0x00080000 /* IERAT class field as TID */ -#define MMUCR1_ITTID 0x00040000 /* IERAT thdid field as TID */ -#define MMUCR1_DCTID 0x00020000 /* DERAT class field as TID */ -#define MMUCR1_DTTID 0x00010000 /* DERAT thdid field as TID */ -#define MMUCR1_DCCD 0x00008000 /* DERAT class ignore */ -#define MMUCR1_TLBWE_BINV 0x00004000 /* back invalidate on tlbwe */ - -/* A2 MMUCR2 bits */ -#define MMUCR2_PSSEL_SHIFT 4 - -/* A2 MMUCR3 bits */ -#define MMUCR3_THID 0x0000000f /* Thread ID */ - -/* *** ERAT TLB bits definitions */ -#define TLB0_EPN_MASK ASM_CONST(0xfffffffffffff000) -#define TLB0_CLASS_MASK ASM_CONST(0x0000000000000c00) -#define TLB0_CLASS_00 ASM_CONST(0x0000000000000000) -#define TLB0_CLASS_01 ASM_CONST(0x0000000000000400) -#define TLB0_CLASS_10 ASM_CONST(0x0000000000000800) -#define TLB0_CLASS_11 ASM_CONST(0x0000000000000c00) -#define TLB0_V ASM_CONST(0x0000000000000200) -#define TLB0_X ASM_CONST(0x0000000000000100) -#define TLB0_SIZE_MASK ASM_CONST(0x00000000000000f0) -#define TLB0_SIZE_4K ASM_CONST(0x0000000000000010) -#define TLB0_SIZE_64K ASM_CONST(0x0000000000000030) -#define TLB0_SIZE_1M ASM_CONST(0x0000000000000050) -#define TLB0_SIZE_16M ASM_CONST(0x0000000000000070) -#define TLB0_SIZE_1G ASM_CONST(0x00000000000000a0) -#define TLB0_THDID_MASK ASM_CONST(0x000000000000000f) -#define TLB0_THDID_0 ASM_CONST(0x0000000000000001) -#define TLB0_THDID_1 ASM_CONST(0x0000000000000002) -#define TLB0_THDID_2 ASM_CONST(0x0000000000000004) -#define TLB0_THDID_3 ASM_CONST(0x0000000000000008) -#define TLB0_THDID_ALL ASM_CONST(0x000000000000000f) - -#define TLB1_RESVATTR ASM_CONST(0x00f0000000000000) -#define TLB1_U0 ASM_CONST(0x0008000000000000) -#define TLB1_U1 ASM_CONST(0x0004000000000000) -#define TLB1_U2 ASM_CONST(0x0002000000000000) -#define TLB1_U3 ASM_CONST(0x0001000000000000) -#define TLB1_R ASM_CONST(0x0000800000000000) -#define TLB1_C ASM_CONST(0x0000400000000000) -#define TLB1_RPN_MASK ASM_CONST(0x000003fffffff000) -#define TLB1_W ASM_CONST(0x0000000000000800) -#define TLB1_I ASM_CONST(0x0000000000000400) -#define TLB1_M ASM_CONST(0x0000000000000200) -#define TLB1_G ASM_CONST(0x0000000000000100) -#define TLB1_E ASM_CONST(0x0000000000000080) -#define TLB1_VF ASM_CONST(0x0000000000000040) -#define TLB1_UX ASM_CONST(0x0000000000000020) -#define TLB1_SX ASM_CONST(0x0000000000000010) -#define TLB1_UW ASM_CONST(0x0000000000000008) -#define TLB1_SW ASM_CONST(0x0000000000000004) -#define TLB1_UR ASM_CONST(0x0000000000000002) -#define TLB1_SR ASM_CONST(0x0000000000000001) - -/* A2 erativax attributes definitions */ -#define ERATIVAX_RS_IS_ALL 0x000 -#define ERATIVAX_RS_IS_TID 0x040 -#define ERATIVAX_RS_IS_CLASS 0x080 -#define ERATIVAX_RS_IS_FULLMATCH 0x0c0 -#define ERATIVAX_CLASS_00 0x000 -#define ERATIVAX_CLASS_01 0x010 -#define ERATIVAX_CLASS_10 0x020 -#define ERATIVAX_CLASS_11 0x030 -#define ERATIVAX_PSIZE_4K (TLB_PSIZE_4K >> 1) -#define ERATIVAX_PSIZE_64K (TLB_PSIZE_64K >> 1) -#define ERATIVAX_PSIZE_1M (TLB_PSIZE_1M >> 1) -#define ERATIVAX_PSIZE_16M (TLB_PSIZE_16M >> 1) -#define ERATIVAX_PSIZE_1G (TLB_PSIZE_1G >> 1) - -/* A2 eratilx attributes definitions */ -#define ERATILX_T_ALL 0 -#define ERATILX_T_TID 1 -#define ERATILX_T_TGS 2 -#define ERATILX_T_FULLMATCH 3 -#define ERATILX_T_CLASS0 4 -#define ERATILX_T_CLASS1 5 -#define ERATILX_T_CLASS2 6 -#define ERATILX_T_CLASS3 7 - -/* XUCR0 bits */ -#define XUCR0_TRACE_UM_T0 0x40000000 /* Thread 0 */ -#define XUCR0_TRACE_UM_T1 0x20000000 /* Thread 1 */ -#define XUCR0_TRACE_UM_T2 0x10000000 /* Thread 2 */ -#define XUCR0_TRACE_UM_T3 0x08000000 /* Thread 3 */ - -/* A2 CCR0 register */ -#define A2_CCR0_PME_DISABLED 0x00000000 -#define A2_CCR0_PME_SLEEP 0x40000000 -#define A2_CCR0_PME_RVW 0x80000000 -#define A2_CCR0_PME_DISABLED2 0xc0000000 - -/* A2 CCR2 register */ -#define A2_CCR2_ERAT_ONLY_MODE 0x00000001 -#define A2_CCR2_ENABLE_ICSWX 0x00000002 -#define A2_CCR2_ENABLE_PC 0x20000000 -#define A2_CCR2_ENABLE_TRACE 0x40000000 - -#endif /* __ASM_POWERPC_REG_A2_H__ */ diff --git a/arch/powerpc/include/asm/reg_booke.h b/arch/powerpc/include/asm/reg_booke.h index f26fe482fbca..af56980b6cdb 100644 --- a/arch/powerpc/include/asm/reg_booke.h +++ b/arch/powerpc/include/asm/reg_booke.h @@ -174,7 +174,6 @@ #define SPRN_L1CSR1 0x3F3 /* L1 Cache Control and Status Register 1 */ #define SPRN_MMUCSR0 0x3F4 /* MMU Control and Status Register 0 */ #define SPRN_MMUCFG 0x3F7 /* MMU Configuration Register */ -#define SPRN_PIT 0x3DB /* Programmable Interval Timer */ #define SPRN_BUCSR 0x3F5 /* Branch Unit Control and Status */ #define SPRN_L2CSR0 0x3F9 /* L2 Data Cache Control and Status Register 0 */ #define SPRN_L2CSR1 0x3FA /* L2 Data Cache Control and Status Register 1 */ @@ -247,7 +246,7 @@ #define PPC47x_MCSR_FPR 0x00800000 /* FPR parity error */ #define PPC47x_MCSR_IPR 0x00400000 /* Imprecise Machine Check Exception */ -#ifdef CONFIG_E500 +#ifdef CONFIG_PPC_E500 /* All e500 */ #define MCSR_MCP 0x80000000UL /* Machine Check Input Pin */ #define MCSR_ICPERR 0x40000000UL /* I-Cache Parity Error */ @@ -282,20 +281,8 @@ #define MSRP_PMMP 0x00000004 /* Protect MSR[PMM] */ #endif -#ifdef CONFIG_E200 -#define MCSR_MCP 0x80000000UL /* Machine Check Input Pin */ -#define MCSR_CP_PERR 0x20000000UL /* Cache Push Parity Error */ -#define MCSR_CPERR 0x10000000UL /* Cache Parity Error */ -#define MCSR_EXCP_ERR 0x08000000UL /* ISI, ITLB, or Bus Error on 1st insn - fetch for an exception handler */ -#define MCSR_BUS_IRERR 0x00000010UL /* Read Bus Error on instruction fetch*/ -#define MCSR_BUS_DRERR 0x00000008UL /* Read Bus Error on data load */ -#define MCSR_BUS_WRERR 0x00000004UL /* Write Bus Error on buffered - store or cache line push */ -#endif - /* Bit definitions for the HID1 */ -#ifdef CONFIG_E500 +#ifdef CONFIG_PPC_E500 /* e500v1/v2 */ #define HID1_PLL_CFG_MASK 0xfc000000 /* PLL_CFG input pins */ #define HID1_RFXE 0x00020000 /* Read fault exception enable */ @@ -558,7 +545,7 @@ #define TCR_FIE 0x00800000 /* FIT Interrupt Enable */ #define TCR_ARE 0x00400000 /* Auto Reload Enable */ -#ifdef CONFIG_E500 +#ifdef CONFIG_PPC_E500 #define TCR_GET_WP(tcr) ((((tcr) & 0xC0000000) >> 30) | \ (((tcr) & 0x1E0000) >> 15)) #else @@ -663,60 +650,6 @@ #define EPC_EPID 0x00003fff #define EPC_EPID_SHIFT 0 -/* - * The IBM-403 is an even more odd special case, as it is much - * older than the IBM-405 series. We put these down here incase someone - * wishes to support these machines again. - */ -#ifdef CONFIG_403GCX -/* Special Purpose Registers (SPRNs)*/ -#define SPRN_TBHU 0x3CC /* Time Base High User-mode */ -#define SPRN_TBLU 0x3CD /* Time Base Low User-mode */ -#define SPRN_CDBCR 0x3D7 /* Cache Debug Control Register */ -#define SPRN_TBHI 0x3DC /* Time Base High */ -#define SPRN_TBLO 0x3DD /* Time Base Low */ -#define SPRN_DBCR 0x3F2 /* Debug Control Register */ -#define SPRN_PBL1 0x3FC /* Protection Bound Lower 1 */ -#define SPRN_PBL2 0x3FE /* Protection Bound Lower 2 */ -#define SPRN_PBU1 0x3FD /* Protection Bound Upper 1 */ -#define SPRN_PBU2 0x3FF /* Protection Bound Upper 2 */ - - -/* Bit definitions for the DBCR. */ -#define DBCR_EDM DBCR0_EDM -#define DBCR_IDM DBCR0_IDM -#define DBCR_RST(x) (((x) & 0x3) << 28) -#define DBCR_RST_NONE 0 -#define DBCR_RST_CORE 1 -#define DBCR_RST_CHIP 2 -#define DBCR_RST_SYSTEM 3 -#define DBCR_IC DBCR0_IC /* Instruction Completion Debug Evnt */ -#define DBCR_BT DBCR0_BT /* Branch Taken Debug Event */ -#define DBCR_EDE DBCR0_EDE /* Exception Debug Event */ -#define DBCR_TDE DBCR0_TDE /* TRAP Debug Event */ -#define DBCR_FER 0x00F80000 /* First Events Remaining Mask */ -#define DBCR_FT 0x00040000 /* Freeze Timers on Debug Event */ -#define DBCR_IA1 0x00020000 /* Instr. Addr. Compare 1 Enable */ -#define DBCR_IA2 0x00010000 /* Instr. Addr. Compare 2 Enable */ -#define DBCR_D1R 0x00008000 /* Data Addr. Compare 1 Read Enable */ -#define DBCR_D1W 0x00004000 /* Data Addr. Compare 1 Write Enable */ -#define DBCR_D1S(x) (((x) & 0x3) << 12) /* Data Adrr. Compare 1 Size */ -#define DAC_BYTE 0 -#define DAC_HALF 1 -#define DAC_WORD 2 -#define DAC_QUAD 3 -#define DBCR_D2R 0x00000800 /* Data Addr. Compare 2 Read Enable */ -#define DBCR_D2W 0x00000400 /* Data Addr. Compare 2 Write Enable */ -#define DBCR_D2S(x) (((x) & 0x3) << 8) /* Data Addr. Compare 2 Size */ -#define DBCR_SBT 0x00000040 /* Second Branch Taken Debug Event */ -#define DBCR_SED 0x00000020 /* Second Exception Debug Event */ -#define DBCR_STD 0x00000010 /* Second Trap Debug Event */ -#define DBCR_SIA 0x00000008 /* Second IAC Enable */ -#define DBCR_SDA 0x00000004 /* Second DAC Enable */ -#define DBCR_JOI 0x00000002 /* JTAG Serial Outbound Int. Enable */ -#define DBCR_JII 0x00000001 /* JTAG Serial Inbound Int. Enable */ -#endif /* 403GCX */ - /* Some 476 specific registers */ #define SPRN_SSPCR 830 #define SPRN_USPCR 831 @@ -758,6 +691,9 @@ #define mttmr(rn, v) asm volatile(MTTMR(rn, %0) : \ : "r" ((unsigned long)(v)) \ : "memory") + +extern unsigned long global_dbcr0[]; + #endif /* !__ASSEMBLY__ */ #endif /* __ASM_POWERPC_REG_BOOKE_H__ */ diff --git a/arch/powerpc/include/asm/rtas-types.h b/arch/powerpc/include/asm/rtas-types.h new file mode 100644 index 000000000000..9d5b16803cbb --- /dev/null +++ b/arch/powerpc/include/asm/rtas-types.h @@ -0,0 +1,114 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _ASM_POWERPC_RTAS_TYPES_H +#define _ASM_POWERPC_RTAS_TYPES_H + +#include <linux/compiler_attributes.h> + +typedef __be32 rtas_arg_t; + +struct rtas_args { + __be32 token; + __be32 nargs; + __be32 nret; + rtas_arg_t args[16]; + rtas_arg_t *rets; /* Pointer to return values in args[]. */ +} __aligned(8); + +struct rtas_t { + unsigned long entry; /* physical address pointer */ + unsigned long base; /* physical address pointer */ + unsigned long size; + struct device_node *dev; /* virtual address pointer */ +}; + +struct rtas_error_log { + /* Byte 0 */ + u8 byte0; /* Architectural version */ + + /* Byte 1 */ + u8 byte1; + /* XXXXXXXX + * XXX 3: Severity level of error + * XX 2: Degree of recovery + * X 1: Extended log present? + * XX 2: Reserved + */ + + /* Byte 2 */ + u8 byte2; + /* XXXXXXXX + * XXXX 4: Initiator of event + * XXXX 4: Target of failed operation + */ + u8 byte3; /* General event or error*/ + __be32 extended_log_length; /* length in bytes */ + unsigned char buffer[1]; /* Start of extended log */ + /* Variable length. */ +}; + +/* RTAS general extended event log, Version 6. The extended log starts + * from "buffer" field of struct rtas_error_log defined above. + */ +struct rtas_ext_event_log_v6 { + /* Byte 0 */ + u8 byte0; + /* XXXXXXXX + * X 1: Log valid + * X 1: Unrecoverable error + * X 1: Recoverable (correctable or successfully retried) + * X 1: Bypassed unrecoverable error (degraded operation) + * X 1: Predictive error + * X 1: "New" log (always 1 for data returned from RTAS) + * X 1: Big Endian + * X 1: Reserved + */ + + /* Byte 1 */ + u8 byte1; /* reserved */ + + /* Byte 2 */ + u8 byte2; + /* XXXXXXXX + * X 1: Set to 1 (indicating log is in PowerPC format) + * XXX 3: Reserved + * XXXX 4: Log format used for bytes 12-2047 + */ + + /* Byte 3 */ + u8 byte3; /* reserved */ + /* Byte 4-11 */ + u8 reserved[8]; /* reserved */ + /* Byte 12-15 */ + __be32 company_id; /* Company ID of the company */ + /* that defines the format for */ + /* the vendor specific log type */ + /* Byte 16-end of log */ + u8 vendor_log[1]; /* Start of vendor specific log */ + /* Variable length. */ +}; + +/* Vendor specific Platform Event Log Format, Version 6, section header */ +struct pseries_errorlog { + __be16 id; /* 0x00 2-byte ASCII section ID */ + __be16 length; /* 0x02 Section length in bytes */ + u8 version; /* 0x04 Section version */ + u8 subtype; /* 0x05 Section subtype */ + __be16 creator_component; /* 0x06 Creator component ID */ + u8 data[]; /* 0x08 Start of section data */ +}; + +/* RTAS pseries hotplug errorlog section */ +struct pseries_hp_errorlog { + u8 resource; + u8 action; + u8 id_type; + u8 reserved; + union { + __be32 drc_index; + __be32 drc_count; + struct { __be32 count, index; } ic; + char drc_name[1]; + } _drc_u; +}; + +#endif /* _ASM_POWERPC_RTAS_TYPES_H */ diff --git a/arch/powerpc/include/asm/rtas-work-area.h b/arch/powerpc/include/asm/rtas-work-area.h new file mode 100644 index 000000000000..251a395dbd2e --- /dev/null +++ b/arch/powerpc/include/asm/rtas-work-area.h @@ -0,0 +1,96 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef _ASM_POWERPC_RTAS_WORK_AREA_H +#define _ASM_POWERPC_RTAS_WORK_AREA_H + +#include <linux/build_bug.h> +#include <linux/sizes.h> +#include <linux/types.h> + +#include <asm/page.h> + +/** + * struct rtas_work_area - RTAS work area descriptor. + * + * Descriptor for a "work area" in PAPR terminology that satisfies + * RTAS addressing requirements. + */ +struct rtas_work_area { + /* private: Use the APIs provided below. */ + char *buf; + size_t size; +}; + +enum { + /* Maximum allocation size, enforced at build time. */ + RTAS_WORK_AREA_MAX_ALLOC_SZ = SZ_128K, +}; + +/** + * rtas_work_area_alloc() - Acquire a work area of the requested size. + * @size_: Allocation size. Must be compile-time constant and not more + * than %RTAS_WORK_AREA_MAX_ALLOC_SZ. + * + * Allocate a buffer suitable for passing to RTAS functions that have + * a memory address parameter, often (but not always) referred to as a + * "work area" in PAPR. Although callers are allowed to block while + * holding a work area, the amount of memory reserved for this purpose + * is limited, and allocations should be short-lived. A good guideline + * is to release any allocated work area before returning from a + * system call. + * + * This function does not fail. It blocks until the allocation + * succeeds. To prevent deadlocks, callers are discouraged from + * allocating more than one work area simultaneously in a single task + * context. + * + * Context: This function may sleep. + * Return: A &struct rtas_work_area descriptor for the allocated work area. + */ +#define rtas_work_area_alloc(size_) ({ \ + static_assert(__builtin_constant_p(size_)); \ + static_assert((size_) > 0); \ + static_assert((size_) <= RTAS_WORK_AREA_MAX_ALLOC_SZ); \ + __rtas_work_area_alloc(size_); \ +}) + +/* + * Do not call __rtas_work_area_alloc() directly. Use + * rtas_work_area_alloc(). + */ +struct rtas_work_area *__rtas_work_area_alloc(size_t size); + +/** + * rtas_work_area_free() - Release a work area. + * @area: Work area descriptor as returned from rtas_work_area_alloc(). + * + * Return a work area buffer to the pool. + */ +void rtas_work_area_free(struct rtas_work_area *area); + +static inline char *rtas_work_area_raw_buf(const struct rtas_work_area *area) +{ + return area->buf; +} + +static inline size_t rtas_work_area_size(const struct rtas_work_area *area) +{ + return area->size; +} + +static inline phys_addr_t rtas_work_area_phys(const struct rtas_work_area *area) +{ + return __pa(area->buf); +} + +/* + * Early setup for the work area allocator. Call from + * rtas_initialize() only. + */ + +#ifdef CONFIG_PPC_PSERIES +void rtas_work_area_reserve_arena(phys_addr_t limit); +#else /* CONFIG_PPC_PSERIES */ +static inline void rtas_work_area_reserve_arena(phys_addr_t limit) {} +#endif /* CONFIG_PPC_PSERIES */ + +#endif /* _ASM_POWERPC_RTAS_WORK_AREA_H */ diff --git a/arch/powerpc/include/asm/rtas.h b/arch/powerpc/include/asm/rtas.h index 3c1887351c71..9bb2210c8d44 100644 --- a/arch/powerpc/include/asm/rtas.h +++ b/arch/powerpc/include/asm/rtas.h @@ -3,8 +3,10 @@ #define _POWERPC_RTAS_H #ifdef __KERNEL__ +#include <linux/mutex.h> #include <linux/spinlock.h> #include <asm/page.h> +#include <asm/rtas-types.h> #include <linux/time.h> #include <linux/cpumask.h> @@ -15,59 +17,216 @@ * Copyright (C) 2001 PPC 64 Team, IBM Corp */ +enum rtas_function_index { + RTAS_FNIDX__CHECK_EXCEPTION, + RTAS_FNIDX__DISPLAY_CHARACTER, + RTAS_FNIDX__EVENT_SCAN, + RTAS_FNIDX__FREEZE_TIME_BASE, + RTAS_FNIDX__GET_POWER_LEVEL, + RTAS_FNIDX__GET_SENSOR_STATE, + RTAS_FNIDX__GET_TERM_CHAR, + RTAS_FNIDX__GET_TIME_OF_DAY, + RTAS_FNIDX__IBM_ACTIVATE_FIRMWARE, + RTAS_FNIDX__IBM_CBE_START_PTCAL, + RTAS_FNIDX__IBM_CBE_STOP_PTCAL, + RTAS_FNIDX__IBM_CHANGE_MSI, + RTAS_FNIDX__IBM_CLOSE_ERRINJCT, + RTAS_FNIDX__IBM_CONFIGURE_BRIDGE, + RTAS_FNIDX__IBM_CONFIGURE_CONNECTOR, + RTAS_FNIDX__IBM_CONFIGURE_KERNEL_DUMP, + RTAS_FNIDX__IBM_CONFIGURE_PE, + RTAS_FNIDX__IBM_CREATE_PE_DMA_WINDOW, + RTAS_FNIDX__IBM_DISPLAY_MESSAGE, + RTAS_FNIDX__IBM_ERRINJCT, + RTAS_FNIDX__IBM_EXTI2C, + RTAS_FNIDX__IBM_GET_CONFIG_ADDR_INFO, + RTAS_FNIDX__IBM_GET_CONFIG_ADDR_INFO2, + RTAS_FNIDX__IBM_GET_DYNAMIC_SENSOR_STATE, + RTAS_FNIDX__IBM_GET_INDICES, + RTAS_FNIDX__IBM_GET_RIO_TOPOLOGY, + RTAS_FNIDX__IBM_GET_SYSTEM_PARAMETER, + RTAS_FNIDX__IBM_GET_VPD, + RTAS_FNIDX__IBM_GET_XIVE, + RTAS_FNIDX__IBM_INT_OFF, + RTAS_FNIDX__IBM_INT_ON, + RTAS_FNIDX__IBM_IO_QUIESCE_ACK, + RTAS_FNIDX__IBM_LPAR_PERFTOOLS, + RTAS_FNIDX__IBM_MANAGE_FLASH_IMAGE, + RTAS_FNIDX__IBM_MANAGE_STORAGE_PRESERVATION, + RTAS_FNIDX__IBM_NMI_INTERLOCK, + RTAS_FNIDX__IBM_NMI_REGISTER, + RTAS_FNIDX__IBM_OPEN_ERRINJCT, + RTAS_FNIDX__IBM_OPEN_SRIOV_ALLOW_UNFREEZE, + RTAS_FNIDX__IBM_OPEN_SRIOV_MAP_PE_NUMBER, + RTAS_FNIDX__IBM_OS_TERM, + RTAS_FNIDX__IBM_PARTNER_CONTROL, + RTAS_FNIDX__IBM_PHYSICAL_ATTESTATION, + RTAS_FNIDX__IBM_PLATFORM_DUMP, + RTAS_FNIDX__IBM_POWER_OFF_UPS, + RTAS_FNIDX__IBM_QUERY_INTERRUPT_SOURCE_NUMBER, + RTAS_FNIDX__IBM_QUERY_PE_DMA_WINDOW, + RTAS_FNIDX__IBM_READ_PCI_CONFIG, + RTAS_FNIDX__IBM_READ_SLOT_RESET_STATE, + RTAS_FNIDX__IBM_READ_SLOT_RESET_STATE2, + RTAS_FNIDX__IBM_REMOVE_PE_DMA_WINDOW, + RTAS_FNIDX__IBM_RESET_PE_DMA_WINDOWS, + RTAS_FNIDX__IBM_SCAN_LOG_DUMP, + RTAS_FNIDX__IBM_SET_DYNAMIC_INDICATOR, + RTAS_FNIDX__IBM_SET_EEH_OPTION, + RTAS_FNIDX__IBM_SET_SLOT_RESET, + RTAS_FNIDX__IBM_SET_SYSTEM_PARAMETER, + RTAS_FNIDX__IBM_SET_XIVE, + RTAS_FNIDX__IBM_SLOT_ERROR_DETAIL, + RTAS_FNIDX__IBM_SUSPEND_ME, + RTAS_FNIDX__IBM_TUNE_DMA_PARMS, + RTAS_FNIDX__IBM_UPDATE_FLASH_64_AND_REBOOT, + RTAS_FNIDX__IBM_UPDATE_NODES, + RTAS_FNIDX__IBM_UPDATE_PROPERTIES, + RTAS_FNIDX__IBM_VALIDATE_FLASH_IMAGE, + RTAS_FNIDX__IBM_WRITE_PCI_CONFIG, + RTAS_FNIDX__NVRAM_FETCH, + RTAS_FNIDX__NVRAM_STORE, + RTAS_FNIDX__POWER_OFF, + RTAS_FNIDX__PUT_TERM_CHAR, + RTAS_FNIDX__QUERY_CPU_STOPPED_STATE, + RTAS_FNIDX__READ_PCI_CONFIG, + RTAS_FNIDX__RTAS_LAST_ERROR, + RTAS_FNIDX__SET_INDICATOR, + RTAS_FNIDX__SET_POWER_LEVEL, + RTAS_FNIDX__SET_TIME_FOR_POWER_ON, + RTAS_FNIDX__SET_TIME_OF_DAY, + RTAS_FNIDX__START_CPU, + RTAS_FNIDX__STOP_SELF, + RTAS_FNIDX__SYSTEM_REBOOT, + RTAS_FNIDX__THAW_TIME_BASE, + RTAS_FNIDX__WRITE_PCI_CONFIG, +}; + +/* + * Opaque handle for client code to refer to RTAS functions. All valid + * function handles are build-time constants prefixed with RTAS_FN_. + */ +typedef struct { + const enum rtas_function_index index; +} rtas_fn_handle_t; + + +#define rtas_fn_handle(x_) ((const rtas_fn_handle_t) { .index = x_, }) + +#define RTAS_FN_CHECK_EXCEPTION rtas_fn_handle(RTAS_FNIDX__CHECK_EXCEPTION) +#define RTAS_FN_DISPLAY_CHARACTER rtas_fn_handle(RTAS_FNIDX__DISPLAY_CHARACTER) +#define RTAS_FN_EVENT_SCAN rtas_fn_handle(RTAS_FNIDX__EVENT_SCAN) +#define RTAS_FN_FREEZE_TIME_BASE rtas_fn_handle(RTAS_FNIDX__FREEZE_TIME_BASE) +#define RTAS_FN_GET_POWER_LEVEL rtas_fn_handle(RTAS_FNIDX__GET_POWER_LEVEL) +#define RTAS_FN_GET_SENSOR_STATE rtas_fn_handle(RTAS_FNIDX__GET_SENSOR_STATE) +#define RTAS_FN_GET_TERM_CHAR rtas_fn_handle(RTAS_FNIDX__GET_TERM_CHAR) +#define RTAS_FN_GET_TIME_OF_DAY rtas_fn_handle(RTAS_FNIDX__GET_TIME_OF_DAY) +#define RTAS_FN_IBM_ACTIVATE_FIRMWARE rtas_fn_handle(RTAS_FNIDX__IBM_ACTIVATE_FIRMWARE) +#define RTAS_FN_IBM_CBE_START_PTCAL rtas_fn_handle(RTAS_FNIDX__IBM_CBE_START_PTCAL) +#define RTAS_FN_IBM_CBE_STOP_PTCAL rtas_fn_handle(RTAS_FNIDX__IBM_CBE_STOP_PTCAL) +#define RTAS_FN_IBM_CHANGE_MSI rtas_fn_handle(RTAS_FNIDX__IBM_CHANGE_MSI) +#define RTAS_FN_IBM_CLOSE_ERRINJCT rtas_fn_handle(RTAS_FNIDX__IBM_CLOSE_ERRINJCT) +#define RTAS_FN_IBM_CONFIGURE_BRIDGE rtas_fn_handle(RTAS_FNIDX__IBM_CONFIGURE_BRIDGE) +#define RTAS_FN_IBM_CONFIGURE_CONNECTOR rtas_fn_handle(RTAS_FNIDX__IBM_CONFIGURE_CONNECTOR) +#define RTAS_FN_IBM_CONFIGURE_KERNEL_DUMP rtas_fn_handle(RTAS_FNIDX__IBM_CONFIGURE_KERNEL_DUMP) +#define RTAS_FN_IBM_CONFIGURE_PE rtas_fn_handle(RTAS_FNIDX__IBM_CONFIGURE_PE) +#define RTAS_FN_IBM_CREATE_PE_DMA_WINDOW rtas_fn_handle(RTAS_FNIDX__IBM_CREATE_PE_DMA_WINDOW) +#define RTAS_FN_IBM_DISPLAY_MESSAGE rtas_fn_handle(RTAS_FNIDX__IBM_DISPLAY_MESSAGE) +#define RTAS_FN_IBM_ERRINJCT rtas_fn_handle(RTAS_FNIDX__IBM_ERRINJCT) +#define RTAS_FN_IBM_EXTI2C rtas_fn_handle(RTAS_FNIDX__IBM_EXTI2C) +#define RTAS_FN_IBM_GET_CONFIG_ADDR_INFO rtas_fn_handle(RTAS_FNIDX__IBM_GET_CONFIG_ADDR_INFO) +#define RTAS_FN_IBM_GET_CONFIG_ADDR_INFO2 rtas_fn_handle(RTAS_FNIDX__IBM_GET_CONFIG_ADDR_INFO2) +#define RTAS_FN_IBM_GET_DYNAMIC_SENSOR_STATE rtas_fn_handle(RTAS_FNIDX__IBM_GET_DYNAMIC_SENSOR_STATE) +#define RTAS_FN_IBM_GET_INDICES rtas_fn_handle(RTAS_FNIDX__IBM_GET_INDICES) +#define RTAS_FN_IBM_GET_RIO_TOPOLOGY rtas_fn_handle(RTAS_FNIDX__IBM_GET_RIO_TOPOLOGY) +#define RTAS_FN_IBM_GET_SYSTEM_PARAMETER rtas_fn_handle(RTAS_FNIDX__IBM_GET_SYSTEM_PARAMETER) +#define RTAS_FN_IBM_GET_VPD rtas_fn_handle(RTAS_FNIDX__IBM_GET_VPD) +#define RTAS_FN_IBM_GET_XIVE rtas_fn_handle(RTAS_FNIDX__IBM_GET_XIVE) +#define RTAS_FN_IBM_INT_OFF rtas_fn_handle(RTAS_FNIDX__IBM_INT_OFF) +#define RTAS_FN_IBM_INT_ON rtas_fn_handle(RTAS_FNIDX__IBM_INT_ON) +#define RTAS_FN_IBM_IO_QUIESCE_ACK rtas_fn_handle(RTAS_FNIDX__IBM_IO_QUIESCE_ACK) +#define RTAS_FN_IBM_LPAR_PERFTOOLS rtas_fn_handle(RTAS_FNIDX__IBM_LPAR_PERFTOOLS) +#define RTAS_FN_IBM_MANAGE_FLASH_IMAGE rtas_fn_handle(RTAS_FNIDX__IBM_MANAGE_FLASH_IMAGE) +#define RTAS_FN_IBM_MANAGE_STORAGE_PRESERVATION rtas_fn_handle(RTAS_FNIDX__IBM_MANAGE_STORAGE_PRESERVATION) +#define RTAS_FN_IBM_NMI_INTERLOCK rtas_fn_handle(RTAS_FNIDX__IBM_NMI_INTERLOCK) +#define RTAS_FN_IBM_NMI_REGISTER rtas_fn_handle(RTAS_FNIDX__IBM_NMI_REGISTER) +#define RTAS_FN_IBM_OPEN_ERRINJCT rtas_fn_handle(RTAS_FNIDX__IBM_OPEN_ERRINJCT) +#define RTAS_FN_IBM_OPEN_SRIOV_ALLOW_UNFREEZE rtas_fn_handle(RTAS_FNIDX__IBM_OPEN_SRIOV_ALLOW_UNFREEZE) +#define RTAS_FN_IBM_OPEN_SRIOV_MAP_PE_NUMBER rtas_fn_handle(RTAS_FNIDX__IBM_OPEN_SRIOV_MAP_PE_NUMBER) +#define RTAS_FN_IBM_OS_TERM rtas_fn_handle(RTAS_FNIDX__IBM_OS_TERM) +#define RTAS_FN_IBM_PARTNER_CONTROL rtas_fn_handle(RTAS_FNIDX__IBM_PARTNER_CONTROL) +#define RTAS_FN_IBM_PHYSICAL_ATTESTATION rtas_fn_handle(RTAS_FNIDX__IBM_PHYSICAL_ATTESTATION) +#define RTAS_FN_IBM_PLATFORM_DUMP rtas_fn_handle(RTAS_FNIDX__IBM_PLATFORM_DUMP) +#define RTAS_FN_IBM_POWER_OFF_UPS rtas_fn_handle(RTAS_FNIDX__IBM_POWER_OFF_UPS) +#define RTAS_FN_IBM_QUERY_INTERRUPT_SOURCE_NUMBER rtas_fn_handle(RTAS_FNIDX__IBM_QUERY_INTERRUPT_SOURCE_NUMBER) +#define RTAS_FN_IBM_QUERY_PE_DMA_WINDOW rtas_fn_handle(RTAS_FNIDX__IBM_QUERY_PE_DMA_WINDOW) +#define RTAS_FN_IBM_READ_PCI_CONFIG rtas_fn_handle(RTAS_FNIDX__IBM_READ_PCI_CONFIG) +#define RTAS_FN_IBM_READ_SLOT_RESET_STATE rtas_fn_handle(RTAS_FNIDX__IBM_READ_SLOT_RESET_STATE) +#define RTAS_FN_IBM_READ_SLOT_RESET_STATE2 rtas_fn_handle(RTAS_FNIDX__IBM_READ_SLOT_RESET_STATE2) +#define RTAS_FN_IBM_REMOVE_PE_DMA_WINDOW rtas_fn_handle(RTAS_FNIDX__IBM_REMOVE_PE_DMA_WINDOW) +#define RTAS_FN_IBM_RESET_PE_DMA_WINDOWS rtas_fn_handle(RTAS_FNIDX__IBM_RESET_PE_DMA_WINDOWS) +#define RTAS_FN_IBM_SCAN_LOG_DUMP rtas_fn_handle(RTAS_FNIDX__IBM_SCAN_LOG_DUMP) +#define RTAS_FN_IBM_SET_DYNAMIC_INDICATOR rtas_fn_handle(RTAS_FNIDX__IBM_SET_DYNAMIC_INDICATOR) +#define RTAS_FN_IBM_SET_EEH_OPTION rtas_fn_handle(RTAS_FNIDX__IBM_SET_EEH_OPTION) +#define RTAS_FN_IBM_SET_SLOT_RESET rtas_fn_handle(RTAS_FNIDX__IBM_SET_SLOT_RESET) +#define RTAS_FN_IBM_SET_SYSTEM_PARAMETER rtas_fn_handle(RTAS_FNIDX__IBM_SET_SYSTEM_PARAMETER) +#define RTAS_FN_IBM_SET_XIVE rtas_fn_handle(RTAS_FNIDX__IBM_SET_XIVE) +#define RTAS_FN_IBM_SLOT_ERROR_DETAIL rtas_fn_handle(RTAS_FNIDX__IBM_SLOT_ERROR_DETAIL) +#define RTAS_FN_IBM_SUSPEND_ME rtas_fn_handle(RTAS_FNIDX__IBM_SUSPEND_ME) +#define RTAS_FN_IBM_TUNE_DMA_PARMS rtas_fn_handle(RTAS_FNIDX__IBM_TUNE_DMA_PARMS) +#define RTAS_FN_IBM_UPDATE_FLASH_64_AND_REBOOT rtas_fn_handle(RTAS_FNIDX__IBM_UPDATE_FLASH_64_AND_REBOOT) +#define RTAS_FN_IBM_UPDATE_NODES rtas_fn_handle(RTAS_FNIDX__IBM_UPDATE_NODES) +#define RTAS_FN_IBM_UPDATE_PROPERTIES rtas_fn_handle(RTAS_FNIDX__IBM_UPDATE_PROPERTIES) +#define RTAS_FN_IBM_VALIDATE_FLASH_IMAGE rtas_fn_handle(RTAS_FNIDX__IBM_VALIDATE_FLASH_IMAGE) +#define RTAS_FN_IBM_WRITE_PCI_CONFIG rtas_fn_handle(RTAS_FNIDX__IBM_WRITE_PCI_CONFIG) +#define RTAS_FN_NVRAM_FETCH rtas_fn_handle(RTAS_FNIDX__NVRAM_FETCH) +#define RTAS_FN_NVRAM_STORE rtas_fn_handle(RTAS_FNIDX__NVRAM_STORE) +#define RTAS_FN_POWER_OFF rtas_fn_handle(RTAS_FNIDX__POWER_OFF) +#define RTAS_FN_PUT_TERM_CHAR rtas_fn_handle(RTAS_FNIDX__PUT_TERM_CHAR) +#define RTAS_FN_QUERY_CPU_STOPPED_STATE rtas_fn_handle(RTAS_FNIDX__QUERY_CPU_STOPPED_STATE) +#define RTAS_FN_READ_PCI_CONFIG rtas_fn_handle(RTAS_FNIDX__READ_PCI_CONFIG) +#define RTAS_FN_RTAS_LAST_ERROR rtas_fn_handle(RTAS_FNIDX__RTAS_LAST_ERROR) +#define RTAS_FN_SET_INDICATOR rtas_fn_handle(RTAS_FNIDX__SET_INDICATOR) +#define RTAS_FN_SET_POWER_LEVEL rtas_fn_handle(RTAS_FNIDX__SET_POWER_LEVEL) +#define RTAS_FN_SET_TIME_FOR_POWER_ON rtas_fn_handle(RTAS_FNIDX__SET_TIME_FOR_POWER_ON) +#define RTAS_FN_SET_TIME_OF_DAY rtas_fn_handle(RTAS_FNIDX__SET_TIME_OF_DAY) +#define RTAS_FN_START_CPU rtas_fn_handle(RTAS_FNIDX__START_CPU) +#define RTAS_FN_STOP_SELF rtas_fn_handle(RTAS_FNIDX__STOP_SELF) +#define RTAS_FN_SYSTEM_REBOOT rtas_fn_handle(RTAS_FNIDX__SYSTEM_REBOOT) +#define RTAS_FN_THAW_TIME_BASE rtas_fn_handle(RTAS_FNIDX__THAW_TIME_BASE) +#define RTAS_FN_WRITE_PCI_CONFIG rtas_fn_handle(RTAS_FNIDX__WRITE_PCI_CONFIG) + #define RTAS_UNKNOWN_SERVICE (-1) #define RTAS_INSTANTIATE_MAX (1ULL<<30) /* Don't instantiate rtas at/above this value */ -/* Buffer size for ppc_rtas system call. */ -#define RTAS_RMOBUF_MAX (64 * 1024) - -/* RTAS return status codes */ -#define RTAS_NOT_SUSPENDABLE -9004 -#define RTAS_BUSY -2 /* RTAS Busy */ -#define RTAS_EXTENDED_DELAY_MIN 9900 -#define RTAS_EXTENDED_DELAY_MAX 9905 +/* Memory set aside for sys_rtas to use with calls that need a work area. */ +#define RTAS_USER_REGION_SIZE (64 * 1024) /* - * In general to call RTAS use rtas_token("string") to lookup - * an RTAS token for the given string (e.g. "event-scan"). - * To actually perform the call use - * ret = rtas_call(token, n_in, n_out, ...) - * Where n_in is the number of input parameters and - * n_out is the number of output parameters - * - * If the "string" is invalid on this system, RTAS_UNKNOWN_SERVICE - * will be returned as a token. rtas_call() does look for this - * token and error out gracefully so rtas_call(rtas_token("str"), ...) - * may be safely used for one-shot calls to RTAS. + * Common RTAS function return values, derived from the table "RTAS + * Status Word Values" in PAPR+ v2.13 7.2.8: "Return Codes". If a + * function can return a value in this table then generally it has the + * meaning listed here. More extended commentary in the documentation + * for rtas_call(). * + * RTAS functions may use negative and positive numbers not in this + * set for function-specific error and success conditions, + * respectively. */ - -typedef __be32 rtas_arg_t; - -struct rtas_args { - __be32 