Merge tag 'kgdb-5.8-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/danielt/linux

Pull kgdb updates from Daniel Thompson:
 "By far the biggest change in this cycle are the changes that allow
  much earlier debug of systems that are hooked up via UART by taking
  advantage of the earlycon framework to implement the kgdb I/O hooks
  before handing over to the regular polling I/O drivers once they are
  available. When discussing Doug's work we also found and fixed an
  broken raw_smp_processor_id() sequence in in_dbg_master().

  Also included are a collection of much smaller fixes and tweaks: a
  couple of tweaks to ged rid of doc gen or coccicheck warnings, future
  proof some internal calculations that made implicit power-of-2
  assumptions and eliminate some rather weird handling of magic
  environment variables in kdb"

* tag 'kgdb-5.8-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/danielt/linux:
  kdb: Remove the misfeature 'KDBFLAGS'
  kdb: Cleanup math with KDB_CMD_HISTORY_COUNT
  serial: amba-pl011: Support kgdboc_earlycon
  serial: 8250_early: Support kgdboc_earlycon
  serial: qcom_geni_serial: Support kgdboc_earlycon
  serial: kgdboc: Allow earlycon initialization to be deferred
  Documentation: kgdboc: Document new kgdboc_earlycon parameter
  kgdb: Don't call the deinit under spinlock
  kgdboc: Disable all the early code when kgdboc is a module
  kgdboc: Add kgdboc_earlycon to support early kgdb using boot consoles
  kgdboc: Remove useless #ifdef CONFIG_KGDB_SERIAL_CONSOLE in kgdboc
  kgdb: Prevent infinite recursive entries to the debugger
  kgdb: Delay "kgdbwait" to dbg_late_init() by default
  kgdboc: Use a platform device to handle tty drivers showing up late
  Revert "kgdboc: disable the console lock when in kgdb"
  kgdb: Disable WARN_CONSOLE_UNLOCKED for all kgdb
  kgdb: Return true in kgdb_nmi_poll_knock()
  kgdb: Drop malformed kernel doc comment
  kgdb: Fix spurious true from in_dbg_master()

Documentation/admin-guide/kernel-parameters.txt

@@ -1190,6 +1190,11 @@
 			This is designed to be used in conjunction with
 			the boot argument: earlyprintk=vga
 
+			This parameter works in place of the kgdboc parameter
+			but can only be used if the backing tty is available
+			very early in the boot process. For early debugging
+			via a serial port see kgdboc_earlycon instead.
+
 	edd=		[EDD]
 			Format: {"off" | "on" | "skip[mbr]"}
 
@@ -2112,6 +2117,21 @@
 			 kms, kbd format: kms,kbd
 			 kms, kbd and serial format: kms,kbd,<ser_dev>[,baud]
 
+	kgdboc_earlycon=	[KGDB,HW]
+			If the boot console provides the ability to read
+			characters and can work in polling mode, you can use
+			this parameter to tell kgdb to use it as a backend
+			until the normal console is registered. Intended to
+			be used together with the kgdboc parameter which
+			specifies the normal console to transition to.
+
+			The name of the early console should be specified
+			as the value of this parameter. Note that the name of
+			the early console might be different than the tty
+			name passed to kgdboc. It's OK to leave the value
+			blank and the first boot console that implements
+			read() will be picked.
+
 	kgdbwait	[KGDB] Stop kernel execution and enter the
 			kernel debugger at the earliest opportunity.
 

Documentation/dev-tools/kgdb.rst

@@ -274,6 +274,30 @@ don't like this are to hack gdb to send the :kbd:`SysRq-G` for you as well as
 on the initial connect, or to use a debugger proxy that allows an
 unmodified gdb to do the debugging.
 
