Something went wrong. Try again.
Linux kernel mirror (for testing) git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
Something went wrong. Try again.
1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950515253545556575859606162636465666768697071727374757677787980818283848586878889909192939495969798991001011021031041051061071081091101111121131141151161171181191201211221231241251261271281291301311321331341351361371381391401411421431441451461471481491501511521531541551561571581591601611621631641651661671681691701711721731741751761771781791801811821831841851861871881891901911921931941951961971981992002012022032042052062072082092102112122132142152162172182192202212222232242252262272282292302312322332342352362372382392402412422432442452462472482492502512522532542552562572582592602612622632642652662672682692702712722732742752762772782792802812822832842852862872882892902912922932942952962972982993003013023033043053063073083093103113123133143153163173183193203213223233243253263273283293303313323333343353363373383393403413423433443453463473483493503513523533543553563573583593603613623633643653663673683693703713723733743753763773783793803813823833843853863873883893903913923933943953963973983994004014024034044054064074084094104114124134144154164174184194204214224234244254264274284294304314324334344354364374384394404414424434444454464474484494504514524534544554564574584594604614624634644654664674684694704714724734744754764774784794804814824834844854864874884894904914924934944954964974984995005015025035045055065075085095105115125135145155165175185195205215225235245255265275285295305315325335345355365375385395405415425435445455465475485495505515525535545555565575585595605615625635645655665675685695705715725735745755765775785795805815825835845855865875885895905915925935945955965975985996006016026036046056066076086096106116126136146156166176186196206216226236246256266276286296306316326336346356366376386396406416426436446456466476486496506516526536546556566576586596606616626636646656666676686696706716726736746756766776786796806816826836846856866876886896906916926936946956966976986997007017027037047057067077087097107117127137147157167177187197207217227237247257267277287297307317327337347357367377387397407417427437447457467477487497507517527537547557567577587597607617627637647657667677687697707717727737747757767777787797807817827837847857867877887897907917927937947957967977987998008018028038048058068078088098108118128138148158168178188198208218228238248258268278288298308318328338348358368378388398408418428438448458468478488498508518528538548558568578588598608618628638648658668678688698708718728738748758768778788798808818828838848858868878888898908918928938948958968978988999009019029039049059069079089099109119129139149159169179189199209219229239249259269279289299309319329339349359369379389399409419429439449459469479489499509519529539549559569579589599609619629639649659669679689699709719729739749759769779789799809819829839849859869879889899909919929939949959969979989991000100110021003100410051006100710081009101010111012101310141015101610171018101910201021102210231024102510261027102810291030103110321033103410351036103710381039104010411042104310441045104610471048104910501051105210531054105510561057105810591060106110621063106410651066106710681069107010711072107310741075107610771078107910801081108210831084108510861087108810891090109110921093109410951096109710981099110011011102110311041105110611071108110911101111111211131114111511161117111811191120112111221123112411251126112711281129113011311132113311341135113611371138113911401141114211431144114511461147114811491150115111521153115411551156115711581159116011611162116311641165116611671168116911701171117211731174117511761177117811791180118111821183118411851186118711881189119011911192119311941195119611971198119912001201120212031204120512061207120812091210121112121213121412151216121712181219122012211222122312241225122612271228122912301231123212331234123512361237123812391240124112421243124412451246124712481249125012511252125312541255125612571258125912601261126212631264126512661267126812691270127112721273127412751276127712781279128012811282128312841285128612871288128912901291129212931294129512961297129812991300130113021303130413051306130713081309131013111312131313141315131613171318131913201321132213231324132513261327132813291330133113321333133413351336133713381339134013411342134313441345134613471348134913501351135213531354135513561357135813591360136113621363136413651366136713681369137013711372137313741375137613771378137913801381138213831384138513861387138813891390139113921393139413951396139713981399140014011402140314041405140614071408140914101411141214131414141514161417141814191420142114221423142414251426142714281429143014311432143314341435143614371438143914401441144214431444144514461447144814491450145114521453145414551456145714581459146014611462146314641465146614671468146914701471147214731474147514761477147814791480148114821483148414851486148714881489149014911492149314941495149614971498149915001501150215031504150515061507150815091510151115121513151415151516151715181519152015211522152315241525152615271528152915301531153215331534153515361537153815391540154115421543154415451546154715481549155015511552155315541555155615571558155915601561156215631564156515661567156815691570157115721573157415751576157715781579158015811582158315841585158615871588158915901591159215931594159515961597159815991600160116021603160416051606160716081609161016111612161316141615161616171618161916201621162216231624162516261627162816291630163116321633163416351636163716381639164016411642164316441645164616471648164916501651165216531654165516561657165816591660166116621663166416651666166716681669167016711672167316741675167616771678167916801681168216831684168516861687168816891690169116921693169416951696169716981699170017011702170317041705170617071708170917101711171217131714171517161717171817191720172117221723172417251726172717281729173017311732173317341735173617371738173917401741174217431744174517461747174817491750175117521753175417551756175717581759176017611762176317641765176617671768176917701771177217731774177517761777177817791780178117821783178417851786178717881789179017911792179317941795179617971798179918001801180218031804180518061807180818091810181118121813181418151816181718181819182018211822182318241825182618271828182918301831183218331834183518361837183818391840184118421843184418451846184718481849185018511852185318541855185618571858185918601861186218631864186518661867186818691870187118721873187418751876187718781879188018811882188318841885188618871888188918901891189218931894189518961897189818991900190119021903190419051906190719081909191019111912191319141915191619171918191919201921192219231924192519261927192819291930193119321933193419351936193719381939194019411942194319441945194619471948194919501951195219531954195519561957195819591960196119621963196419651966196719681969197019711972197319741975197619771978197919801981198219831984198519861987198819891990199119921993199419951996199719981999200020012002200320042005200620072008200920102011201220132014201520162017201820192020202120222023202420252026202720282029203020312032203320342035203620372038203920402041204220432044204520462047204820492050205120522053205420552056205720582059206020612062206320642065206620672068206920702071207220732074207520762077207820792080208120822083208420852086208720882089209020912092209320942095209620972098209921002101210221032104210521062107210821092110211121122113211421152116211721182119212021212122212321242125212621272128212921302131213221332134213521362137213821392140214121422143214421452146214721482149215021512152215321542155215621572158215921602161216221632164216521662167216821692170217121722173217421752176217721782179218021812182218321842185218621872188218921902191219221932194219521962197219821992200220122022203220422052206220722082209221022112212221322142215221622172218221922202221222222232224222522262227222822292230223122322233223422352236223722382239224022412242224322442245224622472248224922502251225222532254225522562257225822592260226122622263226422652266226722682269227022712272227322742275227622772278227922802281228222832284228522862287228822892290229122922293229422952296229722982299230023012302230323042305230623072308230923102311231223132314231523162317231823192320232123222323232423252326232723282329233023312332233323342335233623372338233923402341234223432344234523462347234823492350235123522353235423552356235723582359236023612362236323642365236623672368236923702371237223732374237523762377237823792380238123822383238423852386238723882389239023912392239323942395239623972398239924002401240224032404240524062407240824092410241124122413241424152416241724182419// SPDX-License-Identifier: GPL-2.0
#include <kunit/visibility.h>#include <linux/kernel.h>#include <linux/irqflags.h>#include <linux/string.h>#include <linux/errno.h>#include <linux/bug.h>#include "printk_ringbuffer.h"#include "internal.h"
