[f2fs-dev] [PATCH AUTOSEL 5.10 10/31] f2fs: Handle casefolding with Encryption

[f2fs-dev] [PATCH AUTOSEL 5.10 10/31] f2fs: Handle casefolding with Encryption

[Sasha Levin]

From: Daniel Rosenberg <drosen@google.com>

[ Upstream commit 7ad08a58bf67594057362e45cbddd3e27e53e557 ]

Expand f2fs's casefolding support to include encrypted directories.  To
index casefolded+encrypted directories, we use the SipHash of the
casefolded name, keyed by a key derived from the directory's fscrypt
master key.  This ensures that the dirhash doesn't leak information
about the plaintext filenames.

Encryption keys are unavailable during roll-forward recovery, so we
can't compute the dirhash when recovering a new dentry in an encrypted +
casefolded directory.  To avoid having to force a checkpoint when a new
file is fsync'ed, store the dirhash on-disk appended to i_name.

This patch incorporates work by Eric Biggers <ebiggers@google.com>
and Jaegeuk Kim <jaegeuk@kernel.org>.

Co-developed-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Daniel Rosenberg <drosen@google.com>
Reviewed-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/f2fs/dir.c      | 98 +++++++++++++++++++++++++++++++++++-----------
 fs/f2fs/f2fs.h     |  8 ++--
 fs/f2fs/hash.c     | 11 +++++-
 fs/f2fs/inline.c   |  4 ++
 fs/f2fs/recovery.c | 12 +++++-
 fs/f2fs/super.c    |  6 ---
 6 files changed, 106 insertions(+), 33 deletions(-)

diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index 4b9ef8bbfa4a9..4ee0b7070c157 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -5,6 +5,7 @@
  * Copyright (c) 2012 Samsung Electronics Co., Ltd.
  *             http://www.samsung.com/
  */
+#include <asm/unaligned.h>
 #include <linux/fs.h>
 #include <linux/f2fs_fs.h>
 #include <linux/sched/signal.h>
@@ -206,30 +207,55 @@ static struct f2fs_dir_entry *find_in_block(struct inode *dir,
 /*
  * Test whether a case-insensitive directory entry matches the filename
  * being searched for.
+ *
+ * Returns 1 for a match, 0 for no match, and -errno on an error.
  */
-static bool f2fs_match_ci_name(const struct inode *dir, const struct qstr *name,
+static int f2fs_match_ci_name(const struct inode *dir, const struct qstr *name,
 			       const u8 *de_name, u32 de_name_len)
 {
 	const struct super_block *sb = dir->i_sb;
 	const struct unicode_map *um = sb->s_encoding;
+	struct fscrypt_str decrypted_name = FSTR_INIT(NULL, de_name_len);
 	struct qstr entry = QSTR_INIT(de_name, de_name_len);
 	int res;
 
+	if (IS_ENCRYPTED(dir)) {
+		const struct fscrypt_str encrypted_name =
+			FSTR_INIT((u8 *)de_name, de_name_len);
+
+		if (WARN_ON_ONCE(!fscrypt_has_encryption_key(dir)))
+			return -EINVAL;
+
+		decrypted_name.name = kmalloc(de_name_len, GFP_KERNEL);
+		if (!decrypted_name.name)
+			return -ENOMEM;
+		res = fscrypt_fname_disk_to_usr(dir, 0, 0, &encrypted_name,
+						&decrypted_name);
+		if (res < 0)
+			goto out;
+		entry.name = decrypted_name.name;
+		entry.len = decrypted_name.len;
+	}
+
 	res = utf8_strncasecmp_folded(um, name, &entry);
-	if (res < 0) {
-		/*
-		 * In strict mode, ignore invalid names.  In non-strict mode,
-		 * fall back to treating them as opaque byte sequences.
-		 */
-		if (sb_has_strict_encoding(sb) || name->len != entry.len)
-			return false;
-		return !memcmp(name->name, entry.name, name->len);
+	/*
+	 * In strict mode, ignore invalid names.  In non-strict mode,
+	 * fall back to treating them as opaque byte sequences.
+	 */
+	if (res < 0 && !sb_has_strict_encoding(sb)) {
+		res = name->len == entry.len &&
+				memcmp(name->name, entry.name, name->len) == 0;
+	} else {
+		/* utf8_strncasecmp_folded returns 0 on match */
+		res = (res == 0);
 	}
-	return res == 0;
+out:
+	kfree(decrypted_name.name);
+	return res;
 }
 #endif /* CONFIG_UNICODE */
 
-static inline bool f2fs_match_name(const struct inode *dir,
+static inline int f2fs_match_name(const struct inode *dir,
 				   const struct f2fs_filename *fname,
 				   const u8 *de_name, u32 de_name_len)
 {
@@ -256,6 +282,7 @@ struct f2fs_dir_entry *f2fs_find_target_dentry(const struct f2fs_dentry_ptr *d,
 	struct f2fs_dir_entry *de;
 	unsigned long bit_pos = 0;
 	int max_len = 0;
+	int res = 0;
 
 	if (max_slots)
 		*max_slots = 0;
@@ -273,10 +300,15 @@ struct f2fs_dir_entry *f2fs_find_target_dentry(const struct f2fs_dentry_ptr *d,
 			continue;
 		}
 
