4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Oliver Hartkopp socketcan@hartkopp.net

commit 0aaa81377c5a01f686bcdb8c7a6929a7bf330c68 upstream.

Muyu Yu provided a POC where user root with CAP_NET_ADMIN can create a CAN frame modification rule that makes the data length code a higher value than the available CAN frame data size. In combination with a configured checksum calculation where the result is stored relatively to the end of the data (e.g. cgw_csum_xor_rel) the tail of the skb (e.g. frag_list pointer in skb_shared_info) can be rewritten which finally can cause a system crash.

Michael Kubecek suggested to drop frames that have a DLC exceeding the available space after the modification process and provided a patch that can handle CAN FD frames too. Within this patch we also limit the length for the checksum calculations to the maximum of Classic CAN data length (8).

CAN frames that are dropped by these additional checks are counted with the CGW_DELETED counter which indicates misconfigurations in can-gw rules.

This fixes CVE-2019-3701.

Reported-by: Muyu Yu ieatmuttonchuan@gmail.com Reported-by: Marcus Meissner meissner@suse.de Suggested-by: Michal Kubecek mkubecek@suse.cz Tested-by: Muyu Yu ieatmuttonchuan@gmail.com Tested-by: Oliver Hartkopp socketcan@hartkopp.net Signed-off-by: Oliver Hartkopp socketcan@hartkopp.net Cc: linux-stable stable@vger.kernel.org # >= v3.2 Signed-off-by: Marc Kleine-Budde mkl@pengutronix.de Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- net/can/gw.c | 30 +++++++++++++++++++++++++++--- 1 file changed, 27 insertions(+), 3 deletions(-)

--- a/net/can/gw.c +++ b/net/can/gw.c @@ -418,13 +418,29 @@ static void can_can_gw_rcv(struct sk_buf while (modidx < MAX_MODFUNCTIONS && gwj->mod.modfunc[modidx]) (*gwj->mod.modfunc[modidx++])(cf, &gwj->mod);

- /* check for checksum updates when the CAN frame has been modified */ + /* Has the CAN frame been modified? */ if (modidx) { - if (gwj->mod.csumfunc.crc8) + /* get available space for the processed CAN frame type */ + int max_len = nskb->len - offsetof(struct can_frame, data); + + /* dlc may have changed, make sure it fits to the CAN frame */ + if (cf->can_dlc > max_len) + goto out_delete; + + /* check for checksum updates in classic CAN length only */ + if (gwj->mod.csumfunc.crc8) { + if (cf->can_dlc > 8) + goto out_delete; + (*gwj->mod.csumfunc.crc8)(cf, &gwj->mod.csum.crc8); + } + + if (gwj->mod.csumfunc.xor) { + if (cf->can_dlc > 8) + goto out_delete;

- if (gwj->mod.csumfunc.xor) (*gwj->mod.csumfunc.xor)(cf, &gwj->mod.csum.xor); + } }

/* clear the skb timestamp if not configured the other way */ @@ -436,6 +452,14 @@ static void can_can_gw_rcv(struct sk_buf gwj->dropped_frames++; else gwj->handled_frames++; + + return; + + out_delete: + /* delete frame due to misconfiguration */ + gwj->deleted_frames++; + kfree_skb(nskb); + return; }

static inline int cgw_register_filter(struct cgw_job *gwj)

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jaegeuk Kim jaegeuk@kernel.org

commit a51311938e14c17f5a94d30baac9d7bec71f5858 upstream.

There was a subtle bug on nat cache management which incurs wrong nid allocation or wrong block addresses when try_to_free_nats is triggered heavily. This patch enlarges the previous coverage of nat_tree_lock to avoid data race.

Signed-off-by: Jaegeuk Kim jaegeuk@kernel.org Signed-off-by: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/f2fs/node.c | 29 ++++++++++++----------------- 1 file changed, 12 insertions(+), 17 deletions(-)

--- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -261,13 +261,11 @@ static void cache_nat_entry(struct f2fs_ { struct nat_entry *e;

- down_write(&nm_i->nat_tree_lock); e = __lookup_nat_cache(nm_i, nid); if (!e) { e = grab_nat_entry(nm_i, nid); node_info_from_raw_nat(&e->ni, ne); } - up_write(&nm_i->nat_tree_lock); }

static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni, @@ -379,6 +377,8 @@ void get_node_info(struct f2fs_sb_info *

memset(&ne, 0, sizeof(struct f2fs_nat_entry));

+ down_write(&nm_i->nat_tree_lock); + /* Check current segment summary */ mutex_lock(&curseg->curseg_mutex); i = lookup_journal_in_cursum(sum, NAT_JOURNAL, nid, 0); @@ -399,6 +399,7 @@ void get_node_info(struct f2fs_sb_info * cache: /* cache nat entry */ cache_nat_entry(NM_I(sbi), nid, &ne); + up_write(&nm_i->nat_tree_lock); }

/* @@ -1440,13 +1441,10 @@ static int add_free_nid(struct f2fs_sb_i

if (build) { /* do not add allocated nids */ - down_read(&nm_i->nat_tree_lock); ne = __lookup_nat_cache(nm_i, nid); - if (ne && - (!get_nat_flag(ne, IS_CHECKPOINTED) || + if (ne && (!get_nat_flag(ne, IS_CHECKPOINTED) || nat_get_blkaddr(ne) != NULL_ADDR)) allocated = true; - up_read(&nm_i->nat_tree_lock); if (allocated) return 0; } @@ -1532,6 +1530,8 @@ static void build_free_nids(struct f2fs_ ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nid), FREE_NID_PAGES, META_NAT, true);

+ down_read(&nm_i->nat_tree_lock); + while (1) { struct page *page = get_current_nat_page(sbi, nid);

@@ -1560,6 +1560,7 @@ static void build_free_nids(struct f2fs_ remove_free_nid(nm_i, nid); } mutex_unlock(&curseg->curseg_mutex); + up_read(&nm_i->nat_tree_lock);

ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nm_i->next_scan_nid), nm_i->ra_nid_pages, META_NAT, false); @@ -1842,14 +1843,12 @@ static void remove_nats_in_journal(struc

raw_ne = nat_in_journal(sum, i);

- down_write(&nm_i->nat_tree_lock); ne = __lookup_nat_cache(nm_i, nid); if (!ne) { ne = grab_nat_entry(nm_i, nid); node_info_from_raw_nat(&ne->ni, &raw_ne); } __set_nat_cache_dirty(nm_i, ne); - up_write(&nm_i->nat_tree_lock); } update_nats_in_cursum(sum, -i); mutex_unlock(&curseg->curseg_mutex); @@ -1883,7 +1882,6 @@ static void __flush_nat_entry_set(struct struct f2fs_nat_block *nat_blk; struct nat_entry *ne, *cur; struct page *page = NULL; - struct f2fs_nm_info *nm_i = NM_I(sbi);

/* * there are two steps to flush nat entries: @@ -1920,12 +1918,8 @@ static void __flush_nat_entry_set(struct raw_ne = &nat_blk->entries[nid - start_nid]; } raw_nat_from_node_info(raw_ne, &ne->ni); - - down_write(&NM_I(sbi)->nat_tree_lock); nat_reset_flag(ne); __clear_nat_cache_dirty(NM_I(sbi), ne); - up_write(&NM_I(sbi)->nat_tree_lock); - if (nat_get_blkaddr(ne) == NULL_ADDR) add_free_nid(sbi, nid, false); } @@ -1937,9 +1931,7 @@ static void __flush_nat_entry_set(struct

f2fs_bug_on(sbi, set->entry_cnt);

- down_write(&nm_i->nat_tree_lock); radix_tree_delete(&NM_I(sbi)->nat_set_root, set->set); - up_write(&nm_i->nat_tree_lock); kmem_cache_free(nat_entry_set_slab, set); }

@@ -1959,6 +1951,9 @@ void flush_nat_entries(struct f2fs_sb_in

if (!nm_i->dirty_nat_cnt) return; + + down_write(&nm_i->nat_tree_lock); + /* * if there are no enough space in journal to store dirty nat * entries, remove all entries from journal and merge them @@ -1967,7 +1962,6 @@ void flush_nat_entries(struct f2fs_sb_in if (!__has_cursum_space(sum, nm_i->dirty_nat_cnt, NAT_JOURNAL)) remove_nats_in_journal(sbi);

- down_write(&nm_i->nat_tree_lock); while ((found = __gang_lookup_nat_set(nm_i, set_idx, SETVEC_SIZE, setvec))) { unsigned idx; @@ -1976,12 +1970,13 @@ void flush_nat_entries(struct f2fs_sb_in __adjust_nat_entry_set(setvec[idx], &sets, MAX_NAT_JENTRIES(sum)); } - up_write(&nm_i->nat_tree_lock);

/* flush dirty nats in nat entry set */ list_for_each_entry_safe(set, tmp, &sets, set_list) __flush_nat_entry_set(sbi, set);

+ up_write(&nm_i->nat_tree_lock); + f2fs_bug_on(sbi, nm_i->dirty_nat_cnt); }

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Chao Yu chao2.yu@samsung.com

With below serials, we will lose parts of dirents:

1) mount f2fs with inline_dentry option 2) echo 1 > /sys/fs/f2fs/sdX/dir_level 3) mkdir dir 4) touch 180 files named [1-180] in dir 5) touch 181 in dir 6) echo 3 > /proc/sys/vm/drop_caches 7) ll dir

ls: cannot access 2: No such file or directory ls: cannot access 4: No such file or directory ls: cannot access 5: No such file or directory ls: cannot access 6: No such file or directory ls: cannot access 8: No such file or directory ls: cannot access 9: No such file or directory ... total 360 drwxr-xr-x 2 root root 4096 Feb 19 15:12 ./ drwxr-xr-x 3 root root 4096 Feb 19 15:11 ../ -rw-r--r-- 1 root root 0 Feb 19 15:12 1 -rw-r--r-- 1 root root 0 Feb 19 15:12 10 -rw-r--r-- 1 root root 0 Feb 19 15:12 100 -????????? ? ? ? ? ? 101 -????????? ? ? ? ? ? 102 -????????? ? ? ? ? ? 103 ...

The reason is: when doing the inline dir conversion, we didn't consider that directory has hierarchical hash structure which can be configured through sysfs interface 'dir_level'.

By default, dir_level of directory inode is 0, it means we have one bucket in hash table located in first level, all dirents will be hashed in this bucket, so it has no problem for us to do the duplication simply between inline dentry page and converted normal dentry page.

However, if we configured dir_level with the value N (greater than 0), it will expand the bucket number of first level hash table by 2^N - 1, it hashs dirents into different buckets according their hash value, if we still move all dirents to first bucket, it makes incorrent locating for inline dirents, the result is, although we can iterate all dirents through ->readdir, we can't stat some of them in ->lookup which based on hash table searching.

This patch fixes this issue by rehashing dirents into correct position when converting inline directory.

Signed-off-by: Chao Yu chao2.yu@samsung.com Signed-off-by: Jaegeuk Kim jaegeuk@kernel.org [bwh: Backported to 4.4: - Keep using f2fs_crypto functions instead of generic fscrypt API - Use remove_dirty_dir_inode() instead of remove_dirty_inode() - Adjust context] Signed-off-by: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/f2fs/dir.c | 87 +++++++++++++++++++++++--------------------- fs/f2fs/f2fs.h | 4 +- fs/f2fs/inline.c | 94 +++++++++++++++++++++++++++++++++++++++++++++++- include/linux/f2fs_fs.h | 2 + 4 files changed, 144 insertions(+), 43 deletions(-)

--- a/fs/f2fs/dir.c +++ b/fs/f2fs/dir.c @@ -48,7 +48,6 @@ unsigned char f2fs_filetype_table[F2FS_F [F2FS_FT_SYMLINK] = DT_LNK, };

-#define S_SHIFT 12 static unsigned char f2fs_type_by_mode[S_IFMT >> S_SHIFT] = { [S_IFREG >> S_SHIFT] = F2FS_FT_REG_FILE, [S_IFDIR >> S_SHIFT] = F2FS_FT_DIR, @@ -64,6 +63,13 @@ void set_de_type(struct f2fs_dir_entry * de->file_type = f2fs_type_by_mode[(mode & S_IFMT) >> S_SHIFT]; }

+unsigned char get_de_type(struct f2fs_dir_entry *de) +{ + if (de->file_type < F2FS_FT_MAX) + return f2fs_filetype_table[de->file_type]; + return DT_UNKNOWN; +} + static unsigned long dir_block_index(unsigned int level, int dir_level, unsigned int idx) { @@ -519,11 +525,7 @@ void f2fs_update_dentry(nid_t ino, umode test_and_set_bit_le(bit_pos + i, (void *)d->bitmap); }

-/* - * Caller should grab and release a rwsem by calling f2fs_lock_op() and - * f2fs_unlock_op(). - */ -int __f2fs_add_link(struct inode *dir, const struct qstr *name, +int f2fs_add_regular_entry(struct inode *dir, const struct qstr *new_name, struct inode *inode, nid_t ino, umode_t mode) { unsigned int bit_pos; @@ -536,28 +538,11 @@ int __f2fs_add_link(struct inode *dir, c struct f2fs_dentry_block *dentry_blk = NULL; struct f2fs_dentry_ptr d; struct page *page = NULL; - struct f2fs_filename fname; - struct qstr new_name; - int slots, err; - - err = f2fs_fname_setup_filename(dir, name, 0, &fname); - if (err) - return err; - - new_name.name = fname_name(&fname); - new_name.len = fname_len(&fname); - - if (f2fs_has_inline_dentry(dir)) { - err = f2fs_add_inline_entry(dir, &new_name, inode, ino, mode); - if (!err || err != -EAGAIN) - goto out; - else - err = 0; - } + int slots, err = 0;

level = 0; - slots = GET_DENTRY_SLOTS(new_name.len); - dentry_hash = f2fs_dentry_hash(&new_name, NULL); + slots = GET_DENTRY_SLOTS(new_name->len); + dentry_hash = f2fs_dentry_hash(new_name, NULL);

current_depth = F2FS_I(dir)->i_current_depth; if (F2FS_I(dir)->chash == dentry_hash) { @@ -566,10 +551,8 @@ int __f2fs_add_link(struct inode *dir, c }

start: - if (unlikely(current_depth == MAX_DIR_HASH_DEPTH)) { - err = -ENOSPC; - goto out; - } + if (unlikely(current_depth == MAX_DIR_HASH_DEPTH)) + return -ENOSPC;

/* Increase the depth, if required */ if (level == current_depth) @@ -583,10 +566,8 @@ start:

for (block = bidx; block <= (bidx + nblock - 1); block++) { dentry_page = get_new_data_page(dir, NULL, block, true); - if (IS_ERR(dentry_page)) { - err = PTR_ERR(dentry_page); - goto out; - } + if (IS_ERR(dentry_page)) + return PTR_ERR(dentry_page);

dentry_blk = kmap(dentry_page); bit_pos = room_for_filename(&dentry_blk->dentry_bitmap, @@ -606,7 +587,7 @@ add_dentry:

if (inode) { down_write(&F2FS_I(inode)->i_sem); - page = init_inode_metadata(inode, dir, &new_name, NULL); + page = init_inode_metadata(inode, dir, new_name, NULL); if (IS_ERR(page)) { err = PTR_ERR(page); goto fail; @@ -616,7 +597,7 @@ add_dentry: }

make_dentry_ptr(NULL, &d, (void *)dentry_blk, 1); - f2fs_update_dentry(ino, mode, &d, &new_name, dentry_hash, bit_pos); + f2fs_update_dentry(ino, mode, &d, new_name, dentry_hash, bit_pos);

set_page_dirty(dentry_page);

@@ -638,7 +619,34 @@ fail: } kunmap(dentry_page); f2fs_put_page(dentry_page, 1); -out: + + return err; +} + +/* + * Caller should grab and release a rwsem by calling f2fs_lock_op() and + * f2fs_unlock_op(). + */ +int __f2fs_add_link(struct inode *dir, const struct qstr *name, + struct inode *inode, nid_t ino, umode_t mode) +{ + struct f2fs_filename fname; + struct qstr new_name; + int err; + + err = f2fs_fname_setup_filename(dir, name, 0, &fname); + if (err) + return err; + + new_name.name = fname_name(&fname); + new_name.len = fname_len(&fname); + + err = -EAGAIN; + if (f2fs_has_inline_dentry(dir)) + err = f2fs_add_inline_entry(dir, &new_name, inode, ino, mode); + if (err == -EAGAIN) + err = f2fs_add_regular_entry(dir, &new_name, inode, ino, mode); + f2fs_fname_free_filename(&fname); return err; } @@ -792,10 +800,7 @@ bool f2fs_fill_dentries(struct dir_conte break;

de = &d->dentry[bit_pos]; - if (de->file_type < F2FS_FT_MAX) - d_type = f2fs_filetype_table[de->file_type]; - else - d_type = DT_UNKNOWN; + d_type = get_de_type(de);

de_name.name = d->filename[bit_pos]; de_name.len = le16_to_cpu(de->name_len); --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -1677,7 +1677,7 @@ struct dentry *f2fs_get_parent(struct de */ extern unsigned char f2fs_filetype_table[F2FS_FT_MAX]; void set_de_type(struct f2fs_dir_entry *, umode_t); - +unsigned char get_de_type(struct f2fs_dir_entry *); struct f2fs_dir_entry *find_target_dentry(struct f2fs_filename *, f2fs_hash_t, int *, struct f2fs_dentry_ptr *); bool f2fs_fill_dentries(struct dir_context *, struct f2fs_dentry_ptr *, @@ -1698,6 +1698,8 @@ void f2fs_set_link(struct inode *, struc int update_dent_inode(struct inode *, struct inode *, const struct qstr *); void f2fs_update_dentry(nid_t ino, umode_t mode, struct f2fs_dentry_ptr *, const struct qstr *, f2fs_hash_t , unsigned int); +int f2fs_add_regular_entry(struct inode *, const struct qstr *, + struct inode *, nid_t, umode_t); int __f2fs_add_link(struct inode *, const struct qstr *, struct inode *, nid_t, umode_t); void f2fs_delete_entry(struct f2fs_dir_entry *, struct page *, struct inode *, --- a/fs/f2fs/inline.c +++ b/fs/f2fs/inline.c @@ -367,7 +367,7 @@ int make_empty_inline_dir(struct inode * * NOTE: ipage is grabbed by caller, but if any error occurs, we should * release ipage in this function. */ -static int f2fs_convert_inline_dir(struct inode *dir, struct page *ipage, +static int f2fs_move_inline_dirents(struct inode *dir, struct page *ipage, struct f2fs_inline_dentry *inline_dentry) { struct page *page; @@ -428,6 +428,98 @@ out: return err; }

+static int f2fs_add_inline_entries(struct inode *dir, + struct f2fs_inline_dentry *inline_dentry) +{ + struct f2fs_dentry_ptr d; + unsigned long bit_pos = 0; + int err = 0; + + make_dentry_ptr(NULL, &d, (void *)inline_dentry, 2); + + while (bit_pos < d.max) { + struct f2fs_dir_entry *de; + struct qstr new_name; + nid_t ino; + umode_t fake_mode; + + if (!test_bit_le(bit_pos, d.bitmap)) { + bit_pos++; + continue; + } + + de = &d.dentry[bit_pos]; + new_name.name = d.filename[bit_pos]; + new_name.len = de->name_len; + + ino = le32_to_cpu(de->ino); + fake_mode = get_de_type(de) << S_SHIFT; + + err = f2fs_add_regular_entry(dir, &new_name, NULL, + ino, fake_mode); + if (err) + goto punch_dentry_pages; + + if (unlikely(!de->name_len)) + d.max = -1; + + bit_pos += GET_DENTRY_SLOTS(le16_to_cpu(de->name_len)); + } + return 0; +punch_dentry_pages: + truncate_inode_pages(&dir->i_data, 0); + truncate_blocks(dir, 0, false); + remove_dirty_dir_inode(dir); + return err; +} + +static int f2fs_move_rehashed_dirents(struct inode *dir, struct page *ipage, + struct f2fs_inline_dentry *inline_dentry) +{ + struct f2fs_inline_dentry *backup_dentry; + int err; + + backup_dentry = kmalloc(sizeof(struct f2fs_inline_dentry), + GFP_F2FS_ZERO); + if (!backup_dentry) + return -ENOMEM; + + memcpy(backup_dentry, inline_dentry, MAX_INLINE_DATA); + truncate_inline_inode(ipage, 0); + + unlock_page(ipage); + + err = f2fs_add_inline_entries(dir, backup_dentry); + if (err) + goto recover; + + lock_page(ipage); + + stat_dec_inline_dir(dir); + clear_inode_flag(F2FS_I(dir), FI_INLINE_DENTRY); + update_inode(dir, ipage); + kfree(backup_dentry); + return 0; +recover: + lock_page(ipage); + memcpy(inline_dentry, backup_dentry, MAX_INLINE_DATA); + i_size_write(dir, MAX_INLINE_DATA); + update_inode(dir, ipage); + f2fs_put_page(ipage, 1); + + kfree(backup_dentry); + return err; +} + +static int f2fs_convert_inline_dir(struct inode *dir, struct page *ipage, + struct f2fs_inline_dentry *inline_dentry) +{ + if (!F2FS_I(dir)->i_dir_level) + return f2fs_move_inline_dirents(dir, ipage, inline_dentry); + else + return f2fs_move_rehashed_dirents(dir, ipage, inline_dentry); +} + int f2fs_add_inline_entry(struct inode *dir, const struct qstr *name, struct inode *inode, nid_t ino, umode_t mode) { --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -497,4 +497,6 @@ enum { F2FS_FT_MAX };

+#define S_SHIFT 12 + #endif /* _LINUX_F2FS_FS_H */

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jaegeuk Kim jaegeuk@kernel.org

commit fb58ae22067e0595d974e3d856522c1ed6d2d7bf upstream.

This patch removes an obsolete variable used in add_free_nid.

Signed-off-by: Jaegeuk Kim jaegeuk@kernel.org [bwh: Picked as dependency of commit 30a61ddf8117 "f2fs: fix race condition in between free nid allocator/initializer"] Signed-off-by: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/f2fs/node.c | 3 --- 1 file changed, 3 deletions(-)

--- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -1430,7 +1430,6 @@ static int add_free_nid(struct f2fs_sb_i struct f2fs_nm_info *nm_i = NM_I(sbi); struct free_nid *i; struct nat_entry *ne; - bool allocated = false;

if (!available_free_memory(sbi, FREE_NIDS)) return -1; @@ -1444,8 +1443,6 @@ static int add_free_nid(struct f2fs_sb_i ne = __lookup_nat_cache(nm_i, nid); if (ne && (!get_nat_flag(ne, IS_CHECKPOINTED) || nat_get_blkaddr(ne) != NULL_ADDR)) - allocated = true; - if (allocated) return 0; }

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Chao Yu yuchao0@huawei.com

commit f61cce5b81f91ba336184008b24baec84afbb3dd upstream.

When testing f2fs with inline_dentry option, generic/342 reports: VFS: Busy inodes after unmount of dm-0. Self-destruct in 5 seconds. Have a nice day...

After rmmod f2fs module, kenrel shows following dmesg: ============================================================================= BUG f2fs_inode_cache (Tainted: G O ): Objects remaining in f2fs_inode_cache on __kmem_cache_shutdown() -----------------------------------------------------------------------------

Disabling lock debugging due to kernel taint INFO: Slab 0xf51ca0e0 objects=22 used=1 fp=0xd1e6fc60 flags=0x40004080 CPU: 3 PID: 7455 Comm: rmmod Tainted: G B O 4.6.0-rc4+ #16 Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 00000086 00000086 d062fe18 c13a83a0 f51ca0e0 d062fe38 d062fea4 c11c7276 c1981040 f51ca0e0 00000016 00000001 d1e6fc60 40004080 656a624f 20737463 616d6572 6e696e69 6e692067 66326620 6e695f73 5f65646f 68636163 6e6f2065 Call Trace: [<c13a83a0>] dump_stack+0x5f/0x8f [<c11c7276>] slab_err+0x76/0x80 [<c11cbfc0>] ? __kmem_cache_shutdown+0x100/0x2f0 [<c11cbfc0>] ? __kmem_cache_shutdown+0x100/0x2f0 [<c11cbfe5>] __kmem_cache_shutdown+0x125/0x2f0 [<c1198a38>] kmem_cache_destroy+0x158/0x1f0 [<c176b43d>] ? mutex_unlock+0xd/0x10 [<f8f15aa3>] exit_f2fs_fs+0x4b/0x5a8 [f2fs] [<c10f596c>] SyS_delete_module+0x16c/0x1d0 [<c1001b10>] ? do_fast_syscall_32+0x30/0x1c0 [<c13c59bf>] ? __this_cpu_preempt_check+0xf/0x20 [<c10afa7d>] ? trace_hardirqs_on_caller+0xdd/0x210 [<c10ad50b>] ? trace_hardirqs_off+0xb/0x10 [<c1001b81>] do_fast_syscall_32+0xa1/0x1c0 [<c176d888>] sysenter_past_esp+0x45/0x74 INFO: Object 0xd1e6d9e0 @offset=6624 kmem_cache_destroy f2fs_inode_cache: Slab cache still has objects CPU: 3 PID: 7455 Comm: rmmod Tainted: G B O 4.6.0-rc4+ #16 Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 00000286 00000286 d062fef4 c13a83a0 f174b000 d062ff14 d062ff28 c1198ac7 c197fe18 f3c5b980 d062ff20 000d04f2 d062ff0c d062ff0c d062ff14 d062ff14 f8f20dc0 fffffff5 d062e000 d062ff30 f8f15aa3 d062ff7c c10f596c 73663266 Call Trace: [<c13a83a0>] dump_stack+0x5f/0x8f [<c1198ac7>] kmem_cache_destroy+0x1e7/0x1f0 [<f8f15aa3>] exit_f2fs_fs+0x4b/0x5a8 [f2fs] [<c10f596c>] SyS_delete_module+0x16c/0x1d0 [<c1001b10>] ? do_fast_syscall_32+0x30/0x1c0 [<c13c59bf>] ? __this_cpu_preempt_check+0xf/0x20 [<c10afa7d>] ? trace_hardirqs_on_caller+0xdd/0x210 [<c10ad50b>] ? trace_hardirqs_off+0xb/0x10 [<c1001b81>] do_fast_syscall_32+0xa1/0x1c0 [<c176d888>] sysenter_past_esp+0x45/0x74

The reason is: in recovery flow, we use delayed iput mechanism for directory which has recovered dentry block. It means the reference of inode will be held until last dirty dentry page being writebacked.

But when we mount f2fs with inline_dentry option, during recovery, dirent may only be recovered into dir inode page rather than dentry page, so there are no chance for us to release inode reference in ->writepage when writebacking last dentry page.

We can call paired iget/iput explicityly for inline_dentry case, but for non-inline_dentry case, iput will call writeback_single_inode to write all data pages synchronously, but during recovery, ->writepages of f2fs skips writing all pages, result in losing dirent.

This patch fixes this issue by obsoleting old mechanism, and introduce a new dir_list to hold all directory inodes which has recovered datas until finishing recovery.

Signed-off-by: Chao Yu yuchao0@huawei.com Signed-off-by: Jaegeuk Kim jaegeuk@kernel.org [bwh: Backported to 4.4: - Deleted add_dirty_dir_inode() function is different - Adjust context] Signed-off-by: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/f2fs/checkpoint.c | 24 --------------------- fs/f2fs/f2fs.h | 2 - fs/f2fs/recovery.c | 56 ++++++++++++++++++++++++++++----------------------- 3 files changed, 31 insertions(+), 51 deletions(-)

--- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -771,24 +771,6 @@ out: f2fs_trace_pid(page); }

-void add_dirty_dir_inode(struct inode *inode) -{ - struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - struct inode_entry *new = - f2fs_kmem_cache_alloc(inode_entry_slab, GFP_NOFS); - int ret = 0; - - new->inode = inode; - INIT_LIST_HEAD(&new->list); - - spin_lock(&sbi->dir_inode_lock); - ret = __add_dirty_inode(inode, new); - spin_unlock(&sbi->dir_inode_lock); - - if (ret) - kmem_cache_free(inode_entry_slab, new); -} - void remove_dirty_dir_inode(struct inode *inode) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); @@ -811,12 +793,6 @@ void remove_dirty_dir_inode(struct inode stat_dec_dirty_dir(sbi); spin_unlock(&sbi->dir_inode_lock); kmem_cache_free(inode_entry_slab, entry); - - /* Only from the recovery routine */ - if (is_inode_flag_set(F2FS_I(inode), FI_DELAY_IPUT)) { - clear_inode_flag(F2FS_I(inode), FI_DELAY_IPUT); - iput(inode); - } }

void sync_dirty_dir_inodes(struct f2fs_sb_info *sbi) --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -1402,7 +1402,6 @@ enum { FI_NO_ALLOC, /* should not allocate any blocks */ FI_FREE_NID, /* free allocated nide */ FI_UPDATE_DIR, /* should update inode block for consistency */ - FI_DELAY_IPUT, /* used for the recovery */ FI_NO_EXTENT, /* not to use the extent cache */ FI_INLINE_XATTR, /* used for inline xattr */ FI_INLINE_DATA, /* used for inline data*/ @@ -1828,7 +1827,6 @@ void remove_orphan_inode(struct f2fs_sb_ int recover_orphan_inodes(struct f2fs_sb_info *); int get_valid_checkpoint(struct f2fs_sb_info *); void update_dirty_page(struct inode *, struct page *); -void add_dirty_dir_inode(struct inode *); void remove_dirty_dir_inode(struct inode *); void sync_dirty_dir_inodes(struct f2fs_sb_info *); void write_checkpoint(struct f2fs_sb_info *, struct cp_control *); --- a/fs/f2fs/recovery.c +++ b/fs/f2fs/recovery.c @@ -89,7 +89,8 @@ static void del_fsync_inode(struct fsync kmem_cache_free(fsync_entry_slab, entry); }

-static int recover_dentry(struct inode *inode, struct page *ipage) +static int recover_dentry(struct inode *inode, struct page *ipage, + struct list_head *dir_list) { struct f2fs_inode *raw_inode = F2FS_INODE(ipage); nid_t pino = le32_to_cpu(raw_inode->i_pino); @@ -97,18 +98,29 @@ static int recover_dentry(struct inode * struct qstr name; struct page *page; struct inode *dir, *einode; + struct fsync_inode_entry *entry; int err = 0;

- dir = f2fs_iget(inode->i_sb, pino); - if (IS_ERR(dir)) { - err = PTR_ERR(dir); - goto out; + entry = get_fsync_inode(dir_list, pino); + if (!entry) { + dir = f2fs_iget(inode->i_sb, pino); + if (IS_ERR(dir)) { + err = PTR_ERR(dir); + goto out; + } + + entry = add_fsync_inode(dir_list, dir); + if (!entry) { + err = -ENOMEM; + iput(dir); + goto out; + } }

- if (file_enc_name(inode)) { - iput(dir); + dir = entry->inode; + + if (file_enc_name(inode)) return 0; - }

name.len = le32_to_cpu(raw_inode->i_namelen); name.name = raw_inode->i_name; @@ -116,7 +128,7 @@ static int recover_dentry(struct inode * if (unlikely(name.len > F2FS_NAME_LEN)) { WARN_ON(1); err = -ENAMETOOLONG; - goto out_err; + goto out; } retry: de = f2fs_find_entry(dir, &name, &page); @@ -142,23 +154,12 @@ retry: goto retry; } err = __f2fs_add_link(dir, &name, inode, inode->i_ino, inode->i_mode); - if (err) - goto out_err; - - if (is_inode_flag_set(F2FS_I(dir), FI_DELAY_IPUT)) { - iput(dir); - } else { - add_dirty_dir_inode(dir); - set_inode_flag(F2FS_I(dir), FI_DELAY_IPUT); - }

goto out;

out_unmap_put: f2fs_dentry_kunmap(dir, page); f2fs_put_page(page, 0); -out_err: - iput(dir); out: f2fs_msg(inode->i_sb, KERN_NOTICE, "%s: ino = %x, name = %s, dir = %lx, err = %d", @@ -479,7 +480,8 @@ out: return err; }

-static int recover_data(struct f2fs_sb_info *sbi, struct list_head *head) +static int recover_data(struct f2fs_sb_info *sbi, struct list_head *inode_list, + struct list_head *dir_list) { unsigned long long cp_ver = cur_cp_version(F2FS_CKPT(sbi)); struct curseg_info *curseg; @@ -506,7 +508,7 @@ static int recover_data(struct f2fs_sb_i break; }

- entry = get_fsync_inode(head, ino_of_node(page)); + entry = get_fsync_inode(inode_list, ino_of_node(page)); if (!entry) goto next; /* @@ -517,7 +519,7 @@ static int recover_data(struct f2fs_sb_i if (entry->last_inode == blkaddr) recover_inode(entry->inode, page); if (entry->last_dentry == blkaddr) { - err = recover_dentry(entry->inode, page); + err = recover_dentry(entry->inode, page, dir_list); if (err) { f2fs_put_page(page, 1); break; @@ -545,6 +547,7 @@ int recover_fsync_data(struct f2fs_sb_in { struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_WARM_NODE); struct list_head inode_list; + struct list_head dir_list; block_t blkaddr; int err; int ret = 0; @@ -556,6 +559,7 @@ int recover_fsync_data(struct f2fs_sb_in return -ENOMEM;

INIT_LIST_HEAD(&inode_list); + INIT_LIST_HEAD(&dir_list);

/* prevent checkpoint */ mutex_lock(&sbi->cp_mutex); @@ -575,12 +579,11 @@ int recover_fsync_data(struct f2fs_sb_in need_writecp = true;

/* step #2: recover data */ - err = recover_data(sbi, &inode_list); + err = recover_data(sbi, &inode_list, &dir_list); if (!err) f2fs_bug_on(sbi, !list_empty(&inode_list)); out: destroy_fsync_dnodes(&inode_list); - kmem_cache_destroy(fsync_entry_slab);

/* truncate meta pages to be used by the recovery */ truncate_inode_pages_range(META_MAPPING(sbi), @@ -618,5 +621,8 @@ out: } else { mutex_unlock(&sbi->cp_mutex); } + + destroy_fsync_dnodes(&dir_list); + kmem_cache_destroy(fsync_entry_slab); return ret ? ret: err; }

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Yunlei He heyunlei@huawei.com

commit bb413d6acd4e1c361daebf8486efc3923f429792 upstream.

we came across an error as below:

[build_nat_area_bitmap:1710] nid[0x 1718] addr[0x 1c18ddc] ino[0x 1718] [build_nat_area_bitmap:1710] nid[0x 1719] addr[0x 1c193d5] ino[0x 1719] [build_nat_area_bitmap:1710] nid[0x 171a] addr[0x 1c1736e] ino[0x 171a] [build_nat_area_bitmap:1710] nid[0x 171b] addr[0x 58b3ee8f] ino[0x815f92ed] [build_nat_area_bitmap:1710] nid[0x 171c] addr[0x fcdc94b] ino[0x49366377] [build_nat_area_bitmap:1710] nid[0x 171d] addr[0x 7cd2facf] ino[0xb3c55300] [build_nat_area_bitmap:1710] nid[0x 171e] addr[0x bd4e25d0] ino[0x77c34c09]

... ...

