Kernel

kernel@openeuler.org

18 participants
18905 discussions

[PATCH OLK-5.10 005/107] fs/ntfs3: Add attrib operations
by Yin Xiujiang 08 Dec '21

08 Dec '21

From: Konstantin Komarov <almaz.alexandrovich(a)paragon-software.com> mainline inclusion from mainline-v5.15-rc1 commit be71b5cba2e6485e8959da7a9f9a44461a1bb074 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4G67J?from=project-issue CVE: NA ---------------------------------------------------------------------- This adds attrib operations Signed-off-by: Konstantin Komarov <almaz.alexandrovich(a)paragon-software.com> Signed-off-by: Yin Xiujiang <yinxiujiang(a)kylinos.cn> --- fs/ntfs3/attrib.c | 2096 +++++++++++++++++++++++++++++++++++++++++++ fs/ntfs3/attrlist.c | 456 ++++++++++ fs/ntfs3/xattr.c | 1128 +++++++++++++++++++++++ 3 files changed, 3680 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..046dc57f75f2 --- /dev/null +++ b/fs/ntfs3/attrib.c @@ -0,0 +1,2096 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * + * Copyright (C) 2019-2021 Paragon Software GmbH, All rights reserved. + * + * TODO: merge attr_set_size/attr_data_get_block/attr_allocate_frame? + */ + +#include <linux/blkdev.h> +#include <linux/buffer_head.h> +#include <linux/fs.h> +#include <linux/hash.h> +#include <linux/nls.h> +#include <linux/ratelimit.h> +#include <linux/slab.h> + +#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, const CLST *vcn) +{ + 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; + + if (vcn && (evcn < *vcn || *vcn < svcn)) + return -EINVAL; + + 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, + vcn ? *vcn : svcn, 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 vcn_next, 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; + + vcn_next = vcn + clen; + if (!run_get_entry(run, ++idx, &vcn, &lcn, &clen) || + vcn != vcn_next) { + // 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, opt == ALLOCATE_MFT)) { + 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; +} + +/* + * if page is not NULL - it is already contains resident data + * and locked (called from ni_write_frame) + */ +int attr_make_nonresident(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, struct page *page) +{ + struct ntfs_sb_info *sbi; + struct ATTRIB *attr_s; + struct MFT_REC *rec; + u32 used, asize, rsize, aoff, align; + bool is_data; + CLST len, alen; + char *next; + int err; + + if (attr->non_res) { + *ins_attr = attr; + return 0; + } + + sbi = mi->sbi; + rec = mi->mrec; + attr_s = NULL; + used = le32_to_cpu(rec->used); + asize = le32_to_cpu(attr->size); + next = Add2Ptr(attr, asize); + aoff = PtrOffset(rec, attr); + rsize = le32_to_cpu(attr->res.data_size); + is_data = attr->type == ATTR_DATA && !attr->name_len; + + align = sbi->cluster_size; + if (is_attr_compressed(attr)) + align <<= COMPRESSION_UNIT; + len = (rsize + align - 1) >> sbi->cluster_bits; + + run_init(run); + + /* make a copy of original attribute */ + attr_s = ntfs_memdup(attr, asize); + if (!attr_s) { + err = -ENOMEM; + goto out; + } + + if (!len) { + /* empty resident -> empty nonresident */ + alen = 0; + } else { + const char *data = resident_data(attr); + + err = attr_allocate_clusters(sbi, run, 0, 0, len, NULL, + ALLOCATE_DEF, &alen, 0, NULL); + if (err) + goto out1; + + if (!rsize) { + /* empty resident -> non empty nonresident */ + } else if (!is_data) { + err = ntfs_sb_write_run(sbi, run, 0, data, rsize); + if (err) + goto out2; + } else if (!page) { + char *kaddr; + + page = grab_cache_page(ni->vfs_inode.i_mapping, 0); + if (!page) { + err = -ENOMEM; + goto out2; + } + kaddr = kmap_atomic(page); + memcpy(kaddr, data, rsize); + memset(kaddr + rsize, 0, PAGE_SIZE - rsize); + kunmap_atomic(kaddr); + flush_dcache_page(page); + SetPageUptodate(page); + set_page_dirty(page); + unlock_page(page); + put_page(page); + } + } + + /* remove original attribute */ + 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 out3; + + ntfs_free(attr_s); + attr->nres.data_size = cpu_to_le64(rsize); + attr->nres.valid_size = attr->nres.data_size; + + *ins_attr = attr; + + if (is_data) + ni->ni_flags &= ~NI_FLAG_RESIDENT; + + /* Resident attribute becomes non resident */ + return 0; + +out3: + attr = Add2Ptr(rec, aoff); + memmove(next, attr, used - aoff); + memcpy(attr, attr_s, asize); + rec->used = cpu_to_le32(used + asize); + mi->dirty = true; +out2: + /* undo: do not trim new allocated clusters */ + run_deallocate(sbi, run, false); + run_close(run); +out1: + ntfs_free(attr_s); + /*reinsert le*/ +out: + 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) +{ + 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); + s64 dsize = QuadAlign(new_size) - QuadAlign(rsize); + + if (dsize < 0) { + memmove(next + dsize, next, tail); + } else if (dsize > 0) { + if (used + dsize > sbi->max_bytes_per_attr) + return attr_make_nonresident(ni, attr, le, mi, new_size, + run, ins_attr, NULL); + + memmove(next + dsize, next, tail); + memset(next, 0, dsize); + } + + if (new_size > rsize) + memset(Add2Ptr(resident_data(attr), rsize), 0, + new_size - rsize); + + 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; +} + +/* + * 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 = NULL, *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: + align = sbi->cluster_size; + + if (is_ext) { + align <<= attr_b->nres.c_unit; + if (is_attr_sparsed(attr_b)) + keep_prealloc = false; + } + + 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, NULL); + 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, + false)) { + 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; + + alen = 0; + 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) + 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 && ((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; + } + + if (attr_b && attr_b->non_res) { + 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 = NULL, *attr_b; + struct ATTR_LIST_ENTRY *le, *le_b; + struct mft_inode *mi, *mi_b; + CLST hint, svcn, to_alloc, evcn1, next_svcn, asize, end; + u64 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; + + ni_lock(ni); + down_write(&ni->file.run_lock); + + 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) { + *lcn = RESIDENT_LCN; + *len = 1; + goto out; + } + + asize = le64_to_cpu(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, NULL); + 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 ok; + } + + if (!ok && !new) { + *len = 0; + err = 0; + goto ok; + } + + if (ok && clen > *len) { + clen = *len; + 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, + false)) { + 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; + + end = vcn + *len; + + total_size = le64_to_cpu(attr_b->nres.total_size) + + ((u64)*len << cluster_bits); + +repack: + err = mi_pack_runs(mi, attr, run, max(end, evcn1) - svcn); + if (err) + goto out; + + attr_b->nres.total_size = cpu_to_le64(total_size); + inode_set_bytes(&ni->vfs_inode, total_size); + ni->ni_flags |= NI_FLAG_UPDATE_PARENT; + + mi_b->dirty = true; + mark_inode_dirty(&ni->vfs_inode); + + /* stored [vcn : next_svcn) from [vcn : end) */ + next_svcn = le64_to_cpu(attr->nres.evcn) + 1; + + if (end <= evcn1) { + if (next_svcn == evcn1) { + /* Normal way. update attribute and exit */ + goto ok; + } + /* add new segment [next_svcn : evcn1 - next_svcn )*/ + 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; + } + } + + svcn = evcn1; + + /* Estimate next attribute */ + attr = ni_find_attr(ni, attr, &le, ATTR_DATA, NULL, 0, &svcn, &mi); + + if (attr) { + CLST alloc = bytes_to_cluster( + sbi, le64_to_cpu(attr_b->nres.alloc_size)); + CLST evcn = le64_to_cpu(attr->nres.evcn); + + if (end < next_svcn) + end = next_svcn; + while (end > evcn) { + /* remove segment [svcn : evcn)*/ + mi_remove_attr(mi, attr); + + if (!al_remove_le(ni, le)) { + err = -EINVAL; + goto out; + } + + if (evcn + 1 >= alloc) { + /* last attribute segment */ + evcn1 = evcn + 1; + goto ins_ext; + } + + if (ni_load_mi(ni, le, &mi)) { + attr = NULL; + goto out; + } + + attr = mi_find_attr(mi, NULL, ATTR_DATA, NULL, 0, + &le->id); + if (!attr) { + err = -EINVAL; + goto out; + } + svcn = le64_to_cpu(attr->nres.svcn); + evcn = le64_to_cpu(attr->nres.evcn); + } + + if (end < svcn) + end = svcn; + + err = attr_load_runs(attr, ni, run, &end); + if (err) + goto out; + + evcn1 = evcn + 1; + attr->nres.svcn = cpu_to_le64(next_svcn); + err = mi_pack_runs(mi, attr, run, evcn1 - next_svcn); + if (err) + goto out; + + le->vcn = cpu_to_le64(next_svcn); + ni->attr_list.dirty = true; + mi->dirty = true; + + next_svcn = le64_to_cpu(attr->nres.evcn) + 1; + } +ins_ext: + if (evcn1 > next_svcn) { + err = ni_insert_nonresident(ni, ATTR_DATA, NULL, 0, run, + next_svcn, evcn1 - next_svcn, + attr_b->flags, &attr, &mi); + if (err) + goto out; + } +ok: + run_truncate_around(run, vcn); +out: + up_write(&ni->file.run_lock); + ni_unlock(ni); + + return err; +} + +int attr_data_read_resident(struct ntfs_inode *ni, struct page *page) +{ + u64 vbo; + struct ATTRIB *attr; + u32 data_size; + + attr = ni_find_attr(ni, NULL, NULL, ATTR_DATA, NULL, 0, NULL, NULL); + if (!attr) + return -EINVAL; + + if (attr->non_res) + return E_NTFS_NONRESIDENT; + + vbo = page->index << PAGE_SHIFT; + data_size = le32_to_cpu(attr->res.data_size); + if (vbo < data_size) { + const char *data = resident_data(attr); + char *kaddr = kmap_atomic(page); + u32 use = data_size - vbo; + + if (use > PAGE_SIZE) + use = PAGE_SIZE; + + memcpy(kaddr, data + vbo, use); + memset(kaddr + use, 0, PAGE_SIZE - use); + kunmap_atomic(kaddr); + flush_dcache_page(page); + SetPageUptodate(page); + } else if (!PageUptodate(page)) { + zero_user_segment(page, 0, PAGE_SIZE); + SetPageUptodate(page); + } + + return 0; +} + +int attr_data_write_resident(struct ntfs_inode *ni, struct page *page) +{ + u64 vbo; + struct mft_inode *mi; + struct ATTRIB *attr; + u32 data_size; + + attr = ni_find_attr(ni, NULL, NULL, ATTR_DATA, NULL, 0, NULL, &mi); + if (!attr) + return -EINVAL; + + if (attr->non_res) { + /*return special error code to check this case*/ + return E_NTFS_NONRESIDENT; + } + + vbo = page->index << PAGE_SHIFT; + data_size = le32_to_cpu(attr->res.data_size); + if (vbo < data_size) { + char *data = resident_data(attr); + char *kaddr = kmap_atomic(page); + u32 use = data_size - vbo; + + if (use > PAGE_SIZE) + use = PAGE_SIZE; + memcpy(data + vbo, kaddr, use); + kunmap_atomic(kaddr); + mi->dirty = true; + } + ni->i_valid = data_size; + + return 0; +} + +/* + * 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, svcn, + Add2Ptr(attr, ro), le32_to_cpu(attr->size) - ro); + if (err < 0) + return err; + return 0; +} + +/* + * load runs for given range [from to) + */ +int attr_load_runs_range(struct ntfs_inode *ni, enum ATTR_TYPE type, + const __le16 *name, u8 name_len, struct runs_tree *run, + u64 from, u64 to) +{ + struct ntfs_sb_info *sbi = ni->mi.sbi; + u8 cluster_bits = sbi->cluster_bits; + CLST vcn = from >> cluster_bits; + CLST vcn_last = (to - 1) >> cluster_bits; + CLST lcn, clen; + int err; + + for (vcn = from >> cluster_bits; vcn <= vcn_last; vcn += clen) { + if (!run_lookup_entry(run, vcn, &lcn, &clen, NULL)) { + err = attr_load_runs_vcn(ni, type, name, name_len, run, + vcn); + if (err) + return err; + clen = 0; /*next run_lookup_entry(vcn) must be success*/ + } + } + + return 0; +} + +#ifdef CONFIG_NTFS3_LZX_XPRESS +/* + * attr_wof_frame_info + * + * read header of xpress/lzx file to get info about frame + */ +int attr_wof_frame_info(struct ntfs_inode *ni, struct ATTRIB *attr, + struct runs_tree *run, u64 frame, u64 frames, + u8 frame_bits, u32 *ondisk_size, u64 *vbo_data) +{ + struct ntfs_sb_info *sbi = ni->mi.sbi; + u64 vbo[2], off[2], wof_size; + u32 voff; + u8 bytes_per_off; + char *addr; + struct page *page; + int i, err; + __le32 *off32; + __le64 *off64; + + if (ni->vfs_inode.i_size < 0x100000000ull) { + /* file starts with array of 32 bit offsets */ + bytes_per_off = sizeof(__le32); + vbo[1] = frame << 2; + *vbo_data = frames << 2; + } else { + /* file starts with array of 64 bit offsets */ + bytes_per_off = sizeof(__le64); + vbo[1] = frame << 3; + *vbo_data = frames << 3; + } + + /* + * read 4/8 bytes at [vbo - 4(8)] == offset where compressed frame starts + * read 4/8 bytes at [vbo] == offset where compressed frame ends + */ + if (!attr->non_res) { + if (vbo[1] + bytes_per_off > le32_to_cpu(attr->res.data_size)) { + ntfs_inode_err(&ni->vfs_inode, "is corrupted"); + return -EINVAL; + } + addr = resident_data(attr); + + if (bytes_per_off == sizeof(__le32)) { + off32 = Add2Ptr(addr, vbo[1]); + off[0] = vbo[1] ? le32_to_cpu(off32[-1]) : 0; + off[1] = le32_to_cpu(off32[0]); + } else { + off64 = Add2Ptr(addr, vbo[1]); + off[0] = vbo[1] ? le64_to_cpu(off64[-1]) : 0; + off[1] = le64_to_cpu(off64[0]); + } + + *vbo_data += off[0]; + *ondisk_size = off[1] - off[0]; + return 0; + } + + wof_size = le64_to_cpu(attr->nres.data_size); + down_write(&ni->file.run_lock); + page = ni->file.offs_page; + if (!page) { + page = alloc_page(GFP_KERNEL); + if (!page) { + err = -ENOMEM; + goto out; + } + page->index = -1; + ni->file.offs_page = page; + } + lock_page(page); + addr = page_address(page); + + if (vbo[1]) { + voff = vbo[1] & (PAGE_SIZE - 1); + vbo[0] = vbo[1] - bytes_per_off; + i = 0; + } else { + voff = 0; + vbo[0] = 0; + off[0] = 0; + i = 1; + } + + do { + pgoff_t index = vbo[i] >> PAGE_SHIFT; + + if (index != page->index) { + u64 from = vbo[i] & ~(u64)(PAGE_SIZE - 1); + u64 to = min(from + PAGE_SIZE, wof_size); + + err = attr_load_runs_range(ni, ATTR_DATA, WOF_NAME, + ARRAY_SIZE(WOF_NAME), run, + from, to); + if (err) + goto out1; + + err = ntfs_bio_pages(sbi, run, &page, 1, from, + to - from, REQ_OP_READ); + if (err) { + page->index = -1; + goto out1; + } + page->index = index; + } + + if (i) { + if (bytes_per_off == sizeof(__le32)) { + off32 = Add2Ptr(addr, voff); + off[1] = le32_to_cpu(*off32); + } else { + off64 = Add2Ptr(addr, voff); + off[1] = le64_to_cpu(*off64); + } + } else if (!voff) { + if (bytes_per_off == sizeof(__le32)) { + off32 = Add2Ptr(addr, PAGE_SIZE - sizeof(u32)); + off[0] = le32_to_cpu(*off32); + } else { + off64 = Add2Ptr(addr, PAGE_SIZE - sizeof(u64)); + off[0] = le64_to_cpu(*off64); + } + } else { + /* two values in one page*/ + if (bytes_per_off == sizeof(__le32)) { + off32 = Add2Ptr(addr, voff); + off[0] = le32_to_cpu(off32[-1]); + off[1] = le32_to_cpu(off32[0]); + } else { + off64 = Add2Ptr(addr, voff); + off[0] = le64_to_cpu(off64[-1]); + off[1] = le64_to_cpu(off64[0]); + } + break; + } + } while (++i < 2); + + *vbo_data += off[0]; + *ondisk_size = off[1] - off[0]; + +out1: + unlock_page(page); +out: + up_write(&ni->file.run_lock); + return err; +} +#endif + +/* + * 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) +{ + int err; + u32 clst_frame; + CLST clen, lcn, vcn, alen, slen, vcn_next; + size_t idx; + struct runs_tree *run; + + *clst_data = 0; + + 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, &clen, &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, &clen, &idx)) + return -EINVAL; + } + + if (lcn == SPARSE_LCN) { + /* sparsed frame */ + return 0; + } + + if (clen >= 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 = clen; + + /* + * The frame is compressed if *clst_data + slen >= clst_frame + * Check next fragments + */ + while ((vcn += clen) < alen) { + vcn_next = vcn; + + if (!run_get_entry(run, ++idx, &vcn, &lcn, &clen) || + vcn_next != vcn) { + err = attr_load_runs_vcn(ni, attr->type, + attr_name(attr), + attr->name_len, run, vcn_next); + if (err) + return err; + vcn = vcn_next; + + if (!run_lookup_entry(run, vcn, &lcn, &clen, &idx)) + return -EINVAL; + } + + if (lcn == SPARSE_LCN) { + slen += clen; + } else { + if (slen) { + /* + * data_clusters + sparse_clusters = + * not enough for frame + */ + return -EINVAL; + } + *clst_data += clen; + } + + 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 { + /*frame is compressed*/ + } + break; + } + } + + return 0; +} + +/* + * attr_allocate_frame + * + * allocate/free clusters for 'frame' + * assumed: down_write(&ni->file.run_lock); + */ +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 = NULL, *attr_b; + struct ATTR_LIST_ENTRY *le, *le_b; + struct mft_inode *mi, *mi_b; + CLST svcn, evcn1, next_svcn, lcn, len; + CLST vcn, end, clst_data; + u64 total_size, valid_size, data_size; + + 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, NULL); + if (err) + goto out; + + err = attr_is_frame_compressed(ni, attr_b, frame, &clst_data); + 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, + false)) { + err = -ENOMEM; + goto out; + } + end = vcn + clst_data; + /* run contains updated range [vcn + len : end) */ + } else { + CLST alen, hint = 0; + /* 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; + + end = vcn + len; + /* run contains updated range [vcn + clst_data : end) */ + } + + total_size += (u64)len << sbi->cluster_bits; + +repack: + err = mi_pack_runs(mi, attr, run, max(end, evcn1) - svcn); + if (err) + 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); + + /* stored [vcn : next_svcn) from [vcn : end) */ + next_svcn = le64_to_cpu(attr->nres.evcn) + 1; + + if (end <= evcn1) { + if (next_svcn == evcn1) { + /* Normal way. update attribute and exit */ + goto ok; + } + /* add new segment [next_svcn : evcn1 - next_svcn )*/ + 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; + } + } + + svcn = evcn1; + + /* Estimate next attribute */ + attr = ni_find_attr(ni, attr, &le, ATTR_DATA, NULL, 0, &svcn, &mi); + + if (attr) { + CLST alloc = bytes_to_cluster( + sbi, le64_to_cpu(attr_b->nres.alloc_size)); + CLST evcn = le64_to_cpu(attr->nres.evcn); + + if (end < next_svcn) + end = next_svcn; + while (end > evcn) { + /* remove segment [svcn : evcn)*/ + mi_remove_attr(mi, attr); + + if (!al_remove_le(ni, le)) { + err = -EINVAL; + goto out; + } + + if (evcn + 1 >= alloc) { + /* last attribute segment */ + evcn1 = evcn + 1; + goto ins_ext; + } + + if (ni_load_mi(ni, le, &mi)) { + attr = NULL; + goto out; + } + + attr = mi_find_attr(mi, NULL, ATTR_DATA, NULL, 0, + &le->id); + if (!attr) { + err = -EINVAL; + goto out; + } + svcn = le64_to_cpu(attr->nres.svcn); + evcn = le64_to_cpu(attr->nres.evcn); + } + + if (end < svcn) + end = svcn; + + err = attr_load_runs(attr, ni, run, &end); + if (err) + goto out; + + evcn1 = evcn + 1; + attr->nres.svcn = cpu_to_le64(next_svcn); + err = mi_pack_runs(mi, attr, run, evcn1 - next_svcn); + if (err) + goto out; + + le->vcn = cpu_to_le64(next_svcn); + ni->attr_list.dirty = true; + mi->dirty = true; + + next_svcn = le64_to_cpu(attr->nres.evcn) + 1; + } +ins_ext: + if (evcn1 > next_svcn) { + err = ni_insert_nonresident(ni, ATTR_DATA, NULL, 0, run, + next_svcn, evcn1 - next_svcn, + attr_b->flags, &attr, &mi); + if (err) + goto out; + } +ok: + run_truncate_around(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; +} + +/* Collapse range in file */ +int attr_collapse_range(struct ntfs_inode *ni, u64 vbo, u64 bytes) +{ + int err = 0; + struct runs_tree *run = &ni->file.run; + struct ntfs_sb_info *sbi = ni->mi.sbi; + struct ATTRIB *attr = NULL, *attr_b; + struct ATTR_LIST_ENTRY *le, *le_b; + struct mft_inode *mi, *mi_b; + CLST svcn, evcn1, len, dealloc, alen; + CLST vcn, end; + u64 valid_size, data_size, alloc_size, total_size; + u32 mask; + __le16 a_flags; + + if (!bytes) + return 0; + + 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 (!attr_b->non_res) { + /* Attribute is resident. Nothing to do? */ + return 0; + } + + data_size = le64_to_cpu(attr_b->nres.data_size); + alloc_size = le64_to_cpu(attr_b->nres.alloc_size); + a_flags = attr_b->flags; + + if (is_attr_ext(attr_b)) { + total_size = le64_to_cpu(attr_b->nres.total_size); + mask = (sbi->cluster_size << attr_b->nres.c_unit) - 1; + } else { + total_size = alloc_size; + mask = sbi->cluster_mask; + } + + if ((vbo & mask) || (bytes & mask)) { + /* allow to collapse only cluster aligned ranges */ + return -EINVAL; + } + + if (vbo > data_size) + return -EINVAL; + + down_write(&ni->file.run_lock); + + if (vbo + bytes >= data_size) { + u64 new_valid = min(ni->i_valid, vbo); + + /* Simple truncate file at 'vbo' */ + truncate_setsize(&ni->vfs_inode, vbo); + err = attr_set_size(ni, ATTR_DATA, NULL, 0, &ni->file.run, vbo, + &new_valid, true, NULL); + + if (!err && new_valid < ni->i_valid) + ni->i_valid = new_valid; + + goto out; + } + + /* + * Enumerate all attribute segments and collapse + */ + alen = alloc_size >> sbi->cluster_bits; + vcn = vbo >> sbi->cluster_bits; + len = bytes >> sbi->cluster_bits; + end = vcn + len; + dealloc = 0; + + svcn = le64_to_cpu(attr_b->nres.svcn); + evcn1 = le64_to_cpu(attr_b->nres.evcn) + 1; + + 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; + } + + for (;;) { + if (svcn >= end) { + /* shift vcn */ + attr->nres.svcn = cpu_to_le64(svcn - len); + attr->nres.evcn = cpu_to_le64(evcn1 - 1 - len); + if (le) { + le->vcn = attr->nres.svcn; + ni->attr_list.dirty = true; + } + mi->dirty = true; + } else if (svcn < vcn || end < evcn1) { + CLST vcn1, eat, next_svcn; + + /* collapse a part of this attribute segment */ + err = attr_load_runs(attr, ni, run, &svcn); + if (err) + goto out; + vcn1 = max(vcn, svcn); + eat = min(end, evcn1) - vcn1; + + err = run_deallocate_ex(sbi, run, vcn1, eat, &dealloc, + true); + if (err) + goto out; + + if (!run_collapse_range(run, vcn1, eat)) { + err = -ENOMEM; + goto out; + } + + if (svcn >= vcn) { + /* shift vcn */ + attr->nres.svcn = cpu_to_le64(vcn); + if (le) { + le->vcn = attr->nres.svcn; + ni->attr_list.dirty = true; + } + } + + err = mi_pack_runs(mi, attr, run, evcn1 - svcn - eat); + if (err) + goto out; + + next_svcn = le64_to_cpu(attr->nres.evcn) + 1; + if (next_svcn + eat < evcn1) { + err = ni_insert_nonresident( + ni, ATTR_DATA, NULL, 0, run, next_svcn, + evcn1 - eat - next_svcn, a_flags, &attr, + &mi); + if (err) + goto out; + + /* layout of records maybe changed */ + attr_b = NULL; + le = al_find_ex(ni, NULL, ATTR_DATA, NULL, 0, + &next_svcn); + if (!le) { + err = -EINVAL; + goto out; + } + } + + /* free all allocated memory */ + run_truncate(run, 0); + } else { + u16 le_sz; + u16 roff = le16_to_cpu(attr->nres.run_off); + + /*run==1 means unpack and deallocate*/ + run_unpack_ex(RUN_DEALLOCATE, sbi, ni->mi.rno, svcn, + evcn1 - 1, svcn, Add2Ptr(attr, roff), + le32_to_cpu(attr->size) - roff); + + /* delete this attribute segment */ + mi_remove_attr(mi, attr); + if (!le) + break; + + le_sz = le16_to_cpu(le->size); + if (!al_remove_le(ni, le)) { + err = -EINVAL; + goto out; + } + + if (evcn1 >= alen) + break; + + if (!svcn) { + /* Load next record that contains this attribute */ + if (ni_load_mi(ni, le, &mi)) { + err = -EINVAL; + goto out; + } + + /* Look for required attribute */ + attr = mi_find_attr(mi, NULL, ATTR_DATA, NULL, + 0, &le->id); + if (!attr) { + err = -EINVAL; + goto out; + } + goto next_attr; + } + le = (struct ATTR_LIST_ENTRY *)((u8 *)le - le_sz); + } + + if (evcn1 >= alen) + break; + + attr = ni_enum_attr_ex(ni, attr, &le, &mi); + if (!attr) { + err = -EINVAL; + goto out; + } + +next_attr: + svcn = le64_to_cpu(attr->nres.svcn); + evcn1 = le64_to_cpu(attr->nres.evcn) + 1; + } + + if (!attr_b) { + 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; + } + } + + data_size -= bytes; + valid_size = ni->i_valid; + if (vbo + bytes <= valid_size) + valid_size -= bytes; + else if (vbo < valid_size) + valid_size = vbo; + + attr_b->nres.alloc_size = cpu_to_le64(alloc_size - bytes); + attr_b->nres.data_size = cpu_to_le64(data_size); + attr_b->nres.valid_size = cpu_to_le64(min(valid_size, data_size)); + total_size -= (u64)dealloc << sbi->cluster_bits; + if (is_attr_ext(attr_b)) + attr_b->nres.total_size = cpu_to_le64(total_size); + mi_b->dirty = true; + + /*update inode size*/ + ni->i_valid = valid_size; + ni->vfs_inode.i_size = data_size; + inode_set_bytes(&ni->vfs_inode, total_size); + ni->ni_flags |= NI_FLAG_UPDATE_PARENT; + mark_inode_dirty(&ni->vfs_inode); + +out: + up_write(&ni->file.run_lock); + if (err) + make_bad_inode(&ni->vfs_inode); + + return err; +} + +/* not for normal files */ +int attr_punch_hole(struct ntfs_inode *ni, u64 vbo, u64 bytes, u32 *frame_size) +{ + int err = 0; + struct runs_tree *run = &ni->file.run; + struct ntfs_sb_info *sbi = ni->mi.sbi; + struct ATTRIB *attr = NULL, *attr_b; + struct ATTR_LIST_ENTRY *le, *le_b; + struct mft_inode *mi, *mi_b; + CLST svcn, evcn1, vcn, len, end, alen, dealloc; + u64 total_size, alloc_size; + u32 mask; + + if (!bytes) + return 0; + + 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 (!attr_b->non_res) { + u32 data_size = le32_to_cpu(attr->res.data_size); + u32 from, to; + + if (vbo > data_size) + return 0; + + from = vbo; + to = (vbo + bytes) < data_size ? (vbo + bytes) : data_size; + memset(Add2Ptr(resident_data(attr_b), from), 0, to - from); + return 0; + } + + if (!is_attr_ext(attr_b)) + return -EOPNOTSUPP; + + alloc_size = le64_to_cpu(attr_b->nres.alloc_size); + total_size = le64_to_cpu(attr_b->nres.total_size); + + if (vbo >= alloc_size) { + // NOTE: it is allowed + return 0; + } + + mask = (sbi->cluster_size << attr_b->nres.c_unit) - 1; + + bytes += vbo; + if (bytes > alloc_size) + bytes = alloc_size; + bytes -= vbo; + + if ((vbo & mask) || (bytes & mask)) { + /* We have to zero a range(s)*/ + if (frame_size == NULL) { + /* Caller insists range is aligned */ + return -EINVAL; + } + *frame_size = mask + 1; + return E_NTFS_NOTALIGNED; + } + + down_write(&ni->file.run_lock); + /* + * Enumerate all attribute segments and punch hole where necessary + */ + alen = alloc_size >> sbi->cluster_bits; + vcn = vbo >> sbi->cluster_bits; + len = bytes >> sbi->cluster_bits; + end = vcn + len; + dealloc = 0; + + svcn = le64_to_cpu(attr_b->nres.svcn); + evcn1 = le64_to_cpu(attr_b->nres.evcn) + 1; + + 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; + } + + while (svcn < end) { + CLST vcn1, zero, dealloc2; + + err = attr_load_runs(attr, ni, run, &svcn); + if (err) + goto out; + vcn1 = max(vcn, svcn); + zero = min(end, evcn1) - vcn1; + + dealloc2 = dealloc; + err = run_deallocate_ex(sbi, run, vcn1, zero, &dealloc, true); + if (err) + goto out; + + if (dealloc2 == dealloc) { + /* looks like the required range is already sparsed */ + } else { + if (!run_add_entry(run, vcn1, SPARSE_LCN, zero, + false)) { + err = -ENOMEM; + goto out; + } + + err = mi_pack_runs(mi, attr, run, evcn1 - svcn); + if (err) + goto out; + } + /* free all allocated memory */ + run_truncate(run, 0); + + if (evcn1 >= alen) + break; + + attr = ni_enum_attr_ex(ni, attr, &le, &mi); + if (!attr) { + err = -EINVAL; + goto out; + } + + svcn = le64_to_cpu(attr->nres.svcn); + evcn1 = le64_to_cpu(attr->nres.evcn) + 1; + } + + total_size -= (u64)dealloc << sbi->cluster_bits; + attr_b->nres.total_size = cpu_to_le64(total_size); + mi_b->dirty = true; + + /*update inode size*/ + inode_set_bytes(&ni->vfs_inode, total_size); + ni->ni_flags |= NI_FLAG_UPDATE_PARENT; + mark_inode_dirty(&ni->vfs_inode); + +out: + up_write(&ni->file.run_lock); + if (err) + make_bad_inode(&ni->vfs_inode); + + return err; +} diff --git a/fs/ntfs3/attrlist.c b/fs/ntfs3/attrlist.c new file mode 100644 index 000000000000..ea561361b576 --- /dev/null +++ b/fs/ntfs3/attrlist.c @@ -0,0 +1,456 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * + * Copyright (C) 2019-2021 Paragon Software GmbH, All rights reserved. + * + */ + +#include <linux/blkdev.h> +#include <linux/buffer_head.h> +#include <linux/fs.h> +#include <linux/nls.h> + +#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_malloc(al_aligned(lsize)); + 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), 0, + Add2Ptr(attr, run_off), + le32_to_cpu(attr->size) - run_off); + if (err < 0) + goto out; + + le = ntfs_malloc(al_aligned(lsize)); + 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 = le32_to_cpu(le->type) - type_in; + + /* List entries are sorted by type, name and vcn */ + if (diff < 0) + continue; + + if (diff > 0) + return ret; + + if (le->name_len != name_len) + continue; + + le_vcn = le64_to_cpu(le->vcn); + if (!le_vcn) { + /* + * compare entry names only for entry with vcn == 0 + */ + diff = ntfs_cmp_names(le_name(le), name_len, name, + name_len, ni->mi.sbi->upcase, + true); + if (diff < 0) + continue; + + if (diff > 0) + return ret; + } + + if (!vcn) + return le; + + 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 + */ +static struct ATTR_LIST_ENTRY *al_find_le_to_insert(struct ntfs_inode *ni, + enum ATTR_TYPE type, + const __le16 *name, + u8 name_len, CLST vcn) +{ + struct ATTR_LIST_ENTRY *le = NULL, *prev; + u32 type_in = le32_to_cpu(type); + + /* List entries are sorted by type, name, vcn */ + while ((le = al_enumerate(ni, prev = le))) { + int diff = le32_to_cpu(le->type) - type_in; + + if (diff < 0) + continue; + + if (diff > 0) + return le; + + if (!le->vcn) { + /* + * compare entry names only for entry with vcn == 0 + */ + diff = ntfs_cmp_names(le_name(le), le->name_len, name, + name_len, ni->mi.sbi->upcase, + true); + if (diff < 0) + continue; + + if (diff > 0) + return le; + } + + if (le64_to_cpu(le->vcn) >= vcn) + return le; + } + + return prev ? Add2Ptr(prev, le16_to_cpu(prev->size)) : ni->attr_list.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' + */ + 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_malloc(new_asize); + + 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); + +next: + if (off >= al->size) + return false; + if (le->type != type) + return false; + if (le->name_len != name_len) + return false; + if (name_len && ntfs_cmp_names(le_name(le), name_len, name, name_len, + ni->mi.sbi->upcase, true)) + return false; + if (le64_to_cpu(le->vcn) != vcn) + return false; + + /* + * 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. + */ + if (ref && memcmp(ref, &le->ref, sizeof(*ref))) { + off += le16_to_cpu(le->size); + le = Add2Ptr(al->le, off); + goto next; + } + + /* Save on stack the size of 'le' */ + size = le16_to_cpu(le->size); + /* Delete '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 ATTRIB *attr; + typeof(ni->attr_list) *al = &ni->attr_list; + + if (!al->dirty || !al->size) + return 0; + + /* + * attribute list increased on demand in al_add_le + * attribute list decreased here + */ + 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(ni->mi.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..98871c895e77 --- /dev/null +++ b/fs/ntfs3/xattr.c @@ -0,0 +1,1128 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * + * Copyright (C) 2019-2021 Paragon Software GmbH, All rights reserved. + * + */ + +#include <linux/blkdev.h> +#include <linux/buffer_head.h> +#include <linux/fs.h> +#include <linux/nls.h> +#include <linux/posix_acl.h> +#include <linux/posix_acl_xattr.h> +#include <linux/xattr.h> + +#include "debug.h" +#include "ntfs.h" +#include "ntfs_fs.h" + +// clang-format off +#define SYSTEM_DOS_ATTRIB "system.dos_attrib" +#define SYSTEM_NTFS_ATTRIB "system.ntfs_attrib" +#define SYSTEM_NTFS_SECURITY "system.ntfs_security" +// clang-format on + +static inline size_t unpacked_ea_size(const struct EA_FULL *ea) +{ + return ea->size ? le32_to_cpu(ea->size) + : DwordAlign(struct_size( + ea, name, + 1 + ea->name_len + le16_to_cpu(ea->elength))); +} + +static inline size_t packed_ea_size(const struct EA_FULL *ea) +{ + return struct_size(ea, name, + 1 + ea->name_len + le16_to_cpu(ea->elength)) - + offsetof(struct EA_FULL, flags); +} + +/* + * 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 > ni->mi.sbi->ea_max_size) + return -EFBIG; + + if (attr_size(attr_ea) > ni->mi.sbi->ea_max_size) + return -EFBIG; + + /* Allocate memory for packed Ea */ + ea_p = ntfs_malloc(size + add_bytes); + 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, NULL); + 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_list_ea + * + * copy a list of xattrs names into the buffer + * provided, or compute the buffer size required + * + * Returns a negative error number on failure, or the number of bytes + * used / required on success. + */ +static ssize_t ntfs_list_ea(struct ntfs_inode *ni, char *buffer, + size_t bytes_per_buffer) +{ + const struct EA_INFO *info; + struct EA_FULL *ea_all = NULL; + const struct EA_FULL *ea; + u32 off, size; + int err; + size_t ret; + + 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 (ret = 0, off = 0; off < size; off += unpacked_ea_size(ea)) { + ea = Add2Ptr(ea_all, off); + + if (buffer) { + if (ret + ea->name_len + 1 > bytes_per_buffer) { + err = -ERANGE; + goto out; + } + + memcpy(buffer + ret, ea->name, ea->name_len); + buffer[ret + ea->name_len] = 0; + } + + ret += ea->name_len + 1; + } + +out: + ntfs_free(ea_all); + return err ? err : ret; +} + +static int ntfs_get_ea(struct inode *inode, const char *name, size_t name_len, + void *buffer, size_t size, size_t *required) +{ + struct ntfs_inode *ni = ntfs_i(inode); + const struct EA_INFO *info; + struct EA_FULL *ea_all = NULL; + const struct EA_FULL *ea; + u32 off, len; + int err; + + if (!(ni->ni_flags & NI_FLAG_EA)) + return -ENODATA; + + if (!required) + ni_lock(ni); + + 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 > size) { + err = -ERANGE; + if (required) + *required = len; + goto out; + } + + memcpy(buffer, ea->name + ea->name_len + 1, len); + err = 0; + +out: + ntfs_free(ea_all); + if (!required) + ni_unlock(ni); + + return err ? err : len; +} + +static noinline int ntfs_set_ea(struct inode *inode, const char *name, + size_t name_len, 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 add, new_pack; + 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); + + if (name_len > 255) { + err = -ENAMETOOLONG; + goto out; + } + + add = DwordAlign(struct_size(ea_all, 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; + } + + ea = Add2Ptr(ea_all, off); + + /* + * Check simple case when we try to insert xattr with the same value + * e.g. ntfs_save_wsl_perm + */ + if (val_size && le16_to_cpu(ea->elength) == val_size && + !memcmp(ea->name + ea->name_len + 1, value, val_size)) { + /* xattr already contains the required value */ + goto out; + } + + /* Remove current xattr */ + 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) { + /* remove xattr */ + goto update_ea; + } + } else { + if (flags & XATTR_REPLACE) { + err = -ENODATA; + goto out; + } + + if (!ea_all) { + ea_all = ntfs_zalloc(add); + 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); + new_pack = le16_to_cpu(ea_info.size_pack) + packed_ea_size(new_ea); + + /* should fit into 16 bits */ + if (new_pack > 0xffff) { + err = -EFBIG; // -EINVAL? + goto out; + } + ea_info.size_pack = cpu_to_le16(new_pack); + + /* new size of ATTR_EA */ + size += add; + if (size > sbi->ea_max_size) { + err = -EFBIG; // -EINVAL? + goto out; + } + 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; + } + + /* Check if we delete the last xattr */ + if (size) + ni->ni_flags |= NI_FLAG_EA; + else + ni->ni_flags &= ~NI_FLAG_EA; + + if (ea_info.size_pack != size_pack) + ni->ni_flags |= NI_FLAG_UPDATE_PARENT; + mark_inode_dirty(&ni->vfs_inode); + +out: + if (!locked) + ni_unlock(ni); + + run_close(&ea_run); + ntfs_free(ea_all); + + return err; +} + +#ifdef CONFIG_NTFS3_FS_POSIX_ACL +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 user_namespace *mnt_userns, + struct inode *inode, int type, + int locked) +{ + struct ntfs_inode *ni = ntfs_i(inode); + const char *name; + size_t name_len; + struct posix_acl *acl; + size_t req; + int err; + void *buf; + + /* allocate PATH_MAX bytes */ + buf = __getname(); + if (!buf) + return ERR_PTR(-ENOMEM); + + /* Possible values of 'type' was already checked above */ + if (type == ACL_TYPE_ACCESS) { + name = XATTR_NAME_POSIX_ACL_ACCESS; + name_len = sizeof(XATTR_NAME_POSIX_ACL_ACCESS) - 1; + } else { + name = XATTR_NAME_POSIX_ACL_DEFAULT; + name_len = sizeof(XATTR_NAME_POSIX_ACL_DEFAULT) - 1; + } + + if (!locked) + ni_lock(ni); + + err = ntfs_get_ea(inode, name, name_len, buf, PATH_MAX, &req); + + if (!locked) + ni_unlock(ni); + + /* Translate extended attribute to acl */ + if (err > 0) { + acl = posix_acl_from_xattr(mnt_userns, 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) +{ + /* TODO: init_user_ns? */ + return ntfs_get_acl_ex(&init_user_ns, inode, type, 0); +} + +static noinline int ntfs_set_acl_ex(struct user_namespace *mnt_userns, + struct inode *inode, struct posix_acl *acl, + int type, int locked) +{ + const char *name; + size_t size, name_len; + 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; + } + } + name = XATTR_NAME_POSIX_ACL_ACCESS; + name_len = sizeof(XATTR_NAME_POSIX_ACL_ACCESS) - 1; + break; + + case ACL_TYPE_DEFAULT: + if (!S_ISDIR(inode->i_mode)) + return acl ? -EACCES : 0; + name = XATTR_NAME_POSIX_ACL_DEFAULT; + name_len = sizeof(XATTR_NAME_POSIX_ACL_DEFAULT) - 1; + break; + + default: + return -EINVAL; + } + + if (!acl) { + size = 0; + value = NULL; + } else { + size = posix_acl_xattr_size(acl->a_count); + value = ntfs_malloc(size); + if (!value) + return -ENOMEM; + + err = posix_acl_to_xattr(mnt_userns, acl, value, size); + if (err < 0) + goto out; + } + + err = ntfs_set_ea(inode, name, name_len, value, size, + acl ? 0 : XATTR_REPLACE, locked); + if (!err) + set_cached_acl(inode, type, acl); + +out: + ntfs_free(value); + + return err; +} + +/* + * ntfs_set_acl + * + * inode_operations::set_acl + */ +int ntfs_set_acl(struct user_namespace *mnt_userns, struct inode *inode, + struct posix_acl *acl, int type) +{ + return ntfs_set_acl_ex(mnt_userns, inode, acl, type, 0); +} + +static int ntfs_xattr_get_acl(struct user_namespace *mnt_userns, + struct inode *inode, int type, void *buffer, + size_t size) +{ + struct posix_acl *acl; + int err; + + if (!(inode->i_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(mnt_userns, acl, buffer, size); + ntfs_posix_acl_release(acl); + + return err; +} + +static int ntfs_xattr_set_acl(struct user_namespace *mnt_userns, + struct inode *inode, int type, const void *value, + size_t size) +{ + struct posix_acl *acl; + int err; + + if (!(inode->i_sb->s_flags & SB_POSIXACL)) + return -EOPNOTSUPP; + + if (!inode_owner_or_capable(mnt_userns, inode)) + return -EPERM; + + if (!value) { + acl = NULL; + } else { + acl = posix_acl_from_xattr(mnt_userns, value, size); + if (IS_ERR(acl)) + return PTR_ERR(acl); + + if (acl) { + err = posix_acl_valid(mnt_userns, acl); + if (err) + goto release_and_out; + } + } + + err = ntfs_set_acl(mnt_userns, inode, acl, type); + +release_and_out: + ntfs_posix_acl_release(acl); + return err; +} + +/* + * Initialize the ACLs of a new inode. Called from ntfs_create_inode. + */ +int ntfs_init_acl(struct user_namespace *mnt_userns, 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(mnt_userns, 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(mnt_userns, inode, default_acl, + ACL_TYPE_DEFAULT, 1); + + if (!acl) + inode->i_acl = NULL; + else if (!err) + err = ntfs_set_acl_ex(mnt_userns, inode, acl, ACL_TYPE_ACCESS, + 1); + + posix_acl_release(acl); +out1: + posix_acl_release(default_acl); + +out: + return err; +} +#endif + +/* + * ntfs_acl_chmod + * + * helper for 'ntfs3_setattr' + */ +int ntfs_acl_chmod(struct user_namespace *mnt_userns, struct inode *inode) +{ + struct super_block *sb = inode->i_sb; + + if (!(sb->s_flags & SB_POSIXACL)) + return 0; + + if (S_ISLNK(inode->i_mode)) + return -EOPNOTSUPP; + + return posix_acl_chmod(mnt_userns, inode, inode->i_mode); +} + +/* + * ntfs_permission + * + * inode_operations::permission + */ +int ntfs_permission(struct user_namespace *mnt_userns, struct inode *inode, + int mask) +{ + if (ntfs_sb(inode->i_sb)->options.no_acs_rules) { + /* "no access rules" mode - allow all changes */ + return 0; + } + + return generic_permission(mnt_userns, inode, mask); +} + +/* + * 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; + + if (!(ni->ni_flags & NI_FLAG_EA)) { + /* no xattr in file */ + return 0; + } + + ni_lock(ni); + + ret = ntfs_list_ea(ni, buffer, size); + + ni_unlock(ni); + + 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(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; + } + +#ifdef CONFIG_NTFS3_FS_POSIX_ACL + 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)))) { + /* TODO: init_user_ns? */ + err = ntfs_xattr_get_acl( + &init_user_ns, inode, + name_len == sizeof(XATTR_NAME_POSIX_ACL_ACCESS) - 1 + ? ACL_TYPE_ACCESS + : ACL_TYPE_DEFAULT, + buffer, size); + goto out; + } +#endif + /* deal with ntfs extended attribute */ + err = ntfs_get_ea(inode, name, name_len, buffer, size, NULL); + +out: + return err; +} + +/* + * ntfs_setxattr + * + * inode_operations::setxattr + */ +static noinline int ntfs_setxattr(const struct xattr_handler *handler, + struct user_namespace *mnt_userns, + 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); + enum FILE_ATTRIBUTE 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; + new_fa = cpu_to_le32(*(u8 *)value); + goto set_new_fa; + } + + if (name_len == sizeof(SYSTEM_NTFS_ATTRIB) - 1 && + !memcmp(name, SYSTEM_NTFS_ATTRIB, sizeof(SYSTEM_NTFS_ATTRIB))) { + if (size != sizeof(u32)) + goto out; + new_fa = cpu_to_le32(*(u32 *)value); + + if (S_ISREG(inode->i_mode)) { + /* Process compressed/sparsed in special way*/ + ni_lock(ni); + err = ni_new_attr_flags(ni, new_fa); + ni_unlock(ni); + if (err) + goto out; + } +set_new_fa: + /* + * Thanks Mark Harmstone: + * keep directory bit consistency + */ + 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; + if (new_fa & FILE_ATTRIBUTE_READONLY) + inode->i_mode &= ~0222; + else + inode->i_mode |= 0222; + /* 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; + } + +#ifdef CONFIG_NTFS3_FS_POSIX_ACL + 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( + mnt_userns, inode, + name_len == sizeof(XATTR_NAME_POSIX_ACL_ACCESS) - 1 + ? ACL_TYPE_ACCESS + : ACL_TYPE_DEFAULT, + value, size); + goto out; + } +#endif + /* deal with ntfs extended attribute */ + err = ntfs_set_ea(inode, name, name_len, value, size, flags, 0); + +out: + return err; +} + +/* + * ntfs_save_wsl_perm + * + * save uid/gid/mode in xattr + */ +int ntfs_save_wsl_perm(struct inode *inode) +{ + int err; + __le32 value; + + value = cpu_to_le32(i_uid_read(inode)); + err = ntfs_set_ea(inode, "$LXUID", sizeof("$LXUID") - 1, &value, + sizeof(value), 0, 0); + if (err) + goto out; + + value = cpu_to_le32(i_gid_read(inode)); + err = ntfs_set_ea(inode, "$LXGID", sizeof("$LXGID") - 1, &value, + sizeof(value), 0, 0); + if (err) + goto out; + + value = cpu_to_le32(inode->i_mode); + err = ntfs_set_ea(inode, "$LXMOD", sizeof("$LXMOD") - 1, &value, + sizeof(value), 0, 0); + if (err) + goto out; + + if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode)) { + value = cpu_to_le32(inode->i_rdev); + err = ntfs_set_ea(inode, "$LXDEV", sizeof("$LXDEV") - 1, &value, + sizeof(value), 0, 0); + if (err) + goto out; + } + +out: + /* In case of error should we delete all WSL xattr? */ + return err; +} + +/* + * ntfs_get_wsl_perm + * + * get uid/gid/mode from xattr + * it is called from ntfs_iget5->ntfs_read_mft + */ +void ntfs_get_wsl_perm(struct inode *inode) +{ + size_t sz; + __le32 value[3]; + + if (ntfs_get_ea(inode, "$LXUID", sizeof("$LXUID") - 1, &value[0], + sizeof(value[0]), &sz) == sizeof(value[0]) && + ntfs_get_ea(inode, "$LXGID", sizeof("$LXGID") - 1, &value[1], + sizeof(value[1]), &sz) == sizeof(value[1]) && + ntfs_get_ea(inode, "$LXMOD", sizeof("$LXMOD") - 1, &value[2], + sizeof(value[2]), &sz) == sizeof(value[2])) { + i_uid_write(inode, (uid_t)le32_to_cpu(value[0])); + i_gid_write(inode, (gid_t)le32_to_cpu(value[1])); + inode->i_mode = le32_to_cpu(value[2]); + + if (ntfs_get_ea(inode, "$LXDEV", sizeof("$$LXDEV") - 1, + &value[0], sizeof(value), + &sz) == sizeof(value[0])) { + inode->i_rdev = le32_to_cpu(value[0]); + } + } +} + +static bool ntfs_xattr_user_list(struct dentry *dentry) +{ + return true; +} + +// clang-format off +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, +}; +// clang-format on -- 2.30.0