/** * DOC: printk_ringbuffer overview * * Data Structure * -------------- * The printk_ringbuffer is made up of 2 internal ringbuffers: * * desc_ring * A ring of descriptors and their meta data (such as sequence number, * timestamp, loglevel, etc.) as well as internal state information about * the record and logical positions specifying where in the other * ringbuffer the text strings are located. * * text_data_ring * A ring of data blocks. A data block consists of an unsigned long * integer (ID) that maps to a desc_ring index followed by the text * string of the record. * * The internal state information of a descriptor is the key element to allow * readers and writers to locklessly synchronize access to the data. * * Implementation * -------------- * * Descriptor Ring * ~~~~~~~~~~~~~~~ * The descriptor ring is an array of descriptors. A descriptor contains * essential meta data to track the data of a printk record using * blk_lpos structs pointing to associated text data blocks (see * "Data Rings" below). Each descriptor is assigned an ID that maps * directly to index values of the descriptor array and has a state. The ID * and the state are bitwise combined into a single descriptor field named * @state_var, allowing ID and state to be synchronously and atomically * updated. * * Descriptors have four states: * * reserved * A writer is modifying the record. * * committed * The record and all its data are written. A writer can reopen the * descriptor (transitioning it back to reserved), but in the committed * state the data is consistent. * * finalized * The record and all its data are complete and available for reading. A * writer cannot reopen the descriptor. * * reusable * The record exists, but its text and/or meta data may no longer be * available. * * Querying the @state_var of a record requires providing the ID of the * descriptor to query. This can yield a possible fifth (pseudo) state: * * miss * The descriptor being queried has an unexpected ID. * * The descriptor ring has a @tail_id that contains the ID of the oldest * descriptor and @head_id that contains the ID of the newest descriptor. * * When a new descriptor should be created (and the ring is full), the tail * descriptor is invalidated by first transitioning to the reusable state and * then invalidating all tail data blocks up to and including the data blocks * associated with the tail descriptor (for the text ring). Then * @tail_id is advanced, followed by advancing @head_id. And finally the * @state_var of the new descriptor is initialized to the new ID and reserved * state. * * The @tail_id can only be advanced if the new @tail_id would be in the * committed or reusable queried state. This makes it possible that a valid * sequence number of the tail is always available. * * Descriptor Finalization * ~~~~~~~~~~~~~~~~~~~~~~~ * When a writer calls the commit function prb_commit(), record data is * fully stored and is consistent within the ringbuffer. However, a writer can * reopen that record, claiming exclusive access (as with prb_reserve()), and * modify that record. When finished, the writer must again commit the record. * * In order for a record to be made available to readers (and also become * recyclable for writers), it must be finalized. A finalized record cannot be * reopened and can never become "unfinalized". Record finalization can occur * in three different scenarios: * * 1) A writer can simultaneously commit and finalize its record by calling * prb_final_commit() instead of prb_commit(). * * 2) When a new record is reserved and the previous record has been * committed via prb_commit(), that previous record is automatically * finalized. * * 3) When a record is committed via prb_commit() and a newer record * already exists, the record being committed is automatically finalized. * * Data Ring * ~~~~~~~~~ * The text data ring is a byte array composed of data blocks. Data blocks are * referenced by blk_lpos structs that point to the logical position of the * beginning of a data block and the beginning of the next adjacent data * block. Logical positions are mapped directly to index values of the byte * array ringbuffer. * * Each data block consists of an ID followed by the writer data. The ID is * the identifier of a descriptor that is associated with the data block. A * given data block is considered valid if all of the following conditions * are met: * * 1) The descriptor associated with the data block is in the committed * or finalized queried state. * * 2) The blk_lpos struct within the descriptor associated with the data * block references back to the same data block. * * 3) The data block is within the head/tail logical position range. * * If the writer data of a data block would extend beyond the end of the * byte array, only the ID of the data block is stored at the logical * position and the full data block (ID and writer data) is stored at the * beginning of the byte array. The referencing blk_lpos will point to the * ID before the wrap and the next data block will be at the logical * position adjacent the full data block after the wrap. * * Data rings have a @tail_lpos that points to the beginning of the oldest * data block and a @head_lpos that points to the logical position of the * next (not yet existing) data block. * * When a new data block should be created (and the ring is full), tail data * blocks will first be invalidated by putting their associated descriptors * into the reusable state and then pushing the @tail_lpos forward beyond * them. Then the @head_lpos is pushed forward and is associated with a new * descriptor. If a data block is not valid, the @tail_lpos cannot be * advanced beyond it. * * Info Array * ~~~~~~~~~~ * The general meta data of printk records are stored in printk_info structs, * stored in an array with the same number of elements as the descriptor ring. * Each info corresponds to the descriptor of the same index in the * descriptor ring. Info validity is confirmed by evaluating the corresponding * descriptor before and after loading the info. * * Usage * ----- * Here are some simple examples demonstrating writers and readers. For the * examples a global ringbuffer (test_rb) is available (which is not the * actual ringbuffer used by printk):: * * DEFINE_PRINTKRB(test_rb, 15, 5); * * This ringbuffer allows up to 32768 records (2 ^ 15) and has a size of * 1 MiB (2 ^ (15 + 5)) for text data. * * Sample writer code:: * * const char *textstr = "message text"; * struct prb_reserved_entry e; * struct printk_record r; * * // specify how much to allocate * prb_rec_init_wr(&r, strlen(textstr) + 1); * * if (prb_reserve(&e, &test_rb, &r)) { * snprintf(r.text_buf, r.text_buf_size, "%s", textstr); * * r.info->text_len = strlen(textstr); * r.info->ts_nsec = local_clock(); * r.info->caller_id = printk_caller_id(); * * // commit and finalize the record * prb_final_commit(&e); * } * * Note that additional writer functions are available to extend a record * after it has been committed but not yet finalized. This can be done as * long as no new records have been reserved and the caller is the same. * * Sample writer code (record extending):: * * // alternate rest of previous example * * r.info->text_len = strlen(textstr); * r.info->ts_nsec = local_clock(); * r.info->caller_id = printk_caller_id(); * * // commit the record (but do not finalize yet) * prb_commit(&e); * } * * ... * * // specify additional 5 bytes text space to extend * prb_rec_init_wr(&r, 5); * * // try to extend, but only if it does not exceed 32 bytes * if (prb_reserve_in_last(&e, &test_rb, &r, printk_caller_id(), 32)) { * snprintf(&r.text_buf[r.info->text_len], * r.text_buf_size - r.info->text_len, "hello"); * * r.info->text_len += 5; * * // commit and finalize the record * prb_final_commit(&e); * } * * Sample reader code:: * * struct printk_info info; * struct printk_record r; * char text_buf[32]; * u64 seq; * * prb_rec_init_rd(&r, &info, &text_buf[0], sizeof(text_buf)); * * prb_for_each_record(0, &test_rb, seq, &r) { * if (info.seq != seq) * pr_warn("lost %llu records\n", info.seq - seq); * * if (info.text_len > r.text_buf_size) { * pr_warn("record %llu text truncated\n", info.seq); * text_buf[r.text_buf_size - 1] = 0; * } * * pr_info("%llu: %llu: %s\n", info.seq, info.ts_nsec, * &text_buf[0]); * } * * Note that additional less convenient reader functions are available to * allow complex record access. * * ABA Issues * ~~~~~~~~~~ * To help avoid ABA issues, descriptors are referenced by IDs (array index * values combined with tagged bits counting array wraps) and data blocks are * referenced by logical positions (array index values combined with tagged * bits counting array wraps). However, on 32-bit systems the number of * tagged bits is relatively small such that an ABA incident is (at least * theoretically) possible. For example, if 4 million maximally sized (1KiB) * printk messages were to occur in NMI context on a 32-bit system, the * interrupted context would not be able to recognize that the 32-bit integer * completely wrapped and thus represents a different data block than the one * the interrupted context expects. * * To help combat this possibility, additional state checking is performed * (such as using cmpxchg() even though set() would suffice). These extra * checks are commented as such and will hopefully catch any ABA issue that * a 32-bit system might experience. * * Memory Barriers * ~~~~~~~~~~~~~~~ * Multiple memory barriers are used. To simplify proving correctness and * generating litmus tests, lines of code related to memory barriers * (loads, stores, and the associated memory barriers) are labeled:: * * LMM(function:letter) * * Comments reference the labels using only the "function:letter" part. * * The memory barrier pairs and their ordering are: * * desc_reserve:D / desc_reserve:B * push descriptor tail (id), then push descriptor head (id) * * desc_reserve:D / data_push_tail:B * push data tail (lpos), then set new descriptor reserved (state) * * desc_reserve:D / desc_push_tail:C * push descriptor tail (id), then set new descriptor reserved (state) * * desc_reserve:D / prb_first_seq:C * push descriptor tail (id), then set new descriptor reserved (state) * * desc_reserve:F / desc_read:D * set new descriptor id and reserved (state), then allow writer changes * * data_alloc:A (or data_realloc:A) / desc_read:D * set old descriptor reusable (state), then modify new data block area * * data_alloc:A (or data_realloc:A) / data_push_tail:B * push data tail (lpos), then modify new data block area * * _prb_commit:B / desc_read:B * store writer changes, then set new descriptor committed (state) * * desc_reopen_last:A / _prb_commit:B * set descriptor reserved (state), then read descriptor data * * _prb_commit:B / desc_reserve:D * set new descriptor committed (state), then check descriptor head (id) * * data_push_tail:D / data_push_tail:A * set descriptor reusable (state), then push data tail (lpos) * * desc_push_tail:B / desc_reserve:D * set descriptor reusable (state), then push descriptor tail (id) * * desc_update_last_finalized:A / desc_last_finalized_seq:A * store finalized record, then set new highest finalized sequence number */
#define DATA_SIZE(data_ring) _DATA_SIZE((data_ring)->size_bits)#define DATA_SIZE_MASK(data_ring) (DATA_SIZE(data_ring) - 1)
#define DESCS_COUNT(desc_ring) _DESCS_COUNT((desc_ring)->count_bits)#define DESCS_COUNT_MASK(desc_ring) (DESCS_COUNT(desc_ring) - 1)
/* Determine the data array index from a logical position. */#define DATA_INDEX(data_ring, lpos) ((lpos) & DATA_SIZE_MASK(data_ring))
/* Determine the desc array index from an ID or sequence number. */#define DESC_INDEX(desc_ring, n) ((n) & DESCS_COUNT_MASK(desc_ring))