[build_nat_area_bitmap:1710] nid[0x 1718] addr[0x 1c18ddc] ino[0x 1718] [build_nat_area_bitmap:1710] nid[0x 1719] addr[0x 1c193d5] ino[0x 1719] [build_nat_area_bitmap:1710] nid[0x 171a] addr[0x 1c1736e] ino[0x 171a] [build_nat_area_bitmap:1710] nid[0x 171b] addr[0x 58b3ee8f] ino[0x815f92ed] [build_nat_area_bitmap:1710] nid[0x 171c] addr[0x fcdc94b] ino[0x49366377] [build_nat_area_bitmap:1710] nid[0x 171d] addr[0x 7cd2facf] ino[0xb3c55300] [build_nat_area_bitmap:1710] nid[0x 171e] addr[0x bd4e25d0] ino[0x77c34c09]

One nat block may be stepped by a data block, so this patch forbid to write if the blkaddr is illegal

Signed-off-by: Yunlei He heyunlei@huawei.com Signed-off-by: Jaegeuk Kim jaegeuk@kernel.org Signed-off-by: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/f2fs/segment.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/fs/f2fs/segment.h +++ b/fs/f2fs/segment.h @@ -576,8 +576,8 @@ static inline void check_seg_range(struc

static inline void verify_block_addr(struct f2fs_sb_info *sbi, block_t blk_addr) { - f2fs_bug_on(sbi, blk_addr < SEG0_BLKADDR(sbi) - || blk_addr >= MAX_BLKADDR(sbi)); + BUG_ON(blk_addr < SEG0_BLKADDR(sbi) + || blk_addr >= MAX_BLKADDR(sbi)); }

/*

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jaegeuk Kim jaegeuk@kernel.org

commit a468f0ef516fda9c7d91bb550d458e853d76955e upstream.

Previously, we used cp_version only to detect recoverable dnodes. In order to avoid same garbage cp_version, we needed to truncate the next dnode during checkpoint, resulting in additional discard or data write. If we can distinguish this by using crc in addition to cp_version, we can remove this overhead.

There is backward compatibility concern where it changes node_footer layout. So, this patch introduces a new checkpoint flag, CP_CRC_RECOVERY_FLAG, to detect new layout. New layout will be activated only when this flag is set.

Signed-off-by: Jaegeuk Kim jaegeuk@kernel.org [bwh: Backported to 4.4: - Deleted code is slightly different - Adjust context] Signed-off-by: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/f2fs/checkpoint.c | 21 +------------ fs/f2fs/f2fs.h | 1 fs/f2fs/node.h | 77 ++++++++++++++++++++++++++++++------------------ fs/f2fs/recovery.c | 30 +++--------------- fs/f2fs/segment.c | 22 ------------- fs/f2fs/super.c | 5 ++- include/linux/f2fs_fs.h | 1 7 files changed, 63 insertions(+), 94 deletions(-)

--- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -902,7 +902,6 @@ static void wait_on_all_pages_writeback( static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) { struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); - struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_WARM_NODE); struct f2fs_nm_info *nm_i = NM_I(sbi); unsigned long orphan_num = sbi->im[ORPHAN_INO].ino_num; nid_t last_nid = nm_i->next_scan_nid; @@ -911,15 +910,6 @@ static void do_checkpoint(struct f2fs_sb __u32 crc32 = 0; int i; int cp_payload_blks = __cp_payload(sbi); - block_t discard_blk = NEXT_FREE_BLKADDR(sbi, curseg); - bool invalidate = false; - - /* - * This avoids to conduct wrong roll-forward operations and uses - * metapages, so should be called prior to sync_meta_pages below. - */ - if (discard_next_dnode(sbi, discard_blk)) - invalidate = true;

/* Flush all the NAT/SIT pages */ while (get_pages(sbi, F2FS_DIRTY_META)) { @@ -996,6 +986,9 @@ static void do_checkpoint(struct f2fs_sb if (is_sbi_flag_set(sbi, SBI_NEED_FSCK)) set_ckpt_flags(ckpt, CP_FSCK_FLAG);

+ /* set this flag to activate crc|cp_ver for recovery */ + set_ckpt_flags(ckpt, CP_CRC_RECOVERY_FLAG); + /* update SIT/NAT bitmap */ get_sit_bitmap(sbi, __bitmap_ptr(sbi, SIT_BITMAP)); get_nat_bitmap(sbi, __bitmap_ptr(sbi, NAT_BITMAP)); @@ -1053,14 +1046,6 @@ static void do_checkpoint(struct f2fs_sb /* wait for previous submitted meta pages writeback */ wait_on_all_pages_writeback(sbi);

- /* - * invalidate meta page which is used temporarily for zeroing out - * block at the end of warm node chain. - */ - if (invalidate) - invalidate_mapping_pages(META_MAPPING(sbi), discard_blk, - discard_blk); - release_dirty_inode(sbi);

if (unlikely(f2fs_cp_error(sbi))) --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -1780,7 +1780,6 @@ bool is_checkpointed_data(struct f2fs_sb void refresh_sit_entry(struct f2fs_sb_info *, block_t, block_t); void clear_prefree_segments(struct f2fs_sb_info *, struct cp_control *); void release_discard_addrs(struct f2fs_sb_info *); -bool discard_next_dnode(struct f2fs_sb_info *, block_t); int npages_for_summary_flush(struct f2fs_sb_info *, bool); void allocate_new_segments(struct f2fs_sb_info *); int f2fs_trim_fs(struct f2fs_sb_info *, struct fstrim_range *); --- a/fs/f2fs/node.h +++ b/fs/f2fs/node.h @@ -212,6 +212,37 @@ static inline void set_to_next_nat(struc f2fs_change_bit(block_off, nm_i->nat_bitmap); }

+static inline nid_t ino_of_node(struct page *node_page) +{ + struct f2fs_node *rn = F2FS_NODE(node_page); + return le32_to_cpu(rn->footer.ino); +} + +static inline nid_t nid_of_node(struct page *node_page) +{ + struct f2fs_node *rn = F2FS_NODE(node_page); + return le32_to_cpu(rn->footer.nid); +} + +static inline unsigned int ofs_of_node(struct page *node_page) +{ + struct f2fs_node *rn = F2FS_NODE(node_page); + unsigned flag = le32_to_cpu(rn->footer.flag); + return flag >> OFFSET_BIT_SHIFT; +} + +static inline __u64 cpver_of_node(struct page *node_page) +{ + struct f2fs_node *rn = F2FS_NODE(node_page); + return le64_to_cpu(rn->footer.cp_ver); +} + +static inline block_t next_blkaddr_of_node(struct page *node_page) +{ + struct f2fs_node *rn = F2FS_NODE(node_page); + return le32_to_cpu(rn->footer.next_blkaddr); +} + static inline void fill_node_footer(struct page *page, nid_t nid, nid_t ino, unsigned int ofs, bool reset) { @@ -242,40 +273,30 @@ static inline void fill_node_footer_blka { struct f2fs_checkpoint *ckpt = F2FS_CKPT(F2FS_P_SB(page)); struct f2fs_node *rn = F2FS_NODE(page); + size_t crc_offset = le32_to_cpu(ckpt->checksum_offset); + __u64 cp_ver = le64_to_cpu(ckpt->checkpoint_ver);

- rn->footer.cp_ver = ckpt->checkpoint_ver; + if (is_set_ckpt_flags(ckpt, CP_CRC_RECOVERY_FLAG)) { + __u64 crc = le32_to_cpu(*((__le32 *) + ((unsigned char *)ckpt + crc_offset))); + cp_ver |= (crc << 32); + } + rn->footer.cp_ver = cpu_to_le64(cp_ver); rn->footer.next_blkaddr = cpu_to_le32(blkaddr); }

-static inline nid_t ino_of_node(struct page *node_page) -{ - struct f2fs_node *rn = F2FS_NODE(node_page); - return le32_to_cpu(rn->footer.ino); -} - -static inline nid_t nid_of_node(struct page *node_page) -{ - struct f2fs_node *rn = F2FS_NODE(node_page); - return le32_to_cpu(rn->footer.nid); -} - -static inline unsigned int ofs_of_node(struct page *node_page) -{ - struct f2fs_node *rn = F2FS_NODE(node_page); - unsigned flag = le32_to_cpu(rn->footer.flag); - return flag >> OFFSET_BIT_SHIFT; -} - -static inline unsigned long long cpver_of_node(struct page *node_page) +static inline bool is_recoverable_dnode(struct page *page) { - struct f2fs_node *rn = F2FS_NODE(node_page); - return le64_to_cpu(rn->footer.cp_ver); -} + struct f2fs_checkpoint *ckpt = F2FS_CKPT(F2FS_P_SB(page)); + size_t crc_offset = le32_to_cpu(ckpt->checksum_offset); + __u64 cp_ver = cur_cp_version(ckpt);

-static inline block_t next_blkaddr_of_node(struct page *node_page) -{ - struct f2fs_node *rn = F2FS_NODE(node_page); - return le32_to_cpu(rn->footer.next_blkaddr); + if (is_set_ckpt_flags(ckpt, CP_CRC_RECOVERY_FLAG)) { + __u64 crc = le32_to_cpu(*((__le32 *) + ((unsigned char *)ckpt + crc_offset))); + cp_ver |= (crc << 32); + } + return cpu_to_le64(cp_ver) == cpver_of_node(page); }

/* --- a/fs/f2fs/recovery.c +++ b/fs/f2fs/recovery.c @@ -193,7 +193,6 @@ static void recover_inode(struct inode *

static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head) { - unsigned long long cp_ver = cur_cp_version(F2FS_CKPT(sbi)); struct curseg_info *curseg; struct inode *inode; struct page *page = NULL; @@ -214,7 +213,7 @@ static int find_fsync_dnodes(struct f2fs

page = get_tmp_page(sbi, blkaddr);

- if (cp_ver != cpver_of_node(page)) + if (!is_recoverable_dnode(page)) break;

if (!is_fsync_dnode(page)) @@ -483,7 +482,6 @@ out: static int recover_data(struct f2fs_sb_info *sbi, struct list_head *inode_list, struct list_head *dir_list) { - unsigned long long cp_ver = cur_cp_version(F2FS_CKPT(sbi)); struct curseg_info *curseg; struct page *page = NULL; int err = 0; @@ -503,7 +501,7 @@ static int recover_data(struct f2fs_sb_i

page = get_tmp_page(sbi, blkaddr);

- if (cp_ver != cpver_of_node(page)) { + if (!is_recoverable_dnode(page)) { f2fs_put_page(page, 1); break; } @@ -595,31 +593,15 @@ out: }

clear_sbi_flag(sbi, SBI_POR_DOING); - if (err) { - bool invalidate = false; - - if (discard_next_dnode(sbi, blkaddr)) - invalidate = true; - - /* Flush all the NAT/SIT pages */ - while (get_pages(sbi, F2FS_DIRTY_META)) - sync_meta_pages(sbi, META, LONG_MAX); - - /* invalidate temporary meta page */ - if (invalidate) - invalidate_mapping_pages(META_MAPPING(sbi), - blkaddr, blkaddr); - + if (err) set_ckpt_flags(sbi->ckpt, CP_ERROR_FLAG); - mutex_unlock(&sbi->cp_mutex); - } else if (need_writecp) { + mutex_unlock(&sbi->cp_mutex); + + if (!err && need_writecp) { struct cp_control cpc = { .reason = CP_RECOVERY, }; - mutex_unlock(&sbi->cp_mutex); write_checkpoint(sbi, &cpc); - } else { - mutex_unlock(&sbi->cp_mutex); }

destroy_fsync_dnodes(&dir_list); --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -519,28 +519,6 @@ static int f2fs_issue_discard(struct f2f return blkdev_issue_discard(sbi->sb->s_bdev, start, len, GFP_NOFS, 0); }

-bool discard_next_dnode(struct f2fs_sb_info *sbi, block_t blkaddr) -{ - int err = -ENOTSUPP; - - if (test_opt(sbi, DISCARD)) { - struct seg_entry *se = get_seg_entry(sbi, - GET_SEGNO(sbi, blkaddr)); - unsigned int offset = GET_BLKOFF_FROM_SEG0(sbi, blkaddr); - - if (f2fs_test_bit(offset, se->discard_map)) - return false; - - err = f2fs_issue_discard(sbi, blkaddr, 1); - } - - if (err) { - update_meta_page(sbi, NULL, blkaddr); - return true; - } - return false; -} - static void __add_discard_entry(struct f2fs_sb_info *sbi, struct cp_control *cpc, struct seg_entry *se, unsigned int start, unsigned int end) --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -1457,6 +1457,9 @@ try_onemore: if (need_fsck) set_sbi_flag(sbi, SBI_NEED_FSCK);

+ if (!retry) + goto skip_recovery; + err = recover_fsync_data(sbi, false); if (err < 0) { need_fsck = true; @@ -1474,7 +1477,7 @@ try_onemore: goto free_kobj; } } - +skip_recovery: /* recover_fsync_data() cleared this already */ clear_sbi_flag(sbi, SBI_POR_DOING);

--- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -99,6 +99,7 @@ struct f2fs_super_block { /* * For checkpoint */ +#define CP_CRC_RECOVERY_FLAG 0x00000040 #define CP_FASTBOOT_FLAG 0x00000020 #define CP_FSCK_FLAG 0x00000010 #define CP_ERROR_FLAG 0x00000008

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jaegeuk Kim jaegeuk@kernel.org

commit 9e1e6df412a28cdbbd2909de5c6189eda4a3383d upstream.

Before checkpoint, we'd be better drop any inodes.

Signed-off-by: Jaegeuk Kim jaegeuk@kernel.org Signed-off-by: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/f2fs/recovery.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

--- a/fs/f2fs/recovery.c +++ b/fs/f2fs/recovery.c @@ -597,6 +597,9 @@ out: set_ckpt_flags(sbi->ckpt, CP_ERROR_FLAG); mutex_unlock(&sbi->cp_mutex);

+ /* let's drop all the directory inodes for clean checkpoint */ + destroy_fsync_dnodes(&dir_list); + if (!err && need_writecp) { struct cp_control cpc = { .reason = CP_RECOVERY, @@ -604,7 +607,6 @@ out: write_checkpoint(sbi, &cpc); }

- destroy_fsync_dnodes(&dir_list); kmem_cache_destroy(fsync_entry_slab); return ret ? ret: err; }

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jaegeuk Kim jaegeuk@kernel.org

commit 2040fce83fe17763b07c97c1f691da2bb85e4135 upstream.

Previous mkfs.f2fs allows small partition inappropriately, so f2fs should detect that as well.

Refer this in f2fs-tools.

mkfs.f2fs: detect small partition by overprovision ratio and # of segments

Reported-and-Tested-by: Eric Biggers ebiggers@google.com Signed-off-by: Jaegeuk Kim jaegeuk@kernel.org [bwh: Backported to 4.4: adjust context] Signed-off-by: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/f2fs/segment.h | 2 ++ fs/f2fs/super.c | 11 +++++++++++ 2 files changed, 13 insertions(+)

--- a/fs/f2fs/segment.h +++ b/fs/f2fs/segment.h @@ -17,6 +17,8 @@

#define DEF_RECLAIM_PREFREE_SEGMENTS 5 /* 5% over total segments */

+#define F2FS_MIN_SEGMENTS 9 /* SB + 2 (CP + SIT + NAT) + SSA + MAIN */ + /* L: Logical segment # in volume, R: Relative segment # in main area */ #define GET_L2R_SEGNO(free_i, segno) (segno - free_i->start_segno) #define GET_R2L_SEGNO(free_i, segno) (segno + free_i->start_segno) --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -1078,6 +1078,7 @@ int sanity_check_ckpt(struct f2fs_sb_inf unsigned int total, fsmeta; struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi); struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); + unsigned int ovp_segments, reserved_segments; unsigned int main_segs, blocks_per_seg; unsigned int sit_segs, nat_segs; unsigned int sit_bitmap_size, nat_bitmap_size; @@ -1096,6 +1097,16 @@ int sanity_check_ckpt(struct f2fs_sb_inf if (unlikely(fsmeta >= total)) return 1;

+ ovp_segments = le32_to_cpu(ckpt->overprov_segment_count); + reserved_segments = le32_to_cpu(ckpt->rsvd_segment_count); + + if (unlikely(fsmeta < F2FS_MIN_SEGMENTS || + ovp_segments == 0 || reserved_segments == 0)) { + f2fs_msg(sbi->sb, KERN_ERR, + "Wrong layout: check mkfs.f2fs version"); + return 1; + } + main_segs = le32_to_cpu(raw_super->segment_count_main); blocks_per_seg = sbi->blocks_per_seg;

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Chao Yu yuchao0@huawei.com

commit 30a61ddf8117c26ac5b295e1233eaa9629a94ca3 upstream.

In below concurrent case, allocated nid can be loaded into free nid cache and be allocated again.

Thread A Thread B - f2fs_create - f2fs_new_inode - alloc_nid - __insert_nid_to_list(ALLOC_NID_LIST) - f2fs_balance_fs_bg - build_free_nids - __build_free_nids - scan_nat_page - add_free_nid - __lookup_nat_cache - f2fs_add_link - init_inode_metadata - new_inode_page - new_node_page - set_node_addr - alloc_nid_done - __remove_nid_from_list(ALLOC_NID_LIST) - __insert_nid_to_list(FREE_NID_LIST)

This patch makes nat cache lookup and free nid list operation being atomical to avoid this race condition.

Signed-off-by: Jaegeuk Kim jaegeuk@kernel.org Signed-off-by: Chao Yu yuchao0@huawei.com Signed-off-by: Jaegeuk Kim jaegeuk@kernel.org [bwh: Backported to 4.4: - add_free_nid() returns 0 in case of any error (except low memory) - Tree/list addition has not been moved into __insert_nid_to_list()] Signed-off-by: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/f2fs/node.c | 62 +++++++++++++++++++++++++++++++++++++++------------------ 1 file changed, 43 insertions(+), 19 deletions(-)

--- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -1428,8 +1428,9 @@ static void __del_from_free_nid_list(str static int add_free_nid(struct f2fs_sb_info *sbi, nid_t nid, bool build) { struct f2fs_nm_info *nm_i = NM_I(sbi); - struct free_nid *i; + struct free_nid *i, *e; struct nat_entry *ne; + int err = -EINVAL;

if (!available_free_memory(sbi, FREE_NIDS)) return -1; @@ -1438,35 +1439,58 @@ static int add_free_nid(struct f2fs_sb_i if (unlikely(nid == 0)) return 0;

- if (build) { - /* do not add allocated nids */ - ne = __lookup_nat_cache(nm_i, nid); - if (ne && (!get_nat_flag(ne, IS_CHECKPOINTED) || - nat_get_blkaddr(ne) != NULL_ADDR)) - return 0; - } - i = f2fs_kmem_cache_alloc(free_nid_slab, GFP_NOFS); i->nid = nid; i->state = NID_NEW;

- if (radix_tree_preload(GFP_NOFS)) { - kmem_cache_free(free_nid_slab, i); - return 0; - } + if (radix_tree_preload(GFP_NOFS)) + goto err;

spin_lock(&nm_i->free_nid_list_lock); - if (radix_tree_insert(&nm_i->free_nid_root, i->nid, i)) { - spin_unlock(&nm_i->free_nid_list_lock); - radix_tree_preload_end(); - kmem_cache_free(free_nid_slab, i); - return 0; + + if (build) { + /* + * Thread A Thread B + * - f2fs_create + * - f2fs_new_inode + * - alloc_nid + * - __insert_nid_to_list(ALLOC_NID_LIST) + * - f2fs_balance_fs_bg + * - build_free_nids + * - __build_free_nids + * - scan_nat_page + * - add_free_nid + * - __lookup_nat_cache + * - f2fs_add_link + * - init_inode_metadata + * - new_inode_page + * - new_node_page + * - set_node_addr + * - alloc_nid_done + * - __remove_nid_from_list(ALLOC_NID_LIST) + * - __insert_nid_to_list(FREE_NID_LIST) + */ + ne = __lookup_nat_cache(nm_i, nid); + if (ne && (!get_nat_flag(ne, IS_CHECKPOINTED) || + nat_get_blkaddr(ne) != NULL_ADDR)) + goto err_out; + + e = __lookup_free_nid_list(nm_i, nid); + if (e) + goto err_out; } + if (radix_tree_insert(&nm_i->free_nid_root, i->nid, i)) + goto err_out; + err = 0; list_add_tail(&i->list, &nm_i->free_nid_list); nm_i->fcnt++; +err_out: spin_unlock(&nm_i->free_nid_list_lock); radix_tree_preload_end(); - return 1; +err: + if (err) + kmem_cache_free(free_nid_slab, i); + return !err; }

static void remove_free_nid(struct f2fs_nm_info *nm_i, nid_t nid)

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Yunlei He heyunlei@huawei.com

commit 0833721ec3658a4e9d5e58b6fa82cf9edc431e59 upstream.

This patch check blkaddr more accuratly before issue a write or read bio.

Signed-off-by: Yunlei He heyunlei@huawei.com Reviewed-by: Chao Yu yuchao0@huawei.com Signed-off-by: Jaegeuk Kim jaegeuk@kernel.org [bwh: Backported to 4.4: - CoW is not implemented so check f2fs_io_info::blk_addr instead of f2fs_io_info::{old,new}_blkaddr - Operation code is f2fs_io_info::rw instead of f2fs_io_info::op - Adjust context] Signed-off-by: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/f2fs/checkpoint.c | 2 ++ fs/f2fs/data.c | 3 ++- fs/f2fs/f2fs.h | 1 + fs/f2fs/segment.h | 25 +++++++++++++++++++------ 4 files changed, 24 insertions(+), 7 deletions(-)

--- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -58,6 +58,7 @@ static struct page *__get_meta_page(stru .rw = READ_SYNC | REQ_META | REQ_PRIO, .blk_addr = index, .encrypted_page = NULL, + .is_meta = is_meta, };

if (unlikely(!is_meta)) @@ -151,6 +152,7 @@ int ra_meta_pages(struct f2fs_sb_info *s .type = META, .rw = sync ? (READ_SYNC | REQ_META | REQ_PRIO) : READA, .encrypted_page = NULL, + .is_meta = (type != META_POR), };

if (unlikely(type == META_POR)) --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -147,6 +147,7 @@ int f2fs_submit_page_bio(struct f2fs_io_ struct bio *bio; struct page *page = fio->encrypted_page ? fio->encrypted_page : fio->page;

+ verify_block_addr(fio, fio->blk_addr); trace_f2fs_submit_page_bio(page, fio); f2fs_trace_ios(fio, 0);

@@ -172,7 +173,7 @@ void f2fs_submit_page_mbio(struct f2fs_i

io = is_read ? &sbi->read_io : &sbi->write_io[btype];

- verify_block_addr(sbi, fio->blk_addr); + verify_block_addr(fio, fio->blk_addr);

down_write(&io->io_rwsem);

--- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -684,6 +684,7 @@ struct f2fs_io_info { block_t blk_addr; /* block address to be written */ struct page *page; /* page to be written */ struct page *encrypted_page; /* encrypted page */ + bool is_meta; /* indicate borrow meta inode mapping or not */ };

#define is_read_io(rw) (((rw) & 1) == READ) --- a/fs/f2fs/segment.h +++ b/fs/f2fs/segment.h @@ -48,13 +48,19 @@ (secno == CURSEG_I(sbi, CURSEG_COLD_NODE)->segno / \ sbi->segs_per_sec)) \

-#define MAIN_BLKADDR(sbi) (SM_I(sbi)->main_blkaddr) -#define SEG0_BLKADDR(sbi) (SM_I(sbi)->seg0_blkaddr) +#define MAIN_BLKADDR(sbi) \ + (SM_I(sbi) ? SM_I(sbi)->main_blkaddr : \ + le32_to_cpu(F2FS_RAW_SUPER(sbi)->main_blkaddr)) +#define SEG0_BLKADDR(sbi) \ + (SM_I(sbi) ? SM_I(sbi)->seg0_blkaddr : \ + le32_to_cpu(F2FS_RAW_SUPER(sbi)->segment0_blkaddr))

#define MAIN_SEGS(sbi) (SM_I(sbi)->main_segments) #define MAIN_SECS(sbi) (sbi->total_sections)

-#define TOTAL_SEGS(sbi) (SM_I(sbi)->segment_count) +#define TOTAL_SEGS(sbi) \ + (SM_I(sbi) ? SM_I(sbi)->segment_count : \ + le32_to_cpu(F2FS_RAW_SUPER(sbi)->segment_count)) #define TOTAL_BLKS(sbi) (TOTAL_SEGS(sbi) << sbi->log_blocks_per_seg)

#define MAX_BLKADDR(sbi) (SEG0_BLKADDR(sbi) + TOTAL_BLKS(sbi)) @@ -576,10 +582,17 @@ static inline void check_seg_range(struc f2fs_bug_on(sbi, segno > TOTAL_SEGS(sbi) - 1); }

-static inline void verify_block_addr(struct f2fs_sb_info *sbi, block_t blk_addr) +static inline void verify_block_addr(struct f2fs_io_info *fio, block_t blk_addr) { - BUG_ON(blk_addr < SEG0_BLKADDR(sbi) - || blk_addr >= MAX_BLKADDR(sbi)); + struct f2fs_sb_info *sbi = fio->sbi; + + if (PAGE_TYPE_OF_BIO(fio->type) == META && + (!is_read_io(fio->rw) || fio->is_meta)) + BUG_ON(blk_addr < SEG0_BLKADDR(sbi) || + blk_addr >= MAIN_BLKADDR(sbi)); + else + BUG_ON(blk_addr < MAIN_BLKADDR(sbi) || + blk_addr >= MAX_BLKADDR(sbi)); }

/*

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jaegeuk Kim jaegeuk@kernel.org

commit 0cfe75c5b011994651a4ca6d74f20aa997bfc69a upstream.

In order to avoid the below overflow issue, we should have checked the boundaries in superblock before reaching out to allocation. As Linus suggested, the right place should be sanity_check_raw_super().

Dr Silvio Cesare of InfoSect reported:

There are integer overflows with using the cp_payload superblock field in the f2fs filesystem potentially leading to memory corruption.

include/linux/f2fs_fs.h

struct f2fs_super_block { ... __le32 cp_payload;

fs/f2fs/f2fs.h

typedef u32 block_t; /* * should not change u32, since it is the on-disk block * address format, __le32. */ ...

static inline block_t __cp_payload(struct f2fs_sb_info *sbi) { return le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_payload); }

fs/f2fs/checkpoint.c

block_t start_blk, orphan_blocks, i, j; ... start_blk = __start_cp_addr(sbi) + 1 + __cp_payload(sbi); orphan_blocks = __start_sum_addr(sbi) - 1 - __cp_payload(sbi);

+++ integer overflows

... unsigned int cp_blks = 1 + __cp_payload(sbi); ... sbi->ckpt = kzalloc(cp_blks * blk_size, GFP_KERNEL);

+++ integer overflow leading to incorrect heap allocation.

int cp_payload_blks = __cp_payload(sbi); ... ckpt->cp_pack_start_sum = cpu_to_le32(1 + cp_payload_blks + orphan_blocks);

+++ sign bug and integer overflow

... for (i = 1; i < 1 + cp_payload_blks; i++)

+++ integer overflow

...

sbi->max_orphans = (sbi->blocks_per_seg - F2FS_CP_PACKS - NR_CURSEG_TYPE - __cp_payload(sbi)) * F2FS_ORPHANS_PER_BLOCK;

+++ integer overflow

Reported-by: Greg KH greg@kroah.com Reported-by: Silvio Cesare silvio.cesare@gmail.com Suggested-by: Linus Torvalds torvalds@linux-foundation.org Reviewed-by: Chao Yu yuchao0@huawei.com Signed-off-by: Jaegeuk Kim jaegeuk@kernel.org [bwh: Backported to 4.4: - No hot file extension support - Adjust context] Signed-off-by: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/f2fs/super.c | 71 ++++++++++++++++++++++++++++++++++++++++++++++++++------ 1 file changed, 64 insertions(+), 7 deletions(-)

--- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -994,6 +994,8 @@ static inline bool sanity_check_area_bou static int sanity_check_raw_super(struct super_block *sb, struct f2fs_super_block *raw_super) { + block_t segment_count, segs_per_sec, secs_per_zone; + block_t total_sections, blocks_per_seg; unsigned int blocksize;

if (F2FS_SUPER_MAGIC != le32_to_cpu(raw_super->magic)) { @@ -1047,6 +1049,68 @@ static int sanity_check_raw_super(struct return 1; }

+ segment_count = le32_to_cpu(raw_super->segment_count); + segs_per_sec = le32_to_cpu(raw_super->segs_per_sec); + secs_per_zone = le32_to_cpu(raw_super->secs_per_zone); + total_sections = le32_to_cpu(raw_super->section_count); + + /* blocks_per_seg should be 512, given the above check */ + blocks_per_seg = 1 << le32_to_cpu(raw_super->log_blocks_per_seg); + + if (segment_count > F2FS_MAX_SEGMENT || + segment_count < F2FS_MIN_SEGMENTS) { + f2fs_msg(sb, KERN_INFO, + "Invalid segment count (%u)", + segment_count); + return 1; + } + + if (total_sections > segment_count || + total_sections < F2FS_MIN_SEGMENTS || + segs_per_sec > segment_count || !segs_per_sec) { + f2fs_msg(sb, KERN_INFO, + "Invalid segment/section count (%u, %u x %u)", + segment_count, total_sections, segs_per_sec); + return 1; + } + + if ((segment_count / segs_per_sec) < total_sections) { + f2fs_msg(sb, KERN_INFO, + "Small segment_count (%u < %u * %u)", + segment_count, segs_per_sec, total_sections); + return 1; + } + + if (segment_count > (le32_to_cpu(raw_super->block_count) >> 9)) { + f2fs_msg(sb, KERN_INFO, + "Wrong segment_count / block_count (%u > %u)", + segment_count, le32_to_cpu(raw_super->block_count)); + return 1; + } + + if (secs_per_zone > total_sections) { + f2fs_msg(sb, KERN_INFO, + "Wrong secs_per_zone (%u > %u)", + secs_per_zone, total_sections); + return 1; + } + if (le32_to_cpu(raw_super->extension_count) > F2FS_MAX_EXTENSION) { + f2fs_msg(sb, KERN_INFO, + "Corrupted extension count (%u > %u)", + le32_to_cpu(raw_super->extension_count), + F2FS_MAX_EXTENSION); + return 1; + } + + if (le32_to_cpu(raw_super->cp_payload) > + (blocks_per_seg - F2FS_CP_PACKS)) { + f2fs_msg(sb, KERN_INFO, + "Insane cp_payload (%u > %u)", + le32_to_cpu(raw_super->cp_payload), + blocks_per_seg - F2FS_CP_PACKS); + return 1; + } + /* check reserved ino info */ if (le32_to_cpu(raw_super->node_ino) != 1 || le32_to_cpu(raw_super->meta_ino) != 2 || @@ -1059,13 +1123,6 @@ static int sanity_check_raw_super(struct return 1; }

- if (le32_to_cpu(raw_super->segment_count) > F2FS_MAX_SEGMENT) { - f2fs_msg(sb, KERN_INFO, - "Invalid segment count (%u)", - le32_to_cpu(raw_super->segment_count)); - return 1; - } - /* check CP/SIT/NAT/SSA/MAIN_AREA area boundary */ if (sanity_check_area_boundary(sb, raw_super)) return 1;

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Chao Yu yuchao0@huawei.com

commit e1da7872f6eda977bd812346bf588c35e4495a1e upstream.

