diff options
| -rw-r--r-- | Documentation/nvdimm/btt.txt | 273 | ||||
| -rw-r--r-- | drivers/acpi/nfit.c | 1 | ||||
| -rw-r--r-- | drivers/nvdimm/Kconfig | 28 | ||||
| -rw-r--r-- | drivers/nvdimm/Makefile | 3 | ||||
| -rw-r--r-- | drivers/nvdimm/btt.c | 1371 | ||||
| -rw-r--r-- | drivers/nvdimm/btt.h | 141 | ||||
| -rw-r--r-- | drivers/nvdimm/btt_devs.c | 3 | ||||
| -rw-r--r-- | drivers/nvdimm/namespace_devs.c | 24 | ||||
| -rw-r--r-- | drivers/nvdimm/nd.h | 22 | ||||
| -rw-r--r-- | drivers/nvdimm/pmem.c | 14 | ||||
| -rw-r--r-- | drivers/nvdimm/region.c | 12 | ||||
| -rw-r--r-- | drivers/nvdimm/region_devs.c | 82 | ||||
| -rw-r--r-- | include/linux/libnvdimm.h | 1 |
13 files changed, 1950 insertions, 25 deletions
diff --git a/Documentation/nvdimm/btt.txt b/Documentation/nvdimm/btt.txt new file mode 100644 index 000000000000..95134d5ec4a0 --- /dev/null +++ b/Documentation/nvdimm/btt.txt @@ -0,0 +1,273 @@ +BTT - Block Translation Table +============================= + + +1. Introduction +--------------- + +Persistent memory based storage is able to perform IO at byte (or more +accurately, cache line) granularity. However, we often want to expose such +storage as traditional block devices. The block drivers for persistent memory +will do exactly this. However, they do not provide any atomicity guarantees. +Traditional SSDs typically provide protection against torn sectors in hardware, +using stored energy in capacitors to complete in-flight block writes, or perhaps +in firmware. We don't have this luxury with persistent memory - if a write is in +progress, and we experience a power failure, the block will contain a mix of old +and new data. Applications may not be prepared to handle such a scenario. + +The Block Translation Table (BTT) provides atomic sector update semantics for +persistent memory devices, so that applications that rely on sector writes not +being torn can continue to do so. The BTT manifests itself as a stacked block +device, and reserves a portion of the underlying storage for its metadata. At +the heart of it, is an indirection table that re-maps all the blocks on the +volume. It can be thought of as an extremely simple file system that only +provides atomic sector updates. + + +2. Static Layout +---------------- + +The underlying storage on which a BTT can be laid out is not limited in any way. +The BTT, however, splits the available space into chunks of up to 512 GiB, +called "Arenas". + +Each arena follows the same layout for its metadata, and all references in an +arena are internal to it (with the exception of one field that points to the +next arena). The following depicts the "On-disk" metadata layout: + + + Backing Store +-------> Arena ++---------------+ | +------------------+ +| | | | Arena info block | +| Arena 0 +---+ | 4K | +| 512G | +------------------+ +| | | | ++---------------+ | | +| | | | +| Arena 1 | | Data Blocks | +| 512G | | | +| | | | ++---------------+ | | +| . | | | +| . | | | +| . | | | +| | | | +| | | | ++---------------+ +------------------+ + | | + | BTT Map | + | | + | | + +------------------+ + | | + | BTT Flog | + | | + +------------------+ + | Info block copy | + | 4K | + +------------------+ + + +3. Theory of Operation +---------------------- + + +a. The BTT Map +-------------- + +The map is a simple lookup/indirection table that maps an LBA to an internal +block. Each map entry is 32 bits. The two most significant bits are special +flags, and the remaining form the internal block number. + +Bit Description +31 : TRIM flag - marks if the block was trimmed or discarded +30 : ERROR flag - marks an error block. Cleared on write. +29 - 0 : Mappings to internal 'postmap' blocks + + +Some of the terminology that will be subsequently used: + +External LBA : LBA as made visible to upper layers. +ABA : Arena Block Address - Block offset/number within an arena +Premap ABA : The block offset into an arena, which