/* Determine how many times the data array has wrapped. */#define DATA_WRAPS(data_ring, lpos) ((lpos) >> (data_ring)->size_bits)
/* Determine if a logical position refers to a data-less block. */#define LPOS_DATALESS(lpos) ((lpos) & 1UL)#define BLK_DATALESS(blk) (LPOS_DATALESS((blk)->begin) && \ LPOS_DATALESS((blk)->next))
/* Get the logical position at index 0 of the current wrap. */#define DATA_THIS_WRAP_START_LPOS(data_ring, lpos) \((lpos) & ~DATA_SIZE_MASK(data_ring))
/* Get the ID for the same index of the previous wrap as the given ID. */#define DESC_ID_PREV_WRAP(desc_ring, id) \DESC_ID((id) - DESCS_COUNT(desc_ring))
/* * A data block: mapped directly to the beginning of the data block area * specified as a logical position within the data ring. * * @id: the ID of the associated descriptor * @data: the writer data * * Note that the size of a data block is only known by its associated * descriptor. */struct prb_data_block { unsigned long id; char data[];};
/* * Return the descriptor associated with @n. @n can be either a * descriptor ID or a sequence number. */static struct prb_desc *to_desc(struct prb_desc_ring *desc_ring, u64 n){ return &desc_ring->descs[DESC_INDEX(desc_ring, n)];}
/* * Return the printk_info associated with @n. @n can be either a * descriptor ID or a sequence number. */static struct printk_info *to_info(struct prb_desc_ring *desc_ring, u64 n){ return &desc_ring->infos[DESC_INDEX(desc_ring, n)];}
static struct prb_data_block *to_block(struct prb_data_ring *data_ring, unsigned long begin_lpos){ return (void *)&data_ring->data[DATA_INDEX(data_ring, begin_lpos)];}
/* * Increase the data size to account for data block meta data plus any * padding so that the adjacent data block is aligned on the ID size. */static unsigned int to_blk_size(unsigned int size){ struct prb_data_block *db = NULL;
size += sizeof(*db); size = ALIGN(size, sizeof(db->id)); return size;}
/* * Sanity checker for reserve size. The ringbuffer code assumes that a data * block does not exceed the maximum possible size that could fit within the * ringbuffer. This function provides that basic size check so that the * assumption is safe. In particular, it guarantees that data_push_tail() will * never attempt to push the tail beyond the head. */static bool data_check_size(struct prb_data_ring *data_ring, unsigned int size){ /* Data-less blocks take no space. */ if (size == 0) return true;
/* * If data blocks were allowed to be larger than half the data ring * size, a wrapping data block could require more space than the full * ringbuffer. */ return to_blk_size(size) <= DATA_SIZE(data_ring) / 2;}
/* * Compare the current and requested logical position and decide * whether more space is needed. * * Return false when @lpos_current is already at or beyond @lpos_target. * * Also return false when the difference between the positions is bigger * than the size of the data buffer. It might happen only when the caller * raced with another CPU(s) which already made and used the space. */static bool need_more_space(struct prb_data_ring *data_ring, unsigned long lpos_current, unsigned long lpos_target){ return lpos_target - lpos_current - 1 < DATA_SIZE(data_ring);}
/* Query the state of a descriptor. */static enum desc_state get_desc_state(unsigned long id, unsigned long state_val){ if (id != DESC_ID(state_val)) return desc_miss;
return DESC_STATE(state_val);}
/* * Get a copy of a specified descriptor and return its queried state. If the * descriptor is in an inconsistent state (miss or reserved), the caller can * only expect the descriptor's @state_var field to be valid. * * The sequence number and caller_id can be optionally retrieved. Like all * non-state_var data, they are only valid if the descriptor is in a * consistent state. */static enum desc_state desc_read(struct prb_desc_ring *desc_ring, unsigned long id, struct prb_desc *desc_out, u64 *seq_out, u32 *caller_id_out){ struct printk_info *info = to_info(desc_ring, id); struct prb_desc *desc = to_desc(desc_ring, id); atomic_long_t *state_var = &desc->state_var; enum desc_state d_state; unsigned long state_val;
/* Check the descriptor state. */ state_val = atomic_long_read(state_var); /* LMM(desc_read:A) */ d_state = get_desc_state(id, state_val); if (d_state == desc_miss || d_state == desc_reserved) { /* * The descriptor is in an inconsistent state. Set at least * @state_var so that the caller can see the details of * the inconsistent state. */ goto out; }
/* * Guarantee the state is loaded before copying the descriptor * content. This avoids copying obsolete descriptor content that might * not apply to the descriptor state. This pairs with _prb_commit:B. * * Memory barrier involvement: * * If desc_read:A reads from _prb_commit:B, then desc_read:C reads * from _prb_commit:A. * * Relies on: * * WMB from _prb_commit:A to _prb_commit:B * matching * RMB from desc_read:A to desc_read:C */ smp_rmb(); /* LMM(desc_read:B) */
/* * Copy the descriptor data. The data is not valid until the * state has been re-checked. A memcpy() for all of @desc * cannot be used because of the atomic_t @state_var field. */ if (desc_out) { memcpy(&desc_out->text_blk_lpos, &desc->text_blk_lpos, sizeof(desc_out->text_blk_lpos)); /* LMM(desc_read:C) */ } if (seq_out) *seq_out = info->seq; /* also part of desc_read:C */ if (caller_id_out) *caller_id_out = info->caller_id; /* also part of desc_read:C */
/* * 1. Guarantee the descriptor content is loaded before re-checking * the state. This avoids reading an obsolete descriptor state * that may not apply to the copied content. This pairs with * desc_reserve:F. * * Memory barrier involvement: * * If desc_read:C reads from desc_reserve:G, then desc_read:E * reads from desc_reserve:F. * * Relies on: * * WMB from desc_reserve:F to desc_reserve:G * matching * RMB from desc_read:C to desc_read:E * * 2. Guarantee the record data is loaded before re-checking the * state. This avoids reading an obsolete descriptor state that may * not apply to the copied data. This pairs with data_alloc:A and * data_realloc:A. * * Memory barrier involvement: * * If copy_data:A reads from data_alloc:B, then desc_read:E * reads from desc_make_reusable:A. * * Relies on: * * MB from desc_make_reusable:A to data_alloc:B * matching * RMB from desc_read:C to desc_read:E * * Note: desc_make_reusable:A and data_alloc:B can be different * CPUs. However, the data_alloc:B CPU (which performs the * full memory barrier) must have previously seen * desc_make_reusable:A. */ smp_rmb(); /* LMM(desc_read:D) */
/* * The data has been copied. Return the current descriptor state, * which may have changed since the load above. */ state_val = atomic_long_read(state_var); /* LMM(desc_read:E) */ d_state = get_desc_state(id, state_val);out: if (desc_out) atomic_long_set(&desc_out->state_var, state_val); return d_state;}
/* * Take a specified descriptor out of the finalized state by attempting * the transition from finalized to reusable. Either this context or some * other context will have been successful. */static void desc_make_reusable(struct prb_desc_ring *desc_ring, unsigned long id){ unsigned long val_finalized = DESC_SV(id, desc_finalized); unsigned long val_reusable = DESC_SV(id, desc_reusable); struct prb_desc *desc = to_desc(desc_ring, id); atomic_long_t *state_var = &desc->state_var;
atomic_long_cmpxchg_relaxed(state_var, val_finalized, val_reusable); /* LMM(desc_make_reusable:A) */}
/* * Given the text data ring, put the associated descriptor of each * data block from @lpos_begin until @lpos_end into the reusable state. * * If there is any problem making the associated descriptor reusable, either * the descriptor has not yet been finalized or another writer context has * already pushed the tail lpos past the problematic data block. Regardless, * on error the caller can re-load the tail lpos to determine the situation. */static bool data_make_reusable(struct printk_ringbuffer *rb, unsigned long lpos_begin, unsigned long lpos_end, unsigned long *lpos_out){
struct prb_data_ring *data_ring = &rb->text_data_ring; struct prb_desc_ring *desc_ring = &rb->desc_ring; struct prb_data_block *blk; enum desc_state d_state; struct prb_desc desc; struct prb_data_blk_lpos *blk_lpos = &desc.text_blk_lpos; unsigned long id;
/* Loop until @lpos_begin has advanced to or beyond @lpos_end. */ while (need_more_space(data_ring, lpos_begin, lpos_end)) { blk = to_block(data_ring, lpos_begin);
/* * Load the block ID from the data block. This is a data race * against a writer that may have newly reserved this data * area. If the loaded value matches a valid descriptor ID, * the blk_lpos of that descriptor will be checked to make * sure it points back to this data block. If the check fails, * the data area has been recycled by another writer. */ id = blk->id; /* LMM(data_make_reusable:A) */
d_state = desc_read(desc_ring, id, &desc, NULL, NULL); /* LMM(data_make_reusable:B) */
switch (d_state) { case desc_miss: case desc_reserved: case desc_committed: return false; case desc_finalized: /* * This data block is invalid if the descriptor * does not point back to it. */ if (blk_lpos->begin != lpos_begin) return false; desc_make_reusable(desc_ring, id); break; case desc_reusable: /* * This data block is invalid if the descriptor * does not point back to it. */ if (blk_lpos->begin != lpos_begin) return false; break; }
/* Advance @lpos_begin to the next data block. */ lpos_begin = blk_lpos->next; }
*lpos_out = lpos_begin; return true;}
/* * Advance the data ring tail to at least @lpos. This function puts * descriptors into the reusable state if the tail is pushed beyond * their associated data block. */static bool data_push_tail(struct printk_ringbuffer *rb, unsigned long lpos){ struct prb_data_ring *data_ring = &rb->text_data_ring; unsigned long tail_lpos_new; unsigned long tail_lpos; unsigned long next_lpos;
/* If @lpos is from a data-less block, there is nothing to do. */ if (LPOS_DATALESS(lpos)) return true;
/* * Any descriptor states that have transitioned to reusable due to the * data tail being pushed to this loaded value will be visible to this * CPU. This pairs with data_push_tail:D. * * Memory barrier involvement: * * If data_push_tail:A reads from data_push_tail:D, then this CPU can * see desc_make_reusable:A. * * Relies on: * * MB from desc_make_reusable:A to data_push_tail:D * matches * READFROM from data_push_tail:D to data_push_tail:A * thus * READFROM from desc_make_reusable:A to this CPU */ tail_lpos = atomic_long_read(&data_ring->tail_lpos); /* LMM(data_push_tail:A) */
