The patch below does not apply to the 5.10-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.10.y
git checkout FETCH_HEAD
git cherry-pick -x 93aef9eda1cea9e84ab2453fcceb8addad0e46f1
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024070808-exclude-sighing-1813@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^..
Possible dependencies:
93aef9eda1ce ("nilfs2: fix incorrect inode allocation from reserved inodes")
af6eae646851 ("nilfs2: convert persistent object allocator to use kmap_local")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 93aef9eda1cea9e84ab2453fcceb8addad0e46f1 Mon Sep 17 00:00:00 2001
From: Ryusuke Konishi <konishi.ryusuke(a)gmail.com>
Date: Sun, 23 Jun 2024 14:11:35 +0900
Subject: [PATCH] nilfs2: fix incorrect inode allocation from reserved inodes
If the bitmap block that manages the inode allocation status is corrupted,
nilfs_ifile_create_inode() may allocate a new inode from the reserved
inode area where it should not be allocated.
Previous fix commit d325dc6eb763 ("nilfs2: fix use-after-free bug of
struct nilfs_root"), fixed the problem that reserved inodes with inode
numbers less than NILFS_USER_INO (=11) were incorrectly reallocated due to
bitmap corruption, but since the start number of non-reserved inodes is
read from the super block and may change, in which case inode allocation
may occur from the extended reserved inode area.
If that happens, access to that inode will cause an IO error, causing the
file system to degrade to an error state.
Fix this potential issue by adding a wraparound option to the common
metadata object allocation routine and by modifying
nilfs_ifile_create_inode() to disable the option so that it only allocates
inodes with inode numbers greater than or equal to the inode number read
in "nilfs->ns_first_ino", regardless of the bitmap status of reserved
inodes.
Link: https://lkml.kernel.org/r/20240623051135.4180-4-konishi.ryusuke@gmail.com
Signed-off-by: Ryusuke Konishi <konishi.ryusuke(a)gmail.com>
Cc: Hillf Danton <hdanton(a)sina.com>
Cc: Jan Kara <jack(a)suse.cz>
Cc: Matthew Wilcox (Oracle) <willy(a)infradead.org>
Cc: <stable(a)vger.kernel.org>
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
diff --git a/fs/nilfs2/alloc.c b/fs/nilfs2/alloc.c
index 89caef7513db..ba50388ee4bf 100644
--- a/fs/nilfs2/alloc.c
+++ b/fs/nilfs2/alloc.c
@@ -377,11 +377,12 @@ void *nilfs_palloc_block_get_entry(const struct inode *inode, __u64 nr,
* @target: offset number of an entry in the group (start point)
* @bsize: size in bits
* @lock: spin lock protecting @bitmap
+ * @wrap: whether to wrap around
*/
static int nilfs_palloc_find_available_slot(unsigned char *bitmap,
unsigned long target,
unsigned int bsize,
- spinlock_t *lock)
+ spinlock_t *lock, bool wrap)
{
int pos, end = bsize;
@@ -397,6 +398,8 @@ static int nilfs_palloc_find_available_slot(unsigned char *bitmap,
end = target;
}
+ if (!wrap)
+ return -ENOSPC;
/* wrap around */
for (pos = 0; pos < end; pos++) {
@@ -495,9 +498,10 @@ int nilfs_palloc_count_max_entries(struct inode *inode, u64 nused, u64 *nmaxp)
* nilfs_palloc_prepare_alloc_entry - prepare to allocate a persistent object
* @inode: inode of metadata file using this allocator
* @req: nilfs_palloc_req structure exchanged for the allocation
+ * @wrap: whether to wrap around
*/
int nilfs_palloc_prepare_alloc_entry(struct inode *inode,
- struct nilfs_palloc_req *req)
+ struct nilfs_palloc_req *req, bool wrap)
{
struct buffer_head *desc_bh, *bitmap_bh;
struct nilfs_palloc_group_desc *desc;
@@ -516,7 +520,7 @@ int nilfs_palloc_prepare_alloc_entry(struct inode *inode,
entries_per_group = nilfs_palloc_entries_per_group(inode);
for (i = 0; i < ngroups; i += n) {
- if (group >= ngroups) {
+ if (group >= ngroups && wrap) {
/* wrap around */
group = 0;
maxgroup = nilfs_palloc_group(inode, req->pr_entry_nr,
@@ -550,7 +554,14 @@ int nilfs_palloc_prepare_alloc_entry(struct inode *inode,
bitmap_kaddr = kmap_local_page(bitmap_bh->b_page);
bitmap = bitmap_kaddr + bh_offset(bitmap_bh);
pos = nilfs_palloc_find_available_slot(
- bitmap, group_offset, entries_per_group, lock);
+ bitmap, group_offset, entries_per_group, lock,
+ wrap);
+ /*
+ * Since the search for a free slot in the second and
+ * subsequent bitmap blocks always starts from the
+ * beginning, the wrap flag only has an effect on the
+ * first search.