1 0

[PATCH OLK-5.10 003/107] fs/ntfs3: Add bitmap
by Yin Xiujiang 08 Dec '21

08 Dec '21

From: Konstantin Komarov <almaz.alexandrovich(a)paragon-software.com> mainline inclusion from mainline-v5.15-rc1 commit 3f3b442b5ad2455507c9bfdacf39a3792eb3a6d0 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4G67J?from=project-issue CVE: NA ---------------------------------------------------------------------- This adds bitmap Signed-off-by: Konstantin Komarov <almaz.alexandrovich(a)paragon-software.com> Signed-off-by: Yin Xiujiang <yinxiujiang(a)kylinos.cn> --- fs/ntfs3/bitfunc.c | 135 ++++ fs/ntfs3/bitmap.c | 1519 ++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 1654 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..2de5faef2721 --- /dev/null +++ b/fs/ntfs3/bitfunc.c @@ -0,0 +1,135 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * + * Copyright (C) 2019-2021 Paragon Software GmbH, All rights reserved. + * + */ +#include <linux/blkdev.h> +#include <linux/buffer_head.h> +#include <linux/fs.h> +#include <linux/nls.h> + +#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..32aab0031221 --- /dev/null +++ b/fs/ntfs3/bitmap.c @@ -0,0 +1,1519 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * + * Copyright (C) 2019-2021 Paragon Software GmbH, All rights reserved. + * + * This code builds two trees of free clusters extents. + * Trees are sorted by start of extent and by length of extent. + * NTFS_MAX_WND_EXTENTS defines the maximum number of elements in trees. + * In extreme case code reads on-disk bitmap to find free clusters + * + */ + +#include <linux/blkdev.h> +#include <linux/buffer_head.h> +#include <linux/fs.h> +#include <linux/nls.h> + +#include "debug.h" +#include "ntfs.h" +#include "ntfs_fs.h" + +/* + * Maximum number of extents in tree. + */ +#define NTFS_MAX_WND_EXTENTS (32u * 1024u) + +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 struct kmem_cache *ntfs_enode_cachep; + +int __init ntfs3_init_bitmap(void) +{ + ntfs_enode_cachep = + kmem_cache_create("ntfs3_enode_cache", sizeof(struct e_node), 0, + SLAB_RECLAIM_ACCOUNT, NULL); + return ntfs_enode_cachep ? 0 : -ENOMEM; +} + +void ntfs3_exit_bitmap(void) +{ + kmem_cache_destroy(ntfs_enode_cachep); +} + +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 + * + * Frees all resources + */ +void wnd_close(struct wnd_bitmap *wnd) +{ + struct rb_node *node, *next; + + 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); + kmem_cache_free(ntfs_enode_cachep, + 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 'start' 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; +} + +/* + * 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 + kmem_cache_free(ntfs_enode_cachep, 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) + kmem_cache_free(ntfs_enode_cachep, 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 : kmem_cache_alloc(ntfs_enode_cachep, GFP_ATOMIC); + 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; + kmem_cache_free(ntfs_enode_cachep, 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; + kmem_cache_free(ntfs_enode_cachep, 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 = kmem_cache_alloc(ntfs_enode_cachep, GFP_ATOMIC); + 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) { + u32 off = vbo & sbi->cluster_mask; + + if (!run_lookup_entry(&wnd->run, vbo >> cluster_bits, + &lcn, &clen, NULL)) { + err = -ENOENT; + goto out; + } + + lbo = ((u64)lcn << cluster_bits) + off; + len = ((u64)clen << cluster_bits) - off; + } + + 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; + + wnd->free_bits = ntfs_zalloc(wnd->nwnd * sizeof(u16)); + 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) { + new_free = ntfs_malloc(new_wnd * sizeof(u16)); + 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)); + 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; +} -- 2.30.0

1 0

[PATCH OLK-5.10 002/107] fs/ntfs3: Add initialization of super block
by Yin Xiujiang 08 Dec '21

08 Dec '21

From: Konstantin Komarov <almaz.alexandrovich(a)paragon-software.com> mainline inclusion from mainline-v5.15-rc1 commit 82cae269cfa953032fbb8980a7d554d60fb00b17 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4G67J?from=project-issue CVE: NA ---------------------------------------------------------------------- This adds initialization of super block Signed-off-by: Konstantin Komarov <almaz.alexandrovich(a)paragon-software.com> Signed-off-by: Yin Xiujiang <yinxiujiang(a)kylinos.cn> --- fs/ntfs3/fsntfs.c | 2551 +++++++++++++++++++++++++++++++++++++++++++ fs/ntfs3/index.c | 2647 +++++++++++++++++++++++++++++++++++++++++++++ fs/ntfs3/inode.c | 2029 ++++++++++++++++++++++++++++++++++ fs/ntfs3/super.c | 1504 ++++++++++++++++++++++++++ 4 files changed, 8731 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..92140050fb6c --- /dev/null +++ b/fs/ntfs3/fsntfs.c @@ -0,0 +1,2551 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * + * Copyright (C) 2019-2021 Paragon Software GmbH, All rights reserved. + * + */ + +#include <linux/blkdev.h> +#include <linux/buffer_head.h> +#include <linux/fs.h> +#include <linux/nls.h> + +#include "debug.h" +#include "ntfs.h" +#include "ntfs_fs.h" + +// clang-format off +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'), +}; + +#ifdef CONFIG_NTFS3_LZX_XPRESS +const __le16 WOF_NAME[17] = { + cpu_to_le16('W'), cpu_to_le16('o'), cpu_to_le16('f'), cpu_to_le16('C'), + cpu_to_le16('o'), cpu_to_le16('m'), cpu_to_le16('p'), cpu_to_le16('r'), + cpu_to_le16('e'), cpu_to_le16('s'), cpu_to_le16('s'), cpu_to_le16('e'), + cpu_to_le16('d'), cpu_to_le16('D'), cpu_to_le16('a'), cpu_to_le16('t'), + cpu_to_le16('a'), +}; +#endif + +// clang-format on + +/* + * 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) { + /* Fixup does not match! Is it serious error? */ + ret = -E_NTFS_FIXUP; + } + + /* 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; + bool initialized = false; + struct MFT_REF ref; + struct inode *inode; + + /* Check for 4GB */ + if (ni->vfs_inode.i_size >= 0x100000000ull) { + ntfs_err(sb, "\x24LogFile 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); + + /* LogFile should not contains attribute list */ + err = ni_load_all_mi(sbi->mft.ni); + if (!err) + err = log_replay(ni, &initialized); + + iput(inode); + sbi->mft.ni = NULL; + + sync_blockdev(sb->s_bdev); + invalidate_bdev(sb->s_bdev); + + if (sbi->flags & NTFS_FLAGS_NEED_REPLAY) { + err = 0; + goto out; + } + + if (sb_rdonly(sb) || !initialized) + goto out; + + /* fill LogFile by '-1' if it is initialized */ + err = ntfs_bio_fill_1(sbi, &ni->file.run); + +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; + + mutex_lock_nested(&ni->ni_lock, NTFS_INODE_MUTEX_DIRTY); + + 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: + ni_unlock(ni); + if (err) + return err; + + mark_inode_dirty(&ni->vfs_inode); + /*verify(!ntfs_update_mftmirr()); */ + + /* + * if we used wait=1, sync_inode_metadata waits for the io for the + * inode to finish. It hangs when media is removed. + * So wait=0 is sent down to sync_inode_metadata + * and filemap_fdatawrite is used for the data blocks + */ + err = sync_inode_metadata(&ni->vfs_inode, 0); + if (!err) + err = filemap_fdatawrite(ni->vfs_inode.i_mapping); + + 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, vcn = vbo >> cluster_bits, vcn_next; + u64 lbo, len; + size_t idx; + + if (!run_lookup_entry(run, vcn, &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; + + vcn_next = vcn + clen; + if (!run_get_entry(run, ++idx, &vcn, &lcn, &clen) || + vcn != vcn_next) + return -ENOENT; + + if (lcn == SPARSE_LCN) + return -EINVAL; + + if (buf) + buf = Add2Ptr(buf, op); + + lbo = ((u64)lcn << cluster_bits); + len = ((u64)clen << cluster_bits); + } + + 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 vcn_next, vcn = vbo >> cluster_bits; + 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, vcn, &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); + + vcn_next = vcn + clen; + if (!run_get_entry(run, ++idx, &vcn, &lcn, &clen) || + vcn != vcn_next) { + 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, '-E_NTFS_FIXUP' 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; + CLST vcn_next, vcn = vbo >> cluster_bits; + u32 off; + u32 nbh = 0; + CLST lcn, clen; + u64 lbo, len; + size_t idx; + + nb->bytes = bytes; + + if (!run_lookup_entry(run, vcn, &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); + + vcn_next = vcn + clen; + if (!run_get_entry(run, ++idx, &vcn, &lcn, &clen) || + vcn != vcn_next) { + 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; +} + +static inline struct bio *ntfs_alloc_bio(u32 nr_vecs) +{ + struct bio *bio = bio_alloc(GFP_NOFS | __GFP_HIGH, nr_vecs); + + if (!bio && (current->flags & PF_MEMALLOC)) { + while (!bio && (nr_vecs /= 2)) + bio = bio_alloc(GFP_NOFS | __GFP_HIGH, nr_vecs); + } + return bio; +} + +/* read/write pages from/to disk*/ +int ntfs_bio_pages(struct ntfs_sb_info *sbi, const struct runs_tree *run, + struct page **pages, u32 nr_pages, u64 vbo, u32 bytes, + u32 op) +{ + int err = 0; + struct bio *new, *bio = NULL; + struct super_block *sb = sbi->sb; + struct block_device *bdev = sb->s_bdev; + struct page *page; + u8 cluster_bits = sbi->cluster_bits; + CLST lcn, clen, vcn, vcn_next; + u32 add, off, page_idx; + u64 lbo, len; + size_t run_idx; + struct blk_plug plug; + + if (!bytes) + return 0; + + blk_start_plug(&plug); + + /* align vbo and bytes to be 512 bytes aligned */ + lbo = (vbo + bytes + 511) & ~511ull; + vbo = vbo & ~511ull; + bytes = lbo - vbo; + + vcn = vbo >> cluster_bits; + if (!run_lookup_entry(run, vcn, &lcn, &clen, &run_idx)) { + err = -ENOENT; + goto out; + } + off = vbo & sbi->cluster_mask; + page_idx = 0; + page = pages[0]; + + for (;;) { + lbo = ((u64)lcn << cluster_bits) + off; + len = ((u64)clen << cluster_bits) - off; +new_bio: + new = ntfs_alloc_bio(nr_pages - page_idx); + if (!new) { + err = -ENOMEM; + goto out; + } + if (bio) { + bio_chain(bio, new); + submit_bio(bio); + } + bio = new; + bio_set_dev(bio, bdev); + bio->bi_iter.bi_sector = lbo >> 9; + bio->bi_opf = op; + + while (len) { + off = vbo & (PAGE_SIZE - 1); + add = off + len > PAGE_SIZE ? (PAGE_SIZE - off) : len; + + if (bio_add_page(bio, page, add, off) < add) + goto new_bio; + + if (bytes <= add) + goto out; + bytes -= add; + vbo += add; + + if (add + off == PAGE_SIZE) { + page_idx += 1; + if (WARN_ON(page_idx >= nr_pages)) { + err = -EINVAL; + goto out; + } + page = pages[page_idx]; + } + + if (len <= add) + break; + len -= add; + lbo += add; + } + + vcn_next = vcn + clen; + if (!run_get_entry(run, ++run_idx, &vcn, &lcn, &clen) || + vcn != vcn_next) { + err = -ENOENT; + goto out; + } + off = 0; + } +out: + if (bio) { + if (!err) + err = submit_bio_wait(bio); + bio_put(bio); + } + blk_finish_plug(&plug); + + return err; +} + +/* + * Helper for ntfs_loadlog_and_replay + * fill on-disk logfile range by (-1) + * this means empty logfile + */ +int ntfs_bio_fill_1(struct ntfs_sb_info *sbi, const struct runs_tree *run) +{ + int err = 0; + struct super_block *sb = sbi->sb; + struct block_device *bdev = sb->s_bdev; + u8 cluster_bits = sbi->cluster_bits; + struct bio *new, *bio = NULL; + CLST lcn, clen; + u64 lbo, len; + size_t run_idx; + struct page *fill; + void *kaddr; + struct blk_plug plug; + + fill = alloc_page(GFP_KERNEL); + if (!fill) + return -ENOMEM; + + kaddr = kmap_atomic(fill); + memset(kaddr, -1, PAGE_SIZE); + kunmap_atomic(kaddr); + flush_dcache_page(fill); + lock_page(fill); + + if (!run_lookup_entry(run, 0, &lcn, &clen, &run_idx)) { + err = -ENOENT; + goto out; + } + + /* + * TODO: try blkdev_issue_write_same + */ + blk_start_plug(&plug); + do { + lbo = (u64)lcn << cluster_bits; + len = (u64)clen << cluster_bits; +new_bio: + new = ntfs_alloc_bio(BIO_MAX_VECS); + if (!new) { + err = -ENOMEM; + break; + } + if (bio) { + bio_chain(bio, new); + submit_bio(bio); + } + bio = new; + bio_set_dev(bio, bdev); + bio->bi_opf = REQ_OP_WRITE; + bio->bi_iter.bi_sector = lbo >> 9; + + for (;;) { + u32 add = len > PAGE_SIZE ? PAGE_SIZE : len; + + if (bio_add_page(bio, fill, add, 0) < add) + goto new_bio; + + lbo += add; + if (len <= add) + break; + len -= add; + } + } while (run_get_entry(run, ++run_idx, NULL, &lcn, &clen)); + + if (bio) { + if (!err) + err = submit_bio_wait(bio); + bio_put(bio); + } + blk_finish_plug(&plug); +out: + unlock_page(fill); + put_page(fill); + + 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 struct_size(sid, SubAuthority, sid->SubAuthorityCount); +} + +/* + * 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 && + acl->AclRevision != ACL_REVISION_DS) { + /* + * This value should be ACL_REVISION, unless the ACL contains an + * object-specific ACE, in which case this value must be ACL_REVISION_DS. + * All ACEs in an ACL must be at the same revision level. + */ + 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 & 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(); + 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; + + mutex_lock_nested(&ni->ni_lock, NTFS_INODE_MUTEX_SECURITY); + + fnd_sii = fnd_get(); + 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_malloc(*size); + 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); + ni_unlock(ni); + + 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_zalloc(aligned_sec_size); + if (!d_security) + return -ENOMEM; + + mutex_lock_nested(&ni->ni_lock, NTFS_INODE_MUTEX_SECURITY); + + fnd_sdh = fnd_get(); + 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); + mark_inode_dirty(&ni->vfs_inode); + ni_unlock(ni); + 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; + + mutex_lock_nested(&ni->ni_lock, NTFS_INODE_MUTEX_OBJID); + + err = indx_delete_entry(indx, ni, guid, sizeof(*guid), NULL); + + mark_inode_dirty(&ni->vfs_inode); + ni_unlock(ni); + + 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.de.view.data_off = cpu_to_le16(offsetof(struct NTFS_DE_R, zero)); + re.de.size = cpu_to_le16(sizeof(struct NTFS_DE_R)); + re.de.key_size = cpu_to_le16(sizeof(re.key)); + + re.key.ReparseTag = rtag; + memcpy(&re.key.ref, ref, sizeof(*ref)); + + mutex_lock_nested(&ni->ni_lock, NTFS_INODE_MUTEX_REPARSE); + + err = indx_insert_entry(indx, ni, &re.de, NULL, NULL); + + mark_inode_dirty(&ni->vfs_inode); + ni_unlock(ni); + + return err; +} + +int ntfs_remove_reparse(struct ntfs_sb_info *sbi, __le32 rtag, + const struct MFT_REF *ref) +{ + int err, diff; + struct ntfs_inode *ni = sbi->reparse.ni; + struct ntfs_index *indx = &sbi->reparse.index_r; + struct ntfs_fnd *fnd = NULL; + struct REPARSE_KEY rkey; + struct NTFS_DE_R *re; + struct INDEX_ROOT *root_r; + + if (!ni) + return -EINVAL; + + rkey.ReparseTag = rtag; + rkey.ref = *ref; + + mutex_lock_nested(&ni->ni_lock, NTFS_INODE_MUTEX_REPARSE); + + if (rtag) { + err = indx_delete_entry(indx, ni, &rkey, sizeof(rkey), NULL); + goto out1; + } + + fnd = fnd_get(); + if (!fnd) { + err = -ENOMEM; + goto out1; + } + + root_r = indx_get_root(indx, ni, NULL, NULL); + if (!root_r) { + err = -EINVAL; + goto out; + } + + /* 1 - forces to ignore rkey.ReparseTag when comparing keys */ + err = indx_find(indx, ni, root_r, &rkey, sizeof(rkey), (void *)1, &diff, + (struct NTFS_DE **)&re, fnd); + if (err) + goto out; + + if (memcmp(&re->key.ref, ref, sizeof(*ref))) { + /* Impossible. Looks like volume corrupt?*/ + 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: + mark_inode_dirty(&ni->vfs_inode); + ni_unlock(ni); + + 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..6aa9540ece47 --- /dev/null +++ b/fs/ntfs3/index.c @@ -0,0 +1,2647 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * + * Copyright (C) 2019-2021 Paragon Software GmbH, All rights reserved. + * + */ + +#include <linux/blkdev.h> +#include <linux/buffer_head.h> +#include <linux/fs.h> +#include <linux/nls.h> + +#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 + * key1 - cpu_str, key2 - ATTR_FILE_NAME + */ +static int cmp_fnames(const void *key1, size_t l1, const void *key2, size_t l2, + const void *data) +{ + const struct ATTR_FILE_NAME *f2 = key2; + const struct ntfs_sb_info *sbi = data; + const struct ATTR_FILE_NAME *f1; + u16 fsize2; + bool both_case; + + if (l2 <= offsetof(struct ATTR_FILE_NAME, name)) + return -1; + + fsize2 = fname_full_size(f2); + if (l2 < fsize2) + return -1; + + both_case = f2->type != FILE_NAME_DOS /*&& !sbi->options.nocase*/; + if (!l1) { + const struct le_str *s2 = (struct le_str *)&f2->name_len; + + /* + * If names are equal (case insensitive) + * try to compare it case sensitive + */ + return ntfs_cmp_names_cpu(key1, s2, sbi->upcase, both_case); + } + + f1 = key1; + return ntfs_cmp_names(f1->name, f1->name_len, f2->name, f2->name_len, + sbi->upcase, both_case); +} + +/* $SII of $Secure and $Q of Quota */ +static int cmp_uint(const void *key1, size_t l1, const void *key2, size_t l2, + const void *data) +{ + const u32 *k1 = key1; + const u32 *k2 = key2; + + if (l2 < sizeof(u32)) + return -1; + + if (*k1 < *k2) + return -1; + if (*k1 > *k2) + return 1; + return 0; +} + +/* $SDH of $Secure */ +static int cmp_sdh(const void *key1, size_t l1, const void *key2, size_t l2, + const void *data) +{ + const struct SECURITY_KEY *k1 = key1; + const struct SECURITY_KEY *k2 = key2; + 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 (data) { + 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; +} + +/* $O of ObjId and "$R" for Reparse */ +static int cmp_uints(const void *key1, size_t l1, const void *key2, size_t l2, + const void *data) +{ + const __le32 *k1 = key1; + const __le32 *k2 = key2; + size_t count; + + if ((size_t)data == 1) { + /* + * ni_delete_all -> ntfs_remove_reparse -> delete all with this reference + * k1, k2 - pointers to REPARSE_KEY + */ + + k1 += 1; // skip REPARSE_KEY.ReparseTag + k2 += 1; // skip REPARSE_KEY.ReparseTag + if (l2 <= sizeof(int)) + return -1; + l2 -= sizeof(int); + if (l1 <= sizeof(int)) + return 1; + l1 -= sizeof(int); + } + + 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 &cmp_fnames; + break; + case ATTR_ZERO: + switch (root->rule) { + case NTFS_COLLATION_TYPE_UINT: + return &cmp_uint; + case NTFS_COLLATION_TYPE_SECURITY_HASH: + return &cmp_sdh; + case NTFS_COLLATION_TYPE_UINTS: + return &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 (WARN_ON(off >= data_size)) { + /* looks like filesystem error */ + 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; +} + +/* + * if ntfs_readdir calls this function (indx_used_bit -> scan_nres_bitmap), + * inode is shared locked and no ni_lock + * use rw_semaphore for read/write access to bitmap_run + */ +static int scan_nres_bitmap(struct ntfs_inode *ni, struct ATTRIB *bitmap, + struct ntfs_index *indx, size_t from, + bool (*fn)(const ulong *buf, u32 bit, u32 bits, + size_t *ret), + size_t *ret) +{ + struct ntfs_sb_info *sbi = ni->mi.sbi; + struct super_block *sb = sbi->sb; + struct runs_tree *run = &indx->bitmap_run; + struct rw_semaphore *lock = &indx->run_lock; + 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, clen, vcn, vcn_next; + size_t idx; + struct buffer_head *bh; + bool ok; + + *ret = MINUS_ONE_T; + + if (vblock >= eblock) + return 0; + + from &= nbits - 1; + vcn = vbo >> sbi->cluster_bits; + + down_read(lock); + ok = run_lookup_entry(run, vcn, &lcn, &clen, &idx); + up_read(lock); + +next_run: + if (!ok) { + int err; + const struct INDEX_NAMES *name = &s_index_names[indx->type]; + + down_write(lock); + err = attr_load_runs_vcn(ni, ATTR_BITMAP, name->name, + name->name_len, run, vcn); + up_write(lock); + if (err) + return err; + down_read(lock); + ok = run_lookup_entry(run, vcn, &lcn, &clen, &idx); + up_read(lock); + if (!ok) + return -EINVAL; + } + + blen = (sector_t)clen * sbi->blocks_per_cluster; + block = (sector_t)lcn * sbi->blocks_per_cluster; + + for (; blk < blen; blk++, from = 0) { + 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; + } + } + blk = 0; + vcn_next = vcn + clen; + down_read(lock); + ok = run_get_entry(run, ++idx, &vcn, &lcn, &clen) && vcn == vcn_next; + if (!ok) + vcn = vcn_next; + up_read(lock); + 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]; + int err; + + 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 { + err = scan_nres_bitmap(ni, b, indx, 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]; + int err; + + 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 { + err = scan_nres_bitmap(ni, b, indx, 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 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 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]; +} + +/* + * 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_malloc(sizeof(u16) * nslots); + 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_malloc(sizeof(u16) * new_slots); + 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; + } + + init_rwsem(&indx->run_lock); + + 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_zalloc(sizeof(struct indx_node)); + if (!r) + return ERR_PTR(-ENOMEM); + + index = ntfs_zalloc(bytes); + 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); +} + +/* + * if ntfs_readdir calls this function + * inode is shared locked and no ni_lock + * use rw_semaphore for read/write access to alloc_run + */ +int indx_read(struct ntfs_index *indx, struct ntfs_inode *ni, CLST vbn, + struct indx_node **node) +{ + int err; + struct INDEX_BUFFER *ib; + struct runs_tree *run = &indx->alloc_run; + struct rw_semaphore *lock = &indx->run_lock; + 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_zalloc(sizeof(struct indx_node)); + if (!in) + return -ENOMEM; + } else { + nb_put(&in->nb); + } + + ib = in->index; + if (!ib) { + ib = ntfs_malloc(bytes); + if (!ib) { + err = -ENOMEM; + goto out; + } + } + + down_read(lock); + err = ntfs_read_bh(ni->mi.sbi, run, vbo, &ib->rhdr, bytes, &in->nb); + up_read(lock); + if (!err) + goto ok; + + if (err == -E_NTFS_FIXUP) + goto ok; + + if (err != -ENOENT) + goto out; + + name = &s_index_names[indx->type]; + down_write(lock); + err = attr_load_runs_range(ni, ATTR_ALLOC, name->name, name->name_len, + run, vbo, vbo + bytes); + up_write(lock); + if (err) + goto out; + + down_read(lock); + err = ntfs_read_bh(ni->mi.sbi, run, vbo, &ib->rhdr, bytes, &in->nb); + up_read(lock); + if (err == -E_NTFS_FIXUP) + goto ok; + + if (err) + goto out; + +ok: + if (err == -E_NTFS_FIXUP) { + 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 data_size = 1u << indx->index_bits; + u32 alloc_size = ntfs_up_cluster(sbi, data_size); + 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; + + alloc->nres.valid_size = alloc->nres.data_size = cpu_to_le64(data_size); + + err = ni_insert_resident(ni, bitmap_size(1), ATTR_BITMAP, in->name, + in->name_len, &bitmap, NULL); + if (err) + goto out2; + + if (in->name == I30_NAME) { + ni->vfs_inode.i_size = data_size; + inode_set_bytes(&ni->vfs_inode, alloc_size); + } + + memcpy(&indx->alloc_run, &run, sizeof(run)); + + *vbn = 0; + + 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; + u64 bmp_size, bmp_size_v; + 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) { + bmp_size = le64_to_cpu(bmp->nres.data_size); + bmp_size_v = le64_to_cpu(bmp->nres.valid_size); + } else { + bmp_size = bmp_size_v = le32_to_cpu(bmp->res.data_size); + } + + bit = bmp_size << 3; + } + + data_size = (u64)(bit + 1) << indx->index_bits; + + if (bmp) { + /* Increase bitmap */ + err = attr_set_size(ni, ATTR_BITMAP, in->name, in->name_len, + &indx->bitmap_run, bitmap_size(bit + 1), + NULL, true, NULL); + if (err) + goto out1; + } + + alloc = ni_find_attr(ni, NULL, NULL, ATTR_ALLOC, in->name, in->name_len, + NULL, &mi); + if (!alloc) { + if (bmp) + goto out2; + goto out1; + } + + /* Increase allocation */ + err = attr_set_size(ni, ATTR_ALLOC, in->name, in->name_len, + &indx->alloc_run, data_size, &data_size, true, + NULL); + if (err) { + if (bmp) + goto out2; + goto out1; + } + + *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, bmp_size, &bmp_size_v, 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, used, to_move; + u32 root_size, new_root_size; + struct ntfs_sb_info *sbi; + 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; + 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); + 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 */ + mi_resize_attr(mi, attr, ds_root); + 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; + + 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) + mi_resize_attr(mi, attr, ds_root); + + /* 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); + mi->dirty = true; + + /* Create alloc and bitmap attributes (if not) */ + err = run_is_empty(&indx->alloc_run) + ? indx_create_allocate(indx, ni, &new_vbn) + : indx_add_allocate(indx, ni, &new_vbn); + + /* layout of record may be changed, so rescan root */ + root = indx_get_root(indx, ni, &attr, &mi); + if (!root) { + /* bug? */ + ntfs_set_state(sbi, NTFS_DIRTY_ERROR); + err = -EINVAL; + goto out1; + } + + if (err) { + /* restore root */ + if (mi_resize_attr(mi, attr, -ds_root)) + memcpy(attr, a_root, asize); + else { + /* bug? */ + ntfs_set_state(sbi, NTFS_DIRTY_ERROR); + } + goto out1; + } + + e = (struct NTFS_DE *)(root + 1); + *(__le64 *)(e + 1) = cpu_to_le64(new_vbn); + mi->dirty = true; + + /* 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_malloc(sp_size + sizeof(u64)); + 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(); + 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: + 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_data; + 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, b, indx, bit, &scan_for_used, &used); + if (err) + return err; + + if (used != MINUS_ONE_T) + return 0; + } + + new_data = (u64)bit << indx->index_bits; + + err = attr_set_size(ni, ATTR_ALLOC, in->name, in->name_len, + &indx->alloc_run, new_data, &new_data, false, NULL); + if (err) + return err; + + 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_malloc(le16_to_cpu(te->size) + sizeof(u64)); + 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(); + if (!fnd) { + err = -ENOMEM; + goto out2; + } + + fnd2 = fnd_get(); + 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; + } + +out: + fnd_put(fnd2); +out1: + fnd_put(fnd); +out2: + return err; +} + +/* + * Update duplicated information in directory entry + * 'dup' - info from MFT record + */ +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(); + if (!fnd) { + err = -ENOMEM; + goto out1; + } + + root = indx_get_root(indx, ni, NULL, &mi); + if (!root) { + err = -EINVAL; + goto out; + } + + /* Find entry in directory */ + 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) { + /* directory entry in index */ + err = indx_write(indx, ni, fnd->nodes[fnd->level - 1], sync); + } else { + /* directory entry in directory MFT record */ + mi->dirty = true; + if (sync) + err = mi_write(mi, 1); + else + 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..bf51e294432e --- /dev/null +++ b/fs/ntfs3/inode.c @@ -0,0 +1,2029 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * + * Copyright (C) 2019-2021 Paragon Software GmbH, All rights reserved. + * + */ + +#include <linux/blkdev.h> +#include <linux/buffer_head.h> +#include <linux/fs.h> +#include <linux/iversion.h> +#include <linux/mpage.h> +#include <linux/namei.h> +#include <linux/nls.h> +#include <linux/uio.h> +#include <linux/version.h> +#include <linux/writeback.h> + +#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; + /* Setup 'uid' and 'gid' */ + inode->i_uid = sbi->options.fs_uid; + inode->i_gid = sbi->options.fs_gid; + + 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, true)) { + 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, NULL) )) + */ +next_attr: + run = NULL; + err = -EINVAL; + attr = ni_enum_attr_ex(ni, attr, &le, NULL); + 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, false)) + 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 CONFIG_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; + /* + * ntfs_get_wsl_perm updates inode->i_uid, inode->i_gid, inode->i_mode + */ + inode->i_mode = mode; + ntfs_get_wsl_perm(inode); + mode = inode->i_mode; + } + goto next_attr; + + default: + goto next_attr; + } + +attr_unpack_run: + roff = le16_to_cpu(attr->nres.run_off); + + t64 = le64_to_cpu(attr->nres.svcn); + err = run_unpack_ex(run, sbi, ino, t64, le64_to_cpu(attr->nres.evcn), + t64, 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; + + if (!names) { + err = -EINVAL; + goto out; + } + + set_nlink(inode, names); + + 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 + */ + 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); // ?? + } else if (S_ISREG(mode)) { + ni->std_fa &= ~FILE_ATTRIBUTE_DIRECTORY; + 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 (S_ISCHR(mode) || S_ISBLK(mode) || S_ISFIFO(mode) || + S_ISSOCK(mode)) { + inode->i_op = &ntfs_special_inode_operations; + init_special_inode(inode, mode, inode->i_rdev); + } 