Linux-stable-mirror

linux-stable-mirror@lists.linaro.org

341 participants
124249 discussions

[PATCH 6.1.y] fs/ntfs3: Change new sparse cluster processing

by Miguel García

From: Konstantin Komarov <almaz.alexandrovich(a)paragon-software.com> commit c380b52f6c5702cc4bdda5e6d456d6c19a201a0b upstream. This patch is a backport. Remove ntfs_sparse_cluster. Zero clusters in attr_allocate_clusters. Fixes xfstest generic/263 The fix has been verified by executing the syzkaller reproducer test case. Bug: https://syzkaller.appspot.com/bug?extid=f3e5d0948a1837ed1bb0 Reported-by: syzbot+f3e5d0948a1837ed1bb0(a)syzkaller.appspotmail.com Cc: <stable(a)vger.kernel.org> Signed-off-by: Konstantin Komarov <almaz.alexandrovich(a)paragon-software.com> Signed-off-by: Miguel Garcia Roman <miguelgarciaroman8(a)gmail.com> (cherry picked from commit c380b52f6c5702cc4bdda5e6d456d6c19a201a0b) --- fs/ntfs3/attrib.c | 176 +++++++++++++++++++++++++++++++-------------- fs/ntfs3/file.c | 151 +++++++++----------------------------- fs/ntfs3/frecord.c | 2 +- fs/ntfs3/index.c | 4 +- fs/ntfs3/inode.c | 12 ++-- fs/ntfs3/ntfs_fs.h | 7 +- 6 files changed, 166 insertions(+), 186 deletions(-) diff --git a/fs/ntfs3/attrib.c b/fs/ntfs3/attrib.c index 0388e6b42100..3e402b597e0f 100644 --- a/fs/ntfs3/attrib.c +++ b/fs/ntfs3/attrib.c @@ -176,7 +176,7 @@ static int run_deallocate_ex(struct ntfs_sb_info *sbi, struct runs_tree *run, int attr_allocate_clusters(struct ntfs_sb_info *sbi, struct runs_tree *run, CLST vcn, CLST lcn, CLST len, CLST *pre_alloc, enum ALLOCATE_OPT opt, CLST *alen, const size_t fr, - CLST *new_lcn) + CLST *new_lcn, CLST *new_len) { int err; CLST flen, vcn0 = vcn, pre = pre_alloc ? *pre_alloc : 0; @@ -196,20 +196,36 @@ int attr_allocate_clusters(struct ntfs_sb_info *sbi, struct runs_tree *run, if (err) goto out; - if (new_lcn && vcn == vcn0) - *new_lcn = lcn; + if (vcn == vcn0) { + /* Return the first fragment. */ + if (new_lcn) + *new_lcn = lcn; + if (new_len) + *new_len = flen; + } /* Add new fragment into run storage. */ - if (!run_add_entry(run, vcn, lcn, flen, opt == ALLOCATE_MFT)) { + if (!run_add_entry(run, vcn, lcn, flen, opt & ALLOCATE_MFT)) { /* Undo last 'ntfs_look_for_free_space' */ mark_as_free_ex(sbi, lcn, len, false); err = -ENOMEM; goto out; } + if (opt & ALLOCATE_ZERO) { + u8 shift = sbi->cluster_bits - SECTOR_SHIFT; + + err = blkdev_issue_zeroout(sbi->sb->s_bdev, + (sector_t)lcn << shift, + (sector_t)flen << shift, + GFP_NOFS, 0); + if (err) + goto out; + } + vcn += flen; - if (flen >= len || opt == ALLOCATE_MFT || + if (flen >= len || (opt & ALLOCATE_MFT) || (fr && run->count - cnt >= fr)) { *alen = vcn - vcn0; return 0; @@ -287,7 +303,8 @@ int attr_make_nonresident(struct ntfs_inode *ni, struct ATTRIB *attr, const char *data = resident_data(attr); err = attr_allocate_clusters(sbi, run, 0, 0, len, NULL, - ALLOCATE_DEF, &alen, 0, NULL); + ALLOCATE_DEF, &alen, 0, NULL, + NULL); if (err) goto out1; @@ -582,13 +599,13 @@ int attr_set_size(struct ntfs_inode *ni, enum ATTR_TYPE type, /* ~3 bytes per fragment. */ err = attr_allocate_clusters( sbi, run, vcn, lcn, to_allocate, &pre_alloc, - is_mft ? ALLOCATE_MFT : 0, &alen, + is_mft ? ALLOCATE_MFT : ALLOCATE_DEF, &alen, is_mft ? 0 : (sbi->record_size - le32_to_cpu(rec->used) + 8) / 3 + 1, - NULL); + NULL, NULL); if (err) goto out; } @@ -886,8 +903,19 @@ int attr_set_size(struct ntfs_inode *ni, enum ATTR_TYPE type, return err; } +/* + * attr_data_get_block - Returns 'lcn' and 'len' for given 'vcn'. + * + * @new == NULL means just to get current mapping for 'vcn' + * @new != NULL means allocate real cluster if 'vcn' maps to hole + * @zero - zeroout new allocated clusters + * + * NOTE: + * - @new != NULL is called only for sparsed or compressed attributes. + * - new allocated clusters are zeroed via blkdev_issue_zeroout. + */ int attr_data_get_block(struct ntfs_inode *ni, CLST vcn, CLST clen, CLST *lcn, - CLST *len, bool *new) + CLST *len, bool *new, bool zero) { int err = 0; struct runs_tree *run = &ni->file.run; @@ -896,29 +924,27 @@ int attr_data_get_block(struct ntfs_inode *ni, CLST vcn, CLST clen, CLST *lcn, 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; + CLST hint, svcn, to_alloc, evcn1, next_svcn, asize, end, vcn0, alen; + unsigned int fr; u64 total_size; - u32 clst_per_frame; - bool ok; if (new) *new = false; + /* Try to find in cache. */ down_read(&ni->file.run_lock); - ok = run_lookup_entry(run, vcn, lcn, len, NULL); + if (!run_lookup_entry(run, vcn, lcn, len, NULL)) + *len = 0; up_read(&ni->file.run_lock); - if (ok && (*lcn != SPARSE_LCN || !new)) { - /* Normal way. */ - return 0; + if (*len) { + if (*lcn != SPARSE_LCN || !new) + return 0; /* Fast normal way without allocation. */ + else if (clen > *len) + clen = *len; } - if (!clen) - clen = 1; - - if (ok && clen > *len) - clen = *len; - + /* No cluster in cache or we need to allocate cluster in hole. */ sbi = ni->mi.sbi; cluster_bits = sbi->cluster_bits; @@ -944,12 +970,6 @@ int attr_data_get_block(struct ntfs_inode *ni, CLST vcn, CLST clen, CLST *lcn, 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; @@ -968,36 +988,68 @@ int attr_data_get_block(struct ntfs_inode *ni, CLST vcn, CLST clen, CLST *lcn, evcn1 = le64_to_cpu(attr->nres.evcn) + 1; } + /* Load in cache actual information. */ 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 (!