printk changes for 5.15

-----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCAAdFiEESH4wyp42V4tXvYsjUqAMR0iAlPIFAmEt+hwACgkQUqAMR0iA
 lPLppBAAiyrUNVmqqtdww+IJajEs1uD/4FqPsysHRwroHBFymJeQG1XCwUpDZ7jj
 6gXT0chxyjQE18gT/W9nf+PSmA9XvIVA1WSR+WCECTNW3YoZXqtgwiHfgnitXYku
 HlmoZLthYeuoXWw2wn+hVLfTRh6VcPHYEaC21jXrs6B1pOXHbvjJ5eTLHlX9oCfL
 UKSK+jFTHAJcn/GskRzviBe0Hpe8fqnkRol2XX13ltxqtQ73MjaGNu7imEH6/Pa7
 /MHXWtuWJtOvuYz17aztQP4Qwh1xy+kakMy3aHucdlxRBTP4PTzzTuQI3L/RYi6l
 +ttD7OHdRwqFAauBLY3bq3uJjYb5v/64ofd8DNnT2CJvtznY8wrPbTdFoSdPcL2Q
 69/opRWHcUwbU/Gt4WLtyQf3Mk0vepgMbbVg1B5SSy55atRZaXMrA2QJ/JeawZTB
 KK6D/mE7ccze/YFzsySunCUVKCm0veoNxEAcakCCZKXSbsvd1MYcIRC0e+2cv6e5
 2NEH7gL4dD+5tqu5nzvIuKDn3NrDQpbi28iUBoFbkxRgcVyvHJ9AGSa62wtb5h3D
 OgkqQMdVKBbjYNeUodPlQPzmXZDasytavyd0/BC/KENOcBvU/8gW++2UZTfsh/1A
 dLjgwFBdyJncQcCS9Abn20/EKntbIMEX8NLa97XWkA3fuzMKtak=
 =yEVq
 -----END PGP SIGNATURE-----

Merge tag 'printk-for-5.15' of git://git.kernel.org/pub/scm/linux/kernel/git/printk/linux

Pull printk updates from Petr Mladek:

 - Optionally, provide an index of possible printk messages via
   <debugfs>/printk/index/. It can be used when monitoring important
   kernel messages on a farm of various hosts. The monitor has to be
   updated when some messages has changed or are not longer available by
   a newly deployed kernel.

 - Add printk.console_no_auto_verbose boot parameter. It allows to
   generate crash dump even with slow consoles in a reasonable time
   frame.

 - Remove printk_safe buffers. The messages are always stored directly
   to the main logbuffer, even in NMI or recursive context. Also it
   allows to serialize syslog operations by a mutex instead of a spin
   lock.

 - Misc clean up and build fixes.

* tag 'printk-for-5.15' of git://git.kernel.org/pub/scm/linux/kernel/git/printk/linux:
  printk/index: Fix -Wunused-function warning
  lib/nmi_backtrace: Serialize even messages about idle CPUs
  printk: Add printk.console_no_auto_verbose boot parameter
  printk: Remove console_silent()
  lib/test_scanf: Handle n_bits == 0 in random tests
  printk: syslog: close window between wait and read
  printk: convert @syslog_lock to mutex
  printk: remove NMI tracking
  printk: remove safe buffers
  printk: track/limit recursion
  lib/nmi_backtrace: explicitly serialize banner and regs
  printk: Move the printk() kerneldoc comment to its new home
  printk/index: Fix warning about missing prototypes
  MIPS/asm/printk: Fix build failure caused by printk
  printk: index: Add indexing support to dev_printk
  printk: Userspace format indexing support
  printk: Rework parse_prefix into printk_parse_prefix
  printk: Straighten out log_flags into printk_info_flags
  string_helpers: Escape double quotes in escape_special
  printk/console: Check consistent sequence number when handling race in console_unlock()

Documentation/admin-guide/kernel-parameters.txt

@@ -4198,6 +4198,15 @@
 			Format: <bool>  (1/Y/y=enable, 0/N/n=disable)
 			default: disabled
 
+	printk.console_no_auto_verbose=
+			Disable console loglevel raise on oops, panic
+			or lockdep-detected issues (only if lock debug is on).
+			With an exception to setups with low baudrate on
+			serial console, keeping this 0 is a good choice
+			in order to provide more debug information.
+			Format: <bool>
+			default: 0 (auto_verbose is enabled)
+
 	printk.devkmsg={on,off,ratelimit}
 			Control writing to /dev/kmsg.
 			on - unlimited logging to /dev/kmsg from userspace

Documentation/core-api/printk-basics.rst

@@ -107,9 +107,6 @@ also ``CONFIG_DYNAMIC_DEBUG`` in the case of pr_debug()) is defined.
 Function reference
 ==================
 
-.. kernel-doc:: kernel/printk/printk.c
-   :functions: printk
-
 .. kernel-doc:: include/linux/printk.h
-   :functions: pr_emerg pr_alert pr_crit pr_err pr_warn pr_notice pr_info
+   :functions: printk pr_emerg pr_alert pr_crit pr_err pr_warn pr_notice pr_info
       pr_fmt pr_debug pr_devel pr_cont

MAINTAINERS

@@ -15021,6 +15021,11 @@ S:	Maintained
 F:	include/linux/printk.h
 F:	kernel/printk/
 
+PRINTK INDEXING
+R:	Chris Down <chris@chrisdown.name>
+S:	Maintained
+F:	kernel/printk/index.c
+
 PROC FILESYSTEM
 L:	linux-kernel@vger.kernel.org
 L:	linux-fsdevel@vger.kernel.org

arch/arm/kernel/entry-v7m.S

@@ -23,7 +23,7 @@ __invalid_entry:
 	adr	r0, strerr
 	mrs	r1, ipsr
 	mov	r2, lr
-	bl	printk
+	bl	_printk
 #endif
 	mov	r0, sp
 	bl	show_regs

arch/arm/kernel/smp.c

@@ -667,9 +667,9 @@ static void do_handle_IPI(int ipinr)
 		break;
 
 	case IPI_CPU_BACKTRACE:
-		printk_nmi_enter();
+		printk_deferred_enter();
 		nmi_cpu_backtrace(get_irq_regs());
-		printk_nmi_exit();
+		printk_deferred_exit();
 		break;
 
 	default:

arch/arm/lib/backtrace-clang.S

@@ -202,7 +202,7 @@ finished_setup:
 1006:		adr	r0, .Lbad
 		mov	r1, loglvl
 		mov	r2, frame
-		bl	printk
+		bl	_printk
 no_frame:	ldmfd	sp!, {r4 - r9, fp, pc}
 ENDPROC(c_backtrace)
 		.pushsection __ex_table,"a"

arch/arm/lib/backtrace.S

@@ -103,7 +103,7 @@ for_each_frame:	tst	frame, mask		@ Check for address exceptions
 1006:		adr	r0, .Lbad
 		mov	r1, loglvl
 		mov	r2, frame
-		bl	printk
+		bl	_printk
 no_frame:	ldmfd	sp!, {r4 - r9, pc}
 ENDPROC(c_backtrace)
 		

arch/arm/mach-rpc/io-acorn.S

@@ -25,4 +25,4 @@ ENTRY(insl)
 ENTRY(outsl)
 		adr	r0, .Liosl_warning
 		mov	r1, lr
-		b	printk
+		b	_printk

arch/arm/vfp/vfphw.S

@@ -23,7 +23,7 @@
 #ifdef DEBUG
 	stmfd	sp!, {r0-r3, ip, lr}
 	ldr	r0, =1f
-	bl	printk
+	bl	_printk
 	ldmfd	sp!, {r0-r3, ip, lr}
 
 	.pushsection .rodata, "a"
@@ -38,7 +38,7 @@
 	stmfd	sp!, {r0-r3, ip, lr}
 	mov	r1, \arg
 	ldr	r0, =1f
-	bl	printk
+	bl	_printk
 	ldmfd	sp!, {r0-r3, ip, lr}
 
 	.pushsection .rodata, "a"
@@ -55,7 +55,7 @@
 	mov	r2, \arg2
 	mov	r1, \arg1
 	ldr	r0, =1f
-	bl	printk
+	bl	_printk
 	ldmfd	sp!, {r0-r3, ip, lr}
 
 	.pushsection .rodata, "a"

arch/ia64/include/uapi/asm/cmpxchg.h

@@ -143,9 +143,9 @@ extern long ia64_cmpxchg_called_with_bad_pointer(void);
 do {									\
 	if (_cmpxchg_bugcheck_count-- <= 0) {				\
 		void *ip;						\
-		extern int printk(const char *fmt, ...);		\
+		extern int _printk(const char *fmt, ...);		\
 		ip = (void *) ia64_getreg(_IA64_REG_IP);		\
-		printk("CMPXCHG_BUGCHECK: stuck at %p on word %p\n", ip, (v));\
+		_printk("CMPXCHG_BUGCHECK: stuck at %p on word %p\n", ip, (v));\
 		break;							\
 	}								\
 } while (0)

arch/mips/include/asm/asm.h

@@ -114,7 +114,7 @@ symbol		=	value
 		.set	push;				\
 		.set	reorder;			\
 		PTR_LA	a0, 8f;				\
-		jal	printk;				\
+		jal	_printk;			\
 		.set	pop;				\
 		TEXT(string)
 #else

arch/openrisc/kernel/entry.S

@@ -551,7 +551,7 @@ EXCEPTION_ENTRY(_external_irq_handler)
 	l.movhi r3,hi(42f)
 	l.ori	r3,r3,lo(42f)
 	l.sw    0x0(r1),r3
-	l.jal   printk
+	l.jal   _printk
 	l.sw    0x4(r1),r4
 	l.addi  r1,r1,0x8
 
@@ -681,8 +681,8 @@ _syscall_debug:
 	l.sw    -4(r1),r27
 	l.sw    -8(r1),r11
 	l.addi  r1,r1,-8
-	l.movhi r27,hi(printk)
+	l.movhi r27,hi(_printk)
-	l.ori   r27,r27,lo(printk)
+	l.ori   r27,r27,lo(_printk)
 	l.jalr  r27
 	 l.nop
 	l.addi  r1,r1,8

arch/powerpc/kernel/head_fsl_booke.S

@@ -858,7 +858,7 @@ KernelSPE:
 	ori	r3,r3,87f@l
 	mr	r4,r2		/* current */
 	lwz	r5,_NIP(r1)
-	bl	printk
+	bl	_printk
 #endif
 	b	interrupt_return
 #ifdef CONFIG_PRINTK

arch/powerpc/kernel/traps.c

@@ -171,7 +171,6 @@ extern void panic_flush_kmsg_start(void)
 
 extern void panic_flush_kmsg_end(void)
 {
-	printk_safe_flush_on_panic();
 	kmsg_dump(KMSG_DUMP_PANIC);
 	bust_spinlocks(0);
 	debug_locks_off();

arch/powerpc/kernel/watchdog.c

@@ -184,11 +184,6 @@ static void watchdog_smp_panic(int cpu, u64 tb)
 
 	wd_smp_unlock(&flags);
 