/* * Loop until the tail lpos is at or beyond @lpos. This condition * may already be satisfied, resulting in no full memory barrier * from data_push_tail:D being performed. However, since this CPU * sees the new tail lpos, any descriptor states that transitioned to * the reusable state must already be visible. */ while (need_more_space(data_ring, tail_lpos, lpos)) { /* * Make all descriptors reusable that are associated with * data blocks before @lpos. */ if (!data_make_reusable(rb, tail_lpos, lpos, &next_lpos)) { /* * 1. Guarantee the block ID loaded in * data_make_reusable() is performed before * reloading the tail lpos. The failed * data_make_reusable() may be due to a newly * recycled data area causing the tail lpos to * have been previously pushed. This pairs with * data_alloc:A and data_realloc:A. * * Memory barrier involvement: * * If data_make_reusable:A reads from data_alloc:B, * then data_push_tail:C reads from * data_push_tail:D. * * Relies on: * * MB from data_push_tail:D to data_alloc:B * matching * RMB from data_make_reusable:A to * data_push_tail:C * * Note: data_push_tail:D and data_alloc:B can be * different CPUs. However, the data_alloc:B * CPU (which performs the full memory * barrier) must have previously seen * data_push_tail:D. * * 2. Guarantee the descriptor state loaded in * data_make_reusable() is performed before * reloading the tail lpos. The failed * data_make_reusable() may be due to a newly * recycled descriptor causing the tail lpos to * have been previously pushed. This pairs with * desc_reserve:D. * * Memory barrier involvement: * * If data_make_reusable:B reads from * desc_reserve:F, then data_push_tail:C reads * from data_push_tail:D. * * Relies on: * * MB from data_push_tail:D to desc_reserve:F * matching * RMB from data_make_reusable:B to * data_push_tail:C * * Note: data_push_tail:D and desc_reserve:F can * be different CPUs. However, the * desc_reserve:F CPU (which performs the * full memory barrier) must have previously * seen data_push_tail:D. */ smp_rmb(); /* LMM(data_push_tail:B) */
tail_lpos_new = atomic_long_read(&data_ring->tail_lpos ); /* LMM(data_push_tail:C) */ if (tail_lpos_new == tail_lpos) return false;
/* Another CPU pushed the tail. Try again. */ tail_lpos = tail_lpos_new; continue; }
/* * Guarantee any descriptor states that have transitioned to * reusable are stored before pushing the tail lpos. A full * memory barrier is needed since other CPUs may have made * the descriptor states reusable. This pairs with * data_push_tail:A. */ if (atomic_long_try_cmpxchg(&data_ring->tail_lpos, &tail_lpos, next_lpos)) { /* LMM(data_push_tail:D) */ break; } }
return true;}
/* * Advance the desc ring tail. This function advances the tail by one * descriptor, thus invalidating the oldest descriptor. Before advancing * the tail, the tail descriptor is made reusable and all data blocks up to * and including the descriptor's data block are invalidated (i.e. the data * ring tail is pushed past the data block of the descriptor being made * reusable). */static bool desc_push_tail(struct printk_ringbuffer *rb, unsigned long tail_id){ struct prb_desc_ring *desc_ring = &rb->desc_ring; enum desc_state d_state; struct prb_desc desc;
d_state = desc_read(desc_ring, tail_id, &desc, NULL, NULL);
switch (d_state) { case desc_miss: /* * If the ID is exactly 1 wrap behind the expected, it is * in the process of being reserved by another writer and * must be considered reserved. */ if (DESC_ID(atomic_long_read(&desc.state_var)) == DESC_ID_PREV_WRAP(desc_ring, tail_id)) { return false; }
/* * The ID has changed. Another writer must have pushed the * tail and recycled the descriptor already. Success is * returned because the caller is only interested in the * specified tail being pushed, which it was. */ return true; case desc_reserved: case desc_committed: return false; case desc_finalized: desc_make_reusable(desc_ring, tail_id); break; case desc_reusable: break; }
/* * Data blocks must be invalidated before their associated * descriptor can be made available for recycling. Invalidating * them later is not possible because there is no way to trust * data blocks once their associated descriptor is gone. */
if (!data_push_tail(rb, desc.text_blk_lpos.next)) return false;
/* * Check the next descriptor after @tail_id before pushing the tail * to it because the tail must always be in a finalized or reusable * state. The implementation of prb_first_seq() relies on this. * * A successful read implies that the next descriptor is less than or * equal to @head_id so there is no risk of pushing the tail past the * head. */ d_state = desc_read(desc_ring, DESC_ID(tail_id + 1), &desc, NULL, NULL); /* LMM(desc_push_tail:A) */
if (d_state == desc_finalized || d_state == desc_reusable) { /* * Guarantee any descriptor states that have transitioned to * reusable are stored before pushing the tail ID. This allows * verifying the recycled descriptor state. A full memory * barrier is needed since other CPUs may have made the * descriptor states reusable. This pairs with desc_reserve:D. */ atomic_long_cmpxchg(&desc_ring->tail_id, tail_id, DESC_ID(tail_id + 1)); /* LMM(desc_push_tail:B) */ } else { /* * Guarantee the last state load from desc_read() is before * reloading @tail_id in order to see a new tail ID in the * case that the descriptor has been recycled. This pairs * with desc_reserve:D. * * Memory barrier involvement: * * If desc_push_tail:A reads from desc_reserve:F, then * desc_push_tail:D reads from desc_push_tail:B. * * Relies on: * * MB from desc_push_tail:B to desc_reserve:F * matching * RMB from desc_push_tail:A to desc_push_tail:D * * Note: desc_push_tail:B and desc_reserve:F can be different * CPUs. However, the desc_reserve:F CPU (which performs * the full memory barrier) must have previously seen * desc_push_tail:B. */ smp_rmb(); /* LMM(desc_push_tail:C) */
/* * Re-check the tail ID. The descriptor following @tail_id is * not in an allowed tail state. But if the tail has since * been moved by another CPU, then it does not matter. */ if (atomic_long_read(&desc_ring->tail_id) == tail_id) /* LMM(desc_push_tail:D) */ return false; }
return true;}
/* Reserve a new descriptor, invalidating the oldest if necessary. */static bool desc_reserve(struct printk_ringbuffer *rb, unsigned long *id_out){ struct prb_desc_ring *desc_ring = &rb->desc_ring; unsigned long prev_state_val; unsigned long id_prev_wrap; struct prb_desc *desc; unsigned long head_id; unsigned long id;
head_id = atomic_long_read(&desc_ring->head_id); /* LMM(desc_reserve:A) */
do { id = DESC_ID(head_id + 1); id_prev_wrap = DESC_ID_PREV_WRAP(desc_ring, id);
/* * Guarantee the head ID is read before reading the tail ID. * Since the tail ID is updated before the head ID, this * guarantees that @id_prev_wrap is never ahead of the tail * ID. This pairs with desc_reserve:D. * * Memory barrier involvement: * * If desc_reserve:A reads from desc_reserve:D, then * desc_reserve:C reads from desc_push_tail:B. * * Relies on: * * MB from desc_push_tail:B to desc_reserve:D * matching * RMB from desc_reserve:A to desc_reserve:C * * Note: desc_push_tail:B and desc_reserve:D can be different * CPUs. However, the desc_reserve:D CPU (which performs * the full memory barrier) must have previously seen * desc_push_tail:B. */ smp_rmb(); /* LMM(desc_reserve:B) */
if (id_prev_wrap == atomic_long_read(&desc_ring->tail_id )) { /* LMM(desc_reserve:C) */ /* * Make space for the new descriptor by * advancing the tail. */ if (!desc_push_tail(rb, id_prev_wrap)) return false; }
/* * 1. Guarantee the tail ID is read before validating the * recycled descriptor state. A read memory barrier is * sufficient for this. This pairs with desc_push_tail:B. * * Memory barrier involvement: * * If desc_reserve:C reads from desc_push_tail:B, then * desc_reserve:E reads from desc_make_reusable:A. * * Relies on: * * MB from desc_make_reusable:A to desc_push_tail:B * matching * RMB from desc_reserve:C to desc_reserve:E * * Note: desc_make_reusable:A and desc_push_tail:B can be * different CPUs. However, the desc_push_tail:B CPU * (which performs the full memory barrier) must have * previously seen desc_make_reusable:A. * * 2. Guarantee the tail ID is stored before storing the head * ID. This pairs with desc_reserve:B. * * 3. Guarantee any data ring tail changes are stored before * recycling the descriptor. Data ring tail changes can * happen via desc_push_tail()->data_push_tail(). A full * memory barrier is needed since another CPU may have * pushed the data ring tails. This pairs with * data_push_tail:B. * * 4. Guarantee a new tail ID is stored before recycling the * descriptor. A full memory barrier is needed since * another CPU may have pushed the tail ID. This pairs * with desc_push_tail:C and this also pairs with * prb_first_seq:C. * * 5. Guarantee the head ID is stored before trying to * finalize the previous descriptor. This pairs with * _prb_commit:B. */ } while (!atomic_long_try_cmpxchg(&desc_ring->head_id, &head_id, id)); /* LMM(desc_reserve:D) */
desc = to_desc(desc_ring, id);
/* * If the descriptor has been recycled, verify the old state val. * See "ABA Issues" about why this verification is performed. */ prev_state_val = atomic_long_read(&desc->state_var); /* LMM(desc_reserve:E) */ if (prev_state_val && get_desc_state(id_prev_wrap, prev_state_val) != desc_reusable) { WARN_ON_ONCE(1); return false; }
/* * Assign the descriptor a new ID and set its state to reserved. * See "ABA Issues" about why cmpxchg() instead of set() is used. * * Guarantee the new descriptor ID and state is stored before making * any other changes. A write memory barrier is sufficient for this. * This pairs with desc_read:D. */ if (!atomic_long_try_cmpxchg(&desc->state_var, &prev_state_val, DESC_SV(id, desc_reserved))) { /* LMM(desc_reserve:F) */ WARN_ON_ONCE(1); return false; }
/* Now data in @desc can be modified: LMM(desc_reserve:G) */
*id_out = id; return true;}
static bool is_blk_wrapped(struct prb_data_ring *data_ring, unsigned long begin_lpos, unsigned long next_lpos){ /* * Subtract one from next_lpos since it's not actually part of this data * block. This allows perfectly fitting records to not wrap. */ return DATA_WRAPS(data_ring, begin_lpos) != DATA_WRAPS(data_ring, next_lpos - 1);}
/* Determine the end of a data block. */static unsigned long get_next_lpos(struct prb_data_ring *data_ring, unsigned long lpos, unsigned int size){ unsigned long begin_lpos; unsigned long next_lpos;
begin_lpos = lpos; next_lpos = lpos + size;
/* First check if the data block does not wrap. */ if (!is_blk_wrapped(data_ring, begin_lpos, next_lpos)) return next_lpos;
/* Wrapping data blocks store their data at the beginning. */ return (DATA_THIS_WRAP_START_LPOS(data_ring, next_lpos) + size);}
/* * Allocate a new data block, invalidating the oldest data block(s) * if necessary. This function also associates the data block with * a specified descriptor. */static char *data_alloc(struct printk_ringbuffer *rb, unsigned int size, struct prb_data_blk_lpos *blk_lpos, unsigned long id){ struct prb_data_ring *data_ring = &rb->text_data_ring; struct prb_data_block *blk; unsigned long begin_lpos; unsigned long next_lpos;
if (size == 0) { /* * Data blocks are not created for empty lines. Instead, the * reader will recognize these special lpos values and handle * it appropriately. */ blk_lpos->begin = EMPTY_LINE_LPOS; blk_lpos->next = EMPTY_LINE_LPOS; return NULL; }
size = to_blk_size(size);
begin_lpos = atomic_long_read(&data_ring->head_lpos);
do { next_lpos = get_next_lpos(data_ring, begin_lpos, size);
/* * data_check_size() prevents data block allocation that could * cause illegal ringbuffer states. But double check that the * used space will not be bigger than the ring buffer. Wrapped * messages need to reserve more space, see get_next_lpos(). * * Specify a data-less block when the check or the allocation * fails. */ if (WARN_ON_ONCE(next_lpos - begin_lpos > DATA_SIZE(data_ring)) || !data_push_tail(rb, next_lpos - DATA_SIZE(data_ring))) { blk_lpos->begin = FAILED_LPOS; blk_lpos->next = FAILED_LPOS; return NULL; }
/* * 1. Guarantee any descriptor states that have transitioned * to reusable are stored before modifying the newly * allocated data area. A full memory barrier is needed * since other CPUs may have made the descriptor states * reusable. See data_push_tail:A about why the reusable * states are visible. This pairs with desc_read:D. * * 2. Guarantee any updated tail lpos is stored before * modifying the newly allocated data area. Another CPU may * be in data_make_reusable() and is reading a block ID * from this area. data_make_reusable() can handle reading * a garbage block ID value, but then it must be able to * load a new tail lpos. A full memory barrier is needed * since other CPUs may have updated the tail lpos. This * pairs with data_push_tail:B. */ } while (!atomic_long_try_cmpxchg(&data_ring->head_lpos, &begin_lpos, next_lpos)); /* LMM(data_alloc:A) */
blk = to_block(data_ring, begin_lpos); blk->id = id; /* LMM(data_alloc:B) */
if (is_blk_wrapped(data_ring, begin_lpos, next_lpos)) { /* Wrapping data blocks store their data at the beginning. */ blk = to_block(data_ring, 0);
/* * Store the ID on the wrapped block for consistency. * The printk_ringbuffer does not actually use it. */ blk->id = id; }
blk_lpos->begin = begin_lpos; blk_lpos->next = next_lpos;
return &blk->data[0];}
/* * Try to resize an existing data block associated with the descriptor * specified by @id. If the resized data block should become wrapped, it * copies the old data to the new data block. If @size yields a data block * with the same or less size, the data block is left as is. * * Fail if this is not the last allocated data block or if there is not * enough space or it is not possible make enough space. * * Return a pointer to the beginning of the entire data buffer or NULL on * failure. */static char *data_realloc(struct printk_ringbuffer *rb, unsigned int size, struct prb_data_blk_lpos *blk_lpos, unsigned long id){ struct prb_data_ring *data_ring = &rb->text_data_ring; struct prb_data_block *blk; unsigned long head_lpos; unsigned long next_lpos; bool wrapped;
/* Reallocation only works if @blk_lpos is the newest data block. */ head_lpos = atomic_long_read(&data_ring->head_lpos); if (head_lpos != blk_lpos->next) return NULL;
/* Keep track if @blk_lpos was a wrapping data block. */ wrapped = is_blk_wrapped(data_ring, blk_lpos->begin, blk_lpos->next);
size = to_blk_size(size);
next_lpos = get_next_lpos(data_ring, blk_lpos->begin, size);
/* * Use the current data block when the size does not increase, i.e. * when @head_lpos is already able to accommodate the new @next_lpos. * * Note that need_more_space() could never return false here because * the difference between the positions was bigger than the data * buffer size. The data block is reopened and can't get reused. */ if (!need_more_space(data_ring, head_lpos, next_lpos)) { if (wrapped) blk = to_block(data_ring, 0); else blk = to_block(data_ring, blk_lpos->begin); return &blk->data[0]; }
/* * data_check_size() prevents data block reallocation that could * cause illegal ringbuffer states. But double check that the * new used space will not be bigger than the ring buffer. Wrapped * messages need to reserve more space, see get_next_lpos(). * * Specify failure when the check or the allocation fails. */ if (WARN_ON_ONCE(next_lpos - blk_lpos->begin > DATA_SIZE(data_ring)) || !data_push_tail(rb, next_lpos - DATA_SIZE(data_ring))) { return NULL; }
/* The memory barrier involvement is the same as data_alloc:A. */ if (!atomic_long_try_cmpxchg(&data_ring->head_lpos, &head_lpos, next_lpos)) { /* LMM(data_realloc:A) */ return NULL; }
blk = to_block(data_ring, blk_lpos->begin);
if (is_blk_wrapped(data_ring, blk_lpos->begin, next_lpos)) { struct prb_data_block *old_blk = blk;
/* Wrapping data blocks store their data at the beginning. */ blk = to_block(data_ring, 0);
/* * Store the ID on the wrapped block for consistency. * The printk_ringbuffer does not actually use it. */ blk->id = id;
if (!wrapped) { /* * Since the allocated space is now in the newly * created wrapping data block, copy the content * from the old data block. */ memcpy(&blk->data[0], &old_blk->data[0], (blk_lpos->next - blk_lpos->begin) - sizeof(blk->id)); } }
blk_lpos->next = next_lpos;
return &blk->data[0];}
/* Return the number of bytes used by a data block. */static unsigned int space_used(struct prb_data_ring *data_ring, struct prb_data_blk_lpos *blk_lpos){ /* Data-less blocks take no space. */ if (BLK_DATALESS(blk_lpos)) return 0;
if (!is_blk_wrapped(data_ring, blk_lpos->begin, blk_lpos->next)) { /* Data block does not wrap. */ return (DATA_INDEX(data_ring, blk_lpos->next) - DATA_INDEX(data_ring, blk_lpos->begin)); }
/* * For wrapping data blocks, the trailing (wasted) space is * also counted. */ return (DATA_INDEX(data_ring, blk_lpos->next) + DATA_SIZE(data_ring) - DATA_INDEX(data_ring, blk_lpos->begin));}
/* * Given @blk_lpos, return a pointer to the writer data from the data block * and calculate the size of the data part. A NULL pointer is returned if * @blk_lpos specifies values that could never be legal. * * This function (used by readers) performs strict validation on the lpos * values to possibly detect bugs in the writer code. A WARN_ON_ONCE() is * triggered if an internal error is detected. */static const char *get_data(struct prb_data_ring *data_ring, struct prb_data_blk_lpos *blk_lpos, unsigned int *data_size){ struct prb_data_block *db;
/* Data-less data block description. */ if (BLK_DATALESS(blk_lpos)) { /* * Records that are just empty lines are also valid, even * though they do not have a data block. For such records * explicitly return empty string data to signify success. */ if (blk_lpos->begin == EMPTY_LINE_LPOS && blk_lpos->next == EMPTY_LINE_LPOS) { *data_size = 0; return ""; }
/* Data lost, invalid, or otherwise unavailable. */ return NULL; }
/* Regular data block: @begin and @next in the same wrap. */ if (!is_blk_wrapped(data_ring, blk_lpos->begin, blk_lpos->next)) { db = to_block(data_ring, blk_lpos->begin); *data_size = blk_lpos->next - blk_lpos->begin;
/* Wrapping data block: @begin is one wrap behind @next. */ } else if (!is_blk_wrapped(data_ring, blk_lpos->begin + DATA_SIZE(data_ring), blk_lpos->next)) { db = to_block(data_ring, 0); *data_size = DATA_INDEX(data_ring, blk_lpos->next);
/* Illegal block description. */ } else { WARN_ON_ONCE(1); return NULL; }
/* A valid data block will always be aligned to the ID size. */ if (WARN_ON_ONCE(blk_lpos->begin != ALIGN(blk_lpos->begin, sizeof(db->id))) || WARN_ON_ONCE(blk_lpos->next != ALIGN(blk_lpos->next, sizeof(db->id)))) { return NULL; }
/* * A regular data block will always have an ID and at least * 1 byte of data. Data-less blocks were handled earlier. */ if (WARN_ON_ONCE(*data_size <= sizeof(db->id))) return NULL;
/* Subtract block ID space from size to reflect data size. */ *data_size -= sizeof(db->id);
/* Sanity check the max size of the regular data block. */ if (WARN_ON_ONCE(!data_check_size(data_ring, *data_size))) return NULL;
return &db->data[0];}
/* * Attempt to transition the newest descriptor from committed back to reserved * so that the record can be modified by a writer again. This is only possible * if the descriptor is not yet finalized and the provided @caller_id matches. */static struct prb_desc *desc_reopen_last(struct prb_desc_ring *desc_ring, u32 caller_id, unsigned long *id_out){ unsigned long prev_state_val; enum desc_state d_state; struct prb_desc desc; struct prb_desc *d; unsigned long id; u32 cid;
id = atomic_long_read(&desc_ring->head_id);
/* * To reduce unnecessarily reopening, first check if the descriptor * state and caller ID are correct. */ d_state = desc_read(desc_ring, id, &desc, NULL, &cid); if (d_state != desc_committed || cid != caller_id) return NULL;
d = to_desc(desc_ring, id);
prev_state_val = DESC_SV(id, desc_committed);
/* * Guarantee the reserved state is stored before reading any * record data. A full memory barrier is needed because @state_var * modification is followed by reading. This pairs with _prb_commit:B. * * Memory barrier involvement: * * If desc_reopen_last:A reads from _prb_commit:B, then * prb_reserve_in_last:A reads from _prb_commit:A. * * Relies on: * * WMB from _prb_commit:A to _prb_commit:B * matching * MB from desc_reopen_last:A to prb_reserve_in_last:A */ if (!atomic_long_try_cmpxchg(&d->state_var, &prev_state_val, DESC_SV(id, desc_reserved))) { /* LMM(desc_reopen_last:A) */ return NULL; }
*id_out = id; return d;}
/** * prb_reserve_in_last() - Re-reserve and extend the space in the ringbuffer * used by the newest record. * * @e: The entry structure to setup. * @rb: The ringbuffer to re-reserve and extend data in. * @r: The record structure to allocate buffers for. * @caller_id: The caller ID of the caller (reserving writer). * @max_size: Fail if the extended size would be greater than this. * * This is the public function available to writers to re-reserve and extend * data. * * The writer specifies the text size to extend (not the new total size) by * setting the @text_buf_size field of @r. To ensure proper initialization * of @r, prb_rec_init_wr() should be used. * * This function will fail if @caller_id does not match the caller ID of the * newest record. In that case the caller must reserve new data using * prb_reserve(). * * Context: Any context. Disables local interrupts on success. * Return: true if text data could be extended, otherwise false. * * On success: * * - @r->text_buf points to the beginning of the entire text buffer. * * - @r->text_buf_size is set to the new total size of the buffer. * * - @r->info is not touched so that @r->info->text_len could be used * to append the text. * * - prb_record_text_space() can be used on @e to query the new * actually used space. * * Important: All @r->info fields will already be set with the current values * for the record. I.e. @r->info->text_len will be less than * @text_buf_size. Writers can use @r->info->text_len to know * where concatenation begins and writers should update * @r->info->text_len after concatenating. */bool prb_reserve_in_last(struct prb_reserved_entry *e, struct printk_ringbuffer *rb, struct printk_record *r, u32 caller_id, unsigned int max_size){ struct prb_desc_ring *desc_ring = &rb->desc_ring; struct printk_info *info; unsigned int data_size; struct prb_desc *d; unsigned long id;
local_irq_save(e->irqflags);
/* Transition the newest descriptor back to the reserved state. */ d = desc_reopen_last(desc_ring, caller_id, &id); if (!d) { local_irq_restore(e->irqflags); goto fail_reopen; }
/* Now the writer has exclusive access: LMM(prb_reserve_in_last:A) */
info = to_info(desc_ring, id);
/* * Set the @e fields here so that prb_commit() can be used if * anything fails from now on. */ e->rb = rb; e->id = id;
/* * desc_reopen_last() checked the caller_id, but there was no * exclusive access at that point. The descriptor may have * changed since then. */ if (caller_id != info->caller_id) goto fail;
if (BLK_DATALESS(&d->text_blk_lpos)) { if (WARN_ON_ONCE(info->text_len != 0)) { pr_warn_once("wrong text_len value (%hu, expecting 0)\n", info->text_len); info->text_len = 0; }
if (!data_check_size(&rb->text_data_ring, r->text_buf_size)) goto fail;
if (r->text_buf_size > max_size) goto fail;
r->text_buf = data_alloc(rb, r->text_buf_size, &d->text_blk_lpos, id); } else { if (!get_data(&rb->text_data_ring, &d->text_blk_lpos, &data_size)) goto fail;
/* * Increase the buffer size to include the original size. If * the meta data (@text_len) is not sane, use the full data * block size. */ if (WARN_ON_ONCE(info->text_len > data_size)) { pr_warn_once("wrong text_len value (%hu, expecting <=%u)\n", info->text_len, data_size); info->text_len = data_size; } r->text_buf_size += info->text_len;
if (!data_check_size(&rb->text_data_ring, r->text_buf_size)) goto fail;
if (r->text_buf_size > max_size) goto fail;
r->text_buf = data_realloc(rb, r->text_buf_size, &d->text_blk_lpos, id); } if (r->text_buf_size && !r->text_buf) goto fail;
r->info = info;
e->text_space = space_used(&rb->text_data_ring, &d->text_blk_lpos);
return true;fail: prb_commit(e); /* prb_commit() re-enabled interrupts. */fail_reopen: /* Make it clear to the caller that the re-reserve failed. */ memset(r, 0, sizeof(*r)); return false;}
/* * @last_finalized_seq value guarantees that all records up to and including * this sequence number are finalized and can be read. The only exception are * too old records which have already been overwritten. * * It is also guaranteed that @last_finalized_seq only increases. * * Be aware that finalized records following non-finalized records are not * reported because they are not yet available to the reader. For example, * a new record stored via printk() will not be available to a printer if * it follows a record that has not been finalized yet. However, once that * non-finalized record becomes finalized, @last_finalized_seq will be * appropriately updated and the full set of finalized records will be * available to the printer. And since each printk() caller will either * directly print or trigger deferred printing of all available unprinted * records, all printk() messages will get printed. */static u64 desc_last_finalized_seq(struct printk_ringbuffer *rb){ struct prb_desc_ring *desc_ring = &rb->desc_ring; unsigned long ulseq;
/* * Guarantee the sequence number is loaded before loading the * associated record in order to guarantee that the record can be * seen by this CPU. This pairs with desc_update_last_finalized:A. */ ulseq = atomic_long_read_acquire(&desc_ring->last_finalized_seq ); /* LMM(desc_last_finalized_seq:A) */
return __ulseq_to_u64seq(rb, ulseq);}
static bool _prb_read_valid(struct printk_ringbuffer *rb, u64 *seq, struct printk_record *r, unsigned int *line_count);
/* * Check if there are records directly following @last_finalized_seq that are * finalized. If so, update @last_finalized_seq to the latest of these * records. It is not allowed to skip over records that are not yet finalized. */static void desc_update_last_finalized(struct printk_ringbuffer *rb){ struct prb_desc_ring *desc_ring = &rb->desc_ring; u64 old_seq = desc_last_finalized_seq(rb); unsigned long oldval; unsigned long newval; u64 finalized_seq; u64 try_seq;
try_again: finalized_seq = old_seq; try_seq = finalized_seq + 1;
/* Try to find later finalized records. */ while (_prb_read_valid(rb, &try_seq, NULL, NULL)) { finalized_seq = try_seq; try_seq++; }
/* No update needed if no later finalized record was found. */ if (finalized_seq == old_seq) return;
oldval = __u64seq_to_ulseq(old_seq); newval = __u64seq_to_ulseq(finalized_seq);
/* * Set the sequence number of a later finalized record that has been * seen. * * Guarantee the record data is visible to other CPUs before storing * its sequence number. This pairs with desc_last_finalized_seq:A. * * Memory barrier involvement: * * If desc_last_finalized_seq:A reads from * desc_update_last_finalized:A, then desc_read:A reads from * _prb_commit:B. * * Relies on: * * RELEASE from _prb_commit:B to desc_update_last_finalized:A * matching * ACQUIRE from desc_last_finalized_seq:A to desc_read:A * * Note: _prb_commit:B and desc_update_last_finalized:A can be * different CPUs. However, the desc_update_last_finalized:A * CPU (which performs the release) must have previously seen * _prb_commit:B. */ if (!atomic_long_try_cmpxchg_release(&desc_ring->last_finalized_seq, &oldval, newval)) { /* LMM(desc_update_last_finalized:A) */ old_seq = __ulseq_to_u64seq(rb, oldval); goto try_again; }}
/* * Attempt to finalize a specified descriptor. If this fails, the descriptor * is either already final or it will finalize itself when the writer commits. */static void desc_make_final(struct printk_ringbuffer *rb, unsigned long id){ struct prb_desc_ring *desc_ring = &rb->desc_ring; unsigned long prev_state_val = DESC_SV(id, desc_committed); struct prb_desc *d = to_desc(desc_ring, id);
if (atomic_long_try_cmpxchg_relaxed(&d->state_var, &prev_state_val, DESC_SV(id, desc_finalized))) { /* LMM(desc_make_final:A) */ desc_update_last_finalized(rb); }}
/** * prb_reserve() - Reserve space in the ringbuffer. * * @e: The entry structure to setup. * @rb: The ringbuffer to reserve data in. * @r: The record structure to allocate buffers for. * * This is the public function available to writers to reserve data. * * The writer specifies the text size to reserve by setting the * @text_buf_size field of @r. To ensure proper initialization of @r, * prb_rec_init_wr() should be used. * * Context: Any context. Disables local interrupts on success. * Return: true if at least text data could be allocated, otherwise false. * * On success, the fields @info and @text_buf of @r will be set by this * function and should be filled in by the writer before committing. Also * on success, prb_record_text_space() can be used on @e to query the actual * space used for the text data block. * * Important: @info->text_len needs to be set correctly by the writer in * order for data to be readable and/or extended. Its value * is initialized to 0. */bool prb_reserve(struct prb_reserved_entry *e, struct printk_ringbuffer *rb, struct printk_record *r){ struct prb_desc_ring *desc_ring = &rb->desc_ring; struct printk_info *info; struct prb_desc *d; unsigned long id; u64 seq;
if (!data_check_size(&rb->text_data_ring, r->text_buf_size)) goto fail;
/* * Descriptors in the reserved state act as blockers to all further * reservations once the desc_ring has fully wrapped. Disable * interrupts during the reserve/commit window in order to minimize * the likelihood of this happening. */ local_irq_save(e->irqflags);
if (!desc_reserve(rb, &id)) { /* Descriptor reservation failures are tracked. */ atomic_long_inc(&rb->fail); local_irq_restore(e->irqflags); goto fail; }
d = to_desc(desc_ring, id); info = to_info(desc_ring, id);
/* * All @info fields (except @seq) are cleared and must be filled in * by the writer. Save @seq before clearing because it is used to * determine the new sequence number. */ seq = info->seq; memset(info, 0, sizeof(*info));
/* * Set the @e fields here so that prb_commit() can be used if * text data allocation fails. */ e->rb = rb; e->id = id;
/* * Initialize the sequence number if it has "never been set". * Otherwise just increment it by a full wrap. * * @seq is considered "never been set" if it has a value of 0, * _except_ for @infos[0], which was specially setup by the ringbuffer * initializer and therefore is always considered as set. * * See the "Bootstrap" comment block in printk_ringbuffer.h for * details about how the initializer bootstraps the descriptors. */ if (seq == 0 && DESC_INDEX(desc_ring, id) != 0) info->seq = DESC_INDEX(desc_ring, id); else info->seq = seq + DESCS_COUNT(desc_ring);
/* * New data is about to be reserved. Once that happens, previous * descriptors are no longer able to be extended. Finalize the * previous descriptor now so that it can be made available to * readers. (For seq==0 there is no previous descriptor.) */ if (info->seq > 0) desc_make_final(rb, DESC_ID(id - 1));
r->text_buf = data_alloc(rb, r->text_buf_size, &d->text_blk_lpos, id); /* If text data allocation fails, a data-less record is committed. */ if (r->text_buf_size && !r->text_buf) { prb_commit(e); /* prb_commit() re-enabled interrupts. */ goto fail; }
r->info = info;
/* Record full text space used by record. */ e->text_space = space_used(&rb->text_data_ring, &d->text_blk_lpos);
return true;fail: /* Make it clear to the caller that the reserve failed. */ memset(r, 0, sizeof(*r)); return false;}EXPORT_SYMBOL_IF_KUNIT(prb_reserve);
/* Commit the data (possibly finalizing it) and restore interrupts. */static void _prb_commit(struct prb_reserved_entry *e, unsigned long state_val){ struct prb_desc_ring *desc_ring = &e->rb->desc_ring; struct prb_desc *d = to_desc(desc_ring, e->id); unsigned long prev_state_val = DESC_SV(e->id, desc_reserved);
/* Now the writer has finished all writing: LMM(_prb_commit:A) */
/* * Set the descriptor as committed. See "ABA Issues" about why * cmpxchg() instead of set() is used. * * 1 Guarantee all record data is stored before the descriptor state * is stored as committed. A write memory barrier is sufficient * for this. This pairs with desc_read:B and desc_reopen_last:A. * * 2. Guarantee the descriptor state is stored as committed before * re-checking the head ID in order to possibly finalize this * descriptor. This pairs with desc_reserve:D. * * Memory barrier involvement: * * If prb_commit:A reads from desc_reserve:D, then * desc_make_final:A reads from _prb_commit:B. * * Relies on: * * MB from _prb_commit:B to prb_commit:A * matching * MB from desc_reserve:D to desc_make_final:A */ if (!atomic_long_try_cmpxchg(&d->state_var, &prev_state_val, DESC_SV(e->id, state_val))) { /* LMM(_prb_commit:B) */ WARN_ON_ONCE(1); }
/* Restore interrupts, the reserve/commit window is finished. */ local_irq_restore(e->irqflags);}
/** * prb_commit() - Commit (previously reserved) data to the ringbuffer. * * @e: The entry containing the reserved data information. * * This is the public function available to writers to commit data. * * Note that the data is not yet available to readers until it is finalized. * Finalizing happens automatically when space for the next record is * reserved. * * See prb_final_commit() for a version of this function that finalizes * immediately. * * Context: Any context. Enables local interrupts. */void prb_commit(struct prb_reserved_entry *e){ struct prb_desc_ring *desc_ring = &e->rb->desc_ring; unsigned long head_id;
_prb_commit(e, desc_committed);
/* * If this descriptor is no longer the head (i.e. a new record has * been allocated), extending the data for this record is no longer * allowed and therefore it must be finalized. */ head_id = atomic_long_read(&desc_ring->head_id); /* LMM(prb_commit:A) */ if (head_id != e->id) desc_make_final(e->rb, e->id);}EXPORT_SYMBOL_IF_KUNIT(prb_commit);
/** * prb_final_commit() - Commit and finalize (previously reserved) data to * the ringbuffer. * * @e: The entry containing the reserved data information. * * This is the public function available to writers to commit+finalize data. * * By finalizing, the data is made immediately available to readers. * * This function should only be used if there are no intentions of extending * this data using prb_reserve_in_last(). * * Context: Any context. Enables local interrupts. */void prb_final_commit(struct prb_reserved_entry *e){ _prb_commit(e, desc_finalized);
desc_update_last_finalized(e->rb);}
/* * Count the number of lines in provided text. All text has at least 1 line * (even if @text_size is 0). Each '\n' processed is counted as an additional * line. */static unsigned int count_lines(const char *text, unsigned int text_size){ unsigned int next_size = text_size; unsigned int line_count = 1; const char *next = text;
while (next_size) { next = memchr(next, '\n', next_size); if (!next) break; line_count++; next++; next_size = text_size - (next - text); }
return line_count;}
/* * Given @blk_lpos, copy an expected @len of data into the provided buffer. * If @line_count is provided, count the number of lines in the data. * * This function (used by readers) performs strict validation on the data * size to possibly detect bugs in the writer code. A WARN_ON_ONCE() is * triggered if an internal error is detected. */static bool copy_data(struct prb_data_ring *data_ring, struct prb_data_blk_lpos *blk_lpos, u16 len, char *buf, unsigned int buf_size, unsigned int *line_count){ unsigned int data_size; const char *data;
/* Caller might not want any data. */ if ((!buf || !buf_size) && !line_count) return true;
data = get_data(data_ring, blk_lpos, &data_size); if (!data) return false;
/* * Actual cannot be less than expected. It can be more than expected * because of the trailing alignment padding. * * Note that invalid @len values can occur because the caller loads * the value during an allowed data race. */ if (data_size < (unsigned int)len) return false;
/* Caller interested in the line count? */ if (line_count) *line_count = count_lines(data, len);
/* Caller interested in the data content? */ if (!buf || !buf_size) return true;
data_size = min_t(unsigned int, buf_size, len);
memcpy(&buf[0], data, data_size); /* LMM(copy_data:A) */ return true;}
/* * This is an extended version of desc_read(). It gets a copy of a specified * descriptor. However, it also verifies that the record is finalized and has * the sequence number @seq. On success, 0 is returned. * * Error return values: * -EINVAL: A finalized record with sequence number @seq does not exist. * -ENOENT: A finalized record with sequence number @seq exists, but its data * is not available. This is a valid record, so readers should * continue with the next record. */static int desc_read_finalized_seq(struct prb_desc_ring *desc_ring, unsigned long id, u64 seq, struct prb_desc *desc_out){ struct prb_data_blk_lpos *blk_lpos = &desc_out->text_blk_lpos; enum desc_state d_state; u64 s;
d_state = desc_read(desc_ring, id, desc_out, &s, NULL);
/* * An unexpected @id (desc_miss) or @seq mismatch means the record * does not exist. A descriptor in the reserved or committed state * means the record does not yet exist for the reader. */ if (d_state == desc_miss || d_state == desc_reserved || d_state == desc_committed || s != seq) { return -EINVAL; }
/* * A descriptor in the reusable state may no longer have its data * available; report it as existing but with lost data. Or the record * may actually be a record with lost data. */ if (d_state == desc_reusable || (blk_lpos->begin == FAILED_LPOS && blk_lpos->next == FAILED_LPOS)) { return -ENOENT; }
return 0;}
/* * Copy the ringbuffer data from the record with @seq to the provided * @r buffer. On success, 0 is returned. * * See desc_read_finalized_seq() for error return values. */static int prb_read(struct printk_ringbuffer *rb, u64 seq, struct printk_record *r, unsigned int *line_count){ struct prb_desc_ring *desc_ring = &rb->desc_ring; struct printk_info *info = to_info(desc_ring, seq); struct prb_desc *rdesc = to_desc(desc_ring, seq); atomic_long_t *state_var = &rdesc->state_var; struct prb_desc desc; unsigned long id; int err;
/* Extract the ID, used to specify the descriptor to read. */ id = DESC_ID(atomic_long_read(state_var));
/* Get a local copy of the correct descriptor (if available). */ err = desc_read_finalized_seq(desc_ring, id, seq, &desc);
/* * If @r is NULL, the caller is only interested in the availability * of the record. */ if (err || !r) return err;
/* If requested, copy meta data. */ if (r->info) memcpy(r->info, info, sizeof(*(r->info)));
/* Copy text data. If it fails, this is a data-less record. */ if (!copy_data(&rb->text_data_ring, &desc.text_blk_lpos, info->text_len, r->text_buf, r->text_buf_size, line_count)) { return -ENOENT; }
/* Ensure the record is still finalized and has the same @seq. */ return desc_read_finalized_seq(desc_ring, id, seq, &desc);}
/* Get the sequence number of the tail descriptor. */u64 prb_first_seq(struct printk_ringbuffer *rb){ struct prb_desc_ring *desc_ring = &rb->desc_ring; enum desc_state d_state; struct prb_desc desc; unsigned long id; u64 seq;
for (;;) { id = atomic_long_read(&rb->desc_ring.tail_id); /* LMM(prb_first_seq:A) */
d_state = desc_read(desc_ring, id, &desc, &seq, NULL); /* LMM(prb_first_seq:B) */
/* * This loop will not be infinite because the tail is * _always_ in the finalized or reusable state. */ if (d_state == desc_finalized || d_state == desc_reusable) break;
/* * Guarantee the last state load from desc_read() is before * reloading @tail_id in order to see a new tail in the case * that the descriptor has been recycled. This pairs with * desc_reserve:D. * * Memory barrier involvement: * * If prb_first_seq:B reads from desc_reserve:F, then * prb_first_seq:A reads from desc_push_tail:B. * * Relies on: * * MB from desc_push_tail:B to desc_reserve:F * matching * RMB from prb_first_seq:B to prb_first_seq:A */ smp_rmb(); /* LMM(prb_first_seq:C) */ }
return seq;}
/** * prb_next_reserve_seq() - Get the sequence number after the most recently * reserved record. * * @rb: The ringbuffer to get the sequence number from. * * This is the public function available to readers to see what sequence * number will be assigned to the next reserved record. * * Note that depending on the situation, this value can be equal to or * higher than the sequence number returned by prb_next_seq(). * * Context: Any context. * Return: The sequence number that will be assigned to the next record * reserved. */u64 prb_next_reserve_seq(struct printk_ringbuffer *rb){ struct prb_desc_ring *desc_ring = &rb->desc_ring; unsigned long last_finalized_id; atomic_long_t *state_var; u64 last_finalized_seq; unsigned long head_id; struct prb_desc desc; unsigned long diff; struct prb_desc *d; int err;
