mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-26 10:49:33 +00:00
![Huang Ying](/assets/img/avatar_default.png)
Thanks to commit 4b3ef9daa4
("mm/swap: split swap cache into 64MB
trunks"), after swapoff the address_space associated with the swap
device will be freed. So page_mapping() users which may touch the
address_space need some kind of mechanism to prevent the address_space
from being freed during accessing.
The dcache flushing functions (flush_dcache_page(), etc) in architecture
specific code may access the address_space of swap device for anonymous
pages in swap cache via page_mapping() function. But in some cases
there are no mechanisms to prevent the swap device from being swapoff,
for example,
CPU1 CPU2
__get_user_pages() swapoff()
flush_dcache_page()
mapping = page_mapping()
... exit_swap_address_space()
... kvfree(spaces)
mapping_mapped(mapping)
The address space may be accessed after being freed.
But from cachetlb.txt and Russell King, flush_dcache_page() only care
about file cache pages, for anonymous pages, flush_anon_page() should be
used. The implementation of flush_dcache_page() in all architectures
follows this too. They will check whether page_mapping() is NULL and
whether mapping_mapped() is true to determine whether to flush the
dcache immediately. And they will use interval tree (mapping->i_mmap)
to find all user space mappings. While mapping_mapped() and
mapping->i_mmap isn't used by anonymous pages in swap cache at all.
So, to fix the race between swapoff and flush dcache, __page_mapping()
is add to return the address_space for file cache pages and NULL
otherwise. All page_mapping() invoking in flush dcache functions are
replaced with page_mapping_file().
[akpm@linux-foundation.org: simplify page_mapping_file(), per Mike]
Link: http://lkml.kernel.org/r/20180305083634.15174-1-ying.huang@intel.com
Signed-off-by: "Huang, Ying" <ying.huang@intel.com>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Chen Liqin <liqin.linux@gmail.com>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Cc: "James E.J. Bottomley" <jejb@parisc-linux.org>
Cc: Guan Xuetao <gxt@mprc.pku.edu.cn>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Chris Zankel <chris@zankel.net>
Cc: Vineet Gupta <vgupta@synopsys.com>
Cc: Ley Foon Tan <lftan@altera.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
135 lines
3.6 KiB
C
135 lines
3.6 KiB
C
/*
|
|
* linux/arch/arm/lib/copypage-xscale.S
|
|
*
|
|
* Copyright (C) 1995-2005 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.
|
|
*
|
|
* This handles the mini data cache, as found on SA11x0 and XScale
|
|
* processors. When we copy a user page page, we map it in such a way
|
|
* that accesses to this page will not touch the main data cache, but
|
|
* will be cached in the mini data cache. This prevents us thrashing
|
|
* the main data cache on page faults.
|
|
*/
|
|
#include <linux/init.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/highmem.h>
|
|
|
|
#include <asm/pgtable.h>
|
|
#include <asm/tlbflush.h>
|
|
#include <asm/cacheflush.h>
|
|
|
|
#include "mm.h"
|
|
|
|
#define minicache_pgprot __pgprot(L_PTE_PRESENT | L_PTE_YOUNG | \
|
|
L_PTE_MT_MINICACHE)
|
|
|
|
static DEFINE_RAW_SPINLOCK(minicache_lock);
|
|
|
|
/*
|
|
* XScale mini-dcache optimised copy_user_highpage
|
|
*
|
|
* We flush the destination cache lines just before we write the data into the
|
|
* corresponding address. Since the Dcache is read-allocate, this removes the
|
|
* Dcache aliasing issue. The writes will be forwarded to the write buffer,
|
|
* and merged as appropriate.
