kernel_optimize_test/arch/sh/mm/cache-sh7705.c
Huang Ying cb9f753a37 mm: fix races between swapoff and flush dcache
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>
2018-04-05 21:36:26 -07:00

196 lines
4.9 KiB
C

/*
* arch/sh/mm/cache-sh7705.c
*
* Copyright (C) 1999, 2000 Niibe Yutaka
* Copyright (C) 2004 Alex Song
*
* This file is subject to the terms and conditions of the GNU General Public
* License. See the file "COPYING" in the main directory of this archive
* for more details.
*
*/
#include <linux/init.h>
#include <linux/mman.h>
#include <linux/mm.h>
#include <linux/fs.h>
#include <linux/threads.h>
#include <asm/addrspace.h>
#include <asm/page.h>
#include <asm/pgtable.h>
#include <asm/processor.h>
#include <asm/cache.h>
#include <asm/io.h>
#include <linux/uaccess.h>
#include <asm/pgalloc.h>
#include <asm/mmu_context.h>
#include <asm/cacheflush.h>
/*
* The 32KB cache on the SH7705 suffers from the same synonym problem
* as SH4 CPUs
*/
static inline void cache_wback_all(void)
{
unsigned long ways, waysize, addrstart;
ways = current_cpu_data.dcache.ways;
waysize = current_cpu_data.dcache.sets;
waysize <<= current_cpu_data.dcache.entry_shift;
addrstart = CACHE_OC_ADDRESS_ARRAY;
do {
unsigned long addr;
for (addr = addrstart;
addr < addrstart + waysize;
addr += current_cpu_data.dcache.linesz) {
unsigned long data;
int v = SH_CACHE_UPDATED | SH_CACHE_VALID;
data = __raw_readl(addr);
if ((data & v) == v)
__raw_writel(data & ~v, addr);
}
addrstart += current_cpu_data.dcache.way_incr;
} while (--ways);
}
/*
* Write back the range of D-cache, and purge the I-cache.
*
* Called from kernel/module.c:sys_init_module and routine for a.out format.
*/
static void sh7705_flush_icache_range(void *args)
{
struct flusher_data *data = args;
unsigned long start, end;
start = data->addr1;
end = data->addr2;
__flush_wback_region((void *)start, end - start);
}
/*
* Writeback&Invalidate the D-cache of the page
*/
static void __flush_dcache_page(unsigned long phys)
{
unsigned long ways, waysize, addrstart;
unsigned long flags;
phys |= SH_CACHE_VALID;
/*
* Here, phys is the physical address of the page. We check all the
* tags in the cache for those with the same page number as this page
* (by masking off the lowest 2 bits of the 19-bit tag; these bits are
* derived from the offset within in the 4k page). Matching valid
* entries are invalidated.
*
* Since 2 bits of the cache index are derived from the virtual page
* number, knowing this would reduce the number of cache entries to be
* searched by a factor of 4. However this function exists to deal with
* potential cache aliasing, therefore the optimisation is probably not
* possible.
*/
local_irq_save(flags);
jump_to_uncached();
ways = current_cpu_data.dcache.ways;
waysize = current_cpu_data.dcache.sets;
waysize <<= current_cpu_data.dcache.entry_shift;
addrstart = CACHE_OC_ADDRESS_ARRAY;
do {
unsigned long addr;
for (addr = addrstart;
addr < addrstart + waysize;
addr += current_cpu_data.dcache.linesz) {
unsigned long data;
data = __raw_readl(addr) & (0x1ffffC00 | SH_CACHE_VALID);
if (data == phys) {
data &= ~(SH_CACHE_VALID | SH_CACHE_UPDATED);
__raw_writel(data, addr);
}
}
addrstart += current_cpu_data.dcache.way_incr;
} while (--ways);
back_to_cached();
local_irq_restore(flags);
}
/*
* Write back & invalidate the D-cache of the page.
* (To avoid "alias" issues)
*/
static void sh7705_flush_dcache_page(void *arg)
{
struct page *page = arg;
struct address_space *mapping = page_mapping_file(page);
if (mapping && !mapping_mapped(mapping))
clear_bit(PG_dcache_clean, &page->flags);
else
__flush_dcache_page(__pa(page_address(page)));
}
static void sh7705_flush_cache_all(void *args)
{
unsigned long flags;
local_irq_save(flags);
jump_to_uncached();
cache_wback_all();
back_to_cached();
local_irq_restore(flags);
}
/*
* Write back and invalidate I/D-caches for the page.
*
* ADDRESS: Virtual Address (U0 address)
*/
static void sh7705_flush_cache_page(void *args)
{
struct flusher_data *data = args;
unsigned long pfn = data->addr2;
__flush_dcache_page(pfn << PAGE_SHIFT);
}
/*
* This is called when a page-cache page is about to be mapped into a
* user process' address space. It offers an opportunity for a
* port to ensure d-cache/i-cache coherency if necessary.
*
* Not entirely sure why this is necessary on SH3 with 32K cache but
* without it we get occasional "Memory fault" when loading a program.
*/
static void sh7705_flush_icache_page(void *page)
{
__flush_purge_region(page_address(page), PAGE_SIZE);
}
void __init sh7705_cache_init(void)
{
local_flush_icache_range = sh7705_flush_icache_range;
local_flush_dcache_page = sh7705_flush_dcache_page;
local_flush_cache_all = sh7705_flush_cache_all;
local_flush_cache_mm = sh7705_flush_cache_all;
local_flush_cache_dup_mm = sh7705_flush_cache_all;
local_flush_cache_range = sh7705_flush_cache_all;
local_flush_cache_page = sh7705_flush_cache_page;
local_flush_icache_page = sh7705_flush_icache_page;
}