+ */
kunmap_local(bitmap_kaddr);
if (pos >= 0)
goto found;
diff --git a/fs/nilfs2/alloc.h b/fs/nilfs2/alloc.h
index b667e869ac07..d825a9faca6d 100644
--- a/fs/nilfs2/alloc.h
+++ b/fs/nilfs2/alloc.h
@@ -50,8 +50,8 @@ struct nilfs_palloc_req {
struct buffer_head *pr_entry_bh;
};
-int nilfs_palloc_prepare_alloc_entry(struct inode *,
- struct nilfs_palloc_req *);
+int nilfs_palloc_prepare_alloc_entry(struct inode *inode,
+ struct nilfs_palloc_req *req, bool wrap);
void nilfs_palloc_commit_alloc_entry(struct inode *,
struct nilfs_palloc_req *);
void nilfs_palloc_abort_alloc_entry(struct inode *, struct nilfs_palloc_req *);
diff --git a/fs/nilfs2/dat.c b/fs/nilfs2/dat.c
index 180fc8d36213..fc1caf63a42a 100644
--- a/fs/nilfs2/dat.c
+++ b/fs/nilfs2/dat.c
@@ -75,7 +75,7 @@ int nilfs_dat_prepare_alloc(struct inode *dat, struct nilfs_palloc_req *req)
{
int ret;
- ret = nilfs_palloc_prepare_alloc_entry(dat, req);
+ ret = nilfs_palloc_prepare_alloc_entry(dat, req, true);
if (ret < 0)
return ret;
diff --git a/fs/nilfs2/ifile.c b/fs/nilfs2/ifile.c
index 612e609158b5..1e86b9303b7c 100644
--- a/fs/nilfs2/ifile.c
+++ b/fs/nilfs2/ifile.c
@@ -56,13 +56,10 @@ int nilfs_ifile_create_inode(struct inode *ifile, ino_t *out_ino,
struct nilfs_palloc_req req;
int ret;
- req.pr_entry_nr = 0; /*
- * 0 says find free inode from beginning
- * of a group. dull code!!
- */
+ req.pr_entry_nr = NILFS_FIRST_INO(ifile->i_sb);
req.pr_entry_bh = NULL;
- ret = nilfs_palloc_prepare_alloc_entry(ifile, &req);
+ ret = nilfs_palloc_prepare_alloc_entry(ifile, &req, false);
if (!ret) {
ret = nilfs_palloc_get_entry_block(ifile, req.pr_entry_nr, 1,
&req.pr_entry_bh);
The patch below does not apply to the 5.15-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y
git checkout FETCH_HEAD
git cherry-pick -x 93aef9eda1cea9e84ab2453fcceb8addad0e46f1
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024070807-flagpole-strut-4d64@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^..
Possible dependencies:
93aef9eda1ce ("nilfs2: fix incorrect inode allocation from reserved inodes")
af6eae646851 ("nilfs2: convert persistent object allocator to use kmap_local")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 93aef9eda1cea9e84ab2453fcceb8addad0e46f1 Mon Sep 17 00:00:00 2001
From: Ryusuke Konishi <konishi.ryusuke(a)gmail.com>
Date: Sun, 23 Jun 2024 14:11:35 +0900
Subject: [PATCH] nilfs2: fix incorrect inode allocation from reserved inodes
If the bitmap block that manages the inode allocation status is corrupted,
nilfs_ifile_create_inode() may allocate a new inode from the reserved
inode area where it should not be allocated.
Previous fix commit d325dc6eb763 ("nilfs2: fix use-after-free bug of
struct nilfs_root"), fixed the problem that reserved inodes with inode
numbers less than NILFS_USER_INO (=11) were incorrectly reallocated due to
bitmap corruption, but since the start number of non-reserved inodes is
read from the super block and may change, in which case inode allocation
may occur from the extended reserved inode area.
If that happens, access to that inode will cause an IO error, causing the
file system to degrade to an error state.
Fix this potential issue by adding a wraparound option to the common
metadata object allocation routine and by modifying
nilfs_ifile_create_inode() to disable the option so that it only allocates
inodes with inode numbers greater than or equal to the inode number read
in "nilfs->ns_first_ino", regardless of the bitmap status of reserved
inodes.
Link: https://lkml.kernel.org/r/20240623051135.4180-4-konishi.ryusuke@gmail.com
Signed-off-by: Ryusuke Konishi <konishi.ryusuke(a)gmail.com>
Cc: Hillf Danton <hdanton(a)sina.com>
Cc: Jan Kara <jack(a)suse.cz>
Cc: Matthew Wilcox (Oracle) <willy(a)infradead.org>
Cc: <stable(a)vger.kernel.org>
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
diff --git a/fs/nilfs2/alloc.c b/fs/nilfs2/alloc.c
index 89caef7513db..ba50388ee4bf 100644
--- a/fs/nilfs2/alloc.c
+++ b/fs/nilfs2/alloc.c
@@ -377,11 +377,12 @@ void *nilfs_palloc_block_get_entry(const struct inode *inode, __u64 nr,
* @target: offset number of an entry in the group (start point)
* @bsize: size in bits
* @lock: spin lock protecting @bitmap
+ * @wrap: whether to wrap around
*/
static int nilfs_palloc_find_available_slot(unsigned char *bitmap,
unsigned long target,
unsigned int bsize,
- spinlock_t *lock)
+ spinlock_t *lock, bool wrap)
{
int pos, end = bsize;
@@ -397,6 +398,8 @@ static int nilfs_palloc_find_available_slot(unsigned char *bitmap,
end = target;
}
+ if (!wrap)
+ return -ENOSPC;
/* wrap around */
for (pos = 0; pos < end; pos++) {
@@ -495,9 +498,10 @@ int nilfs_palloc_count_max_entries(struct inode *inode, u64 nused, u64 *nmaxp)
* nilfs_palloc_prepare_alloc_entry - prepare to allocate a persistent object
* @inode: inode of metadata file using this allocator
* @req: nilfs_palloc_req structure exchanged for the allocation
+ * @wrap: whether to wrap around
*/
int nilfs_palloc_prepare_alloc_entry(struct inode *inode,
- struct nilfs_palloc_req *req)
+ struct nilfs_palloc_req *req, bool wrap)
{
struct buffer_head *desc_bh, *bitmap_bh;
struct nilfs_palloc_group_desc *desc;
@@ -516,7 +520,7 @@ int nilfs_palloc_prepare_alloc_entry(struct inode *inode,
entries_per_group = nilfs_palloc_entries_per_group(inode);
for (i = 0; i < ngroups; i += n) {
- if (group >= ngroups) {
+ if (group >= ngroups && wrap) {
/* wrap around */
group = 0;
maxgroup = nilfs_palloc_group(inode, req->pr_entry_nr,
@@ -550,7 +554,14 @@ int nilfs_palloc_prepare_alloc_entry(struct inode *inode,
bitmap_kaddr = kmap_local_page(bitmap_bh->b_page);
bitmap = bitmap_kaddr + bh_offset(bitmap_bh);
pos = nilfs_palloc_find_available_slot(
- bitmap, group_offset, entries_per_group, lock);
+ bitmap, group_offset, entries_per_group, lock,
+ wrap);
+ /*
+ * Since the search for a free slot in the second and
+ * subsequent bitmap blocks always starts from the
+ * beginning, the wrap flag only has an effect on the
+ * first search.
+ */
kunmap_local(bitmap_kaddr);
if (pos >= 0)
goto found;
diff --git a/fs/nilfs2/alloc.h b/fs/nilfs2/alloc.h
index b667e869ac07..d825a9faca6d 100644
--- a/fs/nilfs2/alloc.h
+++ b/fs/nilfs2/alloc.h
@@ -50,8 +50,8 @@ struct nilfs_palloc_req {
struct buffer_head *pr_entry_bh;
};
-int nilfs_palloc_prepare_alloc_entry(struct inode *,
- struct nilfs_palloc_req *);
+int nilfs_palloc_prepare_alloc_entry(struct inode *inode,
+ struct nilfs_palloc_req *req, bool wrap);
void nilfs_palloc_commit_alloc_entry(struct inode *,
struct nilfs_palloc_req *);
void nilfs_palloc_abort_alloc_entry(struct inode *, struct nilfs_palloc_req *);
diff --git a/fs/nilfs2/dat.c b/fs/nilfs2/dat.c
index 180fc8d36213..fc1caf63a42a 100644
--- a/fs/nilfs2/dat.c
+++ b/fs/nilfs2/dat.c
@@ -75,7 +75,7 @@ int nilfs_dat_prepare_alloc(struct inode *dat, struct nilfs_palloc_req *req)
{
int ret;
- ret = nilfs_palloc_prepare_alloc_entry(dat, req);
+ ret = nilfs_palloc_prepare_alloc_entry(dat, req, true);
if (ret < 0)
return ret;
diff --git a/fs/nilfs2/ifile.c b/fs/nilfs2/ifile.c
index 612e609158b5..1e86b9303b7c 100644
--- a/fs/nilfs2/ifile.c
+++ b/fs/nilfs2/ifile.c
@@ -56,13 +56,10 @@ int nilfs_ifile_create_inode(struct inode *ifile, ino_t *out_ino,
struct nilfs_palloc_req req;
int ret;
- req.pr_entry_nr = 0; /*
- * 0 says find free inode from beginning
- * of a group. dull code!!
- */
+ req.pr_entry_nr = NILFS_FIRST_INO(ifile->i_sb);
req.pr_entry_bh = NULL;
- ret = nilfs_palloc_prepare_alloc_entry(ifile, &req);
+ ret = nilfs_palloc_prepare_alloc_entry(ifile, &req, false);
if (!ret) {
ret = nilfs_palloc_get_entry_block(ifile, req.pr_entry_nr, 1,
&req.pr_entry_bh);
The patch below does not apply to the 6.1-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y
git checkout FETCH_HEAD
git cherry-pick -x 93aef9eda1cea9e84ab2453fcceb8addad0e46f1
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024070806-fifteen-agnostic-36a6@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^..
Possible dependencies:
93aef9eda1ce ("nilfs2: fix incorrect inode allocation from reserved inodes")
af6eae646851 ("nilfs2: convert persistent object allocator to use kmap_local")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 93aef9eda1cea9e84ab2453fcceb8addad0e46f1 Mon Sep 17 00:00:00 2001
From: Ryusuke Konishi <konishi.ryusuke(a)gmail.com>
Date: Sun, 23 Jun 2024 14:11:35 +0900
Subject: [PATCH] nilfs2: fix incorrect inode allocation from reserved inodes
If the bitmap block that manages the inode allocation status is corrupted,
nilfs_ifile_create_inode() may allocate a new inode from the reserved
inode area where it should not be allocated.
Previous fix commit d325dc6eb763 ("nilfs2: fix use-after-free bug of
struct nilfs_root"), fixed the problem that reserved inodes with inode
numbers less than NILFS_USER_INO (=11) were incorrectly reallocated due to
bitmap corruption, but since the start number of non-reserved inodes is
read from the super block and may change, in which case inode allocation
may occur from the extended reserved inode area.
If that happens, access to that inode will cause an IO error, causing the
file system to degrade to an error state.
Fix this potential issue by adding a wraparound option to the common
metadata object allocation routine and by modifying
nilfs_ifile_create_inode() to disable the option so that it only allocates
inodes with inode numbers greater than or equal to the inode number read
in "nilfs->ns_first_ino", regardless of the bitmap status of reserved
inodes.
