===================================================================
@@ -334,6 +334,17 @@ config DM_CACHE_SMQ
of less memory utilization, improved performance and increased
adaptability in the face of changing workloads.
+config DM_WRITECACHE
+ tristate "Writecache target"
+ depends on BLK_DEV_DM
+ ---help---
+ The writecache target caches writes on persistent memory or SSD.
+ It is intended for databases or other programs that need extremely
+ low commit latency.
+
+ The writecache target doesn't cache reads because reads are supposed
+ to be cached in standard RAM.
+
config DM_ERA
tristate "Era target (EXPERIMENTAL)"
depends on BLK_DEV_DM
===================================================================
@@ -67,6 +67,7 @@ obj-$(CONFIG_DM_ERA) += dm-era.o
obj-$(CONFIG_DM_LOG_WRITES) += dm-log-writes.o
obj-$(CONFIG_DM_INTEGRITY) += dm-integrity.o
obj-$(CONFIG_DM_ZONED) += dm-zoned.o
+obj-$(CONFIG_DM_WRITECACHE) += dm-writecache.o
ifeq ($(CONFIG_DM_UEVENT),y)
dm-mod-objs += dm-uevent.o
===================================================================
@@ -0,0 +1,2382 @@
+/*
+ * Copyright (C) 2018 Red Hat. All rights reserved.
+ *
+ * This file is released under the GPL.
+ */
+
+#include <linux/device-mapper.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/vmalloc.h>
+#include <linux/kthread.h>
+#include <linux/swait.h>
+#include <linux/dm-io.h>
+#include <linux/dm-kcopyd.h>
+#include <linux/dax.h>
+#include <linux/pfn_t.h>
+#include <linux/libnvdimm.h>
+
+#define DM_MSG_PREFIX "writecache"
+
+#define HIGH_WATERMARK 50
+#define LOW_WATERMARK 45
+#define MAX_WRITEBACK_JOBS 0
+#define ENDIO_LATENCY 16
+#define WRITEBACK_LATENCY 64
+#define AUTOCOMMIT_BLOCKS_SSD 65536
+#define AUTOCOMMIT_BLOCKS_PMEM 64
+#define AUTOCOMMIT_MSEC 1000
+
+/*
+ * If the architecture doesn't support persistent memory, we can use this driver
+ * in SSD-only mode.
+ */
+#if !defined(CONFIG_ARCH_HAS_PMEM_API) || !defined(CONFIG_DAX)
+#define DM_WRITECACHE_ONLY_SSD
+#endif
+
+//#define WC_MEASURE_LATENCY
+
+#define BITMAP_GRANULARITY 65536
+#if BITMAP_GRANULARITY < PAGE_SIZE
+#undef BITMAP_GRANULARITY
+#define BITMAP_GRANULARITY PAGE_SIZE
+#endif
+
+#define pmem_assign(dest, src) \
+do { \
+ typeof(dest) uniq = (src); \
+ memcpy_flushcache(&(dest), &uniq, sizeof(dest)); \
+} while (0)
+
+#if defined(__HAVE_ARCH_MEMCPY_MCSAFE) && !defined(DM_WRITECACHE_ONLY_SSD)
+#define DM_WRITECACHE_HANDLE_HARDWARE_ERRORS
+#endif
+
+#define MEMORY_SUPERBLOCK_MAGIC 0x23489321
+#define MEMORY_SUPERBLOCK_VERSION 1
+
+struct wc_memory_entry {
+ __le64 original_sector;
+ __le64 seq_count;
+};
+
+struct wc_memory_superblock {
+ union {
+ struct {
+ __le32 magic;
+ __le32 version;
+ __le32 block_size;
+ __le32 pad;
+ __le64 n_blocks;
+ __le64 seq_count;
+ };
+ __le64 padding[8];
+ };
+ struct wc_memory_entry entries[0];
+};
+
+struct wc_entry {
+ struct rb_node rb_node;
+ struct list_head lru;
+ unsigned short wc_list_contiguous;
+ bool write_in_progress
+#if BITS_PER_LONG == 64
+ :1
+#endif
+ ;
+ unsigned long index
+#if BITS_PER_LONG == 64
+ :47
+#endif
+ ;
+#ifdef DM_WRITECACHE_HANDLE_HARDWARE_ERRORS
+ uint64_t original_sector;
+ uint64_t seq_count;
+#endif
+};
+
+#ifndef DM_WRITECACHE_ONLY_SSD
+#define WC_MODE_PMEM(wc) (likely((wc)->pmem_mode))
+#define WC_MODE_FUA(wc) ((wc)->writeback_fua)
+#else
+#define WC_MODE_PMEM(wc) false
+#define WC_MODE_FUA(wc) false
+#endif
+#define WC_MODE_SORT_FREELIST(wc) (!WC_MODE_PMEM(wc))
+
+struct dm_writecache {
+#ifndef DM_WRITECACHE_ONLY_SSD
+ bool pmem_mode;
+ bool writeback_fua;
+#endif
+ struct mutex lock;
+ struct rb_root tree;
+ struct list_head lru;
+ union {
+ struct list_head freelist;
+ struct {
+ struct rb_root freetree;
+ struct wc_entry *current_free;
+ };
+ };
+ size_t freelist_size;
+ size_t writeback_size;
+ unsigned uncommitted_blocks;
+ unsigned autocommit_blocks;
+ unsigned max_writeback_jobs;
+ size_t freelist_high_watermark;
+ size_t freelist_low_watermark;
+ struct timer_list autocommit_timer;
+ unsigned long autocommit_jiffies;
+ struct swait_queue_head freelist_wait;
+
+ struct dm_target *ti;
+ struct dm_dev *dev;
+ struct dm_dev *ssd_dev;
+ void *memory_map;
+ uint64_t memory_map_size;
+ size_t metadata_sectors;
+ void *block_start;
+ struct wc_entry *entries;
+ unsigned block_size;
+ unsigned char block_size_bits;
+ size_t n_blocks;
+ uint64_t seq_count;
+ int error;
+
+ bool overwrote_committed;
+ bool memory_vmapped;
+
+ atomic_t bio_in_progress[2];
+ struct swait_queue_head bio_in_progress_wait[2];
+
+ struct dm_io_client *dm_io;
+
+ unsigned writeback_all;
+ struct workqueue_struct *writeback_wq;
+ struct work_struct writeback_work;
+ struct work_struct flush_work;
+
+ struct swait_queue_head endio_thread_wait;
+ struct list_head endio_list;
+ struct task_struct *endio_thread;
+
+ struct task_struct *flush_thread;
+ struct bio *flush_bio;
+ struct completion flush_completion;
+
+ struct bio_set *bio_set;
+ mempool_t *copy_pool;
+
+ struct dm_kcopyd_client *dm_kcopyd;
+ unsigned long *dirty_bitmap;
+ unsigned dirty_bitmap_size;
+
+ bool high_wm_percent_set;
+ bool low_wm_percent_set;
+ bool max_writeback_jobs_set;
+ bool autocommit_blocks_set;
+ bool autocommit_time_set;
+ bool writeback_fua_set;
+ bool flush_on_suspend;
+
+#ifdef WC_MEASURE_LATENCY
+ ktime_t lock_acquired_time;
+ ktime_t max_lock_held;
+ ktime_t max_lock_wait;
+ ktime_t max_freelist_wait;
+ ktime_t measure_latency_time;
+ ktime_t max_measure_latency;
+#endif
+};
+
+#define WB_LIST_INLINE 16
+
+struct writeback_struct {
+ struct list_head endio_entry;
+ struct dm_writecache *wc;
+ struct wc_entry **wc_list;
+ unsigned wc_list_n;
+ unsigned page_offset;
+ struct page *page;
+ struct wc_entry *wc_list_inline[WB_LIST_INLINE];
+ struct bio bio;
+};
+
+struct copy_struct {
+ struct list_head endio_entry;
+ struct dm_writecache *wc;
+ struct wc_entry *e;
+ unsigned n_entries;
+ int error;
+};
+
+DECLARE_DM_KCOPYD_THROTTLE_WITH_MODULE_PARM(dm_writecache_throttle,
+ "A percentage of time allocated for data copying");
+
+static inline void measure_latency_start(struct dm_writecache *wc)
+{
+#ifdef WC_MEASURE_LATENCY
+ wc->measure_latency_time = ktime_get();
+#endif
+}
+
+static inline void measure_latency_end(struct dm_writecache *wc, unsigned long n)
+{
+#ifdef WC_MEASURE_LATENCY
+ ktime_t now = ktime_get();
+ if (now - wc->measure_latency_time > wc->max_measure_latency) {
+ wc->max_measure_latency = now - wc->measure_latency_time;
+ printk(KERN_DEBUG "dm-writecache: measured latency %lld.%03lldus, %lu steps\n",
+ wc->max_measure_latency / 1000, wc->max_measure_latency % 1000, n);
+ }
+#endif
+}
+
+static void __wc_lock(struct dm_writecache *wc, int line)
+{
+#ifdef WC_MEASURE_LATENCY
+ ktime_t before, after;
+ before = ktime_get();
+#endif
+ mutex_lock(&wc->lock);
+#ifdef WC_MEASURE_LATENCY
+ after = ktime_get();
+ if (unlikely(after - before > wc->max_lock_wait)) {
+ wc->max_lock_wait = after - before;
+ printk(KERN_DEBUG "dm-writecache: waiting for lock for %lld.%03lldus at %d\n",
+ wc->max_lock_wait / 1000, wc->max_lock_wait % 1000, line);
+ after = ktime_get();
+ }
+ wc->lock_acquired_time = after;
+#endif
+}
+#define wc_lock(wc) __wc_lock(wc, __LINE__)
+
+static void __wc_unlock(struct dm_writecache *wc, int line)
+{
+#ifdef WC_MEASURE_LATENCY
+ ktime_t now = ktime_get();
+ if (now - wc->lock_acquired_time > wc->max_lock_held) {
+ wc->max_lock_held = now - wc->lock_acquired_time;
+ printk(KERN_DEBUG "dm-writecache: lock held for %lld.%03lldus at %d\n",
+ wc->max_lock_held / 1000, wc->max_lock_held % 1000, line);
+ }
+#endif
+ mutex_unlock(&wc->lock);
+}
+#define wc_unlock(wc) __wc_unlock(wc, __LINE__)
+
+#define wc_unlock_long(wc) mutex_unlock(&wc->lock)
+
+#ifndef DM_WRITECACHE_ONLY_SSD
+static int persistent_memory_claim(struct dm_writecache *wc)
+{
+ int r;
+ loff_t s;
+ long p, da;
