Re: [PATCH v4 2/5] powerpc/mm/slice: Enhance for supporting PPC32

From: Aneesh Kumar K.V
Date: Mon Feb 12 2018 - 00:47:09 EST

Next message: Aneesh Kumar K.V: "Re: [PATCH v4 4/5] powerpc/mm/slice: Allow up to 64 low slices"
Previous message: Siva Reddy Kallam: "Re: tg3 crashes under high load, when using 100Mbits"
In reply to: Nicholas Piggin: "Re: [PATCH v4 2/5] powerpc/mm/slice: Enhance for supporting PPC32"
Next in thread: Christophe Leroy: "[PATCH v4 4/5] powerpc/mm/slice: Allow up to 64 low slices"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

Christophe Leroy <christophe.leroy@xxxxxx> writes:

> In preparation for the following patch which will fix an issue on
> the 8xx by re-using the 'slices', this patch enhances the
> 'slices' implementation to support 32 bits CPUs.
>
> On PPC32, the address space is limited to 4Gbytes, hence only the low
> slices will be used.
>
> This patch moves "slices" functions prototypes from page64.h to slice.h
>
> The high slices use bitmaps. As bitmap functions are not prepared to
> handling bitmaps of size 0, the bitmap_xxx() calls are wrapped into
> slice_bitmap_xxx() functions which will void on PPC32
>

Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@xxxxxxxxxxxxxxxxxx>

> Signed-off-by: Christophe Leroy <christophe.leroy@xxxxxx>
> ---
> v2: First patch of v1 serie split in two parts ; added slice_bitmap_xxx() macros.
> v3: Moving slice related stuff in slice.h and slice_32/64.h
> slice_bitmap_xxx() are now static inline functions and platform dependent
> SLICE_LOW_TOP declared ull on PPC32 with correct casts allows to keep it 0x100000000
> v4: Moved slice_32.h and slice_64.h to respective subarch dirs
> Moved somes #ifdefs from asm/slice.h to respective subarch slice.h
> SLICE_LOW_ details distributed in repective subarch slices allthough they are identical for the moment
>
> arch/powerpc/include/asm/book3s/64/slice.h | 79 ++++++++++++++++++++++++++++++
> arch/powerpc/include/asm/nohash/32/slice.h | 65 ++++++++++++++++++++++++
> arch/powerpc/include/asm/nohash/64/slice.h | 12 +++++
> arch/powerpc/include/asm/page.h | 1 +
> arch/powerpc/include/asm/page_64.h | 59 ----------------------
> arch/powerpc/include/asm/slice.h | 42 ++++++++++++++++
> arch/powerpc/mm/slice.c | 38 ++++++++------
> 7 files changed, 221 insertions(+), 75 deletions(-)
> create mode 100644 arch/powerpc/include/asm/book3s/64/slice.h
> create mode 100644 arch/powerpc/include/asm/nohash/32/slice.h
> create mode 100644 arch/powerpc/include/asm/nohash/64/slice.h
> create mode 100644 arch/powerpc/include/asm/slice.h
>
> diff --git a/arch/powerpc/include/asm/book3s/64/slice.h b/arch/powerpc/include/asm/book3s/64/slice.h
> new file mode 100644
> index 000000000000..f9a2c8bd7a77
> --- /dev/null
> +++ b/arch/powerpc/include/asm/book3s/64/slice.h
> @@ -0,0 +1,79 @@
> +/* SPDX-License-Identifier: GPL-2.0 */
