mdadm/0004-super1-PPL-support.patch

From 35753b5ec92fd1d80c22b91aee4b61ed69691986 Mon Sep 17 00:00:00 2001
From: Artur Paszkiewicz <artur.paszkiewicz@intel.com>
Date: Thu, 16 Mar 2017 22:09:46 +0100
Subject: [PATCH] super1: PPL support

Enable creating and assembling raid5 arrays with PPL for 1.x metadata.

When creating, reserve enough space for PPL and store its size and
location in the superblock and set MD_FEATURE_PPL bit. Write an initial
empty header in the PPL area on each device. PPL is stored in the
metadata region reserved for internal write-intent bitmap, so don't
allow using bitmap and PPL together.

While at it, fix two endianness issues in write_empty_r5l_meta_block()
and write_init_super1().

Signed-off-by: Artur Paszkiewicz <artur.paszkiewicz@intel.com>
---
 Assemble.c    |   3 ++
 Create.c      |   2 +
 Grow.c        |  15 +++++-
 Incremental.c |   3 ++
 mdadm.h       |   1 +
 super1.c      | 150 +++++++++++++++++++++++++++++++++++++++++++++++++++-------
 6 files changed, 155 insertions(+), 19 deletions(-)

diff --git a/Assemble.c b/Assemble.c
index 8e55b49fa406..c09842016c0a 100644
--- a/Assemble.c
+++ b/Assemble.c
@@ -962,6 +962,9 @@ static int start_array(int mdfd,
 		c->readonly = 1;
 	}
 
+	if (content->consistency_policy == CONSISTENCY_POLICY_PPL)
+		clean = 1;
+
 	rv = set_array_info(mdfd, st, content);
 	if (rv && !err_ok) {
 		pr_err("failed to set array info for %s: %s\n",
diff --git a/Create.c b/Create.c
index 4080bf69f05b..10e7d108956d 100644
--- a/Create.c
+++ b/Create.c
@@ -524,6 +524,8 @@ int Create(struct supertype *st, char *mddev,
 	if (!s->bitmap_file &&
 	    s->level >= 1 &&
 	    st->ss->add_internal_bitmap &&
+	    (s->consistency_policy != CONSISTENCY_POLICY_RESYNC &&
+	     s->consistency_policy != CONSISTENCY_POLICY_PPL) &&
 	    (s->write_behind || s->size > 100*1024*1024ULL)) {
 		if (c->verbose > 0)
 			pr_err("automatically enabling write-intent bitmap on large array\n");
diff --git a/Grow.c b/Grow.c
index 455c5f90bf58..e4351d7f952a 100755
--- a/Grow.c
+++ b/Grow.c
@@ -290,6 +290,7 @@ int Grow_addbitmap(char *devname, int fd, struct context *c, struct shape *s)
 	int major = BITMAP_MAJOR_HI;
 	int vers = md_get_version(fd);
 	unsigned long long bitmapsize, array_size;
+	struct mdinfo *mdi;
 
 	if (vers < 9003) {
 		major = BITMAP_MAJOR_HOSTENDIAN;
@@ -389,12 +390,23 @@ int Grow_addbitmap(char *devname, int fd, struct context *c, struct shape *s)
 		free(st);
 		return 1;
 	}
+
+	mdi = sysfs_read(fd, NULL, GET_CONSISTENCY_POLICY);
+	if (mdi) {
+		if (mdi->consistency_policy == CONSISTENCY_POLICY_PPL) {
+			pr_err("Cannot add bitmap to array with PPL\n");
+			free(mdi);
+			free(st);
+			return 1;
+		}
+		free(mdi);
+	}
+
 	if (strcmp(s->bitmap_file, "internal") == 0 ||
 	    strcmp(s->bitmap_file, "clustered") == 0) {
 		int rv;
 		int d;
 		int offset_setable = 0;
-		struct mdinfo *mdi;
 		if (st->ss->add_internal_bitmap == NULL) {
 			pr_err("Internal bitmaps not supported with %s metadata\n", st->ss->name);
 			return 1;
@@ -446,6 +458,7 @@ int Grow_addbitmap(char *devname, int fd, struct context *c, struct shape *s)
 			sysfs_init(mdi, fd, NULL);
 			rv = sysfs_set_num_signed(mdi, NULL, "bitmap/location",
 						  mdi->bitmap_offset);
+			free(mdi);
 		} else {
 			if (strcmp(s->bitmap_file, "clustered") == 0)
 				array.state |= (1 << MD_SB_CLUSTERED);
diff --git a/Incremental.c b/Incremental.c
index 0f507bb32c9e..81afc7ec36ae 100644
--- a/Incremental.c
+++ b/Incremental.c
@@ -528,6 +528,9 @@ int Incremental(struct mddev_dev *devlist, struct context *c,
 
 	journal_device_missing = (info.journal_device_required) && (info.journal_clean == 0);
 
