linux_dsm_epyc7002/arch/mips/mm/cache.c
Paul Burton 37d22a0d79 MIPS: Sync icache & dcache in set_pte_at
It's possible for pages to become visible prior to update_mmu_cache
running if a thread within the same address space preempts the current
thread or runs simultaneously on another CPU. That is, the following
scenario is possible:

    CPU0                            CPU1

    write to page
    flush_dcache_page
    flush_icache_page
    set_pte_at
                                    map page
    update_mmu_cache

If CPU1 maps the page in between CPU0's set_pte_at, which marks it valid
& visible, and update_mmu_cache where the dcache flush occurs then CPU1s
icache will fill from stale data (unless it fills from the dcache, in
which case all is good, but most MIPS CPUs don't have this property).
Commit 4d46a67a3e ("MIPS: Fix race condition in lazy cache flushing.")
attempted to fix that by performing the dcache flush in
flush_icache_page such that it occurs before the set_pte_at call makes
the page visible. However it has the problem that not all code that
writes to pages exposed to userland call flush_icache_page. There are
many callers of set_pte_at under mm/ and only 2 of them do call
flush_icache_page. Thus the race window between a page becoming visible
& being coherent between the icache & dcache remains open in some cases.

To illustrate some of the cases, a WARN was added to __update_cache with
this patch applied that triggered in cases where a page about to be
flushed from the dcache was not the last page provided to
flush_icache_page. That is, backtraces were obtained for cases in which
the race window is left open without this patch. The 2 standout examples
follow.

When forking a process:

[   15.271842] [<80417630>] __update_cache+0xcc/0x188
[   15.277274] [<80530394>] copy_page_range+0x56c/0x6ac
[   15.282861] [<8042936c>] copy_process.part.54+0xd40/0x17ac
[   15.289028] [<80429f80>] do_fork+0xe4/0x420
[   15.293747] [<80413808>] handle_sys+0x128/0x14c

When exec'ing an ELF binary:

[   14.445964] [<80417630>] __update_cache+0xcc/0x188
[   14.451369] [<80538d88>] move_page_tables+0x414/0x498
[   14.457075] [<8055d848>] setup_arg_pages+0x220/0x318
[   14.462685] [<805b0f38>] load_elf_binary+0x530/0x12a0
[   14.468374] [<8055ec3c>] search_binary_handler+0xbc/0x214
[   14.474444] [<8055f6c0>] do_execveat_common+0x43c/0x67c
[   14.480324] [<8055f938>] do_execve+0x38/0x44
[   14.485137] [<80413808>] handle_sys+0x128/0x14c

These code paths write into a page, call flush_dcache_page then call
set_pte_at without flush_icache_page inbetween. The end result is that
the icache can become corrupted & userland processes may execute
unexpected or invalid code, typically resulting in a reserved
instruction exception, a trap or a segfault.

Fix this race condition fully by performing any cache maintenance
required to keep the icache & dcache in sync in set_pte_at, before the
page is made valid. This has the added bonus of ensuring the cache
maintenance always happens in one location, rather than being duplicated
in flush_icache_page & update_mmu_cache. It also matches the way other
architectures solve the same problem (see arm, ia64 & powerpc).

Signed-off-by: Paul Burton <paul.burton@imgtec.com>
Reported-by: Ionela Voinescu <ionela.voinescu@imgtec.com>
Cc: Lars Persson <lars.persson@axis.com>
Fixes: 4d46a67a3e ("MIPS: Fix race condition in lazy cache flushing.")
Cc: Steven J. Hill <sjhill@realitydiluted.com>
Cc: David Daney <david.daney@cavium.com>
Cc: Huacai Chen <chenhc@lemote.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Jerome Marchand <jmarchan@redhat.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: linux-mips@linux-mips.org
Cc: linux-kernel@vger.kernel.org
Cc: stable <stable@vger.kernel.org> # v4.1+
Patchwork: https://patchwork.linux-mips.org/patch/12722/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2016-05-13 14:01:58 +02:00

242 lines
7.0 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) 1994 - 2003, 06, 07 by Ralf Baechle (ralf@linux-mips.org)
* Copyright (C) 2007 MIPS Technologies, Inc.
*/
#include <linux/fs.h>
#include <linux/fcntl.h>
#include <linux/kernel.h>
#include <linux/linkage.h>
#include <linux/module.h>
#include <linux/sched.h>
#include <linux/syscalls.h>
#include <linux/mm.h>
#include <asm/cacheflush.h>
#include <asm/highmem.h>
#include <asm/processor.h>
#include <asm/cpu.h>
#include <asm/cpu-features.h>
/* Cache operations. */
void (*flush_cache_all)(void);
void (*__flush_cache_all)(void);
void (*flush_cache_mm)(struct mm_struct *mm);
void (*flush_cache_range)(struct vm_area_struct *vma, unsigned long start,
unsigned long end);
void (*flush_cache_page)(struct vm_area_struct *vma, unsigned long page,
unsigned long pfn);
void (*flush_icache_range)(unsigned long start, unsigned long end);
EXPORT_SYMBOL_GPL(flush_icache_range);
void (*local_flush_icache_range)(unsigned long start, unsigned long end);
EXPORT_SYMBOL_GPL(local_flush_icache_range);
void (*__flush_cache_vmap)(void);
void (*__flush_cache_vunmap)(void);
void (*__flush_kernel_vmap_range)(unsigned long vaddr, int size);
EXPORT_SYMBOL_GPL(__flush_kernel_vmap_range);
void (*__invalidate_kernel_vmap_range)(unsigned long vaddr, int size);
/* MIPS specific cache operations */
void (*flush_cache_sigtramp)(unsigned long addr);
void (*local_flush_data_cache_page)(void * addr);
void (*flush_data_cache_page)(unsigned long addr);
void (*flush_icache_all)(void);
EXPORT_SYMBOL_GPL(local_flush_data_cache_page);
EXPORT_SYMBOL(flush_data_cache_page);
EXPORT_SYMBOL(flush_icache_all);
#if defined(CONFIG_DMA_NONCOHERENT) || defined(CONFIG_DMA_MAYBE_COHERENT)
/* DMA cache operations. */
void (*_dma_cache_wback_inv)(unsigned long start, unsigned long size);
void (*_dma_cache_wback)(unsigned long start, unsigned long size);
void (*_dma_cache_inv)(unsigned long start, unsigned long size);
EXPORT_SYMBOL(_dma_cache_wback_inv);
#endif /* CONFIG_DMA_NONCOHERENT || CONFIG_DMA_MAYBE_COHERENT */
/*
* We could optimize the case where the cache argument is not BCACHE but
* that seems very atypical use ...
*/
SYSCALL_DEFINE3(cacheflush, unsigned long, addr, unsigned long, bytes,
unsigned int, cache)
{
if (bytes == 0)
return 0;
if (!access_ok(VERIFY_WRITE, (void __user *) addr, bytes))
return -EFAULT;
flush_icache_range(addr, addr + bytes);
return 0;
}
void __flush_dcache_page(struct page *page)
{
struct address_space *mapping = page_mapping(page);
unsigned long addr;
if (mapping && !mapping_mapped(mapping)) {
SetPageDcacheDirty(page);
return;
}
/*
* We could delay the flush for the !page_mapping case too. But that
* case is for exec env/arg pages and those are %99 certainly going to
* get faulted into the tlb (and thus flushed) anyways.
*/
if (PageHighMem(page))
addr = (unsigned long)kmap_atomic(page);
else
addr = (unsigned long)page_address(page);
flush_data_cache_page(addr);
if (PageHighMem(page))
__kunmap_atomic((void *)addr);
}
EXPORT_SYMBOL(__flush_dcache_page);
void __flush_anon_page(struct page *page, unsigned long vmaddr)
{
unsigned long addr = (unsigned long) page_address(page);
if (pages_do_alias(addr, vmaddr)) {
if (page_mapcount(page) && !Page_dcache_dirty(page)) {
void *kaddr;
kaddr = kmap_coherent(page, vmaddr);
flush_data_cache_page((unsigned long)kaddr);