This patch introduces verify_blkaddr to check meta/data block address with valid range to detect bug earlier.

In addition, once we encounter an invalid blkaddr, notice user to run fsck to fix, and let the kernel panic.

Signed-off-by: Chao Yu yuchao0@huawei.com Signed-off-by: Jaegeuk Kim jaegeuk@kernel.org [bwh: Backported to 4.4: - I skipped an earlier renaming of is_valid_meta_blkaddr() to f2fs_is_valid_meta_blkaddr() - Drop inapplicable change to check on f2fs_fio_info::old_blkaddr - Adjust context] Signed-off-by: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/f2fs/checkpoint.c | 11 +++++++++-- fs/f2fs/data.c | 4 ++-- fs/f2fs/f2fs.h | 32 +++++++++++++++++++++++++++++--- fs/f2fs/file.c | 9 +++++---- fs/f2fs/inode.c | 7 ++++--- fs/f2fs/node.c | 4 ++-- fs/f2fs/recovery.c | 6 +++--- fs/f2fs/segment.c | 4 ++-- fs/f2fs/segment.h | 8 +++----- 9 files changed, 59 insertions(+), 26 deletions(-)

--- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -107,7 +107,8 @@ struct page *get_tmp_page(struct f2fs_sb return __get_meta_page(sbi, index, false); }

-bool is_valid_meta_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr, int type) +bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi, + block_t blkaddr, int type) { switch (type) { case META_NAT: @@ -127,10 +128,16 @@ bool is_valid_meta_blkaddr(struct f2fs_s return false; break; case META_POR: + case DATA_GENERIC: if (unlikely(blkaddr >= MAX_BLKADDR(sbi) || blkaddr < MAIN_BLKADDR(sbi))) return false; break; + case META_GENERIC: + if (unlikely(blkaddr < SEG0_BLKADDR(sbi) || + blkaddr >= MAIN_BLKADDR(sbi))) + return false; + break; default: BUG(); } @@ -160,7 +167,7 @@ int ra_meta_pages(struct f2fs_sb_info *s

for (; nrpages-- > 0; blkno++) {

- if (!is_valid_meta_blkaddr(sbi, blkno, type)) + if (!f2fs_is_valid_blkaddr(sbi, blkno, type)) goto out;

switch (type) { --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -604,7 +604,7 @@ static int f2fs_map_blocks(struct inode goto unlock_out; }

- if (!is_valid_blkaddr(dn.data_blkaddr)) { + if (!is_valid_data_blkaddr(sbi, dn.data_blkaddr)) { if (create) { if (unlikely(f2fs_cp_error(sbi))) { err = -EIO; @@ -1090,7 +1090,7 @@ int do_write_data_page(struct f2fs_io_in * If current allocation needs SSR, * it had better in-place writes for updated data. */ - if (unlikely(is_valid_blkaddr(fio->blk_addr) && + if (unlikely(is_valid_data_blkaddr(fio->sbi, fio->blk_addr) && !is_cold_data(page) && need_inplace_update(inode))) { rewrite_data_page(fio); --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -135,7 +135,7 @@ struct cp_control { };

/* - * For CP/NAT/SIT/SSA readahead + * indicate meta/data type */ enum { META_CP, @@ -143,6 +143,8 @@ enum { META_SIT, META_SSA, META_POR, + DATA_GENERIC, + META_GENERIC, };

/* for the list of ino */ @@ -1647,13 +1649,36 @@ static inline void *f2fs_kvzalloc(size_t (pgofs - ADDRS_PER_INODE(fi) + ADDRS_PER_BLOCK) / \ ADDRS_PER_BLOCK * ADDRS_PER_BLOCK + ADDRS_PER_INODE(fi))

-static inline bool is_valid_blkaddr(block_t blkaddr) +bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi, + block_t blkaddr, int type); +void f2fs_msg(struct super_block *sb, const char *level, const char *fmt, ...); +static inline void verify_blkaddr(struct f2fs_sb_info *sbi, + block_t blkaddr, int type) +{ + if (!f2fs_is_valid_blkaddr(sbi, blkaddr, type)) { + f2fs_msg(sbi->sb, KERN_ERR, + "invalid blkaddr: %u, type: %d, run fsck to fix.", + blkaddr, type); + f2fs_bug_on(sbi, 1); + } +} + +static inline bool __is_valid_data_blkaddr(block_t blkaddr) { if (blkaddr == NEW_ADDR || blkaddr == NULL_ADDR) return false; return true; }

+static inline bool is_valid_data_blkaddr(struct f2fs_sb_info *sbi, + block_t blkaddr) +{ + if (!__is_valid_data_blkaddr(blkaddr)) + return false; + verify_blkaddr(sbi, blkaddr, DATA_GENERIC); + return true; +} + /* * file.c */ @@ -1825,7 +1850,8 @@ void destroy_segment_manager_caches(void struct page *grab_meta_page(struct f2fs_sb_info *, pgoff_t); struct page *get_meta_page(struct f2fs_sb_info *, pgoff_t); struct page *get_tmp_page(struct f2fs_sb_info *, pgoff_t); -bool is_valid_meta_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr, int type); +bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi, + block_t blkaddr, int type); int ra_meta_pages(struct f2fs_sb_info *, block_t, int, int, bool); void ra_meta_pages_cond(struct f2fs_sb_info *, pgoff_t); long sync_meta_pages(struct f2fs_sb_info *, enum page_type, long); --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -305,13 +305,13 @@ static pgoff_t __get_first_dirty_index(s return pgofs; }

-static bool __found_offset(block_t blkaddr, pgoff_t dirty, pgoff_t pgofs, - int whence) +static bool __found_offset(struct f2fs_sb_info *sbi, block_t blkaddr, + pgoff_t dirty, pgoff_t pgofs, int whence) { switch (whence) { case SEEK_DATA: if ((blkaddr == NEW_ADDR && dirty == pgofs) || - is_valid_blkaddr(blkaddr)) + is_valid_data_blkaddr(sbi, blkaddr)) return true; break; case SEEK_HOLE: @@ -374,7 +374,8 @@ static loff_t f2fs_seek_block(struct fil block_t blkaddr; blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node);

- if (__found_offset(blkaddr, dirty, pgofs, whence)) { + if (__found_offset(F2FS_I_SB(inode), blkaddr, dirty, + pgofs, whence)) { f2fs_put_dnode(&dn); goto found; } --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -50,11 +50,12 @@ static void __get_inode_rdev(struct inod } }

-static bool __written_first_block(struct f2fs_inode *ri) +static bool __written_first_block(struct f2fs_sb_info *sbi, + struct f2fs_inode *ri) { block_t addr = le32_to_cpu(ri->i_addr[0]);

- if (is_valid_blkaddr(addr)) + if (is_valid_data_blkaddr(sbi, addr)) return true; return false; } @@ -149,7 +150,7 @@ static int do_read_inode(struct inode *i /* get rdev by using inline_info */ __get_inode_rdev(inode, ri);

- if (__written_first_block(ri)) + if (__written_first_block(sbi, ri)) set_inode_flag(F2FS_I(inode), FI_FIRST_BLOCK_WRITTEN);

f2fs_put_page(node_page, 1); --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -296,7 +296,7 @@ static void set_node_addr(struct f2fs_sb new_blkaddr == NULL_ADDR); f2fs_bug_on(sbi, nat_get_blkaddr(e) == NEW_ADDR && new_blkaddr == NEW_ADDR); - f2fs_bug_on(sbi, is_valid_blkaddr(nat_get_blkaddr(e)) && + f2fs_bug_on(sbi, is_valid_data_blkaddr(sbi, nat_get_blkaddr(e)) && new_blkaddr == NEW_ADDR);

/* increment version no as node is removed */ @@ -311,7 +311,7 @@ static void set_node_addr(struct f2fs_sb

/* change address */ nat_set_blkaddr(e, new_blkaddr); - if (!is_valid_blkaddr(new_blkaddr)) + if (!is_valid_data_blkaddr(sbi, new_blkaddr)) set_nat_flag(e, IS_CHECKPOINTED, false); __set_nat_cache_dirty(nm_i, e);

--- a/fs/f2fs/recovery.c +++ b/fs/f2fs/recovery.c @@ -208,7 +208,7 @@ static int find_fsync_dnodes(struct f2fs while (1) { struct fsync_inode_entry *entry;

- if (!is_valid_meta_blkaddr(sbi, blkaddr, META_POR)) + if (!f2fs_is_valid_blkaddr(sbi, blkaddr, META_POR)) return 0;

page = get_tmp_page(sbi, blkaddr); @@ -443,7 +443,7 @@ static int do_recover_data(struct f2fs_s }

/* dest is valid block, try to recover from src to dest */ - if (is_valid_meta_blkaddr(sbi, dest, META_POR)) { + if (f2fs_is_valid_blkaddr(sbi, dest, META_POR)) {

if (src == NULL_ADDR) { err = reserve_new_block(&dn); @@ -494,7 +494,7 @@ static int recover_data(struct f2fs_sb_i while (1) { struct fsync_inode_entry *entry;

- if (!is_valid_meta_blkaddr(sbi, blkaddr, META_POR)) + if (!f2fs_is_valid_blkaddr(sbi, blkaddr, META_POR)) break;

ra_meta_pages_cond(sbi, blkaddr); --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -752,7 +752,7 @@ bool is_checkpointed_data(struct f2fs_sb struct seg_entry *se; bool is_cp = false;

- if (!is_valid_blkaddr(blkaddr)) + if (!is_valid_data_blkaddr(sbi, blkaddr)) return true;

mutex_lock(&sit_i->sentry_lock); @@ -1466,7 +1466,7 @@ void f2fs_wait_on_encrypted_page_writeba { struct page *cpage;

- if (!is_valid_blkaddr(blkaddr)) + if (!is_valid_data_blkaddr(sbi, blkaddr)) return;

f2fs_bug_on(sbi, blkaddr == NULL_ADDR); --- a/fs/f2fs/segment.h +++ b/fs/f2fs/segment.h @@ -80,7 +80,7 @@ (GET_SEGOFF_FROM_SEG0(sbi, blk_addr) & (sbi->blocks_per_seg - 1))

#define GET_SEGNO(sbi, blk_addr) \ - ((!is_valid_blkaddr(blk_addr)) ? \ + ((!is_valid_data_blkaddr(sbi, blk_addr)) ? \ NULL_SEGNO : GET_L2R_SEGNO(FREE_I(sbi), \ GET_SEGNO_FROM_SEG0(sbi, blk_addr))) #define GET_SECNO(sbi, segno) \ @@ -588,11 +588,9 @@ static inline void verify_block_addr(str

if (PAGE_TYPE_OF_BIO(fio->type) == META && (!is_read_io(fio->rw) || fio->is_meta)) - BUG_ON(blk_addr < SEG0_BLKADDR(sbi) || - blk_addr >= MAIN_BLKADDR(sbi)); + verify_blkaddr(sbi, blk_addr, META_GENERIC); else - BUG_ON(blk_addr < MAIN_BLKADDR(sbi) || - blk_addr >= MAX_BLKADDR(sbi)); + verify_blkaddr(sbi, blk_addr, DATA_GENERIC); }

/*

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Chao Yu yuchao0@huawei.com

commit 9dc956b2c8523aed39d1e6508438be9fea28c8fc upstream.

This patch fixs to do sanity check with user_block_count.

- Overview Divide zero in utilization when mount() a corrupted f2fs image

- Reproduce (4.18 upstream kernel)

- Kernel message [ 564.099503] F2FS-fs (loop0): invalid crc value [ 564.101991] divide error: 0000 [#1] SMP KASAN PTI [ 564.103103] CPU: 1 PID: 1298 Comm: f2fs_discard-7: Not tainted 4.18.0-rc1+ #4 [ 564.104584] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 564.106624] RIP: 0010:issue_discard_thread+0x248/0x5c0 [ 564.107692] Code: ff ff 48 8b bd e8 fe ff ff 41 8b 9d 4c 04 00 00 e8 cd b8 ad ff 41 8b 85 50 04 00 00 31 d2 48 8d 04 80 48 8d 04 80 48 c1 e0 02 <48> f7 f3 83 f8 50 7e 16 41 c7 86 7c ff ff ff 01 00 00 00 41 c7 86 [ 564.111686] RSP: 0018:ffff8801f3117dc0 EFLAGS: 00010206 [ 564.112775] RAX: 0000000000000384 RBX: 0000000000000000 RCX: ffffffffb88c1e03 [ 564.114250] RDX: 0000000000000000 RSI: dffffc0000000000 RDI: ffff8801e3aa4850 [ 564.115706] RBP: ffff8801f3117f00 R08: 1ffffffff751a1d0 R09: fffffbfff751a1d0 [ 564.117177] R10: 0000000000000001 R11: fffffbfff751a1d0 R12: 00000000fffffffc [ 564.118634] R13: ffff8801e3aa4400 R14: ffff8801f3117ed8 R15: ffff8801e2050000 [ 564.120094] FS: 0000000000000000(0000) GS:ffff8801f6f00000(0000) knlGS:0000000000000000 [ 564.121748] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 564.122923] CR2: 000000000202b078 CR3: 00000001f11ac000 CR4: 00000000000006e0 [ 564.124383] Call Trace: [ 564.124924] ? __issue_discard_cmd+0x480/0x480 [ 564.125882] ? __sched_text_start+0x8/0x8 [ 564.126756] ? __kthread_parkme+0xcb/0x100 [ 564.127620] ? kthread_blkcg+0x70/0x70 [ 564.128412] kthread+0x180/0x1d0 [ 564.129105] ? __issue_discard_cmd+0x480/0x480 [ 564.130029] ? kthread_associate_blkcg+0x150/0x150 [ 564.131033] ret_from_fork+0x35/0x40 [ 564.131794] Modules linked in: snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_pcm snd_timer snd mac_hid i2c_piix4 soundcore ib_iser rdma_cm iw_cm ib_cm ib_core iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi raid10 raid456 async_raid6_recov async_memcpy async_pq async_xor async_tx raid1 raid0 multipath linear 8139too crct10dif_pclmul crc32_pclmul qxl drm_kms_helper syscopyarea aesni_intel sysfillrect sysimgblt fb_sys_fops ttm drm aes_x86_64 crypto_simd cryptd 8139cp glue_helper mii pata_acpi floppy [ 564.141798] ---[ end trace 4ce02f25ff7d3df5 ]--- [ 564.142773] RIP: 0010:issue_discard_thread+0x248/0x5c0 [ 564.143885] Code: ff ff 48 8b bd e8 fe ff ff 41 8b 9d 4c 04 00 00 e8 cd b8 ad ff 41 8b 85 50 04 00 00 31 d2 48 8d 04 80 48 8d 04 80 48 c1 e0 02 <48> f7 f3 83 f8 50 7e 16 41 c7 86 7c ff ff ff 01 00 00 00 41 c7 86 [ 564.147776] RSP: 0018:ffff8801f3117dc0 EFLAGS: 00010206 [ 564.148856] RAX: 0000000000000384 RBX: 0000000000000000 RCX: ffffffffb88c1e03 [ 564.150424] RDX: 0000000000000000 RSI: dffffc0000000000 RDI: ffff8801e3aa4850 [ 564.151906] RBP: ffff8801f3117f00 R08: 1ffffffff751a1d0 R09: fffffbfff751a1d0 [ 564.153463] R10: 0000000000000001 R11: fffffbfff751a1d0 R12: 00000000fffffffc [ 564.154915] R13: ffff8801e3aa4400 R14: ffff8801f3117ed8 R15: ffff8801e2050000 [ 564.156405] FS: 0000000000000000(0000) GS:ffff8801f6f00000(0000) knlGS:0000000000000000 [ 564.158070] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 564.159279] CR2: 000000000202b078 CR3: 00000001f11ac000 CR4: 00000000000006e0 [ 564.161043] ================================================================== [ 564.162587] BUG: KASAN: stack-out-of-bounds in from_kuid_munged+0x1d/0x50 [ 564.163994] Read of size 4 at addr ffff8801f3117c84 by task f2fs_discard-7:/1298

[ 564.165852] CPU: 1 PID: 1298 Comm: f2fs_discard-7: Tainted: G D 4.18.0-rc1+ #4 [ 564.167593] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 564.169522] Call Trace: [ 564.170057] dump_stack+0x7b/0xb5 [ 564.170778] print_address_description+0x70/0x290 [ 564.171765] kasan_report+0x291/0x390 [ 564.172540] ? from_kuid_munged+0x1d/0x50 [ 564.173408] __asan_load4+0x78/0x80 [ 564.174148] from_kuid_munged+0x1d/0x50 [ 564.174962] do_notify_parent+0x1f5/0x4f0 [ 564.175808] ? send_sigqueue+0x390/0x390 [ 564.176639] ? css_set_move_task+0x152/0x340 [ 564.184197] do_exit+0x1290/0x1390 [ 564.184950] ? __issue_discard_cmd+0x480/0x480 [ 564.185884] ? mm_update_next_owner+0x380/0x380 [ 564.186829] ? __sched_text_start+0x8/0x8 [ 564.187672] ? __kthread_parkme+0xcb/0x100 [ 564.188528] ? kthread_blkcg+0x70/0x70 [ 564.189333] ? kthread+0x180/0x1d0 [ 564.190052] ? __issue_discard_cmd+0x480/0x480 [ 564.190983] rewind_stack_do_exit+0x17/0x20

[ 564.192190] The buggy address belongs to the page: [ 564.193213] page:ffffea0007cc45c0 count:0 mapcount:0 mapping:0000000000000000 index:0x0 [ 564.194856] flags: 0x2ffff0000000000() [ 564.195644] raw: 02ffff0000000000 0000000000000000 dead000000000200 0000000000000000 [ 564.197247] raw: 0000000000000000 0000000000000000 00000000ffffffff 0000000000000000 [ 564.198826] page dumped because: kasan: bad access detected

[ 564.200299] Memory state around the buggy address: [ 564.201306] ffff8801f3117b80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 564.202779] ffff8801f3117c00: 00 00 00 00 00 00 00 00 00 00 00 f3 f3 f3 f3 f3 [ 564.204252] >ffff8801f3117c80: f3 f3 f3 00 00 00 00 00 00 00 00 00 f1 f1 f1 f1 [ 564.205742] ^ [ 564.206424] ffff8801f3117d00: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 564.207908] ffff8801f3117d80: f3 f3 f3 f3 f3 f3 f3 f3 00 00 00 00 00 00 00 00 [ 564.209389] ================================================================== [ 564.231795] F2FS-fs (loop0): Mounted with checkpoint version = 2

- Location https://elixir.bootlin.com/linux/v4.18-rc1/source/fs/f2fs/segment.h#L586 return div_u64((u64)valid_user_blocks(sbi) * 100, sbi->user_block_count); Missing checks on sbi->user_block_count.

Reported-by: Wen Xu wen.xu@gatech.edu Signed-off-by: Chao Yu yuchao0@huawei.com Signed-off-by: Jaegeuk Kim jaegeuk@kernel.org Signed-off-by: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/f2fs/super.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-)

--- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -1140,6 +1140,8 @@ int sanity_check_ckpt(struct f2fs_sb_inf unsigned int sit_segs, nat_segs; unsigned int sit_bitmap_size, nat_bitmap_size; unsigned int log_blocks_per_seg; + unsigned int segment_count_main; + block_t user_block_count; int i;

total = le32_to_cpu(raw_super->segment_count); @@ -1164,6 +1166,16 @@ int sanity_check_ckpt(struct f2fs_sb_inf return 1; }

+ user_block_count = le64_to_cpu(ckpt->user_block_count); + segment_count_main = le32_to_cpu(raw_super->segment_count_main); + log_blocks_per_seg = le32_to_cpu(raw_super->log_blocks_per_seg); + if (!user_block_count || user_block_count >= + segment_count_main << log_blocks_per_seg) { + f2fs_msg(sbi->sb, KERN_ERR, + "Wrong user_block_count: %u", user_block_count); + return 1; + } + main_segs = le32_to_cpu(raw_super->segment_count_main); blocks_per_seg = sbi->blocks_per_seg;

@@ -1180,7 +1192,6 @@ int sanity_check_ckpt(struct f2fs_sb_inf

sit_bitmap_size = le32_to_cpu(ckpt->sit_ver_bitmap_bytesize); nat_bitmap_size = le32_to_cpu(ckpt->nat_ver_bitmap_bytesize); - log_blocks_per_seg = le32_to_cpu(raw_super->log_blocks_per_seg);

if (sit_bitmap_size != ((sit_segs / 2) << log_blocks_per_seg) / 8 || nat_bitmap_size != ((nat_segs / 2) << log_blocks_per_seg) / 8) {

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Chao Yu yuchao0@huawei.com

commit e34438c903b653daca2b2a7de95aed46226f8ed3 upstream.

This patch adds to do sanity check with below fields of inode to avoid reported panic. - node footer - iblocks

https://bugzilla.kernel.org/show_bug.cgi?id=200223

- Overview BUG() triggered in f2fs_truncate_inode_blocks() when un-mounting a mounted f2fs image after writing to it

- Reproduce

- POC (poc.c)

static void activity(char *mpoint) {

char *foo_bar_baz; int err;

static int buf[8192]; memset(buf, 0, sizeof(buf));

err = asprintf(&foo_bar_baz, "%s/foo/bar/baz", mpoint);

// open / write / read int fd = open(foo_bar_baz, O_RDWR | O_TRUNC, 0777); if (fd >= 0) { write(fd, (char *)buf, 517); write(fd, (char *)buf, sizeof(buf)); close(fd); }

}

int main(int argc, char *argv[]) { activity(argv[1]); return 0; }

- Kernel meesage [ 552.479723] F2FS-fs (loop0): Mounted with checkpoint version = 2 [ 556.451891] ------------[ cut here ]------------ [ 556.451899] kernel BUG at fs/f2fs/node.c:987! [ 556.452920] invalid opcode: 0000 [#1] SMP KASAN PTI [ 556.453936] CPU: 1 PID: 1310 Comm: umount Not tainted 4.18.0-rc1+ #4 [ 556.455213] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 556.457140] RIP: 0010:f2fs_truncate_inode_blocks+0x4a7/0x6f0 [ 556.458280] Code: e8 ae ea ff ff 41 89 c7 c1 e8 1f 84 c0 74 0a 41 83 ff fe 0f 85 35 ff ff ff 81 85 b0 fe ff ff fb 03 00 00 e9 f7 fd ff ff 0f 0b <0f> 0b e8 62 b7 9a 00 48 8b bd a0 fe ff ff e8 56 54 ae ff 48 8b b5 [ 556.462015] RSP: 0018:ffff8801f292f808 EFLAGS: 00010286 [ 556.463068] RAX: ffffed003e73242d RBX: ffff8801f292f958 RCX: ffffffffb88b81bc [ 556.464479] RDX: 0000000000000000 RSI: 0000000000000004 RDI: ffff8801f3992164 [ 556.465901] RBP: ffff8801f292f980 R08: ffffed003e73242d R09: ffffed003e73242d [ 556.467311] R10: 0000000000000001 R11: ffffed003e73242c R12: 00000000fffffc64 [ 556.468706] R13: ffff8801f3992000 R14: 0000000000000058 R15: 00000000ffff8801 [ 556.470117] FS: 00007f8029297840(0000) GS:ffff8801f6f00000(0000) knlGS:0000000000000000 [ 556.471702] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 556.472838] CR2: 000055f5f57305d8 CR3: 00000001f18b0000 CR4: 00000000000006e0 [ 556.474265] Call Trace: [ 556.474782] ? f2fs_alloc_nid_failed+0xf0/0xf0 [ 556.475686] ? truncate_nodes+0x980/0x980 [ 556.476516] ? pagecache_get_page+0x21f/0x2f0 [ 556.477412] ? __asan_loadN+0xf/0x20 [ 556.478153] ? __get_node_page+0x331/0x5b0 [ 556.478992] ? reweight_entity+0x1e6/0x3b0 [ 556.479826] f2fs_truncate_blocks+0x55e/0x740 [ 556.480709] ? f2fs_truncate_data_blocks+0x20/0x20 [ 556.481689] ? __radix_tree_lookup+0x34/0x160 [ 556.482630] ? radix_tree_lookup+0xd/0x10 [ 556.483445] f2fs_truncate+0xd4/0x1a0 [ 556.484206] f2fs_evict_inode+0x5ce/0x630 [ 556.485032] evict+0x16f/0x290 [ 556.485664] iput+0x280/0x300 [ 556.486300] dentry_unlink_inode+0x165/0x1e0 [ 556.487169] __dentry_kill+0x16a/0x260 [ 556.487936] dentry_kill+0x70/0x250 [ 556.488651] shrink_dentry_list+0x125/0x260 [ 556.489504] shrink_dcache_parent+0xc1/0x110 [ 556.490379] ? shrink_dcache_sb+0x200/0x200 [ 556.491231] ? bit_wait_timeout+0xc0/0xc0 [ 556.492047] do_one_tree+0x12/0x40 [ 556.492743] shrink_dcache_for_umount+0x3f/0xa0 [ 556.493656] generic_shutdown_super+0x43/0x1c0 [ 556.494561] kill_block_super+0x52/0x80 [ 556.495341] kill_f2fs_super+0x62/0x70 [ 556.496105] deactivate_locked_super+0x6f/0xa0 [ 556.497004] deactivate_super+0x5e/0x80 [ 556.497785] cleanup_mnt+0x61/0xa0 [ 556.498492] __cleanup_mnt+0x12/0x20 [ 556.499218] task_work_run+0xc8/0xf0 [ 556.499949] exit_to_usermode_loop+0x125/0x130 [ 556.500846] do_syscall_64+0x138/0x170 [ 556.501609] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 556.502659] RIP: 0033:0x7f8028b77487 [ 556.503384] Code: 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 31 f6 e9 09 00 00 00 66 0f 1f 84 00 00 00 00 00 b8 a6 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d e1 c9 2b 00 f7 d8 64 89 01 48 [ 556.507137] RSP: 002b:00007fff9f2e3598 EFLAGS: 00000246 ORIG_RAX: 00000000000000a6 [ 556.508637] RAX: 0000000000000000 RBX: 0000000000ebd030 RCX: 00007f8028b77487 [ 556.510069] RDX: 0000000000000001 RSI: 0000000000000000 RDI: 0000000000ec41e0 [ 556.511481] RBP: 0000000000ec41e0 R08: 0000000000000000 R09: 0000000000000014 [ 556.512892] R10: 00000000000006b2 R11: 0000000000000246 R12: 00007f802908083c [ 556.514320] R13: 0000000000000000 R14: 0000000000ebd210 R15: 00007fff9f2e3820 [ 556.515745] Modules linked in: snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_pcm snd_timer snd mac_hid i2c_piix4 soundcore ib_iser rdma_cm iw_cm ib_cm ib_core iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi raid10 raid456 async_raid6_recov async_memcpy async_pq async_xor async_tx raid1 raid0 multipath linear 8139too crct10dif_pclmul crc32_pclmul qxl drm_kms_helper syscopyarea aesni_intel sysfillrect sysimgblt fb_sys_fops ttm drm aes_x86_64 crypto_simd cryptd 8139cp glue_helper mii pata_acpi floppy [ 556.529276] ---[ end trace 4ce02f25ff7d3df5 ]--- [ 556.530340] RIP: 0010:f2fs_truncate_inode_blocks+0x4a7/0x6f0 [ 556.531513] Code: e8 ae ea ff ff 41 89 c7 c1 e8 1f 84 c0 74 0a 41 83 ff fe 0f 85 35 ff ff ff 81 85 b0 fe ff ff fb 03 00 00 e9 f7 fd ff ff 0f 0b <0f> 0b e8 62 b7 9a 00 48 8b bd a0 fe ff ff e8 56 54 ae ff 48 8b b5 [ 556.535330] RSP: 0018:ffff8801f292f808 EFLAGS: 00010286 [ 556.536395] RAX: ffffed003e73242d RBX: ffff8801f292f958 RCX: ffffffffb88b81bc [ 556.537824] RDX: 0000000000000000 RSI: 0000000000000004 RDI: ffff8801f3992164 [ 556.539290] RBP: ffff8801f292f980 R08: ffffed003e73242d R09: ffffed003e73242d [ 556.540709] R10: 0000000000000001 R11: ffffed003e73242c R12: 00000000fffffc64 [ 556.542131] R13: ffff8801f3992000 R14: 0000000000000058 R15: 00000000ffff8801 [ 556.543579] FS: 00007f8029297840(0000) GS:ffff8801f6f00000(0000) knlGS:0000000000000000 [ 556.545180] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 556.546338] CR2: 000055f5f57305d8 CR3: 00000001f18b0000 CR4: 00000000000006e0 [ 556.547809] ================================================================== [ 556.549248] BUG: KASAN: stack-out-of-bounds in arch_tlb_gather_mmu+0x52/0x170 [ 556.550672] Write of size 8 at addr ffff8801f292fd10 by task umount/1310

[ 556.552338] CPU: 1 PID: 1310 Comm: umount Tainted: G D 4.18.0-rc1+ #4 [ 556.553886] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 556.555756] Call Trace: [ 556.556264] dump_stack+0x7b/0xb5 [ 556.556944] print_address_description+0x70/0x290 [ 556.557903] kasan_report+0x291/0x390 [ 556.558649] ? arch_tlb_gather_mmu+0x52/0x170 [ 556.559537] __asan_store8+0x57/0x90 [ 556.560268] arch_tlb_gather_mmu+0x52/0x170 [ 556.561110] tlb_gather_mmu+0x12/0x40 [ 556.561862] exit_mmap+0x123/0x2a0 [ 556.562555] ? __ia32_sys_munmap+0x50/0x50 [ 556.563384] ? exit_aio+0x98/0x230 [ 556.564079] ? __x32_compat_sys_io_submit+0x260/0x260 [ 556.565099] ? taskstats_exit+0x1f4/0x640 [ 556.565925] ? kasan_check_read+0x11/0x20 [ 556.566739] ? mm_update_next_owner+0x322/0x380 [ 556.567652] mmput+0x8b/0x1d0 [ 556.568260] do_exit+0x43a/0x1390 [ 556.568937] ? mm_update_next_owner+0x380/0x380 [ 556.569855] ? deactivate_super+0x5e/0x80 [ 556.570668] ? cleanup_mnt+0x61/0xa0 [ 556.571395] ? __cleanup_mnt+0x12/0x20 [ 556.572156] ? task_work_run+0xc8/0xf0 [ 556.572917] ? exit_to_usermode_loop+0x125/0x130 [ 556.573861] rewind_stack_do_exit+0x17/0x20 [ 556.574707] RIP: 0033:0x7f8028b77487 [ 556.575428] Code: Bad RIP value. [ 556.576106] RSP: 002b:00007fff9f2e3598 EFLAGS: 00000246 ORIG_RAX: 00000000000000a6 [ 556.577599] RAX: 0000000000000000 RBX: 0000000000ebd030 RCX: 00007f8028b77487 [ 556.579020] RDX: 0000000000000001 RSI: 0000000000000000 RDI: 0000000000ec41e0 [ 556.580422] RBP: 0000000000ec41e0 R08: 0000000000000000 R09: 0000000000000014 [ 556.581833] R10: 00000000000006b2 R11: 0000000000000246 R12: 00007f802908083c [ 556.583252] R13: 0000000000000000 R14: 0000000000ebd210 R15: 00007fff9f2e3820

[ 556.584983] The buggy address belongs to the page: [ 556.585961] page:ffffea0007ca4bc0 count:0 mapcount:0 mapping:0000000000000000 index:0x0 [ 556.587540] flags: 0x2ffff0000000000() [ 556.588296] raw: 02ffff0000000000 0000000000000000 dead000000000200 0000000000000000 [ 556.589822] raw: 0000000000000000 0000000000000000 00000000ffffffff 0000000000000000 [ 556.591359] page dumped because: kasan: bad access detected

[ 556.592786] Memory state around the buggy address: [ 556.593753] ffff8801f292fc00: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 556.595191] ffff8801f292fc80: 00 00 00 00 00 00 00 00 f1 f1 f1 f1 00 00 00 00 [ 556.596613] >ffff8801f292fd00: 00 00 f3 00 00 00 00 f3 f3 00 00 00 00 f4 f4 f4 [ 556.598044] ^ [ 556.598797] ffff8801f292fd80: f3 f3 f3 f3 00 00 00 00 00 00 00 00 00 00 00 00 [ 556.600225] ffff8801f292fe00: 00 00 00 00 00 00 00 00 f1 f1 f1 f1 00 f4 f4 f4 [ 556.601647] ==================================================================

- Location https://elixir.bootlin.com/linux/v4.18-rc1/source/fs/f2fs/node.c#L987 case NODE_DIND_BLOCK: err = truncate_nodes(&dn, nofs, offset[1], 3); cont = 0; break;

default: BUG(); <--- }

Reported-by Wen Xu wen.xu@gatech.edu Signed-off-by: Chao Yu yuchao0@huawei.com Signed-off-by: Jaegeuk Kim jaegeuk@kernel.org Signed-off-by: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/f2fs/inode.c | 25 +++++++++++++++++++++++-- 1 file changed, 23 insertions(+), 2 deletions(-)

--- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -95,9 +95,30 @@ static void __recover_inline_status(stru return; }

-static bool sanity_check_inode(struct inode *inode) +static bool sanity_check_inode(struct inode *inode, struct page *node_page) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + unsigned long long iblocks; + + iblocks = le64_to_cpu(F2FS_INODE(node_page)->i_blocks); + if (!iblocks) { + set_sbi_flag(sbi, SBI_NEED_FSCK); + f2fs_msg(sbi->sb, KERN_WARNING, + "%s: corrupted inode i_blocks i_ino=%lx iblocks=%llu, " + "run fsck to fix.", + __func__, inode->i_ino, iblocks); + return false; + } + + if (ino_of_node(node_page) != nid_of_node(node_page)) { + set_sbi_flag(sbi, SBI_NEED_FSCK); + f2fs_msg(sbi->sb, KERN_WARNING, + "%s: corrupted inode footer i_ino=%lx, ino,nid: " + "[%u, %u] run fsck to fix.", + __func__, inode->i_ino, + ino_of_node(node_page), nid_of_node(node_page)); + return false; + }

return true; } @@ -150,7 +171,7 @@ static int do_read_inode(struct inode *i

get_inline_info(fi, ri);

- if (!sanity_check_inode(inode)) { + if (!sanity_check_inode(inode, node_page)) { f2fs_put_page(node_page, 1); return -EINVAL; }

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Chao Yu yuchao0@huawei.com

commit c9b60788fc760d136211853f10ce73dc152d1f4a upstream.

