// SPDX-License-Identifier: GPL-2.0-or-later /* * ec.c - ACPI Embedded Controller Driver (v3) * * Copyright (C) 2001-2015 Intel Corporation * Author: 2014, 2015 Lv Zheng * 2006, 2007 Alexey Starikovskiy * 2006 Denis Sadykov * 2004 Luming Yu * 2001, 2002 Andy Grover * 2001, 2002 Paul Diefenbaugh * Copyright (C) 2008 Alexey Starikovskiy */ /* Uncomment next line to get verbose printout */ /* #define DEBUG */ #define pr_fmt(fmt) "ACPI: EC: " fmt #include #include #include #include #include #include #include #include #include #include #include #include #include #include "internal.h" #define ACPI_EC_CLASS "embedded_controller" #define ACPI_EC_DEVICE_NAME "Embedded Controller" #define ACPI_EC_FILE_INFO "info" /* EC status register */ #define ACPI_EC_FLAG_OBF 0x01 /* Output buffer full */ #define ACPI_EC_FLAG_IBF 0x02 /* Input buffer full */ #define ACPI_EC_FLAG_CMD 0x08 /* Input buffer contains a command */ #define ACPI_EC_FLAG_BURST 0x10 /* burst mode */ #define ACPI_EC_FLAG_SCI 0x20 /* EC-SCI occurred */ /* * The SCI_EVT clearing timing is not defined by the ACPI specification. * This leads to lots of practical timing issues for the host EC driver. * The following variations are defined (from the target EC firmware's * perspective): * STATUS: After indicating SCI_EVT edge triggered IRQ to the host, the * target can clear SCI_EVT at any time so long as the host can see * the indication by reading the status register (EC_SC). So the * host should re-check SCI_EVT after the first time the SCI_EVT * indication is seen, which is the same time the query request * (QR_EC) is written to the command register (EC_CMD). SCI_EVT set * at any later time could indicate another event. Normally such * kind of EC firmware has implemented an event queue and will * return 0x00 to indicate "no outstanding event". * QUERY: After seeing the query request (QR_EC) written to the command * register (EC_CMD) by the host and having prepared the responding * event value in the data register (EC_DATA), the target can safely * clear SCI_EVT because the target can confirm that the current * event is being handled by the host. The host then should check * SCI_EVT right after reading the event response from the data * register (EC_DATA). * EVENT: After seeing the event response read from the data register * (EC_DATA) by the host, the target can clear SCI_EVT. As the * target requires time to notice the change in the data register * (EC_DATA), the host may be required to wait additional guarding * time before checking the SCI_EVT again. Such guarding may not be * necessary if the host is notified via another IRQ. */ #define ACPI_EC_EVT_TIMING_STATUS 0x00 #define ACPI_EC_EVT_TIMING_QUERY 0x01 #define ACPI_EC_EVT_TIMING_EVENT 0x02 /* EC commands */ enum ec_command { ACPI_EC_COMMAND_READ = 0x80, ACPI_EC_COMMAND_WRITE = 0x81, ACPI_EC_BURST_ENABLE = 0x82, ACPI_EC_BURST_DISABLE = 0x83, ACPI_EC_COMMAND_QUERY = 0x84, }; #define ACPI_EC_DELAY 500 /* Wait 500ms max. during EC ops */ #define ACPI_EC_UDELAY_GLK 1000 /* Wait 1ms max. to get global lock */ #define ACPI_EC_UDELAY_POLL 550 /* Wait 1ms for EC transaction polling */ #define ACPI_EC_CLEAR_MAX 100 /* Maximum number of events to query * when trying to clear the EC */ #define ACPI_EC_MAX_QUERIES 16 /* Maximum number of parallel queries */ enum { EC_FLAGS_QUERY_ENABLED, /* Query is enabled */ EC_FLAGS_QUERY_PENDING, /* Query is pending */ EC_FLAGS_QUERY_GUARDING, /* Guard for SCI_EVT check */ EC_FLAGS_EVENT_HANDLER_INSTALLED, /* Event handler installed */ EC_FLAGS_EC_HANDLER_INSTALLED, /* OpReg handler installed */ EC_FLAGS_QUERY_METHODS_INSTALLED, /* _Qxx handlers installed */ EC_FLAGS_STARTED, /* Driver is started */ EC_FLAGS_STOPPED, /* Driver is stopped */ EC_FLAGS_EVENTS_MASKED, /* Events masked */ }; #define ACPI_EC_COMMAND_POLL 0x01 /* Available for command byte */ #define ACPI_EC_COMMAND_COMPLETE 0x02 /* Completed last byte */ /* ec.c is compiled in acpi namespace so this shows up as acpi.ec_delay param */ static unsigned int ec_delay __read_mostly = ACPI_EC_DELAY; module_param(ec_delay, uint, 0644); MODULE_PARM_DESC(ec_delay, "Timeout(ms) waited until an EC command completes"); static unsigned int ec_max_queries __read_mostly = ACPI_EC_MAX_QUERIES; module_param(ec_max_queries, uint, 0644); MODULE_PARM_DESC(ec_max_queries, "Maximum parallel _Qxx evaluations"); static bool ec_busy_polling __read_mostly; module_param(ec_busy_polling, bool, 0644); MODULE_PARM_DESC(ec_busy_polling, "Use busy polling to advance EC transaction"); static unsigned int ec_polling_guard __read_mostly = ACPI_EC_UDELAY_POLL; module_param(ec_polling_guard, uint, 0644); MODULE_PARM_DESC(ec_polling_guard, "Guard time(us) between EC accesses in polling modes"); static unsigned int ec_event_clearing __read_mostly = ACPI_EC_EVT_TIMING_QUERY; /* * If the number of false interrupts per one transaction exceeds * this threshold, will think there is a GPE storm happened and * will disable the GPE for normal transaction. */ static unsigned int ec_storm_threshold __read_mostly = 8; module_param(ec_storm_threshold, uint, 0644); MODULE_PARM_DESC(ec_storm_threshold, "Maxim false GPE numbers not considered as GPE storm"); static bool ec_freeze_events __read_mostly = false; module_param(ec_freeze_events, bool, 0644); MODULE_PARM_DESC(ec_freeze_events, "Disabling event handling during suspend/resume"); static bool ec_no_wakeup __read_mostly; module_param(ec_no_wakeup, bool, 0644); MODULE_PARM_DESC(ec_no_wakeup, "Do not wake up from suspend-to-idle"); struct acpi_ec_query_handler { struct list_head node; acpi_ec_query_func func; acpi_handle handle; void *data; u8 query_bit; struct kref kref; }; struct transaction { const u8 *wdata; u8 *rdata; unsigned short irq_count; u8 command; u8 wi; u8 ri; u8 wlen; u8 rlen; u8 flags; }; struct acpi_ec_query { struct transaction transaction; struct work_struct work; struct acpi_ec_query_handler *handler; }; static int acpi_ec_query(struct acpi_ec *ec, u8 *data); static void advance_transaction(struct acpi_ec *ec); static void acpi_ec_event_handler(struct work_struct *work); static void acpi_ec_event_processor(struct work_struct *work); struct acpi_ec *first_ec; EXPORT_SYMBOL(first_ec); static struct acpi_ec *boot_ec; static bool boot_ec_is_ecdt = false; static struct workqueue_struct *ec_query_wq; static int EC_FLAGS_QUERY_HANDSHAKE; /* Needs QR_EC issued when SCI_EVT set */ static int EC_FLAGS_CORRECT_ECDT; /* Needs ECDT port address correction */ static int EC_FLAGS_IGNORE_DSDT_GPE; /* Needs ECDT GPE as correction setting */ static int EC_FLAGS_CLEAR_ON_RESUME; /* Needs acpi_ec_clear() on boot/resume */ /* -------------------------------------------------------------------------- * Logging/Debugging * -------------------------------------------------------------------------- */ /* * Splitters used by the developers to track the boundary of the EC * handling processes. */ #ifdef DEBUG #define EC_DBG_SEP " " #define EC_DBG_DRV "+++++" #define EC_DBG_STM "=====" #define EC_DBG_REQ "*****" #define EC_DBG_EVT "#####" #else #define EC_DBG_SEP "" #define EC_DBG_DRV #define EC_DBG_STM #define EC_DBG_REQ #define EC_DBG_EVT #endif #define ec_log_raw(fmt, ...) \ pr_info(fmt "\n", ##__VA_ARGS__) #define ec_dbg_raw(fmt, ...) \ pr_debug(fmt "\n", ##__VA_ARGS__) #define ec_log(filter, fmt, ...) \ ec_log_raw(filter EC_DBG_SEP fmt EC_DBG_SEP filter, ##__VA_ARGS__) #define ec_dbg(filter, fmt, ...) \ ec_dbg_raw(filter EC_DBG_SEP fmt EC_DBG_SEP filter, ##__VA_ARGS__) #define ec_log_drv(fmt, ...) \ ec_log(EC_DBG_DRV, fmt, ##__VA_ARGS__) #define ec_dbg_drv(fmt, ...) \ ec_dbg(EC_DBG_DRV, fmt, ##__VA_ARGS__) #define ec_dbg_stm(fmt, ...) \ ec_dbg(EC_DBG_STM, fmt, ##__VA_ARGS__) #define ec_dbg_req(fmt, ...) \ ec_dbg(EC_DBG_REQ, fmt, ##__VA_ARGS__) #define ec_dbg_evt(fmt, ...) \ ec_dbg(EC_DBG_EVT, fmt, ##__VA_ARGS__) #define ec_dbg_ref(ec, fmt, ...) \ ec_dbg_raw("%lu: " fmt, ec->reference_count, ## __VA_ARGS__) /* -------------------------------------------------------------------------- * Device Flags * -------------------------------------------------------------------------- */ static bool acpi_ec_started(struct acpi_ec *ec) { return test_bit(EC_FLAGS_STARTED, &ec->flags) && !test_bit(EC_FLAGS_STOPPED, &ec->flags); } static bool acpi_ec_event_enabled(struct acpi_ec *ec) { /* * There is an OSPM early stage logic. During the early stages * (boot/resume), OSPMs shouldn't enable the event handling, only * the EC transactions are allowed to be performed. */ if (!test_bit(EC_FLAGS_QUERY_ENABLED, &ec->flags)) return false; /* * However, disabling the event handling is experimental for late * stage (suspend), and is controlled by the boot parameter of * "ec_freeze_events": * 1. true: The EC event handling is disabled before entering * the noirq stage. * 2. false: The EC event handling is automatically disabled as * soon as the EC driver is stopped. */ if (ec_freeze_events) return acpi_ec_started(ec); else return test_bit(EC_FLAGS_STARTED, &ec->flags); } static bool acpi_ec_flushed(struct acpi_ec *ec) { return ec->reference_count == 1; } /* -------------------------------------------------------------------------- * EC Registers * -------------------------------------------------------------------------- */ static inline u8 acpi_ec_read_status(struct acpi_ec *ec) { u8 x = inb(ec->command_addr); ec_dbg_raw("EC_SC(R) = 0x%2.2x " "SCI_EVT=%d BURST=%d CMD=%d IBF=%d OBF=%d", x, !!(x & ACPI_EC_FLAG_SCI), !!(x & ACPI_EC_FLAG_BURST), !!(x & ACPI_EC_FLAG_CMD), !!(x & ACPI_EC_FLAG_IBF), !!(x & ACPI_EC_FLAG_OBF)); return x; } static inline u8 acpi_ec_read_data(struct acpi_ec *ec) { u8 x = inb(ec->data_addr); ec->timestamp = jiffies; ec_dbg_raw("EC_DATA(R) = 0x%2.2x", x); return x; } static inline void acpi_ec_write_cmd(struct acpi_ec *ec, u8 command) { ec_dbg_raw("EC_SC(W) = 0x%2.2x", command); outb(command, ec->command_addr); ec->timestamp = jiffies; } static inline void acpi_ec_write_data(struct acpi_ec *ec, u8 data) { ec_dbg_raw("EC_DATA(W) = 0x%2.2x", data); outb(data, ec->data_addr); ec->timestamp = jiffies; } #if defined(DEBUG) || defined(CONFIG_DYNAMIC_DEBUG) static const char *acpi_ec_cmd_string(u8 cmd) { switch (cmd) { case 0x80: return "RD_EC"; case 0x81: return "WR_EC"; case 0x82: return "BE_EC"; case 0x83: return "BD_EC"; case 0x84: return "QR_EC"; } return "UNKNOWN"; } #else #define acpi_ec_cmd_string(cmd) "UNDEF" #endif /* -------------------------------------------------------------------------- * GPE Registers * -------------------------------------------------------------------------- */ static inline bool acpi_ec_is_gpe_raised(struct acpi_ec *ec) { acpi_event_status gpe_status = 0; (void)acpi_get_gpe_status(NULL, ec->gpe, &gpe_status); return (gpe_status & ACPI_EVENT_FLAG_STATUS_SET) ? true : false; } static inline void acpi_ec_enable_gpe(struct acpi_ec *ec, bool open) { if (open) acpi_enable_gpe(NULL, ec->gpe); else { BUG_ON(ec->reference_count < 1); acpi_set_gpe(NULL, ec->gpe, ACPI_GPE_ENABLE); } if (acpi_ec_is_gpe_raised(ec)) { /* * On some platforms, EN=1 writes cannot trigger GPE. So * software need to manually trigger a pseudo GPE event on * EN=1 writes. */ ec_dbg_raw("Polling quirk"); advance_transaction(ec); } } static inline void acpi_ec_disable_gpe(struct acpi_ec *ec, bool close) { if (close) acpi_disable_gpe(NULL, ec->gpe); else { BUG_ON(ec->reference_count < 1); acpi_set_gpe(NULL, ec->gpe, ACPI_GPE_DISABLE); } } static inline void acpi_ec_clear_gpe(struct acpi_ec *ec) { /* * GPE STS is a W1C register, which means: * 1. Software can clear it without worrying about clearing other * GPEs' STS bits when the hardware sets them in parallel. * 2. As long as software can ensure only clearing it when it is * set, hardware won't set it in parallel. * So software can clear GPE in any contexts. * Warning: do not move the check into advance_transaction() as the * EC commands will be sent without GPE raised. */ if (!acpi_ec_is_gpe_raised(ec)) return; acpi_clear_gpe(NULL, ec->gpe); } /* -------------------------------------------------------------------------- * Transaction Management * -------------------------------------------------------------------------- */ static void acpi_ec_submit_request(struct acpi_ec *ec) { ec->reference_count++; if (test_bit(EC_FLAGS_EVENT_HANDLER_INSTALLED, &ec->flags) && ec->gpe >= 0 && ec->reference_count == 1) acpi_ec_enable_gpe(ec, true); } static void acpi_ec_complete_request(struct acpi_ec *ec) { bool flushed = false; ec->reference_count--; if (test_bit(EC_FLAGS_EVENT_HANDLER_INSTALLED, &ec->flags) && ec->gpe >= 0 && ec->reference_count == 0) acpi_ec_disable_gpe(ec, true); flushed = acpi_ec_flushed(ec); if (flushed) wake_up(&ec->wait); } static void acpi_ec_mask_events(struct acpi_ec *ec) { if (!test_bit(EC_FLAGS_EVENTS_MASKED, &ec->flags)) { if (ec->gpe >= 0) acpi_ec_disable_gpe(ec, false); else disable_irq_nosync(ec->irq); ec_dbg_drv("Polling enabled"); set_bit(EC_FLAGS_EVENTS_MASKED, &ec->flags); } } static void acpi_ec_unmask_events(struct acpi_ec *ec) { if (test_bit(EC_FLAGS_EVENTS_MASKED, &ec->flags)) { clear_bit(EC_FLAGS_EVENTS_MASKED, &ec->flags); if (ec->gpe >= 0) acpi_ec_enable_gpe(ec, false); else enable_irq(ec->irq); ec_dbg_drv("Polling disabled"); } } /* * acpi_ec_submit_flushable_request() - Increase the reference count unless * the flush operation is not in * progress * @ec: the EC device * * This function must be used before taking a new action that should hold * the reference count. If this function returns false, then the action * must be discarded or it will prevent the flush operation from being * completed. */ static bool acpi_ec_submit_flushable_request(struct acpi_ec *ec) { if (!acpi_ec_started(ec)) return false; acpi_ec_submit_request(ec); return true; } static void acpi_ec_submit_query(struct acpi_ec *ec) { acpi_ec_mask_events(ec); if (!acpi_ec_event_enabled(ec)) return; if (!test_and_set_bit(EC_FLAGS_QUERY_PENDING, &ec->flags)) { ec_dbg_evt("Command(%s) submitted/blocked", acpi_ec_cmd_string(ACPI_EC_COMMAND_QUERY)); ec->nr_pending_queries++; schedule_work(&ec->work); } } static void acpi_ec_complete_query(struct acpi_ec *ec) { if (test_and_clear_bit(EC_FLAGS_QUERY_PENDING, &ec->flags)) ec_dbg_evt("Command(%s) unblocked", acpi_ec_cmd_string(ACPI_EC_COMMAND_QUERY)); acpi_ec_unmask_events(ec); } static inline void __acpi_ec_enable_event(struct acpi_ec *ec) { if (!test_and_set_bit(EC_FLAGS_QUERY_ENABLED, &ec->flags)) ec_log_drv("event unblocked"); /* * Unconditionally invoke this once after enabling the event * handling mechanism to detect the pending events. */ advance_transaction(ec); } static inline void __acpi_ec_disable_event(struct acpi_ec *ec) { if (test_and_clear_bit(EC_FLAGS_QUERY_ENABLED, &ec->flags)) ec_log_drv("event blocked"); } /* * Process _Q events that might have accumulated in the EC. * Run with locked ec mutex. */ static void acpi_ec_clear(struct acpi_ec *ec) { int i, status; u8 value = 0; for (i = 0; i < ACPI_EC_CLEAR_MAX; i++) { status = acpi_ec_query(ec, &value); if (status || !value) break; } if (unlikely(i == ACPI_EC_CLEAR_MAX)) pr_warn("Warning: Maximum of %d stale EC events cleared\n", i); else pr_info("%d stale EC events cleared\n", i); } static void acpi_ec_enable_event(struct acpi_ec *ec) { unsigned long flags; spin_lock_irqsave(&ec->lock, flags); if (acpi_ec_started(ec)) __acpi_ec_enable_event(ec); spin_unlock_irqrestore(&ec->lock, flags); /* Drain additional events if hardware requires that */ if (EC_FLAGS_CLEAR_ON_RESUME) acpi_ec_clear(ec); } #ifdef CONFIG_PM_SLEEP static void __acpi_ec_flush_work(void) { flush_scheduled_work(); /* flush ec->work */ flush_workqueue(ec_query_wq); /* flush queries */ } static void acpi_ec_disable_event(struct acpi_ec *ec) { unsigned long flags; spin_lock_irqsave(&ec->lock, flags); __acpi_ec_disable_event(ec); spin_unlock_irqrestore(&ec->lock, flags); /* * When ec_freeze_events is true, we need to flush events in * the proper position before entering the noirq stage. */ __acpi_ec_flush_work(); } void acpi_ec_flush_work(void) { /* Without ec_query_wq there is nothing to flush. */ if (!ec_query_wq) return; __acpi_ec_flush_work(); } #endif /* CONFIG_PM_SLEEP */ static bool acpi_ec_guard_event(struct acpi_ec *ec) { bool guarded = true; unsigned long flags; spin_lock_irqsave(&ec->lock, flags); /* * If firmware SCI_EVT clearing timing is "event", we actually * don't know when the SCI_EVT will be cleared by firmware after * evaluating _Qxx, so we need to re-check SCI_EVT after waiting an * acceptable period. * * The guarding period begins when EC_FLAGS_QUERY_PENDING is * flagged, which means SCI_EVT check has just been performed. * But if the current transaction is ACPI_EC_COMMAND_QUERY, the * guarding should have already been performed (via * EC_FLAGS_QUERY_GUARDING) and should not be applied so that the * ACPI_EC_COMMAND_QUERY transaction can be transitioned into * ACPI_EC_COMMAND_POLL state immediately. */ if (ec_event_clearing == ACPI_EC_EVT_TIMING_STATUS || ec_event_clearing == ACPI_EC_EVT_TIMING_QUERY || !test_bit(EC_FLAGS_QUERY_PENDING, &ec->flags) || (ec->curr && ec->curr->command == ACPI_EC_COMMAND_QUERY)) guarded = false; spin_unlock_irqrestore(&ec->lock, flags); return guarded; } static int ec_transaction_polled(struct acpi_ec *ec) { unsigned long flags; int ret = 0; spin_lock_irqsave(&ec->lock, flags); if (ec->curr && (ec->curr->flags & ACPI_EC_COMMAND_POLL)) ret = 1; spin_unlock_irqrestore(&ec->lock, flags); return ret; } static int ec_transaction_completed(struct acpi_ec *ec) { unsigned long flags; int ret = 0; spin_lock_irqsave(&ec->lock, flags); if (ec->curr && (ec->curr->flags & ACPI_EC_COMMAND_COMPLETE)) ret = 1; spin_unlock_irqrestore(&ec->lock, flags); return ret; } static inline void ec_transaction_transition(struct acpi_ec *ec, unsigned long flag) { ec->curr->flags |= flag; if (ec->curr->command == ACPI_EC_COMMAND_QUERY) { if (ec_event_clearing == ACPI_EC_EVT_TIMING_STATUS && flag == ACPI_EC_COMMAND_POLL) acpi_ec_complete_query(ec); if (ec_event_clearing == ACPI_EC_EVT_TIMING_QUERY && flag == ACPI_EC_COMMAND_COMPLETE) acpi_ec_complete_query(ec); if (ec_event_clearing == ACPI_EC_EVT_TIMING_EVENT && flag == ACPI_EC_COMMAND_COMPLETE) set_bit(EC_FLAGS_QUERY_GUARDING, &ec->flags); } } static void advance_transaction(struct acpi_ec *ec) { struct transaction *t; u8 status; bool wakeup = false; ec_dbg_stm("%s (%d)", in_interrupt() ? "IRQ" : "TASK", smp_processor_id()); /* * By always clearing STS before handling all indications, we can * ensure a hardware STS 0->1 change after this clearing can always * trigger a GPE interrupt. */ if (ec->gpe >= 0) acpi_ec_clear_gpe(ec); status = acpi_ec_read_status(ec); t = ec->curr; /* * Another IRQ or a guarded polling mode advancement is detected, * the next QR_EC submission is then allowed. */ if (!t || !(t->flags & ACPI_EC_COMMAND_POLL)) { if (ec_event_clearing == ACPI_EC_EVT_TIMING_EVENT && (!ec->nr_pending_queries || test_bit(EC_FLAGS_QUERY_GUARDING, &ec->flags))) { clear_bit(EC_FLAGS_QUERY_GUARDING, &ec->flags); acpi_ec_complete_query(ec); } } if (!t) goto err; if (t->flags & ACPI_EC_COMMAND_POLL) { if (t->wlen > t->wi) { if ((status & ACPI_EC_FLAG_IBF) == 0) acpi_ec_write_data(ec, t->wdata[t->wi++]); else goto err; } else if (t->rlen > t->ri) { if ((status & ACPI_EC_FLAG_OBF) == 1) { t->rdata[t->ri++] = acpi_ec_read_data(ec); if (t->rlen == t->ri) { ec_transaction_transition(ec, ACPI_EC_COMMAND_COMPLETE); if (t->command == ACPI_EC_COMMAND_QUERY) ec_dbg_evt("Command(%s) completed by hardware", acpi_ec_cmd_string(ACPI_EC_COMMAND_QUERY)); wakeup = true; } } else goto err; } else if (t->wlen == t->wi && (status & ACPI_EC_FLAG_IBF) == 0) { ec_transaction_transition(ec, ACPI_EC_COMMAND_COMPLETE); wakeup = true; } goto out; } else { if (EC_FLAGS_QUERY_HANDSHAKE && !(status & ACPI_EC_FLAG_SCI) && (t->command == ACPI_EC_COMMAND_QUERY)) { ec_transaction_transition(ec, ACPI_EC_COMMAND_POLL); t->rdata[t->ri++] = 0x00; ec_transaction_transition(ec, ACPI_EC_COMMAND_COMPLETE); ec_dbg_evt("Command(%s) completed by software", acpi_ec_cmd_string(ACPI_EC_COMMAND_QUERY)); wakeup = true; } else if ((status & ACPI_EC_FLAG_IBF) == 0) { acpi_ec_write_cmd(ec, t->command); ec_transaction_transition(ec, ACPI_EC_COMMAND_POLL); } else goto err; goto out; } err: /* * If SCI bit is set, then don't think it's a false IRQ * otherwise will take a not handled IRQ as a false one. */ if (!(status & ACPI_EC_FLAG_SCI)) { if (in_interrupt() && t) { if (t->irq_count < ec_storm_threshold) ++t->irq_count; /* Allow triggering on 0 threshold */ if (t->irq_count == ec_storm_threshold) acpi_ec_mask_events(ec); } } out: if (status & ACPI_EC_FLAG_SCI) acpi_ec_submit_query(ec); if (wakeup && in_interrupt()) wake_up(&ec->wait); } static void start_transaction(struct acpi_ec *ec) { ec->curr->irq_count = ec->curr->wi = ec->curr->ri = 0; ec->curr->flags = 0; } static int ec_guard(struct acpi_ec *ec) { unsigned long guard = usecs_to_jiffies(ec->polling_guard); unsigned long timeout = ec->timestamp + guard; /* Ensure guarding period before polling EC status */ do { if (ec->busy_polling) { /* Perform busy polling */ if (ec_transaction_completed(ec)) return 0; udelay(jiffies_to_usecs(guard)); } else { /* * Perform wait polling * 1. Wait the transaction to be completed by the * GPE handler after the transaction enters * ACPI_EC_COMMAND_POLL state. * 2. A special guarding logic is also required * for event clearing mode "event" before the * transaction enters ACPI_EC_COMMAND_POLL * state. */ if (!ec_transaction_polled(ec) && !acpi_ec_guard_event(ec)) break; if (wait_event_timeout(ec->wait, ec_transaction_completed(ec), guard)) return 0; } } while (time_before(jiffies, timeout)); return -ETIME; } static int ec_poll(struct acpi_ec *ec) { unsigned long flags; int repeat = 5; /* number of command restarts */ while (repeat--) { unsigned long delay = jiffies + msecs_to_jiffies(ec_delay); do { if (!ec_guard(ec)) return 0; spin_lock_irqsave(&ec->lock, flags); advance_transaction(ec); spin_unlock_irqrestore(&ec->lock, flags); } while (time_before(jiffies, delay)); pr_debug("controller reset, restart transaction\n"); spin_lock_irqsave(&ec->lock, flags); start_transaction(ec); spin_unlock_irqrestore(&ec->lock, flags); } return -ETIME; } static int acpi_ec_transaction_unlocked(struct acpi_ec *ec, struct transaction *t) { unsigned long tmp; int ret = 0; /* start transaction */ spin_lock_irqsave(&ec->lock, tmp); /* Enable GPE for command processing (IBF=0/OBF=1) */ if (!acpi_ec_submit_flushable_request(ec)) { ret = -EINVAL; goto unlock; } ec_dbg_ref(ec, "Increase command"); /* following two actions should be kept atomic */ ec->curr = t; ec_dbg_req("Command(%s) started", acpi_ec_cmd_string(t->command)); start_transaction(ec); spin_unlock_irqrestore(&ec->lock, tmp); ret = ec_poll(ec); spin_lock_irqsave(&ec->lock, tmp); if (t->irq_count == ec_storm_threshold) acpi_ec_unmask_events(ec); ec_dbg_req("Command(%s) stopped", acpi_ec_cmd_string(t->command)); ec->curr = NULL; /* Disable GPE for command processing (IBF=0/OBF=1) */ acpi_ec_complete_request(ec); ec_dbg_ref(ec, "Decrease command"); unlock: spin_unlock_irqrestore(&ec->lock, tmp); return ret; } static int acpi_ec_transaction(struct acpi_ec *ec, struct transaction *t) { int status; u32 glk; if (!ec || (!t) || (t->wlen && !t->wdata) || (t->rlen && !t->rdata)) return -EINVAL; if (t->rdata) memset(t->rdata, 0, t->rlen); mutex_lock(&ec->mutex); if (ec->global_lock) { status = acpi_acquire_global_lock(ACPI_EC_UDELAY_GLK, &glk); if (ACPI_FAILURE(status)) { status = -ENODEV; goto unlock; } } status = acpi_ec_transaction_unlocked(ec, t); if (ec->global_lock) acpi_release_global_lock(glk); unlock: mutex_unlock(&ec->mutex); return status; } static int acpi_ec_burst_enable(struct acpi_ec *ec) { u8 d; struct transaction t = {.command = ACPI_EC_BURST_ENABLE, .wdata = NULL, .rdata = &d, .wlen = 0, .rlen = 1}; return acpi_ec_transaction(ec, &t); } static int acpi_ec_burst_disable(struct acpi_ec *ec) { struct transaction t = {.command = ACPI_EC_BURST_DISABLE, .wdata = NULL, .rdata = NULL, .wlen = 0, .rlen = 0}; return (acpi_ec_read_status(ec) & ACPI_EC_FLAG_BURST) ? acpi_ec_transaction(ec, &t) : 0; } static int acpi_ec_read(struct acpi_ec *ec, u8 address, u8 *data) { int result; u8 d; struct transaction t = {.command = ACPI_EC_COMMAND_READ, .wdata = &address, .rdata = &d, .wlen = 1, .rlen = 1}; result = acpi_ec_transaction(ec, &t); *data = d; return result; } static int acpi_ec_write(struct acpi_ec *ec, u8 address, u8 data) { u8 wdata[2] = { address, data }; struct transaction t = {.command = ACPI_EC_COMMAND_WRITE, .wdata = wdata, .rdata = NULL, .wlen = 2, .rlen = 0}; return acpi_ec_transaction(ec, &t); } int ec_read(u8 addr, u8 *val) { int err; u8 temp_data; if (!first_ec) return -ENODEV; err = acpi_ec_read(first_ec, addr, &temp_data); if (!err) { *val = temp_data; return 0; } return err; } EXPORT_SYMBOL(ec_read); int ec_write(u8 addr, u8 val) { int err; if (!first_ec) return -ENODEV; err = acpi_ec_write(first_ec, addr, val); return err; } EXPORT_SYMBOL(ec_write); int ec_transaction(u8 command, const u8 *wdata, unsigned wdata_len, u8 *rdata, unsigned rdata_len) { struct transaction t = {.command = command, .wdata = wdata, .rdata = rdata, .wlen = wdata_len, .rlen = rdata_len}; if (!first_ec) return -ENODEV; return acpi_ec_transaction(first_ec, &t); } EXPORT_SYMBOL(ec_transaction); /* Get the handle to the EC device */ acpi_handle ec_get_handle(void) { if (!first_ec) return NULL; return first_ec->handle; } EXPORT_SYMBOL(ec_get_handle); static void acpi_ec_start(struct acpi_ec *ec, bool resuming) { unsigned long flags; spin_lock_irqsave(&ec->lock, flags); if (!test_and_set_bit(EC_FLAGS_STARTED, &ec->flags)) { ec_dbg_drv("Starting EC"); /* Enable GPE for event processing (SCI_EVT=1) */ if (!resuming) { acpi_ec_submit_request(ec); ec_dbg_ref(ec, "Increase driver"); } ec_log_drv("EC started"); } spin_unlock_irqrestore(&ec->lock, flags); } static bool acpi_ec_stopped(struct acpi_ec *ec) { unsigned long flags; bool flushed; spin_lock_irqsave(&ec->lock, flags); flushed = acpi_ec_flushed(ec); spin_unlock_irqrestore(&ec->lock, flags); return flushed; } static void acpi_ec_stop(struct acpi_ec *ec, bool suspending) { unsigned long flags; spin_lock_irqsave(&ec->lock, flags); if (acpi_ec_started(ec)) { ec_dbg_drv("Stopping EC"); set_bit(EC_FLAGS_STOPPED, &ec->flags); spin_unlock_irqrestore(&ec->lock, flags); wait_event(ec->wait, acpi_ec_stopped(ec)); spin_lock_irqsave(&ec->lock, flags); /* Disable GPE for event processing (SCI_EVT=1) */ if (!suspending) { acpi_ec_complete_request(ec); ec_dbg_ref(ec, "Decrease driver"); } else if (!ec_freeze_events) __acpi_ec_disable_event(ec); clear_bit(EC_FLAGS_STARTED, &ec->flags); clear_bit(EC_FLAGS_STOPPED, &ec->flags); ec_log_drv("EC stopped"); } spin_unlock_irqrestore(&ec->lock, flags); } static void acpi_ec_enter_noirq(struct acpi_ec *ec) { unsigned long flags; spin_lock_irqsave(&ec->lock, flags); ec->busy_polling = true; ec->polling_guard = 0; ec_log_drv("interrupt blocked"); spin_unlock_irqrestore(&ec->lock, flags); } static void acpi_ec_leave_noirq(struct acpi_ec *ec) { unsigned long flags; spin_lock_irqsave(&ec->lock, flags); ec->busy_polling = ec_busy_polling; ec->polling_guard = ec_polling_guard; ec_log_drv("interrupt unblocked"); spin_unlock_irqrestore(&ec->lock, flags); } void acpi_ec_block_transactions(void) { struct acpi_ec *ec = first_ec; if (!ec) return; mutex_lock(&ec->mutex); /* Prevent transactions from being carried out */ acpi_ec_stop(ec, true); mutex_unlock(&ec->mutex); } void acpi_ec_unblock_transactions(void) { /* * Allow transactions to happen again (this function is called from * atomic context during wakeup, so we don't need to acquire the mutex). */ if (first_ec) acpi_ec_start(first_ec, true); } /* -------------------------------------------------------------------------- Event Management -------------------------------------------------------------------------- */ static struct acpi_ec_query_handler * acpi_ec_get_query_handler(struct acpi_ec_query_handler *handler) { if (handler) kref_get(&handler->kref); return handler; } static struct acpi_ec_query_handler * acpi_ec_get_query_handler_by_value(struct acpi_ec *ec, u8 value) { struct acpi_ec_query_handler *handler; bool found = false; mutex_lock(&ec->mutex); list_for_each_entry(handler, &ec->list, node) { if (value == handler->query_bit) { found = true; break; } } mutex_unlock(&ec->mutex); return found ? acpi_ec_get_query_handler(handler) : NULL; } static void acpi_ec_query_handler_release(struct kref *kref) { struct acpi_ec_query_handler *handler = container_of(kref, struct acpi_ec_query_handler, kref); kfree(handler); } static void acpi_ec_put_query_handler(struct acpi_ec_query_handler *handler) { kref_put(&handler->kref, acpi_ec_query_handler_release); } int acpi_ec_add_query_handler(struct acpi_ec *ec, u8 query_bit, acpi_handle handle, acpi_ec_query_func func, void *data) { struct acpi_ec_query_handler *handler = kzalloc(sizeof(struct acpi_ec_query_handler), GFP_KERNEL); if (!handler) return -ENOMEM; handler->query_bit = query_bit; handler->handle = handle; handler->func = func; handler->data = data; mutex_lock(&ec->mutex); kref_init(&handler->kref); list_add(&handler->node, &ec->list); mutex_unlock(&ec->mutex); return 0; } EXPORT_SYMBOL_GPL(acpi_ec_add_query_handler); static void acpi_ec_remove_query_handlers(struct acpi_ec *ec, bool remove_all, u8 query_bit) { struct acpi_ec_query_handler *handler, *tmp; LIST_HEAD(free_list); mutex_lock(&ec->mutex); list_for_each_entry_safe(handler, tmp, &ec->list, node) { if (remove_all || query_bit == handler->query_bit) { list_del_init(&handler->node); list_add(&handler->node, &free_list); } } mutex_unlock(&ec->mutex); list_for_each_entry_safe(handler, tmp, &free_list, node) acpi_ec_put_query_handler(handler); } void acpi_ec_remove_query_handler(struct acpi_ec *ec, u8 query_bit) { acpi_ec_remove_query_handlers(ec, false, query_bit); } EXPORT_SYMBOL_GPL(acpi_ec_remove_query_handler); static struct acpi_ec_query *acpi_ec_create_query(u8 *pval) { struct acpi_ec_query *q; struct transaction *t; q = kzalloc(sizeof (struct acpi_ec_query), GFP_KERNEL); if (!q) return NULL; INIT_WORK(&q->work, acpi_ec_event_processor); t = &q->transaction; t->command = ACPI_EC_COMMAND_QUERY; t->rdata = pval; t->rlen = 1; return q; } static void acpi_ec_delete_query(struct acpi_ec_query *q) { if (q) { if (q->handler) acpi_ec_put_query_handler(q->handler); kfree(q); } } static void acpi_ec_event_processor(struct work_struct *work) { struct acpi_ec_query *q = container_of(work, struct acpi_ec_query, work); struct acpi_ec_query_handler *handler = q->handler; ec_dbg_evt("Query(0x%02x) started", handler->query_bit); if (handler->func) handler->func(handler->data); else if (handler->handle) acpi_evaluate_object(handler->handle, NULL, NULL, NULL); ec_dbg_evt("Query(0x%02x) stopped", handler->query_bit); acpi_ec_delete_query(q); } static int acpi_ec_query(struct acpi_ec *ec, u8 *data) { u8 value = 0; int result; struct acpi_ec_query *q; q = acpi_ec_create_query(&value); if (!q) return -ENOMEM; /* * Query the EC to find out which _Qxx method we need to evaluate. * Note that successful completion of the query causes the ACPI_EC_SCI * bit to be cleared (and thus clearing the interrupt source). */ result = acpi_ec_transaction(ec, &q->transaction); if (!value) result = -ENODATA; if (result) goto err_exit; q->handler = acpi_ec_get_query_handler_by_value(ec, value); if (!q->handler) { result = -ENODATA; goto err_exit; } /* * It is reported that _Qxx are evaluated in a parallel way on * Windows: * https://bugzilla.kernel.org/show_bug.cgi?id=94411 * * Put this log entry before schedule_work() in order to make * it appearing before any other log entries occurred during the * work queue execution. */ ec_dbg_evt("Query(0x%02x) scheduled", value); if (!queue_work(ec_query_wq, &q->work)) { ec_dbg_evt("Query(0x%02x) overlapped", value); result = -EBUSY; } err_exit: if (result) acpi_ec_delete_query(q); if (data) *data = value; return result; } static void acpi_ec_check_event(struct acpi_ec *ec) { unsigned long flags; if (ec_event_clearing == ACPI_EC_EVT_TIMING_EVENT) { if (ec_guard(ec)) { spin_lock_irqsave(&ec->lock, flags); /* * Take care of the SCI_EVT unless no one else is * taking care of it. */ if (!ec->curr) advance_transaction(ec); spin_unlock_irqrestore(&ec->lock, flags); } } } static void acpi_ec_event_handler(struct work_struct *work) { unsigned long flags; struct acpi_ec *ec = container_of(work, struct acpi_ec, work); ec_dbg_evt("Event started"); spin_lock_irqsave(&ec->lock, flags); while (ec->nr_pending_queries) { spin_unlock_irqrestore(&ec->lock, flags); (void)acpi_ec_query(ec, NULL); spin_lock_irqsave(&ec->lock, flags); ec->nr_pending_queries--; /* * Before exit, make sure that this work item can be * scheduled again. There might be QR_EC failures, leaving * EC_FLAGS_QUERY_PENDING uncleared and preventing this work * item from being scheduled again. */ if (!ec->nr_pending_queries) { if (ec_event_clearing == ACPI_EC_EVT_TIMING_STATUS || ec_event_clearing == ACPI_EC_EVT_TIMING_QUERY) acpi_ec_complete_query(ec); } } spin_unlock_irqrestore(&ec->lock, flags); ec_dbg_evt("Event stopped"); acpi_ec_check_event(ec); } static void acpi_ec_handle_interrupt(struct acpi_ec *ec) { unsigned long flags; spin_lock_irqsave(&ec->lock, flags); advance_transaction(ec); spin_unlock_irqrestore(&ec->lock, flags); } static u32 acpi_ec_gpe_handler(acpi_handle gpe_device, u32 gpe_number, void *data) { acpi_ec_handle_interrupt(data); return ACPI_INTERRUPT_HANDLED; } static irqreturn_t acpi_ec_irq_handler(int irq, void *data) { acpi_ec_handle_interrupt(data); return IRQ_HANDLED; } /* -------------------------------------------------------------------------- * Address Space Management * -------------------------------------------------------------------------- */ static acpi_status acpi_ec_space_handler(u32 function, acpi_physical_address address, u32 bits, u64 *value64, void *handler_context, void *region_context) { struct acpi_ec *ec = handler_context; int result = 0, i, bytes = bits / 8; u8 *value = (u8 *)value64; if ((address > 0xFF) || !value || !handler_context) return AE_BAD_PARAMETER; if (function != ACPI_READ && function != ACPI_WRITE) return AE_BAD_PARAMETER; if (ec->busy_polling || bits > 8) acpi_ec_burst_enable(ec); for (i = 0; i < bytes; ++i, ++address, ++value) result = (function == ACPI_READ) ? acpi_ec_read(ec, address, value) : acpi_ec_write(ec, address, *value); if (ec->busy_polling || bits > 8) acpi_ec_burst_disable(ec); switch (result) { case -EINVAL: return AE_BAD_PARAMETER; case -ENODEV: return AE_NOT_FOUND; case -ETIME: return AE_TIME; default: return AE_OK; } } /* -------------------------------------------------------------------------- * Driver Interface * -------------------------------------------------------------------------- */ static acpi_status ec_parse_io_ports(struct acpi_resource *resource, void *context); static void acpi_ec_free(struct acpi_ec *ec) { if (first_ec == ec) first_ec = NULL; if (boot_ec == ec) boot_ec = NULL; kfree(ec); } static struct acpi_ec *acpi_ec_alloc(void) { struct acpi_ec *ec = kzalloc(sizeof(struct acpi_ec), GFP_KERNEL); if (!ec) return NULL; mutex_init(&ec->mutex); init_waitqueue_head(&ec->wait); INIT_LIST_HEAD(&ec->list); spin_lock_init(&ec->lock); INIT_WORK(&ec->work, acpi_ec_event_handler); ec->timestamp = jiffies; ec->busy_polling = true; ec->polling_guard = 0; ec->gpe = -1; ec->irq = -1; return ec; } static acpi_status acpi_ec_register_query_methods(acpi_handle handle, u32 level, void *context, void **return_value) { char node_name[5]; struct acpi_buffer buffer = { sizeof(node_name), node_name }; struct acpi_ec *ec = context; int value = 0; acpi_status status; status = acpi_get_name(handle, ACPI_SINGLE_NAME, &buffer); if (ACPI_SUCCESS(status) && sscanf(node_name, "_Q%x", &value) == 1) acpi_ec_add_query_handler(ec, value, handle, NULL, NULL); return AE_OK; } static acpi_status ec_parse_device(acpi_handle handle, u32 Level, void *context, void **retval) { acpi_status status; unsigned long long tmp = 0; struct acpi_ec *ec = context; /* clear addr values, ec_parse_io_ports depend on it */ ec->command_addr = ec->data_addr = 0; status = acpi_walk_resources(handle, METHOD_NAME__CRS, ec_parse_io_ports, ec); if (ACPI_FAILURE(status)) return status; if (ec->data_addr == 0 || ec->command_addr == 0) return AE_OK; if (boot_ec && boot_ec_is_ecdt && EC_FLAGS_IGNORE_DSDT_GPE) { /* * Always inherit the GPE number setting from the ECDT * EC. */ ec->gpe = boot_ec->gpe; } else { /* Get GPE bit assignment (EC events). */ /* TODO: Add support for _GPE returning a package */ status = acpi_evaluate_integer(handle, "_GPE", NULL, &tmp); if (ACPI_SUCCESS(status)) ec->gpe = tmp; /* * Errors are non-fatal, allowing for ACPI Reduced Hardware * platforms which use GpioInt instead of GPE. */ } /* Use the global lock for all EC transactions? */ tmp = 0; acpi_evaluate_integer(handle, "_GLK", NULL, &tmp); ec->global_lock = tmp; ec->handle = handle; return AE_CTRL_TERMINATE; } static void install_gpe_event_handler(struct acpi_ec *ec) { acpi_status status = acpi_install_gpe_raw_handler(NULL, ec->gpe, ACPI_GPE_EDGE_TRIGGERED, &acpi_ec_gpe_handler, ec); if (ACPI_SUCCESS(status)) { /* This is not fatal as we can poll EC events */ set_bit(EC_FLAGS_EVENT_HANDLER_INSTALLED, &ec->flags); acpi_ec_leave_noirq(ec); if (test_bit(EC_FLAGS_STARTED, &ec->flags) && ec->reference_count >= 1) acpi_ec_enable_gpe(ec, true); } } /* ACPI reduced hardware platforms use a GpioInt specified in _CRS. */ static int install_gpio_irq_event_handler(struct acpi_ec *ec, struct acpi_device *device) { int irq = acpi_dev_gpio_irq_get(device, 0); int ret; if (irq < 0) return irq; ret = request_irq(irq, acpi_ec_irq_handler, IRQF_SHARED, "ACPI EC", ec); /* * Unlike the GPE case, we treat errors here as fatal, we'll only * implement GPIO polling if we find a case that needs it. */ if (ret < 0) return ret; ec->irq = irq; set_bit(EC_FLAGS_EVENT_HANDLER_INSTALLED, &ec->flags); acpi_ec_leave_noirq(ec); return 0; } /* * Note: This function returns an error code only when the address space * handler is not installed, which means "not able to handle * transactions". */ static int ec_install_handlers(struct acpi_ec *ec, struct acpi_device *device, bool handle_events) { acpi_status status; acpi_ec_start(ec, false); if (!test_bit(EC_FLAGS_EC_HANDLER_INSTALLED, &ec->flags)) { acpi_ec_enter_noirq(ec); status = acpi_install_address_space_handler(ec->handle, ACPI_ADR_SPACE_EC, &acpi_ec_space_handler, NULL, ec); if (ACPI_FAILURE(status)) { if (status == AE_NOT_FOUND) { /* * Maybe OS fails in evaluating the _REG * object. The AE_NOT_FOUND error will be * ignored and OS * continue to initialize * EC. */ pr_err("Fail in evaluating the _REG object" " of EC device. Broken bios is suspected.\n"); } else { acpi_ec_stop(ec, false); return -ENODEV; } } set_bit(EC_FLAGS_EC_HANDLER_INSTALLED, &ec->flags); } if (!handle_events) return 0; if (!test_bit(EC_FLAGS_QUERY_METHODS_INSTALLED, &ec->flags)) { /* Find and register all query methods */ acpi_walk_namespace(ACPI_TYPE_METHOD, ec->handle, 1, acpi_ec_register_query_methods, NULL, ec, NULL); set_bit(EC_FLAGS_QUERY_METHODS_INSTALLED, &ec->flags); } if (!test_bit(EC_FLAGS_EVENT_HANDLER_INSTALLED, &ec->flags)) { if (ec->gpe >= 0) { install_gpe_event_handler(ec); } else if (device) { int ret = install_gpio_irq_event_handler(ec, device); if (ret) return ret; } else { /* No GPE and no GpioInt? */ return -ENODEV; } } /* EC is fully operational, allow queries */ acpi_ec_enable_event(ec); return 0; } static void ec_remove_handlers(struct acpi_ec *ec) { if (test_bit(EC_FLAGS_EC_HANDLER_INSTALLED, &ec->flags)) { if (ACPI_FAILURE(acpi_remove_address_space_handler(ec->handle, ACPI_ADR_SPACE_EC, &acpi_ec_space_handler))) pr_err("failed to remove space handler\n"); clear_bit(EC_FLAGS_EC_HANDLER_INSTALLED, &ec->flags); } /* * Stops handling the EC transactions after removing the operation * region handler. This is required because _REG(DISCONNECT) * invoked during the removal can result in new EC transactions. * * Flushes the EC requests and thus disables the GPE before * removing the GPE handler. This is required by the current ACPICA * GPE core. ACPICA GPE core will automatically disable a GPE when * it is indicated but there is no way to handle it. So the drivers * must disable the GPEs prior to removing the GPE handlers. */ acpi_ec_stop(ec, false); if (test_bit(EC_FLAGS_EVENT_HANDLER_INSTALLED, &ec->flags)) { if (ec->gpe >= 0 && ACPI_FAILURE(acpi_remove_gpe_handler(NULL, ec->gpe, &acpi_ec_gpe_handler))) pr_err("failed to remove gpe handler\n"); if (ec->irq >= 0) free_irq(ec->irq, ec); clear_bit(EC_FLAGS_EVENT_HANDLER_INSTALLED, &ec->flags); } if (test_bit(EC_FLAGS_QUERY_METHODS_INSTALLED, &ec->flags)) { acpi_ec_remove_query_handlers(ec, true, 0); clear_bit(EC_FLAGS_QUERY_METHODS_INSTALLED, &ec->flags); } } static int acpi_ec_setup(struct acpi_ec *ec, struct acpi_device *device, bool handle_events) { int ret; ret = ec_install_handlers(ec, device, handle_events); if (ret) return ret; /* First EC capable of handling transactions */ if (!first_ec) { first_ec = ec; acpi_handle_info(first_ec->handle, "Used as first EC\n"); } acpi_handle_info(ec->handle, "GPE=0x%x, IRQ=%d, EC_CMD/EC_SC=0x%lx, EC_DATA=0x%lx\n", ec->gpe, ec->irq, ec->command_addr, ec->data_addr); return ret; } static bool acpi_ec_ecdt_get_handle(acpi_handle *phandle) { struct acpi_table_ecdt *ecdt_ptr; acpi_status status; acpi_handle handle; status = acpi_get_table(ACPI_SIG_ECDT, 1, (struct acpi_table_header **)&ecdt_ptr); if (ACPI_FAILURE(status)) return false; status = acpi_get_handle(NULL, ecdt_ptr->id, &handle); if (ACPI_FAILURE(status)) return false; *phandle = handle; return true; } static int acpi_ec_add(struct acpi_device *device) { struct acpi_ec *ec = NULL; bool dep_update = true; acpi_status status; int ret; strcpy(acpi_device_name(device), ACPI_EC_DEVICE_NAME); strcpy(acpi_device_class(device), ACPI_EC_CLASS); if (!strcmp(acpi_device_hid(device), ACPI_ECDT_HID)) { boot_ec_is_ecdt = true; ec = boot_ec; dep_update = false; } else { ec = acpi_ec_alloc(); if (!ec) return -ENOMEM; status = ec_parse_device(device->handle, 0, ec, NULL); if (status != AE_CTRL_TERMINATE) { ret = -EINVAL; goto err_alloc; } if (boot_ec && ec->command_addr == boot_ec->command_addr && ec->data_addr == boot_ec->data_addr) { boot_ec_is_ecdt = false; /* * Trust PNP0C09 namespace location rather than * ECDT ID. But trust ECDT GPE rather than _GPE * because of ASUS quirks, so do not change * boot_ec->gpe to ec->gpe. */ boot_ec->handle = ec->handle; acpi_handle_debug(ec->handle, "duplicated.\n"); acpi_ec_free(ec); ec = boot_ec; } } ret = acpi_ec_setup(ec, device, true); if (ret) goto err_query; if (ec == boot_ec) acpi_handle_info(boot_ec->handle, "Boot %s EC used to handle transactions and events\n", boot_ec_is_ecdt ? "ECDT" : "DSDT"); device->driver_data = ec; ret = !!request_region(ec->data_addr, 1, "EC data"); WARN(!ret, "Could not request EC data io port 0x%lx", ec->data_addr); ret = !!request_region(ec->command_addr, 1, "EC cmd"); WARN(!ret, "Could not request EC cmd io port 0x%lx", ec->command_addr); if (dep_update) { /* Reprobe devices depending on the EC */ acpi_walk_dep_device_list(ec->handle); } acpi_handle_debug(ec->handle, "enumerated.\n"); return 0; err_query: if (ec != boot_ec) acpi_ec_remove_query_handlers(ec, true, 0); err_alloc: if (ec != boot_ec) acpi_ec_free(ec); return ret; } static int acpi_ec_remove(struct acpi_device *device) { struct acpi_ec *ec; if (!device) return -EINVAL; ec = acpi_driver_data(device); release_region(ec->data_addr, 1); release_region(ec->command_addr, 1); device->driver_data = NULL; if (ec != boot_ec) { ec_remove_handlers(ec); acpi_ec_free(ec); } return 0; } static acpi_status ec_parse_io_ports(struct acpi_resource *resource, void *context) { struct acpi_ec *ec = context; if (resource->type != ACPI_RESOURCE_TYPE_IO) return AE_OK; /* * The first address region returned is the data port, and * the second address region returned is the status/command * port. */ if (ec->data_addr == 0) ec->data_addr = resource->data.io.minimum; else if (ec->command_addr == 0) ec->command_addr = resource->data.io.minimum; else return AE_CTRL_TERMINATE; return AE_OK; } static const struct acpi_device_id ec_device_ids[] = { {"PNP0C09", 0}, {ACPI_ECDT_HID, 0}, {"", 0}, }; /* * This function is not Windows-compatible as Windows never enumerates the * namespace EC before the main ACPI device enumeration process. It is * retained for historical reason and will be deprecated in the future. */ void __init acpi_ec_dsdt_probe(void) { struct acpi_ec *ec; acpi_status status; int ret; /* * If a platform has ECDT, there is no need to proceed as the * following probe is not a part of the ACPI device enumeration, * executing _STA is not safe, and thus this probe may risk of * picking up an invalid EC device. */ if (boot_ec) return; ec = acpi_ec_alloc(); if (!ec) return; /* * At this point, the namespace is initialized, so start to find * the namespace objects. */ status = acpi_get_devices(ec_device_ids[0].id, ec_parse_device, ec, NULL); if (ACPI_FAILURE(status) || !ec->handle) { acpi_ec_free(ec); return; } /* * When the DSDT EC is available, always re-configure boot EC to * have _REG evaluated. _REG can only be evaluated after the * namespace initialization. * At this point, the GPE is not fully initialized, so do not to * handle the events. */ ret = acpi_ec_setup(ec, NULL, false); if (ret) { acpi_ec_free(ec); return; } boot_ec = ec; acpi_handle_info(ec->handle, "Boot DSDT EC used to handle transactions\n"); } /* * If the DSDT EC is not functioning, we still need to prepare a fully * functioning ECDT EC first in order to handle the events. * https://bugzilla.kernel.org/show_bug.cgi?id=115021 */ static int __init acpi_ec_ecdt_start(void) { acpi_handle handle; if (!boot_ec) return -ENODEV; /* In case acpi_ec_ecdt_start() is called after acpi_ec_add() */ if (!boot_ec_is_ecdt) return -ENODEV; /* * At this point, the namespace and the GPE is initialized, so * start to find the namespace objects and handle the events. * * Note: ec->handle can be valid if this function is called after * acpi_ec_add(), hence the fast path. */ if (boot_ec->handle == ACPI_ROOT_OBJECT) { if (!acpi_ec_ecdt_get_handle(&handle)) return -ENODEV; boot_ec->handle = handle; } /* Register to ACPI bus with PM ops attached */ return acpi_bus_register_early_device(ACPI_BUS_TYPE_ECDT_EC); } #if 0 /* * Some EC firmware variations refuses to respond QR_EC when SCI_EVT is not * set, for which case, we complete the QR_EC without issuing it to the * firmware. * https://bugzilla.kernel.org/show_bug.cgi?id=82611 * https://bugzilla.kernel.org/show_bug.cgi?id=97381 */ static int ec_flag_query_handshake(const struct dmi_system_id *id) { pr_debug("Detected the EC firmware requiring QR_EC issued when SCI_EVT set\n"); EC_FLAGS_QUERY_HANDSHAKE = 1; return 0; } #endif /* * On some hardware it is necessary to clear events accumulated by the EC during * sleep. These ECs stop reporting GPEs until they are manually polled, if too * many events are accumulated. (e.g. Samsung Series 5/9 notebooks) * * https://bugzilla.kernel.org/show_bug.cgi?id=44161 * * Ideally, the EC should also be instructed NOT to accumulate events during * sleep (which Windows seems to do somehow), but the interface to control this * behaviour is not known at this time. * * Models known to be affected are Samsung 530Uxx/535Uxx/540Uxx/550Pxx/900Xxx, * however it is very likely that other Samsung models are affected. * * On systems which don't accumulate _Q events during sleep, this extra check * should be harmless. */ static int ec_clear_on_resume(const struct dmi_system_id *id) { pr_debug("Detected system needing EC poll on resume.\n"); EC_FLAGS_CLEAR_ON_RESUME = 1; ec_event_clearing = ACPI_EC_EVT_TIMING_STATUS; return 0; } /* * Some ECDTs contain wrong register addresses. * MSI MS-171F * https://bugzilla.kernel.org/show_bug.cgi?id=12461 */ static int ec_correct_ecdt(const struct dmi_system_id *id) { pr_debug("Detected system needing ECDT address correction.\n"); EC_FLAGS_CORRECT_ECDT = 1; return 0; } /* * Some DSDTs contain wrong GPE setting. * Asus FX502VD/VE, GL702VMK, X550VXK, X580VD * https://bugzilla.kernel.org/show_bug.cgi?id=195651 */ static int ec_honor_ecdt_gpe(const struct dmi_system_id *id) { pr_debug("Detected system needing ignore DSDT GPE setting.\n"); EC_FLAGS_IGNORE_DSDT_GPE = 1; return 0; } static const struct dmi_system_id ec_dmi_table[] __initconst = { { ec_correct_ecdt, "MSI MS-171F", { DMI_MATCH(DMI_SYS_VENDOR, "Micro-Star"), DMI_MATCH(DMI_PRODUCT_NAME, "MS-171F"),}, NULL}, { ec_honor_ecdt_gpe, "ASUS FX502VD", { DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), DMI_MATCH(DMI_PRODUCT_NAME, "FX502VD"),}, NULL}, { ec_honor_ecdt_gpe, "ASUS FX502VE", { DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), DMI_MATCH(DMI_PRODUCT_NAME, "FX502VE"),}, NULL}, { ec_honor_ecdt_gpe, "ASUS GL702VMK", { DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), DMI_MATCH(DMI_PRODUCT_NAME, "GL702VMK"),}, NULL}, { ec_honor_ecdt_gpe, "ASUS X550VXK", { DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), DMI_MATCH(DMI_PRODUCT_NAME, "X550VXK"),}, NULL}, { ec_honor_ecdt_gpe, "ASUS X580VD", { DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), DMI_MATCH(DMI_PRODUCT_NAME, "X580VD"),}, NULL}, { ec_clear_on_resume, "Samsung hardware", { DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD.")}, NULL}, {}, }; void __init acpi_ec_ecdt_probe(void) { struct acpi_table_ecdt *ecdt_ptr; struct acpi_ec *ec; acpi_status status; int ret; /* Generate a boot ec context. */ dmi_check_system(ec_dmi_table); status = acpi_get_table(ACPI_SIG_ECDT, 1, (struct acpi_table_header **)&ecdt_ptr); if (ACPI_FAILURE(status)) return; if (!ecdt_ptr->control.address || !ecdt_ptr->data.address) { /* * Asus X50GL: * https://bugzilla.kernel.org/show_bug.cgi?id=11880 */ return; } ec = acpi_ec_alloc(); if (!ec) return; if (EC_FLAGS_CORRECT_ECDT) { ec->command_addr = ecdt_ptr->data.address; ec->data_addr = ecdt_ptr->control.address; } else { ec->command_addr = ecdt_ptr->control.address; ec->data_addr = ecdt_ptr->data.address; } /* * Ignore the GPE value on Reduced Hardware platforms. * Some products have this set to an erroneous value. */ if (!acpi_gbl_reduced_hardware) ec->gpe = ecdt_ptr->gpe; ec->handle = ACPI_ROOT_OBJECT; /* * At this point, the namespace is not initialized, so do not find * the namespace objects, or handle the events. */ ret = acpi_ec_setup(ec, NULL, false); if (ret) { acpi_ec_free(ec); return; } boot_ec = ec; boot_ec_is_ecdt = true; pr_info("Boot ECDT EC used to handle transactions\n"); } #ifdef CONFIG_PM_SLEEP static int acpi_ec_suspend(struct device *dev) { struct acpi_ec *ec = acpi_driver_data(to_acpi_device(dev)); if (!pm_suspend_no_platform() && ec_freeze_events) acpi_ec_disable_event(ec); return 0; } static int acpi_ec_suspend_noirq(struct device *dev) { struct acpi_ec *ec = acpi_driver_data(to_acpi_device(dev)); /* * The SCI handler doesn't run at this point, so the GPE can be * masked at the low level without side effects. */ if (ec_no_wakeup && test_bit(EC_FLAGS_STARTED, &ec->flags) && ec->gpe >= 0 && ec->reference_count >= 1) acpi_set_gpe(NULL, ec->gpe, ACPI_GPE_DISABLE); acpi_ec_enter_noirq(ec); return 0; } static int acpi_ec_resume_noirq(struct device *dev) { struct acpi_ec *ec = acpi_driver_data(to_acpi_device(dev)); acpi_ec_leave_noirq(ec); if (ec_no_wakeup && test_bit(EC_FLAGS_STARTED, &ec->flags) && ec->gpe >= 0 && ec->reference_count >= 1) acpi_set_gpe(NULL, ec->gpe, ACPI_GPE_ENABLE); return 0; } static int acpi_ec_resume(struct device *dev) { struct acpi_ec *ec = acpi_driver_data(to_acpi_device(dev)); acpi_ec_enable_event(ec); return 0; } void acpi_ec_mark_gpe_for_wake(void) { if (first_ec && !ec_no_wakeup) acpi_mark_gpe_for_wake(NULL, first_ec->gpe); } EXPORT_SYMBOL_GPL(acpi_ec_mark_gpe_for_wake); void acpi_ec_set_gpe_wake_mask(u8 action) { if (pm_suspend_no_platform() && first_ec && !ec_no_wakeup) acpi_set_gpe_wake_mask(NULL, first_ec->gpe, action); } bool acpi_ec_dispatch_gpe(void) { u32 ret; if (!first_ec) return false; ret = acpi_dispatch_gpe(NULL, first_ec->gpe); if (ret == ACPI_INTERRUPT_HANDLED) { pm_pr_dbg("EC GPE dispatched\n"); return true; } return false; } #endif /* CONFIG_PM_SLEEP */ static const struct dev_pm_ops acpi_ec_pm = { SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(acpi_ec_suspend_noirq, acpi_ec_resume_noirq) SET_SYSTEM_SLEEP_PM_OPS(acpi_ec_suspend, acpi_ec_resume) }; static int param_set_event_clearing(const char *val, const struct kernel_param *kp) { int result = 0; if (!strncmp(val, "status", sizeof("status") - 1)) { ec_event_clearing = ACPI_EC_EVT_TIMING_STATUS; pr_info("Assuming SCI_EVT clearing on EC_SC accesses\n"); } else if (!strncmp(val, "query", sizeof("query") - 1)) { ec_event_clearing = ACPI_EC_EVT_TIMING_QUERY; pr_info("Assuming SCI_EVT clearing on QR_EC writes\n"); } else if (!strncmp(val, "event", sizeof("event") - 1)) { ec_event_clearing = ACPI_EC_EVT_TIMING_EVENT; pr_info("Assuming SCI_EVT clearing on event reads\n"); } else result = -EINVAL; return result; } static int param_get_event_clearing(char *buffer, const struct kernel_param *kp) { switch (ec_event_clearing) { case ACPI_EC_EVT_TIMING_STATUS: return sprintf(buffer, "status"); case ACPI_EC_EVT_TIMING_QUERY: return sprintf(buffer, "query"); case ACPI_EC_EVT_TIMING_EVENT: return sprintf(buffer, "event"); default: return sprintf(buffer, "invalid"); } return 0; } module_param_call(ec_event_clearing, param_set_event_clearing, param_get_event_clearing, NULL, 0644); MODULE_PARM_DESC(ec_event_clearing, "Assumed SCI_EVT clearing timing"); static struct acpi_driver acpi_ec_driver = { .name = "ec", .class = ACPI_EC_CLASS, .ids = ec_device_ids, .ops = { .add = acpi_ec_add, .remove = acpi_ec_remove, }, .drv.pm = &acpi_ec_pm, }; static inline int acpi_ec_query_init(void) { if (!ec_query_wq) { ec_query_wq = alloc_workqueue("kec_query", 0, ec_max_queries); if (!ec_query_wq) return -ENODEV; } return 0; } static inline void acpi_ec_query_exit(void) { if (ec_query_wq) { destroy_workqueue(ec_query_wq); ec_query_wq = NULL; } } static const struct dmi_system_id acpi_ec_no_wakeup[] = { { .ident = "Thinkpad X1 Carbon 6th", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), DMI_MATCH(DMI_PRODUCT_FAMILY, "Thinkpad X1 Carbon 6th"), }, }, { .ident = "ThinkPad X1 Carbon 6th", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), DMI_MATCH(DMI_PRODUCT_FAMILY, "ThinkPad X1 Carbon 6th"), }, }, { .ident = "ThinkPad X1 Yoga 3rd", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), DMI_MATCH(DMI_PRODUCT_FAMILY, "ThinkPad X1 Yoga 3rd"), }, }, { }, }; int __init acpi_ec_init(void) { int result; int ecdt_fail, dsdt_fail; /* register workqueue for _Qxx evaluations */ result = acpi_ec_query_init(); if (result) return result; /* * Disable EC wakeup on following systems to prevent periodic * wakeup from EC GPE. */ if (dmi_check_system(acpi_ec_no_wakeup)) { ec_no_wakeup = true; pr_debug("Disabling EC wakeup on suspend-to-idle\n"); } /* Drivers must be started after acpi_ec_query_init() */ dsdt_fail = acpi_bus_register_driver(&acpi_ec_driver); /* * Register ECDT to ACPI bus only when PNP0C09 probe fails. This is * useful for platforms (confirmed on ASUS X550ZE) with valid ECDT * settings but invalid DSDT settings. * https://bugzilla.kernel.org/show_bug.cgi?id=196847 */ ecdt_fail = acpi_ec_ecdt_start(); return ecdt_fail && dsdt_fail ? -ENODEV : 0; } /* EC driver currently not unloadable */ #if 0 static void __exit acpi_ec_exit(void) { acpi_bus_unregister_driver(&acpi_ec_driver); acpi_ec_query_exit(); } #endif /* 0 */ >1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 
/*
 * QEMU disk image utility
 *
 * Copyright (c) 2003-2008 Fabrice Bellard
 *
 * Permission is hereby granted, free of charge, to any person obtaining a copy
 * of this software and associated documentation files (the "Software"), to deal
 * in the Software without restriction, including without limitation the rights
 * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
 * copies of the Software, and to permit persons to whom the Software is
 * furnished to do so, subject to the following conditions:
 *
 * The above copyright notice and this permission notice shall be included in
 * all copies or substantial portions of the Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
 * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
 * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
 * THE SOFTWARE.
 */