-		if (de->hash_code == fname->hash &&
-		    f2fs_match_name(d->inode, fname, d->filename[bit_pos],
-				    le16_to_cpu(de->name_len)))
-			goto found;
+		if (de->hash_code == fname->hash) {
+			res = f2fs_match_name(d->inode, fname,
+					      d->filename[bit_pos],
+					      le16_to_cpu(de->name_len));
+			if (res < 0)
+				return ERR_PTR(res);
+			if (res)
+				goto found;
+		}
 
 		if (max_slots && max_len > *max_slots)
 			*max_slots = max_len;
@@ -326,7 +358,11 @@ static struct f2fs_dir_entry *find_in_level(struct inode *dir,
 		}
 
 		de = find_in_block(dir, dentry_page, fname, &max_slots);
-		if (de) {
+		if (IS_ERR(de)) {
+			*res_page = ERR_CAST(de);
+			de = NULL;
+			break;
+		} else if (de) {
 			*res_page = dentry_page;
 			break;
 		}
@@ -448,17 +484,39 @@ void f2fs_set_link(struct inode *dir, struct f2fs_dir_entry *de,
 	f2fs_put_page(page, 1);
 }
 
-static void init_dent_inode(const struct f2fs_filename *fname,
+static void init_dent_inode(struct inode *dir, struct inode *inode,
+			    const struct f2fs_filename *fname,
 			    struct page *ipage)
 {
 	struct f2fs_inode *ri;
 
+	if (!fname) /* tmpfile case? */
+		return;
+
 	f2fs_wait_on_page_writeback(ipage, NODE, true, true);
 
 	/* copy name info. to this inode page */
 	ri = F2FS_INODE(ipage);
 	ri->i_namelen = cpu_to_le32(fname->disk_name.len);
 	memcpy(ri->i_name, fname->disk_name.name, fname->disk_name.len);
+	if (IS_ENCRYPTED(dir)) {
+		file_set_enc_name(inode);
+		/*
+		 * Roll-forward recovery doesn't have encryption keys available,
+		 * so it can't compute the dirhash for encrypted+casefolded
+		 * filenames.  Append it to i_name if possible.  Else, disable
+		 * roll-forward recovery of the dentry (i.e., make fsync'ing the
+		 * file force a checkpoint) by setting LOST_PINO.
+		 */
+		if (IS_CASEFOLDED(dir)) {
+			if (fname->disk_name.len + sizeof(f2fs_hash_t) <=
+			    F2FS_NAME_LEN)
+				put_unaligned(fname->hash, (f2fs_hash_t *)
+					&ri->i_name[fname->disk_name.len]);
+			else
+				file_lost_pino(inode);
+		}
+	}
 	set_page_dirty(ipage);
 }
 
@@ -541,11 +599,7 @@ struct page *f2fs_init_inode_metadata(struct inode *inode, struct inode *dir,
 			return page;
 	}
 
-	if (fname) {
-		init_dent_inode(fname, page);
-		if (IS_ENCRYPTED(dir))
-			file_set_enc_name(inode);
-	}
+	init_dent_inode(dir, inode, fname, page);
 
 	/*
 	 * This file should be checkpointed during fsync.
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 9a321c52facec..8cba43eb0b24a 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -533,9 +533,11 @@ struct f2fs_filename {
 #ifdef CONFIG_UNICODE
 	/*
 	 * For casefolded directories: the casefolded name, but it's left NULL
-	 * if the original name is not valid Unicode or if the filesystem is
-	 * doing an internal operation where usr_fname is also NULL.  In these
-	 * cases we fall back to treating the name as an opaque byte sequence.
+	 * if the original name is not valid Unicode, if the directory is both
+	 * casefolded and encrypted and its encryption key is unavailable, or if
+	 * the filesystem is doing an internal operation where usr_fname is also
+	 * NULL.  In all these cases we fall back to treating the name as an
+	 * opaque byte sequence.
 	 */
 	struct fscrypt_str cf_name;
 #endif
diff --git a/fs/f2fs/hash.c b/fs/f2fs/hash.c
index de841aaf3c439..e3beac546c63a 100644
--- a/fs/f2fs/hash.c
+++ b/fs/f2fs/hash.c
@@ -111,7 +111,9 @@ void f2fs_hash_filename(const struct inode *dir, struct f2fs_filename *fname)
 		 * If the casefolded name is provided, hash it instead of the
 		 * on-disk name.  If the casefolded name is *not* provided, that
 		 * should only be because the name wasn't valid Unicode, so fall
-		 * back to treating the name as an opaque byte sequence.
+		 * back to treating the name as an opaque byte sequence.  Note
+		 * that to handle encrypted directories, the fallback must use
+		 * usr_fname (plaintext) rather than disk_name (ciphertext).
 		 */
 		WARN_ON_ONCE(!fname->usr_fname->name);
 		if (fname->cf_name.name) {
@@ -121,6 +123,13 @@ void f2fs_hash_filename(const struct inode *dir, struct f2fs_filename *fname)
 			name = fname->usr_fname->name;
 			len = fname->usr_fname->len;
 		}
+		if (IS_ENCRYPTED(dir)) {
+			struct qstr tmp = QSTR_INIT(name, len);
+
+			fname->hash =
+				cpu_to_le32(fscrypt_fname_siphash(dir, &tmp));
+			return;
+		}
 	}
 #endif
 	fname->hash = cpu_to_le32(TEA_hash_name(name, len));
diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c
index 70384e31788db..92e9852d316ad 100644
--- a/fs/f2fs/inline.c
+++ b/fs/f2fs/inline.c
@@ -332,6 +332,10 @@ struct f2fs_dir_entry *f2fs_find_in_inline_dir(struct inode *dir,
 	make_dentry_ptr_inline(dir, &d, inline_dentry);
 	de = f2fs_find_target_dentry(&d, fname, NULL);
 	unlock_page(ipage);
+	if (IS_ERR(de)) {
+		*res_page = ERR_CAST(de);
+		de = NULL;
+	}
 	if (de)
 		*res_page = ipage;
 	else
diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c
index 4f12ade6410a1..0947d36af1a8e 100644
--- a/fs/f2fs/recovery.c
+++ b/fs/f2fs/recovery.c
@@ -5,6 +5,7 @@
  * Copyright (c) 2012 Samsung Electronics Co., Ltd.
  *             http://www.samsung.com/
  */
+#include <asm/unaligned.h>
 #include <linux/fs.h>
 #include <linux/f2fs_fs.h>
 #include "f2fs.h"
@@ -128,7 +129,16 @@ static int init_recovered_filename(const struct inode *dir,
 	}
 