-	printk_safe_flush();
-	/*
-	 * printk_safe_flush() seems to require another print
-	 * before anything actually goes out to console.
-	 */
 	if (sysctl_hardlockup_all_cpu_backtrace)
 		trigger_allbutself_cpu_backtrace();
 

arch/powerpc/kexec/crash.c

@@ -313,7 +313,7 @@ void default_machine_crash_shutdown(struct pt_regs *regs)
 	int (*old_handler)(struct pt_regs *regs);
 
 	/* Avoid hardlocking with irresponsive CPU holding logbuf_lock */
-	printk_nmi_enter();
+	printk_deferred_enter();
 
 	/*
 	 * This function is only called after the system

arch/um/include/shared/user.h

@@ -38,7 +38,8 @@ extern void panic(const char *fmt, ...)
 #define UM_KERN_CONT	KERN_CONT
 
 #ifdef UML_CONFIG_PRINTK
-extern int printk(const char *fmt, ...)
+#define printk(...) _printk(__VA_ARGS__)
+extern int _printk(const char *fmt, ...)
 	__attribute__ ((format (printf, 1, 2)));
 #else
 static inline int printk(const char *fmt, ...)

arch/x86/kernel/head_32.S

@@ -432,7 +432,7 @@ SYM_FUNC_START(early_ignore_irq)
 	pushl 32(%esp)
 	pushl 40(%esp)
 	pushl $int_msg
-	call printk
+	call _printk
 
 	call dump_stack
 

drivers/base/core.c

@@ -4579,7 +4579,7 @@ static void __dev_printk(const char *level, const struct device *dev,
 		printk("%s(NULL device *): %pV", level, vaf);
 }
 
-void dev_printk(const char *level, const struct device *dev,
+void _dev_printk(const char *level, const struct device *dev,
 		 const char *fmt, ...)
 {
 	struct va_format vaf;
@@ -4594,7 +4594,7 @@ void dev_printk(const char *level, const struct device *dev,
 
 	va_end(args);
 }
-EXPORT_SYMBOL(dev_printk);
+EXPORT_SYMBOL(_dev_printk);
 
 #define define_dev_printk_level(func, kern_level)		\
 void func(const struct device *dev, const char *fmt, ...)	\

include/asm-generic/vmlinux.lds.h

@@ -483,6 +483,8 @@
 									\
 	TRACEDATA							\
 									\
+	PRINTK_INDEX							\
+									\
 	/* Kernel symbol table: Normal symbols */			\
 	__ksymtab         : AT(ADDR(__ksymtab) - LOAD_OFFSET) {		\
 		__start___ksymtab = .;					\
@@ -894,6 +896,17 @@
 #define TRACEDATA
 #endif
 
+#ifdef CONFIG_PRINTK_INDEX
+#define PRINTK_INDEX							\
+	.printk_index : AT(ADDR(.printk_index) - LOAD_OFFSET) {		\
+		__start_printk_index = .;				\
+		*(.printk_index)					\
+		__stop_printk_index = .;				\
+	}
+#else
+#define PRINTK_INDEX
+#endif
+
 #define NOTES								\
 	.notes : AT(ADDR(.notes) - LOAD_OFFSET) {			\
 		__start_notes = .;					\

include/linux/dev_printk.h

@@ -38,7 +38,7 @@ __printf(3, 4) __cold
 int dev_printk_emit(int level, const struct device *dev, const char *fmt, ...);
 
 __printf(3, 4) __cold
-void dev_printk(const char *level, const struct device *dev,
+void _dev_printk(const char *level, const struct device *dev,
 		 const char *fmt, ...);
 __printf(2, 3) __cold
 void _dev_emerg(const struct device *dev, const char *fmt, ...);
@@ -69,7 +69,7 @@ static inline void __dev_printk(const char *level, const struct device *dev,
 				struct va_format *vaf)
 {}
 static inline __printf(3, 4)
-void dev_printk(const char *level, const struct device *dev,
+void _dev_printk(const char *level, const struct device *dev,
 		 const char *fmt, ...)
 {}
 
@@ -97,25 +97,57 @@ void _dev_info(const struct device *dev, const char *fmt, ...)
 
 #endif
 
+/*
+ * Need to take variadic arguments even though we don't use them, as dev_fmt()
+ * may only just have been expanded and may result in multiple arguments.
+ */
+#define dev_printk_index_emit(level, fmt, ...) \
+	printk_index_subsys_emit("%s %s: ", level, fmt)
+
+#define dev_printk_index_wrap(_p_func, level, dev, fmt, ...)		\
+	({								\
+		dev_printk_index_emit(level, fmt);			\
+		_p_func(dev, fmt, ##__VA_ARGS__);			\
+	})
+
+/*
+ * Some callsites directly call dev_printk rather than going through the
+ * dev_<level> infrastructure, so we need to emit here as well as inside those
+ * level-specific macros. Only one index entry will be produced, either way,
+ * since dev_printk's `fmt` isn't known at compile time if going through the
+ * dev_<level> macros.
+ *
+ * dev_fmt() isn't called for dev_printk when used directly, as it's used by
+ * the dev_<level> macros internally which already have dev_fmt() processed.
+ *
+ * We also can't use dev_printk_index_wrap directly, because we have a separate
+ * level to process.
+ */
+#define dev_printk(level, dev, fmt, ...)				\
+	({								\
+		dev_printk_index_emit(level, fmt);			\
+		_dev_printk(level, dev, fmt, ##__VA_ARGS__);		\
+	})
+
 /*
  * #defines for all the dev_<level> macros to prefix with whatever
  * possible use of #define dev_fmt(fmt) ...
  */
 
 #define dev_emerg(dev, fmt, ...) \
-	_dev_emerg(dev, dev_fmt(fmt), ##__VA_ARGS__)
+	dev_printk_index_wrap(_dev_emerg, KERN_EMERG, dev, dev_fmt(fmt), ##__VA_ARGS__)
 #define dev_crit(dev, fmt, ...) \
-	_dev_crit(dev, dev_fmt(fmt), ##__VA_ARGS__)
+	dev_printk_index_wrap(_dev_crit, KERN_CRIT, dev, dev_fmt(fmt), ##__VA_ARGS__)
 #define dev_alert(dev, fmt, ...) \
-	_dev_alert(dev, dev_fmt(fmt), ##__VA_ARGS__)
+	dev_printk_index_wrap(_dev_alert, KERN_ALERT, dev, dev_fmt(fmt), ##__VA_ARGS__)
 #define dev_err(dev, fmt, ...) \
-	_dev_err(dev, dev_fmt(fmt), ##__VA_ARGS__)
+	dev_printk_index_wrap(_dev_err, KERN_ERR, dev, dev_fmt(fmt), ##__VA_ARGS__)
 #define dev_warn(dev, fmt, ...) \
-	_dev_warn(dev, dev_fmt(fmt), ##__VA_ARGS__)
+	dev_printk_index_wrap(_dev_warn, KERN_WARNING, dev, dev_fmt(fmt), ##__VA_ARGS__)
 #define dev_notice(dev, fmt, ...) \
-	_dev_notice(dev, dev_fmt(fmt), ##__VA_ARGS__)
+	dev_printk_index_wrap(_dev_notice, KERN_NOTICE, dev, dev_fmt(fmt), ##__VA_ARGS__)
 #define dev_info(dev, fmt, ...) \
-	_dev_info(dev, dev_fmt(fmt), ##__VA_ARGS__)
+	dev_printk_index_wrap(_dev_info, KERN_INFO, dev, dev_fmt(fmt), ##__VA_ARGS__)
 
 #if defined(CONFIG_DYNAMIC_DEBUG) || \
 	(defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE))

include/linux/hardirq.h

@@ -116,7 +116,6 @@ extern void rcu_nmi_exit(void);
 	do {							\
 		lockdep_off();					\
 		arch_nmi_enter();				\
-		printk_nmi_enter();				\
 		BUG_ON(in_nmi() == NMI_MASK);			\
 		__preempt_count_add(NMI_OFFSET + HARDIRQ_OFFSET);	\
 	} while (0)
@@ -135,7 +134,6 @@ extern void rcu_nmi_exit(void);
 	do {							\
 		BUG_ON(!in_nmi());				\
 		__preempt_count_sub(NMI_OFFSET + HARDIRQ_OFFSET);	\
-		printk_nmi_exit();				\
 		arch_nmi_exit();				\
 		lockdep_on();					\
 	} while (0)

include/linux/module.h

@@ -511,6 +511,11 @@ struct module {
 	struct klp_modinfo *klp_info;
 #endif
 
+#ifdef CONFIG_PRINTK_INDEX
+	unsigned int printk_index_size;
+	struct pi_entry **printk_index_start;
+#endif
+
 #ifdef CONFIG_MODULE_UNLOAD
 	/* What modules depend on me? */
 	struct list_head source_list;

include/linux/printk.h

@@ -70,16 +70,7 @@ extern int console_printk[];
 #define minimum_console_loglevel (console_printk[2])
 #define default_console_loglevel (console_printk[3])
 
-static inline void console_silent(void)
+extern void console_verbose(void);
-{
-	console_loglevel = CONSOLE_LOGLEVEL_SILENT;
-}
-
-static inline void console_verbose(void)
-{
-	if (console_loglevel)
-		console_loglevel = CONSOLE_LOGLEVEL_MOTORMOUTH;
-}
 
 /* strlen("ratelimit") + 1 */
 #define DEVKMSG_STR_MAX_SIZE 10
@@ -150,18 +141,6 @@ static inline __printf(1, 2) __cold
 void early_printk(const char *s, ...) { }
 #endif
 
-#ifdef CONFIG_PRINTK_NMI
-extern void printk_nmi_enter(void);
-extern void printk_nmi_exit(void);
-extern void printk_nmi_direct_enter(void);
-extern void printk_nmi_direct_exit(void);
-#else
-static inline void printk_nmi_enter(void) { }
-static inline void printk_nmi_exit(void) { }
-static inline void printk_nmi_direct_enter(void) { }
-static inline void printk_nmi_direct_exit(void) { }
-#endif /* PRINTK_NMI */
-
 struct dev_printk_info;
 
 #ifdef CONFIG_PRINTK
@@ -174,12 +153,22 @@ asmlinkage __printf(1, 0)
 int vprintk(const char *fmt, va_list args);
 
 asmlinkage __printf(1, 2) __cold
-int printk(const char *fmt, ...);
+int _printk(const char *fmt, ...);
 
 /*
  * Special printk facility for scheduler/timekeeping use only, _DO_NOT_USE_ !
  */
-__printf(1, 2) __cold int printk_deferred(const char *fmt, ...);
+__printf(1, 2) __cold int _printk_deferred(const char *fmt, ...);
+
+extern void __printk_safe_enter(void);
+extern void __printk_safe_exit(void);
+/*
+ * The printk_deferred_enter/exit macros are available only as a hack for
+ * some code paths that need to defer all printk console printing. Interrupts
+ * must be disabled for the deferred duration.
+ */
+#define printk_deferred_enter __printk_safe_enter
+#define printk_deferred_exit __printk_safe_exit
 