token; - __be32 nargs; - __be32 nret; - rtas_arg_t args[16]; - rtas_arg_t *rets; /* Pointer to return values in args[]. */ -}; - -struct rtas_t { - unsigned long entry; /* physical address pointer */ - unsigned long base; /* physical address pointer */ - unsigned long size; - arch_spinlock_t lock; - struct rtas_args args; - struct device_node *dev; /* virtual address pointer */ -}; - -struct rtas_suspend_me_data { - atomic_t working; /* number of cpus accessing this struct */ - atomic_t done; - int token; /* ibm,suspend-me */ - atomic_t error; - struct completion *complete; /* wait on this until working == 0 */ -}; +#define RTAS_SUCCESS 0 /* Success. */ +#define RTAS_HARDWARE_ERROR -1 /* Hardware or other unspecified error. */ +#define RTAS_BUSY -2 /* Retry immediately. */ +#define RTAS_INVALID_PARAMETER -3 /* Invalid indicator/domain/sensor etc. */ +#define RTAS_UNEXPECTED_STATE_CHANGE -7 /* Seems limited to EEH and slot reset. */ +#define RTAS_EXTENDED_DELAY_MIN 9900 /* Retry after delaying for ~1ms. */ +#define RTAS_EXTENDED_DELAY_MAX 9905 /* Retry after delaying for ~100s. */ +#define RTAS_ML_ISOLATION_ERROR -9000 /* Multi-level isolation error. */ + +/* statuses specific to ibm,suspend-me */ +#define RTAS_SUSPEND_ABORTED 9000 /* Suspension aborted */ +#define RTAS_NOT_SUSPENDABLE -9004 /* Partition not suspendable */ +#define RTAS_THREADS_ACTIVE -9005 /* Multiple processor threads active */ +#define RTAS_OUTSTANDING_COPROC -9006 /* Outstanding coprocessor operations */ /* RTAS event classes */ #define RTAS_INTERNAL_ERROR 0x80000000 /* set bit 0 */ @@ -123,7 +282,7 @@ struct rtas_suspend_me_data { #define RTAS_TYPE_DEALLOC 0xE3 #define RTAS_TYPE_DUMP 0xE4 #define RTAS_TYPE_HOTPLUG 0xE5 -/* I don't add PowerMGM events right now, this is a different topic */ +/* I don't add PowerMGM events right now, this is a different topic */ #define RTAS_TYPE_PMGM_POWER_SW_ON 0x60 #define RTAS_TYPE_PMGM_POWER_SW_OFF 0x61 #define RTAS_TYPE_PMGM_LID_OPEN 0x62 @@ -148,31 +307,6 @@ struct rtas_suspend_me_data { /* RTAS check-exception vector offset */ #define RTAS_VECTOR_EXTERNAL_INTERRUPT 0x500 -struct rtas_error_log { - /* Byte 0 */ - uint8_t byte0; /* Architectural version */ - - /* Byte 1 */ - uint8_t byte1; - /* XXXXXXXX - * XXX 3: Severity level of error - * XX 2: Degree of recovery - * X 1: Extended log present? - * XX 2: Reserved - */ - - /* Byte 2 */ - uint8_t byte2; - /* XXXXXXXX - * XXXX 4: Initiator of event - * XXXX 4: Target of failed operation - */ - uint8_t byte3; /* General event or error*/ - __be32 extended_log_length; /* length in bytes */ - unsigned char buffer[1]; /* Start of extended log */ - /* Variable length. */ -}; - static inline uint8_t rtas_error_severity(const struct rtas_error_log *elog) { return (elog->byte1 & 0xE0) >> 5; @@ -212,47 +346,6 @@ uint32_t rtas_error_extended_log_length(const struct rtas_error_log *elog) #define RTAS_V6EXT_COMPANY_ID_IBM (('I' << 24) | ('B' << 16) | ('M' << 8)) -/* RTAS general extended event log, Version 6. The extended log starts - * from "buffer" field of struct rtas_error_log defined above. - */ -struct rtas_ext_event_log_v6 { - /* Byte 0 */ - uint8_t byte0; - /* XXXXXXXX - * X 1: Log valid - * X 1: Unrecoverable error - * X 1: Recoverable (correctable or successfully retried) - * X 1: Bypassed unrecoverable error (degraded operation) - * X 1: Predictive error - * X 1: "New" log (always 1 for data returned from RTAS) - * X 1: Big Endian - * X 1: Reserved - */ - - /* Byte 1 */ - uint8_t byte1; /* reserved */ - - /* Byte 2 */ - uint8_t byte2; - /* XXXXXXXX - * X 1: Set to 1 (indicating log is in PowerPC format) - * XXX 3: Reserved - * XXXX 4: Log format used for bytes 12-2047 - */ - - /* Byte 3 */ - uint8_t byte3; /* reserved */ - /* Byte 4-11 */ - uint8_t reserved[8]; /* reserved */ - /* Byte 12-15 */ - __be32 company_id; /* Company ID of the company */ - /* that defines the format for */ - /* the vendor specific log type */ - /* Byte 16-end of log */ - uint8_t vendor_log[1]; /* Start of vendor specific log */ - /* Variable length. */ -}; - static inline uint8_t rtas_ext_event_log_format(struct rtas_ext_event_log_v6 *ext_log) { @@ -287,16 +380,6 @@ inline uint32_t rtas_ext_event_company_id(struct rtas_ext_event_log_v6 *ext_log) #define PSERIES_ELOG_SECT_ID_HOTPLUG (('H' << 8) | 'P') #define PSERIES_ELOG_SECT_ID_MCE (('M' << 8) | 'C') -/* Vendor specific Platform Event Log Format, Version 6, section header */ -struct pseries_errorlog { - __be16 id; /* 0x00 2-byte ASCII section ID */ - __be16 length; /* 0x02 Section length in bytes */ - uint8_t version; /* 0x04 Section version */ - uint8_t subtype; /* 0x05 Section subtype */ - __be16 creator_component; /* 0x06 Creator component ID */ - uint8_t data[]; /* 0x08 Start of section data */ -}; - static inline uint16_t pseries_errorlog_id(struct pseries_errorlog *sect) { @@ -309,20 +392,6 @@ inline uint16_t pseries_errorlog_length(struct pseries_errorlog *sect) return be16_to_cpu(sect->length); } -/* RTAS pseries hotplug errorlog section */ -struct pseries_hp_errorlog { - u8 resource; - u8 action; - u8 id_type; - u8 reserved; - union { - __be32 drc_index; - __be32 drc_count; - struct { __be32 count, index; } ic; - char drc_name[1]; - } _drc_u; -}; - #define PSERIES_HP_ELOG_RESOURCE_CPU 1 #define PSERIES_HP_ELOG_RESOURCE_MEM 2 #define PSERIES_HP_ELOG_RESOURCE_SLOT 3 @@ -331,7 +400,6 @@ struct pseries_hp_errorlog { #define PSERIES_HP_ELOG_ACTION_ADD 1 #define PSERIES_HP_ELOG_ACTION_REMOVE 2 -#define PSERIES_HP_ELOG_ACTION_READD 3 #define PSERIES_HP_ELOG_ID_DRC_NAME 1 #define PSERIES_HP_ELOG_ID_DRC_INDEX 2 @@ -349,60 +417,64 @@ extern void (*rtas_flash_term_hook)(int); extern struct rtas_t rtas; -extern int rtas_token(const char *service); -extern int rtas_service_present(const char *service); -extern int rtas_call(int token, int, int, int *, ...); +s32 rtas_function_token(const rtas_fn_handle_t handle); +static inline bool rtas_function_implemented(const rtas_fn_handle_t handle) +{ + return rtas_function_token(handle) != RTAS_UNKNOWN_SERVICE; +} +int rtas_token(const char *service); +int rtas_call(int token, int nargs, int nret, int *outputs, ...); void rtas_call_unlocked(struct rtas_args *args, int token, int nargs, int nret, ...); -extern void __noreturn rtas_restart(char *cmd); -extern void rtas_power_off(void); -extern void __noreturn rtas_halt(void); -extern void rtas_os_term(char *str); -extern int rtas_get_sensor(int sensor, int index, int *state); -extern int rtas_get_sensor_fast(int sensor, int index, int *state); -extern int rtas_get_power_level(int powerdomain, int *level); -extern int rtas_set_power_level(int powerdomain, int level, int *setlevel); -extern bool rtas_indicator_present(int token, int *maxindex); -extern int rtas_set_indicator(int indicator, int index, int new_value); -extern int rtas_set_indicator_fast(int indicator, int index, int new_value); -extern void rtas_progress(char *s, unsigned short hex); -extern int rtas_suspend_cpu(struct rtas_suspend_me_data *data); -extern int rtas_suspend_last_cpu(struct rtas_suspend_me_data *data); -extern int rtas_online_cpus_mask(cpumask_var_t cpus); -extern int rtas_offline_cpus_mask(cpumask_var_t cpus); -extern int rtas_ibm_suspend_me(u64 handle); +void __noreturn rtas_restart(char *cmd); +void rtas_power_off(void); +void __noreturn rtas_halt(void); +void rtas_os_term(char *str); +void rtas_activate_firmware(void); +int rtas_get_sensor(int sensor, int index, int *state); +int rtas_get_sensor_fast(int sensor, int index, int *state); +int rtas_get_power_level(int powerdomain, int *level); +int rtas_set_power_level(int powerdomain, int level, int *setlevel); +bool rtas_indicator_present(int token, int *maxindex); +int rtas_set_indicator(int indicator, int index, int new_value); +int rtas_set_indicator_fast(int indicator, int index, int new_value); +void rtas_progress(char *s, unsigned short hex); +int rtas_ibm_suspend_me(int *fw_status); +int rtas_error_rc(int rtas_rc); struct rtc_time; -extern time64_t rtas_get_boot_time(void); -extern void rtas_get_rtc_time(struct rtc_time *rtc_time); -extern int rtas_set_rtc_time(struct rtc_time *rtc_time); +time64_t rtas_get_boot_time(void); +void rtas_get_rtc_time(struct rtc_time *rtc_time); +int rtas_set_rtc_time(struct rtc_time *rtc_time); -extern unsigned int rtas_busy_delay_time(int status); -extern unsigned int rtas_busy_delay(int status); +unsigned int rtas_busy_delay_time(int status); +bool rtas_busy_delay(int status); -extern int early_init_dt_scan_rtas(unsigned long node, - const char *uname, int depth, void *data); +int early_init_dt_scan_rtas(unsigned long node, const char *uname, int depth, void *data); -extern void pSeries_log_error(char *buf, unsigned int err_type, int fatal); +void pSeries_log_error(char *buf, unsigned int err_type, int fatal); #ifdef CONFIG_PPC_PSERIES extern time64_t last_rtas_event; -extern int clobbering_unread_rtas_event(void); -extern int pseries_devicetree_update(s32 scope); -extern void post_mobility_fixup(void); +int clobbering_unread_rtas_event(void); +int rtas_syscall_dispatch_ibm_suspend_me(u64 handle); #else static inline int clobbering_unread_rtas_event(void) { return 0; } +static inline int rtas_syscall_dispatch_ibm_suspend_me(u64 handle) +{ + return -EINVAL; +} #endif #ifdef CONFIG_PPC_RTAS_DAEMON -extern void rtas_cancel_event_scan(void); +void rtas_cancel_event_scan(void); #else static inline void rtas_cancel_event_scan(void) { } #endif /* Error types logged. */ #define ERR_FLAG_ALREADY_LOGGED 0x0 -#define ERR_FLAG_BOOT 0x1 /* log was pulled from NVRAM on boot */ +#define ERR_FLAG_BOOT 0x1 /* log was pulled from NVRAM on boot */ #define ERR_TYPE_RTAS_LOG 0x2 /* from rtas event-scan */ #define ERR_TYPE_KERNEL_PANIC 0x4 /* from die()/panic() */ #define ERR_TYPE_KERNEL_PANIC_GZ 0x8 /* ditto, compressed */ @@ -412,7 +484,7 @@ static inline void rtas_cancel_event_scan(void) { } (ERR_TYPE_RTAS_LOG | ERR_TYPE_KERNEL_PANIC | ERR_TYPE_KERNEL_PANIC_GZ) #define RTAS_DEBUG KERN_DEBUG "RTAS: " - + #define RTAS_ERROR_LOG_MAX 2048 /* @@ -420,7 +492,7 @@ static inline void rtas_cancel_event_scan(void) { } * for all rtas calls that require an error buffer argument. * This includes 'check-exception' and 'rtas-last-error'. */ -extern int rtas_get_error_log_max(void); +int rtas_get_error_log_max(void); /* Event Scan Parameters */ #define EVENT_SCAN_ALL_EVENTS 0xf0000000 @@ -441,6 +513,8 @@ extern char rtas_data_buf[RTAS_DATA_BUF_SIZE]; /* RMO buffer reserved for user-space RTAS use */ extern unsigned long rtas_rmo_buf; +extern struct mutex rtas_ibm_get_vpd_lock; + #define GLOBAL_INTERRUPT_QUEUE 9005 /** @@ -459,29 +533,33 @@ static inline u32 rtas_config_addr(int busno, int devfn, int reg) (devfn << 8) | (reg & 0xff); } -extern void rtas_give_timebase(void); -extern void rtas_take_timebase(void); +void rtas_give_timebase(void); +void rtas_take_timebase(void); #ifdef CONFIG_PPC_RTAS static inline int page_is_rtas_user_buf(unsigned long pfn) { unsigned long paddr = (pfn << PAGE_SHIFT); - if (paddr >= rtas_rmo_buf && paddr < (rtas_rmo_buf + RTAS_RMOBUF_MAX)) + if (paddr >= rtas_rmo_buf && paddr < (rtas_rmo_buf + RTAS_USER_REGION_SIZE)) return 1; return 0; } /* Not the best place to put pSeries_coalesce_init, will be fixed when we * move some of the rtas suspend-me stuff to pseries */ -extern void pSeries_coalesce_init(void); +void pSeries_coalesce_init(void); void rtas_initialize(void); #else static inline int page_is_rtas_user_buf(unsigned long pfn) { return 0;} static inline void pSeries_coalesce_init(void) { } -static inline void rtas_initialize(void) { }; +static inline void rtas_initialize(void) { } #endif -extern int call_rtas(const char *, int, int, unsigned long *, ...); +#ifdef CONFIG_HV_PERF_CTRS +void read_24x7_sys_info(void); +#else +static inline void read_24x7_sys_info(void) { } +#endif #endif /* __KERNEL__ */ #endif /* _POWERPC_RTAS_H */ diff --git a/arch/powerpc/include/asm/runlatch.h b/arch/powerpc/include/asm/runlatch.h index cfb390edf7d0..ceb66d761fe1 100644 --- a/arch/powerpc/include/asm/runlatch.h +++ b/arch/powerpc/include/asm/runlatch.h @@ -19,10 +19,9 @@ extern void __ppc64_runlatch_off(void); do { \ if (cpu_has_feature(CPU_FTR_CTRL) && \ test_thread_local_flags(_TLF_RUNLATCH)) { \ - unsigned long msr = mfmsr(); \ __hard_irq_disable(); \ __ppc64_runlatch_off(); \ - if (msr & MSR_EE) \ + if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS)) \ __hard_irq_enable(); \ } \ } while (0) @@ -31,10 +30,9 @@ extern void __ppc64_runlatch_off(void); do { \ if (cpu_has_feature(CPU_FTR_CTRL) && \ !test_thread_local_flags(_TLF_RUNLATCH)) { \ - unsigned long msr = mfmsr(); \ __hard_irq_disable(); \ __ppc64_runlatch_on(); \ - if (msr & MSR_EE) \ + if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS)) \ __hard_irq_enable(); \ } \ } while (0) diff --git a/arch/powerpc/include/asm/seccomp.h b/arch/powerpc/include/asm/seccomp.h index 51209f6071c5..ac2033f134f0 100644 --- a/arch/powerpc/include/asm/seccomp.h +++ b/arch/powerpc/include/asm/seccomp.h @@ -8,4 +8,27 @@ #include <asm-generic/seccomp.h> +#ifdef __LITTLE_ENDIAN__ +#define __SECCOMP_ARCH_LE __AUDIT_ARCH_LE +#define __SECCOMP_ARCH_LE_NAME "le" +#else +#define __SECCOMP_ARCH_LE 0 +#define __SECCOMP_ARCH_LE_NAME +#endif + +#ifdef CONFIG_PPC64 +# define SECCOMP_ARCH_NATIVE (AUDIT_ARCH_PPC64 | __SECCOMP_ARCH_LE) +# define SECCOMP_ARCH_NATIVE_NR NR_syscalls +# define SECCOMP_ARCH_NATIVE_NAME "ppc64" __SECCOMP_ARCH_LE_NAME +# ifdef CONFIG_COMPAT +# define SECCOMP_ARCH_COMPAT (AUDIT_ARCH_PPC | __SECCOMP_ARCH_LE) +# define SECCOMP_ARCH_COMPAT_NR NR_syscalls +# define SECCOMP_ARCH_COMPAT_NAME "ppc" __SECCOMP_ARCH_LE_NAME +# endif +#else /* !CONFIG_PPC64 */ +# define SECCOMP_ARCH_NATIVE (AUDIT_ARCH_PPC | __SECCOMP_ARCH_LE) +# define SECCOMP_ARCH_NATIVE_NR NR_syscalls +# define SECCOMP_ARCH_NATIVE_NAME "ppc" __SECCOMP_ARCH_LE_NAME +#endif + #endif /* _ASM_POWERPC_SECCOMP_H */ diff --git a/arch/powerpc/include/asm/sections.h b/arch/powerpc/include/asm/sections.h index d19871763ed4..ea26665f82cf 100644 --- a/arch/powerpc/include/asm/sections.h +++ b/arch/powerpc/include/asm/sections.h @@ -6,31 +6,33 @@ #include <linux/elf.h> #include <linux/uaccess.h> -#define arch_is_kernel_initmem_freed arch_is_kernel_initmem_freed +#ifdef CONFIG_HAVE_FUNCTION_DESCRIPTORS +typedef struct func_desc func_desc_t; +#endif #include <asm-generic/sections.h> -extern bool init_mem_is_free; - -static inline int arch_is_kernel_initmem_freed(unsigned long addr) -{ - if (!init_mem_is_free) - return 0; +extern char __head_end[]; +extern char __srwx_boundary[]; - return addr >= (unsigned long)__init_begin && - addr < (unsigned long)__init_end; -} +/* Patch sites */ +extern s32 patch__call_flush_branch_caches1; +extern s32 patch__call_flush_branch_caches2; +extern s32 patch__call_flush_branch_caches3; +extern s32 patch__flush_count_cache_return; +extern s32 patch__flush_link_stack_return; +extern s32 patch__call_kvm_flush_link_stack; +extern s32 patch__call_kvm_flush_link_stack_p9; +extern s32 patch__memset_nocache, patch__memcpy_nocache; -extern char __head_end[]; +extern long flush_branch_caches; +extern long kvm_flush_link_stack; #ifdef __powerpc64__ extern char __start_interrupts[]; extern char __end_interrupts[]; -extern char __prom_init_toc_start[]; -extern char __prom_init_toc_end[]; - #ifdef CONFIG_PPC_POWERNV extern char start_real_trampolines[]; extern char end_real_trampolines[]; @@ -38,24 +40,21 @@ extern char start_virt_trampolines[]; extern char end_virt_trampolines[]; #endif -static inline int in_kernel_text(unsigned long addr) -{ - if (addr >= (unsigned long)_stext && addr < (unsigned long)__init_end) - return 1; - - return 0; -} - +/* + * This assumes the kernel is never compiled -mcmodel=small or + * the total .toc is always less than 64k. + */ static inline unsigned long kernel_toc_addr(void) { - /* Defined by the linker, see vmlinux.lds.S */ - extern unsigned long __toc_start; - - /* - * The TOC register (r2) points 32kB into the TOC, so that 64kB of - * the TOC can be addressed using a single machine instruction. - */ - return (unsigned long)(&__toc_start) + 0x8000UL; +#ifdef CONFIG_PPC_KERNEL_PCREL + BUILD_BUG(); + return -1UL; +#else + unsigned long toc_ptr; + + asm volatile("mr %0, 2" : "=r" (toc_ptr)); + return toc_ptr; +#endif } static inline int overlaps_interrupt_vector_text(unsigned long start, @@ -75,31 +74,8 @@ static inline int overlaps_kernel_text(unsigned long start, unsigned long end) (unsigned long)_stext < end; } -#ifdef PPC64_ELF_ABI_v1 - -#define HAVE_DEREFERENCE_FUNCTION_DESCRIPTOR 1 - -#undef dereference_function_descriptor -static inline void *dereference_function_descriptor(void *ptr) -{ - struct ppc64_opd_entry *desc = ptr; - void *p; - - if (!probe_kernel_address(&desc->funcaddr, p)) - ptr = p; - return ptr; -} - -#undef dereference_kernel_function_descriptor -static inline void *dereference_kernel_function_descriptor(void *ptr) -{ - if (ptr < (void *)__start_opd || ptr >= (void *)__end_opd) - return ptr; - - return dereference_function_descriptor(ptr); -} -#endif /* PPC64_ELF_ABI_v1 */ - +#else +static inline unsigned long kernel_toc_addr(void) { BUILD_BUG(); return -1UL; } #endif #endif /* __KERNEL__ */ diff --git a/arch/powerpc/include/asm/security_features.h b/arch/powerpc/include/asm/security_features.h index 7c05e95a5c44..27574f218b37 100644 --- a/arch/powerpc/include/asm/security_features.h +++ b/arch/powerpc/include/asm/security_features.h @@ -39,6 +39,11 @@ static inline bool security_ftr_enabled(u64 feature) return !!(powerpc_security_features & feature); } +#ifdef CONFIG_PPC_BOOK3S_64 +enum stf_barrier_type stf_barrier_type_get(void); +#else +static inline enum stf_barrier_type stf_barrier_type_get(void) { return STF_BARRIER_NONE; } +#endif // Features indicating support for Spectre/Meltdown mitigations @@ -63,6 +68,8 @@ static inline bool security_ftr_enabled(u64 feature) // bcctr 2,0,0 triggers a hardware assisted count cache flush #define SEC_FTR_BCCTR_FLUSH_ASSIST 0x0000000000000800ull +// bcctr 2,0,0 triggers a hardware assisted link stack flush +#define SEC_FTR_BCCTR_LINK_FLUSH_ASSIST 0x0000000000002000ull // Features indicating need for Spectre/Meltdown mitigations @@ -84,12 +91,23 @@ static inline bool security_ftr_enabled(u64 feature) // Software required to flush link stack on context switch #define SEC_FTR_FLUSH_LINK_STACK 0x0000000000001000ull +// The L1-D cache should be flushed when entering the kernel +#define SEC_FTR_L1D_FLUSH_ENTRY 0x0000000000004000ull + +// The L1-D cache should be flushed after user accesses from the kernel +#define SEC_FTR_L1D_FLUSH_UACCESS 0x0000000000008000ull + +// The STF flush should be executed on privilege state switch +#define SEC_FTR_STF_BARRIER 0x0000000000010000ull // Features enabled by default #define SEC_FTR_DEFAULT \ (SEC_FTR_L1D_FLUSH_HV | \ SEC_FTR_L1D_FLUSH_PR | \ SEC_FTR_BNDS_CHK_SPEC_BAR | \ + SEC_FTR_L1D_FLUSH_ENTRY | \ + SEC_FTR_L1D_FLUSH_UACCESS | \ + SEC_FTR_STF_BARRIER | \ SEC_FTR_FAVOUR_SECURITY) #endif /* _ASM_POWERPC_SECURITY_FEATURES_H */ diff --git a/arch/powerpc/include/asm/secvar.h b/arch/powerpc/include/asm/secvar.h index 4cc35b58b986..4828e0ab7e3c 100644 --- a/arch/powerpc/include/asm/secvar.h +++ b/arch/powerpc/include/asm/secvar.h @@ -10,25 +10,30 @@ #include <linux/types.h> #include <linux/errno.h> +#include <linux/sysfs.h> extern const struct secvar_operations *secvar_ops; struct secvar_operations { - int (*get)(const char *key, uint64_t key_len, u8 *data, - uint64_t *data_size); - int (*get_next)(const char *key, uint64_t *key_len, - uint64_t keybufsize); - int (*set)(const char *key, uint64_t key_len, u8 *data, - uint64_t data_size); + int (*get)(const char *key, u64 key_len, u8 *data, u64 *data_size); + int (*get_next)(const char *key, u64 *key_len, u64 keybufsize); + int (*set)(const char *key, u64 key_len, u8 *data, u64 data_size); + ssize_t (*format)(char *buf, size_t bufsize); + int (*max_size)(u64 *max_size); + const struct attribute **config_attrs; + + // NULL-terminated array of fixed variable names + // Only used if get_next() isn't provided + const char * const *var_names; }; #ifdef CONFIG_PPC_SECURE_BOOT -extern void set_secvar_ops(const struct secvar_operations *ops); +int set_secvar_ops(const struct secvar_operations *ops); #else -static inline void set_secvar_ops(const struct secvar_operations *ops) { } +static inline int set_secvar_ops(const struct secvar_operations *ops) { return 0; } #endif diff --git a/arch/powerpc/include/asm/set_memory.h b/arch/powerpc/include/asm/set_memory.h new file mode 100644 index 000000000000..7ebc807aa8cc --- /dev/null +++ b/arch/powerpc/include/asm/set_memory.h @@ -0,0 +1,44 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_POWERPC_SET_MEMORY_H +#define _ASM_POWERPC_SET_MEMORY_H + +#define SET_MEMORY_RO 0 +#define SET_MEMORY_RW 1 +#define SET_MEMORY_NX 2 +#define SET_MEMORY_X 3 +#define SET_MEMORY_NP 4 /* Set memory non present */ +#define SET_MEMORY_P 5 /* Set memory present */ + +int change_memory_attr(unsigned long addr, int numpages, long action); + +static inline int set_memory_ro(unsigned long addr, int numpages) +{ + return change_memory_attr(addr, numpages, SET_MEMORY_RO); +} + +static inline int set_memory_rw(unsigned long addr, int numpages) +{ + return change_memory_attr(addr, numpages, SET_MEMORY_RW); +} + +static inline int set_memory_nx(unsigned long addr, int numpages) +{ + return change_memory_attr(addr, numpages, SET_MEMORY_NX); +} + +static inline int set_memory_x(unsigned long addr, int numpages) +{ + return change_memory_attr(addr, numpages, SET_MEMORY_X); +} + +static inline int set_memory_np(unsigned long addr, int numpages) +{ + return change_memory_attr(addr, numpages, SET_MEMORY_NP); +} + +static inline int set_memory_p(unsigned long addr, int numpages) +{ + return change_memory_attr(addr, numpages, SET_MEMORY_P); +} + +#endif diff --git a/arch/powerpc/include/asm/setjmp.h b/arch/powerpc/include/asm/setjmp.h index e9f81bb3f83b..f798e80e4106 100644 --- a/arch/powerpc/include/asm/setjmp.h +++ b/arch/powerpc/include/asm/setjmp.h @@ -7,7 +7,9 @@ #define JMP_BUF_LEN 23 -extern long setjmp(long *) __attribute__((returns_twice)); -extern void longjmp(long *, long) __attribute__((noreturn)); +typedef long jmp_buf[JMP_BUF_LEN]; + +extern int setjmp(jmp_buf env) __attribute__((returns_twice)); +extern void longjmp(jmp_buf env, int val) __attribute__((noreturn)); #endif /* _ASM_POWERPC_SETJMP_H */ diff --git a/arch/powerpc/include/asm/setup.h b/arch/powerpc/include/asm/setup.h index 65676e2325b8..eed74c1fb832 100644 --- a/arch/powerpc/include/asm/setup.h +++ b/arch/powerpc/include/asm/setup.h @@ -7,14 +7,9 @@ #ifndef __ASSEMBLY__ extern void ppc_printk_progress(char *s, unsigned short hex); -extern unsigned int rtas_data; extern unsigned long long memory_limit; -extern bool init_mem_is_free; -extern unsigned long klimit; -extern void *zalloc_maybe_bootmem(size_t size, gfp_t mask); struct device_node; -extern void note_scsi_host(struct device_node *, void *); /* Used in very early kernel initialization. */ extern unsigned long reloc_offset(void); @@ -30,12 +25,14 @@ void setup_panic(void); #define ARCH_PANIC_TIMEOUT 180 #ifdef CONFIG_PPC_PSERIES -extern void pseries_enable_reloc_on_exc(void); +extern bool pseries_reloc_on_exception(void); +extern bool pseries_enable_reloc_on_exc(void); extern void pseries_disable_reloc_on_exc(void); extern void pseries_big_endian_exceptions(void); -extern void pseries_little_endian_exceptions(void); +void __init pseries_little_endian_exceptions(void); #else -static inline void pseries_enable_reloc_on_exc(void) {} +static inline bool pseries_reloc_on_exception(void) { return false; } +static inline bool pseries_enable_reloc_on_exc(void) { return false; } static inline void pseries_disable_reloc_on_exc(void) {} static inline void pseries_big_endian_exceptions(void) {} static inline void pseries_little_endian_exceptions(void) {} @@ -52,27 +49,45 @@ enum l1d_flush_type { }; void setup_rfi_flush(enum l1d_flush_type, bool enable); +void setup_entry_flush(bool enable); +void setup_uaccess_flush(bool enable); void do_rfi_flush_fixups(enum l1d_flush_type types); #ifdef CONFIG_PPC_BARRIER_NOSPEC -void setup_barrier_nospec(void); +void __init setup_barrier_nospec(void); #else -static inline void setup_barrier_nospec(void) { }; +static inline void setup_barrier_nospec(void) { } #endif +void do_uaccess_flush_fixups(enum l1d_flush_type types); +void do_entry_flush_fixups(enum l1d_flush_type types); void do_barrier_nospec_fixups(bool enable); extern bool barrier_nospec_enabled; #ifdef CONFIG_PPC_BARRIER_NOSPEC void do_barrier_nospec_fixups_range(bool enable, void *start, void *end); #else -static inline void do_barrier_nospec_fixups_range(bool enable, void *start, void *end) { }; +static inline void do_barrier_nospec_fixups_range(bool enable, void *start, void *end) { } #endif -#ifdef CONFIG_PPC_FSL_BOOK3E -void setup_spectre_v2(void); +#ifdef CONFIG_PPC_E500 +void __init setup_spectre_v2(void); #else -static inline void setup_spectre_v2(void) {}; +static inline void setup_spectre_v2(void) {} #endif -void do_btb_flush_fixups(void); +void __init do_btb_flush_fixups(void); + +#ifdef CONFIG_PPC32 +unsigned long __init early_init(unsigned long dt_ptr); +void __init machine_init(u64 dt_ptr); +#endif +void __init early_setup(unsigned long dt_ptr); +void early_setup_secondary(void); + +/* prom_init (OpenFirmware) */ +unsigned long __init prom_init(unsigned long r3, unsigned long r4, + unsigned long pp, unsigned long r6, + unsigned long r7, unsigned long kbase); + +extern struct seq_buf ppc_hw_desc; #endif /* !