// SPDX-License-Identifier: GPL-2.0 #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 3 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. */static bool data_check_size(struct prb_data_ring *data_ring, unsigned int size){ struct prb_data_block *db = NULL; if (size == 0) return true; /* * Ensure the alignment padded size could possibly fit in the data * array. The largest possible data block must still leave room for * at least the ID of the next block. */ size = to_blk_size(size); if (size > DATA_SIZE(data_ring) - sizeof(db->id)) return false; return true;} /* 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. *Lines 1–500 of 2353. Load more
// SPDX-License-Identifier: GPL-2.0 #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 3 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. */ static bool data_check_size(struct prb_data_ring *data_ring, unsigned int size) { struct prb_data_block *db = NULL; if (size == 0) return true; /* * Ensure the alignment padded size could possibly fit in the data * array. The largest possible data block must still leave room for * at least the ID of the next block. */ size = to_blk_size(size); if (size > DATA_SIZE(data_ring) - sizeof(db->id)) return false; return true; } /* 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. *