This patch add to do sanity check with below field: - cp_pack_total_block_count - blkaddr of data/node - extent info

- Overview BUG() in verify_block_addr() when writing to a corrupted f2fs image

- Reproduce (4.18 upstream kernel)

- POC (poc.c)

static void activity(char *mpoint) {

char *foo_bar_baz; int err;

static int buf[8192]; memset(buf, 0, sizeof(buf));

err = asprintf(&foo_bar_baz, "%s/foo/bar/baz", mpoint);

int fd = open(foo_bar_baz, O_RDWR | O_TRUNC, 0777); if (fd >= 0) { write(fd, (char *)buf, sizeof(buf)); fdatasync(fd); close(fd); } }

int main(int argc, char *argv[]) { activity(argv[1]); return 0; }

- Kernel message [ 689.349473] F2FS-fs (loop0): Mounted with checkpoint version = 3 [ 699.728662] WARNING: CPU: 0 PID: 1309 at fs/f2fs/segment.c:2860 f2fs_inplace_write_data+0x232/0x240 [ 699.728670] Modules linked in: snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_pcm snd_timer snd mac_hid i2c_piix4 soundcore ib_iser rdma_cm iw_cm ib_cm ib_core iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi raid10 raid456 async_raid6_recov async_memcpy async_pq async_xor async_tx raid1 raid0 multipath linear 8139too crct10dif_pclmul crc32_pclmul qxl drm_kms_helper syscopyarea aesni_intel sysfillrect sysimgblt fb_sys_fops ttm drm aes_x86_64 crypto_simd cryptd 8139cp glue_helper mii pata_acpi floppy [ 699.729056] CPU: 0 PID: 1309 Comm: a.out Not tainted 4.18.0-rc1+ #4 [ 699.729064] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 699.729074] RIP: 0010:f2fs_inplace_write_data+0x232/0x240 [ 699.729076] Code: ff e9 cf fe ff ff 49 8d 7d 10 e8 39 45 ad ff 4d 8b 7d 10 be 04 00 00 00 49 8d 7f 48 e8 07 49 ad ff 45 8b 7f 48 e9 fb fe ff ff <0f> 0b f0 41 80 4d 48 04 e9 65 fe ff ff 90 66 66 66 66 90 55 48 8d [ 699.729130] RSP: 0018:ffff8801f43af568 EFLAGS: 00010202 [ 699.729139] RAX: 000000000000003f RBX: ffff8801f43af7b8 RCX: ffffffffb88c9113 [ 699.729142] RDX: 0000000000000003 RSI: dffffc0000000000 RDI: ffff8802024e5540 [ 699.729144] RBP: ffff8801f43af590 R08: 0000000000000009 R09: ffffffffffffffe8 [ 699.729147] R10: 0000000000000001 R11: ffffed0039b0596a R12: ffff8802024e5540 [ 699.729149] R13: ffff8801f0335500 R14: ffff8801e3e7a700 R15: ffff8801e1ee4450 [ 699.729154] FS: 00007f9bf97f5700(0000) GS:ffff8801f6e00000(0000) knlGS:0000000000000000 [ 699.729156] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 699.729159] CR2: 00007f9bf925d170 CR3: 00000001f0c34000 CR4: 00000000000006f0 [ 699.729171] Call Trace: [ 699.729192] f2fs_do_write_data_page+0x2e2/0xe00 [ 699.729203] ? f2fs_should_update_outplace+0xd0/0xd0 [ 699.729238] ? memcg_drain_all_list_lrus+0x280/0x280 [ 699.729269] ? __radix_tree_replace+0xa3/0x120 [ 699.729276] __write_data_page+0x5c7/0xe30 [ 699.729291] ? kasan_check_read+0x11/0x20 [ 699.729310] ? page_mapped+0x8a/0x110 [ 699.729321] ? page_mkclean+0xe9/0x160 [ 699.729327] ? f2fs_do_write_data_page+0xe00/0xe00 [ 699.729331] ? invalid_page_referenced_vma+0x130/0x130 [ 699.729345] ? clear_page_dirty_for_io+0x332/0x450 [ 699.729351] f2fs_write_cache_pages+0x4ca/0x860 [ 699.729358] ? __write_data_page+0xe30/0xe30 [ 699.729374] ? percpu_counter_add_batch+0x22/0xa0 [ 699.729380] ? kasan_check_write+0x14/0x20 [ 699.729391] ? _raw_spin_lock+0x17/0x40 [ 699.729403] ? f2fs_mark_inode_dirty_sync.part.18+0x16/0x30 [ 699.729413] ? iov_iter_advance+0x113/0x640 [ 699.729418] ? f2fs_write_end+0x133/0x2e0 [ 699.729423] ? balance_dirty_pages_ratelimited+0x239/0x640 [ 699.729428] f2fs_write_data_pages+0x329/0x520 [ 699.729433] ? generic_perform_write+0x250/0x320 [ 699.729438] ? f2fs_write_cache_pages+0x860/0x860 [ 699.729454] ? current_time+0x110/0x110 [ 699.729459] ? f2fs_preallocate_blocks+0x1ef/0x370 [ 699.729464] do_writepages+0x37/0xb0 [ 699.729468] ? f2fs_write_cache_pages+0x860/0x860 [ 699.729472] ? do_writepages+0x37/0xb0 [ 699.729478] __filemap_fdatawrite_range+0x19a/0x1f0 [ 699.729483] ? delete_from_page_cache_batch+0x4e0/0x4e0 [ 699.729496] ? __vfs_write+0x2b2/0x410 [ 699.729501] file_write_and_wait_range+0x66/0xb0 [ 699.729506] f2fs_do_sync_file+0x1f9/0xd90 [ 699.729511] ? truncate_partial_data_page+0x290/0x290 [ 699.729521] ? __sb_end_write+0x30/0x50 [ 699.729526] ? vfs_write+0x20f/0x260 [ 699.729530] f2fs_sync_file+0x9a/0xb0 [ 699.729534] ? f2fs_do_sync_file+0xd90/0xd90 [ 699.729548] vfs_fsync_range+0x68/0x100 [ 699.729554] ? __fget_light+0xc9/0xe0 [ 699.729558] do_fsync+0x3d/0x70 [ 699.729562] __x64_sys_fdatasync+0x24/0x30 [ 699.729585] do_syscall_64+0x78/0x170 [ 699.729595] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 699.729613] RIP: 0033:0x7f9bf930d800 [ 699.729615] Code: 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 83 3d 49 bf 2c 00 00 75 10 b8 4b 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8 be 78 01 00 48 89 04 24 [ 699.729668] RSP: 002b:00007ffee3606c68 EFLAGS: 00000246 ORIG_RAX: 000000000000004b [ 699.729673] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f9bf930d800 [ 699.729675] RDX: 0000000000008000 RSI: 00000000006010a0 RDI: 0000000000000003 [ 699.729678] RBP: 00007ffee3606ca0 R08: 0000000001503010 R09: 0000000000000000 [ 699.729680] R10: 00000000000002e8 R11: 0000000000000246 R12: 0000000000400610 [ 699.729683] R13: 00007ffee3606da0 R14: 0000000000000000 R15: 0000000000000000 [ 699.729687] ---[ end trace 4ce02f25ff7d3df5 ]--- [ 699.729782] ------------[ cut here ]------------ [ 699.729785] kernel BUG at fs/f2fs/segment.h:654! [ 699.731055] invalid opcode: 0000 [#1] SMP KASAN PTI [ 699.732104] CPU: 0 PID: 1309 Comm: a.out Tainted: G W 4.18.0-rc1+ #4 [ 699.733684] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 699.735611] RIP: 0010:f2fs_submit_page_bio+0x29b/0x730 [ 699.736649] Code: 54 49 8d bd 18 04 00 00 e8 b2 59 af ff 41 8b 8d 18 04 00 00 8b 45 b8 41 d3 e6 44 01 f0 4c 8d 73 14 41 39 c7 0f 82 37 fe ff ff <0f> 0b 65 8b 05 2c 04 77 47 89 c0 48 0f a3 05 52 c1 d5 01 0f 92 c0 [ 699.740524] RSP: 0018:ffff8801f43af508 EFLAGS: 00010283 [ 699.741573] RAX: 0000000000000000 RBX: ffff8801f43af7b8 RCX: ffffffffb88a7cef [ 699.743006] RDX: 0000000000000007 RSI: dffffc0000000000 RDI: ffff8801e3e7a64c [ 699.744426] RBP: ffff8801f43af558 R08: ffffed003e066b55 R09: ffffed003e066b55 [ 699.745833] R10: 0000000000000001 R11: ffffed003e066b54 R12: ffffea0007876940 [ 699.747256] R13: ffff8801f0335500 R14: ffff8801e3e7a600 R15: 0000000000000001 [ 699.748683] FS: 00007f9bf97f5700(0000) GS:ffff8801f6e00000(0000) knlGS:0000000000000000 [ 699.750293] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 699.751462] CR2: 00007f9bf925d170 CR3: 00000001f0c34000 CR4: 00000000000006f0 [ 699.752874] Call Trace: [ 699.753386] ? f2fs_inplace_write_data+0x93/0x240 [ 699.754341] f2fs_inplace_write_data+0xd2/0x240 [ 699.755271] f2fs_do_write_data_page+0x2e2/0xe00 [ 699.756214] ? f2fs_should_update_outplace+0xd0/0xd0 [ 699.757215] ? memcg_drain_all_list_lrus+0x280/0x280 [ 699.758209] ? __radix_tree_replace+0xa3/0x120 [ 699.759164] __write_data_page+0x5c7/0xe30 [ 699.760002] ? kasan_check_read+0x11/0x20 [ 699.760823] ? page_mapped+0x8a/0x110 [ 699.761573] ? page_mkclean+0xe9/0x160 [ 699.762345] ? f2fs_do_write_data_page+0xe00/0xe00 [ 699.763332] ? invalid_page_referenced_vma+0x130/0x130 [ 699.764374] ? clear_page_dirty_for_io+0x332/0x450 [ 699.765347] f2fs_write_cache_pages+0x4ca/0x860 [ 699.766276] ? __write_data_page+0xe30/0xe30 [ 699.767161] ? percpu_counter_add_batch+0x22/0xa0 [ 699.768112] ? kasan_check_write+0x14/0x20 [ 699.768951] ? _raw_spin_lock+0x17/0x40 [ 699.769739] ? f2fs_mark_inode_dirty_sync.part.18+0x16/0x30 [ 699.770885] ? iov_iter_advance+0x113/0x640 [ 699.771743] ? f2fs_write_end+0x133/0x2e0 [ 699.772569] ? balance_dirty_pages_ratelimited+0x239/0x640 [ 699.773680] f2fs_write_data_pages+0x329/0x520 [ 699.774603] ? generic_perform_write+0x250/0x320 [ 699.775544] ? f2fs_write_cache_pages+0x860/0x860 [ 699.776510] ? current_time+0x110/0x110 [ 699.777299] ? f2fs_preallocate_blocks+0x1ef/0x370 [ 699.778279] do_writepages+0x37/0xb0 [ 699.779026] ? f2fs_write_cache_pages+0x860/0x860 [ 699.779978] ? do_writepages+0x37/0xb0 [ 699.780755] __filemap_fdatawrite_range+0x19a/0x1f0 [ 699.781746] ? delete_from_page_cache_batch+0x4e0/0x4e0 [ 699.782820] ? __vfs_write+0x2b2/0x410 [ 699.783597] file_write_and_wait_range+0x66/0xb0 [ 699.784540] f2fs_do_sync_file+0x1f9/0xd90 [ 699.785381] ? truncate_partial_data_page+0x290/0x290 [ 699.786415] ? __sb_end_write+0x30/0x50 [ 699.787204] ? vfs_write+0x20f/0x260 [ 699.787941] f2fs_sync_file+0x9a/0xb0 [ 699.788694] ? f2fs_do_sync_file+0xd90/0xd90 [ 699.789572] vfs_fsync_range+0x68/0x100 [ 699.790360] ? __fget_light+0xc9/0xe0 [ 699.791128] do_fsync+0x3d/0x70 [ 699.791779] __x64_sys_fdatasync+0x24/0x30 [ 699.792614] do_syscall_64+0x78/0x170 [ 699.793371] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 699.794406] RIP: 0033:0x7f9bf930d800 [ 699.795134] Code: 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 83 3d 49 bf 2c 00 00 75 10 b8 4b 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8 be 78 01 00 48 89 04 24 [ 699.798960] RSP: 002b:00007ffee3606c68 EFLAGS: 00000246 ORIG_RAX: 000000000000004b [ 699.800483] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f9bf930d800 [ 699.801923] RDX: 0000000000008000 RSI: 00000000006010a0 RDI: 0000000000000003 [ 699.803373] RBP: 00007ffee3606ca0 R08: 0000000001503010 R09: 0000000000000000 [ 699.804798] R10: 00000000000002e8 R11: 0000000000000246 R12: 0000000000400610 [ 699.806233] R13: 00007ffee3606da0 R14: 0000000000000000 R15: 0000000000000000 [ 699.807667] Modules linked in: snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_pcm snd_timer snd mac_hid i2c_piix4 soundcore ib_iser rdma_cm iw_cm ib_cm ib_core iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi raid10 raid456 async_raid6_recov async_memcpy async_pq async_xor async_tx raid1 raid0 multipath linear 8139too crct10dif_pclmul crc32_pclmul qxl drm_kms_helper syscopyarea aesni_intel sysfillrect sysimgblt fb_sys_fops ttm drm aes_x86_64 crypto_simd cryptd 8139cp glue_helper mii pata_acpi floppy [ 699.817079] ---[ end trace 4ce02f25ff7d3df6 ]--- [ 699.818068] RIP: 0010:f2fs_submit_page_bio+0x29b/0x730 [ 699.819114] Code: 54 49 8d bd 18 04 00 00 e8 b2 59 af ff 41 8b 8d 18 04 00 00 8b 45 b8 41 d3 e6 44 01 f0 4c 8d 73 14 41 39 c7 0f 82 37 fe ff ff <0f> 0b 65 8b 05 2c 04 77 47 89 c0 48 0f a3 05 52 c1 d5 01 0f 92 c0 [ 699.822919] RSP: 0018:ffff8801f43af508 EFLAGS: 00010283 [ 699.823977] RAX: 0000000000000000 RBX: ffff8801f43af7b8 RCX: ffffffffb88a7cef [ 699.825436] RDX: 0000000000000007 RSI: dffffc0000000000 RDI: ffff8801e3e7a64c [ 699.826881] RBP: ffff8801f43af558 R08: ffffed003e066b55 R09: ffffed003e066b55 [ 699.828292] R10: 0000000000000001 R11: ffffed003e066b54 R12: ffffea0007876940 [ 699.829750] R13: ffff8801f0335500 R14: ffff8801e3e7a600 R15: 0000000000000001 [ 699.831192] FS: 00007f9bf97f5700(0000) GS:ffff8801f6e00000(0000) knlGS:0000000000000000 [ 699.832793] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 699.833981] CR2: 00007f9bf925d170 CR3: 00000001f0c34000 CR4: 00000000000006f0 [ 699.835556] ================================================================== [ 699.837029] BUG: KASAN: stack-out-of-bounds in update_stack_state+0x38c/0x3e0 [ 699.838462] Read of size 8 at addr ffff8801f43af970 by task a.out/1309

[ 699.840086] CPU: 0 PID: 1309 Comm: a.out Tainted: G D W 4.18.0-rc1+ #4 [ 699.841603] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 699.843475] Call Trace: [ 699.843982] dump_stack+0x7b/0xb5 [ 699.844661] print_address_description+0x70/0x290 [ 699.845607] kasan_report+0x291/0x390 [ 699.846351] ? update_stack_state+0x38c/0x3e0 [ 699.853831] __asan_load8+0x54/0x90 [ 699.854569] update_stack_state+0x38c/0x3e0 [ 699.855428] ? __read_once_size_nocheck.constprop.7+0x20/0x20 [ 699.856601] ? __save_stack_trace+0x5e/0x100 [ 699.857476] unwind_next_frame.part.5+0x18e/0x490 [ 699.858448] ? unwind_dump+0x290/0x290 [ 699.859217] ? clear_page_dirty_for_io+0x332/0x450 [ 699.860185] __unwind_start+0x106/0x190 [ 699.860974] __save_stack_trace+0x5e/0x100 [ 699.861808] ? __save_stack_trace+0x5e/0x100 [ 699.862691] ? unlink_anon_vmas+0xba/0x2c0 [ 699.863525] save_stack_trace+0x1f/0x30 [ 699.864312] save_stack+0x46/0xd0 [ 699.864993] ? __alloc_pages_slowpath+0x1420/0x1420 [ 699.865990] ? flush_tlb_mm_range+0x15e/0x220 [ 699.866889] ? kasan_check_write+0x14/0x20 [ 699.867724] ? __dec_node_state+0x92/0xb0 [ 699.868543] ? lock_page_memcg+0x85/0xf0 [ 699.869350] ? unlock_page_memcg+0x16/0x80 [ 699.870185] ? page_remove_rmap+0x198/0x520 [ 699.871048] ? mark_page_accessed+0x133/0x200 [ 699.871930] ? _cond_resched+0x1a/0x50 [ 699.872700] ? unmap_page_range+0xcd4/0xe50 [ 699.873551] ? rb_next+0x58/0x80 [ 699.874217] ? rb_next+0x58/0x80 [ 699.874895] __kasan_slab_free+0x13c/0x1a0 [ 699.875734] ? unlink_anon_vmas+0xba/0x2c0 [ 699.876563] kasan_slab_free+0xe/0x10 [ 699.877315] kmem_cache_free+0x89/0x1e0 [ 699.878095] unlink_anon_vmas+0xba/0x2c0 [ 699.878913] free_pgtables+0x101/0x1b0 [ 699.879677] exit_mmap+0x146/0x2a0 [ 699.880378] ? __ia32_sys_munmap+0x50/0x50 [ 699.881214] ? kasan_check_read+0x11/0x20 [ 699.882052] ? mm_update_next_owner+0x322/0x380 [ 699.882985] mmput+0x8b/0x1d0 [ 699.883602] do_exit+0x43a/0x1390 [ 699.884288] ? mm_update_next_owner+0x380/0x380 [ 699.885212] ? f2fs_sync_file+0x9a/0xb0 [ 699.885995] ? f2fs_do_sync_file+0xd90/0xd90 [ 699.886877] ? vfs_fsync_range+0x68/0x100 [ 699.887694] ? __fget_light+0xc9/0xe0 [ 699.888442] ? do_fsync+0x3d/0x70 [ 699.889118] ? __x64_sys_fdatasync+0x24/0x30 [ 699.889996] rewind_stack_do_exit+0x17/0x20 [ 699.890860] RIP: 0033:0x7f9bf930d800 [ 699.891585] Code: Bad RIP value. [ 699.892268] RSP: 002b:00007ffee3606c68 EFLAGS: 00000246 ORIG_RAX: 000000000000004b [ 699.893781] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f9bf930d800 [ 699.895220] RDX: 0000000000008000 RSI: 00000000006010a0 RDI: 0000000000000003 [ 699.896643] RBP: 00007ffee3606ca0 R08: 0000000001503010 R09: 0000000000000000 [ 699.898069] R10: 00000000000002e8 R11: 0000000000000246 R12: 0000000000400610 [ 699.899505] R13: 00007ffee3606da0 R14: 0000000000000000 R15: 0000000000000000

[ 699.901241] The buggy address belongs to the page: [ 699.902215] page:ffffea0007d0ebc0 count:0 mapcount:0 mapping:0000000000000000 index:0x0 [ 699.903811] flags: 0x2ffff0000000000() [ 699.904585] raw: 02ffff0000000000 0000000000000000 ffffffff07d00101 0000000000000000 [ 699.906125] raw: 0000000000000000 0000000000240000 00000000ffffffff 0000000000000000 [ 699.907673] page dumped because: kasan: bad access detected

[ 699.909108] Memory state around the buggy address: [ 699.910077] ffff8801f43af800: 00 f1 f1 f1 f1 00 f4 f4 f4 f3 f3 f3 f3 00 00 00 [ 699.911528] ffff8801f43af880: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 699.912953] >ffff8801f43af900: 00 00 00 00 00 00 00 00 f1 01 f4 f4 f4 f2 f2 f2 [ 699.914392] ^ [ 699.915758] ffff8801f43af980: f2 00 f4 f4 00 00 00 00 f2 00 00 00 00 00 00 00 [ 699.917193] ffff8801f43afa00: 00 00 00 00 00 00 00 00 00 f3 f3 f3 00 00 00 00 [ 699.918634] ==================================================================

- Location https://elixir.bootlin.com/linux/v4.18-rc1/source/fs/f2fs/segment.h#L644

Reported-by Wen Xu wen.xu@gatech.edu Signed-off-by: Chao Yu yuchao0@huawei.com Signed-off-by: Jaegeuk Kim jaegeuk@kernel.org [bwh: Backported to 4.4: - CoW is not implemented so check f2fs_io_info::blk_addr instead of f2fs_io_info::{old,new}_blkaddr - Operation code is f2fs_io_info::rw instead of f2fs_io_info::op - f2fs_stop_checkpoint() only takes one argument - In f2fs_map_blocks(), validate dn.data_blkaddr instead of blkaddr - Adjust context] Signed-off-by: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/f2fs/checkpoint.c | 22 +++++++++++++++++++--- fs/f2fs/data.c | 21 ++++++++++++++++++++- fs/f2fs/f2fs.h | 3 +++ fs/f2fs/file.c | 12 ++++++++++++ fs/f2fs/inode.c | 16 ++++++++++++++++ fs/f2fs/node.c | 4 ++++ fs/f2fs/segment.h | 3 +-- 7 files changed, 75 insertions(+), 6 deletions(-)

--- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -75,8 +75,10 @@ repeat: fio.page = page;

if (f2fs_submit_page_bio(&fio)) { - f2fs_put_page(page, 1); - goto repeat; + memset(page_address(page), 0, PAGE_SIZE); + f2fs_stop_checkpoint(sbi); + f2fs_bug_on(sbi, 1); + return page; }

lock_page(page); @@ -130,8 +132,14 @@ bool f2fs_is_valid_blkaddr(struct f2fs_s case META_POR: case DATA_GENERIC: if (unlikely(blkaddr >= MAX_BLKADDR(sbi) || - blkaddr < MAIN_BLKADDR(sbi))) + blkaddr < MAIN_BLKADDR(sbi))) { + if (type == DATA_GENERIC) { + f2fs_msg(sbi->sb, KERN_WARNING, + "access invalid blkaddr:%u", blkaddr); + WARN_ON(1); + } return false; + } break; case META_GENERIC: if (unlikely(blkaddr < SEG0_BLKADDR(sbi) || @@ -651,6 +659,14 @@ static struct page *validate_checkpoint( &cp_page_1, version); if (err) goto invalid_cp1; + + if (le32_to_cpu(cp_block->cp_pack_total_block_count) > + sbi->blocks_per_seg) { + f2fs_msg(sbi->sb, KERN_WARNING, + "invalid cp_pack_total_block_count:%u", + le32_to_cpu(cp_block->cp_pack_total_block_count)); + goto invalid_cp1; + } pre_version = *version;

cp_addr += le32_to_cpu(cp_block->cp_pack_total_block_count) - 1; --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -147,7 +147,10 @@ int f2fs_submit_page_bio(struct f2fs_io_ struct bio *bio; struct page *page = fio->encrypted_page ? fio->encrypted_page : fio->page;

- verify_block_addr(fio, fio->blk_addr); + if (!f2fs_is_valid_blkaddr(fio->sbi, fio->blk_addr, + __is_meta_io(fio) ? META_GENERIC : DATA_GENERIC)) + return -EFAULT; + trace_f2fs_submit_page_bio(page, fio); f2fs_trace_ios(fio, 0);

@@ -604,6 +607,12 @@ static int f2fs_map_blocks(struct inode goto unlock_out; }

+ if (__is_valid_data_blkaddr(dn.data_blkaddr) && + !f2fs_is_valid_blkaddr(sbi, dn.data_blkaddr, DATA_GENERIC)) { + err = -EFAULT; + goto sync_out; + } + if (!is_valid_data_blkaddr(sbi, dn.data_blkaddr)) { if (create) { if (unlikely(f2fs_cp_error(sbi))) { @@ -972,6 +981,10 @@ got_it: SetPageUptodate(page); goto confused; } + + if (!f2fs_is_valid_blkaddr(F2FS_I_SB(inode), block_nr, + DATA_GENERIC)) + goto set_error_page; } else { zero_user_segment(page, 0, PAGE_CACHE_SIZE); SetPageUptodate(page); @@ -1086,6 +1099,12 @@ int do_write_data_page(struct f2fs_io_in

set_page_writeback(page);

+ if (__is_valid_data_blkaddr(fio->blk_addr) && + !f2fs_is_valid_blkaddr(fio->sbi, fio->blk_addr, + DATA_GENERIC)) { + err = -EFAULT; + goto out_writepage; + } /* * If current allocation needs SSR, * it had better in-place writes for updated data. --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -1649,6 +1649,9 @@ static inline void *f2fs_kvzalloc(size_t (pgofs - ADDRS_PER_INODE(fi) + ADDRS_PER_BLOCK) / \ ADDRS_PER_BLOCK * ADDRS_PER_BLOCK + ADDRS_PER_INODE(fi))

+#define __is_meta_io(fio) (PAGE_TYPE_OF_BIO(fio->type) == META && \ + (!is_read_io(fio->rw) || fio->is_meta)) + bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr, int type); void f2fs_msg(struct super_block *sb, const char *level, const char *fmt, ...); --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -374,6 +374,13 @@ static loff_t f2fs_seek_block(struct fil block_t blkaddr; blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node);

+ if (__is_valid_data_blkaddr(blkaddr) && + !f2fs_is_valid_blkaddr(F2FS_I_SB(inode), + blkaddr, DATA_GENERIC)) { + f2fs_put_dnode(&dn); + goto fail; + } + if (__found_offset(F2FS_I_SB(inode), blkaddr, dirty, pgofs, whence)) { f2fs_put_dnode(&dn); @@ -467,6 +474,11 @@ int truncate_data_blocks_range(struct dn

dn->data_blkaddr = NULL_ADDR; set_data_blkaddr(dn); + + if (__is_valid_data_blkaddr(blkaddr) && + !f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC)) + continue; + invalidate_blocks(sbi, blkaddr); if (dn->ofs_in_node == 0 && IS_INODE(dn->node_page)) clear_inode_flag(F2FS_I(dn->inode), --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -120,6 +120,22 @@ static bool sanity_check_inode(struct in return false; }

+ if (F2FS_I(inode)->extent_tree) { + struct extent_info *ei = &F2FS_I(inode)->extent_tree->largest; + + if (ei->len && + (!f2fs_is_valid_blkaddr(sbi, ei->blk, DATA_GENERIC) || + !f2fs_is_valid_blkaddr(sbi, ei->blk + ei->len - 1, + DATA_GENERIC))) { + set_sbi_flag(sbi, SBI_NEED_FSCK); + f2fs_msg(sbi->sb, KERN_WARNING, + "%s: inode (ino=%lx) extent info [%u, %u, %u] " + "is incorrect, run fsck to fix", + __func__, inode->i_ino, + ei->blk, ei->fofs, ei->len); + return false; + } + } return true; }

--- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -1341,6 +1341,10 @@ static int f2fs_write_node_page(struct p return 0; }

+ if (__is_valid_data_blkaddr(ni.blk_addr) && + !f2fs_is_valid_blkaddr(sbi, ni.blk_addr, DATA_GENERIC)) + goto redirty_out; + set_page_writeback(page); fio.blk_addr = ni.blk_addr; write_node_page(nid, &fio); --- a/fs/f2fs/segment.h +++ b/fs/f2fs/segment.h @@ -586,8 +586,7 @@ static inline void verify_block_addr(str { struct f2fs_sb_info *sbi = fio->sbi;

- if (PAGE_TYPE_OF_BIO(fio->type) == META && - (!is_read_io(fio->rw) || fio->is_meta)) + if (__is_meta_io(fio)) verify_blkaddr(sbi, blk_addr, META_GENERIC); else verify_blkaddr(sbi, blk_addr, DATA_GENERIC);

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Chao Yu yuchao0@huawei.com

commit e494c2f995d6181d6e29c4927d68e0f295ecf75b upstream.

After fuzzing, cp_pack_start_sum could be corrupted, so current log's summary info should be wrong due to loading incorrect summary block. Then, if segment's type in current log is exceeded NR_CURSEG_TYPE, it can lead accessing invalid dirty_i->dirty_segmap bitmap finally.

