Merge tag 'mm-nonmm-stable-2024-05-19-11-56' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mmHEADmaster

Pull non-mm updates from Andrew Morton:
 "Mainly singleton patches, documented in their respective changelogs.
  Notable series include:

   - Some maintenance and performance work for ocfs2 in Heming Zhao's
     series "improve write IO performance when fragmentation is high".

   - Some ocfs2 bugfixes from Su Yue in the series "ocfs2 bugs fixes
     exposed by fstests".

   - kfifo header rework from Andy Shevchenko in the series "kfifo:
     Clean up kfifo.h".

   - GDB script fixes from Florian Rommel in the series "scripts/gdb:
     Fixes for $lx_current and $lx_per_cpu".

   - After much discussion, a coding-style update from Barry Song
     explaining one reason why inline functions are preferred over
     macros. The series is "codingstyle: avoid unused parameters for a
     function-like macro""

* tag 'mm-nonmm-stable-2024-05-19-11-56' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (62 commits)
  fs/proc: fix softlockup in __read_vmcore
  nilfs2: convert BUG_ON() in nilfs_finish_roll_forward() to WARN_ON()
  scripts: checkpatch: check unused parameters for function-like macro
  Documentation: coding-style: ask function-like macros to evaluate parameters
  nilfs2: use __field_struct() for a bitwise field
  selftests/kcmp: remove unused open mode
  nilfs2: remove calls to folio_set_error() and folio_clear_error()
  kernel/watchdog_perf.c: tidy up kerneldoc
  watchdog: allow nmi watchdog to use raw perf event
  watchdog: handle comma separated nmi_watchdog command line
  nilfs2: make superblock data array index computation sparse friendly
  squashfs: remove calls to set the folio error flag
  squashfs: convert squashfs_symlink_read_folio to use folio APIs
  scripts/gdb: fix detection of current CPU in KGDB
  scripts/gdb: make get_thread_info accept pointers
  scripts/gdb: fix parameter handling in $lx_per_cpu
  scripts/gdb: fix failing KGDB detection during probe
  kfifo: don't use "proxy" headers
  media: stih-cec: add missing io.h
  media: rc: add missing io.h
  ...

77 files changed, 679 insertions, 427 deletions

diff --git a/Documentation/admin-guide/kdump/kdump.rst b/Documentation/admin-guide/kdump/kdump.rst
index 0302a93b1d40b..5376890adbeb0 100644
--- a/Documentation/admin-guide/kdump/kdump.rst
+++ b/Documentation/admin-guide/kdump/kdump.rst
@@ -136,10 +136,6 @@ System kernel config options
 
 	CONFIG_KEXEC_CORE=y
 
-   Subsequently, CRASH_CORE is selected by KEXEC_CORE::
-
-	CONFIG_CRASH_CORE=y
-
 2) Enable "sysfs file system support" in "Filesystem" -> "Pseudo
    filesystems." This is usually enabled by default::
 
@@ -168,6 +164,10 @@ Dump-capture kernel config options (Arch Independent)
 
 	CONFIG_CRASH_DUMP=y
 
+   And this will select VMCORE_INFO and CRASH_RESERVE::
+	CONFIG_VMCORE_INFO=y
+	CONFIG_CRASH_RESERVE=y
+
 2) Enable "/proc/vmcore support" under "Filesystems" -> "Pseudo filesystems"::
 
 	CONFIG_PROC_VMCORE=y
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 90f79a2854270..ef25e06ec08cc 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -3787,10 +3787,12 @@
 			Format: [state][,regs][,debounce][,die]
 
 	nmi_watchdog=	[KNL,BUGS=X86] Debugging features for SMP kernels
-			Format: [panic,][nopanic,][num]
+			Format: [panic,][nopanic,][rNNN,][num]
 			Valid num: 0 or 1
 			0 - turn hardlockup detector in nmi_watchdog off
 			1 - turn hardlockup detector in nmi_watchdog on
+			rNNN - configure the watchdog with raw perf event 0xNNN
+
 			When panic is specified, panic when an NMI watchdog
 			timeout occurs (or 'nopanic' to not panic on an NMI
 			watchdog, if CONFIG_BOOTPARAM_HARDLOCKUP_PANIC is set)
@@ -7507,4 +7509,3 @@
 				memory, and other data can't be written using
 				xmon commands.
 			off	xmon is disabled.
-
diff --git a/Documentation/dev-tools/checkpatch.rst b/Documentation/dev-tools/checkpatch.rst
index 1279689958473..a9fac978a5251 100644
--- a/Documentation/dev-tools/checkpatch.rst
+++ b/Documentation/dev-tools/checkpatch.rst
@@ -906,6 +906,20 @@ Macros, Attributes and Symbols
 
     See: https://lore.kernel.org/lkml/1399671106.2912.21.camel@joe-AO725/
 
+  **MACRO_ARG_UNUSED**
+    If function-like macros do not utilize a parameter, it might result
+    in a build warning. We advocate for utilizing static inline functions
+    to replace such macros.
+    For example, for a macro such as the one below::
+
+      #define test(a) do { } while (0)
+
+    there would be a warning like below::
+
+      WARNING: Argument 'a' is not used in function-like macro.
+
+    See: https://www.kernel.org/doc/html/latest/process/coding-style.html#macros-enums-and-rtl
+
   **SINGLE_STATEMENT_DO_WHILE_MACRO**
     For the multi-statement macros, it is necessary to use the do-while
     loop to avoid unpredictable code paths. The do-while loop helps to
diff --git a/Documentation/process/coding-style.rst b/Documentation/process/coding-style.rst
index 9c7cf73473943..7e768c65aa926 100644
--- a/Documentation/process/coding-style.rst
+++ b/Documentation/process/coding-style.rst
@@ -827,6 +827,29 @@ Macros with multiple statements should be enclosed in a do - while block:
 				do_this(b, c);		\
 		} while (0)
 
+Function-like macros with unused parameters should be replaced by static
+inline functions to avoid the issue of unused variables:
+
+.. code-block:: c
+
+	static inline void fun(struct foo *foo)
+	{
+	}
+
+Due to historical practices, many files still employ the "cast to (void)"
+approach to evaluate parameters. However, this method is not advisable.
+Inline functions address the issue of "expression with side effects
+evaluated more than once", circumvent unused-variable problems, and
+are generally better documented than macros for some reason.
+
+.. code-block:: c
+
+	/*
+	 * Avoid doing this whenever possible and instead opt for static
+	 * inline functions
+	 */
+	#define macrofun(foo) do { (void) (foo); } while (0)
+
 Things to avoid when using macros:
 
 1) macros that affect control flow:
diff --git a/arch/x86/lib/copy_mc.c b/arch/x86/lib/copy_mc.c
index 6e8b7e600def5..97e88e58567bf 100644
--- a/arch/x86/lib/copy_mc.c
+++ b/arch/x86/lib/copy_mc.c
@@ -4,6 +4,7 @@
 #include <linux/jump_label.h>
 #include <linux/uaccess.h>
 #include <linux/export.h>
+#include <linux/instrumented.h>
 #include <linux/string.h>
 #include <linux/types.h>
 
@@ -61,10 +62,20 @@ unsigned long copy_mc_enhanced_fast_string(void *dst, const void *src, unsigned
  */
 unsigned long __must_check copy_mc_to_kernel(void *dst, const void *src, unsigned len)
 {
-	if (copy_mc_fragile_enabled)
-		return copy_mc_fragile(dst, src, len);
-	if (static_cpu_has(X86_FEATURE_ERMS))
-		return copy_mc_enhanced_fast_string(dst, src, len);
+	unsigned long ret;
+
+	if (copy_mc_fragile_enabled) {
+		instrument_memcpy_before(dst, src, len);
+		ret = copy_mc_fragile(dst, src, len);
+		instrument_memcpy_after(dst, src, len, ret);
+		return ret;
+	}
+	if (static_cpu_has(X86_FEATURE_ERMS)) {
+		instrument_memcpy_before(dst, src, len);
+		ret = copy_mc_enhanced_fast_string(dst, src, len);
+		instrument_memcpy_after(dst, src, len, ret);
+		return ret;
+	}
 	memcpy(dst, src, len);
 	return 0;
 }
@@ -75,6 +86,7 @@ unsigned long __must_check copy_mc_to_user(void __user *dst, const void *src, un
 	unsigned long ret;
 
 	if (copy_mc_fragile_enabled) {
+		instrument_copy_to_user(dst, src, len);
 		__uaccess_begin();
 		ret = copy_mc_fragile((__force void *)dst, src, len);
 		__uaccess_end();
@@ -82,6 +94,7 @@ unsigned long __must_check copy_mc_to_user(void __user *dst, const void *src, un
 	}
 
 	if (static_cpu_has(X86_FEATURE_ERMS)) {
+		instrument_copy_to_user(dst, src, len);
 		__uaccess_begin();
 		ret = copy_mc_enhanced_fast_string((__force void *)dst, src, len);
 		__uaccess_end();
diff --git a/block/partitions/ldm.c b/block/partitions/ldm.c
index 38e58960ae036..2bd42fedb907a 100644
--- a/block/partitions/ldm.c
+++ b/block/partitions/ldm.c
@@ -131,8 +131,7 @@ static bool ldm_parse_tocblock (const u8 *data, struct tocblock *toc)
 		ldm_crit ("Cannot find TOCBLOCK, database may be corrupt.");
 		return false;
 	}
-	strncpy (toc->bitmap1_name, data + 0x24, sizeof (toc->bitmap1_name));
-	toc->bitmap1_name[sizeof (toc->bitmap1_name) - 1] = 0;
+	strscpy_pad(toc->bitmap1_name, data + 0x24, sizeof(toc->bitmap1_name));
 	toc->bitmap1_start = get_unaligned_be64(data + 0x2E);
 	toc->bitmap1_size  = get_unaligned_be64(data + 0x36);
 
@@ -142,8 +141,7 @@ static bool ldm_parse_tocblock (const u8 *data, struct tocblock *toc)
 				TOC_BITMAP1, toc->bitmap1_name);
 		return false;
 	}
-	strncpy (toc->bitmap2_name, data + 0x46, sizeof (toc->bitmap2_name));
-	toc->bitmap2_name[sizeof (toc->bitmap2_name) - 1] = 0;
+	strscpy_pad(toc->bitmap2_name, data + 0x46, sizeof(toc->bitmap2_name));
 	toc->bitmap2_start = get_unaligned_be64(data + 0x50);
 	toc->bitmap2_size  = get_unaligned_be64(data + 0x58);
 	if (strncmp (toc->bitmap2_name, TOC_BITMAP2,
diff --git a/drivers/hwtracing/intel_th/core.c b/drivers/hwtracing/intel_th/core.c
index cc7f879bb175d..86c8efecd7c26 100644
--- a/drivers/hwtracing/intel_th/core.c
+++ b/drivers/hwtracing/intel_th/core.c
@@ -871,7 +871,7 @@ intel_th_alloc(struct device *dev, const struct intel_th_drvdata *drvdata,
 	if (!th)
 		return ERR_PTR(-ENOMEM);
 
-	th->id = ida_simple_get(&intel_th_ida, 0, 0, GFP_KERNEL);
+	th->id = ida_alloc(&intel_th_ida, GFP_KERNEL);
 	if (th->id < 0) {
 		err = th->id;
 		goto err_alloc;
@@ -931,7 +931,7 @@ err_chrdev:
 			    "intel_th/output");
 
 err_ida:
-	ida_simple_remove(&intel_th_ida, th->id);
+	ida_free(&intel_th_ida, th->id);
 
 err_alloc:
 	kfree(th);
@@ -964,7 +964,7 @@ void intel_th_free(struct intel_th *th)
 	__unregister_chrdev(th->major, 0, TH_POSSIBLE_OUTPUTS,
 			    "intel_th/output");
 
-	ida_simple_remove(&intel_th_ida, th->id);
+	ida_free(&intel_th_ida, th->id);
 
 	kfree(th);
 }
diff --git a/drivers/media/cec/platform/sti/stih-cec.c b/drivers/media/cec/platform/sti/stih-cec.c
index a20fc5c0c88d0..99978a7c8d9b7 100644
--- a/drivers/media/cec/platform/sti/stih-cec.c
+++ b/drivers/media/cec/platform/sti/stih-cec.c
@@ -6,6 +6,7 @@
  */
 #include <linux/clk.h>
 #include <linux/interrupt.h>
+#include <linux/io.h>
 #include <linux/kernel.h>
 #include <linux/mfd/syscon.h>
 #include <linux/module.h>
diff --git a/drivers/media/rc/mtk-cir.c b/drivers/media/rc/mtk-cir.c
index 4e294e59d3cba..b2f82b2d1c8d4 100644
--- a/drivers/media/rc/mtk-cir.c
+++ b/drivers/media/rc/mtk-cir.c
@@ -8,6 +8,7 @@
 #include <linux/clk.h>
 #include <linux/interrupt.h>
 #include <linux/module.h>
+#include <linux/io.h>
 #include <linux/of.h>
 #include <linux/platform_device.h>
 #include <linux/reset.h>
diff --git a/drivers/media/rc/serial_ir.c b/drivers/media/rc/serial_ir.c
index 96ae0294ac102..fc5fd39271772 100644
--- a/drivers/media/rc/serial_ir.c
+++ b/drivers/media/rc/serial_ir.c
@@ -18,6 +18,7 @@
 #include <linux/module.h>
 #include <linux/errno.h>
 #include <linux/interrupt.h>
+#include <linux/io.h>
 #include <linux/kernel.h>
 #include <linux/serial_reg.h>
 #include <linux/types.h>
diff --git a/drivers/media/rc/st_rc.c b/drivers/media/rc/st_rc.c
index 28477aa955635..988b09191c4c7 100644
--- a/drivers/media/rc/st_rc.c
+++ b/drivers/media/rc/st_rc.c
@@ -6,6 +6,7 @@
 #include <linux/kernel.h>
 #include <linux/clk.h>
 #include <linux/interrupt.h>
+#include <linux/io.h>
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/platform_device.h>
diff --git a/drivers/media/rc/sunxi-cir.c b/drivers/media/rc/sunxi-cir.c
index bf58c965ead8c..b49df8355e6b3 100644
--- a/drivers/media/rc/sunxi-cir.c
+++ b/drivers/media/rc/sunxi-cir.c
@@ -12,6 +12,7 @@
 
 #include <linux/clk.h>
 #include <linux/interrupt.h>
+#include <linux/io.h>
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/platform_device.h>
diff --git a/drivers/mux/core.c b/drivers/mux/core.c
index 7758161129320..78c0022697ec7 100644
--- a/drivers/mux/core.c
+++ b/drivers/mux/core.c
@@ -64,7 +64,7 @@ static void mux_chip_release(struct device *dev)
 {
 	struct mux_chip *mux_chip = to_mux_chip(dev);
 
