forked from Minki/linux
16af97dc5a
Patch series "fixes of TLB batching races", v6.
It turns out that Linux TLB batching mechanism suffers from various
races. Races that are caused due to batching during reclamation were
recently handled by Mel and this patch-set deals with others. The more
fundamental issue is that concurrent updates of the page-tables allow
for TLB flushes to be batched on one core, while another core changes
the page-tables. This other core may assume a PTE change does not
require a flush based on the updated PTE value, while it is unaware that
TLB flushes are still pending.
This behavior affects KSM (which may result in memory corruption) and
MADV_FREE and MADV_DONTNEED (which may result in incorrect behavior). A
proof-of-concept can easily produce the wrong behavior of MADV_DONTNEED.
Memory corruption in KSM is harder to produce in practice, but was
observed by hacking the kernel and adding a delay before flushing and
replacing the KSM page.
Finally, there is also one memory barrier missing, which may affect
architectures with weak memory model.
This patch (of 7):
Setting and clearing mm->tlb_flush_pending can be performed by multiple
threads, since mmap_sem may only be acquired for read in
task_numa_work(). If this happens, tlb_flush_pending might be cleared
while one of the threads still changes PTEs and batches TLB flushes.
This can lead to the same race between migration and
change_protection_range() that led to the introduction of
tlb_flush_pending. The result of this race was data corruption, which
means that this patch also addresses a theoretically possible data
corruption.
An actual data corruption was not observed, yet the race was was
confirmed by adding assertion to check tlb_flush_pending is not set by
two threads, adding artificial latency in change_protection_range() and
using sysctl to reduce kernel.numa_balancing_scan_delay_ms.
Link: http://lkml.kernel.org/r/20170802000818.4760-2-namit@vmware.com
Fixes: 2084140594
("mm: fix TLB flush race between migration, and
change_protection_range")
Signed-off-by: Nadav Amit <namit@vmware.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Acked-by: Rik van Riel <riel@redhat.com>
Acked-by: Minchan Kim <minchan@kernel.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jeff Dike <jdike@addtoit.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
169 lines
4.3 KiB
C
169 lines
4.3 KiB
C
/*
|
|
* mm/debug.c
|
|
*
|
|
* mm/ specific debug routines.
|
|
*
|
|
*/
|
|
|
|
#include <linux/kernel.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/trace_events.h>
|
|
#include <linux/memcontrol.h>
|
|
#include <trace/events/mmflags.h>
|
|
#include <linux/migrate.h>
|
|
#include <linux/page_owner.h>
|
|
|
|
#include "internal.h"
|
|
|
|
char *migrate_reason_names[MR_TYPES] = {
|
|
"compaction",
|
|
"memory_failure",
|
|
"memory_hotplug",
|
|
"syscall_or_cpuset",
|
|
"mempolicy_mbind",
|
|
"numa_misplaced",
|
|
"cma",
|
|
};
|
|
|
|
const struct trace_print_flags pageflag_names[] = {
|
|
__def_pageflag_names,
|
|
{0, NULL}
|
|
};
|
|
|
|
const struct trace_print_flags gfpflag_names[] = {
|
|
__def_gfpflag_names,
|
|
{0, NULL}
|
|
};
|
|
|
|
const struct trace_print_flags vmaflag_names[] = {
|
|
__def_vmaflag_names,
|
|
{0, NULL}
|
|
};
|
|
|
|
void __dump_page(struct page *page, const char *reason)
|
|
{
|
|
/*
|
|
* Avoid VM_BUG_ON() in page_mapcount().
|
|
* page->_mapcount space in struct page is used by sl[aou]b pages to
|
|
* encode own info.
