Merge branch 'net-netconsole-convert-to-nbcon-console-infrastructure'

Breno Leitao says:

====================
net: netconsole: convert to NBCON console infrastructure

This series adds support for the nbcon (new buffer console) infrastructure
to netconsole, enabling lock-free, priority-based console operations that
are safer in crash scenarios.

The implementation is introduced in three steps:

0) Extend printk to expose CPU and taskname (task->comm) where the
   printk originated from. (Thanks John and Petr for the support in
   getting this done)
1) Refactor the message fragmentation logic into a reusable helper function
2) Extend nbcon support to non-extended (basic) consoles using the same
   infrastructure.

The initial discussion about it appeared a while ago in [1], in order to
solve Mike's HARDIRQ-safe -> HARDIRQ-unsafe lock order warning, and the root
cause is that some hosts were calling IRQ unsafe locks from inside console
lock.

At that time, we didn't have the CON_NBCON_ATOMIC_UNSAFE yet. John
kindly implemented CON_NBCON_ATOMIC_UNSAFE in 187de7c212e5 ("printk:
nbcon: Allow unsafe write_atomic() for panic"), and now we can
implement netconsole on top of nbcon.

Important to note that netconsole continues to call netpoll and the
network TX helpers with interrupt disable, given the TX are called with
target_list_lock.
====================

Link: https://patch.msgid.link/20260206-nbcon-v7-0-62bda69b1b41@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

8 files changed, 197 insertions, 60 deletions

diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index 9c7953f8e637..7e9becad91df 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -341,6 +341,7 @@ config NETCONSOLE_DYNAMIC
 	bool "Dynamic reconfiguration of logging targets"
 	depends on NETCONSOLE && SYSFS && CONFIGFS_FS && \
 			!(NETCONSOLE=y && CONFIGFS_FS=m)
+	select PRINTK_EXECUTION_CTX
 	help
 	  This option enables the ability to dynamically reconfigure target
 	  parameters (interface, IP addresses, port numbers, MAC addresses)
diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c
index 82c232f9ede2..0f44ce5ccc0a 100644
--- a/drivers/net/netconsole.c
+++ b/drivers/net/netconsole.c
@@ -1490,18 +1490,20 @@ static void populate_configfs_item(struct netconsole_target *nt,
 	init_target_config_group(nt, target_name);
 }
 
-static int sysdata_append_cpu_nr(struct netconsole_target *nt, int offset)
+static int sysdata_append_cpu_nr(struct netconsole_target *nt, int offset,
+				 struct nbcon_write_context *wctxt)
 {
 	return scnprintf(&nt->sysdata[offset],
 			 MAX_EXTRADATA_ENTRY_LEN, " cpu=%u\n",
-			 raw_smp_processor_id());
+			 wctxt->cpu);
 }
 
-static int sysdata_append_taskname(struct netconsole_target *nt, int offset)
+static int sysdata_append_taskname(struct netconsole_target *nt, int offset,
+				   struct nbcon_write_context *wctxt)
 {
 	return scnprintf(&nt->sysdata[offset],
 			 MAX_EXTRADATA_ENTRY_LEN, " taskname=%s\n",
-			 current->comm);
+			 wctxt->comm);
 }
 
 static int sysdata_append_release(struct netconsole_target *nt, int offset)
@@ -1522,8 +1524,10 @@ static int sysdata_append_msgid(struct netconsole_target *nt, int offset)
 /*
  * prepare_sysdata - append sysdata in runtime
  * @nt: target to send message to
+ * @wctxt: nbcon write context containing message metadata
  */
-static int prepare_sysdata(struct netconsole_target *nt)
+static int prepare_sysdata(struct netconsole_target *nt,
+			   struct nbcon_write_context *wctxt)
 {
 	int sysdata_len = 0;
 
