mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-10-30 16:07:39 +00:00
7fccfc00c0
When unmapping N pages (e.g. shared memory) the amount of TLB flushes done can be (N*PAGE_SIZE/ZAP_BLOCK_SIZE)*N although it should be N at maximum. With PREEMPT kernel ZAP_BLOCK_SIZE is 8 pages, so there is a noticeable performance penalty when unmapping a large VMA and the system is spending its time in flush_tlb_range(). The problem is that tlb_end_vma() is always flushing the full VMA range. The subrange that needs to be flushed can be calculated by tlb_remove_tlb_entry(). This approach was suggested by Hugh Dickins, and is also used by other arches. The speed increase is roughly 3x for 8M mappings and for larger mappings even more. Signed-off-by: Aaro Koskinen <Aaro.Koskinen@nokia.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
111 lines
2.7 KiB
C
111 lines
2.7 KiB
C
/*
|
|
* arch/arm/include/asm/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>
|
|
|
|
#ifndef CONFIG_MMU
|
|
|
|
#include <linux/pagemap.h>
|
|
#include <asm-generic/tlb.h>
|
|
|
|
#else /* !CONFIG_MMU */
|
|
|
|
#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;
|
|
unsigned long range_start;
|
|
unsigned long range_end;
|
|
};
|
|
|
|
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);
|
|
}
|
|
|
|
/*
|
|
* Memorize the range for the TLB flush.
|
|
*/
|
|
static inline void
|
|
tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep, unsigned long addr)
|
|
{
|
|
if (!tlb->fullmm) {
|
|
if (addr < tlb->range_start)
|
|
tlb->range_start = addr;
|
|
if (addr + PAGE_SIZE > tlb->range_end)
|
|
tlb->range_end = addr + PAGE_SIZE;
|
|
}
|
|
}
|
|
|
|
/*
|
|
* 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);
|
|
tlb->range_start = TASK_SIZE;
|
|
tlb->range_end = 0;
|
|
}
|
|
}
|
|
|
|
static inline void
|
|
tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
|
|
{
|
|
if (!tlb->fullmm && tlb->range_end > 0)
|
|
flush_tlb_range(vma, tlb->range_start, tlb->range_end);
|
|
}
|
|
|
|
#define tlb_remove_page(tlb,page) free_page_and_swap_cache(page)
|
|
#define pte_free_tlb(tlb, ptep) pte_free((tlb)->mm, ptep)
|
|
#define pmd_free_tlb(tlb, pmdp) pmd_free((tlb)->mm, pmdp)
|
|
|
|
#define tlb_migrate_finish(mm) do { } while (0)
|
|
|
|
#endif /* CONFIG_MMU */
|
|
#endif
|