> +#ifndef _ASM_POWERPC_BOOK3S_64_SLICE_H
> +#define _ASM_POWERPC_BOOK3S_64_SLICE_H
> +
> +#ifdef CONFIG_PPC_MM_SLICES
> +
> +#define SLICE_LOW_SHIFT 28
> +#define SLICE_LOW_TOP (0x100000000ul)
> +#define SLICE_NUM_LOW (SLICE_LOW_TOP >> SLICE_LOW_SHIFT)
> +#define GET_LOW_SLICE_INDEX(addr) ((addr) >> SLICE_LOW_SHIFT)
> +
> +#define SLICE_HIGH_SHIFT 40
> +#define SLICE_NUM_HIGH (H_PGTABLE_RANGE >> SLICE_HIGH_SHIFT)
> +#define GET_HIGH_SLICE_INDEX(addr) ((addr) >> SLICE_HIGH_SHIFT)
> +
> +#ifndef __ASSEMBLY__
> +
> +#include <linux/bitmap.h>
> +
> +static inline void slice_bitmap_zero(unsigned long *dst, unsigned int nbits)
> +{
> + bitmap_zero(dst, nbits);
> +}
> +
> +static inline int slice_bitmap_and(unsigned long *dst,
> + const unsigned long *src1,
> + const unsigned long *src2,
> + unsigned int nbits)
> +{
> + return bitmap_and(dst, src1, src2, nbits);
> +}
> +
> +static inline void slice_bitmap_or(unsigned long *dst,
> + const unsigned long *src1,
> + const unsigned long *src2,
> + unsigned int nbits)
> +{
> + bitmap_or(dst, src1, src2, nbits);
> +}
> +
> +static inline int slice_bitmap_andnot(unsigned long *dst,
> + const unsigned long *src1,
> + const unsigned long *src2,
> + unsigned int nbits)
> +{
> + return bitmap_andnot(dst, src1, src2, nbits);
> +}
> +
> +static inline int slice_bitmap_equal(const unsigned long *src1,
> + const unsigned long *src2,
> + unsigned int nbits)
> +{
> + return bitmap_equal(src1, src2, nbits);
> +}
> +
> +static inline int slice_bitmap_empty(const unsigned long *src, unsigned nbits)
> +{
> + return bitmap_empty(src, nbits);
> +}
> +
> +static inline void slice_bitmap_set(unsigned long *map, unsigned int start,
> + unsigned int nbits)
> +{
> + bitmap_set(map, start, nbits);
> +}
> +#endif /* __ASSEMBLY__ */
> +
> +#else /* CONFIG_PPC_MM_SLICES */
> +
> +#define get_slice_psize(mm, addr) ((mm)->context.user_psize)
> +#define slice_set_user_psize(mm, psize) \
> +do { \
> + (mm)->context.user_psize = (psize); \
> + (mm)->context.sllp = SLB_VSID_USER | mmu_psize_defs[(psize)].sllp; \
> +} while (0)
> +
> +#endif /* CONFIG_PPC_MM_SLICES */
> +
> +#endif /* _ASM_POWERPC_BOOK3S_64_SLICE_H */
> diff --git a/arch/powerpc/include/asm/nohash/32/slice.h b/arch/powerpc/include/asm/nohash/32/slice.h
> new file mode 100644
> index 000000000000..bcb4924f7d22
> --- /dev/null
> +++ b/arch/powerpc/include/asm/nohash/32/slice.h
> @@ -0,0 +1,65 @@
> +/* SPDX-License-Identifier: GPL-2.0 */
> +#ifndef _ASM_POWERPC_NOHASH_32_SLICE_H
> +#define _ASM_POWERPC_NOHASH_32_SLICE_H
> +
> +#ifdef CONFIG_PPC_MM_SLICES
> +
> +#define SLICE_LOW_SHIFT 28
> +#define SLICE_LOW_TOP (0x100000000ull)
> +#define SLICE_NUM_LOW (SLICE_LOW_TOP >> SLICE_LOW_SHIFT)
> +#define GET_LOW_SLICE_INDEX(addr) ((addr) >> SLICE_LOW_SHIFT)
> +
> +#define SLICE_HIGH_SHIFT 0
> +#define SLICE_NUM_HIGH 0ul