|
|
*/
|
|
int mapcount = PageSlab(page) ? 0 : page_mapcount(page);
|
|
|
|
pr_emerg("page:%p count:%d mapcount:%d mapping:%p index:%#lx",
|
|
page, page_ref_count(page), mapcount,
|
|
page->mapping, page_to_pgoff(page));
|
|
if (PageCompound(page))
|
|
pr_cont(" compound_mapcount: %d", compound_mapcount(page));
|
|
pr_cont("\n");
|
|
BUILD_BUG_ON(ARRAY_SIZE(pageflag_names) != __NR_PAGEFLAGS + 1);
|
|
|
|
pr_emerg("flags: %#lx(%pGp)\n", page->flags, &page->flags);
|
|
|
|
print_hex_dump(KERN_ALERT, "raw: ", DUMP_PREFIX_NONE, 32,
|
|
sizeof(unsigned long), page,
|
|
sizeof(struct page), false);
|
|
|
|
if (reason)
|
|
pr_alert("page dumped because: %s\n", reason);
|
|
|
|
#ifdef CONFIG_MEMCG
|
|
if (page->mem_cgroup)
|
|
pr_alert("page->mem_cgroup:%p\n", page->mem_cgroup);
|
|
#endif
|
|
}
|
|
|
|
void dump_page(struct page *page, const char *reason)
|
|
{
|
|
__dump_page(page, reason);
|
|
dump_page_owner(page);
|
|
}
|
|
EXPORT_SYMBOL(dump_page);
|
|
|
|
#ifdef CONFIG_DEBUG_VM
|
|
|
|
void dump_vma(const struct vm_area_struct *vma)
|
|
{
|
|
pr_emerg("vma %p start %p end %p\n"
|
|
"next %p prev %p mm %p\n"
|
|
"prot %lx anon_vma %p vm_ops %p\n"
|
|
"pgoff %lx file %p private_data %p\n"
|
|
"flags: %#lx(%pGv)\n",
|
|
vma, (void *)vma->vm_start, (void *)vma->vm_end, vma->vm_next,
|
|
vma->vm_prev, vma->vm_mm,
|
|
(unsigned long)pgprot_val(vma->vm_page_prot),
|
|
vma->anon_vma, vma->vm_ops, vma->vm_pgoff,
|
|
vma->vm_file, vma->vm_private_data,
|
|
vma->vm_flags, &vma->vm_flags);
|
|
}
|
|
EXPORT_SYMBOL(dump_vma);
|
|
|
|
void dump_mm(const struct mm_struct *mm)
|
|
{
|
|
pr_emerg("mm %p mmap %p seqnum %d task_size %lu\n"
|
|
#ifdef CONFIG_MMU
|
|
"get_unmapped_area %p\n"
|
|
#endif
|
|
"mmap_base %lu mmap_legacy_base %lu highest_vm_end %lu\n"
|
|
"pgd %p mm_users %d mm_count %d nr_ptes %lu nr_pmds %lu map_count %d\n"
|
|
"hiwater_rss %lx hiwater_vm %lx total_vm %lx locked_vm %lx\n"
|
|
"pinned_vm %lx data_vm %lx exec_vm %lx stack_vm %lx\n"
|
|
"start_code %lx end_code %lx start_data %lx end_data %lx\n"
|
|
"start_brk %lx brk %lx start_stack %lx\n"
|
|
"arg_start %lx arg_end %lx env_start %lx env_end %lx\n"
|
|
"binfmt %p flags %lx core_state %p\n"
|
|
#ifdef CONFIG_AIO
|
|
"ioctx_table %p\n"
|
|
#endif
|
|
#ifdef CONFIG_MEMCG
|
|
"owner %p "
|
|
#endif
|
|
"exe_file %p\n"
|
|
#ifdef CONFIG_MMU_NOTIFIER
|
|
"mmu_notifier_mm %p\n"
|
|
#endif
|
|
#ifdef CONFIG_NUMA_BALANCING
|
|
"numa_next_scan %lu numa_scan_offset %lu numa_scan_seq %d\n"
|
|
#endif
|
|
#if defined(CONFIG_NUMA_BALANCING) || defined(CONFIG_COMPACTION)
|
|
"tlb_flush_pending %d\n"
|
|
#endif
|
|
"def_flags: %#lx(%pGv)\n",
|
|
|
|
mm, mm->mmap, mm->vmacache_seqnum, mm->task_size,
|
|
#ifdef CONFIG_MMU
|
|
mm->get_unmapped_area,
|
|
#endif
|
|
mm->mmap_base, mm->mmap_legacy_base, mm->highest_vm_end,
|
|
mm->pgd, atomic_read(&mm->mm_users),
|
|
atomic_read(&mm->mm_count),
|
|
atomic_long_read((atomic_long_t *)&mm->nr_ptes),
|
|
mm_nr_pmds((struct mm_struct *)mm),
|
|
mm->map_count,
|
|
mm->hiwater_rss, mm->hiwater_vm, mm->total_vm, mm->locked_vm,
|
|
mm->pinned_vm, mm->data_vm, mm->exec_vm, mm->stack_vm,
|
|
mm->start_code, mm->end_code, mm->start_data, mm->end_data,
|
|
mm->start_brk, mm->brk, mm->start_stack,
|
|
mm->arg_start, mm->arg_end, mm->env_start, mm->env_end,
|
|
mm->binfmt, mm->flags, mm->core_state,
|
|
#ifdef CONFIG_AIO
|
|
mm->ioctx_table,
|
|
#endif
|
|
#ifdef CONFIG_MEMCG
|
|
mm->owner,
|
|
#endif
|
|
mm->exe_file,
|
|
#ifdef CONFIG_MMU_NOTIFIER
|
|
mm->mmu_notifier_mm,
|
|
#endif
|
|
#ifdef CONFIG_NUMA_BALANCING
|
|
mm->numa_next_scan, mm->numa_scan_offset, mm->numa_scan_seq,
|
|
#endif
|
|
#if defined(CONFIG_NUMA_BALANCING) || defined(CONFIG_COMPACTION)
|
|
atomic_read(&mm->tlb_flush_pending),
|
|
#endif
|
|
mm->def_flags, &mm->def_flags
|
|
);
|
|
}
|
|
|
|
#endif /* CONFIG_DEBUG_VM */
|