#include "qemu/osdep.h"
#include <getopt.h>

#include "qemu/help-texts.h"
#include "qemu/qemu-progress.h"
#include "qemu-version.h"
#include "qapi/error.h"
#include "qapi/qapi-commands-block-core.h"
#include "qapi/qapi-visit-block-core.h"
#include "qapi/qobject-output-visitor.h"
#include "qobject/qjson.h"
#include "qobject/qdict.h"
#include "qemu/cutils.h"
#include "qemu/config-file.h"
#include "qemu/option.h"
#include "qemu/error-report.h"
#include "qemu/log.h"
#include "qemu/main-loop.h"
#include "qemu/module.h"
#include "qemu/sockets.h"
#include "qemu/units.h"
#include "qemu/memalign.h"
#include "qom/object_interfaces.h"
#include "system/block-backend.h"
#include "block/block_int.h"
#include "block/blockjob.h"
#include "block/dirty-bitmap.h"
#include "block/qapi.h"
#include "crypto/init.h"
#include "trace/control.h"
#include "qemu/throttle.h"
#include "block/throttle-groups.h"

#define QEMU_IMG_VERSION "qemu-img version " QEMU_FULL_VERSION \
                          "\n" QEMU_COPYRIGHT "\n"

typedef struct img_cmd_t {
    const char *name;
    int (*handler)(int argc, char **argv);
} img_cmd_t;

enum {
    OPTION_OUTPUT = 256,
    OPTION_BACKING_CHAIN = 257,
    OPTION_OBJECT = 258,
    OPTION_IMAGE_OPTS = 259,
    OPTION_PATTERN = 260,
    OPTION_FLUSH_INTERVAL = 261,
    OPTION_NO_DRAIN = 262,
    OPTION_TARGET_IMAGE_OPTS = 263,
    OPTION_SIZE = 264,
    OPTION_PREALLOCATION = 265,
    OPTION_SHRINK = 266,
    OPTION_SALVAGE = 267,
    OPTION_TARGET_IS_ZERO = 268,
    OPTION_ADD = 269,
    OPTION_REMOVE = 270,
    OPTION_CLEAR = 271,
    OPTION_ENABLE = 272,
    OPTION_DISABLE = 273,
    OPTION_MERGE = 274,
    OPTION_BITMAPS = 275,
    OPTION_FORCE = 276,
    OPTION_SKIP_BROKEN = 277,
};

typedef enum OutputFormat {
    OFORMAT_JSON,
    OFORMAT_HUMAN,
} OutputFormat;

/* Default to cache=writeback as data integrity is not important for qemu-img */
#define BDRV_DEFAULT_CACHE "writeback"

static void format_print(void *opaque, const char *name)
{
    printf(" %s", name);
}

static G_NORETURN G_GNUC_PRINTF(1, 2)
void error_exit(const char *fmt, ...)
{
    va_list ap;

    va_start(ap, fmt);
    error_vreport(fmt, ap);
    va_end(ap);

    error_printf("Try 'qemu-img --help' for more information\n");
    exit(EXIT_FAILURE);
}

static G_NORETURN
void missing_argument(const char *option)
{
    error_exit("missing argument for option '%s'", option);
}

static G_NORETURN
void unrecognized_option(const char *option)
{
    error_exit("unrecognized option '%s'", option);
}

/* Please keep in synch with docs/tools/qemu-img.rst */
static G_NORETURN
void help(void)
{
    const char *help_msg =
           QEMU_IMG_VERSION
           "usage: qemu-img [standard options] command [command options]\n"
           "QEMU disk image utility\n"
           "\n"
           "    '-h', '--help'       display this help and exit\n"
           "    '-V', '--version'    output version information and exit\n"
           "    '-T', '--trace'      [[enable=]<pattern>][,events=<file>][,file=<file>]\n"
           "                         specify tracing options\n"
           "\n"
           "Command syntax:\n"
#define DEF(option, callback, arg_string)        \
           "  " arg_string "\n"
#include "qemu-img-cmds.h"
#undef DEF
           "\n"
           "Command parameters:\n"
           "  'filename' is a disk image filename\n"
           "  'objectdef' is a QEMU user creatable object definition. See the qemu(1)\n"
           "    manual page for a description of the object properties. The most common\n"
           "    object type is a 'secret', which is used to supply passwords and/or\n"
           "    encryption keys.\n"
           "  'fmt' is the disk image format. It is guessed automatically in most cases\n"
           "  'cache' is the cache mode used to write the output disk image, the valid\n"
           "    options are: 'none', 'writeback' (default, except for convert), 'writethrough',\n"
           "    'directsync' and 'unsafe' (default for convert)\n"
           "  'src_cache' is the cache mode used to read input disk images, the valid\n"
           "    options are the same as for the 'cache' option\n"
           "  'size' is the disk image size in bytes. Optional suffixes\n"
           "    'k' or 'K' (kilobyte, 1024), 'M' (megabyte, 1024k), 'G' (gigabyte, 1024M),\n"
           "    'T' (terabyte, 1024G), 'P' (petabyte, 1024T) and 'E' (exabyte, 1024P)  are\n"
           "    supported. 'b' is ignored.\n"
           "  'output_filename' is the destination disk image filename\n"
           "  'output_fmt' is the destination format\n"
           "  'options' is a comma separated list of format specific options in a\n"
           "    name=value format. Use -o help for an overview of the options supported by\n"
           "    the used format\n"
           "  'snapshot_param' is param used for internal snapshot, format\n"
           "    is 'snapshot.id=[ID],snapshot.name=[NAME]', or\n"
           "    '[ID_OR_NAME]'\n"
           "  '-c' indicates that target image must be compressed (qcow format only)\n"
           "  '-u' allows unsafe backing chains. For rebasing, it is assumed that old and\n"
           "       new backing file match exactly. The image doesn't need a working\n"
           "       backing file before rebasing in this case (useful for renaming the\n"
           "       backing file). For image creation, allow creating without attempting\n"
           "       to open the backing file.\n"
           "  '-h' with or without a command shows this help and lists the supported formats\n"
           "  '-p' show progress of command (only certain commands)\n"
           "  '-q' use Quiet mode - do not print any output (except errors)\n"
           "  '-S' indicates the consecutive number of bytes (defaults to 4k) that must\n"
           "       contain only zeros for qemu-img to create a sparse image during\n"
           "       conversion. If the number of bytes is 0, the source will not be scanned for\n"
           "       unallocated or zero sectors, and the destination image will always be\n"
           "       fully allocated\n"
           "  '--output' takes the format in which the output must be done (human or json)\n"
           "  '-n' skips the target volume creation (useful if the volume is created\n"
           "       prior to running qemu-img)\n"
           "\n"
           "Parameters to bitmap subcommand:\n"
           "  'bitmap' is the name of the bitmap to manipulate, through one or more\n"
           "       actions from '--add', '--remove', '--clear', '--enable', '--disable',\n"
           "       or '--merge source'\n"
           "  '-g granularity' sets the granularity for '--add' actions\n"
           "  '-b source' and '-F src_fmt' tell '--merge' actions to find the source\n"
           "       bitmaps from an alternative file\n"
           "\n"
           "Parameters to check subcommand:\n"
           "  '-r' tries to repair any inconsistencies that are found during the check.\n"
           "       '-r leaks' repairs only cluster leaks, whereas '-r all' fixes all\n"
           "       kinds of errors, with a higher risk of choosing the wrong fix or\n"
           "       hiding corruption that has already occurred.\n"
           "\n"
           "Parameters to convert subcommand:\n"
           "  '--bitmaps' copies all top-level persistent bitmaps to destination\n"
           "  '-m' specifies how many coroutines work in parallel during the convert\n"
           "       process (defaults to 8)\n"
           "  '-W' allow to write to the target out of order rather than sequential\n"
           "\n"
           "Parameters to snapshot subcommand:\n"
           "  'snapshot' is the name of the snapshot to create, apply or delete\n"
           "  '-a' applies a snapshot (revert disk to saved state)\n"
           "  '-c' creates a snapshot\n"
           "  '-d' deletes a snapshot\n"
           "  '-l' lists all snapshots in the given image\n"
           "\n"
           "Parameters to compare subcommand:\n"
           "  '-f' first image format\n"
           "  '-F' second image format\n"
           "  '-s' run in Strict mode - fail on different image size or sector allocation\n"
           "\n"
           "Parameters to dd subcommand:\n"
           "  'bs=BYTES' read and write up to BYTES bytes at a time "
           "(default: 512)\n"
           "  'count=N' copy only N input blocks\n"
           "  'if=FILE' read from FILE\n"
           "  'of=FILE' write to FILE\n"
           "  'skip=N' skip N bs-sized blocks at the start of input\n";

    printf("%s\nSupported formats:", help_msg);
    bdrv_iterate_format(format_print, NULL, false);
    printf("\n\n" QEMU_HELP_BOTTOM "\n");
    exit(EXIT_SUCCESS);
}

/*
 * Is @list safe for accumulate_options()?
 * It is when multiple of them can be joined together separated by ','.
 * To make that work, @list must not start with ',' (or else a
 * separating ',' preceding it gets escaped), and it must not end with
 * an odd number of ',' (or else a separating ',' following it gets
 * escaped), or be empty (or else a separating ',' preceding it can
 * escape a separating ',' following it).
 * 
 */
static bool is_valid_option_list(const char *list)
{
    size_t len = strlen(list);
    size_t i;

    if (!list[0] || list[0] == ',') {
        return false;
    }

    for (i = len; i > 0 && list[i - 1] == ','; i--) {
    }
    if ((len - i) % 2) {
        return false;
    }

    return true;
}

static int accumulate_options(char **options, char *list)
{
    char *new_options;

    if (!is_valid_option_list(list)) {
        error_report("Invalid option list: %s", list);
        return -1;
    }

    if (!*options) {
        *options = g_strdup(list);
    } else {
        new_options = g_strdup_printf("%s,%s", *options, list);
        g_free(*options);
        *options = new_options;
    }
    return 0;
}

static QemuOptsList qemu_source_opts = {
    .name = "source",
    .implied_opt_name = "file",
    .head = QTAILQ_HEAD_INITIALIZER(qemu_source_opts.head),
    .desc = {
        { }
    },
};

static int G_GNUC_PRINTF(2, 3) qprintf(bool quiet, const char *fmt, ...)
{
    int ret = 0;
    if (!quiet) {
        va_list args;
        va_start(args, fmt);
        ret = vprintf(fmt, args);
        va_end(args);
    }
    return ret;
}


static int print_block_option_help(const char *filename, const char *fmt)
{
    BlockDriver *drv, *proto_drv;
    QemuOptsList *create_opts = NULL;
    Error *local_err = NULL;

    /* Find driver and parse its options */
    drv = bdrv_find_format(fmt);
    if (!drv) {
        error_report("Unknown file format '%s'", fmt);
        return 1;
    }

    if (!drv->create_opts) {
        error_report("Format driver '%s' does not support image creation", fmt);
        return 1;
    }

    create_opts = qemu_opts_append(create_opts, drv->create_opts);
    if (filename) {
        proto_drv = bdrv_find_protocol(filename, true, &local_err);
        if (!proto_drv) {
            error_report_err(local_err);
            qemu_opts_free(create_opts);
            return 1;
        }
        if (!proto_drv->create_opts) {
            error_report("Protocol driver '%s' does not support image creation",
                         proto_drv->format_name);
            qemu_opts_free(create_opts);
            return 1;
        }
        create_opts = qemu_opts_append(create_opts, proto_drv->create_opts);
    }

    if (filename) {
        printf("Supported options:\n");
    } else {
        printf("Supported %s options:\n", fmt);
    }
    qemu_opts_print_help(create_opts, false);
    qemu_opts_free(create_opts);

    if (!filename) {
        printf("\n"
               "The protocol level may support further options.\n"
               "Specify the target filename to include those options.\n");
    }

    return 0;
}


static BlockBackend *img_open_opts(const char *optstr,
                                   QemuOpts *opts, int flags, bool writethrough,
                                   bool quiet, bool force_share)
{
    QDict *options;
    Error *local_err = NULL;
    BlockBackend *blk;
    options = qemu_opts_to_qdict(opts, NULL);
    if (force_share) {
        if (qdict_haskey(options, BDRV_OPT_FORCE_SHARE)
            && strcmp(qdict_get_str(options, BDRV_OPT_FORCE_SHARE), "on")) {
            error_report("--force-share/-U conflicts with image options");
            qobject_unref(options);
            return NULL;
        }
        qdict_put_str(options, BDRV_OPT_FORCE_SHARE, "on");
    }
    blk = blk_new_open(NULL, NULL, options, flags, &local_err);
    if (!blk) {
        error_reportf_err(local_err, "Could not open '%s': ", optstr);
        return NULL;
    }
    blk_set_enable_write_cache(blk, !writethrough);

    return blk;
}

static BlockBackend *img_open_file(const char *filename,
                                   QDict *options,
                                   const char *fmt, int flags,
                                   bool writethrough, bool quiet,
                                   bool force_share)
{
    BlockBackend *blk;
    Error *local_err = NULL;

    if (!options) {
        options = qdict_new();
    }
    if (fmt) {
        qdict_put_str(options, "driver", fmt);
    }

    if (force_share) {
        qdict_put_bool(options, BDRV_OPT_FORCE_SHARE, true);
    }
    blk = blk_new_open(filename, NULL, options, flags, &local_err);
    if (!blk) {
        error_reportf_err(local_err, "Could not open '%s': ", filename);
        return NULL;
    }
    blk_set_enable_write_cache(blk, !writethrough);

    return blk;
}


static int img_add_key_secrets(void *opaque,
                               const char *name, const char *value,
                               Error **errp)
{
    QDict *options = opaque;

    if (g_str_has_suffix(name, "key-secret")) {
        qdict_put_str(options, name, value);
    }

    return 0;
}


static BlockBackend *img_open(bool image_opts,
                              const char *filename,
                              const char *fmt, int flags, bool writethrough,
                              bool quiet, bool force_share)
{
    BlockBackend *blk;
    if (image_opts) {
        QemuOpts *opts;
        if (fmt) {
            error_report("--image-opts and --format are mutually exclusive");
            return NULL;
        }
        opts = qemu_opts_parse_noisily(qemu_find_opts("source"),
                                       filename, true);
        if (!opts) {
            return NULL;
        }
        blk = img_open_opts(filename, opts, flags, writethrough, quiet,
                            force_share);
    } else {
        blk = img_open_file(filename, NULL, fmt, flags, writethrough, quiet,
                            force_share);
    }

    if (blk) {
        blk_set_force_allow_inactivate(blk);
    }

    return blk;
}


static int add_old_style_options(const char *fmt, QemuOpts *opts,
                                 const char *base_filename,
                                 const char *base_fmt)
{
    if (base_filename) {
        if (!qemu_opt_set(opts, BLOCK_OPT_BACKING_FILE, base_filename,
                          NULL)) {
            error_report("Backing file not supported for file format '%s'",
                         fmt);
            return -1;
        }
    }
    if (base_fmt) {
        if (!qemu_opt_set(opts, BLOCK_OPT_BACKING_FMT, base_fmt, NULL)) {
            error_report("Backing file format not supported for file "
                         "format '%s'", fmt);
            return -1;
        }
    }
    return 0;
}

static int64_t cvtnum_full(const char *name, const char *value, int64_t min,
                           int64_t max)
{
    int err;
    uint64_t res;

    err = qemu_strtosz(value, NULL, &res);
    if (err < 0 && err != -ERANGE) {
        error_report("Invalid %s specified. You may use "
                     "k, M, G, T, P or E suffixes for", name);
        error_report("kilobytes, megabytes, gigabytes, terabytes, "
                     "petabytes and exabytes.");
        return err;
    }
    if (err == -ERANGE || res > max || res < min) {
        error_report("Invalid %s specified. Must be between %" PRId64
                     " and %" PRId64 ".", name, min, max);
        return -ERANGE;
    }
    return res;
}

static int64_t cvtnum(const char *name, const char *value)
{
    return cvtnum_full(name, value, 0, INT64_MAX);
}

static int img_create(int argc, char **argv)
{
    int c;
    uint64_t img_size = -1;
    const char *fmt = "raw";
    const char *base_fmt = NULL;
    const char *filename;
    const char *base_filename = NULL;
    char *options = NULL;
    Error *local_err = NULL;
    bool quiet = false;
    int flags = 0;

    for(;;) {
        static const struct option long_options[] = {
            {"help", no_argument, 0, 'h'},
            {"object", required_argument, 0, OPTION_OBJECT},
            {0, 0, 0, 0}
        };
        c = getopt_long(argc, argv, ":F:b:f:ho:qu",
                        long_options, NULL);
        if (c == -1) {
            break;
        }
        switch(c) {
        case ':':
            missing_argument(argv[optind - 1]);
            break;
        case '?':
            unrecognized_option(argv[optind - 1]);
            break;
        case 'h':
            help();
            break;
        case 'F':
            base_fmt = optarg;
            break;
        case 'b':
            base_filename = optarg;
            break;
        case 'f':
            fmt = optarg;
            break;
        case 'o':
            if (accumulate_options(&options, optarg) < 0) {
                goto fail;
            }
            break;
        case 'q':
            quiet = true;
            break;
        case 'u':
            flags |= BDRV_O_NO_BACKING;
            break;
        case OPTION_OBJECT:
            user_creatable_process_cmdline(optarg);
            break;
        }
    }

    /* Get the filename */
    filename = (optind < argc) ? argv[optind] : NULL;
    if (options && has_help_option(options)) {
        g_free(options);
        return print_block_option_help(filename, fmt);
    }

    if (optind >= argc) {
        error_exit("Expecting image file name");
    }
    optind++;

    /* Get image size, if specified */
    if (optind < argc) {
        int64_t sval;

        sval = cvtnum("image size", argv[optind++]);
        if (sval < 0) {
            goto fail;
        }
        img_size = (uint64_t)sval;
    }
    if (optind != argc) {
        error_exit("Unexpected argument: %s", argv[optind]);
    }

    bdrv_img_create(filename, fmt, base_filename, base_fmt,
                    options, img_size, flags, quiet, &local_err);
    if (local_err) {
        error_reportf_err(local_err, "%s: ", filename);
        goto fail;
    }

    g_free(options);
    return 0;

fail:
    g_free(options);
    return 1;
}

static void dump_json_image_check(ImageCheck *check, bool quiet)
{
    GString *str;
    QObject *obj;
    Visitor *v = qobject_output_visitor_new(&obj);

    visit_type_ImageCheck(v, NULL, &check, &error_abort);
    visit_complete(v, &obj);
    str = qobject_to_json_pretty(obj, true);
    assert(str != NULL);
    qprintf(quiet, "%s\n", str->str);
    qobject_unref(obj);
    visit_free(v);
    g_string_free(str, true);
}

static void dump_human_image_check(ImageCheck *check, bool quiet)
{
    if (!(check->corruptions || check->leaks || check->check_errors)) {
        qprintf(quiet, "No errors were found on the image.\n");
    } else {
        if (check->corruptions) {
            qprintf(quiet, "\n%" PRId64 " errors were found on the image.\n"
                    "Data may be corrupted, or further writes to the image "
                    "may corrupt it.\n",
                    check->corruptions);
        }

        if (check->leaks) {
            qprintf(quiet,
                    "\n%" PRId64 " leaked clusters were found on the image.\n"
                    "This means waste of disk space, but no harm to data.\n",
                    check->leaks);
        }

        if (check->check_errors) {
            qprintf(quiet,
                    "\n%" PRId64
                    " internal errors have occurred during the check.\n",
                    check->check_errors);
        }
    }

    if (check->total_clusters != 0 && check->allocated_clusters != 0) {
        qprintf(quiet, "%" PRId64 "/%" PRId64 " = %0.2f%% allocated, "
                "%0.2f%% fragmented, %0.2f%% compressed clusters\n",
                check->allocated_clusters, check->total_clusters,
                check->allocated_clusters * 100.0 / check->total_clusters,
                check->fragmented_clusters * 100.0 / check->allocated_clusters,
                check->compressed_clusters * 100.0 /
                check->allocated_clusters);
    }

    if (check->image_end_offset) {
        qprintf(quiet,
                "Image end offset: %" PRId64 "\n", check->image_end_offset);
    }
}

static int collect_image_check(BlockDriverState *bs,
                   ImageCheck *check,
                   const char *filename,
                   const char *fmt,
                   int fix)
{
    int ret;
    BdrvCheckResult result;

    ret = bdrv_check(bs, &result, fix);
    if (ret < 0) {
        return ret;
    }

    check->filename                 = g_strdup(filename);
    check->format                   = g_strdup(bdrv_get_format_name(bs));
    check->check_errors             = result.check_errors;
    check->corruptions              = result.corruptions;
    check->has_corruptions          = result.corruptions != 0;
    check->leaks                    = result.leaks;
    check->has_leaks                = result.leaks != 0;
    check->corruptions_fixed        = result.corruptions_fixed;
    check->has_corruptions_fixed    = result.corruptions_fixed != 0;
    check->leaks_fixed              = result.leaks_fixed;
    check->has_leaks_fixed          = result.leaks_fixed != 0;
    check->image_end_offset         = result.image_end_offset;
    check->has_image_end_offset     = result.image_end_offset != 0;
    check->total_clusters           = result.bfi.total_clusters;
    check->has_total_clusters       = result.bfi.total_clusters != 0;
    check->allocated_clusters       = result.bfi.allocated_clusters;
    check->has_allocated_clusters   = result.bfi.allocated_clusters != 0;
    check->fragmented_clusters      = result.bfi.fragmented_clusters;
    check->has_fragmented_clusters  = result.bfi.fragmented_clusters != 0;
    check->compressed_clusters      = result.bfi.compressed_clusters;
    check->has_compressed_clusters  = result.bfi.compressed_clusters != 0;

    return 0;
}

/*
 * Checks an image for consistency. Exit codes:
 *
 *  0 - Check completed, image is good
 *  1 - Check not completed because of internal errors
 *  2 - Check completed, image is corrupted
 *  3 - Check completed, image has leaked clusters, but is good otherwise
 * 63 - Checks are not supported by the image format
 */
static int img_check(int argc, char **argv)
{
    int c, ret;
    OutputFormat output_format = OFORMAT_HUMAN;
    const char *filename, *fmt, *output, *cache;
    BlockBackend *blk;
    BlockDriverState *bs;
    int fix = 0;
    int flags = BDRV_O_CHECK;
    bool writethrough;
    ImageCheck *check;
    bool quiet = false;
    bool image_opts = false;
    bool force_share = false;

    fmt = NULL;
    output = NULL;
    cache = BDRV_DEFAULT_CACHE;

    for(;;) {
        int option_index = 0;
        static const struct option long_options[] = {
            {"help", no_argument, 0, 'h'},
            {"format", required_argument, 0, 'f'},
            {"repair", required_argument, 0, 'r'},
            {"output", required_argument, 0, OPTION_OUTPUT},
            {"object", required_argument, 0, OPTION_OBJECT},
            {"image-opts", no_argument, 0, OPTION_IMAGE_OPTS},
            {"force-share", no_argument, 0, 'U'},
            {0, 0, 0, 0}
        };
        c = getopt_long(argc, argv, ":hf:r:T:qU",
                        long_options, &option_index);
        if (c == -1) {
            break;
        }
        switch(c) {
        case ':':
            missing_argument(argv[optind - 1]);
            break;
        case '?':
            unrecognized_option(argv[optind - 1]);
            break;
        case 'h':
            help();
            break;
        case 'f':
            fmt = optarg;
            break;
        case 'r':
            flags |= BDRV_O_RDWR;

            if (!strcmp(optarg, "leaks")) {
                fix = BDRV_FIX_LEAKS;
            } else if (!strcmp(optarg, "all")) {
                fix = BDRV_FIX_LEAKS | BDRV_FIX_ERRORS;
            } else {
                error_exit("Unknown option value for -r "
                           "(expecting 'leaks' or 'all'): %s", optarg);
            }
            break;
        case OPTION_OUTPUT:
            output = optarg;
            break;
        case 'T':
            cache = optarg;
            break;
        case 'q':
            quiet = true;
            break;
        case 'U':
            force_share = true;
            break;
        case OPTION_OBJECT:
            user_creatable_process_cmdline(optarg);
            break;
        case OPTION_IMAGE_OPTS:
            image_opts = true;
            break;
        }
    }
    if (optind != argc - 1) {
        error_exit("Expecting one image file name");
    }
    filename = argv[optind++];

    if (output && !strcmp(output, "json")) {
        output_format = OFORMAT_JSON;
    } else if (output && !strcmp(output, "human")) {
        output_format = OFORMAT_HUMAN;
    } else if (output) {
        error_report("--output must be used with human or json as argument.");
        return 1;
    }

    ret = bdrv_parse_cache_mode(cache, &flags, &writethrough);
    if (ret < 0) {
        error_report("Invalid source cache option: %s", cache);
        return 1;
    }

    blk = img_open(image_opts, filename, fmt, flags, writethrough, quiet,
                   force_share);
    if (!blk) {
        return 1;
    }
    bs = blk_bs(blk);

    check = g_new0(ImageCheck, 1);
    ret = collect_image_check(bs, check, filename, fmt, fix);

    if (ret == -ENOTSUP) {
        error_report("This image format does not support checks");
        ret = 63;
        goto fail;
    }

    if (check->corruptions_fixed || check->leaks_fixed) {
        int corruptions_fixed, leaks_fixed;
        bool has_leaks_fixed, has_corruptions_fixed;

        leaks_fixed         = check->leaks_fixed;
        has_leaks_fixed     = check->has_leaks_fixed;
        corruptions_fixed   = check->corruptions_fixed;
        has_corruptions_fixed = check->has_corruptions_fixed;

        if (output_format == OFORMAT_HUMAN) {
            qprintf(quiet,
                    "The following inconsistencies were found and repaired:\n\n"
                    "    %" PRId64 " leaked clusters\n"
                    "    %" PRId64 " corruptions\n\n"
                    "Double checking the fixed image now...\n",
                    check->leaks_fixed,
                    check->corruptions_fixed);
        }

        qapi_free_ImageCheck(check);
        check = g_new0(ImageCheck, 1);
        ret = collect_image_check(bs, check, filename, fmt, 0);

        check->leaks_fixed          = leaks_fixed;
        check->has_leaks_fixed      = has_leaks_fixed;
        check->corruptions_fixed    = corruptions_fixed;
        check->has_corruptions_fixed = has_corruptions_fixed;
    }

    if (!ret) {
        switch (output_format) {
        case OFORMAT_HUMAN:
            dump_human_image_check(check, quiet);
            break;
        case OFORMAT_JSON:
            dump_json_image_check(check, quiet);
            break;
        }
    }

    if (ret || check->check_errors) {
        if (ret) {
            error_report("Check failed: %s", strerror(-ret));
        } else {
            error_report("Check failed");
        }
        ret = 1;
        goto fail;
    }

    if (check->corruptions) {
        ret = 2;
    } else if (check->leaks) {
        ret = 3;
    } else {
        ret = 0;
    }

fail:
    qapi_free_ImageCheck(check);
    blk_unref(blk);
    return ret;
}

typedef struct CommonBlockJobCBInfo {
    BlockDriverState *bs;
    Error **errp;
} CommonBlockJobCBInfo;

static void common_block_job_cb(void *opaque, int ret)
{
    CommonBlockJobCBInfo *cbi = opaque;

    if (ret < 0) {
        error_setg_errno(cbi->errp, -ret, "Block job failed");
    }
}

static void run_block_job(BlockJob *job, Error **errp)
{
    uint64_t progress_current, progress_total;
    AioContext *aio_context = block_job_get_aio_context(job);
    int ret = 0;

    job_lock();
    job_ref_locked(&job->job);
    do {
        float progress = 0.0f;
        job_unlock();
        aio_poll(aio_context, true);

        progress_get_snapshot(&job->job.progress, &progress_current,
                              &progress_total);
        if (progress_total) {
            progress = (float)progress_current / progress_total * 100.f;
        }
        qemu_progress_print(progress, 0);
        job_lock();
    } while (!job_is_ready_locked(&job->job) &&
             !job_is_completed_locked(&job->job));

    if (!job_is_completed_locked(&job->job)) {
        ret = job_complete_sync_locked(&job->job, errp);
    } else {
        ret = job->job.ret;
    }
    job_unref_locked(&job->job);
    job_unlock();

    /* publish completion progress only when success */
    if (!ret) {
        qemu_progress_print(100.f, 0);
    }
}

static int img_commit(int argc, char **argv)
{
    int c, ret, flags;
    const char *filename, *fmt, *cache, *base;
    BlockBackend *blk;
    BlockDriverState *bs, *base_bs;
    BlockJob *job;
    bool progress = false, quiet = false, drop = false;
    bool writethrough;
    Error *local_err = NULL;
    CommonBlockJobCBInfo cbi;
    bool image_opts = false;
    int64_t rate_limit = 0;

    fmt = NULL;
    cache = BDRV_DEFAULT_CACHE;
    base = NULL;
    for(;;) {
        static const struct option long_options[] = {
            {"help", no_argument, 0, 'h'},
            {"object", required_argument, 0, OPTION_OBJECT},
            {"image-opts", no_argument, 0, OPTION_IMAGE_OPTS},
            {0, 0, 0, 0}
        };
        c = getopt_long(argc, argv, ":f:ht:b:dpqr:",
                        long_options, NULL);
        if (c == -1) {
            break;
        }
        switch(c) {
        case ':':
            missing_argument(argv[optind - 1]);
            break;
        case '?':
            unrecognized_option(argv[optind - 1]);
            break;
        case 'h':
            help();
            break;
        case 'f':
            fmt = optarg;
            break;
        case 't':
            cache = optarg;
            break;
        case 'b':
            base = optarg;
            /* -b implies -d */
            drop = true;
            break;
        case 'd':
            drop = true;
            break;
        case 'p':
            progress = true;
            break;
        case 'q':
            quiet = true;
            break;
        case 'r':
            rate_limit = cvtnum("rate limit", optarg);
            if (rate_limit < 0) {
                return 1;
            }
            break;
        case OPTION_OBJECT:
            user_creatable_process_cmdline(optarg);
            break;
        case OPTION_IMAGE_OPTS:
            image_opts = true;
            break;
        }
    }

    /* Progress is not shown in Quiet mode */
    if (quiet) {
        progress = false;
    }

    if (optind != argc - 1) {
        error_exit("Expecting one image file name");
    }
    filename = argv[optind++];

    flags = BDRV_O_RDWR | BDRV_O_UNMAP;
    ret = bdrv_parse_cache_mode(cache, &flags, &writethrough);
    if (ret < 0) {
        error_report("Invalid cache option: %s", cache);
        return 1;
    }

    blk = img_open(image_opts, filename, fmt, flags, writethrough, quiet,
                   false);
    if (!blk) {
        return 1;
    }
    bs = blk_bs(blk);

    qemu_progress_init(progress, 1.f);
    qemu_progress_print(0.f, 100);

    bdrv_graph_rdlock_main_loop();
    if (base) {
        base_bs = bdrv_find_backing_image(bs, base);
        if (!base_bs) {
            error_setg(&local_err,
                       "Did not find '%s' in the backing chain of '%s'",
                       base, filename);
            bdrv_graph_rdunlock_main_loop();
            goto done;
        }
    } else {
        /* This is different from QMP, which by default uses the deepest file in
         * the backing chain (i.e., the very base); however, the traditional
         * behavior of qemu-img commit is using the immediate backing file. */
        base_bs = bdrv_backing_chain_next(bs);
        if (!base_bs) {
            error_setg(&local_err, "Image does not have a backing file");
            bdrv_graph_rdunlock_main_loop();
            goto done;
        }
    }
    bdrv_graph_rdunlock_main_loop();

    cbi = (CommonBlockJobCBInfo){
        .errp = &local_err,
        .bs   = bs,
    };

    commit_active_start("commit", bs, base_bs, JOB_DEFAULT, rate_limit,
                        BLOCKDEV_ON_ERROR_REPORT, NULL, common_block_job_cb,
                        &cbi, false, &local_err);
    if (local_err) {
        goto done;
    }

    /* When the block job completes, the BlockBackend reference will point to
     * the old backing file. In order to avoid that the top image is already
     * deleted, so we can still empty it afterwards, increment the reference
     * counter here preemptively. */
    if (!drop) {
        bdrv_ref(bs);
    }

    job = block_job_get("commit");
    assert(job);
    run_block_job(job, &local_err);
    if (local_err) {
        goto unref_backing;
    }

    if (!drop) {
        BlockBackend *old_backing_blk;

        old_backing_blk = blk_new_with_bs(bs, BLK_PERM_WRITE, BLK_PERM_ALL,
                                          &local_err);
        if (!old_backing_blk) {
            goto unref_backing;
        }
        ret = blk_make_empty(old_backing_blk, &local_err);
        blk_unref(old_backing_blk);
        if (ret == -ENOTSUP) {
            error_free(local_err);
            local_err = NULL;
        } else if (ret < 0) {
            goto unref_backing;
        }
    }

unref_backing:
    if (!drop) {
        bdrv_unref(bs);
    }

done:
    qemu_progress_end();

    /*
     * Manually inactivate the image first because this way we can know whether
     * an error occurred. blk_unref() doesn't tell us about failures.
     */
    ret = bdrv_inactivate_all();
    if (ret < 0 && !local_err) {
        error_setg_errno(&local_err, -ret, "Error while closing the image");
    }
    blk_unref(blk);

    if (local_err) {
        error_report_err(local_err);
        return 1;
    }

    qprintf(quiet, "Image committed.\n");
    return 0;
}

/*
 * Returns -1 if 'buf' contains only zeroes, otherwise the byte index
 * of the first sector boundary within buf where the sector contains a
 * non-zero byte.  This function is robust to a buffer that is not
 * sector-aligned.
 */
static int64_t find_nonzero(const uint8_t *buf, int64_t n)
{
    int64_t i;
    int64_t end = QEMU_ALIGN_DOWN(n, BDRV_SECTOR_SIZE);

    for (i = 0; i < end; i += BDRV_SECTOR_SIZE) {
        if (!buffer_is_zero(buf + i, BDRV_SECTOR_SIZE)) {
            return i;
        }
    }
    if (i < n && !buffer_is_zero(buf + i, n - end)) {
        return i;
    }
    return -1;
}

/*
 * Returns true iff the first sector pointed to by 'buf' contains at least
 * a non-NUL byte.
 *
 * 'pnum' is set to the number of sectors (including and immediately following
 * the first one) that are known to be in the same allocated/unallocated state.
 * The function will try to align the end offset to alignment boundaries so
 * that the request will at least end aligned and consecutive requests will
 * also start at an aligned offset.
 */
static int is_allocated_sectors(const uint8_t *buf, int n, int *pnum,
                                int64_t sector_num, int alignment)
{
    bool is_zero;
    int i, tail;

    if (n <= 0) {
        *pnum = 0;
        return 0;
    }
    is_zero = buffer_is_zero(buf, BDRV_SECTOR_SIZE);
    for(i = 1; i < n; i++) {
        buf += BDRV_SECTOR_SIZE;
        if (is_zero != buffer_is_zero(buf, BDRV_SECTOR_SIZE)) {
            break;
        }
    }

    if (i == n) {
        /*
         * The whole buf is the same.
         * No reason to split it into chunks, so return now.
         */
        *pnum = i;
        return !is_zero;
    }

    tail = (sector_num + i) & (alignment - 1);
    if (tail) {
        if (is_zero && i <= tail) {
            /*
             * For sure next sector after i is data, and it will rewrite this
             * tail anyway due to RMW. So, let's just write data now.
             */
            is_zero = false;
        }
        if (!is_zero) {
            /* If possible, align up end offset of allocated areas. */
            i += alignment - tail;
            i = MIN(i, n);
        } else {
            /*
             * For sure next sector after i is data, and it will rewrite this
             * tail anyway due to RMW. Better is avoid RMW and write zeroes up
             * to aligned bound.
             */
            i -= tail;
        }
    }
    *pnum = i;
    return !is_zero;
}

/*
 * Like is_allocated_sectors, but if the buffer starts with a used sector,
 * up to 'min' consecutive sectors containing zeros are ignored. This avoids
 * breaking up write requests for only small sparse areas.
 */
static int is_allocated_sectors_min(const uint8_t *buf, int n, int *pnum,
    int min, int64_t sector_num, int alignment)
{
    int ret;
    int num_checked, num_used;

    if (n < min) {
        min = n;
    }

    ret = is_allocated_sectors(buf, n, pnum, sector_num, alignment);
    if (!ret) {
        return ret;
    }

    num_used = *pnum;
    buf += BDRV_SECTOR_SIZE * *pnum;
    n -= *pnum;
    sector_num += *pnum;
    num_checked = num_used;

    while (n > 0) {
        ret = is_allocated_sectors(buf, n, pnum, sector_num, alignment);

        buf += BDRV_SECTOR_SIZE * *pnum;
        n -= *pnum;
        sector_num += *pnum;
        num_checked += *pnum;
        if (ret) {
            num_used = num_checked;
        } else if (*pnum >= min) {
            break;
        }
    }

    *pnum = num_used;
    return 1;
}

/*
 * Compares two buffers chunk by chunk, where @chsize is the chunk size.
 * If @chsize is 0, default chunk size of BDRV_SECTOR_SIZE is used.
 * Returns 0 if the first chunk of each buffer matches, non-zero otherwise.
 *
 * @pnum is set to the size of the buffer prefix aligned to @chsize that
 * has the same matching status as the first chunk.
 */
static int compare_buffers(const uint8_t *buf1, const uint8_t *buf2,
                           int64_t bytes, uint64_t chsize, int64_t *pnum)
{
    bool res;
    int64_t i;

    assert(bytes > 0);

    if (!chsize) {
        chsize = BDRV_SECTOR_SIZE;
    }
    i = MIN(bytes, chsize);

    res = !!memcmp(buf1, buf2, i);
    while (i < bytes) {
        int64_t len = MIN(bytes - i, chsize);

        if (!!memcmp(buf1 + i, buf2 + i, len) != res) {
            break;
        }
        i += len;
    }

    *pnum = i;
    return res;
}

#define IO_BUF_SIZE (2 * MiB)

/*
 * Check if passed sectors are empty (not allocated or contain only 0 bytes)
 *
 * Intended for use by 'qemu-img compare': Returns 0 in case sectors are
 * filled with 0, 1 if sectors contain non-zero data (this is a comparison
 * failure), and 4 on error (the exit status for read errors), after emitting
 * an error message.
 *
 * @param blk:  BlockBackend for the image
 * @param offset: Starting offset to check
 * @param bytes: Number of bytes to check
 * @param filename: Name of disk file we are checking (logging purpose)
 * @param buffer: Allocated buffer for storing read data
 * @param quiet: Flag for quiet mode
 */
static int check_empty_sectors(BlockBackend *blk, int64_t offset,
                               int64_t bytes, const char *filename,
                               uint8_t *buffer, bool quiet)
{
    int ret = 0;
    int64_t idx;

    ret = blk_pread(blk, offset, bytes, buffer, 0);
    if (ret < 0) {
        error_report("Error while reading offset %" PRId64 " of %s: %s",
                     offset, filename, strerror(-ret));
        return 4;
    }
    idx = find_nonzero(buffer, bytes);
    if (idx >= 0) {
        qprintf(quiet, "Content mismatch at offset %" PRId64 "!\n",
                offset + idx);
        return 1;
    }

    return 0;
}

/*
 * Compares two images. Exit codes:
 *
 * 0 - Images are identical or the requested help was printed
 * 1 - Images differ
 * >1 - Error occurred
 */
static int img_compare(int argc, char **argv)
{
    const char *fmt1 = NULL, *fmt2 = NULL, *cache, *filename1, *filename2;
    BlockBackend *blk1, *blk2;
    BlockDriverState *bs1, *bs2;
    int64_t total_size1, total_size2;
    uint8_t *buf1 = NULL, *buf2 = NULL;
    int64_t pnum1, pnum2;
    int allocated1, allocated2;
    int ret = 0; /* return value - 0 Ident, 1 Different, >1 Error */
    bool progress = false, quiet = false, strict = false;
    int flags;
    bool writethrough;
    int64_t total_size;
    int64_t offset = 0;
    int64_t chunk;
    int c;
    uint64_t progress_base;
    bool image_opts = false;
    bool force_share = false;

    cache = BDRV_DEFAULT_CACHE;
    for (;;) {
        static const struct option long_options[] = {
            {"help", no_argument, 0, 'h'},
            {"object", required_argument, 0, OPTION_OBJECT},
            {"image-opts", no_argument, 0, OPTION_IMAGE_OPTS},
            {"force-share", no_argument, 0, 'U'},
            {0, 0, 0, 0}
        };
        c = getopt_long(argc, argv, ":hf:F:T:pqsU",
                        long_options, NULL);
        if (c == -1) {
            break;
        }
        switch (c) {
        case ':':
            missing_argument(argv[optind - 1]);
            break;
        case '?':
            unrecognized_option(argv[optind - 1]);
            break;
        case 'h':
            help();
            break;
        case 'f':
            fmt1 = optarg;
            break;
        case 'F':
            fmt2 = optarg;
            break;
        case 'T':
            cache = optarg;
            break;
        case 'p':
            progress = true;
            break;
        case 'q':
            quiet = true;
            break;
        case 's':
            strict = true;
            break;
        case 'U':
            force_share = true;
            break;
        case OPTION_OBJECT:
            {
                Error *local_err = NULL;

                if (!user_creatable_add_from_str(optarg, &local_err)) {
                    if (local_err) {
                        error_report_err(local_err);
                        exit(2);
                    } else {
                        /* Help was printed */
                        exit(EXIT_SUCCESS);
                    }
                }
                break;
            }
        case OPTION_IMAGE_OPTS:
            image_opts = true;
            break;
        }
    }

    /* Progress is not shown in Quiet mode */
    if (quiet) {
        progress = false;
    }


    if (optind != argc - 2) {
        error_exit("Expecting two image file names");
    }
    filename1 = argv[optind++];
    filename2 = argv[optind++];

    /* Initialize before goto out */
    qemu_progress_init(progress, 2.0);

    flags = 0;
    ret = bdrv_parse_cache_mode(cache, &flags, &writethrough);
    if (ret < 0) {
        error_report("Invalid source cache option: %s", cache);
        ret = 2;
        goto out3;
    }

    blk1 = img_open(image_opts, filename1, fmt1, flags, writethrough, quiet,
                    force_share);
    if (!blk1) {
        ret = 2;
        goto out3;
    }

    blk2 = img_open(image_opts, filename2, fmt2, flags, writethrough, quiet,
                    force_share);
    if (!blk2) {
        ret = 2;
        goto out2;
    }
    bs1 = blk_bs(blk1);
    bs2 = blk_bs(blk2);

    buf1 = blk_blockalign(blk1, IO_BUF_SIZE);
    buf2 = blk_blockalign(blk2, IO_BUF_SIZE);
    total_size1 = blk_getlength(blk1);
    if (total_size1 < 0) {
        error_report("Can't get size of %s: %s",
                     filename1, strerror(-total_size1));
        ret = 4;
        goto out;
    }
    total_size2 = blk_getlength(blk2);
    if (total_size2 < 0) {
        error_report("Can't get size of %s: %s",
                     filename2, strerror(-total_size2));
        ret = 4;
        goto out;
    }
    total_size = MIN(total_size1, total_size2);
    progress_base = MAX(total_size1, total_size2);

    qemu_progress_print(0, 100);

    if (strict && total_size1 != total_size2) {
        ret = 1;
        qprintf(quiet, "Strict mode: Image size mismatch!\n");
        goto out;
    }

    while (offset < total_size) {
        int status1, status2;

        status1 = bdrv_block_status_above(bs1, NULL, offset,
                                          total_size1 - offset, &pnum1, NULL,
                                          NULL);
        if (status1 < 0) {
            ret = 3;
            error_report("Sector allocation test failed for %s", filename1);
            goto out;
        }
        allocated1 = status1 & BDRV_BLOCK_ALLOCATED;

        status2 = bdrv_block_status_above(bs2, NULL, offset,
                                          total_size2 - offset, &pnum2, NULL,
                                          NULL);
        if (status2 < 0) {
            ret = 3;
            error_report("Sector allocation test failed for %s", filename2);
            goto out;
        }
        allocated2 = status2 & BDRV_BLOCK_ALLOCATED;

        assert(pnum1 && pnum2);
        chunk = MIN(pnum1, pnum2);

        if (strict) {
            if (status1 != status2) {
                ret = 1;
                qprintf(quiet, "Strict mode: Offset %" PRId64
                        " block status mismatch!\n", offset);
                goto out;
            }
        }
        if ((status1 & BDRV_BLOCK_ZERO) && (status2 & BDRV_BLOCK_ZERO)) {
            /* nothing to do */
        } else if (allocated1 == allocated2) {
            if (allocated1) {
                int64_t pnum;

                chunk = MIN(chunk, IO_BUF_SIZE);
                ret = blk_pread(blk1, offset, chunk, buf1, 0);
                if (ret < 0) {
                    error_report("Error while reading offset %" PRId64
                                 " of %s: %s",
                                 offset, filename1, strerror(-ret));
                    ret = 4;
                    goto out;
                }
                ret = blk_pread(blk2, offset, chunk, buf2, 0);
                if (ret < 0) {
                    error_report("Error while reading offset %" PRId64
                                 " of %s: %s",
                                 offset, filename2, strerror(-ret));
                    ret = 4;
                    goto out;
                }
                ret = compare_buffers(buf1, buf2, chunk, 0, &pnum);
                if (ret || pnum != chunk) {
                    qprintf(quiet, "Content mismatch at offset %" PRId64 "!\n",
                            offset + (ret ? 0 : pnum));
                    ret = 1;
                    goto out;
                }
            }
        } else {
            chunk = MIN(chunk, IO_BUF_SIZE);
            if (allocated1) {
                ret = check_empty_sectors(blk1, offset, chunk,
                                          filename1, buf1, quiet);
            } else {
                ret = check_empty_sectors(blk2, offset, chunk,
                                          filename2, buf1, quiet);
            }
            if (ret) {
                goto out;
            }
        }
        offset += chunk;
        qemu_progress_print(((float) chunk / progress_base) * 100, 100);
    }

    if (total_size1 != total_size2) {
        BlockBackend *blk_over;
        const char *filename_over;

        qprintf(quiet, "Warning: Image size mismatch!\n");
        if (total_size1 > total_size2) {
            blk_over = blk1;
            filename_over = filename1;
        } else {
            blk_over = blk2;
            filename_over = filename2;
        }

        while (offset < progress_base) {
            ret = bdrv_block_status_above(blk_bs(blk_over), NULL, offset,
                                          progress_base - offset, &chunk,
                                          NULL, NULL);
            if (ret < 0) {
                ret = 3;
                error_report("Sector allocation test failed for %s",
                             filename_over);
                goto out;

            }
            if (ret & BDRV_BLOCK_ALLOCATED && !(ret & BDRV_BLOCK_ZERO)) {
                chunk = MIN(chunk, IO_BUF_SIZE);
                ret = check_empty_sectors(blk_over, offset, chunk,
                                          filename_over, buf1, quiet);
                if (ret) {
                    goto out;
                }
            }
            offset += chunk;
            qemu_progress_print(((float) chunk / progress_base) * 100, 100);
        }
    }

    qprintf(quiet, "Images are identical.\n");
    ret = 0;

out:
    qemu_vfree(buf1);
    qemu_vfree(buf2);
    blk_unref(blk2);
out2:
    blk_unref(blk1);
out3:
    qemu_progress_end();
    return ret;
}

/* Convenience wrapper around qmp_block_dirty_bitmap_merge */
static void do_dirty_bitmap_merge(const char *dst_node, const char *dst_name,
                                  const char *src_node, const char *src_name,
                                  Error **errp)
{
    BlockDirtyBitmapOrStr *merge_src;
    BlockDirtyBitmapOrStrList *list = NULL;

    merge_src = g_new0(BlockDirtyBitmapOrStr, 1);
    merge_src->type = QTYPE_QDICT;
    merge_src->u.external.node = g_strdup(src_node);
    merge_src->u.external.name = g_strdup(src_name);
    QAPI_LIST_PREPEND(list, merge_src);
    qmp_block_dirty_bitmap_merge(dst_node, dst_name, list, errp);
    qapi_free_BlockDirtyBitmapOrStrList(list);
}

enum ImgConvertBlockStatus {
    BLK_DATA,
    BLK_ZERO,
    BLK_BACKING_FILE,
};

#define MAX_COROUTINES 16
#define CONVERT_THROTTLE_GROUP "img_convert"

typedef struct ImgConvertState {
    BlockBackend **src;
    int64_t *src_sectors;
    int *src_alignment;
    int src_num;
    int64_t total_sectors;
    int64_t allocated_sectors;
    int64_t allocated_done;
    int64_t sector_num;
    int64_t wr_offs;
    enum ImgConvertBlockStatus status;
    int64_t sector_next_status;
    BlockBackend *target;
    bool has_zero_init;
    bool compressed;
    bool target_is_new;
    bool target_has_backing;
    int64_t target_backing_sectors; /* negative if unknown */
    bool wr_in_order;
    bool copy_range;
    bool salvage;
    bool quiet;
    int min_sparse;
    int alignment;
    size_t cluster_sectors;
    size_t buf_sectors;
    long num_coroutines;
    int running_coroutines;
    Coroutine *co[MAX_COROUTINES];
    int64_t wait_sector_num[MAX_COROUTINES];
    CoMutex lock;
    int ret;
} ImgConvertState;

static void convert_select_part(ImgConvertState *s, int64_t sector_num,
                                int *src_cur, int64_t *src_cur_offset)
{
    *src_cur = 0;
    *src_cur_offset = 0;
    while (sector_num - *src_cur_offset >= s->src_sectors[*src_cur]) {
        *src_cur_offset += s->src_sectors[*src_cur];
        (*src_cur)++;
        assert(*src_cur < s->src_num);
    }
}

static int coroutine_mixed_fn GRAPH_RDLOCK
convert_iteration_sectors(ImgConvertState *s, int64_t sector_num)
{
    int64_t src_cur_offset;
    int ret, n, src_cur;
    bool post_backing_zero = false;

    convert_select_part(s, sector_num, &src_cur, &src_cur_offset);

    assert(s->total_sectors > sector_num);
    n = MIN(s->total_sectors - sector_num, BDRV_REQUEST_MAX_SECTORS);

    if (s->target_backing_sectors >= 0) {
        if (sector_num >= s->target_backing_sectors) {
            post_backing_zero = true;
        } else if (sector_num + n > s->target_backing_sectors) {
            /* Split requests around target_backing_sectors (because
             * starting from there, zeros are handled differently) */
            n = s->target_backing_sectors - sector_num;
        }
    }

    if (s->sector_next_status <= sector_num) {
        uint64_t offset = (sector_num - src_cur_offset) * BDRV_SECTOR_SIZE;
        int64_t count;
        int tail;
        BlockDriverState *src_bs = blk_bs(s->src[src_cur]);
        BlockDriverState *base;

        if (s->target_has_backing) {
            base = bdrv_cow_bs(bdrv_skip_filters(src_bs));
        } else {
            base = NULL;
        }

        do {
            count = n * BDRV_SECTOR_SIZE;

            ret = bdrv_block_status_above(src_bs, base, offset, count, &count,
                                          NULL, NULL);

            if (ret < 0) {
                if (s->salvage) {
                    if (n == 1) {
                        if (!s->quiet) {
                            warn_report("error while reading block status at "
                                        "offset %" PRIu64 ": %s", offset,
                                        strerror(-ret));
                        }
                        /* Just try to read the data, then */
                        ret = BDRV_BLOCK_DATA;
                        count = BDRV_SECTOR_SIZE;
                    } else {
                        /* Retry on a shorter range */
                        n = DIV_ROUND_UP(n, 4);
                    }
                } else {
                    error_report("error while reading block status at offset "
                                 "%" PRIu64 ": %s", offset, strerror(-ret));
                    return ret;
                }
            }
        } while (ret < 0);

        n = DIV_ROUND_UP(count, BDRV_SECTOR_SIZE);

        /*
         * Avoid that s->sector_next_status becomes unaligned to the source
         * request alignment and/or cluster size to avoid unnecessary read
         * cycles.
         */
        tail = (sector_num - src_cur_offset + n) % s->src_alignment[src_cur];
        if (n > tail) {
            n -= tail;
        }

        if (ret & BDRV_BLOCK_ZERO) {
            s->status = post_backing_zero ? BLK_BACKING_FILE : BLK_ZERO;
        } else if (ret & BDRV_BLOCK_DATA) {
            s->status = BLK_DATA;
        } else {
            s->status = s->target_has_backing ? BLK_BACKING_FILE : BLK_DATA;
        }

        s->sector_next_status = sector_num + n;
    }

    n = MIN(n, s->sector_next_status - sector_num);
    if (s->status == BLK_DATA) {
        n = MIN(n, s->buf_sectors);
    }

    /* We need to write complete clusters for compressed images, so if an
     * unallocated area is shorter than that, we must consider the whole
     * cluster allocated. */
    if (s->compressed) {
        if (n < s->cluster_sectors) {
            n = MIN(s->cluster_sectors, s->total_sectors - sector_num);
            s->status = BLK_DATA;
        } else {
            n = QEMU_ALIGN_DOWN(n, s->cluster_sectors);
        }
    }

    return n;
}

static int coroutine_fn convert_co_read(ImgConvertState *s, int64_t sector_num,
                                        int nb_sectors, uint8_t *buf)
{
    uint64_t single_read_until = 0;
    int n, ret;

    assert(nb_sectors <= s->buf_sectors);
    while (nb_sectors > 0) {
        BlockBackend *blk;
        int src_cur;
        int64_t bs_sectors, src_cur_offset;
        uint64_t offset;

        /* In the case of compression with multiple source files, we can get a
         * nb_sectors that spreads into the next part. So we must be able to
         * read across multiple BDSes for one convert_read() call. */
        convert_select_part(s, sector_num, &src_cur, &src_cur_offset);
        blk = s->src[src_cur];
        bs_sectors = s->src_sectors[src_cur];

        offset = (sector_num - src_cur_offset) << BDRV_SECTOR_BITS;

        n = MIN(nb_sectors, bs_sectors - (sector_num - src_cur_offset));
        if (single_read_until > offset) {
            n = 1;
        }

        ret = blk_co_pread(blk, offset, n << BDRV_SECTOR_BITS, buf, 0);
        if (ret < 0) {
            if (s->salvage) {
                if (n > 1) {
                    single_read_until = offset + (n << BDRV_SECTOR_BITS);
                    continue;
                } else {
                    if (!s->quiet) {
                        warn_report("error while reading offset %" PRIu64
                                    ": %s", offset, strerror(-ret));
                    }
                    memset(buf, 0, BDRV_SECTOR_SIZE);
                }
            } else {
                return ret;
            }
        }

        sector_num += n;
        nb_sectors -= n;
        buf += n * BDRV_SECTOR_SIZE;
    }

    return 0;
}


static int coroutine_fn convert_co_write(ImgConvertState *s, int64_t sector_num,
                                         int nb_sectors, uint8_t *buf,
                                         enum ImgConvertBlockStatus status)
{
    int ret;

    while (nb_sectors > 0) {
        int n = nb_sectors;
        BdrvRequestFlags flags = s->compressed ? BDRV_REQ_WRITE_COMPRESSED : 0;

        switch (status) {
        case BLK_BACKING_FILE:
            /* If we have a backing file, leave clusters unallocated that are
             * unallocated in the source image, so that the backing file is
             * visible at the respective offset. */
            assert(s->target_has_backing);
            break;

        case BLK_DATA:
            /* If we're told to keep the target fully allocated (-S 0) or there
             * is real non-zero data, we must write it. Otherwise we can treat
             * it as zero sectors.
             * Compressed clusters need to be written as a whole, so in that
             * case we can only save the write if the buffer is completely
             * zeroed. */
            if (!s->min_sparse ||
                (!s->compressed &&
                 is_allocated_sectors_min(buf, n, &n, s->min_sparse,
                                          sector_num, s->alignment)) ||
                (s->compressed &&
                 !buffer_is_zero(buf, n * BDRV_SECTOR_SIZE)))
            {
                ret = blk_co_pwrite(s->target, sector_num << BDRV_SECTOR_BITS,
                                    n << BDRV_SECTOR_BITS, buf, flags);
                if (ret < 0) {
                    return ret;
                }
                break;
            }
            /* fall-through */

        case BLK_ZERO:
            if (s->has_zero_init) {
                assert(!s->target_has_backing);
                break;
            }
            ret = blk_co_pwrite_zeroes(s->target,
                                       sector_num << BDRV_SECTOR_BITS,
                                       n << BDRV_SECTOR_BITS,
                                       BDRV_REQ_MAY_UNMAP);
            if (ret < 0) {
                return ret;
            }
            break;
        }

        sector_num += n;
        nb_sectors -= n;
        buf += n * BDRV_SECTOR_SIZE;
    }

    return 0;
}

static int coroutine_fn convert_co_copy_range(ImgConvertState *s, int64_t sector_num,
                                              int nb_sectors)
{
    int n, ret;

    while (nb_sectors > 0) {
        BlockBackend *blk;
        int src_cur;
        int64_t bs_sectors, src_cur_offset;
        int64_t offset;

        convert_select_part(s, sector_num, &src_cur, &src_cur_offset);
        offset = (sector_num - src_cur_offset) << BDRV_SECTOR_BITS;
        blk = s->src[src_cur];
        bs_sectors = s->src_sectors[src_cur];

        n = MIN(nb_sectors, bs_sectors - (sector_num - src_cur_offset));

        ret = blk_co_copy_range(blk, offset, s->target,
                                sector_num << BDRV_SECTOR_BITS,
                                n << BDRV_SECTOR_BITS, 0, 0);
        if (ret < 0) {
            return ret;
        }

        sector_num += n;
        nb_sectors -= n;
    }
    return 0;
}

static void coroutine_fn convert_co_do_copy(void *opaque)
{
    ImgConvertState *s = opaque;
    uint8_t *buf = NULL;
    int ret, i;
    int index = -1;

    for (i = 0; i < s->num_coroutines; i++) {
        if (s->co[i] == qemu_coroutine_self()) {
            index = i;
            break;
        }
    }
    assert(index >= 0);

    s->running_coroutines++;
    buf = blk_blockalign(s->target, s->buf_sectors * BDRV_SECTOR_SIZE);

    while (1) {
        int n;
        int64_t sector_num;
        enum ImgConvertBlockStatus status;
        bool copy_range;

        qemu_co_mutex_lock(&s->lock);
        if (s->ret != -EINPROGRESS || s->sector_num >= s->total_sectors) {
            qemu_co_mutex_unlock(&s->lock);
            break;
        }
        WITH_GRAPH_RDLOCK_GUARD() {
            n = convert_iteration_sectors(s, s->sector_num);
        }
        if (n < 0) {
            qemu_co_mutex_unlock(&s->lock);
            s->ret = n;
            break;
        }
        /* save current sector and allocation status to local variables */
        sector_num = s->sector_num;
        status = s->status;
        if (!s->min_sparse && s->status == BLK_ZERO) {
            n = MIN(n, s->buf_sectors);
        }
        /* increment global sector counter so that other coroutines can
         * already continue reading beyond this request */
        s->sector_num += n;
        qemu_co_mutex_unlock(&s->lock);

        if (status == BLK_DATA || (!s->min_sparse && status == BLK_ZERO)) {
            s->allocated_done += n;
            qemu_progress_print(100.0 * s->allocated_done /
                                        s->allocated_sectors, 0);
        }

retry:
        copy_range = s->copy_range && s->status == BLK_DATA;
        if (status == BLK_DATA && !copy_range) {
            ret = convert_co_read(s, sector_num, n, buf);
            if (ret < 0) {
                error_report("error while reading at byte %lld: %s",
                             sector_num * BDRV_SECTOR_SIZE, strerror(-ret));
                s->ret = ret;
            }
        } else if (!s->min_sparse && status == BLK_ZERO) {
            status = BLK_DATA;
            memset(buf, 0x00, n * BDRV_SECTOR_SIZE);
        }

        if (s->wr_in_order) {
            /* keep writes in order */
            while (s->wr_offs != sector_num && s->ret == -EINPROGRESS) {
                s->wait_sector_num[index] = sector_num;
                qemu_coroutine_yield();
            }
            s->wait_sector_num[index] = -1;
        }

        if (s->ret == -EINPROGRESS) {
            if (copy_range) {
                WITH_GRAPH_RDLOCK_GUARD() {
                    ret = convert_co_copy_range(s, sector_num, n);
                }
                if (ret) {
                    s->copy_range = false;
                    goto retry;
                }
            } else {
                ret = convert_co_write(s, sector_num, n, buf, status);
            }
            if (ret < 0) {
                error_report("error while writing at byte %lld: %s",
                             sector_num * BDRV_SECTOR_SIZE, strerror(-ret));
                s->ret = ret;
            }
        }

        if (s->wr_in_order) {
            /* reenter the coroutine that might have waited
             * for this write to complete */
            s->wr_offs = sector_num + n;
            for (i = 0; i < s->num_coroutines; i++) {
                if (s->co[i] && s->wait_sector_num[i] == s->wr_offs) {
                    /*
                     * A -> B -> A cannot occur because A has
                     * s->wait_sector_num[i] == -1 during A -> B.  Therefore
                     * B will never enter A during this time window.
                     */
                    qemu_coroutine_enter(s->co[i]);
                    break;
                }
            }
        }
    }

    qemu_vfree(buf);
    s->co[index] = NULL;
    s->running_coroutines--;
    if (!s->running_coroutines && s->ret == -EINPROGRESS) {
        /* the convert job finished successfully */
        s->ret = 0;
    }
}

static int convert_do_copy(ImgConvertState *s)
{
    int ret, i, n;
    int64_t sector_num = 0;

    /* Check whether we have zero initialisation or can get it efficiently */
    if (!s->has_zero_init && s->target_is_new && s->min_sparse &&
        !s->target_has_backing) {
        bdrv_graph_rdlock_main_loop();
        s->has_zero_init = bdrv_has_zero_init(blk_bs(s->target));
        bdrv_graph_rdunlock_main_loop();
    }

    /* Allocate buffer for copied data. For compressed images, only one cluster
     * can be copied at a time. */
    if (s->compressed) {
        if (s->cluster_sectors <= 0 || s->cluster_sectors > s->buf_sectors) {
            error_report("invalid cluster size");
            return -EINVAL;
        }
        s->buf_sectors = s->cluster_sectors;
    }

    while (sector_num < s->total_sectors) {
        bdrv_graph_rdlock_main_loop();
        n = convert_iteration_sectors(s, sector_num);
        bdrv_graph_rdunlock_main_loop();
        if (n < 0) {
            return n;
        }
        if (s->status == BLK_DATA || (!s->min_sparse && s->status == BLK_ZERO))
        {
            s->allocated_sectors += n;
        }
        sector_num += n;
    }

    /* Do the copy */
    s->sector_next_status = 0;
    s->ret = -EINPROGRESS;

    qemu_co_mutex_init(&s->lock);
    for (i = 0; i < s->num_coroutines; i++) {
        s->co[i] = qemu_coroutine_create(convert_co_do_copy, s);
        s->wait_sector_num[i] = -1;
        qemu_coroutine_enter(s->co[i]);
    }

    while (s->running_coroutines) {
        main_loop_wait(false);
    }

    if (s->compressed && !s->ret) {
        /* signal EOF to align */
        ret = blk_pwrite_compressed(s->target, 0, 0, NULL);
        if (ret < 0) {
            return ret;
        }
    }

    return s->ret;
}

/* Check that bitmaps can be copied, or output an error */
static int convert_check_bitmaps(BlockDriverState *src, bool skip_broken)
{
    BdrvDirtyBitmap *bm;

    if (!bdrv_supports_persistent_dirty_bitmap(src)) {
        error_report("Source lacks bitmap support");
        return -1;
    }
    FOR_EACH_DIRTY_BITMAP(src, bm) {
        if (!bdrv_dirty_bitmap_get_persistence(bm)) {
            continue;
        }
        if (!skip_broken && bdrv_dirty_bitmap_inconsistent(bm)) {
            error_report("Cannot copy inconsistent bitmap '%s'",
                         bdrv_dirty_bitmap_name(bm));
            error_printf("Try --skip-broken-bitmaps, or "
                         "use 'qemu-img bitmap --remove' to delete it\n");
            return -1;
        }
    }
    return 0;
}

static int convert_copy_bitmaps(BlockDriverState *src, BlockDriverState *dst,
                                bool skip_broken)
{
    BdrvDirtyBitmap *bm;
    Error *err = NULL;

    FOR_EACH_DIRTY_BITMAP(src, bm) {
        const char *name;

        if (!bdrv_dirty_bitmap_get_persistence(bm)) {
            continue;
        }
        name = bdrv_dirty_bitmap_name(bm);
        if (skip_broken && bdrv_dirty_bitmap_inconsistent(bm)) {
            warn_report("Skipping inconsistent bitmap '%s'", name);
            continue;
        }
        qmp_block_dirty_bitmap_add(dst->node_name, name,
                                   true, bdrv_dirty_bitmap_granularity(bm),
                                   true, true,
                                   true, !bdrv_dirty_bitmap_enabled(bm),
                                   &err);
        if (err) {
            error_reportf_err(err, "Failed to create bitmap %s: ", name);
            return -1;
        }

        do_dirty_bitmap_merge(dst->node_name, name, src->node_name, name,
                              &err);
        if (err) {
            error_reportf_err(err, "Failed to populate bitmap %s: ", name);
            qmp_block_dirty_bitmap_remove(dst->node_name, name, NULL);
            return -1;
        }
    }

    return 0;
}

#define MAX_BUF_SECTORS 32768

static void set_rate_limit(BlockBackend *blk, int64_t rate_limit)
{
    ThrottleConfig cfg;

    throttle_config_init(&cfg);
    cfg.buckets[THROTTLE_BPS_WRITE].avg = rate_limit;

    blk_io_limits_enable(blk, CONVERT_THROTTLE_GROUP);
    blk_set_io_limits(blk, &cfg);
}

static int img_convert(int argc, char **argv)
{
    int c, bs_i, flags, src_flags = BDRV_O_NO_SHARE;
    const char *fmt = NULL, *out_fmt = NULL, *cache = "unsafe",
               *src_cache = BDRV_DEFAULT_CACHE, *out_baseimg = NULL,
               *out_filename, *out_baseimg_param, *snapshot_name = NULL,
               *backing_fmt = NULL;
    BlockDriver *drv = NULL, *proto_drv = NULL;
    BlockDriverInfo bdi;
    BlockDriverState *out_bs;
    QemuOpts *opts = NULL, *sn_opts = NULL;
    QemuOptsList *create_opts = NULL;
    QDict *open_opts = NULL;
    char *options = NULL;
    Error *local_err = NULL;
    bool writethrough, src_writethrough, image_opts = false,
         skip_create = false, progress = false, tgt_image_opts = false;
    int64_t ret = -EINVAL;
    bool force_share = false;
    bool explict_min_sparse = false;
    bool bitmaps = false;
    bool skip_broken = false;
    int64_t rate_limit = 0;

    ImgConvertState s = (ImgConvertState) {
        /* Need at least 4k of zeros for sparse detection */
        .min_sparse         = 8,
        .copy_range         = false,
        .buf_sectors        = IO_BUF_SIZE / BDRV_SECTOR_SIZE,
        .wr_in_order        = true,
        .num_coroutines     = 8,
    };

    for(;;) {
        static const struct option long_options[] = {
            {"help", no_argument, 0, 'h'},
            {"object", required_argument, 0, OPTION_OBJECT},
            {"image-opts", no_argument, 0, OPTION_IMAGE_OPTS},
            {"force-share", no_argument, 0, 'U'},
            {"target-image-opts", no_argument, 0, OPTION_TARGET_IMAGE_OPTS},
            {"salvage", no_argument, 0, OPTION_SALVAGE},
            {"target-is-zero", no_argument, 0, OPTION_TARGET_IS_ZERO},
            {"bitmaps", no_argument, 0, OPTION_BITMAPS},
            {"skip-broken-bitmaps", no_argument, 0, OPTION_SKIP_BROKEN},
            {0, 0, 0, 0}
        };
        c = getopt_long(argc, argv, ":hf:O:B:CcF:o:l:S:pt:T:qnm:WUr:",
                        long_options, NULL);
        if (c == -1) {
            break;
        }
        switch(c) {
        case ':':
            missing_argument(argv[optind - 1]);
            break;
        case '?':
            unrecognized_option(argv[optind - 1]);
            break;
        case 'h':
            help();
            break;
        case 'f':
            fmt = optarg;
            break;
        case 'O':
            out_fmt = optarg;
            break;
        case 'B':
            out_baseimg = optarg;
            break;
        case 'C':
            s.copy_range = true;
            break;
        case 'c':
            s.compressed = true;
            break;
        case 'F':
            backing_fmt = optarg;
            break;
        case 'o':
            if (accumulate_options(&options, optarg) < 0) {
                goto fail_getopt;
            }
            break;
        case 'l':
            if (strstart(optarg, SNAPSHOT_OPT_BASE, NULL)) {
                sn_opts = qemu_opts_parse_noisily(&internal_snapshot_opts,
                                                  optarg, false);
                if (!sn_opts) {
                    error_report("Failed in parsing snapshot param '%s'",
                                 optarg);
                    goto fail_getopt;
                }
            } else {
                snapshot_name = optarg;
            }
            break;
        case 'S':
        {
            int64_t sval;

            sval = cvtnum("buffer size for sparse output", optarg);
            if (sval < 0) {
                goto fail_getopt;
            } else if (!QEMU_IS_ALIGNED(sval, BDRV_SECTOR_SIZE) ||
                sval / BDRV_SECTOR_SIZE > MAX_BUF_SECTORS) {
                error_report("Invalid buffer size for sparse output specified. "
                    "Valid sizes are multiples of %llu up to %llu. Select "
                    "0 to disable sparse detection (fully allocates output).",
                    BDRV_SECTOR_SIZE, MAX_BUF_SECTORS * BDRV_SECTOR_SIZE);
                goto fail_getopt;
            }

            s.min_sparse = sval / BDRV_SECTOR_SIZE;
            explict_min_sparse = true;
            break;
        }
        case 'p':
            progress = true;
            break;
        case 't':
            cache = optarg;
            break;
        case 'T':
            src_cache = optarg;
            break;
        case 'q':
            s.quiet = true;
            break;
        case 'n':
            skip_create = true;
            break;
        case 'm':
            if (qemu_strtol(optarg, NULL, 0, &s.num_coroutines) ||
                s.num_coroutines < 1 || s.num_coroutines > MAX_COROUTINES) {
                error_report("Invalid number of coroutines. Allowed number of"
                             " coroutines is between 1 and %d", MAX_COROUTINES);
                goto fail_getopt;
            }
            break;
        case 'W':
            s.wr_in_order = false;
            break;
        case 'U':
            force_share = true;
            break;
        case 'r':
            rate_limit = cvtnum("rate limit", optarg);
            if (rate_limit < 0) {
                goto fail_getopt;
            }
            break;
        case OPTION_OBJECT:
            user_creatable_process_cmdline(optarg);
            break;
        case OPTION_IMAGE_OPTS:
            image_opts = true;
            break;
        case OPTION_SALVAGE:
            s.salvage = true;
            break;
        case OPTION_TARGET_IMAGE_OPTS:
            tgt_image_opts = true;
            break;
        case OPTION_TARGET_IS_ZERO:
            /*
             * The user asserting that the target is blank has the
             * same effect as the target driver supporting zero
             * initialisation.
             */
            s.has_zero_init = true;
            break;
        case OPTION_BITMAPS:
            bitmaps = true;
            break;
        case OPTION_SKIP_BROKEN:
            skip_broken = true;
            break;
        }
    }

    if (!out_fmt && !tgt_image_opts) {
        out_fmt = "raw";
    }

    if (skip_broken && !bitmaps) {
        error_report("Use of --skip-broken-bitmaps requires --bitmaps");
        goto fail_getopt;
    }

    if (s.compressed && s.copy_range) {
        error_report("Cannot enable copy offloading when -c is used");
        goto fail_getopt;
    }

    if (explict_min_sparse && s.copy_range) {
        error_report("Cannot enable copy offloading when -S is used");
        goto fail_getopt;
    }

    if (s.copy_range && s.salvage) {
        error_report("Cannot use copy offloading in salvaging mode");
        goto fail_getopt;
    }

    if (tgt_image_opts && !skip_create) {
        error_report("--target-image-opts requires use of -n flag");
        goto fail_getopt;
    }

    if (skip_create && options) {
        error_report("-o has no effect when skipping image creation");
        goto fail_getopt;
    }

    if (s.has_zero_init && !skip_create) {
        error_report("--target-is-zero requires use of -n flag");
        goto fail_getopt;
    }

    s.src_num = argc - optind - 1;
    out_filename = s.src_num >= 1 ? argv[argc - 1] : NULL;

    if (options && has_help_option(options)) {
        if (out_fmt) {
            ret = print_block_option_help(out_filename, out_fmt);
            goto fail_getopt;
        } else {
            error_report("Option help requires a format be specified");
            goto fail_getopt;
        }
    }

    if (s.src_num < 1) {
        error_report("Must specify image file name");
        goto fail_getopt;
    }

    /* ret is still -EINVAL until here */
    ret = bdrv_parse_cache_mode(src_cache, &src_flags, &src_writethrough);
    if (ret < 0) {
        error_report("Invalid source cache option: %s", src_cache);
        goto fail_getopt;
    }

    /* Initialize before goto out */
    if (s.quiet) {
        progress = false;
    }
    qemu_progress_init(progress, 1.0);
    qemu_progress_print(0, 100);

    s.src = g_new0(BlockBackend *, s.src_num);
    s.src_sectors = g_new(int64_t, s.src_num);
    s.src_alignment = g_new(int, s.src_num);

    for (bs_i = 0; bs_i < s.src_num; bs_i++) {
        BlockDriverState *src_bs;
        s.src[bs_i] = img_open(image_opts, argv[optind + bs_i],
                               fmt, src_flags, src_writethrough, s.quiet,
                               force_share);
        if (!s.src[bs_i]) {
            ret = -1;
            goto out;
        }
        s.src_sectors[bs_i] = blk_nb_sectors(s.src[bs_i]);
        if (s.src_sectors[bs_i] < 0) {
            error_report("Could not get size of %s: %s",
                         argv[optind + bs_i], strerror(-s.src_sectors[bs_i]));
            ret = -1;
            goto out;
        }
        src_bs = blk_bs(s.src[bs_i]);
        s.src_alignment[bs_i] = DIV_ROUND_UP(src_bs->bl.request_alignment,
                                             BDRV_SECTOR_SIZE);
        if (!bdrv_get_info(src_bs, &bdi)) {
            s.src_alignment[bs_i] = MAX(s.src_alignment[bs_i],
                                        bdi.cluster_size / BDRV_SECTOR_SIZE);
        }
        s.total_sectors += s.src_sectors[bs_i];
    }

    if (sn_opts) {
        bdrv_snapshot_load_tmp(blk_bs(s.src[0]),
                               qemu_opt_get(sn_opts, SNAPSHOT_OPT_ID),
                               qemu_opt_get(sn_opts, SNAPSHOT_OPT_NAME),
                               &local_err);
    } else if (snapshot_name != NULL) {
        if (s.src_num > 1) {
            error_report("No support for concatenating multiple snapshot");
            ret = -1;
            goto out;
        }

        bdrv_snapshot_load_tmp_by_id_or_name(blk_bs(s.src[0]), snapshot_name,
                                             &local_err);
    }
    if (local_err) {
        error_reportf_err(local_err, "Failed to load snapshot: ");
        ret = -1;
        goto out;
    }

    if (!skip_create) {
        /* Find driver and parse its options */
        drv = bdrv_find_format(out_fmt);
        if (!drv) {
            error_report("Unknown file format '%s'", out_fmt);
            ret = -1;
            goto out;
        }

        proto_drv = bdrv_find_protocol(out_filename, true, &local_err);
        if (!proto_drv) {
            error_report_err(local_err);
            ret = -1;
            goto out;
        }

        if (!drv->create_opts) {
            error_report("Format driver '%s' does not support image creation",
                         drv->format_name);
            ret = -1;
            goto out;
        }

        if (!proto_drv->create_opts) {
            error_report("Protocol driver '%s' does not support image creation",
                         proto_drv->format_name);
            ret = -1;
            goto out;
        }

        create_opts = qemu_opts_append(create_opts, drv->create_opts);
        create_opts = qemu_opts_append(create_opts, proto_drv->create_opts);

        opts = qemu_opts_create(create_opts, NULL, 0, &error_abort);
        if (options) {
            if (!qemu_opts_do_parse(opts, options, NULL, &local_err)) {
                error_report_err(local_err);
                ret = -1;
                goto out;
            }
        }

        qemu_opt_set_number(opts, BLOCK_OPT_SIZE,
                            s.total_sectors * BDRV_SECTOR_SIZE, &error_abort);
        ret = add_old_style_options(out_fmt, opts, out_baseimg, backing_fmt);
        if (ret < 0) {
            goto out;
        }
    }