+Kernel parameter: ``kgdboc_earlycon``
+-------------------------------------
+
+If you specify the kernel parameter ``kgdboc_earlycon`` and your serial
+driver registers a boot console that supports polling (doesn't need
+interrupts and implements a nonblocking read() function) kgdb will attempt
+to work using the boot console until it can transition to the regular
+tty driver specified by the ``kgdboc`` parameter.
+
+Normally there is only one boot console (especially that implements the
+read() function) so just adding ``kgdboc_earlycon`` on its own is
+sufficient to make this work. If you have more than one boot console you
+can add the boot console's name to differentiate. Note that names that
+are registered through the boot console layer and the tty layer are not
+the same for the same port.
+
+For instance, on one board to be explicit you might do::
+
+   kgdboc_earlycon=qcom_geni kgdboc=ttyMSM0
+
+If the only boot console on the device was "qcom_geni", you could simplify::
+
+   kgdboc_earlycon kgdboc=ttyMSM0
+
 Kernel parameter: ``kgdbwait``
 ------------------------------
 

arch/x86/Kconfig

@@ -60,6 +60,7 @@ config X86
 	select ARCH_HAS_ACPI_TABLE_UPGRADE	if ACPI
 	select ARCH_HAS_DEBUG_VIRTUAL
 	select ARCH_HAS_DEVMEM_IS_ALLOWED
+	select ARCH_HAS_EARLY_DEBUG		if KGDB
 	select ARCH_HAS_ELF_RANDOMIZE
 	select ARCH_HAS_FAST_MULTIPLIER
 	select ARCH_HAS_FILTER_PGPROT

drivers/tty/serial/8250/8250_early.c

@@ -109,6 +109,28 @@ static void early_serial8250_write(struct console *console,
 	uart_console_write(port, s, count, serial_putc);
 }
 
+#ifdef CONFIG_CONSOLE_POLL
+static int early_serial8250_read(struct console *console,
+				 char *s, unsigned int count)
+{
+	struct earlycon_device *device = console->data;
+	struct uart_port *port = &device->port;
+	unsigned int status;
+	int num_read = 0;
+
+	while (num_read < count) {
+		status = serial8250_early_in(port, UART_LSR);
+		if (!(status & UART_LSR_DR))
+			break;
+		s[num_read++] = serial8250_early_in(port, UART_RX);
+	}
+
+	return num_read;
+}
+#else
+#define early_serial8250_read NULL
+#endif
+
 static void __init init_port(struct earlycon_device *device)
 {
 	struct uart_port *port = &device->port;
@@ -149,6 +171,7 @@ int __init early_serial8250_setup(struct earlycon_device *device,
 		init_port(device);
 
 	device->con->write = early_serial8250_write;
+	device->con->read = early_serial8250_read;
 	return 0;
 }
 EARLYCON_DECLARE(uart8250, early_serial8250_setup);

drivers/tty/serial/amba-pl011.c

@@ -2435,6 +2435,37 @@ static void pl011_early_write(struct console *con, const char *s, unsigned n)
 	uart_console_write(&dev->port, s, n, pl011_putc);
 }
 
+#ifdef CONFIG_CONSOLE_POLL
+static int pl011_getc(struct uart_port *port)
+{
+	if (readl(port->membase + UART01x_FR) & UART01x_FR_RXFE)
+		return NO_POLL_CHAR;
+
+	if (port->iotype == UPIO_MEM32)
+		return readl(port->membase + UART01x_DR);
+	else
+		return readb(port->membase + UART01x_DR);
+}
+
+static int pl011_early_read(struct console *con, char *s, unsigned int n)
+{
+	struct earlycon_device *dev = con->data;
+	int ch, num_read = 0;
+
+	while (num_read < n) {
+		ch = pl011_getc(&dev->port);
+		if (ch == NO_POLL_CHAR)
+			break;
+
+		s[num_read++] = ch;
+	}
+
+	return num_read;
+}
+#else
+#define pl011_early_read NULL
+#endif
+
 /*
  * On non-ACPI systems, earlycon is enabled by specifying
  * "earlycon=pl011,<address>" on the kernel command line.
@@ -2454,6 +2485,7 @@ static int __init pl011_early_console_setup(struct earlycon_device *device,
 		return -ENODEV;
 
 	device->con->write = pl011_early_write;
+	device->con->read = pl011_early_read;
 
 	return 0;
 }

drivers/tty/serial/qcom_geni_serial.c

@@ -1090,6 +1090,36 @@ static void qcom_geni_serial_earlycon_write(struct console *con,
 	__qcom_geni_serial_console_write(&dev->port, s, n);
 }
 
+#ifdef CONFIG_CONSOLE_POLL
+static int qcom_geni_serial_earlycon_read(struct console *con,
+					  char *s, unsigned int n)
+{
+	struct earlycon_device *dev = con->data;
+	struct uart_port *uport = &dev->port;
+	int num_read = 0;
+	int ch;
+
+	while (num_read < n) {
+		ch = qcom_geni_serial_get_char(uport);
+		if (ch == NO_POLL_CHAR)
+			break;
+		s[num_read++] = ch;
+	}
+
+	return num_read;
+}
+
+static void __init qcom_geni_serial_enable_early_read(struct geni_se *se,
+						      struct console *con)
+{
+	geni_se_setup_s_cmd(se, UART_START_READ, 0);
+	con->read = qcom_geni_serial_earlycon_read;
+}
+#else
+static inline void qcom_geni_serial_enable_early_read(struct geni_se *se,
+						      struct console *con) { }
+#endif
+
 static int __init qcom_geni_serial_earlycon_setup(struct earlycon_device *dev,
 								const char *opt)
 {
@@ -1136,6 +1166,8 @@ static int __init qcom_geni_serial_earlycon_setup(struct earlycon_device *dev,
 
 	dev->con->write = qcom_geni_serial_earlycon_write;
 	dev->con->setup = NULL;
+	qcom_geni_serial_enable_early_read(&se, dev->con);
+
 	return 0;
 }
 OF_EARLYCON_DECLARE(qcom_geni, "qcom,geni-debug-uart",

include/linux/kdb.h

@@ -125,7 +125,7 @@ extern const char *kdb_diemsg;
 #define KDB_FLAG_NO_I8042	(1 << 7) /* No i8042 chip is available, do
 					  * not use keyboard */
 
-extern int kdb_flags;	/* Global flags, see kdb_state for per cpu state */
+extern unsigned int kdb_flags;	/* Global flags, see kdb_state for per cpu state */
 
 extern void kdb_save_flags(void);
 extern void kdb_restore_flags(void);

include/linux/kgdb.h

@@ -269,6 +269,9 @@ struct kgdb_arch {
  * @write_char: Pointer to a function that will write one char.
  * @flush: Pointer to a function that will flush any pending writes.
  * @init: Pointer to a function that will initialize the device.
+ * @deinit: Pointer to a function that will deinit the device. Implies that
+ * this I/O driver is temporary and expects to be replaced. Called when
+ * an I/O driver is replaced or explicitly unregistered.
  * @pre_exception: Pointer to a function that will do any prep work for
  * the I/O driver.
  * @post_exception: Pointer to a function that will do any cleanup work
@@ -282,6 +285,7 @@ struct kgdb_io {
 	void			(*write_char) (u8);
 	void			(*flush) (void);
 	int			(*init) (void);
+	void			(*deinit) (void);
 	void			(*pre_exception) (void);
 	void			(*post_exception) (void);
 	int			is_console;
@@ -298,7 +302,7 @@ extern bool kgdb_nmi_poll_knock(void);
 #else
 static inline int kgdb_register_nmi_console(void) { return 0; }
 static inline int kgdb_unregister_nmi_console(void) { return 0; }
-static inline bool kgdb_nmi_poll_knock(void) { return 1; }
+static inline bool kgdb_nmi_poll_knock(void) { return true; }
 #endif
 
 extern int kgdb_register_io_module(struct kgdb_io *local_kgdb_io_ops);
@@ -323,7 +327,7 @@ extern void gdbstub_exit(int status);
 extern int			kgdb_single_step;
 extern atomic_t			kgdb_active;
 #define in_dbg_master() \
-	(raw_smp_processor_id() == atomic_read(&kgdb_active))
+	(irqs_disabled() && (smp_processor_id() == atomic_read(&kgdb_active)))
 extern bool dbg_is_early;
 extern void __init dbg_late_init(void);
 extern void kgdb_panic(const char *msg);

kernel/debug/debug_core.c

@@ -67,9 +67,7 @@ static int kgdb_break_asap;
 
 struct debuggerinfo_struct kgdb_info[NR_CPUS];
 