 	/* Compute the hash of the filename */
-	if (IS_CASEFOLDED(dir)) {
+	if (IS_ENCRYPTED(dir) && IS_CASEFOLDED(dir)) {
+		/*
+		 * In this case the hash isn't computable without the key, so it
+		 * was saved on-disk.
+		 */
+		if (fname->disk_name.len + sizeof(f2fs_hash_t) > F2FS_NAME_LEN)
+			return -EINVAL;
+		fname->hash = get_unaligned((f2fs_hash_t *)
+				&raw_inode->i_name[fname->disk_name.len]);
+	} else if (IS_CASEFOLDED(dir)) {
 		err = f2fs_init_casefolded_name(dir, fname);
 		if (err)
 			return err;
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 00eff2f518079..ba859eeca69a3 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -3399,12 +3399,6 @@ static int f2fs_setup_casefold(struct f2fs_sb_info *sbi)
 		struct unicode_map *encoding;
 		__u16 encoding_flags;
 
-		if (f2fs_sb_has_encrypt(sbi)) {
-			f2fs_err(sbi,
-				"Can't mount with encoding and encryption");
-			return -EINVAL;
-		}
-
 		if (f2fs_sb_read_encoding(sbi->raw_super, &encoding_info,
 					  &encoding_flags)) {
 			f2fs_err(sbi,
-- 
2.27.0



_______________________________________________
Linux-f2fs-devel mailing list
Linux-f2fs-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel

[f2fs-dev] [PATCH AUTOSEL 5.10 11/31] f2fs: avoid race condition for shrinker count

[Sasha Levin]

From: Jaegeuk Kim <jaegeuk@kernel.org>

[ Upstream commit a95ba66ac1457b76fe472c8e092ab1006271f16c ]

Light reported sometimes shinker gets nat_cnt < dirty_nat_cnt resulting in
wrong do_shinker work. Let's avoid to return insane overflowed value by adding
single tracking value.

Reported-by: Light Hsieh <Light.Hsieh@mediatek.com>
Reviewed-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/f2fs/checkpoint.c |  2 +-
 fs/f2fs/debug.c      | 11 ++++++-----
 fs/f2fs/f2fs.h       | 10 ++++++++--
 fs/f2fs/node.c       | 29 ++++++++++++++++++-----------
 fs/f2fs/node.h       |  4 ++--
 fs/f2fs/shrinker.c   |  4 +---
 6 files changed, 36 insertions(+), 24 deletions(-)

diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index 023462e80e58d..b39bf416d5114 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -1600,7 +1600,7 @@ int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 			goto out;
 		}
 
-		if (NM_I(sbi)->dirty_nat_cnt == 0 &&
+		if (NM_I(sbi)->nat_cnt[DIRTY_NAT] == 0 &&
 				SIT_I(sbi)->dirty_sentries == 0 &&
 				prefree_segments(sbi) == 0) {
 			f2fs_flush_sit_entries(sbi, cpc);
diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c
index a8357fd4f5fab..197c914119da8 100644
--- a/fs/f2fs/debug.c
+++ b/fs/f2fs/debug.c
@@ -145,8 +145,8 @@ static void update_general_status(struct f2fs_sb_info *sbi)
 		si->node_pages = NODE_MAPPING(sbi)->nrpages;
 	if (sbi->meta_inode)
 		si->meta_pages = META_MAPPING(sbi)->nrpages;
-	si->nats = NM_I(sbi)->nat_cnt;
-	si->dirty_nats = NM_I(sbi)->dirty_nat_cnt;
+	si->nats = NM_I(sbi)->nat_cnt[TOTAL_NAT];
+	si->dirty_nats = NM_I(sbi)->nat_cnt[DIRTY_NAT];
 	si->sits = MAIN_SEGS(sbi);
 	si->dirty_sits = SIT_I(sbi)->dirty_sentries;
 	si->free_nids = NM_I(sbi)->nid_cnt[FREE_NID];
@@ -278,9 +278,10 @@ static void update_mem_info(struct f2fs_sb_info *sbi)
 	si->cache_mem += (NM_I(sbi)->nid_cnt[FREE_NID] +
 				NM_I(sbi)->nid_cnt[PREALLOC_NID]) *
 				sizeof(struct free_nid);
-	si->cache_mem += NM_I(sbi)->nat_cnt * sizeof(struct nat_entry);
-	si->cache_mem += NM_I(sbi)->dirty_nat_cnt *
-					sizeof(struct nat_entry_set);
+	si->cache_mem += NM_I(sbi)->nat_cnt[TOTAL_NAT] *
+				sizeof(struct nat_entry);
+	si->cache_mem += NM_I(sbi)->nat_cnt[DIRTY_NAT] *
+				sizeof(struct nat_entry_set);
 	si->cache_mem += si->inmem_pages * sizeof(struct inmem_pages);
 	for (i = 0; i < MAX_INO_ENTRY; i++)
 		si->cache_mem += sbi->im[i].ino_num * sizeof(struct ino_entry);
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 8cba43eb0b24a..14ace0e21d389 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -896,6 +896,13 @@ enum nid_state {
 	MAX_NID_STATE,
 };
 
+enum nat_state {
+	TOTAL_NAT,
+	DIRTY_NAT,
+	RECLAIMABLE_NAT,
+	MAX_NAT_STATE,
+};
+
 struct f2fs_nm_info {
 	block_t nat_blkaddr;		/* base disk address of NAT */
 	nid_t max_nid;			/* maximum possible node ids */
@@ -911,8 +918,7 @@ struct f2fs_nm_info {
 	struct rw_semaphore nat_tree_lock;	/* protect nat_tree_lock */
 	struct list_head nat_entries;	/* cached nat entry list (clean) */
 	spinlock_t nat_list_lock;	/* protect clean nat entry list */
-	unsigned int nat_cnt;		/* the # of cached nat entries */
-	unsigned int dirty_nat_cnt;	/* total num of nat entries in set */
+	unsigned int nat_cnt[MAX_NAT_STATE]; /* the # of cached nat entries */
 	unsigned int nat_blocks;	/* # of nat blocks */
 
 	/* free node ids management */
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index d5d8ce077f295..56505b8e2b8d3 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -62,8 +62,8 @@ bool f2fs_available_free_memory(struct f2fs_sb_info *sbi, int type)
 				sizeof(struct free_nid)) >> PAGE_SHIFT;
 		res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 2);
 	} else if (type == NAT_ENTRIES) {
-		mem_size = (nm_i->nat_cnt * sizeof(struct nat_entry)) >>
-							PAGE_SHIFT;
+		mem_size = (nm_i->nat_cnt[TOTAL_NAT] *
+				sizeof(struct nat_entry)) >> PAGE_SHIFT;
 		res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 2);
 		if (excess_cached_nats(sbi))
 			res = false;
@@ -177,7 +177,8 @@ static struct nat_entry *__init_nat_entry(struct f2fs_nm_info *nm_i,
 	list_add_tail(&ne->list, &nm_i->nat_entries);
 	spin_unlock(&nm_i->nat_list_lock);
 
-	nm_i->nat_cnt++;
+	nm_i->nat_cnt[TOTAL_NAT]++;
+	nm_i->nat_cnt[RECLAIMABLE_NAT]++;
 	return ne;
 }
 
@@ -207,7 +208,8 @@ static unsigned int __gang_lookup_nat_cache(struct f2fs_nm_info *nm_i,
 static void __del_from_nat_cache(struct f2fs_nm_info *nm_i, struct nat_entry *e)
 {
 	radix_tree_delete(&nm_i->nat_root, nat_get_nid(e));
-	nm_i->nat_cnt--;
+	nm_i->nat_cnt[TOTAL_NAT]--;
+	nm_i->nat_cnt[RECLAIMABLE_NAT]--;
 	__free_nat_entry(e);
 }
 
@@ -253,7 +255,8 @@ static void __set_nat_cache_dirty(struct f2fs_nm_info *nm_i,
 	if (get_nat_flag(ne, IS_DIRTY))
 		goto refresh_list;
 
-	nm_i->dirty_nat_cnt++;
+	nm_i->nat_cnt[DIRTY_NAT]++;
+	nm_i->nat_cnt[RECLAIMABLE_NAT]--;
 	set_nat_flag(ne, IS_DIRTY, true);
 refresh_list:
 	spin_lock(&nm_i->nat_list_lock);
@@ -273,7 +276,8 @@ static void __clear_nat_cache_dirty(struct f2fs_nm_info *nm_i,
 
 	set_nat_flag(ne, IS_DIRTY, false);
 	set->entry_cnt--;
-	nm_i->dirty_nat_cnt--;
+	nm_i->nat_cnt[DIRTY_NAT]--;
+	nm_i->nat_cnt[RECLAIMABLE_NAT]++;
 }
 
 static unsigned int __gang_lookup_nat_set(struct f2fs_nm_info *nm_i,
@@ -2944,14 +2948,17 @@ int f2fs_flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	LIST_HEAD(sets);
 	int err = 0;
 
-	/* during unmount, let's flush nat_bits before checking dirty_nat_cnt */
+	/*
+	 * during unmount, let's flush nat_bits before checking
+	 * nat_cnt[DIRTY_NAT].
+	 */
 	if (enabled_nat_bits(sbi, cpc)) {
 		down_write(&nm_i->nat_tree_lock);
 		remove_nats_in_journal(sbi);
 		up_write(&nm_i->nat_tree_lock);
 	}
 
