From 8fdd60f2ae3682caf2a7258626abc21eb4711892 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Thu, 31 Jan 2019 23:41:11 -0500 Subject: Revert "ext4: use ext4_write_inode() when fsyncing w/o a journal" This reverts commit ad211f3e94b314a910d4af03178a0b52a7d1ee0a. As Jan Kara pointed out, this change was unsafe since it means we lose the call to sync_mapping_buffers() in the nojournal case. The original point of the commit was avoid taking the inode mutex (since it causes a lockdep warning in generic/113); but we need the mutex in order to call sync_mapping_buffers(). The real fix to this problem was discussed here: https://lore.kernel.org/lkml/20181025150540.259281-4-bvanassche@acm.org The proposed patch was to fix a syzbot complaint, but the problem can also demonstrated via "kvm-xfstests -c nojournal generic/113". Multiple solutions were discused in the e-mail thread, but none have landed in the kernel as of this writing. Anyway, commit ad211f3e94b314 is absolutely the wrong way to suppress the lockdep, so revert it. Fixes: ad211f3e94b314a910d4af03178a0b52a7d1ee0a ("ext4: use ext4_write_inode() when fsyncing w/o a journal") Signed-off-by: Theodore Ts'o Reported: Jan Kara --- fs/ext4/fsync.c | 13 ++++--------- 1 file changed, 4 insertions(+), 9 deletions(-) (limited to 'fs') diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c index 712f00995390..5508baa11bb6 100644 --- a/fs/ext4/fsync.c +++ b/fs/ext4/fsync.c @@ -116,16 +116,8 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync) goto out; } - ret = file_write_and_wait_range(file, start, end); - if (ret) - return ret; - if (!journal) { - struct writeback_control wbc = { - .sync_mode = WB_SYNC_ALL - }; - - ret = ext4_write_inode(inode, &wbc); + ret = __generic_file_fsync(file, start, end, datasync); if (!ret) ret = ext4_sync_parent(inode); if (test_opt(inode->i_sb, BARRIER)) @@ -133,6 +125,9 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync) goto out; } + ret = file_write_and_wait_range(file, start, end); + if (ret) + return ret; /* * data=writeback,ordered: * The caller's filemap_fdatawrite()/wait will sync the data. -- cgit v1.2.3 From ec51f8ee1e63498e9f521ec0e5a6d04622bb2c67 Mon Sep 17 00:00:00 2001 From: Mike Marshall Date: Tue, 5 Feb 2019 14:13:35 -0500 Subject: aio: initialize kiocb private in case any filesystems expect it. A recent optimization had left private uninitialized. Fixes: 2bc4ca9bb600 ("aio: don't zero entire aio_kiocb aio_get_req()") Reviewed-by: Christoph Hellwig Signed-off-by: Mike Marshall Signed-off-by: Jens Axboe --- fs/aio.c | 1 + 1 file changed, 1 insertion(+) (limited to 'fs') diff --git a/fs/aio.c b/fs/aio.c index b906ff70c90f..aaaaf4d12c73 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -1436,6 +1436,7 @@ static int aio_prep_rw(struct kiocb *req, const struct iocb *iocb) if (unlikely(!req->ki_filp)) return -EBADF; req->ki_complete = aio_complete_rw; + req->private = NULL; req->ki_pos = iocb->aio_offset; req->ki_flags = iocb_flags(req->ki_filp); if (iocb->aio_flags & IOCB_FLAG_RESFD) -- cgit v1.2.3 From 43636c804df0126da669c261fc820fb22f62bfc2 Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Mon, 21 Jan 2019 22:49:37 +0900 Subject: fs: ratelimit __find_get_block_slow() failure message. When something let __find_get_block_slow() hit all_mapped path, it calls printk() for 100+ times per a second. But there is no need to print same message with such high frequency; it is just asking for stall warning, or at least bloating log files. [ 399.866302][T15342] __find_get_block_slow() failed. block=1, b_blocknr=8 [ 399.873324][T15342] b_state=0x00000029, b_size=512 [ 399.878403][T15342] device loop0 blocksize: 4096 [ 399.883296][T15342] __find_get_block_slow() failed. block=1, b_blocknr=8 [ 399.890400][T15342] b_state=0x00000029, b_size=512 [ 399.895595][T15342] device loop0 blocksize: 4096 [ 399.900556][T15342] __find_get_block_slow() failed. block=1, b_blocknr=8 [ 399.907471][T15342] b_state=0x00000029, b_size=512 [ 399.912506][T15342] device loop0 blocksize: 4096 This patch reduces frequency to up to once per a second, in addition to concatenating three lines into one. [ 399.866302][T15342] __find_get_block_slow() failed. block=1, b_blocknr=8, b_state=0x00000029, b_size=512, device loop0 blocksize: 4096 Signed-off-by: Tetsuo Handa Reviewed-by: Jan Kara Cc: Dmitry Vyukov Signed-off-by: Jens Axboe --- fs/buffer.c | 19 ++++++++++--------- 1 file changed, 10 insertions(+), 9 deletions(-) (limited to 'fs') diff --git a/fs/buffer.c b/fs/buffer.c index 52d024bfdbc1..48318fb74938 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -200,6 +200,7 @@ __find_get_block_slow(struct block_device *bdev, sector_t block) struct buffer_head *head; struct page *page; int all_mapped = 1; + static DEFINE_RATELIMIT_STATE(last_warned, HZ, 1); index = block >> (PAGE_SHIFT - bd_inode->i_blkbits); page = find_get_page_flags(bd_mapping, index, FGP_ACCESSED); @@ -227,15 +228,15 @@ __find_get_block_slow(struct block_device *bdev, sector_t block) * file io on the block device and getblk. It gets dealt with * elsewhere, don't buffer_error if we had some unmapped buffers */ - if (all_mapped) { - printk("__find_get_block_slow() failed. " - "block=%llu, b_blocknr=%llu\n", - (unsigned long long)block, - (unsigned long long)bh->b_blocknr); - printk("b_state=0x%08lx, b_size=%zu\n", - bh->b_state, bh->b_size); - printk("device %pg blocksize: %d\n", bdev, - 1 << bd_inode->i_blkbits); + ratelimit_set_flags(&last_warned, RATELIMIT_MSG_ON_RELEASE); + if (all_mapped && __ratelimit(&last_warned)) { + printk("__find_get_block_slow() failed. block=%llu, " + "b_blocknr=%llu, b_state=0x%08lx, b_size=%zu, " + "device %pg blocksize: %d\n", + (unsigned long long)block, + (unsigned long long)bh->b_blocknr, + bh->b_state, bh->b_size, bdev, + 1 << bd_inode->i_blkbits); } out_unlock: spin_unlock(&bd_mapping->private_lock); -- cgit v1.2.3 From 69056ee6a8a3d576ed31e38b3b14c70d6c74edcc Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Tue, 12 Feb 2019 15:35:51 -0800 Subject: Revert "mm: don't reclaim inodes with many attached pages" This reverts commit a76cf1a474d7d ("mm: don't reclaim inodes with many attached pages"). This change causes serious changes to page cache and inode cache behaviour and balance, resulting in major performance regressions when combining worklaods such as large file copies and kernel compiles. https://bugzilla.kernel.org/show_bug.cgi?id=202441 This change is a hack to work around the problems introduced by changing how agressive shrinkers are on small caches in commit 172b06c32b94 ("mm: slowly shrink slabs with a relatively small number of objects"). It creates more problems than it solves, wasn't adequately reviewed or tested, so it needs to be reverted. Link: http://lkml.kernel.org/r/20190130041707.27750-2-david@fromorbit.com Fixes: a76cf1a474d7d ("mm: don't reclaim inodes with many attached pages") Signed-off-by: Dave Chinner Cc: Wolfgang Walter Cc: Roman Gushchin Cc: Spock Cc: Rik van Riel Cc: Michal Hocko Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/inode.