+	if (info.consistency_policy == CONSISTENCY_POLICY_PPL)
+		info.array.state |= 1;
+
 	if (enough(info.array.level, info.array.raid_disks,
 		   info.array.layout, info.array.state & 1,
 		   avail) == 0) {
diff --git a/mdadm.h b/mdadm.h
index 10c204160351..ab1b7fc66e7c 100644
--- a/mdadm.h
+++ b/mdadm.h
@@ -302,6 +302,7 @@ struct mdinfo {
 	long			bitmap_offset;	/* 0 == none, 1 == a file */
 	unsigned int		ppl_size;
 	unsigned long long	ppl_sector;
+	int			ppl_offset;
 	unsigned long		safe_mode_delay; /* ms delay to mark clean */
 	int			new_level, delta_disks, new_layout, new_chunk;
 	int			errors;
diff --git a/super1.c b/super1.c
index 672cdde690b4..76eeca111821 100644
--- a/super1.c
+++ b/super1.c
@@ -48,10 +48,18 @@ struct mdp_superblock_1 {
 
 	__u32	chunksize;	/* in 512byte sectors */
 	__u32	raid_disks;
-	__u32	bitmap_offset;	/* sectors after start of superblock that bitmap starts
-				 * NOTE: signed, so bitmap can be before superblock
-				 * only meaningful of feature_map[0] is set.
-				 */
+	union {
+		__u32	bitmap_offset;	/* sectors after start of superblock that bitmap starts
+					 * NOTE: signed, so bitmap can be before superblock
+					 * only meaningful of feature_map[0] is set.
+					 */
+
+		/* only meaningful when feature_map[MD_FEATURE_PPL] is set */
+		struct {
+			__s16 offset; /* sectors from start of superblock that ppl starts */
+			__u16 size; /* ppl size in sectors */
+		} ppl;
+	};
 
 	/* These are only valid with feature bit '4' */
 	__u32	new_level;	/* new level we are reshaping to		*/
@@ -131,6 +139,7 @@ struct misc_dev_info {
 #define	MD_FEATURE_NEW_OFFSET		64 /* new_offset must be honoured */
 #define	MD_FEATURE_BITMAP_VERSIONED	256 /* bitmap version number checked properly */
 #define	MD_FEATURE_JOURNAL		512 /* support write journal */
+#define	MD_FEATURE_PPL			1024 /* support PPL */
 #define	MD_FEATURE_ALL			(MD_FEATURE_BITMAP_OFFSET	\
 					|MD_FEATURE_RECOVERY_OFFSET	\
 					|MD_FEATURE_RESHAPE_ACTIVE	\
@@ -140,6 +149,7 @@ struct misc_dev_info {
 					|MD_FEATURE_NEW_OFFSET		\
 					|MD_FEATURE_BITMAP_VERSIONED	\
 					|MD_FEATURE_JOURNAL		\
+					|MD_FEATURE_PPL			\
 					)
 
 #ifndef MDASSEMBLE
@@ -289,6 +299,11 @@ static int awrite(struct align_fd *afd, void *buf, int len)
 	return len;
 }
 
