From patchwork Fri Oct 9 14:22:52 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Konstantin Komarov X-Patchwork-Id: 11825943 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id CCD1614D5 for ; Fri, 9 Oct 2020 14:23:13 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 8495822365 for ; Fri, 9 Oct 2020 14:23:13 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (1024-bit key) header.d=paragon-software.com header.i=@paragon-software.com header.b="K8iqEAyu" Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S2388714AbgJIOXM (ORCPT ); Fri, 9 Oct 2020 10:23:12 -0400 Received: from relayfre-01.paragon-software.com ([176.12.100.13]:52088 "EHLO relayfre-01.paragon-software.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1731820AbgJIOXK (ORCPT ); Fri, 9 Oct 2020 10:23:10 -0400 Received: from dlg2.mail.paragon-software.com (vdlg-exch-02.paragon-software.com [172.30.1.105]) by relayfre-01.paragon-software.com (Postfix) with ESMTPS id 7E2F52118; Fri, 9 Oct 2020 17:23:07 +0300 (MSK) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=paragon-software.com; s=mail; t=1602253387; bh=Pb9YHvLAO/0hWDGmlW7R79g1VHpSm634mCFbEwLP8Zk=; h=From:To:CC:Subject:Date:In-Reply-To:References; b=K8iqEAyubrQJM+W04JG2mtsaqJsZb/lZ8Ui7Eh3rVOGV3puyP9UaVcoUi7eGqvh+e Z1kLrDV7/XjxPTWmbGEqKcyDHt1pWJQVvCIrkTb10njKDjGQEJcaA79R6uw9JsfXRz yL1sNcLGHP8QBhBDEA4Q5bV387EY4BILZntXoDnE= Received: from fsd-lkpg.ufsd.paragon-software.com (172.30.114.105) by vdlg-exch-02.paragon-software.com (172.30.1.105) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id 15.1.1847.3; Fri, 9 Oct 2020 17:23:06 +0300 From: Konstantin Komarov To: CC: , , , , , , , , , , , , Konstantin Komarov Subject: [PATCH v8 01/10] fs/ntfs3: Add headers and misc files Date: Fri, 9 Oct 2020 17:22:52 +0300 Message-ID: <20201009142301.412454-2-almaz.alexandrovich@paragon-software.com> X-Mailer: git-send-email 2.25.4 In-Reply-To: <20201009142301.412454-1-almaz.alexandrovich@paragon-software.com> References: <20201009142301.412454-1-almaz.alexandrovich@paragon-software.com> MIME-Version: 1.0 X-Originating-IP: [172.30.114.105] X-ClientProxiedBy: vdlg-exch-02.paragon-software.com (172.30.1.105) To vdlg-exch-02.paragon-software.com (172.30.1.105) Precedence: bulk List-ID: X-Mailing-List: linux-fsdevel@vger.kernel.org This adds headers and misc files Signed-off-by: Konstantin Komarov --- fs/ntfs3/debug.h | 62 +++ fs/ntfs3/ntfs.h | 1295 ++++++++++++++++++++++++++++++++++++++++++++ fs/ntfs3/ntfs_fs.h | 984 +++++++++++++++++++++++++++++++++ fs/ntfs3/upcase.c | 78 +++ 4 files changed, 2419 insertions(+) create mode 100644 fs/ntfs3/debug.h create mode 100644 fs/ntfs3/ntfs.h create mode 100644 fs/ntfs3/ntfs_fs.h create mode 100644 fs/ntfs3/upcase.c diff --git a/fs/ntfs3/debug.h b/fs/ntfs3/debug.h new file mode 100644 index 000000000000..b23cae11eba7 --- /dev/null +++ b/fs/ntfs3/debug.h @@ -0,0 +1,62 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * linux/fs/ntfs3/debug.h + * + * Copyright (C) 2019-2020 Paragon Software GmbH, All rights reserved. + * + * useful functions for debuging + */ + +// clang-format off +#ifndef Add2Ptr +#define Add2Ptr(P, I) (void *)((u8 *)(P) + (I)) +#define PtrOffset(B, O) ((size_t)((size_t)(O) - (size_t)(B))) +#endif + +#define QuadAlign(n) (((n) + 7u) & (~7u)) +#define IsQuadAligned(n) (!((size_t)(n)&7u)) +#define Quad2Align(n) (((n) + 15u) & (~15u)) +#define IsQuad2Aligned(n) (!((size_t)(n)&15u)) +#define Quad4Align(n) (((n) + 31u) & (~31u)) +#define IsSizeTAligned(n) (!((size_t)(n) & (sizeof(size_t) - 1))) +#define DwordAlign(n) (((n) + 3u) & (~3u)) +#define IsDwordAligned(n) (!((size_t)(n)&3u)) +#define WordAlign(n) (((n) + 1u) & (~1u)) +#define IsWordAligned(n) (!((size_t)(n)&1u)) +// clang-format on + +#ifdef CONFIG_PRINTK +__printf(2, 3) void ntfs_printk(const struct super_block *sb, const char *fmt, + ...); +__printf(2, 3) void ntfs_inode_printk(struct inode *inode, const char *fmt, + ...); +#else +static inline __printf(2, 3) void ntfs_printk(const struct super_block *sb, + const char *fmt, ...) +{ +} + +static inline __printf(2, 3) void ntfs_inode_printk(struct inode *inode, + const char *fmt, ...) +{ +} +#endif + +/* + * Logging macros ( thanks Joe Perches for implementation ) + */ + +#define ntfs_err(sb, fmt, ...) ntfs_printk(sb, KERN_ERR fmt, ##__VA_ARGS__) +#define ntfs_warn(sb, fmt, ...) ntfs_printk(sb, KERN_WARNING fmt, ##__VA_ARGS__) +#define ntfs_info(sb, fmt, ...) ntfs_printk(sb, KERN_INFO fmt, ##__VA_ARGS__) +#define ntfs_notice(sb, fmt, ...) \ + ntfs_printk(sb, KERN_NOTICE fmt, ##__VA_ARGS__) + +#define ntfs_inode_err(inode, fmt, ...) \ + ntfs_inode_printk(inode, KERN_ERR fmt, ##__VA_ARGS__) +#define ntfs_inode_warn(inode, fmt, ...) \ + ntfs_inode_printk(inode, KERN_WARNING fmt, ##__VA_ARGS__) + +#define ntfs_alloc(s, z) kmalloc(s, z ? (GFP_NOFS | __GFP_ZERO) : GFP_NOFS) +#define ntfs_free(p) kfree(p) +#define ntfs_memdup(src, len) kmemdup(src, len, GFP_NOFS) diff --git a/fs/ntfs3/ntfs.h b/fs/ntfs3/ntfs.h new file mode 100644 index 000000000000..645a492fc1b9 --- /dev/null +++ b/fs/ntfs3/ntfs.h @@ -0,0 +1,1295 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * linux/fs/ntfs3/ntfs.h + * + * Copyright (C) 2019-2020 Paragon Software GmbH, All rights reserved. + * + * on-disk ntfs structs + */ + +/* TODO: + * - Check 4K mft record and 512 bytes cluster + */ + +/* + * Activate this define to use binary search in indexes + */ +#define NTFS3_INDEX_BINARY_SEARCH + +/* + * Check each run for marked clusters + */ +#define NTFS3_CHECK_FREE_CLST + +#define NTFS_NAME_LEN 255 + +/* + * ntfs.sys used 500 maximum links + * on-disk struct allows up to 0xffff + */ +#define NTFS_LINK_MAX 0x400 +//#define NTFS_LINK_MAX 0xffff + +/* + * Activate to use 64 bit clusters instead of 32 bits in ntfs.sys + * Logical and virtual cluster number + * If needed, may be redefined to use 64 bit value + */ +//#define NTFS3_64BIT_CLUSTER + +#define NTFS_LZNT_MAX_CLUSTER 4096 +#define NTFS_LZNT_CUNIT 4 + +struct GUID { + __le32 Data1; + __le16 Data2; + __le16 Data3; + u8 Data4[8]; +}; + +/* + * this struct repeats layout of ATTR_FILE_NAME + * at offset 0x40 + * it used to store global constants NAME_MFT/NAME_MIRROR... + * most constant names are shorter than 10 + */ +struct cpu_str { + u8 len; + u8 unused; + u16 name[10]; +}; + +struct le_str { + u8 len; + u8 unused; + __le16 name[1]; +}; + +static_assert(SECTOR_SHIFT == 9); + +#ifdef NTFS3_64BIT_CLUSTER +typedef u64 CLST; +static_assert(sizeof(size_t) == 8); +#else +typedef u32 CLST; +#endif + +#define SPARSE_LCN ((CLST)-1) +#define RESIDENT_LCN ((CLST)-2) +#define COMPRESSED_LCN ((CLST)-3) + +#define COMPRESSION_UNIT 4 +#define COMPRESS_MAX_CLUSTER 0x1000 +#define MFT_INCREASE_CHUNK 1024 + +enum RECORD_NUM { + MFT_REC_MFT = 0, + MFT_REC_MIRR = 1, + MFT_REC_LOG = 2, + MFT_REC_VOL = 3, + MFT_REC_ATTR = 4, + MFT_REC_ROOT = 5, + MFT_REC_BITMAP = 6, + MFT_REC_BOOT = 7, + MFT_REC_BADCLUST = 8, + MFT_REC_QUOTA = 9, + MFT_REC_SECURE = 9, // NTFS 3.0 + MFT_REC_UPCASE = 10, + MFT_REC_EXTEND = 11, // NTFS 3.0 + MFT_REC_RESERVED = 11, + MFT_REC_FREE = 16, + MFT_REC_USER = 24, +}; + +enum ATTR_TYPE { + ATTR_ZERO = cpu_to_le32(0x00), + ATTR_STD = cpu_to_le32(0x10), + ATTR_LIST = cpu_to_le32(0x20), + ATTR_NAME = cpu_to_le32(0x30), + // ATTR_VOLUME_VERSION on Nt4 + ATTR_ID = cpu_to_le32(0x40), + ATTR_SECURE = cpu_to_le32(0x50), + ATTR_LABEL = cpu_to_le32(0x60), + ATTR_VOL_INFO = cpu_to_le32(0x70), + ATTR_DATA = cpu_to_le32(0x80), + ATTR_ROOT = cpu_to_le32(0x90), + ATTR_ALLOC = cpu_to_le32(0xA0), + ATTR_BITMAP = cpu_to_le32(0xB0), + // ATTR_SYMLINK on Nt4 + ATTR_REPARSE = cpu_to_le32(0xC0), + ATTR_EA_INFO = cpu_to_le32(0xD0), + ATTR_EA = cpu_to_le32(0xE0), + ATTR_PROPERTYSET = cpu_to_le32(0xF0), + ATTR_LOGGED_UTILITY_STREAM = cpu_to_le32(0x100), + ATTR_END = cpu_to_le32(0xFFFFFFFF) +}; + +static_assert(sizeof(enum ATTR_TYPE) == 4); + +enum FILE_ATTRIBUTE { + FILE_ATTRIBUTE_READONLY = cpu_to_le32(0x00000001), + FILE_ATTRIBUTE_HIDDEN = cpu_to_le32(0x00000002), + FILE_ATTRIBUTE_SYSTEM = cpu_to_le32(0x00000004), + FILE_ATTRIBUTE_ARCHIVE = cpu_to_le32(0x00000020), + FILE_ATTRIBUTE_DEVICE = cpu_to_le32(0x00000040), + + FILE_ATTRIBUTE_TEMPORARY = cpu_to_le32(0x00000100), + FILE_ATTRIBUTE_SPARSE_FILE = cpu_to_le32(0x00000200), + FILE_ATTRIBUTE_REPARSE_POINT = cpu_to_le32(0x00000400), + FILE_ATTRIBUTE_COMPRESSED = cpu_to_le32(0x00000800), + + FILE_ATTRIBUTE_OFFLINE = cpu_to_le32(0x00001000), + FILE_ATTRIBUTE_NOT_CONTENT_INDEXED = cpu_to_le32(0x00002000), + FILE_ATTRIBUTE_ENCRYPTED = cpu_to_le32(0x00004000), + + FILE_ATTRIBUTE_VALID_FLAGS = cpu_to_le32(0x00007fb7), + + FILE_ATTRIBUTE_DIRECTORY = cpu_to_le32(0x10000000), +}; + +static_assert(sizeof(enum FILE_ATTRIBUTE) == 4); + +extern const struct cpu_str NAME_MFT; // L"$MFT" +extern const struct cpu_str NAME_MIRROR; // L"$MFTMirr" +extern const struct cpu_str NAME_LOGFILE; // L"$LogFile" +extern const struct cpu_str NAME_VOLUME; // L"$Volume" +extern const struct cpu_str NAME_ATTRDEF; // L"$AttrDef" +extern const struct cpu_str NAME_ROOT; // L"." +extern const struct cpu_str NAME_BITMAP; // L"$Bitmap" +extern const struct cpu_str NAME_BOOT; // L"$Boot" +extern const struct cpu_str NAME_BADCLUS; // L"$BadClus" +extern const struct cpu_str NAME_QUOTA; // L"$Quota" +extern const struct cpu_str NAME_SECURE; // L"$Secure" +extern const struct cpu_str NAME_UPCASE; // L"$UpCase" +extern const struct cpu_str NAME_EXTEND; // L"$Extend" +extern const struct cpu_str NAME_OBJID; // L"$ObjId" +extern const struct cpu_str NAME_REPARSE; // L"$Reparse" +extern const struct cpu_str NAME_USNJRNL; // L"$UsnJrnl" +extern const struct cpu_str NAME_UGM; // L"$UGM" + +extern const __le16 I30_NAME[4]; // L"$I30" +extern const __le16 SII_NAME[4]; // L"$SII" +extern const __le16 SDH_NAME[4]; // L"$SDH" +extern const __le16 SO_NAME[2]; // L"$O" +extern const __le16 SQ_NAME[2]; // L"$Q" +extern const __le16 SR_NAME[2]; // L"$R" + +extern const __le16 BAD_NAME[4]; // L"$Bad" +extern const __le16 SDS_NAME[4]; // L"$SDS" +extern const __le16 EFS_NAME[4]; // L"$EFS" +extern const __le16 WOF_NAME[17]; // L"WofCompressedData" +extern const __le16 J_NAME[2]; // L"$J" +extern const __le16 MAX_NAME[4]; // L"$Max" + +/* MFT record number structure */ +struct MFT_REF { + __le32 low; // The low part of the number + __le16 high; // The high part of the number + __le16 seq; // The sequence number of MFT record +}; + +static_assert(sizeof(__le64) == sizeof(struct MFT_REF)); + +static inline CLST ino_get(const struct MFT_REF *ref) +{ +#ifdef NTFS3_64BIT_CLUSTER + return le32_to_cpu(ref->low) | ((u64)le16_to_cpu(ref->high) << 32); +#else + return le32_to_cpu(ref->low); +#endif +} + +struct NTFS_BOOT { + u8 jump_code[3]; // 0x00: Jump to boot code + u8 system_id[8]; // 0x03: System ID, equals "NTFS " + + // NOTE: this member is not aligned(!) + // bytes_per_sector[0] must be 0 + // bytes_per_sector[1] must be multiplied by 256 + u8 bytes_per_sector[2]; // 0x0B: Bytes per sector + + u8 sectors_per_clusters; // 0x0D: Sectors per cluster + u8 unused1[7]; + u8 media_type; // 0x15: Media type (0xF8 - harddisk) + u8 unused2[2]; + __le16 secotrs_per_track; // 0x18: number of sectors per track + __le16 heads; // 0x1A: number of heads per cylinder + __le32 hidden_sectors; // 0x1C: number of 'hidden' sectors + u8 unused3[4]; + u8 bios_drive_num; // 0x24: BIOS drive number =0x80 + u8 unused4; + u8 signature_ex; // 0x26: Extended BOOT signature =0x80 + u8 unused5; + __le64 sectors_per_volume; // 0x28: size of volume in sectors + __le64 mft_clst; // 0x30: first cluster of $MFT + __le64 mft2_clst; // 0x38: first cluster of $MFTMirr + s8 record_size; // 0x40: size of MFT record in clusters(sectors) + u8 unused6[3]; + s8 index_size; // 0x44: size of INDX record in clusters(sectors) + u8 unused7[3]; + __le64 serial_num; // 0x48: Volume serial number + __le32 check_sum; // 0x50: Simple additive checksum of all of the u32's which + // precede the 'check_sum' + + u8 boot_code[0x200 - 0x50 - 2 - 4]; // 0x54: + u8 boot_magic[2]; // 0x1FE: Boot signature =0x55 + 0xAA +}; + +static_assert(sizeof(struct NTFS_BOOT) == 0x200); + +enum NTFS_SIGNATURE { + NTFS_FILE_SIGNATURE = cpu_to_le32(0x454C4946), // 'FILE' + NTFS_INDX_SIGNATURE = cpu_to_le32(0x58444E49), // 'INDX' + NTFS_CHKD_SIGNATURE = cpu_to_le32(0x444B4843), // 'CHKD' + NTFS_RSTR_SIGNATURE = cpu_to_le32(0x52545352), // 'RSTR' + NTFS_RCRD_SIGNATURE = cpu_to_le32(0x44524352), // 'RCRD' + NTFS_BAAD_SIGNATURE = cpu_to_le32(0x44414142), // 'BAAD' + NTFS_HOLE_SIGNATURE = cpu_to_le32(0x454C4F48), // 'HOLE' + NTFS_FFFF_SIGNATURE = cpu_to_le32(0xffffffff), +}; + +static_assert(sizeof(enum NTFS_SIGNATURE) == 4); + +/* MFT Record header structure */ +struct NTFS_RECORD_HEADER { + /* Record magic number, equals 'FILE'/'INDX'/'RSTR'/'RCRD' */ + enum NTFS_SIGNATURE sign; // 0x00: + __le16 fix_off; // 0x04: + __le16 fix_num; // 0x06: + __le64 lsn; // 0x08: Log file sequence number +}; + +static_assert(sizeof(struct NTFS_RECORD_HEADER) == 0x10); + +static inline int is_baad(const struct NTFS_RECORD_HEADER *hdr) +{ + return hdr->sign == NTFS_BAAD_SIGNATURE; +} + +/* Possible bits in struct MFT_REC.flags */ +enum RECORD_FLAG { + RECORD_FLAG_IN_USE = cpu_to_le16(0x0001), + RECORD_FLAG_DIR = cpu_to_le16(0x0002), + RECORD_FLAG_SYSTEM = cpu_to_le16(0x0004), + RECORD_FLAG_UNKNOWN = cpu_to_le16(0x0008), +}; + +/* MFT Record structure */ +struct MFT_REC { + struct NTFS_RECORD_HEADER rhdr; // 'FILE' + + __le16 seq; // 0x10: Sequence number for this record + __le16 hard_links; // 0x12: The number of hard links to record + __le16 attr_off; // 0x14: Offset to attributes + __le16 flags; // 0x16: 1=non-resident, 2=dir. See RECORD_FLAG_XXX + __le32 used; // 0x18: The size of used part + __le32 total; // 0x1C: Total record size + + struct MFT_REF parent_ref; // 0x20: Parent MFT record + __le16 next_attr_id; // 0x28: The next attribute Id + + // + // NTFS of version 3.1 uses this record header + // if fix_off >= 0x30 + + __le16 Res; // 0x2A: ? High part of MftRecord + __le32 MftRecord; // 0x2C: Current record number + __le16 Fixups[1]; // 0x30: +}; + +#define MFTRECORD_FIXUP_OFFSET_1 offsetof(struct MFT_REC, Res) +#define MFTRECORD_FIXUP_OFFSET_3 offsetof(struct MFT_REC, Fixups) + +static_assert(MFTRECORD_FIXUP_OFFSET_1 == 0x2A); +static_assert(MFTRECORD_FIXUP_OFFSET_3 == 0x30); + +static inline bool is_rec_base(const struct MFT_REC *rec) +{ + const struct MFT_REF *r = &rec->parent_ref; + + return !r->low && !r->high && !r->seq; +} + +static inline bool is_mft_rec5(const struct MFT_REC *rec) +{ + return le16_to_cpu(rec->rhdr.fix_off) >= + offsetof(struct MFT_REC, Fixups); +} + +static inline bool is_rec_inuse(const struct MFT_REC *rec) +{ + return rec->flags & RECORD_FLAG_IN_USE; +} + +static inline bool clear_rec_inuse(struct MFT_REC *rec) +{ + return rec->flags &= ~RECORD_FLAG_IN_USE; +} + +/* Possible values of ATTR_RESIDENT.flags */ +#define RESIDENT_FLAG_INDEXED 0x01 + +struct ATTR_RESIDENT { + __le32 data_size; // 0x10: The size of data + __le16 data_off; // 0x14: Offset to data + u8 flags; // 0x16: resident flags ( 1 - indexed ) + u8 res; // 0x17: +}; // sizeof() = 0x18 + +struct ATTR_NONRESIDENT { + __le64 svcn; // 0x10: Starting VCN of this segment + __le64 evcn; // 0x18: End VCN of this segment + __le16 run_off; // 0x20: Offset to packed runs + // Unit of Compression size for this stream, expressed + // as a log of the cluster size. + // + // 0 means file is not compressed + // 1, 2, 3, and 4 are potentially legal values if the + // stream is compressed, however the implementation + // may only choose to use 4, or possibly 3. Note + // that 4 means cluster size time 16. If convenient + // the implementation may wish to accept a + // reasonable range of legal values here (1-5?), + // even if the implementation only generates + // a smaller set of values itself. + u8 c_unit; // 0x22 + u8 res1[5]; // 0x23: + __le64 alloc_size; // 0x28: The allocated size of attribute in bytes + // (multiple of cluster size) + __le64 data_size; // 0x30: The size of attribute in bytes <= alloc_size + __le64 valid_size; // 0x38: The size of valid part in bytes <= data_size + __le64 total_size; // 0x40: The sum of the allocated clusters for a file + // (present only for the first segment (0 == vcn) + // of compressed attribute) + +}; // sizeof()=0x40 or 0x48 (if compressed) + +/* Possible values of ATTRIB.flags: */ +#define ATTR_FLAG_COMPRESSED cpu_to_le16(0x0001) +#define ATTR_FLAG_COMPRESSED_MASK cpu_to_le16(0x00FF) +#define ATTR_FLAG_ENCRYPTED cpu_to_le16(0x4000) +#define ATTR_FLAG_SPARSED cpu_to_le16(0x8000) + +struct ATTRIB { + enum ATTR_TYPE type; // 0x00: The type of this attribute + __le32 size; // 0x04: The size of this attribute + u8 non_res; // 0x08: Is this attribute non-resident ? + u8 name_len; // 0x09: This attribute name length + __le16 name_off; // 0x0A: Offset to the attribute name + __le16 flags; // 0x0C: See ATTR_FLAG_XXX + __le16 id; // 0x0E: unique id (per record) + + union { + struct ATTR_RESIDENT res; // 0x10 + struct ATTR_NONRESIDENT nres; // 0x10 + }; +}; + +/* Define attribute sizes */ +#define SIZEOF_RESIDENT 0x18 +#define SIZEOF_NONRESIDENT_EX 0x48 +#define SIZEOF_NONRESIDENT 0x40 + +#define SIZEOF_RESIDENT_LE cpu_to_le16(0x18) +#define SIZEOF_NONRESIDENT_EX_LE cpu_to_le16(0x48) +#define SIZEOF_NONRESIDENT_LE cpu_to_le16(0x40) + +static inline u64 attr_ondisk_size(const struct ATTRIB *attr) +{ + return attr->non_res ? ((attr->flags & + (ATTR_FLAG_COMPRESSED | ATTR_FLAG_SPARSED)) ? + le64_to_cpu(attr->nres.total_size) : + le64_to_cpu(attr->nres.alloc_size)) : + QuadAlign(le32_to_cpu(attr->res.data_size)); +} + +static inline u64 attr_size(const struct ATTRIB *attr) +{ + return attr->non_res ? le64_to_cpu(attr->nres.data_size) : + le32_to_cpu(attr->res.data_size); +} + +static inline bool is_attr_encrypted(const struct ATTRIB *attr) +{ + return attr->flags & ATTR_FLAG_ENCRYPTED; +} + +static inline bool is_attr_sparsed(const struct ATTRIB *attr) +{ + return attr->flags & ATTR_FLAG_SPARSED; +} + +static inline bool is_attr_compressed(const struct ATTRIB *attr) +{ + return attr->flags & ATTR_FLAG_COMPRESSED; +} + +static inline bool is_attr_ext(const struct ATTRIB *attr) +{ + return attr->flags & (ATTR_FLAG_SPARSED | ATTR_FLAG_COMPRESSED); +} + +static inline bool is_attr_indexed(const struct ATTRIB *attr) +{ + return !attr->non_res && (attr->res.flags & RESIDENT_FLAG_INDEXED); +} + +static inline const __le16 *attr_name(const struct ATTRIB *attr) +{ + return Add2Ptr(attr, le16_to_cpu(attr->name_off)); +} + +static inline u64 attr_svcn(const struct ATTRIB *attr) +{ + return attr->non_res ? le64_to_cpu(attr->nres.svcn) : 0; +} + +/* the size of resident attribute by its resident size */ +#define BYTES_PER_RESIDENT(b) (0x18 + (b)) + +static_assert(sizeof(struct ATTRIB) == 0x48); +static_assert(sizeof(((struct ATTRIB *)NULL)->res) == 0x08); +static_assert(sizeof(((struct ATTRIB *)NULL)->nres) == 0x38); + +static inline void *resident_data_ex(const struct ATTRIB *attr, u32 datasize) +{ + u32 asize, rsize; + u16 off; + + if (attr->non_res) + return NULL; + + asize = le32_to_cpu(attr->size); + off = le16_to_cpu(attr->res.data_off); + + if (asize < datasize + off) + return NULL; + + rsize = le32_to_cpu(attr->res.data_size); + if (rsize < datasize) + return NULL; + + return Add2Ptr(attr, off); +} + +static inline void *resident_data(const struct ATTRIB *attr) +{ + return Add2Ptr(attr, le16_to_cpu(attr->res.data_off)); +} + +static inline void *attr_run(const struct ATTRIB *attr) +{ + return Add2Ptr(attr, le16_to_cpu(attr->nres.run_off)); +} + +/* Standard information attribute (0x10) */ +struct ATTR_STD_INFO { + __le64 cr_time; // 0x00: File creation file + __le64 m_time; // 0x08: File modification time + __le64 c_time; // 0x10: Last time any attribute was modified. + __le64 a_time; // 0x18: File last access time + enum FILE_ATTRIBUTE fa; // 0x20: Standard DOS attributes & more + __le32 max_ver_num; // 0x24: Maximum Number of Versions + __le32 ver_num; // 0x28: Version Number + __le32 class_id; // 0x2C: Class Id from bidirectional Class Id index +}; + +static_assert(sizeof(struct ATTR_STD_INFO) == 0x30); + +#define SECURITY_ID_INVALID 0x00000000 +#define SECURITY_ID_FIRST 0x00000100 + +struct ATTR_STD_INFO5 { + __le64 cr_time; // 0x00: File creation file + __le64 m_time; // 0x08: File modification time + __le64 c_time; // 0x10: Last time any attribute was modified. + __le64 a_time; // 0x18: File last access time + enum FILE_ATTRIBUTE fa; // 0x20: Standard DOS attributes & more + __le32 max_ver_num; // 0x24: Maximum Number of Versions + __le32 ver_num; // 0x28: Version Number + __le32 class_id; // 0x2C: Class Id from bidirectional Class Id index + + __le32 owner_id; // 0x30: Owner Id of the user owning the file. This Id is a key + // in the $O and $Q Indexes of the file $Quota. If zero, then + // quotas are disabled + __le32 security_id; // 0x34: The Security Id is a key in the $SII Index and $SDS + // Data Stream in the file $Secure. + __le64 quota_charge; // 0x38: The number of bytes this file user from the user's + // quota. This should be the total data size of all streams. + // If zero, then quotas are disabled. + __le64 usn; // 0x40: Last Update Sequence Number of the file. This is a direct + // index into the file $UsnJrnl. If zero, the USN Journal is + // disabled. +}; + +static_assert(sizeof(struct ATTR_STD_INFO5) == 0x48); + +/* attribute list entry structure (0x20) */ +struct ATTR_LIST_ENTRY { + enum ATTR_TYPE type; // 0x00: The type of attribute + __le16 size; // 0x04: The size of this record + u8 name_len; // 0x06: The length of attribute name + u8 name_off; // 0x07: The offset to attribute name + __le64 vcn; // 0x08: Starting VCN of this attribute + struct MFT_REF ref; // 0x10: MFT record number with attribute + __le16 id; // 0x18: struct ATTRIB ID + __le16 name[3]; // 0x1A: Just to align. To get real name can use bNameOffset + +}; // sizeof(0x20) + +static_assert(sizeof(struct ATTR_LIST_ENTRY) == 0x20); + +static inline u32 le_size(u8 name_len) +{ + return QuadAlign(offsetof(struct ATTR_LIST_ENTRY, name) + + name_len * sizeof(short)); +} + +/* returns 0 if 'attr' has the same type and name */ +static inline int le_cmp(const struct ATTR_LIST_ENTRY *le, + const struct ATTRIB *attr) +{ + return le->type != attr->type || le->name_len != attr->name_len || + (!le->name_len && + memcmp(Add2Ptr(le, le->name_off), + Add2Ptr(attr, le16_to_cpu(attr->name_off)), + le->name_len * sizeof(short))); +} + +static inline const __le16 *le_name(const struct ATTR_LIST_ENTRY *le) +{ + return Add2Ptr(le, le->name_off); +} + +/* File name types (the field type in struct ATTR_FILE_NAME ) */ +#define FILE_NAME_POSIX 0 +#define FILE_NAME_UNICODE 1 +#define FILE_NAME_DOS 2 +#define FILE_NAME_UNICODE_AND_DOS (FILE_NAME_DOS | FILE_NAME_UNICODE) + +/* Filename attribute structure (0x30) */ +struct NTFS_DUP_INFO { + __le64 cr_time; // 0x00: File creation file + __le64 m_time; // 0x08: File modification time + __le64 c_time; // 0x10: Last time any attribute was modified + __le64 a_time; // 0x18: File last access time + __le64 alloc_size; // 0x20: Data attribute allocated size, multiple of cluster size + __le64 data_size; // 0x28: Data attribute size <= Dataalloc_size + enum FILE_ATTRIBUTE fa; // 0x30: Standard DOS attributes & more + __le16 ea_size; // 0x34: Packed EAs + __le16 reparse; // 0x36: Used by Reparse + +}; // 0x38 + +struct ATTR_FILE_NAME { + struct MFT_REF home; // 0x00: MFT record for directory + struct NTFS_DUP_INFO dup; // 0x08 + u8 name_len; // 0x40: File name length in words + u8 type; // 0x41: File name type + __le16 name[1]; // 0x42: File name +}; + +static_assert(sizeof(((struct ATTR_FILE_NAME *)NULL)->dup) == 0x38); +static_assert(offsetof(struct ATTR_FILE_NAME, name) == 0x42); +#define SIZEOF_ATTRIBUTE_FILENAME 0x44 +#define SIZEOF_ATTRIBUTE_FILENAME_MAX (0x42 + 255 * 2) + +static inline struct ATTRIB *attr_from_name(struct ATTR_FILE_NAME *fname) +{ + return (struct ATTRIB *)((char *)fname - SIZEOF_RESIDENT); +} + +static inline u16 fname_full_size(const struct ATTR_FILE_NAME *fname) +{ + return offsetof(struct ATTR_FILE_NAME, name) + + fname->name_len * sizeof(short); +} + +static inline u8 paired_name(u8 type) +{ + if (type == FILE_NAME_UNICODE) + return FILE_NAME_DOS; + if (type == FILE_NAME_DOS) + return FILE_NAME_UNICODE; + return FILE_NAME_POSIX; +} + +/* Index entry defines ( the field flags in NtfsDirEntry ) */ +#define NTFS_IE_HAS_SUBNODES cpu_to_le16(1) +#define NTFS_IE_LAST cpu_to_le16(2) + +/* Directory entry structure */ +struct NTFS_DE { + union { + struct MFT_REF ref; // 0x00: MFT record number with this file + struct { + __le16 data_off; // 0x00: + __le16 data_size; // 0x02: + __le32 res; // 0x04: must be 0 + } view; + }; + __le16 size; // 0x08: The size of this entry + __le16 key_size; // 0x0A: The size of File name length in bytes + 0x42 + __le16 flags; // 0x0C: Entry flags, 1=subnodes, 2=last + __le16 res; // 0x0E: + + // Here any indexed attribute can be placed + // One of them is: + // struct ATTR_FILE_NAME AttrFileName; + // + + // The last 8 bytes of this structure contains + // the VBN of subnode + // !!! Note !!! + // This field is presented only if (flags & NTFS_IE_HAS_SUBNODES) + // __le64 vbn; +}; + +static_assert(sizeof(struct NTFS_DE) == 0x10); + +static inline void de_set_vbn_le(struct NTFS_DE *e, __le64 vcn) +{ + __le64 *v = Add2Ptr(e, le16_to_cpu(e->size) - sizeof(__le64)); + + *v = vcn; +} + +static inline void de_set_vbn(struct NTFS_DE *e, CLST vcn) +{ + __le64 *v = Add2Ptr(e, le16_to_cpu(e->size) - sizeof(__le64)); + + *v = cpu_to_le64(vcn); +} + +static inline __le64 de_get_vbn_le(const struct NTFS_DE *e) +{ + return *(__le64 *)Add2Ptr(e, le16_to_cpu(e->size) - sizeof(__le64)); +} + +static inline CLST de_get_vbn(const struct NTFS_DE *e) +{ + __le64 *v = Add2Ptr(e, le16_to_cpu(e->size) - sizeof(__le64)); + + return le64_to_cpu(*v); +} + +static inline struct NTFS_DE *de_get_next(const struct NTFS_DE *e) +{ + return Add2Ptr(e, le16_to_cpu(e->size)); +} + +static inline struct ATTR_FILE_NAME *de_get_fname(const struct NTFS_DE *e) +{ + return le16_to_cpu(e->key_size) >= SIZEOF_ATTRIBUTE_FILENAME ? + Add2Ptr(e, sizeof(struct NTFS_DE)) : + NULL; +} + +static inline bool de_is_last(const struct NTFS_DE *e) +{ + return e->flags & NTFS_IE_LAST; +} + +static inline bool de_has_vcn(const struct NTFS_DE *e) +{ + return e->flags & NTFS_IE_HAS_SUBNODES; +} + +static inline bool de_has_vcn_ex(const struct NTFS_DE *e) +{ + return (e->flags & NTFS_IE_HAS_SUBNODES) && + (u64)(-1) != *((u64 *)Add2Ptr(e, le16_to_cpu(e->size) - + sizeof(__le64))); +} + +#define MAX_BYTES_PER_NAME_ENTRY \ + QuadAlign(sizeof(struct NTFS_DE) + \ + offsetof(struct ATTR_FILE_NAME, name) + \ + NTFS_NAME_LEN * sizeof(short)) + +struct INDEX_HDR { + // The offset from the start of this structure to the first NtfsDirEntry + __le32 de_off; // 0x00: + // The size of this structure plus all entries (quad-word aligned) + __le32 used; // 0x04 + // The allocated size of for this structure plus all entries + __le32 total; // 0x08: + // 0x00 = Small directory, 0x01 = Large directory + u8 flags; // 0x0C + u8 res[3]; + + // + // de_off + used <= total + // +}; + +static_assert(sizeof(struct INDEX_HDR) == 0x10); + +static inline struct NTFS_DE *hdr_first_de(const struct INDEX_HDR *hdr) +{ + u32 de_off = le32_to_cpu(hdr->de_off); + u32 used = le32_to_cpu(hdr->used); + struct NTFS_DE *e = Add2Ptr(hdr, de_off); + u16 esize; + + if (de_off >= used || de_off >= le32_to_cpu(hdr->total)) + return NULL; + + esize = le16_to_cpu(e->size); + if (esize < sizeof(struct NTFS_DE) || de_off + esize > used) + return NULL; + + return e; +} + +static inline struct NTFS_DE *hdr_next_de(const struct INDEX_HDR *hdr, + const struct NTFS_DE *e) +{ + size_t off = PtrOffset(hdr, e); + u32 used = le32_to_cpu(hdr->used); + u16 esize; + + if (off >= used) + return NULL; + + esize = le16_to_cpu(e->size); + + if (esize < sizeof(struct NTFS_DE) || + off + esize + sizeof(struct NTFS_DE) > used) + return NULL; + + return Add2Ptr(e, esize); +} + +static inline bool hdr_has_subnode(const struct INDEX_HDR *hdr) +{ + return hdr->flags & 1; +} + +struct INDEX_BUFFER { + struct NTFS_RECORD_HEADER rhdr; // 'INDX' + __le64 vbn; // 0x10: vcn if index >= cluster or vsn id index < cluster + struct INDEX_HDR ihdr; // 0x18: +}; + +static_assert(sizeof(struct INDEX_BUFFER) == 0x28); + +static inline bool ib_is_empty(const struct INDEX_BUFFER *ib) +{ + const struct NTFS_DE *first = hdr_first_de(&ib->ihdr); + + return !first || de_is_last(first); +} + +static inline bool ib_is_leaf(const struct INDEX_BUFFER *ib) +{ + return !(ib->ihdr.flags & 1); +} + +/* Index root structure ( 0x90 ) */ +enum COLLATION_RULE { + NTFS_COLLATION_TYPE_BINARY = cpu_to_le32(0), + NTFS_COLLATION_TYPE_FILENAME = cpu_to_le32(0x01), + // $SII of $Secure / $Q of Quota + NTFS_COLLATION_TYPE_UINT = cpu_to_le32(0x10), + // $O of Quota + NTFS_COLLATION_TYPE_SID = cpu_to_le32(0x11), + // $SDH of $Secure + NTFS_COLLATION_TYPE_SECURITY_HASH = cpu_to_le32(0x12), + // $O of ObjId and "$R" for Reparse + NTFS_COLLATION_TYPE_UINTS = cpu_to_le32(0x13) +}; + +static_assert(sizeof(enum COLLATION_RULE) == 4); + +// +struct INDEX_ROOT { + enum ATTR_TYPE type; // 0x00: The type of attribute to index on + enum COLLATION_RULE rule; // 0x04: The rule + __le32 index_block_size; // 0x08: The size of index record + u8 index_block_clst; // 0x0C: The number of clusters per index + u8 res[3]; + struct INDEX_HDR ihdr; // 0x10: +}; + +static_assert(sizeof(struct INDEX_ROOT) == 0x20); +static_assert(offsetof(struct INDEX_ROOT, ihdr) == 0x10); + +#define VOLUME_FLAG_DIRTY cpu_to_le16(0x0001) +#define VOLUME_FLAG_RESIZE_LOG_FILE cpu_to_le16(0x0002) + +struct VOLUME_INFO { + __le64 res1; // 0x00 + u8 major_ver; // 0x08: NTFS major version number (before .) + u8 minor_ver; // 0x09: NTFS minor version number (after .) + __le16 flags; // 0x0A: Volume flags, see VOLUME_FLAG_XXX + +}; // sizeof=0xC + +#define SIZEOF_ATTRIBUTE_VOLUME_INFO 0xc + +#define NTFS_LABEL_MAX_LENGTH (0x100 / sizeof(short)) +#define NTFS_ATTR_INDEXABLE cpu_to_le32(0x00000002) +#define NTFS_ATTR_DUPALLOWED cpu_to_le32(0x00000004) +#define NTFS_ATTR_MUST_BE_INDEXED cpu_to_le32(0x00000010) +#define NTFS_ATTR_MUST_BE_NAMED cpu_to_le32(0x00000020) +#define NTFS_ATTR_MUST_BE_RESIDENT cpu_to_le32(0x00000040) +#define NTFS_ATTR_LOG_ALWAYS cpu_to_le32(0x00000080) + +/* $AttrDef file entry */ +struct ATTR_DEF_ENTRY { + __le16 name[0x40]; // 0x00: Attr name + enum ATTR_TYPE type; // 0x80: struct ATTRIB type + __le32 res; // 0x84: + enum COLLATION_RULE rule; // 0x88: + __le32 flags; // 0x8C: NTFS_ATTR_XXX (see above) + __le64 min_sz; // 0x90: Minimum attribute data size + __le64 max_sz; // 0x98: Maximum attribute data size +}; + +static_assert(sizeof(struct ATTR_DEF_ENTRY) == 0xa0); + +/* Object ID (0x40) */ +struct OBJECT_ID { + struct GUID ObjId; // 0x00: Unique Id assigned to file + struct GUID + BirthVolumeId; // 0x10: Birth Volume Id is the Object Id of the Volume on + // which the Object Id was allocated. It never changes + struct GUID + BirthObjectId; // 0x20: Birth Object Id is the first Object Id that was + // ever assigned to this MFT Record. I.e. If the Object Id + // is changed for some reason, this field will reflect the + // original value of the Object Id. + struct GUID + DomainId; // 0x30: Domain Id is currently unused but it is intended to be + // used in a network environment where the local machine is + // part of a Windows 2000 Domain. This may be used in a Windows + // 2000 Advanced Server managed domain. +}; + +static_assert(sizeof(struct OBJECT_ID) == 0x40); + +/* O Directory entry structure ( rule = 0x13 ) */ +struct NTFS_DE_O { + struct NTFS_DE de; + // See struct OBJECT_ID (0x40) for details + struct GUID ObjId; // 0x10: Unique Id assigned to file + struct MFT_REF ref; // 0x20: MFT record number with this file + struct GUID + BirthVolumeId; // 0x28: Birth Volume Id is the Object Id of the Volume on + // which the Object Id was allocated. It never changes + struct GUID + BirthObjectId; // 0x38: Birth Object Id is the first Object Id that was + // ever assigned to this MFT Record. I.e. If the Object Id + // is changed for some reason, this field will reflect the + // original value of the Object Id. + // This field is valid if data_size == 0x48 + struct GUID + BirthDomainId; // 0x48: Domain Id is currently unused but it is intended + // to be used in a network environment where the local + // machine is part of a Windows 2000 Domain. This may be + // used in a Windows 2000 Advanced Server managed domain. + + // The last 8 bytes of this structure contains + // the VCN of subnode + // !!! Note !!! + // This field is presented only if (flags & 0x1) + // __le64 SubnodesVCN; +}; + +static_assert(sizeof(struct NTFS_DE_O) == 0x58); + +#define NTFS_OBJECT_ENTRY_DATA_SIZE1 \ + 0x38 // struct NTFS_DE_O.BirthDomainId is not used +#define NTFS_OBJECT_ENTRY_DATA_SIZE2 \ + 0x48 // struct NTFS_DE_O.BirthDomainId is used + +/* Q Directory entry structure ( rule = 0x11 ) */ +struct NTFS_DE_Q { + struct NTFS_DE de; + __le32 owner_id; // 0x10: Unique Id assigned to file + __le32 Version; // 0x14: 0x02 + __le32 flags2; // 0x18: Quota flags, see above + __le64 BytesUsed; // 0x1C: + __le64 ChangeTime; // 0x24: + __le64 WarningLimit; // 0x28: + __le64 HardLimit; // 0x34: + __le64 ExceededTime; // 0x3C: + + // SID is placed here + + // The last 8 bytes of this structure contains + // the VCN of subnode + // !!! Note !!! + // This field is presented only if (flags & 0x1) + // __le64 SubnodesVCN; + +}; // __attribute__ ((packed)); // sizeof() = 0x44 + +#define SIZEOF_NTFS_DE_Q 0x44 + +#define SecurityDescriptorsBlockSize 0x40000 // 256K +#define SecurityDescriptorMaxSize 0x20000 // 128K +#define Log2OfSecurityDescriptorsBlockSize 18 + +struct SECURITY_KEY { + __le32 hash; // Hash value for descriptor + __le32 sec_id; // Security Id (guaranteed unique) +}; + +/* Security descriptors (the content of $Secure::SDS data stream) */ +struct SECURITY_HDR { + struct SECURITY_KEY key; // 0x00: Security Key + __le64 off; // 0x08: Offset of this entry in the file + __le32 size; // 0x10: Size of this entry, 8 byte aligned + // + // Security descriptor itself is placed here + // Total size is 16 byte aligned + // + +} __packed; + +#define SIZEOF_SECURITY_HDR 0x14 + +/* SII Directory entry structure */ +struct NTFS_DE_SII { + struct NTFS_DE de; + __le32 sec_id; // 0x10: Key: sizeof(security_id) = wKeySize + struct SECURITY_HDR sec_hdr; // 0x14: + +} __packed; + +#define SIZEOF_SII_DIRENTRY 0x28 + +/* SDH Directory entry structure */ +struct NTFS_DE_SDH { + struct NTFS_DE de; + struct SECURITY_KEY key; // 0x10: Key + struct SECURITY_HDR sec_hdr; // 0x18: Data + __le16 magic[2]; // 0x2C: 0x00490049 "I I" +}; + +#define SIZEOF_SDH_DIRENTRY 0x30 + +struct REPARSE_KEY { + __le32 ReparseTag; // 0x00: Reparse Tag + struct MFT_REF ref; // 0x04: MFT record number with this file + +}; // sizeof() = 0x0C + +static_assert(offsetof(struct REPARSE_KEY, ref) == 0x04); +#define SIZEOF_REPARSE_KEY 0x0C + +/* Reparse Directory entry structure */ +struct NTFS_DE_R { + struct NTFS_DE de; + struct REPARSE_KEY Key; // 0x10: Reparse Key (Tag + struct MFT_REF) + + // The last 8 bytes of this structure contains + // the VCN of subnode + // !!! Note !!! + // This field is presented only if (flags & 0x1) + // __le64 SubnodesVCN; + +}; // sizeof() = 0x1C + +#define SIZEOF_R_DIRENTRY 0x1C + +/* CompressReparseBuffer.WofVersion */ +#define WOF_CURRENT_VERSION cpu_to_le32(1) +/* CompressReparseBuffer.WofProvider */ +#define WOF_PROVIDER_WIM cpu_to_le32(1) +/* CompressReparseBuffer.WofProvider */ +#define WOF_PROVIDER_SYSTEM cpu_to_le32(2) +/* CompressReparseBuffer.ProviderVer */ +#define WOF_PROVIDER_CURRENT_VERSION cpu_to_le32(1) + +#define WOF_COMPRESSION_XPRESS4K 0 // 4k +#define WOF_COMPRESSION_LZX 1 // 32k +#define WOF_COMPRESSION_XPRESS8K 2 // 8k +#define WOF_COMPRESSION_XPRESS16K 3 // 16k + +/* + * ATTR_REPARSE (0xC0) + * + * The reparse struct GUID structure is used by all 3rd party layered drivers to + * store data in a reparse point. For non-Microsoft tags, The struct GUID field + * cannot be GUID_NULL. + * The constraints on reparse tags are defined below. + * Microsoft tags can also be used with this format of the reparse point buffer. + */ +struct REPARSE_POINT { + __le32 ReparseTag; // 0x00: + __le16 ReparseDataLength; // 0x04: + __le16 Reserved; + + struct GUID Guid; // 0x08: + + // + // Here GenericReparseBuffer is placed + // +}; + +static_assert(sizeof(struct REPARSE_POINT) == 0x18); + +// +// Maximum allowed size of the reparse data. +// +#define MAXIMUM_REPARSE_DATA_BUFFER_SIZE (16 * 1024) + +// +// The value of the following constant needs to satisfy the following +// conditions: +// (1) Be at least as large as the largest of the reserved tags. +// (2) Be strictly smaller than all the tags in use. +// +#define IO_REPARSE_TAG_RESERVED_RANGE 1 + +// +// The reparse tags are a ULONG. The 32 bits are laid out as follows: +// +// 3 3 2 2 2 2 2 2 2 2 2 2 1 1 1 1 1 1 1 1 1 1 +// 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 +// +-+-+-+-+-----------------------+-------------------------------+ +// |M|R|N|R| Reserved bits | Reparse Tag Value | +// +-+-+-+-+-----------------------+-------------------------------+ +// +// M is the Microsoft bit. When set to 1, it denotes a tag owned by Microsoft. +// All ISVs must use a tag with a 0 in this position. +// Note: If a Microsoft tag is used by non-Microsoft software, the +// behavior is not defined. +// +// R is reserved. Must be zero for non-Microsoft tags. +// +// N is name surrogate. When set to 1, the file represents another named +// entity in the system. +// +// The M and N bits are OR-able. +// The following macros check for the M and N bit values: +// + +// +// Macro to determine whether a reparse point tag corresponds to a tag +// owned by Microsoft. +// +#define IsReparseTagMicrosoft(_tag) (((_tag)&IO_REPARSE_TAG_MICROSOFT)) + +// +// Macro to determine whether a reparse point tag is a name surrogate +// +#define IsReparseTagNameSurrogate(_tag) (((_tag)&IO_REPARSE_TAG_NAME_SURROGATE)) + +// +// The following constant represents the bits that are valid to use in +// reparse tags. +// +#define IO_REPARSE_TAG_VALID_VALUES 0xF000FFFF + +// +// Macro to determine whether a reparse tag is a valid tag. +// +#define IsReparseTagValid(_tag) \ + (!((_tag) & ~IO_REPARSE_TAG_VALID_VALUES) && \ + ((_tag) > IO_REPARSE_TAG_RESERVED_RANGE)) + +// +// Microsoft tags for reparse points. +// + +enum IO_REPARSE_TAG { + IO_REPARSE_TAG_SYMBOLIC_LINK = cpu_to_le32(0), + IO_REPARSE_TAG_NAME_SURROGATE = cpu_to_le32(0x20000000), + IO_REPARSE_TAG_MICROSOFT = cpu_to_le32(0x80000000), + IO_REPARSE_TAG_MOUNT_POINT = cpu_to_le32(0xA0000003), + IO_REPARSE_TAG_SYMLINK = cpu_to_le32(0xA000000C), + IO_REPARSE_TAG_HSM = cpu_to_le32(0xC0000004), + IO_REPARSE_TAG_SIS = cpu_to_le32(0x80000007), + IO_REPARSE_TAG_DEDUP = cpu_to_le32(0x80000013), + IO_REPARSE_TAG_COMPRESS = cpu_to_le32(0x80000017), + + // + // The reparse tag 0x80000008 is reserved for Microsoft internal use + // (may be published in the future) + // + + // + // Microsoft reparse tag reserved for DFS + // + IO_REPARSE_TAG_DFS = cpu_to_le32(0x8000000A), + + // + // Microsoft reparse tag reserved for the file system filter manager + // + IO_REPARSE_TAG_FILTER_MANAGER = cpu_to_le32(0x8000000B), + + // + // Non-Microsoft tags for reparse points + // + + // + // Tag allocated to CONGRUENT, May 2000. Used by IFSTEST + // + IO_REPARSE_TAG_IFSTEST_CONGRUENT = cpu_to_le32(0x00000009), + + // + // Tag allocated to ARKIVIO + // + IO_REPARSE_TAG_ARKIVIO = cpu_to_le32(0x0000000C), + + // + // Tag allocated to SOLUTIONSOFT + // + IO_REPARSE_TAG_SOLUTIONSOFT = cpu_to_le32(0x2000000D), + + // + // Tag allocated to COMMVAULT + // + IO_REPARSE_TAG_COMMVAULT = cpu_to_le32(0x0000000E), + + // OneDrive?? + IO_REPARSE_TAG_CLOUD = cpu_to_le32(0x9000001A), + IO_REPARSE_TAG_CLOUD_1 = cpu_to_le32(0x9000101A), + IO_REPARSE_TAG_CLOUD_2 = cpu_to_le32(0x9000201A), + IO_REPARSE_TAG_CLOUD_3 = cpu_to_le32(0x9000301A), + IO_REPARSE_TAG_CLOUD_4 = cpu_to_le32(0x9000401A), + IO_REPARSE_TAG_CLOUD_5 = cpu_to_le32(0x9000501A), + IO_REPARSE_TAG_CLOUD_6 = cpu_to_le32(0x9000601A), + IO_REPARSE_TAG_CLOUD_7 = cpu_to_le32(0x9000701A), + IO_REPARSE_TAG_CLOUD_8 = cpu_to_le32(0x9000801A), + IO_REPARSE_TAG_CLOUD_9 = cpu_to_le32(0x9000901A), + IO_REPARSE_TAG_CLOUD_A = cpu_to_le32(0x9000A01A), + IO_REPARSE_TAG_CLOUD_B = cpu_to_le32(0x9000B01A), + IO_REPARSE_TAG_CLOUD_C = cpu_to_le32(0x9000C01A), + IO_REPARSE_TAG_CLOUD_D = cpu_to_le32(0x9000D01A), + IO_REPARSE_TAG_CLOUD_E = cpu_to_le32(0x9000E01A), + IO_REPARSE_TAG_CLOUD_F = cpu_to_le32(0x9000F01A), + +}; + +/* Microsoft reparse buffer. (see DDK for details) */ +struct REPARSE_DATA_BUFFER { + __le32 ReparseTag; // 0x00: + __le16 ReparseDataLength; // 0x04: + __le16 Reserved; + + union { + // If ReparseTag == 0 + struct { + __le16 SubstituteNameOffset; // 0x08 + __le16 SubstituteNameLength; // 0x0A + __le16 PrintNameOffset; // 0x0C + __le16 PrintNameLength; // 0x0E + __le16 PathBuffer[1]; // 0x10 + } SymbolicLinkReparseBuffer; + + // If ReparseTag == 0xA0000003U + struct { + __le16 SubstituteNameOffset; // 0x08 + __le16 SubstituteNameLength; // 0x0A + __le16 PrintNameOffset; // 0x0C + __le16 PrintNameLength; // 0x0E + __le16 PathBuffer[1]; // 0x10 + } MountPointReparseBuffer; + + // If ReparseTag == IO_REPARSE_TAG_SYMLINK2 (0xA000000CU) + // https://msdn.microsoft.com/en-us/library/cc232006.aspx + struct { + __le16 SubstituteNameOffset; // 0x08 + __le16 SubstituteNameLength; // 0x0A + __le16 PrintNameOffset; // 0x0C + __le16 PrintNameLength; // 0x0E + // 0-absolute path 1- relative path + __le32 Flags; // 0x10 + __le16 PathBuffer[1]; // 0x14 + } SymbolicLink2ReparseBuffer; + + // If ReparseTag == 0x80000017U + struct { + __le32 WofVersion; // 0x08 == 1 + /* 1 - WIM backing provider ("WIMBoot"), + * 2 - System compressed file provider + */ + __le32 WofProvider; // 0x0C + __le32 ProviderVer; // 0x10: == 1 WOF_FILE_PROVIDER_CURRENT_VERSION == 1 + __le32 CompressionFormat; // 0x14: 0, 1, 2, 3. See WOF_COMPRESSION_XXX + } CompressReparseBuffer; + + struct { + u8 DataBuffer[1]; // 0x08 + } GenericReparseBuffer; + }; +}; + +static inline u32 ntfs_reparse_bytes(u32 uni_len) +{ + /* two unicode strings + header */ + return sizeof(short) * (2 * uni_len + 4) + + offsetof(struct REPARSE_DATA_BUFFER, + SymbolicLink2ReparseBuffer.PathBuffer); +} + +/* ATTR_EA_INFO (0xD0) */ + +#define FILE_NEED_EA 0x80 // See ntifs.h +/* FILE_NEED_EA, indicates that the file to which the EA belongs cannot be + * interpreted without understanding the associated extended attributes. + */ +struct EA_INFO { + __le16 size_pack; // 0x00: Size of buffer to hold in packed form + __le16 count; // 0x02: Count of EA's with FILE_NEED_EA bit set + __le32 size; // 0x04: Size of buffer to hold in unpacked form +}; + +static_assert(sizeof(struct EA_INFO) == 8); + +/* ATTR_EA (0xE0) */ +struct EA_FULL { + __le32 size; // 0x00: (not in packed) + u8 flags; // 0x04 + u8 name_len; // 0x05 + __le16 elength; // 0x06 + u8 name[1]; // 0x08 +}; + +static_assert(offsetof(struct EA_FULL, name) == 8); + +#define MAX_EA_DATA_SIZE (256 * 1024) + +#define ACL_REVISION 2 + +#define SE_SELF_RELATIVE 0x8000 + +struct SECURITY_DESCRIPTOR_RELATIVE { + u8 Revision; + u8 Sbz1; + __le16 Control; + __le32 Owner; + __le32 Group; + __le32 Sacl; + __le32 Dacl; +}; +static_assert(sizeof(struct SECURITY_DESCRIPTOR_RELATIVE) == 0x14); + +struct ACE_HEADER { + u8 AceType; + u8 AceFlags; + __le16 AceSize; +}; +static_assert(sizeof(struct ACE_HEADER) == 4); + +struct ACL { + u8 AclRevision; + u8 Sbz1; + __le16 AclSize; + __le16 AceCount; + __le16 Sbz2; +}; +static_assert(sizeof(struct ACL) == 8); + +struct SID { + u8 Revision; + u8 SubAuthorityCount; + u8 IdentifierAuthority[6]; + __le32 SubAuthority[1]; +}; +static_assert(offsetof(struct SID, SubAuthority) == 8); diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h new file mode 100644 index 000000000000..bf26ee5f2172 --- /dev/null +++ b/fs/ntfs3/ntfs_fs.h @@ -0,0 +1,984 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * linux/fs/ntfs3/ntfs_fs.h + * + * Copyright (C) 2019-2020 Paragon Software GmbH, All rights reserved. + * + */ + +/* "true" when [s,s+c) intersects with [l,l+w) */ +#define IS_IN_RANGE(s, c, l, w) \ + (((c) > 0 && (w) > 0) && \ + (((l) <= (s) && (s) < ((l) + (w))) || \ + ((s) <= (l) && ((s) + (c)) >= ((l) + (w))) || \ + ((l) < ((s) + (c)) && ((s) + (c)) < ((l) + (w))))) + +/* "true" when [s,se) intersects with [l,le) */ +#define IS_IN_RANGE2(s, se, l, le) \ + (((se) > (s) && (le) > (l)) && \ + (((l) <= (s) && (s) < (le)) || ((s) <= (l) && (se) >= (le)) || \ + ((l) < (se) && (se) < (le)))) + +#define MINUS_ONE_T ((size_t)(-1)) +/* Biggest MFT / smallest cluster */ +#define MAXIMUM_BYTES_PER_MFT 4096 // ?? +#define NTFS_BLOCKS_PER_MFT_RECORD (MAXIMUM_BYTES_PER_MFT / 512) + +#define MAXIMUM_BYTES_PER_INDEX 4096 // ?? +#define NTFS_BLOCKS_PER_INODE (MAXIMUM_BYTES_PER_INDEX / 512) + +struct ntfs_inode; +struct ntfs_sb_info; +struct lznt; + +struct ntfs_mount_options { + struct nls_table *nls[2]; + + kuid_t fs_uid; + kgid_t fs_gid; + u16 fs_fmask_inv; + u16 fs_dmask_inv; + + unsigned uid : 1, /* uid was set */ + gid : 1, /* gid was set */ + fmask : 1, /* fmask was set */ + dmask : 1, /*dmask was set*/ + sys_immutable : 1, /* set = system files are immutable */ + discard : 1, /* issue discard requests on deletions */ + sparse : 1, /*create sparse files*/ + showmeta : 1, /*show meta files*/ + nohidden : 1, /*do not show hidden files*/ + force : 1, /*rw mount dirty volume*/ + no_acs_rules : 1, /*exclude acs rules*/ + prealloc : 1 /*preallocate space when file is growing*/ + ; +}; + +struct ntfs_run; + +/* TODO: use rb tree instead of array */ +struct runs_tree { + struct ntfs_run *runs_; + size_t count; // Currently used size a ntfs_run storage. + size_t allocated; // Currently allocated ntfs_run storage size. +}; + +struct ntfs_buffers { + /* Biggest MFT / smallest cluster = 4096 / 512 = 8 */ + /* Biggest index / smallest cluster = 4096 / 512 = 8 */ + struct buffer_head *bh[PAGE_SIZE >> SECTOR_SHIFT]; + u32 bytes; + u32 nbufs; + u32 off; +}; + +#define NTFS_FLAGS_NODISCARD 0x00000001 +#define NTFS_FLAGS_NEED_REPLAY 0x04000000 + +enum ALLOCATE_OPT { + ALLOCATE_DEF = 0, // Allocate all clusters + ALLOCATE_MFT = 1, // Allocate for MFT +}; + +enum bitmap_mutex_classes { + BITMAP_MUTEX_CLUSTERS = 0, + BITMAP_MUTEX_MFT = 1, +}; + +struct wnd_bitmap { + struct super_block *sb; + struct rw_semaphore rw_lock; + + struct runs_tree run; + size_t nbits; + + u16 free_holder[8]; // holder for free_bits + + size_t total_zeroes; // total number of free bits + u16 *free_bits; // free bits in each window + size_t nwnd; + u32 bits_last; // bits in last window + + struct rb_root start_tree; // extents, sorted by 'start' + struct rb_root count_tree; // extents, sorted by 'count + start' + size_t count; // extents count + int uptodated; // -1 Tree is activated but not updated (too many fragments) + // 0 - Tree is not activated + // 1 - Tree is activated and updated + size_t extent_min; // Minimal extent used while building + size_t extent_max; // Upper estimate of biggest free block + + /* Zone [bit, end) */ + size_t zone_bit; + size_t zone_end; + + bool set_tail; // not necessary in driver + bool inited; +}; + +typedef int (*NTFS_CMP_FUNC)(const void *key1, size_t len1, const void *key2, + size_t len2, const void *param); + +enum index_mutex_classed { + INDEX_MUTEX_I30 = 0, + INDEX_MUTEX_SII = 1, + INDEX_MUTEX_SDH = 2, + INDEX_MUTEX_SO = 3, + INDEX_MUTEX_SQ = 4, + INDEX_MUTEX_SR = 5, + INDEX_MUTEX_TOTAL +}; + +/* This struct works with indexes */ +struct ntfs_index { + struct runs_tree bitmap_run; + struct runs_tree alloc_run; + + /*TODO: remove 'cmp'*/ + NTFS_CMP_FUNC cmp; + + u8 index_bits; // log2(root->index_block_size) + u8 idx2vbn_bits; // log2(root->index_block_clst) + u8 vbn2vbo_bits; // index_block_size < cluster? 9 : cluster_bits + u8 changed; // set when tree is changed + u8 type; // index_mutex_classed +}; + +/* Set when $LogFile is replaying */ +#define NTFS_FLAGS_LOG_REPLAYING 0x00000008 + +/* Set when we changed first MFT's which copy must be updated in $MftMirr */ +#define NTFS_FLAGS_MFTMIRR 0x00001000 + +/* Minimum mft zone */ +#define NTFS_MIN_MFT_ZONE 100 + +/* ntfs file system in-core superblock data */ +struct ntfs_sb_info { + struct super_block *sb; + + u32 discard_granularity; + u64 discard_granularity_mask_inv; // ~(discard_granularity_mask_inv-1) + + u32 cluster_size; // bytes per cluster + u32 cluster_mask; // == cluster_size - 1 + u64 cluster_mask_inv; // ~(cluster_size - 1) + u32 block_mask; // sb->s_blocksize - 1 + u32 blocks_per_cluster; // cluster_size / sb->s_blocksize + + u32 record_size; + u32 sector_size; + u32 index_size; + + u8 sector_bits; + u8 cluster_bits; + u8 record_bits; + + u64 maxbytes; // Maximum size for normal files + u64 maxbytes_sparse; // Maximum size for sparse file + + u32 flags; // See NTFS_FLAGS_XXX + + CLST bad_clusters; // The count of marked bad clusters + + u16 max_bytes_per_attr; // maximum attribute size in record + u16 attr_size_tr; // attribute size threshold (320 bytes) + + /* Records in $Extend */ + CLST objid_no; + CLST quota_no; + CLST reparse_no; + CLST usn_jrnl_no; + + struct ATTR_DEF_ENTRY *def_table; // attribute definition table + u32 def_entries; + + struct MFT_REC *new_rec; + + u16 *upcase; + + struct { + u64 lbo, lbo2; + struct ntfs_inode *ni; + struct wnd_bitmap bitmap; // $MFT::Bitmap + ulong reserved_bitmap; + size_t next_free; // The next record to allocate from + size_t used; + u32 recs_mirr; // Number of records MFTMirr + u8 next_reserved; + u8 reserved_bitmap_inited; + } mft; + + struct { + struct wnd_bitmap bitmap; // $Bitmap::Data + CLST next_free_lcn; + } used; + + struct { + u64 size; // in bytes + u64 blocks; // in blocks + u64 ser_num; + struct ntfs_inode *ni; + __le16 flags; // see VOLUME_FLAG_XXX + u8 major_ver; + u8 minor_ver; + char label[65]; + bool real_dirty; /* real fs state*/ + } volume; + + struct { + struct ntfs_index index_sii; + struct ntfs_index index_sdh; + struct ntfs_inode *ni; + u32 next_id; + u64 next_off; + + __le32 def_security_id; + } security; + + struct { + struct ntfs_index index_r; + struct ntfs_inode *ni; + u64 max_size; // 16K + } reparse; + + struct { + struct ntfs_index index_o; + struct ntfs_inode *ni; + } objid; + + struct { + /*protect 'frame_unc' and 'ctx'*/ + spinlock_t lock; + u8 *frame_unc; + struct lznt *ctx; + } compress; + + struct ntfs_mount_options options; + struct ratelimit_state msg_ratelimit; +}; + +struct mft_inode { + struct rb_node node; + struct ntfs_sb_info *sbi; + + CLST rno; + struct MFT_REC *mrec; + struct ntfs_buffers nb; + + bool dirty; +}; + +#define NI_FLAG_DIR 0x00000001 +#define NI_FLAG_RESIDENT 0x00000002 +#define NI_FLAG_UPDATE_PARENT 0x00000004 + +/* Data attribute is compressed special way */ +#define NI_FLAG_COMPRESSED_MASK 0x00000f00 // +/* Data attribute is deduplicated */ +#define NI_FLAG_DEDUPLICATED 0x00001000 +#define NI_FLAG_EA 0x00002000 + +/* ntfs file system inode data memory */ +struct ntfs_inode { + struct mft_inode mi; // base record + + loff_t i_valid; /* valid size */ + struct timespec64 i_crtime; + + struct mutex ni_lock; + + /* file attributes from std */ + enum FILE_ATTRIBUTE std_fa; + __le32 std_security_id; + + // subrecords tree + struct rb_root mi_tree; + + union { + struct ntfs_index dir; + struct { + struct rw_semaphore run_lock; + struct runs_tree run; + } file; + }; + + struct { + struct runs_tree run; + struct ATTR_LIST_ENTRY *le; // 1K aligned memory + size_t size; + bool dirty; + } attr_list; + + size_t ni_flags; // NI_FLAG_XXX + + struct inode vfs_inode; +}; + +struct indx_node { + struct ntfs_buffers nb; + struct INDEX_BUFFER *index; +}; + +struct ntfs_fnd { + int level; + struct indx_node *nodes[20]; + struct NTFS_DE *de[20]; + struct NTFS_DE *root_de; +}; + +enum REPARSE_SIGN { + REPARSE_NONE = 0, + REPARSE_COMPRESSED = 1, + REPARSE_DEDUPLICATED = 2, + REPARSE_LINK = 3 +}; + +/* functions from attrib.c*/ +int attr_load_runs(struct ATTRIB *attr, struct ntfs_inode *ni, + struct runs_tree *run); +int attr_allocate_clusters(struct ntfs_sb_info *sbi, struct runs_tree *run, + CLST vcn, CLST lcn, CLST len, CLST *pre_alloc, + enum ALLOCATE_OPT opt, CLST *alen, const size_t fr, + CLST *new_lcn); +int attr_set_size(struct ntfs_inode *ni, enum ATTR_TYPE type, + const __le16 *name, u8 name_len, struct runs_tree *run, + u64 new_size, const u64 *new_valid, bool keep_prealloc, + struct ATTRIB **ret); +int attr_data_get_block(struct ntfs_inode *ni, CLST vcn, CLST clen, CLST *lcn, + CLST *len, bool *new); +int attr_load_runs_vcn(struct ntfs_inode *ni, enum ATTR_TYPE type, + const __le16 *name, u8 name_len, struct runs_tree *run, + CLST vcn); +int attr_is_frame_compressed(struct ntfs_inode *ni, struct ATTRIB *attr, + CLST frame, CLST *clst_data, bool *is_compr); +int attr_allocate_frame(struct ntfs_inode *ni, CLST frame, size_t compr_size, + u64 new_valid); + +/* functions from attrlist.c*/ +void al_destroy(struct ntfs_inode *ni); +bool al_verify(struct ntfs_inode *ni); +int ntfs_load_attr_list(struct ntfs_inode *ni, struct ATTRIB *attr); +struct ATTR_LIST_ENTRY *al_enumerate(struct ntfs_inode *ni, + struct ATTR_LIST_ENTRY *le); +struct ATTR_LIST_ENTRY *al_find_le(struct ntfs_inode *ni, + struct ATTR_LIST_ENTRY *le, + const struct ATTRIB *attr); +struct ATTR_LIST_ENTRY *al_find_ex(struct ntfs_inode *ni, + struct ATTR_LIST_ENTRY *le, + enum ATTR_TYPE type, const __le16 *name, + u8 name_len, const CLST *vcn); +int al_add_le(struct ntfs_inode *ni, enum ATTR_TYPE type, const __le16 *name, + u8 name_len, CLST svcn, __le16 id, const struct MFT_REF *ref, + struct ATTR_LIST_ENTRY **new_le); +bool al_remove_le(struct ntfs_inode *ni, struct ATTR_LIST_ENTRY *le); +bool al_delete_le(struct ntfs_inode *ni, enum ATTR_TYPE type, CLST vcn, + const __le16 *name, size_t name_len, + const struct MFT_REF *ref); +int al_update(struct ntfs_inode *ni); +static inline size_t al_aligned(size_t size) +{ + return (size + 1023) & ~(size_t)1023; +} + +/* globals from bitfunc.c */ +bool are_bits_clear(const ulong *map, size_t bit, size_t nbits); +bool are_bits_set(const ulong *map, size_t bit, size_t nbits); +size_t get_set_bits_ex(const ulong *map, size_t bit, size_t nbits); + +/* globals from dir.c */ +int ntfs_utf16_to_nls(struct ntfs_sb_info *sbi, const struct le_str *uni, + u8 *buf, int buf_len); +int ntfs_nls_to_utf16(struct ntfs_sb_info *sbi, const u8 *name, u32 name_len, + struct cpu_str *uni, u32 max_ulen, + enum utf16_endian endian); +struct inode *dir_search_u(struct inode *dir, const struct cpu_str *uni, + struct ntfs_fnd *fnd); +bool dir_is_empty(struct inode *dir); +extern const struct file_operations ntfs_dir_operations; + +/* globals from file.c*/ +int ntfs_getattr(const struct path *path, struct kstat *stat, u32 request_mask, + u32 flags); +void ntfs_sparse_cluster(struct inode *inode, struct page *page0, loff_t vbo, + u32 bytes); +int ntfs_file_fsync(struct file *filp, loff_t start, loff_t end, int datasync); +void ntfs_truncate_blocks(struct inode *inode, loff_t offset); +int ntfs_setattr(struct dentry *dentry, struct iattr *attr); +int ntfs_file_open(struct inode *inode, struct file *file); +int ntfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, + __u64 start, __u64 len); +extern const struct inode_operations ntfs_special_inode_operations; +extern const struct inode_operations ntfs_file_inode_operations; +extern const struct file_operations ntfs_file_operations; + +/* globals from frecord.c */ +void ni_remove_mi(struct ntfs_inode *ni, struct mft_inode *mi); +struct ATTR_STD_INFO *ni_std(struct ntfs_inode *ni); +struct ATTR_STD_INFO5 *ni_std5(struct ntfs_inode *ni); +void ni_clear(struct ntfs_inode *ni); +int ni_load_mi_ex(struct ntfs_inode *ni, CLST rno, struct mft_inode **mi); +int ni_load_mi(struct ntfs_inode *ni, struct ATTR_LIST_ENTRY *le, + struct mft_inode **mi); +struct ATTRIB *ni_find_attr(struct ntfs_inode *ni, struct ATTRIB *attr, + struct ATTR_LIST_ENTRY **entry_o, + enum ATTR_TYPE type, const __le16 *name, + u8 name_len, const CLST *vcn, + struct mft_inode **mi); +struct ATTRIB *ni_enum_attr_ex(struct ntfs_inode *ni, struct ATTRIB *attr, + struct ATTR_LIST_ENTRY **le); +struct ATTRIB *ni_load_attr(struct ntfs_inode *ni, enum ATTR_TYPE type, + const __le16 *name, u8 name_len, CLST vcn, + struct mft_inode **pmi); +int ni_load_all_mi(struct ntfs_inode *ni); +bool ni_add_subrecord(struct ntfs_inode *ni, CLST rno, struct mft_inode **mi); +int ni_remove_attr(struct ntfs_inode *ni, enum ATTR_TYPE type, + const __le16 *name, size_t name_len, bool base_only, + const __le16 *id); +int ni_create_attr_list(struct ntfs_inode *ni); +int ni_expand_list(struct ntfs_inode *ni); +int ni_insert_nonresident(struct ntfs_inode *ni, enum ATTR_TYPE type, + const __le16 *name, u8 name_len, + const struct runs_tree *run, CLST svcn, CLST len, + __le16 flags, struct ATTRIB **new_attr, + struct mft_inode **mi); +int ni_insert_resident(struct ntfs_inode *ni, u32 data_size, + enum ATTR_TYPE type, const __le16 *name, u8 name_len, + struct ATTRIB **new_attr, struct mft_inode **mi); +int ni_remove_attr_le(struct ntfs_inode *ni, struct ATTRIB *attr, + struct ATTR_LIST_ENTRY *le); +int ni_delete_all(struct ntfs_inode *ni); +struct ATTR_FILE_NAME *ni_fname_name(struct ntfs_inode *ni, + const struct cpu_str *uni, + const struct MFT_REF *home, + struct ATTR_LIST_ENTRY **entry); +struct ATTR_FILE_NAME *ni_fname_type(struct ntfs_inode *ni, u8 name_type, + struct ATTR_LIST_ENTRY **entry); +u16 ni_fnames_count(struct ntfs_inode *ni); +enum REPARSE_SIGN ni_parse_reparse(struct ntfs_inode *ni, struct ATTRIB *attr, + void *buffer); +int ni_write_inode(struct inode *inode, int sync, const char *hint); +#define _ni_write_inode(i, w) ni_write_inode(i, w, __func__) +int ni_fiemap(struct ntfs_inode *ni, struct fiemap_extent_info *fieinfo, + __u64 vbo, __u64 len); +int ni_readpage_cmpr(struct ntfs_inode *ni, struct page *page); +int ni_write_frame(struct ntfs_inode *ni, struct page **pages, u32 npages); + +/* globals from fslog.c */ +int log_replay(struct ntfs_inode *ni); + +/* globals from fsntfs.c */ +bool ntfs_fix_pre_write(struct NTFS_RECORD_HEADER *rhdr, size_t bytes); +int ntfs_fix_post_read(struct NTFS_RECORD_HEADER *rhdr, size_t bytes, + bool simple); +int ntfs_extend_init(struct ntfs_sb_info *sbi); +int ntfs_loadlog_and_replay(struct ntfs_inode *ni, struct ntfs_sb_info *sbi); +const struct ATTR_DEF_ENTRY *ntfs_query_def(struct ntfs_sb_info *sbi, + enum ATTR_TYPE Type); +int ntfs_look_for_free_space(struct ntfs_sb_info *sbi, CLST lcn, CLST len, + CLST *new_lcn, CLST *new_len, + enum ALLOCATE_OPT opt); +int ntfs_look_free_mft(struct ntfs_sb_info *sbi, CLST *rno, bool mft, + struct ntfs_inode *ni, struct mft_inode **mi); +void ntfs_mark_rec_free(struct ntfs_sb_info *sbi, CLST nRecord); +int ntfs_clear_mft_tail(struct ntfs_sb_info *sbi, size_t from, size_t to); +int ntfs_refresh_zone(struct ntfs_sb_info *sbi); +int ntfs_update_mftmirr(struct ntfs_sb_info *sbi, int wait); +enum NTFS_DIRTY_FLAGS { + NTFS_DIRTY_CLEAR = 0, + NTFS_DIRTY_DIRTY = 1, + NTFS_DIRTY_ERROR = 2, +}; +int ntfs_set_state(struct ntfs_sb_info *sbi, enum NTFS_DIRTY_FLAGS dirty); +int ntfs_sb_read(struct super_block *sb, u64 lbo, size_t bytes, void *buffer); +int ntfs_sb_write(struct super_block *sb, u64 lbo, size_t bytes, + const void *buffer, int wait); +int ntfs_sb_write_run(struct ntfs_sb_info *sbi, const struct runs_tree *run, + u64 vbo, const void *buf, size_t bytes); +struct buffer_head *ntfs_bread_run(struct ntfs_sb_info *sbi, + const struct runs_tree *run, u64 vbo); +int ntfs_read_run_nb(struct ntfs_sb_info *sbi, const struct runs_tree *run, + u64 vbo, void *buf, u32 bytes, struct ntfs_buffers *nb); +int ntfs_read_bh(struct ntfs_sb_info *sbi, const struct runs_tree *run, u64 vbo, + struct NTFS_RECORD_HEADER *rhdr, u32 bytes, + struct ntfs_buffers *nb); +int ntfs_get_bh(struct ntfs_sb_info *sbi, const struct runs_tree *run, u64 vbo, + u32 bytes, struct ntfs_buffers *nb); +int ntfs_write_bh(struct ntfs_sb_info *sbi, struct NTFS_RECORD_HEADER *rhdr, + struct ntfs_buffers *nb, int sync); +int ntfs_vbo_to_lbo(struct ntfs_sb_info *sbi, const struct runs_tree *run, + u64 vbo, u64 *lbo, u64 *bytes); +struct ntfs_inode *ntfs_new_inode(struct ntfs_sb_info *sbi, CLST nRec, + bool dir); +extern const u8 s_default_security[0x50]; +bool is_sd_valid(const struct SECURITY_DESCRIPTOR_RELATIVE *sd, u32 len); +int ntfs_security_init(struct ntfs_sb_info *sbi); +int ntfs_get_security_by_id(struct ntfs_sb_info *sbi, __le32 security_id, + struct SECURITY_DESCRIPTOR_RELATIVE **sd, + size_t *size); +int ntfs_insert_security(struct ntfs_sb_info *sbi, + const struct SECURITY_DESCRIPTOR_RELATIVE *sd, + u32 size, __le32 *security_id, bool *inserted); +int ntfs_reparse_init(struct ntfs_sb_info *sbi); +int ntfs_objid_init(struct ntfs_sb_info *sbi); +int ntfs_objid_remove(struct ntfs_sb_info *sbi, struct GUID *guid); +int ntfs_insert_reparse(struct ntfs_sb_info *sbi, __le32 rtag, + const struct MFT_REF *ref); +int ntfs_remove_reparse(struct ntfs_sb_info *sbi, __le32 rtag, + const struct MFT_REF *ref); +void mark_as_free_ex(struct ntfs_sb_info *sbi, CLST lcn, CLST len, bool trim); +int run_deallocate(struct ntfs_sb_info *sbi, struct runs_tree *run, bool trim); + +/* globals from index.c */ +int indx_used_bit(struct ntfs_index *indx, struct ntfs_inode *ni, size_t *bit); +void fnd_clear(struct ntfs_fnd *fnd); +struct ntfs_fnd *fnd_get(struct ntfs_index *indx); +void fnd_put(struct ntfs_fnd *fnd); +void indx_clear(struct ntfs_index *idx); +int indx_init(struct ntfs_index *indx, struct ntfs_sb_info *sbi, + const struct ATTRIB *attr, enum index_mutex_classed type); +struct INDEX_ROOT *indx_get_root(struct ntfs_index *indx, struct ntfs_inode *ni, + struct ATTRIB **attr, struct mft_inode **mi); +int indx_read(struct ntfs_index *idx, struct ntfs_inode *ni, CLST vbn, + struct indx_node **node); +int indx_find(struct ntfs_index *indx, struct ntfs_inode *dir, + const struct INDEX_ROOT *root, const void *Key, size_t KeyLen, + const void *param, int *diff, struct NTFS_DE **entry, + struct ntfs_fnd *fnd); +int indx_find_sort(struct ntfs_index *indx, struct ntfs_inode *ni, + const struct INDEX_ROOT *root, struct NTFS_DE **entry, + struct ntfs_fnd *fnd); +int indx_find_raw(struct ntfs_index *indx, struct ntfs_inode *ni, + const struct INDEX_ROOT *root, struct NTFS_DE **entry, + size_t *off, struct ntfs_fnd *fnd); +int indx_insert_entry(struct ntfs_index *indx, struct ntfs_inode *ni, + const struct NTFS_DE *new_de, const void *param, + struct ntfs_fnd *fnd); +int indx_delete_entry(struct ntfs_index *indx, struct ntfs_inode *ni, + const void *key, u32 key_len, const void *param); +int indx_update_dup(struct ntfs_inode *ni, struct ntfs_sb_info *sbi, + const struct ATTR_FILE_NAME *fname, + const struct NTFS_DUP_INFO *dup, int sync); + +/* globals from inode.c */ +struct inode *ntfs_iget5(struct super_block *sb, const struct MFT_REF *ref, + const struct cpu_str *name); +int ntfs_set_size(struct inode *inode, u64 new_size); +int reset_log_file(struct inode *inode); +int ntfs_get_block(struct inode *inode, sector_t vbn, + struct buffer_head *bh_result, int create); +int ntfs_write_inode(struct inode *inode, struct writeback_control *wbc); +int ntfs_sync_inode(struct inode *inode); +int ntfs_flush_inodes(struct super_block *sb, struct inode *i1, + struct inode *i2); +int inode_write_data(struct inode *inode, const void *data, size_t bytes); +int ntfs_create_inode(struct inode *dir, struct dentry *dentry, + const struct cpu_str *uni, umode_t mode, dev_t dev, + const char *symname, unsigned int size, int excl, + struct ntfs_fnd *fnd, struct inode **new_inode); +int ntfs_link_inode(struct inode *inode, struct dentry *dentry); +int ntfs_unlink_inode(struct inode *dir, const struct dentry *dentry); +void ntfs_evict_inode(struct inode *inode); +int ntfs_readpage(struct file *file, struct page *page); +extern const struct inode_operations ntfs_link_inode_operations; +extern const struct address_space_operations ntfs_aops; +extern const struct address_space_operations ntfs_aops_cmpr; + +/* globals from name_i.c*/ +int fill_name_de(struct ntfs_sb_info *sbi, void *buf, const struct qstr *name, + const struct cpu_str *uni); +struct dentry *ntfs_get_parent(struct dentry *child); + +extern const struct inode_operations ntfs_dir_inode_operations; + +/* globals from record.c */ +int mi_get(struct ntfs_sb_info *sbi, CLST rno, struct mft_inode **mi); +void mi_put(struct mft_inode *mi); +int mi_init(struct mft_inode *mi, struct ntfs_sb_info *sbi, CLST rno); +int mi_read(struct mft_inode *mi, bool is_mft); +struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr); +// TODO: id? +struct ATTRIB *mi_find_attr(struct mft_inode *mi, struct ATTRIB *attr, + enum ATTR_TYPE type, const __le16 *name, + size_t name_len, const __le16 *id); +static inline struct ATTRIB *rec_find_attr_le(struct mft_inode *rec, + struct ATTR_LIST_ENTRY *le) +{ + return mi_find_attr(rec, NULL, le->type, le_name(le), le->name_len, + &le->id); +} +int mi_write(struct mft_inode *mi, int wait); +int mi_format_new(struct mft_inode *mi, struct ntfs_sb_info *sbi, CLST rno, + __le16 flags, bool is_mft); +void mi_mark_free(struct mft_inode *mi); +struct ATTRIB *mi_insert_attr(struct mft_inode *mi, enum ATTR_TYPE type, + const __le16 *name, u8 name_len, u32 asize, + u16 name_off); + +bool mi_remove_attr(struct mft_inode *mi, struct ATTRIB *attr); +bool mi_resize_attr(struct mft_inode *mi, struct ATTRIB *attr, int bytes); +int mi_pack_runs(struct mft_inode *mi, struct ATTRIB *attr, + struct runs_tree *run, CLST len); +static inline bool mi_is_ref(const struct mft_inode *mi, + const struct MFT_REF *ref) +{ + if (le32_to_cpu(ref->low) != mi->rno) + return false; + if (ref->seq != mi->mrec->seq) + return false; + +#ifdef NTFS3_64BIT_CLUSTER + return le16_to_cpu(ref->high) == (mi->rno >> 32); +#else + return !ref->high; +#endif +} + +/* globals from run.c */ +bool run_lookup_entry(const struct runs_tree *run, CLST vcn, CLST *lcn, + CLST *len, size_t *index); +void run_truncate(struct runs_tree *run, CLST vcn); +void run_truncate_head(struct runs_tree *run, CLST vcn); +bool run_lookup(const struct runs_tree *run, CLST Vcn, size_t *Index); +bool run_add_entry(struct runs_tree *run, CLST vcn, CLST lcn, CLST len); +bool run_get_entry(const struct runs_tree *run, size_t index, CLST *vcn, + CLST *lcn, CLST *len); +bool run_is_mapped_full(const struct runs_tree *run, CLST svcn, CLST evcn); + +int run_pack(const struct runs_tree *run, CLST svcn, CLST len, u8 *run_buf, + u32 run_buf_size, CLST *packed_vcns); +int run_unpack(struct runs_tree *run, struct ntfs_sb_info *sbi, CLST ino, + CLST svcn, CLST evcn, const u8 *run_buf, u32 run_buf_size); + +#ifdef NTFS3_CHECK_FREE_CLST +int run_unpack_ex(struct runs_tree *run, struct ntfs_sb_info *sbi, CLST ino, + CLST svcn, CLST evcn, const u8 *run_buf, u32 run_buf_size); +#else +#define run_unpack_ex run_unpack +#endif +int run_get_highest_vcn(CLST vcn, const u8 *run_buf, u64 *highest_vcn); + +/* globals from super.c */ +void *ntfs_set_shared(void *ptr, u32 bytes); +void *ntfs_put_shared(void *ptr); +void ntfs_unmap_meta(struct super_block *sb, CLST lcn, CLST len); +int ntfs_discard(struct ntfs_sb_info *sbi, CLST Lcn, CLST Len); + +/* globals from ubitmap.c*/ +void wnd_close(struct wnd_bitmap *wnd); +static inline size_t wnd_zeroes(const struct wnd_bitmap *wnd) +{ + return wnd->total_zeroes; +} +void wnd_trace(struct wnd_bitmap *wnd); +void wnd_trace_tree(struct wnd_bitmap *wnd, u32 nExtents, const char *Hint); +int wnd_init(struct wnd_bitmap *wnd, struct super_block *sb, size_t nBits); +int wnd_set_free(struct wnd_bitmap *wnd, size_t FirstBit, size_t Bits); +int wnd_set_used(struct wnd_bitmap *wnd, size_t FirstBit, size_t Bits); +bool wnd_is_free(struct wnd_bitmap *wnd, size_t FirstBit, size_t Bits); +bool wnd_is_used(struct wnd_bitmap *wnd, size_t FirstBit, size_t Bits); + +/* Possible values for 'flags' 'wnd_find' */ +#define BITMAP_FIND_MARK_AS_USED 0x01 +#define BITMAP_FIND_FULL 0x02 +size_t wnd_find(struct wnd_bitmap *wnd, size_t to_alloc, size_t hint, + size_t flags, size_t *allocated); +int wnd_extend(struct wnd_bitmap *wnd, size_t new_bits); +void wnd_zone_set(struct wnd_bitmap *wnd, size_t Lcn, size_t Len); +int ntfs_trim_fs(struct ntfs_sb_info *sbi, struct fstrim_range *range); + +/* globals from upcase.c */ +int ntfs_cmp_names(const __le16 *s1, size_t l1, const __le16 *s2, size_t l2, + const u16 *upcase); +int ntfs_cmp_names_cpu(const struct cpu_str *uni1, const struct le_str *uni2, + const u16 *upcase); + +/* globals from xattr.c */ +struct posix_acl *ntfs_get_acl(struct inode *inode, int type); +int ntfs_set_acl(struct inode *inode, struct posix_acl *acl, int type); +int ntfs_acl_chmod(struct inode *inode); +int ntfs_permission(struct inode *inode, int mask); +ssize_t ntfs_listxattr(struct dentry *dentry, char *buffer, size_t size); +int ntfs_init_acl(struct inode *inode, struct inode *dir); +extern const struct xattr_handler *ntfs_xattr_handlers[]; + +/* globals from lznt.c */ +struct lznt *get_compression_ctx(bool std); +size_t compress_lznt(const void *uncompressed, size_t uncompressed_size, + void *compressed, size_t compressed_size, + struct lznt *ctx); +ssize_t decompress_lznt(const void *compressed, size_t compressed_size, + void *uncompressed, size_t uncompressed_size); + +char *attr_str(const struct ATTRIB *attr, char *buf, size_t buf_len); + +static inline bool is_ntfs3(struct ntfs_sb_info *sbi) +{ + return sbi->volume.major_ver >= 3; +} + +/*(sb->s_flags & SB_ACTIVE)*/ +static inline bool is_mounted(struct ntfs_sb_info *sbi) +{ + return !!sbi->sb->s_root; +} + +static inline bool ntfs_is_meta_file(struct ntfs_sb_info *sbi, CLST rno) +{ + return rno < MFT_REC_FREE || rno == sbi->objid_no || + rno == sbi->quota_no || rno == sbi->reparse_no || + rno == sbi->usn_jrnl_no; +} + +static inline void ntfs_unmap_page(struct page *page) +{ + kunmap(page); + put_page(page); +} + +static inline struct page *ntfs_map_page(struct address_space *mapping, + unsigned long index) +{ + struct page *page = read_mapping_page(mapping, index, NULL); + + if (!IS_ERR(page)) { + kmap(page); + if (!PageError(page)) + return page; + ntfs_unmap_page(page); + return ERR_PTR(-EIO); + } + return page; +} + +static inline size_t wnd_zone_bit(const struct wnd_bitmap *wnd) +{ + return wnd->zone_bit; +} + +static inline size_t wnd_zone_len(const struct wnd_bitmap *wnd) +{ + return wnd->zone_end - wnd->zone_bit; +} + +static inline void run_init(struct runs_tree *run) +{ + run->runs_ = NULL; + run->count = 0; + run->allocated = 0; +} + +static inline struct runs_tree *run_alloc(void) +{ + return ntfs_alloc(sizeof(struct runs_tree), 1); +} + +static inline void run_close(struct runs_tree *run) +{ + ntfs_free(run->runs_); + memset(run, 0, sizeof(*run)); +} + +static inline void run_free(struct runs_tree *run) +{ + if (run) { + ntfs_free(run->runs_); + ntfs_free(run); + } +} + +static inline bool run_is_empty(struct runs_tree *run) +{ + return !run->count; +} + +/* NTFS uses quad aligned bitmaps */ +static inline size_t bitmap_size(size_t bits) +{ + return QuadAlign((bits + 7) >> 3); +} + +#define _100ns2seconds 10000000 +#define SecondsToStartOf1970 0x00000002B6109100 + +#define NTFS_TIME_GRAN 100 + +/* + * kernel2nt + * + * converts in-memory kernel timestamp into nt time + */ +static inline __le64 kernel2nt(const struct timespec64 *ts) +{ + // 10^7 units of 100 nanoseconds one second + return cpu_to_le64(_100ns2seconds * + (ts->tv_sec + SecondsToStartOf1970) + + ts->tv_nsec / NTFS_TIME_GRAN); +} + +/* + * nt2kernel + * + * converts on-disk nt time into kernel timestamp + */ +static inline void nt2kernel(const __le64 tm, struct timespec64 *ts) +{ + u64 t = le64_to_cpu(tm) - _100ns2seconds * SecondsToStartOf1970; + + // WARNING: do_div changes its first argument(!) + ts->tv_nsec = do_div(t, _100ns2seconds) * 100; + ts->tv_sec = t; +} + +static inline struct ntfs_sb_info *ntfs_sb(struct super_block *sb) +{ + return sb->s_fs_info; +} + +/* Align up on cluster boundary */ +static inline u64 ntfs_up_cluster(const struct ntfs_sb_info *sbi, u64 size) +{ + return (size + sbi->cluster_mask) & ~((u64)sbi->cluster_mask); +} + +/* Align up on cluster boundary */ +static inline u64 ntfs_up_block(const struct super_block *sb, u64 size) +{ + return (size + sb->s_blocksize - 1) & ~(u64)(sb->s_blocksize - 1); +} + +static inline CLST bytes_to_cluster(const struct ntfs_sb_info *sbi, u64 size) +{ + return (size + sbi->cluster_mask) >> sbi->cluster_bits; +} + +static inline u64 bytes_to_block(const struct super_block *sb, u64 size) +{ + return (size + sb->s_blocksize - 1) >> sb->s_blocksize_bits; +} + +/* calculates ((bytes + frame_size - 1)/frame_size)*frame_size; */ +static inline u64 ntfs_up_frame(const struct ntfs_sb_info *sbi, u64 bytes, + u8 c_unit) +{ + u32 bytes_per_frame = 1u << (c_unit + sbi->cluster_bits); + + return (bytes + bytes_per_frame - 1) & ~(u64)(bytes_per_frame - 1); +} + +static inline struct buffer_head *ntfs_bread(struct super_block *sb, + sector_t block) +{ + struct buffer_head *bh; + + bh = sb_bread(sb, block); + if (bh) + return bh; + + ntfs_err(sb, "failed to read volume at offset 0x%llx", + (u64)block << sb->s_blocksize_bits); + return NULL; +} + +static inline bool is_power_of2(size_t v) +{ + return v && !