32cc0b7c9d
Add powerpc-specific pte_free_defer(), to free table page via call_rcu(). pte_free_defer() will be called inside khugepaged's retract_page_tables() loop, where allocating extra memory cannot be relied upon. This precedes the generic version to avoid build breakage from incompatible pgtable_t. This is awkward because the struct page contains only one rcu_head, but that page may be shared between PTE_FRAG_NR pagetables, each wanting to use the rcu_head at the same time. But powerpc never reuses a fragment once it has been freed: so mark the page Active in pte_free_defer(), before calling pte_fragment_free() directly; and there call_rcu() to pte_free_now() when last fragment is freed and the page is PageActive. Link: https://lkml.kernel.org/r/6e3ca5f1-334d-4b14-b92d-fc8e99914fcb@google.com Suggested-by: Jason Gunthorpe <jgg@ziepe.ca> Signed-off-by: Hugh Dickins <hughd@google.com> Cc: Alexander Gordeev <agordeev@linux.ibm.com> Cc: Alistair Popple <apopple@nvidia.com> Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com> Cc: Anshuman Khandual <anshuman.khandual@arm.com> Cc: Axel Rasmussen <axelrasmussen@google.com> Cc: Christian Borntraeger <borntraeger@linux.ibm.com> Cc: Christophe Leroy <christophe.leroy@csgroup.eu> Cc: Christoph Hellwig <hch@infradead.org> Cc: Claudio Imbrenda <imbrenda@linux.ibm.com> Cc: David Hildenbrand <david@redhat.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com> Cc: Heiko Carstens <hca@linux.ibm.com> Cc: Huang, Ying <ying.huang@intel.com> Cc: Ira Weiny <ira.weiny@intel.com> Cc: Jann Horn <jannh@google.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Lorenzo Stoakes <lstoakes@gmail.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Mike Rapoport (IBM) <rppt@kernel.org> Cc: Minchan Kim <minchan@kernel.org> Cc: Naoya Horiguchi <naoya.horiguchi@nec.com> Cc: Pavel Tatashin <pasha.tatashin@soleen.com> Cc: Peter Xu <peterx@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Qi Zheng <zhengqi.arch@bytedance.com> Cc: Ralph Campbell <rcampbell@nvidia.com> Cc: Russell King <linux@armlinux.org.uk> Cc: SeongJae Park <sj@kernel.org> Cc: Song Liu <song@kernel.org> Cc: Steven Price <steven.price@arm.com> Cc: Suren Baghdasaryan <surenb@google.com> Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com> Cc: Vasily Gorbik <gor@linux.ibm.com> Cc: Vishal Moola (Oracle) <vishal.moola@gmail.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Will Deacon <will@kernel.org> Cc: Yang Shi <shy828301@gmail.com> Cc: Yu Zhao <yuzhao@google.com> Cc: Zack Rusin <zackr@vmware.com> Cc: Zi Yan <ziy@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
78 lines
2.2 KiB
C
78 lines
2.2 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef _ASM_POWERPC_PGALLOC_H
|
|
#define _ASM_POWERPC_PGALLOC_H
|
|
|
|
#include <linux/mm.h>
|
|
|
|
#ifndef MODULE
|
|
static inline gfp_t pgtable_gfp_flags(struct mm_struct *mm, gfp_t gfp)
|
|
{
|
|
if (unlikely(mm == &init_mm))
|
|
return gfp;
|
|
return gfp | __GFP_ACCOUNT;
|
|
}
|
|
#else /* !MODULE */
|
|
static inline gfp_t pgtable_gfp_flags(struct mm_struct *mm, gfp_t gfp)
|
|
{
|
|
return gfp | __GFP_ACCOUNT;
|
|
}
|
|
#endif /* MODULE */
|
|
|
|
#define PGALLOC_GFP (GFP_KERNEL | __GFP_ZERO)
|
|
|
|
pte_t *pte_fragment_alloc(struct mm_struct *mm, int kernel);
|
|
|
|
static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm)
|
|
{
|
|
return (pte_t *)pte_fragment_alloc(mm, 1);
|
|
}
|
|
|
|
static inline pgtable_t pte_alloc_one(struct mm_struct *mm)
|
|
{
|
|
return (pgtable_t)pte_fragment_alloc(mm, 0);
|
|
}
|
|
|
|
void pte_frag_destroy(void *pte_frag);
|
|
void pte_fragment_free(unsigned long *table, int kernel);
|
|
|
|
static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
|
|
{
|
|
pte_fragment_free((unsigned long *)pte, 1);
|
|
}
|
|
|
|
static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage)
|
|
{
|
|
pte_fragment_free((unsigned long *)ptepage, 0);
|
|
}
|
|
|
|
/* arch use pte_free_defer() implementation in arch/powerpc/mm/pgtable-frag.c */
|
|
#define pte_free_defer pte_free_defer
|
|
void pte_free_defer(struct mm_struct *mm, pgtable_t pgtable);
|
|
|
|
/*
|
|
* Functions that deal with pagetables that could be at any level of
|
|
* the table need to be passed an "index_size" so they know how to
|
|
* handle allocation. For PTE pages, the allocation size will be
|
|
* (2^index_size * sizeof(pointer)) and allocations are drawn from
|
|
* the kmem_cache in PGT_CACHE(index_size).
|
|
*
|
|
* The maximum index size needs to be big enough to allow any
|
|
* pagetable sizes we need, but small enough to fit in the low bits of
|
|
* any page table pointer. In other words all pagetables, even tiny
|
|
* ones, must be aligned to allow at least enough low 0 bits to
|
|
* contain this value. This value is also used as a mask, so it must
|
|
* be one less than a power of two.
|
|
*/
|
|
#define MAX_PGTABLE_INDEX_SIZE 0xf
|
|
|
|
extern struct kmem_cache *pgtable_cache[];
|
|
#define PGT_CACHE(shift) pgtable_cache[shift]
|
|
|
|
#ifdef CONFIG_PPC_BOOK3S
|
|
#include <asm/book3s/pgalloc.h>
|
|
#else
|
|
#include <asm/nohash/pgalloc.h>
|
|
#endif
|
|
|
|
#endif /* _ASM_POWERPC_PGALLOC_H */
|