> +#define GET_HIGH_SLICE_INDEX(addr) (addr & 0)
> +
> +#ifndef __ASSEMBLY__
> +
> +static inline void slice_bitmap_zero(unsigned long *dst, unsigned int nbits)
> +{
> +}
> +
> +static inline int slice_bitmap_and(unsigned long *dst,
> + const unsigned long *src1,
> + const unsigned long *src2,
> + unsigned int nbits)
> +{
> + return 0;
> +}
> +
> +static inline void slice_bitmap_or(unsigned long *dst,
> + const unsigned long *src1,
> + const unsigned long *src2,
> + unsigned int nbits)
> +{
> +}
> +
> +static inline int slice_bitmap_andnot(unsigned long *dst,
> + const unsigned long *src1,
> + const unsigned long *src2,
> + unsigned int nbits)
> +{
> + return 0;
> +}
> +
> +static inline int slice_bitmap_equal(const unsigned long *src1,
> + const unsigned long *src2,
> + unsigned int nbits)
> +{
> + return 1;
> +}
> +
> +static inline int slice_bitmap_empty(const unsigned long *src, unsigned nbits)
> +{
> + return 1;
> +}
> +
> +static inline void slice_bitmap_set(unsigned long *map, unsigned int start,
> + unsigned int nbits)
> +{
> +}
> +#endif /* __ASSEMBLY__ */
> +
> +#endif /* CONFIG_PPC_MM_SLICES */
> +
> +#endif /* _ASM_POWERPC_NOHASH_32_SLICE_H */
> diff --git a/arch/powerpc/include/asm/nohash/64/slice.h b/arch/powerpc/include/asm/nohash/64/slice.h
> new file mode 100644
> index 000000000000..ad0d6e3cc1c5
> --- /dev/null
> +++ b/arch/powerpc/include/asm/nohash/64/slice.h
> @@ -0,0 +1,12 @@
> +/* SPDX-License-Identifier: GPL-2.0 */
> +#ifndef _ASM_POWERPC_NOHASH_64_SLICE_H
> +#define _ASM_POWERPC_NOHASH_64_SLICE_H
> +
> +#ifdef CONFIG_PPC_64K_PAGES
> +#define get_slice_psize(mm, addr) MMU_PAGE_64K
> +#else /* CONFIG_PPC_64K_PAGES */
> +#define get_slice_psize(mm, addr) MMU_PAGE_4K
> +#endif /* !CONFIG_PPC_64K_PAGES */
> +#define slice_set_user_psize(mm, psize) do { BUG(); } while (0)
> +
> +#endif /* _ASM_POWERPC_NOHASH_64_SLICE_H */
> diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h
> index 8da5d4c1cab2..d5f1c41b7dba 100644
> --- a/arch/powerpc/include/asm/page.h
> +++ b/arch/powerpc/include/asm/page.h
> @@ -344,5 +344,6 @@ typedef struct page *pgtable_t;
>
> #include <asm-generic/memory_model.h>
> #endif /* __ASSEMBLY__ */
> +#include <asm/slice.h>
>
> #endif /* _ASM_POWERPC_PAGE_H */
> diff --git a/arch/powerpc/include/asm/page_64.h b/arch/powerpc/include/asm/page_64.h
> index 56234c6fcd61..af04acdb873f 100644
> --- a/arch/powerpc/include/asm/page_64.h
> +++ b/arch/powerpc/include/asm/page_64.h
> @@ -86,65 +86,6 @@ extern u64 ppc64_pft_size;
>
> #endif /* __ASSEMBLY__ */
>
> -#ifdef CONFIG_PPC_MM_SLICES
> -
> -#define SLICE_LOW_SHIFT 28
> -#define SLICE_HIGH_SHIFT 40
> -
> -#define SLICE_LOW_TOP (0x100000000ul)
> -#define SLICE_NUM_LOW (SLICE_LOW_TOP >> SLICE_LOW_SHIFT)
> -#define SLICE_NUM_HIGH (H_PGTABLE_RANGE >> SLICE_HIGH_SHIFT)
> -
> -#define GET_LOW_SLICE_INDEX(addr) ((addr) >> SLICE_LOW_SHIFT)
