On 2022/12/6 AM12:00, Xie XiuQi wrote:
> This series fix some issue for arm64 synchronous External Data Abort.
>
> 1. fix unhandled processor error
> According to the RAS documentation, if we cannot determine the impact
> of the error based on the details of the error when an SEA occurs, the
> process cannot safely continue to run. Therefore, for unhandled error,
> we should signal the system and terminate the process immediately.
>
> 2. improve for handling memory errors
>
> If error happened in current execution context, we need pass
> MF_ACTION_REQUIRED flag to memory_failure(), and if memory_failure()
> recovery failed, we must handle this case, other than ignore it.
>
> ---
> v3: add improve for handing memory errors
> v2: fix compile warning reported by kernel test robot.
>
> Xie XiuQi (4):
> ACPI: APEI: include missing acpi/apei.h
> arm64: ghes: fix error unhandling in synchronous External Data Abort
> arm64: ghes: handle the case when memory_failure recovery failed
> arm64: ghes: pass MF_ACTION_REQUIRED to memory_failure when sea
>
> arch/arm64/kernel/acpi.c | 6 ++++++
> drivers/acpi/apei/apei-base.c | 5 +++++
> drivers/acpi/apei/ghes.c | 31 ++++++++++++++++++++++++-------
> include/acpi/apei.h | 1 +
> include/linux/mm.h | 2 +-
> mm/memory-failure.c | 24 +++++++++++++++++-------
> 6 files changed, 54 insertions(+), 15 deletions(-)
>
Hi, XiuQi,
As we discussed, if you want to fix this problem before the new UEFI version comes out,
you need a another patch separated synchronous error handling into task work when SEA
notification is used. Be careful that do not break error handling of other notification
type.
A reference code is pasted bellow.
Thank you.
Best Regards,
Shuai
----
diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index 57cae48ebc1f..1982a5e3fd8c 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -445,15 +445,71 @@ static void ghes_kick_task_work(struct callback_head *head)
gen_pool_free(ghes_estatus_pool, (unsigned long)estatus_node, node_len);
}
+/**
+ * struct mce_task_work - for synchronous RAS event
+ *
+ * @twork: callback_head for task work
+ * @pfn: page frame number of corrupted page
+ * @flags: fine tune action taken
+ *
+ * Structure to pass task work to be handled before
+ * ret_to_user via task_work_add().
+ */
+struct mce_task_work {
+ struct callback_head twork;
+ u64 pfn;
+ int flags;
+};
+
+static void memory_failure_cb(struct callback_head *twork)
+{
+ int rc;
+ struct mce_task_work *twcb =
+ container_of(twork, struct mce_task_work, twork);
+
+ rc = memory_failure(twcb->pfn, twcb->flags);
+ kfree(twcb);
+
+ if (!rc)
+ return;
+ /*
+ * -EHWPOISON from memory_failure() means that it already sent SIGBUS
+ * to the current process with the proper error info,
+ * -EOPNOTSUPP means hwpoison_filter() filtered the error event,
+ *
+ * In both cases, no further processing is required.
+ */
+ if (ret == -EHWPOISON || ret == -EOPNOTSUPP)
+ return;
+
+ pr_err("Memory error not recovered");
+ force_sig(SIGBUS);
+}
+
static bool ghes_do_memory_failure(u64 physical_addr, int flags)
{
unsigned long pfn;
+ struct mce_task_work *twcb;
if (!IS_ENABLED(CONFIG_ACPI_APEI_MEMORY_FAILURE))
return false;
pfn = PHYS_PFN(physical_addr);
- memory_failure_queue(pfn, flags);
+
+ if (flags == MF_ACTION_REQUIRED && task->mm) {
+ twcb = kmalloc(sizeof(*twcb), GFP_ATOMIC);
+ if (!twcb)
+ return false;
+
+ twcb->pfn = pfn;
+ twcb->flags = flags;
+ init_task_work(&twcb->twork, memory_failure_cb);
+ task_work_add(current, &twcb->twork, TWA_RESUME);
+ return false;
+ } else {
+ memory_failure_queue(pfn, flags);
+ }
+
return true;
}
--
2.20.1.12.g72788fdb