Link: https://lkml.kernel.org/r/20240623051135.4180-4-konishi.ryusuke@gmail.com
Signed-off-by: Ryusuke Konishi <konishi.ryusuke(a)gmail.com>
Cc: Hillf Danton <hdanton(a)sina.com>
Cc: Jan Kara <jack(a)suse.cz>
Cc: Matthew Wilcox (Oracle) <willy(a)infradead.org>
Cc: <stable(a)vger.kernel.org>
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
diff --git a/fs/nilfs2/alloc.c b/fs/nilfs2/alloc.c
index 89caef7513db..ba50388ee4bf 100644
--- a/fs/nilfs2/alloc.c
+++ b/fs/nilfs2/alloc.c
@@ -377,11 +377,12 @@ void *nilfs_palloc_block_get_entry(const struct inode *inode, __u64 nr,
* @target: offset number of an entry in the group (start point)
* @bsize: size in bits
* @lock: spin lock protecting @bitmap
+ * @wrap: whether to wrap around
*/
static int nilfs_palloc_find_available_slot(unsigned char *bitmap,
unsigned long target,
unsigned int bsize,
- spinlock_t *lock)
+ spinlock_t *lock, bool wrap)
{
int pos, end = bsize;
@@ -397,6 +398,8 @@ static int nilfs_palloc_find_available_slot(unsigned char *bitmap,
end = target;
}
+ if (!wrap)
+ return -ENOSPC;
/* wrap around */
for (pos = 0; pos < end; pos++) {
@@ -495,9 +498,10 @@ int nilfs_palloc_count_max_entries(struct inode *inode, u64 nused, u64 *nmaxp)
* nilfs_palloc_prepare_alloc_entry - prepare to allocate a persistent object
* @inode: inode of metadata file using this allocator
* @req: nilfs_palloc_req structure exchanged for the allocation
+ * @wrap: whether to wrap around
*/
int nilfs_palloc_prepare_alloc_entry(struct inode *inode,
- struct nilfs_palloc_req *req)
+ struct nilfs_palloc_req *req, bool wrap)
{
struct buffer_head *desc_bh, *bitmap_bh;
struct nilfs_palloc_group_desc *desc;
@@ -516,7 +520,7 @@ int nilfs_palloc_prepare_alloc_entry(struct inode *inode,
entries_per_group = nilfs_palloc_entries_per_group(inode);
for (i = 0; i < ngroups; i += n) {
- if (group >= ngroups) {
+ if (group >= ngroups && wrap) {
/* wrap around */
group = 0;
maxgroup = nilfs_palloc_group(inode, req->pr_entry_nr,
@@ -550,7 +554,14 @@ int nilfs_palloc_prepare_alloc_entry(struct inode *inode,
bitmap_kaddr = kmap_local_page(bitmap_bh->b_page);
bitmap = bitmap_kaddr + bh_offset(bitmap_bh);
pos = nilfs_palloc_find_available_slot(
- bitmap, group_offset, entries_per_group, lock);
+ bitmap, group_offset, entries_per_group, lock,
+ wrap);
+ /*
+ * Since the search for a free slot in the second and
+ * subsequent bitmap blocks always starts from the
+ * beginning, the wrap flag only has an effect on the
+ * first search.
+ */
kunmap_local(bitmap_kaddr);
if (pos >= 0)
goto found;
diff --git a/fs/nilfs2/alloc.h b/fs/nilfs2/alloc.h
index b667e869ac07..d825a9faca6d 100644
--- a/fs/nilfs2/alloc.h
+++ b/fs/nilfs2/alloc.h
@@ -50,8 +50,8 @@ struct nilfs_palloc_req {
struct buffer_head *pr_entry_bh;
};
-int nilfs_palloc_prepare_alloc_entry(struct inode *,
- struct nilfs_palloc_req *);
+int nilfs_palloc_prepare_alloc_entry(struct inode *inode,
+ struct nilfs_palloc_req *req, bool wrap);
void nilfs_palloc_commit_alloc_entry(struct inode *,
struct nilfs_palloc_req *);
void nilfs_palloc_abort_alloc_entry(struct inode *, struct nilfs_palloc_req *);
diff --git a/fs/nilfs2/dat.c b/fs/nilfs2/dat.c
index 180fc8d36213..fc1caf63a42a 100644
--- a/fs/nilfs2/dat.c
+++ b/fs/nilfs2/dat.c
@@ -75,7 +75,7 @@ int nilfs_dat_prepare_alloc(struct inode *dat, struct nilfs_palloc_req *req)
{
int ret;
- ret = nilfs_palloc_prepare_alloc_entry(dat, req);
+ ret = nilfs_palloc_prepare_alloc_entry(dat, req, true);
if (ret < 0)
return ret;
diff --git a/fs/nilfs2/ifile.c b/fs/nilfs2/ifile.c
index 612e609158b5..1e86b9303b7c 100644
--- a/fs/nilfs2/ifile.c
+++ b/fs/nilfs2/ifile.c
@@ -56,13 +56,10 @@ int nilfs_ifile_create_inode(struct inode *ifile, ino_t *out_ino,
struct nilfs_palloc_req req;
int ret;
- req.pr_entry_nr = 0; /*
- * 0 says find free inode from beginning
- * of a group. dull code!!
