Something went wrong. Try again.
(I'm so sorry!) Linux kernel mirror (for testing) git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
kernel os linux
Something went wrong. Try again.
1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950515253545556575859606162636465666768697071727374757677787980818283848586878889909192939495969798991001011021031041051061071081091101111121131141151161171181191201211221231241251261271281291301311321331341351361371381391401411421431441451461471481491501511521531541551561571581591601611621631641651661671681691701711721731741751761771781791801811821831841851861871881891901911921931941951961971981992002012022032042052062072082092102112122132142152162172182192202212222232242252262272282292302312322332342352362372382392402412422432442452462472482492502512522532542552562572582592602612622632642652662672682692702712722732742752762772782792802812822832842852862872882892902912922932942952962972982993003013023033043053063073083093103113123133143153163173183193203213223233243253263273283293303313323333343353363373383393403413423433443453463473483493503513523533543553563573583593603613623633643653663673683693703713723733743753763773783793803813823833843853863873883893903913923933943953963973983994004014024034044054064074084094104114124134144154164174184194204214224234244254264274284294304314324334344354364374384394404414424434444454464474484494504514524534544554564574584594604614624634644654664674684694704714724734744754764774784794804814824834844854864874884894904914924934944954964974984995005015025035045055065075085095105115125135145155165175185195205215225235245255265275285295305315325335345355365375385395405415425435445455465475485495505515525535545555565575585595605615625635645655665675685695705715725735745755765775785795805815825835845855865875885895905915925935945955965975985996006016026036046056066076086096106116126136146156166176186196206216226236246256266276286296306316326336346356366376386396406416426436446456466476486496506516526536546556566576586596606616626636646656666676686696706716726736746756766776786796806816826836846856866876886896906916926936946956966976986997007017027037047057067077087097107117127137147157167177187197207217227237247257267277287297307317327337347357367377387397407417427437447457467477487497507517527537547557567577587597607617627637647657667677687697707717727737747757767777787797807817827837847857867877887897907917927937947957967977987998008018028038048058068078088098108118128138148158168178188198208218228238248258268278288298308318328338348358368378388398408418428438448458468478488498508518528538548558568578588598608618628638648658668678688698708718728738748758768778788798808818828838848858868878888898908918928938948958968978988999009019029039049059069079089099109119129139149159169179189199209219229239249259269279289299309319329339349359369379389399409419429439449459469479489499509519529539549559569579589599609619629639649659669679689699709719729739749759769779789799809819829839849859869879889899909919929939949959969979989991000100110021003100410051006100710081009101010111012101310141015101610171018101910201021102210231024102510261027102810291030103110321033103410351036103710381039104010411042104310441045104610471048104910501051105210531054105510561057105810591060106110621063106410651066106710681069107010711072107310741075107610771078107910801081108210831084108510861087108810891090109110921093109410951096109710981099110011011102110311041105110611071108110911101111111211131114111511161117111811191120112111221123112411251126112711281129113011311132113311341135113611371138113911401141114211431144114511461147114811491150115111521153115411551156115711581159116011611162116311641165116611671168116911701171117211731174117511761177117811791180118111821183118411851186118711881189119011911192119311941195119611971198119912001201120212031204120512061207120812091210121112121213121412151216121712181219122012211222122312241225122612271228122912301231123212331234123512361237123812391240124112421243124412451246124712481249125012511252125312541255125612571258125912601261126212631264126512661267126812691270127112721273127412751276127712781279128012811282128312841285128612871288128912901291129212931294129512961297129812991300130113021303130413051306130713081309131013111312131313141315131613171318131913201321132213231324132513261327132813291330133113321333133413351336133713381339134013411342134313441345134613471348134913501351135213531354135513561357135813591360136113621363136413651366136713681369137013711372137313741375137613771378137913801381138213831384138513861387138813891390139113921393139413951396139713981399140014011402140314041405140614071408140914101411141214131414141514161417141814191420142114221423142414251426142714281429143014311432143314341435143614371438143914401441144214431444144514461447144814491450145114521453145414551456145714581459146014611462146314641465146614671468146914701471147214731474147514761477147814791480148114821483148414851486148714881489149014911492149314941495149614971498149915001501150215031504150515061507150815091510151115121513151415151516151715181519152015211522152315241525152615271528152915301531153215331534153515361537153815391540154115421543154415451546154715481549155015511552155315541555155615571558155915601561156215631564156515661567156815691570157115721573157415751576157715781579158015811582158315841585158615871588158915901591159215931594159515961597159815991600160116021603160416051606160716081609161016111612161316141615161616171618161916201621162216231624162516261627162816291630163116321633163416351636163716381639164016411642164316441645164616471648164916501651165216531654165516561657165816591660166116621663166416651666166716681669167016711672167316741675167616771678167916801681168216831684168516861687168816891690169116921693169416951696169716981699170017011702170317041705170617071708170917101711171217131714171517161717171817191720172117221723172417251726172717281729173017311732173317341735173617371738173917401741174217431744174517461747174817491750175117521753175417551756175717581759176017611762176317641765176617671768176917701771177217731774177517761777177817791780178