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, void *data) +{ + struct MFT_REF *ref = data; + + return ino_get(ref) == inode->i_ino; +} + +static int ntfs_set_inode(struct inode *inode, void *data) +{ + const struct MFT_REF *ref = data; + + 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), ntfs_test_inode, 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) { + /* inode overlaps? */ + 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); + struct page *page = bh->b_page; + u8 cluster_bits = sbi->cluster_bits; + u32 block_size = sb->s_blocksize; + u64 bytes, lbo, valid; + u32 off; + int err; + CLST vcn, lcn, len; + bool new; + + /*clear previous state*/ + clear_buffer_new(bh); + clear_buffer_uptodate(bh); + + /* direct write uses 'create=0'*/ + if (!create && vbo >= ni->i_valid) { + /* out of valid */ + return 0; + } + + if (vbo >= inode->i_size) { + /* out of size */ + return 0; + } + + if (is_resident(ni)) { + ni_lock(ni); + err = attr_data_read_resident(ni, page); + ni_unlock(ni); + + if (!err) + set_buffer_uptodate(bh); + bh->b_size = block_size; + return err; + } + + 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); + } + + if (new) { + set_buffer_new(bh); + if ((len << cluster_bits) > block_size) + ntfs_sparse_cluster(inode, page, vcn, len); + } + + lbo = ((u64)lcn << cluster_bits) + off; + + set_buffer_mapped(bh); + bh->b_bdev = sb->s_bdev; + bh->b_blocknr = lbo >> sb->s_blocksize_bits; + + valid = ni->i_valid; + + if (ctx == GET_BLOCK_DIRECT_IO_W) { + /*ntfs_direct_IO will update ni->i_valid */ + if (vbo >= valid) + set_buffer_new(bh); + } else if (create) { + /*normal write*/ + if (bytes > bh->b_size) + bytes = bh->b_size; + + if (vbo >= valid) + set_buffer_new(bh); + + if (vbo + bytes > valid) { + ni->i_valid = vbo + bytes; + mark_inode_dirty(inode); + } + } else if (vbo >= valid) { + /* read out of valid data*/ + /* should never be here 'cause already checked */ + clear_buffer_mapped(bh); + } else if (vbo + bytes <= valid) { + /* normal read */ + } else if (vbo + block_size <= valid) { + /* normal short read */ + bytes = block_size; + } else { + /* + * read across valid size: vbo < valid && valid < vbo + block_size + */ + bytes = block_size; + + if (page) { + u32 voff = valid - vbo; + + bh->b_size = block_size; + off = vbo & (PAGE_SIZE - 1); + set_bh_page(bh, page, off); + ll_rw_block(REQ_OP_READ, 0, 1, &bh); + wait_on_buffer(bh); + if (!buffer_uptodate(bh)) { + err = -EIO; + goto out; + } + zero_user_segment(page, off + voff, off + block_size); + } + } + + 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; +} + +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); +} + +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); +} + +static 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); + + if (is_resident(ni)) { + ni_lock(ni); + err = attr_data_read_resident(ni, page); + ni_unlock(ni); + if (err != E_NTFS_NONRESIDENT) { + unlock_page(page); + return err; + } + } + + if (is_compressed(ni)) { + ni_lock(ni); + err = ni_readpage_cmpr(ni, page); + ni_unlock(ni); + return err; + } + + /* normal + sparse files */ + return mpage_readpage(page, ntfs_get_block); +} + +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 (is_resident(ni)) { + /* no readahead for resident */ + return; + } + + if (is_compressed(ni)) { + /* no readahead for compressed */ + return; + } + + valid = ni->i_valid; + pos = readahead_pos(rac); + + if (valid < i_size_read(inode) && pos <= valid && + valid < pos + readahead_length(rac)) { + /* range cross 'valid'. read it page by page */ + return; + } + + mpage_readahead(rac, ntfs_get_block); +} + +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 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); + loff_t vbo = iocb->ki_pos; + loff_t end; + int wr = iov_iter_rw(iter) & WRITE; + loff_t valid; + ssize_t ret; + + if (is_resident(ni)) { + /*switch to buffered write*/ + ret = 0; + goto out; + } + + ret = blockdev_direct_IO(iocb, inode, iter, + wr ? ntfs_get_block_direct_IO_W + : ntfs_get_block_direct_IO_R); + + if (ret <= 0) + goto out; + + end = vbo + ret; + valid = ni->i_valid; + if (wr) { + if (end > valid && !S_ISBLK(inode->i_mode)) { + ni->i_valid = end; + mark_inode_dirty(inode); + } + } else if (vbo < valid && valid < end) { + /* fix page */ + iov_iter_revert(iter, end - valid); + iov_iter_zero(end - valid, iter); + } + +out: + return ret; +} + +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) +{ + struct address_space *mapping = page->mapping; + struct inode *inode = mapping->host; + struct ntfs_inode *ni = ntfs_i(inode); + int err; + + if (is_resident(ni)) { + ni_lock(ni); + err = attr_data_write_resident(ni, page); + ni_unlock(ni); + if (err != E_NTFS_NONRESIDENT) { + unlock_page(page); + return err; + } + } + + return block_write_full_page(page, ntfs_get_block, wbc); +} + +static int ntfs_writepages(struct address_space *mapping, + struct writeback_control *wbc) +{ + struct inode *inode = mapping->host; + struct ntfs_inode *ni = ntfs_i(inode); + /* redirect call to 'ntfs_writepage' for resident files*/ + get_block_t *get_block = is_resident(ni) ? NULL : &ntfs_get_block; + + return mpage_writepages(mapping, wbc, get_block); +} + +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; + struct inode *inode = mapping->host; + struct ntfs_inode *ni = ntfs_i(inode); + + *pagep = NULL; + if (is_resident(ni)) { + struct page *page = grab_cache_page_write_begin( + mapping, pos >> PAGE_SHIFT, flags); + + if (!page) { + err = -ENOMEM; + goto out; + } + + ni_lock(ni); + err = attr_data_read_resident(ni, page); + ni_unlock(ni); + + if (!err) { + *pagep = page; + goto out; + } + unlock_page(page); + put_page(page); + + if (err != E_NTFS_NONRESIDENT) + goto out; + } + + err = block_write_begin(mapping, pos, len, flags, pagep, + ntfs_get_block_write_begin); + +out: + 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; + bool dirty = false; + int err; + + if (is_resident(ni)) { + ni_lock(ni); + err = attr_data_write_resident(ni, page); + ni_unlock(ni); + if (!err) { + dirty = true; + /* clear any buffers in page*/ + if (page_has_buffers(page)) { + struct buffer_head *head, *bh; + + bh = head = page_buffers(page); + do { + clear_buffer_dirty(bh); + clear_buffer_mapped(bh); + set_buffer_uptodate(bh); + } while (head != (bh = bh->b_this_page)); + } + SetPageUptodate(page); + err = copied; + } + unlock_page(page); + put_page(page); + } else { + err = generic_write_end(file, mapping, pos, len, copied, page, + fsdata); + } + + if (err >= 0) { + 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 ntfs3_write_inode(struct inode *inode, struct writeback_control *wbc) +{ + 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; +} + +/* + * number of bytes to for REPARSE_DATA_BUFFER(IO_REPARSE_TAG_SYMLINK) + * for unicode string of 'uni_len' length + */ +static inline u32 ntfs_reparse_bytes(u32 uni_len) +{ + /* header + unicode string + decorated unicode string */ + return sizeof(short) * (2 * uni_len + 4) + + offsetof(struct REPARSE_DATA_BUFFER, + SymbolicLinkReparseBuffer.PathBuffer); +} + +static struct REPARSE_DATA_BUFFER * +ntfs_create_reparse_buffer(struct ntfs_sb_info *sbi, const char *symname, + u32 size, u16 *nsize) +{ + int i, err; + struct REPARSE_DATA_BUFFER *rp; + __le16 *rp_name; + typeof(rp->SymbolicLinkReparseBuffer) *rs; + + rp = ntfs_zalloc(ntfs_reparse_bytes(2 * size + 2)); + if (!rp) + return ERR_PTR(-ENOMEM); + + rs = &rp->SymbolicLinkReparseBuffer; + rp_name = rs->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 out; + + /* err = the length of unicode name of symlink */ + *nsize = ntfs_reparse_bytes(err); + + if (*nsize > sbi->reparse.max_size) { + err = -EFBIG; + goto out; + } + + /* translate linux '/' into windows '\' */ + for (i = 0; i < err; i++) { + if (rp_name[i] == cpu_to_le16('/')) + rp_name[i] = cpu_to_le16('\\'); + } + + rp->ReparseTag = IO_REPARSE_TAG_SYMLINK; + rp->ReparseDataLength = + cpu_to_le16(*nsize - offsetof(struct REPARSE_DATA_BUFFER, + SymbolicLinkReparseBuffer)); + + /* PrintName + SubstituteName */ + rs->SubstituteNameOffset = cpu_to_le16(sizeof(short) * err); + rs->SubstituteNameLength = cpu_to_le16(sizeof(short) * err + 8); + rs->PrintNameLength = rs->SubstituteNameOffset; + + /* + * TODO: use relative path if possible to allow windows to parse this path + * 0-absolute path 1- relative path (SYMLINK_FLAG_RELATIVE) + */ + rs->Flags = 0; + + memmove(rp_name + err + 4, rp_name, sizeof(short) * err); + + /* decorate SubstituteName */ + 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('\\'); + + return rp; +out: + ntfs_free(rp); + return ERR_PTR(err); +} + +struct inode *ntfs_create_inode(struct user_namespace *mnt_userns, + struct inode *dir, struct dentry *dentry, + const struct cpu_str *uni, umode_t mode, + dev_t dev, const char *symname, u32 size, + struct ntfs_fnd *fnd) +{ + 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; + bool rp_inserted = false; + + dir_root = indx_get_root(&dir_ni->dir, dir_ni, NULL, NULL); + if (!dir_root) + return ERR_PTR(-EINVAL); + + if (S_ISDIR(mode)) { + /* use parent's directory attributes */ + fa = dir_ni->std_fa | FILE_ATTRIBUTE_DIRECTORY | + FILE_ATTRIBUTE_ARCHIVE; + /* + * By default child directory inherits parent attributes + * root directory is hidden + system + * Make an exception for children in root + */ + if (dir->i_ino == MFT_REC_ROOT) + fa &= ~(FILE_ATTRIBUTE_HIDDEN | FILE_ATTRIBUTE_SYSTEM); + } else if (S_ISLNK(mode)) { + /* It is good idea that link should be the same type (file/dir) as target */ + fa = FILE_ATTRIBUTE_REPARSE_POINT; + + /* + * linux: there are dir/file/symlink and so on + * NTFS: symlinks are "dir + reparse" or "file + reparse" + * It is good idea to create: + * dir + reparse if 'symname' points to directory + * or + * file + reparse if 'symname' points to file + * Unfortunately kern_path hangs if symname contains 'dir' + */ + + /* + * struct path path; + * + * if (!kern_path(symname, LOOKUP_FOLLOW, &path)){ + * struct inode *target = d_inode(path.dentry); + * + * if (S_ISDIR(target->i_mode)) + * fa |= FILE_ATTRIBUTE_DIRECTORY; + * // if ( target->i_sb == sb ){ + * // use relative path? + * // } + * path_put(&path); + * } + */ + } else if (S_ISREG(mode)) { + if (sbi->options.sparse) { + /* sparsed regular file, cause option 'sparse' */ + fa = FILE_ATTRIBUTE_SPARSE_FILE | + FILE_ATTRIBUTE_ARCHIVE; + } else if (dir_ni->std_fa & FILE_ATTRIBUTE_COMPRESSED) { + /* compressed regular file, if parent is compressed */ + fa = FILE_ATTRIBUTE_COMPRESSED | FILE_ATTRIBUTE_ARCHIVE; + } else { + /* regular file, default attributes */ + fa = FILE_ATTRIBUTE_ARCHIVE; + } + } else { + fa = FILE_ATTRIBUTE_ARCHIVE; + } + + if (!(mode & 0222)) + fa |= FILE_ATTRIBUTE_READONLY; + + /* allocate PATH_MAX bytes */ + 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, fa & FILE_ATTRIBUTE_DIRECTORY); + if (IS_ERR(ni)) { + err = PTR_ERR(ni); + ni = NULL; + goto out3; + } + inode = &ni->vfs_inode; + inode_init_owner(mnt_userns, inode, dir, mode); + + 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; + + mi_get_ref(&ni->mi, &new_de->ref); + + fname = (struct ATTR_FILE_NAME *)(new_de + 1); + mi_get_ref(&dir_ni->mi, &fname->home); + 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 (fa & FILE_ATTRIBUTE_DIRECTORY) { + /* + * regular directory or symlink to directory + * Create root attribute + */ + 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; + } else if (S_ISLNK(mode)) { + /* + * symlink to file + * Create empty resident data attribute + */ + 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; + } else { + /* + * regular file or node + */ + attr->type = ATTR_DATA; + attr->id = cpu_to_le16(aid++); + + if (S_ISREG(mode)) { + /* Create empty 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; + } else { + /* Create empty resident data attribute */ + attr->size = cpu_to_le32(SIZEOF_RESIDENT); + attr->name_off = SIZEOF_RESIDENT_LE; + if (fa & FILE_ATTRIBUTE_SPARSE_FILE) + attr->flags = ATTR_FLAG_SPARSED; + else if (fa & FILE_ATTRIBUTE_COMPRESSED) + attr->flags = ATTR_FLAG_COMPRESSED; + attr->res.data_off = SIZEOF_RESIDENT_LE; + asize = SIZEOF_RESIDENT; + ni->ni_flags |= NI_FLAG_RESIDENT; + } + } + + if (S_ISDIR(mode)) { + 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)) { + rp = ntfs_create_reparse_buffer(sbi, symname, size, &nsize); + + if (IS_ERR(rp)) { + err = PTR_ERR(rp); + rp = NULL; + goto out4; + } + + /* + * Insert ATTR_REPARSE + */ + attr = Add2Ptr(attr, asize); + 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; + } + + 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); + + inode->i_generation = le16_to_cpu(rec->seq); + + dir->i_mtime = dir->i_ctime = inode->i_atime; + + if (S_ISDIR(mode)) { + 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 if (S_ISREG(mode)) { + 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); + } else { + inode->i_op = &ntfs_special_inode_operations; + init_special_inode(inode, mode, dev); + } + +#ifdef CONFIG_NTFS3_FS_POSIX_ACL + if (!S_ISLNK(mode) && (sb->s_flags & SB_POSIXACL)) { + err = ntfs_init_acl(mnt_userns, inode, dir); + if (err) + goto out6; + } else +#endif + { + 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); + + ntfs_save_wsl_perm(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 (S_ISDIR(mode) || 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_PTR(err); + + unlock_new_inode(inode); + + return inode; +} + +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; + + /* allocate PATH_MAX bytes */ + 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); + err = ni_insert_resident(ni, key_size, ATTR_NAME, NULL, 0, &attr, NULL); + if (err) + goto out; + + mi_get_ref(&ni->mi, &new_de->ref); + + fname = (struct ATTR_FILE_NAME *)(new_de + 1); + mi_get_ref(&dir_ni->mi, &fname->home); + 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; + } + + /* allocate PATH_MAX bytes */ + 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 out2; + + /*mark rw ntfs as dirty. it will be cleared at umount*/ + ntfs_set_state(sbi, NTFS_DIRTY_DIRTY); + + /* find name in record */ + mi_get_ref(&dir_ni->mi, &ref); + + le = NULL; + 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 out3; + + /* 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 out3; + + ni_remove_attr_le(ni, attr_from_name(fname), le); + + le16_add_cpu(&ni->mi.mrec->hard_links, -1); + } + } +out3: + 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); + +out2: + __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 i, 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_malloc(i_size); + 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_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->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_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)) { + /* unknown Microsoft Tag */ + 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(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; + + /* translate windows '\' into linux '/' */ + for (i = 0; i < err; i++) { + if (buffer[i] == '\\') + buffer[i] = '/'; + } + + /* 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; +} + +// clang-format off +const struct inode_operations ntfs_link_inode_operations = { + .get_link = ntfs_get_link, + .setattr = ntfs3_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, + .set_page_dirty = __set_page_dirty_buffers, +}; + +const struct address_space_operations ntfs_aops_cmpr = { + .readpage = ntfs_readpage, + .readahead = ntfs_readahead, +}; +// clang-format on diff --git a/fs/ntfs3/super.c b/fs/ntfs3/super.c new file mode 100644 index 000000000000..6be13e256c1a --- /dev/null +++ b/fs/ntfs3/super.c @@ -0,0 +1,1504 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * + * Copyright (C) 2019-2021 Paragon Software GmbH, All rights reserved. + * + * + * terminology + * + * cluster - allocation unit - 512,1K,2K,4K,...,2M + * 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 + * run - maps vcn to lcn - stored in attributes in packed form + * attr - attribute segment - std/name/data etc records inside MFT + * mi - mft inode - one MFT record(usually 1024 bytes or 4K), consists of attributes + * ni - ntfs inode - extends linux inode. consists of one or more mft inodes + * index - unit inside directory - 2K, 4K, <=page size, does not depend on cluster size + * + * WSL - Windows Subsystem for Linux + * https://docs.microsoft.com/en-us/windows/wsl/file-permissions + * It stores uid/gid/mode/dev in xattr + * + */ + +#include <linux/backing-dev.h> +#include <linux/blkdev.h> +#include <linux/buffer_head.h> +#include <linux/exportfs.h> +#include <linux/fs.h> +#include <linux/iversion.h> +#include <linux/module.h> +#include <linux/nls.h> +#include <linux/parser.h> +#include <linux/seq_file.h> +#include <linux/statfs.h> + +#include "debug.h" +#include "ntfs.h" +#include "ntfs_fs.h" +#ifdef CONFIG_NTFS3_LZX_XPRESS +#include "lib/lib.h" +#endif + +#ifdef CONFIG_PRINTK +/* + * Trace warnings/notices/errors + * Thanks Joe Perches <joe(a)perches.com> 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); +} + +static char s_name_buf[512]; +static atomic_t s_name_buf_cnt = ATOMIC_INIT(1); // 1 means 'free s_name_buf' + +/* 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; + char *name; + va_list args; + struct va_format vaf; + int level; + + if (!___ratelimit(&sbi->msg_ratelimit, "ntfs3")) + return; + + /* use static allocated buffer, if possible */ + name = atomic_dec_and_test(&s_name_buf_cnt) + ? s_name_buf + : kmalloc(sizeof(s_name_buf), GFP_NOFS); + + if (name) { + struct dentry *de = d_find_alias(inode); + const u32 name_len = ARRAY_SIZE(s_name_buf) - 1; + + if (de) { + spin_lock(&de->d_lock); + snprintf(name, name_len, " \"%s\"", de->d_name.name); + spin_unlock(&de->d_lock); + name[name_len] = 0; /* to be sure*/ + } else { + name[0] = 0; + } + dput(de); /* cocci warns if placed in branch "if (de)" */ + } + + va_start(args, fmt); + + level = printk_get_level(fmt); + vaf.fmt = printk_skip_level(fmt); + vaf.va = &args; + + printk("%c%cntfs3: %s: ino=%lx,%s %pV\n", KERN_SOH_ASCII, level, + sb->s_id, inode->i_ino, name ? name : "", &vaf); + + va_end(args); + + atomic_inc(&s_name_buf_cnt); + if (name != s_name_buf) + kfree(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 inline void clear_mount_options(struct ntfs_mount_options *options) +{ + unload_nls(options->nls); +} + +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_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_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 option; + char nls_name[30]; + struct nls_table *nls; + + opts->fs_uid = current_uid(); + opts->fs_gid = current_gid(); + opts->fs_fmask_inv = opts->fs_dmask_inv = ~current_umask(); + nls_name[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: +#ifdef CONFIG_NTFS3_FS_POSIX_ACL + sb->s_flags |= SB_POSIXACL; + break; +#else + ntfs_err(sb, "support for ACL not compiled in!"); + return -EINVAL; +#endif + case Opt_noatime: + sb->s_flags |= SB_NOATIME; + break; + case Opt_showmeta: + opts->showmeta = 1; + break; + case Opt_nls: + match_strlcpy(nls_name, &args[0], sizeof(nls_name)); + 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: + if (!strcmp(nls_name[0] ? nls_name : CONFIG_NLS_DEFAULT, "utf8")) { + /* For UTF-8 use utf16s_to_utf8s/utf8s_to_utf16s instead of nls */ + nls = NULL; + } else if (nls_name[0]) { + nls = load_nls(nls_name); + if (!nls) { + ntfs_err(sb, "failed to load \"%s\"", nls_name); + return -EINVAL; + } + } else { + nls = load_nls_default(); + if (!nls) { + ntfs_err(sb, "failed to load default nls"); + return -EINVAL; + } + } + opts->nls = nls; + + 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 = sb_rdonly(sb) && !(*flags & SB_RDONLY); + if (ro_rw && (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_vfree(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.lznt); +#ifdef CONFIG_NTFS3_LZX_XPRESS + xpress_free_decompressor(sbi->compress.xpress); + lzx_free_decompressor(sbi->compress.lzx); +#endif + 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] = sbi->volume.ser_num; + buf->f_fsid.val[1] = (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; + struct user_namespace *user_ns = seq_user_ns(m); + + if (opts->uid) + seq_printf(m, ",uid=%u", + from_kuid_munged(user_ns, opts->fs_uid)); + if (opts->gid) + seq_printf(m, ",gid=%u", + from_kgid_munged(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) + seq_printf(m, ",nls=%s", opts->nls->charset); + else + seq_puts(m, ",nls=utf8"); + 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 = ntfs3_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 CONFIG_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 = ntfs3_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 = 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; + } + + /* cluster size: 512, 1K, 2K, 4K, ... 2M */ + 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; +#ifndef CONFIG_NTFS3_64BIT_CLUSTER + /* 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; + } +#elif BITS_PER_LONG < 64 +#error "CONFIG_NTFS3_64BIT_CLUSTER incompatible in 32 bit OS" +#endif + + sbi->used.bitmap.nbits = clusters; + + rec = ntfs_zalloc(record_size); + 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 CONFIG_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_zalloc(sizeof(struct ntfs_sb_info)); + 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; + + 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; + +#ifdef CONFIG_NTFS3_64BIT_CLUSTER + sb->s_maxbytes = MAX_LFS_FILESIZE; +#else + sb->s_maxbytes = 0xFFFFFFFFull << sbi->cluster_bits; +#endif + + mutex_init(&sbi->compress.mtx_lznt); +#ifdef CONFIG_NTFS3_LZX_XPRESS + mutex_init(&sbi->compress.mtx_xpress); + mutex_init(&sbi->compress.mtx_lzx); +#endif + + /* + * 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) { + /* It is ok if no ATTR_LABEL */ + } 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 \x24LogFile."); + 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 CONFIG_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_malloc(bytes); + 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; + sbi->ea_max_size = 0x10000; /* default formater value */ + + while (done + sizeof(struct ATTR_DEF_ENTRY) <= bytes) { + u32 t32 = le32_to_cpu(t->type); + u64 sz = le64_to_cpu(t->max_sz); + + if ((t32 & 0xF) || le32_to_cpu(t[-1].type) >= t32) + break; + + if (t->type == ATTR_REPARSE) + sbi->reparse.max_size = sz; + else if (t->type == ATTR_EA) + sbi->ea_max_size = 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 \x24LogFile."); + inode = NULL; + goto out; + } + + ni = ntfs_i(inode); + + if (inode->i_size != 0x10000 * sizeof(short)) { + err = -EINVAL; + goto out; + } + + sbi->upcase = upcase = ntfs_vmalloc(0x10000 * sizeof(short)); + if (!upcase) { + err = -ENOMEM; + goto out; + } + + for (idx = 0; idx < (0x10000 * sizeof(short) >> PAGE_SHIFT); idx++) { + const __le16 *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_vfree(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); +} + +// clang-format off +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 | FS_ALLOW_IDMAP, +}; +// clang-format on + +static int __init init_ntfs_fs(void) +{ + int err; + + pr_notice("ntfs3: Index binary search\n"); + pr_notice("ntfs3: Hot fix free clusters\n"); + pr_notice("ntfs3: Max link count %u\n", NTFS_LINK_MAX); + +#ifdef CONFIG_NTFS3_FS_POSIX_ACL + pr_notice("ntfs3: Enabled Linux POSIX ACLs support\n"); +#endif +#ifdef CONFIG_NTFS3_64BIT_CLUSTER + pr_notice("ntfs3: Activated 64 bits per cluster\n"); +#else + pr_notice("ntfs3: Activated 32 bits per cluster\n"); +#endif +#ifdef CONFIG_NTFS3_LZX_XPRESS + pr_notice("ntfs3: Read-only lzx/xpress compression included\n"); +#endif + + err = ntfs3_init_bitmap(); + if (err) + return err; + + 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 out1; + } + + err = register_filesystem(&ntfs_fs_type); + if (err) + goto out; + + return 0; +out: + kmem_cache_destroy(ntfs_inode_cachep); +out1: + ntfs3_exit_bitmap(); + 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); + ntfs3_exit_bitmap(); +} + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("ntfs3 read/write filesystem"); +MODULE_INFO(behaviour, "Index binary search"); +MODULE_INFO(behaviour, "Hot fix free clusters"); +#ifdef CONFIG_NTFS3_FS_POSIX_ACL +MODULE_INFO(behaviour, "Enabled Linux POSIX ACLs support"); +#endif +#ifdef CONFIG_NTFS3_64BIT_CLUSTER +MODULE_INFO(cluster, "Activated 64 bits per cluster"); +#else +MODULE_INFO(cluster, "Activated 32 bits per cluster"); +#endif +#ifdef CONFIG_NTFS3_LZX_XPRESS +MODULE_INFO(compression, "Read-only lzx/xpress compression included"); +#endif + +MODULE_AUTHOR("Konstantin Komarov"); +MODULE_ALIAS_FS("ntfs3"); + +module_init(init_ntfs_fs); +module_exit(exit_ntfs_fs); -- 2.30.0