-	ida_simple_remove(&mux_ida, mux_chip->id);
+	ida_free(&mux_ida, mux_chip->id);
 	kfree(mux_chip);
 }
 
@@ -111,7 +111,7 @@ struct mux_chip *mux_chip_alloc(struct device *dev,
 	mux_chip->dev.of_node = dev->of_node;
 	dev_set_drvdata(&mux_chip->dev, mux_chip);
 
-	mux_chip->id = ida_simple_get(&mux_ida, 0, 0, GFP_KERNEL);
+	mux_chip->id = ida_alloc(&mux_ida, GFP_KERNEL);
 	if (mux_chip->id < 0) {
 		int err = mux_chip->id;
 
diff --git a/drivers/pps/clients/pps_parport.c b/drivers/pps/clients/pps_parport.c
index 42f93d4c6ee32..af972cdc04b53 100644
--- a/drivers/pps/clients/pps_parport.c
+++ b/drivers/pps/clients/pps_parport.c
@@ -148,7 +148,7 @@ static void parport_attach(struct parport *port)
 		return;
 	}
 
-	index = ida_simple_get(&pps_client_index, 0, 0, GFP_KERNEL);
+	index = ida_alloc(&pps_client_index, GFP_KERNEL);
 	memset(&pps_client_cb, 0, sizeof(pps_client_cb));
 	pps_client_cb.private = device;
 	pps_client_cb.irq_func = parport_irq;
@@ -188,7 +188,7 @@ err_release_dev:
 err_unregister_dev:
 	parport_unregister_device(device->pardev);
 err_free:
-	ida_simple_remove(&pps_client_index, index);
+	ida_free(&pps_client_index, index);
 	kfree(device);
 }
 
@@ -208,7 +208,7 @@ static void parport_detach(struct parport *port)
 	pps_unregister_source(device->pps);
 	parport_release(pardev);
 	parport_unregister_device(pardev);
-	ida_simple_remove(&pps_client_index, device->index);
+	ida_free(&pps_client_index, device->index);
 	kfree(device);
 }
 
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index b5a25ee49eea4..a43897b03ce94 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -1934,7 +1934,7 @@ static void free_note_info(struct elf_note_info *info)
 		threads = t->next;
 		WARN_ON(t->notes[0].data && t->notes[0].data != &t->prstatus);
 		for (i = 1; i < info->thread_notes; ++i)
-			kfree(t->notes[i].data);
+			kvfree(t->notes[i].data);
 		kfree(t);
 	}
 	kfree(info->psinfo.data);
diff --git a/fs/fat/dir.c b/fs/fat/dir.c
index 00235b8a1823a..acbec5bdd5210 100644
--- a/fs/fat/dir.c
+++ b/fs/fat/dir.c
@@ -269,6 +269,18 @@ enum { PARSE_INVALID = 1, PARSE_NOT_LONGNAME, PARSE_EOF, };
 /**
  * fat_parse_long - Parse extended directory entry.
  *
+ * @dir: Pointer to the inode that represents the directory.
+ * @pos: On input, contains the starting position to read from.
+ *       On output, updated with the new position.
+ * @bh: Pointer to the buffer head that may be used for reading directory
+ *	 entries. May be updated.
+ * @de: On input, points to the current directory entry.
+ *      On output, points to the next directory entry.
+ * @unicode: Pointer to a buffer where the parsed Unicode long filename will be
+ *	      stored.
+ * @nr_slots: Pointer to a variable that will store the number of longname
+ *	       slots found.
+ *
  * This function returns zero on success, negative value on error, or one of
  * the following:
  *
diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c
index 65659fa0372e6..a139970e48041 100644
--- a/fs/nilfs2/btree.c
+++ b/fs/nilfs2/btree.c
@@ -1857,13 +1857,22 @@ nilfs_btree_commit_convert_and_insert(struct nilfs_bmap *btree,
 }
 
 /**
- * nilfs_btree_convert_and_insert -
- * @bmap:
- * @key:
- * @ptr:
- * @keys:
- * @ptrs:
- * @n:
+ * nilfs_btree_convert_and_insert - Convert and insert entries into a B-tree
+ * @btree: NILFS B-tree structure
+ * @key: Key of the new entry to be inserted
+ * @ptr: Pointer (block number) associated with the key to be inserted
+ * @keys: Array of keys to be inserted in addition to @key
+ * @ptrs: Array of pointers associated with @keys
+ * @n: Number of keys and pointers in @keys and @ptrs
+ *
+ * This function is used to insert a new entry specified by @key and @ptr,
+ * along with additional entries specified by @keys and @ptrs arrays, into a
+ * NILFS B-tree.
+ * It prepares the necessary changes by allocating the required blocks and any
+ * necessary intermediate nodes. It converts configurations from other forms of
+ * block mapping (the one that currently exists is direct mapping) to a B-tree.
+ *
+ * Return: 0 on success or a negative error code on failure.
  */
 int nilfs_btree_convert_and_insert(struct nilfs_bmap *btree,
 				   __u64 key, __u64 ptr,
diff --git a/fs/nilfs2/dir.c b/fs/nilfs2/dir.c
index aee40db7a036f..a002a44ff1617 100644
--- a/fs/nilfs2/dir.c
+++ b/fs/nilfs2/dir.c
@@ -174,7 +174,6 @@ Eend:
 		    dir->i_ino, (folio->index << PAGE_SHIFT) + offs,
 		    (unsigned long)le64_to_cpu(p->inode));
 fail:
-	folio_set_error(folio);
 	return false;
 }
 
diff --git a/fs/nilfs2/gcinode.c b/fs/nilfs2/gcinode.c
index bf9a11d588172..1c9ae36a03abe 100644
--- a/fs/nilfs2/gcinode.c
+++ b/fs/nilfs2/gcinode.c
@@ -175,6 +175,7 @@ int nilfs_init_gcinode(struct inode *inode)
 
 /**
  * nilfs_remove_all_gcinodes() - remove all unprocessed gc inodes
+ * @nilfs: NILFS filesystem instance
  */
 void nilfs_remove_all_gcinodes(struct the_nilfs *nilfs)
 {
diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h
index 2e29b98ba8bab..728e90be3570b 100644
--- a/fs/nilfs2/nilfs.h
+++ b/fs/nilfs2/nilfs.h
@@ -335,8 +335,8 @@ void __nilfs_error(struct super_block *sb, const char *function,
 
 extern struct nilfs_super_block *
 nilfs_read_super_block(struct super_block *, u64, int, struct buffer_head **);
-extern int nilfs_store_magic_and_option(struct super_block *,
-					struct nilfs_super_block *, char *);
+extern int nilfs_store_magic(struct super_block *sb,
+			     struct nilfs_super_block *sbp);
 extern int nilfs_check_feature_compatibility(struct super_block *,
 					     struct nilfs_super_block *);
 extern void nilfs_set_log_cursor(struct nilfs_super_block *,
diff --git a/fs/nilfs2/recovery.c b/fs/nilfs2/recovery.c
index 49a70c68bf3c0..020f304c600e1 100644
--- a/fs/nilfs2/recovery.c
+++ b/fs/nilfs2/recovery.c
@@ -563,6 +563,7 @@ static int nilfs_recover_dsync_blocks(struct the_nilfs *nilfs,
  * checkpoint
  * @nilfs: nilfs object
  * @sb: super block instance
+ * @root: NILFS root instance
  * @ri: pointer to a nilfs_recovery_info
  */
 static int nilfs_do_roll_forward(struct the_nilfs *nilfs,
@@ -698,7 +699,9 @@ static void nilfs_finish_roll_forward(struct the_nilfs *nilfs,
 		return;
 
 	bh = __getblk(nilfs->ns_bdev, ri->ri_lsegs_start, nilfs->ns_blocksize);
-	BUG_ON(!bh);
+	if (WARN_ON(!bh))
+		return;  /* should never happen */
+
 	memset(bh->b_data, 0, bh->b_size);
 	set_buffer_dirty(bh);
 	err = sync_dirty_buffer(bh);
diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c
index aa5290cb7467c..8654ab8ad5340 100644
--- a/fs/nilfs2/segment.c
+++ b/fs/nilfs2/segment.c
@@ -1725,14 +1725,8 @@ static void nilfs_end_folio_io(struct folio *folio, int err)
 		return;
 	}
 
-	if (!err) {
-		if (!nilfs_folio_buffers_clean(folio))
-			filemap_dirty_folio(folio->mapping, folio);
-		folio_clear_error(folio);
-	} else {
+	if (err || !nilfs_folio_buffers_clean(folio))
 		filemap_dirty_folio(folio->mapping, folio);
-		folio_set_error(folio);
-	}
 
 	folio_end_writeback(folio);
 }
diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c
index ac24ed109ce93..e835e1f5a7120 100644
--- a/fs/nilfs2/super.c
+++ b/fs/nilfs2/super.c
@@ -29,13 +29,13 @@
 #include <linux/slab.h>
 #include <linux/init.h>
 #include <linux/blkdev.h>
-#include <linux/parser.h>
 #include <linux/crc32.h>
 #include <linux/vfs.h>
 #include <linux/writeback.h>
 #include <linux/seq_file.h>
 #include <linux/mount.h>
 #include <linux/fs_context.h>
+#include <linux/fs_parser.h>
 #include "nilfs.h"
 #include "export.h"
 #include "mdt.h"
@@ -61,7 +61,6 @@ struct kmem_cache *nilfs_segbuf_cachep;
 struct kmem_cache *nilfs_btree_path_cache;
 
 static int nilfs_setup_super(struct super_block *sb, int is_mount);
-static int nilfs_remount(struct super_block *sb, int *flags, char *data);
 
 void __nilfs_msg(struct super_block *sb, const char *fmt, ...)
 {
@@ -702,105 +701,98 @@ static const struct super_operations nilfs_sops = {
 	.freeze_fs	= nilfs_freeze,
 	.unfreeze_fs	= nilfs_unfreeze,
 	.statfs         = nilfs_statfs,
-	.remount_fs     = nilfs_remount,
 	.show_options = nilfs_show_options
 };
 
 enum {
-	Opt_err_cont, Opt_err_panic, Opt_err_ro,
-	Opt_barrier, Opt_nobarrier, Opt_snapshot, Opt_order, Opt_norecovery,
-	Opt_discard, Opt_nodiscard, Opt_err,
+	Opt_err, Opt_barrier, Opt_snapshot, Opt_order, Opt_norecovery,
+	Opt_discard,
 };
 
-static match_table_t tokens = {
-	{Opt_err_cont, "errors=continue"},
-	{Opt_err_panic, "errors=panic"},
-	{Opt_err_ro, "errors=remount-ro"},
-	{Opt_barrier, "barrier"},
-	{Opt_nobarrier, "nobarrier"},
-	{Opt_snapshot, "cp=%u"},
-	{Opt_order, "order=%s"},
-	{Opt_norecovery, "norecovery"},
-	{Opt_discard, "discard"},
-	{Opt_nodiscard, "nodiscard"},
-	{Opt_err, NULL}
+static const struct constant_table nilfs_param_err[] = {
+	{"continue",	NILFS_MOUNT_ERRORS_CONT},
+	{"panic",	NILFS_MOUNT_ERRORS_PANIC},
+	{"remount-ro",	NILFS_MOUNT_ERRORS_RO},
+	{}
 };
 
-static int parse_options(char *options, struct super_block *sb, int is_remount)
-{
-	struct the_nilfs *nilfs = sb->s_fs_info;
-	char *p;
-	substring_t args[MAX_OPT_ARGS];
-
-	if (!options)
-		return 1;
-
-	while ((p = strsep(&options, ",")) != NULL) {
-		int token;
+static const struct fs_parameter_spec nilfs_param_spec[] = {
+	fsparam_enum	("errors", Opt_err, nilfs_param_err),
+	fsparam_flag_no	("barrier", Opt_barrier),
+	fsparam_u64	("cp", Opt_snapshot),
+	fsparam_string	("order", Opt_order),
+	fsparam_flag	("norecovery", Opt_norecovery),
+	fsparam_flag_no	("discard", Opt_discard),
+	{}
+};
 
-		if (!*p)
-			continue;
+struct nilfs_fs_context {
+	unsigned long ns_mount_opt;
+	__u64 cno;
+};
 
-		token = match_token(p, tokens, args);
-		switch (token) {
-		case Opt_barrier:
-			nilfs_set_opt(nilfs, BARRIER);
-			break;
-		case Opt_nobarrier:
+static int nilfs_parse_param(struct fs_context *fc, struct fs_parameter *param)
+{
+	struct nilfs_fs_context *nilfs = fc->fs_private;
+	int is_remount = fc->purpose == FS_CONTEXT_FOR_RECONFIGURE;
+	struct fs_parse_result result;
+	int opt;
+
+	opt = fs_parse(fc, nilfs_param_spec, param, &result);
+	if (opt < 0)
+		return opt;
+
+	switch (opt) {
+	case Opt_barrier:
+		if (result.negated)
 			nilfs_clear_opt(nilfs, BARRIER);
-			break;
-		case Opt_order:
-			if (strcmp(args[0].from, "relaxed") == 0)
-				/* Ordered data semantics */
-				nilfs_clear_opt(nilfs, STRICT_ORDER);
-			else if (strcmp(args[0].from, "strict") == 0)
-				/* Strict in-order semantics */
-				nilfs_set_opt(nilfs, STRICT_ORDER);
-			else
-				return 0;
-			break;
-		case Opt_err_panic:
-			nilfs_write_opt(nilfs, ERROR_MODE, ERRORS_PANIC);
-			break;
-		case Opt_err_ro:
-			nilfs_write_opt(nilfs, ERROR_MODE, ERRORS_RO);
-			break;
-		case Opt_err_cont:
-			nilfs_write_opt(nilfs, ERROR_MODE, ERRORS_CONT);
-			break;
-		case Opt_snapshot:
-			if (is_remount) {
-				nilfs_err(sb,
-					  "\"%s\" option is invalid for remount",
-					  p);
-				return 0;
-			}
-			break;
-		case Opt_norecovery:
-			nilfs_set_opt(nilfs, NORECOVERY);
-			break;
-		case Opt_discard:
-			nilfs_set_opt(nilfs, DISCARD);
-			break;
-		case Opt_nodiscard:
-			nilfs_clear_opt(nilfs, DISCARD);
-			break;
-		default:
-			nilfs_err(sb, "unrecognized mount option \"%s\"", p);
-			return 0;
+		else
+			nilfs_set_opt(nilfs, BARRIER);
+		break;
+	case Opt_order:
+		if (strcmp(param->string, "relaxed") == 0)
+			/* Ordered data semantics */
+			nilfs_clear_opt(nilfs, STRICT_ORDER);
+		else if (strcmp(param->string, "strict") == 0)
+			/* Strict in-order semantics */
+			nilfs_set_opt(nilfs, STRICT_ORDER);
+		else
+			return -EINVAL;
+		break;
+	case Opt_err:
+		nilfs->ns_mount_opt &= ~NILFS_MOUNT_ERROR_MODE;
+		nilfs->ns_mount_opt |= result.uint_32;
+		break;
+	case Opt_snapshot:
+		if (is_remount) {
+			struct super_block *sb = fc->root->d_sb;
+
+			nilfs_err(sb,
+				  "\"%s\" option is invalid for remount",
+				  param->key);
+			return -EINVAL;
+		}
+		if (result.uint_64 == 0) {
+			nilfs_err(NULL,
+				  "invalid option \"cp=0\": invalid checkpoint number 0");
+			return -EINVAL;
 		}
+		nilfs->cno = result.uint_64;
+		break;
+	case Opt_norecovery:
+		nilfs_set_opt(nilfs, NORECOVERY);
+		break;
+	case Opt_discard:
+		if (result.negated)
+			nilfs_clear_opt(nilfs, DISCARD);
+		else
+			nilfs_set_opt(nilfs, DISCARD);
+		break;
+	default:
+		return -EINVAL;
 	}
-	return 1;
-}
-
-static inline void
-nilfs_set_default_options(struct super_block *sb,
-			  struct nilfs_super_block *sbp)
-{
-	struct the_nilfs *nilfs = sb->s_fs_info;
 
-	nilfs->ns_mount_opt =
-		NILFS_MOUNT_ERRORS_RO | NILFS_MOUNT_BARRIER;
+	return 0;
 }
 
 static int nilfs_setup_super(struct super_block *sb, int is_mount)
@@ -857,9 +849,8 @@ struct nilfs_super_block *nilfs_read_super_block(struct super_block *sb,
 	return (struct nilfs_super_block *)((char *)(*pbh)->b_data + offset);
 }
 
-int nilfs_store_magic_and_option(struct super_block *sb,
-				 struct nilfs_super_block *sbp,
-				 char *data)
+int nilfs_store_magic(struct super_block *sb,
+		      struct nilfs_super_block *sbp)
 {
 	struct the_nilfs *nilfs = sb->s_fs_info;
 
@@ -870,14 +861,12 @@ int nilfs_store_magic_and_option(struct super_block *sb,
 	sb->s_flags |= SB_NOATIME;
 #endif
 
-	nilfs_set_default_options(sb, sbp);
-
 	nilfs->ns_resuid = le16_to_cpu(sbp->s_def_resuid);
 	nilfs->ns_resgid = le16_to_cpu(sbp->s_def_resgid);
 	nilfs->ns_interval = le32_to_cpu(sbp->s_c_interval);
 	nilfs->ns_watermark = le32_to_cpu(sbp->s_c_block_max);
 
-	return !parse_options(data, sb, 0) ? -EINVAL : 0;
+	return 0;
 }
 
 int nilfs_check_feature_compatibility(struct super_block *sb,
@@ -1035,17 +1024,17 @@ int nilfs_checkpoint_is_mounted(struct super_block *sb, __u64 cno)
 /**
  * nilfs_fill_super() - initialize a super block instance
  * @sb: super_block
- * @data: mount options
- * @silent: silent mode flag
+ * @fc: filesystem context
  *
  * This function is called exclusively by nilfs->ns_mount_mutex.
  * So, the recovery process is protected from other simultaneous mounts.
  */
 static int
-nilfs_fill_super(struct super_block *sb, void *data, int silent)
+nilfs_fill_super(struct super_block *sb, struct fs_context *fc)
 {
 	struct the_nilfs *nilfs;
 	struct nilfs_root *fsroot;
+	struct nilfs_fs_context *ctx = fc->fs_private;
 	__u64 cno;
 	int err;
 
@@ -1055,10 +1044,13 @@ nilfs_fill_super(struct super_block *sb, void *data, int silent)
 
 	sb->s_fs_info = nilfs;
 
-	err = init_nilfs(nilfs, sb, (char *)data);
+	err = init_nilfs(nilfs, sb);
 	if (err)
 		goto failed_nilfs;
 
+	/* Copy in parsed mount options */
+	nilfs->ns_mount_opt = ctx->ns_mount_opt;
+
 	sb->s_op = &nilfs_sops;
 	sb->s_export_op = &nilfs_export_ops;
 	sb->s_root = NULL;
@@ -1117,34 +1109,25 @@ nilfs_fill_super(struct super_block *sb, void *data, int silent)
 	return err;
 }
 
-static int nilfs_remount(struct super_block *sb, int *flags, char *data)
+static int nilfs_reconfigure(struct fs_context *fc)
 {
+	struct nilfs_fs_context *ctx = fc->fs_private;
+	struct super_block *sb = fc->root->d_sb;
 	struct the_nilfs *nilfs = sb->s_fs_info;
-	unsigned long old_sb_flags;
-	unsigned long old_mount_opt;
 	int err;
 
 	sync_filesystem(sb);
-	old_sb_flags = sb->s_flags;
-	old_mount_opt = nilfs->ns_mount_opt;
-
-	if (!parse_options(data, sb, 1)) {
-		err = -EINVAL;
-		goto restore_opts;
-	}
-	sb->s_flags = (sb->s_flags & ~SB_POSIXACL);
 
 	err = -EINVAL;
 
 	if (!nilfs_valid_fs(nilfs)) {
 		nilfs_warn(sb,
 			   "couldn't remount because the filesystem is in an incomplete recovery state");
-		goto restore_opts;
+		goto ignore_opts;
 	}
-
-	if ((bool)(*flags & SB_RDONLY) == sb_rdonly(sb))
+	if ((bool)(fc->sb_flags & SB_RDONLY) == sb_rdonly(sb))
 		goto out;
-	if (*flags & SB_RDONLY) {
+	if (fc->sb_flags & SB_RDONLY) {
 		sb->s_flags |= SB_RDONLY;
 
 		/*
@@ -1172,138 +1155,67 @@ static int nilfs_remount(struct super_block *sb, int *flags, char *data)
 				   "couldn't remount RDWR because of unsupported optional features (%llx)",
 				   (unsigned long long)features);
 			err = -EROFS;
-			goto restore_opts;
+			goto ignore_opts;
 		}
 
 		sb->s_flags &= ~SB_RDONLY;
 
 		root = NILFS_I(d_inode(sb->s_root))->i_root;
 		err = nilfs_attach_log_writer(sb, root);
-		if (err)
-			goto restore_opts;
+		if (err) {
+			sb->s_flags |= SB_RDONLY;
+			goto ignore_opts;
+		}
 
 		down_write(&nilfs->ns_sem);
 		nilfs_setup_super(sb, true);
 		up_write(&nilfs->ns_sem);
 	}
  out:
-	return 0;
-
- restore_opts:
-	sb->s_flags = old_sb_flags;
-	nilfs->ns_mount_opt = old_mount_opt;
-	return err;
-}
-
-struct nilfs_super_data {
-	__u64 cno;
-	int flags;
-};
-
-static int nilfs_parse_snapshot_option(const char *option,
-				       const substring_t *arg,
-				       struct nilfs_super_data *sd)
-{
-	unsigned long long val;
-	const char *msg = NULL;
-	int err;
-
-	if (!(sd->flags & SB_RDONLY)) {
-		msg = "read-only option is not specified";
-		goto parse_error;
-	}
-
-	err = kstrtoull(arg->from, 0, &val);
-	if (err) {
-		if (err == -ERANGE)
-			msg = "too large checkpoint number";
-		else
-			msg = "malformed argument";
-		goto parse_error;
-	} else if (val == 0) {
-		msg = "invalid checkpoint number 0";
-		goto parse_error;
-	}
-	sd->cno = val;
-	return 0;
-
-parse_error:
-	nilfs_err(NULL, "invalid option \"%s\": %s", option, msg);
-	return 1;
-}
-
-/**
- * nilfs_identify - pre-read mount options needed to identify mount instance
- * @data: mount options
- * @sd: nilfs_super_data
- */
-static int nilfs_identify(char *data, struct nilfs_super_data *sd)
-{
-	char *p, *options = data;
-	substring_t args[MAX_OPT_ARGS];
-	int token;
-	int ret = 0;
-
-	do {
-		p = strsep(&options, ",");
-		if (p != NULL && *p) {
-			token = match_token(p, tokens, args);
-			if (token == Opt_snapshot)
-				ret = nilfs_parse_snapshot_option(p, &args[0],
-								  sd);
-		}
-		if (!options)
-			break;
-		BUG_ON(options == data);
-		*(options - 1) = ',';
-	} while (!ret);
-	return ret;
-}
+	sb->s_flags = (sb->s_flags & ~SB_POSIXACL);
+	/* Copy over parsed remount options */
+	nilfs->ns_mount_opt = ctx->ns_mount_opt;
 
-static int nilfs_set_bdev_super(struct super_block *s, void *data)
-{
-	s->s_dev = *(dev_t *)data;
 	return 0;
-}
 
-static int nilfs_test_bdev_super(struct super_block *s, void *data)
-{
-	return !(s->s_iflags & SB_I_RETIRED) && s->s_dev == *(dev_t *)data;
+ ignore_opts:
+	return err;
 }
 
-static struct dentry *
-nilfs_mount(struct file_system_type *fs_type, int flags,
-	     const char *dev_name, void *data)
+static int
+nilfs_get_tree(struct fs_context *fc)
 {
-	struct nilfs_super_data sd = { .flags = flags };
+	struct nilfs_fs_context *ctx = fc->fs_private;
 	struct super_block *s;
 	dev_t dev;
 	int err;
 
-	if (nilfs_identify(data, &sd))
-		return ERR_PTR(-EINVAL);
+	if (ctx->cno && !(fc->sb_flags & SB_RDONLY)) {
+		nilfs_err(NULL,
+			  "invalid option \"cp=%llu\": read-only option is not specified",
+			  ctx->cno);
+		return -EINVAL;
+	}
 
-	err = lookup_bdev(dev_name, &dev);
+	err = lookup_bdev(fc->source, &dev);
 	if (err)
-		return ERR_PTR(err);
+		return err;
 
-	s = sget(fs_type, nilfs_test_bdev_super, nilfs_set_bdev_super, flags,
-		 &dev);
+	s = sget_dev(fc, dev);
 	if (IS_ERR(s))
-		return ERR_CAST(s);
+		return PTR_ERR(s);
 
 	if (!s->s_root) {
-		err = setup_bdev_super(s, flags, NULL);
+		err = setup_bdev_super(s, fc->sb_flags, fc);
 		if (!err)
-			err = nilfs_fill_super(s, data,
-					       flags & SB_SILENT ? 1 : 0);
+			err = nilfs_fill_super(s, fc);
 		if (err)
 			goto failed_super;
 
 		s->s_flags |= SB_ACTIVE;
-	} else if (!sd.cno) {
+	} else if (!ctx->cno) {
 		if (nilfs_tree_is_busy(s->s_root)) {
-			if ((flags ^ s->s_flags) & SB_RDONLY) {
+			if ((fc->sb_flags ^ s->s_flags) & SB_RDONLY) {
 				nilfs_err(s,
 					  "the device already has a %s mount.",
 					  sb_rdonly(s) ? "read-only" : "read/write");
@@ -1312,37 +1224,75 @@ nilfs_mount(struct file_system_type *fs_type, int flags,
 			}
 		} else {
 			/*
-			 * Try remount to setup mount states if the current
+			 * Try reconfigure to setup mount states if the current
 			 * tree is not mounted and only snapshots use this sb.
+			 *
+			 * Since nilfs_reconfigure() requires fc->root to be
+			 * set, set it first and release it on failure.
 			 */
-			err = nilfs_remount(s, &flags, data);
-			if (err)
+			fc->root = dget(s->s_root);
+			err = nilfs_reconfigure(fc);
+			if (err) {
+				dput(fc->root);
+				fc->root = NULL;  /* prevent double release */
 				goto failed_super;
+			}
+			return 0;
 		}
 	}
 
-	if (sd.cno) {
+	if (ctx->cno) {
 		struct dentry *root_dentry;
 
-		err = nilfs_attach_snapshot(s, sd.cno, &root_dentry);
+		err = nilfs_attach_snapshot(s, ctx->cno, &root_dentry);
 		if (err)
 			goto failed_super;
-		return root_dentry;
+		fc->root = root_dentry;
+		return 0;
 	}
 
-	return dget(s->s_root);
+	fc->root = dget(s->s_root);
+	return 0;
 
  failed_super:
 	deactivate_locked_super(s);
-	return ERR_PTR(err);
+	return err;
+}
+
+static void nilfs_free_fc(struct fs_context *fc)
+{
+	kfree(fc->fs_private);
+}
+
+static const struct fs_context_operations nilfs_context_ops = {
+	.parse_param	= nilfs_parse_param,
+	.get_tree	= nilfs_get_tree,
+	.reconfigure	= nilfs_reconfigure,
+	.free		= nilfs_free_fc,
+};
+
+static int nilfs_init_fs_context(struct fs_context *fc)
+{
+	struct nilfs_fs_context *ctx;
+
+	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+
+	ctx->ns_mount_opt = NILFS_MOUNT_ERRORS_RO | NILFS_MOUNT_BARRIER;
+	fc->fs_private = ctx;
+	fc->ops = &nilfs_context_ops;
+
+	return 0;
 }
 
 struct file_system_type nilfs_fs_type = {
 	.owner    = THIS_MODULE,
 	.name     = "nilfs2",
-	.mount    = nilfs_mount,
 	.kill_sb  = kill_block_super,
 	.fs_flags = FS_REQUIRES_DEV,
+	.init_fs_context = nilfs_init_fs_context,
+	.parameters = nilfs_param_spec,
 };
 MODULE_ALIAS_FS("nilfs2");
 
diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c
index 2ae2c1bbf6d17..f41d7b6d432c6 100644
--- a/fs/nilfs2/the_nilfs.c
+++ b/fs/nilfs2/the_nilfs.c
@@ -592,7 +592,7 @@ static int nilfs_load_super_block(struct the_nilfs *nilfs,
 	struct nilfs_super_block **sbp = nilfs->ns_sbp;
 	struct buffer_head **sbh = nilfs->ns_sbh;
 	u64 sb2off, devsize = bdev_nr_bytes(nilfs->ns_bdev);
-	int valid[2], swp = 0;
+	int valid[2], swp = 0, older;
 
 	if (devsize < NILFS_SEG_MIN_BLOCKS * NILFS_MIN_BLOCK_SIZE + 4096) {
 		nilfs_err(sb, "device size too small");
@@ -648,9 +648,25 @@ static int nilfs_load_super_block(struct the_nilfs *nilfs,
 	if (swp)
 		nilfs_swap_super_block(nilfs);
 