+ pfn_t pfn;
+ int id;
+ struct page **pages;
+
+ wc->memory_vmapped = false;
+
+ if (!wc->ssd_dev->dax_dev) {
+ r = -EOPNOTSUPP;
+ goto err1;
+ }
+ s = wc->memory_map_size;
+ p = s >> PAGE_SHIFT;
+ if (!p) {
+ r = -EINVAL;
+ goto err1;
+ }
+ if (p != s >> PAGE_SHIFT) {
+ r = -EOVERFLOW;
+ goto err1;
+ }
+
+ id = dax_read_lock();
+
+ da = dax_direct_access(wc->ssd_dev->dax_dev, 0, p, &wc->memory_map, &pfn);
+ if (da < 0) {
+ wc->memory_map = NULL;
+ r = da;
+ goto err2;
+ }
+ if (!pfn_t_has_page(pfn)) {
+ wc->memory_map = NULL;
+ r = -EOPNOTSUPP;
+ goto err2;
+ }
+#ifdef WC_MEASURE_LATENCY
+ printk(KERN_DEBUG "dm-writecache: device %s, pfn %016llx\n",
+ wc->ssd_dev->name, pfn.val);
+#endif
+ if (da != p) {
+ long i;
+ wc->memory_map = NULL;
+ pages = kvmalloc(p * sizeof(struct page *), GFP_KERNEL);
+ if (!pages) {
+ r = -ENOMEM;
+ goto err2;
+ }
+ i = 0;
+ do {
+ long daa;
+ void *dummy_addr;
+ daa = dax_direct_access(wc->ssd_dev->dax_dev, i, p - i,
+ &dummy_addr, &pfn);
+ if (daa <= 0) {
+ r = daa ? daa : -EINVAL;
+ goto err3;
+ }
+ if (!pfn_t_has_page(pfn)) {
+ r = -EOPNOTSUPP;
+ goto err3;
+ }
+ while (daa-- && i < p) {
+ pages[i++] = pfn_t_to_page(pfn);
+ pfn.val++;
+ }
+ } while (i < p);
+ wc->memory_map = vmap(pages, p, VM_MAP, PAGE_KERNEL);
+ if (!wc->memory_map) {
+ r = -ENOMEM;
+ goto err3;
+ }
+ kvfree(pages);
+ wc->memory_vmapped = true;
+ }
+
+ dax_read_unlock(id);
+
+ return 0;
+
+err3:
+ kvfree(pages);
+err2:
+ dax_read_unlock(id);
+err1:
+ return r;
+}
+#endif
+
+static void persistent_memory_release(struct dm_writecache *wc)
+{
+ if (wc->memory_vmapped)
+ vunmap(wc->memory_map);
+}
+
+static struct page *persistent_memory_page(void *addr)
+{
+ if (is_vmalloc_addr(addr))
+ return vmalloc_to_page(addr);
+ else
+ return virt_to_page(addr);
+}
+
+static unsigned persistent_memory_page_offset(void *addr)
+{
+ return (unsigned long)addr & (PAGE_SIZE - 1);
+}
+
+static void persistent_memory_flush_cache(void *ptr, size_t size)
+{
+ if (is_vmalloc_addr(ptr))
+ flush_kernel_vmap_range(ptr, size);
+}
+
+static void persistent_memory_invalidate_cache(void *ptr, size_t size)
+{
+ if (is_vmalloc_addr(ptr))
+ invalidate_kernel_vmap_range(ptr, size);
+}
+
+static struct wc_memory_superblock *sb(struct dm_writecache *wc)
+{
+ return wc->memory_map;
+}
+
+static struct wc_memory_entry *memory_entry(struct dm_writecache *wc, struct wc_entry *e)
+{
+ if (is_power_of_2(sizeof(struct wc_entry)) && 0)
+ return &sb(wc)->entries[e - wc->entries];
+ else
+ return &sb(wc)->entries[e->index];
+}
+
+static void *memory_data(struct dm_writecache *wc, struct wc_entry *e)
+{
+ return (char *)wc->block_start + (e->index << wc->block_size_bits);
+}
+
+static sector_t cache_sector(struct dm_writecache *wc, struct wc_entry *e)
+{
+ return wc->metadata_sectors +
+ ((sector_t)e->index << (wc->block_size_bits - SECTOR_SHIFT));
+}
+
+static uint64_t read_original_sector(struct dm_writecache *wc, struct wc_entry *e)
+{
+#ifdef DM_WRITECACHE_HANDLE_HARDWARE_ERRORS
+ return e->original_sector;
+#else
+ return le64_to_cpu(memory_entry(wc, e)->original_sector);
+#endif
+}
+
+static uint64_t read_seq_count(struct dm_writecache *wc, struct wc_entry *e)
+{
+#ifdef DM_WRITECACHE_HANDLE_HARDWARE_ERRORS
+ return e->seq_count;
+#else
+ return le64_to_cpu(memory_entry(wc, e)->seq_count);
+#endif
+}
+
+static void clear_seq_count(struct dm_writecache *wc, struct wc_entry *e)
+{
+#ifdef DM_WRITECACHE_HANDLE_HARDWARE_ERRORS
+ e->seq_count = -1;
+#endif
+ pmem_assign(memory_entry(wc, e)->seq_count, cpu_to_le64(-1));
+}
+
+static void write_original_sector_seq_count(struct dm_writecache *wc, struct wc_entry *e,
+ uint64_t original_sector, uint64_t seq_count)
+{
+ struct wc_memory_entry me;
+#ifdef DM_WRITECACHE_HANDLE_HARDWARE_ERRORS
+ e->original_sector = original_sector;
+ e->seq_count = seq_count;
+#endif
+ me.original_sector = cpu_to_le64(original_sector);
+ me.seq_count = cpu_to_le64(seq_count);
+ pmem_assign(*memory_entry(wc, e), me);
+}
+
+#define writecache_error(wc, err, msg, arg...) \
+do { \
+ if (!cmpxchg(&(wc)->error, 0, err)) \
+ DMERR(msg, ##arg); \
+ swake_up(&(wc)->freelist_wait); \
+} while (0)
+
+#define writecache_has_error(wc) (unlikely(READ_ONCE((wc)->error)))
+
+static void writecache_flush_all_metadata(struct dm_writecache *wc)
+{
+ if (!WC_MODE_PMEM(wc))
+ memset(wc->dirty_bitmap, -1, wc->dirty_bitmap_size);
+}
+
+static void writecache_flush_region(struct dm_writecache *wc, void *ptr, size_t size)
+{
+ if (!WC_MODE_PMEM(wc))
+ __set_bit(((char *)ptr - (char *)wc->memory_map) / BITMAP_GRANULARITY,
+ wc->dirty_bitmap);
+}
+
+static void writecache_disk_flush(struct dm_writecache *wc, struct dm_dev *dev);
+
+struct io_notify {
+ struct dm_writecache *wc;
+ struct completion c;
+ atomic_t count;
+};
+
+static void writecache_notify_io(unsigned long error, void *context)
+{
+ struct io_notify *endio = context;
+
+ if (unlikely(error != 0))
+ writecache_error(endio->wc, -EIO, "error writing metadata");
+ BUG_ON(atomic_read(&endio->count) <= 0);
+ if (atomic_dec_and_test(&endio->count))
+ complete(&endio->c);
+}
+
+static void ssd_commit_flushed(struct dm_writecache *wc)
+{
+ struct dm_io_region region;
+ struct dm_io_request req;
+ struct io_notify endio = {
+ wc,
+ COMPLETION_INITIALIZER_ONSTACK(endio.c),
+ ATOMIC_INIT(1),
+ };
+ unsigned bitmap_bits = wc->dirty_bitmap_size * BITS_PER_LONG;
+ unsigned i = 0;
+
+ while (1) {
+ unsigned j;
+ i = find_next_bit(wc->dirty_bitmap, bitmap_bits, i);
+ if (unlikely(i == bitmap_bits))
+ break;
+ j = find_next_zero_bit(wc->dirty_bitmap, bitmap_bits, i);
+
+ region.bdev = wc->ssd_dev->bdev;
+ region.sector = (sector_t)i * (BITMAP_GRANULARITY >> SECTOR_SHIFT);
+ region.count = (sector_t)(j - i) * (BITMAP_GRANULARITY >> SECTOR_SHIFT);
+
+ if (unlikely(region.sector >= wc->metadata_sectors))
+ break;
+ if (unlikely(region.sector + region.count > wc->metadata_sectors))
+ region.count = wc->metadata_sectors - region.sector;
+
+ atomic_inc(&endio.count);
+ req.bi_op = REQ_OP_WRITE;
+ req.bi_op_flags = REQ_SYNC;
+ req.mem.type = DM_IO_VMA;
+ req.mem.ptr.vma = (char *)wc->memory_map + (size_t)i * BITMAP_GRANULARITY;
+ req.client = wc->dm_io;
+ req.notify.fn = writecache_notify_io;
+ req.notify.context = &endio;
+
+ /* writing via async dm-io (implied by notify.fn above) won't return an error */
+ (void) dm_io(&req, 1, ®ion, NULL);
+ i = j;
+ }
+
+ writecache_notify_io(0, &endio);
+ wait_for_completion_io(&endio.c);
+
+ writecache_disk_flush(wc, wc->ssd_dev);
+
+ memset(wc->dirty_bitmap, 0, wc->dirty_bitmap_size);
+}
+
+static void writecache_commit_flushed(struct dm_writecache *wc)
+{
+ if (WC_MODE_PMEM(wc))
+ wmb();
+ else
+ ssd_commit_flushed(wc);
+}
+
+static void writecache_disk_flush(struct dm_writecache *wc, struct dm_dev *dev)
+{
+ int r;
+ struct dm_io_region region;
+ struct dm_io_request req;
+
+ region.bdev = dev->bdev;
+ region.sector = 0;
+ region.count = 0;
+ req.bi_op = REQ_OP_WRITE;
+ req.bi_op_flags = REQ_PREFLUSH;
+ req.mem.type = DM_IO_KMEM;
+ req.mem.ptr.addr = NULL;
+ req.client = wc->dm_io;
+ req.notify.fn = NULL;
+
+ r = dm_io(&req, 1, ®ion, NULL);
+ if (unlikely(r))
+ writecache_error(wc, r, "error flushing metadata: %d", r);
+}
+
+static void writecache_wait_for_ios(struct dm_writecache *wc, int direction)
+{
+ swait_event(wc->bio_in_progress_wait[direction],
+ !atomic_read(&wc->bio_in_progress[direction]));
+}
+
+#define WFE_RETURN_FOLLOWING 1
+#define WFE_LOWEST_SEQ 2
+
+static struct wc_entry *writecache_find_entry(struct dm_writecache *wc,
+ uint64_t block, int flags)
+{
+ struct wc_entry *e;
+ struct rb_node *node = wc->tree.rb_node;
+
+ if (unlikely(!node))
+ return NULL;
+
+ while (1) {
+ e = container_of(node, struct wc_entry, rb_node);
+ if (read_original_sector(wc, e) == block)
+ break;
+ node = (read_original_sector(wc, e) >= block ?
