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 +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#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) { + /* Alloc memory for arena */ + arena = alloc_arena(btt, 0, 0, 0); + if (!arena) { + ret = -ENOMEM; + goto out_super; + } + + arena->infooff = cur_off; + ret = btt_info_read(arena, super); + if (ret) + goto out; + + if (!arena_is_valid(arena, super, btt->nd_btt->uuid, + btt->lbasize)) { + if (remaining == btt->rawsize) { + btt->init_state = INIT_NOTFOUND; + dev_info(to_dev(arena), "No existing arenas\n"); + goto out; + } else { + dev_info(to_dev(arena), + "Found corrupted metadata!\n"); + ret = -ENODEV; + goto out; + } + } + + arena->external_lba_start = cur_nlba; + parse_arena_meta(arena, super, cur_off); + + ret = btt_freelist_init(arena); + if (ret) + goto out; + + ret = btt_rtt_init(arena); + if (ret) + goto out; + + ret = btt_maplocks_init(arena); + if (ret) + goto out; + + list_add_tail(&arena->list, &btt->arena_list); + + remaining -= arena->size; + cur_off += arena->size; + cur_nlba += arena->external_nlba; + num_arenas++; + + if (arena->nextoff == 0) + break; + } + btt->num_arenas = num_arenas; + btt->nlba = cur_nlba; + btt->init_state = INIT_READY; + + kfree(super); + return ret; + + out: + kfree(arena); + free_arenas(btt); + out_super: + kfree(super); + return ret; +} + +static int create_arenas(struct btt *btt) +{ + size_t remaining = btt->rawsize; + size_t cur_off = 0; + + while (remaining) { + struct arena_info *arena; + size_t arena_size = min_t(u64, ARENA_MAX_SIZE, remaining); + + remaining -= arena_size; + if (arena_size < ARENA_MIN_SIZE) + break; + + arena = alloc_arena(btt, arena_size, btt->nlba, cur_off); + if (!arena) { + free_arenas(btt); + return -ENOMEM; + } + btt->nlba += arena->external_nlba; + if (remaining >= ARENA_MIN_SIZE) + arena->nextoff = arena->size; + else + arena->nextoff = 0; + cur_off += arena_size; + list_add_tail(&arena->list, &btt->arena_list); + } + + return 0; +} + +/* + * This function completes arena initialization by writing + * all the metadata. + * It is only called for an uninitialized arena when a write + * to that arena occurs for the first time. + */ +static int btt_arena_write_layout(struct arena_info *arena, u8 *uuid) +{ + int ret; + struct btt_sb *super; + + ret = btt_map_init(arena); + if (ret) + return ret; + + ret = btt_log_init(arena); + if (ret) + return ret; + + super = kzalloc(sizeof(struct btt_sb), GFP_NOIO); + if (!super) + return -ENOMEM; + + strncpy(super->signature, BTT_SIG, BTT_SIG_LEN); + memcpy(super->uuid, uuid, 16); + super->flags = cpu_to_le32(arena->flags); + super->version_major = cpu_to_le16(arena->version_major); + super->version_minor = cpu_to_le16(arena->version_minor); + super->external_lbasize = cpu_to_le32(arena->external_lbasize); + super->external_nlba = cpu_to_le32(arena->external_nlba); + super->internal_lbasize = cpu_to_le32(arena->internal_lbasize); + super->internal_nlba = cpu_to_le32(arena->internal_nlba); + super->nfree = cpu_to_le32(arena->nfree); + super->infosize = cpu_to_le32(sizeof(struct btt_sb)); + super->nextoff = cpu_to_le64(arena->nextoff); + /* + * Subtract arena->infooff (arena start) so numbers are relative + * to 'this' arena + */ + super->dataoff = cpu_to_le64(arena->dataoff - arena->infooff); + super->mapoff = cpu_to_le64(arena->mapoff - arena->infooff); + super->logoff = cpu_to_le64(arena->logoff - arena->infooff); + super->info2off = cpu_to_le64(arena->info2off - arena->infooff); + + super->flags = 0; + super->checksum = cpu_to_le64(nd_btt_sb_checksum(super)); + + ret = btt_info_write(arena, super); + + kfree(super); + return ret; +} + +/* + * This function completes the initialization for the BTT namespace + * such that it is ready to accept IOs + */ +static int btt_meta_init(struct btt *btt) +{ + int ret = 0; + struct arena_info *arena; + + mutex_lock(&btt->init_lock); + list_for_each_entry(arena, &btt->arena_list, list) { + ret = btt_arena_write_layout(arena, btt->nd_btt->uuid); + if (ret) + goto unlock; + + ret = btt_freelist_init(arena); + if (ret) + goto unlock; + + ret = btt_rtt_init(arena); + if (ret) + goto unlock; + + ret = btt_maplocks_init(arena); + if (ret) + goto unlock; + } + + btt->init_state = INIT_READY; + + unlock: + mutex_unlock(&btt->init_lock); + return ret; +} + +/* + * This function calculates the arena in which the given LBA lies + * by doing a linear walk. This is acceptable since we expect only + * a few arenas. If we have backing devices that get much larger, + * we can construct a balanced binary tree of arenas at init time + * so that this range search becomes faster. + */ +static int lba_to_arena(struct btt *btt, sector_t sector, __u32 *premap, + struct arena_info **arena) +{ + struct arena_info *arena_list; + __u64 lba = div_u64(sector << SECTOR_SHIFT, btt->sector_size); + + list_for_each_entry(arena_list, &btt->arena_list, list) { + if (lba < arena_list->external_nlba) { + *arena = arena_list; + *premap = lba; + return 0; + } + lba -= arena_list->external_nlba; + } + + return -EIO; +} + +/* + * The following (lock_map, unlock_map) are mostly just to improve + * readability, since they index into an array of locks + */ +static void lock_map(struct arena_info *arena, u32 premap) + __acquires(&arena->map_locks[idx].lock) +{ + u32 idx = (premap * MAP_ENT_SIZE / L1_CACHE_BYTES) % arena->nfree; + + spin_lock(&arena->map_locks[idx].lock); +} + +static void unlock_map(struct arena_info *arena, u32 premap) + __releases(&arena->map_locks[idx].lock) +{ + u32 idx = (premap * MAP_ENT_SIZE / L1_CACHE_BYTES) % arena->nfree; + + spin_unlock(&arena->map_locks[idx].lock); +} + +static u64 to_namespace_offset(struct arena_info *arena, u64 lba) +{ + return arena->dataoff + ((u64)lba * arena->internal_lbasize); +} + +static int btt_data_read(struct arena_info *arena, struct page *page, + unsigned int off, u32 lba, u32 len) +{ + int ret; + u64 nsoff = to_namespace_offset(arena, lba); + void *mem = kmap_atomic(page); + + ret = arena_read_bytes(arena, nsoff, mem + off, len); + kunmap_atomic(mem); + + return ret; +} + +static int btt_data_write(struct arena_info *arena, u32 lba, + struct page *page, unsigned int off, u32 len) +{ + int ret; + u64 nsoff = to_namespace_offset(arena, lba); + void *mem = kmap_atomic(page); + + ret = arena_write_bytes(arena, nsoff, mem + off, len); + kunmap_atomic(mem); + + return ret; +} + +static void zero_fill_data(struct page *page, unsigned int off, u32 len) +{ + void *mem = kmap_atomic(page); + + memset(mem + off, 0, len); + kunmap_atomic(mem); +} + +static int btt_read_pg(struct btt *btt, struct page *page, unsigned int off, + sector_t sector, unsigned int len) +{ + int ret = 0; + int t_flag, e_flag; + struct arena_info *arena = NULL; + u32 lane = 0, premap, postmap; + + while (len) { + u32 cur_len; + + lane = nd_region_acquire_lane(btt->nd_region); + + ret = lba_to_arena(btt, sector, &premap, &arena); + if (ret) + goto out_lane; + + cur_len = min(btt->sector_size, len); + + ret = btt_map_read(arena, premap, &postmap, &t_flag, &e_flag); + if (ret) + goto out_lane; + + /* + * We loop to make sure that the post map LBA didn't change + * from under us between writing the RTT and doing the actual + * read. + */ + while (1) { + u32 new_map; + + if (t_flag) { + zero_fill_data(page, off, cur_len); + goto out_lane; + } + + if (e_flag) { + ret = -EIO; + goto out_lane; + } + + arena->rtt[lane] = RTT_VALID | postmap; + /* + * Barrier to make sure this write is not reordered + * to do the verification map_read before the RTT store + */ + barrier(); + + ret = btt_map_read(arena, premap, &new_map, &t_flag, + &e_flag); + if (ret) + goto out_rtt; + + if (postmap == new_map) + break; + + postmap = new_map; + } + + ret = btt_data_read(arena, page, off, postmap, cur_len); + if (ret) + goto out_rtt; + + arena->rtt[lane] = RTT_INVALID; + nd_region_release_lane(btt->nd_region, lane); + + len -= cur_len; + off += cur_len; + sector += btt->sector_size >> SECTOR_SHIFT; + } + + return 0; + + out_rtt: + arena->rtt[lane] = RTT_INVALID; + out_lane: + nd_region_release_lane(btt->nd_region, lane); + return