|
|
*/
|
|
static void __naked
|
|
mc_copy_user_page(void *from, void *to)
|
|
{
|
|
/*
|
|
* Strangely enough, best performance is achieved
|
|
* when prefetching destination as well. (NP)
|
|
*/
|
|
asm volatile(
|
|
"stmfd sp!, {r4, r5, lr} \n\
|
|
mov lr, %2 \n\
|
|
pld [r0, #0] \n\
|
|
pld [r0, #32] \n\
|
|
pld [r1, #0] \n\
|
|
pld [r1, #32] \n\
|
|
1: pld [r0, #64] \n\
|
|
pld [r0, #96] \n\
|
|
pld [r1, #64] \n\
|
|
pld [r1, #96] \n\
|
|
2: ldrd r2, [r0], #8 \n\
|
|
ldrd r4, [r0], #8 \n\
|
|
mov ip, r1 \n\
|
|
strd r2, [r1], #8 \n\
|
|
ldrd r2, [r0], #8 \n\
|
|
strd r4, [r1], #8 \n\
|
|
ldrd r4, [r0], #8 \n\
|
|
strd r2, [r1], #8 \n\
|
|
strd r4, [r1], #8 \n\
|
|
mcr p15, 0, ip, c7, c10, 1 @ clean D line\n\
|
|
ldrd r2, [r0], #8 \n\
|
|
mcr p15, 0, ip, c7, c6, 1 @ invalidate D line\n\
|
|
ldrd r4, [r0], #8 \n\
|
|
mov ip, r1 \n\
|
|
strd r2, [r1], #8 \n\
|
|
ldrd r2, [r0], #8 \n\
|
|
strd r4, [r1], #8 \n\
|
|
ldrd r4, [r0], #8 \n\
|
|
strd r2, [r1], #8 \n\
|
|
strd r4, [r1], #8 \n\
|
|
mcr p15, 0, ip, c7, c10, 1 @ clean D line\n\
|
|
subs lr, lr, #1 \n\
|
|
mcr p15, 0, ip, c7, c6, 1 @ invalidate D line\n\
|
|
bgt 1b \n\
|
|
beq 2b \n\
|
|
ldmfd sp!, {r4, r5, pc} "
|
|
:
|
|
: "r" (from), "r" (to), "I" (PAGE_SIZE / 64 - 1));
|
|
}
|
|
|
|
void xscale_mc_copy_user_highpage(struct page *to, struct page *from,
|
|
unsigned long vaddr, struct vm_area_struct *vma)
|
|
{
|
|
void *kto = kmap_atomic(to);
|
|
|
|
if (!test_and_set_bit(PG_dcache_clean, &from->flags))
|
|
__flush_dcache_page(page_mapping_file(from), from);
|
|
|
|
raw_spin_lock(&minicache_lock);
|
|
|
|
set_top_pte(COPYPAGE_MINICACHE, mk_pte(from, minicache_pgprot));
|
|
|
|
mc_copy_user_page((void *)COPYPAGE_MINICACHE, kto);
|
|
|
|
raw_spin_unlock(&minicache_lock);
|
|
|
|
kunmap_atomic(kto);
|
|
}
|
|
|
|
/*
|
|
* XScale optimised clear_user_page
|
|
*/
|
|
void
|
|
xscale_mc_clear_user_highpage(struct page *page, unsigned long vaddr)
|
|
{
|
|
void *ptr, *kaddr = kmap_atomic(page);
|
|
asm volatile(
|
|
"mov r1, %2 \n\
|
|
mov r2, #0 \n\
|
|
mov r3, #0 \n\
|
|
1: mov ip, %0 \n\
|
|
strd r2, [%0], #8 \n\
|
|
strd r2, [%0], #8 \n\
|
|
strd r2, [%0], #8 \n\
|
|
strd r2, [%0], #8 \n\
|
|
mcr p15, 0, ip, c7, c10, 1 @ clean D line\n\
|
|
subs r1, r1, #1 \n\
|
|
mcr p15, 0, ip, c7, c6, 1 @ invalidate D line\n\
|
|
bne 1b"
|
|
: "=r" (ptr)
|
|
: "0" (kaddr), "I" (PAGE_SIZE / 32)
|
|
: "r1", "r2", "r3", "ip");
|
|
kunmap_atomic(kaddr);
|
|
}
|
|
|
|
struct cpu_user_fns xscale_mc_user_fns __initdata = {
|
|
.cpu_clear_user_highpage = xscale_mc_clear_user_highpage,
|
|
.cpu_copy_user_highpage = xscale_mc_copy_user_highpage,
|
|
};
|