+ e->rb_node.rb_left : e->rb_node.rb_right);
+ if (unlikely(!node)) {
+ if (!(flags & WFE_RETURN_FOLLOWING)) {
+ return NULL;
+ }
+ if (read_original_sector(wc, e) >= block) {
+ break;
+ } else {
+ node = rb_next(&e->rb_node);
+ if (unlikely(!node)) {
+ return NULL;
+ }
+ e = container_of(node, struct wc_entry, rb_node);
+ break;
+ }
+ }
+ }
+
+ while (1) {
+ struct wc_entry *e2;
+ if (flags & WFE_LOWEST_SEQ)
+ node = rb_prev(&e->rb_node);
+ else
+ node = rb_next(&e->rb_node);
+ if (!node)
+ return e;
+ e2 = container_of(node, struct wc_entry, rb_node);
+ if (read_original_sector(wc, e2) != block)
+ return e;
+ e = e2;
+ }
+}
+
+static void writecache_insert_entry(struct dm_writecache *wc, struct wc_entry *ins)
+{
+ struct wc_entry *e;
+ struct rb_node **node = &wc->tree.rb_node, *parent = NULL;
+
+ while (*node) {
+ e = container_of(*node, struct wc_entry, rb_node);
+ parent = &e->rb_node;
+ if (read_original_sector(wc, e) > read_original_sector(wc, ins))
+ node = &parent->rb_left;
+ else
+ node = &parent->rb_right;
+ }
+ rb_link_node(&ins->rb_node, parent, node);
+ rb_insert_color(&ins->rb_node, &wc->tree);
+ list_add(&ins->lru, &wc->lru);
+}
+
+static void writecache_unlink(struct dm_writecache *wc, struct wc_entry *e)
+{
+ list_del(&e->lru);
+ rb_erase(&e->rb_node, &wc->tree);
+}
+
+static void writecache_add_to_freelist(struct dm_writecache *wc, struct wc_entry *e)
+{
+ if (WC_MODE_SORT_FREELIST(wc)) {
+ struct rb_node **node = &wc->freetree.rb_node, *parent = NULL;
+ if (unlikely(!*node))
+ wc->current_free = e;
+ while (*node) {
+ parent = *node;
+ if (&e->rb_node < *node)
+ node = &parent->rb_left;
+ else
+ node = &parent->rb_right;
+ }
+ rb_link_node(&e->rb_node, parent, node);
+ rb_insert_color(&e->rb_node, &wc->freetree);
+ } else {
+ list_add_tail(&e->lru, &wc->freelist);
+ }
+ wc->freelist_size++;
+}
+
+static struct wc_entry *writecache_pop_from_freelist(struct dm_writecache *wc)
+{
+ struct wc_entry *e;
+
+ if (WC_MODE_SORT_FREELIST(wc)) {
+ struct rb_node *next;
+ if (unlikely(!wc->current_free))
+ return NULL;
+ e = wc->current_free;
+ next = rb_next(&e->rb_node);
+ rb_erase(&e->rb_node, &wc->freetree);
+ if (unlikely(!next))
+ next = rb_first(&wc->freetree);
+ wc->current_free = next ? container_of(next, struct wc_entry, rb_node) : NULL;
+ } else {
+ if (unlikely(list_empty(&wc->freelist)))
+ return NULL;
+ e = container_of(wc->freelist.next, struct wc_entry, lru);
+ list_del(&e->lru);
+ }
+ wc->freelist_size--;
+ if (unlikely(wc->freelist_size <= wc->freelist_high_watermark))
+ queue_work(wc->writeback_wq, &wc->writeback_work);
+
+ return e;
+}
+
+static void writecache_free_entry(struct dm_writecache *wc, struct wc_entry *e)
+{
+ writecache_unlink(wc, e);
+ writecache_add_to_freelist(wc, e);
+ clear_seq_count(wc, e);
+ writecache_flush_region(wc, memory_entry(wc, e), sizeof(struct wc_memory_entry));
+ if (unlikely(swait_active(&wc->freelist_wait)))
+ swake_up(&wc->freelist_wait);
+}
+
+static void __writecache_wait_on_freelist(struct dm_writecache *wc, bool measure, int line)
+{
+ DECLARE_SWAITQUEUE(wait);
+#ifdef WC_MEASURE_LATENCY
+ ktime_t before, after;
+#endif
+
+ prepare_to_swait(&wc->freelist_wait, &wait, TASK_UNINTERRUPTIBLE);
+ wc_unlock(wc);
+#ifdef WC_MEASURE_LATENCY
+ if (measure)
+ before = ktime_get();
+#endif
+ io_schedule();
+ finish_swait(&wc->freelist_wait, &wait);
+#ifdef WC_MEASURE_LATENCY
+ if (measure) {
+ after = ktime_get();
+ if (unlikely(after - before > wc->max_freelist_wait)) {
+ wc->max_freelist_wait = after - before;
+ printk(KERN_DEBUG "dm-writecache: waiting on freelist for %lld.%03lldus at %d\n",
+ wc->max_freelist_wait / 1000, wc->max_freelist_wait % 1000, line);
+ }
+ }
+#endif
+ wc_lock(wc);
+}
+#define writecache_wait_on_freelist(wc) __writecache_wait_on_freelist(wc, true, __LINE__)
+#define writecache_wait_on_freelist_long(wc) __writecache_wait_on_freelist(wc, false, __LINE__)
+
+static void writecache_poison_lists(struct dm_writecache *wc)
+{
+ /*
+ * Catch incorrect access to these values while the device is suspended.
+ */
+ memset(&wc->tree, -1, sizeof wc->tree);
+ wc->lru.next = LIST_POISON1;
+ wc->lru.prev = LIST_POISON2;
+ wc->freelist.next = LIST_POISON1;
+ wc->freelist.prev = LIST_POISON2;
+}
+
+static void writecache_flush_entry(struct dm_writecache *wc, struct wc_entry *e)
+{
+ writecache_flush_region(wc, memory_entry(wc, e), sizeof(struct wc_memory_entry));
+ if (WC_MODE_PMEM(wc))
+ writecache_flush_region(wc, memory_data(wc, e), wc->block_size);
+}
+
+static bool writecache_entry_is_committed(struct dm_writecache *wc, struct wc_entry *e)
+{
+ return read_seq_count(wc, e) < wc->seq_count;
+}
+
+static void writecache_flush(struct dm_writecache *wc)
+{
+ struct wc_entry *e, *e2;
+ bool need_flush_after_free;
+
+ wc->uncommitted_blocks = 0;
+ del_timer(&wc->autocommit_timer);
+
+ if (list_empty(&wc->lru))
+ return;
+
+ e = container_of(wc->lru.next, struct wc_entry, lru);
+ if (writecache_entry_is_committed(wc, e)) {
+ if (wc->overwrote_committed) {
+ writecache_wait_for_ios(wc, WRITE);
+ writecache_disk_flush(wc, wc->ssd_dev);
+ wc->overwrote_committed = false;
+ }
+ return;
+ }
+ while (1) {
+ writecache_flush_entry(wc, e);
+ if (unlikely(e->lru.next == &wc->lru))
+ break;
+ e2 = container_of(e->lru.next, struct wc_entry, lru);
+ if (writecache_entry_is_committed(wc, e2))
+ break;
+ e = e2;
+ cond_resched();
+ }
+ writecache_commit_flushed(wc);
+
+ writecache_wait_for_ios(wc, WRITE);
+
+ wc->seq_count++;
+ pmem_assign(sb(wc)->seq_count, cpu_to_le64(wc->seq_count));
+ writecache_flush_region(wc, &sb(wc)->seq_count, sizeof sb(wc)->seq_count);
+ writecache_commit_flushed(wc);
+
+ wc->overwrote_committed = false;
+
+ need_flush_after_free = false;
+ while (1) {
+ /* Free another committed entry with lower seq-count */
+ struct rb_node *rb_node = rb_prev(&e->rb_node);
+
+ if (rb_node) {
+ e2 = container_of(rb_node, struct wc_entry, rb_node);
+ if (read_original_sector(wc, e2) == read_original_sector(wc, e) &&
+ likely(!e2->write_in_progress)) {
+ writecache_free_entry(wc, e2);
+ need_flush_after_free = true;
+ }
+ }
+ if (unlikely(e->lru.prev == &wc->lru))
+ break;
+ e = container_of(e->lru.prev, struct wc_entry, lru);
+ cond_resched();
+ }
+
+ if (need_flush_after_free)
+ writecache_commit_flushed(wc);
+}
+
+static void writecache_flush_work(struct work_struct *work)
+{
+ struct dm_writecache *wc = container_of(work, struct dm_writecache, flush_work);
+ wc_lock(wc);
+ writecache_flush(wc);
+ wc_unlock(wc);
+}
+
+static void writecache_autocommit_timer(struct timer_list *t)
+{
+ struct dm_writecache *wc = from_timer(wc, t, autocommit_timer);
+ if (!writecache_has_error(wc))
+ queue_work(wc->writeback_wq, &wc->flush_work);
+}
+
+static void writecache_schedule_autocommit(struct dm_writecache *wc)
+{
+ if (!timer_pending(&wc->autocommit_timer))
+ mod_timer(&wc->autocommit_timer, jiffies + wc->autocommit_jiffies);
+}
+
+static void writecache_discard(struct dm_writecache *wc, sector_t start, sector_t end)
+{
+ struct wc_entry *e;
+ bool discarded_something = false;
+
+ e = writecache_find_entry(wc, start, WFE_RETURN_FOLLOWING | WFE_LOWEST_SEQ);
+ if (unlikely(!e))
+ return;
+
+ while (read_original_sector(wc, e) < end) {
+ struct rb_node *node = rb_next(&e->rb_node);
+
+ if (likely(!e->write_in_progress)) {
+ if (!discarded_something) {
+ writecache_wait_for_ios(wc, READ);
+ writecache_wait_for_ios(wc, WRITE);
+ discarded_something = true;
+ }
+ writecache_free_entry(wc, e);
+ }
+
+ if (!node)
+ break;
+
+ e = container_of(node, struct wc_entry, rb_node);
+ }
+
+ if (discarded_something)
+ writecache_commit_flushed(wc);
+}
+
+static bool writecache_wait_for_writeback(struct dm_writecache *wc)
+{
+ if (wc->writeback_size) {
+ writecache_wait_on_freelist(wc);
+ return true;
+ }
+ return false;
+}
+
+static void writecache_suspend(struct dm_target *ti)
+{
+ struct dm_writecache *wc = ti->private;
+ bool flush_on_suspend;
+
+ del_timer_sync(&wc->autocommit_timer);
+
+ wc_lock(wc);
+ writecache_flush(wc);
+ flush_on_suspend = wc->flush_on_suspend;
+ if (flush_on_suspend) {
+ wc->flush_on_suspend = false;
+ wc->writeback_all++;