 /*
  * Please don't use printk_ratelimit(), because it shares ratelimiting state
@@ -209,8 +198,6 @@ void dump_stack_print_info(const char *log_lvl);
 void show_regs_print_info(const char *log_lvl);
 extern asmlinkage void dump_stack_lvl(const char *log_lvl) __cold;
 extern asmlinkage void dump_stack(void) __cold;
-extern void printk_safe_flush(void);
-extern void printk_safe_flush_on_panic(void);
 #else
 static inline __printf(1, 0)
 int vprintk(const char *s, va_list args)
@@ -218,15 +205,24 @@ int vprintk(const char *s, va_list args)
 	return 0;
 }
 static inline __printf(1, 2) __cold
-int printk(const char *s, ...)
+int _printk(const char *s, ...)
 {
 	return 0;
 }
 static inline __printf(1, 2) __cold
-int printk_deferred(const char *s, ...)
+int _printk_deferred(const char *s, ...)
 {
 	return 0;
 }
+
+static inline void printk_deferred_enter(void)
+{
+}
+
+static inline void printk_deferred_exit(void)
+{
+}
+
 static inline int printk_ratelimit(void)
 {
 	return 0;
@@ -278,14 +274,6 @@ static inline void dump_stack_lvl(const char *log_lvl)
 static inline void dump_stack(void)
 {
 }
-
-static inline void printk_safe_flush(void)
-{
-}
-
-static inline void printk_safe_flush_on_panic(void)
-{
-}
 #endif
 
 #ifdef CONFIG_SMP
@@ -348,6 +336,117 @@ extern int kptr_restrict;
 #define pr_fmt(fmt) fmt
 #endif
 
+struct module;
+
+#ifdef CONFIG_PRINTK_INDEX
+struct pi_entry {
+	const char *fmt;
+	const char *func;
+	const char *file;
+	unsigned int line;
+
+	/*
+	 * While printk and pr_* have the level stored in the string at compile
+	 * time, some subsystems dynamically add it at runtime through the
+	 * format string. For these dynamic cases, we allow the subsystem to
+	 * tell us the level at compile time.
+	 *
+	 * NULL indicates that the level, if any, is stored in fmt.
+	 */
+	const char *level;
+
+	/*
+	 * The format string used by various subsystem specific printk()
+	 * wrappers to prefix the message.
+	 *
+	 * Note that the static prefix defined by the pr_fmt() macro is stored
+	 * directly in the message format (@fmt), not here.
+	 */
+	const char *subsys_fmt_prefix;
+} __packed;
+
+#define __printk_index_emit(_fmt, _level, _subsys_fmt_prefix)		\
+	do {								\
+		if (__builtin_constant_p(_fmt) && __builtin_constant_p(_level)) { \
+			/*
+			 * We check __builtin_constant_p multiple times here
+			 * for the same input because GCC will produce an error
+			 * if we try to assign a static variable to fmt if it
+			 * is not a constant, even with the outer if statement.
+			 */						\
+			static const struct pi_entry _entry		\
+			__used = {					\
+				.fmt = __builtin_constant_p(_fmt) ? (_fmt) : NULL, \
+				.func = __func__,			\
+				.file = __FILE__,			\
+				.line = __LINE__,			\
+				.level = __builtin_constant_p(_level) ? (_level) : NULL, \
+				.subsys_fmt_prefix = _subsys_fmt_prefix,\
+			};						\
+			static const struct pi_entry *_entry_ptr	\
+			__used __section(".printk_index") = &_entry;	\
+		}							\
+	} while (0)
+
+#else /* !CONFIG_PRINTK_INDEX */
+#define __printk_index_emit(...) do {} while (0)
+#endif /* CONFIG_PRINTK_INDEX */
+
+/*
+ * Some subsystems have their own custom printk that applies a va_format to a
+ * generic format, for example, to include a device number or other metadata
+ * alongside the format supplied by the caller.
+ *
+ * In order to store these in the way they would be emitted by the printk
+ * infrastructure, the subsystem provides us with the start, fixed string, and
+ * any subsequent text in the format string.
+ *
+ * We take a variable argument list as pr_fmt/dev_fmt/etc are sometimes passed
+ * as multiple arguments (eg: `"%s: ", "blah"`), and we must only take the
+ * first one.
+ *
+ * subsys_fmt_prefix must be known at compile time, or compilation will fail
+ * (since this is a mistake). If fmt or level is not known at compile time, no
+ * index entry will be made (since this can legitimately happen).
+ */
+#define printk_index_subsys_emit(subsys_fmt_prefix, level, fmt, ...) \
+	__printk_index_emit(fmt, level, subsys_fmt_prefix)
+
+#define printk_index_wrap(_p_func, _fmt, ...)				\
+	({								\
+		__printk_index_emit(_fmt, NULL, NULL);			\
+		_p_func(_fmt, ##__VA_ARGS__);				\
+	})
+
+
+/**
+ * printk - print a kernel message
+ * @fmt: format string
+ *
+ * This is printk(). It can be called from any context. We want it to work.
+ *
+ * If printk indexing is enabled, _printk() is called from printk_index_wrap.
+ * Otherwise, printk is simply #defined to _printk.
+ *
+ * We try to grab the console_lock. If we succeed, it's easy - we log the
+ * output and call the console drivers.  If we fail to get the semaphore, we
+ * place the output into the log buffer and return. The current holder of
+ * the console_sem will notice the new output in console_unlock(); and will
+ * send it to the consoles before releasing the lock.
+ *
+ * One effect of this deferred printing is that code which calls printk() and
+ * then changes console_loglevel may break. This is because console_loglevel
+ * is inspected when the actual printing occurs.
+ *
+ * See also:
+ * printf(3)
+ *
+ * See the vsnprintf() documentation for format string extensions over C99.
+ */
+#define printk(fmt, ...) printk_index_wrap(_printk, fmt, ##__VA_ARGS__)
+#define printk_deferred(fmt, ...)					\
+	printk_index_wrap(_printk_deferred, fmt, ##__VA_ARGS__)
+
 /**
  * pr_emerg - Print an emergency-level message
  * @fmt: format string

init/Kconfig

@@ -775,6 +775,20 @@ config PRINTK_SAFE_LOG_BUF_SHIFT
 		     13 =>   8 KB for each CPU
 		     12 =>   4 KB for each CPU
 
+config PRINTK_INDEX
+	bool "Printk indexing debugfs interface"
+	depends on PRINTK && DEBUG_FS
+	help
+	  Add support for indexing of all printk formats known at compile time
+	  at <debugfs>/printk/index/<module>.
+
+	  This can be used as part of maintaining daemons which monitor
+	  /dev/kmsg, as it permits auditing the printk formats present in a
+	  kernel, allowing detection of cases where monitored printks are
+	  changed or no longer present.
+
+	  There is no additional runtime cost to printk with this enabled.
+
 #
 # Architectures with an unreliable sched_clock() should select this:
 #
@@ -1509,11 +1523,6 @@ config PRINTK
 	  very difficult to diagnose system problems, saying N here is
 	  strongly discouraged.
 
-config PRINTK_NMI
-	def_bool y
-	depends on PRINTK
-	depends on HAVE_NMI
-
 config BUG
 	bool "BUG() support" if EXPERT
 	default y

kernel/kexec_core.c

@@ -979,7 +979,6 @@ void crash_kexec(struct pt_regs *regs)
 	old_cpu = atomic_cmpxchg(&panic_cpu, PANIC_CPU_INVALID, this_cpu);
 	if (old_cpu == PANIC_CPU_INVALID) {
 		/* This is the 1st CPU which comes here, so go ahead. */
-		printk_safe_flush_on_panic();
 		__crash_kexec(regs);
 
 		/*

kernel/module.c

@@ -3355,6 +3355,11 @@ static int find_module_sections(struct module *mod, struct load_info *info)
 						sizeof(unsigned long),
 						&mod->num_kprobe_blacklist);
 #endif
+#ifdef CONFIG_PRINTK_INDEX
+	mod->printk_index_start = section_objs(info, ".printk_index",
+					       sizeof(*mod->printk_index_start),
+					       &mod->printk_index_size);
+#endif
 #ifdef CONFIG_HAVE_STATIC_CALL_INLINE
 	mod->static_call_sites = section_objs(info, ".static_call_sites",
 					      sizeof(*mod->static_call_sites),

kernel/panic.c

@@ -248,7 +248,6 @@ void panic(const char *fmt, ...)
 	 * Bypass the panic_cpu check and call __crash_kexec directly.
 	 */
 	if (!_crash_kexec_post_notifiers) {
-		printk_safe_flush_on_panic();
 		__crash_kexec(NULL);
 
 		/*
@@ -272,8 +271,6 @@ void panic(const char *fmt, ...)
 	 */
 	atomic_notifier_call_chain(&panic_notifier_list, 0, buf);
 
-	/* Call flush even twice. It tries harder with a single online CPU */
-	printk_safe_flush_on_panic();
 	kmsg_dump(KMSG_DUMP_PANIC);
 
 	/*

kernel/printk/Makefile

@@ -3,3 +3,4 @@ obj-y	= printk.o
 obj-$(CONFIG_PRINTK)	+= printk_safe.o
 obj-$(CONFIG_A11Y_BRAILLE_CONSOLE)	+= braille.o
 obj-$(CONFIG_PRINTK)	+= printk_ringbuffer.o
+obj-$(CONFIG_PRINTK_INDEX)	+= index.o

