linux_dsm_epyc7002/arch/nios2/mm/cacheflush.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

270 lines
6.8 KiB
C

/*
* 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.
*
* Copyright (C) 2009, Wind River Systems Inc
* Implemented by fredrik.markstrom@gmail.com and ivarholmqvist@gmail.com
*/
#include <linux/export.h>
#include <linux/sched.h>
#include <linux/mm.h>
#include <linux/fs.h>
#include <asm/cacheflush.h>
#include <asm/cpuinfo.h>
static void __flush_dcache(unsigned long start, unsigned long end)
{
unsigned long addr;
start &= ~(cpuinfo.dcache_line_size - 1);
end += (cpuinfo.dcache_line_size - 1);
end &= ~(cpuinfo.dcache_line_size - 1);
if (end > start + cpuinfo.dcache_size)
end = start + cpuinfo.dcache_size;
for (addr = start; addr < end; addr += cpuinfo.dcache_line_size) {
__asm__ __volatile__ (" flushd 0(%0)\n"
: /* Outputs */
: /* Inputs */ "r"(addr)
/* : No clobber */);
}
}
static void __invalidate_dcache(unsigned long start, unsigned long end)
{
unsigned long addr;
start &= ~(cpuinfo.dcache_line_size - 1);
end += (cpuinfo.dcache_line_size - 1);
end &= ~(cpuinfo.dcache_line_size - 1);
for (addr = start; addr < end; addr += cpuinfo.dcache_line_size) {
__asm__ __volatile__ (" initda 0(%0)\n"
: /* Outputs */
: /* Inputs */ "r"(addr)
/* : No clobber */);
}
}
static void __flush_icache(unsigned long start, unsigned long end)
{
unsigned long addr;
start &= ~(cpuinfo.icache_line_size - 1);
end += (cpuinfo.icache_line_size - 1);
end &= ~(cpuinfo.icache_line_size - 1);
if (end > start + cpuinfo.icache_size)
end = start + cpuinfo.icache_size;
for (addr = start; addr < end; addr += cpuinfo.icache_line_size) {
__asm__ __volatile__ (" flushi %0\n"
: /* Outputs */
: /* Inputs */ "r"(addr)
/* : No clobber */);
}
__asm__ __volatile(" flushp\n");
}
static void flush_aliases(struct address_space *mapping, struct page *page)
{
struct mm_struct *mm = current->active_mm;
struct vm_area_struct *mpnt;
pgoff_t pgoff;
pgoff = page->index;
flush_dcache_mmap_lock(mapping);
vma_interval_tree_foreach(mpnt, &mapping->i_mmap, pgoff, pgoff) {
unsigned long offset;
if (mpnt->vm_mm != mm)
continue;
if (!(mpnt->vm_flags & VM_MAYSHARE))
continue;
offset = (pgoff - mpnt->vm_pgoff) << PAGE_SHIFT;
flush_cache_page(mpnt, mpnt->vm_start + offset,
page_to_pfn(page));
}
flush_dcache_mmap_unlock(mapping);
}
void flush_cache_all(void)
{
__flush_dcache(0, cpuinfo.dcache_size);
__flush_icache(0, cpuinfo.icache_size);
}
void flush_cache_mm(struct mm_struct *mm)
{
flush_cache_all();
}
void flush_cache_dup_mm(struct mm_struct *mm)
{
flush_cache_all();
}
void flush_icache_range(unsigned long start, unsigned long end)
{
__flush_dcache(start, end);
__flush_icache(start, end);
}
void flush_dcache_range(unsigned long start, unsigned long end)
{
__flush_dcache(start, end);
__flush_icache(start, end);
}
EXPORT_SYMBOL(flush_dcache_range);
void invalidate_dcache_range(unsigned long start, unsigned long end)
{
__invalidate_dcache(start, end);
}
EXPORT_SYMBOL(invalidate_dcache_range);
void flush_cache_range(struct vm_area_struct *vma, unsigned long start,
unsigned long end)
{
__flush_dcache(start, end);
if (vma == NULL || (vma->vm_flags & VM_EXEC))
__flush_icache(start, end);
}
void flush_icache_page(struct vm_area_struct *vma, struct page *page)
{
unsigned long start = (unsigned long) page_address(page);
unsigned long end = start + PAGE_SIZE;
__flush_dcache(start, end);
__flush_icache(start, end);
}
void flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr,
unsigned long pfn)
{
unsigned long start = vmaddr;
unsigned long end = start + PAGE_SIZE;
__flush_dcache(start, end);
if (vma->vm_flags & VM_EXEC)
__flush_icache(start, end);
}
void __flush_dcache_page(struct address_space *mapping, struct page *page)
{
/*
* Writeback any data associated with the kernel mapping of this
* page. This ensures that data in the physical page is mutually
* coherent with the kernels mapping.
