[PATCH v4 1/3] platform/chrome: cros_ec_spi: Move to real time priority for transfers

From: Douglas Anderson
Date: Wed May 15 2019 - 12:50:35 EST


In commit 37a186225a0c ("platform/chrome: cros_ec_spi: Transfer
messages at high priority") we moved transfers to a high priority
workqueue. This helped make them much more reliable.

...but, we still saw failures.

We were actually finding ourselves competing for time with dm-crypt
which also scheduled work on HIGHPRI workqueues. While we can
consider reverting the change that made dm-crypt run its work at
HIGHPRI, the argument in commit a1b89132dc4f ("dm crypt: use
WQ_HIGHPRI for the IO and crypt workqueues") is somewhat compelling.
It does make sense for IO to be scheduled at a priority that's higher
than the default user priority. It also turns out that dm-crypt isn't
alone in using high priority like this. loop_prepare_queue() does
something similar for loopback devices.

Looking in more detail, it can be seen that the high priority
workqueue isn't actually that high of a priority. It runs at MIN_NICE
which is _fairly_ high priority but still below all real time
priority.

Should we move cros_ec_spi to real time priority to fix our problems,
or is this just escalating a priority war? I'll argue here that
cros_ec_spi _does_ belong at real time priority. Specifically
cros_ec_spi actually needs to run quickly for correctness. As I
understand this is exactly what real time priority is for.

There currently doesn't appear to be any way to use the standard
workqueue APIs with a real time priority, so we'll switch over to
using using a kthread worker. We'll match the priority that the SPI
core uses when it wants to do things on a realtime thread and just use
"MAX_RT_PRIO - 1".

This commit plus the patch ("platform/chrome: cros_ec_spi: Request the
SPI thread be realtime") are enough to get communications very close
to 100% reliable (the only known problem left is when serial console
is turned on, which isn't something that happens in shipping devices).
Specifically this test case now passes (tested on rk3288-veyron-jerry):

dd if=/dev/zero of=/var/log/foo.txt bs=4M count=512&
while true; do
ectool version > /dev/null;
done

It should be noted that "/var/log" is encrypted (and goes through
dm-crypt) and also passes through a loopback device.

Signed-off-by: Douglas Anderson <dianders@xxxxxxxxxxxx>
---

Changes in v4:
- No needless init of err in cros_ec_spi_devm_high_pri_alloc (Guenter).
- Removed blank lines near #includes (Guenter).
- Switch to kthread_create_worker() and fix error handling (Guenter).
- Cleaner devm code (Guenter).

Changes in v3:
- cros_ec realtime patch replaces revert; now patch #1

Changes in v2: None

drivers/platform/chrome/cros_ec_spi.c | 65 ++++++++++++++++++++++-----
1 file changed, 53 insertions(+), 12 deletions(-)

diff --git a/drivers/platform/chrome/cros_ec_spi.c b/drivers/platform/chrome/cros_ec_spi.c
index 8e9451720e73..1e38a885c539 100644
--- a/drivers/platform/chrome/cros_ec_spi.c
+++ b/drivers/platform/chrome/cros_ec_spi.c
@@ -12,7 +12,7 @@
#include <linux/platform_device.h>
#include <linux/slab.h>
#include <linux/spi/spi.h>
-
+#include <uapi/linux/sched/types.h>

/* The header byte, which follows the preamble */
#define EC_MSG_HEADER 0xec
@@ -67,12 +67,14 @@
* is sent when we want to turn on CS at the start of a transaction.
* @end_of_msg_delay: used to set the delay_usecs on the spi_transfer that
* is sent when we want to turn off CS at the end of a transaction.
+ * @high_pri_worker: Used to schedule high priority work.
*/
struct cros_ec_spi {
struct spi_device *spi;
s64 last_transfer_ns;
unsigned int start_of_msg_delay;
unsigned int end_of_msg_delay;
+ struct kthread_worker *high_pri_worker;
};

typedef int (*cros_ec_xfer_fn_t) (struct cros_ec_device *ec_dev,
@@ -89,7 +91,7 @@ typedef int (*cros_ec_xfer_fn_t) (struct cros_ec_device *ec_dev,
*/

struct cros_ec_xfer_work_params {
- struct work_struct work;
+ struct kthread_work work;
cros_ec_xfer_fn_t fn;
struct cros_ec_device *ec_dev;
struct cros_ec_command *ec_msg;
@@ -632,7 +634,7 @@ static int do_cros_ec_cmd_xfer_spi(struct cros_ec_device *ec_dev,
return ret;
}

-static void cros_ec_xfer_high_pri_work(struct work_struct *work)
+static void cros_ec_xfer_high_pri_work(struct kthread_work *work)
{
struct cros_ec_xfer_work_params *params;

@@ -644,12 +646,14 @@ static int cros_ec_xfer_high_pri(struct cros_ec_device *ec_dev,
struct cros_ec_command *ec_msg,
cros_ec_xfer_fn_t fn)
{
- struct cros_ec_xfer_work_params params;
-
- INIT_WORK_ONSTACK(&params.work, cros_ec_xfer_high_pri_work);
- params.ec_dev = ec_dev;
- params.ec_msg = ec_msg;
- params.fn = fn;
+ struct cros_ec_spi *ec_spi = ec_dev->priv;
+ struct cros_ec_xfer_work_params params = {
+ .work = KTHREAD_WORK_INIT(params.work,
+ cros_ec_xfer_high_pri_work),
+ .ec_dev = ec_dev,
+ .ec_msg = ec_msg,
+ .fn = fn,
+ };

/*
* This looks a bit ridiculous. Why do the work on a
@@ -660,9 +664,8 @@ static int cros_ec_xfer_high_pri(struct cros_ec_device *ec_dev,
* context switched out for too long and the EC giving up on
* the transfer.
*/
- queue_work(system_highpri_wq, &params.work);
- flush_work(&params.work);
- destroy_work_on_stack(&params.work);
+ kthread_queue_work(ec_spi->high_pri_worker, &params.work);
+ kthread_flush_work(&params.work);

return params.ret;
}
@@ -694,6 +697,40 @@ static void cros_ec_spi_dt_probe(struct cros_ec_spi *ec_spi, struct device *dev)
ec_spi->end_of_msg_delay = val;
}

+static void cros_ec_spi_high_pri_release(void *worker)
+{
+ kthread_destroy_worker(worker);
+}
+
+static int cros_ec_spi_devm_high_pri_alloc(struct device *dev,
+ struct cros_ec_spi *ec_spi)
+{
+ struct sched_param sched_priority = {
+ .sched_priority = MAX_RT_PRIO - 1,
+ };
+ int err;
+
+ ec_spi->high_pri_worker =
+ kthread_create_worker(0, "cros_ec_spi_high_pri");
+
+ if (IS_ERR(ec_spi->high_pri_worker)) {
+ err = PTR_ERR(ec_spi->high_pri_worker);
+ dev_err(dev, "Can't create cros_ec high pri worker: %d\n", err);
+ return err;
+ }
+
+ err = devm_add_action_or_reset(dev, cros_ec_spi_high_pri_release,
+ ec_spi->high_pri_worker);
+ if (err)
+ return err;
+
+ err = sched_setscheduler_nocheck(ec_spi->high_pri_worker->task,
+ SCHED_FIFO, &sched_priority);
+ if (err)
+ dev_err(dev, "Can't set cros_ec high pri priority: %d\n", err);
+ return err;
+}
+
static int cros_ec_spi_probe(struct spi_device *spi)
{
struct device *dev = &spi->dev;
@@ -732,6 +769,10 @@ static int cros_ec_spi_probe(struct spi_device *spi)

ec_spi->last_transfer_ns = ktime_get_ns();

+ err = cros_ec_spi_devm_high_pri_alloc(dev, ec_spi);
+ if (err)
+ return err;
+
err = cros_ec_register(ec_dev);
if (err) {
dev_err(dev, "cannot register EC\n");
--
2.21.0.1020.gf2820cf01a-goog