Recovery action when get_user() triggers a machine check uses the fixup
path to make get_user() return -EFAULT. Also queue_task_work() sets up
so that kill_me_maybe() will be called on return to user mode to send a
SIGBUS to the current process.
But there are places in the kernel where the code assumes that this
EFAULT return was simply because of a page fault. The code takes some
action to fix that, and then retries the access. This results in a second
machine check.
While processing this second machine check queue_task_work() is called
again. But since this uses the same callback_head structure that
was used in the first call, the net result is an entry on the
current->task_works list that points to itself. When task_work_run()
is called it loops forever in this code:
do {
next = work->next;
work->func(work);
work = next;
cond_resched();
} while (work);
Add a "mce_busy" counter so that task_work_add() is only called once
per faulty page in this task.
Do not allow too many repeated machine checks, or machine checks to
a different page from the first.
Signed-off-by: Tony Luck <tony.luck@xxxxxxxxx>
---
V3: Thanks to extensive commentary from Andy & Boris
Throws out the changes to get_user() and subsequent changes to core
code. Everything is now handled in the machine check code. Downside is
that we can (and do) take multiple machine checks from a single poisoned
page before generic kernel code finally gets the message that a page is
really and truly gone (but all the failed get_user() calls still return
the legacy -EFAULT code, so none of that code will ever mistakenly use
a value from a bad page). But even on an old machine that does broadcast
interrupts for each machine check things survive multiple cycles of my
test injection into a futex operation.
I picked "10" as the magic upper limit for how many times the machine
check code will allow a fault from the same page before deciding to
panic. We can bike shed that value if you like.
arch/x86/kernel/cpu/mce/core.c | 27 ++++++++++++++++++++-------
include/linux/sched.h | 1 +
2 files changed, 21 insertions(+), 7 deletions(-)
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 13d3f1cbda17..25daf6517dc9 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -1246,6 +1246,7 @@ static void kill_me_maybe(struct callback_head *cb)
struct task_struct *p = container_of(cb, struct task_struct, mce_kill_me);
int flags = MF_ACTION_REQUIRED;
+ p->mce_count = 0;
pr_err("Uncorrected hardware memory error in user-access at %llx", p->mce_addr);
if (!p->mce_ripv)
@@ -1266,12 +1267,24 @@ static void kill_me_maybe(struct callback_head *cb)
}
}
-static void queue_task_work(struct mce *m, int kill_current_task)
+static void queue_task_work(struct mce *m, char *msg, int kill_current_task)
{
- current->mce_addr = m->addr;
- current->mce_kflags = m->kflags;
- current->mce_ripv = !!(m->mcgstatus & MCG_STATUS_RIPV);
- current->mce_whole_page = whole_page(m);
+ if (current->mce_count++ == 0) {
+ current->mce_addr = m->addr;
+ current->mce_kflags = m->kflags;
+ current->mce_ripv = !!(m->mcgstatus & MCG_STATUS_RIPV);
+ current->mce_whole_page = whole_page(m);
+ }
+
+ if (current->mce_count > 10)
+ mce_panic("Too many machine checks while accessing user data", m, msg);
+
+ if (current->mce_count > 1 || (current->mce_addr >> PAGE_SHIFT) != (m->addr >> PAGE_SHIFT))
+ mce_panic("Machine checks to different user pages", m, msg);
+
+ /* Do not call task_work_add() more than once */
+ if (current->mce_count > 1)
+ return;
if (kill_current_task)
current->mce_kill_me.func = kill_me_now;
@@ -1414,7 +1427,7 @@ noinstr void do_machine_check(struct pt_regs *regs)
/* If this triggers there is no way to recover. Die hard. */
BUG_ON(!on_thread_stack() || !user_mode(regs));
- queue_task_work(&m, kill_current_task);
+ queue_task_work(&m, msg, kill_current_task);
} else {
/*
@@ -1432,7 +1445,7 @@ noinstr void do_machine_check(struct pt_regs *regs)
}
if (m.kflags & MCE_IN_KERNEL_COPYIN)
- queue_task_work(&m, kill_current_task);
+ queue_task_work(&m, msg, kill_current_task);
}
out:
mce_wrmsrl(MSR_IA32_MCG_STATUS, 0);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 6e3a5eeec509..386366c9c757 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1362,6 +1362,7 @@ struct task_struct {
mce_whole_page : 1,
__mce_reserved : 62;
struct callback_head mce_kill_me;
+ int mce_count;
#endif
#ifdef CONFIG_KRETPROBES
--
2.21.1
