Merge branch 'rework/nbcon-base' into for-linus

include/linux/console.h

@@ -156,6 +156,8 @@ static inline int con_debug_leave(void)
  *			/dev/kmesg which requires a larger output buffer.
  * @CON_SUSPENDED:	Indicates if a console is suspended. If true, the
  *			printing callbacks must not be called.
+ * @CON_NBCON:		Console can operate outside of the legacy style console_lock
+ *			constraints.
  */
 enum cons_flags {
 	CON_PRINTBUFFER		= BIT(0),
@@ -166,6 +168,111 @@ enum cons_flags {
 	CON_BRL			= BIT(5),
 	CON_EXTENDED		= BIT(6),
 	CON_SUSPENDED		= BIT(7),
+	CON_NBCON		= BIT(8),
+};
+
+/**
+ * struct nbcon_state - console state for nbcon consoles
+ * @atom:	Compound of the state fields for atomic operations
+ *
+ * @req_prio:		The priority of a handover request
+ * @prio:		The priority of the current owner
+ * @unsafe:		Console is busy in a non takeover region
+ * @unsafe_takeover:	A hostile takeover in an unsafe state happened in the
+ *			past. The console cannot be safe until re-initialized.
+ * @cpu:		The CPU on which the owner runs
+ *
+ * To be used for reading and preparing of the value stored in the nbcon
+ * state variable @console::nbcon_state.
+ *
+ * The @prio and @req_prio fields are particularly important to allow
+ * spin-waiting to timeout and give up without the risk of a waiter being
+ * assigned the lock after giving up.
+ */
+struct nbcon_state {
+	union {
+		unsigned int	atom;
+		struct {
+			unsigned int prio		:  2;
+			unsigned int req_prio		:  2;
+			unsigned int unsafe		:  1;
+			unsigned int unsafe_takeover	:  1;
+			unsigned int cpu		: 24;
+		};
+	};
+};
+
+/*
+ * The nbcon_state struct is used to easily create and interpret values that
+ * are stored in the @console::nbcon_state variable. Ensure this struct stays
+ * within the size boundaries of the atomic variable's underlying type in
+ * order to avoid any accidental truncation.
+ */
+static_assert(sizeof(struct nbcon_state) <= sizeof(int));
+
+/**
+ * nbcon_prio - console owner priority for nbcon consoles
+ * @NBCON_PRIO_NONE:		Unused
+ * @NBCON_PRIO_NORMAL:		Normal (non-emergency) usage
+ * @NBCON_PRIO_EMERGENCY:	Emergency output (WARN/OOPS...)
+ * @NBCON_PRIO_PANIC:		Panic output
+ * @NBCON_PRIO_MAX:		The number of priority levels
+ *
+ * A higher priority context can takeover the console when it is
+ * in the safe state. The final attempt to flush consoles in panic()
+ * can be allowed to do so even in an unsafe state (Hope and pray).
+ */
+enum nbcon_prio {
+	NBCON_PRIO_NONE = 0,
+	NBCON_PRIO_NORMAL,
+	NBCON_PRIO_EMERGENCY,
+	NBCON_PRIO_PANIC,
+	NBCON_PRIO_MAX,
+};
+
+struct console;
+struct printk_buffers;
+
+/**
+ * struct nbcon_context - Context for console acquire/release
+ * @console:			The associated console
+ * @spinwait_max_us:		Limit for spin-wait acquire
+ * @prio:			Priority of the context
+ * @allow_unsafe_takeover:	Allow performing takeover even if unsafe. Can
+ *				be used only with NBCON_PRIO_PANIC @prio. It
+ *				might cause a system freeze when the console
+ *				is used later.
+ * @backlog:			Ringbuffer has pending records
+ * @pbufs:			Pointer to the text buffer for this context
+ * @seq:			The sequence number to print for this context
+ */
+struct nbcon_context {
+	/* members set by caller */
+	struct console		*console;
+	unsigned int		spinwait_max_us;
+	enum nbcon_prio		prio;
+	unsigned int		allow_unsafe_takeover	: 1;
+
+	/* members set by emit */
+	unsigned int		backlog			: 1;
+
+	/* members set by acquire */
+	struct printk_buffers	*pbufs;
+	u64			seq;
+};
+
+/**
+ * struct nbcon_write_context - Context handed to the nbcon write callbacks
+ * @ctxt:		The core console context
+ * @outbuf:		Pointer to the text buffer for output
+ * @len:		Length to write
+ * @unsafe_takeover:	If a hostile takeover in an unsafe state has occurred
+ */
+struct nbcon_write_context {
+	struct nbcon_context	__private ctxt;
+	char			*outbuf;
+	unsigned int		len;
+	bool			unsafe_takeover;
 };
 
 /**
@@ -187,6 +294,11 @@ enum cons_flags {
  * @dropped:		Number of unreported dropped ringbuffer records
  * @data:		Driver private data
  * @node:		hlist node for the console list
+ *
+ * @write_atomic:	Write callback for atomic context
+ * @nbcon_state:	State for nbcon consoles
+ * @nbcon_seq:		Sequence number of the next record for nbcon to print
+ * @pbufs:		Pointer to nbcon private buffer
  */
 struct console {
 	char			name[16];
@@ -206,6 +318,13 @@ struct console {
 	unsigned long		dropped;
 	void			*data;
 	struct hlist_node	node;
+
+	/* nbcon console specific members */
+	bool			(*write_atomic)(struct console *con,
+						struct nbcon_write_context *wctxt);
+	atomic_t		__private nbcon_state;
+	atomic_long_t		__private nbcon_seq;
+	struct printk_buffers	*pbufs;
 };
 
 #ifdef CONFIG_LOCKDEP
@@ -332,6 +451,16 @@ static inline bool console_is_registered(const struct console *con)
 	lockdep_assert_console_list_lock_held();			\
 	hlist_for_each_entry(con, &console_list, node)
 
+#ifdef CONFIG_PRINTK
+extern bool nbcon_can_proceed(struct nbcon_write_context *wctxt);
+extern bool nbcon_enter_unsafe(struct nbcon_write_context *wctxt);
+extern bool nbcon_exit_unsafe(struct nbcon_write_context *wctxt);
+#else
+static inline bool nbcon_can_proceed(struct nbcon_write_context *wctxt) { return false; }
+static inline bool nbcon_enter_unsafe(struct nbcon_write_context *wctxt) { return false; }
+static inline bool nbcon_exit_unsafe(struct nbcon_write_context *wctxt) { return false; }
+#endif
+
 extern int console_set_on_cmdline;
 extern struct console *early_console;
 

kernel/printk/Makefile

 # SPDX-License-Identifier: GPL-2.0-only
 obj-y	= printk.o
-obj-$(CONFIG_PRINTK)	+= printk_safe.o
+obj-$(CONFIG_PRINTK)	+= printk_safe.o nbcon.o
 obj-$(CONFIG_A11Y_BRAILLE_CONSOLE)	+= braille.o
 obj-$(CONFIG_PRINTK_INDEX)	+= index.o
 

kernel/printk/internal.h

@@ -3,6 +3,8 @@
  * internal.h - printk internal definitions
  */
 #include <linux/percpu.h>
+#include <linux/console.h>
+#include "printk_ringbuffer.h"
 
 #if defined(CONFIG_PRINTK) && defined(CONFIG_SYSCTL)
 void __init printk_sysctl_init(void);
@@ -12,6 +14,12 @@ int devkmsg_sysctl_set_loglvl(struct ctl_table *table, int write,
 #define printk_sysctl_init() do { } while (0)
 #endif
 
+#define con_printk(lvl, con, fmt, ...)				\
+	printk(lvl pr_fmt("%s%sconsole [%s%d] " fmt),		\
+		(con->flags & CON_NBCON) ? "" : "legacy ",	\
+		(con->flags & CON_BOOT) ? "boot" : "",		\
+		con->name, con->index, ##__VA_ARGS__)
+
 #ifdef CONFIG_PRINTK
 
 #ifdef CONFIG_PRINTK_CALLER
@@ -35,6 +43,8 @@ enum printk_info_flags {
 	LOG_CONT	= 8,	/* text is a fragment of a continuation line */
 };
 
+extern struct printk_ringbuffer *prb;
+
 __printf(4, 0)
 int vprintk_store(int facility, int level,
 		  const struct dev_printk_info *dev_info,
@@ -61,6 +71,13 @@ void defer_console_output(void);
 
 u16 printk_parse_prefix(const char *text, int *level,
 			enum printk_info_flags *flags);
+
+u64 nbcon_seq_read(struct console *con);
+void nbcon_seq_force(struct console *con, u64 seq);
+bool nbcon_alloc(struct console *con);
+void nbcon_init(struct console *con);
+void nbcon_free(struct console *con);
+
 #else
 
 #define PRINTK_PREFIX_MAX	0
@@ -76,8 +93,16 @@ u16 printk_parse_prefix(const char *text, int *level,
 #define printk_safe_exit_irqrestore(flags) local_irq_restore(flags)
 
 static inline bool printk_percpu_data_ready(void) { return false; }
+static inline u64 nbcon_seq_read(struct console *con) { return 0; }
+static inline void nbcon_seq_force(struct console *con, u64 seq) { }
+static inline bool nbcon_alloc(struct console *con) { return false; }
+static inline void nbcon_init(struct console *con) { }
+static inline void nbcon_free(struct console *con) { }
+
 #endif /* CONFIG_PRINTK */
 
+extern struct printk_buffers printk_shared_pbufs;
+
 /**
  * struct printk_buffers - Buffers to read/format/output printk messages.
  * @outbuf:	After formatting, contains text to output.
@@ -105,3 +130,9 @@ struct printk_message {
 };
 
 bool other_cpu_in_panic(void);
+bool printk_get_next_message(struct printk_message *pmsg, u64 seq,
+			     bool is_extended, bool may_supress);
+
+#ifdef CONFIG_PRINTK
+void console_prepend_dropped(struct printk_message *pmsg, unsigned long dropped);
+#endif

kernel/printk/printk.c

@@ -102,12 +102,6 @@ DEFINE_STATIC_SRCU(console_srcu);
  */
 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"
@@ -445,6 +439,12 @@ static int console_msg_format = MSG_FORMAT_DEFAULT;
 static DEFINE_MUTEX(syslog_lock);
 
 #ifdef CONFIG_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;
+
 DECLARE_WAIT_QUEUE_HEAD(log_wait);
 /* All 3 protected by @syslog_lock. */
 /* the next printk record to read by syslog(READ) or /proc/kmsg */
@@ -494,7 +494,7 @@ _DEFINE_PRINTKRB(printk_rb_static, CONFIG_LOG_BUF_SHIFT - PRB_AVGBITS,
 
 static struct printk_ringbuffer printk_rb_dynamic;
 
-static struct printk_ringbuffer *prb = &printk_rb_static;
+struct printk_ringbuffer *prb = &printk_rb_static;
 
 /*
  * We cannot access per-CPU data (e.g. per-CPU flush irq_work) before
@@ -698,9 +698,6 @@ static ssize_t msg_print_ext_body(char *buf, size_t size,
 	return len;
 }
 
-static bool printk_get_next_message(struct printk_message *pmsg, u64 seq,
-				    bool is_extended, bool may_supress);
-
 /* /dev/kmsg - userspace message inject/listen interface */
 struct devkmsg_user {
 	atomic64_t seq;
@@ -2348,22 +2345,6 @@ static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progre
 
 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(int cookie) { return 0; }
-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; }
 
@@ -2717,6 +2698,8 @@ static void __console_unlock(void)
 	up_console_sem();
 }
 
+#ifdef CONFIG_PRINTK
+
 /*
  * Prepend the message in @pmsg->pbufs->outbuf with a "dropped message". This
  * is achieved by shifting the existing message over and inserting the dropped
@@ -2731,8 +2714,7 @@ static void __console_unlock(void)
  *
  * If @pmsg->pbufs->outbuf is modified, @pmsg->outbuf_len is updated.
  */
-#ifdef CONFIG_PRINTK
-static void console_prepend_dropped(struct printk_message *pmsg, unsigned long dropped)
+void console_prepend_dropped(struct printk_message *pmsg, unsigned long dropped)
 {
 	struct printk_buffers *pbufs = pmsg->pbufs;
 	const size_t scratchbuf_sz = sizeof(pbufs->scratchbuf);
@@ -2763,9 +2745,6 @@ static void console_prepend_dropped(struct printk_message *pmsg, unsigned long d
 	memcpy(outbuf, scratchbuf, len);
 	pmsg->outbuf_len += len;
 }
-#else
-#define console_prepend_dropped(pmsg, dropped)
-#endif /* CONFIG_PRINTK */
 
 /*
  * Read and format the specified record (or a later record if the specified
@@ -2786,8 +2765,8 @@ static void console_prepend_dropped(struct printk_message *pmsg, unsigned long d
  * of @pmsg are valid. (See the documentation of struct printk_message
  * for information about the @pmsg fields.)
  */
-static bool printk_get_next_message(struct printk_message *pmsg, u64 seq,
-				    bool is_extended, bool may_suppress)
+bool printk_get_next_message(struct printk_message *pmsg, u64 seq,
+			     bool is_extended, bool may_suppress)
 {
 	static int panic_console_dropped;
 
@@ -2845,6 +2824,13 @@ static bool printk_get_next_message(struct printk_message *pmsg, u64 seq,
 	return true;
 }
 
+/*
+ * Used as the printk buffers for non-panic, serialized console printing.
+ * This is for legacy (!CON_NBCON) as well as all boot (CON_BOOT) consoles.
+ * Its usage requires the console_lock held.
+ */
+struct printk_buffers printk_shared_pbufs;
+
 /*
  * Print one record for the given console. The record printed is whatever
  * record is the next available record for the given console.
@@ -2862,12 +2848,10 @@ static bool printk_get_next_message(struct printk_message *pmsg, u64 seq,
  */
 static bool console_emit_next_record(struct console *con, bool *handover, int cookie)
 {
-	static struct printk_buffers pbufs;
-
 	bool is_extended = console_srcu_read_flags(con) & CON_EXTENDED;
-	char *outbuf = &pbufs.outbuf[0];
+	char *outbuf = &printk_shared_pbufs.outbuf[0];
 	struct printk_message pmsg = {
-		.pbufs = &pbufs,
+		.pbufs = &printk_shared_pbufs,
 	};
 	unsigned long flags;
 
@@ -2918,6 +2902,16 @@ static bool console_emit_next_record(struct console *con, bool *handover, int co
 	return true;
 }
 
+#else
+
+static bool console_emit_next_record(struct console *con, bool *handover, int cookie)
+{
+	*handover = false;
+	return false;
+}
+
+#endif /* CONFIG_PRINTK */
+
 /*
  * Print out all remaining records to all consoles.
  *
@@ -3162,6 +3156,7 @@ void console_flush_on_panic(enum con_flush_mode mode)
 
 	if (mode == CONSOLE_REPLAY_ALL) {
 		struct console *c;
+		short flags;
 		int cookie;
 		u64 seq;
 
@@ -3169,11 +3164,17 @@ void console_flush_on_panic(enum con_flush_mode mode)
 
 		cookie = console_srcu_read_lock();
 		for_each_console_srcu(c) {
-			/*
-			 * This is an unsynchronized assignment, but the
-			 * kernel is in "hope and pray" mode anyway.
-			 */
-			c->seq = seq;
+			flags = console_srcu_read_flags(c);
+
+			if (flags & CON_NBCON) {
+				nbcon_seq_force(c, seq);
+			} else {
+				/*
+				 * This is an unsynchronized assignment. On
+				 * panic legacy consoles are only best effort.
+				 */
+				c->seq = seq;
+			}
 		}
 		console_srcu_read_unlock(cookie);
 	}
@@ -3325,11 +3326,6 @@ static void try_enable_default_console(struct console *newcon)
 		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__)
-
 static void console_init_seq(struct console *newcon, bool bootcon_registered)
 {
 	struct console *con;
@@ -3443,6 +3439,15 @@ void register_console(struct console *newcon)
 		goto unlock;
 	}
 
+	if (newcon->flags & CON_NBCON) {
+		/*
+		 * Ensure the nbcon console buffers can be allocated
+		 * before modifying any global data.
+		 */
+		if (!nbcon_alloc(newcon))
+			goto unlock;
+	}
+
 	/*
 	 * See if we want to enable this console driver by default.
 	 *
@@ -3470,8 +3475,11 @@ void register_console(struct console *newcon)
 		err = try_enable_preferred_console(newcon, false);
 
 	/* printk() messages are not printed to the Braille console. */
-	if (err || newcon->flags & CON_BRL)
+	if (err || newcon->flags & CON_BRL) {
+		if (newcon->flags & CON_NBCON)
+			nbcon_free(newcon);
 		goto unlock;
+	}
 
 	/*
 	 * If we have a bootconsole, and are switching to a real console,
@@ -3487,6 +3495,9 @@ void register_console(struct console *newcon)
 	newcon->dropped = 0;
 	console_init_seq(newcon, bootcon_registered);
 
+	if (newcon->flags & CON_NBCON)
+		nbcon_init(newcon);
+
 	/*
 	 * Put this console in the list - keep the
 	 * preferred driver at the head of the list.
@@ -3578,6 +3589,9 @@ static int unregister_console_locked(struct console *console)
 	 */
 	synchronize_srcu(&console_srcu);
 
+	if (console->flags & CON_NBCON)
+		nbcon_free(console);
+
 	console_sysfs_notify();
 
 	if (console->exit)
@@ -3732,6 +3746,7 @@ static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progre
 	struct console *c;
 	u64 last_diff = 0;
 	u64 printk_seq;
+	short flags;
 	int cookie;
 	u64 diff;
 	u64 seq;
@@ -3762,6 +3777,9 @@ static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progre
 		for_each_console_srcu(c) {
 			if (con && con != c)
 				continue;
+
+			flags = console_srcu_read_flags(c);
+
 			/*
 			 * If consoles are not usable, it cannot be expected
 			 * that they make forward progress, so only increment
@@ -3769,7 +3787,13 @@ static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progre
 			 */
 			if (!console_is_usable(c))
 				continue;
-			printk_seq = c->seq;
+
+			if (flags & CON_NBCON) {
+				printk_seq = nbcon_seq_read(c);
+			} else {
+				printk_seq = c->seq;
+			}
+
 			if (printk_seq < seq)
 				diff += seq - printk_seq;
 		}