Add sanity check for cp_pack_start_sum to fix this issue.

https://bugzilla.kernel.org/show_bug.cgi?id=200419

- Reproduce

- Kernel message (f2fs-dev w/ KASAN) [ 3117.578432] F2FS-fs (loop0): Invalid log blocks per segment (8)

[ 3117.578445] F2FS-fs (loop0): Can't find valid F2FS filesystem in 2th superblock [ 3117.581364] F2FS-fs (loop0): invalid crc_offset: 30716 [ 3117.583564] WARNING: CPU: 1 PID: 1225 at fs/f2fs/checkpoint.c:90 __get_meta_page+0x448/0x4b0 [ 3117.583570] Modules linked in: snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hda_core snd_hwdep snd_pcm snd_timer joydev input_leds serio_raw snd soundcore mac_hid i2c_piix4 ib_iser rdma_cm iw_cm ib_cm ib_core configfs iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi btrfs zstd_decompress zstd_compress xxhash raid10 raid456 async_raid6_recov async_memcpy async_pq async_xor async_tx xor raid6_pq libcrc32c raid1 raid0 multipath linear 8139too qxl ttm drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops drm crct10dif_pclmul crc32_pclmul ghash_clmulni_intel pcbc aesni_intel psmouse aes_x86_64 8139cp crypto_simd cryptd mii glue_helper pata_acpi floppy [ 3117.584014] CPU: 1 PID: 1225 Comm: mount Not tainted 4.17.0+ #1 [ 3117.584017] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 3117.584022] RIP: 0010:__get_meta_page+0x448/0x4b0 [ 3117.584023] Code: 00 49 8d bc 24 84 00 00 00 e8 74 54 da ff 41 83 8c 24 84 00 00 00 08 4c 89 f6 4c 89 ef e8 c0 d9 95 00 48 89 ef e8 18 e3 00 00 <0f> 0b f0 80 4d 48 04 e9 0f fe ff ff 0f 0b 48 89 c7 48 89 04 24 e8 [ 3117.584072] RSP: 0018:ffff88018eb678c0 EFLAGS: 00010286 [ 3117.584082] RAX: ffff88018f0a6a78 RBX: ffffea0007a46600 RCX: ffffffff9314d1b2 [ 3117.584085] RDX: ffffffff00000001 RSI: 0000000000000000 RDI: ffff88018f0a6a98 [ 3117.584087] RBP: ffff88018ebe9980 R08: 0000000000000002 R09: 0000000000000001 [ 3117.584090] R10: 0000000000000001 R11: ffffed00326e4450 R12: ffff880193722200 [ 3117.584092] R13: ffff88018ebe9afc R14: 0000000000000206 R15: ffff88018eb67900 [ 3117.584096] FS: 00007f5694636840(0000) GS:ffff8801f3b00000(0000) knlGS:0000000000000000 [ 3117.584098] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 3117.584101] CR2: 00000000016f21b8 CR3: 0000000191c22000 CR4: 00000000000006e0 [ 3117.584112] Call Trace: [ 3117.584121] ? f2fs_set_meta_page_dirty+0x150/0x150 [ 3117.584127] ? f2fs_build_segment_manager+0xbf9/0x3190 [ 3117.584133] ? f2fs_npages_for_summary_flush+0x75/0x120 [ 3117.584145] f2fs_build_segment_manager+0xda8/0x3190 [ 3117.584151] ? f2fs_get_valid_checkpoint+0x298/0xa00 [ 3117.584156] ? f2fs_flush_sit_entries+0x10e0/0x10e0 [ 3117.584184] ? map_id_range_down+0x17c/0x1b0 [ 3117.584188] ? __put_user_ns+0x30/0x30 [ 3117.584206] ? find_next_bit+0x53/0x90 [ 3117.584237] ? cpumask_next+0x16/0x20 [ 3117.584249] f2fs_fill_super+0x1948/0x2b40 [ 3117.584258] ? f2fs_commit_super+0x1a0/0x1a0 [ 3117.584279] ? sget_userns+0x65e/0x690 [ 3117.584296] ? set_blocksize+0x88/0x130 [ 3117.584302] ? f2fs_commit_super+0x1a0/0x1a0 [ 3117.584305] mount_bdev+0x1c0/0x200 [ 3117.584310] mount_fs+0x5c/0x190 [ 3117.584320] vfs_kern_mount+0x64/0x190 [ 3117.584330] do_mount+0x2e4/0x1450 [ 3117.584343] ? lockref_put_return+0x130/0x130 [ 3117.584347] ? copy_mount_string+0x20/0x20 [ 3117.584357] ? kasan_unpoison_shadow+0x31/0x40 [ 3117.584362] ? kasan_kmalloc+0xa6/0xd0 [ 3117.584373] ? memcg_kmem_put_cache+0x16/0x90 [ 3117.584377] ? __kmalloc_track_caller+0x196/0x210 [ 3117.584383] ? _copy_from_user+0x61/0x90 [ 3117.584396] ? memdup_user+0x3e/0x60 [ 3117.584401] ksys_mount+0x7e/0xd0 [ 3117.584405] __x64_sys_mount+0x62/0x70 [ 3117.584427] do_syscall_64+0x73/0x160 [ 3117.584440] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 3117.584455] RIP: 0033:0x7f5693f14b9a [ 3117.584456] Code: 48 8b 0d 01 c3 2b 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 49 89 ca b8 a5 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d ce c2 2b 00 f7 d8 64 89 01 48 [ 3117.584505] RSP: 002b:00007fff27346488 EFLAGS: 00000206 ORIG_RAX: 00000000000000a5 [ 3117.584510] RAX: ffffffffffffffda RBX: 00000000016e2030 RCX: 00007f5693f14b9a [ 3117.584512] RDX: 00000000016e2210 RSI: 00000000016e3f30 RDI: 00000000016ee040 [ 3117.584514] RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000013 [ 3117.584516] R10: 00000000c0ed0000 R11: 0000000000000206 R12: 00000000016ee040 [ 3117.584519] R13: 00000000016e2210 R14: 0000000000000000 R15: 0000000000000003 [ 3117.584523] ---[ end trace a8e0d899985faf31 ]--- [ 3117.685663] F2FS-fs (loop0): f2fs_check_nid_range: out-of-range nid=2, run fsck to fix. [ 3117.685673] F2FS-fs (loop0): recover_data: ino = 2 (i_size: recover) recovered = 1, err = 0 [ 3117.685707] ================================================================== [ 3117.685955] BUG: KASAN: slab-out-of-bounds in __remove_dirty_segment+0xdd/0x1e0 [ 3117.686175] Read of size 8 at addr ffff88018f0a63d0 by task mount/1225

[ 3117.686477] CPU: 0 PID: 1225 Comm: mount Tainted: G W 4.17.0+ #1 [ 3117.686481] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 3117.686483] Call Trace: [ 3117.686494] dump_stack+0x71/0xab [ 3117.686512] print_address_description+0x6b/0x290 [ 3117.686517] kasan_report+0x28e/0x390 [ 3117.686522] ? __remove_dirty_segment+0xdd/0x1e0 [ 3117.686527] __remove_dirty_segment+0xdd/0x1e0 [ 3117.686532] locate_dirty_segment+0x189/0x190 [ 3117.686538] f2fs_allocate_new_segments+0xa9/0xe0 [ 3117.686543] recover_data+0x703/0x2c20 [ 3117.686547] ? f2fs_recover_fsync_data+0x48f/0xd50 [ 3117.686553] ? ksys_mount+0x7e/0xd0 [ 3117.686564] ? policy_nodemask+0x1a/0x90 [ 3117.686567] ? policy_node+0x56/0x70 [ 3117.686571] ? add_fsync_inode+0xf0/0xf0 [ 3117.686592] ? blk_finish_plug+0x44/0x60 [ 3117.686597] ? f2fs_ra_meta_pages+0x38b/0x5e0 [ 3117.686602] ? find_inode_fast+0xac/0xc0 [ 3117.686606] ? f2fs_is_valid_blkaddr+0x320/0x320 [ 3117.686618] ? __radix_tree_lookup+0x150/0x150 [ 3117.686633] ? dqget+0x670/0x670 [ 3117.686648] ? pagecache_get_page+0x29/0x410 [ 3117.686656] ? kmem_cache_alloc+0x176/0x1e0 [ 3117.686660] ? f2fs_is_valid_blkaddr+0x11d/0x320 [ 3117.686664] f2fs_recover_fsync_data+0xc23/0xd50 [ 3117.686670] ? f2fs_space_for_roll_forward+0x60/0x60 [ 3117.686674] ? rb_insert_color+0x323/0x3d0 [ 3117.686678] ? f2fs_recover_orphan_inodes+0xa5/0x700 [ 3117.686683] ? proc_register+0x153/0x1d0 [ 3117.686686] ? f2fs_remove_orphan_inode+0x10/0x10 [ 3117.686695] ? f2fs_attr_store+0x50/0x50 [ 3117.686700] ? proc_create_single_data+0x52/0x60 [ 3117.686707] f2fs_fill_super+0x1d06/0x2b40 [ 3117.686728] ? f2fs_commit_super+0x1a0/0x1a0 [ 3117.686735] ? sget_userns+0x65e/0x690 [ 3117.686740] ? set_blocksize+0x88/0x130 [ 3117.686745] ? f2fs_commit_super+0x1a0/0x1a0 [ 3117.686748] mount_bdev+0x1c0/0x200 [ 3117.686753] mount_fs+0x5c/0x190 [ 3117.686758] vfs_kern_mount+0x64/0x190 [ 3117.686762] do_mount+0x2e4/0x1450 [ 3117.686769] ? lockref_put_return+0x130/0x130 [ 3117.686773] ? copy_mount_string+0x20/0x20 [ 3117.686777] ? kasan_unpoison_shadow+0x31/0x40 [ 3117.686780] ? kasan_kmalloc+0xa6/0xd0 [ 3117.686786] ? memcg_kmem_put_cache+0x16/0x90 [ 3117.686790] ? __kmalloc_track_caller+0x196/0x210 [ 3117.686795] ? _copy_from_user+0x61/0x90 [ 3117.686801] ? memdup_user+0x3e/0x60 [ 3117.686804] ksys_mount+0x7e/0xd0 [ 3117.686809] __x64_sys_mount+0x62/0x70 [ 3117.686816] do_syscall_64+0x73/0x160 [ 3117.686824] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 3117.686829] RIP: 0033:0x7f5693f14b9a [ 3117.686830] Code: 48 8b 0d 01 c3 2b 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 49 89 ca b8 a5 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d ce c2 2b 00 f7 d8 64 89 01 48 [ 3117.686887] RSP: 002b:00007fff27346488 EFLAGS: 00000206 ORIG_RAX: 00000000000000a5 [ 3117.686892] RAX: ffffffffffffffda RBX: 00000000016e2030 RCX: 00007f5693f14b9a [ 3117.686894] RDX: 00000000016e2210 RSI: 00000000016e3f30 RDI: 00000000016ee040 [ 3117.686896] RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000013 [ 3117.686899] R10: 00000000c0ed0000 R11: 0000000000000206 R12: 00000000016ee040 [ 3117.686901] R13: 00000000016e2210 R14: 0000000000000000 R15: 0000000000000003

[ 3117.687005] Allocated by task 1225: [ 3117.687152] kasan_kmalloc+0xa6/0xd0 [ 3117.687157] kmem_cache_alloc_trace+0xfd/0x200 [ 3117.687161] f2fs_build_segment_manager+0x2d09/0x3190 [ 3117.687165] f2fs_fill_super+0x1948/0x2b40 [ 3117.687168] mount_bdev+0x1c0/0x200 [ 3117.687171] mount_fs+0x5c/0x190 [ 3117.687174] vfs_kern_mount+0x64/0x190 [ 3117.687177] do_mount+0x2e4/0x1450 [ 3117.687180] ksys_mount+0x7e/0xd0 [ 3117.687182] __x64_sys_mount+0x62/0x70 [ 3117.687186] do_syscall_64+0x73/0x160 [ 3117.687190] entry_SYSCALL_64_after_hwframe+0x44/0xa9

[ 3117.687285] Freed by task 19: [ 3117.687412] __kasan_slab_free+0x137/0x190 [ 3117.687416] kfree+0x8b/0x1b0 [ 3117.687460] ttm_bo_man_put_node+0x61/0x80 [ttm] [ 3117.687476] ttm_bo_cleanup_refs+0x15f/0x250 [ttm] [ 3117.687492] ttm_bo_delayed_delete+0x2f0/0x300 [ttm] [ 3117.687507] ttm_bo_delayed_workqueue+0x17/0x50 [ttm] [ 3117.687528] process_one_work+0x2f9/0x740 [ 3117.687531] worker_thread+0x78/0x6b0 [ 3117.687541] kthread+0x177/0x1c0 [ 3117.687545] ret_from_fork+0x35/0x40

[ 3117.687638] The buggy address belongs to the object at ffff88018f0a6300 which belongs to the cache kmalloc-192 of size 192 [ 3117.688014] The buggy address is located 16 bytes to the right of 192-byte region [ffff88018f0a6300, ffff88018f0a63c0) [ 3117.688382] The buggy address belongs to the page: [ 3117.688554] page:ffffea00063c2980 count:1 mapcount:0 mapping:ffff8801f3403180 index:0x0 [ 3117.688788] flags: 0x17fff8000000100(slab) [ 3117.688944] raw: 017fff8000000100 ffffea00063c2840 0000000e0000000e ffff8801f3403180 [ 3117.689166] raw: 0000000000000000 0000000080100010 00000001ffffffff 0000000000000000 [ 3117.689386] page dumped because: kasan: bad access detected

[ 3117.689653] Memory state around the buggy address: [ 3117.689816] ffff88018f0a6280: fb fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc [ 3117.690027] ffff88018f0a6300: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 3117.690239] >ffff88018f0a6380: 00 00 fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 3117.690448] ^ [ 3117.690644] ffff88018f0a6400: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 3117.690868] ffff88018f0a6480: 00 00 fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 3117.691077] ================================================================== [ 3117.691290] Disabling lock debugging due to kernel taint [ 3117.693893] BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 [ 3117.694120] PGD 80000001f01bc067 P4D 80000001f01bc067 PUD 1d9638067 PMD 0 [ 3117.694338] Oops: 0002 [#1] SMP KASAN PTI [ 3117.694490] CPU: 1 PID: 1225 Comm: mount Tainted: G B W 4.17.0+ #1 [ 3117.694703] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 3117.695073] RIP: 0010:__remove_dirty_segment+0xe2/0x1e0 [ 3117.695246] Code: c4 48 89 c7 e8 cf bb d7 ff 45 0f b6 24 24 41 83 e4 3f 44 88 64 24 07 41 83 e4 3f 4a 8d 7c e3 08 e8 b3 bc d7 ff 4a 8b 4c e3 08 <f0> 4c 0f b3 29 0f 82 94 00 00 00 48 8d bd 20 04 00 00 e8 97 bb d7 [ 3117.695793] RSP: 0018:ffff88018eb67638 EFLAGS: 00010292 [ 3117.695969] RAX: 0000000000000000 RBX: ffff88018f0a6300 RCX: 0000000000000000 [ 3117.696182] RDX: 0000000000000000 RSI: 0000000000000297 RDI: 0000000000000297 [ 3117.696391] RBP: ffff88018ebe9980 R08: ffffed003e743ebb R09: ffffed003e743ebb [ 3117.696604] R10: 0000000000000001 R11: ffffed003e743eba R12: 0000000000000019 [ 3117.696813] R13: 0000000000000014 R14: 0000000000000320 R15: ffff88018ebe99e0 [ 3117.697032] FS: 00007f5694636840(0000) GS:ffff8801f3b00000(0000) knlGS:0000000000000000 [ 3117.697280] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 3117.702357] CR2: 00007fe89bb1a000 CR3: 0000000191c22000 CR4: 00000000000006e0 [ 3117.707235] Call Trace: [ 3117.712077] locate_dirty_segment+0x189/0x190 [ 3117.716891] f2fs_allocate_new_segments+0xa9/0xe0 [ 3117.721617] recover_data+0x703/0x2c20 [ 3117.726316] ? f2fs_recover_fsync_data+0x48f/0xd50 [ 3117.730957] ? ksys_mount+0x7e/0xd0 [ 3117.735573] ? policy_nodemask+0x1a/0x90 [ 3117.740198] ? policy_node+0x56/0x70 [ 3117.744829] ? add_fsync_inode+0xf0/0xf0 [ 3117.749487] ? blk_finish_plug+0x44/0x60 [ 3117.754152] ? f2fs_ra_meta_pages+0x38b/0x5e0 [ 3117.758831] ? find_inode_fast+0xac/0xc0 [ 3117.763448] ? f2fs_is_valid_blkaddr+0x320/0x320 [ 3117.768046] ? __radix_tree_lookup+0x150/0x150 [ 3117.772603] ? dqget+0x670/0x670 [ 3117.777159] ? pagecache_get_page+0x29/0x410 [ 3117.781648] ? kmem_cache_alloc+0x176/0x1e0 [ 3117.786067] ? f2fs_is_valid_blkaddr+0x11d/0x320 [ 3117.790476] f2fs_recover_fsync_data+0xc23/0xd50 [ 3117.794790] ? f2fs_space_for_roll_forward+0x60/0x60 [ 3117.799086] ? rb_insert_color+0x323/0x3d0 [ 3117.803304] ? f2fs_recover_orphan_inodes+0xa5/0x700 [ 3117.807563] ? proc_register+0x153/0x1d0 [ 3117.811766] ? f2fs_remove_orphan_inode+0x10/0x10 [ 3117.815947] ? f2fs_attr_store+0x50/0x50 [ 3117.820087] ? proc_create_single_data+0x52/0x60 [ 3117.824262] f2fs_fill_super+0x1d06/0x2b40 [ 3117.828367] ? f2fs_commit_super+0x1a0/0x1a0 [ 3117.832432] ? sget_userns+0x65e/0x690 [ 3117.836500] ? set_blocksize+0x88/0x130 [ 3117.840501] ? f2fs_commit_super+0x1a0/0x1a0 [ 3117.844420] mount_bdev+0x1c0/0x200 [ 3117.848275] mount_fs+0x5c/0x190 [ 3117.852053] vfs_kern_mount+0x64/0x190 [ 3117.855810] do_mount+0x2e4/0x1450 [ 3117.859441] ? lockref_put_return+0x130/0x130 [ 3117.862996] ? copy_mount_string+0x20/0x20 [ 3117.866417] ? kasan_unpoison_shadow+0x31/0x40 [ 3117.869719] ? kasan_kmalloc+0xa6/0xd0 [ 3117.872948] ? memcg_kmem_put_cache+0x16/0x90 [ 3117.876121] ? __kmalloc_track_caller+0x196/0x210 [ 3117.879333] ? _copy_from_user+0x61/0x90 [ 3117.882467] ? memdup_user+0x3e/0x60 [ 3117.885604] ksys_mount+0x7e/0xd0 [ 3117.888700] __x64_sys_mount+0x62/0x70 [ 3117.891742] do_syscall_64+0x73/0x160 [ 3117.894692] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 3117.897669] RIP: 0033:0x7f5693f14b9a [ 3117.900563] Code: 48 8b 0d 01 c3 2b 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 49 89 ca b8 a5 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d ce c2 2b 00 f7 d8 64 89 01 48 [ 3117.906922] RSP: 002b:00007fff27346488 EFLAGS: 00000206 ORIG_RAX: 00000000000000a5 [ 3117.910159] RAX: ffffffffffffffda RBX: 00000000016e2030 RCX: 00007f5693f14b9a [ 3117.913469] RDX: 00000000016e2210 RSI: 00000000016e3f30 RDI: 00000000016ee040 [ 3117.916764] RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000013 [ 3117.920071] R10: 00000000c0ed0000 R11: 0000000000000206 R12: 00000000016ee040 [ 3117.923393] R13: 00000000016e2210 R14: 0000000000000000 R15: 0000000000000003 [ 3117.926680] Modules linked in: snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hda_core snd_hwdep snd_pcm snd_timer joydev input_leds serio_raw snd soundcore mac_hid i2c_piix4 ib_iser rdma_cm iw_cm ib_cm ib_core configfs iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi btrfs zstd_decompress zstd_compress xxhash raid10 raid456 async_raid6_recov async_memcpy async_pq async_xor async_tx xor raid6_pq libcrc32c raid1 raid0 multipath linear 8139too qxl ttm drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops drm crct10dif_pclmul crc32_pclmul ghash_clmulni_intel pcbc aesni_intel psmouse aes_x86_64 8139cp crypto_simd cryptd mii glue_helper pata_acpi floppy [ 3117.949979] CR2: 0000000000000000 [ 3117.954283] ---[ end trace a8e0d899985faf32 ]--- [ 3117.958575] RIP: 0010:__remove_dirty_segment+0xe2/0x1e0 [ 3117.962810] Code: c4 48 89 c7 e8 cf bb d7 ff 45 0f b6 24 24 41 83 e4 3f 44 88 64 24 07 41 83 e4 3f 4a 8d 7c e3 08 e8 b3 bc d7 ff 4a 8b 4c e3 08 <f0> 4c 0f b3 29 0f 82 94 00 00 00 48 8d bd 20 04 00 00 e8 97 bb d7 [ 3117.971789] RSP: 0018:ffff88018eb67638 EFLAGS: 00010292 [ 3117.976333] RAX: 0000000000000000 RBX: ffff88018f0a6300 RCX: 0000000000000000 [ 3117.980926] RDX: 0000000000000000 RSI: 0000000000000297 RDI: 0000000000000297 [ 3117.985497] RBP: ffff88018ebe9980 R08: ffffed003e743ebb R09: ffffed003e743ebb [ 3117.990098] R10: 0000000000000001 R11: ffffed003e743eba R12: 0000000000000019 [ 3117.994761] R13: 0000000000000014 R14: 0000000000000320 R15: ffff88018ebe99e0 [ 3117.999392] FS: 00007f5694636840(0000) GS:ffff8801f3b00000(0000) knlGS:0000000000000000 [ 3118.004096] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 3118.008816] CR2: 00007fe89bb1a000 CR3: 0000000191c22000 CR4: 00000000000006e0

- Location https://elixir.bootlin.com/linux/v4.18-rc3/source/fs/f2fs/segment.c#L775 if (test_and_clear_bit(segno, dirty_i->dirty_segmap[t])) dirty_i->nr_dirty[t]--; Here dirty_i->dirty_segmap[t] can be NULL which leads to crash in test_and_clear_bit()

Reported-by Wen Xu wen.xu@gatech.edu Signed-off-by: Chao Yu yuchao0@huawei.com Signed-off-by: Jaegeuk Kim jaegeuk@kernel.org [bwh: Backported to 4.4: The function is called sanity_check_ckpt()] Signed-off-by: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/f2fs/checkpoint.c | 8 ++++---- fs/f2fs/super.c | 12 ++++++++++++ 2 files changed, 16 insertions(+), 4 deletions(-)

--- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -731,15 +731,15 @@ int get_valid_checkpoint(struct f2fs_sb_ cp_block = (struct f2fs_checkpoint *)page_address(cur_page); memcpy(sbi->ckpt, cp_block, blk_size);

- /* Sanity checking of checkpoint */ - if (sanity_check_ckpt(sbi)) - goto free_fail_no_cp; - if (cur_page == cp1) sbi->cur_cp_pack = 1; else sbi->cur_cp_pack = 2;

+ /* Sanity checking of checkpoint */ + if (sanity_check_ckpt(sbi)) + goto free_fail_no_cp; + if (cp_blks <= 1) goto done;

--- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -1141,6 +1141,7 @@ int sanity_check_ckpt(struct f2fs_sb_inf unsigned int sit_bitmap_size, nat_bitmap_size; unsigned int log_blocks_per_seg; unsigned int segment_count_main; + unsigned int cp_pack_start_sum, cp_payload; block_t user_block_count; int i;

@@ -1201,6 +1202,17 @@ int sanity_check_ckpt(struct f2fs_sb_inf return 1; }

+ cp_pack_start_sum = __start_sum_addr(sbi); + cp_payload = __cp_payload(sbi); + if (cp_pack_start_sum < cp_payload + 1 || + cp_pack_start_sum > blocks_per_seg - 1 - + NR_CURSEG_TYPE) { + f2fs_msg(sbi->sb, KERN_ERR, + "Wrong cp_pack_start_sum: %u", + cp_pack_start_sum); + return 1; + } + if (unlikely(f2fs_cp_error(sbi))) { f2fs_msg(sbi->sb, KERN_ERR, "A bug case: need to run fsck"); return 1;

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jaegeuk Kim jaegeuk@kernel.org

commit 89d13c38501df730cbb2e02c4499da1b5187119d upstream.

This patch fixes missing up_read call.

Fixes: c9b60788fc76 ("f2fs: fix to do sanity check with block address in main area") Reviewed-by: Chao Yu yuchao0@huawei.com Signed-off-by: Jaegeuk Kim jaegeuk@kernel.org Signed-off-by: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/f2fs/node.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

--- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -1342,8 +1342,10 @@ static int f2fs_write_node_page(struct p }

if (__is_valid_data_blkaddr(ni.blk_addr) && - !f2fs_is_valid_blkaddr(sbi, ni.blk_addr, DATA_GENERIC)) + !f2fs_is_valid_blkaddr(sbi, ni.blk_addr, DATA_GENERIC)) { + up_read(&sbi->node_write); goto redirty_out; + }

set_page_writeback(page); fio.blk_addr = ni.blk_addr;

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ben Hutchings ben@decadent.org.uk

The backport of commit afeaade90db4 "media: em28xx: make v4l2-compliance happier by starting sequence on zero" added a reset on em28xx_v4l2::field_count to em28xx_ctrl_notify(), but it should be done in em28xx_start_analog_streaming().

Signed-off-by: Ben Hutchings ben@decadent.org.uk Cc: Mauro Carvalho Chehab mchehab+samsung@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/media/usb/em28xx/em28xx-video.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/drivers/media/usb/em28xx/em28xx-video.c +++ b/drivers/media/usb/em28xx/em28xx-video.c @@ -930,6 +930,8 @@ int em28xx_start_analog_streaming(struct

em28xx_videodbg("%s\n", __func__);

+ dev->v4l2->field_count = 0; + /* Make sure streaming is not already in progress for this type of filehandle (e.g. video, vbi) */ rc = res_get(dev, vq->type); @@ -1149,8 +1151,6 @@ static void em28xx_ctrl_notify(struct v4 { struct em28xx *dev = priv;

- dev->v4l2->field_count = 0; - /* * In the case of non-AC97 volume controls, we still need * to do some setups at em28xx, in order to mute/unmute

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

[ Backport of upstream commit 4eaed6aa2c628101246bcabc91b203bfac1193f8 ]

In KVM we define the configuration of HCR_EL2 for a VHE HOST in HCR_HOST_VHE_FLAGS, but we don't have a similar definition for the non-VHE host flags, and open-code HCR_RW. Further, in head.S we open-code the flags for VHE and non-VHE configurations.

In future, we're going to want to configure more flags for the host, so lets add a HCR_HOST_NVHE_FLAGS defintion, and consistently use both HCR_HOST_VHE_FLAGS and HCR_HOST_NVHE_FLAGS in the kvm code and head.S.

We now use mov_q to generate the HCR_EL2 value, as we use when configuring other registers in head.S.

Reviewed-by: Marc Zyngier marc.zyngier@arm.com Reviewed-by: Richard Henderson richard.henderson@linaro.org Signed-off-by: Mark Rutland mark.rutland@arm.com Reviewed-by: Christoffer Dall christoffer.dall@arm.com Cc: Catalin Marinas catalin.marinas@arm.com Cc: Marc Zyngier marc.zyngier@arm.com Cc: Will Deacon will.deacon@arm.com Cc: kvmarm@lists.cs.columbia.edu Signed-off-by: Will Deacon will.deacon@arm.com [kristina: backport to 4.4.y: non-VHE only; __deactivate_traps_nvhe in assembly; add #include] Signed-off-by: Kristina Martsenko kristina.martsenko@arm.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm64/include/asm/kvm_arm.h | 1 + arch/arm64/kernel/head.S | 3 ++- arch/arm64/kvm/hyp.S | 2 +- 3 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h index ef8e13d379cb..013b7de45ee7 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -81,6 +81,7 @@ HCR_AMO | HCR_SWIO | HCR_TIDCP | HCR_RW) #define HCR_VIRT_EXCP_MASK (HCR_VA | HCR_VI | HCR_VF) #define HCR_INT_OVERRIDE (HCR_FMO | HCR_IMO) +#define HCR_HOST_NVHE_FLAGS (HCR_RW)

/* Hyp System Control Register (SCTLR_EL2) bits */ diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index d019c3a58cc2..0382eba4bf7b 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -30,6 +30,7 @@ #include <asm/cache.h> #include <asm/cputype.h> #include <asm/kernel-pgtable.h> +#include <asm/kvm_arm.h> #include <asm/memory.h> #include <asm/pgtable-hwdef.h> #include <asm/pgtable.h> @@ -464,7 +465,7 @@ CPU_LE( bic x0, x0, #(3 << 24) ) // Clear the EE and E0E bits for EL1 ret

/* Hyp configuration. */ -2: mov x0, #(1 << 31) // 64-bit EL1 +2: mov_q x0, HCR_HOST_NVHE_FLAGS msr hcr_el2, x0

/* Generic timers. */ diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S index 86c289832272..8d3da858c257 100644 --- a/arch/arm64/kvm/hyp.S +++ b/arch/arm64/kvm/hyp.S @@ -494,7 +494,7 @@ .endm

.macro deactivate_traps - mov x2, #HCR_RW + mov_q x2, HCR_HOST_NVHE_FLAGS msr hcr_el2, x2 msr hstr_el2, xzr

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eric Dumazet edumazet@google.com

[ Upstream commit 7d033c9f6a7fd3821af75620a0257db87c2b552a ]

This patch makes sure the flow label in the IPv6 header forged in ipv6_local_error() is initialized.

BUG: KMSAN: kernel-infoleak in _copy_to_user+0x16b/0x1f0 lib/usercopy.c:32 CPU: 1 PID: 24675 Comm: syz-executor1 Not tainted 4.20.0-rc7+ #4 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x173/0x1d0 lib/dump_stack.c:113 kmsan_report+0x12e/0x2a0 mm/kmsan/kmsan.c:613 kmsan_internal_check_memory+0x455/0xb00 mm/kmsan/kmsan.c:675 kmsan_copy_to_user+0xab/0xc0 mm/kmsan/kmsan_hooks.c:601 _copy_to_user+0x16b/0x1f0 lib/usercopy.c:32 copy_to_user include/linux/uaccess.h:177 [inline] move_addr_to_user+0x2e9/0x4f0 net/socket.c:227 ___sys_recvmsg+0x5d7/0x1140 net/socket.c:2284 __sys_recvmsg net/socket.c:2327 [inline] __do_sys_recvmsg net/socket.c:2337 [inline] __se_sys_recvmsg+0x2fa/0x450 net/socket.c:2334 __x64_sys_recvmsg+0x4a/0x70 net/socket.c:2334 do_syscall_64+0xbc/0xf0 arch/x86/entry/common.c:291 entry_SYSCALL_64_after_hwframe+0x63/0xe7 RIP: 0033:0x457ec9 Code: 6d b7 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 3b b7 fb ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007f8750c06c78 EFLAGS: 00000246 ORIG_RAX: 000000000000002f RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 0000000000457ec9 RDX: 0000000000002000 RSI: 0000000020000400 RDI: 0000000000000005 RBP: 000000000073bf00 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00007f8750c076d4 R13: 00000000004c4a60 R14: 00000000004d8140 R15: 00000000ffffffff

Uninit was stored to memory at: kmsan_save_stack_with_flags mm/kmsan/kmsan.c:204 [inline] kmsan_save_stack mm/kmsan/kmsan.c:219 [inline] kmsan_internal_chain_origin+0x134/0x230 mm/kmsan/kmsan.c:439 __msan_chain_origin+0x70/0xe0 mm/kmsan/kmsan_instr.c:200 ipv6_recv_error+0x1e3f/0x1eb0 net/ipv6/datagram.c:475 udpv6_recvmsg+0x398/0x2ab0 net/ipv6/udp.c:335 inet_recvmsg+0x4fb/0x600 net/ipv4/af_inet.c:830 sock_recvmsg_nosec net/socket.c:794 [inline] sock_recvmsg+0x1d1/0x230 net/socket.c:801 ___sys_recvmsg+0x4d5/0x1140 net/socket.c:2278 __sys_recvmsg net/socket.c:2327 [inline] __do_sys_recvmsg net/socket.c:2337 [inline] __se_sys_recvmsg+0x2fa/0x450 net/socket.c:2334 __x64_sys_recvmsg+0x4a/0x70 net/socket.c:2334 do_syscall_64+0xbc/0xf0 arch/x86/entry/common.c:291 entry_SYSCALL_64_after_hwframe+0x63/0xe7

Uninit was created at: kmsan_save_stack_with_flags mm/kmsan/kmsan.c:204 [inline] kmsan_internal_poison_shadow+0x92/0x150 mm/kmsan/kmsan.c:158 kmsan_kmalloc+0xa6/0x130 mm/kmsan/kmsan_hooks.c:176 kmsan_slab_alloc+0xe/0x10 mm/kmsan/kmsan_hooks.c:185 slab_post_alloc_hook mm/slab.h:446 [inline] slab_alloc_node mm/slub.c:2759 [inline] __kmalloc_node_track_caller+0xe18/0x1030 mm/slub.c:4383 __kmalloc_reserve net/core/skbuff.c:137 [inline] __alloc_skb+0x309/0xa20 net/core/skbuff.c:205 alloc_skb include/linux/skbuff.h:998 [inline] ipv6_local_error+0x1a7/0x9e0 net/ipv6/datagram.c:334 __ip6_append_data+0x129f/0x4fd0 net/ipv6/ip6_output.c:1311 ip6_make_skb+0x6cc/0xcf0 net/ipv6/ip6_output.c:1775 udpv6_sendmsg+0x3f8e/0x45d0 net/ipv6/udp.c:1384 inet_sendmsg+0x54a/0x720 net/ipv4/af_inet.c:798 sock_sendmsg_nosec net/socket.c:621 [inline] sock_sendmsg net/socket.c:631 [inline] __sys_sendto+0x8c4/0xac0 net/socket.c:1788 __do_sys_sendto net/socket.c:1800 [inline] __se_sys_sendto+0x107/0x130 net/socket.c:1796 __x64_sys_sendto+0x6e/0x90 net/socket.c:1796 do_syscall_64+0xbc/0xf0 arch/x86/entry/common.c:291 entry_SYSCALL_64_after_hwframe+0x63/0xe7

Bytes 4-7 of 28 are uninitialized Memory access of size 28 starts at ffff8881937bfce0 Data copied to user address 0000000020000000

Signed-off-by: Eric Dumazet edumazet@google.com Reported-by: syzbot syzkaller@googlegroups.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/ipv6/datagram.c | 1 + 1 file changed, 1 insertion(+)

--- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -290,6 +290,7 @@ void ipv6_local_error(struct sock *sk, i skb_reset_network_header(skb); iph = ipv6_hdr(skb); iph->daddr = fl6->daddr; + ip6_flow_hdr(iph, 0, 0);

serr = SKB_EXT_ERR(skb); serr->ee.ee_errno = err;

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jason Gunthorpe jgg@mellanox.com

[ Upstream commit d972f3dce8d161e2142da0ab1ef25df00e2f21a9 ]

'dev' is non NULL when the addr_len check triggers so it must goto a label that does the dev_put otherwise dev will have a leaked refcount.