kunmap_coherent();
} else
flush_data_cache_page(addr);
}
}
EXPORT_SYMBOL(__flush_anon_page);
void __update_cache(unsigned long address, pte_t pte)
{
struct page *page;
unsigned long pfn, addr;
int exec = !pte_no_exec(pte) && !cpu_has_ic_fills_f_dc;
pfn = pte_pfn(pte);
if (unlikely(!pfn_valid(pfn)))
return;
page = pfn_to_page(pfn);
if (Page_dcache_dirty(page)) {
if (PageHighMem(page))
addr = (unsigned long)kmap_atomic(page);
else
addr = (unsigned long)page_address(page);
if (exec || pages_do_alias(addr, address & PAGE_MASK))
flush_data_cache_page(addr);
if (PageHighMem(page))
__kunmap_atomic((void *)addr);
ClearPageDcacheDirty(page);
}
}
unsigned long _page_cachable_default;
EXPORT_SYMBOL(_page_cachable_default);
static inline void setup_protection_map(void)
{
if (cpu_has_rixi) {
protection_map[0] = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_NO_READ);
protection_map[1] = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_NO_EXEC);
protection_map[2] = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_NO_READ);
protection_map[3] = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_NO_EXEC);
protection_map[4] = __pgprot(_page_cachable_default | _PAGE_PRESENT);
protection_map[5] = __pgprot(_page_cachable_default | _PAGE_PRESENT);
protection_map[6] = __pgprot(_page_cachable_default | _PAGE_PRESENT);
protection_map[7] = __pgprot(_page_cachable_default | _PAGE_PRESENT);
protection_map[8] = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_NO_READ);
protection_map[9] = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_NO_EXEC);
protection_map[10] = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_WRITE | _PAGE_NO_READ);
protection_map[11] = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_WRITE);
protection_map[12] = __pgprot(_page_cachable_default | _PAGE_PRESENT);
protection_map[13] = __pgprot(_page_cachable_default | _PAGE_PRESENT);
protection_map[14] = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_WRITE);
protection_map[15] = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_WRITE);
} else {
protection_map[0] = PAGE_NONE;
protection_map[1] = PAGE_READONLY;
protection_map[2] = PAGE_COPY;
protection_map[3] = PAGE_COPY;
protection_map[4] = PAGE_READONLY;
protection_map[5] = PAGE_READONLY;
protection_map[6] = PAGE_COPY;
protection_map[7] = PAGE_COPY;
protection_map[8] = PAGE_NONE;
protection_map[9] = PAGE_READONLY;
protection_map[10] = PAGE_SHARED;
protection_map[11] = PAGE_SHARED;
protection_map[12] = PAGE_READONLY;
protection_map[13] = PAGE_READONLY;
protection_map[14] = PAGE_SHARED;
protection_map[15] = PAGE_SHARED;
}
}
void cpu_cache_init(void)
{
if (cpu_has_3k_cache) {
extern void __weak r3k_cache_init(void);
r3k_cache_init();
}
if (cpu_has_6k_cache) {
extern void __weak r6k_cache_init(void);
r6k_cache_init();
}
if (cpu_has_4k_cache) {
extern void __weak r4k_cache_init(void);
r4k_cache_init();
}
if (cpu_has_8k_cache) {
extern void __weak r8k_cache_init(void);
r8k_cache_init();
}
if (cpu_has_tx39_cache) {
extern void __weak tx39_cache_init(void);
tx39_cache_init();
}
if (cpu_has_octeon_cache) {
extern void __weak octeon_cache_init(void);
octeon_cache_init();
}
setup_protection_map();
}
int __weak __uncached_access(struct file *file, unsigned long addr)
{
if (file->f_flags & O_DSYNC)
return 1;
return addr >= __pa(high_memory);
}