-	if (!nm_i->dirty_nat_cnt)
+	if (!nm_i->nat_cnt[DIRTY_NAT])
 		return 0;
 
 	down_write(&nm_i->nat_tree_lock);
@@ -2962,7 +2969,8 @@ int f2fs_flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	 * into nat entry set.
 	 */
 	if (enabled_nat_bits(sbi, cpc) ||
-		!__has_cursum_space(journal, nm_i->dirty_nat_cnt, NAT_JOURNAL))
+		!__has_cursum_space(journal,
+			nm_i->nat_cnt[DIRTY_NAT], NAT_JOURNAL))
 		remove_nats_in_journal(sbi);
 
 	while ((found = __gang_lookup_nat_set(nm_i,
@@ -3086,7 +3094,6 @@ static int init_node_manager(struct f2fs_sb_info *sbi)
 						F2FS_RESERVED_NODE_NUM;
 	nm_i->nid_cnt[FREE_NID] = 0;
 	nm_i->nid_cnt[PREALLOC_NID] = 0;
-	nm_i->nat_cnt = 0;
 	nm_i->ram_thresh = DEF_RAM_THRESHOLD;
 	nm_i->ra_nid_pages = DEF_RA_NID_PAGES;
 	nm_i->dirty_nats_ratio = DEF_DIRTY_NAT_RATIO_THRESHOLD;
@@ -3220,7 +3227,7 @@ void f2fs_destroy_node_manager(struct f2fs_sb_info *sbi)
 			__del_from_nat_cache(nm_i, natvec[idx]);
 		}
 	}
-	f2fs_bug_on(sbi, nm_i->nat_cnt);
+	f2fs_bug_on(sbi, nm_i->nat_cnt[TOTAL_NAT]);
 
 	/* destroy nat set cache */
 	nid = 0;
diff --git a/fs/f2fs/node.h b/fs/f2fs/node.h
index 69e5859e993cf..f84541b57acbb 100644
--- a/fs/f2fs/node.h
+++ b/fs/f2fs/node.h
@@ -126,13 +126,13 @@ static inline void raw_nat_from_node_info(struct f2fs_nat_entry *raw_ne,
 
 static inline bool excess_dirty_nats(struct f2fs_sb_info *sbi)
 {
-	return NM_I(sbi)->dirty_nat_cnt >= NM_I(sbi)->max_nid *
+	return NM_I(sbi)->nat_cnt[DIRTY_NAT] >= NM_I(sbi)->max_nid *
 					NM_I(sbi)->dirty_nats_ratio / 100;
 }
 
 static inline bool excess_cached_nats(struct f2fs_sb_info *sbi)
 {
-	return NM_I(sbi)->nat_cnt >= DEF_NAT_CACHE_THRESHOLD;
+	return NM_I(sbi)->nat_cnt[TOTAL_NAT] >= DEF_NAT_CACHE_THRESHOLD;
 }
 
 static inline bool excess_dirty_nodes(struct f2fs_sb_info *sbi)
diff --git a/fs/f2fs/shrinker.c b/fs/f2fs/shrinker.c
index d66de5999a26d..dd3c3c7a90ec8 100644
--- a/fs/f2fs/shrinker.c
+++ b/fs/f2fs/shrinker.c
@@ -18,9 +18,7 @@ static unsigned int shrinker_run_no;
 
 static unsigned long __count_nat_entries(struct f2fs_sb_info *sbi)
 {
-	long count = NM_I(sbi)->nat_cnt - NM_I(sbi)->dirty_nat_cnt;
-
-	return count > 0 ? count : 0;
+	return NM_I(sbi)->nat_cnt[RECLAIMABLE_NAT];
 }
 
 static unsigned long __count_free_nids(struct f2fs_sb_info *sbi)
-- 
2.27.0



_______________________________________________
Linux-f2fs-devel mailing list
Linux-f2fs-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel

[f2fs-dev] [PATCH AUTOSEL 5.10 12/31] f2fs: fix race of pending_pages in decompression

[Sasha Levin]

From: Daeho Jeong <daehojeong@google.com>

[ Upstream commit 6422a71ef40e4751d59b8c9412e7e2dafe085878 ]

I found out f2fs_free_dic() is invoked in a wrong timing, but
f2fs_verify_bio() still needed the dic info and it triggered the
below kernel panic. It has been caused by the race condition of
pending_pages value between decompression and verity logic, when
the same compression cluster had been split in different bios.
By split bios, f2fs_verify_bio() ended up with decreasing
pending_pages value before it is reset to nr_cpages by
f2fs_decompress_pages() and caused the kernel panic.

[ 4416.564763] Unable to handle kernel NULL pointer dereference
               at virtual address 0000000000000000
...
[ 4416.896016] Workqueue: fsverity_read_queue f2fs_verity_work
[ 4416.908515] pc : fsverity_verify_page+0x20/0x78
[ 4416.913721] lr : f2fs_verify_bio+0x11c/0x29c
[ 4416.913722] sp : ffffffc019533cd0
[ 4416.913723] x29: ffffffc019533cd0 x28: 0000000000000402
[ 4416.913724] x27: 0000000000000001 x26: 0000000000000100
[ 4416.913726] x25: 0000000000000001 x24: 0000000000000004
[ 4416.913727] x23: 0000000000001000 x22: 0000000000000000
[ 4416.913728] x21: 0000000000000000 x20: ffffffff2076f9c0
[ 4416.913729] x19: ffffffff2076f9c0 x18: ffffff8a32380c30
[ 4416.913731] x17: ffffffc01f966d97 x16: 0000000000000298
[ 4416.913732] x15: 0000000000000000 x14: 0000000000000000
[ 4416.913733] x13: f074faec89ffffff x12: 0000000000000000
[ 4416.913734] x11: 0000000000001000 x10: 0000000000001000
[ 4416.929176] x9 : ffffffff20d1f5c7 x8 : 0000000000000000
[ 4416.929178] x7 : 626d7464ff286b6b x6 : ffffffc019533ade
[ 4416.929179] x5 : 000000008049000e x4 : ffffffff2793e9e0
[ 4416.929180] x3 : 000000008049000e x2 : ffffff89ecfa74d0
[ 4416.929181] x1 : 0000000000000c40 x0 : ffffffff2076f9c0
[ 4416.929184] Call trace:
[ 4416.929187]  fsverity_verify_page+0x20/0x78
[ 4416.929189]  f2fs_verify_bio+0x11c/0x29c
[ 4416.929192]  f2fs_verity_work+0x58/0x84
[ 4417.050667]  process_one_work+0x270/0x47c
[ 4417.055354]  worker_thread+0x27c/0x4d8
[ 4417.059784]  kthread+0x13c/0x320
[ 4417.063693]  ret_from_fork+0x10/0x18

Chao pointed this can happen by the below race condition.

Thread A        f2fs_post_read_wq          fsverity_wq
- f2fs_read_multi_pages()
  - f2fs_alloc_dic
   - dic->pending_pages = 2
   - submit_bio()
   - submit_bio()
               - f2fs_post_read_work() handle first bio
                - f2fs_decompress_work()
                 - __read_end_io()
                  - f2fs_decompress_pages()
                   - dic->pending_pages--
                - enqueue f2fs_verity_work()
                                           - f2fs_verity_work() handle first bio
                                            - f2fs_verify_bio()
                                             - dic->pending_pages--
               - f2fs_post_read_work() handle second bio
                - f2fs_decompress_work()
                - enqueue f2fs_verity_work()
                                            - f2fs_verify_pages()
                                            - f2fs_free_dic()

                                          - f2fs_verity_work() handle second bio
                                           - f2fs_verfy_bio()
                                                 - use-after-free on dic

Signed-off-by: Daeho Jeong <daehojeong@google.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/f2fs/compress.c |  2 --
 fs/f2fs/data.c     | 58 +++++++++++++++++++++++++++++++++++++---------
 fs/f2fs/f2fs.h     |  1 +
 3 files changed, 48 insertions(+), 13 deletions(-)

diff --git a/fs/f2fs/compress.c b/fs/f2fs/compress.c
index 14262e0f1cd60..c5fee4d7ea72f 100644
--- a/fs/f2fs/compress.c
+++ b/fs/f2fs/compress.c
@@ -798,8 +798,6 @@ void f2fs_decompress_pages(struct bio *bio, struct page *page, bool verity)
 	if (cops->destroy_decompress_ctx)
 		cops->destroy_decompress_ctx(dic);
 out_free_dic:
-	if (verity)
-		atomic_set(&dic->pending_pages, dic->nr_cpages);
 	if (!verity)
 		f2fs_decompress_end_io(dic->rpages, dic->cluster_size,
 								ret, false);
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index be4da52604edc..b29243ee1c3e5 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -202,7 +202,7 @@ static void f2fs_verify_bio(struct bio *bio)
 		dic = (struct decompress_io_ctx *)page_private(page);
 
 		if (dic) {
-			if (atomic_dec_return(&dic->pending_pages))
+			if (atomic_dec_return(&dic->verity_pages))
 				continue;
 			f2fs_verify_pages(dic->rpages,
 						dic->cluster_size);
@@ -1027,7 +1027,8 @@ static inline bool f2fs_need_verity(const struct inode *inode, pgoff_t idx)
 
 static struct bio *f2fs_grab_read_bio(struct inode *inode, block_t blkaddr,
 				      unsigned nr_pages, unsigned op_flag,
-				      pgoff_t first_idx, bool for_write)
+				      pgoff_t first_idx, bool for_write,
+				      bool for_verity)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct bio *bio;
@@ -1049,7 +1050,7 @@ static struct bio *f2fs_grab_read_bio(struct inode *inode, block_t blkaddr,
 		post_read_steps |= 1 << STEP_DECRYPT;
 	if (f2fs_compressed_file(inode))
 		post_read_steps |= 1 << STEP_DECOMPRESS_NOWQ;
-	if (f2fs_need_verity(inode, first_idx))
+	if (for_verity && f2fs_need_verity(inode, first_idx))
 		post_read_steps |= 1 << STEP_VERITY;
 
 	if (post_read_steps) {
@@ -1079,7 +1080,7 @@ static int f2fs_submit_page_read(struct inode *inode, struct page *page,
 	struct bio *bio;
 
 	bio = f2fs_grab_read_bio(inode, blkaddr, 1, op_flags,
-					page->index, for_write);
+					page->index, for_write, true);
 	if (IS_ERR(bio))
 		return PTR_ERR(bio);
 
