mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-28 04:45:12 +07:00
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>
115 lines
2.2 KiB
C
115 lines
2.2 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef _MOTOROLA_PGALLOC_H
|
|
#define _MOTOROLA_PGALLOC_H
|
|
|
|
#include <asm/tlb.h>
|
|
#include <asm/tlbflush.h>
|
|
|
|
extern pmd_t *get_pointer_table(void);
|
|
extern int free_pointer_table(pmd_t *);
|
|
|
|
static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm)
|
|
{
|
|
pte_t *pte;
|
|
|
|
pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_ZERO);
|
|
if (pte) {
|
|
__flush_page_to_ram(pte);
|
|
flush_tlb_kernel_page(pte);
|
|
nocache_page(pte);
|
|
}
|
|
|
|
return pte;
|
|
}
|
|
|
|
static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
|
|
{
|
|
cache_page(pte);
|
|
free_page((unsigned long) pte);
|
|
}
|
|
|
|
static inline pgtable_t pte_alloc_one(struct mm_struct *mm)
|
|
{
|
|
struct page *page;
|
|
pte_t *pte;
|
|
|
|
page = alloc_pages(GFP_KERNEL|__GFP_ZERO, 0);
|
|
if(!page)
|
|
return NULL;
|
|
if (!pgtable_page_ctor(page)) {
|
|
__free_page(page);
|
|
return NULL;
|
|
}
|
|
|
|
pte = kmap(page);
|
|
__flush_page_to_ram(pte);
|
|
flush_tlb_kernel_page(pte);
|
|
nocache_page(pte);
|
|
kunmap(page);
|
|
return page;
|
|
}
|
|
|
|
static inline void pte_free(struct mm_struct *mm, pgtable_t page)
|
|
{
|
|
pgtable_page_dtor(page);
|
|
cache_page(kmap(page));
|
|
kunmap(page);
|
|
__free_page(page);
|
|
}
|
|
|
|
static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t page,
|
|
unsigned long address)
|
|
{
|
|
pgtable_page_dtor(page);
|
|
cache_page(kmap(page));
|
|
kunmap(page);
|
|
__free_page(page);
|
|
}
|
|
|
|
|
|
static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address)
|
|
{
|
|
return get_pointer_table();
|
|
}
|
|
|
|
static inline int pmd_free(struct mm_struct *mm, pmd_t *pmd)
|
|
{
|
|
return free_pointer_table(pmd);
|
|
}
|
|
|
|
static inline int __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd,
|
|
unsigned long address)
|
|
{
|
|
return free_pointer_table(pmd);
|
|
}
|
|
|
|
|
|
static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
|
|
{
|
|
pmd_free(mm, (pmd_t *)pgd);
|
|
}
|
|
|
|
static inline pgd_t *pgd_alloc(struct mm_struct *mm)
|
|
{
|
|
return (pgd_t *)get_pointer_table();
|
|
}
|
|
|
|
|
|
static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, pte_t *pte)
|
|
{
|
|
pmd_set(pmd, pte);
|
|
}
|
|
|
|
static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, pgtable_t page)
|
|
{
|
|
pmd_set(pmd, page_address(page));
|
|
}
|
|
#define pmd_pgtable(pmd) pmd_page(pmd)
|
|
|
|
static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pmd_t *pmd)
|
|
{
|
|
pgd_set(pgd, pmd);
|
|
}
|
|
|
|
#endif /* _MOTOROLA_PGALLOC_H */
|