> -#define GET_HIGH_SLICE_INDEX(addr) ((addr) >> SLICE_HIGH_SHIFT)
> -
> -#ifndef __ASSEMBLY__
> -struct mm_struct;
> -
> -extern unsigned long slice_get_unmapped_area(unsigned long addr,
> - unsigned long len,
> - unsigned long flags,
> - unsigned int psize,
> - int topdown);
> -
> -extern unsigned int get_slice_psize(struct mm_struct *mm,
> - unsigned long addr);
> -
> -extern void slice_set_user_psize(struct mm_struct *mm, unsigned int psize);
> -extern void slice_set_range_psize(struct mm_struct *mm, unsigned long start,
> - unsigned long len, unsigned int psize);
> -
> -#endif /* __ASSEMBLY__ */
> -#else
> -#define slice_init()
> -#ifdef CONFIG_PPC_BOOK3S_64
> -#define get_slice_psize(mm, addr) ((mm)->context.user_psize)
> -#define slice_set_user_psize(mm, psize) \
> -do { \
> - (mm)->context.user_psize = (psize); \
> - (mm)->context.sllp = SLB_VSID_USER | mmu_psize_defs[(psize)].sllp; \
> -} while (0)
> -#else /* !CONFIG_PPC_BOOK3S_64 */
> -#ifdef CONFIG_PPC_64K_PAGES
> -#define get_slice_psize(mm, addr) MMU_PAGE_64K
> -#else /* CONFIG_PPC_64K_PAGES */
> -#define get_slice_psize(mm, addr) MMU_PAGE_4K
> -#endif /* !CONFIG_PPC_64K_PAGES */
> -#define slice_set_user_psize(mm, psize) do { BUG(); } while(0)
> -#endif /* CONFIG_PPC_BOOK3S_64 */
> -
> -#define slice_set_range_psize(mm, start, len, psize) \
> - slice_set_user_psize((mm), (psize))
> -#endif /* CONFIG_PPC_MM_SLICES */
> -
> -#ifdef CONFIG_HUGETLB_PAGE
> -
> -#ifdef CONFIG_PPC_MM_SLICES
> -#define HAVE_ARCH_HUGETLB_UNMAPPED_AREA
> -#endif
> -
> -#endif /* !CONFIG_HUGETLB_PAGE */
> -
> #define VM_DATA_DEFAULT_FLAGS \
> (is_32bit_task() ? \
> VM_DATA_DEFAULT_FLAGS32 : VM_DATA_DEFAULT_FLAGS64)
> diff --git a/arch/powerpc/include/asm/slice.h b/arch/powerpc/include/asm/slice.h
> new file mode 100644
> index 000000000000..172711fadb1c
> --- /dev/null
> +++ b/arch/powerpc/include/asm/slice.h
> @@ -0,0 +1,42 @@
> +/* SPDX-License-Identifier: GPL-2.0 */
> +#ifndef _ASM_POWERPC_SLICE_H
> +#define _ASM_POWERPC_SLICE_H
> +
> +#ifdef CONFIG_PPC_BOOK3S_64
> +#include <asm/book3s/64/slice.h>
> +#elif defined(CONFIG_PPC64)
> +#include <asm/nohash/64/slice.h>
> +#elif defined(CONFIG_PPC_MMU_NOHASH)
> +#include <asm/nohash/32/slice.h>
> +#endif
> +
> +#ifdef CONFIG_PPC_MM_SLICES
> +
> +#ifdef CONFIG_HUGETLB_PAGE
> +#define HAVE_ARCH_HUGETLB_UNMAPPED_AREA
> +#endif
> +#define HAVE_ARCH_UNMAPPED_AREA
> +#define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN
> +
> +#ifndef __ASSEMBLY__
> +
> +struct mm_struct;
> +
> +unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len,
> + unsigned long flags, unsigned int psize,
> + int topdown);
> +
> +unsigned int get_slice_psize(struct mm_struct *mm, unsigned long addr);
> +
> +void slice_set_user_psize(struct mm_struct *mm, unsigned int psize);
> +void slice_set_range_psize(struct mm_struct *mm, unsigned long start,