(v & (v - 1)); +} + +static inline struct ntfs_inode *ntfs_i(struct inode *inode) +{ + return container_of(inode, struct ntfs_inode, vfs_inode); +} + +static inline bool is_compressed(const struct ntfs_inode *ni) +{ + return (ni->std_fa & FILE_ATTRIBUTE_COMPRESSED) || + (ni->ni_flags & NI_FLAG_COMPRESSED_MASK); +} + +static inline bool is_dedup(const struct ntfs_inode *ni) +{ + return ni->ni_flags & NI_FLAG_DEDUPLICATED; +} + +static inline bool is_encrypted(const struct ntfs_inode *ni) +{ + return ni->std_fa & FILE_ATTRIBUTE_ENCRYPTED; +} + +static inline bool is_sparsed(const struct ntfs_inode *ni) +{ + return ni->std_fa & FILE_ATTRIBUTE_SPARSE_FILE; +} + +static inline void le16_sub_cpu(__le16 *var, u16 val) +{ + *var = cpu_to_le16(le16_to_cpu(*var) - val); +} + +static inline void le32_sub_cpu(__le32 *var, u32 val) +{ + *var = cpu_to_le32(le32_to_cpu(*var) - val); +} + +static inline void nb_put(struct ntfs_buffers *nb) +{ + u32 i, nbufs = nb->nbufs; + + if (!nbufs) + return; + + for (i = 0; i < nbufs; i++) + put_bh(nb->bh[i]); + nb->nbufs = 0; +} + +static inline void put_indx_node(struct indx_node *in) +{ + if (!in) + return; + + ntfs_free(in->index); + nb_put(&in->nb); + ntfs_free(in); +} + +static inline void mi_clear(struct mft_inode *mi) +{ + nb_put(&mi->nb); + ntfs_free(mi->mrec); + mi->mrec = NULL; +} + +static inline void ni_lock(struct ntfs_inode *ni) +{ + mutex_lock(&ni->ni_lock); +} + +static inline void ni_unlock(struct ntfs_inode *ni) +{ + mutex_unlock(&ni->ni_lock); +} + +static inline int ni_trylock(struct ntfs_inode *ni) +{ + return mutex_trylock(&ni->ni_lock); +} + +static inline int ni_has_resident_data(struct ntfs_inode *ni) +{ + return ni->ni_flags & NI_FLAG_RESIDENT; +} + +static inline int attr_load_runs_attr(struct ntfs_inode *ni, + struct ATTRIB *attr, + struct runs_tree *run, CLST vcn) +{ + return attr_load_runs_vcn(ni, attr->type, attr_name(attr), + attr->name_len, run, vcn); +} + +static inline void le64_sub_cpu(__le64 *var, u64 val) +{ + *var = cpu_to_le64(le64_to_cpu(*var) - val); +} diff --git a/fs/ntfs3/upcase.c b/fs/ntfs3/upcase.c new file mode 100644 index 000000000000..16e05a27c423 --- /dev/null +++ b/fs/ntfs3/upcase.c @@ -0,0 +1,78 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * linux/fs/ntfs3/upcase.c + * + * Copyright (C) 2019-2020 Paragon Software GmbH, All rights reserved. + * + */ +#include +#include +#include +#include + +#include "debug.h" +#include "ntfs.h" +#include "ntfs_fs.h" + +static inline u16 upcase_unicode_char(const u16 *upcase, u16 chr) +{ + if (chr < 'a') + return chr; + + if (chr <= 'z') + return chr - ('a' - 'A'); + + return upcase[chr]; +} + +int ntfs_cmp_names(const __le16 *s1, size_t l1, const __le16 *s2, size_t l2, + const u16 *upcase) +{ + int diff; + size_t len = l1 < l2 ? l1 : l2; + + if (upcase) { + while (len--) { + diff = upcase_unicode_char(upcase, le16_to_cpu(*s1++)) - + upcase_unicode_char(upcase, le16_to_cpu(*s2++)); + if (diff) + return diff; + } + } else { + while (len--) { + diff = le16_to_cpu(*s1++) - le16_to_cpu(*s2++); + if (diff) + return diff; + } + } + + return (int)(l1 - l2); +} + +int ntfs_cmp_names_cpu(const struct cpu_str *uni1, const struct le_str *uni2, + const u16 *upcase) +{ + const u16 *s1 = uni1->name; + const __le16 *s2 = uni2->name; + size_t l1 = uni1->len; + size_t l2 = uni2->len; + size_t len = l1 < l2 ? l1 : l2; + int diff; + + if (upcase) { + while (len--) { + diff = upcase_unicode_char(upcase, *s1++) - + upcase_unicode_char(upcase, le16_to_cpu(*s2++)); + if (diff) + return diff; + } + } else { + while (len--) { + diff = *s1++ - le16_to_cpu(*s2++); + if (diff) + return diff; + } + } + + return l1 - l2; +} From patchwork Fri Oct 9 14:22:53 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Konstantin Komarov X-Patchwork-Id: 11825963 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 9686C14D5 for ; Fri, 9 Oct 2020 14:23:57 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 45F14222C3 for ; Fri, 9 Oct 2020 14:23:57 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (1024-bit key) header.d=paragon-software.com header.i=@paragon-software.com header.b="Ru64+mhP" Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S2388798AbgJIOX4 (ORCPT ); Fri, 9 Oct 2020 10:23:56 -0400 Received: from relayfre-01.paragon-software.com ([176.12.100.13]:52122 "EHLO relayfre-01.paragon-software.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S2387662AbgJIOXW (ORCPT ); Fri, 9 Oct 2020 10:23:22 -0400 Received: from dlg2.mail.paragon-software.com (vdlg-exch-02.paragon-software.com [172.30.1.105]) by relayfre-01.paragon-software.com (Postfix) with ESMTPS id CBBEF2119; Fri, 9 Oct 2020 17:23:08 +0300 (MSK) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=paragon-software.com; s=mail; t=1602253388; bh=kqkoxQaBcspZRa4K6t7gq4gd/pZu/SEWZ//sG9enmtQ=; h=From:To:CC:Subject:Date:In-Reply-To:References; b=Ru64+mhPDuBuTal+XWAiBw3LHpOY1l4RUiwlFfmKQy7KrDsn0FVVGPNvUNMhI3Z12 Hu8I8V3kKJ41L38fyAlo/5baQNdAMuj5HHpYbpMRBdisvJbXVwO3Rp0sfiTWGm06Wy KhX7ZhJmBOlSz7+Bafc8NXM85/s1xSvpriNz2LnQ= Received: from fsd-lkpg.ufsd.paragon-software.com (172.30.114.105) by vdlg-exch-02.paragon-software.com (172.30.1.105) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id 15.1.1847.3; Fri, 9 Oct 2020 17:23:07 +0300 From: Konstantin Komarov To: CC: , , , , , , , , , , , , Konstantin Komarov Subject: [PATCH v8 02/10] fs/ntfs3: Add initialization of super block Date: Fri, 9 Oct 2020 17:22:53 +0300 Message-ID: <20201009142301.412454-3-almaz.alexandrovich@paragon-software.com> X-Mailer: git-send-email 2.25.4 In-Reply-To: <20201009142301.412454-1-almaz.alexandrovich@paragon-software.com> References: <20201009142301.412454-1-almaz.alexandrovich@paragon-software.com> MIME-Version: 1.0 X-Originating-IP: [172.30.114.105] X-ClientProxiedBy: vdlg-exch-02.paragon-software.com (172.30.1.105) To vdlg-exch-02.paragon-software.com (172.30.1.105) Precedence: bulk List-ID: X-Mailing-List: linux-fsdevel@vger.kernel.org This adds initialization of super block Signed-off-by: Konstantin Komarov --- fs/ntfs3/fsntfs.c | 2385 ++++++++++++++++++++++++++++++++++++++++ fs/ntfs3/index.c | 2646 +++++++++++++++++++++++++++++++++++++++++++++ fs/ntfs3/inode.c | 1956 +++++++++++++++++++++++++++++++++ fs/ntfs3/super.c | 1489 +++++++++++++++++++++++++ 4 files changed, 8476 insertions(+) create mode 100644 fs/ntfs3/fsntfs.c create mode 100644 fs/ntfs3/index.c create mode 100644 fs/ntfs3/inode.c create mode 100644 fs/ntfs3/super.c diff --git a/fs/ntfs3/fsntfs.c b/fs/ntfs3/fsntfs.c new file mode 100644 index 000000000000..03554ad50ad6 --- /dev/null +++ b/fs/ntfs3/fsntfs.c @@ -0,0 +1,2385 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * linux/fs/ntfs3/fsntfs.c + * + * Copyright (C) 2019-2020 Paragon Software GmbH, All rights reserved. + * + */ + +#include +#include +#include +#include +#include + +#include "debug.h" +#include "ntfs.h" +#include "ntfs_fs.h" + +const struct cpu_str NAME_MFT = { + 4, + 0, + { '$', 'M', 'F', 'T' }, +}; +const struct cpu_str NAME_MIRROR = { + 8, + 0, + { '$', 'M', 'F', 'T', 'M', 'i', 'r', 'r' }, +}; +const struct cpu_str NAME_LOGFILE = { + 8, + 0, + { '$', 'L', 'o', 'g', 'F', 'i', 'l', 'e' }, +}; +const struct cpu_str NAME_VOLUME = { + 7, + 0, + { '$', 'V', 'o', 'l', 'u', 'm', 'e' }, +}; +const struct cpu_str NAME_ATTRDEF = { + 8, + 0, + { '$', 'A', 't', 't', 'r', 'D', 'e', 'f' }, +}; +const struct cpu_str NAME_ROOT = { + 1, + 0, + { '.' }, +}; +const struct cpu_str NAME_BITMAP = { + 7, + 0, + { '$', 'B', 'i', 't', 'm', 'a', 'p' }, +}; +const struct cpu_str NAME_BOOT = { + 5, + 0, + { '$', 'B', 'o', 'o', 't' }, +}; +const struct cpu_str NAME_BADCLUS = { + 8, + 0, + { '$', 'B', 'a', 'd', 'C', 'l', 'u', 's' }, +}; +const struct cpu_str NAME_QUOTA = { + 6, + 0, + { '$', 'Q', 'u', 'o', 't', 'a' }, +}; +const struct cpu_str NAME_SECURE = { + 7, + 0, + { '$', 'S', 'e', 'c', 'u', 'r', 'e' }, +}; +const struct cpu_str NAME_UPCASE = { + 7, + 0, + { '$', 'U', 'p', 'C', 'a', 's', 'e' }, +}; +const struct cpu_str NAME_EXTEND = { + 7, + 0, + { '$', 'E', 'x', 't', 'e', 'n', 'd' }, +}; +const struct cpu_str NAME_OBJID = { + 6, + 0, + { '$', 'O', 'b', 'j', 'I', 'd' }, +}; +const struct cpu_str NAME_REPARSE = { + 8, + 0, + { '$', 'R', 'e', 'p', 'a', 'r', 's', 'e' }, +}; +const struct cpu_str NAME_USNJRNL = { + 8, + 0, + { '$', 'U', 's', 'n', 'J', 'r', 'n', 'l' }, +}; +const __le16 BAD_NAME[4] = { + cpu_to_le16('$'), + cpu_to_le16('B'), + cpu_to_le16('a'), + cpu_to_le16('d'), +}; +const __le16 I30_NAME[4] = { + cpu_to_le16('$'), + cpu_to_le16('I'), + cpu_to_le16('3'), + cpu_to_le16('0'), +}; +const __le16 SII_NAME[4] = { + cpu_to_le16('$'), + cpu_to_le16('S'), + cpu_to_le16('I'), + cpu_to_le16('I'), +}; +const __le16 SDH_NAME[4] = { + cpu_to_le16('$'), + cpu_to_le16('S'), + cpu_to_le16('D'), + cpu_to_le16('H'), +}; +const __le16 SDS_NAME[4] = { + cpu_to_le16('$'), + cpu_to_le16('S'), + cpu_to_le16('D'), + cpu_to_le16('S'), +}; +const __le16 SO_NAME[2] = { + cpu_to_le16('$'), + cpu_to_le16('O'), +}; +const __le16 SQ_NAME[2] = { + cpu_to_le16('$'), + cpu_to_le16('Q'), +}; +const __le16 SR_NAME[2] = { + cpu_to_le16('$'), + cpu_to_le16('R'), +}; +//const __le16 EFS_NAME[4] = { '$', 'E', 'F', 'S' }; + +//const __le16 WOF_NAME[17] = { 'W', 'o', 'f', 'C', 'o', 'm', 'p', 'r', 'e', +// 'S', 'S', 'e', 'd', 'D', 'a', 't', 'a' }; +//const __le16 J_NAME[2] = { '$', 'J' }; +//const __le16 MAX_NAME[4] = { '$', 'M', 'a', 'x' }; + +/* + * ntfs_fix_pre_write + * + * inserts fixups into 'rhdr' before writing to disk + */ +bool ntfs_fix_pre_write(struct NTFS_RECORD_HEADER *rhdr, size_t bytes) +{ + u16 *fixup, *ptr; + u16 sample; + u16 fo = le16_to_cpu(rhdr->fix_off); + u16 fn = le16_to_cpu(rhdr->fix_num); + + if ((fo & 1) || fo + fn * sizeof(short) > SECTOR_SIZE || !fn-- || + fn * SECTOR_SIZE > bytes) { + return false; + } + + /* Get fixup pointer */ + fixup = Add2Ptr(rhdr, fo); + + if (*fixup >= 0x7FFF) + *fixup = 1; + else + *fixup += 1; + + sample = *fixup; + + ptr = Add2Ptr(rhdr, SECTOR_SIZE - sizeof(short)); + + while (fn--) { + *++fixup = *ptr; + *ptr = sample; + ptr += SECTOR_SIZE / sizeof(short); + } + return true; +} + +/* + * ntfs_fix_post_read + * + * remove fixups after reading from disk + * Returns < 0 if error, 0 if ok, 1 if need to update fixups + */ +int ntfs_fix_post_read(struct NTFS_RECORD_HEADER *rhdr, size_t bytes, + bool simple) +{ + int ret; + u16 *fixup, *ptr; + u16 sample, fo, fn; + + fo = le16_to_cpu(rhdr->fix_off); + fn = simple ? ((bytes >> SECTOR_SHIFT) + 1) : + le16_to_cpu(rhdr->fix_num); + + /* Check errors */ + if ((fo & 1) || fo + fn * sizeof(short) > SECTOR_SIZE || !fn-- || + fn * SECTOR_SIZE > bytes) { + return -EINVAL; /* native chkntfs returns ok! */ + } + + /* Get fixup pointer */ + fixup = Add2Ptr(rhdr, fo); + sample = *fixup; + ptr = Add2Ptr(rhdr, SECTOR_SIZE - sizeof(short)); + ret = 0; + + while (fn--) { + /* Test current word */ + if (*ptr != sample) + ret = 1; + + /* Replace fixup */ + *ptr = *++fixup; + ptr += SECTOR_SIZE / sizeof(short); + } + + return ret; +} + +/* + * ntfs_extend_init + * + * loads $Extend file + */ +int ntfs_extend_init(struct ntfs_sb_info *sbi) +{ + int err; + struct super_block *sb = sbi->sb; + struct inode *inode, *inode2; + struct MFT_REF ref; + + if (sbi->volume.major_ver < 3) { + ntfs_notice(sb, "Skip $Extend 'cause NTFS version"); + return 0; + } + + ref.low = cpu_to_le32(MFT_REC_EXTEND); + ref.high = 0; + ref.seq = cpu_to_le16(MFT_REC_EXTEND); + inode = ntfs_iget5(sb, &ref, &NAME_EXTEND); + if (IS_ERR(inode)) { + err = PTR_ERR(inode); + ntfs_err(sb, "Failed to load $Extend."); + inode = NULL; + goto out; + } + + /* if ntfs_iget5 reads from disk it never returns bad inode */ + if (!S_ISDIR(inode->i_mode)) { + err = -EINVAL; + goto out; + } + + /* Try to find $ObjId */ + inode2 = dir_search_u(inode, &NAME_OBJID, NULL); + if (inode2 && !IS_ERR(inode2)) { + if (is_bad_inode(inode2)) { + iput(inode2); + } else { + sbi->objid.ni = ntfs_i(inode2); + sbi->objid_no = inode2->i_ino; + } + } + + /* Try to find $Quota */ + inode2 = dir_search_u(inode, &NAME_QUOTA, NULL); + if (inode2 && !IS_ERR(inode2)) { + sbi->quota_no = inode2->i_ino; + iput(inode2); + } + + /* Try to find $Reparse */ + inode2 = dir_search_u(inode, &NAME_REPARSE, NULL); + if (inode2 && !IS_ERR(inode2)) { + sbi->reparse.ni = ntfs_i(inode2); + sbi->reparse_no = inode2->i_ino; + } + + /* Try to find $UsnJrnl */ + inode2 = dir_search_u(inode, &NAME_USNJRNL, NULL); + if (inode2 && !IS_ERR(inode2)) { + sbi->usn_jrnl_no = inode2->i_ino; + iput(inode2); + } + + err = 0; +out: + iput(inode); + return err; +} + +int ntfs_loadlog_and_replay(struct ntfs_inode *ni, struct ntfs_sb_info *sbi) +{ + int err = 0; + struct super_block *sb = sbi->sb; + struct inode *inode; + struct MFT_REF ref; + u32 idx; + CLST lcn, len; + + inode = &ni->vfs_inode; + + /* Check for 4GB */ + if (inode->i_size >= 0x100000000ull) { + ntfs_err(sb, "$LogFile is too big"); + err = -EINVAL; + goto out; + } + + sbi->flags |= NTFS_FLAGS_LOG_REPLAYING; + + ref.low = cpu_to_le32(MFT_REC_MFT); + ref.high = 0; + ref.seq = cpu_to_le16(1); + + inode = ntfs_iget5(sb, &ref, NULL); + + if (IS_ERR(inode)) + inode = NULL; + + if (!inode) { + /* Try to use mft copy */ + u64 t64 = sbi->mft.lbo; + + sbi->mft.lbo = sbi->mft.lbo2; + inode = ntfs_iget5(sb, &ref, NULL); + sbi->mft.lbo = t64; + if (IS_ERR(inode)) + inode = NULL; + } + + if (!inode) { + err = -EINVAL; + ntfs_err(sb, "Failed to load $MFT."); + goto out; + } + + sbi->mft.ni = ntfs_i(inode); + + err = ni_load_all_mi(sbi->mft.ni); + if (!err) + err = log_replay(ni); + + iput(inode); + sbi->mft.ni = NULL; + + sync_blockdev(sb->s_bdev); + invalidate_bdev(sb->s_bdev); + + /* reinit MFT */ + if (sbi->flags & NTFS_FLAGS_NEED_REPLAY) { + err = 0; + goto out; + } + + if (sb_rdonly(sb)) + goto out; + + idx = 0; + while (run_get_entry(&ni->file.run, idx++, NULL, &lcn, &len)) { + u64 lbo = (u64)lcn << sbi->cluster_bits; + u64 bytes = (u64)len << sbi->cluster_bits; + + err = ntfs_sb_write(sb, lbo, bytes, NULL, 0); + if (err) + goto out; + } + +out: + sbi->flags &= ~NTFS_FLAGS_LOG_REPLAYING; + + return err; +} + +/* + * ntfs_query_def + * + * returns current ATTR_DEF_ENTRY for given attribute type + */ +const struct ATTR_DEF_ENTRY *ntfs_query_def(struct ntfs_sb_info *sbi, + enum ATTR_TYPE type) +{ + int type_in = le32_to_cpu(type); + size_t min_idx = 0; + size_t max_idx = sbi->def_entries - 1; + + while (min_idx <= max_idx) { + size_t i = min_idx + ((max_idx - min_idx) >> 1); + const struct ATTR_DEF_ENTRY *entry = sbi->def_table + i; + int diff = le32_to_cpu(entry->type) - type_in; + + if (!diff) + return entry; + if (diff < 0) + min_idx = i + 1; + else if (i) + max_idx = i - 1; + else + return NULL; + } + return NULL; +} + +/* + * ntfs_look_for_free_space + * + * looks for a free space in bitmap + */ +int ntfs_look_for_free_space(struct ntfs_sb_info *sbi, CLST lcn, CLST len, + CLST *new_lcn, CLST *new_len, + enum ALLOCATE_OPT opt) +{ + int err; + struct super_block *sb = sbi->sb; + size_t a_lcn, zlen, zeroes, zlcn, zlen2, ztrim, new_zlen; + struct wnd_bitmap *wnd = &sbi->used.bitmap; + + down_write_nested(&wnd->rw_lock, BITMAP_MUTEX_CLUSTERS); + if (opt & ALLOCATE_MFT) { + CLST alen; + + zlen = wnd_zone_len(wnd); + + if (!zlen) { + err = ntfs_refresh_zone(sbi); + if (err) + goto out; + + zlen = wnd_zone_len(wnd); + + if (!zlen) { + ntfs_err(sbi->sb, + "no free space to extend mft"); + err = -ENOSPC; + goto out; + } + } + + lcn = wnd_zone_bit(wnd); + alen = zlen > len ? len : zlen; + + wnd_zone_set(wnd, lcn + alen, zlen - alen); + + err = wnd_set_used(wnd, lcn, alen); + if (err) + goto out; + + *new_lcn = lcn; + *new_len = alen; + goto ok; + } + + /* + * 'Cause cluster 0 is always used this value means that we should use + * cached value of 'next_free_lcn' to improve performance + */ + if (!lcn) + lcn = sbi->used.next_free_lcn; + + if (lcn >= wnd->nbits) + lcn = 0; + + *new_len = wnd_find(wnd, len, lcn, BITMAP_FIND_MARK_AS_USED, &a_lcn); + if (*new_len) { + *new_lcn = a_lcn; + goto ok; + } + + /* Try to use clusters from MftZone */ + zlen = wnd_zone_len(wnd); + zeroes = wnd_zeroes(wnd); + + /* Check too big request */ + if (len > zeroes + zlen) + goto no_space; + + if (zlen <= NTFS_MIN_MFT_ZONE) + goto no_space; + + /* How many clusters to cat from zone */ + zlcn = wnd_zone_bit(wnd); + zlen2 = zlen >> 1; + ztrim = len > zlen ? zlen : (len > zlen2 ? len : zlen2); + new_zlen = zlen - ztrim; + + if (new_zlen < NTFS_MIN_MFT_ZONE) { + new_zlen = NTFS_MIN_MFT_ZONE; + if (new_zlen > zlen) + new_zlen = zlen; + } + + wnd_zone_set(wnd, zlcn, new_zlen); + + /* allocate continues clusters */ + *new_len = + wnd_find(wnd, len, 0, + BITMAP_FIND_MARK_AS_USED | BITMAP_FIND_FULL, &a_lcn); + if (*new_len) { + *new_lcn = a_lcn; + goto ok; + } + +no_space: + up_write(&wnd->rw_lock); + + return -ENOSPC; + +ok: + err = 0; + + ntfs_unmap_meta(sb, *new_lcn, *new_len); + + if (opt & ALLOCATE_MFT) + goto out; + + /* Set hint for next requests */ + sbi->used.next_free_lcn = *new_lcn + *new_len; + +out: + up_write(&wnd->rw_lock); + return err; +} + +/* + * ntfs_extend_mft + * + * allocates additional MFT records + * sbi->mft.bitmap is locked for write + * + * NOTE: recursive: + * ntfs_look_free_mft -> + * ntfs_extend_mft -> + * attr_set_size -> + * ni_insert_nonresident -> + * ni_insert_attr -> + * ni_ins_attr_ext -> + * ntfs_look_free_mft -> + * ntfs_extend_mft + * To avoid recursive always allocate space for two new mft records + * see attrib.c: "at least two mft to avoid recursive loop" + */ +static int ntfs_extend_mft(struct ntfs_sb_info *sbi) +{ + int err; + struct ntfs_inode *ni = sbi->mft.ni; + size_t new_mft_total; + u64 new_mft_bytes, new_bitmap_bytes; + struct ATTRIB *attr; + struct wnd_bitmap *wnd = &sbi->mft.bitmap; + + new_mft_total = (wnd->nbits + MFT_INCREASE_CHUNK + 127) & (CLST)~127; + new_mft_bytes = (u64)new_mft_total << sbi->record_bits; + + /* Step 1: Resize $MFT::DATA */ + down_write(&ni->file.run_lock); + err = attr_set_size(ni, ATTR_DATA, NULL, 0, &ni->file.run, + new_mft_bytes, NULL, false, &attr); + + if (err) { + up_write(&ni->file.run_lock); + goto out; + } + + attr->nres.valid_size = attr->nres.data_size; + new_mft_total = le64_to_cpu(attr->nres.alloc_size) >> sbi->record_bits; + ni->mi.dirty = true; + + /* Step 2: Resize $MFT::BITMAP */ + new_bitmap_bytes = bitmap_size(new_mft_total); + + err = attr_set_size(ni, ATTR_BITMAP, NULL, 0, &sbi->mft.bitmap.run, + new_bitmap_bytes, &new_bitmap_bytes, true, NULL); + + /* Refresh Mft Zone if necessary */ + down_write_nested(&sbi->used.bitmap.rw_lock, BITMAP_MUTEX_CLUSTERS); + + ntfs_refresh_zone(sbi); + + up_write(&sbi->used.bitmap.rw_lock); + up_write(&ni->file.run_lock); + + if (err) + goto out; + + err = wnd_extend(wnd, new_mft_total); + + if (err) + goto out; + + ntfs_clear_mft_tail(sbi, sbi->mft.used, new_mft_total); + + err = _ni_write_inode(&ni->vfs_inode, 0); +out: + return err; +} + +/* + * ntfs_look_free_mft + * + * looks for a free MFT record + */ +int ntfs_look_free_mft(struct ntfs_sb_info *sbi, CLST *rno, bool mft, + struct ntfs_inode *ni, struct mft_inode **mi) +{ + int err = 0; + size_t zbit, zlen, from, to, fr; + size_t mft_total; + struct MFT_REF ref; + struct super_block *sb = sbi->sb; + struct wnd_bitmap *wnd = &sbi->mft.bitmap; + u32 ir; + + static_assert(sizeof(sbi->mft.reserved_bitmap) * 8 >= + MFT_REC_FREE - MFT_REC_RESERVED); + + if (!mft) + down_write_nested(&wnd->rw_lock, BITMAP_MUTEX_MFT); + + zlen = wnd_zone_len(wnd); + + /* Always reserve space for MFT */ + if (zlen) { + if (mft) { + zbit = wnd_zone_bit(wnd); + *rno = zbit; + wnd_zone_set(wnd, zbit + 1, zlen - 1); + } + goto found; + } + + /* No MFT zone. find the nearest to '0' free MFT */ + if (!wnd_find(wnd, 1, MFT_REC_FREE, 0, &zbit)) { + /* Resize MFT */ + mft_total = wnd->nbits; + + err = ntfs_extend_mft(sbi); + if (!err) { + zbit = mft_total; + goto reserve_mft; + } + + if (!mft || MFT_REC_FREE == sbi->mft.next_reserved) + goto out; + + err = 0; + + /* + * Look for free record reserved area [11-16) == + * [MFT_REC_RESERVED, MFT_REC_FREE ) MFT bitmap always + * marks it as used + */ + if (!sbi->mft.reserved_bitmap) { + /* Once per session create internal bitmap for 5 bits */ + sbi->mft.reserved_bitmap = 0xFF; + + ref.high = 0; + for (ir = MFT_REC_RESERVED; ir < MFT_REC_FREE; ir++) { + struct inode *i; + struct ntfs_inode *ni; + struct MFT_REC *mrec; + + ref.low = cpu_to_le32(ir); + ref.seq = cpu_to_le16(ir); + + i = ntfs_iget5(sb, &ref, NULL); + if (IS_ERR(i)) { +next: + ntfs_notice( + sb, + "Invalid reserved record %x", + ref.low); + continue; + } + if (is_bad_inode(i)) { + iput(i); + goto next; + } + + ni = ntfs_i(i); + + mrec = ni->mi.mrec; + + if (!is_rec_base(mrec)) + goto next; + + if (mrec->hard_links) + goto next; + + if (!ni_std(ni)) + goto next; + + if (ni_find_attr(ni, NULL, NULL, ATTR_NAME, + NULL, 0, NULL, NULL)) + goto next; + + __clear_bit(ir - MFT_REC_RESERVED, + &sbi->mft.reserved_bitmap); + } + } + + /* Scan 5 bits for zero. Bit 0 == MFT_REC_RESERVED */ + zbit = find_next_zero_bit(&sbi->mft.reserved_bitmap, + MFT_REC_FREE, MFT_REC_RESERVED); + if (zbit >= MFT_REC_FREE) { + sbi->mft.next_reserved = MFT_REC_FREE; + goto out; + } + + zlen = 1; + sbi->mft.next_reserved = zbit; + } else { +reserve_mft: + zlen = zbit == MFT_REC_FREE ? (MFT_REC_USER - MFT_REC_FREE) : 4; + if (zbit + zlen > wnd->nbits) + zlen = wnd->nbits - zbit; + + while (zlen > 1 && !wnd_is_free(wnd, zbit, zlen)) + zlen -= 1; + + /* [zbit, zbit + zlen) will be used for Mft itself */ + from = sbi->mft.used; + if (from < zbit) + from = zbit; + to = zbit + zlen; + if (from < to) { + ntfs_clear_mft_tail(sbi, from, to); + sbi->mft.used = to; + } + } + + if (mft) { + *rno = zbit; + zbit += 1; + zlen -= 1; + } + + wnd_zone_set(wnd, zbit, zlen); + +found: + if (!mft) { + /* The request to get record for general purpose */ + if (sbi->mft.next_free < MFT_REC_USER) + sbi->mft.next_free = MFT_REC_USER; + + for (;;) { + if (sbi->mft.next_free >= sbi->mft.bitmap.nbits) { + } else if (!wnd_find(wnd, 1, MFT_REC_USER, 0, &fr)) { + sbi->mft.next_free = sbi->mft.bitmap.nbits; + } else { + *rno = fr; + sbi->mft.next_free = *rno + 1; + break; + } + + err = ntfs_extend_mft(sbi); + if (err) + goto out; + } + } + + if (ni && !ni_add_subrecord(ni, *rno, mi)) { + err = -ENOMEM; + goto out; + } + + /* We have found a record that are not reserved for next MFT */ + if (*rno >= MFT_REC_FREE) + wnd_set_used(wnd, *rno, 1); + else if (*rno >= MFT_REC_RESERVED && sbi->mft.reserved_bitmap_inited) + __set_bit(*rno - MFT_REC_RESERVED, &sbi->mft.reserved_bitmap); + +out: + if (!mft) + up_write(&wnd->rw_lock); + + return err; +} + +/* + * ntfs_mark_rec_free + * + * marks record as free + */ +void ntfs_mark_rec_free(struct ntfs_sb_info *sbi, CLST rno) +{ + struct wnd_bitmap *wnd = &sbi->mft.bitmap; + + down_write_nested(&wnd->rw_lock, BITMAP_MUTEX_MFT); + if (rno >= wnd->nbits) + goto out; + + if (rno >= MFT_REC_FREE) { + if (!wnd_is_used(wnd, rno, 1)) + ntfs_set_state(sbi, NTFS_DIRTY_ERROR); + else + wnd_set_free(wnd, rno, 1); + } else if (rno >= MFT_REC_RESERVED && sbi->mft.reserved_bitmap_inited) { + __clear_bit(rno - MFT_REC_RESERVED, &sbi->mft.reserved_bitmap); + } + + if (rno < wnd_zone_bit(wnd)) + wnd_zone_set(wnd, rno, 1); + else if (rno < sbi->mft.next_free && rno >= MFT_REC_USER) + sbi->mft.next_free = rno; + +out: + up_write(&wnd->rw_lock); +} + +/* + * ntfs_clear_mft_tail + * + * formats empty records [from, to) + * sbi->mft.bitmap is locked for write + */ +int ntfs_clear_mft_tail(struct ntfs_sb_info *sbi, size_t from, size_t to) +{ + int err; + u32 rs; + u64 vbo; + struct runs_tree *run; + struct ntfs_inode *ni; + + if (from >= to) + return 0; + + rs = sbi->record_size; + ni = sbi->mft.ni; + run = &ni->file.run; + + down_read(&ni->file.run_lock); + vbo = (u64)from * rs; + for (; from < to; from++, vbo += rs) { + struct ntfs_buffers nb; + + err = ntfs_get_bh(sbi, run, vbo, rs, &nb); + if (err) + goto out; + + err = ntfs_write_bh(sbi, &sbi->new_rec->rhdr, &nb, 0); + nb_put(&nb); + if (err) + goto out; + } + +out: + sbi->mft.used = from; + up_read(&ni->file.run_lock); + return err; +} + +/* + * ntfs_refresh_zone + * + * refreshes Mft zone + * sbi->used.bitmap is locked for rw + * sbi->mft.bitmap is locked for write + * sbi->mft.ni->file.run_lock for write + */ +int ntfs_refresh_zone(struct ntfs_sb_info *sbi) +{ + CLST zone_limit, zone_max, lcn, vcn, len; + size_t lcn_s, zlen; + struct wnd_bitmap *wnd = &sbi->used.bitmap; + struct ntfs_inode *ni = sbi->mft.ni; + + /* Do not change anything unless we have non empty Mft zone */ + if (wnd_zone_len(wnd)) + return 0; + + /* + * Compute the mft zone at two steps + * It would be nice if we are able to allocate + * 1/8 of total clusters for MFT but not more then 512 MB + */ + zone_limit = (512 * 1024 * 1024) >> sbi->cluster_bits; + zone_max = wnd->nbits >> 3; + if (zone_max > zone_limit) + zone_max = zone_limit; + + vcn = bytes_to_cluster(sbi, + (u64)sbi->mft.bitmap.nbits << sbi->record_bits); + + if (!run_lookup_entry(&ni->file.run, vcn - 1, &lcn, &len, NULL)) + lcn = SPARSE_LCN; + + /* We should always find Last Lcn for MFT */ + if (lcn == SPARSE_LCN) + return -EINVAL; + + lcn_s = lcn + 1; + + /* Try to allocate clusters after last MFT run */ + zlen = wnd_find(wnd, zone_max, lcn_s, 0, &lcn_s); + if (!zlen) { + ntfs_notice(sbi->sb, "MftZone: unavailable"); + return 0; + } + + /* Truncate too large zone */ + wnd_zone_set(wnd, lcn_s, zlen); + + return 0; +} + +/* + * ntfs_update_mftmirr + * + * updates $MFTMirr data + */ +int ntfs_update_mftmirr(struct ntfs_sb_info *sbi, int wait) +{ + int err; + struct super_block *sb = sbi->sb; + u32 blocksize = sb->s_blocksize; + sector_t block1, block2; + u32 bytes; + + if (!(sbi->flags & NTFS_FLAGS_MFTMIRR)) + return 0; + + err = 0; + bytes = sbi->mft.recs_mirr << sbi->record_bits; + block1 = sbi->mft.lbo >> sb->s_blocksize_bits; + block2 = sbi->mft.lbo2 >> sb->s_blocksize_bits; + + for (; bytes >= blocksize; bytes -= blocksize) { + struct buffer_head *bh1, *bh2; + + bh1 = sb_bread(sb, block1++); + if (!bh1) { + err = -EIO; + goto out; + } + + bh2 = sb_getblk(sb, block2++); + if (!bh2) { + put_bh(bh1); + err = -EIO; + goto out; + } + + if (buffer_locked(bh2)) + __wait_on_buffer(bh2); + + lock_buffer(bh2); + memcpy(bh2->b_data, bh1->b_data, blocksize); + set_buffer_uptodate(bh2); + mark_buffer_dirty(bh2); + unlock_buffer(bh2); + + put_bh(bh1); + bh1 = NULL; + + if (wait) + err = sync_dirty_buffer(bh2); + + put_bh(bh2); + if (err) + goto out; + } + + sbi->flags &= ~NTFS_FLAGS_MFTMIRR; + +out: + return err; +} + +/* + * ntfs_set_state + * + * mount: ntfs_set_state(NTFS_DIRTY_DIRTY) + * umount: ntfs_set_state(NTFS_DIRTY_CLEAR) + * ntfs error: ntfs_set_state(NTFS_DIRTY_ERROR) + */ +int ntfs_set_state(struct ntfs_sb_info *sbi, enum NTFS_DIRTY_FLAGS dirty) +{ + int err; + struct ATTRIB *attr; + struct VOLUME_INFO *info; + struct mft_inode *mi; + struct ntfs_inode *ni; + + /* + * do not change state if fs was real_dirty + * do not change state if fs already dirty(clear) + * do not change any thing if mounted read only + */ + if (sbi->volume.real_dirty || sb_rdonly(sbi->sb)) + return 0; + + /* Check cached value */ + if ((dirty == NTFS_DIRTY_CLEAR ? 0 : VOLUME_FLAG_DIRTY) == + (sbi->volume.flags & VOLUME_FLAG_DIRTY)) + return 0; + + ni = sbi->volume.ni; + if (!ni) + return -EINVAL; + + inode_lock(&ni->vfs_inode); + + attr = ni_find_attr(ni, NULL, NULL, ATTR_VOL_INFO, NULL, 0, NULL, &mi); + if (!attr) { + err = -EINVAL; + goto out; + } + + info = resident_data_ex(attr, SIZEOF_ATTRIBUTE_VOLUME_INFO); + if (!info) { + err = -EINVAL; + goto out; + } + + switch (dirty) { + case NTFS_DIRTY_ERROR: + ntfs_notice(sbi->sb, "Mark volume as dirty due to NTFS errors"); + sbi->volume.real_dirty = true; + fallthrough; + case NTFS_DIRTY_DIRTY: + info->flags |= VOLUME_FLAG_DIRTY; + break; + case NTFS_DIRTY_CLEAR: + info->flags &= ~VOLUME_FLAG_DIRTY; + break; + } + /* cache current volume flags*/ + sbi->volume.flags = info->flags; + mi->dirty = true; + err = 0; + +out: + inode_unlock(&ni->vfs_inode); + if (err) + return err; + + mark_inode_dirty(&ni->vfs_inode); + /*verify(!ntfs_update_mftmirr()); */ + err = sync_inode_metadata(&ni->vfs_inode, 1); + + return err; +} + +/* + * security_hash + * + * calculates a hash of security descriptor + */ +static inline __le32 security_hash(const void *sd, size_t bytes) +{ + u32 hash = 0; + const __le32 *ptr = sd; + + bytes >>= 2; + while (bytes--) + hash = ((hash >> 0x1D) | (hash << 3)) + le32_to_cpu(*ptr++); + return cpu_to_le32(hash); +} + +int ntfs_sb_read(struct super_block *sb, u64 lbo, size_t bytes, void *buffer) +{ + struct block_device *bdev = sb->s_bdev; + u32 blocksize = sb->s_blocksize; + u64 block = lbo >> sb->s_blocksize_bits; + u32 off = lbo & (blocksize - 1); + u32 op = blocksize - off; + + for (; bytes; block += 1, off = 0, op = blocksize) { + struct buffer_head *bh = __bread(bdev, block, blocksize); + + if (!bh) + return -EIO; + + if (op > bytes) + op = bytes; + + memcpy(buffer, bh->b_data + off, op); + + put_bh(bh); + + bytes -= op; + buffer = Add2Ptr(buffer, op); + } + + return 0; +} + +int ntfs_sb_write(struct super_block *sb, u64 lbo, size_t bytes, + const void *buf, int wait) +{ + u32 blocksize = sb->s_blocksize; + struct block_device *bdev = sb->s_bdev; + sector_t block = lbo >> sb->s_blocksize_bits; + u32 off = lbo & (blocksize - 1); + u32 op = blocksize - off; + struct buffer_head *bh; + + if (!wait && (sb->s_flags & SB_SYNCHRONOUS)) + wait = 1; + + for (; bytes; block += 1, off = 0, op = blocksize) { + if (op > bytes) + op = bytes; + + if (op < blocksize) { + bh = __bread(bdev, block, blocksize); + if (!bh) { + ntfs_err(sb, "failed to read block %llx", + (u64)block); + return -EIO; + } + } else { + bh = __getblk(bdev, block, blocksize); + if (!bh) + return -ENOMEM; + } + + if (buffer_locked(bh)) + __wait_on_buffer(bh); + + lock_buffer(bh); + if (buf) { + memcpy(bh->b_data + off, buf, op); + buf = Add2Ptr(buf, op); + } else { + memset(bh->b_data + off, -1, op); + } + + set_buffer_uptodate(bh); + mark_buffer_dirty(bh); + unlock_buffer(bh); + + if (wait) { + int err = sync_dirty_buffer(bh); + + if (err) { + ntfs_err( + sb, + "failed to sync buffer at block %llx, error %d", + (u64)block, err); + put_bh(bh); + return err; + } + } + + put_bh(bh); + + bytes -= op; + } + return 0; +} + +int ntfs_sb_write_run(struct ntfs_sb_info *sbi, const struct runs_tree *run, + u64 vbo, const void *buf, size_t bytes) +{ + struct super_block *sb = sbi->sb; + u8 cluster_bits = sbi->cluster_bits; + u32 off = vbo & sbi->cluster_mask; + CLST lcn, clen; + u64 lbo, len; + size_t idx; + + if (!run_lookup_entry(run, vbo >> cluster_bits, &lcn, &clen, &idx)) + return -ENOENT; + + if (lcn == SPARSE_LCN) + return -EINVAL; + + lbo = ((u64)lcn << cluster_bits) + off; + len = ((u64)clen << cluster_bits) - off; + + for (;;) { + u32 op = len < bytes ? len : bytes; + int err = ntfs_sb_write(sb, lbo, op, buf, 0); + + if (err) + return err; + + bytes -= op; + if (!bytes) + break; + + if (!run_get_entry(run, ++idx, NULL, &lcn, &clen)) + return -ENOENT; + + if (lcn == SPARSE_LCN) + return -EINVAL; + + if (buf) + buf = Add2Ptr(buf, op); + + lbo = ((u64)lcn << cluster_bits) + off; + len = ((u64)clen << cluster_bits) - off; + } + + return 0; +} + +struct buffer_head *ntfs_bread_run(struct ntfs_sb_info *sbi, + const struct runs_tree *run, u64 vbo) +{ + struct super_block *sb = sbi->sb; + u8 cluster_bits = sbi->cluster_bits; + CLST lcn; + u64 lbo; + + if (!run_lookup_entry(run, vbo >> cluster_bits, &lcn, NULL, NULL)) + return ERR_PTR(-ENOENT); + + lbo = ((u64)lcn << cluster_bits) + (vbo & sbi->cluster_mask); + + return ntfs_bread(sb, lbo >> sb->s_blocksize_bits); +} + +int ntfs_read_run_nb(struct ntfs_sb_info *sbi, const struct runs_tree *run, + u64 vbo, void *buf, u32 bytes, struct ntfs_buffers *nb) +{ + int err; + struct super_block *sb = sbi->sb; + u32 blocksize = sb->s_blocksize; + u8 cluster_bits = sbi->cluster_bits; + u32 off = vbo & sbi->cluster_mask; + u32 nbh = 0; + CLST lcn, clen; + u64 lbo, len; + size_t idx; + struct buffer_head *bh; + + if (!run) { + /* first reading of $Volume + $MFTMirr + $LogFile goes here*/ + if (vbo > MFT_REC_VOL * sbi->record_size) { + err = -ENOENT; + goto out; + } + + /* use absolute boot's 'MFTCluster' to read record */ + lbo = vbo + sbi->mft.lbo; + len = sbi->record_size; + } else if (!run_lookup_entry(run, vbo >> cluster_bits, &lcn, &clen, + &idx)) { + err = -ENOENT; + goto out; + } else { + if (lcn == SPARSE_LCN) { + err = -EINVAL; + goto out; + } + + lbo = ((u64)lcn << cluster_bits) + off; + len = ((u64)clen << cluster_bits) - off; + } + + off = lbo & (blocksize - 1); + if (nb) { + nb->off = off; + nb->bytes = bytes; + } + + for (;;) { + u32 len32 = len >= bytes ? bytes : len; + sector_t block = lbo >> sb->s_blocksize_bits; + + do { + u32 op = blocksize - off; + + if (op > len32) + op = len32; + + bh = ntfs_bread(sb, block); + if (!bh) { + err = -EIO; + goto out; + } + + if (buf) { + memcpy(buf, bh->b_data + off, op); + buf = Add2Ptr(buf, op); + } + + if (!nb) { + put_bh(bh); + } else if (nbh >= ARRAY_SIZE(nb->bh)) { + err = -EINVAL; + goto out; + } else { + nb->bh[nbh++] = bh; + nb->nbufs = nbh; + } + + bytes -= op; + if (!bytes) + return 0; + len32 -= op; + block += 1; + off = 0; + + } while (len32); + + if (!run_get_entry(run, ++idx, NULL, &lcn, &clen)) { + err = -ENOENT; + goto out; + } + + if (lcn == SPARSE_LCN) { + err = -EINVAL; + goto out; + } + + lbo = ((u64)lcn << cluster_bits); + len = ((u64)clen << cluster_bits); + } + +out: + if (!nbh) + return err; + + while (nbh) { + put_bh(nb->bh[--nbh]); + nb->bh[nbh] = NULL; + } + + nb->nbufs = 0; + return err; +} + +/* Returns < 0 if error, 0 if ok, 1 if need to update fixups */ +int ntfs_read_bh(struct ntfs_sb_info *sbi, const struct runs_tree *run, u64 vbo, + struct NTFS_RECORD_HEADER *rhdr, u32 bytes, + struct ntfs_buffers *nb) +{ + int err = ntfs_read_run_nb(sbi, run, vbo, rhdr, bytes, nb); + + if (err) + return err; + return ntfs_fix_post_read(rhdr, nb->bytes, true); +} + +int ntfs_get_bh(struct ntfs_sb_info *sbi, const struct runs_tree *run, u64 vbo, + u32 bytes, struct ntfs_buffers *nb) +{ + int err = 0; + struct super_block *sb = sbi->sb; + u32 blocksize = sb->s_blocksize; + u8 cluster_bits = sbi->cluster_bits; + u32 off; + u32 nbh = 0; + CLST lcn, clen; + u64 lbo, len; + size_t idx; + + nb->bytes = bytes; + + if (!run_lookup_entry(run, vbo >> cluster_bits, &lcn, &clen, &idx)) { + err = -ENOENT; + goto out; + } + + off = vbo & sbi->cluster_mask; + lbo = ((u64)lcn << cluster_bits) + off; + len = ((u64)clen << cluster_bits) - off; + + nb->off = off = lbo & (blocksize - 1); + + for (;;) { + u32 len32 = len < bytes ? len : bytes; + sector_t block = lbo >> sb->s_blocksize_bits; + + do { + u32 op; + struct buffer_head *bh; + + if (nbh >= ARRAY_SIZE(nb->bh)) { + err = -EINVAL; + goto out; + } + + op = blocksize - off; + if (op > len32) + op = len32; + + if (op == blocksize) { + bh = sb_getblk(sb, block); + if (!bh) { + err = -ENOMEM; + goto out; + } + if (buffer_locked(bh)) + __wait_on_buffer(bh); + set_buffer_uptodate(bh); + } else { + bh = ntfs_bread(sb, block); + if (!bh) { + err = -EIO; + goto out; + } + } + + nb->bh[nbh++] = bh; + bytes -= op; + if (!bytes) { + nb->nbufs = nbh; + return 0; + } + + block += 1; + len32 -= op; + off = 0; + } while (len32); + + if (!run_get_entry(run, ++idx, NULL, &lcn, &clen)) { + err = -ENOENT; + goto out; + } + + lbo = ((u64)lcn << cluster_bits); + len = ((u64)clen << cluster_bits); + } + +out: + while (nbh) { + put_bh(nb->bh[--nbh]); + nb->bh[nbh] = NULL; + } + + nb->nbufs = 0; + + return err; +} + +int ntfs_write_bh(struct ntfs_sb_info *sbi, struct NTFS_RECORD_HEADER *rhdr, + struct ntfs_buffers *nb, int sync) +{ + int err = 0; + struct super_block *sb = sbi->sb; + u32 block_size = sb->s_blocksize; + u32 bytes = nb->bytes; + u32 off = nb->off; + u16 fo = le16_to_cpu(rhdr->fix_off); + u16 fn = le16_to_cpu(rhdr->fix_num); + u32 idx; + __le16 *fixup; + __le16 sample; + + if ((fo & 1) || fo + fn * sizeof(short) > SECTOR_SIZE || !fn-- || + fn * SECTOR_SIZE > bytes) { + return -EINVAL; + } + + for (idx = 0; bytes && idx < nb->nbufs; idx += 1, off = 0) { + u32 op = block_size - off; + char *bh_data; + struct buffer_head *bh = nb->bh[idx]; + __le16 *ptr, *end_data; + + if (op > bytes) + op = bytes; + + if (buffer_locked(bh)) + __wait_on_buffer(bh); + + lock_buffer(nb->bh[idx]); + + bh_data = bh->b_data + off; + end_data = Add2Ptr(bh_data, op); + memcpy(bh_data, rhdr, op); + + if (!idx) { + u16 t16; + + fixup = Add2Ptr(bh_data, fo); + sample = *fixup; + t16 = le16_to_cpu(sample); + if (t16 >= 0x7FFF) { + sample = *fixup = cpu_to_le16(1); + } else { + sample = cpu_to_le16(t16 + 1); + *fixup = sample; + } + + *(__le16 *)Add2Ptr(rhdr, fo) = sample; + } + + ptr = Add2Ptr(bh_data, SECTOR_SIZE - sizeof(short)); + + do { + *++fixup = *ptr; + *ptr = sample; + ptr += SECTOR_SIZE / sizeof(short); + } while (ptr < end_data); + + set_buffer_uptodate(bh); + mark_buffer_dirty(bh); + unlock_buffer(bh); + + if (sync) { + int err2 = sync_dirty_buffer(bh); + + if (!err && err2) + err = err2; + } + + bytes -= op; + rhdr = Add2Ptr(rhdr, op); + } + + return err; +} + +int ntfs_vbo_to_lbo(struct ntfs_sb_info *sbi, const struct runs_tree *run, + u64 vbo, u64 *lbo, u64 *bytes) +{ + u32 off; + CLST lcn, len; + u8 cluster_bits = sbi->cluster_bits; + + if (!run_lookup_entry(run, vbo >> cluster_bits, &lcn, &len, NULL)) + return -ENOENT; + + off = vbo & sbi->cluster_mask; + *lbo = lcn == SPARSE_LCN ? -1 : (((u64)lcn << cluster_bits) + off); + *bytes = ((u64)len << cluster_bits) - off; + + return 0; +} + +struct ntfs_inode *ntfs_new_inode(struct ntfs_sb_info *sbi, CLST rno, bool dir) +{ + int err = 0; + struct super_block *sb = sbi->sb; + struct inode *inode = new_inode(sb); + struct ntfs_inode *ni; + + if (!inode) + return ERR_PTR(-ENOMEM); + + ni = ntfs_i(inode); + + err = mi_format_new(&ni->mi, sbi, rno, dir ? RECORD_FLAG_DIR : 0, + false); + if (err) + goto out; + + inode->i_ino = rno; + if (insert_inode_locked(inode) < 0) { + err = -EIO; + goto out; + } + +out: + if (err) { + iput(inode); + ni = ERR_PTR(err); + } + return ni; +} + +/* + * O:BAG:BAD:(A;OICI;FA;;;WD) + * owner S-1-5-32-544 (Administrators) + * group S-1-5-32-544 (Administrators) + * ACE: allow S-1-1-0 (Everyone) with FILE_ALL_ACCESS + */ +const u8 s_default_security[] __aligned(8) = { + 0x01, 0x00, 0x04, 0x80, 0x30, 0x00, 0x00, 0x00, 0x40, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x14, 0x00, 0x00, 0x00, 0x02, 0x00, 0x1C, 0x00, + 0x01, 0x00, 0x00, 0x00, 0x00, 0x03, 0x14, 0x00, 0xFF, 0x01, 0x1F, 0x00, + 0x01, 0x01, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01, 0x00, 0x00, 0x00, 0x00, + 0x01, 0x02, 0x00, 0x00, 0x00, 0x00, 0x00, 0x05, 0x20, 0x00, 0x00, 0x00, + 0x20, 0x02, 0x00, 0x00, 0x01, 0x02, 0x00, 0x00, 0x00, 0x00, 0x00, 0x05, + 0x20, 0x00, 0x00, 0x00, 0x20, 0x02, 0x00, 0x00, +}; + +static_assert(sizeof(s_default_security) == 0x50); + +static inline u32 sid_length(const struct SID *sid) +{ + return offsetof(struct SID, SubAuthority[0]) + + (sid->SubAuthorityCount * sizeof(u32)); +} + +/* + * Thanks Mark Harmstone for idea + */ +static bool is_acl_valid(const struct ACL *acl, u32 len) +{ + const struct ACE_HEADER *ace; + u32 i; + u16 ace_count, ace_size; + + if (acl->AclRevision != ACL_REVISION) + return false; + + if (acl->Sbz1) + return false; + + if (le16_to_cpu(acl->AclSize) > len) + return false; + + if (acl->Sbz2) + return false; + + len -= sizeof(struct ACL); + + ace = (struct ACE_HEADER *)&acl[1]; + ace_count = le16_to_cpu(acl->AceCount); + + for (i = 0; i < ace_count; i++) { + if (len < sizeof(struct ACE_HEADER)) + return false; + + ace_size = le16_to_cpu(ace->AceSize); + if (len < ace_size) + return false; + + len -= ace_size; + + ace = Add2Ptr(ace, ace_size); + } + + return true; +} + +bool is_sd_valid(const struct SECURITY_DESCRIPTOR_RELATIVE *sd, u32 len) +{ + u32 sd_owner, sd_group, sd_sacl, sd_dacl; + + if (len < sizeof(struct SECURITY_DESCRIPTOR_RELATIVE)) + return false; + + if (sd->Revision != 1) + return false; + + if (sd->Sbz1) + return false; + + if (!(sd->Control & cpu_to_le16(SE_SELF_RELATIVE))) + return false; + + sd_owner = le32_to_cpu(sd->Owner); + if (sd_owner) { + const struct SID *owner = Add2Ptr(sd, sd_owner); + + if (sd_owner + offsetof(struct SID, SubAuthority) > len) + return false; + + if (owner->Revision != 1) + return false; + + if (sd_owner + sid_length(owner) > len) + return false; + } + + sd_group = le32_to_cpu(sd->Group); + if (sd_group) { + const struct SID *group = Add2Ptr(sd, sd_group); + + if (sd_group + offsetof(struct SID, SubAuthority) > len) + return false; + + if (group->Revision != 1) + return false; + + if (sd_group + sid_length(group) > len) + return false; + } + + sd_sacl = le32_to_cpu(sd->Sacl); + if (sd_sacl) { + const struct ACL *sacl = Add2Ptr(sd, sd_sacl); + + if (sd_sacl + sizeof(struct ACL) > len) + return false; + + if (!is_acl_valid(sacl, len - sd_sacl)) + return false; + } + + sd_dacl = le32_to_cpu(sd->Dacl); + if (sd_dacl) { + const struct ACL *dacl = Add2Ptr(sd, sd_dacl); + + if (sd_dacl + sizeof(struct ACL) > len) + return false; + + if (!is_acl_valid(dacl, len - sd_dacl)) + return false; + } + + return true; +} + +/* + * ntfs_security_init + * + * loads and parse $Secure + */ +int ntfs_security_init(struct ntfs_sb_info *sbi) +{ + int err; + struct super_block *sb = sbi->sb; + struct inode *inode; + struct ntfs_inode *ni; + struct MFT_REF ref; + struct ATTRIB *attr; + struct ATTR_LIST_ENTRY *le; + u64 sds_size; + size_t cnt, off; + struct NTFS_DE *ne; + struct NTFS_DE_SII *sii_e; + struct ntfs_fnd *fnd_sii = NULL; + const struct INDEX_ROOT *root_sii; + const struct INDEX_ROOT *root_sdh; + struct ntfs_index *indx_sdh = &sbi->security.index_sdh; + struct ntfs_index *indx_sii = &sbi->security.index_sii; + + ref.low = cpu_to_le32(MFT_REC_SECURE); + ref.high = 0; + ref.seq = cpu_to_le16(MFT_REC_SECURE); + + inode = ntfs_iget5(sb, &ref, &NAME_SECURE); + if (IS_ERR(inode)) { + err = PTR_ERR(inode); + ntfs_err(sb, "Failed to load $Secure."); + inode = NULL; + goto out; + } + + ni = ntfs_i(inode); + + le = NULL; + + attr = ni_find_attr(ni, NULL, &le, ATTR_ROOT, SDH_NAME, + ARRAY_SIZE(SDH_NAME), NULL, NULL); + if (!attr) { + err = -EINVAL; + goto out; + } + + root_sdh = resident_data(attr); + if (root_sdh->type != ATTR_ZERO || + root_sdh->rule != NTFS_COLLATION_TYPE_SECURITY_HASH) { + err = -EINVAL; + goto out; + } + + err = indx_init(indx_sdh, sbi, attr, INDEX_MUTEX_SDH); + if (err) + goto out; + + attr = ni_find_attr(ni, attr, &le, ATTR_ROOT, SII_NAME, + ARRAY_SIZE(SII_NAME), NULL, NULL); + if (!attr) { + err = -EINVAL; + goto out; + } + + root_sii = resident_data(attr); + if (root_sii->type != ATTR_ZERO || + root_sii->rule != NTFS_COLLATION_TYPE_UINT) { + err = -EINVAL; + goto out; + } + + err = indx_init(indx_sii, sbi, attr, INDEX_MUTEX_SII); + if (err) + goto out; + + fnd_sii = fnd_get(indx_sii); + if (!fnd_sii) { + err = -ENOMEM; + goto out; + } + + sds_size = inode->i_size; + + /* Find the last valid Id */ + sbi->security.next_id = SECURITY_ID_FIRST; + /* Always write new security at the end of bucket */ + sbi->security.next_off = + Quad2Align(sds_size - SecurityDescriptorsBlockSize); + + cnt = 0; + off = 0; + ne = NULL; + + for (;;) { + u32 next_id; + + err = indx_find_raw(indx_sii, ni, root_sii, &ne, &off, fnd_sii); + if (err || !ne) + break; + + sii_e = (struct NTFS_DE_SII *)ne; + if (le16_to_cpu(ne->view.data_size) < SIZEOF_SECURITY_HDR) + continue; + + next_id = le32_to_cpu(sii_e->sec_id) + 1; + if (next_id >= sbi->security.next_id) + sbi->security.next_id = next_id; + + cnt += 1; + } + + sbi->security.ni = ni; + inode = NULL; +out: + iput(inode); + fnd_put(fnd_sii); + + return err; +} + +/* + * ntfs_get_security_by_id + * + * reads security descriptor by id + */ +int ntfs_get_security_by_id(struct ntfs_sb_info *sbi, __le32 security_id, + struct SECURITY_DESCRIPTOR_RELATIVE **sd, + size_t *size) +{ + int err; + int diff; + struct ntfs_inode *ni = sbi->security.ni; + struct ntfs_index *indx = &sbi->security.index_sii; + void *p = NULL; + struct NTFS_DE_SII *sii_e; + struct ntfs_fnd *fnd_sii; + struct SECURITY_HDR d_security; + const struct INDEX_ROOT *root_sii; + u32 t32; + + *sd = NULL; + + inode_lock_shared(&ni->vfs_inode); + + fnd_sii = fnd_get(indx); + if (!fnd_sii) { + err = -ENOMEM; + goto out; + } + + root_sii = indx_get_root(indx, ni, NULL, NULL); + if (!root_sii) { + err = -EINVAL; + goto out; + } + + /* Try to find this SECURITY descriptor in SII indexes */ + err = indx_find(indx, ni, root_sii, &security_id, sizeof(security_id), + NULL, &diff, (struct NTFS_DE **)&sii_e, fnd_sii); + if (err) + goto out; + + if (diff) + goto out; + + t32 = le32_to_cpu(sii_e->sec_hdr.size); + if (t32 < SIZEOF_SECURITY_HDR) { + err = -EINVAL; + goto out; + } + + if (t32 > SIZEOF_SECURITY_HDR + 0x10000) { + /* + * looks like too big security. 0x10000 - is arbitrary big number + */ + err = -EFBIG; + goto out; + } + + *size = t32 - SIZEOF_SECURITY_HDR; + + p = ntfs_alloc(*size, 0); + if (!p) { + err = -ENOMEM; + goto out; + } + + err = ntfs_read_run_nb(sbi, &ni->file.run, + le64_to_cpu(sii_e->sec_hdr.off), &d_security, + sizeof(d_security), NULL); + if (err) + goto out; + + if (memcmp(&d_security, &sii_e->sec_hdr, SIZEOF_SECURITY_HDR)) { + err = -EINVAL; + goto out; + } + + err = ntfs_read_run_nb(sbi, &ni->file.run, + le64_to_cpu(sii_e->sec_hdr.off) + + SIZEOF_SECURITY_HDR, + p, *size, NULL); + if (err) + goto out; + + *sd = p; + p = NULL; + +out: + ntfs_free(p); + fnd_put(fnd_sii); + inode_unlock_shared(&ni->vfs_inode); + + return err; +} + +/* + * ntfs_insert_security + * + * inserts security descriptor into $Secure::SDS + * + * SECURITY Descriptor Stream data is organized into chunks of 256K bytes + * and it contains a mirror copy of each security descriptor. When writing + * to a security descriptor at location X, another copy will be written at + * location (X+256K). + * When writing a security descriptor that will cross the 256K boundary, + * the pointer will be advanced by 256K to skip + * over the mirror portion. + */ +int ntfs_insert_security(struct ntfs_sb_info *sbi, + const struct SECURITY_DESCRIPTOR_RELATIVE *sd, + u32 size_sd, __le32 *security_id, bool *inserted) +{ + int err, diff; + struct ntfs_inode *ni = sbi->security.ni; + struct ntfs_index *indx_sdh = &sbi->security.index_sdh; + struct ntfs_index *indx_sii = &sbi->security.index_sii; + struct NTFS_DE_SDH *e; + struct NTFS_DE_SDH sdh_e; + struct NTFS_DE_SII sii_e; + struct SECURITY_HDR *d_security; + u32 new_sec_size = size_sd + SIZEOF_SECURITY_HDR; + u32 aligned_sec_size = Quad2Align(new_sec_size); + struct SECURITY_KEY hash_key; + struct ntfs_fnd *fnd_sdh = NULL; + const struct INDEX_ROOT *root_sdh; + const struct INDEX_ROOT *root_sii; + u64 mirr_off, new_sds_size; + u32 next, left; + + static_assert((1 << Log2OfSecurityDescriptorsBlockSize) == + SecurityDescriptorsBlockSize); + + hash_key.hash = security_hash(sd, size_sd); + hash_key.sec_id = SECURITY_ID_INVALID; + + if (inserted) + *inserted = false; + *security_id = SECURITY_ID_INVALID; + + /* Allocate a temporal buffer*/ + d_security = ntfs_alloc(aligned_sec_size, 1); + if (!d_security) + return -ENOMEM; + + inode_lock(&ni->vfs_inode); + + fnd_sdh = fnd_get(indx_sdh); + if (!fnd_sdh) { + err = -ENOMEM; + goto out; + } + + root_sdh = indx_get_root(indx_sdh, ni, NULL, NULL); + if (!root_sdh) { + err = -EINVAL; + goto out; + } + + root_sii = indx_get_root(indx_sii, ni, NULL, NULL); + if (!root_sii) { + err = -EINVAL; + goto out; + } + + /* + * Check if such security already exists + * use "SDH" and hash -> to get the offset in "SDS" + */ + err = indx_find(indx_sdh, ni, root_sdh, &hash_key, sizeof(hash_key), + &d_security->key.sec_id, &diff, (struct NTFS_DE **)&e, + fnd_sdh); + if (err) + goto out; + + while (e) { + if (le32_to_cpu(e->sec_hdr.size) == new_sec_size) { + err = ntfs_read_run_nb(sbi, &ni->file.run, + le64_to_cpu(e->sec_hdr.off), + d_security, new_sec_size, NULL); + if (err) + goto out; + + if (le32_to_cpu(d_security->size) == new_sec_size && + d_security->key.hash == hash_key.hash && + !memcmp(d_security + 1, sd, size_sd)) { + *security_id = d_security->key.sec_id; + /*such security already exists*/ + err = 0; + goto out; + } + } + + err = indx_find_sort(indx_sdh, ni, root_sdh, + (struct NTFS_DE **)&e, fnd_sdh); + if (err) + goto out; + + if (!e || e->key.hash != hash_key.hash) + break; + } + + /* Zero unused space */ + next = sbi->security.next_off & (SecurityDescriptorsBlockSize - 1); + left = SecurityDescriptorsBlockSize - next; + + /* Zero gap until SecurityDescriptorsBlockSize */ + if (left < new_sec_size) { + /* zero "left" bytes from sbi->security.next_off */ + sbi->security.next_off += SecurityDescriptorsBlockSize + left; + } + + /* Zero tail of previous security */ + //used = ni->vfs_inode.i_size & (SecurityDescriptorsBlockSize - 1); + + /* + * Example: + * 0x40438 == ni->vfs_inode.i_size + * 0x00440 == sbi->security.next_off + * need to zero [0x438-0x440) + * if (next > used) { + * u32 tozero = next - used; + * zero "tozero" bytes from sbi->security.next_off - tozero + */ + + /* format new security descriptor */ + d_security->key.hash = hash_key.hash; + d_security->key.sec_id = cpu_to_le32(sbi->security.next_id); + d_security->off = cpu_to_le64(sbi->security.next_off); + d_security->size = cpu_to_le32(new_sec_size); + memcpy(d_security + 1, sd, size_sd); + + /* Write main SDS bucket */ + err = ntfs_sb_write_run(sbi, &ni->file.run, sbi->security.next_off, + d_security, aligned_sec_size); + + if (err) + goto out; + + mirr_off = sbi->security.next_off + SecurityDescriptorsBlockSize; + new_sds_size = mirr_off + aligned_sec_size; + + if (new_sds_size > ni->vfs_inode.i_size) { + err = attr_set_size(ni, ATTR_DATA, SDS_NAME, + ARRAY_SIZE(SDS_NAME), &ni->file.run, + new_sds_size, &new_sds_size, false, NULL); + if (err) + goto out; + } + + /* Write copy SDS bucket */ + err = ntfs_sb_write_run(sbi, &ni->file.run, mirr_off, d_security, + aligned_sec_size); + if (err) + goto out; + + /* Fill SII entry */ + sii_e.de.view.data_off = + cpu_to_le16(offsetof(struct NTFS_DE_SII, sec_hdr)); + sii_e.de.view.data_size = cpu_to_le16(SIZEOF_SECURITY_HDR); + sii_e.de.view.res = 0; + sii_e.de.size = cpu_to_le16(SIZEOF_SII_DIRENTRY); + sii_e.de.key_size = cpu_to_le16(sizeof(d_security->key.sec_id)); + sii_e.de.flags = 0; + sii_e.de.res = 0; + sii_e.sec_id = d_security->key.sec_id; + memcpy(&sii_e.sec_hdr, d_security, SIZEOF_SECURITY_HDR); + + err = indx_insert_entry(indx_sii, ni, &sii_e.de, NULL, NULL); + if (err) + goto out; + + /* Fill SDH entry */ + sdh_e.de.view.data_off = + cpu_to_le16(offsetof(struct NTFS_DE_SDH, sec_hdr)); + sdh_e.de.view.data_size = cpu_to_le16(SIZEOF_SECURITY_HDR); + sdh_e.de.view.res = 0; + sdh_e.de.size = cpu_to_le16(SIZEOF_SDH_DIRENTRY); + sdh_e.de.key_size = cpu_to_le16(sizeof(sdh_e.key)); + sdh_e.de.flags = 0; + sdh_e.de.res = 0; + sdh_e.key.hash = d_security->key.hash; + sdh_e.key.sec_id = d_security->key.sec_id; + memcpy(&sdh_e.sec_hdr, d_security, SIZEOF_SECURITY_HDR); + sdh_e.magic[0] = cpu_to_le16('I'); + sdh_e.magic[1] = cpu_to_le16('I'); + + fnd_clear(fnd_sdh); + err = indx_insert_entry(indx_sdh, ni, &sdh_e.de, (void *)(size_t)1, + fnd_sdh); + if (err) + goto out; + + *security_id = d_security->key.sec_id; + if (inserted) + *inserted = true; + + /* Update Id and offset for next descriptor */ + sbi->security.next_id += 1; + sbi->security.next_off += aligned_sec_size; + +out: + fnd_put(fnd_sdh); + inode_unlock(&ni->vfs_inode); + ntfs_free(d_security); + + return err; +} + +/* + * ntfs_reparse_init + * + * loads and parse $Extend/$Reparse + */ +int ntfs_reparse_init(struct ntfs_sb_info *sbi) +{ + int err; + struct ntfs_inode *ni = sbi->reparse.ni; + struct ntfs_index *indx = &sbi->reparse.index_r; + struct ATTRIB *attr; + struct ATTR_LIST_ENTRY *le; + const struct INDEX_ROOT *root_r; + + if (!ni) + return 0; + + le = NULL; + attr = ni_find_attr(ni, NULL, &le, ATTR_ROOT, SR_NAME, + ARRAY_SIZE(SR_NAME), NULL, NULL); + if (!attr) { + err = -EINVAL; + goto out; + } + + root_r = resident_data(attr); + if (root_r->type != ATTR_ZERO || + root_r->rule != NTFS_COLLATION_TYPE_UINTS) { + err = -EINVAL; + goto out; + } + + err = indx_init(indx, sbi, attr, INDEX_MUTEX_SR); + if (err) + goto out; + +out: + return err; +} + +/* + * ntfs_objid_init + * + * loads and parse $Extend/$ObjId + */ +int ntfs_objid_init(struct ntfs_sb_info *sbi) +{ + int err; + struct ntfs_inode *ni = sbi->objid.ni; + struct ntfs_index *indx = &sbi->objid.index_o; + struct ATTRIB *attr; + struct ATTR_LIST_ENTRY *le; + const struct INDEX_ROOT *root; + + if (!ni) + return 0; + + le = NULL; + attr = ni_find_attr(ni, NULL, &le, ATTR_ROOT, SO_NAME, + ARRAY_SIZE(SO_NAME), NULL, NULL); + if (!attr) { + err = -EINVAL; + goto out; + } + + root = resident_data(attr); + if (root->type != ATTR_ZERO || + root->rule != NTFS_COLLATION_TYPE_UINTS) { + err = -EINVAL; + goto out; + } + + err = indx_init(indx, sbi, attr, INDEX_MUTEX_SO); + if (err) + goto out; + +out: + return err; +} + +int ntfs_objid_remove(struct ntfs_sb_info *sbi, struct GUID *guid) +{ + int err; + struct ntfs_inode *ni = sbi->objid.ni; + struct ntfs_index *indx = &sbi->objid.index_o; + + if (!ni) + return -EINVAL; + + inode_lock(&ni->vfs_inode); + + err = indx_delete_entry(indx, ni, guid, sizeof(*guid), NULL); + + inode_unlock(&ni->vfs_inode); + + return err; +} + +int ntfs_insert_reparse(struct ntfs_sb_info *sbi, __le32 rtag, + const struct MFT_REF *ref) +{ + int err; + struct ntfs_inode *ni = sbi->reparse.ni; + struct ntfs_index *indx = &sbi->reparse.index_r; + struct NTFS_DE_R re; + + if (!ni) + return -EINVAL; + + memset(&re, 0, sizeof(re)); + + re.Key.ReparseTag = rtag; + memcpy(&re.Key.ref, ref, sizeof(*ref)); + + re.de.view.data_off = cpu_to_le16(offsetof(struct NTFS_DE_R, Key)); + re.de.size = cpu_to_le16(QuadAlign(SIZEOF_R_DIRENTRY)); + re.de.key_size = cpu_to_le16(sizeof(re.Key)); + + inode_lock(&ni->vfs_inode); + + err = indx_insert_entry(indx, ni, &re.de, NULL, NULL); + + inode_unlock(&ni->vfs_inode); + + return err; +} + +int ntfs_remove_reparse(struct ntfs_sb_info *sbi, __le32 rtag, + const struct MFT_REF *ref) +{ + int err; + struct ntfs_inode *ni = sbi->reparse.ni; + struct ntfs_index *indx = &sbi->reparse.index_r; + struct REPARSE_KEY rkey; + int diff; + struct NTFS_DE_R *re; + struct ntfs_fnd *fnd = NULL; + struct INDEX_ROOT *root_r; + + if (!ni) + return -EINVAL; + + rkey.ReparseTag = rtag; + rkey.ref = *ref; + + inode_lock(&ni->vfs_inode); + + if (rtag) { + err = indx_delete_entry(indx, ni, &rkey, sizeof(rkey), NULL); + goto out1; + } + + fnd = fnd_get(indx); + if (!fnd) { + err = -ENOMEM; + goto out1; + } + + root_r = indx_get_root(indx, ni, NULL, NULL); + if (!root_r) { + err = -EINVAL; + goto out; + } + + err = indx_find(indx, ni, root_r, &rkey, sizeof(rkey), NULL, &diff, + (struct NTFS_DE **)&re, fnd); + if (err) + goto out; + + if (memcmp(&re->Key.ref, ref, sizeof(*ref))) + goto out; + + memcpy(&rkey, &re->Key, sizeof(rkey)); + + fnd_put(fnd); + fnd = NULL; + + err = indx_delete_entry(indx, ni, &rkey, sizeof(rkey), NULL); + if (err) + goto out; + +out: + fnd_put(fnd); + +out1: + inode_unlock(&ni->vfs_inode); + + return err; +} + +static inline void ntfs_unmap_and_discard(struct ntfs_sb_info *sbi, CLST lcn, + CLST len) +{ + ntfs_unmap_meta(sbi->sb, lcn, len); + ntfs_discard(sbi, lcn, len); +} + +void mark_as_free_ex(struct ntfs_sb_info *sbi, CLST lcn, CLST len, bool trim) +{ + CLST end, i; + struct wnd_bitmap *wnd = &sbi->used.bitmap; + + down_write_nested(&wnd->rw_lock, BITMAP_MUTEX_CLUSTERS); + if (!wnd_is_used(wnd, lcn, len)) { + ntfs_set_state(sbi, NTFS_DIRTY_ERROR); + + end = lcn + len; + len = 0; + for (i = lcn; i < end; i++) { + if (wnd_is_used(wnd, i, 1)) { + if (!len) + lcn = i; + len += 1; + continue; + } + + if (!len) + continue; + + if (trim) + ntfs_unmap_and_discard(sbi, lcn, len); + + wnd_set_free(wnd, lcn, len); + len = 0; + } + + if (!len) + goto out; + } + + if (trim) + ntfs_unmap_and_discard(sbi, lcn, len); + wnd_set_free(wnd, lcn, len); + +out: + up_write(&wnd->rw_lock); +} + +/* + * run_deallocate + * + * deallocate clusters + */ +int run_deallocate(struct ntfs_sb_info *sbi, struct runs_tree *run, bool trim) +{ + CLST lcn, len; + size_t idx = 0; + + while (run_get_entry(run, idx++, NULL, &lcn, &len)) { + if (lcn == SPARSE_LCN) + continue; + + mark_as_free_ex(sbi, lcn, len, trim); + } + + return 0; +} diff --git a/fs/ntfs3/index.c b/fs/ntfs3/index.c new file mode 100644 index 000000000000..db892dcc66be --- /dev/null +++ b/fs/ntfs3/index.c @@ -0,0 +1,2646 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * linux/fs/ntfs3/index.c + * + * Copyright (C) 2019-2020 Paragon Software GmbH, All rights reserved. + * + */ + +#include +#include +#include +#include +#include + +#include "debug.h" +#include "ntfs.h" +#include "ntfs_fs.h" + +static const struct INDEX_NAMES { + const __le16 *name; + u8 name_len; +} s_index_names[INDEX_MUTEX_TOTAL] = { + { I30_NAME, ARRAY_SIZE(I30_NAME) }, { SII_NAME, ARRAY_SIZE(SII_NAME) }, + { SDH_NAME, ARRAY_SIZE(SDH_NAME) }, { SO_NAME, ARRAY_SIZE(SO_NAME) }, + { SQ_NAME, ARRAY_SIZE(SQ_NAME) }, { SR_NAME, ARRAY_SIZE(SR_NAME) }, +}; + +/* + * compare two names in index + * if l1 != 0 + * both names are little endian on-disk ATTR_FILE_NAME structs + * else + * f1 - cpu_str, f2 - ATTR_FILE_NAME + */ +static int cmp_fnames(const struct ATTR_FILE_NAME *f1, size_t l1, + const struct ATTR_FILE_NAME *f2, size_t l2, + const struct ntfs_sb_info *sbi) +{ + int diff; + u16 fsize2; + + if (l2 <= offsetof(struct ATTR_FILE_NAME, name)) + return -1; + + fsize2 = fname_full_size(f2); + if (l2 < fsize2) + return -1; + + if (!l1) { + const struct cpu_str *s1 = (struct cpu_str *)f1; + const struct le_str *s2 = (struct le_str *)&f2->name_len; + + diff = ntfs_cmp_names_cpu(s1, s2, sbi->upcase); + + if (diff) + return diff; + + /* + * If names are equal (case insensitive) + * try to compare it case sensitive + */ + if (/*sbi->options.nocase || */ f2->type == FILE_NAME_DOS) + return 0; + + return ntfs_cmp_names_cpu(s1, s2, NULL); + } + + diff = ntfs_cmp_names(f1->name, f1->name_len, f2->name, f2->name_len, + sbi->upcase); + + if (diff) + return diff; + + /* + * If names are equal (case insensitive) + * try to compare it case sensitive + */ + if (/*sbi->options.nocase || */ f2->type == FILE_NAME_DOS) + return 0; + + return ntfs_cmp_names(f1->name, f1->name_len, f2->name, f2->name_len, + NULL); +} + +static int cmp_uint(const u32 *k1, size_t l1, const u32 *k2, size_t l2, + const void *p) +{ + if (l2 < sizeof(u32)) + return -1; + + if (*k1 < *k2) + return -1; + if (*k1 > *k2) + return 1; + return 0; +} + +static int cmp_sdh(const struct SECURITY_KEY *k1, size_t l1, + const struct SECURITY_KEY *k2, size_t l2, const void *p) +{ + u32 t1, t2; + + if (l2 < sizeof(struct SECURITY_KEY)) + return -1; + + t1 = le32_to_cpu(k1->hash); + t2 = le32_to_cpu(k2->hash); + + /* First value is a hash value itself */ + if (t1 < t2) + return -1; + if (t1 > t2) + return 1; + + /* Second value is security Id */ + if (p) { + t1 = le32_to_cpu(k1->sec_id); + t2 = le32_to_cpu(k2->sec_id); + if (t1 < t2) + return -1; + if (t1 > t2) + return 1; + } + + return 0; +} + +static int cmp_uints(const __le32 *k1, size_t l1, const __le32 *k2, size_t l2, + const void *p) +{ + size_t count; + + if (l2 < sizeof(int)) + return -1; + + for (count = min(l1, l2) >> 2; count > 0; --count, ++k1, ++k2) { + u32 t1 = le32_to_cpu(*k1); + u32 t2 = le32_to_cpu(*k2); + + if (t1 > t2) + return 1; + if (t1 < t2) + return -1; + } + + if (l1 > l2) + return 1; + if (l1 < l2) + return -1; + + return 0; +} + +static inline NTFS_CMP_FUNC get_cmp_func(const struct INDEX_ROOT *root) +{ + switch (root->type) { + case ATTR_NAME: + if (root->rule == NTFS_COLLATION_TYPE_FILENAME) + return (NTFS_CMP_FUNC)&cmp_fnames; + break; + case ATTR_ZERO: + switch (root->rule) { + case NTFS_COLLATION_TYPE_UINT: + return (NTFS_CMP_FUNC)&cmp_uint; + case NTFS_COLLATION_TYPE_SECURITY_HASH: + return (NTFS_CMP_FUNC)&cmp_sdh; + case NTFS_COLLATION_TYPE_UINTS: + return (NTFS_CMP_FUNC)&cmp_uints; + default: + break; + } + default: + break; + } + + return NULL; +} + +struct bmp_buf { + struct ATTRIB *b; + struct mft_inode *mi; + struct buffer_head *bh; + ulong *buf; + size_t bit; + u32 nbits; + u64 new_valid; +}; + +static int bmp_buf_get(struct ntfs_index *indx, struct ntfs_inode *ni, + size_t bit, struct bmp_buf *bbuf) +{ + struct ATTRIB *b; + size_t data_size, valid_size, vbo, off = bit >> 3; + struct ntfs_sb_info *sbi = ni->mi.sbi; + CLST vcn = off >> sbi->cluster_bits; + struct ATTR_LIST_ENTRY *le = NULL; + struct buffer_head *bh; + struct super_block *sb; + u32 blocksize; + const struct INDEX_NAMES *in = &s_index_names[indx->type]; + + bbuf->bh = NULL; + + b = ni_find_attr(ni, NULL, &le, ATTR_BITMAP, in->name, in->name_len, + &vcn, &bbuf->mi); + bbuf->b = b; + if (!b) + return -EINVAL; + + if (!b->non_res) { + data_size = le32_to_cpu(b->res.data_size); + + if (off >= data_size) + return -EINVAL; + + bbuf->buf = (ulong *)resident_data(b); + bbuf->bit = 0; + bbuf->nbits = data_size * 8; + + return 0; + } + + data_size = le64_to_cpu(b->nres.data_size); + if (off >= data_size) { + WARN_ON(1); + return -EINVAL; + } + + valid_size = le64_to_cpu(b->nres.valid_size); + + bh = ntfs_bread_run(sbi, &indx->bitmap_run, off); + if (!bh) + return -EIO; + + if (IS_ERR(bh)) + return PTR_ERR(bh); + + bbuf->bh = bh; + + if (buffer_locked(bh)) + __wait_on_buffer(bh); + + lock_buffer(bh); + + sb = sbi->sb; + blocksize = sb->s_blocksize; + + vbo = off & ~(size_t)sbi->block_mask; + + bbuf->new_valid = vbo + blocksize; + if (bbuf->new_valid <= valid_size) + bbuf->new_valid = 0; + else if (bbuf->new_valid > data_size) + bbuf->new_valid = data_size; + + if (vbo >= valid_size) { + memset(bh->b_data, 0, blocksize); + } else if (vbo + blocksize > valid_size) { + u32 voff = valid_size & sbi->block_mask; + + memset(bh->b_data + voff, 0, blocksize - voff); + } + + bbuf->buf = (ulong *)bh->b_data; + bbuf->bit = 8 * (off & ~(size_t)sbi->block_mask); + bbuf->nbits = 8 * blocksize; + + return 0; +} + +static void bmp_buf_put(struct bmp_buf *bbuf, bool dirty) +{ + struct buffer_head *bh = bbuf->bh; + struct ATTRIB *b = bbuf->b; + + if (!bh) { + if (b && !b->non_res && dirty) + bbuf->mi->dirty = true; + return; + } + + if (!dirty) + goto out; + + if (bbuf->new_valid) { + b->nres.valid_size = cpu_to_le64(bbuf->new_valid); + bbuf->mi->dirty = true; + } + + set_buffer_uptodate(bh); + mark_buffer_dirty(bh); + +out: + unlock_buffer(bh); + put_bh(bh); +} + +/* + * indx_mark_used + * + * marks the bit 'bit' as used + */ +static int indx_mark_used(struct ntfs_index *indx, struct ntfs_inode *ni, + size_t bit) +{ + int err; + struct bmp_buf bbuf; + + err = bmp_buf_get(indx, ni, bit, &bbuf); + if (err) + return err; + + __set_bit(bit - bbuf.bit, bbuf.buf); + + bmp_buf_put(&bbuf, true); + + return 0; +} + +/* + * indx_mark_free + * + * the bit 'bit' as free + */ +static int indx_mark_free(struct ntfs_index *indx, struct ntfs_inode *ni, + size_t bit) +{ + int err; + struct bmp_buf bbuf; + + err = bmp_buf_get(indx, ni, bit, &bbuf); + if (err) + return err; + + __clear_bit(bit - bbuf.bit, bbuf.buf); + + bmp_buf_put(&bbuf, true); + + return 0; +} + +static int scan_nres_bitmap(struct ntfs_sb_info *sbi, struct ATTRIB *bitmap, + struct runs_tree *run, size_t from, + bool (*fn)(const ulong *buf, u32 bit, u32 bits, + size_t *ret), + size_t *ret) +{ + struct super_block *sb = sbi->sb; + u32 nbits = sb->s_blocksize * 8; + u32 blocksize = sb->s_blocksize; + u64 valid_size = le64_to_cpu(bitmap->nres.valid_size); + u64 data_size = le64_to_cpu(bitmap->nres.data_size); + sector_t eblock = bytes_to_block(sb, data_size); + size_t vbo = from >> 3; + sector_t blk = (vbo & sbi->cluster_mask) >> sb->s_blocksize_bits; + sector_t vblock = vbo >> sb->s_blocksize_bits; + sector_t blen, block; + CLST lcn, len; + size_t idx; + struct buffer_head *bh; + + *ret = MINUS_ONE_T; + + if (vblock >= eblock) + return 0; + + from &= nbits - 1; + + if (!run_lookup_entry(run, vbo >> sbi->cluster_bits, &lcn, &len, + &idx)) { + return -ENOENT; + } + + blen = (sector_t)len * sbi->blocks_per_cluster; + block = (sector_t)lcn * sbi->blocks_per_cluster; + +next_run: + for (; blk < blen; blk++, from = 0) { + bool ok; + + bh = ntfs_bread(sb, block + blk); + if (!bh) + return -EIO; + + vbo = (u64)vblock << sb->s_blocksize_bits; + if (vbo >= valid_size) { + memset(bh->b_data, 0, blocksize); + } else if (vbo + blocksize > valid_size) { + u32 voff = valid_size & sbi->block_mask; + + memset(bh->b_data + voff, 0, blocksize - voff); + } + + if (vbo + blocksize > data_size) + nbits = 8 * (data_size - vbo); + + ok = nbits > from ? + (*fn)((ulong *)bh->b_data, from, nbits, ret) : + false; + put_bh(bh); + + if (ok) { + *ret += 8 * vbo; + return 0; + } + + if (++vblock >= eblock) { + *ret = MINUS_ONE_T; + return 0; + } + } + + if (!run_get_entry(run, ++idx, NULL, &lcn, &len)) + return -ENOENT; + + blk = 0; + blen = (sector_t)len * sbi->blocks_per_cluster; + block = (sector_t)lcn * sbi->blocks_per_cluster; + goto next_run; +} + +static bool scan_for_free(const ulong *buf, u32 bit, u32 bits, size_t *ret) +{ + size_t pos = find_next_zero_bit(buf, bits, bit); + + if (pos >= bits) + return false; + *ret = pos; + return true; +} + +/* + * indx_find_free + * + * looks for free bit + * returns -1 if no free bits + */ +static int indx_find_free(struct ntfs_index *indx, struct ntfs_inode *ni, + size_t *bit, struct ATTRIB **bitmap) +{ + struct ATTRIB *b; + struct ATTR_LIST_ENTRY *le = NULL; + const struct INDEX_NAMES *in = &s_index_names[indx->type]; + + b = ni_find_attr(ni, NULL, &le, ATTR_BITMAP, in->name, in->name_len, + NULL, NULL); + + if (!b) + return -ENOENT; + + *bitmap = b; + *bit = MINUS_ONE_T; + + if (!b->non_res) { + u32 nbits = 8 * le32_to_cpu(b->res.data_size); + size_t pos = find_next_zero_bit(resident_data(b), nbits, 0); + + if (pos < nbits) + *bit = pos; + } else { + int err = scan_nres_bitmap(ni->mi.sbi, b, &indx->bitmap_run, 0, + &scan_for_free, bit); + + if (err) + return err; + } + + return 0; +} + +static bool scan_for_used(const ulong *buf, u32 bit, u32 bits, size_t *ret) +{ + size_t pos = find_next_bit(buf, bits, bit); + + if (pos >= bits) + return false; + *ret = pos; + return true; +} + +/* + * indx_used_bit + * + * looks for used bit + * returns MINUS_ONE_T if no used bits + */ +int indx_used_bit(struct ntfs_index *indx, struct ntfs_inode *ni, size_t *bit) +{ + struct ATTRIB *b; + struct ATTR_LIST_ENTRY *le = NULL; + size_t from = *bit; + const struct INDEX_NAMES *in = &s_index_names[indx->type]; + + b = ni_find_attr(ni, NULL, &le, ATTR_BITMAP, in->name, in->name_len, + NULL, NULL); + + if (!b) + return -ENOENT; + + *bit = MINUS_ONE_T; + + if (!b->non_res) { + u32 nbits = le32_to_cpu(b->res.data_size) * 8; + size_t pos = find_next_bit(resident_data(b), nbits, from); + + if (pos < nbits) + *bit = pos; + } else { + int err = scan_nres_bitmap(ni->mi.sbi, b, &indx->bitmap_run, + from, &scan_for_used, bit); + if (err) + return err; + } + + return 0; +} + +/* + * hdr_find_split + * + * finds a point at which the index allocation buffer would like to + * be split. + * NOTE: This function should never return 'END' entry NULL returns on error + */ +static inline const struct NTFS_DE *hdr_find_split(const struct INDEX_HDR *hdr) +{ + size_t o; + const struct NTFS_DE *e = hdr_first_de(hdr); + u32 used_2 = le32_to_cpu(hdr->used) >> 1; + u16 esize = le16_to_cpu(e->size); + + if (!e || de_is_last(e)) + return NULL; + + for (o = le32_to_cpu(hdr->de_off) + esize; o < used_2; o += esize) { + const struct NTFS_DE *p = e; + + e = Add2Ptr(hdr, o); + + /* We must not return END entry */ + if (de_is_last(e)) + return p; + + esize = le16_to_cpu(e->size); + } + + return e; +} + +/* + * hdr_insert_head + * + * inserts some entries at the beginning of the buffer. + * It is used to insert entries into a newly-created buffer. + */ +static inline const struct NTFS_DE * +hdr_insert_head(struct INDEX_HDR *hdr, const void *ins, u32 ins_bytes) +{ + u32 to_move; + struct NTFS_DE *e = hdr_first_de(hdr); + u32 used = le32_to_cpu(hdr->used); + + if (!e) + return NULL; + + /* Now we just make room for the inserted entries and jam it in. */ + to_move = used - le32_to_cpu(hdr->de_off); + memmove(Add2Ptr(e, ins_bytes), e, to_move); + memcpy(e, ins, ins_bytes); + hdr->used = cpu_to_le32(used + ins_bytes); + + return e; +} + +void fnd_clear(struct ntfs_fnd *fnd) +{ + int i; + + for (i = 0; i < fnd->level; i++) { + struct indx_node *n = fnd->nodes[i]; + + if (!n) + continue; + + put_indx_node(n); + fnd->nodes[i] = NULL; + } + fnd->level = 0; + fnd->root_de = NULL; +} + +static int fnd_push(struct ntfs_fnd *fnd, struct indx_node *n, + struct NTFS_DE *e) +{ + int i; + + i = fnd->level; + if (i < 0 || i >= ARRAY_SIZE(fnd->nodes)) + return -EINVAL; + fnd->nodes[i] = n; + fnd->de[i] = e; + fnd->level += 1; + return 0; +} + +static struct indx_node *fnd_pop(struct ntfs_fnd *fnd) +{ + struct indx_node *n; + int i = fnd->level; + + i -= 1; + n = fnd->nodes[i]; + fnd->nodes[i] = NULL; + fnd->level = i; + + return n; +} + +static bool fnd_is_empty(struct ntfs_fnd *fnd) +{ + if (!fnd->level) + return !fnd->root_de; + + return !fnd->de[fnd->level - 1]; +} + +struct ntfs_fnd *fnd_get(struct ntfs_index *indx) +{ + struct ntfs_fnd *fnd = ntfs_alloc(sizeof(struct ntfs_fnd), 1); + + if (!fnd) + return NULL; + + return fnd; +} + +void fnd_put(struct ntfs_fnd *fnd) +{ + if (!fnd) + return; + fnd_clear(fnd); + ntfs_free(fnd); +} + +/* + * hdr_find_e + * + * locates an entry the index buffer. + * If no matching entry is found, it returns the first entry which is greater + * than the desired entry If the search key is greater than all the entries the + * buffer, it returns the 'end' entry. This function does a binary search of the + * current index buffer, for the first entry that is <= to the search value + * Returns NULL if error + */ +static struct NTFS_DE *hdr_find_e(const struct ntfs_index *indx, + const struct INDEX_HDR *hdr, const void *key, + size_t key_len, const void *ctx, int *diff) +{ + struct NTFS_DE *e; + NTFS_CMP_FUNC cmp = indx->cmp; + u32 e_size, e_key_len; + u32 end = le32_to_cpu(hdr->used); + u32 off = le32_to_cpu(hdr->de_off); + +#ifdef NTFS3_INDEX_BINARY_SEARCH + int max_idx = 0, fnd, min_idx; + int nslots = 64; + u16 *offs; + + if (end > 0x10000) + goto next; + + offs = ntfs_alloc(sizeof(u16) * nslots, 0); + if (!offs) + goto next; + + /* use binary search algorithm */ +next1: + if (off + sizeof(struct NTFS_DE) > end) { + e = NULL; + goto out1; + } + e = Add2Ptr(hdr, off); + e_size = le16_to_cpu(e->size); + + if (e_size < sizeof(struct NTFS_DE) || off + e_size > end) { + e = NULL; + goto out1; + } + + if (max_idx >= nslots) { + u16 *ptr; + int new_slots = QuadAlign(2 * nslots); + + ptr = ntfs_alloc(sizeof(u16) * new_slots, 0); + if (ptr) + memcpy(ptr, offs, sizeof(u16) * max_idx); + ntfs_free(offs); + offs = ptr; + nslots = new_slots; + if (!ptr) + goto next; + } + + /* Store entry table */ + offs[max_idx] = off; + + if (!de_is_last(e)) { + off += e_size; + max_idx += 1; + goto next1; + } + + /* + * Table of pointers is created + * Use binary search to find entry that is <= to the search value + */ + fnd = -1; + min_idx = 0; + + while (min_idx <= max_idx) { + int mid_idx = min_idx + ((max_idx - min_idx) >> 1); + int diff2; + + e = Add2Ptr(hdr, offs[mid_idx]); + + e_key_len = le16_to_cpu(e->key_size); + + diff2 = (*cmp)(key, key_len, e + 1, e_key_len, ctx); + + if (!diff2) { + *diff = 0; + goto out1; + } + + if (diff2 < 0) { + max_idx = mid_idx - 1; + fnd = mid_idx; + if (!fnd) + break; + } else { + min_idx = mid_idx + 1; + } + } + + if (fnd == -1) { + e = NULL; + goto out1; + } + + *diff = -1; + e = Add2Ptr(hdr, offs[fnd]); + +out1: + ntfs_free(offs); + + return e; +#endif + +next: + /* + * Entries index are sorted + * Enumerate all entries until we find entry that is <= to the search value + */ + if (off + sizeof(struct NTFS_DE) > end) + return NULL; + + e = Add2Ptr(hdr, off); + e_size = le16_to_cpu(e->size); + + if (e_size < sizeof(struct NTFS_DE) || off + e_size > end) + return NULL; + + off += e_size; + + e_key_len = le16_to_cpu(e->key_size); + + *diff = (*cmp)(key, key_len, e + 1, e_key_len, ctx); + if (!*diff) + return e; + + if (*diff <= 0) + return e; + + if (de_is_last(e)) { + *diff = 1; + return e; + } + goto next; +} + +/* + * hdr_insert_de + * + * inserts an index entry into the buffer. + * 'before' should be a pointer previously returned from hdr_find_e + */ +static struct NTFS_DE *hdr_insert_de(const struct ntfs_index *indx, + struct INDEX_HDR *hdr, + const struct NTFS_DE *de, + struct NTFS_DE *before, const void *ctx) +{ + int diff; + size_t off = PtrOffset(hdr, before); + u32 used = le32_to_cpu(hdr->used); + u32 total = le32_to_cpu(hdr->total); + u16 de_size = le16_to_cpu(de->size); + + /* First, check to see if there's enough room */ + if (used + de_size > total) + return NULL; + + /* We know there's enough space, so we know we'll succeed. */ + if (before) { + /* Check that before is inside Index */ + if (off >= used || off < le32_to_cpu(hdr->de_off) || + off + le16_to_cpu(before->size) > total) { + return NULL; + } + goto ok; + } + /* No insert point is applied. Get it manually */ + before = hdr_find_e(indx, hdr, de + 1, le16_to_cpu(de->key_size), ctx, + &diff); + if (!before) + return NULL; + off = PtrOffset(hdr, before); + +ok: + /* Now we just make room for the entry and jam it in. */ + memmove(Add2Ptr(before, de_size), before, used - off); + + hdr->used = cpu_to_le32(used + de_size); + memcpy(before, de, de_size); + + return before; +} + +/* + * hdr_delete_de + * + * removes an entry from the index buffer + */ +static inline struct NTFS_DE *hdr_delete_de(struct INDEX_HDR *hdr, + struct NTFS_DE *re) +{ + u32 used = le32_to_cpu(hdr->used); + u16 esize = le16_to_cpu(re->size); + u32 off = PtrOffset(hdr, re); + int bytes = used - (off + esize); + + if (off >= used || esize < sizeof(struct NTFS_DE) || + bytes < sizeof(struct NTFS_DE)) + return NULL; + + hdr->used = cpu_to_le32(used - esize); + memmove(re, Add2Ptr(re, esize), bytes); + + return re; +} + +void indx_clear(struct ntfs_index *indx) +{ + run_close(&indx->alloc_run); + run_close(&indx->bitmap_run); +} + +int indx_init(struct ntfs_index *indx, struct ntfs_sb_info *sbi, + const struct ATTRIB *attr, enum index_mutex_classed type) +{ + u32 t32; + const struct INDEX_ROOT *root = resident_data(attr); + + /* Check root fields */ + if (!root->index_block_clst) + return -EINVAL; + + indx->type = type; + indx->idx2vbn_bits = __ffs(root->index_block_clst); + + t32 = le32_to_cpu(root->index_block_size); + indx->index_bits = blksize_bits(t32); + + /* Check index record size */ + if (t32 < sbi->cluster_size) { + /* index record is smaller than a cluster, use 512 blocks */ + if (t32 != root->index_block_clst * SECTOR_SIZE) + return -EINVAL; + + /* Check alignment to a cluster */ + if ((sbi->cluster_size >> SECTOR_SHIFT) & + (root->index_block_clst - 1)) { + return -EINVAL; + } + + indx->vbn2vbo_bits = SECTOR_SHIFT; + } else { + /* index record must be a multiple of cluster size */ + if (t32 != root->index_block_clst << sbi->cluster_bits) + return -EINVAL; + + indx->vbn2vbo_bits = sbi->cluster_bits; + } + + indx->cmp = get_cmp_func(root); + + return indx->cmp ? 