+	/*
+	 * Calculate the array index of the older superblock data.
+	 * If one has been dropped, set index 0 pointing to the remaining one,
+	 * otherwise set index 1 pointing to the old one (including if both
+	 * are the same).
+	 *
+	 *  Divided case             valid[0]  valid[1]  swp  ->  older
+	 *  -------------------------------------------------------------
+	 *  Both SBs are invalid        0         0       N/A (Error)
+	 *  SB1 is invalid              0         1       1         0
+	 *  SB2 is invalid              1         0       0         0
+	 *  SB2 is newer                1         1       1         0
+	 *  SB2 is older or the same    1         1       0         1
+	 */
+	older = valid[1] ^ swp;
+
 	nilfs->ns_sbwcount = 0;
 	nilfs->ns_sbwtime = le64_to_cpu(sbp[0]->s_wtime);
-	nilfs->ns_prot_seq = le64_to_cpu(sbp[valid[1] & !swp]->s_last_seq);
+	nilfs->ns_prot_seq = le64_to_cpu(sbp[older]->s_last_seq);
 	*sbpp = sbp[0];
 	return 0;
 }
@@ -659,7 +675,6 @@ static int nilfs_load_super_block(struct the_nilfs *nilfs,
  * init_nilfs - initialize a NILFS instance.
  * @nilfs: the_nilfs structure
  * @sb: super block
- * @data: mount options
  *
  * init_nilfs() performs common initialization per block device (e.g.
  * reading the super block, getting disk layout information, initializing
@@ -668,7 +683,7 @@ static int nilfs_load_super_block(struct the_nilfs *nilfs,
  * Return Value: On success, 0 is returned. On error, a negative error
  * code is returned.
  */
-int init_nilfs(struct the_nilfs *nilfs, struct super_block *sb, char *data)
+int init_nilfs(struct the_nilfs *nilfs, struct super_block *sb)
 {
 	struct nilfs_super_block *sbp;
 	int blocksize;
@@ -686,7 +701,7 @@ int init_nilfs(struct the_nilfs *nilfs, struct super_block *sb, char *data)
 	if (err)
 		goto out;
 
-	err = nilfs_store_magic_and_option(sb, sbp, data);
+	err = nilfs_store_magic(sb, sbp);
 	if (err)
 		goto failed_sbh;
 
diff --git a/fs/nilfs2/the_nilfs.h b/fs/nilfs2/the_nilfs.h
index cd4ae1b8ae165..85da0629415df 100644
--- a/fs/nilfs2/the_nilfs.h
+++ b/fs/nilfs2/the_nilfs.h
@@ -219,10 +219,6 @@ THE_NILFS_FNS(PURGING, purging)
 #define nilfs_set_opt(nilfs, opt)  \
 	((nilfs)->ns_mount_opt |= NILFS_MOUNT_##opt)
 #define nilfs_test_opt(nilfs, opt) ((nilfs)->ns_mount_opt & NILFS_MOUNT_##opt)
-#define nilfs_write_opt(nilfs, mask, opt)				\
-	((nilfs)->ns_mount_opt =					\
-		(((nilfs)->ns_mount_opt & ~NILFS_MOUNT_##mask) |	\
-		 NILFS_MOUNT_##opt))					\
 
 /**
  * struct nilfs_root - nilfs root object
@@ -276,7 +272,7 @@ static inline int nilfs_sb_will_flip(struct the_nilfs *nilfs)
 void nilfs_set_last_segment(struct the_nilfs *, sector_t, u64, __u64);
 struct the_nilfs *alloc_nilfs(struct super_block *sb);
 void destroy_nilfs(struct the_nilfs *nilfs);
-int init_nilfs(struct the_nilfs *nilfs, struct super_block *sb, char *data);
+int init_nilfs(struct the_nilfs *nilfs, struct super_block *sb);
 int load_nilfs(struct the_nilfs *nilfs, struct super_block *sb);
 unsigned long nilfs_nrsvsegs(struct the_nilfs *nilfs, unsigned long nsegs);
 void nilfs_set_nsegments(struct the_nilfs *nilfs, unsigned long nsegs);
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index b82185075de7d..f0467d3b3c880 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -2283,8 +2283,6 @@ unlock:
 	ocfs2_inode_unlock(inode, 1);
 	brelse(di_bh);
 out:
-	if (ret < 0)
-		ret = -EIO;
 	return ret;
 }
 
diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c
index 5c04dde99981c..2018501b22493 100644
--- a/fs/ocfs2/dlm/dlmdomain.c
+++ b/fs/ocfs2/dlm/dlmdomain.c
@@ -1274,7 +1274,7 @@ static int dlm_query_nodeinfo_handler(struct o2net_msg *msg, u32 len,
 {
 	struct dlm_query_nodeinfo *qn;
 	struct dlm_ctxt *dlm = NULL;
-	int locked = 0, status = -EINVAL;
+	int status = -EINVAL;
 
 	qn = (struct dlm_query_nodeinfo *) msg->buf;
 
@@ -1290,12 +1290,11 @@ static int dlm_query_nodeinfo_handler(struct o2net_msg *msg, u32 len,
 	}
 
 	spin_lock(&dlm->spinlock);
-	locked = 1;
 	if (dlm->joining_node != qn->qn_nodenum) {
 		mlog(ML_ERROR, "Node %d queried nodes on domain %s but "
 		     "joining node is %d\n", qn->qn_nodenum, qn->qn_domain,
 		     dlm->joining_node);
-		goto bail;
+		goto unlock;
 	}
 
 	/* Support for node query was added in 1.1 */
@@ -1305,14 +1304,14 @@ static int dlm_query_nodeinfo_handler(struct o2net_msg *msg, u32 len,
 		     "but active dlm protocol is %d.%d\n", qn->qn_nodenum,
 		     qn->qn_domain, dlm->dlm_locking_proto.pv_major,
 		     dlm->dlm_locking_proto.pv_minor);
-		goto bail;
+		goto unlock;
 	}
 
 	status = dlm_match_nodes(dlm, qn);
 
+unlock:
+	spin_unlock(&dlm->spinlock);
 bail:
-	if (locked)
-		spin_unlock(&dlm->spinlock);
 	spin_unlock(&dlm_domain_lock);
 
 	return status;
@@ -1528,7 +1527,6 @@ static void dlm_send_join_asserts(struct dlm_ctxt *dlm,
 {
 	int status, node, live;
 
-	status = 0;
 	node = -1;
 	while ((node = find_next_bit(node_map, O2NM_MAX_NODES,
 				     node + 1)) < O2NM_MAX_NODES) {
diff --git a/fs/ocfs2/export.c b/fs/ocfs2/export.c
index b8b6a191b5cb5..96b684763b390 100644
--- a/fs/ocfs2/export.c
+++ b/fs/ocfs2/export.c
@@ -255,9 +255,9 @@ static struct dentry *ocfs2_fh_to_dentry(struct super_block *sb,
 	if (fh_len < 3 || fh_type > 2)
 		return NULL;
 
-	handle.ih_blkno = (u64)le32_to_cpu(fid->raw[0]) << 32;
-	handle.ih_blkno |= (u64)le32_to_cpu(fid->raw[1]);
-	handle.ih_generation = le32_to_cpu(fid->raw[2]);
+	handle.ih_blkno = (u64)le32_to_cpu((__force __le32)fid->raw[0]) << 32;
+	handle.ih_blkno |= (u64)le32_to_cpu((__force __le32)fid->raw[1]);
+	handle.ih_generation = le32_to_cpu((__force __le32)fid->raw[2]);
 	return ocfs2_get_dentry(sb, &handle);
 }
 
@@ -269,9 +269,9 @@ static struct dentry *ocfs2_fh_to_parent(struct super_block *sb,
 	if (fh_type != 2 || fh_len < 6)
 		return NULL;
 
-	parent.ih_blkno = (u64)le32_to_cpu(fid->raw[3]) << 32;
-	parent.ih_blkno |= (u64)le32_to_cpu(fid->raw[4]);
-	parent.ih_generation = le32_to_cpu(fid->raw[5]);
+	parent.ih_blkno = (u64)le32_to_cpu((__force __le32)fid->raw[3]) << 32;
+	parent.ih_blkno |= (u64)le32_to_cpu((__force __le32)fid->raw[4]);
+	parent.ih_generation = le32_to_cpu((__force __le32)fid->raw[5]);
 	return ocfs2_get_dentry(sb, &parent);
 }
 
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 0da8e7bd32616..ccc57038a9779 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -1936,6 +1936,8 @@ static int __ocfs2_change_file_space(struct file *file, struct inode *inode,
 
 	inode_lock(inode);
 
+	/* Wait all existing dio workers, newcomers will block on i_rwsem */
+	inode_dio_wait(inode);
 	/*
 	 * This prevents concurrent writes on other nodes
 	 */
diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c
index 999111bfc2717..2cc5c99fe9416 100644
--- a/fs/ocfs2/inode.c
+++ b/fs/ocfs2/inode.c
@@ -1621,6 +1621,7 @@ static struct super_block *ocfs2_inode_cache_get_super(struct ocfs2_caching_info
 }
 
 static void ocfs2_inode_cache_lock(struct ocfs2_caching_info *ci)
+__acquires(&oi->ip_lock)
 {
 	struct ocfs2_inode_info *oi = cache_info_to_inode(ci);
 
@@ -1628,6 +1629,7 @@ static void ocfs2_inode_cache_lock(struct ocfs2_caching_info *ci)
 }
 
 static void ocfs2_inode_cache_unlock(struct ocfs2_caching_info *ci)
+__releases(&oi->ip_lock)
 {
 	struct ocfs2_inode_info *oi = cache_info_to_inode(ci);
 
diff --git a/fs/ocfs2/ioctl.c b/fs/ocfs2/ioctl.c
index b1550ba73f963..71beef7f8a60b 100644
--- a/fs/ocfs2/ioctl.c
+++ b/fs/ocfs2/ioctl.c
@@ -125,6 +125,7 @@ int ocfs2_fileattr_set(struct mnt_idmap *idmap,
 
 	ocfs2_inode->ip_attr = flags;
 	ocfs2_set_inode_flags(inode);
+	inode_set_ctime_current(inode);
 
 	status = ocfs2_mark_inode_dirty(handle, inode, bh);
 	if (status < 0)
diff --git a/fs/ocfs2/localalloc.c b/fs/ocfs2/localalloc.c
index c803c10dd97ef..5df34561c551c 100644
--- a/fs/ocfs2/localalloc.c
+++ b/fs/ocfs2/localalloc.c
@@ -212,14 +212,15 @@ static inline int ocfs2_la_state_enabled(struct ocfs2_super *osb)
 void ocfs2_local_alloc_seen_free_bits(struct ocfs2_super *osb,
 				      unsigned int num_clusters)
 {
-	spin_lock(&osb->osb_lock);
-	if (osb->local_alloc_state == OCFS2_LA_DISABLED ||
-	    osb->local_alloc_state == OCFS2_LA_THROTTLED)
-		if (num_clusters >= osb->local_alloc_default_bits) {
+	if (num_clusters >= osb->local_alloc_default_bits) {
+		spin_lock(&osb->osb_lock);
+		if (osb->local_alloc_state == OCFS2_LA_DISABLED ||
+		    osb->local_alloc_state == OCFS2_LA_THROTTLED) {
 			cancel_delayed_work(&osb->la_enable_wq);
 			osb->local_alloc_state = OCFS2_LA_ENABLED;
 		}
-	spin_unlock(&osb->osb_lock);
+		spin_unlock(&osb->osb_lock);
+	}
 }
 
 void ocfs2_la_enable_worker(struct work_struct *work)
@@ -335,7 +336,7 @@ int ocfs2_load_local_alloc(struct ocfs2_super *osb)
 		     "found = %u, set = %u, taken = %u, off = %u\n",
 		     num_used, le32_to_cpu(alloc->id1.bitmap1.i_used),
 		     le32_to_cpu(alloc->id1.bitmap1.i_total),
-		     OCFS2_LOCAL_ALLOC(alloc)->la_bm_off);
+		     le32_to_cpu(OCFS2_LOCAL_ALLOC(alloc)->la_bm_off));
 
 		status = -EINVAL;
 		goto bail;
@@ -863,14 +864,8 @@ static int ocfs2_local_alloc_find_clear_bits(struct ocfs2_super *osb,
 
 	numfound = bitoff = startoff = 0;
 	left = le32_to_cpu(alloc->id1.bitmap1.i_total);
-	while ((bitoff = ocfs2_find_next_zero_bit(bitmap, left, startoff)) != -1) {
-		if (bitoff == left) {
-			/* mlog(0, "bitoff (%d) == left", bitoff); */
-			break;
-		}
-		/* mlog(0, "Found a zero: bitoff = %d, startoff = %d, "
-		   "numfound = %d\n", bitoff, startoff, numfound);*/
-
+	while ((bitoff = ocfs2_find_next_zero_bit(bitmap, left, startoff)) <
+	       left) {
 		/* Ok, we found a zero bit... is it contig. or do we
 		 * start over?*/
 		if (bitoff == startoff) {
@@ -976,9 +971,9 @@ static int ocfs2_sync_local_to_main(struct ocfs2_super *osb,
 	start = count = 0;
 	left = le32_to_cpu(alloc->id1.bitmap1.i_total);
 
-	while ((bit_off = ocfs2_find_next_zero_bit(bitmap, left, start))
-	       != -1) {
-		if ((bit_off < left) && (bit_off == start)) {
+	while ((bit_off = ocfs2_find_next_zero_bit(bitmap, left, start)) <
+	       left) {
+		if (bit_off == start) {
 			count++;
 			start++;
 			continue;
@@ -1002,8 +997,7 @@ static int ocfs2_sync_local_to_main(struct ocfs2_super *osb,
 				goto bail;
 			}
 		}
-		if (bit_off >= left)
-			break;
+
 		count = 1;
 		start = bit_off + 1;
 	}
@@ -1220,7 +1214,7 @@ retry_enospc:
 			     OCFS2_LOCAL_ALLOC(alloc)->la_bitmap);
 
 	trace_ocfs2_local_alloc_new_window_result(
-		OCFS2_LOCAL_ALLOC(alloc)->la_bm_off,
+		le32_to_cpu(OCFS2_LOCAL_ALLOC(alloc)->la_bm_off),
 		le32_to_cpu(alloc->id1.bitmap1.i_total));
 
 bail:
diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c
index 1f9ed117e78b6..f9d6a4f9ca921 100644
--- a/fs/ocfs2/move_extents.c
+++ b/fs/ocfs2/move_extents.c
@@ -685,7 +685,7 @@ static int ocfs2_move_extent(struct ocfs2_move_extents_context *context,
 	}
 
 	ret = ocfs2_block_group_set_bits(handle, gb_inode, gd, gd_bh,
-					 goal_bit, len);
+					 goal_bit, len, 0, 0);
 	if (ret) {
 		ocfs2_rollback_alloc_dinode_counts(gb_inode, gb_bh, len,
 					       le16_to_cpu(gd->bg_chain));
diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index 9221a33f917b8..4d1ea8703fcdf 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -566,7 +566,7 @@ static int __ocfs2_mknod_locked(struct inode *dir,
 	fe->i_last_eb_blk = 0;
 	strcpy(fe->i_signature, OCFS2_INODE_SIGNATURE);
 	fe->i_flags |= cpu_to_le32(OCFS2_VALID_FL);
-	ktime_get_real_ts64(&ts);
+	ktime_get_coarse_real_ts64(&ts);
 	fe->i_atime = fe->i_ctime = fe->i_mtime =
 		cpu_to_le64(ts.tv_sec);
 	fe->i_mtime_nsec = fe->i_ctime_nsec = fe->i_atime_nsec =
@@ -797,6 +797,7 @@ static int ocfs2_link(struct dentry *old_dentry,
 	ocfs2_set_links_count(fe, inode->i_nlink);
 	fe->i_ctime = cpu_to_le64(inode_get_ctime_sec(inode));
 	fe->i_ctime_nsec = cpu_to_le32(inode_get_ctime_nsec(inode));
+	ocfs2_update_inode_fsync_trans(handle, inode, 0);
 	ocfs2_journal_dirty(handle, fe_bh);
 
 	err = ocfs2_add_entry(handle, dentry, inode,
@@ -993,6 +994,7 @@ static int ocfs2_unlink(struct inode *dir,
 		drop_nlink(inode);
 	drop_nlink(inode);
 	ocfs2_set_links_count(fe, inode->i_nlink);
+	ocfs2_update_inode_fsync_trans(handle, inode, 0);
 	ocfs2_journal_dirty(handle, fe_bh);
 
 	inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir));
diff --git a/fs/ocfs2/ocfs2_fs.h b/fs/ocfs2/ocfs2_fs.h
index 7aebdbf5cc0a5..c93689b568fe0 100644
--- a/fs/ocfs2/ocfs2_fs.h
+++ b/fs/ocfs2/ocfs2_fs.h
@@ -883,7 +883,8 @@ struct ocfs2_group_desc
 	__le16	bg_free_bits_count;     /* Free bits count */
 	__le16   bg_chain;               /* What chain I am in. */
 /*10*/	__le32   bg_generation;
-	__le32	bg_reserved1;
+	__le16   bg_contig_free_bits;   /* max contig free bits length */
+	__le16   bg_reserved1;
 	__le64   bg_next_group;          /* Next group in my list, in
 					   blocks */
 /*20*/	__le64   bg_parent_dinode;       /* dinode which owns me, in
diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c
index 3f80a56d0d603..1f303b1adf1ab 100644
--- a/fs/ocfs2/refcounttree.c
+++ b/fs/ocfs2/refcounttree.c
@@ -630,7 +630,7 @@ static int ocfs2_create_refcount_tree(struct inode *inode,
 	rb->rf_records.rl_count =
 			cpu_to_le16(ocfs2_refcount_recs_per_rb(osb->sb));
 	spin_lock(&osb->osb_lock);
-	rb->rf_generation = osb->s_next_generation++;
+	rb->rf_generation = cpu_to_le32(osb->s_next_generation++);
 	spin_unlock(&osb->osb_lock);
 
 	ocfs2_journal_dirty(handle, new_bh);
diff --git a/fs/ocfs2/reservations.c b/fs/ocfs2/reservations.c
index a9d1296d736dc..1fe61974d9f02 100644
--- a/fs/ocfs2/reservations.c
+++ b/fs/ocfs2/reservations.c
@@ -414,7 +414,7 @@ static int ocfs2_resmap_find_free_bits(struct ocfs2_reservation_map *resmap,
 
 	start = search_start;
 	while ((offset = ocfs2_find_next_zero_bit(bitmap, resmap->m_bitmap_len,
-						 start)) != -1) {
+					start)) < resmap->m_bitmap_len) {
 		/* Search reached end of the region */
 		if (offset >= (search_start + search_len))
 			break;
diff --git a/fs/ocfs2/resize.c b/fs/ocfs2/resize.c
index d65d43c61857a..c4a4016d3866a 100644
--- a/fs/ocfs2/resize.c
+++ b/fs/ocfs2/resize.c
@@ -91,6 +91,8 @@ static int ocfs2_update_last_group_and_inode(handle_t *handle,
 	u16 cl_bpc = le16_to_cpu(cl->cl_bpc);
 	u16 cl_cpg = le16_to_cpu(cl->cl_cpg);
 	u16 old_bg_clusters;
+	u16 contig_bits;
+	__le16 old_bg_contig_free_bits;
 
 	trace_ocfs2_update_last_group_and_inode(new_clusters,
 						first_new_cluster);
@@ -122,6 +124,11 @@ static int ocfs2_update_last_group_and_inode(handle_t *handle,
 		le16_add_cpu(&group->bg_free_bits_count, -1 * backups);
 	}
 
+	contig_bits = ocfs2_find_max_contig_free_bits(group->bg_bitmap,
+					le16_to_cpu(group->bg_bits), 0);
+	old_bg_contig_free_bits = group->bg_contig_free_bits;
+	group->bg_contig_free_bits = cpu_to_le16(contig_bits);
+
 	ocfs2_journal_dirty(handle, group_bh);
 
 	/* update the inode accordingly. */
@@ -160,6 +167,7 @@ out_rollback:
 		le16_add_cpu(&group->bg_free_bits_count, backups);
 		le16_add_cpu(&group->bg_bits, -1 * num_bits);
 		le16_add_cpu(&group->bg_free_bits_count, -1 * num_bits);
+		group->bg_contig_free_bits = old_bg_contig_free_bits;
 	}
 out:
 	if (ret)
diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c
index 166c8918c825a..f7b483f0de2ad 100644
--- a/fs/ocfs2/suballoc.c
+++ b/fs/ocfs2/suballoc.c
@@ -50,6 +50,10 @@ struct ocfs2_suballoc_result {
 	u64		sr_blkno;	/* The first allocated block */
 	unsigned int	sr_bit_offset;	/* The bit in the bg */
 	unsigned int	sr_bits;	/* How many bits we claimed */
+	unsigned int	sr_max_contig_bits; /* The length for contiguous
+					     * free bits, only available
+					     * for cluster group
+					     */
 };
 
 static u64 ocfs2_group_from_res(struct ocfs2_suballoc_result *res)
@@ -1272,6 +1276,26 @@ static int ocfs2_test_bg_bit_allocatable(struct buffer_head *bg_bh,
 	return ret;
 }
 
+u16 ocfs2_find_max_contig_free_bits(void *bitmap,
+			 u16 total_bits, u16 start)
+{
+	u16 offset, free_bits;
+	u16 contig_bits = 0;
+
+	while (start < total_bits) {
+		offset = ocfs2_find_next_zero_bit(bitmap, total_bits, start);
+		if (offset == total_bits)
+			break;
+
+		start = ocfs2_find_next_bit(bitmap, total_bits, offset);
+		free_bits = start - offset;
+		if (contig_bits < free_bits)
+			contig_bits = free_bits;
+	}
+
+	return contig_bits;
+}
+
 static int ocfs2_block_group_find_clear_bits(struct ocfs2_super *osb,
 					     struct buffer_head *bg_bh,
 					     unsigned int bits_wanted,
@@ -1280,6 +1304,7 @@ static int ocfs2_block_group_find_clear_bits(struct ocfs2_super *osb,
 {
 	void *bitmap;
 	u16 best_offset, best_size;
+	u16 prev_best_size = 0;
 	int offset, start, found, status = 0;
 	struct ocfs2_group_desc *bg = (struct ocfs2_group_desc *) bg_bh->b_data;
 
@@ -1290,10 +1315,8 @@ static int ocfs2_block_group_find_clear_bits(struct ocfs2_super *osb,
 	found = start = best_offset = best_size = 0;
 	bitmap = bg->bg_bitmap;
 
-	while((offset = ocfs2_find_next_zero_bit(bitmap, total_bits, start)) != -1) {
-		if (offset == total_bits)
-			break;
-
+	while ((offset = ocfs2_find_next_zero_bit(bitmap, total_bits, start)) <
+	       total_bits) {
 		if (!ocfs2_test_bg_bit_allocatable(bg_bh, offset)) {
 			/* We found a zero, but we can't use it as it
 			 * hasn't been put to disk yet! */
@@ -1308,6 +1331,7 @@ static int ocfs2_block_group_find_clear_bits(struct ocfs2_super *osb,
 			/* got a zero after some ones */
 			found = 1;
 			start = offset + 1;
+			prev_best_size = best_size;
 		}
 		if (found > best_size) {
 			best_size = found;
@@ -1320,6 +1344,8 @@ static int ocfs2_block_group_find_clear_bits(struct ocfs2_super *osb,
 		}
 	}
 
+	/* best_size will be allocated, we save prev_best_size */
+	res->sr_max_contig_bits = prev_best_size;
 	if (best_size) {
 		res->sr_bit_offset = best_offset;
 		res->sr_bits = best_size;
@@ -1337,11 +1363,16 @@ int ocfs2_block_group_set_bits(handle_t *handle,
 					     struct ocfs2_group_desc *bg,
 					     struct buffer_head *group_bh,
 					     unsigned int bit_off,
-					     unsigned int num_bits)
+					     unsigned int num_bits,
+					     unsigned int max_contig_bits,
+					     int fastpath)
 {
 	int status;
 	void *bitmap = bg->bg_bitmap;
 	int journal_type = OCFS2_JOURNAL_ACCESS_WRITE;
+	unsigned int start = bit_off + num_bits;
+	u16 contig_bits;
+	struct ocfs2_super *osb = OCFS2_SB(alloc_inode->i_sb);
 
 	/* All callers get the descriptor via
 	 * ocfs2_read_group_descriptor().  Any corruption is a code bug. */
@@ -1373,6 +1404,29 @@ int ocfs2_block_group_set_bits(handle_t *handle,
 	while(num_bits--)
 		ocfs2_set_bit(bit_off++, bitmap);
 
+	/*
+	 * this is optimize path, caller set old contig value
+	 * in max_contig_bits to bypass finding action.
+	 */
+	if (fastpath) {
+		bg->bg_contig_free_bits = cpu_to_le16(max_contig_bits);
+	} else if (ocfs2_is_cluster_bitmap(alloc_inode)) {
+		/*
+		 * Usually, the block group bitmap allocates only 1 bit
+		 * at a time, while the cluster group allocates n bits
+		 * each time. Therefore, we only save the contig bits for
+		 * the cluster group.
+		 */
+		contig_bits = ocfs2_find_max_contig_free_bits(bitmap,
+				    le16_to_cpu(bg->bg_bits), start);
+		if (contig_bits > max_contig_bits)
+			max_contig_bits = contig_bits;
+		bg->bg_contig_free_bits = cpu_to_le16(max_contig_bits);
+		ocfs2_local_alloc_seen_free_bits(osb, max_contig_bits);
+	} else {
+		bg->bg_contig_free_bits = 0;
+	}
+
 	ocfs2_journal_dirty(handle, group_bh);
 
 bail:
@@ -1486,7 +1540,12 @@ static int ocfs2_cluster_group_search(struct inode *inode,
 
 	BUG_ON(!ocfs2_is_cluster_bitmap(inode));
 
-	if (gd->bg_free_bits_count) {
+	if (le16_to_cpu(gd->bg_contig_free_bits) &&
+	    le16_to_cpu(gd->bg_contig_free_bits) < bits_wanted)
+		return -ENOSPC;
+
+	/* ->bg_contig_free_bits may un-initialized, so compare again */
+	if (le16_to_cpu(gd->bg_free_bits_count) >= bits_wanted) {
 		max_bits = le16_to_cpu(gd->bg_bits);
 
 		/* Tail groups in cluster bitmaps which aren't cpg
@@ -1530,13 +1589,6 @@ static int ocfs2_cluster_group_search(struct inode *inode,
 		 * of bits. */
 		if (min_bits <= res->sr_bits)
 			search = 0; /* success */
-		else if (res->sr_bits) {
-			/*
-			 * Don't show bits which we'll be returning
-			 * for allocation to the local alloc bitmap.
-			 */
-			ocfs2_local_alloc_seen_free_bits(osb, res->sr_bits);
-		}
 	}
 
 	return search;
@@ -1555,7 +1607,7 @@ static int ocfs2_block_group_search(struct inode *inode,
 	BUG_ON(min_bits != 1);
 	BUG_ON(ocfs2_is_cluster_bitmap(inode));
 