+ queue_work(wc->writeback_wq, &wc->writeback_work);
+ }
+ wc_unlock(wc);
+
+ flush_workqueue(wc->writeback_wq);
+
+ wc_lock(wc);
+ if (flush_on_suspend) {
+ wc->writeback_all--;
+ }
+ while (writecache_wait_for_writeback(wc));
+
+ if (WC_MODE_PMEM(wc))
+ persistent_memory_flush_cache(wc->memory_map, wc->memory_map_size);
+
+ writecache_poison_lists(wc);
+
+ wc_unlock_long(wc);
+}
+
+static int writecache_alloc_entries(struct dm_writecache *wc)
+{
+ size_t b;
+ if (wc->entries)
+ return 0;
+ wc->entries = vmalloc(sizeof(struct wc_entry) * wc->n_blocks);
+ if (!wc->entries)
+ return -ENOMEM;
+ for (b = 0; b < wc->n_blocks; b++) {
+ struct wc_entry *e = &wc->entries[b];
+ e->index = b;
+ e->write_in_progress = false;
+ }
+ return 0;
+}
+
+static void writecache_resume(struct dm_target *ti)
+{
+ struct dm_writecache *wc = ti->private;
+ size_t b;
+ bool need_flush = false;
+ __le64 sb_seq_count;
+ int r;
+
+ wc_lock(wc);
+
+ if (WC_MODE_PMEM(wc))
+ persistent_memory_invalidate_cache(wc->memory_map, wc->memory_map_size);
+
+ wc->tree = RB_ROOT;
+ INIT_LIST_HEAD(&wc->lru);
+ if (WC_MODE_SORT_FREELIST(wc)) {
+ wc->freetree = RB_ROOT;
+ wc->current_free = NULL;
+ } else {
+ INIT_LIST_HEAD(&wc->freelist);
+ }
+ wc->freelist_size = 0;
+
+ r = memcpy_mcsafe(&sb_seq_count, &sb(wc)->seq_count, sizeof(uint64_t));
+ if (r) {
+ writecache_error(wc, r, "hardware memory error when reading superblock: %d", r);
+ sb_seq_count = cpu_to_le64(0);
+ }
+ wc->seq_count = le64_to_cpu(sb_seq_count);
+
+#ifdef DM_WRITECACHE_HANDLE_HARDWARE_ERRORS
+ for (b = 0; b < wc->n_blocks; b++) {
+ struct wc_entry *e = &wc->entries[b];
+ struct wc_memory_entry wme;
+ if (writecache_has_error(wc)) {
+ e->original_sector = -1;
+ e->seq_count = -1;
+ continue;
+ }
+ r = memcpy_mcsafe(&wme, memory_entry(wc, e), sizeof(struct wc_memory_entry));
+ if (r) {
+ writecache_error(wc, r, "hardware memory error when reading metadata entry %lu: %d",
+ (unsigned long)b, r);
+ e->original_sector = -1;
+ e->seq_count = -1;
+ } else {
+ e->original_sector = le64_to_cpu(wme.original_sector);
+ e->seq_count = le64_to_cpu(wme.seq_count);
+ }
+ }
+#endif
+ for (b = 0; b < wc->n_blocks; b++) {
+ struct wc_entry *e = &wc->entries[b];
+ if (!writecache_entry_is_committed(wc, e)) {
+ if (read_seq_count(wc, e) != -1) {
+erase_this:
+ clear_seq_count(wc, e);
+ need_flush = true;
+ }
+ writecache_add_to_freelist(wc, e);
+ } else {
+ struct wc_entry *old;
+
+ old = writecache_find_entry(wc, read_original_sector(wc, e), 0);
+ if (!old) {
+ writecache_insert_entry(wc, e);
+ } else {
+ if (read_seq_count(wc, old) == read_seq_count(wc, e)) {
+ writecache_error(wc, -EINVAL,
+ "two identical entries, position %llu, sector %llu, sequence %llu",
+ (unsigned long long)b, (unsigned long long)read_original_sector(wc, e),
+ (unsigned long long)read_seq_count(wc, e));
+ }
+ if (read_seq_count(wc, old) > read_seq_count(wc, e)) {
+ goto erase_this;
+ } else {
+ writecache_free_entry(wc, old);
+ writecache_insert_entry(wc, e);
+ need_flush = true;
+ }
+ }
+ }
+ cond_resched();
+ }
+
+ if (need_flush) {
+ writecache_flush_all_metadata(wc);
+ writecache_commit_flushed(wc);
+ }
+
+ wc_unlock_long(wc);
+}
+
+static int process_flush_mesg(unsigned argc, char **argv, struct dm_writecache *wc)
+{
+ if (argc != 1)
+ return -EINVAL;
+
+ wc_lock(wc);
+ if (dm_suspended(wc->ti)) {
+ wc_unlock(wc);
+ return -EBUSY;
+ }
+ if (writecache_has_error(wc)) {
+ wc_unlock(wc);
+ return -EIO;
+ }
+
+ writecache_flush(wc);
+ wc->writeback_all++;
+ queue_work(wc->writeback_wq, &wc->writeback_work);
+ wc_unlock(wc);
+
+ flush_workqueue(wc->writeback_wq);
+
+ wc_lock(wc);
+ wc->writeback_all--;
+ if (writecache_has_error(wc)) {
+ wc_unlock(wc);
+ return -EIO;
+ }
+ wc_unlock(wc);
+
+ return 0;
+}
+
+static int process_flush_on_suspend_mesg(unsigned argc, char **argv, struct dm_writecache *wc)
+{
+ if (argc != 1)
+ return -EINVAL;
+
+ wc_lock(wc);
+ wc->flush_on_suspend = true;
+ wc_unlock(wc);
+
+ return 0;
+}
+
+static int writecache_message(struct dm_target *ti, unsigned argc, char **argv,
+ char *result, unsigned maxlen)
+{
+ int r = -EINVAL;
+ struct dm_writecache *wc = ti->private;
+
+ if (!strcasecmp(argv[0], "flush"))
+ r = process_flush_mesg(argc, argv, wc);
+ else if (!strcasecmp(argv[0], "flush_on_suspend"))
+ r = process_flush_on_suspend_mesg(argc, argv, wc);
+ else
+ DMWARN("unrecognised message received: %s", argv[0]);
+
+ return r;
+}
+
+static void bio_copy_block(struct dm_writecache *wc, struct bio *bio, void *data)
+{
+ void *buf;
+ unsigned long flags;
+ unsigned size;
+ int rw = bio_data_dir(bio);
+ unsigned remaining_size = wc->block_size;
+
+ do {
+ struct bio_vec bv = bio_iter_iovec(bio, bio->bi_iter);
+ buf = bvec_kmap_irq(&bv, &flags);
+ size = bv.bv_len;
+ if (unlikely(size > remaining_size))
+ size = remaining_size;
+
+ if (rw == READ) {
+ int r;
+ r = memcpy_mcsafe(buf, data, size);
+ flush_dcache_page(bio_page(bio));
+ if (unlikely(r)) {
+ writecache_error(wc, r, "hardware memory error when reading data: %d", r);
+ bio->bi_status = BLK_STS_IOERR;
+ }
+ } else {
+ flush_dcache_page(bio_page(bio));
+ memcpy_flushcache(data, buf, size);
+ }
+
+ bvec_kunmap_irq(buf, &flags);
+
+ data = (char *)data + size;
+ remaining_size -= size;
+ bio_advance(bio, size);
+ } while (unlikely(remaining_size));
+}
+
+static int writecache_flush_thread(void *data)
+{
+ struct dm_writecache *wc = data;
+
+ while (!kthread_should_stop()) {
+ struct bio *bio = wc->flush_bio;
+
+ if (likely(bio)) {
+ if (bio_op(bio) == REQ_OP_DISCARD)
+ writecache_discard(wc, bio->bi_iter.bi_sector, bio_end_sector(bio));
+ else
+ writecache_flush(wc);
+ }
+
+ set_current_state(TASK_INTERRUPTIBLE);
+ /* for debugging - catch uninitialized use */
+ wc->flush_bio = (void *)0x600 + POISON_POINTER_DELTA;
+ complete(&wc->flush_completion);
+
+ schedule();
+ }
+
+ set_current_state(TASK_RUNNING);
+
+ return 0;
+}
+
+static void writecache_offload_bio(struct dm_writecache *wc, struct bio *bio)
+{
+ wc->flush_bio = bio;
+ reinit_completion(&wc->flush_completion);
+ wake_up_process(wc->flush_thread);
+ wait_for_completion_io(&wc->flush_completion);
+}
+
+/* FIXME: all the gotos in writecache_map() suggest the need for refactoring */
+static int writecache_map(struct dm_target *ti, struct bio *bio)
+{
+ struct wc_entry *e;
+ struct dm_writecache *wc = ti->private;
+
+ bio->bi_private = NULL;
+
+ wc_lock(wc);
+
+ if (unlikely(bio->bi_opf & REQ_PREFLUSH)) {
+ if (writecache_has_error(wc))
+ goto unlock_error;
+ if (WC_MODE_PMEM(wc))
+ writecache_flush(wc);
+ else
+ writecache_offload_bio(wc, bio);
+ goto unlock_ok_flush;
+ }
+
+ bio->bi_iter.bi_sector = dm_target_offset(ti, bio->bi_iter.bi_sector);
+
+ if (unlikely((((unsigned)bio->bi_iter.bi_sector | bio_sectors(bio)) &
+ (wc->block_size / 512 - 1)) != 0)) {
+ DMWARN("I/O is not aligned, sector %llu, size %u, block size %u",
+ (unsigned long long)bio->bi_iter.bi_sector,
+ bio->bi_iter.bi_size, wc->block_size);
+ goto unlock_error;
+ }
+
+ if (unlikely(bio_op(bio) == REQ_OP_DISCARD)) {
+ if (writecache_has_error(wc))
+ goto unlock_error;
+ if (WC_MODE_PMEM(wc))
+ writecache_discard(wc, bio->bi_iter.bi_sector, bio_end_sector(bio));
+ else
+ writecache_offload_bio(wc, bio);
+ goto unlock_remap_origin;
+ }
+
+ if (bio_data_dir(bio) == READ) {
+next_block:
+ e = writecache_find_entry(wc, bio->bi_iter.bi_sector, WFE_RETURN_FOLLOWING);
+ if (e && read_original_sector(wc, e) == bio->bi_iter.bi_sector) {
+ if (WC_MODE_PMEM(wc)) {
+ bio_copy_block(wc, bio, memory_data(wc, e));
+ if (bio->bi_iter.bi_size)
+ goto next_block;
+ goto unlock_ok_read;
+ } else {
+ dm_accept_partial_bio(bio, wc->block_size >> SECTOR_SHIFT);
+ bio_set_dev(bio, wc->ssd_dev->bdev);
+ bio->bi_iter.bi_sector = cache_sector(wc, e);
+ if (!writecache_entry_is_committed(wc, e))
+ writecache_wait_for_ios(wc, WRITE);
+ goto unlock_remap;
+ }
+ } else {
+ if (e) {
+ sector_t next_boundary =
+ read_original_sector(wc, e) - bio->bi_iter.bi_sector;
+ if (next_boundary < bio->bi_iter.bi_size >> SECTOR_SHIFT) {
+ dm_accept_partial_bio(bio, next_boundary);
+ }
+ }
+ goto unlock_remap_origin;
+ }
+ } else {
+ do {
+ if (writecache_has_error(wc))
+ goto unlock_error;
