Merge tag 'printk-for-5.10' of git://git.kernel.org/pub/scm/linux/kernel/git/printk/linux

Pull printk updates from Petr Mladek:
 "The big new thing is the fully lockless ringbuffer implementation,
  including the support for continuous lines. It will allow to store and
  read messages in any situation wihtout the risk of deadlocks and
  without the need of temporary per-CPU buffers.

  The access is still serialized by logbuf_lock. It synchronizes few
  more operations, for example, temporary buffer for formatting the
  message, syslog and kmsg_dump operations. The lock removal is being
  discussed and should be ready for the next release.

  The continuous lines are handled exactly the same way as before to
  avoid regressions in user space. It means that they are appended to
  the last message when the caller is the same. Only the last message
  can be extended.

  The data ring includes plain text of the messages. Except for an
  integer at the beginning of each message that points back to the
  descriptor ring with other metadata.

  The dictionary has to stay. journalctl uses it to filter the log. It
  allows to show messages related to a given device. The dictionary
  values are stored in the descriptor ring with the other metadata.

  This is the first part of the printk rework as discussed at Plumbers
  2019, see https://lore.kernel.org/r/87k1acz5rx.fsf@linutronix.de. The
  next big step will be handling consoles by kthreads during the normal
  system operation. It will require special handling of situations when
  the kthreads could not get scheduled, for example, early boot,
  suspend, panic.

  Other changes:

   - Add John Ogness as a reviewer for printk subsystem. He is author of
     the rework and is familiar with the code and history.

   - Fix locking in serial8250_do_startup() to prevent lockdep report.

   - Few code cleanups"

* tag 'printk-for-5.10' of git://git.kernel.org/pub/scm/linux/kernel/git/printk/linux: (27 commits)
  printk: Use fallthrough pseudo-keyword
  printk: reduce setup_text_buf size to LOG_LINE_MAX
  printk: avoid and/or handle record truncation
  printk: remove dict ring
  printk: move dictionary keys to dev_printk_info
  printk: move printk_info into separate array
  printk: reimplement log_cont using record extension
  printk: ringbuffer: add finalization/extension support
  printk: ringbuffer: change representation of states
  printk: ringbuffer: clear initial reserved fields
  printk: ringbuffer: add BLK_DATALESS() macro
  printk: ringbuffer: relocate get_data()
  printk: ringbuffer: avoid memcpy() on state_var
  printk: ringbuffer: fix setting state in desc_read()
  kernel.h: Move oops_in_progress to printk.h
  scripts/gdb: update for lockless printk ringbuffer
  scripts/gdb: add utils.read_ulong()
  docs: vmcoreinfo: add lockless printk ringbuffer vmcoreinfo
  printk: reduce LOG_BUF_SHIFT range for H8300
  printk: ringbuffer: support dataless records
  ...

18 files changed, 3410 insertions, 731 deletions

diff --git a/Documentation/admin-guide/kdump/gdbmacros.txt b/Documentation/admin-guide/kdump/gdbmacros.txt
index 220d0a80ca2c..82aecdcae8a6 100644
--- a/Documentation/admin-guide/kdump/gdbmacros.txt
+++ b/Documentation/admin-guide/kdump/gdbmacros.txt
@@ -170,57 +170,103 @@ document trapinfo
 	address the kernel panicked.
 end
 
-define dump_log_idx
-	set $idx = $arg0
-	if ($argc > 1)
-		set $prev_flags = $arg1
+define dump_record
+	set var $desc = $arg0
+	set var $info = $arg1
+	if ($argc > 2)
+		set var $prev_flags = $arg2
 	else
-		set $prev_flags = 0
+		set var $prev_flags = 0
 	end
-	set $msg = ((struct printk_log *) (log_buf + $idx))
-	set $prefix = 1
-	set $newline = 1
-	set $log = log_buf + $idx + sizeof(*$msg)
-
-	# prev & LOG_CONT && !(msg->flags & LOG_PREIX)
-	if (($prev_flags & 8) && !($msg->flags & 4))
-		set $prefix = 0
+
+	set var $prefix = 1
+	set var $newline = 1
+
+	set var $begin = $desc->text_blk_lpos.begin % (1U << prb->text_data_ring.size_bits)
+	set var $next = $desc->text_blk_lpos.next % (1U << prb->text_data_ring.size_bits)
+
+	# handle data-less record
+	if ($begin & 1)
+		set var $text_len = 0
+		set var $log = ""
+	else
+		# handle wrapping data block
+		if ($begin > $next)
+			set var $begin = 0
+		end
+
+		# skip over descriptor id
+		set var $begin = $begin + sizeof(long)
+
+		# handle truncated message
+		if ($next - $begin < $info->text_len)
+			set var $text_len = $next - $begin
+		else
+			set var $text_len = $info->text_len
+		end
+
+		set var $log = &prb->text_data_ring.data[$begin]
+	end
+
+	# prev & LOG_CONT && !(info->flags & LOG_PREIX)
+	if (($prev_flags & 8) && !($info->flags & 4))
+		set var $prefix = 0
 	end
 
