[tip: sched/rt] printk: nbcon: Rely on kthreads for normal operation

From: tip-bot2 for John Ogness
Date: Mon Sep 09 2024 - 13:29:20 EST


The following commit has been merged into the sched/rt branch of tip:

Commit-ID: 13189fa73afae2b961d29132fd36d9cc0be77ecb
Gitweb: https://git.kernel.org/tip/13189fa73afae2b961d29132fd36d9cc0be77ecb
Author: John Ogness <john.ogness@xxxxxxxxxxxxx>
AuthorDate: Wed, 04 Sep 2024 14:11:28 +02:06
Committer: Petr Mladek <pmladek@xxxxxxxx>
CommitterDate: Wed, 04 Sep 2024 15:56:32 +02:00

printk: nbcon: Rely on kthreads for normal operation

Once the kthread is running and available
(i.e. @printk_kthreads_running is set), the kthread becomes
responsible for flushing any pending messages which are added
in NBCON_PRIO_NORMAL context. Namely the legacy
console_flush_all() and device_release() no longer flush the
console. And nbcon_atomic_flush_pending() used by
nbcon_cpu_emergency_exit() no longer flushes messages added
after the emergency messages.

The console context is safe when used by the kthread only when
one of the following conditions are true:

1. Other caller acquires the console context with
NBCON_PRIO_NORMAL with preemption disabled. It will
release the context before rescheduling.

2. Other caller acquires the console context with
NBCON_PRIO_NORMAL under the device_lock.

3. The kthread is the only context which acquires the console
with NBCON_PRIO_NORMAL.

This is satisfied for all atomic printing call sites:

nbcon_legacy_emit_next_record() (#1)

nbcon_atomic_flush_pending_con() (#1)

nbcon_device_release() (#2)

It is even double guaranteed when @printk_kthreads_running
is set because then _only_ the kthread will print for
NBCON_PRIO_NORMAL. (#3)

Signed-off-by: John Ogness <john.ogness@xxxxxxxxxxxxx>
Reviewed-by: Petr Mladek <pmladek@xxxxxxxx>
Link: https://lore.kernel.org/r/20240904120536.115780-10-john.ogness@xxxxxxxxxxxxx
Signed-off-by: Petr Mladek <pmladek@xxxxxxxx>
---
kernel/printk/internal.h | 26 +++++++++++++++++++++-
kernel/printk/nbcon.c | 17 +++++++++-----
kernel/printk/printk.c | 48 ++++++++++++++++++++++++++++++++++++++-
3 files changed, 84 insertions(+), 7 deletions(-)

diff --git a/kernel/printk/internal.h b/kernel/printk/internal.h
index a96d411..8166e24 100644
--- a/kernel/printk/internal.h
+++ b/kernel/printk/internal.h
@@ -113,6 +113,13 @@ static inline bool console_is_usable(struct console *con, short flags, bool use_
/* The write_atomic() callback is optional. */
if (use_atomic && !con->write_atomic)
return false;
+
+ /*
+ * For the !use_atomic case, @printk_kthreads_running is not
+ * checked because the write_thread() callback is also used
+ * via the legacy loop when the printer threads are not
+ * available.
+ */
} else {
if (!con->write)
return false;
@@ -176,6 +183,7 @@ static inline void nbcon_atomic_flush_pending(void) { }
static inline bool nbcon_legacy_emit_next_record(struct console *con, bool *handover,
int cookie, bool use_atomic) { return false; }
static inline void nbcon_kthread_wake(struct console *con) { }
+static inline void nbcon_kthreads_wake(void) { }

static inline bool console_is_usable(struct console *con, short flags,
bool use_atomic) { return false; }
@@ -190,6 +198,7 @@ extern bool legacy_allow_panic_sync;
/**
* struct console_flush_type - Define available console flush methods
* @nbcon_atomic: Flush directly using nbcon_atomic() callback
+ * @nbcon_offload: Offload flush to printer thread
* @legacy_direct: Call the legacy loop in this context
* @legacy_offload: Offload the legacy loop into IRQ
*
@@ -197,6 +206,7 @@ extern bool legacy_allow_panic_sync;
*/
struct console_flush_type {
bool nbcon_atomic;
+ bool nbcon_offload;
bool legacy_direct;
bool legacy_offload;
};
@@ -211,6 +221,22 @@ static inline void printk_get_console_flush_type(struct console_flush_type *ft)

switch (nbcon_get_default_prio()) {
case NBCON_PRIO_NORMAL:
+ if (have_nbcon_console && !have_boot_console) {
+ if (printk_kthreads_running)
+ ft->nbcon_offload = true;
+ else
+ ft->nbcon_atomic = true;
+ }
+
+ /* Legacy consoles are flushed directly when possible. */
+ if (have_legacy_console || have_boot_console) {
+ if (!is_printk_legacy_deferred())
+ ft->legacy_direct = true;
+ else
+ ft->legacy_offload = true;
+ }
+ break;
+
case NBCON_PRIO_EMERGENCY:
if (have_nbcon_console && !have_boot_console)
ft->nbcon_atomic = true;
diff --git a/kernel/printk/nbcon.c b/kernel/printk/nbcon.c
index 784e5de..5146ce9 100644
--- a/kernel/printk/nbcon.c
+++ b/kernel/printk/nbcon.c
@@ -1494,6 +1494,7 @@ static int __nbcon_atomic_flush_pending_con(struct console *con, u64 stop_seq,
static void nbcon_atomic_flush_pending_con(struct console *con, u64 stop_seq,
bool allow_unsafe_takeover)
{
+ struct console_flush_type ft;
unsigned long flags;
int err;

