Add support for ZBC ioctl's
BLKREPORT - Issue Report Zones to device.
BLKZONEACTION - Issue a Zone Action (Close, Finish, Open, or Reset)
Signed-off-by: Shaun Tancheff <shaun.tanch...@seagate.com>
---
v8:
- Changed ioctl for zone actions to a single ioctl that takes
a structure including the zone, zone action, all flag, and force option
- Mapped REQ_META flag to 'force unit access' for zone operations
v6:
- Added GFP_DMA to gfp mask.
v4:
- Rebase on linux-next tag next-20160617.
- Change bio flags to bio op's
block/ioctl.c | 149 ++++++++++++++++++++++++++++++++++++++
include/uapi/linux/blkzoned_api.h | 30 +++++++-
include/uapi/linux/fs.h | 1 +
3 files changed, 179 insertions(+), 1 deletion(-)
diff --git a/block/ioctl.c b/block/ioctl.c
index ed2397f..d760523 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -194,6 +194,151 @@ int blkdev_reread_part(struct block_device *bdev)
}
EXPORT_SYMBOL(blkdev_reread_part);
+static int blk_zoned_report_ioctl(struct block_device *bdev, fmode_t mode,
+ void __user *parg)
+{
+ int error = -EFAULT;
+ gfp_t gfp = GFP_KERNEL | GFP_DMA;
+ void *iopg = NULL;
+ struct bdev_zone_report_io *bzrpt = NULL;
+ int order = 0;
+ struct page *pgs = NULL;
+ u32 alloc_size = PAGE_SIZE;
+ unsigned int op_flags = 0;
+ u8 opt = 0;
+
+ if (!(mode & FMODE_READ))
+ return -EBADF;
+
+ iopg = (void *)get_zeroed_page(gfp);
+ if (!iopg) {
+ error = -ENOMEM;
+ goto report_zones_out;
+ }
+ bzrpt = iopg;
+ if (copy_from_user(bzrpt, parg, sizeof(*bzrpt))) {
+ error = -EFAULT;
+ goto report_zones_out;
+ }
+ if (bzrpt->data.in.return_page_count > alloc_size) {
+ int npages;
+
+ alloc_size = bzrpt->data.in.return_page_count;
+ npages = (alloc_size + PAGE_SIZE - 1) >> PAGE_SHIFT;
+ pgs = alloc_pages(gfp, ilog2(npages));
+ if (pgs) {
+ void *mem = page_address(pgs);
+
+ if (!mem) {
+ error = -ENOMEM;
+ goto report_zones_out;
+ }
+ order = ilog2(npages);
+ memset(mem, 0, alloc_size);
+ memcpy(mem, bzrpt, sizeof(*bzrpt));
+ bzrpt = mem;
+ } else {
+ /* Result requires DMA capable memory */
+ pr_err("Not enough memory available for request.\n");
+ error = -ENOMEM;
+ goto report_zones_out;
+ }
+ } else {
+ alloc_size = bzrpt->data.in.return_page_count;
+ }
+ if (bzrpt->data.in.force_unit_access)
+ op_flags |= REQ_META;
+ opt = bzrpt->data.in.report_option;
+ error = blkdev_issue_zone_report(bdev, op_flags,
+ bzrpt->data.in.zone_locator_lba, opt,
+ pgs ? pgs : virt_to_page(iopg),
+ alloc_size, GFP_KERNEL);
+ if (error)
+ goto report_zones_out;
+
+ if (pgs) {
+ void *src = bzrpt;
+ u32 off = 0;
+
+ /*
+ * When moving a multi-order page with GFP_DMA
+ * the copy to user can trap "<spans multiple pages>"
+ * so instead we copy out 1 page at a time.
+ */
+ while (off < alloc_size && !error) {
+ u32 len = min_t(u32, PAGE_SIZE, alloc_size - off);
+
+ memcpy(iopg, src + off, len);
+ if (copy_to_user(parg + off, iopg, len))
+ error = -EFAULT;
+ off += len;
+ }
+ } else {
+ if (copy_to_user(parg, iopg, alloc_size))
+ error = -EFAULT;
+ }
+
+report_zones_out:
+ if (pgs)
+ __free_pages(pgs, order);
+ if (iopg)
+ free_page((unsigned long)iopg);
+ return error;
+}
+
+static int blk_zoned_action_ioctl(struct block_device *bdev, fmode_t mode,
+ void __user *parg)
+{
+ unsigned int op = 0;
+ unsigned int op_flags = 0;
+ sector_t lba;
+ struct bdev_zone_action za;
+
+ if (!(mode & FMODE_WRITE))
+ return -EBADF;
+
+ /* When acting on zones we explicitly disallow using a partition. */
+ if (bdev != bdev->bd_contains) {
+ pr_err("%s: All zone operations disallowed on this device\n",
+ __func__);
+ return -EFAULT;
+ }
+
+ if (copy_from_user(&za, parg, sizeof(za)))
+ return -EFAULT;
+
+ switch (za.action) {
+ case ZONE_ACTION_CLOSE:
+ op = REQ_OP_ZONE_CLOSE;
+ break;
+ case ZONE_ACTION_FINISH:
+ op = REQ_OP_ZONE_FINISH;
+ break;
+ case ZONE_ACTION_OPEN:
+ op = REQ_OP_ZONE_OPEN;
+ break;
+ case ZONE_ACTION_RESET:
+ op = REQ_OP_ZONE_RESET;
+ break;
+ default:
+ pr_err("%s: Unknown action: %u\n", __func__, za.action);
+ return -EINVAL;
+ }
+
+ lba = za.zone_locator_lba;
+ if (za.all_zones) {
+ if (lba) {
+ pr_err("%s: if all_zones, LBA must be 0.\n", __func__);
+ return -EINVAL;
+ }
+ lba = ~0ul;
+ }
+ if (za.force_unit_access || lba == ~0ul)
+ op_flags |= REQ_META;
+
+ return blkdev_issue_zone_action(bdev, op, op_flags, lba, GFP_KERNEL);
+}
+
static int blk_ioctl_discard(struct block_device *bdev, fmode_t mode,
unsigned long arg, unsigned long flags)
{
@@ -568,6 +713,10 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode,
unsigned cmd,
case BLKTRACESETUP:
case BLKTRACETEARDOWN:
return blk_trace_ioctl(bdev, cmd, argp);
+ case BLKREPORT:
+ return blk_zoned_report_ioctl(bdev, mode, argp);
+ case BLKZONEACTION:
+ return blk_zoned_action_ioctl(bdev, mode, argp);
case IOC_PR_REGISTER:
return blkdev_pr_register(bdev, argp);
case IOC_PR_RESERVE:
diff --git a/include/uapi/linux/blkzoned_api.h
b/include/uapi/linux/blkzoned_api.h
index d2bdba5..cd81a9f 100644
--- a/include/uapi/linux/blkzoned_api.h
+++ b/include/uapi/linux/blkzoned_api.h
@@ -115,6 +115,7 @@ enum bdev_zone_same {
* @zone_locator_lba: starting lba for first [reported] zone
* @return_page_count: number of *bytes* allocated for result
* @report_option: see: zone_report_option enum
+ * @force_unit_access: Force report from media
*
* Used to issue report zones command to connected device
*/
@@ -122,6 +123,25 @@ struct bdev_zone_get_report {
__u64 zone_locator_lba;
__u32 return_page_count;
__u8 report_option;
+ __u8 force_unit_access;
+} __packed;
+
+/**
+ * struct bdev_zone_action - ioctl: Perform Zone Action
+ *
+ * @zone_locator_lba: starting lba for first [reported] zone
+ * @return_page_count: number of *bytes* allocated for result
+ * @action: One of the ZONE_ACTION_*'s Close,Finish,Open, or Reset
+ * @all_zones: Flag to indicate if command should apply to all zones.
+ * @force_unit_access: Force command to media and update zone cache on success
+ *
+ * Used to issue report zones command to connected device
+ */
+struct bdev_zone_action {
+ __u64 zone_locator_lba;
+ __u32 action;
+ __u8 all_zones;
+ __u8 force_unit_access;
} __packed;
/**
@@ -134,7 +154,6 @@ struct bdev_zone_get_report {
* @lba_start: lba where the zone starts.
* @lba_wptr: lba of the current write pointer.
* @reserved: padding
- *
*/
struct bdev_zone_descriptor {
__u8 type;
@@ -179,4 +198,13 @@ struct bdev_zone_report_io {
} data;
} __packed;
+/* continuing from uapi/linux/fs.h: */
+#define BLKREPORT _IOWR(0x12, 130, struct bdev_zone_report_io)
+#define BLKZONEACTION _IOW(0x12, 131, struct bdev_zone_action)
+
+#define ZONE_ACTION_CLOSE 0x01
+#define ZONE_ACTION_FINISH 0x02
+#define ZONE_ACTION_OPEN 0x03
+#define ZONE_ACTION_RESET 0x04
+
#endif /* _UAPI_BLKZONED_API_H */
diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h
index 3b00f7c..350fb3f2 100644
--- a/include/uapi/linux/fs.h
+++ b/include/uapi/linux/fs.h
@@ -222,6 +222,7 @@ struct fsxattr {
#define BLKSECDISCARD _IO(0x12,125)
#define BLKROTATIONAL _IO(0x12,126)
#define BLKZEROOUT _IO(0x12,127)
+/* A jump here: See blkzoned_api.h, Reserving 130 and 131. */
#define BMAP_IOCTL 1 /* obsolete - kept for compatibility */
#define FIBMAP _IO(0x00,1) /* bmap access */
--
2.9.3
--
To unsubscribe from this list: send the line "unsubscribe linux-scsi" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