-	# msg->flags & LOG_CONT
-	if ($msg->flags & 8)
+	# info->flags & LOG_CONT
+	if ($info->flags & 8)
 		# (prev & LOG_CONT && !(prev & LOG_NEWLINE))
 		if (($prev_flags & 8) && !($prev_flags & 2))
-			set $prefix = 0
+			set var $prefix = 0
 		end
-		# (!(msg->flags & LOG_NEWLINE))
-		if (!($msg->flags & 2))
-			set $newline = 0
+		# (!(info->flags & LOG_NEWLINE))
+		if (!($info->flags & 2))
+			set var $newline = 0
 		end
 	end
 
 	if ($prefix)
-		printf "[%5lu.%06lu] ", $msg->ts_nsec / 1000000000, $msg->ts_nsec % 1000000000
+		printf "[%5lu.%06lu] ", $info->ts_nsec / 1000000000, $info->ts_nsec % 1000000000
 	end
-	if ($msg->text_len != 0)
-		eval "printf \"%%%d.%ds\", $log", $msg->text_len, $msg->text_len
+	if ($text_len)
+		eval "printf \"%%%d.%ds\", $log", $text_len, $text_len
 	end
 	if ($newline)
 		printf "\n"
 	end
-	if ($msg->dict_len > 0)
-		set $dict = $log + $msg->text_len
-		set $idx = 0
-		set $line = 1
-		while ($idx < $msg->dict_len)
-			if ($line)
-				printf " "
-				set $line = 0
+
+	# handle dictionary data
+
+	set var $dict = &$info->dev_info.subsystem[0]
+	set var $dict_len = sizeof($info->dev_info.subsystem)
+	if ($dict[0] != '\0')
+		printf " SUBSYSTEM="
+		set var $idx = 0
+		while ($idx < $dict_len)
+			set var $c = $dict[$idx]
+			if ($c == '\0')
+				loop_break
+			else
+				if ($c < ' ' || $c >= 127 || $c == '\\')
+					printf "\\x%02x", $c
+				else
+					printf "%c", $c
+				end
 			end
-			set $c = $dict[$idx]
+			set var $idx = $idx + 1
+		end
+		printf "\n"
+	end
+
+	set var $dict = &$info->dev_info.device[0]
+	set var $dict_len = sizeof($info->dev_info.device)
+	if ($dict[0] != '\0')
+		printf " DEVICE="
+		set var $idx = 0
+		while ($idx < $dict_len)
+			set var $c = $dict[$idx]
 			if ($c == '\0')
-				printf "\n"
-				set $line = 1
+				loop_break
 			else
 				if ($c < ' ' || $c >= 127 || $c == '\\')
 					printf "\\x%02x", $c
@@ -228,33 +274,46 @@ define dump_log_idx
 					printf "%c", $c
 				end
 			end
-			set $idx = $idx + 1
+			set var $idx = $idx + 1
 		end
 		printf "\n"
 	end
 end
-document dump_log_idx
-	Dump a single log given its index in the log buffer.  The first
-	parameter is the index into log_buf, the second is optional and
-	specified the previous log buffer's flags, used for properly
-	formatting continued lines.
+document dump_record
+	Dump a single record. The first parameter is the descriptor,
+	the second parameter is the info, the third parameter is
+	optional and specifies the previous record's flags, used for
+	properly formatting continued lines.
 end
 