-	if (bg->bg_free_bits_count) {
+	if (le16_to_cpu(bg->bg_free_bits_count) >= bits_wanted) {
 		ret = ocfs2_block_group_find_clear_bits(OCFS2_SB(inode->i_sb),
 							group_bh, bits_wanted,
 							le16_to_cpu(bg->bg_bits),
@@ -1715,7 +1767,8 @@ static int ocfs2_search_one_group(struct ocfs2_alloc_context *ac,
 	}
 
 	ret = ocfs2_block_group_set_bits(handle, alloc_inode, gd, group_bh,
-					 res->sr_bit_offset, res->sr_bits);
+					 res->sr_bit_offset, res->sr_bits,
+					 res->sr_max_contig_bits, 0);
 	if (ret < 0) {
 		ocfs2_rollback_alloc_dinode_counts(alloc_inode, ac->ac_bh,
 					       res->sr_bits,
@@ -1849,7 +1902,9 @@ static int ocfs2_search_chain(struct ocfs2_alloc_context *ac,
 					    bg,
 					    group_bh,
 					    res->sr_bit_offset,
-					    res->sr_bits);
+					    res->sr_bits,
+					    res->sr_max_contig_bits,
+					    0);
 	if (status < 0) {
 		ocfs2_rollback_alloc_dinode_counts(alloc_inode,
 					ac->ac_bh, res->sr_bits, chain);
@@ -1951,7 +2006,7 @@ static int ocfs2_claim_suballoc_bits(struct ocfs2_alloc_context *ac,
 	for (i = 0; i < le16_to_cpu(cl->cl_next_free_rec); i ++) {
 		if (i == victim)
 			continue;
-		if (!cl->cl_recs[i].c_free)
+		if (le32_to_cpu(cl->cl_recs[i].c_free) < bits_wanted)
 			continue;
 
 		ac->ac_chain = i;
@@ -2163,7 +2218,9 @@ int ocfs2_claim_new_inode_at_loc(handle_t *handle,
 					 bg,
 					 bg_bh,
 					 res->sr_bit_offset,
-					 res->sr_bits);
+					 res->sr_bits,
+					 res->sr_max_contig_bits,
+					 0);
 	if (ret < 0) {
 		ocfs2_rollback_alloc_dinode_counts(ac->ac_inode,
 					       ac->ac_bh, res->sr_bits, chain);
@@ -2382,11 +2439,13 @@ static int ocfs2_block_group_clear_bits(handle_t *handle,
 					struct buffer_head *group_bh,
 					unsigned int bit_off,
 					unsigned int num_bits,
+					unsigned int max_contig_bits,
 					void (*undo_fn)(unsigned int bit,
 							unsigned long *bmap))
 {
 	int status;
 	unsigned int tmp;
+	u16 contig_bits;
 	struct ocfs2_group_desc *undo_bg = NULL;
 	struct journal_head *jh;
 
@@ -2433,6 +2492,20 @@ static int ocfs2_block_group_clear_bits(handle_t *handle,
 				   num_bits);
 	}
 
+	/*
+	 * TODO: even 'num_bits == 1' (the worst case, release 1 cluster),
+	 * we still need to rescan whole bitmap.
+	 */
+	if (ocfs2_is_cluster_bitmap(alloc_inode)) {
+		contig_bits = ocfs2_find_max_contig_free_bits(bg->bg_bitmap,
+				    le16_to_cpu(bg->bg_bits), 0);
+		if (contig_bits > max_contig_bits)
+			max_contig_bits = contig_bits;
+		bg->bg_contig_free_bits = cpu_to_le16(max_contig_bits);
+	} else {
+		bg->bg_contig_free_bits = 0;
+	}
+
 	if (undo_fn)
 		spin_unlock(&jh->b_state_lock);
 
@@ -2459,6 +2532,7 @@ static int _ocfs2_free_suballoc_bits(handle_t *handle,
 	struct ocfs2_chain_list *cl = &fe->id2.i_chain;
 	struct buffer_head *group_bh = NULL;
 	struct ocfs2_group_desc *group;
+	__le16 old_bg_contig_free_bits = 0;
 
 	/* The alloc_bh comes from ocfs2_free_dinode() or
 	 * ocfs2_free_clusters().  The callers have all locked the
@@ -2483,9 +2557,11 @@ static int _ocfs2_free_suballoc_bits(handle_t *handle,
 
 	BUG_ON((count + start_bit) > le16_to_cpu(group->bg_bits));
 
+	if (ocfs2_is_cluster_bitmap(alloc_inode))
+		old_bg_contig_free_bits = group->bg_contig_free_bits;
 	status = ocfs2_block_group_clear_bits(handle, alloc_inode,
 					      group, group_bh,
-					      start_bit, count, undo_fn);
+					      start_bit, count, 0, undo_fn);
 	if (status < 0) {
 		mlog_errno(status);
 		goto bail;
@@ -2496,7 +2572,8 @@ static int _ocfs2_free_suballoc_bits(handle_t *handle,
 	if (status < 0) {
 		mlog_errno(status);
 		ocfs2_block_group_set_bits(handle, alloc_inode, group, group_bh,
-				start_bit, count);
+				start_bit, count,
+				le16_to_cpu(old_bg_contig_free_bits), 1);
 		goto bail;
 	}
 
diff --git a/fs/ocfs2/suballoc.h b/fs/ocfs2/suballoc.h
index 9c74eace3adc1..b481b834857d3 100644
--- a/fs/ocfs2/suballoc.h
+++ b/fs/ocfs2/suballoc.h
@@ -79,12 +79,16 @@ void ocfs2_rollback_alloc_dinode_counts(struct inode *inode,
 			 struct buffer_head *di_bh,
 			 u32 num_bits,
 			 u16 chain);
+u16 ocfs2_find_max_contig_free_bits(void *bitmap,
+			 u16 total_bits, u16 start);
 int ocfs2_block_group_set_bits(handle_t *handle,
 			 struct inode *alloc_inode,
 			 struct ocfs2_group_desc *bg,
 			 struct buffer_head *group_bh,
 			 unsigned int bit_off,
-			 unsigned int num_bits);
+			 unsigned int num_bits,
+			 unsigned int max_contig_bits,
+			 int fastpath);
 
 int ocfs2_claim_metadata(handle_t *handle,
 			 struct ocfs2_alloc_context *ac,
diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
index 1fb213f379a5b..b52d85f8ad592 100644
--- a/fs/proc/vmcore.c
+++ b/fs/proc/vmcore.c
@@ -383,6 +383,8 @@ static ssize_t __read_vmcore(struct iov_iter *iter, loff_t *fpos)
 		/* leave now if filled buffer already */
 		if (!iov_iter_count(iter))
 			return acc;
+
+		cond_resched();
 	}
 
 	list_for_each_entry(m, &vmcore_list, list) {
@@ -1370,9 +1372,8 @@ static void vmcoredd_write_header(void *buf, struct vmcoredd_data *data,
 	vdd_hdr->n_descsz = size + sizeof(vdd_hdr->dump_name);
 	vdd_hdr->n_type = NT_VMCOREDD;
 
-	strncpy((char *)vdd_hdr->name, VMCOREDD_NOTE_NAME,
-		sizeof(vdd_hdr->name));
-	memcpy(vdd_hdr->dump_name, data->dump_name, sizeof(vdd_hdr->dump_name));
+	strscpy_pad(vdd_hdr->name, VMCOREDD_NOTE_NAME);
+	strscpy_pad(vdd_hdr->dump_name, data->dump_name);
 }
 
 /**
diff --git a/fs/squashfs/file.c b/fs/squashfs/file.c
index e8df6430444b0..a8c1e7f9a6092 100644
--- a/fs/squashfs/file.c
+++ b/fs/squashfs/file.c
@@ -375,8 +375,6 @@ void squashfs_fill_page(struct page *page, struct squashfs_cache_entry *buffer,
 	flush_dcache_page(page);
 	if (copied == avail)
 		SetPageUptodate(page);
-	else
-		SetPageError(page);
 }
 
 /* Copy data into page cache  */
@@ -471,7 +469,7 @@ static int squashfs_read_folio(struct file *file, struct folio *folio)
 
 		res = read_blocklist(inode, index, &block);
 		if (res < 0)
-			goto error_out;
+			goto out;
 
 		if (res == 0)
 			res = squashfs_readpage_sparse(page, expected);
@@ -483,8 +481,6 @@ static int squashfs_read_folio(struct file *file, struct folio *folio)
 	if (!res)
 		return 0;
 
-error_out:
-	SetPageError(page);
 out:
 	pageaddr = kmap_atomic(page);
 	memset(pageaddr, 0, PAGE_SIZE);
diff --git a/fs/squashfs/file_direct.c b/fs/squashfs/file_direct.c
index 763a3f7a75f6d..2a689ce71de98 100644
--- a/fs/squashfs/file_direct.c
+++ b/fs/squashfs/file_direct.c
@@ -106,14 +106,13 @@ int squashfs_readpage_block(struct page *target_page, u64 block, int bsize,
 	return 0;
 
 mark_errored:
-	/* Decompression failed, mark pages as errored.  Target_page is
+	/* Decompression failed.  Target_page is
 	 * dealt with by the caller
 	 */
 	for (i = 0; i < pages; i++) {
 		if (page[i] == NULL || page[i] == target_page)
 			continue;
 		flush_dcache_page(page[i]);
-		SetPageError(page[i]);
 		unlock_page(page[i]);
 		put_page(page[i]);
 	}
diff --git a/fs/squashfs/namei.c b/fs/squashfs/namei.c
index 11e4539b9eae4..65aae7e2a859d 100644
--- a/fs/squashfs/namei.c
+++ b/fs/squashfs/namei.c
@@ -62,27 +62,21 @@
  */
 static int get_dir_index_using_name(struct super_block *sb,
 			u64 *next_block, int *next_offset, u64 index_start,
-			int index_offset, int i_count, const char *name,
-			int len)
+			int index_offset, int i_count, const char *name)
 {
 	struct squashfs_sb_info *msblk = sb->s_fs_info;
 	int i, length = 0, err;
 	unsigned int size;
 	struct squashfs_dir_index *index;
-	char *str;
 
 	TRACE("Entered get_dir_index_using_name, i_count %d\n", i_count);
 
-	index = kmalloc(sizeof(*index) + SQUASHFS_NAME_LEN * 2 + 2, GFP_KERNEL);
+	index = kmalloc(sizeof(*index) + SQUASHFS_NAME_LEN + 1, GFP_KERNEL);
 	if (index == NULL) {
 		ERROR("Failed to allocate squashfs_dir_index\n");
 		goto out;
 	}
 
-	str = &index->name[SQUASHFS_NAME_LEN + 1];
-	strncpy(str, name, len);
-	str[len] = '\0';
-
 	for (i = 0; i < i_count; i++) {
 		err = squashfs_read_metadata(sb, index, &index_start,
 					&index_offset, sizeof(*index));
@@ -101,7 +95,7 @@ static int get_dir_index_using_name(struct super_block *sb,
 
 		index->name[size] = '\0';
 
-		if (strcmp(index->name, str) > 0)
+		if (strcmp(index->name, name) > 0)
 			break;
 
 		length = le32_to_cpu(index->index);
@@ -153,7 +147,7 @@ static struct dentry *squashfs_lookup(struct inode *dir, struct dentry *dentry,
 	length = get_dir_index_using_name(dir->i_sb, &block, &offset,
 				squashfs_i(dir)->dir_idx_start,
 				squashfs_i(dir)->dir_idx_offset,
-				squashfs_i(dir)->dir_idx_cnt, name, len);
+				squashfs_i(dir)->dir_idx_cnt, name);
 
 	while (length < i_size_read(dir)) {
 		/*
diff --git a/fs/squashfs/symlink.c b/fs/squashfs/symlink.c
index 2bf977a52c2c3..6ef735bd841a1 100644
--- a/fs/squashfs/symlink.c
+++ b/fs/squashfs/symlink.c
@@ -32,20 +32,19 @@
 
 static int squashfs_symlink_read_folio(struct file *file, struct folio *folio)
 {
-	struct page *page = &folio->page;
-	struct inode *inode = page->mapping->host;
+	struct inode *inode = folio->mapping->host;
 	struct super_block *sb = inode->i_sb;
 	struct squashfs_sb_info *msblk = sb->s_fs_info;
-	int index = page->index << PAGE_SHIFT;
+	int index = folio_pos(folio);
 	u64 block = squashfs_i(inode)->start;
 	int offset = squashfs_i(inode)->offset;
 	int length = min_t(int, i_size_read(inode) - index, PAGE_SIZE);
-	int bytes, copied;
+	int bytes, copied, error;
 	void *pageaddr;
 	struct squashfs_cache_entry *entry;
 
 	TRACE("Entered squashfs_symlink_readpage, page index %ld, start block "
-			"%llx, offset %x\n", page->index, block, offset);
+			"%llx, offset %x\n", folio->index, block, offset);
 
 	/*
 	 * Skip index bytes into symlink metadata.
@@ -57,14 +56,15 @@ static int squashfs_symlink_read_folio(struct file *file, struct folio *folio)
 			ERROR("Unable to read symlink [%llx:%x]\n",
 				squashfs_i(inode)->start,
 				squashfs_i(inode)->offset);
-			goto error_out;
+			error = bytes;
+			goto out;
 		}
 	}
 
 	/*
 	 * Read length bytes from symlink metadata.  Squashfs_read_metadata
 	 * is not used here because it can sleep and we want to use
-	 * kmap_atomic to map the page.  Instead call the underlying
+	 * kmap_local to map the folio.  Instead call the underlying
 	 * squashfs_cache_get routine.  As length bytes may overlap metadata
 	 * blocks, we may need to call squashfs_cache_get multiple times.
 	 */
@@ -75,29 +75,26 @@ static int squashfs_symlink_read_folio(struct file *file, struct folio *folio)
 				squashfs_i(inode)->start,
 				squashfs_i(inode)->offset);
 			squashfs_cache_put(entry);
-			goto error_out;
+			error = entry->error;
+			goto out;
 		}
 
-		pageaddr = kmap_atomic(page);
+		pageaddr = kmap_local_folio(folio, 0);
 		copied = squashfs_copy_data(pageaddr + bytes, entry, offset,
 								length - bytes);
 		if (copied == length - bytes)
 			memset(pageaddr + length, 0, PAGE_SIZE - length);
 		else
 			block = entry->next_index;
-		kunmap_atomic(pageaddr);
+		kunmap_local(pageaddr);
 		squashfs_cache_put(entry);
 	}
 
-	flush_dcache_page(page);
-	SetPageUptodate(page);
-	unlock_page(page);
-	return 0;
-
-error_out:
-	SetPageError(page);
-	unlock_page(page);
-	return 0;
+	flush_dcache_folio(folio);
+	error = 0;
+out:
+	folio_end_read(folio, error == 0);
+	return error;
 }
 
 
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index e8c412ee6400d..7600e877908fb 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -1057,11 +1057,6 @@ void init_cpu_present(const struct cpumask *src);
 void init_cpu_possible(const struct cpumask *src);
 void init_cpu_online(const struct cpumask *src);
 
-static inline void reset_cpu_possible_mask(void)
-{
-	bitmap_zero(cpumask_bits(&__cpu_possible_mask), NR_CPUS);
-}
-
 static inline void
 set_cpu_possible(unsigned int cpu, bool possible)
 {
diff --git a/include/linux/instrumented.h b/include/linux/instrumented.h
index 1b608e00290aa..711a1f0d1a735 100644
--- a/include/linux/instrumented.h
+++ b/include/linux/instrumented.h
@@ -148,6 +148,41 @@ instrument_copy_from_user_after(const void *to, const void __user *from,
 }
 
 /**
+ * instrument_memcpy_before - add instrumentation before non-instrumented memcpy
+ * @to: destination address
+ * @from: source address
+ * @n: number of bytes to copy
+ *
+ * Instrument memory accesses that happen in custom memcpy implementations. The
+ * instrumentation should be inserted before the memcpy call.
+ */
+static __always_inline void instrument_memcpy_before(void *to, const void *from,
+						     unsigned long n)
+{
+	kasan_check_write(to, n);
+	kasan_check_read(from, n);
+	kcsan_check_write(to, n);
+	kcsan_check_read(from, n);
+}
+
+/**
+ * instrument_memcpy_after - add instrumentation after non-instrumented memcpy
+ * @to: destination address
+ * @from: source address
+ * @n: number of bytes to copy
+ * @left: number of bytes not copied (if known)
+ *
+ * Instrument memory accesses that happen in custom memcpy implementations. The
+ * instrumentation should be inserted after the memcpy call.
+ */
+static __always_inline void instrument_memcpy_after(void *to, const void *from,
+						    unsigned long n,
+						    unsigned long left)
+{
+	kmsan_memmove(to, from, n - left);
+}
+
+/**
  * instrument_get_user() - add instrumentation to get_user()-like macros
  * @to: destination variable, may not be address-taken
  *
diff --git a/include/linux/kexec.h b/include/linux/kexec.h
index 5b93a5767413a..f0e9f8eda7a3c 100644
--- a/include/linux/kexec.h
+++ b/include/linux/kexec.h
@@ -464,10 +464,8 @@ static inline void arch_kexec_pre_free_pages(void *vaddr, unsigned int pages) {
 
 extern bool kexec_file_dbg_print;
 
-#define kexec_dprintk(fmt, ...)					\
-	printk("%s" fmt,					\
-	       kexec_file_dbg_print ? KERN_INFO : KERN_DEBUG,	\
-	       ##__VA_ARGS__)
+#define kexec_dprintk(fmt, arg...) \
+        do { if (kexec_file_dbg_print) pr_info(fmt, ##arg); } while (0)
 
 #else /* !CONFIG_KEXEC_CORE */
 struct pt_regs;
diff --git a/include/linux/kfifo.h b/include/linux/kfifo.h
index 0b35a41440ff1..6b28d642f3325 100644
--- a/include/linux/kfifo.h
+++ b/include/linux/kfifo.h
@@ -36,10 +36,15 @@
  * to lock the reader.
  */
 
-#include <linux/kernel.h>
+#include <linux/array_size.h>
 #include <linux/spinlock.h>
 #include <linux/stddef.h>
-#include <linux/scatterlist.h>
+#include <linux/types.h>
+
+#include <asm/barrier.h>
+#include <asm/errno.h>
+
+struct scatterlist;
 
 struct __kfifo {
 	unsigned int	in;
diff --git a/include/linux/kmsan-checks.h b/include/linux/kmsan-checks.h
index c4cae333deec5..e1082dc40abc2 100644
--- a/include/linux/kmsan-checks.h
+++ b/include/linux/kmsan-checks.h
@@ -61,6 +61,17 @@ void kmsan_check_memory(const void *address, size_t size);
 void kmsan_copy_to_user(void __user *to, const void *from, size_t to_copy,
 			size_t left);
 
+/**
+ * kmsan_memmove() - Notify KMSAN about a data copy within kernel.
+ * @to:   destination address in the kernel.
+ * @from: source address in the kernel.
+ * @size: number of bytes to copy.
+ *
+ * Invoked after non-instrumented version (e.g. implemented using assembly
+ * code) of memmove()/memcpy() is called, in order to copy KMSAN's metadata.
+ */
+void kmsan_memmove(void *to, const void *from, size_t to_copy);
+
 #else
 
 static inline void kmsan_poison_memory(const void *address, size_t size,
@@ -78,6 +89,10 @@ static inline void kmsan_copy_to_user(void __user *to, const void *from,
 {
 }
 
+static inline void kmsan_memmove(void *to, const void *from, size_t to_copy)
+{
+}
+
 #endif
 
 #endif /* _LINUX_KMSAN_CHECKS_H */
diff --git a/include/linux/nmi.h b/include/linux/nmi.h
index f53438eae815d..a8dfb38c9bb6f 100644
--- a/include/linux/nmi.h
+++ b/include/linux/nmi.h
@@ -105,10 +105,12 @@ void watchdog_hardlockup_check(unsigned int cpu, struct pt_regs *regs);
 extern void hardlockup_detector_perf_stop(void);
 extern void hardlockup_detector_perf_restart(void);
 extern void hardlockup_detector_perf_cleanup(void);
+extern void hardlockup_config_perf_event(const char *str);
 #else
 static inline void hardlockup_detector_perf_stop(void) { }
 static inline void hardlockup_detector_perf_restart(void) { }
 static inline void hardlockup_detector_perf_cleanup(void) { }
+static inline void hardlockup_config_perf_event(const char *str) { }
 #endif
 
 void watchdog_hardlockup_stop(void);
diff --git a/include/trace/events/nilfs2.h b/include/trace/events/nilfs2.h
index 8efc6236f57c3..8880c11733dd3 100644
--- a/include/trace/events/nilfs2.h
+++ b/include/trace/events/nilfs2.h
@@ -200,7 +200,11 @@ TRACE_EVENT(nilfs2_mdt_submit_block,
 		    __field(struct inode *, inode)
 		    __field(unsigned long, ino)
 		    __field(unsigned long, blkoff)
-		    __field(enum req_op, mode)
+		    /*
+		     * Use field_struct() to avoid is_signed_type() on the
+		     * bitwise type enum req_op.
+		     */
+		    __field_struct(enum req_op, mode)
 	    ),
 
 	    TP_fast_assign(
diff --git a/init/do_mounts_initrd.c b/init/do_mounts_initrd.c
index 425f4bcf4b77e..22c7f41ff6422 100644
--- a/init/do_mounts_initrd.c
+++ b/init/do_mounts_initrd.c
@@ -29,7 +29,6 @@ static struct ctl_table kern_do_mounts_initrd_table[] = {
 		.mode           = 0644,
 		.proc_handler   = proc_dointvec,
 	},
-	{ }
 };
 
 static __init int kernel_do_mounts_initrd_sysctls_init(void)
diff --git a/init/main.c b/init/main.c
index 91e74827f8589..206acdde51f5a 100644
--- a/init/main.c
+++ b/init/main.c
@@ -345,6 +345,11 @@ static int __init xbc_snprint_cmdline(char *buf, size_t size,
 			continue;
 		}
 		xbc_array_for_each_value(vnode, val) {
+			/*
+			 * For prettier and more readable /proc/cmdline, only
+			 * quote the value when necessary, i.e. when it contains
+			 * whitespace.
+			 */
 			q = strpbrk(val, " \t\r\n") ? "\"" : "";
 			ret = snprintf(buf, rest(buf, end), "%s=%s%s%s ",
 				       xbc_namebuf, q, val, q);
@@ -881,6 +886,19 @@ static void __init print_unknown_bootoptions(void)
 	memblock_free(unknown_options, len);
 }
 
+static void __init early_numa_node_init(void)
+{
+#ifdef CONFIG_USE_PERCPU_NUMA_NODE_ID
+#ifndef cpu_to_node
+	int cpu;
+
+	/* The early_cpu_to_node() should be ready here. */
+	for_each_possible_cpu(cpu)
+		set_cpu_numa_node(cpu, early_cpu_to_node(cpu));
+#endif
+#endif
+}
+
 asmlinkage __visible __init __no_sanitize_address __noreturn __no_stack_protector
 void start_kernel(void)
 {
@@ -911,6 +929,7 @@ void start_kernel(void)
 	setup_nr_cpu_ids();
 	setup_per_cpu_areas();
 	smp_prepare_boot_cpu();	/* arch-specific boot-cpu hooks */
+	early_numa_node_init();
 	boot_cpu_hotplug_init();
 
 	pr_notice("Kernel command line: %s\n", saved_command_line);
diff --git a/ipc/ipc_sysctl.c b/ipc/ipc_sysctl.c
index 113452038303b..9465b0ae470ba 100644
--- a/ipc/ipc_sysctl.c
+++ b/ipc/ipc_sysctl.c
@@ -178,7 +178,6 @@ static struct ctl_table ipc_sysctls[] = {
 		.extra2		= SYSCTL_INT_MAX,
 	},
 #endif
-	{}
 };
 
 static struct ctl_table_set *set_lookup(struct ctl_table_root *root)
diff --git a/ipc/mq_sysctl.c b/ipc/mq_sysctl.c
index 068e7d5aa42b8..b70dc2ff22d84 100644
--- a/ipc/mq_sysctl.c
+++ b/ipc/mq_sysctl.c
@@ -64,7 +64,6 @@ static struct ctl_table mq_sysctls[] = {
 		.extra1		= &msg_maxsize_limit_min,
 		.extra2		= &msg_maxsize_limit_max,
 	},
-	{}
 };
 
 static struct ctl_table_set *set_lookup(struct ctl_table_root *root)
diff --git a/kernel/crash_core.c b/kernel/crash_core.c
index 394db3ebe8353..63cf89393c6eb 100644
--- a/kernel/crash_core.c
+++ b/kernel/crash_core.c
@@ -4,6 +4,8 @@
  * Copyright (C) 2002-2004 Eric Biederman  <ebiederm@xmission.com>
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/buildid.h>
 #include <linux/init.h>
 #include <linux/utsname.h>
diff --git a/kernel/crash_reserve.c b/kernel/crash_reserve.c
index 066668799f757..5b2722a93a48c 100644
--- a/kernel/crash_reserve.c
+++ b/kernel/crash_reserve.c
@@ -109,7 +109,7 @@ static int __init parse_crashkernel_mem(char *cmdline,
 
 		size = memparse(cur, &tmp);
 		if (cur == tmp) {
-			pr_warn("Memory value expected\n");
+			pr_warn("crashkernel: Memory value expected\n");
 			return -EINVAL;
 		}
 		cur = tmp;
@@ -132,7 +132,7 @@ static int __init parse_crashkernel_mem(char *cmdline,
 			cur++;
 			*crash_base = memparse(cur, &tmp);
 			if (cur == tmp) {
-				pr_warn("Memory value expected after '@'\n");
+				pr_warn("crahskernel: Memory value expected after '@'\n");
 				return -EINVAL;
 			}
 		}
diff --git a/kernel/kcov.c b/kernel/kcov.c
index f9ac2e9e460fc..c3124f6d5536b 100644
--- a/kernel/kcov.c
+++ b/kernel/kcov.c
@@ -627,7 +627,8 @@ static int kcov_ioctl_locked(struct kcov *kcov, unsigned int cmd,
 		mode = kcov_get_mode(remote_arg->trace_mode);
 		if (mode < 0)
 			return mode;
-		if (remote_arg->area_size > LONG_MAX / sizeof(unsigned long))
+		if ((unsigned long)remote_arg->area_size >
+		    LONG_MAX / sizeof(unsigned long))
 			return -EINVAL;
 		kcov->mode = mode;
 		t->kcov = kcov;
diff --git a/kernel/regset.c b/kernel/regset.c
index 586823786f397..b2871fa68b2a7 100644
--- a/kernel/regset.c
+++ b/kernel/regset.c
@@ -16,14 +16,14 @@ static int __regset_get(struct task_struct *target,
 	if (size > regset->n * regset->size)
 		size = regset->n * regset->size;
 	if (!p) {
-		to_free = p = kzalloc(size, GFP_KERNEL);
+		to_free = p = kvzalloc(size, GFP_KERNEL);
 		if (!p)
 			return -ENOMEM;
 	}
 	res = regset->regset_get(target, regset,
 			   (struct membuf){.p = p, .left = size});
 	if (res < 0) {
-		kfree(to_free);
+		kvfree(to_free);
 		return res;
 	}
 	*data = p;
@@ -71,6 +71,6 @@ int copy_regset_to_user(struct task_struct *target,
 	ret = regset_get_alloc(target, regset, size, &buf);
 	if (ret > 0)
 		ret = copy_to_user(data, buf, ret) ? -EFAULT : 0;
-	kfree(buf);
+	kvfree(buf);
 	return ret;
 }
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index d5d94510afd3f..8fd292d34d898 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -524,8 +524,7 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 	if (!buts->buf_size || !buts->buf_nr)
 		return -EINVAL;
 
-	strncpy(buts->name, name, BLKTRACE_BDEV_SIZE);
-	buts->name[BLKTRACE_BDEV_SIZE - 1] = '\0';
+	strscpy_pad(buts->name, name, BLKTRACE_BDEV_SIZE);
 
 	/*
 	 * some device names have larger paths - convert the slashes
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 941236828de80..51915b44ac73c 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -78,6 +78,7 @@ void __init hardlockup_detector_disable(void)
 
 static int __init hardlockup_panic_setup(char *str)
 {
+next:
 	if (!strncmp(str, "panic", 5))
 		hardlockup_panic = 1;
 	else if (!strncmp(str, "nopanic", 7))
@@ -86,6 +87,14 @@ static int __init hardlockup_panic_setup(char *str)
 		watchdog_hardlockup_user_enabled = 0;
 	else if (!strncmp(str, "1", 1))
 		watchdog_hardlockup_user_enabled = 1;
+	else if (!strncmp(str, "r", 1))
+		hardlockup_config_perf_event(str + 1);
+	while (*(str++)) {
+		if (*str == ',') {
+			str++;
+			goto next;
+		}
+	}
 	return 1;
 }
 __setup("nmi_watchdog=", hardlockup_panic_setup);
diff --git a/kernel/watchdog_perf.c b/kernel/watchdog_perf.c
index 8ea00c4a24b2d..d577c4a8321ee 100644
--- a/kernel/watchdog_perf.c
+++ b/kernel/watchdog_perf.c
@@ -90,6 +90,14 @@ static struct perf_event_attr wd_hw_attr = {
 	.disabled	= 1,
 };
 
+static struct perf_event_attr fallback_wd_hw_attr = {
+	.type		= PERF_TYPE_HARDWARE,
+	.config		= PERF_COUNT_HW_CPU_CYCLES,
+	.size		= sizeof(struct perf_event_attr),
+	.pinned		= 1,
+	.disabled	= 1,
+};
+
 /* Callback function for perf event subsystem */
 static void watchdog_overflow_callback(struct perf_event *event,
 				       struct perf_sample_data *data,
@@ -123,6 +131,13 @@ static int hardlockup_detector_event_create(void)
 	evt = perf_event_create_kernel_counter(wd_attr, cpu, NULL,
 					       watchdog_overflow_callback, NULL);
 	if (IS_ERR(evt)) {
+		wd_attr = &fallback_wd_hw_attr;
+		wd_attr->sample_period = hw_nmi_get_sample_period(watchdog_thresh);
+		evt = perf_event_create_kernel_counter(wd_attr, cpu, NULL,
+						       watchdog_overflow_callback, NULL);
+	}
+
+	if (IS_ERR(evt)) {
 		pr_debug("Perf event create on CPU %d failed with %ld\n", cpu,
 			 PTR_ERR(evt));
 		return PTR_ERR(evt);
@@ -133,7 +148,6 @@ static int hardlockup_detector_event_create(void)
 