0 : -EINVAL; +} + +static struct indx_node *indx_new(struct ntfs_index *indx, + struct ntfs_inode *ni, CLST vbn, + const __le64 *sub_vbn) +{ + int err; + struct NTFS_DE *e; + struct indx_node *r; + struct INDEX_HDR *hdr; + struct INDEX_BUFFER *index; + u64 vbo = (u64)vbn << indx->vbn2vbo_bits; + u32 bytes = 1u << indx->index_bits; + u16 fn; + u32 eo; + + r = ntfs_alloc(sizeof(struct indx_node), 1); + if (!r) + return ERR_PTR(-ENOMEM); + + index = ntfs_alloc(bytes, 1); + if (!index) { + ntfs_free(r); + return ERR_PTR(-ENOMEM); + } + + err = ntfs_get_bh(ni->mi.sbi, &indx->alloc_run, vbo, bytes, &r->nb); + + if (err) { + ntfs_free(index); + ntfs_free(r); + return ERR_PTR(err); + } + + /* Create header */ + index->rhdr.sign = NTFS_INDX_SIGNATURE; + index->rhdr.fix_off = cpu_to_le16(sizeof(struct INDEX_BUFFER)); // 0x28 + fn = (bytes >> SECTOR_SHIFT) + 1; // 9 + index->rhdr.fix_num = cpu_to_le16(fn); + index->vbn = cpu_to_le64(vbn); + hdr = &index->ihdr; + eo = QuadAlign(sizeof(struct INDEX_BUFFER) + fn * sizeof(short)); + hdr->de_off = cpu_to_le32(eo); + + e = Add2Ptr(hdr, eo); + + if (sub_vbn) { + e->flags = NTFS_IE_LAST | NTFS_IE_HAS_SUBNODES; + e->size = cpu_to_le16(sizeof(struct NTFS_DE) + sizeof(u64)); + hdr->used = + cpu_to_le32(eo + sizeof(struct NTFS_DE) + sizeof(u64)); + de_set_vbn_le(e, *sub_vbn); + hdr->flags = 1; + } else { + e->size = cpu_to_le16(sizeof(struct NTFS_DE)); + hdr->used = cpu_to_le32(eo + sizeof(struct NTFS_DE)); + e->flags = NTFS_IE_LAST; + } + + hdr->total = cpu_to_le32(bytes - offsetof(struct INDEX_BUFFER, ihdr)); + + r->index = index; + return r; +} + +struct INDEX_ROOT *indx_get_root(struct ntfs_index *indx, struct ntfs_inode *ni, + struct ATTRIB **attr, struct mft_inode **mi) +{ + struct ATTR_LIST_ENTRY *le = NULL; + struct ATTRIB *a; + const struct INDEX_NAMES *in = &s_index_names[indx->type]; + + a = ni_find_attr(ni, NULL, &le, ATTR_ROOT, in->name, in->name_len, NULL, + mi); + if (!a) + return NULL; + + if (attr) + *attr = a; + + return resident_data_ex(a, sizeof(struct INDEX_ROOT)); +} + +static int indx_write(struct ntfs_index *indx, struct ntfs_inode *ni, + struct indx_node *node, int sync) +{ + struct INDEX_BUFFER *ib = node->index; + + return ntfs_write_bh(ni->mi.sbi, &ib->rhdr, &node->nb, sync); +} + +int indx_read(struct ntfs_index *indx, struct ntfs_inode *ni, CLST vbn, + struct indx_node **node) +{ + int err; + struct INDEX_BUFFER *ib; + u64 vbo = (u64)vbn << indx->vbn2vbo_bits; + u32 bytes = 1u << indx->index_bits; + struct indx_node *in = *node; + const struct INDEX_NAMES *name; + + if (!in) { + in = ntfs_alloc(sizeof(struct indx_node), 1); + if (!in) + return -ENOMEM; + } else { + nb_put(&in->nb); + } + + ib = in->index; + if (!ib) { + ib = ntfs_alloc(bytes, 0); + if (!ib) { + err = -ENOMEM; + goto out; + } + } + + err = ntfs_read_bh(ni->mi.sbi, &indx->alloc_run, vbo, &ib->rhdr, bytes, + &in->nb); + + if (!err) + goto ok; + + if (err == 1) + goto ok; + + if (err != -ENOENT) + goto out; + + name = &s_index_names[indx->type]; + err = attr_load_runs_vcn(ni, ATTR_ALLOC, name->name, name->name_len, + &indx->alloc_run, + vbo >> ni->mi.sbi->cluster_bits); + if (err) + goto out; + + err = ntfs_read_bh(ni->mi.sbi, &indx->alloc_run, vbo, &ib->rhdr, bytes, + &in->nb); + if (err == 1) + goto ok; + + if (err) + goto out; + +ok: + if (err == 1) { + ntfs_write_bh(ni->mi.sbi, &ib->rhdr, &in->nb, 0); + err = 0; + } + + in->index = ib; + *node = in; + +out: + if (ib != in->index) + ntfs_free(ib); + + if (*node != in) { + nb_put(&in->nb); + ntfs_free(in); + } + + return err; +} + +/* + * indx_find + * + * scans NTFS directory for given entry + */ +int indx_find(struct ntfs_index *indx, struct ntfs_inode *ni, + const struct INDEX_ROOT *root, const void *key, size_t key_len, + const void *ctx, int *diff, struct NTFS_DE **entry, + struct ntfs_fnd *fnd) +{ + int err; + struct NTFS_DE *e; + const struct INDEX_HDR *hdr; + struct indx_node *node; + + if (!root) + root = indx_get_root(&ni->dir, ni, NULL, NULL); + + if (!root) { + err = -EINVAL; + goto out; + } + + hdr = &root->ihdr; + + /* Check cache */ + e = fnd->level ? fnd->de[fnd->level - 1] : fnd->root_de; + if (e && !de_is_last(e) && + !(*indx->cmp)(key, key_len, e + 1, le16_to_cpu(e->key_size), ctx)) { + *entry = e; + *diff = 0; + return 0; + } + + /* Soft finder reset */ + fnd_clear(fnd); + + /* Lookup entry that is <= to the search value */ + e = hdr_find_e(indx, hdr, key, key_len, ctx, diff); + if (!e) + return -EINVAL; + + if (fnd) + fnd->root_de = e; + + err = 0; + + for (;;) { + node = NULL; + if (*diff >= 0 || !de_has_vcn_ex(e)) { + *entry = e; + goto out; + } + + /* Read next level. */ + err = indx_read(indx, ni, de_get_vbn(e), &node); + if (err) + goto out; + + /* Lookup entry that is <= to the search value */ + e = hdr_find_e(indx, &node->index->ihdr, key, key_len, ctx, + diff); + if (!e) { + err = -EINVAL; + put_indx_node(node); + goto out; + } + + fnd_push(fnd, node, e); + } + +out: + return err; +} + +int indx_find_sort(struct ntfs_index *indx, struct ntfs_inode *ni, + const struct INDEX_ROOT *root, struct NTFS_DE **entry, + struct ntfs_fnd *fnd) +{ + int err; + struct indx_node *n = NULL; + struct NTFS_DE *e; + size_t iter = 0; + int level = fnd->level; + + if (!*entry) { + /* Start find */ + e = hdr_first_de(&root->ihdr); + if (!e) + return 0; + fnd_clear(fnd); + fnd->root_de = e; + } else if (!level) { + if (de_is_last(fnd->root_de)) { + *entry = NULL; + return 0; + } + + e = hdr_next_de(&root->ihdr, fnd->root_de); + if (!e) + return -EINVAL; + fnd->root_de = e; + } else { + n = fnd->nodes[level - 1]; + e = fnd->de[level - 1]; + + if (de_is_last(e)) + goto pop_level; + + e = hdr_next_de(&n->index->ihdr, e); + if (!e) + return -EINVAL; + + fnd->de[level - 1] = e; + } + + /* Just to avoid tree cycle */ +next_iter: + if (iter++ >= 1000) + return -EINVAL; + + while (de_has_vcn_ex(e)) { + if (le16_to_cpu(e->size) < + sizeof(struct NTFS_DE) + sizeof(u64)) { + if (n) { + fnd_pop(fnd); + ntfs_free(n); + } + return -EINVAL; + } + + /* Read next level */ + err = indx_read(indx, ni, de_get_vbn(e), &n); + if (err) + return err; + + /* Try next level */ + e = hdr_first_de(&n->index->ihdr); + if (!e) { + ntfs_free(n); + return -EINVAL; + } + + fnd_push(fnd, n, e); + } + + if (le16_to_cpu(e->size) > sizeof(struct NTFS_DE)) { + *entry = e; + return 0; + } + +pop_level: + for (;;) { + if (!de_is_last(e)) + goto next_iter; + + /* Pop one level */ + if (n) { + fnd_pop(fnd); + ntfs_free(n); + } + + level = fnd->level; + + if (level) { + n = fnd->nodes[level - 1]; + e = fnd->de[level - 1]; + } else if (fnd->root_de) { + n = NULL; + e = fnd->root_de; + fnd->root_de = NULL; + } else { + *entry = NULL; + return 0; + } + + if (le16_to_cpu(e->size) > sizeof(struct NTFS_DE)) { + *entry = e; + if (!fnd->root_de) + fnd->root_de = e; + return 0; + } + } +} + +int indx_find_raw(struct ntfs_index *indx, struct ntfs_inode *ni, + const struct INDEX_ROOT *root, struct NTFS_DE **entry, + size_t *off, struct ntfs_fnd *fnd) +{ + int err; + struct indx_node *n = NULL; + struct NTFS_DE *e = NULL; + struct NTFS_DE *e2; + size_t bit; + CLST next_used_vbn; + CLST next_vbn; + u32 record_size = ni->mi.sbi->record_size; + + /* Use non sorted algorithm */ + if (!*entry) { + /* This is the first call */ + e = hdr_first_de(&root->ihdr); + if (!e) + return 0; + fnd_clear(fnd); + fnd->root_de = e; + + /* The first call with setup of initial element */ + if (*off >= record_size) { + next_vbn = (((*off - record_size) >> indx->index_bits)) + << indx->idx2vbn_bits; + /* jump inside cycle 'for'*/ + goto next; + } + + /* Start enumeration from root */ + *off = 0; + } else if (!fnd->root_de) + return -EINVAL; + + for (;;) { + /* Check if current entry can be used */ + if (e && le16_to_cpu(e->size) > sizeof(struct NTFS_DE)) + goto ok; + + if (!fnd->level) { + /* Continue to enumerate root */ + if (!de_is_last(fnd->root_de)) { + e = hdr_next_de(&root->ihdr, fnd->root_de); + if (!e) + return -EINVAL; + fnd->root_de = e; + continue; + } + + /* Start to enumerate indexes from 0 */ + next_vbn = 0; + } else { + /* Continue to enumerate indexes */ + e2 = fnd->de[fnd->level - 1]; + + n = fnd->nodes[fnd->level - 1]; + + if (!de_is_last(e2)) { + e = hdr_next_de(&n->index->ihdr, e2); + if (!e) + return -EINVAL; + fnd->de[fnd->level - 1] = e; + continue; + } + + /* Continue with next index */ + next_vbn = le64_to_cpu(n->index->vbn) + + root->index_block_clst; + } + +next: + /* Release current index */ + if (n) { + fnd_pop(fnd); + put_indx_node(n); + n = NULL; + } + + /* Skip all free indexes */ + bit = next_vbn >> indx->idx2vbn_bits; + err = indx_used_bit(indx, ni, &bit); + if (err == -ENOENT || bit == MINUS_ONE_T) { + /* No used indexes */ + *entry = NULL; + return 0; + } + + next_used_vbn = bit << indx->idx2vbn_bits; + + /* Read buffer into memory */ + err = indx_read(indx, ni, next_used_vbn, &n); + if (err) + return err; + + e = hdr_first_de(&n->index->ihdr); + fnd_push(fnd, n, e); + if (!e) + return -EINVAL; + } + +ok: + /* return offset to restore enumerator if necessary */ + if (!n) { + /* 'e' points in root */ + *off = PtrOffset(&root->ihdr, e); + } else { + /* 'e' points in index */ + *off = (le64_to_cpu(n->index->vbn) << indx->vbn2vbo_bits) + + record_size + PtrOffset(&n->index->ihdr, e); + } + + *entry = e; + return 0; +} + +/* + * indx_create_allocate + * + * create "Allocation + Bitmap" attributes + */ +static int indx_create_allocate(struct ntfs_index *indx, struct ntfs_inode *ni, + CLST *vbn) +{ + int err = -ENOMEM; + struct ntfs_sb_info *sbi = ni->mi.sbi; + struct ATTRIB *bitmap; + struct ATTRIB *alloc; + u32 alloc_size = ntfs_up_cluster(sbi, 1u << indx->index_bits); + CLST len = alloc_size >> sbi->cluster_bits; + const struct INDEX_NAMES *in = &s_index_names[indx->type]; + CLST alen; + struct runs_tree run; + + run_init(&run); + + err = attr_allocate_clusters(sbi, &run, 0, 0, len, NULL, 0, &alen, 0, + NULL); + if (err) + goto out; + + err = ni_insert_nonresident(ni, ATTR_ALLOC, in->name, in->name_len, + &run, 0, len, 0, &alloc, NULL); + if (err) + goto out1; + + err = ni_insert_resident(ni, QuadAlign(1), ATTR_BITMAP, in->name, + in->name_len, &bitmap, NULL); + if (err) + goto out2; + + memcpy(&indx->alloc_run, &run, sizeof(run)); + + *vbn = 0; + + if (in->name == I30_NAME) + ni->vfs_inode.i_size = alloc_size; + + return 0; + +out2: + mi_remove_attr(&ni->mi, alloc); + +out1: + run_deallocate(sbi, &run, false); + +out: + return err; +} + +/* + * indx_add_allocate + * + * add clusters to index + */ +static int indx_add_allocate(struct ntfs_index *indx, struct ntfs_inode *ni, + CLST *vbn) +{ + int err; + size_t bit; + u64 data_size, alloc_size; + u64 bpb, vbpb; + struct ATTRIB *bmp, *alloc; + struct mft_inode *mi; + const struct INDEX_NAMES *in = &s_index_names[indx->type]; + + err = indx_find_free(indx, ni, &bit, &bmp); + if (err) + goto out1; + + if (bit != MINUS_ONE_T) { + bmp = NULL; + } else { + if (bmp->non_res) { + bpb = le64_to_cpu(bmp->nres.data_size); + vbpb = le64_to_cpu(bmp->nres.valid_size); + } else { + bpb = vbpb = le32_to_cpu(bmp->res.data_size); + } + + /* Increase bitmap */ + err = attr_set_size(ni, ATTR_BITMAP, in->name, in->name_len, + &indx->bitmap_run, QuadAlign(bpb + 8), NULL, + true, NULL); + if (err) + goto out1; + + bit = bpb << 3; + } + + alloc = ni_find_attr(ni, NULL, NULL, ATTR_ALLOC, in->name, in->name_len, + NULL, &mi); + if (!alloc) { + if (bmp) + goto out2; + goto out1; + } + + data_size = (u64)(bit + 1) << indx->index_bits; + alloc_size = ntfs_up_cluster(ni->mi.sbi, data_size); + + if (alloc_size > le64_to_cpu(alloc->nres.alloc_size)) { + /* Increase allocation */ + err = attr_set_size(ni, ATTR_ALLOC, in->name, in->name_len, + &indx->alloc_run, alloc_size, &alloc_size, + true, NULL); + if (err) { + if (bmp) + goto out2; + goto out1; + } + + if (in->name == I30_NAME) + ni->vfs_inode.i_size = alloc_size; + } else if (data_size > le64_to_cpu(alloc->nres.data_size)) { + alloc->nres.data_size = alloc->nres.valid_size = + cpu_to_le64(data_size); + mi->dirty = true; + } + + *vbn = bit << indx->idx2vbn_bits; + + return 0; + +out2: + /* Ops (no space?) */ + attr_set_size(ni, ATTR_BITMAP, in->name, in->name_len, + &indx->bitmap_run, bpb, &vbpb, false, NULL); + +out1: + return err; +} + +/* + * indx_insert_into_root + * + * attempts to insert an entry into the index root + * If necessary, it will twiddle the index b-tree. + */ +static int indx_insert_into_root(struct ntfs_index *indx, struct ntfs_inode *ni, + const struct NTFS_DE *new_de, + struct NTFS_DE *root_de, const void *ctx, + struct ntfs_fnd *fnd) +{ + int err = 0; + struct NTFS_DE *e, *e0, *re; + struct mft_inode *mi; + struct ATTRIB *attr; + struct MFT_REC *rec; + struct INDEX_HDR *hdr; + struct indx_node *n; + CLST new_vbn; + __le64 *sub_vbn, t_vbn; + u16 new_de_size; + u32 hdr_used, hdr_total, asize, tail, used, aoff, to_move; + u32 root_size, new_root_size; + struct ntfs_sb_info *sbi; + char *next; + int ds_root; + struct INDEX_ROOT *root, *a_root = NULL; + + /* Get the record this root placed in */ + root = indx_get_root(indx, ni, &attr, &mi); + if (!root) + goto out; + + /* + * Try easy case: + * hdr_insert_de will succeed if there's room the root for the new entry. + */ + hdr = &root->ihdr; + sbi = ni->mi.sbi; + rec = mi->mrec; + aoff = PtrOffset(rec, attr); + used = le32_to_cpu(rec->used); + new_de_size = le16_to_cpu(new_de->size); + hdr_used = le32_to_cpu(hdr->used); + hdr_total = le32_to_cpu(hdr->total); + asize = le32_to_cpu(attr->size); + next = Add2Ptr(attr, asize); + tail = used - aoff - asize; + root_size = le32_to_cpu(attr->res.data_size); + + ds_root = new_de_size + hdr_used - hdr_total; + + if (used + ds_root < sbi->max_bytes_per_attr) { + /* make a room for new elements */ + memmove(next + ds_root, next, used - aoff - asize); + hdr->total = cpu_to_le32(hdr_total + ds_root); + e = hdr_insert_de(indx, hdr, new_de, root_de, ctx); + WARN_ON(!e); + fnd_clear(fnd); + fnd->root_de = e; + attr->size = cpu_to_le32(asize + ds_root); + attr->res.data_size = cpu_to_le32(root_size + ds_root); + rec->used = cpu_to_le32(used + ds_root); + + return 0; + } + + /* Make a copy of root attribute to restore if error */ + a_root = ntfs_memdup(attr, asize); + if (!a_root) { + err = -ENOMEM; + goto out; + } + + /* copy all the non-end entries from the index root to the new buffer.*/ + to_move = 0; + e0 = hdr_first_de(hdr); + + /* Calculate the size to copy */ + for (e = e0;; e = hdr_next_de(hdr, e)) { + if (!e) { + err = -EINVAL; + goto out; + } + + if (de_is_last(e)) + break; + to_move += le16_to_cpu(e->size); + } + + n = NULL; + if (!to_move) { + re = NULL; + } else { + re = ntfs_memdup(e0, to_move); + if (!re) { + err = -ENOMEM; + goto out; + } + } + + sub_vbn = NULL; + if (de_has_vcn(e)) { + t_vbn = de_get_vbn_le(e); + sub_vbn = &t_vbn; + } + + new_root_size = sizeof(struct INDEX_ROOT) + sizeof(struct NTFS_DE) + + sizeof(u64); + ds_root = new_root_size - root_size; + + if (ds_root > 0 && used + ds_root > sbi->max_bytes_per_attr) { + /* make root external */ + err = -EOPNOTSUPP; + goto out; + } + + if (ds_root) { + memmove(next + ds_root, next, tail); + used += ds_root; + asize += ds_root; + rec->used = cpu_to_le32(used); + attr->size = cpu_to_le32(asize); + attr->res.data_size = cpu_to_le32(new_root_size); + mi->dirty = true; + } + + /* Fill first entry (vcn will be set later) */ + e = (struct NTFS_DE *)(root + 1); + memset(e, 0, sizeof(struct NTFS_DE)); + e->size = cpu_to_le16(sizeof(struct NTFS_DE) + sizeof(u64)); + e->flags = NTFS_IE_HAS_SUBNODES | NTFS_IE_LAST; + + hdr->flags = 1; + hdr->used = hdr->total = + cpu_to_le32(new_root_size - offsetof(struct INDEX_ROOT, ihdr)); + + fnd->root_de = hdr_first_de(hdr); + + /* Create alloc and bitmap attributes (if not) */ + if (run_is_empty(&indx->alloc_run)) { + err = indx_create_allocate(indx, ni, &new_vbn); + if (err) { + /* restore root after 'indx_create_allocate' */ + memmove(next - ds_root, next, tail); + used -= ds_root; + rec->used = cpu_to_le32(used); + memcpy(attr, a_root, asize); + goto out1; + } + } else { + err = indx_add_allocate(indx, ni, &new_vbn); + if (err) + goto out1; + } + + root = indx_get_root(indx, ni, &attr, &mi); + if (!root) { + err = -EINVAL; + goto out1; + } + + e = (struct NTFS_DE *)(root + 1); + *(__le64 *)(e + 1) = cpu_to_le64(new_vbn); + + /* now we can create/format the new buffer and copy the entries into */ + n = indx_new(indx, ni, new_vbn, sub_vbn); + if (IS_ERR(n)) { + err = PTR_ERR(n); + goto out1; + } + + hdr = &n->index->ihdr; + hdr_used = le32_to_cpu(hdr->used); + hdr_total = le32_to_cpu(hdr->total); + + /* Copy root entries into new buffer */ + hdr_insert_head(hdr, re, to_move); + + /* Update bitmap attribute */ + indx_mark_used(indx, ni, new_vbn >> indx->idx2vbn_bits); + + /* Check if we can insert new entry new index buffer */ + if (hdr_used + new_de_size > hdr_total) { + /* + * This occurs if mft record is the same or bigger than index + * buffer. Move all root new index and have no space to add + * new entry classic case when mft record is 1K and index + * buffer 4K the problem should not occurs + */ + ntfs_free(re); + indx_write(indx, ni, n, 0); + + put_indx_node(n); + fnd_clear(fnd); + err = indx_insert_entry(indx, ni, new_de, ctx, fnd); + goto out; + } + + /* + * Now root is a parent for new index buffer + * Insert NewEntry a new buffer + */ + e = hdr_insert_de(indx, hdr, new_de, NULL, ctx); + if (!e) { + err = -EINVAL; + goto out1; + } + fnd_push(fnd, n, e); + + /* Just write updates index into disk */ + indx_write(indx, ni, n, 0); + + n = NULL; + +out1: + ntfs_free(re); + if (n) + put_indx_node(n); + +out: + ntfs_free(a_root); + return err; +} + +/* + * indx_insert_into_buffer + * + * attempts to insert an entry into an Index Allocation Buffer. + * If necessary, it will split the buffer. + */ +static int +indx_insert_into_buffer(struct ntfs_index *indx, struct ntfs_inode *ni, + struct INDEX_ROOT *root, const struct NTFS_DE *new_de, + const void *ctx, int level, struct ntfs_fnd *fnd) +{ + int err; + const struct NTFS_DE *sp; + struct NTFS_DE *e, *de_t, *up_e = NULL; + struct indx_node *n2 = NULL; + struct indx_node *n1 = fnd->nodes[level]; + struct INDEX_HDR *hdr1 = &n1->index->ihdr; + struct INDEX_HDR *hdr2; + u32 to_copy, used; + CLST new_vbn; + __le64 t_vbn, *sub_vbn; + u16 sp_size; + + /* Try the most easy case */ + e = fnd->level - 1 == level ? fnd->de[level] : NULL; + e = hdr_insert_de(indx, hdr1, new_de, e, ctx); + fnd->de[level] = e; + if (e) { + /* Just write updated index into disk */ + indx_write(indx, ni, n1, 0); + return 0; + } + + /* + * No space to insert into buffer. Split it. + * To split we: + * - Save split point ('cause index buffers will be changed) + * - Allocate NewBuffer and copy all entries <= sp into new buffer + * - Remove all entries (sp including) from TargetBuffer + * - Insert NewEntry into left or right buffer (depending on sp <=> + * NewEntry) + * - Insert sp into parent buffer (or root) + * - Make sp a parent for new buffer + */ + sp = hdr_find_split(hdr1); + if (!sp) + return -EINVAL; + + sp_size = le16_to_cpu(sp->size); + up_e = ntfs_alloc(sp_size + sizeof(u64), 0); + if (!up_e) + return -ENOMEM; + memcpy(up_e, sp, sp_size); + + if (!hdr1->flags) { + up_e->flags |= NTFS_IE_HAS_SUBNODES; + up_e->size = cpu_to_le16(sp_size + sizeof(u64)); + sub_vbn = NULL; + } else { + t_vbn = de_get_vbn_le(up_e); + sub_vbn = &t_vbn; + } + + /* Allocate on disk a new index allocation buffer. */ + err = indx_add_allocate(indx, ni, &new_vbn); + if (err) + goto out; + + /* Allocate and format memory a new index buffer */ + n2 = indx_new(indx, ni, new_vbn, sub_vbn); + if (IS_ERR(n2)) { + err = PTR_ERR(n2); + goto out; + } + + hdr2 = &n2->index->ihdr; + + /* Make sp a parent for new buffer */ + de_set_vbn(up_e, new_vbn); + + /* copy all the entries <= sp into the new buffer. */ + de_t = hdr_first_de(hdr1); + to_copy = PtrOffset(de_t, sp); + hdr_insert_head(hdr2, de_t, to_copy); + + /* remove all entries (sp including) from hdr1 */ + used = le32_to_cpu(hdr1->used) - to_copy - sp_size; + memmove(de_t, Add2Ptr(sp, sp_size), used - le32_to_cpu(hdr1->de_off)); + hdr1->used = cpu_to_le32(used); + + /* Insert new entry into left or right buffer (depending on sp <=> new_de) */ + hdr_insert_de(indx, + (*indx->cmp)(new_de + 1, le16_to_cpu(new_de->key_size), + up_e + 1, le16_to_cpu(up_e->key_size), + ctx) < 0 ? + hdr2 : + hdr1, + new_de, NULL, ctx); + + indx_mark_used(indx, ni, new_vbn >> indx->idx2vbn_bits); + + indx_write(indx, ni, n1, 0); + indx_write(indx, ni, n2, 0); + + put_indx_node(n2); + + /* + * we've finished splitting everybody, so we are ready to + * insert the promoted entry into the parent. + */ + if (!level) { + /* Insert in root */ + err = indx_insert_into_root(indx, ni, up_e, NULL, ctx, fnd); + if (err) + goto out; + } else { + /* + * The target buffer's parent is another index buffer + * TODO: Remove recursion + */ + err = indx_insert_into_buffer(indx, ni, root, up_e, ctx, + level - 1, fnd); + if (err) + goto out; + } + +out: + ntfs_free(up_e); + + return err; +} + +/* + * indx_insert_entry + * + * inserts new entry into index + */ +int indx_insert_entry(struct ntfs_index *indx, struct ntfs_inode *ni, + const struct NTFS_DE *new_de, const void *ctx, + struct ntfs_fnd *fnd) +{ + int err; + int diff; + struct NTFS_DE *e; + struct ntfs_fnd *fnd_a = NULL; + struct INDEX_ROOT *root; + + if (!fnd) { + fnd_a = fnd_get(indx); + if (!fnd_a) { + err = -ENOMEM; + goto out1; + } + fnd = fnd_a; + } + + root = indx_get_root(indx, ni, NULL, NULL); + if (!root) { + err = -EINVAL; + goto out; + } + + if (fnd_is_empty(fnd)) { + /* Find the spot the tree where we want to insert the new entry. */ + err = indx_find(indx, ni, root, new_de + 1, + le16_to_cpu(new_de->key_size), ctx, &diff, &e, + fnd); + if (err) + goto out; + + if (!diff) { + err = -EEXIST; + goto out; + } + } + + if (!fnd->level) { + /* The root is also a leaf, so we'll insert the new entry into it. */ + err = indx_insert_into_root(indx, ni, new_de, fnd->root_de, ctx, + fnd); + if (err) + goto out; + } else { + /* found a leaf buffer, so we'll insert the new entry into it.*/ + err = indx_insert_into_buffer(indx, ni, root, new_de, ctx, + fnd->level - 1, fnd); + if (err) + goto out; + } + +out: + indx->changed = true; + fnd_put(fnd_a); +out1: + + return err; +} + +/* + * indx_find_buffer + * + * locates a buffer the tree. + */ +static struct indx_node *indx_find_buffer(struct ntfs_index *indx, + struct ntfs_inode *ni, + const struct INDEX_ROOT *root, + __le64 vbn, struct indx_node *n) +{ + int err; + const struct NTFS_DE *e; + struct indx_node *r; + const struct INDEX_HDR *hdr = n ? &n->index->ihdr : &root->ihdr; + + /* Step 1: Scan one level */ + for (e = hdr_first_de(hdr);; e = hdr_next_de(hdr, e)) { + if (!e) + return ERR_PTR(-EINVAL); + + if (de_has_vcn(e) && vbn == de_get_vbn_le(e)) + return n; + + if (de_is_last(e)) + break; + } + + /* Step2: Do recursion */ + e = Add2Ptr(hdr, le32_to_cpu(hdr->de_off)); + for (;;) { + if (de_has_vcn_ex(e)) { + err = indx_read(indx, ni, de_get_vbn(e), &n); + if (err) + return ERR_PTR(err); + + r = indx_find_buffer(indx, ni, root, vbn, n); + if (r) + return r; + } + + if (de_is_last(e)) + break; + + e = Add2Ptr(e, le16_to_cpu(e->size)); + } + + return NULL; +} + +/* + * indx_shrink + * + * deallocates unused tail indexes + */ +static int indx_shrink(struct ntfs_index *indx, struct ntfs_inode *ni, + size_t bit) +{ + int err = 0; + u64 bpb, new_alloc; + size_t nbits; + struct ATTRIB *b; + struct ATTR_LIST_ENTRY *le = NULL; + const struct INDEX_NAMES *in = &s_index_names[indx->type]; + + b = ni_find_attr(ni, NULL, &le, ATTR_BITMAP, in->name, in->name_len, + NULL, NULL); + + if (!b) + return -ENOENT; + + if (!b->non_res) { + unsigned long pos; + const unsigned long *bm = resident_data(b); + + nbits = le32_to_cpu(b->res.data_size) * 8; + + if (bit >= nbits) + return 0; + + pos = find_next_bit(bm, nbits, bit); + if (pos < nbits) + return 0; + } else { + size_t used = MINUS_ONE_T; + + nbits = le64_to_cpu(b->nres.data_size) * 8; + + if (bit >= nbits) + return 0; + + err = scan_nres_bitmap(ni->mi.sbi, b, &indx->bitmap_run, bit, + &scan_for_used, &used); + if (err) + return err; + + if (used != MINUS_ONE_T) + return 0; + } + + new_alloc = (u64)bit << indx->index_bits; + + err = attr_set_size(ni, ATTR_ALLOC, in->name, in->name_len, + &indx->alloc_run, new_alloc, &new_alloc, false, + NULL); + if (err) + return err; + + if (in->name == I30_NAME) + ni->vfs_inode.i_size = new_alloc; + + bpb = bitmap_size(bit); + if (bpb * 8 == nbits) + return 0; + + err = attr_set_size(ni, ATTR_BITMAP, in->name, in->name_len, + &indx->bitmap_run, bpb, &bpb, false, NULL); + + return err; +} + +static int indx_free_children(struct ntfs_index *indx, struct ntfs_inode *ni, + const struct NTFS_DE *e, bool trim) +{ + int err; + struct indx_node *n; + struct INDEX_HDR *hdr; + CLST vbn = de_get_vbn(e); + size_t i; + + err = indx_read(indx, ni, vbn, &n); + if (err) + return err; + + hdr = &n->index->ihdr; + /* First, recurse into the children, if any.*/ + if (hdr_has_subnode(hdr)) { + for (e = hdr_first_de(hdr); e; e = hdr_next_de(hdr, e)) { + indx_free_children(indx, ni, e, false); + if (de_is_last(e)) + break; + } + } + + put_indx_node(n); + + i = vbn >> indx->idx2vbn_bits; + /* We've gotten rid of the children; add this buffer to the free list. */ + indx_mark_free(indx, ni, i); + + if (!trim) + return 0; + + /* + * If there are no used indexes after current free index + * then we can truncate allocation and bitmap + * Use bitmap to estimate the case + */ + indx_shrink(indx, ni, i + 1); + return 0; +} + +/* + * indx_get_entry_to_replace + * + * finds a replacement entry for a deleted entry + * always returns a node entry: + * NTFS_IE_HAS_SUBNODES is set the flags and the size includes the sub_vcn + */ +static int indx_get_entry_to_replace(struct ntfs_index *indx, + struct ntfs_inode *ni, + const struct NTFS_DE *de_next, + struct NTFS_DE **de_to_replace, + struct ntfs_fnd *fnd) +{ + int err; + int level = -1; + CLST vbn; + struct NTFS_DE *e, *te, *re; + struct indx_node *n; + struct INDEX_BUFFER *ib; + + *de_to_replace = NULL; + + /* Find first leaf entry down from de_next */ + vbn = de_get_vbn(de_next); + for (;;) { + n = NULL; + err = indx_read(indx, ni, vbn, &n); + if (err) + goto out; + + e = hdr_first_de(&n->index->ihdr); + fnd_push(fnd, n, e); + + if (!de_is_last(e)) { + /* + * This buffer is non-empty, so its first entry could be used as the + * replacement entry. + */ + level = fnd->level - 1; + } + + if (!de_has_vcn(e)) + break; + + /* This buffer is a node. Continue to go down */ + vbn = de_get_vbn(e); + } + + if (level == -1) + goto out; + + n = fnd->nodes[level]; + te = hdr_first_de(&n->index->ihdr); + /* Copy the candidate entry into the replacement entry buffer. */ + re = ntfs_alloc(le16_to_cpu(te->size) + sizeof(u64), 0); + if (!re) { + err = -ENOMEM; + goto out; + } + + *de_to_replace = re; + memcpy(re, te, le16_to_cpu(te->size)); + + if (!de_has_vcn(re)) { + /* + * The replacement entry we found doesn't have a sub_vcn. increase its size + * to hold one. + */ + le16_add_cpu(&re->size, sizeof(u64)); + re->flags |= NTFS_IE_HAS_SUBNODES; + } else { + /* + * The replacement entry we found was a node entry, which means that all + * its child buffers are empty. Return them to the free pool. + */ + indx_free_children(indx, ni, te, true); + } + + /* + * Expunge the replacement entry from its former location, + * and then write that buffer. + */ + ib = n->index; + e = hdr_delete_de(&ib->ihdr, te); + + fnd->de[level] = e; + indx_write(indx, ni, n, 0); + + /* Check to see if this action created an empty leaf. */ + if (ib_is_leaf(ib) && ib_is_empty(ib)) + return 0; + +out: + fnd_clear(fnd); + + return err; +} + +/* + * indx_delete_entry + * + * deletes an entry from the index. + */ +int indx_delete_entry(struct ntfs_index *indx, struct ntfs_inode *ni, + const void *key, u32 key_len, const void *ctx) +{ + int err, diff; + struct INDEX_ROOT *root; + struct INDEX_HDR *hdr; + struct ntfs_fnd *fnd, *fnd2; + struct INDEX_BUFFER *ib; + struct NTFS_DE *e, *re, *next, *prev, *me; + struct indx_node *n, *n2d = NULL; + __le64 sub_vbn; + int level, level2; + struct ATTRIB *attr; + struct mft_inode *mi; + u32 e_size, root_size, new_root_size; + size_t trim_bit; + const struct INDEX_NAMES *in; + + fnd = fnd_get(indx); + if (!fnd) { + err = -ENOMEM; + goto out2; + } + + fnd2 = fnd_get(NULL); + if (!fnd2) { + err = -ENOMEM; + goto out1; + } + + root = indx_get_root(indx, ni, &attr, &mi); + if (!root) { + err = -EINVAL; + goto out; + } + + /* Locate the entry to remove. */ + err = indx_find(indx, ni, root, key, key_len, ctx, &diff, &e, fnd); + if (err) + goto out; + + if (!e || diff) { + err = -ENOENT; + goto out; + } + + level = fnd->level; + + if (level) { + n = fnd->nodes[level - 1]; + e = fnd->de[level - 1]; + ib = n->index; + hdr = &ib->ihdr; + } else { + hdr = &root->ihdr; + e = fnd->root_de; + n = NULL; + } + + e_size = le16_to_cpu(e->size); + + if (!de_has_vcn_ex(e)) { + /* The entry to delete is a leaf, so we can just rip it out */ + hdr_delete_de(hdr, e); + + if (!level) { + hdr->total = hdr->used; + + /* Shrink resident root attribute */ + mi_resize_attr(mi, attr, 0 - e_size); + goto out; + } + + indx_write(indx, ni, n, 0); + + /* + * Check to see if removing that entry made + * the leaf empty. + */ + if (ib_is_leaf(ib) && ib_is_empty(ib)) { + fnd_pop(fnd); + fnd_push(fnd2, n, e); + } + } else { + /* + * The entry we wish to delete is a node buffer, so we + * have to find a replacement for it. + */ + next = de_get_next(e); + + err = indx_get_entry_to_replace(indx, ni, next, &re, fnd2); + if (err) + goto out; + + if (re) { + de_set_vbn_le(re, de_get_vbn_le(e)); + hdr_delete_de(hdr, e); + + err = level ? indx_insert_into_buffer(indx, ni, root, + re, ctx, + fnd->level - 1, + fnd) : + indx_insert_into_root(indx, ni, re, e, + ctx, fnd); + ntfs_free(re); + + if (err) + goto out; + } else { + /* + * There is no replacement for the current entry. + * This means that the subtree rooted at its node is empty, + * and can be deleted, which turn means that the node can + * just inherit the deleted entry sub_vcn + */ + indx_free_children(indx, ni, next, true); + + de_set_vbn_le(next, de_get_vbn_le(e)); + hdr_delete_de(hdr, e); + if (level) { + indx_write(indx, ni, n, 0); + } else { + hdr->total = hdr->used; + + /* Shrink resident root attribute */ + mi_resize_attr(mi, attr, 0 - e_size); + } + } + } + + /* Delete a branch of tree */ + if (!fnd2 || !fnd2->level) + goto out; + + /* Reinit root 'cause it can be changed */ + root = indx_get_root(indx, ni, &attr, &mi); + if (!root) { + err = -EINVAL; + goto out; + } + + n2d = NULL; + sub_vbn = fnd2->nodes[0]->index->vbn; + level2 = 0; + level = fnd->level; + + hdr = level ? &fnd->nodes[level - 1]->index->ihdr : &root->ihdr; + + /* Scan current level */ + for (e = hdr_first_de(hdr);; e = hdr_next_de(hdr, e)) { + if (!e) { + err = -EINVAL; + goto out; + } + + if (de_has_vcn(e) && sub_vbn == de_get_vbn_le(e)) + break; + + if (de_is_last(e)) { + e = NULL; + break; + } + } + + if (!e) { + /* Do slow search from root */ + struct indx_node *in; + + fnd_clear(fnd); + + in = indx_find_buffer(indx, ni, root, sub_vbn, NULL); + if (IS_ERR(in)) { + err = PTR_ERR(in); + goto out; + } + + if (in) + fnd_push(fnd, in, NULL); + } + + /* Merge fnd2 -> fnd */ + for (level = 0; level < fnd2->level; level++) { + fnd_push(fnd, fnd2->nodes[level], fnd2->de[level]); + fnd2->nodes[level] = NULL; + } + fnd2->level = 0; + + hdr = NULL; + for (level = fnd->level; level; level--) { + struct indx_node *in = fnd->nodes[level - 1]; + + ib = in->index; + if (ib_is_empty(ib)) { + sub_vbn = ib->vbn; + } else { + hdr = &ib->ihdr; + n2d = in; + level2 = level; + break; + } + } + + if (!hdr) + hdr = &root->ihdr; + + e = hdr_first_de(hdr); + if (!e) { + err = -EINVAL; + goto out; + } + + if (hdr != &root->ihdr || !de_is_last(e)) { + prev = NULL; + while (!de_is_last(e)) { + if (de_has_vcn(e) && sub_vbn == de_get_vbn_le(e)) + break; + prev = e; + e = hdr_next_de(hdr, e); + if (!e) { + err = -EINVAL; + goto out; + } + } + + if (sub_vbn != de_get_vbn_le(e)) { + /* + * Didn't find the parent entry, although this buffer is the parent trail. + * Something is corrupt. + */ + err = -EINVAL; + goto out; + } + + if (de_is_last(e)) { + /* + * Since we can't remove the end entry, we'll remove its + * predecessor instead. This means we have to transfer the + * predecessor's sub_vcn to the end entry. + * Note: that this index block is not empty, so the + * predecessor must exist + */ + if (!prev) { + err = -EINVAL; + goto out; + } + + if (de_has_vcn(prev)) { + de_set_vbn_le(e, de_get_vbn_le(prev)); + } else if (de_has_vcn(e)) { + le16_sub_cpu(&e->size, sizeof(u64)); + e->flags &= ~NTFS_IE_HAS_SUBNODES; + le32_sub_cpu(&hdr->used, sizeof(u64)); + } + e = prev; + } + + /* + * Copy the current entry into a temporary buffer (stripping off its + * down-pointer, if any) and delete it from the current buffer or root, + * as appropriate. + */ + e_size = le16_to_cpu(e->size); + me = ntfs_memdup(e, e_size); + if (!me) { + err = -ENOMEM; + goto out; + } + + if (de_has_vcn(me)) { + me->flags &= ~NTFS_IE_HAS_SUBNODES; + le16_sub_cpu(&me->size, sizeof(u64)); + } + + hdr_delete_de(hdr, e); + + if (hdr == &root->ihdr) { + level = 0; + hdr->total = hdr->used; + + /* Shrink resident root attribute */ + mi_resize_attr(mi, attr, 0 - e_size); + } else { + indx_write(indx, ni, n2d, 0); + level = level2; + } + + /* Mark unused buffers as free */ + trim_bit = -1; + for (; level < fnd->level; level++) { + ib = fnd->nodes[level]->index; + if (ib_is_empty(ib)) { + size_t k = le64_to_cpu(ib->vbn) >> + indx->idx2vbn_bits; + + indx_mark_free(indx, ni, k); + if (k < trim_bit) + trim_bit = k; + } + } + + fnd_clear(fnd); + /*fnd->root_de = NULL;*/ + + /* + * Re-insert the entry into the tree. + * Find the spot the tree where we want to insert the new entry. + */ + err = indx_insert_entry(indx, ni, me, ctx, fnd); + ntfs_free(me); + if (err) + goto out; + + if (trim_bit != -1) + indx_shrink(indx, ni, trim_bit); + } else { + /* + * This tree needs to be collapsed down to an empty root. + * Recreate the index root as an empty leaf and free all the bits the + * index allocation bitmap. + */ + fnd_clear(fnd); + fnd_clear(fnd2); + + in = &s_index_names[indx->type]; + + err = attr_set_size(ni, ATTR_ALLOC, in->name, in->name_len, + &indx->alloc_run, 0, NULL, false, NULL); + err = ni_remove_attr(ni, ATTR_ALLOC, in->name, in->name_len, + false, NULL); + run_close(&indx->alloc_run); + + err = attr_set_size(ni, ATTR_BITMAP, in->name, in->name_len, + &indx->bitmap_run, 0, NULL, false, NULL); + err = ni_remove_attr(ni, ATTR_BITMAP, in->name, in->name_len, + false, NULL); + run_close(&indx->bitmap_run); + + root = indx_get_root(indx, ni, &attr, &mi); + if (!root) { + err = -EINVAL; + goto out; + } + + root_size = le32_to_cpu(attr->res.data_size); + new_root_size = + sizeof(struct INDEX_ROOT) + sizeof(struct NTFS_DE); + + if (new_root_size != root_size && + !mi_resize_attr(mi, attr, new_root_size - root_size)) { + err = -EINVAL; + goto out; + } + + /* Fill first entry */ + e = (struct NTFS_DE *)(root + 1); + e->ref.low = 0; + e->ref.high = 0; + e->ref.seq = 0; + e->size = cpu_to_le16(sizeof(struct NTFS_DE)); + e->flags = NTFS_IE_LAST; // 0x02 + e->key_size = 0; + e->res = 0; + + hdr = &root->ihdr; + hdr->flags = 0; + hdr->used = hdr->total = cpu_to_le32( + new_root_size - offsetof(struct INDEX_ROOT, ihdr)); + mi->dirty = true; + + if (in->name == I30_NAME) + ni->vfs_inode.i_size = 0; + } + +out: + fnd_put(fnd2); +out1: + indx->changed = true; + fnd_put(fnd); + +out2: + return err; +} + +int indx_update_dup(struct ntfs_inode *ni, struct ntfs_sb_info *sbi, + const struct ATTR_FILE_NAME *fname, + const struct NTFS_DUP_INFO *dup, int sync) +{ + int err, diff; + struct NTFS_DE *e = NULL; + struct ATTR_FILE_NAME *e_fname; + struct ntfs_fnd *fnd; + struct INDEX_ROOT *root; + struct mft_inode *mi; + struct ntfs_index *indx = &ni->dir; + + fnd = fnd_get(indx); + if (!fnd) { + err = -ENOMEM; + goto out1; + } + + root = indx_get_root(indx, ni, NULL, &mi); + if (!root) { + err = -EINVAL; + goto out; + } + + /* Find entries tree and on disk */ + err = indx_find(indx, ni, root, fname, fname_full_size(fname), sbi, + &diff, &e, fnd); + if (err) + goto out; + + if (!e) { + err = -EINVAL; + goto out; + } + + if (diff) { + err = -EINVAL; + goto out; + } + + e_fname = (struct ATTR_FILE_NAME *)(e + 1); + + if (!memcmp(&e_fname->dup, dup, sizeof(*dup))) { + /* nothing to update in index! Try to avoid this call */ + goto out; + } + + memcpy(&e_fname->dup, dup, sizeof(*dup)); + + if (fnd->level) { + err = indx_write(indx, ni, fnd->nodes[fnd->level - 1], sync); + } else if (sync) { + mi->dirty = true; + err = mi_write(mi, 1); + } else { + mi->dirty = true; + mark_inode_dirty(&ni->vfs_inode); + } + +out: + fnd_put(fnd); + +out1: + return err; +} diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c new file mode 100644 index 000000000000..48f978032e4e --- /dev/null +++ b/fs/ntfs3/inode.c @@ -0,0 +1,1956 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * linux/fs/ntfs3/inode.c + * + * Copyright (C) 2019-2020 Paragon Software GmbH, All rights reserved. + * + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "debug.h" +#include "ntfs.h" +#include "ntfs_fs.h" + +/* + * ntfs_read_mft + * + * reads record and parses MFT + */ +static struct inode *ntfs_read_mft(struct inode *inode, + const struct cpu_str *name, + const struct MFT_REF *ref) +{ + int err = 0; + struct ntfs_inode *ni = ntfs_i(inode); + struct super_block *sb = inode->i_sb; + struct ntfs_sb_info *sbi = sb->s_fs_info; + mode_t mode = 0; + struct ATTR_STD_INFO5 *std5 = NULL; + struct ATTR_LIST_ENTRY *le; + struct ATTRIB *attr; + bool is_match = false; + bool is_root = false; + bool is_dir; + unsigned long ino = inode->i_ino; + u32 rp_fa = 0, asize, t32; + u16 roff, rsize, names = 0; + const struct ATTR_FILE_NAME *fname = NULL; + const struct INDEX_ROOT *root; + struct REPARSE_DATA_BUFFER rp; // 0x18 bytes + u64 t64; + struct MFT_REC *rec; + struct runs_tree *run; + + inode->i_op = NULL; + + err = mi_init(&ni->mi, sbi, ino); + if (err) + goto out; + + if (!sbi->mft.ni && ino == MFT_REC_MFT && !sb->s_root) { + t64 = sbi->mft.lbo >> sbi->cluster_bits; + t32 = bytes_to_cluster(sbi, MFT_REC_VOL * sbi->record_size); + sbi->mft.ni = ni; + init_rwsem(&ni->file.run_lock); + + if (!run_add_entry(&ni->file.run, 0, t64, t32)) { + err = -ENOMEM; + goto out; + } + } + + err = mi_read(&ni->mi, ino == MFT_REC_MFT); + + if (err) + goto out; + + rec = ni->mi.mrec; + + if (sbi->flags & NTFS_FLAGS_LOG_REPLAYING) { + ; + } else if (ref->seq != rec->seq) { + err = -EINVAL; + ntfs_err(sb, "MFT: r=%lx, expect seq=%x instead of %x!", ino, + le16_to_cpu(ref->seq), le16_to_cpu(rec->seq)); + goto out; + } else if (!is_rec_inuse(rec)) { + err = -EINVAL; + ntfs_err(sb, "Inode r=%x is not in use!", (u32)ino); + goto out; + } + + if (le32_to_cpu(rec->total) != sbi->record_size) { + // bad inode? + err = -EINVAL; + goto out; + } + + if (!is_rec_base(rec)) + goto Ok; + + /* record should contain $I30 root */ + is_dir = rec->flags & RECORD_FLAG_DIR; + + inode->i_generation = le16_to_cpu(rec->seq); + + /* Enumerate all struct Attributes MFT */ + le = NULL; + attr = NULL; + + /* + * to reduce tab pressure use goto instead of + * while( (attr = ni_enum_attr_ex(ni, attr, &le) )) + */ +next_attr: + run = NULL; + err = -EINVAL; + attr = ni_enum_attr_ex(ni, attr, &le); + if (!attr) + goto end_enum; + + if (le && le->vcn) { + /* This is non primary attribute segment. Ignore if not MFT */ + if (ino != MFT_REC_MFT || attr->type != ATTR_DATA) + goto next_attr; + + run = &ni->file.run; + asize = le32_to_cpu(attr->size); + goto attr_unpack_run; + } + + roff = attr->non_res ? 0 : le16_to_cpu(attr->res.data_off); + rsize = attr->non_res ? 0 : le32_to_cpu(attr->res.data_size); + asize = le32_to_cpu(attr->size); + + switch (attr->type) { + case ATTR_STD: + if (attr->non_res || + asize < sizeof(struct ATTR_STD_INFO) + roff || + rsize < sizeof(struct ATTR_STD_INFO)) + goto out; + + if (std5) + goto next_attr; + + std5 = Add2Ptr(attr, roff); + +#ifdef STATX_BTIME + nt2kernel(std5->cr_time, &ni->i_crtime); +#endif + nt2kernel(std5->a_time, &inode->i_atime); + nt2kernel(std5->c_time, &inode->i_ctime); + nt2kernel(std5->m_time, &inode->i_mtime); + + ni->std_fa = std5->fa; + + if (asize >= sizeof(struct ATTR_STD_INFO5) + roff && + rsize >= sizeof(struct ATTR_STD_INFO5)) + ni->std_security_id = std5->security_id; + goto next_attr; + + case ATTR_LIST: + if (attr->name_len || le || ino == MFT_REC_LOG) + goto out; + + err = ntfs_load_attr_list(ni, attr); + if (err) + goto out; + + le = NULL; + attr = NULL; + goto next_attr; + + case ATTR_NAME: + if (attr->non_res || asize < SIZEOF_ATTRIBUTE_FILENAME + roff || + rsize < SIZEOF_ATTRIBUTE_FILENAME) + goto out; + + fname = Add2Ptr(attr, roff); + if (fname->type == FILE_NAME_DOS) + goto next_attr; + + names += 1; + if (name && name->len == fname->name_len && + !ntfs_cmp_names_cpu(name, (struct le_str *)&fname->name_len, + NULL)) + is_match = true; + + goto next_attr; + + case ATTR_DATA: + if (is_dir) { + /* ignore data attribute in dir record */ + goto next_attr; + } + + if (ino == MFT_REC_BADCLUST && !attr->non_res) + goto next_attr; + + if (attr->name_len && + ((ino != MFT_REC_BADCLUST || !attr->non_res || + attr->name_len != ARRAY_SIZE(BAD_NAME) || + memcmp(attr_name(attr), BAD_NAME, sizeof(BAD_NAME))) && + (ino != MFT_REC_SECURE || !attr->non_res || + attr->name_len != ARRAY_SIZE(SDS_NAME) || + memcmp(attr_name(attr), SDS_NAME, sizeof(SDS_NAME))))) { + /* file contains stream attribute. ignore it */ + goto next_attr; + } + + if (is_attr_sparsed(attr)) + ni->std_fa |= FILE_ATTRIBUTE_SPARSE_FILE; + else + ni->std_fa &= ~FILE_ATTRIBUTE_SPARSE_FILE; + + if (is_attr_compressed(attr)) + ni->std_fa |= FILE_ATTRIBUTE_COMPRESSED; + else + ni->std_fa &= ~FILE_ATTRIBUTE_COMPRESSED; + + if (is_attr_encrypted(attr)) + ni->std_fa |= FILE_ATTRIBUTE_ENCRYPTED; + else + ni->std_fa &= ~FILE_ATTRIBUTE_ENCRYPTED; + + if (!attr->non_res) { + ni->i_valid = inode->i_size = rsize; + inode_set_bytes(inode, rsize); + t32 = asize; + } else { + t32 = le16_to_cpu(attr->nres.run_off); + } + + mode = S_IFREG | (0777 & sbi->options.fs_fmask_inv); + + if (!attr->non_res) { + ni->ni_flags |= NI_FLAG_RESIDENT; + goto next_attr; + } + + inode_set_bytes(inode, attr_ondisk_size(attr)); + + ni->i_valid = le64_to_cpu(attr->nres.valid_size); + inode->i_size = le64_to_cpu(attr->nres.data_size); + if (!attr->nres.alloc_size) + goto next_attr; + + run = ino == MFT_REC_BITMAP ? &sbi->used.bitmap.run : + &ni->file.run; + break; + + case ATTR_ROOT: + if (attr->non_res) + goto out; + + root = Add2Ptr(attr, roff); + is_root = true; + + if (attr->name_len != ARRAY_SIZE(I30_NAME) || + memcmp(attr_name(attr), I30_NAME, sizeof(I30_NAME))) + goto next_attr; + + if (root->type != ATTR_NAME || + root->rule != NTFS_COLLATION_TYPE_FILENAME) + goto out; + + if (!is_dir) + goto next_attr; + + ni->ni_flags |= NI_FLAG_DIR; + + err = indx_init(&ni->dir, sbi, attr, INDEX_MUTEX_I30); + if (err) + goto out; + + mode = sb->s_root ? + (S_IFDIR | (0777 & sbi->options.fs_dmask_inv)) : + (S_IFDIR | 0777); + goto next_attr; + + case ATTR_ALLOC: + if (!is_root || attr->name_len != ARRAY_SIZE(I30_NAME) || + memcmp(attr_name(attr), I30_NAME, sizeof(I30_NAME))) + goto next_attr; + + inode->i_size = le64_to_cpu(attr->nres.data_size); + ni->i_valid = le64_to_cpu(attr->nres.valid_size); + inode_set_bytes(inode, le64_to_cpu(attr->nres.alloc_size)); + + run = &ni->dir.alloc_run; + break; + + case ATTR_BITMAP: + if (ino == MFT_REC_MFT) { + if (!attr->non_res) + goto out; +#ifndef NTFS3_64BIT_CLUSTER + /* 0x20000000 = 2^32 / 8 */ + if (le64_to_cpu(attr->nres.alloc_size) >= 0x20000000) + goto out; +#endif + run = &sbi->mft.bitmap.run; + break; + } else if (is_dir && attr->name_len == ARRAY_SIZE(I30_NAME) && + !memcmp(attr_name(attr), I30_NAME, + sizeof(I30_NAME)) && + attr->non_res) { + run = &ni->dir.bitmap_run; + break; + } + goto next_attr; + + case ATTR_REPARSE: + if (attr->name_len) + goto next_attr; + + rp_fa = ni_parse_reparse(ni, attr, &rp); + switch (rp_fa) { + case REPARSE_LINK: + if (!attr->non_res) { + inode->i_size = rsize; + inode_set_bytes(inode, rsize); + t32 = asize; + } else { + inode->i_size = + le64_to_cpu(attr->nres.data_size); + t32 = le16_to_cpu(attr->nres.run_off); + } + + /* Looks like normal symlink */ + ni->i_valid = inode->i_size; + + /* Clear directory bit */ + if (ni->ni_flags & NI_FLAG_DIR) { + indx_clear(&ni->dir); + memset(&ni->dir, 0, sizeof(ni->dir)); + ni->ni_flags &= ~NI_FLAG_DIR; + } else { + run_close(&ni->file.run); + } + mode = S_IFLNK | 0777; + is_dir = false; + if (attr->non_res) { + run = &ni->file.run; + goto attr_unpack_run; // double break + } + break; + + case REPARSE_COMPRESSED: + break; + + case REPARSE_DEDUPLICATED: + break; + } + goto next_attr; + + case ATTR_EA_INFO: + if (!attr->name_len && + resident_data_ex(attr, sizeof(struct EA_INFO))) + ni->ni_flags |= NI_FLAG_EA; + goto next_attr; + + default: + goto next_attr; + } + +attr_unpack_run: + roff = le16_to_cpu(attr->nres.run_off); + + err = run_unpack_ex(run, sbi, ino, le64_to_cpu(attr->nres.svcn), + le64_to_cpu(attr->nres.evcn), Add2Ptr(attr, roff), + asize - roff); + if (err < 0) + goto out; + err = 0; + goto next_attr; + +end_enum: + + if (!std5) + goto out; + + if (!is_match && name) { + /* reuse rec as buffer for ascii name */ + err = -ENOENT; + goto out; + } + + if (std5->fa & FILE_ATTRIBUTE_READONLY) + mode &= ~0222; + + /* Setup 'uid' and 'gid' */ + inode->i_uid = sbi->options.fs_uid; + inode->i_gid = sbi->options.fs_gid; + + if (!names) { + err = -EINVAL; + goto out; + } + + if (S_ISDIR(mode)) { + ni->std_fa |= FILE_ATTRIBUTE_DIRECTORY; + + /* + * dot and dot-dot should be included in count but was not + * included in enumeration. + * Usually a hard links to directories are disabled + */ + set_nlink(inode, 1); + inode->i_op = &ntfs_dir_inode_operations; + inode->i_fop = &ntfs_dir_operations; + ni->i_valid = 0; + } else if (S_ISLNK(mode)) { + ni->std_fa &= ~FILE_ATTRIBUTE_DIRECTORY; + inode->i_op = &ntfs_link_inode_operations; + inode->i_fop = NULL; + inode_nohighmem(inode); // ?? + set_nlink(inode, names); + } else if (S_ISREG(mode)) { + ni->std_fa &= ~FILE_ATTRIBUTE_DIRECTORY; + + set_nlink(inode, names); + + inode->i_op = &ntfs_file_inode_operations; + inode->i_fop = &ntfs_file_operations; + inode->i_mapping->a_ops = + is_compressed(ni) ? &ntfs_aops_cmpr : &ntfs_aops; + + if (ino != MFT_REC_MFT) + init_rwsem(&ni->file.run_lock); + } else if (fname && fname->home.low == cpu_to_le32(MFT_REC_EXTEND) && + fname->home.seq == cpu_to_le16(MFT_REC_EXTEND)) { + /* Records in $Extend are not a files or general directories */ + } else { + err = -EINVAL; + goto out; + } + + if ((sbi->options.sys_immutable && + (std5->fa & FILE_ATTRIBUTE_SYSTEM)) && + !S_ISFIFO(mode) && !S_ISSOCK(mode) && !S_ISLNK(mode)) { + inode->i_flags |= S_IMMUTABLE; + } else { + inode->i_flags &= ~S_IMMUTABLE; + } + + inode->i_mode = mode; + if (!(ni->ni_flags & NI_FLAG_EA)) { + /* if no xattr then no security (stored in xattr) */ + inode->i_flags |= S_NOSEC; + } + +Ok: + if (ino == MFT_REC_MFT && !sb->s_root) + sbi->mft.ni = NULL; + + unlock_new_inode(inode); + + return inode; + +out: + if (ino == MFT_REC_MFT && !sb->s_root) + sbi->mft.ni = NULL; + + iget_failed(inode); + + return ERR_PTR(err); +} + +/* returns 1 if match */ +static int ntfs_test_inode(struct inode *inode, const struct MFT_REF *ref) +{ + return ino_get(ref) == inode->i_ino; +} + +static int ntfs_set_inode(struct inode *inode, const struct MFT_REF *ref) +{ + inode->i_ino = ino_get(ref); + + return 0; +} + +struct inode *ntfs_iget5(struct super_block *sb, const struct MFT_REF *ref, + const struct cpu_str *name) +{ + struct inode *inode; + + inode = iget5_locked(sb, ino_get(ref), + (int (*)(struct inode *, void *))ntfs_test_inode, + (int (*)(struct inode *, void *))ntfs_set_inode, + (void *)ref); + if (unlikely(!inode)) + return ERR_PTR(-ENOMEM); + + /* If this is a freshly allocated inode, need to read it now. */ + if (inode->i_state & I_NEW) + inode = ntfs_read_mft(inode, name, ref); + else if (ref->seq != ntfs_i(inode)->mi.mrec->seq) + make_bad_inode(inode); + + return inode; +} + +enum get_block_ctx { + GET_BLOCK_GENERAL = 0, + GET_BLOCK_WRITE_BEGIN = 1, + GET_BLOCK_DIRECT_IO_R = 2, + GET_BLOCK_DIRECT_IO_W = 3, + GET_BLOCK_BMAP = 4, +}; + +static noinline int ntfs_get_block_vbo(struct inode *inode, u64 vbo, + struct buffer_head *bh, int create, + enum get_block_ctx ctx) +{ + struct super_block *sb = inode->i_sb; + struct ntfs_sb_info *sbi = sb->s_fs_info; + struct ntfs_inode *ni = ntfs_i(inode); + u64 bytes, lbo; + u32 off; + int err; + CLST vcn, lcn, len; + u8 cluster_bits = sbi->cluster_bits; + bool new; + + /*clear previous state*/ + clear_buffer_new(bh); + clear_buffer_uptodate(bh); + + /* direct write uses 'create=0'*/ + if (!create && vbo >= ni->i_valid) + return 0; + + if (vbo >= inode->i_size) + return 0; + + vcn = vbo >> cluster_bits; + off = vbo & sbi->cluster_mask; + new = false; + + err = attr_data_get_block(ni, vcn, 1, &lcn, &len, create ? &new : NULL); + if (err) + goto out; + + if (!len) + return 0; + + bytes = ((u64)len << cluster_bits) - off; + + if (lcn == SPARSE_LCN) { + if (!create) { + if (bh->b_size > bytes) + bh->b_size = bytes; + + return 0; + } + WARN_ON(1); + } + + WARN_ON(lcn == RESIDENT_LCN); + + if (new) { + u32 allocated = len * sbi->cluster_size; + + set_buffer_new(bh); + if (allocated > sb->s_blocksize) + ntfs_sparse_cluster(inode, bh->b_page, + (loff_t)vcn << sbi->cluster_bits, + allocated); + } + + lbo = ((u64)lcn << cluster_bits) + off; + + set_buffer_mapped(bh); + bh->b_bdev = sb->s_bdev; + bh->b_blocknr = lbo >> sb->s_blocksize_bits; + + if (ctx == GET_BLOCK_DIRECT_IO_W) { + /*ntfs_direct_IO will update ni->i_valid */ + if (vbo >= ni->i_valid) + set_buffer_new(bh); + } else if (create && ctx == GET_BLOCK_WRITE_BEGIN && + vbo + bh->b_size > ni->i_valid) { + u32 voff = ni->i_valid > vbo ? (ni->i_valid - vbo) : 0; + struct page *page = bh->b_page; + + off = bh_offset(bh); + zero_user_segment(page, off + voff, off + bh->b_size); + set_buffer_uptodate(bh); + ni->i_valid = vbo + bh->b_size; + + /* ntfs_write_end will update ni->i_valid*/ + } else if (create) { + /*normal write*/ + if (vbo >= ni->i_valid) { + set_buffer_new(bh); + if (bytes > bh->b_size) + bytes = bh->b_size; + ni->i_valid = vbo + bytes; + mark_inode_dirty(inode); + } + } else if (vbo >= ni->i_valid) { + /* read out of valid data*/ + /* should never be here 'cause already checked */ + clear_buffer_mapped(bh); + } else if (vbo + bytes <= ni->i_valid) { + /* normal read */ + } else { + /* here: vbo <= ni->i_valid && ni->i_valid < vbo + bytes */ + u64 valid_up = + (ni->i_valid + PAGE_SIZE - 1) & ~(u64)(PAGE_SIZE - 1); + + bytes = valid_up - vbo; + if (bytes < sb->s_blocksize) + bytes = sb->s_blocksize; + } + + if (bh->b_size > bytes) + bh->b_size = bytes; + +#ifndef __LP64__ + if (ctx == GET_BLOCK_DIRECT_IO_W || ctx == GET_BLOCK_DIRECT_IO_R) { + static_assert(sizeof(size_t) < sizeof(loff_t)); + if (bytes > 0x40000000u) + bh->b_size = 0x40000000u; + } +#endif + + return 0; + +out: + return err; +} + +/*ntfs_readpage*/ +/*ntfs_readpages*/ +/*ntfs_writepage*/ +/*ntfs_writepages*/ +/*ntfs_block_truncate_page*/ +int ntfs_get_block(struct inode *inode, sector_t vbn, + struct buffer_head *bh_result, int create) +{ + return ntfs_get_block_vbo(inode, (u64)vbn << inode->i_blkbits, + bh_result, create, GET_BLOCK_GENERAL); +} + +/*ntfs_bmap*/ +static int ntfs_get_block_bmap(struct inode *inode, sector_t vsn, + struct buffer_head *bh_result, int create) +{ + return ntfs_get_block_vbo(inode, + (u64)vsn << inode->i_sb->s_blocksize_bits, + bh_result, create, GET_BLOCK_BMAP); +} + +static sector_t ntfs_bmap(struct address_space *mapping, sector_t block) +{ + return generic_block_bmap(mapping, block, ntfs_get_block_bmap); +} + +int ntfs_readpage(struct file *file, struct page *page) +{ + int err; + struct address_space *mapping = page->mapping; + struct inode *inode = mapping->host; + struct ntfs_inode *ni = ntfs_i(inode); + u64 vbo = (u64)page->index << PAGE_SHIFT; + u64 valid; + struct ATTRIB *attr; + const char *data; + u32 data_size; + + if (ni_has_resident_data(ni)) { + ni_lock(ni); + + if (!ni_has_resident_data(ni)) { + ni_unlock(ni); + } else { + attr = ni_find_attr(ni, NULL, NULL, ATTR_DATA, NULL, 0, + NULL, NULL); + if (!attr) { + err = -EINVAL; + ni_unlock(ni); + unlock_page(page); + goto out; + } + + WARN_ON(attr->non_res); + + vbo = page->index << PAGE_SHIFT; + data = resident_data(attr); + data_size = le32_to_cpu(attr->res.data_size); + + if (vbo < data_size) { + void *kaddr = kmap_atomic(page); + + err = data_size - vbo; + if (err > PAGE_SIZE) + err = PAGE_SIZE; + + memcpy(kaddr, data + vbo, err); + flush_dcache_page(page); + kunmap_atomic(kaddr); + zero_user_segment(page, err, PAGE_SIZE); + SetPageUptodate(page); + } else if (!PageUptodate(page)) { + zero_user_segment(page, 0, PAGE_SIZE); + SetPageUptodate(page); + } + + ni_unlock(ni); + unlock_page(page); + return 0; + } + } + + if (is_compressed(ni)) { + if (PageUptodate(page)) { + unlock_page(page); + return 0; + } + + ni_lock(ni); + err = ni_readpage_cmpr(ni, page); + ni_unlock(ni); + return err; + } + + /* normal + sparse files */ + err = mpage_readpage(page, ntfs_get_block); + if (err) + goto out; + + valid = ni->i_valid; + if (vbo < valid && valid < vbo + PAGE_SIZE) { + if (PageLocked(page)) + wait_on_page_bit(page, PG_locked); + if (PageError(page)) { + ntfs_inode_warn(inode, "file garbage at 0x%llx", valid); + goto out; + } + zero_user_segment(page, valid & (PAGE_SIZE - 1), PAGE_SIZE); + } + +out: + return err; +} + +static void ntfs_readahead(struct readahead_control *rac) +{ + struct address_space *mapping = rac->mapping; + struct inode *inode = mapping->host; + struct ntfs_inode *ni = ntfs_i(inode); + u64 valid; + loff_t pos; + + if (ni_has_resident_data(ni)) + return; + + WARN_ON(is_compressed(ni)); + + valid = ni->i_valid; + pos = readahead_pos(rac); + + if (pos <= valid && valid < pos + readahead_length(rac)) + return; + + mpage_readahead(rac, ntfs_get_block); +} + +/*ntfs_direct_IO*/ +static int ntfs_get_block_direct_IO_R(struct inode *inode, sector_t iblock, + struct buffer_head *bh_result, int create) +{ + return ntfs_get_block_vbo(inode, (u64)iblock << inode->i_blkbits, + bh_result, create, GET_BLOCK_DIRECT_IO_R); +} + +static int ntfs_get_block_direct_IO_W(struct inode *inode, sector_t iblock, + struct buffer_head *bh_result, int create) +{ + return ntfs_get_block_vbo(inode, (u64)iblock << inode->i_blkbits, + bh_result, create, GET_BLOCK_DIRECT_IO_W); +} + +static void ntfs_write_failed(struct address_space *mapping, loff_t to) +{ + struct inode *inode = mapping->host; + + if (to > inode->i_size) { + truncate_pagecache(inode, inode->i_size); + ntfs_truncate_blocks(inode, inode->i_size); + } +} + +static ssize_t ntfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) +{ + struct file *file = iocb->ki_filp; + struct address_space *mapping = file->f_mapping; + struct inode *inode = mapping->host; + struct ntfs_inode *ni = ntfs_i(inode); + size_t count = iov_iter_count(iter); + loff_t vbo = iocb->ki_pos; + loff_t end = vbo + count; + int wr = iov_iter_rw(iter) & WRITE; + const struct iovec *iov = iter->iov; + unsigned long nr_segs = iter->nr_segs; + loff_t valid; + ssize_t ret; + + ret = blockdev_direct_IO(iocb, inode, iter, + wr ? ntfs_get_block_direct_IO_W : + ntfs_get_block_direct_IO_R); + valid = ni->i_valid; + if (wr) { + if (ret < 0) + ntfs_write_failed(mapping, end); + if (ret <= 0) + goto out; + + vbo += ret; + if (vbo > valid && !S_ISBLK(inode->i_mode)) { + ni->i_valid = vbo; + mark_inode_dirty(inode); + } + } else if (vbo < valid && valid < end) { + /* fix page */ + unsigned long uaddr = ~0ul; + struct page *page; + long i, npages; + size_t dvbo = valid - vbo; + size_t off = 0; + + /*Find user address*/ + for (i = 0; i < nr_segs; i++) { + if (off <= dvbo && dvbo < off + iov[i].iov_len) { + uaddr = (unsigned long)iov[i].iov_base + dvbo - + off; + break; + } + off += iov[i].iov_len; + } + + if (uaddr == ~0ul) + goto fix_error; + + npages = get_user_pages_unlocked(uaddr, 1, &page, FOLL_WRITE); + + if (npages <= 0) + goto fix_error; + + zero_user_segment(page, valid & (PAGE_SIZE - 1), PAGE_SIZE); + put_page(page); + } + +out: + return ret; +fix_error: + ntfs_inode_warn(inode, "file garbage at 0x%llx", valid); + goto out; +} + +int ntfs_set_size(struct inode *inode, u64 new_size) +{ + struct super_block *sb = inode->i_sb; + struct ntfs_sb_info *sbi = sb->s_fs_info; + struct ntfs_inode *ni = ntfs_i(inode); + int err; + + /* Check for maximum file size */ + if (is_sparsed(ni) || is_compressed(ni)) { + if (new_size > sbi->maxbytes_sparse) { + err = -EFBIG; + goto out; + } + } else if (new_size > sbi->maxbytes) { + err = -EFBIG; + goto out; + } + + ni_lock(ni); + down_write(&ni->file.run_lock); + + err = attr_set_size(ni, ATTR_DATA, NULL, 0, &ni->file.run, new_size, + &ni->i_valid, true, NULL); + + up_write(&ni->file.run_lock); + ni_unlock(ni); + + mark_inode_dirty(inode); + +out: + return err; +} + +static int ntfs_writepage(struct page *page, struct writeback_control *wbc) +{ + return block_write_full_page(page, ntfs_get_block, wbc); +} + +static int ntfs_writepages(struct address_space *mapping, + struct writeback_control *wbc) +{ + return mpage_writepages(mapping, wbc, ntfs_get_block); +} + +/*ntfs_write_begin*/ +static int ntfs_get_block_write_begin(struct inode *inode, sector_t vbn, + struct buffer_head *bh_result, int create) +{ + return ntfs_get_block_vbo(inode, (u64)vbn << inode->i_blkbits, + bh_result, create, GET_BLOCK_WRITE_BEGIN); +} + +static int ntfs_write_begin(struct file *file, struct address_space *mapping, + loff_t pos, u32 len, u32 flags, struct page **pagep, + void **fsdata) +{ + int err; + + *pagep = NULL; + + err = block_write_begin(mapping, pos, len, flags, pagep, + ntfs_get_block_write_begin); + if (err < 0) + ntfs_write_failed(mapping, pos + len); + + return err; +} + +/* address_space_operations::write_end */ +static int ntfs_write_end(struct file *file, struct address_space *mapping, + loff_t pos, u32 len, u32 copied, struct page *page, + void *fsdata) + +{ + struct inode *inode = mapping->host; + struct ntfs_inode *ni = ntfs_i(inode); + u64 valid = ni->i_valid; + int err; + + err = generic_write_end(file, mapping, pos, len, copied, page, fsdata); + + if (err < len) + ntfs_write_failed(mapping, pos + len); + if (err >= 0) { + bool dirty = false; + + if (!(ni->std_fa & FILE_ATTRIBUTE_ARCHIVE)) { + inode->i_ctime = inode->i_mtime = current_time(inode); + ni->std_fa |= FILE_ATTRIBUTE_ARCHIVE; + dirty = true; + } + + if (valid != ni->i_valid) { + /* ni->i_valid is changed in ntfs_get_block_vbo */ + dirty = true; + } + + if (dirty) + mark_inode_dirty(inode); + } + + return err; +} + +int reset_log_file(struct inode *inode) +{ + int err; + loff_t pos = 0; + u32 log_size = inode->i_size; + struct address_space *mapping = inode->i_mapping; + + for (;;) { + u32 len; + void *kaddr; + struct page *page; + + len = pos + PAGE_SIZE > log_size ? (log_size - pos) : PAGE_SIZE; + + err = block_write_begin(mapping, pos, len, 0, &page, + ntfs_get_block_write_begin); + if (err) + goto out; + + kaddr = kmap_atomic(page); + memset(kaddr, -1, len); + kunmap_atomic(kaddr); + flush_dcache_page(page); + + err = block_write_end(NULL, mapping, pos, len, len, page, NULL); + if (err < 0) + goto out; + pos += len; + + if (pos >= log_size) + break; + balance_dirty_pages_ratelimited(mapping); + } +out: + mark_inode_dirty_sync(inode); + + return err; +} + +int ntfs_write_inode(struct inode *inode, struct writeback_control *wbc) +{ + if (WARN_ON_ONCE(current->flags & PF_MEMALLOC) || + sb_rdonly(inode->i_sb)) + return 0; + + return _ni_write_inode(inode, wbc->sync_mode == WB_SYNC_ALL); +} + +int ntfs_sync_inode(struct inode *inode) +{ + return _ni_write_inode(inode, 1); +} + +/* + * helper function for ntfs_flush_inodes. This writes both the inode + * and the file data blocks, waiting for in flight data blocks before + * the start of the call. It does not wait for any io started + * during the call + */ +static int writeback_inode(struct inode *inode) +{ + int ret = sync_inode_metadata(inode, 0); + + if (!ret) + ret = filemap_fdatawrite(inode->i_mapping); + return ret; +} + +/* + * write data and metadata corresponding to i1 and i2. The io is + * started but we do not wait for any of it to finish. + * + * filemap_flush is used for the block device, so if there is a dirty + * page for a block already in flight, we will not wait and start the + * io over again + */ +int ntfs_flush_inodes(struct super_block *sb, struct inode *i1, + struct inode *i2) +{ + int ret = 0; + + if (i1) + ret = writeback_inode(i1); + if (!ret && i2) + ret = writeback_inode(i2); + if (!ret) + ret = filemap_flush(sb->s_bdev->bd_inode->i_mapping); + return ret; +} + +int inode_write_data(struct inode *inode, const void *data, size_t bytes) +{ + pgoff_t idx; + + /* Write non resident data */ + for (idx = 0; bytes; idx++) { + size_t op = bytes > PAGE_SIZE ? PAGE_SIZE : bytes; + struct page *page = ntfs_map_page(inode->i_mapping, idx); + + if (IS_ERR(page)) + return PTR_ERR(page); + + lock_page(page); + WARN_ON(!PageUptodate(page)); + ClearPageUptodate(page); + + memcpy(page_address(page), data, op); + + flush_dcache_page(page); + SetPageUptodate(page); + unlock_page(page); + + ntfs_unmap_page(page); + + bytes -= op; + data = Add2Ptr(data, PAGE_SIZE); + } + return 0; +} + +int ntfs_create_inode(struct inode *dir, struct dentry *dentry, + const struct cpu_str *uni, umode_t mode, dev_t dev, + const char *symname, unsigned int size, int excl, + struct ntfs_fnd *fnd, struct inode **new_inode) +{ + int err; + struct super_block *sb = dir->i_sb; + struct ntfs_sb_info *sbi = sb->s_fs_info; + const struct qstr *name = &dentry->d_name; + CLST ino = 0; + struct ntfs_inode *dir_ni = ntfs_i(dir); + struct ntfs_inode *ni = NULL; + struct inode *inode = NULL; + struct ATTRIB *attr; + struct ATTR_STD_INFO5 *std5; + struct ATTR_FILE_NAME *fname; + struct MFT_REC *rec; + u32 asize, dsize, sd_size; + enum FILE_ATTRIBUTE fa; + __le32 security_id = SECURITY_ID_INVALID; + CLST vcn; + const void *sd; + u16 t16, nsize = 0, aid = 0; + struct INDEX_ROOT *root, *dir_root; + struct NTFS_DE *e, *new_de = NULL; + struct REPARSE_DATA_BUFFER *rp = NULL; + typeof(rp->SymbolicLink2ReparseBuffer) *rb; + __le16 *rp_name; + bool is_dir = S_ISDIR(mode); + bool rp_inserted = false; + bool is_sp = S_ISCHR(mode) || S_ISBLK(mode) || S_ISFIFO(mode) || + S_ISSOCK(mode); + + if (is_sp) + return -EOPNOTSUPP; + + dir_root = indx_get_root(&dir_ni->dir, dir_ni, NULL, NULL); + if (!dir_root) + return -EINVAL; + + fa = (is_dir ? (dir_ni->std_fa | FILE_ATTRIBUTE_DIRECTORY) : + S_ISLNK(mode) ? + FILE_ATTRIBUTE_REPARSE_POINT : + sbi->options.sparse ? + FILE_ATTRIBUTE_SPARSE_FILE : + (dir_ni->std_fa & FILE_ATTRIBUTE_COMPRESSED) ? + FILE_ATTRIBUTE_COMPRESSED : + 0) | + FILE_ATTRIBUTE_ARCHIVE; + + if (!(mode & 0222)) + fa |= FILE_ATTRIBUTE_READONLY; + + new_de = __getname(); + if (!new_de) { + err = -ENOMEM; + goto out1; + } + + /*mark rw ntfs as dirty. it will be cleared at umount*/ + ntfs_set_state(sbi, NTFS_DIRTY_DIRTY); + + /* Step 1: allocate and fill new mft record */ + err = ntfs_look_free_mft(sbi, &ino, false, NULL, NULL); + if (err) + goto out2; + + ni = ntfs_new_inode(sbi, ino, is_dir); + if (IS_ERR(ni)) { + err = PTR_ERR(ni); + ni = NULL; + goto out3; + } + inode = &ni->vfs_inode; + + inode->i_atime = inode->i_mtime = inode->i_ctime = ni->i_crtime = + current_time(inode); + + rec = ni->mi.mrec; + rec->hard_links = cpu_to_le16(1); + attr = Add2Ptr(rec, le16_to_cpu(rec->attr_off)); + + /* Get default security id */ + sd = s_default_security; + sd_size = sizeof(s_default_security); + + if (is_ntfs3(sbi)) { + security_id = dir_ni->std_security_id; + if (le32_to_cpu(security_id) < SECURITY_ID_FIRST) { + security_id = sbi->security.def_security_id; + + if (security_id == SECURITY_ID_INVALID && + !ntfs_insert_security(sbi, sd, sd_size, + &security_id, NULL)) + sbi->security.def_security_id = security_id; + } + } + + /* Insert standard info */ + std5 = Add2Ptr(attr, SIZEOF_RESIDENT); + + if (security_id == SECURITY_ID_INVALID) { + dsize = sizeof(struct ATTR_STD_INFO); + } else { + dsize = sizeof(struct ATTR_STD_INFO5); + std5->security_id = security_id; + ni->std_security_id = security_id; + } + asize = SIZEOF_RESIDENT + dsize; + + attr->type = ATTR_STD; + attr->size = cpu_to_le32(asize); + attr->id = cpu_to_le16(aid++); + attr->res.data_off = SIZEOF_RESIDENT_LE; + attr->res.data_size = cpu_to_le32(dsize); + + std5->cr_time = std5->m_time = std5->c_time = std5->a_time = + kernel2nt(&inode->i_atime); + + ni->std_fa = fa; + std5->fa = fa; + + attr = Add2Ptr(attr, asize); + + /* Insert file name */ + err = fill_name_de(sbi, new_de, name, uni); + if (err) + goto out4; + + fname = (struct ATTR_FILE_NAME *)(new_de + 1); + + new_de->ref.low = cpu_to_le32(ino); +#ifdef NTFS3_64BIT_CLUSTER + new_de->ref.high = cpu_to_le16(ino >> 32); + fname->home.high = cpu_to_le16(dir->i_ino >> 32); +#endif + new_de->ref.seq = rec->seq; + + fname->home.low = cpu_to_le32(dir->i_ino & 0xffffffff); + fname->home.seq = dir_ni->mi.mrec->seq; + + fname->dup.cr_time = fname->dup.m_time = fname->dup.c_time = + fname->dup.a_time = std5->cr_time; + fname->dup.alloc_size = fname->dup.data_size = 0; + fname->dup.fa = std5->fa; + fname->dup.ea_size = fname->dup.reparse = 0; + + dsize = le16_to_cpu(new_de->key_size); + asize = QuadAlign(SIZEOF_RESIDENT + dsize); + + attr->type = ATTR_NAME; + attr->size = cpu_to_le32(asize); + attr->res.data_off = SIZEOF_RESIDENT_LE; + attr->res.flags = RESIDENT_FLAG_INDEXED; + attr->id = cpu_to_le16(aid++); + attr->res.data_size = cpu_to_le32(dsize); + memcpy(Add2Ptr(attr, SIZEOF_RESIDENT), fname, dsize); + + attr = Add2Ptr(attr, asize); + + if (security_id == SECURITY_ID_INVALID) { + /* Insert security attribute */ + asize = SIZEOF_RESIDENT + QuadAlign(sd_size); + + attr->type = ATTR_SECURE; + attr->size = cpu_to_le32(asize); + attr->id = cpu_to_le16(aid++); + attr->res.data_off = SIZEOF_RESIDENT_LE; + attr->res.data_size = cpu_to_le32(sd_size); + memcpy(Add2Ptr(attr, SIZEOF_RESIDENT), sd, sd_size); + + attr = Add2Ptr(attr, asize); + } + + if (is_dir) { + /* Create root of directory */ + dsize = sizeof(struct INDEX_ROOT) + sizeof(struct NTFS_DE); + asize = sizeof(I30_NAME) + SIZEOF_RESIDENT + dsize; + + attr->type = ATTR_ROOT; + attr->size = cpu_to_le32(asize); + attr->id = cpu_to_le16(aid++); + + attr->name_len = ARRAY_SIZE(I30_NAME); + attr->name_off = SIZEOF_RESIDENT_LE; + attr->res.data_off = + cpu_to_le16(sizeof(I30_NAME) + SIZEOF_RESIDENT); + attr->res.data_size = cpu_to_le32(dsize); + memcpy(Add2Ptr(attr, SIZEOF_RESIDENT), I30_NAME, + sizeof(I30_NAME)); + + root = Add2Ptr(attr, sizeof(I30_NAME) + SIZEOF_RESIDENT); + memcpy(root, dir_root, offsetof(struct INDEX_ROOT, ihdr)); + root->ihdr.de_off = + cpu_to_le32(sizeof(struct INDEX_HDR)); // 0x10 + root->ihdr.used = cpu_to_le32(sizeof(struct INDEX_HDR) + + sizeof(struct NTFS_DE)); + root->ihdr.total = root->ihdr.used; + + e = Add2Ptr(root, sizeof(struct INDEX_ROOT)); + e->size = cpu_to_le16(sizeof(struct NTFS_DE)); + e->flags = NTFS_IE_LAST; + + ni->ni_flags |= NI_FLAG_DIR; + + err = indx_init(&ni->dir, sbi, attr, INDEX_MUTEX_I30); + if (err) + goto out4; + } else if (S_ISLNK(mode)) { + /* Create symlink */ + dsize = 0; + asize = SIZEOF_RESIDENT; + + /* insert empty ATTR_DATA */ + attr->type = ATTR_DATA; + attr->size = cpu_to_le32(SIZEOF_RESIDENT); + attr->id = cpu_to_le16(aid++); + attr->name_off = SIZEOF_RESIDENT_LE; + attr->res.data_off = SIZEOF_RESIDENT_LE; + + attr = Add2Ptr(attr, asize); + + /* + * Insert ATTR_REPARSE + * Assume each symbol is coded at most with 2 utf16 and zero + */ + rp = ntfs_alloc(ntfs_reparse_bytes(2 * size + 2), 1); + if (!rp) { + err = -ENOMEM; + goto out4; + } + rb = &rp->SymbolicLink2ReparseBuffer; + rp_name = rb->PathBuffer; + + /* Convert link name to utf16 */ + err = ntfs_nls_to_utf16(sbi, symname, size, + (struct cpu_str *)(rp_name - 1), + 2 * size, UTF16_LITTLE_ENDIAN); + if (err < 0) + goto out4; + + /* err = the length of unicode name of symlink */ + nsize = ntfs_reparse_bytes(err); + + if (nsize > sbi->reparse.max_size) { + err = -EFBIG; + goto out4; + } + + rp->ReparseTag = IO_REPARSE_TAG_SYMLINK; + rp->ReparseDataLength = cpu_to_le16( + (nsize - offsetof(struct REPARSE_DATA_BUFFER, + SymbolicLink2ReparseBuffer))); + rb = &rp->SymbolicLink2ReparseBuffer; + rb->SubstituteNameOffset = cpu_to_le16(sizeof(short) * err); + rb->SubstituteNameLength = cpu_to_le16(sizeof(short) * err + 8); + rb->PrintNameLength = rb->SubstituteNameOffset; + rb->Flags = 0; + + memmove(rp_name + err + 4, rp_name, sizeof(short) * err); + + rp_name += err; + rp_name[0] = cpu_to_le16('\\'); + rp_name[1] = cpu_to_le16('?'); + rp_name[2] = cpu_to_le16('?'); + rp_name[3] = cpu_to_le16('\\'); + + attr->type = ATTR_REPARSE; + attr->id = cpu_to_le16(aid++); + + /* resident or non resident? */ + asize = QuadAlign(SIZEOF_RESIDENT + nsize); + t16 = PtrOffset(rec, attr); + + if (asize + t16 + 8 > sbi->record_size) { + CLST alen; + CLST clst = bytes_to_cluster(sbi, nsize); + + /* bytes per runs */ + t16 = sbi->record_size - t16 - SIZEOF_NONRESIDENT; + + attr->non_res = 1; + attr->nres.evcn = cpu_to_le64(clst - 1); + attr->name_off = SIZEOF_NONRESIDENT_LE; + attr->nres.run_off = attr->name_off; + attr->nres.data_size = cpu_to_le64(nsize); + attr->nres.valid_size = attr->nres.data_size; + attr->nres.alloc_size = + cpu_to_le64(ntfs_up_cluster(sbi, nsize)); + + err = attr_allocate_clusters(sbi, &ni->file.run, 0, 0, + clst, NULL, 0, &alen, 0, + NULL); + if (err) + goto out5; + + err = run_pack(&ni->file.run, 0, clst, + Add2Ptr(attr, SIZEOF_NONRESIDENT), t16, + &vcn); + if (err < 0) + goto out5; + + if (vcn != clst) { + err = -EINVAL; + goto out5; + } + + asize = SIZEOF_NONRESIDENT + QuadAlign(err); + inode->i_size = nsize; + } else { + attr->res.data_off = SIZEOF_RESIDENT_LE; + attr->res.data_size = cpu_to_le32(nsize); + memcpy(Add2Ptr(attr, SIZEOF_RESIDENT), rp, nsize); + inode->i_size = nsize; + nsize = 0; + } + + attr->size = cpu_to_le32(asize); + + err = ntfs_insert_reparse(sbi, IO_REPARSE_TAG_SYMLINK, + &new_de->ref); + if (err) + goto out5; + + rp_inserted = true; + } else { + attr->type = ATTR_DATA; + attr->id = cpu_to_le16(aid++); + /* Create non resident data attribute */ + attr->non_res = 1; + attr->nres.evcn = cpu_to_le64(-1ll); + if (fa & FILE_ATTRIBUTE_SPARSE_FILE) { + attr->size = cpu_to_le32(SIZEOF_NONRESIDENT_EX + 8); + attr->name_off = SIZEOF_NONRESIDENT_EX_LE; + attr->flags = ATTR_FLAG_SPARSED; + asize = SIZEOF_NONRESIDENT_EX + 8; + } else if (fa & FILE_ATTRIBUTE_COMPRESSED) { + attr->size = cpu_to_le32(SIZEOF_NONRESIDENT_EX + 8); + attr->name_off = SIZEOF_NONRESIDENT_EX_LE; + attr->flags = ATTR_FLAG_COMPRESSED; + attr->nres.c_unit = COMPRESSION_UNIT; + asize = SIZEOF_NONRESIDENT_EX + 8; + } else { + attr->size = cpu_to_le32(SIZEOF_NONRESIDENT + 8); + attr->name_off = SIZEOF_NONRESIDENT_LE; + asize = SIZEOF_NONRESIDENT + 8; + } + attr->nres.run_off = attr->name_off; + } + + attr = Add2Ptr(attr, asize); + attr->type = ATTR_END; + + rec->used = cpu_to_le32(PtrOffset(rec, attr) + 8); + rec->next_attr_id = cpu_to_le16(aid); + + /* Step 2: Add new name in index */ + err = indx_insert_entry(&dir_ni->dir, dir_ni, new_de, sbi, fnd); + if (err) + goto out6; + + /* Update current directory record */ + mark_inode_dirty(dir); + + /* Fill vfs inode fields */ + inode->i_uid = sbi->options.uid ? sbi->options.fs_uid : current_fsuid(); + inode->i_gid = + sbi->options.gid ? + sbi->options.fs_gid : + (dir->i_mode & S_ISGID) ? dir->i_gid : current_fsgid(); + inode->i_generation = le16_to_cpu(rec->seq); + + dir->i_mtime = dir->i_ctime = inode->i_atime; + + if (is_dir) { + if (dir->i_mode & S_ISGID) + mode |= S_ISGID; + inode->i_op = &ntfs_dir_inode_operations; + inode->i_fop = &ntfs_dir_operations; + } else if (S_ISLNK(mode)) { + inode->i_op = &ntfs_link_inode_operations; + inode->i_fop = NULL; + inode->i_mapping->a_ops = &ntfs_aops; + } else { + inode->i_op = &ntfs_file_inode_operations; + inode->i_fop = &ntfs_file_operations; + inode->i_mapping->a_ops = + is_compressed(ni) ? &ntfs_aops_cmpr : &ntfs_aops; + init_rwsem(&ni->file.run_lock); + } + + inode->i_mode = mode; + + if (!S_ISLNK(mode) && (sb->s_flags & SB_POSIXACL)) { + err = ntfs_init_acl(inode, dir); + if (err) + goto out6; + } else { + inode->i_flags |= S_NOSEC; + } + + /* Write non resident data */ + if (nsize) { + err = ntfs_sb_write_run(sbi, &ni->file.run, 0, rp, nsize); + if (err) + goto out7; + } + + /* call 'd_instantiate' after inode->i_op is set but before finish_open */ + d_instantiate(dentry, inode); + + mark_inode_dirty(inode); + mark_inode_dirty(dir); + + /* normal exit */ + goto out2; + +out7: + + /* undo 'indx_insert_entry' */ + indx_delete_entry(&dir_ni->dir, dir_ni, new_de + 1, + le16_to_cpu(new_de->key_size), sbi); +out6: + if (rp_inserted) + ntfs_remove_reparse(sbi, IO_REPARSE_TAG_SYMLINK, &new_de->ref); + +out5: + if (is_dir || run_is_empty(&ni->file.run)) + goto out4; + + run_deallocate(sbi, &ni->file.run, false); + +out4: + clear_rec_inuse(rec); + clear_nlink(inode); + ni->mi.dirty = false; + discard_new_inode(inode); +out3: + ntfs_mark_rec_free(sbi, ino); + +out2: + __putname(new_de); + ntfs_free(rp); + +out1: + if (err) + return err; + + unlock_new_inode(inode); + + *new_inode = inode; + return 0; +} + +int ntfs_link_inode(struct inode *inode, struct dentry *dentry) +{ + int err; + struct inode *dir = d_inode(dentry->d_parent); + struct ntfs_inode *dir_ni = ntfs_i(dir); + struct ntfs_inode *ni = ntfs_i(inode); + struct super_block *sb = inode->i_sb; + struct ntfs_sb_info *sbi = sb->s_fs_info; + const struct qstr *name = &dentry->d_name; + struct NTFS_DE *new_de = NULL; + struct ATTR_FILE_NAME *fname; + struct ATTRIB *attr; + u16 key_size; + struct INDEX_ROOT *dir_root; + + dir_root = indx_get_root(&dir_ni->dir, dir_ni, NULL, NULL); + if (!dir_root) + return -EINVAL; + + new_de = __getname(); + if (!new_de) + return -ENOMEM; + + /*mark rw ntfs as dirty. it will be cleared at umount*/ + ntfs_set_state(ni->mi.sbi, NTFS_DIRTY_DIRTY); + + // Insert file name + err = fill_name_de(sbi, new_de, name, NULL); + if (err) + goto out; + + key_size = le16_to_cpu(new_de->key_size); + fname = (struct ATTR_FILE_NAME *)(new_de + 1); + + err = ni_insert_resident(ni, key_size, ATTR_NAME, NULL, 0, &attr, NULL); + if (err) + goto out; + + new_de->ref.low = cpu_to_le32(inode->i_ino); +#ifdef NTFS3_64BIT_CLUSTER + new_de->ref.high = cpu_to_le16(inode->i_ino >> 32); + fname->home.high = cpu_to_le16(dir->i_ino >> 32); +#endif + new_de->ref.seq = ni->mi.mrec->seq; + + fname->home.low = cpu_to_le32(dir->i_ino & 0xffffffff); + fname->home.seq = dir_ni->mi.mrec->seq; + + fname->dup.cr_time = fname->dup.m_time = fname->dup.c_time = + fname->dup.a_time = kernel2nt(&inode->i_ctime); + fname->dup.alloc_size = fname->dup.data_size = 0; + fname->dup.fa = ni->std_fa; + fname->dup.ea_size = fname->dup.reparse = 0; + + memcpy(Add2Ptr(attr, SIZEOF_RESIDENT), fname, key_size); + + err = indx_insert_entry(&dir_ni->dir, dir_ni, new_de, sbi, NULL); + if (err) + goto out; + + le16_add_cpu(&ni->mi.mrec->hard_links, 1); + ni->mi.dirty = true; + +out: + __putname(new_de); + return err; +} + +/* + * ntfs_unlink_inode + * + * inode_operations::unlink + * inode_operations::rmdir + */ +int ntfs_unlink_inode(struct inode *dir, const struct dentry *dentry) +{ + int err; + struct super_block *sb = dir->i_sb; + struct ntfs_sb_info *sbi = sb->s_fs_info; + struct inode *inode = d_inode(dentry); + struct ntfs_inode *ni = ntfs_i(inode); + const struct qstr *name = &dentry->d_name; + struct ntfs_inode *dir_ni = ntfs_i(dir); + struct ntfs_index *indx = &dir_ni->dir; + struct cpu_str *uni = NULL; + struct ATTR_FILE_NAME *fname; + u8 name_type; + struct ATTR_LIST_ENTRY *le; + struct MFT_REF ref; + bool is_dir = S_ISDIR(inode->i_mode); + struct INDEX_ROOT *dir_root; + + dir_root = indx_get_root(indx, dir_ni, NULL, NULL); + if (!dir_root) + return -EINVAL; + + ni_lock(ni); + + if (is_dir && !dir_is_empty(inode)) { + err = -ENOTEMPTY; + goto out1; + } + + if (ntfs_is_meta_file(sbi, inode->i_ino)) { + err = -EINVAL; + goto out1; + } + + uni = __getname(); + if (!uni) { + err = -ENOMEM; + goto out1; + } + + /* Convert input string to unicode */ + err = ntfs_nls_to_utf16(sbi, name->name, name->len, uni, NTFS_NAME_LEN, + UTF16_HOST_ENDIAN); + if (err < 0) + goto out4; + + le = NULL; + + /*mark rw ntfs as dirty. it will be cleared at umount*/ + ntfs_set_state(sbi, NTFS_DIRTY_DIRTY); + + /* find name in record */ +#ifdef NTFS3_64BIT_CLUSTER + ref.low = cpu_to_le32(dir->i_ino & 0xffffffff); + ref.high = cpu_to_le16(dir->i_ino >> 32); +#else + ref.low = cpu_to_le32(dir->i_ino & 0xffffffff); + ref.high = 0; +#endif + ref.seq = dir_ni->mi.mrec->seq; + + fname = ni_fname_name(ni, uni, &ref, &le); + if (!fname) { + err = -ENOENT; + goto out3; + } + + name_type = paired_name(fname->type); + + err = indx_delete_entry(indx, dir_ni, fname, fname_full_size(fname), + sbi); + if (err) + goto out4; + + /* Then remove name from mft */ + ni_remove_attr_le(ni, attr_from_name(fname), le); + + le16_add_cpu(&ni->mi.mrec->hard_links, -1); + ni->mi.dirty = true; + + if (name_type != FILE_NAME_POSIX) { + /* Now we should delete name by type */ + fname = ni_fname_type(ni, name_type, &le); + if (fname) { + err = indx_delete_entry(indx, dir_ni, fname, + fname_full_size(fname), sbi); + if (err) + goto out4; + + ni_remove_attr_le(ni, attr_from_name(fname), le); + + le16_add_cpu(&ni->mi.mrec->hard_links, -1); + } + } + +out4: + switch (err) { + case 0: + drop_nlink(inode); + case -ENOTEMPTY: + case -ENOSPC: + case -EROFS: + break; + default: + make_bad_inode(inode); + } + + dir->i_mtime = dir->i_ctime = current_time(dir); + mark_inode_dirty(dir); + inode->i_ctime = dir->i_ctime; + if (inode->i_nlink) + mark_inode_dirty(inode); + +out3: + __putname(uni); +out1: + ni_unlock(ni); + return err; +} + +void ntfs_evict_inode(struct inode *inode) +{ + truncate_inode_pages_final(&inode->i_data); + + if (inode->i_nlink) + _ni_write_inode(inode, inode_needs_sync(inode)); + + invalidate_inode_buffers(inode); + clear_inode(inode); + + ni_clear(ntfs_i(inode)); +} + +static noinline int ntfs_readlink_hlp(struct inode *inode, char *buffer, + int buflen) +{ + int err = 0; + struct ntfs_inode *ni = ntfs_i(inode); + struct super_block *sb = inode->i_sb; + struct ntfs_sb_info *sbi = sb->s_fs_info; + u64 i_size = inode->i_size; + u16 nlen = 0; + void *to_free = NULL; + struct REPARSE_DATA_BUFFER *rp; + struct le_str *uni; + struct ATTRIB *attr; + + /* Reparse data present. Try to parse it */ + static_assert(!offsetof(struct REPARSE_DATA_BUFFER, ReparseTag)); + static_assert(sizeof(u32) == sizeof(rp->ReparseTag)); + + *buffer = 0; + + /* Read into temporal buffer */ + if (i_size > sbi->reparse.max_size || i_size <= sizeof(u32)) { + err = -EINVAL; + goto out; + } + + attr = ni_find_attr(ni, NULL, NULL, ATTR_REPARSE, NULL, 0, NULL, NULL); + if (!attr) { + err = -EINVAL; + goto out; + } + + if (!attr->non_res) { + rp = resident_data_ex(attr, i_size); + if (!rp) { + err = -EINVAL; + goto out; + } + } else { + rp = ntfs_alloc(i_size, 0); + if (!rp) { + err = -ENOMEM; + goto out; + } + to_free = rp; + err = ntfs_read_run_nb(sbi, &ni->file.run, 0, rp, i_size, NULL); + if (err) + goto out; + } + + err = -EINVAL; + + /* Microsoft Tag */ + switch (rp->ReparseTag) { + case IO_REPARSE_TAG_MICROSOFT | IO_REPARSE_TAG_SYMBOLIC_LINK: + /* Symbolic link */ + /* Can we use 'Rp->SymbolicLinkReparseBuffer.PrintNameLength'? */ + if (i_size <= offsetof(struct REPARSE_DATA_BUFFER, + SymbolicLinkReparseBuffer.PathBuffer)) + goto out; + uni = Add2Ptr(rp, + offsetof(struct REPARSE_DATA_BUFFER, + SymbolicLinkReparseBuffer.PathBuffer) + + le16_to_cpu(rp->SymbolicLinkReparseBuffer + .PrintNameOffset) - + 2); + nlen = le16_to_cpu( + rp->SymbolicLinkReparseBuffer.PrintNameLength); + break; + + case IO_REPARSE_TAG_MOUNT_POINT: + /* Mount points and junctions */ + /* Can we use 'Rp->MountPointReparseBuffer.PrintNameLength'? */ + if (i_size <= offsetof(struct REPARSE_DATA_BUFFER, + MountPointReparseBuffer.PathBuffer)) + goto out; + uni = Add2Ptr(rp, + offsetof(struct REPARSE_DATA_BUFFER, + MountPointReparseBuffer.PathBuffer) + + le16_to_cpu(rp->MountPointReparseBuffer + .PrintNameOffset) - + 2); + nlen = le16_to_cpu(rp->MountPointReparseBuffer.PrintNameLength); + break; + + case IO_REPARSE_TAG_SYMLINK: + /* FolderSymbolicLink */ + /* Can we use 'Rp->SymbolicLink2ReparseBuffer.PrintNameLength'? */ + if (i_size <= offsetof(struct REPARSE_DATA_BUFFER, + SymbolicLink2ReparseBuffer.PathBuffer)) + goto out; + uni = Add2Ptr(rp, + offsetof(struct REPARSE_DATA_BUFFER, + SymbolicLink2ReparseBuffer.PathBuffer) + + le16_to_cpu(rp->SymbolicLink2ReparseBuffer + .PrintNameOffset) - + 2); + nlen = le16_to_cpu( + rp->SymbolicLink2ReparseBuffer.PrintNameLength); + break; + + case IO_REPARSE_TAG_CLOUD: + case IO_REPARSE_TAG_CLOUD_1: + case IO_REPARSE_TAG_CLOUD_2: + case IO_REPARSE_TAG_CLOUD_3: + case IO_REPARSE_TAG_CLOUD_4: + case IO_REPARSE_TAG_CLOUD_5: + case IO_REPARSE_TAG_CLOUD_6: + case IO_REPARSE_TAG_CLOUD_7: + case IO_REPARSE_TAG_CLOUD_8: + case IO_REPARSE_TAG_CLOUD_9: + case IO_REPARSE_TAG_CLOUD_A: + case IO_REPARSE_TAG_CLOUD_B: + case IO_REPARSE_TAG_CLOUD_C: + case IO_REPARSE_TAG_CLOUD_D: + case IO_REPARSE_TAG_CLOUD_E: + case IO_REPARSE_TAG_CLOUD_F: + err = sizeof("OneDrive") - 1; + if (err > buflen) + err = buflen; + memcpy(buffer, "OneDrive", err); + goto out; + + default: + if (IsReparseTagMicrosoft(rp->ReparseTag)) + goto out; + if (!IsReparseTagNameSurrogate(rp->ReparseTag) || + i_size <= sizeof(struct REPARSE_POINT)) { + goto out; + } + + /* Users tag */ + uni = Add2Ptr(rp, sizeof(struct REPARSE_POINT) - 2); + nlen = le16_to_cpu( + ((struct REPARSE_POINT *)rp)->ReparseDataLength) - + sizeof(struct REPARSE_POINT); + } + + /* Convert nlen from bytes to UNICODE chars */ + nlen >>= 1; + + /* Check that name is available */ + if (!nlen || &uni->name[nlen] > (__le16 *)Add2Ptr(rp, i_size)) + goto out; + + /* If name is already zero terminated then truncate it now */ + if (!uni->name[nlen - 1]) + nlen -= 1; + uni->len = nlen; + + err = ntfs_utf16_to_nls(sbi, uni, buffer, buflen); + + if (err < 0) + goto out; + + /* Always set last zero */ + buffer[err] = 0; + +out: + ntfs_free(to_free); + + return err; +} + +static const char *ntfs_get_link(struct dentry *de, struct inode *inode, + struct delayed_call *done) +{ + int err; + char *ret; + + if (!de) + return ERR_PTR(-ECHILD); + + ret = kmalloc(PAGE_SIZE, GFP_NOFS); + if (!ret) + return ERR_PTR(-ENOMEM); + + err = ntfs_readlink_hlp(inode, ret, PAGE_SIZE); + if (err < 0) { + kfree(ret); + return ERR_PTR(err); + } + + set_delayed_call(done, kfree_link, ret); + + return ret; +} + +const struct inode_operations ntfs_link_inode_operations = { + .get_link = ntfs_get_link, + .setattr = ntfs_setattr, + .listxattr = ntfs_listxattr, + .permission = ntfs_permission, + .get_acl = ntfs_get_acl, + .set_acl = ntfs_set_acl, +}; + +const struct address_space_operations ntfs_aops = { + .readpage = ntfs_readpage, + .readahead = ntfs_readahead, + .writepage = ntfs_writepage, + .writepages = ntfs_writepages, + .write_begin = ntfs_write_begin, + .write_end = ntfs_write_end, + .direct_IO = ntfs_direct_IO, + .bmap = ntfs_bmap, +}; + +const struct address_space_operations ntfs_aops_cmpr = { + .readpage = ntfs_readpage, +}; diff --git a/fs/ntfs3/super.c b/fs/ntfs3/super.c new file mode 100644 index 000000000000..6ad5d9488314 --- /dev/null +++ b/fs/ntfs3/super.c @@ -0,0 +1,1489 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * linux/fs/ntfs3/super.c + * + * Copyright (C) 2019-2020 Paragon Software GmbH, All rights reserved. + * + * + * terminology + * + * vcn - virtual cluster number - offset inside the file in clusters + * vbo - virtual byte offset - offset inside the file in bytes + * lcn - logical cluster number - 0 based cluster in clusters heap + * lbo - logical byte offset - absolute position inside volume + * + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "debug.h" +#include "ntfs.h" +#include "ntfs_fs.h" + +#ifdef CONFIG_PRINTK +/* + * Trace warnings/notices/errors + * Thanks Joe Perches for implementation + */ +void ntfs_printk(const struct super_block *sb, const char *fmt, ...) +{ + struct va_format vaf; + va_list args; + int level; + struct ntfs_sb_info *sbi = sb->s_fs_info; + + /*should we use different ratelimits for warnings/notices/errors? */ + if (!