 define dmesg
-	set $i = log_first_idx
-	set $end_idx = log_first_idx
-	set $prev_flags = 0
+	# definitions from kernel/printk/printk_ringbuffer.h
+	set var $desc_committed = 1
+	set var $desc_finalized = 2
+	set var $desc_sv_bits = sizeof(long) * 8
+	set var $desc_flags_shift = $desc_sv_bits - 2
+	set var $desc_flags_mask = 3 << $desc_flags_shift
+	set var $id_mask = ~$desc_flags_mask
+
+	set var $desc_count = 1U << prb->desc_ring.count_bits
+	set var $prev_flags = 0
+
+	set var $id = prb->desc_ring.tail_id.counter
+	set var $end_id = prb->desc_ring.head_id.counter
 
 	while (1)
-		set $msg = ((struct printk_log *) (log_buf + $i))
-		if ($msg->len == 0)
-			set $i = 0
-		else
-			dump_log_idx $i $prev_flags
-			set $i = $i + $msg->len
-			set $prev_flags = $msg->flags
+		set var $desc = &prb->desc_ring.descs[$id % $desc_count]
+		set var $info = &prb->desc_ring.infos[$id % $desc_count]
+
+		# skip non-committed record
+		set var $state = 3 & ($desc->state_var.counter >> $desc_flags_shift)
+		if ($state == $desc_committed || $state == $desc_finalized)
+			dump_record $desc $info $prev_flags
+			set var $prev_flags = $info->flags
 		end
-		if ($i == $end_idx)
+
+		set var $id = ($id + 1) & $id_mask
+		if ($id == $end_id)
 			loop_break
 		end
 	end
diff --git a/Documentation/admin-guide/kdump/vmcoreinfo.rst b/Documentation/admin-guide/kdump/vmcoreinfo.rst
index 2baad0bfb09d..e44a6c01f336 100644
--- a/Documentation/admin-guide/kdump/vmcoreinfo.rst
+++ b/Documentation/admin-guide/kdump/vmcoreinfo.rst
@@ -189,50 +189,123 @@ from this.
 Free areas descriptor. User-space tools use this value to iterate the
 free_area ranges. MAX_ORDER is used by the zone buddy allocator.
 
-log_first_idx
+prb
+---
+
+A pointer to the printk ringbuffer (struct printk_ringbuffer). This
+may be pointing to the static boot ringbuffer or the dynamically
+allocated ringbuffer, depending on when the the core dump occurred.
+Used by user-space tools to read the active kernel log buffer.
+
+printk_rb_static
+----------------
+
+A pointer to the static boot printk ringbuffer. If @prb has a
+different value, this is useful for viewing the initial boot messages,
+which may have been overwritten in the dynamically allocated
+ringbuffer.
+
+clear_seq
+---------
+
+The sequence number of the printk() record after the last clear
+command. It indicates the first record after the last
+SYSLOG_ACTION_CLEAR, like issued by 'dmesg -c'. Used by user-space
+tools to dump a subset of the dmesg log.
+
+printk_ringbuffer
+-----------------
+
+The size of a printk_ringbuffer structure. This structure contains all
+information required for accessing the various components of the
+kernel log buffer.
+
+(printk_ringbuffer, desc_ring|text_data_ring|dict_data_ring|fail)
+-----------------------------------------------------------------
+
+Offsets for the various components of the printk ringbuffer. Used by
+user-space tools to view the kernel log buffer without requiring the
+declaration of the structure.
+
+prb_desc_ring
 -------------
 
-Index of the first record stored in the buffer log_buf. Used by
-user-space tools to read the strings in the log_buf.
+The size of the prb_desc_ring structure. This structure contains
+information about the set of record descriptors.
 
-log_buf
--------
+(prb_desc_ring, count_bits|descs|head_id|tail_id)
+-------------------------------------------------
+
+Offsets for the fields describing the set of record descriptors. Used
+by user-space tools to be able to traverse the descriptors without
+requiring the declaration of the structure.
+
+prb_desc
+--------
+
+The size of the prb_desc structure. This structure contains
+information about a single record descriptor.
+
+(prb_desc, info|state_var|text_blk_lpos|dict_blk_lpos)
+------------------------------------------------------
+
+Offsets for the fields describing a record descriptors. Used by
+user-space tools to be able to read descriptors without requiring
+the declaration of the structure.
+
+prb_data_blk_lpos
+-----------------
+
+The size of the prb_data_blk_lpos structure. This structure contains
+information about where the text or dictionary data (data block) is
+located within the respective data ring.
+
+(prb_data_blk_lpos, begin|next)
+-------------------------------
 
-Console output is written to the ring buffer log_buf at index
-log_first_idx. Used to get the kernel log.
+Offsets for the fields describing the location of a data block. Used
+by user-space tools to be able to locate data blocks without
+requiring the declaration of the structure.
 
-log_buf_len
+printk_info
 -----------
 
-log_buf's length.
+The size of the printk_info structure. This structure contains all
+the meta-data for a record.
 
-clear_idx
----------
+(printk_info, seq|ts_nsec|text_len|dict_len|caller_id)
+------------------------------------------------------
 
-The index that the next printk() record to read after the last clear
-command. It indicates the first record after the last SYSLOG_ACTION
-_CLEAR, like issued by 'dmesg -c'. Used by user-space tools to dump
-the dmesg log.
+Offsets for the fields providing the meta-data for a record. Used by
+user-space tools to be able to read the information without requiring
+the declaration of the structure.
 
-log_next_idx
-------------
+prb_data_ring
+-------------
 
-The index of the next record to store in the buffer log_buf. Used to
-compute the index of the current buffer position.
+The size of the prb_data_ring structure. This structure contains
+information about a set of data blocks.
 
-printk_log
-----------
+(prb_data_ring, size_bits|data|head_lpos|tail_lpos)
+---------------------------------------------------
 
-The size of a structure printk_log. Used to compute the size of
-messages, and extract dmesg log. It encapsulates header information for
-log_buf, such as timestamp, syslog level, etc.
+Offsets for the fields describing a set of data blocks. Used by
+user-space tools to be able to access the data blocks without
+requiring the declaration of the structure.
 
-(printk_log, ts_nsec|len|text_len|dict_len)
--------------------------------------------
+atomic_long_t
+-------------
+
+The size of the atomic_long_t structure. Used by user-space tools to
+be able to copy the full structure, regardless of its
+architecture-specific implementation.
+
+(atomic_long_t, counter)
+------------------------
 
-It represents field offsets in struct printk_log. User space tools
-parse it and check whether the values of printk_log's members have been
-changed.
+Offset for the long value of an atomic_long_t variable. Used by
+user-space tools to access the long value without requiring the
+architecture-specific declaration.
 
 (free_area.free_list, MIGRATE_TYPES)
 ------------------------------------
diff --git a/MAINTAINERS b/MAINTAINERS
index 71291bb26a07..6da16c3707c6 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -13970,6 +13970,7 @@ PRINTK
 M:	Petr Mladek <pmladek@suse.com>
 M:	Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
 R:	Steven Rostedt <rostedt@goodmis.org>
+R:	John Ogness <john.ogness@linutronix.de>
 S:	Maintained
 F:	include/linux/printk.h
 F:	kernel/printk/
diff --git a/drivers/base/core.c b/drivers/base/core.c
index bb5806a2bd4c..f90e9f77bf8c 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -4061,22 +4061,21 @@ void device_shutdown(void)
  */
 
 #ifdef CONFIG_PRINTK
-static int
-create_syslog_header(const struct device *dev, char *hdr, size_t hdrlen)
+static void
+set_dev_info(const struct device *dev, struct dev_printk_info *dev_info)
 {
 	const char *subsys;
-	size_t pos = 0;
+
+	memset(dev_info, 0, sizeof(*dev_info));
 
 	if (dev->class)
 		subsys = dev->class->name;
 	else if (dev->bus)
 		subsys = dev->bus->name;
 	else
-		return 0;
+		return;
 
-	pos += snprintf(hdr + pos, hdrlen - pos, "SUBSYSTEM=%s", subsys);
-	if (pos >= hdrlen)
-		goto overflow;
+	strscpy(dev_info->subsystem, subsys, sizeof(dev_info->subsystem));
 
 	/*
 	 * Add device identifier DEVICE=:
@@ -4092,41 +4091,28 @@ create_syslog_header(const struct device *dev, char *hdr, size_t hdrlen)
 			c = 'b';
 		else
 			c = 'c';
-		pos++;
-		pos += snprintf(hdr + pos, hdrlen - pos,
-				"DEVICE=%c%u:%u",
-				c, MAJOR(dev->devt), MINOR(dev->devt));
+
+		snprintf(dev_info->device, sizeof(dev_info->device),
+			 "%c%u:%u", c, MAJOR(dev->devt), MINOR(dev->devt));
 	} else if (strcmp(subsys, "net") == 0) {
 		struct net_device *net = to_net_dev(dev);
 