This bug causes the ib_ipoib module to become unloadable when using systemd-network as it triggers this check on InfiniBand links.

Fixes: 99137b7888f4 ("packet: validate address length") Reported-by: Leon Romanovsky leonro@mellanox.com Signed-off-by: Jason Gunthorpe jgg@mellanox.com Acked-by: Willem de Bruijn willemb@google.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/packet/af_packet.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2514,7 +2514,7 @@ static int tpacket_snd(struct packet_soc addr = saddr->sll_halen ? saddr->sll_addr : NULL; dev = dev_get_by_index(sock_net(&po->sk), saddr->sll_ifindex); if (addr && dev && saddr->sll_halen < dev->addr_len) - goto out; + goto out_put; }

err = -ENXIO; @@ -2683,7 +2683,7 @@ static int packet_snd(struct socket *soc addr = saddr->sll_halen ? saddr->sll_addr : NULL; dev = dev_get_by_index(sock_net(sk), saddr->sll_ifindex); if (addr && dev && saddr->sll_halen < dev->addr_len) - goto out; + goto out_unlock; }

err = -ENXIO;

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Harsh Jain harsh@chelsio.com

commit a7773363624b034ab198c738661253d20a8055c2 upstream.

Authencesn template in decrypt path unconditionally calls aead_request_complete after ahash_verify which leads to following kernel panic in after decryption.

[ 338.539800] BUG: unable to handle kernel NULL pointer dereference at 0000000000000004 [ 338.548372] PGD 0 P4D 0 [ 338.551157] Oops: 0000 [#1] SMP PTI [ 338.554919] CPU: 0 PID: 0 Comm: swapper/0 Kdump: loaded Tainted: G W I 4.19.7+ #13 [ 338.564431] Hardware name: Supermicro X8ST3/X8ST3, BIOS 2.0 07/29/10 [ 338.572212] RIP: 0010:esp_input_done2+0x350/0x410 [esp4] [ 338.578030] Code: ff 0f b6 68 10 48 8b 83 c8 00 00 00 e9 8e fe ff ff 8b 04 25 04 00 00 00 83 e8 01 48 98 48 8b 3c c5 10 00 00 00 e9 f7 fd ff ff <8b> 04 25 04 00 00 00 83 e8 01 48 98 4c 8b 24 c5 10 00 00 00 e9 3b [ 338.598547] RSP: 0018:ffff911c97803c00 EFLAGS: 00010246 [ 338.604268] RAX: 0000000000000002 RBX: ffff911c4469ee00 RCX: 0000000000000000 [ 338.612090] RDX: 0000000000000000 RSI: 0000000000000130 RDI: ffff911b87c20400 [ 338.619874] RBP: 0000000000000000 R08: ffff911b87c20498 R09: 000000000000000a [ 338.627610] R10: 0000000000000001 R11: 0000000000000004 R12: 0000000000000000 [ 338.635402] R13: ffff911c89590000 R14: ffff911c91730000 R15: 0000000000000000 [ 338.643234] FS: 0000000000000000(0000) GS:ffff911c97800000(0000) knlGS:0000000000000000 [ 338.652047] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 338.658299] CR2: 0000000000000004 CR3: 00000001ec20a000 CR4: 00000000000006f0 [ 338.666382] Call Trace: [ 338.669051] <IRQ> [ 338.671254] esp_input_done+0x12/0x20 [esp4] [ 338.675922] chcr_handle_resp+0x3b5/0x790 [chcr] [ 338.680949] cpl_fw6_pld_handler+0x37/0x60 [chcr] [ 338.686080] chcr_uld_rx_handler+0x22/0x50 [chcr] [ 338.691233] uldrx_handler+0x8c/0xc0 [cxgb4] [ 338.695923] process_responses+0x2f0/0x5d0 [cxgb4] [ 338.701177] ? bitmap_find_next_zero_area_off+0x3a/0x90 [ 338.706882] ? matrix_alloc_area.constprop.7+0x60/0x90 [ 338.712517] ? apic_update_irq_cfg+0x82/0xf0 [ 338.717177] napi_rx_handler+0x14/0xe0 [cxgb4] [ 338.722015] net_rx_action+0x2aa/0x3e0 [ 338.726136] __do_softirq+0xcb/0x280 [ 338.730054] irq_exit+0xde/0xf0 [ 338.733504] do_IRQ+0x54/0xd0 [ 338.736745] common_interrupt+0xf/0xf

Fixes: 104880a6b470 ("crypto: authencesn - Convert to new AEAD...") Signed-off-by: Harsh Jain harsh@chelsio.com Cc: stable@vger.kernel.org Signed-off-by: Herbert Xu herbert@gondor.apana.org.au Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- crypto/authencesn.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/crypto/authencesn.c +++ b/crypto/authencesn.c @@ -276,7 +276,7 @@ static void authenc_esn_verify_ahash_don struct aead_request *req = areq->data;

err = err ?: crypto_authenc_esn_decrypt_tail(req, 0); - aead_request_complete(req, err); + authenc_esn_request_complete(req, err); }

static int crypto_authenc_esn_decrypt(struct aead_request *req)

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Josef Bacik josef@toxicpanda.com

commit 74d5d229b1bf60f93bff244b2dfc0eb21ec32a07 upstream.

If we flip read-only before we initiate writeback on all dirty pages for ordered extents we've created then we'll have ordered extents left over on umount, which results in all sorts of bad things happening. Fix this by making sure we wait on ordered extents if we have to do the aborted transaction cleanup stuff.

generic/475 can produce this warning:

[ 8531.177332] WARNING: CPU: 2 PID: 11997 at fs/btrfs/disk-io.c:3856 btrfs_free_fs_root+0x95/0xa0 [btrfs] [ 8531.183282] CPU: 2 PID: 11997 Comm: umount Tainted: G W 5.0.0-rc1-default+ #394 [ 8531.185164] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996),BIOS rel-1.11.2-0-gf9626cc-prebuilt.qemu-project.org 04/01/2014 [ 8531.187851] RIP: 0010:btrfs_free_fs_root+0x95/0xa0 [btrfs] [ 8531.193082] RSP: 0018:ffffb1ab86163d98 EFLAGS: 00010286 [ 8531.194198] RAX: ffff9f3449494d18 RBX: ffff9f34a2695000 RCX:0000000000000000 [ 8531.195629] RDX: 0000000000000002 RSI: 0000000000000001 RDI:0000000000000000 [ 8531.197315] RBP: ffff9f344e930000 R08: 0000000000000001 R09:0000000000000000 [ 8531.199095] R10: 0000000000000000 R11: ffff9f34494d4ff8 R12:ffffb1ab86163dc0 [ 8531.200870] R13: ffff9f344e9300b0 R14: ffffb1ab86163db8 R15:0000000000000000 [ 8531.202707] FS: 00007fc68e949fc0(0000) GS:ffff9f34bd800000(0000)knlGS:0000000000000000 [ 8531.204851] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 8531.205942] CR2: 00007ffde8114dd8 CR3: 000000002dfbd000 CR4:00000000000006e0 [ 8531.207516] Call Trace: [ 8531.208175] btrfs_free_fs_roots+0xdb/0x170 [btrfs] [ 8531.210209] ? wait_for_completion+0x5b/0x190 [ 8531.211303] close_ctree+0x157/0x350 [btrfs] [ 8531.212412] generic_shutdown_super+0x64/0x100 [ 8531.213485] kill_anon_super+0x14/0x30 [ 8531.214430] btrfs_kill_super+0x12/0xa0 [btrfs] [ 8531.215539] deactivate_locked_super+0x29/0x60 [ 8531.216633] cleanup_mnt+0x3b/0x70 [ 8531.217497] task_work_run+0x98/0xc0 [ 8531.218397] exit_to_usermode_loop+0x83/0x90 [ 8531.219324] do_syscall_64+0x15b/0x180 [ 8531.220192] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 8531.221286] RIP: 0033:0x7fc68e5e4d07 [ 8531.225621] RSP: 002b:00007ffde8116608 EFLAGS: 00000246 ORIG_RAX:00000000000000a6 [ 8531.227512] RAX: 0000000000000000 RBX: 00005580c2175970 RCX:00007fc68e5e4d07 [ 8531.229098] RDX: 0000000000000001 RSI: 0000000000000000 RDI:00005580c2175b80 [ 8531.230730] RBP: 0000000000000000 R08: 00005580c2175ba0 R09:00007ffde8114e80 [ 8531.232269] R10: 0000000000000000 R11: 0000000000000246 R12:00005580c2175b80 [ 8531.233839] R13: 00007fc68eac61c4 R14: 00005580c2175a68 R15:0000000000000000

Leaving a tree in the rb-tree:

3853 void btrfs_free_fs_root(struct btrfs_root *root) 3854 { 3855 iput(root->ino_cache_inode); 3856 WARN_ON(!RB_EMPTY_ROOT(&root->inode_tree));

CC: stable@vger.kernel.org Reviewed-by: Nikolay Borisov nborisov@suse.com Signed-off-by: Josef Bacik josef@toxicpanda.com [ add stacktrace ] Signed-off-by: David Sterba dsterba@suse.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- fs/btrfs/disk-io.c | 8 ++++++++ 1 file changed, 8 insertions(+)

--- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -4111,6 +4111,14 @@ static void btrfs_destroy_all_ordered_ex spin_lock(&fs_info->ordered_root_lock); } spin_unlock(&fs_info->ordered_root_lock); + + /* + * We need this here because if we've been flipped read-only we won't + * get sync() from the umount, so we need to make sure any ordered + * extents that haven't had their dirty pages IO start writeout yet + * actually get run and error out properly. + */ + btrfs_wait_ordered_roots(fs_info, -1); }

static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ivan Mironov mironov.ivan@gmail.com

commit 44759979a49bfd2d20d789add7fa81a21eb1a4ab upstream.

Changing of caching mode via /sys/devices/.../scsi_disk/.../cache_type may fail if device responds to MODE SENSE command with DPOFUA flag set, and then checks this flag to be not set on MODE SELECT command.

In this scenario, when trying to change cache_type, write always fails:

# echo "none" >cache_type bash: echo: write error: Invalid argument

And following appears in dmesg:

[13007.865745] sd 1:0:1:0: [sda] Sense Key : Illegal Request [current] [13007.865753] sd 1:0:1:0: [sda] Add. Sense: Invalid field in parameter list

From SBC-4 r15, 6.5.1 "Mode pages overview", description of DEVICE-SPECIFIC

PARAMETER field in the mode parameter header: ... The write protect (WP) bit for mode data sent with a MODE SELECT command shall be ignored by the device server. ... The DPOFUA bit is reserved for mode data sent with a MODE SELECT command. ...

The remaining bits in the DEVICE-SPECIFIC PARAMETER byte are also reserved and shall be set to zero.

[mkp: shuffled commentary to commit description]

Cc: stable@vger.kernel.org Signed-off-by: Ivan Mironov mironov.ivan@gmail.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/scsi/sd.c | 6 ++++++ 1 file changed, 6 insertions(+)

--- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -207,6 +207,12 @@ cache_type_store(struct device *dev, str sp = buffer_data[0] & 0x80 ? 1 : 0; buffer_data[0] &= ~0x80;

+ /* + * Ensure WP, DPOFUA, and RESERVED fields are cleared in + * received mode parameter buffer before doing MODE SELECT. + */ + data.device_specific = 0; + if (scsi_mode_select(sdp, 1, sp, 8, buffer_data, len, SD_TIMEOUT, SD_MAX_RETRIES, &data, &sshdr)) { if (scsi_sense_valid(&sshdr))

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jonathan Hunter jonathanh@nvidia.com

commit ac4ca4b9f4623ba5e1ea7a582f286567c611e027 upstream.

The tps6586x driver creates an irqchip that is used by its various child devices for managing interrupts. The tps6586x-rtc device is one of its children that uses the tps6586x irqchip. When using the tps6586x-rtc as a wake-up device from suspend, the following is seen:

PM: Syncing filesystems ... done. Freezing user space processes ... (elapsed 0.001 seconds) done. OOM killer disabled. Freezing remaining freezable tasks ... (elapsed 0.000 seconds) done. Disabling non-boot CPUs ... Entering suspend state LP1 Enabling non-boot CPUs ... CPU1 is up tps6586x 3-0034: failed to read interrupt status tps6586x 3-0034: failed to read interrupt status

The reason why the tps6586x interrupt status cannot be read is because the tps6586x interrupt is not masked during suspend and when the tps6586x-rtc interrupt occurs, to wake-up the device, the interrupt is seen before the i2c controller has been resumed in order to read the tps6586x interrupt status.

The tps6586x-rtc driver sets it's interrupt as a wake-up source during suspend, which gets propagated to the parent tps6586x interrupt. However, the tps6586x-rtc driver cannot disable it's interrupt during suspend otherwise we would never be woken up and so the tps6586x must disable it's interrupt instead.

Prevent the tps6586x interrupt handler from executing on exiting suspend before the i2c controller has been resumed by disabling the tps6586x interrupt on entering suspend and re-enabling it on resuming from suspend.

Cc: stable@vger.kernel.org Signed-off-by: Jon Hunter jonathanh@nvidia.com Reviewed-by: Dmitry Osipenko digetx@gmail.com Tested-by: Dmitry Osipenko digetx@gmail.com Acked-by: Thierry Reding treding@nvidia.com Signed-off-by: Lee Jones lee.jones@linaro.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/mfd/tps6586x.c | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+)

--- a/drivers/mfd/tps6586x.c +++ b/drivers/mfd/tps6586x.c @@ -594,6 +594,29 @@ static int tps6586x_i2c_remove(struct i2 return 0; }

+static int __maybe_unused tps6586x_i2c_suspend(struct device *dev) +{ + struct tps6586x *tps6586x = dev_get_drvdata(dev); + + if (tps6586x->client->irq) + disable_irq(tps6586x->client->irq); + + return 0; +} + +static int __maybe_unused tps6586x_i2c_resume(struct device *dev) +{ + struct tps6586x *tps6586x = dev_get_drvdata(dev); + + if (tps6586x->client->irq) + enable_irq(tps6586x->client->irq); + + return 0; +} + +static SIMPLE_DEV_PM_OPS(tps6586x_pm_ops, tps6586x_i2c_suspend, + tps6586x_i2c_resume); + static const struct i2c_device_id tps6586x_id_table[] = { { "tps6586x", 0 }, { }, @@ -604,6 +627,7 @@ static struct i2c_driver tps6586x_driver .driver = { .name = "tps6586x", .of_match_table = of_match_ptr(tps6586x_of_match), + .pm = &tps6586x_pm_ops, }, .probe = tps6586x_i2c_probe, .remove = tps6586x_i2c_remove,

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Vlad Tsyrklevich vlad@tsyrklevich.net

commit a01421e4484327fe44f8e126793ed5a48a221e24 upstream.

Using [1] for static analysis I found that the OMAPFB_QUERY_PLANE, OMAPFB_GET_COLOR_KEY, OMAPFB_GET_DISPLAY_INFO, and OMAPFB_GET_VRAM_INFO cases could all leak uninitialized stack memory--either due to uninitialized padding or 'reserved' fields.

Fix them by clearing the shared union used to store copied out data.

[1] https://github.com/vlad902/kernel-uninitialized-memory-checker

Signed-off-by: Vlad Tsyrklevich vlad@tsyrklevich.net Reviewed-by: Kees Cook keescook@chromium.org Fixes: b39a982ddecf ("OMAP: DSS2: omapfb driver") Cc: security@kernel.org [b.zolnierkie: prefix patch subject with "omap2fb: "] Signed-off-by: Bartlomiej Zolnierkiewicz b.zolnierkie@samsung.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/video/fbdev/omap2/omapfb/omapfb-ioctl.c | 2 ++ 1 file changed, 2 insertions(+)

--- a/drivers/video/fbdev/omap2/omapfb/omapfb-ioctl.c +++ b/drivers/video/fbdev/omap2/omapfb/omapfb-ioctl.c @@ -609,6 +609,8 @@ int omapfb_ioctl(struct fb_info *fbi, un

int r = 0;

+ memset(&p, 0, sizeof(p)); + switch (cmd) { case OMAPFB_SYNC_GFX: DBG("ioctl SYNC_GFX\n");

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Hans Verkuil hverkuil-cisco@xs4all.nl

commit 9729d6d282a6d7ce88e64c9119cecdf79edf4e88 upstream.

The capture DV timings capabilities allowed for a minimum width and height of 0. So passing a timings struct with 0 values is allowed and will later cause a division by zero.

Ensure that the width and height must be >= 16 to avoid this.

Signed-off-by: Hans Verkuil hverkuil-cisco@xs4all.nl Reported-by: syzbot+57c3d83d71187054d56f@syzkaller.appspotmail.com Signed-off-by: Mauro Carvalho Chehab mchehab+samsung@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/media/platform/vivid/vivid-vid-common.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/media/platform/vivid/vivid-vid-common.c +++ b/drivers/media/platform/vivid/vivid-vid-common.c @@ -33,7 +33,7 @@ const struct v4l2_dv_timings_cap vivid_d .type = V4L2_DV_BT_656_1120, /* keep this initialization for compatibility with GCC < 4.4.6 */ .reserved = { 0 }, - V4L2_INIT_BT_TIMINGS(0, MAX_WIDTH, 0, MAX_HEIGHT, 14000000, 775000000, + V4L2_INIT_BT_TIMINGS(16, MAX_WIDTH, 16, MAX_HEIGHT, 14000000, 775000000, V4L2_DV_BT_STD_CEA861 | V4L2_DV_BT_STD_DMT | V4L2_DV_BT_STD_CVT | V4L2_DV_BT_STD_GTF, V4L2_DV_BT_CAP_PROGRESSIVE | V4L2_DV_BT_CAP_INTERLACED)

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Hans Verkuil hverkuil@xs4all.nl

commit cd26d1c4d1bc947b56ae404998ae2276df7b39b7 upstream.

If a filehandle is dup()ped, then it is possible to close it from one fd and call mmap from the other. This creates a race condition in vb2_mmap where it is using queue data that __vb2_queue_free (called from close()) is in the process of releasing.

By moving up the mutex_lock(mmap_lock) in vb2_mmap this race is avoided since __vb2_queue_free is called with the same mutex locked. So vb2_mmap now reads consistent buffer data.

Signed-off-by: Hans Verkuil hverkuil@xs4all.nl Reported-by: syzbot+be93025dd45dccd8923c@syzkaller.appspotmail.com Signed-off-by: Hans Verkuil hansverk@cisco.com Signed-off-by: Mauro Carvalho Chehab mchehab+samsung@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/media/v4l2-core/videobuf2-core.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-)

--- a/drivers/media/v4l2-core/videobuf2-core.c +++ b/drivers/media/v4l2-core/videobuf2-core.c @@ -1976,9 +1976,13 @@ int vb2_mmap(struct vb2_queue *q, struct return -EINVAL; } } + + mutex_lock(&q->mmap_lock); + if (vb2_fileio_is_active(q)) { dprintk(1, "mmap: file io in progress\n"); - return -EBUSY; + ret = -EBUSY; + goto unlock; }

/* @@ -1986,7 +1990,7 @@ int vb2_mmap(struct vb2_queue *q, struct */ ret = __find_plane_by_offset(q, off, &buffer, &plane); if (ret) - return ret; + goto unlock;

vb = q->bufs[buffer];

@@ -2002,8 +2006,9 @@ int vb2_mmap(struct vb2_queue *q, struct return -EINVAL; }

- mutex_lock(&q->mmap_lock); ret = call_memop(vb, mmap, vb->planes[plane].mem_priv, vma); + +unlock: mutex_unlock(&q->mmap_lock); if (ret) return ret;

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Stephen Smalley sds@tycho.nsa.gov

commit 5b0e7310a2a33c06edc7eb81ffc521af9b2c5610 upstream.

levdatum->level can be NULL if we encounter an error while loading the policy during sens_read prior to initializing it. Make sure sens_destroy handles that case correctly.

Reported-by: syzbot+6664500f0f18f07a5c0e@syzkaller.appspotmail.com Signed-off-by: Stephen Smalley sds@tycho.nsa.gov Signed-off-by: Paul Moore paul@paul-moore.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- security/selinux/ss/policydb.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

--- a/security/selinux/ss/policydb.c +++ b/security/selinux/ss/policydb.c @@ -726,7 +726,8 @@ static int sens_destroy(void *key, void kfree(key); if (datum) { levdatum = datum; - ebitmap_destroy(&levdatum->level->cat); + if (levdatum->level) + ebitmap_destroy(&levdatum->level->cat); kfree(levdatum->level); } kfree(datum);

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ying Xue ying.xue@windriver.com

commit 8b66fee7f8ee18f9c51260e7a43ab37db5177a05 upstream.

syzbot reports following splat:

BUG: KMSAN: uninit-value in strlen+0x3b/0xa0 lib/string.c:486 CPU: 1 PID: 11057 Comm: syz-executor0 Not tainted 4.20.0-rc7+ #2 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x173/0x1d0 lib/dump_stack.c:113 kmsan_report+0x12e/0x2a0 mm/kmsan/kmsan.c:613 __msan_warning+0x82/0xf0 mm/kmsan/kmsan_instr.c:295 strlen+0x3b/0xa0 lib/string.c:486 nla_put_string include/net/netlink.h:1154 [inline] tipc_nl_compat_link_reset_stats+0x1f0/0x360 net/tipc/netlink_compat.c:760 __tipc_nl_compat_doit net/tipc/netlink_compat.c:311 [inline] tipc_nl_compat_doit+0x3aa/0xaf0 net/tipc/netlink_compat.c:344 tipc_nl_compat_handle net/tipc/netlink_compat.c:1107 [inline] tipc_nl_compat_recv+0x14d7/0x2760 net/tipc/netlink_compat.c:1210 genl_family_rcv_msg net/netlink/genetlink.c:601 [inline] genl_rcv_msg+0x185f/0x1a60 net/netlink/genetlink.c:626 netlink_rcv_skb+0x444/0x640 net/netlink/af_netlink.c:2477 genl_rcv+0x63/0x80 net/netlink/genetlink.c:637 netlink_unicast_kernel net/netlink/af_netlink.c:1310 [inline] netlink_unicast+0xf40/0x1020 net/netlink/af_netlink.c:1336 netlink_sendmsg+0x127f/0x1300 net/netlink/af_netlink.c:1917 sock_sendmsg_nosec net/socket.c:621 [inline] sock_sendmsg net/socket.c:631 [inline] ___sys_sendmsg+0xdb9/0x11b0 net/socket.c:2116 __sys_sendmsg net/socket.c:2154 [inline] __do_sys_sendmsg net/socket.c:2163 [inline] __se_sys_sendmsg+0x305/0x460 net/socket.c:2161 __x64_sys_sendmsg+0x4a/0x70 net/socket.c:2161 do_syscall_64+0xbc/0xf0 arch/x86/entry/common.c:291 entry_SYSCALL_64_after_hwframe+0x63/0xe7 RIP: 0033:0x457ec9 Code: 6d b7 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 3b b7 fb ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007f2557338c78 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 0000000000457ec9 RDX: 0000000000000000 RSI: 00000000200001c0 RDI: 0000000000000003 RBP: 000000000073bf00 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00007f25573396d4 R13: 00000000004cb478 R14: 00000000004d86c8 R15: 00000000ffffffff

Uninit was created at: kmsan_save_stack_with_flags mm/kmsan/kmsan.c:204 [inline] kmsan_internal_poison_shadow+0x92/0x150 mm/kmsan/kmsan.c:158 kmsan_kmalloc+0xa6/0x130 mm/kmsan/kmsan_hooks.c:176 kmsan_slab_alloc+0xe/0x10 mm/kmsan/kmsan_hooks.c:185 slab_post_alloc_hook mm/slab.h:446 [inline] slab_alloc_node mm/slub.c:2759 [inline] __kmalloc_node_track_caller+0xe18/0x1030 mm/slub.c:4383 __kmalloc_reserve net/core/skbuff.c:137 [inline] __alloc_skb+0x309/0xa20 net/core/skbuff.c:205 alloc_skb include/linux/skbuff.h:998 [inline] netlink_alloc_large_skb net/netlink/af_netlink.c:1182 [inline] netlink_sendmsg+0xb82/0x1300 net/netlink/af_netlink.c:1892 sock_sendmsg_nosec net/socket.c:621 [inline] sock_sendmsg net/socket.c:631 [inline] ___sys_sendmsg+0xdb9/0x11b0 net/socket.c:2116 __sys_sendmsg net/socket.c:2154 [inline] __do_sys_sendmsg net/socket.c:2163 [inline] __se_sys_sendmsg+0x305/0x460 net/socket.c:2161 __x64_sys_sendmsg+0x4a/0x70 net/socket.c:2161 do_syscall_64+0xbc/0xf0 arch/x86/entry/common.c:291 entry_SYSCALL_64_after_hwframe+0x63/0xe7

The uninitialised access happened in tipc_nl_compat_link_reset_stats: nla_put_string(skb, TIPC_NLA_LINK_NAME, name)

This is because name string is not validated before it's used.

Reported-by: syzbot+e01d94b5a4c266be6e4c@syzkaller.appspotmail.com Signed-off-by: Ying Xue ying.xue@windriver.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- net/tipc/netlink_compat.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+)

--- a/net/tipc/netlink_compat.c +++ b/net/tipc/netlink_compat.c @@ -87,6 +87,11 @@ static int tipc_skb_tailroom(struct sk_b return limit; }

+static inline int TLV_GET_DATA_LEN(struct tlv_desc *tlv) +{ + return TLV_GET_LEN(tlv) - TLV_SPACE(0); +} + static int tipc_add_tlv(struct sk_buff *skb, u16 type, void *data, u16 len) { struct tlv_desc *tlv = (struct tlv_desc *)skb_tail_pointer(skb); @@ -166,6 +171,11 @@ static struct sk_buff *tipc_get_err_tlv( return buf; }

+static inline bool string_is_valid(char *s, int len) +{ + return memchr(s, '\0', len) ? true : false; +} + static int __tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd, struct tipc_nl_compat_msg *msg, struct sk_buff *arg) @@ -711,6 +721,7 @@ static int tipc_nl_compat_link_reset_sta { char *name; struct nlattr *link; + int len;

name = (char *)TLV_DATA(msg->req);

@@ -718,6 +729,10 @@ static int tipc_nl_compat_link_reset_sta if (!link) return -EMSGSIZE;

+ len = min_t(int, TLV_GET_DATA_LEN(msg->req), TIPC_MAX_LINK_NAME); + if (!string_is_valid(name, len)) + return -EINVAL; + if (nla_put_string(skb, TIPC_NLA_LINK_NAME, name)) return -EMSGSIZE;

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ying Xue ying.xue@windriver.com

commit edf5ff04a45750ac8ce2435974f001dc9cfbf055 upstream.

syzbot reports following splat:

BUG: KMSAN: uninit-value in strlen+0x3b/0xa0 lib/string.c:486 CPU: 1 PID: 9306 Comm: syz-executor172 Not tainted 4.20.0-rc7+ #2 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x173/0x1d0 lib/dump_stack.c:113 kmsan_report+0x12e/0x2a0 mm/kmsan/kmsan.c:613 __msan_warning+0x82/0xf0 mm/kmsan/kmsan_instr.c:313 strlen+0x3b/0xa0 lib/string.c:486 nla_put_string include/net/netlink.h:1154 [inline] __tipc_nl_compat_link_set net/tipc/netlink_compat.c:708 [inline] tipc_nl_compat_link_set+0x929/0x1220 net/tipc/netlink_compat.c:744 __tipc_nl_compat_doit net/tipc/netlink_compat.c:311 [inline] tipc_nl_compat_doit+0x3aa/0xaf0 net/tipc/netlink_compat.c:344 tipc_nl_compat_handle net/tipc/netlink_compat.c:1107 [inline] tipc_nl_compat_recv+0x14d7/0x2760 net/tipc/netlink_compat.c:1210 genl_family_rcv_msg net/netlink/genetlink.c:601 [inline] genl_rcv_msg+0x185f/0x1a60 net/netlink/genetlink.c:626 netlink_rcv_skb+0x444/0x640 net/netlink/af_netlink.c:2477 genl_rcv+0x63/0x80 net/netlink/genetlink.c:637 netlink_unicast_kernel net/netlink/af_netlink.c:1310 [inline] netlink_unicast+0xf40/0x1020 net/netlink/af_netlink.c:1336 netlink_sendmsg+0x127f/0x1300 net/netlink/af_netlink.c:1917 sock_sendmsg_nosec net/socket.c:621 [inline] sock_sendmsg net/socket.c:631 [inline] ___sys_sendmsg+0xdb9/0x11b0 net/socket.c:2116 __sys_sendmsg net/socket.c:2154 [inline] __do_sys_sendmsg net/socket.c:2163 [inline] __se_sys_sendmsg+0x305/0x460 net/socket.c:2161 __x64_sys_sendmsg+0x4a/0x70 net/socket.c:2161 do_syscall_64+0xbc/0xf0 arch/x86/entry/common.c:291 entry_SYSCALL_64_after_hwframe+0x63/0xe7

The uninitialised access happened in nla_put_string(skb, TIPC_NLA_LINK_NAME, lc->name)

This is because lc->name string is not validated before it's used.

Reported-by: syzbot+d78b8a29241a195aefb8@syzkaller.appspotmail.com Signed-off-by: Ying Xue ying.xue@windriver.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- net/tipc/netlink_compat.c | 5 +++++ 1 file changed, 5 insertions(+)

--- a/net/tipc/netlink_compat.c +++ b/net/tipc/netlink_compat.c @@ -723,9 +723,14 @@ static int tipc_nl_compat_link_set(struc struct tipc_link_config *lc; struct tipc_bearer *bearer; struct tipc_media *media; + int len;

lc = (struct tipc_link_config *)TLV_DATA(msg->req);

+ len = min_t(int, TLV_GET_DATA_LEN(msg->req), TIPC_MAX_LINK_NAME); + if (!string_is_valid(lc->name, len)) + return -EINVAL; + media = tipc_media_find(lc->name); if (media) { cmd->doit = &tipc_nl_media_set;

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ying Xue ying.xue@windriver.com

commit 2753ca5d9009c180dbfd4c802c80983b4b6108d1 upstream.

BUG: KMSAN: uninit-value in tipc_nl_compat_doit+0x404/0xa10 net/tipc/netlink_compat.c:335 CPU: 0 PID: 4514 Comm: syz-executor485 Not tainted 4.16.0+ #87 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:17 [inline] dump_stack+0x185/0x1d0 lib/dump_stack.c:53 kmsan_report+0x142/0x240 mm/kmsan/kmsan.c:1067 __msan_warning_32+0x6c/0xb0 mm/kmsan/kmsan_instr.c:683 tipc_nl_compat_doit+0x404/0xa10 net/tipc/netlink_compat.c:335 tipc_nl_compat_recv+0x164b/0x2700 net/tipc/netlink_compat.c:1153 genl_family_rcv_msg net/netlink/genetlink.c:599 [inline] genl_rcv_msg+0x1686/0x1810 net/netlink/genetlink.c:624 netlink_rcv_skb+0x378/0x600 net/netlink/af_netlink.c:2447 genl_rcv+0x63/0x80 net/netlink/genetlink.c:635 netlink_unicast_kernel net/netlink/af_netlink.c:1311 [inline] netlink_unicast+0x166b/0x1740 net/netlink/af_netlink.c:1337 netlink_sendmsg+0x1048/0x1310 net/netlink/af_netlink.c:1900 sock_sendmsg_nosec net/socket.c:630 [inline] sock_sendmsg net/socket.c:640 [inline] ___sys_sendmsg+0xec0/0x1310 net/socket.c:2046 __sys_sendmsg net/socket.c:2080 [inline] SYSC_sendmsg+0x2a3/0x3d0 net/socket.c:2091 SyS_sendmsg+0x54/0x80 net/socket.c:2087 do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 RIP: 0033:0x43fda9 RSP: 002b:00007ffd0c184ba8 EFLAGS: 00000213 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 00000000004002c8 RCX: 000000000043fda9 RDX: 0000000000000000 RSI: 0000000020023000 RDI: 0000000000000003 RBP: 00000000006ca018 R08: 00000000004002c8 R09: 00000000004002c8 R10: 00000000004002c8 R11: 0000000000000213 R12: 00000000004016d0 R13: 0000000000401760 R14: 0000000000000000 R15: 0000000000000000

Uninit was created at: kmsan_save_stack_with_flags mm/kmsan/kmsan.c:278 [inline] kmsan_internal_poison_shadow+0xb8/0x1b0 mm/kmsan/kmsan.c:188 kmsan_kmalloc+0x94/0x100 mm/kmsan/kmsan.c:314 kmsan_slab_alloc+0x11/0x20 mm/kmsan/kmsan.c:321 slab_post_alloc_hook mm/slab.h:445 [inline] slab_alloc_node mm/slub.c:2737 [inline] __kmalloc_node_track_caller+0xaed/0x11c0 mm/slub.c:4369 __kmalloc_reserve net/core/skbuff.c:138 [inline] __alloc_skb+0x2cf/0x9f0 net/core/skbuff.c:206 alloc_skb include/linux/skbuff.h:984 [inline] netlink_alloc_large_skb net/netlink/af_netlink.c:1183 [inline] netlink_sendmsg+0x9a6/0x1310 net/netlink/af_netlink.c:1875 sock_sendmsg_nosec net/socket.c:630 [inline] sock_sendmsg net/socket.c:640 [inline] ___sys_sendmsg+0xec0/0x1310 net/socket.c:2046 __sys_sendmsg net/socket.c:2080 [inline] SYSC_sendmsg+0x2a3/0x3d0 net/socket.c:2091 SyS_sendmsg+0x54/0x80 net/socket.c:2087 do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287 entry_SYSCALL_64_after_hwframe+0x3d/0xa2

In tipc_nl_compat_recv(), when the len variable returned by nlmsg_attrlen() is 0, the message is still treated as a valid one, which is obviously unresonable. When len is zero, it means the message not only doesn't contain any valid TLV payload, but also TLV header is not included. Under this stituation, tlv_type field in TLV header is still accessed in tipc_nl_compat_dumpit() or tipc_nl_compat_doit(), but the field space is obviously illegal. Of course, it is not initialized.