-/**
- * kgdb_connected - Is a host GDB connected to us?
- */
+/* kgdb_connected - Is a host GDB connected to us? */
 int				kgdb_connected;
 EXPORT_SYMBOL_GPL(kgdb_connected);
 
@@ -532,6 +530,7 @@ static int kgdb_reenter_check(struct kgdb_state *ks)
 
 	if (exception_level > 1) {
 		dump_stack();
+		kgdb_io_module_registered = false;
 		panic("Recursive entry to debugger");
 	}
 
@@ -668,6 +667,8 @@ static int kgdb_cpu_enter(struct kgdb_state *ks, struct pt_regs *regs,
 	if (kgdb_skipexception(ks->ex_vector, ks->linux_regs))
 		goto kgdb_restore;
 
+	atomic_inc(&ignore_console_lock_warning);
+
 	/* Call the I/O driver's pre_exception routine */
 	if (dbg_io_ops->pre_exception)
 		dbg_io_ops->pre_exception();
@@ -740,6 +741,8 @@ static int kgdb_cpu_enter(struct kgdb_state *ks, struct pt_regs *regs,
 	if (dbg_io_ops->post_exception)
 		dbg_io_ops->post_exception();
 
+	atomic_dec(&ignore_console_lock_warning);
+
 	if (!kgdb_single_step) {
 		raw_spin_unlock(&dbg_slave_lock);
 		/* Wait till all the CPUs have quit from the debugger. */
@@ -946,6 +949,14 @@ void kgdb_panic(const char *msg)
 	kgdb_breakpoint();
 }
 
+static void kgdb_initial_breakpoint(void)
+{
+	kgdb_break_asap = 0;
+
+	pr_crit("Waiting for connection from remote gdb...\n");
+	kgdb_breakpoint();
+}
+
 void __weak kgdb_arch_late(void)
 {
 }
@@ -956,6 +967,9 @@ void __init dbg_late_init(void)
 	if (kgdb_io_module_registered)
 		kgdb_arch_late();
 	kdb_init(KDB_INIT_FULL);
+
+	if (kgdb_io_module_registered && kgdb_break_asap)
+		kgdb_initial_breakpoint();
 }
 
 static int
@@ -1051,14 +1065,6 @@ void kgdb_schedule_breakpoint(void)
 }
 EXPORT_SYMBOL_GPL(kgdb_schedule_breakpoint);
 
-static void kgdb_initial_breakpoint(void)
-{
-	kgdb_break_asap = 0;
-
-	pr_crit("Waiting for connection from remote gdb...\n");
-	kgdb_breakpoint();
-}
-
 /**
  *	kgdb_register_io_module - register KGDB IO module
  *	@new_dbg_io_ops: the io ops vector
@@ -1067,15 +1073,22 @@ static void kgdb_initial_breakpoint(void)
  */
 int kgdb_register_io_module(struct kgdb_io *new_dbg_io_ops)
 {
+	struct kgdb_io *old_dbg_io_ops;
 	int err;
 
 	spin_lock(&kgdb_registration_lock);
 
-	if (dbg_io_ops) {
-		spin_unlock(&kgdb_registration_lock);
+	old_dbg_io_ops = dbg_io_ops;
+	if (old_dbg_io_ops) {
+		if (!old_dbg_io_ops->deinit) {
+			spin_unlock(&kgdb_registration_lock);
 
-		pr_err("Another I/O driver is already registered with KGDB\n");
-		return -EBUSY;
+			pr_err("KGDB I/O driver %s can't replace %s.\n",
+				new_dbg_io_ops->name, old_dbg_io_ops->name);
+			return -EBUSY;
+		}
+		pr_info("Replacing I/O driver %s with %s\n",
+			old_dbg_io_ops->name, new_dbg_io_ops->name);
 	}
 
 	if (new_dbg_io_ops->init) {
@@ -1090,12 +1103,18 @@ int kgdb_register_io_module(struct kgdb_io *new_dbg_io_ops)
 
 	spin_unlock(&kgdb_registration_lock);
 
+	if (old_dbg_io_ops) {
+		old_dbg_io_ops->deinit();
+		return 0;
+	}
+
 	pr_info("Registered I/O driver %s\n", new_dbg_io_ops->name);
 