*/
unsigned long start = (unsigned long)page_address(page);
__flush_dcache(start, start + PAGE_SIZE);
}
void flush_dcache_page(struct page *page)
{
struct address_space *mapping;
/*
* The zero page is never written to, so never has any dirty
* cache lines, and therefore never needs to be flushed.
*/
if (page == ZERO_PAGE(0))
return;
mapping = page_mapping_file(page);
/* Flush this page if there are aliases. */
if (mapping && !mapping_mapped(mapping)) {
clear_bit(PG_dcache_clean, &page->flags);
} else {
__flush_dcache_page(mapping, page);
if (mapping) {
unsigned long start = (unsigned long)page_address(page);
flush_aliases(mapping, page);
flush_icache_range(start, start + PAGE_SIZE);
}
set_bit(PG_dcache_clean, &page->flags);
}
}
EXPORT_SYMBOL(flush_dcache_page);
void update_mmu_cache(struct vm_area_struct *vma,
unsigned long address, pte_t *pte)
{
unsigned long pfn = pte_pfn(*pte);
struct page *page;
struct address_space *mapping;
if (!pfn_valid(pfn))
return;
/*
* The zero page is never written to, so never has any dirty
* cache lines, and therefore never needs to be flushed.
*/
page = pfn_to_page(pfn);
if (page == ZERO_PAGE(0))
return;
mapping = page_mapping_file(page);
if (!test_and_set_bit(PG_dcache_clean, &page->flags))
__flush_dcache_page(mapping, page);
if(mapping)
{
flush_aliases(mapping, page);
if (vma->vm_flags & VM_EXEC)
flush_icache_page(vma, page);
}
}
void copy_user_page(void *vto, void *vfrom, unsigned long vaddr,
struct page *to)
{
__flush_dcache(vaddr, vaddr + PAGE_SIZE);
__flush_icache(vaddr, vaddr + PAGE_SIZE);
copy_page(vto, vfrom);
__flush_dcache((unsigned long)vto, (unsigned long)vto + PAGE_SIZE);
__flush_icache((unsigned long)vto, (unsigned long)vto + PAGE_SIZE);
}
void clear_user_page(void *addr, unsigned long vaddr, struct page *page)
{
__flush_dcache(vaddr, vaddr + PAGE_SIZE);
__flush_icache(vaddr, vaddr + PAGE_SIZE);
clear_page(addr);
__flush_dcache((unsigned long)addr, (unsigned long)addr + PAGE_SIZE);
__flush_icache((unsigned long)addr, (unsigned long)addr + PAGE_SIZE);
}
void copy_from_user_page(struct vm_area_struct *vma, struct page *page,
unsigned long user_vaddr,
void *dst, void *src, int len)
{
flush_cache_page(vma, user_vaddr, page_to_pfn(page));
memcpy(dst, src, len);
__flush_dcache((unsigned long)src, (unsigned long)src + len);
if (vma->vm_flags & VM_EXEC)
__flush_icache((unsigned long)src, (unsigned long)src + len);
}
void copy_to_user_page(struct vm_area_struct *vma, struct page *page,
unsigned long user_vaddr,
void *dst, void *src, int len)
{
flush_cache_page(vma, user_vaddr, page_to_pfn(page));
memcpy(dst, src, len);
__flush_dcache((unsigned long)dst, (unsigned long)dst + len);
if (vma->vm_flags & VM_EXEC)
__flush_icache((unsigned long)dst, (unsigned long)dst + len);
}