-		pos++;
-		pos += snprintf(hdr + pos, hdrlen - pos,
-				"DEVICE=n%u", net->ifindex);
+		snprintf(dev_info->device, sizeof(dev_info->device),
+			 "n%u", net->ifindex);
 	} else {
-		pos++;
-		pos += snprintf(hdr + pos, hdrlen - pos,
-				"DEVICE=+%s:%s", subsys, dev_name(dev));
+		snprintf(dev_info->device, sizeof(dev_info->device),
+			 "+%s:%s", subsys, dev_name(dev));
 	}
-
-	if (pos >= hdrlen)
-		goto overflow;
-
-	return pos;
-
-overflow:
-	dev_WARN(dev, "device/subsystem name too long");
-	return 0;
 }
 
 int dev_vprintk_emit(int level, const struct device *dev,
 		     const char *fmt, va_list args)
 {
-	char hdr[128];
-	size_t hdrlen;
+	struct dev_printk_info dev_info;
 
-	hdrlen = create_syslog_header(dev, hdr, sizeof(hdr));
+	set_dev_info(dev, &dev_info);
 
-	return vprintk_emit(0, level, hdrlen ? hdr : NULL, hdrlen, fmt, args);
+	return vprintk_emit(0, level, &dev_info, fmt, args);
 }
 EXPORT_SYMBOL(dev_vprintk_emit);
 
diff --git a/include/linux/crash_core.h b/include/linux/crash_core.h
index 6594dbc34a37..206bde8308b2 100644
--- a/include/linux/crash_core.h
+++ b/include/linux/crash_core.h
@@ -55,6 +55,9 @@ phys_addr_t paddr_vmcoreinfo_note(void);
 #define VMCOREINFO_OFFSET(name, field) \
 	vmcoreinfo_append_str("OFFSET(%s.%s)=%lu\n", #name, #field, \
 			      (unsigned long)offsetof(struct name, field))
+#define VMCOREINFO_TYPE_OFFSET(name, field) \
+	vmcoreinfo_append_str("OFFSET(%s.%s)=%lu\n", #name, #field, \
+			      (unsigned long)offsetof(name, field))
 #define VMCOREINFO_LENGTH(name, value) \
 	vmcoreinfo_append_str("LENGTH(%s)=%lu\n", #name, (unsigned long)value)
 #define VMCOREINFO_NUMBER(name) \
diff --git a/include/linux/debug_locks.h b/include/linux/debug_locks.h
index e7e45f0cc7da..2915f56ad421 100644
--- a/include/linux/debug_locks.h
+++ b/include/linux/debug_locks.h
@@ -2,9 +2,9 @@
 #ifndef __LINUX_DEBUG_LOCKING_H
 #define __LINUX_DEBUG_LOCKING_H
 
-#include <linux/kernel.h>
 #include <linux/atomic.h>
 #include <linux/bug.h>
+#include <linux/printk.h>
 
 struct task_struct;
 
diff --git a/include/linux/dev_printk.h b/include/linux/dev_printk.h
index 3028b644b4fb..6f009559ee54 100644
--- a/include/linux/dev_printk.h
+++ b/include/linux/dev_printk.h
@@ -21,6 +21,14 @@
 
 struct device;
 
+#define PRINTK_INFO_SUBSYSTEM_LEN	16
+#define PRINTK_INFO_DEVICE_LEN		48
+
+struct dev_printk_info {
+	char subsystem[PRINTK_INFO_SUBSYSTEM_LEN];
+	char device[PRINTK_INFO_DEVICE_LEN];
+};
+
 #ifdef CONFIG_PRINTK
 
 __printf(3, 0) __cold
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index c25b8e41c0ea..e4aa29b1ad62 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -526,7 +526,6 @@ extern unsigned int sysctl_oops_all_cpu_backtrace;
 #endif /* CONFIG_SMP */
 
 extern void bust_spinlocks(int yes);
-extern int oops_in_progress;		/* If set, an oops, panic(), BUG() or die() is in progress */
 extern int panic_timeout;
 extern unsigned long panic_print;
 extern int panic_on_oops;
diff --git a/include/linux/printk.h b/include/linux/printk.h
index 34c1a7be3e01..78479633ccfc 100644
--- a/include/linux/printk.h
+++ b/include/linux/printk.h
@@ -12,6 +12,8 @@
 extern const char linux_banner[];
 extern const char linux_proc_banner[];
 
