diff options
| author | Nicholas Piggin <npiggin@gmail.com> | 2018-03-07 11:37:12 +1000 |
|---|---|---|
| committer | Michael Ellerman <mpe@ellerman.id.au> | 2018-03-13 23:43:06 +1100 |
| commit | 5709f7cfd8305252dc327206bd674ad65ca4d77f (patch) | |
| tree | 3bff567b21774e60411dbc9722211e121983f9c6 /arch/powerpc/include/asm/book3s/64/mmu.h | |
| parent | 830fd2d45aa11631325404904d02c7b530d40119 (diff) | |
| download | linux-0-day-5709f7cfd8305252dc327206bd674ad65ca4d77f.tar.gz linux-0-day-5709f7cfd8305252dc327206bd674ad65ca4d77f.tar.xz | |
powerpc/mm/slice: implement a slice mask cache
Calculating the slice mask can become a signifcant overhead for
get_unmapped_area. This patch adds a struct slice_mask for
each page size in the mm_context, and keeps these in synch with
the slices psize arrays and slb_addr_limit.
On Book3S/64 this adds 288 bytes to the mm_context_t for the
slice mask caches.
On POWER8, this increases vfork+exec+exit performance by 9.9%
and reduces time to mmap+munmap a 64kB page by 28%.
Reduces time to mmap+munmap by about 10% on 8xx.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Diffstat (limited to 'arch/powerpc/include/asm/book3s/64/mmu.h')
| -rw-r--r-- | arch/powerpc/include/asm/book3s/64/mmu.h | 18 |
1 files changed, 18 insertions, 0 deletions
diff --git a/arch/powerpc/include/asm/book3s/64/mmu.h b/arch/powerpc/include/asm/book3s/64/mmu.h index bef6e39ed63a2..777778579305e 100644 --- a/arch/powerpc/include/asm/book3s/64/mmu.h +++ b/arch/powerpc/include/asm/book3s/64/mmu.h @@ -80,6 +80,16 @@ struct spinlock; /* Maximum possible number of NPUs in a system. */ #define NV_MAX_NPUS 8 +/* + * One bit per slice. We have lower slices which cover 256MB segments + * upto 4G range. That gets us 16 low slices. For the rest we track slices + * in 1TB size. + */ +struct slice_mask { + u64 low_slices; + DECLARE_BITMAP(high_slices, SLICE_NUM_HIGH); +}; + typedef struct { mm_context_id_t id; u16 user_psize; /* page size index */ @@ -95,6 +105,14 @@ typedef struct { unsigned char low_slices_psize[BITS_PER_LONG / BITS_PER_BYTE]; unsigned char high_slices_psize[SLICE_ARRAY_SIZE]; unsigned long slb_addr_limit; +# ifdef CONFIG_PPC_64K_PAGES + struct slice_mask mask_64k; +# endif + struct slice_mask mask_4k; +# ifdef CONFIG_HUGETLB_PAGE + struct slice_mask mask_16m; + struct slice_mask mask_16g; +# endif #else u16 sllp; /* SLB page size encoding */ #endif |