Reported-by: syzbot+bca0dc46634781f08b38@syzkaller.appspotmail.com Reported-by: syzbot+6bdb590321a7ae40c1a6@syzkaller.appspotmail.com Signed-off-by: Ying Xue ying.xue@windriver.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- net/tipc/netlink_compat.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/net/tipc/netlink_compat.c +++ b/net/tipc/netlink_compat.c @@ -1165,7 +1165,7 @@ static int tipc_nl_compat_recv(struct sk }

len = nlmsg_attrlen(req_nlh, GENL_HDRLEN + TIPC_GENL_HDRLEN); - if (len && !TLV_OK(msg.req, len)) { + if (!len || !TLV_OK(msg.req, len)) { msg.rep = tipc_get_err_tlv(TIPC_CFG_NOT_SUPPORTED); err = -EOPNOTSUPP; goto send;

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jan Kara jack@suse.cz

commit 967d1dc144b50ad005e5eecdfadfbcfb399ffff6 upstream.

__loop_release() has a single call site. Fold it there. This is currently not a huge win but it will make following replacement of loop_index_mutex more obvious.

Signed-off-by: Jan Kara jack@suse.cz Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/block/loop.c | 16 +++++++--------- 1 file changed, 7 insertions(+), 9 deletions(-)

--- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -1586,12 +1586,15 @@ out: return err; }

-static void __lo_release(struct loop_device *lo) +static void lo_release(struct gendisk *disk, fmode_t mode) { + struct loop_device *lo; int err;

+ mutex_lock(&loop_index_mutex); + lo = disk->private_data; if (atomic_dec_return(&lo->lo_refcnt)) - return; + goto unlock_index;

mutex_lock(&loop_ctl_mutex); if (lo->lo_flags & LO_FLAGS_AUTOCLEAR) { @@ -1601,7 +1604,7 @@ static void __lo_release(struct loop_dev */ err = loop_clr_fd(lo); if (!err) - return; + goto unlock_index; } else { /* * Otherwise keep thread (if running) and config, @@ -1611,12 +1614,7 @@ static void __lo_release(struct loop_dev }

mutex_unlock(&loop_ctl_mutex); -} - -static void lo_release(struct gendisk *disk, fmode_t mode) -{ - mutex_lock(&loop_index_mutex); - __lo_release(disk->private_data); +unlock_index: mutex_unlock(&loop_index_mutex); }

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Tetsuo Handa penguin-kernel@I-love.SAKURA.ne.jp

commit 628bd85947091830a8c4872adfd5ed1d515a9cf2 upstream.

Commit 0a42e99b58a20883 ("loop: Get rid of loop_index_mutex") forgot to remove mutex_unlock(&loop_ctl_mutex) from loop_control_ioctl() when replacing loop_index_mutex with loop_ctl_mutex.

Fixes: 0a42e99b58a20883 ("loop: Get rid of loop_index_mutex") Reported-by: syzbot syzbot+c0138741c2290fc5e63f@syzkaller.appspotmail.com Reviewed-by: Ming Lei ming.lei@redhat.com Reviewed-by: Jan Kara jack@suse.cz Signed-off-by: Tetsuo Handa penguin-kernel@I-love.SAKURA.ne.jp Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/block/loop.c | 2 -- 1 file changed, 2 deletions(-)

--- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -1936,12 +1936,10 @@ static long loop_control_ioctl(struct fi break; if (lo->lo_state != Lo_unbound) { ret = -EBUSY; - mutex_unlock(&loop_ctl_mutex); break; } if (atomic_read(&lo->lo_refcnt) > 0) { ret = -EBUSY; - mutex_unlock(&loop_ctl_mutex); break; } lo->lo_disk->private_data = NULL;

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Mauro Carvalho Chehab mchehab+samsung@kernel.org

commit c06ef2e9acef4cda1feee2ce055b8086e33d251a upstream.

As reported by smatch: drivers/media/common/videobuf2/videobuf2-core.c: drivers/media/common/videobuf2/videobuf2-core.c:2159 vb2_mmap() warn: inconsistent returns 'mutex:&q->mmap_lock'. Locked on: line 2148 Unlocked on: line 2100 line 2108 line 2113 line 2118 line 2156 line 2159

There is one error condition that doesn't unlock a mutex.

Fixes: cd26d1c4d1bc ("media: vb2: vb2_mmap: move lock up") Reviewed-by: Hans Verkuil hverkuil-cisco@xs4all.nl Signed-off-by: Mauro Carvalho Chehab mchehab+samsung@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/media/v4l2-core/videobuf2-core.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

--- a/drivers/media/v4l2-core/videobuf2-core.c +++ b/drivers/media/v4l2-core/videobuf2-core.c @@ -2003,7 +2003,8 @@ int vb2_mmap(struct vb2_queue *q, struct if (length < (vma->vm_end - vma->vm_start)) { dprintk(1, "MMAP invalid, as it would overflow buffer length\n"); - return -EINVAL; + ret = -EINVAL; + goto unlock; }

ret = call_memop(vb, mmap, vb->planes[plane].mem_priv, vma);

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: David Ahern dsahern@gmail.com

[ Upstream commit ec90ad334986fa5856d11dd272f7f22fa86c55c4 ]

Similar to c5ee066333eb ("ipv6: Consider sk_bound_dev_if when binding a socket to an address"), binding a socket to v4 mapped addresses needs to consider if the socket is bound to a device.

This problem also exists from the beginning of git history.

Signed-off-by: David Ahern dsahern@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/ipv6/af_inet6.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-)

--- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -292,6 +292,7 @@ int inet6_bind(struct socket *sock, stru

/* Check if the address belongs to the host. */ if (addr_type == IPV6_ADDR_MAPPED) { + struct net_device *dev = NULL; int chk_addr_ret;

/* Binding to v4-mapped address on a v6-only socket @@ -302,9 +303,17 @@ int inet6_bind(struct socket *sock, stru goto out; }

+ if (sk->sk_bound_dev_if) { + dev = dev_get_by_index_rcu(net, sk->sk_bound_dev_if); + if (!dev) { + err = -ENODEV; + goto out; + } + } + /* Reproduce AF_INET checks to make the bindings consistent */ v4addr = addr->sin6_addr.s6_addr32[3]; - chk_addr_ret = inet_addr_type(net, v4addr); + chk_addr_ret = inet_addr_type_dev_table(net, dev, v4addr); if (!net->ipv4.sysctl_ip_nonlocal_bind && !(inet->freebind || inet->transparent) && v4addr != htonl(INADDR_ANY) &&

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Darrick J. Wong darrick.wong@oracle.com

commit 7b38460dc8e4eafba06c78f8e37099d3b34d473c upstream.

Kanda Motohiro reported that expanding a tiny xattr into a large xattr fails on XFS because we remove the tiny xattr from a shortform fork and then try to re-add it after converting the fork to extents format having not removed the ATTR_REPLACE flag. This fails because the attr is no longer present, causing a fs shutdown.

This is derived from the patch in his bug report, but we really shouldn't ignore a nonzero retval from the remove call.

Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=199119 Reported-by: kanda.motohiro@gmail.com Reviewed-by: Dave Chinner dchinner@redhat.com Reviewed-by: Christoph Hellwig hch@lst.de Signed-off-by: Darrick J. Wong darrick.wong@oracle.com Cc: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- fs/xfs/libxfs/xfs_attr.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-)

--- a/fs/xfs/libxfs/xfs_attr.c +++ b/fs/xfs/libxfs/xfs_attr.c @@ -528,7 +528,14 @@ xfs_attr_shortform_addname(xfs_da_args_t if (args->flags & ATTR_CREATE) return retval; retval = xfs_attr_shortform_remove(args); - ASSERT(retval == 0); + if (retval) + return retval; + /* + * Since we have removed the old attr, clear ATTR_REPLACE so + * that the leaf format add routine won't trip over the attr + * not being around. + */ + args->flags &= ~ATTR_REPLACE; }

if (args->namelen >= XFS_ATTR_SF_ENTSIZE_MAX ||

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

[ Upstream commit e1f65b0d70e9e5c80e15105cd96fa00174d7c436 ]

It seems with some NICs supported by the e1000e driver a SYSTIM reading may occasionally be few microseconds before the previous reading and if enabled also pass e1000e_sanitize_systim() without reaching the maximum number of rereads, even if the function is modified to check three consecutive readings (i.e. it doesn't look like a double read error). This causes an underflow in the timecounter and the PHC time jumps hours ahead.

This was observed on 82574, I217 and I219. The fastest way to reproduce it is to run a program that continuously calls the PTP_SYS_OFFSET ioctl on the PHC.

Modify e1000e_phc_gettime() to use timecounter_cyc2time() instead of timecounter_read() in order to allow non-monotonic SYSTIM readings and prevent the PHC from jumping.

Cc: Richard Cochran richardcochran@gmail.com Signed-off-by: Miroslav Lichvar mlichvar@redhat.com Acked-by: Jacob Keller jacob.e.keller@intel.com Tested-by: Aaron Brown aaron.f.brown@intel.com Signed-off-by: Jeff Kirsher jeffrey.t.kirsher@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/intel/e1000e/ptp.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/intel/e1000e/ptp.c b/drivers/net/ethernet/intel/e1000e/ptp.c index 25a0ad5102d6..855cf8c15c8a 100644 --- a/drivers/net/ethernet/intel/e1000e/ptp.c +++ b/drivers/net/ethernet/intel/e1000e/ptp.c @@ -111,10 +111,14 @@ static int e1000e_phc_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts) struct e1000_adapter *adapter = container_of(ptp, struct e1000_adapter, ptp_clock_info); unsigned long flags; - u64 ns; + u64 cycles, ns;

spin_lock_irqsave(&adapter->systim_lock, flags); - ns = timecounter_read(&adapter->tc); + + /* Use timecounter_cyc2time() to allow non-monotonic SYSTIM readings */ + cycles = adapter->cc.read(&adapter->cc); + ns = timecounter_cyc2time(&adapter->tc, cycles); + spin_unlock_irqrestore(&adapter->systim_lock, flags);

*ts = ns_to_timespec64(ns); @@ -170,9 +174,12 @@ static void e1000e_systim_overflow_work(struct work_struct *work) systim_overflow_work.work); struct e1000_hw *hw = &adapter->hw; struct timespec64 ts; + u64 ns;

- adapter->ptp_clock_info.gettime64(&adapter->ptp_clock_info, &ts); + /* Update the timecounter */ + ns = timecounter_read(&adapter->tc);

+ ts = ns_to_timespec64(ns); e_dbg("SYSTIM overflow check at %lld.%09lu\n", (long long) ts.tv_sec, ts.tv_nsec);

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

[ Upstream commit e4849aff1e169b86c561738daf8ff020e9de1011 ]

The Broadcom SiByte BCM1250, BCM1125, and BCM1125H SOCs have an onchip DRAM controller that supports memory amounts of up to 16GiB, and due to how the address decoder has been wired in the SOC any memory beyond 1GiB is actually mapped starting from 4GiB physical up, that is beyond the 32-bit addressable limit[1]. Consequently if the maximum amount of memory has been installed, then it will span up to 19GiB.

Many of the evaluation boards we support that are based on one of these SOCs have their memory soldered and the amount present fits in the 32-bit address range. The BCM91250A SWARM board however has actual DIMM slots and accepts, depending on the peripherals revision of the SOC, up to 4GiB or 8GiB of memory in commercially available JEDEC modules[2]. I believe this is also the case with the BCM91250C2 LittleSur board. This means that up to either 3GiB or 7GiB of memory requires 64-bit addressing to access.

I believe the BCM91480B BigSur board, which has the BCM1480 SOC instead, accepts at least as much memory, although I have no documentation or actual hardware available to verify that.

Both systems have PCI slots installed for use by any PCI option boards, including ones that only support 32-bit addressing (additionally the 32-bit PCI host bridge of the BCM1250, BCM1125, and BCM1125H SOCs limits addressing to 32-bits), and there is no IOMMU available. Therefore for PCI DMA to work in the presence of memory beyond enable swiotlb for the affected systems.

All the other SOC onchip DMA devices use 40-bit addressing and therefore can address the whole memory, so only enable swiotlb if PCI support and support for DMA beyond 4GiB have been both enabled in the configuration of the kernel.

This shows up as follows:

Broadcom SiByte BCM1250 B2 @ 800 MHz (SB1 rev 2) Board type: SiByte BCM91250A (SWARM) Determined physical RAM map: memory: 000000000fe7fe00 @ 0000000000000000 (usable) memory: 000000001ffffe00 @ 0000000080000000 (usable) memory: 000000000ffffe00 @ 00000000c0000000 (usable) memory: 0000000087fffe00 @ 0000000100000000 (usable) software IO TLB: mapped [mem 0xcbffc000-0xcfffc000] (64MB)

in the bootstrap log and removes failures like these:

defxx 0000:02:00.0: dma_direct_map_page: overflow 0x0000000185bc6080+4608 of device mask ffffffff bus mask 0 fddi0: Receive buffer allocation failed fddi0: Adapter open failed! IP-Config: Failed to open fddi0 defxx 0000:09:08.0: dma_direct_map_page: overflow 0x0000000185bc6080+4608 of device mask ffffffff bus mask 0 fddi1: Receive buffer allocation failed fddi1: Adapter open failed! IP-Config: Failed to open fddi1

when memory beyond 4GiB is handed out to devices that can only do 32-bit addressing.

This updates commit cce335ae47e2 ("[MIPS] 64-bit Sibyte kernels need DMA32.").

References:

[1] "BCM1250/BCM1125/BCM1125H User Manual", Revision 1250_1125-UM100-R, Broadcom Corporation, 21 Oct 2002, Section 3: "System Overview", "Memory Map", pp. 34-38

[2] "BCM91250A User Manual", Revision 91250A-UM100-R, Broadcom Corporation, 18 May 2004, Section 3: "Physical Description", "Supported DRAM", p. 23

Signed-off-by: Maciej W. Rozycki macro@linux-mips.org [paul.burton@mips.com: Remove GPL text from dma.c; SPDX tag covers it] Signed-off-by: Paul Burton paul.burton@mips.com Reviewed-by: Christoph Hellwig hch@lst.de Patchwork: https://patchwork.linux-mips.org/patch/21108/ References: cce335ae47e2 ("[MIPS] 64-bit Sibyte kernels need DMA32.") Cc: Ralf Baechle ralf@linux-mips.org Cc: linux-mips@linux-mips.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- arch/mips/Kconfig | 3 +++ arch/mips/sibyte/common/Makefile | 1 + arch/mips/sibyte/common/dma.c | 14 ++++++++++++++ 3 files changed, 18 insertions(+) create mode 100644 arch/mips/sibyte/common/dma.c

diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 3a908cc81317..333ea0389adb 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -760,6 +760,7 @@ config SIBYTE_SWARM select SYS_SUPPORTS_HIGHMEM select SYS_SUPPORTS_LITTLE_ENDIAN select ZONE_DMA32 if 64BIT + select SWIOTLB if ARCH_DMA_ADDR_T_64BIT && PCI

config SIBYTE_LITTLESUR bool "Sibyte BCM91250C2-LittleSur" @@ -782,6 +783,7 @@ config SIBYTE_SENTOSA select SYS_HAS_CPU_SB1 select SYS_SUPPORTS_BIG_ENDIAN select SYS_SUPPORTS_LITTLE_ENDIAN + select SWIOTLB if ARCH_DMA_ADDR_T_64BIT && PCI

config SIBYTE_BIGSUR bool "Sibyte BCM91480B-BigSur" @@ -795,6 +797,7 @@ config SIBYTE_BIGSUR select SYS_SUPPORTS_HIGHMEM select SYS_SUPPORTS_LITTLE_ENDIAN select ZONE_DMA32 if 64BIT + select SWIOTLB if ARCH_DMA_ADDR_T_64BIT && PCI

config SNI_RM bool "SNI RM200/300/400" diff --git a/arch/mips/sibyte/common/Makefile b/arch/mips/sibyte/common/Makefile index b3d6bf23a662..3ef3fb658136 100644 --- a/arch/mips/sibyte/common/Makefile +++ b/arch/mips/sibyte/common/Makefile @@ -1,4 +1,5 @@ obj-y := cfe.o +obj-$(CONFIG_SWIOTLB) += dma.o obj-$(CONFIG_SIBYTE_BUS_WATCHER) += bus_watcher.o obj-$(CONFIG_SIBYTE_CFE_CONSOLE) += cfe_console.o obj-$(CONFIG_SIBYTE_TBPROF) += sb_tbprof.o diff --git a/arch/mips/sibyte/common/dma.c b/arch/mips/sibyte/common/dma.c new file mode 100644 index 000000000000..eb47a94f3583 --- /dev/null +++ b/arch/mips/sibyte/common/dma.c @@ -0,0 +1,14 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * DMA support for Broadcom SiByte platforms. + * + * Copyright (c) 2018 Maciej W. Rozycki + */ + +#include <linux/swiotlb.h> +#include <asm/bootinfo.h> + +void __init plat_swiotlb_setup(void) +{ + swiotlb_init(1); +}

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

[ Upstream commit a788c5272769ddbcdbab297cf386413eeac04463 ]

jffs2_sync_fs makes the assumption that if CONFIG_JFFS2_FS_WRITEBUFFER is defined then a write buffer is available and has been initialized. However, this does is not the case when the mtd device has no out-of-band buffer:

int jffs2_nand_flash_setup(struct jffs2_sb_info *c) { if (!c->mtd->oobsize) return 0; ...

The resulting call to cancel_delayed_work_sync passing a uninitialized (but zeroed) delayed_work struct forces lockdep to become disabled.

[ 90.050639] overlayfs: upper fs does not support tmpfile. [ 90.652264] INFO: trying to register non-static key. [ 90.662171] the code is fine but needs lockdep annotation. [ 90.673090] turning off the locking correctness validator. [ 90.684021] CPU: 0 PID: 1762 Comm: mount_root Not tainted 4.14.63 #0 [ 90.696672] Stack : 00000000 00000000 80d8f6a2 00000038 805f0000 80444600 8fe364f4 805dfbe7 [ 90.713349] 80563a30 000006e2 8068370c 00000001 00000000 00000001 8e2fdc48 ffffffff [ 90.730020] 00000000 00000000 80d90000 00000000 00000106 00000000 6465746e 312e3420 [ 90.746690] 6b636f6c 03bf0000 f8000000 20676e69 00000000 80000000 00000000 8e2c2a90 [ 90.763362] 80d90000 00000001 00000000 8e2c2a90 00000003 80260dc0 08052098 80680000 [ 90.780033] ... [ 90.784902] Call Trace: [ 90.789793] [<8000f0d8>] show_stack+0xb8/0x148 [ 90.798659] [<8005a000>] register_lock_class+0x270/0x55c [ 90.809247] [<8005cb64>] __lock_acquire+0x13c/0xf7c [ 90.818964] [<8005e314>] lock_acquire+0x194/0x1dc [ 90.828345] [<8003f27c>] flush_work+0x200/0x24c [ 90.837374] [<80041dfc>] __cancel_work_timer+0x158/0x210 [ 90.847958] [<801a8770>] jffs2_sync_fs+0x20/0x54 [ 90.857173] [<80125cf4>] iterate_supers+0xf4/0x120 [ 90.866729] [<80158fc4>] sys_sync+0x44/0x9c [ 90.875067] [<80014424>] syscall_common+0x34/0x58

Signed-off-by: Daniel Santos daniel.santos@pobox.com Reviewed-by: Hou Tao houtao1@huawei.com Signed-off-by: Boris Brezillon boris.brezillon@bootlin.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/jffs2/super.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/jffs2/super.c b/fs/jffs2/super.c index 1544f530ccd0..023e7f32ee1b 100644 --- a/fs/jffs2/super.c +++ b/fs/jffs2/super.c @@ -101,7 +101,8 @@ static int jffs2_sync_fs(struct super_block *sb, int wait) struct jffs2_sb_info *c = JFFS2_SB_INFO(sb);

#ifdef CONFIG_JFFS2_FS_WRITEBUFFER - cancel_delayed_work_sync(&c->wbuf_dwork); + if (jffs2_is_writebuffered(c)) + cancel_delayed_work_sync(&c->wbuf_dwork); #endif

mutex_lock(&c->alloc_sem);

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

[ Upstream commit 2b038cbc5fcf12a7ee1cc9bfd5da1e46dacdee87 ]

When booting a pseries kernel with PREEMPT enabled, it dumps the following warning:

BUG: using smp_processor_id() in preemptible [00000000] code: swapper/0/1 caller is pseries_processor_idle_init+0x5c/0x22c CPU: 13 PID: 1 Comm: swapper/0 Not tainted 4.20.0-rc3-00090-g12201a0128bc-dirty #828 Call Trace: [c000000429437ab0] [c0000000009c8878] dump_stack+0xec/0x164 (unreliable) [c000000429437b00] [c0000000005f2f24] check_preemption_disabled+0x154/0x160 [c000000429437b90] [c000000000cab8e8] pseries_processor_idle_init+0x5c/0x22c [c000000429437c10] [c000000000010ed4] do_one_initcall+0x64/0x300 [c000000429437ce0] [c000000000c54500] kernel_init_freeable+0x3f0/0x500 [c000000429437db0] [c0000000000112dc] kernel_init+0x2c/0x160 [c000000429437e20] [c00000000000c1d0] ret_from_kernel_thread+0x5c/0x6c

This happens because the code calls get_lppaca() which calls get_paca() and it checks if preemption is disabled through check_preemption_disabled().

Preemption should be disabled because the per CPU variable may make no sense if there is a preemption (and a CPU switch) after it reads the per CPU data and when it is used.

In this device driver specifically, it is not a problem, because this code just needs to have access to one lppaca struct, and it does not matter if it is the current per CPU lppaca struct or not (i.e. when there is a preemption and a CPU migration).

That said, the most appropriate fix seems to be related to avoiding the debug_smp_processor_id() call at get_paca(), instead of calling preempt_disable() before get_paca().

Signed-off-by: Breno Leitao leitao@debian.org Signed-off-by: Michael Ellerman mpe@ellerman.id.au Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/cpuidle/cpuidle-pseries.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/cpuidle/cpuidle-pseries.c b/drivers/cpuidle/cpuidle-pseries.c index 07135e009d8b..601a6c3acc7f 100644 --- a/drivers/cpuidle/cpuidle-pseries.c +++ b/drivers/cpuidle/cpuidle-pseries.c @@ -240,7 +240,13 @@ static int pseries_idle_probe(void) return -ENODEV;

if (firmware_has_feature(FW_FEATURE_SPLPAR)) { - if (lppaca_shared_proc(get_lppaca())) { + /* + * Use local_paca instead of get_lppaca() since + * preemption is not disabled, and it is not required in + * fact, since lppaca_ptr does not need to be the value + * associated to the current CPU, it can be from any CPU. + */ + if (lppaca_shared_proc(local_paca->lppaca_ptr)) { cpuidle_state_table = shared_states; max_idle_state = ARRAY_SIZE(shared_states); } else {

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

[ Upstream commit 0fbe82e628c817e292ff588cd5847fc935e025f2 ]

after set SO_DONTROUTE to 1, the IP layer should not route packets if the dest IP address is not in link scope. But if the socket has cached the dst_entry, such packets would be routed until the sk_dst_cache expires. So we should clean the sk_dst_cache when a user set SO_DONTROUTE option. Below are server/client python scripts which could reprodue this issue:

server side code:

========================================================================== import socket import struct import time

s = socket.socket(socket.AF_INET, socket.SOCK_STREAM) s.bind(('0.0.0.0', 9000)) s.listen(1) sock, addr = s.accept() sock.setsockopt(socket.SOL_SOCKET, socket.SO_DONTROUTE, struct.pack('i', 1)) while True: sock.send(b'foo') time.sleep(1) ==========================================================================

client side code: ========================================================================== import socket import time

s = socket.socket(socket.AF_INET, socket.SOCK_STREAM) s.connect(('server_address', 9000)) while True: data = s.recv(1024) print(data) ==========================================================================

Signed-off-by: yupeng yupeng0921@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/core/sock.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/net/core/sock.c b/net/core/sock.c index 9fb1c073d0c4..8aa4a5f89572 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -732,6 +732,7 @@ int sock_setsockopt(struct socket *sock, int level, int optname, break; case SO_DONTROUTE: sock_valbool_flag(sk, SOCK_LOCALROUTE, valbool); + sk_dst_reset(sk); break; case SO_BROADCAST: sock_valbool_flag(sk, SOCK_BROADCAST, valbool);

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

[ Upstream commit f7542d817733f461258fd3a47d77da35b2d9fc81 ]

The exclusive gates may be set up in the wrong way by software running before the clock driver comes up. In that case the exclusive setup is locked in its initial state, as the complementary function can't be activated without disabling the initial setup first.

To avoid this lock situation, reset the exclusive gates to the off state and allow the kernel to provide the proper setup.

Signed-off-by: Lucas Stach l.stach@pengutronix.de Reviewed-by: Dong Aisheng Aisheng.dong@nxp.com Signed-off-by: Stephen Boyd sboyd@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/clk/imx/clk-imx6q.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/clk/imx/clk-imx6q.c b/drivers/clk/imx/clk-imx6q.c index a0df83e6b84b..46c05c9a9354 100644 --- a/drivers/clk/imx/clk-imx6q.c +++ b/drivers/clk/imx/clk-imx6q.c @@ -239,8 +239,12 @@ static void __init imx6q_clocks_init(struct device_node *ccm_node) * lvds1_gate and lvds2_gate are pseudo-gates. Both can be * independently configured as clock inputs or outputs. We treat * the "output_enable" bit as a gate, even though it's really just - * enabling clock output. + * enabling clock output. Initially the gate bits are cleared, as + * otherwise the exclusive configuration gets locked in the setup done + * by software running before the clock driver, with no way to change + * it. */ + writel(readl(base + 0x160) & ~0x3c00, base + 0x160); clk[IMX6QDL_CLK_LVDS1_GATE] = imx_clk_gate_exclusive("lvds1_gate", "lvds1_sel", base + 0x160, 10, BIT(12)); clk[IMX6QDL_CLK_LVDS2_GATE] = imx_clk_gate_exclusive("lvds2_gate", "lvds2_sel", base + 0x160, 11, BIT(13));

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

[ Upstream commit fbac5977d81cb2b2b7e37b11c459055d9585273c ]

An unterminated string literal followed by new line is passed to the parser (with "multi-line strings not supported" warning shown), then handled properly there.

On the other hand, an unterminated string literal at end of file is never passed to the parser, then results in memory leak.

[Test Code]

----------(Kconfig begin)---------- source "Kconfig.inc"

config A bool "a" -----------(Kconfig end)-----------

--------(Kconfig.inc begin)-------- config B bool "b\No new line at end of file ---------(Kconfig.inc end)---------

[Summary from Valgrind]

Before the fix:

LEAK SUMMARY: definitely lost: 16 bytes in 1 blocks ...

After the fix:

LEAK SUMMARY: definitely lost: 0 bytes in 0 blocks ...

Eliminate the memory leak path by handling this case. Of course, such a Kconfig file is wrong already, so I will add an error message later.

Signed-off-by: Masahiro Yamada yamada.masahiro@socionext.com Signed-off-by: Sasha Levin sashal@kernel.org --- scripts/kconfig/zconf.l | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/scripts/kconfig/zconf.l b/scripts/kconfig/zconf.l index 6534dc5ac803..0c7800112ff5 100644 --- a/scripts/kconfig/zconf.l +++ b/scripts/kconfig/zconf.l @@ -191,6 +191,8 @@ n [A-Za-z0-9_-] } <<EOF>> { BEGIN(INITIAL); + yylval.string = text; + return T_WORD_QUOTE; } }

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

[ Upstream commit 1c6f709b9f96366cc47af23c05ecec9b8c0c392d ]

Users should never use 'pt=0', but if they do it may give a meaningless error:

$ perf record -e intel_pt/pt=0/u uname Error: The sys_perf_event_open() syscall returned with 22 (Invalid argument) for event (intel_pt/pt=0/u).

Fix that by forcing 'pt=1'.

Committer testing:

# perf record -e intel_pt/pt=0/u uname Error: The sys_perf_event_open() syscall returned with 22 (Invalid argument) for event (intel_pt/pt=0/u). /bin/dmesg | grep -i perf may provide additional information.

# perf record -e intel_pt/pt=0/u uname pt=0 doesn't make sense, forcing pt=1 Linux [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.020 MB perf.data ] #

Signed-off-by: Adrian Hunter adrian.hunter@intel.com Tested-by: Arnaldo Carvalho de Melo acme@redhat.com Cc: Jiri Olsa jolsa@redhat.com Link: http://lkml.kernel.org/r/b7c5b4e5-9497-10e5-fd43-5f3e4a0fe51d@intel.com Signed-off-by: Arnaldo Carvalho de Melo acme@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- tools/perf/arch/x86/util/intel-pt.c | 11 +++++++++++ 1 file changed, 11 insertions(+)

diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c index c53f78767568..df21da796fa7 100644 --- a/tools/perf/arch/x86/util/intel-pt.c +++ b/tools/perf/arch/x86/util/intel-pt.c @@ -471,10 +471,21 @@ static int intel_pt_validate_config(struct perf_pmu *intel_pt_pmu, struct perf_evsel *evsel) { int err; + char c;

if (!evsel) return 0;

+ /* + * If supported, force pass-through config term (pt=1) even if user + * sets pt=0, which avoids senseless kernel errors. + */ + if (perf_pmu__scan_file(intel_pt_pmu, "format/pt", "%c", &c) == 1 && + !(evsel->attr.config & 1)) { + pr_warning("pt=0 doesn't make sense, forcing pt=1\n"); + evsel->attr.config |= 1; + } + err = intel_pt_val_config_term(intel_pt_pmu, "caps/cycle_thresholds", "cyc_thresh", "caps/psb_cyc", evsel->attr.config);

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

[ Upstream commit bd8d57fb7e25e9fcf67a9eef5fa13aabe2016e07 ]

The strncpy() function may leave the destination string buffer unterminated, better use strlcpy() that we have a __weak fallback implementation for systems without it.

This fixes this warning on an Alpine Linux Edge system with gcc 8.2:

util/parse-events.c: In function 'print_symbol_events': util/parse-events.c:2465:4: error: 'strncpy' specified bound 100 equals destination size [-Werror=stringop-truncation] strncpy(name, syms->symbol, MAX_NAME_LEN); ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ In function 'print_symbol_events.constprop', inlined from 'print_events' at util/parse-events.c:2508:2: util/parse-events.c:2465:4: error: 'strncpy' specified bound 100 equals destination size [-Werror=stringop-truncation] strncpy(name, syms->symbol, MAX_NAME_LEN); ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ In function 'print_symbol_events.constprop', inlined from 'print_events' at util/parse-events.c:2511:2: util/parse-events.c:2465:4: error: 'strncpy' specified bound 100 equals destination size [-Werror=stringop-truncation] strncpy(name, syms->symbol, MAX_NAME_LEN); ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ cc1: all warnings being treated as errors

Cc: Adrian Hunter adrian.hunter@intel.com Cc: Jiri Olsa jolsa@kernel.org Cc: Namhyung Kim namhyung@kernel.org Fixes: 947b4ad1d198 ("perf list: Fix max event string size") Link: https://lkml.kernel.org/n/tip-b663e33bm6x8hrkie4uxh7u2@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo acme@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- tools/perf/util/parse-events.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index e81dfb2e239c..9351738df703 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -1903,7 +1903,7 @@ restart: if (!name_only && strlen(syms->alias)) snprintf(name, MAX_NAME_LEN, "%s OR %s", syms->symbol, syms->alias); else - strncpy(name, syms->symbol, MAX_NAME_LEN); + strlcpy(name, syms->symbol, MAX_NAME_LEN);

evt_list[evt_i] = strdup(name); if (evt_list[evt_i] == NULL)

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

[ Upstream commit 721b1d98fb517ae99ab3b757021cf81db41e67be ]

kcopyd has no upper limit to the number of jobs one can allocate and issue. Under certain workloads this can lead to excessive memory usage and workqueue stalls. For example, when creating multiple dm-snapshot targets with a 4K chunk size and then writing to the origin through the page cache. Syncing the page cache causes a large number of BIOs to be issued to the dm-snapshot origin target, which itself issues an even larger (because of the BIO splitting taking place) number of kcopyd jobs.