was decided upon by range + checking the External LBA +Postmap ABA : The block number in the "Data Blocks" area obtained after + indirection from the map +nfree : The number of free blocks that are maintained at any given time. + This is the number of concurrent writes that can happen to the + arena. + + +For example, after adding a BTT, we surface a disk of 1024G. We get a read for +the external LBA at 768G. This falls into the second arena, and of the 512G +worth of blocks that this arena contributes, this block is at 256G. Thus, the +premap ABA is 256G. We now refer to the map, and find out the mapping for block +'X' (256G) points to block 'Y', say '64'. Thus the postmap ABA is 64. + + +b. The BTT Flog +--------------- + +The BTT provides sector atomicity by making every write an "allocating write", +i.e. Every write goes to a "free" block. A running list of free blocks is +maintained in the form of the BTT flog. 'Flog' is a combination of the words +"free list" and "log". The flog contains 'nfree' entries, and an entry contains: + +lba : The premap ABA that is being written to +old_map : The old postmap ABA - after 'this' write completes, this will be a + free block. +new_map : The new postmap ABA. The map will up updated to reflect this + lba->postmap_aba mapping, but we log it here in case we have to + recover. +seq : Sequence number to mark which of the 2 sections of this flog entry is + valid/newest. It cycles between 01->10->11->01 (binary) under normal + operation, with 00 indicating an uninitialized state. +lba' : alternate lba entry +old_map': alternate old postmap entry +new_map': alternate new postmap entry +seq' : alternate sequence number. + +Each of the above fields is 32-bit, making one entry 16 bytes. Flog updates are +done such that for any entry being written, it: +a. overwrites the 'old' section in the entry based on sequence numbers +b. writes the new entry such that the sequence number is written last. + + +c. The concept of lanes +----------------------- + +While 'nfree' describes the number of concurrent IOs an arena can process +concurrently, 'nlanes' is the number of IOs the BTT device as a whole can +process. + nlanes = min(nfree, num_cpus) +A lane number is obtained at the start of any IO, and is used for indexing into +all the on-disk and in-memory data structures for the duration of the IO. It is +protected by a spinlock. + + +d. In-memory data structure: Read Tracking Table (RTT) +------------------------------------------------------ + +Consider a case where we have two threads, one doing reads and the other, +writes. We can hit a condition where the writer thread grabs a free block to do +a new IO, but the (slow) reader thread is still reading from it. In other words, +the reader consulted a map entry, and started reading the corresponding block. A +writer started writing to the same external LBA, and finished the write updating +the map for that external LBA to point to its new postmap ABA. At this point the +internal, postmap block that the reader is (still) reading has been inserted +into the list of free blocks. If another write comes in for the same LBA, it can +grab this free block, and start writing to it, causing the reader to read +incorrect data. To prevent this, we introduce the RTT. + +The RTT is a simple, per arena table with 'nfree' entries. Every reader inserts +into rtt[lane_number], the postmap ABA it is reading, and clears it after the +read is complete. Every writer thread, after grabbing a free block, checks the +RTT for its presence. If the postmap free block is in the RTT, it waits till the +reader clears the RTT entry, and only then starts writing to it. + + +e. In-memory data structure: map locks +-------------------------------------- + +Consider a case where two writer threads are writing to the same LBA. There can +be a race in the following sequence of steps: + +free[lane] = map[premap_aba] +map[premap_aba] = postmap_aba + +Both threads can update their respective free[lane] with the same old, freed +postmap_aba. This has made the layout inconsistent by losing a free entry, and +at the same time, duplicating another free entry for two lanes. + +To solve this, we could have a single map lock (per arena) that has to be taken +before performing the above sequence, but we feel that could be too contentious. +Instead we use an array of (nfree) map_locks that is indexed by +(premap_aba modulo nfree). + + +f. Reconstruction from the Flog +------------------------------- + +On startup, we analyze the BTT flog to create our list of free blocks. We walk +through all the entries, and for each lane, of the set of two possible +'sections', we always look at the most recent one only (based on the sequence +number). The reconstruction rules/steps are simple: +- Read map[log_entry.lba]. +- If log_entry.new matches the map entry, then log_entry.old is free. +- If log_entry.new does not match the map entry, then log_entry.new is free. + (This case can only be caused by power-fails/unsafe shutdowns) + + +g. Summarizing - Read and Write flows +------------------------------------- + +Read: + +1. Convert external LBA to arena number + pre-map ABA +2. Get a lane (and take lane_lock) +3. Read map to get the entry for this pre-map ABA +4. Enter post-map ABA into RTT[lane] +5. If TRIM flag set in map, return zeroes, and end IO (go to step 8) +6. If ERROR flag set in map, end IO with EIO (go to step 8) +7. Read data from this block +8. Remove post-map ABA entry from RTT[lane] +9. Release lane (and lane_lock) + +Write: + +1. Convert external LBA to Arena number + pre-map ABA +2. Get a lane (and take lane_lock) +3. Use lane to index into in-memory free list and obtain a new block, next flog + index, next sequence number +4. Scan the RTT to check if free block is present, and spin/wait if it is. +5. Write data to this free block +6. Read map to get the existing post-map ABA entry for this pre-map ABA +7. Write flog entry: [premap_aba / old postmap_aba / new postmap_aba / seq_num] +8. Write new post-map ABA into map. +9. Write old post-map entry into the free list +10. Calculate next sequence number and write into the free list entry +11. Release lane (and lane_lock) + + +4. Error Handling +================= + +An arena would be in an error state if any of the metadata is corrupted +irrecoverably, either due to a bug or a media error. The following conditions +indicate an error: +- Info block checksum does not match (and recovering from the copy also fails) +- All internal available blocks are not uniquely and entirely addressed by the + sum of mapped blocks and free blocks (from the BTT flog). +- Rebuilding free list from the flog reveals missing/duplicate/impossible + entries +- A map entry is out of bounds + +If any of these error conditions are encountered, the arena is put into a read +only state using a flag in the info block. + + +5. In-kernel usage +================== + +Any block driver that supports byte granularity IO to the storage may register +with the BTT. It will have to provide the rw_bytes interface in its +block_device_operations struct: + + int (*rw_bytes)(struct gendisk *, void *, size_t, off_t, int rw); + +It may register with the BTT after it adds its own gendisk, using btt_init: + + struct btt *btt_init(struct gendisk *disk, unsigned long long rawsize, + u32 lbasize, u8 uuid[], int maxlane); + +note that maxlane is the maximum amount of concurrency the driver wishes to +allow the BTT to use. + +The BTT 'disk' appears as a stacked block device that grabs the underlying block +device in the O_EXCL mode. + +When the driver wishes to remove the backing disk, it should similarly call +btt_fini using the same struct btt* handle that was provided to it by btt_init. + + void btt_fini(struct btt *btt); + diff --git a/drivers/acpi/nfit.c b/drivers/acpi/nfit.c