 	/* Arm KGDB now. */
 	kgdb_register_callbacks();
 
-	if (kgdb_break_asap)
+	if (kgdb_break_asap &&
+	    (!dbg_is_early || IS_ENABLED(CONFIG_ARCH_HAS_EARLY_DEBUG)))
 		kgdb_initial_breakpoint();
 
 	return 0;
@@ -1125,6 +1144,9 @@ void kgdb_unregister_io_module(struct kgdb_io *old_dbg_io_ops)
 
 	spin_unlock(&kgdb_registration_lock);
 
+	if (old_dbg_io_ops->deinit)
+		old_dbg_io_ops->deinit();
+
 	pr_info("Unregistered I/O driver %s, debugger disabled\n",
 		old_dbg_io_ops->name);
 }
@@ -1165,7 +1187,8 @@ static int __init opt_kgdb_wait(char *str)
 	kgdb_break_asap = 1;
 
 	kdb_init(KDB_INIT_EARLY);
-	if (kgdb_io_module_registered)
+	if (kgdb_io_module_registered &&
+	    IS_ENABLED(CONFIG_ARCH_HAS_EARLY_DEBUG))
 		kgdb_initial_breakpoint();
 
 	return 0;

kernel/debug/kdb/kdb_main.c

@@ -62,7 +62,7 @@ int kdb_grep_trailing;
 /*
  * Kernel debugger state flags
  */
-int kdb_flags;
+unsigned int kdb_flags;
 
 /*
  * kdb_lock protects updates to kdb_initial_cpu.  Used to
@@ -418,8 +418,7 @@ int kdb_set(int argc, const char **argv)
 				    argv[2]);
 			return 0;
 		}
-		kdb_flags = (kdb_flags &
-			     ~(KDB_DEBUG_FLAG_MASK << KDB_DEBUG_FLAG_SHIFT))
+		kdb_flags = (kdb_flags & ~KDB_DEBUG(MASK))
 			| (debugflags << KDB_DEBUG_FLAG_SHIFT);
 
 		return 0;
@@ -1108,7 +1107,8 @@ static int handle_ctrl_cmd(char *cmd)
 	switch (*cmd) {
 	case CTRL_P:
 		if (cmdptr != cmd_tail)
-			cmdptr = (cmdptr-1) % KDB_CMD_HISTORY_COUNT;
+			cmdptr = (cmdptr + KDB_CMD_HISTORY_COUNT - 1) %
+				 KDB_CMD_HISTORY_COUNT;
 		strscpy(cmd_cur, cmd_hist[cmdptr], CMD_BUFLEN);
 		return 1;
 	case CTRL_N:
@@ -2081,7 +2081,8 @@ static int kdb_env(int argc, const char **argv)
 	}
 
 	if (KDB_DEBUG(MASK))
-		kdb_printf("KDBFLAGS=0x%x\n", kdb_flags);
+		kdb_printf("KDBDEBUG=0x%x\n",
+			(kdb_flags & KDB_DEBUG(MASK)) >> KDB_DEBUG_FLAG_SHIFT);
 
 	return 0;
 }

lib/Kconfig.kgdb

@@ -124,4 +124,22 @@ config KDB_CONTINUE_CATASTROPHIC
 	  CONFIG_KDB_CONTINUE_CATASTROPHIC == 2. KDB forces a reboot.
 	  If you are not sure, say 0.
 
+config ARCH_HAS_EARLY_DEBUG
+	bool
+	default n
+	help
+	  If an architecture can definitely handle entering the debugger
+	  when early_param's are parsed then it select this config.
+	  Otherwise, if "kgdbwait" is passed on the kernel command line it
+	  won't actually be processed until dbg_late_init() just after the
+	  call to kgdb_arch_late() is made.
+
+	  NOTE: Even if this isn't selected by an architecture we will
+	  still try to register kgdb to handle breakpoints and crashes
+	  when early_param's are parsed, we just won't act on the
+	  "kgdbwait" parameter until dbg_late_init().  If you get a
+	  crash and try to drop into kgdb somewhere between these two
+	  places you might or might not end up being able to use kgdb
+	  depending on exactly how far along the architecture has initted.
+
 endif # KGDB