mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-28 11:18:45 +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>
240 lines
5.4 KiB
C
240 lines
5.4 KiB
C
/*
|
|
* Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
|
|
* Licensed under the GPL
|
|
*/
|
|
|
|
#include <linux/stddef.h>
|
|
#include <linux/module.h>
|
|
#include <linux/memblock.h>
|
|
#include <linux/highmem.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/swap.h>
|
|
#include <linux/slab.h>
|
|
#include <asm/fixmap.h>
|
|
#include <asm/page.h>
|
|
#include <as-layout.h>
|
|
#include <init.h>
|
|
#include <kern.h>
|
|
#include <kern_util.h>
|
|
#include <mem_user.h>
|
|
#include <os.h>
|
|
|
|
/* allocated in paging_init, zeroed in mem_init, and unchanged thereafter */
|
|
unsigned long *empty_zero_page = NULL;
|
|
EXPORT_SYMBOL(empty_zero_page);
|
|
|
|
/*
|
|
* Initialized during boot, and readonly for initializing page tables
|
|
* afterwards
|
|
*/
|
|
pgd_t swapper_pg_dir[PTRS_PER_PGD];
|
|
|
|
/* Initialized at boot time, and readonly after that */
|
|
unsigned long long highmem;
|
|
int kmalloc_ok = 0;
|
|
|
|
/* Used during early boot */
|
|
static unsigned long brk_end;
|
|
|
|
void __init mem_init(void)
|
|
{
|
|
/* clear the zero-page */
|
|
memset(empty_zero_page, 0, PAGE_SIZE);
|
|
|
|
/* Map in the area just after the brk now that kmalloc is about
|
|
* to be turned on.
|
|
*/
|
|
brk_end = (unsigned long) UML_ROUND_UP(sbrk(0));
|
|
map_memory(brk_end, __pa(brk_end), uml_reserved - brk_end, 1, 1, 0);
|
|
memblock_free(__pa(brk_end), uml_reserved - brk_end);
|
|
uml_reserved = brk_end;
|
|
|
|
/* this will put all low memory onto the freelists */
|
|
memblock_free_all();
|
|
max_low_pfn = totalram_pages();
|
|
max_pfn = max_low_pfn;
|
|
mem_init_print_info(NULL);
|
|
kmalloc_ok = 1;
|
|
}
|
|
|
|
/*
|
|
* Create a page table and place a pointer to it in a middle page
|
|
* directory entry.
|
|
*/
|
|
static void __init one_page_table_init(pmd_t *pmd)
|
|
{
|
|
if (pmd_none(*pmd)) {
|
|
pte_t *pte = (pte_t *) memblock_alloc_low(PAGE_SIZE,
|
|
PAGE_SIZE);
|
|
set_pmd(pmd, __pmd(_KERNPG_TABLE +
|
|
(unsigned long) __pa(pte)));
|
|
if (pte != pte_offset_kernel(pmd, 0))
|
|
BUG();
|
|
}
|
|
}
|
|
|
|
static void __init one_md_table_init(pud_t *pud)
|
|
{
|
|
#ifdef CONFIG_3_LEVEL_PGTABLES
|
|
pmd_t *pmd_table = (pmd_t *) memblock_alloc_low(PAGE_SIZE, PAGE_SIZE);
|
|
set_pud(pud, __pud(_KERNPG_TABLE + (unsigned long) __pa(pmd_table)));
|
|
if (pmd_table != pmd_offset(pud, 0))
|
|
BUG();
|
|
#endif
|
|
}
|
|
|
|
static void __init fixrange_init(unsigned long start, unsigned long end,
|
|
pgd_t *pgd_base)
|
|
{
|
|
pgd_t *pgd;
|
|
pud_t *pud;
|
|
pmd_t *pmd;
|
|
int i, j;
|
|
unsigned long vaddr;
|
|
|
|
vaddr = start;
|
|
i = pgd_index(vaddr);
|
|
j = pmd_index(vaddr);
|
|
pgd = pgd_base + i;
|
|
|
|
for ( ; (i < PTRS_PER_PGD) && (vaddr < end); pgd++, i++) {
|
|
pud = pud_offset(pgd, vaddr);
|
|
if (pud_none(*pud))
|
|
one_md_table_init(pud);
|
|
pmd = pmd_offset(pud, vaddr);
|
|
for (; (j < PTRS_PER_PMD) && (vaddr < end); pmd++, j++) {
|
|
one_page_table_init(pmd);
|
|
vaddr += PMD_SIZE;
|
|
}
|
|
j = 0;
|
|
}
|
|
}
|
|
|
|
static void __init fixaddr_user_init( void)
|
|
{
|
|
#ifdef CONFIG_ARCH_REUSE_HOST_VSYSCALL_AREA
|
|
long size = FIXADDR_USER_END - FIXADDR_USER_START;
|
|
pgd_t *pgd;
|
|
pud_t *pud;
|
|
pmd_t *pmd;
|
|
pte_t *pte;
|
|
phys_t p;
|
|
unsigned long v, vaddr = FIXADDR_USER_START;
|
|
|
|
if (!size)
|
|
return;
|
|
|
|
fixrange_init( FIXADDR_USER_START, FIXADDR_USER_END, swapper_pg_dir);
|
|
v = (unsigned long) memblock_alloc_low(size, PAGE_SIZE);
|
|
memcpy((void *) v , (void *) FIXADDR_USER_START, size);
|
|
p = __pa(v);
|
|
for ( ; size > 0; size -= PAGE_SIZE, vaddr += PAGE_SIZE,
|
|
p += PAGE_SIZE) {
|
|
pgd = swapper_pg_dir + pgd_index(vaddr);
|
|
pud = pud_offset(pgd, vaddr);
|
|
pmd = pmd_offset(pud, vaddr);
|
|
pte = pte_offset_kernel(pmd, vaddr);
|
|
pte_set_val(*pte, p, PAGE_READONLY);
|
|
}
|
|
#endif
|
|
}
|
|
|
|
void __init paging_init(void)
|
|
{
|
|
unsigned long zones_size[MAX_NR_ZONES], vaddr;
|
|
int i;
|
|
|
|
empty_zero_page = (unsigned long *) memblock_alloc_low(PAGE_SIZE,
|
|
PAGE_SIZE);
|
|
for (i = 0; i < ARRAY_SIZE(zones_size); i++)
|
|
zones_size[i] = 0;
|
|
|
|
zones_size[ZONE_NORMAL] = (end_iomem >> PAGE_SHIFT) -
|
|
(uml_physmem >> PAGE_SHIFT);
|
|
free_area_init(zones_size);
|
|
|
|
/*
|
|
* Fixed mappings, only the page table structure has to be
|
|
* created - mappings will be set by set_fixmap():
|
|
*/
|
|
vaddr = __fix_to_virt(__end_of_fixed_addresses - 1) & PMD_MASK;
|
|
fixrange_init(vaddr, FIXADDR_TOP, swapper_pg_dir);
|
|
|
|
fixaddr_user_init();
|
|
}
|
|
|
|
/*
|
|
* This can't do anything because nothing in the kernel image can be freed
|
|
* since it's not in kernel physical memory.
|
|
*/
|
|
|
|
void free_initmem(void)
|
|
{
|
|
}
|
|
|
|
#ifdef CONFIG_BLK_DEV_INITRD
|
|
void free_initrd_mem(unsigned long start, unsigned long end)
|
|
{
|
|
free_reserved_area((void *)start, (void *)end, -1, "initrd");
|
|
}
|
|
#endif
|
|
|
|
/* Allocate and free page tables. */
|
|
|
|
pgd_t *pgd_alloc(struct mm_struct *mm)
|
|
{
|
|
pgd_t *pgd = (pgd_t *)__get_free_page(GFP_KERNEL);
|
|
|
|
if (pgd) {
|
|
memset(pgd, 0, USER_PTRS_PER_PGD * sizeof(pgd_t));
|
|
memcpy(pgd + USER_PTRS_PER_PGD,
|
|
swapper_pg_dir + USER_PTRS_PER_PGD,
|
|
(PTRS_PER_PGD - USER_PTRS_PER_PGD) * sizeof(pgd_t));
|
|
}
|
|
return pgd;
|
|
}
|
|
|
|
void pgd_free(struct mm_struct *mm, pgd_t *pgd)
|
|
{
|
|
free_page((unsigned long) pgd);
|
|
}
|
|
|
|
pte_t *pte_alloc_one_kernel(struct mm_struct *mm)
|
|
{
|
|
pte_t *pte;
|
|
|
|
pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_ZERO);
|
|
return pte;
|
|
}
|
|
|
|
pgtable_t pte_alloc_one(struct mm_struct *mm)
|
|
{
|
|
struct page *pte;
|
|
|
|
pte = alloc_page(GFP_KERNEL|__GFP_ZERO);
|
|
if (!pte)
|
|
return NULL;
|
|
if (!pgtable_page_ctor(pte)) {
|
|
__free_page(pte);
|
|
return NULL;
|
|
}
|
|
return pte;
|
|
}
|
|
|
|
#ifdef CONFIG_3_LEVEL_PGTABLES
|
|
pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address)
|
|
{
|
|
pmd_t *pmd = (pmd_t *) __get_free_page(GFP_KERNEL);
|
|
|
|
if (pmd)
|
|
memset(pmd, 0, PAGE_SIZE);
|
|
|
|
return pmd;
|
|
}
|
|
#endif
|
|
|
|
void *uml_kmalloc(int size, int flags)
|
|
{
|
|
return kmalloc(size, flags);
|
|
}
|