__ASSEMBLY__ */ diff --git a/arch/powerpc/include/asm/signal.h b/arch/powerpc/include/asm/signal.h index 0803ca8b9149..922d43700fb4 100644 --- a/arch/powerpc/include/asm/signal.h +++ b/arch/powerpc/include/asm/signal.h @@ -6,4 +6,12 @@ #include <uapi/asm/signal.h> #include <uapi/asm/ptrace.h> +struct pt_regs; +void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags); + +unsigned long get_min_sigframe_size_32(void); +unsigned long get_min_sigframe_size_64(void); +unsigned long get_min_sigframe_size(void); +unsigned long get_min_sigframe_size_compat(void); + #endif /* _ASM_POWERPC_SIGNAL_H */ diff --git a/arch/powerpc/include/asm/simple_spinlock.h b/arch/powerpc/include/asm/simple_spinlock.h new file mode 100644 index 000000000000..4dd12dcb9ef8 --- /dev/null +++ b/arch/powerpc/include/asm/simple_spinlock.h @@ -0,0 +1,268 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _ASM_POWERPC_SIMPLE_SPINLOCK_H +#define _ASM_POWERPC_SIMPLE_SPINLOCK_H + +/* + * Simple spin lock operations. + * + * Copyright (C) 2001-2004 Paul Mackerras <paulus@au.ibm.com>, IBM + * Copyright (C) 2001 Anton Blanchard <anton@au.ibm.com>, IBM + * Copyright (C) 2002 Dave Engebretsen <engebret@us.ibm.com>, IBM + * Rework to support virtual processors + * + * Type of int is used as a full 64b word is not necessary. + * + * (the type definitions are in asm/simple_spinlock_types.h) + */ +#include <linux/irqflags.h> +#include <linux/kcsan-checks.h> +#include <asm/paravirt.h> +#include <asm/paca.h> +#include <asm/synch.h> +#include <asm/ppc-opcode.h> + +#ifdef CONFIG_PPC64 +/* use 0x800000yy when locked, where yy == CPU number */ +#ifdef __BIG_ENDIAN__ +#define LOCK_TOKEN (*(u32 *)(&get_paca()->lock_token)) +#else +#define LOCK_TOKEN (*(u32 *)(&get_paca()->paca_index)) +#endif +#else +#define LOCK_TOKEN 1 +#endif + +static __always_inline int arch_spin_value_unlocked(arch_spinlock_t lock) +{ + return lock.slock == 0; +} + +static inline int arch_spin_is_locked(arch_spinlock_t *lock) +{ + return !arch_spin_value_unlocked(READ_ONCE(*lock)); +} + +/* + * This returns the old value in the lock, so we succeeded + * in getting the lock if the return value is 0. + */ +static inline unsigned long __arch_spin_trylock(arch_spinlock_t *lock) +{ + unsigned long tmp, token; + unsigned int eh = IS_ENABLED(CONFIG_PPC64); + + token = LOCK_TOKEN; + __asm__ __volatile__( +"1: lwarx %0,0,%2,%[eh]\n\ + cmpwi 0,%0,0\n\ + bne- 2f\n\ + stwcx. %1,0,%2\n\ + bne- 1b\n" + PPC_ACQUIRE_BARRIER +"2:" + : "=&r" (tmp) + : "r" (token), "r" (&lock->slock), [eh] "n" (eh) + : "cr0", "memory"); + + return tmp; +} + +static inline int arch_spin_trylock(arch_spinlock_t *lock) +{ + return __arch_spin_trylock(lock) == 0; +} + +/* + * On a system with shared processors (that is, where a physical + * processor is multiplexed between several virtual processors), + * there is no point spinning on a lock if the holder of the lock + * isn't currently scheduled on a physical processor. Instead + * we detect this situation and ask the hypervisor to give the + * rest of our timeslice to the lock holder. + * + * So that we can tell which virtual processor is holding a lock, + * we put 0x80000000 | smp_processor_id() in the lock when it is + * held. Conveniently, we have a word in the paca that holds this + * value. + */ + +#if defined(CONFIG_PPC_SPLPAR) +/* We only yield to the hypervisor if we are in shared processor mode */ +void splpar_spin_yield(arch_spinlock_t *lock); +void splpar_rw_yield(arch_rwlock_t *lock); +#else /* SPLPAR */ +static inline void splpar_spin_yield(arch_spinlock_t *lock) {} +static inline void splpar_rw_yield(arch_rwlock_t *lock) {} +#endif + +static inline void spin_yield(arch_spinlock_t *lock) +{ + if (is_shared_processor()) + splpar_spin_yield(lock); + else + barrier(); +} + +static inline void rw_yield(arch_rwlock_t *lock) +{ + if (is_shared_processor()) + splpar_rw_yield(lock); + else + barrier(); +} + +static inline void arch_spin_lock(arch_spinlock_t *lock) +{ + while (1) { + if (likely(__arch_spin_trylock(lock) == 0)) + break; + do { + HMT_low(); + if (is_shared_processor()) + splpar_spin_yield(lock); + } while (unlikely(lock->slock != 0)); + HMT_medium(); + } +} + +static inline void arch_spin_unlock(arch_spinlock_t *lock) +{ + kcsan_mb(); + __asm__ __volatile__("# arch_spin_unlock\n\t" + PPC_RELEASE_BARRIER: : :"memory"); + lock->slock = 0; +} + +/* + * Read-write spinlocks, allowing multiple readers + * but only one writer. + * + * NOTE! it is quite common to have readers in interrupts + * but no interrupt writers. For those circumstances we + * can "mix" irq-safe locks - any writer needs to get a + * irq-safe write-lock, but readers can get non-irqsafe + * read-locks. + */ + +#ifdef CONFIG_PPC64 +#define __DO_SIGN_EXTEND "extsw %0,%0\n" +#define WRLOCK_TOKEN LOCK_TOKEN /* it's negative */ +#else +#define __DO_SIGN_EXTEND +#define WRLOCK_TOKEN (-1) +#endif + +/* + * This returns the old value in the lock + 1, + * so we got a read lock if the return value is > 0. + */ +static inline long __arch_read_trylock(arch_rwlock_t *rw) +{ + long tmp; + unsigned int eh = IS_ENABLED(CONFIG_PPC64); + + __asm__ __volatile__( +"1: lwarx %0,0,%1,%[eh]\n" + __DO_SIGN_EXTEND +" addic. %0,%0,1\n\ + ble- 2f\n" +" stwcx. %0,0,%1\n\ + bne- 1b\n" + PPC_ACQUIRE_BARRIER +"2:" : "=&r" (tmp) + : "r" (&rw->lock), [eh] "n" (eh) + : "cr0", "xer", "memory"); + + return tmp; +} + +/* + * This returns the old value in the lock, + * so we got the write lock if the return value is 0. + */ +static inline long __arch_write_trylock(arch_rwlock_t *rw) +{ + long tmp, token; + unsigned int eh = IS_ENABLED(CONFIG_PPC64); + + token = WRLOCK_TOKEN; + __asm__ __volatile__( +"1: lwarx %0,0,%2,%[eh]\n\ + cmpwi 0,%0,0\n\ + bne- 2f\n" +" stwcx. %1,0,%2\n\ + bne- 1b\n" + PPC_ACQUIRE_BARRIER +"2:" : "=&r" (tmp) + : "r" (token), "r" (&rw->lock), [eh] "n" (eh) + : "cr0", "memory"); + + return tmp; +} + +static inline void arch_read_lock(arch_rwlock_t *rw) +{ + while (1) { + if (likely(__arch_read_trylock(rw) > 0)) + break; + do { + HMT_low(); + if (is_shared_processor()) + splpar_rw_yield(rw); + } while (unlikely(rw->lock < 0)); + HMT_medium(); + } +} + +static inline void arch_write_lock(arch_rwlock_t *rw) +{ + while (1) { + if (likely(__arch_write_trylock(rw) == 0)) + break; + do { + HMT_low(); + if (is_shared_processor()) + splpar_rw_yield(rw); + } while (unlikely(rw->lock != 0)); + HMT_medium(); + } +} + +static inline int arch_read_trylock(arch_rwlock_t *rw) +{ + return __arch_read_trylock(rw) > 0; +} + +static inline int arch_write_trylock(arch_rwlock_t *rw) +{ + return __arch_write_trylock(rw) == 0; +} + +static inline void arch_read_unlock(arch_rwlock_t *rw) +{ + long tmp; + + __asm__ __volatile__( + "# read_unlock\n\t" + PPC_RELEASE_BARRIER +"1: lwarx %0,0,%1\n\ + addic %0,%0,-1\n" +" stwcx. %0,0,%1\n\ + bne- 1b" + : "=&r"(tmp) + : "r"(&rw->lock) + : "cr0", "xer", "memory"); +} + +static inline void arch_write_unlock(arch_rwlock_t *rw) +{ + __asm__ __volatile__("# write_unlock\n\t" + PPC_RELEASE_BARRIER: : :"memory"); + rw->lock = 0; +} + +#define arch_spin_relax(lock) spin_yield(lock) +#define arch_read_relax(lock) rw_yield(lock) +#define arch_write_relax(lock) rw_yield(lock) + +#endif /* _ASM_POWERPC_SIMPLE_SPINLOCK_H */ diff --git a/arch/powerpc/include/asm/simple_spinlock_types.h b/arch/powerpc/include/asm/simple_spinlock_types.h new file mode 100644 index 000000000000..08243338069d --- /dev/null +++ b/arch/powerpc/include/asm/simple_spinlock_types.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_POWERPC_SIMPLE_SPINLOCK_TYPES_H +#define _ASM_POWERPC_SIMPLE_SPINLOCK_TYPES_H + +#ifndef __LINUX_SPINLOCK_TYPES_RAW_H +# error "please don't include this file directly" +#endif + +typedef struct { + volatile unsigned int slock; +} arch_spinlock_t; + +#define __ARCH_SPIN_LOCK_UNLOCKED { 0 } + +typedef struct { + volatile signed int lock; +} arch_rwlock_t; + +#define __ARCH_RW_LOCK_UNLOCKED { 0 } + +#endif /* _ASM_POWERPC_SIMPLE_SPINLOCK_TYPES_H */ diff --git a/arch/powerpc/include/asm/slice.h b/arch/powerpc/include/asm/slice.h deleted file mode 100644 index c6f466f4c241..000000000000 --- a/arch/powerpc/include/asm/slice.h +++ /dev/null @@ -1,48 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ASM_POWERPC_SLICE_H -#define _ASM_POWERPC_SLICE_H - -#ifdef CONFIG_PPC_BOOK3S_64 -#include <asm/book3s/64/slice.h> -#elif defined(CONFIG_PPC_MMU_NOHASH_32) -#include <asm/nohash/32/slice.h> -#endif - -#ifndef __ASSEMBLY__ - -struct mm_struct; - -#ifdef CONFIG_PPC_MM_SLICES - -#ifdef CONFIG_HUGETLB_PAGE -#define HAVE_ARCH_HUGETLB_UNMAPPED_AREA -#endif -#define HAVE_ARCH_UNMAPPED_AREA -#define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN - -unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len, - unsigned long flags, unsigned int psize, - int topdown); - -unsigned int get_slice_psize(struct mm_struct *mm, unsigned long addr); - -void slice_set_range_psize(struct mm_struct *mm, unsigned long start, - unsigned long len, unsigned int psize); - -void slice_init_new_context_exec(struct mm_struct *mm); -void slice_setup_new_exec(void); - -#else /* CONFIG_PPC_MM_SLICES */ - -static inline void slice_init_new_context_exec(struct mm_struct *mm) {} - -static inline unsigned int get_slice_psize(struct mm_struct *mm, unsigned long addr) -{ - return 0; -} - -#endif /* CONFIG_PPC_MM_SLICES */ - -#endif /* __ASSEMBLY__ */ - -#endif /* _ASM_POWERPC_SLICE_H */ diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h index 49a25e2400f2..aaaa576d0e15 100644 --- a/arch/powerpc/include/asm/smp.h +++ b/arch/powerpc/include/asm/smp.h @@ -26,11 +26,17 @@ #include <asm/percpu.h> extern int boot_cpuid; +extern int boot_cpu_hwid; /* PPC64 only */ extern int spinning_secondaries; extern u32 *cpu_to_phys_id; +extern bool coregroup_enabled; -extern void cpu_die(void); extern int cpu_to_chip_id(int cpu); +extern int *chip_id_lookup_table; + +DECLARE_PER_CPU(cpumask_var_t, thread_group_l1_cache_map); +DECLARE_PER_CPU(cpumask_var_t, thread_group_l2_cache_map); +DECLARE_PER_CPU(cpumask_var_t, thread_group_l3_cache_map); #ifdef CONFIG_SMP @@ -50,12 +56,18 @@ struct smp_ops_t { int (*cpu_disable)(void); void (*cpu_die)(unsigned int nr); int (*cpu_bootable)(unsigned int nr); +#ifdef CONFIG_HOTPLUG_CPU + void (*cpu_offline_self)(void); +#endif }; +extern struct task_struct *secondary_current; + +void start_secondary(void *unused); extern int smp_send_nmi_ipi(int cpu, void (*fn)(struct pt_regs *), u64 delay_us); extern int smp_send_safe_nmi_ipi(int cpu, void (*fn)(struct pt_regs *), u64 delay_us); extern void smp_send_debugger_break(void); -extern void start_secondary_resume(void); +extern void __noreturn start_secondary_resume(void); extern void smp_generic_give_timebase(void); extern void smp_generic_take_timebase(void); @@ -79,22 +91,7 @@ int is_cpu_dead(unsigned int cpu); /* 32-bit */ extern int smp_hw_index[]; -/* - * This is particularly ugly: it appears we can't actually get the definition - * of task_struct here, but we need access to the CPU this task is running on. - * Instead of using task_struct we're using _TASK_CPU which is extracted from - * asm-offsets.h by kbuild to get the current processor ID. - * - * This also needs to be safeguarded when building asm-offsets.s because at - * that time _TASK_CPU is not defined yet. It could have been guarded by - * _TASK_CPU itself, but we want the build to fail if _TASK_CPU is missing - * when building something else than asm-offsets.s - */ -#ifdef GENERATING_ASM_OFFSETS -#define raw_smp_processor_id() (0) -#else -#define raw_smp_processor_id() (*(unsigned int *)((void *)current + _TASK_CPU)) -#endif +#define raw_smp_processor_id() (current_thread_info()->cpu) #define hard_smp_processor_id() (smp_hw_index[smp_processor_id()]) static inline int get_hard_smp_processor_id(int cpu) @@ -135,6 +132,21 @@ static inline struct cpumask *cpu_smallcore_mask(int cpu) extern int cpu_to_core_id(int cpu); +extern bool has_big_cores; +extern bool thread_group_shares_l2; +extern bool thread_group_shares_l3; + +#define cpu_smt_mask cpu_smt_mask +#ifdef CONFIG_SCHED_SMT +static inline const struct cpumask *cpu_smt_mask(int cpu) +{ + if (has_big_cores) + return per_cpu(cpu_smallcore_map, cpu); + + return per_cpu(cpu_sibling_map, cpu); +} +#endif /* CONFIG_SCHED_SMT */ + /* Since OpenPIC has only 4 IPIs, we use slightly different message numbers. * * Make sure this matches openpic_request_IPIs in open_pic.c, or what shows up @@ -176,8 +188,8 @@ extern void __cpu_die(unsigned int cpu); /* for UP */ #define hard_smp_processor_id() get_hard_smp_processor_id(0) #define smp_setup_cpu_maps() -static inline void inhibit_secondary_onlining(void) {} -static inline void uninhibit_secondary_onlining(void) {} +#define thread_group_shares_l2 0 +#define thread_group_shares_l3 0 static inline const struct cpumask *cpu_sibling_mask(int cpu) { return cpumask_of(cpu); @@ -188,6 +200,10 @@ static inline const struct cpumask *cpu_smallcore_mask(int cpu) return cpumask_of(cpu); } +static inline const struct cpumask *cpu_l2_cache_mask(int cpu) +{ + return cpumask_of(cpu); +} #endif /* CONFIG_SMP */ #ifdef CONFIG_PPC64 @@ -219,7 +235,7 @@ static inline void set_hard_smp_processor_id(int cpu, int phys) #if defined(CONFIG_PPC64) && (defined(CONFIG_SMP) || defined(CONFIG_KEXEC_CORE)) extern void smp_release_cpus(void); #else -static inline void smp_release_cpus(void) { }; +static inline void smp_release_cpus(void) { } #endif extern int smt_enabled_at_boot; @@ -243,7 +259,6 @@ extern void arch_send_call_function_ipi_mask(const struct cpumask *mask); * 64-bit but defining them all here doesn't harm */ extern void generic_secondary_smp_init(void); -extern void generic_secondary_thread_init(void); extern unsigned long __secondary_hold_spinloop; extern unsigned long __secondary_hold_acknowledge; extern char __secondary_hold; diff --git a/arch/powerpc/include/asm/smu.h b/arch/powerpc/include/asm/smu.h index 8dff086c0cab..2ac6ab903023 100644 --- a/arch/powerpc/include/asm/smu.h +++ b/arch/powerpc/include/asm/smu.h @@ -108,7 +108,7 @@ /* * i2c commands * - * To issue an i2c command, first is to send a parameter block to the + * To issue an i2c command, first is to send a parameter block to * the SMU. This is a command of type 0x9a with 9 bytes of header * eventually followed by data for a write: * @@ -456,7 +456,7 @@ extern void smu_poll(void); /* * Init routine, presence check.... */ -extern int smu_init(void); +int __init smu_init(void); extern int smu_present(void); struct platform_device; extern struct platform_device *smu_get_ofdev(void); diff --git a/arch/powerpc/include/asm/sparsemem.h b/arch/powerpc/include/asm/sparsemem.h index 3192d454a733..d072866842e4 100644 --- a/arch/powerpc/include/asm/sparsemem.h +++ b/arch/powerpc/include/asm/sparsemem.h @@ -13,14 +13,9 @@ #endif /* CONFIG_SPARSEMEM */ #ifdef CONFIG_MEMORY_HOTPLUG -extern int create_section_mapping(unsigned long start, unsigned long end, int nid); extern int remove_section_mapping(unsigned long start, unsigned long end); - -#ifdef CONFIG_PPC_BOOK3S_64 -extern int resize_hpt_for_hotplug(unsigned long new_mem_size); -#else -static inline int resize_hpt_for_hotplug(unsigned long new_mem_size) { return 0; } -#endif +extern int memory_add_physaddr_to_nid(u64 start); +#define memory_add_physaddr_to_nid memory_add_physaddr_to_nid #ifdef CONFIG_NUMA extern int hot_add_scn_to_nid(unsigned long scn_addr); @@ -31,6 +26,5 @@ static inline int hot_add_scn_to_nid(unsigned long scn_addr) } #endif /* CONFIG_NUMA */ #endif /* CONFIG_MEMORY_HOTPLUG */ - #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_SPARSEMEM_H */ diff --git a/arch/powerpc/include/asm/spinlock.h b/arch/powerpc/include/asm/spinlock.h index e9a960e28f3c..7dafca8e3f02 100644 --- a/arch/powerpc/include/asm/spinlock.h +++ b/arch/powerpc/include/asm/spinlock.h @@ -3,318 +3,19 @@ #define __ASM_SPINLOCK_H #ifdef __KERNEL__ -/* - * Simple spin lock operations. - * - * Copyright (C) 2001-2004 Paul Mackerras <paulus@au.ibm.com>, IBM - * Copyright (C) 2001 Anton Blanchard <anton@au.ibm.com>, IBM - * Copyright (C) 2002 Dave Engebretsen <engebret@us.ibm.com>, IBM - * Rework to support virtual processors - * - * Type of int is used as a full 64b word is not necessary. - * - * (the type definitions are in asm/spinlock_types.h) - */ -#include <linux/irqflags.h> -#ifdef CONFIG_PPC64 -#include <asm/paca.h> -#include <asm/hvcall.h> -#endif -#include <asm/synch.h> -#include <asm/ppc-opcode.h> -#include <asm/asm-405.h> - -#ifdef CONFIG_PPC64 -/* use 0x800000yy when locked, where yy == CPU number */ -#ifdef __BIG_ENDIAN__ -#define LOCK_TOKEN (*(u32 *)(&get_paca()->lock_token)) -#else -#define LOCK_TOKEN (*(u32 *)(&get_paca()->paca_index)) -#endif +#ifdef CONFIG_PPC_QUEUED_SPINLOCKS +#include <asm/qspinlock.h> +#include <asm/qrwlock.h> #else -#define LOCK_TOKEN 1 -#endif - -#ifdef CONFIG_PPC_PSERIES -#define vcpu_is_preempted vcpu_is_preempted -static inline bool vcpu_is_preempted(int cpu) -{ - if (!firmware_has_feature(FW_FEATURE_SPLPAR)) - return false; - return !!(be32_to_cpu(lppaca_of(cpu).yield_count) & 1); -} +#include <asm/simple_spinlock.h> #endif -static __always_inline int arch_spin_value_unlocked(arch_spinlock_t lock) -{ - return lock.slock == 0; -} - -static inline int arch_spin_is_locked(arch_spinlock_t *lock) -{ - smp_mb(); - return !arch_spin_value_unlocked(*lock); -} - -/* - * This returns the old value in the lock, so we succeeded - * in getting the lock if the return value is 0. - */ -static inline unsigned long __arch_spin_trylock(arch_spinlock_t *lock) -{ - unsigned long tmp, token; - - token = LOCK_TOKEN; - __asm__ __volatile__( -"1: " PPC_LWARX(%0,0,%2,1) "\n\ - cmpwi 0,%0,0\n\ - bne- 2f\n\ - stwcx. %1,0,%2\n\ - bne- 1b\n" - PPC_ACQUIRE_BARRIER -"2:" - : "=&r" (tmp) - : "r" (token), "r" (&lock->slock) - : "cr0", "memory"); - - return tmp; -} - -static inline int arch_spin_trylock(arch_spinlock_t *lock) -{ - return __arch_spin_trylock(lock) == 0; -} - -/* - * On a system with shared processors (that is, where a physical - * processor is multiplexed between several virtual processors), - * there is no point spinning on a lock if the holder of the lock - * isn't currently scheduled on a physical processor. Instead - * we detect this situation and ask the hypervisor to give the - * rest of our timeslice to the lock holder. - * - * So that we can tell which virtual processor is holding a lock, - * we put 0x80000000 | smp_processor_id() in the lock when it is - * held. Conveniently, we have a word in the paca that holds this - * value. - */ - -#if defined(CONFIG_PPC_SPLPAR) -/* We only yield to the hypervisor if we are in shared processor mode */ -void splpar_spin_yield(arch_spinlock_t *lock); -void splpar_rw_yield(arch_rwlock_t *lock); -#else /* SPLPAR */ -static inline void splpar_spin_yield(arch_spinlock_t *lock) {}; -static inline void splpar_rw_yield(arch_rwlock_t *lock) {}; -#endif - -static inline bool is_shared_processor(void) -{ -/* - * LPPACA is only available on Pseries so guard anything LPPACA related to - * allow other platforms (which include this common header) to compile. - */ -#ifdef CONFIG_PPC_PSERIES - return (IS_ENABLED(CONFIG_PPC_SPLPAR) && - lppaca_shared_proc(local_paca->lppaca_ptr)); -#else - return false; -#endif -} - -static inline void spin_yield(arch_spinlock_t *lock) -{ - if (is_shared_processor()) - splpar_spin_yield(lock); - else - barrier(); -} - -static inline void rw_yield(arch_rwlock_t *lock) -{ - if (is_shared_processor()) - splpar_rw_yield(lock); - else - barrier(); -} - -static inline void arch_spin_lock(arch_spinlock_t *lock) -{ - while (1) { - if (likely(__arch_spin_trylock(lock) == 0)) - break; - do { - HMT_low(); - if (is_shared_processor()) - splpar_spin_yield(lock); - } while (unlikely(lock->slock != 0)); - HMT_medium(); - } -} - -static inline -void arch_spin_lock_flags(arch_spinlock_t *lock, unsigned long flags) -{ - unsigned long flags_dis; - - while (1) { - if (likely(__arch_spin_trylock(lock) == 0)) - break; - local_save_flags(flags_dis); - local_irq_restore(flags); - do { - HMT_low(); - if (is_shared_processor()) - splpar_spin_yield(lock); - } while (unlikely(lock->slock != 0)); - HMT_medium(); - local_irq_restore(flags_dis); - } -} -#define arch_spin_lock_flags arch_spin_lock_flags - -static inline void arch_spin_unlock(arch_spinlock_t *lock) -{ - __asm__ __volatile__("# arch_spin_unlock\n\t" - PPC_RELEASE_BARRIER: : :"memory"); - lock->slock = 0; -} - -/* - * Read-write spinlocks, allowing multiple readers - * but only one writer. - * - * NOTE! it is quite common to have readers in interrupts - * but no interrupt writers. For those circumstances we - * can "mix" irq-safe locks - any writer needs to get a - * irq-safe write-lock, but readers can get non-irqsafe - * read-locks. - */ +/* See include/linux/spinlock.h */ +#define smp_mb__after_spinlock() smp_mb() -#ifdef CONFIG_PPC64 -#define __DO_SIGN_EXTEND "extsw %0,%0\n" -#define WRLOCK_TOKEN LOCK_TOKEN /* it's negative */ -#else -#define __DO_SIGN_EXTEND -#define WRLOCK_TOKEN (-1) +#ifndef CONFIG_PPC_QUEUED_SPINLOCKS +static inline void pv_spinlocks_init(void) { } #endif -/* - * This returns the old value in the lock + 1, - * so we got a read lock if the return value is > 0. - */ -static inline long __arch_read_trylock(arch_rwlock_t *rw) -{ - long tmp; - - __asm__ __volatile__( -"1: " PPC_LWARX(%0,0,%1,1) "\n" - __DO_SIGN_EXTEND -" addic. %0,%0,1\n\ - ble- 2f\n" - PPC405_ERR77(0,%1) -" stwcx. %0,0,%1\n\ - bne- 1b\n" - PPC_ACQUIRE_BARRIER -"2:" : "=&r" (tmp) - : "r" (&rw->lock) - : "cr0", "xer", "memory"); - - return tmp; -} - -/* - * This returns the old value in the lock, - * so we got the write lock if the return value is 0. - */ -static inline long __arch_write_trylock(arch_rwlock_t *rw) -{ - long tmp, token; - - token = WRLOCK_TOKEN; - __asm__ __volatile__( -"1: " PPC_LWARX(%0,0,%2,1) "\n\ - cmpwi 0,%0,0\n\ - bne- 2f\n" - PPC405_ERR77(0,%1) -" stwcx. %1,0,%2\n\ - bne- 1b\n" - PPC_ACQUIRE_BARRIER -"2:" : "=&r" (tmp) - : "r" (token), "r" (&rw->lock) - : "cr0", "memory"); - - return tmp; -} - -static inline void arch_read_lock(arch_rwlock_t *rw) -{ - while (1) { - if (likely(__arch_read_trylock(rw) > 0)) - break; - do { - HMT_low(); - if (is_shared_processor()) - splpar_rw_yield(rw); - } while (unlikely(rw->lock < 0)); - HMT_medium(); - } -} - -static inline void arch_write_lock(arch_rwlock_t *rw) -{ - while (1) { - if (likely(__arch_write_trylock(rw) == 0)) - break; - do { - HMT_low(); - if (is_shared_processor()) - splpar_rw_yield(rw); - } while (unlikely(rw->lock != 0)); - HMT_medium(); - } -} - -static inline int arch_read_trylock(arch_rwlock_t *rw) -{ - return __arch_read_trylock(rw) > 0; -} - -static inline int arch_write_trylock(arch_rwlock_t *rw) -{ - return __arch_write_trylock(rw) == 0; -} - -static inline void arch_read_unlock(arch_rwlock_t *rw) -{ - long tmp; - - __asm__ __volatile__( - "# read_unlock\n\t" - PPC_RELEASE_BARRIER -"1: lwarx %0,0,%1\n\ - addic %0,%0,-1\n" - PPC405_ERR77(0,%1) -" stwcx. %0,0,%1\n\ - bne- 1b" - : "=&r"(tmp) - : "r"(&rw->lock) - : "cr0", "xer", "memory"); -} - -static inline void arch_write_unlock(arch_rwlock_t *rw) -{ - __asm__ __volatile__("# write_unlock\n\t" - PPC_RELEASE_BARRIER: : :"memory"); - rw->lock = 0; -} - -#define arch_spin_relax(lock) spin_yield(lock) -#define arch_read_relax(lock) rw_yield(lock) -#define arch_write_relax(lock) rw_yield(lock) - -/* See include/linux/spinlock.h */ -#define smp_mb__after_spinlock() smp_mb() - #endif /* __KERNEL__ */ #endif /* __ASM_SPINLOCK_H */ diff --git a/arch/powerpc/include/asm/spinlock_types.h b/arch/powerpc/include/asm/spinlock_types.h index 87adaf13b7e8..40b01446cf75 100644 --- a/arch/powerpc/include/asm/spinlock_types.h +++ b/arch/powerpc/include/asm/spinlock_types.h @@ -2,20 +2,15 @@ #ifndef _ASM_POWERPC_SPINLOCK_TYPES_H #define _ASM_POWERPC_SPINLOCK_TYPES_H -#ifndef __LINUX_SPINLOCK_TYPES_H +#ifndef __LINUX_SPINLOCK_TYPES_RAW_H # error "please don't include this file directly" #endif -typedef struct { - volatile unsigned int slock; -} arch_spinlock_t; - -#define __ARCH_SPIN_LOCK_UNLOCKED { 0 } - -typedef struct { - volatile signed int lock; -} arch_rwlock_t; - -#define __ARCH_RW_LOCK_UNLOCKED { 0 } +#ifdef CONFIG_PPC_QUEUED_SPINLOCKS +#include <asm/qspinlock_types.h> +#include <asm-generic/qrwlock_types.h> +#else +#include <asm/simple_spinlock_types.h> +#endif #endif diff --git a/arch/powerpc/include/asm/spu.h b/arch/powerpc/include/asm/spu.h index 9666491bcb8a..96ad4510c895 100644 --- a/arch/powerpc/include/asm/spu.h +++ b/arch/powerpc/include/asm/spu.h @@ -201,20 +201,6 @@ int spu_64k_pages_available(void); struct mm_struct; extern void spu_flush_all_slbs(struct mm_struct *mm); -/* This interface allows a profiler (e.g., OProfile) to store a ref - * to spu context information that it creates. This caching technique - * avoids the need to recreate this information after a save/restore operation. - * - * Assumes the caller has already incremented the ref count to - * profile_info; then spu_context_destroy must call kref_put - * on prof_info_kref. - */ -void spu_set_profile_private_kref(struct spu_context *ctx, - struct kref *prof_info_kref, - void ( * prof_info_release) (struct kref *kref)); - -void *spu_get_profile_private_kref(struct spu_context *ctx); - /* system callbacks from the SPU */ struct spu_syscall_block { u64 nr_ret; @@ -263,27 +249,8 @@ void unregister_spu_syscalls(struct spufs_calls *calls); int spu_add_dev_attr(struct device_attribute *attr); void spu_remove_dev_attr(struct device_attribute *attr); -int spu_add_dev_attr_group(struct attribute_group *attrs); -void spu_remove_dev_attr_group(struct attribute_group *attrs); - -/* - * Notifier blocks: - * - * oprofile can get notified when a context switch is performed - * on an spe. The notifer function that gets called is passed - * a pointer to the SPU structure as well as the object-id that - * identifies the binary running on that SPU now. - * - * For a context save, the object-id that is passed is zero, - * identifying that the kernel will run from that moment on. - * - * For a context restore, the object-id is the value written - * to object-id spufs file from user space and the notifer - * function can assume that spu->ctx is valid. - */ -struct notifier_block; -int spu_switch_event_register(struct notifier_block * n); -int spu_switch_event_unregister(struct notifier_block * n); +int spu_add_dev_attr_group(const struct attribute_group *attrs); +void spu_remove_dev_attr_group(const struct attribute_group *attrs); extern void notify_spus_active(void); extern void do_notify_spus_active(void); diff --git a/arch/powerpc/include/asm/sstep.h b/arch/powerpc/include/asm/sstep.h index 769f055509c9..50950deedb87 100644 --- a/arch/powerpc/include/asm/sstep.h +++ b/arch/powerpc/include/asm/sstep.h @@ -2,6 +2,7 @@ /* * Copyright (C) 2004 Paul Mackerras <paulus@au.ibm.com>, IBM */ +#include <asm/inst.h> struct pt_regs; @@ -12,12 +13,11 @@ struct pt_regs; * we don't allow putting a breakpoint on an mtmsrd instruction. * Similarly we don't allow breakpoints on rfid instructions. * These macros tell us if an instruction is a mtmsrd or rfid. - * Note that IS_MTMSRD returns true for both an mtmsr (32-bit) - * and an mtmsrd (64-bit). + * Note that these return true for both mtmsr/rfi (32-bit) + * and mtmsrd/rfid (64-bit). */ -#define IS_MTMSRD(instr) (((instr) & 0xfc0007be) == 0x7c000124) -#define IS_RFID(instr) (((instr) & 0xfc0007fe) == 0x4c000024) -#define IS_RFI(instr) (((instr) & 0xfc0007fe) == 0x4c000064) +#define IS_MTMSRD(instr) ((ppc_inst_val(instr) & 0xfc0007be) == 0x7c000124) +#define IS_RFID(instr) ((ppc_inst_val(instr) & 0xfc0007be) == 0x4c000024) enum instruction_type { COMPUTE, /* arith/logical/CR op, etc. */ @@ -39,6 +39,7 @@ enum instruction_type { CACHEOP, BARRIER, SYSCALL, + SYSCALL_VECTORED_0, MFMSR, MTMSR, RFI, @@ -48,6 +49,8 @@ enum instruction_type { #define INSTR_TYPE_MASK 0x1f +#define OP_IS_LOAD(type) ((LOAD <= (type) && (type) <= LOAD_VSX) || (type) == LARX) +#define OP_IS_STORE(type) ((STORE <= (type) && (type) <= STORE_VSX) || (type) == STCX) #define OP_IS_LOAD_STORE(type) (LOAD <= (type) && (type) <= STCX) /* Compute flags, ORed in with type */ @@ -89,14 +92,24 @@ enum instruction_type { #define VSX_LDLEFT 4 /* load VSX register from left */ #define VSX_CHECK_VEC 8 /* check MSR_VEC not MSR_VSX for reg >= 32 */ +/* Prefixed flag, ORed in with type */ +#define PREFIXED 0x800 + /* Size field in type word */ #define SIZE(n) ((n) << 12) #define GETSIZE(w) ((w) >> 12) #define GETTYPE(t) ((t) & INSTR_TYPE_MASK) +#define GETLENGTH(t) (((t) & PREFIXED) ? 