+ e = writecache_find_entry(wc, bio->bi_iter.bi_sector, 0);
+ if (e) {
+ if (!writecache_entry_is_committed(wc, e))
+ goto bio_copy;
+ if (!WC_MODE_PMEM(wc) && !e->write_in_progress) {
+ wc->overwrote_committed = true;
+ goto bio_copy;
+ }
+ }
+ e = writecache_pop_from_freelist(wc);
+ if (unlikely(!e)) {
+ writecache_wait_on_freelist(wc);
+ continue;
+ }
+ write_original_sector_seq_count(wc, e, bio->bi_iter.bi_sector, wc->seq_count);
+ writecache_insert_entry(wc, e);
+ wc->uncommitted_blocks++;
+bio_copy:
+ if (WC_MODE_PMEM(wc)) {
+ bio_copy_block(wc, bio, memory_data(wc, e));
+ } else {
+ dm_accept_partial_bio(bio, wc->block_size >> SECTOR_SHIFT);
+ bio_set_dev(bio, wc->ssd_dev->bdev);
+ bio->bi_iter.bi_sector = cache_sector(wc, e);
+ if (unlikely(wc->uncommitted_blocks >= wc->autocommit_blocks)) {
+ wc->uncommitted_blocks = 0;
+ queue_work(wc->writeback_wq, &wc->flush_work);
+ } else {
+ writecache_schedule_autocommit(wc);
+ }
+ goto unlock_remap;
+ }
+ } while (bio->bi_iter.bi_size);
+
+ if (unlikely(wc->uncommitted_blocks >= wc->autocommit_blocks)) {
+ writecache_flush(wc);
+ } else {
+ writecache_schedule_autocommit(wc);
+ }
+
+ goto unlock_ok_write;
+ }
+
+unlock_remap_origin:
+ bio_set_dev(bio, wc->dev->bdev);
+ wc_unlock(wc);
+ return DM_MAPIO_REMAPPED;
+
+unlock_remap:
+ /* make sure that writecache_end_io decrements bio_in_progress: */
+ bio->bi_private = (void *)1;
+ atomic_inc(&wc->bio_in_progress[bio_data_dir(bio)]);
+ wc_unlock(wc);
+ return DM_MAPIO_REMAPPED;
+
+unlock_ok_flush:
+#ifdef WC_MEASURE_LATENCY
+ wc_unlock(wc);
+ bio_endio(bio);
+ return DM_MAPIO_SUBMITTED;
+#endif
+
+unlock_ok_read:
+#ifdef WC_MEASURE_LATENCY
+ wc_unlock(wc);
+ bio_endio(bio);
+ return DM_MAPIO_SUBMITTED;
+#endif
+
+unlock_ok_write:
+ wc_unlock(wc);
+ bio_endio(bio);
+ return DM_MAPIO_SUBMITTED;
+
+unlock_error:
+ wc_unlock(wc);
+ bio_io_error(bio);
+ return DM_MAPIO_SUBMITTED;
+}
+
+static int writecache_end_io(struct dm_target *ti, struct bio *bio, blk_status_t *status)
+{
+ struct dm_writecache *wc = ti->private;
+
+ if (bio->bi_private != NULL) {
+ int dir = bio_data_dir(bio);
+ if (atomic_dec_and_test(&wc->bio_in_progress[dir]))
+ if (unlikely(swait_active(&wc->bio_in_progress_wait[dir])))
+ swake_up(&wc->bio_in_progress_wait[dir]);
+ }
+ return 0;
+}
+
+static int writecache_iterate_devices(struct dm_target *ti,
+ iterate_devices_callout_fn fn, void *data)
+{
+ struct dm_writecache *wc = ti->private;
+
+ return fn(ti, wc->dev, 0, ti->len, data);
+}
+
+static void writecache_io_hints(struct dm_target *ti, struct queue_limits *limits)
+{
+ struct dm_writecache *wc = ti->private;
+
+ if (limits->logical_block_size < wc->block_size)
+ limits->logical_block_size = wc->block_size;
+
+ if (limits->physical_block_size < wc->block_size)
+ limits->physical_block_size = wc->block_size;
+
+ if (limits->io_min < wc->block_size)
+ limits->io_min = wc->block_size;
+}
+
+
+static void writecache_writeback_endio(struct bio *bio)
+{
+ struct writeback_struct *wb = container_of(bio, struct writeback_struct, bio);
+ struct dm_writecache *wc = wb->wc;
+ unsigned long flags;
+
+ raw_spin_lock_irqsave(&wc->endio_thread_wait.lock, flags);
+ list_add_tail(&wb->endio_entry, &wc->endio_list);
+ swake_up_locked(&wc->endio_thread_wait);
+ raw_spin_unlock_irqrestore(&wc->endio_thread_wait.lock, flags);
+}
+
+static void writecache_copy_endio(int read_err, unsigned long write_err, void *ptr)
+{
+ struct copy_struct *c = ptr;
+ struct dm_writecache *wc = c->wc;
+
+ c->error = likely(!(read_err | write_err)) ? 0 : -EIO;
+
+ raw_spin_lock_irq(&wc->endio_thread_wait.lock);
+ list_add_tail(&c->endio_entry, &wc->endio_list);
+ swake_up_locked(&wc->endio_thread_wait);
+ raw_spin_unlock_irq(&wc->endio_thread_wait.lock);
+}
+
+static void __writecache_endio_pmem(struct dm_writecache *wc, struct list_head *list)
+{
+ unsigned i;
+ struct writeback_struct *wb;
+ struct wc_entry *e;
+ unsigned long n_walked = 0;
+
+ do {
+ wb = list_entry(list->next, struct writeback_struct, endio_entry);
+ list_del(&wb->endio_entry);
+
+ if (unlikely(wb->bio.bi_status != BLK_STS_OK))
+ writecache_error(wc, blk_status_to_errno(wb->bio.bi_status),
+ "write error %d", wb->bio.bi_status);
+ i = 0;
+ do {
+ e = wb->wc_list[i];
+ BUG_ON(!e->write_in_progress);
+ e->write_in_progress = false;
+ INIT_LIST_HEAD(&e->lru);
+ if (!writecache_has_error(wc))
+ writecache_free_entry(wc, e);
+ BUG_ON(!wc->writeback_size);
+ wc->writeback_size--;
+ n_walked++;
+ if (unlikely(n_walked >= ENDIO_LATENCY)) {
+ writecache_commit_flushed(wc);
+ wc_unlock(wc);
+ wc_lock(wc);
+ n_walked = 0;
+ }
+ } while (++i < wb->wc_list_n);
+
+ if (wb->wc_list != wb->wc_list_inline)
+ kfree(wb->wc_list);
+ bio_put(&wb->bio);
+ } while (!list_empty(list));
+}
+
+static void __writecache_endio_ssd(struct dm_writecache *wc, struct list_head *list)
+{
+ struct copy_struct *c;
+ struct wc_entry *e;
+
+ do {
+ c = list_entry(list->next, struct copy_struct, endio_entry);
+ list_del(&c->endio_entry);
+
+ if (unlikely(c->error))
+ writecache_error(wc, c->error, "copy error");
+
+ e = c->e;
+ do {
+ BUG_ON(!e->write_in_progress);
+ e->write_in_progress = false;
+ INIT_LIST_HEAD(&e->lru);
+ if (!writecache_has_error(wc))
+ writecache_free_entry(wc, e);
+
+ BUG_ON(!wc->writeback_size);
+ wc->writeback_size--;
+ e++;
+ } while (--c->n_entries);
+ mempool_free(c, wc->copy_pool);
+ } while (!list_empty(list));
+}
+
+static int writecache_endio_thread(void *data)
+{
+ struct dm_writecache *wc = data;
+
+ while (1) {
+ DECLARE_SWAITQUEUE(wait);
+ struct list_head list;
+
+ raw_spin_lock_irq(&wc->endio_thread_wait.lock);
+continue_locked:
+ if (!list_empty(&wc->endio_list))
+ goto pop_from_list;
+ set_current_state(TASK_INTERRUPTIBLE);
+ __prepare_to_swait(&wc->endio_thread_wait, &wait);
+ raw_spin_unlock_irq(&wc->endio_thread_wait.lock);
+
+ if (unlikely(kthread_should_stop())) {
+ finish_swait(&wc->endio_thread_wait, &wait);
+ break;
+ }
+
+ schedule();
+
+ raw_spin_lock_irq(&wc->endio_thread_wait.lock);
+ __finish_swait(&wc->endio_thread_wait, &wait);
+ goto continue_locked;
+
+pop_from_list:
+ list = wc->endio_list;
+ list.next->prev = list.prev->next = &list;
+ INIT_LIST_HEAD(&wc->endio_list);
+ raw_spin_unlock_irq(&wc->endio_thread_wait.lock);
+
+ if (!WC_MODE_FUA(wc))
+ writecache_disk_flush(wc, wc->dev);
+
+ wc_lock(wc);
+
+ if (WC_MODE_PMEM(wc)) {
+ __writecache_endio_pmem(wc, &list);
+ } else {
+ __writecache_endio_ssd(wc, &list);
+ writecache_wait_for_ios(wc, READ);
+ }
+
+ writecache_commit_flushed(wc);
+
+ wc_unlock(wc);
+ }
+
+ return 0;
+}
+
+static bool wc_add_block(struct writeback_struct *wb, struct wc_entry *e, gfp_t gfp)
+{
+ struct dm_writecache *wc = wb->wc;
+ unsigned block_size = wc->block_size;
+ void *address = memory_data(wc, e);
+
+ persistent_memory_flush_cache(address, block_size);
+ return bio_add_page(&wb->bio, persistent_memory_page(address),
+ block_size, persistent_memory_page_offset(address)) != 0;
+}
+
+struct writeback_list {
+ struct list_head list;
+ size_t size;
+};
+
+static void __writeback_throttle(struct dm_writecache *wc, struct writeback_list *wbl)
+{
+ if (unlikely(wc->max_writeback_jobs)) {
+ if (READ_ONCE(wc->writeback_size) - wbl->size >= wc->max_writeback_jobs) {
+ wc_lock(wc);
+ while (wc->writeback_size - wbl->size >= wc->max_writeback_jobs) {
+ writecache_wait_on_freelist_long(wc);
+ }
+ wc_unlock(wc);
+ }
+ }
+ cond_resched();
+}
+
+static void __writecache_writeback_pmem(struct dm_writecache *wc, struct writeback_list *wbl)
+{
+ struct wc_entry *e, *f;
+ struct bio *bio;
+ struct writeback_struct *wb;
+ unsigned max_pages;
+
+ while (wbl->size) {
+ wbl->size--;
+ e = container_of(wbl->list.prev, struct wc_entry, lru);
+ list_del(&e->lru);
+
+ max_pages = e->wc_list_contiguous;
+
+ bio = bio_alloc_bioset(GFP_NOIO, max_pages, wc->bio_set);
+ wb = container_of(bio, struct writeback_struct, bio);
+ wb->wc = wc;
+ wb->bio.bi_end_io = writecache_writeback_endio;
+ bio_set_dev(&wb->bio, wc->dev->bdev);
+ wb->bio.bi_iter.bi_sector = read_original_sector(wc, e);
+ wb->page_offset = PAGE_SIZE;
+ if (max_pages > WB_LIST_INLINE) {