ret; +} + +static int btt_write_pg(struct btt *btt, sector_t sector, struct page *page, + unsigned int off, unsigned int len) +{ + int ret = 0; + struct arena_info *arena = NULL; + u32 premap = 0, old_postmap, new_postmap, lane = 0, i; + struct log_entry log; + int sub; + + while (len) { + u32 cur_len; + + lane = nd_region_acquire_lane(btt->nd_region); + + ret = lba_to_arena(btt, sector, &premap, &arena); + if (ret) + goto out_lane; + cur_len = min(btt->sector_size, len); + + if ((arena->flags & IB_FLAG_ERROR_MASK) != 0) { + ret = -EIO; + goto out_lane; + } + + new_postmap = arena->freelist[lane].block; + + /* Wait if the new block is being read from */ + for (i = 0; i < arena->nfree; i++) + while (arena->rtt[i] == (RTT_VALID | new_postmap)) + cpu_relax(); + + + if (new_postmap >= arena->internal_nlba) { + ret = -EIO; + goto out_lane; + } else + ret = btt_data_write(arena, new_postmap, page, + off, cur_len); + if (ret) + goto out_lane; + + lock_map(arena, premap); + ret = btt_map_read(arena, premap, &old_postmap, NULL, NULL); + if (ret) + goto out_map; + if (old_postmap >= arena->internal_nlba) { + ret = -EIO; + goto out_map; + } + + log.lba = cpu_to_le32(premap); + log.old_map = cpu_to_le32(old_postmap); + log.new_map = cpu_to_le32(new_postmap); + log.seq = cpu_to_le32(arena->freelist[lane].seq); + sub = arena->freelist[lane].sub; + ret = btt_flog_write(arena, lane, sub, &log); + if (ret) + goto out_map; + + ret = btt_map_write(arena, premap, new_postmap, 0, 0); + if (ret) + goto out_map; + + unlock_map(arena, premap); + nd_region_release_lane(btt->nd_region, lane); + + len -= cur_len; + off += cur_len; + sector += btt->sector_size >> SECTOR_SHIFT; + } + + return 0; + + out_map: + unlock_map(arena, premap); + out_lane: + nd_region_release_lane(btt->nd_region, lane); + return ret; +} + +static int btt_do_bvec(struct btt *btt, struct page *page, + unsigned int len, unsigned int off, int rw, + sector_t sector) +{ + int ret; + + if (rw == READ) { + ret = btt_read_pg(btt, page, off, sector, len); + flush_dcache_page(page); + } else { + flush_dcache_page(page); + ret = btt_write_pg(btt, sector, page, off, len); + } + + return ret; +} + +static void btt_make_request(struct request_queue *q, struct bio *bio) +{ + struct btt *btt = q->queuedata; + struct bvec_iter iter; + struct bio_vec bvec; + int err = 0, rw; + + rw = bio_data_dir(bio); + bio_for_each_segment(bvec, bio, iter) { + unsigned int len = bvec.bv_len; + + BUG_ON(len > PAGE_SIZE); + /* Make sure len is in multiples of sector size. */ + /* XXX is this right? */ + BUG_ON(len < btt->sector_size); + BUG_ON(len % btt->sector_size); + + err = btt_do_bvec(btt, bvec.bv_page, len, bvec.bv_offset, + rw, iter.bi_sector); + if (err) { + dev_info(&btt->nd_btt->dev, + "io error in %s sector %lld, len %d,\n", + (rw == READ) ? "READ" : "WRITE", + (unsigned long long) iter.bi_sector, len); + goto out; + } + } + +out: + bio_endio(bio, err); +} + +static int btt_rw_page(struct block_device *bdev, sector_t sector, + struct page *page, int rw) +{ + struct btt *btt = bdev->bd_disk->private_data; + + btt_do_bvec(btt, page, PAGE_CACHE_SIZE, 0, rw, sector); + page_endio(page, rw & WRITE, 0); + return 0; +} + + +static int btt_getgeo(struct block_device *bd, struct hd_geometry *geo) +{ + /* some standard values */ + geo->heads = 1 << 6; + geo->sectors = 1 << 5; + geo->cylinders = get_capacity(bd->bd_disk) >> 11; + return 0; +} + +static const struct block_device_operations btt_fops = { + .owner = THIS_MODULE, + .rw_page = btt_rw_page, + .getgeo = btt_getgeo, +}; + +static int btt_blk_init(struct btt *btt) +{ + struct nd_btt *nd_btt = btt->nd_btt; + struct nd_namespace_common *ndns = nd_btt->ndns; + + /* create a new disk and request queue for btt */ + btt->btt_queue = blk_alloc_queue(GFP_KERNEL); + if (!btt->btt_queue) + return -ENOMEM; + + btt->btt_disk = alloc_disk(0); + if (!btt->btt_disk) { + blk_cleanup_queue(btt->btt_queue); + return -ENOMEM; + } + + nvdimm_namespace_disk_name(ndns, btt->btt_disk->disk_name); + btt->btt_disk->driverfs_dev = &btt->nd_btt->dev; + btt->btt_disk->major = btt_major; + btt->btt_disk->first_minor = 0; + btt->btt_disk->fops = &btt_fops; + btt->btt_disk->private_data = btt; + btt->btt_disk->queue = btt->btt_queue; + btt->btt_disk->flags = GENHD_FL_EXT_DEVT; + + blk_queue_make_request(btt->btt_queue, btt_make_request); + blk_queue_logical_block_size(btt->btt_queue, btt->sector_size); + blk_queue_max_hw_sectors(btt->btt_queue, UINT_MAX); + blk_queue_bounce_limit(btt->btt_queue, BLK_BOUNCE_ANY); + queue_flag_set_unlocked(QUEUE_FLAG_NONROT, btt->btt_queue); + btt->btt_queue->queuedata = btt; + + set_capacity(btt->btt_disk, + btt->nlba * btt->sector_size >> SECTOR_SHIFT); + add_disk(btt->btt_disk); + + return 0; +} + +static void btt_blk_cleanup(struct btt *btt) +{ + del_gendisk(btt->btt_disk); + put_disk(btt->btt_disk); + blk_cleanup_queue(btt->btt_queue); +} + +/** + * btt_init - initialize a block translation table for the given device + * @nd_btt: device with BTT geometry and backing device info + * @rawsize: raw size in bytes of the backing device + * @lbasize: lba size of the backing device + * @uuid: A uuid for the backing device - this is stored on media + * @maxlane: maximum number of parallel requests the device can handle + * + * Initialize a Block Translation Table on a backing device to provide + * single sector power fail atomicity. + * + * Context: + * Might sleep. + * + * Returns: + * Pointer to a new struct btt on success, NULL on failure. + */ +static struct btt *btt_init(struct nd_btt *nd_btt, unsigned long long rawsize, + u32 lbasize, u8 *uuid, struct nd_region *nd_region) +{ + int ret; + struct btt *btt; + struct device *dev = &nd_btt->dev; + + btt = kzalloc(sizeof(struct btt), GFP_KERNEL); + if (!btt) + return NULL; + + btt->nd_btt = nd_btt; + btt->rawsize = rawsize; + btt->lbasize = lbasize; + btt->sector_size = ((lbasize >= 4096) ? 4096 : 512); + INIT_LIST_HEAD(&btt->arena_list); + mutex_init(&btt->init_lock); + btt->nd_region = nd_region; + + ret = discover_arenas(btt); + if (ret) { + dev_err(dev, "init: error in arena_discover: %d\n", ret); + goto out_free; + } + + if (btt->init_state != INIT_READY) { + btt->num_arenas = (rawsize / ARENA_MAX_SIZE) + + ((rawsize % ARENA_MAX_SIZE) ? 1 : 0); + dev_dbg(dev, "init: %d arenas for %llu rawsize\n", + btt->num_arenas, rawsize); + + ret = create_arenas(btt); + if (ret) { + dev_info(dev, "init: create_arenas: %d\n", ret); + goto out_free; + } + + ret = btt_meta_init(btt); + if (ret) { + dev_err(dev, "init: error in meta_init: %d\n", ret); + return NULL; + } + } + + ret = btt_blk_init(btt); + if (ret) { + dev_err(dev, "init: error in blk_init: %d\n", ret); + goto out_free; + } + + btt_debugfs_init(btt); + + return btt; + + out_free: + kfree(btt); + return NULL; +} + +/** + * btt_fini - de-initialize a BTT + * @btt: the BTT handle that was generated by btt_init + * + * De-initialize a Block Translation Table on device removal + * + * Context: + * Might sleep. + */ +static void btt_fini(struct btt *btt) +{ + if (btt) { + btt_blk_cleanup(btt); + free_arenas(btt); + debugfs_remove_recursive(btt->debugfs_dir); + kfree(btt); + } +} + +int nvdimm_namespace_attach_btt(struct nd_namespace_common *ndns) +{ + struct nd_btt *nd_btt = to_nd_btt(ndns->claim); + struct nd_region *nd_region; + struct btt *btt; + size_t rawsize; + + if (!nd_btt->uuid || !nd_btt->ndns || !nd_btt->lbasize) + return -ENODEV; + + rawsize = nvdimm_namespace_capacity(ndns) - SZ_4K; + if (rawsize < ARENA_MIN_SIZE) { + return -ENXIO; + } + nd_region = to_nd_region(nd_btt->dev.parent); + btt = btt_init(nd_btt, rawsize, nd_btt->lbasize, nd_btt->uuid, + nd_region); + if (!btt) + return -ENOMEM; + nd_btt->btt = btt; + + return 0; +} +EXPORT_SYMBOL(nvdimm_namespace_attach_btt); + +int nvdimm_namespace_detach_btt(struct nd_namespace_common *ndns) +{ + struct nd_btt *nd_btt = to_nd_btt(ndns->claim); + struct btt *btt = nd_btt->btt; + + btt_fini(btt); + nd_btt->btt = NULL; + + return 0; +} +EXPORT_SYMBOL(nvdimm_namespace_detach_btt); + +static int __init nd_btt_init(void) +{ + int rc; + + BUILD_BUG_ON(sizeof(struct