kernel/printk/index.c

@@ -0,0 +1,195 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Userspace indexing of printk formats
+ */
+
+#include <linux/debugfs.h>
+#include <linux/module.h>
+#include <linux/printk.h>
+#include <linux/slab.h>
+#include <linux/string_helpers.h>
+
+#include "internal.h"
+
+extern struct pi_entry *__start_printk_index[];
+extern struct pi_entry *__stop_printk_index[];
+
+/* The base dir for module formats, typically debugfs/printk/index/ */
+static struct dentry *dfs_index;
+
+static struct pi_entry *pi_get_entry(const struct module *mod, loff_t pos)
+{
+	struct pi_entry **entries;
+	unsigned int nr_entries;
+
+#ifdef CONFIG_MODULES
+	if (mod) {
+		entries = mod->printk_index_start;
+		nr_entries = mod->printk_index_size;
+	}
+#endif
+
+	if (!mod) {
+		/* vmlinux, comes from linker symbols */
+		entries = __start_printk_index;
+		nr_entries = __stop_printk_index - __start_printk_index;
+	}
+
+	if (pos >= nr_entries)
+		return NULL;
+
+	return entries[pos];
+}
+
+static void *pi_next(struct seq_file *s, void *v, loff_t *pos)
+{
+	const struct module *mod = s->file->f_inode->i_private;
+	struct pi_entry *entry = pi_get_entry(mod, *pos);
+
+	(*pos)++;
+
+	return entry;
+}
+
+static void *pi_start(struct seq_file *s, loff_t *pos)
+{
+	/*
+	 * Make show() print the header line. Do not update *pos because
+	 * pi_next() still has to return the entry at index 0 later.
+	 */
+	if (*pos == 0)
+		return SEQ_START_TOKEN;
+
+	return pi_next(s, NULL, pos);
+}
+
+/*
+ * We need both ESCAPE_ANY and explicit characters from ESCAPE_SPECIAL in @only
+ * because otherwise ESCAPE_NAP will cause double quotes and backslashes to be
+ * ignored for quoting.
+ */
+#define seq_escape_printf_format(s, src) \
+	seq_escape_str(s, src, ESCAPE_ANY | ESCAPE_NAP | ESCAPE_APPEND, "\"\\")
+
+static int pi_show(struct seq_file *s, void *v)
+{
+	const struct pi_entry *entry = v;
+	int level = LOGLEVEL_DEFAULT;
+	enum printk_info_flags flags = 0;
+	u16 prefix_len = 0;
+
+	if (v == SEQ_START_TOKEN) {
+		seq_puts(s, "# <level/flags> filename:line function \"format\"\n");
+		return 0;
+	}
+
+	if (!entry->fmt)
+		return 0;
+
+	if (entry->level)
+		printk_parse_prefix(entry->level, &level, &flags);
+	else
+		prefix_len = printk_parse_prefix(entry->fmt, &level, &flags);
+
+
+	if (flags & LOG_CONT) {
+		/*
+		 * LOGLEVEL_DEFAULT here means "use the same level as the
+		 * message we're continuing from", not the default message
+		 * loglevel, so don't display it as such.
+		 */
+		if (level == LOGLEVEL_DEFAULT)
+			seq_puts(s, "<c>");
+		else
+			seq_printf(s, "<%d,c>", level);
+	} else
+		seq_printf(s, "<%d>", level);
+
+	seq_printf(s, " %s:%d %s \"", entry->file, entry->line, entry->func);
+	if (entry->subsys_fmt_prefix)
+		seq_escape_printf_format(s, entry->subsys_fmt_prefix);
+	seq_escape_printf_format(s, entry->fmt + prefix_len);
+	seq_puts(s, "\"\n");
+
+	return 0;
+}
+
+static void pi_stop(struct seq_file *p, void *v) { }
+
+static const struct seq_operations dfs_index_sops = {
+	.start = pi_start,
+	.next  = pi_next,
+	.show  = pi_show,
+	.stop  = pi_stop,
+};
+
+DEFINE_SEQ_ATTRIBUTE(dfs_index);
+
+#ifdef CONFIG_MODULES
+static const char *pi_get_module_name(struct module *mod)
+{
+	return mod ? mod->name : "vmlinux";
+}
+#else
+static const char *pi_get_module_name(struct module *mod)
+{
+	return "vmlinux";
+}
+#endif
+
+static void pi_create_file(struct module *mod)
+{
+	debugfs_create_file(pi_get_module_name(mod), 0444, dfs_index,
+				       mod, &dfs_index_fops);
+}
+
+#ifdef CONFIG_MODULES
+static void pi_remove_file(struct module *mod)
+{
+	debugfs_remove(debugfs_lookup(pi_get_module_name(mod), dfs_index));
+}
+
+static int pi_module_notify(struct notifier_block *nb, unsigned long op,
+			    void *data)
+{
+	struct module *mod = data;
+
+	switch (op) {
+	case MODULE_STATE_COMING:
+		pi_create_file(mod);
+		break;
+	case MODULE_STATE_GOING:
+		pi_remove_file(mod);
+		break;
+	default: /* we don't care about other module states */
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block module_printk_fmts_nb = {
+	.notifier_call = pi_module_notify,
+};
+
+static void __init pi_setup_module_notifier(void)
+{
+	register_module_notifier(&module_printk_fmts_nb);
+}
+#else
+static inline void __init pi_setup_module_notifier(void) { }
+#endif
+
+static int __init pi_init(void)
+{
+	struct dentry *dfs_root = debugfs_create_dir("printk", NULL);
+
+	dfs_index = debugfs_create_dir("index", dfs_root);
+	pi_setup_module_notifier();
+	pi_create_file(NULL);
+
+	return 0;
+}
+
+/* debugfs comes up on core and must be initialised first */
+postcore_initcall(pi_init);

kernel/printk/internal.h

@@ -6,11 +6,11 @@
 
 #ifdef CONFIG_PRINTK
 
-#define PRINTK_SAFE_CONTEXT_MASK	0x007ffffff
+/* Flags for a single printk record. */
-#define PRINTK_NMI_DIRECT_CONTEXT_MASK	0x008000000
+enum printk_info_flags {
-#define PRINTK_NMI_CONTEXT_MASK		0xff0000000
+	LOG_NEWLINE	= 2,	/* text ended with a newline */
-
+	LOG_CONT	= 8,	/* text is a fragment of a continuation line */
-#define PRINTK_NMI_CONTEXT_OFFSET	0x010000000
+};
 
 __printf(4, 0)
 int vprintk_store(int facility, int level,
@@ -19,10 +19,7 @@ int vprintk_store(int facility, int level,
 
 __printf(1, 0) int vprintk_default(const char *fmt, va_list args);
 __printf(1, 0) int vprintk_deferred(const char *fmt, va_list args);
-void __printk_safe_enter(void);
-void __printk_safe_exit(void);
 
-void printk_safe_init(void);
 bool printk_percpu_data_ready(void);
 
 #define printk_safe_enter_irqsave(flags)	\
@@ -37,20 +34,10 @@ bool printk_percpu_data_ready(void);
 		local_irq_restore(flags);	\
 	} while (0)
 
-#define printk_safe_enter_irq()		\
-	do {					\
-		local_irq_disable();		\
-		__printk_safe_enter();		\
-	} while (0)
-
-#define printk_safe_exit_irq()			\
-	do {					\
-		__printk_safe_exit();		\
-		local_irq_enable();		\
-	} while (0)
-
 void defer_console_output(void);
 
+u16 printk_parse_prefix(const char *text, int *level,
+			enum printk_info_flags *flags);
 #else
 
 /*
@@ -61,9 +48,5 @@ void defer_console_output(void);
 #define printk_safe_enter_irqsave(flags) local_irq_save(flags)
 #define printk_safe_exit_irqrestore(flags) local_irq_restore(flags)
 
-#define printk_safe_enter_irq() local_irq_disable()
-#define printk_safe_exit_irq() local_irq_enable()
-
-static inline void printk_safe_init(void) { }
 static inline bool printk_percpu_data_ready(void) { return false; }
 #endif /* CONFIG_PRINTK */

kernel/printk/printk.c

@@ -350,13 +350,8 @@ static int console_msg_format = MSG_FORMAT_DEFAULT;
  * non-prinatable characters are escaped in the "\xff" notation.
  */
 
-enum log_flags {
-	LOG_NEWLINE	= 2,	/* text ended with a newline */
-	LOG_CONT	= 8,	/* text is a fragment of a continuation line */
-};
-
 /* syslog_lock protects syslog_* variables and write access to clear_seq. */
-static DEFINE_RAW_SPINLOCK(syslog_lock);
+static DEFINE_MUTEX(syslog_lock);
 
 #ifdef CONFIG_PRINTK
 DECLARE_WAIT_QUEUE_HEAD(log_wait);
@@ -732,27 +727,22 @@ static ssize_t devkmsg_read(struct file *file, char __user *buf,
 	if (ret)
 		return ret;
 
-	printk_safe_enter_irq();
 	if (!prb_read_valid(prb, atomic64_read(&user->seq), r)) {
 		if (file->f_flags & O_NONBLOCK) {
 			ret = -EAGAIN;
-			printk_safe_exit_irq();
 			goto out;
 		}
 
-		printk_safe_exit_irq();
 		ret = wait_event_interruptible(log_wait,
 				prb_read_valid(prb, atomic64_read(&user->seq), r));
 		if (ret)
 			goto out;
-		printk_safe_enter_irq();
 	}
 
 	if (r->info->seq != atomic64_read(&user->seq)) {
 		/* our last seen message is gone, return error and reset */
 		atomic64_set(&user->seq, r->info->seq);
 		ret = -EPIPE;
-		printk_safe_exit_irq();
 		goto out;
 	}
 
@@ -762,7 +752,6 @@ static ssize_t devkmsg_read(struct file *file, char __user *buf,
 				  &r->info->dev_info);
 
 	atomic64_set(&user->seq, r->info->seq + 1);
-	printk_safe_exit_irq();
 
 	if (len > count) {
 		ret = -EINVAL;
@@ -797,7 +786,6 @@ static loff_t devkmsg_llseek(struct file *file, loff_t offset, int whence)
 	if (offset)
 		return -ESPIPE;
 
-	printk_safe_enter_irq();
 	switch (whence) {
 	case SEEK_SET:
 		/* the first record */
@@ -818,7 +806,6 @@ static loff_t devkmsg_llseek(struct file *file, loff_t offset, int whence)
 	default:
 		ret = -EINVAL;
 	}
-	printk_safe_exit_irq();
 	return ret;
 }
 
@@ -833,7 +820,6 @@ static __poll_t devkmsg_poll(struct file *file, poll_table *wait)
 
 	poll_wait(file, &log_wait, wait);
 
-	printk_safe_enter_irq();
 	if (prb_read_valid_info(prb, atomic64_read(&user->seq), &info, NULL)) {
 		/* return error when data has vanished underneath us */
 		if (info.seq != atomic64_read(&user->seq))
@@ -841,7 +827,6 @@ static __poll_t devkmsg_poll(struct file *file, poll_table *wait)
 		else
 			ret = EPOLLIN|EPOLLRDNORM;
 	}
-	printk_safe_exit_irq();
 
 	return ret;
 }
@@ -874,9 +859,7 @@ static int devkmsg_open(struct inode *inode, struct file *file)
 	prb_rec_init_rd(&user->record, &user->info,
 			&user->text_buf[0], sizeof(user->text_buf));
 
-	printk_safe_enter_irq();
 	atomic64_set(&user->seq, prb_first_valid_seq(prb));
-	printk_safe_exit_irq();
 
 	file->private_data = user;
 	return 0;
@@ -1042,9 +1025,6 @@ static inline void log_buf_add_cpu(void) {}
 
 static void __init set_percpu_data_ready(void)
 {
-	printk_safe_init();
-	/* Make sure we set this flag only after printk_safe() init is done */
-	barrier();
 	__printk_percpu_data_ready = true;
 }
 
@@ -1082,6 +1062,7 @@ void __init setup_log_buf(int early)
 	struct prb_desc *new_descs;
 	struct printk_info info;
 	struct printk_record r;
+	unsigned int text_size;
 	size_t new_descs_size;
 	size_t new_infos_size;
 	unsigned long flags;
@@ -1142,24 +1123,37 @@ void __init setup_log_buf(int early)
 		 new_descs, ilog2(new_descs_count),
 		 new_infos);
 
-	printk_safe_enter_irqsave(flags);
+	local_irq_save(flags);
 
 	log_buf_len = new_log_buf_len;
 	log_buf = new_log_buf;
 	new_log_buf_len = 0;
 
 	free = __LOG_BUF_LEN;
-	prb_for_each_record(0, &printk_rb_static, seq, &r)
+	prb_for_each_record(0, &printk_rb_static, seq, &r) {
-		free -= add_to_rb(&printk_rb_dynamic, &r);
+		text_size = add_to_rb(&printk_rb_dynamic, &r);
+		if (text_size > free)
+			free = 0;
+		else
+			free -= text_size;
+	}
 
-	/*
-	 * This is early enough that everything is still running on the
-	 * boot CPU and interrupts are disabled. So no new messages will
-	 * appear during the transition to the dynamic buffer.
-	 */
 	prb = &printk_rb_dynamic;
 
-	printk_safe_exit_irqrestore(flags);
+	local_irq_restore(flags);
+
+	/*
+	 * Copy any remaining messages that might have appeared from
+	 * NMI context after copying but before switching to the
+	 * dynamic buffer.
+	 */
+	prb_for_each_record(seq, &printk_rb_static, seq, &r) {
+		text_size = add_to_rb(&printk_rb_dynamic, &r);
+		if (text_size > free)
+			free = 0;
+		else
+			free -= text_size;
+	}
 
 	if (seq != prb_next_seq(&printk_rb_static)) {
 		pr_err("dropped %llu messages\n",
@@ -1481,12 +1475,14 @@ static u64 find_first_fitting_seq(u64 start_seq, u64 max_seq, size_t size,
 	return seq;
 }
 
+/* The caller is responsible for making sure @size is greater than 0. */
 static int syslog_print(char __user *buf, int size)
 {
 	struct printk_info info;
 	struct printk_record r;
 	char *text;
 	int len = 0;
+	u64 seq;
 
 	text = kmalloc(CONSOLE_LOG_MAX, GFP_KERNEL);
 	if (!text)
@@ -1494,17 +1490,35 @@ static int syslog_print(char __user *buf, int size)
 
 	prb_rec_init_rd(&r, &info, text, CONSOLE_LOG_MAX);
 
-	while (size > 0) {
+	mutex_lock(&syslog_lock);
+
+	/*
+	 * Wait for the @syslog_seq record to be available. @syslog_seq may
+	 * change while waiting.
+	 */
+	do {
+		seq = syslog_seq;
+
+		mutex_unlock(&syslog_lock);
+		len = wait_event_interruptible(log_wait, prb_read_valid(prb, seq, NULL));
+		mutex_lock(&syslog_lock);
+
+		if (len)
+			goto out;
+	} while (syslog_seq != seq);
+
+	/*
+	 * Copy records that fit into the buffer. The above cycle makes sure
+	 * that the first record is always available.
+	 */
+	do {
 		size_t n;
 		size_t skip;
+		int err;
 
-		printk_safe_enter_irq();
+		if (!prb_read_valid(prb, syslog_seq, &r))
-		raw_spin_lock(&syslog_lock);
-		if (!prb_read_valid(prb, syslog_seq, &r)) {
-			raw_spin_unlock(&syslog_lock);
-			printk_safe_exit_irq();
 			break;
-		}
+
 		if (r.info->seq != syslog_seq) {
 			/* message is gone, move to next valid one */
 			syslog_seq = r.info->seq;
@@ -1531,13 +1545,15 @@ static int syslog_print(char __user *buf, int size)
 			syslog_partial += n;
 		} else
 			n = 0;
-		raw_spin_unlock(&syslog_lock);
-		printk_safe_exit_irq();
 
 		if (!n)
 			break;
 
-		if (copy_to_user(buf, text + skip, n)) {
+		mutex_unlock(&syslog_lock);
+		err = copy_to_user(buf, text + skip, n);
+		mutex_lock(&syslog_lock);
+
+		if (err) {
 			if (!len)
 				len = -EFAULT;
 			break;
@@ -1546,8 +1562,9 @@ static int syslog_print(char __user *buf, int size)
 		len += n;
 		size -= n;
 		buf += n;
-	}
+	} while (size);
-
+out:
+	mutex_unlock(&syslog_lock);
 	kfree(text);
 	return len;
 }
@@ -1566,7 +1583,6 @@ static int syslog_print_all(char __user *buf, int size, bool clear)
 		return -ENOMEM;
 
 	time = printk_time;
-	printk_safe_enter_irq();
 	/*
 	 * Find first record that fits, including all following records,
 	 * into the user-provided buffer for this dump.
@@ -1587,23 +1603,20 @@ static int syslog_print_all(char __user *buf, int size, bool clear)
 			break;
 		}
 
-		printk_safe_exit_irq();
 		if (copy_to_user(buf + len, text, textlen))
 			len = -EFAULT;
 		else
 			len += textlen;
-		printk_safe_enter_irq();
 
 		if (len < 0)
 			break;
 	}
 
 	if (clear) {
-		raw_spin_lock(&syslog_lock);
+		mutex_lock(&syslog_lock);
 		latched_seq_write(&clear_seq, seq);
-		raw_spin_unlock(&syslog_lock);
+		mutex_unlock(&syslog_lock);
 	}
-	printk_safe_exit_irq();
 
 	kfree(text);
 	return len;
@@ -1611,23 +1624,9 @@ static int syslog_print_all(char __user *buf, int size, bool clear)
 
 static void syslog_clear(void)
 {
-	printk_safe_enter_irq();
+	mutex_lock(&syslog_lock);
-	raw_spin_lock(&syslog_lock);
 	latched_seq_write(&clear_seq, prb_next_seq(prb));
-	raw_spin_unlock(&syslog_lock);
+	mutex_unlock(&syslog_lock);
-	printk_safe_exit_irq();
-}
-
-/* Return a consistent copy of @syslog_seq. */
-static u64 read_syslog_seq_irq(void)
-{
-	u64 seq;
-
-	raw_spin_lock_irq(&syslog_lock);
-	seq = syslog_seq;
-	raw_spin_unlock_irq(&syslog_lock);
-
-	return seq;
 }
 
 int do_syslog(int type, char __user *buf, int len, int source)
@@ -1653,11 +1652,6 @@ int do_syslog(int type, char __user *buf, int len, int source)
 			return 0;
 		if (!access_ok(buf, len))
 			return -EFAULT;
-
-		error = wait_event_interruptible(log_wait,
-				prb_read_valid(prb, read_syslog_seq_irq(), NULL));
-		if (error)
-			return error;
 		error = syslog_print(buf, len);
 		break;
 	/* Read/clear last kernel messages */
@@ -1703,12 +1697,10 @@ int do_syslog(int type, char __user *buf, int len, int source)
 		break;
 	/* Number of chars in the log buffer */
 	case SYSLOG_ACTION_SIZE_UNREAD:
-		printk_safe_enter_irq();
+		mutex_lock(&syslog_lock);
-		raw_spin_lock(&syslog_lock);
 		if (!prb_read_valid_info(prb, syslog_seq, &info, NULL)) {
 			/* No unread messages. */
-			raw_spin_unlock(&syslog_lock);
+			mutex_unlock(&syslog_lock);
-			printk_safe_exit_irq();
 			return 0;
 		}
 		if (info.seq != syslog_seq) {
@@ -1736,8 +1728,7 @@ int do_syslog(int type, char __user *buf, int len, int source)
 			}
 			error -= syslog_partial;
 		}
-		raw_spin_unlock(&syslog_lock);
+		mutex_unlock(&syslog_lock);
-		printk_safe_exit_irq();
 		break;
 	/* Size of the log buffer */
 	case SYSLOG_ACTION_SIZE_BUFFER:
@@ -1940,6 +1931,76 @@ static void call_console_drivers(const char *ext_text, size_t ext_len,
 	}
 }
 
+/*
+ * Recursion is tracked separately on each CPU. If NMIs are supported, an
+ * additional NMI context per CPU is also separately tracked. Until per-CPU
+ * is available, a separate "early tracking" is performed.
+ */
+static DEFINE_PER_CPU(u8, printk_count);
+static u8 printk_count_early;
+#ifdef CONFIG_HAVE_NMI
+static DEFINE_PER_CPU(u8, printk_count_nmi);
+static u8 printk_count_nmi_early;
+#endif
+
+/*
+ * Recursion is limited to keep the output sane. printk() should not require
+ * more than 1 level of recursion (allowing, for example, printk() to trigger
+ * a WARN), but a higher value is used in case some printk-internal errors
+ * exist, such as the ringbuffer validation checks failing.
+ */
+#define PRINTK_MAX_RECURSION 3
+
+/*
+ * Return a pointer to the dedicated counter for the CPU+context of the
+ * caller.
+ */
+static u8 *__printk_recursion_counter(void)
+{
+#ifdef CONFIG_HAVE_NMI
+	if (in_nmi()) {
+		if (printk_percpu_data_ready())
+			return this_cpu_ptr(&printk_count_nmi);
+		return &printk_count_nmi_early;
+	}
+#endif
+	if (printk_percpu_data_ready())
+		return this_cpu_ptr(&printk_count);
+	return &printk_count_early;
+}
+
+/*
+ * Enter recursion tracking. Interrupts are disabled to simplify tracking.
+ * The caller must check the boolean return value to see if the recursion is
+ * allowed. On failure, interrupts are not disabled.
+ *
+ * @recursion_ptr must be a variable of type (u8 *) and is the same variable
+ * that is passed to printk_exit_irqrestore().
+ */
+#define printk_enter_irqsave(recursion_ptr, flags)	\
+({							\
+	bool success = true;				\
+							\
+	typecheck(u8 *, recursion_ptr);			\
+	local_irq_save(flags);				\
+	(recursion_ptr) = __printk_recursion_counter();	\
+	if (*(recursion_ptr) > PRINTK_MAX_RECURSION) {	\
+		local_irq_restore(flags);		\
+		success = false;			\
+	} else {					\
+		(*(recursion_ptr))++;			\
+	}						\
+	success;					\
+})
+
+/* Exit recursion tracking, restoring interrupts. */
+#define printk_exit_irqrestore(recursion_ptr, flags)	\
+	do {						\
+		typecheck(u8 *, recursion_ptr);		\
+		(*(recursion_ptr))--;			\
+		local_irq_restore(flags);		\
+	} while (0)
+
 int printk_delay_msec __read_mostly;
 
 static inline void printk_delay(void)
@@ -1961,23 +2022,24 @@ static inline u32 printk_caller_id(void)
 }
 
 /**
- * parse_prefix - Parse level and control flags.
+ * printk_parse_prefix - Parse level and control flags.
  *
  * @text:     The terminated text message.
  * @level:    A pointer to the current level value, will be updated.
- * @lflags:   A pointer to the current log flags, will be updated.
+ * @flags:    A pointer to the current printk_info flags, will be updated.
  *
  * @level may be NULL if the caller is not interested in the parsed value.
  * Otherwise the variable pointed to by @level must be set to
  * LOGLEVEL_DEFAULT in order to be updated with the parsed value.
  *
- * @lflags may be NULL if the caller is not interested in the parsed value.
+ * @flags may be NULL if the caller is not interested in the parsed value.
- * Otherwise the variable pointed to by @lflags will be OR'd with the parsed
+ * Otherwise the variable pointed to by @flags will be OR'd with the parsed
  * value.
  *
  * Return: The length of the parsed level and control flags.
  */
-static u16 parse_prefix(char *text, int *level, enum log_flags *lflags)
+u16 printk_parse_prefix(const char *text, int *level,
+			enum printk_info_flags *flags)
 {
 	u16 prefix_len = 0;
 	int kern_level;
@@ -1993,8 +2055,8 @@ static u16 parse_prefix(char *text, int *level, enum log_flags *lflags)
 				*level = kern_level - '0';
 			break;
 		case 'c':	/* KERN_CONT */
-			if (lflags)
+			if (flags)
-				*lflags |= LOG_CONT;
+				*flags |= LOG_CONT;
 		}
 
 		prefix_len += 2;
@@ -2004,8 +2066,9 @@ static u16 parse_prefix(char *text, int *level, enum log_flags *lflags)
 	return prefix_len;
 }
 