+ wb->wc_list = kmalloc(max_pages * sizeof(struct wc_entry *),
+ GFP_NOIO | __GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN);
+ if (unlikely(!wb->wc_list))
+ goto use_inline_list;
+ } else {
+use_inline_list:
+ wb->wc_list = wb->wc_list_inline;
+ max_pages = WB_LIST_INLINE;
+ }
+
+ BUG_ON(!wc_add_block(wb, e, GFP_NOIO));
+
+ wb->wc_list[0] = e;
+ wb->wc_list_n = 1;
+
+ while (wbl->size && wb->wc_list_n < max_pages) {
+ f = container_of(wbl->list.prev, struct wc_entry, lru);
+ if (read_original_sector(wc, f) !=
+ read_original_sector(wc, e) + (wc->block_size >> SECTOR_SHIFT))
+ break;
+ if (!wc_add_block(wb, f, GFP_NOWAIT | __GFP_NOWARN))
+ break;
+ wbl->size--;
+ list_del(&f->lru);
+ wb->wc_list[wb->wc_list_n++] = f;
+ e = f;
+ }
+ bio_set_op_attrs(&wb->bio, REQ_OP_WRITE, WC_MODE_FUA(wc) * REQ_FUA);
+ if (writecache_has_error(wc)) {
+ bio->bi_status = BLK_STS_IOERR;
+ bio_endio(&wb->bio);
+ } else {
+ submit_bio(&wb->bio);
+ }
+
+ __writeback_throttle(wc, wbl);
+ }
+}
+
+static void __writecache_writeback_ssd(struct dm_writecache *wc, struct writeback_list *wbl)
+{
+ struct wc_entry *e, *f;
+ struct dm_io_region from, to;
+ struct copy_struct *c;
+
+ while (wbl->size) {
+ unsigned n_sectors;
+
+ wbl->size--;
+ e = container_of(wbl->list.prev, struct wc_entry, lru);
+ list_del(&e->lru);
+
+ n_sectors = e->wc_list_contiguous << (wc->block_size_bits - SECTOR_SHIFT);
+
+ from.bdev = wc->ssd_dev->bdev;
+ from.sector = cache_sector(wc, e);
+ from.count = n_sectors;
+ to.bdev = wc->dev->bdev;
+ to.sector = read_original_sector(wc, e);
+ to.count = n_sectors;
+
+ c = mempool_alloc(wc->copy_pool, GFP_NOIO);
+ c->wc = wc;
+ c->e = e;
+ c->n_entries = e->wc_list_contiguous;
+
+ while ((n_sectors -= wc->block_size >> SECTOR_SHIFT)) {
+ wbl->size--;
+ f = container_of(wbl->list.prev, struct wc_entry, lru);
+ BUG_ON(f != e + 1);
+ list_del(&f->lru);
+ e = f;
+ }
+
+ dm_kcopyd_copy(wc->dm_kcopyd, &from, 1, &to, 0, writecache_copy_endio, c);
+
+ __writeback_throttle(wc, wbl);
+ }
+}
+
+static void writecache_writeback(struct work_struct *work)
+{
+ struct dm_writecache *wc = container_of(work, struct dm_writecache, writeback_work);
+ struct blk_plug plug;
+ struct wc_entry *e, *f, *g;
+ struct rb_node *node, *next_node;
+ struct list_head skipped;
+ struct writeback_list wbl;
+ unsigned long n_walked;
+
+ wc_lock(wc);
+restart:
+ if (writecache_has_error(wc)) {
+ wc_unlock(wc);
+ return;
+ }
+
+ if (unlikely(wc->writeback_all)) {
+ if (writecache_wait_for_writeback(wc))
+ goto restart;
+ }
+
+ if (wc->overwrote_committed) {
+ writecache_wait_for_ios(wc, WRITE);
+ }
+
+ n_walked = 0;
+ INIT_LIST_HEAD(&skipped);
+ INIT_LIST_HEAD(&wbl.list);
+ wbl.size = 0;
+ while (!list_empty(&wc->lru) &&
+ (wc->writeback_all ||
+ wc->freelist_size + wc->writeback_size <= wc->freelist_high_watermark)) {
+
+ n_walked++;
+ if (unlikely(n_walked > WRITEBACK_LATENCY) &&
+ likely(!wc->writeback_all) && likely(!dm_suspended(wc->ti))) {
+ queue_work(wc->writeback_wq, &wc->writeback_work);
+ break;
+ }
+
+ e = container_of(wc->lru.prev, struct wc_entry, lru);
+ BUG_ON(e->write_in_progress);
+ if (unlikely(!writecache_entry_is_committed(wc, e))) {
+ writecache_flush(wc);
+ }
+ node = rb_prev(&e->rb_node);
+ if (node) {
+ f = container_of(node, struct wc_entry, rb_node);
+ if (unlikely(read_original_sector(wc, f) ==
+ read_original_sector(wc, e))) {
+ BUG_ON(!f->write_in_progress);
+ list_del(&e->lru);
+ list_add(&e->lru, &skipped);
+ cond_resched();
+ continue;
+ }
+ }
+ wc->writeback_size++;
+ list_del(&e->lru);
+ list_add(&e->lru, &wbl.list);
+ wbl.size++;
+ e->write_in_progress = true;
+ e->wc_list_contiguous = 1;
+
+ f = e;
+
+ while (1) {
+ next_node = rb_next(&f->rb_node);
+ if (unlikely(!next_node))
+ break;
+ g = container_of(next_node, struct wc_entry, rb_node);
+ if (read_original_sector(wc, g) ==
+ read_original_sector(wc, f)) {
+ f = g;
+ continue;
+ }
+ if (read_original_sector(wc, g) !=
+ read_original_sector(wc, f) + (wc->block_size >> SECTOR_SHIFT))
+ break;
+ if (unlikely(g->write_in_progress))
+ break;
+ if (unlikely(!writecache_entry_is_committed(wc, g)))
+ break;
+
+ if (!WC_MODE_PMEM(wc)) {
+ if (g != f + 1)
+ break;
+ }
+
+ n_walked++;
+ //if (unlikely(n_walked > WRITEBACK_LATENCY) && likely(!wc->writeback_all))
+ // break;
+
+ wc->writeback_size++;
+ list_del(&g->lru);
+ list_add(&g->lru, &wbl.list);
+ wbl.size++;
+ g->write_in_progress = true;
+ g->wc_list_contiguous = BIO_MAX_PAGES;
+ f = g;
+ e->wc_list_contiguous++;
+ if (unlikely(e->wc_list_contiguous == BIO_MAX_PAGES))
+ break;
+ }
+ cond_resched();
+ }
+
+ if (!list_empty(&skipped)) {
+ list_splice_tail(&skipped, &wc->lru);
+ /*
+ * If we didn't do any progress, we must wait until some
+ * writeback finishes to avoid burning CPU in a loop
+ */
+ if (unlikely(!wbl.size))
+ writecache_wait_for_writeback(wc);
+ }
+
+ wc_unlock(wc);
+
+ blk_start_plug(&plug);
+
+ if (WC_MODE_PMEM(wc))
+ __writecache_writeback_pmem(wc, &wbl);
+ else
+ __writecache_writeback_ssd(wc, &wbl);
+
+ blk_finish_plug(&plug);
+
+ if (unlikely(wc->writeback_all)) {
+ wc_lock(wc);
+ while (writecache_wait_for_writeback(wc));
+ wc_unlock(wc);
+ }
+}
+
+static int calculate_memory_size(uint64_t device_size, unsigned block_size,
+ size_t *n_blocks_p, size_t *n_metadata_blocks_p)
+{
+ uint64_t n_blocks, offset;
+ struct wc_entry e;
+
+ n_blocks = device_size;
+ do_div(n_blocks, block_size + sizeof(struct wc_memory_entry));
+
+ while (1) {
+ if (!n_blocks)
+ return -ENOSPC;
+ /* Verify the following entries[n_blocks] won't overflow */
+ if (n_blocks >= (size_t)-sizeof(struct wc_memory_superblock) / sizeof(struct wc_memory_entry))
+ return -EFBIG;
+ offset = offsetof(struct wc_memory_superblock, entries[n_blocks]);
+ offset = (offset + block_size - 1) & ~(uint64_t)(block_size - 1);
+ if (offset + n_blocks * block_size <= device_size)
+ break;
+ n_blocks--;
+ }
+
+ /* check if the bit field overflows */
+ e.index = n_blocks;
+ if (e.index != n_blocks)
+ return -EFBIG;
+
+ if (n_blocks_p)
+ *n_blocks_p = n_blocks;
+ if (n_metadata_blocks_p)
+ *n_metadata_blocks_p = offset >> __ffs(block_size);
+ return 0;
+}
+
+static int init_memory(struct dm_writecache *wc)
+{
+ size_t b;
+ int r;
+
+ r = calculate_memory_size(wc->memory_map_size, wc->block_size, &wc->n_blocks, NULL);
+ if (r)
+ return r;
+
+ r = writecache_alloc_entries(wc);
+ if (r)
+ return r;
+
+ for (b = 0; b < ARRAY_SIZE(sb(wc)->padding); b++)
+ pmem_assign(sb(wc)->padding[b], cpu_to_le64(0));
+ pmem_assign(sb(wc)->version, cpu_to_le32(MEMORY_SUPERBLOCK_VERSION));
+ pmem_assign(sb(wc)->block_size, cpu_to_le32(wc->block_size));
+ pmem_assign(sb(wc)->n_blocks, cpu_to_le64(wc->n_blocks));
+ pmem_assign(sb(wc)->seq_count, cpu_to_le64(0));
+
+ for (b = 0; b < wc->n_blocks; b++)
+ write_original_sector_seq_count(wc, &wc->entries[b], -1, -1);
+
+ writecache_flush_all_metadata(wc);
+ writecache_commit_flushed(wc);
+ pmem_assign(sb(wc)->magic, cpu_to_le32(MEMORY_SUPERBLOCK_MAGIC));
+ writecache_flush_region(wc, &sb(wc)->magic, sizeof sb(wc)->magic);
+ writecache_commit_flushed(wc);
+
+ return 0;
+}
+
+static void writecache_dtr(struct dm_target *ti)
+{
+ struct dm_writecache *wc = ti->private;
+
+ if (!wc)
+ return;
+
+ if (wc->endio_thread)
+ kthread_stop(wc->endio_thread);
+
+ if (wc->flush_thread)
+ kthread_stop(wc->flush_thread);
+
+ if (wc->bio_set)
+ bioset_free(wc->bio_set);
+
+ mempool_destroy(wc->copy_pool);
+
+ if (wc->writeback_wq)
+ destroy_workqueue(wc->writeback_wq);
+
+ if (wc->dev)
+ dm_put_device(ti, wc->dev);
+
+ if (wc->ssd_dev)
+ dm_put_device(ti, wc->ssd_dev);
+
+ if (wc->entries)
+ vfree(wc->entries);
+
+ if (wc->memory_map) {
+ if (WC_MODE_PMEM(wc))
+ persistent_memory_release(wc);
+ else
+ vfree(wc->memory_map);
+ }
+
+ if (wc->dm_kcopyd)
+ dm_kcopyd_client_destroy(wc->dm_kcopyd);
+
+ if (wc->dm_io)
+ dm_io_client_destroy(wc->dm_io);
+
+ if (wc->dirty_bitmap)
+ vfree(wc->dirty_bitmap);
+
+ kfree(wc);
+}
+
+static int writecache_ctr(struct dm_target *ti, unsigned argc, char **argv)
+{
+ struct dm_writecache *wc;
+ struct dm_arg_set as;
+ const char *string;
+ unsigned opt_params;
+ size_t offset, data_size;
+ int i, r;
+ char dummy;
+ int high_wm_percent = HIGH_WATERMARK;
