diff options
Diffstat (limited to 'arch/alpha/include/asm')
111 files changed, 13235 insertions, 0 deletions
diff --git a/arch/alpha/include/asm/Kbuild b/arch/alpha/include/asm/Kbuild new file mode 100644 index 000000000..76aeb8fa5 --- /dev/null +++ b/arch/alpha/include/asm/Kbuild @@ -0,0 +1,11 @@ + + +generic-y += clkdev.h +generic-y += cputime.h +generic-y += exec.h +generic-y += irq_work.h +generic-y += mcs_spinlock.h +generic-y += preempt.h +generic-y += scatterlist.h +generic-y += sections.h +generic-y += trace_clock.h diff --git a/arch/alpha/include/asm/a.out-core.h b/arch/alpha/include/asm/a.out-core.h new file mode 100644 index 000000000..9e33e92e5 --- /dev/null +++ b/arch/alpha/include/asm/a.out-core.h @@ -0,0 +1,80 @@ +/* a.out coredump register dumper + * + * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ + +#ifndef _ASM_A_OUT_CORE_H +#define _ASM_A_OUT_CORE_H + +#ifdef __KERNEL__ + +#include <linux/user.h> + +/* + * Fill in the user structure for an ECOFF core dump. + */ +static inline void aout_dump_thread(struct pt_regs *pt, struct user *dump) +{ + /* switch stack follows right below pt_regs: */ + struct switch_stack * sw = ((struct switch_stack *) pt) - 1; + + dump->magic = CMAGIC; + dump->start_code = current->mm->start_code; + dump->start_data = current->mm->start_data; + dump->start_stack = rdusp() & ~(PAGE_SIZE - 1); + dump->u_tsize = ((current->mm->end_code - dump->start_code) + >> PAGE_SHIFT); + dump->u_dsize = ((current->mm->brk + PAGE_SIZE-1 - dump->start_data) + >> PAGE_SHIFT); + dump->u_ssize = (current->mm->start_stack - dump->start_stack + + PAGE_SIZE-1) >> PAGE_SHIFT; + + /* + * We store the registers in an order/format that is + * compatible with DEC Unix/OSF/1 as this makes life easier + * for gdb. + */ + dump->regs[EF_V0] = pt->r0; + dump->regs[EF_T0] = pt->r1; + dump->regs[EF_T1] = pt->r2; + dump->regs[EF_T2] = pt->r3; + dump->regs[EF_T3] = pt->r4; + dump->regs[EF_T4] = pt->r5; + dump->regs[EF_T5] = pt->r6; + dump->regs[EF_T6] = pt->r7; + dump->regs[EF_T7] = pt->r8; + dump->regs[EF_S0] = sw->r9; + dump->regs[EF_S1] = sw->r10; + dump->regs[EF_S2] = sw->r11; + dump->regs[EF_S3] = sw->r12; + dump->regs[EF_S4] = sw->r13; + dump->regs[EF_S5] = sw->r14; + dump->regs[EF_S6] = sw->r15; + dump->regs[EF_A3] = pt->r19; + dump->regs[EF_A4] = pt->r20; + dump->regs[EF_A5] = pt->r21; + dump->regs[EF_T8] = pt->r22; + dump->regs[EF_T9] = pt->r23; + dump->regs[EF_T10] = pt->r24; + dump->regs[EF_T11] = pt->r25; + dump->regs[EF_RA] = pt->r26; + dump->regs[EF_T12] = pt->r27; + dump->regs[EF_AT] = pt->r28; + dump->regs[EF_SP] = rdusp(); + dump->regs[EF_PS] = pt->ps; + dump->regs[EF_PC] = pt->pc; + dump->regs[EF_GP] = pt->gp; + dump->regs[EF_A0] = pt->r16; + dump->regs[EF_A1] = pt->r17; + dump->regs[EF_A2] = pt->r18; + memcpy((char *)dump->regs + EF_SIZE, sw->fp, 32 * 8); +} + +#endif /* __KERNEL__ */ +#endif /* _ASM_A_OUT_CORE_H */ diff --git a/arch/alpha/include/asm/a.out.h b/arch/alpha/include/asm/a.out.h new file mode 100644 index 000000000..9abbd2455 --- /dev/null +++ b/arch/alpha/include/asm/a.out.h @@ -0,0 +1,15 @@ +#ifndef __ALPHA_A_OUT_H__ +#define __ALPHA_A_OUT_H__ + +#include <uapi/asm/a.out.h> + + +/* Assume that start addresses below 4G belong to a TASO application. + Unfortunately, there is no proper bit in the exec header to check. + Worse, we have to notice the start address before swapping to use + /sbin/loader, which of course is _not_ a TASO application. */ +#define SET_AOUT_PERSONALITY(BFPM, EX) \ + set_personality (((BFPM->taso || EX.ah.entry < 0x100000000L \ + ? ADDR_LIMIT_32BIT : 0) | PER_OSF4)) + +#endif /* __A_OUT_GNU_H__ */ diff --git a/arch/alpha/include/asm/agp.h b/arch/alpha/include/asm/agp.h new file mode 100644 index 000000000..a94d48b86 --- /dev/null +++ b/arch/alpha/include/asm/agp.h @@ -0,0 +1,18 @@ +#ifndef AGP_H +#define AGP_H 1 + +#include <asm/io.h> + +/* dummy for now */ + +#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 diff --git a/arch/alpha/include/asm/agp_backend.h b/arch/alpha/include/asm/agp_backend.h new file mode 100644 index 000000000..55dd44a2c --- /dev/null +++ b/arch/alpha/include/asm/agp_backend.h @@ -0,0 +1,42 @@ +#ifndef _ALPHA_AGP_BACKEND_H +#define _ALPHA_AGP_BACKEND_H 1 + +typedef union _alpha_agp_mode { + struct { + u32 rate : 3; + u32 reserved0 : 1; + u32 fw : 1; + u32 fourgb : 1; + u32 reserved1 : 2; + u32 enable : 1; + u32 sba : 1; + u32 reserved2 : 14; + u32 rq : 8; + } bits; + u32 lw; +} alpha_agp_mode; + +typedef struct _alpha_agp_info { + struct pci_controller *hose; + struct { + dma_addr_t bus_base; + unsigned long size; + void *sysdata; + } aperture; + alpha_agp_mode capability; + alpha_agp_mode mode; + void *private; + struct alpha_agp_ops *ops; +} alpha_agp_info; + +struct alpha_agp_ops { + int (*setup)(alpha_agp_info *); + void (*cleanup)(alpha_agp_info *); + int (*configure)(alpha_agp_info *); + int (*bind)(alpha_agp_info *, off_t, struct agp_memory *); + int (*unbind)(alpha_agp_info *, off_t, struct agp_memory *); + unsigned long (*translate)(alpha_agp_info *, dma_addr_t); +}; + + +#endif /* _ALPHA_AGP_BACKEND_H */ diff --git a/arch/alpha/include/asm/asm-offsets.h b/arch/alpha/include/asm/asm-offsets.h new file mode 100644 index 000000000..d370ee36a --- /dev/null +++ b/arch/alpha/include/asm/asm-offsets.h @@ -0,0 +1 @@ +#include <generated/asm-offsets.h> diff --git a/arch/alpha/include/asm/atomic.h b/arch/alpha/include/asm/atomic.h new file mode 100644 index 000000000..8f8eafbed --- /dev/null +++ b/arch/alpha/include/asm/atomic.h @@ -0,0 +1,242 @@ +#ifndef _ALPHA_ATOMIC_H +#define _ALPHA_ATOMIC_H + +#include <linux/types.h> +#include <asm/barrier.h> +#include <asm/cmpxchg.h> + +/* + * Atomic operations that C can't guarantee us. Useful for + * resource counting etc... + * + * But use these as seldom as possible since they are much slower + * than regular operations. + */ + + +#define ATOMIC_INIT(i) { (i) } +#define ATOMIC64_INIT(i) { (i) } + +#define atomic_read(v) ACCESS_ONCE((v)->counter) +#define atomic64_read(v) ACCESS_ONCE((v)->counter) + +#define atomic_set(v,i) ((v)->counter = (i)) +#define atomic64_set(v,i) ((v)->counter = (i)) + +/* + * To get proper branch prediction for the main line, we must branch + * forward to code at the end of this object's .text section, then + * branch back to restart the operation. + */ + +#define ATOMIC_OP(op) \ +static __inline__ void atomic_##op(int i, atomic_t * v) \ +{ \ + unsigned long temp; \ + __asm__ __volatile__( \ + "1: ldl_l %0,%1\n" \ + " " #op "l %0,%2,%0\n" \ + " stl_c %0,%1\n" \ + " beq %0,2f\n" \ + ".subsection 2\n" \ + "2: br 1b\n" \ + ".previous" \ + :"=&r" (temp), "=m" (v->counter) \ + :"Ir" (i), "m" (v->counter)); \ +} \ + +#define ATOMIC_OP_RETURN(op) \ +static inline int atomic_##op##_return(int i, atomic_t *v) \ +{ \ + long temp, result; \ + smp_mb(); \ + __asm__ __volatile__( \ + "1: ldl_l %0,%1\n" \ + " " #op "l %0,%3,%2\n" \ + " " #op "l %0,%3,%0\n" \ + " stl_c %0,%1\n" \ + " beq %0,2f\n" \ + ".subsection 2\n" \ + "2: br 1b\n" \ + ".previous" \ + :"=&r" (temp), "=m" (v->counter), "=&r" (result) \ + :"Ir" (i), "m" (v->counter) : "memory"); \ + smp_mb(); \ + return result; \ +} + +#define ATOMIC64_OP(op) \ +static __inline__ void atomic64_##op(long i, atomic64_t * v) \ +{ \ + unsigned long temp; \ + __asm__ __volatile__( \ + "1: ldq_l %0,%1\n" \ + " " #op "q %0,%2,%0\n" \ + " stq_c %0,%1\n" \ + " beq %0,2f\n" \ + ".subsection 2\n" \ + "2: br 1b\n" \ + ".previous" \ + :"=&r" (temp), "=m" (v->counter) \ + :"Ir" (i), "m" (v->counter)); \ +} \ + +#define ATOMIC64_OP_RETURN(op) \ +static __inline__ long atomic64_##op##_return(long i, atomic64_t * v) \ +{ \ + long temp, result; \ + smp_mb(); \ + __asm__ __volatile__( \ + "1: ldq_l %0,%1\n" \ + " " #op "q %0,%3,%2\n" \ + " " #op "q %0,%3,%0\n" \ + " stq_c %0,%1\n" \ + " beq %0,2f\n" \ + ".subsection 2\n" \ + "2: br 1b\n" \ + ".previous" \ + :"=&r" (temp), "=m" (v->counter), "=&r" (result) \ + :"Ir" (i), "m" (v->counter) : "memory"); \ + smp_mb(); \ + return result; \ +} + +#define ATOMIC_OPS(opg) \ + ATOMIC_OP(opg) \ + ATOMIC_OP_RETURN(opg) \ + ATOMIC64_OP(opg) \ + ATOMIC64_OP_RETURN(opg) + +ATOMIC_OPS(add) +ATOMIC_OPS(sub) + +#undef ATOMIC_OPS +#undef ATOMIC64_OP_RETURN +#undef ATOMIC64_OP +#undef ATOMIC_OP_RETURN +#undef ATOMIC_OP + +#define atomic64_cmpxchg(v, old, new) (cmpxchg(&((v)->counter), old, new)) +#define atomic64_xchg(v, new) (xchg(&((v)->counter), new)) + +#define atomic_cmpxchg(v, old, new) (cmpxchg(&((v)->counter), old, new)) +#define atomic_xchg(v, new) (xchg(&((v)->counter), new)) + +/** + * __atomic_add_unless - add unless the number is a given value + * @v: pointer of type atomic_t + * @a: the amount to add to v... + * @u: ...unless v is equal to u. + * + * Atomically adds @a to @v, so long as it was not @u. + * Returns the old value of @v. + */ +static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u) +{ + int c, new, old; + smp_mb(); + __asm__ __volatile__( + "1: ldl_l %[old],%[mem]\n" + " cmpeq %[old],%[u],%[c]\n" + " addl %[old],%[a],%[new]\n" + " bne %[c],2f\n" + " stl_c %[new],%[mem]\n" + " beq %[new],3f\n" + "2:\n" + ".subsection 2\n" + "3: br 1b\n" + ".previous" + : [old] "=&r"(old), [new] "=&r"(new), [c] "=&r"(c) + : [mem] "m"(*v), [a] "rI"(a), [u] "rI"((long)u) + : "memory"); + smp_mb(); + return old; +} + + +/** + * atomic64_add_unless - add unless the number is a given value + * @v: pointer of type atomic64_t + * @a: the amount to add to v... + * @u: ...unless v is equal to u. + * + * Atomically adds @a to @v, so long as it was not @u. + * Returns true iff @v was not @u. + */ +static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u) +{ + long c, tmp; + smp_mb(); + __asm__ __volatile__( + "1: ldq_l %[tmp],%[mem]\n" + " cmpeq %[tmp],%[u],%[c]\n" + " addq %[tmp],%[a],%[tmp]\n" + " bne %[c],2f\n" + " stq_c %[tmp],%[mem]\n" + " beq %[tmp],3f\n" + "2:\n" + ".subsection 2\n" + "3: br 1b\n" + ".previous" + : [tmp] "=&r"(tmp), [c] "=&r"(c) + : [mem] "m"(*v), [a] "rI"(a), [u] "rI"(u) + : "memory"); + smp_mb(); + return !c; +} + +/* + * atomic64_dec_if_positive - decrement by 1 if old value positive + * @v: pointer of type atomic_t + * + * The function returns the old value of *v minus 1, even if + * the atomic variable, v, was not decremented. + */ +static inline long atomic64_dec_if_positive(atomic64_t *v) +{ + long old, tmp; + smp_mb(); + __asm__ __volatile__( + "1: ldq_l %[old],%[mem]\n" + " subq %[old],1,%[tmp]\n" + " ble %[old],2f\n" + " stq_c %[tmp],%[mem]\n" + " beq %[tmp],3f\n" + "2:\n" + ".subsection 2\n" + "3: br 1b\n" + ".previous" + : [old] "=&r"(old), [tmp] "=&r"(tmp) + : [mem] "m"(*v) + : "memory"); + smp_mb(); + return old - 1; +} + +#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0) + +#define atomic_add_negative(a, v) (atomic_add_return((a), (v)) < 0) +#define atomic64_add_negative(a, v) (atomic64_add_return((a), (v)) < 0) + +#define atomic_dec_return(v) atomic_sub_return(1,(v)) +#define atomic64_dec_return(v) atomic64_sub_return(1,(v)) + +#define atomic_inc_return(v) atomic_add_return(1,(v)) +#define atomic64_inc_return(v) atomic64_add_return(1,(v)) + +#define atomic_sub_and_test(i,v) (atomic_sub_return((i), (v)) == 0) +#define atomic64_sub_and_test(i,v) (atomic64_sub_return((i), (v)) == 0) + +#define atomic_inc_and_test(v) (atomic_add_return(1, (v)) == 0) +#define atomic64_inc_and_test(v) (atomic64_add_return(1, (v)) == 0) + +#define atomic_dec_and_test(v) (atomic_sub_return(1, (v)) == 0) +#define atomic64_dec_and_test(v) (atomic64_sub_return(1, (v)) == 0) + +#define atomic_inc(v) atomic_add(1,(v)) +#define atomic64_inc(v) atomic64_add(1,(v)) + +#define atomic_dec(v) atomic_sub(1,(v)) +#define atomic64_dec(v) atomic64_sub(1,(v)) + +#endif /* _ALPHA_ATOMIC_H */ diff --git a/arch/alpha/include/asm/barrier.h b/arch/alpha/include/asm/barrier.h new file mode 100644 index 000000000..77516c872 --- /dev/null +++ b/arch/alpha/include/asm/barrier.h @@ -0,0 +1,71 @@ +#ifndef __BARRIER_H +#define __BARRIER_H + +#include <asm/compiler.h> + +#define mb() __asm__ __volatile__("mb": : :"memory") +#define rmb() __asm__ __volatile__("mb": : :"memory") +#define wmb() __asm__ __volatile__("wmb": : :"memory") + +/** + * read_barrier_depends - Flush all pending reads that subsequents reads + * depend on. + * + * No data-dependent reads from memory-like regions are ever reordered + * over this barrier. All reads preceding this primitive are guaranteed + * to access memory (but not necessarily other CPUs' caches) before any + * reads following this primitive that depend on the data return by + * any of the preceding reads. This primitive is much lighter weight than + * rmb() on most CPUs, and is never heavier weight than is + * rmb(). + * + * These ordering constraints are respected by both the local CPU + * and the compiler. + * + * Ordering is not guaranteed by anything other than these primitives, + * not even by data dependencies. See the documentation for + * memory_barrier() for examples and URLs to more information. + * + * For example, the following code would force ordering (the initial + * value of "a" is zero, "b" is one, and "p" is "&a"): + * + * <programlisting> + * CPU 0 CPU 1 + * + * b = 2; + * memory_barrier(); + * p = &b; q = p; + * read_barrier_depends(); + * d = *q; + * </programlisting> + * + * because the read of "*q" depends on the read of "p" and these + * two reads are separated by a read_barrier_depends(). However, + * the following code, with the same initial values for "a" and "b": + * + * <programlisting> + * CPU 0 CPU 1 + * + * a = 2; + * memory_barrier(); + * b = 3; y = b; + * read_barrier_depends(); + * x = a; + * </programlisting> + * + * does not enforce ordering, since there is no data dependency between + * the read of "a" and the read of "b". Therefore, on some CPUs, such + * as Alpha, "y" could be set to 3 and "x" to 0. Use rmb() + * in cases like this where there are no data dependencies. + */ +#define read_barrier_depends() __asm__ __volatile__("mb": : :"memory") + +#ifdef CONFIG_SMP +#define __ASM_SMP_MB "\tmb\n" +#else +#define __ASM_SMP_MB +#endif + +#include <asm-generic/barrier.h> + +#endif /* __BARRIER_H */ diff --git a/arch/alpha/include/asm/bitops.h b/arch/alpha/include/asm/bitops.h new file mode 100644 index 000000000..4bdfbd444 --- /dev/null +++ b/arch/alpha/include/asm/bitops.h @@ -0,0 +1,460 @@ +#ifndef _ALPHA_BITOPS_H +#define _ALPHA_BITOPS_H + +#ifndef _LINUX_BITOPS_H +#error only <linux/bitops.h> can be included directly +#endif + +#include <asm/compiler.h> +#include <asm/barrier.h> + +/* + * Copyright 1994, Linus Torvalds. + */ + +/* + * These have to be done with inline assembly: that way the bit-setting + * is guaranteed to be atomic. All bit operations return 0 if the bit + * was cleared before the operation and != 0 if it was not. + * + * To get proper branch prediction for the main line, we must branch + * forward to code at the end of this object's .text section, then + * branch back to restart the operation. + * + * bit 0 is the LSB of addr; bit 64 is the LSB of (addr+1). + */ + +static inline void +set_bit(unsigned long nr, volatile void * addr) +{ + unsigned long temp; + int *m = ((int *) addr) + (nr >> 5); + + __asm__ __volatile__( + "1: ldl_l %0,%3\n" + " bis %0,%2,%0\n" + " stl_c %0,%1\n" + " beq %0,2f\n" + ".subsection 2\n" + "2: br 1b\n" + ".previous" + :"=&r" (temp), "=m" (*m) + :"Ir" (1UL << (nr & 31)), "m" (*m)); +} + +/* + * WARNING: non atomic version. + */ +static inline void +__set_bit(unsigned long nr, volatile void * addr) +{ + int *m = ((int *) addr) + (nr >> 5); + + *m |= 1 << (nr & 31); +} + +static inline void +clear_bit(unsigned long nr, volatile void * addr) +{ + unsigned long temp; + int *m = ((int *) addr) + (nr >> 5); + + __asm__ __volatile__( + "1: ldl_l %0,%3\n" + " bic %0,%2,%0\n" + " stl_c %0,%1\n" + " beq %0,2f\n" + ".subsection 2\n" + "2: br 1b\n" + ".previous" + :"=&r" (temp), "=m" (*m) + :"Ir" (1UL << (nr & 31)), "m" (*m)); +} + +static inline void +clear_bit_unlock(unsigned long nr, volatile void * addr) +{ + smp_mb(); + clear_bit(nr, addr); +} + +/* + * WARNING: non atomic version. + */ +static __inline__ void +__clear_bit(unsigned long nr, volatile void * addr) +{ + int *m = ((int *) addr) + (nr >> 5); + + *m &= ~(1 << (nr & 31)); +} + +static inline void +__clear_bit_unlock(unsigned long nr, volatile void * addr) +{ + smp_mb(); + __clear_bit(nr, addr); +} + +static inline void +change_bit(unsigned long nr, volatile void * addr) +{ + unsigned long temp; + int *m = ((int *) addr) + (nr >> 5); + + __asm__ __volatile__( + "1: ldl_l %0,%3\n" + " xor %0,%2,%0\n" + " stl_c %0,%1\n" + " beq %0,2f\n" + ".subsection 2\n" + "2: br 1b\n" + ".previous" + :"=&r" (temp), "=m" (*m) + :"Ir" (1UL << (nr & 31)), "m" (*m)); +} + +/* + * WARNING: non atomic version. + */ +static __inline__ void +__change_bit(unsigned long nr, volatile void * addr) +{ + int *m = ((int *) addr) + (nr >> 5); + + *m ^= 1 << (nr & 31); +} + +static inline int +test_and_set_bit(unsigned long nr, volatile void *addr) +{ + unsigned long oldbit; + unsigned long temp; + int *m = ((int *) addr) + (nr >> 5); + + __asm__ __volatile__( +#ifdef CONFIG_SMP + " mb\n" +#endif + "1: ldl_l %0,%4\n" + " and %0,%3,%2\n" + " bne %2,2f\n" + " xor %0,%3,%0\n" + " stl_c %0,%1\n" + " beq %0,3f\n" + "2:\n" +#ifdef CONFIG_SMP + " mb\n" +#endif + ".subsection 2\n" + "3: br 1b\n" + ".previous" + :"=&r" (temp), "=m" (*m), "=&r" (oldbit) + :"Ir" (1UL << (nr & 31)), "m" (*m) : "memory"); + + return oldbit != 0; +} + +static inline int +test_and_set_bit_lock(unsigned long nr, volatile void *addr) +{ + unsigned long oldbit; + unsigned long temp; + int *m = ((int *) addr) + (nr >> 5); + + __asm__ __volatile__( + "1: ldl_l %0,%4\n" + " and %0,%3,%2\n" + " bne %2,2f\n" + " xor %0,%3,%0\n" + " stl_c %0,%1\n" + " beq %0,3f\n" + "2:\n" +#ifdef CONFIG_SMP + " mb\n" +#endif + ".subsection 2\n" + "3: br 1b\n" + ".previous" + :"=&r" (temp), "=m" (*m), "=&r" (oldbit) + :"Ir" (1UL << (nr & 31)), "m" (*m) : "memory"); + + return oldbit != 0; +} + +/* + * WARNING: non atomic version. + */ +static inline int +__test_and_set_bit(unsigned long nr, volatile void * addr) +{ + unsigned long mask = 1 << (nr & 0x1f); + int *m = ((int *) addr) + (nr >> 5); + int old = *m; + + *m = old | mask; + return (old & mask) != 0; +} + +static inline int +test_and_clear_bit(unsigned long nr, volatile void * addr) +{ + unsigned long oldbit; + unsigned long temp; + int *m = ((int *) addr) + (nr >> 5); + + __asm__ __volatile__( +#ifdef CONFIG_SMP + " mb\n" +#endif + "1: ldl_l %0,%4\n" + " and %0,%3,%2\n" + " beq %2,2f\n" + " xor %0,%3,%0\n" + " stl_c %0,%1\n" + " beq %0,3f\n" + "2:\n" +#ifdef CONFIG_SMP + " mb\n" +#endif + ".subsection 2\n" + "3: br 1b\n" + ".previous" + :"=&r" (temp), "=m" (*m), "=&r" (oldbit) + :"Ir" (1UL << (nr & 31)), "m" (*m) : "memory"); + + return oldbit != 0; +} + +/* + * WARNING: non atomic version. + */ +static inline int +__test_and_clear_bit(unsigned long nr, volatile void * addr) +{ + unsigned long mask = 1 << (nr & 0x1f); + int *m = ((int *) addr) + (nr >> 5); + int old = *m; + + *m = old & ~mask; + return (old & mask) != 0; +} + +static inline int +test_and_change_bit(unsigned long nr, volatile void * addr) +{ + unsigned long oldbit; + unsigned long temp; + int *m = ((int *) addr) + (nr >> 5); + + __asm__ __volatile__( +#ifdef CONFIG_SMP + " mb\n" +#endif + "1: ldl_l %0,%4\n" + " and %0,%3,%2\n" + " xor %0,%3,%0\n" + " stl_c %0,%1\n" + " beq %0,3f\n" +#ifdef CONFIG_SMP + " mb\n" +#endif + ".subsection 2\n" + "3: br 1b\n" + ".previous" + :"=&r" (temp), "=m" (*m), "=&r" (oldbit) + :"Ir" (1UL << (nr & 31)), "m" (*m) : "memory"); + + return oldbit != 0; +} + +/* + * WARNING: non atomic version. + */ +static __inline__ int +__test_and_change_bit(unsigned long nr, volatile void * addr) +{ + unsigned long mask = 1 << (nr & 0x1f); + int *m = ((int *) addr) + (nr >> 5); + int old = *m; + + *m = old ^ mask; + return (old & mask) != 0; +} + +static inline int +test_bit(int nr, const volatile void * addr) +{ + return (1UL & (((const int *) addr)[nr >> 5] >> (nr & 31))) != 0UL; +} + +/* + * ffz = Find First Zero in word. Undefined if no zero exists, + * so code should check against ~0UL first.. + * + * Do a binary search on the bits. Due to the nature of large + * constants on the alpha, it is worthwhile to split the search. + */ +static inline unsigned long ffz_b(unsigned long x) +{ + unsigned long sum, x1, x2, x4; + + x = ~x & -~x; /* set first 0 bit, clear others */ + x1 = x & 0xAA; + x2 = x & 0xCC; + x4 = x & 0xF0; + sum = x2 ? 2 : 0; + sum += (x4 != 0) * 4; + sum += (x1 != 0); + + return sum; +} + +static inline unsigned long ffz(unsigned long word) +{ +#if defined(CONFIG_ALPHA_EV6) && defined(CONFIG_ALPHA_EV67) + /* Whee. EV67 can calculate it directly. */ + return __kernel_cttz(~word); +#else + unsigned long bits, qofs, bofs; + + bits = __kernel_cmpbge(word, ~0UL); + qofs = ffz_b(bits); + bits = __kernel_extbl(word, qofs); + bofs = ffz_b(bits); + + return qofs*8 + bofs; +#endif +} + +/* + * __ffs = Find First set bit in word. Undefined if no set bit exists. + */ +static inline unsigned long __ffs(unsigned long word) +{ +#if defined(CONFIG_ALPHA_EV6) && defined(CONFIG_ALPHA_EV67) + /* Whee. EV67 can calculate it directly. */ + return __kernel_cttz(word); +#else + unsigned long bits, qofs, bofs; + + bits = __kernel_cmpbge(0, word); + qofs = ffz_b(bits); + bits = __kernel_extbl(word, qofs); + bofs = ffz_b(~bits); + + return qofs*8 + bofs; +#endif +} + +#ifdef __KERNEL__ + +/* + * ffs: find first bit set. This is defined the same way as + * the libc and compiler builtin ffs routines, therefore + * differs in spirit from the above __ffs. + */ + +static inline int ffs(int word) +{ + int result = __ffs(word) + 1; + return word ? result : 0; +} + +/* + * fls: find last bit set. + */ +#if defined(CONFIG_ALPHA_EV6) && defined(CONFIG_ALPHA_EV67) +static inline int fls64(unsigned long word) +{ + return 64 - __kernel_ctlz(word); +} +#else +extern const unsigned char __flsm1_tab[256]; + +static inline int fls64(unsigned long x) +{ + unsigned long t, a, r; + + t = __kernel_cmpbge (x, 0x0101010101010101UL); + a = __flsm1_tab[t]; + t = __kernel_extbl (x, a); + r = a*8 + __flsm1_tab[t] + (x != 0); + + return r; +} +#endif + +static inline unsigned long __fls(unsigned long x) +{ + return fls64(x) - 1; +} + +static inline int fls(int x) +{ + return fls64((unsigned int) x); +} + +/* + * hweightN: returns the hamming weight (i.e. the number + * of bits set) of a N-bit word + */ + +#if defined(CONFIG_ALPHA_EV6) && defined(CONFIG_ALPHA_EV67) +/* Whee. EV67 can calculate it directly. */ +static inline unsigned long __arch_hweight64(unsigned long w) +{ + return __kernel_ctpop(w); +} + +static inline unsigned int __arch_hweight32(unsigned int w) +{ + return __arch_hweight64(w); +} + +static inline unsigned int __arch_hweight16(unsigned int w) +{ + return __arch_hweight64(w & 0xffff); +} + +static inline unsigned int __arch_hweight8(unsigned int w) +{ + return __arch_hweight64(w & 0xff); +} +#else +#include <asm-generic/bitops/arch_hweight.h> +#endif + +#include <asm-generic/bitops/const_hweight.h> + +#endif /* __KERNEL__ */ + +#include <asm-generic/bitops/find.h> + +#ifdef __KERNEL__ + +/* + * Every architecture must define this function. It's the fastest + * way of searching a 100-bit bitmap. It's guaranteed that at least + * one of the 100 bits is cleared. + */ +static inline unsigned long +sched_find_first_bit(const unsigned long b[2]) +{ + unsigned long b0, b1, ofs, tmp; + + b0 = b[0]; + b1 = b[1]; + ofs = (b0 ? 0 : 64); + tmp = (b0 ? b0 : b1); + + return __ffs(tmp) + ofs; +} + +#include <asm-generic/bitops/le.h> + +#include <asm-generic/bitops/ext2-atomic-setbit.h> + +#endif /* __KERNEL__ */ + +#endif /* _ALPHA_BITOPS_H */ diff --git a/arch/alpha/include/asm/bug.h b/arch/alpha/include/asm/bug.h new file mode 100644 index 000000000..f091682e3 --- /dev/null +++ b/arch/alpha/include/asm/bug.h @@ -0,0 +1,24 @@ +#ifndef _ALPHA_BUG_H +#define _ALPHA_BUG_H + +#include <linux/linkage.h> + +#ifdef CONFIG_BUG +#include <asm/pal.h> + +/* ??? Would be nice to use .gprel32 here, but we can't be sure that the + function loaded the GP, so this could fail in modules. */ +#define BUG() do { \ + __asm__ __volatile__( \ + "call_pal %0 # bugchk\n\t" \ + ".long %1\n\t.8byte %2" \ + : : "i"(PAL_bugchk), "i"(__LINE__), "i"(__FILE__)); \ + unreachable(); \ + } while (0) + +#define HAVE_ARCH_BUG +#endif + +#include <asm-generic/bug.h> + +#endif diff --git a/arch/alpha/include/asm/bugs.h b/arch/alpha/include/asm/bugs.h new file mode 100644 index 000000000..78030d1c7 --- /dev/null +++ b/arch/alpha/include/asm/bugs.h @@ -0,0 +1,20 @@ +/* + * include/asm-alpha/bugs.h + * + * Copyright (C) 1994 Linus Torvalds + */ + +/* + * This is included by init/main.c to check for architecture-dependent bugs. + * + * Needs: + * void check_bugs(void); + */ + +/* + * I don't know of any alpha bugs yet.. Nice chip + */ + +static void check_bugs(void) +{ +} diff --git a/arch/alpha/include/asm/cache.h b/arch/alpha/include/asm/cache.h new file mode 100644 index 000000000..ad368a93a --- /dev/null +++ b/arch/alpha/include/asm/cache.h @@ -0,0 +1,22 @@ +/* + * include/asm-alpha/cache.h + */ +#ifndef __ARCH_ALPHA_CACHE_H +#define __ARCH_ALPHA_CACHE_H + + +/* Bytes per L1 (data) cache line. */ +#if defined(CONFIG_ALPHA_GENERIC) || defined(CONFIG_ALPHA_EV6) +# define L1_CACHE_BYTES 64 +# define L1_CACHE_SHIFT 6 +#else +/* Both EV4 and EV5 are write-through, read-allocate, + direct-mapped, physical. +*/ +# define L1_CACHE_BYTES 32 +# define L1_CACHE_SHIFT 5 +#endif + +#define SMP_CACHE_BYTES L1_CACHE_BYTES + +#endif diff --git a/arch/alpha/include/asm/cacheflush.h b/arch/alpha/include/asm/cacheflush.h new file mode 100644 index 000000000..a9cb6aa44 --- /dev/null +++ b/arch/alpha/include/asm/cacheflush.h @@ -0,0 +1,77 @@ +#ifndef _ALPHA_CACHEFLUSH_H +#define _ALPHA_CACHEFLUSH_H + +#include <linux/mm.h> + +/* Caches aren't brain-dead on the Alpha. */ +#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 ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0 +#define flush_dcache_page(page) do { } while (0) +#define flush_dcache_mmap_lock(mapping) do { } while (0) +#define flush_dcache_mmap_unlock(mapping) do { } while (0) +#define flush_cache_vmap(start, end) do { } while (0) +#define flush_cache_vunmap(start, end) do { } while (0) + +/* Note that the following two definitions are _highly_ dependent + on the contexts in which they are used in the kernel. I personally + think it is criminal how loosely defined these macros are. */ + +/* We need to flush the kernel's icache after loading modules. The + only other use of this macro is in load_aout_interp which is not + used on Alpha. + + Note that this definition should *not* be used for userspace + icache flushing. While functional, it is _way_ overkill. The + icache is tagged with ASNs and it suffices to allocate a new ASN + for the process. */ +#ifndef CONFIG_SMP +#define flush_icache_range(start, end) imb() +#else +#define flush_icache_range(start, end) smp_imb() +extern void smp_imb(void); +#endif + +/* We need to flush the userspace icache after setting breakpoints in + ptrace. + + Instead of indiscriminately using imb, take advantage of the fact + that icache entries are tagged with the ASN and load a new mm context. */ +/* ??? Ought to use this in arch/alpha/kernel/signal.c too. */ + +#ifndef CONFIG_SMP +#include <linux/sched.h> + +extern void __load_new_mm_context(struct mm_struct *); +static inline void +flush_icache_user_range(struct vm_area_struct *vma, struct page *page, + unsigned long addr, int len) +{ + if (vma->vm_flags & VM_EXEC) { + struct mm_struct *mm = vma->vm_mm; + if (current->active_mm == mm) + __load_new_mm_context(mm); + else + mm->context[smp_processor_id()] = 0; + } +} +#else +extern void flush_icache_user_range(struct vm_area_struct *vma, + struct page *page, unsigned long addr, int len); +#endif + +/* This is used only in __do_fault and do_swap_page. */ +#define flush_icache_page(vma, page) \ + flush_icache_user_range((vma), (page), 0, 0) + +#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) + +#endif /* _ALPHA_CACHEFLUSH_H */ diff --git a/arch/alpha/include/asm/checksum.h b/arch/alpha/include/asm/checksum.h new file mode 100644 index 000000000..d3854bbf0 --- /dev/null +++ b/arch/alpha/include/asm/checksum.h @@ -0,0 +1,75 @@ +#ifndef _ALPHA_CHECKSUM_H +#define _ALPHA_CHECKSUM_H + +#include <linux/in6.h> + +/* + * This is a version of ip_compute_csum() optimized for IP headers, + * which always checksum on 4 octet boundaries. + */ +extern __sum16 ip_fast_csum(const void *iph, unsigned int ihl); + +/* + * computes the checksum of the TCP/UDP pseudo-header + * returns a 16-bit checksum, already complemented + */ +extern __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr, + unsigned short len, + unsigned short proto, + __wsum sum); + +__wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr, + unsigned short len, unsigned short proto, + __wsum sum); + +/* + * computes the checksum of a memory block at buff, length len, + * and adds in "sum" (32-bit) + * + * returns a 32-bit number suitable for feeding into itself + * or csum_tcpudp_magic + * + * this function must be called with even lengths, except + * for the last fragment, which may be odd + * + * it's best to have buff aligned on a 32-bit boundary + */ +extern __wsum csum_partial(const void *buff, int len, __wsum sum); + +/* + * the same as csum_partial, but copies from src while it + * checksums + * + * here even more important to align src and dst on a 32-bit (or even + * better 64-bit) boundary + */ +__wsum csum_partial_copy_from_user(const void __user *src, void *dst, int len, __wsum sum, int *errp); + +__wsum csum_partial_copy_nocheck(const void *src, void *dst, int len, __wsum sum); + + +/* + * this routine is used for miscellaneous IP-like checksums, mainly + * in icmp.c + */ + +extern __sum16 ip_compute_csum(const void *buff, int len); + +/* + * Fold a partial checksum without adding pseudo headers + */ + +static inline __sum16 csum_fold(__wsum csum) +{ + u32 sum = (__force u32)csum; + sum = (sum & 0xffff) + (sum >> 16); + sum = (sum & 0xffff) + (sum >> 16); + return (__force __sum16)~sum; +} + +#define _HAVE_ARCH_IPV6_CSUM +extern __sum16 csum_ipv6_magic(const struct in6_addr *saddr, + const struct in6_addr *daddr, + __u32 len, unsigned short proto, + __wsum sum); +#endif diff --git a/arch/alpha/include/asm/cmpxchg.h b/arch/alpha/include/asm/cmpxchg.h new file mode 100644 index 000000000..429e8cd0d --- /dev/null +++ b/arch/alpha/include/asm/cmpxchg.h @@ -0,0 +1,71 @@ +#ifndef _ALPHA_CMPXCHG_H +#define _ALPHA_CMPXCHG_H + +/* + * Atomic exchange routines. + */ + +#define __ASM__MB +#define ____xchg(type, args...) __xchg ## type ## _local(args) +#define ____cmpxchg(type, args...) __cmpxchg ## type ## _local(args) +#include <asm/xchg.h> + +#define xchg_local(ptr, x) \ +({ \ + __typeof__(*(ptr)) _x_ = (x); \ + (__typeof__(*(ptr))) __xchg_local((ptr), (unsigned long)_x_, \ + sizeof(*(ptr))); \ +}) + +#define cmpxchg_local(ptr, o, n) \ +({ \ + __typeof__(*(ptr)) _o_ = (o); \ + __typeof__(*(ptr)) _n_ = (n); \ + (__typeof__(*(ptr))) __cmpxchg_local((ptr), (unsigned long)_o_, \ + (unsigned long)_n_, \ + sizeof(*(ptr))); \ +}) + +#define cmpxchg64_local(ptr, o, n) \ +({ \ + BUILD_BUG_ON(sizeof(*(ptr)) != 8); \ + cmpxchg_local((ptr), (o), (n)); \ +}) + +#ifdef CONFIG_SMP +#undef __ASM__MB +#define __ASM__MB "\tmb\n" +#endif +#undef ____xchg +#undef ____cmpxchg +#define ____xchg(type, args...) __xchg ##type(args) +#define ____cmpxchg(type, args...) __cmpxchg ##type(args) +#include <asm/xchg.h> + +#define xchg(ptr, x) \ +({ \ + __typeof__(*(ptr)) _x_ = (x); \ + (__typeof__(*(ptr))) __xchg((ptr), (unsigned long)_x_, \ + sizeof(*(ptr))); \ +}) + +#define cmpxchg(ptr, o, n) \ +({ \ + __typeof__(*(ptr)) _o_ = (o); \ + __typeof__(*(ptr)) _n_ = (n); \ + (__typeof__(*(ptr))) __cmpxchg((ptr), (unsigned long)_o_, \ + (unsigned long)_n_, sizeof(*(ptr)));\ +}) + +#define cmpxchg64(ptr, o, n) \ +({ \ + BUILD_BUG_ON(sizeof(*(ptr)) != 8); \ + cmpxchg((ptr), (o), (n)); \ +}) + +#undef __ASM__MB +#undef ____cmpxchg + +#define __HAVE_ARCH_CMPXCHG 1 + +#endif /* _ALPHA_CMPXCHG_H */ diff --git a/arch/alpha/include/asm/compiler.h b/arch/alpha/include/asm/compiler.h new file mode 100644 index 000000000..a7720b96b --- /dev/null +++ b/arch/alpha/include/asm/compiler.h @@ -0,0 +1,17 @@ +#ifndef __ALPHA_COMPILER_H +#define __ALPHA_COMPILER_H + +#include <uapi/asm/compiler.h> + +/* Some idiots over in <linux/compiler.h> thought inline should imply + always_inline. This breaks stuff. We'll include this file whenever + we run into such problems. */ + +#include <linux/compiler.h> +#undef inline +#undef __inline__ +#undef __inline +#undef __always_inline +#define __always_inline inline __attribute__((always_inline)) + +#endif /* __ALPHA_COMPILER_H */ diff --git a/arch/alpha/include/asm/console.h b/arch/alpha/include/asm/console.h new file mode 100644 index 000000000..f2b584fe0 --- /dev/null +++ b/arch/alpha/include/asm/console.h @@ -0,0 +1,29 @@ +#ifndef __AXP_CONSOLE_H +#define __AXP_CONSOLE_H + +#include <uapi/asm/console.h> + +#ifndef __ASSEMBLY__ +extern long callback_puts(long unit, const char *s, long length); +extern long callback_getc(long unit); +extern long callback_open_console(void); +extern long callback_close_console(void); +extern long callback_open(const char *device, long length); +extern long callback_close(long unit); +extern long callback_read(long channel, long count, const char *buf, long lbn); +extern long callback_getenv(long id, const char *buf, unsigned long buf_size); +extern long callback_setenv(long id, const char *buf, unsigned long buf_size); +extern long callback_save_env(void); + +extern int srm_fixup(unsigned long new_callback_addr, + unsigned long new_hwrpb_addr); +extern long srm_puts(const char *, long); +extern long srm_printk(const char *, ...) + __attribute__ ((format (printf, 1, 2))); + +struct crb_struct; +struct hwrpb_struct; +extern int callback_init_done; +extern void * callback_init(void *); +#endif /* __ASSEMBLY__ */ +#endif /* __AXP_CONSOLE_H */ diff --git a/arch/alpha/include/asm/core_apecs.h b/arch/alpha/include/asm/core_apecs.h new file mode 100644 index 000000000..6785ff7e0 --- /dev/null +++ b/arch/alpha/include/asm/core_apecs.h @@ -0,0 +1,517 @@ +#ifndef __ALPHA_APECS__H__ +#define __ALPHA_APECS__H__ + +#include <linux/types.h> +#include <asm/compiler.h> + +/* + * APECS is the internal name for the 2107x chipset which provides + * memory controller and PCI access for the 21064 chip based systems. + * + * This file is based on: + * + * DECchip 21071-AA and DECchip 21072-AA Core Logic Chipsets + * Data Sheet + * + * EC-N0648-72 + * + * + * david.rusling@reo.mts.dec.com Initial Version. + * + */ + +/* + An AVANTI *might* be an XL, and an XL has only 27 bits of ISA address + that get passed through the PCI<->ISA bridge chip. So we've gotta use + both windows to max out the physical memory we can DMA to. Sigh... + + If we try a window at 0 for 1GB as a work-around, we run into conflicts + with ISA/PCI bus memory which can't be relocated, like VGA aperture and + BIOS ROMs. So we must put the windows high enough to avoid these areas. + + We put window 1 at BUS 64Mb for 64Mb, mapping physical 0 to 64Mb-1, + and window 2 at BUS 1Gb for 1Gb, mapping physical 0 to 1Gb-1. + Yes, this does map 0 to 64Mb-1 twice, but only window 1 will actually + be used for that range (via virt_to_bus()). + + Note that we actually fudge the window 1 maximum as 48Mb instead of 64Mb, + to keep virt_to_bus() from returning an address in the first window, for + a data area that goes beyond the 64Mb first DMA window. Sigh... + The fudge factor MUST match with <asm/dma.h> MAX_DMA_ADDRESS, but + we can't just use that here, because of header file looping... :-( + + Window 1 will be used for all DMA from the ISA bus; yes, that does + limit what memory an ISA floppy or sound card or Ethernet can touch, but + it's also a known limitation on other platforms as well. We use the + same technique that is used on INTEL platforms with similar limitation: + set MAX_DMA_ADDRESS and clear some pages' DMAable flags during mem_init(). + We trust that any ISA bus device drivers will *always* ask for DMAable + memory explicitly via kmalloc()/get_free_pages() flags arguments. + + Note that most PCI bus devices' drivers do *not* explicitly ask for + DMAable memory; they count on being able to DMA to any memory they + get from kmalloc()/get_free_pages(). They will also use window 1 for + any physical memory accesses below 64Mb; the rest will be handled by + window 2, maxing out at 1Gb of memory. I trust this is enough... :-) + + We hope that the area before the first window is large enough so that + there will be no overlap at the top end (64Mb). We *must* locate the + PCI cards' memory just below window 1, so that there's still the + possibility of being able to access it via SPARSE space. This is + important for cards such as the Matrox Millennium, whose Xserver + wants to access memory-mapped registers in byte and short lengths. + + Note that the XL is treated differently from the AVANTI, even though + for most other things they are identical. It didn't seem reasonable to + make the AVANTI support pay for the limitations of the XL. It is true, + however, that an XL kernel will run on an AVANTI without problems. + + %%% All of this should be obviated by the ability to route + everything through the iommu. +*/ + +/* + * 21071-DA Control and Status registers. + * These are used for PCI memory access. + */ +#define APECS_IOC_DCSR (IDENT_ADDR + 0x1A0000000UL) +#define APECS_IOC_PEAR (IDENT_ADDR + 0x1A0000020UL) +#define APECS_IOC_SEAR (IDENT_ADDR + 0x1A0000040UL) +#define APECS_IOC_DR1 (IDENT_ADDR + 0x1A0000060UL) +#define APECS_IOC_DR2 (IDENT_ADDR + 0x1A0000080UL) +#define APECS_IOC_DR3 (IDENT_ADDR + 0x1A00000A0UL) + +#define APECS_IOC_TB1R (IDENT_ADDR + 0x1A00000C0UL) +#define APECS_IOC_TB2R (IDENT_ADDR + 0x1A00000E0UL) + +#define APECS_IOC_PB1R (IDENT_ADDR + 0x1A0000100UL) +#define APECS_IOC_PB2R (IDENT_ADDR + 0x1A0000120UL) + +#define APECS_IOC_PM1R (IDENT_ADDR + 0x1A0000140UL) +#define APECS_IOC_PM2R (IDENT_ADDR + 0x1A0000160UL) + +#define APECS_IOC_HAXR0 (IDENT_ADDR + 0x1A0000180UL) +#define APECS_IOC_HAXR1 (IDENT_ADDR + 0x1A00001A0UL) +#define APECS_IOC_HAXR2 (IDENT_ADDR + 0x1A00001C0UL) + +#define APECS_IOC_PMLT (IDENT_ADDR + 0x1A00001E0UL) + +#define APECS_IOC_TLBTAG0 (IDENT_ADDR + 0x1A0000200UL) +#define APECS_IOC_TLBTAG1 (IDENT_ADDR + 0x1A0000220UL) +#define APECS_IOC_TLBTAG2 (IDENT_ADDR + 0x1A0000240UL) +#define APECS_IOC_TLBTAG3 (IDENT_ADDR + 0x1A0000260UL) +#define APECS_IOC_TLBTAG4 (IDENT_ADDR + 0x1A0000280UL) +#define APECS_IOC_TLBTAG5 (IDENT_ADDR + 0x1A00002A0UL) +#define APECS_IOC_TLBTAG6 (IDENT_ADDR + 0x1A00002C0UL) +#define APECS_IOC_TLBTAG7 (IDENT_ADDR + 0x1A00002E0UL) + +#define APECS_IOC_TLBDATA0 (IDENT_ADDR + 0x1A0000300UL) +#define APECS_IOC_TLBDATA1 (IDENT_ADDR + 0x1A0000320UL) +#define APECS_IOC_TLBDATA2 (IDENT_ADDR + 0x1A0000340UL) +#define APECS_IOC_TLBDATA3 (IDENT_ADDR + 0x1A0000360UL) +#define APECS_IOC_TLBDATA4 (IDENT_ADDR + 0x1A0000380UL) +#define APECS_IOC_TLBDATA5 (IDENT_ADDR + 0x1A00003A0UL) +#define APECS_IOC_TLBDATA6 (IDENT_ADDR + 0x1A00003C0UL) +#define APECS_IOC_TLBDATA7 (IDENT_ADDR + 0x1A00003E0UL) + +#define APECS_IOC_TBIA (IDENT_ADDR + 0x1A0000400UL) + + +/* + * 21071-CA Control and Status registers. + * These are used to program memory timing, + * configure memory and initialise the B-Cache. + */ +#define APECS_MEM_GCR (IDENT_ADDR + 0x180000000UL) +#define APECS_MEM_EDSR (IDENT_ADDR + 0x180000040UL) +#define APECS_MEM_TAR (IDENT_ADDR + 0x180000060UL) +#define APECS_MEM_ELAR (IDENT_ADDR + 0x180000080UL) +#define APECS_MEM_EHAR (IDENT_ADDR + 0x1800000a0UL) +#define APECS_MEM_SFT_RST (IDENT_ADDR + 0x1800000c0UL) +#define APECS_MEM_LDxLAR (IDENT_ADDR + 0x1800000e0UL) +#define APECS_MEM_LDxHAR (IDENT_ADDR + 0x180000100UL) +#define APECS_MEM_GTR (IDENT_ADDR + 0x180000200UL) +#define APECS_MEM_RTR (IDENT_ADDR + 0x180000220UL) +#define APECS_MEM_VFPR (IDENT_ADDR + 0x180000240UL) +#define APECS_MEM_PDLDR (IDENT_ADDR + 0x180000260UL) +#define APECS_MEM_PDhDR (IDENT_ADDR + 0x180000280UL) + +/* Bank x Base Address Register */ +#define APECS_MEM_B0BAR (IDENT_ADDR + 0x180000800UL) +#define APECS_MEM_B1BAR (IDENT_ADDR + 0x180000820UL) +#define APECS_MEM_B2BAR (IDENT_ADDR + 0x180000840UL) +#define APECS_MEM_B3BAR (IDENT_ADDR + 0x180000860UL) +#define APECS_MEM_B4BAR (IDENT_ADDR + 0x180000880UL) +#define APECS_MEM_B5BAR (IDENT_ADDR + 0x1800008A0UL) +#define APECS_MEM_B6BAR (IDENT_ADDR + 0x1800008C0UL) +#define APECS_MEM_B7BAR (IDENT_ADDR + 0x1800008E0UL) +#define APECS_MEM_B8BAR (IDENT_ADDR + 0x180000900UL) + +/* Bank x Configuration Register */ +#define APECS_MEM_B0BCR (IDENT_ADDR + 0x180000A00UL) +#define APECS_MEM_B1BCR (IDENT_ADDR + 0x180000A20UL) +#define APECS_MEM_B2BCR (IDENT_ADDR + 0x180000A40UL) +#define APECS_MEM_B3BCR (IDENT_ADDR + 0x180000A60UL) +#define APECS_MEM_B4BCR (IDENT_ADDR + 0x180000A80UL) +#define APECS_MEM_B5BCR (IDENT_ADDR + 0x180000AA0UL) +#define APECS_MEM_B6BCR (IDENT_ADDR + 0x180000AC0UL) +#define APECS_MEM_B7BCR (IDENT_ADDR + 0x180000AE0UL) +#define APECS_MEM_B8BCR (IDENT_ADDR + 0x180000B00UL) + +/* Bank x Timing Register A */ +#define APECS_MEM_B0TRA (IDENT_ADDR + 0x180000C00UL) +#define APECS_MEM_B1TRA (IDENT_ADDR + 0x180000C20UL) +#define APECS_MEM_B2TRA (IDENT_ADDR + 0x180000C40UL) +#define APECS_MEM_B3TRA (IDENT_ADDR + 0x180000C60UL) +#define APECS_MEM_B4TRA (IDENT_ADDR + 0x180000C80UL) +#define APECS_MEM_B5TRA (IDENT_ADDR + 0x180000CA0UL) +#define APECS_MEM_B6TRA (IDENT_ADDR + 0x180000CC0UL) +#define APECS_MEM_B7TRA (IDENT_ADDR + 0x180000CE0UL) +#define APECS_MEM_B8TRA (IDENT_ADDR + 0x180000D00UL) + +/* Bank x Timing Register B */ +#define APECS_MEM_B0TRB (IDENT_ADDR + 0x180000E00UL) +#define APECS_MEM_B1TRB (IDENT_ADDR + 0x180000E20UL) +#define APECS_MEM_B2TRB (IDENT_ADDR + 0x180000E40UL) +#define APECS_MEM_B3TRB (IDENT_ADDR + 0x180000E60UL) +#define APECS_MEM_B4TRB (IDENT_ADDR + 0x180000E80UL) +#define APECS_MEM_B5TRB (IDENT_ADDR + 0x180000EA0UL) +#define APECS_MEM_B6TRB (IDENT_ADDR + 0x180000EC0UL) +#define APECS_MEM_B7TRB (IDENT_ADDR + 0x180000EE0UL) +#define APECS_MEM_B8TRB (IDENT_ADDR + 0x180000F00UL) + + +/* + * Memory spaces: + */ +#define APECS_IACK_SC (IDENT_ADDR + 0x1b0000000UL) +#define APECS_CONF (IDENT_ADDR + 0x1e0000000UL) +#define APECS_IO (IDENT_ADDR + 0x1c0000000UL) +#define APECS_SPARSE_MEM (IDENT_ADDR + 0x200000000UL) +#define APECS_DENSE_MEM (IDENT_ADDR + 0x300000000UL) + + +/* + * Bit definitions for I/O Controller status register 0: + */ +#define APECS_IOC_STAT0_CMD 0xf +#define APECS_IOC_STAT0_ERR (1<<4) +#define APECS_IOC_STAT0_LOST (1<<5) +#define APECS_IOC_STAT0_THIT (1<<6) +#define APECS_IOC_STAT0_TREF (1<<7) +#define APECS_IOC_STAT0_CODE_SHIFT 8 +#define APECS_IOC_STAT0_CODE_MASK 0x7 +#define APECS_IOC_STAT0_P_NBR_SHIFT 13 +#define APECS_IOC_STAT0_P_NBR_MASK 0x7ffff + +#define APECS_HAE_ADDRESS APECS_IOC_HAXR1 + + +/* + * Data structure for handling APECS machine checks: + */ + +struct el_apecs_mikasa_sysdata_mcheck +{ + unsigned long coma_gcr; + unsigned long coma_edsr; + unsigned long coma_ter; + unsigned long coma_elar; + unsigned long coma_ehar; + unsigned long coma_ldlr; + unsigned long coma_ldhr; + unsigned long coma_base0; + unsigned long coma_base1; + unsigned long coma_base2; + unsigned long coma_base3; + unsigned long coma_cnfg0; + unsigned long coma_cnfg1; + unsigned long coma_cnfg2; + unsigned long coma_cnfg3; + unsigned long epic_dcsr; + unsigned long epic_pear; + unsigned long epic_sear; + unsigned long epic_tbr1; + unsigned long epic_tbr2; + unsigned long epic_pbr1; + unsigned long epic_pbr2; + unsigned long epic_pmr1; + unsigned long epic_pmr2; + unsigned long epic_harx1; + unsigned long epic_harx2; + unsigned long epic_pmlt; + unsigned long epic_tag0; + unsigned long epic_tag1; + unsigned long epic_tag2; + unsigned long epic_tag3; + unsigned long epic_tag4; + unsigned long epic_tag5; + unsigned long epic_tag6; + unsigned long epic_tag7; + unsigned long epic_data0; + unsigned long epic_data1; + unsigned long epic_data2; + unsigned long epic_data3; + unsigned long epic_data4; + unsigned long epic_data5; + unsigned long epic_data6; + unsigned long epic_data7; + + unsigned long pceb_vid; + unsigned long pceb_did; + unsigned long pceb_revision; + unsigned long pceb_command; + unsigned long pceb_status; + unsigned long pceb_latency; + unsigned long pceb_control; + unsigned long pceb_arbcon; + unsigned long pceb_arbpri; + + unsigned long esc_id; + unsigned long esc_revision; + unsigned long esc_int0; + unsigned long esc_int1; + unsigned long esc_elcr0; + unsigned long esc_elcr1; + unsigned long esc_last_eisa; + unsigned long esc_nmi_stat; + + unsigned long pci_ir; + unsigned long pci_imr; + unsigned long svr_mgr; +}; + +/* This for the normal APECS machines. */ +struct el_apecs_sysdata_mcheck +{ + unsigned long coma_gcr; + unsigned long coma_edsr; + unsigned long coma_ter; + unsigned long coma_elar; + unsigned long coma_ehar; + unsigned long coma_ldlr; + unsigned long coma_ldhr; + unsigned long coma_base0; + unsigned long coma_base1; + unsigned long coma_base2; + unsigned long coma_cnfg0; + unsigned long coma_cnfg1; + unsigned long coma_cnfg2; + unsigned long epic_dcsr; + unsigned long epic_pear; + unsigned long epic_sear; + unsigned long epic_tbr1; + unsigned long epic_tbr2; + unsigned long epic_pbr1; + unsigned long epic_pbr2; + unsigned long epic_pmr1; + unsigned long epic_pmr2; + unsigned long epic_harx1; + unsigned long epic_harx2; + unsigned long epic_pmlt; + unsigned long epic_tag0; + unsigned long epic_tag1; + unsigned long epic_tag2; + unsigned long epic_tag3; + unsigned long epic_tag4; + unsigned long epic_tag5; + unsigned long epic_tag6; + unsigned long epic_tag7; + unsigned long epic_data0; + unsigned long epic_data1; + unsigned long epic_data2; + unsigned long epic_data3; + unsigned long epic_data4; + unsigned long epic_data5; + unsigned long epic_data6; + unsigned long epic_data7; +}; + +struct el_apecs_procdata +{ + unsigned long paltemp[32]; /* PAL TEMP REGS. */ + /* EV4-specific fields */ + unsigned long exc_addr; /* Address of excepting instruction. */ + unsigned long exc_sum; /* Summary of arithmetic traps. */ + unsigned long exc_mask; /* Exception mask (from exc_sum). */ + unsigned long iccsr; /* IBox hardware enables. */ + unsigned long pal_base; /* Base address for PALcode. */ + unsigned long hier; /* Hardware Interrupt Enable. */ + unsigned long hirr; /* Hardware Interrupt Request. */ + unsigned long csr; /* D-stream fault info. */ + unsigned long dc_stat; /* D-cache status (ECC/Parity Err). */ + unsigned long dc_addr; /* EV3 Phys Addr for ECC/DPERR. */ + unsigned long abox_ctl; /* ABox Control Register. */ + unsigned long biu_stat; /* BIU Status. */ + unsigned long biu_addr; /* BUI Address. */ + unsigned long biu_ctl; /* BIU Control. */ + unsigned long fill_syndrome;/* For correcting ECC errors. */ + unsigned long fill_addr; /* Cache block which was being read */ + unsigned long va; /* Effective VA of fault or miss. */ + unsigned long bc_tag; /* Backup Cache Tag Probe Results.*/ +}; + + +#ifdef __KERNEL__ + +#ifndef __EXTERN_INLINE +#define __EXTERN_INLINE extern inline +#define __IO_EXTERN_INLINE +#endif + +/* + * I/O functions: + * + * Unlike Jensen, the APECS machines have no concept of local + * I/O---everything goes over the PCI bus. + * + * There is plenty room for optimization here. In particular, + * the Alpha's insb/insw/extb/extw should be useful in moving + * data to/from the right byte-lanes. + */ + +#define vip volatile int __force * +#define vuip volatile unsigned int __force * +#define vulp volatile unsigned long __force * + +#define APECS_SET_HAE \ + do { \ + if (addr >= (1UL << 24)) { \ + unsigned long msb = addr & 0xf8000000; \ + addr -= msb; \ + set_hae(msb); \ + } \ + } while (0) + +__EXTERN_INLINE unsigned int apecs_ioread8(void __iomem *xaddr) +{ + unsigned long addr = (unsigned long) xaddr; + unsigned long result, base_and_type; + + if (addr >= APECS_DENSE_MEM) { + addr -= APECS_DENSE_MEM; + APECS_SET_HAE; + base_and_type = APECS_SPARSE_MEM + 0x00; + } else { + addr -= APECS_IO; + base_and_type = APECS_IO + 0x00; + } + + result = *(vip) ((addr << 5) + base_and_type); + return __kernel_extbl(result, addr & 3); +} + +__EXTERN_INLINE void apecs_iowrite8(u8 b, void __iomem *xaddr) +{ + unsigned long addr = (unsigned long) xaddr; + unsigned long w, base_and_type; + + if (addr >= APECS_DENSE_MEM) { + addr -= APECS_DENSE_MEM; + APECS_SET_HAE; + base_and_type = APECS_SPARSE_MEM + 0x00; + } else { + addr -= APECS_IO; + base_and_type = APECS_IO + 0x00; + } + + w = __kernel_insbl(b, addr & 3); + *(vuip) ((addr << 5) + base_and_type) = w; +} + +__EXTERN_INLINE unsigned int apecs_ioread16(void __iomem *xaddr) +{ + unsigned long addr = (unsigned long) xaddr; + unsigned long result, base_and_type; + + if (addr >= APECS_DENSE_MEM) { + addr -= APECS_DENSE_MEM; + APECS_SET_HAE; + base_and_type = APECS_SPARSE_MEM + 0x08; + } else { + addr -= APECS_IO; + base_and_type = APECS_IO + 0x08; + } + + result = *(vip) ((addr << 5) + base_and_type); + return __kernel_extwl(result, addr & 3); +} + +__EXTERN_INLINE void apecs_iowrite16(u16 b, void __iomem *xaddr) +{ + unsigned long addr = (unsigned long) xaddr; + unsigned long w, base_and_type; + + if (addr >= APECS_DENSE_MEM) { + addr -= APECS_DENSE_MEM; + APECS_SET_HAE; + base_and_type = APECS_SPARSE_MEM + 0x08; + } else { + addr -= APECS_IO; + base_and_type = APECS_IO + 0x08; + } + + w = __kernel_inswl(b, addr & 3); + *(vuip) ((addr << 5) + base_and_type) = w; +} + +__EXTERN_INLINE unsigned int apecs_ioread32(void __iomem *xaddr) +{ + unsigned long addr = (unsigned long) xaddr; + if (addr < APECS_DENSE_MEM) + addr = ((addr - APECS_IO) << 5) + APECS_IO + 0x18; + return *(vuip)addr; +} + +__EXTERN_INLINE void apecs_iowrite32(u32 b, void __iomem *xaddr) +{ + unsigned long addr = (unsigned long) xaddr; + if (addr < APECS_DENSE_MEM) + addr = ((addr - APECS_IO) << 5) + APECS_IO + 0x18; + *(vuip)addr = b; +} + +__EXTERN_INLINE void __iomem *apecs_ioportmap(unsigned long addr) +{ + return (void __iomem *)(addr + APECS_IO); +} + +__EXTERN_INLINE void __iomem *apecs_ioremap(unsigned long addr, + unsigned long size) +{ + return (void __iomem *)(addr + APECS_DENSE_MEM); +} + +__EXTERN_INLINE int apecs_is_ioaddr(unsigned long addr) +{ + return addr >= IDENT_ADDR + 0x180000000UL; +} + +__EXTERN_INLINE int apecs_is_mmio(const volatile void __iomem *addr) +{ + return (unsigned long)addr >= APECS_DENSE_MEM; +} + +#undef APECS_SET_HAE + +#undef vip +#undef vuip +#undef vulp + +#undef __IO_PREFIX +#define __IO_PREFIX apecs +#define apecs_trivial_io_bw 0 +#define apecs_trivial_io_lq 0 +#define apecs_trivial_rw_bw 2 +#define apecs_trivial_rw_lq 1 +#define apecs_trivial_iounmap 1 +#include <asm/io_trivial.h> + +#ifdef __IO_EXTERN_INLINE +#undef __EXTERN_INLINE +#undef __IO_EXTERN_INLINE +#endif + +#endif /* __KERNEL__ */ + +#endif /* __ALPHA_APECS__H__ */ diff --git a/arch/alpha/include/asm/core_cia.h b/arch/alpha/include/asm/core_cia.h new file mode 100644 index 000000000..9e0516c0c --- /dev/null +++ b/arch/alpha/include/asm/core_cia.h @@ -0,0 +1,500 @@ +#ifndef __ALPHA_CIA__H__ +#define __ALPHA_CIA__H__ + +/* Define to experiment with fitting everything into one 512MB HAE window. */ +#define CIA_ONE_HAE_WINDOW 1 + +#include <linux/types.h> +#include <asm/compiler.h> + +/* + * CIA is the internal name for the 21171 chipset which provides + * memory controller and PCI access for the 21164 chip based systems. + * Also supported here is the 21172 (CIA-2) and 21174 (PYXIS). + * + * The lineage is a bit confused, since the 21174 was reportedly started + * from the 21171 Pass 1 mask, and so is missing bug fixes that appear + * in 21171 Pass 2 and 21172, but it also contains additional features. + * + * This file is based on: + * + * DECchip 21171 Core Logic Chipset + * Technical Reference Manual + * + * EC-QE18B-TE + * + * david.rusling@reo.mts.dec.com Initial Version. + * + */ + +/* + * CIA ADDRESS BIT DEFINITIONS + * + * 3333 3333 3322 2222 2222 1111 1111 11 + * 9876 5432 1098 7654 3210 9876 5432 1098 7654 3210 + * ---- ---- ---- ---- ---- ---- ---- ---- ---- ---- + * 1 000 + * ---- ---- ---- ---- ---- ---- ---- ---- ---- ---- + * | |\| + * | Byte Enable --+ | + * | Transfer Length --+ + * +-- IO space, not cached + * + * Byte Transfer + * Enable Length Transfer Byte Address + * adr<6:5> adr<4:3> Length Enable Adder + * --------------------------------------------- + * 00 00 Byte 1110 0x000 + * 01 00 Byte 1101 0x020 + * 10 00 Byte 1011 0x040 + * 11 00 Byte 0111 0x060 + * + * 00 01 Word 1100 0x008 + * 01 01 Word 1001 0x028 <= Not supported in this code. + * 10 01 Word 0011 0x048 + * + * 00 10 Tribyte 1000 0x010 + * 01 10 Tribyte 0001 0x030 + * + * 10 11 Longword 0000 0x058 + * + * Note that byte enables are asserted low. + * + */ + +#define CIA_MEM_R1_MASK 0x1fffffff /* SPARSE Mem region 1 mask is 29 bits */ +#define CIA_MEM_R2_MASK 0x07ffffff /* SPARSE Mem region 2 mask is 27 bits */ +#define CIA_MEM_R3_MASK 0x03ffffff /* SPARSE Mem region 3 mask is 26 bits */ + +/* + * 21171-CA Control and Status Registers + */ +#define CIA_IOC_CIA_REV (IDENT_ADDR + 0x8740000080UL) +# define CIA_REV_MASK 0xff +#define CIA_IOC_PCI_LAT (IDENT_ADDR + 0x87400000C0UL) +#define CIA_IOC_CIA_CTRL (IDENT_ADDR + 0x8740000100UL) +# define CIA_CTRL_PCI_EN (1 << 0) +# define CIA_CTRL_PCI_LOCK_EN (1 << 1) +# define CIA_CTRL_PCI_LOOP_EN (1 << 2) +# define CIA_CTRL_FST_BB_EN (1 << 3) +# define CIA_CTRL_PCI_MST_EN (1 << 4) +# define CIA_CTRL_PCI_MEM_EN (1 << 5) +# define CIA_CTRL_PCI_REQ64_EN (1 << 6) +# define CIA_CTRL_PCI_ACK64_EN (1 << 7) +# define CIA_CTRL_ADDR_PE_EN (1 << 8) +# define CIA_CTRL_PERR_EN (1 << 9) +# define CIA_CTRL_FILL_ERR_EN (1 << 10) +# define CIA_CTRL_MCHK_ERR_EN (1 << 11) +# define CIA_CTRL_ECC_CHK_EN (1 << 12) +# define CIA_CTRL_ASSERT_IDLE_BC (1 << 13) +# define CIA_CTRL_COM_IDLE_BC (1 << 14) +# define CIA_CTRL_CSR_IOA_BYPASS (1 << 15) +# define CIA_CTRL_IO_FLUSHREQ_EN (1 << 16) +# define CIA_CTRL_CPU_FLUSHREQ_EN (1 << 17) +# define CIA_CTRL_ARB_CPU_EN (1 << 18) +# define CIA_CTRL_EN_ARB_LINK (1 << 19) +# define CIA_CTRL_RD_TYPE_SHIFT 20 +# define CIA_CTRL_RL_TYPE_SHIFT 24 +# define CIA_CTRL_RM_TYPE_SHIFT 28 +# define CIA_CTRL_EN_DMA_RD_PERF (1 << 31) +#define CIA_IOC_CIA_CNFG (IDENT_ADDR + 0x8740000140UL) +# define CIA_CNFG_IOA_BWEN (1 << 0) +# define CIA_CNFG_PCI_MWEN (1 << 4) +# define CIA_CNFG_PCI_DWEN (1 << 5) +# define CIA_CNFG_PCI_WLEN (1 << 8) +#define CIA_IOC_FLASH_CTRL (IDENT_ADDR + 0x8740000200UL) +#define CIA_IOC_HAE_MEM (IDENT_ADDR + 0x8740000400UL) +#define CIA_IOC_HAE_IO (IDENT_ADDR + 0x8740000440UL) +#define CIA_IOC_CFG (IDENT_ADDR + 0x8740000480UL) +#define CIA_IOC_CACK_EN (IDENT_ADDR + 0x8740000600UL) +# define CIA_CACK_EN_LOCK_EN (1 << 0) +# define CIA_CACK_EN_MB_EN (1 << 1) +# define CIA_CACK_EN_SET_DIRTY_EN (1 << 2) +# define CIA_CACK_EN_BC_VICTIM_EN (1 << 3) + + +/* + * 21171-CA Diagnostic Registers + */ +#define CIA_IOC_CIA_DIAG (IDENT_ADDR + 0x8740002000UL) +#define CIA_IOC_DIAG_CHECK (IDENT_ADDR + 0x8740003000UL) + +/* + * 21171-CA Performance Monitor registers + */ +#define CIA_IOC_PERF_MONITOR (IDENT_ADDR + 0x8740004000UL) +#define CIA_IOC_PERF_CONTROL (IDENT_ADDR + 0x8740004040UL) + +/* + * 21171-CA Error registers + */ +#define CIA_IOC_CPU_ERR0 (IDENT_ADDR + 0x8740008000UL) +#define CIA_IOC_CPU_ERR1 (IDENT_ADDR + 0x8740008040UL) +#define CIA_IOC_CIA_ERR (IDENT_ADDR + 0x8740008200UL) +# define CIA_ERR_COR_ERR (1 << 0) +# define CIA_ERR_UN_COR_ERR (1 << 1) +# define CIA_ERR_CPU_PE (1 << 2) +# define CIA_ERR_MEM_NEM (1 << 3) +# define CIA_ERR_PCI_SERR (1 << 4) +# define CIA_ERR_PERR (1 << 5) +# define CIA_ERR_PCI_ADDR_PE (1 << 6) +# define CIA_ERR_RCVD_MAS_ABT (1 << 7) +# define CIA_ERR_RCVD_TAR_ABT (1 << 8) +# define CIA_ERR_PA_PTE_INV (1 << 9) +# define CIA_ERR_FROM_WRT_ERR (1 << 10) +# define CIA_ERR_IOA_TIMEOUT (1 << 11) +# define CIA_ERR_LOST_CORR_ERR (1 << 16) +# define CIA_ERR_LOST_UN_CORR_ERR (1 << 17) +# define CIA_ERR_LOST_CPU_PE (1 << 18) +# define CIA_ERR_LOST_MEM_NEM (1 << 19) +# define CIA_ERR_LOST_PERR (1 << 21) +# define CIA_ERR_LOST_PCI_ADDR_PE (1 << 22) +# define CIA_ERR_LOST_RCVD_MAS_ABT (1 << 23) +# define CIA_ERR_LOST_RCVD_TAR_ABT (1 << 24) +# define CIA_ERR_LOST_PA_PTE_INV (1 << 25) +# define CIA_ERR_LOST_FROM_WRT_ERR (1 << 26) +# define CIA_ERR_LOST_IOA_TIMEOUT (1 << 27) +# define CIA_ERR_VALID (1 << 31) +#define CIA_IOC_CIA_STAT (IDENT_ADDR + 0x8740008240UL) +#define CIA_IOC_ERR_MASK (IDENT_ADDR + 0x8740008280UL) +#define CIA_IOC_CIA_SYN (IDENT_ADDR + 0x8740008300UL) +#define CIA_IOC_MEM_ERR0 (IDENT_ADDR + 0x8740008400UL) +#define CIA_IOC_MEM_ERR1 (IDENT_ADDR + 0x8740008440UL) +#define CIA_IOC_PCI_ERR0 (IDENT_ADDR + 0x8740008800UL) +#define CIA_IOC_PCI_ERR1 (IDENT_ADDR + 0x8740008840UL) +#define CIA_IOC_PCI_ERR3 (IDENT_ADDR + 0x8740008880UL) + +/* + * 21171-CA System configuration registers + */ +#define CIA_IOC_MCR (IDENT_ADDR + 0x8750000000UL) +#define CIA_IOC_MBA0 (IDENT_ADDR + 0x8750000600UL) +#define CIA_IOC_MBA2 (IDENT_ADDR + 0x8750000680UL) +#define CIA_IOC_MBA4 (IDENT_ADDR + 0x8750000700UL) +#define CIA_IOC_MBA6 (IDENT_ADDR + 0x8750000780UL) +#define CIA_IOC_MBA8 (IDENT_ADDR + 0x8750000800UL) +#define CIA_IOC_MBAA (IDENT_ADDR + 0x8750000880UL) +#define CIA_IOC_MBAC (IDENT_ADDR + 0x8750000900UL) +#define CIA_IOC_MBAE (IDENT_ADDR + 0x8750000980UL) +#define CIA_IOC_TMG0 (IDENT_ADDR + 0x8750000B00UL) +#define CIA_IOC_TMG1 (IDENT_ADDR + 0x8750000B40UL) +#define CIA_IOC_TMG2 (IDENT_ADDR + 0x8750000B80UL) + +/* + * 2117A-CA PCI Address and Scatter-Gather Registers. + */ +#define CIA_IOC_PCI_TBIA (IDENT_ADDR + 0x8760000100UL) + +#define CIA_IOC_PCI_W0_BASE (IDENT_ADDR + 0x8760000400UL) +#define CIA_IOC_PCI_W0_MASK (IDENT_ADDR + 0x8760000440UL) +#define CIA_IOC_PCI_T0_BASE (IDENT_ADDR + 0x8760000480UL) + +#define CIA_IOC_PCI_W1_BASE (IDENT_ADDR + 0x8760000500UL) +#define CIA_IOC_PCI_W1_MASK (IDENT_ADDR + 0x8760000540UL) +#define CIA_IOC_PCI_T1_BASE (IDENT_ADDR + 0x8760000580UL) + +#define CIA_IOC_PCI_W2_BASE (IDENT_ADDR + 0x8760000600UL) +#define CIA_IOC_PCI_W2_MASK (IDENT_ADDR + 0x8760000640UL) +#define CIA_IOC_PCI_T2_BASE (IDENT_ADDR + 0x8760000680UL) + +#define CIA_IOC_PCI_W3_BASE (IDENT_ADDR + 0x8760000700UL) +#define CIA_IOC_PCI_W3_MASK (IDENT_ADDR + 0x8760000740UL) +#define CIA_IOC_PCI_T3_BASE (IDENT_ADDR + 0x8760000780UL) + +#define CIA_IOC_PCI_Wn_BASE(N) (IDENT_ADDR + 0x8760000400UL + (N)*0x100) +#define CIA_IOC_PCI_Wn_MASK(N) (IDENT_ADDR + 0x8760000440UL + (N)*0x100) +#define CIA_IOC_PCI_Tn_BASE(N) (IDENT_ADDR + 0x8760000480UL + (N)*0x100) + +#define CIA_IOC_PCI_W_DAC (IDENT_ADDR + 0x87600007C0UL) + +/* + * 2117A-CA Address Translation Registers. + */ + +/* 8 tag registers, the first 4 of which are lockable. */ +#define CIA_IOC_TB_TAGn(n) \ + (IDENT_ADDR + 0x8760000800UL + (n)*0x40) + +/* 4 page registers per tag register. */ +#define CIA_IOC_TBn_PAGEm(n,m) \ + (IDENT_ADDR + 0x8760001000UL + (n)*0x100 + (m)*0x40) + +/* + * Memory spaces: + */ +#define CIA_IACK_SC (IDENT_ADDR + 0x8720000000UL) +#define CIA_CONF (IDENT_ADDR + 0x8700000000UL) +#define CIA_IO (IDENT_ADDR + 0x8580000000UL) +#define CIA_SPARSE_MEM (IDENT_ADDR + 0x8000000000UL) +#define CIA_SPARSE_MEM_R2 (IDENT_ADDR + 0x8400000000UL) +#define CIA_SPARSE_MEM_R3 (IDENT_ADDR + 0x8500000000UL) +#define CIA_DENSE_MEM (IDENT_ADDR + 0x8600000000UL) +#define CIA_BW_MEM (IDENT_ADDR + 0x8800000000UL) +#define CIA_BW_IO (IDENT_ADDR + 0x8900000000UL) +#define CIA_BW_CFG_0 (IDENT_ADDR + 0x8a00000000UL) +#define CIA_BW_CFG_1 (IDENT_ADDR + 0x8b00000000UL) + +/* + * ALCOR's GRU ASIC registers + */ +#define GRU_INT_REQ (IDENT_ADDR + 0x8780000000UL) +#define GRU_INT_MASK (IDENT_ADDR + 0x8780000040UL) +#define GRU_INT_EDGE (IDENT_ADDR + 0x8780000080UL) +#define GRU_INT_HILO (IDENT_ADDR + 0x87800000C0UL) +#define GRU_INT_CLEAR (IDENT_ADDR + 0x8780000100UL) + +#define GRU_CACHE_CNFG (IDENT_ADDR + 0x8780000200UL) +#define GRU_SCR (IDENT_ADDR + 0x8780000300UL) +#define GRU_LED (IDENT_ADDR + 0x8780000800UL) +#define GRU_RESET (IDENT_ADDR + 0x8780000900UL) + +#define ALCOR_GRU_INT_REQ_BITS 0x800fffffUL +#define XLT_GRU_INT_REQ_BITS 0x80003fffUL +#define GRU_INT_REQ_BITS (alpha_mv.sys.cia.gru_int_req_bits+0) + +/* + * PYXIS interrupt control registers + */ +#define PYXIS_INT_REQ (IDENT_ADDR + 0x87A0000000UL) +#define PYXIS_INT_MASK (IDENT_ADDR + 0x87A0000040UL) +#define PYXIS_INT_HILO (IDENT_ADDR + 0x87A00000C0UL) +#define PYXIS_INT_ROUTE (IDENT_ADDR + 0x87A0000140UL) +#define PYXIS_GPO (IDENT_ADDR + 0x87A0000180UL) +#define PYXIS_INT_CNFG (IDENT_ADDR + 0x87A00001C0UL) +#define PYXIS_RT_COUNT (IDENT_ADDR + 0x87A0000200UL) +#define PYXIS_INT_TIME (IDENT_ADDR + 0x87A0000240UL) +#define PYXIS_IIC_CTRL (IDENT_ADDR + 0x87A00002C0UL) +#define PYXIS_RESET (IDENT_ADDR + 0x8780000900UL) + +/* Offset between ram physical addresses and pci64 DAC bus addresses. */ +#define PYXIS_DAC_OFFSET (1UL << 40) + +/* + * Data structure for handling CIA machine checks. + */ + +/* System-specific info. */ +struct el_CIA_sysdata_mcheck { + unsigned long cpu_err0; + unsigned long cpu_err1; + unsigned long cia_err; + unsigned long cia_stat; + unsigned long err_mask; + unsigned long cia_syn; + unsigned long mem_err0; + unsigned long mem_err1; + unsigned long pci_err0; + unsigned long pci_err1; + unsigned long pci_err2; +}; + + +#ifdef __KERNEL__ + +#ifndef __EXTERN_INLINE +/* Do not touch, this should *NOT* be static inline */ +#define __EXTERN_INLINE extern inline +#define __IO_EXTERN_INLINE +#endif + +/* + * I/O functions: + * + * CIA (the 2117x PCI/memory support chipset for the EV5 (21164) + * series of processors uses a sparse address mapping scheme to + * get at PCI memory and I/O. + */ + +/* + * Memory functions. 64-bit and 32-bit accesses are done through + * dense memory space, everything else through sparse space. + * + * For reading and writing 8 and 16 bit quantities we need to + * go through one of the three sparse address mapping regions + * and use the HAE_MEM CSR to provide some bits of the address. + * The following few routines use only sparse address region 1 + * which gives 1Gbyte of accessible space which relates exactly + * to the amount of PCI memory mapping *into* system address space. + * See p 6-17 of the specification but it looks something like this: + * + * 21164 Address: + * + * 3 2 1 + * 9876543210987654321098765432109876543210 + * 1ZZZZ0.PCI.QW.Address............BBLL + * + * ZZ = SBZ + * BB = Byte offset + * LL = Transfer length + * + * PCI Address: + * + * 3 2 1 + * 10987654321098765432109876543210 + * HHH....PCI.QW.Address........ 00 + * + * HHH = 31:29 HAE_MEM CSR + * + */ + +#define vip volatile int __force * +#define vuip volatile unsigned int __force * +#define vulp volatile unsigned long __force * + +__EXTERN_INLINE unsigned int cia_ioread8(void __iomem *xaddr) +{ + unsigned long addr = (unsigned long) xaddr; + unsigned long result, base_and_type; + + if (addr >= CIA_DENSE_MEM) + base_and_type = CIA_SPARSE_MEM + 0x00; + else + base_and_type = CIA_IO + 0x00; + + /* We can use CIA_MEM_R1_MASK for io ports too, since it is large + enough to cover all io ports, and smaller than CIA_IO. */ + addr &= CIA_MEM_R1_MASK; + result = *(vip) ((addr << 5) + base_and_type); + return __kernel_extbl(result, addr & 3); +} + +__EXTERN_INLINE void cia_iowrite8(u8 b, void __iomem *xaddr) +{ + unsigned long addr = (unsigned long) xaddr; + unsigned long w, base_and_type; + + if (addr >= CIA_DENSE_MEM) + base_and_type = CIA_SPARSE_MEM + 0x00; + else + base_and_type = CIA_IO + 0x00; + + addr &= CIA_MEM_R1_MASK; + w = __kernel_insbl(b, addr & 3); + *(vuip) ((addr << 5) + base_and_type) = w; +} + +__EXTERN_INLINE unsigned int cia_ioread16(void __iomem *xaddr) +{ + unsigned long addr = (unsigned long) xaddr; + unsigned long result, base_and_type; + + if (addr >= CIA_DENSE_MEM) + base_and_type = CIA_SPARSE_MEM + 0x08; + else + base_and_type = CIA_IO + 0x08; + + addr &= CIA_MEM_R1_MASK; + result = *(vip) ((addr << 5) + base_and_type); + return __kernel_extwl(result, addr & 3); +} + +__EXTERN_INLINE void cia_iowrite16(u16 b, void __iomem *xaddr) +{ + unsigned long addr = (unsigned long) xaddr; + unsigned long w, base_and_type; + + if (addr >= CIA_DENSE_MEM) + base_and_type = CIA_SPARSE_MEM + 0x08; + else + base_and_type = CIA_IO + 0x08; + + addr &= CIA_MEM_R1_MASK; + w = __kernel_inswl(b, addr & 3); + *(vuip) ((addr << 5) + base_and_type) = w; +} + +__EXTERN_INLINE unsigned int cia_ioread32(void __iomem *xaddr) +{ + unsigned long addr = (unsigned long) xaddr; + if (addr < CIA_DENSE_MEM) + addr = ((addr - CIA_IO) << 5) + CIA_IO + 0x18; + return *(vuip)addr; +} + +__EXTERN_INLINE void cia_iowrite32(u32 b, void __iomem *xaddr) +{ + unsigned long addr = (unsigned long) xaddr; + if (addr < CIA_DENSE_MEM) + addr = ((addr - CIA_IO) << 5) + CIA_IO + 0x18; + *(vuip)addr = b; +} + +__EXTERN_INLINE void __iomem *cia_ioportmap(unsigned long addr) +{ + return (void __iomem *)(addr + CIA_IO); +} + +__EXTERN_INLINE void __iomem *cia_ioremap(unsigned long addr, + unsigned long size) +{ + return (void __iomem *)(addr + CIA_DENSE_MEM); +} + +__EXTERN_INLINE int cia_is_ioaddr(unsigned long addr) +{ + return addr >= IDENT_ADDR + 0x8000000000UL; +} + +__EXTERN_INLINE int cia_is_mmio(const volatile void __iomem *addr) +{ + return (unsigned long)addr >= CIA_DENSE_MEM; +} + +__EXTERN_INLINE void __iomem *cia_bwx_ioportmap(unsigned long addr) +{ + return (void __iomem *)(addr + CIA_BW_IO); +} + +__EXTERN_INLINE void __iomem *cia_bwx_ioremap(unsigned long addr, + unsigned long size) +{ + return (void __iomem *)(addr + CIA_BW_MEM); +} + +__EXTERN_INLINE int cia_bwx_is_ioaddr(unsigned long addr) +{ + return addr >= IDENT_ADDR + 0x8000000000UL; +} + +__EXTERN_INLINE int cia_bwx_is_mmio(const volatile void __iomem *addr) +{ + return (unsigned long)addr < CIA_BW_IO; +} + +#undef vip +#undef vuip +#undef vulp + +#undef __IO_PREFIX +#define __IO_PREFIX cia +#define cia_trivial_rw_bw 2 +#define cia_trivial_rw_lq 1 +#define cia_trivial_io_bw 0 +#define cia_trivial_io_lq 0 +#define cia_trivial_iounmap 1 +#include <asm/io_trivial.h> + +#undef __IO_PREFIX +#define __IO_PREFIX cia_bwx +#define cia_bwx_trivial_rw_bw 1 +#define cia_bwx_trivial_rw_lq 1 +#define cia_bwx_trivial_io_bw 1 +#define cia_bwx_trivial_io_lq 1 +#define cia_bwx_trivial_iounmap 1 +#include <asm/io_trivial.h> + +#undef __IO_PREFIX +#ifdef CONFIG_ALPHA_PYXIS +#define __IO_PREFIX cia_bwx +#else +#define __IO_PREFIX cia +#endif + +#ifdef __IO_EXTERN_INLINE +#undef __EXTERN_INLINE +#undef __IO_EXTERN_INLINE +#endif + +#endif /* __KERNEL__ */ + +#endif /* __ALPHA_CIA__H__ */ diff --git a/arch/alpha/include/asm/core_irongate.h b/arch/alpha/include/asm/core_irongate.h new file mode 100644 index 000000000..24b2db541 --- /dev/null +++ b/arch/alpha/include/asm/core_irongate.h @@ -0,0 +1,232 @@ +#ifndef __ALPHA_IRONGATE__H__ +#define __ALPHA_IRONGATE__H__ + +#include <linux/types.h> +#include <asm/compiler.h> + +/* + * IRONGATE is the internal name for the AMD-751 K7 core logic chipset + * which provides memory controller and PCI access for NAUTILUS-based + * EV6 (21264) systems. + * + * This file is based on: + * + * IronGate management library, (c) 1999 Alpha Processor, Inc. + * Copyright (C) 1999 Alpha Processor, Inc., + * (David Daniel, Stig Telfer, Soohoon Lee) + */ + +/* + * The 21264 supports, and internally recognizes, a 44-bit physical + * address space that is divided equally between memory address space + * and I/O address space. Memory address space resides in the lower + * half of the physical address space (PA[43]=0) and I/O address space + * resides in the upper half of the physical address space (PA[43]=1). + */ + +/* + * Irongate CSR map. Some of the CSRs are 8 or 16 bits, but all access + * through the routines given is 32-bit. + * + * The first 0x40 bytes are standard as per the PCI spec. + */ + +typedef volatile __u32 igcsr32; + +typedef struct { + igcsr32 dev_vendor; /* 0x00 - device ID, vendor ID */ + igcsr32 stat_cmd; /* 0x04 - status, command */ + igcsr32 class; /* 0x08 - class code, rev ID */ + igcsr32 latency; /* 0x0C - header type, PCI latency */ + igcsr32 bar0; /* 0x10 - BAR0 - AGP */ + igcsr32 bar1; /* 0x14 - BAR1 - GART */ + igcsr32 bar2; /* 0x18 - Power Management reg block */ + + igcsr32 rsrvd0[6]; /* 0x1C-0x33 reserved */ + + igcsr32 capptr; /* 0x34 - Capabilities pointer */ + + igcsr32 rsrvd1[2]; /* 0x38-0x3F reserved */ + + igcsr32 bacsr10; /* 0x40 - base address chip selects */ + igcsr32 bacsr32; /* 0x44 - base address chip selects */ + igcsr32 bacsr54_eccms761; /* 0x48 - 751: base addr. chip selects + 761: ECC, mode/status */ + + igcsr32 rsrvd2[1]; /* 0x4C-0x4F reserved */ + + igcsr32 drammap; /* 0x50 - address mapping control */ + igcsr32 dramtm; /* 0x54 - timing, driver strength */ + igcsr32 dramms; /* 0x58 - DRAM mode/status */ + + igcsr32 rsrvd3[1]; /* 0x5C-0x5F reserved */ + + igcsr32 biu0; /* 0x60 - bus interface unit */ + igcsr32 biusip; /* 0x64 - Serial initialisation pkt */ + + igcsr32 rsrvd4[2]; /* 0x68-0x6F reserved */ + + igcsr32 mro; /* 0x70 - memory request optimiser */ + + igcsr32 rsrvd5[3]; /* 0x74-0x7F reserved */ + + igcsr32 whami; /* 0x80 - who am I */ + igcsr32 pciarb; /* 0x84 - PCI arbitration control */ + igcsr32 pcicfg; /* 0x88 - PCI config status */ + + igcsr32 rsrvd6[4]; /* 0x8C-0x9B reserved */ + + igcsr32 pci_mem; /* 0x9C - PCI top of memory, + 761 only */ + + /* AGP (bus 1) control registers */ + igcsr32 agpcap; /* 0xA0 - AGP Capability Identifier */ + igcsr32 agpstat; /* 0xA4 - AGP status register */ + igcsr32 agpcmd; /* 0xA8 - AGP control register */ + igcsr32 agpva; /* 0xAC - AGP Virtual Address Space */ + igcsr32 agpmode; /* 0xB0 - AGP/GART mode control */ +} Irongate0; + + +typedef struct { + + igcsr32 dev_vendor; /* 0x00 - Device and Vendor IDs */ + igcsr32 stat_cmd; /* 0x04 - Status and Command regs */ + igcsr32 class; /* 0x08 - subclass, baseclass etc */ + igcsr32 htype; /* 0x0C - header type (at 0x0E) */ + igcsr32 rsrvd0[2]; /* 0x10-0x17 reserved */ + igcsr32 busnos; /* 0x18 - Primary, secondary bus nos */ + igcsr32 io_baselim_regs; /* 0x1C - IO base, IO lim, AGP status */ + igcsr32 mem_baselim; /* 0x20 - memory base, memory lim */ + igcsr32 pfmem_baselim; /* 0x24 - prefetchable base, lim */ + igcsr32 rsrvd1[2]; /* 0x28-0x2F reserved */ + igcsr32 io_baselim; /* 0x30 - IO base, IO limit */ + igcsr32 rsrvd2[2]; /* 0x34-0x3B - reserved */ + igcsr32 interrupt; /* 0x3C - interrupt, PCI bridge ctrl */ + +} Irongate1; + +extern igcsr32 *IronECC; + +/* + * Memory spaces: + */ + +/* Irongate is consistent with a subset of the Tsunami memory map */ +#ifdef USE_48_BIT_KSEG +#define IRONGATE_BIAS 0x80000000000UL +#else +#define IRONGATE_BIAS 0x10000000000UL +#endif + + +#define IRONGATE_MEM (IDENT_ADDR | IRONGATE_BIAS | 0x000000000UL) +#define IRONGATE_IACK_SC (IDENT_ADDR | IRONGATE_BIAS | 0x1F8000000UL) +#define IRONGATE_IO (IDENT_ADDR | IRONGATE_BIAS | 0x1FC000000UL) +#define IRONGATE_CONF (IDENT_ADDR | IRONGATE_BIAS | 0x1FE000000UL) + +/* + * PCI Configuration space accesses are formed like so: + * + * 0x1FE << 24 | : 2 2 2 2 1 1 1 1 : 1 1 1 1 1 1 0 0 : 0 0 0 0 0 0 0 0 : + * : 3 2 1 0 9 8 7 6 : 5 4 3 2 1 0 9 8 : 7 6 5 4 3 2 1 0 : + * ---bus numer--- -device-- -fun- ---register---- + */ + +#define IGCSR(dev,fun,reg) ( IRONGATE_CONF | \ + ((dev)<<11) | \ + ((fun)<<8) | \ + (reg) ) + +#define IRONGATE0 ((Irongate0 *) IGCSR(0, 0, 0)) +#define IRONGATE1 ((Irongate1 *) IGCSR(1, 0, 0)) + +/* + * Data structure for handling IRONGATE machine checks: + * This is the standard OSF logout frame + */ + +#define SCB_Q_SYSERR 0x620 /* OSF definitions */ +#define SCB_Q_PROCERR 0x630 +#define SCB_Q_SYSMCHK 0x660 +#define SCB_Q_PROCMCHK 0x670 + +struct el_IRONGATE_sysdata_mcheck { + __u32 FrameSize; /* Bytes, including this field */ + __u32 FrameFlags; /* <31> = Retry, <30> = Second Error */ + __u32 CpuOffset; /* Offset to CPU-specific into */ + __u32 SystemOffset; /* Offset to system-specific info */ + __u32 MCHK_Code; + __u32 MCHK_Frame_Rev; + __u64 I_STAT; + __u64 DC_STAT; + __u64 C_ADDR; + __u64 DC1_SYNDROME; + __u64 DC0_SYNDROME; + __u64 C_STAT; + __u64 C_STS; + __u64 RESERVED0; + __u64 EXC_ADDR; + __u64 IER_CM; + __u64 ISUM; + __u64 MM_STAT; + __u64 PAL_BASE; + __u64 I_CTL; + __u64 PCTX; +}; + + +#ifdef __KERNEL__ + +#ifndef __EXTERN_INLINE +#define __EXTERN_INLINE extern inline +#define __IO_EXTERN_INLINE +#endif + +/* + * I/O functions: + * + * IRONGATE (AMD-751) PCI/memory support chip for the EV6 (21264) and + * K7 can only use linear accesses to get at PCI memory and I/O spaces. + */ + +/* + * Memory functions. All accesses are done through linear space. + */ + +__EXTERN_INLINE void __iomem *irongate_ioportmap(unsigned long addr) +{ + return (void __iomem *)(addr + IRONGATE_IO); +} + +extern void __iomem *irongate_ioremap(unsigned long addr, unsigned long size); +extern void irongate_iounmap(volatile void __iomem *addr); + +__EXTERN_INLINE int irongate_is_ioaddr(unsigned long addr) +{ + return addr >= IRONGATE_MEM; +} + +__EXTERN_INLINE int irongate_is_mmio(const volatile void __iomem *xaddr) +{ + unsigned long addr = (unsigned long)xaddr; + return addr < IRONGATE_IO || addr >= IRONGATE_CONF; +} + +#undef __IO_PREFIX +#define __IO_PREFIX irongate +#define irongate_trivial_rw_bw 1 +#define irongate_trivial_rw_lq 1 +#define irongate_trivial_io_bw 1 +#define irongate_trivial_io_lq 1 +#define irongate_trivial_iounmap 0 +#include <asm/io_trivial.h> + +#ifdef __IO_EXTERN_INLINE +#undef __EXTERN_INLINE +#undef __IO_EXTERN_INLINE +#endif + +#endif /* __KERNEL__ */ + +#endif /* __ALPHA_IRONGATE__H__ */ diff --git a/arch/alpha/include/asm/core_lca.h b/arch/alpha/include/asm/core_lca.h new file mode 100644 index 000000000..8ee6c5162 --- /dev/null +++ b/arch/alpha/include/asm/core_lca.h @@ -0,0 +1,361 @@ +#ifndef __ALPHA_LCA__H__ +#define __ALPHA_LCA__H__ + +#include <asm/compiler.h> +#include <asm/mce.h> + +/* + * Low Cost Alpha (LCA) definitions (these apply to 21066 and 21068, + * for example). + * + * This file is based on: + * + * DECchip 21066 and DECchip 21068 Alpha AXP Microprocessors + * Hardware Reference Manual; Digital Equipment Corp.; May 1994; + * Maynard, MA; Order Number: EC-N2681-71. + */ + +/* + * NOTE: The LCA uses a Host Address Extension (HAE) register to access + * PCI addresses that are beyond the first 27 bits of address + * space. Updating the HAE requires an external cycle (and + * a memory barrier), which tends to be slow. Instead of updating + * it on each sparse memory access, we keep the current HAE value + * cached in variable cache_hae. Only if the cached HAE differs + * from the desired HAE value do we actually updated HAE register. + * The HAE register is preserved by the interrupt handler entry/exit + * code, so this scheme works even in the presence of interrupts. + * + * Dense memory space doesn't require the HAE, but is restricted to + * aligned 32 and 64 bit accesses. Special Cycle and Interrupt + * Acknowledge cycles may also require the use of the HAE. The LCA + * limits I/O address space to the bottom 24 bits of address space, + * but this easily covers the 16 bit ISA I/O address space. + */ + +/* + * NOTE 2! The memory operations do not set any memory barriers, as + * it's not needed for cases like a frame buffer that is essentially + * memory-like. You need to do them by hand if the operations depend + * on ordering. + * + * Similarly, the port I/O operations do a "mb" only after a write + * operation: if an mb is needed before (as in the case of doing + * memory mapped I/O first, and then a port I/O operation to the same + * device), it needs to be done by hand. + * + * After the above has bitten me 100 times, I'll give up and just do + * the mb all the time, but right now I'm hoping this will work out. + * Avoiding mb's may potentially be a noticeable speed improvement, + * but I can't honestly say I've tested it. + * + * Handling interrupts that need to do mb's to synchronize to + * non-interrupts is another fun race area. Don't do it (because if + * you do, I'll have to do *everything* with interrupts disabled, + * ugh). + */ + +/* + * Memory Controller registers: + */ +#define LCA_MEM_BCR0 (IDENT_ADDR + 0x120000000UL) +#define LCA_MEM_BCR1 (IDENT_ADDR + 0x120000008UL) +#define LCA_MEM_BCR2 (IDENT_ADDR + 0x120000010UL) +#define LCA_MEM_BCR3 (IDENT_ADDR + 0x120000018UL) +#define LCA_MEM_BMR0 (IDENT_ADDR + 0x120000020UL) +#define LCA_MEM_BMR1 (IDENT_ADDR + 0x120000028UL) +#define LCA_MEM_BMR2 (IDENT_ADDR + 0x120000030UL) +#define LCA_MEM_BMR3 (IDENT_ADDR + 0x120000038UL) +#define LCA_MEM_BTR0 (IDENT_ADDR + 0x120000040UL) +#define LCA_MEM_BTR1 (IDENT_ADDR + 0x120000048UL) +#define LCA_MEM_BTR2 (IDENT_ADDR + 0x120000050UL) +#define LCA_MEM_BTR3 (IDENT_ADDR + 0x120000058UL) +#define LCA_MEM_GTR (IDENT_ADDR + 0x120000060UL) +#define LCA_MEM_ESR (IDENT_ADDR + 0x120000068UL) +#define LCA_MEM_EAR (IDENT_ADDR + 0x120000070UL) +#define LCA_MEM_CAR (IDENT_ADDR + 0x120000078UL) +#define LCA_MEM_VGR (IDENT_ADDR + 0x120000080UL) +#define LCA_MEM_PLM (IDENT_ADDR + 0x120000088UL) +#define LCA_MEM_FOR (IDENT_ADDR + 0x120000090UL) + +/* + * I/O Controller registers: + */ +#define LCA_IOC_HAE (IDENT_ADDR + 0x180000000UL) +#define LCA_IOC_CONF (IDENT_ADDR + 0x180000020UL) +#define LCA_IOC_STAT0 (IDENT_ADDR + 0x180000040UL) +#define LCA_IOC_STAT1 (IDENT_ADDR + 0x180000060UL) +#define LCA_IOC_TBIA (IDENT_ADDR + 0x180000080UL) +#define LCA_IOC_TB_ENA (IDENT_ADDR + 0x1800000a0UL) +#define LCA_IOC_SFT_RST (IDENT_ADDR + 0x1800000c0UL) +#define LCA_IOC_PAR_DIS (IDENT_ADDR + 0x1800000e0UL) +#define LCA_IOC_W_BASE0 (IDENT_ADDR + 0x180000100UL) +#define LCA_IOC_W_BASE1 (IDENT_ADDR + 0x180000120UL) +#define LCA_IOC_W_MASK0 (IDENT_ADDR + 0x180000140UL) +#define LCA_IOC_W_MASK1 (IDENT_ADDR + 0x180000160UL) +#define LCA_IOC_T_BASE0 (IDENT_ADDR + 0x180000180UL) +#define LCA_IOC_T_BASE1 (IDENT_ADDR + 0x1800001a0UL) +#define LCA_IOC_TB_TAG0 (IDENT_ADDR + 0x188000000UL) +#define LCA_IOC_TB_TAG1 (IDENT_ADDR + 0x188000020UL) +#define LCA_IOC_TB_TAG2 (IDENT_ADDR + 0x188000040UL) +#define LCA_IOC_TB_TAG3 (IDENT_ADDR + 0x188000060UL) +#define LCA_IOC_TB_TAG4 (IDENT_ADDR + 0x188000070UL) +#define LCA_IOC_TB_TAG5 (IDENT_ADDR + 0x1880000a0UL) +#define LCA_IOC_TB_TAG6 (IDENT_ADDR + 0x1880000c0UL) +#define LCA_IOC_TB_TAG7 (IDENT_ADDR + 0x1880000e0UL) + +/* + * Memory spaces: + */ +#define LCA_IACK_SC (IDENT_ADDR + 0x1a0000000UL) +#define LCA_CONF (IDENT_ADDR + 0x1e0000000UL) +#define LCA_IO (IDENT_ADDR + 0x1c0000000UL) +#define LCA_SPARSE_MEM (IDENT_ADDR + 0x200000000UL) +#define LCA_DENSE_MEM (IDENT_ADDR + 0x300000000UL) + +/* + * Bit definitions for I/O Controller status register 0: + */ +#define LCA_IOC_STAT0_CMD 0xf +#define LCA_IOC_STAT0_ERR (1<<4) +#define LCA_IOC_STAT0_LOST (1<<5) +#define LCA_IOC_STAT0_THIT (1<<6) +#define LCA_IOC_STAT0_TREF (1<<7) +#define LCA_IOC_STAT0_CODE_SHIFT 8 +#define LCA_IOC_STAT0_CODE_MASK 0x7 +#define LCA_IOC_STAT0_P_NBR_SHIFT 13 +#define LCA_IOC_STAT0_P_NBR_MASK 0x7ffff + +#define LCA_HAE_ADDRESS LCA_IOC_HAE + +/* LCA PMR Power Management register defines */ +#define LCA_PMR_ADDR (IDENT_ADDR + 0x120000098UL) +#define LCA_PMR_PDIV 0x7 /* Primary clock divisor */ +#define LCA_PMR_ODIV 0x38 /* Override clock divisor */ +#define LCA_PMR_INTO 0x40 /* Interrupt override */ +#define LCA_PMR_DMAO 0x80 /* DMA override */ +#define LCA_PMR_OCCEB 0xffff0000L /* Override cycle counter - even bits */ +#define LCA_PMR_OCCOB 0xffff000000000000L /* Override cycle counter - even bits */ +#define LCA_PMR_PRIMARY_MASK 0xfffffffffffffff8L + +/* LCA PMR Macros */ + +#define LCA_READ_PMR (*(volatile unsigned long *)LCA_PMR_ADDR) +#define LCA_WRITE_PMR(d) (*((volatile unsigned long *)LCA_PMR_ADDR) = (d)) + +#define LCA_GET_PRIMARY(r) ((r) & LCA_PMR_PDIV) +#define LCA_GET_OVERRIDE(r) (((r) >> 3) & LCA_PMR_PDIV) +#define LCA_SET_PRIMARY_CLOCK(r, c) ((r) = (((r) & LCA_PMR_PRIMARY_MASK)|(c))) + +/* LCA PMR Divisor values */ +#define LCA_PMR_DIV_1 0x0 +#define LCA_PMR_DIV_1_5 0x1 +#define LCA_PMR_DIV_2 0x2 +#define LCA_PMR_DIV_4 0x3 +#define LCA_PMR_DIV_8 0x4 +#define LCA_PMR_DIV_16 0x5 +#define LCA_PMR_DIV_MIN DIV_1 +#define LCA_PMR_DIV_MAX DIV_16 + + +/* + * Data structure for handling LCA machine checks. Correctable errors + * result in a short logout frame, uncorrectable ones in a long one. + */ +struct el_lca_mcheck_short { + struct el_common h; /* common logout header */ + unsigned long esr; /* error-status register */ + unsigned long ear; /* error-address register */ + unsigned long dc_stat; /* dcache status register */ + unsigned long ioc_stat0; /* I/O controller status register 0 */ + unsigned long ioc_stat1; /* I/O controller status register 1 */ +}; + +struct el_lca_mcheck_long { + struct el_common h; /* common logout header */ + unsigned long pt[31]; /* PAL temps */ + unsigned long exc_addr; /* exception address */ + unsigned long pad1[3]; + unsigned long pal_base; /* PALcode base address */ + unsigned long hier; /* hw interrupt enable */ + unsigned long hirr; /* hw interrupt request */ + unsigned long mm_csr; /* MMU control & status */ + unsigned long dc_stat; /* data cache status */ + unsigned long dc_addr; /* data cache addr register */ + unsigned long abox_ctl; /* address box control register */ + unsigned long esr; /* error status register */ + unsigned long ear; /* error address register */ + unsigned long car; /* cache control register */ + unsigned long ioc_stat0; /* I/O controller status register 0 */ + unsigned long ioc_stat1; /* I/O controller status register 1 */ + unsigned long va; /* virtual address register */ +}; + +union el_lca { + struct el_common * c; + struct el_lca_mcheck_long * l; + struct el_lca_mcheck_short * s; +}; + +#ifdef __KERNEL__ + +#ifndef __EXTERN_INLINE +#define __EXTERN_INLINE extern inline +#define __IO_EXTERN_INLINE +#endif + +/* + * I/O functions: + * + * Unlike Jensen, the Noname machines have no concept of local + * I/O---everything goes over the PCI bus. + * + * There is plenty room for optimization here. In particular, + * the Alpha's insb/insw/extb/extw should be useful in moving + * data to/from the right byte-lanes. + */ + +#define vip volatile int __force * +#define vuip volatile unsigned int __force * +#define vulp volatile unsigned long __force * + +#define LCA_SET_HAE \ + do { \ + if (addr >= (1UL << 24)) { \ + unsigned long msb = addr & 0xf8000000; \ + addr -= msb; \ + set_hae(msb); \ + } \ + } while (0) + + +__EXTERN_INLINE unsigned int lca_ioread8(void __iomem *xaddr) +{ + unsigned long addr = (unsigned long) xaddr; + unsigned long result, base_and_type; + + if (addr >= LCA_DENSE_MEM) { + addr -= LCA_DENSE_MEM; + LCA_SET_HAE; + base_and_type = LCA_SPARSE_MEM + 0x00; + } else { + addr -= LCA_IO; + base_and_type = LCA_IO + 0x00; + } + + result = *(vip) ((addr << 5) + base_and_type); + return __kernel_extbl(result, addr & 3); +} + +__EXTERN_INLINE void lca_iowrite8(u8 b, void __iomem *xaddr) +{ + unsigned long addr = (unsigned long) xaddr; + unsigned long w, base_and_type; + + if (addr >= LCA_DENSE_MEM) { + addr -= LCA_DENSE_MEM; + LCA_SET_HAE; + base_and_type = LCA_SPARSE_MEM + 0x00; + } else { + addr -= LCA_IO; + base_and_type = LCA_IO + 0x00; + } + + w = __kernel_insbl(b, addr & 3); + *(vuip) ((addr << 5) + base_and_type) = w; +} + +__EXTERN_INLINE unsigned int lca_ioread16(void __iomem *xaddr) +{ + unsigned long addr = (unsigned long) xaddr; + unsigned long result, base_and_type; + + if (addr >= LCA_DENSE_MEM) { + addr -= LCA_DENSE_MEM; + LCA_SET_HAE; + base_and_type = LCA_SPARSE_MEM + 0x08; + } else { + addr -= LCA_IO; + base_and_type = LCA_IO + 0x08; + } + + result = *(vip) ((addr << 5) + base_and_type); + return __kernel_extwl(result, addr & 3); +} + +__EXTERN_INLINE void lca_iowrite16(u16 b, void __iomem *xaddr) +{ + unsigned long addr = (unsigned long) xaddr; + unsigned long w, base_and_type; + + if (addr >= LCA_DENSE_MEM) { + addr -= LCA_DENSE_MEM; + LCA_SET_HAE; + base_and_type = LCA_SPARSE_MEM + 0x08; + } else { + addr -= LCA_IO; + base_and_type = LCA_IO + 0x08; + } + + w = __kernel_inswl(b, addr & 3); + *(vuip) ((addr << 5) + base_and_type) = w; +} + +__EXTERN_INLINE unsigned int lca_ioread32(void __iomem *xaddr) +{ + unsigned long addr = (unsigned long) xaddr; + if (addr < LCA_DENSE_MEM) + addr = ((addr - LCA_IO) << 5) + LCA_IO + 0x18; + return *(vuip)addr; +} + +__EXTERN_INLINE void lca_iowrite32(u32 b, void __iomem *xaddr) +{ + unsigned long addr = (unsigned long) xaddr; + if (addr < LCA_DENSE_MEM) + addr = ((addr - LCA_IO) << 5) + LCA_IO + 0x18; + *(vuip)addr = b; +} + +__EXTERN_INLINE void __iomem *lca_ioportmap(unsigned long addr) +{ + return (void __iomem *)(addr + LCA_IO); +} + +__EXTERN_INLINE void __iomem *lca_ioremap(unsigned long addr, + unsigned long size) +{ + return (void __iomem *)(addr + LCA_DENSE_MEM); +} + +__EXTERN_INLINE int lca_is_ioaddr(unsigned long addr) +{ + return addr >= IDENT_ADDR + 0x120000000UL; +} + +__EXTERN_INLINE int lca_is_mmio(const volatile void __iomem *addr) +{ + return (unsigned long)addr >= LCA_DENSE_MEM; +} + +#undef vip +#undef vuip +#undef vulp + +#undef __IO_PREFIX +#define __IO_PREFIX lca +#define lca_trivial_rw_bw 2 +#define lca_trivial_rw_lq 1 +#define lca_trivial_io_bw 0 +#define lca_trivial_io_lq 0 +#define lca_trivial_iounmap 1 +#include <asm/io_trivial.h> + +#ifdef __IO_EXTERN_INLINE +#undef __EXTERN_INLINE +#undef __IO_EXTERN_INLINE +#endif + +#endif /* __KERNEL__ */ + +#endif /* __ALPHA_LCA__H__ */ diff --git a/arch/alpha/include/asm/core_marvel.h b/arch/alpha/include/asm/core_marvel.h new file mode 100644 index 000000000..dad300fa1 --- /dev/null +++ b/arch/alpha/include/asm/core_marvel.h @@ -0,0 +1,377 @@ +/* + * Marvel systems use the IO7 I/O chip provides PCI/PCIX/AGP access + * + * This file is based on: + * + * Marvel / EV7 System Programmer's Manual + * Revision 1.00 + * 14 May 2001 + */ + +#ifndef __ALPHA_MARVEL__H__ +#define __ALPHA_MARVEL__H__ + +#include <linux/types.h> +#include <linux/spinlock.h> + +#include <asm/compiler.h> + +#define MARVEL_MAX_PIDS 32 /* as long as we rely on 43-bit superpage */ +#define MARVEL_IRQ_VEC_PE_SHIFT (10) +#define MARVEL_IRQ_VEC_IRQ_MASK ((1 << MARVEL_IRQ_VEC_PE_SHIFT) - 1) +#define MARVEL_NR_IRQS \ + (16 + (MARVEL_MAX_PIDS * (1 << MARVEL_IRQ_VEC_PE_SHIFT))) + +/* + * EV7 RBOX Registers + */ +typedef struct { + volatile unsigned long csr __attribute__((aligned(16))); +} ev7_csr; + +typedef struct { + ev7_csr RBOX_CFG; /* 0x0000 */ + ev7_csr RBOX_NSVC; + ev7_csr RBOX_EWVC; + ev7_csr RBOX_WHAMI; + ev7_csr RBOX_TCTL; /* 0x0040 */ + ev7_csr RBOX_INT; + ev7_csr RBOX_IMASK; + ev7_csr RBOX_IREQ; + ev7_csr RBOX_INTQ; /* 0x0080 */ + ev7_csr RBOX_INTA; + ev7_csr RBOX_IT; + ev7_csr RBOX_SCRATCH1; + ev7_csr RBOX_SCRATCH2; /* 0x00c0 */ + ev7_csr RBOX_L_ERR; +} ev7_csrs; + +/* + * EV7 CSR addressing macros + */ +#define EV7_MASK40(addr) ((addr) & ((1UL << 41) - 1)) +#define EV7_KERN_ADDR(addr) ((void *)(IDENT_ADDR | EV7_MASK40(addr))) + +#define EV7_PE_MASK 0x1ffUL /* 9 bits ( 256 + mem/io ) */ +#define EV7_IPE(pe) ((~((long)(pe)) & EV7_PE_MASK) << 35) + +#define EV7_CSR_PHYS(pe, off) (EV7_IPE(pe) | (0x7FFCUL << 20) | (off)) +#define EV7_CSRS_PHYS(pe) (EV7_CSR_PHYS(pe, 0UL)) + +#define EV7_CSR_KERN(pe, off) (EV7_KERN_ADDR(EV7_CSR_PHYS(pe, off))) +#define EV7_CSRS_KERN(pe) (EV7_KERN_ADDR(EV7_CSRS_PHYS(pe))) + +#define EV7_CSR_OFFSET(name) ((unsigned long)&((ev7_csrs *)NULL)->name.csr) + +/* + * IO7 registers + */ +typedef struct { + volatile unsigned long csr __attribute__((aligned(64))); +} io7_csr; + +typedef struct { + /* I/O Port Control Registers */ + io7_csr POx_CTRL; /* 0x0000 */ + io7_csr POx_CACHE_CTL; + io7_csr POx_TIMER; + io7_csr POx_IO_ADR_EXT; + io7_csr POx_MEM_ADR_EXT; /* 0x0100 */ + io7_csr POx_XCAL_CTRL; + io7_csr rsvd1[2]; /* ?? spec doesn't show 0x180 */ + io7_csr POx_DM_SOURCE; /* 0x0200 */ + io7_csr POx_DM_DEST; + io7_csr POx_DM_SIZE; + io7_csr POx_DM_CTRL; + io7_csr rsvd2[4]; /* 0x0300 */ + + /* AGP Control Registers -- port 3 only */ + io7_csr AGP_CAP_ID; /* 0x0400 */ + io7_csr AGP_STAT; + io7_csr AGP_CMD; + io7_csr rsvd3; + + /* I/O Port Monitor Registers */ + io7_csr POx_MONCTL; /* 0x0500 */ + io7_csr POx_CTRA; + io7_csr POx_CTRB; + io7_csr POx_CTR56; + io7_csr POx_SCRATCH; /* 0x0600 */ + io7_csr POx_XTRA_A; + io7_csr POx_XTRA_TS; + io7_csr POx_XTRA_Z; + io7_csr rsvd4; /* 0x0700 */ + io7_csr POx_THRESHA; + io7_csr POx_THRESHB; + io7_csr rsvd5[33]; + + /* System Address Space Window Control Registers */ + + io7_csr POx_WBASE[4]; /* 0x1000 */ + io7_csr POx_WMASK[4]; + io7_csr POx_TBASE[4]; + io7_csr POx_SG_TBIA; + io7_csr POx_MSI_WBASE; + io7_csr rsvd6[50]; + + /* I/O Port Error Registers */ + io7_csr POx_ERR_SUM; + io7_csr POx_FIRST_ERR; + io7_csr POx_MSK_HEI; + io7_csr POx_TLB_ERR; + io7_csr POx_SPL_COMPLT; + io7_csr POx_TRANS_SUM; + io7_csr POx_FRC_PCI_ERR; + io7_csr POx_MULT_ERR; + io7_csr rsvd7[8]; + + /* I/O Port End of Interrupt Registers */ + io7_csr EOI_DAT; + io7_csr rsvd8[7]; + io7_csr POx_IACK_SPECIAL; + io7_csr rsvd9[103]; +} io7_ioport_csrs; + +typedef struct { + io7_csr IO_ASIC_REV; /* 0x30.0000 */ + io7_csr IO_SYS_REV; + io7_csr SER_CHAIN3; + io7_csr PO7_RST1; + io7_csr PO7_RST2; /* 0x30.0100 */ + io7_csr POx_RST[4]; + io7_csr IO7_DWNH; + io7_csr IO7_MAF; + io7_csr IO7_MAF_TO; + io7_csr IO7_ACC_CLUMP; /* 0x30.0300 */ + io7_csr IO7_PMASK; + io7_csr IO7_IOMASK; + io7_csr IO7_UPH; + io7_csr IO7_UPH_TO; /* 0x30.0400 */ + io7_csr RBX_IREQ_OFF; + io7_csr RBX_INTA_OFF; + io7_csr INT_RTY; + io7_csr PO7_MONCTL; /* 0x30.0500 */ + io7_csr PO7_CTRA; + io7_csr PO7_CTRB; + io7_csr PO7_CTR56; + io7_csr PO7_SCRATCH; /* 0x30.0600 */ + io7_csr PO7_XTRA_A; + io7_csr PO7_XTRA_TS; + io7_csr PO7_XTRA_Z; + io7_csr PO7_PMASK; /* 0x30.0700 */ + io7_csr PO7_THRESHA; + io7_csr PO7_THRESHB; + io7_csr rsvd1[97]; + io7_csr PO7_ERROR_SUM; /* 0x30.2000 */ + io7_csr PO7_BHOLE_MASK; + io7_csr PO7_HEI_MSK; + io7_csr PO7_CRD_MSK; + io7_csr PO7_UNCRR_SYM; /* 0x30.2100 */ + io7_csr PO7_CRRCT_SYM; + io7_csr PO7_ERR_PKT[2]; + io7_csr PO7_UGBGE_SYM; /* 0x30.2200 */ + io7_csr rsbv2[887]; + io7_csr PO7_LSI_CTL[128]; /* 0x31.0000 */ + io7_csr rsvd3[123]; + io7_csr HLT_CTL; /* 0x31.3ec0 */ + io7_csr HPI_CTL; /* 0x31.3f00 */ + io7_csr CRD_CTL; + io7_csr STV_CTL; + io7_csr HEI_CTL; + io7_csr PO7_MSI_CTL[16]; /* 0x31.4000 */ + io7_csr rsvd4[240]; + + /* + * Interrupt Diagnostic / Test + */ + struct { + io7_csr INT_PND; + io7_csr INT_CLR; + io7_csr INT_EOI; + io7_csr rsvd[29]; + } INT_DIAG[4]; + io7_csr rsvd5[125]; /* 0x31.a000 */ + io7_csr MISC_PND; /* 0x31.b800 */ + io7_csr rsvd6[31]; + io7_csr MSI_PND[16]; /* 0x31.c000 */ + io7_csr rsvd7[16]; + io7_csr MSI_CLR[16]; /* 0x31.c800 */ +} io7_port7_csrs; + +/* + * IO7 DMA Window Base register (POx_WBASEx) + */ +#define wbase_m_ena 0x1 +#define wbase_m_sg 0x2 +#define wbase_m_dac 0x4 +#define wbase_m_addr 0xFFF00000 +union IO7_POx_WBASE { + struct { + unsigned ena : 1; /* <0> */ + unsigned sg : 1; /* <1> */ + unsigned dac : 1; /* <2> -- window 3 only */ + unsigned rsvd1 : 17; + unsigned addr : 12; /* <31:20> */ + unsigned rsvd2 : 32; + } bits; + unsigned as_long[2]; + unsigned as_quad; +}; + +/* + * IO7 IID (Interrupt IDentifier) format + * + * For level-sensative interrupts, int_num is encoded as: + * + * bus/port slot/device INTx + * <7:5> <4:2> <1:0> + */ +union IO7_IID { + struct { + unsigned int_num : 9; /* <8:0> */ + unsigned tpu_mask : 4; /* <12:9> rsvd */ + unsigned msi : 1; /* 13 */ + unsigned ipe : 10; /* <23:14> */ + unsigned long rsvd : 40; + } bits; + unsigned int as_long[2]; + unsigned long as_quad; +}; + +/* + * IO7 addressing macros + */ +#define IO7_KERN_ADDR(addr) (EV7_KERN_ADDR(addr)) + +#define IO7_PORT_MASK 0x07UL /* 3 bits of port */ + +#define IO7_IPE(pe) (EV7_IPE(pe)) +#define IO7_IPORT(port) ((~((long)(port)) & IO7_PORT_MASK) << 32) + +#define IO7_HOSE(pe, port) (IO7_IPE(pe) | IO7_IPORT(port)) + +#define IO7_MEM_PHYS(pe, port) (IO7_HOSE(pe, port) | 0x00000000UL) +#define IO7_CONF_PHYS(pe, port) (IO7_HOSE(pe, port) | 0xFE000000UL) +#define IO7_IO_PHYS(pe, port) (IO7_HOSE(pe, port) | 0xFF000000UL) +#define IO7_CSR_PHYS(pe, port, off) \ + (IO7_HOSE(pe, port) | 0xFF800000UL | (off)) +#define IO7_CSRS_PHYS(pe, port) (IO7_CSR_PHYS(pe, port, 0UL)) +#define IO7_PORT7_CSRS_PHYS(pe) (IO7_CSR_PHYS(pe, 7, 0x300000UL)) + +#define IO7_MEM_KERN(pe, port) (IO7_KERN_ADDR(IO7_MEM_PHYS(pe, port))) +#define IO7_CONF_KERN(pe, port) (IO7_KERN_ADDR(IO7_CONF_PHYS(pe, port))) +#define IO7_IO_KERN(pe, port) (IO7_KERN_ADDR(IO7_IO_PHYS(pe, port))) +#define IO7_CSR_KERN(pe, port, off) (IO7_KERN_ADDR(IO7_CSR_PHYS(pe,port,off))) +#define IO7_CSRS_KERN(pe, port) (IO7_KERN_ADDR(IO7_CSRS_PHYS(pe, port))) +#define IO7_PORT7_CSRS_KERN(pe) (IO7_KERN_ADDR(IO7_PORT7_CSRS_PHYS(pe))) + +#define IO7_PLL_RNGA(pll) (((pll) >> 3) & 0x7) +#define IO7_PLL_RNGB(pll) (((pll) >> 6) & 0x7) + +#define IO7_MEM_SPACE (2UL * 1024 * 1024 * 1024) /* 2GB MEM */ +#define IO7_IO_SPACE (8UL * 1024 * 1024) /* 8MB I/O */ + + +/* + * Offset between ram physical addresses and pci64 DAC addresses + */ +#define IO7_DAC_OFFSET (1UL << 49) + +/* + * This is needed to satisify the IO() macro used in initializing the machvec + */ +#define MARVEL_IACK_SC \ + ((unsigned long) \ + (&(((io7_ioport_csrs *)IO7_CSRS_KERN(0, 0))->POx_IACK_SPECIAL))) + +#ifdef __KERNEL__ + +/* + * IO7 structs + */ +#define IO7_NUM_PORTS 4 +#define IO7_AGP_PORT 3 + +struct io7_port { + struct io7 *io7; + struct pci_controller *hose; + + int enabled; + unsigned int port; + io7_ioport_csrs *csrs; + + unsigned long saved_wbase[4]; + unsigned long saved_wmask[4]; + unsigned long saved_tbase[4]; +}; + +struct io7 { + struct io7 *next; + + unsigned int pe; + io7_port7_csrs *csrs; + struct io7_port ports[IO7_NUM_PORTS]; + + spinlock_t irq_lock; +}; + +#ifndef __EXTERN_INLINE +# define __EXTERN_INLINE extern inline +# define __IO_EXTERN_INLINE +#endif + +/* + * I/O functions. All access through linear space. + */ + +/* + * Memory functions. All accesses through linear space. + */ + +#define vucp volatile unsigned char __force * +#define vusp volatile unsigned short __force * + +extern unsigned int marvel_ioread8(void __iomem *); +extern void marvel_iowrite8(u8 b, void __iomem *); + +__EXTERN_INLINE unsigned int marvel_ioread16(void __iomem *addr) +{ + return __kernel_ldwu(*(vusp)addr); +} + +__EXTERN_INLINE void marvel_iowrite16(u16 b, void __iomem *addr) +{ + __kernel_stw(b, *(vusp)addr); +} + +extern void __iomem *marvel_ioremap(unsigned long addr, unsigned long size); +extern void marvel_iounmap(volatile void __iomem *addr); +extern void __iomem *marvel_ioportmap (unsigned long addr); + +__EXTERN_INLINE int marvel_is_ioaddr(unsigned long addr) +{ + return (addr >> 40) & 1; +} + +extern int marvel_is_mmio(const volatile void __iomem *); + +#undef vucp +#undef vusp + +#undef __IO_PREFIX +#define __IO_PREFIX marvel +#define marvel_trivial_rw_bw 1 +#define marvel_trivial_rw_lq 1 +#define marvel_trivial_io_bw 0 +#define marvel_trivial_io_lq 1 +#define marvel_trivial_iounmap 0 +#include <asm/io_trivial.h> + +#ifdef __IO_EXTERN_INLINE +# undef __EXTERN_INLINE +# undef __IO_EXTERN_INLINE +#endif + +#endif /* __KERNEL__ */ + +#endif /* __ALPHA_MARVEL__H__ */ diff --git a/arch/alpha/include/asm/core_mcpcia.h b/arch/alpha/include/asm/core_mcpcia.h new file mode 100644 index 000000000..ad44bef29 --- /dev/null +++ b/arch/alpha/include/asm/core_mcpcia.h @@ -0,0 +1,381 @@ +#ifndef __ALPHA_MCPCIA__H__ +#define __ALPHA_MCPCIA__H__ + +/* Define to experiment with fitting everything into one 128MB HAE window. + One window per bus, that is. */ +#define MCPCIA_ONE_HAE_WINDOW 1 + +#include <linux/types.h> +#include <asm/compiler.h> +#include <asm/mce.h> + +/* + * MCPCIA is the internal name for a core logic chipset which provides + * PCI access for the RAWHIDE family of systems. + * + * This file is based on: + * + * RAWHIDE System Programmer's Manual + * 16-May-96 + * Rev. 1.4 + * + */ + +/*------------------------------------------------------------------------** +** ** +** I/O procedures ** +** ** +** inport[b|w|t|l], outport[b|w|t|l] 8:16:24:32 IO xfers ** +** inportbxt: 8 bits only ** +** inport: alias of inportw ** +** outport: alias of outportw ** +** ** +** inmem[b|w|t|l], outmem[b|w|t|l] 8:16:24:32 ISA memory xfers ** +** inmembxt: 8 bits only ** +** inmem: alias of inmemw ** +** outmem: alias of outmemw ** +** ** +**------------------------------------------------------------------------*/ + + +/* MCPCIA ADDRESS BIT DEFINITIONS + * + * 3333 3333 3322 2222 2222 1111 1111 11 + * 9876 5432 1098 7654 3210 9876 5432 1098 7654 3210 + * ---- ---- ---- ---- ---- ---- ---- ---- ---- ---- + * 1 000 + * ---- ---- ---- ---- ---- ---- ---- ---- ---- ---- + * | |\| + * | Byte Enable --+ | + * | Transfer Length --+ + * +-- IO space, not cached + * + * Byte Transfer + * Enable Length Transfer Byte Address + * adr<6:5> adr<4:3> Length Enable Adder + * --------------------------------------------- + * 00 00 Byte 1110 0x000 + * 01 00 Byte 1101 0x020 + * 10 00 Byte 1011 0x040 + * 11 00 Byte 0111 0x060 + * + * 00 01 Word 1100 0x008 + * 01 01 Word 1001 0x028 <= Not supported in this code. + * 10 01 Word 0011 0x048 + * + * 00 10 Tribyte 1000 0x010 + * 01 10 Tribyte 0001 0x030 + * + * 10 11 Longword 0000 0x058 + * + * Note that byte enables are asserted low. + * + */ + +#define MCPCIA_MAX_HOSES 4 + +#define MCPCIA_MID(m) ((unsigned long)(m) << 33) + +/* Dodge has PCI0 and PCI1 at MID 4 and 5 respectively. + Durango adds PCI2 and PCI3 at MID 6 and 7 respectively. */ +#define MCPCIA_HOSE2MID(h) ((h) + 4) + +#define MCPCIA_MEM_MASK 0x07ffffff /* SPARSE Mem region mask is 27 bits */ + +/* + * Memory spaces: + */ +#define MCPCIA_SPARSE(m) (IDENT_ADDR + 0xf000000000UL + MCPCIA_MID(m)) +#define MCPCIA_DENSE(m) (IDENT_ADDR + 0xf100000000UL + MCPCIA_MID(m)) +#define MCPCIA_IO(m) (IDENT_ADDR + 0xf180000000UL + MCPCIA_MID(m)) +#define MCPCIA_CONF(m) (IDENT_ADDR + 0xf1c0000000UL + MCPCIA_MID(m)) +#define MCPCIA_CSR(m) (IDENT_ADDR + 0xf1e0000000UL + MCPCIA_MID(m)) +#define MCPCIA_IO_IACK(m) (IDENT_ADDR + 0xf1f0000000UL + MCPCIA_MID(m)) +#define MCPCIA_DENSE_IO(m) (IDENT_ADDR + 0xe1fc000000UL + MCPCIA_MID(m)) +#define MCPCIA_DENSE_CONF(m) (IDENT_ADDR + 0xe1fe000000UL + MCPCIA_MID(m)) + +/* + * General Registers + */ +#define MCPCIA_REV(m) (MCPCIA_CSR(m) + 0x000) +#define MCPCIA_WHOAMI(m) (MCPCIA_CSR(m) + 0x040) +#define MCPCIA_PCI_LAT(m) (MCPCIA_CSR(m) + 0x080) +#define MCPCIA_CAP_CTRL(m) (MCPCIA_CSR(m) + 0x100) +#define MCPCIA_HAE_MEM(m) (MCPCIA_CSR(m) + 0x400) +#define MCPCIA_HAE_IO(m) (MCPCIA_CSR(m) + 0x440) +#define _MCPCIA_IACK_SC(m) (MCPCIA_CSR(m) + 0x480) +#define MCPCIA_HAE_DENSE(m) (MCPCIA_CSR(m) + 0x4C0) + +/* + * Interrupt Control registers + */ +#define MCPCIA_INT_CTL(m) (MCPCIA_CSR(m) + 0x500) +#define MCPCIA_INT_REQ(m) (MCPCIA_CSR(m) + 0x540) +#define MCPCIA_INT_TARG(m) (MCPCIA_CSR(m) + 0x580) +#define MCPCIA_INT_ADR(m) (MCPCIA_CSR(m) + 0x5C0) +#define MCPCIA_INT_ADR_EXT(m) (MCPCIA_CSR(m) + 0x600) +#define MCPCIA_INT_MASK0(m) (MCPCIA_CSR(m) + 0x640) +#define MCPCIA_INT_MASK1(m) (MCPCIA_CSR(m) + 0x680) +#define MCPCIA_INT_ACK0(m) (MCPCIA_CSR(m) + 0x10003f00) +#define MCPCIA_INT_ACK1(m) (MCPCIA_CSR(m) + 0x10003f40) + +/* + * Performance Monitor registers + */ +#define MCPCIA_PERF_MON(m) (MCPCIA_CSR(m) + 0x300) +#define MCPCIA_PERF_CONT(m) (MCPCIA_CSR(m) + 0x340) + +/* + * Diagnostic Registers + */ +#define MCPCIA_CAP_DIAG(m) (MCPCIA_CSR(m) + 0x700) +#define MCPCIA_TOP_OF_MEM(m) (MCPCIA_CSR(m) + 0x7C0) + +/* + * Error registers + */ +#define MCPCIA_MC_ERR0(m) (MCPCIA_CSR(m) + 0x800) +#define MCPCIA_MC_ERR1(m) (MCPCIA_CSR(m) + 0x840) +#define MCPCIA_CAP_ERR(m) (MCPCIA_CSR(m) + 0x880) +#define MCPCIA_PCI_ERR1(m) (MCPCIA_CSR(m) + 0x1040) +#define MCPCIA_MDPA_STAT(m) (MCPCIA_CSR(m) + 0x4000) +#define MCPCIA_MDPA_SYN(m) (MCPCIA_CSR(m) + 0x4040) +#define MCPCIA_MDPA_DIAG(m) (MCPCIA_CSR(m) + 0x4080) +#define MCPCIA_MDPB_STAT(m) (MCPCIA_CSR(m) + 0x8000) +#define MCPCIA_MDPB_SYN(m) (MCPCIA_CSR(m) + 0x8040) +#define MCPCIA_MDPB_DIAG(m) (MCPCIA_CSR(m) + 0x8080) + +/* + * PCI Address Translation Registers. + */ +#define MCPCIA_SG_TBIA(m) (MCPCIA_CSR(m) + 0x1300) +#define MCPCIA_HBASE(m) (MCPCIA_CSR(m) + 0x1340) + +#define MCPCIA_W0_BASE(m) (MCPCIA_CSR(m) + 0x1400) +#define MCPCIA_W0_MASK(m) (MCPCIA_CSR(m) + 0x1440) +#define MCPCIA_T0_BASE(m) (MCPCIA_CSR(m) + 0x1480) + +#define MCPCIA_W1_BASE(m) (MCPCIA_CSR(m) + 0x1500) +#define MCPCIA_W1_MASK(m) (MCPCIA_CSR(m) + 0x1540) +#define MCPCIA_T1_BASE(m) (MCPCIA_CSR(m) + 0x1580) + +#define MCPCIA_W2_BASE(m) (MCPCIA_CSR(m) + 0x1600) +#define MCPCIA_W2_MASK(m) (MCPCIA_CSR(m) + 0x1640) +#define MCPCIA_T2_BASE(m) (MCPCIA_CSR(m) + 0x1680) + +#define MCPCIA_W3_BASE(m) (MCPCIA_CSR(m) + 0x1700) +#define MCPCIA_W3_MASK(m) (MCPCIA_CSR(m) + 0x1740) +#define MCPCIA_T3_BASE(m) (MCPCIA_CSR(m) + 0x1780) + +/* Hack! Only words for bus 0. */ + +#ifndef MCPCIA_ONE_HAE_WINDOW +#define MCPCIA_HAE_ADDRESS MCPCIA_HAE_MEM(4) +#endif +#define MCPCIA_IACK_SC _MCPCIA_IACK_SC(4) + +/* + * The canonical non-remaped I/O and MEM addresses have these values + * subtracted out. This is arranged so that folks manipulating ISA + * devices can use their familiar numbers and have them map to bus 0. + */ + +#define MCPCIA_IO_BIAS MCPCIA_IO(4) +#define MCPCIA_MEM_BIAS MCPCIA_DENSE(4) + +/* Offset between ram physical addresses and pci64 DAC bus addresses. */ +#define MCPCIA_DAC_OFFSET (1UL << 40) + +/* + * Data structure for handling MCPCIA machine checks: + */ +struct el_MCPCIA_uncorrected_frame_mcheck { + struct el_common header; + struct el_common_EV5_uncorrectable_mcheck procdata; +}; + + +#ifdef __KERNEL__ + +#ifndef __EXTERN_INLINE +#define __EXTERN_INLINE extern inline +#define __IO_EXTERN_INLINE +#endif + +/* + * I/O functions: + * + * MCPCIA, the RAWHIDE family PCI/memory support chipset for the EV5 (21164) + * and EV56 (21164a) processors, can use either a sparse address mapping + * scheme, or the so-called byte-word PCI address space, to get at PCI memory + * and I/O. + * + * Unfortunately, we can't use BWIO with EV5, so for now, we always use SPARSE. + */ + +/* + * Memory functions. 64-bit and 32-bit accesses are done through + * dense memory space, everything else through sparse space. + * + * For reading and writing 8 and 16 bit quantities we need to + * go through one of the three sparse address mapping regions + * and use the HAE_MEM CSR to provide some bits of the address. + * The following few routines use only sparse address region 1 + * which gives 1Gbyte of accessible space which relates exactly + * to the amount of PCI memory mapping *into* system address space. + * See p 6-17 of the specification but it looks something like this: + * + * 21164 Address: + * + * 3 2 1 + * 9876543210987654321098765432109876543210 + * 1ZZZZ0.PCI.QW.Address............BBLL + * + * ZZ = SBZ + * BB = Byte offset + * LL = Transfer length + * + * PCI Address: + * + * 3 2 1 + * 10987654321098765432109876543210 + * HHH....PCI.QW.Address........ 00 + * + * HHH = 31:29 HAE_MEM CSR + * + */ + +#define vip volatile int __force * +#define vuip volatile unsigned int __force * + +#ifndef MCPCIA_ONE_HAE_WINDOW +#define MCPCIA_FROB_MMIO \ + if (__mcpcia_is_mmio(hose)) { \ + set_hae(hose & 0xffffffff); \ + hose = hose - MCPCIA_DENSE(4) + MCPCIA_SPARSE(4); \ + } +#else +#define MCPCIA_FROB_MMIO \ + if (__mcpcia_is_mmio(hose)) { \ + hose = hose - MCPCIA_DENSE(4) + MCPCIA_SPARSE(4); \ + } +#endif + +extern inline int __mcpcia_is_mmio(unsigned long addr) +{ + return (addr & 0x80000000UL) == 0; +} + +__EXTERN_INLINE unsigned int mcpcia_ioread8(void __iomem *xaddr) +{ + unsigned long addr = (unsigned long)xaddr & MCPCIA_MEM_MASK; + unsigned long hose = (unsigned long)xaddr & ~MCPCIA_MEM_MASK; + unsigned long result; + + MCPCIA_FROB_MMIO; + + result = *(vip) ((addr << 5) + hose + 0x00); + return __kernel_extbl(result, addr & 3); +} + +__EXTERN_INLINE void mcpcia_iowrite8(u8 b, void __iomem *xaddr) +{ + unsigned long addr = (unsigned long)xaddr & MCPCIA_MEM_MASK; + unsigned long hose = (unsigned long)xaddr & ~MCPCIA_MEM_MASK; + unsigned long w; + + MCPCIA_FROB_MMIO; + + w = __kernel_insbl(b, addr & 3); + *(vuip) ((addr << 5) + hose + 0x00) = w; +} + +__EXTERN_INLINE unsigned int mcpcia_ioread16(void __iomem *xaddr) +{ + unsigned long addr = (unsigned long)xaddr & MCPCIA_MEM_MASK; + unsigned long hose = (unsigned long)xaddr & ~MCPCIA_MEM_MASK; + unsigned long result; + + MCPCIA_FROB_MMIO; + + result = *(vip) ((addr << 5) + hose + 0x08); + return __kernel_extwl(result, addr & 3); +} + +__EXTERN_INLINE void mcpcia_iowrite16(u16 b, void __iomem *xaddr) +{ + unsigned long addr = (unsigned long)xaddr & MCPCIA_MEM_MASK; + unsigned long hose = (unsigned long)xaddr & ~MCPCIA_MEM_MASK; + unsigned long w; + + MCPCIA_FROB_MMIO; + + w = __kernel_inswl(b, addr & 3); + *(vuip) ((addr << 5) + hose + 0x08) = w; +} + +__EXTERN_INLINE unsigned int mcpcia_ioread32(void __iomem *xaddr) +{ + unsigned long addr = (unsigned long)xaddr; + + if (!__mcpcia_is_mmio(addr)) + addr = ((addr & 0xffff) << 5) + (addr & ~0xfffful) + 0x18; + + return *(vuip)addr; +} + +__EXTERN_INLINE void mcpcia_iowrite32(u32 b, void __iomem *xaddr) +{ + unsigned long addr = (unsigned long)xaddr; + + if (!__mcpcia_is_mmio(addr)) + addr = ((addr & 0xffff) << 5) + (addr & ~0xfffful) + 0x18; + + *(vuip)addr = b; +} + + +__EXTERN_INLINE void __iomem *mcpcia_ioportmap(unsigned long addr) +{ + return (void __iomem *)(addr + MCPCIA_IO_BIAS); +} + +__EXTERN_INLINE void __iomem *mcpcia_ioremap(unsigned long addr, + unsigned long size) +{ + return (void __iomem *)(addr + MCPCIA_MEM_BIAS); +} + +__EXTERN_INLINE int mcpcia_is_ioaddr(unsigned long addr) +{ + return addr >= MCPCIA_SPARSE(0); +} + +__EXTERN_INLINE int mcpcia_is_mmio(const volatile void __iomem *xaddr) +{ + unsigned long addr = (unsigned long) xaddr; + return __mcpcia_is_mmio(addr); +} + +#undef MCPCIA_FROB_MMIO + +#undef vip +#undef vuip + +#undef __IO_PREFIX +#define __IO_PREFIX mcpcia +#define mcpcia_trivial_rw_bw 2 +#define mcpcia_trivial_rw_lq 1 +#define mcpcia_trivial_io_bw 0 +#define mcpcia_trivial_io_lq 0 +#define mcpcia_trivial_iounmap 1 +#include <asm/io_trivial.h> + +#ifdef __IO_EXTERN_INLINE +#undef __EXTERN_INLINE +#undef __IO_EXTERN_INLINE +#endif + +#endif /* __KERNEL__ */ + +#endif /* __ALPHA_MCPCIA__H__ */ diff --git a/arch/alpha/include/asm/core_polaris.h b/arch/alpha/include/asm/core_polaris.h new file mode 100644 index 000000000..2f966b646 --- /dev/null +++ b/arch/alpha/include/asm/core_polaris.h @@ -0,0 +1,110 @@ +#ifndef __ALPHA_POLARIS__H__ +#define __ALPHA_POLARIS__H__ + +#include <linux/types.h> +#include <asm/compiler.h> + +/* + * POLARIS is the internal name for a core logic chipset which provides + * memory controller and PCI access for the 21164PC chip based systems. + * + * This file is based on: + * + * Polaris System Controller + * Device Functional Specification + * 22-Jan-98 + * Rev. 4.2 + * + */ + +/* Polaris memory regions */ +#define POLARIS_SPARSE_MEM_BASE (IDENT_ADDR + 0xf800000000UL) +#define POLARIS_DENSE_MEM_BASE (IDENT_ADDR + 0xf900000000UL) +#define POLARIS_SPARSE_IO_BASE (IDENT_ADDR + 0xf980000000UL) +#define POLARIS_SPARSE_CONFIG_BASE (IDENT_ADDR + 0xf9c0000000UL) +#define POLARIS_IACK_BASE (IDENT_ADDR + 0xf9f8000000UL) +#define POLARIS_DENSE_IO_BASE (IDENT_ADDR + 0xf9fc000000UL) +#define POLARIS_DENSE_CONFIG_BASE (IDENT_ADDR + 0xf9fe000000UL) + +#define POLARIS_IACK_SC POLARIS_IACK_BASE + +/* The Polaris command/status registers live in PCI Config space for + * bus 0/device 0. As such, they may be bytes, words, or doublewords. + */ +#define POLARIS_W_VENID (POLARIS_DENSE_CONFIG_BASE) +#define POLARIS_W_DEVID (POLARIS_DENSE_CONFIG_BASE+2) +#define POLARIS_W_CMD (POLARIS_DENSE_CONFIG_BASE+4) +#define POLARIS_W_STATUS (POLARIS_DENSE_CONFIG_BASE+6) + +/* + * Data structure for handling POLARIS machine checks: + */ +struct el_POLARIS_sysdata_mcheck { + u_long psc_status; + u_long psc_pcictl0; + u_long psc_pcictl1; + u_long psc_pcictl2; +}; + +#ifdef __KERNEL__ + +#ifndef __EXTERN_INLINE +#define __EXTERN_INLINE extern inline +#define __IO_EXTERN_INLINE +#endif + +/* + * I/O functions: + * + * POLARIS, the PCI/memory support chipset for the PCA56 (21164PC) + * processors, can use either a sparse address mapping scheme, or the + * so-called byte-word PCI address space, to get at PCI memory and I/O. + * + * However, we will support only the BWX form. + */ + +/* + * Memory functions. Polaris allows all accesses (byte/word + * as well as long/quad) to be done through dense space. + * + * We will only support DENSE access via BWX insns. + */ + +__EXTERN_INLINE void __iomem *polaris_ioportmap(unsigned long addr) +{ + return (void __iomem *)(addr + POLARIS_DENSE_IO_BASE); +} + +__EXTERN_INLINE void __iomem *polaris_ioremap(unsigned long addr, + unsigned long size) +{ + return (void __iomem *)(addr + POLARIS_DENSE_MEM_BASE); +} + +__EXTERN_INLINE int polaris_is_ioaddr(unsigned long addr) +{ + return addr >= POLARIS_SPARSE_MEM_BASE; +} + +__EXTERN_INLINE int polaris_is_mmio(const volatile void __iomem *addr) +{ + return (unsigned long)addr < POLARIS_SPARSE_IO_BASE; +} + +#undef __IO_PREFIX +#define __IO_PREFIX polaris +#define polaris_trivial_rw_bw 1 +#define polaris_trivial_rw_lq 1 +#define polaris_trivial_io_bw 1 +#define polaris_trivial_io_lq 1 +#define polaris_trivial_iounmap 1 +#include <asm/io_trivial.h> + +#ifdef __IO_EXTERN_INLINE +#undef __EXTERN_INLINE +#undef __IO_EXTERN_INLINE +#endif + +#endif /* __KERNEL__ */ + +#endif /* __ALPHA_POLARIS__H__ */ diff --git a/arch/alpha/include/asm/core_t2.h b/arch/alpha/include/asm/core_t2.h new file mode 100644 index 000000000..ade9d92e6 --- /dev/null +++ b/arch/alpha/include/asm/core_t2.h @@ -0,0 +1,614 @@ +#ifndef __ALPHA_T2__H__ +#define __ALPHA_T2__H__ + +/* Fit everything into one 128MB HAE window. */ +#define T2_ONE_HAE_WINDOW 1 + +#include <linux/types.h> +#include <linux/spinlock.h> +#include <asm/compiler.h> + +/* + * T2 is the internal name for the core logic chipset which provides + * memory controller and PCI access for the SABLE-based systems. + * + * This file is based on: + * + * SABLE I/O Specification + * Revision/Update Information: 1.3 + * + * jestabro@amt.tay1.dec.com Initial Version. + * + */ + +#define T2_MEM_R1_MASK 0x07ffffff /* Mem sparse region 1 mask is 27 bits */ + +/* GAMMA-SABLE is a SABLE with EV5-based CPUs */ +/* All LYNX machines, EV4 or EV5, use the GAMMA bias also */ +#define _GAMMA_BIAS 0x8000000000UL + +#if defined(CONFIG_ALPHA_GENERIC) +#define GAMMA_BIAS alpha_mv.sys.t2.gamma_bias +#elif defined(CONFIG_ALPHA_GAMMA) +#define GAMMA_BIAS _GAMMA_BIAS +#else +#define GAMMA_BIAS 0 +#endif + +/* + * Memory spaces: + */ +#define T2_CONF (IDENT_ADDR + GAMMA_BIAS + 0x390000000UL) +#define T2_IO (IDENT_ADDR + GAMMA_BIAS + 0x3a0000000UL) +#define T2_SPARSE_MEM (IDENT_ADDR + GAMMA_BIAS + 0x200000000UL) +#define T2_DENSE_MEM (IDENT_ADDR + GAMMA_BIAS + 0x3c0000000UL) + +#define T2_IOCSR (IDENT_ADDR + GAMMA_BIAS + 0x38e000000UL) +#define T2_CERR1 (IDENT_ADDR + GAMMA_BIAS + 0x38e000020UL) +#define T2_CERR2 (IDENT_ADDR + GAMMA_BIAS + 0x38e000040UL) +#define T2_CERR3 (IDENT_ADDR + GAMMA_BIAS + 0x38e000060UL) +#define T2_PERR1 (IDENT_ADDR + GAMMA_BIAS + 0x38e000080UL) +#define T2_PERR2 (IDENT_ADDR + GAMMA_BIAS + 0x38e0000a0UL) +#define T2_PSCR (IDENT_ADDR + GAMMA_BIAS + 0x38e0000c0UL) +#define T2_HAE_1 (IDENT_ADDR + GAMMA_BIAS + 0x38e0000e0UL) +#define T2_HAE_2 (IDENT_ADDR + GAMMA_BIAS + 0x38e000100UL) +#define T2_HBASE (IDENT_ADDR + GAMMA_BIAS + 0x38e000120UL) +#define T2_WBASE1 (IDENT_ADDR + GAMMA_BIAS + 0x38e000140UL) +#define T2_WMASK1 (IDENT_ADDR + GAMMA_BIAS + 0x38e000160UL) +#define T2_TBASE1 (IDENT_ADDR + GAMMA_BIAS + 0x38e000180UL) +#define T2_WBASE2 (IDENT_ADDR + GAMMA_BIAS + 0x38e0001a0UL) +#define T2_WMASK2 (IDENT_ADDR + GAMMA_BIAS + 0x38e0001c0UL) +#define T2_TBASE2 (IDENT_ADDR + GAMMA_BIAS + 0x38e0001e0UL) +#define T2_TLBBR (IDENT_ADDR + GAMMA_BIAS + 0x38e000200UL) +#define T2_IVR (IDENT_ADDR + GAMMA_BIAS + 0x38e000220UL) +#define T2_HAE_3 (IDENT_ADDR + GAMMA_BIAS + 0x38e000240UL) +#define T2_HAE_4 (IDENT_ADDR + GAMMA_BIAS + 0x38e000260UL) + +/* The CSRs below are T3/T4 only */ +#define T2_WBASE3 (IDENT_ADDR + GAMMA_BIAS + 0x38e000280UL) +#define T2_WMASK3 (IDENT_ADDR + GAMMA_BIAS + 0x38e0002a0UL) +#define T2_TBASE3 (IDENT_ADDR + GAMMA_BIAS + 0x38e0002c0UL) + +#define T2_TDR0 (IDENT_ADDR + GAMMA_BIAS + 0x38e000300UL) +#define T2_TDR1 (IDENT_ADDR + GAMMA_BIAS + 0x38e000320UL) +#define T2_TDR2 (IDENT_ADDR + GAMMA_BIAS + 0x38e000340UL) +#define T2_TDR3 (IDENT_ADDR + GAMMA_BIAS + 0x38e000360UL) +#define T2_TDR4 (IDENT_ADDR + GAMMA_BIAS + 0x38e000380UL) +#define T2_TDR5 (IDENT_ADDR + GAMMA_BIAS + 0x38e0003a0UL) +#define T2_TDR6 (IDENT_ADDR + GAMMA_BIAS + 0x38e0003c0UL) +#define T2_TDR7 (IDENT_ADDR + GAMMA_BIAS + 0x38e0003e0UL) + +#define T2_WBASE4 (IDENT_ADDR + GAMMA_BIAS + 0x38e000400UL) +#define T2_WMASK4 (IDENT_ADDR + GAMMA_BIAS + 0x38e000420UL) +#define T2_TBASE4 (IDENT_ADDR + GAMMA_BIAS + 0x38e000440UL) + +#define T2_AIR (IDENT_ADDR + GAMMA_BIAS + 0x38e000460UL) +#define T2_VAR (IDENT_ADDR + GAMMA_BIAS + 0x38e000480UL) +#define T2_DIR (IDENT_ADDR + GAMMA_BIAS + 0x38e0004a0UL) +#define T2_ICE (IDENT_ADDR + GAMMA_BIAS + 0x38e0004c0UL) + +#ifndef T2_ONE_HAE_WINDOW +#define T2_HAE_ADDRESS T2_HAE_1 +#endif + +/* T2 CSRs are in the non-cachable primary IO space from 3.8000.0000 to + 3.8fff.ffff + * + * +--------------+ 3 8000 0000 + * | CPU 0 CSRs | + * +--------------+ 3 8100 0000 + * | CPU 1 CSRs | + * +--------------+ 3 8200 0000 + * | CPU 2 CSRs | + * +--------------+ 3 8300 0000 + * | CPU 3 CSRs | + * +--------------+ 3 8400 0000 + * | CPU Reserved | + * +--------------+ 3 8700 0000 + * | Mem Reserved | + * +--------------+ 3 8800 0000 + * | Mem 0 CSRs | + * +--------------+ 3 8900 0000 + * | Mem 1 CSRs | + * +--------------+ 3 8a00 0000 + * | Mem 2 CSRs | + * +--------------+ 3 8b00 0000 + * | Mem 3 CSRs | + * +--------------+ 3 8c00 0000 + * | Mem Reserved | + * +--------------+ 3 8e00 0000 + * | PCI Bridge | + * +--------------+ 3 8f00 0000 + * | Expansion IO | + * +--------------+ 3 9000 0000 + * + * + */ +#define T2_CPU0_BASE (IDENT_ADDR + GAMMA_BIAS + 0x380000000L) +#define T2_CPU1_BASE (IDENT_ADDR + GAMMA_BIAS + 0x381000000L) +#define T2_CPU2_BASE (IDENT_ADDR + GAMMA_BIAS + 0x382000000L) +#define T2_CPU3_BASE (IDENT_ADDR + GAMMA_BIAS + 0x383000000L) + +#define T2_CPUn_BASE(n) (T2_CPU0_BASE + (((n)&3) * 0x001000000L)) + +#define T2_MEM0_BASE (IDENT_ADDR + GAMMA_BIAS + 0x388000000L) +#define T2_MEM1_BASE (IDENT_ADDR + GAMMA_BIAS + 0x389000000L) +#define T2_MEM2_BASE (IDENT_ADDR + GAMMA_BIAS + 0x38a000000L) +#define T2_MEM3_BASE (IDENT_ADDR + GAMMA_BIAS + 0x38b000000L) + + +/* + * Sable CPU Module CSRS + * + * These are CSRs for hardware other than the CPU chip on the CPU module. + * The CPU module has Backup Cache control logic, Cbus control logic, and + * interrupt control logic on it. There is a duplicate tag store to speed + * up maintaining cache coherency. + */ + +struct sable_cpu_csr { + unsigned long bcc; long fill_00[3]; /* Backup Cache Control */ + unsigned long bcce; long fill_01[3]; /* Backup Cache Correctable Error */ + unsigned long bccea; long fill_02[3]; /* B-Cache Corr Err Address Latch */ + unsigned long bcue; long fill_03[3]; /* B-Cache Uncorrectable Error */ + unsigned long bcuea; long fill_04[3]; /* B-Cache Uncorr Err Addr Latch */ + unsigned long dter; long fill_05[3]; /* Duplicate Tag Error */ + unsigned long cbctl; long fill_06[3]; /* CBus Control */ + unsigned long cbe; long fill_07[3]; /* CBus Error */ + unsigned long cbeal; long fill_08[3]; /* CBus Error Addr Latch low */ + unsigned long cbeah; long fill_09[3]; /* CBus Error Addr Latch high */ + unsigned long pmbx; long fill_10[3]; /* Processor Mailbox */ + unsigned long ipir; long fill_11[3]; /* Inter-Processor Int Request */ + unsigned long sic; long fill_12[3]; /* System Interrupt Clear */ + unsigned long adlk; long fill_13[3]; /* Address Lock (LDxL/STxC) */ + unsigned long madrl; long fill_14[3]; /* CBus Miss Address */ + unsigned long rev; long fill_15[3]; /* CMIC Revision */ +}; + +/* + * Data structure for handling T2 machine checks: + */ +struct el_t2_frame_header { + unsigned int elcf_fid; /* Frame ID (from above) */ + unsigned int elcf_size; /* Size of frame in bytes */ +}; + +struct el_t2_procdata_mcheck { + unsigned long elfmc_paltemp[32]; /* PAL TEMP REGS. */ + /* EV4-specific fields */ + unsigned long elfmc_exc_addr; /* Addr of excepting insn. */ + unsigned long elfmc_exc_sum; /* Summary of arith traps. */ + unsigned long elfmc_exc_mask; /* Exception mask (from exc_sum). */ + unsigned long elfmc_iccsr; /* IBox hardware enables. */ + unsigned long elfmc_pal_base; /* Base address for PALcode. */ + unsigned long elfmc_hier; /* Hardware Interrupt Enable. */ + unsigned long elfmc_hirr; /* Hardware Interrupt Request. */ + unsigned long elfmc_mm_csr; /* D-stream fault info. */ + unsigned long elfmc_dc_stat; /* D-cache status (ECC/Parity Err). */ + unsigned long elfmc_dc_addr; /* EV3 Phys Addr for ECC/DPERR. */ + unsigned long elfmc_abox_ctl; /* ABox Control Register. */ + unsigned long elfmc_biu_stat; /* BIU Status. */ + unsigned long elfmc_biu_addr; /* BUI Address. */ + unsigned long elfmc_biu_ctl; /* BIU Control. */ + unsigned long elfmc_fill_syndrome; /* For correcting ECC errors. */ + unsigned long elfmc_fill_addr;/* Cache block which was being read. */ + unsigned long elfmc_va; /* Effective VA of fault or miss. */ + unsigned long elfmc_bc_tag; /* Backup Cache Tag Probe Results. */ +}; + +/* + * Sable processor specific Machine Check Data segment. + */ + +struct el_t2_logout_header { + unsigned int elfl_size; /* size in bytes of logout area. */ + unsigned int elfl_sbz1:31; /* Should be zero. */ + unsigned int elfl_retry:1; /* Retry flag. */ + unsigned int elfl_procoffset; /* Processor-specific offset. */ + unsigned int elfl_sysoffset; /* Offset of system-specific. */ + unsigned int elfl_error_type; /* PAL error type code. */ + unsigned int elfl_frame_rev; /* PAL Frame revision. */ +}; +struct el_t2_sysdata_mcheck { + unsigned long elcmc_bcc; /* CSR 0 */ + unsigned long elcmc_bcce; /* CSR 1 */ + unsigned long elcmc_bccea; /* CSR 2 */ + unsigned long elcmc_bcue; /* CSR 3 */ + unsigned long elcmc_bcuea; /* CSR 4 */ + unsigned long elcmc_dter; /* CSR 5 */ + unsigned long elcmc_cbctl; /* CSR 6 */ + unsigned long elcmc_cbe; /* CSR 7 */ + unsigned long elcmc_cbeal; /* CSR 8 */ + unsigned long elcmc_cbeah; /* CSR 9 */ + unsigned long elcmc_pmbx; /* CSR 10 */ + unsigned long elcmc_ipir; /* CSR 11 */ + unsigned long elcmc_sic; /* CSR 12 */ + unsigned long elcmc_adlk; /* CSR 13 */ + unsigned long elcmc_madrl; /* CSR 14 */ + unsigned long elcmc_crrev4; /* CSR 15 */ +}; + +/* + * Sable memory error frame - sable pfms section 3.42 + */ +struct el_t2_data_memory { + struct el_t2_frame_header elcm_hdr; /* ID$MEM-FERR = 0x08 */ + unsigned int elcm_module; /* Module id. */ + unsigned int elcm_res04; /* Reserved. */ + unsigned long elcm_merr; /* CSR0: Error Reg 1. */ + unsigned long elcm_mcmd1; /* CSR1: Command Trap 1. */ + unsigned long elcm_mcmd2; /* CSR2: Command Trap 2. */ + unsigned long elcm_mconf; /* CSR3: Configuration. */ + unsigned long elcm_medc1; /* CSR4: EDC Status 1. */ + unsigned long elcm_medc2; /* CSR5: EDC Status 2. */ + unsigned long elcm_medcc; /* CSR6: EDC Control. */ + unsigned long elcm_msctl; /* CSR7: Stream Buffer Control. */ + unsigned long elcm_mref; /* CSR8: Refresh Control. */ + unsigned long elcm_filter; /* CSR9: CRD Filter Control. */ +}; + + +/* + * Sable other CPU error frame - sable pfms section 3.43 + */ +struct el_t2_data_other_cpu { + short elco_cpuid; /* CPU ID */ + short elco_res02[3]; + unsigned long elco_bcc; /* CSR 0 */ + unsigned long elco_bcce; /* CSR 1 */ + unsigned long elco_bccea; /* CSR 2 */ + unsigned long elco_bcue; /* CSR 3 */ + unsigned long elco_bcuea; /* CSR 4 */ + unsigned long elco_dter; /* CSR 5 */ + unsigned long elco_cbctl; /* CSR 6 */ + unsigned long elco_cbe; /* CSR 7 */ + unsigned long elco_cbeal; /* CSR 8 */ + unsigned long elco_cbeah; /* CSR 9 */ + unsigned long elco_pmbx; /* CSR 10 */ + unsigned long elco_ipir; /* CSR 11 */ + unsigned long elco_sic; /* CSR 12 */ + unsigned long elco_adlk; /* CSR 13 */ + unsigned long elco_madrl; /* CSR 14 */ + unsigned long elco_crrev4; /* CSR 15 */ +}; + +/* + * Sable other CPU error frame - sable pfms section 3.44 + */ +struct el_t2_data_t2{ + struct el_t2_frame_header elct_hdr; /* ID$T2-FRAME */ + unsigned long elct_iocsr; /* IO Control and Status Register */ + unsigned long elct_cerr1; /* Cbus Error Register 1 */ + unsigned long elct_cerr2; /* Cbus Error Register 2 */ + unsigned long elct_cerr3; /* Cbus Error Register 3 */ + unsigned long elct_perr1; /* PCI Error Register 1 */ + unsigned long elct_perr2; /* PCI Error Register 2 */ + unsigned long elct_hae0_1; /* High Address Extension Register 1 */ + unsigned long elct_hae0_2; /* High Address Extension Register 2 */ + unsigned long elct_hbase; /* High Base Register */ + unsigned long elct_wbase1; /* Window Base Register 1 */ + unsigned long elct_wmask1; /* Window Mask Register 1 */ + unsigned long elct_tbase1; /* Translated Base Register 1 */ + unsigned long elct_wbase2; /* Window Base Register 2 */ + unsigned long elct_wmask2; /* Window Mask Register 2 */ + unsigned long elct_tbase2; /* Translated Base Register 2 */ + unsigned long elct_tdr0; /* TLB Data Register 0 */ + unsigned long elct_tdr1; /* TLB Data Register 1 */ + unsigned long elct_tdr2; /* TLB Data Register 2 */ + unsigned long elct_tdr3; /* TLB Data Register 3 */ + unsigned long elct_tdr4; /* TLB Data Register 4 */ + unsigned long elct_tdr5; /* TLB Data Register 5 */ + unsigned long elct_tdr6; /* TLB Data Register 6 */ + unsigned long elct_tdr7; /* TLB Data Register 7 */ +}; + +/* + * Sable error log data structure - sable pfms section 3.40 + */ +struct el_t2_data_corrected { + unsigned long elcpb_biu_stat; + unsigned long elcpb_biu_addr; + unsigned long elcpb_biu_ctl; + unsigned long elcpb_fill_syndrome; + unsigned long elcpb_fill_addr; + unsigned long elcpb_bc_tag; +}; + +/* + * Sable error log data structure + * Note there are 4 memory slots on sable (see t2.h) + */ +struct el_t2_frame_mcheck { + struct el_t2_frame_header elfmc_header; /* ID$P-FRAME_MCHECK */ + struct el_t2_logout_header elfmc_hdr; + struct el_t2_procdata_mcheck elfmc_procdata; + struct el_t2_sysdata_mcheck elfmc_sysdata; + struct el_t2_data_t2 elfmc_t2data; + struct el_t2_data_memory elfmc_memdata[4]; + struct el_t2_frame_header elfmc_footer; /* empty */ +}; + + +/* + * Sable error log data structures on memory errors + */ +struct el_t2_frame_corrected { + struct el_t2_frame_header elfcc_header; /* ID$P-BC-COR */ + struct el_t2_logout_header elfcc_hdr; + struct el_t2_data_corrected elfcc_procdata; +/* struct el_t2_data_t2 elfcc_t2data; */ +/* struct el_t2_data_memory elfcc_memdata[4]; */ + struct el_t2_frame_header elfcc_footer; /* empty */ +}; + + +#ifdef __KERNEL__ + +#ifndef __EXTERN_INLINE +#define __EXTERN_INLINE extern inline +#define __IO_EXTERN_INLINE +#endif + +/* + * I/O functions: + * + * T2 (the core logic PCI/memory support chipset for the SABLE + * series of processors uses a sparse address mapping scheme to + * get at PCI memory and I/O. + */ + +#define vip volatile int * +#define vuip volatile unsigned int * + +extern inline u8 t2_inb(unsigned long addr) +{ + long result = *(vip) ((addr << 5) + T2_IO + 0x00); + return __kernel_extbl(result, addr & 3); +} + +extern inline void t2_outb(u8 b, unsigned long addr) +{ + unsigned long w; + + w = __kernel_insbl(b, addr & 3); + *(vuip) ((addr << 5) + T2_IO + 0x00) = w; + mb(); +} + +extern inline u16 t2_inw(unsigned long addr) +{ + long result = *(vip) ((addr << 5) + T2_IO + 0x08); + return __kernel_extwl(result, addr & 3); +} + +extern inline void t2_outw(u16 b, unsigned long addr) +{ + unsigned long w; + + w = __kernel_inswl(b, addr & 3); + *(vuip) ((addr << 5) + T2_IO + 0x08) = w; + mb(); +} + +extern inline u32 t2_inl(unsigned long addr) +{ + return *(vuip) ((addr << 5) + T2_IO + 0x18); +} + +extern inline void t2_outl(u32 b, unsigned long addr) +{ + *(vuip) ((addr << 5) + T2_IO + 0x18) = b; + mb(); +} + + +/* + * Memory functions. + * + * For reading and writing 8 and 16 bit quantities we need to + * go through one of the three sparse address mapping regions + * and use the HAE_MEM CSR to provide some bits of the address. + * The following few routines use only sparse address region 1 + * which gives 1Gbyte of accessible space which relates exactly + * to the amount of PCI memory mapping *into* system address space. + * See p 6-17 of the specification but it looks something like this: + * + * 21164 Address: + * + * 3 2 1 + * 9876543210987654321098765432109876543210 + * 1ZZZZ0.PCI.QW.Address............BBLL + * + * ZZ = SBZ + * BB = Byte offset + * LL = Transfer length + * + * PCI Address: + * + * 3 2 1 + * 10987654321098765432109876543210 + * HHH....PCI.QW.Address........ 00 + * + * HHH = 31:29 HAE_MEM CSR + * + */ + +#ifdef T2_ONE_HAE_WINDOW +#define t2_set_hae +#else +#define t2_set_hae { \ + unsigned long msb = addr >> 27; \ + addr &= T2_MEM_R1_MASK; \ + set_hae(msb); \ +} +#endif + +/* + * NOTE: take T2_DENSE_MEM off in each readX/writeX routine, since + * they may be called directly, rather than through the + * ioreadNN/iowriteNN routines. + */ + +__EXTERN_INLINE u8 t2_readb(const volatile void __iomem *xaddr) +{ + unsigned long addr = (unsigned long) xaddr - T2_DENSE_MEM; + unsigned long result; + + t2_set_hae; + + result = *(vip) ((addr << 5) + T2_SPARSE_MEM + 0x00); + return __kernel_extbl(result, addr & 3); +} + +__EXTERN_INLINE u16 t2_readw(const volatile void __iomem *xaddr) +{ + unsigned long addr = (unsigned long) xaddr - T2_DENSE_MEM; + unsigned long result; + + t2_set_hae; + + result = *(vuip) ((addr << 5) + T2_SPARSE_MEM + 0x08); + return __kernel_extwl(result, addr & 3); +} + +/* + * On SABLE with T2, we must use SPARSE memory even for 32-bit access, + * because we cannot access all of DENSE without changing its HAE. + */ +__EXTERN_INLINE u32 t2_readl(const volatile void __iomem *xaddr) +{ + unsigned long addr = (unsigned long) xaddr - T2_DENSE_MEM; + unsigned long result; + + t2_set_hae; + + result = *(vuip) ((addr << 5) + T2_SPARSE_MEM + 0x18); + return result & 0xffffffffUL; +} + +__EXTERN_INLINE u64 t2_readq(const volatile void __iomem *xaddr) +{ + unsigned long addr = (unsigned long) xaddr - T2_DENSE_MEM; + unsigned long r0, r1, work; + + t2_set_hae; + + work = (addr << 5) + T2_SPARSE_MEM + 0x18; + r0 = *(vuip)(work); + r1 = *(vuip)(work + (4 << 5)); + return r1 << 32 | r0; +} + +__EXTERN_INLINE void t2_writeb(u8 b, volatile void __iomem *xaddr) +{ + unsigned long addr = (unsigned long) xaddr - T2_DENSE_MEM; + unsigned long w; + + t2_set_hae; + + w = __kernel_insbl(b, addr & 3); + *(vuip) ((addr << 5) + T2_SPARSE_MEM + 0x00) = w; +} + +__EXTERN_INLINE void t2_writew(u16 b, volatile void __iomem *xaddr) +{ + unsigned long addr = (unsigned long) xaddr - T2_DENSE_MEM; + unsigned long w; + + t2_set_hae; + + w = __kernel_inswl(b, addr & 3); + *(vuip) ((addr << 5) + T2_SPARSE_MEM + 0x08) = w; +} + +/* + * On SABLE with T2, we must use SPARSE memory even for 32-bit access, + * because we cannot access all of DENSE without changing its HAE. + */ +__EXTERN_INLINE void t2_writel(u32 b, volatile void __iomem *xaddr) +{ + unsigned long addr = (unsigned long) xaddr - T2_DENSE_MEM; + + t2_set_hae; + + *(vuip) ((addr << 5) + T2_SPARSE_MEM + 0x18) = b; +} + +__EXTERN_INLINE void t2_writeq(u64 b, volatile void __iomem *xaddr) +{ + unsigned long addr = (unsigned long) xaddr - T2_DENSE_MEM; + unsigned long work; + + t2_set_hae; + + work = (addr << 5) + T2_SPARSE_MEM + 0x18; + *(vuip)work = b; + *(vuip)(work + (4 << 5)) = b >> 32; +} + +__EXTERN_INLINE void __iomem *t2_ioportmap(unsigned long addr) +{ + return (void __iomem *)(addr + T2_IO); +} + +__EXTERN_INLINE void __iomem *t2_ioremap(unsigned long addr, + unsigned long size) +{ + return (void __iomem *)(addr + T2_DENSE_MEM); +} + +__EXTERN_INLINE int t2_is_ioaddr(unsigned long addr) +{ + return (long)addr >= 0; +} + +__EXTERN_INLINE int t2_is_mmio(const volatile void __iomem *addr) +{ + return (unsigned long)addr >= T2_DENSE_MEM; +} + +/* New-style ioread interface. The mmio routines are so ugly for T2 that + it doesn't make sense to merge the pio and mmio routines. */ + +#define IOPORT(OS, NS) \ +__EXTERN_INLINE unsigned int t2_ioread##NS(void __iomem *xaddr) \ +{ \ + if (t2_is_mmio(xaddr)) \ + return t2_read##OS(xaddr); \ + else \ + return t2_in##OS((unsigned long)xaddr - T2_IO); \ +} \ +__EXTERN_INLINE void t2_iowrite##NS(u##NS b, void __iomem *xaddr) \ +{ \ + if (t2_is_mmio(xaddr)) \ + t2_write##OS(b, xaddr); \ + else \ + t2_out##OS(b, (unsigned long)xaddr - T2_IO); \ +} + +IOPORT(b, 8) +IOPORT(w, 16) +IOPORT(l, 32) + +#undef IOPORT + +#undef vip +#undef vuip + +#undef __IO_PREFIX +#define __IO_PREFIX t2 +#define t2_trivial_rw_bw 0 +#define t2_trivial_rw_lq 0 +#define t2_trivial_io_bw 0 +#define t2_trivial_io_lq 0 +#define t2_trivial_iounmap 1 +#include <asm/io_trivial.h> + +#ifdef __IO_EXTERN_INLINE +#undef __EXTERN_INLINE +#undef __IO_EXTERN_INLINE +#endif + +#endif /* __KERNEL__ */ + +#endif /* __ALPHA_T2__H__ */ diff --git a/arch/alpha/include/asm/core_titan.h b/arch/alpha/include/asm/core_titan.h new file mode 100644 index 000000000..8cf79d121 --- /dev/null +++ b/arch/alpha/include/asm/core_titan.h @@ -0,0 +1,409 @@ +#ifndef __ALPHA_TITAN__H__ +#define __ALPHA_TITAN__H__ + +#include <linux/types.h> +#include <asm/compiler.h> + +/* + * TITAN is the internal names for a core logic chipset which provides + * memory controller and PCI/AGP access for 21264 based systems. + * + * This file is based on: + * + * Titan Chipset Engineering Specification + * Revision 0.12 + * 13 July 1999 + * + */ + +/* XXX: Do we need to conditionalize on this? */ +#ifdef USE_48_BIT_KSEG +#define TI_BIAS 0x80000000000UL +#else +#define TI_BIAS 0x10000000000UL +#endif + +/* + * CChip, DChip, and PChip registers + */ + +typedef struct { + volatile unsigned long csr __attribute__((aligned(64))); +} titan_64; + +typedef struct { + titan_64 csc; + titan_64 mtr; + titan_64 misc; + titan_64 mpd; + titan_64 aar0; + titan_64 aar1; + titan_64 aar2; + titan_64 aar3; + titan_64 dim0; + titan_64 dim1; + titan_64 dir0; + titan_64 dir1; + titan_64 drir; + titan_64 prben; + titan_64 iic0; + titan_64 iic1; + titan_64 mpr0; + titan_64 mpr1; + titan_64 mpr2; + titan_64 mpr3; + titan_64 rsvd[2]; + titan_64 ttr; + titan_64 tdr; + titan_64 dim2; + titan_64 dim3; + titan_64 dir2; + titan_64 dir3; + titan_64 iic2; + titan_64 iic3; + titan_64 pwr; + titan_64 reserved[17]; + titan_64 cmonctla; + titan_64 cmonctlb; + titan_64 cmoncnt01; + titan_64 cmoncnt23; + titan_64 cpen; +} titan_cchip; + +typedef struct { + titan_64 dsc; + titan_64 str; + titan_64 drev; + titan_64 dsc2; +} titan_dchip; + +typedef struct { + titan_64 wsba[4]; + titan_64 wsm[4]; + titan_64 tba[4]; + titan_64 pctl; + titan_64 plat; + titan_64 reserved0[2]; + union { + struct { + titan_64 serror; + titan_64 serren; + titan_64 serrset; + titan_64 reserved0; + titan_64 gperror; + titan_64 gperren; + titan_64 gperrset; + titan_64 reserved1; + titan_64 gtlbiv; + titan_64 gtlbia; + titan_64 reserved2[2]; + titan_64 sctl; + titan_64 reserved3[3]; + } g; + struct { + titan_64 agperror; + titan_64 agperren; + titan_64 agperrset; + titan_64 agplastwr; + titan_64 aperror; + titan_64 aperren; + titan_64 aperrset; + titan_64 reserved0; + titan_64 atlbiv; + titan_64 atlbia; + titan_64 reserved1[6]; + } a; + } port_specific; + titan_64 sprst; + titan_64 reserved1[31]; +} titan_pachip_port; + +typedef struct { + titan_pachip_port g_port; + titan_pachip_port a_port; +} titan_pachip; + +#define TITAN_cchip ((titan_cchip *)(IDENT_ADDR+TI_BIAS+0x1A0000000UL)) +#define TITAN_dchip ((titan_dchip *)(IDENT_ADDR+TI_BIAS+0x1B0000800UL)) +#define TITAN_pachip0 ((titan_pachip *)(IDENT_ADDR+TI_BIAS+0x180000000UL)) +#define TITAN_pachip1 ((titan_pachip *)(IDENT_ADDR+TI_BIAS+0x380000000UL)) +extern unsigned TITAN_agp; +extern int TITAN_bootcpu; + +/* + * TITAN PA-chip Window Space Base Address register. + * (WSBA[0-2]) + */ +#define wsba_m_ena 0x1 +#define wsba_m_sg 0x2 +#define wsba_m_addr 0xFFF00000 +#define wmask_k_sz1gb 0x3FF00000 +union TPAchipWSBA { + struct { + unsigned wsba_v_ena : 1; + unsigned wsba_v_sg : 1; + unsigned wsba_v_rsvd1 : 18; + unsigned wsba_v_addr : 12; + unsigned wsba_v_rsvd2 : 32; + } wsba_r_bits; + int wsba_q_whole [2]; +}; + +/* + * TITAN PA-chip Control Register + * This definition covers both the G-Port GPCTL and the A-PORT APCTL. + * Bits <51:0> are the same in both cases. APCTL<63:52> are only + * applicable to AGP. + */ +#define pctl_m_fbtb 0x00000001 +#define pctl_m_thdis 0x00000002 +#define pctl_m_chaindis 0x00000004 +#define pctl_m_tgtlat 0x00000018 +#define pctl_m_hole 0x00000020 +#define pctl_m_mwin 0x00000040 +#define pctl_m_arbena 0x00000080 +#define pctl_m_prigrp 0x0000FF00 +#define pctl_m_ppri 0x00010000 +#define pctl_m_pcispd66 0x00020000 +#define pctl_m_cngstlt 0x003C0000 +#define pctl_m_ptpdesten 0x3FC00000 +#define pctl_m_dpcen 0x40000000 +#define pctl_m_apcen 0x0000000080000000UL +#define pctl_m_dcrtv 0x0000000300000000UL +#define pctl_m_en_stepping 0x0000000400000000UL +#define apctl_m_rsvd1 0x000FFFF800000000UL +#define apctl_m_agp_rate 0x0030000000000000UL +#define apctl_m_agp_sba_en 0x0040000000000000UL +#define apctl_m_agp_en 0x0080000000000000UL +#define apctl_m_rsvd2 0x0100000000000000UL +#define apctl_m_agp_present 0x0200000000000000UL +#define apctl_agp_hp_rd 0x1C00000000000000UL +#define apctl_agp_lp_rd 0xE000000000000000UL +#define gpctl_m_rsvd 0xFFFFFFF800000000UL +union TPAchipPCTL { + struct { + unsigned pctl_v_fbtb : 1; /* A/G [0] */ + unsigned pctl_v_thdis : 1; /* A/G [1] */ + unsigned pctl_v_chaindis : 1; /* A/G [2] */ + unsigned pctl_v_tgtlat : 2; /* A/G [4:3] */ + unsigned pctl_v_hole : 1; /* A/G [5] */ + unsigned pctl_v_mwin : 1; /* A/G [6] */ + unsigned pctl_v_arbena : 1; /* A/G [7] */ + unsigned pctl_v_prigrp : 8; /* A/G [15:8] */ + unsigned pctl_v_ppri : 1; /* A/G [16] */ + unsigned pctl_v_pcispd66 : 1; /* A/G [17] */ + unsigned pctl_v_cngstlt : 4; /* A/G [21:18] */ + unsigned pctl_v_ptpdesten : 8; /* A/G [29:22] */ + unsigned pctl_v_dpcen : 1; /* A/G [30] */ + unsigned pctl_v_apcen : 1; /* A/G [31] */ + unsigned pctl_v_dcrtv : 2; /* A/G [33:32] */ + unsigned pctl_v_en_stepping :1; /* A/G [34] */ + unsigned apctl_v_rsvd1 : 17; /* A [51:35] */ + unsigned apctl_v_agp_rate : 2; /* A [53:52] */ + unsigned apctl_v_agp_sba_en : 1; /* A [54] */ + unsigned apctl_v_agp_en : 1; /* A [55] */ + unsigned apctl_v_rsvd2 : 1; /* A [56] */ + unsigned apctl_v_agp_present : 1; /* A [57] */ + unsigned apctl_v_agp_hp_rd : 3; /* A [60:58] */ + unsigned apctl_v_agp_lp_rd : 3; /* A [63:61] */ + } pctl_r_bits; + unsigned int pctl_l_whole [2]; + unsigned long pctl_q_whole; +}; + +/* + * SERROR / SERREN / SERRSET + */ +union TPAchipSERR { + struct { + unsigned serr_v_lost_uecc : 1; /* [0] */ + unsigned serr_v_uecc : 1; /* [1] */ + unsigned serr_v_cre : 1; /* [2] */ + unsigned serr_v_nxio : 1; /* [3] */ + unsigned serr_v_lost_cre : 1; /* [4] */ + unsigned serr_v_rsvd0 : 10; /* [14:5] */ + unsigned serr_v_addr : 32; /* [46:15] */ + unsigned serr_v_rsvd1 : 5; /* [51:47] */ + unsigned serr_v_source : 2; /* [53:52] */ + unsigned serr_v_cmd : 2; /* [55:54] */ + unsigned serr_v_syn : 8; /* [63:56] */ + } serr_r_bits; + unsigned int serr_l_whole[2]; + unsigned long serr_q_whole; +}; + +/* + * GPERROR / APERROR / GPERREN / APERREN / GPERRSET / APERRSET + */ +union TPAchipPERR { + struct { + unsigned long perr_v_lost : 1; /* [0] */ + unsigned long perr_v_serr : 1; /* [1] */ + unsigned long perr_v_perr : 1; /* [2] */ + unsigned long perr_v_dcrto : 1; /* [3] */ + unsigned long perr_v_sge : 1; /* [4] */ + unsigned long perr_v_ape : 1; /* [5] */ + unsigned long perr_v_ta : 1; /* [6] */ + unsigned long perr_v_dpe : 1; /* [7] */ + unsigned long perr_v_nds : 1; /* [8] */ + unsigned long perr_v_iptpr : 1; /* [9] */ + unsigned long perr_v_iptpw : 1; /* [10] */ + unsigned long perr_v_rsvd0 : 3; /* [13:11] */ + unsigned long perr_v_addr : 33; /* [46:14] */ + unsigned long perr_v_dac : 1; /* [47] */ + unsigned long perr_v_mwin : 1; /* [48] */ + unsigned long perr_v_rsvd1 : 3; /* [51:49] */ + unsigned long perr_v_cmd : 4; /* [55:52] */ + unsigned long perr_v_rsvd2 : 8; /* [63:56] */ + } perr_r_bits; + unsigned int perr_l_whole[2]; + unsigned long perr_q_whole; +}; + +/* + * AGPERROR / AGPERREN / AGPERRSET + */ +union TPAchipAGPERR { + struct { + unsigned agperr_v_lost : 1; /* [0] */ + unsigned agperr_v_lpqfull : 1; /* [1] */ + unsigned apgerr_v_hpqfull : 1; /* [2] */ + unsigned agperr_v_rescmd : 1; /* [3] */ + unsigned agperr_v_ipte : 1; /* [4] */ + unsigned agperr_v_ptp : 1; /* [5] */ + unsigned agperr_v_nowindow : 1; /* [6] */ + unsigned agperr_v_rsvd0 : 8; /* [14:7] */ + unsigned agperr_v_addr : 32; /* [46:15] */ + unsigned agperr_v_rsvd1 : 1; /* [47] */ + unsigned agperr_v_dac : 1; /* [48] */ + unsigned agperr_v_mwin : 1; /* [49] */ + unsigned agperr_v_cmd : 3; /* [52:50] */ + unsigned agperr_v_length : 6; /* [58:53] */ + unsigned agperr_v_fence : 1; /* [59] */ + unsigned agperr_v_rsvd2 : 4; /* [63:60] */ + } agperr_r_bits; + unsigned int agperr_l_whole[2]; + unsigned long agperr_q_whole; +}; +/* + * Memory spaces: + * Hose numbers are assigned as follows: + * 0 - pachip 0 / G Port + * 1 - pachip 1 / G Port + * 2 - pachip 0 / A Port + * 3 - pachip 1 / A Port + */ +#define TITAN_HOSE_SHIFT (33) +#define TITAN_HOSE(h) (((unsigned long)(h)) << TITAN_HOSE_SHIFT) +#define TITAN_BASE (IDENT_ADDR + TI_BIAS) +#define TITAN_MEM(h) (TITAN_BASE+TITAN_HOSE(h)+0x000000000UL) +#define _TITAN_IACK_SC(h) (TITAN_BASE+TITAN_HOSE(h)+0x1F8000000UL) +#define TITAN_IO(h) (TITAN_BASE+TITAN_HOSE(h)+0x1FC000000UL) +#define TITAN_CONF(h) (TITAN_BASE+TITAN_HOSE(h)+0x1FE000000UL) + +#define TITAN_HOSE_MASK TITAN_HOSE(3) +#define TITAN_IACK_SC _TITAN_IACK_SC(0) /* hack! */ + +/* + * The canonical non-remaped I/O and MEM addresses have these values + * subtracted out. This is arranged so that folks manipulating ISA + * devices can use their familiar numbers and have them map to bus 0. + */ + +#define TITAN_IO_BIAS TITAN_IO(0) +#define TITAN_MEM_BIAS TITAN_MEM(0) + +/* The IO address space is larger than 0xffff */ +#define TITAN_IO_SPACE (TITAN_CONF(0) - TITAN_IO(0)) + +/* TIG Space */ +#define TITAN_TIG_SPACE (TITAN_BASE + 0x100000000UL) + +/* Offset between ram physical addresses and pci64 DAC bus addresses. */ +/* ??? Just a guess. Ought to confirm it hasn't been moved. */ +#define TITAN_DAC_OFFSET (1UL << 40) + +/* + * Data structure for handling TITAN machine checks: + */ +#define SCB_Q_SYSERR 0x620 +#define SCB_Q_PROCERR 0x630 +#define SCB_Q_SYSMCHK 0x660 +#define SCB_Q_PROCMCHK 0x670 +#define SCB_Q_SYSEVENT 0x680 /* environmental / system management */ +struct el_TITAN_sysdata_mcheck { + u64 summary; /* 0x00 */ + u64 c_dirx; /* 0x08 */ + u64 c_misc; /* 0x10 */ + u64 p0_serror; /* 0x18 */ + u64 p0_gperror; /* 0x20 */ + u64 p0_aperror; /* 0x28 */ + u64 p0_agperror;/* 0x30 */ + u64 p1_serror; /* 0x38 */ + u64 p1_gperror; /* 0x40 */ + u64 p1_aperror; /* 0x48 */ + u64 p1_agperror;/* 0x50 */ +}; + +/* + * System area for a privateer 680 environmental/system management mcheck + */ +struct el_PRIVATEER_envdata_mcheck { + u64 summary; /* 0x00 */ + u64 c_dirx; /* 0x08 */ + u64 smir; /* 0x10 */ + u64 cpuir; /* 0x18 */ + u64 psir; /* 0x20 */ + u64 fault; /* 0x28 */ + u64 sys_doors; /* 0x30 */ + u64 temp_warn; /* 0x38 */ + u64 fan_ctrl; /* 0x40 */ + u64 code; /* 0x48 */ + u64 reserved; /* 0x50 */ +}; + +#ifdef __KERNEL__ + +#ifndef __EXTERN_INLINE +#define __EXTERN_INLINE extern inline +#define __IO_EXTERN_INLINE +#endif + +/* + * I/O functions: + * + * TITAN, a 21??? PCI/memory support chipset for the EV6 (21264) + * can only use linear accesses to get at PCI/AGP memory and I/O spaces. + */ + +/* + * Memory functions. all accesses are done through linear space. + */ +extern void __iomem *titan_ioportmap(unsigned long addr); +extern void __iomem *titan_ioremap(unsigned long addr, unsigned long size); +extern void titan_iounmap(volatile void __iomem *addr); + +__EXTERN_INLINE int titan_is_ioaddr(unsigned long addr) +{ + return addr >= TITAN_BASE; +} + +extern int titan_is_mmio(const volatile void __iomem *addr); + +#undef __IO_PREFIX +#define __IO_PREFIX titan +#define titan_trivial_rw_bw 1 +#define titan_trivial_rw_lq 1 +#define titan_trivial_io_bw 1 +#define titan_trivial_io_lq 1 +#define titan_trivial_iounmap 0 +#include <asm/io_trivial.h> + +#ifdef __IO_EXTERN_INLINE +#undef __EXTERN_INLINE +#undef __IO_EXTERN_INLINE +#endif + +#endif /* __KERNEL__ */ + +#endif /* __ALPHA_TITAN__H__ */ diff --git a/arch/alpha/include/asm/core_tsunami.h b/arch/alpha/include/asm/core_tsunami.h new file mode 100644 index 000000000..8e39ecf09 --- /dev/null +++ b/arch/alpha/include/asm/core_tsunami.h @@ -0,0 +1,334 @@ +#ifndef __ALPHA_TSUNAMI__H__ +#define __ALPHA_TSUNAMI__H__ + +#include <linux/types.h> +#include <asm/compiler.h> + +/* + * TSUNAMI/TYPHOON are the internal names for the core logic chipset which + * provides memory controller and PCI access for the 21264 based systems. + * + * This file is based on: + * + * Tsunami System Programmers Manual + * Preliminary, Chapters 2-5 + * + */ + +/* XXX: Do we need to conditionalize on this? */ +#ifdef USE_48_BIT_KSEG +#define TS_BIAS 0x80000000000UL +#else +#define TS_BIAS 0x10000000000UL +#endif + +/* + * CChip, DChip, and PChip registers + */ + +typedef struct { + volatile unsigned long csr __attribute__((aligned(64))); +} tsunami_64; + +typedef struct { + tsunami_64 csc; + tsunami_64 mtr; + tsunami_64 misc; + tsunami_64 mpd; + tsunami_64 aar0; + tsunami_64 aar1; + tsunami_64 aar2; + tsunami_64 aar3; + tsunami_64 dim0; + tsunami_64 dim1; + tsunami_64 dir0; + tsunami_64 dir1; + tsunami_64 drir; + tsunami_64 prben; + tsunami_64 iic; /* a.k.a. iic0 */ + tsunami_64 wdr; /* a.k.a. iic1 */ + tsunami_64 mpr0; + tsunami_64 mpr1; + tsunami_64 mpr2; + tsunami_64 mpr3; + tsunami_64 mctl; + tsunami_64 __pad1; + tsunami_64 ttr; + tsunami_64 tdr; + tsunami_64 dim2; + tsunami_64 dim3; + tsunami_64 dir2; + tsunami_64 dir3; + tsunami_64 iic2; + tsunami_64 iic3; +} tsunami_cchip; + +typedef struct { + tsunami_64 dsc; + tsunami_64 str; + tsunami_64 drev; +} tsunami_dchip; + +typedef struct { + tsunami_64 wsba[4]; + tsunami_64 wsm[4]; + tsunami_64 tba[4]; + tsunami_64 pctl; + tsunami_64 plat; + tsunami_64 reserved; + tsunami_64 perror; + tsunami_64 perrmask; + tsunami_64 perrset; + tsunami_64 tlbiv; + tsunami_64 tlbia; + tsunami_64 pmonctl; + tsunami_64 pmoncnt; +} tsunami_pchip; + +#define TSUNAMI_cchip ((tsunami_cchip *)(IDENT_ADDR+TS_BIAS+0x1A0000000UL)) +#define TSUNAMI_dchip ((tsunami_dchip *)(IDENT_ADDR+TS_BIAS+0x1B0000800UL)) +#define TSUNAMI_pchip0 ((tsunami_pchip *)(IDENT_ADDR+TS_BIAS+0x180000000UL)) +#define TSUNAMI_pchip1 ((tsunami_pchip *)(IDENT_ADDR+TS_BIAS+0x380000000UL)) +extern int TSUNAMI_bootcpu; + +/* + * TSUNAMI Pchip Error register. + */ + +#define perror_m_lost 0x1 +#define perror_m_serr 0x2 +#define perror_m_perr 0x4 +#define perror_m_dcrto 0x8 +#define perror_m_sge 0x10 +#define perror_m_ape 0x20 +#define perror_m_ta 0x40 +#define perror_m_rdpe 0x80 +#define perror_m_nds 0x100 +#define perror_m_rto 0x200 +#define perror_m_uecc 0x400 +#define perror_m_cre 0x800 +#define perror_m_addrl 0xFFFFFFFF0000UL +#define perror_m_addrh 0x7000000000000UL +#define perror_m_cmd 0xF0000000000000UL +#define perror_m_syn 0xFF00000000000000UL +union TPchipPERROR { + struct { + unsigned int perror_v_lost : 1; + unsigned perror_v_serr : 1; + unsigned perror_v_perr : 1; + unsigned perror_v_dcrto : 1; + unsigned perror_v_sge : 1; + unsigned perror_v_ape : 1; + unsigned perror_v_ta : 1; + unsigned perror_v_rdpe : 1; + unsigned perror_v_nds : 1; + unsigned perror_v_rto : 1; + unsigned perror_v_uecc : 1; + unsigned perror_v_cre : 1; + unsigned perror_v_rsvd1 : 4; + unsigned perror_v_addrl : 32; + unsigned perror_v_addrh : 3; + unsigned perror_v_rsvd2 : 1; + unsigned perror_v_cmd : 4; + unsigned perror_v_syn : 8; + } perror_r_bits; + int perror_q_whole [2]; +}; + +/* + * TSUNAMI Pchip Window Space Base Address register. + */ +#define wsba_m_ena 0x1 +#define wsba_m_sg 0x2 +#define wsba_m_ptp 0x4 +#define wsba_m_addr 0xFFF00000 +#define wmask_k_sz1gb 0x3FF00000 +union TPchipWSBA { + struct { + unsigned wsba_v_ena : 1; + unsigned wsba_v_sg : 1; + unsigned wsba_v_ptp : 1; + unsigned wsba_v_rsvd1 : 17; + unsigned wsba_v_addr : 12; + unsigned wsba_v_rsvd2 : 32; + } wsba_r_bits; + int wsba_q_whole [2]; +}; + +/* + * TSUNAMI Pchip Control Register + */ +#define pctl_m_fdsc 0x1 +#define pctl_m_fbtb 0x2 +#define pctl_m_thdis 0x4 +#define pctl_m_chaindis 0x8 +#define pctl_m_tgtlat 0x10 +#define pctl_m_hole 0x20 +#define pctl_m_mwin 0x40 +#define pctl_m_arbena 0x80 +#define pctl_m_prigrp 0x7F00 +#define pctl_m_ppri 0x8000 +#define pctl_m_rsvd1 0x30000 +#define pctl_m_eccen 0x40000 +#define pctl_m_padm 0x80000 +#define pctl_m_cdqmax 0xF00000 +#define pctl_m_rev 0xFF000000 +#define pctl_m_crqmax 0xF00000000UL +#define pctl_m_ptpmax 0xF000000000UL +#define pctl_m_pclkx 0x30000000000UL +#define pctl_m_fdsdis 0x40000000000UL +#define pctl_m_fdwdis 0x80000000000UL +#define pctl_m_ptevrfy 0x100000000000UL +#define pctl_m_rpp 0x200000000000UL +#define pctl_m_pid 0xC00000000000UL +#define pctl_m_rsvd2 0xFFFF000000000000UL + +union TPchipPCTL { + struct { + unsigned pctl_v_fdsc : 1; + unsigned pctl_v_fbtb : 1; + unsigned pctl_v_thdis : 1; + unsigned pctl_v_chaindis : 1; + unsigned pctl_v_tgtlat : 1; + unsigned pctl_v_hole : 1; + unsigned pctl_v_mwin : 1; + unsigned pctl_v_arbena : 1; + unsigned pctl_v_prigrp : 7; + unsigned pctl_v_ppri : 1; + unsigned pctl_v_rsvd1 : 2; + unsigned pctl_v_eccen : 1; + unsigned pctl_v_padm : 1; + unsigned pctl_v_cdqmax : 4; + unsigned pctl_v_rev : 8; + unsigned pctl_v_crqmax : 4; + unsigned pctl_v_ptpmax : 4; + unsigned pctl_v_pclkx : 2; + unsigned pctl_v_fdsdis : 1; + unsigned pctl_v_fdwdis : 1; + unsigned pctl_v_ptevrfy : 1; + unsigned pctl_v_rpp : 1; + unsigned pctl_v_pid : 2; + unsigned pctl_v_rsvd2 : 16; + } pctl_r_bits; + int pctl_q_whole [2]; +}; + +/* + * TSUNAMI Pchip Error Mask Register. + */ +#define perrmask_m_lost 0x1 +#define perrmask_m_serr 0x2 +#define perrmask_m_perr 0x4 +#define perrmask_m_dcrto 0x8 +#define perrmask_m_sge 0x10 +#define perrmask_m_ape 0x20 +#define perrmask_m_ta 0x40 +#define perrmask_m_rdpe 0x80 +#define perrmask_m_nds 0x100 +#define perrmask_m_rto 0x200 +#define perrmask_m_uecc 0x400 +#define perrmask_m_cre 0x800 +#define perrmask_m_rsvd 0xFFFFFFFFFFFFF000UL +union TPchipPERRMASK { + struct { + unsigned int perrmask_v_lost : 1; + unsigned perrmask_v_serr : 1; + unsigned perrmask_v_perr : 1; + unsigned perrmask_v_dcrto : 1; + unsigned perrmask_v_sge : 1; + unsigned perrmask_v_ape : 1; + unsigned perrmask_v_ta : 1; + unsigned perrmask_v_rdpe : 1; + unsigned perrmask_v_nds : 1; + unsigned perrmask_v_rto : 1; + unsigned perrmask_v_uecc : 1; + unsigned perrmask_v_cre : 1; + unsigned perrmask_v_rsvd1 : 20; + unsigned perrmask_v_rsvd2 : 32; + } perrmask_r_bits; + int perrmask_q_whole [2]; +}; + +/* + * Memory spaces: + */ +#define TSUNAMI_HOSE(h) (((unsigned long)(h)) << 33) +#define TSUNAMI_BASE (IDENT_ADDR + TS_BIAS) + +#define TSUNAMI_MEM(h) (TSUNAMI_BASE+TSUNAMI_HOSE(h) + 0x000000000UL) +#define _TSUNAMI_IACK_SC(h) (TSUNAMI_BASE+TSUNAMI_HOSE(h) + 0x1F8000000UL) +#define TSUNAMI_IO(h) (TSUNAMI_BASE+TSUNAMI_HOSE(h) + 0x1FC000000UL) +#define TSUNAMI_CONF(h) (TSUNAMI_BASE+TSUNAMI_HOSE(h) + 0x1FE000000UL) + +#define TSUNAMI_IACK_SC _TSUNAMI_IACK_SC(0) /* hack! */ + + +/* + * The canonical non-remaped I/O and MEM addresses have these values + * subtracted out. This is arranged so that folks manipulating ISA + * devices can use their familiar numbers and have them map to bus 0. + */ + +#define TSUNAMI_IO_BIAS TSUNAMI_IO(0) +#define TSUNAMI_MEM_BIAS TSUNAMI_MEM(0) + +/* The IO address space is larger than 0xffff */ +#define TSUNAMI_IO_SPACE (TSUNAMI_CONF(0) - TSUNAMI_IO(0)) + +/* Offset between ram physical addresses and pci64 DAC bus addresses. */ +#define TSUNAMI_DAC_OFFSET (1UL << 40) + +/* + * Data structure for handling TSUNAMI machine checks: + */ +struct el_TSUNAMI_sysdata_mcheck { +}; + + +#ifdef __KERNEL__ + +#ifndef __EXTERN_INLINE +#define __EXTERN_INLINE extern inline +#define __IO_EXTERN_INLINE +#endif + +/* + * I/O functions: + * + * TSUNAMI, the 21??? PCI/memory support chipset for the EV6 (21264) + * can only use linear accesses to get at PCI memory and I/O spaces. + */ + +/* + * Memory functions. all accesses are done through linear space. + */ +extern void __iomem *tsunami_ioportmap(unsigned long addr); +extern void __iomem *tsunami_ioremap(unsigned long addr, unsigned long size); +__EXTERN_INLINE int tsunami_is_ioaddr(unsigned long addr) +{ + return addr >= TSUNAMI_BASE; +} + +__EXTERN_INLINE int tsunami_is_mmio(const volatile void __iomem *xaddr) +{ + unsigned long addr = (unsigned long) xaddr; + return (addr & 0x100000000UL) == 0; +} + +#undef __IO_PREFIX +#define __IO_PREFIX tsunami +#define tsunami_trivial_rw_bw 1 +#define tsunami_trivial_rw_lq 1 +#define tsunami_trivial_io_bw 1 +#define tsunami_trivial_io_lq 1 +#define tsunami_trivial_iounmap 1 +#include <asm/io_trivial.h> + +#ifdef __IO_EXTERN_INLINE +#undef __EXTERN_INLINE +#undef __IO_EXTERN_INLINE +#endif + +#endif /* __KERNEL__ */ + +#endif /* __ALPHA_TSUNAMI__H__ */ diff --git a/arch/alpha/include/asm/core_wildfire.h b/arch/alpha/include/asm/core_wildfire.h new file mode 100644 index 000000000..cd562f544 --- /dev/null +++ b/arch/alpha/include/asm/core_wildfire.h @@ -0,0 +1,318 @@ +#ifndef __ALPHA_WILDFIRE__H__ +#define __ALPHA_WILDFIRE__H__ + +#include <linux/types.h> +#include <asm/compiler.h> + +#define WILDFIRE_MAX_QBB 8 /* more than 8 requires other mods */ +#define WILDFIRE_PCA_PER_QBB 4 +#define WILDFIRE_IRQ_PER_PCA 64 + +#define WILDFIRE_NR_IRQS \ + (WILDFIRE_MAX_QBB * WILDFIRE_PCA_PER_QBB * WILDFIRE_IRQ_PER_PCA) + +extern unsigned char wildfire_hard_qbb_map[WILDFIRE_MAX_QBB]; +extern unsigned char wildfire_soft_qbb_map[WILDFIRE_MAX_QBB]; +#define QBB_MAP_EMPTY 0xff + +extern unsigned long wildfire_hard_qbb_mask; +extern unsigned long wildfire_soft_qbb_mask; +extern unsigned long wildfire_gp_mask; +extern unsigned long wildfire_hs_mask; +extern unsigned long wildfire_iop_mask; +extern unsigned long wildfire_ior_mask; +extern unsigned long wildfire_pca_mask; +extern unsigned long wildfire_cpu_mask; +extern unsigned long wildfire_mem_mask; + +#define WILDFIRE_QBB_EXISTS(qbbno) (wildfire_soft_qbb_mask & (1 << (qbbno))) + +#define WILDFIRE_MEM_EXISTS(qbbno) (wildfire_mem_mask & (0xf << ((qbbno) << 2))) + +#define WILDFIRE_PCA_EXISTS(qbbno, pcano) \ + (wildfire_pca_mask & (1 << (((qbbno) << 2) + (pcano)))) + +typedef struct { + volatile unsigned long csr __attribute__((aligned(64))); +} wildfire_64; + +typedef struct { + volatile unsigned long csr __attribute__((aligned(256))); +} wildfire_256; + +typedef struct { + volatile unsigned long csr __attribute__((aligned(2048))); +} wildfire_2k; + +typedef struct { + wildfire_64 qsd_whami; + wildfire_64 qsd_rev; + wildfire_64 qsd_port_present; + wildfire_64 qsd_port_active; + wildfire_64 qsd_fault_ena; + wildfire_64 qsd_cpu_int_ena; + wildfire_64 qsd_mem_config; + wildfire_64 qsd_err_sum; + wildfire_64 ce_sum[4]; + wildfire_64 dev_init[4]; + wildfire_64 it_int[4]; + wildfire_64 ip_int[4]; + wildfire_64 uce_sum[4]; + wildfire_64 se_sum__non_dev_int[4]; + wildfire_64 scratch[4]; + wildfire_64 qsd_timer; + wildfire_64 qsd_diag; +} wildfire_qsd; + +typedef struct { + wildfire_256 qsd_whami; + wildfire_256 __pad1; + wildfire_256 ce_sum; + wildfire_256 dev_init; + wildfire_256 it_int; + wildfire_256 ip_int; + wildfire_256 uce_sum; + wildfire_256 se_sum; +} wildfire_fast_qsd; + +typedef struct { + wildfire_2k qsa_qbb_id; + wildfire_2k __pad1; + wildfire_2k qsa_port_ena; + wildfire_2k qsa_scratch; + wildfire_2k qsa_config[5]; + wildfire_2k qsa_ref_int; + wildfire_2k qsa_qbb_pop[2]; + wildfire_2k qsa_dtag_fc; + wildfire_2k __pad2[3]; + wildfire_2k qsa_diag; + wildfire_2k qsa_diag_lock[4]; + wildfire_2k __pad3[11]; + wildfire_2k qsa_cpu_err_sum; + wildfire_2k qsa_misc_err_sum; + wildfire_2k qsa_tmo_err_sum; + wildfire_2k qsa_err_ena; + wildfire_2k qsa_tmo_config; + wildfire_2k qsa_ill_cmd_err_sum; + wildfire_2k __pad4[26]; + wildfire_2k qsa_busy_mask; + wildfire_2k qsa_arr_valid; + wildfire_2k __pad5[2]; + wildfire_2k qsa_port_map[4]; + wildfire_2k qsa_arr_addr[8]; + wildfire_2k qsa_arr_mask[8]; +} wildfire_qsa; + +typedef struct { + wildfire_64 ioa_config; + wildfire_64 iod_config; + wildfire_64 iop_switch_credits; + wildfire_64 __pad1; + wildfire_64 iop_hose_credits; + wildfire_64 __pad2[11]; + struct { + wildfire_64 __pad3; + wildfire_64 init; + } iop_hose[4]; + wildfire_64 ioa_hose_0_ctrl; + wildfire_64 iod_hose_0_ctrl; + wildfire_64 ioa_hose_1_ctrl; + wildfire_64 iod_hose_1_ctrl; + wildfire_64 ioa_hose_2_ctrl; + wildfire_64 iod_hose_2_ctrl; + wildfire_64 ioa_hose_3_ctrl; + wildfire_64 iod_hose_3_ctrl; + struct { + wildfire_64 target; + wildfire_64 __pad4; + } iop_dev_int[4]; + + wildfire_64 iop_err_int_target; + wildfire_64 __pad5[7]; + wildfire_64 iop_qbb_err_sum; + wildfire_64 __pad6; + wildfire_64 iop_qbb_se_sum; + wildfire_64 __pad7; + wildfire_64 ioa_err_sum; + wildfire_64 iod_err_sum; + wildfire_64 __pad8[4]; + wildfire_64 ioa_diag_force_err; + wildfire_64 iod_diag_force_err; + wildfire_64 __pad9[4]; + wildfire_64 iop_diag_send_err_int; + wildfire_64 __pad10[15]; + wildfire_64 ioa_scratch; + wildfire_64 iod_scratch; +} wildfire_iop; + +typedef struct { + wildfire_2k gpa_qbb_map[4]; + wildfire_2k gpa_mem_pop_map; + wildfire_2k gpa_scratch; + wildfire_2k gpa_diag; + wildfire_2k gpa_config_0; + wildfire_2k __pad1; + wildfire_2k gpa_init_id; + wildfire_2k gpa_config_2; + /* not complete */ +} wildfire_gp; + +typedef struct { + wildfire_64 pca_what_am_i; + wildfire_64 pca_err_sum; + wildfire_64 pca_diag_force_err; + wildfire_64 pca_diag_send_err_int; + wildfire_64 pca_hose_credits; + wildfire_64 pca_scratch; + wildfire_64 pca_micro_addr; + wildfire_64 pca_micro_data; + wildfire_64 pca_pend_int; + wildfire_64 pca_sent_int; + wildfire_64 __pad1; + wildfire_64 pca_stdio_edge_level; + wildfire_64 __pad2[52]; + struct { + wildfire_64 target; + wildfire_64 enable; + } pca_int[4]; + wildfire_64 __pad3[56]; + wildfire_64 pca_alt_sent_int[32]; +} wildfire_pca; + +typedef struct { + wildfire_64 ne_what_am_i; + /* not complete */ +} wildfire_ne; + +typedef struct { + wildfire_64 fe_what_am_i; + /* not complete */ +} wildfire_fe; + +typedef struct { + wildfire_64 pci_io_addr_ext; + wildfire_64 pci_ctrl; + wildfire_64 pci_err_sum; + wildfire_64 pci_err_addr; + wildfire_64 pci_stall_cnt; + wildfire_64 pci_iack_special; + wildfire_64 __pad1[2]; + wildfire_64 pci_pend_int; + wildfire_64 pci_sent_int; + wildfire_64 __pad2[54]; + struct { + wildfire_64 wbase; + wildfire_64 wmask; + wildfire_64 tbase; + } pci_window[4]; + wildfire_64 pci_flush_tlb; + wildfire_64 pci_perf_mon; +} wildfire_pci; + +#define WILDFIRE_ENTITY_SHIFT 18 + +#define WILDFIRE_GP_ENTITY (0x10UL << WILDFIRE_ENTITY_SHIFT) +#define WILDFIRE_IOP_ENTITY (0x08UL << WILDFIRE_ENTITY_SHIFT) +#define WILDFIRE_QSA_ENTITY (0x04UL << WILDFIRE_ENTITY_SHIFT) +#define WILDFIRE_QSD_ENTITY_SLOW (0x05UL << WILDFIRE_ENTITY_SHIFT) +#define WILDFIRE_QSD_ENTITY_FAST (0x01UL << WILDFIRE_ENTITY_SHIFT) + +#define WILDFIRE_PCA_ENTITY(pca) ((0xc|(pca))<<WILDFIRE_ENTITY_SHIFT) + +#define WILDFIRE_BASE (IDENT_ADDR | (1UL << 40)) + +#define WILDFIRE_QBB_MASK 0x0fUL /* for now, only 4 bits/16 QBBs */ + +#define WILDFIRE_QBB(q) ((~((long)(q)) & WILDFIRE_QBB_MASK) << 36) +#define WILDFIRE_HOSE(h) ((long)(h) << 33) + +#define WILDFIRE_QBB_IO(q) (WILDFIRE_BASE | WILDFIRE_QBB(q)) +#define WILDFIRE_QBB_HOSE(q,h) (WILDFIRE_QBB_IO(q) | WILDFIRE_HOSE(h)) + +#define WILDFIRE_MEM(q,h) (WILDFIRE_QBB_HOSE(q,h) | 0x000000000UL) +#define WILDFIRE_CONF(q,h) (WILDFIRE_QBB_HOSE(q,h) | 0x1FE000000UL) +#define WILDFIRE_IO(q,h) (WILDFIRE_QBB_HOSE(q,h) | 0x1FF000000UL) + +#define WILDFIRE_qsd(q) \ + ((wildfire_qsd *)(WILDFIRE_QBB_IO(q)|WILDFIRE_QSD_ENTITY_SLOW|(((1UL<<13)-1)<<23))) + +#define WILDFIRE_fast_qsd() \ + ((wildfire_fast_qsd *)(WILDFIRE_QBB_IO(0)|WILDFIRE_QSD_ENTITY_FAST|(((1UL<<13)-1)<<23))) + +#define WILDFIRE_qsa(q) \ + ((wildfire_qsa *)(WILDFIRE_QBB_IO(q)|WILDFIRE_QSA_ENTITY|(((1UL<<13)-1)<<23))) + +#define WILDFIRE_iop(q) \ + ((wildfire_iop *)(WILDFIRE_QBB_IO(q)|WILDFIRE_IOP_ENTITY|(((1UL<<13)-1)<<23))) + +#define WILDFIRE_gp(q) \ + ((wildfire_gp *)(WILDFIRE_QBB_IO(q)|WILDFIRE_GP_ENTITY|(((1UL<<13)-1)<<23))) + +#define WILDFIRE_pca(q,pca) \ + ((wildfire_pca *)(WILDFIRE_QBB_IO(q)|WILDFIRE_PCA_ENTITY(pca)|(((1UL<<13)-1)<<23))) + +#define WILDFIRE_ne(q,pca) \ + ((wildfire_ne *)(WILDFIRE_QBB_IO(q)|WILDFIRE_PCA_ENTITY(pca)|(((1UL<<13)-1)<<23)|(1UL<<16))) + +#define WILDFIRE_fe(q,pca) \ + ((wildfire_fe *)(WILDFIRE_QBB_IO(q)|WILDFIRE_PCA_ENTITY(pca)|(((1UL<<13)-1)<<23)|(3UL<<15))) + +#define WILDFIRE_pci(q,h) \ + ((wildfire_pci *)(WILDFIRE_QBB_IO(q)|WILDFIRE_PCA_ENTITY(((h)&6)>>1)|((((h)&1)|2)<<16)|(((1UL<<13)-1)<<23))) + +#define WILDFIRE_IO_BIAS WILDFIRE_IO(0,0) +#define WILDFIRE_MEM_BIAS WILDFIRE_MEM(0,0) /* ??? */ + +/* The IO address space is larger than 0xffff */ +#define WILDFIRE_IO_SPACE (8UL*1024*1024) + +#ifdef __KERNEL__ + +#ifndef __EXTERN_INLINE +#define __EXTERN_INLINE extern inline +#define __IO_EXTERN_INLINE +#endif + +/* + * Memory functions. all accesses are done through linear space. + */ + +__EXTERN_INLINE void __iomem *wildfire_ioportmap(unsigned long addr) +{ + return (void __iomem *)(addr + WILDFIRE_IO_BIAS); +} + +__EXTERN_INLINE void __iomem *wildfire_ioremap(unsigned long addr, + unsigned long size) +{ + return (void __iomem *)(addr + WILDFIRE_MEM_BIAS); +} + +__EXTERN_INLINE int wildfire_is_ioaddr(unsigned long addr) +{ + return addr >= WILDFIRE_BASE; +} + +__EXTERN_INLINE int wildfire_is_mmio(const volatile void __iomem *xaddr) +{ + unsigned long addr = (unsigned long)xaddr; + return (addr & 0x100000000UL) == 0; +} + +#undef __IO_PREFIX +#define __IO_PREFIX wildfire +#define wildfire_trivial_rw_bw 1 +#define wildfire_trivial_rw_lq 1 +#define wildfire_trivial_io_bw 1 +#define wildfire_trivial_io_lq 1 +#define wildfire_trivial_iounmap 1 +#include <asm/io_trivial.h> + +#ifdef __IO_EXTERN_INLINE +#undef __EXTERN_INLINE +#undef __IO_EXTERN_INLINE +#endif + +#endif /* __KERNEL__ */ + +#endif /* __ALPHA_WILDFIRE__H__ */ diff --git a/arch/alpha/include/asm/current.h b/arch/alpha/include/asm/current.h new file mode 100644 index 000000000..094d285a1 --- /dev/null +++ b/arch/alpha/include/asm/current.h @@ -0,0 +1,9 @@ +#ifndef _ALPHA_CURRENT_H +#define _ALPHA_CURRENT_H + +#include <linux/thread_info.h> + +#define get_current() (current_thread_info()->task) +#define current get_current() + +#endif /* _ALPHA_CURRENT_H */ diff --git a/arch/alpha/include/asm/delay.h b/arch/alpha/include/asm/delay.h new file mode 100644 index 000000000..2aa3f410f --- /dev/null +++ b/arch/alpha/include/asm/delay.h @@ -0,0 +1,10 @@ +#ifndef __ALPHA_DELAY_H +#define __ALPHA_DELAY_H + +extern void __delay(int loops); +extern void udelay(unsigned long usecs); + +extern void ndelay(unsigned long nsecs); +#define ndelay ndelay + +#endif /* defined(__ALPHA_DELAY_H) */ diff --git a/arch/alpha/include/asm/device.h b/arch/alpha/include/asm/device.h new file mode 100644 index 000000000..d8f9872b0 --- /dev/null +++ b/arch/alpha/include/asm/device.h @@ -0,0 +1,7 @@ +/* + * Arch specific extensions to struct device + * + * This file is released under the GPLv2 + */ +#include <asm-generic/device.h> + diff --git a/arch/alpha/include/asm/div64.h b/arch/alpha/include/asm/div64.h new file mode 100644 index 000000000..6cd978cef --- /dev/null +++ b/arch/alpha/include/asm/div64.h @@ -0,0 +1 @@ +#include <asm-generic/div64.h> diff --git a/arch/alpha/include/asm/dma-mapping.h b/arch/alpha/include/asm/dma-mapping.h new file mode 100644 index 000000000..dfa32f061 --- /dev/null +++ b/arch/alpha/include/asm/dma-mapping.h @@ -0,0 +1,53 @@ +#ifndef _ALPHA_DMA_MAPPING_H +#define _ALPHA_DMA_MAPPING_H + +#include <linux/dma-attrs.h> + +extern struct dma_map_ops *dma_ops; + +static inline struct dma_map_ops *get_dma_ops(struct device *dev) +{ + return dma_ops; +} + +#include <asm-generic/dma-mapping-common.h> + +#define dma_alloc_coherent(d,s,h,f) dma_alloc_attrs(d,s,h,f,NULL) + +static inline void *dma_alloc_attrs(struct device *dev, size_t size, + dma_addr_t *dma_handle, gfp_t gfp, + struct dma_attrs *attrs) +{ + return get_dma_ops(dev)->alloc(dev, size, dma_handle, gfp, attrs); +} + +#define dma_free_coherent(d,s,c,h) dma_free_attrs(d,s,c,h,NULL) + +static inline void dma_free_attrs(struct device *dev, size_t size, + void *vaddr, dma_addr_t dma_handle, + struct dma_attrs *attrs) +{ + get_dma_ops(dev)->free(dev, size, vaddr, dma_handle, attrs); +} + +static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) +{ + return get_dma_ops(dev)->mapping_error(dev, dma_addr); +} + +static inline int dma_supported(struct device *dev, u64 mask) +{ + return get_dma_ops(dev)->dma_supported(dev, mask); +} + +static inline int dma_set_mask(struct device *dev, u64 mask) +{ + return get_dma_ops(dev)->set_dma_mask(dev, mask); +} + +#define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f) +#define dma_free_noncoherent(d, s, v, h) dma_free_coherent(d, s, v, h) + +#define dma_cache_sync(dev, va, size, dir) ((void)0) + +#endif /* _ALPHA_DMA_MAPPING_H */ diff --git a/arch/alpha/include/asm/dma.h b/arch/alpha/include/asm/dma.h new file mode 100644 index 000000000..87cfdbdf0 --- /dev/null +++ b/arch/alpha/include/asm/dma.h @@ -0,0 +1,376 @@ +/* + * include/asm-alpha/dma.h + * + * This is essentially the same as the i386 DMA stuff, as the AlphaPCs + * use ISA-compatible dma. The only extension is support for high-page + * registers that allow to set the top 8 bits of a 32-bit DMA address. + * This register should be written last when setting up a DMA address + * as this will also enable DMA across 64 KB boundaries. + */ + +/* $Id: dma.h,v 1.7 1992/12/14 00:29:34 root Exp root $ + * linux/include/asm/dma.h: Defines for using and allocating dma channels. + * Written by Hennus Bergman, 1992. + * High DMA channel support & info by Hannu Savolainen + * and John Boyd, Nov. 1992. + */ + +#ifndef _ASM_DMA_H +#define _ASM_DMA_H + +#include <linux/spinlock.h> +#include <asm/io.h> + +#define dma_outb outb +#define dma_inb inb + +/* + * NOTES about DMA transfers: + * + * controller 1: channels 0-3, byte operations, ports 00-1F + * controller 2: channels 4-7, word operations, ports C0-DF + * + * - ALL registers are 8 bits only, regardless of transfer size + * - channel 4 is not used - cascades 1 into 2. + * - channels 0-3 are byte - addresses/counts are for physical bytes + * - channels 5-7 are word - addresses/counts are for physical words + * - transfers must not cross physical 64K (0-3) or 128K (5-7) boundaries + * - transfer count loaded to registers is 1 less than actual count + * - controller 2 offsets are all even (2x offsets for controller 1) + * - page registers for 5-7 don't use data bit 0, represent 128K pages + * - page registers for 0-3 use bit 0, represent 64K pages + * + * DMA transfers are limited to the lower 16MB of _physical_ memory. + * Note that addresses loaded into registers must be _physical_ addresses, + * not logical addresses (which may differ if paging is active). + * + * Address mapping for channels 0-3: + * + * A23 ... A16 A15 ... A8 A7 ... A0 (Physical addresses) + * | ... | | ... | | ... | + * | ... | | ... | | ... | + * | ... | | ... | | ... | + * P7 ... P0 A7 ... A0 A7 ... A0 + * | Page | Addr MSB | Addr LSB | (DMA registers) + * + * Address mapping for channels 5-7: + * + * A23 ... A17 A16 A15 ... A9 A8 A7 ... A1 A0 (Physical addresses) + * | ... | \ \ ... \ \ \ ... \ \ + * | ... | \ \ ... \ \ \ ... \ (not used) + * | ... | \ \ ... \ \ \ ... \ + * P7 ... P1 (0) A7 A6 ... A0 A7 A6 ... A0 + * | Page | Addr MSB | Addr LSB | (DMA registers) + * + * Again, channels 5-7 transfer _physical_ words (16 bits), so addresses + * and counts _must_ be word-aligned (the lowest address bit is _ignored_ at + * the hardware level, so odd-byte transfers aren't possible). + * + * Transfer count (_not # bytes_) is limited to 64K, represented as actual + * count - 1 : 64K => 0xFFFF, 1 => 0x0000. Thus, count is always 1 or more, + * and up to 128K bytes may be transferred on channels 5-7 in one operation. + * + */ + +#define MAX_DMA_CHANNELS 8 + +/* + ISA DMA limitations on Alpha platforms, + + These may be due to SIO (PCI<->ISA bridge) chipset limitation, or + just a wiring limit. +*/ + +/* The maximum address for ISA DMA transfer on Alpha XL, due to an + hardware SIO limitation, is 64MB. +*/ +#define ALPHA_XL_MAX_ISA_DMA_ADDRESS 0x04000000UL + +/* The maximum address for ISA DMA transfer on RUFFIAN, + due to an hardware SIO limitation, is 16MB. +*/ +#define ALPHA_RUFFIAN_MAX_ISA_DMA_ADDRESS 0x01000000UL + +/* The maximum address for ISA DMA transfer on SABLE, and some ALCORs, + due to an hardware SIO chip limitation, is 2GB. +*/ +#define ALPHA_SABLE_MAX_ISA_DMA_ADDRESS 0x80000000UL +#define ALPHA_ALCOR_MAX_ISA_DMA_ADDRESS 0x80000000UL + +/* + Maximum address for all the others is the complete 32-bit bus + address space. +*/ +#define ALPHA_MAX_ISA_DMA_ADDRESS 0x100000000UL + +#ifdef CONFIG_ALPHA_GENERIC +# define MAX_ISA_DMA_ADDRESS (alpha_mv.max_isa_dma_address) +#else +# if defined(CONFIG_ALPHA_XL) +# define MAX_ISA_DMA_ADDRESS ALPHA_XL_MAX_ISA_DMA_ADDRESS +# elif defined(CONFIG_ALPHA_RUFFIAN) +# define MAX_ISA_DMA_ADDRESS ALPHA_RUFFIAN_MAX_ISA_DMA_ADDRESS +# elif defined(CONFIG_ALPHA_SABLE) +# define MAX_ISA_DMA_ADDRESS ALPHA_SABLE_MAX_ISA_DMA_ADDRESS +# elif defined(CONFIG_ALPHA_ALCOR) +# define MAX_ISA_DMA_ADDRESS ALPHA_ALCOR_MAX_ISA_DMA_ADDRESS +# else +# define MAX_ISA_DMA_ADDRESS ALPHA_MAX_ISA_DMA_ADDRESS +# endif +#endif + +/* If we have the iommu, we don't have any address limitations on DMA. + Otherwise (Nautilus, RX164), we have to have 0-16 Mb DMA zone + like i386. */ +#define MAX_DMA_ADDRESS (alpha_mv.mv_pci_tbi ? \ + ~0UL : IDENT_ADDR + 0x01000000) + +/* 8237 DMA controllers */ +#define IO_DMA1_BASE 0x00 /* 8 bit slave DMA, channels 0..3 */ +#define IO_DMA2_BASE 0xC0 /* 16 bit master DMA, ch 4(=slave input)..7 */ + +/* DMA controller registers */ +#define DMA1_CMD_REG 0x08 /* command register (w) */ +#define DMA1_STAT_REG 0x08 /* status register (r) */ +#define DMA1_REQ_REG 0x09 /* request register (w) */ +#define DMA1_MASK_REG 0x0A /* single-channel mask (w) */ +#define DMA1_MODE_REG 0x0B /* mode register (w) */ +#define DMA1_CLEAR_FF_REG 0x0C /* clear pointer flip-flop (w) */ +#define DMA1_TEMP_REG 0x0D /* Temporary Register (r) */ +#define DMA1_RESET_REG 0x0D /* Master Clear (w) */ +#define DMA1_CLR_MASK_REG 0x0E /* Clear Mask */ +#define DMA1_MASK_ALL_REG 0x0F /* all-channels mask (w) */ +#define DMA1_EXT_MODE_REG (0x400 | DMA1_MODE_REG) + +#define DMA2_CMD_REG 0xD0 /* command register (w) */ +#define DMA2_STAT_REG 0xD0 /* status register (r) */ +#define DMA2_REQ_REG 0xD2 /* request register (w) */ +#define DMA2_MASK_REG 0xD4 /* single-channel mask (w) */ +#define DMA2_MODE_REG 0xD6 /* mode register (w) */ +#define DMA2_CLEAR_FF_REG 0xD8 /* clear pointer flip-flop (w) */ +#define DMA2_TEMP_REG 0xDA /* Temporary Register (r) */ +#define DMA2_RESET_REG 0xDA /* Master Clear (w) */ +#define DMA2_CLR_MASK_REG 0xDC /* Clear Mask */ +#define DMA2_MASK_ALL_REG 0xDE /* all-channels mask (w) */ +#define DMA2_EXT_MODE_REG (0x400 | DMA2_MODE_REG) + +#define DMA_ADDR_0 0x00 /* DMA address registers */ +#define DMA_ADDR_1 0x02 +#define DMA_ADDR_2 0x04 +#define DMA_ADDR_3 0x06 +#define DMA_ADDR_4 0xC0 +#define DMA_ADDR_5 0xC4 +#define DMA_ADDR_6 0xC8 +#define DMA_ADDR_7 0xCC + +#define DMA_CNT_0 0x01 /* DMA count registers */ +#define DMA_CNT_1 0x03 +#define DMA_CNT_2 0x05 +#define DMA_CNT_3 0x07 +#define DMA_CNT_4 0xC2 +#define DMA_CNT_5 0xC6 +#define DMA_CNT_6 0xCA +#define DMA_CNT_7 0xCE + +#define DMA_PAGE_0 0x87 /* DMA page registers */ +#define DMA_PAGE_1 0x83 +#define DMA_PAGE_2 0x81 +#define DMA_PAGE_3 0x82 +#define DMA_PAGE_5 0x8B +#define DMA_PAGE_6 0x89 +#define DMA_PAGE_7 0x8A + +#define DMA_HIPAGE_0 (0x400 | DMA_PAGE_0) +#define DMA_HIPAGE_1 (0x400 | DMA_PAGE_1) +#define DMA_HIPAGE_2 (0x400 | DMA_PAGE_2) +#define DMA_HIPAGE_3 (0x400 | DMA_PAGE_3) +#define DMA_HIPAGE_4 (0x400 | DMA_PAGE_4) +#define DMA_HIPAGE_5 (0x400 | DMA_PAGE_5) +#define DMA_HIPAGE_6 (0x400 | DMA_PAGE_6) +#define DMA_HIPAGE_7 (0x400 | DMA_PAGE_7) + +#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 */ +#define DMA_MODE_CASCADE 0xC0 /* pass thru DREQ->HRQ, DACK<-HLDA only */ + +#define DMA_AUTOINIT 0x10 + +extern spinlock_t dma_spin_lock; + +static __inline__ unsigned long claim_dma_lock(void) +{ + unsigned long flags; + spin_lock_irqsave(&dma_spin_lock, flags); + return flags; +} + +static __inline__ void release_dma_lock(unsigned long flags) +{ + spin_unlock_irqrestore(&dma_spin_lock, flags); +} + +/* enable/disable a specific DMA channel */ +static __inline__ void enable_dma(unsigned int dmanr) +{ + if (dmanr<=3) + dma_outb(dmanr, DMA1_MASK_REG); + else + dma_outb(dmanr & 3, DMA2_MASK_REG); +} + +static __inline__ void disable_dma(unsigned int dmanr) +{ + if (dmanr<=3) + dma_outb(dmanr | 4, DMA1_MASK_REG); + else + dma_outb((dmanr & 3) | 4, DMA2_MASK_REG); +} + +/* Clear the 'DMA Pointer Flip Flop'. + * Write 0 for LSB/MSB, 1 for MSB/LSB access. + * Use this once to initialize the FF to a known state. + * After that, keep track of it. :-) + * --- In order to do that, the DMA routines below should --- + * --- only be used while interrupts are disabled! --- + */ +static __inline__ void clear_dma_ff(unsigned int dmanr) +{ + if (dmanr<=3) + dma_outb(0, DMA1_CLEAR_FF_REG); + else + dma_outb(0, DMA2_CLEAR_FF_REG); +} + +/* set mode (above) for a specific DMA channel */ +static __inline__ void set_dma_mode(unsigned int dmanr, char mode) +{ + if (dmanr<=3) + dma_outb(mode | dmanr, DMA1_MODE_REG); + else + dma_outb(mode | (dmanr&3), DMA2_MODE_REG); +} + +/* set extended mode for a specific DMA channel */ +static __inline__ void set_dma_ext_mode(unsigned int dmanr, char ext_mode) +{ + if (dmanr<=3) + dma_outb(ext_mode | dmanr, DMA1_EXT_MODE_REG); + else + dma_outb(ext_mode | (dmanr&3), DMA2_EXT_MODE_REG); +} + +/* Set only the page register bits of the transfer address. + * This is used for successive transfers when we know the contents of + * the lower 16 bits of the DMA current address register. + */ +static __inline__ void set_dma_page(unsigned int dmanr, unsigned int pagenr) +{ + switch(dmanr) { + case 0: + dma_outb(pagenr, DMA_PAGE_0); + dma_outb((pagenr >> 8), DMA_HIPAGE_0); + break; + case 1: + dma_outb(pagenr, DMA_PAGE_1); + dma_outb((pagenr >> 8), DMA_HIPAGE_1); + break; + case 2: + dma_outb(pagenr, DMA_PAGE_2); + dma_outb((pagenr >> 8), DMA_HIPAGE_2); + break; + case 3: + dma_outb(pagenr, DMA_PAGE_3); + dma_outb((pagenr >> 8), DMA_HIPAGE_3); + break; + case 5: + dma_outb(pagenr & 0xfe, DMA_PAGE_5); + dma_outb((pagenr >> 8), DMA_HIPAGE_5); + break; + case 6: + dma_outb(pagenr & 0xfe, DMA_PAGE_6); + dma_outb((pagenr >> 8), DMA_HIPAGE_6); + break; + case 7: + dma_outb(pagenr & 0xfe, DMA_PAGE_7); + dma_outb((pagenr >> 8), DMA_HIPAGE_7); + break; + } +} + + +/* Set transfer address & page bits for specific DMA channel. + * Assumes dma flipflop is clear. + */ +static __inline__ void set_dma_addr(unsigned int dmanr, unsigned int a) +{ + if (dmanr <= 3) { + dma_outb( a & 0xff, ((dmanr&3)<<1) + IO_DMA1_BASE ); + dma_outb( (a>>8) & 0xff, ((dmanr&3)<<1) + IO_DMA1_BASE ); + } else { + dma_outb( (a>>1) & 0xff, ((dmanr&3)<<2) + IO_DMA2_BASE ); + dma_outb( (a>>9) & 0xff, ((dmanr&3)<<2) + IO_DMA2_BASE ); + } + set_dma_page(dmanr, a>>16); /* set hipage last to enable 32-bit mode */ +} + + +/* Set transfer size (max 64k for DMA1..3, 128k for DMA5..7) for + * a specific DMA channel. + * You must ensure the parameters are valid. + * NOTE: from a manual: "the number of transfers is one more + * than the initial word count"! This is taken into account. + * Assumes dma flip-flop is clear. + * NOTE 2: "count" represents _bytes_ and must be even for channels 5-7. + */ +static __inline__ void set_dma_count(unsigned int dmanr, unsigned int count) +{ + count--; + if (dmanr <= 3) { + dma_outb( count & 0xff, ((dmanr&3)<<1) + 1 + IO_DMA1_BASE ); + dma_outb( (count>>8) & 0xff, ((dmanr&3)<<1) + 1 + IO_DMA1_BASE ); + } else { + dma_outb( (count>>1) & 0xff, ((dmanr&3)<<2) + 2 + IO_DMA2_BASE ); + dma_outb( (count>>9) & 0xff, ((dmanr&3)<<2) + 2 + IO_DMA2_BASE ); + } +} + + +/* Get DMA residue count. After a DMA transfer, this + * should return zero. Reading this while a DMA transfer is + * still in progress will return unpredictable results. + * If called before the channel has been used, it may return 1. + * Otherwise, it returns the number of _bytes_ left to transfer. + * + * Assumes DMA flip-flop is clear. + */ +static __inline__ int get_dma_residue(unsigned int dmanr) +{ + unsigned int io_port = (dmanr<=3)? ((dmanr&3)<<1) + 1 + IO_DMA1_BASE + : ((dmanr&3)<<2) + 2 + IO_DMA2_BASE; + + /* using short to get 16-bit wrap around */ + unsigned short count; + + count = 1 + dma_inb(io_port); + count += dma_inb(io_port) << 8; + + return (dmanr<=3)? count : (count<<1); +} + + +/* These are in kernel/dma.c: */ +extern int request_dma(unsigned int dmanr, const char * device_id); /* reserve a DMA channel */ +extern void free_dma(unsigned int dmanr); /* release it again */ +#define KERNEL_HAVE_CHECK_DMA +extern int check_dma(unsigned int dmanr); + +/* From PCI */ + +#ifdef CONFIG_PCI +extern int isa_dma_bridge_buggy; +#else +#define isa_dma_bridge_buggy (0) +#endif + + +#endif /* _ASM_DMA_H */ diff --git a/arch/alpha/include/asm/elf.h b/arch/alpha/include/asm/elf.h new file mode 100644 index 000000000..968d9991f --- /dev/null +++ b/arch/alpha/include/asm/elf.h @@ -0,0 +1,165 @@ +#ifndef __ASM_ALPHA_ELF_H +#define __ASM_ALPHA_ELF_H + +#include <asm/auxvec.h> +#include <asm/special_insns.h> + +/* Special values for the st_other field in the symbol table. */ + +#define STO_ALPHA_NOPV 0x80 +#define STO_ALPHA_STD_GPLOAD 0x88 + +/* + * Alpha ELF relocation types + */ +#define R_ALPHA_NONE 0 /* No reloc */ +#define R_ALPHA_REFLONG 1 /* Direct 32 bit */ +#define R_ALPHA_REFQUAD 2 /* Direct 64 bit */ +#define R_ALPHA_GPREL32 3 /* GP relative 32 bit */ +#define R_ALPHA_LITERAL 4 /* GP relative 16 bit w/optimization */ +#define R_ALPHA_LITUSE 5 /* Optimization hint for LITERAL */ +#define R_ALPHA_GPDISP 6 /* Add displacement to GP */ +#define R_ALPHA_BRADDR 7 /* PC+4 relative 23 bit shifted */ +#define R_ALPHA_HINT 8 /* PC+4 relative 16 bit shifted */ +#define R_ALPHA_SREL16 9 /* PC relative 16 bit */ +#define R_ALPHA_SREL32 10 /* PC relative 32 bit */ +#define R_ALPHA_SREL64 11 /* PC relative 64 bit */ +#define R_ALPHA_GPRELHIGH 17 /* GP relative 32 bit, high 16 bits */ +#define R_ALPHA_GPRELLOW 18 /* GP relative 32 bit, low 16 bits */ +#define R_ALPHA_GPREL16 19 /* GP relative 16 bit */ +#define R_ALPHA_COPY 24 /* Copy symbol at runtime */ +#define R_ALPHA_GLOB_DAT 25 /* Create GOT entry */ +#define R_ALPHA_JMP_SLOT 26 /* Create PLT entry */ +#define R_ALPHA_RELATIVE 27 /* Adjust by program base */ +#define R_ALPHA_BRSGP 28 +#define R_ALPHA_TLSGD 29 +#define R_ALPHA_TLS_LDM 30 +#define R_ALPHA_DTPMOD64 31 +#define R_ALPHA_GOTDTPREL 32 +#define R_ALPHA_DTPREL64 33 +#define R_ALPHA_DTPRELHI 34 +#define R_ALPHA_DTPRELLO 35 +#define R_ALPHA_DTPREL16 36 +#define R_ALPHA_GOTTPREL 37 +#define R_ALPHA_TPREL64 38 +#define R_ALPHA_TPRELHI 39 +#define R_ALPHA_TPRELLO 40 +#define R_ALPHA_TPREL16 41 + +#define SHF_ALPHA_GPREL 0x10000000 + +/* Legal values for e_flags field of Elf64_Ehdr. */ + +#define EF_ALPHA_32BIT 1 /* All addresses are below 2GB */ + +/* + * ELF register definitions.. + */ + +/* + * The OSF/1 version of <sys/procfs.h> makes gregset_t 46 entries long. + * I have no idea why that is so. For now, we just leave it at 33 + * (32 general regs + processor status word). + */ +#define ELF_NGREG 33 +#define ELF_NFPREG 32 + +typedef unsigned long elf_greg_t; +typedef elf_greg_t elf_gregset_t[ELF_NGREG]; + +typedef double elf_fpreg_t; +typedef elf_fpreg_t elf_fpregset_t[ELF_NFPREG]; + +/* + * This is used to ensure we don't load something for the wrong architecture. + */ +#define elf_check_arch(x) ((x)->e_machine == EM_ALPHA) + +/* + * These are used to set parameters in the core dumps. + */ +#define ELF_CLASS ELFCLASS64 +#define ELF_DATA ELFDATA2LSB +#define ELF_ARCH EM_ALPHA + +#define ELF_EXEC_PAGESIZE 8192 + +/* This is the location that an ET_DYN program is loaded if exec'ed. Typical + use of this is to invoke "./ld.so someprog" to test out a new version of + the loader. We need to make sure that it is out of the way of the program + that it will "exec", and that there is sufficient room for the brk. */ + +#define ELF_ET_DYN_BASE (TASK_UNMAPPED_BASE + 0x1000000) + +/* $0 is set by ld.so to a pointer to a function which might be + registered using atexit. This provides a mean for the dynamic + linker to call DT_FINI functions for shared libraries that have + been loaded before the code runs. + + So that we can use the same startup file with static executables, + we start programs with a value of 0 to indicate that there is no + such function. */ + +#define ELF_PLAT_INIT(_r, load_addr) _r->r0 = 0 + +/* The registers are laid out in pt_regs for PAL and syscall + convenience. Re-order them for the linear elf_gregset_t. */ + +struct pt_regs; +struct thread_info; +struct task_struct; +extern void dump_elf_thread(elf_greg_t *dest, struct pt_regs *pt, + struct thread_info *ti); +#define ELF_CORE_COPY_REGS(DEST, REGS) \ + dump_elf_thread(DEST, REGS, current_thread_info()); + +/* Similar, but for a thread other than current. */ + +extern int dump_elf_task(elf_greg_t *dest, struct task_struct *task); +#define ELF_CORE_COPY_TASK_REGS(TASK, DEST) \ + dump_elf_task(*(DEST), TASK) + +/* Similar, but for the FP registers. */ + +extern int dump_elf_task_fp(elf_fpreg_t *dest, struct task_struct *task); +#define ELF_CORE_COPY_FPREGS(TASK, DEST) \ + dump_elf_task_fp(*(DEST), TASK) + +/* This yields a mask that user programs can use to figure out what + instruction set this CPU supports. This is trivial on Alpha, + but not so on other machines. */ + +#define ELF_HWCAP (~amask(-1)) + +/* This yields a string that ld.so will use to load implementation + specific libraries for optimization. This is more specific in + intent than poking at uname or /proc/cpuinfo. */ + +#define ELF_PLATFORM \ +({ \ + enum implver_enum i_ = implver(); \ + ( i_ == IMPLVER_EV4 ? "ev4" \ + : i_ == IMPLVER_EV5 \ + ? (amask(AMASK_BWX) ? "ev5" : "ev56") \ + : amask (AMASK_CIX) ? "ev6" : "ev67"); \ +}) + +#define SET_PERSONALITY(EX) \ + set_personality(((EX).e_flags & EF_ALPHA_32BIT) \ + ? PER_LINUX_32BIT : PER_LINUX) + +extern int alpha_l1i_cacheshape; +extern int alpha_l1d_cacheshape; +extern int alpha_l2_cacheshape; +extern int alpha_l3_cacheshape; + +/* update AT_VECTOR_SIZE_ARCH if the number of NEW_AUX_ENT entries changes */ +#define ARCH_DLINFO \ + do { \ + NEW_AUX_ENT(AT_L1I_CACHESHAPE, alpha_l1i_cacheshape); \ + NEW_AUX_ENT(AT_L1D_CACHESHAPE, alpha_l1d_cacheshape); \ + NEW_AUX_ENT(AT_L2_CACHESHAPE, alpha_l2_cacheshape); \ + NEW_AUX_ENT(AT_L3_CACHESHAPE, alpha_l3_cacheshape); \ + } while (0) + +#endif /* __ASM_ALPHA_ELF_H */ diff --git a/arch/alpha/include/asm/emergency-restart.h b/arch/alpha/include/asm/emergency-restart.h new file mode 100644 index 000000000..108d8c48e --- /dev/null +++ b/arch/alpha/include/asm/emergency-restart.h @@ -0,0 +1,6 @@ +#ifndef _ASM_EMERGENCY_RESTART_H +#define _ASM_EMERGENCY_RESTART_H + +#include <asm-generic/emergency-restart.h> + +#endif /* _ASM_EMERGENCY_RESTART_H */ diff --git a/arch/alpha/include/asm/err_common.h b/arch/alpha/include/asm/err_common.h new file mode 100644 index 000000000..c25095942 --- /dev/null +++ b/arch/alpha/include/asm/err_common.h @@ -0,0 +1,118 @@ +/* + * linux/include/asm-alpha/err_common.h + * + * Copyright (C) 2000 Jeff Wiedemeier (Compaq Computer Corporation) + * + * Contains declarations and macros to support Alpha error handling + * implementations. + */ + +#ifndef __ALPHA_ERR_COMMON_H +#define __ALPHA_ERR_COMMON_H 1 + +/* + * SCB Vector definitions + */ +#define SCB_Q_SYSERR 0x620 +#define SCB_Q_PROCERR 0x630 +#define SCB_Q_SYSMCHK 0x660 +#define SCB_Q_PROCMCHK 0x670 +#define SCB_Q_SYSEVENT 0x680 + +/* + * Disposition definitions for logout frame parser + */ +#define MCHK_DISPOSITION_UNKNOWN_ERROR 0x00 +#define MCHK_DISPOSITION_REPORT 0x01 +#define MCHK_DISPOSITION_DISMISS 0x02 + +/* + * Error Log definitions + */ +/* + * Types + */ + +#define EL_CLASS__TERMINATION (0) +# define EL_TYPE__TERMINATION__TERMINATION (0) +#define EL_CLASS__HEADER (5) +# define EL_TYPE__HEADER__SYSTEM_ERROR_FRAME (1) +# define EL_TYPE__HEADER__SYSTEM_EVENT_FRAME (2) +# define EL_TYPE__HEADER__HALT_FRAME (3) +# define EL_TYPE__HEADER__LOGOUT_FRAME (19) +#define EL_CLASS__GENERAL_NOTIFICATION (9) +#define EL_CLASS__PCI_ERROR_FRAME (11) +#define EL_CLASS__REGATTA_FAMILY (12) +# define EL_TYPE__REGATTA__PROCESSOR_ERROR_FRAME (1) +# define EL_TYPE__REGATTA__SYSTEM_ERROR_FRAME (2) +# define EL_TYPE__REGATTA__ENVIRONMENTAL_FRAME (3) +# define EL_TYPE__REGATTA__TITAN_PCHIP0_EXTENDED (8) +# define EL_TYPE__REGATTA__TITAN_PCHIP1_EXTENDED (9) +# define EL_TYPE__REGATTA__TITAN_MEMORY_EXTENDED (10) +# define EL_TYPE__REGATTA__PROCESSOR_DBL_ERROR_HALT (11) +# define EL_TYPE__REGATTA__SYSTEM_DBL_ERROR_HALT (12) +#define EL_CLASS__PAL (14) +# define EL_TYPE__PAL__LOGOUT_FRAME (1) +# define EL_TYPE__PAL__EV7_PROCESSOR (4) +# define EL_TYPE__PAL__EV7_ZBOX (5) +# define EL_TYPE__PAL__EV7_RBOX (6) +# define EL_TYPE__PAL__EV7_IO (7) +# define EL_TYPE__PAL__ENV__AMBIENT_TEMPERATURE (10) +# define EL_TYPE__PAL__ENV__AIRMOVER_FAN (11) +# define EL_TYPE__PAL__ENV__VOLTAGE (12) +# define EL_TYPE__PAL__ENV__INTRUSION (13) +# define EL_TYPE__PAL__ENV__POWER_SUPPLY (14) +# define EL_TYPE__PAL__ENV__LAN (15) +# define EL_TYPE__PAL__ENV__HOT_PLUG (16) + +union el_timestamp { + struct { + u8 second; + u8 minute; + u8 hour; + u8 day; + u8 month; + u8 year; + } b; + u64 as_int; +}; + +struct el_subpacket { + u16 length; /* length of header (in bytes) */ + u16 class; /* header class and type... */ + u16 type; /* ...determine content */ + u16 revision; /* header revision */ + union { + struct { /* Class 5, Type 1 - System Error */ + u32 frame_length; + u32 frame_packet_count; + } sys_err; + struct { /* Class 5, Type 2 - System Event */ + union el_timestamp timestamp; + u32 frame_length; + u32 frame_packet_count; + } sys_event; + struct { /* Class 5, Type 3 - Double Error Halt */ + u16 halt_code; + u16 reserved; + union el_timestamp timestamp; + u32 frame_length; + u32 frame_packet_count; + } err_halt; + struct { /* Clasee 5, Type 19 - Logout Frame Header */ + u32 frame_length; + u32 frame_flags; + u32 cpu_offset; + u32 system_offset; + } logout_header; + struct { /* Class 12 - Regatta */ + u64 cpuid; + u64 data_start[1]; + } regatta_frame; + struct { /* Raw */ + u64 data_start[1]; + } raw; + } by_type; +}; + +#endif /* __ALPHA_ERR_COMMON_H */ diff --git a/arch/alpha/include/asm/err_ev6.h b/arch/alpha/include/asm/err_ev6.h new file mode 100644 index 000000000..ea637791e --- /dev/null +++ b/arch/alpha/include/asm/err_ev6.h @@ -0,0 +1,6 @@ +#ifndef __ALPHA_ERR_EV6_H +#define __ALPHA_ERR_EV6_H 1 + +/* Dummy include for now. */ + +#endif /* __ALPHA_ERR_EV6_H */ diff --git a/arch/alpha/include/asm/err_ev7.h b/arch/alpha/include/asm/err_ev7.h new file mode 100644 index 000000000..87f99777c --- /dev/null +++ b/arch/alpha/include/asm/err_ev7.h @@ -0,0 +1,202 @@ +#ifndef __ALPHA_ERR_EV7_H +#define __ALPHA_ERR_EV7_H 1 + +/* + * Data for el packet class PAL (14), type LOGOUT_FRAME (1) + */ +struct ev7_pal_logout_subpacket { + u32 mchk_code; + u32 subpacket_count; + u64 whami; + u64 rbox_whami; + u64 rbox_int; + u64 exc_addr; + union el_timestamp timestamp; + u64 halt_code; + u64 reserved; +}; + +/* + * Data for el packet class PAL (14), type EV7_PROCESSOR (4) + */ +struct ev7_pal_processor_subpacket { + u64 i_stat; + u64 dc_stat; + u64 c_addr; + u64 c_syndrome_1; + u64 c_syndrome_0; + u64 c_stat; + u64 c_sts; + u64 mm_stat; + u64 exc_addr; + u64 ier_cm; + u64 isum; + u64 pal_base; + u64 i_ctl; + u64 process_context; + u64 cbox_ctl; + u64 cbox_stp_ctl; + u64 cbox_acc_ctl; + u64 cbox_lcl_set; + u64 cbox_gbl_set; + u64 bbox_ctl; + u64 bbox_err_sts; + u64 bbox_err_idx; + u64 cbox_ddp_err_sts; + u64 bbox_dat_rmp; + u64 reserved[2]; +}; + +/* + * Data for el packet class PAL (14), type EV7_ZBOX (5) + */ +struct ev7_pal_zbox_subpacket { + u32 zbox0_dram_err_status_1; + u32 zbox0_dram_err_status_2; + u32 zbox0_dram_err_status_3; + u32 zbox0_dram_err_ctl; + u32 zbox0_dram_err_adr; + u32 zbox0_dift_timeout; + u32 zbox0_dram_mapper_ctl; + u32 zbox0_frc_err_adr; + u32 zbox0_dift_err_status; + u32 reserved1; + u32 zbox1_dram_err_status_1; + u32 zbox1_dram_err_status_2; + u32 zbox1_dram_err_status_3; + u32 zbox1_dram_err_ctl; + u32 zbox1_dram_err_adr; + u32 zbox1_dift_timeout; + u32 zbox1_dram_mapper_ctl; + u32 zbox1_frc_err_adr; + u32 zbox1_dift_err_status; + u32 reserved2; + u64 cbox_ctl; + u64 cbox_stp_ctl; + u64 zbox0_error_pa; + u64 zbox1_error_pa; + u64 zbox0_ored_syndrome; + u64 zbox1_ored_syndrome; + u64 reserved3[2]; +}; + +/* + * Data for el packet class PAL (14), type EV7_RBOX (6) + */ +struct ev7_pal_rbox_subpacket { + u64 rbox_cfg; + u64 rbox_n_cfg; + u64 rbox_s_cfg; + u64 rbox_e_cfg; + u64 rbox_w_cfg; + u64 rbox_n_err; + u64 rbox_s_err; + u64 rbox_e_err; + u64 rbox_w_err; + u64 rbox_io_cfg; + u64 rbox_io_err; + u64 rbox_l_err; + u64 rbox_whoami; + u64 rbox_imask; + u64 rbox_intq; + u64 rbox_int; + u64 reserved[2]; +}; + +/* + * Data for el packet class PAL (14), type EV7_IO (7) + */ +struct ev7_pal_io_one_port { + u64 pox_err_sum; + u64 pox_tlb_err; + u64 pox_spl_cmplt; + u64 pox_trans_sum; + u64 pox_first_err; + u64 pox_mult_err; + u64 pox_dm_source; + u64 pox_dm_dest; + u64 pox_dm_size; + u64 pox_dm_ctrl; + u64 reserved; +}; + +struct ev7_pal_io_subpacket { + u64 io_asic_rev; + u64 io_sys_rev; + u64 io7_uph; + u64 hpi_ctl; + u64 crd_ctl; + u64 hei_ctl; + u64 po7_error_sum; + u64 po7_uncrr_sym; + u64 po7_crrct_sym; + u64 po7_ugbge_sym; + u64 po7_err_pkt0; + u64 po7_err_pkt1; + u64 reserved[2]; + struct ev7_pal_io_one_port ports[4]; +}; + +/* + * Environmental subpacket. Data used for el packets: + * class PAL (14), type AMBIENT_TEMPERATURE (10) + * class PAL (14), type AIRMOVER_FAN (11) + * class PAL (14), type VOLTAGE (12) + * class PAL (14), type INTRUSION (13) + * class PAL (14), type POWER_SUPPLY (14) + * class PAL (14), type LAN (15) + * class PAL (14), type HOT_PLUG (16) + */ +struct ev7_pal_environmental_subpacket { + u16 cabinet; + u16 drawer; + u16 reserved1[2]; + u8 module_type; + u8 unit_id; /* unit reporting condition */ + u8 reserved2; + u8 condition; /* condition reported */ +}; + +/* + * Convert environmental type to index + */ +static inline int ev7_lf_env_index(int type) +{ + BUG_ON((type < EL_TYPE__PAL__ENV__AMBIENT_TEMPERATURE) + || (type > EL_TYPE__PAL__ENV__HOT_PLUG)); + + return type - EL_TYPE__PAL__ENV__AMBIENT_TEMPERATURE; +} + +/* + * Data for generic el packet class PAL. + */ +struct ev7_pal_subpacket { + union { + struct ev7_pal_logout_subpacket logout; /* Type 1 */ + struct ev7_pal_processor_subpacket ev7; /* Type 4 */ + struct ev7_pal_zbox_subpacket zbox; /* Type 5 */ + struct ev7_pal_rbox_subpacket rbox; /* Type 6 */ + struct ev7_pal_io_subpacket io; /* Type 7 */ + struct ev7_pal_environmental_subpacket env; /* Type 10-16 */ + u64 as_quad[1]; /* Raw u64 */ + } by_type; +}; + +/* + * Struct to contain collected logout from subpackets. + */ +struct ev7_lf_subpackets { + struct ev7_pal_logout_subpacket *logout; /* Type 1 */ + struct ev7_pal_processor_subpacket *ev7; /* Type 4 */ + struct ev7_pal_zbox_subpacket *zbox; /* Type 5 */ + struct ev7_pal_rbox_subpacket *rbox; /* Type 6 */ + struct ev7_pal_io_subpacket *io; /* Type 7 */ + struct ev7_pal_environmental_subpacket *env[7]; /* Type 10-16 */ + + unsigned int io_pid; +}; + +#endif /* __ALPHA_ERR_EV7_H */ + + diff --git a/arch/alpha/include/asm/fb.h b/arch/alpha/include/asm/fb.h new file mode 100644 index 000000000..fa9bbb96b --- /dev/null +++ b/arch/alpha/include/asm/fb.h @@ -0,0 +1,13 @@ +#ifndef _ASM_FB_H_ +#define _ASM_FB_H_ +#include <linux/device.h> + +/* Caching is off in the I/O space quadrant by design. */ +#define fb_pgprotect(...) do {} while (0) + +static inline int fb_is_primary_device(struct fb_info *info) +{ + return 0; +} + +#endif /* _ASM_FB_H_ */ diff --git a/arch/alpha/include/asm/floppy.h b/arch/alpha/include/asm/floppy.h new file mode 100644 index 000000000..bae97eb19 --- /dev/null +++ b/arch/alpha/include/asm/floppy.h @@ -0,0 +1,115 @@ +/* + * Architecture specific parts of the Floppy driver + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * Copyright (C) 1995 + */ +#ifndef __ASM_ALPHA_FLOPPY_H +#define __ASM_ALPHA_FLOPPY_H + + +#define fd_inb(port) inb_p(port) +#define fd_outb(value,port) outb_p(value,port) + +#define fd_enable_dma() enable_dma(FLOPPY_DMA) +#define fd_disable_dma() disable_dma(FLOPPY_DMA) +#define fd_request_dma() request_dma(FLOPPY_DMA,"floppy") +#define fd_free_dma() free_dma(FLOPPY_DMA) +#define fd_clear_dma_ff() clear_dma_ff(FLOPPY_DMA) +#define fd_set_dma_mode(mode) set_dma_mode(FLOPPY_DMA,mode) +#define fd_set_dma_addr(addr) set_dma_addr(FLOPPY_DMA,virt_to_bus(addr)) +#define fd_set_dma_count(count) set_dma_count(FLOPPY_DMA,count) +#define fd_enable_irq() enable_irq(FLOPPY_IRQ) +#define fd_disable_irq() disable_irq(FLOPPY_IRQ) +#define fd_cacheflush(addr,size) /* nothing */ +#define fd_request_irq() request_irq(FLOPPY_IRQ, floppy_interrupt,\ + 0, "floppy", NULL) +#define fd_free_irq() free_irq(FLOPPY_IRQ, NULL) + +#ifdef CONFIG_PCI + +#include <linux/pci.h> + +#define fd_dma_setup(addr,size,mode,io) alpha_fd_dma_setup(addr,size,mode,io) + +static __inline__ int +alpha_fd_dma_setup(char *addr, unsigned long size, int mode, int io) +{ + static unsigned long prev_size; + static dma_addr_t bus_addr = 0; + static char *prev_addr; + static int prev_dir; + int dir; + + dir = (mode != DMA_MODE_READ) ? PCI_DMA_FROMDEVICE : PCI_DMA_TODEVICE; + + if (bus_addr + && (addr != prev_addr || size != prev_size || dir != prev_dir)) { + /* different from last time -- unmap prev */ + pci_unmap_single(isa_bridge, bus_addr, prev_size, prev_dir); + bus_addr = 0; + } + + if (!bus_addr) /* need to map it */ + bus_addr = pci_map_single(isa_bridge, addr, size, dir); + + /* remember this one as prev */ + prev_addr = addr; + prev_size = size; + prev_dir = dir; + + fd_clear_dma_ff(); + fd_cacheflush(addr, size); + fd_set_dma_mode(mode); + set_dma_addr(FLOPPY_DMA, bus_addr); + fd_set_dma_count(size); + virtual_dma_port = io; + fd_enable_dma(); + + return 0; +} + +#endif /* CONFIG_PCI */ + +__inline__ void virtual_dma_init(void) +{ + /* Nothing to do on an Alpha */ +} + +static int FDC1 = 0x3f0; +static int FDC2 = -1; + +/* + * Again, the CMOS information doesn't work on the alpha.. + */ +#define FLOPPY0_TYPE 6 +#define FLOPPY1_TYPE 0 + +#define N_FDC 2 +#define N_DRIVE 8 + +/* + * Most Alphas have no problems with floppy DMA crossing 64k borders, + * except for certain ones, like XL and RUFFIAN. + * + * However, the test is simple and fast, and this *is* floppy, after all, + * so we do it for all platforms, just to make sure. + * + * This is advantageous in other circumstances as well, as in moving + * about the PCI DMA windows and forcing the floppy to start doing + * scatter-gather when it never had before, and there *is* a problem + * on that platform... ;-} + */ + +static inline unsigned long CROSS_64KB(void *a, unsigned long s) +{ + unsigned long p = (unsigned long)a; + return ((p + s - 1) ^ p) & ~0xffffUL; +} + +#define EXTRA_FLOPPY_PARAMS + +#endif /* __ASM_ALPHA_FLOPPY_H */ diff --git a/arch/alpha/include/asm/fpu.h b/arch/alpha/include/asm/fpu.h new file mode 100644 index 000000000..71c20956b --- /dev/null +++ b/arch/alpha/include/asm/fpu.h @@ -0,0 +1,75 @@ +#ifndef __ASM_ALPHA_FPU_H +#define __ASM_ALPHA_FPU_H + +#include <asm/special_insns.h> +#include <uapi/asm/fpu.h> + +/* The following two functions don't need trapb/excb instructions + around the mf_fpcr/mt_fpcr instructions because (a) the kernel + never generates arithmetic faults and (b) call_pal instructions + are implied trap barriers. */ + +static inline unsigned long +rdfpcr(void) +{ + unsigned long tmp, ret; + +#if defined(CONFIG_ALPHA_EV6) || defined(CONFIG_ALPHA_EV67) + __asm__ __volatile__ ( + "ftoit $f0,%0\n\t" + "mf_fpcr $f0\n\t" + "ftoit $f0,%1\n\t" + "itoft %0,$f0" + : "=r"(tmp), "=r"(ret)); +#else + __asm__ __volatile__ ( + "stt $f0,%0\n\t" + "mf_fpcr $f0\n\t" + "stt $f0,%1\n\t" + "ldt $f0,%0" + : "=m"(tmp), "=m"(ret)); +#endif + + return ret; +} + +static inline void +wrfpcr(unsigned long val) +{ + unsigned long tmp; + +#if defined(CONFIG_ALPHA_EV6) || defined(CONFIG_ALPHA_EV67) + __asm__ __volatile__ ( + "ftoit $f0,%0\n\t" + "itoft %1,$f0\n\t" + "mt_fpcr $f0\n\t" + "itoft %0,$f0" + : "=&r"(tmp) : "r"(val)); +#else + __asm__ __volatile__ ( + "stt $f0,%0\n\t" + "ldt $f0,%1\n\t" + "mt_fpcr $f0\n\t" + "ldt $f0,%0" + : "=m"(tmp) : "m"(val)); +#endif +} + +static inline unsigned long +swcr_update_status(unsigned long swcr, unsigned long fpcr) +{ + /* EV6 implements most of the bits in hardware. Collect + the acrued exception bits from the real fpcr. */ + if (implver() == IMPLVER_EV6) { + swcr &= ~IEEE_STATUS_MASK; + swcr |= (fpcr >> 35) & IEEE_STATUS_MASK; + } + return swcr; +} + +extern unsigned long alpha_read_fp_reg (unsigned long reg); +extern void alpha_write_fp_reg (unsigned long reg, unsigned long val); +extern unsigned long alpha_read_fp_reg_s (unsigned long reg); +extern void alpha_write_fp_reg_s (unsigned long reg, unsigned long val); + +#endif /* __ASM_ALPHA_FPU_H */ diff --git a/arch/alpha/include/asm/ftrace.h b/arch/alpha/include/asm/ftrace.h new file mode 100644 index 000000000..40a8c178f --- /dev/null +++ b/arch/alpha/include/asm/ftrace.h @@ -0,0 +1 @@ +/* empty */ diff --git a/arch/alpha/include/asm/futex.h b/arch/alpha/include/asm/futex.h new file mode 100644 index 000000000..f93979436 --- /dev/null +++ b/arch/alpha/include/asm/futex.h @@ -0,0 +1,119 @@ +#ifndef _ASM_ALPHA_FUTEX_H +#define _ASM_ALPHA_FUTEX_H + +#ifdef __KERNEL__ + +#include <linux/futex.h> +#include <linux/uaccess.h> +#include <asm/errno.h> +#include <asm/barrier.h> + +#define __futex_atomic_op(insn, ret, oldval, uaddr, oparg) \ + __asm__ __volatile__( \ + __ASM_SMP_MB \ + "1: ldl_l %0,0(%2)\n" \ + insn \ + "2: stl_c %1,0(%2)\n" \ + " beq %1,4f\n" \ + " mov $31,%1\n" \ + "3: .subsection 2\n" \ + "4: br 1b\n" \ + " .previous\n" \ + " .section __ex_table,\"a\"\n" \ + " .long 1b-.\n" \ + " lda $31,3b-1b(%1)\n" \ + " .long 2b-.\n" \ + " lda $31,3b-2b(%1)\n" \ + " .previous\n" \ + : "=&r" (oldval), "=&r"(ret) \ + : "r" (uaddr), "r"(oparg) \ + : "memory") + +static inline int futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr) +{ + int op = (encoded_op >> 28) & 7; + int cmp = (encoded_op >> 24) & 15; + int oparg = (encoded_op << 8) >> 20; + int cmparg = (encoded_op << 20) >> 20; + int oldval = 0, ret; + if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28)) + oparg = 1 << oparg; + + if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))) + return -EFAULT; + + pagefault_disable(); + + switch (op) { + case FUTEX_OP_SET: + __futex_atomic_op("mov %3,%1\n", ret, oldval, uaddr, oparg); + break; + case FUTEX_OP_ADD: + __futex_atomic_op("addl %0,%3,%1\n", ret, oldval, uaddr, oparg); + break; + case FUTEX_OP_OR: + __futex_atomic_op("or %0,%3,%1\n", ret, oldval, uaddr, oparg); + break; + case FUTEX_OP_ANDN: + __futex_atomic_op("andnot %0,%3,%1\n", ret, oldval, uaddr, oparg); + break; + case FUTEX_OP_XOR: + __futex_atomic_op("xor %0,%3,%1\n", ret, oldval, uaddr, oparg); + break; + default: + ret = -ENOSYS; + } + + pagefault_enable(); + + if (!ret) { + switch (cmp) { + case FUTEX_OP_CMP_EQ: ret = (oldval == cmparg); break; + case FUTEX_OP_CMP_NE: ret = (oldval != cmparg); break; + case FUTEX_OP_CMP_LT: ret = (oldval < cmparg); break; + case FUTEX_OP_CMP_GE: ret = (oldval >= cmparg); break; + case FUTEX_OP_CMP_LE: ret = (oldval <= cmparg); break; + case FUTEX_OP_CMP_GT: ret = (oldval > cmparg); break; + default: ret = -ENOSYS; + } + } + return ret; +} + +static inline int +futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, + u32 oldval, u32 newval) +{ + int ret = 0, cmp; + u32 prev; + + if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))) + return -EFAULT; + + __asm__ __volatile__ ( + __ASM_SMP_MB + "1: ldl_l %1,0(%3)\n" + " cmpeq %1,%4,%2\n" + " beq %2,3f\n" + " mov %5,%2\n" + "2: stl_c %2,0(%3)\n" + " beq %2,4f\n" + "3: .subsection 2\n" + "4: br 1b\n" + " .previous\n" + " .section __ex_table,\"a\"\n" + " .long 1b-.\n" + " lda $31,3b-1b(%0)\n" + " .long 2b-.\n" + " lda $31,3b-2b(%0)\n" + " .previous\n" + : "+r"(ret), "=&r"(prev), "=&r"(cmp) + : "r"(uaddr), "r"((long)(int)oldval), "r"(newval) + : "memory"); + + *uval = prev; + return ret; +} + +#endif /* __KERNEL__ */ +#endif /* _ASM_ALPHA_FUTEX_H */ diff --git a/arch/alpha/include/asm/gct.h b/arch/alpha/include/asm/gct.h new file mode 100644 index 000000000..3504c7049 --- /dev/null +++ b/arch/alpha/include/asm/gct.h @@ -0,0 +1,58 @@ +#ifndef __ALPHA_GCT_H +#define __ALPHA_GCT_H + +typedef u64 gct_id; +typedef u64 gct6_handle; + +typedef struct __gct6_node { + u8 type; + u8 subtype; + u16 size; + u32 hd_extension; + gct6_handle owner; + gct6_handle active_user; + gct_id id; + u64 flags; + u16 rev; + u16 change_counter; + u16 max_child; + u16 reserved1; + gct6_handle saved_owner; + gct6_handle affinity; + gct6_handle parent; + gct6_handle next; + gct6_handle prev; + gct6_handle child; + u64 fw_flags; + u64 os_usage; + u64 fru_id; + u32 checksum; + u32 magic; /* 'GLXY' */ +} gct6_node; + +typedef struct { + u8 type; + u8 subtype; + void (*callout)(gct6_node *); +} gct6_search_struct; + +#define GCT_NODE_MAGIC 0x59584c47 /* 'GLXY' */ + +/* + * node types + */ +#define GCT_TYPE_HOSE 0x0E + +/* + * node subtypes + */ +#define GCT_SUBTYPE_IO_PORT_MODULE 0x2C + +#define GCT_NODE_PTR(off) ((gct6_node *)((char *)hwrpb + \ + hwrpb->frut_offset + \ + (gct6_handle)(off))) \ + +int gct6_find_nodes(gct6_node *, gct6_search_struct *); + +#endif /* __ALPHA_GCT_H */ + diff --git a/arch/alpha/include/asm/gpio.h b/arch/alpha/include/asm/gpio.h new file mode 100644 index 000000000..b3799d88f --- /dev/null +++ b/arch/alpha/include/asm/gpio.h @@ -0,0 +1,4 @@ +#ifndef __LINUX_GPIO_H +#warning Include linux/gpio.h instead of asm/gpio.h +#include <linux/gpio.h> +#endif diff --git a/arch/alpha/include/asm/hardirq.h b/arch/alpha/include/asm/hardirq.h new file mode 100644 index 000000000..242c09ba9 --- /dev/null +++ b/arch/alpha/include/asm/hardirq.h @@ -0,0 +1,9 @@ +#ifndef _ALPHA_HARDIRQ_H +#define _ALPHA_HARDIRQ_H + +void ack_bad_irq(unsigned int irq); +#define ack_bad_irq ack_bad_irq + +#include <asm-generic/hardirq.h> + +#endif /* _ALPHA_HARDIRQ_H */ diff --git a/arch/alpha/include/asm/hw_irq.h b/arch/alpha/include/asm/hw_irq.h new file mode 100644 index 000000000..5050ac81c --- /dev/null +++ b/arch/alpha/include/asm/hw_irq.h @@ -0,0 +1,14 @@ +#ifndef _ALPHA_HW_IRQ_H +#define _ALPHA_HW_IRQ_H + + +extern volatile unsigned long irq_err_count; +DECLARE_PER_CPU(unsigned long, irq_pmi_count); + +#ifdef CONFIG_ALPHA_GENERIC +#define ACTUAL_NR_IRQS alpha_mv.nr_irqs +#else +#define ACTUAL_NR_IRQS NR_IRQS +#endif + +#endif diff --git a/arch/alpha/include/asm/hwrpb.h b/arch/alpha/include/asm/hwrpb.h new file mode 100644 index 000000000..8e8f871af --- /dev/null +++ b/arch/alpha/include/asm/hwrpb.h @@ -0,0 +1,220 @@ +#ifndef __ALPHA_HWRPB_H +#define __ALPHA_HWRPB_H + +#define INIT_HWRPB ((struct hwrpb_struct *) 0x10000000) + +/* + * DEC processor types for Alpha systems. Found in HWRPB. + * These values are architected. + */ + +#define EV3_CPU 1 /* EV3 */ +#define EV4_CPU 2 /* EV4 (21064) */ +#define LCA4_CPU 4 /* LCA4 (21066/21068) */ +#define EV5_CPU 5 /* EV5 (21164) */ +#define EV45_CPU 6 /* EV4.5 (21064/xxx) */ +#define EV56_CPU 7 /* EV5.6 (21164) */ +#define EV6_CPU 8 /* EV6 (21264) */ +#define PCA56_CPU 9 /* PCA56 (21164PC) */ +#define PCA57_CPU 10 /* PCA57 (notyet) */ +#define EV67_CPU 11 /* EV67 (21264A) */ +#define EV68CB_CPU 12 /* EV68CB (21264C) */ +#define EV68AL_CPU 13 /* EV68AL (21264B) */ +#define EV68CX_CPU 14 /* EV68CX (21264D) */ +#define EV7_CPU 15 /* EV7 (21364) */ +#define EV79_CPU 16 /* EV79 (21364??) */ +#define EV69_CPU 17 /* EV69 (21264/EV69A) */ + +/* + * DEC system types for Alpha systems. Found in HWRPB. + * These values are architected. + */ + +#define ST_ADU 1 /* Alpha ADU systype */ +#define ST_DEC_4000 2 /* Cobra systype */ +#define ST_DEC_7000 3 /* Ruby systype */ +#define ST_DEC_3000_500 4 /* Flamingo systype */ +#define ST_DEC_2000_300 6 /* Jensen systype */ +#define ST_DEC_3000_300 7 /* Pelican systype */ +#define ST_DEC_2100_A500 9 /* Sable systype */ +#define ST_DEC_AXPVME_64 10 /* AXPvme system type */ +#define ST_DEC_AXPPCI_33 11 /* NoName system type */ +#define ST_DEC_TLASER 12 /* Turbolaser systype */ +#define ST_DEC_2100_A50 13 /* Avanti systype */ +#define ST_DEC_MUSTANG 14 /* Mustang systype */ +#define ST_DEC_ALCOR 15 /* Alcor (EV5) systype */ +#define ST_DEC_1000 17 /* Mikasa systype */ +#define ST_DEC_EB64 18 /* EB64 systype */ +#define ST_DEC_EB66 19 /* EB66 systype */ +#define ST_DEC_EB64P 20 /* EB64+ systype */ +#define ST_DEC_BURNS 21 /* laptop systype */ +#define ST_DEC_RAWHIDE 22 /* Rawhide systype */ +#define ST_DEC_K2 23 /* K2 systype */ +#define ST_DEC_LYNX 24 /* Lynx systype */ +#define ST_DEC_XL 25 /* Alpha XL systype */ +#define ST_DEC_EB164 26 /* EB164 systype */ +#define ST_DEC_NORITAKE 27 /* Noritake systype */ +#define ST_DEC_CORTEX 28 /* Cortex systype */ +#define ST_DEC_MIATA 30 /* Miata systype */ +#define ST_DEC_XXM 31 /* XXM systype */ +#define ST_DEC_TAKARA 32 /* Takara systype */ +#define ST_DEC_YUKON 33 /* Yukon systype */ +#define ST_DEC_TSUNAMI 34 /* Tsunami systype */ +#define ST_DEC_WILDFIRE 35 /* Wildfire systype */ +#define ST_DEC_CUSCO 36 /* CUSCO systype */ +#define ST_DEC_EIGER 37 /* Eiger systype */ +#define ST_DEC_TITAN 38 /* Titan systype */ +#define ST_DEC_MARVEL 39 /* Marvel systype */ + +/* UNOFFICIAL!!! */ +#define ST_UNOFFICIAL_BIAS 100 +#define ST_DTI_RUFFIAN 101 /* RUFFIAN systype */ + +/* Alpha Processor, Inc. systems */ +#define ST_API_BIAS 200 +#define ST_API_NAUTILUS 201 /* UP1000 systype */ + +struct pcb_struct { + unsigned long ksp; + unsigned long usp; + unsigned long ptbr; + unsigned int pcc; + unsigned int asn; + unsigned long unique; + unsigned long flags; + unsigned long res1, res2; +}; + +struct percpu_struct { + unsigned long hwpcb[16]; + unsigned long flags; + unsigned long pal_mem_size; + unsigned long pal_scratch_size; + unsigned long pal_mem_pa; + unsigned long pal_scratch_pa; + unsigned long pal_revision; + unsigned long type; + unsigned long variation; + unsigned long revision; + unsigned long serial_no[2]; + unsigned long logout_area_pa; + unsigned long logout_area_len; + unsigned long halt_PCBB; + unsigned long halt_PC; + unsigned long halt_PS; + unsigned long halt_arg; + unsigned long halt_ra; + unsigned long halt_pv; + unsigned long halt_reason; + unsigned long res; + unsigned long ipc_buffer[21]; + unsigned long palcode_avail[16]; + unsigned long compatibility; + unsigned long console_data_log_pa; + unsigned long console_data_log_length; + unsigned long bcache_info; +}; + +struct procdesc_struct { + unsigned long weird_vms_stuff; + unsigned long address; +}; + +struct vf_map_struct { + unsigned long va; + unsigned long pa; + unsigned long count; +}; + +struct crb_struct { + struct procdesc_struct * dispatch_va; + struct procdesc_struct * dispatch_pa; + struct procdesc_struct * fixup_va; + struct procdesc_struct * fixup_pa; + /* virtual->physical map */ + unsigned long map_entries; + unsigned long map_pages; + struct vf_map_struct map[1]; +}; + +struct memclust_struct { + unsigned long start_pfn; + unsigned long numpages; + unsigned long numtested; + unsigned long bitmap_va; + unsigned long bitmap_pa; + unsigned long bitmap_chksum; + unsigned long usage; +}; + +struct memdesc_struct { + unsigned long chksum; + unsigned long optional_pa; + unsigned long numclusters; + struct memclust_struct cluster[0]; +}; + +struct dsr_struct { + long smm; /* SMM nubber used by LMF */ + unsigned long lurt_off; /* offset to LURT table */ + unsigned long sysname_off; /* offset to sysname char count */ +}; + +struct hwrpb_struct { + unsigned long phys_addr; /* check: physical address of the hwrpb */ + unsigned long id; /* check: "HWRPB\0\0\0" */ + unsigned long revision; + unsigned long size; /* size of hwrpb */ + unsigned long cpuid; + unsigned long pagesize; /* 8192, I hope */ + unsigned long pa_bits; /* number of physical address bits */ + unsigned long max_asn; + unsigned char ssn[16]; /* system serial number: big bother is watching */ + unsigned long sys_type; + unsigned long sys_variation; + unsigned long sys_revision; + unsigned long intr_freq; /* interval clock frequency * 4096 */ + unsigned long cycle_freq; /* cycle counter frequency */ + unsigned long vptb; /* Virtual Page Table Base address */ + unsigned long res1; + unsigned long tbhb_offset; /* Translation Buffer Hint Block */ + unsigned long nr_processors; + unsigned long processor_size; + unsigned long processor_offset; + unsigned long ctb_nr; + unsigned long ctb_size; /* console terminal block size */ + unsigned long ctbt_offset; /* console terminal block table offset */ + unsigned long crb_offset; /* console callback routine block */ + unsigned long mddt_offset; /* memory data descriptor table */ + unsigned long cdb_offset; /* configuration data block (or NULL) */ + unsigned long frut_offset; /* FRU table (or NULL) */ + void (*save_terminal)(unsigned long); + unsigned long save_terminal_data; + void (*restore_terminal)(unsigned long); + unsigned long restore_terminal_data; + void (*CPU_restart)(unsigned long); + unsigned long CPU_restart_data; + unsigned long res2; + unsigned long res3; + unsigned long chksum; + unsigned long rxrdy; + unsigned long txrdy; + unsigned long dsr_offset; /* "Dynamic System Recognition Data Block Table" */ +}; + +#ifdef __KERNEL__ + +extern struct hwrpb_struct *hwrpb; + +static inline void +hwrpb_update_checksum(struct hwrpb_struct *h) +{ + unsigned long sum = 0, *l; + for (l = (unsigned long *) h; l < (unsigned long *) &h->chksum; ++l) + sum += *l; + h->chksum = sum; +} + +#endif /* __KERNEL__ */ + +#endif /* __ALPHA_HWRPB_H */ diff --git a/arch/alpha/include/asm/io.h b/arch/alpha/include/asm/io.h new file mode 100644 index 000000000..f05bdb4b1 --- /dev/null +++ b/arch/alpha/include/asm/io.h @@ -0,0 +1,584 @@ +#ifndef __ALPHA_IO_H +#define __ALPHA_IO_H + +#ifdef __KERNEL__ + +#include <linux/kernel.h> +#include <linux/mm.h> +#include <asm/compiler.h> +#include <asm/pgtable.h> +#include <asm/machvec.h> +#include <asm/hwrpb.h> + +/* The generic header contains only prototypes. Including it ensures that + the implementation we have here matches that interface. */ +#include <asm-generic/iomap.h> + +/* We don't use IO slowdowns on the Alpha, but.. */ +#define __SLOW_DOWN_IO do { } while (0) +#define SLOW_DOWN_IO do { } while (0) + +/* + * Virtual -> physical identity mapping starts at this offset + */ +#ifdef USE_48_BIT_KSEG +#define IDENT_ADDR 0xffff800000000000UL +#else +#define IDENT_ADDR 0xfffffc0000000000UL +#endif + +/* + * We try to avoid hae updates (thus the cache), but when we + * do need to update the hae, we need to do it atomically, so + * that any interrupts wouldn't get confused with the hae + * register not being up-to-date with respect to the hardware + * value. + */ +extern inline void __set_hae(unsigned long new_hae) +{ + unsigned long flags = swpipl(IPL_MAX); + + barrier(); + + alpha_mv.hae_cache = new_hae; + *alpha_mv.hae_register = new_hae; + mb(); + /* Re-read to make sure it was written. */ + new_hae = *alpha_mv.hae_register; + + setipl(flags); + barrier(); +} + +extern inline void set_hae(unsigned long new_hae) +{ + if (new_hae != alpha_mv.hae_cache) + __set_hae(new_hae); +} + +/* + * Change virtual addresses to physical addresses and vv. + */ +#ifdef USE_48_BIT_KSEG +static inline unsigned long virt_to_phys(void *address) +{ + return (unsigned long)address - IDENT_ADDR; +} + +static inline void * phys_to_virt(unsigned long address) +{ + return (void *) (address + IDENT_ADDR); +} +#else +static inline unsigned long virt_to_phys(void *address) +{ + unsigned long phys = (unsigned long)address; + + /* Sign-extend from bit 41. */ + phys <<= (64 - 41); + phys = (long)phys >> (64 - 41); + + /* Crop to the physical address width of the processor. */ + phys &= (1ul << hwrpb->pa_bits) - 1; + + return phys; +} + +static inline void * phys_to_virt(unsigned long address) +{ + return (void *)(IDENT_ADDR + (address & ((1ul << 41) - 1))); +} +#endif + +#define page_to_phys(page) page_to_pa(page) + +static inline dma_addr_t __deprecated isa_page_to_bus(struct page *page) +{ + return page_to_phys(page); +} + +/* Maximum PIO space address supported? */ +#define IO_SPACE_LIMIT 0xffff + +/* + * Change addresses as seen by the kernel (virtual) to addresses as + * seen by a device (bus), and vice versa. + * + * Note that this only works for a limited range of kernel addresses, + * and very well may not span all memory. Consider this interface + * deprecated in favour of the DMA-mapping API. + */ +extern unsigned long __direct_map_base; +extern unsigned long __direct_map_size; + +static inline unsigned long __deprecated virt_to_bus(void *address) +{ + unsigned long phys = virt_to_phys(address); + unsigned long bus = phys + __direct_map_base; + return phys <= __direct_map_size ? bus : 0; +} +#define isa_virt_to_bus virt_to_bus + +static inline void * __deprecated bus_to_virt(unsigned long address) +{ + void *virt; + + /* This check is a sanity check but also ensures that bus address 0 + maps to virtual address 0 which is useful to detect null pointers + (the NCR driver is much simpler if NULL pointers are preserved). */ + address -= __direct_map_base; + virt = phys_to_virt(address); + return (long)address <= 0 ? NULL : virt; +} +#define isa_bus_to_virt bus_to_virt + +/* + * There are different chipsets to interface the Alpha CPUs to the world. + */ + +#define IO_CONCAT(a,b) _IO_CONCAT(a,b) +#define _IO_CONCAT(a,b) a ## _ ## b + +#ifdef CONFIG_ALPHA_GENERIC + +/* In a generic kernel, we always go through the machine vector. */ + +#define REMAP1(TYPE, NAME, QUAL) \ +static inline TYPE generic_##NAME(QUAL void __iomem *addr) \ +{ \ + return alpha_mv.mv_##NAME(addr); \ +} + +#define REMAP2(TYPE, NAME, QUAL) \ +static inline void generic_##NAME(TYPE b, QUAL void __iomem *addr) \ +{ \ + alpha_mv.mv_##NAME(b, addr); \ +} + +REMAP1(unsigned int, ioread8, /**/) +REMAP1(unsigned int, ioread16, /**/) +REMAP1(unsigned int, ioread32, /**/) +REMAP1(u8, readb, const volatile) +REMAP1(u16, readw, const volatile) +REMAP1(u32, readl, const volatile) +REMAP1(u64, readq, const volatile) + +REMAP2(u8, iowrite8, /**/) +REMAP2(u16, iowrite16, /**/) +REMAP2(u32, iowrite32, /**/) +REMAP2(u8, writeb, volatile) +REMAP2(u16, writew, volatile) +REMAP2(u32, writel, volatile) +REMAP2(u64, writeq, volatile) + +#undef REMAP1 +#undef REMAP2 + +extern inline void __iomem *generic_ioportmap(unsigned long a) +{ + return alpha_mv.mv_ioportmap(a); +} + +static inline void __iomem *generic_ioremap(unsigned long a, unsigned long s) +{ + return alpha_mv.mv_ioremap(a, s); +} + +static inline void generic_iounmap(volatile void __iomem *a) +{ + return alpha_mv.mv_iounmap(a); +} + +static inline int generic_is_ioaddr(unsigned long a) +{ + return alpha_mv.mv_is_ioaddr(a); +} + +static inline int generic_is_mmio(const volatile void __iomem *a) +{ + return alpha_mv.mv_is_mmio(a); +} + +#define __IO_PREFIX generic +#define generic_trivial_rw_bw 0 +#define generic_trivial_rw_lq 0 +#define generic_trivial_io_bw 0 +#define generic_trivial_io_lq 0 +#define generic_trivial_iounmap 0 + +#else + +#if defined(CONFIG_ALPHA_APECS) +# include <asm/core_apecs.h> +#elif defined(CONFIG_ALPHA_CIA) +# include <asm/core_cia.h> +#elif defined(CONFIG_ALPHA_IRONGATE) +# include <asm/core_irongate.h> +#elif defined(CONFIG_ALPHA_JENSEN) +# include <asm/jensen.h> +#elif defined(CONFIG_ALPHA_LCA) +# include <asm/core_lca.h> +#elif defined(CONFIG_ALPHA_MARVEL) +# include <asm/core_marvel.h> +#elif defined(CONFIG_ALPHA_MCPCIA) +# include <asm/core_mcpcia.h> +#elif defined(CONFIG_ALPHA_POLARIS) +# include <asm/core_polaris.h> +#elif defined(CONFIG_ALPHA_T2) +# include <asm/core_t2.h> +#elif defined(CONFIG_ALPHA_TSUNAMI) +# include <asm/core_tsunami.h> +#elif defined(CONFIG_ALPHA_TITAN) +# include <asm/core_titan.h> +#elif defined(CONFIG_ALPHA_WILDFIRE) +# include <asm/core_wildfire.h> +#else +#error "What system is this?" +#endif + +#endif /* GENERIC */ + +/* + * We always have external versions of these routines. + */ +extern u8 inb(unsigned long port); +extern u16 inw(unsigned long port); +extern u32 inl(unsigned long port); +extern void outb(u8 b, unsigned long port); +extern void outw(u16 b, unsigned long port); +extern void outl(u32 b, unsigned long port); + +extern u8 readb(const volatile void __iomem *addr); +extern u16 readw(const volatile void __iomem *addr); +extern u32 readl(const volatile void __iomem *addr); +extern u64 readq(const volatile void __iomem *addr); +extern void writeb(u8 b, volatile void __iomem *addr); +extern void writew(u16 b, volatile void __iomem *addr); +extern void writel(u32 b, volatile void __iomem *addr); +extern void writeq(u64 b, volatile void __iomem *addr); + +extern u8 __raw_readb(const volatile void __iomem *addr); +extern u16 __raw_readw(const volatile void __iomem *addr); +extern u32 __raw_readl(const volatile void __iomem *addr); +extern u64 __raw_readq(const volatile void __iomem *addr); +extern void __raw_writeb(u8 b, volatile void __iomem *addr); +extern void __raw_writew(u16 b, volatile void __iomem *addr); +extern void __raw_writel(u32 b, volatile void __iomem *addr); +extern void __raw_writeq(u64 b, volatile void __iomem *addr); + +/* + * Mapping from port numbers to __iomem space is pretty easy. + */ + +/* These two have to be extern inline because of the extern prototype from + <asm-generic/iomap.h>. It is not legal to mix "extern" and "static" for + the same declaration. */ +extern inline void __iomem *ioport_map(unsigned long port, unsigned int size) +{ + return IO_CONCAT(__IO_PREFIX,ioportmap) (port); +} + +extern inline void ioport_unmap(void __iomem *addr) +{ +} + +static inline void __iomem *ioremap(unsigned long port, unsigned long size) +{ + return IO_CONCAT(__IO_PREFIX,ioremap) (port, size); +} + +static inline void __iomem *__ioremap(unsigned long port, unsigned long size, + unsigned long flags) +{ + return ioremap(port, size); +} + +static inline void __iomem * ioremap_nocache(unsigned long offset, + unsigned long size) +{ + return ioremap(offset, size); +} + +static inline void iounmap(volatile void __iomem *addr) +{ + IO_CONCAT(__IO_PREFIX,iounmap)(addr); +} + +static inline int __is_ioaddr(unsigned long addr) +{ + return IO_CONCAT(__IO_PREFIX,is_ioaddr)(addr); +} +#define __is_ioaddr(a) __is_ioaddr((unsigned long)(a)) + +static inline int __is_mmio(const volatile void __iomem *addr) +{ + return IO_CONCAT(__IO_PREFIX,is_mmio)(addr); +} + + +/* + * If the actual I/O bits are sufficiently trivial, then expand inline. + */ + +#if IO_CONCAT(__IO_PREFIX,trivial_io_bw) +extern inline unsigned int ioread8(void __iomem *addr) +{ + unsigned int ret = IO_CONCAT(__IO_PREFIX,ioread8)(addr); + mb(); + return ret; +} + +extern inline unsigned int ioread16(void __iomem *addr) +{ + unsigned int ret = IO_CONCAT(__IO_PREFIX,ioread16)(addr); + mb(); + return ret; +} + +extern inline void iowrite8(u8 b, void __iomem *addr) +{ + IO_CONCAT(__IO_PREFIX,iowrite8)(b, addr); + mb(); +} + +extern inline void iowrite16(u16 b, void __iomem *addr) +{ + IO_CONCAT(__IO_PREFIX,iowrite16)(b, addr); + mb(); +} + +extern inline u8 inb(unsigned long port) +{ + return ioread8(ioport_map(port, 1)); +} + +extern inline u16 inw(unsigned long port) +{ + return ioread16(ioport_map(port, 2)); +} + +extern inline void outb(u8 b, unsigned long port) +{ + iowrite8(b, ioport_map(port, 1)); +} + +extern inline void outw(u16 b, unsigned long port) +{ + iowrite16(b, ioport_map(port, 2)); +} +#endif + +#if IO_CONCAT(__IO_PREFIX,trivial_io_lq) +extern inline unsigned int ioread32(void __iomem *addr) +{ + unsigned int ret = IO_CONCAT(__IO_PREFIX,ioread32)(addr); + mb(); + return ret; +} + +extern inline void iowrite32(u32 b, void __iomem *addr) +{ + IO_CONCAT(__IO_PREFIX,iowrite32)(b, addr); + mb(); +} + +extern inline u32 inl(unsigned long port) +{ + return ioread32(ioport_map(port, 4)); +} + +extern inline void outl(u32 b, unsigned long port) +{ + iowrite32(b, ioport_map(port, 4)); +} +#endif + +#if IO_CONCAT(__IO_PREFIX,trivial_rw_bw) == 1 +extern inline u8 __raw_readb(const volatile void __iomem *addr) +{ + return IO_CONCAT(__IO_PREFIX,readb)(addr); +} + +extern inline u16 __raw_readw(const volatile void __iomem *addr) +{ + return IO_CONCAT(__IO_PREFIX,readw)(addr); +} + +extern inline void __raw_writeb(u8 b, volatile void __iomem *addr) +{ + IO_CONCAT(__IO_PREFIX,writeb)(b, addr); +} + +extern inline void __raw_writew(u16 b, volatile void __iomem *addr) +{ + IO_CONCAT(__IO_PREFIX,writew)(b, addr); +} + +extern inline u8 readb(const volatile void __iomem *addr) +{ + u8 ret = __raw_readb(addr); + mb(); + return ret; +} + +extern inline u16 readw(const volatile void __iomem *addr) +{ + u16 ret = __raw_readw(addr); + mb(); + return ret; +} + +extern inline void writeb(u8 b, volatile void __iomem *addr) +{ + __raw_writeb(b, addr); + mb(); +} + +extern inline void writew(u16 b, volatile void __iomem *addr) +{ + __raw_writew(b, addr); + mb(); +} +#endif + +#if IO_CONCAT(__IO_PREFIX,trivial_rw_lq) == 1 +extern inline u32 __raw_readl(const volatile void __iomem *addr) +{ + return IO_CONCAT(__IO_PREFIX,readl)(addr); +} + +extern inline u64 __raw_readq(const volatile void __iomem *addr) +{ + return IO_CONCAT(__IO_PREFIX,readq)(addr); +} + +extern inline void __raw_writel(u32 b, volatile void __iomem *addr) +{ + IO_CONCAT(__IO_PREFIX,writel)(b, addr); +} + +extern inline void __raw_writeq(u64 b, volatile void __iomem *addr) +{ + IO_CONCAT(__IO_PREFIX,writeq)(b, addr); +} + +extern inline u32 readl(const volatile void __iomem *addr) +{ + u32 ret = __raw_readl(addr); + mb(); + return ret; +} + +extern inline u64 readq(const volatile void __iomem *addr) +{ + u64 ret = __raw_readq(addr); + mb(); + return ret; +} + +extern inline void writel(u32 b, volatile void __iomem *addr) +{ + __raw_writel(b, addr); + mb(); +} + +extern inline void writeq(u64 b, volatile void __iomem *addr) +{ + __raw_writeq(b, addr); + mb(); +} +#endif + +#define ioread16be(p) be16_to_cpu(ioread16(p)) +#define ioread32be(p) be32_to_cpu(ioread32(p)) +#define iowrite16be(v,p) iowrite16(cpu_to_be16(v), (p)) +#define iowrite32be(v,p) iowrite32(cpu_to_be32(v), (p)) + +#define inb_p inb +#define inw_p inw +#define inl_p inl +#define outb_p outb +#define outw_p outw +#define outl_p outl +#define readb_relaxed(addr) __raw_readb(addr) +#define readw_relaxed(addr) __raw_readw(addr) +#define readl_relaxed(addr) __raw_readl(addr) +#define readq_relaxed(addr) __raw_readq(addr) +#define writeb_relaxed(b, addr) __raw_writeb(b, addr) +#define writew_relaxed(b, addr) __raw_writew(b, addr) +#define writel_relaxed(b, addr) __raw_writel(b, addr) +#define writeq_relaxed(b, addr) __raw_writeq(b, addr) + +#define mmiowb() + +/* + * String version of IO memory access ops: + */ +extern void memcpy_fromio(void *, const volatile void __iomem *, long); +extern void memcpy_toio(volatile void __iomem *, const void *, long); +extern void _memset_c_io(volatile void __iomem *, unsigned long, long); + +static inline void memset_io(volatile void __iomem *addr, u8 c, long len) +{ + _memset_c_io(addr, 0x0101010101010101UL * c, len); +} + +#define __HAVE_ARCH_MEMSETW_IO +static inline void memsetw_io(volatile void __iomem *addr, u16 c, long len) +{ + _memset_c_io(addr, 0x0001000100010001UL * c, len); +} + +/* + * String versions of in/out ops: + */ +extern void insb (unsigned long port, void *dst, unsigned long count); +extern void insw (unsigned long port, void *dst, unsigned long count); +extern void insl (unsigned long port, void *dst, unsigned long count); +extern void outsb (unsigned long port, const void *src, unsigned long count); +extern void outsw (unsigned long port, const void *src, unsigned long count); +extern void outsl (unsigned long port, const void *src, unsigned long count); + +/* + * The Alpha Jensen hardware for some rather strange reason puts + * the RTC clock at 0x170 instead of 0x70. Probably due to some + * misguided idea about using 0x70 for NMI stuff. + * + * These defines will override the defaults when doing RTC queries + */ + +#ifdef CONFIG_ALPHA_GENERIC +# define RTC_PORT(x) ((x) + alpha_mv.rtc_port) +#else +# ifdef CONFIG_ALPHA_JENSEN +# define RTC_PORT(x) (0x170+(x)) +# else +# define RTC_PORT(x) (0x70 + (x)) +# endif +#endif +#define RTC_ALWAYS_BCD 0 + +/* + * Some mucking forons use if[n]def writeq to check if platform has it. + * It's a bloody bad idea and we probably want ARCH_HAS_WRITEQ for them + * to play with; for now just use cpp anti-recursion logics and make sure + * that damn thing is defined and expands to itself. + */ + +#define writeq writeq +#define readq readq + +/* + * 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 + +#endif /* __KERNEL__ */ + +#endif /* __ALPHA_IO_H */ diff --git a/arch/alpha/include/asm/io_trivial.h b/arch/alpha/include/asm/io_trivial.h new file mode 100644 index 000000000..1c77f10b4 --- /dev/null +++ b/arch/alpha/include/asm/io_trivial.h @@ -0,0 +1,131 @@ +/* Trivial implementations of basic i/o routines. Assumes that all + of the hard work has been done by ioremap and ioportmap, and that + access to i/o space is linear. */ + +/* This file may be included multiple times. */ + +#if IO_CONCAT(__IO_PREFIX,trivial_io_bw) +__EXTERN_INLINE unsigned int +IO_CONCAT(__IO_PREFIX,ioread8)(void __iomem *a) +{ + return __kernel_ldbu(*(volatile u8 __force *)a); +} + +__EXTERN_INLINE unsigned int +IO_CONCAT(__IO_PREFIX,ioread16)(void __iomem *a) +{ + return __kernel_ldwu(*(volatile u16 __force *)a); +} + +__EXTERN_INLINE void +IO_CONCAT(__IO_PREFIX,iowrite8)(u8 b, void __iomem *a) +{ + __kernel_stb(b, *(volatile u8 __force *)a); +} + +__EXTERN_INLINE void +IO_CONCAT(__IO_PREFIX,iowrite16)(u16 b, void __iomem *a) +{ + __kernel_stw(b, *(volatile u16 __force *)a); +} +#endif + +#if IO_CONCAT(__IO_PREFIX,trivial_io_lq) +__EXTERN_INLINE unsigned int +IO_CONCAT(__IO_PREFIX,ioread32)(void __iomem *a) +{ + return *(volatile u32 __force *)a; +} + +__EXTERN_INLINE void +IO_CONCAT(__IO_PREFIX,iowrite32)(u32 b, void __iomem *a) +{ + *(volatile u32 __force *)a = b; +} +#endif + +#if IO_CONCAT(__IO_PREFIX,trivial_rw_bw) == 1 +__EXTERN_INLINE u8 +IO_CONCAT(__IO_PREFIX,readb)(const volatile void __iomem *a) +{ + return __kernel_ldbu(*(const volatile u8 __force *)a); +} + +__EXTERN_INLINE u16 +IO_CONCAT(__IO_PREFIX,readw)(const volatile void __iomem *a) +{ + return __kernel_ldwu(*(const volatile u16 __force *)a); +} + +__EXTERN_INLINE void +IO_CONCAT(__IO_PREFIX,writeb)(u8 b, volatile void __iomem *a) +{ + __kernel_stb(b, *(volatile u8 __force *)a); +} + +__EXTERN_INLINE void +IO_CONCAT(__IO_PREFIX,writew)(u16 b, volatile void __iomem *a) +{ + __kernel_stw(b, *(volatile u16 __force *)a); +} +#elif IO_CONCAT(__IO_PREFIX,trivial_rw_bw) == 2 +__EXTERN_INLINE u8 +IO_CONCAT(__IO_PREFIX,readb)(const volatile void __iomem *a) +{ + void __iomem *addr = (void __iomem *)a; + return IO_CONCAT(__IO_PREFIX,ioread8)(addr); +} + +__EXTERN_INLINE u16 +IO_CONCAT(__IO_PREFIX,readw)(const volatile void __iomem *a) +{ + void __iomem *addr = (void __iomem *)a; + return IO_CONCAT(__IO_PREFIX,ioread16)(addr); +} + +__EXTERN_INLINE void +IO_CONCAT(__IO_PREFIX,writeb)(u8 b, volatile void __iomem *a) +{ + void __iomem *addr = (void __iomem *)a; + IO_CONCAT(__IO_PREFIX,iowrite8)(b, addr); +} + +__EXTERN_INLINE void +IO_CONCAT(__IO_PREFIX,writew)(u16 b, volatile void __iomem *a) +{ + void __iomem *addr = (void __iomem *)a; + IO_CONCAT(__IO_PREFIX,iowrite16)(b, addr); +} +#endif + +#if IO_CONCAT(__IO_PREFIX,trivial_rw_lq) == 1 +__EXTERN_INLINE u32 +IO_CONCAT(__IO_PREFIX,readl)(const volatile void __iomem *a) +{ + return *(const volatile u32 __force *)a; +} + +__EXTERN_INLINE u64 +IO_CONCAT(__IO_PREFIX,readq)(const volatile void __iomem *a) +{ + return *(const volatile u64 __force *)a; +} + +__EXTERN_INLINE void +IO_CONCAT(__IO_PREFIX,writel)(u32 b, volatile void __iomem *a) +{ + *(volatile u32 __force *)a = b; +} + +__EXTERN_INLINE void +IO_CONCAT(__IO_PREFIX,writeq)(u64 b, volatile void __iomem *a) +{ + *(volatile u64 __force *)a = b; +} +#endif + +#if IO_CONCAT(__IO_PREFIX,trivial_iounmap) +__EXTERN_INLINE void IO_CONCAT(__IO_PREFIX,iounmap)(volatile void __iomem *a) +{ +} +#endif diff --git a/arch/alpha/include/asm/irq.h b/arch/alpha/include/asm/irq.h new file mode 100644 index 000000000..06377400d --- /dev/null +++ b/arch/alpha/include/asm/irq.h @@ -0,0 +1,91 @@ +#ifndef _ALPHA_IRQ_H +#define _ALPHA_IRQ_H + +/* + * linux/include/alpha/irq.h + * + * (C) 1994 Linus Torvalds + */ + +#include <linux/linkage.h> + +#if defined(CONFIG_ALPHA_GENERIC) + +/* Here NR_IRQS is not exact, but rather an upper bound. This is used + many places throughout the kernel to size static arrays. That's ok, + we'll use alpha_mv.nr_irqs when we want the real thing. */ + +/* When LEGACY_START_ADDRESS is selected, we leave out: + TITAN + WILDFIRE + MARVEL + + This helps keep the kernel object size reasonable for the majority + of machines. +*/ + +# if defined(CONFIG_ALPHA_LEGACY_START_ADDRESS) +# define NR_IRQS (128) /* max is RAWHIDE/TAKARA */ +# else +# define NR_IRQS (32768 + 16) /* marvel - 32 pids */ +# endif + +#elif defined(CONFIG_ALPHA_CABRIOLET) || \ + defined(CONFIG_ALPHA_EB66P) || \ + defined(CONFIG_ALPHA_EB164) || \ + defined(CONFIG_ALPHA_PC164) || \ + defined(CONFIG_ALPHA_LX164) +# define NR_IRQS 35 + +#elif defined(CONFIG_ALPHA_EB66) || \ + defined(CONFIG_ALPHA_EB64P) || \ + defined(CONFIG_ALPHA_MIKASA) +# define NR_IRQS 32 + +#elif defined(CONFIG_ALPHA_ALCOR) || \ + defined(CONFIG_ALPHA_MIATA) || \ + defined(CONFIG_ALPHA_RUFFIAN) || \ + defined(CONFIG_ALPHA_RX164) || \ + defined(CONFIG_ALPHA_NORITAKE) +# define NR_IRQS 48 + +#elif defined(CONFIG_ALPHA_SABLE) || \ + defined(CONFIG_ALPHA_SX164) +# define NR_IRQS 40 + +#elif defined(CONFIG_ALPHA_DP264) || \ + defined(CONFIG_ALPHA_LYNX) || \ + defined(CONFIG_ALPHA_SHARK) || \ + defined(CONFIG_ALPHA_EIGER) +# define NR_IRQS 64 + +#elif defined(CONFIG_ALPHA_TITAN) +#define NR_IRQS 80 + +#elif defined(CONFIG_ALPHA_RAWHIDE) || \ + defined(CONFIG_ALPHA_TAKARA) +# define NR_IRQS 128 + +#elif defined(CONFIG_ALPHA_WILDFIRE) +# define NR_IRQS 2048 /* enuff for 8 QBBs */ + +#elif defined(CONFIG_ALPHA_MARVEL) +# define NR_IRQS (32768 + 16) /* marvel - 32 pids*/ + +#else /* everyone else */ +# define NR_IRQS 16 +#endif + +static __inline__ int irq_canonicalize(int irq) +{ + /* + * XXX is this true for all Alpha's? The old serial driver + * did it this way for years without any complaints, so.... + */ + return ((irq == 2) ? 9 : irq); +} + +struct pt_regs; +extern void (*perf_irq)(unsigned long, struct pt_regs *); + +#endif /* _ALPHA_IRQ_H */ diff --git a/arch/alpha/include/asm/irq_regs.h b/arch/alpha/include/asm/irq_regs.h new file mode 100644 index 000000000..3dd9c0b70 --- /dev/null +++ b/arch/alpha/include/asm/irq_regs.h @@ -0,0 +1 @@ +#include <asm-generic/irq_regs.h> diff --git a/arch/alpha/include/asm/irqflags.h b/arch/alpha/include/asm/irqflags.h new file mode 100644 index 000000000..ffb172648 --- /dev/null +++ b/arch/alpha/include/asm/irqflags.h @@ -0,0 +1,67 @@ +#ifndef __ALPHA_IRQFLAGS_H +#define __ALPHA_IRQFLAGS_H + +#include <asm/pal.h> + +#define IPL_MIN 0 +#define IPL_SW0 1 +#define IPL_SW1 2 +#define IPL_DEV0 3 +#define IPL_DEV1 4 +#define IPL_TIMER 5 +#define IPL_PERF 6 +#define IPL_POWERFAIL 6 +#define IPL_MCHECK 7 +#define IPL_MAX 7 + +#ifdef CONFIG_ALPHA_BROKEN_IRQ_MASK +#undef IPL_MIN +#define IPL_MIN __min_ipl +extern int __min_ipl; +#endif + +#define getipl() (rdps() & 7) +#define setipl(ipl) ((void) swpipl(ipl)) + +static inline unsigned long arch_local_save_flags(void) +{ + return rdps(); +} + +static inline void arch_local_irq_disable(void) +{ + setipl(IPL_MAX); + barrier(); +} + +static inline unsigned long arch_local_irq_save(void) +{ + unsigned long flags = swpipl(IPL_MAX); + barrier(); + return flags; +} + +static inline void arch_local_irq_enable(void) +{ + barrier(); + setipl(IPL_MIN); +} + +static inline void arch_local_irq_restore(unsigned long flags) +{ + barrier(); + setipl(flags); + barrier(); +} + +static inline bool arch_irqs_disabled_flags(unsigned long flags) +{ + return flags == IPL_MAX; +} + +static inline bool arch_irqs_disabled(void) +{ + return arch_irqs_disabled_flags(getipl()); +} + +#endif /* __ALPHA_IRQFLAGS_H */ diff --git a/arch/alpha/include/asm/jensen.h b/arch/alpha/include/asm/jensen.h new file mode 100644 index 000000000..964b06ead --- /dev/null +++ b/arch/alpha/include/asm/jensen.h @@ -0,0 +1,346 @@ +#ifndef __ALPHA_JENSEN_H +#define __ALPHA_JENSEN_H + +#include <asm/compiler.h> + +/* + * Defines for the AlphaPC EISA IO and memory address space. + */ + +/* + * NOTE! The memory operations do not set any memory barriers, as it's + * not needed for cases like a frame buffer that is essentially memory-like. + * You need to do them by hand if the operations depend on ordering. + * + * Similarly, the port IO operations do a "mb" only after a write operation: + * if an mb is needed before (as in the case of doing memory mapped IO + * first, and then a port IO operation to the same device), it needs to be + * done by hand. + * + * After the above has bitten me 100 times, I'll give up and just do the + * mb all the time, but right now I'm hoping this will work out. Avoiding + * mb's may potentially be a noticeable speed improvement, but I can't + * honestly say I've tested it. + * + * Handling interrupts that need to do mb's to synchronize to non-interrupts + * is another fun race area. Don't do it (because if you do, I'll have to + * do *everything* with interrupts disabled, ugh). + */ + +/* + * EISA Interrupt Acknowledge address + */ +#define EISA_INTA (IDENT_ADDR + 0x100000000UL) + +/* + * FEPROM addresses + */ +#define EISA_FEPROM0 (IDENT_ADDR + 0x180000000UL) +#define EISA_FEPROM1 (IDENT_ADDR + 0x1A0000000UL) + +/* + * VL82C106 base address + */ +#define EISA_VL82C106 (IDENT_ADDR + 0x1C0000000UL) + +/* + * EISA "Host Address Extension" address (bits 25-31 of the EISA address) + */ +#define EISA_HAE (IDENT_ADDR + 0x1D0000000UL) + +/* + * "SYSCTL" register address + */ +#define EISA_SYSCTL (IDENT_ADDR + 0x1E0000000UL) + +/* + * "spare" register address + */ +#define EISA_SPARE (IDENT_ADDR + 0x1F0000000UL) + +/* + * EISA memory address offset + */ +#define EISA_MEM (IDENT_ADDR + 0x200000000UL) + +/* + * EISA IO address offset + */ +#define EISA_IO (IDENT_ADDR + 0x300000000UL) + + +#ifdef __KERNEL__ + +#ifndef __EXTERN_INLINE +#define __EXTERN_INLINE extern inline +#define __IO_EXTERN_INLINE +#endif + +/* + * Handle the "host address register". This needs to be set + * to the high 7 bits of the EISA address. This is also needed + * for EISA IO addresses, which are only 16 bits wide (the + * hae needs to be set to 0). + * + * HAE isn't needed for the local IO operations, though. + */ + +#define JENSEN_HAE_ADDRESS EISA_HAE +#define JENSEN_HAE_MASK 0x1ffffff + +__EXTERN_INLINE void jensen_set_hae(unsigned long addr) +{ + /* hae on the Jensen is bits 31:25 shifted right */ + addr >>= 25; + if (addr != alpha_mv.hae_cache) + set_hae(addr); +} + +#define vuip volatile unsigned int * + +/* + * IO functions + * + * The "local" functions are those that don't go out to the EISA bus, + * but instead act on the VL82C106 chip directly.. This is mainly the + * keyboard, RTC, printer and first two serial lines.. + * + * The local stuff makes for some complications, but it seems to be + * gone in the PCI version. I hope I can get DEC suckered^H^H^H^H^H^H^H^H + * convinced that I need one of the newer machines. + */ + +static inline unsigned int jensen_local_inb(unsigned long addr) +{ + return 0xff & *(vuip)((addr << 9) + EISA_VL82C106); +} + +static inline void jensen_local_outb(u8 b, unsigned long addr) +{ + *(vuip)((addr << 9) + EISA_VL82C106) = b; + mb(); +} + +static inline unsigned int jensen_bus_inb(unsigned long addr) +{ + long result; + + jensen_set_hae(0); + result = *(volatile int *)((addr << 7) + EISA_IO + 0x00); + return __kernel_extbl(result, addr & 3); +} + +static inline void jensen_bus_outb(u8 b, unsigned long addr) +{ + jensen_set_hae(0); + *(vuip)((addr << 7) + EISA_IO + 0x00) = b * 0x01010101; + mb(); +} + +/* + * It seems gcc is not very good at optimizing away logical + * operations that result in operations across inline functions. + * Which is why this is a macro. + */ + +#define jensen_is_local(addr) ( \ +/* keyboard */ (addr == 0x60 || addr == 0x64) || \ +/* RTC */ (addr == 0x170 || addr == 0x171) || \ +/* mb COM2 */ (addr >= 0x2f8 && addr <= 0x2ff) || \ +/* mb LPT1 */ (addr >= 0x3bc && addr <= 0x3be) || \ +/* mb COM2 */ (addr >= 0x3f8 && addr <= 0x3ff)) + +__EXTERN_INLINE u8 jensen_inb(unsigned long addr) +{ + if (jensen_is_local(addr)) + return jensen_local_inb(addr); + else + return jensen_bus_inb(addr); +} + +__EXTERN_INLINE void jensen_outb(u8 b, unsigned long addr) +{ + if (jensen_is_local(addr)) + jensen_local_outb(b, addr); + else + jensen_bus_outb(b, addr); +} + +__EXTERN_INLINE u16 jensen_inw(unsigned long addr) +{ + long result; + + jensen_set_hae(0); + result = *(volatile int *) ((addr << 7) + EISA_IO + 0x20); + result >>= (addr & 3) * 8; + return 0xffffUL & result; +} + +__EXTERN_INLINE u32 jensen_inl(unsigned long addr) +{ + jensen_set_hae(0); + return *(vuip) ((addr << 7) + EISA_IO + 0x60); +} + +__EXTERN_INLINE void jensen_outw(u16 b, unsigned long addr) +{ + jensen_set_hae(0); + *(vuip) ((addr << 7) + EISA_IO + 0x20) = b * 0x00010001; + mb(); +} + +__EXTERN_INLINE void jensen_outl(u32 b, unsigned long addr) +{ + jensen_set_hae(0); + *(vuip) ((addr << 7) + EISA_IO + 0x60) = b; + mb(); +} + +/* + * Memory functions. + */ + +__EXTERN_INLINE u8 jensen_readb(const volatile void __iomem *xaddr) +{ + unsigned long addr = (unsigned long) xaddr; + long result; + + jensen_set_hae(addr); + addr &= JENSEN_HAE_MASK; + result = *(volatile int *) ((addr << 7) + EISA_MEM + 0x00); + result >>= (addr & 3) * 8; + return 0xffUL & result; +} + +__EXTERN_INLINE u16 jensen_readw(const volatile void __iomem *xaddr) +{ + unsigned long addr = (unsigned long) xaddr; + long result; + + jensen_set_hae(addr); + addr &= JENSEN_HAE_MASK; + result = *(volatile int *) ((addr << 7) + EISA_MEM + 0x20); + result >>= (addr & 3) * 8; + return 0xffffUL & result; +} + +__EXTERN_INLINE u32 jensen_readl(const volatile void __iomem *xaddr) +{ + unsigned long addr = (unsigned long) xaddr; + jensen_set_hae(addr); + addr &= JENSEN_HAE_MASK; + return *(vuip) ((addr << 7) + EISA_MEM + 0x60); +} + +__EXTERN_INLINE u64 jensen_readq(const volatile void __iomem *xaddr) +{ + unsigned long addr = (unsigned long) xaddr; + unsigned long r0, r1; + + jensen_set_hae(addr); + addr &= JENSEN_HAE_MASK; + addr = (addr << 7) + EISA_MEM + 0x60; + r0 = *(vuip) (addr); + r1 = *(vuip) (addr + (4 << 7)); + return r1 << 32 | r0; +} + +__EXTERN_INLINE void jensen_writeb(u8 b, volatile void __iomem *xaddr) +{ + unsigned long addr = (unsigned long) xaddr; + jensen_set_hae(addr); + addr &= JENSEN_HAE_MASK; + *(vuip) ((addr << 7) + EISA_MEM + 0x00) = b * 0x01010101; +} + +__EXTERN_INLINE void jensen_writew(u16 b, volatile void __iomem *xaddr) +{ + unsigned long addr = (unsigned long) xaddr; + jensen_set_hae(addr); + addr &= JENSEN_HAE_MASK; + *(vuip) ((addr << 7) + EISA_MEM + 0x20) = b * 0x00010001; +} + +__EXTERN_INLINE void jensen_writel(u32 b, volatile void __iomem *xaddr) +{ + unsigned long addr = (unsigned long) xaddr; + jensen_set_hae(addr); + addr &= JENSEN_HAE_MASK; + *(vuip) ((addr << 7) + EISA_MEM + 0x60) = b; +} + +__EXTERN_INLINE void jensen_writeq(u64 b, volatile void __iomem *xaddr) +{ + unsigned long addr = (unsigned long) xaddr; + jensen_set_hae(addr); + addr &= JENSEN_HAE_MASK; + addr = (addr << 7) + EISA_MEM + 0x60; + *(vuip) (addr) = b; + *(vuip) (addr + (4 << 7)) = b >> 32; +} + +__EXTERN_INLINE void __iomem *jensen_ioportmap(unsigned long addr) +{ + return (void __iomem *)addr; +} + +__EXTERN_INLINE void __iomem *jensen_ioremap(unsigned long addr, + unsigned long size) +{ + return (void __iomem *)(addr + 0x100000000ul); +} + +__EXTERN_INLINE int jensen_is_ioaddr(unsigned long addr) +{ + return (long)addr >= 0; +} + +__EXTERN_INLINE int jensen_is_mmio(const volatile void __iomem *addr) +{ + return (unsigned long)addr >= 0x100000000ul; +} + +/* New-style ioread interface. All the routines are so ugly for Jensen + that it doesn't make sense to merge them. */ + +#define IOPORT(OS, NS) \ +__EXTERN_INLINE unsigned int jensen_ioread##NS(void __iomem *xaddr) \ +{ \ + if (jensen_is_mmio(xaddr)) \ + return jensen_read##OS(xaddr - 0x100000000ul); \ + else \ + return jensen_in##OS((unsigned long)xaddr); \ +} \ +__EXTERN_INLINE void jensen_iowrite##NS(u##NS b, void __iomem *xaddr) \ +{ \ + if (jensen_is_mmio(xaddr)) \ + jensen_write##OS(b, xaddr - 0x100000000ul); \ + else \ + jensen_out##OS(b, (unsigned long)xaddr); \ +} + +IOPORT(b, 8) +IOPORT(w, 16) +IOPORT(l, 32) + +#undef IOPORT + +#undef vuip + +#undef __IO_PREFIX +#define __IO_PREFIX jensen +#define jensen_trivial_rw_bw 0 +#define jensen_trivial_rw_lq 0 +#define jensen_trivial_io_bw 0 +#define jensen_trivial_io_lq 0 +#define jensen_trivial_iounmap 1 +#include <asm/io_trivial.h> + +#ifdef __IO_EXTERN_INLINE +#undef __EXTERN_INLINE +#undef __IO_EXTERN_INLINE +#endif + +#endif /* __KERNEL__ */ + +#endif /* __ALPHA_JENSEN_H */ diff --git a/arch/alpha/include/asm/kdebug.h b/arch/alpha/include/asm/kdebug.h new file mode 100644 index 000000000..6ece1b037 --- /dev/null +++ b/arch/alpha/include/asm/kdebug.h @@ -0,0 +1 @@ +#include <asm-generic/kdebug.h> diff --git a/arch/alpha/include/asm/kmap_types.h b/arch/alpha/include/asm/kmap_types.h new file mode 100644 index 000000000..a8d4ec8ea --- /dev/null +++ b/arch/alpha/include/asm/kmap_types.h @@ -0,0 +1,14 @@ +#ifndef _ASM_KMAP_TYPES_H +#define _ASM_KMAP_TYPES_H + +/* Dummy header just to define km_type. */ + +#ifdef CONFIG_DEBUG_HIGHMEM +#define __WITH_KM_FENCE +#endif + +#include <asm-generic/kmap_types.h> + +#undef __WITH_KM_FENCE + +#endif diff --git a/arch/alpha/include/asm/linkage.h b/arch/alpha/include/asm/linkage.h new file mode 100644 index 000000000..7cfd06e8c --- /dev/null +++ b/arch/alpha/include/asm/linkage.h @@ -0,0 +1,8 @@ +#ifndef __ASM_LINKAGE_H +#define __ASM_LINKAGE_H + +#define cond_syscall(x) asm(".weak\t" #x "\n" #x " = sys_ni_syscall") +#define SYSCALL_ALIAS(alias, name) \ + asm ( #alias " = " #name "\n\t.globl " #alias) + +#endif diff --git a/arch/alpha/include/asm/local.h b/arch/alpha/include/asm/local.h new file mode 100644 index 000000000..9c94b8456 --- /dev/null +++ b/arch/alpha/include/asm/local.h @@ -0,0 +1,101 @@ +#ifndef _ALPHA_LOCAL_H +#define _ALPHA_LOCAL_H + +#include <linux/percpu.h> +#include <linux/atomic.h> + +typedef struct +{ + atomic_long_t a; +} local_t; + +#define LOCAL_INIT(i) { ATOMIC_LONG_INIT(i) } +#define local_read(l) atomic_long_read(&(l)->a) +#define local_set(l,i) atomic_long_set(&(l)->a, (i)) +#define local_inc(l) atomic_long_inc(&(l)->a) +#define local_dec(l) atomic_long_dec(&(l)->a) +#define local_add(i,l) atomic_long_add((i),(&(l)->a)) +#define local_sub(i,l) atomic_long_sub((i),(&(l)->a)) + +static __inline__ long local_add_return(long i, local_t * l) +{ + long temp, result; + __asm__ __volatile__( + "1: ldq_l %0,%1\n" + " addq %0,%3,%2\n" + " addq %0,%3,%0\n" + " stq_c %0,%1\n" + " beq %0,2f\n" + ".subsection 2\n" + "2: br 1b\n" + ".previous" + :"=&r" (temp), "=m" (l->a.counter), "=&r" (result) + :"Ir" (i), "m" (l->a.counter) : "memory"); + return result; +} + +static __inline__ long local_sub_return(long i, local_t * l) +{ + long temp, result; + __asm__ __volatile__( + "1: ldq_l %0,%1\n" + " subq %0,%3,%2\n" + " subq %0,%3,%0\n" + " stq_c %0,%1\n" + " beq %0,2f\n" + ".subsection 2\n" + "2: br 1b\n" + ".previous" + :"=&r" (temp), "=m" (l->a.counter), "=&r" (result) + :"Ir" (i), "m" (l->a.counter) : "memory"); + return result; +} + +#define local_cmpxchg(l, o, n) \ + (cmpxchg_local(&((l)->a.counter), (o), (n))) +#define local_xchg(l, n) (xchg_local(&((l)->a.counter), (n))) + +/** + * local_add_unless - add unless the number is a given value + * @l: pointer of type local_t + * @a: the amount to add to l... + * @u: ...unless l 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. + */ +#define local_add_unless(l, a, u) \ +({ \ + long c, old; \ + c = local_read(l); \ + for (;;) { \ + if (unlikely(c == (u))) \ + break; \ + old = local_cmpxchg((l), c, c + (a)); \ + if (likely(old == c)) \ + break; \ + c = old; \ + } \ + c != (u); \ +}) +#define local_inc_not_zero(l) local_add_unless((l), 1, 0) + +#define local_add_negative(a, l) (local_add_return((a), (l)) < 0) + +#define local_dec_return(l) local_sub_return(1,(l)) + +#define local_inc_return(l) local_add_return(1,(l)) + +#define local_sub_and_test(i,l) (local_sub_return((i), (l)) == 0) + +#define local_inc_and_test(l) (local_add_return(1, (l)) == 0) + +#define local_dec_and_test(l) (local_sub_return(1, (l)) == 0) + +/* Verify if faster than atomic ops */ +#define __local_inc(l) ((l)->a.counter++) +#define __local_dec(l) ((l)->a.counter++) +#define __local_add(i,l) ((l)->a.counter+=(i)) +#define __local_sub(i,l) ((l)->a.counter-=(i)) + +#endif /* _ALPHA_LOCAL_H */ diff --git a/arch/alpha/include/asm/local64.h b/arch/alpha/include/asm/local64.h new file mode 100644 index 000000000..36c93b5cc --- /dev/null +++ b/arch/alpha/include/asm/local64.h @@ -0,0 +1 @@ +#include <asm-generic/local64.h> diff --git a/arch/alpha/include/asm/machvec.h b/arch/alpha/include/asm/machvec.h new file mode 100644 index 000000000..75cb3641e --- /dev/null +++ b/arch/alpha/include/asm/machvec.h @@ -0,0 +1,142 @@ +#ifndef __ALPHA_MACHVEC_H +#define __ALPHA_MACHVEC_H 1 + +#include <linux/types.h> + +/* + * This file gets pulled in by asm/io.h from user space. We don't + * want most of this escaping. + */ + +#ifdef __KERNEL__ + +/* The following structure vectors all of the I/O and IRQ manipulation + from the generic kernel to the hardware specific backend. */ + +struct task_struct; +struct mm_struct; +struct vm_area_struct; +struct linux_hose_info; +struct pci_dev; +struct pci_ops; +struct pci_controller; +struct _alpha_agp_info; +struct rtc_time; + +struct alpha_machine_vector +{ + /* This "belongs" down below with the rest of the runtime + variables, but it is convenient for entry.S if these + two slots are at the beginning of the struct. */ + unsigned long hae_cache; + unsigned long *hae_register; + + int nr_irqs; + int rtc_port; + int rtc_boot_cpu_only; + unsigned int max_asn; + unsigned long max_isa_dma_address; + unsigned long irq_probe_mask; + unsigned long iack_sc; + unsigned long min_io_address; + unsigned long min_mem_address; + unsigned long pci_dac_offset; + + void (*mv_pci_tbi)(struct pci_controller *hose, + dma_addr_t start, dma_addr_t end); + + unsigned int (*mv_ioread8)(void __iomem *); + unsigned int (*mv_ioread16)(void __iomem *); + unsigned int (*mv_ioread32)(void __iomem *); + + void (*mv_iowrite8)(u8, void __iomem *); + void (*mv_iowrite16)(u16, void __iomem *); + void (*mv_iowrite32)(u32, void __iomem *); + + u8 (*mv_readb)(const volatile void __iomem *); + u16 (*mv_readw)(const volatile void __iomem *); + u32 (*mv_readl)(const volatile void __iomem *); + u64 (*mv_readq)(const volatile void __iomem *); + + void (*mv_writeb)(u8, volatile void __iomem *); + void (*mv_writew)(u16, volatile void __iomem *); + void (*mv_writel)(u32, volatile void __iomem *); + void (*mv_writeq)(u64, volatile void __iomem *); + + void __iomem *(*mv_ioportmap)(unsigned long); + void __iomem *(*mv_ioremap)(unsigned long, unsigned long); + void (*mv_iounmap)(volatile void __iomem *); + int (*mv_is_ioaddr)(unsigned long); + int (*mv_is_mmio)(const volatile void __iomem *); + + void (*mv_switch_mm)(struct mm_struct *, struct mm_struct *, + struct task_struct *); + void (*mv_activate_mm)(struct mm_struct *, struct mm_struct *); + + void (*mv_flush_tlb_current)(struct mm_struct *); + void (*mv_flush_tlb_current_page)(struct mm_struct * mm, + struct vm_area_struct *vma, + unsigned long addr); + + void (*update_irq_hw)(unsigned long, unsigned long, int); + void (*ack_irq)(unsigned long); + void (*device_interrupt)(unsigned long vector); + void (*machine_check)(unsigned long vector, unsigned long la); + + void (*smp_callin)(void); + void (*init_arch)(void); + void (*init_irq)(void); + void (*init_rtc)(void); + void (*init_pci)(void); + void (*kill_arch)(int); + + u8 (*pci_swizzle)(struct pci_dev *, u8 *); + int (*pci_map_irq)(const struct pci_dev *, u8, u8); + struct pci_ops *pci_ops; + + struct _alpha_agp_info *(*agp_info)(void); + + const char *vector_name; + + /* NUMA information */ + int (*pa_to_nid)(unsigned long); + int (*cpuid_to_nid)(int); + unsigned long (*node_mem_start)(int); + unsigned long (*node_mem_size)(int); + + /* System specific parameters. */ + union { + struct { + unsigned long gru_int_req_bits; + } cia; + + struct { + unsigned long gamma_bias; + } t2; + + struct { + unsigned int route_tab; + } sio; + } sys; +}; + +extern struct alpha_machine_vector alpha_mv; + +#ifdef CONFIG_ALPHA_GENERIC +extern int alpha_using_srm; +extern int alpha_using_qemu; +#else +# ifdef CONFIG_ALPHA_SRM +# define alpha_using_srm 1 +# else +# define alpha_using_srm 0 +# endif +# ifdef CONFIG_ALPHA_QEMU +# define alpha_using_qemu 1 +# else +# define alpha_using_qemu 0 +# endif +#endif /* GENERIC */ + +#endif /* __KERNEL__ */ +#endif /* __ALPHA_MACHVEC_H */ diff --git a/arch/alpha/include/asm/mc146818rtc.h b/arch/alpha/include/asm/mc146818rtc.h new file mode 100644 index 000000000..097703f1c --- /dev/null +++ b/arch/alpha/include/asm/mc146818rtc.h @@ -0,0 +1,27 @@ +/* + * Machine dependent access functions for RTC registers. + */ +#ifndef __ASM_ALPHA_MC146818RTC_H +#define __ASM_ALPHA_MC146818RTC_H + +#include <asm/io.h> + +#ifndef RTC_PORT +#define RTC_PORT(x) (0x70 + (x)) +#define RTC_ALWAYS_BCD 1 /* RTC operates in binary mode */ +#endif + +/* + * The yet supported machines all access the RTC index register via + * an ISA port access but the way to access the date register differs ... + */ +#define CMOS_READ(addr) ({ \ +outb_p((addr),RTC_PORT(0)); \ +inb_p(RTC_PORT(1)); \ +}) +#define CMOS_WRITE(val, addr) ({ \ +outb_p((addr),RTC_PORT(0)); \ +outb_p((val),RTC_PORT(1)); \ +}) + +#endif /* __ASM_ALPHA_MC146818RTC_H */ diff --git a/arch/alpha/include/asm/mce.h b/arch/alpha/include/asm/mce.h new file mode 100644 index 000000000..660285b9a --- /dev/null +++ b/arch/alpha/include/asm/mce.h @@ -0,0 +1,83 @@ +#ifndef __ALPHA_MCE_H +#define __ALPHA_MCE_H + +/* + * This is the logout header that should be common to all platforms + * (assuming they are running OSF/1 PALcode, I guess). + */ +struct el_common { + unsigned int size; /* size in bytes of logout area */ + unsigned int sbz1 : 30; /* should be zero */ + unsigned int err2 : 1; /* second error */ + unsigned int retry : 1; /* retry flag */ + unsigned int proc_offset; /* processor-specific offset */ + unsigned int sys_offset; /* system-specific offset */ + unsigned int code; /* machine check code */ + unsigned int frame_rev; /* frame revision */ +}; + +/* Machine Check Frame for uncorrectable errors (Large format) + * --- This is used to log uncorrectable errors such as + * double bit ECC errors. + * --- These errors are detected by both processor and systems. + */ +struct el_common_EV5_uncorrectable_mcheck { + unsigned long shadow[8]; /* Shadow reg. 8-14, 25 */ + unsigned long paltemp[24]; /* PAL TEMP REGS. */ + unsigned long exc_addr; /* Address of excepting instruction*/ + unsigned long exc_sum; /* Summary of arithmetic traps. */ + unsigned long exc_mask; /* Exception mask (from exc_sum). */ + unsigned long pal_base; /* Base address for PALcode. */ + unsigned long isr; /* Interrupt Status Reg. */ + unsigned long icsr; /* CURRENT SETUP OF EV5 IBOX */ + unsigned long ic_perr_stat; /* I-CACHE Reg. <11> set Data parity + <12> set TAG parity*/ + unsigned long dc_perr_stat; /* D-CACHE error Reg. Bits set to 1: + <2> Data error in bank 0 + <3> Data error in bank 1 + <4> Tag error in bank 0 + <5> Tag error in bank 1 */ + unsigned long va; /* Effective VA of fault or miss. */ + unsigned long mm_stat; /* Holds the reason for D-stream + fault or D-cache parity errors */ + unsigned long sc_addr; /* Address that was being accessed + when EV5 detected Secondary cache + failure. */ + unsigned long sc_stat; /* Helps determine if the error was + TAG/Data parity(Secondary Cache)*/ + unsigned long bc_tag_addr; /* Contents of EV5 BC_TAG_ADDR */ + unsigned long ei_addr; /* Physical address of any transfer + that is logged in EV5 EI_STAT */ + unsigned long fill_syndrome; /* For correcting ECC errors. */ + unsigned long ei_stat; /* Helps identify reason of any + processor uncorrectable error + at its external interface. */ + unsigned long ld_lock; /* Contents of EV5 LD_LOCK register*/ +}; + +struct el_common_EV6_mcheck { + unsigned int FrameSize; /* Bytes, including this field */ + unsigned int FrameFlags; /* <31> = Retry, <30> = Second Error */ + unsigned int CpuOffset; /* Offset to CPU-specific info */ + unsigned int SystemOffset; /* Offset to system-specific info */ + unsigned int MCHK_Code; + unsigned int MCHK_Frame_Rev; + unsigned long I_STAT; /* EV6 Internal Processor Registers */ + unsigned long DC_STAT; /* (See the 21264 Spec) */ + unsigned long C_ADDR; + unsigned long DC1_SYNDROME; + unsigned long DC0_SYNDROME; + unsigned long C_STAT; + unsigned long C_STS; + unsigned long MM_STAT; + unsigned long EXC_ADDR; + unsigned long IER_CM; + unsigned long ISUM; + unsigned long RESERVED0; + unsigned long PAL_BASE; + unsigned long I_CTL; + unsigned long PCTX; +}; + + +#endif /* __ALPHA_MCE_H */ diff --git a/arch/alpha/include/asm/mmu.h b/arch/alpha/include/asm/mmu.h new file mode 100644 index 000000000..3dc127779 --- /dev/null +++ b/arch/alpha/include/asm/mmu.h @@ -0,0 +1,7 @@ +#ifndef __ALPHA_MMU_H +#define __ALPHA_MMU_H + +/* The alpha MMU context is one "unsigned long" bitmap per CPU */ +typedef unsigned long mm_context_t[NR_CPUS]; + +#endif diff --git a/arch/alpha/include/asm/mmu_context.h b/arch/alpha/include/asm/mmu_context.h new file mode 100644 index 000000000..4c51c0533 --- /dev/null +++ b/arch/alpha/include/asm/mmu_context.h @@ -0,0 +1,259 @@ +#ifndef __ALPHA_MMU_CONTEXT_H +#define __ALPHA_MMU_CONTEXT_H + +/* + * get a new mmu context.. + * + * Copyright (C) 1996, Linus Torvalds + */ + +#include <asm/machvec.h> +#include <asm/compiler.h> +#include <asm-generic/mm_hooks.h> + +/* + * Force a context reload. This is needed when we change the page + * table pointer or when we update the ASN of the current process. + */ + +/* Don't get into trouble with dueling __EXTERN_INLINEs. */ +#ifndef __EXTERN_INLINE +#include <asm/io.h> +#endif + + +static inline unsigned long +__reload_thread(struct pcb_struct *pcb) +{ + register unsigned long a0 __asm__("$16"); + register unsigned long v0 __asm__("$0"); + + a0 = virt_to_phys(pcb); + __asm__ __volatile__( + "call_pal %2 #__reload_thread" + : "=r"(v0), "=r"(a0) + : "i"(PAL_swpctx), "r"(a0) + : "$1", "$22", "$23", "$24", "$25"); + + return v0; +} + + +/* + * The maximum ASN's the processor supports. On the EV4 this is 63 + * but the PAL-code doesn't actually use this information. On the + * EV5 this is 127, and EV6 has 255. + * + * On the EV4, the ASNs are more-or-less useless anyway, as they are + * only used as an icache tag, not for TB entries. On the EV5 and EV6, + * ASN's also validate the TB entries, and thus make a lot more sense. + * + * The EV4 ASN's don't even match the architecture manual, ugh. And + * I quote: "If a processor implements address space numbers (ASNs), + * and the old PTE has the Address Space Match (ASM) bit clear (ASNs + * in use) and the Valid bit set, then entries can also effectively be + * made coherent by assigning a new, unused ASN to the currently + * running process and not reusing the previous ASN before calling the + * appropriate PALcode routine to invalidate the translation buffer (TB)". + * + * In short, the EV4 has a "kind of" ASN capability, but it doesn't actually + * work correctly and can thus not be used (explaining the lack of PAL-code + * support). + */ +#define EV4_MAX_ASN 63 +#define EV5_MAX_ASN 127 +#define EV6_MAX_ASN 255 + +#ifdef CONFIG_ALPHA_GENERIC +# define MAX_ASN (alpha_mv.max_asn) +#else +# ifdef CONFIG_ALPHA_EV4 +# define MAX_ASN EV4_MAX_ASN +# elif defined(CONFIG_ALPHA_EV5) +# define MAX_ASN EV5_MAX_ASN +# else +# define MAX_ASN EV6_MAX_ASN +# endif +#endif + +/* + * cpu_last_asn(processor): + * 63 0 + * +-------------+----------------+--------------+ + * | asn version | this processor | hardware asn | + * +-------------+----------------+--------------+ + */ + +#include <asm/smp.h> +#ifdef CONFIG_SMP +#define cpu_last_asn(cpuid) (cpu_data[cpuid].last_asn) +#else +extern unsigned long last_asn; +#define cpu_last_asn(cpuid) last_asn +#endif /* CONFIG_SMP */ + +#define WIDTH_HARDWARE_ASN 8 +#define ASN_FIRST_VERSION (1UL << WIDTH_HARDWARE_ASN) +#define HARDWARE_ASN_MASK ((1UL << WIDTH_HARDWARE_ASN) - 1) + +/* + * NOTE! The way this is set up, the high bits of the "asn_cache" (and + * the "mm->context") are the ASN _version_ code. A version of 0 is + * always considered invalid, so to invalidate another process you only + * need to do "p->mm->context = 0". + * + * If we need more ASN's than the processor has, we invalidate the old + * user TLB's (tbiap()) and start a new ASN version. That will automatically + * force a new asn for any other processes the next time they want to + * run. + */ + +#ifndef __EXTERN_INLINE +#define __EXTERN_INLINE extern inline +#define __MMU_EXTERN_INLINE +#endif + +extern inline unsigned long +__get_new_mm_context(struct mm_struct *mm, long cpu) +{ + unsigned long asn = cpu_last_asn(cpu); + unsigned long next = asn + 1; + + if ((asn & HARDWARE_ASN_MASK) >= MAX_ASN) { + tbiap(); + imb(); + next = (asn & ~HARDWARE_ASN_MASK) + ASN_FIRST_VERSION; + } + cpu_last_asn(cpu) = next; + return next; +} + +__EXTERN_INLINE void +ev5_switch_mm(struct mm_struct *prev_mm, struct mm_struct *next_mm, + struct task_struct *next) +{ + /* Check if our ASN is of an older version, and thus invalid. */ + unsigned long asn; + unsigned long mmc; + long cpu = smp_processor_id(); + +#ifdef CONFIG_SMP + cpu_data[cpu].asn_lock = 1; + barrier(); +#endif + asn = cpu_last_asn(cpu); + mmc = next_mm->context[cpu]; + if ((mmc ^ asn) & ~HARDWARE_ASN_MASK) { + mmc = __get_new_mm_context(next_mm, cpu); + next_mm->context[cpu] = mmc; + } +#ifdef CONFIG_SMP + else + cpu_data[cpu].need_new_asn = 1; +#endif + + /* Always update the PCB ASN. Another thread may have allocated + a new mm->context (via flush_tlb_mm) without the ASN serial + number wrapping. We have no way to detect when this is needed. */ + task_thread_info(next)->pcb.asn = mmc & HARDWARE_ASN_MASK; +} + +__EXTERN_INLINE void +ev4_switch_mm(struct mm_struct *prev_mm, struct mm_struct *next_mm, + struct task_struct *next) +{ + /* As described, ASN's are broken for TLB usage. But we can + optimize for switching between threads -- if the mm is + unchanged from current we needn't flush. */ + /* ??? May not be needed because EV4 PALcode recognizes that + ASN's are broken and does a tbiap itself on swpctx, under + the "Must set ASN or flush" rule. At least this is true + for a 1992 SRM, reports Joseph Martin (jmartin@hlo.dec.com). + I'm going to leave this here anyway, just to Be Sure. -- r~ */ + if (prev_mm != next_mm) + tbiap(); + + /* Do continue to allocate ASNs, because we can still use them + to avoid flushing the icache. */ + ev5_switch_mm(prev_mm, next_mm, next); +} + +extern void __load_new_mm_context(struct mm_struct *); + +#ifdef CONFIG_SMP +#define check_mmu_context() \ +do { \ + int cpu = smp_processor_id(); \ + cpu_data[cpu].asn_lock = 0; \ + barrier(); \ + if (cpu_data[cpu].need_new_asn) { \ + struct mm_struct * mm = current->active_mm; \ + cpu_data[cpu].need_new_asn = 0; \ + if (!mm->context[cpu]) \ + __load_new_mm_context(mm); \ + } \ +} while(0) +#else +#define check_mmu_context() do { } while(0) +#endif + +__EXTERN_INLINE void +ev5_activate_mm(struct mm_struct *prev_mm, struct mm_struct *next_mm) +{ + __load_new_mm_context(next_mm); +} + +__EXTERN_INLINE void +ev4_activate_mm(struct mm_struct *prev_mm, struct mm_struct *next_mm) +{ + __load_new_mm_context(next_mm); + tbiap(); +} + +#define deactivate_mm(tsk,mm) do { } while (0) + +#ifdef CONFIG_ALPHA_GENERIC +# define switch_mm(a,b,c) alpha_mv.mv_switch_mm((a),(b),(c)) +# define activate_mm(x,y) alpha_mv.mv_activate_mm((x),(y)) +#else +# ifdef CONFIG_ALPHA_EV4 +# define switch_mm(a,b,c) ev4_switch_mm((a),(b),(c)) +# define activate_mm(x,y) ev4_activate_mm((x),(y)) +# else +# define switch_mm(a,b,c) ev5_switch_mm((a),(b),(c)) +# define activate_mm(x,y) ev5_activate_mm((x),(y)) +# endif +#endif + +static inline int +init_new_context(struct task_struct *tsk, struct mm_struct *mm) +{ + int i; + + for_each_online_cpu(i) + mm->context[i] = 0; + if (tsk != current) + task_thread_info(tsk)->pcb.ptbr + = ((unsigned long)mm->pgd - IDENT_ADDR) >> PAGE_SHIFT; + return 0; +} + +extern inline void +destroy_context(struct mm_struct *mm) +{ + /* Nothing to do. */ +} + +static inline void +enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk) +{ + task_thread_info(tsk)->pcb.ptbr + = ((unsigned long)mm->pgd - IDENT_ADDR) >> PAGE_SHIFT; +} + +#ifdef __MMU_EXTERN_INLINE +#undef __EXTERN_INLINE +#undef __MMU_EXTERN_INLINE +#endif + +#endif /* __ALPHA_MMU_CONTEXT_H */ diff --git a/arch/alpha/include/asm/mmzone.h b/arch/alpha/include/asm/mmzone.h new file mode 100644 index 000000000..14ce27bcc --- /dev/null +++ b/arch/alpha/include/asm/mmzone.h @@ -0,0 +1,112 @@ +/* + * Written by Kanoj Sarcar (kanoj@sgi.com) Aug 99 + * Adapted for the alpha wildfire architecture Jan 2001. + */ +#ifndef _ASM_MMZONE_H_ +#define _ASM_MMZONE_H_ + +#include <asm/smp.h> + +struct bootmem_data_t; /* stupid forward decl. */ + +/* + * Following are macros that are specific to this numa platform. + */ + +extern pg_data_t node_data[]; + +#define alpha_pa_to_nid(pa) \ + (alpha_mv.pa_to_nid \ + ? alpha_mv.pa_to_nid(pa) \ + : (0)) +#define node_mem_start(nid) \ + (alpha_mv.node_mem_start \ + ? alpha_mv.node_mem_start(nid) \ + : (0UL)) +#define node_mem_size(nid) \ + (alpha_mv.node_mem_size \ + ? alpha_mv.node_mem_size(nid) \ + : ((nid) ? (0UL) : (~0UL))) + +#define pa_to_nid(pa) alpha_pa_to_nid(pa) +#define NODE_DATA(nid) (&node_data[(nid)]) + +#define node_localnr(pfn, nid) ((pfn) - NODE_DATA(nid)->node_start_pfn) + +#if 1 +#define PLAT_NODE_DATA_LOCALNR(p, n) \ + (((p) >> PAGE_SHIFT) - PLAT_NODE_DATA(n)->gendata.node_start_pfn) +#else +static inline unsigned long +PLAT_NODE_DATA_LOCALNR(unsigned long p, int n) +{ + unsigned long temp; + temp = p >> PAGE_SHIFT; + return temp - PLAT_NODE_DATA(n)->gendata.node_start_pfn; +} +#endif + +#ifdef CONFIG_DISCONTIGMEM + +/* + * Following are macros that each numa implementation must define. + */ + +/* + * Given a kernel address, find the home node of the underlying memory. + */ +#define kvaddr_to_nid(kaddr) pa_to_nid(__pa(kaddr)) + +/* + * Given a kaddr, LOCAL_BASE_ADDR finds the owning node of the memory + * and returns the kaddr corresponding to first physical page in the + * node's mem_map. + */ +#define LOCAL_BASE_ADDR(kaddr) \ + ((unsigned long)__va(NODE_DATA(kvaddr_to_nid(kaddr))->node_start_pfn \ + << PAGE_SHIFT)) + +/* XXX: FIXME -- nyc */ +#define kern_addr_valid(kaddr) (0) + +#define virt_to_page(kaddr) pfn_to_page(__pa(kaddr) >> PAGE_SHIFT) + +#define pmd_page(pmd) (pfn_to_page(pmd_val(pmd) >> 32)) +#define pgd_page(pgd) (pfn_to_page(pgd_val(pgd) >> 32)) +#define pte_pfn(pte) (pte_val(pte) >> 32) + +#define mk_pte(page, pgprot) \ +({ \ + pte_t pte; \ + unsigned long pfn; \ + \ + pfn = page_to_pfn(page) << 32; \ + pte_val(pte) = pfn | pgprot_val(pgprot); \ + \ + pte; \ +}) + +#define pte_page(x) \ +({ \ + unsigned long kvirt; \ + struct page * __xx; \ + \ + kvirt = (unsigned long)__va(pte_val(x) >> (32-PAGE_SHIFT)); \ + __xx = virt_to_page(kvirt); \ + \ + __xx; \ +}) + +#define page_to_pa(page) \ + (page_to_pfn(page) << PAGE_SHIFT) + +#define pfn_to_nid(pfn) pa_to_nid(((u64)(pfn) << PAGE_SHIFT)) +#define pfn_valid(pfn) \ + (((pfn) - node_start_pfn(pfn_to_nid(pfn))) < \ + node_spanned_pages(pfn_to_nid(pfn))) \ + +#define virt_addr_valid(kaddr) pfn_valid((__pa(kaddr) >> PAGE_SHIFT)) + +#endif /* CONFIG_DISCONTIGMEM */ + +#endif /* _ASM_MMZONE_H_ */ diff --git a/arch/alpha/include/asm/module.h b/arch/alpha/include/asm/module.h new file mode 100644 index 000000000..9cd13b551 --- /dev/null +++ b/arch/alpha/include/asm/module.h @@ -0,0 +1,17 @@ +#ifndef _ALPHA_MODULE_H +#define _ALPHA_MODULE_H + +#include <asm-generic/module.h> + +struct mod_arch_specific +{ + unsigned int gotsecindex; +}; + +#define ARCH_SHF_SMALL SHF_ALPHA_GPREL + +#ifdef MODULE +asm(".section .got,\"aws\",@progbits; .align 3; .previous"); +#endif + +#endif /*_ALPHA_MODULE_H*/ diff --git a/arch/alpha/include/asm/mutex.h b/arch/alpha/include/asm/mutex.h new file mode 100644 index 000000000..458c1f7fb --- /dev/null +++ b/arch/alpha/include/asm/mutex.h @@ -0,0 +1,9 @@ +/* + * Pull in the generic implementation for the mutex fastpath. + * + * TODO: implement optimized primitives instead, or leave the generic + * implementation in place, or pick the atomic_xchg() based generic + * implementation. (see asm-generic/mutex-xchg.h for details) + */ + +#include <asm-generic/mutex-dec.h> diff --git a/arch/alpha/include/asm/page.h b/arch/alpha/include/asm/page.h new file mode 100644 index 000000000..07af06254 --- /dev/null +++ b/arch/alpha/include/asm/page.h @@ -0,0 +1,98 @@ +#ifndef _ALPHA_PAGE_H +#define _ALPHA_PAGE_H + +#include <linux/const.h> +#include <asm/pal.h> + +/* PAGE_SHIFT determines the page size */ +#define PAGE_SHIFT 13 +#define PAGE_SIZE (_AC(1,UL) << PAGE_SHIFT) +#define PAGE_MASK (~(PAGE_SIZE-1)) + +#ifndef __ASSEMBLY__ + +#define STRICT_MM_TYPECHECKS + +extern void clear_page(void *page); +#define clear_user_page(page, vaddr, pg) clear_page(page) + +#define __alloc_zeroed_user_highpage(movableflags, vma, vaddr) \ + alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO | movableflags, vma, vmaddr) +#define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE + +extern void copy_page(void * _to, void * _from); +#define copy_user_page(to, from, vaddr, pg) copy_page(to, from) + +#ifdef STRICT_MM_TYPECHECKS +/* + * These are used to make use of C type-checking.. + */ +typedef struct { unsigned long pte; } pte_t; +typedef struct { unsigned long pmd; } pmd_t; +typedef struct { unsigned long pgd; } pgd_t; +typedef struct { unsigned long pgprot; } pgprot_t; + +#define pte_val(x) ((x).pte) +#define pmd_val(x) ((x).pmd) +#define pgd_val(x) ((x).pgd) +#define pgprot_val(x) ((x).pgprot) + +#define __pte(x) ((pte_t) { (x) } ) +#define __pmd(x) ((pmd_t) { (x) } ) +#define __pgd(x) ((pgd_t) { (x) } ) +#define __pgprot(x) ((pgprot_t) { (x) } ) + +#else +/* + * .. while these make it easier on the compiler + */ +typedef unsigned long pte_t; +typedef unsigned long pmd_t; +typedef unsigned long pgd_t; +typedef unsigned long pgprot_t; + +#define pte_val(x) (x) +#define pmd_val(x) (x) +#define pgd_val(x) (x) +#define pgprot_val(x) (x) + +#define __pte(x) (x) +#define __pgd(x) (x) +#define __pgprot(x) (x) + +#endif /* STRICT_MM_TYPECHECKS */ + +typedef struct page *pgtable_t; + +#ifdef USE_48_BIT_KSEG +#define PAGE_OFFSET 0xffff800000000000UL +#else +#define PAGE_OFFSET 0xfffffc0000000000UL +#endif + +#else + +#ifdef USE_48_BIT_KSEG +#define PAGE_OFFSET 0xffff800000000000 +#else +#define PAGE_OFFSET 0xfffffc0000000000 +#endif + +#endif /* !__ASSEMBLY__ */ + +#define __pa(x) ((unsigned long) (x) - PAGE_OFFSET) +#define __va(x) ((void *)((unsigned long) (x) + PAGE_OFFSET)) +#ifndef CONFIG_DISCONTIGMEM +#define virt_to_page(kaddr) pfn_to_page(__pa(kaddr) >> PAGE_SHIFT) + +#define pfn_valid(pfn) ((pfn) < max_mapnr) +#define virt_addr_valid(kaddr) pfn_valid(__pa(kaddr) >> PAGE_SHIFT) +#endif /* CONFIG_DISCONTIGMEM */ + +#define VM_DATA_DEFAULT_FLAGS (VM_READ | VM_WRITE | VM_EXEC | \ + VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) + +#include <asm-generic/memory_model.h> +#include <asm-generic/getorder.h> + +#endif /* _ALPHA_PAGE_H */ diff --git a/arch/alpha/include/asm/pal.h b/arch/alpha/include/asm/pal.h new file mode 100644 index 000000000..5422a4764 --- /dev/null +++ b/arch/alpha/include/asm/pal.h @@ -0,0 +1,186 @@ +#ifndef __ALPHA_PAL_H +#define __ALPHA_PAL_H + +#include <uapi/asm/pal.h> + +#ifndef __ASSEMBLY__ + +extern void halt(void) __attribute__((noreturn)); +#define __halt() __asm__ __volatile__ ("call_pal %0 #halt" : : "i" (PAL_halt)) + +#define imb() \ +__asm__ __volatile__ ("call_pal %0 #imb" : : "i" (PAL_imb) : "memory") + +#define draina() \ +__asm__ __volatile__ ("call_pal %0 #draina" : : "i" (PAL_draina) : "memory") + +#define __CALL_PAL_R0(NAME, TYPE) \ +extern inline TYPE NAME(void) \ +{ \ + register TYPE __r0 __asm__("$0"); \ + __asm__ __volatile__( \ + "call_pal %1 # " #NAME \ + :"=r" (__r0) \ + :"i" (PAL_ ## NAME) \ + :"$1", "$16", "$22", "$23", "$24", "$25"); \ + return __r0; \ +} + +#define __CALL_PAL_W1(NAME, TYPE0) \ +extern inline void NAME(TYPE0 arg0) \ +{ \ + register TYPE0 __r16 __asm__("$16") = arg0; \ + __asm__ __volatile__( \ + "call_pal %1 # "#NAME \ + : "=r"(__r16) \ + : "i"(PAL_ ## NAME), "0"(__r16) \ + : "$1", "$22", "$23", "$24", "$25"); \ +} + +#define __CALL_PAL_W2(NAME, TYPE0, TYPE1) \ +extern inline void NAME(TYPE0 arg0, TYPE1 arg1) \ +{ \ + register TYPE0 __r16 __asm__("$16") = arg0; \ + register TYPE1 __r17 __asm__("$17") = arg1; \ + __asm__ __volatile__( \ + "call_pal %2 # "#NAME \ + : "=r"(__r16), "=r"(__r17) \ + : "i"(PAL_ ## NAME), "0"(__r16), "1"(__r17) \ + : "$1", "$22", "$23", "$24", "$25"); \ +} + +#define __CALL_PAL_RW1(NAME, RTYPE, TYPE0) \ +extern inline RTYPE NAME(TYPE0 arg0) \ +{ \ + register RTYPE __r0 __asm__("$0"); \ + register TYPE0 __r16 __asm__("$16") = arg0; \ + __asm__ __volatile__( \ + "call_pal %2 # "#NAME \ + : "=r"(__r16), "=r"(__r0) \ + : "i"(PAL_ ## NAME), "0"(__r16) \ + : "$1", "$22", "$23", "$24", "$25"); \ + return __r0; \ +} + +#define __CALL_PAL_RW2(NAME, RTYPE, TYPE0, TYPE1) \ +extern inline RTYPE NAME(TYPE0 arg0, TYPE1 arg1) \ +{ \ + register RTYPE __r0 __asm__("$0"); \ + register TYPE0 __r16 __asm__("$16") = arg0; \ + register TYPE1 __r17 __asm__("$17") = arg1; \ + __asm__ __volatile__( \ + "call_pal %3 # "#NAME \ + : "=r"(__r16), "=r"(__r17), "=r"(__r0) \ + : "i"(PAL_ ## NAME), "0"(__r16), "1"(__r17) \ + : "$1", "$22", "$23", "$24", "$25"); \ + return __r0; \ +} + +__CALL_PAL_W1(cflush, unsigned long); +__CALL_PAL_R0(rdmces, unsigned long); +__CALL_PAL_R0(rdps, unsigned long); +__CALL_PAL_R0(rdusp, unsigned long); +__CALL_PAL_RW1(swpipl, unsigned long, unsigned long); +__CALL_PAL_R0(whami, unsigned long); +__CALL_PAL_W2(wrent, void*, unsigned long); +__CALL_PAL_W1(wripir, unsigned long); +__CALL_PAL_W1(wrkgp, unsigned long); +__CALL_PAL_W1(wrmces, unsigned long); +__CALL_PAL_RW2(wrperfmon, unsigned long, unsigned long, unsigned long); +__CALL_PAL_W1(wrusp, unsigned long); +__CALL_PAL_W1(wrvptptr, unsigned long); +__CALL_PAL_RW1(wtint, unsigned long, unsigned long); + +/* + * TB routines.. + */ +#define __tbi(nr,arg,arg1...) \ +({ \ + register unsigned long __r16 __asm__("$16") = (nr); \ + register unsigned long __r17 __asm__("$17"); arg; \ + __asm__ __volatile__( \ + "call_pal %3 #__tbi" \ + :"=r" (__r16),"=r" (__r17) \ + :"0" (__r16),"i" (PAL_tbi) ,##arg1 \ + :"$0", "$1", "$22", "$23", "$24", "$25"); \ +}) + +#define tbi(x,y) __tbi(x,__r17=(y),"1" (__r17)) +#define tbisi(x) __tbi(1,__r17=(x),"1" (__r17)) +#define tbisd(x) __tbi(2,__r17=(x),"1" (__r17)) +#define tbis(x) __tbi(3,__r17=(x),"1" (__r17)) +#define tbiap() __tbi(-1, /* no second argument */) +#define tbia() __tbi(-2, /* no second argument */) + +/* + * QEMU Cserv routines.. + */ + +static inline unsigned long +qemu_get_walltime(void) +{ + register unsigned long v0 __asm__("$0"); + register unsigned long a0 __asm__("$16") = 3; + + asm("call_pal %2 # cserve get_time" + : "=r"(v0), "+r"(a0) + : "i"(PAL_cserve) + : "$17", "$18", "$19", "$20", "$21"); + + return v0; +} + +static inline unsigned long +qemu_get_alarm(void) +{ + register unsigned long v0 __asm__("$0"); + register unsigned long a0 __asm__("$16") = 4; + + asm("call_pal %2 # cserve get_alarm" + : "=r"(v0), "+r"(a0) + : "i"(PAL_cserve) + : "$17", "$18", "$19", "$20", "$21"); + + return v0; +} + +static inline void +qemu_set_alarm_rel(unsigned long expire) +{ + register unsigned long a0 __asm__("$16") = 5; + register unsigned long a1 __asm__("$17") = expire; + + asm volatile("call_pal %2 # cserve set_alarm_rel" + : "+r"(a0), "+r"(a1) + : "i"(PAL_cserve) + : "$0", "$18", "$19", "$20", "$21"); +} + +static inline void +qemu_set_alarm_abs(unsigned long expire) +{ + register unsigned long a0 __asm__("$16") = 6; + register unsigned long a1 __asm__("$17") = expire; + + asm volatile("call_pal %2 # cserve set_alarm_abs" + : "+r"(a0), "+r"(a1) + : "i"(PAL_cserve) + : "$0", "$18", "$19", "$20", "$21"); +} + +static inline unsigned long +qemu_get_vmtime(void) +{ + register unsigned long v0 __asm__("$0"); + register unsigned long a0 __asm__("$16") = 7; + + asm("call_pal %2 # cserve get_time" + : "=r"(v0), "+r"(a0) + : "i"(PAL_cserve) + : "$17", "$18", "$19", "$20", "$21"); + + return v0; +} + +#endif /* !__ASSEMBLY__ */ +#endif /* __ALPHA_PAL_H */ diff --git a/arch/alpha/include/asm/param.h b/arch/alpha/include/asm/param.h new file mode 100644 index 000000000..a5b68b268 --- /dev/null +++ b/arch/alpha/include/asm/param.h @@ -0,0 +1,11 @@ +#ifndef _ASM_ALPHA_PARAM_H +#define _ASM_ALPHA_PARAM_H + +#include <uapi/asm/param.h> + +# undef HZ +# define HZ CONFIG_HZ +# define USER_HZ 1024 +# define CLOCKS_PER_SEC USER_HZ /* frequency at which times() counts */ + +#endif /* _ASM_ALPHA_PARAM_H */ diff --git a/arch/alpha/include/asm/parport.h b/arch/alpha/include/asm/parport.h new file mode 100644 index 000000000..6abd0af11 --- /dev/null +++ b/arch/alpha/include/asm/parport.h @@ -0,0 +1,18 @@ +/* + * parport.h: platform-specific PC-style parport initialisation + * + * Copyright (C) 1999, 2000 Tim Waugh <tim@cyberelk.demon.co.uk> + * + * This file should only be included by drivers/parport/parport_pc.c. + */ + +#ifndef _ASM_AXP_PARPORT_H +#define _ASM_AXP_PARPORT_H 1 + +static int parport_pc_find_isa_ports (int autoirq, int autodma); +static int parport_pc_find_nonpci_ports (int autoirq, int autodma) +{ + return parport_pc_find_isa_ports (autoirq, autodma); +} + +#endif /* !(_ASM_AXP_PARPORT_H) */ diff --git a/arch/alpha/include/asm/pci.h b/arch/alpha/include/asm/pci.h new file mode 100644 index 000000000..f7f680f74 --- /dev/null +++ b/arch/alpha/include/asm/pci.h @@ -0,0 +1,133 @@ +#ifndef __ALPHA_PCI_H +#define __ALPHA_PCI_H + +#ifdef __KERNEL__ + +#include <linux/spinlock.h> +#include <linux/dma-mapping.h> +#include <asm/scatterlist.h> +#include <asm/machvec.h> +#include <asm-generic/pci-bridge.h> + +/* + * The following structure is used to manage multiple PCI busses. + */ + +struct pci_dev; +struct pci_bus; +struct resource; +struct pci_iommu_arena; +struct page; + +/* A controller. Used to manage multiple PCI busses. */ + +struct pci_controller { + struct pci_controller *next; + struct pci_bus *bus; + struct resource *io_space; + struct resource *mem_space; + + /* The following are for reporting to userland. The invariant is + that if we report a BWX-capable dense memory, we do not report + a sparse memory at all, even if it exists. */ + unsigned long sparse_mem_base; + unsigned long dense_mem_base; + unsigned long sparse_io_base; + unsigned long dense_io_base; + + /* This one's for the kernel only. It's in KSEG somewhere. */ + unsigned long config_space_base; + + unsigned int index; + /* For compatibility with current (as of July 2003) pciutils + and XFree86. Eventually will be removed. */ + unsigned int need_domain_info; + + struct pci_iommu_arena *sg_pci; + struct pci_iommu_arena *sg_isa; + + void *sysdata; +}; + +/* Override the logic in pci_scan_bus for skipping already-configured + bus numbers. */ + +#define pcibios_assign_all_busses() 1 + +#define PCIBIOS_MIN_IO alpha_mv.min_io_address +#define PCIBIOS_MIN_MEM alpha_mv.min_mem_address + +extern void pcibios_set_master(struct pci_dev *dev); + +/* IOMMU controls. */ + +/* The PCI address space does not equal the physical memory address space. + The networking and block device layers use this boolean for bounce buffer + decisions. */ +#define PCI_DMA_BUS_IS_PHYS 0 + +#ifdef CONFIG_PCI + +/* implement the pci_ DMA API in terms of the generic device dma_ one */ +#include <asm-generic/pci-dma-compat.h> + +static inline void pci_dma_burst_advice(struct pci_dev *pdev, + enum pci_dma_burst_strategy *strat, + unsigned long *strategy_parameter) +{ + unsigned long cacheline_size; + u8 byte; + + pci_read_config_byte(pdev, PCI_CACHE_LINE_SIZE, &byte); + if (byte == 0) + cacheline_size = 1024; + else + cacheline_size = (int) byte * 4; + + *strat = PCI_DMA_BURST_BOUNDARY; + *strategy_parameter = cacheline_size; +} +#endif + +/* TODO: integrate with include/asm-generic/pci.h ? */ +static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel) +{ + return channel ? 15 : 14; +} + +#define pci_domain_nr(bus) ((struct pci_controller *)(bus)->sysdata)->index + +static inline int pci_proc_domain(struct pci_bus *bus) +{ + struct pci_controller *hose = bus->sysdata; + return hose->need_domain_info; +} + +#endif /* __KERNEL__ */ + +/* Values for the `which' argument to sys_pciconfig_iobase. */ +#define IOBASE_HOSE 0 +#define IOBASE_SPARSE_MEM 1 +#define IOBASE_DENSE_MEM 2 +#define IOBASE_SPARSE_IO 3 +#define IOBASE_DENSE_IO 4 +#define IOBASE_ROOT_BUS 5 +#define IOBASE_FROM_HOSE 0x10000 + +extern struct pci_dev *isa_bridge; + +extern int pci_legacy_read(struct pci_bus *bus, loff_t port, u32 *val, + size_t count); +extern int pci_legacy_write(struct pci_bus *bus, loff_t port, u32 val, + size_t count); +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 int pci_create_resource_files(struct pci_dev *dev); +extern void pci_remove_resource_files(struct pci_dev *dev); + +#endif /* __ALPHA_PCI_H */ diff --git a/arch/alpha/include/asm/percpu.h b/arch/alpha/include/asm/percpu.h new file mode 100644 index 000000000..2c12378e3 --- /dev/null +++ b/arch/alpha/include/asm/percpu.h @@ -0,0 +1,18 @@ +#ifndef __ALPHA_PERCPU_H +#define __ALPHA_PERCPU_H + +/* + * To calculate addresses of locally defined variables, GCC uses + * 32-bit displacement from the GP. Which doesn't work for per cpu + * variables in modules, as an offset to the kernel per cpu area is + * way above 4G. + * + * Always use weak definitions for percpu variables in modules. + */ +#if defined(MODULE) && defined(CONFIG_SMP) +#define ARCH_NEEDS_WEAK_PER_CPU +#endif + +#include <asm-generic/percpu.h> + +#endif /* __ALPHA_PERCPU_H */ diff --git a/arch/alpha/include/asm/perf_event.h b/arch/alpha/include/asm/perf_event.h new file mode 100644 index 000000000..5996e7a67 --- /dev/null +++ b/arch/alpha/include/asm/perf_event.h @@ -0,0 +1,4 @@ +#ifndef __ASM_ALPHA_PERF_EVENT_H +#define __ASM_ALPHA_PERF_EVENT_H + +#endif /* __ASM_ALPHA_PERF_EVENT_H */ diff --git a/arch/alpha/include/asm/pgalloc.h b/arch/alpha/include/asm/pgalloc.h new file mode 100644 index 000000000..aab14a019 --- /dev/null +++ b/arch/alpha/include/asm/pgalloc.h @@ -0,0 +1,91 @@ +#ifndef _ALPHA_PGALLOC_H +#define _ALPHA_PGALLOC_H + +#include <linux/mm.h> +#include <linux/mmzone.h> + +/* + * Allocate and free page tables. The xxx_kernel() versions are + * used to allocate a kernel page table - this turns on ASN bits + * if any. + */ + +static inline void +pmd_populate(struct mm_struct *mm, pmd_t *pmd, pgtable_t pte) +{ + pmd_set(pmd, (pte_t *)(page_to_pa(pte) + PAGE_OFFSET)); +} +#define pmd_pgtable(pmd) pmd_page(pmd) + +static inline void +pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, pte_t *pte) +{ + pmd_set(pmd, pte); +} + +static inline void +pgd_populate(struct mm_struct *mm, pgd_t *pgd, pmd_t *pmd) +{ + pgd_set(pgd, pmd); +} + +extern pgd_t *pgd_alloc(struct mm_struct *mm); + +static inline void +pgd_free(struct mm_struct *mm, pgd_t *pgd) +{ + free_page((unsigned long)pgd); +} + +static inline pmd_t * +pmd_alloc_one(struct mm_struct *mm, unsigned long address) +{ + pmd_t *ret = (pmd_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO); + return ret; +} + +static inline void +pmd_free(struct mm_struct *mm, pmd_t *pmd) +{ + free_page((unsigned long)pmd); +} + +static inline pte_t * +pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address) +{ + pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO); + return pte; +} + +static inline void +pte_free_kernel(struct mm_struct *mm, pte_t *pte) +{ + free_page((unsigned long)pte); +} + +static inline pgtable_t +pte_alloc_one(struct mm_struct *mm, unsigned long address) +{ + pte_t *pte = pte_alloc_one_kernel(mm, address); + struct page *page; + + if (!pte) + return NULL; + page = virt_to_page(pte); + if (!pgtable_page_ctor(page)) { + __free_page(page); + return NULL; + } + return page; +} + +static inline void +pte_free(struct mm_struct *mm, pgtable_t page) +{ + pgtable_page_dtor(page); + __free_page(page); +} + +#define check_pgt_cache() do { } while (0) + +#endif /* _ALPHA_PGALLOC_H */ diff --git a/arch/alpha/include/asm/pgtable.h b/arch/alpha/include/asm/pgtable.h new file mode 100644 index 000000000..a9a119592 --- /dev/null +++ b/arch/alpha/include/asm/pgtable.h @@ -0,0 +1,369 @@ +#ifndef _ALPHA_PGTABLE_H +#define _ALPHA_PGTABLE_H + +#include <asm-generic/4level-fixup.h> + +/* + * This file contains the functions and defines necessary to modify and use + * the Alpha page table tree. + * + * This hopefully works with any standard Alpha page-size, as defined + * in <asm/page.h> (currently 8192). + */ +#include <linux/mmzone.h> + +#include <asm/page.h> +#include <asm/processor.h> /* For TASK_SIZE */ +#include <asm/machvec.h> +#include <asm/setup.h> + +struct mm_struct; +struct vm_area_struct; + +/* Certain architectures need to do special things when PTEs + * within a page table are directly modified. Thus, the following + * hook is made available. + */ +#define set_pte(pteptr, pteval) ((*(pteptr)) = (pteval)) +#define set_pte_at(mm,addr,ptep,pteval) set_pte(ptep,pteval) + +/* PMD_SHIFT determines the size of the area a second-level page table can map */ +#define PMD_SHIFT (PAGE_SHIFT + (PAGE_SHIFT-3)) +#define PMD_SIZE (1UL << PMD_SHIFT) +#define PMD_MASK (~(PMD_SIZE-1)) + +/* PGDIR_SHIFT determines what a third-level page table entry can map */ +#define PGDIR_SHIFT (PAGE_SHIFT + 2*(PAGE_SHIFT-3)) +#define PGDIR_SIZE (1UL << PGDIR_SHIFT) +#define PGDIR_MASK (~(PGDIR_SIZE-1)) + +/* + * Entries per page directory level: the Alpha is three-level, with + * all levels having a one-page page table. + */ +#define PTRS_PER_PTE (1UL << (PAGE_SHIFT-3)) +#define PTRS_PER_PMD (1UL << (PAGE_SHIFT-3)) +#define PTRS_PER_PGD (1UL << (PAGE_SHIFT-3)) +#define USER_PTRS_PER_PGD (TASK_SIZE / PGDIR_SIZE) +#define FIRST_USER_ADDRESS 0UL + +/* Number of pointers that fit on a page: this will go away. */ +#define PTRS_PER_PAGE (1UL << (PAGE_SHIFT-3)) + +#ifdef CONFIG_ALPHA_LARGE_VMALLOC +#define VMALLOC_START 0xfffffe0000000000 +#else +#define VMALLOC_START (-2*PGDIR_SIZE) +#endif +#define VMALLOC_END (-PGDIR_SIZE) + +/* + * OSF/1 PAL-code-imposed page table bits + */ +#define _PAGE_VALID 0x0001 +#define _PAGE_FOR 0x0002 /* used for page protection (fault on read) */ +#define _PAGE_FOW 0x0004 /* used for page protection (fault on write) */ +#define _PAGE_FOE 0x0008 /* used for page protection (fault on exec) */ +#define _PAGE_ASM 0x0010 +#define _PAGE_KRE 0x0100 /* xxx - see below on the "accessed" bit */ +#define _PAGE_URE 0x0200 /* xxx */ +#define _PAGE_KWE 0x1000 /* used to do the dirty bit in software */ +#define _PAGE_UWE 0x2000 /* used to do the dirty bit in software */ + +/* .. and these are ours ... */ +#define _PAGE_DIRTY 0x20000 +#define _PAGE_ACCESSED 0x40000 + +/* + * NOTE! The "accessed" bit isn't necessarily exact: it can be kept exactly + * by software (use the KRE/URE/KWE/UWE bits appropriately), but I'll fake it. + * Under Linux/AXP, the "accessed" bit just means "read", and I'll just use + * the KRE/URE bits to watch for it. That way we don't need to overload the + * KWE/UWE bits with both handling dirty and accessed. + * + * Note that the kernel uses the accessed bit just to check whether to page + * out a page or not, so it doesn't have to be exact anyway. + */ + +#define __DIRTY_BITS (_PAGE_DIRTY | _PAGE_KWE | _PAGE_UWE) +#define __ACCESS_BITS (_PAGE_ACCESSED | _PAGE_KRE | _PAGE_URE) + +#define _PFN_MASK 0xFFFFFFFF00000000UL + +#define _PAGE_TABLE (_PAGE_VALID | __DIRTY_BITS | __ACCESS_BITS) +#define _PAGE_CHG_MASK (_PFN_MASK | __DIRTY_BITS | __ACCESS_BITS) + +/* + * All the normal masks have the "page accessed" bits on, as any time they are used, + * the page is accessed. They are cleared only by the page-out routines + */ +#define PAGE_NONE __pgprot(_PAGE_VALID | __ACCESS_BITS | _PAGE_FOR | _PAGE_FOW | _PAGE_FOE) +#define PAGE_SHARED __pgprot(_PAGE_VALID | __ACCESS_BITS) +#define PAGE_COPY __pgprot(_PAGE_VALID | __ACCESS_BITS | _PAGE_FOW) +#define PAGE_READONLY __pgprot(_PAGE_VALID | __ACCESS_BITS | _PAGE_FOW) +#define PAGE_KERNEL __pgprot(_PAGE_VALID | _PAGE_ASM | _PAGE_KRE | _PAGE_KWE) + +#define _PAGE_NORMAL(x) __pgprot(_PAGE_VALID | __ACCESS_BITS | (x)) + +#define _PAGE_P(x) _PAGE_NORMAL((x) | (((x) & _PAGE_FOW)?0:_PAGE_FOW)) +#define _PAGE_S(x) _PAGE_NORMAL(x) + +/* + * The hardware can handle write-only mappings, but as the Alpha + * architecture does byte-wide writes with a read-modify-write + * sequence, it's not practical to have write-without-read privs. + * Thus the "-w- -> rw-" and "-wx -> rwx" mapping here (and in + * arch/alpha/mm/fault.c) + */ + /* xwr */ +#define __P000 _PAGE_P(_PAGE_FOE | _PAGE_FOW | _PAGE_FOR) +#define __P001 _PAGE_P(_PAGE_FOE | _PAGE_FOW) +#define __P010 _PAGE_P(_PAGE_FOE) +#define __P011 _PAGE_P(_PAGE_FOE) +#define __P100 _PAGE_P(_PAGE_FOW | _PAGE_FOR) +#define __P101 _PAGE_P(_PAGE_FOW) +#define __P110 _PAGE_P(0) +#define __P111 _PAGE_P(0) + +#define __S000 _PAGE_S(_PAGE_FOE | _PAGE_FOW | _PAGE_FOR) +#define __S001 _PAGE_S(_PAGE_FOE | _PAGE_FOW) +#define __S010 _PAGE_S(_PAGE_FOE) +#define __S011 _PAGE_S(_PAGE_FOE) +#define __S100 _PAGE_S(_PAGE_FOW | _PAGE_FOR) +#define __S101 _PAGE_S(_PAGE_FOW) +#define __S110 _PAGE_S(0) +#define __S111 _PAGE_S(0) + +/* + * pgprot_noncached() is only for infiniband pci support, and a real + * implementation for RAM would be more complicated. + */ +#define pgprot_noncached(prot) (prot) + +/* + * BAD_PAGETABLE is used when we need a bogus page-table, while + * BAD_PAGE is used for a bogus page. + * + * ZERO_PAGE is a global shared page that is always zero: used + * for zero-mapped memory areas etc.. + */ +extern pte_t __bad_page(void); +extern pmd_t * __bad_pagetable(void); + +extern unsigned long __zero_page(void); + +#define BAD_PAGETABLE __bad_pagetable() +#define BAD_PAGE __bad_page() +#define ZERO_PAGE(vaddr) (virt_to_page(ZERO_PGE)) + +/* number of bits that fit into a memory pointer */ +#define BITS_PER_PTR (8*sizeof(unsigned long)) + +/* to align the pointer to a pointer address */ +#define PTR_MASK (~(sizeof(void*)-1)) + +/* sizeof(void*)==1<<SIZEOF_PTR_LOG2 */ +#define SIZEOF_PTR_LOG2 3 + +/* to find an entry in a page-table */ +#define PAGE_PTR(address) \ + ((unsigned long)(address)>>(PAGE_SHIFT-SIZEOF_PTR_LOG2)&PTR_MASK&~PAGE_MASK) + +/* + * On certain platforms whose physical address space can overlap KSEG, + * namely EV6 and above, we must re-twiddle the physaddr to restore the + * correct high-order bits. + * + * This is extremely confusing until you realize that this is actually + * just working around a userspace bug. The X server was intending to + * provide the physical address but instead provided the KSEG address. + * Or tried to, except it's not representable. + * + * On Tsunami there's nothing meaningful at 0x40000000000, so this is + * a safe thing to do. Come the first core logic that does put something + * in this area -- memory or whathaveyou -- then this hack will have + * to go away. So be prepared! + */ + +#if defined(CONFIG_ALPHA_GENERIC) && defined(USE_48_BIT_KSEG) +#error "EV6-only feature in a generic kernel" +#endif +#if defined(CONFIG_ALPHA_GENERIC) || \ + (defined(CONFIG_ALPHA_EV6) && !defined(USE_48_BIT_KSEG)) +#define KSEG_PFN (0xc0000000000UL >> PAGE_SHIFT) +#define PHYS_TWIDDLE(pfn) \ + ((((pfn) & KSEG_PFN) == (0x40000000000UL >> PAGE_SHIFT)) \ + ? ((pfn) ^= KSEG_PFN) : (pfn)) +#else +#define PHYS_TWIDDLE(pfn) (pfn) +#endif + +/* + * Conversion functions: convert a page and protection to a page entry, + * and a page entry and page directory to the page they refer to. + */ +#ifndef CONFIG_DISCONTIGMEM +#define page_to_pa(page) (((page) - mem_map) << PAGE_SHIFT) + +#define pte_pfn(pte) (pte_val(pte) >> 32) +#define pte_page(pte) pfn_to_page(pte_pfn(pte)) +#define mk_pte(page, pgprot) \ +({ \ + pte_t pte; \ + \ + pte_val(pte) = (page_to_pfn(page) << 32) | pgprot_val(pgprot); \ + pte; \ +}) +#endif + +extern inline pte_t pfn_pte(unsigned long physpfn, pgprot_t pgprot) +{ pte_t pte; pte_val(pte) = (PHYS_TWIDDLE(physpfn) << 32) | pgprot_val(pgprot); return pte; } + +extern inline pte_t pte_modify(pte_t pte, pgprot_t newprot) +{ pte_val(pte) = (pte_val(pte) & _PAGE_CHG_MASK) | pgprot_val(newprot); return pte; } + +extern inline void pmd_set(pmd_t * pmdp, pte_t * ptep) +{ pmd_val(*pmdp) = _PAGE_TABLE | ((((unsigned long) ptep) - PAGE_OFFSET) << (32-PAGE_SHIFT)); } + +extern inline void pgd_set(pgd_t * pgdp, pmd_t * pmdp) +{ pgd_val(*pgdp) = _PAGE_TABLE | ((((unsigned long) pmdp) - PAGE_OFFSET) << (32-PAGE_SHIFT)); } + + +extern inline unsigned long +pmd_page_vaddr(pmd_t pmd) +{ + return ((pmd_val(pmd) & _PFN_MASK) >> (32-PAGE_SHIFT)) + PAGE_OFFSET; +} + +#ifndef CONFIG_DISCONTIGMEM +#define pmd_page(pmd) (mem_map + ((pmd_val(pmd) & _PFN_MASK) >> 32)) +#define pgd_page(pgd) (mem_map + ((pgd_val(pgd) & _PFN_MASK) >> 32)) +#endif + +extern inline unsigned long pgd_page_vaddr(pgd_t pgd) +{ return PAGE_OFFSET + ((pgd_val(pgd) & _PFN_MASK) >> (32-PAGE_SHIFT)); } + +extern inline int pte_none(pte_t pte) { return !pte_val(pte); } +extern inline int pte_present(pte_t pte) { return pte_val(pte) & _PAGE_VALID; } +extern inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) +{ + pte_val(*ptep) = 0; +} + +extern inline int pmd_none(pmd_t pmd) { return !pmd_val(pmd); } +extern inline int pmd_bad(pmd_t pmd) { return (pmd_val(pmd) & ~_PFN_MASK) != _PAGE_TABLE; } +extern inline int pmd_present(pmd_t pmd) { return pmd_val(pmd) & _PAGE_VALID; } +extern inline void pmd_clear(pmd_t * pmdp) { pmd_val(*pmdp) = 0; } + +extern inline int pgd_none(pgd_t pgd) { return !pgd_val(pgd); } +extern inline int pgd_bad(pgd_t pgd) { return (pgd_val(pgd) & ~_PFN_MASK) != _PAGE_TABLE; } +extern inline int pgd_present(pgd_t pgd) { return pgd_val(pgd) & _PAGE_VALID; } +extern inline void pgd_clear(pgd_t * pgdp) { pgd_val(*pgdp) = 0; } + +/* + * The following only work if pte_present() is true. + * Undefined behaviour if not.. + */ +extern inline int pte_write(pte_t pte) { return !(pte_val(pte) & _PAGE_FOW); } +extern inline int pte_dirty(pte_t pte) { return pte_val(pte) & _PAGE_DIRTY; } +extern inline int pte_young(pte_t pte) { return pte_val(pte) & _PAGE_ACCESSED; } +extern inline int pte_special(pte_t pte) { return 0; } + +extern inline pte_t pte_wrprotect(pte_t pte) { pte_val(pte) |= _PAGE_FOW; return pte; } +extern inline pte_t pte_mkclean(pte_t pte) { pte_val(pte) &= ~(__DIRTY_BITS); return pte; } +extern inline pte_t pte_mkold(pte_t pte) { pte_val(pte) &= ~(__ACCESS_BITS); return pte; } +extern inline pte_t pte_mkwrite(pte_t pte) { pte_val(pte) &= ~_PAGE_FOW; return pte; } +extern inline pte_t pte_mkdirty(pte_t pte) { pte_val(pte) |= __DIRTY_BITS; return pte; } +extern inline pte_t pte_mkyoung(pte_t pte) { pte_val(pte) |= __ACCESS_BITS; return pte; } +extern inline pte_t pte_mkspecial(pte_t pte) { return pte; } + +#define PAGE_DIR_OFFSET(tsk,address) pgd_offset((tsk),(address)) + +/* 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) & (PTRS_PER_PGD-1)) +#define pgd_offset(mm, address) ((mm)->pgd+pgd_index(address)) + +/* + * The smp_read_barrier_depends() in the following functions are required to + * order the load of *dir (the pointer in the top level page table) with any + * subsequent load of the returned pmd_t *ret (ret is data dependent on *dir). + * + * If this ordering is not enforced, the CPU might load an older value of + * *ret, which may be uninitialized data. See mm/memory.c:__pte_alloc for + * more details. + * + * Note that we never change the mm->pgd pointer after the task is running, so + * pgd_offset does not require such a barrier. + */ + +/* Find an entry in the second-level page table.. */ +extern inline pmd_t * pmd_offset(pgd_t * dir, unsigned long address) +{ + pmd_t *ret = (pmd_t *) pgd_page_vaddr(*dir) + ((address >> PMD_SHIFT) & (PTRS_PER_PAGE - 1)); + smp_read_barrier_depends(); /* see above */ + return ret; +} + +/* Find an entry in the third-level page table.. */ +extern inline pte_t * pte_offset_kernel(pmd_t * dir, unsigned long address) +{ + pte_t *ret = (pte_t *) pmd_page_vaddr(*dir) + + ((address >> PAGE_SHIFT) & (PTRS_PER_PAGE - 1)); + smp_read_barrier_depends(); /* see above */ + return ret; +} + +#define pte_offset_map(dir,addr) pte_offset_kernel((dir),(addr)) +#define pte_unmap(pte) do { } while (0) + +extern pgd_t swapper_pg_dir[1024]; + +/* + * The Alpha doesn't have any external MMU info: the kernel page + * tables contain all the necessary information. + */ +extern inline void update_mmu_cache(struct vm_area_struct * vma, + unsigned long address, pte_t *ptep) +{ +} + +/* + * Non-present pages: high 24 bits are offset, next 8 bits type, + * low 32 bits zero. + */ +extern inline pte_t mk_swap_pte(unsigned long type, unsigned long offset) +{ pte_t pte; pte_val(pte) = (type << 32) | (offset << 40); return pte; } + +#define __swp_type(x) (((x).val >> 32) & 0xff) +#define __swp_offset(x) ((x).val >> 40) +#define __swp_entry(type, off) ((swp_entry_t) { pte_val(mk_swap_pte((type), (off))) }) +#define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) }) +#define __swp_entry_to_pte(x) ((pte_t) { (x).val }) + +#ifndef CONFIG_DISCONTIGMEM +#define kern_addr_valid(addr) (1) +#endif + +#define pte_ERROR(e) \ + printk("%s:%d: bad pte %016lx.\n", __FILE__, __LINE__, pte_val(e)) +#define pmd_ERROR(e) \ + printk("%s:%d: bad pmd %016lx.\n", __FILE__, __LINE__, pmd_val(e)) +#define pgd_ERROR(e) \ + printk("%s:%d: bad pgd %016lx.\n", __FILE__, __LINE__, pgd_val(e)) + +extern void paging_init(void); + +#include <asm-generic/pgtable.h> + +/* + * No page table caches to initialise + */ +#define pgtable_cache_init() do { } while (0) + +/* We have our own get_unmapped_area to cope with ADDR_LIMIT_32BIT. */ +#define HAVE_ARCH_UNMAPPED_AREA + +#endif /* _ALPHA_PGTABLE_H */ diff --git a/arch/alpha/include/asm/processor.h b/arch/alpha/include/asm/processor.h new file mode 100644 index 000000000..43a7559c4 --- /dev/null +++ b/arch/alpha/include/asm/processor.h @@ -0,0 +1,89 @@ +/* + * include/asm-alpha/processor.h + * + * Copyright (C) 1994 Linus Torvalds + */ + +#ifndef __ASM_ALPHA_PROCESSOR_H +#define __ASM_ALPHA_PROCESSOR_H + +#include <linux/personality.h> /* for ADDR_LIMIT_32BIT */ + +/* + * Returns current instruction pointer ("program counter"). + */ +#define current_text_addr() \ + ({ void *__pc; __asm__ ("br %0,.+4" : "=r"(__pc)); __pc; }) + +/* + * We have a 42-bit user address space: 4TB user VM... + */ +#define TASK_SIZE (0x40000000000UL) + +#define STACK_TOP \ + (current->personality & ADDR_LIMIT_32BIT ? 0x80000000 : 0x00120000000UL) + +#define STACK_TOP_MAX 0x00120000000UL + +/* This decides where the kernel will search for a free chunk of vm + * space during mmap's. + */ +#define TASK_UNMAPPED_BASE \ + ((current->personality & ADDR_LIMIT_32BIT) ? 0x40000000 : TASK_SIZE / 2) + +typedef struct { + unsigned long seg; +} mm_segment_t; + +/* This is dead. Everything has been moved to thread_info. */ +struct thread_struct { }; +#define INIT_THREAD { } + +/* Return saved PC of a blocked thread. */ +struct task_struct; +extern unsigned long thread_saved_pc(struct task_struct *); + +/* Do necessary setup to start up a newly executed thread. */ +struct pt_regs; +extern void start_thread(struct pt_regs *, unsigned long, unsigned long); + +/* Free all resources held by a thread. */ +extern void release_thread(struct task_struct *); + +unsigned long get_wchan(struct task_struct *p); + +#define KSTK_EIP(tsk) (task_pt_regs(tsk)->pc) + +#define KSTK_ESP(tsk) \ + ((tsk) == current ? rdusp() : task_thread_info(tsk)->pcb.usp) + +#define cpu_relax() barrier() +#define cpu_relax_lowlatency() cpu_relax() + +#define ARCH_HAS_PREFETCH +#define ARCH_HAS_PREFETCHW +#define ARCH_HAS_SPINLOCK_PREFETCH + +#ifndef CONFIG_SMP +/* Nothing to prefetch. */ +#define spin_lock_prefetch(lock) do { } while (0) +#endif + +extern inline void prefetch(const void *ptr) +{ + __builtin_prefetch(ptr, 0, 3); +} + +extern inline void prefetchw(const void *ptr) +{ + __builtin_prefetch(ptr, 1, 3); +} + +#ifdef CONFIG_SMP +extern inline void spin_lock_prefetch(const void *ptr) +{ + __builtin_prefetch(ptr, 1, 3); +} +#endif + +#endif /* __ASM_ALPHA_PROCESSOR_H */ diff --git a/arch/alpha/include/asm/ptrace.h b/arch/alpha/include/asm/ptrace.h new file mode 100644 index 000000000..9047c2fe8 --- /dev/null +++ b/arch/alpha/include/asm/ptrace.h @@ -0,0 +1,27 @@ +#ifndef _ASMAXP_PTRACE_H +#define _ASMAXP_PTRACE_H + +#include <uapi/asm/ptrace.h> + + +#define arch_has_single_step() (1) +#define user_mode(regs) (((regs)->ps & 8) != 0) +#define instruction_pointer(regs) ((regs)->pc) +#define profile_pc(regs) instruction_pointer(regs) +#define current_user_stack_pointer() rdusp() + +#define task_pt_regs(task) \ + ((struct pt_regs *) (task_stack_page(task) + 2*PAGE_SIZE) - 1) + +#define current_pt_regs() \ + ((struct pt_regs *) ((char *)current_thread_info() + 2*PAGE_SIZE) - 1) +#define signal_pt_regs current_pt_regs + +#define force_successful_syscall_return() (current_pt_regs()->r0 = 0) + +static inline unsigned long regs_return_value(struct pt_regs *regs) +{ + return regs->r0; +} + +#endif diff --git a/arch/alpha/include/asm/rtc.h b/arch/alpha/include/asm/rtc.h new file mode 100644 index 000000000..f71c3b0ed --- /dev/null +++ b/arch/alpha/include/asm/rtc.h @@ -0,0 +1 @@ +#include <asm-generic/rtc.h> diff --git a/arch/alpha/include/asm/rwsem.h b/arch/alpha/include/asm/rwsem.h new file mode 100644 index 000000000..a83bbea62 --- /dev/null +++ b/arch/alpha/include/asm/rwsem.h @@ -0,0 +1,223 @@ +#ifndef _ALPHA_RWSEM_H +#define _ALPHA_RWSEM_H + +/* + * Written by Ivan Kokshaysky <ink@jurassic.park.msu.ru>, 2001. + * Based on asm-alpha/semaphore.h and asm-i386/rwsem.h + */ + +#ifndef _LINUX_RWSEM_H +#error "please don't include asm/rwsem.h directly, use linux/rwsem.h instead" +#endif + +#ifdef __KERNEL__ + +#include <linux/compiler.h> + +#define RWSEM_UNLOCKED_VALUE 0x0000000000000000L +#define RWSEM_ACTIVE_BIAS 0x0000000000000001L +#define RWSEM_ACTIVE_MASK 0x00000000ffffffffL +#define RWSEM_WAITING_BIAS (-0x0000000100000000L) +#define RWSEM_ACTIVE_READ_BIAS RWSEM_ACTIVE_BIAS +#define RWSEM_ACTIVE_WRITE_BIAS (RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS) + +static inline void __down_read(struct rw_semaphore *sem) +{ + long oldcount; +#ifndef CONFIG_SMP + oldcount = sem->count; + sem->count += RWSEM_ACTIVE_READ_BIAS; +#else + long temp; + __asm__ __volatile__( + "1: ldq_l %0,%1\n" + " addq %0,%3,%2\n" + " stq_c %2,%1\n" + " beq %2,2f\n" + " mb\n" + ".subsection 2\n" + "2: br 1b\n" + ".previous" + :"=&r" (oldcount), "=m" (sem->count), "=&r" (temp) + :"Ir" (RWSEM_ACTIVE_READ_BIAS), "m" (sem->count) : "memory"); +#endif + if (unlikely(oldcount < 0)) + rwsem_down_read_failed(sem); +} + +/* + * trylock for reading -- returns 1 if successful, 0 if contention + */ +static inline int __down_read_trylock(struct rw_semaphore *sem) +{ + long old, new, res; + + res = sem->count; + do { + new = res + RWSEM_ACTIVE_READ_BIAS; + if (new <= 0) + break; + old = res; + res = cmpxchg(&sem->count, old, new); + } while (res != old); + return res >= 0 ? 1 : 0; +} + +static inline void __down_write(struct rw_semaphore *sem) +{ + long oldcount; +#ifndef CONFIG_SMP + oldcount = sem->count; + sem->count += RWSEM_ACTIVE_WRITE_BIAS; +#else + long temp; + __asm__ __volatile__( + "1: ldq_l %0,%1\n" + " addq %0,%3,%2\n" + " stq_c %2,%1\n" + " beq %2,2f\n" + " mb\n" + ".subsection 2\n" + "2: br 1b\n" + ".previous" + :"=&r" (oldcount), "=m" (sem->count), "=&r" (temp) + :"Ir" (RWSEM_ACTIVE_WRITE_BIAS), "m" (sem->count) : "memory"); +#endif + if (unlikely(oldcount)) + rwsem_down_write_failed(sem); +} + +/* + * trylock for writing -- returns 1 if successful, 0 if contention + */ +static inline int __down_write_trylock(struct rw_semaphore *sem) +{ + long ret = cmpxchg(&sem->count, RWSEM_UNLOCKED_VALUE, + RWSEM_ACTIVE_WRITE_BIAS); + if (ret == RWSEM_UNLOCKED_VALUE) + return 1; + return 0; +} + +static inline void __up_read(struct rw_semaphore *sem) +{ + long oldcount; +#ifndef CONFIG_SMP + oldcount = sem->count; + sem->count -= RWSEM_ACTIVE_READ_BIAS; +#else + long temp; + __asm__ __volatile__( + " mb\n" + "1: ldq_l %0,%1\n" + " subq %0,%3,%2\n" + " stq_c %2,%1\n" + " beq %2,2f\n" + ".subsection 2\n" + "2: br 1b\n" + ".previous" + :"=&r" (oldcount), "=m" (sem->count), "=&r" (temp) + :"Ir" (RWSEM_ACTIVE_READ_BIAS), "m" (sem->count) : "memory"); +#endif + if (unlikely(oldcount < 0)) + if ((int)oldcount - RWSEM_ACTIVE_READ_BIAS == 0) + rwsem_wake(sem); +} + +static inline void __up_write(struct rw_semaphore *sem) +{ + long count; +#ifndef CONFIG_SMP + sem->count -= RWSEM_ACTIVE_WRITE_BIAS; + count = sem->count; +#else + long temp; + __asm__ __volatile__( + " mb\n" + "1: ldq_l %0,%1\n" + " subq %0,%3,%2\n" + " stq_c %2,%1\n" + " beq %2,2f\n" + " subq %0,%3,%0\n" + ".subsection 2\n" + "2: br 1b\n" + ".previous" + :"=&r" (count), "=m" (sem->count), "=&r" (temp) + :"Ir" (RWSEM_ACTIVE_WRITE_BIAS), "m" (sem->count) : "memory"); +#endif + if (unlikely(count)) + if ((int)count == 0) + rwsem_wake(sem); +} + +/* + * downgrade write lock to read lock + */ +static inline void __downgrade_write(struct rw_semaphore *sem) +{ + long oldcount; +#ifndef CONFIG_SMP + oldcount = sem->count; + sem->count -= RWSEM_WAITING_BIAS; +#else + long temp; + __asm__ __volatile__( + "1: ldq_l %0,%1\n" + " addq %0,%3,%2\n" + " stq_c %2,%1\n" + " beq %2,2f\n" + " mb\n" + ".subsection 2\n" + "2: br 1b\n" + ".previous" + :"=&r" (oldcount), "=m" (sem->count), "=&r" (temp) + :"Ir" (-RWSEM_WAITING_BIAS), "m" (sem->count) : "memory"); +#endif + if (unlikely(oldcount < 0)) + rwsem_downgrade_wake(sem); +} + +static inline void rwsem_atomic_add(long val, struct rw_semaphore *sem) +{ +#ifndef CONFIG_SMP + sem->count += val; +#else + long temp; + __asm__ __volatile__( + "1: ldq_l %0,%1\n" + " addq %0,%2,%0\n" + " stq_c %0,%1\n" + " beq %0,2f\n" + ".subsection 2\n" + "2: br 1b\n" + ".previous" + :"=&r" (temp), "=m" (sem->count) + :"Ir" (val), "m" (sem->count)); +#endif +} + +static inline long rwsem_atomic_update(long val, struct rw_semaphore *sem) +{ +#ifndef CONFIG_SMP + sem->count += val; + return sem->count; +#else + long ret, temp; + __asm__ __volatile__( + "1: ldq_l %0,%1\n" + " addq %0,%3,%2\n" + " addq %0,%3,%0\n" + " stq_c %2,%1\n" + " beq %2,2f\n" + ".subsection 2\n" + "2: br 1b\n" + ".previous" + :"=&r" (ret), "=m" (sem->count), "=&r" (temp) + :"Ir" (val), "m" (sem->count)); + + return ret; +#endif +} + +#endif /* __KERNEL__ */ +#endif /* _ALPHA_RWSEM_H */ diff --git a/arch/alpha/include/asm/segment.h b/arch/alpha/include/asm/segment.h new file mode 100644 index 000000000..0453d97da --- /dev/null +++ b/arch/alpha/include/asm/segment.h @@ -0,0 +1,6 @@ +#ifndef __ALPHA_SEGMENT_H +#define __ALPHA_SEGMENT_H + +/* Only here because we have some old header files that expect it.. */ + +#endif diff --git a/arch/alpha/include/asm/serial.h b/arch/alpha/include/asm/serial.h new file mode 100644 index 000000000..9d263e8d8 --- /dev/null +++ b/arch/alpha/include/asm/serial.h @@ -0,0 +1,29 @@ +/* + * include/asm-alpha/serial.h + */ + + +/* + * This assumes you have a 1.8432 MHz clock for your UART. + * + * It'd be nice if someone built a serial card with a 24.576 MHz + * clock, since the 16550A is capable of handling a top speed of 1.5 + * megabits/second; but this requires the faster clock. + */ +#define BASE_BAUD ( 1843200 / 16 ) + +/* Standard COM flags (except for COM4, because of the 8514 problem) */ +#ifdef CONFIG_SERIAL_DETECT_IRQ +#define STD_COM_FLAGS (ASYNC_BOOT_AUTOCONF | ASYNC_SKIP_TEST | ASYNC_AUTO_IRQ) +#define STD_COM4_FLAGS (ASYNC_BOOT_AUTOCONF | ASYNC_AUTO_IRQ) +#else +#define STD_COM_FLAGS (ASYNC_BOOT_AUTOCONF | ASYNC_SKIP_TEST) +#define STD_COM4_FLAGS ASYNC_BOOT_AUTOCONF +#endif + +#define SERIAL_PORT_DFNS \ + /* UART CLK PORT IRQ FLAGS */ \ + { 0, BASE_BAUD, 0x3F8, 4, STD_COM_FLAGS }, /* ttyS0 */ \ + { 0, BASE_BAUD, 0x2F8, 3, STD_COM_FLAGS }, /* ttyS1 */ \ + { 0, BASE_BAUD, 0x3E8, 4, STD_COM_FLAGS }, /* ttyS2 */ \ + { 0, BASE_BAUD, 0x2E8, 3, STD_COM4_FLAGS }, /* ttyS3 */ diff --git a/arch/alpha/include/asm/sfp-machine.h b/arch/alpha/include/asm/sfp-machine.h new file mode 100644 index 000000000..5fe63afbd --- /dev/null +++ b/arch/alpha/include/asm/sfp-machine.h @@ -0,0 +1,82 @@ +/* Machine-dependent software floating-point definitions. + Alpha kernel version. + Copyright (C) 1997,1998,1999 Free Software Foundation, Inc. + This file is part of the GNU C Library. + Contributed by Richard Henderson (rth@cygnus.com), + Jakub Jelinek (jakub@redhat.com) and + David S. Miller (davem@redhat.com). + + The GNU C Library is free software; you can redistribute it and/or + modify it under the terms of the GNU Library General Public License as + published by the Free Software Foundation; either version 2 of the + License, or (at your option) any later version. + + The GNU C Library is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + Library General Public License for more details. + + You should have received a copy of the GNU Library General Public + License along with the GNU C Library; see the file COPYING.LIB. If + not, write to the Free Software Foundation, Inc., + 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. */ + +#ifndef _SFP_MACHINE_H +#define _SFP_MACHINE_H + +#define _FP_W_TYPE_SIZE 64 +#define _FP_W_TYPE unsigned long +#define _FP_WS_TYPE signed long +#define _FP_I_TYPE long + +#define _FP_MUL_MEAT_S(R,X,Y) \ + _FP_MUL_MEAT_1_imm(_FP_WFRACBITS_S,R,X,Y) +#define _FP_MUL_MEAT_D(R,X,Y) \ + _FP_MUL_MEAT_1_wide(_FP_WFRACBITS_D,R,X,Y,umul_ppmm) +#define _FP_MUL_MEAT_Q(R,X,Y) \ + _FP_MUL_MEAT_2_wide(_FP_WFRACBITS_Q,R,X,Y,umul_ppmm) + +#define _FP_DIV_MEAT_S(R,X,Y) _FP_DIV_MEAT_1_imm(S,R,X,Y,_FP_DIV_HELP_imm) +#define _FP_DIV_MEAT_D(R,X,Y) _FP_DIV_MEAT_1_udiv(D,R,X,Y) +#define _FP_DIV_MEAT_Q(R,X,Y) _FP_DIV_MEAT_2_udiv(Q,R,X,Y) + +#define _FP_NANFRAC_S _FP_QNANBIT_S +#define _FP_NANFRAC_D _FP_QNANBIT_D +#define _FP_NANFRAC_Q _FP_QNANBIT_Q +#define _FP_NANSIGN_S 1 +#define _FP_NANSIGN_D 1 +#define _FP_NANSIGN_Q 1 + +#define _FP_KEEPNANFRACP 1 + +/* Alpha Architecture Handbook, 4.7.10.4 sais that + * we should prefer any type of NaN in Fb, then Fa. + */ +#define _FP_CHOOSENAN(fs, wc, R, X, Y, OP) \ + do { \ + R##_s = Y##_s; \ + _FP_FRAC_COPY_##wc(R,X); \ + R##_c = FP_CLS_NAN; \ + } while (0) + +/* Obtain the current rounding mode. */ +#define FP_ROUNDMODE mode +#define FP_RND_NEAREST (FPCR_DYN_NORMAL >> FPCR_DYN_SHIFT) +#define FP_RND_ZERO (FPCR_DYN_CHOPPED >> FPCR_DYN_SHIFT) +#define FP_RND_PINF (FPCR_DYN_PLUS >> FPCR_DYN_SHIFT) +#define FP_RND_MINF (FPCR_DYN_MINUS >> FPCR_DYN_SHIFT) + +/* Exception flags. */ +#define FP_EX_INVALID IEEE_TRAP_ENABLE_INV +#define FP_EX_OVERFLOW IEEE_TRAP_ENABLE_OVF +#define FP_EX_UNDERFLOW IEEE_TRAP_ENABLE_UNF +#define FP_EX_DIVZERO IEEE_TRAP_ENABLE_DZE +#define FP_EX_INEXACT IEEE_TRAP_ENABLE_INE +#define FP_EX_DENORM IEEE_TRAP_ENABLE_DNO + +#define FP_DENORM_ZERO (swcr & IEEE_MAP_DMZ) + +/* We write the results always */ +#define FP_INHIBIT_RESULTS 0 + +#endif diff --git a/arch/alpha/include/asm/shmparam.h b/arch/alpha/include/asm/shmparam.h new file mode 100644 index 000000000..cc901d58a --- /dev/null +++ b/arch/alpha/include/asm/shmparam.h @@ -0,0 +1,6 @@ +#ifndef _ASMAXP_SHMPARAM_H +#define _ASMAXP_SHMPARAM_H + +#define SHMLBA PAGE_SIZE /* attach addr a multiple of this */ + +#endif /* _ASMAXP_SHMPARAM_H */ diff --git a/arch/alpha/include/asm/signal.h b/arch/alpha/include/asm/signal.h new file mode 100644 index 000000000..963f0494d --- /dev/null +++ b/arch/alpha/include/asm/signal.h @@ -0,0 +1,27 @@ +#ifndef _ASMAXP_SIGNAL_H +#define _ASMAXP_SIGNAL_H + +#include <uapi/asm/signal.h> + +/* Digital Unix defines 64 signals. Most things should be clean enough + to redefine this at will, if care is taken to make libc match. */ + +#define _NSIG 64 +#define _NSIG_BPW 64 +#define _NSIG_WORDS (_NSIG / _NSIG_BPW) + +typedef unsigned long old_sigset_t; /* at least 32 bits */ + +typedef struct { + unsigned long sig[_NSIG_WORDS]; +} sigset_t; + +struct osf_sigaction { + __sighandler_t sa_handler; + old_sigset_t sa_mask; + int sa_flags; +}; + +#define __ARCH_HAS_KA_RESTORER +#include <asm/sigcontext.h> +#endif diff --git a/arch/alpha/include/asm/smp.h b/arch/alpha/include/asm/smp.h new file mode 100644 index 000000000..c46e714aa --- /dev/null +++ b/arch/alpha/include/asm/smp.h @@ -0,0 +1,59 @@ +#ifndef __ASM_SMP_H +#define __ASM_SMP_H + +#include <linux/threads.h> +#include <linux/cpumask.h> +#include <linux/bitops.h> +#include <asm/pal.h> + +/* HACK: Cabrio WHAMI return value is bogus if more than 8 bits used.. :-( */ + +static __inline__ unsigned char +__hard_smp_processor_id(void) +{ + register unsigned char __r0 __asm__("$0"); + __asm__ __volatile__( + "call_pal %1 #whami" + : "=r"(__r0) + :"i" (PAL_whami) + : "$1", "$22", "$23", "$24", "$25"); + return __r0; +} + +#ifdef CONFIG_SMP + +#include <asm/irq.h> + +struct cpuinfo_alpha { + unsigned long loops_per_jiffy; + unsigned long last_asn; + int need_new_asn; + int asn_lock; + unsigned long ipi_count; + unsigned long prof_multiplier; + unsigned long prof_counter; + unsigned char mcheck_expected; + unsigned char mcheck_taken; + unsigned char mcheck_extra; +} __attribute__((aligned(64))); + +extern struct cpuinfo_alpha cpu_data[NR_CPUS]; + +#define hard_smp_processor_id() __hard_smp_processor_id() +#define raw_smp_processor_id() (current_thread_info()->cpu) + +extern int smp_num_cpus; + +extern void arch_send_call_function_single_ipi(int cpu); +extern void arch_send_call_function_ipi_mask(const struct cpumask *mask); + +#else /* CONFIG_SMP */ + +#define hard_smp_processor_id() 0 +#define smp_call_function_on_cpu(func,info,wait,cpu) ({ 0; }) + +#endif /* CONFIG_SMP */ + +#define NO_PROC_ID (-1) + +#endif diff --git a/arch/alpha/include/asm/socket.h b/arch/alpha/include/asm/socket.h new file mode 100644 index 000000000..8d806d80e --- /dev/null +++ b/arch/alpha/include/asm/socket.h @@ -0,0 +1,10 @@ +#ifndef _ASM_SOCKET_H +#define _ASM_SOCKET_H + +#include <uapi/asm/socket.h> + +/* O_NONBLOCK clashes with the bits used for socket types. Therefore we + * have to define SOCK_NONBLOCK to a different value here. + */ +#define SOCK_NONBLOCK 0x40000000 +#endif /* _ASM_SOCKET_H */ diff --git a/arch/alpha/include/asm/special_insns.h b/arch/alpha/include/asm/special_insns.h new file mode 100644 index 000000000..88d3452b2 --- /dev/null +++ b/arch/alpha/include/asm/special_insns.h @@ -0,0 +1,41 @@ +#ifndef __ALPHA_SPECIAL_INSNS_H +#define __ALPHA_SPECIAL_INSNS_H + +enum implver_enum { + IMPLVER_EV4, + IMPLVER_EV5, + IMPLVER_EV6 +}; + +#ifdef CONFIG_ALPHA_GENERIC +#define implver() \ +({ unsigned long __implver; \ + __asm__ ("implver %0" : "=r"(__implver)); \ + (enum implver_enum) __implver; }) +#else +/* Try to eliminate some dead code. */ +#ifdef CONFIG_ALPHA_EV4 +#define implver() IMPLVER_EV4 +#endif +#ifdef CONFIG_ALPHA_EV5 +#define implver() IMPLVER_EV5 +#endif +#if defined(CONFIG_ALPHA_EV6) +#define implver() IMPLVER_EV6 +#endif +#endif + +enum amask_enum { + AMASK_BWX = (1UL << 0), + AMASK_FIX = (1UL << 1), + AMASK_CIX = (1UL << 2), + AMASK_MAX = (1UL << 8), + AMASK_PRECISE_TRAP = (1UL << 9), +}; + +#define amask(mask) \ +({ unsigned long __amask, __input = (mask); \ + __asm__ ("amask %1,%0" : "=r"(__amask) : "rI"(__input)); \ + __amask; }) + +#endif /* __ALPHA_SPECIAL_INSNS_H */ diff --git a/arch/alpha/include/asm/spinlock.h b/arch/alpha/include/asm/spinlock.h new file mode 100644 index 000000000..37b570d01 --- /dev/null +++ b/arch/alpha/include/asm/spinlock.h @@ -0,0 +1,171 @@ +#ifndef _ALPHA_SPINLOCK_H +#define _ALPHA_SPINLOCK_H + +#include <linux/kernel.h> +#include <asm/current.h> + +/* + * Simple spin lock operations. There are two variants, one clears IRQ's + * on the local processor, one does not. + * + * We make no fairness assumptions. They have a cost. + */ + +#define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock) +#define arch_spin_is_locked(x) ((x)->lock != 0) +#define arch_spin_unlock_wait(x) \ + do { cpu_relax(); } while ((x)->lock) + +static inline void arch_spin_unlock(arch_spinlock_t * lock) +{ + mb(); + lock->lock = 0; +} + +static inline void arch_spin_lock(arch_spinlock_t * lock) +{ + long tmp; + + __asm__ __volatile__( + "1: ldl_l %0,%1\n" + " bne %0,2f\n" + " lda %0,1\n" + " stl_c %0,%1\n" + " beq %0,2f\n" + " mb\n" + ".subsection 2\n" + "2: ldl %0,%1\n" + " bne %0,2b\n" + " br 1b\n" + ".previous" + : "=&r" (tmp), "=m" (lock->lock) + : "m"(lock->lock) : "memory"); +} + +static inline int arch_spin_trylock(arch_spinlock_t *lock) +{ + return !test_and_set_bit(0, &lock->lock); +} + +/***********************************************************/ + +static inline int arch_read_can_lock(arch_rwlock_t *lock) +{ + return (lock->lock & 1) == 0; +} + +static inline int arch_write_can_lock(arch_rwlock_t *lock) +{ + return lock->lock == 0; +} + +static inline void arch_read_lock(arch_rwlock_t *lock) +{ + long regx; + + __asm__ __volatile__( + "1: ldl_l %1,%0\n" + " blbs %1,6f\n" + " subl %1,2,%1\n" + " stl_c %1,%0\n" + " beq %1,6f\n" + " mb\n" + ".subsection 2\n" + "6: ldl %1,%0\n" + " blbs %1,6b\n" + " br 1b\n" + ".previous" + : "=m" (*lock), "=&r" (regx) + : "m" (*lock) : "memory"); +} + +static inline void arch_write_lock(arch_rwlock_t *lock) +{ + long regx; + + __asm__ __volatile__( + "1: ldl_l %1,%0\n" + " bne %1,6f\n" + " lda %1,1\n" + " stl_c %1,%0\n" + " beq %1,6f\n" + " mb\n" + ".subsection 2\n" + "6: ldl %1,%0\n" + " bne %1,6b\n" + " br 1b\n" + ".previous" + : "=m" (*lock), "=&r" (regx) + : "m" (*lock) : "memory"); +} + +static inline int arch_read_trylock(arch_rwlock_t * lock) +{ + long regx; + int success; + + __asm__ __volatile__( + "1: ldl_l %1,%0\n" + " lda %2,0\n" + " blbs %1,2f\n" + " subl %1,2,%2\n" + " stl_c %2,%0\n" + " beq %2,6f\n" + "2: mb\n" + ".subsection 2\n" + "6: br 1b\n" + ".previous" + : "=m" (*lock), "=&r" (regx), "=&r" (success) + : "m" (*lock) : "memory"); + + return success; +} + +static inline int arch_write_trylock(arch_rwlock_t * lock) +{ + long regx; + int success; + + __asm__ __volatile__( + "1: ldl_l %1,%0\n" + " lda %2,0\n" + " bne %1,2f\n" + " lda %2,1\n" + " stl_c %2,%0\n" + " beq %2,6f\n" + "2: mb\n" + ".subsection 2\n" + "6: br 1b\n" + ".previous" + : "=m" (*lock), "=&r" (regx), "=&r" (success) + : "m" (*lock) : "memory"); + + return success; +} + +static inline void arch_read_unlock(arch_rwlock_t * lock) +{ + long regx; + __asm__ __volatile__( + " mb\n" + "1: ldl_l %1,%0\n" + " addl %1,2,%1\n" + " stl_c %1,%0\n" + " beq %1,6f\n" + ".subsection 2\n" + "6: br 1b\n" + ".previous" + : "=m" (*lock), "=&r" (regx) + : "m" (*lock) : "memory"); +} + +static inline void arch_write_unlock(arch_rwlock_t * lock) +{ + mb(); + lock->lock = 0; +} + +#define arch_read_lock_flags(lock, flags) arch_read_lock(lock) +#define arch_write_lock_flags(lock, flags) arch_write_lock(lock) + +#endif /* _ALPHA_SPINLOCK_H */ diff --git a/arch/alpha/include/asm/spinlock_types.h b/arch/alpha/include/asm/spinlock_types.h new file mode 100644 index 000000000..54c2afce0 --- /dev/null +++ b/arch/alpha/include/asm/spinlock_types.h @@ -0,0 +1,20 @@ +#ifndef _ALPHA_SPINLOCK_TYPES_H +#define _ALPHA_SPINLOCK_TYPES_H + +#ifndef __LINUX_SPINLOCK_TYPES_H +# error "please don't include this file directly" +#endif + +typedef struct { + volatile unsigned int lock; +} arch_spinlock_t; + +#define __ARCH_SPIN_LOCK_UNLOCKED { 0 } + +typedef struct { + volatile unsigned int lock; +} arch_rwlock_t; + +#define __ARCH_RW_LOCK_UNLOCKED { 0 } + +#endif diff --git a/arch/alpha/include/asm/string.h b/arch/alpha/include/asm/string.h new file mode 100644 index 000000000..c2911f591 --- /dev/null +++ b/arch/alpha/include/asm/string.h @@ -0,0 +1,78 @@ +#ifndef __ALPHA_STRING_H__ +#define __ALPHA_STRING_H__ + +#ifdef __KERNEL__ + +/* + * GCC of any recent vintage doesn't do stupid things with bcopy. + * EGCS 1.1 knows all about expanding memcpy inline, others don't. + * + * Similarly for a memset with data = 0. + */ + +#define __HAVE_ARCH_MEMCPY +extern void * memcpy(void *, const void *, size_t); +#define __HAVE_ARCH_MEMMOVE +extern void * memmove(void *, const void *, size_t); + +/* For backward compatibility with modules. Unused otherwise. */ +extern void * __memcpy(void *, const void *, size_t); + +#define memcpy __builtin_memcpy + +#define __HAVE_ARCH_MEMSET +extern void * __constant_c_memset(void *, unsigned long, size_t); +extern void * ___memset(void *, int, size_t); +extern void * __memset(void *, int, size_t); +extern void * memset(void *, int, size_t); + +/* For gcc 3.x, we cannot have the inline function named "memset" because + the __builtin_memset will attempt to resolve to the inline as well, + leading to a "sorry" about unimplemented recursive inlining. */ +extern inline void *__memset(void *s, int c, size_t n) +{ + if (__builtin_constant_p(c)) { + if (__builtin_constant_p(n)) { + return __builtin_memset(s, c, n); + } else { + unsigned long c8 = (c & 0xff) * 0x0101010101010101UL; + return __constant_c_memset(s, c8, n); + } + } + return ___memset(s, c, n); +} + +#define memset __memset + +#define __HAVE_ARCH_STRCPY +extern char * strcpy(char *,const char *); +#define __HAVE_ARCH_STRNCPY +extern char * strncpy(char *, const char *, size_t); +#define __HAVE_ARCH_STRCAT +extern char * strcat(char *, const char *); +#define __HAVE_ARCH_STRNCAT +extern char * strncat(char *, const char *, size_t); +#define __HAVE_ARCH_STRCHR +extern char * strchr(const char *,int); +#define __HAVE_ARCH_STRRCHR +extern char * strrchr(const char *,int); +#define __HAVE_ARCH_STRLEN +extern size_t strlen(const char *); +#define __HAVE_ARCH_MEMCHR +extern void * memchr(const void *, int, size_t); + +/* The following routine is like memset except that it writes 16-bit + aligned values. The DEST and COUNT parameters must be even for + correct operation. */ + +#define __HAVE_ARCH_MEMSETW +extern void * __memsetw(void *dest, unsigned short, size_t count); + +#define memsetw(s, c, n) \ +(__builtin_constant_p(c) \ + ? __constant_c_memset((s),0x0001000100010001UL*(unsigned short)(c),(n)) \ + : __memsetw((s),(c),(n))) + +#endif /* __KERNEL__ */ + +#endif /* __ALPHA_STRING_H__ */ diff --git a/arch/alpha/include/asm/switch_to.h b/arch/alpha/include/asm/switch_to.h new file mode 100644 index 000000000..44c0d4f2c --- /dev/null +++ b/arch/alpha/include/asm/switch_to.h @@ -0,0 +1,14 @@ +#ifndef __ALPHA_SWITCH_TO_H +#define __ALPHA_SWITCH_TO_H + + +struct task_struct; +extern struct task_struct *alpha_switch_to(unsigned long, struct task_struct *); + +#define switch_to(P,N,L) \ + do { \ + (L) = alpha_switch_to(virt_to_phys(&task_thread_info(N)->pcb), (P)); \ + check_mmu_context(); \ + } while (0) + +#endif /* __ALPHA_SWITCH_TO_H */ diff --git a/arch/alpha/include/asm/syscall.h b/arch/alpha/include/asm/syscall.h new file mode 100644 index 000000000..88d28eb2a --- /dev/null +++ b/arch/alpha/include/asm/syscall.h @@ -0,0 +1,11 @@ +#ifndef _ASM_ALPHA_SYSCALL_H +#define _ASM_ALPHA_SYSCALL_H + +#include <uapi/linux/audit.h> + +static inline int syscall_get_arch(void) +{ + return AUDIT_ARCH_ALPHA; +} + +#endif /* _ASM_ALPHA_SYSCALL_H */ diff --git a/arch/alpha/include/asm/termios.h b/arch/alpha/include/asm/termios.h new file mode 100644 index 000000000..7fde0f88d --- /dev/null +++ b/arch/alpha/include/asm/termios.h @@ -0,0 +1,80 @@ +#ifndef _ALPHA_TERMIOS_H +#define _ALPHA_TERMIOS_H + +#include <uapi/asm/termios.h> + +/* eof=^D eol=\0 eol2=\0 erase=del + werase=^W kill=^U reprint=^R sxtc=\0 + intr=^C quit=^\ susp=^Z <OSF/1 VDSUSP> + start=^Q stop=^S lnext=^V discard=^U + vmin=\1 vtime=\0 +*/ +#define INIT_C_CC "\004\000\000\177\027\025\022\000\003\034\032\000\021\023\026\025\001\000" + +/* + * Translate a "termio" structure into a "termios". Ugh. + */ + +#define user_termio_to_kernel_termios(a_termios, u_termio) \ +({ \ + struct ktermios *k_termios = (a_termios); \ + struct termio k_termio; \ + int canon, ret; \ + \ + ret = copy_from_user(&k_termio, u_termio, sizeof(k_termio)); \ + if (!ret) { \ + /* Overwrite only the low bits. */ \ + *(unsigned short *)&k_termios->c_iflag = k_termio.c_iflag; \ + *(unsigned short *)&k_termios->c_oflag = k_termio.c_oflag; \ + *(unsigned short *)&k_termios->c_cflag = k_termio.c_cflag; \ + *(unsigned short *)&k_termios->c_lflag = k_termio.c_lflag; \ + canon = k_termio.c_lflag & ICANON; \ + \ + k_termios->c_cc[VINTR] = k_termio.c_cc[_VINTR]; \ + k_termios->c_cc[VQUIT] = k_termio.c_cc[_VQUIT]; \ + k_termios->c_cc[VERASE] = k_termio.c_cc[_VERASE]; \ + k_termios->c_cc[VKILL] = k_termio.c_cc[_VKILL]; \ + k_termios->c_cc[VEOL2] = k_termio.c_cc[_VEOL2]; \ + k_termios->c_cc[VSWTC] = k_termio.c_cc[_VSWTC]; \ + k_termios->c_cc[canon ? VEOF : VMIN] = k_termio.c_cc[_VEOF]; \ + k_termios->c_cc[canon ? VEOL : VTIME] = k_termio.c_cc[_VEOL]; \ + } \ + ret; \ +}) + +/* + * Translate a "termios" structure into a "termio". Ugh. + * + * Note the "fun" _VMIN overloading. + */ +#define kernel_termios_to_user_termio(u_termio, a_termios) \ +({ \ + struct ktermios *k_termios = (a_termios); \ + struct termio k_termio; \ + int canon; \ + \ + k_termio.c_iflag = k_termios->c_iflag; \ + k_termio.c_oflag = k_termios->c_oflag; \ + k_termio.c_cflag = k_termios->c_cflag; \ + canon = (k_termio.c_lflag = k_termios->c_lflag) & ICANON; \ + \ + k_termio.c_line = k_termios->c_line; \ + k_termio.c_cc[_VINTR] = k_termios->c_cc[VINTR]; \ + k_termio.c_cc[_VQUIT] = k_termios->c_cc[VQUIT]; \ + k_termio.c_cc[_VERASE] = k_termios->c_cc[VERASE]; \ + k_termio.c_cc[_VKILL] = k_termios->c_cc[VKILL]; \ + k_termio.c_cc[_VEOF] = k_termios->c_cc[canon ? VEOF : VMIN]; \ + k_termio.c_cc[_VEOL] = k_termios->c_cc[canon ? VEOL : VTIME]; \ + k_termio.c_cc[_VEOL2] = k_termios->c_cc[VEOL2]; \ + k_termio.c_cc[_VSWTC] = k_termios->c_cc[VSWTC]; \ + \ + copy_to_user(u_termio, &k_termio, sizeof(k_termio)); \ +}) + +#define user_termios_to_kernel_termios(k, u) \ + copy_from_user(k, u, sizeof(struct termios)) + +#define kernel_termios_to_user_termios(u, k) \ + copy_to_user(u, k, sizeof(struct termios)) + +#endif /* _ALPHA_TERMIOS_H */ diff --git a/arch/alpha/include/asm/thread_info.h b/arch/alpha/include/asm/thread_info.h new file mode 100644 index 000000000..32e920a83 --- /dev/null +++ b/arch/alpha/include/asm/thread_info.h @@ -0,0 +1,141 @@ +#ifndef _ALPHA_THREAD_INFO_H +#define _ALPHA_THREAD_INFO_H + +#ifdef __KERNEL__ + +#ifndef __ASSEMBLY__ +#include <asm/processor.h> +#include <asm/types.h> +#include <asm/hwrpb.h> +#include <asm/sysinfo.h> +#endif + +#ifndef __ASSEMBLY__ +struct thread_info { + struct pcb_struct pcb; /* palcode state */ + + struct task_struct *task; /* main task structure */ + unsigned int flags; /* low level flags */ + unsigned int ieee_state; /* see fpu.h */ + + mm_segment_t addr_limit; /* thread address space */ + unsigned cpu; /* current CPU */ + int preempt_count; /* 0 => preemptable, <0 => BUG */ + unsigned int status; /* thread-synchronous flags */ + + int bpt_nsaved; + unsigned long bpt_addr[2]; /* breakpoint handling */ + unsigned int bpt_insn[2]; +}; + +/* + * Macros/functions for gaining access to the thread information structure. + */ +#define INIT_THREAD_INFO(tsk) \ +{ \ + .task = &tsk, \ + .addr_limit = KERNEL_DS, \ + .preempt_count = INIT_PREEMPT_COUNT, \ +} + +#define init_thread_info (init_thread_union.thread_info) +#define init_stack (init_thread_union.stack) + +/* How to get the thread information struct from C. */ +register struct thread_info *__current_thread_info __asm__("$8"); +#define current_thread_info() __current_thread_info + +#endif /* __ASSEMBLY__ */ + +/* Thread information allocation. */ +#define THREAD_SIZE_ORDER 1 +#define THREAD_SIZE (2*PAGE_SIZE) + +/* + * Thread information flags: + * - these are process state flags and used from assembly + * - pending work-to-be-done flags come first and must be assigned to be + * within bits 0 to 7 to fit in and immediate operand. + * + * TIF_SYSCALL_TRACE is known to be 0 via blbs. + */ +#define TIF_SYSCALL_TRACE 0 /* syscall trace active */ +#define TIF_NOTIFY_RESUME 1 /* callback before returning to user */ +#define TIF_SIGPENDING 2 /* signal pending */ +#define TIF_NEED_RESCHED 3 /* rescheduling necessary */ +#define TIF_SYSCALL_AUDIT 4 /* syscall audit active */ +#define TIF_DIE_IF_KERNEL 9 /* dik recursion lock */ +#define TIF_MEMDIE 13 /* is terminating due to OOM killer */ +#define TIF_POLLING_NRFLAG 14 /* idle is polling for TIF_NEED_RESCHED */ + +#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_RESUME (1<<TIF_NOTIFY_RESUME) +#define _TIF_SYSCALL_AUDIT (1<<TIF_SYSCALL_AUDIT) +#define _TIF_POLLING_NRFLAG (1<<TIF_POLLING_NRFLAG) + +/* Work to do on interrupt/exception return. */ +#define _TIF_WORK_MASK (_TIF_SIGPENDING | _TIF_NEED_RESCHED | \ + _TIF_NOTIFY_RESUME) + +/* Work to do on any return to userspace. */ +#define _TIF_ALLWORK_MASK (_TIF_WORK_MASK \ + | _TIF_SYSCALL_TRACE) + +#define TS_UAC_NOPRINT 0x0001 /* ! Preserve the following three */ +#define TS_UAC_NOFIX 0x0002 /* ! flags as they match */ +#define TS_UAC_SIGBUS 0x0004 /* ! userspace part of 'osf_sysinfo' */ +#define TS_RESTORE_SIGMASK 0x0008 /* restore signal mask in do_signal() */ + +#ifndef __ASSEMBLY__ +#define HAVE_SET_RESTORE_SIGMASK 1 +static inline void set_restore_sigmask(void) +{ + struct thread_info *ti = current_thread_info(); + ti->status |= TS_RESTORE_SIGMASK; + WARN_ON(!test_bit(TIF_SIGPENDING, (unsigned long *)&ti->flags)); +} +static inline void clear_restore_sigmask(void) +{ + current_thread_info()->status &= ~TS_RESTORE_SIGMASK; +} +static inline bool test_restore_sigmask(void) +{ + return current_thread_info()->status & TS_RESTORE_SIGMASK; +} +static inline bool test_and_clear_restore_sigmask(void) +{ + struct thread_info *ti = current_thread_info(); + if (!(ti->status & TS_RESTORE_SIGMASK)) + return false; + ti->status &= ~TS_RESTORE_SIGMASK; + return true; +} +#endif + +#define SET_UNALIGN_CTL(task,value) ({ \ + __u32 status = task_thread_info(task)->status & ~UAC_BITMASK; \ + if (value & PR_UNALIGN_NOPRINT) \ + status |= TS_UAC_NOPRINT; \ + if (value & PR_UNALIGN_SIGBUS) \ + status |= TS_UAC_SIGBUS; \ + if (value & 4) /* alpha-specific */ \ + status |= TS_UAC_NOFIX; \ + task_thread_info(task)->status = status; \ + 0; }) + +#define GET_UNALIGN_CTL(task,value) ({ \ + __u32 status = task_thread_info(task)->status & ~UAC_BITMASK; \ + __u32 res = 0; \ + if (status & TS_UAC_NOPRINT) \ + res |= PR_UNALIGN_NOPRINT; \ + if (status & TS_UAC_SIGBUS) \ + res |= PR_UNALIGN_SIGBUS; \ + if (status & TS_UAC_NOFIX) \ + res |= 4; \ + put_user(res, (int __user *)(value)); \ + }) + +#endif /* __KERNEL__ */ +#endif /* _ALPHA_THREAD_INFO_H */ diff --git a/arch/alpha/include/asm/timex.h b/arch/alpha/include/asm/timex.h new file mode 100644 index 000000000..afa0c45e3 --- /dev/null +++ b/arch/alpha/include/asm/timex.h @@ -0,0 +1,31 @@ +/* + * linux/include/asm-alpha/timex.h + * + * ALPHA architecture timex specifications + */ +#ifndef _ASMALPHA_TIMEX_H +#define _ASMALPHA_TIMEX_H + +/* With only one or two oddballs, we use the RTC as the ticker, selecting + the 32.768kHz reference clock, which nicely divides down to our HZ. */ +#define CLOCK_TICK_RATE 32768 + +/* + * Standard way to access the cycle counter. + * Currently only used on SMP for scheduling. + * + * Only the low 32 bits are available as a continuously counting entity. + * But this only means we'll force a reschedule every 8 seconds or so, + * which isn't an evil thing. + */ + +typedef unsigned int cycles_t; + +static inline cycles_t get_cycles (void) +{ + cycles_t ret; + __asm__ __volatile__ ("rpcc %0" : "=r"(ret)); + return ret; +} + +#endif diff --git a/arch/alpha/include/asm/tlb.h b/arch/alpha/include/asm/tlb.h new file mode 100644 index 000000000..42866759f --- /dev/null +++ b/arch/alpha/include/asm/tlb.h @@ -0,0 +1,15 @@ +#ifndef _ALPHA_TLB_H +#define _ALPHA_TLB_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, pte, addr) do { } while (0) + +#define tlb_flush(tlb) flush_tlb_mm((tlb)->mm) + +#include <asm-generic/tlb.h> + +#define __pte_free_tlb(tlb, pte, address) pte_free((tlb)->mm, pte) +#define __pmd_free_tlb(tlb, pmd, address) pmd_free((tlb)->mm, pmd) + +#endif diff --git a/arch/alpha/include/asm/tlbflush.h b/arch/alpha/include/asm/tlbflush.h new file mode 100644 index 000000000..e89e0c2e1 --- /dev/null +++ b/arch/alpha/include/asm/tlbflush.h @@ -0,0 +1,152 @@ +#ifndef _ALPHA_TLBFLUSH_H +#define _ALPHA_TLBFLUSH_H + +#include <linux/mm.h> +#include <linux/sched.h> +#include <asm/compiler.h> +#include <asm/pgalloc.h> + +#ifndef __EXTERN_INLINE +#define __EXTERN_INLINE extern inline +#define __MMU_EXTERN_INLINE +#endif + +extern void __load_new_mm_context(struct mm_struct *); + + +/* Use a few helper functions to hide the ugly broken ASN + numbers on early Alphas (ev4 and ev45). */ + +__EXTERN_INLINE void +ev4_flush_tlb_current(struct mm_struct *mm) +{ + __load_new_mm_context(mm); + tbiap(); +} + +__EXTERN_INLINE void +ev5_flush_tlb_current(struct mm_struct *mm) +{ + __load_new_mm_context(mm); +} + +/* Flush just one page in the current TLB set. We need to be very + careful about the icache here, there is no way to invalidate a + specific icache page. */ + +__EXTERN_INLINE void +ev4_flush_tlb_current_page(struct mm_struct * mm, + struct vm_area_struct *vma, + unsigned long addr) +{ + int tbi_flag = 2; + if (vma->vm_flags & VM_EXEC) { + __load_new_mm_context(mm); + tbi_flag = 3; + } + tbi(tbi_flag, addr); +} + +__EXTERN_INLINE void +ev5_flush_tlb_current_page(struct mm_struct * mm, + struct vm_area_struct *vma, + unsigned long addr) +{ + if (vma->vm_flags & VM_EXEC) + __load_new_mm_context(mm); + else + tbi(2, addr); +} + + +#ifdef CONFIG_ALPHA_GENERIC +# define flush_tlb_current alpha_mv.mv_flush_tlb_current +# define flush_tlb_current_page alpha_mv.mv_flush_tlb_current_page +#else +# ifdef CONFIG_ALPHA_EV4 +# define flush_tlb_current ev4_flush_tlb_current +# define flush_tlb_current_page ev4_flush_tlb_current_page +# else +# define flush_tlb_current ev5_flush_tlb_current +# define flush_tlb_current_page ev5_flush_tlb_current_page +# endif +#endif + +#ifdef __MMU_EXTERN_INLINE +#undef __EXTERN_INLINE +#undef __MMU_EXTERN_INLINE +#endif + +/* Flush current user mapping. */ +static inline void +flush_tlb(void) +{ + flush_tlb_current(current->active_mm); +} + +/* Flush someone else's user mapping. */ +static inline void +flush_tlb_other(struct mm_struct *mm) +{ + unsigned long *mmc = &mm->context[smp_processor_id()]; + /* Check it's not zero first to avoid cacheline ping pong + when possible. */ + if (*mmc) *mmc = 0; +} + +#ifndef CONFIG_SMP +/* Flush everything (kernel mapping may also have changed + due to vmalloc/vfree). */ +static inline void flush_tlb_all(void) +{ + tbia(); +} + +/* Flush a specified user mapping. */ +static inline void +flush_tlb_mm(struct mm_struct *mm) +{ + if (mm == current->active_mm) + flush_tlb_current(mm); + else + flush_tlb_other(mm); +} + +/* Page-granular tlb flush. */ +static inline void +flush_tlb_page(struct vm_area_struct *vma, unsigned long addr) +{ + struct mm_struct *mm = vma->vm_mm; + + if (mm == current->active_mm) + flush_tlb_current_page(mm, vma, addr); + else + flush_tlb_other(mm); +} + +/* Flush a specified range of user mapping. On the Alpha we flush + the whole user tlb. */ +static inline void +flush_tlb_range(struct vm_area_struct *vma, unsigned long start, + unsigned long end) +{ + flush_tlb_mm(vma->vm_mm); +} + +#else /* CONFIG_SMP */ + +extern void flush_tlb_all(void); +extern void flush_tlb_mm(struct mm_struct *); +extern void flush_tlb_page(struct vm_area_struct *, unsigned long); +extern void flush_tlb_range(struct vm_area_struct *, unsigned long, + unsigned long); + +#endif /* CONFIG_SMP */ + +static inline void flush_tlb_kernel_range(unsigned long start, + unsigned long end) +{ + flush_tlb_all(); +} + +#endif /* _ALPHA_TLBFLUSH_H */ diff --git a/arch/alpha/include/asm/topology.h b/arch/alpha/include/asm/topology.h new file mode 100644 index 000000000..9251e13e1 --- /dev/null +++ b/arch/alpha/include/asm/topology.h @@ -0,0 +1,49 @@ +#ifndef _ASM_ALPHA_TOPOLOGY_H +#define _ASM_ALPHA_TOPOLOGY_H + +#include <linux/smp.h> +#include <linux/threads.h> +#include <asm/machvec.h> + +#ifdef CONFIG_NUMA +static inline int cpu_to_node(int cpu) +{ + int node; + + if (!alpha_mv.cpuid_to_nid) + return 0; + + node = alpha_mv.cpuid_to_nid(cpu); + +#ifdef DEBUG_NUMA + BUG_ON(node < 0); +#endif + + return node; +} + +extern struct cpumask node_to_cpumask_map[]; +/* FIXME: This is dumb, recalculating every time. But simple. */ +static const struct cpumask *cpumask_of_node(int node) +{ + int cpu; + + if (node == -1) + return cpu_all_mask; + + cpumask_clear(&node_to_cpumask_map[node]); + + for_each_online_cpu(cpu) { + if (cpu_to_node(cpu) == node) + cpumask_set_cpu(cpu, node_to_cpumask_map[node]); + } + + return &node_to_cpumask_map[node]; +} + +#define cpumask_of_pcibus(bus) (cpu_online_mask) + +#endif /* !CONFIG_NUMA */ +# include <asm-generic/topology.h> + +#endif /* _ASM_ALPHA_TOPOLOGY_H */ diff --git a/arch/alpha/include/asm/types.h b/arch/alpha/include/asm/types.h new file mode 100644 index 000000000..4cb4b6d34 --- /dev/null +++ b/arch/alpha/include/asm/types.h @@ -0,0 +1,6 @@ +#ifndef _ALPHA_TYPES_H +#define _ALPHA_TYPES_H + +#include <asm-generic/int-ll64.h> + +#endif /* _ALPHA_TYPES_H */ diff --git a/arch/alpha/include/asm/uaccess.h b/arch/alpha/include/asm/uaccess.h new file mode 100644 index 000000000..9b0d40093 --- /dev/null +++ b/arch/alpha/include/asm/uaccess.h @@ -0,0 +1,489 @@ +#ifndef __ALPHA_UACCESS_H +#define __ALPHA_UACCESS_H + +#include <linux/errno.h> +#include <linux/sched.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. + * + * Or at least it did once upon a time. Nowadays it is a mask that + * defines which bits of the address space are off limits. This is a + * wee bit faster than the above. + * + * For historical reasons, these macros are grossly misnamed. + */ + +#define KERNEL_DS ((mm_segment_t) { 0UL }) +#define USER_DS ((mm_segment_t) { -0x40000000000UL }) + +#define VERIFY_READ 0 +#define VERIFY_WRITE 1 + +#define get_fs() (current_thread_info()->addr_limit) +#define get_ds() (KERNEL_DS) +#define set_fs(x) (current_thread_info()->addr_limit = (x)) + +#define segment_eq(a, b) ((a).seg == (b).seg) + +/* + * Is a address valid? This does a straightforward calculation rather + * than tests. + * + * Address valid if: + * - "addr" doesn't have any high-bits set + * - AND "size" doesn't have any high-bits set + * - AND "addr+size" doesn't have any high-bits set + * - OR we are in kernel mode. + */ +#define __access_ok(addr, size, segment) \ + (((segment).seg & (addr | size | (addr+size))) == 0) + +#define access_ok(type, addr, size) \ +({ \ + __chk_user_ptr(addr); \ + __access_ok(((unsigned long)(addr)), (size), get_fs()); \ +}) + +/* + * These are the main single-value transfer routines. They automatically + * use the right size if we just have the right pointer type. + * + * As the alpha uses the same address space for kernel and user + * data, we can just do these as direct assignments. (Of course, the + * exception handling means that it's no longer "just"...) + * + * Careful to not + * (a) re-use the arguments for side effects (sizeof/typeof is ok) + * (b) require any knowledge of processes at this stage + */ +#define put_user(x, ptr) \ + __put_user_check((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr)), get_fs()) +#define get_user(x, ptr) \ + __get_user_check((x), (ptr), sizeof(*(ptr)), get_fs()) + +/* + * The "__xxx" versions do not do address space checking, useful when + * doing multiple accesses to the same area (the programmer has to do the + * checks by hand with "access_ok()") + */ +#define __put_user(x, ptr) \ + __put_user_nocheck((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr))) +#define __get_user(x, ptr) \ + __get_user_nocheck((x), (ptr), sizeof(*(ptr))) + +/* + * The "lda %1, 2b-1b(%0)" bits are magic to get the assembler to + * encode the bits we need for resolving the exception. See the + * more extensive comments with fixup_inline_exception below for + * more information. + */ + +extern void __get_user_unknown(void); + +#define __get_user_nocheck(x, ptr, size) \ +({ \ + long __gu_err = 0; \ + unsigned long __gu_val; \ + __chk_user_ptr(ptr); \ + switch (size) { \ + case 1: __get_user_8(ptr); break; \ + case 2: __get_user_16(ptr); break; \ + case 4: __get_user_32(ptr); break; \ + case 8: __get_user_64(ptr); break; \ + default: __get_user_unknown(); break; \ + } \ + (x) = (__force __typeof__(*(ptr))) __gu_val; \ + __gu_err; \ +}) + +#define __get_user_check(x, ptr, size, segment) \ +({ \ + long __gu_err = -EFAULT; \ + unsigned long __gu_val = 0; \ + const __typeof__(*(ptr)) __user *__gu_addr = (ptr); \ + if (__access_ok((unsigned long)__gu_addr, size, segment)) { \ + __gu_err = 0; \ + switch (size) { \ + case 1: __get_user_8(__gu_addr); break; \ + case 2: __get_user_16(__gu_addr); break; \ + case 4: __get_user_32(__gu_addr); break; \ + case 8: __get_user_64(__gu_addr); break; \ + default: __get_user_unknown(); break; \ + } \ + } \ + (x) = (__force __typeof__(*(ptr))) __gu_val; \ + __gu_err; \ +}) + +struct __large_struct { unsigned long buf[100]; }; +#define __m(x) (*(struct __large_struct __user *)(x)) + +#define __get_user_64(addr) \ + __asm__("1: ldq %0,%2\n" \ + "2:\n" \ + ".section __ex_table,\"a\"\n" \ + " .long 1b - .\n" \ + " lda %0, 2b-1b(%1)\n" \ + ".previous" \ + : "=r"(__gu_val), "=r"(__gu_err) \ + : "m"(__m(addr)), "1"(__gu_err)) + +#define __get_user_32(addr) \ + __asm__("1: ldl %0,%2\n" \ + "2:\n" \ + ".section __ex_table,\"a\"\n" \ + " .long 1b - .\n" \ + " lda %0, 2b-1b(%1)\n" \ + ".previous" \ + : "=r"(__gu_val), "=r"(__gu_err) \ + : "m"(__m(addr)), "1"(__gu_err)) + +#ifdef __alpha_bwx__ +/* Those lucky bastards with ev56 and later CPUs can do byte/word moves. */ + +#define __get_user_16(addr) \ + __asm__("1: ldwu %0,%2\n" \ + "2:\n" \ + ".section __ex_table,\"a\"\n" \ + " .long 1b - .\n" \ + " lda %0, 2b-1b(%1)\n" \ + ".previous" \ + : "=r"(__gu_val), "=r"(__gu_err) \ + : "m"(__m(addr)), "1"(__gu_err)) + +#define __get_user_8(addr) \ + __asm__("1: ldbu %0,%2\n" \ + "2:\n" \ + ".section __ex_table,\"a\"\n" \ + " .long 1b - .\n" \ + " lda %0, 2b-1b(%1)\n" \ + ".previous" \ + : "=r"(__gu_val), "=r"(__gu_err) \ + : "m"(__m(addr)), "1"(__gu_err)) +#else +/* Unfortunately, we can't get an unaligned access trap for the sub-word + load, so we have to do a general unaligned operation. */ + +#define __get_user_16(addr) \ +{ \ + long __gu_tmp; \ + __asm__("1: ldq_u %0,0(%3)\n" \ + "2: ldq_u %1,1(%3)\n" \ + " extwl %0,%3,%0\n" \ + " extwh %1,%3,%1\n" \ + " or %0,%1,%0\n" \ + "3:\n" \ + ".section __ex_table,\"a\"\n" \ + " .long 1b - .\n" \ + " lda %0, 3b-1b(%2)\n" \ + " .long 2b - .\n" \ + " lda %0, 3b-2b(%2)\n" \ + ".previous" \ + : "=&r"(__gu_val), "=&r"(__gu_tmp), "=r"(__gu_err) \ + : "r"(addr), "2"(__gu_err)); \ +} + +#define __get_user_8(addr) \ + __asm__("1: ldq_u %0,0(%2)\n" \ + " extbl %0,%2,%0\n" \ + "2:\n" \ + ".section __ex_table,\"a\"\n" \ + " .long 1b - .\n" \ + " lda %0, 2b-1b(%1)\n" \ + ".previous" \ + : "=&r"(__gu_val), "=r"(__gu_err) \ + : "r"(addr), "1"(__gu_err)) +#endif + +extern void __put_user_unknown(void); + +#define __put_user_nocheck(x, ptr, size) \ +({ \ + long __pu_err = 0; \ + __chk_user_ptr(ptr); \ + switch (size) { \ + case 1: __put_user_8(x, ptr); break; \ + case 2: __put_user_16(x, ptr); break; \ + case 4: __put_user_32(x, ptr); break; \ + case 8: __put_user_64(x, ptr); break; \ + default: __put_user_unknown(); break; \ + } \ + __pu_err; \ +}) + +#define __put_user_check(x, ptr, size, segment) \ +({ \ + long __pu_err = -EFAULT; \ + __typeof__(*(ptr)) __user *__pu_addr = (ptr); \ + if (__access_ok((unsigned long)__pu_addr, size, segment)) { \ + __pu_err = 0; \ + switch (size) { \ + case 1: __put_user_8(x, __pu_addr); break; \ + case 2: __put_user_16(x, __pu_addr); break; \ + case 4: __put_user_32(x, __pu_addr); break; \ + case 8: __put_user_64(x, __pu_addr); break; \ + default: __put_user_unknown(); break; \ + } \ + } \ + __pu_err; \ +}) + +/* + * The "__put_user_xx()" macros tell gcc they read from memory + * instead of writing: this is because they do not write to + * any memory gcc knows about, so there are no aliasing issues + */ +#define __put_user_64(x, addr) \ +__asm__ __volatile__("1: stq %r2,%1\n" \ + "2:\n" \ + ".section __ex_table,\"a\"\n" \ + " .long 1b - .\n" \ + " lda $31,2b-1b(%0)\n" \ + ".previous" \ + : "=r"(__pu_err) \ + : "m" (__m(addr)), "rJ" (x), "0"(__pu_err)) + +#define __put_user_32(x, addr) \ +__asm__ __volatile__("1: stl %r2,%1\n" \ + "2:\n" \ + ".section __ex_table,\"a\"\n" \ + " .long 1b - .\n" \ + " lda $31,2b-1b(%0)\n" \ + ".previous" \ + : "=r"(__pu_err) \ + : "m"(__m(addr)), "rJ"(x), "0"(__pu_err)) + +#ifdef __alpha_bwx__ +/* Those lucky bastards with ev56 and later CPUs can do byte/word moves. */ + +#define __put_user_16(x, addr) \ +__asm__ __volatile__("1: stw %r2,%1\n" \ + "2:\n" \ + ".section __ex_table,\"a\"\n" \ + " .long 1b - .\n" \ + " lda $31,2b-1b(%0)\n" \ + ".previous" \ + : "=r"(__pu_err) \ + : "m"(__m(addr)), "rJ"(x), "0"(__pu_err)) + +#define __put_user_8(x, addr) \ +__asm__ __volatile__("1: stb %r2,%1\n" \ + "2:\n" \ + ".section __ex_table,\"a\"\n" \ + " .long 1b - .\n" \ + " lda $31,2b-1b(%0)\n" \ + ".previous" \ + : "=r"(__pu_err) \ + : "m"(__m(addr)), "rJ"(x), "0"(__pu_err)) +#else +/* Unfortunately, we can't get an unaligned access trap for the sub-word + write, so we have to do a general unaligned operation. */ + +#define __put_user_16(x, addr) \ +{ \ + long __pu_tmp1, __pu_tmp2, __pu_tmp3, __pu_tmp4; \ + __asm__ __volatile__( \ + "1: ldq_u %2,1(%5)\n" \ + "2: ldq_u %1,0(%5)\n" \ + " inswh %6,%5,%4\n" \ + " inswl %6,%5,%3\n" \ + " mskwh %2,%5,%2\n" \ + " mskwl %1,%5,%1\n" \ + " or %2,%4,%2\n" \ + " or %1,%3,%1\n" \ + "3: stq_u %2,1(%5)\n" \ + "4: stq_u %1,0(%5)\n" \ + "5:\n" \ + ".section __ex_table,\"a\"\n" \ + " .long 1b - .\n" \ + " lda $31, 5b-1b(%0)\n" \ + " .long 2b - .\n" \ + " lda $31, 5b-2b(%0)\n" \ + " .long 3b - .\n" \ + " lda $31, 5b-3b(%0)\n" \ + " .long 4b - .\n" \ + " lda $31, 5b-4b(%0)\n" \ + ".previous" \ + : "=r"(__pu_err), "=&r"(__pu_tmp1), \ + "=&r"(__pu_tmp2), "=&r"(__pu_tmp3), \ + "=&r"(__pu_tmp4) \ + : "r"(addr), "r"((unsigned long)(x)), "0"(__pu_err)); \ +} + +#define __put_user_8(x, addr) \ +{ \ + long __pu_tmp1, __pu_tmp2; \ + __asm__ __volatile__( \ + "1: ldq_u %1,0(%4)\n" \ + " insbl %3,%4,%2\n" \ + " mskbl %1,%4,%1\n" \ + " or %1,%2,%1\n" \ + "2: stq_u %1,0(%4)\n" \ + "3:\n" \ + ".section __ex_table,\"a\"\n" \ + " .long 1b - .\n" \ + " lda $31, 3b-1b(%0)\n" \ + " .long 2b - .\n" \ + " lda $31, 3b-2b(%0)\n" \ + ".previous" \ + : "=r"(__pu_err), \ + "=&r"(__pu_tmp1), "=&r"(__pu_tmp2) \ + : "r"((unsigned long)(x)), "r"(addr), "0"(__pu_err)); \ +} +#endif + + +/* + * Complex access routines + */ + +/* This little bit of silliness is to get the GP loaded for a function + that ordinarily wouldn't. Otherwise we could have it done by the macro + directly, which can be optimized the linker. */ +#ifdef MODULE +#define __module_address(sym) "r"(sym), +#define __module_call(ra, arg, sym) "jsr $" #ra ",(%" #arg ")," #sym +#else +#define __module_address(sym) +#define __module_call(ra, arg, sym) "bsr $" #ra "," #sym " !samegp" +#endif + +extern void __copy_user(void); + +extern inline long +__copy_tofrom_user_nocheck(void *to, const void *from, long len) +{ + register void * __cu_to __asm__("$6") = to; + register const void * __cu_from __asm__("$7") = from; + register long __cu_len __asm__("$0") = len; + + __asm__ __volatile__( + __module_call(28, 3, __copy_user) + : "=r" (__cu_len), "=r" (__cu_from), "=r" (__cu_to) + : __module_address(__copy_user) + "0" (__cu_len), "1" (__cu_from), "2" (__cu_to) + : "$1", "$2", "$3", "$4", "$5", "$28", "memory"); + + return __cu_len; +} + +extern inline long +__copy_tofrom_user(void *to, const void *from, long len, const void __user *validate) +{ + if (__access_ok((unsigned long)validate, len, get_fs())) + len = __copy_tofrom_user_nocheck(to, from, len); + return len; +} + +#define __copy_to_user(to, from, n) \ +({ \ + __chk_user_ptr(to); \ + __copy_tofrom_user_nocheck((__force void *)(to), (from), (n)); \ +}) +#define __copy_from_user(to, from, n) \ +({ \ + __chk_user_ptr(from); \ + __copy_tofrom_user_nocheck((to), (__force void *)(from), (n)); \ +}) + +#define __copy_to_user_inatomic __copy_to_user +#define __copy_from_user_inatomic __copy_from_user + + +extern inline long +copy_to_user(void __user *to, const void *from, long n) +{ + return __copy_tofrom_user((__force void *)to, from, n, to); +} + +extern inline long +copy_from_user(void *to, const void __user *from, long n) +{ + return __copy_tofrom_user(to, (__force void *)from, n, from); +} + +extern void __do_clear_user(void); + +extern inline long +__clear_user(void __user *to, long len) +{ + register void __user * __cl_to __asm__("$6") = to; + register long __cl_len __asm__("$0") = len; + __asm__ __volatile__( + __module_call(28, 2, __do_clear_user) + : "=r"(__cl_len), "=r"(__cl_to) + : __module_address(__do_clear_user) + "0"(__cl_len), "1"(__cl_to) + : "$1", "$2", "$3", "$4", "$5", "$28", "memory"); + return __cl_len; +} + +extern inline long +clear_user(void __user *to, long len) +{ + if (__access_ok((unsigned long)to, len, get_fs())) + len = __clear_user(to, len); + return len; +} + +#undef __module_address +#undef __module_call + +#define user_addr_max() \ + (segment_eq(get_fs(), USER_DS) ? TASK_SIZE : ~0UL) + +extern long strncpy_from_user(char *dest, const char __user *src, long count); +extern __must_check long strlen_user(const char __user *str); +extern __must_check long strnlen_user(const char __user *str, long n); + +/* + * About the exception table: + * + * - insn is a 32-bit pc-relative offset from the faulting insn. + * - nextinsn is a 16-bit offset off of the faulting instruction + * (not off of the *next* instruction as branches are). + * - errreg is the register in which to place -EFAULT. + * - valreg is the final target register for the load sequence + * and will be zeroed. + * + * Either errreg or valreg may be $31, in which case nothing happens. + * + * The exception fixup information "just so happens" to be arranged + * as in a MEM format instruction. This lets us emit our three + * values like so: + * + * lda valreg, nextinsn(errreg) + * + */ + +struct exception_table_entry +{ + signed int insn; + union exception_fixup { + unsigned unit; + struct { + signed int nextinsn : 16; + unsigned int errreg : 5; + unsigned int valreg : 5; + } bits; + } fixup; +}; + +/* Returns the new pc */ +#define fixup_exception(map_reg, _fixup, pc) \ +({ \ + if ((_fixup)->fixup.bits.valreg != 31) \ + map_reg((_fixup)->fixup.bits.valreg) = 0; \ + if ((_fixup)->fixup.bits.errreg != 31) \ + map_reg((_fixup)->fixup.bits.errreg) = -EFAULT; \ + (pc) + (_fixup)->fixup.bits.nextinsn; \ +}) + +#define ARCH_HAS_SORT_EXTABLE +#define ARCH_HAS_SEARCH_EXTABLE + +#endif /* __ALPHA_UACCESS_H */ diff --git a/arch/alpha/include/asm/ucontext.h b/arch/alpha/include/asm/ucontext.h new file mode 100644 index 000000000..47578ab42 --- /dev/null +++ b/arch/alpha/include/asm/ucontext.h @@ -0,0 +1,13 @@ +#ifndef _ASMAXP_UCONTEXT_H +#define _ASMAXP_UCONTEXT_H + +struct ucontext { + unsigned long uc_flags; + struct ucontext *uc_link; + old_sigset_t uc_osf_sigmask; + stack_t uc_stack; + struct sigcontext uc_mcontext; + sigset_t uc_sigmask; /* mask last for extensibility */ +}; + +#endif /* !_ASMAXP_UCONTEXT_H */ diff --git a/arch/alpha/include/asm/unaligned.h b/arch/alpha/include/asm/unaligned.h new file mode 100644 index 000000000..3787c60ae --- /dev/null +++ b/arch/alpha/include/asm/unaligned.h @@ -0,0 +1,11 @@ +#ifndef _ASM_ALPHA_UNALIGNED_H +#define _ASM_ALPHA_UNALIGNED_H + +#include <linux/unaligned/le_struct.h> +#include <linux/unaligned/be_byteshift.h> +#include <linux/unaligned/generic.h> + +#define get_unaligned __get_unaligned_le +#define put_unaligned __put_unaligned_le + +#endif /* _ASM_ALPHA_UNALIGNED_H */ diff --git a/arch/alpha/include/asm/unistd.h b/arch/alpha/include/asm/unistd.h new file mode 100644 index 000000000..a56e608db --- /dev/null +++ b/arch/alpha/include/asm/unistd.h @@ -0,0 +1,20 @@ +#ifndef _ALPHA_UNISTD_H +#define _ALPHA_UNISTD_H + +#include <uapi/asm/unistd.h> + +#define NR_SYSCALLS 514 + +#define __ARCH_WANT_OLD_READDIR +#define __ARCH_WANT_STAT64 +#define __ARCH_WANT_SYS_GETHOSTNAME +#define __ARCH_WANT_SYS_FADVISE64 +#define __ARCH_WANT_SYS_GETPGRP +#define __ARCH_WANT_SYS_OLD_GETRLIMIT +#define __ARCH_WANT_SYS_OLDUMOUNT +#define __ARCH_WANT_SYS_SIGPENDING +#define __ARCH_WANT_SYS_FORK +#define __ARCH_WANT_SYS_VFORK +#define __ARCH_WANT_SYS_CLONE + +#endif /* _ALPHA_UNISTD_H */ diff --git a/arch/alpha/include/asm/user.h b/arch/alpha/include/asm/user.h new file mode 100644 index 000000000..a4eb6a4ca --- /dev/null +++ b/arch/alpha/include/asm/user.h @@ -0,0 +1,53 @@ +#ifndef _ALPHA_USER_H +#define _ALPHA_USER_H + +#include <linux/sched.h> +#include <linux/ptrace.h> + +#include <asm/page.h> +#include <asm/reg.h> + +/* + * Core file format: The core file is written in such a way that gdb + * can understand it and provide useful information to the user (under + * linux we use the `trad-core' bfd, NOT the osf-core). The file contents + * are as follows: + * + * upage: 1 page consisting of a user struct that tells gdb + * what is present in the file. Directly after this is a + * copy of the task_struct, which is currently not used by gdb, + * but it may come in handy at some point. All of the registers + * are stored as part of the upage. The upage should always be + * only one page long. + * data: The data segment follows next. We use current->end_text to + * current->brk to pick up all of the user variables, plus any memory + * that may have been sbrk'ed. No attempt is made to determine if a + * page is demand-zero or if a page is totally unused, we just cover + * the entire range. All of the addresses are rounded in such a way + * that an integral number of pages is written. + * stack: We need the stack information in order to get a meaningful + * backtrace. We need to write the data from usp to + * current->start_stack, so we round each of these in order to be able + * to write an integer number of pages. + */ +struct user { + unsigned long regs[EF_SIZE/8+32]; /* integer and fp regs */ + size_t u_tsize; /* text size (pages) */ + size_t u_dsize; /* data size (pages) */ + size_t u_ssize; /* stack size (pages) */ + unsigned long start_code; /* text starting address */ + unsigned long start_data; /* data starting address */ + unsigned long start_stack; /* stack starting address */ + long int signal; /* signal causing core dump */ + unsigned long u_ar0; /* help gdb find registers */ + unsigned long magic; /* identifies a core file */ + 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 /* _ALPHA_USER_H */ diff --git a/arch/alpha/include/asm/vga.h b/arch/alpha/include/asm/vga.h new file mode 100644 index 000000000..c00106bac --- /dev/null +++ b/arch/alpha/include/asm/vga.h @@ -0,0 +1,82 @@ +/* + * Access to VGA videoram + * + * (c) 1998 Martin Mares <mj@ucw.cz> + */ + +#ifndef _LINUX_ASM_VGA_H_ +#define _LINUX_ASM_VGA_H_ + +#include <asm/io.h> + +#define VT_BUF_HAVE_RW +#define VT_BUF_HAVE_MEMSETW +#define VT_BUF_HAVE_MEMCPYW + +static inline void scr_writew(u16 val, volatile u16 *addr) +{ + if (__is_ioaddr(addr)) + __raw_writew(val, (volatile u16 __iomem *) addr); + else + *addr = val; +} + +static inline u16 scr_readw(volatile const u16 *addr) +{ + if (__is_ioaddr(addr)) + return __raw_readw((volatile const u16 __iomem *) addr); + else + return *addr; +} + +static inline void scr_memsetw(u16 *s, u16 c, unsigned int count) +{ + if (__is_ioaddr(s)) + memsetw_io((u16 __iomem *) s, c, count); + else + memsetw(s, c, count); +} + +/* Do not trust that the usage will be correct; analyze the arguments. */ +extern void scr_memcpyw(u16 *d, const u16 *s, unsigned int count); + +/* ??? These are currently only used for downloading character sets. As + such, they don't need memory barriers. Is this all they are intended + to be used for? */ +#define vga_readb(a) readb((u8 __iomem *)(a)) +#define vga_writeb(v,a) writeb(v, (u8 __iomem *)(a)) + +#ifdef CONFIG_VGA_HOSE +#include <linux/ioport.h> +#include <linux/pci.h> + +extern struct pci_controller *pci_vga_hose; + +# define __is_port_vga(a) \ + (((a) >= 0x3b0) && ((a) < 0x3e0) && \ + ((a) != 0x3b3) && ((a) != 0x3d3)) + +# define __is_mem_vga(a) \ + (((a) >= 0xa0000) && ((a) <= 0xc0000)) + +# define FIXUP_IOADDR_VGA(a) do { \ + if (pci_vga_hose && __is_port_vga(a)) \ + (a) += pci_vga_hose->io_space->start; \ + } while(0) + +# define FIXUP_MEMADDR_VGA(a) do { \ + if (pci_vga_hose && __is_mem_vga(a)) \ + (a) += pci_vga_hose->mem_space->start; \ + } while(0) + +#else /* CONFIG_VGA_HOSE */ +# define pci_vga_hose 0 +# define __is_port_vga(a) 0 +# define __is_mem_vga(a) 0 +# define FIXUP_IOADDR_VGA(a) +# define FIXUP_MEMADDR_VGA(a) +#endif /* CONFIG_VGA_HOSE */ + +#define VGA_MAP_MEM(x,s) ((unsigned long) ioremap(x, s)) + +#endif diff --git a/arch/alpha/include/asm/word-at-a-time.h b/arch/alpha/include/asm/word-at-a-time.h new file mode 100644 index 000000000..6b340d0f1 --- /dev/null +++ b/arch/alpha/include/asm/word-at-a-time.h @@ -0,0 +1,55 @@ +#ifndef _ASM_WORD_AT_A_TIME_H +#define _ASM_WORD_AT_A_TIME_H + +#include <asm/compiler.h> + +/* + * word-at-a-time interface for Alpha. + */ + +/* + * We do not use the word_at_a_time struct on Alpha, but it needs to be + * implemented to humour the generic code. + */ +struct word_at_a_time { + const unsigned long unused; +}; + +#define WORD_AT_A_TIME_CONSTANTS { 0 } + +/* Return nonzero if val has a zero */ +static inline unsigned long has_zero(unsigned long val, unsigned long *bits, const struct word_at_a_time *c) +{ + unsigned long zero_locations = __kernel_cmpbge(0, val); + *bits = zero_locations; + return zero_locations; +} + +static inline unsigned long prep_zero_mask(unsigned long val, unsigned long bits, const struct word_at_a_time *c) +{ + return bits; +} + +#define create_zero_mask(bits) (bits) + +static inline unsigned long find_zero(unsigned long bits) +{ +#if defined(CONFIG_ALPHA_EV6) && defined(CONFIG_ALPHA_EV67) + /* Simple if have CIX instructions */ + return __kernel_cttz(bits); +#else + unsigned long t1, t2, t3; + /* Retain lowest set bit only */ + bits &= -bits; + /* Binary search for lowest set bit */ + t1 = bits & 0xf0; + t2 = bits & 0xcc; + t3 = bits & 0xaa; + if (t1) t1 = 4; + if (t2) t2 = 2; + if (t3) t3 = 1; + return t1 + t2 + t3; +#endif +} + +#endif /* _ASM_WORD_AT_A_TIME_H */ diff --git a/arch/alpha/include/asm/wrperfmon.h b/arch/alpha/include/asm/wrperfmon.h new file mode 100644 index 000000000..319bf6788 --- /dev/null +++ b/arch/alpha/include/asm/wrperfmon.h @@ -0,0 +1,93 @@ +/* + * Definitions for use with the Alpha wrperfmon PAL call. + */ + +#ifndef __ALPHA_WRPERFMON_H +#define __ALPHA_WRPERFMON_H + +/* Following commands are implemented on all CPUs */ +#define PERFMON_CMD_DISABLE 0 +#define PERFMON_CMD_ENABLE 1 +#define PERFMON_CMD_DESIRED_EVENTS 2 +#define PERFMON_CMD_LOGGING_OPTIONS 3 +/* Following commands on EV5/EV56/PCA56 only */ +#define PERFMON_CMD_INT_FREQ 4 +#define PERFMON_CMD_ENABLE_CLEAR 7 +/* Following commands are on EV5 and better CPUs */ +#define PERFMON_CMD_READ 5 +#define PERFMON_CMD_WRITE 6 +/* Following command are on EV6 and better CPUs */ +#define PERFMON_CMD_ENABLE_WRITE 7 +/* Following command are on EV67 and better CPUs */ +#define PERFMON_CMD_I_STAT 8 +#define PERFMON_CMD_PMPC 9 + + +/* EV5/EV56/PCA56 Counters */ +#define EV5_PCTR_0 (1UL<<0) +#define EV5_PCTR_1 (1UL<<1) +#define EV5_PCTR_2 (1UL<<2) + +#define EV5_PCTR_0_COUNT_SHIFT 48 +#define EV5_PCTR_1_COUNT_SHIFT 32 +#define EV5_PCTR_2_COUNT_SHIFT 16 + +#define EV5_PCTR_0_COUNT_MASK 0xffffUL +#define EV5_PCTR_1_COUNT_MASK 0xffffUL +#define EV5_PCTR_2_COUNT_MASK 0x3fffUL + +/* EV6 Counters */ +#define EV6_PCTR_0 (1UL<<0) +#define EV6_PCTR_1 (1UL<<1) + +#define EV6_PCTR_0_COUNT_SHIFT 28 +#define EV6_PCTR_1_COUNT_SHIFT 6 + +#define EV6_PCTR_0_COUNT_MASK 0xfffffUL +#define EV6_PCTR_1_COUNT_MASK 0xfffffUL + +/* EV67 (and subsequent) counters */ +#define EV67_PCTR_0 (1UL<<0) +#define EV67_PCTR_1 (1UL<<1) + +#define EV67_PCTR_0_COUNT_SHIFT 28 +#define EV67_PCTR_1_COUNT_SHIFT 6 + +#define EV67_PCTR_0_COUNT_MASK 0xfffffUL +#define EV67_PCTR_1_COUNT_MASK 0xfffffUL + + +/* + * The Alpha Architecure Handbook, vers. 4 (1998) appears to have a misprint + * in Table E-23 regarding the bits that set the event PCTR 1 counts. + * Hopefully what we have here is correct. + */ +#define EV6_PCTR_0_EVENT_MASK 0x10UL +#define EV6_PCTR_1_EVENT_MASK 0x0fUL + +/* EV6 Events */ +#define EV6_PCTR_0_CYCLES (0UL << 4) +#define EV6_PCTR_0_INSTRUCTIONS (1UL << 4) + +#define EV6_PCTR_1_CYCLES 0 +#define EV6_PCTR_1_BRANCHES 1 +#define EV6_PCTR_1_BRANCH_MISPREDICTS 2 +#define EV6_PCTR_1_DTB_SINGLE_MISSES 3 +#define EV6_PCTR_1_DTB_DOUBLE_MISSES 4 +#define EV6_PCTR_1_ITB_MISSES 5 +#define EV6_PCTR_1_UNALIGNED_TRAPS 6 +#define EV6_PCTR_1_REPLY_TRAPS 7 + +/* From the Alpha Architecture Reference Manual, 4th edn., 2002 */ +#define EV67_PCTR_MODE_MASK 0x10UL +#define EV67_PCTR_EVENT_MASK 0x0CUL + +#define EV67_PCTR_MODE_PROFILEME (1UL<<4) +#define EV67_PCTR_MODE_AGGREGATE (0UL<<4) + +#define EV67_PCTR_INSTR_CYCLES (0UL<<2) +#define EV67_PCTR_CYCLES_UNDEF (1UL<<2) +#define EV67_PCTR_INSTR_BCACHEMISS (2UL<<2) +#define EV67_PCTR_CYCLES_MBOX (3UL<<2) + +#endif diff --git a/arch/alpha/include/asm/xchg.h b/arch/alpha/include/asm/xchg.h new file mode 100644 index 000000000..0ca972459 --- /dev/null +++ b/arch/alpha/include/asm/xchg.h @@ -0,0 +1,258 @@ +#ifndef _ALPHA_CMPXCHG_H +#error Do not include xchg.h directly! +#else +/* + * xchg/xchg_local and cmpxchg/cmpxchg_local share the same code + * except that local version do not have the expensive memory barrier. + * So this file is included twice from asm/cmpxchg.h. + */ + +/* + * Atomic exchange. + * Since it can be used to implement critical sections + * it must clobber "memory" (also for interrupts in UP). + */ + +static inline unsigned long +____xchg(_u8, volatile char *m, unsigned long val) +{ + unsigned long ret, tmp, addr64; + + __asm__ __volatile__( + " andnot %4,7,%3\n" + " insbl %1,%4,%1\n" + "1: ldq_l %2,0(%3)\n" + " extbl %2,%4,%0\n" + " mskbl %2,%4,%2\n" + " or %1,%2,%2\n" + " stq_c %2,0(%3)\n" + " beq %2,2f\n" + __ASM__MB + ".subsection 2\n" + "2: br 1b\n" + ".previous" + : "=&r" (ret), "=&r" (val), "=&r" (tmp), "=&r" (addr64) + : "r" ((long)m), "1" (val) : "memory"); + + return ret; +} + +static inline unsigned long +____xchg(_u16, volatile short *m, unsigned long val) +{ + unsigned long ret, tmp, addr64; + + __asm__ __volatile__( + " andnot %4,7,%3\n" + " inswl %1,%4,%1\n" + "1: ldq_l %2,0(%3)\n" + " extwl %2,%4,%0\n" + " mskwl %2,%4,%2\n" + " or %1,%2,%2\n" + " stq_c %2,0(%3)\n" + " beq %2,2f\n" + __ASM__MB + ".subsection 2\n" + "2: br 1b\n" + ".previous" + : "=&r" (ret), "=&r" (val), "=&r" (tmp), "=&r" (addr64) + : "r" ((long)m), "1" (val) : "memory"); + + return ret; +} + +static inline unsigned long +____xchg(_u32, volatile int *m, unsigned long val) +{ + unsigned long dummy; + + __asm__ __volatile__( + "1: ldl_l %0,%4\n" + " bis $31,%3,%1\n" + " stl_c %1,%2\n" + " beq %1,2f\n" + __ASM__MB + ".subsection 2\n" + "2: br 1b\n" + ".previous" + : "=&r" (val), "=&r" (dummy), "=m" (*m) + : "rI" (val), "m" (*m) : "memory"); + + return val; +} + +static inline unsigned long +____xchg(_u64, volatile long *m, unsigned long val) +{ + unsigned long dummy; + + __asm__ __volatile__( + "1: ldq_l %0,%4\n" + " bis $31,%3,%1\n" + " stq_c %1,%2\n" + " beq %1,2f\n" + __ASM__MB + ".subsection 2\n" + "2: br 1b\n" + ".previous" + : "=&r" (val), "=&r" (dummy), "=m" (*m) + : "rI" (val), "m" (*m) : "memory"); + + return val; +} + +/* This function doesn't exist, so you'll get a linker error + if something tries to do an invalid xchg(). */ +extern void __xchg_called_with_bad_pointer(void); + +static __always_inline unsigned long +____xchg(, volatile void *ptr, unsigned long x, int size) +{ + switch (size) { + case 1: + return ____xchg(_u8, ptr, x); + case 2: + return ____xchg(_u16, ptr, x); + case 4: + return ____xchg(_u32, ptr, x); + case 8: + return ____xchg(_u64, ptr, x); + } + __xchg_called_with_bad_pointer(); + return x; +} + +/* + * Atomic compare and exchange. Compare OLD with MEM, if identical, + * store NEW in MEM. Return the initial value in MEM. Success is + * indicated by comparing RETURN with OLD. + * + * The memory barrier should be placed in SMP only when we actually + * make the change. If we don't change anything (so if the returned + * prev is equal to old) then we aren't acquiring anything new and + * we don't need any memory barrier as far I can tell. + */ + +static inline unsigned long +____cmpxchg(_u8, volatile char *m, unsigned char old, unsigned char new) +{ + unsigned long prev, tmp, cmp, addr64; + + __asm__ __volatile__( + " andnot %5,7,%4\n" + " insbl %1,%5,%1\n" + "1: ldq_l %2,0(%4)\n" + " extbl %2,%5,%0\n" + " cmpeq %0,%6,%3\n" + " beq %3,2f\n" + " mskbl %2,%5,%2\n" + " or %1,%2,%2\n" + " stq_c %2,0(%4)\n" + " beq %2,3f\n" + __ASM__MB + "2:\n" + ".subsection 2\n" + "3: br 1b\n" + ".previous" + : "=&r" (prev), "=&r" (new), "=&r" (tmp), "=&r" (cmp), "=&r" (addr64) + : "r" ((long)m), "Ir" (old), "1" (new) : "memory"); + + return prev; +} + +static inline unsigned long +____cmpxchg(_u16, volatile short *m, unsigned short old, unsigned short new) +{ + unsigned long prev, tmp, cmp, addr64; + + __asm__ __volatile__( + " andnot %5,7,%4\n" + " inswl %1,%5,%1\n" + "1: ldq_l %2,0(%4)\n" + " extwl %2,%5,%0\n" + " cmpeq %0,%6,%3\n" + " beq %3,2f\n" + " mskwl %2,%5,%2\n" + " or %1,%2,%2\n" + " stq_c %2,0(%4)\n" + " beq %2,3f\n" + __ASM__MB + "2:\n" + ".subsection 2\n" + "3: br 1b\n" + ".previous" + : "=&r" (prev), "=&r" (new), "=&r" (tmp), "=&r" (cmp), "=&r" (addr64) + : "r" ((long)m), "Ir" (old), "1" (new) : "memory"); + + return prev; +} + +static inline unsigned long +____cmpxchg(_u32, volatile int *m, int old, int new) +{ + unsigned long prev, cmp; + + __asm__ __volatile__( + "1: ldl_l %0,%5\n" + " cmpeq %0,%3,%1\n" + " beq %1,2f\n" + " mov %4,%1\n" + " stl_c %1,%2\n" + " beq %1,3f\n" + __ASM__MB + "2:\n" + ".subsection 2\n" + "3: br 1b\n" + ".previous" + : "=&r"(prev), "=&r"(cmp), "=m"(*m) + : "r"((long) old), "r"(new), "m"(*m) : "memory"); + + return prev; +} + +static inline unsigned long +____cmpxchg(_u64, volatile long *m, unsigned long old, unsigned long new) +{ + unsigned long prev, cmp; + + __asm__ __volatile__( + "1: ldq_l %0,%5\n" + " cmpeq %0,%3,%1\n" + " beq %1,2f\n" + " mov %4,%1\n" + " stq_c %1,%2\n" + " beq %1,3f\n" + __ASM__MB + "2:\n" + ".subsection 2\n" + "3: br 1b\n" + ".previous" + : "=&r"(prev), "=&r"(cmp), "=m"(*m) + : "r"((long) old), "r"(new), "m"(*m) : "memory"); + + return prev; +} + +/* This function doesn't exist, so you'll get a linker error + if something tries to do an invalid cmpxchg(). */ +extern void __cmpxchg_called_with_bad_pointer(void); + +static __always_inline unsigned long +____cmpxchg(, volatile void *ptr, unsigned long old, unsigned long new, + int size) +{ + switch (size) { + case 1: + return ____cmpxchg(_u8, ptr, old, new); + case 2: + return ____cmpxchg(_u16, ptr, old, new); + case 4: + return ____cmpxchg(_u32, ptr, old, new); + case 8: + return ____cmpxchg(_u64, ptr, old, new); + } + __cmpxchg_called_with_bad_pointer(); + return old; +} + +#endif diff --git a/arch/alpha/include/asm/xor.h b/arch/alpha/include/asm/xor.h new file mode 100644 index 000000000..5ee1c2bc0 --- /dev/null +++ b/arch/alpha/include/asm/xor.h @@ -0,0 +1,855 @@ +/* + * include/asm-alpha/xor.h + * + * Optimized RAID-5 checksumming functions for alpha EV5 and EV6 + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2, or (at your option) + * any later version. + * + * You should have received a copy of the GNU General Public License + * (for example /usr/src/linux/COPYING); if not, write to the Free + * Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. + */ + +extern void xor_alpha_2(unsigned long, unsigned long *, unsigned long *); +extern void xor_alpha_3(unsigned long, unsigned long *, unsigned long *, + unsigned long *); +extern void xor_alpha_4(unsigned long, unsigned long *, unsigned long *, + unsigned long *, unsigned long *); +extern void xor_alpha_5(unsigned long, unsigned long *, unsigned long *, + unsigned long *, unsigned long *, unsigned long *); + +extern void xor_alpha_prefetch_2(unsigned long, unsigned long *, + unsigned long *); +extern void xor_alpha_prefetch_3(unsigned long, unsigned long *, + unsigned long *, unsigned long *); +extern void xor_alpha_prefetch_4(unsigned long, unsigned long *, + unsigned long *, unsigned long *, + unsigned long *); +extern void xor_alpha_prefetch_5(unsigned long, unsigned long *, + unsigned long *, unsigned long *, + unsigned long *, unsigned long *); + +asm(" \n\ + .text \n\ + .align 3 \n\ + .ent xor_alpha_2 \n\ +xor_alpha_2: \n\ + .prologue 0 \n\ + srl $16, 6, $16 \n\ + .align 4 \n\ +2: \n\ + ldq $0,0($17) \n\ + ldq $1,0($18) \n\ + ldq $2,8($17) \n\ + ldq $3,8($18) \n\ + \n\ + ldq $4,16($17) \n\ + ldq $5,16($18) \n\ + ldq $6,24($17) \n\ + ldq $7,24($18) \n\ + \n\ + ldq $19,32($17) \n\ + ldq $20,32($18) \n\ + ldq $21,40($17) \n\ + ldq $22,40($18) \n\ + \n\ + ldq $23,48($17) \n\ + ldq $24,48($18) \n\ + ldq $25,56($17) \n\ + xor $0,$1,$0 # 7 cycles from $1 load \n\ + \n\ + ldq $27,56($18) \n\ + xor $2,$3,$2 \n\ + stq $0,0($17) \n\ + xor $4,$5,$4 \n\ + \n\ + stq $2,8($17) \n\ + xor $6,$7,$6 \n\ + stq $4,16($17) \n\ + xor $19,$20,$19 \n\ + \n\ + stq $6,24($17) \n\ + xor $21,$22,$21 \n\ + stq $19,32($17) \n\ + xor $23,$24,$23 \n\ + \n\ + stq $21,40($17) \n\ + xor $25,$27,$25 \n\ + stq $23,48($17) \n\ + subq $16,1,$16 \n\ + \n\ + stq $25,56($17) \n\ + addq $17,64,$17 \n\ + addq $18,64,$18 \n\ + bgt $16,2b \n\ + \n\ + ret \n\ + .end xor_alpha_2 \n\ + \n\ + .align 3 \n\ + .ent xor_alpha_3 \n\ +xor_alpha_3: \n\ + .prologue 0 \n\ + srl $16, 6, $16 \n\ + .align 4 \n\ +3: \n\ + ldq $0,0($17) \n\ + ldq $1,0($18) \n\ + ldq $2,0($19) \n\ + ldq $3,8($17) \n\ + \n\ + ldq $4,8($18) \n\ + ldq $6,16($17) \n\ + ldq $7,16($18) \n\ + ldq $21,24($17) \n\ + \n\ + ldq $22,24($18) \n\ + ldq $24,32($17) \n\ + ldq $25,32($18) \n\ + ldq $5,8($19) \n\ + \n\ + ldq $20,16($19) \n\ + ldq $23,24($19) \n\ + ldq $27,32($19) \n\ + nop \n\ + \n\ + xor $0,$1,$1 # 8 cycles from $0 load \n\ + xor $3,$4,$4 # 6 cycles from $4 load \n\ + xor $6,$7,$7 # 6 cycles from $7 load \n\ + xor $21,$22,$22 # 5 cycles from $22 load \n\ + \n\ + xor $1,$2,$2 # 9 cycles from $2 load \n\ + xor $24,$25,$25 # 5 cycles from $25 load \n\ + stq $2,0($17) \n\ + xor $4,$5,$5 # 6 cycles from $5 load \n\ + \n\ + stq $5,8($17) \n\ + xor $7,$20,$20 # 7 cycles from $20 load \n\ + stq $20,16($17) \n\ + xor $22,$23,$23 # 7 cycles from $23 load \n\ + \n\ + stq $23,24($17) \n\ + xor $25,$27,$27 # 7 cycles from $27 load \n\ + stq $27,32($17) \n\ + nop \n\ + \n\ + ldq $0,40($17) \n\ + ldq $1,40($18) \n\ + ldq $3,48($17) \n\ + ldq $4,48($18) \n\ + \n\ + ldq $6,56($17) \n\ + ldq $7,56($18) \n\ + ldq $2,40($19) \n\ + ldq $5,48($19) \n\ + \n\ + ldq $20,56($19) \n\ + xor $0,$1,$1 # 4 cycles from $1 load \n\ + xor $3,$4,$4 # 5 cycles from $4 load \n\ + xor $6,$7,$7 # 5 cycles from $7 load \n\ + \n\ + xor $1,$2,$2 # 4 cycles from $2 load \n\ + xor $4,$5,$5 # 5 cycles from $5 load \n\ + stq $2,40($17) \n\ + xor $7,$20,$20 # 4 cycles from $20 load \n\ + \n\ + stq $5,48($17) \n\ + subq $16,1,$16 \n\ + stq $20,56($17) \n\ + addq $19,64,$19 \n\ + \n\ + addq $18,64,$18 \n\ + addq $17,64,$17 \n\ + bgt $16,3b \n\ + ret \n\ + .end xor_alpha_3 \n\ + \n\ + .align 3 \n\ + .ent xor_alpha_4 \n\ +xor_alpha_4: \n\ + .prologue 0 \n\ + srl $16, 6, $16 \n\ + .align 4 \n\ +4: \n\ + ldq $0,0($17) \n\ + ldq $1,0($18) \n\ + ldq $2,0($19) \n\ + ldq $3,0($20) \n\ + \n\ + ldq $4,8($17) \n\ + ldq $5,8($18) \n\ + ldq $6,8($19) \n\ + ldq $7,8($20) \n\ + \n\ + ldq $21,16($17) \n\ + ldq $22,16($18) \n\ + ldq $23,16($19) \n\ + ldq $24,16($20) \n\ + \n\ + ldq $25,24($17) \n\ + xor $0,$1,$1 # 6 cycles from $1 load \n\ + ldq $27,24($18) \n\ + xor $2,$3,$3 # 6 cycles from $3 load \n\ + \n\ + ldq $0,24($19) \n\ + xor $1,$3,$3 \n\ + ldq $1,24($20) \n\ + xor $4,$5,$5 # 7 cycles from $5 load \n\ + \n\ + stq $3,0($17) \n\ + xor $6,$7,$7 \n\ + xor $21,$22,$22 # 7 cycles from $22 load \n\ + xor $5,$7,$7 \n\ + \n\ + stq $7,8($17) \n\ + xor $23,$24,$24 # 7 cycles from $24 load \n\ + ldq $2,32($17) \n\ + xor $22,$24,$24 \n\ + \n\ + ldq $3,32($18) \n\ + ldq $4,32($19) \n\ + ldq $5,32($20) \n\ + xor $25,$27,$27 # 8 cycles from $27 load \n\ + \n\ + ldq $6,40($17) \n\ + ldq $7,40($18) \n\ + ldq $21,40($19) \n\ + ldq $22,40($20) \n\ + \n\ + stq $24,16($17) \n\ + xor $0,$1,$1 # 9 cycles from $1 load \n\ + xor $2,$3,$3 # 5 cycles from $3 load \n\ + xor $27,$1,$1 \n\ + \n\ + stq $1,24($17) \n\ + xor $4,$5,$5 # 5 cycles from $5 load \n\ + ldq $23,48($17) \n\ + ldq $24,48($18) \n\ + \n\ + ldq $25,48($19) \n\ + xor $3,$5,$5 \n\ + ldq $27,48($20) \n\ + ldq $0,56($17) \n\ + \n\ + ldq $1,56($18) \n\ + ldq $2,56($19) \n\ + xor $6,$7,$7 # 8 cycles from $6 load \n\ + ldq $3,56($20) \n\ + \n\ + stq $5,32($17) \n\ + xor $21,$22,$22 # 8 cycles from $22 load \n\ + xor $7,$22,$22 \n\ + xor $23,$24,$24 # 5 cycles from $24 load \n\ + \n\ + stq $22,40($17) \n\ + xor $25,$27,$27 # 5 cycles from $27 load \n\ + xor $24,$27,$27 \n\ + xor $0,$1,$1 # 5 cycles from $1 load \n\ + \n\ + stq $27,48($17) \n\ + xor $2,$3,$3 # 4 cycles from $3 load \n\ + xor $1,$3,$3 \n\ + subq $16,1,$16 \n\ + \n\ + stq $3,56($17) \n\ + addq $20,64,$20 \n\ + addq $19,64,$19 \n\ + addq $18,64,$18 \n\ + \n\ + addq $17,64,$17 \n\ + bgt $16,4b \n\ + ret \n\ + .end xor_alpha_4 \n\ + \n\ + .align 3 \n\ + .ent xor_alpha_5 \n\ +xor_alpha_5: \n\ + .prologue 0 \n\ + srl $16, 6, $16 \n\ + .align 4 \n\ +5: \n\ + ldq $0,0($17) \n\ + ldq $1,0($18) \n\ + ldq $2,0($19) \n\ + ldq $3,0($20) \n\ + \n\ + ldq $4,0($21) \n\ + ldq $5,8($17) \n\ + ldq $6,8($18) \n\ + ldq $7,8($19) \n\ + \n\ + ldq $22,8($20) \n\ + ldq $23,8($21) \n\ + ldq $24,16($17) \n\ + ldq $25,16($18) \n\ + \n\ + ldq $27,16($19) \n\ + xor $0,$1,$1 # 6 cycles from $1 load \n\ + ldq $28,16($20) \n\ + xor $2,$3,$3 # 6 cycles from $3 load \n\ + \n\ + ldq $0,16($21) \n\ + xor $1,$3,$3 \n\ + ldq $1,24($17) \n\ + xor $3,$4,$4 # 7 cycles from $4 load \n\ + \n\ + stq $4,0($17) \n\ + xor $5,$6,$6 # 7 cycles from $6 load \n\ + xor $7,$22,$22 # 7 cycles from $22 load \n\ + xor $6,$23,$23 # 7 cycles from $23 load \n\ + \n\ + ldq $2,24($18) \n\ + xor $22,$23,$23 \n\ + ldq $3,24($19) \n\ + xor $24,$25,$25 # 8 cycles from $25 load \n\ + \n\ + stq $23,8($17) \n\ + xor $25,$27,$27 # 8 cycles from $27 load \n\ + ldq $4,24($20) \n\ + xor $28,$0,$0 # 7 cycles from $0 load \n\ + \n\ + ldq $5,24($21) \n\ + xor $27,$0,$0 \n\ + ldq $6,32($17) \n\ + ldq $7,32($18) \n\ + \n\ + stq $0,16($17) \n\ + xor $1,$2,$2 # 6 cycles from $2 load \n\ + ldq $22,32($19) \n\ + xor $3,$4,$4 # 4 cycles from $4 load \n\ + \n\ + ldq $23,32($20) \n\ + xor $2,$4,$4 \n\ + ldq $24,32($21) \n\ + ldq $25,40($17) \n\ + \n\ + ldq $27,40($18) \n\ + ldq $28,40($19) \n\ + ldq $0,40($20) \n\ + xor $4,$5,$5 # 7 cycles from $5 load \n\ + \n\ + stq $5,24($17) \n\ + xor $6,$7,$7 # 7 cycles from $7 load \n\ + ldq $1,40($21) \n\ + ldq $2,48($17) \n\ + \n\ + ldq $3,48($18) \n\ + xor $7,$22,$22 # 7 cycles from $22 load \n\ + ldq $4,48($19) \n\ + xor $23,$24,$24 # 6 cycles from $24 load \n\ + \n\ + ldq $5,48($20) \n\ + xor $22,$24,$24 \n\ + ldq $6,48($21) \n\ + xor $25,$27,$27 # 7 cycles from $27 load \n\ + \n\ + stq $24,32($17) \n\ + xor $27,$28,$28 # 8 cycles from $28 load \n\ + ldq $7,56($17) \n\ + xor $0,$1,$1 # 6 cycles from $1 load \n\ + \n\ + ldq $22,56($18) \n\ + ldq $23,56($19) \n\ + ldq $24,56($20) \n\ + ldq $25,56($21) \n\ + \n\ + xor $28,$1,$1 \n\ + xor $2,$3,$3 # 9 cycles from $3 load \n\ + xor $3,$4,$4 # 9 cycles from $4 load \n\ + xor $5,$6,$6 # 8 cycles from $6 load \n\ + \n\ + stq $1,40($17) \n\ + xor $4,$6,$6 \n\ + xor $7,$22,$22 # 7 cycles from $22 load \n\ + xor $23,$24,$24 # 6 cycles from $24 load \n\ + \n\ + stq $6,48($17) \n\ + xor $22,$24,$24 \n\ + subq $16,1,$16 \n\ + xor $24,$25,$25 # 8 cycles from $25 load \n\ + \n\ + stq $25,56($17) \n\ + addq $21,64,$21 \n\ + addq $20,64,$20 \n\ + addq $19,64,$19 \n\ + \n\ + addq $18,64,$18 \n\ + addq $17,64,$17 \n\ + bgt $16,5b \n\ + ret \n\ + .end xor_alpha_5 \n\ + \n\ + .align 3 \n\ + .ent xor_alpha_prefetch_2 \n\ +xor_alpha_prefetch_2: \n\ + .prologue 0 \n\ + srl $16, 6, $16 \n\ + \n\ + ldq $31, 0($17) \n\ + ldq $31, 0($18) \n\ + \n\ + ldq $31, 64($17) \n\ + ldq $31, 64($18) \n\ + \n\ + ldq $31, 128($17) \n\ + ldq $31, 128($18) \n\ + \n\ + ldq $31, 192($17) \n\ + ldq $31, 192($18) \n\ + .align 4 \n\ +2: \n\ + ldq $0,0($17) \n\ + ldq $1,0($18) \n\ + ldq $2,8($17) \n\ + ldq $3,8($18) \n\ + \n\ + ldq $4,16($17) \n\ + ldq $5,16($18) \n\ + ldq $6,24($17) \n\ + ldq $7,24($18) \n\ + \n\ + ldq $19,32($17) \n\ + ldq $20,32($18) \n\ + ldq $21,40($17) \n\ + ldq $22,40($18) \n\ + \n\ + ldq $23,48($17) \n\ + ldq $24,48($18) \n\ + ldq $25,56($17) \n\ + ldq $27,56($18) \n\ + \n\ + ldq $31,256($17) \n\ + xor $0,$1,$0 # 8 cycles from $1 load \n\ + ldq $31,256($18) \n\ + xor $2,$3,$2 \n\ + \n\ + stq $0,0($17) \n\ + xor $4,$5,$4 \n\ + stq $2,8($17) \n\ + xor $6,$7,$6 \n\ + \n\ + stq $4,16($17) \n\ + xor $19,$20,$19 \n\ + stq $6,24($17) \n\ + xor $21,$22,$21 \n\ + \n\ + stq $19,32($17) \n\ + xor $23,$24,$23 \n\ + stq $21,40($17) \n\ + xor $25,$27,$25 \n\ + \n\ + stq $23,48($17) \n\ + subq $16,1,$16 \n\ + stq $25,56($17) \n\ + addq $17,64,$17 \n\ + \n\ + addq $18,64,$18 \n\ + bgt $16,2b \n\ + ret \n\ + .end xor_alpha_prefetch_2 \n\ + \n\ + .align 3 \n\ + .ent xor_alpha_prefetch_3 \n\ +xor_alpha_prefetch_3: \n\ + .prologue 0 \n\ + srl $16, 6, $16 \n\ + \n\ + ldq $31, 0($17) \n\ + ldq $31, 0($18) \n\ + ldq $31, 0($19) \n\ + \n\ + ldq $31, 64($17) \n\ + ldq $31, 64($18) \n\ + ldq $31, 64($19) \n\ + \n\ + ldq $31, 128($17) \n\ + ldq $31, 128($18) \n\ + ldq $31, 128($19) \n\ + \n\ + ldq $31, 192($17) \n\ + ldq $31, 192($18) \n\ + ldq $31, 192($19) \n\ + .align 4 \n\ +3: \n\ + ldq $0,0($17) \n\ + ldq $1,0($18) \n\ + ldq $2,0($19) \n\ + ldq $3,8($17) \n\ + \n\ + ldq $4,8($18) \n\ + ldq $6,16($17) \n\ + ldq $7,16($18) \n\ + ldq $21,24($17) \n\ + \n\ + ldq $22,24($18) \n\ + ldq $24,32($17) \n\ + ldq $25,32($18) \n\ + ldq $5,8($19) \n\ + \n\ + ldq $20,16($19) \n\ + ldq $23,24($19) \n\ + ldq $27,32($19) \n\ + nop \n\ + \n\ + xor $0,$1,$1 # 8 cycles from $0 load \n\ + xor $3,$4,$4 # 7 cycles from $4 load \n\ + xor $6,$7,$7 # 6 cycles from $7 load \n\ + xor $21,$22,$22 # 5 cycles from $22 load \n\ + \n\ + xor $1,$2,$2 # 9 cycles from $2 load \n\ + xor $24,$25,$25 # 5 cycles from $25 load \n\ + stq $2,0($17) \n\ + xor $4,$5,$5 # 6 cycles from $5 load \n\ + \n\ + stq $5,8($17) \n\ + xor $7,$20,$20 # 7 cycles from $20 load \n\ + stq $20,16($17) \n\ + xor $22,$23,$23 # 7 cycles from $23 load \n\ + \n\ + stq $23,24($17) \n\ + xor $25,$27,$27 # 7 cycles from $27 load \n\ + stq $27,32($17) \n\ + nop \n\ + \n\ + ldq $0,40($17) \n\ + ldq $1,40($18) \n\ + ldq $3,48($17) \n\ + ldq $4,48($18) \n\ + \n\ + ldq $6,56($17) \n\ + ldq $7,56($18) \n\ + ldq $2,40($19) \n\ + ldq $5,48($19) \n\ + \n\ + ldq $20,56($19) \n\ + ldq $31,256($17) \n\ + ldq $31,256($18) \n\ + ldq $31,256($19) \n\ + \n\ + xor $0,$1,$1 # 6 cycles from $1 load \n\ + xor $3,$4,$4 # 5 cycles from $4 load \n\ + xor $6,$7,$7 # 5 cycles from $7 load \n\ + xor $1,$2,$2 # 4 cycles from $2 load \n\ + \n\ + xor $4,$5,$5 # 5 cycles from $5 load \n\ + xor $7,$20,$20 # 4 cycles from $20 load \n\ + stq $2,40($17) \n\ + subq $16,1,$16 \n\ + \n\ + stq $5,48($17) \n\ + addq $19,64,$19 \n\ + stq $20,56($17) \n\ + addq $18,64,$18 \n\ + \n\ + addq $17,64,$17 \n\ + bgt $16,3b \n\ + ret \n\ + .end xor_alpha_prefetch_3 \n\ + \n\ + .align 3 \n\ + .ent xor_alpha_prefetch_4 \n\ +xor_alpha_prefetch_4: \n\ + .prologue 0 \n\ + srl $16, 6, $16 \n\ + \n\ + ldq $31, 0($17) \n\ + ldq $31, 0($18) \n\ + ldq $31, 0($19) \n\ + ldq $31, 0($20) \n\ + \n\ + ldq $31, 64($17) \n\ + ldq $31, 64($18) \n\ + ldq $31, 64($19) \n\ + ldq $31, 64($20) \n\ + \n\ + ldq $31, 128($17) \n\ + ldq $31, 128($18) \n\ + ldq $31, 128($19) \n\ + ldq $31, 128($20) \n\ + \n\ + ldq $31, 192($17) \n\ + ldq $31, 192($18) \n\ + ldq $31, 192($19) \n\ + ldq $31, 192($20) \n\ + .align 4 \n\ +4: \n\ + ldq $0,0($17) \n\ + ldq $1,0($18) \n\ + ldq $2,0($19) \n\ + ldq $3,0($20) \n\ + \n\ + ldq $4,8($17) \n\ + ldq $5,8($18) \n\ + ldq $6,8($19) \n\ + ldq $7,8($20) \n\ + \n\ + ldq $21,16($17) \n\ + ldq $22,16($18) \n\ + ldq $23,16($19) \n\ + ldq $24,16($20) \n\ + \n\ + ldq $25,24($17) \n\ + xor $0,$1,$1 # 6 cycles from $1 load \n\ + ldq $27,24($18) \n\ + xor $2,$3,$3 # 6 cycles from $3 load \n\ + \n\ + ldq $0,24($19) \n\ + xor $1,$3,$3 \n\ + ldq $1,24($20) \n\ + xor $4,$5,$5 # 7 cycles from $5 load \n\ + \n\ + stq $3,0($17) \n\ + xor $6,$7,$7 \n\ + xor $21,$22,$22 # 7 cycles from $22 load \n\ + xor $5,$7,$7 \n\ + \n\ + stq $7,8($17) \n\ + xor $23,$24,$24 # 7 cycles from $24 load \n\ + ldq $2,32($17) \n\ + xor $22,$24,$24 \n\ + \n\ + ldq $3,32($18) \n\ + ldq $4,32($19) \n\ + ldq $5,32($20) \n\ + xor $25,$27,$27 # 8 cycles from $27 load \n\ + \n\ + ldq $6,40($17) \n\ + ldq $7,40($18) \n\ + ldq $21,40($19) \n\ + ldq $22,40($20) \n\ + \n\ + stq $24,16($17) \n\ + xor $0,$1,$1 # 9 cycles from $1 load \n\ + xor $2,$3,$3 # 5 cycles from $3 load \n\ + xor $27,$1,$1 \n\ + \n\ + stq $1,24($17) \n\ + xor $4,$5,$5 # 5 cycles from $5 load \n\ + ldq $23,48($17) \n\ + xor $3,$5,$5 \n\ + \n\ + ldq $24,48($18) \n\ + ldq $25,48($19) \n\ + ldq $27,48($20) \n\ + ldq $0,56($17) \n\ + \n\ + ldq $1,56($18) \n\ + ldq $2,56($19) \n\ + ldq $3,56($20) \n\ + xor $6,$7,$7 # 8 cycles from $6 load \n\ + \n\ + ldq $31,256($17) \n\ + xor $21,$22,$22 # 8 cycles from $22 load \n\ + ldq $31,256($18) \n\ + xor $7,$22,$22 \n\ + \n\ + ldq $31,256($19) \n\ + xor $23,$24,$24 # 6 cycles from $24 load \n\ + ldq $31,256($20) \n\ + xor $25,$27,$27 # 6 cycles from $27 load \n\ + \n\ + stq $5,32($17) \n\ + xor $24,$27,$27 \n\ + xor $0,$1,$1 # 7 cycles from $1 load \n\ + xor $2,$3,$3 # 6 cycles from $3 load \n\ + \n\ + stq $22,40($17) \n\ + xor $1,$3,$3 \n\ + stq $27,48($17) \n\ + subq $16,1,$16 \n\ + \n\ + stq $3,56($17) \n\ + addq $20,64,$20 \n\ + addq $19,64,$19 \n\ + addq $18,64,$18 \n\ + \n\ + addq $17,64,$17 \n\ + bgt $16,4b \n\ + ret \n\ + .end xor_alpha_prefetch_4 \n\ + \n\ + .align 3 \n\ + .ent xor_alpha_prefetch_5 \n\ +xor_alpha_prefetch_5: \n\ + .prologue 0 \n\ + srl $16, 6, $16 \n\ + \n\ + ldq $31, 0($17) \n\ + ldq $31, 0($18) \n\ + ldq $31, 0($19) \n\ + ldq $31, 0($20) \n\ + ldq $31, 0($21) \n\ + \n\ + ldq $31, 64($17) \n\ + ldq $31, 64($18) \n\ + ldq $31, 64($19) \n\ + ldq $31, 64($20) \n\ + ldq $31, 64($21) \n\ + \n\ + ldq $31, 128($17) \n\ + ldq $31, 128($18) \n\ + ldq $31, 128($19) \n\ + ldq $31, 128($20) \n\ + ldq $31, 128($21) \n\ + \n\ + ldq $31, 192($17) \n\ + ldq $31, 192($18) \n\ + ldq $31, 192($19) \n\ + ldq $31, 192($20) \n\ + ldq $31, 192($21) \n\ + .align 4 \n\ +5: \n\ + ldq $0,0($17) \n\ + ldq $1,0($18) \n\ + ldq $2,0($19) \n\ + ldq $3,0($20) \n\ + \n\ + ldq $4,0($21) \n\ + ldq $5,8($17) \n\ + ldq $6,8($18) \n\ + ldq $7,8($19) \n\ + \n\ + ldq $22,8($20) \n\ + ldq $23,8($21) \n\ + ldq $24,16($17) \n\ + ldq $25,16($18) \n\ + \n\ + ldq $27,16($19) \n\ + xor $0,$1,$1 # 6 cycles from $1 load \n\ + ldq $28,16($20) \n\ + xor $2,$3,$3 # 6 cycles from $3 load \n\ + \n\ + ldq $0,16($21) \n\ + xor $1,$3,$3 \n\ + ldq $1,24($17) \n\ + xor $3,$4,$4 # 7 cycles from $4 load \n\ + \n\ + stq $4,0($17) \n\ + xor $5,$6,$6 # 7 cycles from $6 load \n\ + xor $7,$22,$22 # 7 cycles from $22 load \n\ + xor $6,$23,$23 # 7 cycles from $23 load \n\ + \n\ + ldq $2,24($18) \n\ + xor $22,$23,$23 \n\ + ldq $3,24($19) \n\ + xor $24,$25,$25 # 8 cycles from $25 load \n\ + \n\ + stq $23,8($17) \n\ + xor $25,$27,$27 # 8 cycles from $27 load \n\ + ldq $4,24($20) \n\ + xor $28,$0,$0 # 7 cycles from $0 load \n\ + \n\ + ldq $5,24($21) \n\ + xor $27,$0,$0 \n\ + ldq $6,32($17) \n\ + ldq $7,32($18) \n\ + \n\ + stq $0,16($17) \n\ + xor $1,$2,$2 # 6 cycles from $2 load \n\ + ldq $22,32($19) \n\ + xor $3,$4,$4 # 4 cycles from $4 load \n\ + \n\ + ldq $23,32($20) \n\ + xor $2,$4,$4 \n\ + ldq $24,32($21) \n\ + ldq $25,40($17) \n\ + \n\ + ldq $27,40($18) \n\ + ldq $28,40($19) \n\ + ldq $0,40($20) \n\ + xor $4,$5,$5 # 7 cycles from $5 load \n\ + \n\ + stq $5,24($17) \n\ + xor $6,$7,$7 # 7 cycles from $7 load \n\ + ldq $1,40($21) \n\ + ldq $2,48($17) \n\ + \n\ + ldq $3,48($18) \n\ + xor $7,$22,$22 # 7 cycles from $22 load \n\ + ldq $4,48($19) \n\ + xor $23,$24,$24 # 6 cycles from $24 load \n\ + \n\ + ldq $5,48($20) \n\ + xor $22,$24,$24 \n\ + ldq $6,48($21) \n\ + xor $25,$27,$27 # 7 cycles from $27 load \n\ + \n\ + stq $24,32($17) \n\ + xor $27,$28,$28 # 8 cycles from $28 load \n\ + ldq $7,56($17) \n\ + xor $0,$1,$1 # 6 cycles from $1 load \n\ + \n\ + ldq $22,56($18) \n\ + ldq $23,56($19) \n\ + ldq $24,56($20) \n\ + ldq $25,56($21) \n\ + \n\ + ldq $31,256($17) \n\ + xor $28,$1,$1 \n\ + ldq $31,256($18) \n\ + xor $2,$3,$3 # 9 cycles from $3 load \n\ + \n\ + ldq $31,256($19) \n\ + xor $3,$4,$4 # 9 cycles from $4 load \n\ + ldq $31,256($20) \n\ + xor $5,$6,$6 # 8 cycles from $6 load \n\ + \n\ + stq $1,40($17) \n\ + xor $4,$6,$6 \n\ + xor $7,$22,$22 # 7 cycles from $22 load \n\ + xor $23,$24,$24 # 6 cycles from $24 load \n\ + \n\ + stq $6,48($17) \n\ + xor $22,$24,$24 \n\ + ldq $31,256($21) \n\ + xor $24,$25,$25 # 8 cycles from $25 load \n\ + \n\ + stq $25,56($17) \n\ + subq $16,1,$16 \n\ + addq $21,64,$21 \n\ + addq $20,64,$20 \n\ + \n\ + addq $19,64,$19 \n\ + addq $18,64,$18 \n\ + addq $17,64,$17 \n\ + bgt $16,5b \n\ + \n\ + ret \n\ + .end xor_alpha_prefetch_5 \n\ +"); + +static struct xor_block_template xor_block_alpha = { + .name = "alpha", + .do_2 = xor_alpha_2, + .do_3 = xor_alpha_3, + .do_4 = xor_alpha_4, + .do_5 = xor_alpha_5, +}; + +static struct xor_block_template xor_block_alpha_prefetch = { + .name = "alpha prefetch", + .do_2 = xor_alpha_prefetch_2, + .do_3 = xor_alpha_prefetch_3, + .do_4 = xor_alpha_prefetch_4, + .do_5 = xor_alpha_prefetch_5, +}; + +/* For grins, also test the generic routines. */ +#include <asm-generic/xor.h> + +#undef XOR_TRY_TEMPLATES +#define XOR_TRY_TEMPLATES \ + do { \ + xor_speed(&xor_block_8regs); \ + xor_speed(&xor_block_32regs); \ + xor_speed(&xor_block_alpha); \ + xor_speed(&xor_block_alpha_prefetch); \ + } while (0) + +/* Force the use of alpha_prefetch if EV6, as it is significantly + faster in the cold cache case. */ +#define XOR_SELECT_TEMPLATE(FASTEST) \ + (implver() == IMPLVER_EV6 ? &xor_block_alpha_prefetch : FASTEST) |