> + unsigned long len, unsigned int psize);
> +#endif /* __ASSEMBLY__ */
> +
> +#else /* CONFIG_PPC_MM_SLICES */
> +
> +#define slice_set_range_psize(mm, start, len, psize) \
> + slice_set_user_psize((mm), (psize))
> +#endif /* CONFIG_PPC_MM_SLICES */
> +
> +#endif /* _ASM_POWERPC_SLICE_H */
> diff --git a/arch/powerpc/mm/slice.c b/arch/powerpc/mm/slice.c
> index 98b53d48968f..549704dfa777 100644
> --- a/arch/powerpc/mm/slice.c
> +++ b/arch/powerpc/mm/slice.c
> @@ -73,10 +73,11 @@ static void slice_range_to_mask(unsigned long start, unsigned long len,
> unsigned long end = start + len - 1;
>
> ret->low_slices = 0;
> - bitmap_zero(ret->high_slices, SLICE_NUM_HIGH);
> + slice_bitmap_zero(ret->high_slices, SLICE_NUM_HIGH);
>
> if (start < SLICE_LOW_TOP) {
> - unsigned long mend = min(end, (SLICE_LOW_TOP - 1));
> + unsigned long mend = min(end,
> + (unsigned long)(SLICE_LOW_TOP - 1));
>
> ret->low_slices = (1u << (GET_LOW_SLICE_INDEX(mend) + 1))
> - (1u << GET_LOW_SLICE_INDEX(start));
> @@ -87,7 +88,7 @@ static void slice_range_to_mask(unsigned long start, unsigned long len,
> unsigned long align_end = ALIGN(end, (1UL << SLICE_HIGH_SHIFT));
> unsigned long count = GET_HIGH_SLICE_INDEX(align_end) - start_index;
>
> - bitmap_set(ret->high_slices, start_index, count);
> + slice_bitmap_set(ret->high_slices, start_index, count);
> }
> }
>
> @@ -113,11 +114,13 @@ static int slice_high_has_vma(struct mm_struct *mm, unsigned long slice)
> unsigned long start = slice << SLICE_HIGH_SHIFT;
> unsigned long end = start + (1ul << SLICE_HIGH_SHIFT);
>
> +#ifdef CONFIG_PPC64
> /* Hack, so that each addresses is controlled by exactly one
> * of the high or low area bitmaps, the first high area starts
> * at 4GB, not 0 */
> if (start == 0)
> start = SLICE_LOW_TOP;
> +#endif
>
> return !slice_area_is_free(mm, start, end - start);
> }
> @@ -128,7 +131,7 @@ static void slice_mask_for_free(struct mm_struct *mm, struct slice_mask *ret,
> unsigned long i;
>
> ret->low_slices = 0;
> - bitmap_zero(ret->high_slices, SLICE_NUM_HIGH);
> + slice_bitmap_zero(ret->high_slices, SLICE_NUM_HIGH);
>
> for (i = 0; i < SLICE_NUM_LOW; i++)
> if (!slice_low_has_vma(mm, i))
> @@ -151,7 +154,7 @@ static void slice_mask_for_size(struct mm_struct *mm, int psize, struct slice_ma
> u64 lpsizes;
>
> ret->low_slices = 0;
> - bitmap_zero(ret->high_slices, SLICE_NUM_HIGH);
> + slice_bitmap_zero(ret->high_slices, SLICE_NUM_HIGH);
>
> lpsizes = mm->context.low_slices_psize;
> for (i = 0; i < SLICE_NUM_LOW; i++)
> @@ -180,15 +183,16 @@ static int slice_check_fit(struct mm_struct *mm,
> */
> unsigned long slice_count = GET_HIGH_SLICE_INDEX(mm->context.slb_addr_limit);
>
> - bitmap_and(result, mask.high_slices,
> - available.high_slices, slice_count);
> + slice_bitmap_and(result, mask.high_slices, available.high_slices,
> + slice_count);
>