+extern int oops_in_progress;	/* If set, an oops, panic(), BUG() or die() is in progress */
+
 #define PRINTK_MAX_SINGLE_HEADER_LEN 2
 
 static inline int printk_get_level(const char *buffer)
@@ -159,10 +161,12 @@ 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
-asmlinkage __printf(5, 0)
+asmlinkage __printf(4, 0)
 int vprintk_emit(int facility, int level,
-		 const char *dict, size_t dictlen,
+		 const struct dev_printk_info *dev_info,
 		 const char *fmt, va_list args);
 
 asmlinkage __printf(1, 0)
diff --git a/init/Kconfig b/init/Kconfig
index c0f56e455dce..2a583ef2ff66 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -682,7 +682,8 @@ config IKHEADERS
 
 config LOG_BUF_SHIFT
 	int "Kernel log buffer size (16 => 64KB, 17 => 128KB)"
-	range 12 25
+	range 12 25 if !H8300
+	range 12 19 if H8300
 	default 17
 	depends on PRINTK
 	help
diff --git a/kernel/printk/Makefile b/kernel/printk/Makefile
index 4d052fc6bcde..eee3dc9b60a9 100644
--- a/kernel/printk/Makefile
+++ b/kernel/printk/Makefile
@@ -2,3 +2,4 @@
 obj-y	= printk.o
 obj-$(CONFIG_PRINTK)	+= printk_safe.o
 obj-$(CONFIG_A11Y_BRAILLE_CONSOLE)	+= braille.o
+obj-$(CONFIG_PRINTK)	+= printk_ringbuffer.o
diff --git a/kernel/printk/internal.h b/kernel/printk/internal.h
index 660f9a6bf73a..3a8fd491758c 100644
--- a/kernel/printk/internal.h
+++ b/kernel/printk/internal.h
@@ -14,9 +14,9 @@
 
 extern raw_spinlock_t logbuf_lock;
 
-__printf(5, 0)
+__printf(4, 0)
 int vprintk_store(int facility, int level,
-		  const char *dict, size_t dictlen,
+		  const struct dev_printk_info *dev_info,
 		  const char *fmt, va_list args);
 
 __printf(1, 0) int vprintk_default(const char *fmt, va_list args);
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 9b75f6bfc333..fe64a49344bf 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -55,6 +55,7 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/printk.h>
 
+#include "printk_ringbuffer.h"
 #include "console_cmdline.h"
 #include "braille.h"
 #include "internal.h"
@@ -294,30 +295,22 @@ enum con_msg_format_flags {
 static int console_msg_format = MSG_FORMAT_DEFAULT;
 
