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>
158 lines
4.2 KiB
C
158 lines
4.2 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef _ASM_PGALLOC_H
|
|
#define _ASM_PGALLOC_H
|
|
|
|
#include <linux/gfp.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/threads.h>
|
|
#include <asm/processor.h>
|
|
#include <asm/fixmap.h>
|
|
|
|
#include <asm/cache.h>
|
|
|
|
/* Allocate the top level pgd (page directory)
|
|
*
|
|
* Here (for 64 bit kernels) we implement a Hybrid L2/L3 scheme: we
|
|
* allocate the first pmd adjacent to the pgd. This means that we can
|
|
* subtract a constant offset to get to it. The pmd and pgd sizes are
|
|
* arranged so that a single pmd covers 4GB (giving a full 64-bit
|
|
* process access to 8TB) so our lookups are effectively L2 for the
|
|
* first 4GB of the kernel (i.e. for all ILP32 processes and all the
|
|
* kernel for machines with under 4GB of memory) */
|
|
static inline pgd_t *pgd_alloc(struct mm_struct *mm)
|
|
{
|
|
pgd_t *pgd = (pgd_t *)__get_free_pages(GFP_KERNEL,
|
|
PGD_ALLOC_ORDER);
|
|
pgd_t *actual_pgd = pgd;
|
|
|
|
if (likely(pgd != NULL)) {
|
|
memset(pgd, 0, PAGE_SIZE<<PGD_ALLOC_ORDER);
|
|
#if CONFIG_PGTABLE_LEVELS == 3
|
|
actual_pgd += PTRS_PER_PGD;
|
|
/* Populate first pmd with allocated memory. We mark it
|
|
* with PxD_FLAG_ATTACHED as a signal to the system that this
|
|
* pmd entry may not be cleared. */
|
|
__pgd_val_set(*actual_pgd, (PxD_FLAG_PRESENT |
|
|
PxD_FLAG_VALID |
|
|
PxD_FLAG_ATTACHED)
|
|
+ (__u32)(__pa((unsigned long)pgd) >> PxD_VALUE_SHIFT));
|
|
/* The first pmd entry also is marked with PxD_FLAG_ATTACHED as
|
|
* a signal that this pmd may not be freed */
|
|
__pgd_val_set(*pgd, PxD_FLAG_ATTACHED);
|
|
#endif
|
|
}
|
|
return actual_pgd;
|
|
}
|
|
|
|
static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
|
|
{
|
|
#if CONFIG_PGTABLE_LEVELS == 3
|
|
pgd -= PTRS_PER_PGD;
|
|
#endif
|
|
free_pages((unsigned long)pgd, PGD_ALLOC_ORDER);
|
|
}
|
|
|
|
#if CONFIG_PGTABLE_LEVELS == 3
|
|
|
|
/* Three Level Page Table Support for pmd's */
|
|
|
|
static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pmd_t *pmd)
|
|
{
|
|
__pgd_val_set(*pgd, (PxD_FLAG_PRESENT | PxD_FLAG_VALID) +
|
|
(__u32)(__pa((unsigned long)pmd) >> PxD_VALUE_SHIFT));
|
|
}
|
|
|
|
static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address)
|
|
{
|
|
pmd_t *pmd = (pmd_t *)__get_free_pages(GFP_KERNEL, PMD_ORDER);
|
|
if (pmd)
|
|
memset(pmd, 0, PAGE_SIZE<<PMD_ORDER);
|
|
return pmd;
|
|
}
|
|
|
|
static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
|
|
{
|
|
if (pmd_flag(*pmd) & PxD_FLAG_ATTACHED) {
|
|
/*
|
|
* This is the permanent pmd attached to the pgd;
|
|
* cannot free it.
|
|
* Increment the counter to compensate for the decrement
|
|
* done by generic mm code.
|
|
*/
|
|
mm_inc_nr_pmds(mm);
|
|
return;
|
|
}
|
|
free_pages((unsigned long)pmd, PMD_ORDER);
|
|
}
|
|
|
|
#else
|
|
|
|
/* Two Level Page Table Support for pmd's */
|
|
|
|
/*
|
|
* allocating and freeing a pmd is trivial: the 1-entry pmd is
|
|
* inside the pgd, so has no extra memory associated with it.
|
|
*/
|
|
|
|
#define pmd_alloc_one(mm, addr) ({ BUG(); ((pmd_t *)2); })
|
|
#define pmd_free(mm, x) do { } while (0)
|
|
#define pgd_populate(mm, pmd, pte) BUG()
|
|
|
|
#endif
|
|
|
|
static inline void
|
|
pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, pte_t *pte)
|
|
{
|
|
#if CONFIG_PGTABLE_LEVELS == 3
|
|
/* preserve the gateway marker if this is the beginning of
|
|
* the permanent pmd */
|
|
if(pmd_flag(*pmd) & PxD_FLAG_ATTACHED)
|
|
__pmd_val_set(*pmd, (PxD_FLAG_PRESENT |
|
|
PxD_FLAG_VALID |
|
|
PxD_FLAG_ATTACHED)
|
|
+ (__u32)(__pa((unsigned long)pte) >> PxD_VALUE_SHIFT));
|
|
else
|
|
#endif
|
|
__pmd_val_set(*pmd, (PxD_FLAG_PRESENT | PxD_FLAG_VALID)
|
|
+ (__u32)(__pa((unsigned long)pte) >> PxD_VALUE_SHIFT));
|
|
}
|
|
|
|
#define pmd_populate(mm, pmd, pte_page) \
|
|
pmd_populate_kernel(mm, pmd, page_address(pte_page))
|
|
#define pmd_pgtable(pmd) pmd_page(pmd)
|
|
|
|
static inline pgtable_t
|
|
pte_alloc_one(struct mm_struct *mm)
|
|
{
|
|
struct page *page = alloc_page(GFP_KERNEL|__GFP_ZERO);
|
|
if (!page)
|
|
return NULL;
|
|
if (!pgtable_page_ctor(page)) {
|
|
__free_page(page);
|
|
return NULL;
|
|
}
|
|
return page;
|
|
}
|
|
|
|
static inline pte_t *
|
|
pte_alloc_one_kernel(struct mm_struct *mm)
|
|
{
|
|
pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_ZERO);
|
|
return pte;
|
|
}
|
|
|
|
static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
|
|
{
|
|
free_page((unsigned long)pte);
|
|
}
|
|
|
|
static inline void pte_free(struct mm_struct *mm, struct page *pte)
|
|
{
|
|
pgtable_page_dtor(pte);
|
|
pte_free_kernel(mm, page_address(pte));
|
|
}
|
|
|
|
#define check_pgt_cache() do { } while (0)
|
|
|
|
#endif
|