index 35af6f7f0abd..fc38b49eff7d 100644 --- a/drivers/acpi/nfit.c +++ b/drivers/acpi/nfit.c @@ -902,6 +902,7 @@ static int acpi_nfit_init_mapping(struct acpi_nfit_desc *acpi_desc, } else { nd_mapping->size = nfit_mem->bdw->capacity; nd_mapping->start = nfit_mem->bdw->start_address; + ndr_desc->num_lanes = nfit_mem->bdw->windows; blk_valid = 1; } diff --git a/drivers/nvdimm/Kconfig b/drivers/nvdimm/Kconfig index 5680e8e7a7aa..204ee0796411 100644 --- a/drivers/nvdimm/Kconfig +++ b/drivers/nvdimm/Kconfig @@ -8,11 +8,11 @@ menuconfig LIBNVDIMM NFIT, or otherwise can discover NVDIMM resources, a libnvdimm bus is registered to advertise PMEM (persistent memory) namespaces (/dev/pmemX) and BLK (sliding mmio window(s)) - namespaces (/dev/ndX). A PMEM namespace refers to a memory - resource that may span multiple DIMMs and support DAX (see - CONFIG_DAX). A BLK namespace refers to an NVDIMM control - region which exposes an mmio register set for windowed - access mode to non-volatile memory. + namespaces (/dev/ndblkX.Y). A PMEM namespace refers to a + memory resource that may span multiple DIMMs and support DAX + (see CONFIG_DAX). A BLK namespace refers to an NVDIMM control + region which exposes an mmio register set for windowed access + mode to non-volatile memory. if LIBNVDIMM @@ -20,6 +20,7 @@ config BLK_DEV_PMEM tristate "PMEM: Persistent memory block device support" default LIBNVDIMM depends on HAS_IOMEM + select ND_BTT if BTT help Memory ranges for PMEM are described by either an NFIT (NVDIMM Firmware Interface Table, see CONFIG_NFIT_ACPI), a @@ -33,7 +34,22 @@ config BLK_DEV_PMEM Say Y if you want to use an NVDIMM +config ND_BTT + tristate + config BTT - def_bool y + bool "BTT: Block Translation Table (atomic sector updates)" + default y if LIBNVDIMM + help + The Block Translation Table (BTT) provides atomic sector + update semantics for persistent memory devices, so that + applications that rely on sector writes not being torn (a + guarantee that typical disks provide) can continue to do so. + The BTT manifests itself as an alternate personality for an + NVDIMM namespace, i.e. a namespace can be in raw mode (pmemX, + ndblkX.Y, etc...), or 'sectored' mode, (pmemXs, ndblkX.Ys, + etc...). + + Select Y if unsure endif diff --git a/drivers/nvdimm/Makefile b/drivers/nvdimm/Makefile index 6085b4bd7312..d2aab6c58492 100644 --- a/drivers/nvdimm/Makefile +++ b/drivers/nvdimm/Makefile @@ -1,8 +1,11 @@ obj-$(CONFIG_LIBNVDIMM) += libnvdimm.o obj-$(CONFIG_BLK_DEV_PMEM) += nd_pmem.o +obj-$(CONFIG_ND_BTT) += nd_btt.o nd_pmem-y := pmem.o +nd_btt-y := btt.o + libnvdimm-y := core.o libnvdimm-y += bus.o libnvdimm-y += dimm_devs.o diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c new file mode 100644 index 000000000000..7ae38aac2c25 --- /dev/null +++ b/drivers/nvdimm/btt.c @@ -0,0 +1,1371 @@ +/* + * Block Translation Table + * Copyright (c) 2014-2015, Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ +#include <linux/highmem.h> +#include <linux/debugfs.h> +#include <linux/blkdev.h> +#include <linux/module.h> +#include <linux/device.h> +#include <linux/mutex.h> +#include <linux/hdreg.h> +#include <linux/genhd.h> +#include <linux/sizes.h> +#include <linux/ndctl.h> +#include <linux/fs.h> +#include <linux/nd.h> +#include "btt.h" +#include "nd.h" + +enum log_ent_request { + LOG_NEW_ENT = 0, + LOG_OLD_ENT +}; + +static int btt_major; + +static int arena_read_bytes(struct arena_info *arena, resource_size_t offset, + void *buf, size_t n) +{ + struct nd_btt *nd_btt = arena->nd_btt; + struct nd_namespace_common *ndns = nd_btt->ndns; + + /* arena offsets are 4K from the base of the device */ + offset += SZ_4K; + return nvdimm_read_bytes(ndns, offset, buf, n); +} + +static int arena_write_bytes(struct arena_info *arena, resource_size_t offset, + void *buf, size_t n) +{ + struct nd_btt *nd_btt = arena->nd_btt; + struct nd_namespace_common *ndns = nd_btt->ndns; + + /* arena