btt_sb) != SZ_4K); + + btt_major = register_blkdev(0, "btt"); + if (btt_major < 0) + return btt_major; + + debugfs_root = debugfs_create_dir("btt", NULL); + if (IS_ERR_OR_NULL(debugfs_root)) { + rc = -ENXIO; + goto err_debugfs; + } + + return 0; + + err_debugfs: + unregister_blkdev(btt_major, "btt"); + + return rc; +} + +static void __exit nd_btt_exit(void) +{ + debugfs_remove_recursive(debugfs_root); + unregister_blkdev(btt_major, "btt"); +} + +MODULE_ALIAS_ND_DEVICE(ND_DEVICE_BTT); +MODULE_AUTHOR("Vishal Verma "); +MODULE_LICENSE("GPL v2"); +module_init(nd_btt_init); +module_exit(nd_btt_exit); diff --git a/drivers/nvdimm/btt.h b/drivers/nvdimm/btt.h index e8f6d8e0ddd3..8c95a7792c3e 100644 --- a/drivers/nvdimm/btt.h +++ b/drivers/nvdimm/btt.h @@ -19,6 +19,39 @@ #define BTT_SIG_LEN 16 #define BTT_SIG "BTT_ARENA_INFO\0" +#define MAP_ENT_SIZE 4 +#define MAP_TRIM_SHIFT 31 +#define MAP_TRIM_MASK (1 << MAP_TRIM_SHIFT) +#define MAP_ERR_SHIFT 30 +#define MAP_ERR_MASK (1 << MAP_ERR_SHIFT) +#define MAP_LBA_MASK (~((1 << MAP_TRIM_SHIFT) | (1 << MAP_ERR_SHIFT))) +#define MAP_ENT_NORMAL 0xC0000000 +#define LOG_ENT_SIZE sizeof(struct log_entry) +#define ARENA_MIN_SIZE (1UL << 24) /* 16 MB */ +#define ARENA_MAX_SIZE (1ULL << 39) /* 512 GB */ +#define RTT_VALID (1UL << 31) +#define RTT_INVALID 0 +#define INT_LBASIZE_ALIGNMENT 256 +#define BTT_PG_SIZE 4096 +#define BTT_DEFAULT_NFREE ND_MAX_LANES +#define LOG_SEQ_INIT 1 + +#define IB_FLAG_ERROR 0x00000001 +#define IB_FLAG_ERROR_MASK 0x00000001 + +enum btt_init_state { + INIT_UNCHECKED = 0, + INIT_NOTFOUND, + INIT_READY +}; + +struct log_entry { + __le32 lba; + __le32 old_map; + __le32 new_map; + __le32 seq; + __le64 padding[2]; +}; struct btt_sb { u8 signature[BTT_SIG_LEN]; @@ -42,4 +75,112 @@ struct btt_sb { __le64 checksum; }; +struct free_entry { + u32 block; + u8 sub; + u8 seq; +}; + +struct aligned_lock { + union { + spinlock_t lock; + u8 cacheline_padding[L1_CACHE_BYTES]; + }; +}; + +/** + * struct arena_info - handle for an arena + * @size: Size in bytes this arena occupies on the raw device. + * This includes arena metadata. + * @external_lba_start: The first external LBA in this arena. + * @internal_nlba: Number of internal blocks available in the arena + * including nfree reserved blocks + * @internal_lbasize: Internal and external lba sizes may be different as + * we can round up 'odd' external lbasizes such as 520B + * to be aligned. + * @external_nlba: Number of blocks contributed by the arena to the number + * reported to upper layers. (internal_nlba - nfree) + * @external_lbasize: LBA size as exposed to upper layers. + * @nfree: A reserve number of 'free' blocks that is used to + * handle incoming writes. + * @version_major: Metadata layout version major. + * @version_minor: Metadata layout version minor. + * @nextoff: Offset in bytes to the start of the next arena. + * @infooff: Offset in bytes to the info block of this arena. + * @dataoff: Offset in bytes to the data area of this arena. + * @mapoff: Offset in bytes to the map area of this arena. + * @logoff: Offset in bytes to the log area of this arena. + * @info2off: Offset in bytes to the backup info block of this arena. + * @freelist: Pointer to in-memory list of free blocks + * @rtt: Pointer to in-memory "Read Tracking Table" + * @map_locks: Spinlocks protecting concurrent map writes + * @nd_btt: Pointer to parent nd_btt structure. + * @list: List head for list of arenas + * @debugfs_dir: Debugfs dentry + * @flags: Arena flags - may signify error states. + * + * arena_info is a per-arena handle. Once an arena is narrowed down for an + * IO, this struct is passed around for the duration of the IO. + */ +struct arena_info { + u64 size; /* Total bytes for this arena */ + u64 external_lba_start; + u32 internal_nlba; + u32 internal_lbasize; + u32 external_nlba; + u32 external_lbasize; + u32 nfree; + u16 version_major; + u16 version_minor; + /* Byte offsets to the different on-media structures */ + u64 nextoff; + u64 infooff; + u64 dataoff; + u64 mapoff; + u64 logoff; + u64 info2off; + /* Pointers to other in-memory