*len) { + if (run_lookup_entry(run, vcn, lcn, len, NULL)) { + if (*lcn != SPARSE_LCN || !new) + goto ok; /* Slow normal way without allocation. */ - if (!ok && !new) { - *len = 0; - err = 0; + if (clen > *len) + clen = *len; + } else if (!new) { + /* Here we may return -ENOENT. + * In any case caller gets zero length. */ 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)) { + /* The code below only for sparsed or compressed attributes. */ err = -EINVAL; goto out; } + vcn0 = vcn; + to_alloc = clen; + fr = (sbi->record_size - le32_to_cpu(mi->mrec->used) + 8) / 3 + 1; + /* Allocate frame aligned clusters. + * ntfs.sys usually uses 16 clusters per frame for sparsed or compressed. + * ntfs3 uses 1 cluster per frame for new created sparsed files. */ + if (attr_b->nres.c_unit) { + CLST clst_per_frame = 1u << attr_b->nres.c_unit; + CLST cmask = ~(clst_per_frame - 1); + + /* Get frame aligned vcn and to_alloc. */ + vcn = vcn0 & cmask; + to_alloc = ((vcn0 + clen + clst_per_frame - 1) & cmask) - vcn; + if (fr < clst_per_frame) + fr = clst_per_frame; + zero = true; + + /* Check if 'vcn' and 'vcn0' in different attribute segments. */ + if (vcn < svcn || evcn1 <= vcn) { + /* Load attribute for truncated 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 (vcn + to_alloc > asize) + to_alloc = asize - vcn; + /* Get the last LCN to allocate from. */ hint = 0; @@ -1011,18 +1063,33 @@ int attr_data_get_block(struct ntfs_inode *ni, CLST vcn, CLST clen, CLST *lcn, 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); + /* Allocate and zeroout new clusters. */ + err = attr_allocate_clusters(sbi, run, vcn, hint + 1, to_alloc, NULL, + zero ? ALLOCATE_ZERO : ALLOCATE_DEF, &alen, + fr, lcn, len); if (err) goto out; *new = true; - end = vcn + *len; - + end = vcn + alen; total_size = le64_to_cpu(attr_b->nres.total_size) + - ((u64)*len << cluster_bits); + ((u64)alen << cluster_bits); + + if (vcn != vcn0) { + if (!run_lookup_entry(run, vcn0, lcn, len, NULL)) { + err = -EINVAL; + goto out; + } + if (*lcn == SPARSE_LCN) { + /* Internal error. Should not happened. */ + WARN_ON(1); + err = -EINVAL; + goto out; + } + /* Check case when vcn0 + len overlaps new allocated clusters. */ + if (vcn0 + *len > end) + *len = end - vcn0; + } repack: err = mi_pack_runs(mi, attr, run, max(end, evcn1) - svcn); @@ -1547,7 +1614,7 @@ int attr_allocate_frame(struct ntfs_inode *ni, CLST frame, size_t compr_size, 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 svcn, evcn1, next_svcn, len; CLST vcn, end, clst_data; u64 total_size, valid_size, data_size; @@ -1623,8 +1690,9 @@ int attr_allocate_frame(struct ntfs_inode *ni, CLST frame, size_t compr_size, } err = attr_allocate_clusters(sbi, run, vcn + clst_data, - hint + 1, len - clst_data, NULL, 0, - &alen, 0, &lcn); + hint + 1, len - clst_data, NULL, + ALLOCATE_DEF, &alen, 0, NULL, + NULL); if (err) goto out; diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c index 70b38465aee3..72e25842f5dc 100644 --- a/fs/ntfs3/file.c +++ b/fs/ntfs3/file.c @@ -122,8 +122,8 @@ static int ntfs_extend_initialized_size(struct file *file, bits = sbi->cluster_bits; vcn = pos >> bits; - err = attr_data_get_block(ni, vcn, 0, &lcn, &clen, - NULL); + err = attr_data_get_block(ni, vcn, 1, &lcn, &clen, NULL, + false); if (err) goto out; @@ -196,18 +196,18 @@ static int ntfs_zero_range(struct inode *inode, u64 vbo, u64 vbo_to) struct address_space *mapping = inode->i_mapping; u32 blocksize = 1 << inode->i_blkbits; pgoff_t idx = vbo >> PAGE_SHIFT; - u32 z_start = vbo & (PAGE_SIZE - 1); + u32 from = vbo & (PAGE_SIZE - 1); pgoff_t idx_end = (vbo_to + PAGE_SIZE - 1) >> PAGE_SHIFT; loff_t page_off; struct buffer_head *head, *bh; - u32 bh_next, bh_off, z_end; + u32 bh_next, bh_off, to; sector_t iblock; struct page *page; - for (; idx < idx_end; idx += 1, z_start = 0) { + for (; idx < idx_end; idx += 1, from = 0) { page_off = (loff_t)idx << PAGE_SHIFT; - z_end = (page_off + PAGE_SIZE) > vbo_to ? (vbo_to - page_off) - : PAGE_SIZE; + to = (page_off + PAGE_SIZE) > vbo_to ? (vbo_to - page_off) + : PAGE_SIZE; iblock = page_off >> inode->i_blkbits; page = find_or_create_page(mapping, idx, @@ -224,7 +224,7 @@ static int ntfs_zero_range(struct inode *inode, u64 vbo, u64 vbo_to) do { bh_next = bh_off + blocksize; - if (bh_next <= z_start || bh_off >= z_end) + if (bh_next <= from || bh_off >= to) continue; if (!buffer_mapped(bh)) { @@ -258,7 +258,7 @@ static int ntfs_zero_range(struct inode *inode, u64 vbo, u64 vbo_to) } while (bh_off = bh_next, iblock += 1, head != (bh = bh->b_this_page)); - zero_user_segment(page, z_start, z_end); + zero_user_segment(page, from, to); unlock_page(page); put_page(page); @@ -269,81 +269,6 @@ static int ntfs_zero_range(struct inode *inode, u64 vbo, u64 vbo_to) return err; } -/* - * ntfs_sparse_cluster - Helper function to zero a new allocated clusters. - * - * NOTE: 512 <= cluster size <= 2M - */ -void ntfs_sparse_cluster(struct inode *inode, struct page *page0, CLST vcn, - CLST len) -{ - struct address_space *mapping = inode->i_mapping; - struct ntfs_sb_info *sbi = inode->i_sb->s_fs_info; - u64 vbo = (u64)vcn << sbi->cluster_bits; - u64 bytes = (u64)len << sbi->cluster_bits; - u32 blocksize = 1 << inode->i_blkbits; - pgoff_t idx0 = page0 ? page0->index : -1; - loff_t vbo_clst = vbo & sbi->cluster_mask_inv; - loff_t end = ntfs_up_cluster(sbi, vbo + bytes); - pgoff_t idx = vbo_clst >> PAGE_SHIFT; - u32 from = vbo_clst & (PAGE_SIZE - 1); - pgoff_t idx_end = (end + PAGE_SIZE - 1) >> PAGE_SHIFT; - loff_t page_off; - u32 to; - bool partial; - struct page *page; - - for (; idx < idx_end; idx += 1, from = 0) { - page = idx == idx0 ? page0 : grab_cache_page(mapping, idx); - - if (!page) - continue; - - page_off = (loff_t)idx << PAGE_SHIFT; - to = (page_off + PAGE_SIZE) > end ? (end - page_off) - : PAGE_SIZE; - partial = false; - - if ((from || PAGE_SIZE != to) && - likely(!page_has_buffers(page))) { - create_empty_buffers(page, blocksize, 0); - } - - if (page_has_buffers(page)) { - struct buffer_head *head, *bh; - u32 bh_off = 0; - - bh = head = page_buffers(page); - do { - u32 bh_next = bh_off + blocksize; - - if (from <= bh_off && bh_next <= to) { - set_buffer_uptodate(bh); - mark_buffer_dirty(bh); - } else if (!buffer_uptodate(bh)) { - partial = true; - } - bh_off = bh_next; - } while (head != (bh = bh->b_this_page)); - } - - zero_user_segment(page, from, to); - - if (!partial) { - if (!PageUptodate(page)) - SetPageUptodate(page); - set_page_dirty(page); - } - - if (idx != idx0) { - unlock_page(page); - put_page(page); - } - cond_resched(); - } - mark_inode_dirty(inode); -} - /* * ntfs_file_mmap - file_operations::mmap */ @@ -385,13 +310,9 @@ static int ntfs_file_mmap(struct file *file, struct vm_area_struct *vma) for (; vcn < end; vcn += len) { err = attr_data_get_block(ni, vcn, 1, &lcn, - &len, &new); + &len, &new, true); if (err) goto out; - - if (!new) - continue; - ntfs_sparse_cluster(inode, NULL, vcn, 1); } } @@ -532,7 +453,8 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t vbo, loff_t len) struct ntfs_sb_info *sbi = sb->s_fs_info; struct ntfs_inode *ni = ntfs_i(inode); loff_t end = vbo + len; - loff_t vbo_down = round_down(vbo, PAGE_SIZE); + loff_t vbo_down = round_down(vbo, max_t(unsigned long, + sbi->cluster_size, PAGE_SIZE)); bool is_supported_holes = is_sparsed(ni) || is_compressed(ni); loff_t i_size, new_size; bool map_locked; @@ -585,11 +507,8 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t vbo, loff_t len) u32 frame_size; loff_t mask, vbo_a, end_a, tmp; - err = filemap_write_and_wait_range(mapping, vbo, end - 1); - if (err) - goto out; - - err = filemap_write_and_wait_range(mapping, end, LLONG_MAX); + err = filemap_write_and_wait_range(mapping, vbo_down, + LLONG_MAX); if (err) goto out; @@ -692,39 +611,35 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t vbo, loff_t len) goto out; if (is_supported_holes) { - CLST vcn_v = ni->i_valid >> sbi->cluster_bits; CLST vcn = vbo >> sbi->cluster_bits; CLST cend = bytes_to_cluster(sbi, end); + CLST cend_v = bytes_to_cluster(sbi, ni->i_valid); CLST lcn, clen; bool new; + if (cend_v > cend) + cend_v = cend; + /* - * Allocate but do not zero new clusters. (see below comments) - * This breaks security: One can read unused on-disk areas. + * Allocate and zero new clusters. * Zeroing these clusters may be too long. - * Maybe we should check here for root rights? + */ + for (; vcn < cend_v; vcn += clen) { + err = attr_data_get_block(ni, vcn, cend_v - vcn, + &lcn, &clen, &new, + true); + if (err) + goto out; + } + /* + * Allocate but not zero new clusters. */ for (; vcn < cend; vcn += clen) { err = attr_data_get_block(ni, vcn, cend - vcn, - &lcn, &clen, &new); + &lcn, &clen, &new, + false); if (err) goto out; - if (!new || vcn >= vcn_v) - continue; - - /* - * Unwritten area. - * NTFS is not able to store several unwritten areas. - * Activate 'ntfs_sparse_cluster' to zero new allocated clusters. - * - * Dangerous in case: - * 1G of sparsed clusters + 1 cluster of data => - * valid_size == 1G + 1 cluster - * fallocate(1G) will zero 1G and this can be very long - * xfstest 016/086 will fail without 'ntfs_sparse_cluster'. - */ - ntfs_sparse_cluster(inode, NULL, vcn, - min(vcn_v - vcn, clen)); } } @@ -945,8 +860,8 @@ static ssize_t ntfs_compress_write(struct kiocb *iocb, struct iov_iter *from) frame_vbo = valid & ~(frame_size - 1); off = valid & (frame_size - 1); - err = attr_data_get_block(ni, frame << NTFS_LZNT_CUNIT, 0, &lcn, - &clen, NULL); + err = attr_data_get_block(ni, frame << NTFS_LZNT_CUNIT, 1, &lcn, + &clen, NULL, false); if (err) goto out; diff --git a/fs/ntfs3/frecord.c b/fs/ntfs3/frecord.c index d41ddc06f207..fb572688f919 100644 --- a/fs/ntfs3/frecord.c +++ b/fs/ntfs3/frecord.c @@ -2297,7 +2297,7 @@ int ni_decompress_file(struct ntfs_inode *ni) for (vcn = vbo >> sbi->cluster_bits; vcn < end; vcn += clen) { err = attr_data_get_block(ni, vcn, cend - vcn, &lcn, - &clen, &new); + &clen, &new, false); if (err) goto out; } diff --git a/fs/ntfs3/index.c b/fs/ntfs3/index.c index 2589f6d1215f..2dfe74a3de75 100644 --- a/fs/ntfs3/index.c +++ b/fs/ntfs3/index.c @@ -1442,8 +1442,8 @@ static int indx_create_allocate(struct ntfs_index *indx, struct ntfs_inode *ni, run_init(&run); - err = attr_allocate_clusters(sbi, &run, 0, 0, len, NULL, 0, &alen, 0, - NULL); + err = attr_allocate_clusters(sbi, &run, 0, 0, len, NULL, ALLOCATE_DEF, + &alen, 0, NULL, NULL); if (err) goto out; diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c index 057aa3cec902..5baf6a2b3d48 100644 --- a/fs/ntfs3/inode.c +++ b/fs/ntfs3/inode.c @@ -592,7 +592,8 @@ static noinline int ntfs_get_block_vbo(struct inode *inode, u64 vbo, off = vbo & sbi->cluster_mask; new = false; - err = attr_data_get_block(ni, vcn, 1, &lcn, &len, create ? &new : NULL); + err = attr_data_get_block(ni, vcn, 1, &lcn, &len, create ? &new : NULL, + create && sbi->cluster_size > PAGE_SIZE); if (err) goto out; @@ -610,11 +611,8 @@ static noinline int ntfs_get_block_vbo(struct inode *inode, u64 vbo, WARN_ON(1); } - if (new) { + 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; @@ -1533,8 +1531,8 @@ struct inode *ntfs_create_inode(struct user_namespace *mnt_userns, cpu_to_le64(ntfs_up_cluster(sbi, nsize)); err = attr_allocate_clusters(sbi, &ni->file.run, 0, 0, - clst, NULL, 0, &alen, 0, - NULL); + clst, NULL, ALLOCATE_DEF, + &alen, 0, NULL, NULL); if (err) goto out5; diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h index 26dbe1b46fdd..05d9abd66b37 100644 --- a/fs/ntfs3/ntfs_fs.h +++ b/fs/ntfs3/ntfs_fs.h @@ -126,6 +126,7 @@ struct ntfs_buffers { enum ALLOCATE_OPT { ALLOCATE_DEF = 0, // Allocate all clusters. ALLOCATE_MFT = 1, // Allocate for MFT. + ALLOCATE_ZERO = 2, // Zeroout new allocated clusters }; enum bitmap_mutex_classes { @@ -416,7 +417,7 @@ enum REPARSE_SIGN { 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); + CLST *new_lcn, CLST *new_len); 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, @@ -426,7 +427,7 @@ int attr_set_size(struct ntfs_inode *ni, enum ATTR_TYPE type, u64 new_size, const u64 *new_valid, bool keep_prealloc, struct ATTRIB **ret); int attr_data_get_block(struct ntfs_inode *ni, CLST vcn, CLST clen, CLST *lcn, - CLST *len, bool *new); + CLST *len, bool *new, bool zero); int attr_data_read_resident(struct ntfs_inode *ni, struct page *page); int attr_data_write_resident(struct ntfs_inode *ni, struct page *page); int attr_load_runs_vcn(struct ntfs_inode *ni, enum ATTR_TYPE type, @@ -491,8 +492,6 @@ extern const struct file_operations ntfs_dir_operations; /* Globals from file.c */ int ntfs_getattr(struct user_namespace *mnt_userns, const struct path *path, struct kstat *stat, u32 request_mask, u32 flags); -void ntfs_sparse_cluster(struct inode *inode, struct page *page0, CLST vcn, - CLST len); int ntfs3_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, struct iattr *attr); int ntfs_file_open(struct inode *inode, struct file *file); -- 2.34.1

