mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-11-26 09:20:54 +07:00
fc2acab31b
zap_pte_range has been counting the pages it frees in tlb->freed, then tlb_finish_mmu has used that to update the mm's rss. That got stranger when I added anon_rss, yet updated it by a different route; and stranger when rss and anon_rss became mm_counters with special access macros. And it would no longer be viable if we're relying on page_table_lock to stabilize the mm_counter, but calling tlb_finish_mmu outside that lock. Remove the mmu_gather's freed field, let tlb_finish_mmu stick to its own business, just decrement the rss mm_counter in zap_pte_range (yes, there was some point to batching the update, and a subsequent patch restores that). And forget the anal paranoia of first reading the counter to avoid going negative - if rss does go negative, just fix that bug. Remove the mmu_gather's flushes and avoided_flushes from arm and arm26: no use was being made of them. But arm26 alone was actually using the freed, in the way some others use need_flush: give it a need_flush. arm26 seems to prefer spaces to tabs here: respect that. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
86 lines
2.1 KiB
C
86 lines
2.1 KiB
C
/*
|
|
* linux/include/asm-arm/tlb.h
|
|
*
|
|
* Copyright (C) 2002 Russell King
|
|
*
|
|
* This program is free software; you can redistribute it and/or modify
|
|
* it under the terms of the GNU General Public License version 2 as
|
|
* published by the Free Software Foundation.
|
|
*
|
|
* Experimentation shows that on a StrongARM, it appears to be faster
|
|
* to use the "invalidate whole tlb" rather than "invalidate single
|
|
* tlb" for this.
|
|
*
|
|
* This appears true for both the process fork+exit case, as well as
|
|
* the munmap-large-area case.
|
|
*/
|
|
#ifndef __ASMARM_TLB_H
|
|
#define __ASMARM_TLB_H
|
|
|
|
#include <asm/cacheflush.h>
|
|
#include <asm/tlbflush.h>
|
|
#include <asm/pgalloc.h>
|
|
|
|
/*
|
|
* TLB handling. This allows us to remove pages from the page
|
|
* tables, and efficiently handle the TLB issues.
|
|
*/
|
|
struct mmu_gather {
|
|
struct mm_struct *mm;
|
|
unsigned int fullmm;
|
|
};
|
|
|
|
DECLARE_PER_CPU(struct mmu_gather, mmu_gathers);
|
|
|
|
static inline struct mmu_gather *
|
|
tlb_gather_mmu(struct mm_struct *mm, unsigned int full_mm_flush)
|
|
{
|
|
struct mmu_gather *tlb = &get_cpu_var(mmu_gathers);
|
|
|
|
tlb->mm = mm;
|
|
tlb->fullmm = full_mm_flush;
|
|
|
|
return tlb;
|
|
}
|
|
|
|
static inline void
|
|
tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end)
|
|
{
|
|
if (tlb->fullmm)
|
|
flush_tlb_mm(tlb->mm);
|
|
|
|
/* keep the page table cache within bounds */
|
|
check_pgt_cache();
|
|
|
|
put_cpu_var(mmu_gathers);
|
|
}
|
|
|
|
#define tlb_remove_tlb_entry(tlb,ptep,address) do { } while (0)
|
|
|
|
/*
|
|
* In the case of tlb vma handling, we can optimise these away in the
|
|
* case where we're doing a full MM flush. When we're doing a munmap,
|
|
* the vmas are adjusted to only cover the region to be torn down.
|
|
*/
|
|
static inline void
|
|
tlb_start_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
|
|
{
|
|
if (!tlb->fullmm)
|
|
flush_cache_range(vma, vma->vm_start, vma->vm_end);
|
|
}
|
|
|
|
static inline void
|
|
tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
|
|
{
|
|
if (!tlb->fullmm)
|
|
flush_tlb_range(vma, vma->vm_start, vma->vm_end);
|
|
}
|
|
|
|
#define tlb_remove_page(tlb,page) free_page_and_swap_cache(page)
|
|
#define pte_free_tlb(tlb,ptep) pte_free(ptep)
|
|
#define pmd_free_tlb(tlb,pmdp) pmd_free(pmdp)
|
|
|
|
#define tlb_migrate_finish(mm) do { } while (0)
|
|
|
|
#endif
|