OpenVoiceOS/buildroot-external/patches/linux/0103-printk-nbcon-Add-acquire-release-logic.patch

From 48184a3bcad14f6c1a9813ab9dd376f02e540463 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Sat, 16 Sep 2023 21:26:01 +0206
Subject: [PATCH 103/195] printk: nbcon: Add acquire/release logic

Add per console acquire/release functionality.

The state of the console is maintained in the "nbcon_state" atomic
variable.

The console is locked when:

  - The 'prio' field contains the priority of the context that owns the
    console. Only higher priority contexts are allowed to take over the
    lock. A value of 0 (NBCON_PRIO_NONE) means the console is not locked.

  - The 'cpu' field denotes on which CPU the console is locked. It is used
    to prevent busy waiting on the same CPU. Also it informs the lock owner
    that it has lost the lock in a more complex scenario when the lock was
    taken over by a higher priority context, released, and taken on another
    CPU with the same priority as the interrupted owner.

The acquire mechanism uses a few more fields:

  - The 'req_prio' field is used by the handover approach to make the
    current owner aware that there is a context with a higher priority
    waiting for the friendly handover.

  - The 'unsafe' field allows to take over the console in a safe way in the
    middle of emitting a message. The field is set only when accessing some
    shared resources or when the console device is manipulated. It can be
    cleared, for example, after emitting one character when the console
    device is in a consistent state.

  - The 'unsafe_takeover' field is set when a hostile takeover took the
    console in an unsafe state. The console will stay in the unsafe state
    until re-initialized.

The acquire mechanism uses three approaches:

  1) Direct acquire when the console is not owned or is owned by a lower
     priority context and is in a safe state.

  2) Friendly handover mechanism uses a request/grant handshake. It is used
     when the current owner has lower priority and the console is in an
     unsafe state.

     The requesting context:

       a) Sets its priority into the 'req_prio' field.

       b) Waits (with a timeout) for the owning context to unlock the
          console.

       c) Takes the lock and clears the 'req_prio' field.

     The owning context:

       a) Observes the 'req_prio' field set on exit from the unsafe
          console state.

       b) Gives up console ownership by clearing the 'prio' field.

  3) Unsafe hostile takeover allows to take over the lock even when the
     console is an unsafe state. It is used only in panic() by the final
     attempt to flush consoles in a try and hope mode.

     Note that separate record buffers are used in panic(). As a result,
     the messages can be read and formatted without any risk even after
     using the hostile takeover in unsafe state.

The release function simply clears the 'prio' field.

All operations on @console::nbcon_state are atomic cmpxchg based to
handle concurrency.

The acquire/release functions implement only minimal policies:

  - Preference for higher priority contexts.
  - Protection of the panic CPU.

All other policy decisions must be made at the call sites:

  - What is marked as an unsafe section.
  - Whether to spin-wait if there is already an owner and the console is
    in an unsafe state.
  - Whether to attempt an unsafe hostile takeover.

The design allows to implement the well known:

    acquire()
    output_one_printk_record()
    release()

The output of one printk record might be interrupted with a higher priority
context. The new owner is supposed to reprint the entire interrupted record
from scratch.

Co-developed-by: John Ogness <john.ogness@linutronix.de>
Signed-off-by: John Ogness <john.ogness@linutronix.de>
Signed-off-by: Thomas Gleixner (Intel) <tglx@linutronix.de>
Signed-off-by: Petr Mladek <pmladek@suse.com>
Link: https://lore.kernel.org/r/20230916192007.608398-3-john.ogness@linutronix.de
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
 include/linux/console.h |  56 +++++
 kernel/printk/nbcon.c   | 497 ++++++++++++++++++++++++++++++++++++++++
 2 files changed, 553 insertions(+)

diff --git a/include/linux/console.h b/include/linux/console.h
index a2d37a7a98a8..98210fd01f18 100644
--- a/include/linux/console.h
+++ b/include/linux/console.h
@@ -175,13 +175,29 @@ enum cons_flags {
  * 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;
 		};
 	};
 };
@@ -194,6 +210,46 @@ struct nbcon_state {
  */
 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 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.
+ */
+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;
+};
+
 /**
  * struct console - The console descriptor structure
  * @name:		The name of the console driver
diff --git a/kernel/printk/nbcon.c b/kernel/printk/nbcon.c
index 63d24ca62ac5..a2a354f859f9 100644
--- a/kernel/printk/nbcon.c
+++ b/kernel/printk/nbcon.c
@@ -4,10 +4,98 @@
 