9 months, 4 weeks

[PATCH 6.1.y 6.6.y 1/1] netfilter: nft_counter: Use u64_stats_t for statistic.

by Felix Moessbauer

From: Sebastian Andrzej Siewior <bigeasy(a)linutronix.de> commit 4a1d3acd6ea86075e77fcc1188c3fc372833ba73 upstream. The nft_counter uses two s64 counters for statistics. Those two are protected by a seqcount to ensure that the 64bit variable is always properly seen during updates even on 32bit architectures where the store is performed by two writes. A side effect is that the two counter (bytes and packet) are written and read together in the same window. This can be replaced with u64_stats_t. write_seqcount_begin()/ end() is replaced with u64_stats_update_begin()/ end() and behaves the same way as with seqcount_t on 32bit architectures. Additionally there is a preempt_disable on PREEMPT_RT to ensure that a reader does not preempt a writer. On 64bit architectures the macros are removed and the reads happen without any retries. This also means that the reader can observe one counter (bytes) from before the update and the other counter (packets) but that is okay since there is no requirement to have both counter from the same update window. Convert the statistic to u64_stats_t. There is one optimisation: nft_counter_do_init() and nft_counter_clone() allocate a new per-CPU counter and assign a value to it. During this assignment preemption is disabled which is not needed because the counter is not yet exposed to the system so there can not be another writer or reader. Therefore disabling preemption is omitted and raw_cpu_ptr() is used to obtain a pointer to a counter for the assignment. Cc: Eric Dumazet <edumazet(a)google.com> Signed-off-by: Sebastian Andrzej Siewior <bigeasy(a)linutronix.de> Signed-off-by: Pablo Neira Ayuso <pablo(a)netfilter.org> Signed-off-by: Felix Moessbauer <felix.moessbauer(a)siemens.com> --- I propose the backport, as this is a performance improvement. Note, that this is a bugfix on RT kernels. net/netfilter/nft_counter.c | 90 +++++++++++++++++++------------------ 1 file changed, 46 insertions(+), 44 deletions(-) diff --git a/net/netfilter/nft_counter.c b/net/netfilter/nft_counter.c index 781d3a26f5df..8d19bd001277 100644 --- a/net/netfilter/nft_counter.c +++ b/net/netfilter/nft_counter.c @@ -8,7 +8,7 @@ #include <linux/kernel.h> #include <linux/init.h> #include <linux/module.h> -#include <linux/seqlock.h> +#include <linux/u64_stats_sync.h> #include <linux/netlink.h> #include <linux/netfilter.h> #include <linux/netfilter/nf_tables.h> @@ -17,6 +17,11 @@ #include <net/netfilter/nf_tables_offload.h> struct nft_counter { + u64_stats_t bytes; + u64_stats_t packets; +}; + +struct nft_counter_tot { s64 bytes; s64 packets; }; @@ -25,25 +30,24 @@ struct nft_counter_percpu_priv { struct nft_counter __percpu *counter; }; -static DEFINE_PER_CPU(seqcount_t, nft_counter_seq); +static DEFINE_PER_CPU(struct u64_stats_sync, nft_counter_sync); static inline void nft_counter_do_eval(struct nft_counter_percpu_priv *priv, struct nft_regs *regs, const struct nft_pktinfo *pkt) { + struct u64_stats_sync *nft_sync; struct nft_counter *this_cpu; - seqcount_t *myseq; local_bh_disable(); this_cpu = this_cpu_ptr(priv->counter); - myseq = this_cpu_ptr(&nft_counter_seq); - - write_seqcount_begin(myseq); + nft_sync = this_cpu_ptr(&nft_counter_sync); - this_cpu->bytes += pkt->skb->len; - this_cpu->packets++; + u64_stats_update_begin(nft_sync); + u64_stats_add(&this_cpu->bytes, pkt->skb->len); + u64_stats_inc(&this_cpu->packets); + u64_stats_update_end(nft_sync); - write_seqcount_end(myseq); local_bh_enable(); } @@ -66,17 +70,16 @@ static int nft_counter_do_init(const struct nlattr * const tb[], if (cpu_stats == NULL) return -ENOMEM; - preempt_disable(); - this_cpu = this_cpu_ptr(cpu_stats); + this_cpu = raw_cpu_ptr(cpu_stats); if (tb[NFTA_COUNTER_PACKETS]) { - this_cpu->packets = - be64_to_cpu(nla_get_be64(tb[NFTA_COUNTER_PACKETS])); + u64_stats_set(&this_cpu->packets, + be64_to_cpu(nla_get_be64(tb[NFTA_COUNTER_PACKETS]))); } if (tb[NFTA_COUNTER_BYTES]) { - this_cpu->bytes = - be64_to_cpu(nla_get_be64(tb[NFTA_COUNTER_BYTES])); + u64_stats_set(&this_cpu->bytes, + be64_to_cpu(nla_get_be64(tb[NFTA_COUNTER_BYTES]))); } - preempt_enable(); + priv->counter = cpu_stats; return 0; } @@ -104,40 +107,41 @@ static void nft_counter_obj_destroy(const struct nft_ctx *ctx, } static void nft_counter_reset(struct nft_counter_percpu_priv *priv, - struct nft_counter *total) + struct nft_counter_tot *total) { + struct u64_stats_sync *nft_sync; struct nft_counter *this_cpu; - seqcount_t *myseq; local_bh_disable(); this_cpu = this_cpu_ptr(priv->counter); - myseq = this_cpu_ptr(&nft_counter_seq); + nft_sync = this_cpu_ptr(&nft_counter_sync); + + u64_stats_update_begin(nft_sync); + u64_stats_add(&this_cpu->packets, -total->packets); + u64_stats_add(&this_cpu->bytes, -total->bytes); + u64_stats_update_end(nft_sync); - write_seqcount_begin(myseq); - this_cpu->packets -= total->packets; - this_cpu->bytes -= total->bytes; - write_seqcount_end(myseq); local_bh_enable(); } static void nft_counter_fetch(struct nft_counter_percpu_priv *priv, - struct nft_counter *total) + struct nft_counter_tot *total) { struct nft_counter *this_cpu; - const seqcount_t *myseq; u64 bytes, packets; unsigned int seq; int cpu; memset(total, 0, sizeof(*total)); for_each_possible_cpu(cpu) { - myseq = per_cpu_ptr(&nft_counter_seq, cpu); + struct u64_stats_sync *nft_sync = per_cpu_ptr(&nft_counter_sync, cpu); + this_cpu = per_cpu_ptr(priv->counter, cpu); do { - seq = read_seqcount_begin(myseq); - bytes = this_cpu->bytes; - packets = this_cpu->packets; - } while (read_seqcount_retry(myseq, seq)); + seq = u64_stats_fetch_begin(nft_sync); + bytes = u64_stats_read(&this_cpu->bytes); + packets = u64_stats_read(&this_cpu->packets); + } while (u64_stats_fetch_retry(nft_sync, seq)); total->bytes += bytes; total->packets += packets; @@ -148,7 +152,7 @@ static int nft_counter_do_dump(struct sk_buff *skb, struct nft_counter_percpu_priv *priv, bool reset) { - struct nft_counter total; + struct nft_counter_tot total; nft_counter_fetch(priv, &total); @@ -236,7 +240,7 @@ static int nft_counter_clone(struct nft_expr *dst, const struct nft_expr *src, g struct nft_counter_percpu_priv *priv_clone = nft_expr_priv(dst); struct nft_counter __percpu *cpu_stats; struct nft_counter *this_cpu; - struct nft_counter total; + struct nft_counter_tot total; nft_counter_fetch(priv, &total); @@ -244,11 +248,9 @@ static int nft_counter_clone(struct nft_expr *dst, const struct nft_expr *src, g if (cpu_stats == NULL) return -ENOMEM; - preempt_disable(); - this_cpu = this_cpu_ptr(cpu_stats); - this_cpu->packets = total.packets; - this_cpu->bytes = total.bytes; - preempt_enable(); + this_cpu = raw_cpu_ptr(cpu_stats); + u64_stats_set(&this_cpu->packets, total.packets); + u64_stats_set(&this_cpu->bytes, total.bytes); priv_clone->counter = cpu_stats; return 0; @@ -266,17 +268,17 @@ static void nft_counter_offload_stats(struct nft_expr *expr, const struct flow_stats *stats) { struct nft_counter_percpu_priv *priv = nft_expr_priv(expr); + struct u64_stats_sync *nft_sync; struct nft_counter *this_cpu; - seqcount_t *myseq; local_bh_disable(); this_cpu = this_cpu_ptr(priv->counter); - myseq = this_cpu_ptr(&nft_counter_seq); + nft_sync = this_cpu_ptr(&nft_counter_sync); - write_seqcount_begin(myseq); - this_cpu->packets += stats->pkts; - this_cpu->bytes += stats->bytes; - write_seqcount_end(myseq); + u64_stats_update_begin(nft_sync); + u64_stats_add(&this_cpu->packets, stats->pkts); + u64_stats_add(&this_cpu->bytes, stats->bytes); + u64_stats_update_end(nft_sync); local_bh_enable(); } @@ -285,7 +287,7 @@ void nft_counter_init_seqcount(void) int cpu; for_each_possible_cpu(cpu) - seqcount_init(per_cpu_ptr(&nft_counter_seq, cpu)); + u64_stats_init(per_cpu_ptr(&nft_counter_sync, cpu)); } struct nft_expr_type nft_counter_type; -- 2.49.0

9 months, 4 weeks

[PATCH 6.6] wifi: iwlwifi: support BIOS override for 5G9 in CA also in LARI version 8