___ratelimit(&sbi->msg_ratelimit, "ntfs3")) + return; + + va_start(args, fmt); + + level = printk_get_level(fmt); + vaf.fmt = printk_skip_level(fmt); + vaf.va = &args; + printk("%c%cntfs3: %s: %pV\n", KERN_SOH_ASCII, level, sb->s_id, &vaf); + + va_end(args); +} + +/* print warnings/notices/errors about inode using name or inode number */ +void ntfs_inode_printk(struct inode *inode, const char *fmt, ...) +{ + struct super_block *sb = inode->i_sb; + struct ntfs_sb_info *sbi = sb->s_fs_info; + struct dentry *dentry; + char *name; + va_list args; + struct va_format vaf; + int level; + /*not necessary to print full inode name. just for information */ + const u32 name_len = 63; + + if (!___ratelimit(&sbi->msg_ratelimit, "ntfs3")) + return; + + name = ntfs_alloc(name_len + 1, 0); + if (!name) + return; + + dentry = d_find_alias(inode); + if (dentry) { + /*we can get the name of inode*/ + spin_lock(&dentry->d_lock); + snprintf(name, name_len, "%s", dentry->d_name.name); + spin_unlock(&dentry->d_lock); + dput(dentry); + name[name_len] = 0; /* to be sure*/ + } else { + /*use inode number as inode info*/ + snprintf(name, name_len, "ino=%lx", inode->i_ino); + } + + va_start(args, fmt); + + level = printk_get_level(fmt); + vaf.fmt = printk_skip_level(fmt); + vaf.va = &args; + + printk("%c%cntfs3: %s: %s %pV\n", KERN_SOH_ASCII, level, sb->s_id, name, + &vaf); + + va_end(args); + + ntfs_free(name); +} +#endif + +/* + * Shared memory struct. + * + * on-disk ntfs's upcase table is created by ntfs formater + * 'upcase' table is 128K bytes of memory + * we should read it into memory when mounting + * Several ntfs volumes likely use the same 'upcase' table + * It is good idea to share in-memory 'upcase' table between different volumes + * Unfortunately winxp/vista/win7 use different upcase tables + */ +static DEFINE_SPINLOCK(s_shared_lock); + +static struct { + void *ptr; + u32 len; + int cnt; +} s_shared[8]; + +/* + * ntfs_set_shared + * + * Returns 'ptr' if pointer was saved in shared memory + * Returns NULL if pointer was not shared + */ +void *ntfs_set_shared(void *ptr, u32 bytes) +{ + void *ret = NULL; + int i, j = -1; + + spin_lock(&s_shared_lock); + for (i = 0; i < ARRAY_SIZE(s_shared); i++) { + if (!s_shared[i].cnt) { + j = i; + } else if (bytes == s_shared[i].len && + !memcmp(s_shared[i].ptr, ptr, bytes)) { + s_shared[i].cnt += 1; + ret = s_shared[i].ptr; + break; + } + } + + if (!ret && j != -1) { + s_shared[j].ptr = ptr; + s_shared[j].len = bytes; + s_shared[j].cnt = 1; + ret = ptr; + } + spin_unlock(&s_shared_lock); + + return ret; +} + +/* + * ntfs_put_shared + * + * Returns 'ptr' if pointer is not shared anymore + * Returns NULL if pointer is still shared + */ +void *ntfs_put_shared(void *ptr) +{ + void *ret = ptr; + int i; + + spin_lock(&s_shared_lock); + for (i = 0; i < ARRAY_SIZE(s_shared); i++) { + if (s_shared[i].cnt && s_shared[i].ptr == ptr) { + if (--s_shared[i].cnt) + ret = NULL; + break; + } + } + spin_unlock(&s_shared_lock); + + return ret; +} + +static void clear_mount_options(struct ntfs_mount_options *options) +{ + static_assert(ARRAY_SIZE(options->nls) == 2); + + unload_nls(options->nls[0]); + unload_nls(options->nls[1]); +} + +enum Opt { + Opt_uid, + Opt_gid, + Opt_umask, + Opt_dmask, + Opt_fmask, + Opt_immutable, + Opt_discard, + Opt_force, + Opt_sparse, + Opt_nohidden, + Opt_showmeta, + Opt_acl, + Opt_noatime, + Opt_nls, + Opt_nls_alt, + Opt_prealloc, + Opt_no_acs_rules, + Opt_err, +}; + +static const match_table_t ntfs_tokens = { + { Opt_uid, "uid=%u" }, + { Opt_gid, "gid=%u" }, + { Opt_umask, "umask=%o" }, + { Opt_dmask, "dmask=%o" }, + { Opt_fmask, "fmask=%o" }, + { Opt_immutable, "sys_immutable" }, + { Opt_discard, "discard" }, + { Opt_force, "force" }, + { Opt_sparse, "sparse" }, + { Opt_nohidden, "nohidden" }, + { Opt_acl, "acl" }, + { Opt_noatime, "noatime" }, + { Opt_showmeta, "showmeta" }, + { Opt_nls, "nls=%s" }, + { Opt_nls_alt, "nls_alt=%s" }, + { Opt_prealloc, "prealloc" }, + { Opt_no_acs_rules, "no_acs_rules" }, + { Opt_err, NULL }, +}; + +static noinline int ntfs_parse_options(struct super_block *sb, char *options, + int silent, + struct ntfs_mount_options *opts) +{ + char *p; + substring_t args[MAX_OPT_ARGS]; + int i, option; + char nls_name[2][30]; + + opts->fs_uid = current_uid(); + opts->fs_gid = current_gid(); + opts->fs_fmask_inv = opts->fs_dmask_inv = ~current_umask(); + nls_name[0][0] = 0; + nls_name[1][0] = 0; + + if (!options) + goto out; + + while ((p = strsep(&options, ","))) { + int token; + + if (!*p) + continue; + + token = match_token(p, ntfs_tokens, args); + switch (token) { + case Opt_immutable: + opts->sys_immutable = 1; + break; + case Opt_uid: + if (match_int(&args[0], &option)) + return -EINVAL; + opts->fs_uid = make_kuid(current_user_ns(), option); + if (!uid_valid(opts->fs_uid)) + return -EINVAL; + opts->uid = 1; + break; + case Opt_gid: + if (match_int(&args[0], &option)) + return -EINVAL; + opts->fs_gid = make_kgid(current_user_ns(), option); + if (!gid_valid(opts->fs_gid)) + return -EINVAL; + opts->gid = 1; + break; + case Opt_umask: + if (match_octal(&args[0], &option)) + return -EINVAL; + opts->fs_fmask_inv = opts->fs_dmask_inv = ~option; + opts->fmask = opts->dmask = 1; + break; + case Opt_dmask: + if (match_octal(&args[0], &option)) + return -EINVAL; + opts->fs_dmask_inv = ~option; + opts->dmask = 1; + break; + case Opt_fmask: + if (match_octal(&args[0], &option)) + return -EINVAL; + opts->fs_fmask_inv = ~option; + opts->fmask = 1; + break; + case Opt_discard: + opts->discard = 1; + break; + case Opt_force: + opts->force = 1; + break; + case Opt_sparse: + opts->sparse = 1; + break; + case Opt_nohidden: + opts->nohidden = 1; + break; + case Opt_acl: + sb->s_flags |= SB_POSIXACL; + break; + case Opt_noatime: + sb->s_flags |= SB_NOATIME; + break; + case Opt_showmeta: + opts->showmeta = 1; + break; + case Opt_nls: + case Opt_nls_alt: + match_strlcpy(nls_name[token == Opt_nls_alt], &args[0], + sizeof(nls_name[0])); + break; + case Opt_prealloc: + opts->prealloc = 1; + break; + case Opt_no_acs_rules: + opts->no_acs_rules = 1; + break; + default: + if (!silent) + ntfs_err( + sb, + "Unrecognized mount option \"%s\" or missing value", + p); + //return -EINVAL; + } + } + +out: + + for (i = 0; i < ARRAY_SIZE(opts->nls); i++) { + struct nls_table *nls; + + if (nls_name[i][0]) { + nls = load_nls(nls_name[i]); + if (!nls) { + ntfs_err(sb, "failed to load \"%s\"", + nls_name[i]); + return -EINVAL; + } + } else { + nls = load_nls_default(); + if (!nls) { + ntfs_err(sb, "failed to load default nls"); + return -EINVAL; + } + } + + opts->nls[i] = nls; + } + + /* unload alternative nls if it equals primary one */ + if (!strcmp(opts->nls[0]->charset, opts->nls[1]->charset)) { + unload_nls(opts->nls[1]); + opts->nls[1] = NULL; + } + + if (!strcmp(opts->nls[0]->charset, "utf8")) { + /*use utf16s_to_utf8s/utf8s_to_utf16s instead of nls*/ + unload_nls(opts->nls[0]); + opts->nls[0] = NULL; + } + + return 0; +} + +static int ntfs_remount(struct super_block *sb, int *flags, char *data) +{ + int err, ro_rw; + struct ntfs_sb_info *sbi = sb->s_fs_info; + struct ntfs_mount_options old_opts; + char *orig_data = kstrdup(data, GFP_KERNEL); + + if (data && !orig_data) + return -ENOMEM; + + /* Store original options */ + memcpy(&old_opts, &sbi->options, sizeof(old_opts)); + clear_mount_options(&sbi->options); + memset(&sbi->options, 0, sizeof(sbi->options)); + + err = ntfs_parse_options(sb, data, 0, &sbi->options); + if (err) + goto restore_opts; + + ro_rw = 0; + if (sb_rdonly(sb) && !(*flags & SB_RDONLY)) { + /* ro -> rw */ + ro_rw = 1; + if (sbi->flags & NTFS_FLAGS_NEED_REPLAY) { + ntfs_warn( + sb, + "Couldn't remount rw because journal is not replayed. Please umount/remount instead\n"); + err = -EINVAL; + goto restore_opts; + } + } + + sync_filesystem(sb); + + if (ro_rw && (sbi->volume.flags & VOLUME_FLAG_DIRTY) && + !sbi->options.force) { + ntfs_warn(sb, "volume is dirty and \"force\" flag is not set!"); + err = -EINVAL; + goto restore_opts; + } + + clear_mount_options(&old_opts); + + *flags = (*flags & ~SB_LAZYTIME) | (sb->s_flags & SB_LAZYTIME) | + SB_NODIRATIME | SB_NOATIME; + ntfs_info(sb, "re-mounted. Opts: %s", orig_data); + err = 0; + goto out; + +restore_opts: + clear_mount_options(&sbi->options); + memcpy(&sbi->options, &old_opts, sizeof(old_opts)); + +out: + kfree(orig_data); + return err; +} + +static struct kmem_cache *ntfs_inode_cachep; + +static struct inode *ntfs_alloc_inode(struct super_block *sb) +{ + struct ntfs_inode *ni = kmem_cache_alloc(ntfs_inode_cachep, GFP_NOFS); + + if (!ni) + return NULL; + + memset(ni, 0, offsetof(struct ntfs_inode, vfs_inode)); + + mutex_init(&ni->ni_lock); + + return &ni->vfs_inode; +} + +static void ntfs_i_callback(struct rcu_head *head) +{ + struct inode *inode = container_of(head, struct inode, i_rcu); + struct ntfs_inode *ni = ntfs_i(inode); + + mutex_destroy(&ni->ni_lock); + + kmem_cache_free(ntfs_inode_cachep, ni); +} + +static void ntfs_destroy_inode(struct inode *inode) +{ + call_rcu(&inode->i_rcu, ntfs_i_callback); +} + +static void init_once(void *foo) +{ + struct ntfs_inode *ni = foo; + + inode_init_once(&ni->vfs_inode); +} + +/* noinline to reduce binary size*/ +static noinline void put_ntfs(struct ntfs_sb_info *sbi) +{ + ntfs_free(sbi->new_rec); + ntfs_free(ntfs_put_shared(sbi->upcase)); + ntfs_free(sbi->def_table); + + wnd_close(&sbi->mft.bitmap); + wnd_close(&sbi->used.bitmap); + + if (sbi->mft.ni) + iput(&sbi->mft.ni->vfs_inode); + + if (sbi->security.ni) + iput(&sbi->security.ni->vfs_inode); + + if (sbi->reparse.ni) + iput(&sbi->reparse.ni->vfs_inode); + + if (sbi->objid.ni) + iput(&sbi->objid.ni->vfs_inode); + + if (sbi->volume.ni) + iput(&sbi->volume.ni->vfs_inode); + + ntfs_update_mftmirr(sbi, 0); + + indx_clear(&sbi->security.index_sii); + indx_clear(&sbi->security.index_sdh); + indx_clear(&sbi->reparse.index_r); + indx_clear(&sbi->objid.index_o); + ntfs_free(sbi->compress.frame_unc); + ntfs_free(sbi->compress.ctx); + + clear_mount_options(&sbi->options); + + ntfs_free(sbi); +} + +static void ntfs_put_super(struct super_block *sb) +{ + struct ntfs_sb_info *sbi = sb->s_fs_info; + + /*mark rw ntfs as clear, if possible*/ + ntfs_set_state(sbi, NTFS_DIRTY_CLEAR); + + put_ntfs(sbi); + + sync_blockdev(sb->s_bdev); +} + +static int ntfs_statfs(struct dentry *dentry, struct kstatfs *buf) +{ + struct super_block *sb = dentry->d_sb; + struct ntfs_sb_info *sbi = sb->s_fs_info; + struct wnd_bitmap *wnd = &sbi->used.bitmap; + + buf->f_type = sb->s_magic; + buf->f_bsize = sbi->cluster_size; + buf->f_blocks = wnd->nbits; + + buf->f_bfree = buf->f_bavail = wnd_zeroes(wnd); + buf->f_fsid.val[0] = (u32)sbi->volume.ser_num; + buf->f_fsid.val[1] = (u32)(sbi->volume.ser_num >> 32); + buf->f_namelen = NTFS_NAME_LEN; + + return 0; +} + +static int ntfs_show_options(struct seq_file *m, struct dentry *root) +{ + struct super_block *sb = root->d_sb; + struct ntfs_sb_info *sbi = sb->s_fs_info; + struct ntfs_mount_options *opts = &sbi->options; + + if (opts->uid) + seq_printf(m, ",uid=%u", + from_kuid_munged(&init_user_ns, opts->fs_uid)); + if (opts->gid) + seq_printf(m, ",gid=%u", + from_kgid_munged(&init_user_ns, opts->fs_gid)); + if (opts->fmask) + seq_printf(m, ",fmask=%04o", ~opts->fs_fmask_inv); + if (opts->dmask) + seq_printf(m, ",dmask=%04o", ~opts->fs_dmask_inv); + if (opts->nls[0]) + seq_printf(m, ",nls=%s", opts->nls[0]->charset); + else + seq_puts(m, ",nls=utf8"); + if (opts->nls[1]) + seq_printf(m, ",nls_alt=%s", opts->nls[1]->charset); + if (opts->sys_immutable) + seq_puts(m, ",sys_immutable"); + if (opts->discard) + seq_puts(m, ",discard"); + if (opts->sparse) + seq_puts(m, ",sparse"); + if (opts->showmeta) + seq_puts(m, ",showmeta"); + if (opts->nohidden) + seq_puts(m, ",nohidden"); + if (opts->force) + seq_puts(m, ",force"); + if (opts->no_acs_rules) + seq_puts(m, ",no_acs_rules"); + if (opts->prealloc) + seq_puts(m, ",prealloc"); + if (sb->s_flags & SB_POSIXACL) + seq_puts(m, ",acl"); + if (sb->s_flags & SB_NOATIME) + seq_puts(m, ",noatime"); + + return 0; +} + +/*super_operations::sync_fs*/ +static int ntfs_sync_fs(struct super_block *sb, int wait) +{ + int err = 0, err2; + struct ntfs_sb_info *sbi = sb->s_fs_info; + struct ntfs_inode *ni; + struct inode *inode; + + ni = sbi->security.ni; + if (ni) { + inode = &ni->vfs_inode; + err2 = _ni_write_inode(inode, wait); + if (err2 && !err) + err = err2; + } + + ni = sbi->objid.ni; + if (ni) { + inode = &ni->vfs_inode; + err2 = _ni_write_inode(inode, wait); + if (err2 && !err) + err = err2; + } + + ni = sbi->reparse.ni; + if (ni) { + inode = &ni->vfs_inode; + err2 = _ni_write_inode(inode, wait); + if (err2 && !err) + err = err2; + } + + if (!err) + ntfs_set_state(sbi, NTFS_DIRTY_CLEAR); + + ntfs_update_mftmirr(sbi, wait); + + return err; +} + +static const struct super_operations ntfs_sops = { + .alloc_inode = ntfs_alloc_inode, + .destroy_inode = ntfs_destroy_inode, + .evict_inode = ntfs_evict_inode, + .put_super = ntfs_put_super, + .statfs = ntfs_statfs, + .show_options = ntfs_show_options, + .sync_fs = ntfs_sync_fs, + .remount_fs = ntfs_remount, + .write_inode = ntfs_write_inode, +}; + +static struct inode *ntfs_export_get_inode(struct super_block *sb, u64 ino, + u32 generation) +{ + struct MFT_REF ref; + struct inode *inode; + + ref.low = cpu_to_le32(ino); +#ifdef NTFS3_64BIT_CLUSTER + ref.high = cpu_to_le16(ino >> 32); +#else + ref.high = 0; +#endif + ref.seq = cpu_to_le16(generation); + + inode = ntfs_iget5(sb, &ref, NULL); + if (!IS_ERR(inode) && is_bad_inode(inode)) { + iput(inode); + inode = ERR_PTR(-ESTALE); + } + + return inode; +} + +static struct dentry *ntfs_fh_to_dentry(struct super_block *sb, struct fid *fid, + int fh_len, int fh_type) +{ + return generic_fh_to_dentry(sb, fid, fh_len, fh_type, + ntfs_export_get_inode); +} + +static struct dentry *ntfs_fh_to_parent(struct super_block *sb, struct fid *fid, + int fh_len, int fh_type) +{ + return generic_fh_to_parent(sb, fid, fh_len, fh_type, + ntfs_export_get_inode); +} + +/* TODO: == ntfs_sync_inode */ +static int ntfs_nfs_commit_metadata(struct inode *inode) +{ + return _ni_write_inode(inode, 1); +} + +static const struct export_operations ntfs_export_ops = { + .fh_to_dentry = ntfs_fh_to_dentry, + .fh_to_parent = ntfs_fh_to_parent, + .get_parent = ntfs_get_parent, + .commit_metadata = ntfs_nfs_commit_metadata, +}; + +/* Returns Gb,Mb to print with "%u.%02u Gb" */ +static u32 format_size_gb(const u64 bytes, u32 *mb) +{ + /* Do simple right 30 bit shift of 64 bit value */ + u64 kbytes = bytes >> 10; + u32 kbytes32 = (u32)kbytes; + + *mb = (100 * (kbytes32 & 0xfffff) + 0x7ffff) >> 20; + if (*mb >= 100) + *mb = 99; + + return (kbytes32 >> 20) | (((u32)(kbytes >> 32)) << 12); +} + +static u32 true_sectors_per_clst(const struct NTFS_BOOT *boot) +{ + return boot->sectors_per_clusters <= 0x80 ? + boot->sectors_per_clusters : + (1u << (0 - boot->sectors_per_clusters)); +} + +/* inits internal info from on-disk boot sector*/ +static int ntfs_init_from_boot(struct super_block *sb, u32 sector_size, + u64 dev_size) +{ + struct ntfs_sb_info *sbi = sb->s_fs_info; + int err; + u32 mb, gb, boot_sector_size, sct_per_clst, record_size; + u64 sectors, clusters, fs_size, mlcn, mlcn2; + struct NTFS_BOOT *boot; + struct buffer_head *bh; + struct MFT_REC *rec; + u16 fn, ao; + + sbi->volume.blocks = dev_size >> PAGE_SHIFT; + + bh = ntfs_bread(sb, 0); + if (!bh) + return -EIO; + + err = -EINVAL; + boot = (struct NTFS_BOOT *)bh->b_data; + + if (memcmp(boot->system_id, "NTFS ", sizeof("NTFS ") - 1)) + goto out; + + /* 0x55AA is not mandaroty. Thanks Maxim Suhanov*/ + /*if (0x55 != boot->boot_magic[0] || 0xAA != boot->boot_magic[1]) + * goto out; + */ + + boot_sector_size = (u32)boot->bytes_per_sector[1] << 8; + if (boot->bytes_per_sector[0] || boot_sector_size < SECTOR_SIZE || + !is_power_of2(boot_sector_size)) { + goto out; + } + + sct_per_clst = true_sectors_per_clst(boot); + if (!is_power_of2(sct_per_clst)) + goto out; + + mlcn = le64_to_cpu(boot->mft_clst); + mlcn2 = le64_to_cpu(boot->mft2_clst); + sectors = le64_to_cpu(boot->sectors_per_volume); + + if (mlcn * sct_per_clst >= sectors) + goto out; + + if (mlcn2 * sct_per_clst >= sectors) + goto out; + + /* Check MFT record size */ + if ((boot->record_size < 0 && + SECTOR_SIZE > (2U << (-boot->record_size))) || + (boot->record_size >= 0 && !is_power_of2(boot->record_size))) { + goto out; + } + + /* Check index record size */ + if ((boot->index_size < 0 && + SECTOR_SIZE > (2U << (-boot->index_size))) || + (boot->index_size >= 0 && !is_power_of2(boot->index_size))) { + goto out; + } + + sbi->sector_size = boot_sector_size; + sbi->sector_bits = blksize_bits(boot_sector_size); + fs_size = (sectors + 1) << sbi->sector_bits; + + gb = format_size_gb(fs_size, &mb); + + /* + * - Volume formatted and mounted with the same sector size + * - Volume formatted 4K and mounted as 512 + * - Volume formatted 512 and mounted as 4K + */ + if (sbi->sector_size != sector_size) { + ntfs_warn(sb, + "Different NTFS' sector size and media sector size"); + dev_size += sector_size - 1; + } + + sbi->cluster_size = boot_sector_size * sct_per_clst; + sbi->cluster_bits = blksize_bits(sbi->cluster_size); + + sbi->mft.lbo = mlcn << sbi->cluster_bits; + sbi->mft.lbo2 = mlcn2 << sbi->cluster_bits; + + if (sbi->cluster_size < sbi->sector_size) + goto out; + + sbi->cluster_mask = sbi->cluster_size - 1; + sbi->cluster_mask_inv = ~(u64)sbi->cluster_mask; + sbi->record_size = record_size = boot->record_size < 0 ? + 1 << (-boot->record_size) : + (u32)boot->record_size + << sbi->cluster_bits; + + if (record_size > MAXIMUM_BYTES_PER_MFT) + goto out; + + sbi->record_bits = blksize_bits(record_size); + sbi->attr_size_tr = (5 * record_size >> 4); // ~320 bytes + + sbi->max_bytes_per_attr = + record_size - QuadAlign(MFTRECORD_FIXUP_OFFSET_1) - + QuadAlign(((record_size >> SECTOR_SHIFT) * sizeof(short))) - + QuadAlign(sizeof(enum ATTR_TYPE)); + + sbi->index_size = boot->index_size < 0 ? + 1u << (-boot->index_size) : + (u32)boot->index_size << sbi->cluster_bits; + + sbi->volume.ser_num = le64_to_cpu(boot->serial_num); + sbi->volume.size = sectors << sbi->sector_bits; + + /* warning if RAW volume */ + if (dev_size < fs_size) { + u32 mb0, gb0; + + gb0 = format_size_gb(dev_size, &mb0); + ntfs_warn( + sb, + "RAW NTFS volume: Filesystem size %u.%02u Gb > volume size %u.%02u Gb. Mount in read-only", + gb, mb, gb0, mb0); + sb->s_flags |= SB_RDONLY; + } + + clusters = sbi->volume.size >> sbi->cluster_bits; +#ifdef NTFS3_64BIT_CLUSTER +#if BITS_PER_LONG < 64 +#error "NTFS3_64BIT_CLUSTER incompatible in 32 bit OS" +#endif +#else + /* 32 bits per cluster */ + if (clusters >> 32) { + ntfs_notice( + sb, + "NTFS %u.%02u Gb is too big to use 32 bits per cluster", + gb, mb); + goto out; + } +#endif + + sbi->used.bitmap.nbits = clusters; + + rec = ntfs_alloc(record_size, 1); + if (!rec) { + err = -ENOMEM; + goto out; + } + + sbi->new_rec = rec; + rec->rhdr.sign = NTFS_FILE_SIGNATURE; + rec->rhdr.fix_off = cpu_to_le16(MFTRECORD_FIXUP_OFFSET_1); + fn = (sbi->record_size >> SECTOR_SHIFT) + 1; + rec->rhdr.fix_num = cpu_to_le16(fn); + ao = QuadAlign(MFTRECORD_FIXUP_OFFSET_1 + sizeof(short) * fn); + rec->attr_off = cpu_to_le16(ao); + rec->used = cpu_to_le32(ao + QuadAlign(sizeof(enum ATTR_TYPE))); + rec->total = cpu_to_le32(sbi->record_size); + ((struct ATTRIB *)Add2Ptr(rec, ao))->type = ATTR_END; + + if (sbi->cluster_size < PAGE_SIZE) + sb_set_blocksize(sb, sbi->cluster_size); + + sbi->block_mask = sb->s_blocksize - 1; + sbi->blocks_per_cluster = sbi->cluster_size >> sb->s_blocksize_bits; + sbi->volume.blocks = sbi->volume.size >> sb->s_blocksize_bits; + + /* Maximum size for normal files */ + sbi->maxbytes = (clusters << sbi->cluster_bits) - 1; + +#ifdef NTFS3_64BIT_CLUSTER + if (clusters >= (1ull << (64 - sbi->cluster_bits))) + sbi->maxbytes = -1; + sbi->maxbytes_sparse = -1; +#else + /* Maximum size for sparse file */ + sbi->maxbytes_sparse = (1ull << (sbi->cluster_bits + 32)) - 1; +#endif + + err = 0; + +out: + brelse(bh); + + return err; +} + +/* try to mount*/ +static int ntfs_fill_super(struct super_block *sb, void *data, int silent) +{ + int err; + struct ntfs_sb_info *sbi; + struct block_device *bdev = sb->s_bdev; + struct inode *bd_inode = bdev->bd_inode; + struct request_queue *rq = bdev_get_queue(bdev); + struct inode *inode = NULL; + struct ntfs_inode *ni; + size_t i, tt; + CLST vcn, lcn, len; + struct ATTRIB *attr; + const struct VOLUME_INFO *info; + u32 idx, done, bytes; + struct ATTR_DEF_ENTRY *t; + u16 *upcase = NULL; + u16 *shared; + bool is_ro; + struct MFT_REF ref; + + ref.high = 0; + + sbi = ntfs_alloc(sizeof(struct ntfs_sb_info), true); + if (!sbi) + return -ENOMEM; + + sb->s_fs_info = sbi; + sbi->sb = sb; + sb->s_flags |= SB_NODIRATIME; + sb->s_magic = 0x7366746e; // "ntfs" + sb->s_op = &ntfs_sops; + sb->s_export_op = &ntfs_export_ops; + sb->s_time_gran = NTFS_TIME_GRAN; // 100 nsec + sb->s_xattr = ntfs_xattr_handlers; + sb->s_maxbytes = MAX_LFS_FILESIZE; + + ratelimit_state_init(&sbi->msg_ratelimit, DEFAULT_RATELIMIT_INTERVAL, + DEFAULT_RATELIMIT_BURST); + + err = ntfs_parse_options(sb, data, silent, &sbi->options); + if (err) + goto out; + + if (!rq || !blk_queue_discard(rq) || !rq->limits.discard_granularity) { + ; + } else { + sbi->discard_granularity = rq->limits.discard_granularity; + sbi->discard_granularity_mask_inv = + ~(u64)(sbi->discard_granularity - 1); + } + + sb_set_blocksize(sb, PAGE_SIZE); + + /* parse boot */ + err = ntfs_init_from_boot(sb, rq ? queue_logical_block_size(rq) : 512, + bd_inode->i_size); + if (err) + goto out; + + spin_lock_init(&sbi->compress.lock); + if (sbi->cluster_size <= NTFS_LZNT_MAX_CLUSTER) { + u32 bytes_per_frame = sbi->cluster_size << NTFS_LZNT_CUNIT; + + sbi->compress.frame_unc = ntfs_alloc(bytes_per_frame, 0); + if (!sbi->compress.frame_unc) { + err = -ENOMEM; + goto out; + } + + sbi->compress.ctx = get_compression_ctx(true); + if (!sbi->compress.ctx) { + err = -ENOMEM; + goto out; + } + } + + /* + * Load $Volume. This should be done before $LogFile + * 'cause 'sbi->volume.ni' is used 'ntfs_set_state' + */ + ref.low = cpu_to_le32(MFT_REC_VOL); + ref.seq = cpu_to_le16(MFT_REC_VOL); + inode = ntfs_iget5(sb, &ref, &NAME_VOLUME); + if (IS_ERR(inode)) { + err = PTR_ERR(inode); + ntfs_err(sb, "Failed to load $Volume."); + inode = NULL; + goto out; + } + + ni = ntfs_i(inode); + + /* Load and save label (not necessary) */ + attr = ni_find_attr(ni, NULL, NULL, ATTR_LABEL, NULL, 0, NULL, NULL); + + if (!attr) { + ; + } else if (!attr->non_res && !is_attr_ext(attr)) { + /* $AttrDef allows labels to be up to 128 symbols */ + err = utf16s_to_utf8s(resident_data(attr), + le32_to_cpu(attr->res.data_size) >> 1, + UTF16_LITTLE_ENDIAN, sbi->volume.label, + sizeof(sbi->volume.label)); + if (err < 0) + sbi->volume.label[0] = 0; + } else { + /* should we break mounting here? */ + //err = -EINVAL; + //goto out; + } + + attr = ni_find_attr(ni, attr, NULL, ATTR_VOL_INFO, NULL, 0, NULL, NULL); + if (!attr || is_attr_ext(attr)) { + err = -EINVAL; + goto out; + } + + info = resident_data_ex(attr, SIZEOF_ATTRIBUTE_VOLUME_INFO); + if (!info) { + err = -EINVAL; + goto out; + } + + sbi->volume.major_ver = info->major_ver; + sbi->volume.minor_ver = info->minor_ver; + sbi->volume.flags = info->flags; + + sbi->volume.ni = ni; + inode = NULL; + + /* Load $MFTMirr to estimate recs_mirr */ + ref.low = cpu_to_le32(MFT_REC_MIRR); + ref.seq = cpu_to_le16(MFT_REC_MIRR); + inode = ntfs_iget5(sb, &ref, &NAME_MIRROR); + if (IS_ERR(inode)) { + err = PTR_ERR(inode); + ntfs_err(sb, "Failed to load $MFTMirr."); + inode = NULL; + goto out; + } + + sbi->mft.recs_mirr = + ntfs_up_cluster(sbi, inode->i_size) >> sbi->record_bits; + + iput(inode); + + /* Load $LogFile to replay */ + ref.low = cpu_to_le32(MFT_REC_LOG); + ref.seq = cpu_to_le16(MFT_REC_LOG); + inode = ntfs_iget5(sb, &ref, &NAME_LOGFILE); + if (IS_ERR(inode)) { + err = PTR_ERR(inode); + ntfs_err(sb, "Failed to load $LogFile."); + inode = NULL; + goto out; + } + + ni = ntfs_i(inode); + + err = ntfs_loadlog_and_replay(ni, sbi); + if (err) + goto out; + + iput(inode); + inode = NULL; + + is_ro = sb_rdonly(sbi->sb); + + if (sbi->flags & NTFS_FLAGS_NEED_REPLAY) { + if (!is_ro) { + ntfs_warn(sb, + "failed to replay log file. Can't mount rw!"); + err = -EINVAL; + goto out; + } + } else if (sbi->volume.flags & VOLUME_FLAG_DIRTY) { + if (!is_ro && !sbi->options.force) { + ntfs_warn( + sb, + "volume is dirty and \"force\" flag is not set!"); + err = -EINVAL; + goto out; + } + } + + /* Load $MFT */ + ref.low = cpu_to_le32(MFT_REC_MFT); + ref.seq = cpu_to_le16(1); + + inode = ntfs_iget5(sb, &ref, &NAME_MFT); + if (IS_ERR(inode)) { + err = PTR_ERR(inode); + ntfs_err(sb, "Failed to load $MFT."); + inode = NULL; + goto out; + } + + ni = ntfs_i(inode); + + sbi->mft.used = ni->i_valid >> sbi->record_bits; + tt = inode->i_size >> sbi->record_bits; + sbi->mft.next_free = MFT_REC_USER; + + err = wnd_init(&sbi->mft.bitmap, sb, tt); + if (err) + goto out; + + err = ni_load_all_mi(ni); + if (err) + goto out; + + sbi->mft.ni = ni; + + /* Load $BadClus */ + ref.low = cpu_to_le32(MFT_REC_BADCLUST); + ref.seq = cpu_to_le16(MFT_REC_BADCLUST); + inode = ntfs_iget5(sb, &ref, &NAME_BADCLUS); + if (IS_ERR(inode)) { + err = PTR_ERR(inode); + ntfs_err(sb, "Failed to load $BadClus."); + inode = NULL; + goto out; + } + + ni = ntfs_i(inode); + + for (i = 0; run_get_entry(&ni->file.run, i, &vcn, &lcn, &len); i++) { + if (lcn == SPARSE_LCN) + continue; + + if (!sbi->bad_clusters) + ntfs_notice(sb, "Volume contains bad blocks"); + + sbi->bad_clusters += len; + } + + iput(inode); + + /* Load $Bitmap */ + ref.low = cpu_to_le32(MFT_REC_BITMAP); + ref.seq = cpu_to_le16(MFT_REC_BITMAP); + inode = ntfs_iget5(sb, &ref, &NAME_BITMAP); + if (IS_ERR(inode)) { + err = PTR_ERR(inode); + ntfs_err(sb, "Failed to load $Bitmap."); + inode = NULL; + goto out; + } + + ni = ntfs_i(inode); + +#ifndef NTFS3_64BIT_CLUSTER + if (inode->i_size >> 32) { + err = -EINVAL; + goto out; + } +#endif + + /* Check bitmap boundary */ + tt = sbi->used.bitmap.nbits; + if (inode->i_size < bitmap_size(tt)) { + err = -EINVAL; + goto out; + } + + /* Not necessary */ + sbi->used.bitmap.set_tail = true; + err = wnd_init(&sbi->used.bitmap, sbi->sb, tt); + if (err) + goto out; + + iput(inode); + + /* Compute the mft zone */ + err = ntfs_refresh_zone(sbi); + if (err) + goto out; + + /* Load $AttrDef */ + ref.low = cpu_to_le32(MFT_REC_ATTR); + ref.seq = cpu_to_le16(MFT_REC_ATTR); + inode = ntfs_iget5(sbi->sb, &ref, &NAME_ATTRDEF); + if (IS_ERR(inode)) { + err = PTR_ERR(inode); + ntfs_err(sb, "Failed to load $AttrDef -> %d", err); + inode = NULL; + goto out; + } + + if (inode->i_size < sizeof(struct ATTR_DEF_ENTRY)) { + err = -EINVAL; + goto out; + } + bytes = inode->i_size; + sbi->def_table = t = ntfs_alloc(bytes, 0); + if (!t) { + err = -ENOMEM; + goto out; + } + + for (done = idx = 0; done < bytes; done += PAGE_SIZE, idx++) { + unsigned long tail = bytes - done; + struct page *page = ntfs_map_page(inode->i_mapping, idx); + + if (IS_ERR(page)) { + err = PTR_ERR(page); + goto out; + } + memcpy(Add2Ptr(t, done), page_address(page), + min(PAGE_SIZE, tail)); + ntfs_unmap_page(page); + + if (!idx && ATTR_STD != t->type) { + err = -EINVAL; + goto out; + } + } + + t += 1; + sbi->def_entries = 1; + done = sizeof(struct ATTR_DEF_ENTRY); + sbi->reparse.max_size = MAXIMUM_REPARSE_DATA_BUFFER_SIZE; + + while (done + sizeof(struct ATTR_DEF_ENTRY) <= bytes) { + u32 t32 = le32_to_cpu(t->type); + + if ((t32 & 0xF) || le32_to_cpu(t[-1].type) >= t32) + break; + + if (t->type == ATTR_REPARSE) + sbi->reparse.max_size = le64_to_cpu(t->max_sz); + + done += sizeof(struct ATTR_DEF_ENTRY); + t += 1; + sbi->def_entries += 1; + } + iput(inode); + + /* Load $UpCase */ + ref.low = cpu_to_le32(MFT_REC_UPCASE); + ref.seq = cpu_to_le16(MFT_REC_UPCASE); + inode = ntfs_iget5(sb, &ref, &NAME_UPCASE); + if (IS_ERR(inode)) { + err = PTR_ERR(inode); + ntfs_err(sb, "Failed to load $LogFile."); + inode = NULL; + goto out; + } + + ni = ntfs_i(inode); + + if (inode->i_size != 0x10000 * sizeof(short)) { + err = -EINVAL; + goto out; + } + + sbi->upcase = upcase = ntfs_alloc(0x10000 * sizeof(short), 0); + if (!upcase) { + err = -ENOMEM; + goto out; + } + + for (idx = 0; idx < (0x10000 * sizeof(short) >> PAGE_SHIFT); idx++) { + const u16 *src; + u16 *dst = Add2Ptr(upcase, idx << PAGE_SHIFT); + struct page *page = ntfs_map_page(inode->i_mapping, idx); + + if (IS_ERR(page)) { + err = PTR_ERR(page); + goto out; + } + + src = page_address(page); + +#ifdef __BIG_ENDIAN + for (i = 0; i < PAGE_SIZE / sizeof(u16); i++) + *dst++ = le16_to_cpu(*src++); +#else + memcpy(dst, src, PAGE_SIZE); +#endif + ntfs_unmap_page(page); + } + + shared = ntfs_set_shared(upcase, 0x10000 * sizeof(short)); + if (shared && upcase != shared) { + sbi->upcase = shared; + ntfs_free(upcase); + } + + iput(inode); + inode = NULL; + + if (is_ntfs3(sbi)) { + /* Load $Secure */ + err = ntfs_security_init(sbi); + if (err) + goto out; + + /* Load $Extend */ + err = ntfs_extend_init(sbi); + if (err) + goto load_root; + + /* Load $Extend\$Reparse */ + err = ntfs_reparse_init(sbi); + if (err) + goto load_root; + + /* Load $Extend\$ObjId */ + err = ntfs_objid_init(sbi); + if (err) + goto load_root; + } + +load_root: + + /* Load root */ + ref.low = cpu_to_le32(MFT_REC_ROOT); + ref.seq = cpu_to_le16(MFT_REC_ROOT); + inode = ntfs_iget5(sb, &ref, &NAME_ROOT); + if (IS_ERR(inode)) { + err = PTR_ERR(inode); + ntfs_err(sb, "Failed to load root."); + inode = NULL; + goto out; + } + + ni = ntfs_i(inode); + + sb->s_root = d_make_root(inode); + + if (!sb->s_root) { + err = -EINVAL; + goto out; + } + + return 0; + +out: + iput(inode); + + if (sb->s_root) { + d_drop(sb->s_root); + sb->s_root = NULL; + } + + put_ntfs(sbi); + + sb->s_fs_info = NULL; + return err; +} + +void ntfs_unmap_meta(struct super_block *sb, CLST lcn, CLST len) +{ + struct ntfs_sb_info *sbi = sb->s_fs_info; + struct block_device *bdev = sb->s_bdev; + sector_t devblock = (u64)lcn * sbi->blocks_per_cluster; + unsigned long blocks = (u64)len * sbi->blocks_per_cluster; + unsigned long cnt = 0; + unsigned long limit = global_zone_page_state(NR_FREE_PAGES) + << (PAGE_SHIFT - sb->s_blocksize_bits); + + if (limit >= 0x2000) + limit -= 0x1000; + else if (limit < 32) + limit = 32; + else + limit >>= 1; + + while (blocks--) { + clean_bdev_aliases(bdev, devblock++, 1); + if (cnt++ >= limit) { + sync_blockdev(bdev); + cnt = 0; + } + } +} + +/* + * ntfs_discard + * + * issue a discard request (trim for SSD) + */ +int ntfs_discard(struct ntfs_sb_info *sbi, CLST lcn, CLST len) +{ + int err; + u64 lbo, bytes, start, end; + struct super_block *sb; + + if (sbi->used.next_free_lcn == lcn + len) + sbi->used.next_free_lcn = lcn; + + if (sbi->flags & NTFS_FLAGS_NODISCARD) + return -EOPNOTSUPP; + + if (!sbi->options.discard) + return -EOPNOTSUPP; + + lbo = (u64)lcn << sbi->cluster_bits; + bytes = (u64)len << sbi->cluster_bits; + + /* Align up 'start' on discard_granularity */ + start = (lbo + sbi->discard_granularity - 1) & + sbi->discard_granularity_mask_inv; + /* Align down 'end' on discard_granularity */ + end = (lbo + bytes) & sbi->discard_granularity_mask_inv; + + sb = sbi->sb; + if (start >= end) + return 0; + + err = blkdev_issue_discard(sb->s_bdev, start >> 9, (end - start) >> 9, + GFP_NOFS, 0); + + if (err == -EOPNOTSUPP) + sbi->flags |= NTFS_FLAGS_NODISCARD; + + return err; +} + +static struct dentry *ntfs_mount(struct file_system_type *fs_type, int flags, + const char *dev_name, void *data) +{ + return mount_bdev(fs_type, flags, dev_name, data, ntfs_fill_super); +} + +static struct file_system_type ntfs_fs_type = { + .owner = THIS_MODULE, + .name = "ntfs3", + .mount = ntfs_mount, + .kill_sb = kill_block_super, + .fs_flags = FS_REQUIRES_DEV, +}; + +static int __init init_ntfs_fs(void) +{ + int err; + +#ifdef NTFS3_INDEX_BINARY_SEARCH + pr_notice("ntfs3: +index binary search"); +#endif + +#ifdef NTFS3_CHECK_FREE_CLST + pr_notice("ntfs3: +check free clusters"); +#endif + +#if NTFS_LINK_MAX < 0xffff + pr_notice("ntfs3: max link count %u", NTFS_LINK_MAX); +#endif + +#ifdef NTFS3_64BIT_CLUSTER + pr_notice("ntfs3: 64 bits per cluster"); +#else + pr_notice("ntfs3: 32 bits per cluster"); +#endif + + ntfs_inode_cachep = kmem_cache_create( + "ntfs_inode_cache", sizeof(struct ntfs_inode), 0, + (SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD | SLAB_ACCOUNT), + init_once); + if (!ntfs_inode_cachep) { + err = -ENOMEM; + goto failed; + } + + err = register_filesystem(&ntfs_fs_type); + if (!err) + return 0; + +failed: + return err; +} + +static void __exit exit_ntfs_fs(void) +{ + if (ntfs_inode_cachep) { + rcu_barrier(); + kmem_cache_destroy(ntfs_inode_cachep); + } + + unregister_filesystem(&ntfs_fs_type); +} + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("ntfs3 filesystem"); +MODULE_AUTHOR("Konstantin Komarov"); +MODULE_ALIAS_FS("ntfs3"); + +module_init(init_ntfs_fs); +module_exit(exit_ntfs_fs); From patchwork Fri Oct 9 14:22:54 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Konstantin Komarov X-Patchwork-Id: 11825951 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 04AB91744 for ; Fri, 9 Oct 2020 14:23:38 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id C61A4222B9 for ; Fri, 9 Oct 2020 14:23:37 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (1024-bit key) header.d=paragon-software.com header.i=@paragon-software.com header.b="bLrHjtcx" Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S2388740AbgJIOXY (ORCPT ); Fri, 9 Oct 2020 10:23:24 -0400 Received: from relaydlg-01.paragon-software.com ([81.5.88.159]:42910 "EHLO relaydlg-01.paragon-software.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1732056AbgJIOXR (ORCPT ); Fri, 9 Oct 2020 10:23:17 -0400 Received: from dlg2.mail.paragon-software.com (vdlg-exch-02.paragon-software.com [172.30.1.105]) by relaydlg-01.paragon-software.com (Postfix) with ESMTPS id 9667D8237D; Fri, 9 Oct 2020 17:23:08 +0300 (MSK) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=paragon-software.com; s=mail; t=1602253388; bh=kSWB7McBh6rAvVlaUe3Z4KodjULwZfdtwK+g4zsN2IA=; h=From:To:CC:Subject:Date:In-Reply-To:References; b=bLrHjtcxFZ8qmm+yp9Fb+Eo9+DZOxJ36IhAF3vkoyXnjDVE43+73RCGGUWiKLAbcT 0S2JOB3E/uSmRDMZ4DSPvE5ggszFVqUQGF4cjhWpJTybOKHPTqNpWlXAB2QmErq/PX X/bZm4YlCtA9Crf5/FJd9WyQufDKEdH44wHifwp8= Received: from fsd-lkpg.ufsd.paragon-software.com (172.30.114.105) by vdlg-exch-02.paragon-software.com (172.30.1.105) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id 15.1.1847.3; Fri, 9 Oct 2020 17:23:08 +0300 From: Konstantin Komarov To: CC: , , , , , , , , , , , , Konstantin Komarov Subject: [PATCH v8 03/10] fs/ntfs3: Add bitmap Date: Fri, 9 Oct 2020 17:22:54 +0300 Message-ID: <20201009142301.412454-4-almaz.alexandrovich@paragon-software.com> X-Mailer: git-send-email 2.25.4 In-Reply-To: <20201009142301.412454-1-almaz.alexandrovich@paragon-software.com> References: <20201009142301.412454-1-almaz.alexandrovich@paragon-software.com> MIME-Version: 1.0 X-Originating-IP: [172.30.114.105] X-ClientProxiedBy: vdlg-exch-02.paragon-software.com (172.30.1.105) To vdlg-exch-02.paragon-software.com (172.30.1.105) Precedence: bulk List-ID: X-Mailing-List: linux-fsdevel@vger.kernel.org This adds bitmap Signed-off-by: Konstantin Komarov --- fs/ntfs3/bitfunc.c | 137 ++++ fs/ntfs3/bitmap.c | 1508 ++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 1645 insertions(+) create mode 100644 fs/ntfs3/bitfunc.c create mode 100644 fs/ntfs3/bitmap.c diff --git a/fs/ntfs3/bitfunc.c b/fs/ntfs3/bitfunc.c new file mode 100644 index 000000000000..b19972177535 --- /dev/null +++ b/fs/ntfs3/bitfunc.c @@ -0,0 +1,137 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * linux/fs/ntfs3/bitfunc.c + * + * Copyright (C) 2019-2020 Paragon Software GmbH, All rights reserved. + * + */ +#include +#include +#include +#include +#include + +#include "debug.h" +#include "ntfs.h" +#include "ntfs_fs.h" + +#define BITS_IN_SIZE_T (sizeof(size_t) * 8) + +/* + * fill_mask[i] - first i bits are '1' , i = 0,1,2,3,4,5,6,7,8 + * fill_mask[i] = 0xFF >> (8-i) + */ +static const u8 fill_mask[] = { 0x00, 0x01, 0x03, 0x07, 0x0F, + 0x1F, 0x3F, 0x7F, 0xFF }; + +/* + * zero_mask[i] - first i bits are '0' , i = 0,1,2,3,4,5,6,7,8 + * zero_mask[i] = 0xFF << i + */ +static const u8 zero_mask[] = { 0xFF, 0xFE, 0xFC, 0xF8, 0xF0, + 0xE0, 0xC0, 0x80, 0x00 }; + +/* + * are_bits_clear + * + * Returns true if all bits [bit, bit+nbits) are zeros "0" + */ +bool are_bits_clear(const ulong *lmap, size_t bit, size_t nbits) +{ + size_t pos = bit & 7; + const u8 *map = (u8 *)lmap + (bit >> 3); + + if (pos) { + if (8 - pos >= nbits) + return !nbits || !(*map & fill_mask[pos + nbits] & + zero_mask[pos]); + + if (*map++ & zero_mask[pos]) + return false; + nbits -= 8 - pos; + } + + pos = ((size_t)map) & (sizeof(size_t) - 1); + if (pos) { + pos = sizeof(size_t) - pos; + if (nbits >= pos * 8) { + for (nbits -= pos * 8; pos; pos--, map++) { + if (*map) + return false; + } + } + } + + for (pos = nbits / BITS_IN_SIZE_T; pos; pos--, map += sizeof(size_t)) { + if (*((size_t *)map)) + return false; + } + + for (pos = (nbits % BITS_IN_SIZE_T) >> 3; pos; pos--, map++) { + if (*map) + return false; + } + + pos = nbits & 7; + if (pos && (*map & fill_mask[pos])) + return false; + + // All bits are zero + return true; +} + +/* + * are_bits_set + * + * Returns true if all bits [bit, bit+nbits) are ones "1" + */ +bool are_bits_set(const ulong *lmap, size_t bit, size_t nbits) +{ + u8 mask; + size_t pos = bit & 7; + const u8 *map = (u8 *)lmap + (bit >> 3); + + if (pos) { + if (8 - pos >= nbits) { + mask = fill_mask[pos + nbits] & zero_mask[pos]; + return !nbits || (*map & mask) == mask; + } + + mask = zero_mask[pos]; + if ((*map++ & mask) != mask) + return false; + nbits -= 8 - pos; + } + + pos = ((size_t)map) & (sizeof(size_t) - 1); + if (pos) { + pos = sizeof(size_t) - pos; + if (nbits >= pos * 8) { + for (nbits -= pos * 8; pos; pos--, map++) { + if (*map != 0xFF) + return false; + } + } + } + + for (pos = nbits / BITS_IN_SIZE_T; pos; pos--, map += sizeof(size_t)) { + if (*((size_t *)map) != MINUS_ONE_T) + return false; + } + + for (pos = (nbits % BITS_IN_SIZE_T) >> 3; pos; pos--, map++) { + if (*map != 0xFF) + return false; + } + + pos = nbits & 7; + if (pos) { + u8 mask = fill_mask[pos]; + + if ((*map & mask) != mask) + return false; + } + + // All bits are ones + return true; +} diff --git a/fs/ntfs3/bitmap.c b/fs/ntfs3/bitmap.c new file mode 100644 index 000000000000..c5fbdd0a3b1f --- /dev/null +++ b/fs/ntfs3/bitmap.c @@ -0,0 +1,1508 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * linux/fs/ntfs3/bitmap.c + * + * Copyright (C) 2019-2020 Paragon Software GmbH, All rights reserved. + * + */ + +#include +#include +#include +#include +#include + +#include "debug.h" +#include "ntfs.h" +#include "ntfs_fs.h" + +struct rb_node_key { + struct rb_node node; + size_t key; +}; + +/* + * Tree is sorted by start (key) + */ +struct e_node { + struct rb_node_key start; /* Tree sorted by start */ + struct rb_node_key count; /* Tree sorted by len*/ +}; + +static int wnd_rescan(struct wnd_bitmap *wnd); +static struct buffer_head *wnd_map(struct wnd_bitmap *wnd, size_t iw); +static bool wnd_is_free_hlp(struct wnd_bitmap *wnd, size_t bit, size_t bits); + +static inline u32 wnd_bits(const struct wnd_bitmap *wnd, size_t i) +{ + return i + 1 == wnd->nwnd ? wnd->bits_last : wnd->sb->s_blocksize * 8; +} + +/* + * b_pos + b_len - biggest fragment + * Scan range [wpos wbits) window 'buf' + * Returns -1 if not found + */ +static size_t wnd_scan(const ulong *buf, size_t wbit, u32 wpos, u32 wend, + size_t to_alloc, size_t *prev_tail, size_t *b_pos, + size_t *b_len) +{ + while (wpos < wend) { + size_t free_len; + u32 free_bits, end; + u32 used = find_next_zero_bit(buf, wend, wpos); + + if (used >= wend) { + if (*b_len < *prev_tail) { + *b_pos = wbit - *prev_tail; + *b_len = *prev_tail; + } + + *prev_tail = 0; + return -1; + } + + if (used > wpos) { + wpos = used; + if (*b_len < *prev_tail) { + *b_pos = wbit - *prev_tail; + *b_len = *prev_tail; + } + + *prev_tail = 0; + } + + /* + * Now we have a fragment [wpos, wend) staring with 0 + */ + end = wpos + to_alloc - *prev_tail; + free_bits = find_next_bit(buf, min(end, wend), wpos); + + free_len = *prev_tail + free_bits - wpos; + + if (*b_len < free_len) { + *b_pos = wbit + wpos - *prev_tail; + *b_len = free_len; + } + + if (free_len >= to_alloc) + return wbit + wpos - *prev_tail; + + if (free_bits >= wend) { + *prev_tail += free_bits - wpos; + return -1; + } + + wpos = free_bits + 1; + + *prev_tail = 0; + } + + return -1; +} + +/* + * wnd_close + * + * + */ +void wnd_close(struct wnd_bitmap *wnd) +{ + struct rb_node *node, *next; + + if (wnd->free_bits != wnd->free_holder) + ntfs_free(wnd->free_bits); + run_close(&wnd->run); + + node = rb_first(&wnd->start_tree); + + while (node) { + next = rb_next(node); + rb_erase(node, &wnd->start_tree); + ntfs_free(rb_entry(node, struct e_node, start.node)); + node = next; + } +} + +static struct rb_node *rb_lookup(struct rb_root *root, size_t v) +{ + struct rb_node **p = &root->rb_node; + struct rb_node *r = NULL; + + while (*p) { + struct rb_node_key *k; + + k = rb_entry(*p, struct rb_node_key, node); + if (v < k->key) { + p = &(*p)->rb_left; + } else if (v > k->key) { + r = &k->node; + p = &(*p)->rb_right; + } else { + return &k->node; + } + } + + return r; +} + +/* + * rb_insert_count + * + * Helper function to insert special kind of 'count' tree + */ +static inline bool rb_insert_count(struct rb_root *root, struct e_node *e) +{ + struct rb_node **p = &root->rb_node; + struct rb_node *parent = NULL; + size_t e_ckey = e->count.key; + size_t e_skey = e->start.key; + + while (*p) { + struct e_node *k = + rb_entry(parent = *p, struct e_node, count.node); + + if (e_ckey > k->count.key) { + p = &(*p)->rb_left; + } else if (e_ckey < k->count.key) { + p = &(*p)->rb_right; + } else if (e_skey < k->start.key) { + p = &(*p)->rb_left; + } else if (e_skey > k->start.key) { + p = &(*p)->rb_right; + } else { + WARN_ON(1); + return false; + } + } + + rb_link_node(&e->count.node, parent, p); + rb_insert_color(&e->count.node, root); + return true; +} + +/* + * inline bool rb_insert_start + * + * Helper function to insert special kind of 'count' tree + */ +static inline bool rb_insert_start(struct rb_root *root, struct e_node *e) +{ + struct rb_node **p = &root->rb_node; + struct rb_node *parent = NULL; + size_t e_skey = e->start.key; + + while (*p) { + struct e_node *k; + + parent = *p; + + k = rb_entry(parent, struct e_node, start.node); + if (e_skey < k->start.key) { + p = &(*p)->rb_left; + } else if (e_skey > k->start.key) { + p = &(*p)->rb_right; + } else { + WARN_ON(1); + return false; + } + } + + rb_link_node(&e->start.node, parent, p); + rb_insert_color(&e->start.node, root); + return true; +} + +#define NTFS_MAX_WND_EXTENTS (32u * 1024u) + +/* + * wnd_add_free_ext + * + * adds a new extent of free space + * build = 1 when building tree + */ +static void wnd_add_free_ext(struct wnd_bitmap *wnd, size_t bit, size_t len, + bool build) +{ + struct e_node *e, *e0 = NULL; + size_t ib, end_in = bit + len; + struct rb_node *n; + + if (build) { + /* Use extent_min to filter too short extents */ + if (wnd->count >= NTFS_MAX_WND_EXTENTS && + len <= wnd->extent_min) { + wnd->uptodated = -1; + return; + } + } else { + /* Try to find extent before 'bit' */ + n = rb_lookup(&wnd->start_tree, bit); + + if (!n) { + n = rb_first(&wnd->start_tree); + } else { + e = rb_entry(n, struct e_node, start.node); + n = rb_next(n); + if (e->start.key + e->count.key == bit) { + /* Remove left */ + bit = e->start.key; + len += e->count.key; + rb_erase(&e->start.node, &wnd->start_tree); + rb_erase(&e->count.node, &wnd->count_tree); + wnd->count -= 1; + e0 = e; + } + } + + while (n) { + size_t next_end; + + e = rb_entry(n, struct e_node, start.node); + next_end = e->start.key + e->count.key; + if (e->start.key > end_in) + break; + + /* Remove right */ + n = rb_next(n); + len += next_end - end_in; + end_in = next_end; + rb_erase(&e->start.node, &wnd->start_tree); + rb_erase(&e->count.node, &wnd->count_tree); + wnd->count -= 1; + + if (!e0) + e0 = e; + else + ntfs_free(e); + } + + if (wnd->uptodated != 1) { + /* Check bits before 'bit' */ + ib = wnd->zone_bit == wnd->zone_end || + bit < wnd->zone_end ? + 0 : + wnd->zone_end; + + while (bit > ib && wnd_is_free_hlp(wnd, bit - 1, 1)) { + bit -= 1; + len += 1; + } + + /* Check bits after 'end_in' */ + ib = wnd->zone_bit == wnd->zone_end || + end_in > wnd->zone_bit ? + wnd->nbits : + wnd->zone_bit; + + while (end_in < ib && wnd_is_free_hlp(wnd, end_in, 1)) { + end_in += 1; + len += 1; + } + } + } + /* Insert new fragment */ + if (wnd->count >= NTFS_MAX_WND_EXTENTS) { + if (e0) + ntfs_free(e0); + + wnd->uptodated = -1; + + /* Compare with smallest fragment */ + n = rb_last(&wnd->count_tree); + e = rb_entry(n, struct e_node, count.node); + if (len <= e->count.key) + goto out; /* Do not insert small fragments */ + + if (build) { + struct e_node *e2; + + n = rb_prev(n); + e2 = rb_entry(n, struct e_node, count.node); + /* smallest fragment will be 'e2->count.key' */ + wnd->extent_min = e2->count.key; + } + + /* Replace smallest fragment by new one */ + rb_erase(&e->start.node, &wnd->start_tree); + rb_erase(&e->count.node, &wnd->count_tree); + wnd->count -= 1; + } else { + e = e0 ? e0 : ntfs_alloc(sizeof(struct e_node), 0); + if (!e) { + wnd->uptodated = -1; + goto out; + } + + if (build && len <= wnd->extent_min) + wnd->extent_min = len; + } + e->start.key = bit; + e->count.key = len; + if (len > wnd->extent_max) + wnd->extent_max = len; + + rb_insert_start(&wnd->start_tree, e); + rb_insert_count(&wnd->count_tree, e); + wnd->count += 1; + +out:; +} + +/* + * wnd_remove_free_ext + * + * removes a run from the cached free space + */ +static void wnd_remove_free_ext(struct wnd_bitmap *wnd, size_t bit, size_t len) +{ + struct rb_node *n, *n3; + struct e_node *e, *e3; + size_t end_in = bit + len; + size_t end3, end, new_key, new_len, max_new_len; + + /* Try to find extent before 'bit' */ + n = rb_lookup(&wnd->start_tree, bit); + + if (!n) + return; + + e = rb_entry(n, struct e_node, start.node); + end = e->start.key + e->count.key; + + new_key = new_len = 0; + len = e->count.key; + + /* Range [bit,end_in) must be inside 'e' or outside 'e' and 'n' */ + if (e->start.key > bit) + ; + else if (end_in <= end) { + /* Range [bit,end_in) inside 'e' */ + new_key = end_in; + new_len = end - end_in; + len = bit - e->start.key; + } else if (bit > end) { + bool bmax = false; + + n3 = rb_next(n); + + while (n3) { + e3 = rb_entry(n3, struct e_node, start.node); + if (e3->start.key >= end_in) + break; + + if (e3->count.key == wnd->extent_max) + bmax = true; + + end3 = e3->start.key + e3->count.key; + if (end3 > end_in) { + e3->start.key = end_in; + rb_erase(&e3->count.node, &wnd->count_tree); + e3->count.key = end3 - end_in; + rb_insert_count(&wnd->count_tree, e3); + break; + } + + n3 = rb_next(n3); + rb_erase(&e3->start.node, &wnd->start_tree); + rb_erase(&e3->count.node, &wnd->count_tree); + wnd->count -= 1; + ntfs_free(e3); + } + if (!bmax) + return; + n3 = rb_first(&wnd->count_tree); + wnd->extent_max = + n3 ? rb_entry(n3, struct e_node, count.node)->count.key : + 0; + return; + } + + if (e->count.key != wnd->extent_max) { + ; + } else if (rb_prev(&e->count.node)) { + ; + } else { + n3 = rb_next(&e->count.node); + max_new_len = len > new_len ? len : new_len; + if (!n3) { + wnd->extent_max = max_new_len; + } else { + e3 = rb_entry(n3, struct e_node, count.node); + wnd->extent_max = max(e3->count.key, max_new_len); + } + } + + if (!len) { + if (new_len) { + e->start.key = new_key; + rb_erase(&e->count.node, &wnd->count_tree); + e->count.key = new_len; + rb_insert_count(&wnd->count_tree, e); + } else { + rb_erase(&e->start.node, &wnd->start_tree); + rb_erase(&e->count.node, &wnd->count_tree); + wnd->count -= 1; + ntfs_free(e); + } + goto out; + } + rb_erase(&e->count.node, &wnd->count_tree); + e->count.key = len; + rb_insert_count(&wnd->count_tree, e); + + if (!new_len) + goto out; + + if (wnd->count >= NTFS_MAX_WND_EXTENTS) { + wnd->uptodated = -1; + + /* Get minimal extent */ + e = rb_entry(rb_last(&wnd->count_tree), struct e_node, + count.node); + if (e->count.key > new_len) + goto out; + + /* Replace minimum */ + rb_erase(&e->start.node, &wnd->start_tree); + rb_erase(&e->count.node, &wnd->count_tree); + wnd->count -= 1; + } else { + e = ntfs_alloc(sizeof(struct e_node), 0); + if (!e) + wnd->uptodated = -1; + } + + if (e) { + e->start.key = new_key; + e->count.key = new_len; + rb_insert_start(&wnd->start_tree, e); + rb_insert_count(&wnd->count_tree, e); + wnd->count += 1; + } + +out: + if (!wnd->count && 1 != wnd->uptodated) + wnd_rescan(wnd); +} + +/* + * wnd_rescan + * + * Scan all bitmap. used while initialization. + */ +static int wnd_rescan(struct wnd_bitmap *wnd) +{ + int err = 0; + size_t prev_tail = 0; + struct super_block *sb = wnd->sb; + struct ntfs_sb_info *sbi = sb->s_fs_info; + u64 lbo, len = 0; + u32 blocksize = sb->s_blocksize; + u8 cluster_bits = sbi->cluster_bits; + u32 wbits = 8 * sb->s_blocksize; + u32 used, frb; + const ulong *buf; + size_t wpos, wbit, iw, vbo; + struct buffer_head *bh = NULL; + CLST lcn, clen; + + wnd->uptodated = 0; + wnd->extent_max = 0; + wnd->extent_min = MINUS_ONE_T; + wnd->total_zeroes = 0; + + vbo = 0; + + for (iw = 0; iw < wnd->nwnd; iw++) { + if (iw + 1 == wnd->nwnd) + wbits = wnd->bits_last; + + if (wnd->inited) { + if (!wnd->free_bits[iw]) { + /* all ones */ + if (prev_tail) { + wnd_add_free_ext(wnd, + vbo * 8 - prev_tail, + prev_tail, true); + prev_tail = 0; + } + goto next_wnd; + } + if (wbits == wnd->free_bits[iw]) { + /* all zeroes */ + prev_tail += wbits; + wnd->total_zeroes += wbits; + goto next_wnd; + } + } + + if (!len) { + if (!run_lookup_entry(&wnd->run, vbo >> cluster_bits, + &lcn, &clen, NULL)) { + err = -ENOENT; + goto out; + } + + lbo = (u64)lcn << cluster_bits; + len = (u64)clen << cluster_bits; + } + + bh = ntfs_bread(sb, lbo >> sb->s_blocksize_bits); + if (!bh) { + err = -EIO; + goto out; + } + + buf = (ulong *)bh->b_data; + + used = __bitmap_weight(buf, wbits); + if (used < wbits) { + frb = wbits - used; + wnd->free_bits[iw] = frb; + wnd->total_zeroes += frb; + } + + wpos = 0; + wbit = vbo * 8; + + if (wbit + wbits > wnd->nbits) + wbits = wnd->nbits - wbit; + + do { + used = find_next_zero_bit(buf, wbits, wpos); + + if (used > wpos && prev_tail) { + wnd_add_free_ext(wnd, wbit + wpos - prev_tail, + prev_tail, true); + prev_tail = 0; + } + + wpos = used; + + if (wpos >= wbits) { + /* No free blocks */ + prev_tail = 0; + break; + } + + frb = find_next_bit(buf, wbits, wpos); + if (frb >= wbits) { + /* keep last free block */ + prev_tail += frb - wpos; + break; + } + + wnd_add_free_ext(wnd, wbit + wpos - prev_tail, + frb + prev_tail - wpos, true); + + /* Skip free block and first '1' */ + wpos = frb + 1; + /* Reset previous tail */ + prev_tail = 0; + } while (wpos < wbits); + +next_wnd: + + if (bh) + put_bh(bh); + bh = NULL; + + vbo += blocksize; + if (len) { + len -= blocksize; + lbo += blocksize; + } + } + + /* Add last block */ + if (prev_tail) + wnd_add_free_ext(wnd, wnd->nbits - prev_tail, prev_tail, true); + + /* + * Before init cycle wnd->uptodated was 0 + * If any errors or limits occurs while initialization then + * wnd->uptodated will be -1 + * If 'uptodated' is still 0 then Tree is really updated + */ + if (!wnd->uptodated) + wnd->uptodated = 1; + + if (wnd->zone_bit != wnd->zone_end) { + size_t zlen = wnd->zone_end - wnd->zone_bit; + + wnd->zone_end = wnd->zone_bit; + wnd_zone_set(wnd, wnd->zone_bit, zlen); + } + +out: + return err; +} + +/* + * wnd_init + */ +int wnd_init(struct wnd_bitmap *wnd, struct super_block *sb, size_t nbits) +{ + int err; + u32 blocksize = sb->s_blocksize; + u32 wbits = blocksize * 8; + + init_rwsem(&wnd->rw_lock); + + wnd->sb = sb; + wnd->nbits = nbits; + wnd->total_zeroes = nbits; + wnd->extent_max = MINUS_ONE_T; + wnd->zone_bit = wnd->zone_end = 0; + wnd->nwnd = bytes_to_block(sb, bitmap_size(nbits)); + wnd->bits_last = nbits & (wbits - 1); + if (!wnd->bits_last) + wnd->bits_last = wbits; + + if (wnd->nwnd <= ARRAY_SIZE(wnd->free_holder)) { + wnd->free_bits = wnd->free_holder; + } else { + wnd->free_bits = ntfs_alloc(wnd->nwnd * sizeof(u16), 1); + if (!wnd->free_bits) + return -ENOMEM; + } + + err = wnd_rescan(wnd); + if (err) + return err; + + wnd->inited = true; + + return 0; +} + +/* + * wnd_map + * + * call sb_bread for requested window + */ +static struct buffer_head *wnd_map(struct wnd_bitmap *wnd, size_t iw) +{ + size_t vbo; + CLST lcn, clen; + struct super_block *sb = wnd->sb; + struct ntfs_sb_info *sbi; + struct buffer_head *bh; + u64 lbo; + + sbi = sb->s_fs_info; + vbo = (u64)iw << sb->s_blocksize_bits; + + if (!run_lookup_entry(&wnd->run, vbo >> sbi->cluster_bits, &lcn, &clen, + NULL)) { + return ERR_PTR(-ENOENT); + } + + lbo = ((u64)lcn << sbi->cluster_bits) + (vbo & sbi->cluster_mask); + + bh = ntfs_bread(wnd->sb, lbo >> sb->s_blocksize_bits); + + if (!bh) + return ERR_PTR(-EIO); + + return bh; +} + +/* + * wnd_set_free + * + * Marks the bits range from bit to bit + bits as free + */ +int wnd_set_free(struct wnd_bitmap *wnd, size_t bit, size_t bits) +{ + int err = 0; + struct super_block *sb = wnd->sb; + size_t bits0 = bits; + u32 wbits = 8 * sb->s_blocksize; + size_t iw = bit >> (sb->s_blocksize_bits + 3); + u32 wbit = bit & (wbits - 1); + struct buffer_head *bh; + + while (iw < wnd->nwnd && bits) { + u32 tail, op; + ulong *buf; + + if (iw + 1 == wnd->nwnd) + wbits = wnd->bits_last; + + tail = wbits - wbit; + op = tail < bits ? tail : bits; + + bh = wnd_map(wnd, iw); + if (IS_ERR(bh)) { + err = PTR_ERR(bh); + break; + } + + buf = (ulong *)bh->b_data; + + lock_buffer(bh); + + __bitmap_clear(buf, wbit, op); + + wnd->free_bits[iw] += op; + + set_buffer_uptodate(bh); + mark_buffer_dirty(bh); + unlock_buffer(bh); + put_bh(bh); + + wnd->total_zeroes += op; + bits -= op; + wbit = 0; + iw += 1; + } + + wnd_add_free_ext(wnd, bit, bits0, false); + + return err; +} + +/* + * wnd_set_used + * + * Marks the bits range from bit to bit + bits as used + */ +int wnd_set_used(struct wnd_bitmap *wnd, size_t bit, size_t bits) +{ + int err = 0; + struct super_block *sb = wnd->sb; + size_t bits0 = bits; + size_t iw = bit >> (sb->s_blocksize_bits + 3); + u32 wbits = 8 * sb->s_blocksize; + u32 wbit = bit & (wbits - 1); + struct buffer_head *bh; + + while (iw < wnd->nwnd && bits) { + u32 tail, op; + ulong *buf; + + if (unlikely(iw + 1 == wnd->nwnd)) + wbits = wnd->bits_last; + + tail = wbits - wbit; + op = tail < bits ? tail : bits; + + bh = wnd_map(wnd, iw); + if (IS_ERR(bh)) { + err = PTR_ERR(bh); + break; + } + buf = (ulong *)bh->b_data; + + lock_buffer(bh); + + __bitmap_set(buf, wbit, op); + wnd->free_bits[iw] -= op; + + set_buffer_uptodate(bh); + mark_buffer_dirty(bh); + unlock_buffer(bh); + put_bh(bh); + + wnd->total_zeroes -= op; + bits -= op; + wbit = 0; + iw += 1; + } + + if (!RB_EMPTY_ROOT(&wnd->start_tree)) + wnd_remove_free_ext(wnd, bit, bits0); + + return err; +} + +/* + * wnd_is_free_hlp + * + * Returns true if all clusters [bit, bit+bits) are free (bitmap only) + */ +static bool wnd_is_free_hlp(struct wnd_bitmap *wnd, size_t bit, size_t bits) +{ + struct super_block *sb = wnd->sb; + size_t iw = bit >> (sb->s_blocksize_bits + 3); + u32 wbits = 8 * sb->s_blocksize; + u32 wbit = bit & (wbits - 1); + + while (iw < wnd->nwnd && bits) { + u32 tail, op; + + if (unlikely(iw + 1 == wnd->nwnd)) + wbits = wnd->bits_last; + + tail = wbits - wbit; + op = tail < bits ? tail : bits; + + if (wbits != wnd->free_bits[iw]) { + bool ret; + struct buffer_head *bh = wnd_map(wnd, iw); + + if (IS_ERR(bh)) + return false; + + ret = are_bits_clear((ulong *)bh->b_data, wbit, op); + + put_bh(bh); + if (!ret) + return false; + } + + bits -= op; + wbit = 0; + iw += 1; + } + + return true; +} + +/* + * wnd_is_free + * + * Returns true if all clusters [bit, bit+bits) are free + */ +bool wnd_is_free(struct wnd_bitmap *wnd, size_t bit, size_t bits) +{ + bool ret; + struct rb_node *n; + size_t end; + struct e_node *e; + + if (RB_EMPTY_ROOT(&wnd->start_tree)) + goto use_wnd; + + n = rb_lookup(&wnd->start_tree, bit); + if (!n) + goto use_wnd; + + e = rb_entry(n, struct e_node, start.node); + + end = e->start.key + e->count.key; + + if (bit < end && bit + bits <= end) + return true; + +use_wnd: + ret = wnd_is_free_hlp(wnd, bit, bits); + + return ret; +} + +/* + * wnd_is_used + * + * Returns true if all clusters [bit, bit+bits) are used + */ +bool wnd_is_used(struct wnd_bitmap *wnd, size_t bit, size_t bits) +{ + bool ret = false; + struct super_block *sb = wnd->sb; + size_t iw = bit >> (sb->s_blocksize_bits + 3); + u32 wbits = 8 * sb->s_blocksize; + u32 wbit = bit & (wbits - 1); + size_t end; + struct rb_node *n; + struct e_node *e; + + if (RB_EMPTY_ROOT(&wnd->start_tree)) + goto use_wnd; + + end = bit + bits; + n = rb_lookup(&wnd->start_tree, end - 1); + if (!n) + goto use_wnd; + + e = rb_entry(n, struct e_node, start.node); + if (e->start.key + e->count.key > bit) + return false; + +use_wnd: + while (iw < wnd->nwnd && bits) { + u32 tail, op; + + if (unlikely(iw + 1 == wnd->nwnd)) + wbits = wnd->bits_last; + + tail = wbits - wbit; + op = tail < bits ? tail : bits; + + if (wnd->free_bits[iw]) { + bool ret; + struct buffer_head *bh = wnd_map(wnd, iw); + + if (IS_ERR(bh)) + goto out; + + ret = are_bits_set((ulong *)bh->b_data, wbit, op); + put_bh(bh); + if (!ret) + goto out; + } + + bits -= op; + wbit = 0; + iw += 1; + } + ret = true; + +out: + return ret; +} + +/* + * wnd_find + * - flags - BITMAP_FIND_XXX flags + * + * looks for free space + * Returns 0 if not found + */ +size_t wnd_find(struct wnd_bitmap *wnd, size_t to_alloc, size_t hint, + size_t flags, size_t *allocated) +{ + struct super_block *sb; + u32 wbits, wpos, wzbit, wzend; + size_t fnd, max_alloc, b_len, b_pos; + size_t iw, prev_tail, nwnd, wbit, ebit, zbit, zend; + size_t to_alloc0 = to_alloc; + const ulong *buf; + const struct e_node *e; + const struct rb_node *pr, *cr; + u8 log2_bits; + bool fbits_valid; + struct buffer_head *bh; + + /* fast checking for available free space */ + if (flags & BITMAP_FIND_FULL) { + size_t zeroes = wnd_zeroes(wnd); + + zeroes -= wnd->zone_end - wnd->zone_bit; + if (zeroes < to_alloc0) + goto no_space; + + if (to_alloc0 > wnd->extent_max) + goto no_space; + } else { + if (to_alloc > wnd->extent_max) + to_alloc = wnd->extent_max; + } + + if (wnd->zone_bit <= hint && hint < wnd->zone_end) + hint = wnd->zone_end; + + max_alloc = wnd->nbits; + b_len = b_pos = 0; + + if (hint >= max_alloc) + hint = 0; + + if (RB_EMPTY_ROOT(&wnd->start_tree)) { + if (wnd->uptodated == 1) { + /* extents tree is updated -> no free space */ + goto no_space; + } + goto scan_bitmap; + } + + e = NULL; + if (!hint) + goto allocate_biggest; + + /* Use hint: enumerate extents by start >= hint */ + pr = NULL; + cr = wnd->start_tree.rb_node; + + for (;;) { + e = rb_entry(cr, struct e_node, start.node); + + if (e->start.key == hint) + break; + + if (e->start.key < hint) { + pr = cr; + cr = cr->rb_right; + if (!cr) + break; + continue; + } + + cr = cr->rb_left; + if (!cr) { + e = pr ? rb_entry(pr, struct e_node, start.node) : NULL; + break; + } + } + + if (!e) + goto allocate_biggest; + + if (e->start.key + e->count.key > hint) { + /* We have found extension with 'hint' inside */ + size_t len = e->start.key + e->count.key - hint; + + if (len >= to_alloc && hint + to_alloc <= max_alloc) { + fnd = hint; + goto found; + } + + if (!(flags & BITMAP_FIND_FULL)) { + if (len > to_alloc) + len = to_alloc; + + if (hint + len <= max_alloc) { + fnd = hint; + to_alloc = len; + goto found; + } + } + } + +allocate_biggest: + + /* Allocate from biggest free extent */ + e = rb_entry(rb_first(&wnd->count_tree), struct e_node, count.node); + if (e->count.key != wnd->extent_max) + wnd->extent_max = e->count.key; + + if (e->count.key < max_alloc) { + if (e->count.key >= to_alloc) { + ; + } else if (flags & BITMAP_FIND_FULL) { + if (e->count.key < to_alloc0) { + /* Biggest free block is less then requested */ + goto no_space; + } + to_alloc = e->count.key; + } else if (-1 != wnd->uptodated) { + to_alloc = e->count.key; + } else { + /* Check if we can use more bits */ + size_t op, max_check; + struct rb_root start_tree; + + memcpy(&start_tree, &wnd->start_tree, + sizeof(struct rb_root)); + memset(&wnd->start_tree, 0, sizeof(struct rb_root)); + + max_check = e->start.key + to_alloc; + if (max_check > max_alloc) + max_check = max_alloc; + for (op = e->start.key + e->count.key; op < max_check; + op++) { + if (!wnd_is_free(wnd, op, 1)) + break; + } + memcpy(&wnd->start_tree, &start_tree, + sizeof(struct rb_root)); + to_alloc = op - e->start.key; + } + + /* Prepare to return */ + fnd = e->start.key; + if (e->start.key + to_alloc > max_alloc) + to_alloc = max_alloc - e->start.key; + goto found; + } + + if (wnd->uptodated == 1) { + /* extents tree is updated -> no free space */ + goto no_space; + } + + b_len = e->count.key; + b_pos = e->start.key; + +scan_bitmap: + sb = wnd->sb; + log2_bits = sb->s_blocksize_bits + 3; + + /* At most two ranges [hint, max_alloc) + [0, hint) */ +Again: + + /* TODO: optimize request for case nbits > wbits */ + iw = hint >> log2_bits; + wbits = sb->s_blocksize * 8; + wpos = hint & (wbits - 1); + prev_tail = 0; + fbits_valid = true; + + if (max_alloc == wnd->nbits) { + nwnd = wnd->nwnd; + } else { + size_t t = max_alloc + wbits - 1; + + nwnd = likely(t > max_alloc) ? (t >> log2_bits) : wnd->nwnd; + } + + /* Enumerate all windows */ + for (; iw < nwnd; iw++) { + wbit = iw << log2_bits; + + if (!wnd->free_bits[iw]) { + if (prev_tail > b_len) { + b_pos = wbit - prev_tail; + b_len = prev_tail; + } + + /* Skip full used window */ + prev_tail = 0; + wpos = 0; + continue; + } + + if (unlikely(iw + 1 == nwnd)) { + if (max_alloc == wnd->nbits) { + wbits = wnd->bits_last; + } else { + size_t t = max_alloc & (wbits - 1); + + if (t) { + wbits = t; + fbits_valid = false; + } + } + } + + if (wnd->zone_end > wnd->zone_bit) { + ebit = wbit + wbits; + zbit = max(wnd->zone_bit, wbit); + zend = min(wnd->zone_end, ebit); + + /* Here we have a window [wbit, ebit) and zone [zbit, zend) */ + if (zend <= zbit) { + /* Zone does not overlap window */ + } else { + wzbit = zbit - wbit; + wzend = zend - wbit; + + /* Zone overlaps window */ + if (wnd->free_bits[iw] == wzend - wzbit) { + prev_tail = 0; + wpos = 0; + continue; + } + + /* Scan two ranges window: [wbit, zbit) and [zend, ebit) */ + bh = wnd_map(wnd, iw); + + if (IS_ERR(bh)) { + /* TODO: error */ + prev_tail = 0; + wpos = 0; + continue; + } + + buf = (ulong *)bh->b_data; + + /* Scan range [wbit, zbit) */ + if (wpos < wzbit) { + /* Scan range [wpos, zbit) */ + fnd = wnd_scan(buf, wbit, wpos, wzbit, + to_alloc, &prev_tail, + &b_pos, &b_len); + if (fnd != MINUS_ONE_T) { + put_bh(bh); + goto found; + } + } + + prev_tail = 0; + + /* Scan range [zend, ebit) */ + if (wzend < wbits) { + fnd = wnd_scan(buf, wbit, + max(wzend, wpos), wbits, + to_alloc, &prev_tail, + &b_pos, &b_len); + if (fnd != MINUS_ONE_T) { + put_bh(bh); + goto found; + } + } + + wpos = 0; + put_bh(bh); + continue; + } + } + + /* Current window does not overlap zone */ + if (!wpos && fbits_valid && wnd->free_bits[iw] == wbits) { + /* window is empty */ + if (prev_tail + wbits >= to_alloc) { + fnd = wbit + wpos - prev_tail; + goto found; + } + + /* Increase 'prev_tail' and process next window */ + prev_tail += wbits; + wpos = 0; + continue; + } + + /* read window */ + bh = wnd_map(wnd, iw); + if (IS_ERR(bh)) { + // TODO: error + prev_tail = 0; + wpos = 0; + continue; + } + + buf = (ulong *)bh->b_data; + + /* Scan range [wpos, eBits) */ + fnd = wnd_scan(buf, wbit, wpos, wbits, to_alloc, &prev_tail, + &b_pos, &b_len); + put_bh(bh); + if (fnd != MINUS_ONE_T) + goto found; + } + + if (b_len < prev_tail) { + /* The last fragment */ + b_len = prev_tail; + b_pos = max_alloc - prev_tail; + } + + if (hint) { + /* + * We have scanned range [hint max_alloc) + * Prepare to scan range [0 hint + to_alloc) + */ + size_t nextmax = hint + to_alloc; + + if (likely(nextmax >= hint) && nextmax < max_alloc) + max_alloc = nextmax; + hint = 0; + goto Again; + } + + if (!b_len) + goto no_space; + + wnd->extent_max = b_len; + + if (flags & BITMAP_FIND_FULL) + goto no_space; + + fnd = b_pos; + to_alloc = b_len; + +found: + if (flags & BITMAP_FIND_MARK_AS_USED) { + /* TODO optimize remove extent (pass 'e'?) */ + if (wnd_set_used(wnd, fnd, to_alloc)) + goto no_space; + } else if (wnd->extent_max != MINUS_ONE_T && + to_alloc > wnd->extent_max) { + wnd->extent_max = to_alloc; + } + + *allocated = fnd; + return to_alloc; + +no_space: + return 0; +} + +/* + * wnd_extend + * + * Extend bitmap ($MFT bitmap) + */ +int wnd_extend(struct wnd_bitmap *wnd, size_t new_bits) +{ + int err; + struct super_block *sb = wnd->sb; + struct ntfs_sb_info *sbi = sb->s_fs_info; + u32 blocksize = sb->s_blocksize; + u32 wbits = blocksize * 8; + u32 b0, new_last; + size_t bits, iw, new_wnd; + size_t old_bits = wnd->nbits; + u16 *new_free; + + if (new_bits <= old_bits) + return -EINVAL; + + /* align to 8 byte boundary */ + new_wnd = bytes_to_block(sb, bitmap_size(new_bits)); + new_last = new_bits & (wbits - 1); + if (!new_last) + new_last = wbits; + + if (new_wnd != wnd->nwnd) { + if (new_wnd <= ARRAY_SIZE(wnd->free_holder)) { + new_free = wnd->free_holder; + } else { + new_free = ntfs_alloc(new_wnd * sizeof(u16), 0); + if (!new_free) + return -ENOMEM; + } + + if (new_free != wnd->free_bits) + memcpy(new_free, wnd->free_bits, + wnd->nwnd * sizeof(short)); + memset(new_free + wnd->nwnd, 0, + (new_wnd - wnd->nwnd) * sizeof(short)); + if (wnd->free_bits != wnd->free_holder) + ntfs_free(wnd->free_bits); + + wnd->free_bits = new_free; + } + + /* Zero bits [old_bits,new_bits) */ + bits = new_bits - old_bits; + b0 = old_bits & (wbits - 1); + + for (iw = old_bits >> (sb->s_blocksize_bits + 3); bits; iw += 1) { + u32 op; + size_t frb; + u64 vbo, lbo, bytes; + struct buffer_head *bh; + ulong *buf; + + if (iw + 1 == new_wnd) + wbits = new_last; + + op = b0 + bits > wbits ? wbits - b0 : bits; + vbo = (u64)iw * blocksize; + + err = ntfs_vbo_to_lbo(sbi, &wnd->run, vbo, &lbo, &bytes); + if (err) + break; + + bh = ntfs_bread(sb, lbo >> sb->s_blocksize_bits); + if (!bh) + return -EIO; + + lock_buffer(bh); + buf = (ulong *)bh->b_data; + + __bitmap_clear(buf, b0, blocksize * 8 - b0); + frb = wbits - __bitmap_weight(buf, wbits); + wnd->total_zeroes += frb - wnd->free_bits[iw]; + wnd->free_bits[iw] = frb; + + set_buffer_uptodate(bh); + mark_buffer_dirty(bh); + unlock_buffer(bh); + /*err = sync_dirty_buffer(bh);*/ + + b0 = 0; + bits -= op; + } + + wnd->nbits = new_bits; + wnd->nwnd = new_wnd; + wnd->bits_last = new_last; + + wnd_add_free_ext(wnd, old_bits, new_bits - old_bits, false); + + return 0; +} + +/* + * wnd_zone_set + */ +void wnd_zone_set(struct wnd_bitmap *wnd, size_t lcn, size_t len) +{ + size_t zlen; + + zlen = wnd->zone_end - wnd->zone_bit; + if (zlen) + wnd_add_free_ext(wnd, wnd->zone_bit, zlen, false); + + if (!RB_EMPTY_ROOT(&wnd->start_tree) && len) + wnd_remove_free_ext(wnd, lcn, len); + + wnd->zone_bit = lcn; + wnd->zone_end = lcn + len; +} + +int ntfs_trim_fs(struct ntfs_sb_info *sbi, struct fstrim_range *range) +{ + int err = 0; + struct super_block *sb = sbi->sb; + struct wnd_bitmap *wnd = &sbi->used.bitmap; + u32 wbits = 8 * sb->s_blocksize; + CLST len = 0, lcn = 0, done = 0; + CLST minlen = bytes_to_cluster(sbi, range->minlen); + CLST lcn_from = bytes_to_cluster(sbi, range->start); + size_t iw = lcn_from >> (sb->s_blocksize_bits + 3); + u32 wbit = lcn_from & (wbits - 1); + const ulong *buf; + CLST lcn_to; + + if (!minlen) + minlen = 1; + + if (range->len == (u64)-1) + lcn_to = wnd->nbits; + else + lcn_to = bytes_to_cluster(sbi, range->start + range->len); + + down_read_nested(&wnd->rw_lock, BITMAP_MUTEX_CLUSTERS); + + for (; iw < wnd->nbits; iw++, wbit = 0) { + CLST lcn_wnd = iw * wbits; + struct buffer_head *bh; + + if (lcn_wnd > lcn_to) + break; + + if (!wnd->free_bits[iw]) + continue; + + if (iw + 1 == wnd->nwnd) + wbits = wnd->bits_last; + + if (lcn_wnd + wbits > lcn_to) + wbits = lcn_to - lcn_wnd; + + bh = wnd_map(wnd, iw); + if (IS_ERR(bh)) { + err = PTR_ERR(bh); + break; + } + + buf = (ulong *)bh->b_data; + + for (; wbit < wbits; wbit++) { + if (!test_bit(wbit, buf)) { + if (!len) + lcn = lcn_wnd + wbit; + len += 1; + continue; + } + if (len >= minlen) { + err = ntfs_discard(sbi, lcn, len); + if (err) + goto out; + done += len; + } + len = 0; + } + put_bh(bh); + } + + /* Process the last fragment */ + if (len >= minlen) { + err = ntfs_discard(sbi, lcn, len); + if (err) + goto out; + done += len; + } + +out: + range->len = (u64)done << sbi->cluster_bits; + + up_read(&wnd->rw_lock); + + return err; +} From patchwork Fri Oct 9 14:22:55 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Konstantin Komarov X-Patchwork-Id: 11825961 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id E7C171744 for ; Fri, 9 Oct 2020 14:23:55 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 99B5C222C3 for ; Fri, 9 Oct 2020 14:23:55 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (1024-bit key) header.d=paragon-software.com header.i=@paragon-software.com header.b="gcY+JKdT" Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S2388781AbgJIOXr (ORCPT ); Fri, 9 Oct 2020 10:23:47 -0400 Received: from relaydlg-01.paragon-software.com ([81.5.88.159]:42921 "EHLO relaydlg-01.paragon-software.