8 : 4) #define MKOP(t, f, s) ((t) | (f) | SIZE(s)) +/* Prefix instruction operands */ +#define GET_PREFIX_RA(i) (((i) >> 16) & 0x1f) +#define GET_PREFIX_R(i) ((i) & (1ul << 20)) + +extern s32 patch__exec_instr; + struct instruction_op { int type; int reg; @@ -132,7 +145,7 @@ union vsx_reg { * otherwise. */ extern int analyse_instr(struct instruction_op *op, const struct pt_regs *regs, - unsigned int instr); + ppc_inst_t instr); /* * Emulate an instruction that can be executed just by updating @@ -149,7 +162,7 @@ void emulate_update_regs(struct pt_regs *reg, struct instruction_op *op); * 0 if it could not be emulated, or -1 for an instruction that * should not be emulated (rfid, mtmsrd clearing MSR_RI, etc.). */ -extern int emulate_step(struct pt_regs *regs, unsigned int instr); +int emulate_step(struct pt_regs *regs, ppc_inst_t instr); /* * Emulate a load or store instruction by reading/writing the diff --git a/arch/powerpc/include/asm/stackprotector.h b/arch/powerpc/include/asm/stackprotector.h index 1c8460e23583..283c34647856 100644 --- a/arch/powerpc/include/asm/stackprotector.h +++ b/arch/powerpc/include/asm/stackprotector.h @@ -7,8 +7,6 @@ #ifndef _ASM_STACKPROTECTOR_H #define _ASM_STACKPROTECTOR_H -#include <linux/random.h> -#include <linux/version.h> #include <asm/reg.h> #include <asm/current.h> #include <asm/paca.h> @@ -21,13 +19,7 @@ */ static __always_inline void boot_init_stack_canary(void) { - unsigned long canary; - - /* Try to get a semi random initial value. */ - canary = get_random_canary(); - canary ^= mftb(); - canary ^= LINUX_VERSION_CODE; - canary &= CANARY_MASK; + unsigned long canary = get_random_canary(); current->stack_canary = canary; #ifdef CONFIG_PPC64 diff --git a/arch/powerpc/include/asm/static_call.h b/arch/powerpc/include/asm/static_call.h new file mode 100644 index 000000000000..de1018cc522b --- /dev/null +++ b/arch/powerpc/include/asm/static_call.h @@ -0,0 +1,29 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_POWERPC_STATIC_CALL_H +#define _ASM_POWERPC_STATIC_CALL_H + +#define __PPC_SCT(name, inst) \ + asm(".pushsection .text, \"ax\" \n" \ + ".align 5 \n" \ + ".globl " STATIC_CALL_TRAMP_STR(name) " \n" \ + STATIC_CALL_TRAMP_STR(name) ": \n" \ + inst " \n" \ + " lis 12,2f@ha \n" \ + " lwz 12,2f@l(12) \n" \ + " mtctr 12 \n" \ + " bctr \n" \ + "1: li 3, 0 \n" \ + " blr \n" \ + "2: .long 0 \n" \ + ".type " STATIC_CALL_TRAMP_STR(name) ", @function \n" \ + ".size " STATIC_CALL_TRAMP_STR(name) ", . - " STATIC_CALL_TRAMP_STR(name) " \n" \ + ".popsection \n") + +#define PPC_SCT_RET0 20 /* Offset of label 1 */ +#define PPC_SCT_DATA 28 /* Offset of label 2 */ + +#define ARCH_DEFINE_STATIC_CALL_TRAMP(name, func) __PPC_SCT(name, "b " #func) +#define ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name) __PPC_SCT(name, "blr") +#define ARCH_DEFINE_STATIC_CALL_RET0_TRAMP(name) __PPC_SCT(name, "b .+20") + +#endif /* _ASM_POWERPC_STATIC_CALL_H */ diff --git a/arch/powerpc/include/asm/string.h b/arch/powerpc/include/asm/string.h index b72692702f35..60ba22770f51 100644 --- a/arch/powerpc/include/asm/string.h +++ b/arch/powerpc/include/asm/string.h @@ -28,13 +28,19 @@ extern void * memcpy(void *,const void *,__kernel_size_t); extern void * memmove(void *,const void *,__kernel_size_t); extern int memcmp(const void *,const void *,__kernel_size_t); extern void * memchr(const void *,int,__kernel_size_t); -extern void * memcpy_flushcache(void *,const void *,__kernel_size_t); +void memcpy_flushcache(void *dest, const void *src, size_t size); +#ifdef CONFIG_KASAN +/* __mem variants are used by KASAN to implement instrumented meminstrinsics. */ +#ifdef CONFIG_CC_HAS_KASAN_MEMINTRINSIC_PREFIX +#define __memset memset +#define __memcpy memcpy +#define __memmove memmove +#else /* CONFIG_CC_HAS_KASAN_MEMINTRINSIC_PREFIX */ void *__memset(void *s, int c, __kernel_size_t count); void *__memcpy(void *to, const void *from, __kernel_size_t n); void *__memmove(void *to, const void *from, __kernel_size_t n); - -#if defined(CONFIG_KASAN) && !defined(__SANITIZE_ADDRESS__) +#ifndef __SANITIZE_ADDRESS__ /* * For files that are not instrumented (e.g. mm/slub.c) we * should use not instrumented version of mem* functions. @@ -46,16 +52,15 @@ void *__memmove(void *to, const void *from, __kernel_size_t n); #ifndef __NO_FORTIFY #define __NO_FORTIFY /* FORTIFY_SOURCE uses __builtin_memcpy, etc. */ #endif - -#endif +#endif /* !__SANITIZE_ADDRESS__ */ +#endif /* CONFIG_CC_HAS_KASAN_MEMINTRINSIC_PREFIX */ +#endif /* CONFIG_KASAN */ #ifdef CONFIG_PPC64 #ifndef CONFIG_KASAN #define __HAVE_ARCH_MEMSET32 #define __HAVE_ARCH_MEMSET64 -#define __HAVE_ARCH_MEMCPY_MCSAFE -extern int memcpy_mcsafe(void *dst, const void *src, __kernel_size_t sz); extern void *__memset16(uint16_t *, uint16_t v, __kernel_size_t); extern void *__memset32(uint32_t *, uint32_t v, __kernel_size_t); extern void *__memset64(uint64_t *, uint64_t v, __kernel_size_t); diff --git a/arch/powerpc/include/asm/svm.h b/arch/powerpc/include/asm/svm.h index 85580b30aba4..a02bd54b8948 100644 --- a/arch/powerpc/include/asm/svm.h +++ b/arch/powerpc/include/asm/svm.h @@ -10,6 +10,8 @@ #ifdef CONFIG_PPC_SVM +#include <asm/reg.h> + static inline bool is_secure_guest(void) { return mfmsr() & MSR_S; diff --git a/arch/powerpc/include/asm/swiotlb.h b/arch/powerpc/include/asm/swiotlb.h index 3c1a1cd16128..4203b5e0a88e 100644 --- a/arch/powerpc/include/asm/swiotlb.h +++ b/arch/powerpc/include/asm/swiotlb.h @@ -9,6 +9,7 @@ #include <linux/swiotlb.h> extern unsigned int ppc_swiotlb_enable; +extern unsigned int ppc_swiotlb_flags; #ifdef CONFIG_SWIOTLB void swiotlb_detect_4g(void); diff --git a/arch/powerpc/include/asm/switch_to.h b/arch/powerpc/include/asm/switch_to.h index 5b03d8a82409..aee25e3ebf96 100644 --- a/arch/powerpc/include/asm/switch_to.h +++ b/arch/powerpc/include/asm/switch_to.h @@ -5,6 +5,7 @@ #ifndef _ASM_POWERPC_SWITCH_TO_H #define _ASM_POWERPC_SWITCH_TO_H +#include <linux/sched.h> #include <asm/reg.h> struct thread_struct; @@ -22,6 +23,16 @@ extern void switch_booke_debug_regs(struct debug_reg *new_debug); extern int emulate_altivec(struct pt_regs *); +#ifdef CONFIG_PPC_BOOK3S_64 +void restore_math(struct pt_regs *regs); +#else +static inline void restore_math(struct pt_regs *regs) +{ +} +#endif + +void restore_tm_state(struct pt_regs *regs); + extern void flush_all_to_thread(struct task_struct *); extern void giveup_all(struct task_struct *); @@ -51,6 +62,15 @@ static inline void disable_kernel_altivec(void) #else static inline void save_altivec(struct task_struct *t) { } static inline void __giveup_altivec(struct task_struct *t) { } +static inline void enable_kernel_altivec(void) +{ + BUILD_BUG(); +} + +static inline void disable_kernel_altivec(void) +{ + BUILD_BUG(); +} #endif #ifdef CONFIG_VSX @@ -60,6 +80,16 @@ static inline void disable_kernel_vsx(void) { msr_check_and_clear(MSR_FP|MSR_VEC|MSR_VSX); } +#else +static inline void enable_kernel_vsx(void) +{ + BUILD_BUG(); +} + +static inline void disable_kernel_vsx(void) +{ + BUILD_BUG(); +} #endif #ifdef CONFIG_SPE @@ -91,7 +121,8 @@ static inline void clear_task_ebb(struct task_struct *t) #endif } -extern int set_thread_uses_vas(void); +void kvmppc_save_user_regs(void); +void kvmppc_save_current_sprs(void); extern int set_thread_tidr(struct task_struct *t); diff --git a/arch/powerpc/include/asm/synch.h b/arch/powerpc/include/asm/synch.h index aca70fb43147..b0b4c64870d7 100644 --- a/arch/powerpc/include/asm/synch.h +++ b/arch/powerpc/include/asm/synch.h @@ -3,8 +3,9 @@ #define _ASM_POWERPC_SYNCH_H #ifdef __KERNEL__ +#include <asm/cputable.h> #include <asm/feature-fixups.h> -#include <asm/asm-const.h> +#include <asm/ppc-opcode.h> #ifndef __ASSEMBLY__ extern unsigned int __start___lwsync_fixup, __stop___lwsync_fixup; @@ -13,18 +14,37 @@ extern void do_lwsync_fixups(unsigned long value, void *fixup_start, static inline void eieio(void) { - __asm__ __volatile__ ("eieio" : : : "memory"); + if (IS_ENABLED(CONFIG_BOOKE)) + __asm__ __volatile__ ("mbar" : : : "memory"); + else + __asm__ __volatile__ ("eieio" : : : "memory"); } static inline void isync(void) { __asm__ __volatile__ ("isync" : : : "memory"); } + +static inline void ppc_after_tlbiel_barrier(void) +{ + asm volatile("ptesync": : :"memory"); + /* + * POWER9, POWER10 need a cp_abort after tlbiel to ensure the copy is + * invalidated correctly. If this is not done, the paste can take data + * from the physical address that was translated at copy time. + * + * POWER9 in practice does not need this, because address spaces with + * accelerators mapped will use tlbie (which does invalidate the copy) + * to invalidate translations. It's not possible to limit POWER10 this + * way due to local copy-paste. + */ + asm volatile(ASM_FTR_IFSET(PPC_CP_ABORT, "", %0) : : "i" (CPU_FTR_ARCH_31) : "memory"); +} #endif /* __ASSEMBLY__ */ #if defined(__powerpc64__) # define LWSYNC lwsync -#elif defined(CONFIG_E500) +#elif defined(CONFIG_PPC_E500) # define LWSYNC \ START_LWSYNC_SECTION(96); \ sync; \ diff --git a/arch/powerpc/include/asm/syscall.h b/arch/powerpc/include/asm/syscall.h index 38d62acfdce7..3dd36c5e334a 100644 --- a/arch/powerpc/include/asm/syscall.h +++ b/arch/powerpc/include/asm/syscall.h @@ -14,9 +14,16 @@ #include <linux/sched.h> #include <linux/thread_info.h> +#ifdef CONFIG_ARCH_HAS_SYSCALL_WRAPPER +typedef long (*syscall_fn)(const struct pt_regs *); +#else +typedef long (*syscall_fn)(unsigned long, unsigned long, unsigned long, + unsigned long, unsigned long, unsigned long); +#endif + /* ftrace syscalls requires exporting the sys_call_table */ -extern const unsigned long sys_call_table[]; -extern const unsigned long compat_sys_call_table[]; +extern const syscall_fn sys_call_table[]; +extern const syscall_fn compat_sys_call_table[]; static inline int syscall_get_nr(struct task_struct *task, struct pt_regs *regs) { @@ -26,7 +33,10 @@ static inline int syscall_get_nr(struct task_struct *task, struct pt_regs *regs) * This is important for seccomp so that compat tasks can set r0 = -1 * to reject the syscall. */ - return TRAP(regs) == 0xc00 ? regs->gpr[0] : -1; + if (trap_is_syscall(regs)) + return regs->gpr[0]; + else + return -1; } static inline void syscall_rollback(struct task_struct *task, @@ -38,11 +48,17 @@ static inline void syscall_rollback(struct task_struct *task, static inline long syscall_get_error(struct task_struct *task, struct pt_regs *regs) { - /* - * If the system call failed, - * regs->gpr[3] contains a positive ERRORCODE. - */ - return (regs->ccr & 0x10000000UL) ? -regs->gpr[3] : 0; + if (trap_is_scv(regs)) { + unsigned long error = regs->gpr[3]; + + return IS_ERR_VALUE(error) ? error : 0; + } else { + /* + * If the system call failed, + * regs->gpr[3] contains a positive ERRORCODE. + */ + return (regs->ccr & 0x10000000UL) ? -regs->gpr[3] : 0; + } } static inline long syscall_get_return_value(struct task_struct *task, @@ -55,18 +71,22 @@ static inline void syscall_set_return_value(struct task_struct *task, struct pt_regs *regs, int error, long val) { - /* - * In the general case it's not obvious that we must deal with CCR - * here, as the syscall exit path will also do that for us. However - * there are some places, eg. the signal code, which check ccr to - * decide if the value in r3 is actually an error. - */ - if (error) { - regs->ccr |= 0x10000000L; - regs->gpr[3] = error; + if (trap_is_scv(regs)) { + regs->gpr[3] = (long) error ?: val; } else { - regs->ccr &= ~0x10000000L; - regs->gpr[3] = val; + /* + * In the general case it's not obvious that we must deal with + * CCR here, as the syscall exit path will also do that for us. + * However there are some places, eg. the signal code, which + * check ccr to decide if the value in r3 is actually an error. + */ + if (error) { + regs->ccr |= 0x10000000L; + regs->gpr[3] = error; + } else { + regs->ccr &= ~0x10000000L; + regs->gpr[3] = val; + } } } @@ -77,10 +97,9 @@ static inline void syscall_get_arguments(struct task_struct *task, unsigned long val, mask = -1UL; unsigned int n = 6; -#ifdef CONFIG_COMPAT - if (test_tsk_thread_flag(task, TIF_32BIT)) + if (is_tsk_32bit_task(task)) mask = 0xffffffff; -#endif + while (n--) { if (n == 0) val = regs->orig_gpr3; @@ -91,28 +110,13 @@ static inline void syscall_get_arguments(struct task_struct *task, } } -static inline void syscall_set_arguments(struct task_struct *task, - struct pt_regs *regs, - const unsigned long *args) -{ - memcpy(®s->gpr[3], args, 6 * sizeof(args[0])); - - /* Also copy the first argument into orig_gpr3 */ - regs->orig_gpr3 = args[0]; -} - static inline int syscall_get_arch(struct task_struct *task) { - int arch; - - if (IS_ENABLED(CONFIG_PPC64) && !test_tsk_thread_flag(task, TIF_32BIT)) - arch = AUDIT_ARCH_PPC64; + if (is_tsk_32bit_task(task)) + return AUDIT_ARCH_PPC; + else if (IS_ENABLED(CONFIG_CPU_LITTLE_ENDIAN)) + return AUDIT_ARCH_PPC64LE; else - arch = AUDIT_ARCH_PPC; - -#ifdef __LITTLE_ENDIAN__ - arch |= __AUDIT_ARCH_LE; -#endif - return arch; + return AUDIT_ARCH_PPC64; } #endif /* _ASM_SYSCALL_H */ diff --git a/arch/powerpc/include/asm/syscall_wrapper.h b/arch/powerpc/include/asm/syscall_wrapper.h new file mode 100644 index 000000000000..67486c67e8a2 --- /dev/null +++ b/arch/powerpc/include/asm/syscall_wrapper.h @@ -0,0 +1,49 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * syscall_wrapper.h - powerpc specific wrappers to syscall definitions + * + * Based on arch/{x86,arm64}/include/asm/syscall_wrapper.h + */ + +#ifndef __ASM_POWERPC_SYSCALL_WRAPPER_H +#define __ASM_POWERPC_SYSCALL_WRAPPER_H + +struct pt_regs; + +#define SC_POWERPC_REGS_TO_ARGS(x, ...) \ + __MAP(x,__SC_ARGS \ + ,,regs->gpr[3],,regs->gpr[4],,regs->gpr[5] \ + ,,regs->gpr[6],,regs->gpr[7],,regs->gpr[8]) + +#define __SYSCALL_DEFINEx(x, name, ...) \ + long sys##name(const struct pt_regs *regs); \ + ALLOW_ERROR_INJECTION(sys##name, ERRNO); \ + static long __se_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)); \ + static inline long __do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)); \ + long sys##name(const struct pt_regs *regs) \ + { \ + return __se_sys##name(SC_POWERPC_REGS_TO_ARGS(x,__VA_ARGS__)); \ + } \ + static long __se_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)) \ + { \ + long ret = __do_sys##name(__MAP(x,__SC_CAST,__VA_ARGS__)); \ + __MAP(x,__SC_TEST,__VA_ARGS__); \ + __PROTECT(x, ret,__MAP(x,__SC_ARGS,__VA_ARGS__)); \ + return ret; \ + } \ + static inline long __do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)) + +#define SYSCALL_DEFINE0(sname) \ + SYSCALL_METADATA(_##sname, 0); \ + long sys_##sname(const struct pt_regs *__unused); \ + ALLOW_ERROR_INJECTION(sys_##sname, ERRNO); \ + long sys_##sname(const struct pt_regs *__unused) + +#define COND_SYSCALL(name) \ + long sys_##name(const struct pt_regs *regs); \ + long __weak sys_##name(const struct pt_regs *regs) \ + { \ + return sys_ni_syscall(); \ + } + +#endif // __ASM_POWERPC_SYSCALL_WRAPPER_H diff --git a/arch/powerpc/include/asm/syscalls.h b/arch/powerpc/include/asm/syscalls.h index 398171fdcd9f..6d51b007b59e 100644 --- a/arch/powerpc/include/asm/syscalls.h +++ b/arch/powerpc/include/asm/syscalls.h @@ -6,17 +6,156 @@ #include <linux/compiler.h> #include <linux/linkage.h> #include <linux/types.h> +#include <linux/compat.h> + +#include <asm/syscall.h> +#ifdef CONFIG_PPC64 +#include <asm/syscalls_32.h> +#endif +#include <asm/unistd.h> +#include <asm/ucontext.h> + +#ifndef CONFIG_ARCH_HAS_SYSCALL_WRAPPER +long sys_ni_syscall(void); +#else +long sys_ni_syscall(const struct pt_regs *regs); +#endif struct rtas_args; -asmlinkage long sys_mmap(unsigned long addr, size_t len, - unsigned long prot, unsigned long flags, - unsigned long fd, off_t offset); -asmlinkage long sys_mmap2(unsigned long addr, size_t len, - unsigned long prot, unsigned long flags, - unsigned long fd, unsigned long pgoff); -asmlinkage long ppc64_personality(unsigned long personality); -asmlinkage long sys_rtas(struct rtas_args __user *uargs); +/* + * long long munging: + * The 32 bit ABI passes long longs in an odd even register pair. + * High and low parts are swapped depending on endian mode, + * so define a macro (similar to mips linux32) to handle that. + */ +#ifdef __LITTLE_ENDIAN__ +#define merge_64(low, high) (((u64)high << 32) | low) +#else +#define merge_64(high, low) (((u64)high << 32) | low) +#endif + +/* + * PowerPC architecture-specific syscalls + */ + +#ifndef CONFIG_ARCH_HAS_SYSCALL_WRAPPER + +long sys_rtas(struct rtas_args __user *uargs); + +#ifdef CONFIG_PPC64 +long sys_ppc64_personality(unsigned long personality); +#ifdef CONFIG_COMPAT +long compat_sys_ppc64_personality(unsigned long personality); +#endif /* CONFIG_COMPAT */ +#endif /* CONFIG_PPC64 */ + +long sys_swapcontext(struct ucontext __user *old_ctx, + struct ucontext __user *new_ctx, long ctx_size); +long sys_mmap(unsigned long addr, size_t len, + unsigned long prot, unsigned long flags, + unsigned long fd, off_t offset); +long sys_mmap2(unsigned long addr, size_t len, + unsigned long prot, unsigned long flags, + unsigned long fd, unsigned long pgoff); +long sys_switch_endian(void); + +#ifdef CONFIG_PPC32 +long sys_sigreturn(void); +long sys_debug_setcontext(struct ucontext __user *ctx, int ndbg, + struct sig_dbg_op __user *dbg); +#endif + +long sys_rt_sigreturn(void); + +long sys_subpage_prot(unsigned long addr, + unsigned long len, u32 __user *map); + +#ifdef CONFIG_COMPAT +long compat_sys_swapcontext(struct ucontext32 __user *old_ctx, + struct ucontext32 __user *new_ctx, + int ctx_size); +long compat_sys_old_getrlimit(unsigned int resource, + struct compat_rlimit __user *rlim); +long compat_sys_sigreturn(void); +long compat_sys_rt_sigreturn(void); +#endif /* CONFIG_COMPAT */ + +/* + * Architecture specific signatures required by long long munging: + * The 32 bit ABI passes long longs in an odd even register pair. + * The following signatures provide a machine long parameter for + * each register that will be supplied. The implementation is + * responsible for combining parameter pairs. + */ + +#ifdef CONFIG_PPC32 +long sys_ppc_pread64(unsigned int fd, + char __user *ubuf, compat_size_t count, + u32 reg6, u32 pos1, u32 pos2); +long sys_ppc_pwrite64(unsigned int fd, + const char __user *ubuf, compat_size_t count, + u32 reg6, u32 pos1, u32 pos2); +long sys_ppc_readahead(int fd, u32 r4, + u32 offset1, u32 offset2, u32 count); +long sys_ppc_truncate64(const char __user *path, u32 reg4, + unsigned long len1, unsigned long len2); +long sys_ppc_ftruncate64(unsigned int fd, u32 reg4, + unsigned long len1, unsigned long len2); +long sys_ppc32_fadvise64(int fd, u32 unused, u32 offset1, u32 offset2, + size_t len, int advice); +long sys_ppc_sync_file_range2(int fd, unsigned int flags, + unsigned int offset1, + unsigned int offset2, + unsigned int nbytes1, + unsigned int nbytes2); +long sys_ppc_fallocate(int fd, int mode, u32 offset1, u32 offset2, + u32 len1, u32 len2); +#endif +#ifdef CONFIG_COMPAT +long compat_sys_mmap2(unsigned long addr, size_t len, + unsigned long prot, unsigned long flags, + unsigned long fd, unsigned long pgoff); +long compat_sys_ppc_pread64(unsigned int fd, + char __user *ubuf, compat_size_t count, + u32 reg6, u32 pos1, u32 pos2); +long compat_sys_ppc_pwrite64(unsigned int fd, + const char __user *ubuf, compat_size_t count, + u32 reg6, u32 pos1, u32 pos2); +long compat_sys_ppc_readahead(int fd, u32 r4, + u32 offset1, u32 offset2, u32 count); +long compat_sys_ppc_truncate64(const char __user *path, u32 reg4, + unsigned long len1, unsigned long len2); +long compat_sys_ppc_ftruncate64(unsigned int fd, u32 reg4, + unsigned long len1, unsigned long len2); +long compat_sys_ppc32_fadvise64(int fd, u32 unused, u32 offset1, u32 offset2, + size_t len, int advice); +long compat_sys_ppc_sync_file_range2(int fd, unsigned int flags, + unsigned int offset1, + unsigned int offset2, + unsigned int nbytes1, + unsigned int nbytes2); +#endif /* CONFIG_COMPAT */ + +#if defined(CONFIG_PPC32) || defined(CONFIG_COMPAT) +long sys_ppc_fadvise64_64(int fd, int advice, + u32 offset_high, u32 offset_low, + u32 len_high, u32 len_low); +#endif + +#else + +#define __SYSCALL_WITH_COMPAT(nr, native, compat) __SYSCALL(nr, native) +#define __SYSCALL(nr, entry) \ + long entry(const struct pt_regs *regs); + +#ifdef CONFIG_PPC64 +#include <asm/syscall_table_64.h> +#else +#include <asm/syscall_table_32.h> +#endif /* CONFIG_PPC64 */ + +#endif /* CONFIG_ARCH_HAS_SYSCALL_WRAPPER */ #endif /* __KERNEL__ */ #endif /* __ASM_POWERPC_SYSCALLS_H */ diff --git a/arch/powerpc/include/asm/syscalls_32.h b/arch/powerpc/include/asm/syscalls_32.h new file mode 100644 index 000000000000..749255568be9 --- /dev/null +++ b/arch/powerpc/include/asm/syscalls_32.h @@ -0,0 +1,60 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _ASM_POWERPC_SYSCALLS_32_H +#define _ASM_POWERPC_SYSCALLS_32_H + +#include <linux/compat.h> +#include <asm/siginfo.h> +#include <asm/signal.h> + +/* + * Data types and macros for providing 32b PowerPC support. + */ + +/* These are here to support 32-bit syscalls on a 64-bit kernel. */ + +struct pt_regs32 { + unsigned int gpr[32]; + unsigned int nip; + unsigned int msr; + unsigned int orig_gpr3; /* Used for restarting system calls */ + unsigned int ctr; + unsigned int link; + unsigned int xer; + unsigned int ccr; + unsigned int mq; /* 601 only (not used at present) */ + unsigned int trap; /* Reason for being here */ + unsigned int dar; /* Fault registers */ + unsigned int dsisr; + unsigned int result; /* Result of a system call */ +}; + +struct sigcontext32 { + unsigned int _unused[4]; + int signal; + compat_uptr_t handler; + unsigned int oldmask; + compat_uptr_t regs; /* 4 byte pointer to the pt_regs32 structure. */ +}; + +struct mcontext32 { + elf_gregset_t32 mc_gregs; + elf_fpregset_t mc_fregs; + unsigned int mc_pad[2]; + elf_vrregset_t32 mc_vregs __attribute__((__aligned__(16))); + elf_vsrreghalf_t32 mc_vsregs __attribute__((__aligned__(16))); +}; + +struct ucontext32 { + unsigned int uc_flags; + unsigned int uc_link; + compat_stack_t uc_stack; + int uc_pad[7]; + compat_uptr_t uc_regs; /* points to uc_mcontext field */ + compat_sigset_t uc_sigmask; /* mask last for extensibility */ + /* glibc has 1024-bit signal masks, ours are 64-bit */ + int uc_maskext[30]; + int uc_pad2[3]; + struct mcontext32 uc_mcontext; +}; + +#endif // _ASM_POWERPC_SYSCALLS_32_H diff --git a/arch/powerpc/include/asm/task_size_64.h b/arch/powerpc/include/asm/task_size_64.h index c993482237ed..5a709951c901 100644 --- a/arch/powerpc/include/asm/task_size_64.h +++ b/arch/powerpc/include/asm/task_size_64.h @@ -44,11 +44,7 @@ */ #define TASK_SIZE_USER32 (0x0000000100000000UL - (1 * PAGE_SIZE)) -#define TASK_SIZE_OF(tsk) \ - (test_tsk_thread_flag(tsk, TIF_32BIT) ? TASK_SIZE_USER32 : \ - TASK_SIZE_USER64) - -#define TASK_SIZE TASK_SIZE_OF(current) +#define TASK_SIZE (is_32bit_task() ? TASK_SIZE_USER32 : TASK_SIZE_USER64) #define TASK_UNMAPPED_BASE_USER32 (PAGE_ALIGN(TASK_SIZE_USER32 / 4)) #define TASK_UNMAPPED_BASE_USER64 (PAGE_ALIGN(DEFAULT_MAP_WINDOW_USER64 / 4)) @@ -76,4 +72,12 @@ #define STACK_TOP_MAX TASK_SIZE_USER64 #define STACK_TOP (is_32bit_task() ? STACK_TOP_USER32 : STACK_TOP_USER64) +#define arch_get_mmap_base(addr, base) \ + (((addr) > DEFAULT_MAP_WINDOW) ? (base) + TASK_SIZE - DEFAULT_MAP_WINDOW : (base)) + +#define arch_get_mmap_end(addr, len, flags) \ + (((addr) > DEFAULT_MAP_WINDOW) || \ + (((flags) & MAP_FIXED) && ((addr) + (len) > DEFAULT_MAP_WINDOW)) ? TASK_SIZE : \ + DEFAULT_MAP_WINDOW) + #endif /* _ASM_POWERPC_TASK_SIZE_64_H */ diff --git a/arch/powerpc/include/asm/tce.h b/arch/powerpc/include/asm/tce.h index db5fc2f2262d..0c34d2756d92 100644 --- a/arch/powerpc/include/asm/tce.h +++ b/arch/powerpc/include/asm/tce.h @@ -19,15 +19,7 @@ #define TCE_VB 0 #define TCE_PCI 1 -/* TCE page size is 4096 bytes (1 << 12) */ - -#define TCE_SHIFT 12 -#define TCE_PAGE_SIZE (1 << TCE_SHIFT) - #define TCE_ENTRY_SIZE 8 /* each TCE is 64 bits */ - -#define TCE_RPN_MASK 0xfffffffffful /* 40-bit RPN (4K pages) */ -#define TCE_RPN_SHIFT 12 #define TCE_VALID 0x800 /* TCE valid */ #define TCE_ALLIO 0x400 /* TCE valid for all lpars */ #define TCE_PCI_WRITE 0x2 /* write from PCI allowed */ diff --git a/arch/powerpc/include/asm/termios.h b/arch/powerpc/include/asm/termios.h deleted file mode 100644 index 205de8f8a9d3..000000000000 --- a/arch/powerpc/include/asm/termios.h +++ /dev/null @@ -1,18 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * Liberally adapted from alpha/termios.h. In particular, the c_cc[] - * fields have been reordered so that termio & termios share the - * common subset in the same order (for brain dead programs that don't - * know or care about the differences). - */ -#ifndef _ASM_POWERPC_TERMIOS_H -#define _ASM_POWERPC_TERMIOS_H - -#include <uapi/asm/termios.h> - -/* ^C ^\ del ^U ^D 1 0 0 0 0 ^W ^R ^Z ^Q ^S ^V ^U */ -#define INIT_C_CC "\003\034\177\025\004\001\000\000\000\000\027\022\032\021\023\026\025" - -#include <asm-generic/termios-base.h> - -#endif /* _ASM_POWERPC_TERMIOS_H */ diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h index 8e1d0195ac36..bf5dde1a4114 100644 --- a/arch/powerpc/include/asm/thread_info.h +++ b/arch/powerpc/include/asm/thread_info.h @@ -10,18 +10,42 @@ #define _ASM_POWERPC_THREAD_INFO_H #include <asm/asm-const.h> +#include <asm/page.h> #ifdef __KERNEL__ -#define THREAD_SHIFT CONFIG_THREAD_SHIFT +#ifdef CONFIG_KASAN +#define MIN_THREAD_SHIFT (CONFIG_THREAD_SHIFT + 1) +#else +#define MIN_THREAD_SHIFT CONFIG_THREAD_SHIFT +#endif + +#if defined(CONFIG_VMAP_STACK) && MIN_THREAD_SHIFT < PAGE_SHIFT +#define THREAD_SHIFT PAGE_SHIFT +#else +#define THREAD_SHIFT MIN_THREAD_SHIFT +#endif #define THREAD_SIZE (1 << THREAD_SHIFT) +/* + * By aligning VMAP'd stacks to 2 * THREAD_SIZE, we can detect overflow by + * checking sp & (1 << THREAD_SHIFT), which we can do cheaply in the entry + * assembly. + */ +#ifdef CONFIG_VMAP_STACK +#define THREAD_ALIGN_SHIFT (THREAD_SHIFT + 1) +#else +#define THREAD_ALIGN_SHIFT THREAD_SHIFT +#endif + +#define THREAD_ALIGN (1 << THREAD_ALIGN_SHIFT) + #ifndef __ASSEMBLY__ #include <linux/cache.h> #include <asm/processor.h> -#include <asm/page.h> #include <asm/accounting.h> +#include <asm/ppc_asm.h> #define SLB_PRELOAD_NR 16U /* @@ -30,8 +54,11 @@ struct thread_info { int preempt_count; /* 0 => preemptable, <0 => BUG */ +#ifdef CONFIG_SMP + unsigned int cpu; +#endif unsigned long local_flags; /* private flags for thread */ -#ifdef CONFIG_LIVEPATCH +#ifdef CONFIG_LIVEPATCH_64 unsigned long *livepatch_sp; #endif #if defined(CONFIG_VIRT_CPU_ACCOUNTING_NATIVE) && defined(CONFIG_PPC32) @@ -59,10 +86,8 @@ struct thread_info { /* how to get the thread information struct from C */ extern int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src); -#ifdef CONFIG_PPC_BOOK3S_64 void arch_setup_new_exec(void); #define arch_setup_new_exec arch_setup_new_exec -#endif #endif /* __ASSEMBLY__ */ @@ -72,13 +97,12 @@ void arch_setup_new_exec(void); #define TIF_SYSCALL_TRACE 0 /* syscall trace active */ #define TIF_SIGPENDING 1 /* signal pending */ #define TIF_NEED_RESCHED 2 /* rescheduling necessary */ -#define TIF_FSCHECK 3 /* Check FS is USER_DS on return */ +#define TIF_NOTIFY_SIGNAL 3 /* signal notifications exist */ #define TIF_SYSCALL_EMU 4 /* syscall emulation active */ #define TIF_RESTORE_TM 5 /* need to restore TM FP/VEC/VSX */ #define TIF_PATCH_PENDING 6 /* pending live patching update */ #define TIF_SYSCALL_AUDIT 7 /* syscall auditing active */ #define TIF_SINGLESTEP 8 /* singlestepping active */ -#define TIF_NOHZ 9 /* in adaptive nohz mode */ #define TIF_SECCOMP 10 /* secure computing */ #define TIF_RESTOREALL 11 /* Restore all regs (implies NOERROR) */ #define TIF_NOERROR 12 /* Force successful syscall return */ @@ -98,6 +122,7 @@ void arch_setup_new_exec(void); #define _TIF_SYSCALL_TRACE (1<<TIF_SYSCALL_TRACE) #define _TIF_SIGPENDING (1<<TIF_SIGPENDING) #define _TIF_NEED_RESCHED (1<<TIF_NEED_RESCHED) +#define _TIF_NOTIFY_SIGNAL (1<<TIF_NOTIFY_SIGNAL) #define _TIF_POLLING_NRFLAG (1<<TIF_POLLING_NRFLAG) #define _TIF_32BIT (1<<TIF_32BIT) #define _TIF_RESTORE_TM (1<<TIF_RESTORE_TM) @@ -111,17 +136,15 @@ void arch_setup_new_exec(void); #define _TIF_UPROBE (1<<TIF_UPROBE) #define _TIF_SYSCALL_TRACEPOINT (1<<TIF_SYSCALL_TRACEPOINT) #define _TIF_EMULATE_STACK_STORE (1<<TIF_EMULATE_STACK_STORE) -#define _TIF_NOHZ (1<<TIF_NOHZ) -#define _TIF_FSCHECK (1<<TIF_FSCHECK) #define _TIF_SYSCALL_EMU (1<<TIF_SYSCALL_EMU) #define _TIF_SYSCALL_DOTRACE (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \ _TIF_SECCOMP | _TIF_SYSCALL_TRACEPOINT | \ - _TIF_NOHZ | _TIF_SYSCALL_EMU) + _TIF_SYSCALL_EMU) #define _TIF_USER_WORK_MASK (_TIF_SIGPENDING | _TIF_NEED_RESCHED | \ _TIF_NOTIFY_RESUME | _TIF_UPROBE | \ _TIF_RESTORE_TM | _TIF_PATCH_PENDING | \ - _TIF_FSCHECK) + _TIF_NOTIFY_SIGNAL) #define _TIF_PERSYSCALL_MASK (_TIF_RESTOREALL|_TIF_NOERROR) /* Bits in local_flags */ @@ -138,16 +161,26 @@ void arch_setup_new_exec(void); #ifndef __ASSEMBLY__ +static inline void clear_thread_local_flags(unsigned int flags) +{ + struct thread_info *ti = current_thread_info(); + ti->local_flags &= ~flags; +} + static inline bool test_thread_local_flags(unsigned int flags) { struct thread_info *ti = current_thread_info(); return (ti->local_flags & flags) != 0; } -#ifdef CONFIG_PPC64 +#ifdef CONFIG_COMPAT #define is_32bit_task() (test_thread_flag(TIF_32BIT)) +#define is_tsk_32bit_task(tsk) (test_tsk_thread_flag(tsk, TIF_32BIT)) +#define clear_tsk_compat_task(tsk) (clear_tsk_thread_flag(p, TIF_32BIT)) #else -#define is_32bit_task() (1) +#define is_32bit_task() (IS_ENABLED(CONFIG_PPC32)) +#define is_tsk_32bit_task(tsk) (IS_ENABLED(CONFIG_PPC32)) +#define clear_tsk_compat_task(tsk) do { } while (0) #endif #if defined(CONFIG_PPC64) @@ -156,6 +189,43 @@ static inline bool test_thread_local_flags(unsigned int flags) #define is_elf2_task() (0) #endif +/* + * Walks up the stack frames to make sure that the specified object is + * entirely contained by a single stack frame. + * + * Returns: + * GOOD_FRAME if within a frame + * BAD_STACK if placed across a frame boundary (or outside stack) + */ +static inline int arch_within_stack_frames(const void * const stack, + const void * const stackend, + const void *obj, unsigned long len) +{ + const void *params; + const void *frame; + + params = *(const void * const *)current_stack_pointer + STACK_FRAME_PARAMS; + frame = **(const void * const * const *)current_stack_pointer; + + /* + * low -----------------------------------------------------------> high + * [backchain][metadata][params][local vars][saved registers][backchain] + * ^------------------------------------^ + * | allows copies only in this region | + * | | + * params frame + * The metadata region contains the saved LR, CR etc. + */ + while (stack <= frame && frame < stackend) { + if (obj + len <= frame) + return obj >= params ? GOOD_FRAME : BAD_STACK; + params = frame + STACK_FRAME_PARAMS; + frame = *(const void * const *)frame; + } + + return BAD_STACK; +} + #endif /* !__ASSEMBLY__ */ #endif /* __KERNEL__ */ diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h index 08dbe3e6831c..9f50766c4623 100644 --- a/arch/powerpc/include/asm/time.h +++ b/arch/powerpc/include/asm/time.h @@ -15,16 +15,19 @@ #include <asm/processor.h> #include <asm/cpu_has_feature.h> +#include <asm/vdso/timebase.h> /* time.c */ +extern u64 decrementer_max; + extern unsigned long tb_ticks_per_jiffy; extern unsigned long tb_ticks_per_usec; extern unsigned long tb_ticks_per_sec; extern struct clock_event_device decrementer_clockevent; +extern u64 decrementer_max; extern void generic_calibrate_decr(void); -extern void hdec_interrupt(struct pt_regs *regs); /* Some sane defaults: 125 MHz timebase, 1GHz processor */ extern unsigned long ppc_proc_freq; @@ -39,98 +42,12 @@ struct div_result { u64 result_low; }; -/* Accessor functions for the timebase (RTC on 601) registers. */ -/* If one day CONFIG_POWER is added just define __USE_RTC as 1 */ -#define __USE_RTC() (IS_ENABLED(CONFIG_PPC_BOOK3S_601)) - -#ifdef CONFIG_PPC64 - -/* For compatibility, get_tbl() is defined as get_tb() on ppc64 */ -#define get_tbl get_tb - -#else - -static inline unsigned long get_tbl(void) -{ -#if defined(CONFIG_403GCX) - unsigned long tbl; - asm volatile("mfspr %0, 0x3dd" : "=r" (tbl)); - return tbl; -#else - return mftbl(); -#endif -} - -static inline unsigned int get_tbu(void) -{ -#ifdef CONFIG_403GCX - unsigned int tbu; - asm volatile("mfspr %0, 0x3dc" : "=r" (tbu)); - return tbu; -#else - return mftbu(); -#endif -} -#endif /* !CONFIG_PPC64 */ - -static inline unsigned int get_rtcl(void) -{ - unsigned int rtcl; - - asm volatile("mfrtcl %0" : "=r" (rtcl)); - return rtcl; -} - -static inline u64 get_rtc(void) -{ - unsigned int hi, lo, hi2; - - do { - asm volatile("mfrtcu %0; mfrtcl %1; mfrtcu %2" - : "=r" (hi), "=r" (lo), "=r" (hi2)); - } while (hi2 != hi); - return (u64)hi * 1000000000 + lo; -} - static inline u64 get_vtb(void) { -#ifdef CONFIG_PPC_BOOK3S_64 if (cpu_has_feature(CPU_FTR_ARCH_207S)) return mfspr(SPRN_VTB); -#endif - return 0; -} - -#ifdef CONFIG_PPC64 -static inline u64 get_tb(void) -{ - return mftb(); -} -#else /* CONFIG_PPC64 */ -static inline u64 get_tb(void) -{ - unsigned int tbhi, tblo, tbhi2; - - do { - tbhi = get_tbu(); - tblo = get_tbl(); - tbhi2 = get_tbu(); - } while (tbhi != tbhi2); - return ((u64)tbhi << 32) | tblo; -} -#endif /* !CONFIG_PPC64 */ - -static inline u64 get_tb_or_rtc(void) -{ - return __USE_RTC() ? get_rtc() : get_tb(); -} - -static inline void set_tb(unsigned int upper, unsigned int lower) -{ - mtspr(SPRN_TBWL, 0); - mtspr(SPRN_TBWU, upper); - mtspr(SPRN_TBWL, lower); + return 0; } /* Accessor functions for the decrementer register. @@ -141,11 +58,10 @@ static inline void set_tb(unsigned int upper, unsigned int lower) */ static inline u64 get_dec(void) { -#if defined(CONFIG_40x) - return (mfspr(SPRN_PIT)); -#else - return (mfspr(SPRN_DEC)); -#endif + if (IS_ENABLED(CONFIG_40x)) + return mfspr(SPRN_PIT); + + return mfspr(SPRN_DEC); } /* @@ -155,23 +71,17 @@ static inline u64 get_dec(void) */ static inline void set_dec(u64 val) { -#if defined(CONFIG_40x) - mtspr(SPRN_PIT, (u32) val); -#else -#ifndef CONFIG_BOOKE - --val; -#endif - mtspr(SPRN_DEC, val); -#endif /* not 40x */ + if (IS_ENABLED(CONFIG_40x)) + mtspr(SPRN_PIT, (u32)val); + else if (IS_ENABLED(CONFIG_BOOKE)) + mtspr(SPRN_DEC, val); + else + mtspr(SPRN_DEC, val - 1); } static inline unsigned long tb_ticks_since(unsigned long tstamp) { - if (__USE_RTC()) { - int delta = get_rtcl() - (unsigned int) tstamp; - return delta < 0 ? delta + 1000000000 : delta; - } - return get_tbl() - tstamp; + return mftb() - tstamp; } #define mulhwu(x,y) \ @@ -192,8 +102,23 @@ extern void __init time_init(void); DECLARE_PER_CPU(u64, decrementers_next_tb); +static inline u64 timer_get_next_tb(void) +{ + return __this_cpu_read(decrementers_next_tb); +} + +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE +void timer_rearm_host_dec(u64 now); +#endif + /* Convert timebase ticks to nanoseconds */ unsigned long long tb_to_ns(unsigned long long tb_ticks); +void timer_broadcast_interrupt(void); + +/* SPLPAR and VIRT_CPU_ACCOUNTING_NATIVE */ +void pseries_accumulate_stolen_time(void); +u64 pseries_calculate_stolen_time(u64 stop_tb); + #endif /* __KERNEL__ */ #endif /* __POWERPC_TIME_H */ diff --git a/arch/powerpc/include/asm/timex.h b/arch/powerpc/include/asm/timex.h index d2d2c4bd8435..14b4489de52c 100644 --- a/arch/powerpc/include/asm/timex.h +++ b/arch/powerpc/include/asm/timex.h @@ -9,7 +9,7 @@ */ #include <asm/cputable.h> -#include <asm/reg.h> +#include <asm/vdso/timebase.h> #define CLOCK_TICK_RATE 1024000 /* Underlying HZ */ @@ -17,11 +17,9 @@ typedef unsigned long cycles_t; static inline cycles_t get_cycles(void) { - if (IS_ENABLED(CONFIG_BOOK3S_601)) - return 0; - return mftb(); } +#define get_cycles get_cycles #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_TIMEX_H */ diff --git a/arch/powerpc/include/asm/tlb.h b/arch/powerpc/include/asm/tlb.h index b2c0be93929d..b3de6102a907 100644 --- a/arch/powerpc/include/asm/tlb.h +++ b/arch/powerpc/include/asm/tlb.h @@ -10,9 +10,8 @@ #ifdef __KERNEL__ #ifndef __powerpc64__ -#include <asm/pgtable.h> +#include <linux/pgtable.h> #endif -#include <asm/pgalloc.h> #ifndef __powerpc64__ #include <asm/page.h> #include <asm/mmu.h> @@ -20,19 +19,25 @@ #include <linux/pagemap.h> -#define tlb_start_vma(tlb, vma) do { } while (0) -#define tlb_end_vma(tlb, vma) do { } while (0) #define __tlb_remove_tlb_entry __tlb_remove_tlb_entry #define tlb_flush tlb_flush extern void tlb_flush(struct mmu_gather *tlb); +/* + * book3s: + * Hash does not use the linux page-tables, so we can avoid + * the TLB invalidate for page-table freeing, Radix otoh does use the + * page-tables and needs the TLBI. + * + * nohash: + * We still do TLB invalidate in the __pte_free_tlb routine before we + * add the page table pages to mmu gather table batch. + */ +#define tlb_needs_table_invalidate() radix_enabled() /* Get the generic bits... */ #include <asm-generic/tlb.h> -extern void flush_hash_entry(struct mm_struct *mm, pte_t *ptep, - unsigned long address); - static inline void __tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep, unsigned long address) { @@ -56,19 +61,6 @@ static inline int mm_is_thread_local(struct mm_struct *mm) return false; return cpumask_test_cpu(smp_processor_id(), mm_cpumask(mm)); } -static inline void mm_reset_thread_local(struct mm_struct *mm) -{ - WARN_ON(atomic_read(&mm->context.copros) > 0); - /* - * It's possible for mm_access to take a reference on mm_users to - * access the remote mm from another thread, but it's not allowed - * to set mm_cpumask, so mm_users may be > 1 here. - */ - WARN_ON(current->mm != mm); - atomic_set(&mm->context.active_cpus, 1); - cpumask_clear(mm_cpumask(mm)); - cpumask_set_cpu(smp_processor_id(), mm_cpumask(mm)); -} #else /* CONFIG_PPC_BOOK3S_64 */ static inline int mm_is_thread_local(struct mm_struct *mm) { @@ -89,5 +81,11 @@ static inline int mm_is_thread_local(struct mm_struct *mm) } #endif +#define arch_supports_page_table_move arch_supports_page_table_move +static inline bool arch_supports_page_table_move(void) +{ + return radix_enabled(); +} + #endif /* __KERNEL__ */ #endif /* __ASM_POWERPC_TLB_H */ diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h index 2f7e1ea5089e..f4e6f2dd04b7 100644 --- a/arch/powerpc/include/asm/topology.h +++ b/arch/powerpc/include/asm/topology.h @@ -6,6 +6,7 @@ struct device; struct device_node; +struct drmem_lmb; #ifdef CONFIG_NUMA @@ -35,7 +36,7 @@ static inline int pcibus_to_node(struct pci_bus *bus) cpu_all_mask : \ cpumask_of_node(pcibus_to_node(bus))) -extern int cpu_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc); +int cpu_relative_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc); extern int __node_distance(int, int); #define node_distance(a, b) __node_distance(a, b) @@ -43,7 +44,6 @@ extern void __init dump_numa_cpu_topology(void); extern int sysfs_add_device_to_node(struct device *dev, int nid); extern void sysfs_remove_device_from_node(struct device *dev, int nid); -extern int numa_update_cpu_topology(bool cpus_locked); static inline void update_numa_cpu_lookup_table(unsigned int cpu, int node) { @@ -62,6 +62,15 @@ static inline int early_cpu_to_node(int cpu) */ return (nid < 0) ? 0 : nid; } + +int of_drconf_to_nid_single(struct drmem_lmb *lmb); +void update_numa_distance(struct device_node *node); + +extern void map_cpu_to_node(int cpu, int node); +#ifdef CONFIG_HOTPLUG_CPU +extern void unmap_cpu_from_node(unsigned long cpu); +#endif /* CONFIG_HOTPLUG_CPU */ + #else static inline int early_cpu_to_node(int cpu) { return 0; } @@ -78,52 +87,43 @@ static inline void sysfs_remove_device_from_node(struct device *dev, { } -static inline int numa_update_cpu_topology(bool cpus_locked) +static inline void update_numa_cpu_lookup_table(unsigned int cpu, int node) {} + +static inline int cpu_relative_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc) { return 0; } -static inline void update_numa_cpu_lookup_table(unsigned int cpu, int node) {} - -static inline int cpu_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc) +static inline int of_drconf_to_nid_single(struct drmem_lmb *lmb) { - return 0; + return first_online_node; } +static inline void update_numa_distance(struct device_node *node) {} + +#ifdef CONFIG_SMP +static inline void map_cpu_to_node(int cpu, int node) {} +#ifdef CONFIG_HOTPLUG_CPU +static inline void unmap_cpu_from_node(unsigned long cpu) {} +#endif /* CONFIG_HOTPLUG_CPU */ +#endif /* CONFIG_SMP */ + #endif /* CONFIG_NUMA */ #if defined(CONFIG_NUMA) && defined(CONFIG_PPC_SPLPAR) -extern int start_topology_update(void); -extern int stop_topology_update(void); -extern int prrn_is_enabled(void); -extern int find_and_online_cpu_nid(int cpu); -extern int timed_topology_update(int nsecs); -extern void __init shared_proc_topology_init(void); +void find_and_update_cpu_nid(int cpu); +extern int cpu_to_coregroup_id(int cpu); #else -static inline int start_topology_update(void) -{ - return 0; -} -static inline int stop_topology_update(void) -{ - return 0; -} -static inline int prrn_is_enabled(void) -{ - return 0; -} -static inline int find_and_online_cpu_nid(int cpu) -{ - return 0; -} -static inline int timed_topology_update(int nsecs) +static inline void find_and_update_cpu_nid(int cpu) {} +static inline int cpu_to_coregroup_id(int cpu) { +#ifdef CONFIG_SMP + return cpu_to_core_id(cpu); +#else return 0; +#endif } -#ifdef CONFIG_SMP -static inline void shared_proc_topology_init(void) {} -#endif #endif /* CONFIG_NUMA && CONFIG_PPC_SPLPAR */ #include <asm-generic/topology.h> @@ -135,13 +135,28 @@ static inline void shared_proc_topology_init(void) {} #include <asm/smp.h> #define topology_physical_package_id(cpu) (cpu_to_chip_id(cpu)) + #define topology_sibling_cpumask(cpu) (per_cpu(cpu_sibling_map, cpu)) #define topology_core_cpumask(cpu) (per_cpu(cpu_core_map, cpu)) #define topology_core_id(cpu) (cpu_to_core_id(cpu)) -int dlpar_cpu_readd(int cpu); #endif #endif +#ifdef CONFIG_HOTPLUG_SMT +#include <linux/cpu_smt.h> +#include <asm/cputhreads.h> + +static inline bool topology_is_primary_thread(unsigned int cpu) +{ + return cpu == cpu_first_thread_sibling(cpu); +} + +static inline bool topology_smt_thread_allowed(unsigned int cpu) +{ + return cpu_thread_in_core(cpu) < cpu_smt_num_threads; +} +#endif + #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_TOPOLOGY_H */ diff --git a/arch/powerpc/include/asm/trace.h b/arch/powerpc/include/asm/trace.h index 08cd60cd70b7..82cc2c6704e6 100644 --- a/arch/powerpc/include/asm/trace.h +++ b/arch/powerpc/include/asm/trace.h @@ -119,6 +119,109 @@ TRACE_EVENT_FN_COND(hcall_exit, ); #endif +#ifdef CONFIG_PPC_RTAS + +#include <asm/rtas-types.h> + +TRACE_EVENT(rtas_input, + + TP_PROTO(struct rtas_args *rtas_args, const char *name), + + TP_ARGS(rtas_args, name), + + TP_STRUCT__entry( + __field(__u32, nargs) + __string(name, name) + __dynamic_array(__u32, inputs, be32_to_cpu(rtas_args->nargs)) + ), + + TP_fast_assign( + __entry->nargs = be32_to_cpu(rtas_args->nargs); + __assign_str(name, name); + be32_to_cpu_array(__get_dynamic_array(inputs), rtas_args->args, __entry->nargs); + ), + + TP_printk("%s arguments: %s", __get_str(name), + __print_array(__get_dynamic_array(inputs), __entry->nargs, 4) + ) +); + +TRACE_EVENT(rtas_output, + + TP_PROTO(struct rtas_args *rtas_args, const char *name), + + TP_ARGS(rtas_args, name), + + TP_STRUCT__entry( + __field(__u32, nr_other) + __field(__s32, status) + __string(name, name) + __dynamic_array(__u32, other_outputs, be32_to_cpu(rtas_args->nret) - 1) + ), + + TP_fast_assign( + __entry->nr_other = be32_to_cpu(rtas_args->nret) - 1; + __entry->status = be32_to_cpu(rtas_args->rets[0]); + __assign_str(name, name); + be32_to_cpu_array(__get_dynamic_array(other_outputs), + &rtas_args->rets[1], __entry->nr_other); + ), + + TP_printk("%s status: %d, other outputs: %s", __get_str(name), __entry->status, + __print_array(__get_dynamic_array(other_outputs), + __entry->nr_other, 4) + ) +); + +DECLARE_EVENT_CLASS(rtas_parameter_block, + + TP_PROTO(struct rtas_args *rtas_args), + + TP_ARGS(rtas_args), + + TP_STRUCT__entry( + __field(u32, token) + __field(u32, nargs) + __field(u32, nret) + __array(__u32, params, 16) + ), + + TP_fast_assign( + __entry->token = be32_to_cpu(rtas_args->token); + __entry->nargs = be32_to_cpu(rtas_args->nargs); + __entry->nret = be32_to_cpu(rtas_args->nret); + be32_to_cpu_array(__entry->params, rtas_args->args, ARRAY_SIZE(rtas_args->args)); + ), + + TP_printk("token=%u nargs=%u nret=%u params:" + " [0]=0x%08x [1]=0x%08x [2]=0x%08x [3]=0x%08x" + " [4]=0x%08x [5]=0x%08x [6]=0x%08x [7]=0x%08x" + " [8]=0x%08x [9]=0x%08x [10]=0x%08x [11]=0x%08x" + " [12]=0x%08x [13]=0x%08x [14]=0x%08x [15]=0x%08x", + __entry->token, __entry->nargs, __entry->nret, + __entry->params[0], __entry->params[1], __entry->params[2], __entry->params[3], + __entry->params[4], __entry->params[5], __entry->params[6], __entry->params[7], + __entry->params[8], __entry->params[9], __entry->params[10], __entry->params[11], + __entry->params[12], __entry->params[13], __entry->params[14], __entry->params[15] + ) +); + +DEFINE_EVENT(rtas_parameter_block, rtas_ll_entry, + + TP_PROTO(struct rtas_args *rtas_args), + + TP_ARGS(rtas_args) +); + +DEFINE_EVENT(rtas_parameter_block, rtas_ll_exit, + + TP_PROTO(struct rtas_args *rtas_args), + + TP_ARGS(rtas_args) +); + +#endif /* CONFIG_PPC_RTAS */ + #ifdef CONFIG_PPC_POWERNV extern int opal_tracepoint_regfunc(void); extern void opal_tracepoint_unregfunc(void); diff --git a/arch/powerpc/include/asm/types.h b/arch/powerpc/include/asm/types.h index f1630c553efe..93157a661dcc 100644 --- a/arch/powerpc/include/asm/types.h +++ b/arch/powerpc/include/asm/types.h @@ -11,24 +11,10 @@ #include <uapi/asm/types.h> -#ifdef __powerpc64__ -#if defined(_CALL_ELF) && _CALL_ELF == 2 -#define PPC64_ELF_ABI_v2 -#else -#define PPC64_ELF_ABI_v1 -#endif -#endif /* __powerpc64__ */ - #ifndef __ASSEMBLY__ typedef __vector128 vector128; -typedef struct { - unsigned long entry; - unsigned long toc; - unsigned long env; -} func_descr_t; - #endif /* __ASSEMBLY__ */ #endif /* _ASM_POWERPC_TYPES_H */ diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index 15002b51ff18..f1f9890f50d3 100644 --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -2,69 +2,17 @@ #ifndef _ARCH_POWERPC_UACCESS_H #define _ARCH_POWERPC_UACCESS_H -#include <asm/ppc_asm.h> #include <asm/processor.h> #include <asm/page.h> #include <asm/extable.h> #include <asm/kup.h> -/* - * The fs value determines whether argument validity checking should be - * performed or not. If get_fs() == USER_DS, checking is performed, with - * get_fs() == KERNEL_DS, checking is bypassed. - * - * For historical reasons, these macros are grossly misnamed. - * - * The fs/ds values are now the highest legal address in the "segment". - * This simplifies the checking in the routines below. - */ - -#define MAKE_MM_SEG(s) ((mm_segment_t) { (s) }) - -#define KERNEL_DS MAKE_MM_SEG(~0UL) #ifdef __powerpc64__ /* We use TASK_SIZE_USER64 as TASK_SIZE is not constant */ -#define USER_DS MAKE_MM_SEG(TASK_SIZE_USER64 - 1) -#else -#define USER_DS MAKE_MM_SEG(TASK_SIZE - 1) -#endif - -#define get_fs() (current->thread.addr_limit) - -static inline void set_fs(mm_segment_t fs) -{ - current->thread.addr_limit = fs; - /* On user-mode return check addr_limit (fs) is correct */ - set_thread_flag(TIF_FSCHECK); -} - -#define segment_eq(a, b) ((a).seg == (b).seg) - -#define user_addr_max() (get_fs().seg) - -#ifdef __powerpc64__ -/* - * This check is sufficient because there is a large enough - * gap between user addresses and the kernel addresses - */ -#define __access_ok(addr, size, segment) \ - (((addr) <= (segment).seg) && ((size) <= (segment).seg)) - -#else - -static inline int __access_ok(unsigned long addr, unsigned long size, - mm_segment_t seg) -{ - if (addr > seg.seg) - return 0; - return (size == 0 || size - 1 <= seg.seg - addr); -} - +#define TASK_SIZE_MAX TASK_SIZE_USER64 #endif -#define access_ok(addr, size) \ - (__chk_user_ptr(addr), \ - __access_ok((__force unsigned long)(addr), (size), get_fs())) +#include <asm-generic/access_ok.h> /* * These are the main single-value transfer routines. They automatically @@ -85,114 +33,105 @@ static inline int __access_ok(unsigned long addr, unsigned long size, * exception handling means that it's no longer "just"...) * */ -#define get_user(x, ptr) \ - __get_user_check((x), (ptr), sizeof(*(ptr))) -#define put_user(x, ptr) \ - __put_user_check((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr))) - -#define __get_user(x, ptr) \ - __get_user_nocheck((x), (ptr), sizeof(*(ptr))) -#define __put_user(x, ptr) \ - __put_user_nocheck((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr))) - -#define __get_user_inatomic(x, ptr) \ - __get_user_nosleep((x), (ptr), sizeof(*(ptr))) -#define __put_user_inatomic(x, ptr) \ - __put_user_nosleep((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr))) +#define __put_user(x, ptr) \ +({ \ + long __pu_err; \ + __typeof__(*(ptr)) __user *__pu_addr = (ptr); \ + __typeof__(*(ptr)) __pu_val = (__typeof__(*(ptr)))(x); \ + __typeof__(sizeof(*(ptr))) __pu_size = sizeof(*(ptr)); \ + \ + might_fault(); \ + do { \ + __label__ __pu_failed; \ + \ + allow_write_to_user(__pu_addr, __pu_size); \ + __put_user_size_goto(__pu_val, __pu_addr, __pu_size, __pu_failed); \ + prevent_write_to_user(__pu_addr, __pu_size); \ + __pu_err = 0; \ + break; \ + \ +__pu_failed: \ + prevent_write_to_user(__pu_addr, __pu_size); \ + __pu_err = -EFAULT; \ + } while (0); \ + \ + __pu_err; \ +}) -extern long __put_user_bad(void); +#define put_user(x, ptr) \ +({ \ + __typeof__(*(ptr)) __user *_pu_addr = (ptr); \ + \ + access_ok(_pu_addr, sizeof(*(ptr))) ? \ + __put_user(x, _pu_addr) : -EFAULT; \ +}) /* * We don't tell gcc that we are accessing memory, but this is OK * because we do not write to any memory gcc knows about, so there * are no aliasing issues. */ -#define __put_user_asm(x, addr, err, op) \ - __asm__ __volatile__( \ - "1: " op " %1,0(%2) # put_user\n" \ - "2:\n" \ - ".section .fixup,\"ax\"\n" \ - "3: li %0,%3\n" \ - " b 2b\n" \ - ".previous\n" \ - EX_TABLE(1b, 3b) \ - : "=r" (err) \ - : "r" (x), "b" (addr), "i" (-EFAULT), "0" (err)) +/* -mprefixed can generate offsets beyond range, fall back hack */ +#ifdef CONFIG_PPC_KERNEL_PREFIXED +#define __put_user_asm_goto(x, addr, label, op) \ + asm_volatile_goto( \ + "1: " op " %0,0(%1) # put_user\n" \ + EX_TABLE(1b, %l2) \ + : \ + : "r" (x), "b" (addr) \ + : \ + : label) +#else +#define __put_user_asm_goto(x, addr, label, op) \ + asm_volatile_goto( \ + "1: " op "%U1%X1 %0,%1 # put_user\n" \ + EX_TABLE(1b, %l2) \ + : \ + : "r" (x), "m<>" (*addr) \ + : \ + : label) +#endif #ifdef __powerpc64__ -#define __put_user_asm2(x, ptr, retval) \ - __put_user_asm(x, ptr, retval, "std") +#define __put_user_asm2_goto(x, ptr, label) \ + __put_user_asm_goto(x, ptr, label, "std") #else /* __powerpc64__ */ -#define __put_user_asm2(x, addr, err) \ - __asm__ __volatile__( \ - "1: stw %1,0(%2)\n" \ - "2: stw %1+1,4(%2)\n" \ - "3:\n" \ - ".section .fixup,\"ax\"\n" \ - "4: li %0,%3\n" \ - " b 3b\n" \ - ".previous\n" \ - EX_TABLE(1b, 4b) \ - EX_TABLE(2b, 4b) \ - : "=r" (err) \ - : "r" (x), "b" (addr), "i" (-EFAULT), "0" (err)) +#define __put_user_asm2_goto(x, addr, label) \ + asm_volatile_goto( \ + "1: stw%X1 %0, %1\n" \ + "2: stw%X1 %L0, %L1\n" \ + EX_TABLE(1b, %l2) \ + EX_TABLE(2b, %l2) \ + : \ + : "r" (x), "m" (*addr) \ + : \ + : label) #endif /* __powerpc64__ */ -#define __put_user_size(x, ptr, size, retval) \ +#define __put_user_size_goto(x, ptr, size, label) \ do { \ - retval = 0; \ - allow_write_to_user(ptr, size); \ + __typeof__(*(ptr)) __user *__pus_addr = (ptr); \ + \ switch (size) { \ - case 1: __put_user_asm(x, ptr, retval, "stb"); break; \ - case 2: __put_user_asm(x, ptr, retval, "sth"); break; \ - case 4: __put_user_asm(x, ptr, retval, "stw"); break; \ - case 8: __put_user_asm2(x, ptr, retval); break; \ - default: __put_user_bad(); \ + case 1: __put_user_asm_goto(x, __pus_addr, label, "stb"); break; \ + case 2: __put_user_asm_goto(x, __pus_addr, label, "sth"); break; \ + case 4: __put_user_asm_goto(x, __pus_addr, label, "stw"); break; \ + case 8: __put_user_asm2_goto(x, __pus_addr, label); break; \ + default: BUILD_BUG(); \ } \ - prevent_write_to_user(ptr, size); \ } while (0) -#define __put_user_nocheck(x, ptr, size) \ -({ \ - long __pu_err; \ - __typeof__(*(ptr)) __user *__pu_addr = (ptr); \ - if (!is_kernel_addr((unsigned long)__pu_addr)) \ - might_fault(); \ - __chk_user_ptr(ptr); \ - __put_user_size((x), __pu_addr, (size), __pu_err); \ - __pu_err; \ -}) - -#define __put_user_check(x, ptr, size) \ -({ \ - long __pu_err = -EFAULT; \ - __typeof__(*(ptr)) __user *__pu_addr = (ptr); \ - might_fault(); \ - if (access_ok(__pu_addr, size)) \ - __put_user_size((x), __pu_addr, (size), __pu_err); \ - __pu_err; \ -}) - -#define __put_user_nosleep(x, ptr, size) \ -({ \ - long __pu_err; \ - __typeof__(*(ptr)) __user *__pu_addr = (ptr); \ - __chk_user_ptr(ptr); \ - __put_user_size((x), __pu_addr, (size), __pu_err); \ - __pu_err; \ -}) - - -extern long __get_user_bad(void); - /* * This does an atomic 128 byte aligned load from userspace. * Upto caller to do enable_kernel_vmx() before calling! */ #define __get_user_atomic_128_aligned(kaddr, uaddr, err) \ __asm__ __volatile__( \ + ".machine push\n" \ + ".machine altivec\n" \ "1: lvx 0,0,%1 # get user\n" \ " stvx 0,0,%2 # put kernel\n" \ + ".machine pop\n" \ "2:\n" \ ".section .fixup,\"ax\"\n" \ "3: li %0,%3\n" \ @@ -202,9 +141,74 @@ extern long __get_user_bad(void); : "=r" (err) \ : "b" (uaddr), "b" (kaddr), "i" (-EFAULT), "0" (err)) +#ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT + +/* -mprefixed can generate offsets beyond range, fall back hack */ +#ifdef CONFIG_PPC_KERNEL_PREFIXED +#define __get_user_asm_goto(x, addr, label, op) \ + asm_volatile_goto( \ + "1: "op" %0,0(%1) # get_user\n" \ + EX_TABLE(1b, %l2) \ + : "=r" (x) \ + : "b" (addr) \ + : \ + : label) +#else +#define __get_user_asm_goto(x, addr, label, op) \ + asm_volatile_goto( \ + "1: "op"%U1%X1 %0, %1 # get_user\n" \ + EX_TABLE(1b, %l2) \ + : "=r" (x) \ + : "m<>" (*addr) \ + : \ + : label) +#endif + +#ifdef __powerpc64__ +#define __get_user_asm2_goto(x, addr, label) \ + __get_user_asm_goto(x, addr, label, "ld") +#else /* __powerpc64__ */ +#define __get_user_asm2_goto(x, addr, label) \ + asm_volatile_goto( \ + "1: lwz%X1 %0, %1\n" \ + "2: lwz%X1 %L0, %L1\n" \ + EX_TABLE(1b, %l2) \ + EX_TABLE(2b, %l2) \ + : "=&r" (x) \ + : "m" (*addr) \ + : \ + : label) +#endif /* __powerpc64__ */ + +#define __get_user_size_goto(x, ptr, size, label) \ +do { \ + BUILD_BUG_ON(size > sizeof(x)); \ + switch (size) { \ + case 1: __get_user_asm_goto(x, (u8 __user *)ptr, label, "lbz"); break; \ + case 2: __get_user_asm_goto(x, (u16 __user *)ptr, label, "lhz"); break; \ + case 4: __get_user_asm_goto(x, (u32 __user *)ptr, label, "lwz"); break; \ + case 8: __get_user_asm2_goto(x, (u64 __user *)ptr, label); break; \ + default: x = 0; BUILD_BUG(); \ + } \ +} while (0) + +#define __get_user_size_allowed(x, ptr, size, retval) \ +do { \ + __label__ __gus_failed; \ + \ + __get_user_size_goto(x, ptr, size, __gus_failed); \ + retval = 0; \ + break; \ +__gus_failed: \ + x = 0; \ + retval = -EFAULT; \ +} while (0) + +#else /* CONFIG_CC_HAS_ASM_GOTO_OUTPUT */ + #define __get_user_asm(x, addr, err, op) \ __asm__ __volatile__( \ - "1: "op" %1,0(%2) # get_user\n" \ + "1: "op"%U2%X2 %1, %2 # get_user\n" \ "2:\n" \ ".section .fixup,\"ax\"\n" \ "3: li %0,%3\n" \ @@ -213,7 +217,7 @@ extern long __get_user_bad(void); ".previous\n" \ EX_TABLE(1b, 3b) \ : "=r" (err), "=r" (x) \ - : "b" (addr), "i" (-EFAULT), "0" (err)) + : "m<>" (*addr), "i" (-EFAULT), "0" (err)) #ifdef __powerpc64__ #define __get_user_asm2(x, addr, err) \ @@ -221,8 +225,8 @@ extern long __get_user_bad(void); #else /* __powerpc64__ */ #define __get_user_asm2(x, addr, err) \ __asm__ __volatile__( \ - "1: lwz %1,0(%2)\n" \ - "2: lwz %1+1,4(%2)\n" \ + "1: lwz%X2 %1, %2\n" \ + "2: lwz%X2 %L1, %L2\n" \ "3:\n" \ ".section .fixup,\"ax\"\n" \ "4: li %0,%3\n" \ @@ -233,26 +237,33 @@ extern long __get_user_bad(void); EX_TABLE(1b, 4b) \ EX_TABLE(2b, 4b) \ : "=r" (err), "=&r" (x) \ - : "b" (addr), "i" (-EFAULT), "0" (err)) + : "m" (*addr), "i" (-EFAULT), "0" (err)) #endif /* __powerpc64__ */ -#define __get_user_size(x, ptr, size, retval) \ +#define __get_user_size_allowed(x, ptr, size, retval) \ do { \ retval = 0; \ - __chk_user_ptr(ptr); \ - if (size > sizeof(x)) \ - (x) = __get_user_bad(); \ - allow_read_from_user(ptr, size); \ + BUILD_BUG_ON(size > sizeof(x)); \ switch (size) { \ - case 1: __get_user_asm(x, ptr, retval, "lbz"); break; \ - case 2: __get_user_asm(x, ptr, retval, "lhz"); break; \ - case 4: __get_user_asm(x, ptr, retval, "lwz"); break; \ - case 8: __get_user_asm2(x, ptr, retval); break; \ - default: (x) = __get_user_bad(); \ + case 1: __get_user_asm(x, (u8 __user *)ptr, retval, "lbz"); break; \ + case 2: __get_user_asm(x, (u16 __user *)ptr, retval, "lhz"); break; \ + case 4: __get_user_asm(x, (u32 __user *)ptr, retval, "lwz"); break; \ + case 8: __get_user_asm2(x, (u64 __user *)ptr, retval); break; \ + default: x = 0; BUILD_BUG(); \ } \ - prevent_read_from_user(ptr, size); \ } while (0) +#define __get_user_size_goto(x, ptr, size, label) \ +do { \ + long __gus_retval; \ + \ + __get_user_size_allowed(x, ptr, size, __gus_retval); \ + if (__gus_retval) \ + goto label; \ +} while (0) + +#endif /* CONFIG_CC_HAS_ASM_GOTO_OUTPUT */ + /* * This is a type: either unsigned long, if the argument fits into * that type, or otherwise unsigned long long. @@ -260,47 +271,31 @@ do { \ #define __long_type(x) \ __typeof__(__builtin_choose_expr(sizeof(x) > sizeof(0UL), 0ULL, 0UL)) -#define __get_user_nocheck(x, ptr, size) \ +#define __get_user(x, ptr) \ ({ \ long __gu_err; \ __long_type(*(ptr)) __gu_val; \ __typeof__(*(ptr)) __user *__gu_addr = (ptr); \ - __chk_user_ptr(ptr); \ - if (!is_kernel_addr((unsigned long)__gu_addr)) \ - might_fault(); \ - barrier_nospec(); \ - __get_user_size(__gu_val, __gu_addr, (size), __gu_err); \ + __typeof__(sizeof(*(ptr))) __gu_size = sizeof(*(ptr)); \ + \ + might_fault(); \ + allow_read_from_user(__gu_addr, __gu_size); \ + __get_user_size_allowed(__gu_val, __gu_addr, __gu_size, __gu_err); \ + prevent_read_from_user(__gu_addr, __gu_size); \ (x) = (__typeof__(*(ptr)))__gu_val; \ + \ __gu_err; \ }) -#define __get_user_check(x, ptr, size) \ +#define get_user(x, ptr) \ ({ \ - long __gu_err = -EFAULT; \ - __long_type(*(ptr)) __gu_val = 0; \ - __typeof__(*(ptr)) __user *__gu_addr = (ptr); \ - might_fault(); \ - if (access_ok(__gu_addr, (size))) { \ - barrier_nospec(); \ - __get_user_size(__gu_val, __gu_addr, (size), __gu_err); \ - } \ - (x) = (__force __typeof__(*(ptr)))__gu_val; \ - __gu_err; \ + __typeof__(*(ptr)) __user *_gu_addr = (ptr); \ + \ + access_ok(_gu_addr, sizeof(*(ptr))) ? \ + __get_user(x, _gu_addr) : \ + ((x) = (__force __typeof__(*(ptr)))0, -EFAULT); \ }) -#define __get_user_nosleep(x, ptr, size) \ -({ \ - long __gu_err; \ - __long_type(*(ptr)) __gu_val; \ - __typeof__(*(ptr)) __user *__gu_addr = (ptr); \ - __chk_user_ptr(ptr); \ - barrier_nospec(); \ - __get_user_size(__gu_val, __gu_addr, (size), __gu_err); \ - (x) = (__force __typeof__(*(ptr)))__gu_val; \ - __gu_err; \ -}) - - /* more complex routines */ extern unsigned long __copy_tofrom_user(void __user *to, @@ -312,10 +307,9 @@ raw_copy_in_user(void __user *to, const void __user *from, unsigned long n) { unsigned long ret; - barrier_nospec(); - allow_user_access(to, from, n); + allow_read_write_user(to, from, n); ret = __copy_tofrom_user(to, from, n); - prevent_user_access(to, from, n); + prevent_read_write_user(to, from, n); return ret; } #endif /* __powerpc64__ */ @@ -324,62 +318,17 @@ static inline unsigned long raw_copy_from_user(void *to, const void __user *from, unsigned long n) { unsigned long ret; - if (__builtin_constant_p(n) && (n <= 8)) { - ret = 1; - - switch (n) { - case 1: - barrier_nospec(); - __get_user_size(*(u8 *)to, from, 1, ret); - break; - case 2: - barrier_nospec(); - __get_user_size(*(u16 *)to, from, 2, ret); - break; - case 4: - barrier_nospec(); - __get_user_size(*(u32 *)to, from, 4, ret); - break; - case 8: - barrier_nospec(); - __get_user_size(*(u64 *)to, from, 8, ret); - break; - } - if (ret == 0) - return 0; - } - barrier_nospec(); allow_read_from_user(from, n); ret = __copy_tofrom_user((__force void __user *)to, from, n); prevent_read_from_user(from, n); return ret; } -static inline unsigned long raw_copy_to_user(void __user *to, - const void *from, unsigned long n) +static inline unsigned long +raw_copy_to_user(void __user *to, const void *from, unsigned long n) { unsigned long ret; - if (__builtin_constant_p(n) && (n <= 8)) { - ret = 1; - - switch (n) { - case 1: - __put_user_size(*(u8 *)from, (u8 __user *)to, 1, ret); - break; - case 2: - __put_user_size(*(u16 *)from, (u16 __user *)to, 2, ret); - break; - case 4: - __put_user_size(*(u32 *)from, (u32 __user *)to, 4, ret); - break; - case 8: - __put_user_size(*(u64 *)from, (u64 __user *)to, 8, ret); - break; - } - if (ret == 0) - return 0; - } allow_write_to_user(to, n); ret = __copy_tofrom_user(to, (__force const void __user *)from, n); @@ -387,40 +336,158 @@ static inline unsigned long raw_copy_to_user(void __user *to, return ret; } -static __always_inline unsigned long __must_check -copy_to_user_mcsafe(void __user *to, const void *from, unsigned long n) +unsigned long __arch_clear_user(void __user *addr, unsigned long size); + +static inline unsigned long __clear_user(void __user *addr, unsigned long size) +{ + unsigned long ret; + + might_fault(); + allow_write_to_user(addr, size); + ret = __arch_clear_user(addr, size); + prevent_write_to_user(addr, size); + return ret; +} + +static inline unsigned long clear_user(void __user *addr, unsigned long size) +{ + return likely(access_ok(addr, size)) ? __clear_user(addr, size) : size; +} + +extern long strncpy_from_user(char *dst, const char __user *src, long count); +extern __must_check long strnlen_user(const char __user *str, long n); + +#ifdef CONFIG_ARCH_HAS_COPY_MC +unsigned long __must_check +copy_mc_generic(void *to, const void *from, unsigned long size); + +static inline unsigned long __must_check +copy_mc_to_kernel(void *to, const void *from, unsigned long size) +{ + return copy_mc_generic(to, from, size); +} +#define copy_mc_to_kernel copy_mc_to_kernel + +static inline unsigned long __must_check +copy_mc_to_user(void __user *to, const void *from, unsigned long n) { - if (likely(check_copy_size(from, n, true))) { + if (check_copy_size(from, n, true)) { if (access_ok(to, n)) { allow_write_to_user(to, n); - n = memcpy_mcsafe((void *)to, from, n); + n = copy_mc_generic((void __force *)to, from, n); prevent_write_to_user(to, n); } } return n; } +#endif -extern unsigned long __clear_user(void __user *addr, unsigned long size); +extern long __copy_from_user_flushcache(void *dst, const void __user *src, + unsigned size); -static inline unsigned long clear_user(void __user *addr, unsigned long size) +static __must_check __always_inline bool user_access_begin(const void __user *ptr, size_t len) { - unsigned long ret = size; + if (unlikely(!access_ok(ptr, len))) + return false; + might_fault(); - if (likely(access_ok(addr, size))) { - allow_write_to_user(addr, size); - ret = __clear_user(addr, size); - prevent_write_to_user(addr, size); - } - return ret; + + allow_read_write_user((void __user *)ptr, ptr, len); + return true; } +#define user_access_begin user_access_begin +#define user_access_end prevent_current_access_user +#define user_access_save prevent_user_access_return +#define user_access_restore restore_user_access -extern long strncpy_from_user(char *dst, const char __user *src, long count); -extern __must_check long strnlen_user(const char __user *str, long n); +static __must_check __always_inline bool +user_read_access_begin(const void __user *ptr, size_t len) +{ + if (unlikely(!access_ok(ptr, len))) + return false; -extern long __copy_from_user_flushcache(void *dst, const void __user *src, - unsigned size); -extern void memcpy_page_flushcache(char *to, struct page *page, size_t offset, - size_t len); + might_fault(); + + allow_read_from_user(ptr, len); + return true; +} +#define user_read_access_begin user_read_access_begin +#define user_read_access_end prevent_current_read_from_user + +static __must_check __always_inline bool +user_write_access_begin(const void __user *ptr, size_t len) +{ + if (unlikely(!access_ok(ptr, len))) + return false; + + might_fault(); + + allow_write_to_user((void __user *)ptr, len); + return true; +} +#define user_write_access_begin user_write_access_begin +#define user_write_access_end prevent_current_write_to_user + +#define unsafe_get_user(x, p, e) do { \ + __long_type(*(p)) __gu_val; \ + __typeof__(*(p)) __user *__gu_addr = (p); \ + \ + __get_user_size_goto(__gu_val, __gu_addr, sizeof(*(p)), e); \ + (x) = (__typeof__(*(p)))__gu_val; \ +} while (0) + +#define unsafe_put_user(x, p, e) \ + __put_user_size_goto((__typeof__(*(p)))(x), (p), sizeof(*(p)), e) + +#define unsafe_copy_from_user(d, s, l, e) \ +do { \ + u8 *_dst = (u8 *)(d); \ + const u8 __user *_src = (const u8 __user *)(s); \ + size_t _len = (l); \ + int _i; \ + \ + for (_i = 0; _i < (_len & ~(sizeof(u64) - 1)); _i += sizeof(u64)) \ + unsafe_get_user(*(u64 *)(_dst + _i), (u64 __user *)(_src + _i), e); \ + if (_len & 4) { \ + unsafe_get_user(*(u32 *)(_dst + _i), (u32 __user *)(_src + _i), e); \ + _i += 4; \ + } \ + if (_len & 2) { \ + unsafe_get_user(*(u16 *)(_dst + _i), (u16 __user *)(_src + _i), e); \ + _i += 2; \ + } \ + if (_len & 1) \ + unsafe_get_user(*(u8 *)(_dst + _i), (u8 __user *)(_src + _i), e); \ +} while (0) + +#define unsafe_copy_to_user(d, s, l, e) \ +do { \ + u8 __user *_dst = (u8 __user *)(d); \ + const u8 *_src = (const u8 *)(s); \ + size_t _len = (l); \ + int _i; \ + \ + for (_i = 0; _i < (_len & ~(sizeof(u64) - 1)); _i += sizeof(u64)) \ + unsafe_put_user(*(u64 *)(_src + _i), (u64 __user *)(_dst + _i), e); \ + if (_len & 4) { \ + unsafe_put_user(*(u32*)(_src + _i), (u32 __user *)(_dst + _i), e); \ + _i += 4; \ + } \ + if (_len & 2) { \ + unsafe_put_user(*(u16*)(_src + _i), (u16 __user *)(_dst + _i), e); \ + _i += 2; \ + } \ + if (_len & 1) \ + unsafe_put_user(*(u8*)(_src + _i), (u8 __user *)(_dst + _i), e); \ +} while (0) + +#define __get_kernel_nofault(dst, src, type, err_label) \ + __get_user_size_goto(*((type *)(dst)), \ + (__force type __user *)(src), sizeof(type), err_label) + +#define __put_kernel_nofault(dst, src, type, err_label) \ + __put_user_size_goto(*((type *)(src)), \ + (__force type __user *)(dst), sizeof(type), err_label) #endif /* _ARCH_POWERPC_UACCESS_H */ diff --git a/arch/powerpc/include/asm/udbg.h b/arch/powerpc/include/asm/udbg.h index 0ea9e70ed78b..b1f094728b35 100644 --- a/arch/powerpc/include/asm/udbg.h +++ b/arch/powerpc/include/asm/udbg.h @@ -15,44 +15,44 @@ extern void (*udbg_flush)(void); extern int (*udbg_getc)(void); extern int (*udbg_getc_poll)(void); -extern void udbg_puts(const char *s); -extern int udbg_write(const char *s, int n); +void udbg_puts(const char *s); +int udbg_write(const char *s, int n); -extern void register_early_udbg_console(void); -extern void udbg_printf(const char *fmt, ...) +void register_early_udbg_console(void); +void udbg_printf(const char *fmt, ...) __attribute__ ((format (printf, 1, 2))); -extern void udbg_progress(char *s, unsigned short hex); +void udbg_progress(char *s, unsigned short hex); -extern void udbg_uart_init_mmio(void __iomem *addr, unsigned int stride); -extern void udbg_uart_init_pio(unsigned long port, unsigned int stride); +void __init udbg_uart_init_mmio(void __iomem *addr, unsigned int stride); +void __init udbg_uart_init_pio(unsigned long port, unsigned int stride); -extern void udbg_uart_setup(unsigned int speed, unsigned int clock); -extern unsigned int udbg_probe_uart_speed(unsigned int clock); +void __init udbg_uart_setup(unsigned int speed, unsigned int clock); +unsigned int __init udbg_probe_uart_speed(unsigned int clock); struct device_node; -extern void udbg_scc_init(int force_scc); -extern int udbg_adb_init(int force_btext); -extern void udbg_adb_init_early(void); - -extern void __init udbg_early_init(void); -extern void __init udbg_init_debug_lpar(void); -extern void __init udbg_init_debug_lpar_hvsi(void); -extern void __init udbg_init_pmac_realmode(void); -extern void __init udbg_init_maple_realmode(void); -extern void __init udbg_init_pas_realmode(void); -extern void __init udbg_init_rtas_panel(void); -extern void __init udbg_init_rtas_console(void); -extern void __init udbg_init_debug_beat(void); -extern void __init udbg_init_btext(void); -extern void __init udbg_init_44x_as1(void); -extern void __init udbg_init_40x_realmode(void); -extern void __init udbg_init_cpm(void); -extern void __init udbg_init_usbgecko(void); -extern void __init udbg_init_memcons(void); -extern void __init udbg_init_ehv_bc(void); -extern void __init udbg_init_ps3gelic(void); -extern void __init udbg_init_debug_opal_raw(void); -extern void __init udbg_init_debug_opal_hvsi(void); +void __init udbg_scc_init(int force_scc); +int udbg_adb_init(int force_btext); +void udbg_adb_init_early(void); + +void __init udbg_early_init(void); +void __init udbg_init_debug_lpar(void); +void __init udbg_init_debug_lpar_hvsi(void); +void __init udbg_init_pmac_realmode(void); +void __init udbg_init_maple_realmode(void); +void __init udbg_init_pas_realmode(void); +void __init udbg_init_rtas_panel(void); +void __init udbg_init_rtas_console(void); +void __init udbg_init_btext(void); +void __init udbg_init_44x_as1(void); +void __init udbg_init_40x_realmode(void); +void __init udbg_init_cpm(void); +void __init udbg_init_usbgecko(void); +void __init udbg_init_memcons(void); +void __init udbg_init_ehv_bc(void); +void __init udbg_init_ps3gelic(void); +void __init udbg_init_debug_opal_raw(void); +void __init udbg_init_debug_opal_hvsi(void); +void __init udbg_init_debug_16550(void); #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_UDBG_H */ diff --git a/arch/powerpc/include/asm/unaligned.h b/arch/powerpc/include/asm/unaligned.h deleted file mode 100644 index ce69c5eff95e..000000000000 --- a/arch/powerpc/include/asm/unaligned.h +++ /dev/null @@ -1,22 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ASM_POWERPC_UNALIGNED_H -#define _ASM_POWERPC_UNALIGNED_H - -#ifdef __KERNEL__ - -/* - * The PowerPC can do unaligned accesses itself based on its endian mode. - */ -#include <linux/unaligned/access_ok.h> -#include <linux/unaligned/generic.h> - -#ifdef __LITTLE_ENDIAN__ -#define get_unaligned __get_unaligned_le -#define put_unaligned __put_unaligned_le -#else -#define get_unaligned __get_unaligned_be -#define put_unaligned __put_unaligned_be -#endif - -#endif /* __KERNEL__ */ -#endif /* _ASM_POWERPC_UNALIGNED_H */ diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h index b0720c7c3fcf..659a996c75aa 100644 --- a/arch/powerpc/include/asm/unistd.h +++ b/arch/powerpc/include/asm/unistd.h @@ -9,8 +9,6 @@ #define NR_syscalls __NR_syscalls -#define __NR__exit __NR_exit - #ifndef __ASSEMBLY__ #include <linux/types.h> @@ -31,6 +29,7 @@ #define __ARCH_WANT_SYS_SOCKETCALL #define __ARCH_WANT_SYS_FADVISE64 #define __ARCH_WANT_SYS_GETPGRP +#define __ARCH_WANT_SYS_LLSEEK #define __ARCH_WANT_SYS_NICE #define __ARCH_WANT_SYS_OLD_GETRLIMIT #define __ARCH_WANT_SYS_OLD_UNAME @@ -39,11 +38,14 @@ #define __ARCH_WANT_SYS_SIGPROCMASK #ifdef CONFIG_PPC32 #define __ARCH_WANT_OLD_STAT +#define __ARCH_WANT_SYS_OLD_SELECT #endif #ifdef CONFIG_PPC64 #define __ARCH_WANT_SYS_TIME #define __ARCH_WANT_SYS_UTIME #define __ARCH_WANT_SYS_NEWFSTATAT +#define __ARCH_WANT_COMPAT_STAT +#define __ARCH_WANT_COMPAT_FALLOCATE #define __ARCH_WANT_COMPAT_SYS_SENDFILE #endif #define __ARCH_WANT_SYS_FORK diff --git a/arch/powerpc/include/asm/uprobes.h b/arch/powerpc/include/asm/uprobes.h index 2bbdf27d09b5..4fea116d3d37 100644 --- a/arch/powerpc/include/asm/uprobes.h +++ b/arch/powerpc/include/asm/uprobes.h @@ -12,9 +12,9 @@ #include <linux/notifier.h> #include <asm/probes.h> -typedef ppc_opcode_t uprobe_opcode_t; +typedef u32 uprobe_opcode_t; -#define MAX_UINSN_BYTES 4 +#define MAX_UINSN_BYTES 8 #define UPROBE_XOL_SLOT_BYTES (MAX_UINSN_BYTES) /* The following alias is needed for reference from arch-agnostic code */ @@ -23,8 +23,8 @@ typedef ppc_opcode_t uprobe_opcode_t; struct arch_uprobe { union { - u32 insn; - u32 ixol; + u32 insn[2]; + u32 ixol[2]; }; }; diff --git a/arch/powerpc/include/asm/user.h b/arch/powerpc/include/asm/user.h index 99443b8594e7..7fae7e597ba4 100644 --- a/arch/powerpc/include/asm/user.h +++ b/arch/powerpc/include/asm/user.h @@ -44,9 +44,4 @@ struct user { char u_comm[32]; /* user command name */ }; -#define NBPG PAGE_SIZE -#define UPAGES 1 -#define HOST_TEXT_START_ADDR (u.start_code) -#define HOST_DATA_START_ADDR (u.start_data) -#define HOST_STACK_END_ADDR (u.start_stack + u.u_ssize * NBPG) #endif /* _ASM_POWERPC_USER_H */ diff --git a/arch/powerpc/include/asm/vas.h b/arch/powerpc/include/asm/vas.h index f93e6b0f5c84..c36f71e01c0f 100644 --- a/arch/powerpc/include/asm/vas.h +++ b/arch/powerpc/include/asm/vas.h @@ -5,8 +5,10 @@ #ifndef _ASM_POWERPC_VAS_H #define _ASM_POWERPC_VAS_H - -struct vas_window; +#include <linux/sched/mm.h> +#include <linux/mmu_context.h> +#include <asm/icswx.h> +#include <uapi/asm/vas-api.h> /* * Min and max FIFO sizes are based on Version 1.05 Section 3.1.4.25 @@ -28,6 +30,16 @@ struct vas_window; #define VAS_THRESH_FIFO_GT_EIGHTH_FULL 3 /* + * VAS window Linux status bits + */ +#define VAS_WIN_ACTIVE 0x0 /* Used in platform independent */ + /* vas mmap() */ +/* Window is closed in the hypervisor due to lost credit */ +#define VAS_WIN_NO_CRED_CLOSE 0x00000001 +/* Window is closed due to migration */ +#define VAS_WIN_MIGRATE_CLOSE 0x00000002 + +/* * Get/Set bit fields */ #define GET_FIELD(m, v) (((v) & (m)) >> MASK_LSH(m)) @@ -49,10 +61,72 @@ enum vas_cop_type { }; /* + * User space VAS windows are opened by tasks and take references + * to pid and mm until windows are closed. + * Stores pid, mm, and tgid for each window. + */ +struct vas_user_win_ref { + struct pid *pid; /* PID of owner */ + struct pid *tgid; /* Thread group ID of owner */ + struct mm_struct *mm; /* Linux process mm_struct */ + struct mutex mmap_mutex; /* protects paste address mmap() */ + /* with DLPAR close/open windows */ + struct vm_area_struct *vma; /* Save VMA and used in DLPAR ops */ +}; + +/* + * Common VAS window struct on PowerNV and PowerVM + */ +struct vas_window { + u32 winid; + u32 wcreds_max; /* Window credits */ + u32 status; /* Window status used in OS */ + enum vas_cop_type cop; + struct vas_user_win_ref task_ref; + char *dbgname; + struct dentry *dbgdir; +}; + +/* + * User space window operations used for powernv and powerVM + */ +struct vas_user_win_ops { + struct vas_window * (*open_win)(int vas_id, u64 flags, + enum vas_cop_type); + u64 (*paste_addr)(struct vas_window *); + int (*close_win)(struct vas_window *); +}; + +static inline void put_vas_user_win_ref(struct vas_user_win_ref *ref) +{ + /* Drop references to pid, tgid, and mm */ + put_pid(ref->pid); + put_pid(ref->tgid); + if (ref->mm) + mmdrop(ref->mm); +} + +static inline void vas_user_win_add_mm_context(struct vas_user_win_ref *ref) +{ + mm_context_add_vas_window(ref->mm); + /* + * Even a process that has no foreign real address mapping can + * use an unpaired COPY instruction (to no real effect). Issue + * CP_ABORT to clear any pending COPY and prevent a covert + * channel. + * + * __switch_to() will issue CP_ABORT on future context switches + * if process / thread has any open VAS window (Use + * current->mm->context.vas_windows). + */ + asm volatile(PPC_CP_ABORT); +} + +/* * Receive window attributes specified by the (in-kernel) owner of window. */ struct vas_rx_win_attr { - void *rx_fifo; + u64 rx_fifo; int rx_fifo_size; int wcreds_max; @@ -86,7 +160,6 @@ struct vas_tx_win_attr { int wcreds_max; int lpid; int pidr; /* hardware PID (from SPRN_PID) */ - int pid; /* linux process id */ int pswid; int rsvd_txbuf_count; int tc_mode; @@ -101,6 +174,7 @@ struct vas_tx_win_attr { bool rx_win_ord_mode; }; +#ifdef CONFIG_PPC_POWERNV /* * Helper to map a chip id to VAS id. * For POWER9, this is a 1:1 mapping. In the future this maybe a 1:N @@ -163,4 +237,58 @@ int vas_copy_crb(void *crb, int offset); */ int vas_paste_crb(struct vas_window *win, int offset, bool re); +int vas_register_api_powernv(struct module *mod, enum vas_cop_type cop_type, + const char *name); +void vas_unregister_api_powernv(void); +#endif + +#ifdef CONFIG_PPC_PSERIES + +/* VAS Capabilities */ +#define VAS_GZIP_QOS_FEAT 0x1 +#define VAS_GZIP_DEF_FEAT 0x2 +#define VAS_GZIP_QOS_FEAT_BIT PPC_BIT(VAS_GZIP_QOS_FEAT) /* Bit 1 */ +#define VAS_GZIP_DEF_FEAT_BIT PPC_BIT(VAS_GZIP_DEF_FEAT) /* Bit 2 */ + +/* NX Capabilities */ +#define VAS_NX_GZIP_FEAT 0x1 +#define VAS_NX_GZIP_FEAT_BIT PPC_BIT(VAS_NX_GZIP_FEAT) /* Bit 1 */ + +/* + * These structs are used to retrieve overall VAS capabilities that + * the hypervisor provides. + */ +struct hv_vas_all_caps { + __be64 descriptor; + __be64 feat_type; +} __packed __aligned(0x1000); + +struct vas_all_caps { + u64 descriptor; + u64 feat_type; +}; + +int h_query_vas_capabilities(const u64 hcall, u8 query_type, u64 result); +int vas_register_api_pseries(struct module *mod, + enum vas_cop_type cop_type, const char *name); +void vas_unregister_api_pseries(void); +#endif + +/* + * Register / unregister coprocessor type to VAS API which will be exported + * to user space. Applications can use this API to open / close window + * which can be used to send / receive requests directly to cooprcessor. + * + * Only NX GZIP coprocessor type is supported now, but this API can be + * used for others in future. + */ +int vas_register_coproc_api(struct module *mod, enum vas_cop_type cop_type, + const char *name, + const struct vas_user_win_ops *vops); +void vas_unregister_coproc_api(void); + +int get_vas_user_win_ref(struct vas_user_win_ref *task_ref); +void vas_update_csb(struct coprocessor_request_block *crb, + struct vas_user_win_ref *task_ref); +void vas_dump_crb(struct coprocessor_request_block *crb); #endif /* __ASM_POWERPC_VAS_H */ diff --git a/arch/powerpc/include/asm/vdso.h b/arch/powerpc/include/asm/vdso.h index b5e1f8f8a05c..7650b6ce14c8 100644 --- a/arch/powerpc/include/asm/vdso.h +++ b/arch/powerpc/include/asm/vdso.h @@ -1,52 +1,28 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __PPC64_VDSO_H__ -#define __PPC64_VDSO_H__ +#ifndef _ASM_POWERPC_VDSO_H +#define _ASM_POWERPC_VDSO_H -#ifdef __KERNEL__ - -/* Default link addresses for the vDSOs */ -#define VDSO32_LBASE 0x0 -#define VDSO64_LBASE 0x0 +#define VDSO_VERSION_STRING LINUX_2.6.15 -/* Default map addresses for 32bit vDSO */ -#define VDSO32_MBASE 0x100000 +#ifndef __ASSEMBLY__ -#define VDSO_VERSION_STRING LINUX_2.6.15 +#ifdef CONFIG_PPC64 +#include <generated/vdso64-offsets.h> +#endif -/* Define if 64 bits VDSO has procedure descriptors */ -#undef VDS64_HAS_DESCRIPTORS +#ifdef CONFIG_VDSO32 +#include <generated/vdso32-offsets.h> +#endif -#ifndef __ASSEMBLY__ +#define VDSO64_SYMBOL(base, name) ((unsigned long)(base) + (vdso64_offset_##name)) -/* Offsets relative to thread->vdso_base */ -extern unsigned long vdso64_rt_sigtramp; -extern unsigned long vdso32_sigtramp; -extern unsigned long vdso32_rt_sigtramp; +#define VDSO32_SYMBOL(base, name) ((unsigned long)(base) + (vdso32_offset_##name)) int vdso_getcpu_init(void); #else /* __ASSEMBLY__ */ #ifdef __VDSO64__ -#ifdef VDS64_HAS_DESCRIPTORS -#define V_FUNCTION_BEGIN(name) \ - .globl name; \ - .section ".opd","a"; \ - .align 3; \ - name: \ - .quad .name,.TOC.@tocbase,0; \ - .previous; \ - .globl .name; \ - .type .name,@function; \ - .name: \ - -#define V_FUNCTION_END(name) \ - .size .name,.-.name; - -#define V_LOCAL_FUNC(name) (.name) - -#else /* VDS64_HAS_DESCRIPTORS */ - #define V_FUNCTION_BEGIN(name) \ .globl name; \ name: \ @@ -55,8 +31,6 @@ int vdso_getcpu_init(void); .size name,.-name; #define V_LOCAL_FUNC(name) (name) - -#endif /* VDS64_HAS_DESCRIPTORS */ #endif /* __VDSO64__ */ #ifdef __VDSO32__ @@ -75,6 +49,4 @@ int vdso_getcpu_init(void); #endif /* __ASSEMBLY__ */ -#endif /* __KERNEL__ */ - -#endif /* __PPC64_VDSO_H__ */ +#endif /* _ASM_POWERPC_VDSO_H */ diff --git a/arch/powerpc/include/asm/vdso/clocksource.h b/arch/powerpc/include/asm/vdso/clocksource.h new file mode 100644 index 000000000000..c1ba56b82ee5 --- /dev/null +++ b/arch/powerpc/include/asm/vdso/clocksource.h @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_POWERPC_VDSO_CLOCKSOURCE_H +#define _ASM_POWERPC_VDSO_CLOCKSOURCE_H + +#define VDSO_ARCH_CLOCKMODES VDSO_CLOCKMODE_ARCHTIMER + +#endif diff --git a/arch/powerpc/include/asm/vdso/gettimeofday.h b/arch/powerpc/include/asm/vdso/gettimeofday.h new file mode 100644 index 000000000000..f0a4cf01e85c --- /dev/null +++ b/arch/powerpc/include/asm/vdso/gettimeofday.h @@ -0,0 +1,160 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_POWERPC_VDSO_GETTIMEOFDAY_H +#define _ASM_POWERPC_VDSO_GETTIMEOFDAY_H + +#ifndef __ASSEMBLY__ + +#include <asm/page.h> +#include <asm/vdso/timebase.h> +#include <asm/barrier.h> +#include <asm/unistd.h> +#include <uapi/linux/time.h> + +#define VDSO_HAS_CLOCK_GETRES 1 + +#define VDSO_HAS_TIME 1 + +static __always_inline int do_syscall_2(const unsigned long _r0, const unsigned long _r3, + const unsigned long _r4) +{ + register long r0 asm("r0") = _r0; + register unsigned long r3 asm("r3") = _r3; + register unsigned long r4 asm("r4") = _r4; + register int ret asm ("r3"); + + asm volatile( + " sc\n" + " bns+ 1f\n" + " neg %0, %0\n" + "1:\n" + : "=r" (ret), "+r" (r4), "+r" (r0) + : "r" (r3) + : "memory", "r5", "r6", "r7", "r8", "r9", "r10", "r11", "r12", "cr0", "ctr"); + + return ret; +} + +static __always_inline +int gettimeofday_fallback(struct __kernel_old_timeval *_tv, struct timezone *_tz) +{ + return do_syscall_2(__NR_gettimeofday, (unsigned long)_tv, (unsigned long)_tz); +} + +#ifdef __powerpc64__ + +static __always_inline +int clock_gettime_fallback(clockid_t _clkid, struct __kernel_timespec *_ts) +{ + return do_syscall_2(__NR_clock_gettime, _clkid, (unsigned long)_ts); +} + +static __always_inline +int clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts) +{ + return do_syscall_2(__NR_clock_getres, _clkid, (unsigned long)_ts); +} + +#else + +#define BUILD_VDSO32 1 + +static __always_inline +int clock_gettime_fallback(clockid_t _clkid, struct __kernel_timespec *_ts) +{ + return do_syscall_2(__NR_clock_gettime64, _clkid, (unsigned long)_ts); +} + +static __always_inline +int clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts) +{ + return do_syscall_2(__NR_clock_getres_time64, _clkid, (unsigned long)_ts); +} + +static __always_inline +int clock_gettime32_fallback(clockid_t _clkid, struct old_timespec32 *_ts) +{ + return do_syscall_2(__NR_clock_gettime, _clkid, (unsigned long)_ts); +} + +static __always_inline +int clock_getres32_fallback(clockid_t _clkid, struct old_timespec32 *_ts) +{ + return do_syscall_2(__NR_clock_getres, _clkid, (unsigned long)_ts); +} +#endif + +static __always_inline u64 __arch_get_hw_counter(s32 clock_mode, + const struct vdso_data *vd) +{ + return get_tb(); +} + +const struct vdso_data *__arch_get_vdso_data(void); + +#ifdef CONFIG_TIME_NS +static __always_inline +const struct vdso_data *__arch_get_timens_vdso_data(const struct vdso_data *vd) +{ + return (void *)vd + PAGE_SIZE; +} +#endif + +static inline bool vdso_clocksource_ok(const struct vdso_data *vd) +{ + return true; +} +#define vdso_clocksource_ok vdso_clocksource_ok + +/* + * powerpc specific delta calculation. + * + * This variant removes the masking of the subtraction because the + * clocksource mask of all VDSO capable clocksources on powerpc is U64_MAX + * which would result in a pointless operation. The compiler cannot + * optimize it away as the mask comes from the vdso data and is not compile + * time constant. + */ +static __always_inline u64 vdso_calc_delta(u64 cycles, u64 last, u64 mask, u32 mult) +{ + return (cycles - last) * mult; +} +#define vdso_calc_delta vdso_calc_delta + +#ifndef __powerpc64__ +static __always_inline u64 vdso_shift_ns(u64 ns, unsigned long shift) +{ + u32 hi = ns >> 32; + u32 lo = ns; + + lo >>= shift; + lo |= hi << (32 - shift); + hi >>= shift; + + if (likely(hi == 0)) + return lo; + + return ((u64)hi << 32) | lo; +} +#define vdso_shift_ns vdso_shift_ns +#endif + +#ifdef __powerpc64__ +int __c_kernel_clock_gettime(clockid_t clock, struct __kernel_timespec *ts, + const struct vdso_data *vd); +int __c_kernel_clock_getres(clockid_t clock_id, struct __kernel_timespec *res, + const struct vdso_data *vd); +#else +int __c_kernel_clock_gettime(clockid_t clock, struct old_timespec32 *ts, + const struct vdso_data *vd); +int __c_kernel_clock_gettime64(clockid_t clock, struct __kernel_timespec *ts, + const struct vdso_data *vd); +int __c_kernel_clock_getres(clockid_t clock_id, struct old_timespec32 *res, + const struct vdso_data *vd); +#endif +int __c_kernel_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz, + const struct vdso_data *vd); +__kernel_old_time_t __c_kernel_time(__kernel_old_time_t *time, + const struct vdso_data *vd); +#endif /* __ASSEMBLY__ */ + +#endif /* _ASM_POWERPC_VDSO_GETTIMEOFDAY_H */ diff --git a/arch/powerpc/include/asm/vdso/processor.h b/arch/powerpc/include/asm/vdso/processor.h new file mode 100644 index 000000000000..80d13207c568 --- /dev/null +++ b/arch/powerpc/include/asm/vdso/processor.h @@ -0,0 +1,38 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef _ASM_POWERPC_VDSO_PROCESSOR_H +#define _ASM_POWERPC_VDSO_PROCESSOR_H + +#ifndef __ASSEMBLY__ + +/* Macros for adjusting thread priority (hardware multi-threading) */ +#ifdef CONFIG_PPC64 +#define HMT_very_low() asm volatile("or 31, 31, 31 # very low priority") +#define HMT_low() asm volatile("or 1, 1, 1 # low priority") +#define HMT_medium_low() asm volatile("or 6, 6, 6 # medium low priority") +#define HMT_medium() asm volatile("or 2, 2, 2 # medium priority") +#define HMT_medium_high() asm volatile("or 5, 5, 5 # medium high priority") +#define HMT_high() asm volatile("or 3, 3, 3 # high priority") +#else +#define HMT_very_low() +#define HMT_low() +#define HMT_medium_low() +#define HMT_medium() +#define HMT_medium_high() +#define HMT_high() +#endif + +#ifdef CONFIG_PPC64 +#define cpu_relax() \ + asm volatile(ASM_FTR_IFCLR( \ + /* Pre-POWER10 uses low ; medium priority nops */ \ + "or 1,1,1 ; or 2,2,2", \ + /* POWER10 onward uses pause_short (wait 2,0) */ \ + PPC_WAIT(2, 0), \ + %0) :: "i" (CPU_FTR_ARCH_31) : "memory") +#else +#define cpu_relax() barrier() +#endif + +#endif /* __ASSEMBLY__ */ + +#endif /* _ASM_POWERPC_VDSO_PROCESSOR_H */ diff --git a/arch/powerpc/include/asm/vdso/timebase.h b/arch/powerpc/include/asm/vdso/timebase.h new file mode 100644 index 000000000000..e9245f86a46c --- /dev/null +++ b/arch/powerpc/include/asm/vdso/timebase.h @@ -0,0 +1,73 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Common timebase prototypes and such for all ppc machines. + */ + +#ifndef _ASM_POWERPC_VDSO_TIMEBASE_H +#define _ASM_POWERPC_VDSO_TIMEBASE_H + +#include <asm/reg.h> + +/* + * We use __powerpc64__ here because we want the compat VDSO to use the 32-bit + * version below in the else case of the ifdef. + */ +#if defined(__powerpc64__) && (defined(CONFIG_PPC_CELL) || defined(CONFIG_PPC_E500)) +#define mftb() ({unsigned long rval; \ + asm volatile( \ + "90: mfspr %0, %2;\n" \ + ASM_FTR_IFSET( \ + "97: cmpwi %0,0;\n" \ + " beq- 90b;\n", "", %1) \ + : "=r" (rval) \ + : "i" (CPU_FTR_CELL_TB_BUG), "i" (SPRN_TBRL) : "cr0"); \ + rval;}) +#elif defined(CONFIG_PPC_8xx) +#define mftb() ({unsigned long rval; \ + asm volatile("mftbl %0" : "=r" (rval)); rval;}) +#else +#define mftb() ({unsigned long rval; \ + asm volatile("mfspr %0, %1" : \ + "=r" (rval) : "i" (SPRN_TBRL)); rval;}) +#endif /* !CONFIG_PPC_CELL */ + +#if defined(CONFIG_PPC_8xx) +#define mftbu() ({unsigned long rval; \ + asm volatile("mftbu %0" : "=r" (rval)); rval;}) +#else +#define mftbu() ({unsigned long rval; \ + asm volatile("mfspr %0, %1" : "=r" (rval) : \ + "i" (SPRN_TBRU)); rval;}) +#endif + +#define mttbl(v) asm volatile("mttbl %0":: "r"(v)) +#define mttbu(v) asm volatile("mttbu %0":: "r"(v)) + +static __always_inline u64 get_tb(void) +{ + unsigned int tbhi, tblo, tbhi2; + + /* + * We use __powerpc64__ here not CONFIG_PPC64 because we want the compat + * VDSO to use the 32-bit compatible version in the while loop below. + */ + if (__is_defined(__powerpc64__)) + return mftb(); + + do { + tbhi = mftbu(); + tblo = mftb(); + tbhi2 = mftbu(); + } while (tbhi != tbhi2); + + return ((u64)tbhi << 32) | tblo; +} + +static inline void set_tb(unsigned int upper, unsigned int lower) +{ + mtspr(SPRN_TBWL, 0); + mtspr(SPRN_TBWU, upper); + mtspr(SPRN_TBWL, lower); +} + +#endif /* _ASM_POWERPC_VDSO_TIMEBASE_H */ diff --git a/arch/powerpc/include/asm/vdso/vsyscall.h b/arch/powerpc/include/asm/vdso/vsyscall.h new file mode 100644 index 000000000000..48cf23f1e273 --- /dev/null +++ b/arch/powerpc/include/asm/vdso/vsyscall.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_POWERPC_VDSO_VSYSCALL_H +#define _ASM_POWERPC_VDSO_VSYSCALL_H + +#ifndef __ASSEMBLY__ + +#include <linux/timekeeper_internal.h> +#include <asm/vdso_datapage.h> + +/* + * Update the vDSO data page to keep in sync with kernel timekeeping. + */ +static __always_inline +struct vdso_data *__arch_get_k_vdso_data(void) +{ + return vdso_data->data; +} +#define __arch_get_k_vdso_data __arch_get_k_vdso_data + +/* The asm-generic header needs to be included after the definitions above */ +#include <asm-generic/vdso/vsyscall.h> + +#endif /* !__ASSEMBLY__ */ + +#endif /* _ASM_POWERPC_VDSO_VSYSCALL_H */ diff --git a/arch/powerpc/include/asm/vdso_datapage.h b/arch/powerpc/include/asm/vdso_datapage.h index 40f13f3626d3..a585c8e538ff 100644 --- a/arch/powerpc/include/asm/vdso_datapage.h +++ b/arch/powerpc/include/asm/vdso_datapage.h @@ -36,6 +36,7 @@ #include <linux/unistd.h> #include <linux/time.h> +#include <vdso/datapage.h> #define SYSCALL_MAP_SIZE ((NR_syscalls + 31) / 32) @@ -45,7 +46,7 @@ #ifdef CONFIG_PPC64 -struct vdso_data { +struct vdso_arch_data { __u8 eye_catcher[16]; /* Eyecatcher: SYSTEMCFG:PPC64 0x00 */ struct { /* Systemcfg version numbers */ __u32 major; /* Major number 0x10 */ @@ -59,13 +60,13 @@ struct vdso_data { __u32 processor; /* Processor type 0x1C */ __u64 processorCount; /* # of physical processors 0x20 */ __u64 physicalMemorySize; /* Size of real memory(B) 0x28 */ - __u64 tb_orig_stamp; /* Timebase at boot 0x30 */ + __u64 tb_orig_stamp; /* (NU) Timebase at boot 0x30 */ __u64 tb_ticks_per_sec; /* Timebase tics / sec 0x38 */ - __u64 tb_to_xs; /* Inverse of TB to 2^20 0x40 */ - __u64 stamp_xsec; /* 0x48 */ - __u64 tb_update_count; /* Timebase atomicity ctr 0x50 */ - __u32 tz_minuteswest; /* Minutes west of Greenwich 0x58 */ - __u32 tz_dsttime; /* Type of dst correction 0x5C */ + __u64 tb_to_xs; /* (NU) Inverse of TB to 2^20 0x40 */ + __u64 stamp_xsec; /* (NU) 0x48 */ + __u64 tb_update_count; /* (NU) Timebase atomicity ctr 0x50 */ + __u32 tz_minuteswest; /* (NU) Min. west of Greenwich 0x58 */ + __u32 tz_dsttime; /* (NU) Type of dst correction 0x5C */ __u32 dcache_size; /* L1 d-cache size 0x60 */ __u32 dcache_line_size; /* L1 d-cache line size 0x64 */ __u32 icache_size; /* L1 i-cache size 0x68 */ @@ -78,14 +79,10 @@ struct vdso_data { __u32 icache_block_size; /* L1 i-cache block size */ __u32 dcache_log_block_size; /* L1 d-cache log block size */ __u32 icache_log_block_size; /* L1 i-cache log block size */ - __u32 stamp_sec_fraction; /* fractional seconds of stamp_xtime */ - __s32 wtom_clock_nsec; /* Wall to monotonic clock nsec */ - __s64 wtom_clock_sec; /* Wall to monotonic clock sec */ - __s64 stamp_xtime_sec; /* xtime secs as at tb_orig_stamp */ - __s64 stamp_xtime_nsec; /* xtime nsecs as at tb_orig_stamp */ - __u32 hrtimer_res; /* hrtimer resolution */ - __u32 syscall_map_64[SYSCALL_MAP_SIZE]; /* map of syscalls */ - __u32 syscall_map_32[SYSCALL_MAP_SIZE]; /* map of syscalls */ + __u32 syscall_map[SYSCALL_MAP_SIZE]; /* Map of syscalls */ + __u32 compat_syscall_map[SYSCALL_MAP_SIZE]; /* Map of compat syscalls */ + + struct vdso_data data[CS_BASES]; }; #else /* CONFIG_PPC64 */ @@ -93,30 +90,26 @@ struct vdso_data { /* * And here is the simpler 32 bits version */ -struct vdso_data { - __u64 tb_orig_stamp; /* Timebase at boot 0x30 */ +struct vdso_arch_data { __u64 tb_ticks_per_sec; /* Timebase tics / sec 0x38 */ - __u64 tb_to_xs; /* Inverse of TB to 2^20 0x40 */ - __u64 stamp_xsec; /* 0x48 */ - __u32 tb_update_count; /* Timebase atomicity ctr 0x50 */ - __u32 tz_minuteswest; /* Minutes west of Greenwich 0x58 */ - __u32 tz_dsttime; /* Type of dst correction 0x5C */ - __s32 wtom_clock_sec; /* Wall to monotonic clock */ - __s32 wtom_clock_nsec; - __s32 stamp_xtime_sec; /* xtime seconds as at tb_orig_stamp */ - __s32 stamp_xtime_nsec; /* xtime nsecs as at tb_orig_stamp */ - __u32 stamp_sec_fraction; /* fractional seconds of stamp_xtime */ - __u32 hrtimer_res; /* hrtimer resolution */ - __u32 syscall_map_32[SYSCALL_MAP_SIZE]; /* map of syscalls */ - __u32 dcache_block_size; /* L1 d-cache block size */ - __u32 icache_block_size; /* L1 i-cache block size */ - __u32 dcache_log_block_size; /* L1 d-cache log block size */ - __u32 icache_log_block_size; /* L1 i-cache log block size */ + __u32 syscall_map[SYSCALL_MAP_SIZE]; /* Map of syscalls */ + __u32 compat_syscall_map[0]; /* No compat syscalls on PPC32 */ + struct vdso_data data[CS_BASES]; }; #endif /* CONFIG_PPC64 */ -extern struct vdso_data *vdso_data; +extern struct vdso_arch_data *vdso_data; + +#else /* __ASSEMBLY__ */ + +.macro get_datapage ptr + bcl 20, 31, .+4 +999: + mflr \ptr + addis \ptr, \ptr, (_vdso_datapage - 999b)@ha + addi \ptr, \ptr, (_vdso_datapage - 999b)@l +.endm #endif /* __ASSEMBLY__ */ diff --git a/arch/powerpc/include/asm/vermagic.h b/arch/powerpc/include/asm/vermagic.h new file mode 100644 index 000000000000..6f250fe506bd --- /dev/null +++ b/arch/powerpc/include/asm/vermagic.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_VERMAGIC_H +#define _ASM_VERMAGIC_H + +#ifdef CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY +#define MODULE_ARCH_VERMAGIC_FTRACE "patchable-function-entry " +#elif defined(CONFIG_MPROFILE_KERNEL) +#define MODULE_ARCH_VERMAGIC_FTRACE "mprofile-kernel " +#else +#define MODULE_ARCH_VERMAGIC_FTRACE "" +#endif + +#ifdef CONFIG_RELOCATABLE +#define MODULE_ARCH_VERMAGIC_RELOCATABLE "relocatable " +#else +#define MODULE_ARCH_VERMAGIC_RELOCATABLE "" +#endif + +#define MODULE_ARCH_VERMAGIC \ + MODULE_ARCH_VERMAGIC_FTRACE MODULE_ARCH_VERMAGIC_RELOCATABLE + +#endif /* _ASM_VERMAGIC_H */ diff --git a/arch/powerpc/include/asm/vio.h b/arch/powerpc/include/asm/vio.h index 0cf52746531b..cc9b787627ad 100644 --- a/arch/powerpc/include/asm/vio.h +++ b/arch/powerpc/include/asm/vio.h @@ -113,7 +113,8 @@ struct vio_driver { const char *name; const struct vio_device_id *id_table; int (*probe)(struct vio_dev *dev, const struct vio_device_id *id); - int (*remove)(struct vio_dev *dev); + void (*remove)(struct vio_dev *dev); + void (*shutdown)(struct vio_dev *dev); /* A driver must have a get_desired_dma() function to * be loaded in a CMO environment if it uses DMA. */ @@ -160,10 +161,7 @@ static inline struct vio_driver *to_vio_driver(struct device_driver *drv) return container_of(drv, struct vio_driver, driver); } -static inline struct vio_dev *to_vio_dev(struct device *dev) -{ - return container_of(dev, struct vio_dev, dev); -} +#define to_vio_dev(__dev) container_of_const(__dev, struct vio_dev, dev) #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_VIO_H */ diff --git a/arch/powerpc/include/asm/vmalloc.h b/arch/powerpc/include/asm/vmalloc.h new file mode 100644 index 000000000000..4c69ece52a31 --- /dev/null +++ b/arch/powerpc/include/asm/vmalloc.h @@ -0,0 +1,24 @@ +#ifndef _ASM_POWERPC_VMALLOC_H +#define _ASM_POWERPC_VMALLOC_H + +#include <asm/mmu.h> +#include <asm/page.h> + +#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP + +#define arch_vmap_pud_supported arch_vmap_pud_supported +static inline bool arch_vmap_pud_supported(pgprot_t prot) +{ + /* HPT does not cope with large pages in the vmalloc area */ + return radix_enabled(); +} + +#define arch_vmap_pmd_supported arch_vmap_pmd_supported +static inline bool arch_vmap_pmd_supported(pgprot_t prot) +{ + return radix_enabled(); +} + +#endif + +#endif /* _ASM_POWERPC_VMALLOC_H */ diff --git a/arch/powerpc/include/asm/vphn.h b/arch/powerpc/include/asm/vphn.h new file mode 100644 index 000000000000..8c2f795eea68 --- /dev/null +++ b/arch/powerpc/include/asm/vphn.h @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _ASM_POWERPC_VPHN_H +#define _ASM_POWERPC_VPHN_H + +/* The H_HOME_NODE_ASSOCIATIVITY h_call returns 6 64-bit registers. */ +#define VPHN_REGISTER_COUNT 6 + +/* + * 6 64-bit registers unpacked into up to 24 be32 associativity values. To + * form the complete property we have to add the length in the first cell. + */ +#define VPHN_ASSOC_BUFSIZE (VPHN_REGISTER_COUNT*sizeof(u64)/sizeof(u16) + 1) + +/* + * The H_HOME_NODE_ASSOCIATIVITY hcall takes two values for flags: + * 1 for retrieving associativity information for a guest cpu + * 2 for retrieving associativity information for a host/hypervisor cpu + */ +#define VPHN_FLAG_VCPU 1 +#define VPHN_FLAG_PCPU 2 + +long hcall_vphn(unsigned long cpu, u64 flags, __be32 *associativity); + +#endif // _ASM_POWERPC_VPHN_H diff --git a/arch/powerpc/include/asm/word-at-a-time.h b/arch/powerpc/include/asm/word-at-a-time.h index f3f4710d4ff5..30a12d208687 100644 --- a/arch/powerpc/include/asm/word-at-a-time.h +++ b/arch/powerpc/include/asm/word-at-a-time.h @@ -7,7 +7,7 @@ #include <linux/kernel.h> #include <asm/asm-compat.h> -#include <asm/ppc_asm.h> +#include <asm/extable.h> #ifdef __BIG_ENDIAN__ @@ -34,7 +34,7 @@ static inline long find_zero(unsigned long mask) return leading_zero_bits >> 3; } -static inline bool has_zero(unsigned long val, unsigned long *data, const struct word_at_a_time *c) +static inline unsigned long has_zero(unsigned long val, unsigned long *data, const struct word_at_a_time *c) { unsigned long rhs = val | c->low_bits; *data = rhs; diff --git a/arch/powerpc/include/asm/xics.h b/arch/powerpc/include/asm/xics.h index 8e903b3f9c24..89090485bec1 100644 --- a/arch/powerpc/include/asm/xics.h +++ b/arch/powerpc/include/asm/xics.h @@ -38,13 +38,13 @@ static inline int icp_native_init(void) { return -ENODEV; } /* PAPR ICP */ #ifdef CONFIG_PPC_ICP_HV -extern int icp_hv_init(void); +int __init icp_hv_init(void); #else static inline int icp_hv_init(void) { return -ENODEV; } #endif #ifdef CONFIG_PPC_POWERNV -extern int icp_opal_init(void); +int __init icp_opal_init(void); extern void icp_opal_flush_interrupt(void); #else static inline int icp_opal_init(void) { return -ENODEV; } @@ -65,8 +65,12 @@ struct icp_ops { extern const struct icp_ops *icp_ops; +#ifdef CONFIG_PPC_ICS_NATIVE /* Native ICS */ extern int ics_native_init(void); +#else +static inline int ics_native_init(void) { return -ENODEV; } +#endif /* RTAS ICS */ #ifdef CONFIG_PPC_ICS_RTAS @@ -85,10 +89,11 @@ static inline int ics_opal_init(void) { return -ENODEV; } /* ICS instance, hooked up to chip_data of an irq */ struct ics { struct list_head link; - int (*map)(struct ics *ics, unsigned int virq); + int (*check)(struct ics *ics, unsigned int hwirq); void (*mask_unknown)(struct ics *ics, unsigned long vec); long (*get_server)(struct ics *ics, unsigned long vec); int (*host_match)(struct ics *ics, struct device_node *node); + struct irq_chip *chip; char data[]; }; @@ -154,7 +159,6 @@ extern void xics_setup_cpu(void); extern void xics_update_irq_servers(void); extern void xics_set_cpu_giq(unsigned int gserver, unsigned int join); extern void xics_mask_unknown_vec(unsigned int vec); -extern irqreturn_t xics_ipi_dispatch(int cpu); extern void xics_smp_probe(void); extern void xics_register_ics(struct ics *ics); extern void xics_teardown_cpu(void); diff --git a/arch/powerpc/include/asm/xilinx_intc.h b/arch/powerpc/include/asm/xilinx_intc.h deleted file mode 100644 index ca9aa162fb09..000000000000 --- a/arch/powerpc/include/asm/xilinx_intc.h +++ /dev/null @@ -1,16 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * Xilinx intc external definitions - * - * Copyright 2007 Secret Lab Technologies Ltd. - */ -#ifndef _ASM_POWERPC_XILINX_INTC_H -#define _ASM_POWERPC_XILINX_INTC_H - -#ifdef __KERNEL__ - -extern void __init xilinx_intc_init_tree(void); -extern unsigned int xintc_get_irq(void); - -#endif /* __KERNEL__ */ -#endif /* _ASM_POWERPC_XILINX_INTC_H */ diff --git a/arch/powerpc/include/asm/xilinx_pci.h b/arch/powerpc/include/asm/xilinx_pci.h deleted file mode 100644 index 7a8275caf6af..000000000000 --- a/arch/powerpc/include/asm/xilinx_pci.h +++ /dev/null @@ -1,21 +0,0 @@ -/* - * Xilinx pci external definitions - * - * Copyright 2009 Roderick Colenbrander - * Copyright 2009 Secret Lab Technologies Ltd. - * - * This file is licensed under the terms of the GNU General Public License - * version 2. This program is licensed "as is" without any warranty of any - * kind, whether express or implied. - */ - -#ifndef INCLUDE_XILINX_PCI -#define INCLUDE_XILINX_PCI - -#ifdef CONFIG_XILINX_PCI -extern void __init xilinx_pci_init(void); -#else -static inline void __init xilinx_pci_init(void) { return; } -#endif - -#endif /* INCLUDE_XILINX_PCI */ diff --git a/arch/powerpc/include/asm/xive-regs.h b/arch/powerpc/include/asm/xive-regs.h index f2dfcd50a2d3..cf8bb6ac4463 100644 --- a/arch/powerpc/include/asm/xive-regs.h +++ b/arch/powerpc/include/asm/xive-regs.h @@ -37,8 +37,17 @@ #define XIVE_ESB_SET_PQ_10 0xe00 /* Load */ #define XIVE_ESB_SET_PQ_11 0xf00 /* Load */ +/* + * Load-after-store ordering + * + * Adding this offset to the load address will enforce + * load-after-store ordering. This is required to use StoreEOI. + */ +#define XIVE_ESB_LD_ST_MO 0x40 /* Load-after-store ordering */ + #define XIVE_ESB_VAL_P 0x2 #define XIVE_ESB_VAL_Q 0x1 +#define XIVE_ESB_INVALID 0xFF /* * Thread Management (aka "TM") registers @@ -71,10 +80,13 @@ #define TM_QW0W2_VU PPC_BIT32(0) #define TM_QW0W2_LOGIC_SERV PPC_BITMASK32(1,31) // XX 2,31 ? #define TM_QW1W2_VO PPC_BIT32(0) +#define TM_QW1W2_HO PPC_BIT32(1) /* P10 XIVE2 */ #define TM_QW1W2_OS_CAM PPC_BITMASK32(8,31) #define TM_QW2W2_VP PPC_BIT32(0) +#define TM_QW2W2_HP PPC_BIT32(1) /* P10 XIVE2 */ #define TM_QW2W2_POOL_CAM PPC_BITMASK32(8,31) #define TM_QW3W2_VT PPC_BIT32(0) +#define TM_QW3W2_HT PPC_BIT32(1) /* P10 XIVE2 */ #define TM_QW3W2_LP PPC_BIT32(6) #define TM_QW3W2_LE PPC_BIT32(7) #define TM_QW3W2_T PPC_BIT32(31) diff --git a/arch/powerpc/include/asm/xive.h b/arch/powerpc/include/asm/xive.h index 24cdf97376c4..92930b0b5d0e 100644 --- a/arch/powerpc/include/asm/xive.h +++ b/arch/powerpc/include/asm/xive.h @@ -5,6 +5,8 @@ #ifndef _ASM_POWERPC_XIVE_H #define _ASM_POWERPC_XIVE_H +#include <asm/opal-api.h> + #define XIVE_INVALID_VP 0xffffffff #ifdef CONFIG_PPC_XIVE @@ -58,13 +60,13 @@ struct xive_irq_data { }; #define XIVE_IRQ_FLAG_STORE_EOI 0x01 #define XIVE_IRQ_FLAG_LSI 0x02 -#define XIVE_IRQ_FLAG_SHIFT_BUG 0x04 -#define XIVE_IRQ_FLAG_MASK_FW 0x08 -#define XIVE_IRQ_FLAG_EOI_FW 0x10 +/* #define XIVE_IRQ_FLAG_SHIFT_BUG 0x04 */ /* P9 DD1.0 workaround */ +/* #define XIVE_IRQ_FLAG_MASK_FW 0x08 */ /* P9 DD1.0 workaround */ +/* #define XIVE_IRQ_FLAG_EOI_FW 0x10 */ /* P9 DD1.0 workaround */ #define XIVE_IRQ_FLAG_H_INT_ESB 0x20 /* Special flag set by KVM for excalation interrupts */ -#define XIVE_IRQ_NO_EOI 0x80 +#define XIVE_IRQ_FLAG_NO_EOI 0x80 #define XIVE_INVALID_CHIP_ID -1 @@ -87,56 +89,64 @@ extern bool __xive_enabled; static inline bool xive_enabled(void) { return __xive_enabled; } -extern bool xive_spapr_init(void); -extern bool xive_native_init(void); -extern void xive_smp_probe(void); -extern int xive_smp_prepare_cpu(unsigned int cpu); -extern void xive_smp_setup_cpu(void); -extern void xive_smp_disable_cpu(void); -extern void xive_teardown_cpu(void); -extern void xive_shutdown(void); -extern void xive_flush_interrupt(void); +bool xive_spapr_init(void); +bool xive_native_init(void); +void xive_smp_probe(void); +int xive_smp_prepare_cpu(unsigned int cpu); +void xive_smp_setup_cpu(void); +void xive_smp_disable_cpu(void); +void xive_teardown_cpu(void); +void xive_shutdown(void); +void xive_flush_interrupt(void); /* xmon hook */ -extern void xmon_xive_do_dump(int cpu); -extern int xmon_xive_get_irq_config(u32 hw_irq, struct irq_data *d); +void xmon_xive_do_dump(int cpu); +int xmon_xive_get_irq_config(u32 hw_irq, struct irq_data *d); +void xmon_xive_get_irq_all(void); /* APIs used by KVM */ -extern u32 xive_native_default_eq_shift(void); -extern u32 xive_native_alloc_vp_block(u32 max_vcpus); -extern void xive_native_free_vp_block(u32 vp_base); -extern int xive_native_populate_irq_data(u32 hw_irq, - struct xive_irq_data *data); -extern void xive_cleanup_irq_data(struct xive_irq_data *xd); -extern u32 xive_native_alloc_irq(void); -extern void xive_native_free_irq(u32 irq); -extern int xive_native_configure_irq(u32 hw_irq, u32 target, u8 prio, u32 sw_irq); - -extern int xive_native_configure_queue(u32 vp_id, struct xive_q *q, u8 prio, - __be32 *qpage, u32 order, bool can_escalate); -extern void xive_native_disable_queue(u32 vp_id, struct xive_q *q, u8 prio); - -extern void xive_native_sync_source(u32 hw_irq); -extern void xive_native_sync_queue(u32 hw_irq); -extern bool is_xive_irq(struct irq_chip *chip); -extern int xive_native_enable_vp(u32 vp_id, bool single_escalation); -extern int xive_native_disable_vp(u32 vp_id); -extern int xive_native_get_vp_info(u32 vp_id, u32 *out_cam_id, u32 *out_chip_id); -extern bool xive_native_has_single_escalation(void); - -extern int xive_native_get_queue_info(u32 vp_id, uint32_t prio, - u64 *out_qpage, - u64 *out_qsize, - u64 *out_qeoi_page, - u32 *out_escalate_irq, - u64 *out_qflags); - -extern int xive_native_get_queue_state(u32 vp_id, uint32_t prio, u32 *qtoggle, - u32 *qindex); -extern int xive_native_set_queue_state(u32 vp_id, uint32_t prio, u32 qtoggle, - u32 qindex); -extern int xive_native_get_vp_state(u32 vp_id, u64 *out_state); -extern bool xive_native_has_queue_state_support(void); +u32 xive_native_default_eq_shift(void); +u32 xive_native_alloc_vp_block(u32 max_vcpus); +void xive_native_free_vp_block(u32 vp_base); +int xive_native_populate_irq_data(u32 hw_irq, + struct xive_irq_data *data); +void xive_cleanup_irq_data(struct xive_irq_data *xd); +void xive_irq_free_data(unsigned int virq); +void xive_native_free_irq(u32 irq); +int xive_native_configure_irq(u32 hw_irq, u32 target, u8 prio, u32 sw_irq); + +int xive_native_configure_queue(u32 vp_id, struct xive_q *q, u8 prio, + __be32 *qpage, u32 order, bool can_escalate); +void xive_native_disable_queue(u32 vp_id, struct xive_q *q, u8 prio); + +void xive_native_sync_source(u32 hw_irq); +void xive_native_sync_queue(u32 hw_irq); +bool is_xive_irq(struct irq_chip *chip); +int xive_native_enable_vp(u32 vp_id, bool single_escalation); +int xive_native_disable_vp(u32 vp_id); +int xive_native_get_vp_info(u32 vp_id, u32 *out_cam_id, u32 *out_chip_id); +bool xive_native_has_single_escalation(void); +bool xive_native_has_save_restore(void); + +int xive_native_get_queue_info(u32 vp_id, uint32_t prio, + u64 *out_qpage, + u64 *out_qsize, + u64 *out_qeoi_page, + u32 *out_escalate_irq, + u64 *out_qflags); + +int xive_native_get_queue_state(u32 vp_id, uint32_t prio, u32 *qtoggle, + u32 *qindex); +int xive_native_set_queue_state(u32 vp_id, uint32_t prio, u32 qtoggle, + u32 qindex); +int xive_native_get_vp_state(u32 vp_id, u64 *out_state); +bool xive_native_has_queue_state_support(void); +extern u32 xive_native_alloc_irq_on_chip(u32 chip_id); + +static inline u32 xive_native_alloc_irq(void) +{ + return xive_native_alloc_irq_on_chip(OPAL_XIVE_ANY_CHIP); +} #else @@ -148,7 +158,6 @@ static inline void xive_smp_probe(void) { } static inline int xive_smp_prepare_cpu(unsigned int cpu) { return -EINVAL; } static inline void xive_smp_setup_cpu(void) { } static inline void xive_smp_disable_cpu(void) { } -static inline void xive_kexec_teardown_cpu(int secondary) { } static inline void xive_shutdown(void) { } static inline void xive_flush_interrupt(void) { } diff --git a/arch/powerpc/include/asm/xmon.h b/arch/powerpc/include/asm/xmon.h index 454a7fc6113b..f2d44b44f46c 100644 --- a/arch/powerpc/include/asm/xmon.h +++ b/arch/powerpc/include/asm/xmon.h @@ -12,13 +12,13 @@ #ifdef CONFIG_XMON extern void xmon_setup(void); -extern void xmon_register_spus(struct list_head *list); +void __init xmon_register_spus(struct list_head *list); struct pt_regs; extern int xmon(struct pt_regs *excp); extern irqreturn_t xmon_irq(int, void *); #else -static inline void xmon_setup(void) { }; -static inline void xmon_register_spus(struct list_head *list) { }; +static inline void xmon_setup(void) { } +static inline void xmon_register_spus(struct list_head *list) { } #endif #if defined(CONFIG_XMON) && defined(CONFIG_SMP) diff --git a/arch/powerpc/include/asm/xor_altivec.h b/arch/powerpc/include/asm/xor_altivec.h index 6ca923510b59..294620a25f80 100644 --- a/arch/powerpc/include/asm/xor_altivec.h +++ b/arch/powerpc/include/asm/xor_altivec.h @@ -3,17 +3,20 @@ #define _ASM_POWERPC_XOR_ALTIVEC_H #ifdef CONFIG_ALTIVEC - -void xor_altivec_2(unsigned long bytes, unsigned long *v1_in, - unsigned long *v2_in); -void xor_altivec_3(unsigned long bytes, unsigned long *v1_in, - unsigned long *v2_in, unsigned long *v3_in); -void xor_altivec_4(unsigned long bytes, unsigned long *v1_in, - unsigned long *v2_in, unsigned long *v3_in, - unsigned long *v4_in); -void xor_altivec_5(unsigned long bytes, unsigned long *v1_in, - unsigned long *v2_in, unsigned long *v3_in, - unsigned long *v4_in, unsigned long *v5_in); +void xor_altivec_2(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2); +void xor_altivec_3(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2, + const unsigned long * __restrict p3); +void xor_altivec_4(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2, + const unsigned long * __restrict p3, + const unsigned long * __restrict p4); +void xor_altivec_5(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2, + const unsigned long * __restrict p3, + const unsigned long * __restrict p4, + const unsigned long * __restrict p5); #endif #endif /* _ASM_POWERPC_XOR_ALTIVEC_H */ diff --git a/arch/powerpc/include/uapi/asm/auxvec.h b/arch/powerpc/include/uapi/asm/auxvec.h index 7af21dc0e320..aa7c16215453 100644 --- a/arch/powerpc/include/uapi/asm/auxvec.h +++ b/arch/powerpc/include/uapi/asm/auxvec.h @@ -48,6 +48,8 @@ #define AT_L3_CACHESIZE 46 #define AT_L3_CACHEGEOMETRY 47 -#define AT_VECTOR_SIZE_ARCH 14 /* entries in ARCH_DLINFO */ +#define AT_MINSIGSTKSZ 51 /* stack needed for signal delivery */ + +#define AT_VECTOR_SIZE_ARCH 15 /* entries in ARCH_DLINFO */ #endif diff --git a/arch/powerpc/include/uapi/asm/bpf_perf_event.h b/arch/powerpc/include/uapi/asm/bpf_perf_event.h deleted file mode 100644 index 5e1e648aeec4..000000000000 --- a/arch/powerpc/include/uapi/asm/bpf_perf_event.h +++ /dev/null @@ -1,9 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -#ifndef _UAPI__ASM_BPF_PERF_EVENT_H__ -#define _UAPI__ASM_BPF_PERF_EVENT_H__ - -#include <asm/ptrace.h> - -typedef struct user_pt_regs bpf_user_pt_regs_t; - -#endif /* _UAPI__ASM_BPF_PERF_EVENT_H__ */ diff --git a/arch/powerpc/include/uapi/asm/cputable.h b/arch/powerpc/include/uapi/asm/cputable.h index 540592034740..731b97dc2d15 100644 --- a/arch/powerpc/include/uapi/asm/cputable.h +++ b/arch/powerpc/include/uapi/asm/cputable.h @@ -50,6 +50,8 @@ #define PPC_FEATURE2_DARN 0x00200000 /* darn random number insn */ #define PPC_FEATURE2_SCV 0x00100000 /* scv syscall */ #define PPC_FEATURE2_HTM_NO_SUSPEND 0x00080000 /* TM w/out suspended state */ +#define PPC_FEATURE2_ARCH_3_1 0x00040000 /* ISA 3.1 */ +#define PPC_FEATURE2_MMA 0x00020000 /* Matrix Multiply Assist */ /* * IMPORTANT! diff --git a/arch/powerpc/include/uapi/asm/elf.h b/arch/powerpc/include/uapi/asm/elf.h index 860c59291bfc..a5377f494fa3 100644 --- a/arch/powerpc/include/uapi/asm/elf.h +++ b/arch/powerpc/include/uapi/asm/elf.h @@ -98,6 +98,8 @@ #define ELF_NEBB 3 /* includes ebbrr, ebbhr, bescr */ #define ELF_NPMU 5 /* includes siar, sdar, sier, mmcr2, mmcr0 */ #define ELF_NPKEY 3 /* includes amr, iamr, uamor */ +#define ELF_NDEXCR 2 /* includes dexcr, hdexcr */ +#define ELF_NHASHKEYR 1 /* includes hashkeyr */ typedef unsigned long elf_greg_t64; typedef elf_greg_t64 elf_gregset_t64[ELF_NGREG]; @@ -279,8 +281,12 @@ typedef elf_fpreg_t elf_vsrreghalf_t32[ELF_NVSRHALFREG]; #define R_PPC64_TLSLD 108 #define R_PPC64_TOCSAVE 109 +#define R_PPC64_REL24_NOTOC 116 #define R_PPC64_ENTRY 118 +#define R_PPC64_PCREL34 132 +#define R_PPC64_GOT_PCREL34 133 + #define R_PPC64_REL16 249 #define R_PPC64_REL16_LO 250 #define R_PPC64_REL16_HI 251 @@ -289,12 +295,4 @@ typedef elf_fpreg_t elf_vsrreghalf_t32[ELF_NVSRHALFREG]; /* Keep this the last entry. */ #define R_PPC64_NUM 253 -/* There's actually a third entry here, but it's unused */ -struct ppc64_opd_entry -{ - unsigned long funcaddr; - unsigned long r2; -}; - - #endif /* _UAPI_ASM_POWERPC_ELF_H */ diff --git a/arch/powerpc/include/uapi/asm/errno.h b/arch/powerpc/include/uapi/asm/errno.h index cc79856896a1..4ba87de32be0 100644 --- a/arch/powerpc/include/uapi/asm/errno.h +++ b/arch/powerpc/include/uapi/asm/errno.h @@ -2,6 +2,7 @@ #ifndef _ASM_POWERPC_ERRNO_H #define _ASM_POWERPC_ERRNO_H +#undef EDEADLOCK #include <asm-generic/errno.h> #undef EDEADLOCK diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h index 264e266a85bf..9f18fa090f1f 100644 --- a/arch/powerpc/include/uapi/asm/kvm.h +++ b/arch/powerpc/include/uapi/asm/kvm.h @@ -640,6 +640,13 @@ struct kvm_ppc_cpu_char { #define KVM_REG_PPC_ONLINE (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xbf) #define KVM_REG_PPC_PTCR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc0) +/* POWER10 registers */ +#define KVM_REG_PPC_MMCR3 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc1) +#define KVM_REG_PPC_SIER2 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc2) +#define KVM_REG_PPC_SIER3 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc3) +#define KVM_REG_PPC_DAWR1 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc4) +#define KVM_REG_PPC_DAWRX1 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc5) + /* Transactional Memory checkpointed state: * This is all GPRs, all VSX regs and a subset of SPRs */ diff --git a/arch/powerpc/include/uapi/asm/kvm_para.h b/arch/powerpc/include/uapi/asm/kvm_para.h index be48c2215fa2..a809b1b44ddf 100644 --- a/arch/powerpc/include/uapi/asm/kvm_para.h +++ b/arch/powerpc/include/uapi/asm/kvm_para.h @@ -31,7 +31,7 @@ * Struct fields are always 32 or 64 bit aligned, depending on them being 32 * or 64 bit wide respectively. * - * See Documentation/virt/kvm/ppc-pv.txt + * See Documentation/virt/kvm/ppc-pv.rst */ struct kvm_vcpu_arch_shared { __u64 scratch1; diff --git a/arch/powerpc/include/uapi/asm/papr-miscdev.h b/arch/powerpc/include/uapi/asm/papr-miscdev.h new file mode 100644 index 000000000000..49a2a270b7f3 --- /dev/null +++ b/arch/powerpc/include/uapi/asm/papr-miscdev.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI_PAPR_MISCDEV_H_ +#define _UAPI_PAPR_MISCDEV_H_ + +enum { + PAPR_MISCDEV_IOC_ID = 0xb2, +}; + +#endif /* _UAPI_PAPR_MISCDEV_H_ */ diff --git a/arch/powerpc/include/uapi/asm/papr-sysparm.h b/arch/powerpc/include/uapi/asm/papr-sysparm.h new file mode 100644 index 000000000000..9f9a0f267ea5 --- /dev/null +++ b/arch/powerpc/include/uapi/asm/papr-sysparm.h @@ -0,0 +1,58 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI_PAPR_SYSPARM_H_ +#define _UAPI_PAPR_SYSPARM_H_ + +#include <linux/types.h> +#include <asm/ioctl.h> +#include <asm/papr-miscdev.h> + +enum { + PAPR_SYSPARM_MAX_INPUT = 1024, + PAPR_SYSPARM_MAX_OUTPUT = 4000, +}; + +struct papr_sysparm_io_block { + __u32 parameter; + __u16 length; + char data[PAPR_SYSPARM_MAX_OUTPUT]; +}; + +/** + * PAPR_SYSPARM_IOC_GET - Retrieve the value of a PAPR system parameter. + * + * Uses _IOWR because of one corner case: Retrieving the value of the + * "OS Service Entitlement Status" parameter (60) requires the caller + * to supply input data (a date string) in the buffer passed to + * firmware. So the @length and @data of the incoming + * papr_sysparm_io_block are always used to initialize the work area + * supplied to ibm,get-system-parameter. No other parameters are known + * to parameterize the result this way, and callers are encouraged + * (but not required) to zero-initialize @length and @data in the + * common case. + * + * On error the contents of the ioblock are indeterminate. + * + * Return: + * 0: Success; @length is the length of valid data in @data, not to exceed @PAPR_SYSPARM_MAX_OUTPUT. + * -EIO: Platform error. (-1) + * -EINVAL: Incorrect data length or format. (-9999) + * -EPERM: The calling partition is not allowed to access this parameter. (-9002) + * -EOPNOTSUPP: Parameter not supported on this platform (-3) + */ +#define PAPR_SYSPARM_IOC_GET _IOWR(PAPR_MISCDEV_IOC_ID, 1, struct papr_sysparm_io_block) + +/** + * PAPR_SYSPARM_IOC_SET - Update the value of a PAPR system parameter. + * + * The contents of the ioblock are unchanged regardless of success. + * + * Return: + * 0: Success; the parameter has been updated. + * -EIO: Platform error. (-1) + * -EINVAL: Incorrect data length or format. (-9999) + * -EPERM: The calling partition is not allowed to access this parameter. (-9002) + * -EOPNOTSUPP: Parameter not supported on this platform (-3) + */ +#define PAPR_SYSPARM_IOC_SET _IOW(PAPR_MISCDEV_IOC_ID, 2, struct papr_sysparm_io_block) + +#endif /* _UAPI_PAPR_SYSPARM_H_ */ diff --git a/arch/powerpc/include/uapi/asm/papr-vpd.h b/arch/powerpc/include/uapi/asm/papr-vpd.h new file mode 100644 index 000000000000..1c88e87cb420 --- /dev/null +++ b/arch/powerpc/include/uapi/asm/papr-vpd.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI_PAPR_VPD_H_ +#define _UAPI_PAPR_VPD_H_ + +#include <asm/ioctl.h> +#include <asm/papr-miscdev.h> + +struct papr_location_code { + /* + * PAPR+ v2.13 12.3.2.4 Converged Location Code Rules - Length + * Restrictions. 79 characters plus nul. + */ + char str[80]; +}; + +/* + * ioctl for /dev/papr-vpd. Returns a VPD handle fd corresponding to + * the location code. + */ +#define PAPR_VPD_IOC_CREATE_HANDLE _IOW(PAPR_MISCDEV_IOC_ID, 0, struct papr_location_code) + +#endif /* _UAPI_PAPR_VPD_H_ */ diff --git a/arch/powerpc/include/uapi/asm/papr_pdsm.h b/arch/powerpc/include/uapi/asm/papr_pdsm.h new file mode 100644 index 000000000000..17439925045c --- /dev/null +++ b/arch/powerpc/include/uapi/asm/papr_pdsm.h @@ -0,0 +1,165 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * PAPR nvDimm Specific Methods (PDSM) and structs for libndctl + * + * (C) Copyright IBM 2020 + * + * Author: Vaibhav Jain <vaibhav at linux.ibm.com> + */ + +#ifndef _UAPI_ASM_POWERPC_PAPR_PDSM_H_ +#define _UAPI_ASM_POWERPC_PAPR_PDSM_H_ + +#include <linux/types.h> +#include <linux/ndctl.h> + +/* + * PDSM Envelope: + * + * The ioctl ND_CMD_CALL exchange data between user-space and kernel via + * envelope which consists of 2 headers sections and payload sections as + * illustrated below: + * +-----------------+---------------+---------------------------+ + * | 64-Bytes | 8-Bytes | Max 184-Bytes | + * +-----------------+---------------+---------------------------+ + * | ND-HEADER | PDSM-HEADER | PDSM-PAYLOAD | + * +-----------------+---------------+---------------------------+ + * | nd_family | | | + * | nd_size_out | cmd_status | | + * | nd_size_in | reserved | nd_pdsm_payload | + * | nd_command | payload --> | | + * | nd_fw_size | | | + * | nd_payload ---> | | | + * +---------------+-----------------+---------------------------+ + * + * ND Header: + * This is the generic libnvdimm header described as 'struct nd_cmd_pkg' + * which is interpreted by libnvdimm before passed on to papr_scm. Important + * member fields used are: + * 'nd_family' : (In) NVDIMM_FAMILY_PAPR_SCM + * 'nd_size_in' : (In) PDSM-HEADER + PDSM-IN-PAYLOAD (usually 0) + * 'nd_size_out' : (In) PDSM-HEADER + PDSM-RETURN-PAYLOAD + * 'nd_command' : (In) One of PAPR_PDSM_XXX + * 'nd_fw_size' : (Out) PDSM-HEADER + size of actual payload returned + * + * PDSM Header: + * This is papr-scm specific header that precedes the payload. This is defined + * as nd_cmd_pdsm_pkg. Following fields aare available in this header: + * + * 'cmd_status' : (Out) Errors if any encountered while servicing PDSM. + * 'reserved' : Not used, reserved for future and should be set to 0. + * 'payload' : A union of all the possible payload structs + * + * PDSM Payload: + * + * The layout of the PDSM Payload is defined by various structs shared between + * papr_scm and libndctl so that contents of payload can be interpreted. As such + * its defined as a union of all possible payload structs as + * 'union nd_pdsm_payload'. Based on the value of 'nd_cmd_pkg.nd_command' + * appropriate member of the union is accessed. + */ + +/* Max payload size that we can handle */ +#define ND_PDSM_PAYLOAD_MAX_SIZE 184 + +/* Max payload size that we can handle */ +#define ND_PDSM_HDR_SIZE \ + (sizeof(struct nd_pkg_pdsm) - ND_PDSM_PAYLOAD_MAX_SIZE) + +/* Various nvdimm health indicators */ +#define PAPR_PDSM_DIMM_HEALTHY 0 +#define PAPR_PDSM_DIMM_UNHEALTHY 1 +#define PAPR_PDSM_DIMM_CRITICAL 2 +#define PAPR_PDSM_DIMM_FATAL 3 + +/* struct nd_papr_pdsm_health.extension_flags field flags */ + +/* Indicate that the 'dimm_fuel_gauge' field is valid */ +#define PDSM_DIMM_HEALTH_RUN_GAUGE_VALID 1 + +/* Indicate that the 'dimm_dsc' field is valid */ +#define PDSM_DIMM_DSC_VALID 2 + +/* + * Struct exchanged between kernel & ndctl in for PAPR_PDSM_HEALTH + * Various flags indicate the health status of the dimm. + * + * extension_flags : Any extension fields present in the struct. + * dimm_unarmed : Dimm not armed. So contents wont persist. + * dimm_bad_shutdown : Previous shutdown did not persist contents. + * dimm_bad_restore : Contents from previous shutdown werent restored. + * dimm_scrubbed : Contents of the dimm have been scrubbed. + * dimm_locked : Contents of the dimm cant be modified until CEC reboot + * dimm_encrypted : Contents of dimm are encrypted. + * dimm_health : Dimm health indicator. One of PAPR_PDSM_DIMM_XXXX + * dimm_fuel_gauge : Life remaining of DIMM as a percentage from 0-100 + */ +struct nd_papr_pdsm_health { + union { + struct { + __u32 extension_flags; + __u8 dimm_unarmed; + __u8 dimm_bad_shutdown; + __u8 dimm_bad_restore; + __u8 dimm_scrubbed; + __u8 dimm_locked; + __u8 dimm_encrypted; + __u16 dimm_health; + + /* Extension flag PDSM_DIMM_HEALTH_RUN_GAUGE_VALID */ + __u16 dimm_fuel_gauge; + + /* Extension flag PDSM_DIMM_DSC_VALID */ + __u64 dimm_dsc; + }; + __u8 buf[ND_PDSM_PAYLOAD_MAX_SIZE]; + }; +}; + +/* Flags for injecting specific smart errors */ +#define PDSM_SMART_INJECT_HEALTH_FATAL (1 << 0) +#define PDSM_SMART_INJECT_BAD_SHUTDOWN (1 << 1) + +struct nd_papr_pdsm_smart_inject { + union { + struct { + /* One or more of PDSM_SMART_INJECT_ */ + __u32 flags; + __u8 fatal_enable; + __u8 unsafe_shutdown_enable; + }; + __u8 buf[ND_PDSM_PAYLOAD_MAX_SIZE]; + }; +}; + +/* + * Methods to be embedded in ND_CMD_CALL request. These are sent to the kernel + * via 'nd_cmd_pkg.nd_command' member of the ioctl struct + */ +enum papr_pdsm { + PAPR_PDSM_MIN = 0x0, + PAPR_PDSM_HEALTH, + PAPR_PDSM_SMART_INJECT, + PAPR_PDSM_MAX, +}; + +/* Maximal union that can hold all possible payload types */ +union nd_pdsm_payload { + struct nd_papr_pdsm_health health; + struct nd_papr_pdsm_smart_inject smart_inject; + __u8 buf[ND_PDSM_PAYLOAD_MAX_SIZE]; +} __packed; + +/* + * PDSM-header + payload expected with ND_CMD_CALL ioctl from libnvdimm + * Valid member of union 'payload' is identified via 'nd_cmd_pkg.nd_command' + * that should always precede this struct when sent to papr_scm via CMD_CALL + * interface. + */ +struct nd_pkg_pdsm { + __s32 cmd_status; /* Out: Sub-cmd status returned back */ + __u16 reserved[2]; /* Ignored and to be set as '0' */ + union nd_pdsm_payload payload; +} __packed; + +#endif /* _UAPI_ASM_POWERPC_PAPR_PDSM_H_ */ diff --git a/arch/powerpc/include/uapi/asm/perf_regs.h b/arch/powerpc/include/uapi/asm/perf_regs.h index f599064dd8dc..749a2e3af89e 100644 --- a/arch/powerpc/include/uapi/asm/perf_regs.h +++ b/arch/powerpc/include/uapi/asm/perf_regs.h @@ -48,6 +48,48 @@ enum perf_event_powerpc_regs { PERF_REG_POWERPC_DSISR, PERF_REG_POWERPC_SIER, PERF_REG_POWERPC_MMCRA, - PERF_REG_POWERPC_MAX, + /* Extended registers */ + PERF_REG_POWERPC_MMCR0, + PERF_REG_POWERPC_MMCR1, + PERF_REG_POWERPC_MMCR2, + PERF_REG_POWERPC_MMCR3, + PERF_REG_POWERPC_SIER2, + PERF_REG_POWERPC_SIER3, + PERF_REG_POWERPC_PMC1, + PERF_REG_POWERPC_PMC2, + PERF_REG_POWERPC_PMC3, + PERF_REG_POWERPC_PMC4, + PERF_REG_POWERPC_PMC5, + PERF_REG_POWERPC_PMC6, + PERF_REG_POWERPC_SDAR, + PERF_REG_POWERPC_SIAR, + /* Max mask value for interrupt regs w/o extended regs */ + PERF_REG_POWERPC_MAX = PERF_REG_POWERPC_MMCRA + 1, + /* Max mask value for interrupt regs including extended regs */ + PERF_REG_EXTENDED_MAX = PERF_REG_POWERPC_SIAR + 1, }; + +#define PERF_REG_PMU_MASK ((1ULL << PERF_REG_POWERPC_MAX) - 1) + +/* + * PERF_REG_EXTENDED_MASK value for CPU_FTR_ARCH_300 + * includes 11 SPRS from MMCR0 to SIAR excluding the + * unsupported SPRS MMCR3, SIER2 and SIER3. + */ +#define PERF_REG_PMU_MASK_300 \ + ((1ULL << PERF_REG_POWERPC_MMCR0) | (1ULL << PERF_REG_POWERPC_MMCR1) | \ + (1ULL << PERF_REG_POWERPC_MMCR2) | (1ULL << PERF_REG_POWERPC_PMC1) | \ + (1ULL << PERF_REG_POWERPC_PMC2) | (1ULL << PERF_REG_POWERPC_PMC3) | \ + (1ULL << PERF_REG_POWERPC_PMC4) | (1ULL << PERF_REG_POWERPC_PMC5) | \ + (1ULL << PERF_REG_POWERPC_PMC6) | (1ULL << PERF_REG_POWERPC_SDAR) | \ + (1ULL << PERF_REG_POWERPC_SIAR)) + +/* + * PERF_REG_EXTENDED_MASK value for CPU_FTR_ARCH_31 + * includes 14 SPRs from MMCR0 to SIAR. + */ +#define PERF_REG_PMU_MASK_31 \ + (PERF_REG_PMU_MASK_300 | (1ULL << PERF_REG_POWERPC_MMCR3) | \ + (1ULL << PERF_REG_POWERPC_SIER2) | (1ULL << PERF_REG_POWERPC_SIER3)) + #endif /* _UAPI_ASM_POWERPC_PERF_REGS_H */ diff --git a/arch/powerpc/include/uapi/asm/posix_types.h b/arch/powerpc/include/uapi/asm/posix_types.h index f698400e4bb0..9c0342312544 100644 --- a/arch/powerpc/include/uapi/asm/posix_types.h +++ b/arch/powerpc/include/uapi/asm/posix_types.h @@ -12,11 +12,6 @@ typedef unsigned long __kernel_old_dev_t; #define __kernel_old_dev_t __kernel_old_dev_t #else -typedef unsigned int __kernel_size_t; -typedef int __kernel_ssize_t; -typedef long __kernel_ptrdiff_t; -#define __kernel_size_t __kernel_size_t - typedef short __kernel_ipc_pid_t; #define __kernel_ipc_pid_t __kernel_ipc_pid_t #endif diff --git a/arch/powerpc/include/uapi/asm/ptrace.h b/arch/powerpc/include/uapi/asm/ptrace.h index f5f1ccc740fc..7004cfea3f5f 100644 --- a/arch/powerpc/include/uapi/asm/ptrace.h +++ b/arch/powerpc/include/uapi/asm/ptrace.h @@ -222,6 +222,7 @@ struct ppc_debug_info { #define PPC_DEBUG_FEATURE_DATA_BP_RANGE 0x0000000000000004 #define PPC_DEBUG_FEATURE_DATA_BP_MASK 0x0000000000000008 #define PPC_DEBUG_FEATURE_DATA_BP_DAWR 0x0000000000000010 +#define PPC_DEBUG_FEATURE_DATA_BP_ARCH_31 0x0000000000000020 #ifndef __ASSEMBLY__ diff --git a/arch/powerpc/include/uapi/asm/shmbuf.h b/arch/powerpc/include/uapi/asm/shmbuf.h index 00422b2f3c63..439a3a02ba64 100644 --- a/arch/powerpc/include/uapi/asm/shmbuf.h +++ b/arch/powerpc/include/uapi/asm/shmbuf.h @@ -2,6 +2,9 @@ #ifndef _ASM_POWERPC_SHMBUF_H #define _ASM_POWERPC_SHMBUF_H +#include <asm/ipcbuf.h> +#include <asm/posix_types.h> + /* * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License @@ -34,7 +37,7 @@ struct shmid64_ds { unsigned long shm_ctime; /* last change time */ unsigned long __unused4; #endif - size_t shm_segsz; /* size of segment (bytes) */ + __kernel_size_t shm_segsz; /* size of segment (bytes) */ __kernel_pid_t shm_cpid; /* pid of creator */ __kernel_pid_t shm_lpid; /* pid of last operator */ unsigned long shm_nattch; /* no. of current attaches */ diff --git a/arch/powerpc/include/uapi/asm/signal.h b/arch/powerpc/include/uapi/asm/signal.h index 85b0a7aa43e7..a5dfe84f50ab 100644 --- a/arch/powerpc/include/uapi/asm/signal.h +++ b/arch/powerpc/include/uapi/asm/signal.h @@ -60,34 +60,15 @@ typedef struct { #define SIGRTMIN 32 #define SIGRTMAX _NSIG -/* - * SA_FLAGS values: - * - * SA_ONSTACK is not currently supported, but will allow sigaltstack(2). - * SA_RESTART flag to get restarting signals (which were the default long ago) - * SA_NOCLDSTOP flag to turn off SIGCHLD when children stop. - * SA_RESETHAND clears the handler when the signal is delivered. - * SA_NOCLDWAIT flag on SIGCHLD to inhibit zombies. - * SA_NODEFER prevents the current signal from being masked in the handler. - * - * SA_ONESHOT and SA_NOMASK are the historical Linux names for the Single - * Unix names RESETHAND and NODEFER respectively. - */ -#define SA_NOCLDSTOP 0x00000001U -#define SA_NOCLDWAIT 0x00000002U -#define SA_SIGINFO 0x00000004U -#define SA_ONSTACK 0x08000000U -#define SA_RESTART 0x10000000U -#define SA_NODEFER 0x40000000U -#define SA_RESETHAND 0x80000000U - -#define SA_NOMASK SA_NODEFER -#define SA_ONESHOT SA_RESETHAND - #define SA_RESTORER 0x04000000U +#ifdef __powerpc64__ +#define MINSIGSTKSZ 8192 +#define SIGSTKSZ 32768 +#else #define MINSIGSTKSZ 2048 #define SIGSTKSZ 8192 +#endif #include <asm-generic/signal-defs.h> @@ -110,7 +91,7 @@ struct sigaction { typedef struct sigaltstack { void __user *ss_sp; int ss_flags; - size_t ss_size; + __kernel_size_t ss_size; } stack_t; diff --git a/arch/powerpc/include/uapi/asm/stat.h b/arch/powerpc/include/uapi/asm/stat.h index 7871055e5e32..d50901664239 100644 --- a/arch/powerpc/include/uapi/asm/stat.h +++ b/arch/powerpc/include/uapi/asm/stat.h @@ -29,16 +29,16 @@ struct __old_kernel_stat { struct stat { unsigned long st_dev; - ino_t st_ino; + __kernel_ino_t st_ino; #ifdef __powerpc64__ unsigned long st_nlink; - mode_t st_mode; + __kernel_mode_t st_mode; #else - mode_t st_mode; + __kernel_mode_t st_mode; unsigned short st_nlink; #endif - uid_t st_uid; - gid_t st_gid; + __kernel_uid32_t st_uid; + __kernel_gid32_t st_gid; unsigned long st_rdev; long st_size; unsigned long st_blksize; diff --git a/arch/powerpc/include/uapi/asm/termbits.h b/arch/powerpc/include/uapi/asm/termbits.h index ed18bc61f63d..21dc86dcb2f1 100644 --- a/arch/powerpc/include/uapi/asm/termbits.h +++ b/arch/powerpc/include/uapi/asm/termbits.h @@ -9,8 +9,8 @@ * 2 of the License, or (at your option) any later version. */ -typedef unsigned char cc_t; -typedef unsigned int speed_t; +#include <asm-generic/termbits-common.h> + typedef unsigned int tcflag_t; /* @@ -64,115 +64,72 @@ struct ktermios { #define VDISCARD 16 /* c_iflag bits */ -#define IGNBRK 0000001 -#define BRKINT 0000002 -#define IGNPAR 0000004 -#define PARMRK 0000010 -#define INPCK 0000020 -#define ISTRIP 0000040 -#define INLCR 0000100 -#define IGNCR 0000200 -#define ICRNL 0000400 -#define IXON 0001000 -#define IXOFF 0002000 -#define IXANY 0004000 -#define IUCLC 0010000 -#define IMAXBEL 0020000 -#define IUTF8 0040000 +#define IXON 0x0200 +#define IXOFF 0x0400 +#define IUCLC 0x1000 +#define IMAXBEL 0x2000 +#define IUTF8 0x4000 /* c_oflag bits */ -#define OPOST 0000001 -#define ONLCR 0000002 -#define OLCUC 0000004 - -#define OCRNL 0000010 -#define ONOCR 0000020 -#define ONLRET 0000040 - -#define OFILL 00000100 -#define OFDEL 00000200 -#define NLDLY 00001400 -#define NL0 00000000 -#define NL1 00000400 -#define NL2 00001000 -#define NL3 00001400 -#define TABDLY 00006000 -#define TAB0 00000000 -#define TAB1 00002000 -#define TAB2 00004000 -#define TAB3 00006000 -#define XTABS 00006000 /* required by POSIX to == TAB3 */ -#define CRDLY 00030000 -#define CR0 00000000 -#define CR1 00010000 -#define CR2 00020000 -#define CR3 00030000 -#define FFDLY 00040000 -#define FF0 00000000 -#define FF1 00040000 -#define BSDLY 00100000 -#define BS0 00000000 -#define BS1 00100000 -#define VTDLY 00200000 -#define VT0 00000000 -#define VT1 00200000 +#define ONLCR 0x00002 +#define OLCUC 0x00004 +#define NLDLY 0x00300 +#define NL0 0x00000 +#define NL1 0x00100 +#define NL2 0x00200 +#define NL3 0x00300 +#define TABDLY 0x00c00 +#define TAB0 0x00000 +#define TAB1 0x00400 +#define TAB2 0x00800 +#define TAB3 0x00c00 +#define XTABS 0x00c00 /* required by POSIX to == TAB3 */ +#define CRDLY 0x03000 +#define CR0 0x00000 +#define CR1 0x01000 +#define CR2 0x02000 +#define CR3 0x03000 +#define FFDLY 0x04000 +#define FF0 0x00000 +#define FF1 0x04000 +#define BSDLY 0x08000 +#define BS0 0x00000 +#define BS1 0x08000 +#define VTDLY 0x10000 +#define VT0 0x00000 +#define VT1 0x10000 /* c_cflag bit meaning */ -#define CBAUD 0000377 -#define B0 0000000 /* hang up */ -#define B50 0000001 -#define B75 0000002 -#define B110 0000003 -#define B134 0000004 -#define B150 0000005 -#define B200 0000006 -#define B300 0000007 -#define B600 0000010 -#define B1200 0000011 -#define B1800 0000012 -#define B2400 0000013 -#define B4800 0000014 -#define B9600 0000015 -#define B19200 0000016 -#define B38400 0000017 -#define EXTA B19200 -#define EXTB B38400 -#define CBAUDEX 0000000 -#define B57600 00020 -#define B115200 00021 -#define B230400 00022 -#define B460800 00023 -#define B500000 00024 -#define B576000 00025 -#define B921600 00026 -#define B1000000 00027 -#define B1152000 00030 -#define B1500000 00031 -#define B2000000 00032 -#define B2500000 00033 -#define B3000000 00034 -#define B3500000 00035 -#define B4000000 00036 -#define BOTHER 00037 - -#define CIBAUD 077600000 -#define IBSHIFT 16 /* Shift from CBAUD to CIBAUD */ - -#define CSIZE 00001400 -#define CS5 00000000 -#define CS6 00000400 -#define CS7 00001000 -#define CS8 00001400 - -#define CSTOPB 00002000 -#define CREAD 00004000 -#define PARENB 00010000 -#define PARODD 00020000 -#define HUPCL 00040000 - -#define CLOCAL 00100000 -#define CMSPAR 010000000000 /* mark or space (stick) parity */ -#define CRTSCTS 020000000000 /* flow control */ +#define CBAUD 0x000000ff +#define CBAUDEX 0x00000000 +#define BOTHER 0x0000001f +#define B57600 0x00000010 +#define B115200 0x00000011 +#define B230400 0x00000012 +#define B460800 0x00000013 +#define B500000 0x00000014 +#define B576000 0x00000015 +#define B921600 0x00000016 +#define B1000000 0x00000017 +#define B1152000 0x00000018 +#define B1500000 0x00000019 +#define B2000000 0x0000001a +#define B2500000 0x0000001b +#define B3000000 0x0000001c +#define B3500000 0x0000001d +#define B4000000 0x0000001e +#define CSIZE 0x00000300 +#define CS5 0x00000000 +#define CS6 0x00000100 +#define CS7 0x00000200 +#define CS8 0x00000300 +#define CSTOPB 0x00000400 +#define CREAD 0x00000800 +#define PARENB 0x00001000 +#define PARODD 0x00002000 +#define HUPCL 0x00004000 +#define CLOCAL 0x00008000 +#define CIBAUD 0x00ff0000 /* c_lflag bits */ #define ISIG 0x00000080 @@ -192,17 +149,6 @@ struct ktermios { #define IEXTEN 0x00000400 #define EXTPROC 0x10000000 -/* Values for the ACTION argument to `tcflow'. */ -#define TCOOFF 0 -#define TCOON 1 -#define TCIOFF 2 -#define TCION 3 - -/* Values for the QUEUE_SELECTOR argument to `tcflush'. */ -#define TCIFLUSH 0 -#define TCOFLUSH 1 -#define TCIOFLUSH 2 - /* Values for the OPTIONAL_ACTIONS argument to `tcsetattr'. */ #define TCSANOW 0 #define TCSADRAIN 1 diff --git a/arch/powerpc/include/uapi/asm/vas-api.h b/arch/powerpc/include/uapi/asm/vas-api.h new file mode 100644 index 000000000000..7c81301ecdba --- /dev/null +++ b/arch/powerpc/include/uapi/asm/vas-api.h @@ -0,0 +1,28 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ +/* + * Copyright 2019 IBM Corp. + */ + +#ifndef _UAPI_MISC_VAS_H +#define _UAPI_MISC_VAS_H + +#include <linux/types.h> + +#include <asm/ioctl.h> + +#define VAS_MAGIC 'v' +#define VAS_TX_WIN_OPEN _IOW(VAS_MAGIC, 0x20, struct vas_tx_win_open_attr) + +/* Flags to VAS TX open window ioctl */ +/* To allocate a window with QoS credit, otherwise use default credit */ +#define VAS_TX_WIN_FLAG_QOS_CREDIT 0x0000000000000001 + +struct vas_tx_win_open_attr { + __u32 version; + __s16 vas_id; /* specific instance of vas or -1 for default */ + __u16 reserved1; + __u64 flags; + __u64 reserved2[6]; +}; + +#endif /* _UAPI_MISC_VAS_H */ |