117821783178417851786178717881789179017911792179317941795179617971798179918001801180218031804180518061807180818091810181118121813181418151816181718181819182018211822182318241825182618271828182918301831183218331834183518361837183818391840184118421843184418451846184718481849185018511852185318541855185618571858185918601861186218631864186518661867186818691870187118721873187418751876187718781879188018811882188318841885188618871888188918901891189218931894189518961897189818991900190119021903190419051906190719081909191019111912191319141915191619171918191919201921192219231924192519261927192819291930193119321933193419351936193719381939194019411942194319441945194619471948194919501951195219531954195519561957195819591960196119621963196419651966196719681969197019711972197319741975197619771978197919801981198219831984198519861987198819891990199119921993199419951996199719981999200020012002200320042005200620072008200920102011201220132014201520162017201820192020202120222023202420252026202720282029203020312032203320342035203620372038203920402041204220432044204520462047204820492050205120522053205420552056205720582059206020612062206320642065206620672068206920702071207220732074207520762077207820792080208120822083208420852086208720882089209020912092209320942095209620972098209921002101210221032104210521062107210821092110211121122113211421152116211721182119212021212122212321242125212621272128212921302131213221332134213521362137213821392140214121422143214421452146214721482149215021512152215321542155215621572158215921602161216221632164216521662167216821692170217121722173217421752176217721782179218021812182218321842185218621872188218921902191219221932194219521962197219821992200220122022203220422052206220722082209221022112212221322142215221622172218221922202221222222232224222522262227222822292230223122322233223422352236223722382239224022412242224322442245224622472248224922502251225222532254225522562257225822592260226122622263226422652266226722682269227022712272227322742275227622772278227922802281228222832284228522862287228822892290229122922293229422952296229722982299230023012302230323042305230623072308230923102311231223132314231523162317231823192320232123222323232423252326232723282329233023312332233323342335233623372338233923402341234223432344234523462347234823492350235123522353235423552356235723582359236023612362236323642365236623672368236923702371237223732374237523762377237823792380238123822383238423852386238723882389239023912392239323942395239623972398239924002401240224032404240524062407240824092410241124122413241424152416241724182419242024212422242324242425242624272428242924302431243224332434243524362437243824392440244124422443244424452446244724482449245024512452245324542455245624572458245924602461246224632464246524662467246824692470247124722473247424752476247724782479248024812482248324842485248624872488248924902491249224932494249524962497249824992500250125022503250425052506250725082509251025112512251325142515251625172518251925202521252225232524252525262527252825292530253125322533253425352536253725382539254025412542254325442545254625472548254925502551255225532554255525562557255825592560256125622563256425652566256725682569257025712572257325742575257625772578257925802581258225832584258525862587258825892590259125922593259425952596259725982599260026012602260326042605260626072608260926102611261226132614261526162617261826192620262126222623262426252626262726282629263026312632263326342635263626372638263926402641264226432644264526462647264826492650265126522653265426552656265726582659266026612662266326642665266626672668266926702671267226732674267526762677267826792680268126822683268426852686268726882689269026912692269326942695269626972698269927002701270227032704270527062707270827092710271127122713271427152716271727182719272027212722272327242725272627272728272927302731273227332734273527362737273827392740274127422743274427452746274727482749275027512752275327542755275627572758275927602761276227632764276527662767276827692770277127722773277427752776277727782779278027812782278327842785278627872788278927902791279227932794279527962797279827992800280128022803// SPDX-License-Identifier: GPL-2.0-only/* * 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/dm-io.h>#include <linux/dm-kcopyd.h>#include <linux/dax.h>#include <linux/libnvdimm.h>#include <linux/delay.h>#include "dm-io-tracker.h"
#define DM_MSG_PREFIX "writecache"
#define HIGH_WATERMARK 50#define LOW_WATERMARK 45#define MAX_WRITEBACK_JOBS min(0x10000000 / PAGE_SIZE, totalram_pages() / 16)#define ENDIO_LATENCY 16#define WRITEBACK_LATENCY 64#define AUTOCOMMIT_BLOCKS_SSD 65536#define AUTOCOMMIT_BLOCKS_PMEM 64#define AUTOCOMMIT_MSEC 1000#define MAX_AGE_DIV 16#define MAX_AGE_UNSPECIFIED -1UL#define PAUSE_WRITEBACK (HZ * 3)
#define BITMAP_GRANULARITY 65536#if BITMAP_GRANULARITY < PAGE_SIZE#undef BITMAP_GRANULARITY#define BITMAP_GRANULARITY PAGE_SIZE#endif
#if IS_ENABLED(CONFIG_ARCH_HAS_PMEM_API) && IS_ENABLED(CONFIG_FS_DAX)#define DM_WRITECACHE_HAS_PMEM#endif
#ifdef DM_WRITECACHE_HAS_PMEM#define pmem_assign(dest, src) \do { \ typeof(dest) uniq = (src); \ memcpy_flushcache(&(dest), &uniq, sizeof(dest)); \} while (0)#else#define pmem_assign(dest, src) ((dest) = (src))#endif
#if IS_ENABLED(CONFIG_ARCH_HAS_COPY_MC) && defined(DM_WRITECACHE_HAS_PMEM)#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[];};
struct wc_entry { struct rb_node rb_node; struct list_head lru; u32 age; // jiffies unsigned short wc_list_contiguous; bool write_in_progress;#ifdef DM_WRITECACHE_HANDLE_HARDWARE_ERRORS uint64_t original_sector; uint64_t seq_count;#endif};
#ifdef DM_WRITECACHE_HAS_PMEM#define WC_MODE_PMEM(wc) ((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 { struct mutex lock; struct list_head lru; union { struct list_head freelist; struct { struct rb_root freetree; struct wc_entry *current_free; }; }; struct rb_root tree;
size_t freelist_size; size_t writeback_size; size_t freelist_high_watermark; size_t freelist_low_watermark; unsigned long max_age; unsigned long pause;
unsigned int uncommitted_blocks; unsigned int autocommit_blocks; unsigned int max_writeback_jobs;
int error;
unsigned long autocommit_jiffies; struct timer_list autocommit_timer; struct wait_queue_head freelist_wait;
