Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit cf9427b8 authored by Aneesh Kumar K.V's avatar Aneesh Kumar K.V Committed by Benjamin Herrenschmidt
Browse files

powerpc: New hugepage directory format 



Change the hugepage directory format so that we can have leaf ptes directly
at page directory avoiding the allocation of hugepage directory.

With the new table format we have 3 cases for pgds and pmds:
(1) invalid (all zeroes)
(2) pointer to next table, as normal; bottom 6 bits == 0
(4) hugepd pointer, bottom two bits == 00, next 4 bits indicate size of table

Instead of storing shift value in hugepd pointer we use mmu_psize_def index
so that we can fit all the supported hugepage size in 4 bits

Signed-off-by: default avatarAneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Acked-by: default avatarPaul Mackerras <paulus@samba.org>
Signed-off-by: default avatarBenjamin Herrenschmidt <benh@kernel.crashing.org>
parent 0e5f35d0

arch/powerpc/include/asm/hugetlb.h

+30 −0
Original line number Diff line number Diff line
@@ -6,6 +6,33 @@ 


extern struct kmem_cache *hugepte_cache;



#ifdef CONFIG_PPC_BOOK3S_64

/*

 * This should work for other subarchs too. But right now we use the

 * new format only for 64bit book3s

 */

static inline pte_t *hugepd_page(hugepd_t hpd)

{

	BUG_ON(!hugepd_ok(hpd));

	/*

	 * We have only four bits to encode, MMU page size

	 */

	BUILD_BUG_ON((MMU_PAGE_COUNT - 1) > 0xf);

	return (pte_t *)(hpd.pd & ~HUGEPD_SHIFT_MASK);

}



static inline unsigned int hugepd_mmu_psize(hugepd_t hpd)

{

	return (hpd.pd & HUGEPD_SHIFT_MASK) >> 2;

}



static inline unsigned int hugepd_shift(hugepd_t hpd)

{

	return mmu_psize_to_shift(hugepd_mmu_psize(hpd));

}



#else



static inline pte_t *hugepd_page(hugepd_t hpd)

{

	BUG_ON(!hugepd_ok(hpd));
@@ -17,6 +44,9 @@ static inline unsigned int hugepd_shift(hugepd_t hpd) 
	return hpd.pd & HUGEPD_SHIFT_MASK;

}



#endif /* CONFIG_PPC_BOOK3S_64 */





static inline pte_t *hugepte_offset(hugepd_t *hpdp, unsigned long addr,

				    unsigned pdshift)

{

arch/powerpc/include/asm/mmu-hash64.h

+19 −1
Original line number Diff line number Diff line
@@ -21,6 +21,7 @@ 
 * complete pgtable.h but only a portion of it.

 */

#include <asm/pgtable-ppc64.h>

#include <asm/bug.h>



/*

 * Segment table
@@ -159,6 +160,24 @@ struct mmu_psize_def 
	unsigned long	avpnm;	/* bits to mask out in AVPN in the HPTE */

	unsigned long	sllp;	/* SLB L||LP (exact mask to use in slbmte) */

};

extern struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT];



static inline int shift_to_mmu_psize(unsigned int shift)

{

	int psize;



	for (psize = 0; psize < MMU_PAGE_COUNT; ++psize)

		if (mmu_psize_defs[psize].shift == shift)

			return psize;

	return -1;

}



static inline unsigned int mmu_psize_to_shift(unsigned int mmu_psize)

{

	if (mmu_psize_defs[mmu_psize].shift)

		return mmu_psize_defs[mmu_psize].shift;

	BUG();

}



#endif /* __ASSEMBLY__ */
@@ -193,7 +212,6 @@ static inline int segment_shift(int ssize) 
/*