-static u16 printk_sprint(char *text, u16 size, int facility, enum log_flags *lflags,
+static u16 printk_sprint(char *text, u16 size, int facility,
-			 const char *fmt, va_list args)
+			 enum printk_info_flags *flags, const char *fmt,
+			 va_list args)
 {
 	u16 text_len;
 
@@ -2014,14 +2077,14 @@ static u16 printk_sprint(char *text, u16 size, int facility, enum log_flags *lfl
 	/* Mark and strip a trailing newline. */
 	if (text_len && text[text_len - 1] == '\n') {
 		text_len--;
-		*lflags |= LOG_NEWLINE;
+		*flags |= LOG_NEWLINE;
 	}
 
 	/* Strip log level and control flags. */
 	if (facility == 0) {
 		u16 prefix_len;
 
-		prefix_len = parse_prefix(text, NULL, NULL);
+		prefix_len = printk_parse_prefix(text, NULL, NULL);
 		if (prefix_len) {
 			text_len -= prefix_len;
 			memmove(text, text + prefix_len, text_len);
@@ -2038,13 +2101,16 @@ int vprintk_store(int facility, int level,
 {
 	const u32 caller_id = printk_caller_id();
 	struct prb_reserved_entry e;
-	enum log_flags lflags = 0;
+	enum printk_info_flags flags = 0;
 	struct printk_record r;
+	unsigned long irqflags;
 	u16 trunc_msg_len = 0;
 	char prefix_buf[8];
+	u8 *recursion_ptr;
 	u16 reserve_size;
 	va_list args2;
 	u16 text_len;
+	int ret = 0;
 	u64 ts_nsec;
 
 	/*
@@ -2055,6 +2121,9 @@ int vprintk_store(int facility, int level,
 	 */
 	ts_nsec = local_clock();
 
+	if (!printk_enter_irqsave(recursion_ptr, irqflags))
+		return 0;
+
 	/*
 	 * The sprintf needs to come first since the syslog prefix might be
 	 * passed in as a parameter. An extra byte must be reserved so that
@@ -2070,29 +2139,30 @@ int vprintk_store(int facility, int level,
 
 	/* Extract log level or control flags. */
 	if (facility == 0)
-		parse_prefix(&prefix_buf[0], &level, &lflags);
+		printk_parse_prefix(&prefix_buf[0], &level, &flags);
 
 	if (level == LOGLEVEL_DEFAULT)
 		level = default_message_loglevel;
 
 	if (dev_info)
-		lflags |= LOG_NEWLINE;
+		flags |= LOG_NEWLINE;
 
-	if (lflags & LOG_CONT) {
+	if (flags & LOG_CONT) {
 		prb_rec_init_wr(&r, reserve_size);
 		if (prb_reserve_in_last(&e, prb, &r, caller_id, LOG_LINE_MAX)) {
 			text_len = printk_sprint(&r.text_buf[r.info->text_len], reserve_size,
-						 facility, &lflags, fmt, args);
+						 facility, &flags, fmt, args);
 			r.info->text_len += text_len;
 
-			if (lflags & LOG_NEWLINE) {
+			if (flags & LOG_NEWLINE) {
 				r.info->flags |= LOG_NEWLINE;
 				prb_final_commit(&e);
 			} else {
 				prb_commit(&e);
 			}
 
-			return text_len;
+			ret = text_len;
+			goto out;
 		}
 	}
 
@@ -2108,29 +2178,32 @@ int vprintk_store(int facility, int level,
 
 		prb_rec_init_wr(&r, reserve_size + trunc_msg_len);
 		if (!prb_reserve(&e, prb, &r))
-			return 0;
+			goto out;
 	}
 
 	/* fill message */
-	text_len = printk_sprint(&r.text_buf[0], reserve_size, facility, &lflags, fmt, args);
+	text_len = printk_sprint(&r.text_buf[0], reserve_size, facility, &flags, fmt, args);
 	if (trunc_msg_len)
 		memcpy(&r.text_buf[text_len], trunc_msg, trunc_msg_len);
 	r.info->text_len = text_len + trunc_msg_len;
 	r.info->facility = facility;
 	r.info->level = level & 7;
-	r.info->flags = lflags & 0x1f;
+	r.info->flags = flags & 0x1f;
 	r.info->ts_nsec = ts_nsec;
 	r.info->caller_id = caller_id;
 	if (dev_info)
 		memcpy(&r.info->dev_info, dev_info, sizeof(r.info->dev_info));
 
 	/* A message without a trailing newline can be continued. */
-	if (!(lflags & LOG_NEWLINE))
+	if (!(flags & LOG_NEWLINE))
 		prb_commit(&e);
 	else
 		prb_final_commit(&e);
 
-	return (text_len + trunc_msg_len);
+	ret = text_len + trunc_msg_len;
+out:
+	printk_exit_irqrestore(recursion_ptr, irqflags);
+	return ret;
 }
 
 asmlinkage int vprintk_emit(int facility, int level,
@@ -2139,7 +2212,6 @@ asmlinkage int vprintk_emit(int facility, int level,
 {
 	int printed_len;
 	bool in_sched = false;
-	unsigned long flags;
 
 	/* Suppress unimportant messages after panic happens */
 	if (unlikely(suppress_printk))
@@ -2153,9 +2225,7 @@ asmlinkage int vprintk_emit(int facility, int level,
 	boot_delay_msec(level);
 	printk_delay();
 
-	printk_safe_enter_irqsave(flags);
 	printed_len = vprintk_store(facility, level, dev_info, fmt, args);
-	printk_safe_exit_irqrestore(flags);
 
 	/* If called from the scheduler, we can not call up(). */
 	if (!in_sched) {
@@ -2186,28 +2256,7 @@ int vprintk_default(const char *fmt, va_list args)
 }
 EXPORT_SYMBOL_GPL(vprintk_default);
 
-/**
+asmlinkage __visible int _printk(const char *fmt, ...)
- * printk - print a kernel message
- * @fmt: format string
- *
- * This is printk(). It can be called from any context. We want it to work.
- *
- * We try to grab the console_lock. If we succeed, it's easy - we log the
- * output and call the console drivers.  If we fail to get the semaphore, we
- * place the output into the log buffer and return. The current holder of
- * the console_sem will notice the new output in console_unlock(); and will
- * send it to the consoles before releasing the lock.
- *
- * One effect of this deferred printing is that code which calls printk() and
- * then changes console_loglevel may break. This is because console_loglevel
- * is inspected when the actual printing occurs.
- *
- * See also:
- * printf(3)
- *
- * See the vsnprintf() documentation for format string extensions over C99.
- */
-asmlinkage __visible int printk(const char *fmt, ...)
 {
 	va_list args;
 	int r;
@@ -2218,7 +2267,7 @@ asmlinkage __visible int printk(const char *fmt, ...)
 
 	return r;
 }
-EXPORT_SYMBOL(printk);
+EXPORT_SYMBOL(_printk);
 
 #else /* CONFIG_PRINTK */
 
@@ -2404,6 +2453,18 @@ module_param_named(console_suspend, console_suspend_enabled,
 MODULE_PARM_DESC(console_suspend, "suspend console during suspend"
 	" and hibernate operations");
 
+static bool printk_console_no_auto_verbose;
+
+void console_verbose(void)
+{
+	if (console_loglevel && !printk_console_no_auto_verbose)
+		console_loglevel = CONSOLE_LOGLEVEL_MOTORMOUTH;
+}
+EXPORT_SYMBOL_GPL(console_verbose);
+
+module_param_named(console_no_auto_verbose, printk_console_no_auto_verbose, bool, 0644);
+MODULE_PARM_DESC(console_no_auto_verbose, "Disable console loglevel raise to highest on oops/panic/etc");
+
 /**
  * suspend_console - suspend the console subsystem
  *
@@ -2545,6 +2606,7 @@ void console_unlock(void)
 	bool do_cond_resched, retry;
 	struct printk_info info;
 	struct printk_record r;
+	u64 __maybe_unused next_seq;
 
 	if (console_suspended) {
 		up_console_sem();
@@ -2584,9 +2646,9 @@ again:
 
 	for (;;) {
 		size_t ext_len = 0;
+		int handover;
 		size_t len;
 
-		printk_safe_enter_irqsave(flags);
 skip:
 		if (!prb_read_valid(prb, console_seq, &r))
 			break;
@@ -2636,26 +2698,31 @@ skip:
 		 * were to occur on another CPU, it may wait for this one to
 		 * finish. This task can not be preempted if there is a
 		 * waiter waiting to take over.
+		 *
+		 * Interrupts are disabled because the hand over to a waiter
+		 * must not be interrupted until the hand over is completed
+		 * (@console_waiter is cleared).
 		 */
+		printk_safe_enter_irqsave(flags);
 		console_lock_spinning_enable();
 
 		stop_critical_timings();	/* don't trace print latency */
 		call_console_drivers(ext_text, ext_len, text, len);
 		start_critical_timings();
 
-		if (console_lock_spinning_disable_and_check()) {
+		handover = console_lock_spinning_disable_and_check();
 		printk_safe_exit_irqrestore(flags);
+		if (handover)
 			return;
-		}
-
-		printk_safe_exit_irqrestore(flags);
 
 		if (do_cond_resched)
 			cond_resched();
 	}
 
-	console_locked = 0;
+	/* Get consistent value of the next-to-be-used sequence number. */
+	next_seq = console_seq;
 
+	console_locked = 0;
 	up_console_sem();
 
 	/*
@@ -2664,9 +2731,7 @@ skip:
 	 * there's a new owner and the console_unlock() from them will do the
 	 * flush, no worries.
 	 */
-	retry = prb_read_valid(prb, console_seq, NULL);
+	retry = prb_read_valid(prb, next_seq, NULL);
-	printk_safe_exit_irqrestore(flags);
-
 	if (retry && console_trylock())
 		goto again;
 }
@@ -2728,13 +2793,8 @@ void console_flush_on_panic(enum con_flush_mode mode)
 	console_trylock();
 	console_may_schedule = 0;
 
-	if (mode == CONSOLE_REPLAY_ALL) {
+	if (mode == CONSOLE_REPLAY_ALL)
-		unsigned long flags;
-
-		printk_safe_enter_irqsave(flags);
 		console_seq = prb_first_valid_seq(prb);
-		printk_safe_exit_irqrestore(flags);
-	}
 	console_unlock();
 }
 
@@ -2869,7 +2929,6 @@ static int try_enable_new_console(struct console *newcon, bool user_specified)
  */
 void register_console(struct console *newcon)
 {
-	unsigned long flags;
 	struct console *bcon = NULL;
 	int err;
 
@@ -2974,9 +3033,9 @@ void register_console(struct console *newcon)
 		exclusive_console_stop_seq = console_seq;
 
 		/* Get a consistent copy of @syslog_seq. */
-		raw_spin_lock_irqsave(&syslog_lock, flags);
+		mutex_lock(&syslog_lock);
 		console_seq = syslog_seq;
-		raw_spin_unlock_irqrestore(&syslog_lock, flags);
+		mutex_unlock(&syslog_lock);
 	}
 	console_unlock();
 	console_sysfs_notify();
@@ -3203,7 +3262,7 @@ int vprintk_deferred(const char *fmt, va_list args)
 	return r;
 }
 
-int printk_deferred(const char *fmt, ...)
+int _printk_deferred(const char *fmt, ...)
 {
 	va_list args;
 	int r;
@@ -3386,14 +3445,12 @@ bool kmsg_dump_get_line(struct kmsg_dump_iter *iter, bool syslog,
 	struct printk_info info;
 	unsigned int line_count;
 	struct printk_record r;
-	unsigned long flags;
 	size_t l = 0;
 	bool ret = false;
 
 	if (iter->cur_seq < min_seq)
 		iter->cur_seq = min_seq;
 
-	printk_safe_enter_irqsave(flags);
 	prb_rec_init_rd(&r, &info, line, size);
 
 	/* Read text or count text lines? */
@@ -3414,7 +3471,6 @@ bool kmsg_dump_get_line(struct kmsg_dump_iter *iter, bool syslog,
 	iter->cur_seq = r.info->seq + 1;
 	ret = true;
 out:
-	printk_safe_exit_irqrestore(flags);
 	if (len)
 		*len = l;
 	return ret;
@@ -3446,7 +3502,6 @@ bool kmsg_dump_get_buffer(struct kmsg_dump_iter *iter, bool syslog,
 	u64 min_seq = latched_seq_read_nolock(&clear_seq);
 	struct printk_info info;
 	struct printk_record r;
-	unsigned long flags;
 	u64 seq;
 	u64 next_seq;
 	size_t len = 0;
@@ -3459,7 +3514,6 @@ bool kmsg_dump_get_buffer(struct kmsg_dump_iter *iter, bool syslog,
 	if (iter->cur_seq < min_seq)
 		iter->cur_seq = min_seq;
 
-	printk_safe_enter_irqsave(flags);
 	if (prb_read_valid_info(prb, iter->cur_seq, &info, NULL)) {
 		if (info.seq != iter->cur_seq) {
 			/* messages are gone, move to first available one */
@@ -3468,10 +3522,8 @@ bool kmsg_dump_get_buffer(struct kmsg_dump_iter *iter, bool syslog,
 	}
 
 	/* last entry */
-	if (iter->cur_seq >= iter->next_seq) {
+	if (iter->cur_seq >= iter->next_seq)
-		printk_safe_exit_irqrestore(flags);
 		goto out;
-	}
 
 	/*
 	 * Find first record that fits, including all following records,
@@ -3503,7 +3555,6 @@ bool kmsg_dump_get_buffer(struct kmsg_dump_iter *iter, bool syslog,
 
 	iter->next_seq = next_seq;
 	ret = true;
-	printk_safe_exit_irqrestore(flags);
 out:
 	if (len_out)
 		*len_out = len;
@@ -3521,12 +3572,8 @@ EXPORT_SYMBOL_GPL(kmsg_dump_get_buffer);
  */
 void kmsg_dump_rewind(struct kmsg_dump_iter *iter)
 {
-	unsigned long flags;
-
-	printk_safe_enter_irqsave(flags);
 	iter->cur_seq = latched_seq_read_nolock(&clear_seq);
 	iter->next_seq = prb_next_seq(prb);
-	printk_safe_exit_irqrestore(flags);
 }
 EXPORT_SYMBOL_GPL(kmsg_dump_rewind);
 

kernel/printk/printk_safe.c

@@ -4,347 +4,16 @@
  */
 
 #include <linux/preempt.h>
-#include <linux/spinlock.h>
-#include <linux/debug_locks.h>
 #include <linux/kdb.h>
 #include <linux/smp.h>
 #include <linux/cpumask.h>
-#include <linux/irq_work.h>
 #include <linux/printk.h>
 #include <linux/kprobes.h>
 
 #include "internal.h"
 
-/*
- * In NMI and safe mode, printk() avoids taking locks. Instead,
- * it uses an alternative implementation that temporary stores
- * the strings into a per-CPU buffer. The content of the buffer
- * is later flushed into the main ring buffer via IRQ work.
- *
- * The alternative implementation is chosen transparently
- * by examining current printk() context mask stored in @printk_context
- * per-CPU variable.
- *
- * The implementation allows to flush the strings also from another CPU.
- * There are situations when we want to make sure that all buffers
- * were handled or when IRQs are blocked.
- */
-
-#define SAFE_LOG_BUF_LEN ((1 << CONFIG_PRINTK_SAFE_LOG_BUF_SHIFT) -	\
-				sizeof(atomic_t) -			\
-				sizeof(atomic_t) -			\
-				sizeof(struct irq_work))
-
-struct printk_safe_seq_buf {
-	atomic_t		len;	/* length of written data */
-	atomic_t		message_lost;
-	struct irq_work		work;	/* IRQ work that flushes the buffer */
-	unsigned char		buffer[SAFE_LOG_BUF_LEN];
-};
-
-static DEFINE_PER_CPU(struct printk_safe_seq_buf, safe_print_seq);
 static DEFINE_PER_CPU(int, printk_context);
 
-static DEFINE_RAW_SPINLOCK(safe_read_lock);
-
-#ifdef CONFIG_PRINTK_NMI
-static DEFINE_PER_CPU(struct printk_safe_seq_buf, nmi_print_seq);
-#endif
-
-/* Get flushed in a more safe context. */
-static void queue_flush_work(struct printk_safe_seq_buf *s)
-{
-	if (printk_percpu_data_ready())
-		irq_work_queue(&s->work);
-}
-
-/*
- * Add a message to per-CPU context-dependent buffer. NMI and printk-safe
- * have dedicated buffers, because otherwise printk-safe preempted by
- * NMI-printk would have overwritten the NMI messages.
- *
- * The messages are flushed from irq work (or from panic()), possibly,
- * from other CPU, concurrently with printk_safe_log_store(). Should this
- * happen, printk_safe_log_store() will notice the buffer->len mismatch
- * and repeat the write.
- */
-static __printf(2, 0) int printk_safe_log_store(struct printk_safe_seq_buf *s,
-						const char *fmt, va_list args)
-{
-	int add;
-	size_t len;
-	va_list ap;
-
-again:
-	len = atomic_read(&s->len);
-
-	/* The trailing '\0' is not counted into len. */
-	if (len >= sizeof(s->buffer) - 1) {
-		atomic_inc(&s->message_lost);
-		queue_flush_work(s);
-		return 0;
-	}
-
-	/*
-	 * Make sure that all old data have been read before the buffer
-	 * was reset. This is not needed when we just append data.
-	 */
-	if (!len)
-		smp_rmb();
-
-	va_copy(ap, args);
-	add = vscnprintf(s->buffer + len, sizeof(s->buffer) - len, fmt, ap);
-	va_end(ap);
-	if (!add)
-		return 0;
-
-	/*
-	 * Do it once again if the buffer has been flushed in the meantime.
-	 * Note that atomic_cmpxchg() is an implicit memory barrier that
-	 * makes sure that the data were written before updating s->len.
-	 */
-	if (atomic_cmpxchg(&s->len, len, len + add) != len)
-		goto again;
-
-	queue_flush_work(s);
-	return add;
-}
-
-static inline void printk_safe_flush_line(const char *text, int len)
-{
-	/*
-	 * Avoid any console drivers calls from here, because we may be
-	 * in NMI or printk_safe context (when in panic). The messages
-	 * must go only into the ring buffer at this stage.  Consoles will
-	 * get explicitly called later when a crashdump is not generated.
-	 */
-	printk_deferred("%.*s", len, text);
-}
-
-/* printk part of the temporary buffer line by line */
-static int printk_safe_flush_buffer(const char *start, size_t len)
-{
-	const char *c, *end;
-	bool header;
-
-	c = start;
-	end = start + len;
-	header = true;
-
-	/* Print line by line. */
-	while (c < end) {
-		if (*c == '\n') {
-			printk_safe_flush_line(start, c - start + 1);
-			start = ++c;
-			header = true;
-			continue;
-		}
-
-		/* Handle continuous lines or missing new line. */
-		if ((c + 1 < end) && printk_get_level(c)) {
-			if (header) {
-				c = printk_skip_level(c);
-				continue;
-			}
-
-			printk_safe_flush_line(start, c - start);
-			start = c++;
-			header = true;
-			continue;
-		}
-
-		header = false;
-		c++;
-	}
-
-	/* Check if there was a partial line. Ignore pure header. */
-	if (start < end && !header) {
-		static const char newline[] = KERN_CONT "\n";
-
-		printk_safe_flush_line(start, end - start);
-		printk_safe_flush_line(newline, strlen(newline));
-	}
-
-	return len;
-}
-
-static void report_message_lost(struct printk_safe_seq_buf *s)
-{
-	int lost = atomic_xchg(&s->message_lost, 0);
-
-	if (lost)
-		printk_deferred("Lost %d message(s)!\n", lost);
-}
-
-/*
- * Flush data from the associated per-CPU buffer. The function
- * can be called either via IRQ work or independently.
- */
-static void __printk_safe_flush(struct irq_work *work)
-{
-	struct printk_safe_seq_buf *s =
-		container_of(work, struct printk_safe_seq_buf, work);
-	unsigned long flags;
-	size_t len;
-	int i;
-
-	/*
-	 * The lock has two functions. First, one reader has to flush all
-	 * available message to make the lockless synchronization with
-	 * writers easier. Second, we do not want to mix messages from
-	 * different CPUs. This is especially important when printing
-	 * a backtrace.
-	 */
-	raw_spin_lock_irqsave(&safe_read_lock, flags);
-
-	i = 0;
-more:
-	len = atomic_read(&s->len);
-
-	/*
-	 * This is just a paranoid check that nobody has manipulated
-	 * the buffer an unexpected way. If we printed something then
-	 * @len must only increase. Also it should never overflow the
-	 * buffer size.
-	 */
-	if ((i && i >= len) || len > sizeof(s->buffer)) {
-		const char *msg = "printk_safe_flush: internal error\n";
-
-		printk_safe_flush_line(msg, strlen(msg));
-		len = 0;
-	}
-
-	if (!len)
-		goto out; /* Someone else has already flushed the buffer. */
-
-	/* Make sure that data has been written up to the @len */
-	smp_rmb();
-	i += printk_safe_flush_buffer(s->buffer + i, len - i);
-
-	/*
-	 * Check that nothing has got added in the meantime and truncate
-	 * the buffer. Note that atomic_cmpxchg() is an implicit memory
-	 * barrier that makes sure that the data were copied before
-	 * updating s->len.
-	 */
-	if (atomic_cmpxchg(&s->len, len, 0) != len)
-		goto more;
-
-out:
-	report_message_lost(s);
-	raw_spin_unlock_irqrestore(&safe_read_lock, flags);
-}
-
-/**
- * printk_safe_flush - flush all per-cpu nmi buffers.
- *
- * The buffers are flushed automatically via IRQ work. This function
- * is useful only when someone wants to be sure that all buffers have
- * been flushed at some point.
- */
-void printk_safe_flush(void)
-{
-	int cpu;
-
-	for_each_possible_cpu(cpu) {
-#ifdef CONFIG_PRINTK_NMI
-		__printk_safe_flush(&per_cpu(nmi_print_seq, cpu).work);
-#endif
-		__printk_safe_flush(&per_cpu(safe_print_seq, cpu).work);
-	}
-}
-
-/**
- * printk_safe_flush_on_panic - flush all per-cpu nmi buffers when the system
- *	goes down.
- *
- * Similar to printk_safe_flush() but it can be called even in NMI context when
- * the system goes down. It does the best effort to get NMI messages into
- * the main ring buffer.
- *
- * Note that it could try harder when there is only one CPU online.
- */
-void printk_safe_flush_on_panic(void)
-{
-	/*
-	 * Make sure that we could access the safe buffers.
-	 * Do not risk a double release when more CPUs are up.
-	 */
-	if (raw_spin_is_locked(&safe_read_lock)) {
-		if (num_online_cpus() > 1)
-			return;
-
-		debug_locks_off();
-		raw_spin_lock_init(&safe_read_lock);
-	}
-
-	printk_safe_flush();
-}
-
-#ifdef CONFIG_PRINTK_NMI
-/*
- * Safe printk() for NMI context. It uses a per-CPU buffer to
- * store the message. NMIs are not nested, so there is always only
- * one writer running. But the buffer might get flushed from another
- * CPU, so we need to be careful.
- */
-static __printf(1, 0) int vprintk_nmi(const char *fmt, va_list args)
-{
-	struct printk_safe_seq_buf *s = this_cpu_ptr(&nmi_print_seq);
-
-	return printk_safe_log_store(s, fmt, args);
-}
-
-void noinstr printk_nmi_enter(void)
-{
-	this_cpu_add(printk_context, PRINTK_NMI_CONTEXT_OFFSET);
-}
-
-void noinstr printk_nmi_exit(void)
-{
-	this_cpu_sub(printk_context, PRINTK_NMI_CONTEXT_OFFSET);
-}
-
-/*
- * Marks a code that might produce many messages in NMI context
- * and the risk of losing them is more critical than eventual
- * reordering.
- *
- * It has effect only when called in NMI context. Then printk()
- * will store the messages into the main logbuf directly.
- */
-void printk_nmi_direct_enter(void)
-{
-	if (this_cpu_read(printk_context) & PRINTK_NMI_CONTEXT_MASK)
-		this_cpu_or(printk_context, PRINTK_NMI_DIRECT_CONTEXT_MASK);
-}
-
-void printk_nmi_direct_exit(void)
-{
-	this_cpu_and(printk_context, ~PRINTK_NMI_DIRECT_CONTEXT_MASK);
-}
-
-#else
-
-static __printf(1, 0) int vprintk_nmi(const char *fmt, va_list args)
-{
-	return 0;
-}
-
-#endif /* CONFIG_PRINTK_NMI */
-
-/*
- * Lock-less printk(), to avoid deadlocks should the printk() recurse
- * into itself. It uses a per-CPU buffer to store the message, just like
- * NMI.
- */
-static __printf(1, 0) int vprintk_safe(const char *fmt, va_list args)
-{
-	struct printk_safe_seq_buf *s = this_cpu_ptr(&safe_print_seq);
-
-	return printk_safe_log_store(s, fmt, args);
-}
-
 /* Can be preempted by NMI. */
 void __printk_safe_enter(void)
 {
@@ -369,46 +38,15 @@ asmlinkage int vprintk(const char *fmt, va_list args)
 	 * Use the main logbuf even in NMI. But avoid calling console
 	 * drivers that might have their own locks.
 	 */
-	if ((this_cpu_read(printk_context) & PRINTK_NMI_DIRECT_CONTEXT_MASK)) {
+	if (this_cpu_read(printk_context) || in_nmi()) {
-		unsigned long flags;
 		int len;
 
-		printk_safe_enter_irqsave(flags);
 		len = vprintk_store(0, LOGLEVEL_DEFAULT, NULL, fmt, args);
-		printk_safe_exit_irqrestore(flags);
 		defer_console_output();
 		return len;
 	}
 
-	/* Use extra buffer in NMI. */
-	if (this_cpu_read(printk_context) & PRINTK_NMI_CONTEXT_MASK)
-		return vprintk_nmi(fmt, args);
-
-	/* Use extra buffer to prevent a recursion deadlock in safe mode. */
-	if (this_cpu_read(printk_context) & PRINTK_SAFE_CONTEXT_MASK)
-		return vprintk_safe(fmt, args);
-
 	/* No obstacles. */
 	return vprintk_default(fmt, args);
 }
 EXPORT_SYMBOL(vprintk);
-
-void __init printk_safe_init(void)
-{
-	int cpu;
-
-	for_each_possible_cpu(cpu) {
-		struct printk_safe_seq_buf *s;
-
-		s = &per_cpu(safe_print_seq, cpu);
-		init_irq_work(&s->work, __printk_safe_flush);
-
-#ifdef CONFIG_PRINTK_NMI
-		s = &per_cpu(nmi_print_seq, cpu);
-		init_irq_work(&s->work, __printk_safe_flush);
-#endif
-	}
-
-	/* Flush pending messages that did not have scheduled IRQ works. */
-	printk_safe_flush();
-}

kernel/trace/trace.c

@@ -9815,7 +9815,6 @@ void ftrace_dump(enum ftrace_dump_mode oops_dump_mode)
 	tracing_off();
 
 	local_irq_save(flags);
-	printk_nmi_direct_enter();
 
 	/* Simulate the iterator */
 	trace_init_global_iter(&iter);
@@ -9897,7 +9896,6 @@ void ftrace_dump(enum ftrace_dump_mode oops_dump_mode)
 		atomic_dec(&per_cpu_ptr(iter.array_buffer->data, cpu)->disabled);
 	}
 	atomic_dec(&dump_running);
-	printk_nmi_direct_exit();
 	local_irq_restore(flags);
 }
 EXPORT_SYMBOL_GPL(ftrace_dump);

lib/nmi_backtrace.c

@@ -75,12 +75,6 @@ void nmi_trigger_cpumask_backtrace(const cpumask_t *mask,
 		touch_softlockup_watchdog();
 	}
 
-	/*
-	 * Force flush any remote buffers that might be stuck in IRQ context
-	 * and therefore could not run their irq_work.
-	 */
-	printk_safe_flush();
-
 	clear_bit_unlock(0, &backtrace_flag);
 	put_cpu();
 }
@@ -92,8 +86,14 @@ module_param(backtrace_idle, bool, 0644);
 bool nmi_cpu_backtrace(struct pt_regs *regs)
 {
 	int cpu = smp_processor_id();
+	unsigned long flags;
 
 	if (cpumask_test_cpu(cpu, to_cpumask(backtrace_mask))) {
+		/*
+		 * Allow nested NMI backtraces while serializing
+		 * against other CPUs.
+		 */
+		printk_cpu_lock_irqsave(flags);
 		if (!READ_ONCE(backtrace_idle) && regs && cpu_in_idle(instruction_pointer(regs))) {
 			pr_warn("NMI backtrace for cpu %d skipped: idling at %pS\n",
 				cpu, (void *)instruction_pointer(regs));
@@ -104,6 +104,7 @@ bool nmi_cpu_backtrace(struct pt_regs *regs)
 			else
 				dump_stack();
 		}
+		printk_cpu_unlock_irqrestore(flags);
 		cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask));
 		return true;
 	}

lib/string_helpers.c

@@ -361,6 +361,9 @@ static bool escape_special(unsigned char c, char **dst, char *end)
 	case '\e':
 		to = 'e';
 		break;
+	case '"':
+		to = '"';
+		break;
 	default:
 		return false;
 	}
@@ -474,6 +477,7 @@ static bool escape_hex(unsigned char c, char **dst, char *end)
  *		'\t' - horizontal tab
  *		'\v' - vertical tab
  *	%ESCAPE_SPECIAL:
+ *		'\"' - double quote
  *		'\\' - backslash
  *		'\a' - alert (BEL)
  *		'\e' - escape

lib/test-string_helpers.c

@@ -140,13 +140,13 @@ static const struct test_string_2 escape0[] __initconst = {{
 },{
 	.in = "\\h\\\"\a\e\\",
 	.s1 = {{
-		.out = "\\\\h\\\\\"\\a\\e\\\\",
+		.out = "\\\\h\\\\\\\"\\a\\e\\\\",
 		.flags = ESCAPE_SPECIAL,
 	},{
-		.out = "\\\\\\150\\\\\\042\\a\\e\\\\",
+		.out = "\\\\\\150\\\\\\\"\\a\\e\\\\",
 		.flags = ESCAPE_SPECIAL | ESCAPE_OCTAL,
 	},{
-		.out = "\\\\\\x68\\\\\\x22\\a\\e\\\\",
+		.out = "\\\\\\x68\\\\\\\"\\a\\e\\\\",
 		.flags = ESCAPE_SPECIAL | ESCAPE_HEX,
 	},{
 		/* terminator */
@@ -157,10 +157,10 @@ static const struct test_string_2 escape0[] __initconst = {{
 		.out = "\eb \\C\007\"\x90\\r]",
 		.flags = ESCAPE_SPACE,
 	},{
-		.out = "\\eb \\\\C\\a\"\x90\r]",
+		.out = "\\eb \\\\C\\a\\\"\x90\r]",
 		.flags = ESCAPE_SPECIAL,
 	},{
-		.out = "\\eb \\\\C\\a\"\x90\\r]",
+		.out = "\\eb \\\\C\\a\\\"\x90\\r]",
 		.flags = ESCAPE_SPACE | ESCAPE_SPECIAL,
 	},{
 		.out = "\\033\\142\\040\\134\\103\\007\\042\\220\\015\\135",
@@ -169,10 +169,10 @@ static const struct test_string_2 escape0[] __initconst = {{
 		.out = "\\033\\142\\040\\134\\103\\007\\042\\220\\r\\135",
 		.flags = ESCAPE_SPACE | ESCAPE_OCTAL,
 	},{
-		.out = "\\e\\142\\040\\\\\\103\\a\\042\\220\\015\\135",
+		.out = "\\e\\142\\040\\\\\\103\\a\\\"\\220\\015\\135",
 		.flags = ESCAPE_SPECIAL | ESCAPE_OCTAL,
 	},{
-		.out = "\\e\\142\\040\\\\\\103\\a\\042\\220\\r\\135",
+		.out = "\\e\\142\\040\\\\\\103\\a\\\"\\220\\r\\135",
 		.flags = ESCAPE_SPACE | ESCAPE_SPECIAL | ESCAPE_OCTAL,
 	},{
 		.out = "\eb \\C\007\"\x90\r]",

lib/test_scanf.c

@@ -271,7 +271,7 @@ static u32 __init next_test_random(u32 max_bits)
 {
 	u32 n_bits = hweight32(prandom_u32_state(&rnd_state)) % (max_bits + 1);
 
-	return prandom_u32_state(&rnd_state) & (UINT_MAX >> (32 - n_bits));
+	return prandom_u32_state(&rnd_state) & GENMASK(n_bits, 0);
 }
 
 static unsigned long long __init next_test_random_ull(void)
@@ -280,7 +280,7 @@ static unsigned long long __init next_test_random_ull(void)
 	u32 n_bits = (hweight32(rand1) * 3) % 64;
 	u64 val = (u64)prandom_u32_state(&rnd_state) * rand1;
 
-	return val & (ULLONG_MAX >> (64 - n_bits));
+	return val & GENMASK_ULL(n_bits, 0);
 }
 
 #define random_for_type(T)				\