+static inline unsigned int choose_ppl_space(int chunk)
+{
+	return (PPL_HEADER_SIZE >> 9) + (chunk > 128*2 ? chunk : 128*2);
+}
+
 #ifndef MDASSEMBLE
 static void examine_super1(struct supertype *st, char *homehost)
 {
@@ -392,6 +407,10 @@ static void examine_super1(struct supertype *st, char *homehost)
 	if (sb->feature_map & __cpu_to_le32(MD_FEATURE_BITMAP_OFFSET)) {
 		printf("Internal Bitmap : %ld sectors from superblock\n",
 		       (long)(int32_t)__le32_to_cpu(sb->bitmap_offset));
+	} else if (sb->feature_map & __cpu_to_le32(MD_FEATURE_PPL)) {
+		printf("            PPL : %u sectors at offset %d sectors from superblock\n",
+		       __le16_to_cpu(sb->ppl.size),
+		       __le16_to_cpu(sb->ppl.offset));
 	}
 	if (sb->feature_map & __cpu_to_le32(MD_FEATURE_RESHAPE_ACTIVE)) {
 		printf("  Reshape pos'n : %llu%s\n", (unsigned long long)__le64_to_cpu(sb->reshape_position)/2,
@@ -934,10 +953,16 @@ static void getinfo_super1(struct supertype *st, struct mdinfo *info, char *map)
 	if (__le32_to_cpu(bsb->nodes) > 1)
 		info->array.state |= (1 << MD_SB_CLUSTERED);
 
+	super_offset = __le64_to_cpu(sb->super_offset);
 	info->data_offset = __le64_to_cpu(sb->data_offset);
 	info->component_size = __le64_to_cpu(sb->size);
-	if (sb->feature_map & __le32_to_cpu(MD_FEATURE_BITMAP_OFFSET))
+	if (sb->feature_map & __le32_to_cpu(MD_FEATURE_BITMAP_OFFSET)) {
 		info->bitmap_offset = (int32_t)__le32_to_cpu(sb->bitmap_offset);
+	} else if (sb->feature_map & __le32_to_cpu(MD_FEATURE_PPL)) {
+		info->ppl_offset = __le16_to_cpu(sb->ppl.offset);
+		info->ppl_size = __le16_to_cpu(sb->ppl.size);
+		info->ppl_sector = super_offset + info->ppl_offset;
+	}
 
 	info->disk.major = 0;
 	info->disk.minor = 0;
@@ -948,7 +973,6 @@ static void getinfo_super1(struct supertype *st, struct mdinfo *info, char *map)
 	else
 		role = __le16_to_cpu(sb->dev_roles[__le32_to_cpu(sb->dev_number)]);
 
-	super_offset = __le64_to_cpu(sb->super_offset);
 	if (info->array.level <= 0)
 		data_size = __le64_to_cpu(sb->data_size);
 	else
@@ -965,8 +989,8 @@ static void getinfo_super1(struct supertype *st, struct mdinfo *info, char *map)
 				end = bboffset;
 		}
 
-		if (super_offset + info->bitmap_offset < end)
-			end = super_offset + info->bitmap_offset;
+		if (super_offset + info->bitmap_offset + info->ppl_offset < end)
+			end = super_offset + info->bitmap_offset + info->ppl_offset;
 
 		if (info->data_offset + data_size < end)
 			info->space_after = end - data_size - info->data_offset;
@@ -982,6 +1006,11 @@ static void getinfo_super1(struct supertype *st, struct mdinfo *info, char *map)
 			bmend += size;
 			if (bmend > earliest)
 				earliest = bmend;
+		} else if (info->ppl_offset > 0) {
+			unsigned long long pplend = info->ppl_offset +
+						    info->ppl_size;
+			if (pplend > earliest)
+				earliest = pplend;
 		}
 		if (sb->bblog_offset && sb->bblog_size) {
 			unsigned long long bbend = super_offset;
@@ -1075,8 +1104,20 @@ static void getinfo_super1(struct supertype *st, struct mdinfo *info, char *map)
 	}
 
 	info->array.working_disks = working;
-	if (sb->feature_map & __le32_to_cpu(MD_FEATURE_JOURNAL))
+
+	if (sb->feature_map & __le32_to_cpu(MD_FEATURE_JOURNAL)) {
 		info->journal_device_required = 1;
+		info->consistency_policy = CONSISTENCY_POLICY_JOURNAL;
+	} else if (sb->feature_map & __le32_to_cpu(MD_FEATURE_PPL)) {
+		info->consistency_policy = CONSISTENCY_POLICY_PPL;
+	} else if (sb->feature_map & __le32_to_cpu(MD_FEATURE_BITMAP_OFFSET)) {
+		info->consistency_policy = CONSISTENCY_POLICY_BITMAP;
+	} else if (info->array.level <= 0) {
+		info->consistency_policy = CONSISTENCY_POLICY_NONE;
+	} else {
+		info->consistency_policy = CONSISTENCY_POLICY_RESYNC;
+	}
+
 	info->journal_clean = 0;
 }
 