+ int low_wm_percent = LOW_WATERMARK;
+ uint64_t x;
+ struct wc_memory_superblock s;
+
+ static struct dm_arg _args[] = {
+ {0, 10, "Invalid number of feature args"},
+ };
+
+ as.argc = argc;
+ as.argv = argv;
+
+ wc = kzalloc(sizeof(struct dm_writecache), GFP_KERNEL);
+ if (!wc) {
+ ti->error = "Cannot allocate writecache structure";
+ r = -ENOMEM;
+ goto bad;
+ }
+ ti->private = wc;
+ wc->ti = ti;
+
+ mutex_init(&wc->lock);
+ writecache_poison_lists(wc);
+ init_swait_queue_head(&wc->freelist_wait);
+ timer_setup(&wc->autocommit_timer, writecache_autocommit_timer, 0);
+
+ for (i = 0; i < 2; i++) {
+ atomic_set(&wc->bio_in_progress[i], 0);
+ init_swait_queue_head(&wc->bio_in_progress_wait[i]);
+ }
+
+ wc->dm_io = dm_io_client_create();
+ if (IS_ERR(wc->dm_io)) {
+ r = ERR_PTR(wc->dm_io);
+ ti->error = "Unable to allocate dm-io client";
+ goto bad;
+ }
+
+ wc->writeback_wq = alloc_workqueue("writecache-writeabck", WQ_MEM_RECLAIM, 1);
+ if (!wc->writeback_wq) {
+ r = -ENOMEM;
+ ti->error = "Could not allocate writeback workqueue";
+ goto bad;
+ }
+ INIT_WORK(&wc->writeback_work, writecache_writeback);
+ INIT_WORK(&wc->flush_work, writecache_flush_work);
+
+ init_swait_queue_head(&wc->endio_thread_wait);
+ INIT_LIST_HEAD(&wc->endio_list);
+ wc->endio_thread = kthread_create(writecache_endio_thread, wc, "writecache_endio");
+ if (IS_ERR(wc->endio_thread)) {
+ r = PTR_ERR(wc->endio_thread);
+ wc->endio_thread = NULL;
+ ti->error = "Couldn't spawn endio thread";
+ goto bad;
+ }
+ wake_up_process(wc->endio_thread);
+
+ /*
+ * Parse the mode (pmem or ssd)
+ */
+ string = dm_shift_arg(&as);
+ if (!string)
+ goto bad_arguments;
+
+ if (!strcasecmp(string, "s")) {
+#ifndef DM_WRITECACHE_ONLY_SSD
+ wc->pmem_mode = false;
+#endif
+ } else if (!strcasecmp(string, "p")) {
+#ifndef DM_WRITECACHE_ONLY_SSD
+ wc->pmem_mode = true;
+ wc->writeback_fua = true;
+#else
+ r = -EOPNOTSUPP;
+ ti->error = "Persistent memory not supported on this architecture";
+ goto bad;
+#endif
+ } else {
+ goto bad_arguments;
+ }
+
+ if (WC_MODE_PMEM(wc)) {
+ wc->bio_set = bioset_create(BIO_POOL_SIZE,
+ offsetof(struct writeback_struct, bio),
+ BIOSET_NEED_BVECS);
+ if (!wc->bio_set) {
+ r = -ENOMEM;
+ ti->error = "Could not allocate bio set";
+ goto bad;
+ }
+ } else {
+ wc->copy_pool = mempool_create_kmalloc_pool(1, sizeof(struct copy_struct));
+ if (!wc->copy_pool) {
+ r = -ENOMEM;
+ ti->error = "Could not allocate mempool";
+ goto bad;
+ }
+ }
+
+ /*
+ * Parse the origin data device
+ */
+ string = dm_shift_arg(&as);
+ if (!string)
+ goto bad_arguments;
+ r = dm_get_device(ti, string, dm_table_get_mode(ti->table), &wc->dev);
+ if (r) {
+ ti->error = "Origin data device lookup failed";
+ goto bad;
+ }
+
+ /*
+ * Parse cache data device (be it pmem or ssd)
+ */
+ string = dm_shift_arg(&as);
+ if (!string)
+ goto bad_arguments;
+
+ r = dm_get_device(ti, string, dm_table_get_mode(ti->table), &wc->ssd_dev);
+ if (r) {
+ ti->error = "Cache data device lookup failed";
+ goto bad;
+ }
+ wc->memory_map_size = i_size_read(wc->ssd_dev->bdev->bd_inode);
+
+#ifndef DM_WRITECACHE_ONLY_SSD
+ if (WC_MODE_PMEM(wc)) {
+ r = persistent_memory_claim(wc);
+ if (r) {
+ ti->error = "Unable to map persistent memory for cache";
+ goto bad;
+ }
+ }
+#endif
+
+ /*
+ * Parse the cache block size
+ */
+ string = dm_shift_arg(&as);
+ if (!string)
+ goto bad_arguments;
+ if (sscanf(string, "%u%c", &wc->block_size, &dummy) != 1 ||
+ wc->block_size < 512 || wc->block_size > PAGE_SIZE ||
+ (wc->block_size & (wc->block_size - 1))) {
+ r = -EINVAL;
+ ti->error = "Invalid block size";
+ goto bad;
+ }
+ wc->block_size_bits = __ffs(wc->block_size);
+
+ wc->max_writeback_jobs = MAX_WRITEBACK_JOBS;
+ wc->autocommit_blocks = !WC_MODE_PMEM(wc) ? AUTOCOMMIT_BLOCKS_SSD : AUTOCOMMIT_BLOCKS_PMEM;
+ wc->autocommit_jiffies = msecs_to_jiffies(AUTOCOMMIT_MSEC);
+
+ /*
+ * Parse optional arguments
+ */
+ r = dm_read_arg_group(_args, &as, &opt_params, &ti->error);
+ if (r)
+ goto bad;
+
+ while (opt_params) {
+ string = dm_shift_arg(&as), opt_params--;
+ if (!strcasecmp(string, "high_watermark") && opt_params >= 1) {
+ string = dm_shift_arg(&as), opt_params--;
+ if (sscanf(string, "%d%c", &high_wm_percent, &dummy) != 1)
+ goto invalid_optional;
+ if (high_wm_percent < 0 || high_wm_percent > 100)
+ goto invalid_optional;
+ wc->high_wm_percent_set = true;
+ } else if (!strcasecmp(string, "low_watermark") && opt_params >= 1) {
+ string = dm_shift_arg(&as), opt_params--;
+ if (sscanf(string, "%d%c", &low_wm_percent, &dummy) != 1)
+ goto invalid_optional;
+ if (low_wm_percent < 0 || low_wm_percent > 100)
+ goto invalid_optional;
+ wc->low_wm_percent_set = true;
+ } else if (!strcasecmp(string, "writeback_jobs") && opt_params >= 1) {
+ string = dm_shift_arg(&as), opt_params--;
+ if (sscanf(string, "%u%c", &wc->max_writeback_jobs, &dummy) != 1)
+ goto invalid_optional;
+ wc->max_writeback_jobs_set = true;
+ } else if (!strcasecmp(string, "autocommit_blocks") && opt_params >= 1) {
+ string = dm_shift_arg(&as), opt_params--;
+ if (sscanf(string, "%u%c", &wc->autocommit_blocks, &dummy) != 1)
+ goto invalid_optional;
+ wc->autocommit_blocks_set = true;
+ } else if (!strcasecmp(string, "autocommit_time") && opt_params >= 1) {
+ unsigned autocommit_msecs;
+ string = dm_shift_arg(&as), opt_params--;
+ if (sscanf(string, "%u%c", &autocommit_msecs, &dummy) != 1)
+ goto invalid_optional;
+ if (autocommit_msecs > 3600000)
+ goto invalid_optional;
+ wc->autocommit_jiffies = jiffies_to_msecs(autocommit_msecs);
+ wc->autocommit_time_set = true;
+ } else if (!strcasecmp(string, "fua")) {
+ if (WC_MODE_PMEM(wc)) {
+#ifndef DM_WRITECACHE_ONLY_SSD
+ wc->writeback_fua = true;
+ wc->writeback_fua_set = true;
+#endif
+ } else goto invalid_optional;
+ } else if (!strcasecmp(string, "nofua")) {
+ if (WC_MODE_PMEM(wc)) {
+#ifndef DM_WRITECACHE_ONLY_SSD
+ wc->writeback_fua = false;
+ wc->writeback_fua_set = true;
+#endif
+ } else goto invalid_optional;
+ } else {
+invalid_optional:
+ r = -EINVAL;
+ ti->error = "Invalid optional argument";
+ goto bad;
+ }
+ }
+
+ if (!WC_MODE_PMEM(wc)) {
+ struct dm_io_region region;
+ struct dm_io_request req;
+ size_t n_blocks, n_metadata_blocks;
+ uint64_t n_bitmap_bits;
+
+ init_completion(&wc->flush_completion);
+ wc->flush_thread = kthread_create(writecache_flush_thread, wc, "dm_writecache_flush");
+ if (IS_ERR(wc->flush_thread)) {
+ r = PTR_ERR(wc->flush_thread);
+ wc->flush_thread = NULL;
+ ti->error = "Couldn't spawn endio thread";
+ goto bad;
+ }
+ writecache_offload_bio(wc, NULL);
+
+ r = calculate_memory_size(wc->memory_map_size, wc->block_size,
+ &n_blocks, &n_metadata_blocks);
+ if (r) {
+ ti->error = "Invalid device size";
+ goto bad;
+ }
+
+ n_bitmap_bits = (((uint64_t)n_metadata_blocks << wc->block_size_bits) +
+ BITMAP_GRANULARITY - 1) / BITMAP_GRANULARITY;
+ /* this is limitation of test_bit functions */
+ if (n_bitmap_bits > 1U << 31) {
+ r = -EFBIG;
+ ti->error = "Invalid device size";
+ }
+
+ wc->memory_map = vmalloc(n_metadata_blocks << wc->block_size_bits);
+ if (!wc->memory_map) {
+ r = -ENOMEM;
+ ti->error = "Unable to allocate memory for metadata";
+ goto bad;
+ }
+
+ wc->dm_kcopyd = dm_kcopyd_client_create(&dm_kcopyd_throttle);
+ if (!wc->dm_kcopyd) {
+ r = -ENOMEM;
+ ti->error = "Unable to allocate dm-kcopyd client";
+ goto bad;
+ }
+
+ wc->metadata_sectors = n_metadata_blocks << (wc->block_size_bits - SECTOR_SHIFT);
+ wc->dirty_bitmap_size = (n_bitmap_bits + BITS_PER_LONG - 1) /
+ BITS_PER_LONG * sizeof(unsigned long);
+ wc->dirty_bitmap = vzalloc(wc->dirty_bitmap_size);
+ if (!wc->dirty_bitmap) {
+ r = -ENOMEM;
+ ti->error = "Unable to allocate dirty bitmap";
+ goto bad;
+ }
+
+ region.bdev = wc->ssd_dev->bdev;
+ region.sector = 0;
+ region.count = wc->metadata_sectors;
+ req.bi_op = REQ_OP_READ;
+ req.bi_op_flags = REQ_SYNC;
+ req.mem.type = DM_IO_VMA;
+ req.mem.ptr.vma = (char *)wc->memory_map;
+ req.client = wc->dm_io;
+ req.notify.fn = NULL;
+
+ r = dm_io(&req, 1, ®ion, NULL);
+ if (r) {
+ ti->error = "Unable to read metadata";
+ goto bad;
+ }
+ }
+
+ r = memcpy_mcsafe(&s, sb(wc), sizeof(struct wc_memory_superblock));
+ if (r) {