> return (mask.low_slices & available.low_slices) == mask.low_slices &&
> - bitmap_equal(result, mask.high_slices, slice_count);
> + slice_bitmap_equal(result, mask.high_slices, slice_count);
> }
>
> static void slice_flush_segments(void *parm)
> {
> +#ifdef CONFIG_PPC64
> struct mm_struct *mm = parm;
> unsigned long flags;
>
> @@ -200,6 +204,7 @@ static void slice_flush_segments(void *parm)
> local_irq_save(flags);
> slb_flush_and_rebolt();
> local_irq_restore(flags);
> +#endif
> }
>
> static void slice_convert(struct mm_struct *mm, struct slice_mask mask, int psize)
> @@ -389,16 +394,16 @@ static unsigned long slice_find_area(struct mm_struct *mm, unsigned long len,
> static inline void slice_or_mask(struct slice_mask *dst, struct slice_mask *src)
> {
> dst->low_slices |= src->low_slices;
> - bitmap_or(dst->high_slices, dst->high_slices, src->high_slices,
> - SLICE_NUM_HIGH);
> + slice_bitmap_or(dst->high_slices, dst->high_slices, src->high_slices,
> + SLICE_NUM_HIGH);
> }
>
> static inline void slice_andnot_mask(struct slice_mask *dst, struct slice_mask *src)
> {
> dst->low_slices &= ~src->low_slices;
>
> - bitmap_andnot(dst->high_slices, dst->high_slices, src->high_slices,
> - SLICE_NUM_HIGH);
> + slice_bitmap_andnot(dst->high_slices, dst->high_slices,
> + src->high_slices, SLICE_NUM_HIGH);
> }
>
> #ifdef CONFIG_PPC_64K_PAGES
> @@ -446,14 +451,14 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len,
> * init different masks
> */
> mask.low_slices = 0;
> - bitmap_zero(mask.high_slices, SLICE_NUM_HIGH);
> + slice_bitmap_zero(mask.high_slices, SLICE_NUM_HIGH);
>
> /* silence stupid warning */;
> potential_mask.low_slices = 0;
> - bitmap_zero(potential_mask.high_slices, SLICE_NUM_HIGH);
> + slice_bitmap_zero(potential_mask.high_slices, SLICE_NUM_HIGH);
>
> compat_mask.low_slices = 0;
> - bitmap_zero(compat_mask.high_slices, SLICE_NUM_HIGH);
> + slice_bitmap_zero(compat_mask.high_slices, SLICE_NUM_HIGH);
>
> /* Sanity checks */
> BUG_ON(mm->task_size == 0);
> @@ -591,7 +596,8 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len,
> convert:
> slice_andnot_mask(&mask, &good_mask);
> slice_andnot_mask(&mask, &compat_mask);
> - if (mask.low_slices || !bitmap_empty(mask.high_slices, SLICE_NUM_HIGH)) {
> + if (mask.low_slices ||
> + !slice_bitmap_empty(mask.high_slices, SLICE_NUM_HIGH)) {
> slice_convert(mm, mask, psize);
> if (psize > MMU_PAGE_BASE)
> on_each_cpu(slice_flush_segments, mm, 1);
> --
> 2.13.3

Next message: Aneesh Kumar K.V: "Re: [PATCH v4 4/5] powerpc/mm/slice: Allow up to 64 low slices"
Previous message: Siva Reddy Kallam: "Re: tg3 crashes under high load, when using 100Mbits"
In reply to: Nicholas Piggin: "Re: [PATCH v4 2/5] powerpc/mm/slice: Enhance for supporting PPC32"
Next in thread: Christophe Leroy: "[PATCH v4 4/5] powerpc/mm/slice: Allow up to 64 low slices"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]