@@ -2133,7 +2134,7 @@ static int f2fs_read_single_page(struct inode *inode, struct page *page,
 	if (bio == NULL) {
 		bio = f2fs_grab_read_bio(inode, block_nr, nr_pages,
 				is_readahead ? REQ_RAHEAD : 0, page->index,
-				false);
+				false, true);
 		if (IS_ERR(bio)) {
 			ret = PTR_ERR(bio);
 			bio = NULL;
@@ -2180,6 +2181,8 @@ int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret,
 	const unsigned blkbits = inode->i_blkbits;
 	const unsigned blocksize = 1 << blkbits;
 	struct decompress_io_ctx *dic = NULL;
+	struct bio_post_read_ctx *ctx;
+	bool for_verity = false;
 	int i;
 	int ret = 0;
 
@@ -2245,10 +2248,29 @@ int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret,
 		goto out_put_dnode;
 	}
 
+	/*
+	 * It's possible to enable fsverity on the fly when handling a cluster,
+	 * which requires complicated error handling. Instead of adding more
+	 * complexity, let's give a rule where end_io post-processes fsverity
+	 * per cluster. In order to do that, we need to submit bio, if previous
+	 * bio sets a different post-process policy.
+	 */
+	if (fsverity_active(cc->inode)) {
+		atomic_set(&dic->verity_pages, cc->nr_cpages);
+		for_verity = true;
+
+		if (bio) {
+			ctx = bio->bi_private;
+			if (!(ctx->enabled_steps & (1 << STEP_VERITY))) {
+				__submit_bio(sbi, bio, DATA);
+				bio = NULL;
+			}
+		}
+	}
+
 	for (i = 0; i < dic->nr_cpages; i++) {
 		struct page *page = dic->cpages[i];
 		block_t blkaddr;
-		struct bio_post_read_ctx *ctx;
 
 		blkaddr = data_blkaddr(dn.inode, dn.node_page,
 						dn.ofs_in_node + i + 1);
@@ -2264,17 +2286,31 @@ int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret,
 		if (!bio) {
 			bio = f2fs_grab_read_bio(inode, blkaddr, nr_pages,
 					is_readahead ? REQ_RAHEAD : 0,
-					page->index, for_write);
+					page->index, for_write, for_verity);
 			if (IS_ERR(bio)) {
+				unsigned int remained = dic->nr_cpages - i;
+				bool release = false;
+
 				ret = PTR_ERR(bio);
 				dic->failed = true;
-				if (!atomic_sub_return(dic->nr_cpages - i,
-							&dic->pending_pages)) {
+
+				if (for_verity) {
+					if (!atomic_sub_return(remained,
+						&dic->verity_pages))
+						release = true;
+				} else {
+					if (!atomic_sub_return(remained,
+						&dic->pending_pages))
+						release = true;
+				}
+
+				if (release) {
 					f2fs_decompress_end_io(dic->rpages,
-							cc->cluster_size, true,
-							false);
+						cc->cluster_size, true,
+						false);
 					f2fs_free_dic(dic);
 				}
+
 				f2fs_put_dnode(&dn);
 				*bio_ret = NULL;
 				return ret;
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 14ace0e21d389..72a25387f49bc 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -1412,6 +1412,7 @@ struct decompress_io_ctx {
 	size_t rlen;			/* valid data length in rbuf */
 	size_t clen;			/* valid data length in cbuf */
 	atomic_t pending_pages;		/* in-flight compressed page count */
+	atomic_t verity_pages;		/* in-flight page count for verity */
 	bool failed;			/* indicate IO error during decompression */
 	void *private;			/* payload buffer for specified decompression algorithm */
 	void *private2;			/* extra payload buffer */
-- 
2.27.0



_______________________________________________
Linux-f2fs-devel mailing list
Linux-f2fs-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel

[f2fs-dev] [PATCH AUTOSEL 5.10 15/31] f2fs: fix shift-out-of-bounds in sanity_check_raw_super()

[Sasha Levin]

From: Chao Yu <yuchao0@huawei.com>

[ Upstream commit e584bbe821229a3e7cc409eecd51df66f9268c21 ]

syzbot reported a bug which could cause shift-out-of-bounds issue,
fix it.

Call Trace:
 __dump_stack lib/dump_stack.c:79 [inline]
 dump_stack+0x107/0x163 lib/dump_stack.c:120
 ubsan_epilogue+0xb/0x5a lib/ubsan.c:148
 __ubsan_handle_shift_out_of_bounds.cold+0xb1/0x181 lib/ubsan.c:395
 sanity_check_raw_super fs/f2fs/super.c:2812 [inline]
 read_raw_super_block fs/f2fs/super.c:3267 [inline]
 f2fs_fill_super.cold+0x16c9/0x16f6 fs/f2fs/super.c:3519
 mount_bdev+0x34d/0x410 fs/super.c:1366
 legacy_get_tree+0x105/0x220 fs/fs_context.c:592
 vfs_get_tree+0x89/0x2f0 fs/super.c:1496
 do_new_mount fs/namespace.c:2896 [inline]
 path_mount+0x12ae/0x1e70 fs/namespace.c:3227
 do_mount fs/namespace.c:3240 [inline]
 __do_sys_mount fs/namespace.c:3448 [inline]
 __se_sys_mount fs/namespace.c:3425 [inline]
 __x64_sys_mount+0x27f/0x300 fs/namespace.c:3425
 do_syscall_64+0x2d/0x70 arch/x86/entry/common.c:46
 entry_SYSCALL_64_after_hwframe+0x44/0xa9

Reported-by: syzbot+ca9a785f8ac472085994@syzkaller.appspotmail.com
Signed-off-by: Anant Thazhemadam <anant.thazhemadam@gmail.com>
Signed-off-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/f2fs/super.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index ba859eeca69a3..822ae8c8fa39a 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -2744,7 +2744,6 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi,
 	block_t total_sections, blocks_per_seg;
 	struct f2fs_super_block *raw_super = (struct f2fs_super_block *)
 					(bh->b_data + F2FS_SUPER_OFFSET);
-	unsigned int blocksize;
 	size_t crc_offset = 0;
 	__u32 crc = 0;
 
@@ -2778,10 +2777,10 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi,
 	}
 
 	/* Currently, support only 4KB block size */
-	blocksize = 1 << le32_to_cpu(raw_super->log_blocksize);
-	if (blocksize != F2FS_BLKSIZE) {
-		f2fs_info(sbi, "Invalid blocksize (%u), supports only 4KB",
-			  blocksize);
+	if (le32_to_cpu(raw_super->log_blocksize) != F2FS_BLKSIZE_BITS) {
+		f2fs_info(sbi, "Invalid log_blocksize (%u), supports only %u",
+			  le32_to_cpu(raw_super->log_blocksize),
+			  F2FS_BLKSIZE_BITS);
 		return -EFSCORRUPTED;
 	}
 
-- 
2.27.0



_______________________________________________
Linux-f2fs-devel mailing list
Linux-f2fs-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel

Re: [f2fs-dev] [PATCH AUTOSEL 5.10 10/31] f2fs: Handle casefolding with Encryption

[Eric Biggers]

On Wed, Dec 30, 2020 at 08:02:52AM -0500, Sasha Levin wrote:
> From: Daniel Rosenberg <drosen@google.com>
> 
> [ Upstream commit 7ad08a58bf67594057362e45cbddd3e27e53e557 ]
> 
> Expand f2fs's casefolding support to include encrypted directories.  To
> index casefolded+encrypted directories, we use the SipHash of the
> casefolded name, keyed by a key derived from the directory's fscrypt
> master key.  This ensures that the dirhash doesn't leak information
> about the plaintext filenames.
> 
> Encryption keys are unavailable during roll-forward recovery, so we
> can't compute the dirhash when recovering a new dentry in an encrypted +
> casefolded directory.  To avoid having to force a checkpoint when a new
> file is fsync'ed, store the dirhash on-disk appended to i_name.
> 
> This patch incorporates work by Eric Biggers <ebiggers@google.com>
> and Jaegeuk Kim <jaegeuk@kernel.org>.
> 
> Co-developed-by: Eric Biggers <ebiggers@google.com>
> Signed-off-by: Eric Biggers <ebiggers@google.com>
> Signed-off-by: Daniel Rosenberg <drosen@google.com>
> Reviewed-by: Eric Biggers <ebiggers@google.com>
> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
> Signed-off-by: Sasha Levin <sashal@kernel.org>

Please don't backport this to the LTS kernels.  This is a new feature, not a
fix, and you missed prerequisite patches...

- Eric


_______________________________________________
Linux-f2fs-devel mailing list
Linux-f2fs-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel

Re: [f2fs-dev] [PATCH AUTOSEL 5.10 10/31] f2fs: Handle casefolding with Encryption

[Sasha Levin]

On Wed, Dec 30, 2020 at 10:01:56AM -0800, Eric Biggers wrote:
>On Wed, Dec 30, 2020 at 08:02:52AM -0500, Sasha Levin wrote:
>> From: Daniel Rosenberg <drosen@google.com>
>>
>> [ Upstream commit 7ad08a58bf67594057362e45cbddd3e27e53e557 ]
>>
>> Expand f2fs's casefolding support to include encrypted directories.  To
>> index casefolded+encrypted directories, we use the SipHash of the
>> casefolded name, keyed by a key derived from the directory's fscrypt
>> master key.  This ensures that the dirhash doesn't leak information
>> about the plaintext filenames.
>>
>> Encryption keys are unavailable during roll-forward recovery, so we
>> can't compute the dirhash when recovering a new dentry in an encrypted +
>> casefolded directory.  To avoid having to force a checkpoint when a new
>> file is fsync'ed, store the dirhash on-disk appended to i_name.
>>
>> This patch incorporates work by Eric Biggers <ebiggers@google.com>
>> and Jaegeuk Kim <jaegeuk@kernel.org>.
>>
>> Co-developed-by: Eric Biggers <ebiggers@google.com>
>> Signed-off-by: Eric Biggers <ebiggers@google.com>
>> Signed-off-by: Daniel Rosenberg <drosen@google.com>
>> Reviewed-by: Eric Biggers <ebiggers@google.com>
>> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
>> Signed-off-by: Sasha Levin <sashal@kernel.org>
>
>Please don't backport this to the LTS kernels.  This is a new feature, not a
>fix, and you missed prerequisite patches...

Sure, I'l drop it. Thanks!

-- 
Thanks,
Sasha


_______________________________________________
Linux-f2fs-devel mailing list
Linux-f2fs-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel