block: make /sys/block/<dev>/queue/discard_max_bytes writeable

Lots of devices support huge discard sizes these days. Depending
on how the device handles them internally, huge discards can
introduce massive latencies (hundreds of msec) on the device side.

We have a sysfs file, discard_max_bytes, that advertises the max
hardware supported discard size. Make this writeable, and split
the settings into a soft and hard limit. This can be set from
'discard_granularity' and up to the hardware limit.

Add a new sysfs file, 'discard_max_hw_bytes', that shows the hw
set limit.

Reviewed-by: Jeff Moyer <jmoyer@redhat.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

1 files changed, 39 insertions, 1 deletions

diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 6264b382d4d1..b1f34e463c0f 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -145,12 +145,43 @@ static ssize_t queue_discard_granularity_show(struct request_queue *q, char *pag
         return queue_var_show(q->limits.discard_granularity, page);
 }
 
+static ssize_t queue_discard_max_hw_show(struct request_queue *q, char *page)
+{
+        unsigned long long val;
+
+        val = q->limits.max_hw_discard_sectors << 9;
+        return sprintf(page, "%llu\n", val);
+}
+
 static ssize_t queue_discard_max_show(struct request_queue *q, char *page)
 {
         return sprintf(page, "%llu\n",
                        (unsigned long long)q->limits.max_discard_sectors << 9);
 }
 
+static ssize_t queue_discard_max_store(struct request_queue *q,
+                                       const char *page, size_t count)
+{
+        unsigned long max_discard;
+        ssize_t ret = queue_var_store(&max_discard, page, count);
+
+        if (ret < 0)
+                return ret;
+
+        if (max_discard & (q->limits.discard_granularity - 1))
+                return -EINVAL;
+
+        max_discard >>= 9;
+        if (max_discard > UINT_MAX)
+                return -EINVAL;
+
+        if (max_discard > q->limits.max_hw_discard_sectors)
+                max_discard = q->limits.max_hw_discard_sectors;
+
+        q->limits.max_discard_sectors = max_discard;
+        return ret;
+}
+
 static ssize_t queue_discard_zeroes_data_show(struct request_queue *q, char *page)
 {
         return queue_var_show(queue_discard_zeroes_data(q), page);
@@ -360,9 +391,15 @@ static struct queue_sysfs_entry queue_discard_granularity_entry = {
         .show = queue_discard_granularity_show,
 };
 
+static struct queue_sysfs_entry queue_discard_max_hw_entry = {
+        .attr = {.name = "discard_max_hw_bytes", .mode = S_IRUGO },
+        .show = queue_discard_max_hw_show,
+};
+
 static struct queue_sysfs_entry queue_discard_max_entry = {
-        .attr = {.name = "discard_max_bytes", .mode = S_IRUGO },
+        .attr = {.name = "discard_max_bytes", .mode = S_IRUGO | S_IWUSR },
         .show = queue_discard_max_show,
+        .store = queue_discard_max_store,
 };
 
 static struct queue_sysfs_entry queue_discard_zeroes_data_entry = {
@@ -421,6 +458,7 @@ static struct attribute *default_attrs[] = {
         &queue_io_opt_entry.attr,
         &queue_discard_granularity_entry.attr,
         &queue_discard_max_entry.attr,
+        &queue_discard_max_hw_entry.attr,
         &queue_discard_zeroes_data_entry.attr,
         &queue_write_same_max_entry.attr,
         &queue_nonrot_entry.attr,