struct timer_list max_age_timer;
atomic_t bio_in_progress[2]; struct wait_queue_head bio_in_progress_wait[2];
struct dm_target *ti; struct dm_dev *dev; struct dm_dev *ssd_dev; sector_t start_sector; void *memory_map; uint64_t memory_map_size; size_t metadata_sectors; size_t n_blocks; uint64_t seq_count; sector_t data_device_sectors; void *block_start; struct wc_entry *entries; unsigned int block_size; unsigned char block_size_bits;
bool pmem_mode:1; bool writeback_fua:1;
bool overwrote_committed:1; bool memory_vmapped:1;
bool start_sector_set:1; bool high_wm_percent_set:1; bool low_wm_percent_set:1; bool max_writeback_jobs_set:1; bool autocommit_blocks_set:1; bool autocommit_time_set:1; bool max_age_set:1; bool writeback_fua_set:1; bool flush_on_suspend:1; bool cleaner:1; bool cleaner_set:1; bool metadata_only:1; bool pause_set:1;
unsigned int high_wm_percent_value; unsigned int low_wm_percent_value; unsigned int autocommit_time_value; unsigned int max_age_value; unsigned int pause_value;
unsigned int writeback_all; struct workqueue_struct *writeback_wq; struct work_struct writeback_work; struct work_struct flush_work;
struct dm_io_tracker iot;
struct dm_io_client *dm_io;
raw_spinlock_t endio_list_lock; struct list_head endio_list; struct task_struct *endio_thread;
struct task_struct *flush_thread; spinlock_t flush_list_lock; struct bio_list flush_list;
struct dm_kcopyd_client *dm_kcopyd; unsigned long *dirty_bitmap; unsigned int dirty_bitmap_size;
struct bio_set bio_set; mempool_t copy_pool;
struct { unsigned long long reads; unsigned long long read_hits; unsigned long long writes; unsigned long long write_hits_uncommitted; unsigned long long write_hits_committed; unsigned long long writes_around; unsigned long long writes_allocate; unsigned long long writes_blocked_on_freelist; unsigned long long flushes; unsigned long long discards; } stats;};
#define WB_LIST_INLINE 16
struct writeback_struct { struct list_head endio_entry; struct dm_writecache *wc; struct wc_entry **wc_list; unsigned int wc_list_n; 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 int n_entries; int error;};
DECLARE_DM_KCOPYD_THROTTLE_WITH_MODULE_PARM(dm_writecache_throttle, "A percentage of time allocated for data copying");
static void wc_lock(struct dm_writecache *wc){ mutex_lock(&wc->lock);}
static void wc_unlock(struct dm_writecache *wc){ mutex_unlock(&wc->lock);}
#ifdef DM_WRITECACHE_HAS_PMEMstatic int persistent_memory_claim(struct dm_writecache *wc){ int r; loff_t s; long p, da; unsigned long pfn; int id; struct page **pages; sector_t offset;
wc->memory_vmapped = false;
s = wc->memory_map_size; p = s >> PAGE_SHIFT; if (!p) { r = -EINVAL; goto err1; } if (p != s >> PAGE_SHIFT) { r = -EOVERFLOW; goto err1; }
offset = get_start_sect(wc->ssd_dev->bdev); if (offset & (PAGE_SIZE / 512 - 1)) { r = -EINVAL; goto err1; } offset >>= PAGE_SHIFT - 9;
id = dax_read_lock();
da = dax_direct_access(wc->ssd_dev->dax_dev, offset, p, DAX_ACCESS, &wc->memory_map, &pfn); if (da < 0) { wc->memory_map = NULL; r = da; goto err2; } if (!pfn_valid(pfn)) { wc->memory_map = NULL; r = -EOPNOTSUPP; goto err2; } if (da != p) { long i;
wc->memory_map = NULL; pages = vmalloc_array(p, sizeof(struct page *)); if (!pages) { r = -ENOMEM; goto err2; } i = 0; do { long daa;
daa = dax_direct_access(wc->ssd_dev->dax_dev, offset + i, p - i, DAX_ACCESS, NULL, &pfn); if (daa <= 0) { r = daa ? daa : -EINVAL; goto err3; } if (!pfn_valid(pfn)) { r = -EOPNOTSUPP; goto err3; } while (daa-- && i < p) { pages[i++] = pfn_to_page(pfn); pfn++; if (!(i & 15)) cond_resched(); } } while (i < p); wc->memory_map = vmap(pages, p, VM_MAP, PAGE_KERNEL); if (!wc->memory_map) { r = -ENOMEM; goto err3; } vfree(pages); wc->memory_vmapped = true; }
dax_read_unlock(id);
wc->memory_map += (size_t)wc->start_sector << SECTOR_SHIFT; wc->memory_map_size -= (size_t)wc->start_sector << SECTOR_SHIFT;
return 0;err3: vfree(pages);err2: dax_read_unlock(id);err1: return r;}#elsestatic int persistent_memory_claim(struct dm_writecache *wc){ return -EOPNOTSUPP;}#endif
static void persistent_memory_release(struct dm_writecache *wc){ if (wc->memory_vmapped) vunmap(wc->memory_map - ((size_t)wc->start_sector << SECTOR_SHIFT));}
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 int 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 inline unsigned long wc_entry_index(const struct wc_entry *base, const struct wc_entry *entry){ return entry - base;}
static struct wc_memory_entry *memory_entry(struct dm_writecache *wc, struct wc_entry *e){ const unsigned long index = wc_entry_index(wc->entries, e); return &sb(wc)->entries[index];}
static void *memory_data(struct dm_writecache *wc, struct wc_entry *e){ const unsigned long index = wc_entry_index(wc->entries, e); return (char *)wc->block_start + (index << wc->block_size_bits);}
static sector_t cache_sector(struct dm_writecache *wc, struct wc_entry *e){ const unsigned long index = wc_entry_index(wc->entries, e); return wc->start_sector + wc->metadata_sectors + ((sector_t)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); \ wake_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, unsigned long unsup, void *context){ struct io_notify *endio = context;
if (unlikely(error != 0)) writecache_error(endio->wc, -EIO, "error writing metadata"); else if (unlikely(unsup != 0)) writecache_error(endio->wc, -EOPNOTSUPP, "error writing metadata"); BUG_ON(atomic_read(&endio->count) <= 0); if (atomic_dec_and_test(&endio->count)) complete(&endio->c);}
static void writecache_wait_for_ios(struct dm_writecache *wc, int direction){ wait_event(wc->bio_in_progress_wait[direction], !atomic_read(&wc->bio_in_progress[direction]));}
static void ssd_commit_flushed(struct dm_writecache *wc, bool wait_for_ios){ struct dm_io_region region; struct dm_io_request req; struct io_notify endio = { wc, COMPLETION_INITIALIZER_ONSTACK(endio.c), ATOMIC_INIT(1), }; unsigned int bitmap_bits = wc->dirty_bitmap_size * 8; unsigned int i = 0;
while (1) { unsigned int 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;
region.sector += wc->start_sector; atomic_inc(&endio.count); req.bi_opf = REQ_OP_WRITE | 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, NULL, IOPRIO_DEFAULT); i = j; }