by Emmanuel Grumbach

From: Miri Korenblit <miriam.rachel.korenblit(a)intel.com> commit b1e8102a4048003097c7054cbc00bbda91a5ced7 upstream Commit 6b3e87cc0ca5 ("iwlwifi: Add support for LARI_CONFIG_CHANGE_CMD cmd v9") added a few bits to iwl_lari_config_change_cmd::oem_unii4_allow_bitmap if the FW has LARI version >= 9. But we also need to send those bits for version 8 if the FW is capable of this feature (indicated with capability bits) Add the FW capability bit, and set the additional bits in the cmd when the version is 8 and the FW capability bit is set. Signed-off-by: Miri Korenblit <miriam.rachel.korenblit(a)intel.com> Reviewed-by: Johannes Berg <johannes.berg(a)intel.com> Link: https://patch.msgid.link/20241226174257.dc5836f84514.I1e38f94465a36731034c9… Signed-off-by: Johannes Berg <johannes.berg(a)intel.com> Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach(a)intel.com> --- drivers/net/wireless/intel/iwlwifi/fw/file.h | 4 ++- drivers/net/wireless/intel/iwlwifi/mvm/fw.c | 37 ++++++++++++++++++-- 2 files changed, 38 insertions(+), 3 deletions(-) diff --git a/drivers/net/wireless/intel/iwlwifi/fw/file.h b/drivers/net/wireless/intel/iwlwifi/fw/file.h index b36e9613a52c..b1687e6d3ad2 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/file.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/file.h @@ -372,6 +372,8 @@ typedef unsigned int __bitwise iwl_ucode_tlv_capa_t; * channels even when these are not enabled. * @IWL_UCODE_TLV_CAPA_DUMP_COMPLETE_SUPPORT: Support for indicating dump collection * complete to FW. + * @IWL_UCODE_TLV_CAPA_BIOS_OVERRIDE_5G9_FOR_CA: supports (de)activating 5G9 + * for CA from BIOS. * * @NUM_IWL_UCODE_TLV_CAPA: number of bits used */ @@ -468,7 +470,7 @@ enum iwl_ucode_tlv_capa { IWL_UCODE_TLV_CAPA_OFFLOAD_BTM_SUPPORT = (__force iwl_ucode_tlv_capa_t)113, IWL_UCODE_TLV_CAPA_STA_EXP_MFP_SUPPORT = (__force iwl_ucode_tlv_capa_t)114, IWL_UCODE_TLV_CAPA_SNIFF_VALIDATE_SUPPORT = (__force iwl_ucode_tlv_capa_t)116, - + IWL_UCODE_TLV_CAPA_BIOS_OVERRIDE_5G9_FOR_CA = (__force iwl_ucode_tlv_capa_t)123, #ifdef __CHECKER__ /* sparse says it cannot increment the previous enum member */ #define NUM_IWL_UCODE_TLV_CAPA 128 diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c index 80b5c20d3a48..c597492668fa 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c @@ -1195,11 +1195,30 @@ static u8 iwl_mvm_eval_dsm_rfi(struct iwl_mvm *mvm) return DSM_VALUE_RFI_DISABLE; } +enum iwl_dsm_unii4_bitmap { + DSM_VALUE_UNII4_US_OVERRIDE_MSK = BIT(0), + DSM_VALUE_UNII4_US_EN_MSK = BIT(1), + DSM_VALUE_UNII4_ETSI_OVERRIDE_MSK = BIT(2), + DSM_VALUE_UNII4_ETSI_EN_MSK = BIT(3), + DSM_VALUE_UNII4_CANADA_OVERRIDE_MSK = BIT(4), + DSM_VALUE_UNII4_CANADA_EN_MSK = BIT(5), +}; + +#define DSM_UNII4_ALLOW_BITMAP (DSM_VALUE_UNII4_US_OVERRIDE_MSK |\ + DSM_VALUE_UNII4_US_EN_MSK |\ + DSM_VALUE_UNII4_ETSI_OVERRIDE_MSK |\ + DSM_VALUE_UNII4_ETSI_EN_MSK |\ + DSM_VALUE_UNII4_CANADA_OVERRIDE_MSK |\ + DSM_VALUE_UNII4_CANADA_EN_MSK) + static void iwl_mvm_lari_cfg(struct iwl_mvm *mvm) { int ret; u32 value; struct iwl_lari_config_change_cmd_v6 cmd = {}; + u8 cmd_ver = iwl_fw_lookup_cmd_ver(mvm->fw, + WIDE_ID(REGULATORY_AND_NVM_GROUP, + LARI_CONFIG_CHANGE), 1); cmd.config_bitmap = iwl_acpi_get_lari_config_bitmap(&mvm->fwrt); @@ -1211,8 +1230,22 @@ static void iwl_mvm_lari_cfg(struct iwl_mvm *mvm) ret = iwl_acpi_get_dsm_u32(mvm->fwrt.dev, 0, DSM_FUNC_ENABLE_UNII4_CHAN, &iwl_guid, &value); - if (!ret) - cmd.oem_unii4_allow_bitmap = cpu_to_le32(value); + if (!ret) { + u32 _value = cpu_to_le32(value); + + _value &= DSM_UNII4_ALLOW_BITMAP; + + /* Since version 9, bits 4 and 5 are supported + * regardless of this capability. + */ + if (cmd_ver < 9 && + !fw_has_capa(&mvm->fw->ucode_capa, + IWL_UCODE_TLV_CAPA_BIOS_OVERRIDE_5G9_FOR_CA)) + _value &= ~(DSM_VALUE_UNII4_CANADA_OVERRIDE_MSK | + DSM_VALUE_UNII4_CANADA_EN_MSK); + + cmd.oem_unii4_allow_bitmap = cpu_to_le32(_value); + } ret = iwl_acpi_get_dsm_u32(mvm->fwrt.dev, 0, DSM_FUNC_ACTIVATE_CHANNEL, -- 2.48.1

9 months, 4 weeks

[PATCH 5.10.y] wifi: ath10k: avoid NULL pointer error during sdio remove

by alvalan9＠foxmail.com

From: Kang Yang <quic_kangyang(a)quicinc.com> [ Upstream commit 95c38953cb1ecf40399a676a1f85dfe2b5780a9a ] When running 'rmmod ath10k', ath10k_sdio_remove() will free sdio workqueue by destroy_workqueue(). But if CONFIG_INIT_ON_FREE_DEFAULT_ON is set to yes, kernel panic will happen: Call trace: destroy_workqueue+0x1c/0x258 ath10k_sdio_remove+0x84/0x94 sdio_bus_remove+0x50/0x16c device_release_driver_internal+0x188/0x25c device_driver_detach+0x20/0x2c This is because during 'rmmod ath10k', ath10k_sdio_remove() will call ath10k_core_destroy() before destroy_workqueue(). wiphy_dev_release() will finally be called in ath10k_core_destroy(). This function will free struct cfg80211_registered_device *rdev and all its members, including wiphy, dev and the pointer of sdio workqueue. Then the pointer of sdio workqueue will be set to NULL due to CONFIG_INIT_ON_FREE_DEFAULT_ON. After device release, destroy_workqueue() will use NULL pointer then the kernel panic happen. Call trace: ath10k_sdio_remove ->ath10k_core_unregister …… ->ath10k_core_stop ->ath10k_hif_stop ->ath10k_sdio_irq_disable ->ath10k_hif_power_down ->del_timer_sync(&ar_sdio->sleep_timer) ->ath10k_core_destroy ->ath10k_mac_destroy ->ieee80211_free_hw ->wiphy_free …… ->wiphy_dev_release ->destroy_workqueue Need to call destroy_workqueue() before ath10k_core_destroy(), free the work queue buffer first and then free pointer of work queue by ath10k_core_destroy(). This order matches the error path order in ath10k_sdio_probe(). No work will be queued on sdio workqueue between it is destroyed and ath10k_core_destroy() is called. Based on the call_stack above, the reason is: Only ath10k_sdio_sleep_timer_handler(), ath10k_sdio_hif_tx_sg() and ath10k_sdio_irq_disable() will queue work on sdio workqueue. Sleep timer will be deleted before ath10k_core_destroy() in ath10k_hif_power_down(). ath10k_sdio_irq_disable() only be called in ath10k_hif_stop(). ath10k_core_unregister() will call ath10k_hif_power_down() to stop hif bus, so ath10k_sdio_hif_tx_sg() won't be called anymore. Tested-on: QCA6174 hw3.2 SDIO WLAN.RMH.4.4.1-00189 Signed-off-by: Kang Yang <quic_kangyang(a)quicinc.com> Tested-by: David Ruth <druth(a)chromium.org> Reviewed-by: David Ruth <druth(a)chromium.org> Link: https://patch.msgid.link/20241008022246.1010-1-quic_kangyang@quicinc.com Signed-off-by: Jeff Johnson <quic_jjohnson(a)quicinc.com> Signed-off-by: Alva Lan <alvalan9(a)foxmail.com> --- drivers/net/wireless/ath/ath10k/sdio.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/net/wireless/ath/ath10k/sdio.c b/drivers/net/wireless/ath/ath10k/sdio.c index 9d1b0890f310..418e40560f59 100644 --- a/drivers/net/wireless/ath/ath10k/sdio.c +++ b/drivers/net/wireless/ath/ath10k/sdio.c @@ -3,6 +3,7 @@ * Copyright (c) 2004-2011 Atheros Communications Inc. * Copyright (c) 2011-2012,2017 Qualcomm Atheros, Inc. * Copyright (c) 2016-2017 Erik Stromdahl <erik.stromdahl(a)gmail.com> + * Copyright (c) 2022-2024 Qualcomm Innovation Center, Inc. All rights reserved. */ #include <linux/module.h> @@ -2649,9 +2650,9 @@ static void ath10k_sdio_remove(struct sdio_func *func) netif_napi_del(&ar->napi); - ath10k_core_destroy(ar); - destroy_workqueue(ar_sdio->workqueue); + + ath10k_core_destroy(ar); } static const struct sdio_device_id ath10k_sdio_devices[] = { -- 2.34.1

9 months, 4 weeks

pm80xx driver crashes in a daisy-chained multipath JBOD configuration

by Jarl Gullberg

I'm having issues on kernel 6.12.12 and 6.13.7 with the pm80xx0 driver using a PMC/Sierra 8001 card pulled from a SUN/Oracle ZFS Storage Appliance. Specifically, the card does not appear to handle daisy-chained multipath configurations correctly, and either locks up at boot, crashes during runtime, or doesn't enumerate the disks in the JBODs correctly. My topology looks like the following: ┌─────────────┐ │ PM8001 │ │ ▒A ▒ │B └─║─────────║─┘ ║ ╚═════╗ ┌─║───────────┐ ║ │ ║ JBOD 1 │ ║ │ ║ │ ║ │ ▒ A ▒ │B ║ └─║─────────║─┘ ║ ┌─║─────────║─┐ ║ │ ║ JBOD 2 ║ │ ║ │ ║ ║ │ ║ │ ▒ A ▒ │B ║ └─║─────────║─┘ ║ ┌─║─────────║─┐ ║ │ ║ JBOD 3 ║ │ ║ │ ║ ║ │ ║ │ ▒ A ▒ │B ║ └───────────║─┘ ║ ║ ║ ╚═════╝ Each JBOD has two dual-ported controllers on it, allowing for multiple shelves to be chained together and the controlling server to be attached at each end. The same topology works with an LSI/Broadcom card. The problem can be divided into three separate instances: 1 - failure to boot The driver crashes outright on boot when enumerating disks. Kernel logs from 6.13.7: https://gist.github.com/Nihlus/8b390a56ce743a85ff7aaf7b38cb501a [ 15.261604] kernel BUG at drivers/scsi/libsas/sas_scsi_host.c:378! [ 15.335390] Oops: invalid opcode: 0000 [#1] PREEMPT SMP PTI [ 15.402050] CPU: 0 UID: 0 PID: 374 Comm: kworker/0:2 Tainted: G W 6.13-amd64 #1 Debian 6.13.7-1~exp1 [ 15.528840] Tainted: [W]=WARN [ 15.564215] Hardware name: SUN MICROSYSTEMS SUN FIRE X4170 M2 SERVER /ASSY,MOTHERBOARD,X4170, BIOS 08060108 12/27/2010 [ 15.698278] Workqueue: pm80xx pm8001_work_fn [pm80xx] [ 15.758607] RIP: 0010:sas_get_local_phy+0x57/0x60 [libsas] [ 15.824126] Code: 9f 2f 86 e0 48 8b 5b 38 49 89 c4 48 89 df e8 e0 29 4c e0 4c 89 e6 48 89 ef e8 45 30 86 e0 48 89 d8 5b 5d 41 5c c3 cc cc cc cc <0f> 0b 90 66 0f 1f 44 00 00 90 90 90 90 90 90 90 90 90 90 90 90 90 [ 16.048618] RSP: 0018:ffffaa888e017db0 EFLAGS: 00010246 [ 16.111024] RAX: ffff8fe450766408 RBX: ffff8fe4515e3c00 RCX: 0000000000000002 [ 16.196288] RDX: 0000000000000000 RSI: 0000000000400000 RDI: ffff8fe4515e3c00 [ 16.281552] RBP: ffff8ff5ca075c00 R08: ffff8ff5ca0758c0 R09: 0000000000000014 [ 16.366815] R10: 0000000000000004 R11: 0000000000000000 R12: ffff8ff577835200 [ 16.452077] R13: ffff8fe450760000 R14: ffff8fe450780e40 R15: 0000000000000000 [ 16.537342] FS: 0000000000000000(0000) GS:ffff8ff577800000(0000) knlGS:0000000000000000 [ 16.634063] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 16.702706] CR2: 00007fa7f2f58273 CR3: 000000035c022003 CR4: 00000000000206f0 [ 16.787969] Call Trace: [ 16.817136] <TASK> [ 16.842151] ? __die_body.cold+0x19/0x27 [ 16.888981] ? die+0x2e/0x50 [ 16.923345] ? do_trap+0xca/0x110 [ 16.962909] ? do_error_trap+0x6a/0x90 [ 17.007658] ? sas_get_local_phy+0x57/0x60 [libsas] [ 17.065922] ? exc_invalid_op+0x50/0x70 [ 17.111710] ? sas_get_local_phy+0x57/0x60 [libsas] [ 17.169970] ? asm_exc_invalid_op+0x1a/0x20 [ 17.219921] ? sas_get_local_phy+0x57/0x60 [libsas] [ 17.278184] pm8001_I_T_nexus_event_handler+0x69/0x1a0 [pm80xx] [ 17.348911] ? psi_task_switch+0xb7/0x200 [ 17.396779] ? finish_task_switch.isra.0+0x97/0x2c0 [ 17.455033] pm8001_work_fn+0x6b/0x4e0 [pm80xx] [ 17.509144] ? __schedule+0x50d/0xbf0 [ 17.552856] process_one_work+0x177/0x330 [ 17.600721] worker_thread+0x251/0x390 [ 17.645468] ? __pfx_worker_thread+0x10/0x10 [ 17.696455] kthread+0xd2/0x100 [ 17.733933] ? __pfx_kthread+0x10/0x10 [ 17.778683] ret_from_fork+0x34/0x50 [ 17.821360] ? __pfx_kthread+0x10/0x10 [ 17.866107] ret_from_fork_asm+0x1a/0x30 [ 17.912942] </TASK> [ 17.938987] Modules linked in: usbhid mii hid usb_storage pm80xx ahci libsas libahci scsi_transport_sas ixgbe uhci_hcd ehci_pci libata ehci_hcd xfrm_algo igb mdio_devres usbcore scsi_mod crc32_pclmul libphy e1000e crc32c_intel i2c_i801 i2c_algo_bit i2c_smbus usb_common lpc_ich dca scsi_common mdio [ 18.253949] clocksource: Long readout interval, skipping watchdog check: cs_nsec: 1981286504 wd_nsec: 1981285958 [ 18.375615] ---[ end trace 0000000000000000 ]--- 2 - runtime crash This happens if the cables are reseated or the JBODs restarted after the device has successfully booted, usually by leaving the cables unplugged. The disk enumeration fails to complete, leading to a call trace in the kernel logs and typically causes the JBOD controllers to get stuck in an unhealthy state (see case 3). Full kernel logs for 6.12.12 are available at https://gist.github.com/Nihlus/cbbabe685de551afa2cc8cdfbc6be6b2 with the relevant part being [ 415.245390] port-0:2:32: trying to add phy phy-0:2:32 fails: it's already part of another port [ 415.245473] ------------[ cut here ]------------ [ 415.245475] kernel BUG at drivers/scsi/scsi_transport_sas.c:1111! [ 415.245483] Oops: invalid opcode: 0000 [#1] PREEMPT SMP PTI [ 415.245487] CPU: 0 UID: 0 PID: 11 Comm: kworker/u96:0 Tainted: G W 6.12.12+bpo-amd64 #1 Debian 6.12.12-1~bpo12+1 [ 415.245492] Tainted: [W]=WARN [ 415.245493] Hardware name: SUN MICROSYSTEMS SUN FIRE X4170 M2 SERVER /ASSY,MOTHERBOARD,X4170, BIOS 08060108 12/27/2010 [ 415.245495] Workqueue: 0000:19:00.0_disco_q sas_revalidate_domain [libsas] [ 415.245522] RIP: 0010:sas_port_add_phy+0x143/0x150 [scsi_transport_sas] [ 415.245539] Code: d5 75 e8 48 39 c3 74 8e 48 8b 4b 50 48 85 c9 75 03 48 8b 0b 48 c7 c2 80 c5 46 c0 48 89 ee 48 c7 c7 ae c6 46 c0 e8 5d 32 ce c9 <0f> 0b 66 66 2e 0f 1f 84 00 00 00 00 00 90 90 90 90 90 90 90 90 90 [ 415.245542] RSP: 0018:ffffb595400d3c80 EFLAGS: 00010246 [ 415.245544] RAX: 0000000000000000 RBX: ffff905c9651d800 RCX: 0000000000000027 [ 415.245546] RDX: 0000000000000000 RSI: 0000000000000001 RDI: ffff906db7821780 [ 415.245547] RBP: ffff905c96eb4400 R08: 0000000000000000 R09: 0000000000000003 [ 415.245549] R10: ffffb595400d3978 R11: ffff907ffff7ab28 R12: ffff905c9651db38 [ 415.245550] R13: ffff905c96eb4720 R14: ffff905c96eb4700 R15: ffff905c8809a800 [ 415.245552] FS: 0000000000000000(0000) GS:ffff906db7800000(0000) knlGS:0000000000000000 [ 415.245554] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 415.245556] CR2: 0000557484600000 CR3: 00000002f2622002 CR4: 00000000000226f0 [ 415.245558] Call Trace: [ 415.245562] <TASK> [ 415.245565] ? die+0x36/0x90 [ 415.245572] ? do_trap+0xdd/0x100 [ 415.245576] ? sas_port_add_phy+0x143/0x150 [scsi_transport_sas] [ 415.245583] ? do_error_trap+0x6a/0x90 [ 415.245585] ? sas_port_add_phy+0x143/0x150 [scsi_transport_sas] [ 415.245592] ? exc_invalid_op+0x50/0x70 [ 415.245597] ? sas_port_add_phy+0x143/0x150 [scsi_transport_sas] [ 415.245603] ? asm_exc_invalid_op+0x1a/0x20 [ 415.245613] ? sas_port_add_phy+0x143/0x150 [scsi_transport_sas] [ 415.245620] sas_ex_get_linkrate+0x9b/0xd0 [libsas] [ 415.245631] sas_ex_discover_devices+0x38f/0xc20 [libsas] [ 415.245644] sas_discover_new+0x71/0x110 [libsas] [ 415.245655] sas_ex_revalidate_domain+0x337/0x430 [libsas] [ 415.245667] sas_revalidate_domain+0x189/0x1a0 [libsas] [ 415.245678] process_one_work+0x17c/0x390 [ 415.245685] worker_thread+0x251/0x360 [ 415.245689] ? __pfx_worker_thread+0x10/0x10 [ 415.245692] kthread+0xd2/0x100 [ 415.245695] ? __pfx_kthread+0x10/0x10 [ 415.245698] ret_from_fork+0x34/0x50 [ 415.245702] ? __pfx_kthread+0x10/0x10 [ 415.245704] ret_from_fork_asm+0x1a/0x30 [ 415.245711] </TASK> [ 415.245712] Modules linked in: binfmt_misc intel_powerclamp coretemp kvm_intel kvm joydev evdev crct10dif_pclmul ghash_clmulni_intel sha512_ssse3 sha256_ssse3 sha1_ssse3 aesni_intel gf128mul crypto_simd cryptd intel_cstate ipmi_ssif ast drm_shmem_helper drm_kms_helper iTCO_wdt intel_pmc_bxt intel_uncore iTCO_vendor_support acpi_ipmi watchdog pcspkr sg i5500_temp ioatdma acpi_cpufreq i7core_edac ipmi_si ipmi_devintf ipmi_msghandler button dm_multipath drm loop efi_pstore configfs ip_tables x_tables autofs4 ext4 crc16 mbcache jbd2 efivarfs raid10 raid456 async_raid6_recov async_memcpy async_pq async_xor async_tx xor raid6_pq libcrc32c crc32c_generic raid0 dm_mod raid1 md_mod ses enclosure sd_mod hid_generic cdc_ether usbnet uas usbhid mii hid usb_storage pm80xx libsas ahci libahci scsi_transport_sas ixgbe libata uhci_hcd ehci_pci ehci_hcd xfrm_algo usbcore mdio_devres igb scsi_mod e1000e libphy crc32_pclmul crc32c_intel i2c_i801 lpc_ich i2c_smbus i2c_algo_bit usb_common scsi_common mdio dca [ 415.245777] ---[ end trace 0000000000000000 ]--- [ 415.245778] RIP: 0010:sas_port_add_phy+0x143/0x150 [scsi_transport_sas] [ 415.245785] Code: d5 75 e8 48 39 c3 74 8e 48 8b 4b 50 48 85 c9 75 03 48 8b 0b 48 c7 c2 80 c5 46 c0 48 89 ee 48 c7 c7 ae c6 46 c0 e8 5d 32 ce c9 <0f> 0b 66 66 2e 0f 1f 84 00 00 00 00 00 90 90 90 90 90 90 90 90 90 [ 415.245788] RSP: 0018:ffffb595400d3c80 EFLAGS: 00010246 [ 415.245790] RAX: 0000000000000000 RBX: ffff905c9651d800 RCX: 0000000000000027 [ 415.245791] RDX: 0000000000000000 RSI: 0000000000000001 RDI: ffff906db7821780 [ 415.245793] RBP: ffff905c96eb4400 R08: 0000000000000000 R09: 0000000000000003 [ 415.245794] R10: ffffb595400d3978 R11: ffff907ffff7ab28 R12: ffff905c9651db38 [ 415.245796] R13: ffff905c96eb4720 R14: ffff905c96eb4700 R15: ffff905c8809a800 [ 415.245797] FS: 0000000000000000(0000) GS:ffff906db7800000(0000) knlGS:0000000000000000 [ 415.245800] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 415.245801] CR2: 0000557484600000 CR3: 00000002f2622002 CR4: 00000000000226f0 [ 415.388491] pm80xx0:: mpi_ssp_completion 1752: status:0x3, tag:0x29b, task:0x00000000bc0fdffa 3 - incorrect enumeration In this case, only disks from JBOD 1 and 2 are enumerated. The device boots correctly, but the controllers on the JBODs are in an unhealty state and are not forwarding traffic as expected (link LED on A1 to A2 is dark, link LED on B2 to B3 is dark). System information: Linux san1 6.12.12+bpo-amd64 #1 SMP PREEMPT_DYNAMIC Debian 6.12.12-1~bpo12+1 (2025-02-23) x86_64 GNU/Linux Kernel config for 6.12.12: https://gist.github.com/Nihlus/33ab520b37270ab2d92d2ec26ddfa730 Kernel config for 6.13.7: https://gist.github.com/Nihlus/8d1af8204b0e4c456aeb30d079659712

