diff options
Diffstat (limited to 'kernel/printk')
| -rw-r--r-- | kernel/printk/Makefile | 9 | ||||
| -rw-r--r-- | kernel/printk/braille.c | 58 | ||||
| -rw-r--r-- | kernel/printk/braille.h | 56 | ||||
| -rw-r--r-- | kernel/printk/console_cmdline.h | 16 | ||||
| -rw-r--r-- | kernel/printk/index.c | 194 | ||||
| -rw-r--r-- | kernel/printk/internal.h | 60 | ||||
| -rw-r--r-- | kernel/printk/printk.c | 3975 | ||||
| -rw-r--r-- | kernel/printk/printk_ringbuffer.c | 2124 | ||||
| -rw-r--r-- | kernel/printk/printk_ringbuffer.h | 384 | ||||
| -rw-r--r-- | kernel/printk/printk_safe.c | 47 | ||||
| -rw-r--r-- | kernel/printk/sysctl.c | 85 |
11 files changed, 7008 insertions, 0 deletions
diff --git a/kernel/printk/Makefile b/kernel/printk/Makefile new file mode 100644 index 000000000..f5b388e81 --- /dev/null +++ b/kernel/printk/Makefile @@ -0,0 +1,9 @@ +# SPDX-License-Identifier: GPL-2.0-only +obj-y = printk.o +obj-$(CONFIG_PRINTK) += printk_safe.o +obj-$(CONFIG_A11Y_BRAILLE_CONSOLE) += braille.o +obj-$(CONFIG_PRINTK_INDEX) += index.o + +obj-$(CONFIG_PRINTK) += printk_support.o +printk_support-y := printk_ringbuffer.o +printk_support-$(CONFIG_SYSCTL) += sysctl.o diff --git a/kernel/printk/braille.c b/kernel/printk/braille.c new file mode 100644 index 000000000..17a9591e5 --- /dev/null +++ b/kernel/printk/braille.c @@ -0,0 +1,58 @@ +// SPDX-License-Identifier: GPL-2.0 +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/kernel.h> +#include <linux/console.h> +#include <linux/errno.h> +#include <linux/string.h> + +#include "console_cmdline.h" +#include "braille.h" + +int _braille_console_setup(char **str, char **brl_options) +{ + size_t len; + + len = str_has_prefix(*str, "brl,"); + if (len) { + *brl_options = ""; + *str += len; + return 0; + } + + len = str_has_prefix(*str, "brl="); + if (len) { + *brl_options = *str + len; + *str = strchr(*brl_options, ','); + if (!*str) { + pr_err("need port name after brl=\n"); + return -EINVAL; + } + *((*str)++) = 0; + } + + return 0; +} + +int +_braille_register_console(struct console *console, struct console_cmdline *c) +{ + int rtn = 0; + + if (c->brl_options) { + console->flags |= CON_BRL; + rtn = braille_register_console(console, c->index, c->options, + c->brl_options); + } + + return rtn; +} + +int +_braille_unregister_console(struct console *console) +{ + if (console->flags & CON_BRL) + return braille_unregister_console(console); + + return 0; +} diff --git a/kernel/printk/braille.h b/kernel/printk/braille.h new file mode 100644 index 000000000..123154f86 --- /dev/null +++ b/kernel/printk/braille.h @@ -0,0 +1,56 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _PRINTK_BRAILLE_H +#define _PRINTK_BRAILLE_H + +#ifdef CONFIG_A11Y_BRAILLE_CONSOLE + +static inline void +braille_set_options(struct console_cmdline *c, char *brl_options) +{ + c->brl_options = brl_options; +} + +/* + * Setup console according to braille options. + * Return -EINVAL on syntax error, 0 on success (or no braille option was + * actually given). + * Modifies str to point to the serial options + * Sets brl_options to the parsed braille options. + */ +int +_braille_console_setup(char **str, char **brl_options); + +int +_braille_register_console(struct console *console, struct console_cmdline *c); + +int +_braille_unregister_console(struct console *console); + +#else + +static inline void +braille_set_options(struct console_cmdline *c, char *brl_options) +{ +} + +static inline int +_braille_console_setup(char **str, char **brl_options) +{ + return 0; +} + +static inline int +_braille_register_console(struct console *console, struct console_cmdline *c) +{ + return 0; +} + +static inline int +_braille_unregister_console(struct console *console) +{ + return 0; +} + +#endif + +#endif diff --git a/kernel/printk/console_cmdline.h b/kernel/printk/console_cmdline.h new file mode 100644 index 000000000..3ca74ad39 --- /dev/null +++ b/kernel/printk/console_cmdline.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _CONSOLE_CMDLINE_H +#define _CONSOLE_CMDLINE_H + +struct console_cmdline +{ + char name[16]; /* Name of the driver */ + int index; /* Minor dev. to use */ + bool user_specified; /* Specified by command line vs. platform */ + char *options; /* Options for the driver */ +#ifdef CONFIG_A11Y_BRAILLE_CONSOLE + char *brl_options; /* Options for braille driver */ +#endif +}; + +#endif diff --git a/kernel/printk/index.c b/kernel/printk/index.c new file mode 100644 index 000000000..a6b27526b --- /dev/null +++ b/kernel/printk/index.c @@ -0,0 +1,194 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Userspace indexing of printk formats + */ + +#include <linux/debugfs.h> +#include <linux/module.h> +#include <linux/printk.h> +#include <linux/slab.h> +#include <linux/string_helpers.h> + +#include "internal.h" + +extern struct pi_entry *__start_printk_index[]; +extern struct pi_entry *__stop_printk_index[]; + +/* The base dir for module formats, typically debugfs/printk/index/ */ +static struct dentry *dfs_index; + +static struct pi_entry *pi_get_entry(const struct module *mod, loff_t pos) +{ + struct pi_entry **entries; + unsigned int nr_entries; + +#ifdef CONFIG_MODULES + if (mod) { + entries = mod->printk_index_start; + nr_entries = mod->printk_index_size; + } else +#endif + { + /* vmlinux, comes from linker symbols */ + entries = __start_printk_index; + nr_entries = __stop_printk_index - __start_printk_index; + } + + if (pos >= nr_entries) + return NULL; + + return entries[pos]; +} + +static void *pi_next(struct seq_file *s, void *v, loff_t *pos) +{ + const struct module *mod = s->file->f_inode->i_private; + struct pi_entry *entry = pi_get_entry(mod, *pos); + + (*pos)++; + + return entry; +} + +static void *pi_start(struct seq_file *s, loff_t *pos) +{ + /* + * Make show() print the header line. Do not update *pos because + * pi_next() still has to return the entry at index 0 later. + */ + if (*pos == 0) + return SEQ_START_TOKEN; + + return pi_next(s, NULL, pos); +} + +/* + * We need both ESCAPE_ANY and explicit characters from ESCAPE_SPECIAL in @only + * because otherwise ESCAPE_NAP will cause double quotes and backslashes to be + * ignored for quoting. + */ +#define seq_escape_printf_format(s, src) \ + seq_escape_str(s, src, ESCAPE_ANY | ESCAPE_NAP | ESCAPE_APPEND, "\"\\") + +static int pi_show(struct seq_file *s, void *v) +{ + const struct pi_entry *entry = v; + int level = LOGLEVEL_DEFAULT; + enum printk_info_flags flags = 0; + u16 prefix_len = 0; + + if (v == SEQ_START_TOKEN) { + seq_puts(s, "# <level/flags> filename:line function \"format\"\n"); + return 0; + } + + if (!entry->fmt) + return 0; + + if (entry->level) + printk_parse_prefix(entry->level, &level, &flags); + else + prefix_len = printk_parse_prefix(entry->fmt, &level, &flags); + + + if (flags & LOG_CONT) { + /* + * LOGLEVEL_DEFAULT here means "use the same level as the + * message we're continuing from", not the default message + * loglevel, so don't display it as such. + */ + if (level == LOGLEVEL_DEFAULT) + seq_puts(s, "<c>"); + else + seq_printf(s, "<%d,c>", level); + } else + seq_printf(s, "<%d>", level); + + seq_printf(s, " %s:%d %s \"", entry->file, entry->line, entry->func); + if (entry->subsys_fmt_prefix) + seq_escape_printf_format(s, entry->subsys_fmt_prefix); + seq_escape_printf_format(s, entry->fmt + prefix_len); + seq_puts(s, "\"\n"); + + return 0; +} + +static void pi_stop(struct seq_file *p, void *v) { } + +static const struct seq_operations dfs_index_sops = { + .start = pi_start, + .next = pi_next, + .show = pi_show, + .stop = pi_stop, +}; + +DEFINE_SEQ_ATTRIBUTE(dfs_index); + +#ifdef CONFIG_MODULES +static const char *pi_get_module_name(struct module *mod) +{ + return mod ? mod->name : "vmlinux"; +} +#else +static const char *pi_get_module_name(struct module *mod) +{ + return "vmlinux"; +} +#endif + +static void pi_create_file(struct module *mod) +{ + debugfs_create_file(pi_get_module_name(mod), 0444, dfs_index, + mod, &dfs_index_fops); +} + +#ifdef CONFIG_MODULES +static void pi_remove_file(struct module *mod) +{ + debugfs_lookup_and_remove(pi_get_module_name(mod), dfs_index); +} + +static int pi_module_notify(struct notifier_block *nb, unsigned long op, + void *data) +{ + struct module *mod = data; + + switch (op) { + case MODULE_STATE_COMING: + pi_create_file(mod); + break; + case MODULE_STATE_GOING: + pi_remove_file(mod); + break; + default: /* we don't care about other module states */ + break; + } + + return NOTIFY_OK; +} + +static struct notifier_block module_printk_fmts_nb = { + .notifier_call = pi_module_notify, +}; + +static void __init pi_setup_module_notifier(void) +{ + register_module_notifier(&module_printk_fmts_nb); +} +#else +static inline void __init pi_setup_module_notifier(void) { } +#endif + +static int __init pi_init(void) +{ + struct dentry *dfs_root = debugfs_create_dir("printk", NULL); + + dfs_index = debugfs_create_dir("index", dfs_root); + pi_setup_module_notifier(); + pi_create_file(NULL); + + return 0; +} + +/* debugfs comes up on core and must be initialised first */ +postcore_initcall(pi_init); diff --git a/kernel/printk/internal.h b/kernel/printk/internal.h new file mode 100644 index 000000000..d947ca6c8 --- /dev/null +++ b/kernel/printk/internal.h @@ -0,0 +1,60 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * internal.h - printk internal definitions + */ +#include <linux/percpu.h> + +#if defined(CONFIG_PRINTK) && defined(CONFIG_SYSCTL) +void __init printk_sysctl_init(void); +int devkmsg_sysctl_set_loglvl(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos); +#else +#define printk_sysctl_init() do { } while (0) +#endif + +#ifdef CONFIG_PRINTK + +/* Flags for a single printk record. */ +enum printk_info_flags { + LOG_NEWLINE = 2, /* text ended with a newline */ + LOG_CONT = 8, /* text is a fragment of a continuation line */ +}; + +__printf(4, 0) +int vprintk_store(int facility, int level, + const struct dev_printk_info *dev_info, + const char *fmt, va_list args); + +__printf(1, 0) int vprintk_default(const char *fmt, va_list args); +__printf(1, 0) int vprintk_deferred(const char *fmt, va_list args); + +bool printk_percpu_data_ready(void); + +#define printk_safe_enter_irqsave(flags) \ + do { \ + local_irq_save(flags); \ + __printk_safe_enter(); \ + } while (0) + +#define printk_safe_exit_irqrestore(flags) \ + do { \ + __printk_safe_exit(); \ + local_irq_restore(flags); \ + } while (0) + +void defer_console_output(void); + +u16 printk_parse_prefix(const char *text, int *level, + enum printk_info_flags *flags); +#else + +/* + * In !PRINTK builds we still export console_sem + * semaphore and some of console functions (console_unlock()/etc.), so + * printk-safe must preserve the existing local IRQ guarantees. + */ +#define printk_safe_enter_irqsave(flags) local_irq_save(flags) +#define printk_safe_exit_irqrestore(flags) local_irq_restore(flags) + +static inline bool printk_percpu_data_ready(void) { return false; } +#endif /* CONFIG_PRINTK */ diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c new file mode 100644 index 000000000..cc53fb77f --- /dev/null +++ b/kernel/printk/printk.c @@ -0,0 +1,3975 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * linux/kernel/printk.c + * + * Copyright (C) 1991, 1992 Linus Torvalds + * + * Modified to make sys_syslog() more flexible: added commands to + * return the last 4k of kernel messages, regardless of whether + * they've been read or not. Added option to suppress kernel printk's + * to the console. Added hook for sending the console messages + * elsewhere, in preparation for a serial line console (someday). + * Ted Ts'o, 2/11/93. + * Modified for sysctl support, 1/8/97, Chris Horn. + * Fixed SMP synchronization, 08/08/99, Manfred Spraul + * manfred@colorfullife.com + * Rewrote bits to get rid of console_lock + * 01Mar01 Andrew Morton + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/kernel.h> +#include <linux/mm.h> +#include <linux/tty.h> +#include <linux/tty_driver.h> +#include <linux/console.h> +#include <linux/init.h> +#include <linux/jiffies.h> +#include <linux/nmi.h> +#include <linux/module.h> +#include <linux/moduleparam.h> +#include <linux/delay.h> +#include <linux/smp.h> +#include <linux/security.h> +#include <linux/memblock.h> +#include <linux/syscalls.h> +#include <linux/crash_core.h> +#include <linux/ratelimit.h> +#include <linux/kmsg_dump.h> +#include <linux/syslog.h> +#include <linux/cpu.h> +#include <linux/rculist.h> +#include <linux/poll.h> +#include <linux/irq_work.h> +#include <linux/ctype.h> +#include <linux/uio.h> +#include <linux/sched/clock.h> +#include <linux/sched/debug.h> +#include <linux/sched/task_stack.h> + +#include <linux/uaccess.h> +#include <asm/sections.h> + +#include <trace/events/initcall.h> +#define CREATE_TRACE_POINTS +#include <trace/events/printk.h> + +#include "printk_ringbuffer.h" +#include "console_cmdline.h" +#include "braille.h" +#include "internal.h" + +int console_printk[4] = { + CONSOLE_LOGLEVEL_DEFAULT, /* console_loglevel */ + MESSAGE_LOGLEVEL_DEFAULT, /* default_message_loglevel */ + CONSOLE_LOGLEVEL_MIN, /* minimum_console_loglevel */ + CONSOLE_LOGLEVEL_DEFAULT, /* default_console_loglevel */ +}; +EXPORT_SYMBOL_GPL(console_printk); + +atomic_t ignore_console_lock_warning __read_mostly = ATOMIC_INIT(0); +EXPORT_SYMBOL(ignore_console_lock_warning); + +/* + * Low level drivers may need that to know if they can schedule in + * their unblank() callback or not. So let's export it. + */ +int oops_in_progress; +EXPORT_SYMBOL(oops_in_progress); + +/* + * console_sem protects the console_drivers list, and also + * provides serialisation for access to the entire console + * driver system. + */ +static DEFINE_SEMAPHORE(console_sem); +struct console *console_drivers; +EXPORT_SYMBOL_GPL(console_drivers); + +/* + * System may need to suppress printk message under certain + * circumstances, like after kernel panic happens. + */ +int __read_mostly suppress_printk; + +/* + * During panic, heavy printk by other CPUs can delay the + * panic and risk deadlock on console resources. + */ +static int __read_mostly suppress_panic_printk; + +#ifdef CONFIG_LOCKDEP +static struct lockdep_map console_lock_dep_map = { + .name = "console_lock" +}; +#endif + +enum devkmsg_log_bits { + __DEVKMSG_LOG_BIT_ON = 0, + __DEVKMSG_LOG_BIT_OFF, + __DEVKMSG_LOG_BIT_LOCK, +}; + +enum devkmsg_log_masks { + DEVKMSG_LOG_MASK_ON = BIT(__DEVKMSG_LOG_BIT_ON), + DEVKMSG_LOG_MASK_OFF = BIT(__DEVKMSG_LOG_BIT_OFF), + DEVKMSG_LOG_MASK_LOCK = BIT(__DEVKMSG_LOG_BIT_LOCK), +}; + +/* Keep both the 'on' and 'off' bits clear, i.e. ratelimit by default: */ +#define DEVKMSG_LOG_MASK_DEFAULT 0 + +static unsigned int __read_mostly devkmsg_log = DEVKMSG_LOG_MASK_DEFAULT; + +static int __control_devkmsg(char *str) +{ + size_t len; + + if (!str) + return -EINVAL; + + len = str_has_prefix(str, "on"); + if (len) { + devkmsg_log = DEVKMSG_LOG_MASK_ON; + return len; + } + + len = str_has_prefix(str, "off"); + if (len) { + devkmsg_log = DEVKMSG_LOG_MASK_OFF; + return len; + } + + len = str_has_prefix(str, "ratelimit"); + if (len) { + devkmsg_log = DEVKMSG_LOG_MASK_DEFAULT; + return len; + } + + return -EINVAL; +} + +static int __init control_devkmsg(char *str) +{ + if (__control_devkmsg(str) < 0) { + pr_warn("printk.devkmsg: bad option string '%s'\n", str); + return 1; + } + + /* + * Set sysctl string accordingly: + */ + if (devkmsg_log == DEVKMSG_LOG_MASK_ON) + strcpy(devkmsg_log_str, "on"); + else if (devkmsg_log == DEVKMSG_LOG_MASK_OFF) + strcpy(devkmsg_log_str, "off"); + /* else "ratelimit" which is set by default. */ + + /* + * Sysctl cannot change it anymore. The kernel command line setting of + * this parameter is to force the setting to be permanent throughout the + * runtime of the system. This is a precation measure against userspace + * trying to be a smarta** and attempting to change it up on us. + */ + devkmsg_log |= DEVKMSG_LOG_MASK_LOCK; + + return 1; +} +__setup("printk.devkmsg=", control_devkmsg); + +char devkmsg_log_str[DEVKMSG_STR_MAX_SIZE] = "ratelimit"; +#if defined(CONFIG_PRINTK) && defined(CONFIG_SYSCTL) +int devkmsg_sysctl_set_loglvl(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) +{ + char old_str[DEVKMSG_STR_MAX_SIZE]; + unsigned int old; + int err; + + if (write) { + if (devkmsg_log & DEVKMSG_LOG_MASK_LOCK) + return -EINVAL; + + old = devkmsg_log; + strncpy(old_str, devkmsg_log_str, DEVKMSG_STR_MAX_SIZE); + } + + err = proc_dostring(table, write, buffer, lenp, ppos); + if (err) + return err; + + if (write) { + err = __control_devkmsg(devkmsg_log_str); + + /* + * Do not accept an unknown string OR a known string with + * trailing crap... + */ + if (err < 0 || (err + 1 != *lenp)) { + + /* ... and restore old setting. */ + devkmsg_log = old; + strncpy(devkmsg_log_str, old_str, DEVKMSG_STR_MAX_SIZE); + + return -EINVAL; + } + } + + return 0; +} +#endif /* CONFIG_PRINTK && CONFIG_SYSCTL */ + +/* + * Helper macros to handle lockdep when locking/unlocking console_sem. We use + * macros instead of functions so that _RET_IP_ contains useful information. + */ +#define down_console_sem() do { \ + down(&console_sem);\ + mutex_acquire(&console_lock_dep_map, 0, 0, _RET_IP_);\ +} while (0) + +static int __down_trylock_console_sem(unsigned long ip) +{ + int lock_failed; + unsigned long flags; + + /* + * Here and in __up_console_sem() we need to be in safe mode, + * because spindump/WARN/etc from under console ->lock will + * deadlock in printk()->down_trylock_console_sem() otherwise. + */ + printk_safe_enter_irqsave(flags); + lock_failed = down_trylock(&console_sem); + printk_safe_exit_irqrestore(flags); + + if (lock_failed) + return 1; + mutex_acquire(&console_lock_dep_map, 0, 1, ip); + return 0; +} +#define down_trylock_console_sem() __down_trylock_console_sem(_RET_IP_) + +static void __up_console_sem(unsigned long ip) +{ + unsigned long flags; + + mutex_release(&console_lock_dep_map, ip); + + printk_safe_enter_irqsave(flags); + up(&console_sem); + printk_safe_exit_irqrestore(flags); +} +#define up_console_sem() __up_console_sem(_RET_IP_) + +static bool panic_in_progress(void) +{ + return unlikely(atomic_read(&panic_cpu) != PANIC_CPU_INVALID); +} + +/* + * This is used for debugging the mess that is the VT code by + * keeping track if we have the console semaphore held. It's + * definitely not the perfect debug tool (we don't know if _WE_ + * hold it and are racing, but it helps tracking those weird code + * paths in the console code where we end up in places I want + * locked without the console semaphore held). + */ +static int console_locked, console_suspended; + +/* + * Array of consoles built from command line options (console=) + */ + +#define MAX_CMDLINECONSOLES 8 + +static struct console_cmdline console_cmdline[MAX_CMDLINECONSOLES]; + +static int preferred_console = -1; +int console_set_on_cmdline; +EXPORT_SYMBOL(console_set_on_cmdline); + +/* Flag: console code may call schedule() */ +static int console_may_schedule; + +enum con_msg_format_flags { + MSG_FORMAT_DEFAULT = 0, + MSG_FORMAT_SYSLOG = (1 << 0), +}; + +static int console_msg_format = MSG_FORMAT_DEFAULT; + +/* + * The printk log buffer consists of a sequenced collection of records, each + * containing variable length message text. Every record also contains its + * own meta-data (@info). + * + * Every record meta-data carries the timestamp in microseconds, as well as + * the standard userspace syslog level and syslog facility. The usual kernel + * messages use LOG_KERN; userspace-injected messages always carry a matching + * syslog facility, by default LOG_USER. The origin of every message can be + * reliably determined that way. + * + * The human readable log message of a record is available in @text, the + * length of the message text in @text_len. The stored message is not + * terminated. + * + * Optionally, a record can carry a dictionary of properties (key/value + * pairs), to provide userspace with a machine-readable message context. + * + * Examples for well-defined, commonly used property names are: + * DEVICE=b12:8 device identifier + * b12:8 block dev_t + * c127:3 char dev_t + * n8 netdev ifindex + * +sound:card0 subsystem:devname + * SUBSYSTEM=pci driver-core subsystem name + * + * Valid characters in property names are [a-zA-Z0-9.-_]. Property names + * and values are terminated by a '\0' character. + * + * Example of record values: + * record.text_buf = "it's a line" (unterminated) + * record.info.seq = 56 + * record.info.ts_nsec = 36863 + * record.info.text_len = 11 + * record.info.facility = 0 (LOG_KERN) + * record.info.flags = 0 + * record.info.level = 3 (LOG_ERR) + * record.info.caller_id = 299 (task 299) + * record.info.dev_info.subsystem = "pci" (terminated) + * record.info.dev_info.device = "+pci:0000:00:01.0" (terminated) + * + * The 'struct printk_info' buffer must never be directly exported to + * userspace, it is a kernel-private implementation detail that might + * need to be changed in the future, when the requirements change. + * + * /dev/kmsg exports the structured data in the following line format: + * "<level>,<sequnum>,<timestamp>,<contflag>[,additional_values, ... ];<message text>\n" + * + * Users of the export format should ignore possible additional values + * separated by ',', and find the message after the ';' character. + * + * The optional key/value pairs are attached as continuation lines starting + * with a space character and terminated by a newline. All possible + * non-prinatable characters are escaped in the "\xff" notation. + */ + +/* syslog_lock protects syslog_* variables and write access to clear_seq. */ +static DEFINE_MUTEX(syslog_lock); + +#ifdef CONFIG_PRINTK +DECLARE_WAIT_QUEUE_HEAD(log_wait); +/* All 3 protected by @syslog_lock. */ +/* the next printk record to read by syslog(READ) or /proc/kmsg */ +static u64 syslog_seq; +static size_t syslog_partial; +static bool syslog_time; + +struct latched_seq { + seqcount_latch_t latch; + u64 val[2]; +}; + +/* + * The next printk record to read after the last 'clear' command. There are + * two copies (updated with seqcount_latch) so that reads can locklessly + * access a valid value. Writers are synchronized by @syslog_lock. + */ +static struct latched_seq clear_seq = { + .latch = SEQCNT_LATCH_ZERO(clear_seq.latch), + .val[0] = 0, + .val[1] = 0, +}; + +#ifdef CONFIG_PRINTK_CALLER +#define PREFIX_MAX 48 +#else +#define PREFIX_MAX 32 +#endif + +/* the maximum size of a formatted record (i.e. with prefix added per line) */ +#define CONSOLE_LOG_MAX 1024 + +/* the maximum size for a dropped text message */ +#define DROPPED_TEXT_MAX 64 + +/* the maximum size allowed to be reserved for a record */ +#define LOG_LINE_MAX (CONSOLE_LOG_MAX - PREFIX_MAX) + +#define LOG_LEVEL(v) ((v) & 0x07) +#define LOG_FACILITY(v) ((v) >> 3 & 0xff) + +/* record buffer */ +#define LOG_ALIGN __alignof__(unsigned long) +#define __LOG_BUF_LEN (1 << CONFIG_LOG_BUF_SHIFT) +#define LOG_BUF_LEN_MAX (u32)(1 << 31) +static char __log_buf[__LOG_BUF_LEN] __aligned(LOG_ALIGN); +static char *log_buf = __log_buf; +static u32 log_buf_len = __LOG_BUF_LEN; + +/* + * Define the average message size. This only affects the number of + * descriptors that will be available. Underestimating is better than + * overestimating (too many available descriptors is better than not enough). + */ +#define PRB_AVGBITS 5 /* 32 character average length */ + +#if CONFIG_LOG_BUF_SHIFT <= PRB_AVGBITS +#error CONFIG_LOG_BUF_SHIFT value too small. +#endif +_DEFINE_PRINTKRB(printk_rb_static, CONFIG_LOG_BUF_SHIFT - PRB_AVGBITS, + PRB_AVGBITS, &__log_buf[0]); + +static struct printk_ringbuffer printk_rb_dynamic; + +static struct printk_ringbuffer *prb = &printk_rb_static; + +/* + * We cannot access per-CPU data (e.g. per-CPU flush irq_work) before + * per_cpu_areas are initialised. This variable is set to true when + * it's safe to access per-CPU data. + */ +static bool __printk_percpu_data_ready __ro_after_init; + +bool printk_percpu_data_ready(void) +{ + return __printk_percpu_data_ready; +} + +/* Must be called under syslog_lock. */ +static void latched_seq_write(struct latched_seq *ls, u64 val) +{ + raw_write_seqcount_latch(&ls->latch); + ls->val[0] = val; + raw_write_seqcount_latch(&ls->latch); + ls->val[1] = val; +} + +/* Can be called from any context. */ +static u64 latched_seq_read_nolock(struct latched_seq *ls) +{ + unsigned int seq; + unsigned int idx; + u64 val; + + do { + seq = raw_read_seqcount_latch(&ls->latch); + idx = seq & 0x1; + val = ls->val[idx]; + } while (read_seqcount_latch_retry(&ls->latch, seq)); + + return val; +} + +/* Return log buffer address */ +char *log_buf_addr_get(void) +{ + return log_buf; +} + +/* Return log buffer size */ +u32 log_buf_len_get(void) +{ + return log_buf_len; +} + +/* + * Define how much of the log buffer we could take at maximum. The value + * must be greater than two. Note that only half of the buffer is available + * when the index points to the middle. + */ +#define MAX_LOG_TAKE_PART 4 +static const char trunc_msg[] = "<truncated>"; + +static void truncate_msg(u16 *text_len, u16 *trunc_msg_len) +{ + /* + * The message should not take the whole buffer. Otherwise, it might + * get removed too soon. + */ + u32 max_text_len = log_buf_len / MAX_LOG_TAKE_PART; + + if (*text_len > max_text_len) + *text_len = max_text_len; + + /* enable the warning message (if there is room) */ + *trunc_msg_len = strlen(trunc_msg); + if (*text_len >= *trunc_msg_len) + *text_len -= *trunc_msg_len; + else + *trunc_msg_len = 0; +} + +int dmesg_restrict = IS_ENABLED(CONFIG_SECURITY_DMESG_RESTRICT); + +static int syslog_action_restricted(int type) +{ + if (dmesg_restrict) + return 1; + /* + * Unless restricted, we allow "read all" and "get buffer size" + * for everybody. + */ + return type != SYSLOG_ACTION_READ_ALL && + type != SYSLOG_ACTION_SIZE_BUFFER; +} + +static int check_syslog_permissions(int type, int source) +{ + /* + * If this is from /proc/kmsg and we've already opened it, then we've + * already done the capabilities checks at open time. + */ + if (source == SYSLOG_FROM_PROC && type != SYSLOG_ACTION_OPEN) + goto ok; + + if (syslog_action_restricted(type)) { + if (capable(CAP_SYSLOG)) + goto ok; + /* + * For historical reasons, accept CAP_SYS_ADMIN too, with + * a warning. + */ + if (capable(CAP_SYS_ADMIN)) { + pr_warn_once("%s (%d): Attempt to access syslog with " + "CAP_SYS_ADMIN but no CAP_SYSLOG " + "(deprecated).\n", + current->comm, task_pid_nr(current)); + goto ok; + } + return -EPERM; + } +ok: + return security_syslog(type); +} + +static void append_char(char **pp, char *e, char c) +{ + if (*pp < e) + *(*pp)++ = c; +} + +static ssize_t info_print_ext_header(char *buf, size_t size, + struct printk_info *info) +{ + u64 ts_usec = info->ts_nsec; + char caller[20]; +#ifdef CONFIG_PRINTK_CALLER + u32 id = info->caller_id; + + snprintf(caller, sizeof(caller), ",caller=%c%u", + id & 0x80000000 ? 'C' : 'T', id & ~0x80000000); +#else + caller[0] = '\0'; +#endif + + do_div(ts_usec, 1000); + + return scnprintf(buf, size, "%u,%llu,%llu,%c%s;", + (info->facility << 3) | info->level, info->seq, + ts_usec, info->flags & LOG_CONT ? 'c' : '-', caller); +} + +static ssize_t msg_add_ext_text(char *buf, size_t size, + const char *text, size_t text_len, + unsigned char endc) +{ + char *p = buf, *e = buf + size; + size_t i; + + /* escape non-printable characters */ + for (i = 0; i < text_len; i++) { + unsigned char c = text[i]; + + if (c < ' ' || c >= 127 || c == '\\') + p += scnprintf(p, e - p, "\\x%02x", c); + else + append_char(&p, e, c); + } + append_char(&p, e, endc); + + return p - buf; +} + +static ssize_t msg_add_dict_text(char *buf, size_t size, + const char *key, const char *val) +{ + size_t val_len = strlen(val); + ssize_t len; + + if (!val_len) + return 0; + + len = msg_add_ext_text(buf, size, "", 0, ' '); /* dict prefix */ + len += msg_add_ext_text(buf + len, size - len, key, strlen(key), '='); + len += msg_add_ext_text(buf + len, size - len, val, val_len, '\n'); + + return len; +} + +static ssize_t msg_print_ext_body(char *buf, size_t size, + char *text, size_t text_len, + struct dev_printk_info *dev_info) +{ + ssize_t len; + + len = msg_add_ext_text(buf, size, text, text_len, '\n'); + + if (!dev_info) + goto out; + + len += msg_add_dict_text(buf + len, size - len, "SUBSYSTEM", + dev_info->subsystem); + len += msg_add_dict_text(buf + len, size - len, "DEVICE", + dev_info->device); +out: + return len; +} + +/* /dev/kmsg - userspace message inject/listen interface */ +struct devkmsg_user { + atomic64_t seq; + struct ratelimit_state rs; + struct mutex lock; + char buf[CONSOLE_EXT_LOG_MAX]; + + struct printk_info info; + char text_buf[CONSOLE_EXT_LOG_MAX]; + struct printk_record record; +}; + +static __printf(3, 4) __cold +int devkmsg_emit(int facility, int level, const char *fmt, ...) +{ + va_list args; + int r; + + va_start(args, fmt); + r = vprintk_emit(facility, level, NULL, fmt, args); + va_end(args); + + return r; +} + +static ssize_t devkmsg_write(struct kiocb *iocb, struct iov_iter *from) +{ + char *buf, *line; + int level = default_message_loglevel; + int facility = 1; /* LOG_USER */ + struct file *file = iocb->ki_filp; + struct devkmsg_user *user = file->private_data; + size_t len = iov_iter_count(from); + ssize_t ret = len; + + if (!user || len > LOG_LINE_MAX) + return -EINVAL; + + /* Ignore when user logging is disabled. */ + if (devkmsg_log & DEVKMSG_LOG_MASK_OFF) + return len; + + /* Ratelimit when not explicitly enabled. */ + if (!(devkmsg_log & DEVKMSG_LOG_MASK_ON)) { + if (!___ratelimit(&user->rs, current->comm)) + return ret; + } + + buf = kmalloc(len+1, GFP_KERNEL); + if (buf == NULL) + return -ENOMEM; + + buf[len] = '\0'; + if (!copy_from_iter_full(buf, len, from)) { + kfree(buf); + return -EFAULT; + } + + /* + * Extract and skip the syslog prefix <[0-9]*>. Coming from userspace + * the decimal value represents 32bit, the lower 3 bit are the log + * level, the rest are the log facility. + * + * If no prefix or no userspace facility is specified, we + * enforce LOG_USER, to be able to reliably distinguish + * kernel-generated messages from userspace-injected ones. + */ + line = buf; + if (line[0] == '<') { + char *endp = NULL; + unsigned int u; + + u = simple_strtoul(line + 1, &endp, 10); + if (endp && endp[0] == '>') { + level = LOG_LEVEL(u); + if (LOG_FACILITY(u) != 0) + facility = LOG_FACILITY(u); + endp++; + line = endp; + } + } + + devkmsg_emit(facility, level, "%s", line); + kfree(buf); + return ret; +} + +static ssize_t devkmsg_read(struct file *file, char __user *buf, + size_t count, loff_t *ppos) +{ + struct devkmsg_user *user = file->private_data; + struct printk_record *r = &user->record; + size_t len; + ssize_t ret; + + if (!user) + return -EBADF; + + ret = mutex_lock_interruptible(&user->lock); + if (ret) + return ret; + + if (!prb_read_valid(prb, atomic64_read(&user->seq), r)) { + if (file->f_flags & O_NONBLOCK) { + ret = -EAGAIN; + goto out; + } + + /* + * Guarantee this task is visible on the waitqueue before + * checking the wake condition. + * + * The full memory barrier within set_current_state() of + * prepare_to_wait_event() pairs with the full memory barrier + * within wq_has_sleeper(). + * + * This pairs with __wake_up_klogd:A. + */ + ret = wait_event_interruptible(log_wait, + prb_read_valid(prb, + atomic64_read(&user->seq), r)); /* LMM(devkmsg_read:A) */ + if (ret) + goto out; + } + + if (r->info->seq != atomic64_read(&user->seq)) { + /* our last seen message is gone, return error and reset */ + atomic64_set(&user->seq, r->info->seq); + ret = -EPIPE; + goto out; + } + + len = info_print_ext_header(user->buf, sizeof(user->buf), r->info); + len += msg_print_ext_body(user->buf + len, sizeof(user->buf) - len, + &r->text_buf[0], r->info->text_len, + &r->info->dev_info); + + atomic64_set(&user->seq, r->info->seq + 1); + + if (len > count) { + ret = -EINVAL; + goto out; + } + + if (copy_to_user(buf, user->buf, len)) { + ret = -EFAULT; + goto out; + } + ret = len; +out: + mutex_unlock(&user->lock); + return ret; +} + +/* + * Be careful when modifying this function!!! + * + * Only few operations are supported because the device works only with the + * entire variable length messages (records). Non-standard values are + * returned in the other cases and has been this way for quite some time. + * User space applications might depend on this behavior. + */ +static loff_t devkmsg_llseek(struct file *file, loff_t offset, int whence) +{ + struct devkmsg_user *user = file->private_data; + loff_t ret = 0; + + if (!user) + return -EBADF; + if (offset) + return -ESPIPE; + + switch (whence) { + case SEEK_SET: + /* the first record */ + atomic64_set(&user->seq, prb_first_valid_seq(prb)); + break; + case SEEK_DATA: + /* + * The first record after the last SYSLOG_ACTION_CLEAR, + * like issued by 'dmesg -c'. Reading /dev/kmsg itself + * changes no global state, and does not clear anything. + */ + atomic64_set(&user->seq, latched_seq_read_nolock(&clear_seq)); + break; + case SEEK_END: + /* after the last record */ + atomic64_set(&user->seq, prb_next_seq(prb)); + break; + default: + ret = -EINVAL; + } + return ret; +} + +static __poll_t devkmsg_poll(struct file *file, poll_table *wait) +{ + struct devkmsg_user *user = file->private_data; + struct printk_info info; + __poll_t ret = 0; + + if (!user) + return EPOLLERR|EPOLLNVAL; + + poll_wait(file, &log_wait, wait); + + if (prb_read_valid_info(prb, atomic64_read(&user->seq), &info, NULL)) { + /* return error when data has vanished underneath us */ + if (info.seq != atomic64_read(&user->seq)) + ret = EPOLLIN|EPOLLRDNORM|EPOLLERR|EPOLLPRI; + else + ret = EPOLLIN|EPOLLRDNORM; + } + + return ret; +} + +static int devkmsg_open(struct inode *inode, struct file *file) +{ + struct devkmsg_user *user; + int err; + + if (devkmsg_log & DEVKMSG_LOG_MASK_OFF) + return -EPERM; + + /* write-only does not need any file context */ + if ((file->f_flags & O_ACCMODE) != O_WRONLY) { + err = check_syslog_permissions(SYSLOG_ACTION_READ_ALL, + SYSLOG_FROM_READER); + if (err) + return err; + } + + user = kvmalloc(sizeof(struct devkmsg_user), GFP_KERNEL); + if (!user) + return -ENOMEM; + + ratelimit_default_init(&user->rs); + ratelimit_set_flags(&user->rs, RATELIMIT_MSG_ON_RELEASE); + + mutex_init(&user->lock); + + prb_rec_init_rd(&user->record, &user->info, + &user->text_buf[0], sizeof(user->text_buf)); + + atomic64_set(&user->seq, prb_first_valid_seq(prb)); + + file->private_data = user; + return 0; +} + +static int devkmsg_release(struct inode *inode, struct file *file) +{ + struct devkmsg_user *user = file->private_data; + + if (!user) + return 0; + + ratelimit_state_exit(&user->rs); + + mutex_destroy(&user->lock); + kvfree(user); + return 0; +} + +const struct file_operations kmsg_fops = { + .open = devkmsg_open, + .read = devkmsg_read, + .write_iter = devkmsg_write, + .llseek = devkmsg_llseek, + .poll = devkmsg_poll, + .release = devkmsg_release, +}; + +#ifdef CONFIG_CRASH_CORE +/* + * This appends the listed symbols to /proc/vmcore + * + * /proc/vmcore is used by various utilities, like crash and makedumpfile to + * obtain access to symbols that are otherwise very difficult to locate. These + * symbols are specifically used so that utilities can access and extract the + * dmesg log from a vmcore file after a crash. + */ +void log_buf_vmcoreinfo_setup(void) +{ + struct dev_printk_info *dev_info = NULL; + + VMCOREINFO_SYMBOL(prb); + VMCOREINFO_SYMBOL(printk_rb_static); + VMCOREINFO_SYMBOL(clear_seq); + + /* + * Export struct size and field offsets. User space tools can + * parse it and detect any changes to structure down the line. + */ + + VMCOREINFO_STRUCT_SIZE(printk_ringbuffer); + VMCOREINFO_OFFSET(printk_ringbuffer, desc_ring); + VMCOREINFO_OFFSET(printk_ringbuffer, text_data_ring); + VMCOREINFO_OFFSET(printk_ringbuffer, fail); + + VMCOREINFO_STRUCT_SIZE(prb_desc_ring); + VMCOREINFO_OFFSET(prb_desc_ring, count_bits); + VMCOREINFO_OFFSET(prb_desc_ring, descs); + VMCOREINFO_OFFSET(prb_desc_ring, infos); + VMCOREINFO_OFFSET(prb_desc_ring, head_id); + VMCOREINFO_OFFSET(prb_desc_ring, tail_id); + + VMCOREINFO_STRUCT_SIZE(prb_desc); + VMCOREINFO_OFFSET(prb_desc, state_var); + VMCOREINFO_OFFSET(prb_desc, text_blk_lpos); + + VMCOREINFO_STRUCT_SIZE(prb_data_blk_lpos); + VMCOREINFO_OFFSET(prb_data_blk_lpos, begin); + VMCOREINFO_OFFSET(prb_data_blk_lpos, next); + + VMCOREINFO_STRUCT_SIZE(printk_info); + VMCOREINFO_OFFSET(printk_info, seq); + VMCOREINFO_OFFSET(printk_info, ts_nsec); + VMCOREINFO_OFFSET(printk_info, text_len); + VMCOREINFO_OFFSET(printk_info, caller_id); + VMCOREINFO_OFFSET(printk_info, dev_info); + + VMCOREINFO_STRUCT_SIZE(dev_printk_info); + VMCOREINFO_OFFSET(dev_printk_info, subsystem); + VMCOREINFO_LENGTH(printk_info_subsystem, sizeof(dev_info->subsystem)); + VMCOREINFO_OFFSET(dev_printk_info, device); + VMCOREINFO_LENGTH(printk_info_device, sizeof(dev_info->device)); + + VMCOREINFO_STRUCT_SIZE(prb_data_ring); + VMCOREINFO_OFFSET(prb_data_ring, size_bits); + VMCOREINFO_OFFSET(prb_data_ring, data); + VMCOREINFO_OFFSET(prb_data_ring, head_lpos); + VMCOREINFO_OFFSET(prb_data_ring, tail_lpos); + + VMCOREINFO_SIZE(atomic_long_t); + VMCOREINFO_TYPE_OFFSET(atomic_long_t, counter); + + VMCOREINFO_STRUCT_SIZE(latched_seq); + VMCOREINFO_OFFSET(latched_seq, val); +} +#endif + +/* requested log_buf_len from kernel cmdline */ +static unsigned long __initdata new_log_buf_len; + +/* we practice scaling the ring buffer by powers of 2 */ +static void __init log_buf_len_update(u64 size) +{ + if (size > (u64)LOG_BUF_LEN_MAX) { + size = (u64)LOG_BUF_LEN_MAX; + pr_err("log_buf over 2G is not supported.\n"); + } + + if (size) + size = roundup_pow_of_two(size); + if (size > log_buf_len) + new_log_buf_len = (unsigned long)size; +} + +/* save requested log_buf_len since it's too early to process it */ +static int __init log_buf_len_setup(char *str) +{ + u64 size; + + if (!str) + return -EINVAL; + + size = memparse(str, &str); + + log_buf_len_update(size); + + return 0; +} +early_param("log_buf_len", log_buf_len_setup); + +#ifdef CONFIG_SMP +#define __LOG_CPU_MAX_BUF_LEN (1 << CONFIG_LOG_CPU_MAX_BUF_SHIFT) + +static void __init log_buf_add_cpu(void) +{ + unsigned int cpu_extra; + + /* + * archs should set up cpu_possible_bits properly with + * set_cpu_possible() after setup_arch() but just in + * case lets ensure this is valid. + */ + if (num_possible_cpus() == 1) + return; + + cpu_extra = (num_possible_cpus() - 1) * __LOG_CPU_MAX_BUF_LEN; + + /* by default this will only continue through for large > 64 CPUs */ + if (cpu_extra <= __LOG_BUF_LEN / 2) + return; + + pr_info("log_buf_len individual max cpu contribution: %d bytes\n", + __LOG_CPU_MAX_BUF_LEN); + pr_info("log_buf_len total cpu_extra contributions: %d bytes\n", + cpu_extra); + pr_info("log_buf_len min size: %d bytes\n", __LOG_BUF_LEN); + + log_buf_len_update(cpu_extra + __LOG_BUF_LEN); +} +#else /* !CONFIG_SMP */ +static inline void log_buf_add_cpu(void) {} +#endif /* CONFIG_SMP */ + +static void __init set_percpu_data_ready(void) +{ + __printk_percpu_data_ready = true; +} + +static unsigned int __init add_to_rb(struct printk_ringbuffer *rb, + struct printk_record *r) +{ + struct prb_reserved_entry e; + struct printk_record dest_r; + + prb_rec_init_wr(&dest_r, r->info->text_len); + + if (!prb_reserve(&e, rb, &dest_r)) + return 0; + + memcpy(&dest_r.text_buf[0], &r->text_buf[0], r->info->text_len); + dest_r.info->text_len = r->info->text_len; + dest_r.info->facility = r->info->facility; + dest_r.info->level = r->info->level; + dest_r.info->flags = r->info->flags; + dest_r.info->ts_nsec = r->info->ts_nsec; + dest_r.info->caller_id = r->info->caller_id; + memcpy(&dest_r.info->dev_info, &r->info->dev_info, sizeof(dest_r.info->dev_info)); + + prb_final_commit(&e); + + return prb_record_text_space(&e); +} + +static char setup_text_buf[LOG_LINE_MAX] __initdata; + +void __init setup_log_buf(int early) +{ + struct printk_info *new_infos; + unsigned int new_descs_count; + struct prb_desc *new_descs; + struct printk_info info; + struct printk_record r; + unsigned int text_size; + size_t new_descs_size; + size_t new_infos_size; + unsigned long flags; + char *new_log_buf; + unsigned int free; + u64 seq; + + /* + * Some archs call setup_log_buf() multiple times - first is very + * early, e.g. from setup_arch(), and second - when percpu_areas + * are initialised. + */ + if (!early) + set_percpu_data_ready(); + + if (log_buf != __log_buf) + return; + + if (!early && !new_log_buf_len) + log_buf_add_cpu(); + + if (!new_log_buf_len) + return; + + new_descs_count = new_log_buf_len >> PRB_AVGBITS; + if (new_descs_count == 0) { + pr_err("new_log_buf_len: %lu too small\n", new_log_buf_len); + return; + } + + new_log_buf = memblock_alloc(new_log_buf_len, LOG_ALIGN); + if (unlikely(!new_log_buf)) { + pr_err("log_buf_len: %lu text bytes not available\n", + new_log_buf_len); + return; + } + + new_descs_size = new_descs_count * sizeof(struct prb_desc); + new_descs = memblock_alloc(new_descs_size, LOG_ALIGN); + if (unlikely(!new_descs)) { + pr_err("log_buf_len: %zu desc bytes not available\n", + new_descs_size); + goto err_free_log_buf; + } + + new_infos_size = new_descs_count * sizeof(struct printk_info); + new_infos = memblock_alloc(new_infos_size, LOG_ALIGN); + if (unlikely(!new_infos)) { + pr_err("log_buf_len: %zu info bytes not available\n", + new_infos_size); + goto err_free_descs; + } + + prb_rec_init_rd(&r, &info, &setup_text_buf[0], sizeof(setup_text_buf)); + + prb_init(&printk_rb_dynamic, + new_log_buf, ilog2(new_log_buf_len), + new_descs, ilog2(new_descs_count), + new_infos); + + local_irq_save(flags); + + log_buf_len = new_log_buf_len; + log_buf = new_log_buf; + new_log_buf_len = 0; + + free = __LOG_BUF_LEN; + prb_for_each_record(0, &printk_rb_static, seq, &r) { + text_size = add_to_rb(&printk_rb_dynamic, &r); + if (text_size > free) + free = 0; + else + free -= text_size; + } + + prb = &printk_rb_dynamic; + + local_irq_restore(flags); + + /* + * Copy any remaining messages that might have appeared from + * NMI context after copying but before switching to the + * dynamic buffer. + */ + prb_for_each_record(seq, &printk_rb_static, seq, &r) { + text_size = add_to_rb(&printk_rb_dynamic, &r); + if (text_size > free) + free = 0; + else + free -= text_size; + } + + if (seq != prb_next_seq(&printk_rb_static)) { + pr_err("dropped %llu messages\n", + prb_next_seq(&printk_rb_static) - seq); + } + + pr_info("log_buf_len: %u bytes\n", log_buf_len); + pr_info("early log buf free: %u(%u%%)\n", + free, (free * 100) / __LOG_BUF_LEN); + return; + +err_free_descs: + memblock_free(new_descs, new_descs_size); +err_free_log_buf: + memblock_free(new_log_buf, new_log_buf_len); +} + +static bool __read_mostly ignore_loglevel; + +static int __init ignore_loglevel_setup(char *str) +{ + ignore_loglevel = true; + pr_info("debug: ignoring loglevel setting.\n"); + + return 0; +} + +early_param("ignore_loglevel", ignore_loglevel_setup); +module_param(ignore_loglevel, bool, S_IRUGO | S_IWUSR); +MODULE_PARM_DESC(ignore_loglevel, + "ignore loglevel setting (prints all kernel messages to the console)"); + +static bool suppress_message_printing(int level) +{ + return (level >= console_loglevel && !ignore_loglevel); +} + +#ifdef CONFIG_BOOT_PRINTK_DELAY + +static int boot_delay; /* msecs delay after each printk during bootup */ +static unsigned long long loops_per_msec; /* based on boot_delay */ + +static int __init boot_delay_setup(char *str) +{ + unsigned long lpj; + + lpj = preset_lpj ? preset_lpj : 1000000; /* some guess */ + loops_per_msec = (unsigned long long)lpj / 1000 * HZ; + + get_option(&str, &boot_delay); + if (boot_delay > 10 * 1000) + boot_delay = 0; + + pr_debug("boot_delay: %u, preset_lpj: %ld, lpj: %lu, " + "HZ: %d, loops_per_msec: %llu\n", + boot_delay, preset_lpj, lpj, HZ, loops_per_msec); + return 0; +} +early_param("boot_delay", boot_delay_setup); + +static void boot_delay_msec(int level) +{ + unsigned long long k; + unsigned long timeout; + + if ((boot_delay == 0 || system_state >= SYSTEM_RUNNING) + || suppress_message_printing(level)) { + return; + } + + k = (unsigned long long)loops_per_msec * boot_delay; + + timeout = jiffies + msecs_to_jiffies(boot_delay); + while (k) { + k--; + cpu_relax(); + /* + * use (volatile) jiffies to prevent + * compiler reduction; loop termination via jiffies + * is secondary and may or may not happen. + */ + if (time_after(jiffies, timeout)) + break; + touch_nmi_watchdog(); + } +} +#else +static inline void boot_delay_msec(int level) +{ +} +#endif + +static bool printk_time = IS_ENABLED(CONFIG_PRINTK_TIME); +module_param_named(time, printk_time, bool, S_IRUGO | S_IWUSR); + +static size_t print_syslog(unsigned int level, char *buf) +{ + return sprintf(buf, "<%u>", level); +} + +static size_t print_time(u64 ts, char *buf) +{ + unsigned long rem_nsec = do_div(ts, 1000000000); + + return sprintf(buf, "[%5lu.%06lu]", + (unsigned long)ts, rem_nsec / 1000); +} + +#ifdef CONFIG_PRINTK_CALLER +static size_t print_caller(u32 id, char *buf) +{ + char caller[12]; + + snprintf(caller, sizeof(caller), "%c%u", + id & 0x80000000 ? 'C' : 'T', id & ~0x80000000); + return sprintf(buf, "[%6s]", caller); +} +#else +#define print_caller(id, buf) 0 +#endif + +static size_t info_print_prefix(const struct printk_info *info, bool syslog, + bool time, char *buf) +{ + size_t len = 0; + + if (syslog) + len = print_syslog((info->facility << 3) | info->level, buf); + + if (time) + len += print_time(info->ts_nsec, buf + len); + + len += print_caller(info->caller_id, buf + len); + + if (IS_ENABLED(CONFIG_PRINTK_CALLER) || time) { + buf[len++] = ' '; + buf[len] = '\0'; + } + + return len; +} + +/* + * Prepare the record for printing. The text is shifted within the given + * buffer to avoid a need for another one. The following operations are + * done: + * + * - Add prefix for each line. + * - Drop truncated lines that no longer fit into the buffer. + * - Add the trailing newline that has been removed in vprintk_store(). + * - Add a string terminator. + * + * Since the produced string is always terminated, the maximum possible + * return value is @r->text_buf_size - 1; + * + * Return: The length of the updated/prepared text, including the added + * prefixes and the newline. The terminator is not counted. The dropped + * line(s) are not counted. + */ +static size_t record_print_text(struct printk_record *r, bool syslog, + bool time) +{ + size_t text_len = r->info->text_len; + size_t buf_size = r->text_buf_size; + char *text = r->text_buf; + char prefix[PREFIX_MAX]; + bool truncated = false; + size_t prefix_len; + size_t line_len; + size_t len = 0; + char *next; + + /* + * If the message was truncated because the buffer was not large + * enough, treat the available text as if it were the full text. + */ + if (text_len > buf_size) + text_len = buf_size; + + prefix_len = info_print_prefix(r->info, syslog, time, prefix); + + /* + * @text_len: bytes of unprocessed text + * @line_len: bytes of current line _without_ newline + * @text: pointer to beginning of current line + * @len: number of bytes prepared in r->text_buf + */ + for (;;) { + next = memchr(text, '\n', text_len); + if (next) { + line_len = next - text; + } else { + /* Drop truncated line(s). */ + if (truncated) + break; + line_len = text_len; + } + + /* + * Truncate the text if there is not enough space to add the + * prefix and a trailing newline and a terminator. + */ + if (len + prefix_len + text_len + 1 + 1 > buf_size) { + /* Drop even the current line if no space. */ + if (len + prefix_len + line_len + 1 + 1 > buf_size) + break; + + text_len = buf_size - len - prefix_len - 1 - 1; + truncated = true; + } + + memmove(text + prefix_len, text, text_len); + memcpy(text, prefix, prefix_len); + + /* + * Increment the prepared length to include the text and + * prefix that were just moved+copied. Also increment for the + * newline at the end of this line. If this is the last line, + * there is no newline, but it will be added immediately below. + */ + len += prefix_len + line_len + 1; + if (text_len == line_len) { + /* + * This is the last line. Add the trailing newline + * removed in vprintk_store(). + */ + text[prefix_len + line_len] = '\n'; + break; + } + + /* + * Advance beyond the added prefix and the related line with + * its newline. + */ + text += prefix_len + line_len + 1; + + /* + * The remaining text has only decreased by the line with its + * newline. + * + * Note that @text_len can become zero. It happens when @text + * ended with a newline (either due to truncation or the + * original string ending with "\n\n"). The loop is correctly + * repeated and (if not truncated) an empty line with a prefix + * will be prepared. + */ + text_len -= line_len + 1; + } + + /* + * If a buffer was provided, it will be terminated. Space for the + * string terminator is guaranteed to be available. The terminator is + * not counted in the return value. + */ + if (buf_size > 0) + r->text_buf[len] = 0; + + return len; +} + +static size_t get_record_print_text_size(struct printk_info *info, + unsigned int line_count, + bool syslog, bool time) +{ + char prefix[PREFIX_MAX]; + size_t prefix_len; + + prefix_len = info_print_prefix(info, syslog, time, prefix); + + /* + * Each line will be preceded with a prefix. The intermediate + * newlines are already within the text, but a final trailing + * newline will be added. + */ + return ((prefix_len * line_count) + info->text_len + 1); +} + +/* + * Beginning with @start_seq, find the first record where it and all following + * records up to (but not including) @max_seq fit into @size. + * + * @max_seq is simply an upper bound and does not need to exist. If the caller + * does not require an upper bound, -1 can be used for @max_seq. + */ +static u64 find_first_fitting_seq(u64 start_seq, u64 max_seq, size_t size, + bool syslog, bool time) +{ + struct printk_info info; + unsigned int line_count; + size_t len = 0; + u64 seq; + + /* Determine the size of the records up to @max_seq. */ + prb_for_each_info(start_seq, prb, seq, &info, &line_count) { + if (info.seq >= max_seq) + break; + len += get_record_print_text_size(&info, line_count, syslog, time); + } + + /* + * Adjust the upper bound for the next loop to avoid subtracting + * lengths that were never added. + */ + if (seq < max_seq) + max_seq = seq; + + /* + * Move first record forward until length fits into the buffer. Ignore + * newest messages that were not counted in the above cycle. Messages + * might appear and get lost in the meantime. This is a best effort + * that prevents an infinite loop that could occur with a retry. + */ + prb_for_each_info(start_seq, prb, seq, &info, &line_count) { + if (len <= size || info.seq >= max_seq) + break; + len -= get_record_print_text_size(&info, line_count, syslog, time); + } + + return seq; +} + +/* The caller is responsible for making sure @size is greater than 0. */ +static int syslog_print(char __user *buf, int size) +{ + struct printk_info info; + struct printk_record r; + char *text; + int len = 0; + u64 seq; + + text = kmalloc(CONSOLE_LOG_MAX, GFP_KERNEL); + if (!text) + return -ENOMEM; + + prb_rec_init_rd(&r, &info, text, CONSOLE_LOG_MAX); + + mutex_lock(&syslog_lock); + + /* + * Wait for the @syslog_seq record to be available. @syslog_seq may + * change while waiting. + */ + do { + seq = syslog_seq; + + mutex_unlock(&syslog_lock); + /* + * Guarantee this task is visible on the waitqueue before + * checking the wake condition. + * + * The full memory barrier within set_current_state() of + * prepare_to_wait_event() pairs with the full memory barrier + * within wq_has_sleeper(). + * + * This pairs with __wake_up_klogd:A. + */ + len = wait_event_interruptible(log_wait, + prb_read_valid(prb, seq, NULL)); /* LMM(syslog_print:A) */ + mutex_lock(&syslog_lock); + + if (len) + goto out; + } while (syslog_seq != seq); + + /* + * Copy records that fit into the buffer. The above cycle makes sure + * that the first record is always available. + */ + do { + size_t n; + size_t skip; + int err; + + if (!prb_read_valid(prb, syslog_seq, &r)) + break; + + if (r.info->seq != syslog_seq) { + /* message is gone, move to next valid one */ + syslog_seq = r.info->seq; + syslog_partial = 0; + } + + /* + * To keep reading/counting partial line consistent, + * use printk_time value as of the beginning of a line. + */ + if (!syslog_partial) + syslog_time = printk_time; + + skip = syslog_partial; + n = record_print_text(&r, true, syslog_time); + if (n - syslog_partial <= size) { + /* message fits into buffer, move forward */ + syslog_seq = r.info->seq + 1; + n -= syslog_partial; + syslog_partial = 0; + } else if (!len){ + /* partial read(), remember position */ + n = size; + syslog_partial += n; + } else + n = 0; + + if (!n) + break; + + mutex_unlock(&syslog_lock); + err = copy_to_user(buf, text + skip, n); + mutex_lock(&syslog_lock); + + if (err) { + if (!len) + len = -EFAULT; + break; + } + + len += n; + size -= n; + buf += n; + } while (size); +out: + mutex_unlock(&syslog_lock); + kfree(text); + return len; +} + +static int syslog_print_all(char __user *buf, int size, bool clear) +{ + struct printk_info info; + struct printk_record r; + char *text; + int len = 0; + u64 seq; + bool time; + + text = kmalloc(CONSOLE_LOG_MAX, GFP_KERNEL); + if (!text) + return -ENOMEM; + + time = printk_time; + /* + * Find first record that fits, including all following records, + * into the user-provided buffer for this dump. + */ + seq = find_first_fitting_seq(latched_seq_read_nolock(&clear_seq), -1, + size, true, time); + + prb_rec_init_rd(&r, &info, text, CONSOLE_LOG_MAX); + + len = 0; + prb_for_each_record(seq, prb, seq, &r) { + int textlen; + + textlen = record_print_text(&r, true, time); + + if (len + textlen > size) { + seq--; + break; + } + + if (copy_to_user(buf + len, text, textlen)) + len = -EFAULT; + else + len += textlen; + + if (len < 0) + break; + } + + if (clear) { + mutex_lock(&syslog_lock); + latched_seq_write(&clear_seq, seq); + mutex_unlock(&syslog_lock); + } + + kfree(text); + return len; +} + +static void syslog_clear(void) +{ + mutex_lock(&syslog_lock); + latched_seq_write(&clear_seq, prb_next_seq(prb)); + mutex_unlock(&syslog_lock); +} + +int do_syslog(int type, char __user *buf, int len, int source) +{ + struct printk_info info; + bool clear = false; + static int saved_console_loglevel = LOGLEVEL_DEFAULT; + int error; + + error = check_syslog_permissions(type, source); + if (error) + return error; + + switch (type) { + case SYSLOG_ACTION_CLOSE: /* Close log */ + break; + case SYSLOG_ACTION_OPEN: /* Open log */ + break; + case SYSLOG_ACTION_READ: /* Read from log */ + if (!buf || len < 0) + return -EINVAL; + if (!len) + return 0; + if (!access_ok(buf, len)) + return -EFAULT; + error = syslog_print(buf, len); + break; + /* Read/clear last kernel messages */ + case SYSLOG_ACTION_READ_CLEAR: + clear = true; + fallthrough; + /* Read last kernel messages */ + case SYSLOG_ACTION_READ_ALL: + if (!buf || len < 0) + return -EINVAL; + if (!len) + return 0; + if (!access_ok(buf, len)) + return -EFAULT; + error = syslog_print_all(buf, len, clear); + break; + /* Clear ring buffer */ + case SYSLOG_ACTION_CLEAR: + syslog_clear(); + break; + /* Disable logging to console */ + case SYSLOG_ACTION_CONSOLE_OFF: + if (saved_console_loglevel == LOGLEVEL_DEFAULT) + saved_console_loglevel = console_loglevel; + console_loglevel = minimum_console_loglevel; + break; + /* Enable logging to console */ + case SYSLOG_ACTION_CONSOLE_ON: + if (saved_console_loglevel != LOGLEVEL_DEFAULT) { + console_loglevel = saved_console_loglevel; + saved_console_loglevel = LOGLEVEL_DEFAULT; + } + break; + /* Set level of messages printed to console */ + case SYSLOG_ACTION_CONSOLE_LEVEL: + if (len < 1 || len > 8) + return -EINVAL; + if (len < minimum_console_loglevel) + len = minimum_console_loglevel; + console_loglevel = len; + /* Implicitly re-enable logging to console */ + saved_console_loglevel = LOGLEVEL_DEFAULT; + break; + /* Number of chars in the log buffer */ + case SYSLOG_ACTION_SIZE_UNREAD: + mutex_lock(&syslog_lock); + if (!prb_read_valid_info(prb, syslog_seq, &info, NULL)) { + /* No unread messages. */ + mutex_unlock(&syslog_lock); + return 0; + } + if (info.seq != syslog_seq) { + /* messages are gone, move to first one */ + syslog_seq = info.seq; + syslog_partial = 0; + } + if (source == SYSLOG_FROM_PROC) { + /* + * Short-cut for poll(/"proc/kmsg") which simply checks + * for pending data, not the size; return the count of + * records, not the length. + */ + error = prb_next_seq(prb) - syslog_seq; + } else { + bool time = syslog_partial ? syslog_time : printk_time; + unsigned int line_count; + u64 seq; + + prb_for_each_info(syslog_seq, prb, seq, &info, + &line_count) { + error += get_record_print_text_size(&info, line_count, + true, time); + time = printk_time; + } + error -= syslog_partial; + } + mutex_unlock(&syslog_lock); + break; + /* Size of the log buffer */ + case SYSLOG_ACTION_SIZE_BUFFER: + error = log_buf_len; + break; + default: + error = -EINVAL; + break; + } + + return error; +} + +SYSCALL_DEFINE3(syslog, int, type, char __user *, buf, int, len) +{ + return do_syslog(type, buf, len, SYSLOG_FROM_READER); +} + +/* + * Special console_lock variants that help to reduce the risk of soft-lockups. + * They allow to pass console_lock to another printk() call using a busy wait. + */ + +#ifdef CONFIG_LOCKDEP +static struct lockdep_map console_owner_dep_map = { + .name = "console_owner" +}; +#endif + +static DEFINE_RAW_SPINLOCK(console_owner_lock); +static struct task_struct *console_owner; +static bool console_waiter; + +/** + * console_lock_spinning_enable - mark beginning of code where another + * thread might safely busy wait + * + * This basically converts console_lock into a spinlock. This marks + * the section where the console_lock owner can not sleep, because + * there may be a waiter spinning (like a spinlock). Also it must be + * ready to hand over the lock at the end of the section. + */ +static void console_lock_spinning_enable(void) +{ + raw_spin_lock(&console_owner_lock); + console_owner = current; + raw_spin_unlock(&console_owner_lock); + + /* The waiter may spin on us after setting console_owner */ + spin_acquire(&console_owner_dep_map, 0, 0, _THIS_IP_); +} + +/** + * console_lock_spinning_disable_and_check - mark end of code where another + * thread was able to busy wait and check if there is a waiter + * + * This is called at the end of the section where spinning is allowed. + * It has two functions. First, it is a signal that it is no longer + * safe to start busy waiting for the lock. Second, it checks if + * there is a busy waiter and passes the lock rights to her. + * + * Important: Callers lose the lock if there was a busy waiter. + * They must not touch items synchronized by console_lock + * in this case. + * + * Return: 1 if the lock rights were passed, 0 otherwise. + */ +static int console_lock_spinning_disable_and_check(void) +{ + int waiter; + + raw_spin_lock(&console_owner_lock); + waiter = READ_ONCE(console_waiter); + console_owner = NULL; + raw_spin_unlock(&console_owner_lock); + + if (!waiter) { + spin_release(&console_owner_dep_map, _THIS_IP_); + return 0; + } + + /* The waiter is now free to continue */ + WRITE_ONCE(console_waiter, false); + + spin_release(&console_owner_dep_map, _THIS_IP_); + + /* + * Hand off console_lock to waiter. The waiter will perform + * the up(). After this, the waiter is the console_lock owner. + */ + mutex_release(&console_lock_dep_map, _THIS_IP_); + return 1; +} + +/** + * console_trylock_spinning - try to get console_lock by busy waiting + * + * This allows to busy wait for the console_lock when the current + * owner is running in specially marked sections. It means that + * the current owner is running and cannot reschedule until it + * is ready to lose the lock. + * + * Return: 1 if we got the lock, 0 othrewise + */ +static int console_trylock_spinning(void) +{ + struct task_struct *owner = NULL; + bool waiter; + bool spin = false; + unsigned long flags; + + if (console_trylock()) + return 1; + + /* + * It's unsafe to spin once a panic has begun. If we are the + * panic CPU, we may have already halted the owner of the + * console_sem. If we are not the panic CPU, then we should + * avoid taking console_sem, so the panic CPU has a better + * chance of cleanly acquiring it later. + */ + if (panic_in_progress()) + return 0; + + printk_safe_enter_irqsave(flags); + + raw_spin_lock(&console_owner_lock); + owner = READ_ONCE(console_owner); + waiter = READ_ONCE(console_waiter); + if (!waiter && owner && owner != current) { + WRITE_ONCE(console_waiter, true); + spin = true; + } + raw_spin_unlock(&console_owner_lock); + + /* + * If there is an active printk() writing to the + * consoles, instead of having it write our data too, + * see if we can offload that load from the active + * printer, and do some printing ourselves. + * Go into a spin only if there isn't already a waiter + * spinning, and there is an active printer, and + * that active printer isn't us (recursive printk?). + */ + if (!spin) { + printk_safe_exit_irqrestore(flags); + return 0; + } + + /* We spin waiting for the owner to release us */ + spin_acquire(&console_owner_dep_map, 0, 0, _THIS_IP_); + /* Owner will clear console_waiter on hand off */ + while (READ_ONCE(console_waiter)) + cpu_relax(); + spin_release(&console_owner_dep_map, _THIS_IP_); + + printk_safe_exit_irqrestore(flags); + /* + * The owner passed the console lock to us. + * Since we did not spin on console lock, annotate + * this as a trylock. Otherwise lockdep will + * complain. + */ + mutex_acquire(&console_lock_dep_map, 0, 1, _THIS_IP_); + + return 1; +} + +/* + * Call the specified console driver, asking it to write out the specified + * text and length. If @dropped_text is non-NULL and any records have been + * dropped, a dropped message will be written out first. + */ +static void call_console_driver(struct console *con, const char *text, size_t len, + char *dropped_text) +{ + size_t dropped_len; + + if (con->dropped && dropped_text) { + dropped_len = snprintf(dropped_text, DROPPED_TEXT_MAX, + "** %lu printk messages dropped **\n", + con->dropped); + con->dropped = 0; + con->write(con, dropped_text, dropped_len); + } + + con->write(con, text, len); +} + +/* + * Recursion is tracked separately on each CPU. If NMIs are supported, an + * additional NMI context per CPU is also separately tracked. Until per-CPU + * is available, a separate "early tracking" is performed. + */ +static DEFINE_PER_CPU(u8, printk_count); +static u8 printk_count_early; +#ifdef CONFIG_HAVE_NMI +static DEFINE_PER_CPU(u8, printk_count_nmi); +static u8 printk_count_nmi_early; +#endif + +/* + * Recursion is limited to keep the output sane. printk() should not require + * more than 1 level of recursion (allowing, for example, printk() to trigger + * a WARN), but a higher value is used in case some printk-internal errors + * exist, such as the ringbuffer validation checks failing. + */ +#define PRINTK_MAX_RECURSION 3 + +/* + * Return a pointer to the dedicated counter for the CPU+context of the + * caller. + */ +static u8 *__printk_recursion_counter(void) +{ +#ifdef CONFIG_HAVE_NMI + if (in_nmi()) { + if (printk_percpu_data_ready()) + return this_cpu_ptr(&printk_count_nmi); + return &printk_count_nmi_early; + } +#endif + if (printk_percpu_data_ready()) + return this_cpu_ptr(&printk_count); + return &printk_count_early; +} + +/* + * Enter recursion tracking. Interrupts are disabled to simplify tracking. + * The caller must check the boolean return value to see if the recursion is + * allowed. On failure, interrupts are not disabled. + * + * @recursion_ptr must be a variable of type (u8 *) and is the same variable + * that is passed to printk_exit_irqrestore(). + */ +#define printk_enter_irqsave(recursion_ptr, flags) \ +({ \ + bool success = true; \ + \ + typecheck(u8 *, recursion_ptr); \ + local_irq_save(flags); \ + (recursion_ptr) = __printk_recursion_counter(); \ + if (*(recursion_ptr) > PRINTK_MAX_RECURSION) { \ + local_irq_restore(flags); \ + success = false; \ + } else { \ + (*(recursion_ptr))++; \ + } \ + success; \ +}) + +/* Exit recursion tracking, restoring interrupts. */ +#define printk_exit_irqrestore(recursion_ptr, flags) \ + do { \ + typecheck(u8 *, recursion_ptr); \ + (*(recursion_ptr))--; \ + local_irq_restore(flags); \ + } while (0) + +int printk_delay_msec __read_mostly; + +static inline void printk_delay(int level) +{ + boot_delay_msec(level); + + if (unlikely(printk_delay_msec)) { + int m = printk_delay_msec; + + while (m--) { + mdelay(1); + touch_nmi_watchdog(); + } + } +} + +static inline u32 printk_caller_id(void) +{ + return in_task() ? task_pid_nr(current) : + 0x80000000 + smp_processor_id(); +} + +/** + * printk_parse_prefix - Parse level and control flags. + * + * @text: The terminated text message. + * @level: A pointer to the current level value, will be updated. + * @flags: A pointer to the current printk_info flags, will be updated. + * + * @level may be NULL if the caller is not interested in the parsed value. + * Otherwise the variable pointed to by @level must be set to + * LOGLEVEL_DEFAULT in order to be updated with the parsed value. + * + * @flags may be NULL if the caller is not interested in the parsed value. + * Otherwise the variable pointed to by @flags will be OR'd with the parsed + * value. + * + * Return: The length of the parsed level and control flags. + */ +u16 printk_parse_prefix(const char *text, int *level, + enum printk_info_flags *flags) +{ + u16 prefix_len = 0; + int kern_level; + + while (*text) { + kern_level = printk_get_level(text); + if (!kern_level) + break; + + switch (kern_level) { + case '0' ... '7': + if (level && *level == LOGLEVEL_DEFAULT) + *level = kern_level - '0'; + break; + case 'c': /* KERN_CONT */ + if (flags) + *flags |= LOG_CONT; + } + + prefix_len += 2; + text += 2; + } + + return prefix_len; +} + +__printf(5, 0) +static u16 printk_sprint(char *text, u16 size, int facility, + enum printk_info_flags *flags, const char *fmt, + va_list args) +{ + u16 text_len; + + text_len = vscnprintf(text, size, fmt, args); + + /* Mark and strip a trailing newline. */ + if (text_len && text[text_len - 1] == '\n') { + text_len--; + *flags |= LOG_NEWLINE; + } + + /* Strip log level and control flags. */ + if (facility == 0) { + u16 prefix_len; + + prefix_len = printk_parse_prefix(text, NULL, NULL); + if (prefix_len) { + text_len -= prefix_len; + memmove(text, text + prefix_len, text_len); + } + } + + trace_console_rcuidle(text, text_len); + + return text_len; +} + +__printf(4, 0) +int vprintk_store(int facility, int level, + const struct dev_printk_info *dev_info, + const char *fmt, va_list args) +{ + struct prb_reserved_entry e; + enum printk_info_flags flags = 0; + struct printk_record r; + unsigned long irqflags; + u16 trunc_msg_len = 0; + char prefix_buf[8]; + u8 *recursion_ptr; + u16 reserve_size; + va_list args2; + u32 caller_id; + u16 text_len; + int ret = 0; + u64 ts_nsec; + + if (!printk_enter_irqsave(recursion_ptr, irqflags)) + return 0; + + /* + * Since the duration of printk() can vary depending on the message + * and state of the ringbuffer, grab the timestamp now so that it is + * close to the call of printk(). This provides a more deterministic + * timestamp with respect to the caller. + */ + ts_nsec = local_clock(); + + caller_id = printk_caller_id(); + + /* + * The sprintf needs to come first since the syslog prefix might be + * passed in as a parameter. An extra byte must be reserved so that + * later the vscnprintf() into the reserved buffer has room for the + * terminating '\0', which is not counted by vsnprintf(). + */ + va_copy(args2, args); + reserve_size = vsnprintf(&prefix_buf[0], sizeof(prefix_buf), fmt, args2) + 1; + va_end(args2); + + if (reserve_size > LOG_LINE_MAX) + reserve_size = LOG_LINE_MAX; + + /* Extract log level or control flags. */ + if (facility == 0) + printk_parse_prefix(&prefix_buf[0], &level, &flags); + + if (level == LOGLEVEL_DEFAULT) + level = default_message_loglevel; + + if (dev_info) + flags |= LOG_NEWLINE; + + if (flags & LOG_CONT) { + prb_rec_init_wr(&r, reserve_size); + if (prb_reserve_in_last(&e, prb, &r, caller_id, LOG_LINE_MAX)) { + text_len = printk_sprint(&r.text_buf[r.info->text_len], reserve_size, + facility, &flags, fmt, args); + r.info->text_len += text_len; + + if (flags & LOG_NEWLINE) { + r.info->flags |= LOG_NEWLINE; + prb_final_commit(&e); + } else { + prb_commit(&e); + } + + ret = text_len; + goto out; + } + } + + /* + * Explicitly initialize the record before every prb_reserve() call. + * prb_reserve_in_last() and prb_reserve() purposely invalidate the + * structure when they fail. + */ + prb_rec_init_wr(&r, reserve_size); + if (!prb_reserve(&e, prb, &r)) { + /* truncate the message if it is too long for empty buffer */ + truncate_msg(&reserve_size, &trunc_msg_len); + + prb_rec_init_wr(&r, reserve_size + trunc_msg_len); + if (!prb_reserve(&e, prb, &r)) + goto out; + } + + /* fill message */ + text_len = printk_sprint(&r.text_buf[0], reserve_size, facility, &flags, fmt, args); + if (trunc_msg_len) + memcpy(&r.text_buf[text_len], trunc_msg, trunc_msg_len); + r.info->text_len = text_len + trunc_msg_len; + r.info->facility = facility; + r.info->level = level & 7; + r.info->flags = flags & 0x1f; + r.info->ts_nsec = ts_nsec; + r.info->caller_id = caller_id; + if (dev_info) + memcpy(&r.info->dev_info, dev_info, sizeof(r.info->dev_info)); + + /* A message without a trailing newline can be continued. */ + if (!(flags & LOG_NEWLINE)) + prb_commit(&e); + else + prb_final_commit(&e); + + ret = text_len + trunc_msg_len; +out: + printk_exit_irqrestore(recursion_ptr, irqflags); + return ret; +} + +asmlinkage int vprintk_emit(int facility, int level, + const struct dev_printk_info *dev_info, + const char *fmt, va_list args) +{ + int printed_len; + bool in_sched = false; + + /* Suppress unimportant messages after panic happens */ + if (unlikely(suppress_printk)) + return 0; + + if (unlikely(suppress_panic_printk) && + atomic_read(&panic_cpu) != raw_smp_processor_id()) + return 0; + + if (level == LOGLEVEL_SCHED) { + level = LOGLEVEL_DEFAULT; + in_sched = true; + } + + printk_delay(level); + + printed_len = vprintk_store(facility, level, dev_info, fmt, args); + + /* If called from the scheduler, we can not call up(). */ + if (!in_sched) { + /* + * The caller may be holding system-critical or + * timing-sensitive locks. Disable preemption during + * printing of all remaining records to all consoles so that + * this context can return as soon as possible. Hopefully + * another printk() caller will take over the printing. + */ + preempt_disable(); + /* + * Try to acquire and then immediately release the console + * semaphore. The release will print out buffers. With the + * spinning variant, this context tries to take over the + * printing from another printing context. + */ + if (console_trylock_spinning()) + console_unlock(); + preempt_enable(); + } + + if (in_sched) + defer_console_output(); + else + wake_up_klogd(); + + return printed_len; +} +EXPORT_SYMBOL(vprintk_emit); + +int vprintk_default(const char *fmt, va_list args) +{ + return vprintk_emit(0, LOGLEVEL_DEFAULT, NULL, fmt, args); +} +EXPORT_SYMBOL_GPL(vprintk_default); + +asmlinkage __visible int _printk(const char *fmt, ...) +{ + va_list args; + int r; + + va_start(args, fmt); + r = vprintk(fmt, args); + va_end(args); + + return r; +} +EXPORT_SYMBOL(_printk); + +static bool pr_flush(int timeout_ms, bool reset_on_progress); +static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progress); + +#else /* CONFIG_PRINTK */ + +#define CONSOLE_LOG_MAX 0 +#define DROPPED_TEXT_MAX 0 +#define printk_time false + +#define prb_read_valid(rb, seq, r) false +#define prb_first_valid_seq(rb) 0 +#define prb_next_seq(rb) 0 + +static u64 syslog_seq; + +static size_t record_print_text(const struct printk_record *r, + bool syslog, bool time) +{ + return 0; +} +static ssize_t info_print_ext_header(char *buf, size_t size, + struct printk_info *info) +{ + return 0; +} +static ssize_t msg_print_ext_body(char *buf, size_t size, + char *text, size_t text_len, + struct dev_printk_info *dev_info) { return 0; } +static void console_lock_spinning_enable(void) { } +static int console_lock_spinning_disable_and_check(void) { return 0; } +static void call_console_driver(struct console *con, const char *text, size_t len, + char *dropped_text) +{ +} +static bool suppress_message_printing(int level) { return false; } +static bool pr_flush(int timeout_ms, bool reset_on_progress) { return true; } +static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progress) { return true; } + +#endif /* CONFIG_PRINTK */ + +#ifdef CONFIG_EARLY_PRINTK +struct console *early_console; + +asmlinkage __visible void early_printk(const char *fmt, ...) +{ + va_list ap; + char buf[512]; + int n; + + if (!early_console) + return; + + va_start(ap, fmt); + n = vscnprintf(buf, sizeof(buf), fmt, ap); + va_end(ap); + + early_console->write(early_console, buf, n); +} +#endif + +static void set_user_specified(struct console_cmdline *c, bool user_specified) +{ + if (!user_specified) + return; + + /* + * @c console was defined by the user on the command line. + * Do not clear when added twice also by SPCR or the device tree. + */ + c->user_specified = true; + /* At least one console defined by the user on the command line. */ + console_set_on_cmdline = 1; +} + +static int __add_preferred_console(char *name, int idx, char *options, + char *brl_options, bool user_specified) +{ + struct console_cmdline *c; + int i; + + /* + * See if this tty is not yet registered, and + * if we have a slot free. + */ + for (i = 0, c = console_cmdline; + i < MAX_CMDLINECONSOLES && c->name[0]; + i++, c++) { + if (strcmp(c->name, name) == 0 && c->index == idx) { + if (!brl_options) + preferred_console = i; + set_user_specified(c, user_specified); + return 0; + } + } + if (i == MAX_CMDLINECONSOLES) + return -E2BIG; + if (!brl_options) + preferred_console = i; + strlcpy(c->name, name, sizeof(c->name)); + c->options = options; + set_user_specified(c, user_specified); + braille_set_options(c, brl_options); + + c->index = idx; + return 0; +} + +static int __init console_msg_format_setup(char *str) +{ + if (!strcmp(str, "syslog")) + console_msg_format = MSG_FORMAT_SYSLOG; + if (!strcmp(str, "default")) + console_msg_format = MSG_FORMAT_DEFAULT; + return 1; +} +__setup("console_msg_format=", console_msg_format_setup); + +/* + * Set up a console. Called via do_early_param() in init/main.c + * for each "console=" parameter in the boot command line. + */ +static int __init console_setup(char *str) +{ + char buf[sizeof(console_cmdline[0].name) + 4]; /* 4 for "ttyS" */ + char *s, *options, *brl_options = NULL; + int idx; + + /* + * console="" or console=null have been suggested as a way to + * disable console output. Use ttynull that has been created + * for exactly this purpose. + */ + if (str[0] == 0 || strcmp(str, "null") == 0) { + __add_preferred_console("ttynull", 0, NULL, NULL, true); + return 1; + } + + if (_braille_console_setup(&str, &brl_options)) + return 1; + + /* + * Decode str into name, index, options. + */ + if (str[0] >= '0' && str[0] <= '9') { + strcpy(buf, "ttyS"); + strncpy(buf + 4, str, sizeof(buf) - 5); + } else { + strncpy(buf, str, sizeof(buf) - 1); + } + buf[sizeof(buf) - 1] = 0; + options = strchr(str, ','); + if (options) + *(options++) = 0; +#ifdef __sparc__ + if (!strcmp(str, "ttya")) + strcpy(buf, "ttyS0"); + if (!strcmp(str, "ttyb")) + strcpy(buf, "ttyS1"); +#endif + for (s = buf; *s; s++) + if (isdigit(*s) || *s == ',') + break; + idx = simple_strtoul(s, NULL, 10); + *s = 0; + + __add_preferred_console(buf, idx, options, brl_options, true); + return 1; +} +__setup("console=", console_setup); + +/** + * add_preferred_console - add a device to the list of preferred consoles. + * @name: device name + * @idx: device index + * @options: options for this console + * + * The last preferred console added will be used for kernel messages + * and stdin/out/err for init. Normally this is used by console_setup + * above to handle user-supplied console arguments; however it can also + * be used by arch-specific code either to override the user or more + * commonly to provide a default console (ie from PROM variables) when + * the user has not supplied one. + */ +int add_preferred_console(char *name, int idx, char *options) +{ + return __add_preferred_console(name, idx, options, NULL, false); +} + +bool console_suspend_enabled = true; +EXPORT_SYMBOL(console_suspend_enabled); + +static int __init console_suspend_disable(char *str) +{ + console_suspend_enabled = false; + return 1; +} +__setup("no_console_suspend", console_suspend_disable); +module_param_named(console_suspend, console_suspend_enabled, + bool, S_IRUGO | S_IWUSR); +MODULE_PARM_DESC(console_suspend, "suspend console during suspend" + " and hibernate operations"); + +static bool printk_console_no_auto_verbose; + +void console_verbose(void) +{ + if (console_loglevel && !printk_console_no_auto_verbose) + console_loglevel = CONSOLE_LOGLEVEL_MOTORMOUTH; +} +EXPORT_SYMBOL_GPL(console_verbose); + +module_param_named(console_no_auto_verbose, printk_console_no_auto_verbose, bool, 0644); +MODULE_PARM_DESC(console_no_auto_verbose, "Disable console loglevel raise to highest on oops/panic/etc"); + +/** + * suspend_console - suspend the console subsystem + * + * This disables printk() while we go into suspend states + */ +void suspend_console(void) +{ + if (!console_suspend_enabled) + return; + pr_info("Suspending console(s) (use no_console_suspend to debug)\n"); + pr_flush(1000, true); + console_lock(); + console_suspended = 1; + up_console_sem(); +} + +void resume_console(void) +{ + if (!console_suspend_enabled) + return; + down_console_sem(); + console_suspended = 0; + console_unlock(); + pr_flush(1000, true); +} + +/** + * console_cpu_notify - print deferred console messages after CPU hotplug + * @cpu: unused + * + * If printk() is called from a CPU that is not online yet, the messages + * will be printed on the console only if there are CON_ANYTIME consoles. + * This function is called when a new CPU comes online (or fails to come + * up) or goes offline. + */ +static int console_cpu_notify(unsigned int cpu) +{ + if (!cpuhp_tasks_frozen) { + /* If trylock fails, someone else is doing the printing */ + if (console_trylock()) + console_unlock(); + } + return 0; +} + +/* + * Return true when this CPU should unlock console_sem without pushing all + * messages to the console. This reduces the chance that the console is + * locked when the panic CPU tries to use it. + */ +static bool abandon_console_lock_in_panic(void) +{ + if (!panic_in_progress()) + return false; + + /* + * We can use raw_smp_processor_id() here because it is impossible for + * the task to be migrated to the panic_cpu, or away from it. If + * panic_cpu has already been set, and we're not currently executing on + * that CPU, then we never will be. + */ + return atomic_read(&panic_cpu) != raw_smp_processor_id(); +} + +/** + * console_lock - lock the console system for exclusive use. + * + * Acquires a lock which guarantees that the caller has + * exclusive access to the console system and the console_drivers list. + * + * Can sleep, returns nothing. + */ +void console_lock(void) +{ + might_sleep(); + + /* On panic, the console_lock must be left to the panic cpu. */ + while (abandon_console_lock_in_panic()) + msleep(1000); + + down_console_sem(); + if (console_suspended) + return; + console_locked = 1; + console_may_schedule = 1; +} +EXPORT_SYMBOL(console_lock); + +/** + * console_trylock - try to lock the console system for exclusive use. + * + * Try to acquire a lock which guarantees that the caller has exclusive + * access to the console system and the console_drivers list. + * + * returns 1 on success, and 0 on failure to acquire the lock. + */ +int console_trylock(void) +{ + /* On panic, the console_lock must be left to the panic cpu. */ + if (abandon_console_lock_in_panic()) + return 0; + if (down_trylock_console_sem()) + return 0; + if (console_suspended) { + up_console_sem(); + return 0; + } + console_locked = 1; + console_may_schedule = 0; + return 1; +} +EXPORT_SYMBOL(console_trylock); + +int is_console_locked(void) +{ + return console_locked; +} +EXPORT_SYMBOL(is_console_locked); + +/* + * Check if the given console is currently capable and allowed to print + * records. + * + * Requires the console_lock. + */ +static inline bool console_is_usable(struct console *con) +{ + if (!(con->flags & CON_ENABLED)) + return false; + + if (!con->write) + return false; + + /* + * Console drivers may assume that per-cpu resources have been + * allocated. So unless they're explicitly marked as being able to + * cope (CON_ANYTIME) don't call them until this CPU is officially up. + */ + if (!cpu_online(raw_smp_processor_id()) && + !(con->flags & CON_ANYTIME)) + return false; + + return true; +} + +static void __console_unlock(void) +{ + console_locked = 0; + up_console_sem(); +} + +/* + * Print one record for the given console. The record printed is whatever + * record is the next available record for the given console. + * + * @text is a buffer of size CONSOLE_LOG_MAX. + * + * If extended messages should be printed, @ext_text is a buffer of size + * CONSOLE_EXT_LOG_MAX. Otherwise @ext_text must be NULL. + * + * If dropped messages should be printed, @dropped_text is a buffer of size + * DROPPED_TEXT_MAX. Otherwise @dropped_text must be NULL. + * + * @handover will be set to true if a printk waiter has taken over the + * console_lock, in which case the caller is no longer holding the + * console_lock. Otherwise it is set to false. + * + * Returns false if the given console has no next record to print, otherwise + * true. + * + * Requires the console_lock. + */ +static bool console_emit_next_record(struct console *con, char *text, char *ext_text, + char *dropped_text, bool *handover) +{ + static int panic_console_dropped; + struct printk_info info; + struct printk_record r; + unsigned long flags; + char *write_text; + size_t len; + + prb_rec_init_rd(&r, &info, text, CONSOLE_LOG_MAX); + + *handover = false; + + if (!prb_read_valid(prb, con->seq, &r)) + return false; + + if (con->seq != r.info->seq) { + con->dropped += r.info->seq - con->seq; + con->seq = r.info->seq; + if (panic_in_progress() && panic_console_dropped++ > 10) { + suppress_panic_printk = 1; + pr_warn_once("Too many dropped messages. Suppress messages on non-panic CPUs to prevent livelock.\n"); + } + } + + /* Skip record that has level above the console loglevel. */ + if (suppress_message_printing(r.info->level)) { + con->seq++; + goto skip; + } + + if (ext_text) { + write_text = ext_text; + len = info_print_ext_header(ext_text, CONSOLE_EXT_LOG_MAX, r.info); + len += msg_print_ext_body(ext_text + len, CONSOLE_EXT_LOG_MAX - len, + &r.text_buf[0], r.info->text_len, &r.info->dev_info); + } else { + write_text = text; + len = record_print_text(&r, console_msg_format & MSG_FORMAT_SYSLOG, printk_time); + } + + /* + * While actively printing out messages, if another printk() + * were to occur on another CPU, it may wait for this one to + * finish. This task can not be preempted if there is a + * waiter waiting to take over. + * + * Interrupts are disabled because the hand over to a waiter + * must not be interrupted until the hand over is completed + * (@console_waiter is cleared). + */ + printk_safe_enter_irqsave(flags); + console_lock_spinning_enable(); + + stop_critical_timings(); /* don't trace print latency */ + call_console_driver(con, write_text, len, dropped_text); + start_critical_timings(); + + con->seq++; + + *handover = console_lock_spinning_disable_and_check(); + printk_safe_exit_irqrestore(flags); +skip: + return true; +} + +/* + * Print out all remaining records to all consoles. + * + * @do_cond_resched is set by the caller. It can be true only in schedulable + * context. + * + * @next_seq is set to the sequence number after the last available record. + * The value is valid only when this function returns true. It means that all + * usable consoles are completely flushed. + * + * @handover will be set to true if a printk waiter has taken over the + * console_lock, in which case the caller is no longer holding the + * console_lock. Otherwise it is set to false. + * + * Returns true when there was at least one usable console and all messages + * were flushed to all usable consoles. A returned false informs the caller + * that everything was not flushed (either there were no usable consoles or + * another context has taken over printing or it is a panic situation and this + * is not the panic CPU). Regardless the reason, the caller should assume it + * is not useful to immediately try again. + * + * Requires the console_lock. + */ +static bool console_flush_all(bool do_cond_resched, u64 *next_seq, bool *handover) +{ + static char dropped_text[DROPPED_TEXT_MAX]; + static char ext_text[CONSOLE_EXT_LOG_MAX]; + static char text[CONSOLE_LOG_MAX]; + bool any_usable = false; + struct console *con; + bool any_progress; + + *next_seq = 0; + *handover = false; + + do { + any_progress = false; + + for_each_console(con) { + bool progress; + + if (!console_is_usable(con)) + continue; + any_usable = true; + + if (con->flags & CON_EXTENDED) { + /* Extended consoles do not print "dropped messages". */ + progress = console_emit_next_record(con, &text[0], + &ext_text[0], NULL, + handover); + } else { + progress = console_emit_next_record(con, &text[0], + NULL, &dropped_text[0], + handover); + } + if (*handover) + return false; + + /* Track the next of the highest seq flushed. */ + if (con->seq > *next_seq) + *next_seq = con->seq; + + if (!progress) + continue; + any_progress = true; + + /* Allow panic_cpu to take over the consoles safely. */ + if (abandon_console_lock_in_panic()) + return false; + + if (do_cond_resched) + cond_resched(); + } + } while (any_progress); + + return any_usable; +} + +/** + * console_unlock - unlock the console system + * + * Releases the console_lock which the caller holds on the console system + * and the console driver list. + * + * While the console_lock was held, console output may have been buffered + * by printk(). If this is the case, console_unlock(); emits + * the output prior to releasing the lock. + * + * console_unlock(); may be called from any context. + */ +void console_unlock(void) +{ + bool do_cond_resched; + bool handover; + bool flushed; + u64 next_seq; + + if (console_suspended) { + up_console_sem(); + return; + } + + /* + * Console drivers are called with interrupts disabled, so + * @console_may_schedule should be cleared before; however, we may + * end up dumping a lot of lines, for example, if called from + * console registration path, and should invoke cond_resched() + * between lines if allowable. Not doing so can cause a very long + * scheduling stall on a slow console leading to RCU stall and + * softlockup warnings which exacerbate the issue with more + * messages practically incapacitating the system. Therefore, create + * a local to use for the printing loop. + */ + do_cond_resched = console_may_schedule; + + do { + console_may_schedule = 0; + + flushed = console_flush_all(do_cond_resched, &next_seq, &handover); + if (!handover) + __console_unlock(); + + /* + * Abort if there was a failure to flush all messages to all + * usable consoles. Either it is not possible to flush (in + * which case it would be an infinite loop of retrying) or + * another context has taken over printing. + */ + if (!flushed) + break; + + /* + * Some context may have added new records after + * console_flush_all() but before unlocking the console. + * Re-check if there is a new record to flush. If the trylock + * fails, another context is already handling the printing. + */ + } while (prb_read_valid(prb, next_seq, NULL) && console_trylock()); +} +EXPORT_SYMBOL(console_unlock); + +/** + * console_conditional_schedule - yield the CPU if required + * + * If the console code is currently allowed to sleep, and + * if this CPU should yield the CPU to another task, do + * so here. + * + * Must be called within console_lock();. + */ +void __sched console_conditional_schedule(void) +{ + if (console_may_schedule) + cond_resched(); +} +EXPORT_SYMBOL(console_conditional_schedule); + +void console_unblank(void) +{ + struct console *c; + + /* + * console_unblank can no longer be called in interrupt context unless + * oops_in_progress is set to 1.. + */ + if (oops_in_progress) { + if (down_trylock_console_sem() != 0) + return; + } else + console_lock(); + + console_locked = 1; + console_may_schedule = 0; + for_each_console(c) + if ((c->flags & CON_ENABLED) && c->unblank) + c->unblank(); + console_unlock(); + + if (!oops_in_progress) + pr_flush(1000, true); +} + +/** + * console_flush_on_panic - flush console content on panic + * @mode: flush all messages in buffer or just the pending ones + * + * Immediately output all pending messages no matter what. + */ +void console_flush_on_panic(enum con_flush_mode mode) +{ + /* + * If someone else is holding the console lock, trylock will fail + * and may_schedule may be set. Ignore and proceed to unlock so + * that messages are flushed out. As this can be called from any + * context and we don't want to get preempted while flushing, + * ensure may_schedule is cleared. + */ + console_trylock(); + console_may_schedule = 0; + + if (mode == CONSOLE_REPLAY_ALL) { + struct console *c; + u64 seq; + + seq = prb_first_valid_seq(prb); + for_each_console(c) + c->seq = seq; + } + console_unlock(); +} + +/* + * Return the console tty driver structure and its associated index + */ +struct tty_driver *console_device(int *index) +{ + struct console *c; + struct tty_driver *driver = NULL; + + console_lock(); + for_each_console(c) { + if (!c->device) + continue; + driver = c->device(c, index); + if (driver) + break; + } + console_unlock(); + return driver; +} + +/* + * Prevent further output on the passed console device so that (for example) + * serial drivers can disable console output before suspending a port, and can + * re-enable output afterwards. + */ +void console_stop(struct console *console) +{ + __pr_flush(console, 1000, true); + console_lock(); + console->flags &= ~CON_ENABLED; + console_unlock(); +} +EXPORT_SYMBOL(console_stop); + +void console_start(struct console *console) +{ + console_lock(); + console->flags |= CON_ENABLED; + console_unlock(); + __pr_flush(console, 1000, true); +} +EXPORT_SYMBOL(console_start); + +static int __read_mostly keep_bootcon; + +static int __init keep_bootcon_setup(char *str) +{ + keep_bootcon = 1; + pr_info("debug: skip boot console de-registration.\n"); + + return 0; +} + +early_param("keep_bootcon", keep_bootcon_setup); + +/* + * This is called by register_console() to try to match + * the newly registered console with any of the ones selected + * by either the command line or add_preferred_console() and + * setup/enable it. + * + * Care need to be taken with consoles that are statically + * enabled such as netconsole + */ +static int try_enable_preferred_console(struct console *newcon, + bool user_specified) +{ + struct console_cmdline *c; + int i, err; + + for (i = 0, c = console_cmdline; + i < MAX_CMDLINECONSOLES && c->name[0]; + i++, c++) { + if (c->user_specified != user_specified) + continue; + if (!newcon->match || + newcon->match(newcon, c->name, c->index, c->options) != 0) { + /* default matching */ + BUILD_BUG_ON(sizeof(c->name) != sizeof(newcon->name)); + if (strcmp(c->name, newcon->name) != 0) + continue; + if (newcon->index >= 0 && + newcon->index != c->index) + continue; + if (newcon->index < 0) + newcon->index = c->index; + + if (_braille_register_console(newcon, c)) + return 0; + + if (newcon->setup && + (err = newcon->setup(newcon, c->options)) != 0) + return err; + } + newcon->flags |= CON_ENABLED; + if (i == preferred_console) + newcon->flags |= CON_CONSDEV; + return 0; + } + + /* + * Some consoles, such as pstore and netconsole, can be enabled even + * without matching. Accept the pre-enabled consoles only when match() + * and setup() had a chance to be called. + */ + if (newcon->flags & CON_ENABLED && c->user_specified == user_specified) + return 0; + + return -ENOENT; +} + +/* Try to enable the console unconditionally */ +static void try_enable_default_console(struct console *newcon) +{ + if (newcon->index < 0) + newcon->index = 0; + + if (newcon->setup && newcon->setup(newcon, NULL) != 0) + return; + + newcon->flags |= CON_ENABLED; + + if (newcon->device) + newcon->flags |= CON_CONSDEV; +} + +#define con_printk(lvl, con, fmt, ...) \ + printk(lvl pr_fmt("%sconsole [%s%d] " fmt), \ + (con->flags & CON_BOOT) ? "boot" : "", \ + con->name, con->index, ##__VA_ARGS__) + +/* + * The console driver calls this routine during kernel initialization + * to register the console printing procedure with printk() and to + * print any messages that were printed by the kernel before the + * console driver was initialized. + * + * This can happen pretty early during the boot process (because of + * early_printk) - sometimes before setup_arch() completes - be careful + * of what kernel features are used - they may not be initialised yet. + * + * There are two types of consoles - bootconsoles (early_printk) and + * "real" consoles (everything which is not a bootconsole) which are + * handled differently. + * - Any number of bootconsoles can be registered at any time. + * - As soon as a "real" console is registered, all bootconsoles + * will be unregistered automatically. + * - Once a "real" console is registered, any attempt to register a + * bootconsoles will be rejected + */ +void register_console(struct console *newcon) +{ + struct console *con; + bool bootcon_enabled = false; + bool realcon_enabled = false; + int err; + + for_each_console(con) { + if (WARN(con == newcon, "console '%s%d' already registered\n", + con->name, con->index)) + return; + } + + for_each_console(con) { + if (con->flags & CON_BOOT) + bootcon_enabled = true; + else + realcon_enabled = true; + } + + /* Do not register boot consoles when there already is a real one. */ + if (newcon->flags & CON_BOOT && realcon_enabled) { + pr_info("Too late to register bootconsole %s%d\n", + newcon->name, newcon->index); + return; + } + + /* + * See if we want to enable this console driver by default. + * + * Nope when a console is preferred by the command line, device + * tree, or SPCR. + * + * The first real console with tty binding (driver) wins. More + * consoles might get enabled before the right one is found. + * + * Note that a console with tty binding will have CON_CONSDEV + * flag set and will be first in the list. + */ + if (preferred_console < 0) { + if (!console_drivers || !console_drivers->device || + console_drivers->flags & CON_BOOT) { + try_enable_default_console(newcon); + } + } + + /* See if this console matches one we selected on the command line */ + err = try_enable_preferred_console(newcon, true); + + /* If not, try to match against the platform default(s) */ + if (err == -ENOENT) + err = try_enable_preferred_console(newcon, false); + + /* printk() messages are not printed to the Braille console. */ + if (err || newcon->flags & CON_BRL) + return; + + /* + * If we have a bootconsole, and are switching to a real console, + * don't print everything out again, since when the boot console, and + * the real console are the same physical device, it's annoying to + * see the beginning boot messages twice + */ + if (bootcon_enabled && + ((newcon->flags & (CON_CONSDEV | CON_BOOT)) == CON_CONSDEV)) { + newcon->flags &= ~CON_PRINTBUFFER; + } + + /* + * Put this console in the list - keep the + * preferred driver at the head of the list. + */ + console_lock(); + if ((newcon->flags & CON_CONSDEV) || console_drivers == NULL) { + newcon->next = console_drivers; + console_drivers = newcon; + if (newcon->next) + newcon->next->flags &= ~CON_CONSDEV; + /* Ensure this flag is always set for the head of the list */ + newcon->flags |= CON_CONSDEV; + } else { + newcon->next = console_drivers->next; + console_drivers->next = newcon; + } + + newcon->dropped = 0; + if (newcon->flags & CON_PRINTBUFFER) { + /* Get a consistent copy of @syslog_seq. */ + mutex_lock(&syslog_lock); + newcon->seq = syslog_seq; + mutex_unlock(&syslog_lock); + } else { + /* Begin with next message. */ + newcon->seq = prb_next_seq(prb); + } + console_unlock(); + console_sysfs_notify(); + + /* + * By unregistering the bootconsoles after we enable the real console + * we get the "console xxx enabled" message on all the consoles - + * boot consoles, real consoles, etc - this is to ensure that end + * users know there might be something in the kernel's log buffer that + * went to the bootconsole (that they do not see on the real console) + */ + con_printk(KERN_INFO, newcon, "enabled\n"); + if (bootcon_enabled && + ((newcon->flags & (CON_CONSDEV | CON_BOOT)) == CON_CONSDEV) && + !keep_bootcon) { + for_each_console(con) + if (con->flags & CON_BOOT) + unregister_console(con); + } +} +EXPORT_SYMBOL(register_console); + +int unregister_console(struct console *console) +{ + struct console *con; + int res; + + con_printk(KERN_INFO, console, "disabled\n"); + + res = _braille_unregister_console(console); + if (res < 0) + return res; + if (res > 0) + return 0; + + res = -ENODEV; + console_lock(); + if (console_drivers == console) { + console_drivers=console->next; + res = 0; + } else { + for_each_console(con) { + if (con->next == console) { + con->next = console->next; + res = 0; + break; + } + } + } + + if (res) + goto out_disable_unlock; + + /* + * If this isn't the last console and it has CON_CONSDEV set, we + * need to set it on the next preferred console. + */ + if (console_drivers != NULL && console->flags & CON_CONSDEV) + console_drivers->flags |= CON_CONSDEV; + + console->flags &= ~CON_ENABLED; + console_unlock(); + console_sysfs_notify(); + + if (console->exit) + res = console->exit(console); + + return res; + +out_disable_unlock: + console->flags &= ~CON_ENABLED; + console_unlock(); + + return res; +} +EXPORT_SYMBOL(unregister_console); + +/* + * Initialize the console device. This is called *early*, so + * we can't necessarily depend on lots of kernel help here. + * Just do some early initializations, and do the complex setup + * later. + */ +void __init console_init(void) +{ + int ret; + initcall_t call; + initcall_entry_t *ce; + + /* Setup the default TTY line discipline. */ + n_tty_init(); + + /* + * set up the console device so that later boot sequences can + * inform about problems etc.. + */ + ce = __con_initcall_start; + trace_initcall_level("console"); + while (ce < __con_initcall_end) { + call = initcall_from_entry(ce); + trace_initcall_start(call); + ret = call(); + trace_initcall_finish(call, ret); + ce++; + } +} + +/* + * Some boot consoles access data that is in the init section and which will + * be discarded after the initcalls have been run. To make sure that no code + * will access this data, unregister the boot consoles in a late initcall. + * + * If for some reason, such as deferred probe or the driver being a loadable + * module, the real console hasn't registered yet at this point, there will + * be a brief interval in which no messages are logged to the console, which + * makes it difficult to diagnose problems that occur during this time. + * + * To mitigate this problem somewhat, only unregister consoles whose memory + * intersects with the init section. Note that all other boot consoles will + * get unregistered when the real preferred console is registered. + */ +static int __init printk_late_init(void) +{ + struct console *con; + int ret; + + for_each_console(con) { + if (!(con->flags & CON_BOOT)) + continue; + + /* Check addresses that might be used for enabled consoles. */ + if (init_section_intersects(con, sizeof(*con)) || + init_section_contains(con->write, 0) || + init_section_contains(con->read, 0) || + init_section_contains(con->device, 0) || + init_section_contains(con->unblank, 0) || + init_section_contains(con->data, 0)) { + /* + * Please, consider moving the reported consoles out + * of the init section. + */ + pr_warn("bootconsole [%s%d] uses init memory and must be disabled even before the real one is ready\n", + con->name, con->index); + unregister_console(con); + } + } + ret = cpuhp_setup_state_nocalls(CPUHP_PRINTK_DEAD, "printk:dead", NULL, + console_cpu_notify); + WARN_ON(ret < 0); + ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "printk:online", + console_cpu_notify, NULL); + WARN_ON(ret < 0); + printk_sysctl_init(); + return 0; +} +late_initcall(printk_late_init); + +#if defined CONFIG_PRINTK +/* If @con is specified, only wait for that console. Otherwise wait for all. */ +static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progress) +{ + int remaining = timeout_ms; + struct console *c; + u64 last_diff = 0; + u64 printk_seq; + u64 diff; + u64 seq; + + might_sleep(); + + seq = prb_next_seq(prb); + + for (;;) { + diff = 0; + + console_lock(); + + for_each_console(c) { + if (con && con != c) + continue; + if (!console_is_usable(c)) + continue; + printk_seq = c->seq; + if (printk_seq < seq) + diff += seq - printk_seq; + } + + /* + * If consoles are suspended, it cannot be expected that they + * make forward progress, so timeout immediately. @diff is + * still used to return a valid flush status. + */ + if (console_suspended) + remaining = 0; + else if (diff != last_diff && reset_on_progress) + remaining = timeout_ms; + + console_unlock(); + + if (diff == 0 || remaining == 0) + break; + + if (remaining < 0) { + /* no timeout limit */ + msleep(100); + } else if (remaining < 100) { + msleep(remaining); + remaining = 0; + } else { + msleep(100); + remaining -= 100; + } + + last_diff = diff; + } + + return (diff == 0); +} + +/** + * pr_flush() - Wait for printing threads to catch up. + * + * @timeout_ms: The maximum time (in ms) to wait. + * @reset_on_progress: Reset the timeout if forward progress is seen. + * + * A value of 0 for @timeout_ms means no waiting will occur. A value of -1 + * represents infinite waiting. + * + * If @reset_on_progress is true, the timeout will be reset whenever any + * printer has been seen to make some forward progress. + * + * Context: Process context. May sleep while acquiring console lock. + * Return: true if all enabled printers are caught up. + */ +static bool pr_flush(int timeout_ms, bool reset_on_progress) +{ + return __pr_flush(NULL, timeout_ms, reset_on_progress); +} + +/* + * Delayed printk version, for scheduler-internal messages: + */ +#define PRINTK_PENDING_WAKEUP 0x01 +#define PRINTK_PENDING_OUTPUT 0x02 + +static DEFINE_PER_CPU(int, printk_pending); + +static void wake_up_klogd_work_func(struct irq_work *irq_work) +{ + int pending = this_cpu_xchg(printk_pending, 0); + + if (pending & PRINTK_PENDING_OUTPUT) { + /* If trylock fails, someone else is doing the printing */ + if (console_trylock()) + console_unlock(); + } + + if (pending & PRINTK_PENDING_WAKEUP) + wake_up_interruptible(&log_wait); +} + +static DEFINE_PER_CPU(struct irq_work, wake_up_klogd_work) = + IRQ_WORK_INIT_LAZY(wake_up_klogd_work_func); + +static void __wake_up_klogd(int val) +{ + if (!printk_percpu_data_ready()) + return; + + preempt_disable(); + /* + * Guarantee any new records can be seen by tasks preparing to wait + * before this context checks if the wait queue is empty. + * + * The full memory barrier within wq_has_sleeper() pairs with the full + * memory barrier within set_current_state() of + * prepare_to_wait_event(), which is called after ___wait_event() adds + * the waiter but before it has checked the wait condition. + * + * This pairs with devkmsg_read:A and syslog_print:A. + */ + if (wq_has_sleeper(&log_wait) || /* LMM(__wake_up_klogd:A) */ + (val & PRINTK_PENDING_OUTPUT)) { + this_cpu_or(printk_pending, val); + irq_work_queue(this_cpu_ptr(&wake_up_klogd_work)); + } + preempt_enable(); +} + +/** + * wake_up_klogd - Wake kernel logging daemon + * + * Use this function when new records have been added to the ringbuffer + * and the console printing of those records has already occurred or is + * known to be handled by some other context. This function will only + * wake the logging daemon. + * + * Context: Any context. + */ +void wake_up_klogd(void) +{ + __wake_up_klogd(PRINTK_PENDING_WAKEUP); +} + +/** + * defer_console_output - Wake kernel logging daemon and trigger + * console printing in a deferred context + * + * Use this function when new records have been added to the ringbuffer, + * this context is responsible for console printing those records, but + * the current context is not allowed to perform the console printing. + * Trigger an irq_work context to perform the console printing. This + * function also wakes the logging daemon. + * + * Context: Any context. + */ +void defer_console_output(void) +{ + /* + * New messages may have been added directly to the ringbuffer + * using vprintk_store(), so wake any waiters as well. + */ + __wake_up_klogd(PRINTK_PENDING_WAKEUP | PRINTK_PENDING_OUTPUT); +} + +void printk_trigger_flush(void) +{ + defer_console_output(); +} + +int vprintk_deferred(const char *fmt, va_list args) +{ + return vprintk_emit(0, LOGLEVEL_SCHED, NULL, fmt, args); +} + +int _printk_deferred(const char *fmt, ...) +{ + va_list args; + int r; + + va_start(args, fmt); + r = vprintk_deferred(fmt, args); + va_end(args); + + return r; +} + +/* + * printk rate limiting, lifted from the networking subsystem. + * + * This enforces a rate limit: not more than 10 kernel messages + * every 5s to make a denial-of-service attack impossible. + */ +DEFINE_RATELIMIT_STATE(printk_ratelimit_state, 5 * HZ, 10); + +int __printk_ratelimit(const char *func) +{ + return ___ratelimit(&printk_ratelimit_state, func); +} +EXPORT_SYMBOL(__printk_ratelimit); + +/** + * printk_timed_ratelimit - caller-controlled printk ratelimiting + * @caller_jiffies: pointer to caller's state + * @interval_msecs: minimum interval between prints + * + * printk_timed_ratelimit() returns true if more than @interval_msecs + * milliseconds have elapsed since the last time printk_timed_ratelimit() + * returned true. + */ +bool printk_timed_ratelimit(unsigned long *caller_jiffies, + unsigned int interval_msecs) +{ + unsigned long elapsed = jiffies - *caller_jiffies; + + if (*caller_jiffies && elapsed <= msecs_to_jiffies(interval_msecs)) + return false; + + *caller_jiffies = jiffies; + return true; +} +EXPORT_SYMBOL(printk_timed_ratelimit); + +static DEFINE_SPINLOCK(dump_list_lock); +static LIST_HEAD(dump_list); + +/** + * kmsg_dump_register - register a kernel log dumper. + * @dumper: pointer to the kmsg_dumper structure + * + * Adds a kernel log dumper to the system. The dump callback in the + * structure will be called when the kernel oopses or panics and must be + * set. Returns zero on success and %-EINVAL or %-EBUSY otherwise. + */ +int kmsg_dump_register(struct kmsg_dumper *dumper) +{ + unsigned long flags; + int err = -EBUSY; + + /* The dump callback needs to be set */ + if (!dumper->dump) + return -EINVAL; + + spin_lock_irqsave(&dump_list_lock, flags); + /* Don't allow registering multiple times */ + if (!dumper->registered) { + dumper->registered = 1; + list_add_tail_rcu(&dumper->list, &dump_list); + err = 0; + } + spin_unlock_irqrestore(&dump_list_lock, flags); + + return err; +} +EXPORT_SYMBOL_GPL(kmsg_dump_register); + +/** + * kmsg_dump_unregister - unregister a kmsg dumper. + * @dumper: pointer to the kmsg_dumper structure + * + * Removes a dump device from the system. Returns zero on success and + * %-EINVAL otherwise. + */ +int kmsg_dump_unregister(struct kmsg_dumper *dumper) +{ + unsigned long flags; + int err = -EINVAL; + + spin_lock_irqsave(&dump_list_lock, flags); + if (dumper->registered) { + dumper->registered = 0; + list_del_rcu(&dumper->list); + err = 0; + } + spin_unlock_irqrestore(&dump_list_lock, flags); + synchronize_rcu(); + + return err; +} +EXPORT_SYMBOL_GPL(kmsg_dump_unregister); + +static bool always_kmsg_dump; +module_param_named(always_kmsg_dump, always_kmsg_dump, bool, S_IRUGO | S_IWUSR); + +const char *kmsg_dump_reason_str(enum kmsg_dump_reason reason) +{ + switch (reason) { + case KMSG_DUMP_PANIC: + return "Panic"; + case KMSG_DUMP_OOPS: + return "Oops"; + case KMSG_DUMP_EMERG: + return "Emergency"; + case KMSG_DUMP_SHUTDOWN: + return "Shutdown"; + default: + return "Unknown"; + } +} +EXPORT_SYMBOL_GPL(kmsg_dump_reason_str); + +/** + * kmsg_dump - dump kernel log to kernel message dumpers. + * @reason: the reason (oops, panic etc) for dumping + * + * Call each of the registered dumper's dump() callback, which can + * retrieve the kmsg records with kmsg_dump_get_line() or + * kmsg_dump_get_buffer(). + */ +void kmsg_dump(enum kmsg_dump_reason reason) +{ + struct kmsg_dumper *dumper; + + rcu_read_lock(); + list_for_each_entry_rcu(dumper, &dump_list, list) { + enum kmsg_dump_reason max_reason = dumper->max_reason; + + /* + * If client has not provided a specific max_reason, default + * to KMSG_DUMP_OOPS, unless always_kmsg_dump was set. + */ + if (max_reason == KMSG_DUMP_UNDEF) { + max_reason = always_kmsg_dump ? KMSG_DUMP_MAX : + KMSG_DUMP_OOPS; + } + if (reason > max_reason) + continue; + + /* invoke dumper which will iterate over records */ + dumper->dump(dumper, reason); + } + rcu_read_unlock(); +} + +/** + * kmsg_dump_get_line - retrieve one kmsg log line + * @iter: kmsg dump iterator + * @syslog: include the "<4>" prefixes + * @line: buffer to copy the line to + * @size: maximum size of the buffer + * @len: length of line placed into buffer + * + * Start at the beginning of the kmsg buffer, with the oldest kmsg + * record, and copy one record into the provided buffer. + * + * Consecutive calls will return the next available record moving + * towards the end of the buffer with the youngest messages. + * + * A return value of FALSE indicates that there are no more records to + * read. + */ +bool kmsg_dump_get_line(struct kmsg_dump_iter *iter, bool syslog, + char *line, size_t size, size_t *len) +{ + u64 min_seq = latched_seq_read_nolock(&clear_seq); + struct printk_info info; + unsigned int line_count; + struct printk_record r; + size_t l = 0; + bool ret = false; + + if (iter->cur_seq < min_seq) + iter->cur_seq = min_seq; + + prb_rec_init_rd(&r, &info, line, size); + + /* Read text or count text lines? */ + if (line) { + if (!prb_read_valid(prb, iter->cur_seq, &r)) + goto out; + l = record_print_text(&r, syslog, printk_time); + } else { + if (!prb_read_valid_info(prb, iter->cur_seq, + &info, &line_count)) { + goto out; + } + l = get_record_print_text_size(&info, line_count, syslog, + printk_time); + + } + + iter->cur_seq = r.info->seq + 1; + ret = true; +out: + if (len) + *len = l; + return ret; +} +EXPORT_SYMBOL_GPL(kmsg_dump_get_line); + +/** + * kmsg_dump_get_buffer - copy kmsg log lines + * @iter: kmsg dump iterator + * @syslog: include the "<4>" prefixes + * @buf: buffer to copy the line to + * @size: maximum size of the buffer + * @len_out: length of line placed into buffer + * + * Start at the end of the kmsg buffer and fill the provided buffer + * with as many of the *youngest* kmsg records that fit into it. + * If the buffer is large enough, all available kmsg records will be + * copied with a single call. + * + * Consecutive calls will fill the buffer with the next block of + * available older records, not including the earlier retrieved ones. + * + * A return value of FALSE indicates that there are no more records to + * read. + */ +bool kmsg_dump_get_buffer(struct kmsg_dump_iter *iter, bool syslog, + char *buf, size_t size, size_t *len_out) +{ + u64 min_seq = latched_seq_read_nolock(&clear_seq); + struct printk_info info; + struct printk_record r; + u64 seq; + u64 next_seq; + size_t len = 0; + bool ret = false; + bool time = printk_time; + + if (!buf || !size) + goto out; + + if (iter->cur_seq < min_seq) + iter->cur_seq = min_seq; + + if (prb_read_valid_info(prb, iter->cur_seq, &info, NULL)) { + if (info.seq != iter->cur_seq) { + /* messages are gone, move to first available one */ + iter->cur_seq = info.seq; + } + } + + /* last entry */ + if (iter->cur_seq >= iter->next_seq) + goto out; + + /* + * Find first record that fits, including all following records, + * into the user-provided buffer for this dump. Pass in size-1 + * because this function (by way of record_print_text()) will + * not write more than size-1 bytes of text into @buf. + */ + seq = find_first_fitting_seq(iter->cur_seq, iter->next_seq, + size - 1, syslog, time); + + /* + * Next kmsg_dump_get_buffer() invocation will dump block of + * older records stored right before this one. + */ + next_seq = seq; + + prb_rec_init_rd(&r, &info, buf, size); + + len = 0; + prb_for_each_record(seq, prb, seq, &r) { + if (r.info->seq >= iter->next_seq) + break; + + len += record_print_text(&r, syslog, time); + + /* Adjust record to store to remaining buffer space. */ + prb_rec_init_rd(&r, &info, buf + len, size - len); + } + + iter->next_seq = next_seq; + ret = true; +out: + if (len_out) + *len_out = len; + return ret; +} +EXPORT_SYMBOL_GPL(kmsg_dump_get_buffer); + +/** + * kmsg_dump_rewind - reset the iterator + * @iter: kmsg dump iterator + * + * Reset the dumper's iterator so that kmsg_dump_get_line() and + * kmsg_dump_get_buffer() can be called again and used multiple + * times within the same dumper.dump() callback. + */ +void kmsg_dump_rewind(struct kmsg_dump_iter *iter) +{ + iter->cur_seq = latched_seq_read_nolock(&clear_seq); + iter->next_seq = prb_next_seq(prb); +} +EXPORT_SYMBOL_GPL(kmsg_dump_rewind); + +#endif + +#ifdef CONFIG_SMP +static atomic_t printk_cpu_sync_owner = ATOMIC_INIT(-1); +static atomic_t printk_cpu_sync_nested = ATOMIC_INIT(0); + +/** + * __printk_cpu_sync_wait() - Busy wait until the printk cpu-reentrant + * spinning lock is not owned by any CPU. + * + * Context: Any context. + */ +void __printk_cpu_sync_wait(void) +{ + do { + cpu_relax(); + } while (atomic_read(&printk_cpu_sync_owner) != -1); +} +EXPORT_SYMBOL(__printk_cpu_sync_wait); + +/** + * __printk_cpu_sync_try_get() - Try to acquire the printk cpu-reentrant + * spinning lock. + * + * If no processor has the lock, the calling processor takes the lock and + * becomes the owner. If the calling processor is already the owner of the + * lock, this function succeeds immediately. + * + * Context: Any context. Expects interrupts to be disabled. + * Return: 1 on success, otherwise 0. + */ +int __printk_cpu_sync_try_get(void) +{ + int cpu; + int old; + + cpu = smp_processor_id(); + + /* + * Guarantee loads and stores from this CPU when it is the lock owner + * are _not_ visible to the previous lock owner. This pairs with + * __printk_cpu_sync_put:B. + * + * Memory barrier involvement: + * + * If __printk_cpu_sync_try_get:A reads from __printk_cpu_sync_put:B, + * then __printk_cpu_sync_put:A can never read from + * __printk_cpu_sync_try_get:B. + * + * Relies on: + * + * RELEASE from __printk_cpu_sync_put:A to __printk_cpu_sync_put:B + * of the previous CPU + * matching + * ACQUIRE from __printk_cpu_sync_try_get:A to + * __printk_cpu_sync_try_get:B of this CPU + */ + old = atomic_cmpxchg_acquire(&printk_cpu_sync_owner, -1, + cpu); /* LMM(__printk_cpu_sync_try_get:A) */ + if (old == -1) { + /* + * This CPU is now the owner and begins loading/storing + * data: LMM(__printk_cpu_sync_try_get:B) + */ + return 1; + + } else if (old == cpu) { + /* This CPU is already the owner. */ + atomic_inc(&printk_cpu_sync_nested); + return 1; + } + + return 0; +} +EXPORT_SYMBOL(__printk_cpu_sync_try_get); + +/** + * __printk_cpu_sync_put() - Release the printk cpu-reentrant spinning lock. + * + * The calling processor must be the owner of the lock. + * + * Context: Any context. Expects interrupts to be disabled. + */ +void __printk_cpu_sync_put(void) +{ + if (atomic_read(&printk_cpu_sync_nested)) { + atomic_dec(&printk_cpu_sync_nested); + return; + } + + /* + * This CPU is finished loading/storing data: + * LMM(__printk_cpu_sync_put:A) + */ + + /* + * Guarantee loads and stores from this CPU when it was the + * lock owner are visible to the next lock owner. This pairs + * with __printk_cpu_sync_try_get:A. + * + * Memory barrier involvement: + * + * If __printk_cpu_sync_try_get:A reads from __printk_cpu_sync_put:B, + * then __printk_cpu_sync_try_get:B reads from __printk_cpu_sync_put:A. + * + * Relies on: + * + * RELEASE from __printk_cpu_sync_put:A to __printk_cpu_sync_put:B + * of this CPU + * matching + * ACQUIRE from __printk_cpu_sync_try_get:A to + * __printk_cpu_sync_try_get:B of the next CPU + */ + atomic_set_release(&printk_cpu_sync_owner, + -1); /* LMM(__printk_cpu_sync_put:B) */ +} +EXPORT_SYMBOL(__printk_cpu_sync_put); +#endif /* CONFIG_SMP */ diff --git a/kernel/printk/printk_ringbuffer.c b/kernel/printk/printk_ringbuffer.c new file mode 100644 index 000000000..0bbcd1344 --- /dev/null +++ b/kernel/printk/printk_ringbuffer.c @@ -0,0 +1,2124 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/kernel.h> +#include <linux/irqflags.h> +#include <linux/string.h> +#include <linux/errno.h> +#include <linux/bug.h> +#include "printk_ringbuffer.h" + +/** + * DOC: printk_ringbuffer overview + * + * Data Structure + * -------------- + * The printk_ringbuffer is made up of 3 internal ringbuffers: + * + * desc_ring + * A ring of descriptors and their meta data (such as sequence number, + * timestamp, loglevel, etc.) as well as internal state information about + * the record and logical positions specifying where in the other + * ringbuffer the text strings are located. + * + * text_data_ring + * A ring of data blocks. A data block consists of an unsigned long + * integer (ID) that maps to a desc_ring index followed by the text + * string of the record. + * + * The internal state information of a descriptor is the key element to allow + * readers and writers to locklessly synchronize access to the data. + * + * Implementation + * -------------- + * + * Descriptor Ring + * ~~~~~~~~~~~~~~~ + * The descriptor ring is an array of descriptors. A descriptor contains + * essential meta data to track the data of a printk record using + * blk_lpos structs pointing to associated text data blocks (see + * "Data Rings" below). Each descriptor is assigned an ID that maps + * directly to index values of the descriptor array and has a state. The ID + * and the state are bitwise combined into a single descriptor field named + * @state_var, allowing ID and state to be synchronously and atomically + * updated. + * + * Descriptors have four states: + * + * reserved + * A writer is modifying the record. + * + * committed + * The record and all its data are written. A writer can reopen the + * descriptor (transitioning it back to reserved), but in the committed + * state the data is consistent. + * + * finalized + * The record and all its data are complete and available for reading. A + * writer cannot reopen the descriptor. + * + * reusable + * The record exists, but its text and/or meta data may no longer be + * available. + * + * Querying the @state_var of a record requires providing the ID of the + * descriptor to query. This can yield a possible fifth (pseudo) state: + * + * miss + * The descriptor being queried has an unexpected ID. + * + * The descriptor ring has a @tail_id that contains the ID of the oldest + * descriptor and @head_id that contains the ID of the newest descriptor. + * + * When a new descriptor should be created (and the ring is full), the tail + * descriptor is invalidated by first transitioning to the reusable state and + * then invalidating all tail data blocks up to and including the data blocks + * associated with the tail descriptor (for the text ring). Then + * @tail_id is advanced, followed by advancing @head_id. And finally the + * @state_var of the new descriptor is initialized to the new ID and reserved + * state. + * + * The @tail_id can only be advanced if the new @tail_id would be in the + * committed or reusable queried state. This makes it possible that a valid + * sequence number of the tail is always available. + * + * Descriptor Finalization + * ~~~~~~~~~~~~~~~~~~~~~~~ + * When a writer calls the commit function prb_commit(), record data is + * fully stored and is consistent within the ringbuffer. However, a writer can + * reopen that record, claiming exclusive access (as with prb_reserve()), and + * modify that record. When finished, the writer must again commit the record. + * + * In order for a record to be made available to readers (and also become + * recyclable for writers), it must be finalized. A finalized record cannot be + * reopened and can never become "unfinalized". Record finalization can occur + * in three different scenarios: + * + * 1) A writer can simultaneously commit and finalize its record by calling + * prb_final_commit() instead of prb_commit(). + * + * 2) When a new record is reserved and the previous record has been + * committed via prb_commit(), that previous record is automatically + * finalized. + * + * 3) When a record is committed via prb_commit() and a newer record + * already exists, the record being committed is automatically finalized. + * + * Data Ring + * ~~~~~~~~~ + * The text data ring is a byte array composed of data blocks. Data blocks are + * referenced by blk_lpos structs that point to the logical position of the + * beginning of a data block and the beginning of the next adjacent data + * block. Logical positions are mapped directly to index values of the byte + * array ringbuffer. + * + * Each data block consists of an ID followed by the writer data. The ID is + * the identifier of a descriptor that is associated with the data block. A + * given data block is considered valid if all of the following conditions + * are met: + * + * 1) The descriptor associated with the data block is in the committed + * or finalized queried state. + * + * 2) The blk_lpos struct within the descriptor associated with the data + * block references back to the same data block. + * + * 3) The data block is within the head/tail logical position range. + * + * If the writer data of a data block would extend beyond the end of the + * byte array, only the ID of the data block is stored at the logical + * position and the full data block (ID and writer data) is stored at the + * beginning of the byte array. The referencing blk_lpos will point to the + * ID before the wrap and the next data block will be at the logical + * position adjacent the full data block after the wrap. + * + * Data rings have a @tail_lpos that points to the beginning of the oldest + * data block and a @head_lpos that points to the logical position of the + * next (not yet existing) data block. + * + * When a new data block should be created (and the ring is full), tail data + * blocks will first be invalidated by putting their associated descriptors + * into the reusable state and then pushing the @tail_lpos forward beyond + * them. Then the @head_lpos is pushed forward and is associated with a new + * descriptor. If a data block is not valid, the @tail_lpos cannot be + * advanced beyond it. + * + * Info Array + * ~~~~~~~~~~ + * The general meta data of printk records are stored in printk_info structs, + * stored in an array with the same number of elements as the descriptor ring. + * Each info corresponds to the descriptor of the same index in the + * descriptor ring. Info validity is confirmed by evaluating the corresponding + * descriptor before and after loading the info. + * + * Usage + * ----- + * Here are some simple examples demonstrating writers and readers. For the + * examples a global ringbuffer (test_rb) is available (which is not the + * actual ringbuffer used by printk):: + * + * DEFINE_PRINTKRB(test_rb, 15, 5); + * + * This ringbuffer allows up to 32768 records (2 ^ 15) and has a size of + * 1 MiB (2 ^ (15 + 5)) for text data. + * + * Sample writer code:: + * + * const char *textstr = "message text"; + * struct prb_reserved_entry e; + * struct printk_record r; + * + * // specify how much to allocate + * prb_rec_init_wr(&r, strlen(textstr) + 1); + * + * if (prb_reserve(&e, &test_rb, &r)) { + * snprintf(r.text_buf, r.text_buf_size, "%s", textstr); + * + * r.info->text_len = strlen(textstr); + * r.info->ts_nsec = local_clock(); + * r.info->caller_id = printk_caller_id(); + * + * // commit and finalize the record + * prb_final_commit(&e); + * } + * + * Note that additional writer functions are available to extend a record + * after it has been committed but not yet finalized. This can be done as + * long as no new records have been reserved and the caller is the same. + * + * Sample writer code (record extending):: + * + * // alternate rest of previous example + * + * r.info->text_len = strlen(textstr); + * r.info->ts_nsec = local_clock(); + * r.info->caller_id = printk_caller_id(); + * + * // commit the record (but do not finalize yet) + * prb_commit(&e); + * } + * + * ... + * + * // specify additional 5 bytes text space to extend + * prb_rec_init_wr(&r, 5); + * + * // try to extend, but only if it does not exceed 32 bytes + * if (prb_reserve_in_last(&e, &test_rb, &r, printk_caller_id()), 32) { + * snprintf(&r.text_buf[r.info->text_len], + * r.text_buf_size - r.info->text_len, "hello"); + * + * r.info->text_len += 5; + * + * // commit and finalize the record + * prb_final_commit(&e); + * } + * + * Sample reader code:: + * + * struct printk_info info; + * struct printk_record r; + * char text_buf[32]; + * u64 seq; + * + * prb_rec_init_rd(&r, &info, &text_buf[0], sizeof(text_buf)); + * + * prb_for_each_record(0, &test_rb, &seq, &r) { + * if (info.seq != seq) + * pr_warn("lost %llu records\n", info.seq - seq); + * + * if (info.text_len > r.text_buf_size) { + * pr_warn("record %llu text truncated\n", info.seq); + * text_buf[r.text_buf_size - 1] = 0; + * } + * + * pr_info("%llu: %llu: %s\n", info.seq, info.ts_nsec, + * &text_buf[0]); + * } + * + * Note that additional less convenient reader functions are available to + * allow complex record access. + * + * ABA Issues + * ~~~~~~~~~~ + * To help avoid ABA issues, descriptors are referenced by IDs (array index + * values combined with tagged bits counting array wraps) and data blocks are + * referenced by logical positions (array index values combined with tagged + * bits counting array wraps). However, on 32-bit systems the number of + * tagged bits is relatively small such that an ABA incident is (at least + * theoretically) possible. For example, if 4 million maximally sized (1KiB) + * printk messages were to occur in NMI context on a 32-bit system, the + * interrupted context would not be able to recognize that the 32-bit integer + * completely wrapped and thus represents a different data block than the one + * the interrupted context expects. + * + * To help combat this possibility, additional state checking is performed + * (such as using cmpxchg() even though set() would suffice). These extra + * checks are commented as such and will hopefully catch any ABA issue that + * a 32-bit system might experience. + * + * Memory Barriers + * ~~~~~~~~~~~~~~~ + * Multiple memory barriers are used. To simplify proving correctness and + * generating litmus tests, lines of code related to memory barriers + * (loads, stores, and the associated memory barriers) are labeled:: + * + * LMM(function:letter) + * + * Comments reference the labels using only the "function:letter" part. + * + * The memory barrier pairs and their ordering are: + * + * desc_reserve:D / desc_reserve:B + * push descriptor tail (id), then push descriptor head (id) + * + * desc_reserve:D / data_push_tail:B + * push data tail (lpos), then set new descriptor reserved (state) + * + * desc_reserve:D / desc_push_tail:C + * push descriptor tail (id), then set new descriptor reserved (state) + * + * desc_reserve:D / prb_first_seq:C + * push descriptor tail (id), then set new descriptor reserved (state) + * + * desc_reserve:F / desc_read:D + * set new descriptor id and reserved (state), then allow writer changes + * + * data_alloc:A (or data_realloc:A) / desc_read:D + * set old descriptor reusable (state), then modify new data block area + * + * data_alloc:A (or data_realloc:A) / data_push_tail:B + * push data tail (lpos), then modify new data block area + * + * _prb_commit:B / desc_read:B + * store writer changes, then set new descriptor committed (state) + * + * desc_reopen_last:A / _prb_commit:B + * set descriptor reserved (state), then read descriptor data + * + * _prb_commit:B / desc_reserve:D + * set new descriptor committed (state), then check descriptor head (id) + * + * data_push_tail:D / data_push_tail:A + * set descriptor reusable (state), then push data tail (lpos) + * + * desc_push_tail:B / desc_reserve:D + * set descriptor reusable (state), then push descriptor tail (id) + */ + +#define DATA_SIZE(data_ring) _DATA_SIZE((data_ring)->size_bits) +#define DATA_SIZE_MASK(data_ring) (DATA_SIZE(data_ring) - 1) + +#define DESCS_COUNT(desc_ring) _DESCS_COUNT((desc_ring)->count_bits) +#define DESCS_COUNT_MASK(desc_ring) (DESCS_COUNT(desc_ring) - 1) + +/* Determine the data array index from a logical position. */ +#define DATA_INDEX(data_ring, lpos) ((lpos) & DATA_SIZE_MASK(data_ring)) + +/* Determine the desc array index from an ID or sequence number. */ +#define DESC_INDEX(desc_ring, n) ((n) & DESCS_COUNT_MASK(desc_ring)) + +/* Determine how many times the data array has wrapped. */ +#define DATA_WRAPS(data_ring, lpos) ((lpos) >> (data_ring)->size_bits) + +/* Determine if a logical position refers to a data-less block. */ +#define LPOS_DATALESS(lpos) ((lpos) & 1UL) +#define BLK_DATALESS(blk) (LPOS_DATALESS((blk)->begin) && \ + LPOS_DATALESS((blk)->next)) + +/* Get the logical position at index 0 of the current wrap. */ +#define DATA_THIS_WRAP_START_LPOS(data_ring, lpos) \ +((lpos) & ~DATA_SIZE_MASK(data_ring)) + +/* Get the ID for the same index of the previous wrap as the given ID. */ +#define DESC_ID_PREV_WRAP(desc_ring, id) \ +DESC_ID((id) - DESCS_COUNT(desc_ring)) + +/* + * A data block: mapped directly to the beginning of the data block area + * specified as a logical position within the data ring. + * + * @id: the ID of the associated descriptor + * @data: the writer data + * + * Note that the size of a data block is only known by its associated + * descriptor. + */ +struct prb_data_block { + unsigned long id; + char data[]; +}; + +/* + * Return the descriptor associated with @n. @n can be either a + * descriptor ID or a sequence number. + */ +static struct prb_desc *to_desc(struct prb_desc_ring *desc_ring, u64 n) +{ + return &desc_ring->descs[DESC_INDEX(desc_ring, n)]; +} + +/* + * Return the printk_info associated with @n. @n can be either a + * descriptor ID or a sequence number. + */ +static struct printk_info *to_info(struct prb_desc_ring *desc_ring, u64 n) +{ + return &desc_ring->infos[DESC_INDEX(desc_ring, n)]; +} + +static struct prb_data_block *to_block(struct prb_data_ring *data_ring, + unsigned long begin_lpos) +{ + return (void *)&data_ring->data[DATA_INDEX(data_ring, begin_lpos)]; +} + +/* + * Increase the data size to account for data block meta data plus any + * padding so that the adjacent data block is aligned on the ID size. + */ +static unsigned int to_blk_size(unsigned int size) +{ + struct prb_data_block *db = NULL; + + size += sizeof(*db); + size = ALIGN(size, sizeof(db->id)); + return size; +} + +/* + * Sanity checker for reserve size. The ringbuffer code assumes that a data + * block does not exceed the maximum possible size that could fit within the + * ringbuffer. This function provides that basic size check so that the + * assumption is safe. + */ +static bool data_check_size(struct prb_data_ring *data_ring, unsigned int size) +{ + struct prb_data_block *db = NULL; + + if (size == 0) + return true; + + /* + * Ensure the alignment padded size could possibly fit in the data + * array. The largest possible data block must still leave room for + * at least the ID of the next block. + */ + size = to_blk_size(size); + if (size > DATA_SIZE(data_ring) - sizeof(db->id)) + return false; + + return true; +} + +/* Query the state of a descriptor. */ +static enum desc_state get_desc_state(unsigned long id, + unsigned long state_val) +{ + if (id != DESC_ID(state_val)) + return desc_miss; + + return DESC_STATE(state_val); +} + +/* + * Get a copy of a specified descriptor and return its queried state. If the + * descriptor is in an inconsistent state (miss or reserved), the caller can + * only expect the descriptor's @state_var field to be valid. + * + * The sequence number and caller_id can be optionally retrieved. Like all + * non-state_var data, they are only valid if the descriptor is in a + * consistent state. + */ +static enum desc_state desc_read(struct prb_desc_ring *desc_ring, + unsigned long id, struct prb_desc *desc_out, + u64 *seq_out, u32 *caller_id_out) +{ + struct printk_info *info = to_info(desc_ring, id); + struct prb_desc *desc = to_desc(desc_ring, id); + atomic_long_t *state_var = &desc->state_var; + enum desc_state d_state; + unsigned long state_val; + + /* Check the descriptor state. */ + state_val = atomic_long_read(state_var); /* LMM(desc_read:A) */ + d_state = get_desc_state(id, state_val); + if (d_state == desc_miss || d_state == desc_reserved) { + /* + * The descriptor is in an inconsistent state. Set at least + * @state_var so that the caller can see the details of + * the inconsistent state. + */ + goto out; + } + + /* + * Guarantee the state is loaded before copying the descriptor + * content. This avoids copying obsolete descriptor content that might + * not apply to the descriptor state. This pairs with _prb_commit:B. + * + * Memory barrier involvement: + * + * If desc_read:A reads from _prb_commit:B, then desc_read:C reads + * from _prb_commit:A. + * + * Relies on: + * + * WMB from _prb_commit:A to _prb_commit:B + * matching + * RMB from desc_read:A to desc_read:C + */ + smp_rmb(); /* LMM(desc_read:B) */ + + /* + * Copy the descriptor data. The data is not valid until the + * state has been re-checked. A memcpy() for all of @desc + * cannot be used because of the atomic_t @state_var field. + */ + if (desc_out) { + memcpy(&desc_out->text_blk_lpos, &desc->text_blk_lpos, + sizeof(desc_out->text_blk_lpos)); /* LMM(desc_read:C) */ + } + if (seq_out) + *seq_out = info->seq; /* also part of desc_read:C */ + if (caller_id_out) + *caller_id_out = info->caller_id; /* also part of desc_read:C */ + + /* + * 1. Guarantee the descriptor content is loaded before re-checking + * the state. This avoids reading an obsolete descriptor state + * that may not apply to the copied content. This pairs with + * desc_reserve:F. + * + * Memory barrier involvement: + * + * If desc_read:C reads from desc_reserve:G, then desc_read:E + * reads from desc_reserve:F. + * + * Relies on: + * + * WMB from desc_reserve:F to desc_reserve:G + * matching + * RMB from desc_read:C to desc_read:E + * + * 2. Guarantee the record data is loaded before re-checking the + * state. This avoids reading an obsolete descriptor state that may + * not apply to the copied data. This pairs with data_alloc:A and + * data_realloc:A. + * + * Memory barrier involvement: + * + * If copy_data:A reads from data_alloc:B, then desc_read:E + * reads from desc_make_reusable:A. + * + * Relies on: + * + * MB from desc_make_reusable:A to data_alloc:B + * matching + * RMB from desc_read:C to desc_read:E + * + * Note: desc_make_reusable:A and data_alloc:B can be different + * CPUs. However, the data_alloc:B CPU (which performs the + * full memory barrier) must have previously seen + * desc_make_reusable:A. + */ + smp_rmb(); /* LMM(desc_read:D) */ + + /* + * The data has been copied. Return the current descriptor state, + * which may have changed since the load above. + */ + state_val = atomic_long_read(state_var); /* LMM(desc_read:E) */ + d_state = get_desc_state(id, state_val); +out: + if (desc_out) + atomic_long_set(&desc_out->state_var, state_val); + return d_state; +} + +/* + * Take a specified descriptor out of the finalized state by attempting + * the transition from finalized to reusable. Either this context or some + * other context will have been successful. + */ +static void desc_make_reusable(struct prb_desc_ring *desc_ring, + unsigned long id) +{ + unsigned long val_finalized = DESC_SV(id, desc_finalized); + unsigned long val_reusable = DESC_SV(id, desc_reusable); + struct prb_desc *desc = to_desc(desc_ring, id); + atomic_long_t *state_var = &desc->state_var; + + atomic_long_cmpxchg_relaxed(state_var, val_finalized, + val_reusable); /* LMM(desc_make_reusable:A) */ +} + +/* + * Given the text data ring, put the associated descriptor of each + * data block from @lpos_begin until @lpos_end into the reusable state. + * + * If there is any problem making the associated descriptor reusable, either + * the descriptor has not yet been finalized or another writer context has + * already pushed the tail lpos past the problematic data block. Regardless, + * on error the caller can re-load the tail lpos to determine the situation. + */ +static bool data_make_reusable(struct printk_ringbuffer *rb, + unsigned long lpos_begin, + unsigned long lpos_end, + unsigned long *lpos_out) +{ + + struct prb_data_ring *data_ring = &rb->text_data_ring; + struct prb_desc_ring *desc_ring = &rb->desc_ring; + struct prb_data_block *blk; + enum desc_state d_state; + struct prb_desc desc; + struct prb_data_blk_lpos *blk_lpos = &desc.text_blk_lpos; + unsigned long id; + + /* Loop until @lpos_begin has advanced to or beyond @lpos_end. */ + while ((lpos_end - lpos_begin) - 1 < DATA_SIZE(data_ring)) { + blk = to_block(data_ring, lpos_begin); + + /* + * Load the block ID from the data block. This is a data race + * against a writer that may have newly reserved this data + * area. If the loaded value matches a valid descriptor ID, + * the blk_lpos of that descriptor will be checked to make + * sure it points back to this data block. If the check fails, + * the data area has been recycled by another writer. + */ + id = blk->id; /* LMM(data_make_reusable:A) */ + + d_state = desc_read(desc_ring, id, &desc, + NULL, NULL); /* LMM(data_make_reusable:B) */ + + switch (d_state) { + case desc_miss: + case desc_reserved: + case desc_committed: + return false; + case desc_finalized: + /* + * This data block is invalid if the descriptor + * does not point back to it. + */ + if (blk_lpos->begin != lpos_begin) + return false; + desc_make_reusable(desc_ring, id); + break; + case desc_reusable: + /* + * This data block is invalid if the descriptor + * does not point back to it. + */ + if (blk_lpos->begin != lpos_begin) + return false; + break; + } + + /* Advance @lpos_begin to the next data block. */ + lpos_begin = blk_lpos->next; + } + + *lpos_out = lpos_begin; + return true; +} + +/* + * Advance the data ring tail to at least @lpos. This function puts + * descriptors into the reusable state if the tail is pushed beyond + * their associated data block. + */ +static bool data_push_tail(struct printk_ringbuffer *rb, unsigned long lpos) +{ + struct prb_data_ring *data_ring = &rb->text_data_ring; + unsigned long tail_lpos_new; + unsigned long tail_lpos; + unsigned long next_lpos; + + /* If @lpos is from a data-less block, there is nothing to do. */ + if (LPOS_DATALESS(lpos)) + return true; + + /* + * Any descriptor states that have transitioned to reusable due to the + * data tail being pushed to this loaded value will be visible to this + * CPU. This pairs with data_push_tail:D. + * + * Memory barrier involvement: + * + * If data_push_tail:A reads from data_push_tail:D, then this CPU can + * see desc_make_reusable:A. + * + * Relies on: + * + * MB from desc_make_reusable:A to data_push_tail:D + * matches + * READFROM from data_push_tail:D to data_push_tail:A + * thus + * READFROM from desc_make_reusable:A to this CPU + */ + tail_lpos = atomic_long_read(&data_ring->tail_lpos); /* LMM(data_push_tail:A) */ + + /* + * Loop until the tail lpos is at or beyond @lpos. This condition + * may already be satisfied, resulting in no full memory barrier + * from data_push_tail:D being performed. However, since this CPU + * sees the new tail lpos, any descriptor states that transitioned to + * the reusable state must already be visible. + */ + while ((lpos - tail_lpos) - 1 < DATA_SIZE(data_ring)) { + /* + * Make all descriptors reusable that are associated with + * data blocks before @lpos. + */ + if (!data_make_reusable(rb, tail_lpos, lpos, &next_lpos)) { + /* + * 1. Guarantee the block ID loaded in + * data_make_reusable() is performed before + * reloading the tail lpos. The failed + * data_make_reusable() may be due to a newly + * recycled data area causing the tail lpos to + * have been previously pushed. This pairs with + * data_alloc:A and data_realloc:A. + * + * Memory barrier involvement: + * + * If data_make_reusable:A reads from data_alloc:B, + * then data_push_tail:C reads from + * data_push_tail:D. + * + * Relies on: + * + * MB from data_push_tail:D to data_alloc:B + * matching + * RMB from data_make_reusable:A to + * data_push_tail:C + * + * Note: data_push_tail:D and data_alloc:B can be + * different CPUs. However, the data_alloc:B + * CPU (which performs the full memory + * barrier) must have previously seen + * data_push_tail:D. + * + * 2. Guarantee the descriptor state loaded in + * data_make_reusable() is performed before + * reloading the tail lpos. The failed + * data_make_reusable() may be due to a newly + * recycled descriptor causing the tail lpos to + * have been previously pushed. This pairs with + * desc_reserve:D. + * + * Memory barrier involvement: + * + * If data_make_reusable:B reads from + * desc_reserve:F, then data_push_tail:C reads + * from data_push_tail:D. + * + * Relies on: + * + * MB from data_push_tail:D to desc_reserve:F + * matching + * RMB from data_make_reusable:B to + * data_push_tail:C + * + * Note: data_push_tail:D and desc_reserve:F can + * be different CPUs. However, the + * desc_reserve:F CPU (which performs the + * full memory barrier) must have previously + * seen data_push_tail:D. + */ + smp_rmb(); /* LMM(data_push_tail:B) */ + + tail_lpos_new = atomic_long_read(&data_ring->tail_lpos + ); /* LMM(data_push_tail:C) */ + if (tail_lpos_new == tail_lpos) + return false; + + /* Another CPU pushed the tail. Try again. */ + tail_lpos = tail_lpos_new; + continue; + } + + /* + * Guarantee any descriptor states that have transitioned to + * reusable are stored before pushing the tail lpos. A full + * memory barrier is needed since other CPUs may have made + * the descriptor states reusable. This pairs with + * data_push_tail:A. + */ + if (atomic_long_try_cmpxchg(&data_ring->tail_lpos, &tail_lpos, + next_lpos)) { /* LMM(data_push_tail:D) */ + break; + } + } + + return true; +} + +/* + * Advance the desc ring tail. This function advances the tail by one + * descriptor, thus invalidating the oldest descriptor. Before advancing + * the tail, the tail descriptor is made reusable and all data blocks up to + * and including the descriptor's data block are invalidated (i.e. the data + * ring tail is pushed past the data block of the descriptor being made + * reusable). + */ +static bool desc_push_tail(struct printk_ringbuffer *rb, + unsigned long tail_id) +{ + struct prb_desc_ring *desc_ring = &rb->desc_ring; + enum desc_state d_state; + struct prb_desc desc; + + d_state = desc_read(desc_ring, tail_id, &desc, NULL, NULL); + + switch (d_state) { + case desc_miss: + /* + * If the ID is exactly 1 wrap behind the expected, it is + * in the process of being reserved by another writer and + * must be considered reserved. + */ + if (DESC_ID(atomic_long_read(&desc.state_var)) == + DESC_ID_PREV_WRAP(desc_ring, tail_id)) { + return false; + } + + /* + * The ID has changed. Another writer must have pushed the + * tail and recycled the descriptor already. Success is + * returned because the caller is only interested in the + * specified tail being pushed, which it was. + */ + return true; + case desc_reserved: + case desc_committed: + return false; + case desc_finalized: + desc_make_reusable(desc_ring, tail_id); + break; + case desc_reusable: + break; + } + + /* + * Data blocks must be invalidated before their associated + * descriptor can be made available for recycling. Invalidating + * them later is not possible because there is no way to trust + * data blocks once their associated descriptor is gone. + */ + + if (!data_push_tail(rb, desc.text_blk_lpos.next)) + return false; + + /* + * Check the next descriptor after @tail_id before pushing the tail + * to it because the tail must always be in a finalized or reusable + * state. The implementation of prb_first_seq() relies on this. + * + * A successful read implies that the next descriptor is less than or + * equal to @head_id so there is no risk of pushing the tail past the + * head. + */ + d_state = desc_read(desc_ring, DESC_ID(tail_id + 1), &desc, + NULL, NULL); /* LMM(desc_push_tail:A) */ + + if (d_state == desc_finalized || d_state == desc_reusable) { + /* + * Guarantee any descriptor states that have transitioned to + * reusable are stored before pushing the tail ID. This allows + * verifying the recycled descriptor state. A full memory + * barrier is needed since other CPUs may have made the + * descriptor states reusable. This pairs with desc_reserve:D. + */ + atomic_long_cmpxchg(&desc_ring->tail_id, tail_id, + DESC_ID(tail_id + 1)); /* LMM(desc_push_tail:B) */ + } else { + /* + * Guarantee the last state load from desc_read() is before + * reloading @tail_id in order to see a new tail ID in the + * case that the descriptor has been recycled. This pairs + * with desc_reserve:D. + * + * Memory barrier involvement: + * + * If desc_push_tail:A reads from desc_reserve:F, then + * desc_push_tail:D reads from desc_push_tail:B. + * + * Relies on: + * + * MB from desc_push_tail:B to desc_reserve:F + * matching + * RMB from desc_push_tail:A to desc_push_tail:D + * + * Note: desc_push_tail:B and desc_reserve:F can be different + * CPUs. However, the desc_reserve:F CPU (which performs + * the full memory barrier) must have previously seen + * desc_push_tail:B. + */ + smp_rmb(); /* LMM(desc_push_tail:C) */ + + /* + * Re-check the tail ID. The descriptor following @tail_id is + * not in an allowed tail state. But if the tail has since + * been moved by another CPU, then it does not matter. + */ + if (atomic_long_read(&desc_ring->tail_id) == tail_id) /* LMM(desc_push_tail:D) */ + return false; + } + + return true; +} + +/* Reserve a new descriptor, invalidating the oldest if necessary. */ +static bool desc_reserve(struct printk_ringbuffer *rb, unsigned long *id_out) +{ + struct prb_desc_ring *desc_ring = &rb->desc_ring; + unsigned long prev_state_val; + unsigned long id_prev_wrap; + struct prb_desc *desc; + unsigned long head_id; + unsigned long id; + + head_id = atomic_long_read(&desc_ring->head_id); /* LMM(desc_reserve:A) */ + + do { + id = DESC_ID(head_id + 1); + id_prev_wrap = DESC_ID_PREV_WRAP(desc_ring, id); + + /* + * Guarantee the head ID is read before reading the tail ID. + * Since the tail ID is updated before the head ID, this + * guarantees that @id_prev_wrap is never ahead of the tail + * ID. This pairs with desc_reserve:D. + * + * Memory barrier involvement: + * + * If desc_reserve:A reads from desc_reserve:D, then + * desc_reserve:C reads from desc_push_tail:B. + * + * Relies on: + * + * MB from desc_push_tail:B to desc_reserve:D + * matching + * RMB from desc_reserve:A to desc_reserve:C + * + * Note: desc_push_tail:B and desc_reserve:D can be different + * CPUs. However, the desc_reserve:D CPU (which performs + * the full memory barrier) must have previously seen + * desc_push_tail:B. + */ + smp_rmb(); /* LMM(desc_reserve:B) */ + + if (id_prev_wrap == atomic_long_read(&desc_ring->tail_id + )) { /* LMM(desc_reserve:C) */ + /* + * Make space for the new descriptor by + * advancing the tail. + */ + if (!desc_push_tail(rb, id_prev_wrap)) + return false; + } + + /* + * 1. Guarantee the tail ID is read before validating the + * recycled descriptor state. A read memory barrier is + * sufficient for this. This pairs with desc_push_tail:B. + * + * Memory barrier involvement: + * + * If desc_reserve:C reads from desc_push_tail:B, then + * desc_reserve:E reads from desc_make_reusable:A. + * + * Relies on: + * + * MB from desc_make_reusable:A to desc_push_tail:B + * matching + * RMB from desc_reserve:C to desc_reserve:E + * + * Note: desc_make_reusable:A and desc_push_tail:B can be + * different CPUs. However, the desc_push_tail:B CPU + * (which performs the full memory barrier) must have + * previously seen desc_make_reusable:A. + * + * 2. Guarantee the tail ID is stored before storing the head + * ID. This pairs with desc_reserve:B. + * + * 3. Guarantee any data ring tail changes are stored before + * recycling the descriptor. Data ring tail changes can + * happen via desc_push_tail()->data_push_tail(). A full + * memory barrier is needed since another CPU may have + * pushed the data ring tails. This pairs with + * data_push_tail:B. + * + * 4. Guarantee a new tail ID is stored before recycling the + * descriptor. A full memory barrier is needed since + * another CPU may have pushed the tail ID. This pairs + * with desc_push_tail:C and this also pairs with + * prb_first_seq:C. + * + * 5. Guarantee the head ID is stored before trying to + * finalize the previous descriptor. This pairs with + * _prb_commit:B. + */ + } while (!atomic_long_try_cmpxchg(&desc_ring->head_id, &head_id, + id)); /* LMM(desc_reserve:D) */ + + desc = to_desc(desc_ring, id); + + /* + * If the descriptor has been recycled, verify the old state val. + * See "ABA Issues" about why this verification is performed. + */ + prev_state_val = atomic_long_read(&desc->state_var); /* LMM(desc_reserve:E) */ + if (prev_state_val && + get_desc_state(id_prev_wrap, prev_state_val) != desc_reusable) { + WARN_ON_ONCE(1); + return false; + } + + /* + * Assign the descriptor a new ID and set its state to reserved. + * See "ABA Issues" about why cmpxchg() instead of set() is used. + * + * Guarantee the new descriptor ID and state is stored before making + * any other changes. A write memory barrier is sufficient for this. + * This pairs with desc_read:D. + */ + if (!atomic_long_try_cmpxchg(&desc->state_var, &prev_state_val, + DESC_SV(id, desc_reserved))) { /* LMM(desc_reserve:F) */ + WARN_ON_ONCE(1); + return false; + } + + /* Now data in @desc can be modified: LMM(desc_reserve:G) */ + + *id_out = id; + return true; +} + +/* Determine the end of a data block. */ +static unsigned long get_next_lpos(struct prb_data_ring *data_ring, + unsigned long lpos, unsigned int size) +{ + unsigned long begin_lpos; + unsigned long next_lpos; + + begin_lpos = lpos; + next_lpos = lpos + size; + + /* First check if the data block does not wrap. */ + if (DATA_WRAPS(data_ring, begin_lpos) == DATA_WRAPS(data_ring, next_lpos)) + return next_lpos; + + /* Wrapping data blocks store their data at the beginning. */ + return (DATA_THIS_WRAP_START_LPOS(data_ring, next_lpos) + size); +} + +/* + * Allocate a new data block, invalidating the oldest data block(s) + * if necessary. This function also associates the data block with + * a specified descriptor. + */ +static char *data_alloc(struct printk_ringbuffer *rb, unsigned int size, + struct prb_data_blk_lpos *blk_lpos, unsigned long id) +{ + struct prb_data_ring *data_ring = &rb->text_data_ring; + struct prb_data_block *blk; + unsigned long begin_lpos; + unsigned long next_lpos; + + if (size == 0) { + /* Specify a data-less block. */ + blk_lpos->begin = NO_LPOS; + blk_lpos->next = NO_LPOS; + return NULL; + } + + size = to_blk_size(size); + + begin_lpos = atomic_long_read(&data_ring->head_lpos); + + do { + next_lpos = get_next_lpos(data_ring, begin_lpos, size); + + if (!data_push_tail(rb, next_lpos - DATA_SIZE(data_ring))) { + /* Failed to allocate, specify a data-less block. */ + blk_lpos->begin = FAILED_LPOS; + blk_lpos->next = FAILED_LPOS; + return NULL; + } + + /* + * 1. Guarantee any descriptor states that have transitioned + * to reusable are stored before modifying the newly + * allocated data area. A full memory barrier is needed + * since other CPUs may have made the descriptor states + * reusable. See data_push_tail:A about why the reusable + * states are visible. This pairs with desc_read:D. + * + * 2. Guarantee any updated tail lpos is stored before + * modifying the newly allocated data area. Another CPU may + * be in data_make_reusable() and is reading a block ID + * from this area. data_make_reusable() can handle reading + * a garbage block ID value, but then it must be able to + * load a new tail lpos. A full memory barrier is needed + * since other CPUs may have updated the tail lpos. This + * pairs with data_push_tail:B. + */ + } while (!atomic_long_try_cmpxchg(&data_ring->head_lpos, &begin_lpos, + next_lpos)); /* LMM(data_alloc:A) */ + + blk = to_block(data_ring, begin_lpos); + blk->id = id; /* LMM(data_alloc:B) */ + + if (DATA_WRAPS(data_ring, begin_lpos) != DATA_WRAPS(data_ring, next_lpos)) { + /* Wrapping data blocks store their data at the beginning. */ + blk = to_block(data_ring, 0); + + /* + * Store the ID on the wrapped block for consistency. + * The printk_ringbuffer does not actually use it. + */ + blk->id = id; + } + + blk_lpos->begin = begin_lpos; + blk_lpos->next = next_lpos; + + return &blk->data[0]; +} + +/* + * Try to resize an existing data block associated with the descriptor + * specified by @id. If the resized data block should become wrapped, it + * copies the old data to the new data block. If @size yields a data block + * with the same or less size, the data block is left as is. + * + * Fail if this is not the last allocated data block or if there is not + * enough space or it is not possible make enough space. + * + * Return a pointer to the beginning of the entire data buffer or NULL on + * failure. + */ +static char *data_realloc(struct printk_ringbuffer *rb, unsigned int size, + struct prb_data_blk_lpos *blk_lpos, unsigned long id) +{ + struct prb_data_ring *data_ring = &rb->text_data_ring; + struct prb_data_block *blk; + unsigned long head_lpos; + unsigned long next_lpos; + bool wrapped; + + /* Reallocation only works if @blk_lpos is the newest data block. */ + head_lpos = atomic_long_read(&data_ring->head_lpos); + if (head_lpos != blk_lpos->next) + return NULL; + + /* Keep track if @blk_lpos was a wrapping data block. */ + wrapped = (DATA_WRAPS(data_ring, blk_lpos->begin) != DATA_WRAPS(data_ring, blk_lpos->next)); + + size = to_blk_size(size); + + next_lpos = get_next_lpos(data_ring, blk_lpos->begin, size); + + /* If the data block does not increase, there is nothing to do. */ + if (head_lpos - next_lpos < DATA_SIZE(data_ring)) { + if (wrapped) + blk = to_block(data_ring, 0); + else + blk = to_block(data_ring, blk_lpos->begin); + return &blk->data[0]; + } + + if (!data_push_tail(rb, next_lpos - DATA_SIZE(data_ring))) + return NULL; + + /* The memory barrier involvement is the same as data_alloc:A. */ + if (!atomic_long_try_cmpxchg(&data_ring->head_lpos, &head_lpos, + next_lpos)) { /* LMM(data_realloc:A) */ + return NULL; + } + + blk = to_block(data_ring, blk_lpos->begin); + + if (DATA_WRAPS(data_ring, blk_lpos->begin) != DATA_WRAPS(data_ring, next_lpos)) { + struct prb_data_block *old_blk = blk; + + /* Wrapping data blocks store their data at the beginning. */ + blk = to_block(data_ring, 0); + + /* + * Store the ID on the wrapped block for consistency. + * The printk_ringbuffer does not actually use it. + */ + blk->id = id; + + if (!wrapped) { + /* + * Since the allocated space is now in the newly + * created wrapping data block, copy the content + * from the old data block. + */ + memcpy(&blk->data[0], &old_blk->data[0], + (blk_lpos->next - blk_lpos->begin) - sizeof(blk->id)); + } + } + + blk_lpos->next = next_lpos; + + return &blk->data[0]; +} + +/* Return the number of bytes used by a data block. */ +static unsigned int space_used(struct prb_data_ring *data_ring, + struct prb_data_blk_lpos *blk_lpos) +{ + /* Data-less blocks take no space. */ + if (BLK_DATALESS(blk_lpos)) + return 0; + + if (DATA_WRAPS(data_ring, blk_lpos->begin) == DATA_WRAPS(data_ring, blk_lpos->next)) { + /* Data block does not wrap. */ + return (DATA_INDEX(data_ring, blk_lpos->next) - + DATA_INDEX(data_ring, blk_lpos->begin)); + } + + /* + * For wrapping data blocks, the trailing (wasted) space is + * also counted. + */ + return (DATA_INDEX(data_ring, blk_lpos->next) + + DATA_SIZE(data_ring) - DATA_INDEX(data_ring, blk_lpos->begin)); +} + +/* + * Given @blk_lpos, return a pointer to the writer data from the data block + * and calculate the size of the data part. A NULL pointer is returned if + * @blk_lpos specifies values that could never be legal. + * + * This function (used by readers) performs strict validation on the lpos + * values to possibly detect bugs in the writer code. A WARN_ON_ONCE() is + * triggered if an internal error is detected. + */ +static const char *get_data(struct prb_data_ring *data_ring, + struct prb_data_blk_lpos *blk_lpos, + unsigned int *data_size) +{ + struct prb_data_block *db; + + /* Data-less data block description. */ + if (BLK_DATALESS(blk_lpos)) { + if (blk_lpos->begin == NO_LPOS && blk_lpos->next == NO_LPOS) { + *data_size = 0; + return ""; + } + return NULL; + } + + /* Regular data block: @begin less than @next and in same wrap. */ + if (DATA_WRAPS(data_ring, blk_lpos->begin) == DATA_WRAPS(data_ring, blk_lpos->next) && + blk_lpos->begin < blk_lpos->next) { + db = to_block(data_ring, blk_lpos->begin); + *data_size = blk_lpos->next - blk_lpos->begin; + + /* Wrapping data block: @begin is one wrap behind @next. */ + } else if (DATA_WRAPS(data_ring, blk_lpos->begin + DATA_SIZE(data_ring)) == + DATA_WRAPS(data_ring, blk_lpos->next)) { + db = to_block(data_ring, 0); + *data_size = DATA_INDEX(data_ring, blk_lpos->next); + + /* Illegal block description. */ + } else { + WARN_ON_ONCE(1); + return NULL; + } + + /* A valid data block will always be aligned to the ID size. */ + if (WARN_ON_ONCE(blk_lpos->begin != ALIGN(blk_lpos->begin, sizeof(db->id))) || + WARN_ON_ONCE(blk_lpos->next != ALIGN(blk_lpos->next, sizeof(db->id)))) { + return NULL; + } + + /* A valid data block will always have at least an ID. */ + if (WARN_ON_ONCE(*data_size < sizeof(db->id))) + return NULL; + + /* Subtract block ID space from size to reflect data size. */ + *data_size -= sizeof(db->id); + + return &db->data[0]; +} + +/* + * Attempt to transition the newest descriptor from committed back to reserved + * so that the record can be modified by a writer again. This is only possible + * if the descriptor is not yet finalized and the provided @caller_id matches. + */ +static struct prb_desc *desc_reopen_last(struct prb_desc_ring *desc_ring, + u32 caller_id, unsigned long *id_out) +{ + unsigned long prev_state_val; + enum desc_state d_state; + struct prb_desc desc; + struct prb_desc *d; + unsigned long id; + u32 cid; + + id = atomic_long_read(&desc_ring->head_id); + + /* + * To reduce unnecessarily reopening, first check if the descriptor + * state and caller ID are correct. + */ + d_state = desc_read(desc_ring, id, &desc, NULL, &cid); + if (d_state != desc_committed || cid != caller_id) + return NULL; + + d = to_desc(desc_ring, id); + + prev_state_val = DESC_SV(id, desc_committed); + + /* + * Guarantee the reserved state is stored before reading any + * record data. A full memory barrier is needed because @state_var + * modification is followed by reading. This pairs with _prb_commit:B. + * + * Memory barrier involvement: + * + * If desc_reopen_last:A reads from _prb_commit:B, then + * prb_reserve_in_last:A reads from _prb_commit:A. + * + * Relies on: + * + * WMB from _prb_commit:A to _prb_commit:B + * matching + * MB If desc_reopen_last:A to prb_reserve_in_last:A + */ + if (!atomic_long_try_cmpxchg(&d->state_var, &prev_state_val, + DESC_SV(id, desc_reserved))) { /* LMM(desc_reopen_last:A) */ + return NULL; + } + + *id_out = id; + return d; +} + +/** + * prb_reserve_in_last() - Re-reserve and extend the space in the ringbuffer + * used by the newest record. + * + * @e: The entry structure to setup. + * @rb: The ringbuffer to re-reserve and extend data in. + * @r: The record structure to allocate buffers for. + * @caller_id: The caller ID of the caller (reserving writer). + * @max_size: Fail if the extended size would be greater than this. + * + * This is the public function available to writers to re-reserve and extend + * data. + * + * The writer specifies the text size to extend (not the new total size) by + * setting the @text_buf_size field of @r. To ensure proper initialization + * of @r, prb_rec_init_wr() should be used. + * + * This function will fail if @caller_id does not match the caller ID of the + * newest record. In that case the caller must reserve new data using + * prb_reserve(). + * + * Context: Any context. Disables local interrupts on success. + * Return: true if text data could be extended, otherwise false. + * + * On success: + * + * - @r->text_buf points to the beginning of the entire text buffer. + * + * - @r->text_buf_size is set to the new total size of the buffer. + * + * - @r->info is not touched so that @r->info->text_len could be used + * to append the text. + * + * - prb_record_text_space() can be used on @e to query the new + * actually used space. + * + * Important: All @r->info fields will already be set with the current values + * for the record. I.e. @r->info->text_len will be less than + * @text_buf_size. Writers can use @r->info->text_len to know + * where concatenation begins and writers should update + * @r->info->text_len after concatenating. + */ +bool prb_reserve_in_last(struct prb_reserved_entry *e, struct printk_ringbuffer *rb, + struct printk_record *r, u32 caller_id, unsigned int max_size) +{ + struct prb_desc_ring *desc_ring = &rb->desc_ring; + struct printk_info *info; + unsigned int data_size; + struct prb_desc *d; + unsigned long id; + + local_irq_save(e->irqflags); + + /* Transition the newest descriptor back to the reserved state. */ + d = desc_reopen_last(desc_ring, caller_id, &id); + if (!d) { + local_irq_restore(e->irqflags); + goto fail_reopen; + } + + /* Now the writer has exclusive access: LMM(prb_reserve_in_last:A) */ + + info = to_info(desc_ring, id); + + /* + * Set the @e fields here so that prb_commit() can be used if + * anything fails from now on. + */ + e->rb = rb; + e->id = id; + + /* + * desc_reopen_last() checked the caller_id, but there was no + * exclusive access at that point. The descriptor may have + * changed since then. + */ + if (caller_id != info->caller_id) + goto fail; + + if (BLK_DATALESS(&d->text_blk_lpos)) { + if (WARN_ON_ONCE(info->text_len != 0)) { + pr_warn_once("wrong text_len value (%hu, expecting 0)\n", + info->text_len); + info->text_len = 0; + } + + if (!data_check_size(&rb->text_data_ring, r->text_buf_size)) + goto fail; + + if (r->text_buf_size > max_size) + goto fail; + + r->text_buf = data_alloc(rb, r->text_buf_size, + &d->text_blk_lpos, id); + } else { + if (!get_data(&rb->text_data_ring, &d->text_blk_lpos, &data_size)) + goto fail; + + /* + * Increase the buffer size to include the original size. If + * the meta data (@text_len) is not sane, use the full data + * block size. + */ + if (WARN_ON_ONCE(info->text_len > data_size)) { + pr_warn_once("wrong text_len value (%hu, expecting <=%u)\n", + info->text_len, data_size); + info->text_len = data_size; + } + r->text_buf_size += info->text_len; + + if (!data_check_size(&rb->text_data_ring, r->text_buf_size)) + goto fail; + + if (r->text_buf_size > max_size) + goto fail; + + r->text_buf = data_realloc(rb, r->text_buf_size, + &d->text_blk_lpos, id); + } + if (r->text_buf_size && !r->text_buf) + goto fail; + + r->info = info; + + e->text_space = space_used(&rb->text_data_ring, &d->text_blk_lpos); + + return true; +fail: + prb_commit(e); + /* prb_commit() re-enabled interrupts. */ +fail_reopen: + /* Make it clear to the caller that the re-reserve failed. */ + memset(r, 0, sizeof(*r)); + return false; +} + +/* + * Attempt to finalize a specified descriptor. If this fails, the descriptor + * is either already final or it will finalize itself when the writer commits. + */ +static void desc_make_final(struct prb_desc_ring *desc_ring, unsigned long id) +{ + unsigned long prev_state_val = DESC_SV(id, desc_committed); + struct prb_desc *d = to_desc(desc_ring, id); + + atomic_long_cmpxchg_relaxed(&d->state_var, prev_state_val, + DESC_SV(id, desc_finalized)); /* LMM(desc_make_final:A) */ + + /* Best effort to remember the last finalized @id. */ + atomic_long_set(&desc_ring->last_finalized_id, id); +} + +/** + * prb_reserve() - Reserve space in the ringbuffer. + * + * @e: The entry structure to setup. + * @rb: The ringbuffer to reserve data in. + * @r: The record structure to allocate buffers for. + * + * This is the public function available to writers to reserve data. + * + * The writer specifies the text size to reserve by setting the + * @text_buf_size field of @r. To ensure proper initialization of @r, + * prb_rec_init_wr() should be used. + * + * Context: Any context. Disables local interrupts on success. + * Return: true if at least text data could be allocated, otherwise false. + * + * On success, the fields @info and @text_buf of @r will be set by this + * function and should be filled in by the writer before committing. Also + * on success, prb_record_text_space() can be used on @e to query the actual + * space used for the text data block. + * + * Important: @info->text_len needs to be set correctly by the writer in + * order for data to be readable and/or extended. Its value + * is initialized to 0. + */ +bool prb_reserve(struct prb_reserved_entry *e, struct printk_ringbuffer *rb, + struct printk_record *r) +{ + struct prb_desc_ring *desc_ring = &rb->desc_ring; + struct printk_info *info; + struct prb_desc *d; + unsigned long id; + u64 seq; + + if (!data_check_size(&rb->text_data_ring, r->text_buf_size)) + goto fail; + + /* + * Descriptors in the reserved state act as blockers to all further + * reservations once the desc_ring has fully wrapped. Disable + * interrupts during the reserve/commit window in order to minimize + * the likelihood of this happening. + */ + local_irq_save(e->irqflags); + + if (!desc_reserve(rb, &id)) { + /* Descriptor reservation failures are tracked. */ + atomic_long_inc(&rb->fail); + local_irq_restore(e->irqflags); + goto fail; + } + + d = to_desc(desc_ring, id); + info = to_info(desc_ring, id); + + /* + * All @info fields (except @seq) are cleared and must be filled in + * by the writer. Save @seq before clearing because it is used to + * determine the new sequence number. + */ + seq = info->seq; + memset(info, 0, sizeof(*info)); + + /* + * Set the @e fields here so that prb_commit() can be used if + * text data allocation fails. + */ + e->rb = rb; + e->id = id; + + /* + * Initialize the sequence number if it has "never been set". + * Otherwise just increment it by a full wrap. + * + * @seq is considered "never been set" if it has a value of 0, + * _except_ for @infos[0], which was specially setup by the ringbuffer + * initializer and therefore is always considered as set. + * + * See the "Bootstrap" comment block in printk_ringbuffer.h for + * details about how the initializer bootstraps the descriptors. + */ + if (seq == 0 && DESC_INDEX(desc_ring, id) != 0) + info->seq = DESC_INDEX(desc_ring, id); + else + info->seq = seq + DESCS_COUNT(desc_ring); + + /* + * New data is about to be reserved. Once that happens, previous + * descriptors are no longer able to be extended. Finalize the + * previous descriptor now so that it can be made available to + * readers. (For seq==0 there is no previous descriptor.) + */ + if (info->seq > 0) + desc_make_final(desc_ring, DESC_ID(id - 1)); + + r->text_buf = data_alloc(rb, r->text_buf_size, &d->text_blk_lpos, id); + /* If text data allocation fails, a data-less record is committed. */ + if (r->text_buf_size && !r->text_buf) { + prb_commit(e); + /* prb_commit() re-enabled interrupts. */ + goto fail; + } + + r->info = info; + + /* Record full text space used by record. */ + e->text_space = space_used(&rb->text_data_ring, &d->text_blk_lpos); + + return true; +fail: + /* Make it clear to the caller that the reserve failed. */ + memset(r, 0, sizeof(*r)); + return false; +} + +/* Commit the data (possibly finalizing it) and restore interrupts. */ +static void _prb_commit(struct prb_reserved_entry *e, unsigned long state_val) +{ + struct prb_desc_ring *desc_ring = &e->rb->desc_ring; + struct prb_desc *d = to_desc(desc_ring, e->id); + unsigned long prev_state_val = DESC_SV(e->id, desc_reserved); + + /* Now the writer has finished all writing: LMM(_prb_commit:A) */ + + /* + * Set the descriptor as committed. See "ABA Issues" about why + * cmpxchg() instead of set() is used. + * + * 1 Guarantee all record data is stored before the descriptor state + * is stored as committed. A write memory barrier is sufficient + * for this. This pairs with desc_read:B and desc_reopen_last:A. + * + * 2. Guarantee the descriptor state is stored as committed before + * re-checking the head ID in order to possibly finalize this + * descriptor. This pairs with desc_reserve:D. + * + * Memory barrier involvement: + * + * If prb_commit:A reads from desc_reserve:D, then + * desc_make_final:A reads from _prb_commit:B. + * + * Relies on: + * + * MB _prb_commit:B to prb_commit:A + * matching + * MB desc_reserve:D to desc_make_final:A + */ + if (!atomic_long_try_cmpxchg(&d->state_var, &prev_state_val, + DESC_SV(e->id, state_val))) { /* LMM(_prb_commit:B) */ + WARN_ON_ONCE(1); + } + + /* Restore interrupts, the reserve/commit window is finished. */ + local_irq_restore(e->irqflags); +} + +/** + * prb_commit() - Commit (previously reserved) data to the ringbuffer. + * + * @e: The entry containing the reserved data information. + * + * This is the public function available to writers to commit data. + * + * Note that the data is not yet available to readers until it is finalized. + * Finalizing happens automatically when space for the next record is + * reserved. + * + * See prb_final_commit() for a version of this function that finalizes + * immediately. + * + * Context: Any context. Enables local interrupts. + */ +void prb_commit(struct prb_reserved_entry *e) +{ + struct prb_desc_ring *desc_ring = &e->rb->desc_ring; + unsigned long head_id; + + _prb_commit(e, desc_committed); + + /* + * If this descriptor is no longer the head (i.e. a new record has + * been allocated), extending the data for this record is no longer + * allowed and therefore it must be finalized. + */ + head_id = atomic_long_read(&desc_ring->head_id); /* LMM(prb_commit:A) */ + if (head_id != e->id) + desc_make_final(desc_ring, e->id); +} + +/** + * prb_final_commit() - Commit and finalize (previously reserved) data to + * the ringbuffer. + * + * @e: The entry containing the reserved data information. + * + * This is the public function available to writers to commit+finalize data. + * + * By finalizing, the data is made immediately available to readers. + * + * This function should only be used if there are no intentions of extending + * this data using prb_reserve_in_last(). + * + * Context: Any context. Enables local interrupts. + */ +void prb_final_commit(struct prb_reserved_entry *e) +{ + struct prb_desc_ring *desc_ring = &e->rb->desc_ring; + + _prb_commit(e, desc_finalized); + + /* Best effort to remember the last finalized @id. */ + atomic_long_set(&desc_ring->last_finalized_id, e->id); +} + +/* + * Count the number of lines in provided text. All text has at least 1 line + * (even if @text_size is 0). Each '\n' processed is counted as an additional + * line. + */ +static unsigned int count_lines(const char *text, unsigned int text_size) +{ + unsigned int next_size = text_size; + unsigned int line_count = 1; + const char *next = text; + + while (next_size) { + next = memchr(next, '\n', next_size); + if (!next) + break; + line_count++; + next++; + next_size = text_size - (next - text); + } + + return line_count; +} + +/* + * Given @blk_lpos, copy an expected @len of data into the provided buffer. + * If @line_count is provided, count the number of lines in the data. + * + * This function (used by readers) performs strict validation on the data + * size to possibly detect bugs in the writer code. A WARN_ON_ONCE() is + * triggered if an internal error is detected. + */ +static bool copy_data(struct prb_data_ring *data_ring, + struct prb_data_blk_lpos *blk_lpos, u16 len, char *buf, + unsigned int buf_size, unsigned int *line_count) +{ + unsigned int data_size; + const char *data; + + /* Caller might not want any data. */ + if ((!buf || !buf_size) && !line_count) + return true; + + data = get_data(data_ring, blk_lpos, &data_size); + if (!data) + return false; + + /* + * Actual cannot be less than expected. It can be more than expected + * because of the trailing alignment padding. + * + * Note that invalid @len values can occur because the caller loads + * the value during an allowed data race. + */ + if (data_size < (unsigned int)len) + return false; + + /* Caller interested in the line count? */ + if (line_count) + *line_count = count_lines(data, len); + + /* Caller interested in the data content? */ + if (!buf || !buf_size) + return true; + + data_size = min_t(unsigned int, buf_size, len); + + memcpy(&buf[0], data, data_size); /* LMM(copy_data:A) */ + return true; +} + +/* + * This is an extended version of desc_read(). It gets a copy of a specified + * descriptor. However, it also verifies that the record is finalized and has + * the sequence number @seq. On success, 0 is returned. + * + * Error return values: + * -EINVAL: A finalized record with sequence number @seq does not exist. + * -ENOENT: A finalized record with sequence number @seq exists, but its data + * is not available. This is a valid record, so readers should + * continue with the next record. + */ +static int desc_read_finalized_seq(struct prb_desc_ring *desc_ring, + unsigned long id, u64 seq, + struct prb_desc *desc_out) +{ + struct prb_data_blk_lpos *blk_lpos = &desc_out->text_blk_lpos; + enum desc_state d_state; + u64 s; + + d_state = desc_read(desc_ring, id, desc_out, &s, NULL); + + /* + * An unexpected @id (desc_miss) or @seq mismatch means the record + * does not exist. A descriptor in the reserved or committed state + * means the record does not yet exist for the reader. + */ + if (d_state == desc_miss || + d_state == desc_reserved || + d_state == desc_committed || + s != seq) { + return -EINVAL; + } + + /* + * A descriptor in the reusable state may no longer have its data + * available; report it as existing but with lost data. Or the record + * may actually be a record with lost data. + */ + if (d_state == desc_reusable || + (blk_lpos->begin == FAILED_LPOS && blk_lpos->next == FAILED_LPOS)) { + return -ENOENT; + } + + return 0; +} + +/* + * Copy the ringbuffer data from the record with @seq to the provided + * @r buffer. On success, 0 is returned. + * + * See desc_read_finalized_seq() for error return values. + */ +static int prb_read(struct printk_ringbuffer *rb, u64 seq, + struct printk_record *r, unsigned int *line_count) +{ + struct prb_desc_ring *desc_ring = &rb->desc_ring; + struct printk_info *info = to_info(desc_ring, seq); + struct prb_desc *rdesc = to_desc(desc_ring, seq); + atomic_long_t *state_var = &rdesc->state_var; + struct prb_desc desc; + unsigned long id; + int err; + + /* Extract the ID, used to specify the descriptor to read. */ + id = DESC_ID(atomic_long_read(state_var)); + + /* Get a local copy of the correct descriptor (if available). */ + err = desc_read_finalized_seq(desc_ring, id, seq, &desc); + + /* + * If @r is NULL, the caller is only interested in the availability + * of the record. + */ + if (err || !r) + return err; + + /* If requested, copy meta data. */ + if (r->info) + memcpy(r->info, info, sizeof(*(r->info))); + + /* Copy text data. If it fails, this is a data-less record. */ + if (!copy_data(&rb->text_data_ring, &desc.text_blk_lpos, info->text_len, + r->text_buf, r->text_buf_size, line_count)) { + return -ENOENT; + } + + /* Ensure the record is still finalized and has the same @seq. */ + return desc_read_finalized_seq(desc_ring, id, seq, &desc); +} + +/* Get the sequence number of the tail descriptor. */ +static u64 prb_first_seq(struct printk_ringbuffer *rb) +{ + struct prb_desc_ring *desc_ring = &rb->desc_ring; + enum desc_state d_state; + struct prb_desc desc; + unsigned long id; + u64 seq; + + for (;;) { + id = atomic_long_read(&rb->desc_ring.tail_id); /* LMM(prb_first_seq:A) */ + + d_state = desc_read(desc_ring, id, &desc, &seq, NULL); /* LMM(prb_first_seq:B) */ + + /* + * This loop will not be infinite because the tail is + * _always_ in the finalized or reusable state. + */ + if (d_state == desc_finalized || d_state == desc_reusable) + break; + + /* + * Guarantee the last state load from desc_read() is before + * reloading @tail_id in order to see a new tail in the case + * that the descriptor has been recycled. This pairs with + * desc_reserve:D. + * + * Memory barrier involvement: + * + * If prb_first_seq:B reads from desc_reserve:F, then + * prb_first_seq:A reads from desc_push_tail:B. + * + * Relies on: + * + * MB from desc_push_tail:B to desc_reserve:F + * matching + * RMB prb_first_seq:B to prb_first_seq:A + */ + smp_rmb(); /* LMM(prb_first_seq:C) */ + } + + return seq; +} + +/* + * Non-blocking read of a record. Updates @seq to the last finalized record + * (which may have no data available). + * + * See the description of prb_read_valid() and prb_read_valid_info() + * for details. + */ +static bool _prb_read_valid(struct printk_ringbuffer *rb, u64 *seq, + struct printk_record *r, unsigned int *line_count) +{ + u64 tail_seq; + int err; + + while ((err = prb_read(rb, *seq, r, line_count))) { + tail_seq = prb_first_seq(rb); + + if (*seq < tail_seq) { + /* + * Behind the tail. Catch up and try again. This + * can happen for -ENOENT and -EINVAL cases. + */ + *seq = tail_seq; + + } else if (err == -ENOENT) { + /* Record exists, but no data available. Skip. */ + (*seq)++; + + } else { + /* Non-existent/non-finalized record. Must stop. */ + return false; + } + } + + return true; +} + +/** + * prb_read_valid() - Non-blocking read of a requested record or (if gone) + * the next available record. + * + * @rb: The ringbuffer to read from. + * @seq: The sequence number of the record to read. + * @r: A record data buffer to store the read record to. + * + * This is the public function available to readers to read a record. + * + * The reader provides the @info and @text_buf buffers of @r to be + * filled in. Any of the buffer pointers can be set to NULL if the reader + * is not interested in that data. To ensure proper initialization of @r, + * prb_rec_init_rd() should be used. + * + * Context: Any context. + * Return: true if a record was read, otherwise false. + * + * On success, the reader must check r->info.seq to see which record was + * actually read. This allows the reader to detect dropped records. + * + * Failure means @seq refers to a not yet written record. + */ +bool prb_read_valid(struct printk_ringbuffer *rb, u64 seq, + struct printk_record *r) +{ + return _prb_read_valid(rb, &seq, r, NULL); +} + +/** + * prb_read_valid_info() - Non-blocking read of meta data for a requested + * record or (if gone) the next available record. + * + * @rb: The ringbuffer to read from. + * @seq: The sequence number of the record to read. + * @info: A buffer to store the read record meta data to. + * @line_count: A buffer to store the number of lines in the record text. + * + * This is the public function available to readers to read only the + * meta data of a record. + * + * The reader provides the @info, @line_count buffers to be filled in. + * Either of the buffer pointers can be set to NULL if the reader is not + * interested in that data. + * + * Context: Any context. + * Return: true if a record's meta data was read, otherwise false. + * + * On success, the reader must check info->seq to see which record meta data + * was actually read. This allows the reader to detect dropped records. + * + * Failure means @seq refers to a not yet written record. + */ +bool prb_read_valid_info(struct printk_ringbuffer *rb, u64 seq, + struct printk_info *info, unsigned int *line_count) +{ + struct printk_record r; + + prb_rec_init_rd(&r, info, NULL, 0); + + return _prb_read_valid(rb, &seq, &r, line_count); +} + +/** + * prb_first_valid_seq() - Get the sequence number of the oldest available + * record. + * + * @rb: The ringbuffer to get the sequence number from. + * + * This is the public function available to readers to see what the + * first/oldest valid sequence number is. + * + * This provides readers a starting point to begin iterating the ringbuffer. + * + * Context: Any context. + * Return: The sequence number of the first/oldest record or, if the + * ringbuffer is empty, 0 is returned. + */ +u64 prb_first_valid_seq(struct printk_ringbuffer *rb) +{ + u64 seq = 0; + + if (!_prb_read_valid(rb, &seq, NULL, NULL)) + return 0; + + return seq; +} + +/** + * prb_next_seq() - Get the sequence number after the last available record. + * + * @rb: The ringbuffer to get the sequence number from. + * + * This is the public function available to readers to see what the next + * newest sequence number available to readers will be. + * + * This provides readers a sequence number to jump to if all currently + * available records should be skipped. + * + * Context: Any context. + * Return: The sequence number of the next newest (not yet available) record + * for readers. + */ +u64 prb_next_seq(struct printk_ringbuffer *rb) +{ + struct prb_desc_ring *desc_ring = &rb->desc_ring; + enum desc_state d_state; + unsigned long id; + u64 seq; + + /* Check if the cached @id still points to a valid @seq. */ + id = atomic_long_read(&desc_ring->last_finalized_id); + d_state = desc_read(desc_ring, id, NULL, &seq, NULL); + + if (d_state == desc_finalized || d_state == desc_reusable) { + /* + * Begin searching after the last finalized record. + * + * On 0, the search must begin at 0 because of hack#2 + * of the bootstrapping phase it is not known if a + * record at index 0 exists. + */ + if (seq != 0) + seq++; + } else { + /* + * The information about the last finalized sequence number + * has gone. It should happen only when there is a flood of + * new messages and the ringbuffer is rapidly recycled. + * Give up and start from the beginning. + */ + seq = 0; + } + + /* + * The information about the last finalized @seq might be inaccurate. + * Search forward to find the current one. + */ + while (_prb_read_valid(rb, &seq, NULL, NULL)) + seq++; + + return seq; +} + +/** + * prb_init() - Initialize a ringbuffer to use provided external buffers. + * + * @rb: The ringbuffer to initialize. + * @text_buf: The data buffer for text data. + * @textbits: The size of @text_buf as a power-of-2 value. + * @descs: The descriptor buffer for ringbuffer records. + * @descbits: The count of @descs items as a power-of-2 value. + * @infos: The printk_info buffer for ringbuffer records. + * + * This is the public function available to writers to setup a ringbuffer + * during runtime using provided buffers. + * + * This must match the initialization of DEFINE_PRINTKRB(). + * + * Context: Any context. + */ +void prb_init(struct printk_ringbuffer *rb, + char *text_buf, unsigned int textbits, + struct prb_desc *descs, unsigned int descbits, + struct printk_info *infos) +{ + memset(descs, 0, _DESCS_COUNT(descbits) * sizeof(descs[0])); + memset(infos, 0, _DESCS_COUNT(descbits) * sizeof(infos[0])); + + rb->desc_ring.count_bits = descbits; + rb->desc_ring.descs = descs; + rb->desc_ring.infos = infos; + atomic_long_set(&rb->desc_ring.head_id, DESC0_ID(descbits)); + atomic_long_set(&rb->desc_ring.tail_id, DESC0_ID(descbits)); + atomic_long_set(&rb->desc_ring.last_finalized_id, DESC0_ID(descbits)); + + rb->text_data_ring.size_bits = textbits; + rb->text_data_ring.data = text_buf; + atomic_long_set(&rb->text_data_ring.head_lpos, BLK0_LPOS(textbits)); + atomic_long_set(&rb->text_data_ring.tail_lpos, BLK0_LPOS(textbits)); + + atomic_long_set(&rb->fail, 0); + + atomic_long_set(&(descs[_DESCS_COUNT(descbits) - 1].state_var), DESC0_SV(descbits)); + descs[_DESCS_COUNT(descbits) - 1].text_blk_lpos.begin = FAILED_LPOS; + descs[_DESCS_COUNT(descbits) - 1].text_blk_lpos.next = FAILED_LPOS; + + infos[0].seq = -(u64)_DESCS_COUNT(descbits); + infos[_DESCS_COUNT(descbits) - 1].seq = 0; +} + +/** + * prb_record_text_space() - Query the full actual used ringbuffer space for + * the text data of a reserved entry. + * + * @e: The successfully reserved entry to query. + * + * This is the public function available to writers to see how much actual + * space is used in the ringbuffer to store the text data of the specified + * entry. + * + * This function is only valid if @e has been successfully reserved using + * prb_reserve(). + * + * Context: Any context. + * Return: The size in bytes used by the text data of the associated record. + */ +unsigned int prb_record_text_space(struct prb_reserved_entry *e) +{ + return e->text_space; +} diff --git a/kernel/printk/printk_ringbuffer.h b/kernel/printk/printk_ringbuffer.h new file mode 100644 index 000000000..18cd25e48 --- /dev/null +++ b/kernel/printk/printk_ringbuffer.h @@ -0,0 +1,384 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _KERNEL_PRINTK_RINGBUFFER_H +#define _KERNEL_PRINTK_RINGBUFFER_H + +#include <linux/atomic.h> +#include <linux/dev_printk.h> + +/* + * Meta information about each stored message. + * + * All fields are set by the printk code except for @seq, which is + * set by the ringbuffer code. + */ +struct printk_info { + u64 seq; /* sequence number */ + u64 ts_nsec; /* timestamp in nanoseconds */ + u16 text_len; /* length of text message */ + u8 facility; /* syslog facility */ + u8 flags:5; /* internal record flags */ + u8 level:3; /* syslog level */ + u32 caller_id; /* thread id or processor id */ + + struct dev_printk_info dev_info; +}; + +/* + * A structure providing the buffers, used by writers and readers. + * + * Writers: + * Using prb_rec_init_wr(), a writer sets @text_buf_size before calling + * prb_reserve(). On success, prb_reserve() sets @info and @text_buf to + * buffers reserved for that writer. + * + * Readers: + * Using prb_rec_init_rd(), a reader sets all fields before calling + * prb_read_valid(). Note that the reader provides the @info and @text_buf, + * buffers. On success, the struct pointed to by @info will be filled and + * the char array pointed to by @text_buf will be filled with text data. + */ +struct printk_record { + struct printk_info *info; + char *text_buf; + unsigned int text_buf_size; +}; + +/* Specifies the logical position and span of a data block. */ +struct prb_data_blk_lpos { + unsigned long begin; + unsigned long next; +}; + +/* + * A descriptor: the complete meta-data for a record. + * + * @state_var: A bitwise combination of descriptor ID and descriptor state. + */ +struct prb_desc { + atomic_long_t state_var; + struct prb_data_blk_lpos text_blk_lpos; +}; + +/* A ringbuffer of "ID + data" elements. */ +struct prb_data_ring { + unsigned int size_bits; + char *data; + atomic_long_t head_lpos; + atomic_long_t tail_lpos; +}; + +/* A ringbuffer of "struct prb_desc" elements. */ +struct prb_desc_ring { + unsigned int count_bits; + struct prb_desc *descs; + struct printk_info *infos; + atomic_long_t head_id; + atomic_long_t tail_id; + atomic_long_t last_finalized_id; +}; + +/* + * The high level structure representing the printk ringbuffer. + * + * @fail: Count of failed prb_reserve() calls where not even a data-less + * record was created. + */ +struct printk_ringbuffer { + struct prb_desc_ring desc_ring; + struct prb_data_ring text_data_ring; + atomic_long_t fail; +}; + +/* + * Used by writers as a reserve/commit handle. + * + * @rb: Ringbuffer where the entry is reserved. + * @irqflags: Saved irq flags to restore on entry commit. + * @id: ID of the reserved descriptor. + * @text_space: Total occupied buffer space in the text data ring, including + * ID, alignment padding, and wrapping data blocks. + * + * This structure is an opaque handle for writers. Its contents are only + * to be used by the ringbuffer implementation. + */ +struct prb_reserved_entry { + struct printk_ringbuffer *rb; + unsigned long irqflags; + unsigned long id; + unsigned int text_space; +}; + +/* The possible responses of a descriptor state-query. */ +enum desc_state { + desc_miss = -1, /* ID mismatch (pseudo state) */ + desc_reserved = 0x0, /* reserved, in use by writer */ + desc_committed = 0x1, /* committed by writer, could get reopened */ + desc_finalized = 0x2, /* committed, no further modification allowed */ + desc_reusable = 0x3, /* free, not yet used by any writer */ +}; + +#define _DATA_SIZE(sz_bits) (1UL << (sz_bits)) +#define _DESCS_COUNT(ct_bits) (1U << (ct_bits)) +#define DESC_SV_BITS (sizeof(unsigned long) * 8) +#define DESC_FLAGS_SHIFT (DESC_SV_BITS - 2) +#define DESC_FLAGS_MASK (3UL << DESC_FLAGS_SHIFT) +#define DESC_STATE(sv) (3UL & (sv >> DESC_FLAGS_SHIFT)) +#define DESC_SV(id, state) (((unsigned long)state << DESC_FLAGS_SHIFT) | id) +#define DESC_ID_MASK (~DESC_FLAGS_MASK) +#define DESC_ID(sv) ((sv) & DESC_ID_MASK) +#define FAILED_LPOS 0x1 +#define NO_LPOS 0x3 + +#define FAILED_BLK_LPOS \ +{ \ + .begin = FAILED_LPOS, \ + .next = FAILED_LPOS, \ +} + +/* + * Descriptor Bootstrap + * + * The descriptor array is minimally initialized to allow immediate usage + * by readers and writers. The requirements that the descriptor array + * initialization must satisfy: + * + * Req1 + * The tail must point to an existing (committed or reusable) descriptor. + * This is required by the implementation of prb_first_seq(). + * + * Req2 + * Readers must see that the ringbuffer is initially empty. + * + * Req3 + * The first record reserved by a writer is assigned sequence number 0. + * + * To satisfy Req1, the tail initially points to a descriptor that is + * minimally initialized (having no data block, i.e. data-less with the + * data block's lpos @begin and @next values set to FAILED_LPOS). + * + * To satisfy Req2, the initial tail descriptor is initialized to the + * reusable state. Readers recognize reusable descriptors as existing + * records, but skip over them. + * + * To satisfy Req3, the last descriptor in the array is used as the initial + * head (and tail) descriptor. This allows the first record reserved by a + * writer (head + 1) to be the first descriptor in the array. (Only the first + * descriptor in the array could have a valid sequence number of 0.) + * + * The first time a descriptor is reserved, it is assigned a sequence number + * with the value of the array index. A "first time reserved" descriptor can + * be recognized because it has a sequence number of 0 but does not have an + * index of 0. (Only the first descriptor in the array could have a valid + * sequence number of 0.) After the first reservation, all future reservations + * (recycling) simply involve incrementing the sequence number by the array + * count. + * + * Hack #1 + * Only the first descriptor in the array is allowed to have the sequence + * number 0. In this case it is not possible to recognize if it is being + * reserved the first time (set to index value) or has been reserved + * previously (increment by the array count). This is handled by _always_ + * incrementing the sequence number by the array count when reserving the + * first descriptor in the array. In order to satisfy Req3, the sequence + * number of the first descriptor in the array is initialized to minus + * the array count. Then, upon the first reservation, it is incremented + * to 0, thus satisfying Req3. + * + * Hack #2 + * prb_first_seq() can be called at any time by readers to retrieve the + * sequence number of the tail descriptor. However, due to Req2 and Req3, + * initially there are no records to report the sequence number of + * (sequence numbers are u64 and there is nothing less than 0). To handle + * this, the sequence number of the initial tail descriptor is initialized + * to 0. Technically this is incorrect, because there is no record with + * sequence number 0 (yet) and the tail descriptor is not the first + * descriptor in the array. But it allows prb_read_valid() to correctly + * report the existence of a record for _any_ given sequence number at all + * times. Bootstrapping is complete when the tail is pushed the first + * time, thus finally pointing to the first descriptor reserved by a + * writer, which has the assigned sequence number 0. + */ + +/* + * Initiating Logical Value Overflows + * + * Both logical position (lpos) and ID values can be mapped to array indexes + * but may experience overflows during the lifetime of the system. To ensure + * that printk_ringbuffer can handle the overflows for these types, initial + * values are chosen that map to the correct initial array indexes, but will + * result in overflows soon. + * + * BLK0_LPOS + * The initial @head_lpos and @tail_lpos for data rings. It is at index + * 0 and the lpos value is such that it will overflow on the first wrap. + * + * DESC0_ID + * The initial @head_id and @tail_id for the desc ring. It is at the last + * index of the descriptor array (see Req3 above) and the ID value is such + * that it will overflow on the second wrap. + */ +#define BLK0_LPOS(sz_bits) (-(_DATA_SIZE(sz_bits))) +#define DESC0_ID(ct_bits) DESC_ID(-(_DESCS_COUNT(ct_bits) + 1)) +#define DESC0_SV(ct_bits) DESC_SV(DESC0_ID(ct_bits), desc_reusable) + +/* + * Define a ringbuffer with an external text data buffer. The same as + * DEFINE_PRINTKRB() but requires specifying an external buffer for the + * text data. + * + * Note: The specified external buffer must be of the size: + * 2 ^ (descbits + avgtextbits) + */ +#define _DEFINE_PRINTKRB(name, descbits, avgtextbits, text_buf) \ +static struct prb_desc _##name##_descs[_DESCS_COUNT(descbits)] = { \ + /* the initial head and tail */ \ + [_DESCS_COUNT(descbits) - 1] = { \ + /* reusable */ \ + .state_var = ATOMIC_INIT(DESC0_SV(descbits)), \ + /* no associated data block */ \ + .text_blk_lpos = FAILED_BLK_LPOS, \ + }, \ +}; \ +static struct printk_info _##name##_infos[_DESCS_COUNT(descbits)] = { \ + /* this will be the first record reserved by a writer */ \ + [0] = { \ + /* will be incremented to 0 on the first reservation */ \ + .seq = -(u64)_DESCS_COUNT(descbits), \ + }, \ + /* the initial head and tail */ \ + [_DESCS_COUNT(descbits) - 1] = { \ + /* reports the first seq value during the bootstrap phase */ \ + .seq = 0, \ + }, \ +}; \ +static struct printk_ringbuffer name = { \ + .desc_ring = { \ + .count_bits = descbits, \ + .descs = &_##name##_descs[0], \ + .infos = &_##name##_infos[0], \ + .head_id = ATOMIC_INIT(DESC0_ID(descbits)), \ + .tail_id = ATOMIC_INIT(DESC0_ID(descbits)), \ + .last_finalized_id = ATOMIC_INIT(DESC0_ID(descbits)), \ + }, \ + .text_data_ring = { \ + .size_bits = (avgtextbits) + (descbits), \ + .data = text_buf, \ + .head_lpos = ATOMIC_LONG_INIT(BLK0_LPOS((avgtextbits) + (descbits))), \ + .tail_lpos = ATOMIC_LONG_INIT(BLK0_LPOS((avgtextbits) + (descbits))), \ + }, \ + .fail = ATOMIC_LONG_INIT(0), \ +} + +/** + * DEFINE_PRINTKRB() - Define a ringbuffer. + * + * @name: The name of the ringbuffer variable. + * @descbits: The number of descriptors as a power-of-2 value. + * @avgtextbits: The average text data size per record as a power-of-2 value. + * + * This is a macro for defining a ringbuffer and all internal structures + * such that it is ready for immediate use. See _DEFINE_PRINTKRB() for a + * variant where the text data buffer can be specified externally. + */ +#define DEFINE_PRINTKRB(name, descbits, avgtextbits) \ +static char _##name##_text[1U << ((avgtextbits) + (descbits))] \ + __aligned(__alignof__(unsigned long)); \ +_DEFINE_PRINTKRB(name, descbits, avgtextbits, &_##name##_text[0]) + +/* Writer Interface */ + +/** + * prb_rec_init_wr() - Initialize a buffer for writing records. + * + * @r: The record to initialize. + * @text_buf_size: The needed text buffer size. + */ +static inline void prb_rec_init_wr(struct printk_record *r, + unsigned int text_buf_size) +{ + r->info = NULL; + r->text_buf = NULL; + r->text_buf_size = text_buf_size; +} + +bool prb_reserve(struct prb_reserved_entry *e, struct printk_ringbuffer *rb, + struct printk_record *r); +bool prb_reserve_in_last(struct prb_reserved_entry *e, struct printk_ringbuffer *rb, + struct printk_record *r, u32 caller_id, unsigned int max_size); +void prb_commit(struct prb_reserved_entry *e); +void prb_final_commit(struct prb_reserved_entry *e); + +void prb_init(struct printk_ringbuffer *rb, + char *text_buf, unsigned int text_buf_size, + struct prb_desc *descs, unsigned int descs_count_bits, + struct printk_info *infos); +unsigned int prb_record_text_space(struct prb_reserved_entry *e); + +/* Reader Interface */ + +/** + * prb_rec_init_rd() - Initialize a buffer for reading records. + * + * @r: The record to initialize. + * @info: A buffer to store record meta-data. + * @text_buf: A buffer to store text data. + * @text_buf_size: The size of @text_buf. + * + * Initialize all the fields that a reader is interested in. All arguments + * (except @r) are optional. Only record data for arguments that are + * non-NULL or non-zero will be read. + */ +static inline void prb_rec_init_rd(struct printk_record *r, + struct printk_info *info, + char *text_buf, unsigned int text_buf_size) +{ + r->info = info; + r->text_buf = text_buf; + r->text_buf_size = text_buf_size; +} + +/** + * prb_for_each_record() - Iterate over the records of a ringbuffer. + * + * @from: The sequence number to begin with. + * @rb: The ringbuffer to iterate over. + * @s: A u64 to store the sequence number on each iteration. + * @r: A printk_record to store the record on each iteration. + * + * This is a macro for conveniently iterating over a ringbuffer. + * Note that @s may not be the sequence number of the record on each + * iteration. For the sequence number, @r->info->seq should be checked. + * + * Context: Any context. + */ +#define prb_for_each_record(from, rb, s, r) \ +for ((s) = from; prb_read_valid(rb, s, r); (s) = (r)->info->seq + 1) + +/** + * prb_for_each_info() - Iterate over the meta data of a ringbuffer. + * + * @from: The sequence number to begin with. + * @rb: The ringbuffer to iterate over. + * @s: A u64 to store the sequence number on each iteration. + * @i: A printk_info to store the record meta data on each iteration. + * @lc: An unsigned int to store the text line count of each record. + * + * This is a macro for conveniently iterating over a ringbuffer. + * Note that @s may not be the sequence number of the record on each + * iteration. For the sequence number, @r->info->seq should be checked. + * + * Context: Any context. + */ +#define prb_for_each_info(from, rb, s, i, lc) \ +for ((s) = from; prb_read_valid_info(rb, s, i, lc); (s) = (i)->seq + 1) + +bool prb_read_valid(struct printk_ringbuffer *rb, u64 seq, + struct printk_record *r); +bool prb_read_valid_info(struct printk_ringbuffer *rb, u64 seq, + struct printk_info *info, unsigned int *line_count); + +u64 prb_first_valid_seq(struct printk_ringbuffer *rb); +u64 prb_next_seq(struct printk_ringbuffer *rb); + +#endif /* _KERNEL_PRINTK_RINGBUFFER_H */ diff --git a/kernel/printk/printk_safe.c b/kernel/printk/printk_safe.c new file mode 100644 index 000000000..6d10927a0 --- /dev/null +++ b/kernel/printk/printk_safe.c @@ -0,0 +1,47 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * printk_safe.c - Safe printk for printk-deadlock-prone contexts + */ + +#include <linux/preempt.h> +#include <linux/kdb.h> +#include <linux/smp.h> +#include <linux/cpumask.h> +#include <linux/printk.h> +#include <linux/kprobes.h> + +#include "internal.h" + +static DEFINE_PER_CPU(int, printk_context); + +/* Can be preempted by NMI. */ +void __printk_safe_enter(void) +{ + this_cpu_inc(printk_context); +} + +/* Can be preempted by NMI. */ +void __printk_safe_exit(void) +{ + this_cpu_dec(printk_context); +} + +asmlinkage int vprintk(const char *fmt, va_list args) +{ +#ifdef CONFIG_KGDB_KDB + /* Allow to pass printk() to kdb but avoid a recursion. */ + if (unlikely(kdb_trap_printk && kdb_printf_cpu < 0)) + return vkdb_printf(KDB_MSGSRC_PRINTK, fmt, args); +#endif + + /* + * Use the main logbuf even in NMI. But avoid calling console + * drivers that might have their own locks. + */ + if (this_cpu_read(printk_context) || in_nmi()) + return vprintk_deferred(fmt, args); + + /* No obstacles. */ + return vprintk_default(fmt, args); +} +EXPORT_SYMBOL(vprintk); diff --git a/kernel/printk/sysctl.c b/kernel/printk/sysctl.c new file mode 100644 index 000000000..c228343ee --- /dev/null +++ b/kernel/printk/sysctl.c @@ -0,0 +1,85 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * sysctl.c: General linux system control interface + */ + +#include <linux/sysctl.h> +#include <linux/printk.h> +#include <linux/capability.h> +#include <linux/ratelimit.h> +#include "internal.h" + +static const int ten_thousand = 10000; + +static int proc_dointvec_minmax_sysadmin(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) +{ + if (write && !capable(CAP_SYS_ADMIN)) + return -EPERM; + + return proc_dointvec_minmax(table, write, buffer, lenp, ppos); +} + +static struct ctl_table printk_sysctls[] = { + { + .procname = "printk", + .data = &console_loglevel, + .maxlen = 4*sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "printk_ratelimit", + .data = &printk_ratelimit_state.interval, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + { + .procname = "printk_ratelimit_burst", + .data = &printk_ratelimit_state.burst, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "printk_delay", + .data = &printk_delay_msec, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = (void *)&ten_thousand, + }, + { + .procname = "printk_devkmsg", + .data = devkmsg_log_str, + .maxlen = DEVKMSG_STR_MAX_SIZE, + .mode = 0644, + .proc_handler = devkmsg_sysctl_set_loglvl, + }, + { + .procname = "dmesg_restrict", + .data = &dmesg_restrict, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax_sysadmin, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + { + .procname = "kptr_restrict", + .data = &kptr_restrict, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax_sysadmin, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_TWO, + }, + {} +}; + +void __init printk_sysctl_init(void) +{ + register_sysctl_init("kernel", printk_sysctls); +} |