writecache_notify_io(0, 0, &endio); wait_for_completion_io(&endio.c);
if (wait_for_ios) writecache_wait_for_ios(wc, WRITE);
writecache_disk_flush(wc, wc->ssd_dev);
memset(wc->dirty_bitmap, 0, wc->dirty_bitmap_size);}
static void ssd_commit_superblock(struct dm_writecache *wc){ int r; struct dm_io_region region; struct dm_io_request req;
region.bdev = wc->ssd_dev->bdev; region.sector = 0; region.count = max(4096U, wc->block_size) >> SECTOR_SHIFT;
if (unlikely(region.sector + region.count > wc->metadata_sectors)) region.count = wc->metadata_sectors - region.sector;
region.sector += wc->start_sector;
req.bi_opf = REQ_OP_WRITE | REQ_SYNC | REQ_FUA; req.mem.type = DM_IO_VMA; req.mem.ptr.vma = (char *)wc->memory_map; req.client = wc->dm_io; req.notify.fn = NULL; req.notify.context = NULL;
r = dm_io(&req, 1, ®ion, NULL, NULL, IOPRIO_DEFAULT); if (unlikely(r)) writecache_error(wc, r, "error writing superblock");}
static void writecache_commit_flushed(struct dm_writecache *wc, bool wait_for_ios){ if (WC_MODE_PMEM(wc)) pmem_wmb(); else ssd_commit_flushed(wc, wait_for_ios);}
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_opf = REQ_OP_WRITE | 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, NULL, IOPRIO_DEFAULT); if (unlikely(r)) writecache_error(wc, r, "error flushing metadata: %d", r);}
#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) return e;
node = rb_next(&e->rb_node); if (unlikely(!node)) return NULL;
e = container_of(node, struct wc_entry, rb_node); return e; } }
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 (unlikely(!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); ins->age = (u32)jiffies;}
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 inline void writecache_verify_watermark(struct dm_writecache *wc){ if (unlikely(wc->freelist_size + wc->writeback_size <= wc->freelist_high_watermark)) queue_work(wc->writeback_wq, &wc->writeback_work);}
static void writecache_max_age_timer(struct timer_list *t){ struct dm_writecache *wc = timer_container_of(wc, t, max_age_timer);
if (!dm_suspended(wc->ti) && !writecache_has_error(wc)) { queue_work(wc->writeback_wq, &wc->writeback_work); mod_timer(&wc->max_age_timer, jiffies + wc->max_age / MAX_AGE_DIV); }}
static struct wc_entry *writecache_pop_from_freelist(struct dm_writecache *wc, sector_t expected_sector){ 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; if (expected_sector != (sector_t)-1 && unlikely(cache_sector(wc, e) != expected_sector)) return NULL; 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); if (expected_sector != (sector_t)-1 && unlikely(cache_sector(wc, e) != expected_sector)) return NULL; list_del(&e->lru); } wc->freelist_size--;
writecache_verify_watermark(wc);
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(waitqueue_active(&wc->freelist_wait))) wake_up(&wc->freelist_wait);}
static void writecache_wait_on_freelist(struct dm_writecache *wc){ DEFINE_WAIT(wait);
prepare_to_wait(&wc->freelist_wait, &wait, TASK_UNINTERRUPTIBLE); wc_unlock(wc); io_schedule(); finish_wait(&wc->freelist_wait, &wait); wc_lock(wc);}
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; timer_delete(&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, true);
wc->seq_count++; pmem_assign(sb(wc)->seq_count, cpu_to_le64(wc->seq_count)); if (WC_MODE_PMEM(wc)) writecache_commit_flushed(wc, false); else ssd_commit_superblock(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, false);}
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 = timer_container_of(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) { if (!WC_MODE_PMEM(wc)) { writecache_wait_for_ios(wc, READ); writecache_wait_for_ios(wc, WRITE); } discarded_something = true; } writecache_free_entry(wc, e); }
if (unlikely(!node)) break;
e = container_of(node, struct wc_entry, rb_node); }
if (discarded_something) writecache_commit_flushed(wc, false);}
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;
timer_delete_sync(&wc->autocommit_timer); timer_delete_sync(&wc->max_age_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);
drain_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(wc);}
static int writecache_alloc_entries(struct dm_writecache *wc){ size_t b;
if (wc->entries) return 0; wc->entries = vmalloc_array(wc->n_blocks, sizeof(struct wc_entry)); if (!wc->entries) return -ENOMEM; for (b = 0; b < wc->n_blocks; b++) { struct wc_entry *e = &wc->entries[b];
e->write_in_progress = false; cond_resched(); }
return 0;}
static int writecache_read_metadata(struct dm_writecache *wc, sector_t n_sectors){ struct dm_io_region region; struct dm_io_request req;
region.bdev = wc->ssd_dev->bdev; region.sector = wc->start_sector; region.count = n_sectors; req.bi_opf = REQ_OP_READ | 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;
return dm_io(&req, 1, ®ion, NULL, NULL, IOPRIO_DEFAULT);}
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);
wc->data_device_sectors = bdev_nr_sectors(wc->dev->bdev);
if (WC_MODE_PMEM(wc)) { persistent_memory_invalidate_cache(wc->memory_map, wc->memory_map_size); } else { r = writecache_read_metadata(wc, wc->metadata_sectors); if (r) { size_t sb_entries_offset;
writecache_error(wc, r, "unable to read metadata: %d", r); sb_entries_offset = offsetof(struct wc_memory_superblock, entries); memset((char *)wc->memory_map + sb_entries_offset, -1, (wc->metadata_sectors << SECTOR_SHIFT) - sb_entries_offset); } }
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 = copy_mc_to_kernel(&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 = copy_mc_to_kernel(&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); } cond_resched(); }#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, false); }
writecache_verify_watermark(wc);
if (wc->max_age != MAX_AGE_UNSPECIFIED) mod_timer(&wc->max_age_timer, jiffies + wc->max_age / MAX_AGE_DIV);
wc_unlock(wc);}
static int process_flush_mesg(unsigned int 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 int 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 void activate_cleaner(struct dm_writecache *wc){ wc->flush_on_suspend = true; wc->cleaner = true; wc->freelist_high_watermark = wc->n_blocks; wc->freelist_low_watermark = wc->n_blocks;}
