965d3d5ce3
[ Upstream commit 38cf307c1f2011d413750c5acb725456f47d9172 ]
For SMP systems using IPI based TLB invalidation, looking at
current->active_mm is entirely reasonable. This then presents the
following race condition:
CPU0 CPU1
flush_tlb_mm(mm) use_mm(mm)
<send-IPI>
tsk->active_mm = mm;
<IPI>
if (tsk->active_mm == mm)
// flush TLBs
</IPI>
switch_mm(old_mm,mm,tsk);
Where it is possible the IPI flushed the TLBs for @old_mm, not @mm,
because the IPI lands before we actually switched.
Avoid this by disabling IRQs across changing ->active_mm and
switch_mm().
Of the (SMP) architectures that have IPI based TLB invalidate:
Alpha - checks active_mm
ARC - ASID specific
IA64 - checks active_mm
MIPS - ASID specific flush
OpenRISC - shoots down world
PARISC - shoots down world
SH - ASID specific
SPARC - ASID specific
x86 - N/A
xtensa - checks active_mm
So at the very least Alpha, IA64 and Xtensa are suspect.
On top of this, for scheduler consistency we need at least preemption
disabled across changing tsk->mm and doing switch_mm(), which is
currently provided by task_lock(), but that's not sufficient for
PREEMPT_RT.
[akpm@linux-foundation.org: add comment]
Reported-by: Andy Lutomirski <luto@amacapital.net>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Kees Cook <keescook@chromium.org>
Cc: Jann Horn <jannh@google.com>
Cc: Will Deacon <will@kernel.org>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: <stable@vger.kernel.org>
Link: http://lkml.kernel.org/r/20200721154106.GE10769@hirez.programming.kicks-ass.net
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
70 lines
1.5 KiB
C
70 lines
1.5 KiB
C
/* Copyright (C) 2009 Red Hat, Inc.
|
|
*
|
|
* See ../COPYING for licensing terms.
|
|
*/
|
|
|
|
#include <linux/mm.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/sched/mm.h>
|
|
#include <linux/sched/task.h>
|
|
#include <linux/mmu_context.h>
|
|
#include <linux/export.h>
|
|
|
|
#include <asm/mmu_context.h>
|
|
|
|
/*
|
|
* use_mm
|
|
* Makes the calling kernel thread take on the specified
|
|
* mm context.
|
|
* (Note: this routine is intended to be called only
|
|
* from a kernel thread context)
|
|
*/
|
|
void use_mm(struct mm_struct *mm)
|
|
{
|
|
struct mm_struct *active_mm;
|
|
struct task_struct *tsk = current;
|
|
|
|
task_lock(tsk);
|
|
/* Hold off tlb flush IPIs while switching mm's */
|
|
local_irq_disable();
|
|
active_mm = tsk->active_mm;
|
|
if (active_mm != mm) {
|
|
mmgrab(mm);
|
|
tsk->active_mm = mm;
|
|
}
|
|
tsk->mm = mm;
|
|
switch_mm_irqs_off(active_mm, mm, tsk);
|
|
local_irq_enable();
|
|
task_unlock(tsk);
|
|
#ifdef finish_arch_post_lock_switch
|
|
finish_arch_post_lock_switch();
|
|
#endif
|
|
|
|
if (active_mm != mm)
|
|
mmdrop(active_mm);
|
|
}
|
|
EXPORT_SYMBOL_GPL(use_mm);
|
|
|
|
/*
|
|
* unuse_mm
|
|
* Reverses the effect of use_mm, i.e. releases the
|
|
* specified mm context which was earlier taken on
|
|
* by the calling kernel thread
|
|
* (Note: this routine is intended to be called only
|
|
* from a kernel thread context)
|
|
*/
|
|
void unuse_mm(struct mm_struct *mm)
|
|
{
|
|
struct task_struct *tsk = current;
|
|
|
|
task_lock(tsk);
|
|
sync_mm_rss(mm);
|
|
local_irq_disable();
|
|
tsk->mm = NULL;
|
|
/* active_mm is still 'mm' */
|
|
enter_lazy_tlb(mm, tsk);
|
|
local_irq_enable();
|
|
task_unlock(tsk);
|
|
}
|
|
EXPORT_SYMBOL_GPL(unuse_mm);
|