    /* Get backing file name if -o backing_file was used */
    out_baseimg_param = qemu_opt_get(opts, BLOCK_OPT_BACKING_FILE);
    if (out_baseimg_param) {
        out_baseimg = out_baseimg_param;
    }
    s.target_has_backing = (bool) out_baseimg;

    if (s.has_zero_init && s.target_has_backing) {
        error_report("Cannot use --target-is-zero when the destination "
                     "image has a backing file");
        goto out;
    }

    if (s.src_num > 1 && out_baseimg) {
        error_report("Having a backing file for the target makes no sense when "
                     "concatenating multiple input images");
        ret = -1;
        goto out;
    }

    if (out_baseimg_param) {
        if (!qemu_opt_get(opts, BLOCK_OPT_BACKING_FMT)) {
            error_report("Use of backing file requires explicit "
                         "backing format");
            ret = -1;
            goto out;
        }
    }

    /* Check if compression is supported */
    if (s.compressed) {
        bool encryption =
            qemu_opt_get_bool(opts, BLOCK_OPT_ENCRYPT, false);
        const char *encryptfmt =
            qemu_opt_get(opts, BLOCK_OPT_ENCRYPT_FORMAT);
        const char *preallocation =
            qemu_opt_get(opts, BLOCK_OPT_PREALLOC);

        if (drv && !block_driver_can_compress(drv)) {
            error_report("Compression not supported for this file format");
            ret = -1;
            goto out;
        }

        if (encryption || encryptfmt) {
            error_report("Compression and encryption not supported at "
                         "the same time");
            ret = -1;
            goto out;
        }

        if (preallocation
            && strcmp(preallocation, "off"))
        {
            error_report("Compression and preallocation not supported at "
                         "the same time");
            ret = -1;
            goto out;
        }
    }

    /* Determine if bitmaps need copying */
    if (bitmaps) {
        if (s.src_num > 1) {
            error_report("Copying bitmaps only possible with single source");
            ret = -1;
            goto out;
        }
        ret = convert_check_bitmaps(blk_bs(s.src[0]), skip_broken);
        if (ret < 0) {
            goto out;
        }
    }

    /*
     * The later open call will need any decryption secrets, and
     * bdrv_create() will purge "opts", so extract them now before
     * they are lost.
     */
    if (!skip_create) {
        open_opts = qdict_new();
        qemu_opt_foreach(opts, img_add_key_secrets, open_opts, &error_abort);

        /* Create the new image */
        ret = bdrv_create(drv, out_filename, opts, &local_err);
        if (ret < 0) {
            error_reportf_err(local_err, "%s: error while converting %s: ",
                              out_filename, out_fmt);
            goto out;
        }
    }

    s.target_is_new = !skip_create;

    flags = s.min_sparse ? (BDRV_O_RDWR | BDRV_O_UNMAP) : BDRV_O_RDWR;
    ret = bdrv_parse_cache_mode(cache, &flags, &writethrough);
    if (ret < 0) {
        error_report("Invalid cache option: %s", cache);
        goto out;
    }

    if (flags & BDRV_O_NOCACHE) {
        /*
         * If we open the target with O_DIRECT, it may be necessary to
         * extend its size to align to the physical sector size.
         */
        flags |= BDRV_O_RESIZE;
    }

    if (skip_create) {
        s.target = img_open(tgt_image_opts, out_filename, out_fmt,
                            flags, writethrough, s.quiet, false);
    } else {
        /* TODO ultimately we should allow --target-image-opts
         * to be used even when -n is not given.
         * That has to wait for bdrv_create to be improved
         * to allow filenames in option syntax
         */
        s.target = img_open_file(out_filename, open_opts, out_fmt,
                                 flags, writethrough, s.quiet, false);
        open_opts = NULL; /* blk_new_open will have freed it */
    }
    if (!s.target) {
        ret = -1;
        goto out;
    }
    out_bs = blk_bs(s.target);

    if (bitmaps && !bdrv_supports_persistent_dirty_bitmap(out_bs)) {
        error_report("Format driver '%s' does not support bitmaps",
                     out_bs->drv->format_name);
        ret = -1;
        goto out;
    }

    if (s.compressed && !block_driver_can_compress(out_bs->drv)) {
        error_report("Compression not supported for this file format");
        ret = -1;
        goto out;
    }

    /* increase bufsectors from the default 4096 (2M) if opt_transfer
     * or discard_alignment of the out_bs is greater. Limit to
     * MAX_BUF_SECTORS as maximum which is currently 32768 (16MB). */
    s.buf_sectors = MIN(MAX_BUF_SECTORS,
                        MAX(s.buf_sectors,
                            MAX(out_bs->bl.opt_transfer >> BDRV_SECTOR_BITS,
                                out_bs->bl.pdiscard_alignment >>
                                BDRV_SECTOR_BITS)));

    /* try to align the write requests to the destination to avoid unnecessary
     * RMW cycles. */
    s.alignment = MAX(pow2floor(s.min_sparse),
                      DIV_ROUND_UP(out_bs->bl.request_alignment,
                                   BDRV_SECTOR_SIZE));
    assert(is_power_of_2(s.alignment));

    if (skip_create) {
        int64_t output_sectors = blk_nb_sectors(s.target);
        if (output_sectors < 0) {
            error_report("unable to get output image length: %s",
                         strerror(-output_sectors));
            ret = -1;
            goto out;
        } else if (output_sectors < s.total_sectors) {
            error_report("output file is smaller than input file");
            ret = -1;
            goto out;
        }
    }

    if (s.target_has_backing && s.target_is_new) {
        /* Errors are treated as "backing length unknown" (which means
         * s.target_backing_sectors has to be negative, which it will
         * be automatically).  The backing file length is used only
         * for optimizations, so such a case is not fatal. */
        bdrv_graph_rdlock_main_loop();
        s.target_backing_sectors =
            bdrv_nb_sectors(bdrv_backing_chain_next(out_bs));
        bdrv_graph_rdunlock_main_loop();
    } else {
        s.target_backing_sectors = -1;
    }

    ret = bdrv_get_info(out_bs, &bdi);
    if (ret < 0) {
        if (s.compressed) {
            error_report("could not get block driver info");
            goto out;
        }
    } else {
        s.compressed = s.compressed || bdi.needs_compressed_writes;
        s.cluster_sectors = bdi.cluster_size / BDRV_SECTOR_SIZE;
    }

    if (rate_limit) {
        set_rate_limit(s.target, rate_limit);
    }

    ret = convert_do_copy(&s);

    /* Now copy the bitmaps */
    if (bitmaps && ret == 0) {
        ret = convert_copy_bitmaps(blk_bs(s.src[0]), out_bs, skip_broken);
    }

out:
    if (!ret) {
        qemu_progress_print(100, 0);
    }
    qemu_progress_end();
    qemu_opts_del(opts);
    qemu_opts_free(create_opts);
    qobject_unref(open_opts);
    blk_unref(s.target);
    if (s.src) {
        for (bs_i = 0; bs_i < s.src_num; bs_i++) {
            blk_unref(s.src[bs_i]);
        }
        g_free(s.src);
    }
    g_free(s.src_sectors);
    g_free(s.src_alignment);
fail_getopt:
    qemu_opts_del(sn_opts);
    g_free(options);

    return !!ret;
}


static void dump_snapshots(BlockDriverState *bs)
{
    QEMUSnapshotInfo *sn_tab, *sn;
    int nb_sns, i;

    nb_sns = bdrv_snapshot_list(bs, &sn_tab);
    if (nb_sns <= 0)
        return;
    printf("Snapshot list:\n");
    bdrv_snapshot_dump(NULL);
    printf("\n");
    for(i = 0; i < nb_sns; i++) {
        sn = &sn_tab[i];
        bdrv_snapshot_dump(sn);
        printf("\n");
    }
    g_free(sn_tab);
}

static void dump_json_block_graph_info_list(BlockGraphInfoList *list)
{
    GString *str;
    QObject *obj;
    Visitor *v = qobject_output_visitor_new(&obj);

    visit_type_BlockGraphInfoList(v, NULL, &list, &error_abort);
    visit_complete(v, &obj);
    str = qobject_to_json_pretty(obj, true);
    assert(str != NULL);
    printf("%s\n", str->str);
    qobject_unref(obj);
    visit_free(v);
    g_string_free(str, true);
}

static void dump_json_block_graph_info(BlockGraphInfo *info)
{
    GString *str;
    QObject *obj;
    Visitor *v = qobject_output_visitor_new(&obj);

    visit_type_BlockGraphInfo(v, NULL, &info, &error_abort);
    visit_complete(v, &obj);
    str = qobject_to_json_pretty(obj, true);
    assert(str != NULL);
    printf("%s\n", str->str);
    qobject_unref(obj);
    visit_free(v);
    g_string_free(str, true);
}

static void dump_human_image_info(BlockGraphInfo *info, int indentation,
                                  const char *path)
{
    BlockChildInfoList *children_list;

    bdrv_node_info_dump(qapi_BlockGraphInfo_base(info), indentation,
                        info->children == NULL);

    for (children_list = info->children; children_list;
         children_list = children_list->next)
    {
        BlockChildInfo *child = children_list->value;
        g_autofree char *child_path = NULL;

        printf("%*sChild node '%s%s':\n",
               indentation * 4, "", path, child->name);
        child_path = g_strdup_printf("%s%s/", path, child->name);
        dump_human_image_info(child->info, indentation + 1, child_path);
    }
}

static void dump_human_image_info_list(BlockGraphInfoList *list)
{
    BlockGraphInfoList *elem;
    bool delim = false;

    for (elem = list; elem; elem = elem->next) {
        if (delim) {
            printf("\n");
        }
        delim = true;

        dump_human_image_info(elem->value, 0, "/");
    }
}

static gboolean str_equal_func(gconstpointer a, gconstpointer b)
{
    return strcmp(a, b) == 0;
}

/**
 * Open an image file chain and return an BlockGraphInfoList
 *
 * @filename: topmost image filename
 * @fmt: topmost image format (may be NULL to autodetect)
 * @chain: true  - enumerate entire backing file chain
 *         false - only topmost image file
 *
 * Returns a list of BlockNodeInfo objects or NULL if there was an error
 * opening an image file.  If there was an error a message will have been
 * printed to stderr.
 */
static BlockGraphInfoList *collect_image_info_list(bool image_opts,
                                                   const char *filename,
                                                   const char *fmt,
                                                   bool chain, bool force_share)
{
    BlockGraphInfoList *head = NULL;
    BlockGraphInfoList **tail = &head;
    GHashTable *filenames;
    Error *err = NULL;

    filenames = g_hash_table_new_full(g_str_hash, str_equal_func, NULL, NULL);

    while (filename) {
        BlockBackend *blk;
        BlockDriverState *bs;
        BlockGraphInfo *info;

        if (g_hash_table_lookup_extended(filenames, filename, NULL, NULL)) {
            error_report("Backing file '%s' creates an infinite loop.",
                         filename);
            goto err;
        }
        g_hash_table_insert(filenames, (gpointer)filename, NULL);

        blk = img_open(image_opts, filename, fmt,
                       BDRV_O_NO_BACKING | BDRV_O_NO_IO, false, false,
                       force_share);
        if (!blk) {
            goto err;
        }
        bs = blk_bs(blk);

        /*
         * Note that the returned BlockGraphInfo object will not have
         * information about this image's backing node, because we have opened
         * it with BDRV_O_NO_BACKING.  Printing this object will therefore not
         * duplicate the backing chain information that we obtain by walking
         * the chain manually here.
         */
        bdrv_graph_rdlock_main_loop();
        bdrv_query_block_graph_info(bs, &info, &err);
        bdrv_graph_rdunlock_main_loop();

        if (err) {
            error_report_err(err);
            blk_unref(blk);
            goto err;
        }

        QAPI_LIST_APPEND(tail, info);

        blk_unref(blk);

        /* Clear parameters that only apply to the topmost image */
        filename = fmt = NULL;
        image_opts = false;

        if (chain) {
            if (info->full_backing_filename) {
                filename = info->full_backing_filename;
            } else if (info->backing_filename) {
                error_report("Could not determine absolute backing filename,"
                             " but backing filename '%s' present",
                             info->backing_filename);
                goto err;
            }
            if (info->backing_filename_format) {
                fmt = info->backing_filename_format;
            }
        }
    }
    g_hash_table_destroy(filenames);
    return head;

err:
    qapi_free_BlockGraphInfoList(head);
    g_hash_table_destroy(filenames);
    return NULL;
}

static int img_info(int argc, char **argv)
{
    int c;
    OutputFormat output_format = OFORMAT_HUMAN;
    bool chain = false;
    const char *filename, *fmt, *output;
    BlockGraphInfoList *list;
    bool image_opts = false;
    bool force_share = false;

    fmt = NULL;
    output = NULL;
    for(;;) {
        int option_index = 0;
        static const struct option long_options[] = {
            {"help", no_argument, 0, 'h'},
            {"format", required_argument, 0, 'f'},
            {"output", required_argument, 0, OPTION_OUTPUT},
            {"backing-chain", no_argument, 0, OPTION_BACKING_CHAIN},
            {"object", required_argument, 0, OPTION_OBJECT},
            {"image-opts", no_argument, 0, OPTION_IMAGE_OPTS},
            {"force-share", no_argument, 0, 'U'},
            {0, 0, 0, 0}
        };
        c = getopt_long(argc, argv, ":f:hU",
                        long_options, &option_index);
        if (c == -1) {
            break;
        }
        switch(c) {
        case ':':
            missing_argument(argv[optind - 1]);
            break;
        case '?':
            unrecognized_option(argv[optind - 1]);
            break;
        case 'h':
            help();
            break;
        case 'f':
            fmt = optarg;
            break;
        case 'U':
            force_share = true;
            break;
        case OPTION_OUTPUT:
            output = optarg;
            break;
        case OPTION_BACKING_CHAIN:
            chain = true;
            break;
        case OPTION_OBJECT:
            user_creatable_process_cmdline(optarg);
            break;
        case OPTION_IMAGE_OPTS:
            image_opts = true;
            break;
        }
    }
    if (optind != argc - 1) {
        error_exit("Expecting one image file name");
    }
    filename = argv[optind++];

    if (output && !strcmp(output, "json")) {
        output_format = OFORMAT_JSON;
    } else if (output && !strcmp(output, "human")) {
        output_format = OFORMAT_HUMAN;
    } else if (output) {
        error_report("--output must be used with human or json as argument.");
        return 1;
    }

    list = collect_image_info_list(image_opts, filename, fmt, chain,
                                   force_share);
    if (!list) {
        return 1;
    }

    switch (output_format) {
    case OFORMAT_HUMAN:
        dump_human_image_info_list(list);
        break;
    case OFORMAT_JSON:
        if (chain) {
            dump_json_block_graph_info_list(list);
        } else {
            dump_json_block_graph_info(list->value);
        }
        break;
    }

    qapi_free_BlockGraphInfoList(list);
    return 0;
}

static int dump_map_entry(OutputFormat output_format, MapEntry *e,
                          MapEntry *next)
{
    switch (output_format) {
    case OFORMAT_HUMAN:
        if (e->data && !e->has_offset) {
            error_report("File contains external, encrypted or compressed clusters.");
            return -1;
        }
        if (e->data && !e->zero) {
            printf("%#-16"PRIx64"%#-16"PRIx64"%#-16"PRIx64"%s\n",
                   e->start, e->length,
                   e->has_offset ? e->offset : 0,
                   e->filename ?: "");
        }
        /* This format ignores the distinction between 0, ZERO and ZERO|DATA.
         * Modify the flags here to allow more coalescing.
         */
        if (next && (!next->data || next->zero)) {
            next->data = false;
            next->zero = true;
        }
        break;
    case OFORMAT_JSON:
        printf("{ \"start\": %"PRId64", \"length\": %"PRId64","
               " \"depth\": %"PRId64", \"present\": %s, \"zero\": %s,"
               " \"data\": %s, \"compressed\": %s",
               e->start, e->length, e->depth,
               e->present ? "true" : "false",
               e->zero ? "true" : "false",
               e->data ? "true" : "false",
               e->compressed ? "true" : "false");
        if (e->has_offset) {
            printf(", \"offset\": %"PRId64"", e->offset);
        }
        putchar('}');

        if (next) {
            puts(",");
        }
        break;
    }
    return 0;
}

static int get_block_status(BlockDriverState *bs, int64_t offset,
                            int64_t bytes, MapEntry *e)
{
    int ret;
    int depth;
    BlockDriverState *file;
    bool has_offset;
    int64_t map;
    char *filename = NULL;

    GLOBAL_STATE_CODE();
    GRAPH_RDLOCK_GUARD_MAINLOOP();

    /* As an optimization, we could cache the current range of unallocated
     * clusters in each file of the chain, and avoid querying the same
     * range repeatedly.
     */

    depth = 0;
    for (;;) {
        bs = bdrv_skip_filters(bs);
        ret = bdrv_block_status(bs, offset, bytes, &bytes, &map, &file);
        if (ret < 0) {
            return ret;
        }
        assert(bytes);
        if (ret & (BDRV_BLOCK_ZERO|BDRV_BLOCK_DATA)) {
            break;
        }
        bs = bdrv_cow_bs(bs);
        if (bs == NULL) {
            ret = 0;
            break;
        }

        depth++;
    }

    has_offset = !!(ret & BDRV_BLOCK_OFFSET_VALID);

    if (file && has_offset) {
        bdrv_refresh_filename(file);
        filename = file->filename;
    }

    *e = (MapEntry) {
        .start = offset,
        .length = bytes,
        .data = !!(ret & BDRV_BLOCK_DATA),
        .zero = !!(ret & BDRV_BLOCK_ZERO),
        .compressed = !!(ret & BDRV_BLOCK_COMPRESSED),
        .offset = map,
        .has_offset = has_offset,
        .depth = depth,
        .present = !!(ret & BDRV_BLOCK_ALLOCATED),
        .filename = filename,
    };

    return 0;
}

static inline bool entry_mergeable(const MapEntry *curr, const MapEntry *next)
{
    if (curr->length == 0) {
        return false;
    }
    if (curr->zero != next->zero ||
        curr->data != next->data ||
        curr->compressed != next->compressed ||
        curr->depth != next->depth ||
        curr->present != next->present ||
        !curr->filename != !next->filename ||
        curr->has_offset != next->has_offset) {
        return false;
    }
    if (curr->filename && strcmp(curr->filename, next->filename)) {
        return false;
    }
    if (curr->has_offset && curr->offset + curr->length != next->offset) {
        return false;
    }
    return true;
}

static int img_map(int argc, char **argv)
{
    int c;
    OutputFormat output_format = OFORMAT_HUMAN;
    BlockBackend *blk;
    BlockDriverState *bs;
    const char *filename, *fmt, *output;
    int64_t length;
    MapEntry curr = { .length = 0 }, next;
    int ret = 0;
    bool image_opts = false;
    bool force_share = false;
    int64_t start_offset = 0;
    int64_t max_length = -1;

    fmt = NULL;
    output = NULL;
    for (;;) {
        int option_index = 0;
        static const struct option long_options[] = {
            {"help", no_argument, 0, 'h'},
            {"format", required_argument, 0, 'f'},
            {"output", required_argument, 0, OPTION_OUTPUT},
            {"object", required_argument, 0, OPTION_OBJECT},
            {"image-opts", no_argument, 0, OPTION_IMAGE_OPTS},
            {"force-share", no_argument, 0, 'U'},
            {"start-offset", required_argument, 0, 's'},
            {"max-length", required_argument, 0, 'l'},
            {0, 0, 0, 0}
        };
        c = getopt_long(argc, argv, ":f:s:l:hU",
                        long_options, &option_index);
        if (c == -1) {
            break;
        }
        switch (c) {
        case ':':
            missing_argument(argv[optind - 1]);
            break;
        case '?':
            unrecognized_option(argv[optind - 1]);
            break;
        case 'h':
            help();
            break;
        case 'f':
            fmt = optarg;
            break;
        case 'U':
            force_share = true;
            break;
        case OPTION_OUTPUT:
            output = optarg;
            break;
        case 's':
            start_offset = cvtnum("start offset", optarg);
            if (start_offset < 0) {
                return 1;
            }
            break;
        case 'l':
            max_length = cvtnum("max length", optarg);
            if (max_length < 0) {
                return 1;
            }
            break;
        case OPTION_OBJECT:
            user_creatable_process_cmdline(optarg);
            break;
        case OPTION_IMAGE_OPTS:
            image_opts = true;
            break;
        }
    }
    if (optind != argc - 1) {
        error_exit("Expecting one image file name");
    }
    filename = argv[optind];

    if (output && !strcmp(output, "json")) {
        output_format = OFORMAT_JSON;
    } else if (output && !strcmp(output, "human")) {
        output_format = OFORMAT_HUMAN;
    } else if (output) {
        error_report("--output must be used with human or json as argument.");
        return 1;
    }

    blk = img_open(image_opts, filename, fmt, 0, false, false, force_share);
    if (!blk) {
        return 1;
    }
    bs = blk_bs(blk);

    if (output_format == OFORMAT_HUMAN) {
        printf("%-16s%-16s%-16s%s\n", "Offset", "Length", "Mapped to", "File");
    } else if (output_format == OFORMAT_JSON) {
        putchar('[');
    }

    length = blk_getlength(blk);
    if (length < 0) {
        error_report("Failed to get size for '%s'", filename);
        return 1;
    }
    if (max_length != -1) {
        length = MIN(start_offset + max_length, length);
    }

    curr.start = start_offset;
    while (curr.start + curr.length < length) {
        int64_t offset = curr.start + curr.length;
        int64_t n = length - offset;

        ret = get_block_status(bs, offset, n, &next);
        if (ret < 0) {
            error_report("Could not read file metadata: %s", strerror(-ret));
            goto out;
        }

        if (entry_mergeable(&curr, &next)) {
            curr.length += next.length;
            continue;
        }

        if (curr.length > 0) {
            ret = dump_map_entry(output_format, &curr, &next);
            if (ret < 0) {
                goto out;
            }
        }
        curr = next;
    }

    ret = dump_map_entry(output_format, &curr, NULL);
    if (output_format == OFORMAT_JSON) {
        puts("]");
    }

out:
    blk_unref(blk);
    return ret < 0;
}

#define SNAPSHOT_LIST   1
#define SNAPSHOT_CREATE 2
#define SNAPSHOT_APPLY  3
#define SNAPSHOT_DELETE 4

static int img_snapshot(int argc, char **argv)
{
    BlockBackend *blk;
    BlockDriverState *bs;
    QEMUSnapshotInfo sn;
    char *filename, *snapshot_name = NULL;
    int c, ret = 0, bdrv_oflags;
    int action = 0;
    bool quiet = false;
    Error *err = NULL;
    bool image_opts = false;
    bool force_share = false;
    int64_t rt;

    bdrv_oflags = BDRV_O_RDWR;
    /* Parse commandline parameters */
    for(;;) {
        static const struct option long_options[] = {
            {"help", no_argument, 0, 'h'},
            {"object", required_argument, 0, OPTION_OBJECT},
            {"image-opts", no_argument, 0, OPTION_IMAGE_OPTS},
            {"force-share", no_argument, 0, 'U'},
            {0, 0, 0, 0}
        };
        c = getopt_long(argc, argv, ":la:c:d:hqU",
                        long_options, NULL);
        if (c == -1) {
            break;
        }
        switch(c) {
        case ':':
            missing_argument(argv[optind - 1]);
            break;
        case '?':
            unrecognized_option(argv[optind - 1]);
            break;
        case 'h':
            help();
            return 0;
        case 'l':
            if (action) {
                error_exit("Cannot mix '-l', '-a', '-c', '-d'");
                return 0;
            }
            action = SNAPSHOT_LIST;
            bdrv_oflags &= ~BDRV_O_RDWR; /* no need for RW */
            break;
        case 'a':
            if (action) {
                error_exit("Cannot mix '-l', '-a', '-c', '-d'");
                return 0;
            }
            action = SNAPSHOT_APPLY;
            snapshot_name = optarg;
            break;
        case 'c':
            if (action) {
                error_exit("Cannot mix '-l', '-a', '-c', '-d'");
                return 0;
            }
            action = SNAPSHOT_CREATE;
            snapshot_name = optarg;
            break;
        case 'd':
            if (action) {
                error_exit("Cannot mix '-l', '-a', '-c', '-d'");
                return 0;
            }
            action = SNAPSHOT_DELETE;
            snapshot_name = optarg;
            break;
        case 'q':
            quiet = true;
            break;
        case 'U':
            force_share = true;
            break;
        case OPTION_OBJECT:
            user_creatable_process_cmdline(optarg);
            break;
        case OPTION_IMAGE_OPTS:
            image_opts = true;
            break;
        }
    }

    if (optind != argc - 1) {
        error_exit("Expecting one image file name");
    }
    filename = argv[optind++];

    /* Open the image */
    blk = img_open(image_opts, filename, NULL, bdrv_oflags, false, quiet,
                   force_share);
    if (!blk) {
        return 1;
    }
    bs = blk_bs(blk);

    /* Perform the requested action */
    switch(action) {
    case SNAPSHOT_LIST:
        dump_snapshots(bs);
        break;

    case SNAPSHOT_CREATE:
        memset(&sn, 0, sizeof(sn));
        pstrcpy(sn.name, sizeof(sn.name), snapshot_name);

        rt = g_get_real_time();
        sn.date_sec = rt / G_USEC_PER_SEC;
        sn.date_nsec = (rt % G_USEC_PER_SEC) * 1000;

        bdrv_graph_rdlock_main_loop();
        ret = bdrv_snapshot_create(bs, &sn);
        bdrv_graph_rdunlock_main_loop();

        if (ret) {
            error_report("Could not create snapshot '%s': %s",
                snapshot_name, strerror(-ret));
        }
        break;

    case SNAPSHOT_APPLY:
        ret = bdrv_snapshot_goto(bs, snapshot_name, &err);
        if (ret) {
            error_reportf_err(err, "Could not apply snapshot '%s': ",
                              snapshot_name);
        }
        break;

    case SNAPSHOT_DELETE:
        bdrv_graph_rdlock_main_loop();
        ret = bdrv_snapshot_find(bs, &sn, snapshot_name);
        if (ret < 0) {
            error_report("Could not delete snapshot '%s': snapshot not "
                         "found", snapshot_name);
            ret = 1;
        } else {
            ret = bdrv_snapshot_delete(bs, sn.id_str, sn.name, &err);
            if (ret < 0) {
                error_reportf_err(err, "Could not delete snapshot '%s': ",
                                  snapshot_name);
                ret = 1;
            }
        }
        bdrv_graph_rdunlock_main_loop();
        break;
    }

    /* Cleanup */
    blk_unref(blk);
    if (ret) {
        return 1;
    }
    return 0;
}

static int img_rebase(int argc, char **argv)
{
    BlockBackend *blk = NULL, *blk_old_backing = NULL, *blk_new_backing = NULL;
    uint8_t *buf_old = NULL;
    uint8_t *buf_new = NULL;
    BlockDriverState *bs = NULL, *prefix_chain_bs = NULL;
    BlockDriverState *unfiltered_bs, *unfiltered_bs_cow;
    BlockDriverInfo bdi = {0};
    char *filename;
    const char *fmt, *cache, *src_cache, *out_basefmt, *out_baseimg;
    int c, flags, src_flags, ret;
    BdrvRequestFlags write_flags = 0;
    bool writethrough, src_writethrough;
    int unsafe = 0;
    bool force_share = false;
    int progress = 0;
    bool quiet = false;
    bool compress = false;
    Error *local_err = NULL;
    bool image_opts = false;
    int64_t write_align;

    /* Parse commandline parameters */
    fmt = NULL;
    cache = BDRV_DEFAULT_CACHE;
    src_cache = BDRV_DEFAULT_CACHE;
    out_baseimg = NULL;
    out_basefmt = NULL;
    for(;;) {
        static const struct option long_options[] = {
            {"help", no_argument, 0, 'h'},
            {"object", required_argument, 0, OPTION_OBJECT},
            {"image-opts", no_argument, 0, OPTION_IMAGE_OPTS},
            {"force-share", no_argument, 0, 'U'},
            {"compress", no_argument, 0, 'c'},
            {0, 0, 0, 0}
        };
        c = getopt_long(argc, argv, ":hf:F:b:upt:T:qUc",
                        long_options, NULL);
        if (c == -1) {
            break;
        }
        switch(c) {
        case ':':
            missing_argument(argv[optind - 1]);
            break;
        case '?':
            unrecognized_option(argv[optind - 1]);
            break;
        case 'h':
            help();
            return 0;
        case 'f':
            fmt = optarg;
            break;
        case 'F':
            out_basefmt = optarg;
            break;
        case 'b':
            out_baseimg = optarg;
            break;
        case 'u':
            unsafe = 1;
            break;
        case 'p':
            progress = 1;
            break;
        case 't':
            cache = optarg;
            break;
        case 'T':
            src_cache = optarg;
            break;
        case 'q':
            quiet = true;
            break;
        case OPTION_OBJECT:
            user_creatable_process_cmdline(optarg);
            break;
        case OPTION_IMAGE_OPTS:
            image_opts = true;
            break;
        case 'U':
            force_share = true;
            break;
        case 'c':
            compress = true;
            break;
        }
    }

    if (quiet) {
        progress = 0;
    }

    if (optind != argc - 1) {
        error_exit("Expecting one image file name");
    }
    if (!unsafe && !out_baseimg) {
        error_exit("Must specify backing file (-b) or use unsafe mode (-u)");
    }
    filename = argv[optind++];

    qemu_progress_init(progress, 2.0);
    qemu_progress_print(0, 100);

    flags = BDRV_O_RDWR | (unsafe ? BDRV_O_NO_BACKING : 0);
    ret = bdrv_parse_cache_mode(cache, &flags, &writethrough);
    if (ret < 0) {
        error_report("Invalid cache option: %s", cache);
        goto out;
    }

    src_flags = 0;
    ret = bdrv_parse_cache_mode(src_cache, &src_flags, &src_writethrough);
    if (ret < 0) {
        error_report("Invalid source cache option: %s", src_cache);
        goto out;
    }

    /* The source files are opened read-only, don't care about WCE */
    assert((src_flags & BDRV_O_RDWR) == 0);
    (void) src_writethrough;

    /*
     * Open the images.
     *
     * Ignore the old backing file for unsafe rebase in case we want to correct
     * the reference to a renamed or moved backing file.
     */
    blk = img_open(image_opts, filename, fmt, flags, writethrough, quiet,
                   false);
    if (!blk) {
        ret = -1;
        goto out;
    }
    bs = blk_bs(blk);

    bdrv_graph_rdlock_main_loop();
    unfiltered_bs = bdrv_skip_filters(bs);
    unfiltered_bs_cow = bdrv_cow_bs(unfiltered_bs);
    bdrv_graph_rdunlock_main_loop();

    if (compress && !block_driver_can_compress(unfiltered_bs->drv)) {
        error_report("Compression not supported for this file format");
        ret = -1;
        goto out;
    } else if (compress) {
        write_flags |= BDRV_REQ_WRITE_COMPRESSED;
    }

    if (out_basefmt != NULL) {
        if (bdrv_find_format(out_basefmt) == NULL) {
            error_report("Invalid format name: '%s'", out_basefmt);
            ret = -1;
            goto out;
        }
    }

    /*
     * We need overlay subcluster size (or cluster size in case writes are
     * compressed) to make sure write requests are aligned.
     */
    ret = bdrv_get_info(unfiltered_bs, &bdi);
    if (ret < 0) {
        error_report("could not get block driver info");
        goto out;
    } else if (bdi.subcluster_size == 0) {
        bdi.cluster_size = bdi.subcluster_size = 1;
    }

    write_align = compress ? bdi.cluster_size : bdi.subcluster_size;

    /* For safe rebasing we need to compare old and new backing file */
    if (!unsafe) {
        QDict *options = NULL;
        BlockDriverState *base_bs;

        bdrv_graph_rdlock_main_loop();
        base_bs = bdrv_cow_bs(unfiltered_bs);
        bdrv_graph_rdunlock_main_loop();

        if (base_bs) {
            blk_old_backing = blk_new(qemu_get_aio_context(),
                                      BLK_PERM_CONSISTENT_READ,
                                      BLK_PERM_ALL);
            ret = blk_insert_bs(blk_old_backing, base_bs,
                                &local_err);
            if (ret < 0) {
                error_reportf_err(local_err,
                                  "Could not reuse old backing file '%s': ",
                                  base_bs->filename);
                goto out;
            }
        } else {
            blk_old_backing = NULL;
        }

        if (out_baseimg[0]) {
            const char *overlay_filename;
            char *out_real_path;

            options = qdict_new();
            if (out_basefmt) {
                qdict_put_str(options, "driver", out_basefmt);
            }
            if (force_share) {
                qdict_put_bool(options, BDRV_OPT_FORCE_SHARE, true);
            }

            bdrv_graph_rdlock_main_loop();
            bdrv_refresh_filename(bs);
            bdrv_graph_rdunlock_main_loop();
            overlay_filename = bs->exact_filename[0] ? bs->exact_filename
                                                     : bs->filename;
            out_real_path =
                bdrv_get_full_backing_filename_from_filename(overlay_filename,
                                                             out_baseimg,
                                                             &local_err);
            if (local_err) {
                qobject_unref(options);
                error_reportf_err(local_err,
                                  "Could not resolve backing filename: ");
                ret = -1;
                goto out;
            }

            /*
             * Find out whether we rebase an image on top of a previous image
             * in its chain.
             */
            prefix_chain_bs = bdrv_find_backing_image(bs, out_real_path);
            if (prefix_chain_bs) {
                qobject_unref(options);
                g_free(out_real_path);

                blk_new_backing = blk_new(qemu_get_aio_context(),
                                          BLK_PERM_CONSISTENT_READ,
                                          BLK_PERM_ALL);
                ret = blk_insert_bs(blk_new_backing, prefix_chain_bs,
                                    &local_err);
                if (ret < 0) {
                    error_reportf_err(local_err,
                                      "Could not reuse backing file '%s': ",
                                      out_baseimg);
                    goto out;
                }
            } else {
                blk_new_backing = blk_new_open(out_real_path, NULL,
                                               options, src_flags, &local_err);
                g_free(out_real_path);
                if (!blk_new_backing) {
                    error_reportf_err(local_err,
                                      "Could not open new backing file '%s': ",
                                      out_baseimg);
                    ret = -1;
                    goto out;
                }
            }
        }
    }

    /*
     * Check each unallocated cluster in the COW file. If it is unallocated,
     * accesses go to the backing file. We must therefore compare this cluster
     * in the old and new backing file, and if they differ we need to copy it
     * from the old backing file into the COW file.
     *
     * If qemu-img crashes during this step, no harm is done. The content of
     * the image is the same as the original one at any time.
     */
    if (!unsafe) {
        int64_t size;
        int64_t old_backing_size = 0;
        int64_t new_backing_size = 0;
        uint64_t offset;
        int64_t n, n_old = 0, n_new = 0;
        float local_progress = 0;

        if (blk_old_backing && bdrv_opt_mem_align(blk_bs(blk_old_backing)) >
            bdrv_opt_mem_align(blk_bs(blk))) {
            buf_old = blk_blockalign(blk_old_backing, IO_BUF_SIZE);
        } else {
            buf_old = blk_blockalign(blk, IO_BUF_SIZE);
        }
        buf_new = blk_blockalign(blk_new_backing, IO_BUF_SIZE);

        size = blk_getlength(blk);
        if (size < 0) {
            error_report("Could not get size of '%s': %s",
                         filename, strerror(-size));
            ret = -1;
            goto out;
        }
        if (blk_old_backing) {
            old_backing_size = blk_getlength(blk_old_backing);
            if (old_backing_size < 0) {
                char backing_name[PATH_MAX];

                bdrv_get_backing_filename(bs, backing_name,
                                          sizeof(backing_name));
                error_report("Could not get size of '%s': %s",
                             backing_name, strerror(-old_backing_size));
                ret = -1;
                goto out;
            }
        }
        if (blk_new_backing) {
            new_backing_size = blk_getlength(blk_new_backing);
            if (new_backing_size < 0) {
                error_report("Could not get size of '%s': %s",
                             out_baseimg, strerror(-new_backing_size));
                ret = -1;
                goto out;
            }
        }

        if (size != 0) {
            local_progress = (float)100 / (size / MIN(size, IO_BUF_SIZE));
        }

        for (offset = 0; offset < size; offset += n) {
            bool old_backing_eof = false;
            int64_t n_alloc;

            /* How many bytes can we handle with the next read? */
            n = MIN(IO_BUF_SIZE, size - offset);

            /* If the cluster is allocated, we don't need to take action */
            ret = bdrv_is_allocated(unfiltered_bs, offset, n, &n);
            if (ret < 0) {
                error_report("error while reading image metadata: %s",
                             strerror(-ret));
                goto out;
            }
            if (ret) {
                continue;
            }

            if (prefix_chain_bs) {
                uint64_t bytes = n;

                /*
                 * If cluster wasn't changed since prefix_chain, we don't need
                 * to take action
                 */
                ret = bdrv_is_allocated_above(unfiltered_bs_cow,
                                              prefix_chain_bs, false,
                                              offset, n, &n);
                if (ret < 0) {
                    error_report("error while reading image metadata: %s",
                                 strerror(-ret));
                    goto out;
                }
                if (!ret && n) {
                    continue;
                }
                if (!n) {
                    /*
                     * If we've reached EOF of the old backing, it means that
                     * offsets beyond the old backing size were read as zeroes.
                     * Now we will need to explicitly zero the cluster in
                     * order to preserve that state after the rebase.
                     */
                    n = bytes;
                }
            }

            /*
             * At this point we know that the region [offset; offset + n)
             * is unallocated within the target image.  This region might be
             * unaligned to the target image's (sub)cluster boundaries, as
             * old backing may have smaller clusters (or have subclusters).
             * We extend it to the aligned boundaries to avoid CoW on
             * partial writes in blk_pwrite(),
             */
            n += offset - QEMU_ALIGN_DOWN(offset, write_align);
            offset = QEMU_ALIGN_DOWN(offset, write_align);
            n += QEMU_ALIGN_UP(offset + n, write_align) - (offset + n);
            n = MIN(n, size - offset);
            assert(!bdrv_is_allocated(unfiltered_bs, offset, n, &n_alloc) &&
                   n_alloc == n);

            /*
             * Much like with the target image, we'll try to read as much
             * of the old and new backings as we can.
             */
            n_old = MIN(n, MAX(0, old_backing_size - (int64_t) offset));
            n_new = MIN(n, MAX(0, new_backing_size - (int64_t) offset));

            /*
             * Read old and new backing file and take into consideration that
             * backing files may be smaller than the COW image.
             */
            memset(buf_old + n_old, 0, n - n_old);
            if (!n_old) {
                old_backing_eof = true;
            } else {
                ret = blk_pread(blk_old_backing, offset, n_old, buf_old, 0);
                if (ret < 0) {
                    error_report("error while reading from old backing file");
                    goto out;
                }
            }

            memset(buf_new + n_new, 0, n - n_new);
            if (n_new) {
                ret = blk_pread(blk_new_backing, offset, n_new, buf_new, 0);
                if (ret < 0) {
                    error_report("error while reading from new backing file");
                    goto out;
                }
            }

            /* If they differ, we need to write to the COW file */
            uint64_t written = 0;

            while (written < n) {
                int64_t pnum;

                if (compare_buffers(buf_old + written, buf_new + written,
                                    n - written, write_align, &pnum))
                {
                    if (old_backing_eof) {
                        ret = blk_pwrite_zeroes(blk, offset + written, pnum, 0);
                    } else {
                        assert(written + pnum <= IO_BUF_SIZE);
                        ret = blk_pwrite(blk, offset + written, pnum,
                                         buf_old + written, write_flags);
                    }
                    if (ret < 0) {
                        error_report("Error while writing to COW image: %s",
                            strerror(-ret));
                        goto out;
                    }
                }

                written += pnum;
                if (offset + written >= old_backing_size) {
                    old_backing_eof = true;
                }
            }
            qemu_progress_print(local_progress, 100);
        }
    }

    /*
     * Change the backing file. All clusters that are different from the old
     * backing file are overwritten in the COW file now, so the visible content
     * doesn't change when we switch the backing file.
     */
    if (out_baseimg && *out_baseimg) {
        ret = bdrv_change_backing_file(unfiltered_bs, out_baseimg, out_basefmt,
                                       true);
    } else {
        ret = bdrv_change_backing_file(unfiltered_bs, NULL, NULL, false);
    }

    if (ret == -ENOSPC) {
        error_report("Could not change the backing file to '%s': No "
                     "space left in the file header", out_baseimg);
    } else if (ret == -EINVAL && out_baseimg && !out_basefmt) {
        error_report("Could not change the backing file to '%s': backing "
                     "format must be specified", out_baseimg);
    } else if (ret < 0) {
        error_report("Could not change the backing file to '%s': %s",
            out_baseimg, strerror(-ret));
    }

    qemu_progress_print(100, 0);
    /*
     * TODO At this point it is possible to check if any clusters that are
     * allocated in the COW file are the same in the backing file. If so, they
     * could be dropped from the COW file. Don't do this before switching the
     * backing file, in case of a crash this would lead to corruption.
     */
out:
    qemu_progress_end();
    /* Cleanup */
    if (!unsafe) {
        blk_unref(blk_old_backing);
        blk_unref(blk_new_backing);
    }
    qemu_vfree(buf_old);
    qemu_vfree(buf_new);

    blk_unref(blk);
    if (ret) {
        return 1;
    }
    return 0;
}

static int img_resize(int argc, char **argv)
{
    Error *err = NULL;
    int c, ret, relative;
    const char *filename, *fmt, *size;
    int64_t n, total_size, current_size;
    bool quiet = false;
    BlockBackend *blk = NULL;
    PreallocMode prealloc = PREALLOC_MODE_OFF;
    QemuOpts *param;

    static QemuOptsList resize_options = {
        .name = "resize_options",
        .head = QTAILQ_HEAD_INITIALIZER(resize_options.head),
        .desc = {
            {
                .name = BLOCK_OPT_SIZE,
                .type = QEMU_OPT_SIZE,
                .help = "Virtual disk size"
            }, {
                /* end of list */
            }
        },
    };
    bool image_opts = false;
    bool shrink = false;

    /* Remove size from argv manually so that negative numbers are not treated
     * as options by getopt. */
    if (argc < 3) {
        error_exit("Not enough arguments");
        return 1;
    }

    size = argv[--argc];

    /* Parse getopt arguments */
    fmt = NULL;
    for(;;) {
        static const struct option long_options[] = {
            {"help", no_argument, 0, 'h'},
            {"object", required_argument, 0, OPTION_OBJECT},
            {"image-opts", no_argument, 0, OPTION_IMAGE_OPTS},
            {"preallocation", required_argument, 0, OPTION_PREALLOCATION},
            {"shrink", no_argument, 0, OPTION_SHRINK},
            {0, 0, 0, 0}
        };
        c = getopt_long(argc, argv, ":f:hq",
                        long_options, NULL);
        if (c == -1) {
            break;
        }
        switch(c) {
        case ':':
            missing_argument(argv[optind - 1]);
            break;
        case '?':
            unrecognized_option(argv[optind - 1]);
            break;
        case 'h':
            help();
            break;
        case 'f':
            fmt = optarg;
            break;
        case 'q':
            quiet = true;
            break;
        case OPTION_OBJECT:
            user_creatable_process_cmdline(optarg);
            break;
        case OPTION_IMAGE_OPTS:
            image_opts = true;
            break;
        case OPTION_PREALLOCATION:
            prealloc = qapi_enum_parse(&PreallocMode_lookup, optarg,
                                       PREALLOC_MODE__MAX, NULL);
            if (prealloc == PREALLOC_MODE__MAX) {
                error_report("Invalid preallocation mode '%s'", optarg);
                return 1;
            }
            break;
        case OPTION_SHRINK:
            shrink = true;
            break;
        }
    }
    if (optind != argc - 1) {
        error_exit("Expecting image file name and size");
    }
    filename = argv[optind++];

    /* Choose grow, shrink, or absolute resize mode */
    switch (size[0]) {
    case '+':
        relative = 1;
        size++;
        break;
    case '-':
        relative = -1;
        size++;
        break;
    default:
        relative = 0;
        break;
    }

    /* Parse size */
    param = qemu_opts_create(&resize_options, NULL, 0, &error_abort);
    if (!qemu_opt_set(param, BLOCK_OPT_SIZE, size, &err)) {
        error_report_err(err);
        ret = -1;
        qemu_opts_del(param);
        goto out;
    }
    n = qemu_opt_get_size(param, BLOCK_OPT_SIZE, 0);
    qemu_opts_del(param);

    blk = img_open(image_opts, filename, fmt,
                   BDRV_O_RDWR | BDRV_O_RESIZE, false, quiet,
                   false);
    if (!blk) {
        ret = -1;
        goto out;
    }

    current_size = blk_getlength(blk);
    if (current_size < 0) {
        error_report("Failed to inquire current image length: %s",
                     strerror(-current_size));
        ret = -1;
        goto out;
    }

    if (relative) {
        total_size = current_size + n * relative;
    } else {
        total_size = n;
    }
    if (total_size <= 0) {
        error_report("New image size must be positive");
        ret = -1;
        goto out;
    }

    if (total_size <= current_size && prealloc != PREALLOC_MODE_OFF) {
        error_report("Preallocation can only be used for growing images");
        ret = -1;
        goto out;
    }

    if (total_size < current_size && !shrink) {
        error_report("Use the --shrink option to perform a shrink operation.");
        warn_report("Shrinking an image will delete all data beyond the "
                    "shrunken image's end. Before performing such an "
                    "operation, make sure there is no important data there.");
        ret = -1;
        goto out;
    }

    /*
     * The user expects the image to have the desired size after
     * resizing, so pass @exact=true.  It is of no use to report
     * success when the image has not actually been resized.
     */
    ret = blk_truncate(blk, total_size, true, prealloc, 0, &err);
    if (!ret) {
        qprintf(quiet, "Image resized.\n");
    } else {
        error_report_err(err);
    }
out:
    blk_unref(blk);
    if (ret) {
        return 1;
    }
    return 0;
}

static void amend_status_cb(BlockDriverState *bs,
                            int64_t offset, int64_t total_work_size,
                            void *opaque)
{
    qemu_progress_print(100.f * offset / total_work_size, 0);
}

static int print_amend_option_help(const char *format)
{
    BlockDriver *drv;

    GRAPH_RDLOCK_GUARD_MAINLOOP();

    /* Find driver and parse its options */
    drv = bdrv_find_format(format);
    if (!drv) {
        error_report("Unknown file format '%s'", format);
        return 1;
    }

    if (!drv->bdrv_amend_options) {
        error_report("Format driver '%s' does not support option amendment",
                     format);
        return 1;
    }

    /* Every driver supporting amendment must have amend_opts */
    assert(drv->amend_opts);

    printf("Amend options for '%s':\n", format);
    qemu_opts_print_help(drv->amend_opts, false);
    return 0;
}

static int img_amend(int argc, char **argv)
{
    Error *err = NULL;
    int c, ret = 0;
    char *options = NULL;
    QemuOptsList *amend_opts = NULL;
    QemuOpts *opts = NULL;
    const char *fmt = NULL, *filename, *cache;
    int flags;
    bool writethrough;
    bool quiet = false, progress = false;
    BlockBackend *blk = NULL;
    BlockDriverState *bs = NULL;
    bool image_opts = false;
    bool force = false;

    cache = BDRV_DEFAULT_CACHE;
    for (;;) {
        static const struct option long_options[] = {
            {"help", no_argument, 0, 'h'},
            {"object", required_argument, 0, OPTION_OBJECT},
            {"image-opts", no_argument, 0, OPTION_IMAGE_OPTS},
            {"force", no_argument, 0, OPTION_FORCE},
            {0, 0, 0, 0}
        };
        c = getopt_long(argc, argv, ":ho:f:t:pq",
                        long_options, NULL);
        if (c == -1) {
            break;
        }

        switch (c) {
        case ':':
            missing_argument(argv[optind - 1]);
            break;
        case '?':
            unrecognized_option(argv[optind - 1]);
            break;
        case 'h':
            help();
            break;
        case 'o':
            if (accumulate_options(&options, optarg) < 0) {