Running the following test, from the device mapper test suite [1],

dmtest run --suite snapshot -n many_snapshots_of_same_volume_N

, with 8 active snapshots, results in the kcopyd job slab cache growing to 10G. Depending on the available system RAM this can lead to the OOM killer killing user processes:

[463.492878] kthreadd invoked oom-killer: gfp_mask=0x6040c0(GFP_KERNEL|__GFP_COMP), nodemask=(null), order=1, oom_score_adj=0 [463.492894] kthreadd cpuset=/ mems_allowed=0 [463.492948] CPU: 7 PID: 2 Comm: kthreadd Not tainted 4.19.0-rc7 #3 [463.492950] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1 04/01/2014 [463.492952] Call Trace: [463.492964] dump_stack+0x7d/0xbb [463.492973] dump_header+0x6b/0x2fc [463.492987] ? lockdep_hardirqs_on+0xee/0x190 [463.493012] oom_kill_process+0x302/0x370 [463.493021] out_of_memory+0x113/0x560 [463.493030] __alloc_pages_slowpath+0xf40/0x1020 [463.493055] __alloc_pages_nodemask+0x348/0x3c0 [463.493067] cache_grow_begin+0x81/0x8b0 [463.493072] ? cache_grow_begin+0x874/0x8b0 [463.493078] fallback_alloc+0x1e4/0x280 [463.493092] kmem_cache_alloc_node+0xd6/0x370 [463.493098] ? copy_process.part.31+0x1c5/0x20d0 [463.493105] copy_process.part.31+0x1c5/0x20d0 [463.493115] ? __lock_acquire+0x3cc/0x1550 [463.493121] ? __switch_to_asm+0x34/0x70 [463.493129] ? kthread_create_worker_on_cpu+0x70/0x70 [463.493135] ? finish_task_switch+0x90/0x280 [463.493165] _do_fork+0xe0/0x6d0 [463.493191] ? kthreadd+0x19f/0x220 [463.493233] kernel_thread+0x25/0x30 [463.493235] kthreadd+0x1bf/0x220 [463.493242] ? kthread_create_on_cpu+0x90/0x90 [463.493248] ret_from_fork+0x3a/0x50 [463.493279] Mem-Info: [463.493285] active_anon:20631 inactive_anon:4831 isolated_anon:0 [463.493285] active_file:80216 inactive_file:80107 isolated_file:435 [463.493285] unevictable:0 dirty:51266 writeback:109372 unstable:0 [463.493285] slab_reclaimable:31191 slab_unreclaimable:3483521 [463.493285] mapped:526 shmem:4903 pagetables:1759 bounce:0 [463.493285] free:33623 free_pcp:2392 free_cma:0 ... [463.493489] Unreclaimable slab info: [463.493513] Name Used Total [463.493522] bio-6 1028KB 1028KB [463.493525] bio-5 1028KB 1028KB [463.493528] dm_snap_pending_exception 236783KB 243789KB [463.493531] dm_exception 41KB 42KB [463.493534] bio-4 1216KB 1216KB [463.493537] bio-3 439396KB 439396KB [463.493539] kcopyd_job 6973427KB 6973427KB ... [463.494340] Out of memory: Kill process 1298 (ruby2.3) score 1 or sacrifice child [463.494673] Killed process 1298 (ruby2.3) total-vm:435740kB, anon-rss:20180kB, file-rss:4kB, shmem-rss:0kB [463.506437] oom_reaper: reaped process 1298 (ruby2.3), now anon-rss:0kB, file-rss:0kB, shmem-rss:0kB

Moreover, issuing a large number of kcopyd jobs results in kcopyd hogging the CPU, while processing them. As a result, processing of work items, queued for execution on the same CPU as the currently running kcopyd thread, is stalled for long periods of time, hurting performance. Running the aforementioned test we get, in dmesg, messages like the following:

[67501.194592] BUG: workqueue lockup - pool cpus=4 node=0 flags=0x0 nice=0 stuck for 27s! [67501.195586] Showing busy workqueues and worker pools: [67501.195591] workqueue events: flags=0x0 [67501.195597] pwq 8: cpus=4 node=0 flags=0x0 nice=0 active=1/256 [67501.195611] pending: cache_reap [67501.195641] workqueue mm_percpu_wq: flags=0x8 [67501.195645] pwq 8: cpus=4 node=0 flags=0x0 nice=0 active=1/256 [67501.195656] pending: vmstat_update [67501.195682] workqueue kblockd: flags=0x18 [67501.195687] pwq 5: cpus=2 node=0 flags=0x0 nice=-20 active=1/256 [67501.195698] pending: blk_timeout_work [67501.195753] workqueue kcopyd: flags=0x8 [67501.195757] pwq 8: cpus=4 node=0 flags=0x0 nice=0 active=1/256 [67501.195768] pending: do_work [dm_mod] [67501.195802] workqueue kcopyd: flags=0x8 [67501.195806] pwq 8: cpus=4 node=0 flags=0x0 nice=0 active=1/256 [67501.195817] pending: do_work [dm_mod] [67501.195834] workqueue kcopyd: flags=0x8 [67501.195838] pwq 8: cpus=4 node=0 flags=0x0 nice=0 active=1/256 [67501.195848] pending: do_work [dm_mod] [67501.195881] workqueue kcopyd: flags=0x8 [67501.195885] pwq 8: cpus=4 node=0 flags=0x0 nice=0 active=1/256 [67501.195896] pending: do_work [dm_mod] [67501.195920] workqueue kcopyd: flags=0x8 [67501.195924] pwq 8: cpus=4 node=0 flags=0x0 nice=0 active=2/256 [67501.195935] in-flight: 67:do_work [dm_mod] [67501.195945] pending: do_work [dm_mod] [67501.195961] pool 8: cpus=4 node=0 flags=0x0 nice=0 hung=27s workers=3 idle: 129 23765

The root cause for these issues is the way dm-snapshot uses kcopyd. In particular, the lack of an explicit or implicit limit to the maximum number of in-flight COW jobs. The merging path is not affected because it implicitly limits the in-flight kcopyd jobs to one.

Fix these issues by using a semaphore to limit the maximum number of in-flight kcopyd jobs. We grab the semaphore before allocating a new kcopyd job in start_copy() and start_full_bio() and release it after the job finishes in copy_callback().

The initial semaphore value is configurable through a module parameter, to allow fine tuning the maximum number of in-flight COW jobs. Setting this parameter to zero initializes the semaphore to INT_MAX.

A default value of 2048 maximum in-flight kcopyd jobs was chosen. This value was decided experimentally as a trade-off between memory consumption, stalling the kernel's workqueues and maintaining a high enough throughput.

Re-running the aforementioned test:

* Workqueue stalls are eliminated * kcopyd's job slab cache uses a maximum of 130MB * The time taken by the test to write to the snapshot-origin target is reduced from 05m20.48s to 03m26.38s

[1] https://github.com/jthornber/device-mapper-test-suite

Signed-off-by: Nikos Tsironis ntsironis@arrikto.com Signed-off-by: Ilias Tsitsimpis iliastsi@arrikto.com Signed-off-by: Mike Snitzer snitzer@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/md/dm-snap.c | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+)

diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c index e108deebbaaa..5d3797728b9c 100644 --- a/drivers/md/dm-snap.c +++ b/drivers/md/dm-snap.c @@ -19,6 +19,7 @@ #include <linux/vmalloc.h> #include <linux/log2.h> #include <linux/dm-kcopyd.h> +#include <linux/semaphore.h>

#include "dm.h"

@@ -105,6 +106,9 @@ struct dm_snapshot { /* The on disk metadata handler */ struct dm_exception_store *store;

+ /* Maximum number of in-flight COW jobs. */ + struct semaphore cow_count; + struct dm_kcopyd_client *kcopyd_client;

/* Wait for events based on state_bits */ @@ -145,6 +149,19 @@ struct dm_snapshot { #define RUNNING_MERGE 0 #define SHUTDOWN_MERGE 1

+/* + * Maximum number of chunks being copied on write. + * + * The value was decided experimentally as a trade-off between memory + * consumption, stalling the kernel's workqueues and maintaining a high enough + * throughput. + */ +#define DEFAULT_COW_THRESHOLD 2048 + +static int cow_threshold = DEFAULT_COW_THRESHOLD; +module_param_named(snapshot_cow_threshold, cow_threshold, int, 0644); +MODULE_PARM_DESC(snapshot_cow_threshold, "Maximum number of chunks being copied on write"); + DECLARE_DM_KCOPYD_THROTTLE_WITH_MODULE_PARM(snapshot_copy_throttle, "A percentage of time allocated for copy on write");

@@ -1190,6 +1207,8 @@ static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv) goto bad_hash_tables; }

+ sema_init(&s->cow_count, (cow_threshold > 0) ? cow_threshold : INT_MAX); + s->kcopyd_client = dm_kcopyd_client_create(&dm_kcopyd_throttle); if (IS_ERR(s->kcopyd_client)) { r = PTR_ERR(s->kcopyd_client); @@ -1563,6 +1582,7 @@ static void copy_callback(int read_err, unsigned long write_err, void *context) } list_add(&pe->out_of_order_entry, lh); } + up(&s->cow_count); }

/* @@ -1586,6 +1606,7 @@ static void start_copy(struct dm_snap_pending_exception *pe) dest.count = src.count;

/* Hand over to kcopyd */ + down(&s->cow_count); dm_kcopyd_copy(s->kcopyd_client, &src, 1, &dest, 0, copy_callback, pe); }

@@ -1606,6 +1627,7 @@ static void start_full_bio(struct dm_snap_pending_exception *pe, pe->full_bio_end_io = bio->bi_end_io; pe->full_bio_private = bio->bi_private;

+ down(&s->cow_count); callback_data = dm_kcopyd_prepare_callback(s->kcopyd_client, copy_callback, pe);

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

[ Upstream commit 4f4b374332ec0ae9c738ff8ec9bed5cd97ff9adc ]

This is the much more correct fix for my earlier attempt at:

https://lkml.org/lkml/2018/12/10/118

Short recap:

- There's not actually a locking issue, it's just lockdep being a bit too eager to complain about a possible deadlock.

- Contrary to what I claimed the real problem is recursion on kn->count. Greg pointed me at sysfs_break_active_protection(), used by the scsi subsystem to allow a sysfs file to unbind itself. That would be a real deadlock, which isn't what's happening here. Also, breaking the active protection means we'd need to manually handle all the lifetime fun.

- With Rafael we discussed the task_work approach, which kinda works, but has two downsides: It's a functional change for a lockdep annotation issue, and it won't work for the bind file (which needs to get the errno from the driver load function back to userspace).

- Greg also asked why this never showed up: To hit this you need to unregister a 2nd driver from the unload code of your first driver. I guess only gpus do that. The bug has always been there, but only with a recent patch series did we add more locks so that lockdep built a chain from unbinding the snd-hda driver to the acpi_video_unregister call.

Full lockdep splat:

[12301.898799] ============================================ [12301.898805] WARNING: possible recursive locking detected [12301.898811] 4.20.0-rc7+ #84 Not tainted [12301.898815] -------------------------------------------- [12301.898821] bash/5297 is trying to acquire lock: [12301.898826] 00000000f61c6093 (kn->count#39){++++}, at: kernfs_remove_by_name_ns+0x3b/0x80 [12301.898841] but task is already holding lock: [12301.898847] 000000005f634021 (kn->count#39){++++}, at: kernfs_fop_write+0xdc/0x190 [12301.898856] other info that might help us debug this: [12301.898862] Possible unsafe locking scenario: [12301.898867] CPU0 [12301.898870] ---- [12301.898874] lock(kn->count#39); [12301.898879] lock(kn->count#39); [12301.898883] *** DEADLOCK *** [12301.898891] May be due to missing lock nesting notation [12301.898899] 5 locks held by bash/5297: [12301.898903] #0: 00000000cd800e54 (sb_writers#4){.+.+}, at: vfs_write+0x17f/0x1b0 [12301.898915] #1: 000000000465e7c2 (&of->mutex){+.+.}, at: kernfs_fop_write+0xd3/0x190 [12301.898925] #2: 000000005f634021 (kn->count#39){++++}, at: kernfs_fop_write+0xdc/0x190 [12301.898936] #3: 00000000414ef7ac (&dev->mutex){....}, at: device_release_driver_internal+0x34/0x240 [12301.898950] #4: 000000003218fbdf (register_count_mutex){+.+.}, at: acpi_video_unregister+0xe/0x40 [12301.898960] stack backtrace: [12301.898968] CPU: 1 PID: 5297 Comm: bash Not tainted 4.20.0-rc7+ #84 [12301.898974] Hardware name: Hewlett-Packard HP EliteBook 8460p/161C, BIOS 68SCF Ver. F.01 03/11/2011 [12301.898982] Call Trace: [12301.898989] dump_stack+0x67/0x9b [12301.898997] __lock_acquire+0x6ad/0x1410 [12301.899003] ? kernfs_remove_by_name_ns+0x3b/0x80 [12301.899010] ? find_held_lock+0x2d/0x90 [12301.899017] ? mutex_spin_on_owner+0xe4/0x150 [12301.899023] ? find_held_lock+0x2d/0x90 [12301.899030] ? lock_acquire+0x90/0x180 [12301.899036] lock_acquire+0x90/0x180 [12301.899042] ? kernfs_remove_by_name_ns+0x3b/0x80 [12301.899049] __kernfs_remove+0x296/0x310 [12301.899055] ? kernfs_remove_by_name_ns+0x3b/0x80 [12301.899060] ? kernfs_name_hash+0xd/0x80 [12301.899066] ? kernfs_find_ns+0x6c/0x100 [12301.899073] kernfs_remove_by_name_ns+0x3b/0x80 [12301.899080] bus_remove_driver+0x92/0xa0 [12301.899085] acpi_video_unregister+0x24/0x40 [12301.899127] i915_driver_unload+0x42/0x130 [i915] [12301.899160] i915_pci_remove+0x19/0x30 [i915] [12301.899169] pci_device_remove+0x36/0xb0 [12301.899176] device_release_driver_internal+0x185/0x240 [12301.899183] unbind_store+0xaf/0x180 [12301.899189] kernfs_fop_write+0x104/0x190 [12301.899195] __vfs_write+0x31/0x180 [12301.899203] ? rcu_read_lock_sched_held+0x6f/0x80 [12301.899209] ? rcu_sync_lockdep_assert+0x29/0x50 [12301.899216] ? __sb_start_write+0x13c/0x1a0 [12301.899221] ? vfs_write+0x17f/0x1b0 [12301.899227] vfs_write+0xb9/0x1b0 [12301.899233] ksys_write+0x50/0xc0 [12301.899239] do_syscall_64+0x4b/0x180 [12301.899247] entry_SYSCALL_64_after_hwframe+0x49/0xbe [12301.899253] RIP: 0033:0x7f452ac7f7a4 [12301.899259] Code: 00 f7 d8 64 89 02 48 c7 c0 ff ff ff ff eb b7 0f 1f 80 00 00 00 00 8b 05 aa f0 2c 00 48 63 ff 85 c0 75 13 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 54 f3 c3 66 90 55 53 48 89 d5 48 89 f3 48 83 [12301.899273] RSP: 002b:00007ffceafa6918 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 [12301.899282] RAX: ffffffffffffffda RBX: 000000000000000d RCX: 00007f452ac7f7a4 [12301.899288] RDX: 000000000000000d RSI: 00005612a1abf7c0 RDI: 0000000000000001 [12301.899295] RBP: 00005612a1abf7c0 R08: 000000000000000a R09: 00005612a1c46730 [12301.899301] R10: 000000000000000a R11: 0000000000000246 R12: 000000000000000d [12301.899308] R13: 0000000000000001 R14: 00007f452af4a740 R15: 000000000000000d

Looking around I've noticed that usb and i2c already handle similar recursion problems, where a sysfs file can unbind the same type of sysfs somewhere else in the hierarchy. Relevant commits are:

commit 356c05d58af05d582e634b54b40050c73609617b Author: Alan Stern stern@rowland.harvard.edu Date: Mon May 14 13:30:03 2012 -0400

sysfs: get rid of some lockdep false positives

commit e9b526fe704812364bca07edd15eadeba163ebfb Author: Alexander Sverdlin alexander.sverdlin@nsn.com Date: Fri May 17 14:56:35 2013 +0200

i2c: suppress lockdep warning on delete_device

Implement the same trick for driver bind/unbind.

v2: Put the macro into bus.c (Greg).

Reviewed-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Cc: Ramalingam C ramalingam.c@intel.com Cc: Arend van Spriel aspriel@gmail.com Cc: Andy Shevchenko andriy.shevchenko@linux.intel.com Cc: Geert Uytterhoeven geert+renesas@glider.be Cc: Bartosz Golaszewski brgl@bgdev.pl Cc: Heikki Krogerus heikki.krogerus@linux.intel.com Cc: Vivek Gautam vivek.gautam@codeaurora.org Cc: Joe Perches joe@perches.com Signed-off-by: Daniel Vetter daniel.vetter@intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/base/bus.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/base/bus.c b/drivers/base/bus.c index 0346e46e2871..ecca4ae248e0 100644 --- a/drivers/base/bus.c +++ b/drivers/base/bus.c @@ -33,6 +33,9 @@ static struct kset *system_kset;

#define to_drv_attr(_attr) container_of(_attr, struct driver_attribute, attr)

+#define DRIVER_ATTR_IGNORE_LOCKDEP(_name, _mode, _show, _store) \ + struct driver_attribute driver_attr_##_name = \ + __ATTR_IGNORE_LOCKDEP(_name, _mode, _show, _store)

static int __must_check bus_rescan_devices_helper(struct device *dev, void *data); @@ -198,7 +201,7 @@ static ssize_t unbind_store(struct device_driver *drv, const char *buf, bus_put(bus); return err; } -static DRIVER_ATTR_WO(unbind); +static DRIVER_ATTR_IGNORE_LOCKDEP(unbind, S_IWUSR, NULL, unbind_store);

/* * Manually attach a device to a driver. @@ -234,7 +237,7 @@ static ssize_t bind_store(struct device_driver *drv, const char *buf, bus_put(bus); return err; } -static DRIVER_ATTR_WO(bind); +static DRIVER_ATTR_IGNORE_LOCKDEP(bind, S_IWUSR, NULL, bind_store);

static ssize_t show_drivers_autoprobe(struct bus_type *bus, char *buf) {

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

[ Upstream commit 532e1e54c8140188e192348c790317921cb2dc1c ]

mount.ocfs2 ignore the inconsistent error that journal is clean but local alloc is unrecovered. After mount, local alloc not empty, then reserver cluster didn't alloc a new local alloc window, reserveration map is empty(ocfs2_reservation_map.m_bitmap_len = 0), that triggered the following panic.

This issue was reported at

https://oss.oracle.com/pipermail/ocfs2-devel/2015-May/010854.html

and was advised to fixed during mount. But this is a very unusual inconsistent state, usually journal dirty flag should be cleared at the last stage of umount until every other things go right. We may need do further debug to check that. Any way to avoid possible futher corruption, mount should be abort and fsck should be run.

(mount.ocfs2,1765,1):ocfs2_load_local_alloc:353 ERROR: Local alloc hasn't been recovered! found = 6518, set = 6518, taken = 8192, off = 15912372 ocfs2: Mounting device (202,64) on (node 0, slot 3) with ordered data mode. o2dlm: Joining domain 89CEAC63CC4F4D03AC185B44E0EE0F3F ( 0 1 2 3 4 5 6 8 ) 8 nodes ocfs2: Mounting device (202,80) on (node 0, slot 3) with ordered data mode. o2hb: Region 89CEAC63CC4F4D03AC185B44E0EE0F3F (xvdf) is now a quorum device o2net: Accepted connection from node yvwsoa17p (num 7) at 172.22.77.88:7777 o2dlm: Node 7 joins domain 64FE421C8C984E6D96ED12C55FEE2435 ( 0 1 2 3 4 5 6 7 8 ) 9 nodes o2dlm: Node 7 joins domain 89CEAC63CC4F4D03AC185B44E0EE0F3F ( 0 1 2 3 4 5 6 7 8 ) 9 nodes ------------[ cut here ]------------ kernel BUG at fs/ocfs2/reservations.c:507! invalid opcode: 0000 [#1] SMP Modules linked in: ocfs2 rpcsec_gss_krb5 auth_rpcgss nfsv4 nfs fscache lockd grace ocfs2_dlmfs ocfs2_stack_o2cb ocfs2_dlm ocfs2_nodemanager ocfs2_stackglue configfs sunrpc ipt_REJECT nf_reject_ipv4 nf_conntrack_ipv4 nf_defrag_ipv4 iptable_filter ip_tables ip6t_REJECT nf_reject_ipv6 nf_conntrack_ipv6 nf_defrag_ipv6 xt_state nf_conntrack ip6table_filter ip6_tables ib_ipoib rdma_ucm ib_ucm ib_uverbs ib_umad rdma_cm ib_cm iw_cm ib_sa ib_mad ib_core ib_addr ipv6 ovmapi ppdev parport_pc parport xen_netfront fb_sys_fops sysimgblt sysfillrect syscopyarea acpi_cpufreq pcspkr i2c_piix4 i2c_core sg ext4 jbd2 mbcache2 sr_mod cdrom xen_blkfront pata_acpi ata_generic ata_piix floppy dm_mirror dm_region_hash dm_log dm_mod CPU: 0 PID: 4349 Comm: startWebLogic.s Not tainted 4.1.12-124.19.2.el6uek.x86_64 #2 Hardware name: Xen HVM domU, BIOS 4.4.4OVM 09/06/2018 task: ffff8803fb04e200 ti: ffff8800ea4d8000 task.ti: ffff8800ea4d8000 RIP: 0010:[<ffffffffa05e96a8>] [<ffffffffa05e96a8>] __ocfs2_resv_find_window+0x498/0x760 [ocfs2] Call Trace: ocfs2_resmap_resv_bits+0x10d/0x400 [ocfs2] ocfs2_claim_local_alloc_bits+0xd0/0x640 [ocfs2] __ocfs2_claim_clusters+0x178/0x360 [ocfs2] ocfs2_claim_clusters+0x1f/0x30 [ocfs2] ocfs2_convert_inline_data_to_extents+0x634/0xa60 [ocfs2] ocfs2_write_begin_nolock+0x1c6/0x1da0 [ocfs2] ocfs2_write_begin+0x13e/0x230 [ocfs2] generic_perform_write+0xbf/0x1c0 __generic_file_write_iter+0x19c/0x1d0 ocfs2_file_write_iter+0x589/0x1360 [ocfs2] __vfs_write+0xb8/0x110 vfs_write+0xa9/0x1b0 SyS_write+0x46/0xb0 system_call_fastpath+0x18/0xd7 Code: ff ff 8b 75 b8 39 75 b0 8b 45 c8 89 45 98 0f 84 e5 fe ff ff 45 8b 74 24 18 41 8b 54 24 1c e9 56 fc ff ff 85 c0 0f 85 48 ff ff ff <0f> 0b 48 8b 05 cf c3 de ff 48 ba 00 00 00 00 00 00 00 10 48 85 RIP __ocfs2_resv_find_window+0x498/0x760 [ocfs2] RSP <ffff8800ea4db668> ---[ end trace 566f07529f2edf3c ]--- Kernel panic - not syncing: Fatal exception Kernel Offset: disabled

Link: http://lkml.kernel.org/r/20181121020023.3034-2-junxiao.bi@oracle.com Signed-off-by: Junxiao Bi junxiao.bi@oracle.com Reviewed-by: Yiwen Jiang jiangyiwen@huawei.com Acked-by: Joseph Qi jiangqi903@gmail.com Cc: Jun Piao piaojun@huawei.com Cc: Mark Fasheh mfasheh@versity.com Cc: Joel Becker jlbec@evilplan.org Cc: Changwei Ge ge.changwei@h3c.com Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- fs/ocfs2/localalloc.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/fs/ocfs2/localalloc.c b/fs/ocfs2/localalloc.c index 0a4457fb0711..85111d740c9d 100644 --- a/fs/ocfs2/localalloc.c +++ b/fs/ocfs2/localalloc.c @@ -345,13 +345,18 @@ int ocfs2_load_local_alloc(struct ocfs2_super *osb) if (num_used || alloc->id1.bitmap1.i_used || alloc->id1.bitmap1.i_total - || la->la_bm_off) - mlog(ML_ERROR, "Local alloc hasn't been recovered!\n" + || la->la_bm_off) { + mlog(ML_ERROR, "inconsistent detected, clean journal with" + " unrecovered local alloc, please run fsck.ocfs2!\n" "found = %u, set = %u, taken = %u, off = %u\n", num_used, le32_to_cpu(alloc->id1.bitmap1.i_used), le32_to_cpu(alloc->id1.bitmap1.i_total), OCFS2_LOCAL_ALLOC(alloc)->la_bm_off);

+ status = -EINVAL; + goto bail; + } + osb->local_alloc_bh = alloc_bh; osb->local_alloc_state = OCFS2_LA_ENABLED;

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

[ Upstream commit 7550c6079846a24f30d15ac75a941c8515dbedfb ]

Patch series "THP eligibility reporting via proc".

This series of three patches aims at making THP eligibility reporting much more robust and long term sustainable. The trigger for the change is a regression report [2] and the long follow up discussion. In short the specific application didn't have good API to query whether a particular mapping can be backed by THP so it has used VMA flags to workaround that. These flags represent a deep internal state of VMAs and as such they should be used by userspace with a great deal of caution.

A similar has happened for [3] when users complained that VM_MIXEDMAP is no longer set on DAX mappings. Again a lack of a proper API led to an abuse.

The first patch in the series tries to emphasise that that the semantic of flags might change and any application consuming those should be really careful.

The remaining two patches provide a more suitable interface to address [2] and provide a consistent API to query the THP status both for each VMA and process wide as well. [1]

http://lkml.kernel.org/r/20181120103515.25280-1-mhocko@kernel.org [2] http://lkml.kernel.org/r/http://lkml.kernel.org/r/alpine.DEB.2.21.1809241054... [3] http://lkml.kernel.org/r/20181002100531.GC4135@quack2.suse.cz

This patch (of 3):

Even though vma flags exported via /proc/<pid>/smaps are explicitly documented to be not guaranteed for future compatibility the warning doesn't go far enough because it doesn't mention semantic changes to those flags. And they are important as well because these flags are a deep implementation internal to the MM code and the semantic might change at any time.

Let's consider two recent examples: http://lkml.kernel.org/r/20181002100531.GC4135@quack2.suse.cz : commit e1fb4a086495 "dax: remove VM_MIXEDMAP for fsdax and device dax" has : removed VM_MIXEDMAP flag from DAX VMAs. Now our testing shows that in the : mean time certain customer of ours started poking into /proc/<pid>/smaps : and looks at VMA flags there and if VM_MIXEDMAP is missing among the VMA : flags, the application just fails to start complaining that DAX support is : missing in the kernel.

http://lkml.kernel.org/r/alpine.DEB.2.21.1809241054050.224429@chino.kir.corp... : Commit 1860033237d4 ("mm: make PR_SET_THP_DISABLE immediately active") : introduced a regression in that userspace cannot always determine the set : of vmas where thp is ineligible. : Userspace relies on the "nh" flag being emitted as part of /proc/pid/smaps : to determine if a vma is eligible to be backed by hugepages. : Previous to this commit, prctl(PR_SET_THP_DISABLE, 1) would cause thp to : be disabled and emit "nh" as a flag for the corresponding vmas as part of : /proc/pid/smaps. After the commit, thp is disabled by means of an mm : flag and "nh" is not emitted. : This causes smaps parsing libraries to assume a vma is eligible for thp : and ends up puzzling the user on why its memory is not backed by thp.

In both cases userspace was relying on a semantic of a specific VMA flag. The primary reason why that happened is a lack of a proper interface. While this has been worked on and it will be fixed properly, it seems that our wording could see some refinement and be more vocal about semantic aspect of these flags as well.

Link: http://lkml.kernel.org/r/20181211143641.3503-2-mhocko@kernel.org Signed-off-by: Michal Hocko mhocko@suse.com Acked-by: Jan Kara jack@suse.cz Acked-by: Dan Williams dan.j.williams@intel.com Acked-by: David Rientjes rientjes@google.com Acked-by: Mike Rapoport rppt@linux.ibm.com Acked-by: Vlastimil Babka vbabka@suse.cz Cc: Dan Williams dan.j.williams@intel.com Cc: David Rientjes rientjes@google.com Cc: Paul Oppenheimer bepvte@gmail.com Cc: William Kucharski william.kucharski@oracle.com Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- Documentation/filesystems/proc.txt | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt index 6d2689ebf824..5b87946a53a3 100644 --- a/Documentation/filesystems/proc.txt +++ b/Documentation/filesystems/proc.txt @@ -466,7 +466,9 @@ manner. The codes are the following:

Note that there is no guarantee that every flag and associated mnemonic will be present in all further kernel releases. Things get changed, the flags may -be vanished or the reverse -- new added. +be vanished or the reverse -- new added. Interpretation of their meaning +might change in future as well. So each consumer of these flags has to +follow each specific kernel version for the exact semantic.

This file is only present if the CONFIG_MMU kernel configuration option is enabled.

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Corey Minyard cminyard@mvista.com

commit 7d6380cd40f7993f75c4bde5b36f6019237e8719 upstream.

The block number was not being compared right, it was off by one when checking the response.

Some statistics wouldn't be incremented properly in some cases.

Check to see if that middle-part messages always have 31 bytes of data.

Signed-off-by: Corey Minyard cminyard@mvista.com Cc: stable@vger.kernel.org # 4.4 Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/char/ipmi/ipmi_ssif.c | 25 +++++++++++++++++-------- 1 file changed, 17 insertions(+), 8 deletions(-)

--- a/drivers/char/ipmi/ipmi_ssif.c +++ b/drivers/char/ipmi/ipmi_ssif.c @@ -637,8 +637,9 @@ static void msg_done_handler(struct ssif

/* Remove the multi-part read marker. */ len -= 2; + data += 2; for (i = 0; i < len; i++) - ssif_info->data[i] = data[i+2]; + ssif_info->data[i] = data[i]; ssif_info->multi_len = len; ssif_info->multi_pos = 1;

@@ -666,8 +667,19 @@ static void msg_done_handler(struct ssif }

blocknum = data[0]; + len--; + data++; + + if (blocknum != 0xff && len != 31) { + /* All blocks but the last must have 31 data bytes. */ + result = -EIO; + if (ssif_info->ssif_debug & SSIF_DEBUG_MSG) + pr_info("Received middle message <31\n");

- if (ssif_info->multi_len + len - 1 > IPMI_MAX_MSG_LENGTH) { + goto continue_op; + } + + if (ssif_info->multi_len + len > IPMI_MAX_MSG_LENGTH) { /* Received message too big, abort the operation. */ result = -E2BIG; if (ssif_info->ssif_debug & SSIF_DEBUG_MSG) @@ -676,16 +688,14 @@ static void msg_done_handler(struct ssif goto continue_op; }

- /* Remove the blocknum from the data. */ - len--; for (i = 0; i < len; i++) - ssif_info->data[i + ssif_info->multi_len] = data[i + 1]; + ssif_info->data[i + ssif_info->multi_len] = data[i]; ssif_info->multi_len += len; if (blocknum == 0xff) { /* End of read */ len = ssif_info->multi_len; data = ssif_info->data; - } else if (blocknum + 1 != ssif_info->multi_pos) { + } else if (blocknum != ssif_info->multi_pos) { /* * Out of sequence block, just abort. Block * numbers start at zero for the second block, @@ -713,6 +723,7 @@ static void msg_done_handler(struct ssif } }

+ continue_op: if (result < 0) { ssif_inc_stat(ssif_info, receive_errors); } else { @@ -720,8 +731,6 @@ static void msg_done_handler(struct ssif ssif_inc_stat(ssif_info, received_message_parts); }

- - continue_op: if (ssif_info->ssif_debug & SSIF_DEBUG_STATE) pr_info(PFX "DONE 1: state = %d, result=%d.\n", ssif_info->ssif_state, result);