offsets are 4K from the base of the device */ + offset += SZ_4K; + return nvdimm_write_bytes(ndns, offset, buf, n); +} + +static int btt_info_write(struct arena_info *arena, struct btt_sb *super) +{ + int ret; + + ret = arena_write_bytes(arena, arena->info2off, super, + sizeof(struct btt_sb)); + if (ret) + return ret; + + return arena_write_bytes(arena, arena->infooff, super, + sizeof(struct btt_sb)); +} + +static int btt_info_read(struct arena_info *arena, struct btt_sb *super) +{ + WARN_ON(!super); + return arena_read_bytes(arena, arena->infooff, super, + sizeof(struct btt_sb)); +} + +/* + * 'raw' version of btt_map write + * Assumptions: + * mapping is in little-endian + * mapping contains 'E' and 'Z' flags as desired + */ +static int __btt_map_write(struct arena_info *arena, u32 lba, __le32 mapping) +{ + u64 ns_off = arena->mapoff + (lba * MAP_ENT_SIZE); + + WARN_ON(lba >= arena->external_nlba); + return arena_write_bytes(arena, ns_off, &mapping, MAP_ENT_SIZE); +} + +static int btt_map_write(struct arena_info *arena, u32 lba, u32 mapping, + u32 z_flag, u32 e_flag) +{ + u32 ze; + __le32 mapping_le; + + /* + * This 'mapping' is supposed to be just the LBA mapping, without + * any flags set, so strip the flag bits. + */ + mapping &= MAP_LBA_MASK; + + ze = (z_flag << 1) + e_flag; + switch (ze) { + case 0: + /* + * We want to set neither of the Z or E flags, and + * in the actual layout, this means setting the bit + * positions of both to '1' to indicate a 'normal' + * map entry + */ + mapping |= MAP_ENT_NORMAL; + break; + case 1: + mapping |= (1 << MAP_ERR_SHIFT); + break; + case 2: + mapping |= (1 << MAP_TRIM_SHIFT); + break; + default: + /* + * The case where Z and E are both sent in as '1' could be + * construed as a valid 'normal' case, but we decide not to, + * to avoid confusion + */ + WARN_ONCE(1, "Invalid use of Z and E flags\n"); + return -EIO; + } + + mapping_le = cpu_to_le32(mapping); + return __btt_map_write(arena, lba, mapping_le); +} + +static int btt_map_read(struct arena_info *arena, u32 lba, u32 *mapping, + int *trim, int *error) +{ + int ret; + __le32 in; + u32 raw_mapping, postmap, ze, z_flag, e_flag; + u64 ns_off = arena->mapoff + (lba * MAP_ENT_SIZE); + + WARN_ON(lba >= arena->external_nlba); + + ret = arena_read_bytes(arena, ns_off, &in, MAP_ENT_SIZE); + if (ret) + return ret; + + raw_mapping = le32_to_cpu(in); + + z_flag = (raw_mapping & MAP_TRIM_MASK) >> MAP_TRIM_SHIFT; + e_flag = (raw_mapping & MAP_ERR_MASK) >> MAP_ERR_SHIFT; + ze = (z_flag << 1) + e_flag; + postmap = raw_mapping & MAP_LBA_MASK; + + /* Reuse the {z,e}_flag variables for *trim and *error */ + z_flag = 0; + e_flag = 0; + + switch (ze) { + case 0: + /* Initial state. Return postmap = premap */ + *mapping = lba; + break; + case 1: + *mapping = postmap; + e_flag = 1; + break; + case 2: + *mapping = postmap; + z_flag = 1; + break; + case 3: + *mapping = postmap; + break; + default: + return -EIO; + } + + if (trim) + *trim = z_flag; + if (error) + *error = e_flag; + + return ret; +} + +static int btt_log_read_pair(struct arena_info *arena, u32 lane, + struct log_entry *ent) +{ + WARN_ON(!ent); + return arena_read_bytes(arena, + arena->logoff + (2 * lane * LOG_ENT_SIZE), ent, + 2 * LOG_ENT_SIZE); +} + +static struct dentry *debugfs_root; + +static void arena_debugfs_init(struct arena_info *a, struct dentry *parent, + int idx) +{ + char dirname[32]; + struct dentry *d; + + /* If for some reason, parent bttN was not created, exit */ + if (!parent) + return; + + snprintf(dirname, 32, "arena%d", idx); + d = debugfs_create_dir(dirname, parent); + if (IS_ERR_OR_NULL(d)) + return; + a->debugfs_dir = d; + + debugfs_create_x64("size", S_IRUGO, d, &a->size); + debugfs_create_x64("external_lba_start", S_IRUGO, d, + &a->external_lba_start); + debugfs_create_x32("internal_nlba", S_IRUGO, d, &a->internal_nlba); + debugfs_create_u32("internal_lbasize", S_IRUGO, d, + &a->internal_lbasize); + debugfs_create_x32("external_nlba", S_IRUGO, d, &a->external_nlba); + debugfs_create_u32("external_lbasize", S_IRUGO, d, + &a->external_lbasize); + debugfs_create_u32("nfree", S_IRUGO, d, &a->nfree); + debugfs_create_u16("version_major", S_IRUGO, d, &a->version_major); + debugfs_create_u16("version_minor", S_IRUGO, d, &a->version_minor); + debugfs_create_x64("nextoff", S_IRUGO, d, &a->nextoff); + debugfs_create_x64("infooff", S_IRUGO, d, &a->infooff); + debugfs_create_x64("dataoff", S_IRUGO, d, &a->dataoff); + debugfs_create_x64("mapoff", S_IRUGO, d, &a->mapoff); + debugfs_create_x64("logoff", S_IRUGO, d, &a->logoff); + debugfs_create_x64("info2off", S_IRUGO, d, &a->info2off); + debugfs_create_x32("flags", S_IRUGO, d, &a->flags); +} + +static void btt_debugfs_init(struct btt *btt) +{ + int i = 0; + struct arena_info *arena; + + btt->debugfs_dir = debugfs_create_dir(dev_name(&btt->nd_btt->dev), + debugfs_root); + if (IS_ERR_OR_NULL(btt->debugfs_dir)) + return; + + list_for_each_entry(arena, &btt->arena_list, list) { + arena_debugfs_init(arena, btt->debugfs_dir, i); + i++; + } +} + +/* + * This function accepts two log entries, and uses the + * sequence number to find the 'older' entry. + * It also updates the sequence number in this old entry to + * make it the 'new' one if the mark_flag is set. + * Finally, it returns which of the entries was the older one. + * + * TODO The logic feels a bit kludge-y. make it better.. + */ +static int btt_log_get_old(struct log_entry *ent) +{ + int old; + + /* + * the first ever time this is seen, the entry goes into [0] + * the next time, the following logic works out to put this + * (next) entry into [1] + */ + if (ent[0].seq == 0) { + ent[0].seq = cpu_to_le32(1); + return 0; + } + + if (ent[0].seq == ent[1].seq) + return -EINVAL; + if (le32_to_cpu(ent[0].seq) + le32_to_cpu(ent[1].seq) > 5) + return -EINVAL; + + if (le32_to_cpu(ent[0].seq) < le32_to_cpu(ent[1].seq)) { + if (le32_to_cpu(ent[1].seq) - le32_to_cpu(ent[0].seq) == 1) + old = 0; + else + old = 1; + } else { + if (le32_to_cpu(ent[0].seq) - le32_to_cpu(ent[1].seq) == 1) + old = 1; + else + old = 0; + } + + return old; +} + +static struct device *to_dev(struct arena_info *arena) +{ + return &arena->nd_btt->dev; +} + +/* + * This function copies the desired (old/new) log entry into ent if + * it is not NULL. It returns the sub-slot number (0 or 1) + * where the desired log entry was found. Negative return values + * indicate errors. + */ +static int btt_log_read(struct arena_info *arena, u32 lane, + struct log_entry *ent, int old_flag) +{ + int ret; + int old_ent, ret_ent; + struct log_entry log[2]; + + ret = btt_log_read_pair(arena, lane, log); + if (ret) + return -EIO; + + old_ent = btt_log_get_old(log); + if (old_ent < 0 || old_ent > 1) { + dev_info(to_dev(arena), + "log corruption (%d): lane %d seq [%d, %d]\n", + old_ent, lane, log[0].seq, log[1].seq); + /* TODO set error state? */ + return -EIO; + } + + ret_ent = (old_flag ? old_ent : (1 - old_ent)); + + if (ent != NULL) + memcpy(ent, &log[ret_ent], LOG_ENT_SIZE); + + return ret_ent; +} + +/* + * This function commits a log entry to media + * It does _not_ prepare the freelist entry for the next write + * btt_flog_write is the wrapper for updating the freelist elements + */ +static int __btt_log_write(struct arena_info *arena, u32 lane, + u32 sub, struct log_entry *ent) +{ + int ret; + /* + * Ignore the padding in log_entry for calculating log_half. + * The entry is 'committed' when we write the sequence number, + * and we want to ensure that that is the last thing written. + * We don't bother writing the padding as that would be extra + * media wear and write amplification + */ + unsigned int log_half = (LOG_ENT_SIZE - 2 * sizeof(u64)) / 2; + u64 ns_off = arena->logoff + (((2 * lane) + sub) * LOG_ENT_SIZE); + void *src = ent; + + /* split the 16B write into atomic, durable halves */ + ret = arena_write_bytes(arena, ns_off, src, log_half); + if (ret) + return ret; + + ns_off += log_half; + src += log_half; + return arena_write_bytes(arena, ns_off, src, log_half); +} + +static int btt_flog_write(struct arena_info *arena, u32 lane, u32 sub, + struct log_entry *ent) +{ + int ret; + + ret = __btt_log_write(arena, lane, sub, ent); + if (ret) + return ret; + + /* prepare the next free entry */ + arena->freelist[lane].sub = 1 - arena->freelist[lane].sub; + if (++(arena->freelist[lane].seq) == 4) + arena->freelist[lane].seq = 1; + arena->freelist[lane].block = le32_to_cpu(ent->old_map); + + return ret; +} + +/* + * This function initializes the BTT map to the initial state, which is + * all-zeroes, and indicates an identity mapping + */ +static int btt_map_init(struct arena_info *arena) +{ + int ret = -EINVAL; + void *zerobuf; + size_t offset = 0; + size_t chunk_size = SZ_2M; + size_t mapsize = arena->logoff - arena->mapoff; + + zerobuf = kzalloc(chunk_size, GFP_KERNEL); + if (!zerobuf) + return -ENOMEM; + + while (mapsize) { + size_t size = min(mapsize, chunk_size); + + ret = arena_write_bytes(arena, arena->mapoff + offset, zerobuf, + size); + if (ret) + goto free; + + offset += size; + mapsize -= size; + cond_resched(); + } + + free: + kfree(zerobuf); + return ret; +} + +/* + * This function initializes the BTT log with 'fake' entries pointing + * to the initial reserved set of blocks as being free + */ +static int btt_log_init(struct arena_info *arena) +{ + int ret; + u32 i; + struct log_entry log, zerolog; + + memset(&zerolog, 0, sizeof(zerolog)); + + for (i = 0; i < arena->nfree; i++) { + log.lba = cpu_to_le32(i); + log.old_map = cpu_to_le32(arena->external_nlba + i); + log.new_map = cpu_to_le32(arena->external_nlba + i); + log.seq = cpu_to_le32(LOG_SEQ_INIT); + ret = __btt_log_write(arena, i, 0, &log); + if (ret) + return ret; + ret = __btt_log_write(arena, i, 1, &zerolog); + if (ret) + return ret; + } + + return 0; +} + +static int btt_freelist_init(struct arena_info *arena) +{ + int old, new, ret; + u32 i, map_entry; + struct log_entry log_new, log_old; + + arena->freelist = kcalloc(arena->nfree, sizeof(struct free_entry), + GFP_KERNEL); + if (!arena->freelist) + return -ENOMEM; + + for (i = 0; i < arena->nfree; i++) { + old = btt_log_read(arena, i, &log_old, LOG_OLD_ENT); + if (old < 0) + return old; + + new = btt_log_read(arena, i, &log_new, LOG_NEW_ENT); + if (new < 0) + return new; + + /* sub points to the next one to be overwritten */ + arena->freelist[i].sub = 1 - new; + arena->freelist[i].seq = nd_inc_seq(le32_to_cpu(log_new.seq)); + arena->freelist[i].block = le32_to_cpu(log_new.old_map); + + /* This implies a newly created or untouched flog entry */ + if (log_new.old_map == log_new.new_map) + continue; + + /* Check if map recovery is needed */ + ret = btt_map_read(arena, le32_to_cpu(log_new.lba), &map_entry, + NULL, NULL); + if (ret) + return ret; + if ((le32_to_cpu(log_new.new_map) != map_entry) && + (le32_to_cpu(log_new.old_map) == map_entry)) { + /* + * Last transaction wrote the flog, but wasn't able + * to complete the map write. So fix up the map. + */ + ret = btt_map_write(arena, le32_to_cpu(log_new.lba), + le32_to_cpu(log_new.new_map), 0, 0); + if (ret) + return ret; + } + + } + + return 0; +} + +static int btt_rtt_init(struct arena_info *arena) +{ + arena->rtt = kcalloc(arena->nfree, sizeof(u32), GFP_KERNEL); + if (arena->rtt == NULL) + return -ENOMEM; + + return 0; +} + +static int btt_maplocks_init(struct arena_info *arena) +{ + u32 i; + + arena->map_locks = kcalloc(arena->nfree, sizeof(struct aligned_lock), + GFP_KERNEL); + if (!arena->map_locks) + return -ENOMEM; + + for (i = 0; i < arena->nfree; i++) + spin_lock_init(&arena->map_locks[i].lock); + + return 0; +} + +static struct arena_info *alloc_arena(struct btt *btt, size_t size, + size_t start, size_t arena_off) +{ + struct arena_info *arena; + u64 