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'fs') diff --git a/fs/inode.c b/fs/inode.c index 0cd47fe0dbe5..73432e64f874 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -730,11 +730,8 @@ static enum lru_status inode_lru_isolate(struct list_head *item, return LRU_REMOVED; } - /* - * Recently referenced inodes and inodes with many attached pages - * get one more pass. - */ - if (inode->i_state & I_REFERENCED || inode->i_data.nrpages > 1) { + /* recently referenced inodes get one more pass */ + if (inode->i_state & I_REFERENCED) { inode->i_state &= ~I_REFERENCED; spin_unlock(&inode->i_lock); return LRU_ROTATE; -- cgit v1.2.3 From 27dd768ed8db48beefc4d9e006c58e7a00342bde Mon Sep 17 00:00:00 2001 From: Sandeep Patil Date: Tue, 12 Feb 2019 15:36:11 -0800 Subject: mm: proc: smaps_rollup: fix pss_locked calculation The 'pss_locked' field of smaps_rollup was being calculated incorrectly. It accumulated the current pss everytime a locked VMA was found. Fix that by adding to 'pss_locked' the same time as that of 'pss' if the vma being walked is locked. Link: http://lkml.kernel.org/r/20190203065425.14650-1-sspatil@android.com Fixes: 493b0e9d945f ("mm: add /proc/pid/smaps_rollup") Signed-off-by: Sandeep Patil Acked-by: Vlastimil Babka Reviewed-by: Joel Fernandes (Google) Cc: Alexey Dobriyan Cc: Daniel Colascione Cc: [4.14.x, 4.19.x] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/task_mmu.c | 22 ++++++++++++++-------- 1 file changed, 14 insertions(+), 8 deletions(-) (limited to 'fs') diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index f0ec9edab2f3..85b0ef890b28 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -423,7 +423,7 @@ struct mem_size_stats { }; static void smaps_account(struct mem_size_stats *mss, struct page *page, - bool compound, bool young, bool dirty) + bool compound, bool young, bool dirty, bool locked) { int i, nr = compound ? 1 << compound_order(page) : 1; unsigned long size = nr * PAGE_SIZE; @@ -450,24 +450,31 @@ static void smaps_account(struct mem_size_stats *mss, struct page *page, else mss->private_clean += size; mss->pss += (u64)size << PSS_SHIFT; + if (locked) + mss->pss_locked += (u64)size << PSS_SHIFT; return; } for (i = 0; i < nr; i++, page++) { int mapcount = page_mapcount(page); + unsigned long pss = (PAGE_SIZE << PSS_SHIFT); if (mapcount >= 2) { if (dirty || PageDirty(page)) mss->shared_dirty += PAGE_SIZE; else mss->shared_clean += PAGE_SIZE; - mss->pss += (PAGE_SIZE << PSS_SHIFT) / mapcount; + mss->pss += pss / mapcount; + if (locked) + mss->pss_locked += pss / mapcount; } else { if (dirty || PageDirty(page)) mss->private_dirty += PAGE_SIZE; else mss->private_clean += PAGE_SIZE; - mss->pss += PAGE_SIZE << PSS_SHIFT; + mss->pss += pss; + if (locked) + mss->pss_locked += pss; } } } @@ -490,6 +497,7 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr, { struct mem_size_stats *mss = walk->private; struct vm_area_struct *vma = walk->vma; + bool locked = !!(vma->vm_flags & VM_LOCKED); struct page *page = NULL; if (pte_present(*pte)) { @@ -532,7 +540,7 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr, if (!page) return; - smaps_account(mss, page, false, pte_young(*pte), pte_dirty(*pte)); + smaps_account(mss, page, false, pte_young(*pte), pte_dirty(*pte), locked); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE @@ -541,6 +549,7 @@ static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr, { struct mem_size_stats *mss = walk->private; struct vm_area_struct *vma = walk->vma; + bool locked = !!(vma->vm_flags & VM_LOCKED); struct page *page; /* FOLL_DUMP will return -EFAULT on huge zero page */ @@ -555,7 +564,7 @@ static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr, /* pass */; else VM_BUG_ON_PAGE(1, page); - smaps_account(mss, page, true, pmd_young(*pmd), pmd_dirty(*pmd)); + smaps_account(mss, page, true, pmd_young(*pmd), pmd_dirty(*pmd), locked); } #else static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr, @@ -737,11 +746,8 @@ static void smap_gather_stats(struct vm_area_struct *vma, } } #endif - /* mmap_sem is held in m_start */ walk_page_vma(vma, &smaps_walk); - if (vma->vm_flags & VM_LOCKED) - mss->pss_locked += mss->pss; } #define SEQ_PUT_DEC(str, val) \ -- cgit v1.2.3 From 23e93c9b2cde73f9912d0d8534adbddd3dcc48f4 Mon Sep 17 00:00:00 2001 From: Bob Peterson Date: Wed, 13 Feb 2019 15:12:17 -0500 Subject: Revert "gfs2: read journal in large chunks to locate the head" This reverts commit 2a5f14f279f59143139bcd1606903f2f80a34241. This patch causes xfstests generic/311 to fail. Reverting this for now until we have a proper fix. Signed-off-by: Abhi Das Signed-off-by: Bob Peterson Signed-off-by: Linus Torvalds --- fs/gfs2/glops.c | 1 - fs/gfs2/log.c | 4 +- fs/gfs2/lops.c | 190 ++------------------------------------------------- fs/gfs2/lops.h | 4 +- fs/gfs2/ops_fstype.c | 1 - fs/gfs2/recovery.c | 123 +++++++++++++++++++++++++++++++++ fs/gfs2/recovery.h | 2 + fs/gfs2/super.c | 1 - 8 files changed, 134 insertions(+), 192 deletions(-) (limited to 'fs') diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c index f15b4c57c4bd..78510ab91835 100644 --- a/fs/gfs2/glops.c +++ b/fs/gfs2/glops.c @@ -28,7 +28,6 @@ #include "util.h" #include "trans.h" #include "dir.h" -#include "lops.h" struct workqueue_struct *gfs2_freeze_wq; diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index 5bfaf381921a..b8830fda51e8 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -733,7 +733,7 @@ void gfs2_write_log_header(struct gfs2_sbd *sdp, struct gfs2_jdesc *jd, lh->lh_crc = cpu_to_be32(crc); gfs2_log_write(sdp, page, sb->s_blocksize, 0, addr); - gfs2_log_submit_bio(&sdp->sd_log_bio, REQ_OP_WRITE | op_flags); + gfs2_log_submit_bio(&sdp->sd_log_bio, REQ_OP_WRITE, op_flags); log_flush_wait(sdp); } @@ -810,7 +810,7 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl, u32 flags) gfs2_ordered_write(sdp); lops_before_commit(sdp, tr); - gfs2_log_submit_bio(&sdp->sd_log_bio, REQ_OP_WRITE); + gfs2_log_submit_bio(&sdp->sd_log_bio, REQ_OP_WRITE, 0); if (sdp->sd_log_head != sdp->sd_log_flush_head) { log_flush_wait(sdp); diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c index 94dcab655bc0..2295042bc625 100644 --- a/fs/gfs2/lops.c +++ b/fs/gfs2/lops.c @@ -17,9 +17,7 @@ #include #include #include -#include -#include "bmap.h" #include "dir.h" #include "gfs2.h" #include "incore.h" @@ -195,6 +193,7 @@ static void gfs2_end_log_write_bh(struct gfs2_sbd *sdp, struct bio_vec *bvec, /** * gfs2_end_log_write - end of i/o to the log * @bio: The bio + * @error: Status of i/o request * * Each bio_vec contains either data from the pagecache or data * relating to the log itself. Here we iterate over the bio_vec @@ -231,19 +230,20 @@ static void gfs2_end_log_write(struct bio *bio) /** * gfs2_log_submit_bio - Submit any pending log bio * @biop: Address of the bio pointer - * @opf: REQ_OP | op_flags + * @op: REQ_OP + * @op_flags: req_flag_bits * * Submit any pending part-built or full bio to the block device. If * there is no pending bio, then this is a no-op. */ -void gfs2_log_submit_bio(struct bio **biop, int opf) +void gfs2_log_submit_bio(struct bio **biop, int op, int op_flags) { struct bio *bio = *biop; if (bio) { struct gfs2_sbd *sdp = bio->bi_private; atomic_inc(&sdp->sd_log_in_flight); - bio->bi_opf = opf; + bio_set_op_attrs(bio, op, op_flags); submit_bio(bio); *biop = NULL; } @@ -304,7 +304,7 @@ static struct bio *gfs2_log_get_bio(struct gfs2_sbd *sdp, u64 blkno, nblk >>= sdp->sd_fsb2bb_shift; if (blkno == nblk && !flush) return bio; - gfs2_log_submit_bio(biop, op); + gfs2_log_submit_bio(biop, op, 0); } *biop = gfs2_log_alloc_bio(sdp, blkno, end_io); @@ -375,184 +375,6 @@ void gfs2_log_write_page(struct gfs2_sbd *sdp, struct page *page) gfs2_log_bmap(sdp)); } -/** - * gfs2_end_log_read - end I/O callback for reads from the log - * @bio: The bio - * - * Simply unlock the pages in the bio. The main thread will wait on them and - * process them in order as necessary. - */ - -static void gfs2_end_log_read(struct bio *bio) -{ - struct page *page; - struct bio_vec *bvec; - int i; - - bio_for_each_segment_all(bvec, bio, i) { - page = bvec->bv_page; - if (bio->bi_status) { - int err = blk_status_to_errno(bio->bi_status); - - SetPageError(page); - mapping_set_error(page->mapping, err); - } - unlock_page(page); - } - - bio_put(bio); -} - -/** - * gfs2_jhead_pg_srch - Look for the journal head in a given page. - * @jd: The journal descriptor - * @page: The page to look in - * - * Returns: 1 if found, 0 otherwise. - */ - -static bool gfs2_jhead_pg_srch(struct gfs2_jdesc *jd, - struct gfs2_log_header_host *head, - struct page *page) -{ - struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode); - struct gfs2_log_header_host uninitialized_var(lh); - void *kaddr = kmap_atomic(page); - unsigned int offset; - bool ret = false; - - for (offset = 0; offset < PAGE_SIZE; offset += sdp->sd_sb.sb_bsize) { - if (!__get_log_header(sdp, kaddr + offset, 0, &lh)) { - if (lh.lh_sequence > head->lh_sequence) - *head = lh; - else { - ret = true; - break; - } - } - } - kunmap_atomic(kaddr); - return ret; -} - -/** - * gfs2_jhead_process_page - Search/cleanup a page - * @jd: The journal descriptor - * @index: Index of the page to look into - * @done: If set, perform only cleanup, else search and set if found. - * - * Find the page with 'index' in the journal's mapping. Search the page for - * the journal head if requested (cleanup == false). Release refs on the - * page so the page cache can reclaim it (put_page() twice). We grabbed a - * reference on this page two times, first when we did a find_or_create_page() - * to obtain the page to add it to the bio and second when we do a - * find_get_page() here to get the page to wait on while I/O on it is being - * completed. - * This function is also used to free up a page we might've grabbed but not - * used. Maybe we added it to a bio, but not submitted it for I/O. Or we - * submitted the I/O, but we already found the jhead so we only need to drop - * our references to the page. - */ - -static void gfs2_jhead_process_page(struct gfs2_jdesc *jd, unsigned long index, - struct gfs2_log_header_host *head, - bool *done) -{ - struct page *page; - - page = find_get_page(jd->jd_inode->i_mapping, index); - wait_on_page_locked(page); - - if (PageError(page)) - *done = true; - - if (!*done) - *done = gfs2_jhead_pg_srch(jd, head, page); - - put_page(page); /* Once for find_get_page */ - put_page(page); /* Once more for find_or_create_page */ -} - -/** - * gfs2_find_jhead - find the head of a log - * @jd: The journal descriptor - * @head: The log descriptor for the head of the log is returned here - * - * Do a search of a journal by reading it in large chunks using bios and find - * the valid log entry with the highest sequence number. (i.e. the log head) - * - * Returns: 0 on success, errno otherwise - */ - -int gfs2_find_jhead(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head) -{ - struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode); - struct address_space *mapping = jd->jd_inode->i_mapping; - struct gfs2_journal_extent *je; - u32 block, read_idx = 0, submit_idx = 0, index = 0; - int shift = PAGE_SHIFT - sdp->sd_sb.sb_bsize_shift; - int blocks_per_page = 1 << shift, sz, ret = 0; - struct bio *bio = NULL; - struct page *page; - bool done = false; - errseq_t since; - - memset(head, 0, sizeof(*head)); - if (list_empty(&jd->extent_list)) - gfs2_map_journal_extents(sdp, jd); - - since = filemap_sample_wb_err(mapping); - list_for_each_entry(je, &jd->extent_list, list) { - for (block = 0; block < je->blocks; block += blocks_per_page) { - index = (je->lblock + block) >> shift; - - page = find_or_create_page(mapping, index, GFP_NOFS); - if (!page) { - ret = -ENOMEM; - done = true; - goto out; - } - - if (bio) { - sz = bio_add_page(bio, page, PAGE_SIZE, 0); - if (sz == PAGE_SIZE) - goto page_added; - submit_idx = index; - submit_bio(bio); - bio = NULL; - } - - bio = gfs2_log_alloc_bio(sdp, - je->dblock + (index << shift), - gfs2_end_log_read); - bio->bi_opf = REQ_OP_READ; - sz = bio_add_page(bio, page, PAGE_SIZE, 0); - gfs2_assert_warn(sdp, sz == PAGE_SIZE); - -page_added: - if (submit_idx <= read_idx + BIO_MAX_PAGES) { - /* Keep at least one bio in flight */ - continue; - } - - gfs2_jhead_process_page(jd, read_idx++, head, &done); - if (done) - goto out; /* found */ - } - } - -out: - if (bio) - submit_bio(bio); - while (read_idx <= index) - gfs2_jhead_process_page(jd, read_idx++, head, &done); - - if (!ret) - ret = filemap_check_wb_err(mapping, since); - - return ret; -} - static struct page *gfs2_get_log_desc(struct gfs2_sbd *sdp, u32 ld_type, u32 ld_length, u32 ld_data1) { diff --git a/fs/gfs2/lops.h b/fs/gfs2/lops.h index 331160fc568b..711c4d89c063 100644 --- a/fs/gfs2/lops.h +++ b/fs/gfs2/lops.h @@ -30,10 +30,8 @@ extern u64 gfs2_log_bmap(struct gfs2_sbd *sdp); extern void gfs2_log_write(struct gfs2_sbd *sdp, struct page *page, unsigned size, unsigned offset, u64 blkno); extern void gfs2_log_write_page(struct gfs2_sbd *sdp, struct page *page); -extern void gfs2_log_submit_bio(struct bio **biop, int opf); +extern void gfs2_log_submit_bio(struct bio **biop, int op, int op_flags); extern void gfs2_pin(struct gfs2_sbd *sdp, struct buffer_head *bh); -extern int gfs2_find_jhead(struct gfs2_jdesc *jd, - struct gfs2_log_header_host *head); static inline unsigned int buf_limit(struct gfs2_sbd *sdp) { diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index 1179763f6370..b041cb8ae383 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -41,7 +41,6 @@ #include "dir.h" #include "meta_io.h" #include "trace_gfs2.h" -#include "lops.h" #define DO 0 #define UNDO 1 diff --git a/fs/gfs2/recovery.c b/fs/gfs2/recovery.c index 7389e445a7a7..2dac43065382 100644 --- a/fs/gfs2/recovery.c +++ b/fs/gfs2/recovery.c @@ -181,6 +181,129 @@ static int get_log_header(struct gfs2_jdesc *jd, unsigned int blk, return error; } +/** + * find_good_lh - find a good log header + * @jd: the journal + * @blk: the segment to start searching from + * @lh: the log header to fill in + * @forward: if true search forward in the log, else search backward + * + * Call get_log_header() to get a log header for a segment, but if the + * segment is bad, either scan forward or backward until we find a good one. + * + * Returns: errno + */ + +static int find_good_lh(struct gfs2_jdesc *jd, unsigned int *blk, + struct gfs2_log_header_host *head) +{ + unsigned int orig_blk = *blk; + int error; + + for (;;) { + error = get_log_header(jd, *blk, head); + if (error <= 0) + return error; + + if (++*blk == jd->jd_blocks) + *blk = 0; + + if (*blk == orig_blk) { + gfs2_consist_inode(GFS2_I(jd->jd_inode)); + return -EIO; + } + } +} + +/** + * jhead_scan - make sure we've found the head of the log + * @jd: the journal + * @head: this is filled in with the log descriptor of the head + * + * At this point, seg and lh should be either the head of the log or just + * before. Scan forward until we find the head. + * + * Returns: errno + */ + +static int jhead_scan(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head) +{ + unsigned int blk = head->lh_blkno; + struct gfs2_log_header_host lh; + int error; + + for (;;) { + if (++blk == jd->jd_blocks) + blk = 0; + + error = get_log_header(jd, blk, &lh); + if (error < 0) + return error; + if (error == 1) + continue; + + if (lh.lh_sequence == head->lh_sequence) { + gfs2_consist_inode(GFS2_I(jd->jd_inode)); + return -EIO; + } + if (lh.lh_sequence < head->lh_sequence) + break; + + *head = lh; + } + + return 0; +} + +/** + * gfs2_find_jhead - find the head of a log + * @jd: the journal + * @head: the log descriptor for the head of the log is returned here + * + * Do a binary search of a journal and find the valid log entry with the + * highest sequence number. (i.e. the log head) + * + * Returns: errno + */ + +int gfs2_find_jhead(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head) +{ + struct gfs2_log_header_host lh_1, lh_m; + u32 blk_1, blk_2, blk_m; + int error; + + blk_1 = 0; + blk_2 = jd->jd_blocks - 1; + + for (;;) { + blk_m = (blk_1 + blk_2) / 2; + + error = find_good_lh(jd, &blk_1, &lh_1); + if (error) + return error; + + error = find_good_lh(jd, &blk_m, &lh_m); + if (error) + return error; + + if (blk_1 == blk_m || blk_m == blk_2) + break; + + if (lh_1.lh_sequence <= lh_m.lh_sequence) + blk_1 = blk_m; + else + blk_2 = blk_m; + } + + error = jhead_scan(jd, &lh_1); + if (error) + return error; + + *head = lh_1; + + return error; +} + /** * foreach_descriptor - go through the active part of the log * @jd: the journal diff --git a/fs/gfs2/recovery.h b/fs/gfs2/recovery.h index 99575ab81202..11d81248be85 100644 --- a/fs/gfs2/recovery.h +++ b/fs/gfs2/recovery.h @@ -27,6 +27,8 @@ extern int gfs2_revoke_add(struct gfs2_jdesc *jd, u64 blkno, unsigned int where) extern int gfs2_revoke_check(struct gfs2_jdesc *jd, u64 blkno, unsigned int where); extern void gfs2_revoke_clean(struct gfs2_jdesc *jd); +extern int gfs2_find_jhead(struct gfs2_jdesc *jd, + struct gfs2_log_header_host *head); extern int gfs2_recover_journal(struct gfs2_jdesc *gfs2_jd, bool wait); extern void gfs2_recover_func(struct work_struct *work); extern int __get_log_header(struct gfs2_sbd *sdp, diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index d4b11c903971..ca71163ff7cf 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -45,7 +45,6 @@ #include "util.h" #include "sys.h" #include "xattr.h" -#include "lops.h" #define args_neq(a1, a2, x) ((a1)->ar_##x != (a2)->ar_##x) -- cgit v1.2.3 From cb5b020a8d38f77209d0472a0fea755299a8ec78 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 14 Feb 2019 15:02:18 -0800 Subject: Revert "exec: load_script: don't blindly truncate shebang string" This reverts commit 8099b047ecc431518b9bb6bdbba3549bbecdc343. It turns out that people do actually depend on the shebang string being truncated, and on the fact that an interpreter (like perl) will often just re-interpret it entirely to get the full argument list. Reported-by: Samuel Dionne-Riel Acked-by: Kees Cook Cc: Oleg Nesterov Signed-off-by: Linus Torvalds --- fs/binfmt_script.c | 10 +++------- 1 file changed, 3 insertions(+), 7 deletions(-) (limited to 'fs') diff --git a/fs/binfmt_script.c b/fs/binfmt_script.c index d0078cbb718b..7cde3f46ad26 100644 --- a/fs/binfmt_script.c +++ b/fs/binfmt_script.c @@ -42,14 +42,10 @@ static int load_script(struct linux_binprm *bprm) fput(bprm->file); bprm->file = NULL; - for (cp = bprm->buf+2;; cp++) { - if (cp >= bprm->buf + BINPRM_BUF_SIZE) - return -ENOEXEC; - if (!*cp || (*cp == '\n')) - break; - } + bprm->buf[BINPRM_BUF_SIZE - 1] = '\0'; + if ((cp = strchr(bprm->buf, '\n')) == NULL) + cp = bprm->buf+BINPRM_BUF_SIZE-1; *cp = '\0'; - while (cp > bprm->buf) { cp--; if ((*cp == ' ') || (*cp == '\t')) -- cgit v1.2.3