structures for this arena */ + struct free_entry *freelist; + u32 *rtt; + struct aligned_lock *map_locks; + struct nd_btt *nd_btt; + struct list_head list; + struct dentry *debugfs_dir; + /* Arena flags */ + u32 flags; +}; + +/** + * struct btt - handle for a BTT instance + * @btt_disk: Pointer to the gendisk for BTT device + * @btt_queue: Pointer to the request queue for the BTT device + * @arena_list: Head of the list of arenas + * @debugfs_dir: Debugfs dentry + * @nd_btt: Parent nd_btt struct + * @nlba: Number of logical blocks exposed to the upper layers + * after removing the amount of space needed by metadata + * @rawsize: Total size in bytes of the available backing device + * @lbasize: LBA size as requested and presented to upper layers. + * This is sector_size + size of any metadata. + * @sector_size: The Linux sector size - 512 or 4096 + * @lanes: Per-lane spinlocks + * @init_lock: Mutex used for the BTT initialization + * @init_state: Flag describing the initialization state for the BTT + * @num_arenas: Number of arenas in the BTT instance + */ +struct btt { + struct gendisk *btt_disk; + struct request_queue *btt_queue; + struct list_head arena_list; + struct dentry *debugfs_dir; + struct nd_btt *nd_btt; + u64 nlba; + unsigned long long rawsize; + u32 lbasize; + u32 sector_size; + struct nd_region *nd_region; + struct mutex init_lock; + int init_state; + int num_arenas; +}; #endif diff --git a/drivers/nvdimm/btt_devs.c b/drivers/nvdimm/btt_devs.c index effb70a88347..470fbdccd0ac 100644 --- a/drivers/nvdimm/btt_devs.c +++ b/drivers/nvdimm/btt_devs.c @@ -348,7 +348,8 @@ struct device *nd_btt_create(struct nd_region *nd_region) */ u64 nd_btt_sb_checksum(struct btt_sb *btt_sb) { - u64 sum, sum_save; + u64 sum; + __le64 sum_save; sum_save = btt_sb->checksum; btt_sb->checksum = 0; diff --git a/drivers/nvdimm/namespace_devs.c b/drivers/nvdimm/namespace_devs.c index 2c50a0719f8d..4aa647c8d644 100644 --- a/drivers/nvdimm/namespace_devs.c +++ b/drivers/nvdimm/namespace_devs.c @@ -76,6 +76,30 @@ static bool is_namespace_io(struct device *dev) return dev ? dev->type == &namespace_io_device_type : false; } +const char *nvdimm_namespace_disk_name(struct nd_namespace_common *ndns, + char *name) +{ + struct nd_region *nd_region = to_nd_region(ndns->dev.parent); + const char *suffix = ""; + + if (ndns->claim && is_nd_btt(ndns->claim)) + suffix = "s"; + + if (is_namespace_pmem(&ndns->dev) || is_namespace_io(&ndns->dev)) + sprintf(name, "pmem%d%s", nd_region->id, suffix); + else if (is_namespace_blk(&ndns->dev)) { + struct nd_namespace_blk *nsblk; + + nsblk = to_nd_namespace_blk(&ndns->dev); + sprintf(name, "ndblk%d.%d%s", nd_region->id, nsblk->id, suffix); + } else { + return NULL; + } + + return name; +} +EXPORT_SYMBOL(nvdimm_namespace_disk_name); + static ssize_t nstype_show(struct device *dev, struct device_attribute *attr, char *buf) { diff --git a/drivers/nvdimm/nd.h b/drivers/nvdimm/nd.h index d13eccbb67e9..1b937c235913 100644 --- a/drivers/nvdimm/nd.h +++ b/drivers/nvdimm/nd.h @@ -20,6 +20,12 @@ #include "label.h" enum { + /* + * Limits the maximum number of block apertures a dimm can + * support and is an input to the geometry/on-disk-format of a + * BTT instance + */ + ND_MAX_LANES = 256, SECTOR_SHIFT = 9, }; @@ -75,6 +81,11 @@ static inline struct nd_namespace_index *to_next_namespace_index( for (res = (ndd)->dpa.child, next = res ? res->sibling : NULL; \ res; res = next, next = next ? next->sibling : NULL) +struct nd_percpu_lane { + int count; + spinlock_t lock; +}; + struct nd_region { struct device dev; struct ida ns_ida; @@ -84,9 +95,10 @@ struct nd_region { u16 ndr_mappings; u64 ndr_size; u64 ndr_start; - int id; + int id, num_lanes; void *provider_data; struct nd_interleave_set *nd_set; + struct nd_percpu_lane __percpu *lane; struct nd_mapping mapping[0]; }; @@ -100,9 +112,11 @@ static inline unsigned nd_inc_seq(unsigned seq) return next[seq & 3]; } +struct btt; struct nd_btt { struct device dev; struct nd_namespace_common *ndns; + struct btt *btt; unsigned long lbasize; u8 *uuid; int