1 0

[PATCH OLK-5.10] crypto: sm4 - Do not change section of ck and sbox
by shenzijun 07 Dec '21

07 Dec '21

From: 沈子俊 <shenzijun(a)kylinos.cn> mainline inclusion from mainline-v5.16 commit 4a7e1e5fc294687a8941fa3eeb4a7e8539ca5e2f category: bugfix bugzilla: NA CVE: NA ----------------------------------------------------------------- When building with clang and GNU as, there is a warning about ignored changed section attributes: /tmp/sm4-c916c8.s: Assembler messages: /tmp/sm4-c916c8.s:677: Warning: ignoring changed section attributes for .data..cacheline_aligned "static const" places the data in .rodata but __cacheline_aligned has the section attribute to place it in .data..cacheline_aligned, in addition to the aligned attribute. To keep the alignment but avoid attempting to change sections, use the ____cacheline_aligned attribute, which is just the aligned attribute. Fixes: 2b31277af577 ("crypto: sm4 - create SM4 library based on sm4 generic code") Link: https://github.com/ClangBuiltLinux/linux/issues/1441 Signed-off-by: Nathan Chancellor <nathan(a)kernel.org> Reviewed-by: Tianjia Zhang <tianjia.zhang(a)linux.alibaba.com> Signed-off-by: Herbert Xu <herbert(a)gondor.apana.org.au> Signed-off-by: 沈子俊 <shenzijun(a)kylinos.cn> --- lib/crypto/sm4.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/lib/crypto/sm4.c b/lib/crypto/sm4.c index 633b59fed9db..284e62576d0c 100644 --- a/lib/crypto/sm4.c +++ b/lib/crypto/sm4.c @@ -15,7 +15,7 @@ static const u32 fk[4] = { 0xa3b1bac6, 0x56aa3350, 0x677d9197, 0xb27022dc }; -static const u32 __cacheline_aligned ck[32] = { +static const u32 ____cacheline_aligned ck[32] = { 0x00070e15, 0x1c232a31, 0x383f464d, 0x545b6269, 0x70777e85, 0x8c939aa1, 0xa8afb6bd, 0xc4cbd2d9, 0xe0e7eef5, 0xfc030a11, 0x181f262d, 0x343b4249, @@ -26,7 +26,7 @@ static const u32 __cacheline_aligned ck[32] = { 0x10171e25, 0x2c333a41, 0x484f565d, 0x646b7279 }; -static const u8 __cacheline_aligned sbox[256] = { +static const u8 ____cacheline_aligned sbox[256] = { 0xd6, 0x90, 0xe9, 0xfe, 0xcc, 0xe1, 0x3d, 0xb7, 0x16, 0xb6, 0x14, 0xc2, 0x28, 0xfb, 0x2c, 0x05, 0x2b, 0x67, 0x9a, 0x76, 0x2a, 0xbe, 0x04, 0xc3, -- 2.30.0

1 2

[PATCH openEuler-1.0-LTS 1/6] ext4: always panic when errors=panic is specified
by Yang Yingliang 07 Dec '21

07 Dec '21

From: Ye Bin <yebin10(a)huawei.com> mainline inclusion from mainline-v5.13-rc1 commit ac2f7ca51b0929461ea49918f27c11b680f28995 category: bugfix bugzilla: 182973 CVE: NA ------------------------------------------------- Before commit 014c9caa29d3 ("ext4: make ext4_abort() use __ext4_error()"), the following series of commands would trigger a panic: 1. mount /dev/sda -o ro,errors=panic test 2. mount /dev/sda -o remount,abort test After commit 014c9caa29d3, remounting a file system using the test mount option "abort" will no longer trigger a panic. This commit will restore the behaviour immediately before commit 014c9caa29d3. (However, note that the Linux kernel's behavior has not been consistent; some previous kernel versions, including 5.4 and 4.19 similarly did not panic after using the mount option "abort".) This also makes a change to long-standing behaviour; namely, the following series commands will now cause a panic, when previously it did not: 1. mount /dev/sda -o ro,errors=panic test 2. echo test > /sys/fs/ext4/sda/trigger_fs_error However, this makes ext4's behaviour much more consistent, so this is a good thing. Cc: stable(a)kernel.org Fixes: 014c9caa29d3 ("ext4: make ext4_abort() use __ext4_error()") Signed-off-by: Ye Bin <yebin10(a)huawei.com> Link: https://lore.kernel.org/r/20210401081903.3421208-1-yebin10@huawei.com Signed-off-by: Theodore Ts'o <tytso(a)mit.edu> Signed-off-by: Zheng Liang <zhengliang6(a)huawei.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- fs/ext4/super.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index a051671f7cb89..5a58f72ac2090 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -652,12 +652,6 @@ static void ext4_handle_error(struct super_block *sb, bool force_ro, int error, ext4_commit_super(sb); } - if (sb_rdonly(sb)) - return; - - if (continue_fs) - goto out; - /* * We force ERRORS_RO behavior when system is rebooting. Otherwise we * could panic during 'reboot -f' as the underlying device got already @@ -668,6 +662,12 @@ static void ext4_handle_error(struct super_block *sb, bool force_ro, int error, sb->s_id); } + if (sb_rdonly(sb)) + return; + + if (continue_fs) + goto out; + ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only"); /* * Make sure updated value of ->s_mount_flags will be visible before -- 2.25.1

1 5

[openEuler-5.10 00/21] Backport 5.10.81 LTS
by Zheng Zengkai 06 Dec '21

06 Dec '21

Backport 5.10.81 LTS patches from upstream. Borislav Petkov (1): selftests/x86/iopl: Adjust to the faked iopl CLI/STI usage Gao Xiang (1): erofs: fix unsafe pagevec reuse of hooked pclusters Greg Thelen (1): perf/core: Avoid put_page() when GUP fails Joakim Zhang (2): net: stmmac: add clocks management for gmac driver net: stmmac: fix system hang if change mac address after interface ifdown Kees Cook (1): fortify: Explicitly disable Clang support Marc Zyngier (2): PCI/MSI: Deal with devices lying about their MSI mask capability PCI: Add MSI masking quirk for Nvidia ION AHCI Masami Hiramatsu (1): bootconfig: init: Fix memblock leak in xbc_make_cmdline() Michael Riesch (1): net: stmmac: dwmac-rk: fix unbalanced pm_runtime_enable warnings Nathan Chancellor (1): scripts/lld-version.sh: Rewrite based on upstream ld-version.sh Peter Zijlstra (1): x86/iopl: Fake iopl(3) CLI/STI usage Subbaraman Narayanamurthy (1): thermal: Fix NULL pointer dereferences in of_thermal_ functions Sven Schnelle (1): parisc/entry: fix trace test in syscall exit path Thomas Gleixner (1): PCI/MSI: Destroy sysfs before freeing entries Wei Yongjun (1): net: stmmac: platform: fix build error with !CONFIG_PM_SLEEP Wong Vee Khee (1): net: stmmac: fix issue where clk is being unprepared twice Xie Yongji (2): block: Add a helper to validate the block size loop: Use blk_validate_block_size() to validate block size Yang Yingliang (1): net: stmmac: fix missing unlock on error in stmmac_suspend() Yue Hu (1): erofs: remove the occupied parameter from z_erofs_pagevec_enqueue() arch/parisc/kernel/entry.S | 2 +- arch/x86/include/asm/insn-eval.h | 1 + arch/x86/include/asm/processor.h | 1 + arch/x86/kernel/process.c | 1 + arch/x86/kernel/traps.c | 34 ++++++ arch/x86/lib/insn-eval.c | 2 +- drivers/block/loop.c | 19 +-- .../net/ethernet/stmicro/stmmac/dwmac-rk.c | 9 -- drivers/net/ethernet/stmicro/stmmac/stmmac.h | 1 + .../net/ethernet/stmicro/stmmac/stmmac_main.c | 87 ++++++++++++-- .../net/ethernet/stmicro/stmmac/stmmac_mdio.c | 111 ++++++++++++++---- .../ethernet/stmicro/stmmac/stmmac_platform.c | 30 ++++- drivers/pci/msi.c | 27 +++-- drivers/pci/quirks.c | 6 + drivers/thermal/thermal_of.c | 9 +- fs/erofs/zdata.c | 15 ++- fs/erofs/zpvec.h | 14 ++- include/linux/blkdev.h | 8 ++ include/linux/pci.h | 2 + init/main.c | 1 + kernel/events/core.c | 10 +- scripts/lld-version.sh | 35 ++++-- security/Kconfig | 3 + tools/testing/selftests/x86/iopl.c | 78 ++++++++---- 24 files changed, 375 insertions(+), 131 deletions(-) -- 2.20.1

1 21

[openEuler-5.10 000/557] Backport 5.10.80 LTS
by Zheng Zengkai 06 Dec '21

06 Dec '21

Backport 5.10.80 LTS patches from upstream. Ahmad Fatoum (1): watchdog: f71808e_wdt: fix inaccurate report in WDIOC_GETTIMEOUT Ajay Singh (1): wilc1000: fix possible memory leak in cfg_scan_result() Alagu Sankar (1): ath10k: high latency fixes for beacon buffer Aleksander Jan Bajkowski (3): MIPS: lantiq: dma: add small delay after reset MIPS: lantiq: dma: reset correct number of channel MIPS: lantiq: dma: fix burst length for DEU Alex Bee (1): arm64: dts: rockchip: Fix GPU register width for RK3328 Alex Deucher (1): drm/amdgpu/gmc6: fix DMA mask from 44 to 40 bits Alex Xu (Hello71) (1): drm/plane-helper: fix uninitialized variable reference Alexander Tsoy (1): ALSA: usb-audio: Add registration quirk for JBL Quantum 400 Alexandru Ardelean (1): iio: st_sensors: disable regulators after device unregistration Alexei Starovoitov (2): bpf: Fix propagation of bounds from 64-bit min/max into 32-bit and var_off. bpf: Fix propagation of signed bounds from 64-bit min/max into 32-bit. Alexey Gladkov (1): Fix user namespace leak Alok Prasad (1): RDMA/qedr: Fix NULL deref for query_qp on the GSI QP Amelie Delaunay (3): usb: dwc2: drd: fix dwc2_force_mode call in dwc2_ovr_init usb: dwc2: drd: fix dwc2_drd_role_sw_set when clock could be disabled usb: dwc2: drd: reset current session before setting the new one Amit Engel (1): nvmet-tcp: fix header digest verification Anand Jain (1): btrfs: call btrfs_check_rw_degradable only if there is a missing device Anand Moon (2): arm64: dts: meson-g12a: Fix the pwm regulator supply properties arm64: dts: meson-g12b: Fix the pwm regulator supply properties Anant Thazhemadam (1): media: usb: dvd-usb: fix uninit-value bug in dibusb_read_eeprom_byte() Anders Roxell (1): PM: hibernate: fix sparse warnings Andrea Righi (1): selftests/bpf: Fix fclose/pclose mismatch in test_progs Andreas Gruenbacher (3): iov_iter: Fix iov_iter_get_pages{,_alloc} page fault return value gfs2: Cancel remote delete work asynchronously gfs2: Fix glock_hash_walk bugs Andreas Kemnade (1): arm: dts: omap3-gta04a4: accelerometer irq fix Andrej Shadura (2): HID: u2fzero: clarify error check and length calculations HID: u2fzero: properly handle timeouts in usb_submit_urb Andrey Grodzovsky (1): drm/amdgpu: Fix MMIO access page fault Andrii Nakryiko (6): selftests/bpf: Fix strobemeta selftest regression libbpf: Fix BTF data layout checks and allow empty BTF libbpf: Allow loading empty BTFs libbpf: Fix overflow in BTF sanity checks libbpf: Fix BTF header parsing checks selftests/bpf: Fix also no-alu32 strobemeta selftest André Almeida (1): ACPI: battery: Accept charges over the design capacity as full Andy Shevchenko (2): iio: st_sensors: Call st_sensors_power_enable() from bus drivers serial: 8250_dw: Drop wrong use of ACPI_PTR() Anel Orazgaliyeva (1): cpuidle: Fix kobject memory leaks in error paths Anson Jacob (1): drm/amd/display: dcn20_resource_construct reduce scope of FPU enabled Anssi Hannula (1): serial: xilinx_uartps: Fix race condition causing stuck TX Antoine Tenart (1): net-sysfs: try not to restart the syscall if it will fail eventually Arnaud Pouliquen (1): rpmsg: Fix rpmsg_create_ept return when RPMSG config is not defined Arnd Bergmann (9): hyperv/vmbus: include linux/bitops.h ifb: fix building without CONFIG_NET_CLS_ACT ARM: 9136/1: ARMv7-M uses BE-8, not BE-32 drm/amdgpu: fix warning for overflow check crypto: ecc - fix CRYPTO_DEFAULT_RNG dependency memstick: avoid out-of-range warning arm64: pgtable: make __pte_to_phys/__phys_to_pte_val inline functions ARM: 9156/1: drop cc-option fallbacks for architecture selection ath10k: fix invalid dma_addr_t token assignment Arun Easi (1): scsi: qla2xxx: Fix kernel crash when accessing port_speed sysfs file Asmaa Mnebhi (1): gpio: mlxbf2.c: Add check for bgpio_init failure Austin Kim (2): ALSA: synth: missing check for possible NULL after the call to kstrdup evm: mark evm_fixmode as __ro_after_init Baochen Qiang (2): ath11k: Change DMA_FROM_DEVICE to DMA_TO_DEVICE when map reinjected packets ath11k: Fix memory leak in ath11k_qmi_driver_event_work Baptiste Lepers (1): pnfs/flexfiles: Fix misplaced barrier in nfs4_ff_layout_prepare_ds Barnabás Pőcze (1): platform/x86: wmi: do not fail if disabling fails Bastien Roucariès (1): ARM: dts: sun7i: A20-olinuxino-lime2: Fix ethernet phy-mode Benjamin Li (2): wcn36xx: handle connection loss indication wcn36xx: add proper DMA memory barriers in rx path Bixuan Cui (1): powerpc/44x/fsp2: add missing of_node_put Bjorn Andersson (1): soc: qcom: rpmhpd: Make power_on actually enable the domain Borislav Petkov (1): x86/sev: Make the #VC exception stacks part of the default stacks storage Brett Creeley (1): ice: Fix not stopping Tx queues for VFs Bryan O'Donoghue (1): wcn36xx: Fix Antenna Diversity Switching Bryant Mairs (1): drm: panel-orientation-quirks: Add quirk for Aya Neo 2021 Can Guo (1): scsi: ufs: Refactor ufshcd_setup_clocks() to remove skip_ref_clk Charan Teja Reddy (1): dma-buf: WARN on dmabuf release with pending attachments Chen-Yu Tsai (2): media: rkvdec: Do not override sizeimage for output format media: rkvdec: Support dynamic resolution changes Chengfeng Ye (1): nfc: pn533: Fix double free when pn533_fill_fragment_skbs() fails Chenyuan Mi (1): drm/nouveau/svm: Fix refcount leak bug and missing check against null bug Christian Löhle (1): mmc: dw_mmc: Dont wait for DRTO on Write RSP error Christoph Hellwig (1): rds: stop using dmapool Christophe JAILLET (6): media: mtk-vpu: Fix a resource leak in the error handling path of 'mtk_vpu_probe()' mmc: mxs-mmc: disable regulator on error and in the remove function clk: mvebu: ap-cpu-clk: Fix a memory leak in error handling paths soc/tegra: Fix an error handling path in tegra_powergate_power_up() remoteproc: Fix a memory leak in an error handling path in 'rproc_handle_vdev()' i2c: xlr: Fix a resource leak in the error handling path of 'xlr_i2c_probe()' Christophe Leroy (1): video: fbdev: chipsfb: use memset_io() instead of memset() Claudio Imbrenda (2): KVM: s390: pv: avoid double free of sida page KVM: s390: pv: avoid stalls for kvm_s390_pv_init_vm Claudiu Beznea (2): clk: at91: sam9x60-pll: use DIV_ROUND_CLOSEST_ULL dmaengine: at_xdmac: fix AT_XDMAC_CC_PERID() macro Clément Léger (1): clk: at91: check pmc node status before registering syscore ops Colin Ian King (4): media: cxd2880-spi: Fix a null pointer dereference on error handling path media: cx23885: Fix snd_card_free call on null card pointer media: em28xx: Don't use ops->suspend if it is NULL mmc: moxart: Fix null pointer dereference on pointer host Corey Minyard (1): ipmi: Disable some operations during a panic Cyril Strejc (1): net: multicast: calculate csum of looped-back and forwarded packets Damien Le Moal (1): libata: fix read log timeout value Dan Carpenter (13): tpm: Check for integer overflow in tpm2_map_response_body() ath11k: fix some sleeping in atomic bugs b43legacy: fix a lower bounds test b43: fix a lower bounds test memstick: jmb38x_ms: use appropriate free function in jmb38x_ms_alloc_host() drm/msm: potential error pointer dereference in init() drm/msm: uninitialized variable in msm_gem_import() usb: gadget: hid: fix error code in do_config() scsi: csiostor: Uninitialized data in csio_ln_vnp_read_cbfn() phy: ti: gmii-sel: check of_get_address() for failure rtc: rv3032: fix error handling in rv3032_clkout_set_rate() zram: off by one in read_block_state() gve: Fix off by one in gve_tx_timeout() Dan Schatzberg (1): cgroup: Fix rootcg cpu.stat guest double counting Daniel Borkmann (2): net, neigh: Fix NTF_EXT_LEARNED in combination with NTF_USE net, neigh: Enable state migration between NUD_PERMANENT and NTF_USE Daniel Jordan (1): crypto: pcrypt - Delay write to padata->info Dave Jones (1): x86/mce: Add errata workaround for Skylake SKX37 David Hildenbrand (1): s390/gmap: don't unconditionally call pte_unmap_unlock() in __gmap_zap() Davide Baldo (1): ALSA: hda/realtek: Fixes HP Spectre x360 15-eb1xxx speakers Derong Liu (1): mmc: mtk-sd: Add wait dma stop done flow Desmond Cheong Zhi Xi (1): Bluetooth: fix init and cleanup of sco_conn.timeout_work Dinghao Liu (1): Bluetooth: btmtkuart: fix a memleak in mtk_hci_wmt_sync Dirk Bender (1): media: mt9p031: Fix corrupted frame after restarting stream Dmitriy Ulitin (1): media: stm32: Potential NULL pointer dereference in dcmi_irq_thread() Dmitry Bogdanov (1): scsi: qla2xxx: Fix unmap of already freed sgl Dmitry Osipenko (1): soc/tegra: pmc: Fix imbalanced clock disabling in error code path Dominique Martinet (1): 9p/net: fix missing error check in p9_check_errors Dongli Zhang (2): xen/netfront: stop tx queues during live migration vmxnet3: do not stop tx queues after netif_device_detach() Dongliang Mu (2): JFS: fix memleak in jfs_mount memory: fsl_ifc: fix leak of irq and nand_irq in fsl_ifc_ctrl_probe Dust Li (1): net/smc: fix sk_refcnt underflow on linkdown and fallback Eiichi Tsukata (1): vsock: prevent unnecessary refcnt inc for nonblocking connect Eric Badger (1): EDAC/sb_edac: Fix top-of-high-memory value for Broadwell/Haswell Eric Biggers (1): fscrypt: allow 256-bit master keys with AES-256-XTS Eric Dumazet (4): net: annotate data-race in neigh_output() tcp: switch orphan_count to bare per-cpu counters llc: fix out-of-bound array index in llc_sk_dev_hash() net/sched: sch_taprio: fix undefined behavior in ktime_mono_to_any Eric W. Biederman (3): signal: Remove the bogus sigkill_pending in ptrace_stop signal/mips: Update (_save|_restore)_fp_context to fail with -EFAULT signal/sh: Use force_sig(SIGKILL) instead of do_group_exit(SIGKILL) Erik Ekman (2): sfc: Export fibre-specific supported link modes sfc: Don't use netif_info before net_device setup Evgeny Novikov (3): media: atomisp: Fix error handling in probe media: dvb-frontends: mn88443x: Handle errors of clk_prepare_enable() mtd: spi-nor: hisi-sfc: Remove excessive clk_disable_unprepare() Fabio Estevam (1): ath10k: sdio: Add missing BH locking around napi_schdule() Filipe Manana (1): btrfs: fix lost error handling when replaying directory deletes Florian Westphal (3): fcnal-test: kill hanging ping/nettest binaries on cleanup vrf: run conntrack only in context of lower/physdev for locally generated packets netfilter: nfnetlink_queue: fix OOB when mac header was cleared Frank Rowand (1): of: unittest: fix EXPECT text for gpio hog errors Gao Xiang (1): erofs: don't trigger WARN() when decompression fails Geert Uytterhoeven (6): arm64: dts: renesas: beacon: Fix Ethernet PHY mode pinctrl: renesas: checker: Fix off-by-one bug in drive register check mips: cm: Convert to bitfield API to fix out-of-bounds access auxdisplay: img-ascii-lcd: Fix lock-up when displaying empty string auxdisplay: ht16k33: Connect backlight to fbdev auxdisplay: ht16k33: Fix frame buffer device blanking Giovanni Cabiddu (2): crypto: qat - detect PFVF collision after ACK crypto: qat - disregard spurious PFVF interrupts Guo Ren (1): irqchip/sifive-plic: Fixup EOI failed when masked Guru Das Srinagesh (1): firmware: qcom_scm: Fix error retval in __qcom_scm_is_call_available() Halil Pasic (1): s390/cio: make ccw_device_dma_* more robust Hannes Reinecke (1): nvme: drop scan_lock and always kick requeue list when removing namespaces Hans de Goede (6): drm: panel-orientation-quirks: Update the Lenovo Ideapad D330 quirk (v2) drm: panel-orientation-quirks: Add quirk for KD Kurio Smart C15200 2-in-1 drm: panel-orientation-quirks: Add quirk for the Samsung Galaxy Book 10.6 brcmfmac: Add DMI nvram filename quirk for Cyberbook T116 tablet power: supply: bq27xxx: Fix kernel crash on IRQ handler register error ACPI: PMIC: Fix intel_pmic_regs_handler() read accesses Hao Wu (1): tpm: fix Atmel TPM crash caused by too frequent queries Harald Freudenberger (1): s390/ap: Fix hanging ioctl caused by orphaned replies Helge Deller (4): parisc: Fix set_fixmap() on PA1.x CPUs parisc: Fix ptrace check on syscall return task_stack: Fix end_of_stack() for architectures with upwards-growing stack parisc: Fix backtrace to always include init funtion names Henrik Grimler (1): power: supply: max17042_battery: use VFSOC for capacity when no rsns Iago Toral Quiroga (1): drm/v3d: fix wait for TMU write combiner flush Ian Rogers (1): perf bpf: Add missing free to bpf_event__print_bpf_prog_info() Igor Pylypiv (1): scsi: pm80xx: Fix misleading log statement in pm8001_mpi_get_nvmd_resp() Ilya Leoshkevich (1): libbpf: Fix endianness detection in BPF_CORE_READ_BITFIELD_PROBED() Imre Deak (2): ALSA: hda: Release controller display power during shutdown/reboot ALSA: hda: Fix hang during shutdown due to link reset Ingmar Klein (1): PCI: Mark Atheros QCA6174 to avoid bus reset Israel Rukshin (3): nvmet: fix use-after-free when a port is removed nvmet-rdma: fix use-after-free when a port is removed nvmet-tcp: fix use-after-free when a port is removed J. Bruce Fields (1): nfsd: don't alloc under spinlock in rpc_parse_scope_id Jack Andersen (1): mfd: dln2: Add cell for initializing DLN2 ADC Jackie Liu (3): ARM: s3c: irq-s3c24xx: Fix return value check for s3c24xx_init_intc() MIPS: loongson64: make CPU_LOONGSON64 depends on MIPS_FP_SUPPORT ar7: fix kernel builds for compiler test Jaegeuk Kim (1): f2fs: should use GFP_NOFS for directory inodes Jakob Hauser (1): power: supply: rt5033_battery: Change voltage values to µV Jakub Kicinski (4): net: sched: update default qdisc visibility after Tx queue cnt changes net: stream: don't purge sk_error_queue in sk_stream_kill_queues() udp6: allow SO_MARK ctrl msg to affect routing ethtool: fix ethtool msg len calculation for pause stats Jan Kara (1): ocfs2: fix data corruption on truncate Jane Malalane (1): x86/cpu: Fix migration safety with X86_BUG_NULL_SEL Janghyub Seo (1): r8169: Add device 10ec:8162 to driver r8169 Janis Schoetterl-Glausch (1): KVM: s390: Fix handle_sske page fault handling Jaroslav Kysela (1): ALSA: hda/realtek: Add a quirk for Acer Spin SP513-54N Jason Ormes (1): ALSA: usb-audio: Line6 HX-Stomp XL USB_ID for 48k-fixed quirk Jens Axboe (2): block: bump max plugged deferred size from 16 to 32 block: remove inaccurate requeue check Jeremy Soller (1): ALSA: hda/realtek: Headset fixup for Clevo NH77HJQ Jernej Skrabec (1): drm/sun4i: Fix macros in sun8i_csc.h Jessica Zhang (1): drm/msm: Fix potential NULL dereference in DPU SSPP Jia-Ju Bai (1): fs: orangefs: fix error return code of orangefs_revalidate_lookup() Jiasheng Jiang (1): rxrpc: Fix _usecs_to_jiffies() by using usecs_to_jiffies() Jim Mattson (1): KVM: selftests: Fix nested SVM tests when built with clang Jiri Olsa (1): selftests/bpf: Fix perf_buffer test on system with offline cpus Joerg Roedel (1): x86/sev: Fix stack type check in vc_switch_off_ist() Johan Hovold (14): Input: iforce - fix control-message timeout ALSA: ua101: fix division by zero at probe ALSA: 6fire: fix control and bulk message timeouts ALSA: line6: fix control and interrupt message timeouts mwifiex: fix division by zero in fw download path ath6kl: fix division by zero in send path ath6kl: fix control-message timeout ath10k: fix control-message timeout ath10k: fix division by zero in send path rtl8187: fix control-message timeouts serial: 8250: fix racy uartclk update most: fix control-message timeouts USB: iowarrior: fix control-message timeouts USB: chipidea: fix interrupt deadlock Johannes Berg (1): iwlwifi: mvm: disable RX-diversity in powersave John Fastabend (2): bpf, sockmap: Remove unhash handler for BPF sockmap usage bpf: sockmap, strparser, and tls are reusing qdisc_skb_cb and colliding John Fraker (1): gve: Recover from queue stall due to missed IRQ Johnathon Clark (1): ALSA: hda/realtek: Fix mic mute LED for the HP Spectre x360 14 Jon Maxwell (1): tcp: don't free a FIN sk_buff in tcp_remove_empty_skb() Jonas Dreßler (5): mwifiex: Read a PCI register after writing the TX ring write pointer mwifiex: Try waking the firmware until we get an interrupt mwifiex: Run SET_BSS_MODE when changing from P2P to STATION vif-type mwifiex: Properly initialize private structure on interface type changes mwifiex: Send DELBA requests according to spec Josef Bacik (1): btrfs: do not take the uuid_mutex in btrfs_rm_device Josh Don (1): fs/proc/uptime.c: Fix idle time reporting in /proc/uptime Josh Poimboeuf (1): objtool: Add xen_start_kernel() to noreturn list Juergen Gross (1): xen/balloon: add late_initcall_sync() for initial ballooning done Junji Wei (1): RDMA/rxe: Fix wrong port_cap_flags Kai-Heng Feng (1): ALSA: hda/realtek: Add quirk for HP EliteBook 840 G7 mute LED Kalesh Singh (1): tracing/cfi: Fix cmp_entries_* functions signature mismatch Kan Liang (2): perf/x86/intel/uncore: Support extra IMC channel on Ice Lake server perf/x86/intel/uncore: Fix Intel ICX IIO event constraints Kees Cook (5): leaking_addresses: Always print a trailing newline media: radio-wl1273: Avoid card name truncation media: si470x: Avoid card name truncation media: tm6000: Avoid card name truncation clocksource/drivers/timer-ti-dm: Select TIMER_OF Kewei Xu (1): i2c: mediatek: fixing the incorrect register offset Kishon Vijay Abraham I (2): arm64: dts: ti: k3-j721e-main: Fix "max-virtual-functions" in PCIe EP nodes arm64: dts: ti: k3-j721e-main: Fix "bus-range" upto 256 bus number for PCIe Krzysztof Kozlowski (3): regulator: s5m8767: do not use reset value as DVS voltage if GPIO DVS is disabled regulator: dt-bindings: samsung,s5m8767: correct s5m8767,pmic-buck-default-dvs-idx property mfd: core: Add missing of_node_put for loop iteration Kumar Kartikeya Dwivedi (1): selftests/bpf: Fix fd cleanup in sk_lookup test Kunihiko Hayashi (1): PCI: uniphier: Serialize INTx masking/unmasking and fix the bit operation Lad Prabhakar (1): spi: spi-rpc-if: Check return value of rpcif_sw_init() Lars-Peter Clausen (1): dmaengine: dmaengine_desc_callback_valid(): Check for `callback_result` Lasse Collin (2): lib/xz: Avoid overlapping memcpy() with invalid input with in-place decompression lib/xz: Validate the value before assigning it to an enum variable Lee Jones (1): soc: qcom: rpmhpd: Provide some missing struct member descriptions Leon Romanovsky (1): RDMA/mlx4: Return missed an error if device doesn't support steering Li Chen (1): PCI: cadence: Add cdns_plat_pcie_probe() missing return Li Zhang (1): btrfs: clear MISSING device status bit in btrfs_close_one_device Linus Lüssing (1): ath9k: Fix potential interrupt storm on queue reset Linus Walleij (1): net: dsa: rtl8366rb: Fix off-by-one bug Loic Poulain (6): wcn36xx: Fix HT40 capability for 2Ghz band wcn36xx: Fix tx_status mechanism wcn36xx: Fix (QoS) null data frame bitrate/modulation wcn36xx: Correct band/freq reporting on RX ath10k: Fix missing frame timestamp for beacon/probe-resp wcn36xx: Fix discarded frames due to wrong sequence number Lorenz Bauer (3): bpf: Define bpf_jit_alloc_exec_limit for arm64 JIT bpf: Prevent increasing bpf_jit_limit above max selftests: bpf: Convert sk_lookup ctx access tests to PROG_TEST_RUN Lorenzo Bianconi (3): mt76: mt7615: fix endianness warning in mt7615_mac_write_txwi mt76: mt76x02: fix endianness warnings in mt76x02_mac.c mt76: mt7915: fix possible infinite loop release semaphore Lucas Tanure (1): ASoC: cs42l42: Disable regulators if probe fails Lukas Wunner (1): ifb: Depend on netfilter alternatively to tc Maciej W. Rozycki (1): MIPS: Fix assembly error from MIPSr2 code used within MIPS_ISA_ARCH_LEVEL Marc Kleine-Budde (1): can: mcp251xfd: mcp251xfd_chip_start(): fix error handling for mcp251xfd_chip_rx_int_enable() Marek Behún (4): PCI: pci-bridge-emul: Fix emulation of W1C bits PCI: aardvark: Fix return value of MSI domain .alloc() method PCI: aardvark: Read all 16-bits from PCIE_MSI_PAYLOAD_REG PCI: aardvark: Don't spam about PIO Response Status Marek Vasut (3): rsi: Fix module dev_oper_mode parameter description ARM: dts: stm32: Reduce DHCOR SPI NOR frequency to 50 MHz video: backlight: Drop maximum brightness override for brightness zero Marijn Suijten (1): ARM: dts: qcom: msm8974: Add xo_board reference clock to DSI0 PHY Mario (1): drm: panel-orientation-quirks: Add quirk for GPD Win3 Mark Brown (1): tpm_tis_spi: Add missing SPI ID Mark Rutland (2): KVM: arm64: Extract ESR_ELx.EC only irq: mips: avoid nested irq_enter() Markus Schneider-Pargmann (1): hwrng: mtk - Force runtime pm ops for sleep ops Martin Fuzzey (3): rsi: fix occasional initialisation failure with BT coex rsi: fix key enabled check causing unwanted encryption for vap_id > 0 rsi: fix rate mask set leading to P2P failure Martin Kepplinger (1): media: imx: set a media_device bus_info string Masami Hiramatsu (2): ia64: kprobes: Fix to pass correct trampoline address to the handler ARM: clang: Do not rely on lr register for stacktrace Mathias Nyman (1): xhci: Fix USB 3.1 enumeration issues by increasing roothub power-on-good delay Matthew Auld (1): drm/ttm: stop calling tt_swapin in vm_access Matthias Schiffer (1): net: phy: micrel: make *-skew-ps check more lenient Maurizio Lombardi (1): nvmet-tcp: fix a memory leak when releasing a queue Max Gurtovoy (1): nvme-rdma: fix error code in nvme_rdma_setup_ctrl Maxim Kiselev (1): net: davinci_emac: Fix interrupt pacing disable Meng Li (2): soc: fsl: dpio: replace smp_processor_id with raw_smp_processor_id soc: fsl: dpio: use the combined functions to protect critical zone Menglong Dong (1): workqueue: make sysfs of unbound kworker cpumask more clever Miaohe Lin (1): mm/zsmalloc.c: close race window between zs_pool_dec_isolated() and zs_unregister_migration() Michael Ellerman (1): powerpc: Fix is_kvm_guest() / kvm_para_available() Michael Pratt (1): posix-cpu-timers: Clear task::posix_cputimers_work in copy_process() Michael Tretter (1): media: allegro: ignore interrupt if mailbox is not initialized Michael Walle (1): crypto: caam - disable pkc for non-E SoCs Michal Hocko (1): mm, oom: do not trigger out_of_memory from the #PF Michał Mirosław (1): ARM: 9155/1: fix early early_iounmap() Miklos Szeredi (1): fuse: fix page stealing Miquel Raynal (9): mtd: rawnand: socrates: Keep the driver compatible with on-die ECC engines mtd: rawnand: ams-delta: Keep the driver compatible with on-die ECC engines mtd: rawnand: xway: Keep the driver compatible with on-die ECC engines mtd: rawnand: mpc5121: Keep the driver compatible with on-die ECC engines mtd: rawnand: gpio: Keep the driver compatible with on-die ECC engines mtd: rawnand: pasemi: Keep the driver compatible with on-die ECC engines mtd: rawnand: orion: Keep the driver compatible with on-die ECC engines mtd: rawnand: plat_nand: Keep the driver compatible with on-die ECC engines mtd: rawnand: au1550nd: Keep the driver compatible with on-die ECC engines Muchun Song (1): seq_file: fix passing wrong private data Nadezda Lutovinova (2): media: s5p-mfc: Add checking to s5p_mfc_probe(). media: rcar-csi2: Add checking to rcsi2_start_receiver() Naohiro Aota (1): block: schedule queue restart after BLK_STS_ZONE_RESOURCE Nathan Chancellor (1): platform/x86: thinkpad_acpi: Fix bitwise vs. logical warning Nathan Lynch (1): powerpc: fix unbalanced node refcount in check_kvm_guest() Naveen N. Rao (4): powerpc/lib: Add helper to check if offset is within conditional branch range powerpc/bpf: Validate branch ranges powerpc/security: Add a helper to query stf_barrier type powerpc/bpf: Emit stf barrier instruction sequences for BPF_NOSPEC Neeraj Upadhyay (1): rcu: Fix existing exp request check in sync_sched_exp_online_cleanup() Nehal Bakulchandra Shah (1): usb: xhci: Enable runtime-pm by default on AMD Yellow Carp platform Nikita Yushchenko (1): staging: most: dim2: do not double-register the same device Nuno Sá (2): iio: ad5770r: make devicetree property reading consistent iio: adis: do not disabe IRQs in 'adis_init()' Olivier Moysan (2): ARM: dts: stm32: fix SAI sub nodes register range ARM: dts: stm32: fix AV96 board SAI2 pin muxing on stm32mp15 Ondrej Mosnacek (1): selinux: fix race condition when computing ocontext SIDs Pablo Neira Ayuso (2): netfilter: conntrack: set on IPS_ASSURED if flows enters internal stream state netfilter: nft_dynset: relax superfluous check on set updates Pali Rohár (13): serial: core: Fix initializing and restoring termios speed PCI: aardvark: Do not clear status bits of masked interrupts PCI: aardvark: Fix checking for link up via LTSSM state PCI: aardvark: Do not unmask unused interrupts PCI: aardvark: Fix reporting Data Link Layer Link Active PCI: aardvark: Fix configuring Reference clock PCI: aardvark: Fix support for bus mastering and PCI_COMMAND on emulated bridge PCI: aardvark: Fix support for PCI_BRIDGE_CTL_BUS_RESET on emulated bridge PCI: aardvark: Set PCI Bridge Class Code to PCI Bridge PCI: aardvark: Fix support for PCI_ROM_ADDRESS1 on emulated bridge PCI: aardvark: Fix preserving PCI_EXP_RTCTL_CRSSVE flag on emulated bridge PCI: Add PCI_EXP_DEVCTL_PAYLOAD_* macros PCI: aardvark: Fix PCIe Max Payload Size setting Paul E. McKenney (1): rcu-tasks: Move RTGS_WAIT_CBS to beginning of rcu_tasks_kthread() loop Pavel Skripkin (3): ALSA: mixer: fix deadlock in snd_mixer_oss_set_volume media: em28xx: add missing em28xx_close_extension media: dvb-usb: fix ununit-value in az6027_rc_query Pawan Gupta (1): smackfs: Fix use-after-free in netlbl_catmap_walk() Paweł Anikiel (1): reset: socfpga: add empty driver allowing consumers to probe Pekka Korpinen (1): iio: dac: ad5446: Fix ad5622_write() return value Peter Rosin (1): ARM: dts: at91: tse850: the emac<->phy interface is rmii Peter Zijlstra (5): locking/lockdep: Avoid RCU-induced noinstr fail x86: Increase exception stack sizes x86/xen: Mark cpu_bringup_and_idle() as dead_end_function objtool: Fix static_call list generation rcu: Always inline rcu_dynticks_task*_{enter,exit}() Phoenix Huang (1): Input: elantench - fix misreporting trackpoint coordinates Pradeep Kumar Chitrapu (1): ath11k: fix packet drops due to incorrect 6 GHz freq value in rx status Punit Agrawal (1): kprobes: Do not use local variable when creating debugfs file Quentin Monnet (1): bpftool: Avoid leaking the JSON writer prepared for program metadata Quinn Tran (4): scsi: qla2xxx: Fix use after free in eh_abort path scsi: qla2xxx: Relogin during fabric disturbance scsi: qla2xxx: Fix gnl list corruption scsi: qla2xxx: Turn off target reset during issue_lip Rafael J. Wysocki (2): PM: sleep: Do not let "syscore" devices runtime-suspend during system transitions ACPICA: Avoid evaluating methods too early during system resume Rafał Miłecki (1): ARM: dts: BCM5301X: Fix memory nodes names Rahul Lakkireddy (1): cxgb4: fix eeprom len when diagnostics not implemented Rahul Tanwar (1): pinctrl: equilibrium: Fix function addition in multiple groups Rajat Asthana (1): media: mceusb: return without resubmitting URB in case of -EPROTO error. Randy Dunlap (5): mmc: winbond: don't build on M68K ia64: don't do IA64_CMPXCHG_DEBUG without CONFIG_PRINTK usb: musb: select GENERIC_PHY instead of depending on it usb: typec: STUSB160X should select REGMAP_I2C m68k: set a default value for MEMORY_RESERVE Ranjani Sridharan (1): ASoC: SOF: topology: do not power down primary core during topology removal Reimar Döffinger (1): libata: fix checking of DMA state Ricardo Koller (1): KVM: selftests: Add operand to vmsave/vmload/vmrun in svm.c Ricardo Ribalda (7): media: v4l2-ioctl: Fix check_ext_ctrls media: uvcvideo: Set capability in s_param media: uvcvideo: Return -EIO for control errors media: uvcvideo: Set unique vdev name based in type media: ipu3-imgu: imgu_fmt: Handle properly try media: ipu3-imgu: VIDIOC_QUERYCAP: Fix bus_info media: v4l2-ioctl: S_CTRL output the right value Richard Fitzgerald (4): ASoC: cs42l42: Correct some register default values ASoC: cs42l42: Defer probe if request_threaded_irq() returns EPROBE_DEFER ASoC: cs42l42: Use device_property API instead of of_property ASoC: cs42l42: Correct configuring of switch inversion from ts-inv Robert-Ionut Alexa (1): soc: fsl: dpaa2-console: free buffer before returning from dpaa2_console_read Russell King (Oracle) (1): net: phylink: avoid mvneta warning when setting pause parameters Ryder Lee (1): mt76: mt7915: fix an off-by-one bound check Sandeep Maheswaram (1): phy: qcom-snps: Correct the FSEL_MASK Saurav Kashyap (1): scsi: qla2xxx: Changes to support FCP2 Target Scott Wood (1): rcutorture: Avoid problematic critical section nesting on PREEMPT_RT Sean Christopherson (3): x86/irq: Ensure PI wakeup handler is unregistered before module unload KVM: VMX: Unregister posted interrupt wakeup handler on hardware unsetup KVM: nVMX: Query current VMCS when determining if MSR bitmaps are in use Sean Young (3): media: ite-cir: IR receiver stop working after receive overflow media: ir-kbd-i2c: improve responsiveness of hauppauge zilog receivers media: ir_toy: assignment to be16 should be of correct type Sebastian Andrzej Siewior (1): lockdep: Let lock_is_held_type() detect recursive read as read Sebastian Krzyszkowiak (2): power: supply: max17042_battery: Prevent int underflow in set_soc_threshold power: supply: max17042_battery: Clear status bits in interrupt handler Seevalamuthu Mariappan (1): ath11k: Align bss_chan_info structure with firmware Selvin Xavier (1): RDMA/bnxt_re: Fix query SRQ failure Shaoying Xu (1): ext4: fix lazy initialization next schedule time computation in more granular unit Shayne Chen (2): mt76: mt7915: fix sta_rec_wtbl tag len mt76: mt7915: fix muar_idx in mt7915_mcu_alloc_sta_req() Shuah Khan (2): selftests: kvm: fix mismatched fclose() after popen() selftests/core: fix conflicting types compile error for close_range() Shyam Sundar S K (1): net: amd-xgbe: Toggle PLL settings during rate change Sidong Yang (1): btrfs: reflink: initialize return value to 0 in btrfs_extent_same() Simon Ser (1): drm/panel-orientation-quirks: add Valve Steam Deck Srikar Dronamraju (3): powerpc: Refactor is_kvm_guest() declaration to new header powerpc: Rename is_kvm_guest() to check_kvm_guest() powerpc: Reintroduce is_kvm_guest() as a fast-path check Srinivas Kandagatla (2): soundwire: debugfs: use controller id and link_id for debugfs scsi: ufs: ufshcd-pltfrm: Fix memory leak due to probe defer Sriram R (2): ath11k: Avoid reg rules update during firmware recovery ath11k: Avoid race during regd updates Stafford Horne (1): openrisc: fix SMP tlb flush NULL pointer dereference Stefan Agner (2): phy: micrel: ksz8041nl: do not use power down mode serial: imx: fix detach/attach of serial console Stefan Schaeckeler (1): ACPI: AC: Quirk GK45 to skip reading _PSR Stephan Gerhold (2): arm64: dts: qcom: msm8916: Fix Secondary MI2S bit clock arm64: dts: qcom: pm8916: Remove wrong reg-names for rtc@6000 Stephen Suryaputra (1): gre/sit: Don't generate link-local addr if addr_gen_mode is IN6_ADDR_GEN_MODE_NONE Steven Rostedt (VMware) (2): ring-buffer: Protect ring_buffer_reset() from reentrancy tracefs: Have tracefs directories not set OTH permission bits by default Sudarshan Rajagopalan (1): arm64: mm: update max_pfn after memory hotplug Sukadev Bhattiprolu (2): ibmvnic: don't stop queue in xmit ibmvnic: Process crqs after enabling interrupts Sungjong Seo (1): exfat: fix incorrect loading of i_blocks for large files Sven Eckelmann (1): ath10k: fix max antenna gain unit Sven Schnelle (4): parisc: fix warning in flush_tlb_all parisc/unwind: fix unwinder when CONFIG_64BIT is enabled parisc/kgdb: add kgdb_roundup() to make kgdb work with idle polling s390/tape: fix timer initialization in tape_std_assign() Sylwester Dziedziuch (1): ice: Fix replacing VF hardware MAC to existing MAC filter Tadeusz Struk (1): scsi: core: Remove command size deduction from scsi_setup_scsi_cmnd() Takashi Iwai (8): Input: i8042 - Add quirk for Fujitsu Lifebook T725 ALSA: hda/realtek: Add a quirk for HP OMEN 15 mute LED ALSA: hda/realtek: Add quirk for ASUS UX550VE ALSA: hda: Free card instance properly at probe errors ALSA: timer: Unconditionally unlink slave instances, too ALSA: mixer: oss: Fix racy access to slots ALSA: hda: Reduce udelay() at SKL+ position reporting ALSA: hda: Use position buffer for SKL+ again Tang Bin (1): crypto: s5p-sss - Add error handling in s5p_aes_probe() Tao Zhang (1): coresight: cti: Correct the parameter for pm_runtime_put Tetsuo Handa (2): smackfs: use __GFP_NOFAIL for smk_cipso_doi() smackfs: use netlbl_cfg_cipsov4_del() for deleting cipso_v4_doi Thomas Perrot (1): spi: spl022: fix Microwire full duplex mode Tiezhu Yang (1): samples/kretprobes: Fix return value if register_kretprobe() failed Tim Crawford (1): ALSA: hda/realtek: Add quirk for Clevo PC70HS Tim Gardner (2): drm/msm: prevent NULL dereference in msm_gpu_crashstate_capture() net: enetc: unmap DMA in enetc_send_cmd() Todd Kjos (3): binder: use euid from cred instead of using task binder: use cred instead of task for selinux checks binder: use cred instead of task for getsecid Tom Lendacky (3): x86/sme: Use #define USE_EARLY_PGTABLE_L5 in mem_encrypt_identity.c arch/cc: Introduce a function to check for confidential computing features x86/sev: Add an x86 version of cc_platform_has() Tom Rix (2): media: TDA1997x: handle short reads of hdmi info frame. apparmor: fix error check Tong Zhang (1): scsi: dc395: Fix error case unwinding Tony Lindgren (3): mmc: sdhci-omap: Fix NULL pointer exception if regulator is not configured mmc: sdhci-omap: Fix context restore bus: ti-sysc: Fix timekeeping_suspended warning on resume Tony Lu (1): net/smc: Fix smc_link->llc_testlink_time overflow Trond Myklebust (6): NFS: Fix dentry verifier races NFS: Fix deadlocks in nfs_scan_commit_list() NFS: Fix up commit deadlocks NFS: Fix an Oops in pnfs_mark_request_commit() NFSv4: Fix a regression in nfs_set_open_stateid_locked() SUNRPC: Partial revert of commit 6f9f17287e78 Tuo Li (2): media: s5p-mfc: fix possible null-pointer dereference in s5p_mfc_probe() ath: dfs_pattern_detector: Fix possible null-pointer dereference in channel_detector_create() Vasant Hegde (1): powerpc/powernv/prd: Unregister OPAL_MSG_PRD2 notifier during module unload Vasily Averin (2): memcg: prohibit unconditional exceeding the limit of dying tasks mm, oom: pagefault_out_of_memory: don't force global OOM for dying tasks Vegard Nossum (1): staging: ks7010: select CRYPTO_HASH/CRYPTO_MICHAEL_MIC Vincent Donnefort (1): PM: EM: Fix inefficient states detection Vineeth Vijayan (1): s390/cio: check the subchannel validity for dev_busid Vitaly Kuznetsov (1): x86/hyperv: Protect set_hv_tscchange_cb() against getting preempted Vladimir Oltean (1): net: stmmac: allow a tc-taprio base-time of zero Vladimir Zapolskiy (1): phy: qcom-qusb2: Fix a memory leak on probe Waiman Long (1): cgroup: Make rebind_subsystems() disable v2 controllers all at once Walter Stoll (1): watchdog: Fix OMAP watchdog early handling Wan Jiabing (1): soc: qcom: apr: Add of_node_put() before return Wang Hai (3): USB: serial: keyspan: fix memleak on probe errors libertas_tf: Fix possible memory leak in probe and disconnect libertas: Fix possible memory leak in probe and disconnect Wen Gong (1): ath11k: add handler for scan event WMI_SCAN_EVENT_DEQUEUED Wen Gu (1): net/smc: Correct spelling mistake to TCPF_SYN_RECV Willem de Bruijn (1): selftests/net: udpgso_bench_rx: fix port argument Wolfram Sang (1): memory: renesas-rpc-if: Correct QSPI data transfer in Manual mode Xiao Ni (1): md: update superblock after changing rdev flags in state_store Xiaoming Ni (2): powerpc/85xx: Fix oops when mpc85xx_smp_guts_ids node cannot be found powerpc/85xx: fix timebase sync issue when CONFIG_HOTPLUG_CPU=n Xin Xiong (1): mmc: moxart: Fix reference count leaks in moxart_probe Xuan Zhuo (1): virtio_ring: check desc == NULL when using indirect with packed Yajun Deng (1): net: net_namespace: Fix undefined member in key_remove_domain() Yang Yingliang (6): ASoC: soc-core: fix null-ptr-deref in snd_soc_del_component_unlocked() pinctrl: core: fix possible memory leak in pinctrl_enable() spi: bcm-qspi: Fix missing clk_disable_unprepare() on error in bcm_qspi_probe() hwmon: Fix possible memleak in __hwmon_device_register() driver core: Fix possible memory leak in device_link_add() power: supply: max17040: fix null-ptr-deref in max17040_probe() Yazen Ghannam (1): EDAC/amd64: Handle three rank interleaving mode Yifan Zhang (1): drm/amdkfd: fix resume error when iommu disabled in Picasso Yu Xiao (1): nfp: bpf: relax prog rejection for mtu check through max_pkt_offset YueHaibing (2): opp: Fix return in _opp_add_static_v2() xen-pciback: Fix return in pm_ctrl_init() Zev Weiss (3): hwmon: (pmbus/lm25066) Add offset coefficients hwmon: (pmbus/lm25066) Let compiler determine outer dimension of lm25066_coeff mtd: core: don't remove debugfs directory if device is in use Zhang Changzhong (2): can: j1939: j1939_tp_cmd_recv(): ignore abort message in the BAM transport can: j1939: j1939_can_recv(): ignore messages with invalid source address Zhang Qiao (1): kernel/sched: Fix sched_fork() access an invalid sched_task_group Zheyu Ma (7): cavium: Return negative value when pci_alloc_irq_vectors() fails scsi: qla2xxx: Return -ENOMEM if kzalloc() fails mISDN: Fix return values of the probe function cavium: Fix return values of the probe function media: netup_unidvb: handle interrupt properly according to the firmware memstick: r592: Fix a UAF bug when removing the driver mwl8k: Fix use-after-free in mwl8k_fw_state_machine() Ziyang Xuan (2): rsi: stop thread firstly in rsi_91x_init() error handling net: vlan: fix a UAF in vlan_dev_real_dev() Zong-Zhe Yang (1): rtw88: fix RX clock gate setting while fifo dump jing yangyang (1): firmware/psci: fix application of sizeof to pointer liuyuntao (1): virtio-gpu: fix possible memory allocation failure .../admin-guide/kernel-parameters.txt | 7 + .../bindings/regulator/samsung,s5m8767.txt | 23 +- Documentation/filesystems/fscrypt.rst | 10 +- arch/Kconfig | 3 + arch/arm/Makefile | 22 +- arch/arm/boot/dts/at91-tse850-3.dts | 2 +- arch/arm/boot/dts/bcm4708-netgear-r6250.dts | 2 +- arch/arm/boot/dts/bcm4709-asus-rt-ac87u.dts | 2 +- .../boot/dts/bcm4709-buffalo-wxr-1900dhp.dts | 2 +- arch/arm/boot/dts/bcm4709-linksys-ea9200.dts | 2 +- arch/arm/boot/dts/bcm4709-netgear-r7000.dts | 2 +- arch/arm/boot/dts/bcm4709-netgear-r8000.dts | 2 +- .../boot/dts/bcm4709-tplink-archer-c9-v1.dts | 2 +- arch/arm/boot/dts/bcm47094-luxul-xwc-2000.dts | 2 +- arch/arm/boot/dts/bcm53016-meraki-mr32.dts | 2 +- arch/arm/boot/dts/bcm94708.dts | 2 +- arch/arm/boot/dts/bcm94709.dts | 2 +- arch/arm/boot/dts/omap3-gta04.dtsi | 2 +- arch/arm/boot/dts/qcom-msm8974.dtsi | 4 +- arch/arm/boot/dts/stm32mp15-pinctrl.dtsi | 8 +- arch/arm/boot/dts/stm32mp151.dtsi | 16 +- arch/arm/boot/dts/stm32mp15xx-dhcor-som.dtsi | 2 +- .../boot/dts/sun7i-a20-olinuxino-lime2.dts | 2 +- arch/arm/kernel/stacktrace.c | 3 +- arch/arm/mach-s3c/irq-s3c24xx.c | 22 +- arch/arm/mm/Kconfig | 2 +- arch/arm/mm/mmu.c | 4 +- .../boot/dts/amlogic/meson-g12a-sei510.dts | 2 +- .../boot/dts/amlogic/meson-g12a-u200.dts | 2 +- .../boot/dts/amlogic/meson-g12a-x96-max.dts | 2 +- .../dts/amlogic/meson-g12b-khadas-vim3.dtsi | 4 +- .../dts/amlogic/meson-g12b-odroid-n2.dtsi | 4 +- .../boot/dts/amlogic/meson-g12b-w400.dtsi | 4 +- arch/arm64/boot/dts/qcom/msm8916.dtsi | 8 +- arch/arm64/boot/dts/qcom/pm8916.dtsi | 1 - .../boot/dts/renesas/beacon-renesom-som.dtsi | 1 + arch/arm64/boot/dts/rockchip/rk3328.dtsi | 2 +- arch/arm64/boot/dts/ti/k3-j721e-main.dtsi | 16 +- arch/arm64/include/asm/esr.h | 1 + arch/arm64/include/asm/pgtable.h | 12 +- arch/arm64/kvm/hyp/hyp-entry.S | 2 +- arch/arm64/kvm/hyp/nvhe/host.S | 2 +- arch/arm64/mm/mmu.c | 5 + arch/arm64/net/bpf_jit_comp.c | 5 + arch/ia64/Kconfig.debug | 2 +- arch/ia64/kernel/kprobes.c | 9 +- arch/m68k/Kconfig.machine | 1 + arch/mips/Kconfig | 1 + arch/mips/include/asm/cmpxchg.h | 5 +- arch/mips/include/asm/mips-cm.h | 12 +- arch/mips/kernel/mips-cm.c | 21 +- arch/mips/kernel/r2300_fpu.S | 4 +- arch/mips/kernel/syscall.c | 9 - arch/mips/lantiq/xway/dma.c | 23 +- arch/openrisc/kernel/dma.c | 4 +- arch/openrisc/kernel/smp.c | 6 +- arch/parisc/kernel/entry.S | 2 +- arch/parisc/kernel/smp.c | 19 +- arch/parisc/kernel/unwind.c | 21 +- arch/parisc/kernel/vmlinux.lds.S | 3 +- arch/parisc/mm/fixmap.c | 5 +- arch/parisc/mm/init.c | 4 +- arch/powerpc/include/asm/code-patching.h | 1 + arch/powerpc/include/asm/firmware.h | 6 - arch/powerpc/include/asm/kvm_guest.h | 25 ++ arch/powerpc/include/asm/kvm_para.h | 2 +- arch/powerpc/include/asm/security_features.h | 5 + arch/powerpc/kernel/firmware.c | 12 +- arch/powerpc/kernel/security.c | 5 + arch/powerpc/lib/code-patching.c | 7 +- arch/powerpc/net/bpf_jit.h | 33 ++- arch/powerpc/net/bpf_jit64.h | 8 +- arch/powerpc/net/bpf_jit_comp64.c | 64 ++++- arch/powerpc/platforms/44x/fsp2.c | 2 + arch/powerpc/platforms/85xx/Makefile | 4 +- arch/powerpc/platforms/85xx/mpc85xx_pm_ops.c | 7 +- arch/powerpc/platforms/85xx/smp.c | 12 +- arch/powerpc/platforms/powernv/opal-prd.c | 12 +- arch/powerpc/platforms/pseries/smp.c | 3 + arch/s390/kvm/priv.c | 2 + arch/s390/kvm/pv.c | 21 +- arch/s390/mm/gmap.c | 5 +- arch/sh/kernel/cpu/fpu.c | 10 +- arch/x86/Kconfig | 1 + arch/x86/events/intel/uncore_snbep.c | 6 +- arch/x86/hyperv/hv_init.c | 5 +- arch/x86/include/asm/cpu_entry_area.h | 8 +- arch/x86/include/asm/mem_encrypt.h | 1 + arch/x86/include/asm/page_64_types.h | 2 +- arch/x86/kernel/Makefile | 6 + arch/x86/kernel/cc_platform.c | 69 +++++ arch/x86/kernel/cpu/amd.c | 2 + arch/x86/kernel/cpu/common.c | 44 ++- arch/x86/kernel/cpu/cpu.h | 1 + arch/x86/kernel/cpu/hygon.c | 2 + arch/x86/kernel/cpu/mce/intel.c | 5 +- arch/x86/kernel/irq.c | 4 +- arch/x86/kernel/sev-es.c | 32 --- arch/x86/kernel/traps.c | 2 +- arch/x86/kvm/vmx/vmx.c | 15 +- arch/x86/mm/cpu_entry_area.c | 7 + arch/x86/mm/mem_encrypt.c | 1 + arch/x86/mm/mem_encrypt_identity.c | 9 + block/blk-mq.c | 18 +- block/blk.h | 6 + crypto/Kconfig | 2 +- crypto/pcrypt.c | 12 +- drivers/acpi/ac.c | 19 ++ drivers/acpi/acpica/acglobal.h | 2 + drivers/acpi/acpica/hwesleep.c | 8 +- drivers/acpi/acpica/hwsleep.c | 11 +- drivers/acpi/acpica/hwxfsleep.c | 7 + drivers/acpi/battery.c | 2 +- drivers/acpi/pmic/intel_pmic.c | 51 ++-- drivers/android/binder.c | 22 +- drivers/ata/libata-core.c | 2 +- drivers/ata/libata-eh.c | 8 + drivers/auxdisplay/ht16k33.c | 66 +++-- drivers/auxdisplay/img-ascii-lcd.c | 10 + drivers/base/core.c | 4 +- drivers/base/power/main.c | 9 +- drivers/block/zram/zram_drv.c | 2 +- drivers/bluetooth/btmtkuart.c | 13 +- drivers/bus/ti-sysc.c | 65 ++++- drivers/char/hw_random/mtk-rng.c | 9 +- drivers/char/ipmi/ipmi_msghandler.c | 10 +- drivers/char/ipmi/ipmi_watchdog.c | 17 +- drivers/char/tpm/tpm2-space.c | 3 + drivers/char/tpm/tpm_tis_core.c | 26 +- drivers/char/tpm/tpm_tis_core.h | 4 + drivers/char/tpm/tpm_tis_spi_main.c | 1 + drivers/clk/at91/clk-sam9x60-pll.c | 4 +- drivers/clk/at91/pmc.c | 5 + drivers/clk/mvebu/ap-cpu-clk.c | 14 +- drivers/clocksource/Kconfig | 1 + drivers/cpuidle/sysfs.c | 5 +- drivers/crypto/caam/caampkc.c | 19 +- drivers/crypto/caam/regs.h | 3 + drivers/crypto/qat/qat_common/adf_pf2vf_msg.c | 13 + drivers/crypto/qat/qat_common/adf_vf_isr.c | 6 + drivers/crypto/s5p-sss.c | 2 + drivers/dma-buf/dma-buf.c | 1 + drivers/dma/at_xdmac.c | 2 +- drivers/dma/dmaengine.h | 2 +- drivers/edac/amd64_edac.c | 22 +- drivers/edac/sb_edac.c | 2 +- drivers/firmware/psci/psci_checker.c | 2 +- drivers/firmware/qcom_scm.c | 2 +- drivers/gpio/gpio-mlxbf2.c | 5 + drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h | 2 +- drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c | 4 +- drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c | 8 +- drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c | 17 +- drivers/gpu/drm/amd/amdkfd/kfd_device.c | 1 + .../drm/amd/display/dc/dcn20/dcn20_resource.c | 16 +- .../gpu/drm/drm_panel_orientation_quirks.c | 47 +++- drivers/gpu/drm/drm_plane_helper.c | 1 - drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.c | 8 +- drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c | 4 + drivers/gpu/drm/msm/msm_gem.c | 4 +- drivers/gpu/drm/msm/msm_gpu.c | 2 +- drivers/gpu/drm/nouveau/nouveau_svm.c | 4 + drivers/gpu/drm/sun4i/sun8i_csc.h | 4 +- drivers/gpu/drm/ttm/ttm_bo_vm.c | 5 - drivers/gpu/drm/v3d/v3d_gem.c | 4 +- drivers/gpu/drm/virtio/virtgpu_vq.c | 8 +- drivers/hid/hid-u2fzero.c | 10 +- drivers/hv/hyperv_vmbus.h | 1 + drivers/hwmon/hwmon.c | 6 +- drivers/hwmon/pmbus/lm25066.c | 25 +- .../hwtracing/coresight/coresight-cti-core.c | 2 +- drivers/i2c/busses/i2c-mt65xx.c | 2 +- drivers/i2c/busses/i2c-xlr.c | 6 +- drivers/iio/accel/st_accel_core.c | 21 +- drivers/iio/accel/st_accel_i2c.c | 17 +- drivers/iio/accel/st_accel_spi.c | 17 +- drivers/iio/dac/ad5446.c | 9 +- drivers/iio/dac/ad5770r.c | 2 +- drivers/iio/gyro/st_gyro_core.c | 15 +- drivers/iio/gyro/st_gyro_i2c.c | 17 +- drivers/iio/gyro/st_gyro_spi.c | 17 +- drivers/iio/imu/adis.c | 4 +- drivers/iio/magnetometer/st_magn_core.c | 15 +- drivers/iio/magnetometer/st_magn_i2c.c | 14 +- drivers/iio/magnetometer/st_magn_spi.c | 14 +- drivers/iio/pressure/st_pressure_core.c | 15 +- drivers/iio/pressure/st_pressure_i2c.c | 17 +- drivers/iio/pressure/st_pressure_spi.c | 17 +- drivers/infiniband/hw/bnxt_re/qplib_fp.c | 3 +- drivers/infiniband/hw/mlx4/qp.c | 4 +- drivers/infiniband/hw/qedr/verbs.c | 15 +- drivers/infiniband/sw/rxe/rxe_param.h | 2 +- drivers/input/joystick/iforce/iforce-usb.c | 2 +- drivers/input/mouse/elantech.c | 13 + drivers/input/serio/i8042-x86ia64io.h | 14 + drivers/irqchip/irq-bcm6345-l1.c | 2 +- drivers/irqchip/irq-sifive-plic.c | 8 +- drivers/isdn/hardware/mISDN/hfcpci.c | 8 +- drivers/md/md.c | 11 +- drivers/media/dvb-frontends/mn88443x.c | 18 +- drivers/media/i2c/ir-kbd-i2c.c | 1 + drivers/media/i2c/mt9p031.c | 28 +- drivers/media/i2c/tda1997x.c | 8 +- drivers/media/pci/cx23885/cx23885-alsa.c | 3 +- .../pci/netup_unidvb/netup_unidvb_core.c | 27 +- drivers/media/platform/mtk-vpu/mtk_vpu.c | 5 +- drivers/media/platform/rcar-vin/rcar-csi2.c | 2 + drivers/media/platform/s5p-mfc/s5p_mfc.c | 6 +- drivers/media/platform/stm32/stm32-dcmi.c | 19 +- drivers/media/radio/radio-wl1273.c | 2 +- drivers/media/radio/si470x/radio-si470x-i2c.c | 2 +- drivers/media/radio/si470x/radio-si470x-usb.c | 2 +- drivers/media/rc/ir_toy.c | 2 +- drivers/media/rc/ite-cir.c | 2 +- drivers/media/rc/mceusb.c | 1 + drivers/media/spi/cxd2880-spi.c | 2 +- drivers/media/usb/dvb-usb/az6027.c | 1 + drivers/media/usb/dvb-usb/dibusb-common.c | 2 +- drivers/media/usb/em28xx/em28xx-cards.c | 5 +- drivers/media/usb/em28xx/em28xx-core.c | 5 +- drivers/media/usb/tm6000/tm6000-video.c | 3 +- drivers/media/usb/uvc/uvc_driver.c | 7 +- drivers/media/usb/uvc/uvc_v4l2.c | 7 +- drivers/media/usb/uvc/uvc_video.c | 5 + drivers/media/v4l2-core/v4l2-ioctl.c | 67 +++-- drivers/memory/fsl_ifc.c | 13 +- drivers/memory/renesas-rpc-if.c | 113 +++++--- drivers/memstick/core/ms_block.c | 2 +- drivers/memstick/host/jmb38x_ms.c | 2 +- drivers/memstick/host/r592.c | 8 +- drivers/mfd/dln2.c | 18 ++ drivers/mfd/mfd-core.c | 2 + drivers/mmc/host/Kconfig | 2 +- drivers/mmc/host/dw_mmc.c | 3 +- drivers/mmc/host/moxart-mmc.c | 29 +- drivers/mmc/host/mtk-sd.c | 5 + drivers/mmc/host/mxs-mmc.c | 10 + drivers/mmc/host/sdhci-omap.c | 18 +- drivers/most/most_usb.c | 5 +- drivers/mtd/mtdcore.c | 4 +- drivers/mtd/nand/raw/ams-delta.c | 12 +- drivers/mtd/nand/raw/au1550nd.c | 12 +- drivers/mtd/nand/raw/gpio.c | 12 +- drivers/mtd/nand/raw/mpc5121_nfc.c | 12 +- drivers/mtd/nand/raw/orion_nand.c | 12 +- drivers/mtd/nand/raw/pasemi_nand.c | 12 +- drivers/mtd/nand/raw/plat_nand.c | 12 +- drivers/mtd/nand/raw/socrates_nand.c | 12 +- drivers/mtd/nand/raw/xway_nand.c | 12 +- drivers/mtd/spi-nor/controllers/hisi-sfc.c | 1 - drivers/net/Kconfig | 2 +- .../net/can/spi/mcp251xfd/mcp251xfd-core.c | 2 +- drivers/net/dsa/rtl8366rb.c | 2 +- drivers/net/ethernet/amd/xgbe/xgbe-common.h | 8 + drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c | 20 +- .../net/ethernet/cavium/thunder/nic_main.c | 2 +- .../net/ethernet/cavium/thunder/nicvf_main.c | 4 +- .../ethernet/chelsio/cxgb4/cxgb4_ethtool.c | 7 +- drivers/net/ethernet/chelsio/cxgb4/t4_hw.h | 2 + .../chelsio/inline_crypto/chtls/chtls_cm.c | 2 +- .../chelsio/inline_crypto/chtls/chtls_cm.h | 2 +- .../net/ethernet/freescale/enetc/enetc_qos.c | 18 +- drivers/net/ethernet/google/gve/gve.h | 4 +- drivers/net/ethernet/google/gve/gve_adminq.h | 1 + drivers/net/ethernet/google/gve/gve_main.c | 48 +++- drivers/net/ethernet/ibm/ibmvnic.c | 5 +- drivers/net/ethernet/intel/ice/ice_base.c | 2 +- .../net/ethernet/intel/ice/ice_virtchnl_pf.c | 20 +- drivers/net/ethernet/netronome/nfp/bpf/main.c | 16 +- drivers/net/ethernet/netronome/nfp/bpf/main.h | 2 + .../net/ethernet/netronome/nfp/bpf/offload.c | 17 +- drivers/net/ethernet/realtek/r8169_main.c | 1 + drivers/net/ethernet/sfc/mcdi_port_common.c | 37 ++- drivers/net/ethernet/sfc/ptp.c | 4 +- drivers/net/ethernet/sfc/siena_sriov.c | 2 +- .../net/ethernet/stmicro/stmmac/stmmac_tc.c | 2 - drivers/net/ethernet/ti/davinci_emac.c | 16 +- drivers/net/ifb.c | 2 + drivers/net/phy/micrel.c | 9 +- drivers/net/phy/phylink.c | 2 +- drivers/net/vmxnet3/vmxnet3_drv.c | 1 - drivers/net/vrf.c | 28 +- drivers/net/wireless/ath/ath10k/mac.c | 45 +++- drivers/net/wireless/ath/ath10k/sdio.c | 5 +- drivers/net/wireless/ath/ath10k/usb.c | 7 +- drivers/net/wireless/ath/ath10k/wmi.c | 4 + drivers/net/wireless/ath/ath10k/wmi.h | 3 + drivers/net/wireless/ath/ath11k/dbring.c | 16 +- drivers/net/wireless/ath/ath11k/dp_rx.c | 13 +- drivers/net/wireless/ath/ath11k/mac.c | 2 +- drivers/net/wireless/ath/ath11k/qmi.c | 4 +- drivers/net/wireless/ath/ath11k/reg.c | 11 +- drivers/net/wireless/ath/ath11k/reg.h | 2 +- drivers/net/wireless/ath/ath11k/wmi.c | 40 ++- drivers/net/wireless/ath/ath11k/wmi.h | 3 +- drivers/net/wireless/ath/ath6kl/usb.c | 7 +- drivers/net/wireless/ath/ath9k/main.c | 4 +- .../net/wireless/ath/dfs_pattern_detector.c | 10 +- drivers/net/wireless/ath/wcn36xx/dxe.c | 49 ++-- drivers/net/wireless/ath/wcn36xx/main.c | 8 +- drivers/net/wireless/ath/wcn36xx/smd.c | 44 ++- drivers/net/wireless/ath/wcn36xx/txrx.c | 64 +++-- drivers/net/wireless/ath/wcn36xx/txrx.h | 3 +- drivers/net/wireless/broadcom/b43/phy_g.c | 2 +- .../net/wireless/broadcom/b43legacy/radio.c | 2 +- .../broadcom/brcm80211/brcmfmac/dmi.c | 10 + .../net/wireless/intel/iwlwifi/mvm/utils.c | 3 + .../net/wireless/marvell/libertas/if_usb.c | 2 + .../net/wireless/marvell/libertas_tf/if_usb.c | 2 + drivers/net/wireless/marvell/mwifiex/11n.c | 5 +- .../net/wireless/marvell/mwifiex/cfg80211.c | 32 +-- drivers/net/wireless/marvell/mwifiex/pcie.c | 36 ++- drivers/net/wireless/marvell/mwifiex/usb.c | 16 ++ drivers/net/wireless/marvell/mwl8k.c | 2 +- .../net/wireless/mediatek/mt76/mt7615/mac.c | 15 +- .../net/wireless/mediatek/mt76/mt76x02_mac.c | 13 +- .../net/wireless/mediatek/mt76/mt7915/mcu.c | 8 +- .../wireless/microchip/wilc1000/cfg80211.c | 3 +- .../realtek/rtl818x/rtl8187/rtl8225.c | 14 +- drivers/net/wireless/realtek/rtw88/fw.c | 7 +- drivers/net/wireless/realtek/rtw88/reg.h | 1 + drivers/net/wireless/rsi/rsi_91x_core.c | 2 + drivers/net/wireless/rsi/rsi_91x_hal.c | 10 +- drivers/net/wireless/rsi/rsi_91x_mac80211.c | 74 ++---- drivers/net/wireless/rsi/rsi_91x_main.c | 17 +- drivers/net/wireless/rsi/rsi_91x_mgmt.c | 24 +- drivers/net/wireless/rsi/rsi_91x_sdio.c | 5 +- drivers/net/wireless/rsi/rsi_91x_usb.c | 5 +- drivers/net/wireless/rsi/rsi_hal.h | 11 + drivers/net/wireless/rsi/rsi_main.h | 15 +- drivers/net/xen-netfront.c | 8 + drivers/nfc/pn533/pn533.c | 6 +- drivers/nvme/host/multipath.c | 9 +- drivers/nvme/host/rdma.c | 2 + drivers/nvme/target/configfs.c | 2 + drivers/nvme/target/rdma.c | 24 ++ drivers/nvme/target/tcp.c | 21 +- drivers/of/unittest.c | 16 +- drivers/opp/of.c | 2 +- .../controller/cadence/pcie-cadence-plat.c | 2 + drivers/pci/controller/dwc/pcie-uniphier.c | 26 +- drivers/pci/controller/pci-aardvark.c | 251 +++++++++++++++--- drivers/pci/pci-bridge-emul.c | 13 + drivers/pci/quirks.c | 1 + drivers/phy/qualcomm/phy-qcom-qusb2.c | 16 +- drivers/phy/qualcomm/phy-qcom-snps-femto-v2.c | 2 +- drivers/phy/ti/phy-gmii-sel.c | 2 + drivers/pinctrl/core.c | 2 + drivers/pinctrl/pinctrl-equilibrium.c | 7 +- drivers/pinctrl/renesas/core.c | 2 +- drivers/platform/x86/thinkpad_acpi.c | 2 +- drivers/platform/x86/wmi.c | 9 +- drivers/power/supply/bq27xxx_battery_i2c.c | 3 +- drivers/power/supply/max17040_battery.c | 2 + drivers/power/supply/max17042_battery.c | 12 +- drivers/power/supply/rt5033_battery.c | 2 +- drivers/regulator/s5m8767.c | 21 +- drivers/remoteproc/remoteproc_core.c | 8 +- drivers/reset/reset-socfpga.c | 26 ++ drivers/rtc/rtc-rv3032.c | 4 +- drivers/s390/char/tape_std.c | 3 +- drivers/s390/cio/css.c | 4 +- drivers/s390/cio/device_ops.c | 12 +- drivers/s390/crypto/ap_queue.c | 2 + drivers/scsi/csiostor/csio_lnode.c | 2 +- drivers/scsi/dc395x.c | 1 + drivers/scsi/pm8001/pm8001_hwi.c | 2 +- drivers/scsi/qla2xxx/qla_attr.c | 24 +- drivers/scsi/qla2xxx/qla_dbg.c | 3 +- drivers/scsi/qla2xxx/qla_gbl.h | 2 - drivers/scsi/qla2xxx/qla_init.c | 54 +++- drivers/scsi/qla2xxx/qla_mr.c | 23 -- drivers/scsi/qla2xxx/qla_os.c | 47 ++-- drivers/scsi/qla2xxx/qla_target.c | 14 +- drivers/scsi/scsi_lib.c | 2 - drivers/scsi/ufs/ufshcd-pltfrm.c | 6 +- drivers/scsi/ufs/ufshcd.c | 29 +- drivers/scsi/ufs/ufshcd.h | 3 + drivers/soc/fsl/dpaa2-console.c | 1 + drivers/soc/fsl/dpio/dpio-service.c | 2 +- drivers/soc/fsl/dpio/qbman-portal.c | 9 +- drivers/soc/qcom/apr.c | 2 + drivers/soc/qcom/rpmhpd.c | 21 +- drivers/soc/tegra/pmc.c | 4 +- drivers/soundwire/debugfs.c | 2 +- drivers/spi/spi-bcm-qspi.c | 5 +- drivers/spi/spi-pl022.c | 5 +- drivers/spi/spi-rpc-if.c | 4 +- drivers/staging/ks7010/Kconfig | 3 + .../staging/media/allegro-dvt/allegro-core.c | 9 + .../media/atomisp/i2c/atomisp-lm3554.c | 37 ++- .../staging/media/imx/imx-media-dev-common.c | 2 + drivers/staging/media/ipu3/ipu3-v4l2.c | 7 +- drivers/staging/media/rkvdec/rkvdec-h264.c | 5 +- drivers/staging/media/rkvdec/rkvdec.c | 40 +-- drivers/staging/most/dim2/Makefile | 2 +- drivers/staging/most/dim2/dim2.c | 24 +- drivers/staging/most/dim2/sysfs.c | 49 ---- drivers/staging/most/dim2/sysfs.h | 11 - drivers/tty/serial/8250/8250_dw.c | 2 +- drivers/tty/serial/8250/8250_port.c | 21 +- drivers/tty/serial/imx.c | 4 +- drivers/tty/serial/serial_core.c | 16 +- drivers/tty/serial/xilinx_uartps.c | 3 +- drivers/usb/chipidea/core.c | 23 +- drivers/usb/dwc2/drd.c | 24 +- drivers/usb/gadget/legacy/hid.c | 4 +- drivers/usb/host/xhci-hub.c | 3 +- drivers/usb/host/xhci-pci.c | 16 ++ drivers/usb/misc/iowarrior.c | 8 +- drivers/usb/musb/Kconfig | 2 +- drivers/usb/serial/keyspan.c | 15 +- drivers/usb/typec/Kconfig | 4 +- drivers/video/backlight/backlight.c | 6 - drivers/video/fbdev/chipsfb.c | 2 +- drivers/virtio/virtio_ring.c | 14 +- drivers/watchdog/Kconfig | 2 +- drivers/watchdog/f71808e_wdt.c | 4 +- drivers/watchdog/omap_wdt.c | 6 +- drivers/xen/balloon.c | 86 ++++-- .../xen/xen-pciback/conf_space_capability.c | 2 +- fs/btrfs/disk-io.c | 3 +- fs/btrfs/reflink.c | 2 +- fs/btrfs/tree-log.c | 4 +- fs/btrfs/volumes.c | 14 +- fs/crypto/fscrypt_private.h | 5 +- fs/crypto/hkdf.c | 11 +- fs/crypto/keysetup.c | 57 +++- fs/erofs/decompressor.c | 1 - fs/exfat/inode.c | 2 +- fs/ext4/super.c | 9 +- fs/f2fs/inode.c | 2 +- fs/f2fs/namei.c | 2 +- fs/fuse/dev.c | 14 +- fs/gfs2/glock.c | 24 +- fs/jfs/jfs_mount.c | 51 ++-- fs/nfs/dir.c | 7 +- fs/nfs/direct.c | 2 +- fs/nfs/flexfilelayout/flexfilelayoutdev.c | 4 +- fs/nfs/nfs4idmap.c | 2 +- fs/nfs/nfs4proc.c | 15 +- fs/nfs/pnfs.h | 2 +- fs/nfs/pnfs_nfs.c | 6 +- fs/nfs/write.c | 26 +- fs/ocfs2/file.c | 8 +- fs/orangefs/dcache.c | 4 +- fs/proc/stat.c | 4 +- fs/proc/uptime.c | 14 +- fs/tracefs/inode.c | 3 +- include/linux/blkdev.h | 2 - include/linux/cc_platform.h | 88 ++++++ include/linux/console.h | 2 + include/linux/ethtool_netlink.h | 3 + include/linux/filter.h | 1 + include/linux/kernel_stat.h | 1 + include/linux/libata.h | 2 +- include/linux/lsm_hook_defs.h | 14 +- include/linux/lsm_hooks.h | 14 +- include/linux/nfs_fs.h | 1 + include/linux/posix-timers.h | 2 + include/linux/rpmsg.h | 2 +- include/linux/sched/task.h | 3 +- include/linux/sched/task_stack.h | 4 + include/linux/security.h | 33 ++- include/linux/seq_file.h | 2 +- include/linux/tpm.h | 1 + include/memory/renesas-rpc-if.h | 1 + include/net/inet_connection_sock.h | 2 +- include/net/llc.h | 4 +- include/net/neighbour.h | 12 +- include/net/sch_generic.h | 4 + include/net/sock.h | 2 +- include/net/strparser.h | 16 +- include/net/tcp.h | 17 +- include/net/udp.h | 5 +- include/uapi/linux/ethtool_netlink.h | 4 +- include/uapi/linux/pci_regs.h | 6 + kernel/bpf/core.c | 4 +- kernel/bpf/verifier.c | 4 +- kernel/cgroup/cgroup.c | 31 ++- kernel/cgroup/rstat.c | 2 - kernel/fork.c | 3 +- kernel/kprobes.c | 3 +- kernel/locking/lockdep.c | 4 +- kernel/power/energy_model.c | 23 +- kernel/power/swap.c | 2 +- kernel/rcu/rcutorture.c | 48 +++- kernel/rcu/tasks.h | 3 +- kernel/rcu/tree_exp.h | 2 +- kernel/rcu/tree_plugin.h | 8 +- kernel/sched/core.c | 43 +-- kernel/signal.c | 18 +- kernel/time/posix-cpu-timers.c | 19 +- kernel/trace/ring_buffer.c | 5 + kernel/trace/tracing_map.c | 40 +-- kernel/workqueue.c | 15 +- lib/decompress_unxz.c | 2 +- lib/iov_iter.c | 5 +- lib/xz/xz_dec_lzma2.c | 21 +- lib/xz/xz_dec_stream.c | 6 +- mm/memcontrol.c | 27 +- mm/oom_kill.c | 23 +- mm/zsmalloc.c | 7 +- net/8021q/vlan.c | 3 - net/8021q/vlan_dev.c | 3 + net/9p/client.c | 2 + net/bluetooth/sco.c | 9 +- net/can/j1939/main.c | 7 + net/can/j1939/transport.c | 6 + net/core/dev.c | 5 +- net/core/filter.c | 21 ++ net/core/neighbour.c | 48 ++-- net/core/net-sysfs.c | 55 ++++ net/core/net_namespace.c | 4 + net/core/stream.c | 3 - net/core/sysctl_net_core.c | 2 +- net/dccp/dccp.h | 2 +- net/dccp/proto.c | 14 +- net/ethtool/pause.c | 3 +- net/ipv4/inet_connection_sock.c | 4 +- net/ipv4/inet_hashtables.c | 2 +- net/ipv4/proc.c | 2 +- net/ipv4/tcp.c | 40 ++- net/ipv4/tcp_bpf.c | 1 - net/ipv6/addrconf.c | 3 + net/ipv6/udp.c | 2 +- net/netfilter/nf_conntrack_proto_udp.c | 7 +- net/netfilter/nfnetlink_queue.c | 2 +- net/netfilter/nft_dynset.c | 11 +- net/rds/ib.c | 10 - net/rds/ib.h | 6 - net/rds/ib_cm.c | 128 +++++---- net/rds/ib_recv.c | 18 +- net/rds/ib_send.c | 8 + net/rxrpc/rtt.c | 2 +- net/sched/sch_generic.c | 9 + net/sched/sch_mq.c | 24 ++ net/sched/sch_mqprio.c | 23 ++ net/sched/sch_taprio.c | 27 +- net/smc/af_smc.c | 20 +- net/smc/smc_llc.c | 2 +- net/strparser/strparser.c | 10 +- net/sunrpc/addr.c | 40 ++- net/sunrpc/xprt.c | 28 +- net/vmw_vsock/af_vsock.c | 2 + samples/kprobes/kretprobe_example.c | 2 +- scripts/leaking_addresses.pl | 3 +- security/apparmor/label.c | 4 +- security/integrity/evm/evm_main.c | 2 +- security/security.c | 14 +- security/selinux/hooks.c | 36 ++- security/selinux/ss/services.c | 162 ++++++----- security/smack/smackfs.c | 11 +- sound/core/oss/mixer_oss.c | 43 ++- sound/core/timer.c | 13 +- sound/pci/hda/hda_intel.c | 74 +++--- sound/pci/hda/patch_realtek.c | 82 ++++++ sound/soc/codecs/cs42l42.c | 88 +++--- sound/soc/soc-core.c | 1 + sound/soc/sof/topology.c | 9 + sound/synth/emux/emux.c | 2 +- sound/usb/6fire/comm.c | 2 +- sound/usb/6fire/firmware.c | 6 +- sound/usb/format.c | 1 + sound/usb/line6/driver.c | 14 +- sound/usb/line6/driver.h | 2 +- sound/usb/line6/podhd.c | 6 +- sound/usb/line6/toneport.c | 2 +- sound/usb/misc/ua101.c | 4 +- sound/usb/quirks.c | 1 + tools/bpf/bpftool/prog.c | 16 +- tools/lib/bpf/bpf_core_read.h | 2 +- tools/lib/bpf/btf.c | 25 +- tools/objtool/check.c | 19 +- tools/perf/util/bpf-event.c | 4 +- .../selftests/bpf/prog_tests/perf_buffer.c | 4 +- .../selftests/bpf/prog_tests/sk_lookup.c | 85 ++++-- .../testing/selftests/bpf/progs/strobemeta.h | 4 +- .../selftests/bpf/progs/test_sk_lookup.c | 62 +++-- tools/testing/selftests/bpf/test_progs.c | 4 +- .../selftests/bpf/verifier/array_access.c | 2 +- .../testing/selftests/core/close_range_test.c | 2 +- tools/testing/selftests/kvm/lib/x86_64/svm.c | 22 +- .../selftests/kvm/x86_64/mmio_warning_test.c | 2 +- tools/testing/selftests/net/fcnal-test.sh | 3 + tools/testing/selftests/net/udpgso_bench_rx.c | 11 +- 587 files changed, 4709 insertions(+), 2317 deletions(-) create mode 100644 arch/powerpc/include/asm/kvm_guest.h create mode 100644 arch/x86/kernel/cc_platform.c delete mode 100644 drivers/staging/most/dim2/sysfs.c create mode 100644 include/linux/cc_platform.h -- 2.20.1