 /*
- * The printk log buffer consists of a chain of concatenated variable
- * length records. Every record starts with a record header, containing
- * the overall length of the record.
+ * The printk log buffer consists of a sequenced collection of records, each
+ * containing variable length message text. Every record also contains its
+ * own meta-data (@info).
  *
- * The heads to the first and last entry in the buffer, as well as the
- * sequence numbers of these entries are maintained when messages are
- * stored.
+ * Every record meta-data carries the timestamp in microseconds, as well as
+ * the standard userspace syslog level and syslog facility. The usual kernel
+ * messages use LOG_KERN; userspace-injected messages always carry a matching
+ * syslog facility, by default LOG_USER. The origin of every message can be
+ * reliably determined that way.
  *
- * If the heads indicate available messages, the length in the header
- * tells the start next message. A length == 0 for the next message
- * indicates a wrap-around to the beginning of the buffer.
+ * The human readable log message of a record is available in @text, the
+ * length of the message text in @text_len. The stored message is not
+ * terminated.
  *
- * Every record carries the monotonic timestamp in microseconds, as well as
- * the standard userspace syslog level and syslog facility. The usual
- * kernel messages use LOG_KERN; userspace-injected messages always carry
- * a matching syslog facility, by default LOG_USER. The origin of every
- * message can be reliably determined that way.
- *
- * The human readable log message directly follows the message header. The
- * length of the message text is stored in the header, the stored message
- * is not terminated.
- *
- * Optionally, a message can carry a dictionary of properties (key/value pairs),
- * to provide userspace with a machine-readable message context.
+ * Optionally, a record can carry a dictionary of properties (key/value
+ * pairs), to provide userspace with a machine-readable message context.
  *
  * Examples for well-defined, commonly used property names are:
  *   DEVICE=b12:8               device identifier
@@ -327,25 +320,22 @@ static int console_msg_format = MSG_FORMAT_DEFAULT;
  *                                +sound:card0  subsystem:devname
  *   SUBSYSTEM=pci              driver-core subsystem name
  *
- * Valid characters in property names are [a-zA-Z0-9.-_]. The plain text value
- * follows directly after a '=' character. Every property is terminated by
- * a '\0' character. The last property is not terminated.
- *
- * Example of a message structure:
- *   0000  ff 8f 00 00 00 00 00 00      monotonic time in nsec
- *   0008  34 00                        record is 52 bytes long
- *   000a        0b 00                  text is 11 bytes long
- *   000c              1f 00            dictionary is 23 bytes long
- *   000e                    03 00      LOG_KERN (facility) LOG_ERR (level)
- *   0010  69 74 27 73 20 61 20 6c      "it's a l"
- *         69 6e 65                     "ine"
- *   001b           44 45 56 49 43      "DEVIC"
- *         45 3d 62 38 3a 32 00 44      "E=b8:2\0D"
- *         52 49 56 45 52 3d 62 75      "RIVER=bu"
- *         67                           "g"
- *   0032     00 00 00                  padding to next message header
- *
- * The 'struct printk_log' buffer header must never be directly exported to
+ * Valid characters in property names are [a-zA-Z0-9.-_]. Property names
+ * and values are terminated by a '\0' character.
+ *
+ * Example of record values:
+ *   record.text_buf                = "it's a line" (unterminated)
+ *   record.info.seq                = 56
+ *   record.info.ts_nsec            = 36863
+ *   record.info.text_len           = 11
+ *   record.info.facility           = 0 (LOG_KERN)
+ *   record.info.flags              = 0
+ *   record.info.level              = 3 (LOG_ERR)
+ *   record.info.caller_id          = 299 (task 299)
+ *   record.info.dev_info.subsystem = "pci" (terminated)
+ *   record.info.dev_info.device    = "+pci:0000:00:01.0" (terminated)
+ *
+ * The 'struct printk_info' buffer must never be directly exported to
  * userspace, it is a kernel-private implementation detail that might
  * need to be changed in the future, when the requirements change.
  *
@@ -365,23 +355,6 @@ enum log_flags {
 	LOG_CONT	= 8,	/* text is a fragment of a continuation line */
 };
 
-struct printk_log {
-	u64 ts_nsec;		/* timestamp in nanoseconds */
-	u16 len;		/* length of entire record */
-	u16 text_len;		/* length of text buffer */
-	u16 dict_len;		/* length of dictionary buffer */
-	u8 facility;		/* syslog facility */
-	u8 flags:5;		/* internal record flags */
-	u8 level:3;		/* syslog level */
-#ifdef CONFIG_PRINTK_CALLER
-	u32 caller_id;            /* thread id or processor id */
-#endif
-}
-#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
-__packed __aligned(4)
-#endif
-;
-
 /*
  * The logbuf_lock protects kmsg buffer, indices, counters.  This can be taken
  * within the scheduler's rq lock. It must be released before calling
@@ -421,26 +394,16 @@ DEFINE_RAW_SPINLOCK(logbuf_lock);
 DECLARE_WAIT_QUEUE_HEAD(log_wait);
 /* the next printk record to read by syslog(READ) or /proc/kmsg */
 static u64 syslog_seq;
-static u32 syslog_idx;
 static size_t syslog_partial;
 static bool syslog_time;
 
-/* index and sequence number of the first record stored in the buffer */
-static u64 log_first_seq;
-static u32 log_first_idx;
-
-/* index and sequence number of the next record to store in the buffer */
-static u64 log_next_seq;
-static u32 log_next_idx;
-
 /* the next printk record to write to the console */
 static u64 console_seq;
-static u32 console_idx;
 static u64 exclusive_console_stop_seq;
+static unsigned long console_dropped;
 
 /* the next printk record to read after the last 'clear' command */
 static u64 clear_seq;
-static u32 clear_idx;
 
 #ifdef CONFIG_PRINTK_CALLER
 #define PREFIX_MAX		48
@@ -453,7 +416,7 @@ static u32 clear_idx;
 #define LOG_FACILITY(v)		((v) >> 3 & 0xff)
 