id; @@ -157,6 +171,8 @@ static inline struct device *nd_btt_create(struct nd_region *nd_region) #endif struct nd_region *to_nd_region(struct device *dev); +unsigned int nd_region_acquire_lane(struct nd_region *nd_region); +void nd_region_release_lane(struct nd_region *nd_region, unsigned int lane); int nd_region_to_nstype(struct nd_region *nd_region); int nd_region_register_namespaces(struct nd_region *nd_region, int *err); u64 nd_region_interleave_set_cookie(struct nd_region *nd_region); @@ -172,4 +188,8 @@ struct resource *nvdimm_allocate_dpa(struct nvdimm_drvdata *ndd, resource_size_t n); resource_size_t nvdimm_namespace_capacity(struct nd_namespace_common *ndns); struct nd_namespace_common *nvdimm_namespace_common_probe(struct device *dev); +int nvdimm_namespace_attach_btt(struct nd_namespace_common *ndns); +int nvdimm_namespace_detach_btt(struct nd_namespace_common *ndns); +const char *nvdimm_namespace_disk_name(struct nd_namespace_common *ndns, + char *name); #endif /* __ND_H__ */ diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index d0c6b4bdba69..7346054bccbb 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -160,7 +160,6 @@ static void pmem_detach_disk(struct pmem_device *pmem) static int pmem_attach_disk(struct nd_namespace_common *ndns, struct pmem_device *pmem) { - struct nd_region *nd_region = to_nd_region(ndns->dev.parent); struct gendisk *disk; pmem->pmem_queue = blk_alloc_queue(GFP_KERNEL); @@ -183,7 +182,7 @@ static int pmem_attach_disk(struct nd_namespace_common *ndns, disk->private_data = pmem; disk->queue = pmem->pmem_queue; disk->flags = GENHD_FL_EXT_DEVT; - sprintf(disk->disk_name, "pmem%d", nd_region->id); + nvdimm_namespace_disk_name(ndns, disk->disk_name); disk->driverfs_dev = &ndns->dev; set_capacity(disk, pmem->size >> 9); pmem->pmem_disk = disk; @@ -211,17 +210,6 @@ static int pmem_rw_bytes(struct nd_namespace_common *ndns, return 0; } -static int nvdimm_namespace_attach_btt(struct nd_namespace_common *ndns) -{ - /* TODO */ - return -ENXIO; -} - -static void nvdimm_namespace_detach_btt(struct nd_namespace_common *ndns) -{ - /* TODO */ -} - static void pmem_free(struct pmem_device *pmem) { iounmap(pmem->virt_addr); diff --git a/drivers/nvdimm/region.c b/drivers/nvdimm/region.c index 2a5f3f53d79d..eb8aebcd4800 100644 --- a/drivers/nvdimm/region.c +++ b/drivers/nvdimm/region.c @@ -10,6 +10,7 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU * General Public License for more details. */ +#include #include #include #include @@ -18,10 +19,21 @@ static int nd_region_probe(struct device *dev) { int err; + static unsigned long once; struct nd_region_namespaces *num_ns; struct nd_region *nd_region = to_nd_region(dev); int rc = nd_region_register_namespaces(nd_region, &err); + if (nd_region->num_lanes > num_online_cpus() + && nd_region->num_lanes < num_possible_cpus() + && !test_and_set_bit(0, &once)) { + dev_info(dev, "online cpus (%d) < concurrent i/o lanes (%d) < possible cpus (%d)\n", + num_online_cpus(), nd_region->num_lanes, + num_possible_cpus()); + dev_info(dev, "setting nr_cpus=%d may yield better libnvdimm device performance\n", + nd_region->num_lanes); + } + num_ns = devm_kzalloc(dev, sizeof(*num_ns), GFP_KERNEL); if (!num_ns) return -ENOMEM; diff --git a/drivers/nvdimm/region_devs.c b/drivers/nvdimm/region_devs.c index 4fd92389fa7e..fe8ec21fe3d7 100644 --- a/drivers/nvdimm/region_devs.c +++ b/drivers/nvdimm/region_devs.c @@ -32,6 +32,7 @@ static void nd_region_release(struct device *dev) put_device(&nvdimm->dev); } + free_percpu(nd_region->lane); ida_simple_remove(®ion_ida, nd_region->id); kfree(nd_region); } @@ -531,13 +532,66 @@ void *nd_region_provider_data(struct nd_region *nd_region) } EXPORT_SYMBOL_GPL(nd_region_provider_data); +/** + * nd_region_acquire_lane - allocate and lock a lane + * @nd_region: region id and number of lanes possible + * + * A lane correlates to a BLK-data-window and/or a log slot in the BTT. + * We optimize for the common case where there are 256 lanes, one + * per-cpu. For larger systems we need to lock to share lanes. For now + * this implementation assumes the cost of maintaining an allocator for + * free lanes is on the order of the lock hold time, so it implements a + * static lane = cpu % num_lanes mapping. + * + * In the case of a BTT instance on top of a BLK namespace a lane may be + * acquired recursively. We lock on the first instance. + * + * In the case of a BTT instance on top of PMEM, we only acquire a lane + * for the BTT metadata updates. + */ +unsigned int nd_region_acquire_lane(struct nd_region *nd_region) +{ + unsigned int cpu, lane; + + cpu = get_cpu(); + if (nd_region->num_lanes < nr_cpu_ids) { + struct nd_percpu_lane *ndl_lock, *ndl_count; + + lane = cpu % nd_region->num_lanes; + ndl_count = per_cpu_ptr(nd_region->lane, cpu); + ndl_lock = per_cpu_ptr(nd_region->lane, lane); + if (ndl_count->count++ == 0) + spin_lock(&ndl_lock->lock); + } else + lane = cpu; + + return lane; +} +EXPORT_SYMBOL(nd_region_acquire_lane); + +void nd_region_release_lane(struct nd_region *nd_region, unsigned int lane) +{ + if (nd_region->num_lanes < nr_cpu_ids) { + unsigned int cpu = get_cpu(); + struct nd_percpu_lane *ndl_lock, *ndl_count; + + ndl_count = per_cpu_ptr(nd_region->lane, cpu); + ndl_lock = per_cpu_ptr(nd_region->lane, lane); + if (--ndl_count->count == 0) + spin_unlock(&ndl_lock->lock); + put_cpu(); + } + put_cpu(); +} +EXPORT_SYMBOL(nd_region_release_lane); + static struct nd_region *nd_region_create(struct nvdimm_bus *nvdimm_bus, struct nd_region_desc *ndr_desc, struct device_type *dev_type, const char *caller) { struct nd_region *nd_region; struct device *dev; - u16 i; + unsigned int i; for (i = 0; i < ndr_desc->num_mappings; i++) { struct nd_mapping *nd_mapping = &ndr_desc->nd_mapping[i]; @@ -557,9 +611,19 @@ static struct nd_region *nd_region_create(struct nvdimm_bus *nvdimm_bus, if (!nd_region) return NULL; nd_region->id = ida_simple_get(®ion_ida, 0, 0, GFP_KERNEL); - if (nd_region->id < 0) { - kfree(nd_region); - return NULL; + if (nd_region->id < 0) + goto err_id; + + nd_region->lane = alloc_percpu(struct nd_percpu_lane); + if (!nd_region->lane) + goto err_percpu; + + for (i = 0; i < nr_cpu_ids; i++) { + struct nd_percpu_lane *ndl; + + ndl = per_cpu_ptr(nd_region->lane, i); + spin_lock_init(&ndl->lock); + ndl->count = 0; } memcpy(nd_region->mapping, ndr_desc->nd_mapping, @@ -573,6 +637,7 @@ static struct nd_region *nd_region_create(struct nvdimm_bus *nvdimm_bus, nd_region->ndr_mappings = ndr_desc->num_mappings; nd_region->provider_data = ndr_desc->provider_data; nd_region->nd_set = ndr_desc->nd_set; + nd_region->num_lanes = ndr_desc->num_lanes; ida_init(&nd_region->ns_ida); ida_init(&nd_region->btt_ida); dev = &nd_region->dev; @@ -585,11 +650,18 @@ static struct nd_region *nd_region_create(struct nvdimm_bus *nvdimm_bus, nd_device_register(dev); return nd_region; + + err_percpu: + ida_simple_remove(®ion_ida, nd_region->id); + err_id: + kfree(nd_region); + return NULL; } struct nd_region *nvdimm_pmem_region_create(struct nvdimm_bus *nvdimm_bus, struct nd_region_desc *ndr_desc) { + ndr_desc->num_lanes = ND_MAX_LANES; return nd_region_create(nvdimm_bus, ndr_desc, &nd_pmem_device_type, __func__); } @@ -600,6 +672,7 @@ struct nd_region *nvdimm_blk_region_create(struct nvdimm_bus *nvdimm_bus, { if (ndr_desc->num_mappings > 1) return NULL; + ndr_desc->num_lanes = min(ndr_desc->num_lanes, ND_MAX_LANES); return nd_region_create(nvdimm_bus, ndr_desc, &nd_blk_device_type, __func__); } @@ -608,6 +681,7 @@ EXPORT_SYMBOL_GPL(nvdimm_blk_region_create); struct nd_region *nvdimm_volatile_region_create(struct nvdimm_bus *nvdimm_bus, struct nd_region_desc *ndr_desc) { + ndr_desc->num_lanes = ND_MAX_LANES; return nd_region_create(nvdimm_bus, ndr_desc, &nd_volatile_device_type, __func__); } diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h index a59dca17b3aa..531d99dfac68 100644 --- a/include/linux/libnvdimm.h +++ b/include/linux/libnvdimm.h @@ -85,6 +85,7 @@ struct nd_region_desc { const struct attribute_group **attr_groups; struct nd_interleave_set *nd_set; void *provider_data; + int num_lanes; }; struct nvdimm_bus;