/*
* get_mce_event:
* mce Pointer to machine_check_event structure to be filled.
* release Flag to indicate whether to free the event slot or not.
* 0 <= do not release the mce event. Caller will invoke
* release_mce_event() once event has been consumed.
* 1 <= release the slot.
*
* return 1 = success
* 0 = failure
*
* get_mce_event() will be called by platform specific machine check
* handle routine and in KVM.
* When we call get_mce_event(), we are still in interrupt context and
* preemption will not be scheduled until ret_from_expect() routine
* is called.
*/
int get_mce_event(struct machine_check_event *mce, bool release)
{
int index = __this_cpu_read(mce_nest_count) - 1;
struct machine_check_event *mc_evt;
int ret = 0;
/* Sanity check */
if (index < 0)
return ret;
/* Check if we have MCE info to process. */
if (index < MAX_MC_EVT) {
mc_evt = this_cpu_ptr(&mce_event[index]);
/* Copy the event structure and release the original */
if (mce)
*mce = *mc_evt;
if (release)
mc_evt->in_use = 0;
ret = 1;
}
/* Decrement the count to free the slot. */
if (release)
__this_cpu_dec(mce_nest_count);
return ret;
}
/**
* trace_call_bpf - invoke BPF program
* @prog: BPF program
* @ctx: opaque context pointer
*
* kprobe handlers execute BPF programs via this helper.
* Can be used from static tracepoints in the future.
*
* Return: BPF programs always return an integer which is interpreted by
* kprobe handler as:
* 0 - return from kprobe (event is filtered out)
* 1 - store kprobe event into ring buffer
* Other values are reserved and currently alias to 1
*/
unsigned int trace_call_bpf(struct bpf_prog *prog, void *ctx)
{
unsigned int ret;
if (in_nmi()) /* not supported yet */
return 1;
preempt_disable();
if (unlikely(__this_cpu_inc_return(bpf_prog_active) != 1)) {
/*
* since some bpf program is already running on this cpu,
* don't call into another bpf program (same or different)
* and don't send kprobe event into ring-buffer,
* so return zero here
*/
ret = 0;
goto out;
}
rcu_read_lock();
ret = BPF_PROG_RUN(prog, ctx);
rcu_read_unlock();
out:
__this_cpu_dec(bpf_prog_active);
preempt_enable();
return ret;
}
static void queue_ue_paddr(unsigned long paddr)
{
int index;
index = __this_cpu_inc_return(rtas_ue_count) - 1;
if (index >= MAX_MC_EVT) {
__this_cpu_dec(rtas_ue_count);
return;
}
this_cpu_write(rtas_ue_paddr[index], paddr);
schedule_work(&hwpoison_work);
}
static void pseries_hwpoison_work_fn(struct work_struct *work)
{
unsigned long paddr;
int index;
while (__this_cpu_read(rtas_ue_count) > 0) {
index = __this_cpu_read(rtas_ue_count) - 1;
paddr = __this_cpu_read(rtas_ue_paddr[index]);
memory_failure(paddr >> PAGE_SHIFT, 0);
__this_cpu_dec(rtas_ue_count);
}
}
/*
* Queue up the MCE event which then can be handled later.
*/
void machine_check_ue_event(struct machine_check_event *evt)
{
int index;
index = __this_cpu_inc_return(mce_ue_count) - 1;
/* If queue is full, just return for now. */
if (index >= MAX_MC_EVT) {
__this_cpu_dec(mce_ue_count);
return;
}
memcpy(this_cpu_ptr(&mce_ue_event_queue[index]), evt, sizeof(*evt));
/* Queue work to process this event later. */
schedule_work(&mce_ue_event_work);
}
/*
* process pending MCE event from the mce event queue. This function will be
* called during syscall exit.
*/
static void machine_check_process_queued_event(struct irq_work *work)
{
int index;
/*
* For now just print it to console.
* TODO: log this error event to FSP or nvram.
*/
while (__this_cpu_read(mce_queue_count) > 0) {
index = __this_cpu_read(mce_queue_count) - 1;
machine_check_print_event_info(
this_cpu_ptr(&mce_event_queue[index]));
__this_cpu_dec(mce_queue_count);
}
}
/*
* process pending MCE event from the mce event queue. This function will be
* called during syscall exit.
*/
static void machine_check_process_queued_event(struct irq_work *work)
{
int index;
add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);
/*
* For now just print it to console.
* TODO: log this error event to FSP or nvram.
*/
while (__this_cpu_read(mce_queue_count) > 0) {
index = __this_cpu_read(mce_queue_count) - 1;
machine_check_print_event_info(
this_cpu_ptr(&mce_event_queue[index]), false);
__this_cpu_dec(mce_queue_count);
}
}
/*
* Queue up the MCE event which then can be handled later.
*/
void machine_check_queue_event(void)
{
int index;
struct machine_check_event evt;
if (!get_mce_event(&evt, MCE_EVENT_RELEASE))
return;
index = __this_cpu_inc_return(mce_queue_count) - 1;
/* If queue is full, just return for now. */
if (index >= MAX_MC_EVT) {
__this_cpu_dec(mce_queue_count);
return;
}
memcpy(this_cpu_ptr(&mce_event_queue[index]), &evt, sizeof(evt));
/* Queue irq work to process this event later. */
irq_work_queue(&mce_event_process_work);
}
/**
* trace_call_bpf - invoke BPF program
* @call: tracepoint event
* @ctx: opaque context pointer
*
* kprobe handlers execute BPF programs via this helper.
* Can be used from static tracepoints in the future.
*
* Return: BPF programs always return an integer which is interpreted by
* kprobe handler as:
* 0 - return from kprobe (event is filtered out)
* 1 - store kprobe event into ring buffer
* Other values are reserved and currently alias to 1
*/
unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx)
{
unsigned int ret;
if (in_nmi()) /* not supported yet */
return 1;
preempt_disable();
if (unlikely(__this_cpu_inc_return(bpf_prog_active) != 1)) {
/*
* since some bpf program is already running on this cpu,
* don't call into another bpf program (same or different)
* and don't send kprobe event into ring-buffer,
* so return zero here
*/
ret = 0;
goto out;
}
/*
* Instead of moving rcu_read_lock/rcu_dereference/rcu_read_unlock
* to all call sites, we did a bpf_prog_array_valid() there to check
* whether call->prog_array is empty or not, which is
* a heurisitc to speed up execution.
*
* If bpf_prog_array_valid() fetched prog_array was
* non-NULL, we go into trace_call_bpf() and do the actual
* proper rcu_dereference() under RCU lock.
* If it turns out that prog_array is NULL then, we bail out.
* For the opposite, if the bpf_prog_array_valid() fetched pointer
* was NULL, you'll skip the prog_array with the risk of missing
* out of events when it was updated in between this and the
* rcu_dereference() which is accepted risk.
*/
ret = BPF_PROG_RUN_ARRAY_CHECK(call->prog_array, ctx, BPF_PROG_RUN);
out:
__this_cpu_dec(bpf_prog_active);
preempt_enable();
return ret;
}