@@ -1531,9 +1535,9 @@ static int prepare_sysdata(struct netconsole_target *nt)
 		goto out;
 
 	if (nt->sysdata_fields & SYSDATA_CPU_NR)
-		sysdata_len += sysdata_append_cpu_nr(nt, sysdata_len);
+		sysdata_len += sysdata_append_cpu_nr(nt, sysdata_len, wctxt);
 	if (nt->sysdata_fields & SYSDATA_TASKNAME)
-		sysdata_len += sysdata_append_taskname(nt, sysdata_len);
+		sysdata_len += sysdata_append_taskname(nt, sysdata_len, wctxt);
 	if (nt->sysdata_fields & SYSDATA_RELEASE)
 		sysdata_len += sysdata_append_release(nt, sysdata_len);
 	if (nt->sysdata_fields & SYSDATA_MSGID)
@@ -1831,83 +1835,108 @@ static void send_msg_fragmented(struct netconsole_target *nt,
 /**
  * send_ext_msg_udp - send extended log message to target
  * @nt: target to send message to
- * @msg: extended log message to send
- * @msg_len: length of message
+ * @wctxt: nbcon write context containing message and metadata
  *
- * Transfer extended log @msg to @nt.  If @msg is longer than
+ * Transfer extended log message to @nt.  If message is longer than
  * MAX_PRINT_CHUNK, it'll be split and transmitted in multiple chunks with
  * ncfrag header field added to identify them.
  */
-static void send_ext_msg_udp(struct netconsole_target *nt, const char *msg,
-			     int msg_len)
+static void send_ext_msg_udp(struct netconsole_target *nt,
+			     struct nbcon_write_context *wctxt)
 {
 	int userdata_len = 0;
 	int release_len = 0;
 	int sysdata_len = 0;
+	int len;
 
 #ifdef CONFIG_NETCONSOLE_DYNAMIC
-	sysdata_len = prepare_sysdata(nt);
+	sysdata_len = prepare_sysdata(nt, wctxt);
 	userdata_len = nt->userdata_length;
 #endif
 	if (nt->release)
 		release_len = strlen(init_utsname()->release) + 1;
 
-	if (msg_len + release_len + sysdata_len + userdata_len <= MAX_PRINT_CHUNK)
-		return send_msg_no_fragmentation(nt, msg, msg_len, release_len);
+	len = wctxt->len + release_len + sysdata_len + userdata_len;
+	if (len <= MAX_PRINT_CHUNK)
+		return send_msg_no_fragmentation(nt, wctxt->outbuf,
+						 wctxt->len, release_len);
 
-	return send_msg_fragmented(nt, msg, msg_len, release_len,
+	return send_msg_fragmented(nt, wctxt->outbuf, wctxt->len, release_len,
 				   sysdata_len);
 }
 
-static void write_ext_msg(struct console *con, const char *msg,
-			  unsigned int len)
+static void send_msg_udp(struct netconsole_target *nt, const char *msg,
+			 unsigned int len)
 {
-	struct netconsole_target *nt;
-	unsigned long flags;
-
-	if ((oops_only && !oops_in_progress) || list_empty(&target_list))
-		return;
+	const char *tmp = msg;
+	int frag, left = len;
 
-	spin_lock_irqsave(&target_list_lock, flags);
-	list_for_each_entry(nt, &target_list, list)
-		if (nt->extended && nt->state == STATE_ENABLED &&
-		    netif_running(nt->np.dev))
-			send_ext_msg_udp(nt, msg, len);
-	spin_unlock_irqrestore(&target_list_lock, flags);
+	while (left > 0) {
+		frag = min(left, MAX_PRINT_CHUNK);
+		send_udp(nt, tmp, frag);
+		tmp += frag;
+		left -= frag;
+	}
 }
 
-static void write_msg(struct console *con, const char *msg, unsigned int len)
+/**
+ * netconsole_write - Generic function to send a msg to all targets
+ * @wctxt: nbcon write context
+ * @extended: "true" for extended console mode
+ *
+ * Given an nbcon write context, send the message to the netconsole targets
+ */
+static void netconsole_write(struct nbcon_write_context *wctxt, bool extended)
 {
-	int frag, left;
-	unsigned long flags;
 	struct netconsole_target *nt;
-	const char *tmp;
 
 	if (oops_only && !oops_in_progress)
 		return;
-	/* Avoid taking lock and disabling interrupts unnecessarily */
-	if (list_empty(&target_list))
-		return;
 