 #include <linux/kernel.h>
 #include <linux/console.h>
+#include <linux/delay.h>
 #include "internal.h"
 /*
  * Printk console printing implementation for consoles which does not depend
  * on the legacy style console_lock mechanism.
+ *
+ * The state of the console is maintained in the "nbcon_state" atomic
+ * variable.
+ *
+ * The console is locked when:
+ *
+ *   - The 'prio' field contains the priority of the context that owns the
+ *     console. Only higher priority contexts are allowed to take over the
+ *     lock. A value of 0 (NBCON_PRIO_NONE) means the console is not locked.
+ *
+ *   - The 'cpu' field denotes on which CPU the console is locked. It is used
+ *     to prevent busy waiting on the same CPU. Also it informs the lock owner
+ *     that it has lost the lock in a more complex scenario when the lock was
+ *     taken over by a higher priority context, released, and taken on another
+ *     CPU with the same priority as the interrupted owner.
+ *
+ * The acquire mechanism uses a few more fields:
+ *
+ *   - The 'req_prio' field is used by the handover approach to make the
+ *     current owner aware that there is a context with a higher priority
+ *     waiting for the friendly handover.
+ *
+ *   - The 'unsafe' field allows to take over the console in a safe way in the
+ *     middle of emitting a message. The field is set only when accessing some
+ *     shared resources or when the console device is manipulated. It can be
+ *     cleared, for example, after emitting one character when the console
+ *     device is in a consistent state.
+ *
+ *   - The 'unsafe_takeover' field is set when a hostile takeover took the
+ *     console in an unsafe state. The console will stay in the unsafe state
+ *     until re-initialized.
+ *
+ * The acquire mechanism uses three approaches:
+ *
+ *   1) Direct acquire when the console is not owned or is owned by a lower
+ *      priority context and is in a safe state.
+ *
+ *   2) Friendly handover mechanism uses a request/grant handshake. It is used
+ *      when the current owner has lower priority and the console is in an
+ *      unsafe state.
+ *
+ *      The requesting context:
+ *
+ *        a) Sets its priority into the 'req_prio' field.
+ *
+ *        b) Waits (with a timeout) for the owning context to unlock the
+ *           console.
+ *
+ *        c) Takes the lock and clears the 'req_prio' field.
+ *
+ *      The owning context:
+ *
+ *        a) Observes the 'req_prio' field set on exit from the unsafe
+ *           console state.
+ *
+ *        b) Gives up console ownership by clearing the 'prio' field.
+ *
+ *   3) Unsafe hostile takeover allows to take over the lock even when the
+ *      console is an unsafe state. It is used only in panic() by the final
+ *      attempt to flush consoles in a try and hope mode.
+ *
+ * The release function simply clears the 'prio' field.
+ *
+ * All operations on @console::nbcon_state are atomic cmpxchg based to
+ * handle concurrency.
+ *
+ * The acquire/release functions implement only minimal policies:
+ *
+ *   - Preference for higher priority contexts.
+ *   - Protection of the panic CPU.
+ *
+ * All other policy decisions must be made at the call sites:
+ *
+ *   - What is marked as an unsafe section.
+ *   - Whether to spin-wait if there is already an owner and the console is
+ *     in an unsafe state.
+ *   - Whether to attempt an unsafe hostile takeover.
+ *
+ * The design allows to implement the well known:
+ *
+ *     acquire()
+ *     output_one_printk_record()
+ *     release()
+ *
+ * The output of one printk record might be interrupted with a higher priority
+ * context. The new owner is supposed to reprint the entire interrupted record
+ * from scratch.
  */
 
 /**
@@ -47,6 +135,415 @@ static inline bool nbcon_state_try_cmpxchg(struct console *con, struct nbcon_sta
 	return atomic_try_cmpxchg(&ACCESS_PRIVATE(con, nbcon_state), &cur->atom, new->atom);
 }
 
