mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-11-01 08:58:07 +00:00
4cf5892495
Patch series "Add support for fast mremap".
This series speeds up the mremap(2) syscall by copying page tables at
the PMD level even for non-THP systems. There is concern that the extra
'address' argument that mremap passes to pte_alloc may do something
subtle architecture related in the future that may make the scheme not
work. Also we find that there is no point in passing the 'address' to
pte_alloc since its unused. This patch therefore removes this argument
tree-wide resulting in a nice negative diff as well. Also ensuring
along the way that the enabled architectures do not do anything funky
with the 'address' argument that goes unnoticed by the optimization.
Build and boot tested on x86-64. Build tested on arm64. The config
enablement patch for arm64 will be posted in the future after more
testing.
The changes were obtained by applying the following Coccinelle script.
(thanks Julia for answering all Coccinelle questions!).
Following fix ups were done manually:
* Removal of address argument from pte_fragment_alloc
* Removal of pte_alloc_one_fast definitions from m68k and microblaze.
// Options: --include-headers --no-includes
// Note: I split the 'identifier fn' line, so if you are manually
// running it, please unsplit it so it runs for you.
virtual patch
@pte_alloc_func_def depends on patch exists@
identifier E2;
identifier fn =~
"^(__pte_alloc|pte_alloc_one|pte_alloc|__pte_alloc_kernel|pte_alloc_one_kernel)$";
type T2;
@@
fn(...
- , T2 E2
)
{ ... }
@pte_alloc_func_proto_noarg depends on patch exists@
type T1, T2, T3, T4;
identifier fn =~ "^(__pte_alloc|pte_alloc_one|pte_alloc|__pte_alloc_kernel|pte_alloc_one_kernel)$";
@@
(
- T3 fn(T1, T2);
+ T3 fn(T1);
|
- T3 fn(T1, T2, T4);
+ T3 fn(T1, T2);
)
@pte_alloc_func_proto depends on patch exists@
identifier E1, E2, E4;
type T1, T2, T3, T4;
identifier fn =~
"^(__pte_alloc|pte_alloc_one|pte_alloc|__pte_alloc_kernel|pte_alloc_one_kernel)$";
@@
(
- T3 fn(T1 E1, T2 E2);
+ T3 fn(T1 E1);
|
- T3 fn(T1 E1, T2 E2, T4 E4);
+ T3 fn(T1 E1, T2 E2);
)
@pte_alloc_func_call depends on patch exists@
expression E2;
identifier fn =~
"^(__pte_alloc|pte_alloc_one|pte_alloc|__pte_alloc_kernel|pte_alloc_one_kernel)$";
@@
fn(...
-, E2
)
@pte_alloc_macro depends on patch exists@
identifier fn =~
"^(__pte_alloc|pte_alloc_one|pte_alloc|__pte_alloc_kernel|pte_alloc_one_kernel)$";
identifier a, b, c;
expression e;
position p;
@@
(
- #define fn(a, b, c) e
+ #define fn(a, b) e
|
- #define fn(a, b) e
+ #define fn(a) e
)
Link: http://lkml.kernel.org/r/20181108181201.88826-2-joelaf@google.com
Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Suggested-by: Kirill A. Shutemov <kirill@shutemov.name>
Acked-by: Kirill A. Shutemov <kirill@shutemov.name>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Julia Lawall <Julia.Lawall@lip6.fr>
Cc: Kirill A. Shutemov <kirill@shutemov.name>
Cc: William Kucharski <william.kucharski@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
157 lines
4.2 KiB
C
157 lines
4.2 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
/*
|
|
* S390 version
|
|
* Copyright IBM Corp. 1999, 2000
|
|
* Author(s): Hartmut Penner (hp@de.ibm.com)
|
|
* Martin Schwidefsky (schwidefsky@de.ibm.com)
|
|
*
|
|
* Derived from "include/asm-i386/pgalloc.h"
|
|
* Copyright (C) 1994 Linus Torvalds
|
|
*/
|
|
|
|
#ifndef _S390_PGALLOC_H
|
|
#define _S390_PGALLOC_H
|
|
|
|
#include <linux/threads.h>
|
|
#include <linux/string.h>
|
|
#include <linux/gfp.h>
|
|
#include <linux/mm.h>
|
|
|
|
#define CRST_ALLOC_ORDER 2
|
|
|
|
unsigned long *crst_table_alloc(struct mm_struct *);
|
|
void crst_table_free(struct mm_struct *, unsigned long *);
|
|
|
|
unsigned long *page_table_alloc(struct mm_struct *);
|
|
struct page *page_table_alloc_pgste(struct mm_struct *mm);
|
|
void page_table_free(struct mm_struct *, unsigned long *);
|
|