1 557

[PATCH OLK-5.10] Add the configuration for accelerated of SM4
by shenzijun 06 Dec '21

06 Dec '21

From: 沈子俊 <shenzijun(a)kylinos.cn> kylin inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4A842?from=project-issue CVE: NA ------------------------------------------------------------------------- Add the configuration in arch/x86/configs/openeuler_defconfig Signed-off-by: 沈子俊 <shenzijun(a)kylinos.cn> --- arch/x86/configs/openeuler_defconfig | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/x86/configs/openeuler_defconfig b/arch/x86/configs/openeuler_defconfig index b25d908dc7a1..9b23f113f669 100644 --- a/arch/x86/configs/openeuler_defconfig +++ b/arch/x86/configs/openeuler_defconfig @@ -7991,6 +7991,8 @@ CONFIG_CRYPTO_SERPENT_SSE2_X86_64=m CONFIG_CRYPTO_SERPENT_AVX_X86_64=m CONFIG_CRYPTO_SERPENT_AVX2_X86_64=m CONFIG_CRYPTO_SM4=m +CONFIG_CRYPTO_SM4_AESNI_AVX_X86_64=m +CONFIG_CRYPTO_SM4_AESNI_AVX2_X86_64=m CONFIG_CRYPTO_TEA=m CONFIG_CRYPTO_TWOFISH=m CONFIG_CRYPTO_TWOFISH_COMMON=m -- 2.30.0

1 0

[PATCH openEuler-5.10 01/54] hugetlb: before freeing hugetlb page set dtor to appropriate value
by Zheng Zengkai 03 Dec '21

03 Dec '21

From: Mike Kravetz <mike.kravetz(a)oracle.com> mainline inclusion from mainline-v5.15-rc1 commit e32d20c0c88b1cd0a44f882c4f0eb2f536363d1b category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4IGRQ CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… ---------------------------------------------------------------------- When removing a hugetlb page from the pool the ref count is set to one (as the free page has no ref count) and compound page destructor is set to NULL_COMPOUND_DTOR. Since a subsequent call to free the hugetlb page will call __free_pages for non-gigantic pages and free_gigantic_page for gigantic pages the destructor is not used. However, consider the following race with code taking a speculative reference on the page: Thread 0 Thread 1 -------- -------- remove_hugetlb_page set_page_refcounted(page); set_compound_page_dtor(page, NULL_COMPOUND_DTOR); get_page_unless_zero(page) __update_and_free_page __free_pages(page, huge_page_order(h)); /* Note that __free_pages() will simply drop the reference to the page. */ put_page(page) __put_compound_page() destroy_compound_page NULL_COMPOUND_DTOR BUG: kernel NULL pointer dereference, address: 0000000000000000 To address this race, set the dtor to the normal compound page dtor for non-gigantic pages. The dtor for gigantic pages does not matter as gigantic pages are changed from a compound page to 'just a group of pages' before freeing. Hence, the destructor is not used. Link: https://lkml.kernel.org/r/20210809184832.18342-4-mike.kravetz@oracle.com Signed-off-by: Mike Kravetz <mike.kravetz(a)oracle.com> Reviewed-by: Muchun Song <songmuchun(a)bytedance.com> Cc: Michal Hocko <mhocko(a)suse.com> Cc: Oscar Salvador <osalvador(a)suse.de> Cc: David Hildenbrand <david(a)redhat.com> Cc: Matthew Wilcox <willy(a)infradead.org> Cc: Naoya Horiguchi <naoya.horiguchi(a)linux.dev> Cc: Mina Almasry <almasrymina(a)google.com> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> Signed-off-by: Chen Wandun <chenwandun(a)huawei.com> Reviewed-by: Kefeng Wang <wangkefeng.wang(a)huawei.com> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> --- mm/hugetlb.c | 22 +++++++++++++++++++++- 1 file changed, 21 insertions(+), 1 deletion(-) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 47dd6b5e0040..6ae2d2e90681 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1364,8 +1364,28 @@ static void remove_hugetlb_page(struct hstate *h, struct page *page, h->surplus_huge_pages_node[nid]--; } + /* + * Very subtle + * + * For non-gigantic pages set the destructor to the normal compound + * page dtor. This is needed in case someone takes an additional + * temporary ref to the page, and freeing is delayed until they drop + * their reference. + * + * For gigantic pages set the destructor to the null dtor. This + * destructor will never be called. Before freeing the gigantic + * page destroy_compound_gigantic_page will turn the compound page + * into a simple group of pages. After this the destructor does not + * apply. + * + * This handles the case where more than one ref is held when and + * after update_and_free_page is called. + */ set_page_refcounted(page); - set_compound_page_dtor(page, NULL_COMPOUND_DTOR); + if (hstate_is_gigantic(h)) + set_compound_page_dtor(page, NULL_COMPOUND_DTOR); + else + set_compound_page_dtor(page, COMPOUND_PAGE_DTOR); h->nr_huge_pages--; h->nr_huge_pages_node[nid]--; -- 2.20.1

1 53

Re: 【openEuler】Netswift Giga NIC驱动合入openEuler20.03
by Xie XiuQi 03 Dec '21

03 Dec '21

On 2021/12/3 17:46, 郑振鹏 wrote: > 谢工，您好 > > 在千兆驱动合入4.19内核完成后，我打算先推万兆驱动4.19内核功能升级及同步最新bug修复的补丁，再准备5.10内核千兆驱动补丁。 5.10 会在 3 月份发 22.03 LTS 版本，不打算这个版本带进来吗 > > BR， > zhenpeng > > ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ > > **************************************************************** > > 郑振鹏(zheng zhenpeng) > > 北京网迅科技有限公司杭州分公司软件工程师 > > 浙江省杭州市西湖区文三路478号华星时代广场A座507室 310013 > > Beijing WangXun Technology Co., Ltd. Software Engineer. > > Room A507, HuaXing Times Square, No.478 West Wensan Road. > > West Lake District, Hangzhou City, 310013 ZHEJIANG, P.R.CHINA. > > > > Office: +86(0571)89807901-8014 > > Mobile: +86-13656681762 > > E-Mail: z <mailto:jianwang@trustnetic.com>henpengzheng(a)net-swift.com > > **************************************************************** > > > *发件人：* Xie XiuQi <mailto:xiexiuqi@huawei.com> > *发送时间：* 2021-12-03 16:15 > *收件人：* 郑振鹏 <mailto:zhenpengzheng@net-swift.com>; QiuLaibin <mailto:qiulaibin@huawei.com> > *抄送：* yangyingliang(a)huawei.com <mailto:yangyingliang@huawei.com>; kernel(a)openeuler.org <mailto:kernel@openeuler.org> > *主题：* Re: 【openEuler】Netswift Giga NIC驱动合入openEuler20.03 > > > On 2021/12/3 15:17, 郑振鹏 wrote: > > 您好， > > > > 目前我只在x86平台上测试我此次提交的patch，如果完成arm平台测试我再提交新的patch。 > > 感谢。 > > Netswift Giga NIC 对 22.03 （5.10内核）的支持，这个是不是也在做。 > > > > > BR， > > zhenpeng > > > > > ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ > > > > **************************************************************** > > > > 郑振鹏(zheng zhenpeng) > > > > 北京网迅科技有限公司杭州分公司软件工程师 > > > > 浙江省杭州市西湖区文三路478号华星时代广场A座507室 310013 > > > > Beijing WangXun Technology Co., Ltd. Software Engineer. > > > > Room A507, HuaXing Times Square, No.478 West Wensan Road. > > > > West Lake District, Hangzhou City, 310013 ZHEJIANG, P.R.CHINA. > > > > > > > > Office: +86(0571)89807901-8014 > > > > Mobile: +86-13656681762 > > > > E-Mail: z <mailto:jianwang@trustnetic.com>henpengzheng(a)net-swift.com > > > > **************************************************************** > > > > > > *发件人：* QiuLaibin <mailto:qiulaibin@huawei.com> > > *发送时间：* 2021-12-03 15:01 > > *收件人：* zhenpengzheng(a)net-swift.com <mailto:zhenpengzheng@net-swift.com> > > *抄送：* Xiexiuqi <mailto:xiexiuqi@huawei.com>; yangyingliang(a)huawei.com <mailto:yangyingliang@huawei.com> > > *主题：* 【openEuler】Netswift Giga NIC驱动合入openEuler20.03 > > pengzheng您好： > > > > 非常感谢您的提交！ > > > > 目前我们正在向版本合入先前您针对openEuler提交的Netswift Giga NIC驱补丁集： > > > > [openEuler-1.0-LTS,1/2] net: ngbe: Add Netswift Giga NIC driver > > [openEuler-1.0-LTS,2/2] x86/config: Enable netswift Giga NIC driver for x86 > > > > 但鉴于您在编译config只在X86的config中打开，因此我们需要确认是否该驱动只能支持X86平台；arm上是否可以打开支持，若arm相关的config误打开是否会引入问题。 > > > > best regard > > Laibin Qiu > > > > > > >

1 0

Jump to page: