3f31f748a8
This change is inspired by the Peter's proposal patch [1] which was protecting the VMA using SRCU. Unfortunately, SRCU is not scaling well in that particular case, and it is introducing major performance degradation due to excessive scheduling operations. To allow access to the mm_rb tree without grabbing the mmap_sem, this patch is protecting it access using a rwlock. As the mm_rb tree is a O(log n) search it is safe to protect it using such a lock. The VMA cache is not protected by the new rwlock and it should not be used without holding the mmap_sem. To allow the picked VMA structure to be used once the rwlock is released, a use count is added to the VMA structure. When the VMA is allocated it is set to 1. Each time the VMA is picked with the rwlock held its use count is incremented. Each time the VMA is released it is decremented. When the use count hits zero, this means that the VMA is no more used and should be freed. This patch is preparing for 2 kind of VMA access : - as usual, under the control of the mmap_sem, - without holding the mmap_sem for the speculative page fault handler. Access done under the control the mmap_sem doesn't require to grab the rwlock to protect read access to the mm_rb tree, but access in write must be done under the protection of the rwlock too. This affects inserting and removing of elements in the RB tree. The patch is introducing 2 new functions: - vma_get() to find a VMA based on an address by holding the new rwlock. - vma_put() to release the VMA when its no more used. These services are designed to be used when access are made to the RB tree without holding the mmap_sem. When a VMA is removed from the RB tree, its vma->vm_rb field is cleared and we rely on the WMB done when releasing the rwlock to serialize the write with the RMB done in a later patch to check for the VMA's validity. When free_vma is called, the file associated with the VMA is closed immediately, but the policy and the file structure remained in used until the VMA's use count reach 0, which may happens later when exiting an in progress speculative page fault. [1] https://patchwork.kernel.org/patch/5108281/ Change-Id: I9ecc922b8efa4b28975cc6a8e9531284c24ac14e Cc: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Matthew Wilcox <willy@infradead.org> Signed-off-by: Laurent Dufour <ldufour@linux.vnet.ibm.com> Patch-mainline: linux-mm @ Tue, 17 Apr 2018 16:33:23 [vinmenon@codeaurora.org: fix the return of put_vma] Signed-off-by: Vinayak Menon <vinmenon@codeaurora.org> Signed-off-by: Charan Teja Reddy <charante@codeaurora.org>
43 lines
1.3 KiB
C
43 lines
1.3 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
#include <linux/mm_types.h>
|
|
#include <linux/rbtree.h>
|
|
#include <linux/rwsem.h>
|
|
#include <linux/spinlock.h>
|
|
#include <linux/list.h>
|
|
#include <linux/cpumask.h>
|
|
|
|
#include <linux/atomic.h>
|
|
#include <linux/user_namespace.h>
|
|
#include <asm/pgtable.h>
|
|
#include <asm/mmu.h>
|
|
|
|
#ifndef INIT_MM_CONTEXT
|
|
#define INIT_MM_CONTEXT(name)
|
|
#endif
|
|
|
|
/*
|
|
* For dynamically allocated mm_structs, there is a dynamically sized cpumask
|
|
* at the end of the structure, the size of which depends on the maximum CPU
|
|
* number the system can see. That way we allocate only as much memory for
|
|
* mm_cpumask() as needed for the hundreds, or thousands of processes that
|
|
* a system typically runs.
|
|
*
|
|
* Since there is only one init_mm in the entire system, keep it simple
|
|
* and size this cpu_bitmask to NR_CPUS.
|
|
*/
|
|
struct mm_struct init_mm = {
|
|
.mm_rb = RB_ROOT,
|
|
#ifdef CONFIG_SPECULATIVE_PAGE_FAULT
|
|
.mm_rb_lock = __RW_LOCK_UNLOCKED(init_mm.mm_rb_lock),
|
|
#endif
|
|
.pgd = swapper_pg_dir,
|
|
.mm_users = ATOMIC_INIT(2),
|
|
.mm_count = ATOMIC_INIT(1),
|
|
.mmap_sem = __RWSEM_INITIALIZER(init_mm.mmap_sem),
|
|
.page_table_lock = __SPIN_LOCK_UNLOCKED(init_mm.page_table_lock),
|
|
.arg_lock = __SPIN_LOCK_UNLOCKED(init_mm.arg_lock),
|
|
.mmlist = LIST_HEAD_INIT(init_mm.mmlist),
|
|
.user_ns = &init_user_ns,
|
|
.cpu_bitmap = { [BITS_TO_LONGS(NR_CPUS)] = 0},
|
|
INIT_MM_CONTEXT(init_mm)
|
|
};
|