On Sun, Feb 04, 2024 at 04:01:44PM +0800, Shuai Xue wrote:
> Hardware errors could be signaled by asynchronous interrupt, e.g. when an
> error is detected by a background scrubber, or signaled by synchronous
> exception, e.g. when a CPU tries to access a poisoned cache line. Since
> commit a70297d22132 ("ACPI: APEI: set memory failure flags as
> MF_ACTION_REQUIRED on synchronous events")', the flag MF_ACTION_REQUIRED
> could be used to determine whether a synchronous exception occurs on ARM64
> platform. When a synchronous exception is detected, the kernel should
> terminate the current process which accessing the poisoned page. This is
"which has accessed poison data"
> done by sending a SIGBUS signal with an error code BUS_MCEERR_AR,
> indicating an action-required machine check error on read.
>
> However, the memory failure recovery is incorrectly sending a SIGBUS
> with wrong error code BUS_MCEERR_AO for synchronous errors in early kill
> mode, even MF_ACTION_REQUIRED is set. The main problem is that
"even if"
> synchronous errors are queued as a memory_failure() work, and are
> executed within a kernel thread context, not the user-space process that
> encountered the corrupted memory on ARM64 platform. As a result, when
> kill_proc() is called to terminate the process, it sends the incorrect
> SIGBUS error code because the context in which it operates is not the
> one where the error was triggered.
>
> To this end, queue memory_failure() as a task_work so that it runs in
> the context of the process that is actually consuming the poisoned data,
> and it will send SIBBUS with si_code BUS_MCEERR_AR.
SIGBUS
>
> Signed-off-by: Shuai Xue <xueshuai@xxxxxxxxxxxxxxxxx>
> Tested-by: Ma Wupeng <mawupeng1@xxxxxxxxxx>
> Reviewed-by: Kefeng Wang <wangkefeng.wang@xxxxxxxxxx>
> Reviewed-by: Xiaofei Tan <tanxiaofei@xxxxxxxxxx>
> Reviewed-by: Baolin Wang <baolin.wang@xxxxxxxxxxxxxxxxx>
> ---
> drivers/acpi/apei/ghes.c | 77 +++++++++++++++++++++++-----------------
> include/acpi/ghes.h | 3 --
> mm/memory-failure.c | 13 -------
> 3 files changed, 44 insertions(+), 49 deletions(-)
>
> diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
> index 0892550732d4..e5086d795bee 100644
> --- a/drivers/acpi/apei/ghes.c
> +++ b/drivers/acpi/apei/ghes.c
> @@ -465,28 +465,41 @@ static void ghes_clear_estatus(struct ghes *ghes,
> }
>
> /*
> - * Called as task_work before returning to user-space.
> - * Ensure any queued work has been done before we return to the context that
> - * triggered the notification.
> + * struct sync_task_work - for synchronous RAS event
What's so special about it being a "sync_"?
task_work is just fine and something else could use it too.
> + *
> + * @twork: callback_head for task work
> + * @pfn: page frame number of corrupted page
> + * @flags: fine tune action taken
s/fine tune action taken/work control flags/
> + *
> + * Structure to pass task work to be handled before
> + * ret_to_user via task_work_add().
What is "ret_to_user"?
If this is an ARM thing, then make sure you explain stuff properly and
detailed. This driver is used by multiple architectures.
> */
> -static void ghes_kick_task_work(struct callback_head *head)
> +struct sync_task_work {
> + struct callback_head twork;
> + u64 pfn;
> + int flags;
> +};
> +
> +static void memory_failure_cb(struct callback_head *twork)
> {
> - struct acpi_hest_generic_status *estatus;
> - struct ghes_estatus_node *estatus_node;
> - u32 node_len;
> + int ret;
> + struct sync_task_work *twcb =
> + container_of(twork, struct sync_task_work, twork);
Ugly linebreak - no need for it.
> - estatus_node = container_of(head, struct ghes_estatus_node, task_work);
> - if (IS_ENABLED(CONFIG_ACPI_APEI_MEMORY_FAILURE))
> - memory_failure_queue_kick(estatus_node->task_work_cpu);
> + ret = memory_failure(twcb->pfn, twcb->flags);
> + gen_pool_free(ghes_estatus_pool, (unsigned long)twcb, sizeof(*twcb));
>
> - estatus = GHES_ESTATUS_FROM_NODE(estatus_node);
> - node_len = GHES_ESTATUS_NODE_LEN(cper_estatus_len(estatus));
> - gen_pool_free(ghes_estatus_pool, (unsigned long)estatus_node, node_len);
> + if (!ret || ret == -EHWPOISON || ret == -EOPNOTSUPP)
> + return;
> +
> + pr_err("Sending SIGBUS to current task due to memory error not recovered");
> + force_sig(SIGBUS);
> }
>
> static bool ghes_do_memory_failure(u64 physical_addr, int flags)
> {
> unsigned long pfn;
> + struct sync_task_work *twcb;
>
> if (!IS_ENABLED(CONFIG_ACPI_APEI_MEMORY_FAILURE))
> return false;
> @@ -499,6 +512,18 @@ static bool ghes_do_memory_failure(u64 physical_addr, int flags)
> return false;
> }
>
> + if (flags == MF_ACTION_REQUIRED && current->mm) {
> + twcb = (void *)gen_pool_alloc(ghes_estatus_pool, sizeof(*twcb));
> + 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 true;
> + }
> +
> memory_failure_queue(pfn, flags);
> return true;
> }
> @@ -746,7 +771,7 @@ int cxl_cper_unregister_callback(cxl_cper_callback callback)
> }
> EXPORT_SYMBOL_NS_GPL(cxl_cper_unregister_callback, CXL);
>
> -static bool ghes_do_proc(struct ghes *ghes,
> +static void ghes_do_proc(struct ghes *ghes,
> const struct acpi_hest_generic_status *estatus)
> {
> int sev, sec_sev;
> @@ -814,8 +839,6 @@ static bool ghes_do_proc(struct ghes *ghes,
> pr_err("Sending SIGBUS to current task due to memory error not recovered");
> force_sig(SIGBUS);
> }
> -
> - return queued;
> }
>
> static void __ghes_print_estatus(const char *pfx,
> @@ -1117,9 +1140,7 @@ static void ghes_proc_in_irq(struct irq_work *irq_work)
> struct ghes_estatus_node *estatus_node;
> struct acpi_hest_generic *generic;
> struct acpi_hest_generic_status *estatus;
> - bool task_work_pending;
> u32 len, node_len;
> - int ret;
>
> llnode = llist_del_all(&ghes_estatus_llist);
> /*
> @@ -1134,25 +1155,16 @@ static void ghes_proc_in_irq(struct irq_work *irq_work)
> estatus = GHES_ESTATUS_FROM_NODE(estatus_node);
> len = cper_estatus_len(estatus);
> node_len = GHES_ESTATUS_NODE_LEN(len);
> - task_work_pending = ghes_do_proc(estatus_node->ghes, estatus);
> +
> + ghes_do_proc(estatus_node->ghes, estatus);
> +
> if (!ghes_estatus_cached(estatus)) {
> generic = estatus_node->generic;
> if (ghes_print_estatus(NULL, generic, estatus))
> ghes_estatus_cache_add(generic, estatus);
> }
> -
> - if (task_work_pending && current->mm) {
> - estatus_node->task_work.func = ghes_kick_task_work;
> - estatus_node->task_work_cpu = smp_processor_id();
> - ret = task_work_add(current, &estatus_node->task_work,
> - TWA_RESUME);
> - if (ret)
> - estatus_node->task_work.func = NULL;
> - }
> -
> - if (!estatus_node->task_work.func)
> - gen_pool_free(ghes_estatus_pool,
> - (unsigned long)estatus_node, node_len);
I have no clue why this is being removed.
Why doesn't a synchronous exception on ARM call into ghes_proc_in_irq()?
That SDEI thing certainly does.
Well looka here:
7f17b4a121d0 ("ACPI: APEI: Kick the memory_failure() queue for synchronous errors")
that thing does exactly what you're trying to "fix". So why doesn't that
work for you?
--
Regards/Gruss,
Boris.
https://people.kernel.org/tglx/notes-about-netiquette