/* * It may not be possible to read a sequence number for @head_id. * So the ID of @last_finailzed_seq is used to calculate what the * sequence number of @head_id will be. */
try_again: last_finalized_seq = desc_last_finalized_seq(rb);
/* * @head_id is loaded after @last_finalized_seq to ensure that * it points to the record with @last_finalized_seq or newer. * * Memory barrier involvement: * * If desc_last_finalized_seq:A reads from * desc_update_last_finalized:A, then * prb_next_reserve_seq:A reads from desc_reserve:D. * * Relies on: * * RELEASE from desc_reserve:D to desc_update_last_finalized:A * matching * ACQUIRE from desc_last_finalized_seq:A to prb_next_reserve_seq:A * * Note: desc_reserve:D and desc_update_last_finalized:A can be * different CPUs. However, the desc_update_last_finalized:A CPU * (which performs the release) must have previously seen * desc_read:C, which implies desc_reserve:D can be seen. */ head_id = atomic_long_read(&desc_ring->head_id); /* LMM(prb_next_reserve_seq:A) */
d = to_desc(desc_ring, last_finalized_seq); state_var = &d->state_var;
/* Extract the ID, used to specify the descriptor to read. */ last_finalized_id = DESC_ID(atomic_long_read(state_var));
/* Ensure @last_finalized_id is correct. */ err = desc_read_finalized_seq(desc_ring, last_finalized_id, last_finalized_seq, &desc);
if (err == -EINVAL) { if (last_finalized_seq == 0) { /* * No record has been finalized or even reserved yet. * * The @head_id is initialized such that the first * increment will yield the first record (seq=0). * Handle it separately to avoid a negative @diff * below. */ if (head_id == DESC0_ID(desc_ring->count_bits)) return 0;
/* * One or more descriptors are already reserved. Use * the descriptor ID of the first one (@seq=0) for * the @diff below. */ last_finalized_id = DESC0_ID(desc_ring->count_bits) + 1; } else { /* Record must have been overwritten. Try again. */ goto try_again; } }
/* Diff of known descriptor IDs to compute related sequence numbers. */ diff = head_id - last_finalized_id;
/* * @head_id points to the most recently reserved record, but this * function returns the sequence number that will be assigned to the * next (not yet reserved) record. Thus +1 is needed. */ return (last_finalized_seq + diff + 1);}
/* * Non-blocking read of a record. * * On success @seq is updated to the record that was read and (if provided) * @r and @line_count will contain the read/calculated data. * * On failure @seq is updated to a record that is not yet available to the * reader, but it will be the next record available to the reader. * * Note: When the current CPU is in panic, this function will skip over any * non-existent/non-finalized records in order to allow the panic CPU * to print any and all records that have been finalized. */static bool _prb_read_valid(struct printk_ringbuffer *rb, u64 *seq, struct printk_record *r, unsigned int *line_count){ u64 tail_seq; int err;
while ((err = prb_read(rb, *seq, r, line_count))) { tail_seq = prb_first_seq(rb);
if (*seq < tail_seq) { /* * Behind the tail. Catch up and try again. This * can happen for -ENOENT and -EINVAL cases. */ *seq = tail_seq;
} else if (err == -ENOENT) { /* Record exists, but the data was lost. Skip. */ (*seq)++;
} else { /* * Non-existent/non-finalized record. Must stop. * * For panic situations it cannot be expected that * non-finalized records will become finalized. But * there may be other finalized records beyond that * need to be printed for a panic situation. If this * is the panic CPU, skip this * non-existent/non-finalized record unless non-panic * CPUs are still running and their debugging is * explicitly enabled. * * Note that new messages printed on panic CPU are * finalized when we are here. The only exception * might be the last message without trailing newline. * But it would have the sequence number returned * by "prb_next_reserve_seq() - 1". */ if (panic_on_this_cpu() && (!debug_non_panic_cpus || legacy_allow_panic_sync) && ((*seq + 1) < prb_next_reserve_seq(rb))) { (*seq)++; } else { return false; } } }
return true;}
/** * prb_read_valid() - Non-blocking read of a requested record or (if gone) * the next available record. * * @rb: The ringbuffer to read from. * @seq: The sequence number of the record to read. * @r: A record data buffer to store the read record to. * * This is the public function available to readers to read a record. * * The reader provides the @info and @text_buf buffers of @r to be * filled in. Any of the buffer pointers can be set to NULL if the reader * is not interested in that data. To ensure proper initialization of @r, * prb_rec_init_rd() should be used. * * Context: Any context. * Return: true if a record was read, otherwise false. * * On success, the reader must check r->info.seq to see which record was * actually read. This allows the reader to detect dropped records. * * Failure means @seq refers to a record not yet available to the reader. */bool prb_read_valid(struct printk_ringbuffer *rb, u64 seq, struct printk_record *r){ return _prb_read_valid(rb, &seq, r, NULL);}EXPORT_SYMBOL_IF_KUNIT(prb_read_valid);
/** * prb_read_valid_info() - Non-blocking read of meta data for a requested * record or (if gone) the next available record. * * @rb: The ringbuffer to read from. * @seq: The sequence number of the record to read. * @info: A buffer to store the read record meta data to. * @line_count: A buffer to store the number of lines in the record text. * * This is the public function available to readers to read only the * meta data of a record. * * The reader provides the @info, @line_count buffers to be filled in. * Either of the buffer pointers can be set to NULL if the reader is not * interested in that data. * * Context: Any context. * Return: true if a record's meta data was read, otherwise false. * * On success, the reader must check info->seq to see which record meta data * was actually read. This allows the reader to detect dropped records. * * Failure means @seq refers to a record not yet available to the reader. */bool prb_read_valid_info(struct printk_ringbuffer *rb, u64 seq, struct printk_info *info, unsigned int *line_count){ struct printk_record r;
prb_rec_init_rd(&r, info, NULL, 0);
return _prb_read_valid(rb, &seq, &r, line_count);}
/** * prb_first_valid_seq() - Get the sequence number of the oldest available * record. * * @rb: The ringbuffer to get the sequence number from. * * This is the public function available to readers to see what the * first/oldest valid sequence number is. * * This provides readers a starting point to begin iterating the ringbuffer. * * Context: Any context. * Return: The sequence number of the first/oldest record or, if the * ringbuffer is empty, 0 is returned. */u64 prb_first_valid_seq(struct printk_ringbuffer *rb){ u64 seq = 0;
if (!_prb_read_valid(rb, &seq, NULL, NULL)) return 0;
return seq;}
/** * prb_next_seq() - Get the sequence number after the last available record. * * @rb: The ringbuffer to get the sequence number from. * * This is the public function available to readers to see what the next * newest sequence number available to readers will be. * * This provides readers a sequence number to jump to if all currently * available records should be skipped. It is guaranteed that all records * previous to the returned value have been finalized and are (or were) * available to the reader. * * Context: Any context. * Return: The sequence number of the next newest (not yet available) record * for readers. */u64 prb_next_seq(struct printk_ringbuffer *rb){ u64 seq;
seq = desc_last_finalized_seq(rb);
/* * Begin searching after the last finalized record. * * On 0, the search must begin at 0 because of hack#2 * of the bootstrapping phase it is not known if a * record at index 0 exists. */ if (seq != 0) seq++;
/* * The information about the last finalized @seq might be inaccurate. * Search forward to find the current one. */ while (_prb_read_valid(rb, &seq, NULL, NULL)) seq++;
return seq;}
/** * prb_init() - Initialize a ringbuffer to use provided external buffers. * * @rb: The ringbuffer to initialize. * @text_buf: The data buffer for text data. * @textbits: The size of @text_buf as a power-of-2 value. * @descs: The descriptor buffer for ringbuffer records. * @descbits: The count of @descs items as a power-of-2 value. * @infos: The printk_info buffer for ringbuffer records. * * This is the public function available to writers to setup a ringbuffer * during runtime using provided buffers. * * This must match the initialization of DEFINE_PRINTKRB(). * * Context: Any context. */void prb_init(struct printk_ringbuffer *rb, char *text_buf, unsigned int textbits, struct prb_desc *descs, unsigned int descbits, struct printk_info *infos){ memset(descs, 0, _DESCS_COUNT(descbits) * sizeof(descs[0])); memset(infos, 0, _DESCS_COUNT(descbits) * sizeof(infos[0]));
rb->desc_ring.count_bits = descbits; rb->desc_ring.descs = descs; rb->desc_ring.infos = infos; atomic_long_set(&rb->desc_ring.head_id, DESC0_ID(descbits)); atomic_long_set(&rb->desc_ring.tail_id, DESC0_ID(descbits)); atomic_long_set(&rb->desc_ring.last_finalized_seq, 0);
rb->text_data_ring.size_bits = textbits; rb->text_data_ring.data = text_buf; atomic_long_set(&rb->text_data_ring.head_lpos, BLK0_LPOS(textbits)); atomic_long_set(&rb->text_data_ring.tail_lpos, BLK0_LPOS(textbits));
atomic_long_set(&rb->fail, 0);
atomic_long_set(&(descs[_DESCS_COUNT(descbits) - 1].state_var), DESC0_SV(descbits)); descs[_DESCS_COUNT(descbits) - 1].text_blk_lpos.begin = FAILED_LPOS; descs[_DESCS_COUNT(descbits) - 1].text_blk_lpos.next = FAILED_LPOS;
infos[0].seq = -(u64)_DESCS_COUNT(descbits); infos[_DESCS_COUNT(descbits) - 1].seq = 0;}EXPORT_SYMBOL_IF_KUNIT(prb_init);
/** * prb_record_text_space() - Query the full actual used ringbuffer space for * the text data of a reserved entry. * * @e: The successfully reserved entry to query. * * This is the public function available to writers to see how much actual * space is used in the ringbuffer to store the text data of the specified * entry. * * This function is only valid if @e has been successfully reserved using * prb_reserve(). * * Context: Any context. * Return: The size in bytes used by the text data of the associated record. */unsigned int prb_record_text_space(struct prb_reserved_entry *e){ return e->text_space;}