+/**
+ * nbcon_context_try_acquire_direct - Try to acquire directly
+ * @ctxt:	The context of the caller
+ * @cur:	The current console state
+ *
+ * Acquire the console when it is released. Also acquire the console when
+ * the current owner has a lower priority and the console is in a safe state.
+ *
+ * Return:	0 on success. Otherwise, an error code on failure. Also @cur
+ *		is updated to the latest state when failed to modify it.
+ *
+ * Errors:
+ *
+ *	-EPERM:		A panic is in progress and this is not the panic CPU.
+ *			Or the current owner or waiter has the same or higher
+ *			priority. No acquire method can be successful in
+ *			this case.
+ *
+ *	-EBUSY:		The current owner has a lower priority but the console
+ *			in an unsafe state. The caller should try using
+ *			the handover acquire method.
+ */
+static int nbcon_context_try_acquire_direct(struct nbcon_context *ctxt,
+					    struct nbcon_state *cur)
+{
+	unsigned int cpu = smp_processor_id();
+	struct console *con = ctxt->console;
+	struct nbcon_state new;
+
+	do {
+		if (other_cpu_in_panic())
+			return -EPERM;
+
+		if (ctxt->prio <= cur->prio || ctxt->prio <= cur->req_prio)
+			return -EPERM;
+
+		if (cur->unsafe)
+			return -EBUSY;
+
+		/*
+		 * The console should never be safe for a direct acquire
+		 * if an unsafe hostile takeover has ever happened.
+		 */
+		WARN_ON_ONCE(cur->unsafe_takeover);
+
+		new.atom = cur->atom;
+		new.prio	= ctxt->prio;
+		new.req_prio	= NBCON_PRIO_NONE;
+		new.unsafe	= cur->unsafe_takeover;
+		new.cpu		= cpu;
+
+	} while (!nbcon_state_try_cmpxchg(con, cur, &new));
+
+	return 0;
+}
+
+static bool nbcon_waiter_matches(struct nbcon_state *cur, int expected_prio)
+{
+	/*
+	 * The request context is well defined by the @req_prio because:
+	 *
+	 * - Only a context with a higher priority can take over the request.
+	 * - There are only three priorities.
+	 * - Only one CPU is allowed to request PANIC priority.
+	 * - Lower priorities are ignored during panic() until reboot.
+	 *
+	 * As a result, the following scenario is *not* possible:
+	 *
+	 * 1. Another context with a higher priority directly takes ownership.
+	 * 2. The higher priority context releases the ownership.
+	 * 3. A lower priority context takes the ownership.
+	 * 4. Another context with the same priority as this context
+	 *    creates a request and starts waiting.
+	 */
+
+	return (cur->req_prio == expected_prio);
+}
+
+/**
+ * nbcon_context_try_acquire_requested - Try to acquire after having
+ *					 requested a handover
+ * @ctxt:	The context of the caller
+ * @cur:	The current console state
+ *
+ * This is a helper function for nbcon_context_try_acquire_handover().
+ * It is called when the console is in an unsafe state. The current
+ * owner will release the console on exit from the unsafe region.
+ *
+ * Return:	0 on success and @cur is updated to the new console state.
+ *		Otherwise an error code on failure.
+ *
+ * Errors:
+ *
+ *	-EPERM:		A panic is in progress and this is not the panic CPU
+ *			or this context is no longer the waiter.
+ *
+ *	-EBUSY:		The console is still locked. The caller should
+ *			continue waiting.
+ *
+ * Note: The caller must still remove the request when an error has occurred
+ *       except when this context is no longer the waiter.
+ */
+static int nbcon_context_try_acquire_requested(struct nbcon_context *ctxt,
+					       struct nbcon_state *cur)
+{
+	unsigned int cpu = smp_processor_id();
+	struct console *con = ctxt->console;
+	struct nbcon_state new;
+
+	/* Note that the caller must still remove the request! */
+	if (other_cpu_in_panic())
+		return -EPERM;
+
+	/*
+	 * Note that the waiter will also change if there was an unsafe
+	 * hostile takeover.
+	 */
+	if (!nbcon_waiter_matches(cur, ctxt->prio))
+		return -EPERM;
+
+	/* If still locked, caller should continue waiting. */
+	if (cur->prio != NBCON_PRIO_NONE)
+		return -EBUSY;
+
+	/*
+	 * The previous owner should have never released ownership
+	 * in an unsafe region.
+	 */
+	WARN_ON_ONCE(cur->unsafe);
+
+	new.atom = cur->atom;
+	new.prio	= ctxt->prio;
+	new.req_prio	= NBCON_PRIO_NONE;
+	new.unsafe	= cur->unsafe_takeover;
+	new.cpu		= cpu;
+
+	if (!nbcon_state_try_cmpxchg(con, cur, &new)) {
+		/*
+		 * The acquire could fail only when it has been taken
+		 * over by a higher priority context.
+		 */
+		WARN_ON_ONCE(nbcon_waiter_matches(cur, ctxt->prio));
+		return -EPERM;
+	}
+
+	/* Handover success. This context now owns the console. */
+	return 0;
+}
+
+/**
+ * nbcon_context_try_acquire_handover - Try to acquire via handover
+ * @ctxt:	The context of the caller
+ * @cur:	The current console state
+ *
+ * The function must be called only when the context has higher priority
+ * than the current owner and the console is in an unsafe state.
+ * It is the case when nbcon_context_try_acquire_direct() returns -EBUSY.
+ *
+ * The function sets "req_prio" field to make the current owner aware of
+ * the request. Then it waits until the current owner releases the console,
+ * or an even higher context takes over the request, or timeout expires.
+ *
+ * The current owner checks the "req_prio" field on exit from the unsafe
+ * region and releases the console. It does not touch the "req_prio" field
+ * so that the console stays reserved for the waiter.
+ *
+ * Return:	0 on success. Otherwise, an error code on failure. Also @cur
+ *		is updated to the latest state when failed to modify it.
+ *
+ * Errors:
+ *
+ *	-EPERM:		A panic is in progress and this is not the panic CPU.
+ *			Or a higher priority context has taken over the
+ *			console or the handover request.
+ *
+ *	-EBUSY:		The current owner is on the same CPU so that the hand
+ *			shake could not work. Or the current owner is not
+ *			willing to wait (zero timeout). Or the console does
+ *			not enter the safe state before timeout passed. The
+ *			caller might still use the unsafe hostile takeover
+ *			when allowed.
+ *
+ *	-EAGAIN:	@cur has changed when creating the handover request.
+ *			The caller should retry with direct acquire.
+ */
+static int nbcon_context_try_acquire_handover(struct nbcon_context *ctxt,
+					      struct nbcon_state *cur)
+{
+	unsigned int cpu = smp_processor_id();
+	struct console *con = ctxt->console;
+	struct nbcon_state new;
+	int timeout;
+	int request_err = -EBUSY;
+
+	/*
+	 * Check that the handover is called when the direct acquire failed
+	 * with -EBUSY.
+	 */
+	WARN_ON_ONCE(ctxt->prio <= cur->prio || ctxt->prio <= cur->req_prio);
+	WARN_ON_ONCE(!cur->unsafe);
+
+	/* Handover is not possible on the same CPU. */
+	if (cur->cpu == cpu)
+		return -EBUSY;
+
+	/*
+	 * Console stays unsafe after an unsafe takeover until re-initialized.
+	 * Waiting is not going to help in this case.
+	 */
+	if (cur->unsafe_takeover)
+		return -EBUSY;
+
+	/* Is the caller willing to wait? */
+	if (ctxt->spinwait_max_us == 0)
+		return -EBUSY;
+
+	/*
+	 * Setup a request for the handover. The caller should try to acquire
+	 * the console directly when the current state has been modified.
+	 */
+	new.atom = cur->atom;
+	new.req_prio = ctxt->prio;
+	if (!nbcon_state_try_cmpxchg(con, cur, &new))
+		return -EAGAIN;
+
+	cur->atom = new.atom;
+
+	/* Wait until there is no owner and then acquire the console. */
+	for (timeout = ctxt->spinwait_max_us; timeout >= 0; timeout--) {
+		/* On successful acquire, this request is cleared. */
+		request_err = nbcon_context_try_acquire_requested(ctxt, cur);
+		if (!request_err)
+			return 0;
+
+		/*
+		 * If the acquire should be aborted, it must be ensured
+		 * that the request is removed before returning to caller.
+		 */
+		if (request_err == -EPERM)
+			break;
+
+		udelay(1);
+
+		/* Re-read the state because some time has passed. */
+		nbcon_state_read(con, cur);
+	}
+
+	/* Timed out or aborted. Carefully remove handover request. */
+	do {
+		/*
+		 * No need to remove request if there is a new waiter. This
+		 * can only happen if a higher priority context has taken over
+		 * the console or the handover request.
+		 */
+		if (!nbcon_waiter_matches(cur, ctxt->prio))
+			return -EPERM;
+
+		/* Unset request for handover. */
+		new.atom = cur->atom;
