raid5-ppl: Partial Parity Log write logging implementation

Implement the calculation of partial parity for a stripe and PPL write
logging functionality. The description of PPL is added to the
documentation. More details can be found in the comments in raid5-ppl.c.

Attach a page for holding the partial parity data to stripe_head.
Allocate it only if mddev has the MD_HAS_PPL flag set.

Partial parity is the xor of not modified data chunks of a stripe and is
calculated as follows:

- reconstruct-write case:
  xor data from all not updated disks in a stripe

- read-modify-write case:
  xor old data and parity from all updated disks in a stripe

Implement it using the async_tx API and integrate into raid_run_ops().
It must be called when we still have access to old data, so do it when
STRIPE_OP_BIODRAIN is set, but before ops_run_prexor5(). The result is
stored into sh->ppl_page.

Partial parity is not meaningful for full stripe write and is not stored
in the log or used for recovery, so don't attempt to calculate it when
stripe has STRIPE_FULL_WRITE.

Put the PPL metadata structures to md_p.h because userspace tools
(mdadm) will also need to read/write PPL.

Warn about using PPL with enabled disk volatile write-back cache for
now. It can be removed once disk cache flushing before writing PPL is
implemented.

Signed-off-by: Artur Paszkiewicz <artur.paszkiewicz@intel.com>
Signed-off-by: Shaohua Li <shli@fb.com>

1 files changed, 27 insertions, 0 deletions

diff --git a/include/uapi/linux/raid/md_p.h b/include/uapi/linux/raid/md_p.h
index fe2112810c43..d9a1ead867b9 100644
--- a/include/uapi/linux/raid/md_p.h
+++ b/include/uapi/linux/raid/md_p.h
@@ -398,4 +398,31 @@ struct r5l_meta_block {
 
 #define R5LOG_VERSION 0x1
 #define R5LOG_MAGIC 0x6433c509
+
+struct ppl_header_entry {
+	__le64 data_sector;	/* raid sector of the new data */
+	__le32 pp_size;		/* length of partial parity */
+	__le32 data_size;	/* length of data */
+	__le32 parity_disk;	/* member disk containing parity */
+	__le32 checksum;	/* checksum of partial parity data for this
+				 * entry (~crc32c) */
+} __attribute__ ((__packed__));
+
+#define PPL_HEADER_SIZE 4096
+#define PPL_HDR_RESERVED 512
+#define PPL_HDR_ENTRY_SPACE \
+	(PPL_HEADER_SIZE - PPL_HDR_RESERVED - 4 * sizeof(u32) - sizeof(u64))
+#define PPL_HDR_MAX_ENTRIES \
+	(PPL_HDR_ENTRY_SPACE / sizeof(struct ppl_header_entry))
+
+struct ppl_header {
+	__u8 reserved[PPL_HDR_RESERVED];/* reserved space, fill with 0xff */
+	__le32 signature;		/* signature (family number of volume) */
+	__le32 padding;			/* zero pad */
+	__le64 generation;		/* generation number of the header */
+	__le32 entries_count;		/* number of entries in entry array */
+	__le32 checksum;		/* checksum of the header (~crc32c) */
+	struct ppl_header_entry entries[PPL_HDR_MAX_ENTRIES];
+} __attribute__ ((__packed__));
+
 #endif