 * The current system page and segment sizes

 */

extern struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT];

extern int mmu_linear_psize;

extern int mmu_virtual_psize;

extern int mmu_vmalloc_psize;

arch/powerpc/include/asm/page.h

+13 −0
Original line number Diff line number Diff line
@@ -249,6 +249,7 @@ extern long long virt_phys_offset; 
#define is_kernel_addr(x)	((x) >= PAGE_OFFSET)

#endif



#ifndef CONFIG_PPC_BOOK3S_64

/*

 * Use the top bit of the higher-level page table entries to indicate whether

 * the entries we point to contain hugepages.  This works because we know that
@@ -260,6 +261,7 @@ extern long long virt_phys_offset; 
#else

#define PD_HUGE 0x80000000

#endif

#endif /* CONFIG_PPC_BOOK3S_64 */



/*

 * Some number of bits at the level of the page table that points to
@@ -354,10 +356,21 @@ typedef unsigned long pgprot_t; 
typedef struct { signed long pd; } hugepd_t;



#ifdef CONFIG_HUGETLB_PAGE

#ifdef CONFIG_PPC_BOOK3S_64

static inline int hugepd_ok(hugepd_t hpd)

{

	/*

	 * hugepd pointer, bottom two bits == 00 and next 4 bits

	 * indicate size of table

	 */

	return (((hpd.pd & 0x3) == 0x0) && ((hpd.pd & HUGEPD_SHIFT_MASK) != 0));

}

#else

static inline int hugepd_ok(hugepd_t hpd)

{

	return (hpd.pd > 0);

}

#endif



#define is_hugepd(pdep)               (hugepd_ok(*((hugepd_t *)(pdep))))

#else /* CONFIG_HUGETLB_PAGE */

arch/powerpc/include/asm/pgalloc-64.h

+4 −1
Original line number Diff line number Diff line
@@ -35,7 +35,10 @@ struct vmemmap_backing { 
#define MAX_PGTABLE_INDEX_SIZE	0xf



extern struct kmem_cache *pgtable_cache[];

#define PGT_CACHE(shift) (pgtable_cache[(shift)-1])

#define PGT_CACHE(shift) ({				\

			BUG_ON(!(shift));		\

			pgtable_cache[(shift) - 1];	\

		})



static inline pgd_t *pgd_alloc(struct mm_struct *mm)

{

arch/powerpc/mm/hugetlbpage.c

+8 −18
Original line number Diff line number Diff line
@@ -48,23 +48,6 @@ static u64 gpage_freearray[MAX_NUMBER_GPAGES]; 
static unsigned nr_gpages;

#endif



static inline int shift_to_mmu_psize(unsigned int shift)

{

	int psize;



	for (psize = 0; psize < MMU_PAGE_COUNT; ++psize)

		if (mmu_psize_defs[psize].shift == shift)

			return psize;

	return -1;

}



static inline unsigned int mmu_psize_to_shift(unsigned int mmu_psize)

{

	if (mmu_psize_defs[mmu_psize].shift)

		return mmu_psize_defs[mmu_psize].shift;

	BUG();

}



#define hugepd_none(hpd)	((hpd).pd == 0)



pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, unsigned *shift)
@@ -145,6 +128,7 @@ static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp, 
		if (unlikely(!hugepd_none(*hpdp)))

			break;

		else

			/* We use the old format for PPC_FSL_BOOK3E */

			hpdp->pd = ((unsigned long)new & ~PD_HUGE) | pshift;

	}

	/* If we bailed from the for loop early, an error occurred, clean up */
@@ -156,8 +140,14 @@ static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp, 
#else

	if (!hugepd_none(*hpdp))

		kmem_cache_free(cachep, new);

	else

	else {

#ifdef CONFIG_PPC_BOOK3S_64

		hpdp->pd = (unsigned long)new |

			    (shift_to_mmu_psize(pshift) << 2);

#else

		hpdp->pd = ((unsigned long)new & ~PD_HUGE) | pshift;

#endif

	}

#endif

	spin_unlock(&mm->page_table_lock);

	return 0;