+ ti->error = "Hardware memory error when reading superblock";
+ goto bad;
+ }
+ if (!le32_to_cpu(s.magic) && !le32_to_cpu(s.version)) {
+ r = init_memory(wc);
+ if (r) {
+ ti->error = "Unable to initialize device";
+ goto bad;
+ }
+ r = memcpy_mcsafe(&s, sb(wc), sizeof(struct wc_memory_superblock));
+ if (r) {
+ ti->error = "Hardware memory error when reading superblock";
+ goto bad;
+ }
+ }
+
+ if (le32_to_cpu(s.magic) != MEMORY_SUPERBLOCK_MAGIC) {
+ ti->error = "Invalid magic in the superblock";
+ r = -EINVAL;
+ goto bad;
+ }
+
+ if (le32_to_cpu(s.version) != MEMORY_SUPERBLOCK_VERSION) {
+ ti->error = "Invalid version in the superblock";
+ r = -EINVAL;
+ goto bad;
+ }
+
+ if (le32_to_cpu(s.block_size) != wc->block_size) {
+ ti->error = "Block size does not match superblock";
+ r = -EINVAL;
+ goto bad;
+ }
+
+ wc->n_blocks = le64_to_cpu(s.n_blocks);
+
+ offset = wc->n_blocks * sizeof(struct wc_memory_entry);
+ if (offset / sizeof(struct wc_memory_entry) != le64_to_cpu(sb(wc)->n_blocks)) {
+overflow:
+ ti->error = "Overflow in size calculation";
+ r = -EINVAL;
+ goto bad;
+ }
+ offset += sizeof(struct wc_memory_superblock);
+ if (offset < sizeof(struct wc_memory_superblock))
+ goto overflow;
+ offset = (offset + wc->block_size - 1) & ~(size_t)(wc->block_size - 1);
+ data_size = wc->n_blocks * (size_t)wc->block_size;
+ if (!offset || (data_size / wc->block_size != wc->n_blocks) ||
+ (offset + data_size < offset))
+ goto overflow;
+ if (offset + data_size > wc->memory_map_size) {
+ ti->error = "Memory area is too small";
+ r = -EINVAL;
+ goto bad;
+ }
+
+ wc->metadata_sectors = offset >> SECTOR_SHIFT;
+ wc->block_start = (char *)sb(wc) + offset;
+
+ x = (uint64_t)wc->n_blocks * (100 - high_wm_percent);
+ x += 50;
+ do_div(x, 100);
+ wc->freelist_high_watermark = x;
+ x = (uint64_t)wc->n_blocks * (100 - low_wm_percent);
+ x += 50;
+ do_div(x, 100);
+ wc->freelist_low_watermark = x;
+
+ r = writecache_alloc_entries(wc);
+ if (r) {
+ ti->error = "Cannot allocate memory";
+ goto bad;
+ }
+
+ ti->num_flush_bios = 1;
+ ti->flush_supported = true;
+ ti->num_discard_bios = 1;
+
+ if (WC_MODE_PMEM(wc))
+ persistent_memory_flush_cache(wc->memory_map, wc->memory_map_size);
+
+ return 0;
+
+bad_arguments:
+ r = -EINVAL;
+ ti->error = "Bad arguments";
+bad:
+ writecache_dtr(ti);
+ return r;
+}
+
+static void writecache_status(struct dm_target *ti, status_type_t type,
+ unsigned status_flags, char *result, unsigned maxlen)
+{
+ struct dm_writecache *wc = ti->private;
+ unsigned extra_args;
+ unsigned sz = 0;
+ uint64_t x;
+
+ switch (type) {
+ case STATUSTYPE_INFO:
+ DMEMIT("%ld %llu %llu %llu", writecache_has_error(wc),
+ (unsigned long long)wc->n_blocks, (unsigned long long)wc->freelist_size,
+ (unsigned long long)wc->writeback_size);
+ break;
+ case STATUSTYPE_TABLE:
+ DMEMIT("%c %s %s %u ", WC_MODE_PMEM(wc) ? 'p' : 's',
+ wc->dev->name, wc->ssd_dev->name, wc->block_size);
+ extra_args = 0;
+ if (wc->high_wm_percent_set)
+ extra_args += 2;
+ if (wc->low_wm_percent_set)
+ extra_args += 2;
+ if (wc->max_writeback_jobs_set)
+ extra_args += 2;
+ if (wc->autocommit_blocks_set)
+ extra_args += 2;
+ if (wc->autocommit_time_set)
+ extra_args += 2;
+#ifndef DM_WRITECACHE_ONLY_SSD
+ if (wc->writeback_fua_set)
+ extra_args++;
+#endif
+ DMEMIT("%u", extra_args);
+ if (wc->high_wm_percent_set) {
+ x = (uint64_t)wc->freelist_high_watermark * 100;
+ x += wc->n_blocks / 2;
+ do_div(x, (size_t)wc->n_blocks);
+ DMEMIT(" high_watermark %u", 100 - (unsigned)x);
+ }
+ if (wc->low_wm_percent_set) {
+ x = (uint64_t)wc->freelist_low_watermark * 100;
+ x += wc->n_blocks / 2;
+ do_div(x, (size_t)wc->n_blocks);
+ DMEMIT(" low_watermark %u", 100 - (unsigned)x);
+ }
+ if (wc->max_writeback_jobs_set) {
+ DMEMIT(" writeback_jobs %u", wc->max_writeback_jobs);
+ }
+ if (wc->autocommit_blocks_set) {
+ DMEMIT(" autocommit_blocks %u", wc->autocommit_blocks);
+ }
+ if (wc->autocommit_time_set) {
+ DMEMIT(" autocommit_time %u", jiffies_to_msecs(wc->autocommit_jiffies));
+ }
+#ifndef DM_WRITECACHE_ONLY_SSD
+ if (wc->writeback_fua_set) {
+ DMEMIT(" %sfua", wc->writeback_fua ? "" : "no");
+ }
+#endif
+ break;
+ }
+}
+
+static struct target_type writecache_target = {
+ .name = "writecache",
+ .version = {1, 0, 0},
+ .module = THIS_MODULE,
+ .ctr = writecache_ctr,
+ .dtr = writecache_dtr,
+ .status = writecache_status,
+ .postsuspend = writecache_suspend,
+ .resume = writecache_resume,
+ .message = writecache_message,
+ .map = writecache_map,
+ .end_io = writecache_end_io,
+ .iterate_devices = writecache_iterate_devices,
+ .io_hints = writecache_io_hints,
+};
+
+static int __init dm_writecache_init(void)
+{
+ int r;
+
+ r = dm_register_target(&writecache_target);
+ if (r < 0) {
+ DMERR("register failed %d", r);
+ return r;
+ }
+
+ return 0;
+}
+
+static void __exit dm_writecache_exit(void)
+{
+ dm_unregister_target(&writecache_target);
+}
+
+module_init(dm_writecache_init);
+module_exit(dm_writecache_exit);
+
+MODULE_DESCRIPTION(DM_NAME " writecache target");
+MODULE_AUTHOR("Mikulas Patocka <dm-devel@redhat.com>");
+MODULE_LICENSE("GPL");
===================================================================
@@ -0,0 +1,68 @@
+The writecache target caches writes on persistent memory or on SSD. It
+doesn't cache reads because reads are supposed to be cached in page cache
+in normal RAM.
+
+When the device is constructed, the first sector should be zeroed or the
+first sector should contain valid superblock from previous invocation.
+
+Constructor parameters:
+1. type of the cache device - "p" or "s"
+ p - persistent memory
+ s - SSD
+2. the underlying device that will be cached
+3. the cache device
+4. block size (4096 is recommended; the maximum block size is the page
+ size)
+5. the number of optional parameters (the parameters with an argument
+ count as two)
+ high_watermark n (default: 50)
+ start writeback when the number of used blocks reach this
+ watermark
+ low_watermark x (default: 45)
+ stop writeback when the number of used blocks drops below
+ this watermark
+ writeback_jobs n (default: unlimited)
+ limit the number of blocks that are in flight during
+ writeback. Setting this value reduces writeback
+ throughput, but it may improve latency of read requests
+ autocommit_blocks n (default: 64 for pmem, 65536 for ssd)
+ when the application writes this amount of blocks without
+ issuing the FLUSH request, the blocks are automatically
+ commited
+ autocommit_time ms (default: 1000)
+ autocommit time in milliseconds. The data is automatically
+ commited if this time passes and no FLUSH request is
+ received
+ fua (by default on)
+ applicable only to persistent memory - use the FUA flag
+ when writing data from persistent memory back to the
+ underlying device
+ nofua
+ applicable only to persistent memory - don't use the FUA
+ flag when writing back data and send the FLUSH request
+ afterwards
+ - some underlying devices perform better with fua, some
+ with nofua. The user should test it
+
+Status:
+1. error indicator - 0 if there was no error, otherwise error number
+2. the number of blocks
+3. the number of free blocks
+4. the number of blocks under writeback
+
+Messages:
+ flush
+ flush the cache device. The message returns successfully
+ if the cache device was flushed without an error
+ flush_on_suspend
+ flush the cache device on next suspend. Use this message
+ when you are going to remove the cache device. The proper
+ sequence for removing the cache device is:
+ 1. send the "flush_on_suspend" message
+ 2. load an inactive table with a linear target that maps
+ to the underlying device
+ 3. suspend the device
+ 4. ask for status and verify that there are no errors
+ 5. resume the device, so that it will use the linear
+ target
+ 6. the cache device is now inactive and it can be deleted
The dm-writecache target. Signed-off-by: Mikulas Patocka <mpatocka@redhat.com> --- Documentation/device-mapper/writecache.txt | 68 drivers/md/Kconfig | 11 drivers/md/Makefile | 1 drivers/md/dm-writecache.c | 2382 +++++++++++++++++++++++++++++ 4 files changed, 2462 insertions(+) -- dm-devel mailing list dm-devel@redhat.com https://www.redhat.com/mailman/listinfo/dm-devel