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S2387978AbgJIOXi (ORCPT ); Fri, 9 Oct 2020 10:23:38 -0400 Received: from dlg2.mail.paragon-software.com (vdlg-exch-02.paragon-software.com [172.30.1.105]) by relaydlg-01.paragon-software.com (Postfix) with ESMTPS id 251BA8237E; Fri, 9 Oct 2020 17:23:09 +0300 (MSK) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=paragon-software.com; s=mail; t=1602253389; bh=yQv3ktnKKUPW0aJeQX6oo/z2VE66fD79Bo5Lf4v6RLg=; h=From:To:CC:Subject:Date:In-Reply-To:References; b=gcY+JKdTy8UWksfa7eQqTRM+CqsDHTHHQpB6aWh4fOZYQa/F7huI1/QUprvYcqljg fvfc+PRsinPZz6zzpe9Xw10NhDMn7C1XZR5pgLwnxta1C2c5xV4qwpUaHEhp+NmhBD SNPo68JoggQILxHKUuPWVlzItxfYJnk2u4PV6YP8= Received: from fsd-lkpg.ufsd.paragon-software.com (172.30.114.105) by vdlg-exch-02.paragon-software.com (172.30.1.105) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id 15.1.1847.3; Fri, 9 Oct 2020 17:23:08 +0300 From: Konstantin Komarov To: CC: , , , , , , , , , , , , Konstantin Komarov Subject: [PATCH v8 04/10] fs/ntfs3: Add file operations and implementation Date: Fri, 9 Oct 2020 17:22:55 +0300 Message-ID: <20201009142301.412454-5-almaz.alexandrovich@paragon-software.com> X-Mailer: git-send-email 2.25.4 In-Reply-To: <20201009142301.412454-1-almaz.alexandrovich@paragon-software.com> References: <20201009142301.412454-1-almaz.alexandrovich@paragon-software.com> MIME-Version: 1.0 X-Originating-IP: [172.30.114.105] X-ClientProxiedBy: vdlg-exch-02.paragon-software.com (172.30.1.105) To vdlg-exch-02.paragon-software.com (172.30.1.105) Precedence: bulk List-ID: X-Mailing-List: linux-fsdevel@vger.kernel.org This adds file operations and implementation Signed-off-by: Konstantin Komarov --- fs/ntfs3/dir.c | 608 ++++++++++++ fs/ntfs3/file.c | 1154 ++++++++++++++++++++++ fs/ntfs3/frecord.c | 2335 ++++++++++++++++++++++++++++++++++++++++++++ fs/ntfs3/namei.c | 576 +++++++++++ fs/ntfs3/record.c | 615 ++++++++++++ fs/ntfs3/run.c | 1161 ++++++++++++++++++++++ 6 files changed, 6449 insertions(+) create mode 100644 fs/ntfs3/dir.c create mode 100644 fs/ntfs3/file.c create mode 100644 fs/ntfs3/frecord.c create mode 100644 fs/ntfs3/namei.c create mode 100644 fs/ntfs3/record.c create mode 100644 fs/ntfs3/run.c diff --git a/fs/ntfs3/dir.c b/fs/ntfs3/dir.c new file mode 100644 index 000000000000..a142bb9ae6ff --- /dev/null +++ b/fs/ntfs3/dir.c @@ -0,0 +1,608 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * linux/fs/ntfs3/dir.c + * + * Copyright (C) 2019-2020 Paragon Software GmbH, All rights reserved. + * + * directory handling functions for ntfs-based filesystems + * + */ +#include +#include +#include +#include +#include + +#include "debug.h" +#include "ntfs.h" +#include "ntfs_fs.h" + +/* + * Convert little endian utf16 to nls string + */ +int ntfs_utf16_to_nls(struct ntfs_sb_info *sbi, const struct le_str *uni, + u8 *buf, int buf_len) +{ + int ret, uni_len; + const __le16 *ip; + u8 *op; + struct nls_table *nls = sbi->options.nls[0]; + + static_assert(sizeof(wchar_t) == sizeof(__le16)); + + if (!nls) { + /* utf16 -> utf8 */ + ret = utf16s_to_utf8s((wchar_t *)uni->name, uni->len, + UTF16_LITTLE_ENDIAN, buf, buf_len); + buf[ret] = '\0'; + return ret; + } + + ip = uni->name; + op = buf; + uni_len = uni->len; + + while (uni_len--) { + u16 ec; + int charlen; + + if (buf_len < NLS_MAX_CHARSET_SIZE) { + ntfs_warn(sbi->sb, + "filename was truncated while converting."); + break; + } + + ec = le16_to_cpu(*ip++); + charlen = nls->uni2char(ec, op, buf_len); + + if (charlen > 0) { + op += charlen; + buf_len -= charlen; + } else { + *op++ = ':'; + op = hex_byte_pack(op, ec >> 8); + op = hex_byte_pack(op, ec); + buf_len -= 5; + } + } + + *op = '\0'; + return op - buf; +} + +#define PLANE_SIZE 0x00010000 + +#define SURROGATE_PAIR 0x0000d800 +#define SURROGATE_LOW 0x00000400 +#define SURROGATE_BITS 0x000003ff + +static inline void put_utf16(wchar_t *s, unsigned c, enum utf16_endian endian) +{ + switch (endian) { + default: + *s = (wchar_t)c; + break; + case UTF16_LITTLE_ENDIAN: + *s = __cpu_to_le16(c); + break; + case UTF16_BIG_ENDIAN: + *s = __cpu_to_be16(c); + break; + } +} + +/* + * modified version of 'utf8s_to_utf16s' allows to + * detect -ENAMETOOLONG without writing out of expected maximum + */ +static int _utf8s_to_utf16s(const u8 *s, int inlen, enum utf16_endian endian, + wchar_t *pwcs, int maxout) +{ + u16 *op; + int size; + unicode_t u; + + op = pwcs; + while (inlen > 0 && *s) { + if (*s & 0x80) { + size = utf8_to_utf32(s, inlen, &u); + if (size < 0) + return -EINVAL; + s += size; + inlen -= size; + + if (u >= PLANE_SIZE) { + if (maxout < 2) + return -ENAMETOOLONG; + + u -= PLANE_SIZE; + put_utf16(op++, + SURROGATE_PAIR | + ((u >> 10) & SURROGATE_BITS), + endian); + put_utf16(op++, + SURROGATE_PAIR | SURROGATE_LOW | + (u & SURROGATE_BITS), + endian); + maxout -= 2; + } else { + if (maxout < 1) + return -ENAMETOOLONG; + + put_utf16(op++, u, endian); + maxout--; + } + } else { + if (maxout < 1) + return -ENAMETOOLONG; + + put_utf16(op++, *s++, endian); + inlen--; + maxout--; + } + } + return op - pwcs; +} + +/* helper for ntfs_nls_to_utf16 */ +static int _ntfs_nls_to_utf16(struct nls_table *nls, const u8 *name, + u32 name_len, wchar_t *uname, u32 max_ulen, + enum utf16_endian endian) +{ + int ret, slen; + const u8 *end; + + if (!nls) { + /* utf8 -> utf16 */ + return _utf8s_to_utf16s(name, name_len, endian, uname, + max_ulen); + } + + ret = 0; + + for (end = name + name_len; name < end; ret++, name += slen) { + if (ret >= max_ulen) + return -ENAMETOOLONG; + + slen = nls->char2uni(name, end - name, uname + ret); + if (!slen) + return -EINVAL; + if (slen < 0) + return slen; + } + +#ifdef __BIG_ENDIAN + if (endian == UTF16_LITTLE_ENDIAN) { + int i = ret; + + while (i--) { + __cpu_to_le16s(uname); + uname++; + } + } +#else + if (endian == UTF16_BIG_ENDIAN) { + int i = ret; + + while (i--) { + __cpu_to_be16s(uname); + uname++; + } + } +#endif + + return ret; +} + +/* + * Convert input string to utf16 + * + * name, name_len - input name + * uni, max_ulen - destination memory + * endian - endian of target utf16 string + * + * This function is called: + * - to create ntfs name + * - to create symlink + * + * returns utf16 string length or error (if negative) + */ +int ntfs_nls_to_utf16(struct ntfs_sb_info *sbi, const u8 *name, u32 name_len, + struct cpu_str *uni, u32 max_ulen, + enum utf16_endian endian) +{ + int ret; + struct nls_table *nls = sbi->options.nls[0]; + + static_assert(sizeof(wchar_t) == sizeof(u16)); + + /* use primary nls (may be NULL) */ + ret = _ntfs_nls_to_utf16(nls, name, name_len, uni->name, max_ulen, + endian); + + if (ret == -ENAMETOOLONG) + return -ENAMETOOLONG; + + if (ret > 0) + return uni->len = ret; + + if (!sbi->options.nls[1]) { + ntfs_warn(sbi->sb, "%s failed to convert \"%.*s\" into utf16", + nls ? nls->charset : "utf8", name_len, name); + return ret; + } + + /* use alternative nls */ + ret = _ntfs_nls_to_utf16(sbi->options.nls[1], name, name_len, uni->name, + max_ulen, endian); + + if (ret == -ENAMETOOLONG) + return -ENAMETOOLONG; + + if (ret > 0) { + /* + * primary nls failed but alternative nls ok + * should we print something? + */ + return uni->len = ret; + } + + ntfs_warn(sbi->sb, "%s and %s failed to convert \"%.*s\" into utf16", + nls ? nls->charset : "utf8", sbi->options.nls[1]->charset, + name_len, name); + return ret; +} + +/* helper function */ +struct inode *dir_search_u(struct inode *dir, const struct cpu_str *uni, + struct ntfs_fnd *fnd) +{ + int err = 0; + struct super_block *sb = dir->i_sb; + struct ntfs_sb_info *sbi = sb->s_fs_info; + struct ntfs_inode *ni = ntfs_i(dir); + struct NTFS_DE *e; + int diff; + struct inode *inode = NULL; + struct ntfs_fnd *fnd_a = NULL; + + if (!fnd) { + fnd_a = fnd_get(&ni->dir); + if (!fnd_a) { + err = -ENOMEM; + goto out; + } + fnd = fnd_a; + } + + err = indx_find(&ni->dir, ni, NULL, uni, 0, sbi, &diff, &e, fnd); + + if (err) + goto out; + + if (diff) { + err = -ENOENT; + goto out; + } + + inode = ntfs_iget5(sb, &e->ref, uni); + if (!IS_ERR(inode) && is_bad_inode(inode)) { + iput(inode); + err = -EINVAL; + } +out: + fnd_put(fnd_a); + + return err == -ENOENT ? NULL : err ? ERR_PTR(err) : inode; +} + +static inline int ntfs_filldir(struct ntfs_sb_info *sbi, struct ntfs_inode *ni, + const struct NTFS_DE *e, u8 *name, + struct dir_context *ctx) +{ + const struct ATTR_FILE_NAME *fname; + unsigned long ino; + int name_len; + u32 dt_type; + + fname = Add2Ptr(e, sizeof(struct NTFS_DE)); + + if (fname->type == FILE_NAME_DOS) + return 0; + + if (!mi_is_ref(&ni->mi, &fname->home)) + return 0; + + ino = ino_get(&e->ref); + + if (ino == MFT_REC_ROOT) + return 0; + + /* Skip meta files ( unless option to show metafiles is set ) */ + if (!sbi->options.showmeta && ntfs_is_meta_file(sbi, ino)) + return 0; + + if (sbi->options.nohidden && (fname->dup.fa & FILE_ATTRIBUTE_HIDDEN)) + return 0; + + name_len = ntfs_utf16_to_nls(sbi, (struct le_str *)&fname->name_len, + name, PATH_MAX); + if (name_len <= 0) { + ntfs_warn(sbi->sb, "failed to convert name for inode %lx.", + ino); + return 0; + } + + dt_type = (fname->dup.fa & FILE_ATTRIBUTE_DIRECTORY) ? DT_DIR : DT_REG; + + return !dir_emit(ctx, (s8 *)name, name_len, ino, dt_type); +} + +/* + * ntfs_read_hdr + * + * helper function 'ntfs_readdir' + */ +static int ntfs_read_hdr(struct ntfs_sb_info *sbi, struct ntfs_inode *ni, + const struct INDEX_HDR *hdr, u64 vbo, u64 pos, + u8 *name, struct dir_context *ctx) +{ + int err; + const struct NTFS_DE *e; + u32 e_size; + u32 end = le32_to_cpu(hdr->used); + u32 off = le32_to_cpu(hdr->de_off); + + for (;; off += e_size) { + if (off + sizeof(struct NTFS_DE) > end) + return -1; + + e = Add2Ptr(hdr, off); + e_size = le16_to_cpu(e->size); + if (e_size < sizeof(struct NTFS_DE) || off + e_size > end) + return -1; + + if (de_is_last(e)) + return 0; + + /* Skip already enumerated*/ + if (vbo + off < pos) + continue; + + if (le16_to_cpu(e->key_size) < SIZEOF_ATTRIBUTE_FILENAME) + return -1; + + ctx->pos = vbo + off; + + /* Submit the name to the filldir callback. */ + err = ntfs_filldir(sbi, ni, e, name, ctx); + if (err) + return err; + } +} + +/* + * file_operations::iterate_shared + * + * Use non sorted enumeration. + * We have an example of broken volume where sorted enumeration + * counts each name twice + */ +static int ntfs_readdir(struct file *file, struct dir_context *ctx) +{ + const struct INDEX_ROOT *root; + u64 vbo; + size_t bit; + loff_t eod; + int err = 0; + struct inode *dir = file_inode(file); + struct ntfs_inode *ni = ntfs_i(dir); + struct super_block *sb = dir->i_sb; + struct ntfs_sb_info *sbi = sb->s_fs_info; + loff_t i_size = dir->i_size; + u32 pos = ctx->pos; + u8 *name = NULL; + struct indx_node *node = NULL; + u8 index_bits = ni->dir.index_bits; + + /* name is a buffer of PATH_MAX length */ + static_assert(NTFS_NAME_LEN * 4 < PATH_MAX); + + if (ni->dir.changed) { + ni->dir.changed = false; + pos = 0; + } + + eod = i_size + sbi->record_size; + + if (pos >= eod) + return 0; + + if (!dir_emit_dots(file, ctx)) + return 0; + + name = __getname(); + if (!name) + return -ENOMEM; + + ni_lock(ni); + + root = indx_get_root(&ni->dir, ni, NULL, NULL); + if (!root) { + err = -EINVAL; + goto out; + } + + if (pos >= sbi->record_size) { + bit = (pos - sbi->record_size) >> index_bits; + } else { + err = ntfs_read_hdr(sbi, ni, &root->ihdr, 0, pos, name, ctx); + if (err) + goto out; + bit = 0; + } + + if (!i_size) { + ctx->pos = eod; + goto out; + } + + for (;;) { + vbo = (u64)bit << index_bits; + if (vbo >= i_size) { + ctx->pos = eod; + goto out; + } + + err = indx_used_bit(&ni->dir, ni, &bit); + if (err) + goto out; + + if (bit == MINUS_ONE_T) { + ctx->pos = eod; + goto out; + } + + vbo = (u64)bit << index_bits; + if (vbo >= i_size) { + ntfs_inode_err(dir, "Looks like your dir is corrupt"); + err = -EINVAL; + goto out; + } + + err = indx_read(&ni->dir, ni, bit << ni->dir.idx2vbn_bits, + &node); + if (err) + goto out; + + err = ntfs_read_hdr(sbi, ni, &node->index->ihdr, + vbo + sbi->record_size, pos, name, ctx); + if (err) + goto out; + + bit += 1; + } + +out: + + __putname(name); + put_indx_node(node); + + if (err == -ENOENT) { + err = 0; + ctx->pos = pos; + } + + ni_unlock(ni); + + return err; +} + +static int ntfs_dir_count(struct inode *dir, bool *is_empty, size_t *dirs, + size_t *files) +{ + int err = 0; + struct ntfs_inode *ni = ntfs_i(dir); + struct NTFS_DE *e = NULL; + struct INDEX_ROOT *root; + struct INDEX_HDR *hdr; + const struct ATTR_FILE_NAME *fname; + u32 e_size, off, end; + u64 vbo = 0; + size_t drs = 0, fles = 0, bit = 0; + loff_t i_size = ni->vfs_inode.i_size; + struct indx_node *node = NULL; + u8 index_bits = ni->dir.index_bits; + + if (is_empty) + *is_empty = true; + + root = indx_get_root(&ni->dir, ni, NULL, NULL); + if (!root) + return -EINVAL; + + hdr = &root->ihdr; + + for (;;) { + end = le32_to_cpu(hdr->used); + off = le32_to_cpu(hdr->de_off); + + for (; off + sizeof(struct NTFS_DE) <= end; off += e_size) { + e = Add2Ptr(hdr, off); + e_size = le16_to_cpu(e->size); + if (e_size < sizeof(struct NTFS_DE) || + off + e_size > end) + break; + + if (de_is_last(e)) + break; + + fname = de_get_fname(e); + if (!fname) + continue; + + if (fname->type == FILE_NAME_DOS) + continue; + + if (is_empty) { + *is_empty = false; + if (!dirs && !files) + goto out; + } + + if (fname->dup.fa & FILE_ATTRIBUTE_DIRECTORY) + drs += 1; + else + fles += 1; + } + + if (vbo >= i_size) + goto out; + + err = indx_used_bit(&ni->dir, ni, &bit); + if (err) + goto out; + + if (bit == MINUS_ONE_T) + goto out; + + vbo = (u64)bit << index_bits; + if (vbo >= i_size) + goto out; + + err = indx_read(&ni->dir, ni, bit << ni->dir.idx2vbn_bits, + &node); + if (err) + goto out; + + hdr = &node->index->ihdr; + bit += 1; + vbo = (u64)bit << ni->dir.idx2vbn_bits; + } + +out: + put_indx_node(node); + if (dirs) + *dirs = drs; + if (files) + *files = fles; + + return err; +} + +bool dir_is_empty(struct inode *dir) +{ + bool is_empty = false; + + ntfs_dir_count(dir, &is_empty, NULL, NULL); + + return is_empty; +} + +const struct file_operations ntfs_dir_operations = { + .llseek = generic_file_llseek, + .read = generic_read_dir, + .iterate = ntfs_readdir, + .fsync = ntfs_file_fsync, + .open = ntfs_file_open, +}; diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c new file mode 100644 index 000000000000..388b948481e3 --- /dev/null +++ b/fs/ntfs3/file.c @@ -0,0 +1,1154 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * linux/fs/ntfs3/file.c + * + * Copyright (C) 2019-2020 Paragon Software GmbH, All rights reserved. + * + * regular file handling primitives for ntfs-based filesystems + */ +#include +#include +#include +#include +#include +#include /* FAT_IOCTL_XXX */ +#include + +#include "debug.h" +#include "ntfs.h" +#include "ntfs_fs.h" + +static int ntfs_ioctl_fitrim(struct ntfs_sb_info *sbi, unsigned long arg) +{ + struct fstrim_range __user *user_range; + struct fstrim_range range; + struct request_queue *q = bdev_get_queue(sbi->sb->s_bdev); + int err; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + if (!blk_queue_discard(q)) + return -EOPNOTSUPP; + + user_range = (struct fstrim_range __user *)arg; + if (copy_from_user(&range, user_range, sizeof(range))) + return -EFAULT; + + range.minlen = max_t(u32, range.minlen, q->limits.discard_granularity); + + err = ntfs_trim_fs(sbi, &range); + if (err < 0) + return err; + + if (copy_to_user(user_range, &range, sizeof(range))) + return -EFAULT; + + return 0; +} + +static long ntfs_ioctl(struct file *filp, u32 cmd, unsigned long arg) +{ + struct inode *inode = file_inode(filp); + struct ntfs_sb_info *sbi = inode->i_sb->s_fs_info; + u32 __user *user_attr = (u32 __user *)arg; + + switch (cmd) { + case FAT_IOCTL_GET_ATTRIBUTES: + return put_user(le32_to_cpu(ntfs_i(inode)->std_fa), user_attr); + + case FAT_IOCTL_GET_VOLUME_ID: + return put_user(sbi->volume.ser_num, user_attr); + + case FITRIM: + return ntfs_ioctl_fitrim(sbi, arg); + } + return -ENOTTY; /* Inappropriate ioctl for device */ +} + +#ifdef CONFIG_COMPAT +static long ntfs_compat_ioctl(struct file *filp, u32 cmd, unsigned long arg) + +{ + return ntfs_ioctl(filp, cmd, (unsigned long)compat_ptr(arg)); +} +#endif + +/* + * inode_operations::getattr + */ +int ntfs_getattr(const struct path *path, struct kstat *stat, u32 request_mask, + u32 flags) +{ + struct inode *inode = d_inode(path->dentry); + struct ntfs_inode *ni = ntfs_i(inode); + + if (is_compressed(ni)) + stat->attributes |= STATX_ATTR_COMPRESSED; + + if (is_encrypted(ni)) + stat->attributes |= STATX_ATTR_ENCRYPTED; + + stat->attributes_mask |= STATX_ATTR_COMPRESSED | STATX_ATTR_ENCRYPTED; + + generic_fillattr(inode, stat); + + stat->result_mask |= STATX_BTIME; + stat->btime = ni->i_crtime; + + return 0; +} + +static int ntfs_extend_initialized_size(struct file *file, + struct ntfs_inode *ni, + const loff_t valid, + const loff_t new_valid) +{ + struct inode *inode = &ni->vfs_inode; + struct address_space *mapping = inode->i_mapping; + struct ntfs_sb_info *sbi = inode->i_sb->s_fs_info; + loff_t pos = valid; + int err; + + WARN_ON(is_compressed(ni)); + WARN_ON(valid >= new_valid); + + for (;;) { + u32 zerofrom, len; + struct page *page; + void *fsdata; + u8 bits; + CLST vcn, lcn, clen; + + if (is_sparsed(ni)) { + bits = sbi->cluster_bits; + vcn = pos >> bits; + + err = attr_data_get_block(ni, vcn, 0, &lcn, &clen, + NULL); + if (err) + goto out; + + if (lcn == SPARSE_LCN) { + loff_t vbo = (loff_t)vcn << bits; + loff_t to = vbo + ((loff_t)clen << bits); + + if (to <= new_valid) { + ni->i_valid = to; + pos = to; + goto next; + } + + if (vbo < pos) { + pos = vbo; + } else { + to = (new_valid >> bits) << bits; + if (pos < to) { + ni->i_valid = to; + pos = to; + goto next; + } + } + } + } + + zerofrom = pos & (PAGE_SIZE - 1); + len = PAGE_SIZE - zerofrom; + + if (pos + len > new_valid) + len = new_valid - pos; + + err = pagecache_write_begin(file, mapping, pos, len, 0, &page, + &fsdata); + if (err) + goto out; + + zero_user_segment(page, zerofrom, PAGE_SIZE); + + /* this function in any case puts page*/ + err = pagecache_write_end(file, mapping, pos, len, len, page, + fsdata); + if (err < 0) + goto out; + pos += len; + +next: + if (pos >= new_valid) + break; + + balance_dirty_pages_ratelimited(mapping); + cond_resched(); + } + + mark_inode_dirty(inode); + + return 0; + +out: + ni->i_valid = valid; + ntfs_inode_warn(inode, "failed to extend initialized size to %llx.", + new_valid); + return err; +} + +/* + * ntfs_sparse_cluster + * + * Helper function to zero a new allocated clusters + */ +void ntfs_sparse_cluster(struct inode *inode, struct page *page0, loff_t vbo, + u32 bytes) +{ + struct address_space *mapping = inode->i_mapping; + struct ntfs_sb_info *sbi = inode->i_sb->s_fs_info; + u32 blocksize = 1 << inode->i_blkbits; + pgoff_t idx0 = page0 ? page0->index : -1; + loff_t vbo_clst = vbo & sbi->cluster_mask_inv; + loff_t end = ntfs_up_cluster(sbi, vbo + bytes); + pgoff_t idx = vbo_clst >> PAGE_SHIFT; + u32 from = vbo_clst & (PAGE_SIZE - 1); + pgoff_t idx_end = (end + PAGE_SIZE - 1) >> PAGE_SHIFT; + loff_t page_off; + u32 to; + bool partial; + struct page *page; + + for (; idx < idx_end; idx += 1, from = 0) { + page = idx == idx0 ? page0 : grab_cache_page(mapping, idx); + + if (!page) + continue; + + page_off = (loff_t)idx << PAGE_SHIFT; + to = (page_off + PAGE_SIZE) > end ? (end - page_off) : + PAGE_SIZE; + partial = false; + + if ((from || PAGE_SIZE != to) && + likely(!page_has_buffers(page))) { + create_empty_buffers(page, blocksize, 0); + if (!page_has_buffers(page)) { + ntfs_inode_err( + inode, + "failed to allocate page buffers."); + /*err = -ENOMEM;*/ + goto unlock_page; + } + } + + if (page_has_buffers(page)) { + struct buffer_head *head, *bh; + u32 bh_off = 0; + + bh = head = page_buffers(page); + do { + u32 bh_next = bh_off + blocksize; + + if (from <= bh_off && bh_next <= to) { + set_buffer_uptodate(bh); + mark_buffer_dirty(bh); + } else if (!buffer_uptodate(bh)) { + partial = true; + } + bh_off = bh_next; + } while (head != (bh = bh->b_this_page)); + } + + zero_user_segment(page, from, to); + + if (!partial) { + if (!PageUptodate(page)) + SetPageUptodate(page); + set_page_dirty(page); + } + +unlock_page: + if (idx != idx0) { + unlock_page(page); + put_page(page); + } + } + + mark_inode_dirty(inode); +} + +struct vma_cookie { + loff_t to; +}; + +/* + * vm_operations_struct::close + */ +static void ntfs_filemap_close(struct vm_area_struct *vma) +{ + struct inode *inode = file_inode(vma->vm_file); + struct ntfs_inode *ni = ntfs_i(inode); + loff_t to; + + if (sizeof(void *) >= sizeof(loff_t)) + to = (loff_t)vma->vm_private_data; + else + to = ((struct vma_cookie *)vma->vm_private_data)->to; + + // Update valid size + ni->i_valid = max_t(loff_t, ni->i_valid, + min_t(loff_t, i_size_read(inode), to)); + + if (sizeof(void *) < sizeof(loff_t)) { + ntfs_free(vma->vm_private_data); + vma->vm_private_data = NULL; // is it necessary? + } +} + +/* + * vm_operations_struct::fault + */ +static vm_fault_t ntfs_filemap_fault(struct vm_fault *vmf) +{ + struct vm_area_struct *vma = vmf->vma; + vm_fault_t ret; + loff_t to, *vmc_to; + + ret = filemap_fault(vmf); + + if (!(ret & VM_FAULT_LOCKED)) + return ret; + + /* Update maximum mapped range */ + to = (loff_t)(vmf->pgoff + 1) << PAGE_SHIFT; + + if (sizeof(void *) >= sizeof(loff_t)) + vmc_to = (loff_t *)&vma->vm_private_data; + else + vmc_to = &((struct vma_cookie *)vma->vm_private_data)->to; + + if (*vmc_to < to) + *vmc_to = to; + + return ret; +} + +static const struct vm_operations_struct vma_cookie = { + .close = ntfs_filemap_close, + .fault = ntfs_filemap_fault, + .map_pages = filemap_map_pages, + .page_mkwrite = filemap_page_mkwrite, +}; + +/* + * file_operations::mmap + */ +static int ntfs_file_mmap(struct file *file, struct vm_area_struct *vma) +{ + struct address_space *mapping = file->f_mapping; + struct inode *inode = mapping->host; + struct ntfs_inode *ni = ntfs_i(inode); + u64 to, from = ((u64)vma->vm_pgoff << PAGE_SHIFT); + bool rw = vma->vm_flags & VM_WRITE; + int err; + + if (is_encrypted(ni)) { + err = -EOPNOTSUPP; + goto out; + } + + if (!rw) { + err = generic_file_mmap(file, vma); + goto out; + } + + if (is_compressed(ni)) { + err = -EOPNOTSUPP; + goto out; + } + + // map for write + inode_lock(inode); + + to = from + vma->vm_end - vma->vm_start; + + if (to > inode->i_size) + to = inode->i_size; + + if (is_sparsed(ni)) { + /* allocate clusters for rw map */ + struct ntfs_sb_info *sbi = inode->i_sb->s_fs_info; + CLST vcn, lcn, len; + CLST end = bytes_to_cluster(sbi, to); + bool new; + + for (vcn = from >> sbi->cluster_bits; vcn < end; vcn += len) { + err = attr_data_get_block(ni, vcn, 1, &lcn, &len, &new); + if (err) { + inode_unlock(inode); + goto out; + } + if (!new) + continue; + ntfs_sparse_cluster(inode, NULL, + (u64)vcn << sbi->cluster_bits, + sbi->cluster_size); + } + } + + err = ni->i_valid < to ? + ntfs_extend_initialized_size(file, ni, ni->i_valid, to) : + 0; + + inode_unlock(inode); + if (err) + goto out; + + if (vma->vm_private_data) { + ntfs_inode_warn( + inode, + "mmap: failed to keep private vma_data, possible garbidge data"); + err = generic_file_mmap(file, vma); + goto out; + } + + if (!mapping->a_ops->readpage) { + err = -ENOEXEC; + goto out; + } + + /* + * Allocate and init small struct to keep track the mapping operations + * It is useful when mmap(size) + truncate(size/2) + unmap(). see + * xfstests/generic/039 + * + * TODO: if sizeof(void*) == 8 bytes we can store the only field 'to' + * of vma_cookie in vma->vm_private_data + */ + if (sizeof(void *) >= sizeof(loff_t)) + vma->vm_private_data = (void *)to; + else { + struct vma_cookie *vmc = + ntfs_alloc(sizeof(struct vma_cookie), 0); + + if (unlikely(!vmc)) { + err = -ENOMEM; + goto out; + } + vmc->to = to; + vma->vm_private_data = vmc; + } + + file_accessed(file); + vma->vm_ops = &vma_cookie; + +out: + return err; +} + +/* + * file_operations::fsync + */ +int ntfs_file_fsync(struct file *filp, loff_t start, loff_t end, int datasync) +{ + return generic_file_fsync(filp, start, end, datasync); +} + +static int ntfs_extend_ex(struct inode *inode, loff_t pos, size_t count, + struct file *file) +{ + struct ntfs_inode *ni = ntfs_i(inode); + struct address_space *mapping = inode->i_mapping; + loff_t end = pos + count; + int err; + bool extend_init = file && pos > ni->i_valid; + + if (end <= inode->i_size && !extend_init) + return 0; + + /*mark rw ntfs as dirty. it will be cleared at umount*/ + ntfs_set_state(ni->mi.sbi, NTFS_DIRTY_DIRTY); + + if (end > inode->i_size) { + err = ntfs_set_size(inode, end); + if (err) + goto out; + inode->i_size = end; + } + + if (extend_init && !is_compressed(ni)) { + err = ntfs_extend_initialized_size(file, ni, ni->i_valid, pos); + if (err) + goto out; + } else { + err = 0; + } + + inode->i_ctime = inode->i_mtime = current_time(inode); + mark_inode_dirty(inode); + + if (IS_SYNC(inode)) { + int err2; + + err = filemap_fdatawrite_range(mapping, pos, end - 1); + err2 = sync_mapping_buffers(mapping); + if (!err) + err = err2; + err2 = write_inode_now(inode, 1); + if (!err) + err = err2; + if (!err) + err = filemap_fdatawait_range(mapping, pos, end - 1); + } + +out: + return err; +} + +/* + * Preallocate space for a file. This implements ntfs's fallocate file + * operation, which gets called from sys_fallocate system call. User + * space requests 'len' bytes at 'vbo'. If FALLOC_FL_KEEP_SIZE is set + * we just allocate clusters without zeroing them out. Otherwise we + * allocate and zero out clusters via an expanding truncate. + */ +static long ntfs_fallocate(struct file *file, int mode, loff_t vbo, loff_t len) +{ + struct inode *inode = file->f_mapping->host; + struct super_block *sb = inode->i_sb; + struct ntfs_sb_info *sbi = sb->s_fs_info; + struct ntfs_inode *ni = ntfs_i(inode); + loff_t i_size; + loff_t end; + int err; + + /* No support for dir */ + if (!S_ISREG(inode->i_mode)) + return -EOPNOTSUPP; + + /* Return error if mode is not supported */ + if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE | + FALLOC_FL_COLLAPSE_RANGE)) + return -EOPNOTSUPP; + + inode_lock(inode); + i_size = inode->i_size; + + if (mode & FALLOC_FL_PUNCH_HOLE) { + if (!(mode & FALLOC_FL_KEEP_SIZE)) { + err = -EINVAL; + goto out; + } + /*TODO: add support*/ + err = -EOPNOTSUPP; + goto out; + } + + if (mode & FALLOC_FL_COLLAPSE_RANGE) { + if (mode & ~FALLOC_FL_COLLAPSE_RANGE) { + err = -EINVAL; + goto out; + } + + /*TODO: add support*/ + err = -EOPNOTSUPP; + goto out; + } + + end = vbo + len; + + ntfs_set_state(sbi, NTFS_DIRTY_DIRTY); + + /* + * normal file: allocate clusters, do not change 'valid' size + */ + err = ntfs_set_size(inode, max(end, i_size)); + if (err) + goto out; + + if (is_sparsed(ni) || is_compressed(ni)) { + CLST vcn = vbo >> sbi->cluster_bits; + CLST cend = bytes_to_cluster(sbi, end); + CLST lcn, clen; + bool new; + + /* + * allocate but not zero new clusters + * this breaks security (one can read unused on-disk areas) + * zeroing these clusters may be too long + * may be we should check here for root rights? + */ + for (; vcn < cend; vcn += clen) { + err = attr_data_get_block(ni, vcn, cend - vcn, &lcn, + &clen, &new); + if (err) + goto out; + } + } + + if (mode & FALLOC_FL_KEEP_SIZE) { + ni_lock(ni); + /*true - keep preallocated*/ + err = attr_set_size(ni, ATTR_DATA, NULL, 0, &ni->file.run, + i_size, &ni->i_valid, true, NULL); + ni_unlock(ni); + if (err) + goto out; + } + + inode->i_ctime = inode->i_mtime = current_time(inode); + mark_inode_dirty(inode); + +out: + if (err == -EFBIG) + err = -ENOSPC; + + inode_unlock(inode); + return err; +} + +void ntfs_truncate_blocks(struct inode *inode, loff_t new_size) +{ + struct super_block *sb = inode->i_sb; + struct ntfs_sb_info *sbi = sb->s_fs_info; + struct ntfs_inode *ni = ntfs_i(inode); + int err, dirty = 0; + u32 vcn; + u64 new_valid; + + if (!S_ISREG(inode->i_mode)) + return; + + vcn = bytes_to_cluster(sbi, new_size); + new_valid = ntfs_up_block(sb, min(ni->i_valid, new_size)); + + ni_lock(ni); + + truncate_setsize(inode, new_size); + + if (new_valid < ni->i_valid) + ni->i_valid = new_valid; + + ni_unlock(ni); + + ni->std_fa |= FILE_ATTRIBUTE_ARCHIVE; + inode->i_ctime = inode->i_mtime = current_time(inode); + if (!IS_DIRSYNC(inode)) { + dirty = 1; + } else { + err = ntfs_sync_inode(inode); + if (err) + return; + } + + inode->i_blocks = vcn; + + if (dirty) + mark_inode_dirty(inode); + + /*ntfs_flush_inodes(inode->i_sb, inode, NULL);*/ +} + +/* + * inode_operations::setattr + */ +int ntfs_setattr(struct dentry *dentry, struct iattr *attr) +{ + struct super_block *sb = dentry->d_sb; + struct ntfs_sb_info *sbi = sb->s_fs_info; + struct inode *inode = d_inode(dentry); + struct ntfs_inode *ni = ntfs_i(inode); + u32 ia_valid = attr->ia_valid; + umode_t mode = inode->i_mode; + int err; + + if (sbi->options.no_acs_rules) { + /* "no access rules" - force any changes of time etc. */ + attr->ia_valid |= ATTR_FORCE; + /* and disable for editing some attributes */ + attr->ia_valid &= ~(ATTR_UID | ATTR_GID | ATTR_MODE); + ia_valid = attr->ia_valid; + } + + err = setattr_prepare(dentry, attr); + if (err) + goto out; + + if (ia_valid & ATTR_SIZE) { + loff_t oldsize = inode->i_size; + + inode_dio_wait(inode); + + if (attr->ia_size < oldsize) { + if (!is_compressed(ni)) { + err = block_truncate_page(inode->i_mapping, + attr->ia_size, + ntfs_get_block); + if (err) + goto out; + } + ntfs_truncate_blocks(inode, attr->ia_size); + } else if (attr->ia_size > oldsize) { + err = ntfs_extend_ex(inode, attr->ia_size, 0, NULL); + if (err) + goto out; + } + + ni->ni_flags |= NI_FLAG_UPDATE_PARENT; + } + + setattr_copy(inode, attr); + + if (mode != inode->i_mode) { + err = ntfs_acl_chmod(inode); + if (err) + goto out; + + /* linux 'w' -> windows 'ro' */ + if (0222 & inode->i_mode) + ni->std_fa &= ~FILE_ATTRIBUTE_READONLY; + else + ni->std_fa |= FILE_ATTRIBUTE_READONLY; + } + + mark_inode_dirty(inode); +out: + return err; +} + +static ssize_t ntfs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) +{ + ssize_t err; + size_t count = iov_iter_count(iter); + struct file *file = iocb->ki_filp; + struct inode *inode = file->f_mapping->host; + struct ntfs_inode *ni = ntfs_i(inode); + + if (is_encrypted(ni)) { + ntfs_inode_warn(inode, "encrypted i/o not supported"); + return -EOPNOTSUPP; + } + + if (is_compressed(ni) && (iocb->ki_flags & IOCB_DIRECT)) { + ntfs_inode_warn(inode, "direct i/o + compressed not supported"); + return -EOPNOTSUPP; + } + + if (ni->ni_flags & NI_FLAG_COMPRESSED_MASK) { + ntfs_inode_warn( + inode, + "read external compressed file not supported (temporary)"); + return -EOPNOTSUPP; + } + + if (is_dedup(ni)) { + ntfs_inode_warn(inode, "read deduplicated not supported"); + return -EOPNOTSUPP; + } + + err = count ? generic_file_read_iter(iocb, iter) : 0; + + return err; +} + +/* returns array of locked pages */ +static int ntfs_get_frame(struct address_space *mapping, pgoff_t index, + struct page **pages, u32 pages_per_frame, + pgoff_t max_index, bool skip_read) +{ + int err = 0; + u32 npages = 0; + gfp_t gfp_mask = + mapping_gfp_constraint(mapping, ~__GFP_WRITE) | __GFP_FS; + + while (npages < pages_per_frame && index < max_index) { + struct page *page; + + page = find_or_create_page(mapping, index++, gfp_mask); + if (!page) { + err = -ENOMEM; +fail: + while (npages--) { + page = pages[npages]; + unlock_page(page); + put_page(page); + } + + return err; + } + + pages[npages++] = page; + + if (npages == 1 && !skip_read) { + /* it reads full frame */ + err = ntfs_readpage(NULL, page); + if (err) { + /* page is still locked */ + goto fail; + } + + /* page is unlocked */ + lock_page(page); + if (!PageUptodate(page)) { + err = -EIO; + goto fail; + } + + if (page->mapping != mapping) { + unlock_page(page); + put_page(page); + index -= 1; + npages -= 1; + continue; + } + } + } + + return npages; +} + +/*helper for ntfs_file_write_iter (compressed files)*/ +static noinline ssize_t ntfs_compress_write(struct kiocb *iocb, + struct iov_iter *from) +{ + int err; + struct file *file = iocb->ki_filp; + size_t count = iov_iter_count(from); + loff_t pos = iocb->ki_pos; + struct inode *inode = file_inode(file); + struct address_space *mapping = inode->i_mapping; + struct ntfs_inode *ni = ntfs_i(inode); + u64 valid = ni->i_valid; + struct ntfs_sb_info *sbi = ni->mi.sbi; + struct page *page, **pages = NULL; + size_t written = 0; + u8 frame_bits = NTFS_LZNT_CUNIT + sbi->cluster_bits; + u32 frame_size = 1u << frame_bits; + u32 pages_per_frame = frame_size >> PAGE_SHIFT; + u32 npages, ip, off; + CLST frame; + u64 frame_vbo; + pgoff_t index, max_index; + + if (frame_size < PAGE_SIZE) { + /* + * frame_size == 8K if cluster 512 + * frame_size == 64K if cluster 4096 + */ + ntfs_inode_warn(inode, "page size is bigger than frame size"); + return -EOPNOTSUPP; + } + + pages = ntfs_alloc(pages_per_frame * sizeof(struct page *), 0); + if (!pages) + return -ENOMEM; + + current->backing_dev_info = inode_to_bdi(inode); + err = file_remove_privs(file); + if (err) + goto out; + + err = file_update_time(file); + if (err) + goto out; + + /* zero range [valid : pos) */ + max_index = (pos + PAGE_SIZE - 1) >> PAGE_SHIFT; + while (valid < pos) { + CLST lcn, clen; + + frame = valid >> frame_bits; + frame_vbo = valid & ~(frame_size - 1); + off = valid & (frame_size - 1); + + err = attr_data_get_block(ni, frame << NTFS_LZNT_CUNIT, 0, &lcn, + &clen, NULL); + if (err) + goto out; + + if (lcn == SPARSE_LCN) { + ni->i_valid = valid = + frame_vbo + ((u64)clen << sbi->cluster_bits); + continue; + } + + /* Load full frame */ + err = ntfs_get_frame(mapping, frame_vbo >> PAGE_SHIFT, pages, + pages_per_frame, max_index, !off); + if (err < 0) + goto out; + + npages = err; + + ip = off >> PAGE_SHIFT; + off = offset_in_page(valid); + for (; ip < npages; ip++, off = 0) { + page = pages[ip]; + zero_user_segment(page, off, PAGE_SIZE); + flush_dcache_page(page); + SetPageUptodate(page); + } + + ni_lock(ni); + err = ni_write_frame(ni, pages, npages); + ni_unlock(ni); + + for (ip = 0; ip < npages; ip++) { + page = pages[ip]; + ClearPageDirty(page); + SetPageUptodate(page); + unlock_page(page); + put_page(page); + } + + if (err) + goto out; + + ni->i_valid = valid = frame_vbo + frame_size; + } + + max_index = (inode->i_size + PAGE_SIZE - 1) >> PAGE_SHIFT; + + /* copy user data [pos : pos + count) */ + while (count) { + size_t copied, bytes; + bool skip_read; + + off = pos & (frame_size - 1); + bytes = frame_size - off; + if (bytes > count) + bytes = count; + + frame = pos >> frame_bits; + frame_vbo = pos & ~(frame_size - 1); + index = frame_vbo >> PAGE_SHIFT; + + skip_read = !off && (bytes >= frame_size || + pos + bytes >= inode->i_size); + + if (unlikely(iov_iter_fault_in_readable(from, bytes))) { + err = -EFAULT; + goto out; + } + + /* Load full frame */ + err = ntfs_get_frame(mapping, index, pages, pages_per_frame, + max_index, skip_read); + if (err < 0) + goto out; + + npages = err; + + WARN_ON(!bytes); + copied = 0; + ip = off >> PAGE_SHIFT; + off = offset_in_page(pos); + + /* copy user data to pages */ + for (;;) { + size_t cp, tail = PAGE_SIZE - off; + + page = pages[ip]; + + cp = iov_iter_copy_from_user_atomic(page, from, off, + min(tail, bytes)); + flush_dcache_page(page); + + iov_iter_advance(from, cp); + copied += cp; + bytes -= cp; + if (!bytes || !cp) + break; + + if (cp < tail) { + off += cp; + } else { + ip++; + off = 0; + } + } + + ni_lock(ni); + err = ni_write_frame(ni, pages, npages); + ni_unlock(ni); + + for (ip = 0; ip < npages; ip++) { + page = pages[ip]; + ClearPageDirty(page); + SetPageUptodate(page); + unlock_page(page); + put_page(page); + } + + if (err) + goto out; + + /* + * We can loop for a long time in here. Be nice and allow + * us to schedule out to avoid softlocking if preempt + * is disabled. + */ + cond_resched(); + + pos += copied; + written += copied; + + count = iov_iter_count(from); + } + +out: + ntfs_free(pages); + + current->backing_dev_info = NULL; + + if (err < 0) + return err; + + iocb->ki_pos += written; + if (iocb->ki_pos > ni->i_valid) + ni->i_valid = iocb->ki_pos; + + return written; +} + +/* + * file_operations::write_iter + */ +static ssize_t ntfs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) +{ + struct file *file = iocb->ki_filp; + struct address_space *mapping = file->f_mapping; + struct inode *inode = mapping->host; + ssize_t ret; + struct ntfs_inode *ni = ntfs_i(inode); + + if (is_encrypted(ni)) { + ntfs_inode_warn(inode, "encrypted i/o not supported"); + return -EOPNOTSUPP; + } + + if (is_compressed(ni) && (iocb->ki_flags & IOCB_DIRECT)) { + ntfs_inode_warn(inode, "direct i/o + compressed not supported"); + return -EOPNOTSUPP; + } + + if (ni->ni_flags & NI_FLAG_COMPRESSED_MASK) { + ntfs_inode_warn( + inode, + "write into external compressed file not supported (temporary)"); + return -EOPNOTSUPP; + } + + if (is_dedup(ni)) { + ntfs_inode_warn(inode, "write into deduplicated not supported"); + return -EOPNOTSUPP; + } + + if (!inode_trylock(inode)) { + if (iocb->ki_flags & IOCB_NOWAIT) + return -EAGAIN; + inode_lock(inode); + } + + ret = generic_write_checks(iocb, from); + if (ret <= 0) + goto out; + + ret = ntfs_extend_ex(inode, iocb->ki_pos, ret, file); + if (ret) + goto out; + + ret = is_compressed(ni) ? ntfs_compress_write(iocb, from) : + __generic_file_write_iter(iocb, from); + +out: + inode_unlock(inode); + + if (ret > 0) + ret = generic_write_sync(iocb, ret); + + return ret; +} + +/* + * file_operations::open + */ +int ntfs_file_open(struct inode *inode, struct file *file) +{ + struct ntfs_inode *ni = ntfs_i(inode); + + if (unlikely((is_compressed(ni) || is_encrypted(ni)) && + (file->f_flags & O_DIRECT))) { + return -EOPNOTSUPP; + } + + return generic_file_open(inode, file); +} + +/* + * file_operations::release + */ +static int ntfs_file_release(struct inode *inode, struct file *file) +{ + struct ntfs_inode *ni = ntfs_i(inode); + struct ntfs_sb_info *sbi; + int err; + + /* if we are the last writer on the inode, drop the block reservation */ + if (!(file->f_mode & FMODE_WRITE) || + atomic_read(&inode->i_writecount) != 1) + return 0; + + sbi = ni->mi.sbi; + + ni_lock(ni); + down_write(&ni->file.run_lock); + + err = attr_set_size(ni, ATTR_DATA, NULL, 0, &ni->file.run, + inode->i_size, &ni->i_valid, false, NULL); + up_write(&ni->file.run_lock); + ni_unlock(ni); + + return err; +} + +/* file_operations::fiemap */ +int ntfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, + __u64 start, __u64 len) +{ + int err; + struct ntfs_inode *ni = ntfs_i(inode); + + if (fieinfo->fi_flags & FIEMAP_FLAG_XATTR) + return -EOPNOTSUPP; + + ni_lock(ni); + + err = ni_fiemap(ni, fieinfo, start, len); + + ni_unlock(ni); + + return err; +} + +const struct inode_operations ntfs_file_inode_operations = { + .getattr = ntfs_getattr, + .setattr = ntfs_setattr, + .listxattr = ntfs_listxattr, + .permission = ntfs_permission, + .get_acl = ntfs_get_acl, + .set_acl = ntfs_set_acl, + .fiemap = ntfs_fiemap, +}; + +const struct file_operations ntfs_file_operations = { + .llseek = generic_file_llseek, + .read_iter = ntfs_file_read_iter, + .write_iter = ntfs_file_write_iter, + .unlocked_ioctl = ntfs_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = ntfs_compat_ioctl, +#endif + .splice_read = generic_file_splice_read, + .mmap = ntfs_file_mmap, + .open = ntfs_file_open, + .fsync = ntfs_file_fsync, + .splice_write = iter_file_splice_write, + .fallocate = ntfs_fallocate, + .release = ntfs_file_release, +}; diff --git a/fs/ntfs3/frecord.c b/fs/ntfs3/frecord.c new file mode 100644 index 000000000000..6894f0855a62 --- /dev/null +++ b/fs/ntfs3/frecord.c @@ -0,0 +1,2335 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * linux/fs/ntfs3/frecord.c + * + * Copyright (C) 2019-2020 Paragon Software GmbH, All rights reserved. + * + */ + +#include +#include +#include +#include +#include +#include + +#include "debug.h" +#include "ntfs.h" +#include "ntfs_fs.h" + +static inline void get_mi_ref(const struct mft_inode *mi, struct MFT_REF *ref) +{ +#ifdef NTFS3_64BIT_CLUSTER + ref->low = cpu_to_le32(mi->rno); + ref->high = cpu_to_le16(mi->rno >> 32); +#else + ref->low = cpu_to_le32(mi->rno); + ref->high = 0; +#endif + ref->seq = mi->mrec->seq; +} + +static struct mft_inode *ni_ins_mi(struct ntfs_inode *ni, struct rb_root *tree, + CLST ino, struct rb_node *ins) +{ + struct rb_node **p = &tree->rb_node; + struct rb_node *pr = NULL; + + while (*p) { + struct mft_inode *mi; + + pr = *p; + mi = rb_entry(pr, struct mft_inode, node); + if (mi->rno > ino) + p = &pr->rb_left; + else if (mi->rno < ino) + p = &pr->rb_right; + else + return mi; + } + + if (!ins) + return NULL; + + rb_link_node(ins, pr, p); + rb_insert_color(ins, tree); + return rb_entry(ins, struct mft_inode, node); +} + +/* + * ni_find_mi + * + * finds mft_inode by record number + */ +static struct mft_inode *ni_find_mi(struct ntfs_inode *ni, CLST rno) +{ + return ni_ins_mi(ni, &ni->mi_tree, rno, NULL); +} + +/* + * ni_add_mi + * + * adds new mft_inode into ntfs_inode + */ +static void ni_add_mi(struct ntfs_inode *ni, struct mft_inode *mi) +{ + ni_ins_mi(ni, &ni->mi_tree, mi->rno, &mi->node); +} + +/* + * ni_remove_mi + * + * removes mft_inode from ntfs_inode + */ +void ni_remove_mi(struct ntfs_inode *ni, struct mft_inode *mi) +{ + rb_erase(&mi->node, &ni->mi_tree); +} + +/* + * ni_std + * + * returns pointer into std_info from primary record + */ +struct ATTR_STD_INFO *ni_std(struct ntfs_inode *ni) +{ + const struct ATTRIB *attr; + + attr = mi_find_attr(&ni->mi, NULL, ATTR_STD, NULL, 0, NULL); + return attr ? resident_data_ex(attr, sizeof(struct ATTR_STD_INFO)) : + NULL; +} + +/* + * ni_std5 + * + * returns pointer into std_info from primary record + */ +struct ATTR_STD_INFO5 *ni_std5(struct ntfs_inode *ni) +{ + const struct ATTRIB *attr; + + attr = mi_find_attr(&ni->mi, NULL, ATTR_STD, NULL, 0, NULL); + + return attr ? resident_data_ex(attr, sizeof(struct ATTR_STD_INFO5)) : + NULL; +} + +/* + * ni_clear + * + * clears resources allocated by ntfs_inode + */ +void ni_clear(struct ntfs_inode *ni) +{ + struct rb_node *node; + + if (!ni->vfs_inode.i_nlink && is_rec_inuse(ni->mi.mrec)) + ni_delete_all(ni); + + al_destroy(ni); + + for (node = rb_first(&ni->mi_tree); node;) { + struct rb_node *next = rb_next(node); + struct mft_inode *mi = rb_entry(node, struct mft_inode, node); + + rb_erase(node, &ni->mi_tree); + mi_put(mi); + node = next; + } + + /* bad inode always has mode == S_IFREG */ + if (ni->ni_flags & NI_FLAG_DIR) + indx_clear(&ni->dir); + else + run_close(&ni->file.run); + + mi_clear(&ni->mi); +} + +/* + * ni_load_mi_ex + * + * finds mft_inode by record number. + */ +int ni_load_mi_ex(struct ntfs_inode *ni, CLST rno, struct mft_inode **mi) +{ + int err; + struct mft_inode *r; + + r = ni_find_mi(ni, rno); + if (r) + goto out; + + err = mi_get(ni->mi.sbi, rno, &r); + if (err) + return err; + + ni_add_mi(ni, r); + +out: + if (mi) + *mi = r; + return 0; +} + +/* + * ni_load_mi + * + * load mft_inode corresponded list_entry + */ +int ni_load_mi(struct ntfs_inode *ni, struct ATTR_LIST_ENTRY *le, + struct mft_inode **mi) +{ + CLST rno; + + if (!le) { + *mi = &ni->mi; + return 0; + } + + rno = ino_get(&le->ref); + if (rno == ni->mi.rno) { + *mi = &ni->mi; + return 0; + } + return ni_load_mi_ex(ni, rno, mi); +} + +/* + * ni_find_attr + * + * returns attribute and record this attribute belongs to + */ +struct ATTRIB *ni_find_attr(struct ntfs_inode *ni, struct ATTRIB *attr, + struct ATTR_LIST_ENTRY **le_o, enum ATTR_TYPE type, + const __le16 *name, u8 name_len, const CLST *vcn, + struct mft_inode **mi) +{ + struct ATTR_LIST_ENTRY *le; + struct mft_inode *m; + + if (!ni->attr_list.size || + (!name_len && (type == ATTR_LIST || type == ATTR_STD))) { + if (le_o) + *le_o = NULL; + if (mi) + *mi = &ni->mi; + + /* Look for required attribute in primary record */ + return mi_find_attr(&ni->mi, attr, type, name, name_len, NULL); + } + + /* first look for list entry of required type */ + le = al_find_ex(ni, le_o ? *le_o : NULL, type, name, name_len, vcn); + if (!le) + return NULL; + + if (le_o) + *le_o = le; + + /* Load record that contains this attribute */ + if (ni_load_mi(ni, le, &m)) + return NULL; + + /* Look for required attribute */ + attr = mi_find_attr(m, NULL, type, name, name_len, &le->id); + + if (!attr) + goto out; + + if (!attr->non_res) { + if (vcn && *vcn) + goto out; + } else if (!vcn) { + if (attr->nres.svcn) + goto out; + } else if (le64_to_cpu(attr->nres.svcn) > *vcn || + *vcn > le64_to_cpu(attr->nres.evcn)) { + goto out; + } + + if (mi) + *mi = m; + return attr; + +out: + ntfs_set_state(ni->mi.sbi, NTFS_DIRTY_ERROR); + return NULL; +} + +/* + * ni_enum_attr_ex + * + * enumerates attributes in ntfs_inode + */ +struct ATTRIB *ni_enum_attr_ex(struct ntfs_inode *ni, struct ATTRIB *attr, + struct ATTR_LIST_ENTRY **le) +{ + struct mft_inode *mi; + struct ATTR_LIST_ENTRY *le2; + + /* Do we have an attribute list? */ + if (!ni->attr_list.size) { + *le = NULL; + /* Enum attributes in primary record */ + return mi_enum_attr(&ni->mi, attr); + } + + /* get next list entry */ + le2 = *le = al_enumerate(ni, attr ? *le : NULL); + if (!le2) + return NULL; + + /* Load record that contains the required attribute */ + if (ni_load_mi(ni, le2, &mi)) + return NULL; + + /* Find attribute in loaded record */ + attr = rec_find_attr_le(mi, le2); + return attr; +} + +/* + * ni_load_attr + * + * loads attribute that contains given vcn + */ +struct ATTRIB *ni_load_attr(struct ntfs_inode *ni, enum ATTR_TYPE type, + const __le16 *name, u8 name_len, CLST vcn, + struct mft_inode **pmi) +{ + struct ATTR_LIST_ENTRY *le; + struct ATTRIB *attr; + struct mft_inode *mi; + struct ATTR_LIST_ENTRY *next; + + if (!ni->attr_list.size) { + if (pmi) + *pmi = &ni->mi; + return mi_find_attr(&ni->mi, NULL, type, name, name_len, NULL); + } + + le = al_find_ex(ni, NULL, type, name, name_len, NULL); + if (!le) + return NULL; + + /* + * Unfortunately ATTR_LIST_ENTRY contains only start vcn + * So to find the ATTRIB segment that contains 'vcn' we should + * enumerate some entries + */ + if (vcn) { + for (;; le = next) { + next = al_find_ex(ni, le, type, name, name_len, NULL); + if (!next || le64_to_cpu(next->vcn) > vcn) + break; + } + } + + if (ni_load_mi(ni, le, &mi)) + return NULL; + + if (pmi) + *pmi = mi; + + attr = mi_find_attr(mi, NULL, type, name, name_len, &le->id); + if (!attr) + return NULL; + + if (!attr->non_res) + return attr; + + if (le64_to_cpu(attr->nres.svcn) <= vcn && + vcn <= le64_to_cpu(attr->nres.evcn)) + return attr; + + return NULL; +} + +/* + * ni_load_all_mi + * + * loads all subrecords + */ +int ni_load_all_mi(struct ntfs_inode *ni) +{ + int err; + struct ATTR_LIST_ENTRY *le; + + if (!ni->attr_list.size) + return 0; + + le = NULL; + + while ((le = al_enumerate(ni, le))) { + CLST rno = ino_get(&le->ref); + + if (rno == ni->mi.rno) + continue; + + err = ni_load_mi_ex(ni, rno, NULL); + if (err) + return err; + } + + return 0; +} + +/* + * ni_add_subrecord + * + * allocate + format + attach a new subrecord + */ +bool ni_add_subrecord(struct ntfs_inode *ni, CLST rno, struct mft_inode **mi) +{ + struct mft_inode *m; + + m = ntfs_alloc(sizeof(struct mft_inode), 1); + if (!m) + return false; + + if (mi_format_new(m, ni->mi.sbi, rno, 0, ni->mi.rno == MFT_REC_MFT)) { + mi_put(m); + return false; + } + + get_mi_ref(&ni->mi, &m->mrec->parent_ref); + + ni_add_mi(ni, m); + *mi = m; + return true; +} + +/* + * ni_remove_attr + * + * removes all attributes for the given type/name/id + */ +int ni_remove_attr(struct ntfs_inode *ni, enum ATTR_TYPE type, + const __le16 *name, size_t name_len, bool base_only, + const __le16 *id) +{ + int err; + struct ATTRIB *attr; + struct ATTR_LIST_ENTRY *le; + struct mft_inode *mi; + u32 type_in; + int diff; + + if (base_only || type == ATTR_LIST || !ni->attr_list.size) { + attr = mi_find_attr(&ni->mi, NULL, type, name, name_len, id); + if (!attr) + return -ENOENT; + + mi_remove_attr(&ni->mi, attr); + return 0; + } + + type_in = le32_to_cpu(type); + le = NULL; + + for (;;) { + le = al_enumerate(ni, le); + if (!le) + return 0; + +next_le2: + diff = le32_to_cpu(le->type) - type_in; + if (diff < 0) + continue; + + if (diff > 0) + return 0; + + if (le->name_len != name_len) + continue; + + if (name_len && + memcmp(le_name(le), name, name_len * sizeof(short))) + continue; + + if (id && le->id != *id) + continue; + err = ni_load_mi(ni, le, &mi); + if (err) + return err; + + al_remove_le(ni, le); + + attr = mi_find_attr(mi, NULL, type, name, name_len, id); + if (!attr) + return -ENOENT; + + mi_remove_attr(mi, attr); + + if (PtrOffset(ni->attr_list.le, le) >= ni->attr_list.size) + return 0; + goto next_le2; + } +} + +/* + * ni_ins_new_attr + * + * inserts the attribute into record + * Returns not full constructed attribute or NULL if not possible to create + */ +static struct ATTRIB *ni_ins_new_attr(struct ntfs_inode *ni, + struct mft_inode *mi, + struct ATTR_LIST_ENTRY *le, + enum ATTR_TYPE type, const __le16 *name, + u8 name_len, u32 asize, u16 name_off, + CLST svcn) +{ + int err; + struct ATTRIB *attr; + bool le_added = false; + struct MFT_REF ref; + + get_mi_ref(mi, &ref); + + if (type != ATTR_LIST && !le && ni->attr_list.size) { + err = al_add_le(ni, type, name, name_len, svcn, cpu_to_le16(-1), + &ref, &le); + if (err) { + /* no memory or no space */ + return NULL; + } + le_added = true; + + /* + * al_add_le -> attr_set_size (list) -> ni_expand_list + * which moves some attributes out of primary record + * this means that name may point into moved memory + * reinit 'name' from le + */ + name = le->name; + } + + attr = mi_insert_attr(mi, type, name, name_len, asize, name_off); + if (!attr) { + if (le_added) + al_remove_le(ni, le); + return NULL; + } + + if (type == ATTR_LIST) { + /*attr list is not in list entry array*/ + goto out; + } + + if (!le) + goto out; + + /* Update ATTRIB Id and record reference */ + le->id = attr->id; + ni->attr_list.dirty = true; + le->ref = ref; + +out: + + return attr; +} + +/* + * ni_create_attr_list + * + * generates an attribute list for this primary record + */ +int ni_create_attr_list(struct ntfs_inode *ni) +{ + struct ntfs_sb_info *sbi = ni->mi.sbi; + int err; + u32 lsize; + struct ATTRIB *attr; + struct ATTRIB *arr_move[7]; + struct ATTR_LIST_ENTRY *le, *le_b[7]; + struct MFT_REC *rec; + bool is_mft; + CLST rno = 0; + struct mft_inode *mi; + u32 free_b, nb, to_free, rs; + u16 sz; + + is_mft = ni->mi.rno == MFT_REC_MFT; + rec = ni->mi.mrec; + rs = sbi->record_size; + + /* + * Skip estimating exact memory requirement + * Looks like one record_size is always enough + */ + le = ntfs_alloc(al_aligned(rs), 0); + if (!le) { + err = -ENOMEM; + goto out; + } + + get_mi_ref(&ni->mi, &le->ref); + ni->attr_list.le = le; + + attr = NULL; + nb = 0; + free_b = 0; + attr = NULL; + + for (; (attr = mi_enum_attr(&ni->mi, attr)); le = Add2Ptr(le, sz)) { + sz = le_size(attr->name_len); + WARN_ON(PtrOffset(ni->attr_list.le, le) + sz > rs); + + le->type = attr->type; + le->size = cpu_to_le16(sz); + le->name_len = attr->name_len; + le->name_off = offsetof(struct ATTR_LIST_ENTRY, name); + le->vcn = 0; + if (le != ni->attr_list.le) + le->ref = ni->attr_list.le->ref; + le->id = attr->id; + + if (attr->name_len) + memcpy(le->name, attr_name(attr), + sizeof(short) * attr->name_len); + else if (attr->type == ATTR_STD) + continue; + else if (attr->type == ATTR_LIST) + continue; + else if (is_mft && attr->type == ATTR_DATA) + continue; + + if (!nb || nb < ARRAY_SIZE(arr_move)) { + le_b[nb] = le; + arr_move[nb++] = attr; + free_b += le32_to_cpu(attr->size); + } + } + + lsize = PtrOffset(ni->attr_list.le, le); + ni->attr_list.size = lsize; + + to_free = le32_to_cpu(rec->used) + lsize + SIZEOF_RESIDENT; + if (to_free <= rs) { + to_free = 0; + } else { + to_free -= rs; + + if (to_free > free_b) { + err = -EINVAL; + goto out1; + } + } + + /* Allocate child mft. */ + err = ntfs_look_free_mft(sbi, &rno, is_mft, ni, &mi); + if (err) + goto out1; + + /* Call 'mi_remove_attr' in reverse order to keep pointers 'arr_move' valid */ + while (to_free > 0) { + struct ATTRIB *b = arr_move[--nb]; + u32 asize = le32_to_cpu(b->size); + u16 name_off = le16_to_cpu(b->name_off); + + attr = mi_insert_attr(mi, b->type, Add2Ptr(b, name_off), + b->name_len, asize, name_off); + WARN_ON(!attr); + + get_mi_ref(mi, &le_b[nb]->ref); + le_b[nb]->id = attr->id; + + /* copy all except id */ + memcpy(attr, b, asize); + attr->id = le_b[nb]->id; + + WARN_ON(!mi_remove_attr(&ni->mi, b)); + + if (to_free <= asize) + break; + to_free -= asize; + WARN_ON(!nb); + } + + attr = mi_insert_attr(&ni->mi, ATTR_LIST, NULL, 0, + lsize + SIZEOF_RESIDENT, SIZEOF_RESIDENT); + WARN_ON(!attr); + + attr->non_res = 0; + attr->flags = 0; + attr->res.data_size = cpu_to_le32(lsize); + attr->res.data_off = SIZEOF_RESIDENT_LE; + attr->res.flags = 0; + attr->res.res = 0; + + memcpy(resident_data_ex(attr, lsize), ni->attr_list.le, lsize); + + ni->attr_list.dirty = false; + + mark_inode_dirty(&ni->vfs_inode); + goto out; + +out1: + ntfs_free(ni->attr_list.le); + ni->attr_list.le = NULL; + ni->attr_list.size = 0; + +out: + return err; +} + +/* + * ni_ins_attr_ext + * + * This method adds an external attribute to the ntfs_inode. + */ +static int ni_ins_attr_ext(struct ntfs_inode *ni, struct ATTR_LIST_ENTRY *le, + enum ATTR_TYPE type, const __le16 *name, u8 name_len, + u32 asize, CLST svcn, u16 name_off, bool force_ext, + struct ATTRIB **ins_attr, struct mft_inode **ins_mi) +{ + struct ATTRIB *attr; + struct mft_inode *mi; + CLST rno; + u64 vbo; + struct rb_node *node; + int err; + bool is_mft, is_mft_data; + struct ntfs_sb_info *sbi = ni->mi.sbi; + + is_mft = ni->mi.rno == MFT_REC_MFT; + is_mft_data = is_mft && type == ATTR_DATA && !name_len; + + if (asize > sbi->max_bytes_per_attr) { + err = -EINVAL; + goto out; + } + + /* + * standard information and attr_list cannot be made external. + * The Log File cannot have any external attributes + */ + if (type == ATTR_STD || type == ATTR_LIST || + ni->mi.rno == MFT_REC_LOG) { + err = -EINVAL; + goto out; + } + + /* Create attribute list if it is not already existed */ + if (!ni->attr_list.size) { + err = ni_create_attr_list(ni); + if (err) + goto out; + } + + vbo = is_mft_data ? ((u64)svcn << sbi->cluster_bits) : 0; + + if (force_ext) + goto insert_ext; + + /* Load all subrecords into memory. */ + err = ni_load_all_mi(ni); + if (err) + goto out; + + /* Check each of loaded subrecord */ + for (node = rb_first(&ni->mi_tree); node; node = rb_next(node)) { + mi = rb_entry(node, struct mft_inode, node); + + if (is_mft_data && + (mi_enum_attr(mi, NULL) || + vbo <= ((u64)mi->rno << sbi->record_bits))) { + /* We can't accept this record 'case MFT's bootstrapping */ + continue; + } + if (is_mft && + mi_find_attr(mi, NULL, ATTR_DATA, NULL, 0, NULL)) { + /* + * This child record already has a ATTR_DATA. + * So it can't accept any other records. + */ + continue; + } + + if ((type != ATTR_NAME || name_len) && + mi_find_attr(mi, NULL, type, name, name_len, NULL)) { + /* Only indexed attributes can share same record */ + continue; + } + + /* Try to insert attribute into this subrecord */ + attr = ni_ins_new_attr(ni, mi, le, type, name, name_len, asize, + name_off, svcn); + if (!attr) + continue; + + if (ins_attr) + *ins_attr = attr; + return 0; + } + +insert_ext: + /* We have to allocate a new child subrecord*/ + err = ntfs_look_free_mft(sbi, &rno, is_mft_data, ni, &mi); + if (err) + goto out; + + if (is_mft_data && vbo <= ((u64)rno << sbi->record_bits)) { + err = -EINVAL; + goto out1; + } + + attr = ni_ins_new_attr(ni, mi, le, type, name, name_len, asize, + name_off, svcn); + if (!attr) + goto out2; + + if (ins_attr) + *ins_attr = attr; + if (ins_mi) + *ins_mi = mi; + + return 0; + +out2: + ni_remove_mi(ni, mi); + mi_put(mi); + err = -EINVAL; + +out1: + ntfs_mark_rec_free(sbi, rno); + +out: + return err; +} + +/* + * ni_insert_attr + * + * inserts an attribute into the file. + * + * If the primary record has room, it will just insert the attribute. + * If not, it may make the attribute external. + * For $MFT::Data it may make room for the attribute by + * making other attributes external. + * + * NOTE: + * The ATTR_LIST and ATTR_STD cannot be made external. + * This function does not fill new attribute full + * It only fills 'size'/'type'/'id'/'name_len' fields + */ +static int ni_insert_attr(struct ntfs_inode *ni, enum ATTR_TYPE type, + const __le16 *name, u8 name_len, u32 asize, + u16 name_off, CLST svcn, struct ATTRIB **ins_attr, + struct mft_inode **ins_mi) +{ + struct ntfs_sb_info *sbi = ni->mi.sbi; + int err; + struct ATTRIB *attr, *eattr; + struct MFT_REC *rec; + bool is_mft; + struct ATTR_LIST_ENTRY *le; + u32 list_reserve, max_free, free, used, t32; + __le16 id; + u16 t16; + + is_mft = ni->mi.rno == MFT_REC_MFT; + rec = ni->mi.mrec; + + list_reserve = SIZEOF_NONRESIDENT + 3 * (1 + 2 * sizeof(u32)); + used = le32_to_cpu(rec->used); + free = sbi->record_size - used; + + if (is_mft && type != ATTR_LIST) { + /* Reserve space for the ATTRIB List. */ + if (free < list_reserve) + free = 0; + else + free -= list_reserve; + } + + if (asize <= free) { + attr = ni_ins_new_attr(ni, &ni->mi, NULL, type, name, name_len, + asize, name_off, svcn); + if (attr) { + if (ins_attr) + *ins_attr = attr; + if (ins_mi) + *ins_mi = &ni->mi; + err = 0; + goto out; + } + } + + if (!is_mft || type != ATTR_DATA || svcn) { + /* This ATTRIB will be external. */ + err = ni_ins_attr_ext(ni, NULL, type, name, name_len, asize, + svcn, name_off, false, ins_attr, ins_mi); + goto out; + } + + /* + * Here we have: "is_mft && type == ATTR_DATA && !svcn + * + * The first chunk of the $MFT::Data ATTRIB must be the base record. + * Evict as many other attributes as possible. + */ + max_free = free; + + /* Estimate the result of moving all possible attributes away.*/ + attr = NULL; + + while ((attr = mi_enum_attr(&ni->mi, attr))) { + if (attr->type == ATTR_STD) + continue; + if (attr->type == ATTR_LIST) + continue; + max_free += le32_to_cpu(attr->size); + } + + if (max_free < asize + list_reserve) { + /* Impossible to insert this attribute into primary record */ + err = -EINVAL; + goto out; + } + + /* Start real attribute moving */ + attr = NULL; + + for (;;) { + attr = mi_enum_attr(&ni->mi, attr); + if (!attr) { + /* We should never be here 'cause we have already check this case */ + err = -EINVAL; + goto out; + } + + /* Skip attributes that MUST be primary record */ + if (attr->type == ATTR_STD || attr->type == ATTR_LIST) + continue; + + le = NULL; + if (ni->attr_list.size) { + le = al_find_le(ni, NULL, attr); + if (!le) { + /* Really this is a serious bug */ + err = -EINVAL; + goto out; + } + } + + t32 = le32_to_cpu(attr->size); + t16 = le16_to_cpu(attr->name_off); + err = ni_ins_attr_ext(ni, le, attr->type, Add2Ptr(attr, t16), + attr->name_len, t32, attr_svcn(attr), t16, + false, &eattr, NULL); + if (err) + return err; + + id = eattr->id; + memcpy(eattr, attr, t32); + eattr->id = id; + + /* remove attrib from primary record */ + mi_remove_attr(&ni->mi, attr); + + /* attr now points to next attribute */ + if (attr->type == ATTR_END) + goto out; + } + while (asize + list_reserve > sbi->record_size - le32_to_cpu(rec->used)) + ; + + attr = ni_ins_new_attr(ni, &ni->mi, NULL, type, name, name_len, asize, + name_off, svcn); + if (!attr) { + err = -EINVAL; + goto out; + } + + if (ins_attr) + *ins_attr = attr; + if (ins_mi) + *ins_mi = &ni->mi; + +out: + return err; +} + +/* + * ni_expand_mft_list + * + * This method splits ATTR_DATA of $MFT + */ +static int ni_expand_mft_list(struct ntfs_inode *ni) +{ + int err = 0; + struct runs_tree *run = &ni->file.run; + u32 asize, run_size, done = 0; + struct ATTRIB *attr; + struct rb_node *node; + CLST mft_min, mft_new, svcn, evcn, plen; + struct mft_inode *mi, *mi_min, *mi_new; + struct ntfs_sb_info *sbi = ni->mi.sbi; + + /* Find the nearest Mft */ + mft_min = 0; + mft_new = 0; + mi_min = NULL; + + for (node = rb_first(&ni->mi_tree); node; node = rb_next(node)) { + mi = rb_entry(node, struct mft_inode, node); + + attr = mi_enum_attr(mi, NULL); + + if (!attr) { + mft_min = mi->rno; + mi_min = mi; + break; + } + } + + if (ntfs_look_free_mft(sbi, &mft_new, true, ni, &mi_new)) { + mft_new = 0; + // really this is not critical + } else if (mft_min > mft_new) { + mft_min = mft_new; + mi_min = mi_new; + } else { + ntfs_mark_rec_free(sbi, mft_new); + mft_new = 0; + ni_remove_mi(ni, mi_new); + } + + attr = mi_find_attr(&ni->mi, NULL, ATTR_DATA, NULL, 0, NULL); + if (!attr) { + err = -EINVAL; + goto out; + } + + asize = le32_to_cpu(attr->size); + + evcn = le64_to_cpu(attr->nres.evcn); + svcn = bytes_to_cluster(sbi, (u64)(mft_min + 1) << sbi->record_bits); + if (evcn + 1 >= svcn) { + err = -EINVAL; + goto out; + } + + /* + * split primary attribute [0 evcn] in two parts [0 svcn) + [svcn evcn] + * + * Update first part of ATTR_DATA in 'primary MFT + */ + err = run_pack(run, 0, svcn, Add2Ptr(attr, SIZEOF_NONRESIDENT), + asize - SIZEOF_NONRESIDENT, &plen); + if (err < 0) + goto out; + + run_size = QuadAlign(err); + err = 0; + + if (plen < svcn) { + err = -EINVAL; + goto out; + } + + attr->nres.evcn = cpu_to_le64(svcn - 1); + attr->size = cpu_to_le32(run_size + SIZEOF_NONRESIDENT); + /* 'done' - how many bytes of primary MFT becomes free */ + done = asize - run_size - SIZEOF_NONRESIDENT; + le32_sub_cpu(&ni->mi.mrec->used, done); + + /* Estimate the size of second part: run_buf=NULL */ + err = run_pack(run, svcn, evcn + 1 - svcn, NULL, sbi->record_size, + &plen); + if (err < 0) + goto out; + + run_size = QuadAlign(err); + err = 0; + + if (plen < evcn + 1 - svcn) { + err = -EINVAL; + goto out; + } + + /* + * This function may implicitly call expand attr_list + * Insert second part of ATTR_DATA in 'mi_min' + */ + attr = ni_ins_new_attr(ni, mi_min, NULL, ATTR_DATA, NULL, 0, + SIZEOF_NONRESIDENT + run_size, + SIZEOF_NONRESIDENT, svcn); + if (!attr) { + err = -EINVAL; + goto out; + } + + attr->non_res = 1; + attr->name_off = SIZEOF_NONRESIDENT_LE; + attr->flags = 0; + + run_pack(run, svcn, evcn + 1 - svcn, Add2Ptr(attr, SIZEOF_NONRESIDENT), + run_size, &plen); + + attr->nres.svcn = cpu_to_le64(svcn); + attr->nres.evcn = cpu_to_le64(evcn); + attr->nres.run_off = cpu_to_le16(SIZEOF_NONRESIDENT); + +out: + if (mft_new) { + ntfs_mark_rec_free(sbi, mft_new); + ni_remove_mi(ni, mi_new); + } + + return !err && !done ? -EOPNOTSUPP : err; +} + +/* + * ni_expand_list + * + * This method moves all possible attributes out of primary record + */ +int ni_expand_list(struct ntfs_inode *ni) +{ + int err = 0; + u32 asize, done = 0; + struct ATTRIB *attr, *ins_attr; + struct ATTR_LIST_ENTRY *le; + bool is_mft = ni->mi.rno == MFT_REC_MFT; + struct MFT_REF ref; + + get_mi_ref(&ni->mi, &ref); + le = NULL; + + while ((le = al_enumerate(ni, le))) { + if (le->type == ATTR_STD) + continue; + + if (memcmp(&ref, &le->ref, sizeof(struct MFT_REF))) + continue; + + if (is_mft && le->type == ATTR_DATA) + continue; + + /* Find attribute in primary record */ + attr = rec_find_attr_le(&ni->mi, le); + if (!attr) { + err = -EINVAL; + goto out; + } + + asize = le32_to_cpu(attr->size); + + /* Always insert into new record to avoid collisions (deep recursive) */ + err = ni_ins_attr_ext(ni, le, attr->type, attr_name(attr), + attr->name_len, asize, attr_svcn(attr), + le16_to_cpu(attr->name_off), true, + &ins_attr, NULL); + + if (err) + goto out; + + memcpy(ins_attr, attr, asize); + ins_attr->id = le->id; + mi_remove_attr(&ni->mi, attr); + + done += asize; + goto out; + } + + if (!is_mft) { + err = -EFBIG; /* attr list is too big(?) */ + goto out; + } + + /* split mft data as much as possible */ + err = ni_expand_mft_list(ni); + if (err) + goto out; + +out: + return !err && !done ? -EOPNOTSUPP : err; +} + +/* + * ni_insert_nonresident + * + * inserts new nonresident attribute + */ +int ni_insert_nonresident(struct ntfs_inode *ni, enum ATTR_TYPE type, + const __le16 *name, u8 name_len, + const struct runs_tree *run, CLST svcn, CLST len, + __le16 flags, struct ATTRIB **new_attr, + struct mft_inode **mi) +{ + int err; + CLST plen; + struct ATTRIB *attr; + bool is_ext = + (flags & (ATTR_FLAG_SPARSED | ATTR_FLAG_COMPRESSED)) && !svcn; + u32 name_size = QuadAlign(name_len * sizeof(short)); + u32 name_off = is_ext ? SIZEOF_NONRESIDENT_EX : SIZEOF_NONRESIDENT; + u32 run_off = name_off + name_size; + u32 run_size, asize; + struct ntfs_sb_info *sbi = ni->mi.sbi; + + err = run_pack(run, svcn, len, NULL, sbi->max_bytes_per_attr - run_off, + &plen); + if (err < 0) + goto out; + + run_size = QuadAlign(err); + + if (plen < len) { + err = -EINVAL; + goto out; + } + + asize = run_off + run_size; + + if (asize > sbi->max_bytes_per_attr) { + err = -EINVAL; + goto out; + } + + err = ni_insert_attr(ni, type, name, name_len, asize, name_off, svcn, + &attr, mi); + + if (err) + goto out; + + attr->non_res = 1; + attr->name_off = cpu_to_le16(name_off); + attr->flags = flags; + + run_pack(run, svcn, len, Add2Ptr(attr, run_off), run_size, &plen); + + attr->nres.svcn = cpu_to_le64(svcn); + attr->nres.evcn = cpu_to_le64((u64)svcn + len - 1); + + err = 0; + if (new_attr) + *new_attr = attr; + + *(__le64 *)&attr->nres.run_off = cpu_to_le64(run_off); + + attr->nres.alloc_size = + svcn ? 0 : cpu_to_le64((u64)len << ni->mi.sbi->cluster_bits); + attr->nres.data_size = attr->nres.alloc_size; + attr->nres.valid_size = attr->nres.alloc_size; + + if (is_ext) { + if (flags & ATTR_FLAG_COMPRESSED) + attr->nres.c_unit = COMPRESSION_UNIT; + attr->nres.total_size = attr->nres.alloc_size; + } + +out: + return err; +} + +/* + * ni_insert_resident + * + * inserts new resident attribute + */ +int ni_insert_resident(struct ntfs_inode *ni, u32 data_size, + enum ATTR_TYPE type, const __le16 *name, u8 name_len, + struct ATTRIB **new_attr, struct mft_inode **mi) +{ + int err; + u32 name_size = QuadAlign(name_len * sizeof(short)); + u32 asize = SIZEOF_RESIDENT + name_size + QuadAlign(data_size); + struct ATTRIB *attr; + + err = ni_insert_attr(ni, type, name, name_len, asize, SIZEOF_RESIDENT, + 0, &attr, mi); + if (err) + return err; + + attr->non_res = 0; + attr->flags = 0; + + attr->res.data_size = cpu_to_le32(data_size); + attr->res.data_off = cpu_to_le16(SIZEOF_RESIDENT + name_size); + if (type == ATTR_NAME) + attr->res.flags = RESIDENT_FLAG_INDEXED; + attr->res.res = 0; + + if (new_attr) + *new_attr = attr; + + return 0; +} + +/* + * ni_remove_attr_le + * + * removes attribute from record + */ +int ni_remove_attr_le(struct ntfs_inode *ni, struct ATTRIB *attr, + struct ATTR_LIST_ENTRY *le) +{ + int err; + struct mft_inode *mi; + + err = ni_load_mi(ni, le, &mi); + if (err) + return err; + + mi_remove_attr(mi, attr); + + if (le) + al_remove_le(ni, le); + + return 0; +} + +/* + * ni_delete_all + * + * removes all attributes and frees allocates space + * ntfs_evict_inode->ntfs_clear_inode->ni_delete_all (if no links) + */ +int ni_delete_all(struct ntfs_inode *ni) +{ + int err; + struct ATTR_LIST_ENTRY *le = NULL; + struct ATTRIB *attr = NULL; + struct rb_node *node; + u16 roff; + u32 asize; + CLST svcn, evcn; + struct ntfs_sb_info *sbi = ni->mi.sbi; + bool nt3 = is_ntfs3(sbi); + struct MFT_REF ref; + + while ((attr = ni_enum_attr_ex(ni, attr, &le))) { + if (!nt3 || attr->name_len) { + ; + } else if (attr->type == ATTR_REPARSE) { + get_mi_ref(&ni->mi, &ref); + ntfs_remove_reparse(sbi, 0, &ref); + } else if (attr->type == ATTR_ID && !attr->non_res && + le32_to_cpu(attr->res.data_size) >= + sizeof(struct GUID)) { + ntfs_objid_remove(sbi, resident_data(attr)); + } + + if (!attr->non_res) + continue; + + svcn = le64_to_cpu(attr->nres.svcn); + evcn = le64_to_cpu(attr->nres.evcn); + + if (evcn + 1 <= svcn) + continue; + + asize = le32_to_cpu(attr->size); + roff = le16_to_cpu(attr->nres.run_off); + + /*run==1 means unpack and deallocate*/ + run_unpack_ex((struct runs_tree *)(size_t)1, sbi, ni->mi.rno, + svcn, evcn, Add2Ptr(attr, roff), asize - roff); + } + + if (ni->attr_list.size) { + run_deallocate(ni->mi.sbi, &ni->attr_list.run, true); + al_destroy(ni); + } + + /* Free all subrecords */ + for (node = rb_first(&ni->mi_tree); node;) { + struct rb_node *next = rb_next(node); + struct mft_inode *mi = rb_entry(node, struct mft_inode, node); + + clear_rec_inuse(mi->mrec); + mi->dirty = true; + mi_write(mi, 0); + + ntfs_mark_rec_free(sbi, mi->rno); + ni_remove_mi(ni, mi); + mi_put(mi); + node = next; + } + + // Free base record + clear_rec_inuse(ni->mi.mrec); + ni->mi.dirty = true; + err = mi_write(&ni->mi, 0); + + ntfs_mark_rec_free(sbi, ni->mi.rno); + + return err; +} + +/* + * ni_fname_name + * + * returns file name attribute by its value + */ +struct ATTR_FILE_NAME *ni_fname_name(struct ntfs_inode *ni, + const struct cpu_str *uni, + const struct MFT_REF *home_dir, + struct ATTR_LIST_ENTRY **le) +{ + struct ATTRIB *attr = NULL; + struct ATTR_FILE_NAME *fname; + + *le = NULL; + + /* Enumerate all names */ +next: + attr = ni_find_attr(ni, attr, le, ATTR_NAME, NULL, 0, NULL, NULL); + if (!attr) + return NULL; + + fname = resident_data_ex(attr, SIZEOF_ATTRIBUTE_FILENAME); + if (!fname) + goto next; + + if (home_dir && memcmp(home_dir, &fname->home, sizeof(*home_dir))) + goto next; + + if (!uni) + goto next; + + if (uni->len != fname->name_len) + goto next; + + if (ntfs_cmp_names_cpu(uni, (struct le_str *)&fname->name_len, NULL)) + goto next; + + return fname; +} + +/* + * ni_fname_type + * + * returns file name attribute with given type + */ +struct ATTR_FILE_NAME *ni_fname_type(struct ntfs_inode *ni, u8 name_type, + struct ATTR_LIST_ENTRY **le) +{ + struct ATTRIB *attr = NULL; + struct ATTR_FILE_NAME *fname; + + *le = NULL; + + /* Enumerate all names */ + for (;;) { + attr = ni_find_attr(ni, attr, le, ATTR_NAME, NULL, 0, NULL, + NULL); + if (!attr) + return NULL; + + fname = resident_data_ex(attr, SIZEOF_ATTRIBUTE_FILENAME); + if (fname && name_type == fname->type) + return fname; + } +} + +/* + * ni_parse_reparse + * + * buffer is at least 24 bytes + */ +enum REPARSE_SIGN ni_parse_reparse(struct ntfs_inode *ni, struct ATTRIB *attr, + void *buffer) +{ + const struct REPARSE_DATA_BUFFER *rp = NULL; + u32 c_format; + u16 len; + typeof(rp->CompressReparseBuffer) *cmpr; + + /* Try to estimate reparse point */ + if (!attr->non_res) { + rp = resident_data_ex(attr, sizeof(struct REPARSE_DATA_BUFFER)); + } else if (le64_to_cpu(attr->nres.data_size) >= + sizeof(struct REPARSE_DATA_BUFFER)) { + struct runs_tree run; + + run_init(&run); + + if (!attr_load_runs_vcn(ni, ATTR_REPARSE, NULL, 0, &run, 0) && + !ntfs_read_run_nb(ni->mi.sbi, &run, 0, buffer, + sizeof(struct REPARSE_DATA_BUFFER), + NULL)) { + rp = buffer; + } + + run_close(&run); + } + + if (!rp) + return REPARSE_NONE; + + len = le16_to_cpu(rp->ReparseDataLength); + switch (rp->ReparseTag) { + case (IO_REPARSE_TAG_MICROSOFT | IO_REPARSE_TAG_SYMBOLIC_LINK): + break; /* Symbolic link */ + case IO_REPARSE_TAG_MOUNT_POINT: + break; /* Mount points and junctions */ + case IO_REPARSE_TAG_SYMLINK: + break; + case IO_REPARSE_TAG_COMPRESS: + cmpr = &rp->CompressReparseBuffer; + if (len < sizeof(*cmpr) || + cmpr->WofVersion != WOF_CURRENT_VERSION || + cmpr->WofProvider != WOF_PROVIDER_SYSTEM || + cmpr->ProviderVer != WOF_PROVIDER_CURRENT_VERSION) { + return REPARSE_NONE; + } + c_format = le32_to_cpu(cmpr->CompressionFormat); + if (c_format > 3) + return REPARSE_NONE; + + ni->ni_flags |= (c_format + 1) << 8; + return REPARSE_COMPRESSED; + + case IO_REPARSE_TAG_DEDUP: + ni->ni_flags |= NI_FLAG_DEDUPLICATED; + return REPARSE_DEDUPLICATED; + + default: + if (rp->ReparseTag & IO_REPARSE_TAG_NAME_SURROGATE) + break; + + return REPARSE_NONE; + } + + /* Looks like normal symlink */ + return REPARSE_LINK; +} + +/* + * helper for file_fiemap + * assumed ni_lock + * TODO: less aggressive locks + */ +int ni_fiemap(struct ntfs_inode *ni, struct fiemap_extent_info *fieinfo, + __u64 vbo, __u64 len) +{ + int err = 0; + struct ntfs_sb_info *sbi = ni->mi.sbi; + u8 cluster_bits = sbi->cluster_bits; + struct runs_tree *run; + struct rw_semaphore *run_lock; + struct ATTRIB *attr; + CLST vcn = vbo >> cluster_bits; + CLST lcn, clen; + u64 valid = ni->i_valid; + u64 lbo, bytes; + u64 end, alloc_size; + size_t idx = -1; + u32 flags; + bool ok; + + if (S_ISDIR(ni->vfs_inode.i_mode)) { + run = &ni->dir.alloc_run; + attr = ni_find_attr(ni, NULL, NULL, ATTR_ALLOC, I30_NAME, + ARRAY_SIZE(I30_NAME), NULL, NULL); + run_lock = NULL; + } else { + run = &ni->file.run; + attr = ni_find_attr(ni, NULL, NULL, ATTR_DATA, NULL, 0, NULL, + NULL); + if (!attr) { + err = -EINVAL; + goto out; + } + if (is_attr_compressed(attr)) { + /*unfortunately cp -r incorrectly treats compressed clusters*/ + err = -EOPNOTSUPP; + ntfs_inode_warn( + &ni->vfs_inode, + "fiemap is not supported for compressed file (cp -r)"); + goto out; + } + run_lock = &ni->file.run_lock; + } + + if (!attr || !attr->non_res) { + err = fiemap_fill_next_extent( + fieinfo, 0, 0, + attr ? le32_to_cpu(attr->res.data_size) : 0, + FIEMAP_EXTENT_DATA_INLINE | FIEMAP_EXTENT_LAST | + FIEMAP_EXTENT_MERGED); + goto out; + } + + end = vbo + len; + alloc_size = le64_to_cpu(attr->nres.alloc_size); + if (end > alloc_size) + end = alloc_size; + + if (run_lock) + down_read(run_lock); + + while (vbo < end) { + if (idx == -1) { + ok = run_lookup_entry(run, vcn, &lcn, &clen, &idx); + } else { + CLST next_vcn = vcn; + + ok = run_get_entry(run, ++idx, &vcn, &lcn, &clen); + if (ok && vcn != next_vcn) { + ok = false; + vcn = next_vcn; + } + } + + if (!ok) { + if (run_lock) { + up_read(run_lock); + down_write(run_lock); + } + + err = attr_load_runs_vcn(ni, attr->type, + attr_name(attr), + attr->name_len, run, vcn); + + if (run_lock) { + up_write(run_lock); + down_read(run_lock); + } + + if (err) + break; + + ok = run_lookup_entry(run, vcn, &lcn, &clen, &idx); + + if (!ok) { + err = -EINVAL; + break; + } + } + + if (!clen) { + err = -EINVAL; // ? + break; + } + + if (lcn == SPARSE_LCN) { + vcn += clen; + vbo = (u64)vcn << cluster_bits; + continue; + } + + flags = FIEMAP_EXTENT_MERGED; + if (S_ISDIR(ni->vfs_inode.i_mode)) { + ; + } else if (is_attr_compressed(attr)) { + bool is_compr; + CLST clst_data; + + err = attr_is_frame_compressed(ni, attr, + vcn >> attr->nres.c_unit, + &clst_data, &is_compr); + if (err) + break; + if (is_compr) + flags |= FIEMAP_EXTENT_ENCODED; + } else if (is_attr_encrypted(attr)) { + flags |= FIEMAP_EXTENT_DATA_ENCRYPTED; + } + + vbo = (u64)vcn << cluster_bits; + bytes = (u64)clen << cluster_bits; + lbo = (u64)lcn << cluster_bits; + + vcn += clen; + + if (vbo + bytes >= end) { + bytes = end - vbo; + flags |= FIEMAP_EXTENT_LAST; + } + + if (vbo + bytes <= valid) { + ; + } else if (vbo >= valid) { + flags |= FIEMAP_EXTENT_UNWRITTEN; + } else { + /* vbo < valid && valid < vbo + bytes */ + u64 dlen = valid - vbo; + + err = fiemap_fill_next_extent(fieinfo, vbo, lbo, dlen, + flags); + if (err < 0) + break; + if (err == 1) { + err = 0; + break; + } + + vbo = valid; + bytes -= dlen; + if (!bytes) + continue; + + lbo += dlen; + flags |= FIEMAP_EXTENT_UNWRITTEN; + } + + err = fiemap_fill_next_extent(fieinfo, vbo, lbo, bytes, flags); + if (err < 0) + break; + if (err == 1) { + err = 0; + break; + } + + vbo += bytes; + } + + if (run_lock) + up_read(run_lock); + +out: + return err; +} + +/* + * When decompressing, we typically obtain more than one page per reference. + * We inject the additional pages into the page cache. + */ +int ni_readpage_cmpr(struct ntfs_inode *ni, struct page *page) +{ + int err; + struct ntfs_sb_info *sbi = ni->mi.sbi; + struct address_space *mapping = page->mapping; + struct ATTR_LIST_ENTRY *le; + struct ATTRIB *attr; + u8 frame_bits; + u32 frame_size, i, idx; + CLST frame, clst_data; + struct page *pg; + pgoff_t index = page->index, end_index; + u64 vbo = (u64)index << PAGE_SHIFT; + u32 pages_per_frame = 0; + struct page **pages = NULL; /*array of at most 16 pages. stack?*/ + char *frame_buf = NULL; + char *frame_unc = NULL; + bool is_mapped = false; + u32 cmpr_size, unc_size; + u64 frame_vbo, valid_size; + size_t unc_size_fin; + u32 npages, missed = 0; + bool is_cmpr; + + end_index = (ni->vfs_inode.i_size + PAGE_SIZE - 1) >> PAGE_SHIFT; + + if (index >= end_index) { + SetPageUptodate(page); + err = 0; + goto out; + } + + le = NULL; + attr = ni_find_attr(ni, NULL, &le, ATTR_DATA, NULL, 0, NULL, NULL); + if (!attr) { + err = -ENOENT; + goto out; + } + + WARN_ON(!attr->non_res); + + if (ni->ni_flags & NI_FLAG_COMPRESSED_MASK) { + /* TODO: port lzx/xpress */ + err = -EOPNOTSUPP; + goto out; + } + + if (!is_attr_compressed(attr)) { + err = -EINVAL; + goto out; + } + + if (sbi->cluster_size > NTFS_LZNT_MAX_CLUSTER) { + err = -EOPNOTSUPP; + goto out; + } + + if (attr->nres.c_unit != NTFS_LZNT_CUNIT) { + err = -EOPNOTSUPP; + goto out; + } + + frame_bits = NTFS_LZNT_CUNIT + sbi->cluster_bits; + frame_size = sbi->cluster_size << NTFS_LZNT_CUNIT; + frame = vbo >> frame_bits; + frame_vbo = (u64)frame << frame_bits; + + down_write(&ni->file.run_lock); + run_truncate_head(&ni->file.run, le64_to_cpu(attr->nres.svcn)); + err = attr_is_frame_compressed(ni, attr, frame, &clst_data, &is_cmpr); + up_write(&ni->file.run_lock); + + if (err) + goto out; + + pages_per_frame = frame_size >> PAGE_SHIFT; + pages = ntfs_alloc(pages_per_frame * sizeof(*pages), 1); + if (!pages) { + err = -ENOMEM; + goto out; + } + + idx = (vbo - frame_vbo) >> PAGE_SHIFT; + pages[idx] = page; + kmap(page); + + npages = 1; + index = frame_vbo >> PAGE_SHIFT; + for (i = 0; i < pages_per_frame && index < end_index; i++, index++) { + if (i == idx) + continue; + + //pg = grab_cache_page_nowait(mapping, index); + pg = find_get_page(mapping, index); + if (!pg) { + missed += 1; + continue; /* not critical - just not effective */ + } + + pages[i] = pg; + if (!PageDirty(pg) && (!PageUptodate(pg) || PageError(pg))) + ClearPageError(pg); + kmap(pg); + npages += 1; + } + + valid_size = ni->i_valid; + unc_size = (missed + npages) << PAGE_SHIFT; + + if (!missed) { + frame_unc = vmap(pages, npages, VM_MAP, PAGE_KERNEL); + if (frame_unc) + is_mapped = true; + } + + if (frame_vbo >= valid_size || !clst_data) { + /* all zeroes */ + err = 0; + if (is_mapped) { + memset(frame_unc, 0, npages << PAGE_SHIFT); + goto out1; + } + + for (i = 0; i < pages_per_frame; i++) { + pg = pages[i]; + if (!pg) + continue; + memset(page_address(pg), 0, PAGE_SIZE); + flush_dcache_page(pg); + } + + goto out1; + } + + cmpr_size = clst_data << sbi->cluster_bits; + + /* read 'clst_data' clusters from disk */ + if (!is_cmpr && is_mapped) { + down_read(&ni->file.run_lock); + err = ntfs_read_run_nb(sbi, &ni->file.run, frame_vbo, frame_unc, + cmpr_size, NULL); + up_read(&ni->file.run_lock); + goto out1; + } + + frame_buf = ntfs_alloc(cmpr_size, 0); + if (!frame_buf) { + err = -ENOMEM; + goto out1; + } + + down_read(&ni->file.run_lock); + err = ntfs_read_run_nb(sbi, &ni->file.run, frame_vbo, frame_buf, + cmpr_size, NULL); + up_read(&ni->file.run_lock); + + if (err) + goto out2; + + /* compress.lock protects sbi->compress.frame_unc (a-la frame_unc ) and sbi->compress.ctx */ + spin_lock(&sbi->compress.lock); + if (!is_mapped) + frame_unc = sbi->compress.frame_unc; + + /* decompress: frame_buf -> frame_unc */ + unc_size_fin = + decompress_lznt(frame_buf, cmpr_size, frame_unc, unc_size); + if ((ssize_t)unc_size_fin < 0) { + err = unc_size_fin; + goto out3; + } + + if (!unc_size_fin || unc_size_fin > frame_size) { + err = -EINVAL; + goto out3; + } + + if (is_mapped) { + if (valid_size < frame_vbo + unc_size) { + size_t ok = valid_size - frame_vbo; + + memset(frame_unc + ok, 0, unc_size - ok); + } + goto out3; + } + + for (i = 0; i < pages_per_frame; i++) { + u8 *pa; + u32 use, done; + loff_t vbo; + + pg = pages[i]; + if (!pg) + continue; + + if (PageDirty(pg) || (PageUptodate(pg) && !PageError(pg))) + continue; + + pa = page_address(pg); + + use = 0; + done = i * PAGE_SIZE; + vbo = frame_vbo + done; + + if (vbo < valid_size && unc_size_fin > done) { + use = unc_size_fin - done; + if (use > PAGE_SIZE) + use = PAGE_SIZE; + if (vbo + use > valid_size) + use = valid_size - vbo; + memcpy(pa, frame_unc + done, use); + } + + if (use < PAGE_SIZE) + memset(pa + use, 0, PAGE_SIZE - use); + + flush_dcache_page(pg); + } + +out3: + spin_unlock(&sbi->compress.lock); + +out2: + ntfs_free(frame_buf); +out1: + if (is_mapped) + vunmap(frame_unc); + + if (err) { + SetPageError(page); + } else { + for (i = 0; i < pages_per_frame; i++) { + pg = pages[i]; + if (pg) + SetPageUptodate(pg); + } + } + + for (i = 0; i < pages_per_frame; i++) { + pg = pages[i]; + if (i == idx || !pg) + continue; + kunmap(pg); + unlock_page(pg); + put_page(pg); + } + + kunmap(page); + +out: + /* At this point, err contains 0 or -EIO depending on the "critical" page */ + ntfs_free(pages); + unlock_page(page); + + return err; +} + +/* + * ni_write_frame + * + * pages - array of locked pages + */ +int ni_write_frame(struct ntfs_inode *ni, struct page **pages, u32 npages) +{ + int err; + struct ntfs_sb_info *sbi = ni->mi.sbi; + u8 frame_bits = NTFS_LZNT_CUNIT + sbi->cluster_bits; + u32 frame_size = sbi->cluster_size << NTFS_LZNT_CUNIT; + u64 frame_vbo = (u64)pages[0]->index << PAGE_SHIFT; + CLST frame = frame_vbo >> frame_bits; + u32 pages_per_frame; + char *frame_buf = NULL; + char *frame_unc, *frame_wr; + struct ATTR_LIST_ENTRY *le; + struct ATTRIB *attr; + u32 i; + struct page *pg; + bool is_mapped = false; + size_t cmpr_size_fin, cmpr_size; + + le = NULL; + attr = ni_find_attr(ni, NULL, &le, ATTR_DATA, NULL, 0, NULL, NULL); + if (!attr) { + err = -ENOENT; + goto out; + } + + if (!attr->non_res) { + WARN_ON(1); + err = 0; + goto out; + } + + if (!is_attr_compressed(attr)) { + WARN_ON(1); + err = -EINVAL; + goto out; + } + + if (sbi->cluster_size > NTFS_LZNT_MAX_CLUSTER) { + err = -EOPNOTSUPP; + goto out; + } + + if (attr->nres.c_unit != NTFS_LZNT_CUNIT) { + err = -EOPNOTSUPP; + goto out; + } + + frame_buf = ntfs_alloc(frame_size, 0); + if (!frame_buf) { + err = -ENOMEM; + goto out; + } + + pages_per_frame = frame_size >> PAGE_SHIFT; + + for (i = 0; i < npages; i++) + kmap(pages[i]); + + /* + * To compress we should get a continues memory + * Is vmap faster then memcpy? + */ + if (npages == pages_per_frame) { + frame_unc = vmap(pages, npages, VM_MAP, PAGE_KERNEL_RO); + if (frame_unc) + is_mapped = true; + } + + /* compress.lock protects sbi->compress.frame_unc (a-la frame_unc ) and sbi->compress.ctx */ + spin_lock(&sbi->compress.lock); + if (!is_mapped) { + frame_unc = sbi->compress.frame_unc; + + for (i = 0; i < npages; i++) { + pg = pages[i]; + memcpy(frame_unc + i * PAGE_SIZE, page_address(pg), + PAGE_SIZE); + } + + for (; i < pages_per_frame; i++) + memset(frame_unc + i * PAGE_SIZE, 0, PAGE_SIZE); + } + + /* compress: frame_unc -> frame_buf */ + cmpr_size_fin = compress_lznt(frame_unc, frame_size, frame_buf, + frame_size, sbi->compress.ctx); + + frame_wr = frame_buf; + if (cmpr_size_fin + sbi->cluster_size > frame_size) { + /* frame is not compressed */ + cmpr_size_fin = frame_size; + cmpr_size = frame_size; + if (is_mapped) + frame_wr = frame_unc; + else + memcpy(frame_buf, frame_unc, frame_size); + } else if (cmpr_size_fin) { + /* frame is compressed */ + cmpr_size = ntfs_up_cluster(sbi, cmpr_size_fin); + memset(frame_buf + cmpr_size_fin, 0, cmpr_size - cmpr_size_fin); + } else { + /* frame is sparsed */ + cmpr_size = 0; + } + + spin_unlock(&sbi->compress.lock); + + down_write(&ni->file.run_lock); + run_truncate_head(&ni->file.run, le64_to_cpu(attr->nres.svcn)); + err = attr_allocate_frame(ni, frame, cmpr_size_fin, ni->i_valid); + up_write(&ni->file.run_lock); + if (err) + goto out2; + + if (!cmpr_size) + goto out2; + + down_read(&ni->file.run_lock); + err = ntfs_sb_write_run(sbi, &ni->file.run, frame_vbo, frame_wr, + cmpr_size); + up_read(&ni->file.run_lock); + + if (is_mapped) + vunmap(frame_unc); + + for (i = 0; i < npages; i++) + kunmap(pages[i]); + +out2: + ntfs_free(frame_buf); + +out: + return err; +} + +/* + * update duplicate info of ATTR_FILE_NAME in MFT and in parent directories + */ +static bool ni_update_parent(struct ntfs_inode *ni, struct NTFS_DUP_INFO *dup, + int sync) +{ + struct ATTRIB *attr; + struct mft_inode *mi; + struct ATTR_LIST_ENTRY *le = NULL; + struct ntfs_sb_info *sbi = ni->mi.sbi; + struct super_block *sb = sbi->sb; + bool re_dirty = false; + bool active = sb->s_flags & SB_ACTIVE; + bool upd_parent = ni->ni_flags & NI_FLAG_UPDATE_PARENT; + + if (ni->mi.mrec->flags & RECORD_FLAG_DIR) { + dup->fa |= FILE_ATTRIBUTE_DIRECTORY; + attr = NULL; + dup->alloc_size = 0; + dup->data_size = 0; + } else { + dup->fa &= ~FILE_ATTRIBUTE_DIRECTORY; + + attr = ni_find_attr(ni, NULL, &le, ATTR_DATA, NULL, 0, NULL, + &mi); + if (!attr) { + dup->alloc_size = dup->data_size = 0; + } else if (!attr->non_res) { + u32 data_size = le32_to_cpu(attr->res.data_size); + + dup->alloc_size = cpu_to_le64(QuadAlign(data_size)); + dup->data_size = cpu_to_le64(data_size); + } else { + u64 new_valid = ni->i_valid; + u64 data_size = le64_to_cpu(attr->nres.data_size); + __le64 valid_le; + + dup->alloc_size = is_attr_ext(attr) ? + attr->nres.total_size : + attr->nres.alloc_size; + dup->data_size = attr->nres.data_size; + + if (new_valid > data_size) + new_valid = data_size; + + valid_le = cpu_to_le64(new_valid); + if (valid_le != attr->nres.valid_size) { + attr->nres.valid_size = valid_le; + mi->dirty = true; + } + } + } + + /* TODO: fill reparse info */ + dup->reparse = 0; + dup->ea_size = 0; + + if (ni->ni_flags & NI_FLAG_EA) { + attr = ni_find_attr(ni, attr, &le, ATTR_EA_INFO, NULL, 0, NULL, + NULL); + if (attr) { + const struct EA_INFO *info; + + info = resident_data_ex(attr, sizeof(struct EA_INFO)); + + dup->ea_size = info->size_pack; + } + } + + attr = NULL; + le = NULL; + + while ((attr = ni_find_attr(ni, attr, &le, ATTR_NAME, NULL, 0, NULL, + &mi))) { + struct inode *dir; + struct ATTR_FILE_NAME *fname; + + fname = resident_data_ex(attr, SIZEOF_ATTRIBUTE_FILENAME); + if (!fname) + continue; + + if (memcmp(&fname->dup, dup, sizeof(fname->dup))) { + memcpy(&fname->dup, dup, sizeof(fname->dup)); + mi->dirty = true; + } else if (!upd_parent) { + continue; + } + + if (!active) + continue; /*avoid __wait_on_freeing_inode(inode); */ + + /*ntfs_iget5 may sleep*/ + dir = ntfs_iget5(sb, &fname->home, NULL); + if (IS_ERR(dir)) { + ntfs_inode_warn( + &ni->vfs_inode, + "failed to open parent directory r=%lx to update", + (long)ino_get(&fname->home)); + continue; + } + + if (!is_bad_inode(dir)) { + struct ntfs_inode *dir_ni = ntfs_i(dir); + + if (!ni_trylock(dir_ni)) { + re_dirty = true; + } else { + indx_update_dup(dir_ni, sbi, fname, dup, sync); + ni_unlock(dir_ni); + } + } + iput(dir); + } + + return re_dirty; +} + +/* + * ni_write_inode + * + * write mft base record and all subrecords to disk + */ +int ni_write_inode(struct inode *inode, int sync, const char *hint) +{ + int err = 0, err2; + struct ntfs_inode *ni = ntfs_i(inode); + struct super_block *sb = inode->i_sb; + struct ntfs_sb_info *sbi = sb->s_fs_info; + bool re_dirty = false; + struct ATTR_STD_INFO *std; + struct rb_node *node, *next; + struct NTFS_DUP_INFO dup; + + if (is_bad_inode(inode)) + return 0; + + if (!ni_trylock(ni)) { + /* 'ni' is under modification, skip for now */ + mark_inode_dirty_sync(inode); + return 0; + } + + if (is_rec_inuse(ni->mi.mrec) && + !(sbi->flags & NTFS_FLAGS_LOG_REPLAYING) && inode->i_nlink) { + bool modified = false; + + /* update times in standard attribute */ + std = ni_std(ni); + if (!std) { + err = -EINVAL; + goto out; + } + + /* Update the access times if they have changed. */ + dup.m_time = kernel2nt(&inode->i_mtime); + if (std->m_time != dup.m_time) { + std->m_time = dup.m_time; + modified = true; + } + + dup.c_time = kernel2nt(&inode->i_ctime); + if (std->c_time != dup.c_time) { + std->c_time = dup.c_time; + modified = true; + } + + dup.a_time = kernel2nt(&inode->i_atime); + if (std->a_time != dup.a_time) { + std->a_time = dup.a_time; + modified = true; + } + + dup.fa = ni->std_fa; + if (std->fa != dup.fa) { + std->fa = dup.fa; + modified = true; + } + + if (modified) + ni->mi.dirty = true; + + if (!ntfs_is_meta_file(sbi, inode->i_ino) && + (modified || (ni->ni_flags & NI_FLAG_UPDATE_PARENT))) { + dup.cr_time = std->cr_time; + /* Not critical if this function fail */ + re_dirty = ni_update_parent(ni, &dup, sync); + + if (re_dirty) + ni->ni_flags |= NI_FLAG_UPDATE_PARENT; + else + ni->ni_flags &= ~NI_FLAG_UPDATE_PARENT; + } + + /* update attribute list */ + err = al_update(ni); + if (err) + goto out; + } + + for (node = rb_first(&ni->mi_tree); node; node = next) { + struct mft_inode *mi = rb_entry(node, struct mft_inode, node); + bool is_empty; + + next = rb_next(node); + + if (!mi->dirty) + continue; + + is_empty = !mi_enum_attr(mi, NULL); + + if (is_empty) + clear_rec_inuse(mi->mrec); + + err2 = mi_write(mi, sync); + if (!err && err2) + err = err2; + + if (is_empty) { + ntfs_mark_rec_free(sbi, mi->rno); + rb_erase(node, &ni->mi_tree); + mi_put(mi); + } + } + + if (ni->mi.dirty) { + err2 = mi_write(&ni->mi, sync); + if (!err && err2) + err = err2; + } +out: + ni_unlock(ni); + + if (err) { + ntfs_err(sb, "%s r=%lx failed, %d.", hint, inode->i_ino, err); + ntfs_set_state(sbi, NTFS_DIRTY_ERROR); + return err; + } + + if (re_dirty && (sb->s_flags & SB_ACTIVE)) + mark_inode_dirty_sync(inode); + + return 0; +} diff --git a/fs/ntfs3/namei.c b/fs/ntfs3/namei.c new file mode 100644 index 000000000000..b178163a6adc --- /dev/null +++ b/fs/ntfs3/namei.c @@ -0,0 +1,576 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * linux/fs/ntfs3/namei.c + * + * Copyright (C) 2019-2020 Paragon Software GmbH, All rights reserved. + * + */ + +#include +#include +#include +#include +#include +#include + +#include "debug.h" +#include "ntfs.h" +#include "ntfs_fs.h" + +/* + * fill_name_de + * + * formats NTFS_DE in 'buf' + */ +int fill_name_de(struct ntfs_sb_info *sbi, void *buf, const struct qstr *name, + const struct cpu_str *uni) +{ + int err; + struct NTFS_DE *e = buf; + u16 data_size; + struct ATTR_FILE_NAME *fname = (struct ATTR_FILE_NAME *)(e + 1); + +#ifndef NTFS3_64BIT_CLUSTER + e->ref.high = fname->home.high = 0; +#endif + if (uni) { +#ifdef __BIG_ENDIAN + int ulen = uni->len; + __le16 *uname = fname->name; + const u16 *name_cpu = uni->name; + + while (ulen--) + *uname++ = cpu_to_le16(*name_cpu++); +#else + memcpy(fname->name, uni->name, uni->len * sizeof(u16)); +#endif + fname->name_len = uni->len; + + } else { + /* Convert input string to unicode */ + err = ntfs_nls_to_utf16(sbi, name->name, name->len, + (struct cpu_str *)&fname->name_len, + NTFS_NAME_LEN, UTF16_LITTLE_ENDIAN); + if (err < 0) + return err; + } + + fname->type = FILE_NAME_POSIX; + data_size = fname_full_size(fname); + + e->size = cpu_to_le16(QuadAlign(data_size) + sizeof(struct NTFS_DE)); + e->key_size = cpu_to_le16(data_size); + e->flags = 0; + e->res = 0; + + return 0; +} + +/* + * ntfs_lookup + * + * inode_operations::lookup + */ +static struct dentry *ntfs_lookup(struct inode *dir, struct dentry *dentry, + u32 flags) +{ + struct ntfs_inode *ni = ntfs_i(dir); + struct cpu_str *uni = __getname(); + struct inode *inode; + int err; + + if (!uni) + inode = ERR_PTR(-ENOMEM); + else { + err = ntfs_nls_to_utf16(ni->mi.sbi, dentry->d_name.name, + dentry->d_name.len, uni, NTFS_NAME_LEN, + UTF16_HOST_ENDIAN); + if (err < 0) + inode = ERR_PTR(err); + else { + ni_lock(ni); + inode = dir_search_u(dir, uni, NULL); + ni_unlock(ni); + } + __putname(uni); + } + + return d_splice_alias(inode, dentry); +} + +/* + * ntfs_create + * + * inode_operations::create + */ +static int ntfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, + bool excl) +{ + int err; + struct ntfs_inode *ni = ntfs_i(dir); + struct inode *inode; + + ni_lock(ni); + + err = ntfs_create_inode(dir, dentry, NULL, S_IFREG | mode, 0, NULL, 0, + excl, NULL, &inode); + + ni_unlock(ni); + + return err; +} + +/* + * ntfs_link + * + * inode_operations::link + */ +static int ntfs_link(struct dentry *ode, struct inode *dir, struct dentry *de) +{ + int err; + struct inode *inode = d_inode(ode); + struct ntfs_inode *ni = ntfs_i(inode); + + if (S_ISDIR(inode->i_mode)) + return -EPERM; + + if (inode->i_nlink >= NTFS_LINK_MAX) + return -EMLINK; + + ni_lock(ni); + if (inode != dir) + ni_lock(ntfs_i(dir)); + + dir->i_ctime = dir->i_mtime = inode->i_ctime = current_time(inode); + inc_nlink(inode); + ihold(inode); + + err = ntfs_link_inode(inode, de); + if (!err) { + mark_inode_dirty(inode); + mark_inode_dirty(dir); + d_instantiate(de, inode); + } else { + drop_nlink(inode); + iput(inode); + } + + if (inode != dir) + ni_unlock(ntfs_i(dir)); + ni_unlock(ni); + + return err; +} + +/* + * ntfs_unlink + * + * inode_operations::unlink + */ +static int ntfs_unlink(struct inode *dir, struct dentry *dentry) +{ + struct ntfs_inode *ni = ntfs_i(dir); + int err; + + ni_lock(ni); + + err = ntfs_unlink_inode(dir, dentry); + + ni_unlock(ni); + + return err; +} + +/* + * ntfs_symlink + * + * inode_operations::symlink + */ +static int ntfs_symlink(struct inode *dir, struct dentry *dentry, + const char *symname) +{ + int err; + u32 size = strlen(symname); + struct inode *inode; + struct ntfs_inode *ni = ntfs_i(dir); + + ni_lock(ni); + + err = ntfs_create_inode(dir, dentry, NULL, S_IFLNK | 0777, 0, symname, + size, 0, NULL, &inode); + + ni_unlock(ni); + + return err; +} + +/* + * ntfs_mkdir + * + * inode_operations::mkdir + */ +static int ntfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) +{ + int err; + struct inode *inode; + struct ntfs_inode *ni = ntfs_i(dir); + + ni_lock(ni); + + err = ntfs_create_inode(dir, dentry, NULL, S_IFDIR | mode, 0, NULL, -1, + 0, NULL, &inode); + + ni_unlock(ni); + + return err; +} + +/* + * ntfs_rmdir + * + * inode_operations::rm_dir + */ +static int ntfs_rmdir(struct inode *dir, struct dentry *dentry) +{ + struct ntfs_inode *ni = ntfs_i(dir); + int err; + + ni_lock(ni); + + err = ntfs_unlink_inode(dir, dentry); + + ni_unlock(ni); + + return err; +} + +/* + * ntfs_rename + * + * inode_operations::rename + */ +static int ntfs_rename(struct inode *old_dir, struct dentry *old_dentry, + struct inode *new_dir, struct dentry *new_dentry, + u32 flags) +{ + int err; + struct super_block *sb = old_dir->i_sb; + struct ntfs_sb_info *sbi = sb->s_fs_info; + struct ntfs_inode *old_diri = ntfs_i(old_dir); + struct ntfs_inode *new_diri = ntfs_i(new_dir); + struct ntfs_inode *ni; + struct ATTR_FILE_NAME *old_name, *new_name, *fname; + u8 name_type; + bool is_same; + struct inode *old_inode, *new_inode; + struct NTFS_DE *old_de, *new_de; + struct ATTRIB *attr; + struct ATTR_LIST_ENTRY *le; + u16 new_de_key_size; + + static_assert(SIZEOF_ATTRIBUTE_FILENAME_MAX + SIZEOF_RESIDENT < 1024); + static_assert(SIZEOF_ATTRIBUTE_FILENAME_MAX + sizeof(struct NTFS_DE) < + 1024); + static_assert(PATH_MAX >= 4 * 1024); + + if (flags & ~RENAME_NOREPLACE) + return -EINVAL; + + old_inode = d_inode(old_dentry); + new_inode = d_inode(new_dentry); + + ni = ntfs_i(old_inode); + + ni_lock(ni); + ni_lock(old_diri); + + is_same = old_dentry->d_name.len == new_dentry->d_name.len && + !memcmp(old_dentry->d_name.name, new_dentry->d_name.name, + old_dentry->d_name.len); + + if (is_same && old_dir == new_dir) { + /* Nothing to do */ + err = 0; + goto out1; + } + + if (ntfs_is_meta_file(sbi, old_inode->i_ino)) { + err = -EINVAL; + goto out1; + } + + if (new_inode) { + /*target name exists. unlink it*/ + dget(new_dentry); + if (old_diri != new_diri) + ni_lock(new_diri); + err = ntfs_unlink_inode(new_dir, new_dentry); + if (old_diri != new_diri) + ni_unlock(new_diri); + + dput(new_dentry); + if (err) + goto out1; + } + + old_de = __getname(); + if (!old_de) { + err = -ENOMEM; + goto out1; + } + + err = fill_name_de(sbi, old_de, &old_dentry->d_name, NULL); + if (err < 0) + goto out2; + + old_name = (struct ATTR_FILE_NAME *)(old_de + 1); + + if (is_same) { + new_de = old_de; + } else { + new_de = Add2Ptr(old_de, 1024); + err = fill_name_de(sbi, new_de, &new_dentry->d_name, NULL); + if (err < 0) + goto out2; + } + + old_name->home.low = cpu_to_le32(old_dir->i_ino); +#ifdef NTFS3_64BIT_CLUSTER + old_name->home.high = cpu_to_le16(old_dir->i_ino >> 32); +#endif + old_name->home.seq = ntfs_i(old_dir)->mi.mrec->seq; + + /*get pointer to file_name in mft*/ + fname = ni_fname_name(ni, (struct cpu_str *)&old_name->name_len, + &old_name->home, &le); + if (!fname) { + err = -EINVAL; + goto out2; + } + + /* Copy fname info from record into new fname */ + new_name = (struct ATTR_FILE_NAME *)(new_de + 1); + memcpy(&new_name->dup, &fname->dup, sizeof(fname->dup)); + + name_type = paired_name(fname->type); + + /* remove first name from directory */ + err = indx_delete_entry(&old_diri->dir, old_diri, old_de + 1, + le16_to_cpu(old_de->key_size), sbi); + if (err) + goto out3; + + /* remove first name from mft */ + err = ni_remove_attr_le(ni, attr_from_name(fname), le); + if (err) + goto out4; + + le16_add_cpu(&ni->mi.mrec->hard_links, -1); + ni->mi.dirty = true; + + if (name_type != FILE_NAME_POSIX) { + /* get paired name */ + fname = ni_fname_type(ni, name_type, &le); + if (fname) { + /* remove second name from directory */ + err = indx_delete_entry(&old_diri->dir, old_diri, fname, + fname_full_size(fname), sbi); + if (err) + goto out5; + + /* remove second name from mft */ + err = ni_remove_attr_le(ni, attr_from_name(fname), le); + if (err) + goto out6; + + le16_add_cpu(&ni->mi.mrec->hard_links, -1); + ni->mi.dirty = true; + } + } + + /* Add new name */ + new_de->ref.low = cpu_to_le32(old_inode->i_ino); +#ifdef NTFS3_64BIT_CLUSTER + new_de->ref.high = cpu_to_le16(old_inode->i_ino >> 32); + new_name->home.high = cpu_to_le16(new_dir->i_ino >> 32); +#endif + new_de->ref.seq = ni->mi.mrec->seq; + + new_name->home.low = cpu_to_le32(new_dir->i_ino); + new_name->home.seq = ntfs_i(new_dir)->mi.mrec->seq; + + new_de_key_size = le16_to_cpu(new_de->key_size); + + /* insert new name in mft */ + err = ni_insert_resident(ni, new_de_key_size, ATTR_NAME, NULL, 0, &attr, + NULL); + if (err) + goto out7; + + attr->res.flags = RESIDENT_FLAG_INDEXED; + + memcpy(Add2Ptr(attr, SIZEOF_RESIDENT), new_name, new_de_key_size); + + le16_add_cpu(&ni->mi.mrec->hard_links, 1); + ni->mi.dirty = true; + + /* insert new name in directory */ + err = indx_insert_entry(&new_diri->dir, new_diri, new_de, sbi, NULL); + if (err) + goto out8; + + if (IS_DIRSYNC(new_dir)) + err = ntfs_sync_inode(old_inode); + else + mark_inode_dirty(old_inode); + + old_dir->i_ctime = old_dir->i_mtime = current_time(old_dir); + if (IS_DIRSYNC(old_dir)) + (void)ntfs_sync_inode(old_dir); + else + mark_inode_dirty(old_dir); + + if (old_dir != new_dir) { + new_dir->i_mtime = new_dir->i_ctime = old_dir->i_ctime; + mark_inode_dirty(new_dir); + } + + if (old_inode) { + old_inode->i_ctime = old_dir->i_ctime; + mark_inode_dirty(old_inode); + } + + err = 0; + goto out2; + +out8: + mi_remove_attr(&ni->mi, attr); + +out7: +out6: +out5: +out4: + /* Undo: + *err = indx_delete_entry(&old_diri->dir, old_diri, old_de + 1, + * old_de->key_size, NULL); + */ + +out3: +out2: + __putname(old_de); +out1: + ni_unlock(old_diri); + ni_unlock(ni); + + return err; +} + +/* + * ntfs_atomic_open + * + * inode_operations::atomic_open + */ +static int ntfs_atomic_open(struct inode *dir, struct dentry *dentry, + struct file *file, u32 flags, umode_t mode) +{ + int err; + bool excl = !!(flags & O_EXCL); + struct inode *inode; + struct ntfs_fnd *fnd = NULL; + struct ntfs_inode *ni = ntfs_i(dir); + struct dentry *d = NULL; + struct cpu_str *uni = __getname(); + + if (!uni) + return -ENOMEM; + + err = ntfs_nls_to_utf16(ni->mi.sbi, dentry->d_name.name, + dentry->d_name.len, uni, NTFS_NAME_LEN, + UTF16_HOST_ENDIAN); + if (err < 0) + goto out; + + ni_lock(ni); + + if (d_in_lookup(dentry)) { + fnd = fnd_get(&ntfs_i(dir)->dir); + if (!fnd) { + err = -ENOMEM; + goto out1; + } + + d = d_splice_alias(dir_search_u(dir, uni, fnd), dentry); + if (IS_ERR(d)) { + err = PTR_ERR(d); + d = NULL; + goto out2; + } + + if (d) + dentry = d; + } + + if (!(flags & O_CREAT) || d_really_is_positive(dentry)) { + err = finish_no_open(file, d); + goto out2; + } + + file->f_mode |= FMODE_CREATED; + + /*fnd contains tree's path to insert to*/ + err = ntfs_create_inode(dir, dentry, uni, mode, 0, NULL, 0, excl, fnd, + &inode); + if (!err) + err = finish_open(file, dentry, ntfs_file_open); + dput(d); + +out2: + fnd_put(fnd); +out1: + ni_unlock(ni); +out: + __putname(uni); + + return err; +} + +struct dentry *ntfs_get_parent(struct dentry *child) +{ + struct inode *inode = d_inode(child); + struct ntfs_inode *ni = ntfs_i(inode); + + struct ATTR_LIST_ENTRY *le = NULL; + struct ATTRIB *attr = NULL; + struct ATTR_FILE_NAME *fname; + + while ((attr = ni_find_attr(ni, attr, &le, ATTR_NAME, NULL, 0, NULL, + NULL))) { + fname = resident_data_ex(attr, SIZEOF_ATTRIBUTE_FILENAME); + if (!fname) + continue; + + return d_obtain_alias( + ntfs_iget5(inode->i_sb, &fname->home, NULL)); + } + + return ERR_PTR(-ENOENT); +} + +const struct inode_operations ntfs_dir_inode_operations = { + .lookup = ntfs_lookup, + .create = ntfs_create, + .link = ntfs_link, + .unlink = ntfs_unlink, + .symlink = ntfs_symlink, + .mkdir = ntfs_mkdir, + .rmdir = ntfs_rmdir, + .rename = ntfs_rename, + .permission = ntfs_permission, + .get_acl = ntfs_get_acl, + .set_acl = ntfs_set_acl, + .setattr = ntfs_setattr, + .getattr = ntfs_getattr, + .listxattr = ntfs_listxattr, + .atomic_open = ntfs_atomic_open, + .fiemap = ntfs_fiemap, +}; diff --git a/fs/ntfs3/record.c b/fs/ntfs3/record.c new file mode 100644 index 000000000000..dc883fd074aa --- /dev/null +++ b/fs/ntfs3/record.c @@ -0,0 +1,615 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * linux/fs/ntfs3/record.c + * + * Copyright (C) 2019-2020 Paragon Software GmbH, All rights reserved. + * + */ + +#include +#include +#include +#include +#include + +#include "debug.h" +#include "ntfs.h" +#include "ntfs_fs.h" + +static inline int compare_attr(const struct ATTRIB *left, enum ATTR_TYPE type, + const __le16 *name, u8 name_len, + const u16 *upcase) +{ + /* First, compare the type codes: */ + int diff = le32_to_cpu(left->type) - le32_to_cpu(type); + + if (diff) + return diff; + + /* + * They have the same type code, so we have to compare the names. + * First compare case insensitive + */ + diff = ntfs_cmp_names(attr_name(left), left->name_len, name, name_len, + upcase); + if (diff) + return diff; + + /* Second compare case sensitive */ + return ntfs_cmp_names(attr_name(left), left->name_len, name, name_len, + NULL); +} + +/* + * mi_new_attt_id + * + * returns unused attribute id that is less than mrec->next_attr_id + */ +static __le16 mi_new_attt_id(struct mft_inode *mi) +{ + u16 free_id, max_id, t16; + struct MFT_REC *rec = mi->mrec; + struct ATTRIB *attr; + __le16 id; + + id = rec->next_attr_id; + free_id = le16_to_cpu(id); + if (free_id < 0x7FFF) { + rec->next_attr_id = cpu_to_le16(free_id + 1); + return id; + } + + /* One record can store up to 1024/24 ~= 42 attributes */ + free_id = 0; + max_id = 0; + + attr = NULL; + + for (;;) { + attr = mi_enum_attr(mi, attr); + if (!attr) { + rec->next_attr_id = cpu_to_le16(max_id + 1); + mi->dirty = true; + return cpu_to_le16(free_id); + } + + t16 = le16_to_cpu(attr->id); + if (t16 == free_id) { + free_id += 1; + attr = NULL; + } else if (max_id < t16) + max_id = t16; + } +} + +int mi_get(struct ntfs_sb_info *sbi, CLST rno, struct mft_inode **mi) +{ + int err; + struct mft_inode *m = ntfs_alloc(sizeof(struct mft_inode), 1); + + if (!m) + return -ENOMEM; + + err = mi_init(m, sbi, rno); + if (!err) + err = mi_read(m, false); + + if (err) { + mi_put(m); + return err; + } + + *mi = m; + return 0; +} + +void mi_put(struct mft_inode *mi) +{ + mi_clear(mi); + ntfs_free(mi); +} + +int mi_init(struct mft_inode *mi, struct ntfs_sb_info *sbi, CLST rno) +{ + mi->sbi = sbi; + mi->rno = rno; + mi->mrec = ntfs_alloc(sbi->record_size, 0); + if (!mi->mrec) + return -ENOMEM; + + return 0; +} + +/* + * mi_read + * + * reads MFT data + */ +int mi_read(struct mft_inode *mi, bool is_mft) +{ + int err; + struct MFT_REC *rec = mi->mrec; + struct ntfs_sb_info *sbi = mi->sbi; + u32 bpr = sbi->record_size; + u64 vbo = (u64)mi->rno << sbi->record_bits; + struct ntfs_inode *mft_ni = sbi->mft.ni; + struct runs_tree *run = mft_ni ? &mft_ni->file.run : NULL; + struct rw_semaphore *rw_lock = NULL; + + if (is_mounted(sbi)) { + if (!is_mft) { + rw_lock = &mft_ni->file.run_lock; + down_read(rw_lock); + } + } + + err = ntfs_read_bh(sbi, run, vbo, &rec->rhdr, bpr, &mi->nb); + if (rw_lock) + up_read(rw_lock); + if (!err) + goto ok; + + if (err == 1) { + mi->dirty = true; + goto ok; + } + + if (err != -ENOENT) + goto out; + + if (rw_lock) { + ni_lock(mft_ni); + down_write(rw_lock); + } + err = attr_load_runs_vcn(mft_ni, ATTR_DATA, NULL, 0, &mft_ni->file.run, + vbo >> sbi->cluster_bits); + if (rw_lock) { + up_write(rw_lock); + ni_unlock(mft_ni); + } + if (err) + goto out; + + if (rw_lock) + down_read(rw_lock); + err = ntfs_read_bh(sbi, run, vbo, &rec->rhdr, bpr, &mi->nb); + if (rw_lock) + up_read(rw_lock); + + if (err == 1) { + mi->dirty = true; + goto ok; + } + if (err) + goto out; + +ok: + /* check field 'total' only here */ + if (le32_to_cpu(rec->total) != bpr) { + err = -EINVAL; + goto out; + } + + return 0; + +out: + return err; +} + +struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr) +{ + const struct MFT_REC *rec = mi->mrec; + u32 used = le32_to_cpu(rec->used); + u32 t32, off, asize; + u16 t16; + + if (!attr) { + u32 total = le32_to_cpu(rec->total); + + off = le16_to_cpu(rec->attr_off); + + if (used > total) + goto out; + + if (off >= used || off < MFTRECORD_FIXUP_OFFSET_1 || + !IsDwordAligned(off)) { + goto out; + } + + /* Skip non-resident records */ + if (!is_rec_inuse(rec)) + goto out; + + attr = Add2Ptr(rec, off); + } else { + /* Check if input attr inside record */ + off = PtrOffset(rec, attr); + if (off >= used) + goto out; + + asize = le32_to_cpu(attr->size); + if (asize < SIZEOF_RESIDENT) + goto out; + + attr = Add2Ptr(attr, asize); + off += asize; + } + + asize = le32_to_cpu(attr->size); + + /* Can we use the first field (attr->type) */ + if (off + 8 > used) { + static_assert(QuadAlign(sizeof(enum ATTR_TYPE)) == 8); + goto out; + } + + if (attr->type == ATTR_END) { + if (used != off + 8) + goto out; + return NULL; + } + + t32 = le32_to_cpu(attr->type); + if ((t32 & 0xf) || (t32 > 0x100)) + goto out; + + /* Check boundary */ + if (off + asize > used) + goto out; + + /* Check size of attribute */ + if (!attr->non_res) { + if (asize < SIZEOF_RESIDENT) + goto out; + + t16 = le16_to_cpu(attr->res.data_off); + + if (t16 > asize) + goto out; + + t32 = le32_to_cpu(attr->res.data_size); + if (t16 + t32 > asize) + goto out; + + return attr; + } + + /* Check some nonresident fields */ + if (attr->name_len && + le16_to_cpu(attr->name_off) + sizeof(short) * attr->name_len > + le16_to_cpu(attr->nres.run_off)) { + goto out; + } + + if (attr->nres.svcn || !is_attr_ext(attr)) { + if (asize + 8 < SIZEOF_NONRESIDENT) + goto out; + + if (attr->nres.c_unit) + goto out; + } else if (asize + 8 < SIZEOF_NONRESIDENT_EX) + goto out; + + return attr; + +out: + return NULL; +} + +/* + * mi_find_attr + * + * finds the attribute by type and name and id + */ +struct ATTRIB *mi_find_attr(struct mft_inode *mi, struct ATTRIB *attr, + enum ATTR_TYPE type, const __le16 *name, + size_t name_len, const __le16 *id) +{ + u32 type_in = le32_to_cpu(type); + u32 atype; + +next_attr: + attr = mi_enum_attr(mi, attr); + if (!attr) + return NULL; + + atype = le32_to_cpu(attr->type); + if (atype > type_in) + return NULL; + + if (atype < type_in) + goto next_attr; + + if (attr->name_len != name_len) + goto next_attr; + + if (name_len && memcmp(attr_name(attr), name, name_len * sizeof(short))) + goto next_attr; + + if (id && *id != attr->id) + goto next_attr; + + return attr; +} + +int mi_write(struct mft_inode *mi, int wait) +{ + struct MFT_REC *rec; + int err; + struct ntfs_sb_info *sbi; + + if (!mi->dirty) + return 0; + + sbi = mi->sbi; + rec = mi->mrec; + + err = ntfs_write_bh(sbi, &rec->rhdr, &mi->nb, wait); + if (err) + return err; + + if (mi->rno < sbi->mft.recs_mirr) + sbi->flags |= NTFS_FLAGS_MFTMIRR; + + mi->dirty = false; + + return 0; +} + +int mi_format_new(struct mft_inode *mi, struct ntfs_sb_info *sbi, CLST rno, + __le16 flags, bool is_mft) +{ + int err; + u16 seq = 1; + struct MFT_REC *rec; + u64 vbo = (u64)rno << sbi->record_bits; + + err = mi_init(mi, sbi, rno); + if (err) + return err; + + rec = mi->mrec; + + if (rno == MFT_REC_MFT) { + ; + } else if (rno < MFT_REC_FREE) { + seq = rno; + } else if (rno >= sbi->mft.used) { + ; + } else if (mi_read(mi, is_mft)) { + ; + } else if (rec->rhdr.sign == NTFS_FILE_SIGNATURE) { + /* Record is reused. Update its sequence number */ + seq = le16_to_cpu(rec->seq) + 1; + if (!seq) + seq = 1; + } + + memcpy(rec, sbi->new_rec, sbi->record_size); + + rec->seq = cpu_to_le16(seq); + rec->flags = RECORD_FLAG_IN_USE | flags; + + mi->dirty = true; + + if (!mi->nb.nbufs) { + struct ntfs_inode *ni = sbi->mft.ni; + bool lock = false; + + if (is_mounted(sbi) && !is_mft) { + down_read(&ni->file.run_lock); + lock = true; + } + + err = ntfs_get_bh(sbi, &ni->file.run, vbo, sbi->record_size, + &mi->nb); + if (lock) + up_read(&ni->file.run_lock); + } + + return err; +} + +/* + * mi_mark_free + * + * marks record as unused and marks it as free in bitmap + */ +void mi_mark_free(struct mft_inode *mi) +{ + CLST rno = mi->rno; + struct ntfs_sb_info *sbi = mi->sbi; + + if (rno >= MFT_REC_RESERVED && rno < MFT_REC_FREE) { + ntfs_clear_mft_tail(sbi, rno, rno + 1); + mi->dirty = false; + return; + } + + if (mi->mrec) { + clear_rec_inuse(mi->mrec); + mi->dirty = true; + mi_write(mi, 0); + } + ntfs_mark_rec_free(sbi, rno); +} + +/* + * mi_insert_attr + * + * reserves space for new attribute + * returns not full constructed attribute or NULL if not possible to create + */ +struct ATTRIB *mi_insert_attr(struct mft_inode *mi, enum ATTR_TYPE type, + const __le16 *name, u8 name_len, u32 asize, + u16 name_off) +{ + size_t tail; + struct ATTRIB *attr; + __le16 id; + struct MFT_REC *rec = mi->mrec; + struct ntfs_sb_info *sbi = mi->sbi; + u32 used = le32_to_cpu(rec->used); + const u16 *upcase = sbi->upcase; + int diff; + + /* Can we insert mi attribute? */ + if (used + asize > mi->sbi->record_size) + return NULL; + + /* + * Scan through the list of attributes to find the point + * at which we should insert it. + */ + attr = NULL; + while ((attr = mi_enum_attr(mi, attr))) { + diff = compare_attr(attr, type, name, name_len, upcase); + if (diff > 0) + break; + if (diff < 0) + continue; + + if (!is_attr_indexed(attr)) + return NULL; + break; + } + + if (!attr) { + tail = 8; /* not used, just to suppress warning */ + attr = Add2Ptr(rec, used - 8); + } else { + tail = used - PtrOffset(rec, attr); + } + + id = mi_new_attt_id(mi); + + memmove(Add2Ptr(attr, asize), attr, tail); + memset(attr, 0, asize); + + attr->type = type; + attr->size = cpu_to_le32(asize); + attr->name_len = name_len; + attr->name_off = cpu_to_le16(name_off); + attr->id = id; + + memmove(Add2Ptr(attr, name_off), name, name_len * sizeof(short)); + rec->used = cpu_to_le32(used + asize); + + mi->dirty = true; + + return attr; +} + +/* + * mi_remove_attr + * + * removes the attribute from record + * NOTE: The source attr will point to next attribute + */ +bool mi_remove_attr(struct mft_inode *mi, struct ATTRIB *attr) +{ + struct MFT_REC *rec = mi->mrec; + u32 aoff = PtrOffset(rec, attr); + u32 used = le32_to_cpu(rec->used); + u32 asize = le32_to_cpu(attr->size); + + if (aoff + asize > used) + return false; + + used -= asize; + memmove(attr, Add2Ptr(attr, asize), used - aoff); + rec->used = cpu_to_le32(used); + mi->dirty = true; + + return true; +} + +bool mi_resize_attr(struct mft_inode *mi, struct ATTRIB *attr, int bytes) +{ + struct MFT_REC *rec = mi->mrec; + u32 aoff = PtrOffset(rec, attr); + u32 total, used = le32_to_cpu(rec->used); + u32 nsize, asize = le32_to_cpu(attr->size); + u32 rsize = le32_to_cpu(attr->res.data_size); + int tail = (int)(used - aoff - asize); + int dsize; + char *next; + + if (tail < 0 || aoff >= used) + return false; + + if (!bytes) + return true; + + total = le32_to_cpu(rec->total); + next = Add2Ptr(attr, asize); + + if (bytes > 0) { + dsize = QuadAlign(bytes); + if (used + dsize > total) + return false; + nsize = asize + dsize; + // move tail + memmove(next + dsize, next, tail); + memset(next, 0, dsize); + used += dsize; + rsize += dsize; + } else { + dsize = QuadAlign(-bytes); + if (dsize > asize) + return false; + nsize = asize - dsize; + memmove(next - dsize, next, tail); + used -= dsize; + rsize -= dsize; + } + + rec->used = cpu_to_le32(used); + attr->size = cpu_to_le32(nsize); + if (!attr->non_res) + attr->res.data_size = cpu_to_le32(rsize); + mi->dirty = true; + + return true; +} + +int mi_pack_runs(struct mft_inode *mi, struct ATTRIB *attr, + struct runs_tree *run, CLST len) +{ + int err = 0; + struct ntfs_sb_info *sbi = mi->sbi; + u32 new_run_size; + CLST plen; + struct MFT_REC *rec = mi->mrec; + CLST svcn = le64_to_cpu(attr->nres.svcn); + u32 used = le32_to_cpu(rec->used); + u32 aoff = PtrOffset(rec, attr); + u32 asize = le32_to_cpu(attr->size); + char *next = Add2Ptr(attr, asize); + u16 run_off = le16_to_cpu(attr->nres.run_off); + u32 run_size = asize - run_off; + u32 tail = used - aoff - asize; + u32 dsize = sbi->record_size - used; + + /* Make a maximum gap in current record */ + memmove(next + dsize, next, tail); + + /* Pack as much as possible */ + err = run_pack(run, svcn, len, Add2Ptr(attr, run_off), run_size + dsize, + &plen); + if (err < 0) { + memmove(next, next + dsize, tail); + return err; + } + + new_run_size = QuadAlign(err); + + memmove(next + new_run_size - run_size, next + dsize, tail); + + attr->size = cpu_to_le32(asize + new_run_size - run_size); + attr->nres.evcn = cpu_to_le64(svcn + plen - 1); + rec->used = cpu_to_le32(used + new_run_size - run_size); + mi->dirty = true; + + return 0; +} diff --git a/fs/ntfs3/run.c b/fs/ntfs3/run.c new file mode 100644 index 000000000000..14f1830d2a3a --- /dev/null +++ b/fs/ntfs3/run.c @@ -0,0 +1,1161 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * linux/fs/ntfs3/run.c + * + * Copyright (C) 2019-2020 Paragon Software GmbH, All rights reserved. + * + */ + +#include +#include +#include +#include + +#include "debug.h" +#include "ntfs.h" +#include "ntfs_fs.h" + +struct ntfs_run { + CLST vcn; /* virtual cluster number */ + CLST len; /* length in clusters */ + CLST lcn; /* logical cluster number */ +}; + +/* + * run_lookup + * + * Lookup the index of a MCB entry that is first <= vcn. + * case of success it will return non-zero value and set + * 'index' parameter to index of entry been found. + * case of entry missing from list 'index' will be set to + * point to insertion position for the entry question. + */ +bool run_lookup(const struct runs_tree *run, CLST vcn, size_t *index) +{ + size_t min_idx, max_idx, mid_idx; + struct ntfs_run *r; + + if (!run->count) { + *index = 0; + return false; + } + + min_idx = 0; + max_idx = run->count - 1; + + /* Check boundary cases specially, 'cause they cover the often requests */ + r = run->runs_; + if (vcn < r->vcn) { + *index = 0; + return false; + } + + if (vcn < r->vcn + r->len) { + *index = 0; + return true; + } + + r += max_idx; + if (vcn >= r->vcn + r->len) { + *index = run->count; + return false; + } + + if (vcn >= r->vcn) { + *index = max_idx; + return true; + } + + do { + mid_idx = min_idx + ((max_idx - min_idx) >> 1); + r = run->runs_ + mid_idx; + + if (vcn < r->vcn) { + max_idx = mid_idx - 1; + if (!mid_idx) + break; + } else if (vcn >= r->vcn + r->len) { + min_idx = mid_idx + 1; + } else { + *index = mid_idx; + return true; + } + } while (min_idx <= max_idx); + + *index = max_idx + 1; + return false; +} + +/* + * run_consolidate + * + * consolidate runs starting from a given one. + */ +static void run_consolidate(struct runs_tree *run, size_t index) +{ + size_t i; + struct ntfs_run *r = run->runs_ + index; + + while (index + 1 < run->count) { + /* + * I should merge current run with next + * if start of the next run lies inside one being tested. + */ + struct ntfs_run *n = r + 1; + CLST end = r->vcn + r->len; + CLST dl; + + /* Stop if runs are not aligned one to another. */ + if (n->vcn > end) + break; + + dl = end - n->vcn; + + /* + * If range at index overlaps with next one + * then I will either adjust it's start position + * or (if completely matches) dust remove one from the list. + */ + if (dl > 0) { + if (n->len <= dl) + goto remove_next_range; + + n->len -= dl; + n->vcn += dl; + if (n->lcn != SPARSE_LCN) + n->lcn += dl; + } + + /* + * Stop if sparse mode does not match + * both current and next runs. + */ + if ((n->lcn == SPARSE_LCN) != (r->lcn == SPARSE_LCN)) { + index += 1; + r = n; + continue; + } + + /* + * Check if volume block + * of a next run lcn does not match + * last volume block of the current run. + */ + if (n->lcn != SPARSE_LCN && n->lcn != r->lcn + r->len) + break; + + /* + * Next and current are siblings. + * Eat/join. + */ + r->len += n->len - dl; + +remove_next_range: + i = run->count - (index + 1); + if (i > 1) + memmove(n, n + 1, sizeof(*n) * (i - 1)); + + run->count -= 1; + } +} + +bool run_is_mapped_full(const struct runs_tree *run, CLST svcn, CLST evcn) +{ + size_t index; + + if (!run_lookup(run, svcn, &index)) + return false; + + do { + const struct ntfs_run *m = run->runs_ + index; + CLST end = m->vcn + m->len; + + if (end > evcn) + return true; + } while (++index < run->count); + + return false; +} + +bool run_lookup_entry(const struct runs_tree *run, CLST vcn, CLST *lcn, + CLST *len, size_t *index) +{ + size_t idx; + CLST gap; + struct ntfs_run *r; + + /* Fail immediately if nrun was not touched yet. */ + if (!run->runs_) + return false; + + if (!run_lookup(run, vcn, &idx)) + return false; + + r = run->runs_ + idx; + + if (vcn >= r->vcn + r->len) + return false; + + gap = vcn - r->vcn; + if (r->len <= gap) + return false; + + *lcn = r->lcn == SPARSE_LCN ? SPARSE_LCN : (r->lcn + gap); + + if (len) + *len = r->len - gap; + if (index) + *index = idx; + + return true; +} + +/* + * run_truncate_head + * + * decommit the range before vcn + */ +void run_truncate_head(struct runs_tree *run, CLST vcn) +{ + size_t index; + struct ntfs_run *r; + + if (run_lookup(run, vcn, &index)) { + r = run->runs_ + index; + + if (vcn > r->vcn) { + CLST dlen = vcn - r->vcn; + + r->vcn = vcn; + r->len -= dlen; + if (r->lcn != SPARSE_LCN) + r->lcn += dlen; + } + + if (!index) + return; + } + r = run->runs_; + memmove(r, r + index, sizeof(*r) * (run->count - index)); + + run->count -= index; + + if (!run->count) { + ntfs_free(run->runs_); + run->runs_ = NULL; + run->allocated = 0; + } +} + +/* + * run_truncate + * + * decommit the range after vcn + */ +void run_truncate(struct runs_tree *run, CLST vcn) +{ + size_t index; + + /* + * If I hit the range then + * I have to truncate one. + * If range to be truncated is becoming empty + * then it will entirely be removed. + */ + if (run_lookup(run, vcn, &index)) { + struct ntfs_run *r = run->runs_ + index; + + r->len = vcn - r->vcn; + + if (r->len > 0) + index += 1; + } + + /* + * At this point 'index' is set to + * position that should be thrown away (including index itself) + * Simple one - just set the limit. + */ + run->count = index; + + /* Do not reallocate array 'runs'. Only free if possible */ + if (!index) { + ntfs_free(run->runs_); + run->runs_ = NULL; + run->allocated = 0; + } +} + +/* + * run_add_entry + * + * sets location to known state. + * run to be added may overlap with existing location. + * returns false if of memory + */ +bool run_add_entry(struct runs_tree *run, CLST vcn, CLST lcn, CLST len) +{ + size_t used, index; + struct ntfs_run *r; + bool inrange; + CLST tail_vcn = 0, tail_len = 0, tail_lcn = 0; + bool should_add_tail = false; + + /* + * Lookup the insertion point. + * + * Execute bsearch for the entry containing + * start position question. + */ + inrange = run_lookup(run, vcn, &index); + + /* + * Shortcut here would be case of + * range not been found but one been added + * continues previous run. + * this case I can directly make use of + * existing range as my start point. + */ + if (!inrange && index > 0) { + struct ntfs_run *t = run->runs_ + index - 1; + + if (t->vcn + t->len == vcn && + (t->lcn == SPARSE_LCN) == (lcn == SPARSE_LCN) && + (lcn == SPARSE_LCN || lcn == t->lcn + t->len)) { + inrange = true; + index -= 1; + } + } + + /* + * At this point 'index' either points to the range + * containing start position or to the insertion position + * for a new range. + * So first let's check if range I'm probing is here already. + */ + if (!inrange) { +requires_new_range: + /* + * Range was not found. + * Insert at position 'index' + */ + used = run->count * sizeof(struct ntfs_run); + + /* + * Check allocated space. + * If one is not enough to get one more entry + * then it will be reallocated + */ + if (run->allocated < used + sizeof(struct ntfs_run)) { + size_t bytes; + struct ntfs_run *new_ptr; + + /* Use power of 2 for 'bytes'*/ + if (!used) { + bytes = 64; + } else if (used <= 16 * PAGE_SIZE) { + if (is_power_of2(run->allocated)) + bytes = run->allocated << 1; + else + bytes = (size_t)1 + << (2 + blksize_bits(used)); + } else { + bytes = run->allocated + (16 * PAGE_SIZE); + } + + WARN_ON_ONCE(bytes > 0x10000); + + new_ptr = ntfs_alloc(bytes, 0); + if (!new_ptr) + return false; + + r = new_ptr + index; + memcpy(new_ptr, run->runs_, + index * sizeof(struct ntfs_run)); + memcpy(r + 1, run->runs_ + index, + sizeof(struct ntfs_run) * (run->count - index)); + + ntfs_free(run->runs_); + run->runs_ = new_ptr; + run->allocated = bytes; + + } else { + size_t i = run->count - index; + + r = run->runs_ + index; + + /* memmove appears to be a bottle neck here... */ + if (i > 0) + memmove(r + 1, r, sizeof(struct ntfs_run) * i); + } + + r->vcn = vcn; + r->lcn = lcn; + r->len = len; + run->count += 1; + } else { + r = run->runs_ + index; + + /* + * If one of ranges was not allocated + * then I have to split location I just matched. + * and insert current one + * a common case this requires tail to be reinserted + * a recursive call. + */ + if (((lcn == SPARSE_LCN) != (r->lcn == SPARSE_LCN)) || + (lcn != SPARSE_LCN && lcn != r->lcn + (vcn - r->vcn))) { + CLST to_eat = vcn - r->vcn; + CLST Tovcn = to_eat + len; + + should_add_tail = Tovcn < r->len; + + if (should_add_tail) { + tail_lcn = r->lcn == SPARSE_LCN ? + SPARSE_LCN : + (r->lcn + Tovcn); + tail_vcn = r->vcn + Tovcn; + tail_len = r->len - Tovcn; + } + + if (to_eat > 0) { + r->len = to_eat; + inrange = false; + index += 1; + goto requires_new_range; + } + + /* lcn should match one I'm going to add. */ + r->lcn = lcn; + } + + /* + * If existing range fits then I'm done. + * Otherwise extend found one and fall back to range jocode. + */ + if (r->vcn + r->len < vcn + len) + r->len += len - ((r->vcn + r->len) - vcn); + } + + /* + * And normalize it starting from insertion point. + * It's possible that no insertion needed case if + * start point lies withthe range of an entry + * that 'index' points to. + */ + if (inrange && index > 0) + index -= 1; + run_consolidate(run, index); + run_consolidate(run, index + 1); + + /* + * a special case + * I have to add extra range a tail. + */ + if (should_add_tail && + !run_add_entry(run, tail_vcn, tail_lcn, tail_len)) + return false; + + return true; +} + +/* + * run_get_entry + * + * returns index-th mapped region + */ +bool run_get_entry(const struct runs_tree *run, size_t index, CLST *vcn, + CLST *lcn, CLST *len) +{ + const struct ntfs_run *r; + + if (index >= run->count) + return false; + + r = run->runs_ + index; + + if (!r->len) + return false; + + if (vcn) + *vcn = r->vcn; + if (lcn) + *lcn = r->lcn; + if (len) + *len = r->len; + return true; +} + +/* + * run_packed_size + * + * calculates the size of packed int64 + */ +static inline int run_packed_size(const s64 *n) +{ +#ifdef __BIG_ENDIAN + const u8 *p = (const u8 *)n + sizeof(*n) - 1; + + if (*n >= 0) { + if (p[-7] || p[-6] || p[-5] || p[-4]) + p -= 4; + if (p[-3] || p[-2]) + p -= 2; + if (p[-1]) + p -= 1; + if (p[0] & 0x80) + p -= 1; + } else { + if (p[-7] != 0xff || p[-6] != 0xff || p[-5] != 0xff || + p[-4] != 0xff) + p -= 4; + if (p[-3] != 0xff || p[-2] != 0xff) + p -= 2; + if (p[-1] != 0xff) + p -= 1; + if (!(p[0] & 0x80)) + p -= 1; + } + return (const u8 *)n + sizeof(*n) - p; +#else + const u8 *p = (const u8 *)n; + + if (*n >= 0) { + if (p[7] || p[6] || p[5] || p[4]) + p += 4; + if (p[3] || p[2]) + p += 2; + if (p[1]) + p += 1; + if (p[0] & 0x80) + p += 1; + } else { + if (p[7] != 0xff || p[6] != 0xff || p[5] != 0xff || + p[4] != 0xff) + p += 4; + if (p[3] != 0xff || p[2] != 0xff) + p += 2; + if (p[1] != 0xff) + p += 1; + if (!(p[0] & 0x80)) + p += 1; + } + + return 1 + p - (const u8 *)n; +#endif +} + +/* + * run_pack + * + * packs runs into buffer + * packed_vcns - how much runs we have packed + * packed_size - how much bytes we have used run_buf + */ +int run_pack(const struct runs_tree *run, CLST svcn, CLST len, u8 *run_buf, + u32 run_buf_size, CLST *packed_vcns) +{ + CLST next_vcn, vcn, lcn; + CLST prev_lcn = 0; + CLST evcn1 = svcn + len; + int packed_size = 0; + size_t i; + bool ok; + s64 dlcn, len64; + int offset_size, size_size, t; + const u8 *p; + + next_vcn = vcn = svcn; + + *packed_vcns = 0; + + if (!len) + goto out; + + ok = run_lookup_entry(run, vcn, &lcn, &len, &i); + + if (!ok) + goto error; + + if (next_vcn != vcn) + goto error; + + for (;;) { + /* offset of current fragment relatively to previous fragment */ + dlcn = 0; + next_vcn = vcn + len; + + if (next_vcn > evcn1) + len = evcn1 - vcn; + + /* + * mirror of len, but signed, because run_packed_size() + * works with signed int only + */ + len64 = len; + + /* how much bytes is packed len64 */ + size_size = run_packed_size(&len64); + + /* offset_size - how much bytes is packed dlcn */ + if (lcn == SPARSE_LCN) { + offset_size = 0; + } else { + /* NOTE: lcn can be less than prev_lcn! */ + dlcn = (s64)lcn - prev_lcn; + offset_size = run_packed_size(&dlcn); + prev_lcn = lcn; + } + + t = run_buf_size - packed_size - 2 - offset_size; + if (t <= 0) + goto out; + + /* can we store this entire run */ + if (t < size_size) + goto out; + + if (run_buf) { + p = (u8 *)&len64; + + /* pack run header */ + run_buf[0] = ((u8)(size_size | (offset_size << 4))); + run_buf += 1; + + /* Pack the length of run */ + switch (size_size) { +#ifdef __BIG_ENDIAN + case 8: + run_buf[7] = p[0]; + fallthrough; + case 7: + run_buf[6] = p[1]; + fallthrough; + case 6: + run_buf[5] = p[2]; + fallthrough; + case 5: + run_buf[4] = p[3]; + fallthrough; + case 4: + run_buf[3] = p[4]; + fallthrough; + case 3: + run_buf[2] = p[5]; + fallthrough; + case 2: + run_buf[1] = p[6]; + fallthrough; + case 1: + run_buf[0] = p[7]; +#else + case 8: + run_buf[7] = p[7]; + fallthrough; + case 7: + run_buf[6] = p[6]; + fallthrough; + case 6: + run_buf[5] = p[5]; + fallthrough; + case 5: + run_buf[4] = p[4]; + fallthrough; + case 4: + run_buf[3] = p[3]; + fallthrough; + case 3: + run_buf[2] = p[2]; + fallthrough; + case 2: + run_buf[1] = p[1]; + fallthrough; + case 1: + run_buf[0] = p[0]; +#endif + } + + run_buf += size_size; + p = (u8 *)&dlcn; + + /* Pack the offset from previous lcn */ + switch (offset_size) { +#ifdef __BIG_ENDIAN + case 8: + run_buf[7] = p[0]; + fallthrough; + case 7: + run_buf[6] = p[1]; + fallthrough; + case 6: + run_buf[5] = p[2]; + fallthrough; + case 5: + run_buf[4] = p[3]; + fallthrough; + case 4: + run_buf[3] = p[4]; + fallthrough; + case 3: + run_buf[2] = p[5]; + fallthrough; + case 2: + run_buf[1] = p[6]; + fallthrough; + case 1: + run_buf[0] = p[7]; +#else + case 8: + run_buf[7] = p[7]; + fallthrough; + case 7: + run_buf[6] = p[6]; + fallthrough; + case 6: + run_buf[5] = p[5]; + fallthrough; + case 5: + run_buf[4] = p[4]; + fallthrough; + case 4: + run_buf[3] = p[3]; + fallthrough; + case 3: + run_buf[2] = p[2]; + fallthrough; + case 2: + run_buf[1] = p[1]; + fallthrough; + case 1: + run_buf[0] = p[0]; +#endif + } + + run_buf += offset_size; + } + + packed_size += 1 + offset_size + size_size; + *packed_vcns += len; + + if (packed_size + 1 >= run_buf_size || next_vcn >= evcn1) + goto out; + + ok = run_get_entry(run, ++i, &vcn, &lcn, &len); + if (!ok) + goto error; + + if (next_vcn != vcn) + goto error; + } + +out: + /* Store last zero */ + if (run_buf) + run_buf[0] = 0; + + return packed_size + 1; + +error: + return -EOPNOTSUPP; +} + +/* + * run_unpack + * + * unpacks packed runs from "run_buf" + * returns error, if negative, or real used bytes + */ +int run_unpack(struct runs_tree *run, struct ntfs_sb_info *sbi, CLST ino, + CLST svcn, CLST evcn, const u8 *run_buf, u32 run_buf_size) +{ + u64 prev_lcn, vcn; + const u8 *run_last, *run_0; + u64 lcn; + u64 next_vcn; + + /* Check for empty */ + if (evcn + 1 == svcn) + return 0; + + if (evcn < svcn) + return -EINVAL; + + run_0 = run_buf; + run_last = run_buf + run_buf_size; + prev_lcn = 0; + vcn = svcn; + + /* Read all runs the chain */ + /* size_size - how much bytes is packed len */ + while (run_buf < run_last) { + /* size_size - how much bytes is packed len */ + u8 size_size = *run_buf & 0xF; + /* offset_size - how much bytes is packed dlcn */ + u8 offset_size = *run_buf++ >> 4; + u64 len = 0; + u8 *p = (u8 *)&len; + + if (!size_size) + break; + + /* + * Unpack runs. + * NOTE: runs are stored little endian order + * "len" is unsigned value, "dlcn" is signed + * Large positive number requires to store 5 bytes + * e.g.: 05 FF 7E FF FF 00 00 00 + */ + + switch (size_size) { + default: +error: + return -EINVAL; + +#ifdef __BIG_ENDIAN + case 8: + p[0] = run_buf[7]; + fallthrough; + case 7: + p[1] = run_buf[6]; + fallthrough; + case 6: + p[2] = run_buf[5]; + fallthrough; + case 5: + p[3] = run_buf[4]; + fallthrough; + case 4: + p[4] = run_buf[3]; + fallthrough; + case 3: + p[5] = run_buf[2]; + fallthrough; + case 2: + p[6] = run_buf[1]; + fallthrough; + case 1: + p[7] = run_buf[0]; +#else + case 8: + p[7] = run_buf[7]; + fallthrough; + case 7: + p[6] = run_buf[6]; + fallthrough; + case 6: + p[5] = run_buf[5]; + fallthrough; + case 5: + p[4] = run_buf[4]; + fallthrough; + case 4: + p[3] = run_buf[3]; + fallthrough; + case 3: + p[2] = run_buf[2]; + fallthrough; + case 2: + p[1] = run_buf[1]; + fallthrough; + case 1: + p[0] = run_buf[0]; +#endif + } + + /* skip size_size */ + run_buf += size_size; + + if (!len) + goto error; + + if (!offset_size) { + lcn = SPARSE_LCN; + } else { + /* Check sign */ + s64 dlcn = + (run_buf[offset_size - 1] & 0x80) ? (s64)-1 : 0; + + p = (u8 *)&dlcn; + + switch (offset_size) { + default: + goto error; + +#ifdef __BIG_ENDIAN + case 8: + p[0] = run_buf[7]; + fallthrough; + case 7: + p[1] = run_buf[6]; + fallthrough; + case 6: + p[2] = run_buf[5]; + fallthrough; + case 5: + p[3] = run_buf[4]; + fallthrough; + case 4: + p[4] = run_buf[3]; + fallthrough; + case 3: + p[5] = run_buf[2]; + fallthrough; + case 2: + p[6] = run_buf[1]; + fallthrough; + case 1: + p[7] = run_buf[0]; +#else + case 8: + p[7] = run_buf[7]; + fallthrough; + case 7: + p[6] = run_buf[6]; + fallthrough; + case 6: + p[5] = run_buf[5]; + fallthrough; + case 5: + p[4] = run_buf[4]; + fallthrough; + case 4: + p[3] = run_buf[3]; + fallthrough; + case 3: + p[2] = run_buf[2]; + fallthrough; + case 2: + p[1] = run_buf[1]; + fallthrough; + case 1: + p[0] = run_buf[0]; +#endif + } + + /* skip offset_size */ + run_buf += offset_size; + lcn = prev_lcn + dlcn; + prev_lcn = lcn; + } + + next_vcn = vcn + len; + /* check boundary */ + if (next_vcn > evcn + 1) + goto error; + +#ifndef NTFS3_64BIT_CLUSTER + if ((vcn >> 32) + /* 0xffffffffffffffff is a valid 'lcn' */ + || (lcn + 1) > 0x100000000ull || (len >> 32)) { + goto error; + } +#endif + + if (!run) + ; /* called from check_attr(fslog.c) to check run */ + else if ((size_t)run == 1) { + /* called from ni_delete_all to free clusters without storing in run */ + if (lcn != SPARSE_LCN) + mark_as_free_ex(sbi, lcn, len, true); + } else if (!run_add_entry(run, vcn, lcn, len)) + return -ENOMEM; + + if (lcn != SPARSE_LCN && lcn + len > sbi->used.bitmap.nbits) + return -EINVAL; + + vcn = next_vcn; + } + + /* Check vcn consistency */ + if (vcn == evcn + 1) + return run_buf - run_0; + + return -EINVAL; +} + +#ifdef NTFS3_CHECK_FREE_CLST +/* + * run_unpack_ex + * + * unpacks packed runs from "run_buf" + * checks unpacked runs to be used in bitmap + * returns error, if negative, or real used bytes + */ +int run_unpack_ex(struct runs_tree *run, struct ntfs_sb_info *sbi, CLST ino, + CLST svcn, CLST evcn, const u8 *run_buf, u32 run_buf_size) +{ + int ret, err; + CLST next_vcn, vcn, lcn, len; + size_t index; + bool ok; + struct wnd_bitmap *wnd; + + ret = run_unpack(run, sbi, ino, svcn, evcn, run_buf, run_buf_size); + if (ret < 0) + return ret; + + if (!sbi->used.bitmap.sb || !run || (size_t)run == 1) + return ret; + + if (ino == MFT_REC_BADCLUST) + return ret; + + next_vcn = vcn = svcn; + wnd = &sbi->used.bitmap; + + for (ok = run_lookup_entry(run, vcn, &lcn, &len, &index); + next_vcn <= evcn; + ok = run_get_entry(run, ++index, &vcn, &lcn, &len)) { + CLST real_free, i; + + if (!ok || next_vcn != vcn) + return -EINVAL; + + next_vcn = vcn + len; + + if (lcn == SPARSE_LCN) + continue; + + if (sbi->flags & NTFS_FLAGS_NEED_REPLAY) + continue; + +next: + down_read_nested(&wnd->rw_lock, BITMAP_MUTEX_CLUSTERS); + /* Check for free blocks */ + ok = wnd_is_used(wnd, lcn, len); + up_read(&wnd->rw_lock); + if (ok) + continue; + + ntfs_set_state(sbi, NTFS_DIRTY_ERROR); + + if (!down_write_trylock(&wnd->rw_lock)) + continue; + + /* Find first free */ + real_free = len; + while (real_free && !wnd_is_free(wnd, lcn, 1)) { + lcn += 1; + real_free -= 1; + } + + if (!real_free) { + up_write(&wnd->rw_lock); + continue; + } + + /* Find total free */ + i = 1; + while (i < real_free && wnd_is_free(wnd, lcn + i, 1)) + i += 1; + + real_free = i; + + err = wnd_set_used(wnd, lcn, real_free); + up_write(&wnd->rw_lock); + + if (err) + return err; + + if (len != real_free) { + len -= real_free + 1; + lcn += real_free + 1; + goto next; + } + } + + return ret; +} +#endif + +/* + * run_get_highest_vcn + * + * returns the highest vcn from a mapping pairs array + * it used while replaying log file + */ +int run_get_highest_vcn(CLST vcn, const u8 *run_buf, u64 *highest_vcn) +{ + const u8 *run = run_buf; + u64 vcn64 = vcn; + u8 size_size; + + while ((size_size = *run & 0xF)) { + u8 offset_size = *run++ >> 4; + u64 len = 0; + u8 *p = (u8 *)&len; + + switch (size_size) { + default: +error: + return -EINVAL; + +#ifdef __BIG_ENDIAN + case 8: + p[0] = run[7]; + fallthrough; + case 7: + p[1] = run[6]; + fallthrough; + case 6: + p[2] = run[5]; + fallthrough; + case 5: + p[3] = run[4]; + fallthrough; + case 4: + p[4] = run[3]; + fallthrough; + case 3: + p[5] = run[2]; + fallthrough; + case 2: + p[6] = run[1]; + fallthrough; + case 1: + p[7] = run[0]; +#else + case 8: + p[7] = run[7]; + fallthrough; + case 7: + p[6] = run[6]; + fallthrough; + case 6: + p[5] = run[5]; + fallthrough; + case 5: + p[4] = run[4]; + fallthrough; + case 4: + p[3] = run[3]; + fallthrough; + case 3: + p[2] = run[2]; + fallthrough; + case 2: + p[1] = run[1]; + fallthrough; + case 1: + p[0] = run[0]; +#endif + } + + /* skip size_size */ + run += size_size; + + if (!len) + goto error; + + run += offset_size; + +#ifdef NTFS3_64BIT_CLUSTER + if ((vcn >> 32) || (len >> 32)) + goto error; +#endif + vcn64 += len; + } + + *highest_vcn = vcn64 - 1; + return 0; +} From patchwork Fri Oct 9 14:22:56 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Konstantin Komarov X-Patchwork-Id: 11825959 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 8ECBE1744 for ; Fri, 9 Oct 2020 14:23:54 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 2C816222C3 for ; Fri, 9 Oct 2020 14:23:54 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (1024-bit key) header.d=paragon-software.com header.i=@paragon-software.com header.b="jZW0dE3V" Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S2388768AbgJIOXr (ORCPT ); Fri, 9 Oct 2020 10:23:47 -0400 Received: from relaydlg-01.paragon-software.com ([81.5.88.159]:42931 "EHLO relaydlg-01.paragon-software.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S2388579AbgJIOXY (ORCPT ); Fri, 9 Oct 2020 10:23:24 -0400 Received: from dlg2.mail.paragon-software.com (vdlg-exch-02.paragon-software.com [172.30.1.105]) by relaydlg-01.paragon-software.com (Postfix) with ESMTPS id 50B1F8237F; Fri, 9 Oct 2020 17:23:09 +0300 (MSK) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=paragon-software.com; s=mail; t=1602253389; bh=tH1JDRHTaLQKShSXLEr9X6IYqo+MWZr0n2q7S1+K9j8=; h=From:To:CC:Subject:Date:In-Reply-To:References; b=jZW0dE3VLMolCrYVJZzwylsBc7nAHmsEE83b7Si6dRUuR7wgWfPFyt2wVXSU9RBS+ E/mFPCarXfmWI4/Zhex70BFx47UfXqe5AQqJNRmPsBJ9HJB3IpfK5roq6VPcqyEeKK lAnJsByyqSCZyBSu2/0nhAdWC1txZaFiubrNYy50= Received: from fsd-lkpg.ufsd.paragon-software.com (172.30.114.105) by vdlg-exch-02.paragon-software.com (172.30.1.105) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id 15.1.1847.3; Fri, 9 Oct 2020 17:23:08 +0300 From: Konstantin Komarov To: CC: , , , , , , , , , , , , Konstantin Komarov Subject: [PATCH v8 05/10] fs/ntfs3: Add attrib operations Date: Fri, 9 Oct 2020 17:22:56 +0300 Message-ID: <20201009142301.412454-6-almaz.alexandrovich@paragon-software.com> X-Mailer: git-send-email 2.25.4 In-Reply-To: <20201009142301.412454-1-almaz.alexandrovich@paragon-software.com> References: <20201009142301.412454-1-almaz.alexandrovich@paragon-software.com> MIME-Version: 1.0 X-Originating-IP: [172.30.114.105] X-ClientProxiedBy: vdlg-exch-02.paragon-software.com (172.30.1.105) To vdlg-exch-02.paragon-software.com (172.30.1.105) Precedence: bulk List-ID: X-Mailing-List: linux-fsdevel@vger.kernel.org This adds attrib operations Signed-off-by: Konstantin Komarov --- fs/ntfs3/attrib.c | 1325 +++++++++++++++++++++++++++++++++++++++++++ fs/ntfs3/attrlist.c | 462 +++++++++++++++ fs/ntfs3/xattr.c | 1060 ++++++++++++++++++++++++++++++++++ 3 files changed, 2847 insertions(+) create mode 100644 fs/ntfs3/attrib.c create mode 100644 fs/ntfs3/attrlist.c create mode 100644 fs/ntfs3/xattr.c diff --git a/fs/ntfs3/attrib.c b/fs/ntfs3/attrib.c new file mode 100644 index 000000000000..a7dc84626af0 --- /dev/null +++ b/fs/ntfs3/attrib.c @@ -0,0 +1,1325 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * linux/fs/ntfs3/attrib.c + * + * Copyright (C) 2019-2020 Paragon Software GmbH, All rights reserved. + * + * TODO: merge attr_set_size/attr_data_get_block/attr_allocate_frame? + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#include "debug.h" +#include "ntfs.h" +#include "ntfs_fs.h" + +/* + * You can set external NTFS_MIN_LOG2_OF_CLUMP/NTFS_MAX_LOG2_OF_CLUMP to manage + * preallocate algorithm + */ +#ifndef NTFS_MIN_LOG2_OF_CLUMP +#define NTFS_MIN_LOG2_OF_CLUMP 16 +#endif + +#ifndef NTFS_MAX_LOG2_OF_CLUMP +#define NTFS_MAX_LOG2_OF_CLUMP 26 +#endif + +// 16M +#define NTFS_CLUMP_MIN (1 << (NTFS_MIN_LOG2_OF_CLUMP + 8)) +// 16G +#define NTFS_CLUMP_MAX (1ull << (NTFS_MAX_LOG2_OF_CLUMP + 8)) + +/* + * get_pre_allocated + * + */ +static inline u64 get_pre_allocated(u64 size) +{ + u32 clump; + u8 align_shift; + u64 ret; + + if (size <= NTFS_CLUMP_MIN) { + clump = 1 << NTFS_MIN_LOG2_OF_CLUMP; + align_shift = NTFS_MIN_LOG2_OF_CLUMP; + } else if (size >= NTFS_CLUMP_MAX) { + clump = 1 << NTFS_MAX_LOG2_OF_CLUMP; + align_shift = NTFS_MAX_LOG2_OF_CLUMP; + } else { + align_shift = NTFS_MIN_LOG2_OF_CLUMP - 1 + + __ffs(size >> (8 + NTFS_MIN_LOG2_OF_CLUMP)); + clump = 1u << align_shift; + } + + ret = (((size + clump - 1) >> align_shift)) << align_shift; + + return ret; +} + +/* + * attr_must_be_resident + * + * returns true if attribute must be resident + */ +static inline bool attr_must_be_resident(struct ntfs_sb_info *sbi, + enum ATTR_TYPE type) +{ + const struct ATTR_DEF_ENTRY *de; + + switch (type) { + case ATTR_STD: + case ATTR_NAME: + case ATTR_ID: + case ATTR_LABEL: + case ATTR_VOL_INFO: + case ATTR_ROOT: + case ATTR_EA_INFO: + return true; + default: + de = ntfs_query_def(sbi, type); + if (de && (de->flags & NTFS_ATTR_MUST_BE_RESIDENT)) + return true; + return false; + } +} + +/* + * attr_load_runs + * + * load all runs stored in 'attr' + */ +int attr_load_runs(struct ATTRIB *attr, struct ntfs_inode *ni, + struct runs_tree *run) +{ + int err; + CLST svcn = le64_to_cpu(attr->nres.svcn); + CLST evcn = le64_to_cpu(attr->nres.evcn); + u32 asize; + u16 run_off; + + if (svcn >= evcn + 1 || run_is_mapped_full(run, svcn, evcn)) + return 0; + + asize = le32_to_cpu(attr->size); + run_off = le16_to_cpu(attr->nres.run_off); + err = run_unpack_ex(run, ni->mi.sbi, ni->mi.rno, svcn, evcn, + Add2Ptr(attr, run_off), asize - run_off); + if (err < 0) + return err; + + return 0; +} + +/* + * int run_deallocate_ex + * + * Deallocate clusters + */ +static int run_deallocate_ex(struct ntfs_sb_info *sbi, struct runs_tree *run, + CLST vcn, CLST len, CLST *done, bool trim) +{ + int err = 0; + CLST vcn0 = vcn, lcn, clen, dn = 0; + size_t idx; + + if (!len) + goto out; + + if (!run_lookup_entry(run, vcn, &lcn, &clen, &idx)) { +failed: + run_truncate(run, vcn0); + err = -EINVAL; + goto out; + } + + for (;;) { + if (clen > len) + clen = len; + + if (!clen) { + err = -EINVAL; + goto out; + } + + if (lcn != SPARSE_LCN) { + mark_as_free_ex(sbi, lcn, clen, trim); + dn += clen; + } + + len -= clen; + if (!len) + break; + + if (!run_get_entry(run, ++idx, &vcn, &lcn, &clen)) { + // save memory - don't load entire run + goto failed; + } + } + +out: + if (done) + *done = dn; + + return err; +} + +/* + * attr_allocate_clusters + * + * find free space, mark it as used and store in 'run' + */ +int attr_allocate_clusters(struct ntfs_sb_info *sbi, struct runs_tree *run, + CLST vcn, CLST lcn, CLST len, CLST *pre_alloc, + enum ALLOCATE_OPT opt, CLST *alen, const size_t fr, + CLST *new_lcn) +{ + int err; + CLST flen, vcn0 = vcn, pre = pre_alloc ? *pre_alloc : 0; + struct wnd_bitmap *wnd = &sbi->used.bitmap; + size_t cnt = run->count; + + for (;;) { + err = ntfs_look_for_free_space(sbi, lcn, len + pre, &lcn, &flen, + opt); + + if (err == -ENOSPC && pre) { + pre = 0; + if (*pre_alloc) + *pre_alloc = 0; + continue; + } + + if (err) + goto out; + + if (new_lcn && vcn == vcn0) + *new_lcn = lcn; + + /* Add new fragment into run storage */ + if (!run_add_entry(run, vcn, lcn, flen)) { + down_write_nested(&wnd->rw_lock, BITMAP_MUTEX_CLUSTERS); + wnd_set_free(wnd, lcn, flen); + up_write(&wnd->rw_lock); + err = -ENOMEM; + goto out; + } + + vcn += flen; + + if (flen >= len || opt == ALLOCATE_MFT || + (fr && run->count - cnt >= fr)) { + *alen = vcn - vcn0; + return 0; + } + + len -= flen; + } + +out: + /* undo */ + run_deallocate_ex(sbi, run, vcn0, vcn - vcn0, NULL, false); + run_truncate(run, vcn0); + + return err; +} + +/* + * attr_set_size_res + * + * helper for attr_set_size + */ +static int attr_set_size_res(struct ntfs_inode *ni, struct ATTRIB *attr, + struct ATTR_LIST_ENTRY *le, struct mft_inode *mi, + u64 new_size, struct runs_tree *run, + struct ATTRIB **ins_attr) +{ + int err = 0; + struct ntfs_sb_info *sbi = mi->sbi; + struct MFT_REC *rec = mi->mrec; + u32 used = le32_to_cpu(rec->used); + u32 asize = le32_to_cpu(attr->size); + u32 aoff = PtrOffset(rec, attr); + u32 rsize = le32_to_cpu(attr->res.data_size); + u32 tail = used - aoff - asize; + char *next = Add2Ptr(attr, asize); + int dsize = QuadAlign(new_size) - QuadAlign(rsize); + CLST len, alen; + struct ATTRIB *attr_s = NULL; + bool is_ext; + + if (dsize < 0) { + memmove(next + dsize, next, tail); + } else if (dsize > 0) { + if (used + dsize > sbi->max_bytes_per_attr) + goto resident2nonresident; + + memmove(next + dsize, next, tail); + memset(next, 0, dsize); + } + + rec->used = cpu_to_le32(used + dsize); + attr->size = cpu_to_le32(asize + dsize); + attr->res.data_size = cpu_to_le32(new_size); + mi->dirty = true; + *ins_attr = attr; + + return 0; + +resident2nonresident: + len = bytes_to_cluster(sbi, rsize); + + run_init(run); + + is_ext = is_attr_ext(attr); + + if (!len) { + alen = 0; + } else if (is_ext) { + if (!run_add_entry(run, 0, SPARSE_LCN, len)) { + err = -ENOMEM; + goto out; + } + alen = len; + } else { + err = attr_allocate_clusters(sbi, run, 0, 0, len, NULL, + ALLOCATE_DEF, &alen, 0, NULL); + if (err) + goto out; + + err = ntfs_sb_write_run(sbi, run, 0, resident_data(attr), + rsize); + if (err) + goto out; + } + + attr_s = ntfs_memdup(attr, asize); + if (!attr_s) { + err = -ENOMEM; + goto out; + } + + /*verify(mi_remove_attr(mi, attr));*/ + used -= asize; + memmove(attr, Add2Ptr(attr, asize), used - aoff); + rec->used = cpu_to_le32(used); + mi->dirty = true; + if (le) + al_remove_le(ni, le); + + err = ni_insert_nonresident(ni, attr_s->type, attr_name(attr_s), + attr_s->name_len, run, 0, alen, + attr_s->flags, &attr, NULL); + if (err) + goto out; + + ntfs_free(attr_s); + attr->nres.data_size = cpu_to_le64(rsize); + attr->nres.valid_size = attr->nres.data_size; + + *ins_attr = attr; + + if (attr_s->type == ATTR_DATA && !attr_s->name_len && + run == &ni->file.run) { + ni->ni_flags &= ~NI_FLAG_RESIDENT; + } + + /* Resident attribute becomes non resident */ + return 0; + +out: + /* undo: do not trim new allocated clusters */ + run_deallocate(sbi, run, false); + run_close(run); + + if (attr_s) { + memmove(next, Add2Ptr(rec, aoff), used - aoff); + memcpy(Add2Ptr(rec, aoff), attr_s, asize); + rec->used = cpu_to_le32(used + asize); + mi->dirty = true; + ntfs_free(attr_s); + /*reinsert le*/ + } + + return err; +} + +/* + * attr_set_size + * + * change the size of attribute + * Extend: + * - sparse/compressed: no allocated clusters + * - normal: append allocated and preallocated new clusters + * Shrink: + * - no deallocate if keep_prealloc is set + */ +int attr_set_size(struct ntfs_inode *ni, enum ATTR_TYPE type, + const __le16 *name, u8 name_len, struct runs_tree *run, + u64 new_size, const u64 *new_valid, bool keep_prealloc, + struct ATTRIB **ret) +{ + int err = 0; + struct ntfs_sb_info *sbi = ni->mi.sbi; + u8 cluster_bits = sbi->cluster_bits; + bool is_mft = + ni->mi.rno == MFT_REC_MFT && type == ATTR_DATA && !name_len; + u64 old_valid, old_size, old_alloc, new_alloc, new_alloc_tmp; + struct ATTRIB *attr, *attr_b; + struct ATTR_LIST_ENTRY *le, *le_b; + struct mft_inode *mi, *mi_b; + CLST alen, vcn, lcn, new_alen, old_alen, svcn, evcn; + CLST next_svcn, pre_alloc = -1, done = 0; + bool is_ext; + u32 align; + struct MFT_REC *rec; + +again: + le_b = NULL; + attr_b = ni_find_attr(ni, NULL, &le_b, type, name, name_len, NULL, + &mi_b); + if (!attr_b) { + err = -ENOENT; + goto out; + } + + if (!attr_b->non_res) { + err = attr_set_size_res(ni, attr_b, le_b, mi_b, new_size, run, + &attr_b); + if (err || !attr_b->non_res) + goto out; + + /* layout of records may be changed, so do a full search */ + goto again; + } + + is_ext = is_attr_ext(attr_b); + +again_1: + + if (is_ext) { + align = 1u << (attr_b->nres.c_unit + cluster_bits); + if (is_attr_sparsed(attr_b)) + keep_prealloc = false; + } else { + align = sbi->cluster_size; + } + + old_valid = le64_to_cpu(attr_b->nres.valid_size); + old_size = le64_to_cpu(attr_b->nres.data_size); + old_alloc = le64_to_cpu(attr_b->nres.alloc_size); + old_alen = old_alloc >> cluster_bits; + + new_alloc = (new_size + align - 1) & ~(u64)(align - 1); + new_alen = new_alloc >> cluster_bits; + + if (keep_prealloc && is_ext) + keep_prealloc = false; + + if (keep_prealloc && new_size < old_size) { + attr_b->nres.data_size = cpu_to_le64(new_size); + mi_b->dirty = true; + goto ok; + } + + vcn = old_alen - 1; + + svcn = le64_to_cpu(attr_b->nres.svcn); + evcn = le64_to_cpu(attr_b->nres.evcn); + + if (svcn <= vcn && vcn <= evcn) { + attr = attr_b; + le = le_b; + mi = mi_b; + } else if (!le_b) { + err = -EINVAL; + goto out; + } else { + le = le_b; + attr = ni_find_attr(ni, attr_b, &le, type, name, name_len, &vcn, + &mi); + if (!attr) { + err = -EINVAL; + goto out; + } + +next_le_1: + svcn = le64_to_cpu(attr->nres.svcn); + evcn = le64_to_cpu(attr->nres.evcn); + } + +next_le: + rec = mi->mrec; + + err = attr_load_runs(attr, ni, run); + if (err) + goto out; + + if (new_size > old_size) { + CLST to_allocate; + size_t free; + + if (new_alloc <= old_alloc) { + attr_b->nres.data_size = cpu_to_le64(new_size); + mi_b->dirty = true; + goto ok; + } + + to_allocate = new_alen - old_alen; +add_alloc_in_same_attr_seg: + lcn = 0; + if (is_mft) { + /* mft allocates clusters from mftzone */ + pre_alloc = 0; + } else if (is_ext) { + /* no preallocate for sparse/compress */ + pre_alloc = 0; + } else if (pre_alloc == -1) { + pre_alloc = 0; + if (type == ATTR_DATA && !name_len && + sbi->options.prealloc) { + CLST new_alen2 = bytes_to_cluster( + sbi, get_pre_allocated(new_size)); + pre_alloc = new_alen2 - new_alen; + } + + /* Get the last lcn to allocate from */ + if (old_alen && + !run_lookup_entry(run, vcn, &lcn, NULL, NULL)) { + lcn = SPARSE_LCN; + } + + if (lcn == SPARSE_LCN) + lcn = 0; + else if (lcn) + lcn += 1; + + free = wnd_zeroes(&sbi->used.bitmap); + if (to_allocate > free) { + err = -ENOSPC; + goto out; + } + + if (pre_alloc && to_allocate + pre_alloc > free) + pre_alloc = 0; + } + + vcn = old_alen; + + if (is_ext) { + if (!run_add_entry(run, vcn, SPARSE_LCN, to_allocate)) { + err = -ENOMEM; + goto out; + } + alen = to_allocate; + } else { + /* ~3 bytes per fragment */ + err = attr_allocate_clusters( + sbi, run, vcn, lcn, to_allocate, &pre_alloc, + is_mft ? ALLOCATE_MFT : 0, &alen, + is_mft ? 0 : + (sbi->record_size - + le32_to_cpu(rec->used) + 8) / + 3 + + 1, + NULL); + if (err) + goto out; + } + + done += alen; + vcn += alen; + if (to_allocate > alen) + to_allocate -= alen; + else + to_allocate = 0; + +pack_runs: + err = mi_pack_runs(mi, attr, run, vcn - svcn); + if (err) + goto out; + + next_svcn = le64_to_cpu(attr->nres.evcn) + 1; + new_alloc_tmp = (u64)next_svcn << cluster_bits; + attr_b->nres.alloc_size = cpu_to_le64(new_alloc_tmp); + mi_b->dirty = true; + + if (next_svcn >= vcn && !to_allocate) { + /* Normal way. update attribute and exit */ + attr_b->nres.data_size = cpu_to_le64(new_size); + goto ok; + } + + /* at least two mft to avoid recursive loop*/ + if (is_mft && next_svcn == vcn && + ((u64)done << sbi->cluster_bits) >= 2 * sbi->record_size) { + new_size = new_alloc_tmp; + attr_b->nres.data_size = attr_b->nres.alloc_size; + goto ok; + } + + if (le32_to_cpu(rec->used) < sbi->record_size) { + old_alen = next_svcn; + evcn = old_alen - 1; + goto add_alloc_in_same_attr_seg; + } + + attr_b->nres.data_size = attr_b->nres.alloc_size; + if (new_alloc_tmp < old_valid) + attr_b->nres.valid_size = attr_b->nres.data_size; + + if (type == ATTR_LIST) { + err = ni_expand_list(ni); + if (err) + goto out; + if (next_svcn < vcn) + goto pack_runs; + + /* layout of records is changed */ + goto again; + } + + if (!ni->attr_list.size) { + err = ni_create_attr_list(ni); + if (err) + goto out; + /* layout of records is changed */ + } + + if (next_svcn >= vcn) { + /* this is mft data, repeat */ + goto again; + } + + /* insert new attribute segment */ + err = ni_insert_nonresident(ni, type, name, name_len, run, + next_svcn, vcn - next_svcn, + attr_b->flags, &attr, &mi); + if (err) + goto out; + + if (!is_mft) + run_truncate_head(run, evcn + 1); + + svcn = le64_to_cpu(attr->nres.svcn); + evcn = le64_to_cpu(attr->nres.evcn); + + le_b = NULL; + /* layout of records maybe changed */ + /* find base attribute to update*/ + attr_b = ni_find_attr(ni, NULL, &le_b, type, name, name_len, + NULL, &mi_b); + if (!attr_b) { + err = -ENOENT; + goto out; + } + + attr_b->nres.alloc_size = cpu_to_le64((u64)vcn << cluster_bits); + attr_b->nres.data_size = attr_b->nres.alloc_size; + attr_b->nres.valid_size = attr_b->nres.alloc_size; + mi_b->dirty = true; + goto again_1; + } + + if (new_size != old_size || + (new_alloc != old_alloc && !keep_prealloc)) { + vcn = max(svcn, new_alen); + new_alloc_tmp = (u64)vcn << cluster_bits; + + err = run_deallocate_ex(sbi, run, vcn, evcn - vcn + 1, &alen, + true); + if (err) + goto out; + + run_truncate(run, vcn); + + if (vcn > svcn) { + err = mi_pack_runs(mi, attr, run, vcn - svcn); + if (err < 0) + goto out; + } else if (le && le->vcn) { + u16 le_sz = le16_to_cpu(le->size); + + /* + * NOTE: list entries for one attribute are always + * the same size. We deal with last entry (vcn==0) + * and it is not first in entries array + * (list entry for std attribute always first) + * So it is safe to step back + */ + mi_remove_attr(mi, attr); + + if (!al_remove_le(ni, le)) { + err = -EINVAL; + goto out; + } + + le = (struct ATTR_LIST_ENTRY *)((u8 *)le - le_sz); + } else { + attr->nres.evcn = cpu_to_le64((u64)vcn - 1); + mi->dirty = true; + } + + attr_b->nres.alloc_size = cpu_to_le64(new_alloc_tmp); + + if (vcn == new_alen) { + attr_b->nres.data_size = cpu_to_le64(new_size); + if (new_size < old_valid) + attr_b->nres.valid_size = + attr_b->nres.data_size; + } else { + if (new_alloc_tmp <= + le64_to_cpu(attr_b->nres.data_size)) + attr_b->nres.data_size = + attr_b->nres.alloc_size; + if (new_alloc_tmp < + le64_to_cpu(attr_b->nres.valid_size)) + attr_b->nres.valid_size = + attr_b->nres.alloc_size; + } + + if (is_ext) + le64_sub_cpu(&attr_b->nres.total_size, + ((u64)alen << cluster_bits)); + + mi_b->dirty = true; + + if (new_alloc_tmp <= new_alloc) + goto ok; + + old_size = new_alloc_tmp; + vcn = svcn - 1; + + if (le == le_b) { + attr = attr_b; + mi = mi_b; + evcn = svcn - 1; + svcn = 0; + goto next_le; + } + + if (le->type != type || le->name_len != name_len || + memcmp(le_name(le), name, name_len * sizeof(short))) { + err = -EINVAL; + goto out; + } + + err = ni_load_mi(ni, le, &mi); + if (err) + goto out; + + attr = mi_find_attr(mi, NULL, type, name, name_len, &le->id); + if (!attr) { + err = -EINVAL; + goto out; + } + goto next_le_1; + } + +ok: + if (new_valid) { + __le64 valid = cpu_to_le64(min(*new_valid, new_size)); + + if (attr_b->nres.valid_size != valid) { + attr_b->nres.valid_size = valid; + mi_b->dirty = true; + } + } + +out: + if (!err && attr_b && ret) + *ret = attr_b; + + /* update inode_set_bytes*/ + if (!err && attr_b && attr_b->non_res && + ((type == ATTR_DATA && !name_len) || + (type == ATTR_ALLOC && name == I30_NAME))) { + bool dirty = false; + + if (ni->vfs_inode.i_size != new_size) { + ni->vfs_inode.i_size = new_size; + dirty = true; + } + + new_alloc = le64_to_cpu(attr_b->nres.alloc_size); + if (inode_get_bytes(&ni->vfs_inode) != new_alloc) { + inode_set_bytes(&ni->vfs_inode, new_alloc); + dirty = true; + } + + if (dirty) { + ni->ni_flags |= NI_FLAG_UPDATE_PARENT; + mark_inode_dirty(&ni->vfs_inode); + } + } + + return err; +} + +int attr_data_get_block(struct ntfs_inode *ni, CLST vcn, CLST clen, CLST *lcn, + CLST *len, bool *new) +{ + int err = 0; + struct runs_tree *run = &ni->file.run; + struct ntfs_sb_info *sbi; + u8 cluster_bits; + struct ATTRIB *attr, *attr_b; + struct ATTR_LIST_ENTRY *le, *le_b; + struct mft_inode *mi, *mi_b; + CLST hint, svcn, to_alloc, evcn1, new_evcn1, next_svcn, asize; + u64 new_size, total_size; + u32 clst_per_frame; + bool ok; + + if (new) + *new = false; + + down_read(&ni->file.run_lock); + ok = run_lookup_entry(run, vcn, lcn, len, NULL); + up_read(&ni->file.run_lock); + + if (ok && (*lcn != SPARSE_LCN || !new)) { + /* normal way */ + return 0; + } + + if (!clen) + clen = 1; + + if (ok && clen > *len) + clen = *len; + + sbi = ni->mi.sbi; + cluster_bits = sbi->cluster_bits; + new_size = ((u64)vcn + clen) << cluster_bits; + + ni_lock(ni); + down_write(&ni->file.run_lock); + +again: + le_b = NULL; + attr_b = ni_find_attr(ni, NULL, &le_b, ATTR_DATA, NULL, 0, NULL, &mi_b); + if (!attr_b) { + err = -ENOENT; + goto out; + } + + if (!attr_b->non_res) { + if (!new) { + *lcn = RESIDENT_LCN; + goto out; + } + + err = attr_set_size_res(ni, attr_b, le_b, mi_b, new_size, run, + &attr_b); + if (err) + goto out; + + if (!attr_b->non_res) { + /* Resident attribute still resident */ + *lcn = RESIDENT_LCN; + goto out; + } + + /* Resident attribute becomes non resident */ + goto again; + } + + asize = attr_b->nres.alloc_size >> sbi->cluster_bits; + if (vcn >= asize) { + err = -EINVAL; + goto out; + } + + clst_per_frame = 1u << attr_b->nres.c_unit; + to_alloc = (clen + clst_per_frame - 1) & ~(clst_per_frame - 1); + + if (vcn + to_alloc > asize) + to_alloc = asize - vcn; + + svcn = le64_to_cpu(attr_b->nres.svcn); + evcn1 = le64_to_cpu(attr_b->nres.evcn) + 1; + + attr = attr_b; + le = le_b; + mi = mi_b; + + if (le_b && (vcn < svcn || evcn1 <= vcn)) { + attr = ni_find_attr(ni, attr_b, &le, ATTR_DATA, NULL, 0, &vcn, + &mi); + if (!attr) { + err = -EINVAL; + goto out; + } + svcn = le64_to_cpu(attr->nres.svcn); + evcn1 = le64_to_cpu(attr->nres.evcn) + 1; + } + + err = attr_load_runs(attr, ni, run); + if (err) + goto out; + + if (!ok) { + ok = run_lookup_entry(run, vcn, lcn, len, NULL); + if (ok && (*lcn != SPARSE_LCN || !new)) { + /* normal way */ + err = 0; + goto out; + } + + if (!ok && !new) { + *len = 0; + err = 0; + goto out; + } + + if (ok && clen > *len) { + clen = *len; + new_size = ((u64)vcn + clen) << cluster_bits; + to_alloc = (clen + clst_per_frame - 1) & + ~(clst_per_frame - 1); + } + } + + if (!is_attr_ext(attr_b)) { + err = -EINVAL; + goto out; + } + + /* Get the last lcn to allocate from */ + hint = 0; + + if (vcn > evcn1) { + if (!run_add_entry(run, evcn1, SPARSE_LCN, vcn - evcn1)) { + err = -ENOMEM; + goto out; + } + } else if (vcn && !run_lookup_entry(run, vcn - 1, &hint, NULL, NULL)) { + hint = -1; + } + + err = attr_allocate_clusters( + sbi, run, vcn, hint + 1, to_alloc, NULL, 0, len, + (sbi->record_size - le32_to_cpu(mi->mrec->used) + 8) / 3 + 1, + lcn); + if (err) + goto out; + *new = true; + + new_evcn1 = vcn + *len; + if (new_evcn1 < evcn1) + new_evcn1 = evcn1; + + total_size = le64_to_cpu(attr_b->nres.total_size) + + ((u64)*len << cluster_bits); + +repack: + + err = mi_pack_runs(mi, attr, run, new_evcn1 - svcn); + if (err < 0) + goto out; + + attr_b->nres.total_size = cpu_to_le64(total_size); + inode_set_bytes(&ni->vfs_inode, total_size); + + mi_b->dirty = true; + ni->ni_flags |= NI_FLAG_UPDATE_PARENT; + mark_inode_dirty(&ni->vfs_inode); + + next_svcn = le64_to_cpu(attr->nres.evcn) + 1; + if (next_svcn >= evcn1) { + /* Normal way. update attribute and exit */ + goto out; + } + + if (!ni->attr_list.le) { + err = ni_create_attr_list(ni); + if (err) + goto out; + /* layout of records is changed */ + le_b = NULL; + attr_b = ni_find_attr(ni, NULL, &le_b, ATTR_DATA, NULL, 0, NULL, + &mi_b); + if (!attr_b) { + err = -ENOENT; + goto out; + } + + attr = attr_b; + le = le_b; + mi = mi_b; + goto repack; + } + + /* Estimate next attribute */ + attr = ni_find_attr(ni, attr, &le, ATTR_DATA, NULL, 0, &evcn1, &mi); + + if (attr && le32_to_cpu(mi->mrec->used) + 8 <= sbi->record_size) { + svcn = next_svcn; + evcn1 = le64_to_cpu(attr->nres.evcn) + 1; + + err = attr_load_runs(attr, ni, run); + if (err) + goto out; + + attr->nres.svcn = cpu_to_le64(svcn); + err = mi_pack_runs(mi, attr, run, evcn1 - svcn); + if (err < 0) + goto out; + + le->vcn = cpu_to_le64(svcn); + ni->attr_list.dirty = true; + + mi->dirty = true; + + next_svcn = le64_to_cpu(attr->nres.evcn) + 1; + + if (next_svcn >= evcn1) { + /* Normal way. update attribute and exit */ + goto out; + } + } + + err = ni_insert_nonresident(ni, ATTR_DATA, NULL, 0, run, next_svcn, + evcn1 - next_svcn, attr_b->flags, &attr, + &mi); + if (err) + goto out; + + run_truncate_head(run, vcn); + +out: + up_write(&ni->file.run_lock); + ni_unlock(ni); + + return err; +} + +/* + * attr_load_runs_vcn + * + * load runs with vcn + */ +int attr_load_runs_vcn(struct ntfs_inode *ni, enum ATTR_TYPE type, + const __le16 *name, u8 name_len, struct runs_tree *run, + CLST vcn) +{ + struct ATTRIB *attr; + int err; + CLST svcn, evcn; + u16 ro; + + attr = ni_find_attr(ni, NULL, NULL, type, name, name_len, &vcn, NULL); + if (!attr) + return -ENOENT; + + svcn = le64_to_cpu(attr->nres.svcn); + evcn = le64_to_cpu(attr->nres.evcn); + + if (evcn < vcn || vcn < svcn) + return -EINVAL; + + ro = le16_to_cpu(attr->nres.run_off); + err = run_unpack_ex(run, ni->mi.sbi, ni->mi.rno, svcn, evcn, + Add2Ptr(attr, ro), le32_to_cpu(attr->size) - ro); + if (err < 0) + return err; + return 0; +} + +/* + * attr_is_frame_compressed + * + * This function is used to detect compressed frame + */ +int attr_is_frame_compressed(struct ntfs_inode *ni, struct ATTRIB *attr, + CLST frame, CLST *clst_data, bool *is_compr) +{ + int err; + u32 clst_frame; + CLST len, lcn, vcn, alen, slen, vcn1; + size_t idx; + struct runs_tree *run; + + *clst_data = 0; + *is_compr = false; + + if (!is_attr_compressed(attr)) + return 0; + + if (!attr->non_res) + return 0; + + clst_frame = 1u << attr->nres.c_unit; + vcn = frame * clst_frame; + run = &ni->file.run; + + if (!run_lookup_entry(run, vcn, &lcn, &len, &idx)) { + err = attr_load_runs_vcn(ni, attr->type, attr_name(attr), + attr->name_len, run, vcn); + if (err) + return err; + + if (!run_lookup_entry(run, vcn, &lcn, &len, &idx)) + return -ENOENT; + } + + if (lcn == SPARSE_LCN) { + /* The frame is sparsed if "clst_frame" clusters are sparsed */ + *is_compr = true; + return 0; + } + + if (len >= clst_frame) { + /* + * The frame is not compressed 'cause + * it does not contain any sparse clusters + */ + *clst_data = clst_frame; + return 0; + } + + alen = bytes_to_cluster(ni->mi.sbi, le64_to_cpu(attr->nres.alloc_size)); + slen = 0; + *clst_data = len; + + /* + * The frame is compressed if *clst_data + slen >= clst_frame + * Check next fragments + */ + while ((vcn += len) < alen) { + vcn1 = vcn; + + if (!run_get_entry(run, ++idx, &vcn, &lcn, &len) || + vcn1 != vcn) { + err = attr_load_runs_vcn(ni, attr->type, + attr_name(attr), + attr->name_len, run, vcn1); + if (err) + return err; + vcn = vcn1; + + if (!run_lookup_entry(run, vcn, &lcn, &len, &idx)) + return -ENOENT; + } + + if (lcn == SPARSE_LCN) { + slen += len; + } else { + if (slen) { + /* + * data_clusters + sparse_clusters = + * not enough for frame + */ + return -EINVAL; + } + *clst_data += len; + } + + if (*clst_data + slen >= clst_frame) { + if (!slen) { + /* + * There is no sparsed clusters in this frame + * So it is not compressed + */ + *clst_data = clst_frame; + } else { + *is_compr = *clst_data < clst_frame; + } + break; + } + } + + return 0; +} + +/* + * attr_allocate_frame + * + * allocate/free clusters for 'frame' + */ +int attr_allocate_frame(struct ntfs_inode *ni, CLST frame, size_t compr_size, + u64 new_valid) +{ + int err = 0; + struct runs_tree *run = &ni->file.run; + struct ntfs_sb_info *sbi = ni->mi.sbi; + struct ATTRIB *attr, *attr_b; + struct ATTR_LIST_ENTRY *le, *le_b; + struct mft_inode *mi, *mi_b; + CLST svcn, evcn1, next_svcn, lcn, len; + CLST vcn, clst_data; + u64 total_size, valid_size, data_size; + bool is_compr; + + le_b = NULL; + attr_b = ni_find_attr(ni, NULL, &le_b, ATTR_DATA, NULL, 0, NULL, &mi_b); + if (!attr_b) + return -ENOENT; + + if (!is_attr_ext(attr_b)) + return -EINVAL; + + vcn = frame << NTFS_LZNT_CUNIT; + total_size = le64_to_cpu(attr_b->nres.total_size); + + svcn = le64_to_cpu(attr_b->nres.svcn); + evcn1 = le64_to_cpu(attr_b->nres.evcn) + 1; + data_size = le64_to_cpu(attr_b->nres.data_size); + + if (svcn <= vcn && vcn < evcn1) { + attr = attr_b; + le = le_b; + mi = mi_b; + } else if (!le_b) { + err = -EINVAL; + goto out; + } else { + le = le_b; + attr = ni_find_attr(ni, attr_b, &le, ATTR_DATA, NULL, 0, &vcn, + &mi); + if (!attr) { + err = -EINVAL; + goto out; + } + svcn = le64_to_cpu(attr->nres.svcn); + evcn1 = le64_to_cpu(attr->nres.evcn) + 1; + } + + err = attr_load_runs(attr, ni, run); + if (err) + goto out; + + err = attr_is_frame_compressed(ni, attr_b, frame, &clst_data, + &is_compr); + if (err) + goto out; + + total_size -= (u64)clst_data << sbi->cluster_bits; + + len = bytes_to_cluster(sbi, compr_size); + + if (len == clst_data) + goto out; + + if (len < clst_data) { + err = run_deallocate_ex(sbi, run, vcn + len, clst_data - len, + NULL, true); + if (err) + goto out; + + if (!run_add_entry(run, vcn + len, SPARSE_LCN, + clst_data - len)) { + err = -ENOMEM; + goto out; + } + } else { + CLST alen, hint; + /* Get the last lcn to allocate from */ + if (vcn + clst_data && + !run_lookup_entry(run, vcn + clst_data - 1, &hint, NULL, + NULL)) { + hint = -1; + } + + err = attr_allocate_clusters(sbi, run, vcn + clst_data, + hint + 1, len - clst_data, NULL, 0, + &alen, 0, &lcn); + if (err) + goto out; + } + + total_size += (u64)len << sbi->cluster_bits; + +repack: + err = mi_pack_runs(mi, attr, run, evcn1 - svcn); + if (err < 0) + goto out; + + attr_b->nres.total_size = cpu_to_le64(total_size); + inode_set_bytes(&ni->vfs_inode, total_size); + + mi_b->dirty = true; + mark_inode_dirty(&ni->vfs_inode); + + next_svcn = le64_to_cpu(attr->nres.evcn) + 1; + + if (next_svcn >= evcn1) { + /* Normal way. update attribute and exit */ + goto out; + } + + if (!ni->attr_list.size) { + err = ni_create_attr_list(ni); + if (err) + goto out; + /* layout of records is changed */ + le_b = NULL; + attr_b = ni_find_attr(ni, NULL, &le_b, ATTR_DATA, NULL, 0, NULL, + &mi_b); + if (!attr_b) { + err = -ENOENT; + goto out; + } + + attr = attr_b; + le = le_b; + mi = mi_b; + goto repack; + } + + /* Estimate next attribute */ + attr = ni_find_attr(ni, attr, &le, ATTR_DATA, NULL, 0, &evcn1, &mi); + + if (attr && le32_to_cpu(mi->mrec->used) + 8 <= sbi->record_size) { + svcn = next_svcn; + evcn1 = le64_to_cpu(attr->nres.evcn) + 1; + + err = attr_load_runs(attr, ni, run); + if (err) + goto out; + + attr->nres.svcn = cpu_to_le64(svcn); + err = mi_pack_runs(mi, attr, run, evcn1 - svcn); + if (err < 0) + goto out; + + le->vcn = cpu_to_le64(svcn); + ni->attr_list.dirty = true; + mi->dirty = true; + + next_svcn = le64_to_cpu(attr->nres.evcn) + 1; + + if (next_svcn >= evcn1) { + /* Normal way. update attribute and exit */ + goto out; + } + } + + err = ni_insert_nonresident(ni, ATTR_DATA, NULL, 0, run, next_svcn, + evcn1 - next_svcn, attr_b->flags, &attr, + &mi); + if (err) + goto out; + + run_truncate_head(run, vcn); + +out: + if (new_valid > data_size) + new_valid = data_size; + + valid_size = le64_to_cpu(attr_b->nres.valid_size); + if (new_valid != valid_size) { + attr_b->nres.valid_size = cpu_to_le64(valid_size); + mi_b->dirty = true; + } + + return err; +} diff --git a/fs/ntfs3/attrlist.c b/fs/ntfs3/attrlist.c new file mode 100644 index 000000000000..3739572a4eca --- /dev/null +++ b/fs/ntfs3/attrlist.c @@ -0,0 +1,462 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * linux/fs/ntfs3/attrib.c + * + * Copyright (C) 2019-2020 Paragon Software GmbH, All rights reserved. + * + */ + +#include +#include +#include +#include +#include + +#include "debug.h" +#include "ntfs.h" +#include "ntfs_fs.h" + +/* Returns true if le is valid */ +static inline bool al_is_valid_le(const struct ntfs_inode *ni, + struct ATTR_LIST_ENTRY *le) +{ + if (!le || !ni->attr_list.le || !ni->attr_list.size) + return false; + + return PtrOffset(ni->attr_list.le, le) + le16_to_cpu(le->size) <= + ni->attr_list.size; +} + +void al_destroy(struct ntfs_inode *ni) +{ + run_close(&ni->attr_list.run); + ntfs_free(ni->attr_list.le); + ni->attr_list.le = NULL; + ni->attr_list.size = 0; + ni->attr_list.dirty = false; +} + +/* + * ntfs_load_attr_list + * + * This method makes sure that the ATTRIB list, if present, + * has been properly set up. + */ +int ntfs_load_attr_list(struct ntfs_inode *ni, struct ATTRIB *attr) +{ + int err; + size_t lsize; + void *le = NULL; + + if (ni->attr_list.size) + return 0; + + if (!attr->non_res) { + lsize = le32_to_cpu(attr->res.data_size); + le = ntfs_alloc(al_aligned(lsize), 0); + if (!le) { + err = -ENOMEM; + goto out; + } + memcpy(le, resident_data(attr), lsize); + } else if (attr->nres.svcn) { + err = -EINVAL; + goto out; + } else { + u16 run_off = le16_to_cpu(attr->nres.run_off); + + lsize = le64_to_cpu(attr->nres.data_size); + + run_init(&ni->attr_list.run); + + err = run_unpack_ex(&ni->attr_list.run, ni->mi.sbi, ni->mi.rno, + 0, le64_to_cpu(attr->nres.evcn), + Add2Ptr(attr, run_off), + le32_to_cpu(attr->size) - run_off); + if (err < 0) + goto out; + + le = ntfs_alloc(al_aligned(lsize), 0); + if (!le) { + err = -ENOMEM; + goto out; + } + + err = ntfs_read_run_nb(ni->mi.sbi, &ni->attr_list.run, 0, le, + lsize, NULL); + if (err) + goto out; + } + + ni->attr_list.size = lsize; + ni->attr_list.le = le; + + return 0; + +out: + ni->attr_list.le = le; + al_destroy(ni); + + return err; +} + +/* + * al_enumerate + * + * Returns the next list le + * if le is NULL then returns the first le + */ +struct ATTR_LIST_ENTRY *al_enumerate(struct ntfs_inode *ni, + struct ATTR_LIST_ENTRY *le) +{ + size_t off; + u16 sz; + + if (!le) { + le = ni->attr_list.le; + } else { + sz = le16_to_cpu(le->size); + if (sz < sizeof(struct ATTR_LIST_ENTRY)) { + /* Impossible 'cause we should not return such le */ + return NULL; + } + le = Add2Ptr(le, sz); + } + + /* Check boundary */ + off = PtrOffset(ni->attr_list.le, le); + if (off + sizeof(struct ATTR_LIST_ENTRY) > ni->attr_list.size) { + // The regular end of list + return NULL; + } + + sz = le16_to_cpu(le->size); + + /* Check le for errors */ + if (sz < sizeof(struct ATTR_LIST_ENTRY) || + off + sz > ni->attr_list.size || + sz < le->name_off + le->name_len * sizeof(short)) { + return NULL; + } + + return le; +} + +/* + * al_find_le + * + * finds the first le in the list which matches type, name and vcn + * Returns NULL if not found + */ +struct ATTR_LIST_ENTRY *al_find_le(struct ntfs_inode *ni, + struct ATTR_LIST_ENTRY *le, + const struct ATTRIB *attr) +{ + CLST svcn = attr_svcn(attr); + + return al_find_ex(ni, le, attr->type, attr_name(attr), attr->name_len, + &svcn); +} + +/* + * al_find_ex + * + * finds the first le in the list which matches type, name and vcn + * Returns NULL if not found + */ +struct ATTR_LIST_ENTRY *al_find_ex(struct ntfs_inode *ni, + struct ATTR_LIST_ENTRY *le, + enum ATTR_TYPE type, const __le16 *name, + u8 name_len, const CLST *vcn) +{ + struct ATTR_LIST_ENTRY *ret = NULL; + u32 type_in = le32_to_cpu(type); + + while ((le = al_enumerate(ni, le))) { + u64 le_vcn; + int diff; + + /* List entries are sorted by type, name and vcn */ + diff = le32_to_cpu(le->type) - type_in; + if (diff < 0) + continue; + + if (diff > 0) + return ret; + + if (le->name_len != name_len) + continue; + + if (name_len && + memcmp(le_name(le), name, name_len * sizeof(short))) + continue; + + if (!vcn) + return le; + + le_vcn = le64_to_cpu(le->vcn); + if (*vcn == le_vcn) + return le; + + if (*vcn < le_vcn) + return ret; + + ret = le; + } + + return ret; +} + +/* + * al_find_le_to_insert + * + * finds the first list entry which matches type, name and vcn + * Returns NULL if not found + */ +static struct ATTR_LIST_ENTRY * +al_find_le_to_insert(struct ntfs_inode *ni, enum ATTR_TYPE type, + const __le16 *name, u8 name_len, const CLST *vcn) +{ + struct ATTR_LIST_ENTRY *le = NULL, *prev; + u32 type_in = le32_to_cpu(type); + int diff; + + /* List entries are sorted by type, name, vcn */ +next: + le = al_enumerate(ni, prev = le); + if (!le) + goto out; + diff = le32_to_cpu(le->type) - type_in; + if (diff < 0) + goto next; + if (diff > 0) + goto out; + + if (ntfs_cmp_names(name, name_len, le_name(le), le->name_len, NULL) > 0) + goto next; + + if (!vcn || *vcn > le64_to_cpu(le->vcn)) + goto next; + +out: + if (!le) + le = prev ? Add2Ptr(prev, le16_to_cpu(prev->size)) : + ni->attr_list.le; + + return le; +} + +/* + * al_add_le + * + * adds an "attribute list entry" to the list. + */ +int al_add_le(struct ntfs_inode *ni, enum ATTR_TYPE type, const __le16 *name, + u8 name_len, CLST svcn, __le16 id, const struct MFT_REF *ref, + struct ATTR_LIST_ENTRY **new_le) +{ + int err; + struct ATTRIB *attr; + struct ATTR_LIST_ENTRY *le; + size_t off; + u16 sz; + size_t asize, new_asize; + u64 new_size; + typeof(ni->attr_list) *al = &ni->attr_list; + + /* + * Compute the size of the new le and the new length of the + * list with al le added. + */ + sz = le_size(name_len); + new_size = al->size + sz; + asize = al_aligned(al->size); + new_asize = al_aligned(new_size); + + /* Scan forward to the point at which the new le should be inserted. */ + le = al_find_le_to_insert(ni, type, name, name_len, &svcn); + off = PtrOffset(al->le, le); + + if (new_size > asize) { + void *ptr = ntfs_alloc(new_asize, 0); + + if (!ptr) + return -ENOMEM; + + memcpy(ptr, al->le, off); + memcpy(Add2Ptr(ptr, off + sz), le, al->size - off); + le = Add2Ptr(ptr, off); + ntfs_free(al->le); + al->le = ptr; + } else { + memmove(Add2Ptr(le, sz), le, al->size - off); + } + + al->size = new_size; + + le->type = type; + le->size = cpu_to_le16(sz); + le->name_len = name_len; + le->name_off = offsetof(struct ATTR_LIST_ENTRY, name); + le->vcn = cpu_to_le64(svcn); + le->ref = *ref; + le->id = id; + memcpy(le->name, name, sizeof(short) * name_len); + + al->dirty = true; + + err = attr_set_size(ni, ATTR_LIST, NULL, 0, &al->run, new_size, + &new_size, true, &attr); + if (err) + return err; + + if (attr && attr->non_res) { + err = ntfs_sb_write_run(ni->mi.sbi, &al->run, 0, al->le, + al->size); + if (err) + return err; + } + + al->dirty = false; + *new_le = le; + + return 0; +} + +/* + * al_remove_le + * + * removes 'le' from attribute list + */ +bool al_remove_le(struct ntfs_inode *ni, struct ATTR_LIST_ENTRY *le) +{ + u16 size; + size_t off; + typeof(ni->attr_list) *al = &ni->attr_list; + + if (!al_is_valid_le(ni, le)) + return false; + + /* Save on stack the size of le */ + size = le16_to_cpu(le->size); + off = PtrOffset(al->le, le); + + memmove(le, Add2Ptr(le, size), al->size - (off + size)); + + al->size -= size; + al->dirty = true; + + return true; +} + +/* + * al_delete_le + * + * deletes from the list the first le which matches its parameters. + */ +bool al_delete_le(struct ntfs_inode *ni, enum ATTR_TYPE type, CLST vcn, + const __le16 *name, size_t name_len, + const struct MFT_REF *ref) +{ + u16 size; + struct ATTR_LIST_ENTRY *le; + size_t off; + typeof(ni->attr_list) *al = &ni->attr_list; + + /* Scan forward to the first le that matches the input */ + le = al_find_ex(ni, NULL, type, name, name_len, &vcn); + if (!le) + return false; + + off = PtrOffset(al->le, le); + + if (!ref) + goto del; + + /* + * The caller specified a segment reference, so we have to + * scan through the matching entries until we find that segment + * reference or we run of matching entries. + */ +next: + if (off + sizeof(struct ATTR_LIST_ENTRY) > al->size) + goto del; + if (le->type != type) + goto del; + if (le->name_len != name_len) + goto del; + if (name_len && + memcmp(name, Add2Ptr(le, le->name_off), name_len * sizeof(short))) + goto del; + if (le64_to_cpu(le->vcn) != vcn) + goto del; + if (!memcmp(ref, &le->ref, sizeof(*ref))) + goto del; + + off += le16_to_cpu(le->size); + le = Add2Ptr(al->le, off); + goto next; + +del: + /* + * If we've gone off the end of the list, or if the type, name, + * and vcn don't match, then we don't have any matching records. + */ + if (off >= al->size) + return false; + if (le->type != type) + return false; + if (le->name_len != name_len) + return false; + if (name_len && + memcmp(name, Add2Ptr(le, le->name_off), name_len * sizeof(short))) + return false; + if (le64_to_cpu(le->vcn) != vcn) + return false; + + /* Save on stack the size of le */ + size = le16_to_cpu(le->size); + /* Delete the le. */ + memmove(le, Add2Ptr(le, size), al->size - (off + size)); + + al->size -= size; + al->dirty = true; + return true; +} + +/* + * al_update + * + * + */ +int al_update(struct ntfs_inode *ni) +{ + int err; + struct ntfs_sb_info *sbi = ni->mi.sbi; + struct ATTRIB *attr; + typeof(ni->attr_list) *al = &ni->attr_list; + + if (!al->dirty) + return 0; + + err = attr_set_size(ni, ATTR_LIST, NULL, 0, &al->run, al->size, NULL, + false, &attr); + if (err) + goto out; + + if (!attr->non_res) + memcpy(resident_data(attr), al->le, al->size); + else { + err = ntfs_sb_write_run(sbi, &al->run, 0, al->le, al->size); + if (err) + goto out; + + attr->nres.valid_size = attr->nres.data_size; + } + + ni->mi.dirty = true; + al->dirty = false; + +out: + return err; +} diff --git a/fs/ntfs3/xattr.c b/fs/ntfs3/xattr.c new file mode 100644 index 000000000000..086653748a5a --- /dev/null +++ b/fs/ntfs3/xattr.c @@ -0,0 +1,1060 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * linux/fs/ntfs3/xattr.c + * + * Copyright (C) 2019-2020 Paragon Software GmbH, All rights reserved. + * + */ + +#include +#include +#include +#include +#include +#include +#include + +#include "debug.h" +#include "ntfs.h" +#include "ntfs_fs.h" + +#define SYSTEM_DOS_ATTRIB "system.dos_attrib" +#define SYSTEM_NTFS_ATTRIB "system.ntfs_attrib" +#define SYSTEM_NTFS_SECURITY "system.ntfs_security" +#define USER_DOSATTRIB "user.DOSATTRIB" + +static inline size_t unpacked_ea_size(const struct EA_FULL *ea) +{ + return !ea->size ? DwordAlign(offsetof(struct EA_FULL, name) + 1 + + ea->name_len + le16_to_cpu(ea->elength)) : + le32_to_cpu(ea->size); +} + +static inline size_t packed_ea_size(const struct EA_FULL *ea) +{ + return offsetof(struct EA_FULL, name) + 1 - + offsetof(struct EA_FULL, flags) + ea->name_len + + le16_to_cpu(ea->elength); +} + +/* + * find_ea + * + * assume there is at least one xattr in the list + */ +static inline bool find_ea(const struct EA_FULL *ea_all, u32 bytes, + const char *name, u8 name_len, u32 *off) +{ + *off = 0; + + if (!ea_all || !bytes) + return false; + + for (;;) { + const struct EA_FULL *ea = Add2Ptr(ea_all, *off); + u32 next_off = *off + unpacked_ea_size(ea); + + if (next_off > bytes) + return false; + + if (ea->name_len == name_len && + !memcmp(ea->name, name, name_len)) + return true; + + *off = next_off; + if (next_off >= bytes) + return false; + } +} + +/* + * ntfs_read_ea + * + * reads all extended attributes + * ea - new allocated memory + * info - pointer into resident data + */ +static int ntfs_read_ea(struct ntfs_inode *ni, struct EA_FULL **ea, + size_t add_bytes, const struct EA_INFO **info) +{ + int err; + struct ATTR_LIST_ENTRY *le = NULL; + struct ATTRIB *attr_info, *attr_ea; + void *ea_p; + u32 size; + + static_assert(le32_to_cpu(ATTR_EA_INFO) < le32_to_cpu(ATTR_EA)); + + *ea = NULL; + *info = NULL; + + attr_info = + ni_find_attr(ni, NULL, &le, ATTR_EA_INFO, NULL, 0, NULL, NULL); + attr_ea = + ni_find_attr(ni, attr_info, &le, ATTR_EA, NULL, 0, NULL, NULL); + + if (!attr_ea || !attr_info) + return 0; + + *info = resident_data_ex(attr_info, sizeof(struct EA_INFO)); + if (!*info) + return -EINVAL; + + /* Check Ea limit */ + size = le32_to_cpu((*info)->size); + if (size > MAX_EA_DATA_SIZE || size + add_bytes > MAX_EA_DATA_SIZE) + return -EINVAL; + + /* Allocate memory for packed Ea */ + ea_p = ntfs_alloc(size + add_bytes, 0); + if (!ea_p) + return -ENOMEM; + + if (attr_ea->non_res) { + struct runs_tree run; + + run_init(&run); + + err = attr_load_runs(attr_ea, ni, &run); + if (!err) + err = ntfs_read_run_nb(ni->mi.sbi, &run, 0, ea_p, size, + NULL); + run_close(&run); + + if (err) + goto out; + } else { + void *p = resident_data_ex(attr_ea, size); + + if (!p) { + err = -EINVAL; + goto out; + } + memcpy(ea_p, p, size); + } + + memset(Add2Ptr(ea_p, size), 0, add_bytes); + *ea = ea_p; + return 0; + +out: + ntfs_free(ea_p); + *ea = NULL; + return err; +} + +/* + * ntfs_listxattr_hlp + * + * copy a list of xattrs names into the buffer + * provided, or compute the buffer size required + */ +static int ntfs_listxattr_hlp(struct ntfs_inode *ni, char *buffer, + size_t bytes_per_buffer, size_t *bytes) +{ + const struct EA_INFO *info; + struct EA_FULL *ea_all = NULL; + const struct EA_FULL *ea; + u32 off, size; + int err; + + *bytes = 0; + + err = ntfs_read_ea(ni, &ea_all, 0, &info); + if (err) + return err; + + if (!info || !ea_all) + return 0; + + size = le32_to_cpu(info->size); + + /* Enumerate all xattrs */ + for (off = 0; off < size; off += unpacked_ea_size(ea)) { + ea = Add2Ptr(ea_all, off); + + if (buffer) { + if (*bytes + ea->name_len + 1 > bytes_per_buffer) { + err = -ERANGE; + goto out; + } + + memcpy(buffer + *bytes, ea->name, ea->name_len); + buffer[*bytes + ea->name_len] = 0; + } + + *bytes += ea->name_len + 1; + } + +out: + ntfs_free(ea_all); + return err; +} + +/* + * ntfs_get_ea + * + * reads xattr + */ +static int ntfs_get_ea(struct ntfs_inode *ni, const char *name, size_t name_len, + void *buffer, size_t bytes_per_buffer, u32 *len) +{ + const struct EA_INFO *info; + struct EA_FULL *ea_all = NULL; + const struct EA_FULL *ea; + u32 off; + int err; + + *len = 0; + + if (name_len > 255) { + err = -ENAMETOOLONG; + goto out; + } + + err = ntfs_read_ea(ni, &ea_all, 0, &info); + if (err) + goto out; + + if (!info) + goto out; + + /* Enumerate all xattrs */ + if (!find_ea(ea_all, le32_to_cpu(info->size), name, name_len, &off)) { + err = -ENODATA; + goto out; + } + ea = Add2Ptr(ea_all, off); + + *len = le16_to_cpu(ea->elength); + if (!buffer) { + err = 0; + goto out; + } + + if (*len > bytes_per_buffer) { + err = -ERANGE; + goto out; + } + memcpy(buffer, ea->name + ea->name_len + 1, *len); + err = 0; + +out: + ntfs_free(ea_all); + + return err; +} + +static noinline int ntfs_getxattr_hlp(struct inode *inode, const char *name, + void *value, size_t size, + size_t *required) +{ + struct ntfs_inode *ni = ntfs_i(inode); + int err; + u32 len; + + if (!(ni->ni_flags & NI_FLAG_EA)) + return -ENODATA; + + if (!required) + ni_lock(ni); + + err = ntfs_get_ea(ni, name, strlen(name), value, size, &len); + if (!err) + err = len; + else if (-ERANGE == err && required) + *required = len; + + if (!required) + ni_unlock(ni); + + return err; +} + +static noinline int ntfs_set_ea(struct inode *inode, const char *name, + const void *value, size_t val_size, int flags, + int locked) +{ + struct ntfs_inode *ni = ntfs_i(inode); + struct ntfs_sb_info *sbi = ni->mi.sbi; + int err; + struct EA_INFO ea_info; + const struct EA_INFO *info; + struct EA_FULL *new_ea; + struct EA_FULL *ea_all = NULL; + size_t name_len, add; + u32 off, size; + __le16 size_pack; + struct ATTRIB *attr; + struct ATTR_LIST_ENTRY *le; + struct mft_inode *mi; + struct runs_tree ea_run; + u64 new_sz; + void *p; + + if (!locked) + ni_lock(ni); + + run_init(&ea_run); + name_len = strlen(name); + + if (name_len > 255) { + err = -ENAMETOOLONG; + goto out; + } + + add = DwordAlign(offsetof(struct EA_FULL, name) + 1 + name_len + + val_size); + + err = ntfs_read_ea(ni, &ea_all, add, &info); + if (err) + goto out; + + if (!info) { + memset(&ea_info, 0, sizeof(ea_info)); + size = 0; + size_pack = 0; + } else { + memcpy(&ea_info, info, sizeof(ea_info)); + size = le32_to_cpu(ea_info.size); + size_pack = ea_info.size_pack; + } + + if (info && find_ea(ea_all, size, name, name_len, &off)) { + struct EA_FULL *ea; + size_t ea_sz; + + if (flags & XATTR_CREATE) { + err = -EEXIST; + goto out; + } + + /* Remove current xattr */ + ea = Add2Ptr(ea_all, off); + if (ea->flags & FILE_NEED_EA) + le16_add_cpu(&ea_info.count, -1); + + ea_sz = unpacked_ea_size(ea); + + le16_add_cpu(&ea_info.size_pack, 0 - packed_ea_size(ea)); + + memmove(ea, Add2Ptr(ea, ea_sz), size - off - ea_sz); + + size -= ea_sz; + memset(Add2Ptr(ea_all, size), 0, ea_sz); + + ea_info.size = cpu_to_le32(size); + + if ((flags & XATTR_REPLACE) && !val_size) + goto update_ea; + } else { + if (flags & XATTR_REPLACE) { + err = -ENODATA; + goto out; + } + + if (!ea_all) { + ea_all = ntfs_alloc(add, 1); + if (!ea_all) { + err = -ENOMEM; + goto out; + } + } + } + + /* append new xattr */ + new_ea = Add2Ptr(ea_all, size); + new_ea->size = cpu_to_le32(add); + new_ea->flags = 0; + new_ea->name_len = name_len; + new_ea->elength = cpu_to_le16(val_size); + memcpy(new_ea->name, name, name_len); + new_ea->name[name_len] = 0; + memcpy(new_ea->name + name_len + 1, value, val_size); + + le16_add_cpu(&ea_info.size_pack, packed_ea_size(new_ea)); + size += add; + ea_info.size = cpu_to_le32(size); + +update_ea: + + if (!info) { + /* Create xattr */ + if (!size) { + err = 0; + goto out; + } + + err = ni_insert_resident(ni, sizeof(struct EA_INFO), + ATTR_EA_INFO, NULL, 0, NULL, NULL); + if (err) + goto out; + + err = ni_insert_resident(ni, 0, ATTR_EA, NULL, 0, NULL, NULL); + if (err) + goto out; + } + + new_sz = size; + err = attr_set_size(ni, ATTR_EA, NULL, 0, &ea_run, new_sz, &new_sz, + false, NULL); + if (err) + goto out; + + le = NULL; + attr = ni_find_attr(ni, NULL, &le, ATTR_EA_INFO, NULL, 0, NULL, &mi); + if (!attr) { + err = -EINVAL; + goto out; + } + + if (!size) { + /* delete xattr, ATTR_EA_INFO */ + err = ni_remove_attr_le(ni, attr, le); + if (err) + goto out; + } else { + p = resident_data_ex(attr, sizeof(struct EA_INFO)); + if (!p) { + err = -EINVAL; + goto out; + } + memcpy(p, &ea_info, sizeof(struct EA_INFO)); + mi->dirty = true; + } + + le = NULL; + attr = ni_find_attr(ni, NULL, &le, ATTR_EA, NULL, 0, NULL, &mi); + if (!attr) { + err = -EINVAL; + goto out; + } + + if (!size) { + /* delete xattr, ATTR_EA */ + err = ni_remove_attr_le(ni, attr, le); + if (err) + goto out; + } else if (attr->non_res) { + err = ntfs_sb_write_run(sbi, &ea_run, 0, ea_all, size); + if (err) + goto out; + } else { + p = resident_data_ex(attr, size); + if (!p) { + err = -EINVAL; + goto out; + } + memcpy(p, ea_all, size); + mi->dirty = true; + } + + if (ea_info.size_pack != size_pack) + ni->ni_flags |= NI_FLAG_UPDATE_PARENT; + mark_inode_dirty(&ni->vfs_inode); + + /* Check if we delete the last xattr */ + if (val_size || flags != XATTR_REPLACE || + ntfs_listxattr_hlp(ni, NULL, 0, &val_size) || val_size) { + ni->ni_flags |= NI_FLAG_EA; + } else { + ni->ni_flags &= ~NI_FLAG_EA; + } + +out: + if (!locked) + ni_unlock(ni); + + run_close(&ea_run); + ntfs_free(ea_all); + + return err; +} + +static inline void ntfs_posix_acl_release(struct posix_acl *acl) +{ + if (acl && refcount_dec_and_test(&acl->a_refcount)) + kfree(acl); +} + +static struct posix_acl *ntfs_get_acl_ex(struct inode *inode, int type, + int locked) +{ + struct ntfs_inode *ni = ntfs_i(inode); + const char *name; + struct posix_acl *acl; + size_t req; + int err; + void *buf; + + buf = __getname(); + if (!buf) + return ERR_PTR(-ENOMEM); + + /* Possible values of 'type' was already checked above */ + name = type == ACL_TYPE_ACCESS ? XATTR_NAME_POSIX_ACL_ACCESS : + XATTR_NAME_POSIX_ACL_DEFAULT; + + if (!locked) + ni_lock(ni); + + err = ntfs_getxattr_hlp(inode, name, buf, PATH_MAX, &req); + + if (!locked) + ni_unlock(ni); + + /* Translate extended attribute to acl */ + if (err > 0) { + acl = posix_acl_from_xattr(&init_user_ns, buf, err); + if (!IS_ERR(acl)) + set_cached_acl(inode, type, acl); + } else { + acl = err == -ENODATA ? NULL : ERR_PTR(err); + } + + __putname(buf); + + return acl; +} + +/* + * ntfs_get_acl + * + * inode_operations::get_acl + */ +struct posix_acl *ntfs_get_acl(struct inode *inode, int type) +{ + return ntfs_get_acl_ex(inode, type, 0); +} + +static noinline int ntfs_set_acl_ex(struct inode *inode, struct posix_acl *acl, + int type, int locked) +{ + const char *name; + size_t size; + void *value = NULL; + int err = 0; + + if (S_ISLNK(inode->i_mode)) + return -EOPNOTSUPP; + + switch (type) { + case ACL_TYPE_ACCESS: + if (acl) { + umode_t mode = inode->i_mode; + + err = posix_acl_equiv_mode(acl, &mode); + if (err < 0) + return err; + + if (inode->i_mode != mode) { + inode->i_mode = mode; + mark_inode_dirty(inode); + } + + if (!err) { + /* + * acl can be exactly represented in the + * traditional file mode permission bits + */ + acl = NULL; + goto out; + } + } + name = XATTR_NAME_POSIX_ACL_ACCESS; + break; + + case ACL_TYPE_DEFAULT: + if (!S_ISDIR(inode->i_mode)) + return acl ? -EACCES : 0; + name = XATTR_NAME_POSIX_ACL_DEFAULT; + break; + + default: + return -EINVAL; + } + + if (!acl) + goto out; + + size = posix_acl_xattr_size(acl->a_count); + value = ntfs_alloc(size, 0); + if (!value) + return -ENOMEM; + + err = posix_acl_to_xattr(&init_user_ns, acl, value, size); + if (err) + goto out; + + err = ntfs_set_ea(inode, name, value, size, 0, locked); + if (err) + goto out; + + inode->i_flags &= ~S_NOSEC; + +out: + if (!err) + set_cached_acl(inode, type, acl); + + kfree(value); + + return err; +} + +/* + * ntfs_set_acl + * + * inode_operations::set_acl + */ +int ntfs_set_acl(struct inode *inode, struct posix_acl *acl, int type) +{ + return ntfs_set_acl_ex(inode, acl, type, 0); +} + +static int ntfs_xattr_get_acl(struct inode *inode, int type, void *buffer, + size_t size) +{ + struct super_block *sb = inode->i_sb; + struct posix_acl *acl; + int err; + + if (!(sb->s_flags & SB_POSIXACL)) + return -EOPNOTSUPP; + + acl = ntfs_get_acl(inode, type); + if (IS_ERR(acl)) + return PTR_ERR(acl); + + if (!acl) + return -ENODATA; + + err = posix_acl_to_xattr(&init_user_ns, acl, buffer, size); + ntfs_posix_acl_release(acl); + + return err; +} + +static int ntfs_xattr_set_acl(struct inode *inode, int type, const void *value, + size_t size) +{ + struct super_block *sb = inode->i_sb; + struct posix_acl *acl; + int err; + + if (!(sb->s_flags & SB_POSIXACL)) + return -EOPNOTSUPP; + + if (!inode_owner_or_capable(inode)) + return -EPERM; + + if (!value) + return 0; + + acl = posix_acl_from_xattr(&init_user_ns, value, size); + if (IS_ERR(acl)) + return PTR_ERR(acl); + + if (acl) { + err = posix_acl_valid(sb->s_user_ns, acl); + if (err) + goto release_and_out; + } + + err = ntfs_set_acl(inode, acl, type); + +release_and_out: + ntfs_posix_acl_release(acl); + return err; +} + +/* + * ntfs_acl_chmod + * + * helper for 'ntfs_setattr' + */ +int ntfs_acl_chmod(struct inode *inode) +{ + struct super_block *sb = inode->i_sb; + int err; + + if (!(sb->s_flags & SB_POSIXACL)) + return 0; + + if (S_ISLNK(inode->i_mode)) + return -EOPNOTSUPP; + + err = posix_acl_chmod(inode, inode->i_mode); + + return err; +} + +/* + * ntfs_permission + * + * inode_operations::permission + */ +int ntfs_permission(struct inode *inode, int mask) +{ + struct super_block *sb = inode->i_sb; + struct ntfs_sb_info *sbi = sb->s_fs_info; + int err; + + if (sbi->options.no_acs_rules) { + /* "no access rules" mode - allow all changes */ + return 0; + } + + err = generic_permission(inode, mask); + + return err; +} + +/* + * ntfs_listxattr + * + * inode_operations::listxattr + */ +ssize_t ntfs_listxattr(struct dentry *dentry, char *buffer, size_t size) +{ + struct inode *inode = d_inode(dentry); + struct ntfs_inode *ni = ntfs_i(inode); + ssize_t ret = -1; + int err; + + if (!(ni->ni_flags & NI_FLAG_EA)) { + ret = 0; + goto out; + } + + ni_lock(ni); + + err = ntfs_listxattr_hlp(ni, buffer, size, (size_t *)&ret); + + ni_unlock(ni); + + if (err) + ret = err; +out: + + return ret; +} + +static int ntfs_getxattr(const struct xattr_handler *handler, struct dentry *de, + struct inode *inode, const char *name, void *buffer, + size_t size) +{ + int err; + struct ntfs_inode *ni = ntfs_i(inode); + size_t name_len = strlen(name); + + /* Dispatch request */ + if (name_len == sizeof(SYSTEM_DOS_ATTRIB) - 1 && + !memcmp(name, SYSTEM_DOS_ATTRIB, sizeof(SYSTEM_DOS_ATTRIB))) { + /* system.dos_attrib */ + if (!buffer) { + err = sizeof(u8); + } else if (size < sizeof(u8)) { + err = -ENODATA; + } else { + err = sizeof(u8); + *(u8 *)buffer = le32_to_cpu(ni->std_fa); + } + goto out; + } + + if (name_len == sizeof(SYSTEM_NTFS_ATTRIB) - 1 && + !memcmp(name, SYSTEM_NTFS_ATTRIB, sizeof(SYSTEM_NTFS_ATTRIB))) { + /* system.ntfs_attrib */ + if (!buffer) { + err = sizeof(u32); + } else if (size < sizeof(u32)) { + err = -ENODATA; + } else { + err = sizeof(u32); + *(u32 *)buffer = le32_to_cpu(ni->std_fa); + } + goto out; + } + + if (name_len == sizeof(USER_DOSATTRIB) - 1 && + !memcmp(name, USER_DOSATTRIB, sizeof(USER_DOSATTRIB))) { + /* user.DOSATTRIB */ + if (!buffer) { + err = 5; + } else if (size < 5) { + err = -ENODATA; + } else { + err = sprintf((char *)buffer, "0x%x", + le32_to_cpu(ni->std_fa) & 0xff) + + 1; + } + goto out; + } + + if (name_len == sizeof(SYSTEM_NTFS_SECURITY) - 1 && + !memcmp(name, SYSTEM_NTFS_SECURITY, sizeof(SYSTEM_NTFS_SECURITY))) { + /* system.ntfs_security*/ + struct SECURITY_DESCRIPTOR_RELATIVE *sd = NULL; + size_t sd_size = 0; + + if (!is_ntfs3(ni->mi.sbi)) { + /* we should get nt4 security */ + err = -EINVAL; + goto out; + } else if (le32_to_cpu(ni->std_security_id) < + SECURITY_ID_FIRST) { + err = -ENOENT; + goto out; + } + + err = ntfs_get_security_by_id(ni->mi.sbi, ni->std_security_id, + &sd, &sd_size); + if (err) + goto out; + + if (!is_sd_valid(sd, sd_size)) { + ntfs_inode_warn( + inode, + "looks like you get incorrect security descriptor id=%u", + ni->std_security_id); + } + + if (!buffer) { + err = sd_size; + } else if (size < sd_size) { + err = -ENODATA; + } else { + err = sd_size; + memcpy(buffer, sd, sd_size); + } + ntfs_free(sd); + goto out; + } + + if ((name_len == sizeof(XATTR_NAME_POSIX_ACL_ACCESS) - 1 && + !memcmp(name, XATTR_NAME_POSIX_ACL_ACCESS, + sizeof(XATTR_NAME_POSIX_ACL_ACCESS))) || + (name_len == sizeof(XATTR_NAME_POSIX_ACL_DEFAULT) - 1 && + !memcmp(name, XATTR_NAME_POSIX_ACL_DEFAULT, + sizeof(XATTR_NAME_POSIX_ACL_DEFAULT)))) { + err = ntfs_xattr_get_acl( + inode, + name_len == sizeof(XATTR_NAME_POSIX_ACL_ACCESS) - 1 ? + ACL_TYPE_ACCESS : + ACL_TYPE_DEFAULT, + buffer, size); + } else { + err = ntfs_getxattr_hlp(inode, name, buffer, size, NULL); + } + +out: + return err; +} + +/* + * ntfs_setxattr + * + * inode_operations::setxattr + */ +static noinline int ntfs_setxattr(const struct xattr_handler *handler, + struct dentry *de, struct inode *inode, + const char *name, const void *value, + size_t size, int flags) +{ + int err = -EINVAL; + struct ntfs_inode *ni = ntfs_i(inode); + size_t name_len = strlen(name); + u32 attrib = 0; /* not necessary just to suppress warnings */ + __le32 new_fa; + + /* Dispatch request */ + if (name_len == sizeof(SYSTEM_DOS_ATTRIB) - 1 && + !memcmp(name, SYSTEM_DOS_ATTRIB, sizeof(SYSTEM_DOS_ATTRIB))) { + if (sizeof(u8) != size) + goto out; + attrib = *(u8 *)value; + goto set_dos_attr; + } + + if (name_len == sizeof(SYSTEM_NTFS_ATTRIB) - 1 && + !memcmp(name, SYSTEM_NTFS_ATTRIB, sizeof(SYSTEM_NTFS_ATTRIB))) { + if (sizeof(u32) != size) + goto out; + attrib = *(u32 *)value; + goto set_dos_attr; + } + + if (name_len == sizeof(USER_DOSATTRIB) - 1 && + !memcmp(name, USER_DOSATTRIB, sizeof(USER_DOSATTRIB))) { + if (size < 4 || ((char *)value)[size - 1]) + goto out; + + /* + * The input value must be string in form 0x%x with last zero + * This means that the 'size' must be 4, 5, ... + * E.g: 0x1 - 4 bytes, 0x20 - 5 bytes + */ + if (sscanf((char *)value, "0x%x", &attrib) != 1) + goto out; + +set_dos_attr: + if (!value) + goto out; + + /* + * Thanks Mark Harmstone: + * keep directory bit consistency + */ + new_fa = cpu_to_le32(attrib); + if (S_ISDIR(inode->i_mode)) + new_fa |= FILE_ATTRIBUTE_DIRECTORY; + else + new_fa &= ~FILE_ATTRIBUTE_DIRECTORY; + + if (ni->std_fa != new_fa) { + ni->std_fa = new_fa; + /* std attribute always in primary record */ + ni->mi.dirty = true; + mark_inode_dirty(inode); + } + err = 0; + + goto out; + } + + if (name_len == sizeof(SYSTEM_NTFS_SECURITY) - 1 && + !memcmp(name, SYSTEM_NTFS_SECURITY, sizeof(SYSTEM_NTFS_SECURITY))) { + /* system.ntfs_security*/ + __le32 security_id; + bool inserted; + struct ATTR_STD_INFO5 *std; + + if (!is_ntfs3(ni->mi.sbi)) { + /* + * we should replace ATTR_SECURE + * Skip this way cause it is nt4 feature + */ + err = -EINVAL; + goto out; + } + + if (!is_sd_valid(value, size)) { + err = -EINVAL; + ntfs_inode_warn( + inode, + "you try to set invalid security descriptor"); + goto out; + } + + err = ntfs_insert_security(ni->mi.sbi, value, size, + &security_id, &inserted); + if (err) + goto out; + + ni_lock(ni); + std = ni_std5(ni); + if (!std) { + err = -EINVAL; + } else if (std->security_id != security_id) { + std->security_id = ni->std_security_id = security_id; + /* std attribute always in primary record */ + ni->mi.dirty = true; + mark_inode_dirty(&ni->vfs_inode); + } + ni_unlock(ni); + goto out; + } + + if ((name_len == sizeof(XATTR_NAME_POSIX_ACL_ACCESS) - 1 && + !memcmp(name, XATTR_NAME_POSIX_ACL_ACCESS, + sizeof(XATTR_NAME_POSIX_ACL_ACCESS))) || + (name_len == sizeof(XATTR_NAME_POSIX_ACL_DEFAULT) - 1 && + !memcmp(name, XATTR_NAME_POSIX_ACL_DEFAULT, + sizeof(XATTR_NAME_POSIX_ACL_DEFAULT)))) { + err = ntfs_xattr_set_acl( + inode, + name_len == sizeof(XATTR_NAME_POSIX_ACL_ACCESS) - 1 ? + ACL_TYPE_ACCESS : + ACL_TYPE_DEFAULT, + value, size); + } else { + err = ntfs_set_ea(inode, name, value, size, flags, 0); + } + +out: + return err; +} + +/* + * Initialize the ACLs of a new inode. Called from ntfs_create_inode. + */ +int ntfs_init_acl(struct inode *inode, struct inode *dir) +{ + struct posix_acl *default_acl, *acl; + int err; + + /* + * TODO refactoring lock + * ni_lock(dir) ... -> posix_acl_create(dir,...) -> ntfs_get_acl -> ni_lock(dir) + */ + inode->i_default_acl = NULL; + + default_acl = ntfs_get_acl_ex(dir, ACL_TYPE_DEFAULT, 1); + + if (!default_acl || default_acl == ERR_PTR(-EOPNOTSUPP)) { + inode->i_mode &= ~current_umask(); + err = 0; + goto out; + } + + if (IS_ERR(default_acl)) { + err = PTR_ERR(default_acl); + goto out; + } + + acl = default_acl; + err = __posix_acl_create(&acl, GFP_NOFS, &inode->i_mode); + if (err < 0) + goto out1; + if (!err) { + posix_acl_release(acl); + acl = NULL; + } + + if (!S_ISDIR(inode->i_mode)) { + posix_acl_release(default_acl); + default_acl = NULL; + } + + if (default_acl) + err = ntfs_set_acl_ex(inode, default_acl, ACL_TYPE_DEFAULT, 1); + + if (!acl) + inode->i_acl = NULL; + else if (!err) + err = ntfs_set_acl_ex(inode, acl, ACL_TYPE_ACCESS, 1); + + posix_acl_release(acl); +out1: + posix_acl_release(default_acl); + +out: + return err; +} + +static bool ntfs_xattr_user_list(struct dentry *dentry) +{ + return 1; +} + +static const struct xattr_handler ntfs_xattr_handler = { + .prefix = "", + .get = ntfs_getxattr, + .set = ntfs_setxattr, + .list = ntfs_xattr_user_list, +}; + +const struct xattr_handler *ntfs_xattr_handlers[] = { + &ntfs_xattr_handler, + NULL, +}; From patchwork Fri Oct 9 14:22:57 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Konstantin Komarov X-Patchwork-Id: 11825955 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 863861744 for ; Fri, 9 Oct 2020 14:23:40 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 65510222BA for ; Fri, 9 Oct 2020 14:23:40 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (1024-bit key) header.d=paragon-software.com header.i=@paragon-software.com header.b="ubZgKEs9" Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S2388729AbgJIOXV (ORCPT ); Fri, 9 Oct 2020 10:23:21 -0400 Received: from relaydlg-01.paragon-software.com ([81.5.88.159]:42941 "EHLO relaydlg-01.paragon-software.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S2388664AbgJIOXN (ORCPT ); Fri, 9 Oct 2020 10:23:13 -0400 Received: from dlg2.mail.paragon-software.com (vdlg-exch-02.paragon-software.com [172.30.1.105]) by relaydlg-01.paragon-software.com (Postfix) with ESMTPS id 5F7EA82380; Fri, 9 Oct 2020 17:23:09 +0300 (MSK) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=paragon-software.com; s=mail; t=1602253389; bh=Q+KG5Z18YE2u9rcMb4sDFDVT+T/QQmZPhoMCAzYzTjI=; h=From:To:CC:Subject:Date:In-Reply-To:References; b=ubZgKEs9sl4qWgBpc665Q1lo9fuzKb0JzcOeAQki9sCJWrD9KBBSi/f1TikmsKjug VJ1LY1yW/A9thWvME/EOeqoAs+jUVHIjiVXm1qezUe4gEC+OOaVPJYIdnR+8dBZKsX nYzoRW2hl+58Nk+T0/hyMyuTxbMlpMOZpuUjynks= Received: from fsd-lkpg.ufsd.paragon-software.com (172.30.114.105) by vdlg-exch-02.paragon-software.com (172.30.1.105) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id 15.1.1847.3; Fri, 9 Oct 2020 17:23:08 +0300 From: Konstantin Komarov To: CC: , , , , , , , , , , , , Konstantin Komarov Subject: [PATCH v8 06/10] fs/ntfs3: Add compression Date: Fri, 9 Oct 2020 17:22:57 +0300 Message-ID: <20201009142301.412454-7-almaz.alexandrovich@paragon-software.com> X-Mailer: git-send-email 2.25.4 In-Reply-To: <20201009142301.412454-1-almaz.alexandrovich@paragon-software.com> References: <20201009142301.412454-1-almaz.alexandrovich@paragon-software.com> MIME-Version: 1.0 X-Originating-IP: [172.30.114.105] X-ClientProxiedBy: vdlg-exch-02.paragon-software.com (172.30.1.105) To vdlg-exch-02.paragon-software.com (172.30.1.105) Precedence: bulk List-ID: X-Mailing-List: linux-fsdevel@vger.kernel.org This adds compression Signed-off-by: Konstantin Komarov --- fs/ntfs3/lznt.c | 452 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 452 insertions(+) create mode 100644 fs/ntfs3/lznt.c diff --git a/fs/ntfs3/lznt.c b/fs/ntfs3/lznt.c new file mode 100644 index 000000000000..c9bdecfb1294 --- /dev/null +++ b/fs/ntfs3/lznt.c @@ -0,0 +1,452 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * linux/fs/ntfs3/lznt.c + * + * Copyright (C) 2019-2020 Paragon Software GmbH, All rights reserved. + * + */ +#include +#include +#include +#include +#include + +#include "debug.h" +#include "ntfs.h" +#include "ntfs_fs.h" + +/* src buffer is zero */ +#define LZNT_ERROR_ALL_ZEROS 1 +#define LZNT_CHUNK_SIZE 0x1000 + +struct lznt_hash { + const u8 *p1; + const u8 *p2; +}; + +struct lznt { + const u8 *unc; + const u8 *unc_end; + const u8 *best_match; + size_t max_len; + bool std; + + struct lznt_hash hash[LZNT_CHUNK_SIZE]; +}; + +static inline size_t get_match_len(const u8 *ptr, const u8 *end, const u8 *prev, + size_t max_len) +{ + size_t len = 0; + + while (ptr + len < end && ptr[len] == prev[len] && ++len < max_len) + ; + return len; +} + +static size_t longest_match_std(const u8 *src, struct lznt *ctx) +{ + size_t hash_index; + size_t len1 = 0, len2 = 0; + const u8 **hash; + + hash_index = + ((40543U * ((((src[0] << 4) ^ src[1]) << 4) ^ src[2])) >> 4) & + (LZNT_CHUNK_SIZE - 1); + + hash = &(ctx->hash[hash_index].p1); + + if (hash[0] >= ctx->unc && hash[0] < src && hash[0][0] == src[0] && + hash[0][1] == src[1] && hash[0][2] == src[2]) { + len1 = 3; + if (ctx->max_len > 3) + len1 += get_match_len(src + 3, ctx->unc_end, + hash[0] + 3, ctx->max_len - 3); + } + + if (hash[1] >= ctx->unc && hash[1] < src && hash[1][0] == src[0] && + hash[1][1] == src[1] && hash[1][2] == src[2]) { + len2 = 3; + if (ctx->max_len > 3) + len2 += get_match_len(src + 3, ctx->unc_end, + hash[1] + 3, ctx->max_len - 3); + } + + /* Compare two matches and select the best one */ + if (len1 < len2) { + ctx->best_match = hash[1]; + len1 = len2; + } else { + ctx->best_match = hash[0]; + } + + hash[1] = hash[0]; + hash[0] = src; + return len1; +} + +static size_t longest_match_best(const u8 *src, struct lznt *ctx) +{ + size_t max_len; + const u8 *ptr; + + if (ctx->unc >= src || !ctx->max_len) + return 0; + + max_len = 0; + for (ptr = ctx->unc; ptr < src; ++ptr) { + size_t len = + get_match_len(src, ctx->unc_end, ptr, ctx->max_len); + if (len >= max_len) { + max_len = len; + ctx->best_match = ptr; + } + } + + return max_len >= 3 ? max_len : 0; +} + +static const size_t s_max_len[] = { + 0x1002, 0x802, 0x402, 0x202, 0x102, 0x82, 0x42, 0x22, 0x12, +}; + +static const size_t s_max_off[] = { + 0x10, 0x20, 0x40, 0x80, 0x100, 0x200, 0x400, 0x800, 0x1000, +}; + +static inline u16 make_pair(size_t offset, size_t len, size_t index) +{ + return ((offset - 1) << (12 - index)) | + ((len - 3) & (((1 << (12 - index)) - 1))); +} + +static inline size_t parse_pair(u16 pair, size_t *offset, size_t index) +{ + *offset = 1 + (pair >> (12 - index)); + return 3 + (pair & ((1 << (12 - index)) - 1)); +} + +/* + * compress_chunk + * + * returns one of the three values: + * 0 - ok, 'cmpr' contains 'cmpr_chunk_size' bytes of compressed data + * 1 - input buffer is full zero + * -2 - the compressed buffer is too small to hold the compressed data + */ +static inline int compress_chunk(size_t (*match)(const u8 *, struct lznt *), + const u8 *unc, const u8 *unc_end, u8 *cmpr, + u8 *cmpr_end, size_t *cmpr_chunk_size, + struct lznt *ctx) +{ + size_t cnt = 0; + size_t idx = 0; + const u8 *up = unc; + u8 *cp = cmpr + 3; + u8 *cp2 = cmpr + 2; + u8 not_zero = 0; + /* Control byte of 8-bit values: ( 0 - means byte as is, 1 - short pair ) */ + u8 ohdr = 0; + u8 *last; + u16 t16; + + if (unc + LZNT_CHUNK_SIZE < unc_end) + unc_end = unc + LZNT_CHUNK_SIZE; + + last = min(cmpr + LZNT_CHUNK_SIZE + sizeof(short), cmpr_end); + + ctx->unc = unc; + ctx->unc_end = unc_end; + ctx->max_len = s_max_len[0]; + + while (up < unc_end) { + size_t max_len; + + while (unc + s_max_off[idx] < up) + ctx->max_len = s_max_len[++idx]; + + // Find match + max_len = up + 3 <= unc_end ? (*match)(up, ctx) : 0; + + if (!max_len) { + if (cp >= last) + goto NotCompressed; + not_zero |= *cp++ = *up++; + } else if (cp + 1 >= last) { + goto NotCompressed; + } else { + t16 = make_pair(up - ctx->best_match, max_len, idx); + *cp++ = t16; + *cp++ = t16 >> 8; + + ohdr |= 1 << cnt; + up += max_len; + } + + cnt = (cnt + 1) & 7; + if (!cnt) { + *cp2 = ohdr; + ohdr = 0; + cp2 = cp; + cp += 1; + } + } + + if (cp2 < last) + *cp2 = ohdr; + else + cp -= 1; + + *cmpr_chunk_size = cp - cmpr; + + t16 = (*cmpr_chunk_size - 3) | 0xB000; + cmpr[0] = t16; + cmpr[1] = t16 >> 8; + + return not_zero ? 0 : LZNT_ERROR_ALL_ZEROS; + +NotCompressed: + + if ((cmpr + LZNT_CHUNK_SIZE + sizeof(short)) > last) + return -2; + + /* + * Copy non cmpr data + * 0x3FFF == ((LZNT_CHUNK_SIZE + 2 - 3) | 0x3000) + */ + cmpr[0] = 0xff; + cmpr[1] = 0x3f; + + memcpy(cmpr + sizeof(short), unc, LZNT_CHUNK_SIZE); + *cmpr_chunk_size = LZNT_CHUNK_SIZE + sizeof(short); + + return 0; +} + +static inline ssize_t decompress_chunk(u8 *unc, u8 *unc_end, const u8 *cmpr, + const u8 *cmpr_end) +{ + u8 *up = unc; + u8 ch = *cmpr++; + size_t bit = 0; + size_t index = 0; + u16 pair; + size_t offset, length; + + /* Do decompression until pointers are inside range */ + while (up < unc_end && cmpr < cmpr_end) { + /* Correct index */ + while (unc + s_max_off[index] < up) + index += 1; + + /* Check the current flag for zero */ + if (!(ch & (1 << bit))) { + /* Just copy byte */ + *up++ = *cmpr++; + goto next; + } + + /* Check for boundary */ + if (cmpr + 1 >= cmpr_end) + return -EINVAL; + + /* Read a short from little endian stream */ + pair = cmpr[1]; + pair <<= 8; + pair |= cmpr[0]; + + cmpr += 2; + + /* Translate packed information into offset and length */ + length = parse_pair(pair, &offset, index); + + /* Check offset for boundary */ + if (unc + offset > up) + return -EINVAL; + + /* Truncate the length if necessary */ + if (up + length >= unc_end) + length = unc_end - up; + + /* Now we copy bytes. This is the heart of LZ algorithm. */ + for (; length > 0; length--, up++) + *up = *(up - offset); + +next: + /* Advance flag bit value */ + bit = (bit + 1) & 7; + + if (!bit) { + if (cmpr >= cmpr_end) + break; + + ch = *cmpr++; + } + } + + /* return the size of uncompressed data */ + return up - unc; +} + +/* + * std = true - standard compression + * std = false - best compression, requires a lot of cpu + */ +struct lznt *get_compression_ctx(bool std) +{ + struct lznt *r = ntfs_alloc( + std ? sizeof(struct lznt) : offsetof(struct lznt, hash), 1); + + if (r) + r->std = std; + return r; +} + +/* + * compress_lznt + * + * Compresses "unc" into "cmpr" + * +x - ok, 'cmpr' contains 'final_compressed_size' bytes of compressed data + * 0 - input buffer is full zero + */ +size_t compress_lznt(const void *unc, size_t unc_size, void *cmpr, + size_t cmpr_size, struct lznt *ctx) +{ + int err; + size_t (*match)(const u8 *src, struct lznt *ctx); + u8 *p = cmpr; + u8 *end = p + cmpr_size; + const u8 *unc_chunk = unc; + const u8 *unc_end = unc_chunk + unc_size; + bool is_zero = true; + + if (ctx->std) { + match = &longest_match_std; + memset(ctx->hash, 0, sizeof(ctx->hash)); + } else { + match = &longest_match_best; + } + + /* compression cycle */ + for (; unc_chunk < unc_end; unc_chunk += LZNT_CHUNK_SIZE) { + cmpr_size = 0; + err = compress_chunk(match, unc_chunk, unc_end, p, end, + &cmpr_size, ctx); + if (err < 0) + return unc_size; + + if (is_zero && err != LZNT_ERROR_ALL_ZEROS) + is_zero = false; + + p += cmpr_size; + } + + if (p <= end - 2) + p[0] = p[1] = 0; + + return is_zero ? 0 : PtrOffset(cmpr, p); +} + +/* + * decompress_lznt + * + * decompresses "cmpr" into "unc" + */ +ssize_t decompress_lznt(const void *cmpr, size_t cmpr_size, void *unc, + size_t unc_size) +{ + const u8 *cmpr_chunk = cmpr; + const u8 *cmpr_end = cmpr_chunk + cmpr_size; + u8 *unc_chunk = unc; + u8 *unc_end = unc_chunk + unc_size; + u16 chunk_hdr; + + if (cmpr_size < sizeof(short)) + return -EINVAL; + + /* read chunk header */ + chunk_hdr = cmpr_chunk[1]; + chunk_hdr <<= 8; + chunk_hdr |= cmpr_chunk[0]; + + /* loop through decompressing chunks */ + for (;;) { + size_t chunk_size_saved; + size_t unc_use; + size_t cmpr_use = 3 + (chunk_hdr & (LZNT_CHUNK_SIZE - 1)); + + /* Check that the chunk actually fits the supplied buffer */ + if (cmpr_chunk + cmpr_use > cmpr_end) + return -EINVAL; + + /* First make sure the chunk contains compressed data */ + if (chunk_hdr & 0x8000) { + /* Decompress a chunk and return if we get an error */ + ssize_t err = + decompress_chunk(unc_chunk, unc_end, + cmpr_chunk + sizeof(chunk_hdr), + cmpr_chunk + cmpr_use); + if (err < 0) + return err; + unc_use = err; + } else { + /* This chunk does not contain compressed data */ + unc_use = unc_chunk + LZNT_CHUNK_SIZE > unc_end ? + unc_end - unc_chunk : + LZNT_CHUNK_SIZE; + + if (cmpr_chunk + sizeof(chunk_hdr) + unc_use > + cmpr_end) { + return -EINVAL; + } + + memcpy(unc_chunk, cmpr_chunk + sizeof(chunk_hdr), + unc_use); + } + + /* Advance pointers */ + cmpr_chunk += cmpr_use; + unc_chunk += unc_use; + + /* Check for the end of unc buffer */ + if (unc_chunk >= unc_end) + break; + + /* Proceed the next chunk */ + if (cmpr_chunk > cmpr_end - 2) + break; + + chunk_size_saved = LZNT_CHUNK_SIZE; + + /* read chunk header */ + chunk_hdr = cmpr_chunk[1]; + chunk_hdr <<= 8; + chunk_hdr |= cmpr_chunk[0]; + + if (!chunk_hdr) + break; + + /* Check the size of unc buffer */ + if (unc_use < chunk_size_saved) { + size_t t1 = chunk_size_saved - unc_use; + u8 *t2 = unc_chunk + t1; + + /* 'Zero' memory */ + if (t2 >= unc_end) + break; + + memset(unc_chunk, 0, t1); + unc_chunk = t2; + } + } + + /* Check compression boundary */ + if (cmpr_chunk > cmpr_end) + return -EINVAL; + + /* + * The unc size is just a difference between current + * pointer and original one + */ + return PtrOffset(unc, unc_chunk); +} From patchwork Fri Oct 9 14:22:58 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Konstantin Komarov X-Patchwork-Id: 11825957 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 935F414D5 for ; Fri, 9 Oct 2020 14:23:47 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 4BBBA222BA for ; Fri, 9 Oct 2020 14:23:47 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (1024-bit key) header.d=paragon-software.com header.i=@paragon-software.com header.b="ADvTQOa0" Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S2388772AbgJIOXm (ORCPT ); Fri, 9 Oct 2020 10:23:42 -0400 Received: from relayfre-01.paragon-software.com ([176.12.100.13]:52164 "EHLO relayfre-01.paragon-software.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S2388699AbgJIOXU (ORCPT ); Fri, 9 Oct 2020 10:23:20 -0400 Received: from dlg2.mail.paragon-software.com (vdlg-exch-02.paragon-software.com [172.30.1.105]) by relayfre-01.paragon-software.com (Postfix) with ESMTPS id 62ACD212F; Fri, 9 Oct 2020 17:23:10 +0300 (MSK) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=paragon-software.com; s=mail; t=1602253390; bh=UrewsEC6NnwvDjnTG46DV99jRqvJSNNlWVBrIPcb/wA=; h=From:To:CC:Subject:Date:In-Reply-To:References; b=ADvTQOa0a9+khygUGEYbEG86kJWtkMPjFtT1Vx/ln/23pPH6FLL845dxxNhcpkLxN lB9d3lC+cErcd+o2z1rKhVgEFwl364e4BmFten5sTpTE+HtGr3Jh6QLIy6Ye1Vq/yw WjCMYdRP926UDlEFEBakdEMK0csxsO/zMUV68qdc= Received: from fsd-lkpg.ufsd.paragon-software.com (172.30.114.105) by vdlg-exch-02.paragon-software.com (172.30.1.105) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id 15.1.1847.3; Fri, 9 Oct 2020 17:23:09 +0300 From: Konstantin Komarov To: CC: , , , , , , , , , , , , Konstantin Komarov Subject: [PATCH v8 07/10] fs/ntfs3: Add NTFS journal Date: Fri, 9 Oct 2020 17:22:58 +0300 Message-ID: <20201009142301.412454-8-almaz.alexandrovich@paragon-software.com> X-Mailer: git-send-email 2.25.4 In-Reply-To: <20201009142301.412454-1-almaz.alexandrovich@paragon-software.com> References: <20201009142301.412454-1-almaz.alexandrovich@paragon-software.com> MIME-Version: 1.0 X-Originating-IP: [172.30.114.105] X-ClientProxiedBy: vdlg-exch-02.paragon-software.com (172.30.1.105) To vdlg-exch-02.paragon-software.com (172.30.1.105) Precedence: bulk List-ID: X-Mailing-List: linux-fsdevel@vger.kernel.org This adds NTFS journal Signed-off-by: Konstantin Komarov --- fs/ntfs3/fslog.c | 5222 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 5222 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 000000000000..388d332b9ca1 --- /dev/null +++ b/fs/ntfs3/fslog.c @@ -0,0 +1,5222 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * linux/fs/ntfs3/fslog.c + * + * Copyright (C) 2019-2020 Paragon Software GmbH, All rights reserved. + * + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "debug.h" +#include "ntfs.h" +#include "ntfs_fs.h" + +/* + * LOG FILE structs + */ + +#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[1]; +}; + +#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[1]; // 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[1]; // 0x20: +}; + +static_assert(sizeof(struct LOG_REC_HDR) == 0x28); + +#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[1]; +}; + +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[1]; // 0x20: +}; + +static_assert(sizeof(struct DIR_PAGE_ENTRY) == 0x28); + +/* 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 +}; + +// 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 t16 > 1 ? sizeof(struct LOG_REC_HDR) + (t16 - 1) * sizeof(u64) : + sizeof(struct LOG_REC_HDR); +} + +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_alloc(bytes, 1); + + 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 allow_errors, + bool ignore_usa_error, 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_alloc(bytes, 0); + 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; + + /* Check that the update sequence array for this page is valid */ + if (bBAAD) { + /* If we don't allow errors, raise an error status */ + if (!ignore_usa_error) { + err = -EINVAL; + goto out; + } + } + + if (usa_error) + *usa_error = bBAAD; + +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) +{ + int err; + u32 skip, vbo; + struct RESTART_HDR *r_page = ntfs_alloc(DefaultLogPageSize, 0); + + 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 */ + err = read_log_page(log, vbo, + (struct RECORD_PAGE_HDR **)&r_page, true, + true, &usa_error); + + if (err) + 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_alloc(sys_page_size, 1); + if (!r_page) + return -ENOMEM; + + err = read_log_page(log, vbo, + (struct RECORD_PAGE_HDR **)&r_page, + true, true, &usa_error); + + if (err) { + ntfs_free(r_page); + return err; + } + } + + 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 = offsetof(struct RESTART_AREA, clients) + + sizeof(struct CLIENT_REC); + 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_alloc(log->restart_size, 1); + + 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, false, false, 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, + *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_alloc(log->page_size * 0x10, 0); + 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, true, true, + &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, true, true, + &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 free_and_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 { +free_and_tail_read: + 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, allowing errors */ + err = read_log_page(log, curpage_off, &page, true, true, &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, 1, 1, &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, true, true, + &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_alloc(log->page_size, 0); + 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 (;;) { + u32 tail = log->page_size - off; + + if (tail >= data_len) + tail = data_len; + + data_len -= tail; + + err = read_log_page(log, vbo, &ph, false, true, NULL); + 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); + + /* If there are no more bytes to transfer, we exit the loop */ + if (!data_len) { + if (!is_log_record_end(ph) || + lsn > le64_to_cpu(ph->record_hdr.last_end_lsn)) { + err = -EINVAL; + goto out; + } + break; + } + + if (ph->rhdr.lsn == ph->record_hdr.last_end_lsn || + lsn > le64_to_cpu(ph->rhdr.lsn)) { + err = -EINVAL; + goto out; + } + + vbo = next_page_off(log, vbo); + off = log->data_off; + + /* + * adjust our pointer the user's buffer to transfer + * the next block to + */ + buffer = Add2Ptr(buffer, tail); + } + +out: + ntfs_free(ph); + return err; +} + +static int read_rst_area(struct ntfs_log *log, struct NTFS_RESTART **rst_, + u64 *lsn) +{ + int err; + struct LFS_RECORD_HDR *rh = NULL; + const struct CLIENT_REC *cr = + Add2Ptr(log->ra, le16_to_cpu(log->ra->client_off)); + u64 lsnr, lsnc = le64_to_cpu(cr->restart_lsn); + u32 len; + struct NTFS_RESTART *rst; + + *lsn = 0; + *rst_ = NULL; + + /* If the client doesn't have a restart area, go ahead and exit now */ + if (!lsnc) + return 0; + + err = read_log_page(log, lsn_to_vbo(log, lsnc), + (struct RECORD_PAGE_HDR **)&rh, false, false, NULL); + if (err) + return err; + + rst = NULL; + lsnr = le64_to_cpu(rh->this_lsn); + + if (lsnc != lsnr) { + /* If the lsn values don't match, then the disk is corrupt */ + err = -EINVAL; + goto out; + } + + *lsn = lsnr; + len = le32_to_cpu(rh->client_data_len); + + if (!len) { + err = 0; + goto out; + } + + if (len < sizeof(struct NTFS_RESTART)) { + err = -EINVAL; + goto out; + } + + rst = ntfs_alloc(len, 0); + if (!rst) { + err = -ENOMEM; + goto out; + } + + /* Copy the data into the 'rst' buffer */ + err = read_log_rec_buf(log, rh, rst); + if (err) + goto out; + + *rst_ = rst; + rst = NULL; + +out: + ntfs_free(rh); + ntfs_free(rst); + + return err; +} + +static int find_log_rec(struct ntfs_log *log, u64 lsn, struct lcb *lcb) +{ + int err; + struct LFS_RECORD_HDR *rh = lcb->lrh; + u32 rec_len, len; + + /* Read the record header for this lsn */ + if (!rh) { + err = read_log_page(log, lsn_to_vbo(log, lsn), + (struct RECORD_PAGE_HDR **)&rh, false, + false, NULL); + + lcb->lrh = rh; + if (err) + return err; + } + + /* + * If the lsn the log record doesn't match the desired + * lsn then the disk is corrupt + */ + if (lsn != le64_to_cpu(rh->this_lsn)) + return -EINVAL; + + len = le32_to_cpu(rh->client_data_len); + + /* + * check that the length field isn't greater than the total + * available space the log file + */ + rec_len = len + log->record_header_len; + if (rec_len >= log->total_avail) + return -EINVAL; + + /* + * If the entire log record is on this log page, + * put a pointer to the log record the context block + */ + if (rh->flags & LOG_RECORD_MULTI_PAGE) { + void *lr = ntfs_alloc(len, 0); + + if (!lr) + return -ENOMEM; + + lcb->log_rec = lr; + lcb->alloc = true; + + /* Copy the data into the buffer returned */ + err = read_log_rec_buf(log, rh, lr); + if (err) + return err; + } else { + /* If beyond the end of the current page -> an error */ + u32 page_off = lsn_to_page_off(log, lsn); + + if (page_off + len + log->record_header_len > log->page_size) + return -EINVAL; + + lcb->log_rec = Add2Ptr(rh, sizeof(struct LFS_RECORD_HDR)); + lcb->alloc = false; + } + + return 0; +} + +/* + * read_log_rec_lcb + * + * initiates the query operation. + */ +static int read_log_rec_lcb(struct ntfs_log *log, u64 lsn, u32 ctx_mode, + struct lcb **lcb_) +{ + int err; + const struct CLIENT_REC *cr; + struct lcb *lcb; + + switch (ctx_mode) { + case lcb_ctx_undo_next: + case lcb_ctx_prev: + case lcb_ctx_next: + break; + default: + return -EINVAL; + } + + /* check that the given lsn is the legal range for this client */ + cr = Add2Ptr(log->ra, le16_to_cpu(log->ra->client_off)); + + if (!verify_client_lsn(log, cr, lsn)) + return -EINVAL; + + lcb = ntfs_alloc(sizeof(struct lcb), 1); + if (!lcb) + return -ENOMEM; + lcb->client = log->client_id; + lcb->ctx_mode = ctx_mode; + + /* Find the log record indicated by the given lsn */ + err = find_log_rec(log, lsn, lcb); + if (err) + goto out; + + *lcb_ = lcb; + return 0; + +out: + lcb_put(lcb); + *lcb_ = NULL; + return err; +} + +/* + * find_client_next_lsn + * + * attempt to find the next lsn to return to a client based on the context mode. + */ +static int find_client_next_lsn(struct ntfs_log *log, struct lcb *lcb, u64 *lsn) +{ + int err; + u64 next_lsn; + struct LFS_RECORD_HDR *hdr; + + hdr = lcb->lrh; + *lsn = 0; + + if (lcb_ctx_next != lcb->ctx_mode) + goto check_undo_next; + + /* Loop as long as another lsn can be found */ + for (;;) { + u64 current_lsn; + + err = next_log_lsn(log, hdr, ¤t_lsn); + if (err) + goto out; + + if (!current_lsn) + break; + + if (hdr != lcb->lrh) + ntfs_free(hdr); + + hdr = NULL; + err = read_log_page(log, lsn_to_vbo(log, current_lsn), + (struct RECORD_PAGE_HDR **)&hdr, false, + false, NULL); + if (err) + goto out; + + if (memcmp(&hdr->client, &lcb->client, + sizeof(struct CLIENT_ID))) { + /*err = -EINVAL; */ + } else if (LfsClientRecord == hdr->record_type) { + ntfs_free(lcb->lrh); + lcb->lrh = hdr; + *lsn = current_lsn; + return 0; + } + } + +out: + if (hdr != lcb->lrh) + ntfs_free(hdr); + return err; + +check_undo_next: + if (lcb_ctx_undo_next == lcb->ctx_mode) + next_lsn = le64_to_cpu(hdr->client_undo_next_lsn); + else if (lcb_ctx_prev == lcb->ctx_mode) + next_lsn = le64_to_cpu(hdr->client_prev_lsn); + else + return 0; + + if (!next_lsn) + return 0; + + if (!verify_client_lsn( + log, Add2Ptr(log->ra, le16_to_cpu(log->ra->client_off)), + next_lsn)) + return 0; + + hdr = NULL; + err = read_log_page(log, lsn_to_vbo(log, next_lsn), + (struct RECORD_PAGE_HDR **)&hdr, false, false, + NULL); + if (err) + return err; + ntfs_free(lcb->lrh); + lcb->lrh = hdr; + + *lsn = next_lsn; + + return 0; +} + +static int read_next_log_rec(struct ntfs_log *log, struct lcb *lcb, u64 *lsn) +{ + int err; + + err = find_client_next_lsn(log, lcb, lsn); + if (err) + return err; + + if (!