void page_table_free_rcu(struct mmu_gather *, unsigned long *, unsigned long);
|
|
void page_table_free_pgste(struct page *page);
|
|
extern int page_table_allocate_pgste;
|
|
|
|
static inline void crst_table_init(unsigned long *crst, unsigned long entry)
|
|
{
|
|
memset64((u64 *)crst, entry, _CRST_ENTRIES);
|
|
}
|
|
|
|
static inline unsigned long pgd_entry_type(struct mm_struct *mm)
|
|
{
|
|
if (mm_pmd_folded(mm))
|
|
return _SEGMENT_ENTRY_EMPTY;
|
|
if (mm_pud_folded(mm))
|
|
return _REGION3_ENTRY_EMPTY;
|
|
if (mm_p4d_folded(mm))
|
|
return _REGION2_ENTRY_EMPTY;
|
|
return _REGION1_ENTRY_EMPTY;
|
|
}
|
|
|
|
int crst_table_upgrade(struct mm_struct *mm, unsigned long limit);
|
|
void crst_table_downgrade(struct mm_struct *);
|
|
|
|
static inline p4d_t *p4d_alloc_one(struct mm_struct *mm, unsigned long address)
|
|
{
|
|
unsigned long *table = crst_table_alloc(mm);
|
|
|
|
if (table)
|
|
crst_table_init(table, _REGION2_ENTRY_EMPTY);
|
|
return (p4d_t *) table;
|
|
}
|
|
#define p4d_free(mm, p4d) crst_table_free(mm, (unsigned long *) p4d)
|
|
|
|
static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address)
|
|
{
|
|
unsigned long *table = crst_table_alloc(mm);
|
|
if (table)
|
|
crst_table_init(table, _REGION3_ENTRY_EMPTY);
|
|
return (pud_t *) table;
|
|
}
|
|
#define pud_free(mm, pud) crst_table_free(mm, (unsigned long *) pud)
|
|
|
|
static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long vmaddr)
|
|
{
|
|
unsigned long *table = crst_table_alloc(mm);
|
|
|
|
if (!table)
|
|
return NULL;
|
|
crst_table_init(table, _SEGMENT_ENTRY_EMPTY);
|
|
if (!pgtable_pmd_page_ctor(virt_to_page(table))) {
|
|
crst_table_free(mm, table);
|
|
return NULL;
|
|
}
|
|
return (pmd_t *) table;
|
|
}
|
|
|
|
static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
|
|
{
|
|
pgtable_pmd_page_dtor(virt_to_page(pmd));
|
|
crst_table_free(mm, (unsigned long *) pmd);
|
|
}
|
|
|
|
static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, p4d_t *p4d)
|
|
{
|
|
pgd_val(*pgd) = _REGION1_ENTRY | __pa(p4d);
|
|
}
|
|
|
|
static inline void p4d_populate(struct mm_struct *mm, p4d_t *p4d, pud_t *pud)
|
|
{
|
|
p4d_val(*p4d) = _REGION2_ENTRY | __pa(pud);
|
|
}
|
|
|
|
static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
|
|
{
|
|
pud_val(*pud) = _REGION3_ENTRY | __pa(pmd);
|
|
}
|
|
|
|
static inline pgd_t *pgd_alloc(struct mm_struct *mm)
|
|
{
|
|
unsigned long *table = crst_table_alloc(mm);
|
|
|
|
if (!table)
|
|
return NULL;
|
|
if (mm->context.asce_limit == _REGION3_SIZE) {
|
|
/* Forking a compat process with 2 page table levels */
|
|
if (!pgtable_pmd_page_ctor(virt_to_page(table))) {
|
|
crst_table_free(mm, table);
|
|
return NULL;
|
|
}
|
|
}
|
|
return (pgd_t *) table;
|
|
}
|
|
|
|
static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
|
|
{
|
|
if (mm->context.asce_limit == _REGION3_SIZE)
|
|
pgtable_pmd_page_dtor(virt_to_page(pgd));
|
|
crst_table_free(mm, (unsigned long *) pgd);
|
|
}
|
|
|
|
static inline void pmd_populate(struct mm_struct *mm,
|
|
pmd_t *pmd, pgtable_t pte)
|
|
{
|
|
pmd_val(*pmd) = _SEGMENT_ENTRY + __pa(pte);
|
|
}
|
|
|
|
#define pmd_populate_kernel(mm, pmd, pte) pmd_populate(mm, pmd, pte)
|
|
|
|
#define pmd_pgtable(pmd) \
|
|
(pgtable_t)(pmd_val(pmd) & -sizeof(pte_t)*PTRS_PER_PTE)
|
|
|
|
/*
|
|
* page table entry allocation/free routines.
|
|
*/
|
|
#define pte_alloc_one_kernel(mm) ((pte_t *)page_table_alloc(mm))
|
|
#define pte_alloc_one(mm) ((pte_t *)page_table_alloc(mm))
|
|
|
|
#define pte_free_kernel(mm, pte) page_table_free(mm, (unsigned long *) pte)
|
|
#define pte_free(mm, pte) page_table_free(mm, (unsigned long *) pte)
|
|
|
|
extern void rcu_table_freelist_finish(void);
|
|
|
|
void vmem_map_init(void);
|
|
void *vmem_crst_alloc(unsigned long val);
|
|
pte_t *vmem_pte_alloc(void);
|
|
|
|
unsigned long base_asce_alloc(unsigned long addr, unsigned long num_pages);
|
|
void base_asce_free(unsigned long asce);
|
|
|
|
#endif /* _S390_PGALLOC_H */
|