+		new.req_prio = NBCON_PRIO_NONE;
+		if (nbcon_state_try_cmpxchg(con, cur, &new)) {
+			/*
+			 * Request successfully unset. Report failure of
+			 * acquiring via handover.
+			 */
+			cur->atom = new.atom;
+			return request_err;
+		}
+
+		/*
+		 * Unable to remove request. Try to acquire in case
+		 * the owner has released the lock.
+		 */
+	} while (nbcon_context_try_acquire_requested(ctxt, cur));
+
+	/* Lucky timing. The acquire succeeded while removing the request. */
+	return 0;
+}
+
+/**
+ * nbcon_context_try_acquire_hostile - Acquire via unsafe hostile takeover
+ * @ctxt:	The context of the caller
+ * @cur:	The current console state
+ *
+ * Acquire the console even in the unsafe state.
+ *
+ * It can be permitted by setting the 'allow_unsafe_takeover' field only
+ * by the final attempt to flush messages in panic().
+ *
+ * Return:	0 on success. -EPERM when not allowed by the context.
+ */
+static int nbcon_context_try_acquire_hostile(struct nbcon_context *ctxt,
+					     struct nbcon_state *cur)
+{
+	unsigned int cpu = smp_processor_id();
+	struct console *con = ctxt->console;
+	struct nbcon_state new;
+
+	if (!ctxt->allow_unsafe_takeover)
+		return -EPERM;
+
+	/* Ensure caller is allowed to perform unsafe hostile takeovers. */
+	if (WARN_ON_ONCE(ctxt->prio != NBCON_PRIO_PANIC))
+		return -EPERM;
+
+	/*
+	 * Check that try_acquire_direct() and try_acquire_handover() returned
+	 * -EBUSY in the right situation.
+	 */
+	WARN_ON_ONCE(ctxt->prio <= cur->prio || ctxt->prio <= cur->req_prio);
+	WARN_ON_ONCE(cur->unsafe != true);
+
+	do {
+		new.atom = cur->atom;
+		new.cpu			= cpu;
+		new.prio		= ctxt->prio;
+		new.unsafe		|= cur->unsafe_takeover;
+		new.unsafe_takeover	|= cur->unsafe;
+
+	} while (!nbcon_state_try_cmpxchg(con, cur, &new));
+
+	return 0;
+}
+
+/**
+ * nbcon_context_try_acquire - Try to acquire nbcon console
+ * @ctxt:	The context of the caller
+ *
+ * Return:	True if the console was acquired. False otherwise.
+ *
+ * If the caller allowed an unsafe hostile takeover, on success the
+ * caller should check the current console state to see if it is
+ * in an unsafe state. Otherwise, on success the caller may assume
+ * the console is not in an unsafe state.
+ */
+__maybe_unused
+static bool nbcon_context_try_acquire(struct nbcon_context *ctxt)
+{
+	struct console *con = ctxt->console;
+	struct nbcon_state cur;
+	int err;
+
+	nbcon_state_read(con, &cur);
+try_again:
+	err = nbcon_context_try_acquire_direct(ctxt, &cur);
+	if (err != -EBUSY)
+		goto out;
+
+	err = nbcon_context_try_acquire_handover(ctxt, &cur);
+	if (err == -EAGAIN)
+		goto try_again;
+	if (err != -EBUSY)
+		goto out;
+
+	err = nbcon_context_try_acquire_hostile(ctxt, &cur);
+out:
+	return !err;
+}
+
+static bool nbcon_owner_matches(struct nbcon_state *cur, int expected_cpu,
+				int expected_prio)
+{
+	/*
+	 * Since consoles can only be acquired by higher priorities,
+	 * owning contexts are uniquely identified by @prio. However,
+	 * since contexts can unexpectedly lose ownership, it is
+	 * possible that later another owner appears with the same
+	 * priority. For this reason @cpu is also needed.
+	 */
+
+	if (cur->prio != expected_prio)
+		return false;
+
+	if (cur->cpu != expected_cpu)
+		return false;
+
+	return true;
+}
+
+/**
+ * nbcon_context_release - Release the console
+ * @ctxt:	The nbcon context from nbcon_context_try_acquire()
+ */
+__maybe_unused
+static void nbcon_context_release(struct nbcon_context *ctxt)
+{
+	unsigned int cpu = smp_processor_id();
+	struct console *con = ctxt->console;
+	struct nbcon_state cur;
+	struct nbcon_state new;
+
+	nbcon_state_read(con, &cur);
+
+	do {
+		if (!nbcon_owner_matches(&cur, cpu, ctxt->prio))
+			return;
+
+		new.atom = cur.atom;
+		new.prio = NBCON_PRIO_NONE;
+
+		/*
+		 * If @unsafe_takeover is set, it is kept set so that
+		 * the state remains permanently unsafe.
+		 */
+		new.unsafe |= cur.unsafe_takeover;
+
+	} while (!nbcon_state_try_cmpxchg(con, &cur, &new));
+}
+
 /**
  * nbcon_init - Initialize the nbcon console specific data
  * @con:	Console to initialize
-- 
2.43.0