*lsn) + return 0; + + if (lcb->alloc) + ntfs_free(lcb->log_rec); + + lcb->log_rec = NULL; + lcb->alloc = false; + ntfs_free(lcb->lrh); + lcb->lrh = NULL; + + return find_log_rec(log, *lsn, lcb); +} + +static inline bool check_index_header(const struct INDEX_HDR *hdr, size_t bytes) +{ + __le16 mask; + u32 min_de, de_off, used, total; + const struct NTFS_DE *e; + + if (hdr_has_subnode(hdr)) { + min_de = sizeof(struct NTFS_DE) + sizeof(u64); + mask = NTFS_IE_HAS_SUBNODES; + } else { + min_de = sizeof(struct NTFS_DE); + mask = 0; + } + + de_off = le32_to_cpu(hdr->de_off); + used = le32_to_cpu(hdr->used); + total = le32_to_cpu(hdr->total); + + if (de_off > bytes - min_de || used > bytes || total > bytes || + de_off + min_de > used || used > total) { + return false; + } + + e = Add2Ptr(hdr, de_off); + for (;;) { + u16 esize = le16_to_cpu(e->size); + struct NTFS_DE *next = Add2Ptr(e, esize); + + if (esize < min_de || PtrOffset(hdr, next) > used || + (e->flags & NTFS_IE_HAS_SUBNODES) != mask) { + return false; + } + + if (de_is_last(e)) + break; + + e = next; + } + + return true; +} + +static inline bool check_index_buffer(const struct INDEX_BUFFER *ib, u32 bytes) +{ + u16 fo; + const struct NTFS_RECORD_HEADER *r = &ib->rhdr; + + if (r->sign != NTFS_INDX_SIGNATURE) + return false; + + fo = (SECTOR_SIZE - ((bytes >> SECTOR_SHIFT) + 1) * sizeof(short)); + + if (le16_to_cpu(r->fix_off) > fo) + return false; + + if ((le16_to_cpu(r->fix_num) - 1) * SECTOR_SIZE != bytes) + return false; + + return check_index_header(&ib->ihdr, + bytes - offsetof(struct INDEX_BUFFER, ihdr)); +} + +static inline bool check_index_root(const struct ATTRIB *attr, + struct ntfs_sb_info *sbi) +{ + bool ret; + const struct INDEX_ROOT *root = resident_data(attr); + u8 index_bits = + le32_to_cpu(root->index_block_size) >= sbi->cluster_size ? + sbi->cluster_bits : + SECTOR_SHIFT; + u8 block_clst = root->index_block_clst; + + if (le32_to_cpu(attr->res.data_size) < sizeof(struct INDEX_ROOT) || + (root->type != ATTR_NAME && root->type != ATTR_ZERO) || + (root->type == ATTR_NAME && + root->rule != NTFS_COLLATION_TYPE_FILENAME) || + (le32_to_cpu(root->index_block_size) != + (block_clst << index_bits)) || + (block_clst != 1 && block_clst != 2 && block_clst != 4 && + block_clst != 8 && block_clst != 0x10 && block_clst != 0x20 && + block_clst != 0x40 && block_clst != 0x80)) { + return false; + } + + ret = check_index_header(&root->ihdr, + le32_to_cpu(attr->res.data_size) - + offsetof(struct INDEX_ROOT, ihdr)); + return ret; +} + +static inline bool check_attr(const struct MFT_REC *rec, + const struct ATTRIB *attr, + struct ntfs_sb_info *sbi) +{ + u32 asize = le32_to_cpu(attr->size); + u32 rsize = 0; + u64 dsize, svcn, evcn; + u16 run_off; + + /* Check the fixed part of the attribute record header */ + if (asize >= sbi->record_size || + asize + PtrOffset(rec, attr) >= sbi->record_size || + (attr->name_len && + le16_to_cpu(attr->name_off) + attr->name_len * sizeof(short) > + asize)) { + return false; + } + + /* Check the attribute fields */ + switch (attr->non_res) { + case 0: + rsize = le32_to_cpu(attr->res.data_size); + if (rsize >= asize || + le16_to_cpu(attr->res.data_off) + rsize > asize) { + return false; + } + break; + + case 1: + dsize = le64_to_cpu(attr->nres.data_size); + svcn = le64_to_cpu(attr->nres.svcn); + evcn = le64_to_cpu(attr->nres.evcn); + run_off = le16_to_cpu(attr->nres.run_off); + + if (svcn > evcn + 1 || run_off >= asize || + le64_to_cpu(attr->nres.valid_size) > dsize || + dsize > le64_to_cpu(attr->nres.alloc_size)) { + return false; + } + + if (run_unpack(NULL, sbi, 0, svcn, evcn, Add2Ptr(attr, run_off), + asize - run_off) < 0) { + return false; + } + + return true; + + default: + return false; + } + + switch (attr->type) { + case ATTR_NAME: + if (fname_full_size(Add2Ptr( + attr, le16_to_cpu(attr->res.data_off))) > asize) { + return false; + } + break; + + case ATTR_ROOT: + return check_index_root(attr, sbi); + + case ATTR_STD: + if (rsize < sizeof(struct ATTR_STD_INFO5) && + rsize != sizeof(struct ATTR_STD_INFO)) { + return false; + } + break; + + case ATTR_LIST: + case ATTR_ID: + case ATTR_SECURE: + case ATTR_LABEL: + case ATTR_VOL_INFO: + case ATTR_DATA: + case ATTR_ALLOC: + case ATTR_BITMAP: + case ATTR_REPARSE: + case ATTR_EA_INFO: + case ATTR_EA: + case ATTR_PROPERTYSET: + case ATTR_LOGGED_UTILITY_STREAM: + break; + + default: + return false; + } + + return true; +} + +static inline bool check_file_record(const struct MFT_REC *rec, + const struct MFT_REC *rec2, + struct ntfs_sb_info *sbi) +{ + const struct ATTRIB *attr; + u16 fo = le16_to_cpu(rec->rhdr.fix_off); + u16 fn = le16_to_cpu(rec->rhdr.fix_num); + u16 ao = le16_to_cpu(rec->attr_off); + u32 rs = sbi->record_size; + + /* check the file record header for consistency */ + if (rec->rhdr.sign != NTFS_FILE_SIGNATURE || + fo > (SECTOR_SIZE - ((rs >> SECTOR_SHIFT) + 1) * sizeof(short)) || + (fn - 1) * SECTOR_SIZE != rs || ao < MFTRECORD_FIXUP_OFFSET_1 || + ao > sbi->record_size - SIZEOF_RESIDENT || !is_rec_inuse(rec) || + le32_to_cpu(rec->total) != rs) { + return false; + } + + /* Loop to check all of the attributes */ + for (attr = Add2Ptr(rec, ao); attr->type != ATTR_END; + attr = Add2Ptr(attr, le32_to_cpu(attr->size))) { + if (check_attr(rec, attr, sbi)) + continue; + return false; + } + + return true; +} + +static inline int check_lsn(const struct NTFS_RECORD_HEADER *hdr, + const u64 *rlsn) +{ + u64 lsn; + + if (!rlsn) + return true; + + lsn = le64_to_cpu(hdr->lsn); + + if (hdr->sign == NTFS_HOLE_SIGNATURE) + return false; + + if (*rlsn > lsn) + return true; + + return false; +} + +static inline bool check_if_attr(const struct MFT_REC *rec, + const struct LOG_REC_HDR *lrh) +{ + u16 ro = le16_to_cpu(lrh->record_off); + u16 o = le16_to_cpu(rec->attr_off); + const struct ATTRIB *attr = Add2Ptr(rec, o); + + while (o < ro) { + u32 asize; + + if (attr->type == ATTR_END) + break; + + asize = le32_to_cpu(attr->size); + if (!asize) + break; + + o += asize; + attr = Add2Ptr(attr, asize); + } + + return o == ro; +} + +static inline bool check_if_index_root(const struct MFT_REC *rec, + const struct LOG_REC_HDR *lrh) +{ + u16 ro = le16_to_cpu(lrh->record_off); + u16 o = le16_to_cpu(rec->attr_off); + const struct ATTRIB *attr = Add2Ptr(rec, o); + + while (o < ro) { + u32 asize; + + if (attr->type == ATTR_END) + break; + + asize = le32_to_cpu(attr->size); + if (!asize) + break; + + o += asize; + attr = Add2Ptr(attr, asize); + } + + return o == ro && attr->type == ATTR_ROOT; +} + +static inline bool check_if_root_index(const struct ATTRIB *attr, + const struct INDEX_HDR *hdr, + const struct LOG_REC_HDR *lrh) +{ + u16 ao = le16_to_cpu(lrh->attr_off); + u32 de_off = le32_to_cpu(hdr->de_off); + u32 o = PtrOffset(attr, hdr) + de_off; + const struct NTFS_DE *e = Add2Ptr(hdr, de_off); + u32 asize = le32_to_cpu(attr->size); + + while (o < ao) { + u16 esize; + + if (o >= asize) + break; + + esize = le16_to_cpu(e->size); + if (!esize) + break; + + o += esize; + e = Add2Ptr(e, esize); + } + + return o == ao; +} + +static inline bool check_if_alloc_index(const struct INDEX_HDR *hdr, + u32 attr_off) +{ + u32 de_off = le32_to_cpu(hdr->de_off); + u32 o = offsetof(struct INDEX_BUFFER, ihdr) + de_off; + const struct NTFS_DE *e = Add2Ptr(hdr, de_off); + u32 used = le32_to_cpu(hdr->used); + + while (o < attr_off) { + u16 esize; + + if (de_off >= used) + break; + + esize = le16_to_cpu(e->size); + if (!esize) + break; + + o += esize; + de_off += esize; + e = Add2Ptr(e, esize); + } + + return o == attr_off; +} + +static inline void change_attr_size(struct MFT_REC *rec, struct ATTRIB *attr, + u32 nsize) +{ + u32 asize = le32_to_cpu(attr->size); + int dsize = nsize - asize; + u8 *next = Add2Ptr(attr, asize); + u32 used = le32_to_cpu(rec->used); + + memmove(Add2Ptr(attr, nsize), next, used - PtrOffset(rec, next)); + + rec->used = cpu_to_le32(used + dsize); + attr->size = cpu_to_le32(nsize); +} + +struct OpenAttr { + struct ATTRIB *attr; + struct runs_tree *run1; + struct runs_tree run0; + struct ntfs_inode *ni; + // CLST rno; +}; + +/* Returns 0 if 'attr' has the same type and name */ +static inline int cmp_type_and_name(const struct ATTRIB *a1, + const struct ATTRIB *a2) +{ + return a1->type != a2->type || a1->name_len != a2->name_len || + (a1->name_len && memcmp(attr_name(a1), attr_name(a2), + a1->name_len * sizeof(short))); +} + +static struct OpenAttr *find_loaded_attr(struct ntfs_log *log, + const struct ATTRIB *attr, CLST rno) +{ + struct OPEN_ATTR_ENRTY *oe = NULL; + + while ((oe = enum_rstbl(log->open_attr_tbl, oe))) { + struct OpenAttr *op_attr; + + if (ino_get(&oe->ref) != rno) + continue; + + op_attr = (struct OpenAttr *)oe->ptr; + if (!cmp_type_and_name(op_attr->attr, attr)) + return op_attr; + } + return NULL; +} + +static struct ATTRIB *attr_create_nonres_log(struct ntfs_sb_info *sbi, + enum ATTR_TYPE type, u64 size, + const u16 *name, size_t name_len, + __le16 flags) +{ + struct ATTRIB *attr; + u32 name_size = QuadAlign(name_len * sizeof(short)); + bool is_ext = flags & (ATTR_FLAG_COMPRESSED | ATTR_FLAG_SPARSED); + u32 asize = name_size + + (is_ext ? SIZEOF_NONRESIDENT_EX : SIZEOF_NONRESIDENT); + + attr = ntfs_alloc(asize, 1); + if (!attr) + return NULL; + + attr->type = type; + attr->size = cpu_to_le32(asize); + attr->flags = flags; + attr->non_res = 1; + attr->name_len = name_len; + + attr->nres.evcn = cpu_to_le64((u64)bytes_to_cluster(sbi, size) - 1); + attr->nres.alloc_size = cpu_to_le64(ntfs_up_cluster(sbi, size)); + attr->nres.data_size = cpu_to_le64(size); + attr->nres.valid_size = attr->nres.data_size; + if (is_ext) { + attr->name_off = SIZEOF_NONRESIDENT_EX_LE; + if (is_attr_compressed(attr)) + attr->nres.c_unit = COMPRESSION_UNIT; + + attr->nres.run_off = + cpu_to_le16(SIZEOF_NONRESIDENT_EX + name_size); + memcpy(Add2Ptr(attr, SIZEOF_NONRESIDENT_EX), name, + name_len * sizeof(short)); + } else { + attr->name_off = SIZEOF_NONRESIDENT_LE; + attr->nres.run_off = + cpu_to_le16(SIZEOF_NONRESIDENT + name_size); + memcpy(Add2Ptr(attr, SIZEOF_NONRESIDENT), name, + name_len * sizeof(short)); + } + + return attr; +} + +/* + * do_action + * + * common routine for the Redo and Undo Passes + * If rlsn is NULL then undo + */ +static int do_action(struct ntfs_log *log, struct OPEN_ATTR_ENRTY *oe, + const struct LOG_REC_HDR *lrh, u32 op, void *data, + u32 dlen, u32 rec_len, const u64 *rlsn) +{ + int err = 0; + struct ntfs_sb_info *sbi = log->ni->mi.sbi; + struct inode *inode = NULL, *inode_parent; + struct mft_inode *mi = NULL, *mi2_child = NULL; + CLST rno = 0, rno_base = 0; + struct INDEX_BUFFER *ib = NULL; + struct MFT_REC *rec = NULL; + struct ATTRIB *attr = NULL, *attr2; + struct INDEX_HDR *hdr; + struct INDEX_ROOT *root; + struct NTFS_DE *e, *e1, *e2; + struct NEW_ATTRIBUTE_SIZES *new_sz; + struct ATTR_FILE_NAME *fname; + struct OpenAttr *oa, *oa2; + u32 nsize, t32, asize, used, esize, bmp_off, bmp_bits; + u16 t16, id, id2; + u32 record_size = sbi->record_size; + u64 t64; + u64 lco = 0; + u64 cbo = (u64)le16_to_cpu(lrh->cluster_off) << SECTOR_SHIFT; + u64 tvo = le64_to_cpu(lrh->target_vcn) << sbi->cluster_bits; + u64 vbo = cbo + tvo; + void *buffer_le = NULL; + u32 bytes = 0; + bool a_dirty = false; + u16 data_off; + + oa = oe->ptr; + + /* Big switch to prepare */ + switch (op) { + /* ============================================================ + * Process MFT records, as described by the current log record + * ============================================================ + */ + case InitializeFileRecordSegment: + case DeallocateFileRecordSegment: + case WriteEndOfFileRecordSegment: + case CreateAttribute: + case DeleteAttribute: + case UpdateResidentValue: + case UpdateMappingPairs: + case SetNewAttributeSizes: + case AddIndexEntryRoot: + case DeleteIndexEntryRoot: + case SetIndexEntryVcnRoot: + case UpdateFileNameRoot: + case UpdateRecordDataRoot: + case ZeroEndOfFileRecord: + + rno = vbo >> sbi->record_bits; + + inode = ilookup(sbi->sb, rno); + if (inode) { + mi = &ntfs_i(inode)->mi; + } else if (op == InitializeFileRecordSegment) { + mi = ntfs_alloc(sizeof(struct mft_inode), 1); + if (!mi) + return -ENOMEM; + err = mi_format_new(mi, sbi, rno, 0, false); + if (err) + goto out; + } else { + /* read from disk */ + err = mi_get(sbi, rno, &mi); + if (err) + return err; + } + rec = mi->mrec; + + if (op == DeallocateFileRecordSegment) + goto skip_load_parent; + + if (InitializeFileRecordSegment != op) { + if (rec->rhdr.sign == NTFS_BAAD_SIGNATURE) + goto dirty_vol; + if (!check_lsn(&rec->rhdr, rlsn)) + goto out; + if (!check_file_record(rec, NULL, sbi)) + goto dirty_vol; + attr = Add2Ptr(rec, le16_to_cpu(lrh->record_off)); + } + + if (is_rec_base(rec) || InitializeFileRecordSegment == op) { + rno_base = rno; + goto skip_load_parent; + } + + rno_base = ino_get(&rec->parent_ref); + + inode_parent = ntfs_iget5(sbi->sb, &rec->parent_ref, NULL); + if (IS_ERR(inode_parent)) + goto skip_load_parent; + + if (is_bad_inode(inode_parent)) { + iput(inode_parent); + goto skip_load_parent; + } + + if (ni_load_mi_ex(ntfs_i(inode_parent), rno, &mi2_child)) { + iput(inode_parent); + } else { + if (mi2_child->mrec != mi->mrec) + memcpy(mi2_child->mrec, mi->mrec, + sbi->record_size); + + if (inode) + iput(inode); + else if (mi) + mi_put(mi); + + inode = inode_parent; + mi = mi2_child; + rec = mi2_child->mrec; + attr = Add2Ptr(rec, le16_to_cpu(lrh->record_off)); + } + +skip_load_parent: + inode_parent = NULL; + break; + + /* ============================================================ + * Process attributes, as described by the current log record + * ============================================================ + */ + case UpdateNonresidentValue: + case AddIndexEntryAllocation: + case DeleteIndexEntryAllocation: + case WriteEndOfIndexBuffer: + case SetIndexEntryVcnAllocation: + case UpdateFileNameAllocation: + case SetBitsInNonresidentBitMap: + case ClearBitsInNonresidentBitMap: + case UpdateRecordDataAllocation: + + attr = oa->attr; + bytes = UpdateNonresidentValue == op ? dlen : 0; + lco = (u64)le16_to_cpu(lrh->lcns_follow) << sbi->cluster_bits; + + if (attr->type == ATTR_ALLOC) { + t32 = le32_to_cpu(oe->bytes_per_index); + if (bytes < t32) + bytes = t32; + } + + if (!bytes) + bytes = lco - cbo; + + bytes += le16_to_cpu(lrh->record_off); + if (attr->type == ATTR_ALLOC) + bytes = (bytes + 511) & ~511; // align + + buffer_le = ntfs_alloc(bytes, 0); + if (!buffer_le) + return -ENOMEM; + + err = ntfs_read_run_nb(sbi, oa->run1, vbo, buffer_le, bytes, + NULL); + if (err) + goto out; + + if (attr->type == ATTR_ALLOC && *(int *)buffer_le) + ntfs_fix_post_read(buffer_le, bytes, false); + break; + + default: + WARN_ON(1); + } + + /* Big switch to do operation */ + switch (op) { + case InitializeFileRecordSegment: + t16 = le16_to_cpu(lrh->record_off); + if (t16 + dlen > record_size) + goto dirty_vol; + + memcpy(Add2Ptr(rec, t16), data, dlen); + mi->dirty = true; + break; + + case DeallocateFileRecordSegment: + clear_rec_inuse(rec); + le16_add_cpu(&rec->seq, 1); + mi->dirty = true; + break; + + case WriteEndOfFileRecordSegment: + attr2 = (struct ATTRIB *)data; + t16 = le16_to_cpu(lrh->record_off); + + if (!check_if_attr(rec, lrh) || t16 + dlen > record_size) + goto dirty_vol; + + memmove(attr, attr2, dlen); + rec->used = cpu_to_le32(QuadAlign(t16 + dlen)); + + mi->dirty = true; + break; + + case CreateAttribute: + attr2 = (struct ATTRIB *)data; + asize = le32_to_cpu(attr2->size); + used = le32_to_cpu(rec->used); + t16 = le16_to_cpu(lrh->record_off); + + if (!check_if_attr(rec, lrh) || dlen < SIZEOF_RESIDENT || + !IsQuadAligned(asize) || + Add2Ptr(attr2, asize) > Add2Ptr(lrh, rec_len) || + dlen > record_size - used) { + goto dirty_vol; + } + + memmove(Add2Ptr(attr, asize), attr, used - t16); + memcpy(attr, attr2, asize); + + rec->used = cpu_to_le32(used + asize); + id = le16_to_cpu(rec->next_attr_id); + id2 = le16_to_cpu(attr2->id); + if (id <= id2) + rec->next_attr_id = cpu_to_le16(id2 + 1); + if (is_attr_indexed(attr)) + le16_add_cpu(&rec->hard_links, 1); + + oa2 = find_loaded_attr(log, attr, rno_base); + if (oa2) { + void *p2 = ntfs_memdup(attr, le32_to_cpu(attr->size)); + + if (p2) { + // run_close(oa2->run1); + ntfs_free(oa2->attr); + oa2->attr = p2; + } + } + + mi->dirty = true; + break; + + case DeleteAttribute: + asize = le32_to_cpu(attr->size); + used = le32_to_cpu(rec->used); + t16 = le16_to_cpu(lrh->record_off); + + if (!check_if_attr(rec, lrh)) + goto dirty_vol; + + rec->used = cpu_to_le32(used - asize); + if (is_attr_indexed(attr)) + le16_add_cpu(&rec->hard_links, -1); + + memmove(attr, Add2Ptr(attr, asize), used - t16); + + mi->dirty = true; + break; + + case UpdateResidentValue: + t16 = le16_to_cpu(lrh->attr_off); + nsize = t16 + dlen; + + if (!check_if_attr(rec, lrh)) + goto dirty_vol; + + asize = le32_to_cpu(attr->size); + used = le32_to_cpu(rec->used); + + if (lrh->redo_len == lrh->undo_len) { + if (nsize > asize) + goto dirty_vol; + goto move_data; + } + + if (nsize > asize && nsize - asize > record_size - used) + goto dirty_vol; + + nsize = QuadAlign(nsize); + data_off = le16_to_cpu(attr->res.data_off); + + if (nsize < asize) { + memmove(Add2Ptr(attr, t16), data, dlen); + data = NULL; // To skip below memmove + } + + memmove(Add2Ptr(attr, nsize), Add2Ptr(attr, asize), + used - le16_to_cpu(lrh->record_off) - asize); + + rec->used = cpu_to_le32(used + nsize - asize); + attr->size = cpu_to_le32(nsize); + attr->res.data_size = cpu_to_le32(t16 + dlen - data_off); + +move_data: + if (data) + memmove(Add2Ptr(attr, t16), data, dlen); + + oa2 = find_loaded_attr(log, attr, rno_base); + if (oa2) { + void *p2 = ntfs_memdup(attr, le32_to_cpu(attr->size)); + + if (p2) { + // run_close(&oa2->run0); + oa2->run1 = &oa2->run0; + ntfs_free(oa2->attr); + oa2->attr = p2; + } + } + + mi->dirty = true; + break; + + case UpdateMappingPairs: + t16 = le16_to_cpu(lrh->attr_off); + nsize = t16 + dlen; + asize = le32_to_cpu(attr->size); + used = le32_to_cpu(rec->used); + + if (!check_if_attr(rec, lrh) || !attr->non_res || + t16 < le16_to_cpu(attr->nres.run_off) || t16 > asize || + (nsize > asize && nsize - asize > record_size - used)) { + goto dirty_vol; + } + + nsize = QuadAlign(nsize); + + memmove(Add2Ptr(attr, nsize), Add2Ptr(attr, asize), + used - le16_to_cpu(lrh->record_off) - asize); + rec->used = cpu_to_le32(used + nsize - asize); + attr->size = cpu_to_le32(nsize); + memmove(Add2Ptr(attr, t16), data, dlen); + + if (run_get_highest_vcn(le64_to_cpu(attr->nres.svcn), + attr_run(attr), &t64)) { + goto dirty_vol; + } + + attr->nres.evcn = cpu_to_le64(t64); + oa2 = find_loaded_attr(log, attr, rno_base); + if (oa2 && oa2->attr->non_res) + oa2->attr->nres.evcn = attr->nres.evcn; + + mi->dirty = true; + break; + + case SetNewAttributeSizes: + new_sz = data; + + if (!check_if_attr(rec, lrh) || !attr->non_res) + goto dirty_vol; + + attr->nres.alloc_size = new_sz->alloc_size; + attr->nres.data_size = new_sz->data_size; + attr->nres.valid_size = new_sz->valid_size; + + if (dlen >= sizeof(struct NEW_ATTRIBUTE_SIZES)) + attr->nres.total_size = new_sz->total_size; + + oa2 = find_loaded_attr(log, attr, rno_base); + if (oa2) { + void *p2 = ntfs_memdup(attr, le32_to_cpu(attr->size)); + + if (p2) { + ntfs_free(oa2->attr); + oa2->attr = p2; + } + } + mi->dirty = true; + break; + + case AddIndexEntryRoot: + e = (struct NTFS_DE *)data; + esize = le16_to_cpu(e->size); + root = resident_data(attr); + hdr = &root->ihdr; + used = le32_to_cpu(hdr->used); + + if (!check_if_index_root(rec, lrh) || + !check_if_root_index(attr, hdr, lrh) || + Add2Ptr(data, esize) > Add2Ptr(lrh, rec_len) || + esize > le32_to_cpu(rec->total) - le32_to_cpu(rec->used)) { + goto dirty_vol; + } + + e1 = Add2Ptr(attr, le16_to_cpu(lrh->attr_off)); + + change_attr_size(rec, attr, le32_to_cpu(attr->size) + esize); + + memmove(Add2Ptr(e1, esize), e1, + PtrOffset(e1, Add2Ptr(hdr, used))); + memmove(e1, e, esize); + + le32_add_cpu(&attr->res.data_size, esize); + hdr->used = cpu_to_le32(used + esize); + le32_add_cpu(&hdr->total, esize); + + mi->dirty = true; + break; + + case DeleteIndexEntryRoot: + root = resident_data(attr); + hdr = &root->ihdr; + used = le32_to_cpu(hdr->used); + + if (!check_if_index_root(rec, lrh) || + !check_if_root_index(attr, hdr, lrh)) { + goto dirty_vol; + } + + e1 = Add2Ptr(attr, le16_to_cpu(lrh->attr_off)); + esize = le16_to_cpu(e1->size); + e2 = Add2Ptr(e1, esize); + + memmove(e1, e2, PtrOffset(e2, Add2Ptr(hdr, used))); + + le32_sub_cpu(&attr->res.data_size, esize); + hdr->used = cpu_to_le32(used - esize); + le32_sub_cpu(&hdr->total, esize); + + change_attr_size(rec, attr, le32_to_cpu(attr->size) - esize); + + mi->dirty = true; + break; + + case SetIndexEntryVcnRoot: + root = resident_data(attr); + hdr = &root->ihdr; + + if (!check_if_index_root(rec, lrh) || + !check_if_root_index(attr, hdr, lrh)) { + goto dirty_vol; + } + + e = Add2Ptr(attr, le16_to_cpu(lrh->attr_off)); + + de_set_vbn_le(e, *(__le64 *)data); + mi->dirty = true; + break; + + case UpdateFileNameRoot: + root = resident_data(attr); + hdr = &root->ihdr; + + if (!check_if_index_root(rec, lrh) || + !check_if_root_index(attr, hdr, lrh)) { + goto dirty_vol; + } + + e = Add2Ptr(attr, le16_to_cpu(lrh->attr_off)); + fname = (struct ATTR_FILE_NAME *)(e + 1); + memmove(&fname->dup, data, sizeof(fname->dup)); // + mi->dirty = true; + break; + + case UpdateRecordDataRoot: + root = resident_data(attr); + hdr = &root->ihdr; + + if (!check_if_index_root(rec, lrh) || + !check_if_root_index(attr, hdr, lrh)) { + goto dirty_vol; + } + + e = Add2Ptr(attr, le16_to_cpu(lrh->attr_off)); + + memmove(Add2Ptr(e, le16_to_cpu(e->view.data_off)), data, dlen); + + mi->dirty = true; + break; + + case ZeroEndOfFileRecord: + t16 = le16_to_cpu(lrh->record_off); + if (t16 + dlen > record_size) + goto dirty_vol; + + memset(attr, 0, dlen); + mi->dirty = true; + break; + + case UpdateNonresidentValue: + t16 = le16_to_cpu(lrh->record_off); + + if (lco < cbo + t16 + dlen) + goto dirty_vol; + + memcpy(Add2Ptr(buffer_le, t16), data, dlen); + + a_dirty = true; + if (attr->type == ATTR_ALLOC) + ntfs_fix_pre_write(buffer_le, bytes); + break; + + case AddIndexEntryAllocation: + t16 = le16_to_cpu(lrh->record_off); + ib = Add2Ptr(buffer_le, t16); + hdr = &ib->ihdr; + e = data; + esize = le16_to_cpu(e->size); + t16 = le16_to_cpu(lrh->attr_off); + e1 = Add2Ptr(ib, t16); + + if (is_baad(&ib->rhdr)) + goto dirty_vol; + if (!check_lsn(&ib->rhdr, rlsn)) + goto out; + + used = le32_to_cpu(hdr->used); + + if (!check_index_buffer(ib, bytes) || + !check_if_alloc_index(hdr, t16) || + Add2Ptr(e, esize) > Add2Ptr(lrh, rec_len) || + used + esize > le32_to_cpu(hdr->total)) { + goto dirty_vol; + } + + memmove(Add2Ptr(e1, esize), e1, + PtrOffset(e1, Add2Ptr(hdr, used))); + memcpy(e1, e, esize); + + hdr->used = cpu_to_le32(used + esize); + + a_dirty = true; + + ntfs_fix_pre_write(&ib->rhdr, bytes); + break; + + case DeleteIndexEntryAllocation: + t16 = le16_to_cpu(lrh->record_off); + ib = Add2Ptr(buffer_le, t16); + hdr = &ib->ihdr; + t16 = le16_to_cpu(lrh->attr_off); + e = Add2Ptr(ib, t16); + esize = le16_to_cpu(e->size); + + if (is_baad(&ib->rhdr)) + goto dirty_vol; + if (!check_lsn(&ib->rhdr, rlsn)) + goto out; + + if (!check_index_buffer(ib, bytes) || + !check_if_alloc_index(hdr, t16)) { + goto dirty_vol; + } + + e1 = Add2Ptr(e, esize); + nsize = esize; + used = le32_to_cpu(hdr->used); + + memmove(e, e1, PtrOffset(e1, Add2Ptr(hdr, used))); + + hdr->used = cpu_to_le32(used - nsize); + + a_dirty = true; + + ntfs_fix_pre_write(&ib->rhdr, bytes); + break; + + case WriteEndOfIndexBuffer: + t16 = le16_to_cpu(lrh->record_off); + ib = Add2Ptr(buffer_le, t16); + hdr = &ib->ihdr; + t16 = le16_to_cpu(lrh->attr_off); + e = Add2Ptr(ib, t16); + + if (is_baad(&ib->rhdr)) + goto dirty_vol; + if (!check_lsn(&ib->rhdr, rlsn)) + goto out; + if (!check_index_buffer(ib, bytes) || + !check_if_alloc_index(hdr, t16) || + t16 + dlen > offsetof(struct INDEX_BUFFER, ihdr) + + le32_to_cpu(hdr->total)) { + goto dirty_vol; + } + + hdr->used = cpu_to_le32(dlen + PtrOffset(hdr, e)); + memmove(e, data, dlen); + + a_dirty = true; + ntfs_fix_pre_write(&ib->rhdr, bytes); + break; + + case SetIndexEntryVcnAllocation: + t16 = le16_to_cpu(lrh->record_off); + ib = Add2Ptr(buffer_le, t16); + hdr = &ib->ihdr; + t16 = le16_to_cpu(lrh->attr_off); + e = Add2Ptr(ib, t16); + + if (is_baad(&ib->rhdr)) + goto dirty_vol; + + if (!check_lsn(&ib->rhdr, rlsn)) + goto out; + if (!check_index_buffer(ib, bytes) || + !check_if_alloc_index(hdr, t16)) { + goto dirty_vol; + } + + de_set_vbn_le(e, *(__le64 *)data); + + a_dirty = true; + ntfs_fix_pre_write(&ib->rhdr, bytes); + break; + + case UpdateFileNameAllocation: + t16 = le16_to_cpu(lrh->record_off); + ib = Add2Ptr(buffer_le, t16); + hdr = &ib->ihdr; + t16 = le16_to_cpu(lrh->attr_off); + e = Add2Ptr(ib, t16); + + if (is_baad(&ib->rhdr)) + goto dirty_vol; + + if (!check_lsn(&ib->rhdr, rlsn)) + goto out; + if (!check_index_buffer(ib, bytes) || + !check_if_alloc_index(hdr, t16)) { + goto dirty_vol; + } + + fname = (struct ATTR_FILE_NAME *)(e + 1); + memmove(&fname->dup, data, sizeof(fname->dup)); + + a_dirty = true; + ntfs_fix_pre_write(&ib->rhdr, bytes); + break; + + case SetBitsInNonresidentBitMap: + bmp_off = + le32_to_cpu(((struct BITMAP_RANGE *)data)->bitmap_off); + bmp_bits = le32_to_cpu(((struct BITMAP_RANGE *)data)->bits); + t16 = le16_to_cpu(lrh->record_off); + + if (cbo + (bmp_off + 7) / 8 > lco || + cbo + ((bmp_off + bmp_bits + 7) / 8) > lco) { + goto dirty_vol; + } + + __bitmap_set(Add2Ptr(buffer_le, t16), bmp_off, bmp_bits); + a_dirty = true; + break; + + case ClearBitsInNonresidentBitMap: + bmp_off = + le32_to_cpu(((struct BITMAP_RANGE *)data)->bitmap_off); + bmp_bits = le32_to_cpu(((struct BITMAP_RANGE *)data)->bits); + t16 = le16_to_cpu(lrh->record_off); + + if (cbo + (bmp_off + 7) / 8 > lco || + cbo + ((bmp_off + bmp_bits + 7) / 8) > lco) { + goto dirty_vol; + } + + __bitmap_clear(Add2Ptr(buffer_le, t16), bmp_off, bmp_bits); + a_dirty = true; + break; + + case UpdateRecordDataAllocation: + t16 = le16_to_cpu(lrh->record_off); + ib = Add2Ptr(buffer_le, t16); + hdr = &ib->ihdr; + t16 = le16_to_cpu(lrh->attr_off); + e = Add2Ptr(ib, t16); + + if (is_baad(&ib->rhdr)) + goto dirty_vol; + + if (!check_lsn(&ib->rhdr, rlsn)) + goto out; + if (!check_index_buffer(ib, bytes) || + !check_if_alloc_index(hdr, t16)) { + goto dirty_vol; + } + + memmove(Add2Ptr(e, le16_to_cpu(e->view.data_off)), data, dlen); + + a_dirty = true; + ntfs_fix_pre_write(&ib->rhdr, bytes); + break; + + default: + WARN_ON(1); + } + + if (rlsn) { + __le64 t64 = cpu_to_le64(*rlsn); + + if (rec) + rec->rhdr.lsn = t64; + if (ib) + ib->rhdr.lsn = t64; + } + + if (inode) { + err = _ni_write_inode(inode, 0); + } else if (mi && mi->dirty) { + err = mi_write(mi, 0); + if (err) + goto out; + } + + if (a_dirty) { + attr = oa->attr; + err = ntfs_sb_write_run(sbi, oa->run1, vbo, buffer_le, bytes); + if (err) + goto out; + } + +out: + + if (inode) + iput(inode); + else if (mi != mi2_child) + mi_put(mi); + + ntfs_free(buffer_le); + + return err; + +dirty_vol: + log->set_dirty = true; + goto out; +} + +/* + * log_replay + * + * this function is called during mount operation + * it replays log and empties it + */ +int log_replay(struct ntfs_inode *ni) +{ + int err; + struct ntfs_sb_info *sbi = ni->mi.sbi; + struct ntfs_log *log; + + struct restart_info rst_info, rst_info2; + u64 rec_lsn, ra_lsn, checkpt_lsn = 0, rlsn = 0; + struct ATTR_NAME_ENTRY *attr_names = NULL; + struct ATTR_NAME_ENTRY *ane; + struct RESTART_TABLE *dptbl = NULL; + struct RESTART_TABLE *trtbl = NULL; + const struct RESTART_TABLE *rt; + struct RESTART_TABLE *oatbl = NULL; + struct inode *inode; + struct OpenAttr *oa; + struct ntfs_inode *ni_oe; + struct ATTRIB *attr = NULL; + u64 size, vcn, undo_next_lsn; + CLST rno, lcn, lcn0, len0, clen; + void *data; + struct NTFS_RESTART *rst = NULL; + struct lcb *lcb = NULL; + struct OPEN_ATTR_ENRTY *oe; + struct TRANSACTION_ENTRY *tr; + struct DIR_PAGE_ENTRY *dp; + u32 i, bytes_per_attr_entry; + u32 l_size = ni->vfs_inode.i_size; + u32 orig_file_size = l_size; + u32 page_size, vbo, tail, off, dlen; + u32 saved_len, rec_len, transact_id; + bool use_second_page; + struct RESTART_AREA *ra2, *ra = NULL; + struct CLIENT_REC *ca, *cr; + __le16 client; + struct RESTART_HDR *rh; + const struct LFS_RECORD_HDR *frh; + const struct LOG_REC_HDR *lrh; + bool is_mapped; + bool is_ro = sb_rdonly(sbi->sb); + u64 t64; + u16 t16; + u32 t32; + + /* Get the size of page. NOTE: To replay we can use default page */ + page_size = norm_file_page(PAGE_SIZE, &l_size, + PAGE_SIZE >= DefaultLogPageSize && + PAGE_SIZE <= DefaultLogPageSize * 2); + if (!page_size) + return -EINVAL; + + log = ntfs_alloc(sizeof(struct ntfs_log), 1); + if (!log) + return -ENOMEM; + + log->ni = ni; + log->l_size = l_size; + log->one_page_buf = ntfs_alloc(page_size, 0); + + if (!log->one_page_buf) { + err = -ENOMEM; + goto out; + } + + log->page_size = page_size; + log->page_mask = page_size - 1; + log->page_bits = blksize_bits(page_size); + + /* Look for a restart area on the disk */ + err = log_read_rst(log, l_size, true, &rst_info); + if (err) + goto out; + + if (!rst_info.restart) { + if (rst_info.initialized) { + /* no restart area but the file is not initialized */ + err = -EINVAL; + goto out; + } + + log_init_pg_hdr(log, page_size, page_size, 1, 1); + log_create(log, l_size, 0, get_random_int(), false, false); + + log->ra = ra; + + ra = log_create_ra(log); + if (!ra) { + err = -ENOMEM; + goto out; + } + log->ra = ra; + log->init_ra = true; + + goto process_log; + } + + /* + * If the restart offset above wasn't zero then we won't + * look for a second restart + */ + if (rst_info.vbo) + goto check_restart_area; + + err = log_read_rst(log, l_size, false, &rst_info2); + + /* Determine which restart area to use */ + if (!rst_info2.restart || rst_info2.last_lsn <= rst_info.last_lsn) + goto use_first_page; + + use_second_page = true; + + if (rst_info.chkdsk_was_run && page_size != rst_info.vbo) { + struct RECORD_PAGE_HDR *sp = NULL; + + if (!read_log_page(log, page_size, &sp, true, true, NULL) && + sp->rhdr.sign == NTFS_CHKD_SIGNATURE) { + use_second_page = false; + } + ntfs_free(sp); + } + + if (use_second_page) { + ntfs_free(rst_info.r_page); + memcpy(&rst_info, &rst_info2, sizeof(struct restart_info)); + rst_info2.r_page = NULL; + } + +use_first_page: + ntfs_free(rst_info2.r_page); + +check_restart_area: + /* If the restart area is at offset 0, we want to write the second restart area first */ + log->init_ra = !!rst_info.vbo; + + /* If we have a valid page then grab a pointer to the restart area */ + ra2 = rst_info.valid_page ? + Add2Ptr(rst_info.r_page, + le16_to_cpu(rst_info.r_page->ra_off)) : + NULL; + + if (rst_info.chkdsk_was_run || + (ra2 && ra2->client_idx[1] == LFS_NO_CLIENT_LE)) { + bool wrapped = false; + bool use_multi_page = false; + u32 open_log_count; + + /* Do some checks based on whether we have a valid log page */ + if (!rst_info.valid_page) { + open_log_count = get_random_int(); + goto init_log_instance; + } + open_log_count = le32_to_cpu(ra2->open_log_count); + + /* + * If the restart page size isn't changing then we want to + * check how much work we need to do + */ + if (page_size != le32_to_cpu(rst_info.r_page->sys_page_size)) + goto init_log_instance; + +init_log_instance: + log_init_pg_hdr(log, page_size, page_size, 1, 1); + + log_create(log, l_size, rst_info.last_lsn, open_log_count, + wrapped, use_multi_page); + + ra = log_create_ra(log); + if (!ra) { + err = -ENOMEM; + goto out; + } + log->ra = ra; + + /* Put the restart areas and initialize the log file as required */ + goto process_log; + } + + if (!ra2) { + err = -EINVAL; + goto out; + } + + /* + * If the log page or the system page sizes have changed, we can't use the log file + * We must use the system page size instead of the default size + * if there is not a clean shutdown + */ + t32 = le32_to_cpu(rst_info.r_page->sys_page_size); + if (page_size != t32) { + l_size = orig_file_size; + page_size = + norm_file_page(t32, &l_size, t32 == DefaultLogPageSize); + } + + if (page_size != t32 || + page_size != le32_to_cpu(rst_info.r_page->page_size)) { + err = -EINVAL; + goto out; + } + + /* If the file size has shrunk then we won't mount it */ + if (l_size < le64_to_cpu(ra2->l_size)) { + err = -EINVAL; + goto out; + } + + log_init_pg_hdr(log, page_size, page_size, + le16_to_cpu(rst_info.r_page->major_ver), + le16_to_cpu(rst_info.r_page->minor_ver)); + + log->l_size = le64_to_cpu(ra2->l_size); + log->seq_num_bits = le32_to_cpu(ra2->seq_num_bits); + log->file_data_bits = sizeof(u64) * 8 - log->seq_num_bits; + log->seq_num_mask = (8 << log->file_data_bits) - 1; + log->last_lsn = le64_to_cpu(ra2->current_lsn); + log->seq_num = log->last_lsn >> log->file_data_bits; + log->ra_off = le16_to_cpu(rst_info.r_page->ra_off); + log->restart_size = log->sys_page_size - log->ra_off; + log->record_header_len = le16_to_cpu(ra2->rec_hdr_len); + log->ra_size = le16_to_cpu(ra2->ra_len); + log->data_off = le16_to_cpu(ra2->data_off); + log->data_size = log->page_size - log->data_off; + log->reserved = log->data_size - log->record_header_len; + + vbo = lsn_to_vbo(log, log->last_lsn); + + if (vbo < log->first_page) { + /* This is a pseudo lsn */ + log->l_flags |= NTFSLOG_NO_LAST_LSN; + log->next_page = log->first_page; + goto find_oldest; + } + + /* Find the end of this log record */ + off = final_log_off(log, log->last_lsn, + le32_to_cpu(ra2->last_lsn_data_len)); + + /* If we wrapped the file then increment the sequence number */ + if (off <= vbo) { + log->seq_num += 1; + log->l_flags |= NTFSLOG_WRAPPED; + } + + /* Now compute the next log page to use */ + vbo &= ~log->sys_page_mask; + tail = log->page_size - (off & log->page_mask) - 1; + + /* If we can fit another log record on the page, move back a page the log file */ + if (tail >= log->record_header_len) { + log->l_flags |= NTFSLOG_REUSE_TAIL; + log->next_page = vbo; + } else { + log->next_page = next_page_off(log, vbo); + } + +find_oldest: + /* Find the oldest client lsn. Use the last flushed lsn as a starting point */ + log->oldest_lsn = log->last_lsn; + oldest_client_lsn(Add2Ptr(ra2, le16_to_cpu(ra2->client_off)), + ra2->client_idx[1], &log->oldest_lsn); + log->oldest_lsn_off = lsn_to_vbo(log, log->oldest_lsn); + + if (log->oldest_lsn_off < log->first_page) + log->l_flags |= NTFSLOG_NO_OLDEST_LSN; + + if (!(ra2->flags & RESTART_SINGLE_PAGE_IO)) + log->l_flags |= NTFSLOG_WRAPPED | NTFSLOG_MULTIPLE_PAGE_IO; + + log->current_openlog_count = le32_to_cpu(ra2->open_log_count); + log->total_avail_pages = log->l_size - log->first_page; + log->total_avail = log->total_avail_pages >> log->page_bits; + log->max_current_avail = log->total_avail * log->reserved; + log->total_avail = log->total_avail * log->data_size; + + log->current_avail = current_log_avail(log); + + ra = ntfs_alloc(log->restart_size, 1); + if (!ra) { + err = -ENOMEM; + goto out; + } + log->ra = ra; + + t16 = le16_to_cpu(ra2->client_off); + if (t16 == offsetof(struct RESTART_AREA, clients)) { + memcpy(ra, ra2, log->ra_size); + } else { + memcpy(ra, ra2, offsetof(struct RESTART_AREA, clients)); + memcpy(ra->clients, Add2Ptr(ra2, t16), + le16_to_cpu(ra2->ra_len) - t16); + + log->current_openlog_count = get_random_int(); + ra->open_log_count = cpu_to_le32(log->current_openlog_count); + log->ra_size = offsetof(struct RESTART_AREA, clients) + + sizeof(struct CLIENT_REC); + ra->client_off = + cpu_to_le16(offsetof(struct RESTART_AREA, clients)); + ra->ra_len = cpu_to_le16(log->ra_size); + } + + le32_add_cpu(&ra->open_log_count, 1); + + /* Now we need to walk through looking for the last lsn */ + err = last_log_lsn(log); + if (err == -EROFS) + goto out; + + if (err) + goto out; + + log->current_avail = current_log_avail(log); + + /* Remember which restart area to write first */ + log->init_ra = rst_info.vbo; + +process_log: + + /* 1.0, 1.1, 2.0 log->major_ver/minor_ver - short values */ + switch ((log->major_ver << 16) + log->minor_ver) { + case 0x10000: + case 0x10001: + case 0x20000: + break; + default: + ntfs_warn(sbi->sb, "$LogFile version %d.%d is not supported", + log->major_ver, log->minor_ver); + err = -EOPNOTSUPP; + log->set_dirty = true; + goto out; + } + + /* One client "NTFS" per logfile */ + ca = Add2Ptr(ra, le16_to_cpu(ra->client_off)); + + for (client = ra->client_idx[1];; client = cr->next_client) { + if (client == LFS_NO_CLIENT_LE) { + /* Insert "NTFS" client LogFile */ + client = ra->client_idx[0]; + if (client == LFS_NO_CLIENT_LE) + return -EINVAL; + + t16 = le16_to_cpu(client); + cr = ca + t16; + + remove_client(ca, cr, &ra->client_idx[0]); + + cr->restart_lsn = 0; + cr->oldest_lsn = cpu_to_le64(log->oldest_lsn); + cr->name_bytes = cpu_to_le32(8); + cr->name[0] = cpu_to_le16('N'); + cr->name[1] = cpu_to_le16('T'); + cr->name[2] = cpu_to_le16('F'); + cr->name[3] = cpu_to_le16('S'); + + add_client(ca, t16, &ra->client_idx[1]); + break; + } + + cr = ca + le16_to_cpu(client); + + if (cpu_to_le32(8) == cr->name_bytes && + cpu_to_le16('N') == cr->name[0] && + cpu_to_le16('T') == cr->name[1] && + cpu_to_le16('F') == cr->name[2] && + cpu_to_le16('S') == cr->name[3]) + break; + } + + /* Update the client handle with the client block information */ + log->client_id.seq_num = cr->seq_num; + log->client_id.client_idx = client; + + err = read_rst_area(log, &rst, &ra_lsn); + if (err) + goto out; + + if (!rst) + goto out; + + bytes_per_attr_entry = !rst->major_ver ? 0x2C : 0x28; + + checkpt_lsn = le64_to_cpu(rst->check_point_start); + if (!checkpt_lsn) + checkpt_lsn = ra_lsn; + + /* Allocate and Read the Transaction Table */ + if (!rst->transact_table_len) + goto check_dirty_page_table; + + t64 = le64_to_cpu(rst->transact_table_lsn); + + err = read_log_rec_lcb(log, t64, lcb_ctx_prev, &lcb); + if (err) + goto out; + + lrh = lcb->log_rec; + frh = lcb->lrh; + rec_len = le32_to_cpu(frh->client_data_len); + + if (!check_log_rec(lrh, rec_len, le32_to_cpu(frh->transact_id), + bytes_per_attr_entry)) { + err = -EINVAL; + goto out; + } + + t16 = le16_to_cpu(lrh->redo_off); + + rt = Add2Ptr(lrh, t16); + t32 = rec_len - t16; + + /* Now check that this is a valid restart table */ + if (!check_rstbl(rt, t32)) { + err = -EINVAL; + goto out; + } + + trtbl = ntfs_memdup(rt, t32); + if (!trtbl) { + err = -ENOMEM; + goto out; + } + + lcb_put(lcb); + lcb = NULL; + +check_dirty_page_table: + /* The next record back should be the Dirty Pages Table */ + if (!rst->dirty_pages_len) + goto check_attribute_names; + + t64 = le64_to_cpu(rst->dirty_pages_table_lsn); + + err = read_log_rec_lcb(log, t64, lcb_ctx_prev, &lcb); + if (err) + goto out; + + lrh = lcb->log_rec; + frh = lcb->lrh; + rec_len = le32_to_cpu(frh->client_data_len); + + if (!check_log_rec(lrh, rec_len, le32_to_cpu(frh->transact_id), + bytes_per_attr_entry)) { + err = -EINVAL; + goto out; + } + + t16 = le16_to_cpu(lrh->redo_off); + + rt = Add2Ptr(lrh, t16); + t32 = rec_len - t16; + + /* Now check that this is a valid restart table */ + if (!check_rstbl(rt, t32)) { + err = -EINVAL; + goto out; + } + + dptbl = ntfs_memdup(rt, t32); + if (!dptbl) { + err = -ENOMEM; + goto out; + } + + /* Convert Ra version '0' into version '1' */ + if (rst->major_ver) + goto end_conv_1; + + dp = NULL; + while ((dp = enum_rstbl(dptbl, dp))) { + struct DIR_PAGE_ENTRY_32 *dp0 = (struct DIR_PAGE_ENTRY_32 *)dp; + // NOTE: Danger. Check for of boundary + memmove(&dp->vcn, &dp0->vcn_low, + 2 * sizeof(u64) + + le32_to_cpu(dp->lcns_follow) * sizeof(u64)); + } + +end_conv_1: + lcb_put(lcb); + lcb = NULL; + + /* Go through the table and remove the duplicates, remembering the oldest lsn values */ + if (sbi->cluster_size <= log->page_size) + goto trace_dp_table; + + dp = NULL; + while ((dp = enum_rstbl(dptbl, dp))) { + struct DIR_PAGE_ENTRY *next = dp; + + while ((next = enum_rstbl(dptbl, next))) { + if (next->target_attr == dp->target_attr && + next->vcn == dp->vcn) { + if (le64_to_cpu(next->oldest_lsn) < + le64_to_cpu(dp->oldest_lsn)) { + dp->oldest_lsn = next->oldest_lsn; + } + + free_rsttbl_idx(dptbl, PtrOffset(dptbl, next)); + } + } + } +trace_dp_table: + +check_attribute_names: + /* The next record should be the Attribute Names */ + if (!rst->attr_names_len) + goto check_attr_table; + + t64 = le64_to_cpu(rst->attr_names_lsn); + + err = read_log_rec_lcb(log, t64, lcb_ctx_prev, &lcb); + if (err) + goto out; + + lrh = lcb->log_rec; + frh = lcb->lrh; + rec_len = le32_to_cpu(frh->client_data_len); + + if (!check_log_rec(lrh, rec_len, le32_to_cpu(frh->transact_id), + bytes_per_attr_entry)) { + err = -EINVAL; + goto out; + } + + t32 = lrh_length(lrh); + rec_len -= t32; + + attr_names = ntfs_memdup(Add2Ptr(lrh, t32), rec_len); + + lcb_put(lcb); + lcb = NULL; + +check_attr_table: + /* The next record should be the attribute Table */ + if (!rst->open_attr_len) + goto check_attribute_names2; + + t64 = le64_to_cpu(rst->open_attr_table_lsn); + + err = read_log_rec_lcb(log, t64, lcb_ctx_prev, &lcb); + if (err) + goto out; + + lrh = lcb->log_rec; + frh = lcb->lrh; + rec_len = le32_to_cpu(frh->client_data_len); + + if (!check_log_rec(lrh, rec_len, le32_to_cpu(frh->transact_id), + bytes_per_attr_entry)) { + err = -EINVAL; + goto out; + } + + t16 = le16_to_cpu(lrh->redo_off); + + rt = Add2Ptr(lrh, t16); + t32 = rec_len - t16; + + if (!check_rstbl(rt, t32)) { + err = -EINVAL; + goto out; + } + + oatbl = ntfs_memdup(rt, t32); + if (!oatbl) { + err = -ENOMEM; + goto out; + } + + log->open_attr_tbl = oatbl; + + /* Clear all of the Attr pointers */ + oe = NULL; + while ((oe = enum_rstbl(oatbl, oe))) { + if (!rst->major_ver) { + struct OPEN_ATTR_ENRTY_32 oe0; + + /* Really 'oe' points to OPEN_ATTR_ENRTY_32 */ + memcpy(&oe0, oe, SIZEOF_OPENATTRIBUTEENTRY0); + + oe->bytes_per_index = oe0.bytes_per_index; + oe->type = oe0.type; + oe->is_dirty_pages = oe0.is_dirty_pages; + oe->name_len = 0; + oe->ref = oe0.ref; + oe->open_record_lsn = oe0.open_record_lsn; + } + + oe->is_attr_name = 0; + oe->ptr = NULL; + } + + lcb_put(lcb); + lcb = NULL; + +check_attribute_names2: + if (!rst->attr_names_len) + goto trace_attribute_table; + + ane = attr_names; + if (!oatbl) + goto trace_attribute_table; + while (ane->off) { + /* TODO: Clear table on exit! */ + oe = Add2Ptr(oatbl, le16_to_cpu(ane->off)); + t16 = le16_to_cpu(ane->name_bytes); + oe->name_len = t16 / sizeof(short); + oe->ptr = ane->name; + oe->is_attr_name = 2; + ane = Add2Ptr(ane, sizeof(struct ATTR_NAME_ENTRY) + t16); + } + +trace_attribute_table: + /* + * If the checkpt_lsn is zero, then this is a freshly + * formatted disk and we have no work to do + */ + if (!checkpt_lsn) { + err = 0; + goto out; + } + + if (!oatbl) { + oatbl = init_rsttbl(bytes_per_attr_entry, 8); + if (!oatbl) { + err = -ENOMEM; + goto out; + } + } + + log->open_attr_tbl = oatbl; + + /* Start the analysis pass from the Checkpoint lsn. */ + rec_lsn = checkpt_lsn; + + /* Read the first lsn */ + err = read_log_rec_lcb(log, checkpt_lsn, lcb_ctx_next, &lcb); + if (err) + goto out; + + /* Loop to read all subsequent records to the end of the log file */ +next_log_record_analyze: + err = read_next_log_rec(log, lcb, &rec_lsn); + if (err) + goto out; + + if (!rec_lsn) + goto end_log_records_enumerate; + + frh = lcb->lrh; + transact_id = le32_to_cpu(frh->transact_id); + rec_len = le32_to_cpu(frh->client_data_len); + lrh = lcb->log_rec; + + if (!check_log_rec(lrh, rec_len, transact_id, bytes_per_attr_entry)) { + err = -EINVAL; + goto out; + } + + /* + * The first lsn after the previous lsn remembered + * the checkpoint is the first candidate for the rlsn + */ + if (!rlsn) + rlsn = rec_lsn; + + if (LfsClientRecord != frh->record_type) + goto next_log_record_analyze; + + /* + * Now update the Transaction Table for this transaction + * If there is no entry present or it is unallocated we allocate the entry + */ + if (!trtbl) { + trtbl = init_rsttbl(sizeof(struct TRANSACTION_ENTRY), + INITIAL_NUMBER_TRANSACTIONS); + if (!trtbl) { + err = -ENOMEM; + goto out; + } + } + + tr = Add2Ptr(trtbl, transact_id); + + if (transact_id >= bytes_per_rt(trtbl) || + tr->next != RESTART_ENTRY_ALLOCATED_LE) { + tr = alloc_rsttbl_from_idx(&trtbl, transact_id); + if (!tr) { + err = -ENOMEM; + goto out; + } + tr->transact_state = TransactionActive; + tr->first_lsn = cpu_to_le64(rec_lsn); + } + + tr->prev_lsn = tr->undo_next_lsn = cpu_to_le64(rec_lsn); + + /* + * If this is a compensation log record, then change + * the undo_next_lsn to be the undo_next_lsn of this record + */ + if (lrh->undo_op == cpu_to_le16(CompensationLogRecord)) + tr->undo_next_lsn = frh->client_undo_next_lsn; + + /* Dispatch to handle log record depending on type */ + switch (le16_to_cpu(lrh->redo_op)) { + case InitializeFileRecordSegment: + case DeallocateFileRecordSegment: + case WriteEndOfFileRecordSegment: + case CreateAttribute: + case DeleteAttribute: + case UpdateResidentValue: + case UpdateNonresidentValue: + case UpdateMappingPairs: + case SetNewAttributeSizes: + case AddIndexEntryRoot: + case DeleteIndexEntryRoot: + case AddIndexEntryAllocation: + case DeleteIndexEntryAllocation: + case WriteEndOfIndexBuffer: + case SetIndexEntryVcnRoot: + case SetIndexEntryVcnAllocation: + case UpdateFileNameRoot: + case UpdateFileNameAllocation: + case SetBitsInNonresidentBitMap: + case ClearBitsInNonresidentBitMap: + case UpdateRecordDataRoot: + case UpdateRecordDataAllocation: + case ZeroEndOfFileRecord: + t16 = le16_to_cpu(lrh->target_attr); + t64 = le64_to_cpu(lrh->target_vcn); + dp = find_dp(dptbl, t16, t64); + + if (dp) + goto copy_lcns; + + /* + * Calculate the number of clusters per page the system + * which wrote the checkpoint, possibly creating the table + */ + if (dptbl) { + t32 = 1 + (le16_to_cpu(dptbl->size) - + sizeof(struct DIR_PAGE_ENTRY)) / + sizeof(u64); + } else { + t32 = log->clst_per_page; + ntfs_free(dptbl); + dptbl = init_rsttbl(sizeof(struct DIR_PAGE_ENTRY) + + (t32 - 1) * sizeof(u64), + 32); + if (!dptbl) { + err = -ENOMEM; + goto out; + } + } + + dp = alloc_rsttbl_idx(&dptbl); + dp->target_attr = cpu_to_le32(t16); + dp->transfer_len = cpu_to_le32(t32 << sbi->cluster_bits); + dp->lcns_follow = cpu_to_le32(t32); + dp->vcn = cpu_to_le64(t64 & ~((u64)t32 - 1)); + dp->oldest_lsn = cpu_to_le64(rec_lsn); + +copy_lcns: + /* + * Copy the Lcns from the log record into the Dirty Page Entry + * TODO: for different page size support, must somehow make + * whole routine a loop, case Lcns do not fit below + */ + t16 = le16_to_cpu(lrh->lcns_follow); + for (i = 0; i < t16; i++) { + size_t j = (size_t)(le64_to_cpu(lrh->target_vcn) - + le64_to_cpu(dp->vcn)); + dp->page_lcns[j + i] = lrh->page_lcns[i]; + } + + goto next_log_record_analyze; + + case DeleteDirtyClusters: { + u32 range_count = + le16_to_cpu(lrh->redo_len) / sizeof(struct LCN_RANGE); + const struct LCN_RANGE *r = + Add2Ptr(lrh, le16_to_cpu(lrh->redo_off)); + + /* Loop through all of the Lcn ranges this log record */ + for (i = 0; i < range_count; i++, r++) { + u64 lcn0 = le64_to_cpu(r->lcn); + u64 lcn_e = lcn0 + le64_to_cpu(r->len) - 1; + + dp = NULL; + while ((dp = enum_rstbl(dptbl, dp))) { + u32 j; + + t32 = le32_to_cpu(dp->lcns_follow); + for (j = 0; j < t32; j++) { + t64 = le64_to_cpu(dp->page_lcns[j]); + if (t64 >= lcn0 && t64 <= lcn_e) + dp->page_lcns[j] = 0; + } + } + } + goto next_log_record_analyze; + ; + } + + case OpenNonresidentAttribute: + t16 = le16_to_cpu(lrh->target_attr); + if (t16 >= bytes_per_rt(oatbl)) { + /* + * Compute how big the table needs to be. + * Add 10 extra entries for some cushion + */ + u32 new_e = t16 / le16_to_cpu(oatbl->size); + + new_e += 10 - le16_to_cpu(oatbl->used); + + oatbl = extend_rsttbl(oatbl, new_e, ~0u); + log->open_attr_tbl = oatbl; + if (!oatbl) { + err = -ENOMEM; + goto out; + } + } + + /* Point to the entry being opened */ + oe = alloc_rsttbl_from_idx(&oatbl, t16); + log->open_attr_tbl = oatbl; + if (!oe) { + err = -ENOMEM; + goto out; + } + + /* Initialize this entry from the log record */ + t16 = le16_to_cpu(lrh->redo_off); + if (!rst->major_ver) { + /* Convert version '0' into version '1' */ + struct OPEN_ATTR_ENRTY_32 *oe0 = Add2Ptr(lrh, t16); + + oe->bytes_per_index = oe0->bytes_per_index; + oe->type = oe0->type; + oe->is_dirty_pages = oe0->is_dirty_pages; + oe->name_len = 0; //oe0.name_len; + oe->ref = oe0->ref; + oe->open_record_lsn = oe0->open_record_lsn; + } else { + memcpy(oe, Add2Ptr(lrh, t16), bytes_per_attr_entry); + } + + t16 = le16_to_cpu(lrh->undo_len); + if (t16) { + oe->ptr = ntfs_alloc(t16, 0); + if (!oe->ptr) { + err = -ENOMEM; + goto out; + } + oe->name_len = t16 / sizeof(short); + memcpy(oe->ptr, + Add2Ptr(lrh, le16_to_cpu(lrh->undo_off)), t16); + oe->is_attr_name = 1; + } else { + oe->ptr = NULL; + oe->is_attr_name = 0; + } + + goto next_log_record_analyze; + + case HotFix: + t16 = le16_to_cpu(lrh->target_attr); + t64 = le64_to_cpu(lrh->target_vcn); + dp = find_dp(dptbl, t16, t64); + if (dp) { + size_t j = le64_to_cpu(lrh->target_vcn) - + le64_to_cpu(dp->vcn); + if (dp->page_lcns[j]) + dp->page_lcns[j] = lrh->page_lcns[0]; + } + goto next_log_record_analyze; + + case EndTopLevelAction: + tr = Add2Ptr(trtbl, transact_id); + tr->prev_lsn = cpu_to_le64(rec_lsn); + tr->undo_next_lsn = frh->client_undo_next_lsn; + goto next_log_record_analyze; + + case PrepareTransaction: + tr = Add2Ptr(trtbl, transact_id); + tr->transact_state = TransactionPrepared; + goto next_log_record_analyze; + + case CommitTransaction: + tr = Add2Ptr(trtbl, transact_id); + tr->transact_state = TransactionCommitted; + goto next_log_record_analyze; + + case ForgetTransaction: + free_rsttbl_idx(trtbl, transact_id); + goto next_log_record_analyze; + + case Noop: + case OpenAttributeTableDump: + case AttributeNamesDump: + case DirtyPageTableDump: + case TransactionTableDump: + /* The following cases require no action the Analysis Pass */ + goto next_log_record_analyze; + + default: + goto next_log_record_analyze; + } + +end_log_records_enumerate: + lcb_put(lcb); + lcb = NULL; + + /* + * Scan the Dirty Page Table and Transaction Table for + * the lowest lsn, and return it as the Redo lsn + */ + dp = NULL; + while ((dp = enum_rstbl(dptbl, dp))) { + t64 = le64_to_cpu(dp->oldest_lsn); + if (t64 && t64 < rlsn) + rlsn = t64; + } + + tr = NULL; + while ((tr = enum_rstbl(trtbl, tr))) { + t64 = le64_to_cpu(tr->first_lsn); + if (t64 && t64 < rlsn) + rlsn = t64; + } + + /* Only proceed if the Dirty Page Table or Transaction table are not empty */ + if ((!dptbl || !dptbl->total) && (!trtbl || !trtbl->total)) + goto end_reply; + + sbi->flags |= NTFS_FLAGS_NEED_REPLAY; + if (is_ro) + goto out; + + /* Reopen all of the attributes with dirty pages */ + oe = NULL; +next_open_attribute: + + oe = enum_rstbl(oatbl, oe); + if (!oe) { + err = 0; + dp = NULL; + goto next_dirty_page; + } + + oa = ntfs_alloc(sizeof(struct OpenAttr), 1); + if (!oa) { + err = -ENOMEM; + goto out; + } + + inode = ntfs_iget5(sbi->sb, &oe->ref, NULL); + if (IS_ERR(inode)) + goto fake_attr; + + if (is_bad_inode(inode)) { + iput(inode); +fake_attr: + if (oa->ni) { + iput(&oa->ni->vfs_inode); + oa->ni = NULL; + } + + attr = attr_create_nonres_log(sbi, oe->type, 0, oe->ptr, + oe->name_len, 0); + if (!attr) { + ntfs_free(oa); + err = -ENOMEM; + goto out; + } + oa->attr = attr; + oa->run1 = &oa->run0; + goto final_oe; + } + + ni_oe = ntfs_i(inode); + oa->ni = ni_oe; + + attr = ni_find_attr(ni_oe, NULL, NULL, oe->type, oe->ptr, oe->name_len, + NULL, NULL); + + if (!attr) + goto fake_attr; + + t32 = le32_to_cpu(attr->size); + oa->attr = ntfs_memdup(attr, t32); + if (!oa->attr) + goto fake_attr; + + if (!S_ISDIR(inode->i_mode)) { + if (attr->type == ATTR_DATA && !attr->name_len) { + oa->run1 = &ni_oe->file.run; + goto final_oe; + } + } else { + if (attr->type == ATTR_ALLOC && + attr->name_len == ARRAY_SIZE(I30_NAME) && + !memcmp(attr_name(attr), I30_NAME, sizeof(I30_NAME))) { + oa->run1 = &ni_oe->dir.alloc_run; + goto final_oe; + } + } + + if (attr->non_res) { + u16 roff = le16_to_cpu(attr->nres.run_off); + + err = run_unpack(&oa->run0, sbi, inode->i_ino, + le64_to_cpu(attr->nres.svcn), + le64_to_cpu(attr->nres.evcn), + Add2Ptr(attr, roff), t32 - roff); + if (err < 0) { + ntfs_free(oa->attr); + oa->attr = NULL; + goto fake_attr; + } + err = 0; + } + oa->run1 = &oa->run0; + attr = oa->attr; + +final_oe: + if (oe->is_attr_name == 1) + ntfs_free(oe->ptr); + oe->is_attr_name = 0; + oe->ptr = oa; + oe->name_len = attr->name_len; + + goto next_open_attribute; + + /* + * Now loop through the dirty page table to extract all of the Vcn/Lcn + * Mapping that we have, and insert it into the appropriate run + */ +next_dirty_page: + dp = enum_rstbl(dptbl, dp); + if (!dp) + goto do_redo_1; + + oe = Add2Ptr(oatbl, le32_to_cpu(dp->target_attr)); + + if (oe->next != RESTART_ENTRY_ALLOCATED_LE) + goto next_dirty_page; + + oa = oe->ptr; + if (!oa) + goto next_dirty_page; + + i = -1; +next_dirty_page_vcn: + i += 1; + if (i >= le32_to_cpu(dp->lcns_follow)) + goto next_dirty_page; + + vcn = le64_to_cpu(dp->vcn) + i; + size = (vcn + 1) << sbi->cluster_bits; + + if (!dp->page_lcns[i]) + goto next_dirty_page_vcn; + + rno = ino_get(&oe->ref); + if (rno <= MFT_REC_MIRR && + size < (MFT_REC_VOL + 1) * sbi->record_size && + oe->type == ATTR_DATA) { + goto next_dirty_page_vcn; + } + + lcn = le64_to_cpu(dp->page_lcns[i]); + + if ((!run_lookup_entry(oa->run1, vcn, &lcn0, &len0, NULL) || + lcn0 != lcn) && + !run_add_entry(oa->run1, vcn, lcn, 1)) { + err = -ENOMEM; + goto out; + } + attr = oa->attr; + t64 = le64_to_cpu(attr->nres.alloc_size); + if (size > t64) { + attr->nres.valid_size = attr->nres.data_size = + attr->nres.alloc_size = cpu_to_le64(size); + } + goto next_dirty_page_vcn; + +do_redo_1: + /* + * Perform the Redo Pass, to restore all of the dirty pages to the same + * contents that they had immediately before the crash + * If the dirty page table is empty, then we can skip the entire Redo Pass + */ + if (!dptbl || !dptbl->total) + goto do_undo_action; + + rec_lsn = rlsn; + + /* + * Read the record at the Redo lsn, before falling + * into common code to handle each record + */ + err = read_log_rec_lcb(log, rlsn, lcb_ctx_next, &lcb); + if (err) + goto out; + + /* + * Now loop to read all of our log records forwards, + * until we hit the end of the file, cleaning up at the end + */ +do_action_next: + frh = lcb->lrh; + + if (LfsClientRecord != frh->record_type) + goto read_next_log_do_action; + + transact_id = le32_to_cpu(frh->transact_id); + rec_len = le32_to_cpu(frh->client_data_len); + lrh = lcb->log_rec; + + if (!check_log_rec(lrh, rec_len, transact_id, bytes_per_attr_entry)) { + err = -EINVAL; + goto out; + } + + /* Ignore log records that do not update pages */ + if (lrh->lcns_follow) + goto find_dirty_page; + + goto read_next_log_do_action; + +find_dirty_page: + t16 = le16_to_cpu(lrh->target_attr); + t64 = le64_to_cpu(lrh->target_vcn); + dp = find_dp(dptbl, t16, t64); + + if (!dp) + goto read_next_log_do_action; + + if (rec_lsn < le64_to_cpu(dp->oldest_lsn)) + goto read_next_log_do_action; + + t16 = le16_to_cpu(lrh->target_attr); + if (t16 >= bytes_per_rt(oatbl)) { + err = -EINVAL; + goto out; + } + + oe = Add2Ptr(oatbl, t16); + + if (oe->next != RESTART_ENTRY_ALLOCATED_LE) { + err = -EINVAL; + goto out; + } + + oa = oe->ptr; + + if (!oa) { + err = -EINVAL; + goto out; + } + attr = oa->attr; + + vcn = le64_to_cpu(lrh->target_vcn); + + if (!run_lookup_entry(oa->run1, vcn, &lcn, NULL, NULL) || + lcn == SPARSE_LCN) { + goto read_next_log_do_action; + } + + /* Point to the Redo data and get its length */ + data = Add2Ptr(lrh, le16_to_cpu(lrh->redo_off)); + dlen = le16_to_cpu(lrh->redo_len); + + /* Shorten length by any Lcns which were deleted */ + saved_len = dlen; + + for (i = le16_to_cpu(lrh->lcns_follow); i; i--) { + size_t j; + u32 alen, voff; + + voff = le16_to_cpu(lrh->record_off) + + le16_to_cpu(lrh->attr_off); + voff += le16_to_cpu(lrh->cluster_off) << SECTOR_SHIFT; + + /* If the Vcn question is allocated, we can just get out.*/ + j = le64_to_cpu(lrh->target_vcn) - le64_to_cpu(dp->vcn); + if (dp->page_lcns[j + i - 1]) + break; + + if (!saved_len) + saved_len = 1; + + /* + * Calculate the allocated space left relative to the + * log record Vcn, after removing this unallocated Vcn + */ + alen = (i - 1) << sbi->cluster_bits; + + /* + * If the update described this log record goes beyond + * the allocated space, then we will have to reduce the length + */ + if (voff >= alen) + dlen = 0; + else if (voff + dlen > alen) + dlen = alen - voff; + } + + /* If the resulting dlen from above is now zero, we can skip this log record */ + if (!dlen && saved_len) + goto read_next_log_do_action; + + t16 = le16_to_cpu(lrh->redo_op); + if (can_skip_action(t16)) + goto read_next_log_do_action; + + /* Apply the Redo operation a common routine */ + err = do_action(log, oe, lrh, t16, data, dlen, rec_len, &rec_lsn); + if (err) + goto out; + + /* Keep reading and looping back until end of file */ +read_next_log_do_action: + err = read_next_log_rec(log, lcb, &rec_lsn); + if (!err && rec_lsn) + goto do_action_next; + + lcb_put(lcb); + lcb = NULL; + +do_undo_action: + /* Scan Transaction Table */ + tr = NULL; +transaction_table_next: + tr = enum_rstbl(trtbl, tr); + if (!tr) + goto undo_action_done; + + if (TransactionActive != tr->transact_state || !tr->undo_next_lsn) { + free_rsttbl_idx(trtbl, PtrOffset(trtbl, tr)); + goto transaction_table_next; + } + + log->transaction_id = PtrOffset(trtbl, tr); + undo_next_lsn = le64_to_cpu(tr->undo_next_lsn); + + /* + * We only have to do anything if the transaction has + * something its undo_next_lsn field + */ + if (!undo_next_lsn) + goto commit_undo; + + /* Read the first record to be undone by this transaction */ + err = read_log_rec_lcb(log, undo_next_lsn, lcb_ctx_undo_next, &lcb); + if (err) + goto out; + + /* + * Now loop to read all of our log records forwards, + * until we hit the end of the file, cleaning up at the end + */ +undo_action_next: + + lrh = lcb->log_rec; + frh = lcb->lrh; + transact_id = le32_to_cpu(frh->transact_id); + rec_len = le32_to_cpu(frh->client_data_len); + + if (!check_log_rec(lrh, rec_len, transact_id, bytes_per_attr_entry)) { + err = -EINVAL; + goto out; + } + + if (lrh->undo_op == cpu_to_le16(Noop)) + goto read_next_log_undo_action; + + oe = Add2Ptr(oatbl, le16_to_cpu(lrh->target_attr)); + oa = oe->ptr; + + t16 = le16_to_cpu(lrh->lcns_follow); + if (!t16) + goto add_allocated_vcns; + + is_mapped = run_lookup_entry(oa->run1, le64_to_cpu(lrh->target_vcn), + &lcn, &clen, NULL); + + /* + * If the mapping isn't already the table or the mapping + * corresponds to a hole the mapping, we need to make sure + * there is no partial page already memory + */ + if (is_mapped && lcn != SPARSE_LCN && clen >= t16) + goto add_allocated_vcns; + + vcn = le64_to_cpu(lrh->target_vcn); + vcn &= ~(log->clst_per_page - 1); + +add_allocated_vcns: + for (i = 0, vcn = le64_to_cpu(lrh->target_vcn), + size = (vcn + 1) << sbi->cluster_bits; + i < t16; i++, vcn += 1, size += sbi->cluster_size) { + attr = oa->attr; + if (!attr->non_res) { + if (size > le32_to_cpu(attr->res.data_size)) + attr->res.data_size = cpu_to_le32(size); + } else { + if (size > le64_to_cpu(attr->nres.data_size)) + attr->nres.valid_size = attr->nres.data_size = + attr->nres.alloc_size = + cpu_to_le64(size); + } + } + + t16 = le16_to_cpu(lrh->undo_op); + if (can_skip_action(t16)) + goto read_next_log_undo_action; + + /* Point to the Redo data and get its length */ + data = Add2Ptr(lrh, le16_to_cpu(lrh->undo_off)); + dlen = le16_to_cpu(lrh->undo_len); + + /* it is time to apply the undo action */ + err = do_action(log, oe, lrh, t16, data, dlen, rec_len, NULL); + +read_next_log_undo_action: + /* + * Keep reading and looping back until we have read the + * last record for this transaction + */ + err = read_next_log_rec(log, lcb, &rec_lsn); + if (err) + goto out; + + if (rec_lsn) + goto undo_action_next; + +commit_undo: + free_rsttbl_idx(trtbl, log->transaction_id); + + log->transaction_id = 0; + + goto transaction_table_next; + +undo_action_done: + + ntfs_update_mftmirr(sbi, 0); + + sbi->flags &= ~NTFS_FLAGS_NEED_REPLAY; + +end_reply: + + err = 0; + if (is_ro) + goto out; + + rh = ntfs_alloc(log->page_size, 1); + if (!rh) { + err = -ENOMEM; + goto out; + } + + rh->rhdr.sign = NTFS_RSTR_SIGNATURE; + rh->rhdr.fix_off = cpu_to_le16(offsetof(struct RESTART_HDR, fixups)); + t16 = (log->page_size >> SECTOR_SHIFT) + 1; + rh->rhdr.fix_num = cpu_to_le16(t16); + rh->sys_page_size = cpu_to_le32(log->page_size); + rh->page_size = cpu_to_le32(log->page_size); + + t16 = QuadAlign(offsetof(struct RESTART_HDR, fixups) + + sizeof(short) * t16); + rh->ra_off = cpu_to_le16(t16); + rh->minor_ver = cpu_to_le16(1); // 0x1A: + rh->major_ver = cpu_to_le16(1); // 0x1C: + + ra2 = Add2Ptr(rh, t16); + memcpy(ra2, ra, sizeof(struct RESTART_AREA)); + + ra2->client_idx[0] = 0; + ra2->client_idx[1] = LFS_NO_CLIENT_LE; + ra2->flags = cpu_to_le16(2); + + le32_add_cpu(&ra2->open_log_count, 1); + + ntfs_fix_pre_write(&rh->rhdr, log->page_size); + + err = ntfs_sb_write_run(sbi, &ni->file.run, 0, rh, log->page_size); + if (!err) + err = ntfs_sb_write_run(sbi, &log->ni->file.run, log->page_size, + rh, log->page_size); + + ntfs_free(rh); + if (err) + goto out; + +out: + ntfs_free(rst); + if (lcb) + lcb_put(lcb); + + /* Scan the Open Attribute Table to close all of the open attributes */ + oe = NULL; + while ((oe = enum_rstbl(oatbl, oe))) { + rno = ino_get(&oe->ref); + + if (oe->is_attr_name == 1) { + ntfs_free(oe->ptr); + oe->ptr = NULL; + continue; + } + + if (oe->is_attr_name) + continue; + + oa = oe->ptr; + if (!oa) + continue; + + run_close(&oa->run0); + ntfs_free(oa->attr); + if (oa->ni) + iput(&oa->ni->vfs_inode); + ntfs_free(oa); + } + + ntfs_free(trtbl); + ntfs_free(oatbl); + ntfs_free(dptbl); + ntfs_free(attr_names); + ntfs_free(rst_info.r_page); + + ntfs_free(ra); + ntfs_free(log->one_page_buf); + + if (err) + sbi->flags |= NTFS_FLAGS_NEED_REPLAY; + + if (err == -EROFS) + err = 0; + else if (log->set_dirty) + ntfs_set_state(sbi, NTFS_DIRTY_ERROR); + + ntfs_free(log); + + return err; +} From patchwork Fri Oct 9 14:22:59 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Konstantin Komarov X-Patchwork-Id: 11825953 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id E5C4A14D5 for ; Fri, 9 Oct 2020 14:23:38 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id C9FD0222D9 for ; Fri, 9 Oct 2020 14:23:38 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (1024-bit key) header.d=paragon-software.com header.i=@paragon-software.com header.b="iQTa3mD5" Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S2388735AbgJIOXX (ORCPT ); Fri, 9 Oct 2020 10:23:23 -0400 Received: from relayfre-01.paragon-software.com ([176.12.100.13]:52144 "EHLO relayfre-01.paragon-software.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1731698AbgJIOXN (ORCPT ); Fri, 9 Oct 2020 10:23:13 -0400 Received: from dlg2.mail.paragon-software.com (vdlg-exch-02.paragon-software.com [172.30.1.105]) by relayfre-01.paragon-software.com (Postfix) with ESMTPS id 51237212E; Fri, 9 Oct 2020 17:23:10 +0300 (MSK) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=paragon-software.com; s=mail; t=1602253390; bh=hUyZWVbgxKlcw/mUi/FvnWB+WyvlIGoSQAgeC+DQMrg=; h=From:To:CC:Subject:Date:In-Reply-To:References; b=iQTa3mD5OWxsspuGKRAS5UoQA5uO5VPKHvq+kIP7CFayIZ+aF7T7L8mf3PraPnKHR jhQGxSmB3XVIdrWEMwFZbBLyaUugK5cJbgaEe/0yuqu+QqPlcxXIjtcZSxIZ7U92wL MPJC4HTB900SvwPl1BQxehEKSwQe3bRJiyL0bPAw= Received: from fsd-lkpg.ufsd.paragon-software.com (172.30.114.105) by vdlg-exch-02.paragon-software.com (172.30.1.105) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id 15.1.1847.3; Fri, 9 Oct 2020 17:23:09 +0300 From: Konstantin Komarov To: CC: , , , , , , , , , , , , Konstantin Komarov Subject: [PATCH v8 08/10] fs/ntfs3: Add Kconfig, Makefile and doc Date: Fri, 9 Oct 2020 17:22:59 +0300 Message-ID: <20201009142301.412454-9-almaz.alexandrovich@paragon-software.com> X-Mailer: git-send-email 2.25.4 In-Reply-To: <20201009142301.412454-1-almaz.alexandrovich@paragon-software.com> References: <20201009142301.412454-1-almaz.alexandrovich@paragon-software.com> MIME-Version: 1.0 X-Originating-IP: [172.30.114.105] X-ClientProxiedBy: vdlg-exch-02.paragon-software.com (172.30.1.105) To vdlg-exch-02.paragon-software.com (172.30.1.105) Precedence: bulk List-ID: X-Mailing-List: linux-fsdevel@vger.kernel.org This adds Kconfig, Makefile and doc Signed-off-by: Konstantin Komarov --- Documentation/filesystems/ntfs3.rst | 107 ++++++++++++++++++++++++++++ fs/ntfs3/Kconfig | 23 ++++++ fs/ntfs3/Makefile | 11 +++ 3 files changed, 141 insertions(+) create mode 100644 Documentation/filesystems/ntfs3.rst create mode 100644 fs/ntfs3/Kconfig create mode 100644 fs/ntfs3/Makefile diff --git a/Documentation/filesystems/ntfs3.rst b/Documentation/filesystems/ntfs3.rst new file mode 100644 index 000000000000..7b7d71b26c95 --- /dev/null +++ b/Documentation/filesystems/ntfs3.rst @@ -0,0 +1,107 @@ +.. SPDX-License-Identifier: GPL-2.0 + +===== +NTFS3 +===== + + +Summary and Features +==================== + +NTFS3 is fully functional NTFS Read-Write driver. The driver works with +NTFS versions up to 3.1, normal/compressed/sparse files +and journal replaying. File system type to use on mount is 'ntfs3'. + +- This driver implements NTFS read/write support for normal, sparse and + compressed files. + NOTE: Operations with compressed files require increased memory consumption; +- Supports native journal replaying; +- Supports extended attributes; +- Supports NFS export of mounted NTFS volumes. + +Mount Options +============= + +The list below describes mount options supported by NTFS3 driver in addition to +generic ones. + +=============================================================================== + +nls=name This option informs the driver how to interpret path + strings and translate them to Unicode and back. If + this option is not set, the default codepage will be + used (CONFIG_NLS_DEFAULT). + Examples: + 'nls=utf8' + +nls_alt=name This option extends "nls". It will be used to translate + path string to Unicode if primary nls failed. + Examples: + 'nls_alt=cp1251' + +uid= +gid= +umask= Controls the default permissions for files/directories created + after the NTFS volume is mounted. + +fmask= +dmask= Instead of specifying umask which applies both to + files and directories, fmask applies only to files and + dmask only to directories. + +nohidden Files with the Windows-specific HIDDEN (FILE_ATTRIBUTE_HIDDEN) + attribute will not be shown under Linux. + +sys_immutable Files with the Windows-specific SYSTEM + (FILE_ATTRIBUTE_SYSTEM) attribute will be marked as system + immutable files. + +discard Enable support of the TRIM command for improved performance + on delete operations, which is recommended for use with the + solid-state drives (SSD). + +force Forces the driver to mount partitions even if 'dirty' flag + (volume dirty) is set. Not recommended for use. + +sparse Create new files as "sparse". + +showmeta Use this parameter to show all meta-files (System Files) on + a mounted NTFS partition. + By default, all meta-files are hidden. + +prealloc Preallocate space for files excessively when file size is + increasing on writes. Decreases fragmentation in case of + parallel write operations to different files. + +no_acs_rules "No access rules" mount option sets access rights for + files/folders to 777 and owner/group to root. This mount + option absorbs all other permissions: + - permissions change for files/folders will be reported + as successful, but they will remain 777; + - owner/group change will be reported as successful, but + they will stay as root + +acl Support POSIX ACLs (Access Control Lists). Effective if + supported by Kernel. Not to be confused with NTFS ACLs. + The option specified as acl enables support for POSIX ACLs. + +noatime All files and directories will not update their last access + time attribute if a partition is mounted with this parameter. + This option can speed up file system operation. + +=============================================================================== + +ToDo list +========= + +- Full journaling support (currently journal replaying is supported) over JBD. + + +References +========== +https://www.paragon-software.com/home/ntfs-linux-professional/ + - Commercial version of the NTFS driver for Linux. + +almaz.alexandrovich@paragon-software.com + - Direct e-mail address for feedback and requests on the NTFS3 implementation. + diff --git a/fs/ntfs3/Kconfig b/fs/ntfs3/Kconfig new file mode 100644 index 000000000000..92a9c68008c8 --- /dev/null +++ b/fs/ntfs3/Kconfig @@ -0,0 +1,23 @@ +# SPDX-License-Identifier: GPL-2.0-only +config NTFS3_FS + tristate "NTFS Read-Write file system support" + select NLS + help + Windows OS native file system (NTFS) support up to NTFS version 3.1. + + Y or M enables the NTFS3 driver with full features enabled (read, + write, journal replaying, sparse/compressed files support). + File system type to use on mount is "ntfs3". Module name (M option) + is also "ntfs3". + + Documentation: + +config NTFS3_64BIT_CLUSTER + bool "64 bits per NTFS clusters" + depends on NTFS3_FS && 64BIT + help + Windows implementation of ntfs.sys uses 32 bits per clusters. + If activated 64 bits per clusters you will be able to use 4k cluster + for 16T+ volumes. Windows will not be able to mount such volumes. + + It is recommended to say N here. diff --git a/fs/ntfs3/Makefile b/fs/ntfs3/Makefile new file mode 100644 index 000000000000..d99dd1af43aa --- /dev/null +++ b/fs/ntfs3/Makefile @@ -0,0 +1,11 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Makefile for the ntfs3 filesystem support. +# + +obj-$(CONFIG_NTFS3_FS) += ntfs3.o + +ntfs3-y := bitfunc.o bitmap.o inode.o fsntfs.o frecord.o \ + index.o attrlist.o record.o attrib.o run.o xattr.o\ + upcase.o super.o file.o dir.o namei.o lznt.o\ + fslog.o From patchwork Fri Oct 9 14:23:00 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Konstantin Komarov X-Patchwork-Id: 11825949 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 3E85F14D5 for ; Fri, 9 Oct 2020 14:23:24 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 0FB52222EC for ; Fri, 9 Oct 2020 14:23:24 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (1024-bit key) header.d=paragon-software.com header.i=@paragon-software.com header.b="A+uLJYgj" Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S2388733AbgJIOXW (ORCPT ); Fri, 9 Oct 2020 10:23:22 -0400 Received: from relaydlg-01.paragon-software.com ([81.5.88.159]:42946 "EHLO relaydlg-01.paragon-software.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S2388705AbgJIOXN (ORCPT ); Fri, 9 Oct 2020 10:23:13 -0400 Received: from dlg2.mail.paragon-software.com (vdlg-exch-02.paragon-software.com [172.30.1.105]) by relaydlg-01.paragon-software.com (Postfix) with ESMTPS id A4FBC82381; Fri, 9 Oct 2020 17:23:10 +0300 (MSK) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=paragon-software.com; s=mail; t=1602253390; bh=S8gDeoTCBo2l6VTbgmUNJMuSPx/Uom3dBfUMBREzyWI=; h=From:To:CC:Subject:Date:In-Reply-To:References; b=A+uLJYgjRYVmi/ChdFBYbzFHJ0j8TUeAiuDyTOZORaEA3yhJaPvZpn3jQzuk0LYIN NABsAuqfTKQuBRMy/5jZbr1g9QnyKAAxkLKWGXfLppaK09xRDfMYQkKrtoTOBuC8FQ mshhZjX/RaWe2Iv5/rCb4KXf54woB/FOucxRFWAQ= Received: from fsd-lkpg.ufsd.paragon-software.com (172.30.114.105) by vdlg-exch-02.paragon-software.com (172.30.1.105) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id 15.1.1847.3; Fri, 9 Oct 2020 17:23:10 +0300 From: Konstantin Komarov To: CC: , , , , , , , , , , , , Konstantin Komarov Subject: [PATCH v8 09/10] fs/ntfs3: Add NTFS3 in fs/Kconfig and fs/Makefile Date: Fri, 9 Oct 2020 17:23:00 +0300 Message-ID: <20201009142301.412454-10-almaz.alexandrovich@paragon-software.com> X-Mailer: git-send-email 2.25.4 In-Reply-To: <20201009142301.412454-1-almaz.alexandrovich@paragon-software.com> References: <20201009142301.412454-1-almaz.alexandrovich@paragon-software.com> MIME-Version: 1.0 X-Originating-IP: [172.30.114.105] X-ClientProxiedBy: vdlg-exch-02.paragon-software.com (172.30.1.105) To vdlg-exch-02.paragon-software.com (172.30.1.105) Precedence: bulk List-ID: X-Mailing-List: linux-fsdevel@vger.kernel.org This adds NTFS3 in fs/Kconfig and fs/Makefile Signed-off-by: Konstantin Komarov --- fs/Kconfig | 1 + fs/Makefile | 1 + 2 files changed, 2 insertions(+) diff --git a/fs/Kconfig b/fs/Kconfig index aa4c12282301..eae96d55ab67 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -145,6 +145,7 @@ menu "DOS/FAT/EXFAT/NT Filesystems" source "fs/fat/Kconfig" source "fs/exfat/Kconfig" source "fs/ntfs/Kconfig" +source "fs/ntfs3/Kconfig" endmenu endif # BLOCK diff --git a/fs/Makefile b/fs/Makefile index 1c7b0e3f6daa..b0b4ad8affa0 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -100,6 +100,7 @@ obj-$(CONFIG_SYSV_FS) += sysv/ obj-$(CONFIG_CIFS) += cifs/ obj-$(CONFIG_HPFS_FS) += hpfs/ obj-$(CONFIG_NTFS_FS) += ntfs/ +obj-$(CONFIG_NTFS3_FS) += ntfs3/ obj-$(CONFIG_UFS_FS) += ufs/ obj-$(CONFIG_EFS_FS) += efs/ obj-$(CONFIG_JFFS2_FS) += jffs2/ From patchwork Fri Oct 9 14:23:01 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Konstantin Komarov X-Patchwork-Id: 11825947 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id DE89C1744 for ; Fri, 9 Oct 2020 14:23:21 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id B6A4122314 for ; Fri, 9 Oct 2020 14:23:21 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (1024-bit key) header.d=paragon-software.com header.i=@paragon-software.com header.b="uYNAwTr1" Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S2388723AbgJIOXV (ORCPT ); Fri, 9 Oct 2020 10:23:21 -0400 Received: from relayfre-01.paragon-software.com ([176.12.100.13]:52186 "EHLO relayfre-01.paragon-software.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S2388707AbgJIOXN (ORCPT ); Fri, 9 Oct 2020 10:23:13 -0400 Received: from dlg2.mail.paragon-software.com (vdlg-exch-02.paragon-software.com [172.30.1.105]) by relayfre-01.paragon-software.com (Postfix) with ESMTPS id C76DB2130; Fri, 9 Oct 2020 17:23:10 +0300 (MSK) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=paragon-software.com; s=mail; t=1602253390; bh=3PSMyybwiL6Qcr2UqjSnDQnVIfg7Pare5ag/6CfOc8Y=; h=From:To:CC:Subject:Date:In-Reply-To:References; b=uYNAwTr1v4/LybL9g6I0c0I4smtARzjaA5oHTqurU33pZAYIMioFNoc4f7tR3rNGu eRUNQX5DxrOBtKARndUP/GNglEkZiOsslPKN1oBnrwueOQEQPXhnQf/eU/IvebbSSC Aismu1mGHYraMH6XN+p/qWJw8KaCsVchXhpZpiyM= Received: from fsd-lkpg.ufsd.paragon-software.com (172.30.114.105) by vdlg-exch-02.paragon-software.com (172.30.1.105) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id 15.1.1847.3; Fri, 9 Oct 2020 17:23:10 +0300 From: Konstantin Komarov To: CC: , , , , , , , , , , , , Konstantin Komarov Subject: [PATCH v8 10/10] fs/ntfs3: Add MAINTAINERS Date: Fri, 9 Oct 2020 17:23:01 +0300 Message-ID: <20201009142301.412454-11-almaz.alexandrovich@paragon-software.com> X-Mailer: git-send-email 2.25.4 In-Reply-To: <20201009142301.412454-1-almaz.alexandrovich@paragon-software.com> References: <20201009142301.412454-1-almaz.alexandrovich@paragon-software.com> MIME-Version: 1.0 X-Originating-IP: [172.30.114.105] X-ClientProxiedBy: vdlg-exch-02.paragon-software.com (172.30.1.105) To vdlg-exch-02.paragon-software.com (172.30.1.105) Precedence: bulk List-ID: X-Mailing-List: linux-fsdevel@vger.kernel.org This adds MAINTAINERS Signed-off-by: Konstantin Komarov --- MAINTAINERS | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index 9a54806ebf02..e7c9536c311b 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -12382,6 +12382,13 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/aia21/ntfs.git F: Documentation/filesystems/ntfs.rst F: fs/ntfs/ +NTFS3 FILESYSTEM +M: Konstantin Komarov +S: Supported +W: http://www.paragon-software.com/ +F: Documentation/filesystems/ntfs3.rst +F: fs/ntfs3/ + NUBUS SUBSYSTEM M: Finn Thain L: linux-m68k@lists.linux-m68k.org