oslib/linux-blkzoned: make sure that we always support zone capacity

A common problem is that users upgrade their kernel to support NVMe ZNS
devices, however, they still use the kernel uapi headers provided by their
distro.

This means that even if the kernel will populate the zone capacity fields
for each zone in the zone report returned by the ioctl, fio will not know
how to interpret that data.

This leads to fio writing past the zone capacity, which will lead to
I/O errors.

It is not trivial for a user to realize that the kernel uapi headers
provided by their distro is the reason for these I/O errors.

In order to make it easier for these users, provide a copy of the current
zoned block device kernel uapi structs.

If the kernel uapi headers installed on the system are too old to support
zone capacity, use the locally defined structs instead.
If the installed headers are new enough to support zone capacity, use the
installed headers.

This way, fio will always be able to handle zone capacity (if the kernel
supports it). At the same time, we will not redefine any structs from the
installed headers if they are newer than our locally defined structs.

Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com>
Signed-off-by: Niklas Cassel <niklas.cassel@wdc.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

diff --git a/oslib/linux-blkzoned.c b/oslib/linux-blkzoned.c
index f37c67fc86953cadab7eaab2c539c79dbf81027d..81e4e7f0d53544aa40c2ac95533763dfa7ee2c1f 100644 (file)
--- a/oslib/linux-blkzoned.c
+++ b/oslib/linux-blkzoned.c
@@ -23,6 +23,37 @@
 
 #include <linux/blkzoned.h>
 
+/*
+ * If the uapi headers installed on the system lacks zone capacity support,
+ * use our local versions. If the installed headers are recent enough to
+ * support zone capacity, do not redefine any structs.
+ */
+#ifndef CONFIG_HAVE_REP_CAPACITY
+#define BLK_ZONE_REP_CAPACITY  (1 << 0)
+
+struct blk_zone_v2 {
+       __u64   start;          /* Zone start sector */
+       __u64   len;            /* Zone length in number of sectors */
+       __u64   wp;             /* Zone write pointer position */
+       __u8    type;           /* Zone type */
+       __u8    cond;           /* Zone condition */
+       __u8    non_seq;        /* Non-sequential write resources active */
+       __u8    reset;          /* Reset write pointer recommended */
+       __u8    resv[4];
+       __u64   capacity;       /* Zone capacity in number of sectors */
+       __u8    reserved[24];
+};
+#define blk_zone blk_zone_v2
+
+struct blk_zone_report_v2 {
+       __u64   sector;
+       __u32   nr_zones;
+       __u32   flags;
+struct blk_zone zones[0];
+};
+#define blk_zone_report blk_zone_report_v2
+#endif /* CONFIG_HAVE_REP_CAPACITY */
+
 /*
  * Read up to 255 characters from the first line of a file. Strip the trailing
  * newline.
@@ -116,10 +147,8 @@ out:
 static uint64_t zone_capacity(struct blk_zone_report *hdr,
                              struct blk_zone *blkz)
 {
-#ifdef CONFIG_HAVE_REP_CAPACITY
        if (hdr->flags & BLK_ZONE_REP_CAPACITY)
                return blkz->capacity << 9;
-#endif
        return blkz->len << 9;
 }