[PATCH 15/19] s390/dasd: Stamp a format label into newly formatted volumes

[Stefan Haberland <sth@linux.ibm.com>]

When a CDL volume is formatted, write a small on-disk label so the format
can later be recognised by the kernel. The next patch will use this for
ESE detection.

The label records a magic, a version, whether the volume is ESE, and
whether it was formatted quick (space released, thin) or full.

It lives in track 0, head 0, record 4 (the first non-special CDL record).
R4 is written by the same channel program that formats track 0
- its WRITE_CKD transfers count + the label data instead of count-only -
so label and track format reach the disk atomically; a valid magic then
marks a completed format without a separate, racy write.

Quick vs full is derived from a full space release (RAS) preceding the
format: dasd_eckd_release_space_full() sets a per-device flag the next
format consumes. Non-ESE volumes and formats without a preceding full
release are recorded as full.

struct dasd_format_label is exactly 512 bytes (the smallest block size)
so it fits one record; larger blocks zero-pad the rest.

Reviewed-by: Jan Höppner <hoeppner@linux.ibm.com>
Signed-off-by: Stefan Haberland <sth@linux.ibm.com>
---
 drivers/s390/block/dasd_eckd.c | 81 +++++++++++++++++++++++++++++++---
 drivers/s390/block/dasd_eckd.h | 38 ++++++++++++++++
 2 files changed, 114 insertions(+), 5 deletions(-)

diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c
index 62c03c4787c8..25a9055b97a2 100644
--- a/drivers/s390/block/dasd_eckd.c
+++ b/drivers/s390/block/dasd_eckd.c
@@ -19,6 +19,7 @@
 #include <linux/init.h>
 #include <linux/seq_file.h>
 #include <linux/uaccess.h>
+#include <linux/utsname.h>
 #include <linux/io.h>
 #include <linux/overflow.h>
 
@@ -2723,6 +2724,28 @@ dasd_eckd_build_check(struct dasd_device *base, struct format_data_t *fdata,
 	return cqr;
 }
 
+/* Fill the format label into a R4 record buffer, zero-padded to blksize. */
+static void dasd_eckd_fill_format_label(struct dasd_device *device, void *data,
+					unsigned int blksize)
+{
+	struct dasd_eckd_private *private = device->private;
+	struct dasd_format_label *label = data;
+
+	memset(label, 0, blksize);
+	label->magic = DASD_ESE_LABEL_MAGIC;
+	label->version = DASD_ESE_LABEL_VERSION;
+	if (dasd_eckd_is_ese(device))
+		label->flags |= DASD_ESE_LABEL_F_ESE;
+	if (private->ese_format_quick)
+		label->flags |= DASD_ESE_LABEL_F_QUICK;
+	else
+		label->flags |= DASD_ESE_LABEL_F_FULL;
+	label->blksize = blksize;
+	label->format_tod = get_tod_clock();
+	strscpy(label->kernel_version, init_utsname()->release,
+		sizeof(label->kernel_version));
+}
+
 static struct dasd_ccw_req *
 dasd_eckd_build_format(struct dasd_device *base, struct dasd_device *startdev,
 		       struct format_data_t *fdata, int enable_pav)
@@ -2741,6 +2764,7 @@ dasd_eckd_build_format(struct dasd_device *base, struct dasd_device *startdev,
 	int r0_perm;
 	int nr_tracks;
 	int use_prefix;
+	int write_label;
 
 	if (enable_pav)
 		startdev = dasd_alias_get_start_dev(base);
@@ -2774,6 +2798,15 @@ dasd_eckd_build_format(struct dasd_device *base, struct dasd_device *startdev,
 
 	use_prefix = base_priv->features.feature[8] & 0x01;
 
+	/*
+	 * Stamp the format label into R4 of the very first track. Only for CDL
+	 * (R4 is the first non-special record there), only when this request
+	 * covers track 0, only for the record-writing format intensities (not
+	 * track invalidation), and only if the track actually has an R4.
+	 */
+	write_label = (intensity & 0x08) && !((intensity & ~0x08) & 0x04) &&
+		      fdata->start_unit == 0 && rpt > 3;
+
 	switch (intensity) {
 	case 0x00:	/* Normal format */
 	case 0x08:	/* Normal format, use cdl. */
@@ -2820,6 +2853,10 @@ dasd_eckd_build_format(struct dasd_device *base, struct dasd_device *startdev,
 		return ERR_PTR(-EINVAL);
 	}
 
+	/* room for the label data that R4 carries in addition to its count */
+	if (write_label)
+		datasize += fdata->blksize;
+
 	fcp = dasd_fmalloc_request(DASD_ECKD_MAGIC, cplength, datasize, startdev);
 	if (IS_ERR(fcp))
 		return fcp;
@@ -2964,7 +3001,21 @@ dasd_eckd_build_format(struct dasd_device *base, struct dasd_device *startdev,
 					ccw->cmd_code =
 						DASD_ECKD_CCW_WRITE_CKD_MT;
 				ccw->flags = CCW_FLAG_SLI;
-				ccw->count = 8;
+				if (write_label && address.cyl == 0 &&
+				    address.head == 0 && i == 3) {
+					/*
+					 * R4 carries the label as its record
+					 * data; it follows ect contiguously so
+					 * the CCW transfers count + data.
+					 */
+					dasd_eckd_fill_format_label(base,
+								    data,
+								    fdata->blksize);
+					data += fdata->blksize;
+					ccw->count = 8 + fdata->blksize;
+				} else {
+					ccw->count = 8;
+				}
 				ccw->cda = virt_to_dma32(ect);
 				ccw++;
 			}
@@ -3174,6 +3225,9 @@ static int dasd_eckd_format_process_data(struct dasd_device *base,
 static int dasd_eckd_format_device(struct dasd_device *base,
 				   struct format_data_t *fdata, int enable_pav)
 {
+	struct dasd_eckd_private *private = base->private;
+	int rc;
+
 	/*
 	 * A full format (start_unit == 0) returns the device to a fully sparse
 	 * state, so restart the heuristic from ft1 without an offline cycle.
@@ -3181,8 +3235,18 @@ static int dasd_eckd_format_device(struct dasd_device *base,
 	if (fdata->start_unit == 0)
 		dasd_ft_bias_apply(base);
 
-	return dasd_eckd_format_process_data(base, fdata, enable_pav, 0, NULL,
-					     0, NULL);
+	rc = dasd_eckd_format_process_data(base, fdata, enable_pav, 0, NULL,
+					   0, NULL);
+
+	/*
+	 * The quick-format indicator was consumed by the label stamped into
+	 * track 0; clear it so a later format that is not preceded by a full
+	 * space release is recorded as a full format.
+	 */
+	if (fdata->start_unit == 0)
+		private->ese_format_quick = 0;
+
+	return rc;
 }
 
 static bool test_and_set_format_track(sector_t start, sector_t end,
@@ -4085,6 +4149,7 @@ dasd_eckd_dso_ras(struct dasd_device *device, struct dasd_block *block,
 
 static int dasd_eckd_release_space_full(struct dasd_device *device)
 {
+	struct dasd_eckd_private *private;
 	struct dasd_ccw_req *cqr;
 	int rc;
 
@@ -4096,10 +4161,16 @@ static int dasd_eckd_release_space_full(struct dasd_device *device)
 
 	if (!rc) {
 		/*
-		 * Releasing all space (RAS) wipes every track and the device is fully
-		 * sparse again, so restart the heuristic from ft1.
+		 * Releasing all space (RAS) wipes every track and the device is
+		 * fully sparse again, so restart the heuristic from ft1.
 		 */
 		dasd_ft_bias_apply(device);
+		/*
+		 * A full release is what makes a subsequent format a quick
+		 * (thin) one; remember it so the format label records that.
+		 */
+		private = device->private;
+		private->ese_format_quick = 1;
 	}
 
 	dasd_sfree_request(cqr, cqr->memdev);
diff --git a/drivers/s390/block/dasd_eckd.h b/drivers/s390/block/dasd_eckd.h
index 0fdb92fdddc8..92fd8ac92b79 100644
--- a/drivers/s390/block/dasd_eckd.h
+++ b/drivers/s390/block/dasd_eckd.h
@@ -159,6 +159,39 @@ struct eckd_r0 {
 #define DASD_EAV_CYL_HI_SHIFT	16	/* cylinder bits beyond the 16-bit cyl field */
 #define DASD_EAV_HEAD_HI_SHIFT	4	/* head occupies the low-order 4 bits of head */
 
+/*
+ * On-disk DASD format label.
+ *
+ * Written into track 0, head 0, record 4 (R4 - the first non-special CDL
+ * record) as part of the same channel program that formats track 0, so it is
+ * stored atomically with the track: either both the track format and the label
+ * make it to disk or neither does. Its presence with a valid magic therefore
+ * marks a completed format and can be used for format detection.
+ *
+ * The structure is exactly the smallest supported block size (512 bytes) so it
+ * always fits into a single record.
+ * For larger block sizes the rest of the record is zero padded.
+ * The magic together with the version is used to recognise a valid label.
+ */
+#define DASD_ESE_LABEL_MAGIC	0xC4C1E2C4C6D4E3F1ULL	/* EBCDIC "DASDFMT1" */
+#define DASD_ESE_LABEL_VERSION	1
+
+/* dasd_format_label.flags */
+#define DASD_ESE_LABEL_F_ESE	0x00000001	/* volume is extent space efficient */
+#define DASD_ESE_LABEL_F_QUICK	0x00000002	/* quick (space released) format */
+#define DASD_ESE_LABEL_F_FULL	0x00000004	/* full format */
+
+struct dasd_format_label {
+	__u64 magic;			/* DASD_ESE_LABEL_MAGIC */
+	__u32 version;			/* DASD_ESE_LABEL_VERSION */
+	__u32 flags;			/* DASD_ESE_LABEL_F_* */
+	__u32 blksize;			/* block size the volume was formatted with */
+	__u32 reserved0;
+	__u64 format_tod;		/* TOD clock at format time */
+	__u8  kernel_version[64];	/* NUL terminated kernel release (uname -r) */
+	__u8  reserved[416];		/* pad the struct to 512 bytes */
+} __packed;
+
 struct ch_t {
 	__u16 cyl;
 	__u16 head;
@@ -709,6 +742,11 @@ struct dasd_eckd_private {
 
 	u32 fcx_max_data;
 	char suc_reason;
+	/*
+	 * Set when the whole volume's space was released (full RAS); consumed by
+	 * the next format to mark the on-disk label as a quick (vs full) format.
+	 */
+	int ese_format_quick;
 };
 
 
-- 
2.53.0