9 months, 4 weeks

Clarifying stable kernel rule on selftest backporting

by Shung-Hsi Yu

Hi, Do we have any rule regarding whether a patch that adds a new test case in tools/testing/selftests/ can be considered for backport? For example, consider commit 0a5d2efa3827 ("selftests/bpf: Add test case for the freeing of bpf_timer"), it adds a test case for the issue addressed in the same series -- commit 58f038e6d209 ("bpf: Cancel the running bpf_timer through kworker for PREEMPT_RT"). The latter has been backported to 6.12.y. Would commit 0a5d2efa3827 be a worthwhile add to 6.12.y as well? IMO having such test case added would be helpful to check whether the backported fix really works (assuming someone is willing to do the extra work of finding, testing, and sending such tests); yet it does not seem to fit into the current stable kernel rule set of: - It or an equivalent fix must already exist in Linux mainline (upstream). - It must be obviously correct and tested. - It cannot be bigger than 100 lines, with context. - It must follow the Documentation/process/submitting-patches.rst rules. - It must either fix a real bug that bothers people or just add a device ID Appreciate any clarification and/or feedback on this matter. Thanks, Shung-Hsi Yu

9 months, 4 weeks

[PATCH net 1/1] batman-adv: Ignore own maximum aggregation size during RX

by Simon Wunderlich

From: Sven Eckelmann <sven(a)narfation.org> An OGMv1 and OGMv2 packet receive processing were not only limited by the number of bytes in the received packet but also by the nodes maximum aggregation packet size limit. But this limit is relevant for TX and not for RX. It must not be enforced by batadv_(i)v_ogm_aggr_packet to avoid loss of information in case of a different limit for sender and receiver. This has a minor side effect for B.A.T.M.A.N. IV because the batadv_iv_ogm_aggr_packet is also used for the preprocessing for the TX. But since the aggregation code itself will not allow more than BATADV_MAX_AGGREGATION_BYTES bytes, this check was never triggering (in this context) prior of removing it. Cc: stable(a)vger.kernel.org Fixes: c6c8fea29769 ("net: Add batman-adv meshing protocol") Fixes: 9323158ef9f4 ("batman-adv: OGMv2 - implement originators logic") Signed-off-by: Sven Eckelmann <sven(a)narfation.org> Signed-off-by: Simon Wunderlich <sw(a)simonwunderlich.de> --- net/batman-adv/bat_iv_ogm.c | 3 +-- net/batman-adv/bat_v_ogm.c | 3 +-- 2 files changed, 2 insertions(+), 4 deletions(-) diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index 07ae5dd1f150..b12645949ae5 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -325,8 +325,7 @@ batadv_iv_ogm_aggr_packet(int buff_pos, int packet_len, /* check if there is enough space for the optional TVLV */ next_buff_pos += ntohs(ogm_packet->tvlv_len); - return (next_buff_pos <= packet_len) && - (next_buff_pos <= BATADV_MAX_AGGREGATION_BYTES); + return next_buff_pos <= packet_len; } /* send a batman ogm to a given interface */ diff --git a/net/batman-adv/bat_v_ogm.c b/net/batman-adv/bat_v_ogm.c index e503ee0d896b..8f89ffe6020c 100644 --- a/net/batman-adv/bat_v_ogm.c +++ b/net/batman-adv/bat_v_ogm.c @@ -839,8 +839,7 @@ batadv_v_ogm_aggr_packet(int buff_pos, int packet_len, /* check if there is enough space for the optional TVLV */ next_buff_pos += ntohs(ogm2_packet->tvlv_len); - return (next_buff_pos <= packet_len) && - (next_buff_pos <= BATADV_MAX_AGGREGATION_BYTES); + return next_buff_pos <= packet_len; } /** -- 2.39.5

9 months, 4 weeks

Re: [PATCH net 0/3] mptcp: fix data stream corruption and missing sockopts

by patchwork-bot+netdevbpf＠kernel.org

Hello: This series was applied to netdev/net.git (main) by Paolo Abeni <pabeni(a)redhat.com>: On Fri, 14 Mar 2025 21:11:30 +0100 you wrote: > Here are 3 unrelated fixes for the net tree. > > - Patch 1: fix data stream corruption when ending up not sending an > ADD_ADDR. > > - Patch 2: fix missing getsockopt(IPV6_V6ONLY) support -- the set part > is supported. > > [...] Here is the summary with links: - [net,1/3] mptcp: Fix data stream corruption in the address announcement https://git.kernel.org/netdev/net/c/2c1f97a52cb8 - [net,2/3] mptcp: sockopt: fix getting IPV6_V6ONLY (no matching commit) - [net,3/3] mptcp: sockopt: fix getting freebind & transparent (no matching commit) You are awesome, thank you! -- Deet-doot-dot, I am a bot. https://korg.docs.kernel.org/patchwork/pwbot.html

9 months, 4 weeks

[PATCH 5.10.y] tcp/dccp: Don't use timer_pending() in reqsk_queue_unlink().

by bin.lan.cn＠windriver.com

From: Kuniyuki Iwashima <kuniyu(a)amazon.com> [ Upstream commit e8c526f2bdf1845bedaf6a478816a3d06fa78b8f ] Martin KaFai Lau reported use-after-free [0] in reqsk_timer_handler(). """ We are seeing a use-after-free from a bpf prog attached to trace_tcp_retransmit_synack. The program passes the req->sk to the bpf_sk_storage_get_tracing kernel helper which does check for null before using it. """ The commit 83fccfc3940c ("inet: fix potential deadlock in reqsk_queue_unlink()") added timer_pending() in reqsk_queue_unlink() not to call del_timer_sync() from reqsk_timer_handler(), but it introduced a small race window. Before the timer is called, expire_timers() calls detach_timer(timer, true) to clear timer->entry.pprev and marks it as not pending. If reqsk_queue_unlink() checks timer_pending() just after expire_timers() calls detach_timer(), TCP will miss del_timer_sync(); the reqsk timer will continue running and send multiple SYN+ACKs until it expires. The reported UAF could happen if req->sk is close()d earlier than the timer expiration, which is 63s by default. The scenario would be 1. inet_csk_complete_hashdance() calls inet_csk_reqsk_queue_drop(), but del_timer_sync() is missed 2. reqsk timer is executed and scheduled again 3. req->sk is accept()ed and reqsk_put() decrements rsk_refcnt, but reqsk timer still has another one, and inet_csk_accept() does not clear req->sk for non-TFO sockets 4. sk is close()d 5. reqsk timer is executed again, and BPF touches req->sk Let's not use timer_pending() by passing the caller context to __inet_csk_reqsk_queue_drop(). Note that reqsk timer is pinned, so the issue does not happen in most use cases. [1] [0] BUG: KFENCE: use-after-free read in bpf_sk_storage_get_tracing+0x2e/0x1b0 Use-after-free read at 0x00000000a891fb3a (in kfence-#1): bpf_sk_storage_get_tracing+0x2e/0x1b0 bpf_prog_5ea3e95db6da0438_tcp_retransmit_synack+0x1d20/0x1dda bpf_trace_run2+0x4c/0xc0 tcp_rtx_synack+0xf9/0x100 reqsk_timer_handler+0xda/0x3d0 run_timer_softirq+0x292/0x8a0 irq_exit_rcu+0xf5/0x320 sysvec_apic_timer_interrupt+0x6d/0x80 asm_sysvec_apic_timer_interrupt+0x16/0x20 intel_idle_irq+0x5a/0xa0 cpuidle_enter_state+0x94/0x273 cpu_startup_entry+0x15e/0x260 start_secondary+0x8a/0x90 secondary_startup_64_no_verify+0xfa/0xfb kfence-#1: 0x00000000a72cc7b6-0x00000000d97616d9, size=2376, cache=TCPv6 allocated by task 0 on cpu 9 at 260507.901592s: sk_prot_alloc+0x35/0x140 sk_clone_lock+0x1f/0x3f0 inet_csk_clone_lock+0x15/0x160 tcp_create_openreq_child+0x1f/0x410 tcp_v6_syn_recv_sock+0x1da/0x700 tcp_check_req+0x1fb/0x510 tcp_v6_rcv+0x98b/0x1420 ipv6_list_rcv+0x2258/0x26e0 napi_complete_done+0x5b1/0x2990 mlx5e_napi_poll+0x2ae/0x8d0 net_rx_action+0x13e/0x590 irq_exit_rcu+0xf5/0x320 common_interrupt+0x80/0x90 asm_common_interrupt+0x22/0x40 cpuidle_enter_state+0xfb/0x273 cpu_startup_entry+0x15e/0x260 start_secondary+0x8a/0x90 secondary_startup_64_no_verify+0xfa/0xfb freed by task 0 on cpu 9 at 260507.927527s: rcu_core_si+0x4ff/0xf10 irq_exit_rcu+0xf5/0x320 sysvec_apic_timer_interrupt+0x6d/0x80 asm_sysvec_apic_timer_interrupt+0x16/0x20 cpuidle_enter_state+0xfb/0x273 cpu_startup_entry+0x15e/0x260 start_secondary+0x8a/0x90 secondary_startup_64_no_verify+0xfa/0xfb Fixes: 83fccfc3940c ("inet: fix potential deadlock in reqsk_queue_unlink()") Reported-by: Martin KaFai Lau <martin.lau(a)kernel.org> Closes: https://lore.kernel.org/netdev/eb6684d0-ffd9-4bdc-9196-33f690c25824@linux.d… Link: https://lore.kernel.org/netdev/b55e2ca0-42f2-4b7c-b445-6ffd87ca74a0@linux.d… [1] Signed-off-by: Kuniyuki Iwashima <kuniyu(a)amazon.com> Reviewed-by: Eric Dumazet <edumazet(a)google.com> Reviewed-by: Martin KaFai Lau <martin.lau(a)kernel.org> Link: https://patch.msgid.link/20241014223312.4254-1-kuniyu@amazon.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Bin Lan <bin.lan.cn(a)windriver.com> Signed-off-by: He Zhe <zhe.he(a)windriver.com> --- Build test passed. --- net/ipv4/inet_connection_sock.c | 19 +++++++++++++++---- 1 file changed, 15 insertions(+), 4 deletions(-) diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 6ebe43b4d28f..723aab818b52 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -722,21 +722,31 @@ static bool reqsk_queue_unlink(struct request_sock *req) found = __sk_nulls_del_node_init_rcu(req_to_sk(req)); spin_unlock(lock); } - if (timer_pending(&req->rsk_timer) && del_timer_sync(&req->rsk_timer)) - reqsk_put(req); + return found; } -bool inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req) +static bool __inet_csk_reqsk_queue_drop(struct sock *sk, + struct request_sock *req, + bool from_timer) { bool unlinked = reqsk_queue_unlink(req); + if (!from_timer && timer_delete_sync(&req->rsk_timer)) + reqsk_put(req); + if (unlinked) { reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req); reqsk_put(req); } + return unlinked; } + +bool inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req) +{ + return __inet_csk_reqsk_queue_drop(sk, req, false); +} EXPORT_SYMBOL(inet_csk_reqsk_queue_drop); void inet_csk_reqsk_queue_drop_and_put(struct sock *sk, struct request_sock *req) @@ -804,7 +814,8 @@ static void reqsk_timer_handler(struct timer_list *t) return; } drop: - inet_csk_reqsk_queue_drop_and_put(sk_listener, req); + __inet_csk_reqsk_queue_drop(sk_listener, req, true); + reqsk_put(req); } static void reqsk_queue_hash_req(struct request_sock *req, -- 2.34.1

9 months, 4 weeks

Re: [PATCH] block: cleanup and fix batch completion adding conditions

by Sasha Levin

[ Sasha's backport helper bot ] Hi, Summary of potential issues: ⚠️ Found matching upstream commit but patch is missing proper reference to it ⚠️ Found follow-up fixes in mainline Found matching upstream commit: 1f47ed294a2bd577d5ae43e6e28e1c9a3be4a833 Found fixes commits: 9bce6b5f8987 block: change blk_mq_add_to_batch() third argument type to bool e5c2bcc0cd47 nvme: move error logging from nvme_end_req() to __nvme_end_req() Note: The patch differs from the upstream commit: --- 1: 1f47ed294a2bd < -: ------------- block: cleanup and fix batch completion adding conditions -: ------------- > 1: 648e04a805652 Linux 6.13.7 --- Results of testing on various branches: | Branch | Patch Apply | Build Test | |---------------------------|-------------|------------| | stable/linux-6.13.y | Success | Success | | stable/linux-6.12.y | Success | Success | | stable/linux-6.6.y | Success | Success | | stable/linux-6.1.y | Success | Success | | stable/linux-5.15.y | Success | Success | | stable/linux-5.10.y | Success | Success | | stable/linux-5.4.y | Success | Success |

9 months, 4 weeks

Jump to page:

2026

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror