Thread: [Linux-NTFS-Dev] [PATCH v26 07/10] fs/ntfs3: Add NTFS journal (Page 13)

SourceForge Headquarters 225 Broadway Suite 1600 San Diego, CA 92101 +1 (858) 422-6466

This adds NTFS journal

Signed-off-by: Konstantin Komarov <alm...@pa...>
---
 fs/ntfs3/fslog.c | 5181 ++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 5181 insertions(+)
 create mode 100644 fs/ntfs3/fslog.c

diff --git a/fs/ntfs3/fslog.c b/fs/ntfs3/fslog.c
new file mode 100644
index 000000000..53da12252
--- /dev/null
+++ b/fs/ntfs3/fslog.c
@@ -0,0 +1,5181 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *
+ * Copyright (C) 2019-2021 Paragon Software GmbH, All rights reserved.
+ *
+ */
+
+#include <linux/blkdev.h>
+#include <linux/buffer_head.h>
+#include <linux/fs.h>
+#include <linux/hash.h>
+#include <linux/nls.h>
+#include <linux/random.h>
+#include <linux/ratelimit.h>
+#include <linux/slab.h>
+
+#include "debug.h"
+#include "ntfs.h"
+#include "ntfs_fs.h"
+
+/*
+ * LOG FILE structs
+ */
+
+// clang-format off
+
+#define MaxLogFileSize     0x100000000ull
+#define DefaultLogPageSize 4096
+#define MinLogRecordPages  0x30
+
+struct RESTART_HDR {
+	struct NTFS_RECORD_HEADER rhdr; // 'RSTR'
+	__le32 sys_page_size; // 0x10: Page size of the system which initialized the log
+	__le32 page_size;     // 0x14: Log page size used for this log file
+	__le16 ra_off;        // 0x18:
+	__le16 minor_ver;     // 0x1A:
+	__le16 major_ver;     // 0x1C:
+	__le16 fixups[];
+};
+
+#define LFS_NO_CLIENT 0xffff
+#define LFS_NO_CLIENT_LE cpu_to_le16(0xffff)
+
+struct CLIENT_REC {
+	__le64 oldest_lsn;
+	__le64 restart_lsn; // 0x08:
+	__le16 prev_client; // 0x10:
+	__le16 next_client; // 0x12:
+	__le16 seq_num;     // 0x14:
+	u8 align[6];        // 0x16
+	__le32 name_bytes;  // 0x1C: in bytes
+	__le16 name[32];    // 0x20: name of client
+};
+
+static_assert(sizeof(struct CLIENT_REC) == 0x60);
+
+/* Two copies of these will exist at the beginning of the log file */
+struct RESTART_AREA {
+	__le64 current_lsn;    // 0x00: Current logical end of log file
+	__le16 log_clients;    // 0x08: Maximum number of clients
+	__le16 client_idx[2];  // 0x0A: free/use index into the client record arrays
+	__le16 flags;          // 0x0E: See RESTART_SINGLE_PAGE_IO
+	__le32 seq_num_bits;   // 0x10: the number of bits in sequence number.
+	__le16 ra_len;         // 0x14:
+	__le16 client_off;     // 0x16:
+	__le64 l_size;         // 0x18: Usable log file size.
+	__le32 last_lsn_data_len; // 0x20:
+	__le16 rec_hdr_len;    // 0x24: log page data offset
+	__le16 data_off;       // 0x26: log page data length
+	__le32 open_log_count; // 0x28:
+	__le32 align[5];       // 0x2C:
+	struct CLIENT_REC clients[]; // 0x40:
+};
+
+struct LOG_REC_HDR {
+	__le16 redo_op;      // 0x00:  NTFS_LOG_OPERATION
+	__le16 undo_op;      // 0x02:  NTFS_LOG_OPERATION
+	__le16 redo_off;     // 0x04:  Offset to Redo record
+	__le16 redo_len;     // 0x06:  Redo length
+	__le16 undo_off;     // 0x08:  Offset to Undo record
+	__le16 undo_len;     // 0x0A:  Undo length
+	__le16 target_attr;  // 0x0C:
+	__le16 lcns_follow;  // 0x0E:
+	__le16 record_off;   // 0x10:
+	__le16 attr_off;     // 0x12:
+	__le16 cluster_off;  // 0x14:
+	__le16 reserved;     // 0x16:
+	__le64 target_vcn;   // 0x18:
+	__le64 page_lcns[];  // 0x20:
+};
+
+static_assert(sizeof(struct LOG_REC_HDR) == 0x20);
+
+#define RESTART_ENTRY_ALLOCATED    0xFFFFFFFF
+#define RESTART_ENTRY_ALLOCATED_LE cpu_to_le32(0xFFFFFFFF)
+
+struct RESTART_TABLE {
+	__le16 size;       // 0x00:  In bytes
+	__le16 used;       // 0x02: entries
+	__le16 total;      // 0x04: entries
+	__le16 res[3];     // 0x06:
+	__le32 free_goal;  // 0x0C:
+	__le32 first_free; // 0x10
+	__le32 last_free;  // 0x14
+
+};
+
+static_assert(sizeof(struct RESTART_TABLE) == 0x18);
+
+struct ATTR_NAME_ENTRY {
+	__le16 off; // offset in the Open attribute Table
+	__le16 name_bytes;
+	__le16 name[];
+};
+
+struct OPEN_ATTR_ENRTY {
+	__le32 next;            // 0x00: RESTART_ENTRY_ALLOCATED if allocated
+	__le32 bytes_per_index; // 0x04:
+	enum ATTR_TYPE type;    // 0x08:
+	u8 is_dirty_pages;      // 0x0C:
+	u8 is_attr_name;        // 0x0B: Faked field to manage 'ptr'
+	u8 name_len;            // 0x0C: Faked field to manage 'ptr'
+	u8 res;
+	struct MFT_REF ref; // 0x10: File Reference of file containing attribute
+	__le64 open_record_lsn; // 0x18:
+	void *ptr;              // 0x20:
+};
+
+/* 32 bit version of 'struct OPEN_ATTR_ENRTY' */
+struct OPEN_ATTR_ENRTY_32 {
+	__le32 next;            // 0x00: RESTART_ENTRY_ALLOCATED if allocated
+	__le32 ptr;             // 0x04:
+	struct MFT_REF ref;     // 0x08:
+	__le64 open_record_lsn; // 0x10:
+	u8 is_dirty_pages;      // 0x18:
+	u8 is_attr_name;        // 0x19
+	u8 res1[2];
+	enum ATTR_TYPE type;    // 0x1C:
+	u8 name_len;            // 0x20:  in wchar
+	u8 res2[3];
+	__le32 AttributeName;   // 0x24:
+	__le32 bytes_per_index; // 0x28:
+};
+
+#define SIZEOF_OPENATTRIBUTEENTRY0 0x2c
+// static_assert( 0x2C == sizeof(struct OPEN_ATTR_ENRTY_32) );
+static_assert(sizeof(struct OPEN_ATTR_ENRTY) < SIZEOF_OPENATTRIBUTEENTRY0);
+
+/*
+ * One entry exists in the Dirty Pages Table for each page which is dirty at the
+ * time the Restart Area is written
+ */
+struct DIR_PAGE_ENTRY {
+	__le32 next;         // 0x00:  RESTART_ENTRY_ALLOCATED if allocated
+	__le32 target_attr;  // 0x04:  Index into the Open attribute Table
+	__le32 transfer_len; // 0x08:
+	__le32 lcns_follow;  // 0x0C:
+	__le64 vcn;          // 0x10:  Vcn of dirty page
+	__le64 oldest_lsn;   // 0x18:
+	__le64 page_lcns[];  // 0x20:
+};
+
+static_assert(sizeof(struct DIR_PAGE_ENTRY) == 0x20);
+
+/* 32 bit version of 'struct DIR_PAGE_ENTRY' */
+struct DIR_PAGE_ENTRY_32 {
+	__le32 next;         // 0x00:  RESTART_ENTRY_ALLOCATED if allocated
+	__le32 target_attr;  // 0x04:  Index into the Open attribute Table
+	__le32 transfer_len; // 0x08:
+	__le32 lcns_follow;  // 0x0C:
+	__le32 reserved;     // 0x10:
+	__le32 vcn_low;      // 0x14:  Vcn of dirty page
+	__le32 vcn_hi;       // 0x18:  Vcn of dirty page
+	__le32 oldest_lsn_low; // 0x1C:
+	__le32 oldest_lsn_hi; // 0x1C:
+	__le32 page_lcns_low; // 0x24:
+	__le32 page_lcns_hi; // 0x24:
+};
+
+static_assert(offsetof(struct DIR_PAGE_ENTRY_32, vcn_low) == 0x14);
+static_assert(sizeof(struct DIR_PAGE_ENTRY_32) == 0x2c);
+
+enum transact_state {
+	TransactionUninitialized = 0,
+	TransactionActive,
+	TransactionPrepared,
+	TransactionCommitted
+};
+
+struct TRANSACTION_ENTRY {
+	__le32 next;          // 0x00: RESTART_ENTRY_ALLOCATED if allocated
+	u8 transact_state;    // 0x04:
+	u8 reserved[3];       // 0x05:
+	__le64 first_lsn;     // 0x08:
+	__le64 prev_lsn;      // 0x10:
+	__le64 undo_next_lsn; // 0x18:
+	__le32 undo_records;  // 0x20: Number of undo log records pending abort
+	__le32 undo_len;      // 0x24: Total undo size
+};
+
+static_assert(sizeof(struct TRANSACTION_ENTRY) == 0x28);
+
+struct NTFS_RESTART {
+	__le32 major_ver;             // 0x00:
+	__le32 minor_ver;             // 0x04:
+	__le64 check_point_start;     // 0x08:
+	__le64 open_attr_table_lsn;   // 0x10:
+	__le64 attr_names_lsn;        // 0x18:
+	__le64 dirty_pages_table_lsn; // 0x20:
+	__le64 transact_table_lsn;    // 0x28:
+	__le32 open_attr_len;         // 0x30: In bytes
+	__le32 attr_names_len;        // 0x34: In bytes
+	__le32 dirty_pages_len;       // 0x38: In bytes
+	__le32 transact_table_len;    // 0x3C: In bytes
+};
+
+static_assert(sizeof(struct NTFS_RESTART) == 0x40);
+
+struct NEW_ATTRIBUTE_SIZES {
+	__le64 alloc_size;
+	__le64 valid_size;
+	__le64 data_size;
+	__le64 total_size;
+};
+
+struct BITMAP_RANGE {
+	__le32 bitmap_off;
+	__le32 bits;
+};
+
+struct LCN_RANGE {
+	__le64 lcn;
+	__le64 len;
+};
+
+/* The following type defines the different log record types */
+#define LfsClientRecord  cpu_to_le32(1)
+#define LfsClientRestart cpu_to_le32(2)
+
+/* This is used to uniquely identify a client for a particular log file */
+struct CLIENT_ID {
+	__le16 seq_num;
+	__le16 client_idx;
+};
+
+/* This is the header that begins every Log Record in the log file */
+struct LFS_RECORD_HDR {
+	__le64 this_lsn;    // 0x00:
+	__le64 client_prev_lsn;  // 0x08:
+	__le64 client_undo_next_lsn; // 0x10:
+	__le32 client_data_len;  // 0x18:
+	struct CLIENT_ID client; // 0x1C: Owner of this log record
+	__le32 record_type; // 0x20: LfsClientRecord or LfsClientRestart
+	__le32 transact_id; // 0x24:
+	__le16 flags;       // 0x28:	LOG_RECORD_MULTI_PAGE
+	u8 align[6];        // 0x2A:
+};
+
+#define LOG_RECORD_MULTI_PAGE cpu_to_le16(1)
+
+static_assert(sizeof(struct LFS_RECORD_HDR) == 0x30);
+
+struct LFS_RECORD {
+	__le16 next_record_off; // 0x00: Offset of the free space in the page
+	u8 align[6];         // 0x02:
+	__le64 last_end_lsn; // 0x08: lsn for the last log record which ends on the page
+};
+
+static_assert(sizeof(struct LFS_RECORD) == 0x10);
+
+struct RECORD_PAGE_HDR {
+	struct NTFS_RECORD_HEADER rhdr; // 'RCRD'
+	__le32 rflags;     // 0x10:  See LOG_PAGE_LOG_RECORD_END
+	__le16 page_count; // 0x14:
+	__le16 page_pos;   // 0x16:
+	struct LFS_RECORD record_hdr; // 0x18
+	__le16 fixups[10]; // 0x28
+	__le32 file_off;   // 0x3c: used when major version >= 2
+};
+
+// clang-format on
+
+// Page contains the end of a log record
+#define LOG_PAGE_LOG_RECORD_END cpu_to_le32(0x00000001)
+
+static inline bool is_log_record_end(const struct RECORD_PAGE_HDR *hdr)
+{
+	return hdr->rflags & LOG_PAGE_LOG_RECORD_END;
+}
+
+static_assert(offsetof(struct RECORD_PAGE_HDR, file_off) == 0x3c);
+
+/*
+ * END of NTFS LOG structures
+ */
+
+/* Define some tuning parameters to keep the restart tables a reasonable size */
+#define INITIAL_NUMBER_TRANSACTIONS 5
+
+enum NTFS_LOG_OPERATION {
+
+	Noop = 0x00,
+	CompensationLogRecord = 0x01,
+	InitializeFileRecordSegment = 0x02,
+	DeallocateFileRecordSegment = 0x03,
+	WriteEndOfFileRecordSegment = 0x04,
+	CreateAttribute = 0x05,
+	DeleteAttribute = 0x06,
+	UpdateResidentValue = 0x07,
+	UpdateNonresidentValue = 0x08,
+	UpdateMappingPairs = 0x09,
+	DeleteDirtyClusters = 0x0A,
+	SetNewAttributeSizes = 0x0B,
+	AddIndexEntryRoot = 0x0C,
+	DeleteIndexEntryRoot = 0x0D,
+	AddIndexEntryAllocation = 0x0E,
+	DeleteIndexEntryAllocation = 0x0F,
+	WriteEndOfIndexBuffer = 0x10,
+	SetIndexEntryVcnRoot = 0x11,
+	SetIndexEntryVcnAllocation = 0x12,
+	UpdateFileNameRoot = 0x13,
+	UpdateFileNameAllocation = 0x14,
+	SetBitsInNonresidentBitMap = 0x15,
+	ClearBitsInNonresidentBitMap = 0x16,
+	HotFix = 0x17,
+	EndTopLevelAction = 0x18,
+	PrepareTransaction = 0x19,
+	CommitTransaction = 0x1A,
+	ForgetTransaction = 0x1B,
+	OpenNonresidentAttribute = 0x1C,
+	OpenAttributeTableDump = 0x1D,
+	AttributeNamesDump = 0x1E,
+	DirtyPageTableDump = 0x1F,
+	TransactionTableDump = 0x20,
+	UpdateRecordDataRoot = 0x21,
+	UpdateRecordDataAllocation = 0x22,
+
+	UpdateRelativeDataInIndex =
+		0x23, // NtOfsRestartUpdateRelativeDataInIndex
+	UpdateRelativeDataInIndex2 = 0x24,
+	ZeroEndOfFileRecord = 0x25,
+};
+
+/*
+ * Array for log records which require a target attribute
+ * A true indicates that the corresponding restart operation requires a target attribute
+ */
+static const u8 AttributeRequired[] = {
+	0xFC, 0xFB, 0xFF, 0x10, 0x06,
+};
+
+static inline bool is_target_required(u16 op)
+{
+	bool ret = op <= UpdateRecordDataAllocation &&
+		   (AttributeRequired[op >> 3] >> (op & 7) & 1);
+	return ret;
+}
+
+static inline bool can_skip_action(enum NTFS_LOG_OPERATION op)
+{
+	switch (op) {
+	case Noop:
+	case DeleteDirtyClusters:
+	case HotFix:
+	case EndTopLevelAction:
+	case PrepareTransaction:
+	case CommitTransaction:
+	case ForgetTransaction:
+	case CompensationLogRecord:
+	case OpenNonresidentAttribute:
+	case OpenAttributeTableDump:
+	case AttributeNamesDump:
+	case DirtyPageTableDump:
+	case TransactionTableDump:
+		return true;
+	default:
+		return false;
+	}
+}
+
+enum { lcb_ctx_undo_next, lcb_ctx_prev, lcb_ctx_next };
+
+/* bytes per restart table */
+static inline u32 bytes_per_rt(const struct RESTART_TABLE *rt)
+{
+	return le16_to_cpu(rt->used) * le16_to_cpu(rt->size) +
+	       sizeof(struct RESTART_TABLE);
+}
+
+/* log record length */
+static inline u32 lrh_length(const struct LOG_REC_HDR *lr)
+{
+	u16 t16 = le16_to_cpu(lr->lcns_follow);
+
+	return struct_size(lr, page_lcns, max_t(u16, 1, t16));
+}
+
+struct lcb {
+	struct LFS_RECORD_HDR *lrh; // Log record header of the current lsn
+	struct LOG_REC_HDR *log_rec;
+	u32 ctx_mode; // lcb_ctx_undo_next/lcb_ctx_prev/lcb_ctx_next
+	struct CLIENT_ID client;
+	bool alloc; // if true the we should deallocate 'log_rec'
+};
+
+static void lcb_put(struct lcb *lcb)
+{
+	if (lcb->alloc)
+		ntfs_free(lcb->log_rec);
+	ntfs_free(lcb->lrh);
+	ntfs_free(lcb);
+}
+
+/*
+ * oldest_client_lsn
+ *
+ * find the oldest lsn from active clients.
+ */
+static inline void oldest_client_lsn(const struct CLIENT_REC *ca,
+				     __le16 next_client, u64 *oldest_lsn)
+{
+	while (next_client != LFS_NO_CLIENT_LE) {
+		const struct CLIENT_REC *cr = ca + le16_to_cpu(next_client);
+		u64 lsn = le64_to_cpu(cr->oldest_lsn);
+
+		/* ignore this block if it's oldest lsn is 0 */
+		if (lsn && lsn < *oldest_lsn)
+			*oldest_lsn = lsn;
+
+		next_client = cr->next_client;
+	}
+}
+
+static inline bool is_rst_page_hdr_valid(u32 file_off,
+					 const struct RESTART_HDR *rhdr)
+{
+	u32 sys_page = le32_to_cpu(rhdr->sys_page_size);
+	u32 page_size = le32_to_cpu(rhdr->page_size);
+	u32 end_usa;
+	u16 ro;
+
+	if (sys_page < SECTOR_SIZE || page_size < SECTOR_SIZE ||
+	    sys_page & (sys_page - 1) || page_size & (page_size - 1)) {
+		return false;
+	}
+
+	/* Check that if the file offset isn't 0, it is the system page size */
+	if (file_off && file_off != sys_page)
+		return false;
+
+	/* Check support version 1.1+ */
+	if (le16_to_cpu(rhdr->major_ver) <= 1 && !rhdr->minor_ver)
+		return false;
+
+	if (le16_to_cpu(rhdr->major_ver) > 2)
+		return false;
+
+	ro = le16_to_cpu(rhdr->ra_off);
+	if (!IsQuadAligned(ro) || ro > sys_page)
+		return false;
+
+	end_usa = ((sys_page >> SECTOR_SHIFT) + 1) * sizeof(short);
+	end_usa += le16_to_cpu(rhdr->rhdr.fix_off);
+
+	if (ro < end_usa)
+		return false;
+
+	return true;
+}
+
+static inline bool is_rst_area_valid(const struct RESTART_HDR *rhdr)
+{
+	const struct RESTART_AREA *ra;
+	u16 cl, fl, ul;
+	u32 off, l_size, file_dat_bits, file_size_round;
+	u16 ro = le16_to_cpu(rhdr->ra_off);
+	u32 sys_page = le32_to_cpu(rhdr->sys_page_size);
+
+	if (ro + offsetof(struct RESTART_AREA, l_size) >
+	    SECTOR_SIZE - sizeof(short))
+		return false;
+
+	ra = Add2Ptr(rhdr, ro);
+	cl = le16_to_cpu(ra->log_clients);
+
+	if (cl > 1)
+		return false;
+
+	off = le16_to_cpu(ra->client_off);
+
+	if (!IsQuadAligned(off) || ro + off > SECTOR_SIZE - sizeof(short))
+		return false;
+
+	off += cl * sizeof(struct CLIENT_REC);
+
+	if (off > sys_page)
+		return false;
+
+	/*
+	 * Check the restart length field and whether the entire
+	 * restart area is contained that length
+	 */
+	if (le16_to_cpu(rhdr->ra_off) + le16_to_cpu(ra->ra_len) > sys_page ||
+	    off > le16_to_cpu(ra->ra_len)) {
+		return false;
+	}
+
+	/*
+	 * As a final check make sure that the use list and the free list
+	 * are either empty or point to a valid client
+	 */
+	fl = le16_to_cpu(ra->client_idx[0]);
+	ul = le16_to_cpu(ra->client_idx[1]);
+	if ((fl != LFS_NO_CLIENT && fl >= cl) ||
+	    (ul != LFS_NO_CLIENT && ul >= cl))
+		return false;
+
+	/* Make sure the sequence number bits match the log file size */
+	l_size = le64_to_cpu(ra->l_size);
+
+	file_dat_bits = sizeof(u64) * 8 - le32_to_cpu(ra->seq_num_bits);
+	file_size_round = 1u << (file_dat_bits + 3);
+	if (file_size_round != l_size &&
+	    (file_size_round < l_size || (file_size_round / 2) > l_size)) {
+		return false;
+	}
+
+	/* The log page data offset and record header length must be quad-aligned */
+	if (!IsQuadAligned(le16_to_cpu(ra->data_off)) ||
+	    !IsQuadAligned(le16_to_cpu(ra->rec_hdr_len)))
+		return false;
+
+	return true;
+}
+
+static inline bool is_client_area_valid(const struct RESTART_HDR *rhdr,
+					bool usa_error)
+{
+	u16 ro = le16_to_cpu(rhdr->ra_off);
+	const struct RESTART_AREA *ra = Add2Ptr(rhdr, ro);
+	u16 ra_len = le16_to_cpu(ra->ra_len);
+	const struct CLIENT_REC *ca;
+	u32 i;
+
+	if (usa_error && ra_len + ro > SECTOR_SIZE - sizeof(short))
+		return false;
+
+	/* Find the start of the client array */
+	ca = Add2Ptr(ra, le16_to_cpu(ra->client_off));
+
+	/*
+	 * Start with the free list
+	 * Check that all the clients are valid and that there isn't a cycle
+	 * Do the in-use list on the second pass
+	 */
+	for (i = 0; i < 2; i++) {
+		u16 client_idx = le16_to_cpu(ra->client_idx[i]);
+		bool first_client = true;
+		u16 clients = le16_to_cpu(ra->log_clients);
+
+		while (client_idx != LFS_NO_CLIENT) {
+			const struct CLIENT_REC *cr;
+
+			if (!clients ||
+			    client_idx >= le16_to_cpu(ra->log_clients))
+				return false;
+
+			clients -= 1;
+			cr = ca + client_idx;
+
+			client_idx = le16_to_cpu(cr->next_client);
+
+			if (first_client) {
+				first_client = false;
+				if (cr->prev_client != LFS_NO_CLIENT_LE)
+					return false;
+			}
+		}
+	}
+
+	return true;
+}
+
+/*
+ * remove_client
+ *
+ * remove a client record from a client record list an restart area
+ */
+static inline void remove_client(struct CLIENT_REC *ca,
+				 const struct CLIENT_REC *cr, __le16 *head)
+{
+	if (cr->prev_client == LFS_NO_CLIENT_LE)
+		*head = cr->next_client;
+	else
+		ca[le16_to_cpu(cr->prev_client)].next_client = cr->next_client;
+
+	if (cr->next_client != LFS_NO_CLIENT_LE)
+		ca[le16_to_cpu(cr->next_client)].prev_client = cr->prev_client;
+}
+
+/*
+ * add_client
+ *
+ * add a client record to the start of a list
+ */
+static inline void add_client(struct CLIENT_REC *ca, u16 index, __le16 *head)
+{
+	struct CLIENT_REC *cr = ca + index;
+
+	cr->prev_client = LFS_NO_CLIENT_LE;
+	cr->next_client = *head;
+
+	if (*head != LFS_NO_CLIENT_LE)
+		ca[le16_to_cpu(*head)].prev_client = cpu_to_le16(index);
+
+	*head = cpu_to_le16(index);
+}
+
+/*
+ * enum_rstbl
+ *
+ */
+static inline void *enum_rstbl(struct RESTART_TABLE *t, void *c)
+{
+	__le32 *e;
+	u32 bprt;
+	u16 rsize = t ? le16_to_cpu(t->size) : 0;
+
+	if (!c) {
+		if (!t || !t->total)
+			return NULL;
+		e = Add2Ptr(t, sizeof(struct RESTART_TABLE));
+	} else {
+		e = Add2Ptr(c, rsize);
+	}
+
+	/* Loop until we hit the first one allocated, or the end of the list */
+	for (bprt = bytes_per_rt(t); PtrOffset(t, e) < bprt;
+	     e = Add2Ptr(e, rsize)) {
+		if (*e == RESTART_ENTRY_ALLOCATED_LE)
+			return e;
+	}
+	return NULL;
+}
+
+/*
+ * find_dp
+ *
+ * searches for a 'vcn' in Dirty Page Table,
+ */
+static inline struct DIR_PAGE_ENTRY *find_dp(struct RESTART_TABLE *dptbl,
+					     u32 target_attr, u64 vcn)
+{
+	__le32 ta = cpu_to_le32(target_attr);
+	struct DIR_PAGE_ENTRY *dp = NULL;
+
+	while ((dp = enum_rstbl(dptbl, dp))) {
+		u64 dp_vcn = le64_to_cpu(dp->vcn);
+
+		if (dp->target_attr == ta && vcn >= dp_vcn &&
+		    vcn < dp_vcn + le32_to_cpu(dp->lcns_follow)) {
+			return dp;
+		}
+	}
+	return NULL;
+}
+
+static inline u32 norm_file_page(u32 page_size, u32 *l_size, bool use_default)
+{
+	if (use_default)
+		page_size = DefaultLogPageSize;
+
+	/* Round the file size down to a system page boundary */
+	*l_size &= ~(page_size - 1);
+
+	/* File should contain at least 2 restart pages and MinLogRecordPages pages */
+	if (*l_size < (MinLogRecordPages + 2) * page_size)
+		return 0;
+
+	return page_size;
+}
+
+static bool check_log_rec(const struct LOG_REC_HDR *lr, u32 bytes, u32 tr,
+			  u32 bytes_per_attr_entry)
+{
+	u16 t16;
+
+	if (bytes < sizeof(struct LOG_REC_HDR))
+		return false;
+	if (!tr)
+		return false;
+
+	if ((tr - sizeof(struct RESTART_TABLE)) %
+	    sizeof(struct TRANSACTION_ENTRY))
+		return false;
+
+	if (le16_to_cpu(lr->redo_off) & 7)
+		return false;
+
+	if (le16_to_cpu(lr->undo_off) & 7)
+		return false;
+
+	if (lr->target_attr)
+		goto check_lcns;
+
+	if (is_target_required(le16_to_cpu(lr->redo_op)))
+		return false;
+
+	if (is_target_required(le16_to_cpu(lr->undo_op)))
+		return false;
+
+check_lcns:
+	if (!lr->lcns_follow)
+		goto check_length;
+
+	t16 = le16_to_cpu(lr->target_attr);
+	if ((t16 - sizeof(struct RESTART_TABLE)) % bytes_per_attr_entry)
+		return false;
+
+check_length:
+	if (bytes < lrh_length(lr))
+		return false;
+
+	return true;
+}
+
+static bool check_rstbl(const struct RESTART_TABLE *rt, size_t bytes)
+{
+	u32 ts;
+	u32 i, off;
+	u16 rsize = le16_to_cpu(rt->size);
+	u16 ne = le16_to_cpu(rt->used);
+	u32 ff = le32_to_cpu(rt->first_free);
+	u32 lf = le32_to_cpu(rt->last_free);
+
+	ts = rsize * ne + sizeof(struct RESTART_TABLE);
+
+	if (!rsize || rsize > bytes ||
+	    rsize + sizeof(struct RESTART_TABLE) > bytes || bytes < ts ||
+	    le16_to_cpu(rt->total) > ne || ff > ts || lf > ts ||
+	    (ff && ff < sizeof(struct RESTART_TABLE)) ||
+	    (lf && lf < sizeof(struct RESTART_TABLE))) {
+		return false;
+	}
+
+	/* Verify each entry is either allocated or points
+	 * to a valid offset the table
+	 */
+	for (i = 0; i < ne; i++) {
+		off = le32_to_cpu(*(__le32 *)Add2Ptr(
+			rt, i * rsize + sizeof(struct RESTART_TABLE)));
+
+		if (off != RESTART_ENTRY_ALLOCATED && off &&
+		    (off < sizeof(struct RESTART_TABLE) ||
+		     ((off - sizeof(struct RESTART_TABLE)) % rsize))) {
+			return false;
+		}
+	}
+
+	/* Walk through the list headed by the first entry to make
+	 * sure none of the entries are currently being used
+	 */
+	for (off = ff; off;) {
+		if (off == RESTART_ENTRY_ALLOCATED)
+			return false;
+
+		off = le32_to_cpu(*(__le32 *)Add2Ptr(rt, off));
+	}
+
+	return true;
+}
+
+/*
+ * free_rsttbl_idx
+ *
+ * frees a previously allocated index a Restart Table.
+ */
+static inline void free_rsttbl_idx(struct RESTART_TABLE *rt, u32 off)
+{
+	__le32 *e;
+	u32 lf = le32_to_cpu(rt->last_free);
+	__le32 off_le = cpu_to_le32(off);
+
+	e = Add2Ptr(rt, off);
+
+	if (off < le32_to_cpu(rt->free_goal)) {
+		*e = rt->first_free;
+		rt->first_free = off_le;
+		if (!lf)
+			rt->last_free = off_le;
+	} else {
+		if (lf)
+			*(__le32 *)Add2Ptr(rt, lf) = off_le;
+		else
+			rt->first_free = off_le;
+
+		rt->last_free = off_le;
+		*e = 0;
+	}
+
+	le16_sub_cpu(&rt->total, 1);
+}
+
+static inline struct RESTART_TABLE *init_rsttbl(u16 esize, u16 used)
+{
+	__le32 *e, *last_free;
+	u32 off;
+	u32 bytes = esize * used + sizeof(struct RESTART_TABLE);
+	u32 lf = sizeof(struct RESTART_TABLE) + (used - 1) * esize;
+	struct RESTART_TABLE *t = ntfs_zalloc(bytes);
+
+	t->size = cpu_to_le16(esize);
+	t->used = cpu_to_le16(used);
+	t->free_goal = cpu_to_le32(~0u);
+	t->first_free = cpu_to_le32(sizeof(struct RESTART_TABLE));
+	t->last_free = cpu_to_le32(lf);
+
+	e = (__le32 *)(t + 1);
+	last_free = Add2Ptr(t, lf);
+
+	for (off = sizeof(struct RESTART_TABLE) + esize; e < last_free;
+	     e = Add2Ptr(e, esize), off += esize) {
+		*e = cpu_to_le32(off);
+	}
+	return t;
+}
+
+static inline struct RESTART_TABLE *extend_rsttbl(struct RESTART_TABLE *tbl,
+						  u32 add, u32 free_goal)
+{
+	u16 esize = le16_to_cpu(tbl->size);
+	__le32 osize = cpu_to_le32(bytes_per_rt(tbl));
+	u32 used = le16_to_cpu(tbl->used);
+	struct RESTART_TABLE *rt = init_rsttbl(esize, used + add);
+
+	memcpy(rt + 1, tbl + 1, esize * used);
+
+	rt->free_goal = free_goal == ~0u
+				? cpu_to_le32(~0u)
+				: cpu_to_le32(sizeof(struct RESTART_TABLE) +
+					      free_goal * esize);
+
+	if (tbl->first_free) {
+		rt->first_free = tbl->first_free;
+		*(__le32 *)Add2Ptr(rt, le32_to_cpu(tbl->last_free)) = osize;
+	} else {
+		rt->first_free = osize;
+	}
+
+	rt->total = tbl->total;
+
+	ntfs_free(tbl);
+	return rt;
+}
+
+/*
+ * alloc_rsttbl_idx
+ *
+ * allocates an index from within a previously initialized Restart Table
+ */
+static inline void *alloc_rsttbl_idx(struct RESTART_TABLE **tbl)
+{
+	u32 off;
+	__le32 *e;
+	struct RESTART_TABLE *t = *tbl;
+
+	if (!t->first_free)
+		*tbl = t = extend_rsttbl(t, 16, ~0u);
+
+	off = le32_to_cpu(t->first_free);
+
+	/* Dequeue this entry and zero it. */
+	e = Add2Ptr(t, off);
+
+	t->first_free = *e;
+
+	memset(e, 0, le16_to_cpu(t->size));
+
+	*e = RESTART_ENTRY_ALLOCATED_LE;
+
+	/* If list is going empty, then we fix the last_free as well. */
+	if (!t->first_free)
+		t->last_free = 0;
+
+	le16_add_cpu(&t->total, 1);
+
+	return Add2Ptr(t, off);
+}
+
+/*
+ * alloc_rsttbl_from_idx
+ *
+ * allocates a specific index from within a previously initialized Restart Table
+ */
+static inline void *alloc_rsttbl_from_idx(struct RESTART_TABLE **tbl, u32 vbo)
+{
+	u32 off;
+	__le32 *e;
+	struct RESTART_TABLE *rt = *tbl;
+	u32 bytes = bytes_per_rt(rt);
+	u16 esize = le16_to_cpu(rt->size);
+
+	/* If the entry is not the table, we will have to extend the table */
+	if (vbo >= bytes) {
+		/*
+		 * extend the size by computing the number of entries between
+		 * the existing size and the desired index and adding
+		 * 1 to that
+		 */
+		u32 bytes2idx = vbo - bytes;
+
+		/* There should always be an integral number of entries being added */
+		/* Now extend the table */
+		*tbl = rt = extend_rsttbl(rt, bytes2idx / esize + 1, bytes);
+		if (!rt)
+			return NULL;
+	}
+
+	/* see if the entry is already allocated, and just return if it is. */
+	e = Add2Ptr(rt, vbo);
+
+	if (*e == RESTART_ENTRY_ALLOCATED_LE)
+		return e;
+
+	/*
+	 * Walk through the table, looking for the entry we're
+	 * interested and the previous entry
+	 */
+	off = le32_to_cpu(rt->first_free);
+	e = Add2Ptr(rt, off);
+
+	if (off == vbo) {
+		/* this is a match */
+		rt->first_free = *e;
+		goto skip_looking;
+	}
+
+	/*
+	 * need to walk through the list looking for the predecessor of our entry
+	 */
+	for (;;) {
+		/* Remember the entry just found */
+		u32 last_off = off;
+		__le32 *last_e = e;
+
+		/* should never run of entries. */
+
+		/* Lookup up the next entry the list */
+		off = le32_to_cpu(*last_e);
+		e = Add2Ptr(rt, off);
+
+		/* If this is our match we are done */
+		if (off == vbo) {
+			*last_e = *e;
+
+			/* If this was the last entry, we update that the table as well */
+			if (le32_to_cpu(rt->last_free) == off)
+				rt->last_free = cpu_to_le32(last_off);
+			break;
+		}
+	}
+
+skip_looking:
+	/* If the list is now empty, we fix the last_free as well */
+	if (!rt->first_free)
+		rt->last_free = 0;
+
+	/* Zero this entry */
+	memset(e, 0, esize);
+	*e = RESTART_ENTRY_ALLOCATED_LE;
+
+	le16_add_cpu(&rt->total, 1);
+
+	return e;
+}
+
+#define RESTART_SINGLE_PAGE_IO cpu_to_le16(0x0001)
+
+#define NTFSLOG_WRAPPED 0x00000001
+#define NTFSLOG_MULTIPLE_PAGE_IO 0x00000002
+#define NTFSLOG_NO_LAST_LSN 0x00000004
+#define NTFSLOG_REUSE_TAIL 0x00000010
+#define NTFSLOG_NO_OLDEST_LSN 0x00000020
+
+/*
+ * Helper struct to work with NTFS LogFile
+ */
+struct ntfs_log {
+	struct ntfs_inode *ni;
+
+	u32 l_size;
+	u32 sys_page_size;
+	u32 sys_page_mask;
+	u32 page_size;
+	u32 page_mask; // page_size - 1
+	u8 page_bits;
+	struct RECORD_PAGE_HDR *one_page_buf;
+
+	struct RESTART_TABLE *open_attr_tbl;
+	u32 transaction_id;
+	u32 clst_per_page;
+
+	u32 first_page;
+	u32 next_page;
+	u32 ra_off;
+	u32 data_off;
+	u32 restart_size;
+	u32 data_size;
+	u16 record_header_len;
+	u64 seq_num;
+	u32 seq_num_bits;
+	u32 file_data_bits;
+	u32 seq_num_mask; /* (1 << file_data_bits) - 1 */
+
+	struct RESTART_AREA *ra; /* in-memory image of the next restart area */
+	u32 ra_size; /* the usable size of the restart area */
+
+	/*
+	 * If true, then the in-memory restart area is to be written
+	 * to the first position on the disk
+	 */
+	bool init_ra;
+	bool set_dirty; /* true if we need to set dirty flag */
+
+	u64 oldest_lsn;
+
+	u32 oldest_lsn_off;
+	u64 last_lsn;
+
+	u32 total_avail;
+	u32 total_avail_pages;
+	u32 total_undo_commit;
+	u32 max_current_avail;
+	u32 current_avail;
+	u32 reserved;
+
+	short major_ver;
+	short minor_ver;
+
+	u32 l_flags; /* See NTFSLOG_XXX */
+	u32 current_openlog_count; /* On-disk value for open_log_count */
+
+	struct CLIENT_ID client_id;
+	u32 client_undo_commit;
+};
+
+static inline u32 lsn_to_vbo(struct ntfs_log *log, const u64 lsn)
+{
+	u32 vbo = (lsn << log->seq_num_bits) >> (log->seq_num_bits - 3);
+
+	return vbo;
+}
+
+/* compute the offset in the log file of the next log page */
+static inline u32 next_page_off(struct ntfs_log *log, u32 off)
+{
+	off = (off & ~log->sys_page_mask) + log->page_size;
+	return off >= log->l_size ? log->first_page : off;
+}
+
+static inline u32 lsn_to_page_off(struct ntfs_log *log, u64 lsn)
+{
+	return (((u32)lsn) << 3) & log->page_mask;
+}
+
+static inline u64 vbo_to_lsn(struct ntfs_log *log, u32 off, u64 Seq)
+{
+	return (off >> 3) + (Seq << log->file_data_bits);
+}
+
+static inline bool is_lsn_in_file(struct ntfs_log *log, u64 lsn)
+{
+	return lsn >= log->oldest_lsn &&
+	       lsn <= le64_to_cpu(log->ra->current_lsn);
+}
+
+static inline u32 hdr_file_off(struct ntfs_log *log,
+			       struct RECORD_PAGE_HDR *hdr)
+{
+	if (log->major_ver < 2)
+		return le64_to_cpu(hdr->rhdr.lsn);
+
+	return le32_to_cpu(hdr->file_off);
+}
+
+static inline u64 base_lsn(struct ntfs_log *log,
+			   const struct RECORD_PAGE_HDR *hdr, u64 lsn)
+{
+	u64 h_lsn = le64_to_cpu(hdr->rhdr.lsn);
+	u64 ret = (((h_lsn >> log->file_data_bits) +
+		    (lsn < (lsn_to_vbo(log, h_lsn) & ~log->page_mask) ? 1 : 0))
+		   << log->file_data_bits) +
+		  ((((is_log_record_end(hdr) &&
+		      h_lsn <= le64_to_cpu(hdr->record_hdr.last_end_lsn))
+			     ? le16_to_cpu(hdr->record_hdr.next_record_off)
+			     : log->page_size) +
+		    lsn) >>
+		   3);
+
+	return ret;
+}
+
+static inline bool verify_client_lsn(struct ntfs_log *log,
+				     const struct CLIENT_REC *client, u64 lsn)
+{
+	return lsn >= le64_to_cpu(client->oldest_lsn) &&
+	       lsn <= le64_to_cpu(log->ra->current_lsn) && lsn;
+}
+
+struct restart_info {
+	u64 last_lsn;
+	struct RESTART_HDR *r_page;
+	u32 vbo;
+	bool chkdsk_was_run;
+	bool valid_page;
+	bool initialized;
+	bool restart;
+};
+
+static int read_log_page(struct ntfs_log *log, u32 vbo,
+			 struct RECORD_PAGE_HDR **buffer, bool *usa_error)
+{
+	int err = 0;
+	u32 page_idx = vbo >> log->page_bits;
+	u32 page_off = vbo & log->page_mask;
+	u32 bytes = log->page_size - page_off;
+	void *to_free = NULL;
+	u32 page_vbo = page_idx << log->page_bits;
+	struct RECORD_PAGE_HDR *page_buf;
+	struct ntfs_inode *ni = log->ni;
+	bool bBAAD;
+
+	if (vbo >= log->l_size)
+		return -EINVAL;
+
+	if (!*buffer) {
+		to_free = ntfs_malloc(bytes);
+		if (!to_free)
+			return -ENOMEM;
+		*buffer = to_free;
+	}
+
+	page_buf = page_off ? log->one_page_buf : *buffer;
+
+	err = ntfs_read_run_nb(ni->mi.sbi, &ni->file.run, page_vbo, page_buf,
+			       log->page_size, NULL);
+	if (err)
+		goto out;
+
+	if (page_buf->rhdr.sign != NTFS_FFFF_SIGNATURE)
+		ntfs_fix_post_read(&page_buf->rhdr, PAGE_SIZE, false);
+
+	if (page_buf != *buffer)
+		memcpy(*buffer, Add2Ptr(page_buf, page_off), bytes);
+
+	bBAAD = page_buf->rhdr.sign == NTFS_BAAD_SIGNATURE;
+
+	if (usa_error)
+		*usa_error = bBAAD;
+	/* Check that the update sequence array for this page is valid */
+	/* If we don't allow errors, raise an error status */
+	else if (bBAAD)
+		err = -EINVAL;
+
+out:
+	if (err && to_free) {
+		ntfs_free(to_free);
+		*buffer = NULL;
+	}
+
+	return err;
+}
+
+/*
+ * log_read_rst
+ *
+ * it walks through 512 blocks of the file looking for a valid restart page header
+ * It will stop the first time we find a valid page header
+ */
+static int log_read_rst(struct ntfs_log *log, u32 l_size, bool first,
+			struct restart_info *info)
+{
+	u32 skip, vbo;
+	struct RESTART_HDR *r_page = ntfs_malloc(DefaultLogPageSize);
+
+	if (!r_page)
+		return -ENOMEM;
+
+	memset(info, 0, sizeof(struct restart_info));
+
+	/* Determine which restart area we are looking for */
+	if (first) {
+		vbo = 0;
+		skip = 512;
+	} else {
+		vbo = 512;
+		skip = 0;
+	}
+
+	/* loop continuously until we succeed */
+	for (; vbo < l_size; vbo = 2 * vbo + skip, skip = 0) {
+		bool usa_error;
+		u32 sys_page_size;
+		bool brst, bchk;
+		struct RESTART_AREA *ra;
+
+		/* Read a page header at the current offset */
+		if (read_log_page(log, vbo, (struct RECORD_PAGE_HDR **)&r_page,
+				  &usa_error)) {
+			/* ignore any errors */
+			continue;
+		}
+
+		/* exit if the signature is a log record page */
+		if (r_page->rhdr.sign == NTFS_RCRD_SIGNATURE) {
+			info->initialized = true;
+			break;
+		}
+
+		brst = r_page->rhdr.sign == NTFS_RSTR_SIGNATURE;
+		bchk = r_page->rhdr.sign == NTFS_CHKD_SIGNATURE;
+
+		if (!bchk && !brst) {
+			if (r_page->rhdr.sign != NTFS_FFFF_SIGNATURE) {
+				/*
+				 * Remember if the signature does not
+				 * indicate uninitialized file
+				 */
+				info->initialized = true;
+			}
+			continue;
+		}
+
+		ra = NULL;
+		info->valid_page = false;
+		info->initialized = true;
+		info->vbo = vbo;
+
+		/* Let's check the restart area if this is a valid page */
+		if (!is_rst_page_hdr_valid(vbo, r_page))
+			goto check_result;
+		ra = Add2Ptr(r_page, le16_to_cpu(r_page->ra_off));
+
+		if (!is_rst_area_valid(r_page))
+			goto check_result;
+
+		/*
+		 * We have a valid restart page header and restart area.
+		 * If chkdsk was run or we have no clients then we have
+		 * no more checking to do
+		 */
+		if (bchk || ra->client_idx[1] == LFS_NO_CLIENT_LE) {
+			info->valid_page = true;
+			goto check_result;
+		}
+
+		/* Read the entire restart area */
+		sys_page_size = le32_to_cpu(r_page->sys_page_size);
+		if (DefaultLogPageSize != sys_page_size) {
+			ntfs_free(r_page);
+			r_page = ntfs_zalloc(sys_page_size);
+			if (!r_page)
+				return -ENOMEM;
+
+			if (read_log_page(log, vbo,
+					  (struct RECORD_PAGE_HDR **)&r_page,
+					  &usa_error)) {
+				/* ignore any errors */
+				ntfs_free(r_page);
+				r_page = NULL;
+				continue;
+			}
+		}
+
+		if (is_client_area_valid(r_page, usa_error)) {
+			info->valid_page = true;
+			ra = Add2Ptr(r_page, le16_to_cpu(r_page->ra_off));
+		}
+
+check_result:
+		/* If chkdsk was run then update the caller's values and return */
+		if (r_page->rhdr.sign == NTFS_CHKD_SIGNATURE) {
+			info->chkdsk_was_run = true;
+			info->last_lsn = le64_to_cpu(r_page->rhdr.lsn);
+			info->restart = true;
+			info->r_page = r_page;
+			return 0;
+		}
+
+		/* If we have a valid page then copy the values we need from it */
+		if (info->valid_page) {
+			info->last_lsn = le64_to_cpu(ra->current_lsn);
+			info->restart = true;
+			info->r_page = r_page;
+			return 0;
+		}
+	}
+
+	ntfs_free(r_page);
+
+	return 0;
+}
+
+/*
+ * log_init_pg_hdr
+ *
+ * init "log' from restart page header
+ */
+static void log_init_pg_hdr(struct ntfs_log *log, u32 sys_page_size,
+			    u32 page_size, u16 major_ver, u16 minor_ver)
+{
+	log->sys_page_size = sys_page_size;
+	log->sys_page_mask = sys_page_size - 1;
+	log->page_size = page_size;
+	log->page_mask = page_size - 1;
+	log->page_bits = blksize_bits(page_size);
+
+	log->clst_per_page = log->page_size >> log->ni->mi.sbi->cluster_bits;
+	if (!log->clst_per_page)
+		log->clst_per_page = 1;
+
+	log->first_page = major_ver >= 2
+				  ? 0x22 * page_size
+				  : ((sys_page_size << 1) + (page_size << 1));
+	log->major_ver = major_ver;
+	log->minor_ver = minor_ver;
+}
+
+/*
+ * log_create
+ *
+ * init "log" in cases when we don't have a restart area to use
+ */
+static void log_create(struct ntfs_log *log, u32 l_size, const u64 last_lsn,
+		       u32 open_log_count, bool wrapped, bool use_multi_page)
+{
+	log->l_size = l_size;
+	/* All file offsets must be quadword aligned */
+	log->file_data_bits = blksize_bits(l_size) - 3;
+	log->seq_num_mask = (8 << log->file_data_bits) - 1;
+	log->seq_num_bits = sizeof(u64) * 8 - log->file_data_bits;
+	log->seq_num = (last_lsn >> log->file_data_bits) + 2;
+	log->next_page = log->first_page;
+	log->oldest_lsn = log->seq_num << log->file_data_bits;
+	log->oldest_lsn_off = 0;
+	log->last_lsn = log->oldest_lsn;
+
+	log->l_flags |= NTFSLOG_NO_LAST_LSN | NTFSLOG_NO_OLDEST_LSN;
+
+	/* Set the correct flags for the I/O and indicate if we have wrapped */
+	if (wrapped)
+		log->l_flags |= NTFSLOG_WRAPPED;
+
+	if (use_multi_page)
+		log->l_flags |= NTFSLOG_MULTIPLE_PAGE_IO;
+
+	/* Compute the log page values */
+	log->data_off = QuadAlign(
+		offsetof(struct RECORD_PAGE_HDR, fixups) +
+		sizeof(short) * ((log->page_size >> SECTOR_SHIFT) + 1));
+	log->data_size = log->page_size - log->data_off;
+	log->record_header_len = sizeof(struct LFS_RECORD_HDR);
+
+	/* Remember the different page sizes for reservation */
+	log->reserved = log->data_size - log->record_header_len;
+
+	/* Compute the restart page values. */
+	log->ra_off = QuadAlign(
+		offsetof(struct RESTART_HDR, fixups) +
+		sizeof(short) * ((log->sys_page_size >> SECTOR_SHIFT) + 1));
+	log->restart_size = log->sys_page_size - log->ra_off;
+	log->ra_size = struct_size(log->ra, clients, 1);
+	log->current_openlog_count = open_log_count;
+
+	/*
+	 * The total available log file space is the number of
+	 * log file pages times the space available on each page
+	 */
+	log->total_avail_pages = log->l_size - log->first_page;
+	log->total_avail = log->total_avail_pages >> log->page_bits;
+
+	/*
+	 * We assume that we can't use the end of the page less than
+	 * the file record size
+	 * Then we won't need to reserve more than the caller asks for
+	 */
+	log->max_current_avail = log->total_avail * log->reserved;
+	log->total_avail = log->total_avail * log->data_size;
+	log->current_avail = log->max_current_avail;
+}
+
+/*
+ * log_create_ra
+ *
+ * This routine is called to fill a restart area from the values stored in 'log'
+ */
+static struct RESTART_AREA *log_create_ra(struct ntfs_log *log)
+{
+	struct CLIENT_REC *cr;
+	struct RESTART_AREA *ra = ntfs_zalloc(log->restart_size);
+
+	if (!ra)
+		return NULL;
+
+	ra->current_lsn = cpu_to_le64(log->last_lsn);
+	ra->log_clients = cpu_to_le16(1);
+	ra->client_idx[1] = LFS_NO_CLIENT_LE;
+	if (log->l_flags & NTFSLOG_MULTIPLE_PAGE_IO)
+		ra->flags = RESTART_SINGLE_PAGE_IO;
+	ra->seq_num_bits = cpu_to_le32(log->seq_num_bits);
+	ra->ra_len = cpu_to_le16(log->ra_size);
+	ra->client_off = cpu_to_le16(offsetof(struct RESTART_AREA, clients));
+	ra->l_size = cpu_to_le64(log->l_size);
+	ra->rec_hdr_len = cpu_to_le16(log->record_header_len);
+	ra->data_off = cpu_to_le16(log->data_off);
+	ra->open_log_count = cpu_to_le32(log->current_openlog_count + 1);
+
+	cr = ra->clients;
+
+	cr->prev_client = LFS_NO_CLIENT_LE;
+	cr->next_client = LFS_NO_CLIENT_LE;
+
+	return ra;
+}
+
+static u32 final_log_off(struct ntfs_log *log, u64 lsn, u32 data_len)
+{
+	u32 base_vbo = lsn << 3;
+	u32 final_log_off = (base_vbo & log->seq_num_mask) & ~log->page_mask;
+	u32 page_off = base_vbo & log->page_mask;
+	u32 tail = log->page_size - page_off;
+
+	page_off -= 1;
+
+	/* Add the length of the header */
+	data_len += log->record_header_len;
+
+	/*
+	 * If this lsn is contained this log page we are done
+	 * Otherwise we need to walk through several log pages
+	 */
+	if (data_len > tail) {
+		data_len -= tail;
+		tail = log->data_size;
+		page_off = log->data_off - 1;
+
+		for (;;) {
+			final_log_off = next_page_off(log, final_log_off);
+
+			/* We are done if the remaining bytes fit on this page */
+			if (data_len <= tail)
+				break;
+			data_len -= tail;
+		}
+	}
+
+	/*
+	 * We add the remaining bytes to our starting position on this page
+	 * and then add that value to the file offset of this log page
+	 */
+	return final_log_off + data_len + page_off;
+}
+
+static int next_log_lsn(struct ntfs_log *log, const struct LFS_RECORD_HDR *rh,
+			u64 *lsn)
+{
+	int err;
+	u64 this_lsn = le64_to_cpu(rh->this_lsn);
+	u32 vbo = lsn_to_vbo(log, this_lsn);
+	u32 end =
+		final_log_off(log, this_lsn, le32_to_cpu(rh->client_data_len));
+	u32 hdr_off = end & ~log->sys_page_mask;
+	u64 seq = this_lsn >> log->file_data_bits;
+	struct RECORD_PAGE_HDR *page = NULL;
+
+	/* Remember if we wrapped */
+	if (end <= vbo)
+		seq += 1;
+
+	/* log page header for this page */
+	err = read_log_page(log, hdr_off, &page, NULL);
+	if (err)
+		return err;
+
+	/*
+	 * If the lsn we were given was not the last lsn on this page,
+	 * then the starting offset for the next lsn is on a quad word
+	 * boundary following the last file offset for the current lsn
+	 * Otherwise the file offset is the start of the data on the next page
+	 */
+	if (this_lsn == le64_to_cpu(page->rhdr.lsn)) {
+		/* If we wrapped, we need to increment the sequence number */
+		hdr_off = next_page_off(log, hdr_off);
+		if (hdr_off == log->first_page)
+			seq += 1;
+
+		vbo = hdr_off + log->data_off;
+	} else {
+		vbo = QuadAlign(end);
+	}
+
+	/* Compute the lsn based on the file offset and the sequence count */
+	*lsn = vbo_to_lsn(log, vbo, seq);
+
+	/*
+	 * If this lsn is within the legal range for the file, we return true
+	 * Otherwise false indicates that there are no more lsn's
+	 */
+	if (!is_lsn_in_file(log, *lsn))
+		*lsn = 0;
+
+	ntfs_free(page);
+
+	return 0;
+}
+
+/*
+ * current_log_avail
+ *
+ * calculate the number of bytes available for log records
+ */
+static u32 current_log_avail(struct ntfs_log *log)
+{
+	u32 oldest_off, next_free_off, free_bytes;
+
+	if (log->l_flags & NTFSLOG_NO_LAST_LSN) {
+		/* The entire file is available */
+		return log->max_current_avail;
+	}
+
+	/*
+	 * If there is a last lsn the restart area then we know that we will
+	 * have to compute the free range
+	 * If there is no oldest lsn then start at the first page of the file
+	 */
+	oldest_off = (log->l_flags & NTFSLOG_NO_OLDEST_LSN)
+			     ? log->first_page
+			     : (log->oldest_lsn_off & ~log->sys_page_mask);
+
+	/*
+	 * We will use the next log page offset to compute the next free page\
+	 * If we are going to reuse this page go to the next page
+	 * If we are at the first page then use the end of the file
+	 */
+	next_free_off = (log->l_flags & NTFSLOG_REUSE_TAIL)
+				? log->next_page + log->page_size
+			: log->next_page == log->first_page ? log->l_size
+							    : log->next_page;
+
+	/* If the two offsets are the same then there is no available space */
+	if (oldest_off == next_free_off)
+		return 0;
+	/*
+	 * If the free offset follows the oldest offset then subtract
+	 * this range from the total available pages
+	 */
+	free_bytes =
+		oldest_off < next_free_off
+			? log->total_avail_pages - (next_free_off - oldest_off)
+			: oldest_off - next_free_off;
+
+	free_bytes >>= log->page_bits;
+	return free_bytes * log->reserved;
+}
+
+static bool check_subseq_log_page(struct ntfs_log *log,
+				  const struct RECORD_PAGE_HDR *rp, u32 vbo,
+				  u64 seq)
+{
+	u64 lsn_seq;
+	const struct NTFS_RECORD_HEADER *rhdr = &rp->rhdr;
+	u64 lsn = le64_to_cpu(rhdr->lsn);
+
+	if (rhdr->sign == NTFS_FFFF_SIGNATURE || !rhdr->sign)
+		return false;
+
+	/*
+	 * If the last lsn on the page occurs was written after the page
+	 * that caused the original error then we have a fatal error
+	 */
+	lsn_seq = lsn >> log->file_data_bits;
+
+	/*
+	 * If the sequence number for the lsn the page is equal or greater
+	 * than lsn we expect, then this is a subsequent write
+	 */
+	return lsn_seq >= seq ||
+	       (lsn_seq == seq - 1 && log->first_page == vbo &&
+		vbo != (lsn_to_vbo(log, lsn) & ~log->page_mask));
+}
+
+/*
+ * last_log_lsn
+ *
+ * This routine walks through the log pages for a file, searching for the
+ * last log page written to the file
+ */
+static int last_log_lsn(struct ntfs_log *log)
+{
+	int err;
+	bool usa_error = false;
+	bool replace_page = false;
+	bool reuse_page = log->l_flags & NTFSLOG_REUSE_TAIL;
+	bool wrapped_file, wrapped;
+
+	u32 page_cnt = 1, page_pos = 1;
+	u32 page_off = 0, page_off1 = 0, saved_off = 0;
+	u32 final_off, second_off, final_off_prev = 0, second_off_prev = 0;
+	u32 first_file_off = 0, second_file_off = 0;
+	u32 part_io_count = 0;
+	u32 tails = 0;
+	u32 this_off, curpage_off, nextpage_off, remain_pages;
+
+	u64 expected_seq, seq_base = 0, lsn_base = 0;
+	u64 best_lsn, best_lsn1, best_lsn2;
+	u64 lsn_cur, lsn1, lsn2;
+	u64 last_ok_lsn = reuse_page ? log->last_lsn : 0;
+
+	u16 cur_pos, best_page_pos;
+
+	struct RECORD_PAGE_HDR *page = NULL;
+	struct RECORD_PAGE_HDR *tst_page = NULL;
+	struct RECORD_PAGE_HDR *first_tail = NULL;
+	struct RECORD_PAGE_HDR *second_tail = NULL;
+	struct RECORD_PAGE_HDR *tail_page = NULL;
+	struct RECORD_PAGE_HDR *second_tail_prev = NULL;
+	struct RECORD_PAGE_HDR *first_tail_prev = NULL;
+	struct RECORD_PAGE_HDR *page_bufs = NULL;
+	struct RECORD_PAGE_HDR *best_page;
+
+	if (log->major_ver >= 2) {
+		final_off = 0x02 * log->page_size;
+		second_off = 0x12 * log->page_size;
+
+		// 0x10 == 0x12 - 0x2
+		page_bufs = ntfs_malloc(log->page_size * 0x10);
+		if (!page_bufs)
+			return -ENOMEM;
+	} else {
+		second_off = log->first_page - log->page_size;
+		final_off = second_off - log->page_size;
+	}
+
+next_tail:
+	/* Read second tail page (at pos 3/0x12000) */
+	if (read_log_page(log, second_off, &second_tail, &usa_error) ||
+	    usa_error || second_tail->rhdr.sign != NTFS_RCRD_SIGNATURE) {
+		ntfs_free(second_tail);
+		second_tail = NULL;
+		second_file_off = 0;
+		lsn2 = 0;
+	} else {
+		second_file_off = hdr_file_off(log, second_tail);
+		lsn2 = le64_to_cpu(second_tail->record_hdr.last_end_lsn);
+	}
+
+	/* Read first tail page (at pos 2/0x2000 ) */
+	if (read_log_page(log, final_off, &first_tail, &usa_error) ||
+	    usa_error || first_tail->rhdr.sign != NTFS_RCRD_SIGNATURE) {
+		ntfs_free(first_tail);
+		first_tail = NULL;
+		first_file_off = 0;
+		lsn1 = 0;
+	} else {
+		first_file_off = hdr_file_off(log, first_tail);
+		lsn1 = le64_to_cpu(first_tail->record_hdr.last_end_lsn);
+	}
+
+	if (log->major_ver < 2) {
+		int best_page;
+
+		first_tail_prev = first_tail;
+		final_off_prev = first_file_off;
+		second_tail_prev = second_tail;
+		second_off_prev = second_file_off;
+		tails = 1;
+
+		if (!first_tail && !second_tail)
+			goto tail_read;
+
+		if (first_tail && second_tail)
+			best_page = lsn1 < lsn2 ? 1 : 0;
+		else if (first_tail)
+			best_page = 0;
+		else
+			best_page = 1;
+
+		page_off = best_page ? second_file_off : first_file_off;
+		seq_base = (best_page ? lsn2 : lsn1) >> log->file_data_bits;
+		goto tail_read;
+	}
+
+	best_lsn1 = first_tail ? base_lsn(log, first_tail, first_file_off) : 0;
+	best_lsn2 =
+		second_tail ? base_lsn(log, second_tail, second_file_off) : 0;
+
+	if (first_tail && second_tail) {
+		if (best_lsn1 > best_lsn2) {
+			best_lsn = best_lsn1;
+			best_page = first_tail;
+			this_off = first_file_off;
+		} else {
+			best_lsn = best_lsn2;
+			best_page = second_tail;
+			this_off = second_file_off;
+		}
+	} else if (first_tail) {
+		best_lsn = best_lsn1;
+		best_page = first_tail;
+		this_off = first_file_off;
+	} else if (second_tail) {
+		best_lsn = best_lsn2;
+		best_page = second_tail;
+		this_off = second_file_off;
+	} else {
+		goto tail_read;
+	}
+
+	best_page_pos = le16_to_cpu(best_page->page_pos);
+
+	if (!tails) {
+		if (best_page_pos == page_pos) {
+			seq_base = best_lsn >> log->file_data_bits;
+			saved_off = page_off = le32_to_cpu(best_page->file_off);
+			lsn_base = best_lsn;
+
+			memmove(page_bufs, best_page, log->page_size);
+
+			page_cnt = le16_to_cpu(best_page->page_count);
+			if (page_cnt > 1)
+				page_pos += 1;
+
+			tails = 1;
+		}
+	} else if (seq_base == (best_lsn >> log->file_data_bits) &&
+		   saved_off + log->page_size == this_off &&
+		   lsn_base < best_lsn &&
+		   (page_pos != page_cnt || best_page_pos == page_pos ||
+		    best_page_pos == 1) &&
+		   (page_pos >= page_cnt || best_page_pos == page_pos)) {
+		u16 bppc = le16_to_cpu(best_page->page_count);
+
+		saved_off += log->page_size;
+		lsn_base = best_lsn;
+
+		memmove(Add2Ptr(page_bufs, tails * log->page_size), best_page,
+			log->page_size);
+
+		tails += 1;
+
+		if (best_page_pos != bppc) {
+			page_cnt = bppc;
+			page_pos = best_page_pos;
+
+			if (page_cnt > 1)
+				page_pos += 1;
+		} else {
+			page_pos = page_cnt = 1;
+		}
+	} else {
+		ntfs_free(first_tail);
+		ntfs_free(second_tail);
+		goto tail_read;
+	}
+
+	ntfs_free(first_tail_prev);
+	first_tail_prev = first_tail;
+	final_off_prev = first_file_off;
+	first_tail = NULL;
+
+	ntfs_free(second_tail_prev);
+	second_tail_prev = second_tail;
+	second_off_prev = second_file_off;
+	second_tail = NULL;
+
+	final_off += log->page_size;
+	second_off += log->page_size;
+
+	if (tails < 0x10)
+		goto next_tail;
+tail_read:
+	first_tail = first_tail_prev;
+	final_off = final_off_prev;
+
+	second_tail = second_tail_prev;
+	second_off = second_off_prev;
+
+	page_cnt = page_pos = 1;
+
+	curpage_off = seq_base == log->seq_num ? min(log->next_page, page_off)
+					       : log->next_page;
+
+	wrapped_file =
+		curpage_off == log->first_page &&
+		!(log->l_flags & (NTFSLOG_NO_LAST_LSN | NTFSLOG_REUSE_TAIL));
+
+	expected_seq = wrapped_file ? (log->seq_num + 1) : log->seq_num;
+
+	nextpage_off = curpage_off;
+
+next_page:
+	tail_page = NULL;
+	/* Read the next log page */
+	err = read_log_page(log, curpage_off, &page, &usa_error);
+
+	/* Compute the next log page offset the file */
+	nextpage_off = next_page_off(log, curpage_off);
+	wrapped = nextpage_off == log->first_page;
+
+	if (tails > 1) {
+		struct RECORD_PAGE_HDR *cur_page =
+			Add2Ptr(page_bufs, curpage_off - page_off);
+
+		if (curpage_off == saved_off) {
+			tail_page = cur_page;
+			goto use_tail_page;
+		}
+
+		if (page_off > curpage_off || curpage_off >= saved_off)
+			goto use_tail_page;
+
+		if (page_off1)
+			goto use_cur_page;
+
+		if (!err && !usa_error &&
+		    page->rhdr.sign == NTFS_RCRD_SIGNATURE &&
+		    cur_page->rhdr.lsn == page->rhdr.lsn &&
+		    cur_page->record_hdr.next_record_off ==
+			    page->record_hdr.next_record_off &&
+		    ((page_pos == page_cnt &&
+		      le16_to_cpu(page->page_pos) == 1) ||
+		     (page_pos != page_cnt &&
+		      le16_to_cpu(page->page_pos) == page_pos + 1 &&
+		      le16_to_cpu(page->page_count) == page_cnt))) {
+			cur_page = NULL;
+			goto use_tail_page;
+		}
+
+		page_off1 = page_off;
+
+use_cur_page:
+
+		lsn_cur = le64_to_cpu(cur_page->rhdr.lsn);
+
+		if (last_ok_lsn !=
+			    le64_to_cpu(cur_page->record_hdr.last_end_lsn) &&
+		    ((lsn_cur >> log->file_data_bits) +
+		     ((curpage_off <
+		       (lsn_to_vbo(log, lsn_cur) & ~log->page_mask))
+			      ? 1
+			      : 0)) != expected_seq) {
+			goto check_tail;
+		}
+
+		if (!is_log_record_end(cur_page)) {
+			tail_page = NULL;
+			last_ok_lsn = lsn_cur;
+			goto next_page_1;
+		}
+
+		log->seq_num = expected_seq;
+		log->l_flags &= ~NTFSLOG_NO_LAST_LSN;
+		log->last_lsn = le64_to_cpu(cur_page->record_hdr.last_end_lsn);
+		log->ra->current_lsn = cur_page->record_hdr.last_end_lsn;
+
+		if (log->record_header_len <=
+		    log->page_size -
+			    le16_to_cpu(cur_page->record_hdr.next_record_off)) {
+			log->l_flags |= NTFSLOG_REUSE_TAIL;
+			log->next_page = curpage_off;
+		} else {
+			log->l_flags &= ~NTFSLOG_REUSE_TAIL;
+			log->next_page = nextpage_off;
+		}
+
+		if (wrapped_file)
+			log->l_flags |= NTFSLOG_WRAPPED;
+
+		last_ok_lsn = le64_to_cpu(cur_page->record_hdr.last_end_lsn);
+		goto next_page_1;
+	}
+
+	/*
+	 * If we are at the expected first page of a transfer check to see
+	 * if either tail copy is at this offset
+	 * If this page is the last page of a transfer, check if we wrote
+	 * a subsequent tail copy
+	 */
+	if (page_cnt == page_pos || page_cnt == page_pos + 1) {
+		/*
+		 * Check if the offset matches either the first or second
+		 * tail copy. It is possible it will match both
+		 */
+		if (curpage_off == final_off)
+			tail_page = first_tail;
+
+		/*
+		 * If we already matched on the first page then
+		 * check the ending lsn's.
+		 */
+		if (curpage_off == second_off) {
+			if (!tail_page ||
+			    (second_tail &&
+			     le64_to_cpu(second_tail->record_hdr.last_end_lsn) >
+				     le64_to_cpu(first_tail->record_hdr
+							 .last_end_lsn))) {
+				tail_page = second_tail;
+			}
+		}
+	}
+
+use_tail_page:
+	if (tail_page) {
+		/* we have a candidate for a tail copy */
+		lsn_cur = le64_to_cpu(tail_page->record_hdr.last_end_lsn);
+
+		if (last_ok_lsn < lsn_cur) {
+			/*
+			 * If the sequence number is not expected,
+			 * then don't use the tail copy
+			 */
+			if (expected_seq != (lsn_cur >> log->file_data_bits))
+				tail_page = NULL;
+		} else if (last_ok_lsn > lsn_cur) {
+			/*
+			 * If the last lsn is greater than the one on
+			 * this page then forget this tail
+			 */
+			tail_page = NULL;
+		}
+	}
+
+	/* If we have an error on the current page, we will break of this loop */
+	if (err || usa_error)
+		goto check_tail;
+
+	/*
+	 * Done if the last lsn on this page doesn't match the previous known
+	 * last lsn or the sequence number is not expected
+	 */
+	lsn_cur = le64_to_cpu(page->rhdr.lsn);
+	if (last_ok_lsn != lsn_cur &&
+	    expected_seq != (lsn_cur >> log->file_data_bits)) {
+		goto check_tail;
+	}
+
+	/*
+	 * Check that the page position and page count values are correct
+	 * If this is the first page of a transfer the position must be 1
+	 * and the count will be unknown
+	 */
+	if (page_cnt == page_pos) {
+		if (page->page_pos != cpu_to_le16(1) &&
+		    (!reuse_page || page->page_pos != page->page_count)) {
+			/*
+			 * If the current page is the first page we are
+			 * looking at and we are reusing this page then
+			 * it can be either the first or last page of a
+			 * transfer. Otherwise it can only be the first.
+			 */
+			goto check_tail;
+		}
+	} else if (le16_to_cpu(page->page_count) != page_cnt ||
+		   le16_to_cpu(page->page_pos) != page_pos + 1) {
+		/*
+		 * The page position better be 1 more than the last page
+		 * position and the page count better match
+		 */
+		goto check_tail;
+	}
+
+	/*
+	 * We have a valid page the file and may have a valid page
+	 * the tail copy area
+	 * If the tail page was written after the page the file then
+	 * break of the loop
+	 */
+	if (tail_page &&
+	    le64_to_cpu(tail_page->record_hdr.last_end_lsn) > lsn_cur) {
+		/* Remember if we will replace the page */
+		replace_page = true;
+		goto check_tail;
+	}
+
+	tail_page = NULL;
+
+	if (is_log_record_end(page)) {
+		/*
+		 * Since we have read this page we know the sequence number
+		 * is the same as our expected value
+		 */
+		log->seq_num = expected_seq;
+		log->last_lsn = le64_to_cpu(page->record_hdr.last_end_lsn);
+		log->ra->current_lsn = page->record_hdr.last_end_lsn;
+		log->l_flags &= ~NTFSLOG_NO_LAST_LSN;
+
+		/*
+		 * If there is room on this page for another header then
+		 * remember we want to reuse the page
+		 */
+		if (log->record_header_len <=
+		    log->page_size -
+			    le16_to_cpu(page->record_hdr.next_record_off)) {
+			log->l_flags |= NTFSLOG_REUSE_TAIL;
+			log->next_page = curpage_off;
+		} else {
+			log->l_flags &= ~NTFSLOG_REUSE_TAIL;
+			log->next_page = nextpage_off;
+		}
+
+		/* Remember if we wrapped the log file */
+		if (wrapped_file)
+			log->l_flags |= NTFSLOG_WRAPPED;
+	}
+
+	/*
+	 * Remember the last page count and position.
+	 * Also remember the last known lsn
+	 */
+	page_cnt = le16_to_cpu(page->page_count);
+	page_pos = le16_to_cpu(page->page_pos);
+	last_ok_lsn = le64_to_cpu(page->rhdr.lsn);
+
+next_page_1:
+
+	if (wrapped) {
+		expected_seq += 1;
+		wrapped_file = 1;
+	}
+
+	curpage_off = nextpage_off;
+	ntfs_free(page);
+	page = NULL;
+	reuse_page = 0;
+	goto next_page;
+
+check_tail:
+	if (tail_page) {
+		log->seq_num = expected_seq;
+		log->last_lsn = le64_to_cpu(tail_page->record_hdr.last_end_lsn);
+		log->ra->current_lsn = tail_page->record_hdr.last_end_lsn;
+		log->l_flags &= ~NTFSLOG_NO_LAST_LSN;
+
+		if (log->page_size -
+			    le16_to_cpu(
+				    tail_page->record_hdr.next_record_off) >=
+		    log->record_header_len) {
+			log->l_flags |= NTFSLOG_REUSE_TAIL;
+			log->next_page = curpage_off;
+		} else {
+			log->l_flags &= ~NTFSLOG_REUSE_TAIL;
+			log->next_page = nextpage_off;
+		}
+
+		if (wrapped)
+			log->l_flags |= NTFSLOG_WRAPPED;
+	}
+
+	/* Remember that the partial IO will start at the next page */
+	second_off = nextpage_off;
+
+	/*
+	 * If the next page is the first page of the file then update
+	 * the sequence number for log records which begon the next page
+	 */
+	if (wrapped)
+		expected_seq += 1;
+
+	/*
+	 * If we have a tail copy or are performing single page I/O we can
+	 * immediately look at the next page
+	 */
+	if (replace_page || (log->ra->flags & RESTART_SINGLE_PAGE_IO)) {
+		page_cnt = 2;
+		page_pos = 1;
+		goto check_valid;
+	}
+
+	if (page_pos != page_cnt)
+		goto check_valid;
+	/*
+	 * If the next page causes us to wrap to the beginning of the log
+	 * file then we know which page to check next.
+	 */
+	if (wrapped) {
+		page_cnt = 2;
+		page_pos = 1;
+		goto check_valid;
+	}
+
+	cur_pos = 2;
+
+next_test_page:
+	ntfs_free(tst_page);
+	tst_page = NULL;
+
+	/* Walk through the file, reading log pages */
+	err = read_log_page(log, nextpage_off, &tst_page, &usa_error);
+
+	/*
+	 * If we get a USA error then assume that we correctly found
+	 * the end of the original transfer
+	 */
+	if (usa_error)
+		goto file_is_valid;
+
+	/*
+	 * If we were able to read the page, we examine it to see if it
+	 * is the same or different Io block
+	 */
+	if (err)
+		goto next_test_page_1;
+
+	if (le16_to_cpu(tst_page->page_pos) == cur_pos &&
+	    check_subseq_log_page(log, tst_page, nextpage_off, expected_seq)) {
+		page_cnt = le16_to_cpu(tst_page->page_count) + 1;
+		page_pos = le16_to_cpu(tst_page->page_pos);
+		goto check_valid;
+	} else {
+		goto file_is_valid;
+	}
+
+next_test_page_1:
+
+	nextpage_off = next_page_off(log, curpage_off);
+	wrapped = nextpage_off == log->first_page;
+
+	if (wrapped) {
+		expected_seq += 1;
+		page_cnt = 2;
+		page_pos = 1;
+	}
+
+	cur_pos += 1;
+	part_io_count += 1;
+	if (!wrapped)
+		goto next_test_page;
+
+check_valid:
+	/* Skip over the remaining pages this transfer */
+	remain_pages = page_cnt - page_pos - 1;
+	part_io_count += remain_pages;
+
+	while (remain_pages--) {
+		nextpage_off = next_page_off(log, curpage_off);
+		wrapped = nextpage_off == log->first_page;
+
+		if (wrapped)
+			expected_seq += 1;
+	}
+
+	/* Call our routine to check this log page */
+	ntfs_free(tst_page);
+	tst_page = NULL;
+
+	err = read_log_page(log, nextpage_off, &tst_page, &usa_error);
+	if (!err && !usa_error &&
+	    check_subseq_log_page(log, tst_page, nextpage_off, expected_seq)) {
+		err = -EINVAL;
+		goto out;
+	}
+
+file_is_valid:
+
+	/* We have a valid file */
+	if (page_off1 || tail_page) {
+		struct RECORD_PAGE_HDR *tmp_page;
+
+		if (sb_rdonly(log->ni->mi.sbi->sb)) {
+			err = -EROFS;
+			goto out;
+		}
+
+		if (page_off1) {
+			tmp_page = Add2Ptr(page_bufs, page_off1 - page_off);
+			tails -= (page_off1 - page_off) / log->page_size;
+			if (!tail_page)
+				tails -= 1;
+		} else {
+			tmp_page = tail_page;
+			tails = 1;
+		}
+
+		while (tails--) {
+			u64 off = hdr_file_off(log, tmp_page);
+
+			if (!page) {
+				page = ntfs_malloc(log->page_size);
+				if (!page)
+					return -ENOMEM;
+			}
+
+			/*
+			 * Correct page and copy the data from this page
+			 * into it and flush it to disk
+			 */
+			memcpy(page, tmp_page, log->page_size);
+
+			/* Fill last flushed lsn value flush the page */
+			if (log->major_ver < 2)
+				page->rhdr.lsn = page->record_hdr.last_end_lsn;
+			else
+				page->file_off = 0;
+
+			page->page_pos = page->page_count = cpu_to_le16(1);
+
+			ntfs_fix_pre_write(&page->rhdr, log->page_size);
+
+			err = ntfs_sb_write_run(log->ni->mi.sbi,
+						&log->ni->file.run, off, page,
+						log->page_size);
+
+			if (err)
+				goto out;
+
+			if (part_io_count && second_off == off) {
+				second_off += log->page_size;
+				part_io_count -= 1;
+			}
+
+			tmp_page = Add2Ptr(tmp_page, log->page_size);
+		}
+	}
+
+	if (part_io_count) {
+		if (sb_rdonly(log->ni->mi.sbi->sb)) {
+			err = -EROFS;
+			goto out;
+		}
+	}
+
+out:
+	ntfs_free(second_tail);
+	ntfs_free(first_tail);
+	ntfs_free(page);
+	ntfs_free(tst_page);
+	ntfs_free(page_bufs);
+
+	return err;
+}
+
+/*
+ * read_log_rec_buf
+ *
+ * copies a log record from the file to a buffer
+ * The log record may span several log pages and may even wrap the file
+ */
+static int read_log_rec_buf(struct ntfs_log *log,
+			    const struct LFS_RECORD_HDR *rh, void *buffer)
+{
+	int err;
+	struct RECORD_PAGE_HDR *ph = NULL;
+	u64 lsn = le64_to_cpu(rh->this_lsn);
+	u32 vbo = lsn_to_vbo(log, lsn) & ~log->page_mask;
+	u32 off = lsn_to_page_off(log, lsn) + log->record_header_len;
+	u32 data_len = le32_to_cpu(rh->client_data_len);
+
+	/*
+	 * While there are more bytes to transfer,
+	 * we continue to attempt to perform the read
+	 */
+	for (;;) {
+		bool usa_error;
+		u32 tail = log->page_size - off;
+
+		if (tail >= data_len)
+			tail = data_len;
+
+		data_len -= tail;
+
+		err = read_log_page(log, vbo, &ph, &usa_error);
+		if (err)
+			goto out;
+
+		/*
+		 * The last lsn on this page better be greater or equal
+		 * to the lsn we are copying
+		 */
+		if (lsn > le64_to_cpu(ph->rhdr.lsn)) {
+			err = -EINVAL;
+			goto out;
+		}
+
+		memcpy(buffer, Add2Ptr(ph, off), tail);
+
+		...
 
[truncated message content]

Thread: [Linux-NTFS-Dev] [PATCH v26 07/10] fs/ntfs3: Add NTFS journal (Page 13)

Development moved to https://sourceforge.net/projects/ntfs-3g/

linux-ntfs-dev