- */
+ req.pr_entry_nr = NILFS_FIRST_INO(ifile->i_sb);
req.pr_entry_bh = NULL;
- ret = nilfs_palloc_prepare_alloc_entry(ifile, &req);
+ ret = nilfs_palloc_prepare_alloc_entry(ifile, &req, false);
if (!ret) {
ret = nilfs_palloc_get_entry_block(ifile, req.pr_entry_nr, 1,
&req.pr_entry_bh);
The patch below does not apply to the 6.6-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.6.y
git checkout FETCH_HEAD
git cherry-pick -x 93aef9eda1cea9e84ab2453fcceb8addad0e46f1
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024070805-enchanted-nearness-1ecc@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^..
Possible dependencies:
93aef9eda1ce ("nilfs2: fix incorrect inode allocation from reserved inodes")
af6eae646851 ("nilfs2: convert persistent object allocator to use kmap_local")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 93aef9eda1cea9e84ab2453fcceb8addad0e46f1 Mon Sep 17 00:00:00 2001
From: Ryusuke Konishi <konishi.ryusuke(a)gmail.com>
Date: Sun, 23 Jun 2024 14:11:35 +0900
Subject: [PATCH] nilfs2: fix incorrect inode allocation from reserved inodes
If the bitmap block that manages the inode allocation status is corrupted,
nilfs_ifile_create_inode() may allocate a new inode from the reserved
inode area where it should not be allocated.
Previous fix commit d325dc6eb763 ("nilfs2: fix use-after-free bug of
struct nilfs_root"), fixed the problem that reserved inodes with inode
numbers less than NILFS_USER_INO (=11) were incorrectly reallocated due to
bitmap corruption, but since the start number of non-reserved inodes is
read from the super block and may change, in which case inode allocation
may occur from the extended reserved inode area.
If that happens, access to that inode will cause an IO error, causing the
file system to degrade to an error state.
Fix this potential issue by adding a wraparound option to the common
metadata object allocation routine and by modifying
nilfs_ifile_create_inode() to disable the option so that it only allocates
inodes with inode numbers greater than or equal to the inode number read
in "nilfs->ns_first_ino", regardless of the bitmap status of reserved
inodes.