logsize, mapsize, datasize; + u64 available = size; + + arena = kzalloc(sizeof(struct arena_info), GFP_KERNEL); + if (!arena) + return NULL; + arena->nd_btt = btt->nd_btt; + + if (!size) + return arena; + + arena->size = size; + arena->external_lba_start = start; + arena->external_lbasize = btt->lbasize; + arena->internal_lbasize = roundup(arena->external_lbasize, + INT_LBASIZE_ALIGNMENT); + arena->nfree = BTT_DEFAULT_NFREE; + arena->version_major = 1; + arena->version_minor = 1; + + if (available % BTT_PG_SIZE) + available -= (available % BTT_PG_SIZE); + + /* Two pages are reserved for the super block and its copy */ + available -= 2 * BTT_PG_SIZE; + + /* The log takes a fixed amount of space based on nfree */ + logsize = roundup(2 * arena->nfree * sizeof(struct log_entry), + BTT_PG_SIZE); + available -= logsize; + + /* Calculate optimal split between map and data area */ + arena->internal_nlba = div_u64(available - BTT_PG_SIZE, + arena->internal_lbasize + MAP_ENT_SIZE); + arena->external_nlba = arena->internal_nlba - arena->nfree; + + mapsize = roundup((arena->external_nlba * MAP_ENT_SIZE), BTT_PG_SIZE); + datasize = available - mapsize; + + /* 'Absolute' values, relative to start of storage space */ + arena->infooff = arena_off; + arena->dataoff = arena->infooff + BTT_PG_SIZE; + arena->mapoff = arena->dataoff + datasize; + arena->logoff = arena->mapoff + mapsize; + arena->info2off = arena->logoff + logsize; + return arena; +} + +static void free_arenas(struct btt *btt) +{ + struct arena_info *arena, *next; + + list_for_each_entry_safe(arena, next, &btt->arena_list, list) { + list_del(&arena->list); + kfree(arena->rtt); + kfree(arena->map_locks); + kfree(arena->freelist); + debugfs_remove_recursive(arena->debugfs_dir); + kfree(arena); + } +} + +/* + * This function checks if the metadata layout is valid and error free + */ +static int arena_is_valid(struct arena_info *arena, struct btt_sb *super, + u8 *uuid, u32 lbasize) +{ + u64 checksum; + + if (memcmp(super->uuid, uuid, 16)) + return 0; + + checksum = le64_to_cpu(super->checksum); + super->checksum = 0; + if (checksum != nd_btt_sb_checksum(super)) + return 0; + super->checksum = cpu_to_le64(checksum); + + if (lbasize != le32_to_cpu(super->external_lbasize)) + return 0; + + /* TODO: figure out action for this */ + if ((le32_to_cpu(super->flags) & IB_FLAG_ERROR_MASK) != 0) + dev_info(to_dev(arena), "Found arena with an error flag\n"); + + return 1; +} + +/* + * This function reads an existing valid btt superblock and + * populates the corresponding arena_info struct + */ +static void parse_arena_meta(struct arena_info *arena, struct btt_sb *super, + u64 arena_off) +{ + arena->internal_nlba = le32_to_cpu(super->internal_nlba); + arena->internal_lbasize = le32_to_cpu(super->internal_lbasize); + arena->external_nlba = le32_to_cpu(super->external_nlba); + arena->external_lbasize = le32_to_cpu(super->external_lbasize); + arena->nfree = le32_to_cpu(super->nfree); + arena->version_major = le16_to_cpu(super->version_major); + arena->version_minor = le16_to_cpu(super->version_minor); + + arena->nextoff = (super->nextoff == 0) ? 0 : (arena_off + + le64_to_cpu(super->nextoff)); + arena->infooff = arena_off; + arena->dataoff = arena_off + le64_to_cpu(super->dataoff); + arena->mapoff = arena_off + le64_to_cpu(super->mapoff); + arena->logoff = arena_off + le64_to_cpu(super->logoff); + arena->info2off = arena_off + le64_to_cpu(super->info2off); + + arena->size = (super->nextoff > 0) ? (le64_to_cpu(super->nextoff)) : + (arena->info2off - arena->infooff + BTT_PG_SIZE); + + arena->flags = le32_to_cpu(super->flags); +} + +static int discover_arenas(struct btt *btt) +{ + int ret = 0; + struct arena_info *arena; + struct btt_sb *super; + size_t remaining = btt->rawsize; + u64 cur_nlba = 0; + size_t cur_off = 0; + int num_arenas = 0; + + super = kzalloc(sizeof(*super), GFP_KERNEL); + if (!super) + return -ENOMEM; + + while (remaining |