static int process_cleaner_mesg(unsigned int argc, char **argv, struct dm_writecache *wc){ if (argc != 1) return -EINVAL;
wc_lock(wc); activate_cleaner(wc); if (!dm_suspended(wc->ti)) writecache_verify_watermark(wc); wc_unlock(wc);
return 0;}
static int process_clear_stats_mesg(unsigned int argc, char **argv, struct dm_writecache *wc){ if (argc != 1) return -EINVAL;
wc_lock(wc); memset(&wc->stats, 0, sizeof(wc->stats)); wc_unlock(wc);
return 0;}
static int writecache_message(struct dm_target *ti, unsigned int argc, char **argv, char *result, unsigned int 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 if (!strcasecmp(argv[0], "cleaner")) r = process_cleaner_mesg(argc, argv, wc); else if (!strcasecmp(argv[0], "clear_stats")) r = process_clear_stats_mesg(argc, argv, wc); else DMERR("unrecognised message received: %s", argv[0]);
return r;}
static void memcpy_flushcache_optimized(void *dest, void *source, size_t size){ /* * clflushopt performs better with block size 1024, 2048, 4096 * non-temporal stores perform better with block size 512 * * block size 512 1024 2048 4096 * movnti 496 MB/s 642 MB/s 725 MB/s 744 MB/s * clflushopt 373 MB/s 688 MB/s 1.1 GB/s 1.2 GB/s * * We see that movnti performs better for 512-byte blocks, and * clflushopt performs better for 1024-byte and larger blocks. So, we * prefer clflushopt for sizes >= 768. * * NOTE: this happens to be the case now (with dm-writecache's single * threaded model) but re-evaluate this once memcpy_flushcache() is * enabled to use movdir64b which might invalidate this performance * advantage seen with cache-allocating-writes plus flushing. */#ifdef CONFIG_X86 if (cpu_feature_enabled(X86_FEATURE_CLFLUSHOPT) && likely(boot_cpu_data.x86_clflush_size == 64) && likely(size >= 768)) { do { memcpy((void *)dest, (void *)source, 64); clflushopt((void *)dest); dest += 64; source += 64; size -= 64; } while (size >= 64); return; }#endif memcpy_flushcache(dest, source, size);}
static void bio_copy_block(struct dm_writecache *wc, struct bio *bio, void *data){ void *buf; unsigned int size; int rw = bio_data_dir(bio); unsigned int remaining_size = wc->block_size;
do { struct bio_vec bv = bio_iter_iovec(bio, bio->bi_iter);
buf = bvec_kmap_local(&bv); size = bv.bv_len; if (unlikely(size > remaining_size)) size = remaining_size;
if (rw == READ) { int r;
r = copy_mc_to_kernel(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_optimized(data, buf, size); }
kunmap_local(buf);
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 (1) { struct bio *bio;
wc_lock(wc); spin_lock_irq(&wc->flush_list_lock); bio = bio_list_pop(&wc->flush_list); if (!bio) { set_current_state(TASK_INTERRUPTIBLE); spin_unlock_irq(&wc->flush_list_lock); wc_unlock(wc);
if (unlikely(kthread_should_stop())) { set_current_state(TASK_RUNNING); break; }
schedule(); continue; } spin_unlock_irq(&wc->flush_list_lock);
if (bio_op(bio) == REQ_OP_DISCARD) { writecache_discard(wc, bio->bi_iter.bi_sector, bio_end_sector(bio)); wc_unlock(wc); bio_set_dev(bio, wc->dev->bdev); submit_bio_noacct(bio); } else { writecache_flush(wc); wc_unlock(wc); if (writecache_has_error(wc)) bio->bi_status = BLK_STS_IOERR; bio_endio(bio); } }
return 0;}
static void writecache_offload_bio(struct dm_writecache *wc, struct bio *bio){ unsigned long flags; spin_lock_irqsave(&wc->flush_list_lock, flags); if (bio_list_empty(&wc->flush_list)) wake_up_process(wc->flush_thread); bio_list_add(&wc->flush_list, bio); spin_unlock_irqrestore(&wc->flush_list_lock, flags);}
enum wc_map_op { WC_MAP_SUBMIT, WC_MAP_REMAP, WC_MAP_REMAP_ORIGIN, WC_MAP_RETURN, WC_MAP_ERROR,};
static void writecache_map_remap_origin(struct dm_writecache *wc, struct bio *bio, struct wc_entry *e){ 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); }}
static enum wc_map_op writecache_map_read(struct dm_writecache *wc, struct bio *bio){ enum wc_map_op map_op; struct wc_entry *e;
read_next_block: wc->stats.reads++; 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) { wc->stats.read_hits++; if (WC_MODE_PMEM(wc)) { bio_copy_block(wc, bio, memory_data(wc, e)); if (bio->bi_iter.bi_size) goto read_next_block; map_op = WC_MAP_SUBMIT; } 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); map_op = WC_MAP_REMAP; } } else { writecache_map_remap_origin(wc, bio, e); wc->stats.reads += (bio->bi_iter.bi_size - wc->block_size) >> wc->block_size_bits; map_op = WC_MAP_REMAP_ORIGIN; }
return map_op;}
static void writecache_bio_copy_ssd(struct dm_writecache *wc, struct bio *bio, struct wc_entry *e, bool search_used){ unsigned int bio_size = wc->block_size; sector_t start_cache_sec = cache_sector(wc, e); sector_t current_cache_sec = start_cache_sec + (bio_size >> SECTOR_SHIFT);
while (bio_size < bio->bi_iter.bi_size) { if (!search_used) { struct wc_entry *f = writecache_pop_from_freelist(wc, current_cache_sec);
if (!f) break; write_original_sector_seq_count(wc, f, bio->bi_iter.bi_sector + (bio_size >> SECTOR_SHIFT), wc->seq_count); writecache_insert_entry(wc, f); wc->uncommitted_blocks++; } else { struct wc_entry *f; struct rb_node *next = rb_next(&e->rb_node);
if (!next) break; f = container_of(next, struct wc_entry, rb_node); if (f != e + 1) break; if (read_original_sector(wc, f) != read_original_sector(wc, e) + (wc->block_size >> SECTOR_SHIFT)) break; if (unlikely(f->write_in_progress)) break; if (writecache_entry_is_committed(wc, f)) wc->overwrote_committed = true; e = f; } bio_size += wc->block_size; current_cache_sec += wc->block_size >> SECTOR_SHIFT; }
bio_set_dev(bio, wc->ssd_dev->bdev); bio->bi_iter.bi_sector = start_cache_sec; dm_accept_partial_bio(bio, bio_size >> SECTOR_SHIFT);
wc->stats.writes += bio->bi_iter.bi_size >> wc->block_size_bits; if (!search_used) wc->stats.writes_allocate += (bio->bi_iter.bi_size - wc->block_size) >> wc->block_size_bits;
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); }}
static enum wc_map_op writecache_map_write(struct dm_writecache *wc, struct bio *bio){ struct wc_entry *e; enum wc_map_op ret = WC_MAP_SUBMIT; bool need_flush = false;
do { bool found_entry = false; bool search_used = false;