 /* record buffer */
-#define LOG_ALIGN __alignof__(struct printk_log)
+#define LOG_ALIGN __alignof__(unsigned long)
 #define __LOG_BUF_LEN (1 << CONFIG_LOG_BUF_SHIFT)
 #define LOG_BUF_LEN_MAX (u32)(1 << 31)
 static char __log_buf[__LOG_BUF_LEN] __aligned(LOG_ALIGN);
@@ -461,6 +424,23 @@ static char *log_buf = __log_buf;
 static u32 log_buf_len = __LOG_BUF_LEN;
 
 /*
+ * Define the average message size. This only affects the number of
+ * descriptors that will be available. Underestimating is better than
+ * overestimating (too many available descriptors is better than not enough).
+ */
+#define PRB_AVGBITS 5	/* 32 character average length */
+
+#if CONFIG_LOG_BUF_SHIFT <= PRB_AVGBITS
+#error CONFIG_LOG_BUF_SHIFT value too small.
+#endif
+_DEFINE_PRINTKRB(printk_rb_static, CONFIG_LOG_BUF_SHIFT - PRB_AVGBITS,
+		 PRB_AVGBITS, &__log_buf[0]);
+
+static struct printk_ringbuffer printk_rb_dynamic;
+
+static struct printk_ringbuffer *prb = &printk_rb_static;
+
+/*
  * We cannot access per-CPU data (e.g. per-CPU flush irq_work) before
  * per_cpu_areas are initialised. This variable is set to true when
  * it's safe to access per-CPU data.
@@ -484,108 +464,6 @@ u32 log_buf_len_get(void)
 	return log_buf_len;
 }
 
-/* human readable text of the record */
-static char *log_text(const struct printk_log *msg)
-{
-	return (char *)msg + sizeof(struct printk_log);
-}
-
-/* optional key/value pair dictionary attached to the record */
-static char *log_dict(const struct printk_log *msg)
-{
-	return (char *)msg + sizeof(struct printk_log) + msg->text_len;
-}
-
-/* get record by index; idx must point to valid msg */
-static struct printk_log *log_from_idx(u32 idx)
-{
-	struct printk_log *msg = (struct printk_log *)(log_buf + idx);
-
-	/*
-	 * A length == 0 record is the end of buffer marker. Wrap around and
-	 * read the message at the start of the buffer.
-	 */
-	if (!msg->len)
-		return (struct printk_log *)log_buf;
-	return msg;
-}
-
-/* get next record; idx must point to valid msg */
-static u32 log_next(u32 idx)
-{
-	struct printk_log *msg = (struct printk_log *)(log_buf + idx);
-
-	/* length == 0 indicates the end of the buffer; wrap */
-	/*
-	 * A length == 0 record is the end of buffer marker. Wrap around and
-	 * read the message at the start of the buffer as *this* one, and
-	 * return the one after that.
-	 */
-	if (!msg->len) {
-		msg = (struct printk_log *)log_buf;
-		return msg->len;
-	}
-	return idx + msg->len;
-}
-
-/*
- * Check whether there is enough free space for the given message.
- *
- * The same values of first_idx and next_idx mean that the buffer
- * is either empty or full.
- *
- * If the buffer is empty, we must respect the position of the indexes.
- * They cannot be reset to the beginning of the buffer.
- */
-static int logbuf_has_space(u32 msg_size, bool empty)
-{
-	u32 free;
-
-	if (log_next_idx > log_first_idx || empty)
-		free = max(log_buf_len - log_next_idx, log_first_idx);
-	else
-		free = log_first_idx - log_next_idx;
-
-	/*
-	 * We need space also for an empty header that signalizes wrapping
-	 * of the buffer.
-	 */
-	return free >= msg_size + sizeof(struct printk_log);
-}
-
-static int log_make_free_space(u32 msg_size)
-{
-	while (log_first_seq < log_next_seq &&
-	       !logbuf_has_space(msg_size, false)) {
-		/* drop old messages until we have enough contiguous space */
-		log_first_idx = log_next(log_first_idx);
-		log_first_seq++;
-	}
-
-	if (clear_seq < log_first_seq) {
-		clear_seq = log_first_seq;
-		clear_idx = log_first_idx;
-	}
-
-	/* sequence numbers are equal, so the log buffer is empty */
-	if (logbuf_has_space(msg_size, log_first_seq == log_next_seq))
-		return 0;
-
-	return -ENOMEM;
-}
-
-/* compute the message size including the padding bytes */
-static u32 msg_used_size(u16 text_len, u16 dict_len, u32 *pad_len)
-{
-	u32 size;