Merge tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-tracegrafted

Pull tracing fixes from Steven Rostedt:

 - Fix error output of boot instance creation failure

   Currently if a boot instance creation fails, instead of printing out
   the name of the instance that failed, it prints "(null)". That is
   because it prints "cur_str" that had already been processed by
   strsep(). Print the saved name instead.

   While at it, print the error code of the failure.

 - Fix use-after-free for same named historgrams

   Histograms can be named so that they can be used in multiple events.
   But if the named histogram has a variable attached, the second event
   that uses the named histogram which duplicates it and needs to free
   the original after duplication leaves the old variable in place and
   still visible. If another histogram uses than variable, it will use
   the stale one which will try to reference the freed duplicate
   histogram and crash the kernel.

   Free the duplicate variables along with the duplicated histogram
   data.

 - Check return value of kthread_run() in event self test

   The events self tests uses a kthread for testing but does not check
   if it succeeded in creating a kthread. If the kthread creation were
   to fail, the code will still try to call kthread_stop() on the error
   returned.

 - Fix race between reading trace_pipe and updating subbuffer size

   If a user is reading the trace_pipe file at the same time they update
   the ring buffer sub-buffer size, can cause the trace_pipe read to
   read stale data. Add trace_access_lock() around updating the ring
   buffer sub-buffer size.

 - Fix eventfs_inode on failure path in creation of the events directory

   In the creation of the "events" directory, if after allocating the
   eventfs_inode a failure is detected, it calls cleanup_ei() which
   calls free_ei(). The free_ei() will test if eventfs_inode being freed
   has no children. It is a bug if it does. But on the failure case of
   the creation of the "events" directory, the children lists have not
   yet been initialized and the free will trigger a warning because
   list_empty() on an uninitialized list returns false.

   Move the initialization into init_ei() where it makes more sense and
   makes sure that a created eventfs_inode has its lists initialized
   upon creation.

 - Check return value of kthread_run() in ftrace direct sample code

   The sample code that shows how to use the ftrace direct calls does
   not test the return of kthread_run() to see if it succeeds. Return a
   failure if the kthread_run() doesn't succeed.

 - Clear user events state on fork in case of alloc failure

   On fork, the child gets a pointer to the parent's user events state.
   It makes a copy of it then updates the child's pointer to it. But if
   the allocation fails, the duplication function leaves the child with
   a pointer to its parent's descriptor. When the child cleans up its
   data, it will free the parent's descriptor while the parent is still
   using it.

   In the duplication function, set the child's user_event_mm to NULL
   before testing if the allocation succeeded, and when it exits it will
   not free the parent's descriptor.

 - Fix retry exhaustion in simple ring buffer reader swap

   simple_ring_buffer_swap_reader_page() starts with retry set to 8 and
   post-decrements it only after a failed link replacement. On the final
   attempt, a successful replacement leaves retry at zero, while a
   failed replacement leaves it at -1.

   But the check for success expects the retry value to be non-zero and
   exits with an error on zero. This is the opposite result. Fix it.

 - Fail nicely when the remote swap_reader_page() returns an error

   Currently, if the swap_reader_page() of a remote buffer fails, it
   triggers a WARN_ON_ONCE() and continues normally. Instead, have it
   exit with an error and a pr_warn() print instead of a full WARNING.

* tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
  ring-buffer: Stop remote reader update when page swap fails
  tracing: Fix retry exhaustion in simple ring buffer reader swap
  tracing/user_events: Clear copied tracing state before fork duplication
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-multi-modify
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-modify
  eventfs: Initialize ei->children and ei->list in init_ei()
  tracing: Fix use-after-free in trace_pipe read on sub-buffer order change
  tracing: Fix crash passing ERR_PTR to kthread_stop()
  tracing: Fix use-after-free with same-name named triggers
  tracing: Fix logged instance name on creation failure

1 files changed, 780 insertions, 0 deletions

diff --git a/fs/ntfs/logfile.c b/fs/ntfs/logfile.c
new file mode 100644
index 000000000..024ddee42
--- /dev/null
+++ b/fs/ntfs/logfile.c
@@ -0,0 +1,780 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * NTFS kernel journal handling.
+ *
+ * Copyright (c) 2002-2007 Anton Altaparmakov
+ */
+
+#include <linux/blkdev.h>
+
+#include "attrib.h"
+#include "logfile.h"
+#include "ntfs.h"
+
+/*
+ * ntfs_check_restart_page_header - check the page header for consistency
+ * @vi:		LogFile inode to which the restart page header belongs
+ * @rp:		restart page header to check
+ * @pos:	position in @vi at which the restart page header resides
+ *
+ * Check the restart page header @rp for consistency and return 'true' if it is
+ * consistent and 'false' otherwise.
+ *
+ * This function only needs NTFS_BLOCK_SIZE bytes in @rp, i.e. it does not
+ * require the full restart page.
+ */
+static bool ntfs_check_restart_page_header(struct inode *vi,
+		struct restart_page_header *rp, s64 pos)
+{
+	u32 logfile_system_page_size, logfile_log_page_size;
+	u16 ra_ofs, usa_count, usa_ofs, usa_end = 0;
+	bool have_usa = true;
+
+	ntfs_debug("Entering.");
+	/*
+	 * If the system or log page sizes are smaller than the ntfs block size
+	 * or either is not a power of 2 we cannot handle this log file.
+	 */
+	logfile_system_page_size = le32_to_cpu(rp->system_page_size);
+	logfile_log_page_size = le32_to_cpu(rp->log_page_size);
+	if (logfile_system_page_size < NTFS_BLOCK_SIZE ||
+			logfile_log_page_size < NTFS_BLOCK_SIZE ||
+			logfile_system_page_size &
+			(logfile_system_page_size - 1) ||
+			!is_power_of_2(logfile_log_page_size)) {
+		ntfs_error(vi->i_sb, "LogFile uses unsupported page size.");
+		return false;
+	}
+	/*
+	 * We must be either at !pos (1st restart page) or at pos = system page
+	 * size (2nd restart page).
+	 */
+	if (pos && pos != logfile_system_page_size) {
+		ntfs_error(vi->i_sb, "Found restart area in incorrect position in LogFile.");
+		return false;
+	}
+	/* We only know how to handle version 1.1. */
+	if (le16_to_cpu(rp->major_ver) != 1 ||
+	    le16_to_cpu(rp->minor_ver) != 1) {
+		ntfs_error(vi->i_sb,
+			"LogFile version %i.%i is not supported.  (This driver supports version 1.1 only.)",
+			(int)le16_to_cpu(rp->major_ver),
+			(int)le16_to_cpu(rp->minor_ver));
+		return false;
+	}
+	/*
+	 * If chkdsk has been run the restart page may not be protected by an
+	 * update sequence array.
+	 */
+	if (ntfs_is_chkd_record(rp->magic) && !le16_to_cpu(rp->usa_count)) {
+		have_usa = false;
+		goto skip_usa_checks;
+	}
+	/* Verify the size of the update sequence array. */
+	usa_count = 1 + (logfile_system_page_size >> NTFS_BLOCK_SIZE_BITS);
+	if (usa_count != le16_to_cpu(rp->usa_count)) {
+		ntfs_error(vi->i_sb,
+			"LogFile restart page specifies inconsistent update sequence array count.");
+		return false;
+	}
+	/* Verify the position of the update sequence array. */
+	usa_ofs = le16_to_cpu(rp->usa_ofs);
+	usa_end = usa_ofs + usa_count * sizeof(u16);
+	if (usa_ofs < sizeof(struct restart_page_header) ||
+			usa_end > NTFS_BLOCK_SIZE - sizeof(u16)) {
+		ntfs_error(vi->i_sb,
+			"LogFile restart page specifies inconsistent update sequence array offset.");
+		return false;
+	}
+skip_usa_checks:
+	/*
+	 * Verify the position of the restart area.  It must be:
+	 *	- aligned to 8-byte boundary,
+	 *	- after the update sequence array, and
+	 *	- within the system page size.
+	 */
+	ra_ofs = le16_to_cpu(rp->restart_area_offset);
+	if (ra_ofs & 7 || (have_usa ? ra_ofs < usa_end :
+			ra_ofs < sizeof(struct restart_page_header)) ||
+			ra_ofs > logfile_system_page_size) {
+		ntfs_error(vi->i_sb,
+			"LogFile restart page specifies inconsistent restart area offset.");
+		return false;
+	}
+	/*
+	 * Only restart pages modified by chkdsk are allowed to have chkdsk_lsn
+	 * set.
+	 */
+	if (!ntfs_is_chkd_record(rp->magic) && le64_to_cpu(rp->chkdsk_lsn)) {
+		ntfs_error(vi->i_sb,
+			"LogFile restart page is not modified by chkdsk but a chkdsk LSN is specified.");
+		return false;
+	}
+	ntfs_debug("Done.");
+	return true;
+}
+
+/*
+ * ntfs_check_restart_area - check the restart area for consistency
+ * @vi:		LogFile inode to which the restart page belongs
+ * @rp:		restart page whose restart area to check
+ *
+ * Check the restart area of the restart page @rp for consistency and return
+ * 'true' if it is consistent and 'false' otherwise.
+ *
+ * This function assumes that the restart page header has already been
+ * consistency checked.
+ *
+ * This function only needs NTFS_BLOCK_SIZE bytes in @rp, i.e. it does not
+ * require the full restart page.
+ */
+static bool ntfs_check_restart_area(struct inode *vi, struct restart_page_header *rp)
+{
+	u64 file_size;
+	struct restart_area *ra;
+	u32 ra_ofs, ra_len, ca_ofs;
+	u8 fs_bits;
+
+	ntfs_debug("Entering.");
+	ra_ofs = le16_to_cpu(rp->restart_area_offset);
+	ra = (struct restart_area *)((u8 *)rp + ra_ofs);
+	/*
+	 * Everything before ra->file_size must be before the first word
+	 * protected by an update sequence number.  This ensures that it is
+	 * safe to access ra->client_array_offset.
+	 */
+	if (ra_ofs + offsetof(struct restart_area, file_size) >
+			NTFS_BLOCK_SIZE - sizeof(u16)) {
+		ntfs_error(vi->i_sb,
+			"LogFile restart area specifies inconsistent file offset.");
+		return false;
+	}
+	/*
+	 * Now that we can access ra->client_array_offset, make sure everything
+	 * up to the log client array is before the first word protected by an
+	 * update sequence number.  This ensures we can access all of the
+	 * restart area elements safely.  Also, the client array offset must be
+	 * aligned to an 8-byte boundary.
+	 */
+	ca_ofs = le16_to_cpu(ra->client_array_offset);
+	if (((ca_ofs + 7) & ~7) != ca_ofs ||
+			ra_ofs + ca_ofs > NTFS_BLOCK_SIZE - sizeof(u16)) {
+		ntfs_error(vi->i_sb,
+			"LogFile restart area specifies inconsistent client array offset.");
+		return false;
+	}
+	/*
+	 * The restart area must end within the system page size both when
+	 * calculated manually and as specified by ra->restart_area_length.
+	 * Also, the calculated length must not exceed the specified length.
+	 */
+	ra_len = ca_ofs + le16_to_cpu(ra->log_clients) *
+			sizeof(struct log_client_record);
+	if (ra_ofs + ra_len > le32_to_cpu(rp->system_page_size) ||
+			ra_ofs + le16_to_cpu(ra->restart_area_length) >
+			le32_to_cpu(rp->system_page_size) ||
+			ra_len > le16_to_cpu(ra->restart_area_length)) {
+		ntfs_error(vi->i_sb,
+			"LogFile restart area is out of bounds of the system page size specified by the restart page header and/or the specified restart area length is inconsistent.");
+		return false;
+	}
+	/*
+	 * The ra->client_free_list and ra->client_in_use_list must be either
+	 * LOGFILE_NO_CLIENT or less than ra->log_clients or they are
+	 * overflowing the client array.
+	 */
+	if ((ra->client_free_list != LOGFILE_NO_CLIENT &&
+			le16_to_cpu(ra->client_free_list) >=
+			le16_to_cpu(ra->log_clients)) ||
+			(ra->client_in_use_list != LOGFILE_NO_CLIENT &&
+			le16_to_cpu(ra->client_in_use_list) >=
+			le16_to_cpu(ra->log_clients))) {
+		ntfs_error(vi->i_sb,
+			"LogFile restart area specifies overflowing client free and/or in use lists.");
+		return false;
+	}
+	/*
+	 * Check ra->seq_number_bits against ra->file_size for consistency.
+	 * We cannot just use ffs() because the file size is not a power of 2.
+	 */
+	file_size = le64_to_cpu(ra->file_size);
+	fs_bits = 0;
+	while (file_size) {
+		file_size >>= 1;
+		fs_bits++;
+	}
+	if (le32_to_cpu(ra->seq_number_bits) != 67 - fs_bits) {
+		ntfs_error(vi->i_sb,
+			"LogFile restart area specifies inconsistent sequence number bits.");
+		return false;
+	}
+	/* The log record header length must be a multiple of 8. */
+	if (((le16_to_cpu(ra->log_record_header_length) + 7) & ~7) !=
+			le16_to_cpu(ra->log_record_header_length)) {
+		ntfs_error(vi->i_sb,
+			"LogFile restart area specifies inconsistent log record header length.");
+		return false;
+	}
+	/* Dito for the log page data offset. */
+	if (((le16_to_cpu(ra->log_page_data_offset) + 7) & ~7) !=
+			le16_to_cpu(ra->log_page_data_offset)) {
+		ntfs_error(vi->i_sb,
+			"LogFile restart area specifies inconsistent log page data offset.");
+		return false;
+	}
+	ntfs_debug("Done.");
+	return true;
+}
+
+/*
+ * ntfs_check_log_client_array - check the log client array for consistency
+ * @vi:		LogFile inode to which the restart page belongs
+ * @rp:		restart page whose log client array to check
+ *
+ * Check the log client array of the restart page @rp for consistency and
+ * return 'true' if it is consistent and 'false' otherwise.
+ *
+ * This function assumes that the restart page header and the restart area have
+ * already been consistency checked.
+ *
+ * Unlike ntfs_check_restart_page_header() and ntfs_check_restart_area(), this
+ * function needs @rp->system_page_size bytes in @rp, i.e. it requires the full
+ * restart page and the page must be multi sector transfer deprotected.
+ */
+static bool ntfs_check_log_client_array(struct inode *vi,
+		struct restart_page_header *rp)
+{
+	struct restart_area *ra;
+	struct log_client_record *ca, *cr;
+	u16 nr_clients, idx;
+	bool in_free_list, idx_is_first;
+
+	ntfs_debug("Entering.");
+	ra = (struct restart_area *)((u8 *)rp + le16_to_cpu(rp->restart_area_offset));
+	ca = (struct log_client_record *)((u8 *)ra +
+			le16_to_cpu(ra->client_array_offset));
+	/*
+	 * Check the ra->client_free_list first and then check the
+	 * ra->client_in_use_list.  Check each of the log client records in
+	 * each of the lists and check that the array does not overflow the
+	 * ra->log_clients value.  Also keep track of the number of records
+	 * visited as there cannot be more than ra->log_clients records and
+	 * that way we detect eventual loops in within a list.
+	 */
+	nr_clients = le16_to_cpu(ra->log_clients);
+	idx = le16_to_cpu(ra->client_free_list);
+	in_free_list = true;
+check_list:
+	for (idx_is_first = true; idx != LOGFILE_NO_CLIENT_CPU; nr_clients--,
+			idx = le16_to_cpu(cr->next_client)) {
+		if (!nr_clients || idx >= le16_to_cpu(ra->log_clients))
+			goto err_out;
+		/* Set @cr to the current log client record. */
+		cr = ca + idx;
+		/* The first log client record must not have a prev_client. */
+		if (idx_is_first) {
+			if (cr->prev_client != LOGFILE_NO_CLIENT)
+				goto err_out;
+			idx_is_first = false;
+		}
+	}
+	/* Switch to and check the in use list if we just did the free list. */
+	if (in_free_list) {
+		in_free_list = false;
+		idx = le16_to_cpu(ra->client_in_use_list);
+		goto check_list;
+	}
+	ntfs_debug("Done.");
+	return true;
+err_out:
+	ntfs_error(vi->i_sb, "LogFile log client array is corrupt.");
+	return false;
+}
+
+/*
+ * ntfs_check_and_load_restart_page - check the restart page for consistency
+ * @vi:		LogFile inode to which the restart page belongs
+ * @rp:		restart page to check
+ * @pos:	position in @vi at which the restart page resides
+ * @wrp:	[OUT] copy of the multi sector transfer deprotected restart page
+ * @lsn:	[OUT] set to the current logfile lsn on success
+ *
+ * Check the restart page @rp for consistency and return 0 if it is consistent
+ * and -errno otherwise.  The restart page may have been modified by chkdsk in
+ * which case its magic is CHKD instead of RSTR.
+ *
+ * This function only needs NTFS_BLOCK_SIZE bytes in @rp, i.e. it does not
+ * require the full restart page.
+ *
+ * If @wrp is not NULL, on success, *@wrp will point to a buffer containing a
+ * copy of the complete multi sector transfer deprotected page.  On failure,
+ * *@wrp is undefined.
+ *
+ * Simillarly, if @lsn is not NULL, on success *@lsn will be set to the current
+ * logfile lsn according to this restart page.  On failure, *@lsn is undefined.
+ *
+ * The following error codes are defined:
+ *	-EINVAL	- The restart page is inconsistent.
+ *	-ENOMEM	- Not enough memory to load the restart page.
+ *	-EIO	- Failed to reading from LogFile.
+ */
+static int ntfs_check_and_load_restart_page(struct inode *vi,
+		struct restart_page_header *rp, s64 pos, struct restart_page_header **wrp,
+		s64 *lsn)
+{
+	struct restart_area *ra;
+	struct restart_page_header *trp;
+	int size, err;
+
+	ntfs_debug("Entering.");
+	/* Check the restart page header for consistency. */
+	if (!ntfs_check_restart_page_header(vi, rp, pos)) {
+		/* Error output already done inside the function. */
+		return -EINVAL;
+	}
+	/* Check the restart area for consistency. */
+	if (!ntfs_check_restart_area(vi, rp)) {
+		/* Error output already done inside the function. */
+		return -EINVAL;
+	}
+	ra = (struct restart_area *)((u8 *)rp + le16_to_cpu(rp->restart_area_offset));
+	/*
+	 * Allocate a buffer to store the whole restart page so we can multi
+	 * sector transfer deprotect it.
+	 */
+	trp = kvzalloc(le32_to_cpu(rp->system_page_size), GFP_NOFS);
+	if (!trp) {
+		ntfs_error(vi->i_sb, "Failed to allocate memory for LogFile restart page buffer.");
+		return -ENOMEM;
+	}
+	/*
+	 * Read the whole of the restart page into the buffer.  If it fits
+	 * completely inside @rp, just copy it from there.  Otherwise map all
+	 * the required pages and copy the data from them.
+	 */
+	size = PAGE_SIZE - (pos & ~PAGE_MASK);
+	if (size >= le32_to_cpu(rp->system_page_size)) {
+		memcpy(trp, rp, le32_to_cpu(rp->system_page_size));
+	} else {
+		pgoff_t idx;
+		struct folio *folio;
+		int have_read, to_read;
+
+		/* First copy what we already have in @rp. */
+		memcpy(trp, rp, size);
+		/* Copy the remaining data one page at a time. */
+		have_read = size;
+		to_read = le32_to_cpu(rp->system_page_size) - size;
+		idx = (pos + size) >> PAGE_SHIFT;
+		do {
+			folio = read_mapping_folio(vi->i_mapping, idx, NULL);
+			if (IS_ERR(folio)) {
+				ntfs_error(vi->i_sb, "Error mapping LogFile page (index %lu).",
+						idx);
+				err = PTR_ERR(folio);
+				if (err != -EIO && err != -ENOMEM)
+					err = -EIO;
+				goto err_out;
+			}
+			size = min_t(int, to_read, PAGE_SIZE);
+			memcpy((u8 *)trp + have_read, folio_address(folio), size);
+			folio_put(folio);
+			have_read += size;
+			to_read -= size;
+			idx++;
+		} while (to_read > 0);
+	}
+	/*
+	 * Perform the multi sector transfer deprotection on the buffer if the
+	 * restart page is protected.
+	 */
+	if ((!ntfs_is_chkd_record(trp->magic) || le16_to_cpu(trp->usa_count)) &&
+	    post_read_mst_fixup((struct ntfs_record *)trp, le32_to_cpu(rp->system_page_size))) {
+		/*
+		 * A multi sector transfer error was detected.  We only need to
+		 * abort if the restart page contents exceed the multi sector
+		 * transfer fixup of the first sector.
+		 */
+		if (le16_to_cpu(rp->restart_area_offset) +
+				le16_to_cpu(ra->restart_area_length) >
+				NTFS_BLOCK_SIZE - sizeof(u16)) {
+			ntfs_error(vi->i_sb,
+				"Multi sector transfer error detected in LogFile restart page.");
+			err = -EINVAL;
+			goto err_out;
+		}
+	}
+	/*
+	 * If the restart page is modified by chkdsk or there are no active
+	 * logfile clients, the logfile is consistent.  Otherwise, need to
+	 * check the log client records for consistency, too.
+	 */
+	err = 0;
+	if (ntfs_is_rstr_record(rp->magic) &&
+			ra->client_in_use_list != LOGFILE_NO_CLIENT) {
+		if (!ntfs_check_log_client_array(vi, trp)) {
+			err = -EINVAL;
+			goto err_out;
+		}
+	}
+	if (lsn) {
+		if (ntfs_is_rstr_record(rp->magic))
+			*lsn = le64_to_cpu(ra->current_lsn);
+		else /* if (ntfs_is_chkd_record(rp->magic)) */
+			*lsn = le64_to_cpu(rp->chkdsk_lsn);
+	}
+	ntfs_debug("Done.");
+	if (wrp)
+		*wrp = trp;
+	else {
+err_out:
+		kvfree(trp);
+	}
+	return err;
+}
+
+/*
+ * ntfs_check_logfile - check the journal for consistency
+ * @log_vi:	struct inode of loaded journal LogFile to check
+ * @rp:		[OUT] on success this is a copy of the current restart page
+ *
+ * Check the LogFile journal for consistency and return 'true' if it is
+ * consistent and 'false' if not.  On success, the current restart page is
+ * returned in *@rp.  Caller must call kvfree(*@rp) when finished with it.
+ *
+ * At present we only check the two restart pages and ignore the log record
+ * pages.
+ *
+ * Note that the MstProtected flag is not set on the LogFile inode and hence
+ * when reading pages they are not deprotected.  This is because we do not know
+ * if the LogFile was created on a system with a different page size to ours
+ * yet and mst deprotection would fail if our page size is smaller.
+ */
+bool ntfs_check_logfile(struct inode *log_vi, struct restart_page_header **rp)
+{
+	s64 size, pos;
+	s64 rstr1_lsn, rstr2_lsn;
+	struct ntfs_volume *vol = NTFS_SB(log_vi->i_sb);
+	struct address_space *mapping = log_vi->i_mapping;
+	struct folio *folio = NULL;
+	u8 *kaddr = NULL;
+	struct restart_page_header *rstr1_ph = NULL;
+	struct restart_page_header *rstr2_ph = NULL;
+	int log_page_size, err;
+	bool logfile_is_empty = true;
+	u8 log_page_bits;
+
+	ntfs_debug("Entering.");
+	/* An empty LogFile must have been clean before it got emptied. */
+	if (NVolLogFileEmpty(vol))
+		goto is_empty;
+	size = i_size_read(log_vi);
+	/* Make sure the file doesn't exceed the maximum allowed size. */
+	if (size > MaxLogFileSize)
+		size = MaxLogFileSize;
+	/*
+	 * Truncate size to a multiple of the page cache size or the default
+	 * log page size if the page cache size is between the default log page
+	 * log page size if the page cache size is between the default log page
+	 * size and twice that.
+	 */
+	if (DefaultLogPageSize <= PAGE_SIZE &&
+	    DefaultLogPageSize * 2 <= PAGE_SIZE)
+		log_page_size = DefaultLogPageSize;
+	else
+		log_page_size = PAGE_SIZE;
+	/*
+	 * Use ntfs_ffs() instead of ffs() to enable the compiler to
+	 * optimize log_page_size and log_page_bits into constants.
+	 */
+	log_page_bits = ntfs_ffs(log_page_size) - 1;
+	size &= ~(s64)(log_page_size - 1);
+	/*
+	 * Ensure the log file is big enough to store at least the two restart
+	 * pages and the minimum number of log record pages.
+	 */
+	if (size < log_page_size * 2 || (size - log_page_size * 2) >>
+			log_page_bits < MinLogRecordPages) {
+		ntfs_error(vol->sb, "LogFile is too small.");
+		return false;
+	}
+	/*
+	 * Read through the file looking for a restart page.  Since the restart
+	 * page header is at the beginning of a page we only need to search at
+	 * what could be the beginning of a page (for each page size) rather
+	 * than scanning the whole file byte by byte.  If all potential places
+	 * contain empty and uninitialzed records, the log file can be assumed
+	 * to be empty.
+	 */
+	for (pos = 0; pos < size; pos <<= 1) {
+		pgoff_t idx = pos >> PAGE_SHIFT;
+
+		if (!folio || folio->index != idx) {
+			if (folio) {
+				kunmap_local(kaddr);
+				folio_put(folio);
+			}
+			folio = read_mapping_folio(mapping, idx, NULL);
+			if (IS_ERR(folio)) {
+				ntfs_error(vol->sb, "Error mapping LogFile page (index %lu).",
+						idx);
+				goto err_out;
+			}
+		}
+		kaddr = (u8 *)kmap_local_folio(folio, 0) + (pos & ~PAGE_MASK);
+		/*
+		 * A non-empty block means the logfile is not empty while an
+		 * empty block after a non-empty block has been encountered
+		 * means we are done.
+		 */
+		if (!ntfs_is_empty_recordp((__le32 *)kaddr))
+			logfile_is_empty = false;
+		else if (!logfile_is_empty)
+			break;
+		/*
+		 * A log record page means there cannot be a restart page after
+		 * this so no need to continue searching.
+		 */
+		if (ntfs_is_rcrd_recordp((__le32 *)kaddr))
+			break;
+		/* If not a (modified by chkdsk) restart page, continue. */
+		if (!ntfs_is_rstr_recordp((__le32 *)kaddr) &&
+				!ntfs_is_chkd_recordp((__le32 *)kaddr)) {
+			if (!pos)
+				pos = NTFS_BLOCK_SIZE >> 1;
+			continue;
+		}
+		/*
+		 * Check the (modified by chkdsk) restart page for consistency
+		 * and get a copy of the complete multi sector transfer
+		 * deprotected restart page.
+		 */
+		err = ntfs_check_and_load_restart_page(log_vi,
+				(struct restart_page_header *)kaddr, pos,
+				!rstr1_ph ? &rstr1_ph : &rstr2_ph,
+				!rstr1_ph ? &rstr1_lsn : &rstr2_lsn);
+		if (!err) {
+			/*
+			 * If we have now found the first (modified by chkdsk)
+			 * restart page, continue looking for the second one.
+			 */
+			if (!pos) {
+				pos = NTFS_BLOCK_SIZE >> 1;
+				continue;
+			}
+			/*
+			 * We have now found the second (modified by chkdsk)
+			 * restart page, so we can stop looking.
+			 */
+			break;
+		}
+		/*
+		 * Error output already done inside the function.  Note, we do
+		 * not abort if the restart page was invalid as we might still
+		 * find a valid one further in the file.
+		 */
+		if (err != -EINVAL) {
+			kunmap_local(kaddr);
+			folio_put(folio);
+			goto err_out;
+		}
+		/* Continue looking. */
+		if (!pos)
+			pos = NTFS_BLOCK_SIZE >> 1;
+	}
+	if (folio) {
+		kunmap_local(kaddr);
+		folio_put(folio);
+	}
+	if (logfile_is_empty) {
+		NVolSetLogFileEmpty(vol);
+is_empty:
+		ntfs_debug("Done.  (LogFile is empty.)");
+		return true;
+	}
+	if (!rstr1_ph) {
+		ntfs_error(vol->sb,
+			"Did not find any restart pages in LogFile and it was not empty.");
+		return false;
+	}
+	/* If both restart pages were found, use the more recent one. */
+	if (rstr2_ph) {
+		/*
+		 * If the second restart area is more recent, switch to it.
+		 * Otherwise just throw it away.
+		 */
+		if (rstr2_lsn > rstr1_lsn) {
+			ntfs_debug("Using second restart page as it is more recent.");
+			kvfree(rstr1_ph);
+			rstr1_ph = rstr2_ph;
+			/* rstr1_lsn = rstr2_lsn; */
+		} else {
+			ntfs_debug("Using first restart page as it is more recent.");
+			kvfree(rstr2_ph);
+		}
+		rstr2_ph = NULL;
+	}
+	/* All consistency checks passed. */
+	if (rp)
+		*rp = rstr1_ph;
+	else
+		kvfree(rstr1_ph);
+	ntfs_debug("Done.");
+	return true;
+err_out:
+	kvfree(rstr1_ph);
+	return false;
+}
+
+/*
+ * ntfs_empty_logfile - empty the contents of the LogFile journal
+ * @log_vi:	struct inode of loaded journal LogFile to empty
+ *
+ * Empty the contents of the LogFile journal @log_vi and return 'true' on
+ * success and 'false' on error.
+ *
+ * This function assumes that the LogFile journal has already been consistency
+ * checked by a call to ntfs_check_logfile() and that ntfs_is_logfile_clean()
+ * has been used to ensure that the LogFile is clean.
+ */
+bool ntfs_empty_logfile(struct inode *log_vi)
+{
+	s64 vcn, end_vcn;
+	struct ntfs_inode *log_ni = NTFS_I(log_vi);
+	struct ntfs_volume *vol = log_ni->vol;
+	struct super_block *sb = vol->sb;
+	struct runlist_element *rl;
+	unsigned long flags;
+	int err;
+	bool should_wait = true;
+	char *empty_buf = NULL;
+	struct file_ra_state *ra = NULL;
+
+	ntfs_debug("Entering.");
+	if (NVolLogFileEmpty(vol)) {
+		ntfs_debug("Done.");
+		return true;
+	}
+
+	/*
+	 * We cannot use ntfs_attr_set() because we may be still in the middle
+	 * of a mount operation.  Thus we do the emptying by hand by first
+	 * zapping the page cache pages for the LogFile/DATA attribute and
+	 * then emptying each of the buffers in each of the clusters specified
+	 * by the runlist by hand.
+	 */
+	vcn = 0;
+	read_lock_irqsave(&log_ni->size_lock, flags);
+	end_vcn = (log_ni->initialized_size + vol->cluster_size_mask) >>
+			vol->cluster_size_bits;
+	read_unlock_irqrestore(&log_ni->size_lock, flags);
+	truncate_inode_pages(log_vi->i_mapping, 0);
+	down_write(&log_ni->runlist.lock);
+	rl = log_ni->runlist.rl;
+	if (unlikely(!rl || vcn < rl->vcn || !rl->length)) {
+map_vcn:
+		err = ntfs_map_runlist_nolock(log_ni, vcn, NULL);
+		if (err) {
+			ntfs_error(sb, "Failed to map runlist fragment (error %d).", -err);
+			goto err;
+		}
+		rl = log_ni->runlist.rl;
+	}
+	/* Seek to the runlist element containing @vcn. */
+	while (rl->length && vcn >= rl[1].vcn)
+		rl++;
+
+	err = -ENOMEM;
+	empty_buf = kvzalloc(vol->cluster_size, GFP_NOFS);
+	if (!empty_buf)
+		goto err;
+
+	memset(empty_buf, 0xff, vol->cluster_size);
+
+	ra = kzalloc(sizeof(*ra), GFP_NOFS);
+	if (!ra)
+		goto err;
+
+	file_ra_state_init(ra, sb->s_bdev->bd_mapping);
+	do {
+		s64 lcn;
+		loff_t start, end;
+		s64 len;
+
+		/*
+		 * If this run is not mapped map it now and start again as the
+		 * runlist will have been updated.
+		 */
+		lcn = rl->lcn;
+		if (unlikely(lcn == LCN_RL_NOT_MAPPED)) {
+			vcn = rl->vcn;
+			kvfree(empty_buf);
+			empty_buf = NULL;
+			kfree(ra);
+			ra = NULL;
+			goto map_vcn;
+		}
+		/* If this run is not valid abort with an error. */
+		if (unlikely(!rl->length || lcn < LCN_HOLE))
+			goto rl_err;
+		/* Skip holes. */
+		if (lcn == LCN_HOLE)
+			continue;
+		start = NTFS_CLU_TO_B(vol, lcn);
+		len = rl->length;
+		if (rl[1].vcn > end_vcn)
+			len = end_vcn - rl->vcn;
+		end = NTFS_CLU_TO_B(vol, lcn + len);
+
+		page_cache_sync_readahead(sb->s_bdev->bd_mapping, ra, NULL,
+			start >> PAGE_SHIFT, (end - start) >> PAGE_SHIFT);
+
+		do {
+			err = ntfs_bdev_write(sb, empty_buf, start,
+						  vol->cluster_size);
+			if (err) {
+				ntfs_error(sb, "ntfs_dev_write failed, err : %d\n", err);
+				goto io_err;
+			}
+
+			/*
+			 * Submit the buffer and wait for i/o to complete but
+			 * only for the first buffer so we do not miss really
+			 * serious i/o errors.  Once the first buffer has
+			 * completed ignore errors afterwards as we can assume
+			 * that if one buffer worked all of them will work.
+			 */
+			if (should_wait) {
+				should_wait = false;
+				err = filemap_write_and_wait_range(sb->s_bdev->bd_mapping,
+						start, start + vol->cluster_size);
+				if (err)
+					goto io_err;
+			}
+			start += vol->cluster_size;
+		} while (start < end);
+	} while ((++rl)->vcn < end_vcn);
+	up_write(&log_ni->runlist.lock);
+	kvfree(empty_buf);
+	kfree(ra);
+	truncate_inode_pages(log_vi->i_mapping, 0);
+	/* Set the flag so we do not have to do it again on remount. */
+	NVolSetLogFileEmpty(vol);
+	ntfs_debug("Done.");
+	return true;
+io_err:
+	ntfs_error(sb, "Failed to write buffer.  Unmount and run chkdsk.");
+	goto dirty_err;
+rl_err:
+	ntfs_error(sb, "Runlist is corrupt.  Unmount and run chkdsk.");
+dirty_err:
+	NVolSetErrors(vol);
+	err = -EIO;
+err:
+	kvfree(empty_buf);
+	kfree(ra);
+	up_write(&log_ni->runlist.lock);
+	ntfs_error(sb, "Failed to fill LogFile with 0xff bytes (error %d).",
+			-err);
+	return false;
+}