if (writecache_has_error(wc)) { wc->stats.writes += bio->bi_iter.bi_size >> wc->block_size_bits; return WC_MAP_ERROR; } e = writecache_find_entry(wc, bio->bi_iter.bi_sector, 0); if (e) { if (!writecache_entry_is_committed(wc, e)) { wc->stats.write_hits_uncommitted++; search_used = true; goto bio_copy; } wc->stats.write_hits_committed++; if (!WC_MODE_PMEM(wc) && !e->write_in_progress) { wc->overwrote_committed = true; search_used = true; goto bio_copy; } found_entry = true; } else { if (unlikely(wc->cleaner) || (wc->metadata_only && !(bio->bi_opf & REQ_META))) goto direct_write; } e = writecache_pop_from_freelist(wc, (sector_t)-1); if (unlikely(!e)) { if (!WC_MODE_PMEM(wc) && !found_entry) {direct_write: e = writecache_find_entry(wc, bio->bi_iter.bi_sector, WFE_RETURN_FOLLOWING); writecache_map_remap_origin(wc, bio, e); wc->stats.writes_around += bio->bi_iter.bi_size >> wc->block_size_bits; wc->stats.writes += bio->bi_iter.bi_size >> wc->block_size_bits; ret = WC_MAP_REMAP_ORIGIN; goto flush_pmem_and_ret; } wc->stats.writes_blocked_on_freelist++; 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++; wc->stats.writes_allocate++;bio_copy: if (WC_MODE_PMEM(wc)) { bio_copy_block(wc, bio, memory_data(wc, e)); wc->stats.writes++; need_flush = true; } else { writecache_bio_copy_ssd(wc, bio, e, search_used); return WC_MAP_REMAP; } } while (bio->bi_iter.bi_size);
flush_pmem_and_ret: if (need_flush) { if (unlikely(bio->bi_opf & REQ_FUA || wc->uncommitted_blocks >= wc->autocommit_blocks)) { writecache_flush(wc); if (writecache_has_error(wc)) ret = WC_MAP_ERROR; } else { writecache_schedule_autocommit(wc); } }
return ret;}
static enum wc_map_op writecache_map_flush(struct dm_writecache *wc, struct bio *bio){ if (writecache_has_error(wc)) return WC_MAP_ERROR;
if (WC_MODE_PMEM(wc)) { wc->stats.flushes++; writecache_flush(wc); if (writecache_has_error(wc)) return WC_MAP_ERROR; else if (unlikely(wc->cleaner) || unlikely(wc->metadata_only)) return WC_MAP_REMAP_ORIGIN; return WC_MAP_SUBMIT; } /* SSD: */ if (dm_bio_get_target_bio_nr(bio)) return WC_MAP_REMAP_ORIGIN; wc->stats.flushes++; writecache_offload_bio(wc, bio); return WC_MAP_RETURN;}
static enum wc_map_op writecache_map_discard(struct dm_writecache *wc, struct bio *bio){ wc->stats.discards += bio->bi_iter.bi_size >> wc->block_size_bits;
if (writecache_has_error(wc)) return WC_MAP_ERROR;
if (WC_MODE_PMEM(wc)) { writecache_discard(wc, bio->bi_iter.bi_sector, bio_end_sector(bio)); return WC_MAP_REMAP_ORIGIN; } /* SSD: */ writecache_offload_bio(wc, bio); return WC_MAP_RETURN;}
static int writecache_map(struct dm_target *ti, struct bio *bio){ struct dm_writecache *wc = ti->private; enum wc_map_op map_op;
bio->bi_private = NULL;
wc_lock(wc);
if (unlikely(bio->bi_opf & REQ_PREFLUSH)) { map_op = writecache_map_flush(wc, bio); goto done; }
bio->bi_iter.bi_sector = dm_target_offset(ti, bio->bi_iter.bi_sector);
if (unlikely((((unsigned int)bio->bi_iter.bi_sector | bio_sectors(bio)) & (wc->block_size / 512 - 1)) != 0)) { DMERR("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); map_op = WC_MAP_ERROR; goto done; }
if (unlikely(bio_op(bio) == REQ_OP_DISCARD)) { map_op = writecache_map_discard(wc, bio); goto done; }
if (bio_data_dir(bio) == READ) map_op = writecache_map_read(wc, bio); else map_op = writecache_map_write(wc, bio);done: switch (map_op) { case WC_MAP_REMAP_ORIGIN: if (likely(wc->pause != 0)) { if (bio_op(bio) == REQ_OP_WRITE) { dm_iot_io_begin(&wc->iot, 1); bio->bi_private = (void *)2; } } bio_set_dev(bio, wc->dev->bdev); wc_unlock(wc); return DM_MAPIO_REMAPPED;
case WC_MAP_REMAP: /* make sure that writecache_end_io decrements bio_in_progress: */ if (unlikely(bio->bi_opf & REQ_FUA) && bio_op(bio) == REQ_OP_WRITE) bio->bi_private = (void *)3; else bio->bi_private = (void *)1; atomic_inc(&wc->bio_in_progress[bio_data_dir(bio)]); wc_unlock(wc); return DM_MAPIO_REMAPPED;
case WC_MAP_SUBMIT: wc_unlock(wc); bio_endio(bio); return DM_MAPIO_SUBMITTED;
case WC_MAP_RETURN: wc_unlock(wc); return DM_MAPIO_SUBMITTED;
case WC_MAP_ERROR: wc_unlock(wc); bio_io_error(bio); return DM_MAPIO_SUBMITTED;
default: BUG(); wc_unlock(wc); return DM_MAPIO_KILL; }}
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 == (void *)1 || bio->bi_private == (void *)3) { int dir = bio_data_dir(bio); bool fua = bio->bi_private == (void *)3;
if (atomic_dec_and_test(&wc->bio_in_progress[dir])) if (unlikely(waitqueue_active(&wc->bio_in_progress_wait[dir]))) wake_up(&wc->bio_in_progress_wait[dir]);
if (fua && likely(*status == BLK_STS_OK)) { bio->bi_private = NULL; writecache_offload_bio(wc, bio); return DM_ENDIO_INCOMPLETE; } } else if (bio->bi_private == (void *)2) { dm_iot_io_end(&wc->iot, 1); } 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;
dm_stack_bs_limits(limits, 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_list_lock, flags); if (unlikely(list_empty(&wc->endio_list))) wake_up_process(wc->endio_thread); list_add_tail(&wb->endio_entry, &wc->endio_list); raw_spin_unlock_irqrestore(&wc->endio_list_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_list_lock); if (unlikely(list_empty(&wc->endio_list))) wake_up_process(wc->endio_thread); list_add_tail(&c->endio_entry, &wc->endio_list); raw_spin_unlock_irq(&wc->endio_list_lock);}
static void __writecache_endio_pmem(struct dm_writecache *wc, struct list_head *list){ unsigned int 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, false); 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) { struct list_head list;
raw_spin_lock_irq(&wc->endio_list_lock); if (!list_empty(&wc->endio_list)) goto pop_from_list; set_current_state(TASK_INTERRUPTIBLE); raw_spin_unlock_irq(&wc->endio_list_lock);
if (unlikely(kthread_should_stop())) { set_current_state(TASK_RUNNING); break; }
schedule();
continue;
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_list_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, false);
wc_unlock(wc); }
return 0;}
static bool wc_add_block(struct writeback_struct *wb, struct wc_entry *e){ struct dm_writecache *wc = wb->wc; unsigned int block_size = wc->block_size; void *address = memory_data(wc, e);
persistent_memory_flush_cache(address, block_size);