@@ -1239,6 +1280,9 @@ static int update_super1(struct supertype *st, struct mdinfo *info,
 		if (sb->feature_map & __cpu_to_le32(MD_FEATURE_BITMAP_OFFSET)) {
 			bitmap_offset = (long)__le32_to_cpu(sb->bitmap_offset);
 			bm_sectors = calc_bitmap_size(bms, 4096) >> 9;
+		} else if (sb->feature_map & __cpu_to_le32(MD_FEATURE_PPL)) {
+			bitmap_offset = (long)__le16_to_cpu(sb->ppl.offset);
+			bm_sectors = (long)__le16_to_cpu(sb->ppl.size);
 		}
 #endif
 		if (sb_offset < data_offset) {
@@ -1472,6 +1516,9 @@ static int init_super1(struct supertype *st, mdu_array_info_t *info,
 
 	memset(sb->dev_roles, 0xff, MAX_SB_SIZE - sizeof(struct mdp_superblock_1));
 
+	if (s->consistency_policy == CONSISTENCY_POLICY_PPL)
+		sb->feature_map |= __cpu_to_le32(MD_FEATURE_PPL);
+
 	return 1;
 }
 
@@ -1643,10 +1690,49 @@ static unsigned long choose_bm_space(unsigned long devsize)
 
 static void free_super1(struct supertype *st);
 
-#define META_BLOCK_SIZE 4096
+#ifndef MDASSEMBLE
+
 __u32 crc32c_le(__u32 crc, unsigned char const *p, size_t len);
 
-#ifndef MDASSEMBLE
+static int write_init_ppl1(struct supertype *st, struct mdinfo *info, int fd)
+{
+	struct mdp_superblock_1 *sb = st->sb;
+	void *buf;
+	struct ppl_header *ppl_hdr;
+	int ret;
+
+	ret = posix_memalign(&buf, 4096, PPL_HEADER_SIZE);
+	if (ret) {
+		pr_err("Failed to allocate PPL header buffer\n");
+		return ret;
+	}
+
+	memset(buf, 0, PPL_HEADER_SIZE);
+	ppl_hdr = buf;
+	memset(ppl_hdr->reserved, 0xff, PPL_HDR_RESERVED);
+	ppl_hdr->signature = __cpu_to_le32(~crc32c_le(~0, sb->set_uuid,
+						      sizeof(sb->set_uuid)));
+	ppl_hdr->checksum = __cpu_to_le32(~crc32c_le(~0, buf, PPL_HEADER_SIZE));
+
+	if (lseek64(fd, info->ppl_sector * 512, SEEK_SET) < 0) {
+		ret = errno;
+		perror("Failed to seek to PPL header location");
+	}
+
+	if (!ret && write(fd, buf, PPL_HEADER_SIZE) != PPL_HEADER_SIZE) {
+		ret = errno;
+		perror("Write PPL header failed");
+	}
+
+	if (!ret)
+		fsync(fd);
+
+	free(buf);
+	return ret;
+}
+
+#define META_BLOCK_SIZE 4096
+
 static int write_empty_r5l_meta_block(struct supertype *st, int fd)
 {
 	struct r5l_meta_block *mb;
@@ -1673,7 +1759,7 @@ static int write_empty_r5l_meta_block(struct supertype *st, int fd)
 	crc = crc32c_le(crc, (void *)mb, META_BLOCK_SIZE);
 	mb->checksum = crc;
 
-	if (lseek64(fd, (sb->data_offset) * 512, 0) < 0LL) {
+	if (lseek64(fd, __le64_to_cpu(sb->data_offset) * 512, 0) < 0LL) {
 		pr_err("cannot seek to offset of the meta block\n");
 		goto fail_to_write;
 	}
@@ -1706,7 +1792,7 @@ static int write_init_super1(struct supertype *st)
 
 	for (di = st->info; di; di = di->next) {
 		if (di->disk.state & (1 << MD_DISK_JOURNAL))
-			sb->feature_map |= MD_FEATURE_JOURNAL;
+			sb->feature_map |= __cpu_to_le32(MD_FEATURE_JOURNAL);
 	}
 