@@ -1523,10 +1524,12 @@ again:

/*
* If flushing was successful but more records are available, this
- * context must flush those remaining records because there is no
- * other context that will do it.
+ * context must flush those remaining records if the printer thread
+ * is not available do it.
*/
- if (prb_read_valid(prb, nbcon_seq_read(con), NULL)) {
+ printk_get_console_flush_type(&ft);
+ if (!ft.nbcon_offload &&
+ prb_read_valid(prb, nbcon_seq_read(con), NULL)) {
stop_seq = prb_next_reserve_seq(prb);
goto again;
}
@@ -1754,17 +1757,19 @@ void nbcon_device_release(struct console *con)

/*
* This context must flush any new records added while the console
- * was locked. The console_srcu_read_lock must be taken to ensure
- * the console is usable throughout flushing.
+ * was locked if the printer thread is not available to do it. The
+ * console_srcu_read_lock must be taken to ensure the console is
+ * usable throughout flushing.
*/
cookie = console_srcu_read_lock();
+ printk_get_console_flush_type(&ft);
if (console_is_usable(con, console_srcu_read_flags(con), true) &&
+ !ft.nbcon_offload &&
prb_read_valid(prb, nbcon_seq_read(con), NULL)) {
/*
* If nbcon_atomic flushing is not available, fallback to
* using the legacy loop.
*/
- printk_get_console_flush_type(&ft);
if (ft.nbcon_atomic) {
__nbcon_atomic_flush_pending_con(con, prb_next_reserve_seq(prb), false);
} else if (ft.legacy_direct) {
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 55d75db..149c3e0 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -2384,6 +2384,9 @@ asmlinkage int vprintk_emit(int facility, int level,
if (ft.nbcon_atomic)
nbcon_atomic_flush_pending();

+ if (ft.nbcon_offload)
+ nbcon_kthreads_wake();
+
if (ft.legacy_direct) {
/*
* The caller may be holding system-critical or
@@ -2732,6 +2735,7 @@ void suspend_console(void)

void resume_console(void)
{
+ struct console_flush_type ft;
struct console *con;

if (!console_suspend_enabled)
@@ -2749,6 +2753,10 @@ void resume_console(void)
*/
synchronize_srcu(&console_srcu);

+ printk_get_console_flush_type(&ft);
+ if (ft.nbcon_offload)
+ nbcon_kthreads_wake();
+
pr_flush(1000, true);
}

@@ -3060,6 +3068,7 @@ static inline void printk_kthreads_check_locked(void) { }
*/
static bool console_flush_all(bool do_cond_resched, u64 *next_seq, bool *handover)
{
+ struct console_flush_type ft;
bool any_usable = false;
struct console *con;
bool any_progress;
@@ -3071,12 +3080,22 @@ static bool console_flush_all(bool do_cond_resched, u64 *next_seq, bool *handove
do {
any_progress = false;

+ printk_get_console_flush_type(&ft);
+
cookie = console_srcu_read_lock();
for_each_console_srcu(con) {
short flags = console_srcu_read_flags(con);
u64 printk_seq;
bool progress;

+ /*
+ * console_flush_all() is only responsible for nbcon
+ * consoles when the nbcon consoles cannot print via
+ * their atomic or threaded flushing.
+ */
+ if ((flags & CON_NBCON) && (ft.nbcon_atomic || ft.nbcon_offload))
+ continue;
+
if (!console_is_usable(con, flags, !do_cond_resched))
continue;
any_usable = true;
@@ -3387,9 +3406,25 @@ EXPORT_SYMBOL(console_stop);

void console_start(struct console *console)
{
+ struct console_flush_type ft;
+ bool is_nbcon;
+
console_list_lock();
console_srcu_write_flags(console, console->flags | CON_ENABLED);
+ is_nbcon = console->flags & CON_NBCON;
console_list_unlock();
+
+ /*
+ * Ensure that all SRCU list walks have completed. The related
+ * printing context must be able to see it is enabled so that
+ * it is guaranteed to wake up and resume printing.
+ */
+ synchronize_srcu(&console_srcu);
+
+ printk_get_console_flush_type(&ft);
+ if (is_nbcon && ft.nbcon_offload)
+ nbcon_kthread_wake(console);
+
__pr_flush(console, 1000, true);
}
EXPORT_SYMBOL(console_start);
@@ -4115,6 +4150,8 @@ static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progre

/* Flush the consoles so that records up to @seq are printed. */
printk_get_console_flush_type(&ft);
+ if (ft.nbcon_atomic)
+ nbcon_atomic_flush_pending();
if (ft.legacy_direct) {
console_lock();
console_unlock();
@@ -4152,8 +4189,10 @@ static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progre
* that they make forward progress, so only increment
* @diff for usable consoles.
*/
- if (!console_is_usable(c, flags, true))
+ if (!console_is_usable(c, flags, true) &&
+ !console_is_usable(c, flags, false)) {
continue;
+ }

if (flags & CON_NBCON) {
printk_seq = nbcon_seq_read(c);
@@ -4629,8 +4668,15 @@ EXPORT_SYMBOL_GPL(kmsg_dump_rewind);
*/
void console_try_replay_all(void)
{
+ struct console_flush_type ft;
+
+ printk_get_console_flush_type(&ft);
if (console_trylock()) {
__console_rewind_all();
+ if (ft.nbcon_atomic)
+ nbcon_atomic_flush_pending();
+ if (ft.nbcon_offload)
+ nbcon_kthreads_wake();
/* Consoles are flushed as part of console_unlock(). */
console_unlock();
}