-	spin_lock_irqsave(&target_list_lock, flags);
 	list_for_each_entry(nt, &target_list, list) {
-		if (!nt->extended && nt->state == STATE_ENABLED &&
-		    netif_running(nt->np.dev)) {
-			/*
-			 * We nest this inside the for-each-target loop above
-			 * so that we're able to get as much logging out to
-			 * at least one target if we die inside here, instead
-			 * of unnecessarily keeping all targets in lock-step.
-			 */
-			tmp = msg;
-			for (left = len; left;) {
-				frag = min(left, MAX_PRINT_CHUNK);
-				send_udp(nt, tmp, frag);
-				tmp += frag;
-				left -= frag;
-			}
-		}
+		if (nt->extended != extended || nt->state != STATE_ENABLED ||
+		    !netif_running(nt->np.dev))
+			continue;
+
+		/* If nbcon_enter_unsafe() fails, just return given netconsole
+		 * lost the ownership, and iterating over the targets will not
+		 * be able to re-acquire.
+		 */
+		if (!nbcon_enter_unsafe(wctxt))
+			return;
+
+		if (extended)
+			send_ext_msg_udp(nt, wctxt);
+		else
+			send_msg_udp(nt, wctxt->outbuf, wctxt->len);
+
+		nbcon_exit_unsafe(wctxt);
 	}
+}
+
+static void netconsole_write_ext(struct console *con __always_unused,
+				 struct nbcon_write_context *wctxt)
+{
+	netconsole_write(wctxt, true);
+}
+
+static void netconsole_write_basic(struct console *con __always_unused,
+				   struct nbcon_write_context *wctxt)
+{
+	netconsole_write(wctxt, false);
+}
+
+static void netconsole_device_lock(struct console *con __always_unused,
+				   unsigned long *flags)
+__acquires(&target_list_lock)
+{
+	spin_lock_irqsave(&target_list_lock, *flags);
+}
+
+static void netconsole_device_unlock(struct console *con __always_unused,
+				     unsigned long flags)
+__releases(&target_list_lock)
+{
 	spin_unlock_irqrestore(&target_list_lock, flags);
 }
 
@@ -2071,15 +2100,21 @@ static void free_param_target(struct netconsole_target *nt)
 }
 
 static struct console netconsole_ext = {
-	.name	= "netcon_ext",
-	.flags	= CON_ENABLED | CON_EXTENDED,
-	.write	= write_ext_msg,
+	.name = "netcon_ext",
+	.flags = CON_ENABLED | CON_EXTENDED | CON_NBCON | CON_NBCON_ATOMIC_UNSAFE,
+	.write_thread = netconsole_write_ext,
+	.write_atomic = netconsole_write_ext,
+	.device_lock = netconsole_device_lock,
+	.device_unlock = netconsole_device_unlock,
 };
 
 static struct console netconsole = {
-	.name	= "netcon",
-	.flags	= CON_ENABLED,
-	.write	= write_msg,
+	.name = "netcon",
+	.flags = CON_ENABLED | CON_NBCON | CON_NBCON_ATOMIC_UNSAFE,
+	.write_thread = netconsole_write_basic,
+	.write_atomic = netconsole_write_basic,
+	.device_lock = netconsole_device_lock,
+	.device_unlock = netconsole_device_unlock,
 };
 
 static int __init init_netconsole(void)
diff --git a/include/linux/console.h b/include/linux/console.h
index fc9f5c5c1b04..cc5dc3bf58b6 100644
--- a/include/linux/console.h
+++ b/include/linux/console.h
@@ -298,12 +298,20 @@ struct nbcon_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
+ * @cpu:		CPU on which the message was generated
+ * @pid:		PID of the task that generated the message
+ * @comm:		Name of the task that generated the message
  */
 struct nbcon_write_context {
 	struct nbcon_context	__private ctxt;
 	char			*outbuf;
 	unsigned int		len;
 	bool			unsafe_takeover;
+#ifdef CONFIG_PRINTK_EXECUTION_CTX
+	int			cpu;
+	pid_t			pid;
+	char			comm[TASK_COMM_LEN];
+#endif
 };
 
 /**
diff --git a/kernel/printk/internal.h b/kernel/printk/internal.h
index 5f5f626f4279..5fdea5682756 100644
--- a/kernel/printk/internal.h
+++ b/kernel/printk/internal.h
@@ -281,12 +281,20 @@ struct printk_buffers {
  *		nothing to output and this record should be skipped.
  * @seq:	The sequence number of the record used for @pbufs->outbuf.
  * @dropped:	The number of dropped records from reading @seq.
+ * @cpu:	CPU on which the message was generated.
+ * @pid:	PID of the task that generated the message
+ * @comm:	Name of the task that generated the message.
  */
 struct printk_message {
 	struct printk_buffers	*pbufs;
 	unsigned int		outbuf_len;
 	u64			seq;
 	unsigned long		dropped;
+#ifdef CONFIG_PRINTK_EXECUTION_CTX
+	int			cpu;
+	pid_t			pid;
+	char			comm[TASK_COMM_LEN];
+#endif
 };
 
 bool printk_get_next_message(struct printk_message *pmsg, u64 seq,
diff --git a/kernel/printk/nbcon.c b/kernel/printk/nbcon.c
index 32fc12e53675..f6d22510fdc3 100644
--- a/kernel/printk/nbcon.c
+++ b/kernel/printk/nbcon.c
@@ -946,6 +946,20 @@ void nbcon_reacquire_nobuf(struct nbcon_write_context *wctxt)
 }
 EXPORT_SYMBOL_GPL(nbcon_reacquire_nobuf);
 
+#ifdef CONFIG_PRINTK_EXECUTION_CTX
+static void wctxt_load_execution_ctx(struct nbcon_write_context *wctxt,
+				     struct printk_message *pmsg)
+{
+	wctxt->cpu = pmsg->cpu;
+	wctxt->pid = pmsg->pid;
+	memcpy(wctxt->comm, pmsg->comm, sizeof(wctxt->comm));
+	static_assert(sizeof(wctxt->comm) == sizeof(pmsg->comm));
+}
+#else
+static void wctxt_load_execution_ctx(struct nbcon_write_context *wctxt,
+				     struct printk_message *pmsg) {}
+#endif
+
 /**
  * nbcon_emit_next_record - Emit a record in the acquired context
  * @wctxt:	The write context that will be handed to the write function
@@ -1048,6 +1062,8 @@ static bool nbcon_emit_next_record(struct nbcon_write_context *wctxt, bool use_a
 	/* Initialize the write context for driver callbacks. */
 	nbcon_write_context_set_buf(wctxt, &pmsg.pbufs->outbuf[0], pmsg.outbuf_len);
 
+	wctxt_load_execution_ctx(wctxt, &pmsg);
+
 	if (use_atomic)
 		con->write_atomic(con, wctxt);
 	else
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 1d765ad242b8..cf6b52861036 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -2131,11 +2131,39 @@ static inline void printk_delay(int level)
 	}
 }
 
+#define CALLER_ID_MASK 0x80000000
+
 static inline u32 printk_caller_id(void)
 {
 	return in_task() ? task_pid_nr(current) :
-		0x80000000 + smp_processor_id();
+		CALLER_ID_MASK + smp_processor_id();
+}
+
+#ifdef CONFIG_PRINTK_EXECUTION_CTX
+/* Store the opposite info than caller_id. */
+static u32 printk_caller_id2(void)
+{
+	return !in_task() ? task_pid_nr(current) :
+		CALLER_ID_MASK + smp_processor_id();
+}
+
+static pid_t printk_info_get_pid(const struct printk_info *info)
+{
+	u32 caller_id = info->caller_id;
+	u32 caller_id2 = info->caller_id2;
+
+	return caller_id & CALLER_ID_MASK ? caller_id2 : caller_id;
+}
+
+static int printk_info_get_cpu(const struct printk_info *info)
+{
+	u32 caller_id = info->caller_id;
+	u32 caller_id2 = info->caller_id2;
+
+	return ((caller_id & CALLER_ID_MASK ?
+		 caller_id : caller_id2) & ~CALLER_ID_MASK);
 }
+#endif
 
 /**
  * printk_parse_prefix - Parse level and control flags.
@@ -2213,6 +2241,28 @@ static u16 printk_sprint(char *text, u16 size, int facility,
 	return text_len;
 }
 
+#ifdef CONFIG_PRINTK_EXECUTION_CTX
+static void printk_store_execution_ctx(struct printk_info *info)
+{
+	info->caller_id2 = printk_caller_id2();
+	get_task_comm(info->comm, current);
+}
+
+static void pmsg_load_execution_ctx(struct printk_message *pmsg,
+				    const struct printk_info *info)
+{
+	pmsg->cpu = printk_info_get_cpu(info);
+	pmsg->pid = printk_info_get_pid(info);
+	memcpy(pmsg->comm, info->comm, sizeof(pmsg->comm));
+	static_assert(sizeof(pmsg->comm) == sizeof(info->comm));
+}
+#else
+static void printk_store_execution_ctx(struct printk_info *info) {}
+
+static void pmsg_load_execution_ctx(struct printk_message *pmsg,
+				    const struct printk_info *info) {}
+#endif
+
 __printf(4, 0)
 int vprintk_store(int facility, int level,
 		  const struct dev_printk_info *dev_info,
@@ -2320,6 +2370,7 @@ int vprintk_store(int facility, int level,
 	r.info->caller_id = caller_id;
 	if (dev_info)
 		memcpy(&r.info->dev_info, dev_info, sizeof(r.info->dev_info));
+	printk_store_execution_ctx(r.info);
 
 	/* A message without a trailing newline can be continued. */
 	if (!(flags & LOG_NEWLINE))
@@ -3002,6 +3053,7 @@ bool printk_get_next_message(struct printk_message *pmsg, u64 seq,
 	pmsg->seq = r.info->seq;
 	pmsg->dropped = r.info->seq - seq;
 	force_con = r.info->flags & LOG_FORCE_CON;
+	pmsg_load_execution_ctx(pmsg, r.info);
 
 	/*
 	 * Skip records that are not forced to be printed on consoles and that
diff --git a/kernel/printk/printk_ringbuffer.h b/kernel/printk/printk_ringbuffer.h
index 4ef81349d9fb..1651b53ece34 100644
--- a/kernel/printk/printk_ringbuffer.h
+++ b/kernel/printk/printk_ringbuffer.h
@@ -23,6 +23,11 @@ struct printk_info {
 	u8	flags:5;	/* internal record flags */
 	u8	level:3;	/* syslog level */
 	u32	caller_id;	/* thread id or processor id */
+#ifdef CONFIG_PRINTK_EXECUTION_CTX
+	u32	caller_id2;	/* caller_id complement */
+	/* name of the task that generated the message */
+	char	comm[TASK_COMM_LEN];
+#endif
 
 	struct dev_printk_info	dev_info;
 };
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index ba36939fda79..938d967ae3bf 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -35,6 +35,18 @@ config PRINTK_CALLER
 	  no option to enable/disable at the kernel command line parameter or
 	  sysfs interface.
 
+config PRINTK_EXECUTION_CTX
+	bool
+	depends on PRINTK
+	help
+	  This option extends struct printk_info to include extra execution
+	  context in printk, such as task name and CPU number from where the
+	  message originated. This is useful for correlating printk messages
+	  with specific execution contexts.
+
+	  This is automatically enabled when a console driver that supports
+	  execution context is selected.
+
 config STACKTRACE_BUILD_ID
 	bool "Show build ID information in stacktraces"
 	depends on PRINTK