 	for (di = st->info; di; di = di->next) {
@@ -1781,6 +1867,21 @@ static int write_init_super1(struct supertype *st)
 					(((char *)sb) + MAX_SB_SIZE);
 			bm_space = calc_bitmap_size(bms, 4096) >> 9;
 			bm_offset = (long)__le32_to_cpu(sb->bitmap_offset);
+		} else if (sb->feature_map & __cpu_to_le32(MD_FEATURE_PPL)) {
+			bm_space = choose_ppl_space(__le32_to_cpu(sb->chunksize));
+			if (bm_space > UINT16_MAX)
+				bm_space = UINT16_MAX;
+			if (st->minor_version == 0) {
+				bm_offset = -bm_space - 8;
+				if (bm_offset < INT16_MIN) {
+					bm_offset = INT16_MIN;
+					bm_space = -bm_offset - 8;
+				}
+			} else {
+				bm_offset = 8;
+			}
+			sb->ppl.offset = __cpu_to_le16(bm_offset);
+			sb->ppl.size = __cpu_to_le16(bm_space);
 		} else {
 			bm_space = choose_bm_space(array_size);
 			bm_offset = 8;
@@ -1852,8 +1953,17 @@ static int write_init_super1(struct supertype *st)
 				goto error_out;
 		}
 
-		if (rv == 0 && (__le32_to_cpu(sb->feature_map) & 1))
+		if (rv == 0 &&
+		    (__le32_to_cpu(sb->feature_map) & MD_FEATURE_BITMAP_OFFSET)) {
 			rv = st->ss->write_bitmap(st, di->fd, NodeNumUpdate);
+		} else if (rv == 0 &&
+			 (__le32_to_cpu(sb->feature_map) & MD_FEATURE_PPL)) {
+			struct mdinfo info;
+
+			st->ss->getinfo_super(st, &info, NULL);
+			rv = st->ss->write_init_ppl(st, &info, di->fd);
+		}
+
 		close(di->fd);
 		di->fd = -1;
 		if (rv)
@@ -2121,11 +2231,13 @@ static __u64 avail_size1(struct supertype *st, __u64 devsize,
 		return 0;
 
 #ifndef MDASSEMBLE
-	if (__le32_to_cpu(super->feature_map)&MD_FEATURE_BITMAP_OFFSET) {
+	if (__le32_to_cpu(super->feature_map) & MD_FEATURE_BITMAP_OFFSET) {
 		/* hot-add. allow for actual size of bitmap */
 		struct bitmap_super_s *bsb;
 		bsb = (struct bitmap_super_s *)(((char*)super)+MAX_SB_SIZE);
 		bmspace = calc_bitmap_size(bsb, 4096) >> 9;
+	} else if (__le32_to_cpu(super->feature_map) & MD_FEATURE_PPL) {
+		bmspace = __le16_to_cpu(super->ppl.size);
 	}
 #endif
 	/* Allow space for bad block log */
@@ -2528,8 +2640,9 @@ static int validate_geometry1(struct supertype *st, int level,
 		return 0;
 	}
 
-	/* creating:  allow suitable space for bitmap */
-	bmspace = choose_bm_space(devsize);
+	/* creating:  allow suitable space for bitmap or PPL */
+	bmspace = consistency_policy == CONSISTENCY_POLICY_PPL ?
+		  choose_ppl_space((*chunk)*2) : choose_bm_space(devsize);
 
 	if (data_offset == INVALID_SECTORS)
 		data_offset = st->data_offset;
@@ -2564,7 +2677,7 @@ static int validate_geometry1(struct supertype *st, int level,
 	switch(st->minor_version) {
 	case 0: /* metadata at end.  Round down and subtract space to reserve */
 		devsize = (devsize & ~(4ULL*2-1));
-		/* space for metadata, bblog, bitmap */
+		/* space for metadata, bblog, bitmap/ppl */
 		devsize -= 8*2 + 8 + bmspace;
 		break;
 	case 1:
@@ -2640,6 +2753,7 @@ struct superswitch super1 = {
 	.add_to_super = add_to_super1,
 	.examine_badblocks = examine_badblocks_super1,
 	.copy_metadata = copy_metadata1,
+	.write_init_ppl = write_init_ppl1,
 #endif
 	.match_home = match_home1,
 	.uuid_from_super = uuid_from_super1,
-- 
2.12.0