 /**
  * watchdog_hardlockup_enable - Enable the local event
- *
  * @cpu: The CPU to enable hard lockup on.
  */
 void watchdog_hardlockup_enable(unsigned int cpu)
@@ -152,7 +166,6 @@ void watchdog_hardlockup_enable(unsigned int cpu)
 
 /**
  * watchdog_hardlockup_disable - Disable the local event
- *
  * @cpu: The CPU to enable hard lockup on.
  */
 void watchdog_hardlockup_disable(unsigned int cpu)
@@ -259,3 +272,33 @@ int __init watchdog_hardlockup_probe(void)
 	}
 	return ret;
 }
+
+/**
+ * hardlockup_config_perf_event - Overwrite config of wd_hw_attr.
+ * @str: number which identifies the raw perf event to use
+ */
+void __init hardlockup_config_perf_event(const char *str)
+{
+	u64 config;
+	char buf[24];
+	char *comma = strchr(str, ',');
+
+	if (!comma) {
+		if (kstrtoull(str, 16, &config))
+			return;
+	} else {
+		unsigned int len = comma - str;
+
+		if (len >= sizeof(buf))
+			return;
+
+		if (strscpy(buf, str, sizeof(buf)) < 0)
+			return;
+		buf[len] = 0;
+		if (kstrtoull(buf, 16, &config))
+			return;
+	}
+
+	wd_hw_attr.type = PERF_TYPE_RAW;
+	wd_hw_attr.config = config;
+}
diff --git a/lib/Kconfig.kgdb b/lib/Kconfig.kgdb
index b5c0e6576749d..537e1b3f57340 100644
--- a/lib/Kconfig.kgdb
+++ b/lib/Kconfig.kgdb
@@ -122,6 +122,7 @@ config KDB_DEFAULT_ENABLE
 config KDB_KEYBOARD
 	bool "KGDB_KDB: keyboard as input device"
 	depends on VT && KGDB_KDB && !PARISC
+	depends on HAS_IOPORT
 	default n
 	help
 	  KDB can use a PS/2 type keyboard for an input device
diff --git a/lib/build_OID_registry b/lib/build_OID_registry
index d7fc32ea8ac22..56d8bafeb848b 100755
--- a/lib/build_OID_registry
+++ b/lib/build_OID_registry
@@ -8,6 +8,7 @@
 #
 
 use strict;
+use Cwd qw(abs_path);
 
 my @names = ();
 my @oids = ();
@@ -17,6 +18,8 @@ if ($#ARGV != 1) {
     exit(2);
 }
 
+my $abs_srctree = abs_path($ENV{'srctree'});
+
 #
 # Open the file to read from
 #
@@ -35,7 +38,7 @@ close IN_FILE || die;
 #
 open C_FILE, ">$ARGV[1]" or die;
 print C_FILE "/*\n";
-print C_FILE " * Automatically generated by ", $0, ".  Do not edit\n";
+print C_FILE " * Automatically generated by ", $0 =~ s#^\Q$abs_srctree/\E##r, ".  Do not edit\n";
 print C_FILE " */\n";
 
 #
diff --git a/lib/devres.c b/lib/devres.c
index fe0c63caeb689..4fc152de6d8bb 100644
--- a/lib/devres.c
+++ b/lib/devres.c
@@ -1,10 +1,13 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <linux/bug.h>
 #include <linux/device.h>
-#include <linux/err.h>
-#include <linux/io.h>
-#include <linux/gfp.h>
+#include <linux/errno.h>
 #include <linux/export.h>
+#include <linux/gfp_types.h>
+#include <linux/io.h>
+#include <linux/ioport.h>
 #include <linux/of_address.h>
+#include <linux/types.h>
 
 enum devm_ioremap_type {
 	DEVM_IOREMAP = 0,
@@ -125,12 +128,13 @@ __devm_ioremap_resource(struct device *dev, const struct resource *res,
 	resource_size_t size;
 	void __iomem *dest_ptr;
 	char *pretty_name;
+	int ret;
 
 	BUG_ON(!dev);
 
 	if (!res || resource_type(res) != IORESOURCE_MEM) {
-		dev_err(dev, "invalid resource %pR\n", res);
-		return IOMEM_ERR_PTR(-EINVAL);
+		ret = dev_err_probe(dev, -EINVAL, "invalid resource %pR\n", res);
+		return IOMEM_ERR_PTR(ret);
 	}
 
 	if (type == DEVM_IOREMAP && res->flags & IORESOURCE_MEM_NONPOSTED)
@@ -144,20 +148,20 @@ __devm_ioremap_resource(struct device *dev, const struct resource *res,
 	else
 		pretty_name = devm_kstrdup(dev, dev_name(dev), GFP_KERNEL);
 	if (!pretty_name) {
-		dev_err(dev, "can't generate pretty name for resource %pR\n", res);
-		return IOMEM_ERR_PTR(-ENOMEM);
+		ret = dev_err_probe(dev, -ENOMEM, "can't generate pretty name for resource %pR\n", res);
+		return IOMEM_ERR_PTR(ret);
 	}
 
 	if (!devm_request_mem_region(dev, res->start, size, pretty_name)) {
-		dev_err(dev, "can't request region for resource %pR\n", res);
-		return IOMEM_ERR_PTR(-EBUSY);
+		ret = dev_err_probe(dev, -EBUSY, "can't request region for resource %pR\n", res);
+		return IOMEM_ERR_PTR(ret);
 	}
 
 	dest_ptr = __devm_ioremap(dev, res->start, size, type);
 	if (!dest_ptr) {
-		dev_err(dev, "ioremap failed for resource %pR\n", res);
 		devm_release_mem_region(dev, res->start, size);
-		dest_ptr = IOMEM_ERR_PTR(-ENOMEM);
+		ret = dev_err_probe(dev, -ENOMEM, "ioremap failed for resource %pR\n", res);
+		return IOMEM_ERR_PTR(ret);
 	}
 
 	return dest_ptr;
diff --git a/lib/kfifo.c b/lib/kfifo.c
index 12f5a347aa137..15acdee4a8f32 100644
--- a/lib/kfifo.c
+++ b/lib/kfifo.c
@@ -5,13 +5,13 @@
  * Copyright (C) 2009/2010 Stefani Seibold <stefani@seibold.net>
  */
 
-#include <linux/kernel.h>
-#include <linux/export.h>
-#include <linux/slab.h>
 #include <linux/err.h>
+#include <linux/export.h>
+#include <linux/kfifo.h>
 #include <linux/log2.h>
+#include <linux/scatterlist.h>
+#include <linux/slab.h>
 #include <linux/uaccess.h>
-#include <linux/kfifo.h>
 
 /*
  * internal helper to calculate the unused elements in a fifo
diff --git a/lib/test_hexdump.c b/lib/test_hexdump.c
index b916801f23a89..fe2682bb21e6d 100644
--- a/lib/test_hexdump.c
+++ b/lib/test_hexdump.c
@@ -113,7 +113,7 @@ static void __init test_hexdump_prepare_test(size_t len, int rowsize,
 			*p++ = ' ';
 		} while (p < test + rs * 2 + rs / gs + 1);
 
-		strncpy(p, data_a, l);
+		memcpy(p, data_a, l);
 		p += l;
 	}
 
diff --git a/mm/kmsan/hooks.c b/mm/kmsan/hooks.c
index 0b09daa188ef6..22e8657800eff 100644
--- a/mm/kmsan/hooks.c
+++ b/mm/kmsan/hooks.c
@@ -285,6 +285,17 @@ void kmsan_copy_to_user(void __user *to, const void *from, size_t to_copy,
 }
 EXPORT_SYMBOL(kmsan_copy_to_user);
 
+void kmsan_memmove(void *to, const void *from, size_t size)
+{
+	if (!kmsan_enabled || kmsan_in_runtime())
+		return;
+
+	kmsan_enter_runtime();
+	kmsan_internal_memmove_metadata(to, (void *)from, size);
+	kmsan_leave_runtime();
+}
+EXPORT_SYMBOL(kmsan_memmove);
+
 /* Helper function to check an URB. */
 void kmsan_handle_urb(const struct urb *urb, bool is_out)
 {
diff --git a/samples/kfifo/dma-example.c b/samples/kfifo/dma-example.c
index 0cf27483cb361..74fe915b7ffe8 100644
--- a/samples/kfifo/dma-example.c
+++ b/samples/kfifo/dma-example.c
@@ -6,8 +6,9 @@
  */
 
 #include <linux/init.h>
-#include <linux/module.h>
 #include <linux/kfifo.h>
+#include <linux/module.h>
+#include <linux/scatterlist.h>
 
 /*
  * This module shows how to handle fifo dma operations.
diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index 9c4c4a61bc832..2b812210b412b 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -6040,6 +6040,12 @@ sub process {
 					CHK("MACRO_ARG_PRECEDENCE",
 					    "Macro argument '$arg' may be better as '($arg)' to avoid precedence issues\n" . "$herectx");
 				}
+
+# check if this is an unused argument
+				if ($define_stmt !~ /\b$arg\b/) {
+					WARN("MACRO_ARG_UNUSED",
+					     "Argument '$arg' is not used in function-like macro\n" . "$herectx");
+				}
 			}
 
 # check for macros with flow control, but without ## concatenation
diff --git a/scripts/gdb/linux/cpus.py b/scripts/gdb/linux/cpus.py
index cba589e5b57d6..2f11c4f9c345a 100644
--- a/scripts/gdb/linux/cpus.py
+++ b/scripts/gdb/linux/cpus.py
@@ -26,11 +26,7 @@ def get_current_cpu():
     if utils.get_gdbserver_type() == utils.GDBSERVER_QEMU:
         return gdb.selected_thread().num - 1
     elif utils.get_gdbserver_type() == utils.GDBSERVER_KGDB:
-        tid = gdb.selected_thread().ptid[2]
-        if tid > (0x100000000 - MAX_CPUS - 2):
-            return 0x100000000 - tid - 2
-        else:
-            return tasks.get_thread_info(tasks.get_task_by_pid(tid))['cpu']
+        return gdb.parse_and_eval("kgdb_active.counter")
     else:
         raise gdb.GdbError("Sorry, obtaining the current CPU is not yet "
                            "supported with this gdb server.")
@@ -152,9 +148,8 @@ Note that VAR has to be quoted as string."""
     def __init__(self):
         super(PerCpu, self).__init__("lx_per_cpu")
 
-    def invoke(self, var_name, cpu=-1):
-        var_ptr = gdb.parse_and_eval("&" + var_name.string())
-        return per_cpu(var_ptr, cpu)
+    def invoke(self, var, cpu=-1):
+        return per_cpu(var.address, cpu)
 
 
 PerCpu()
diff --git a/scripts/gdb/linux/tasks.py b/scripts/gdb/linux/tasks.py
index 6793d6e86e777..62348397c1f5c 100644
--- a/scripts/gdb/linux/tasks.py
+++ b/scripts/gdb/linux/tasks.py
@@ -85,7 +85,7 @@ thread_info_type = utils.CachedType("struct thread_info")
 
 def get_thread_info(task):
     thread_info_ptr_type = thread_info_type.get_type().pointer()
-    if task.type.fields()[0].type == thread_info_type.get_type():
+    if task_type.get_type().fields()[0].type == thread_info_type.get_type():
         return task['thread_info']
     thread_info = task['stack'].cast(thread_info_ptr_type)
     return thread_info.dereference()
diff --git a/scripts/gdb/linux/utils.py b/scripts/gdb/linux/utils.py
index 7d5278d815fa1..245ab297ea84a 100644
--- a/scripts/gdb/linux/utils.py
+++ b/scripts/gdb/linux/utils.py
@@ -196,7 +196,7 @@ def get_gdbserver_type():
     def probe_kgdb():
         try:
             thread_info = gdb.execute("info thread 2", to_string=True)
-            return "shadowCPU0" in thread_info
+            return "shadowCPU" in thread_info
         except gdb.error:
             return False
 
diff --git a/tools/include/linux/rbtree_augmented.h b/tools/include/linux/rbtree_augmented.h
index 570bb9794421b..95483c7d81df7 100644
--- a/tools/include/linux/rbtree_augmented.h
+++ b/tools/include/linux/rbtree_augmented.h
@@ -158,13 +158,13 @@ RB_DECLARE_CALLBACKS(RBSTATIC, RBNAME,					      \
 
 static inline void rb_set_parent(struct rb_node *rb, struct rb_node *p)
 {
-	rb->__rb_parent_color = rb_color(rb) | (unsigned long)p;
+	rb->__rb_parent_color = rb_color(rb) + (unsigned long)p;
 }
 
 static inline void rb_set_parent_color(struct rb_node *rb,
 				       struct rb_node *p, int color)
 {
-	rb->__rb_parent_color = (unsigned long)p | color;
+	rb->__rb_parent_color = (unsigned long)p + color;
 }
 
 static inline void
diff --git a/tools/lib/rbtree.c b/tools/lib/rbtree.c
index 727396de6be54..9e7307186b7f4 100644
--- a/tools/lib/rbtree.c
+++ b/tools/lib/rbtree.c
@@ -58,7 +58,7 @@
 
 static inline void rb_set_black(struct rb_node *rb)
 {
-	rb->__rb_parent_color |= RB_BLACK;
+	rb->__rb_parent_color += RB_BLACK;
 }
 
 static inline struct rb_node *rb_red_parent(struct rb_node *red)
diff --git a/tools/testing/selftests/kcmp/kcmp_test.c b/tools/testing/selftests/kcmp/kcmp_test.c
index 25110c7c0b3ed..d7a8e321bb16b 100644
--- a/tools/testing/selftests/kcmp/kcmp_test.c
+++ b/tools/testing/selftests/kcmp/kcmp_test.c
@@ -91,7 +91,7 @@ int main(int argc, char **argv)
 		ksft_print_header();
 		ksft_set_plan(3);
 
-		fd2 = open(kpath, O_RDWR, 0644);
+		fd2 = open(kpath, O_RDWR);
 		if (fd2 < 0) {
 			perror("Can't open file");
 			ksft_exit_fail();