if (unlikely(bio_end_sector(&wb->bio) >= wc->data_device_sectors)) return true;
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(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 int 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(wc->dev->bdev, max_pages, REQ_OP_WRITE, GFP_NOIO, &wc->bio_set); wb = container_of(bio, struct writeback_struct, bio); wb->wc = wc; bio->bi_end_io = writecache_writeback_endio; bio->bi_iter.bi_sector = read_original_sector(wc, e);
if (unlikely(max_pages > WB_LIST_INLINE)) wb->wc_list = kmalloc_objs(struct wc_entry *, max_pages, GFP_NOIO | __GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN);
if (likely(max_pages <= WB_LIST_INLINE) || unlikely(!wb->wc_list)) { wb->wc_list = wb->wc_list_inline; max_pages = WB_LIST_INLINE; }
BUG_ON(!wc_add_block(wb, e));
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)) break; wbl->size--; list_del(&f->lru); wb->wc_list[wb->wc_list_n++] = f; e = f; } if (WC_MODE_FUA(wc)) bio->bi_opf |= REQ_FUA; if (writecache_has_error(wc)) { bio->bi_status = BLK_STS_IOERR; bio_endio(bio); } else if (unlikely(!bio_sectors(bio))) { bio->bi_status = BLK_STS_OK; bio_endio(bio); } else { submit_bio(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 int 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; }
if (unlikely(to.sector + to.count > wc->data_device_sectors)) { if (to.sector >= wc->data_device_sectors) { writecache_copy_endio(0, 0, c); continue; } from.count = to.count = wc->data_device_sectors - to.sector; }
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 *f, *g, *e = NULL; struct rb_node *node, *next_node; struct list_head skipped; struct writeback_list wbl; unsigned long n_walked;
if (!WC_MODE_PMEM(wc)) { /* Wait for any active kcopyd work on behalf of ssd writeback */ dm_kcopyd_client_flush(wc->dm_kcopyd); }
if (likely(wc->pause != 0)) { while (1) { unsigned long idle;
if (unlikely(wc->cleaner) || unlikely(wc->writeback_all) || unlikely(dm_suspended(wc->ti))) break; idle = dm_iot_idle_time(&wc->iot); if (idle >= wc->pause) break; idle = wc->pause - idle; if (idle > HZ) idle = HZ; schedule_timeout_idle(idle); } }
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_low_watermark || ((u32)(jiffies - container_of(wc->lru.prev, struct wc_entry, lru)->age) >= wc->max_age - wc->max_age / MAX_AGE_DIV))) {
n_walked++; if (unlikely(n_walked > WRITEBACK_LATENCY) && likely(!wc->writeback_all)) { if (likely(!dm_suspended(wc->ti))) queue_work(wc->writeback_wq, &wc->writeback_work); break; }
if (unlikely(wc->writeback_all)) { if (unlikely(!e)) { writecache_flush(wc); e = container_of(rb_first(&wc->tree), struct wc_entry, rb_node); } else e = g; } else 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_move(&e->lru, &skipped); cond_resched(); continue; } } wc->writeback_size++; list_move(&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 (unlikely(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_move(&g->lru, &wbl.list); wbl.size++; g->write_in_progress = true; g->wc_list_contiguous = BIO_MAX_VECS; f = g; e->wc_list_contiguous++; if (unlikely(e->wc_list_contiguous == BIO_MAX_VECS)) { if (unlikely(wc->writeback_all)) { next_node = rb_next(&f->rb_node); if (likely(next_node)) g = container_of(next_node, struct wc_entry, rb_node); } 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 int block_size, size_t *n_blocks_p, size_t *n_metadata_blocks_p){ uint64_t n_blocks, offset;
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--; }
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); cond_resched(); }
writecache_flush_all_metadata(wc); writecache_commit_flushed(wc, false); 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, false);
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);
bioset_exit(&wc->bio_set);
mempool_exit(&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);
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);
vfree(wc->dirty_bitmap);
kfree(wc);}
static int writecache_ctr(struct dm_target *ti, unsigned int argc, char **argv){ struct dm_writecache *wc; struct dm_arg_set as; const char *string; unsigned int 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, 18, "Invalid number of feature args"}, };
as.argc = argc; as.argv = argv;
wc = kzalloc_obj(struct dm_writecache); if (!wc) { ti->error = "Cannot allocate writecache structure"; r = -ENOMEM; goto bad; } ti->private = wc; wc->ti = ti;
mutex_init(&wc->lock); wc->max_age = MAX_AGE_UNSPECIFIED; writecache_poison_lists(wc); init_waitqueue_head(&wc->freelist_wait); timer_setup(&wc->autocommit_timer, writecache_autocommit_timer, 0); timer_setup(&wc->max_age_timer, writecache_max_age_timer, 0);
for (i = 0; i < 2; i++) { atomic_set(&wc->bio_in_progress[i], 0); init_waitqueue_head(&wc->bio_in_progress_wait[i]); }
wc->dm_io = dm_io_client_create(); if (IS_ERR(wc->dm_io)) { r = PTR_ERR(wc->dm_io); ti->error = "Unable to allocate dm-io client"; wc->dm_io = NULL; goto bad; }
wc->writeback_wq = alloc_workqueue("writecache-writeback", WQ_MEM_RECLAIM | WQ_PERCPU, 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);
dm_iot_init(&wc->iot);
raw_spin_lock_init(&wc->endio_list_lock); INIT_LIST_HEAD(&wc->endio_list); wc->endio_thread = kthread_run(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; }
/* * Parse the mode (pmem or ssd) */ string = dm_shift_arg(&as); if (!string) goto bad_arguments;
if (!strcasecmp(string, "s")) { wc->pmem_mode = false; } else if (!strcasecmp(string, "p")) {#ifdef DM_WRITECACHE_HAS_PMEM wc->pmem_mode = true; wc->writeback_fua = true;#else /* * If the architecture doesn't support persistent memory or * the kernel doesn't support any DAX drivers, this driver can * only be used in SSD-only mode. */ r = -EOPNOTSUPP; ti->error = "Persistent memory or DAX not supported on this system"; goto bad;#endif } else { goto bad_arguments; }
if (WC_MODE_PMEM(wc)) { r = bioset_init(&wc->bio_set, BIO_POOL_SIZE, offsetof(struct writeback_struct, bio), BIOSET_NEED_BVECS); if (r) { ti->error = "Could not allocate bio set"; goto bad; } } else { wc->pause = PAUSE_WRITEBACK; r = mempool_init_kmalloc_pool(&wc->copy_pool, 1, sizeof(struct copy_struct)); if (r) { 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 = bdev_nr_bytes(wc->ssd_dev->bdev);
/* * 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; } if (wc->block_size < bdev_logical_block_size(wc->dev->bdev) || wc->block_size < bdev_logical_block_size(wc->ssd_dev->bdev)) { r = -EINVAL; ti->error = "Block size is smaller than device logical 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, "start_sector") && opt_params >= 1) { unsigned long long start_sector;
string = dm_shift_arg(&as), opt_params--; if (sscanf(string, "%llu%c", &start_sector, &dummy) != 1) goto invalid_optional; wc->start_sector = start_sector; wc->start_sector_set = true; if (wc->start_sector != start_sector || wc->start_sector >= wc->memory_map_size >> SECTOR_SHIFT) goto invalid_optional; } else 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_value = high_wm_percent; 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_value = low_wm_percent; 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 int 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 = msecs_to_jiffies(autocommit_msecs); wc->autocommit_time_value = autocommit_msecs; wc->autocommit_time_set = true; } else if (!strcasecmp(string, "max_age") && opt_params >= 1) { unsigned int max_age_msecs; unsigned long max_age_jiffies;
string = dm_shift_arg(&as), opt_params--; if (sscanf(string, "%u%c", &max_age_msecs, &dummy) != 1) goto invalid_optional; max_age_jiffies = msecs_to_jiffies(max_age_msecs); if (max_age_jiffies >= min(MAX_JIFFY_OFFSET, (7 << 28))) // 7/8ths of 1 << 31 goto invalid_optional; wc->max_age = max_age_jiffies; wc->max_age_set = true; wc->max_age_value = max_age_msecs; } else if (!strcasecmp(string, "cleaner")) { wc->cleaner_set = true; wc->cleaner = true; } else if (!strcasecmp(string, "fua")) { if (WC_MODE_PMEM(wc)) { wc->writeback_fua = true; wc->writeback_fua_set = true; } else goto invalid_optional; } else if (!strcasecmp(string, "nofua")) { if (WC_MODE_PMEM(wc)) { wc->writeback_fua = false; wc->writeback_fua_set = true; } else goto invalid_optional; } else if (!strcasecmp(string, "metadata_only")) { wc->metadata_only = true; } else if (!strcasecmp(string, "pause_writeback") && opt_params >= 1) { unsigned int pause_msecs;
if (WC_MODE_PMEM(wc)) goto invalid_optional; string = dm_shift_arg(&as), opt_params--; if (sscanf(string, "%u%c", &pause_msecs, &dummy) != 1) goto invalid_optional; if (pause_msecs > 60000) goto invalid_optional; wc->pause = msecs_to_jiffies(pause_msecs); wc->pause_set = true; wc->pause_value = pause_msecs; } else {invalid_optional: r = -EINVAL; ti->error = "Invalid optional argument"; goto bad; } }
if (high_wm_percent < low_wm_percent) { r = -EINVAL; ti->error = "High watermark must be greater than or equal to low watermark"; goto bad; }
if (WC_MODE_PMEM(wc)) { if (!wc->ssd_dev->dax_dev) { r = -EOPNOTSUPP; ti->error = "Cache device is not a DAX device"; goto bad; } if (!dax_synchronous(wc->ssd_dev->dax_dev)) { r = -EOPNOTSUPP; ti->error = "Asynchronous persistent memory not supported as pmem cache"; goto bad; }
r = persistent_memory_claim(wc); if (r) { ti->error = "Unable to map persistent memory for cache"; goto bad; } } else { size_t n_blocks, n_metadata_blocks; uint64_t n_bitmap_bits;
wc->memory_map_size -= (uint64_t)wc->start_sector << SECTOR_SHIFT;
spin_lock_init(&wc->flush_list_lock); bio_list_init(&wc->flush_list); wc->flush_thread = kthread_run(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 flush thread"; goto bad; }
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"; goto bad; }
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 (IS_ERR(wc->dm_kcopyd)) { r = PTR_ERR(wc->dm_kcopyd); ti->error = "Unable to allocate dm-kcopyd client"; wc->dm_kcopyd = NULL; 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; }
r = writecache_read_metadata(wc, wc->block_size >> SECTOR_SHIFT); if (r) { ti->error = "Unable to read first block of metadata"; goto bad; } }
r = copy_mc_to_kernel(&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 = copy_mc_to_kernel(&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;
if (wc->cleaner) activate_cleaner(wc);
r = writecache_alloc_entries(wc); if (r) { ti->error = "Cannot allocate memory"; goto bad; }
ti->num_flush_bios = WC_MODE_PMEM(wc) ? 1 : 2; 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 int status_flags, char *result, unsigned int maxlen){ struct dm_writecache *wc = ti->private; unsigned int extra_args; unsigned int sz = 0;
switch (type) { case STATUSTYPE_INFO: DMEMIT("%ld %llu %llu %llu %llu %llu %llu %llu %llu %llu %llu %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, wc->stats.reads, wc->stats.read_hits, wc->stats.writes, wc->stats.write_hits_uncommitted, wc->stats.write_hits_committed, wc->stats.writes_around, wc->stats.writes_allocate, wc->stats.writes_blocked_on_freelist, wc->stats.flushes, wc->stats.discards); 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->start_sector_set) extra_args += 2; 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; if (wc->max_age_set) extra_args += 2; if (wc->cleaner_set) extra_args++; if (wc->writeback_fua_set) extra_args++; if (wc->metadata_only) extra_args++; if (wc->pause_set) extra_args += 2;
DMEMIT("%u", extra_args); if (wc->start_sector_set) DMEMIT(" start_sector %llu", (unsigned long long)wc->start_sector); if (wc->high_wm_percent_set) DMEMIT(" high_watermark %u", wc->high_wm_percent_value); if (wc->low_wm_percent_set) DMEMIT(" low_watermark %u", wc->low_wm_percent_value); 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", wc->autocommit_time_value); if (wc->max_age_set) DMEMIT(" max_age %u", wc->max_age_value); if (wc->cleaner_set) DMEMIT(" cleaner"); if (wc->writeback_fua_set) DMEMIT(" %sfua", wc->writeback_fua ? "" : "no"); if (wc->metadata_only) DMEMIT(" metadata_only"); if (wc->pause_set) DMEMIT(" pause_writeback %u", wc->pause_value); break; case STATUSTYPE_IMA: *result = '\0'; break; }}
static struct target_type writecache_target = { .name = "writecache", .version = {1, 6, 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,};module_dm(writecache);
MODULE_DESCRIPTION(DM_NAME " writecache target");MODULE_AUTHOR("Mikulas Patocka <dm-devel@lists.linux.dev>");MODULE_LICENSE("GPL");