mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-28 11:18:45 +07:00
f4329f2ecb
Exception handlers are aligned to 128 bytes (L1 cache) on 64s, which is overkill. It can reduce the icache footprint of any individual exception path. However taken as a whole, the expansion in icache footprint seems likely to be counter-productive and cause more total misses. Create IFETCH_ALIGN_SHIFT/BYTES, which should give optimal ifetch alignment with much more reasonable alignment. This saves 1792 bytes from head_64.o text with an allmodconfig build. Other subarchitectures should define appropriate IFETCH_ALIGN_SHIFT values if this becomes more widely used. Signed-off-by: Nicholas Piggin <npiggin@gmail.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
97 lines
2.3 KiB
C
97 lines
2.3 KiB
C
#ifndef _ASM_POWERPC_CACHE_H
|
|
#define _ASM_POWERPC_CACHE_H
|
|
|
|
#ifdef __KERNEL__
|
|
|
|
|
|
/* bytes per L1 cache line */
|
|
#if defined(CONFIG_8xx) || defined(CONFIG_403GCX)
|
|
#define L1_CACHE_SHIFT 4
|
|
#define MAX_COPY_PREFETCH 1
|
|
#elif defined(CONFIG_PPC_E500MC)
|
|
#define L1_CACHE_SHIFT 6
|
|
#define MAX_COPY_PREFETCH 4
|
|
#elif defined(CONFIG_PPC32)
|
|
#define MAX_COPY_PREFETCH 4
|
|
#if defined(CONFIG_PPC_47x)
|
|
#define L1_CACHE_SHIFT 7
|
|
#else
|
|
#define L1_CACHE_SHIFT 5
|
|
#endif
|
|
#else /* CONFIG_PPC64 */
|
|
#define L1_CACHE_SHIFT 7
|
|
#define IFETCH_ALIGN_SHIFT 4 /* POWER8,9 */
|
|
#endif
|
|
|
|
#define L1_CACHE_BYTES (1 << L1_CACHE_SHIFT)
|
|
|
|
#define SMP_CACHE_BYTES L1_CACHE_BYTES
|
|
|
|
#define IFETCH_ALIGN_BYTES (1 << IFETCH_ALIGN_SHIFT)
|
|
|
|
#if defined(__powerpc64__) && !defined(__ASSEMBLY__)
|
|
struct ppc64_caches {
|
|
u32 dsize; /* L1 d-cache size */
|
|
u32 dline_size; /* L1 d-cache line size */
|
|
u32 log_dline_size;
|
|
u32 dlines_per_page;
|
|
u32 isize; /* L1 i-cache size */
|
|
u32 iline_size; /* L1 i-cache line size */
|
|
u32 log_iline_size;
|
|
u32 ilines_per_page;
|
|
};
|
|
|
|
extern struct ppc64_caches ppc64_caches;
|
|
#endif /* __powerpc64__ && ! __ASSEMBLY__ */
|
|
|
|
#if defined(__ASSEMBLY__)
|
|
/*
|
|
* For a snooping icache, we still need a dummy icbi to purge all the
|
|
* prefetched instructions from the ifetch buffers. We also need a sync
|
|
* before the icbi to order the the actual stores to memory that might
|
|
* have modified instructions with the icbi.
|
|
*/
|
|
#define PURGE_PREFETCHED_INS \
|
|
sync; \
|
|
icbi 0,r3; \
|
|
sync; \
|
|
isync
|
|
|
|
#else
|
|
#define __read_mostly __attribute__((__section__(".data..read_mostly")))
|
|
|
|
#ifdef CONFIG_6xx
|
|
extern long _get_L2CR(void);
|
|
extern long _get_L3CR(void);
|
|
extern void _set_L2CR(unsigned long);
|
|
extern void _set_L3CR(unsigned long);
|
|
#else
|
|
#define _get_L2CR() 0L
|
|
#define _get_L3CR() 0L
|
|
#define _set_L2CR(val) do { } while(0)
|
|
#define _set_L3CR(val) do { } while(0)
|
|
#endif
|
|
|
|
static inline void dcbz(void *addr)
|
|
{
|
|
__asm__ __volatile__ ("dcbz 0, %0" : : "r"(addr) : "memory");
|
|
}
|
|
|
|
static inline void dcbi(void *addr)
|
|
{
|
|
__asm__ __volatile__ ("dcbi 0, %0" : : "r"(addr) : "memory");
|
|
}
|
|
|
|
static inline void dcbf(void *addr)
|
|
{
|
|
__asm__ __volatile__ ("dcbf 0, %0" : : "r"(addr) : "memory");
|
|
}
|
|
|
|
static inline void dcbst(void *addr)
|
|
{
|
|
__asm__ __volatile__ ("dcbst 0, %0" : : "r"(addr) : "memory");
|
|
}
|
|
#endif /* !__ASSEMBLY__ */
|
|
#endif /* __KERNEL__ */
|
|
#endif /* _ASM_POWERPC_CACHE_H */
|