diff options
Diffstat (limited to 'arch/mips/include')
71 files changed, 2090 insertions, 1945 deletions
diff --git a/arch/mips/include/asm/atomic.h b/arch/mips/include/asm/atomic.h index bb8658cc7f12..e5ac88392d1f 100644 --- a/arch/mips/include/asm/atomic.h +++ b/arch/mips/include/asm/atomic.h @@ -20,157 +20,176 @@ #include <asm/compiler.h> #include <asm/cpu-features.h> #include <asm/cmpxchg.h> +#include <asm/llsc.h> +#include <asm/sync.h> #include <asm/war.h> -/* - * Using a branch-likely instruction to check the result of an sc instruction - * works around a bug present in R10000 CPUs prior to revision 3.0 that could - * cause ll-sc sequences to execute non-atomically. - */ -#if R10000_LLSC_WAR -# define __scbeqz "beqzl" -#else -# define __scbeqz "beqz" -#endif - -#define ATOMIC_INIT(i) { (i) } +#define ATOMIC_OPS(pfx, type) \ +static __always_inline type pfx##_read(const pfx##_t *v) \ +{ \ + return READ_ONCE(v->counter); \ +} \ + \ +static __always_inline void pfx##_set(pfx##_t *v, type i) \ +{ \ + WRITE_ONCE(v->counter, i); \ +} \ + \ +static __always_inline type pfx##_cmpxchg(pfx##_t *v, type o, type n) \ +{ \ + return cmpxchg(&v->counter, o, n); \ +} \ + \ +static __always_inline type pfx##_xchg(pfx##_t *v, type n) \ +{ \ + return xchg(&v->counter, n); \ +} -/* - * atomic_read - read atomic variable - * @v: pointer of type atomic_t - * - * Atomically reads the value of @v. - */ -#define atomic_read(v) READ_ONCE((v)->counter) +#define ATOMIC_INIT(i) { (i) } +ATOMIC_OPS(atomic, int) -/* - * atomic_set - set atomic variable - * @v: pointer of type atomic_t - * @i: required value - * - * Atomically sets the value of @v to @i. - */ -#define atomic_set(v, i) WRITE_ONCE((v)->counter, (i)) +#ifdef CONFIG_64BIT +# define ATOMIC64_INIT(i) { (i) } +ATOMIC_OPS(atomic64, s64) +#endif -#define ATOMIC_OP(op, c_op, asm_op) \ -static __inline__ void atomic_##op(int i, atomic_t * v) \ -{ \ - if (kernel_uses_llsc) { \ - int temp; \ - \ - loongson_llsc_mb(); \ - __asm__ __volatile__( \ - " .set push \n" \ - " .set "MIPS_ISA_LEVEL" \n" \ - "1: ll %0, %1 # atomic_" #op " \n" \ - " " #asm_op " %0, %2 \n" \ - " sc %0, %1 \n" \ - "\t" __scbeqz " %0, 1b \n" \ - " .set pop \n" \ - : "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (v->counter) \ - : "Ir" (i) : __LLSC_CLOBBER); \ - } else { \ - unsigned long flags; \ - \ - raw_local_irq_save(flags); \ - v->counter c_op i; \ - raw_local_irq_restore(flags); \ - } \ +#define ATOMIC_OP(pfx, op, type, c_op, asm_op, ll, sc) \ +static __inline__ void pfx##_##op(type i, pfx##_t * v) \ +{ \ + type temp; \ + \ + if (!kernel_uses_llsc) { \ + unsigned long flags; \ + \ + raw_local_irq_save(flags); \ + v->counter c_op i; \ + raw_local_irq_restore(flags); \ + return; \ + } \ + \ + __asm__ __volatile__( \ + " .set push \n" \ + " .set " MIPS_ISA_LEVEL " \n" \ + " " __SYNC(full, loongson3_war) " \n" \ + "1: " #ll " %0, %1 # " #pfx "_" #op " \n" \ + " " #asm_op " %0, %2 \n" \ + " " #sc " %0, %1 \n" \ + "\t" __SC_BEQZ "%0, 1b \n" \ + " .set pop \n" \ + : "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (v->counter) \ + : "Ir" (i) : __LLSC_CLOBBER); \ } -#define ATOMIC_OP_RETURN(op, c_op, asm_op) \ -static __inline__ int atomic_##op##_return_relaxed(int i, atomic_t * v) \ -{ \ - int result; \ - \ - if (kernel_uses_llsc) { \ - int temp; \ - \ - loongson_llsc_mb(); \ - __asm__ __volatile__( \ - " .set push \n" \ - " .set "MIPS_ISA_LEVEL" \n" \ - "1: ll %1, %2 # atomic_" #op "_return \n" \ - " " #asm_op " %0, %1, %3 \n" \ - " sc %0, %2 \n" \ - "\t" __scbeqz " %0, 1b \n" \ - " " #asm_op " %0, %1, %3 \n" \ - " .set pop \n" \ - : "=&r" (result), "=&r" (temp), \ - "+" GCC_OFF_SMALL_ASM() (v->counter) \ - : "Ir" (i) : __LLSC_CLOBBER); \ - } else { \ - unsigned long flags; \ - \ - raw_local_irq_save(flags); \ - result = v->counter; \ - result c_op i; \ - v->counter = result; \ - raw_local_irq_restore(flags); \ - } \ - \ - return result; \ +#define ATOMIC_OP_RETURN(pfx, op, type, c_op, asm_op, ll, sc) \ +static __inline__ type pfx##_##op##_return_relaxed(type i, pfx##_t * v) \ +{ \ + type temp, result; \ + \ + if (!kernel_uses_llsc) { \ + unsigned long flags; \ + \ + raw_local_irq_save(flags); \ + result = v->counter; \ + result c_op i; \ + v->counter = result; \ + raw_local_irq_restore(flags); \ + return result; \ + } \ + \ + __asm__ __volatile__( \ + " .set push \n" \ + " .set " MIPS_ISA_LEVEL " \n" \ + " " __SYNC(full, loongson3_war) " \n" \ + "1: " #ll " %1, %2 # " #pfx "_" #op "_return\n" \ + " " #asm_op " %0, %1, %3 \n" \ + " " #sc " %0, %2 \n" \ + "\t" __SC_BEQZ "%0, 1b \n" \ + " " #asm_op " %0, %1, %3 \n" \ + " .set pop \n" \ + : "=&r" (result), "=&r" (temp), \ + "+" GCC_OFF_SMALL_ASM() (v->counter) \ + : "Ir" (i) : __LLSC_CLOBBER); \ + \ + return result; \ } -#define ATOMIC_FETCH_OP(op, c_op, asm_op) \ -static __inline__ int atomic_fetch_##op##_relaxed(int i, atomic_t * v) \ -{ \ - int result; \ - \ - if (kernel_uses_llsc) { \ - int temp; \ - \ - loongson_llsc_mb(); \ - __asm__ __volatile__( \ - " .set push \n" \ - " .set "MIPS_ISA_LEVEL" \n" \ - "1: ll %1, %2 # atomic_fetch_" #op " \n" \ - " " #asm_op " %0, %1, %3 \n" \ - " sc %0, %2 \n" \ - "\t" __scbeqz " %0, 1b \n" \ - " .set pop \n" \ - " move %0, %1 \n" \ - : "=&r" (result), "=&r" (temp), \ - "+" GCC_OFF_SMALL_ASM() (v->counter) \ - : "Ir" (i) : __LLSC_CLOBBER); \ - } else { \ - unsigned long flags; \ - \ - raw_local_irq_save(flags); \ - result = v->counter; \ - v->counter c_op i; \ - raw_local_irq_restore(flags); \ - } \ - \ - return result; \ +#define ATOMIC_FETCH_OP(pfx, op, type, c_op, asm_op, ll, sc) \ +static __inline__ type pfx##_fetch_##op##_relaxed(type i, pfx##_t * v) \ +{ \ + int temp, result; \ + \ + if (!kernel_uses_llsc) { \ + unsigned long flags; \ + \ + raw_local_irq_save(flags); \ + result = v->counter; \ + v->counter c_op i; \ + raw_local_irq_restore(flags); \ + return result; \ + } \ + \ + __asm__ __volatile__( \ + " .set push \n" \ + " .set " MIPS_ISA_LEVEL " \n" \ + " " __SYNC(full, loongson3_war) " \n" \ + "1: " #ll " %1, %2 # " #pfx "_fetch_" #op "\n" \ + " " #asm_op " %0, %1, %3 \n" \ + " " #sc " %0, %2 \n" \ + "\t" __SC_BEQZ "%0, 1b \n" \ + " .set pop \n" \ + " move %0, %1 \n" \ + : "=&r" (result), "=&r" (temp), \ + "+" GCC_OFF_SMALL_ASM() (v->counter) \ + : "Ir" (i) : __LLSC_CLOBBER); \ + \ + return result; \ } -#define ATOMIC_OPS(op, c_op, asm_op) \ - ATOMIC_OP(op, c_op, asm_op) \ - ATOMIC_OP_RETURN(op, c_op, asm_op) \ - ATOMIC_FETCH_OP(op, c_op, asm_op) +#undef ATOMIC_OPS +#define ATOMIC_OPS(pfx, op, type, c_op, asm_op, ll, sc) \ + ATOMIC_OP(pfx, op, type, c_op, asm_op, ll, sc) \ + ATOMIC_OP_RETURN(pfx, op, type, c_op, asm_op, ll, sc) \ + ATOMIC_FETCH_OP(pfx, op, type, c_op, asm_op, ll, sc) -ATOMIC_OPS(add, +=, addu) -ATOMIC_OPS(sub, -=, subu) +ATOMIC_OPS(atomic, add, int, +=, addu, ll, sc) +ATOMIC_OPS(atomic, sub, int, -=, subu, ll, sc) #define atomic_add_return_relaxed atomic_add_return_relaxed #define atomic_sub_return_relaxed atomic_sub_return_relaxed #define atomic_fetch_add_relaxed atomic_fetch_add_relaxed #define atomic_fetch_sub_relaxed atomic_fetch_sub_relaxed +#ifdef CONFIG_64BIT +ATOMIC_OPS(atomic64, add, s64, +=, daddu, lld, scd) +ATOMIC_OPS(atomic64, sub, s64, -=, dsubu, lld, scd) +# define atomic64_add_return_relaxed atomic64_add_return_relaxed +# define atomic64_sub_return_relaxed atomic64_sub_return_relaxed +# define atomic64_fetch_add_relaxed atomic64_fetch_add_relaxed +# define atomic64_fetch_sub_relaxed atomic64_fetch_sub_relaxed +#endif /* CONFIG_64BIT */ + #undef ATOMIC_OPS -#define ATOMIC_OPS(op, c_op, asm_op) \ - ATOMIC_OP(op, c_op, asm_op) \ - ATOMIC_FETCH_OP(op, c_op, asm_op) +#define ATOMIC_OPS(pfx, op, type, c_op, asm_op, ll, sc) \ + ATOMIC_OP(pfx, op, type, c_op, asm_op, ll, sc) \ + ATOMIC_FETCH_OP(pfx, op, type, c_op, asm_op, ll, sc) -ATOMIC_OPS(and, &=, and) -ATOMIC_OPS(or, |=, or) -ATOMIC_OPS(xor, ^=, xor) +ATOMIC_OPS(atomic, and, int, &=, and, ll, sc) +ATOMIC_OPS(atomic, or, int, |=, or, ll, sc) +ATOMIC_OPS(atomic, xor, int, ^=, xor, ll, sc) #define atomic_fetch_and_relaxed atomic_fetch_and_relaxed #define atomic_fetch_or_relaxed atomic_fetch_or_relaxed #define atomic_fetch_xor_relaxed atomic_fetch_xor_relaxed +#ifdef CONFIG_64BIT +ATOMIC_OPS(atomic64, and, s64, &=, and, lld, scd) +ATOMIC_OPS(atomic64, or, s64, |=, or, lld, scd) +ATOMIC_OPS(atomic64, xor, s64, ^=, xor, lld, scd) +# define atomic64_fetch_and_relaxed atomic64_fetch_and_relaxed +# define atomic64_fetch_or_relaxed atomic64_fetch_or_relaxed +# define atomic64_fetch_xor_relaxed atomic64_fetch_xor_relaxed +#endif + #undef ATOMIC_OPS #undef ATOMIC_FETCH_OP #undef ATOMIC_OP_RETURN @@ -184,258 +203,66 @@ ATOMIC_OPS(xor, ^=, xor) * Atomically test @v and subtract @i if @v is greater or equal than @i. * The function returns the old value of @v minus @i. */ -static __inline__ int atomic_sub_if_positive(int i, atomic_t * v) -{ - int result; - - smp_mb__before_llsc(); - - if (kernel_uses_llsc) { - int temp; - - loongson_llsc_mb(); - __asm__ __volatile__( - " .set push \n" - " .set "MIPS_ISA_LEVEL" \n" - "1: ll %1, %2 # atomic_sub_if_positive\n" - " .set pop \n" - " subu %0, %1, %3 \n" - " move %1, %0 \n" - " bltz %0, 2f \n" - " .set push \n" - " .set "MIPS_ISA_LEVEL" \n" - " sc %1, %2 \n" - "\t" __scbeqz " %1, 1b \n" - "2: \n" - " .set pop \n" - : "=&r" (result), "=&r" (temp), - "+" GCC_OFF_SMALL_ASM() (v->counter) - : "Ir" (i) : __LLSC_CLOBBER); - } else { - unsigned long flags; - - raw_local_irq_save(flags); - result = v->counter; - result -= i; - if (result >= 0) - v->counter = result; - raw_local_irq_restore(flags); - } - - smp_llsc_mb(); - - return result; +#define ATOMIC_SIP_OP(pfx, type, op, ll, sc) \ +static __inline__ int pfx##_sub_if_positive(type i, pfx##_t * v) \ +{ \ + type temp, result; \ + \ + smp_mb__before_atomic(); \ + \ + if (!kernel_uses_llsc) { \ + unsigned long flags; \ + \ + raw_local_irq_save(flags); \ + result = v->counter; \ + result -= i; \ + if (result >= 0) \ + v->counter = result; \ + raw_local_irq_restore(flags); \ + smp_mb__after_atomic(); \ + return result; \ + } \ + \ + __asm__ __volatile__( \ + " .set push \n" \ + " .set " MIPS_ISA_LEVEL " \n" \ + " " __SYNC(full, loongson3_war) " \n" \ + "1: " #ll " %1, %2 # atomic_sub_if_positive\n" \ + " .set pop \n" \ + " " #op " %0, %1, %3 \n" \ + " move %1, %0 \n" \ + " bltz %0, 2f \n" \ + " .set push \n" \ + " .set " MIPS_ISA_LEVEL " \n" \ + " " #sc " %1, %2 \n" \ + " " __SC_BEQZ "%1, 1b \n" \ + "2: " __SYNC(full, loongson3_war) " \n" \ + " .set pop \n" \ + : "=&r" (result), "=&r" (temp), \ + "+" GCC_OFF_SMALL_ASM() (v->counter) \ + : "Ir" (i) \ + : __LLSC_CLOBBER); \ + \ + /* \ + * In the Loongson3 workaround case we already have a \ + * completion barrier at 2: above, which is needed due to the \ + * bltz that can branch to code outside of the LL/SC loop. As \ + * such, we don't need to emit another barrier here. \ + */ \ + if (!__SYNC_loongson3_war) \ + smp_mb__after_atomic(); \ + \ + return result; \ } -#define atomic_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n))) -#define atomic_xchg(v, new) (xchg(&((v)->counter), (new))) - -/* - * atomic_dec_if_positive - decrement by 1 if old value positive - * @v: pointer of type atomic_t - */ +ATOMIC_SIP_OP(atomic, int, subu, ll, sc) #define atomic_dec_if_positive(v) atomic_sub_if_positive(1, v) #ifdef CONFIG_64BIT - -#define ATOMIC64_INIT(i) { (i) } - -/* - * atomic64_read - read atomic variable - * @v: pointer of type atomic64_t - * - */ -#define atomic64_read(v) READ_ONCE((v)->counter) - -/* - * atomic64_set - set atomic variable - * @v: pointer of type atomic64_t - * @i: required value - */ -#define atomic64_set(v, i) WRITE_ONCE((v)->counter, (i)) - -#define ATOMIC64_OP(op, c_op, asm_op) \ -static __inline__ void atomic64_##op(s64 i, atomic64_t * v) \ -{ \ - if (kernel_uses_llsc) { \ - s64 temp; \ - \ - loongson_llsc_mb(); \ - __asm__ __volatile__( \ - " .set push \n" \ - " .set "MIPS_ISA_LEVEL" \n" \ - "1: lld %0, %1 # atomic64_" #op " \n" \ - " " #asm_op " %0, %2 \n" \ - " scd %0, %1 \n" \ - "\t" __scbeqz " %0, 1b \n" \ - " .set pop \n" \ - : "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (v->counter) \ - : "Ir" (i) : __LLSC_CLOBBER); \ - } else { \ - unsigned long flags; \ - \ - raw_local_irq_save(flags); \ - v->counter c_op i; \ - raw_local_irq_restore(flags); \ - } \ -} - -#define ATOMIC64_OP_RETURN(op, c_op, asm_op) \ -static __inline__ s64 atomic64_##op##_return_relaxed(s64 i, atomic64_t * v) \ -{ \ - s64 result; \ - \ - if (kernel_uses_llsc) { \ - s64 temp; \ - \ - loongson_llsc_mb(); \ - __asm__ __volatile__( \ - " .set push \n" \ - " .set "MIPS_ISA_LEVEL" \n" \ - "1: lld %1, %2 # atomic64_" #op "_return\n" \ - " " #asm_op " %0, %1, %3 \n" \ - " scd %0, %2 \n" \ - "\t" __scbeqz " %0, 1b \n" \ - " " #asm_op " %0, %1, %3 \n" \ - " .set pop \n" \ - : "=&r" (result), "=&r" (temp), \ - "+" GCC_OFF_SMALL_ASM() (v->counter) \ - : "Ir" (i) : __LLSC_CLOBBER); \ - } else { \ - unsigned long flags; \ - \ - raw_local_irq_save(flags); \ - result = v->counter; \ - result c_op i; \ - v->counter = result; \ - raw_local_irq_restore(flags); \ - } \ - \ - return result; \ -} - -#define ATOMIC64_FETCH_OP(op, c_op, asm_op) \ -static __inline__ s64 atomic64_fetch_##op##_relaxed(s64 i, atomic64_t * v) \ -{ \ - s64 result; \ - \ - if (kernel_uses_llsc) { \ - s64 temp; \ - \ - loongson_llsc_mb(); \ - __asm__ __volatile__( \ - " .set push \n" \ - " .set "MIPS_ISA_LEVEL" \n" \ - "1: lld %1, %2 # atomic64_fetch_" #op "\n" \ - " " #asm_op " %0, %1, %3 \n" \ - " scd %0, %2 \n" \ - "\t" __scbeqz " %0, 1b \n" \ - " move %0, %1 \n" \ - " .set pop \n" \ - : "=&r" (result), "=&r" (temp), \ - "+" GCC_OFF_SMALL_ASM() (v->counter) \ - : "Ir" (i) : __LLSC_CLOBBER); \ - } else { \ - unsigned long flags; \ - \ - raw_local_irq_save(flags); \ - result = v->counter; \ - v->counter c_op i; \ - raw_local_irq_restore(flags); \ - } \ - \ - return result; \ -} - -#define ATOMIC64_OPS(op, c_op, asm_op) \ - ATOMIC64_OP(op, c_op, asm_op) \ - ATOMIC64_OP_RETURN(op, c_op, asm_op) \ - ATOMIC64_FETCH_OP(op, c_op, asm_op) - -ATOMIC64_OPS(add, +=, daddu) -ATOMIC64_OPS(sub, -=, dsubu) - -#define atomic64_add_return_relaxed atomic64_add_return_relaxed -#define atomic64_sub_return_relaxed atomic64_sub_return_relaxed -#define atomic64_fetch_add_relaxed atomic64_fetch_add_relaxed -#define atomic64_fetch_sub_relaxed atomic64_fetch_sub_relaxed - -#undef ATOMIC64_OPS -#define ATOMIC64_OPS(op, c_op, asm_op) \ - ATOMIC64_OP(op, c_op, asm_op) \ - ATOMIC64_FETCH_OP(op, c_op, asm_op) - -ATOMIC64_OPS(and, &=, and) -ATOMIC64_OPS(or, |=, or) -ATOMIC64_OPS(xor, ^=, xor) - -#define atomic64_fetch_and_relaxed atomic64_fetch_and_relaxed -#define atomic64_fetch_or_relaxed atomic64_fetch_or_relaxed -#define atomic64_fetch_xor_relaxed atomic64_fetch_xor_relaxed - -#undef ATOMIC64_OPS -#undef ATOMIC64_FETCH_OP -#undef ATOMIC64_OP_RETURN -#undef ATOMIC64_OP - -/* - * atomic64_sub_if_positive - conditionally subtract integer from atomic - * variable - * @i: integer value to subtract - * @v: pointer of type atomic64_t - * - * Atomically test @v and subtract @i if @v is greater or equal than @i. - * The function returns the old value of @v minus @i. - */ -static __inline__ s64 atomic64_sub_if_positive(s64 i, atomic64_t * v) -{ - s64 result; - - smp_mb__before_llsc(); - - if (kernel_uses_llsc) { - s64 temp; - - __asm__ __volatile__( - " .set push \n" - " .set "MIPS_ISA_LEVEL" \n" - "1: lld %1, %2 # atomic64_sub_if_positive\n" - " dsubu %0, %1, %3 \n" - " move %1, %0 \n" - " bltz %0, 1f \n" - " scd %1, %2 \n" - "\t" __scbeqz " %1, 1b \n" - "1: \n" - " .set pop \n" - : "=&r" (result), "=&r" (temp), - "+" GCC_OFF_SMALL_ASM() (v->counter) - : "Ir" (i)); - } else { - unsigned long flags; - - raw_local_irq_save(flags); - result = v->counter; - result -= i; - if (result >= 0) - v->counter = result; - raw_local_irq_restore(flags); - } - - smp_llsc_mb(); - - return result; -} - -#define atomic64_cmpxchg(v, o, n) \ - ((__typeof__((v)->counter))cmpxchg(&((v)->counter), (o), (n))) -#define atomic64_xchg(v, new) (xchg(&((v)->counter), (new))) - -/* - * atomic64_dec_if_positive - decrement by 1 if old value positive - * @v: pointer of type atomic64_t - */ +ATOMIC_SIP_OP(atomic64, s64, dsubu, lld, scd) #define atomic64_dec_if_positive(v) atomic64_sub_if_positive(1, v) +#endif -#endif /* CONFIG_64BIT */ +#undef ATOMIC_SIP_OP #endif /* _ASM_ATOMIC_H */ diff --git a/arch/mips/include/asm/barrier.h b/arch/mips/include/asm/barrier.h index 9228f7386220..49ff172a72b9 100644 --- a/arch/mips/include/asm/barrier.h +++ b/arch/mips/include/asm/barrier.h @@ -9,131 +9,26 @@ #define __ASM_BARRIER_H #include <asm/addrspace.h> +#include <asm/sync.h> -/* - * Sync types defined by the MIPS architecture (document MD00087 table 6.5) - * These values are used with the sync instruction to perform memory barriers. - * Types of ordering guarantees available through the SYNC instruction: - * - Completion Barriers - * - Ordering Barriers - * As compared to the completion barrier, the ordering barrier is a - * lighter-weight operation as it does not require the specified instructions - * before the SYNC to be already completed. Instead it only requires that those - * specified instructions which are subsequent to the SYNC in the instruction - * stream are never re-ordered for processing ahead of the specified - * instructions which are before the SYNC in the instruction stream. - * This potentially reduces how many cycles the barrier instruction must stall - * before it completes. - * Implementations that do not use any of the non-zero values of stype to define - * different barriers, such as ordering barriers, must make those stype values - * act the same as stype zero. - */ - -/* - * Completion barriers: - * - Every synchronizable specified memory instruction (loads or stores or both) - * that occurs in the instruction stream before the SYNC instruction must be - * already globally performed before any synchronizable specified memory - * instructions that occur after the SYNC are allowed to be performed, with - * respect to any other processor or coherent I/O module. - * - * - The barrier does not guarantee the order in which instruction fetches are - * performed. - * - * - A stype value of zero will always be defined such that it performs the most - * complete set of synchronization operations that are defined.This means - * stype zero always does a completion barrier that affects both loads and - * stores preceding the SYNC instruction and both loads and stores that are - * subsequent to the SYNC instruction. Non-zero values of stype may be defined - * by the architecture or specific implementations to perform synchronization - * behaviors that are less complete than that of stype zero. If an - * implementation does not use one of these non-zero values to define a - * different synchronization behavior, then that non-zero value of stype must - * act the same as stype zero completion barrier. This allows software written - * for an implementation with a lighter-weight barrier to work on another - * implementation which only implements the stype zero completion barrier. - * - * - A completion barrier is required, potentially in conjunction with SSNOP (in - * Release 1 of the Architecture) or EHB (in Release 2 of the Architecture), - * to guarantee that memory reference results are visible across operating - * mode changes. For example, a completion barrier is required on some - * implementations on entry to and exit from Debug Mode to guarantee that - * memory effects are handled correctly. - */ - -/* - * stype 0 - A completion barrier that affects preceding loads and stores and - * subsequent loads and stores. - * Older instructions which must reach the load/store ordering point before the - * SYNC instruction completes: Loads, Stores - * Younger instructions which must reach the load/store ordering point only - * after the SYNC instruction completes: Loads, Stores - * Older instructions which must be globally performed when the SYNC instruction - * completes: Loads, Stores - */ -#define STYPE_SYNC 0x0 - -/* - * Ordering barriers: - * - Every synchronizable specified memory instruction (loads or stores or both) - * that occurs in the instruction stream before the SYNC instruction must - * reach a stage in the load/store datapath after which no instruction - * re-ordering is possible before any synchronizable specified memory - * instruction which occurs after the SYNC instruction in the instruction - * stream reaches the same stage in the load/store datapath. - * - * - If any memory instruction before the SYNC instruction in program order, - * generates a memory request to the external memory and any memory - * instruction after the SYNC instruction in program order also generates a - * memory request to external memory, the memory request belonging to the - * older instruction must be globally performed before the time the memory - * request belonging to the younger instruction is globally performed. - * - * - The barrier does not guarantee the order in which instruction fetches are - * performed. - */ +static inline void __sync(void) +{ + asm volatile(__SYNC(full, always) ::: "memory"); +} -/* - * stype 0x10 - An ordering barrier that affects preceding loads and stores and - * subsequent loads and stores. - * Older instructions which must reach the load/store ordering point before the - * SYNC instruction completes: Loads, Stores - * Younger instructions which must reach the load/store ordering point only - * after the SYNC instruction completes: Loads, Stores - * Older instructions which must be globally performed when the SYNC instruction - * completes: N/A - */ -#define STYPE_SYNC_MB 0x10 +static inline void rmb(void) +{ + asm volatile(__SYNC(rmb, always) ::: "memory"); +} +#define rmb rmb -/* - * stype 0x14 - A completion barrier specific to global invalidations - * - * When a sync instruction of this type completes any preceding GINVI or GINVT - * operation has been globalized & completed on all coherent CPUs. Anything - * that the GINV* instruction should invalidate will have been invalidated on - * all coherent CPUs when this instruction completes. It is implementation - * specific whether the GINV* instructions themselves will ensure completion, - * or this sync type will. - * - * In systems implementing global invalidates (ie. with Config5.GI == 2 or 3) - * this sync type also requires that previous SYNCI operations have completed. - */ -#define STYPE_GINV 0x14 +static inline void wmb(void) +{ + asm volatile(__SYNC(wmb, always) ::: "memory"); +} +#define wmb wmb -#ifdef CONFIG_CPU_HAS_SYNC -#define __sync() \ - __asm__ __volatile__( \ - ".set push\n\t" \ - ".set noreorder\n\t" \ - ".set mips2\n\t" \ - "sync\n\t" \ - ".set pop" \ - : /* no output */ \ - : /* no input */ \ - : "memory") -#else -#define __sync() do { } while(0) -#endif +#define fast_mb() __sync() #define __fast_iob() \ __asm__ __volatile__( \ @@ -146,17 +41,8 @@ : "m" (*(int *)CKSEG1) \ : "memory") #ifdef CONFIG_CPU_CAVIUM_OCTEON -# define OCTEON_SYNCW_STR ".set push\n.set arch=octeon\nsyncw\nsyncw\n.set pop\n" -# define __syncw() __asm__ __volatile__(OCTEON_SYNCW_STR : : : "memory") - -# define fast_wmb() __syncw() -# define fast_rmb() barrier() -# define fast_mb() __sync() # define fast_iob() do { } while (0) #else /* ! CONFIG_CPU_CAVIUM_OCTEON */ -# define fast_wmb() __sync() -# define fast_rmb() __sync() -# define fast_mb() __sync() # ifdef CONFIG_SGI_IP28 # define fast_iob() \ __asm__ __volatile__( \ @@ -192,23 +78,14 @@ #endif /* !CONFIG_CPU_HAS_WB */ -#define wmb() fast_wmb() -#define rmb() fast_rmb() - #if defined(CONFIG_WEAK_ORDERING) -# ifdef CONFIG_CPU_CAVIUM_OCTEON -# define __smp_mb() __sync() -# define __smp_rmb() barrier() -# define __smp_wmb() __syncw() -# else -# define __smp_mb() __asm__ __volatile__("sync" : : :"memory") -# define __smp_rmb() __asm__ __volatile__("sync" : : :"memory") -# define __smp_wmb() __asm__ __volatile__("sync" : : :"memory") -# endif +# define __smp_mb() __sync() +# define __smp_rmb() rmb() +# define __smp_wmb() wmb() #else -#define __smp_mb() barrier() -#define __smp_rmb() barrier() -#define __smp_wmb() barrier() +# define __smp_mb() barrier() +# define __smp_rmb() barrier() +# define __smp_wmb() barrier() #endif /* @@ -218,13 +95,14 @@ * ordering will be done by smp_llsc_mb() and friends. */ #if defined(CONFIG_WEAK_REORDERING_BEYOND_LLSC) && defined(CONFIG_SMP) -#define __WEAK_LLSC_MB " sync \n" -#define smp_llsc_mb() __asm__ __volatile__(__WEAK_LLSC_MB : : :"memory") -#define __LLSC_CLOBBER +# define __WEAK_LLSC_MB sync +# define smp_llsc_mb() \ + __asm__ __volatile__(__stringify(__WEAK_LLSC_MB) : : :"memory") +# define __LLSC_CLOBBER #else -#define __WEAK_LLSC_MB " \n" -#define smp_llsc_mb() do { } while (0) -#define __LLSC_CLOBBER "memory" +# define __WEAK_LLSC_MB +# define smp_llsc_mb() do { } while (0) +# define __LLSC_CLOBBER "memory" #endif #ifdef CONFIG_CPU_CAVIUM_OCTEON @@ -241,52 +119,22 @@ #define nudge_writes() mb() #endif -#define __smp_mb__before_atomic() __smp_mb__before_llsc() -#define __smp_mb__after_atomic() smp_llsc_mb() - /* - * Some Loongson 3 CPUs have a bug wherein execution of a memory access (load, - * store or prefetch) in between an LL & SC can cause the SC instruction to - * erroneously succeed, breaking atomicity. Whilst it's unusual to write code - * containing such sequences, this bug bites harder than we might otherwise - * expect due to reordering & speculation: - * - * 1) A memory access appearing prior to the LL in program order may actually - * be executed after the LL - this is the reordering case. - * - * In order to avoid this we need to place a memory barrier (ie. a SYNC - * instruction) prior to every LL instruction, in between it and any earlier - * memory access instructions. - * - * This reordering case is fixed by 3A R2 CPUs, ie. 3A2000 models and later. - * - * 2) If a conditional branch exists between an LL & SC with a target outside - * of the LL-SC loop, for example an exit upon value mismatch in cmpxchg() - * or similar, then misprediction of the branch may allow speculative - * execution of memory accesses from outside of the LL-SC loop. - * - * In order to avoid this we need a memory barrier (ie. a SYNC instruction) - * at each affected branch target, for which we also use loongson_llsc_mb() - * defined below. - * - * This case affects all current Loongson 3 CPUs. - * - * The above described cases cause an error in the cache coherence protocol; - * such that the Invalidate of a competing LL-SC goes 'missing' and SC - * erroneously observes its core still has Exclusive state and lets the SC - * proceed. - * - * Therefore the error only occurs on SMP systems. + * In the Loongson3 LL/SC workaround case, all of our LL/SC loops already have + * a completion barrier immediately preceding the LL instruction. Therefore we + * can skip emitting a barrier from __smp_mb__before_atomic(). */ -#ifdef CONFIG_CPU_LOONGSON3_WORKAROUNDS /* Loongson-3's LLSC workaround */ -#define loongson_llsc_mb() __asm__ __volatile__("sync" : : :"memory") +#ifdef CONFIG_CPU_LOONGSON3_WORKAROUNDS +# define __smp_mb__before_atomic() #else -#define loongson_llsc_mb() do { } while (0) +# define __smp_mb__before_atomic() __smp_mb__before_llsc() #endif +#define __smp_mb__after_atomic() smp_llsc_mb() + static inline void sync_ginv(void) { - asm volatile("sync\t%0" :: "i"(STYPE_GINV)); + asm volatile(__SYNC(ginv, always)); } #include <asm-generic/barrier.h> diff --git a/arch/mips/include/asm/bitops.h b/arch/mips/include/asm/bitops.h index 985d6a02f9ea..a74769940fbd 100644 --- a/arch/mips/include/asm/bitops.h +++ b/arch/mips/include/asm/bitops.h @@ -13,16 +13,55 @@ #error only <linux/bitops.h> can be included directly #endif +#include <linux/bits.h> #include <linux/compiler.h> #include <linux/types.h> #include <asm/barrier.h> #include <asm/byteorder.h> /* sigh ... */ #include <asm/compiler.h> #include <asm/cpu-features.h> +#include <asm/isa-rev.h> #include <asm/llsc.h> #include <asm/sgidefs.h> #include <asm/war.h> +#define __bit_op(mem, insn, inputs...) do { \ + unsigned long temp; \ + \ + asm volatile( \ + " .set push \n" \ + " .set " MIPS_ISA_LEVEL " \n" \ + " " __SYNC(full, loongson3_war) " \n" \ + "1: " __LL "%0, %1 \n" \ + " " insn " \n" \ + " " __SC "%0, %1 \n" \ + " " __SC_BEQZ "%0, 1b \n" \ + " .set pop \n" \ + : "=&r"(temp), "+" GCC_OFF_SMALL_ASM()(mem) \ + : inputs \ + : __LLSC_CLOBBER); \ +} while (0) + +#define __test_bit_op(mem, ll_dst, insn, inputs...) ({ \ + unsigned long orig, temp; \ + \ + asm volatile( \ + " .set push \n" \ + " .set " MIPS_ISA_LEVEL " \n" \ + " " __SYNC(full, loongson3_war) " \n" \ + "1: " __LL ll_dst ", %2 \n" \ + " " insn " \n" \ + " " __SC "%1, %2 \n" \ + " " __SC_BEQZ "%1, 1b \n" \ + " .set pop \n" \ + : "=&r"(orig), "=&r"(temp), \ + "+" GCC_OFF_SMALL_ASM()(mem) \ + : inputs \ + : __LLSC_CLOBBER); \ + \ + orig; \ +}) + /* * These are the "slower" versions of the functions and are in bitops.c. * These functions call raw_local_irq_{save,restore}(). @@ -30,8 +69,6 @@ void __mips_set_bit(unsigned long nr, volatile unsigned long *addr); void __mips_clear_bit(unsigned long nr, volatile unsigned long *addr); void __mips_change_bit(unsigned long nr, volatile unsigned long *addr); -int __mips_test_and_set_bit(unsigned long nr, - volatile unsigned long *addr); int __mips_test_and_set_bit_lock(unsigned long nr, volatile unsigned long *addr); int __mips_test_and_clear_bit(unsigned long nr, @@ -52,51 +89,20 @@ int __mips_test_and_change_bit(unsigned long nr, */ static inline void set_bit(unsigned long nr, volatile unsigned long *addr) { - unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG); - int bit = nr & SZLONG_MASK; - unsigned long temp; + volatile unsigned long *m = &addr[BIT_WORD(nr)]; + int bit = nr % BITS_PER_LONG; - if (kernel_uses_llsc && R10000_LLSC_WAR) { - __asm__ __volatile__( - " .set push \n" - " .set arch=r4000 \n" - "1: " __LL "%0, %1 # set_bit \n" - " or %0, %2 \n" - " " __SC "%0, %1 \n" - " beqzl %0, 1b \n" - " .set pop \n" - : "=&r" (temp), "=" GCC_OFF_SMALL_ASM() (*m) - : "ir" (1UL << bit), GCC_OFF_SMALL_ASM() (*m) - : __LLSC_CLOBBER); -#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6) - } else if (kernel_uses_llsc && __builtin_constant_p(bit)) { - loongson_llsc_mb(); - do { - __asm__ __volatile__( - " " __LL "%0, %1 # set_bit \n" - " " __INS "%0, %3, %2, 1 \n" - " " __SC "%0, %1 \n" - : "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m) - : "ir" (bit), "r" (~0) - : __LLSC_CLOBBER); - } while (unlikely(!temp)); -#endif /* CONFIG_CPU_MIPSR2 || CONFIG_CPU_MIPSR6 */ - } else if (kernel_uses_llsc) { - loongson_llsc_mb(); - do { - __asm__ __volatile__( - " .set push \n" - " .set "MIPS_ISA_ARCH_LEVEL" \n" - " " __LL "%0, %1 # set_bit \n" - " or %0, %2 \n" - " " __SC "%0, %1 \n" - " .set pop \n" - : "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m) - : "ir" (1UL << bit) - : __LLSC_CLOBBER); - } while (unlikely(!temp)); - } else + if (!kernel_uses_llsc) { __mips_set_bit(nr, addr); + return; + } + + if ((MIPS_ISA_REV >= 2) && __builtin_constant_p(bit) && (bit >= 16)) { + __bit_op(*m, __INS "%0, %3, %2, 1", "i"(bit), "r"(~0)); + return; + } + + __bit_op(*m, "or\t%0, %2", "ir"(BIT(bit))); } /* @@ -111,51 +117,20 @@ static inline void set_bit(unsigned long nr, volatile unsigned long *addr) */ static inline void clear_bit(unsigned long nr, volatile unsigned long *addr) { - unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG); - int bit = nr & SZLONG_MASK; - unsigned long temp; + volatile unsigned long *m = &addr[BIT_WORD(nr)]; + int bit = nr % BITS_PER_LONG; - if (kernel_uses_llsc && R10000_LLSC_WAR) { - __asm__ __volatile__( - " .set push \n" - " .set arch=r4000 \n" - "1: " __LL "%0, %1 # clear_bit \n" - " and %0, %2 \n" - " " __SC "%0, %1 \n" - " beqzl %0, 1b \n" - " .set pop \n" - : "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m) - : "ir" (~(1UL << bit)) - : __LLSC_CLOBBER); -#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6) - } else if (kernel_uses_llsc && __builtin_constant_p(bit)) { - loongson_llsc_mb(); - do { - __asm__ __volatile__( - " " __LL "%0, %1 # clear_bit \n" - " " __INS "%0, $0, %2, 1 \n" - " " __SC "%0, %1 \n" - : "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m) - : "ir" (bit) - : __LLSC_CLOBBER); - } while (unlikely(!temp)); -#endif /* CONFIG_CPU_MIPSR2 || CONFIG_CPU_MIPSR6 */ - } else if (kernel_uses_llsc) { - loongson_llsc_mb(); - do { - __asm__ __volatile__( - " .set push \n" - " .set "MIPS_ISA_ARCH_LEVEL" \n" - " " __LL "%0, %1 # clear_bit \n" - " and %0, %2 \n" - " " __SC "%0, %1 \n" - " .set pop \n" - : "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m) - : "ir" (~(1UL << bit)) - : __LLSC_CLOBBER); - } while (unlikely(!temp)); - } else + if (!kernel_uses_llsc) { __mips_clear_bit(nr, addr); + return; + } + + if ((MIPS_ISA_REV >= 2) && __builtin_constant_p(bit)) { + __bit_op(*m, __INS "%0, $0, %2, 1", "i"(bit)); + return; + } + + __bit_op(*m, "and\t%0, %2", "ir"(~BIT(bit))); } /* @@ -183,159 +158,61 @@ static inline void clear_bit_unlock(unsigned long nr, volatile unsigned long *ad */ static inline void change_bit(unsigned long nr, volatile unsigned long *addr) { - int bit = nr & SZLONG_MASK; - - if (kernel_uses_llsc && R10000_LLSC_WAR) { - unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG); - unsigned long temp; - - __asm__ __volatile__( - " .set push \n" - " .set arch=r4000 \n" - "1: " __LL "%0, %1 # change_bit \n" - " xor %0, %2 \n" - " " __SC "%0, %1 \n" - " beqzl %0, 1b \n" - " .set pop \n" - : "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m) - : "ir" (1UL << bit) - : __LLSC_CLOBBER); - } else if (kernel_uses_llsc) { - unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG); - unsigned long temp; - - loongson_llsc_mb(); - do { - __asm__ __volatile__( - " .set push \n" - " .set "MIPS_ISA_ARCH_LEVEL" \n" - " " __LL "%0, %1 # change_bit \n" - " xor %0, %2 \n" - " " __SC "%0, %1 \n" - " .set pop \n" - : "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m) - : "ir" (1UL << bit) - : __LLSC_CLOBBER); - } while (unlikely(!temp)); - } else + volatile unsigned long *m = &addr[BIT_WORD(nr)]; + int bit = nr % BITS_PER_LONG; + + if (!kernel_uses_llsc) { __mips_change_bit(nr, addr); + return; + } + + __bit_op(*m, "xor\t%0, %2", "ir"(BIT(bit))); } /* - * test_and_set_bit - Set a bit and return its old value + * test_and_set_bit_lock - Set a bit and return its old value * @nr: Bit to set * @addr: Address to count from * - * This operation is atomic and cannot be reordered. - * It also implies a memory barrier. + * This operation is atomic and implies acquire ordering semantics + * after the memory operation. */ -static inline int test_and_set_bit(unsigned long nr, +static inline int test_and_set_bit_lock(unsigned long nr, volatile unsigned long *addr) { - int bit = nr & SZLONG_MASK; - unsigned long res; + volatile unsigned long *m = &addr[BIT_WORD(nr)]; + int bit = nr % BITS_PER_LONG; + unsigned long res, orig; - smp_mb__before_llsc(); - - if (kernel_uses_llsc && R10000_LLSC_WAR) { - unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG); - unsigned long temp; - - __asm__ __volatile__( - " .set push \n" - " .set arch=r4000 \n" - "1: " __LL "%0, %1 # test_and_set_bit \n" - " or %2, %0, %3 \n" - " " __SC "%2, %1 \n" - " beqzl %2, 1b \n" - " and %2, %0, %3 \n" - " .set pop \n" - : "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m), "=&r" (res) - : "r" (1UL << bit) - : __LLSC_CLOBBER); - } else if (kernel_uses_llsc) { - unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG); - unsigned long temp; - - loongson_llsc_mb(); - do { - __asm__ __volatile__( - " .set push \n" - " .set "MIPS_ISA_ARCH_LEVEL" \n" - " " __LL "%0, %1 # test_and_set_bit \n" - " or %2, %0, %3 \n" - " " __SC "%2, %1 \n" - " .set pop \n" - : "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m), "=&r" (res) - : "r" (1UL << bit) - : __LLSC_CLOBBER); - } while (unlikely(!res)); - - res = temp & (1UL << bit); - } else - res = __mips_test_and_set_bit(nr, addr); + if (!kernel_uses_llsc) { + res = __mips_test_and_set_bit_lock(nr, addr); + } else { + orig = __test_bit_op(*m, "%0", + "or\t%1, %0, %3", + "ir"(BIT(bit))); + res = (orig & BIT(bit)) != 0; + } smp_llsc_mb(); - return res != 0; + return res; } /* - * test_and_set_bit_lock - Set a bit and return its old value + * test_and_set_bit - Set a bit and return its old value * @nr: Bit to set * @addr: Address to count from * - * This operation is atomic and implies acquire ordering semantics - * after the memory operation. + * This operation is atomic and cannot be reordered. + * It also implies a memory barrier. */ -static inline int test_and_set_bit_lock(unsigned long nr, +static inline int test_and_set_bit(unsigned long nr, volatile unsigned long *addr) { - int bit = nr & SZLONG_MASK; - unsigned long res; - - if (kernel_uses_llsc && R10000_LLSC_WAR) { - unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG); - unsigned long temp; - - __asm__ __volatile__( - " .set push \n" - " .set arch=r4000 \n" - "1: " __LL "%0, %1 # test_and_set_bit \n" - " or %2, %0, %3 \n" - " " __SC "%2, %1 \n" - " beqzl %2, 1b \n" - " and %2, %0, %3 \n" - " .set pop \n" - : "=&r" (temp), "+m" (*m), "=&r" (res) - : "r" (1UL << bit) - : __LLSC_CLOBBER); - } else if (kernel_uses_llsc) { - unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG); - unsigned long temp; - - loongson_llsc_mb(); - do { - __asm__ __volatile__( - " .set push \n" - " .set "MIPS_ISA_ARCH_LEVEL" \n" - " " __LL "%0, %1 # test_and_set_bit \n" - " or %2, %0, %3 \n" - " " __SC "%2, %1 \n" - " .set pop \n" - : "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m), "=&r" (res) - : "r" (1UL << bit) - : __LLSC_CLOBBER); - } while (unlikely(!res)); - - res = temp & (1UL << bit); - } else - res = __mips_test_and_set_bit_lock(nr, addr); - - smp_llsc_mb(); - - return res != 0; + smp_mb__before_atomic(); + return test_and_set_bit_lock(nr, addr); } + /* * test_and_clear_bit - Clear a bit and return its old value * @nr: Bit to clear @@ -347,71 +224,30 @@ static inline int test_and_set_bit_lock(unsigned long nr, static inline int test_and_clear_bit(unsigned long nr, volatile unsigned long *addr) { - int bit = nr & SZLONG_MASK; - unsigned long res; - - smp_mb__before_llsc(); + volatile unsigned long *m = &addr[BIT_WORD(nr)]; + int bit = nr % BITS_PER_LONG; + unsigned long res, orig; - if (kernel_uses_llsc && R10000_LLSC_WAR) { - unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG); - unsigned long temp; + smp_mb__before_atomic(); - __asm__ __volatile__( - " .set push \n" - " .set arch=r4000 \n" - "1: " __LL "%0, %1 # test_and_clear_bit \n" - " or %2, %0, %3 \n" - " xor %2, %3 \n" - " " __SC "%2, %1 \n" - " beqzl %2, 1b \n" - " and %2, %0, %3 \n" - " .set pop \n" - : "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m), "=&r" (res) - : "r" (1UL << bit) - : __LLSC_CLOBBER); -#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6) - } else if (kernel_uses_llsc && __builtin_constant_p(nr)) { - unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG); - unsigned long temp; - - loongson_llsc_mb(); - do { - __asm__ __volatile__( - " " __LL "%0, %1 # test_and_clear_bit \n" - " " __EXT "%2, %0, %3, 1 \n" - " " __INS "%0, $0, %3, 1 \n" - " " __SC "%0, %1 \n" - : "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m), "=&r" (res) - : "ir" (bit) - : __LLSC_CLOBBER); - } while (unlikely(!temp)); -#endif - } else if (kernel_uses_llsc) { - unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG); - unsigned long temp; - - loongson_llsc_mb(); - do { - __asm__ __volatile__( - " .set push \n" - " .set "MIPS_ISA_ARCH_LEVEL" \n" - " " __LL "%0, %1 # test_and_clear_bit \n" - " or %2, %0, %3 \n" - " xor %2, %3 \n" - " " __SC "%2, %1 \n" - " .set pop \n" - : "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m), "=&r" (res) - : "r" (1UL << bit) - : __LLSC_CLOBBER); - } while (unlikely(!res)); - - res = temp & (1UL << bit); - } else + if (!kernel_uses_llsc) { res = __mips_test_and_clear_bit(nr, addr); + } else if ((MIPS_ISA_REV >= 2) && __builtin_constant_p(nr)) { + res = __test_bit_op(*m, "%1", + __EXT "%0, %1, %3, 1;" + __INS "%1, $0, %3, 1", + "i"(bit)); + } else { + orig = __test_bit_op(*m, "%0", + "or\t%1, %0, %3;" + "xor\t%1, %1, %3", + "ir"(BIT(bit))); + res = (orig & BIT(bit)) != 0; + } smp_llsc_mb(); - return res != 0; + return res; } /* @@ -425,54 +261,29 @@ static inline int test_and_clear_bit(unsigned long nr, static inline int test_and_change_bit(unsigned long nr, volatile unsigned long *addr) { - int bit = nr & SZLONG_MASK; - unsigned long res; + volatile unsigned long *m = &addr[BIT_WORD(nr)]; + int bit = nr % BITS_PER_LONG; + unsigned long res, orig; - smp_mb__before_llsc(); - - if (kernel_uses_llsc && R10000_LLSC_WAR) { - unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG); - unsigned long temp; + smp_mb__before_atomic(); - __asm__ __volatile__( - " .set push \n" - " .set arch=r4000 \n" - "1: " __LL "%0, %1 # test_and_change_bit \n" - " xor %2, %0, %3 \n" - " " __SC "%2, %1 \n" - " beqzl %2, 1b \n" - " and %2, %0, %3 \n" - " .set pop \n" - : "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m), "=&r" (res) - : "r" (1UL << bit) - : __LLSC_CLOBBER); - } else if (kernel_uses_llsc) { - unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG); - unsigned long temp; - - loongson_llsc_mb(); - do { - __asm__ __volatile__( - " .set push \n" - " .set "MIPS_ISA_ARCH_LEVEL" \n" - " " __LL "%0, %1 # test_and_change_bit \n" - " xor %2, %0, %3 \n" - " " __SC "\t%2, %1 \n" - " .set pop \n" - : "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m), "=&r" (res) - : "r" (1UL << bit) - : __LLSC_CLOBBER); - } while (unlikely(!res)); - - res = temp & (1UL << bit); - } else + if (!kernel_uses_llsc) { res = __mips_test_and_change_bit(nr, addr); + } else { + orig = __test_bit_op(*m, "%0", + "xor\t%1, %0, %3", + "ir"(BIT(bit))); + res = (orig & BIT(bit)) != 0; + } smp_llsc_mb(); - return res != 0; + return res; } +#undef __bit_op +#undef __test_bit_op + #include <asm-generic/bitops/non-atomic.h> /* diff --git a/arch/mips/include/asm/bootinfo.h b/arch/mips/include/asm/bootinfo.h index 34d62229dea5..d41a5057bc69 100644 --- a/arch/mips/include/asm/bootinfo.h +++ b/arch/mips/include/asm/bootinfo.h @@ -61,7 +61,7 @@ /* * Valid machtype for Loongson family */ -enum loongson_machine_type { +enum loongson2ef_machine_type { MACH_LOONGSON_UNKNOWN, MACH_LEMOTE_FL2E, MACH_LEMOTE_FL2F, @@ -70,7 +70,6 @@ enum loongson_machine_type { MACH_DEXXON_GDIUM2F10, MACH_LEMOTE_NAS, MACH_LEMOTE_LL2F, - MACH_LOONGSON_GENERIC, MACH_LOONGSON_END }; @@ -99,6 +98,7 @@ extern void detect_memory_region(phys_addr_t start, phys_addr_t sz_min, phys_ad extern void prom_init(void); extern void prom_free_prom_memory(void); +extern void prom_cleanup(void); extern void free_init_pages(const char *what, unsigned long begin, unsigned long end); diff --git a/arch/mips/include/asm/bugs.h b/arch/mips/include/asm/bugs.h index d8ab8b7129b5..d72dc6e1cf3c 100644 --- a/arch/mips/include/asm/bugs.h +++ b/arch/mips/include/asm/bugs.h @@ -26,9 +26,8 @@ extern void check_bugs64(void); static inline void check_bugs_early(void) { -#ifdef CONFIG_64BIT - check_bugs64_early(); -#endif + if (IS_ENABLED(CONFIG_CPU_R4X00_BUGS64)) + check_bugs64_early(); } static inline void check_bugs(void) @@ -37,19 +36,18 @@ static inline void check_bugs(void) cpu_data[cpu].udelay_val = loops_per_jiffy; check_bugs32(); -#ifdef CONFIG_64BIT - check_bugs64(); -#endif + + if (IS_ENABLED(CONFIG_CPU_R4X00_BUGS64)) + check_bugs64(); } static inline int r4k_daddiu_bug(void) { -#ifdef CONFIG_64BIT + if (!IS_ENABLED(CONFIG_CPU_R4X00_BUGS64)) + return 0; + WARN_ON(daddiu_bug < 0); return daddiu_bug != 0; -#else - return 0; -#endif } #endif /* _ASM_BUGS_H */ diff --git a/arch/mips/include/asm/cmpxchg.h b/arch/mips/include/asm/cmpxchg.h index f6136871561d..5b0b3a6777ea 100644 --- a/arch/mips/include/asm/cmpxchg.h +++ b/arch/mips/include/asm/cmpxchg.h @@ -11,20 +11,11 @@ #include <linux/bug.h> #include <linux/irqflags.h> #include <asm/compiler.h> +#include <asm/llsc.h> +#include <asm/sync.h> #include <asm/war.h> /* - * Using a branch-likely instruction to check the result of an sc instruction - * works around a bug present in R10000 CPUs prior to revision 3.0 that could - * cause ll-sc sequences to execute non-atomically. - */ -#if R10000_LLSC_WAR -# define __scbeqz "beqzl" -#else -# define __scbeqz "beqz" -#endif - -/* * These functions doesn't exist, so if they are called you'll either: * * - Get an error at compile-time due to __compiletime_error, if supported by @@ -46,18 +37,18 @@ extern unsigned long __xchg_called_with_bad_pointer(void) __typeof(*(m)) __ret; \ \ if (kernel_uses_llsc) { \ - loongson_llsc_mb(); \ __asm__ __volatile__( \ " .set push \n" \ " .set noat \n" \ " .set push \n" \ " .set " MIPS_ISA_ARCH_LEVEL " \n" \ + " " __SYNC(full, loongson3_war) " \n" \ "1: " ld " %0, %2 # __xchg_asm \n" \ " .set pop \n" \ " move $1, %z3 \n" \ " .set " MIPS_ISA_ARCH_LEVEL " \n" \ " " st " $1, %1 \n" \ - "\t" __scbeqz " $1, 1b \n" \ + "\t" __SC_BEQZ "$1, 1b \n" \ " .set pop \n" \ : "=&r" (__ret), "=" GCC_OFF_SMALL_ASM() (*m) \ : GCC_OFF_SMALL_ASM() (*m), "Jr" (val) \ @@ -103,7 +94,13 @@ unsigned long __xchg(volatile void *ptr, unsigned long x, int size) ({ \ __typeof__(*(ptr)) __res; \ \ - smp_mb__before_llsc(); \ + /* \ + * In the Loongson3 workaround case __xchg_asm() already \ + * contains a completion barrier prior to the LL, so we don't \ + * need to emit an extra one here. \ + */ \ + if (!__SYNC_loongson3_war) \ + smp_mb__before_llsc(); \ \ __res = (__typeof__(*(ptr))) \ __xchg((ptr), (unsigned long)(x), sizeof(*(ptr))); \ @@ -118,25 +115,24 @@ unsigned long __xchg(volatile void *ptr, unsigned long x, int size) __typeof(*(m)) __ret; \ \ if (kernel_uses_llsc) { \ - loongson_llsc_mb(); \ __asm__ __volatile__( \ " .set push \n" \ " .set noat \n" \ " .set push \n" \ " .set "MIPS_ISA_ARCH_LEVEL" \n" \ + " " __SYNC(full, loongson3_war) " \n" \ "1: " ld " %0, %2 # __cmpxchg_asm \n" \ " bne %0, %z3, 2f \n" \ " .set pop \n" \ " move $1, %z4 \n" \ " .set "MIPS_ISA_ARCH_LEVEL" \n" \ " " st " $1, %1 \n" \ - "\t" __scbeqz " $1, 1b \n" \ + "\t" __SC_BEQZ "$1, 1b \n" \ " .set pop \n" \ - "2: \n" \ + "2: " __SYNC(full, loongson3_war) " \n" \ : "=&r" (__ret), "=" GCC_OFF_SMALL_ASM() (*m) \ : GCC_OFF_SMALL_ASM() (*m), "Jr" (old), "Jr" (new) \ : __LLSC_CLOBBER); \ - loongson_llsc_mb(); \ } else { \ unsigned long __flags; \ \ @@ -190,9 +186,23 @@ unsigned long __cmpxchg(volatile void *ptr, unsigned long old, ({ \ __typeof__(*(ptr)) __res; \ \ - smp_mb__before_llsc(); \ + /* \ + * In the Loongson3 workaround case __cmpxchg_asm() already \ + * contains a completion barrier prior to the LL, so we don't \ + * need to emit an extra one here. \ + */ \ + if (!__SYNC_loongson3_war) \ + smp_mb__before_llsc(); \ + \ __res = cmpxchg_local((ptr), (old), (new)); \ - smp_llsc_mb(); \ + \ + /* \ + * In the Loongson3 workaround case __cmpxchg_asm() already \ + * contains a completion barrier after the SC, so we don't \ + * need to emit an extra one here. \ + */ \ + if (!__SYNC_loongson3_war) \ + smp_llsc_mb(); \ \ __res; \ }) @@ -233,11 +243,11 @@ static inline unsigned long __cmpxchg64(volatile void *ptr, */ local_irq_save(flags); - loongson_llsc_mb(); asm volatile( " .set push \n" " .set " MIPS_ISA_ARCH_LEVEL " \n" /* Load 64 bits from ptr */ + " " __SYNC(full, loongson3_war) " \n" "1: lld %L0, %3 # __cmpxchg64 \n" /* * Split the 64 bit value we loaded into the 2 registers that hold the @@ -269,9 +279,9 @@ static inline unsigned long __cmpxchg64(volatile void *ptr, /* Attempt to store new at ptr */ " scd %L1, %2 \n" /* If we failed, loop! */ - "\t" __scbeqz " %L1, 1b \n" + "\t" __SC_BEQZ "%L1, 1b \n" " .set pop \n" - "2: \n" + "2: " __SYNC(full, loongson3_war) " \n" : "=&r"(ret), "=&r"(tmp), "=" GCC_OFF_SMALL_ASM() (*(unsigned long long *)ptr) @@ -279,7 +289,6 @@ static inline unsigned long __cmpxchg64(volatile void *ptr, "r" (old), "r" (new) : "memory"); - loongson_llsc_mb(); local_irq_restore(flags); return ret; @@ -312,6 +321,4 @@ static inline unsigned long __cmpxchg64(volatile void *ptr, # endif /* !CONFIG_SMP */ #endif /* !CONFIG_64BIT */ -#undef __scbeqz - #endif /* __ASM_CMPXCHG_H */ diff --git a/arch/mips/include/asm/cop2.h b/arch/mips/include/asm/cop2.h index 63b3468ede4c..6b7396a6a115 100644 --- a/arch/mips/include/asm/cop2.h +++ b/arch/mips/include/asm/cop2.h @@ -33,7 +33,7 @@ extern void nlm_cop2_restore(struct nlm_cop2_state *); #define cop2_present 1 #define cop2_lazy_restore 0 -#elif defined(CONFIG_CPU_LOONGSON3) +#elif defined(CONFIG_CPU_LOONGSON64) #define cop2_present 1 #define cop2_lazy_restore 1 diff --git a/arch/mips/include/asm/cpu-type.h b/arch/mips/include/asm/cpu-type.h index 7bbb66760a07..c46c59b0f1b4 100644 --- a/arch/mips/include/asm/cpu-type.h +++ b/arch/mips/include/asm/cpu-type.h @@ -15,18 +15,17 @@ static inline int __pure __get_cpu_type(const int cpu_type) { switch (cpu_type) { -#if defined(CONFIG_SYS_HAS_CPU_LOONGSON2E) || \ - defined(CONFIG_SYS_HAS_CPU_LOONGSON2F) - case CPU_LOONGSON2: +#if defined(CONFIG_SYS_HAS_CPU_LOONGSON2EF) + case CPU_LOONGSON2EF: #endif -#ifdef CONFIG_SYS_HAS_CPU_LOONGSON3 - case CPU_LOONGSON3: +#ifdef CONFIG_SYS_HAS_CPU_LOONGSON64 + case CPU_LOONGSON64: #endif #if defined(CONFIG_SYS_HAS_CPU_LOONGSON1B) || \ defined(CONFIG_SYS_HAS_CPU_LOONGSON1C) - case CPU_LOONGSON1: + case CPU_LOONGSON32: #endif #ifdef CONFIG_SYS_HAS_CPU_MIPS32_R1 diff --git a/arch/mips/include/asm/cpu.h b/arch/mips/include/asm/cpu.h index 7fddcb8350c6..ea830783d663 100644 --- a/arch/mips/include/asm/cpu.h +++ b/arch/mips/include/asm/cpu.h @@ -91,7 +91,9 @@ #define PRID_IMP_LOONGSON_32 0x4200 /* Loongson-1 */ #define PRID_IMP_R5432 0x5400 #define PRID_IMP_R5500 0x5500 -#define PRID_IMP_LOONGSON_64 0x6300 /* Loongson-2/3 */ +#define PRID_IMP_LOONGSON_64R 0x6100 /* Reduced Loongson-2 */ +#define PRID_IMP_LOONGSON_64C 0x6300 /* Classic Loongson-2 and Loongson-3 */ +#define PRID_IMP_LOONGSON_64G 0xc000 /* Generic Loongson-2 and Loongson-3 */ #define PRID_IMP_UNKNOWN 0xff00 @@ -310,15 +312,15 @@ enum cpu_type_enum { */ CPU_4KC, CPU_4KEC, CPU_4KSC, CPU_24K, CPU_34K, CPU_1004K, CPU_74K, CPU_ALCHEMY, CPU_PR4450, CPU_BMIPS32, CPU_BMIPS3300, CPU_BMIPS4350, - CPU_BMIPS4380, CPU_BMIPS5000, CPU_XBURST, CPU_LOONGSON1, CPU_M14KC, + CPU_BMIPS4380, CPU_BMIPS5000, CPU_XBURST, CPU_LOONGSON32, CPU_M14KC, CPU_M14KEC, CPU_INTERAPTIV, CPU_P5600, CPU_PROAPTIV, CPU_1074K, CPU_M5150, CPU_I6400, CPU_P6600, CPU_M6250, /* * MIPS64 class processors */ - CPU_5KC, CPU_5KE, CPU_20KC, CPU_25KF, CPU_SB1, CPU_SB1A, CPU_LOONGSON2, - CPU_LOONGSON3, CPU_CAVIUM_OCTEON, CPU_CAVIUM_OCTEON_PLUS, + CPU_5KC, CPU_5KE, CPU_20KC, CPU_25KF, CPU_SB1, CPU_SB1A, CPU_LOONGSON2EF, + CPU_LOONGSON64, CPU_CAVIUM_OCTEON, CPU_CAVIUM_OCTEON_PLUS, CPU_CAVIUM_OCTEON2, CPU_CAVIUM_OCTEON3, CPU_XLR, CPU_XLP, CPU_I6500, CPU_QEMU_GENERIC, diff --git a/arch/mips/include/asm/fixmap.h b/arch/mips/include/asm/fixmap.h index 6842ffafd1e7..1784d4348c36 100644 --- a/arch/mips/include/asm/fixmap.h +++ b/arch/mips/include/asm/fixmap.h @@ -70,7 +70,7 @@ enum fixed_addresses { #include <asm-generic/fixmap.h> #define kmap_get_fixmap_pte(vaddr) \ - pte_offset_kernel(pmd_offset(pud_offset(pgd_offset_k(vaddr), (vaddr)), (vaddr)), (vaddr)) + pte_offset_kernel(pmd_offset(pud_offset(p4d_offset(pgd_offset_k(vaddr), (vaddr)), (vaddr)), (vaddr)), (vaddr)) /* * Called from pgtable_init() diff --git a/arch/mips/include/asm/futex.h b/arch/mips/include/asm/futex.h index b83b0397462d..110220705e97 100644 --- a/arch/mips/include/asm/futex.h +++ b/arch/mips/include/asm/futex.h @@ -16,6 +16,7 @@ #include <asm/barrier.h> #include <asm/compiler.h> #include <asm/errno.h> +#include <asm/sync.h> #include <asm/war.h> #define __futex_atomic_op(insn, ret, oldval, uaddr, oparg) \ @@ -32,7 +33,7 @@ " .set arch=r4000 \n" \ "2: sc $1, %2 \n" \ " beqzl $1, 1b \n" \ - __WEAK_LLSC_MB \ + __stringify(__WEAK_LLSC_MB) " \n" \ "3: \n" \ " .insn \n" \ " .set pop \n" \ @@ -50,19 +51,19 @@ "i" (-EFAULT) \ : "memory"); \ } else if (cpu_has_llsc) { \ - loongson_llsc_mb(); \ __asm__ __volatile__( \ " .set push \n" \ " .set noat \n" \ " .set push \n" \ " .set "MIPS_ISA_ARCH_LEVEL" \n" \ + " " __SYNC(full, loongson3_war) " \n" \ "1: "user_ll("%1", "%4")" # __futex_atomic_op\n" \ " .set pop \n" \ " " insn " \n" \ " .set "MIPS_ISA_ARCH_LEVEL" \n" \ "2: "user_sc("$1", "%2")" \n" \ " beqz $1, 1b \n" \ - __WEAK_LLSC_MB \ + __stringify(__WEAK_LLSC_MB) " \n" \ "3: \n" \ " .insn \n" \ " .set pop \n" \ @@ -147,7 +148,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, " .set arch=r4000 \n" "2: sc $1, %2 \n" " beqzl $1, 1b \n" - __WEAK_LLSC_MB + __stringify(__WEAK_LLSC_MB) " \n" "3: \n" " .insn \n" " .set pop \n" @@ -164,13 +165,13 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, "i" (-EFAULT) : "memory"); } else if (cpu_has_llsc) { - loongson_llsc_mb(); __asm__ __volatile__( "# futex_atomic_cmpxchg_inatomic \n" " .set push \n" " .set noat \n" " .set push \n" " .set "MIPS_ISA_ARCH_LEVEL" \n" + " " __SYNC(full, loongson3_war) " \n" "1: "user_ll("%1", "%3")" \n" " bne %1, %z4, 3f \n" " .set pop \n" @@ -178,8 +179,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, " .set "MIPS_ISA_ARCH_LEVEL" \n" "2: "user_sc("$1", "%2")" \n" " beqz $1, 1b \n" - __WEAK_LLSC_MB - "3: \n" + "3: " __SYNC_ELSE(full, loongson3_war, __WEAK_LLSC_MB) "\n" " .insn \n" " .set pop \n" " .section .fixup,\"ax\" \n" @@ -194,7 +194,6 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, : GCC_OFF_SMALL_ASM() (*uaddr), "Jr" (oldval), "Jr" (newval), "i" (-EFAULT) : "memory"); - loongson_llsc_mb(); } else return -ENOSYS; diff --git a/arch/mips/include/asm/hazards.h b/arch/mips/include/asm/hazards.h index 0fa27446869a..a4f48b0f5541 100644 --- a/arch/mips/include/asm/hazards.h +++ b/arch/mips/include/asm/hazards.h @@ -158,7 +158,7 @@ do { \ } while (0) #elif defined(CONFIG_MIPS_ALCHEMY) || defined(CONFIG_CPU_CAVIUM_OCTEON) || \ - defined(CONFIG_CPU_LOONGSON2) || defined(CONFIG_LOONGSON3_ENHANCEMENT) || \ + defined(CONFIG_CPU_LOONGSON2EF) || defined(CONFIG_LOONGSON3_ENHANCEMENT) || \ defined(CONFIG_CPU_R10000) || defined(CONFIG_CPU_R5500) || defined(CONFIG_CPU_XLR) /* diff --git a/arch/mips/include/asm/io.h b/arch/mips/include/asm/io.h index 2b7b56736372..3f6ce74335b4 100644 --- a/arch/mips/include/asm/io.h +++ b/arch/mips/include/asm/io.h @@ -306,7 +306,7 @@ static inline void iounmap(const volatile void __iomem *addr) #undef __IS_KSEG1 } -#if defined(CONFIG_CPU_CAVIUM_OCTEON) || defined(CONFIG_CPU_LOONGSON3) +#if defined(CONFIG_CPU_CAVIUM_OCTEON) || defined(CONFIG_CPU_LOONGSON64) #define war_io_reorder_wmb() wmb() #else #define war_io_reorder_wmb() barrier() diff --git a/arch/mips/include/asm/irqflags.h b/arch/mips/include/asm/irqflags.h index f0b862a83816..c4728bbdf15b 100644 --- a/arch/mips/include/asm/irqflags.h +++ b/arch/mips/include/asm/irqflags.h @@ -41,7 +41,7 @@ static inline unsigned long arch_local_irq_save(void) " .set push \n" " .set reorder \n" " .set noat \n" -#if defined(CONFIG_CPU_LOONGSON3) || defined (CONFIG_CPU_LOONGSON1) +#if defined(CONFIG_CPU_LOONGSON64) || defined(CONFIG_CPU_LOONGSON32) " mfc0 %[flags], $12 \n" " di \n" #else diff --git a/arch/mips/include/asm/llsc.h b/arch/mips/include/asm/llsc.h index c6d17d171147..c49738bc3bda 100644 --- a/arch/mips/include/asm/llsc.h +++ b/arch/mips/include/asm/llsc.h @@ -9,20 +9,31 @@ #ifndef __ASM_LLSC_H #define __ASM_LLSC_H +#include <asm/isa-rev.h> + #if _MIPS_SZLONG == 32 -#define SZLONG_LOG 5 -#define SZLONG_MASK 31UL #define __LL "ll " #define __SC "sc " #define __INS "ins " #define __EXT "ext " #elif _MIPS_SZLONG == 64 -#define SZLONG_LOG 6 -#define SZLONG_MASK 63UL #define __LL "lld " #define __SC "scd " #define __INS "dins " #define __EXT "dext " #endif +/* + * Using a branch-likely instruction to check the result of an sc instruction + * works around a bug present in R10000 CPUs prior to revision 3.0 that could + * cause ll-sc sequences to execute non-atomically. + */ +#if R10000_LLSC_WAR +# define __SC_BEQZ "beqzl " +#elif MIPS_ISA_REV >= 6 +# define __SC_BEQZ "beqzc " +#else +# define __SC_BEQZ "beqz " +#endif + #endif /* __ASM_LLSC_H */ diff --git a/arch/mips/include/asm/mach-ip22/spaces.h b/arch/mips/include/asm/mach-ip22/spaces.h index 7f9fa6f66059..24fe92cb5313 100644 --- a/arch/mips/include/asm/mach-ip22/spaces.h +++ b/arch/mips/include/asm/mach-ip22/spaces.h @@ -10,17 +10,7 @@ #ifndef _ASM_MACH_IP22_SPACES_H #define _ASM_MACH_IP22_SPACES_H - -#ifdef CONFIG_64BIT - -#define PAGE_OFFSET 0xffffffff80000000UL - -#define CAC_BASE 0xffffffff80000000 -#define IO_BASE 0xffffffffa0000000 -#define UNCAC_BASE 0xffffffffa0000000 -#define MAP_BASE 0xc000000000000000 - -#endif /* CONFIG_64BIT */ +#define PHYS_OFFSET _AC(0x08000000, UL) #include <asm/mach-generic/spaces.h> diff --git a/arch/mips/include/asm/mach-ip27/mmzone.h b/arch/mips/include/asm/mach-ip27/mmzone.h index 1cd6a23a84f2..f463826515df 100644 --- a/arch/mips/include/asm/mach-ip27/mmzone.h +++ b/arch/mips/include/asm/mach-ip27/mmzone.h @@ -6,7 +6,7 @@ #include <asm/sn/arch.h> #include <asm/sn/hub.h> -#define pa_to_nid(addr) NASID_TO_COMPACT_NODEID(NASID_GET(addr)) +#define pa_to_nid(addr) NASID_GET(addr) struct hub_data { kern_vars_t kern_vars; diff --git a/arch/mips/include/asm/mach-ip27/topology.h b/arch/mips/include/asm/mach-ip27/topology.h index 965f0793a5f9..be61ddcdacab 100644 --- a/arch/mips/include/asm/mach-ip27/topology.h +++ b/arch/mips/include/asm/mach-ip27/topology.h @@ -7,14 +7,13 @@ #include <asm/mmzone.h> struct cpuinfo_ip27 { - cnodeid_t p_nodeid; /* my node ID in compact-id-space */ nasid_t p_nasid; /* my node ID in numa-as-id-space */ unsigned char p_slice; /* Physical position on node board */ }; extern struct cpuinfo_ip27 sn_cpu_info[NR_CPUS]; -#define cpu_to_node(cpu) (sn_cpu_info[(cpu)].p_nodeid) +#define cpu_to_node(cpu) (cputonasid(cpu)) #define cpumask_of_node(node) ((node) == -1 ? \ cpu_all_mask : \ &hub_data(node)->h_cpus) @@ -23,7 +22,7 @@ extern int pcibus_to_node(struct pci_bus *); #define cpumask_of_pcibus(bus) (cpumask_of_node(pcibus_to_node(bus))) -extern unsigned char __node_distances[MAX_COMPACT_NODES][MAX_COMPACT_NODES]; +extern unsigned char __node_distances[MAX_NUMNODES][MAX_NUMNODES]; #define node_distance(from, to) (__node_distances[(from)][(to)]) diff --git a/arch/mips/include/asm/mach-ip30/cpu-feature-overrides.h b/arch/mips/include/asm/mach-ip30/cpu-feature-overrides.h new file mode 100644 index 000000000000..cfa02f3d25df --- /dev/null +++ b/arch/mips/include/asm/mach-ip30/cpu-feature-overrides.h @@ -0,0 +1,83 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * IP30/Octane cpu-features overrides. + * + * Copyright (C) 2003 Ralf Baechle <ralf@linux-mips.org> + * 2004-2007 Stanislaw Skowronek <skylark@unaligned.org> + * 2009 Johannes Dickgreber <tanzy@gmx.de> + * 2015 Joshua Kinard <kumba@gentoo.org> + * + */ +#ifndef __ASM_MACH_IP30_CPU_FEATURE_OVERRIDES_H +#define __ASM_MACH_IP30_CPU_FEATURE_OVERRIDES_H + +#include <asm/cpu.h> + +/* + * IP30 only supports R1[024]000 processors, all using the same config + */ +#define cpu_has_tlb 1 +#define cpu_has_tlbinv 0 +#define cpu_has_segments 0 +#define cpu_has_eva 0 +#define cpu_has_htw 0 +#define cpu_has_rixiex 0 +#define cpu_has_maar 0 +#define cpu_has_rw_llb 0 +#define cpu_has_3kex 0 +#define cpu_has_4kex 1 +#define cpu_has_3k_cache 0 +#define cpu_has_4k_cache 1 +#define cpu_has_6k_cache 0 +#define cpu_has_8k_cache 0 +#define cpu_has_tx39_cache 0 +#define cpu_has_fpu 1 +#define cpu_has_nofpuex 0 +#define cpu_has_32fpr 1 +#define cpu_has_counter 1 +#define cpu_has_watch 1 +#define cpu_has_64bits 1 +#define cpu_has_divec 0 +#define cpu_has_vce 0 +#define cpu_has_cache_cdex_p 0 +#define cpu_has_cache_cdex_s 0 +#define cpu_has_prefetch 1 +#define cpu_has_mcheck 0 +#define cpu_has_ejtag 0 +#define cpu_has_llsc 1 +#define cpu_has_mips16 0 +#define cpu_has_mdmx 0 +#define cpu_has_mips3d 0 +#define cpu_has_smartmips 0 +#define cpu_has_rixi 0 +#define cpu_has_xpa 0 +#define cpu_has_vtag_icache 0 +#define cpu_has_dc_aliases 0 +#define cpu_has_ic_fills_f_dc 0 + +#define cpu_icache_snoops_remote_store 1 + +#define cpu_has_mips32r1 0 +#define cpu_has_mips32r2 0 +#define cpu_has_mips64r1 0 +#define cpu_has_mips64r2 0 +#define cpu_has_mips32r6 0 +#define cpu_has_mips64r6 0 + +#define cpu_has_dsp 0 +#define cpu_has_dsp2 0 +#define cpu_has_mipsmt 0 +#define cpu_has_userlocal 0 +#define cpu_has_inclusive_pcaches 1 +#define cpu_hwrena_impl_bits 0 +#define cpu_has_perf_cntr_intr_bit 0 +#define cpu_has_vz 0 +#define cpu_has_fre 0 +#define cpu_has_cdmm 0 + +#define cpu_dcache_line_size() 32 +#define cpu_icache_line_size() 64 +#define cpu_scache_line_size() 128 + +#endif /* __ASM_MACH_IP30_CPU_FEATURE_OVERRIDES_H */ + diff --git a/arch/mips/include/asm/mach-ip30/irq.h b/arch/mips/include/asm/mach-ip30/irq.h new file mode 100644 index 000000000000..e5c3dd965266 --- /dev/null +++ b/arch/mips/include/asm/mach-ip30/irq.h @@ -0,0 +1,87 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * HEART IRQ defines + * + * Copyright (C) 2009 Johannes Dickgreber <tanzy@gmx.de> + * 2014-2016 Joshua Kinard <kumba@gentoo.org> + * + */ + +#ifndef __ASM_MACH_IP30_IRQ_H +#define __ASM_MACH_IP30_IRQ_H + +/* + * HEART has 64 hardware interrupts, but use 128 to leave room for a few + * software interrupts as well (such as the CPU timer interrupt. + */ +#define NR_IRQS 128 + +extern void __init ip30_install_ipi(void); + +/* + * HEART has 64 interrupt vectors available to it, subdivided into five + * priority levels. They are numbered 0 to 63. + */ +#define HEART_NUM_IRQS 64 + +/* + * These are the five interrupt priority levels and their corresponding + * CPU IPx interrupt pins. + * + * Level 4 - Error Interrupts. + * Level 3 - HEART timer interrupt. + * Level 2 - CPU IPI, CPU debug, power putton, general device interrupts. + * Level 1 - General device interrupts. + * Level 0 - General device GFX flow control interrupts. + */ +#define HEART_L4_INT_MASK 0xfff8000000000000ULL /* IP6 */ +#define HEART_L3_INT_MASK 0x0004000000000000ULL /* IP5 */ +#define HEART_L2_INT_MASK 0x0003ffff00000000ULL /* IP4 */ +#define HEART_L1_INT_MASK 0x00000000ffff0000ULL /* IP3 */ +#define HEART_L0_INT_MASK 0x000000000000ffffULL /* IP2 */ + +/* HEART L0 Interrupts (Low Priority) */ +#define HEART_L0_INT_GENERIC 0 +#define HEART_L0_INT_FLOW_CTRL_HWTR_0 1 +#define HEART_L0_INT_FLOW_CTRL_HWTR_1 2 + +/* HEART L2 Interrupts (High Priority) */ +#define HEART_L2_INT_RESCHED_CPU_0 46 +#define HEART_L2_INT_RESCHED_CPU_1 47 +#define HEART_L2_INT_CALL_CPU_0 48 +#define HEART_L2_INT_CALL_CPU_1 49 + +/* HEART L3 Interrupts (Compare/Counter Timer) */ +#define HEART_L3_INT_TIMER 50 + +/* HEART L4 Interrupts (Errors) */ +#define HEART_L4_INT_XWID_ERR_9 51 +#define HEART_L4_INT_XWID_ERR_A 52 +#define HEART_L4_INT_XWID_ERR_B 53 +#define HEART_L4_INT_XWID_ERR_C 54 +#define HEART_L4_INT_XWID_ERR_D 55 +#define HEART_L4_INT_XWID_ERR_E 56 +#define HEART_L4_INT_XWID_ERR_F 57 +#define HEART_L4_INT_XWID_ERR_XBOW 58 +#define HEART_L4_INT_CPU_BUS_ERR_0 59 +#define HEART_L4_INT_CPU_BUS_ERR_1 60 +#define HEART_L4_INT_CPU_BUS_ERR_2 61 +#define HEART_L4_INT_CPU_BUS_ERR_3 62 +#define HEART_L4_INT_HEART_EXCP 63 + +/* + * Power Switch is wired via BaseIO BRIDGE slot #6. + * + * ACFail is wired via BaseIO BRIDGE slot #7. + */ +#define IP30_POWER_IRQ HEART_L2_INT_POWER_BTN + +#include_next <irq.h> + +#define IP30_HEART_L0_IRQ (MIPS_CPU_IRQ_BASE + 2) +#define IP30_HEART_L1_IRQ (MIPS_CPU_IRQ_BASE + 3) +#define IP30_HEART_L2_IRQ (MIPS_CPU_IRQ_BASE + 4) +#define IP30_HEART_TIMER_IRQ (MIPS_CPU_IRQ_BASE + 5) +#define IP30_HEART_ERR_IRQ (MIPS_CPU_IRQ_BASE + 6) + +#endif /* __ASM_MACH_IP30_IRQ_H */ diff --git a/arch/mips/include/asm/mach-ip30/kernel-entry-init.h b/arch/mips/include/asm/mach-ip30/kernel-entry-init.h new file mode 100644 index 000000000000..be0472c977d8 --- /dev/null +++ b/arch/mips/include/asm/mach-ip30/kernel-entry-init.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __ASM_MACH_IP30_KERNEL_ENTRY_H +#define __ASM_MACH_IP30_KERNEL_ENTRY_H + + .macro kernel_entry_setup + .endm + + .macro smp_slave_setup + move gp, a0 + .endm + +#endif /* __ASM_MACH_IP30_KERNEL_ENTRY_H */ diff --git a/arch/mips/include/asm/mach-ip30/mangle-port.h b/arch/mips/include/asm/mach-ip30/mangle-port.h new file mode 100644 index 000000000000..f3e1262a2d5e --- /dev/null +++ b/arch/mips/include/asm/mach-ip30/mangle-port.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2003, 2004 Ralf Baechle + */ +#ifndef __ASM_MACH_IP30_MANGLE_PORT_H +#define __ASM_MACH_IP30_MANGLE_PORT_H + +#define __swizzle_addr_b(port) ((port)^3) +#define __swizzle_addr_w(port) ((port)^2) +#define __swizzle_addr_l(port) (port) +#define __swizzle_addr_q(port) (port) + +#define ioswabb(a, x) (x) +#define __mem_ioswabb(a, x) (x) +#define ioswabw(a, x) (x) +#define __mem_ioswabw(a, x) cpu_to_le16(x) +#define ioswabl(a, x) (x) +#define __mem_ioswabl(a, x) cpu_to_le32(x) +#define ioswabq(a, x) (x) +#define __mem_ioswabq(a, x) cpu_to_le64(x) + +#endif /* __ASM_MACH_IP30_MANGLE_PORT_H */ diff --git a/arch/mips/include/asm/mach-ip30/spaces.h b/arch/mips/include/asm/mach-ip30/spaces.h new file mode 100644 index 000000000000..c8a302dfbe05 --- /dev/null +++ b/arch/mips/include/asm/mach-ip30/spaces.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2016 Joshua Kinard <kumba@gentoo.org> + * + */ +#ifndef _ASM_MACH_IP30_SPACES_H +#define _ASM_MACH_IP30_SPACES_H + +/* + * Memory in IP30/Octane is offset 512MB in the physical address space. + */ +#define PHYS_OFFSET _AC(0x20000000, UL) + +#ifdef CONFIG_64BIT +#define CAC_BASE _AC(0xA800000000000000, UL) +#endif + +#include <asm/mach-generic/spaces.h> + +#endif /* _ASM_MACH_IP30_SPACES_H */ diff --git a/arch/mips/include/asm/mach-ip30/war.h b/arch/mips/include/asm/mach-ip30/war.h new file mode 100644 index 000000000000..a98ba204f183 --- /dev/null +++ b/arch/mips/include/asm/mach-ip30/war.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2002, 2004, 2007 by Ralf Baechle <ralf@linux-mips.org> + */ +#ifndef __ASM_MIPS_MACH_IP30_WAR_H +#define __ASM_MIPS_MACH_IP30_WAR_H + +#define R4600_V1_INDEX_ICACHEOP_WAR 0 +#define R4600_V1_HIT_CACHEOP_WAR 0 +#define R4600_V2_HIT_CACHEOP_WAR 0 +#define MIPS_CACHE_SYNC_WAR 0 +#define BCM1250_M3_WAR 0 +#define SIBYTE_1956_WAR 0 +#define MIPS4K_ICACHE_REFILL_WAR 0 +#define MIPS34K_MISSED_ITLB_WAR 0 +#define R5432_CP0_INTERRUPT_WAR 0 +#define TX49XX_ICACHE_INDEX_INV_WAR 0 +#define ICACHE_REFILLS_WORKAROUND_WAR 0 + +#ifdef CONFIG_CPU_R10000 +#define R10000_LLSC_WAR 1 +#else +#define R10000_LLSC_WAR 0 +#endif + +#endif /* __ASM_MIPS_MACH_IP30_WAR_H */ diff --git a/arch/mips/include/asm/mach-loongson2ef/cpu-feature-overrides.h b/arch/mips/include/asm/mach-loongson2ef/cpu-feature-overrides.h new file mode 100644 index 000000000000..b2ee859ca0b7 --- /dev/null +++ b/arch/mips/include/asm/mach-loongson2ef/cpu-feature-overrides.h @@ -0,0 +1,44 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (C) 2009 Wu Zhangjin <wuzhangjin@gmail.com> + * Copyright (C) 2009 Philippe Vachon <philippe@cowpig.ca> + * Copyright (C) 2009 Zhang Le <r0bertz@gentoo.org> + * + * reference: /proc/cpuinfo, + * arch/mips/kernel/cpu-probe.c(cpu_probe_legacy), + * arch/mips/kernel/proc.c(show_cpuinfo), + * loongson2f user manual. + */ + +#ifndef __ASM_MACH_LOONGSON2EF_CPU_FEATURE_OVERRIDES_H +#define __ASM_MACH_LOONGSON2EF_CPU_FEATURE_OVERRIDES_H + +#define cpu_has_32fpr 1 +#define cpu_has_3k_cache 0 +#define cpu_has_4k_cache 1 +#define cpu_has_4kex 1 +#define cpu_has_64bits 1 +#define cpu_has_cache_cdex_p 0 +#define cpu_has_cache_cdex_s 0 +#define cpu_has_counter 1 +#define cpu_has_dc_aliases (PAGE_SIZE < 0x4000) +#define cpu_has_divec 0 +#define cpu_has_ejtag 0 +#define cpu_has_inclusive_pcaches 1 +#define cpu_has_llsc 1 +#define cpu_has_mcheck 0 +#define cpu_has_mdmx 0 +#define cpu_has_mips16 0 +#define cpu_has_mips16e2 0 +#define cpu_has_mips3d 0 +#define cpu_has_mipsmt 0 +#define cpu_has_smartmips 0 +#define cpu_has_tlb 1 +#define cpu_has_tx39_cache 0 +#define cpu_has_vce 0 +#define cpu_has_veic 0 +#define cpu_has_vint 0 +#define cpu_has_vtag_icache 0 +#define cpu_has_watch 1 + +#endif /* __ASM_MACH_LOONGSON64_CPU_FEATURE_OVERRIDES_H */ diff --git a/arch/mips/include/asm/mach-loongson64/cs5536/cs5536.h b/arch/mips/include/asm/mach-loongson2ef/cs5536/cs5536.h index 9795b3361532..9795b3361532 100644 --- a/arch/mips/include/asm/mach-loongson64/cs5536/cs5536.h +++ b/arch/mips/include/asm/mach-loongson2ef/cs5536/cs5536.h diff --git a/arch/mips/include/asm/mach-loongson64/cs5536/cs5536_mfgpt.h b/arch/mips/include/asm/mach-loongson2ef/cs5536/cs5536_mfgpt.h index 52e8bb0fc04d..52e8bb0fc04d 100644 --- a/arch/mips/include/asm/mach-loongson64/cs5536/cs5536_mfgpt.h +++ b/arch/mips/include/asm/mach-loongson2ef/cs5536/cs5536_mfgpt.h diff --git a/arch/mips/include/asm/mach-loongson64/cs5536/cs5536_pci.h b/arch/mips/include/asm/mach-loongson2ef/cs5536/cs5536_pci.h index a0d4b752899e..a0d4b752899e 100644 --- a/arch/mips/include/asm/mach-loongson64/cs5536/cs5536_pci.h +++ b/arch/mips/include/asm/mach-loongson2ef/cs5536/cs5536_pci.h diff --git a/arch/mips/include/asm/mach-loongson64/cs5536/cs5536_vsm.h b/arch/mips/include/asm/mach-loongson2ef/cs5536/cs5536_vsm.h index 70d0153cccc3..70d0153cccc3 100644 --- a/arch/mips/include/asm/mach-loongson64/cs5536/cs5536_vsm.h +++ b/arch/mips/include/asm/mach-loongson2ef/cs5536/cs5536_vsm.h diff --git a/arch/mips/include/asm/mach-loongson2ef/loongson.h b/arch/mips/include/asm/mach-loongson2ef/loongson.h new file mode 100644 index 000000000000..5008af0a1a19 --- /dev/null +++ b/arch/mips/include/asm/mach-loongson2ef/loongson.h @@ -0,0 +1,326 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (C) 2009 Lemote, Inc. + * Author: Wu Zhangjin <wuzhangjin@gmail.com> + */ + +#ifndef __ASM_MACH_LOONGSON2EF_LOONGSON_H +#define __ASM_MACH_LOONGSON2EF_LOONGSON_H + +#include <linux/io.h> +#include <linux/init.h> +#include <linux/irq.h> + +/* loongson internal northbridge initialization */ +extern void bonito_irq_init(void); + +/* machine-specific reboot/halt operation */ +extern void mach_prepare_reboot(void); +extern void mach_prepare_shutdown(void); + +/* environment arguments from bootloader */ +extern u32 cpu_clock_freq; +extern u32 memsize, highmemsize; + +/* loongson-specific command line, env and memory initialization */ +extern void __init prom_init_memory(void); +extern void __init prom_init_machtype(void); +extern void __init prom_init_env(void); +#ifdef CONFIG_LOONGSON_UART_BASE +extern unsigned long _loongson_uart_base, loongson_uart_base; +extern void prom_init_loongson_uart_base(void); +#endif + +static inline void prom_init_uart_base(void) +{ +#ifdef CONFIG_LOONGSON_UART_BASE + prom_init_loongson_uart_base(); +#endif +} + +/* irq operation functions */ +extern void bonito_irqdispatch(void); +extern void __init bonito_irq_init(void); +extern void __init mach_init_irq(void); +extern void mach_irq_dispatch(unsigned int pending); +extern int mach_i8259_irq(void); + +/* We need this in some places... */ +#define delay() ({ \ + int x; \ + for (x = 0; x < 100000; x++) \ + __asm__ __volatile__(""); \ +}) + +#define LOONGSON_REG(x) \ + (*(volatile u32 *)((char *)CKSEG1ADDR(LOONGSON_REG_BASE) + (x))) + +#define LOONGSON_IRQ_BASE 32 +#define LOONGSON2_PERFCNT_IRQ (MIPS_CPU_IRQ_BASE + 6) /* cpu perf counter */ + +#include <linux/interrupt.h> +static inline void do_perfcnt_IRQ(void) +{ +#if IS_ENABLED(CONFIG_OPROFILE) + do_IRQ(LOONGSON2_PERFCNT_IRQ); +#endif +} + +#define LOONGSON_FLASH_BASE 0x1c000000 +#define LOONGSON_FLASH_SIZE 0x02000000 /* 32M */ +#define LOONGSON_FLASH_TOP (LOONGSON_FLASH_BASE+LOONGSON_FLASH_SIZE-1) + +#define LOONGSON_LIO0_BASE 0x1e000000 +#define LOONGSON_LIO0_SIZE 0x01C00000 /* 28M */ +#define LOONGSON_LIO0_TOP (LOONGSON_LIO0_BASE+LOONGSON_LIO0_SIZE-1) + +#define LOONGSON_BOOT_BASE 0x1fc00000 +#define LOONGSON_BOOT_SIZE 0x00100000 /* 1M */ +#define LOONGSON_BOOT_TOP (LOONGSON_BOOT_BASE+LOONGSON_BOOT_SIZE-1) +#define LOONGSON_REG_BASE 0x1fe00000 +#define LOONGSON_REG_SIZE 0x00100000 /* 256Bytes + 256Bytes + ??? */ +#define LOONGSON_REG_TOP (LOONGSON_REG_BASE+LOONGSON_REG_SIZE-1) + +#define LOONGSON_LIO1_BASE 0x1ff00000 +#define LOONGSON_LIO1_SIZE 0x00100000 /* 1M */ +#define LOONGSON_LIO1_TOP (LOONGSON_LIO1_BASE+LOONGSON_LIO1_SIZE-1) + +#define LOONGSON_PCILO0_BASE 0x10000000 +#define LOONGSON_PCILO1_BASE 0x14000000 +#define LOONGSON_PCILO2_BASE 0x18000000 +#define LOONGSON_PCILO_BASE LOONGSON_PCILO0_BASE +#define LOONGSON_PCILO_SIZE 0x0c000000 /* 64M * 3 */ +#define LOONGSON_PCILO_TOP (LOONGSON_PCILO0_BASE+LOONGSON_PCILO_SIZE-1) + +#define LOONGSON_PCICFG_BASE 0x1fe80000 +#define LOONGSON_PCICFG_SIZE 0x00000800 /* 2K */ +#define LOONGSON_PCICFG_TOP (LOONGSON_PCICFG_BASE+LOONGSON_PCICFG_SIZE-1) +#define LOONGSON_PCIIO_BASE 0x1fd00000 + +#define LOONGSON_PCIIO_SIZE 0x00100000 /* 1M */ +#define LOONGSON_PCIIO_TOP (LOONGSON_PCIIO_BASE+LOONGSON_PCIIO_SIZE-1) + +/* Loongson Register Bases */ + +#define LOONGSON_PCICONFIGBASE 0x00 +#define LOONGSON_REGBASE 0x100 + +/* PCI Configuration Registers */ + +#define LOONGSON_PCI_REG(x) LOONGSON_REG(LOONGSON_PCICONFIGBASE + (x)) +#define LOONGSON_PCIDID LOONGSON_PCI_REG(0x00) +#define LOONGSON_PCICMD LOONGSON_PCI_REG(0x04) +#define LOONGSON_PCICLASS LOONGSON_PCI_REG(0x08) +#define LOONGSON_PCILTIMER LOONGSON_PCI_REG(0x0c) +#define LOONGSON_PCIBASE0 LOONGSON_PCI_REG(0x10) +#define LOONGSON_PCIBASE1 LOONGSON_PCI_REG(0x14) +#define LOONGSON_PCIBASE2 LOONGSON_PCI_REG(0x18) +#define LOONGSON_PCIBASE3 LOONGSON_PCI_REG(0x1c) +#define LOONGSON_PCIBASE4 LOONGSON_PCI_REG(0x20) +#define LOONGSON_PCIEXPRBASE LOONGSON_PCI_REG(0x30) +#define LOONGSON_PCIINT LOONGSON_PCI_REG(0x3c) + +#define LOONGSON_PCI_ISR4C LOONGSON_PCI_REG(0x4c) + +#define LOONGSON_PCICMD_PERR_CLR 0x80000000 +#define LOONGSON_PCICMD_SERR_CLR 0x40000000 +#define LOONGSON_PCICMD_MABORT_CLR 0x20000000 +#define LOONGSON_PCICMD_MTABORT_CLR 0x10000000 +#define LOONGSON_PCICMD_TABORT_CLR 0x08000000 +#define LOONGSON_PCICMD_MPERR_CLR 0x01000000 +#define LOONGSON_PCICMD_PERRRESPEN 0x00000040 +#define LOONGSON_PCICMD_ASTEPEN 0x00000080 +#define LOONGSON_PCICMD_SERREN 0x00000100 +#define LOONGSON_PCILTIMER_BUSLATENCY 0x0000ff00 +#define LOONGSON_PCILTIMER_BUSLATENCY_SHIFT 8 + +/* Loongson h/w Configuration */ + +#define LOONGSON_GENCFG_OFFSET 0x4 +#define LOONGSON_GENCFG LOONGSON_REG(LOONGSON_REGBASE + LOONGSON_GENCFG_OFFSET) + +#define LOONGSON_GENCFG_DEBUGMODE 0x00000001 +#define LOONGSON_GENCFG_SNOOPEN 0x00000002 +#define LOONGSON_GENCFG_CPUSELFRESET 0x00000004 + +#define LOONGSON_GENCFG_FORCE_IRQA 0x00000008 +#define LOONGSON_GENCFG_IRQA_ISOUT 0x00000010 +#define LOONGSON_GENCFG_IRQA_FROM_INT1 0x00000020 +#define LOONGSON_GENCFG_BYTESWAP 0x00000040 + +#define LOONGSON_GENCFG_UNCACHED 0x00000080 +#define LOONGSON_GENCFG_PREFETCHEN 0x00000100 +#define LOONGSON_GENCFG_WBEHINDEN 0x00000200 +#define LOONGSON_GENCFG_CACHEALG 0x00000c00 +#define LOONGSON_GENCFG_CACHEALG_SHIFT 10 +#define LOONGSON_GENCFG_PCIQUEUE 0x00001000 +#define LOONGSON_GENCFG_CACHESTOP 0x00002000 +#define LOONGSON_GENCFG_MSTRBYTESWAP 0x00004000 +#define LOONGSON_GENCFG_BUSERREN 0x00008000 +#define LOONGSON_GENCFG_NORETRYTIMEOUT 0x00010000 +#define LOONGSON_GENCFG_SHORTCOPYTIMEOUT 0x00020000 + +/* PCI address map control */ + +#define LOONGSON_PCIMAP LOONGSON_REG(LOONGSON_REGBASE + 0x10) +#define LOONGSON_PCIMEMBASECFG LOONGSON_REG(LOONGSON_REGBASE + 0x14) +#define LOONGSON_PCIMAP_CFG LOONGSON_REG(LOONGSON_REGBASE + 0x18) + +/* GPIO Regs - r/w */ + +#define LOONGSON_GPIODATA LOONGSON_REG(LOONGSON_REGBASE + 0x1c) +#define LOONGSON_GPIOIE LOONGSON_REG(LOONGSON_REGBASE + 0x20) + +/* ICU Configuration Regs - r/w */ + +#define LOONGSON_INTEDGE LOONGSON_REG(LOONGSON_REGBASE + 0x24) +#define LOONGSON_INTSTEER LOONGSON_REG(LOONGSON_REGBASE + 0x28) +#define LOONGSON_INTPOL LOONGSON_REG(LOONGSON_REGBASE + 0x2c) + +/* ICU Enable Regs - IntEn & IntISR are r/o. */ + +#define LOONGSON_INTENSET LOONGSON_REG(LOONGSON_REGBASE + 0x30) +#define LOONGSON_INTENCLR LOONGSON_REG(LOONGSON_REGBASE + 0x34) +#define LOONGSON_INTEN LOONGSON_REG(LOONGSON_REGBASE + 0x38) +#define LOONGSON_INTISR LOONGSON_REG(LOONGSON_REGBASE + 0x3c) + +/* ICU */ +#define LOONGSON_ICU_MBOXES 0x0000000f +#define LOONGSON_ICU_MBOXES_SHIFT 0 +#define LOONGSON_ICU_DMARDY 0x00000010 +#define LOONGSON_ICU_DMAEMPTY 0x00000020 +#define LOONGSON_ICU_COPYRDY 0x00000040 +#define LOONGSON_ICU_COPYEMPTY 0x00000080 +#define LOONGSON_ICU_COPYERR 0x00000100 +#define LOONGSON_ICU_PCIIRQ 0x00000200 +#define LOONGSON_ICU_MASTERERR 0x00000400 +#define LOONGSON_ICU_SYSTEMERR 0x00000800 +#define LOONGSON_ICU_DRAMPERR 0x00001000 +#define LOONGSON_ICU_RETRYERR 0x00002000 +#define LOONGSON_ICU_GPIOS 0x01ff0000 +#define LOONGSON_ICU_GPIOS_SHIFT 16 +#define LOONGSON_ICU_GPINS 0x7e000000 +#define LOONGSON_ICU_GPINS_SHIFT 25 +#define LOONGSON_ICU_MBOX(N) (1<<(LOONGSON_ICU_MBOXES_SHIFT+(N))) +#define LOONGSON_ICU_GPIO(N) (1<<(LOONGSON_ICU_GPIOS_SHIFT+(N))) +#define LOONGSON_ICU_GPIN(N) (1<<(LOONGSON_ICU_GPINS_SHIFT+(N))) + +/* PCI prefetch window base & mask */ + +#define LOONGSON_MEM_WIN_BASE_L LOONGSON_REG(LOONGSON_REGBASE + 0x40) +#define LOONGSON_MEM_WIN_BASE_H LOONGSON_REG(LOONGSON_REGBASE + 0x44) +#define LOONGSON_MEM_WIN_MASK_L LOONGSON_REG(LOONGSON_REGBASE + 0x48) +#define LOONGSON_MEM_WIN_MASK_H LOONGSON_REG(LOONGSON_REGBASE + 0x4c) + +/* PCI_Hit*_Sel_* */ + +#define LOONGSON_PCI_HIT0_SEL_L LOONGSON_REG(LOONGSON_REGBASE + 0x50) +#define LOONGSON_PCI_HIT0_SEL_H LOONGSON_REG(LOONGSON_REGBASE + 0x54) +#define LOONGSON_PCI_HIT1_SEL_L LOONGSON_REG(LOONGSON_REGBASE + 0x58) +#define LOONGSON_PCI_HIT1_SEL_H LOONGSON_REG(LOONGSON_REGBASE + 0x5c) +#define LOONGSON_PCI_HIT2_SEL_L LOONGSON_REG(LOONGSON_REGBASE + 0x60) +#define LOONGSON_PCI_HIT2_SEL_H LOONGSON_REG(LOONGSON_REGBASE + 0x64) + +/* PXArb Config & Status */ + +#define LOONGSON_PXARB_CFG LOONGSON_REG(LOONGSON_REGBASE + 0x68) +#define LOONGSON_PXARB_STATUS LOONGSON_REG(LOONGSON_REGBASE + 0x6c) + +/* Chip Config registor of each physical cpu package, PRid >= Loongson-2F */ +#define LOONGSON_CHIPCFG (void __iomem *)TO_UNCAC(0x1fc00180) + +/* pcimap */ + +#define LOONGSON_PCIMAP_PCIMAP_LO0 0x0000003f +#define LOONGSON_PCIMAP_PCIMAP_LO0_SHIFT 0 +#define LOONGSON_PCIMAP_PCIMAP_LO1 0x00000fc0 +#define LOONGSON_PCIMAP_PCIMAP_LO1_SHIFT 6 +#define LOONGSON_PCIMAP_PCIMAP_LO2 0x0003f000 +#define LOONGSON_PCIMAP_PCIMAP_LO2_SHIFT 12 +#define LOONGSON_PCIMAP_PCIMAP_2 0x00040000 +#define LOONGSON_PCIMAP_WIN(WIN, ADDR) \ + ((((ADDR)>>26) & LOONGSON_PCIMAP_PCIMAP_LO0) << ((WIN)*6)) + +#ifdef CONFIG_CPU_SUPPORTS_CPUFREQ +#include <linux/cpufreq.h> +extern struct cpufreq_frequency_table loongson2_clockmod_table[]; +#endif + +/* + * address windows configuration module + * + * loongson2e do not have this module + */ +#ifdef CONFIG_CPU_SUPPORTS_ADDRWINCFG + +/* address window config module base address */ +#define LOONGSON_ADDRWINCFG_BASE 0x3ff00000ul +#define LOONGSON_ADDRWINCFG_SIZE 0x180 + +extern unsigned long _loongson_addrwincfg_base; +#define LOONGSON_ADDRWINCFG(offset) \ + (*(volatile u64 *)(_loongson_addrwincfg_base + (offset))) + +#define CPU_WIN0_BASE LOONGSON_ADDRWINCFG(0x00) +#define CPU_WIN1_BASE LOONGSON_ADDRWINCFG(0x08) +#define CPU_WIN2_BASE LOONGSON_ADDRWINCFG(0x10) +#define CPU_WIN3_BASE LOONGSON_ADDRWINCFG(0x18) + +#define CPU_WIN0_MASK LOONGSON_ADDRWINCFG(0x20) +#define CPU_WIN1_MASK LOONGSON_ADDRWINCFG(0x28) +#define CPU_WIN2_MASK LOONGSON_ADDRWINCFG(0x30) +#define CPU_WIN3_MASK LOONGSON_ADDRWINCFG(0x38) + +#define CPU_WIN0_MMAP LOONGSON_ADDRWINCFG(0x40) +#define CPU_WIN1_MMAP LOONGSON_ADDRWINCFG(0x48) +#define CPU_WIN2_MMAP LOONGSON_ADDRWINCFG(0x50) +#define CPU_WIN3_MMAP LOONGSON_ADDRWINCFG(0x58) + +#define PCIDMA_WIN0_BASE LOONGSON_ADDRWINCFG(0x60) +#define PCIDMA_WIN1_BASE LOONGSON_ADDRWINCFG(0x68) +#define PCIDMA_WIN2_BASE LOONGSON_ADDRWINCFG(0x70) +#define PCIDMA_WIN3_BASE LOONGSON_ADDRWINCFG(0x78) + +#define PCIDMA_WIN0_MASK LOONGSON_ADDRWINCFG(0x80) +#define PCIDMA_WIN1_MASK LOONGSON_ADDRWINCFG(0x88) +#define PCIDMA_WIN2_MASK LOONGSON_ADDRWINCFG(0x90) +#define PCIDMA_WIN3_MASK LOONGSON_ADDRWINCFG(0x98) + +#define PCIDMA_WIN0_MMAP LOONGSON_ADDRWINCFG(0xa0) +#define PCIDMA_WIN1_MMAP LOONGSON_ADDRWINCFG(0xa8) +#define PCIDMA_WIN2_MMAP LOONGSON_ADDRWINCFG(0xb0) +#define PCIDMA_WIN3_MMAP LOONGSON_ADDRWINCFG(0xb8) + +#define ADDRWIN_WIN0 0 +#define ADDRWIN_WIN1 1 +#define ADDRWIN_WIN2 2 +#define ADDRWIN_WIN3 3 + +#define ADDRWIN_MAP_DST_DDR 0 +#define ADDRWIN_MAP_DST_PCI 1 +#define ADDRWIN_MAP_DST_LIO 1 + +/* + * s: CPU, PCIDMA + * d: DDR, PCI, LIO + * win: 0, 1, 2, 3 + * src: map source + * dst: map destination + * size: ~mask + 1 + */ +#define LOONGSON_ADDRWIN_CFG(s, d, w, src, dst, size) do {\ + s##_WIN##w##_BASE = (src); \ + s##_WIN##w##_MMAP = (dst) | ADDRWIN_MAP_DST_##d; \ + s##_WIN##w##_MASK = ~(size-1); \ +} while (0) + +#define LOONGSON_ADDRWIN_CPUTOPCI(win, src, dst, size) \ + LOONGSON_ADDRWIN_CFG(CPU, PCI, win, src, dst, size) +#define LOONGSON_ADDRWIN_CPUTODDR(win, src, dst, size) \ + LOONGSON_ADDRWIN_CFG(CPU, DDR, win, src, dst, size) +#define LOONGSON_ADDRWIN_PCITODDR(win, src, dst, size) \ + LOONGSON_ADDRWIN_CFG(PCIDMA, DDR, win, src, dst, size) + +#endif /* ! CONFIG_CPU_SUPPORTS_ADDRWINCFG */ + +#endif /* __ASM_MACH_LOONGSON2EF_LOONGSON_H */ diff --git a/arch/mips/include/asm/mach-loongson64/machine.h b/arch/mips/include/asm/mach-loongson2ef/machine.h index 8ef7ea94a26d..4097267ef186 100644 --- a/arch/mips/include/asm/mach-loongson64/machine.h +++ b/arch/mips/include/asm/mach-loongson2ef/machine.h @@ -4,8 +4,8 @@ * Author: Wu Zhangjin <wuzhangjin@gmail.com> */ -#ifndef __ASM_MACH_LOONGSON64_MACHINE_H -#define __ASM_MACH_LOONGSON64_MACHINE_H +#ifndef __ASM_MACH_LOONGSON2EF_MACHINE_H +#define __ASM_MACH_LOONGSON2EF_MACHINE_H #ifdef CONFIG_LEMOTE_FULOONG2E @@ -20,10 +20,4 @@ #endif -#ifdef CONFIG_LOONGSON_MACH3X - -#define LOONGSON_MACHTYPE MACH_LOONGSON_GENERIC - -#endif /* CONFIG_LOONGSON_MACH3X */ - -#endif /* __ASM_MACH_LOONGSON64_MACHINE_H */ +#endif /* __ASM_MACH_LOONGSON2EF_MACHINE_H */ diff --git a/arch/mips/include/asm/mach-loongson2ef/mc146818rtc.h b/arch/mips/include/asm/mach-loongson2ef/mc146818rtc.h new file mode 100644 index 000000000000..00d602629a55 --- /dev/null +++ b/arch/mips/include/asm/mach-loongson2ef/mc146818rtc.h @@ -0,0 +1,36 @@ +/* + * 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) 1998, 2001, 03, 07 by Ralf Baechle (ralf@linux-mips.org) + * + * RTC routines for PC style attached Dallas chip. + */ +#ifndef __ASM_MACH_LOONGSON2EF_MC146818RTC_H +#define __ASM_MACH_LOONGSON2EF_MC146818RTC_H + +#include <linux/io.h> + +#define RTC_PORT(x) (0x70 + (x)) +#define RTC_IRQ 8 + +static inline unsigned char CMOS_READ(unsigned long addr) +{ + outb_p(addr, RTC_PORT(0)); + return inb_p(RTC_PORT(1)); +} + +static inline void CMOS_WRITE(unsigned char data, unsigned long addr) +{ + outb_p(addr, RTC_PORT(0)); + outb_p(data, RTC_PORT(1)); +} + +#define RTC_ALWAYS_BCD 0 + +#ifndef mc146818_decode_year +#define mc146818_decode_year(year) ((year) < 70 ? (year) + 2000 : (year) + 1970) +#endif + +#endif /* __ASM_MACH_LOONGSON2EF_MC146818RTC_H */ diff --git a/arch/mips/include/asm/mach-loongson64/mem.h b/arch/mips/include/asm/mach-loongson2ef/mem.h index ce33c174c04d..d1d759b8974e 100644 --- a/arch/mips/include/asm/mach-loongson64/mem.h +++ b/arch/mips/include/asm/mach-loongson2ef/mem.h @@ -4,8 +4,8 @@ * Author: Wu Zhangjin <wuzhangjin@gmail.com> */ -#ifndef __ASM_MACH_LOONGSON64_MEM_H -#define __ASM_MACH_LOONGSON64_MEM_H +#ifndef __ASM_MACH_LOONGSON2EF_MEM_H +#define __ASM_MACH_LOONGSON2EF_MEM_H /* * high memory space @@ -34,4 +34,4 @@ #define LOONGSON_MMIO_MEM_END 0x80000000 #endif -#endif /* __ASM_MACH_LOONGSON64_MEM_H */ +#endif /* __ASM_MACH_LOONGSON2EF_MEM_H */ diff --git a/arch/mips/include/asm/mach-loongson2ef/pci.h b/arch/mips/include/asm/mach-loongson2ef/pci.h new file mode 100644 index 000000000000..5588c5bc5395 --- /dev/null +++ b/arch/mips/include/asm/mach-loongson2ef/pci.h @@ -0,0 +1,46 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (c) 2008 Zhang Le <r0bertz@gentoo.org> + * Copyright (c) 2009 Wu Zhangjin <wuzhangjin@gmail.com> + */ + +#ifndef __ASM_MACH_LOONGSON2EF_PCI_H_ +#define __ASM_MACH_LOONGSON2EF_PCI_H_ + +extern struct pci_ops loongson_pci_ops; + +/* this is an offset from mips_io_port_base */ +#define LOONGSON_PCI_IO_START 0x00004000UL + +#ifdef CONFIG_CPU_SUPPORTS_ADDRWINCFG + +/* + * we use address window2 to map cpu address space to pci space + * window2: cpu [1G, 2G] -> pci [1G, 2G] + * why not use window 0 & 1? because they are used by cpu when booting. + * window0: cpu [0, 256M] -> ddr [0, 256M] + * window1: cpu [256M, 512M] -> pci [256M, 512M] + */ + +/* the smallest LOONGSON_CPU_MEM_SRC can be 512M */ +#define LOONGSON_CPU_MEM_SRC 0x40000000ul /* 1G */ +#define LOONGSON_PCI_MEM_DST LOONGSON_CPU_MEM_SRC + +#define LOONGSON_PCI_MEM_START LOONGSON_PCI_MEM_DST +#define LOONGSON_PCI_MEM_END (0x80000000ul-1) /* 2G */ + +#define MMAP_CPUTOPCI_SIZE (LOONGSON_PCI_MEM_END - \ + LOONGSON_PCI_MEM_START + 1) + +#else /* loongson2f/32bit & loongson2e */ + +/* this pci memory space is mapped by pcimap in pci.c */ +#define LOONGSON_PCI_MEM_START LOONGSON_PCILO1_BASE +#define LOONGSON_PCI_MEM_END (LOONGSON_PCILO1_BASE + 0x04000000 * 2) + +/* this is an offset from mips_io_port_base */ +#define LOONGSON_PCI_IO_START 0x00004000UL + +#endif /* !CONFIG_CPU_SUPPORTS_ADDRWINCFG */ + +#endif /* !__ASM_MACH_LOONGSON2EF_PCI_H_ */ diff --git a/arch/mips/include/asm/mach-loongson2ef/spaces.h b/arch/mips/include/asm/mach-loongson2ef/spaces.h new file mode 100644 index 000000000000..ba4e8e9b618e --- /dev/null +++ b/arch/mips/include/asm/mach-loongson2ef/spaces.h @@ -0,0 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_MACH_LOONGSON2EF_SPACES_H_ +#define __ASM_MACH_LOONGSON2EF_SPACES_H_ + +#if defined(CONFIG_64BIT) +#define CAC_BASE _AC(0x9800000000000000, UL) +#endif /* CONFIG_64BIT */ + +#include <asm/mach-generic/spaces.h> +#endif diff --git a/arch/mips/include/asm/mach-loongson32/prom.h b/arch/mips/include/asm/mach-loongson32/prom.h deleted file mode 100644 index cb789f18d790..000000000000 --- a/arch/mips/include/asm/mach-loongson32/prom.h +++ /dev/null @@ -1,20 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * Copyright (c) 2011 Zhang, Keguang <keguang.zhang@gmail.com> - */ - -#ifndef __ASM_MACH_LOONGSON32_PROM_H -#define __ASM_MACH_LOONGSON32_PROM_H - -#include <linux/io.h> -#include <linux/init.h> -#include <linux/irq.h> - -/* environment arguments from bootloader */ -extern unsigned long memsize, highmemsize; - -/* loongson-specific command line, env and memory initialization */ -extern char *prom_getenv(char *name); -extern void __init prom_init_cmdline(void); - -#endif /* __ASM_MACH_LOONGSON32_PROM_H */ diff --git a/arch/mips/include/asm/mach-loongson64/cpu-feature-overrides.h b/arch/mips/include/asm/mach-loongson64/cpu-feature-overrides.h index 4aca25f2ff06..7dc8d75445a9 100644 --- a/arch/mips/include/asm/mach-loongson64/cpu-feature-overrides.h +++ b/arch/mips/include/asm/mach-loongson64/cpu-feature-overrides.h @@ -43,11 +43,8 @@ #define cpu_has_vint 0 #define cpu_has_vtag_icache 0 #define cpu_has_watch 1 - -#ifdef CONFIG_CPU_LOONGSON3 #define cpu_has_wsbh 1 #define cpu_has_ic_fills_f_dc 1 #define cpu_hwrena_impl_bits 0xc0000000 -#endif #endif /* __ASM_MACH_LOONGSON64_CPU_FEATURE_OVERRIDES_H */ diff --git a/arch/mips/include/asm/mach-loongson64/irq.h b/arch/mips/include/asm/mach-loongson64/irq.h index be9f727a9328..73a89913dc38 100644 --- a/arch/mips/include/asm/mach-loongson64/irq.h +++ b/arch/mips/include/asm/mach-loongson64/irq.h @@ -4,8 +4,6 @@ #include <boot_param.h> -#ifdef CONFIG_CPU_LOONGSON3 - /* cpu core interrupt numbers */ #define MIPS_CPU_IRQ_BASE 56 @@ -35,8 +33,6 @@ #define LOONGSON_INT_COREx_INTy(x, y) (1<<(x) | 1<<(y+4)) /* route to int y of core x */ -#endif - extern void fixup_irqs(void); extern void loongson3_ipi_interrupt(struct pt_regs *regs); diff --git a/arch/mips/include/asm/mach-loongson64/kernel-entry-init.h b/arch/mips/include/asm/mach-loongson64/kernel-entry-init.h index b5e288a12dfe..87a5bfbf8cfe 100644 --- a/arch/mips/include/asm/mach-loongson64/kernel-entry-init.h +++ b/arch/mips/include/asm/mach-loongson64/kernel-entry-init.h @@ -17,7 +17,6 @@ * Override macros used in arch/mips/kernel/head.S. */ .macro kernel_entry_setup -#ifdef CONFIG_CPU_LOONGSON3 .set push .set mips64 /* Set LPA on LOONGSON3 config3 */ @@ -30,23 +29,29 @@ mtc0 t0, CP0_PAGEGRAIN /* Enable STFill Buffer */ mfc0 t0, CP0_PRID + /* Loongson-3A R4+ */ + andi t1, t0, PRID_IMP_MASK + li t2, PRID_IMP_LOONGSON_64G + beq t1, t2, 1f + nop + /* Loongson-3A R2/R3 */ andi t0, (PRID_IMP_MASK | PRID_REV_MASK) - slti t0, (PRID_IMP_LOONGSON_64 | PRID_REV_LOONGSON3A_R2_0) - bnez t0, 1f + slti t0, (PRID_IMP_LOONGSON_64C | PRID_REV_LOONGSON3A_R2_0) + bnez t0, 2f + nop +1: mfc0 t0, CP0_CONFIG6 or t0, 0x100 mtc0 t0, CP0_CONFIG6 -1: +2: _ehb .set pop -#endif .endm /* * Do SMP slave processor setup. */ .macro smp_slave_setup -#ifdef CONFIG_CPU_LOONGSON3 .set push .set mips64 /* Set LPA on LOONGSON3 config3 */ @@ -59,16 +64,23 @@ mtc0 t0, CP0_PAGEGRAIN /* Enable STFill Buffer */ mfc0 t0, CP0_PRID + /* Loongson-3A R4+ */ + andi t1, t0, PRID_IMP_MASK + li t2, PRID_IMP_LOONGSON_64G + beq t1, t2, 1f + nop + /* Loongson-3A R2/R3 */ andi t0, (PRID_IMP_MASK | PRID_REV_MASK) - slti t0, (PRID_IMP_LOONGSON_64 | PRID_REV_LOONGSON3A_R2_0) - bnez t0, 1f + slti t0, (PRID_IMP_LOONGSON_64C | PRID_REV_LOONGSON3A_R2_0) + bnez t0, 2f + nop +1: mfc0 t0, CP0_CONFIG6 or t0, 0x100 mtc0 t0, CP0_CONFIG6 -1: +2: _ehb .set pop -#endif .endm #endif /* __ASM_MACH_LOONGSON64_KERNEL_ENTRY_H */ diff --git a/arch/mips/include/asm/mach-loongson64/loongson.h b/arch/mips/include/asm/mach-loongson64/loongson.h index 694a58574ec0..a8fce112a9b0 100644 --- a/arch/mips/include/asm/mach-loongson64/loongson.h +++ b/arch/mips/include/asm/mach-loongson64/loongson.h @@ -12,8 +12,6 @@ #include <linux/irq.h> #include <boot_param.h> -/* loongson internal northbridge initialization */ -extern void bonito_irq_init(void); /* machine-specific reboot/halt operation */ extern void mach_prepare_reboot(void); @@ -26,25 +24,9 @@ extern const struct plat_smp_ops loongson3_smp_ops; /* loongson-specific command line, env and memory initialization */ extern void __init prom_init_memory(void); -extern void __init prom_init_cmdline(void); -extern void __init prom_init_machtype(void); extern void __init prom_init_env(void); -#ifdef CONFIG_LOONGSON_UART_BASE -extern unsigned long _loongson_uart_base[], loongson_uart_base[]; -extern void prom_init_loongson_uart_base(void); -#endif - -static inline void prom_init_uart_base(void) -{ -#ifdef CONFIG_LOONGSON_UART_BASE - prom_init_loongson_uart_base(); -#endif -} /* irq operation functions */ -extern void bonito_irqdispatch(void); -extern void __init bonito_irq_init(void); -extern void __init mach_init_irq(void); extern void mach_irq_dispatch(unsigned int pending); extern int mach_i8259_irq(void); @@ -64,17 +46,6 @@ extern int mach_i8259_irq(void); #define LOONGSON3_REG32(base, x) \ (*(volatile u32 *)((char *)TO_UNCAC(base) + (x))) -#define LOONGSON_IRQ_BASE 32 -#define LOONGSON2_PERFCNT_IRQ (MIPS_CPU_IRQ_BASE + 6) /* cpu perf counter */ - -#include <linux/interrupt.h> -static inline void do_perfcnt_IRQ(void) -{ -#if IS_ENABLED(CONFIG_OPROFILE) - do_IRQ(LOONGSON2_PERFCNT_IRQ); -#endif -} - #define LOONGSON_FLASH_BASE 0x1c000000 #define LOONGSON_FLASH_SIZE 0x02000000 /* 32M */ #define LOONGSON_FLASH_TOP (LOONGSON_FLASH_BASE+LOONGSON_FLASH_SIZE-1) @@ -109,11 +80,7 @@ static inline void do_perfcnt_IRQ(void) #define LOONGSON_PCICFG_SIZE 0x00000800 /* 2K */ #define LOONGSON_PCICFG_TOP (LOONGSON_PCICFG_BASE+LOONGSON_PCICFG_SIZE-1) -#ifdef CONFIG_CPU_LOONGSON3 #define LOONGSON_PCIIO_BASE loongson_sysconf.pci_io_base -#else -#define LOONGSON_PCIIO_BASE 0x1fd00000 -#endif #define LOONGSON_PCIIO_SIZE 0x00100000 /* 1M */ #define LOONGSON_PCIIO_TOP (LOONGSON_PCIIO_BASE+LOONGSON_PCIIO_SIZE-1) @@ -270,86 +237,4 @@ extern u64 loongson_freqctrl[MAX_PACKAGES]; #define LOONGSON_PCIMAP_WIN(WIN, ADDR) \ ((((ADDR)>>26) & LOONGSON_PCIMAP_PCIMAP_LO0) << ((WIN)*6)) -#ifdef CONFIG_CPU_SUPPORTS_CPUFREQ -#include <linux/cpufreq.h> -extern struct cpufreq_frequency_table loongson2_clockmod_table[]; -#endif - -/* - * address windows configuration module - * - * loongson2e do not have this module - */ -#ifdef CONFIG_CPU_SUPPORTS_ADDRWINCFG - -/* address window config module base address */ -#define LOONGSON_ADDRWINCFG_BASE 0x3ff00000ul -#define LOONGSON_ADDRWINCFG_SIZE 0x180 - -extern unsigned long _loongson_addrwincfg_base; -#define LOONGSON_ADDRWINCFG(offset) \ - (*(volatile u64 *)(_loongson_addrwincfg_base + (offset))) - -#define CPU_WIN0_BASE LOONGSON_ADDRWINCFG(0x00) -#define CPU_WIN1_BASE LOONGSON_ADDRWINCFG(0x08) -#define CPU_WIN2_BASE LOONGSON_ADDRWINCFG(0x10) -#define CPU_WIN3_BASE LOONGSON_ADDRWINCFG(0x18) - -#define CPU_WIN0_MASK LOONGSON_ADDRWINCFG(0x20) -#define CPU_WIN1_MASK LOONGSON_ADDRWINCFG(0x28) -#define CPU_WIN2_MASK LOONGSON_ADDRWINCFG(0x30) -#define CPU_WIN3_MASK LOONGSON_ADDRWINCFG(0x38) - -#define CPU_WIN0_MMAP LOONGSON_ADDRWINCFG(0x40) -#define CPU_WIN1_MMAP LOONGSON_ADDRWINCFG(0x48) -#define CPU_WIN2_MMAP LOONGSON_ADDRWINCFG(0x50) -#define CPU_WIN3_MMAP LOONGSON_ADDRWINCFG(0x58) - -#define PCIDMA_WIN0_BASE LOONGSON_ADDRWINCFG(0x60) -#define PCIDMA_WIN1_BASE LOONGSON_ADDRWINCFG(0x68) -#define PCIDMA_WIN2_BASE LOONGSON_ADDRWINCFG(0x70) -#define PCIDMA_WIN3_BASE LOONGSON_ADDRWINCFG(0x78) - -#define PCIDMA_WIN0_MASK LOONGSON_ADDRWINCFG(0x80) -#define PCIDMA_WIN1_MASK LOONGSON_ADDRWINCFG(0x88) -#define PCIDMA_WIN2_MASK LOONGSON_ADDRWINCFG(0x90) -#define PCIDMA_WIN3_MASK LOONGSON_ADDRWINCFG(0x98) - -#define PCIDMA_WIN0_MMAP LOONGSON_ADDRWINCFG(0xa0) -#define PCIDMA_WIN1_MMAP LOONGSON_ADDRWINCFG(0xa8) -#define PCIDMA_WIN2_MMAP LOONGSON_ADDRWINCFG(0xb0) -#define PCIDMA_WIN3_MMAP LOONGSON_ADDRWINCFG(0xb8) - -#define ADDRWIN_WIN0 0 -#define ADDRWIN_WIN1 1 -#define ADDRWIN_WIN2 2 -#define ADDRWIN_WIN3 3 - -#define ADDRWIN_MAP_DST_DDR 0 -#define ADDRWIN_MAP_DST_PCI 1 -#define ADDRWIN_MAP_DST_LIO 1 - -/* - * s: CPU, PCIDMA - * d: DDR, PCI, LIO - * win: 0, 1, 2, 3 - * src: map source - * dst: map destination - * size: ~mask + 1 - */ -#define LOONGSON_ADDRWIN_CFG(s, d, w, src, dst, size) do {\ - s##_WIN##w##_BASE = (src); \ - s##_WIN##w##_MMAP = (dst) | ADDRWIN_MAP_DST_##d; \ - s##_WIN##w##_MASK = ~(size-1); \ -} while (0) - -#define LOONGSON_ADDRWIN_CPUTOPCI(win, src, dst, size) \ - LOONGSON_ADDRWIN_CFG(CPU, PCI, win, src, dst, size) -#define LOONGSON_ADDRWIN_CPUTODDR(win, src, dst, size) \ - LOONGSON_ADDRWIN_CFG(CPU, DDR, win, src, dst, size) -#define LOONGSON_ADDRWIN_PCITODDR(win, src, dst, size) \ - LOONGSON_ADDRWIN_CFG(PCIDMA, DDR, win, src, dst, size) - -#endif /* ! CONFIG_CPU_SUPPORTS_ADDRWINCFG */ - #endif /* __ASM_MACH_LOONGSON64_LOONGSON_H */ diff --git a/arch/mips/include/asm/mach-loongson64/loongson_regs.h b/arch/mips/include/asm/mach-loongson64/loongson_regs.h new file mode 100644 index 000000000000..363a47a5d26e --- /dev/null +++ b/arch/mips/include/asm/mach-loongson64/loongson_regs.h @@ -0,0 +1,227 @@ +/* + * Read/Write Loongson Extension Registers + */ + +#ifndef _LOONGSON_REGS_H_ +#define _LOONGSON_REGS_H_ + +#include <linux/types.h> +#include <linux/bits.h> + +#include <asm/mipsregs.h> +#include <asm/cpu.h> + +static inline bool cpu_has_cfg(void) +{ + return ((read_c0_prid() & PRID_IMP_MASK) == PRID_IMP_LOONGSON_64G); +} + +static inline u32 read_cpucfg(u32 reg) +{ + u32 __res; + + __asm__ __volatile__( + "parse_r __res,%0\n\t" + "parse_r reg,%1\n\t" + ".insn \n\t" + ".word (0xc8080118 | (reg << 21) | (__res << 11))\n\t" + :"=r"(__res) + :"r"(reg) + : + ); + return __res; +} + +/* Bit Domains for CFG registers */ +#define LOONGSON_CFG0 0x0 +#define LOONGSON_CFG0_PRID GENMASK(31, 0) + +#define LOONGSON_CFG1 0x1 +#define LOONGSON_CFG1_FP BIT(0) +#define LOONGSON_CFG1_FPREV GENMASK(3, 1) +#define LOONGSON_CFG1_MMI BIT(4) +#define LOONGSON_CFG1_MSA1 BIT(5) +#define LOONGSON_CFG1_MSA2 BIT(6) +#define LOONGSON_CFG1_CGP BIT(7) +#define LOONGSON_CFG1_WRP BIT(8) +#define LOONGSON_CFG1_LSX1 BIT(9) +#define LOONGSON_CFG1_LSX2 BIT(10) +#define LOONGSON_CFG1_LASX BIT(11) +#define LOONGSON_CFG1_R6FXP BIT(12) +#define LOONGSON_CFG1_R6CRCP BIT(13) +#define LOONGSON_CFG1_R6FPP BIT(14) +#define LOONGSON_CFG1_CNT64 BIT(15) +#define LOONGSON_CFG1_LSLDR0 BIT(16) +#define LOONGSON_CFG1_LSPREF BIT(17) +#define LOONGSON_CFG1_LSPREFX BIT(18) +#define LOONGSON_CFG1_LSSYNCI BIT(19) +#define LOONGSON_CFG1_LSUCA BIT(20) +#define LOONGSON_CFG1_LLSYNC BIT(21) +#define LOONGSON_CFG1_TGTSYNC BIT(22) +#define LOONGSON_CFG1_LLEXC BIT(23) +#define LOONGSON_CFG1_SCRAND BIT(24) +#define LOONGSON_CFG1_MUALP BIT(25) +#define LOONGSON_CFG1_KMUALEN BIT(26) +#define LOONGSON_CFG1_ITLBT BIT(27) +#define LOONGSON_CFG1_LSUPERF BIT(28) +#define LOONGSON_CFG1_SFBP BIT(29) +#define LOONGSON_CFG1_CDMAP BIT(30) + +#define LOONGSON_CFG2 0x2 +#define LOONGSON_CFG2_LEXT1 BIT(0) +#define LOONGSON_CFG2_LEXT2 BIT(1) +#define LOONGSON_CFG2_LEXT3 BIT(2) +#define LOONGSON_CFG2_LSPW BIT(3) +#define LOONGSON_CFG2_LBT1 BIT(4) +#define LOONGSON_CFG2_LBT2 BIT(5) +#define LOONGSON_CFG2_LBT3 BIT(6) +#define LOONGSON_CFG2_LBTMMU BIT(7) +#define LOONGSON_CFG2_LPMP BIT(8) +#define LOONGSON_CFG2_LPMPREV GENMASK(11, 9) +#define LOONGSON_CFG2_LAMO BIT(12) +#define LOONGSON_CFG2_LPIXU BIT(13) +#define LOONGSON_CFG2_LPIXUN BIT(14) +#define LOONGSON_CFG2_LZVP BIT(15) +#define LOONGSON_CFG2_LZVREV GENMASK(18, 16) +#define LOONGSON_CFG2_LGFTP BIT(19) +#define LOONGSON_CFG2_LGFTPREV GENMASK(22, 20) +#define LOONGSON_CFG2_LLFTP BIT(23) +#define LOONGSON_CFG2_LLFTPREV GENMASK(26, 24) +#define LOONGSON_CFG2_LCSRP BIT(27) +#define LOONGSON_CFG2_LDISBLIKELY BIT(28) + +#define LOONGSON_CFG3 0x3 +#define LOONGSON_CFG3_LCAMP BIT(0) +#define LOONGSON_CFG3_LCAMREV GENMASK(3, 1) +#define LOONGSON_CFG3_LCAMNUM GENMASK(11, 4) +#define LOONGSON_CFG3_LCAMKW GENMASK(19, 12) +#define LOONGSON_CFG3_LCAMVW GENMASK(27, 20) + +#define LOONGSON_CFG4 0x4 +#define LOONGSON_CFG4_CCFREQ GENMASK(31, 0) + +#define LOONGSON_CFG5 0x5 +#define LOONGSON_CFG5_CFM GENMASK(15, 0) +#define LOONGSON_CFG5_CFD GENMASK(31, 16) + +#define LOONGSON_CFG6 0x6 + +#define LOONGSON_CFG7 0x7 +#define LOONGSON_CFG7_GCCAEQRP BIT(0) +#define LOONGSON_CFG7_UCAWINP BIT(1) + +static inline bool cpu_has_csr(void) +{ + if (cpu_has_cfg()) + return (read_cpucfg(LOONGSON_CFG2) & LOONGSON_CFG2_LCSRP); + + return false; +} + +static inline u32 csr_readl(u32 reg) +{ + u32 __res; + + /* RDCSR reg, val */ + __asm__ __volatile__( + "parse_r __res,%0\n\t" + "parse_r reg,%1\n\t" + ".insn \n\t" + ".word (0xc8000118 | (reg << 21) | (__res << 11))\n\t" + :"=r"(__res) + :"r"(reg) + : + ); + return __res; +} + +static inline u64 csr_readq(u32 reg) +{ + u64 __res; + + /* DWRCSR reg, val */ + __asm__ __volatile__( + "parse_r __res,%0\n\t" + "parse_r reg,%1\n\t" + ".insn \n\t" + ".word (0xc8020118 | (reg << 21) | (__res << 11))\n\t" + :"=r"(__res) + :"r"(reg) + : + ); + return __res; +} + +static inline void csr_writel(u32 val, u32 reg) +{ + /* WRCSR reg, val */ + __asm__ __volatile__( + "parse_r reg,%0\n\t" + "parse_r val,%1\n\t" + ".insn \n\t" + ".word (0xc8010118 | (reg << 21) | (val << 11))\n\t" + : + :"r"(reg),"r"(val) + : + ); +} + +static inline void csr_writeq(u64 val, u32 reg) +{ + /* DWRCSR reg, val */ + __asm__ __volatile__( + "parse_r reg,%0\n\t" + "parse_r val,%1\n\t" + ".insn \n\t" + ".word (0xc8030118 | (reg << 21) | (val << 11))\n\t" + : + :"r"(reg),"r"(val) + : + ); +} + +/* Public CSR Register can also be accessed with regular addresses */ +#define CSR_PUBLIC_MMIO_BASE 0x1fe00000 + +#define MMIO_CSR(x) (void *)TO_UNCAC(CSR_PUBLIC_MMIO_BASE + x) + +#define LOONGSON_CSR_FEATURES 0x8 +#define LOONGSON_CSRF_TEMP BIT(0) +#define LOONGSON_CSRF_NODECNT BIT(1) +#define LOONGSON_CSRF_MSI BIT(2) +#define LOONGSON_CSRF_EXTIOI BIT(3) +#define LOONGSON_CSRF_IPI BIT(4) +#define LOONGSON_CSRF_FREQ BIT(5) + +#define LOONGSON_CSR_VENDOR 0x10 /* Vendor name string, should be "Loongson" */ +#define LOONGSON_CSR_CPUNAME 0x20 /* Processor name string */ +#define LOONGSON_CSR_NODECNT 0x408 +#define LOONGSON_CSR_CPUTEMP 0x428 + +/* PerCore CSR, only accessable by local cores */ +#define LOONGSON_CSR_IPI_STATUS 0x1000 +#define LOONGSON_CSR_IPI_EN 0x1004 +#define LOONGSON_CSR_IPI_SET 0x1008 +#define LOONGSON_CSR_IPI_CLEAR 0x100c +#define LOONGSON_CSR_IPI_SEND 0x1040 +#define CSR_IPI_SEND_IP_SHIFT 0 +#define CSR_IPI_SEND_CPU_SHIFT 16 +#define CSR_IPI_SEND_BLOCK BIT(31) + +static inline u64 drdtime(void) +{ + int rID = 0; + u64 val = 0; + + __asm__ __volatile__( + "parse_r rID,%0\n\t" + "parse_r val,%1\n\t" + ".insn \n\t" + ".word (0xc8090118 | (rID << 21) | (val << 11))\n\t" + :"=r"(rID),"=r"(val) + : + ); + return val; +} + +#endif diff --git a/arch/mips/include/asm/mach-loongson64/mmzone.h b/arch/mips/include/asm/mach-loongson64/mmzone.h index 62073d60739f..3a25dbd3b3e9 100644 --- a/arch/mips/include/asm/mach-loongson64/mmzone.h +++ b/arch/mips/include/asm/mach-loongson64/mmzone.h @@ -6,8 +6,8 @@ * Huacai Chen, chenhc@lemote.com * Xiaofu Meng, Shuangshuang Zhang */ -#ifndef _ASM_MACH_MMZONE_H -#define _ASM_MACH_MMZONE_H +#ifndef _ASM_MACH_LOONGSON64_MMZONE_H +#define _ASM_MACH_LOONGSON64_MMZONE_H #include <boot_param.h> #define NODE_ADDRSPACE_SHIFT 44 @@ -19,30 +19,9 @@ #define pa_to_nid(addr) (((addr) & 0xf00000000000) >> NODE_ADDRSPACE_SHIFT) #define nid_to_addrbase(nid) ((nid) << NODE_ADDRSPACE_SHIFT) -#define LEVELS_PER_SLICE 128 +extern struct pglist_data *__node_data[]; -struct slice_data { - unsigned long irq_enable_mask[2]; - int level_to_irq[LEVELS_PER_SLICE]; -}; - -struct hub_data { - cpumask_t h_cpus; - unsigned long slice_map; - unsigned long irq_alloc_mask[2]; - struct slice_data slice[2]; -}; - -struct node_data { - struct pglist_data pglist; - struct hub_data hub; - cpumask_t cpumask; -}; - -extern struct node_data *__node_data[]; - -#define NODE_DATA(n) (&__node_data[(n)]->pglist) -#define hub_data(n) (&__node_data[(n)]->hub) +#define NODE_DATA(n) (__node_data[n]) extern void setup_zero_pages(void); extern void __init prom_init_numa_memory(void); diff --git a/arch/mips/include/asm/mach-loongson64/pci.h b/arch/mips/include/asm/mach-loongson64/pci.h index 97f807fb2117..8b59d64a23e8 100644 --- a/arch/mips/include/asm/mach-loongson64/pci.h +++ b/arch/mips/include/asm/mach-loongson64/pci.h @@ -12,39 +12,8 @@ extern struct pci_ops loongson_pci_ops; /* this is an offset from mips_io_port_base */ #define LOONGSON_PCI_IO_START 0x00004000UL -#ifdef CONFIG_CPU_SUPPORTS_ADDRWINCFG - -/* - * we use address window2 to map cpu address space to pci space - * window2: cpu [1G, 2G] -> pci [1G, 2G] - * why not use window 0 & 1? because they are used by cpu when booting. - * window0: cpu [0, 256M] -> ddr [0, 256M] - * window1: cpu [256M, 512M] -> pci [256M, 512M] - */ - -/* the smallest LOONGSON_CPU_MEM_SRC can be 512M */ -#define LOONGSON_CPU_MEM_SRC 0x40000000ul /* 1G */ -#define LOONGSON_PCI_MEM_DST LOONGSON_CPU_MEM_SRC - -#define LOONGSON_PCI_MEM_START LOONGSON_PCI_MEM_DST -#define LOONGSON_PCI_MEM_END (0x80000000ul-1) /* 2G */ - -#define MMAP_CPUTOPCI_SIZE (LOONGSON_PCI_MEM_END - \ - LOONGSON_PCI_MEM_START + 1) - -#else /* loongson2f/32bit & loongson2e */ - -/* this pci memory space is mapped by pcimap in pci.c */ -#ifdef CONFIG_CPU_LOONGSON3 #define LOONGSON_PCI_MEM_START 0x40000000UL #define LOONGSON_PCI_MEM_END 0x7effffffUL -#else -#define LOONGSON_PCI_MEM_START LOONGSON_PCILO1_BASE -#define LOONGSON_PCI_MEM_END (LOONGSON_PCILO1_BASE + 0x04000000 * 2) -#endif -/* this is an offset from mips_io_port_base */ -#define LOONGSON_PCI_IO_START 0x00004000UL -#endif /* !CONFIG_CPU_SUPPORTS_ADDRWINCFG */ #endif /* !__ASM_MACH_LOONGSON64_PCI_H_ */ diff --git a/arch/mips/include/asm/mach-loongson64/topology.h b/arch/mips/include/asm/mach-loongson64/topology.h index 7ff819ab308a..3414a1fd1783 100644 --- a/arch/mips/include/asm/mach-loongson64/topology.h +++ b/arch/mips/include/asm/mach-loongson64/topology.h @@ -5,7 +5,9 @@ #ifdef CONFIG_NUMA #define cpu_to_node(cpu) (cpu_logical_map(cpu) >> 2) -#define cpumask_of_node(node) (&__node_data[(node)]->cpumask) + +extern cpumask_t __node_cpumask[]; +#define cpumask_of_node(node) (&__node_cpumask[node]) struct pci_bus; extern int pcibus_to_node(struct pci_bus *); diff --git a/arch/mips/include/asm/mipsregs.h b/arch/mips/include/asm/mipsregs.h index bdbdc19a2b8f..0d5a30988697 100644 --- a/arch/mips/include/asm/mipsregs.h +++ b/arch/mips/include/asm/mipsregs.h @@ -689,6 +689,9 @@ #define MIPS_CONF7_IAR (_ULCAST_(1) << 10) #define MIPS_CONF7_AR (_ULCAST_(1) << 16) +/* Ingenic HPTLB off bits */ +#define XBURST_PAGECTRL_HPTLB_DIS 0xa9000000 + /* Ingenic Config7 bits */ #define MIPS_CONF7_BTB_LOOP_EN (_ULCAST_(1) << 4) @@ -1971,6 +1974,9 @@ do { \ #define read_c0_brcm_sleepcount() __read_32bit_c0_register($22, 7) #define write_c0_brcm_sleepcount(val) __write_32bit_c0_register($22, 7, val) +/* Ingenic page ctrl register */ +#define write_c0_page_ctrl(val) __write_32bit_c0_register($5, 4, val) + /* * Macros to access the guest system control coprocessor */ diff --git a/arch/mips/include/asm/module.h b/arch/mips/include/asm/module.h index ed70994fbbec..9846047b3d3d 100644 --- a/arch/mips/include/asm/module.h +++ b/arch/mips/include/asm/module.h @@ -119,12 +119,12 @@ search_module_dbetables(unsigned long addr) #define MODULE_PROC_FAMILY "RM7000 " #elif defined CONFIG_CPU_SB1 #define MODULE_PROC_FAMILY "SB1 " -#elif defined CONFIG_CPU_LOONGSON1 -#define MODULE_PROC_FAMILY "LOONGSON1 " -#elif defined CONFIG_CPU_LOONGSON2 -#define MODULE_PROC_FAMILY "LOONGSON2 " -#elif defined CONFIG_CPU_LOONGSON3 -#define MODULE_PROC_FAMILY "LOONGSON3 " +#elif defined CONFIG_CPU_LOONGSON32 +#define MODULE_PROC_FAMILY "LOONGSON32 " +#elif defined CONFIG_CPU_LOONGSON2EF +#define MODULE_PROC_FAMILY "LOONGSON2EF " +#elif defined CONFIG_CPU_LOONGSON64 +#define MODULE_PROC_FAMILY "LOONGSON64 " #elif defined CONFIG_CPU_CAVIUM_OCTEON #define MODULE_PROC_FAMILY "OCTEON " #elif defined CONFIG_CPU_XLR diff --git a/arch/mips/include/asm/pci/bridge.h b/arch/mips/include/asm/pci/bridge.h index a92cd30b48c9..3bc630ff9ad4 100644 --- a/arch/mips/include/asm/pci/bridge.h +++ b/arch/mips/include/asm/pci/bridge.h @@ -807,6 +807,7 @@ struct bridge_controller { unsigned long intr_addr; struct irq_domain *domain; unsigned int pci_int[8]; + u32 ioc3_sid[8]; nasid_t nasid; }; diff --git a/arch/mips/include/asm/pgalloc.h b/arch/mips/include/asm/pgalloc.h index 166842337eb2..fa77cb71f303 100644 --- a/arch/mips/include/asm/pgalloc.h +++ b/arch/mips/include/asm/pgalloc.h @@ -96,9 +96,9 @@ static inline void pud_free(struct mm_struct *mm, pud_t *pud) free_pages((unsigned long)pud, PUD_ORDER); } -static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *pud) +static inline void p4d_populate(struct mm_struct *mm, p4d_t *p4d, pud_t *pud) { - set_pgd(pgd, __pgd((unsigned long)pud)); + set_p4d(p4d, __p4d((unsigned long)pud)); } #define __pud_free_tlb(tlb, x, addr) pud_free((tlb)->mm, x) diff --git a/arch/mips/include/asm/pgtable-32.h b/arch/mips/include/asm/pgtable-32.h index ba967148b016..1945c8970141 100644 --- a/arch/mips/include/asm/pgtable-32.h +++ b/arch/mips/include/asm/pgtable-32.h @@ -16,7 +16,6 @@ #include <asm/cachectl.h> #include <asm/fixmap.h> -#define __ARCH_USE_5LEVEL_HACK #include <asm-generic/pgtable-nopmd.h> #ifdef CONFIG_HIGHMEM @@ -196,14 +195,11 @@ static inline pte_t pfn_pte(unsigned long pfn, pgprot_t prot) #define pte_page(x) pfn_to_page(pte_pfn(x)) -#define __pgd_offset(address) pgd_index(address) -#define __pud_offset(address) (((address) >> PUD_SHIFT) & (PTRS_PER_PUD-1)) -#define __pmd_offset(address) (((address) >> PMD_SHIFT) & (PTRS_PER_PMD-1)) - /* to find an entry in a kernel page-table-directory */ #define pgd_offset_k(address) pgd_offset(&init_mm, address) #define pgd_index(address) (((address) >> PGDIR_SHIFT) & (PTRS_PER_PGD-1)) +#define pud_index(address) (((address) >> PUD_SHIFT) & (PTRS_PER_PUD-1)) #define pmd_index(address) (((address) >> PMD_SHIFT) & (PTRS_PER_PMD-1)) /* to find an entry in a page-table-directory */ diff --git a/arch/mips/include/asm/pgtable-64.h b/arch/mips/include/asm/pgtable-64.h index 93a9dce31f25..f92716cfa4f4 100644 --- a/arch/mips/include/asm/pgtable-64.h +++ b/arch/mips/include/asm/pgtable-64.h @@ -17,11 +17,12 @@ #include <asm/cachectl.h> #include <asm/fixmap.h> -#define __ARCH_USE_5LEVEL_HACK -#if defined(CONFIG_PAGE_SIZE_64KB) && !defined(CONFIG_MIPS_VA_BITS_48) +#if CONFIG_PGTABLE_LEVELS == 2 #include <asm-generic/pgtable-nopmd.h> -#elif !(defined(CONFIG_PAGE_SIZE_4KB) && defined(CONFIG_MIPS_VA_BITS_48)) +#elif CONFIG_PGTABLE_LEVELS == 3 #include <asm-generic/pgtable-nopud.h> +#else +#include <asm-generic/pgtable-nop4d.h> #endif /* @@ -186,44 +187,49 @@ extern pud_t invalid_pud_table[PTRS_PER_PUD]; /* * Empty pgd entries point to the invalid_pud_table. */ -static inline int pgd_none(pgd_t pgd) +static inline int p4d_none(p4d_t p4d) { - return pgd_val(pgd) == (unsigned long)invalid_pud_table; + return p4d_val(p4d) == (unsigned long)invalid_pud_table; } -static inline int pgd_bad(pgd_t pgd) +static inline int p4d_bad(p4d_t p4d) { - if (unlikely(pgd_val(pgd) & ~PAGE_MASK)) + if (unlikely(p4d_val(p4d) & ~PAGE_MASK)) return 1; return 0; } -static inline int pgd_present(pgd_t pgd) +static inline int p4d_present(p4d_t p4d) { - return pgd_val(pgd) != (unsigned long)invalid_pud_table; + return p4d_val(p4d) != (unsigned long)invalid_pud_table; } -static inline void pgd_clear(pgd_t *pgdp) +static inline void p4d_clear(p4d_t *p4dp) { - pgd_val(*pgdp) = (unsigned long)invalid_pud_table; + p4d_val(*p4dp) = (unsigned long)invalid_pud_table; } #define pud_index(address) (((address) >> PUD_SHIFT) & (PTRS_PER_PUD - 1)) -static inline unsigned long pgd_page_vaddr(pgd_t pgd) +static inline unsigned long p4d_page_vaddr(p4d_t p4d) { - return pgd_val(pgd); + return p4d_val(p4d); } -static inline pud_t *pud_offset(pgd_t *pgd, unsigned long address) +#define p4d_phys(p4d) virt_to_phys((void *)p4d_val(p4d)) +#define p4d_page(p4d) (pfn_to_page(p4d_phys(p4d) >> PAGE_SHIFT)) + +#define p4d_index(address) (((address) >> P4D_SHIFT) & (PTRS_PER_P4D - 1)) + +static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address) { - return (pud_t *)pgd_page_vaddr(*pgd) + pud_index(address); + return (pud_t *)p4d_page_vaddr(*p4d) + pud_index(address); } -static inline void set_pgd(pgd_t *pgd, pgd_t pgdval) +static inline void set_p4d(p4d_t *p4d, p4d_t p4dval) { - *pgd = pgdval; + *p4d = p4dval; } #endif @@ -314,10 +320,6 @@ static inline void pud_clear(pud_t *pudp) #define pfn_pmd(pfn, prot) __pmd(((pfn) << _PFN_SHIFT) | pgprot_val(prot)) #endif -#define __pgd_offset(address) pgd_index(address) -#define __pud_offset(address) (((address) >> PUD_SHIFT) & (PTRS_PER_PUD-1)) -#define __pmd_offset(address) pmd_index(address) - /* to find an entry in a kernel page-table-directory */ #define pgd_offset_k(address) pgd_offset(&init_mm, address) diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h index f85bd5b15f51..91b89aab1787 100644 --- a/arch/mips/include/asm/pgtable.h +++ b/arch/mips/include/asm/pgtable.h @@ -644,17 +644,6 @@ static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, #include <asm-generic/pgtable.h> /* - * uncached accelerated TLB map for video memory access - */ -#ifdef CONFIG_CPU_SUPPORTS_UNCACHED_ACCELERATED -#define __HAVE_PHYS_MEM_ACCESS_PROT - -struct file; -pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, - unsigned long size, pgprot_t vma_prot); -#endif - -/* * We provide our own get_unmapped area to cope with the virtual aliasing * constraints placed on us by the cache architecture. */ diff --git a/arch/mips/include/asm/pmon.h b/arch/mips/include/asm/pmon.h deleted file mode 100644 index 6ad519189ce2..000000000000 --- a/arch/mips/include/asm/pmon.h +++ /dev/null @@ -1,46 +0,0 @@ -/* - * 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) 2004 by Ralf Baechle - * - * The cpustart method is a PMC-Sierra's function to start the secondary CPU. - * Stock PMON 2000 has the smpfork, semlock and semunlock methods instead. - */ -#ifndef _ASM_PMON_H -#define _ASM_PMON_H - -struct callvectors { - int (*open) (char*, int, int); - int (*close) (int); - int (*read) (int, void*, int); - int (*write) (int, void*, int); - off_t (*lseek) (int, off_t, int); - int (*printf) (const char*, ...); - void (*cacheflush) (void); - char* (*gets) (char*); - union { - int (*smpfork) (unsigned long cp, char *sp); - int (*cpustart) (long, void (*)(void), void *, long); - } _s; - int (*semlock) (int sem); - void (*semunlock) (int sem); -}; - -extern struct callvectors *debug_vectors; - -#define pmon_open(name, flags, mode) debug_vectors->open(name, flage, mode) -#define pmon_close(fd) debug_vectors->close(fd) -#define pmon_read(fd, buf, count) debug_vectors->read(fd, buf, count) -#define pmon_write(fd, buf, count) debug_vectors->write(fd, buf, count) -#define pmon_lseek(fd, off, whence) debug_vectors->lseek(fd, off, whence) -#define pmon_printf(fmt...) debug_vectors->printf(fmt) -#define pmon_cacheflush() debug_vectors->cacheflush() -#define pmon_gets(s) debug_vectors->gets(s) -#define pmon_cpustart(n, f, sp, gp) debug_vectors->_s.cpustart(n, f, sp, gp) -#define pmon_smpfork(cp, sp) debug_vectors->_s.smpfork(cp, sp) -#define pmon_semlock(sem) debug_vectors->semlock(sem) -#define pmon_semunlock(sem) debug_vectors->semunlock(sem) - -#endif /* _ASM_PMON_H */ diff --git a/arch/mips/include/asm/processor.h b/arch/mips/include/asm/processor.h index fba18d4a9190..7619ad319400 100644 --- a/arch/mips/include/asm/processor.h +++ b/arch/mips/include/asm/processor.h @@ -385,7 +385,7 @@ unsigned long get_wchan(struct task_struct *p); #define KSTK_ESP(tsk) (task_pt_regs(tsk)->regs[29]) #define KSTK_STATUS(tsk) (task_pt_regs(tsk)->cp0_status) -#ifdef CONFIG_CPU_LOONGSON3 +#ifdef CONFIG_CPU_LOONGSON64 /* * Loongson-3's SFB (Store-Fill-Buffer) may buffer writes indefinitely when a * tight read loop is executed, because reads take priority over writes & the diff --git a/arch/mips/include/asm/r4kcache.h b/arch/mips/include/asm/r4kcache.h index 7f4a32d3345a..15ab16f99f28 100644 --- a/arch/mips/include/asm/r4kcache.h +++ b/arch/mips/include/asm/r4kcache.h @@ -15,12 +15,14 @@ #include <linux/stringify.h> #include <asm/asm.h> +#include <asm/asm-eva.h> #include <asm/cacheops.h> #include <asm/compiler.h> #include <asm/cpu-features.h> #include <asm/cpu-type.h> #include <asm/mipsmtregs.h> #include <asm/mmzone.h> +#include <asm/unroll.h> #include <linux/uaccess.h> /* for uaccess_kernel() */ extern void (*r4k_blast_dcache)(void); @@ -39,16 +41,19 @@ extern void (*r4k_blast_icache)(void); */ #define INDEX_BASE CKSEG0 -#define cache_op(op,addr) \ +#define _cache_op(insn, op, addr) \ __asm__ __volatile__( \ " .set push \n" \ " .set noreorder \n" \ " .set "MIPS_ISA_ARCH_LEVEL" \n" \ - " cache %0, %1 \n" \ + " " insn("%0", "%1") " \n" \ " .set pop \n" \ : \ : "i" (op), "R" (*(unsigned char *)(addr))) +#define cache_op(op, addr) \ + _cache_op(kernel_cache, op, addr) + static inline void flush_icache_line_indexed(unsigned long addr) { cache_op(Index_Invalidate_I, addr); @@ -67,7 +72,7 @@ static inline void flush_scache_line_indexed(unsigned long addr) static inline void flush_icache_line(unsigned long addr) { switch (boot_cpu_type()) { - case CPU_LOONGSON2: + case CPU_LOONGSON2EF: cache_op(Hit_Invalidate_I_Loongson2, addr); break; @@ -149,7 +154,7 @@ static inline void flush_scache_line(unsigned long addr) static inline int protected_flush_icache_line(unsigned long addr) { switch (boot_cpu_type()) { - case CPU_LOONGSON2: + case CPU_LOONGSON2EF: return protected_cache_op(Hit_Invalidate_I_Loongson2, addr); default: @@ -193,338 +198,10 @@ static inline void invalidate_tcache_page(unsigned long addr) cache_op(Page_Invalidate_T, addr); } -#ifndef CONFIG_CPU_MIPSR6 -#define cache16_unroll32(base,op) \ - __asm__ __volatile__( \ - " .set push \n" \ - " .set noreorder \n" \ - " .set mips3 \n" \ - " cache %1, 0x000(%0); cache %1, 0x010(%0) \n" \ - " cache %1, 0x020(%0); cache %1, 0x030(%0) \n" \ - " cache %1, 0x040(%0); cache %1, 0x050(%0) \n" \ - " cache %1, 0x060(%0); cache %1, 0x070(%0) \n" \ - " cache %1, 0x080(%0); cache %1, 0x090(%0) \n" \ - " cache %1, 0x0a0(%0); cache %1, 0x0b0(%0) \n" \ - " cache %1, 0x0c0(%0); cache %1, 0x0d0(%0) \n" \ - " cache %1, 0x0e0(%0); cache %1, 0x0f0(%0) \n" \ - " cache %1, 0x100(%0); cache %1, 0x110(%0) \n" \ - " cache %1, 0x120(%0); cache %1, 0x130(%0) \n" \ - " cache %1, 0x140(%0); cache %1, 0x150(%0) \n" \ - " cache %1, 0x160(%0); cache %1, 0x170(%0) \n" \ - " cache %1, 0x180(%0); cache %1, 0x190(%0) \n" \ - " cache %1, 0x1a0(%0); cache %1, 0x1b0(%0) \n" \ - " cache %1, 0x1c0(%0); cache %1, 0x1d0(%0) \n" \ - " cache %1, 0x1e0(%0); cache %1, 0x1f0(%0) \n" \ - " .set pop \n" \ - : \ - : "r" (base), \ - "i" (op)); - -#define cache32_unroll32(base,op) \ - __asm__ __volatile__( \ - " .set push \n" \ - " .set noreorder \n" \ - " .set mips3 \n" \ - " cache %1, 0x000(%0); cache %1, 0x020(%0) \n" \ - " cache %1, 0x040(%0); cache %1, 0x060(%0) \n" \ - " cache %1, 0x080(%0); cache %1, 0x0a0(%0) \n" \ - " cache %1, 0x0c0(%0); cache %1, 0x0e0(%0) \n" \ - " cache %1, 0x100(%0); cache %1, 0x120(%0) \n" \ - " cache %1, 0x140(%0); cache %1, 0x160(%0) \n" \ - " cache %1, 0x180(%0); cache %1, 0x1a0(%0) \n" \ - " cache %1, 0x1c0(%0); cache %1, 0x1e0(%0) \n" \ - " cache %1, 0x200(%0); cache %1, 0x220(%0) \n" \ - " cache %1, 0x240(%0); cache %1, 0x260(%0) \n" \ - " cache %1, 0x280(%0); cache %1, 0x2a0(%0) \n" \ - " cache %1, 0x2c0(%0); cache %1, 0x2e0(%0) \n" \ - " cache %1, 0x300(%0); cache %1, 0x320(%0) \n" \ - " cache %1, 0x340(%0); cache %1, 0x360(%0) \n" \ - " cache %1, 0x380(%0); cache %1, 0x3a0(%0) \n" \ - " cache %1, 0x3c0(%0); cache %1, 0x3e0(%0) \n" \ - " .set pop \n" \ - : \ - : "r" (base), \ - "i" (op)); - -#define cache64_unroll32(base,op) \ - __asm__ __volatile__( \ - " .set push \n" \ - " .set noreorder \n" \ - " .set mips3 \n" \ - " cache %1, 0x000(%0); cache %1, 0x040(%0) \n" \ - " cache %1, 0x080(%0); cache %1, 0x0c0(%0) \n" \ - " cache %1, 0x100(%0); cache %1, 0x140(%0) \n" \ - " cache %1, 0x180(%0); cache %1, 0x1c0(%0) \n" \ - " cache %1, 0x200(%0); cache %1, 0x240(%0) \n" \ - " cache %1, 0x280(%0); cache %1, 0x2c0(%0) \n" \ - " cache %1, 0x300(%0); cache %1, 0x340(%0) \n" \ - " cache %1, 0x380(%0); cache %1, 0x3c0(%0) \n" \ - " cache %1, 0x400(%0); cache %1, 0x440(%0) \n" \ - " cache %1, 0x480(%0); cache %1, 0x4c0(%0) \n" \ - " cache %1, 0x500(%0); cache %1, 0x540(%0) \n" \ - " cache %1, 0x580(%0); cache %1, 0x5c0(%0) \n" \ - " cache %1, 0x600(%0); cache %1, 0x640(%0) \n" \ - " cache %1, 0x680(%0); cache %1, 0x6c0(%0) \n" \ - " cache %1, 0x700(%0); cache %1, 0x740(%0) \n" \ - " cache %1, 0x780(%0); cache %1, 0x7c0(%0) \n" \ - " .set pop \n" \ - : \ - : "r" (base), \ - "i" (op)); - -#define cache128_unroll32(base,op) \ - __asm__ __volatile__( \ - " .set push \n" \ - " .set noreorder \n" \ - " .set mips3 \n" \ - " cache %1, 0x000(%0); cache %1, 0x080(%0) \n" \ - " cache %1, 0x100(%0); cache %1, 0x180(%0) \n" \ - " cache %1, 0x200(%0); cache %1, 0x280(%0) \n" \ - " cache %1, 0x300(%0); cache %1, 0x380(%0) \n" \ - " cache %1, 0x400(%0); cache %1, 0x480(%0) \n" \ - " cache %1, 0x500(%0); cache %1, 0x580(%0) \n" \ - " cache %1, 0x600(%0); cache %1, 0x680(%0) \n" \ - " cache %1, 0x700(%0); cache %1, 0x780(%0) \n" \ - " cache %1, 0x800(%0); cache %1, 0x880(%0) \n" \ - " cache %1, 0x900(%0); cache %1, 0x980(%0) \n" \ - " cache %1, 0xa00(%0); cache %1, 0xa80(%0) \n" \ - " cache %1, 0xb00(%0); cache %1, 0xb80(%0) \n" \ - " cache %1, 0xc00(%0); cache %1, 0xc80(%0) \n" \ - " cache %1, 0xd00(%0); cache %1, 0xd80(%0) \n" \ - " cache %1, 0xe00(%0); cache %1, 0xe80(%0) \n" \ - " cache %1, 0xf00(%0); cache %1, 0xf80(%0) \n" \ - " .set pop \n" \ - : \ - : "r" (base), \ - "i" (op)); - -#else -/* - * MIPS R6 changed the cache opcode and moved to a 8-bit offset field. - * This means we now need to increment the base register before we flush - * more cache lines - */ -#define cache16_unroll32(base,op) \ - __asm__ __volatile__( \ - " .set push\n" \ - " .set noreorder\n" \ - " .set mips64r6\n" \ - " .set noat\n" \ - " cache %1, 0x000(%0); cache %1, 0x010(%0)\n" \ - " cache %1, 0x020(%0); cache %1, 0x030(%0)\n" \ - " cache %1, 0x040(%0); cache %1, 0x050(%0)\n" \ - " cache %1, 0x060(%0); cache %1, 0x070(%0)\n" \ - " cache %1, 0x080(%0); cache %1, 0x090(%0)\n" \ - " cache %1, 0x0a0(%0); cache %1, 0x0b0(%0)\n" \ - " cache %1, 0x0c0(%0); cache %1, 0x0d0(%0)\n" \ - " cache %1, 0x0e0(%0); cache %1, 0x0f0(%0)\n" \ - " "__stringify(LONG_ADDIU)" $1, %0, 0x100 \n" \ - " cache %1, 0x000($1); cache %1, 0x010($1)\n" \ - " cache %1, 0x020($1); cache %1, 0x030($1)\n" \ - " cache %1, 0x040($1); cache %1, 0x050($1)\n" \ - " cache %1, 0x060($1); cache %1, 0x070($1)\n" \ - " cache %1, 0x080($1); cache %1, 0x090($1)\n" \ - " cache %1, 0x0a0($1); cache %1, 0x0b0($1)\n" \ - " cache %1, 0x0c0($1); cache %1, 0x0d0($1)\n" \ - " cache %1, 0x0e0($1); cache %1, 0x0f0($1)\n" \ - " .set pop\n" \ - : \ - : "r" (base), \ - "i" (op)); - -#define cache32_unroll32(base,op) \ - __asm__ __volatile__( \ - " .set push\n" \ - " .set noreorder\n" \ - " .set mips64r6\n" \ - " .set noat\n" \ - " cache %1, 0x000(%0); cache %1, 0x020(%0)\n" \ - " cache %1, 0x040(%0); cache %1, 0x060(%0)\n" \ - " cache %1, 0x080(%0); cache %1, 0x0a0(%0)\n" \ - " cache %1, 0x0c0(%0); cache %1, 0x0e0(%0)\n" \ - " "__stringify(LONG_ADDIU)" $1, %0, 0x100 \n" \ - " cache %1, 0x000($1); cache %1, 0x020($1)\n" \ - " cache %1, 0x040($1); cache %1, 0x060($1)\n" \ - " cache %1, 0x080($1); cache %1, 0x0a0($1)\n" \ - " cache %1, 0x0c0($1); cache %1, 0x0e0($1)\n" \ - " "__stringify(LONG_ADDIU)" $1, $1, 0x100 \n" \ - " cache %1, 0x000($1); cache %1, 0x020($1)\n" \ - " cache %1, 0x040($1); cache %1, 0x060($1)\n" \ - " cache %1, 0x080($1); cache %1, 0x0a0($1)\n" \ - " cache %1, 0x0c0($1); cache %1, 0x0e0($1)\n" \ - " "__stringify(LONG_ADDIU)" $1, $1, 0x100\n" \ - " cache %1, 0x000($1); cache %1, 0x020($1)\n" \ - " cache %1, 0x040($1); cache %1, 0x060($1)\n" \ - " cache %1, 0x080($1); cache %1, 0x0a0($1)\n" \ - " cache %1, 0x0c0($1); cache %1, 0x0e0($1)\n" \ - " .set pop\n" \ - : \ - : "r" (base), \ - "i" (op)); - -#define cache64_unroll32(base,op) \ - __asm__ __volatile__( \ - " .set push\n" \ - " .set noreorder\n" \ - " .set mips64r6\n" \ - " .set noat\n" \ - " cache %1, 0x000(%0); cache %1, 0x040(%0)\n" \ - " cache %1, 0x080(%0); cache %1, 0x0c0(%0)\n" \ - " "__stringify(LONG_ADDIU)" $1, %0, 0x100 \n" \ - " cache %1, 0x000($1); cache %1, 0x040($1)\n" \ - " cache %1, 0x080($1); cache %1, 0x0c0($1)\n" \ - " "__stringify(LONG_ADDIU)" $1, $1, 0x100 \n" \ - " cache %1, 0x000($1); cache %1, 0x040($1)\n" \ - " cache %1, 0x080($1); cache %1, 0x0c0($1)\n" \ - " "__stringify(LONG_ADDIU)" $1, $1, 0x100 \n" \ - " cache %1, 0x000($1); cache %1, 0x040($1)\n" \ - " cache %1, 0x080($1); cache %1, 0x0c0($1)\n" \ - " "__stringify(LONG_ADDIU)" $1, $1, 0x100 \n" \ - " cache %1, 0x000($1); cache %1, 0x040($1)\n" \ - " cache %1, 0x080($1); cache %1, 0x0c0($1)\n" \ - " "__stringify(LONG_ADDIU)" $1, $1, 0x100 \n" \ - " cache %1, 0x000($1); cache %1, 0x040($1)\n" \ - " cache %1, 0x080($1); cache %1, 0x0c0($1)\n" \ - " "__stringify(LONG_ADDIU)" $1, $1, 0x100 \n" \ - " cache %1, 0x000($1); cache %1, 0x040($1)\n" \ - " cache %1, 0x080($1); cache %1, 0x0c0($1)\n" \ - " "__stringify(LONG_ADDIU)" $1, $1, 0x100 \n" \ - " cache %1, 0x000($1); cache %1, 0x040($1)\n" \ - " cache %1, 0x080($1); cache %1, 0x0c0($1)\n" \ - " .set pop\n" \ - : \ - : "r" (base), \ - "i" (op)); - -#define cache128_unroll32(base,op) \ - __asm__ __volatile__( \ - " .set push\n" \ - " .set noreorder\n" \ - " .set mips64r6\n" \ - " .set noat\n" \ - " cache %1, 0x000(%0); cache %1, 0x080(%0)\n" \ - " "__stringify(LONG_ADDIU)" $1, %0, 0x100 \n" \ - " cache %1, 0x000($1); cache %1, 0x080($1)\n" \ - " "__stringify(LONG_ADDIU)" $1, $1, 0x100 \n" \ - " cache %1, 0x000($1); cache %1, 0x080($1)\n" \ - " "__stringify(LONG_ADDIU)" $1, $1, 0x100 \n" \ - " cache %1, 0x000($1); cache %1, 0x080($1)\n" \ - " "__stringify(LONG_ADDIU)" $1, $1, 0x100 \n" \ - " cache %1, 0x000($1); cache %1, 0x080($1)\n" \ - " "__stringify(LONG_ADDIU)" $1, $1, 0x100 \n" \ - " cache %1, 0x000($1); cache %1, 0x080($1)\n" \ - " "__stringify(LONG_ADDIU)" $1, $1, 0x100 \n" \ - " cache %1, 0x000($1); cache %1, 0x080($1)\n" \ - " "__stringify(LONG_ADDIU)" $1, $1, 0x100 \n" \ - " cache %1, 0x000($1); cache %1, 0x080($1)\n" \ - " "__stringify(LONG_ADDIU)" $1, $1, 0x100 \n" \ - " cache %1, 0x000($1); cache %1, 0x080($1)\n" \ - " "__stringify(LONG_ADDIU)" $1, $1, 0x100 \n" \ - " cache %1, 0x000($1); cache %1, 0x080($1)\n" \ - " "__stringify(LONG_ADDIU)" $1, $1, 0x100 \n" \ - " cache %1, 0x000($1); cache %1, 0x080($1)\n" \ - " "__stringify(LONG_ADDIU)" $1, $1, 0x100 \n" \ - " cache %1, 0x000($1); cache %1, 0x080($1)\n" \ - " "__stringify(LONG_ADDIU)" $1, $1, 0x100 \n" \ - " cache %1, 0x000($1); cache %1, 0x080($1)\n" \ - " "__stringify(LONG_ADDIU)" $1, $1, 0x100 \n" \ - " cache %1, 0x000($1); cache %1, 0x080($1)\n" \ - " "__stringify(LONG_ADDIU)" $1, $1, 0x100 \n" \ - " cache %1, 0x000($1); cache %1, 0x080($1)\n" \ - " "__stringify(LONG_ADDIU)" $1, $1, 0x100 \n" \ - " cache %1, 0x000($1); cache %1, 0x080($1)\n" \ - " "__stringify(LONG_ADDIU)" $1, $1, 0x100 \n" \ - " cache %1, 0x000($1); cache %1, 0x080($1)\n" \ - " .set pop\n" \ - : \ - : "r" (base), \ - "i" (op)); -#endif /* CONFIG_CPU_MIPSR6 */ - -/* - * Perform the cache operation specified by op using a user mode virtual - * address while in kernel mode. - */ -#define cache16_unroll32_user(base,op) \ - __asm__ __volatile__( \ - " .set push \n" \ - " .set noreorder \n" \ - " .set mips0 \n" \ - " .set eva \n" \ - " cachee %1, 0x000(%0); cachee %1, 0x010(%0) \n" \ - " cachee %1, 0x020(%0); cachee %1, 0x030(%0) \n" \ - " cachee %1, 0x040(%0); cachee %1, 0x050(%0) \n" \ - " cachee %1, 0x060(%0); cachee %1, 0x070(%0) \n" \ - " cachee %1, 0x080(%0); cachee %1, 0x090(%0) \n" \ - " cachee %1, 0x0a0(%0); cachee %1, 0x0b0(%0) \n" \ - " cachee %1, 0x0c0(%0); cachee %1, 0x0d0(%0) \n" \ - " cachee %1, 0x0e0(%0); cachee %1, 0x0f0(%0) \n" \ - " cachee %1, 0x100(%0); cachee %1, 0x110(%0) \n" \ - " cachee %1, 0x120(%0); cachee %1, 0x130(%0) \n" \ - " cachee %1, 0x140(%0); cachee %1, 0x150(%0) \n" \ - " cachee %1, 0x160(%0); cachee %1, 0x170(%0) \n" \ - " cachee %1, 0x180(%0); cachee %1, 0x190(%0) \n" \ - " cachee %1, 0x1a0(%0); cachee %1, 0x1b0(%0) \n" \ - " cachee %1, 0x1c0(%0); cachee %1, 0x1d0(%0) \n" \ - " cachee %1, 0x1e0(%0); cachee %1, 0x1f0(%0) \n" \ - " .set pop \n" \ - : \ - : "r" (base), \ - "i" (op)); - -#define cache32_unroll32_user(base, op) \ - __asm__ __volatile__( \ - " .set push \n" \ - " .set noreorder \n" \ - " .set mips0 \n" \ - " .set eva \n" \ - " cachee %1, 0x000(%0); cachee %1, 0x020(%0) \n" \ - " cachee %1, 0x040(%0); cachee %1, 0x060(%0) \n" \ - " cachee %1, 0x080(%0); cachee %1, 0x0a0(%0) \n" \ - " cachee %1, 0x0c0(%0); cachee %1, 0x0e0(%0) \n" \ - " cachee %1, 0x100(%0); cachee %1, 0x120(%0) \n" \ - " cachee %1, 0x140(%0); cachee %1, 0x160(%0) \n" \ - " cachee %1, 0x180(%0); cachee %1, 0x1a0(%0) \n" \ - " cachee %1, 0x1c0(%0); cachee %1, 0x1e0(%0) \n" \ - " cachee %1, 0x200(%0); cachee %1, 0x220(%0) \n" \ - " cachee %1, 0x240(%0); cachee %1, 0x260(%0) \n" \ - " cachee %1, 0x280(%0); cachee %1, 0x2a0(%0) \n" \ - " cachee %1, 0x2c0(%0); cachee %1, 0x2e0(%0) \n" \ - " cachee %1, 0x300(%0); cachee %1, 0x320(%0) \n" \ - " cachee %1, 0x340(%0); cachee %1, 0x360(%0) \n" \ - " cachee %1, 0x380(%0); cachee %1, 0x3a0(%0) \n" \ - " cachee %1, 0x3c0(%0); cachee %1, 0x3e0(%0) \n" \ - " .set pop \n" \ - : \ - : "r" (base), \ - "i" (op)); - -#define cache64_unroll32_user(base, op) \ - __asm__ __volatile__( \ - " .set push \n" \ - " .set noreorder \n" \ - " .set mips0 \n" \ - " .set eva \n" \ - " cachee %1, 0x000(%0); cachee %1, 0x040(%0) \n" \ - " cachee %1, 0x080(%0); cachee %1, 0x0c0(%0) \n" \ - " cachee %1, 0x100(%0); cachee %1, 0x140(%0) \n" \ - " cachee %1, 0x180(%0); cachee %1, 0x1c0(%0) \n" \ - " cachee %1, 0x200(%0); cachee %1, 0x240(%0) \n" \ - " cachee %1, 0x280(%0); cachee %1, 0x2c0(%0) \n" \ - " cachee %1, 0x300(%0); cachee %1, 0x340(%0) \n" \ - " cachee %1, 0x380(%0); cachee %1, 0x3c0(%0) \n" \ - " cachee %1, 0x400(%0); cachee %1, 0x440(%0) \n" \ - " cachee %1, 0x480(%0); cachee %1, 0x4c0(%0) \n" \ - " cachee %1, 0x500(%0); cachee %1, 0x540(%0) \n" \ - " cachee %1, 0x580(%0); cachee %1, 0x5c0(%0) \n" \ - " cachee %1, 0x600(%0); cachee %1, 0x640(%0) \n" \ - " cachee %1, 0x680(%0); cachee %1, 0x6c0(%0) \n" \ - " cachee %1, 0x700(%0); cachee %1, 0x740(%0) \n" \ - " cachee %1, 0x780(%0); cachee %1, 0x7c0(%0) \n" \ - " .set pop \n" \ - : \ - : "r" (base), \ - "i" (op)); +#define cache_unroll(times, insn, op, addr, lsize) do { \ + int i = 0; \ + unroll(times, _cache_op, insn, op, (addr) + (i++ * (lsize))); \ +} while (0) /* build blast_xxx, blast_xxx_page, blast_xxx_page_indexed */ #define __BUILD_BLAST_CACHE(pfx, desc, indexop, hitop, lsize, extra) \ @@ -539,7 +216,8 @@ static inline void extra##blast_##pfx##cache##lsize(void) \ \ for (ws = 0; ws < ws_end; ws += ws_inc) \ for (addr = start; addr < end; addr += lsize * 32) \ - cache##lsize##_unroll32(addr|ws, indexop); \ + cache_unroll(32, kernel_cache, indexop, \ + addr | ws, lsize); \ } \ \ static inline void extra##blast_##pfx##cache##lsize##_page(unsigned long page) \ @@ -548,7 +226,7 @@ static inline void extra##blast_##pfx##cache##lsize##_page(unsigned long page) \ unsigned long end = page + PAGE_SIZE; \ \ do { \ - cache##lsize##_unroll32(start, hitop); \ + cache_unroll(32, kernel_cache, hitop, start, lsize); \ start += lsize * 32; \ } while (start < end); \ } \ @@ -565,7 +243,8 @@ static inline void extra##blast_##pfx##cache##lsize##_page_indexed(unsigned long \ for (ws = 0; ws < ws_end; ws += ws_inc) \ for (addr = start; addr < end; addr += lsize * 32) \ - cache##lsize##_unroll32(addr|ws, indexop); \ + cache_unroll(32, kernel_cache, indexop, \ + addr | ws, lsize); \ } __BUILD_BLAST_CACHE(d, dcache, Index_Writeback_Inv_D, Hit_Writeback_Inv_D, 16, ) @@ -596,7 +275,7 @@ static inline void blast_##pfx##cache##lsize##_user_page(unsigned long page) \ unsigned long end = page + PAGE_SIZE; \ \ do { \ - cache##lsize##_unroll32_user(start, hitop); \ + cache_unroll(32, user_cache, hitop, start, lsize); \ start += lsize * 32; \ } while (start < end); \ } @@ -688,7 +367,8 @@ static inline void blast_##pfx##cache##lsize##_node(long node) \ \ for (ws = 0; ws < ws_end; ws += ws_inc) \ for (addr = start; addr < end; addr += lsize * 32) \ - cache##lsize##_unroll32(addr|ws, indexop); \ + cache_unroll(32, kernel_cache, indexop, \ + addr | ws, lsize); \ } __BUILD_BLAST_CACHE_NODE(s, scache, Index_Writeback_Inv_SD, Hit_Writeback_Inv_SD, 16) diff --git a/arch/mips/include/asm/sgi/heart.h b/arch/mips/include/asm/sgi/heart.h new file mode 100644 index 000000000000..c423221b4792 --- /dev/null +++ b/arch/mips/include/asm/sgi/heart.h @@ -0,0 +1,272 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * HEART chip definitions + * + * Copyright (C) 2004-2007 Stanislaw Skowronek <skylark@unaligned.org> + * 2009 Johannes Dickgreber <tanzy@gmx.de> + * 2007-2015 Joshua Kinard <kumba@gentoo.org> + */ +#ifndef __ASM_SGI_HEART_H +#define __ASM_SGI_HEART_H + +#include <linux/types.h> +#include <linux/time.h> + +/* + * There are 8 DIMM slots on an IP30 system + * board, which are grouped into four banks + */ +#define HEART_MEMORY_BANKS 4 + +/* HEART can support up to four CPUs */ +#define HEART_MAX_CPUS 4 + +#define HEART_XKPHYS_BASE ((void *)(IO_BASE | 0x000000000ff00000ULL)) + +/** + * struct ip30_heart_regs - struct that maps IP30 HEART registers. + * @mode: HEART_MODE - Purpose Unknown, machine reset called from here. + * @sdram_mode: HEART_SDRAM_MODE - purpose unknown. + * @mem_refresh: HEART_MEM_REF - purpose unknown. + * @mem_req_arb: HEART_MEM_REQ_ARB - purpose unknown. + * @mem_cfg.q: union for 64bit access to HEART_MEMCFG - 4x 64bit registers. + * @mem_cfg.l: union for 32bit access to HEART_MEMCFG - 8x 32bit registers. + * @fc_mode: HEART_FC_MODE - Purpose Unknown, possibly for GFX flow control. + * @fc_timer_limit: HEART_FC_TIMER_LIMIT - purpose unknown. + * @fc_addr: HEART_FC0_ADDR, HEART_FC1_ADDR - purpose unknown. + * @fc_credit_cnt: HEART_FC0_CR_CNT, HEART_FC1_CR_CNT - purpose unknown. + * @fc_timer: HEART_FC0_TIMER, HEART_FC1_TIMER - purpose unknown. + * @status: HEART_STATUS - HEART status information. + * @bus_err_addr: HEART_BERR_ADDR - likely contains addr of recent SIGBUS. + * @bus_err_misc: HEART_BERR_MISC - purpose unknown. + * @mem_err_addr: HEART_MEMERR_ADDR - likely contains addr of recent mem err. + * @mem_err_data: HEART_MEMERR_DATA - purpose unknown. + * @piur_acc_err: HEART_PIUR_ACC_ERR - likely for access err to HEART regs. + * @mlan_clock_div: HEART_MLAN_CLK_DIV - MicroLAN clock divider. + * @mlan_ctrl: HEART_MLAN_CTL - MicroLAN control. + * @__pad0: 0x0f40 bytes of padding -> next HEART register 0x01000. + * @undefined: Undefined/diag register, write to it triggers PIUR_ACC_ERR. + * @__pad1: 0xeff8 bytes of padding -> next HEART register 0x10000. + * @imr: HEART_IMR0 to HEART_IMR3 - per-cpu interrupt mask register. + * @set_isr: HEART_SET_ISR - set interrupt status register. + * @clear_isr: HEART_CLR_ISR - clear interrupt status register. + * @isr: HEART_ISR - interrupt status register (read-only). + * @imsr: HEART_IMSR - purpose unknown. + * @cause: HEART_CAUSE - HEART cause information. + * @__pad2: 0xffb8 bytes of padding -> next HEART register 0x20000. + * @count: HEART_COUNT - 52-bit counter. + * @__pad3: 0xfff8 bytes of padding -> next HEART register 0x30000. + * @compare: HEART_COMPARE - 24-bit compare. + * @__pad4: 0xfff8 bytes of padding -> next HEART register 0x40000. + * @trigger: HEART_TRIGGER - purpose unknown. + * @__pad5: 0xfff8 bytes of padding -> next HEART register 0x50000. + * @cpuid: HEART_PRID - contains CPU ID of CPU currently accessing HEART. + * @__pad6: 0xfff8 bytes of padding -> next HEART register 0x60000. + * @sync: HEART_SYNC - purpose unknown. + * + * HEART is the main system controller ASIC for IP30 system. It incorporates + * a memory controller, interrupt status/cause/set/clear management, basic + * timer with count/compare, and other functionality. For Linux, not all of + * HEART's functions are fully understood. + * + * Implementation note: All HEART registers are 64bits-wide, but the mem_cfg + * register only reports correct values if queried in 32bits. Hence the need + * for a union. Even though mem_cfg.l has 8 array slots, we only ever query + * up to 4 of those. IP30 has 8 DIMM slots arranged into 4 banks, w/ 2 DIMMs + * per bank. Each 32bit read accesses one of these banks. Perhaps HEART was + * designed to address up to 8 banks (16 DIMMs)? We may never know. + */ +struct ip30_heart_regs { /* 0x0ff00000 */ + u64 mode; /* + 0x00000 */ + /* Memory */ + u64 sdram_mode; /* + 0x00008 */ + u64 mem_refresh; /* + 0x00010 */ + u64 mem_req_arb; /* + 0x00018 */ + union { + u64 q[HEART_MEMORY_BANKS]; /* readq() */ + u32 l[HEART_MEMORY_BANKS * 2]; /* readl() */ + } mem_cfg; /* + 0x00020 */ + /* Flow control (gfx?) */ + u64 fc_mode; /* + 0x00040 */ + u64 fc_timer_limit; /* + 0x00048 */ + u64 fc_addr[2]; /* + 0x00050 */ + u64 fc_credit_cnt[2]; /* + 0x00060 */ + u64 fc_timer[2]; /* + 0x00070 */ + /* Status */ + u64 status; /* + 0x00080 */ + /* Bus error */ + u64 bus_err_addr; /* + 0x00088 */ + u64 bus_err_misc; /* + 0x00090 */ + /* Memory error */ + u64 mem_err_addr; /* + 0x00098 */ + u64 mem_err_data; /* + 0x000a0 */ + /* Misc */ + u64 piur_acc_err; /* + 0x000a8 */ + u64 mlan_clock_div; /* + 0x000b0 */ + u64 mlan_ctrl; /* + 0x000b8 */ + u64 __pad0[0x01e8]; /* + 0x000c0 + 0x0f40 */ + /* Undefined */ + u64 undefined; /* + 0x01000 */ + u64 __pad1[0x1dff]; /* + 0x01008 + 0xeff8 */ + /* Interrupts */ + u64 imr[HEART_MAX_CPUS]; /* + 0x10000 */ + u64 set_isr; /* + 0x10020 */ + u64 clear_isr; /* + 0x10028 */ + u64 isr; /* + 0x10030 */ + u64 imsr; /* + 0x10038 */ + u64 cause; /* + 0x10040 */ + u64 __pad2[0x1ff7]; /* + 0x10048 + 0xffb8 */ + /* Timer */ + u64 count; /* + 0x20000 */ + u64 __pad3[0x1fff]; /* + 0x20008 + 0xfff8 */ + u64 compare; /* + 0x30000 */ + u64 __pad4[0x1fff]; /* + 0x30008 + 0xfff8 */ + u64 trigger; /* + 0x40000 */ + u64 __pad5[0x1fff]; /* + 0x40008 + 0xfff8 */ + /* Misc */ + u64 cpuid; /* + 0x50000 */ + u64 __pad6[0x1fff]; /* + 0x50008 + 0xfff8 */ + u64 sync; /* + 0x60000 */ +}; + + +/* For timer-related bits. */ +#define HEART_NS_PER_CYCLE 80 +#define HEART_CYCLES_PER_SEC (NSEC_PER_SEC / HEART_NS_PER_CYCLE) + + +/* + * XXX: Everything below this comment will either go away or be cleaned + * up to fit in better with Linux. A lot of the bit definitions for + * HEART were derived from IRIX's sys/RACER/heart.h header file. + */ + +/* HEART Masks */ +#define HEART_ATK_MASK 0x0007ffffffffffff /* HEART attack mask */ +#define HEART_ACK_ALL_MASK 0xffffffffffffffff /* Ack everything */ +#define HEART_CLR_ALL_MASK 0x0000000000000000 /* Clear all */ +#define HEART_BR_ERR_MASK 0x7ff8000000000000 /* BRIDGE error mask */ +#define HEART_CPU0_ERR_MASK 0x8ff8000000000000 /* CPU0 error mask */ +#define HEART_CPU1_ERR_MASK 0x97f8000000000000 /* CPU1 error mask */ +#define HEART_CPU2_ERR_MASK 0xa7f8000000000000 /* CPU2 error mask */ +#define HEART_CPU3_ERR_MASK 0xc7f8000000000000 /* CPU3 error mask */ +#define HEART_ERR_MASK 0x1ff /* HEART error mask */ +#define HEART_ERR_MASK_START 51 /* HEART error start */ +#define HEART_ERR_MASK_END 63 /* HEART error end */ + +/* Bits in the HEART_MODE register. */ +#define HM_PROC_DISABLE_SHFT 60 +#define HM_PROC_DISABLE_MSK (0xfUL << HM_PROC_DISABLE_SHFT) +#define HM_PROC_DISABLE(x) (0x1UL << (x) + HM_PROC_DISABLE_SHFT) +#define HM_MAX_PSR (0x7UL << 57) +#define HM_MAX_IOSR (0x7UL << 54) +#define HM_MAX_PEND_IOSR (0x7UL << 51) +#define HM_TRIG_SRC_SEL_MSK (0x7UL << 48) +#define HM_TRIG_HEART_EXC (0x0UL << 48) +#define HM_TRIG_REG_BIT (0x1UL << 48) +#define HM_TRIG_SYSCLK (0x2UL << 48) +#define HM_TRIG_MEMCLK_2X (0x3UL << 48) +#define HM_TRIG_MEMCLK (0x4UL << 48) +#define HM_TRIG_IOCLK (0x5UL << 48) +#define HM_PIU_TEST_MODE (0xfUL << 40) +#define HM_GP_FLAG_MSK (0xfUL << 36) +#define HM_GP_FLAG(x) BIT((x) + 36) +#define HM_MAX_PROC_HYST (0xfUL << 32) +#define HM_LLP_WRST_AFTER_RST BIT(28) +#define HM_LLP_LINK_RST BIT(27) +#define HM_LLP_WARM_RST BIT(26) +#define HM_COR_ECC_LCK BIT(25) +#define HM_REDUCED_PWR BIT(24) +#define HM_COLD_RST BIT(23) +#define HM_SW_RST BIT(22) +#define HM_MEM_FORCE_WR BIT(21) +#define HM_DB_ERR_GEN BIT(20) +#define HM_SB_ERR_GEN BIT(19) +#define HM_CACHED_PIO_EN BIT(18) +#define HM_CACHED_PROM_EN BIT(17) +#define HM_PE_SYS_COR_ERE BIT(16) +#define HM_GLOBAL_ECC_EN BIT(15) +#define HM_IO_COH_EN BIT(14) +#define HM_INT_EN BIT(13) +#define HM_DATA_CHK_EN BIT(12) +#define HM_REF_EN BIT(11) +#define HM_BAD_SYSWR_ERE BIT(10) +#define HM_BAD_SYSRD_ERE BIT(9) +#define HM_SYSSTATE_ERE BIT(8) +#define HM_SYSCMD_ERE BIT(7) +#define HM_NCOR_SYS_ERE BIT(6) +#define HM_COR_SYS_ERE BIT(5) +#define HM_DATA_ELMNT_ERE BIT(4) +#define HM_MEM_ADDR_PROC_ERE BIT(3) +#define HM_MEM_ADDR_IO_ERE BIT(2) +#define HM_NCOR_MEM_ERE BIT(1) +#define HM_COR_MEM_ERE BIT(0) + +/* Bits in the HEART_MEM_REF register. */ +#define HEART_MEMREF_REFS(x) ((0xfUL & (x)) << 16) +#define HEART_MEMREF_PERIOD(x) ((0xffffUL & (x))) +#define HEART_MEMREF_REFS_VAL HEART_MEMREF_REFS(8) +#define HEART_MEMREF_PERIOD_VAL HEART_MEMREF_PERIOD(0x4000) +#define HEART_MEMREF_VAL (HEART_MEMREF_REFS_VAL | \ + HEART_MEMREF_PERIOD_VAL) + +/* Bits in the HEART_MEM_REQ_ARB register. */ +#define HEART_MEMARB_IODIS (1 << 20) +#define HEART_MEMARB_MAXPMWRQS (15 << 16) +#define HEART_MEMARB_MAXPMRRQS (15 << 12) +#define HEART_MEMARB_MAXPMRQS (15 << 8) +#define HEART_MEMARB_MAXRRRQS (15 << 4) +#define HEART_MEMARB_MAXGBRRQS (15) + +/* Bits in the HEART_MEMCFG<x> registers. */ +#define HEART_MEMCFG_VALID 0x80000000 /* Bank is valid */ +#define HEART_MEMCFG_DENSITY 0x01c00000 /* Mem density */ +#define HEART_MEMCFG_SIZE_MASK 0x003f0000 /* Mem size mask */ +#define HEART_MEMCFG_ADDR_MASK 0x000001ff /* Base addr mask */ +#define HEART_MEMCFG_SIZE_SHIFT 16 /* Mem size shift */ +#define HEART_MEMCFG_DENSITY_SHIFT 22 /* Density Shift */ +#define HEART_MEMCFG_UNIT_SHIFT 25 /* Unit Shift, 32MB */ + +/* Bits in the HEART_STATUS register */ +#define HEART_STAT_HSTL_SDRV BIT(14) +#define HEART_STAT_FC_CR_OUT(x) BIT((x) + 12) +#define HEART_STAT_DIR_CNNCT BIT(11) +#define HEART_STAT_TRITON BIT(10) +#define HEART_STAT_R4K BIT(9) +#define HEART_STAT_BIG_ENDIAN BIT(8) +#define HEART_STAT_PROC_SHFT 4 +#define HEART_STAT_PROC_MSK (0xfUL << HEART_STAT_PROC_SHFT) +#define HEART_STAT_PROC_ACTIVE(x) (0x1UL << ((x) + HEART_STAT_PROC_SHFT)) +#define HEART_STAT_WIDGET_ID 0xf + +/* Bits in the HEART_CAUSE register */ +#define HC_PE_SYS_COR_ERR_MSK (0xfUL << 60) +#define HC_PE_SYS_COR_ERR(x) BIT((x) + 60) +#define HC_PIOWDB_OFLOW BIT(44) +#define HC_PIORWRB_OFLOW BIT(43) +#define HC_PIUR_ACC_ERR BIT(42) +#define HC_BAD_SYSWR_ERR BIT(41) +#define HC_BAD_SYSRD_ERR BIT(40) +#define HC_SYSSTATE_ERR_MSK (0xfUL << 36) +#define HC_SYSSTATE_ERR(x) BIT((x) + 36) +#define HC_SYSCMD_ERR_MSK (0xfUL << 32) +#define HC_SYSCMD_ERR(x) BIT((x) + 32) +#define HC_NCOR_SYSAD_ERR_MSK (0xfUL << 28) +#define HC_NCOR_SYSAD_ERR(x) BIT((x) + 28) +#define HC_COR_SYSAD_ERR_MSK (0xfUL << 24) +#define HC_COR_SYSAD_ERR(x) BIT((x) + 24) +#define HC_DATA_ELMNT_ERR_MSK (0xfUL << 20) +#define HC_DATA_ELMNT_ERR(x) BIT((x) + 20) +#define HC_WIDGET_ERR BIT(16) +#define HC_MEM_ADDR_ERR_PROC_MSK (0xfUL << 4) +#define HC_MEM_ADDR_ERR_PROC(x) BIT((x) + 4) +#define HC_MEM_ADDR_ERR_IO BIT(2) +#define HC_NCOR_MEM_ERR BIT(1) +#define HC_COR_MEM_ERR BIT(0) + +extern struct ip30_heart_regs __iomem *heart_regs; + +#define heart_read ____raw_readq +#define heart_write ____raw_writeq + +#endif /* __ASM_SGI_HEART_H */ diff --git a/arch/mips/include/asm/sgi/sgi.h b/arch/mips/include/asm/sgi/sgi.h deleted file mode 100644 index b61557151e3f..000000000000 --- a/arch/mips/include/asm/sgi/sgi.h +++ /dev/null @@ -1,48 +0,0 @@ -/* - * 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. - * - * sgi.h: Definitions specific to SGI machines. - * - * Copyright (C) 1996 David S. Miller (dm@sgi.com) - */ -#ifndef _ASM_SGI_SGI_H -#define _ASM_SGI_SGI_H - -/* UP=UniProcessor MP=MultiProcessor(capable) */ -enum sgi_mach { - ip4, /* R2k UP */ - ip5, /* R2k MP */ - ip6, /* R3k UP */ - ip7, /* R3k MP */ - ip9, /* R3k UP */ - ip12, /* R3kA UP, Indigo */ - ip15, /* R3kA MP */ - ip17, /* R4K UP */ - ip19, /* R4K MP */ - ip20, /* R4K UP, Indigo */ - ip21, /* R8k/TFP MP */ - ip22, /* R4x00 UP, Indy, Indigo2 */ - ip25, /* R10k MP */ - ip26, /* R8k/TFP UP, Indigo2 */ - ip27, /* R10k MP, R12k MP, R14k MP, Origin 200/2k, Onyx2 */ - ip28, /* R10k UP, Indigo2 Impact R10k */ - ip30, /* R10k MP, R12k MP, R14k MP, Octane */ - ip32, /* R5k UP, RM5200 UP, RM7k UP, R10k UP, R12k UP, O2 */ - ip35, /* R14k MP, R16k MP, Origin 300/3k, Onyx3, Fuel, Tezro */ -}; - -extern enum sgi_mach sgimach; -extern void sgi_sysinit(void); - -/* Many I/O space registers are byte sized and are contained within - * one byte per word, specifically the MSB, this macro helps out. - */ -#ifdef __MIPSEL__ -#define SGI_MSB(regaddr) (regaddr) -#else -#define SGI_MSB(regaddr) ((regaddr) | 0x3) -#endif - -#endif /* _ASM_SGI_SGI_H */ diff --git a/arch/mips/include/asm/sgialib.h b/arch/mips/include/asm/sgialib.h index 0d9fad5915fe..80f900417f7e 100644 --- a/arch/mips/include/asm/sgialib.h +++ b/arch/mips/include/asm/sgialib.h @@ -15,14 +15,6 @@ #include <asm/sgiarcs.h> extern struct linux_romvec *romvec; -extern int prom_argc; - -extern LONG *_prom_argv, *_prom_envp; - -/* A 32-bit ARC PROM pass arguments and environment as 32-bit pointer. - These macros take care of sign extension. */ -#define prom_argv(index) ((char *) (long) _prom_argv[(index)]) -#define prom_argc(index) ((char *) (long) _prom_argc[(index)]) extern int prom_flags; @@ -47,12 +39,6 @@ extern void prom_meminit(void); /* PROM device tree library routines. */ #define PROM_NULL_COMPONENT ((pcomponent *) 0) -/* Get sibling component of THIS. */ -extern pcomponent *ArcGetPeer(pcomponent *this); - -/* Get child component of THIS. */ -extern pcomponent *ArcGetChild(pcomponent *this); - /* This is called at prom_init time to identify the * ARC architecture we are running on */ @@ -60,22 +46,16 @@ extern void prom_identify_arch(void); /* Environment variable routines. */ extern PCHAR ArcGetEnvironmentVariable(PCHAR name); -extern LONG ArcSetEnvironmentVariable(PCHAR name, PCHAR value); /* ARCS command line parsing. */ -extern void prom_init_cmdline(void); +extern void prom_init_cmdline(int argc, LONG *argv); /* File operations. */ extern LONG ArcRead(ULONG fd, PVOID buf, ULONG num, PULONG cnt); extern LONG ArcWrite(ULONG fd, PVOID buf, ULONG num, PULONG cnt); /* Misc. routines. */ -extern VOID ArcHalt(VOID) __noreturn; -extern VOID ArcPowerDown(VOID) __noreturn; -extern VOID ArcRestart(VOID) __noreturn; -extern VOID ArcReboot(VOID) __noreturn; extern VOID ArcEnterInteractiveMode(VOID) __noreturn; -extern VOID ArcFlushAllCaches(VOID); extern DISPLAY_STATUS *ArcGetDisplayStatus(ULONG FileID); #endif /* _ASM_SGIALIB_H */ diff --git a/arch/mips/include/asm/sgiarcs.h b/arch/mips/include/asm/sgiarcs.h index 105a9479ac5f..e1512cab180b 100644 --- a/arch/mips/include/asm/sgiarcs.h +++ b/arch/mips/include/asm/sgiarcs.h @@ -12,6 +12,8 @@ #ifndef _ASM_SGIARCS_H #define _ASM_SGIARCS_H +#include <linux/kernel.h> + #include <asm/types.h> #include <asm/fw/arc/types.h> @@ -368,110 +370,65 @@ struct linux_smonblock { #if defined(CONFIG_64BIT) && defined(CONFIG_FW_ARC32) -#define __arc_clobbers \ - "$2", "$3" /* ... */, "$8", "$9", "$10", "$11", \ - "$12", "$13", "$14", "$15", "$16", "$24", "$25", "$31" +extern long call_o32(long vec, void *stack, ...); + +extern u64 o32_stk[4096]; +#define O32_STK (&o32_stk[ARRAY_SIZE(o32_stk)]) #define ARC_CALL0(dest) \ ({ long __res; \ long __vec = (long) romvec->dest; \ - __asm__ __volatile__( \ - "dsubu\t$29, 32\n\t" \ - "jalr\t%1\n\t" \ - "daddu\t$29, 32\n\t" \ - "move\t%0, $2" \ - : "=r" (__res), "=r" (__vec) \ - : "1" (__vec) \ - : __arc_clobbers, "$4", "$5", "$6", "$7"); \ - (unsigned long) __res; \ + __res = call_o32(__vec, O32_STK); \ + __res; \ }) #define ARC_CALL1(dest, a1) \ ({ long __res; \ - register signed int __a1 __asm__("$4") = (int) (long) (a1); \ + int __a1 = (int) (long) (a1); \ long __vec = (long) romvec->dest; \ - __asm__ __volatile__( \ - "dsubu\t$29, 32\n\t" \ - "jalr\t%1\n\t" \ - "daddu\t$29, 32\n\t" \ - "move\t%0, $2" \ - : "=r" (__res), "=r" (__vec) \ - : "1" (__vec), "r" (__a1) \ - : __arc_clobbers, "$5", "$6", "$7"); \ - (unsigned long) __res; \ + __res = call_o32(__vec, O32_STK, __a1); \ + __res; \ }) #define ARC_CALL2(dest, a1, a2) \ ({ long __res; \ - register signed int __a1 __asm__("$4") = (int) (long) (a1); \ - register signed int __a2 __asm__("$5") = (int) (long) (a2); \ + int __a1 = (int) (long) (a1); \ + int __a2 = (int) (long) (a2); \ long __vec = (long) romvec->dest; \ - __asm__ __volatile__( \ - "dsubu\t$29, 32\n\t" \ - "jalr\t%1\n\t" \ - "daddu\t$29, 32\n\t" \ - "move\t%0, $2" \ - : "=r" (__res), "=r" (__vec) \ - : "1" (__vec), "r" (__a1), "r" (__a2) \ - : __arc_clobbers, "$6", "$7"); \ + __res = call_o32(__vec, O32_STK, __a1, __a2); \ __res; \ }) #define ARC_CALL3(dest, a1, a2, a3) \ ({ long __res; \ - register signed int __a1 __asm__("$4") = (int) (long) (a1); \ - register signed int __a2 __asm__("$5") = (int) (long) (a2); \ - register signed int __a3 __asm__("$6") = (int) (long) (a3); \ + int __a1 = (int) (long) (a1); \ + int __a2 = (int) (long) (a2); \ + int __a3 = (int) (long) (a3); \ long __vec = (long) romvec->dest; \ - __asm__ __volatile__( \ - "dsubu\t$29, 32\n\t" \ - "jalr\t%1\n\t" \ - "daddu\t$29, 32\n\t" \ - "move\t%0, $2" \ - : "=r" (__res), "=r" (__vec) \ - : "1" (__vec), "r" (__a1), "r" (__a2), "r" (__a3) \ - : __arc_clobbers, "$7"); \ + __res = call_o32(__vec, O32_STK, __a1, __a2, __a3); \ __res; \ }) #define ARC_CALL4(dest, a1, a2, a3, a4) \ ({ long __res; \ - register signed int __a1 __asm__("$4") = (int) (long) (a1); \ - register signed int __a2 __asm__("$5") = (int) (long) (a2); \ - register signed int __a3 __asm__("$6") = (int) (long) (a3); \ - register signed int __a4 __asm__("$7") = (int) (long) (a4); \ + int __a1 = (int) (long) (a1); \ + int __a2 = (int) (long) (a2); \ + int __a3 = (int) (long) (a3); \ + int __a4 = (int) (long) (a4); \ long __vec = (long) romvec->dest; \ - __asm__ __volatile__( \ - "dsubu\t$29, 32\n\t" \ - "jalr\t%1\n\t" \ - "daddu\t$29, 32\n\t" \ - "move\t%0, $2" \ - : "=r" (__res), "=r" (__vec) \ - : "1" (__vec), "r" (__a1), "r" (__a2), "r" (__a3), \ - "r" (__a4) \ - : __arc_clobbers); \ + __res = call_o32(__vec, O32_STK, __a1, __a2, __a3, __a4); \ __res; \ }) -#define ARC_CALL5(dest, a1, a2, a3, a4, a5) \ +#define ARC_CALL5(dest, a1, a2, a3, a4, a5) \ ({ long __res; \ - register signed int __a1 __asm__("$4") = (int) (long) (a1); \ - register signed int __a2 __asm__("$5") = (int) (long) (a2); \ - register signed int __a3 __asm__("$6") = (int) (long) (a3); \ - register signed int __a4 __asm__("$7") = (int) (long) (a4); \ - register signed int __a5 = (int) (long) (a5); \ + int __a1 = (int) (long) (a1); \ + int __a2 = (int) (long) (a2); \ + int __a3 = (int) (long) (a3); \ + int __a4 = (int) (long) (a4); \ + int __a5 = (int) (long) (a5); \ long __vec = (long) romvec->dest; \ - __asm__ __volatile__( \ - "dsubu\t$29, 32\n\t" \ - "sw\t%7, 16($29)\n\t" \ - "jalr\t%1\n\t" \ - "daddu\t$29, 32\n\t" \ - "move\t%0, $2" \ - : "=r" (__res), "=r" (__vec) \ - : "1" (__vec), \ - "r" (__a1), "r" (__a2), "r" (__a3), "r" (__a4), \ - "r" (__a5) \ - : __arc_clobbers); \ + __res = call_o32(__vec, O32_STK, __a1, __a2, __a3, __a4, __a5); \ __res; \ }) diff --git a/arch/mips/include/asm/sn/agent.h b/arch/mips/include/asm/sn/agent.h index e33d09293019..7e9b3271737a 100644 --- a/arch/mips/include/asm/sn/agent.h +++ b/arch/mips/include/asm/sn/agent.h @@ -26,7 +26,7 @@ #if defined(CONFIG_SGI_IP27) #define HUB_NIC_ADDR(_cpuid) \ - REMOTE_HUB_ADDR(COMPACT_TO_NASID_NODEID(cpu_to_node(_cpuid)), \ + REMOTE_HUB_ADDR(cpu_to_node(_cpuid), \ MD_MLAN_CTL) #endif diff --git a/arch/mips/include/asm/sn/arch.h b/arch/mips/include/asm/sn/arch.h index 3f1fb1454749..f7d3273d9599 100644 --- a/arch/mips/include/asm/sn/arch.h +++ b/arch/mips/include/asm/sn/arch.h @@ -19,44 +19,13 @@ #define cputonasid(cpu) (sn_cpu_info[(cpu)].p_nasid) #define cputoslice(cpu) (sn_cpu_info[(cpu)].p_slice) -#define makespnum(_nasid, _slice) \ - (((_nasid) << CPUS_PER_NODE_SHFT) | (_slice)) #define INVALID_NASID (nasid_t)-1 -#define INVALID_CNODEID (cnodeid_t)-1 #define INVALID_PNODEID (pnodeid_t)-1 #define INVALID_MODULE (moduleid_t)-1 #define INVALID_PARTID (partid_t)-1 extern nasid_t get_nasid(void); -extern cnodeid_t get_cpu_cnode(cpuid_t); extern int get_cpu_slice(cpuid_t); -/* - * NO ONE should access these arrays directly. The only reason we refer to - * them here is to avoid the procedure call that would be required in the - * macros below. (Really want private data members here :-) - */ -extern cnodeid_t nasid_to_compact_node[MAX_NASIDS]; -extern nasid_t compact_to_nasid_node[MAX_COMPACT_NODES]; - -/* - * These macros are used by various parts of the kernel to convert - * between the three different kinds of node numbering. At least some - * of them may change to procedure calls in the future, but the macros - * will continue to work. Don't use the arrays above directly. - */ - -#define NASID_TO_REGION(nnode) \ - ((nnode) >> \ - (is_fine_dirmode() ? NASID_TO_FINEREG_SHFT : NASID_TO_COARSEREG_SHFT)) - -extern cnodeid_t nasid_to_compact_node[MAX_NASIDS]; -extern nasid_t compact_to_nasid_node[MAX_COMPACT_NODES]; -extern cnodeid_t cpuid_to_compact_node[MAXCPUS]; - -#define NASID_TO_COMPACT_NODEID(nnode) (nasid_to_compact_node[nnode]) -#define COMPACT_TO_NASID_NODEID(cnode) (compact_to_nasid_node[cnode]) -#define CPUID_TO_COMPACT_NODEID(cpu) (cpuid_to_compact_node[(cpu)]) - #endif /* _ASM_SN_ARCH_H */ diff --git a/arch/mips/include/asm/sn/gda.h b/arch/mips/include/asm/sn/gda.h index 85fa1b5f639d..d52f81620661 100644 --- a/arch/mips/include/asm/sn/gda.h +++ b/arch/mips/include/asm/sn/gda.h @@ -60,9 +60,7 @@ typedef struct gda { /* Pointer to a mask of nodes with copies * of the kernel. */ char g_padding[56]; /* pad out to 128 bytes */ - nasid_t g_nasidtable[MAX_COMPACT_NODES]; /* NASID of each node, - * indexed by cnodeid. - */ + nasid_t g_nasidtable[MAX_NUMNODES]; /* NASID of each node */ } gda_t; #define GDA ((gda_t*) GDA_ADDR(get_nasid())) diff --git a/arch/mips/include/asm/sn/hub.h b/arch/mips/include/asm/sn/hub.h index 338f7eed74f1..45878fbefbae 100644 --- a/arch/mips/include/asm/sn/hub.h +++ b/arch/mips/include/asm/sn/hub.h @@ -10,8 +10,8 @@ #include <asm/xtalk/xtalk.h> /* ip27-hubio.c */ -extern unsigned long hub_pio_map(cnodeid_t cnode, xwidgetnum_t widget, +extern unsigned long hub_pio_map(nasid_t nasid, xwidgetnum_t widget, unsigned long xtalk_addr, size_t size); -extern void hub_pio_init(cnodeid_t cnode); +extern void hub_pio_init(nasid_t nasid); #endif /* __ASM_SN_HUB_H */ diff --git a/arch/mips/include/asm/sn/ioc3.h b/arch/mips/include/asm/sn/ioc3.h index a947eed48fee..78ef760ddde4 100644 --- a/arch/mips/include/asm/sn/ioc3.h +++ b/arch/mips/include/asm/sn/ioc3.h @@ -590,4 +590,13 @@ struct ioc3_etxd { #define MIDR_DATA_MASK 0x0000ffff +/* subsystem IDs supplied by card detection in pci-xtalk-bridge */ +#define IOC3_SUBSYS_IP27_BASEIO6G 0xc300 +#define IOC3_SUBSYS_IP27_MIO 0xc301 +#define IOC3_SUBSYS_IP27_BASEIO 0xc302 +#define IOC3_SUBSYS_IP29_SYSBOARD 0xc303 +#define IOC3_SUBSYS_IP30_SYSBOARD 0xc304 +#define IOC3_SUBSYS_MENET 0xc305 +#define IOC3_SUBSYS_MENET4 0xc306 + #endif /* MIPS_SN_IOC3_H */ diff --git a/arch/mips/include/asm/sn/mapped_kernel.h b/arch/mips/include/asm/sn/mapped_kernel.h index 2f3efa91c16e..3f1049807018 100644 --- a/arch/mips/include/asm/sn/mapped_kernel.h +++ b/arch/mips/include/asm/sn/mapped_kernel.h @@ -37,10 +37,10 @@ #define MAPPED_KERN_RO_TO_PHYS(x) \ ((unsigned long)MAPPED_ADDR_RO_TO_PHYS(x) | \ - MAPPED_KERN_RO_PHYSBASE(get_compact_nodeid())) + MAPPED_KERN_RO_PHYSBASE(get_nasid())) #define MAPPED_KERN_RW_TO_PHYS(x) \ ((unsigned long)MAPPED_ADDR_RW_TO_PHYS(x) | \ - MAPPED_KERN_RW_PHYSBASE(get_compact_nodeid())) + MAPPED_KERN_RW_PHYSBASE(get_nasid())) #else /* CONFIG_MAPPED_KERNEL */ diff --git a/arch/mips/include/asm/sn/sn0/arch.h b/arch/mips/include/asm/sn/sn0/arch.h index 425a67e6a947..12f4c4649ff0 100644 --- a/arch/mips/include/asm/sn/sn0/arch.h +++ b/arch/mips/include/asm/sn/sn0/arch.h @@ -12,25 +12,11 @@ #define _ASM_SN_SN0_ARCH_H -#ifndef SN0XXL /* 128 cpu SMP max */ -/* - * This is the maximum number of nodes that can be part of a kernel. - * Effectively, it's the maximum number of compact node ids (cnodeid_t). - */ -#define MAX_COMPACT_NODES 64 - /* * MAXCPUS refers to the maximum number of CPUs in a single kernel. * This is not necessarily the same as MAXNODES * CPUS_PER_NODE */ -#define MAXCPUS 128 - -#else /* SN0XXL system */ - -#define MAX_COMPACT_NODES 128 -#define MAXCPUS 256 - -#endif /* SN0XXL */ +#define MAXCPUS (MAX_NUMNODES * CPUS_PER_NODE) /* * This is the maximum number of NASIDS that can be present in a system. @@ -66,7 +52,5 @@ #define SLOT_MIN_MEM_SIZE (32*1024*1024) #define CPUS_PER_NODE 2 /* CPUs on a single hub */ -#define CPUS_PER_NODE_SHFT 1 /* Bits to shift in the node number */ -#define CPUS_PER_SUBNODE 2 /* CPUs on a single hub PI */ #endif /* _ASM_SN_SN0_ARCH_H */ diff --git a/arch/mips/include/asm/sn/sn_private.h b/arch/mips/include/asm/sn/sn_private.h index f09ba846c644..63a2c30d81c6 100644 --- a/arch/mips/include/asm/sn/sn_private.h +++ b/arch/mips/include/asm/sn/sn_private.h @@ -7,14 +7,13 @@ extern nasid_t master_nasid; extern void cpu_node_probe(void); -extern cnodeid_t get_compact_nodeid(void); -extern void hub_rtc_init(cnodeid_t); +extern void hub_rtc_init(nasid_t nasid); extern void cpu_time_init(void); extern void per_cpu_init(void); extern void install_cpu_nmi_handler(int slice); extern void install_ipi(void); extern void setup_replication_mask(void); extern void replicate_kernel_text(void); -extern unsigned long node_getfirstfree(cnodeid_t); +extern unsigned long node_getfirstfree(nasid_t nasid); #endif /* __ASM_SN_SN_PRIVATE_H */ diff --git a/arch/mips/include/asm/sn/types.h b/arch/mips/include/asm/sn/types.h index 6d24d4e8b9ed..203c927e84d1 100644 --- a/arch/mips/include/asm/sn/types.h +++ b/arch/mips/include/asm/sn/types.h @@ -12,13 +12,9 @@ #include <linux/types.h> typedef unsigned long cpuid_t; -typedef unsigned long cnodemask_t; typedef signed short nasid_t; /* node id in numa-as-id space */ -typedef signed short cnodeid_t; /* node id in compact-id space */ typedef signed char partid_t; /* partition ID type */ typedef signed short moduleid_t; /* user-visible module number type */ -typedef signed short cmoduleid_t; /* kernel compact module id type */ -typedef unsigned char clusterid_t; /* Clusterid of the cell */ typedef dev_t vertex_hdl_t; /* hardware graph vertex handle */ diff --git a/arch/mips/include/asm/string.h b/arch/mips/include/asm/string.h index 29030cb398ee..1de3bbce8e88 100644 --- a/arch/mips/include/asm/string.h +++ b/arch/mips/include/asm/string.h @@ -10,127 +10,6 @@ #ifndef _ASM_STRING_H #define _ASM_STRING_H - -/* - * Most of the inline functions are rather naive implementations so I just - * didn't bother updating them for 64-bit ... - */ -#ifdef CONFIG_32BIT - -#ifndef IN_STRING_C - -#define __HAVE_ARCH_STRCPY -static __inline__ char *strcpy(char *__dest, __const__ char *__src) -{ - char *__xdest = __dest; - - __asm__ __volatile__( - ".set\tnoreorder\n\t" - ".set\tnoat\n" - "1:\tlbu\t$1,(%1)\n\t" - "addiu\t%1,1\n\t" - "sb\t$1,(%0)\n\t" - "bnez\t$1,1b\n\t" - "addiu\t%0,1\n\t" - ".set\tat\n\t" - ".set\treorder" - : "=r" (__dest), "=r" (__src) - : "0" (__dest), "1" (__src) - : "memory"); - - return __xdest; -} - -#define __HAVE_ARCH_STRNCPY -static __inline__ char *strncpy(char *__dest, __const__ char *__src, size_t __n) -{ - char *__xdest = __dest; - - if (__n == 0) - return __xdest; - - __asm__ __volatile__( - ".set\tnoreorder\n\t" - ".set\tnoat\n" - "1:\tlbu\t$1,(%1)\n\t" - "subu\t%2,1\n\t" - "sb\t$1,(%0)\n\t" - "beqz\t$1,2f\n\t" - "addiu\t%0,1\n\t" - "bnez\t%2,1b\n\t" - "addiu\t%1,1\n" - "2:\n\t" - ".set\tat\n\t" - ".set\treorder" - : "=r" (__dest), "=r" (__src), "=r" (__n) - : "0" (__dest), "1" (__src), "2" (__n) - : "memory"); - - return __xdest; -} - -#define __HAVE_ARCH_STRCMP -static __inline__ int strcmp(__const__ char *__cs, __const__ char *__ct) -{ - int __res; - - __asm__ __volatile__( - ".set\tnoreorder\n\t" - ".set\tnoat\n\t" - "lbu\t%2,(%0)\n" - "1:\tlbu\t$1,(%1)\n\t" - "addiu\t%0,1\n\t" - "bne\t$1,%2,2f\n\t" - "addiu\t%1,1\n\t" - "bnez\t%2,1b\n\t" - "lbu\t%2,(%0)\n\t" -#if defined(CONFIG_CPU_R3000) - "nop\n\t" -#endif - "move\t%2,$1\n" - "2:\tsubu\t%2,$1\n" - "3:\t.set\tat\n\t" - ".set\treorder" - : "=r" (__cs), "=r" (__ct), "=r" (__res) - : "0" (__cs), "1" (__ct)); - - return __res; -} - -#endif /* !defined(IN_STRING_C) */ - -#define __HAVE_ARCH_STRNCMP -static __inline__ int -strncmp(__const__ char *__cs, __const__ char *__ct, size_t __count) -{ - int __res; - - __asm__ __volatile__( - ".set\tnoreorder\n\t" - ".set\tnoat\n" - "1:\tlbu\t%3,(%0)\n\t" - "beqz\t%2,2f\n\t" - "lbu\t$1,(%1)\n\t" - "subu\t%2,1\n\t" - "bne\t$1,%3,3f\n\t" - "addiu\t%0,1\n\t" - "bnez\t%3,1b\n\t" - "addiu\t%1,1\n" - "2:\n\t" -#if defined(CONFIG_CPU_R3000) - "nop\n\t" -#endif - "move\t%3,$1\n" - "3:\tsubu\t%3,$1\n\t" - ".set\tat\n\t" - ".set\treorder" - : "=r" (__cs), "=r" (__ct), "=r" (__count), "=r" (__res) - : "0" (__cs), "1" (__ct), "2" (__count)); - - return __res; -} -#endif /* CONFIG_32BIT */ - #define __HAVE_ARCH_MEMSET extern void *memset(void *__s, int __c, size_t __count); diff --git a/arch/mips/include/asm/sync.h b/arch/mips/include/asm/sync.h new file mode 100644 index 000000000000..7c6a1095f556 --- /dev/null +++ b/arch/mips/include/asm/sync.h @@ -0,0 +1,207 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef __MIPS_ASM_SYNC_H__ +#define __MIPS_ASM_SYNC_H__ + +/* + * sync types are defined by the MIPS64 Instruction Set documentation in Volume + * II-A of the MIPS Architecture Reference Manual, which can be found here: + * + * https://www.mips.com/?do-download=the-mips64-instruction-set-v6-06 + * + * Two types of barrier are provided: + * + * 1) Completion barriers, which ensure that a memory operation has actually + * completed & often involve stalling the CPU pipeline to do so. + * + * 2) Ordering barriers, which only ensure that affected memory operations + * won't be reordered in the CPU pipeline in a manner that violates the + * restrictions imposed by the barrier. + * + * Ordering barriers can be more efficient than completion barriers, since: + * + * a) Ordering barriers only require memory access instructions which preceed + * them in program order (older instructions) to reach a point in the + * load/store datapath beyond which reordering is not possible before + * allowing memory access instructions which follow them (younger + * instructions) to be performed. That is, older instructions don't + * actually need to complete - they just need to get far enough that all + * other coherent CPUs will observe their completion before they observe + * the effects of younger instructions. + * + * b) Multiple variants of ordering barrier are provided which allow the + * effects to be restricted to different combinations of older or younger + * loads or stores. By way of example, if we only care that stores older + * than a barrier are observed prior to stores that are younger than a + * barrier & don't care about the ordering of loads then the 'wmb' + * ordering barrier can be used. Limiting the barrier's effects to stores + * allows loads to continue unaffected & potentially allows the CPU to + * make progress faster than if younger loads had to wait for older stores + * to complete. + */ + +/* + * No sync instruction at all; used to allow code to nullify the effect of the + * __SYNC() macro without needing lots of #ifdefery. + */ +#define __SYNC_none -1 + +/* + * A full completion barrier; all memory accesses appearing prior to this sync + * instruction in program order must complete before any memory accesses + * appearing after this sync instruction in program order. + */ +#define __SYNC_full 0x00 + +/* + * For now we use a full completion barrier to implement all sync types, until + * we're satisfied that lightweight ordering barriers defined by MIPSr6 are + * sufficient to uphold our desired memory model. + */ +#define __SYNC_aq __SYNC_full +#define __SYNC_rl __SYNC_full +#define __SYNC_mb __SYNC_full + +/* + * ...except on Cavium Octeon CPUs, which have been using the 'wmb' ordering + * barrier since 2010 & omit 'rmb' barriers because the CPUs don't perform + * speculative reads. + */ +#ifdef CONFIG_CPU_CAVIUM_OCTEON +# define __SYNC_rmb __SYNC_none +# define __SYNC_wmb 0x04 +#else +# define __SYNC_rmb __SYNC_full +# define __SYNC_wmb __SYNC_full +#endif + +/* + * A GINV sync is a little different; it doesn't relate directly to loads or + * stores, but instead causes synchronization of an icache or TLB global + * invalidation operation triggered by the ginvi or ginvt instructions + * respectively. In cases where we need to know that a ginvi or ginvt operation + * has been performed by all coherent CPUs, we must issue a sync instruction of + * this type. Once this instruction graduates all coherent CPUs will have + * observed the invalidation. + */ +#define __SYNC_ginv 0x14 + +/* Trivial; indicate that we always need this sync instruction. */ +#define __SYNC_always (1 << 0) + +/* + * Indicate that we need this sync instruction only on systems with weakly + * ordered memory access. In general this is most MIPS systems, but there are + * exceptions which provide strongly ordered memory. + */ +#ifdef CONFIG_WEAK_ORDERING +# define __SYNC_weak_ordering (1 << 1) +#else +# define __SYNC_weak_ordering 0 +#endif + +/* + * Indicate that we need this sync instruction only on systems where LL/SC + * don't implicitly provide a memory barrier. In general this is most MIPS + * systems. + */ +#ifdef CONFIG_WEAK_REORDERING_BEYOND_LLSC +# define __SYNC_weak_llsc (1 << 2) +#else +# define __SYNC_weak_llsc 0 +#endif + +/* + * Some Loongson 3 CPUs have a bug wherein execution of a memory access (load, + * store or prefetch) in between an LL & SC can cause the SC instruction to + * erroneously succeed, breaking atomicity. Whilst it's unusual to write code + * containing such sequences, this bug bites harder than we might otherwise + * expect due to reordering & speculation: + * + * 1) A memory access appearing prior to the LL in program order may actually + * be executed after the LL - this is the reordering case. + * + * In order to avoid this we need to place a memory barrier (ie. a SYNC + * instruction) prior to every LL instruction, in between it and any earlier + * memory access instructions. + * + * This reordering case is fixed by 3A R2 CPUs, ie. 3A2000 models and later. + * + * 2) If a conditional branch exists between an LL & SC with a target outside + * of the LL-SC loop, for example an exit upon value mismatch in cmpxchg() + * or similar, then misprediction of the branch may allow speculative + * execution of memory accesses from outside of the LL-SC loop. + * + * In order to avoid this we need a memory barrier (ie. a SYNC instruction) + * at each affected branch target. + * + * This case affects all current Loongson 3 CPUs. + * + * The above described cases cause an error in the cache coherence protocol; + * such that the Invalidate of a competing LL-SC goes 'missing' and SC + * erroneously observes its core still has Exclusive state and lets the SC + * proceed. + * + * Therefore the error only occurs on SMP systems. + */ +#ifdef CONFIG_CPU_LOONGSON3_WORKAROUNDS +# define __SYNC_loongson3_war (1 << 31) +#else +# define __SYNC_loongson3_war 0 +#endif + +/* + * Some Cavium Octeon CPUs suffer from a bug that causes a single wmb ordering + * barrier to be ineffective, requiring the use of 2 in sequence to provide an + * effective barrier as noted by commit 6b07d38aaa52 ("MIPS: Octeon: Use + * optimized memory barrier primitives."). Here we specify that the affected + * sync instructions should be emitted twice. + */ +#ifdef CONFIG_CPU_CAVIUM_OCTEON +# define __SYNC_rpt(type) (1 + (type == __SYNC_wmb)) +#else +# define __SYNC_rpt(type) 1 +#endif + +/* + * The main event. Here we actually emit a sync instruction of a given type, if + * reason is non-zero. + * + * In future we have the option of emitting entries in a fixups-style table + * here that would allow us to opportunistically remove some sync instructions + * when we detect at runtime that we're running on a CPU that doesn't need + * them. + */ +#ifdef CONFIG_CPU_HAS_SYNC +# define ____SYNC(_type, _reason, _else) \ + .if (( _type ) != -1) && ( _reason ); \ + .set push; \ + .set MIPS_ISA_LEVEL_RAW; \ + .rept __SYNC_rpt(_type); \ + sync _type; \ + .endr; \ + .set pop; \ + .else; \ + _else; \ + .endif +#else +# define ____SYNC(_type, _reason, _else) +#endif + +/* + * Preprocessor magic to expand macros used as arguments before we insert them + * into assembly code. + */ +#ifdef __ASSEMBLY__ +# define ___SYNC(type, reason, else) \ + ____SYNC(type, reason, else) +#else +# define ___SYNC(type, reason, else) \ + __stringify(____SYNC(type, reason, else)) +#endif + +#define __SYNC(type, reason) \ + ___SYNC(__SYNC_##type, __SYNC_##reason, ) +#define __SYNC_ELSE(type, reason, else) \ + ___SYNC(__SYNC_##type, __SYNC_##reason, else) + +#endif /* __MIPS_ASM_SYNC_H__ */ diff --git a/arch/mips/include/asm/unroll.h b/arch/mips/include/asm/unroll.h new file mode 100644 index 000000000000..c628747d4ecd --- /dev/null +++ b/arch/mips/include/asm/unroll.h @@ -0,0 +1,77 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef __ASM_UNROLL_H__ +#define __ASM_UNROLL_H__ + +/* + * Explicitly unroll a loop, for use in cases where doing so is performance + * critical. + * + * Ideally we'd rely upon the compiler to provide this but there's no commonly + * available means to do so. For example GCC's "#pragma GCC unroll" + * functionality would be ideal but is only available from GCC 8 onwards. Using + * -funroll-loops is an option but GCC tends to make poor choices when + * compiling our string functions. -funroll-all-loops leads to massive code + * bloat, even if only applied to the string functions. + */ +#define unroll(times, fn, ...) do { \ + extern void bad_unroll(void) \ + __compiletime_error("Unsupported unroll"); \ + \ + /* \ + * We can't unroll if the number of iterations isn't \ + * compile-time constant. Unfortunately GCC versions \ + * up until 4.6 tend to miss obvious constants & cause \ + * this check to fail, even though they go on to \ + * generate reasonable code for the switch statement, \ + * so we skip the sanity check for those compilers. \ + */ \ + BUILD_BUG_ON((CONFIG_GCC_VERSION >= 40700 || \ + CONFIG_CLANG_VERSION >= 80000) && \ + !__builtin_constant_p(times)); \ + \ + switch (times) { \ + case 32: fn(__VA_ARGS__); /* fall through */ \ + case 31: fn(__VA_ARGS__); /* fall through */ \ + case 30: fn(__VA_ARGS__); /* fall through */ \ + case 29: fn(__VA_ARGS__); /* fall through */ \ + case 28: fn(__VA_ARGS__); /* fall through */ \ + case 27: fn(__VA_ARGS__); /* fall through */ \ + case 26: fn(__VA_ARGS__); /* fall through */ \ + case 25: fn(__VA_ARGS__); /* fall through */ \ + case 24: fn(__VA_ARGS__); /* fall through */ \ + case 23: fn(__VA_ARGS__); /* fall through */ \ + case 22: fn(__VA_ARGS__); /* fall through */ \ + case 21: fn(__VA_ARGS__); /* fall through */ \ + case 20: fn(__VA_ARGS__); /* fall through */ \ + case 19: fn(__VA_ARGS__); /* fall through */ \ + case 18: fn(__VA_ARGS__); /* fall through */ \ + case 17: fn(__VA_ARGS__); /* fall through */ \ + case 16: fn(__VA_ARGS__); /* fall through */ \ + case 15: fn(__VA_ARGS__); /* fall through */ \ + case 14: fn(__VA_ARGS__); /* fall through */ \ + case 13: fn(__VA_ARGS__); /* fall through */ \ + case 12: fn(__VA_ARGS__); /* fall through */ \ + case 11: fn(__VA_ARGS__); /* fall through */ \ + case 10: fn(__VA_ARGS__); /* fall through */ \ + case 9: fn(__VA_ARGS__); /* fall through */ \ + case 8: fn(__VA_ARGS__); /* fall through */ \ + case 7: fn(__VA_ARGS__); /* fall through */ \ + case 6: fn(__VA_ARGS__); /* fall through */ \ + case 5: fn(__VA_ARGS__); /* fall through */ \ + case 4: fn(__VA_ARGS__); /* fall through */ \ + case 3: fn(__VA_ARGS__); /* fall through */ \ + case 2: fn(__VA_ARGS__); /* fall through */ \ + case 1: fn(__VA_ARGS__); /* fall through */ \ + case 0: break; \ + \ + default: \ + /* \ + * Either the iteration count is unreasonable \ + * or we need to add more cases above. \ + */ \ + bad_unroll(); \ + break; \ + } \ +} while (0) + +#endif /* __ASM_UNROLL_H__ */ diff --git a/arch/mips/include/asm/vdso/vsyscall.h b/arch/mips/include/asm/vdso/vsyscall.h index 195314732233..00d41b94ba31 100644 --- a/arch/mips/include/asm/vdso/vsyscall.h +++ b/arch/mips/include/asm/vdso/vsyscall.h @@ -28,13 +28,6 @@ int __mips_get_clock_mode(struct timekeeper *tk) } #define __arch_get_clock_mode __mips_get_clock_mode -static __always_inline -int __mips_use_vsyscall(struct vdso_data *vdata) -{ - return (vdata[CS_HRES_COARSE].clock_mode != VDSO_CLOCK_NONE); -} -#define __arch_use_vsyscall __mips_use_vsyscall - /* The asm-generic header needs to be included after the definitions above */ #include <asm-generic/vdso/vsyscall.h> |