Link: https://lkml.kernel.org/r/20240623051135.4180-4-konishi.ryusuke@gmail.com
Signed-off-by: Ryusuke Konishi <konishi.ryusuke(a)gmail.com>
Cc: Hillf Danton <hdanton(a)sina.com>
Cc: Jan Kara <jack(a)suse.cz>
Cc: Matthew Wilcox (Oracle) <willy(a)infradead.org>
Cc: <stable(a)vger.kernel.org>
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
diff --git a/fs/nilfs2/alloc.c b/fs/nilfs2/alloc.c
index 89caef7513db..ba50388ee4bf 100644
--- a/fs/nilfs2/alloc.c
+++ b/fs/nilfs2/alloc.c
@@ -377,11 +377,12 @@ void *nilfs_palloc_block_get_entry(const struct inode *inode, __u64 nr,
* @target: offset number of an entry in the group (start point)
* @bsize: size in bits
* @lock: spin lock protecting @bitmap
+ * @wrap: whether to wrap around
*/
static int nilfs_palloc_find_available_slot(unsigned char *bitmap,
unsigned long target,
unsigned int bsize,
- spinlock_t *lock)
+ spinlock_t *lock, bool wrap)
{
int pos, end = bsize;
@@ -397,6 +398,8 @@ static int nilfs_palloc_find_available_slot(unsigned char *bitmap,
end = target;
}
+ if (!wrap)
+ return -ENOSPC;
/* wrap around */
for (pos = 0; pos < end; pos++) {
@@ -495,9 +498,10 @@ int nilfs_palloc_count_max_entries(struct inode *inode, u64 nused, u64 *nmaxp)
* nilfs_palloc_prepare_alloc_entry - prepare to allocate a persistent object
* @inode: inode of metadata file using this allocator
* @req: nilfs_palloc_req structure exchanged for the allocation
+ * @wrap: whether to wrap around
*/
int nilfs_palloc_prepare_alloc_entry(struct inode *inode,
- struct nilfs_palloc_req *req)
+ struct nilfs_palloc_req *req, bool wrap)
{
struct buffer_head *desc_bh, *bitmap_bh;
struct nilfs_palloc_group_desc *desc;
@@ -516,7 +520,7 @@ int nilfs_palloc_prepare_alloc_entry(struct inode *inode,
entries_per_group = nilfs_palloc_entries_per_group(inode);
for (i = 0; i < ngroups; i += n) {
- if (group >= ngroups) {
+ if (group >= ngroups && wrap) {
/* wrap around */
group = 0;
maxgroup = nilfs_palloc_group(inode, req->pr_entry_nr,
@@ -550,7 +554,14 @@ int nilfs_palloc_prepare_alloc_entry(struct inode *inode,
bitmap_kaddr = kmap_local_page(bitmap_bh->b_page);
bitmap = bitmap_kaddr + bh_offset(bitmap_bh);
pos = nilfs_palloc_find_available_slot(
- bitmap, group_offset, entries_per_group, lock);
+ bitmap, group_offset, entries_per_group, lock,
+ wrap);
+ /*
+ * Since the search for a free slot in the second and
+ * subsequent bitmap blocks always starts from the
+ * beginning, the wrap flag only has an effect on the
+ * first search.
+ */
kunmap_local(bitmap_kaddr);
if (pos >= 0)
goto found;
diff --git a/fs/nilfs2/alloc.h b/fs/nilfs2/alloc.h
index b667e869ac07..d825a9faca6d 100644
--- a/fs/nilfs2/alloc.h
+++ b/fs/nilfs2/alloc.h
@@ -50,8 +50,8 @@ struct nilfs_palloc_req {
struct buffer_head *pr_entry_bh;
};
-int nilfs_palloc_prepare_alloc_entry(struct inode *,
- struct nilfs_palloc_req *);
+int nilfs_palloc_prepare_alloc_entry(struct inode *inode,
+ struct nilfs_palloc_req *req, bool wrap);
void nilfs_palloc_commit_alloc_entry(struct inode *,
struct nilfs_palloc_req *);
void nilfs_palloc_abort_alloc_entry(struct inode *, struct nilfs_palloc_req *);
diff --git a/fs/nilfs2/dat.c b/fs/nilfs2/dat.c
index 180fc8d36213..fc1caf63a42a 100644
--- a/fs/nilfs2/dat.c
+++ b/fs/nilfs2/dat.c
@@ -75,7 +75,7 @@ int nilfs_dat_prepare_alloc(struct inode *dat, struct nilfs_palloc_req *req)
{
int ret;
- ret = nilfs_palloc_prepare_alloc_entry(dat, req);
+ ret = nilfs_palloc_prepare_alloc_entry(dat, req, true);
if (ret < 0)
return ret;
diff --git a/fs/nilfs2/ifile.c b/fs/nilfs2/ifile.c
index 612e609158b5..1e86b9303b7c 100644
--- a/fs/nilfs2/ifile.c
+++ b/fs/nilfs2/ifile.c
@@ -56,13 +56,10 @@ int nilfs_ifile_create_inode(struct inode *ifile, ino_t *out_ino,
struct nilfs_palloc_req req;
int ret;
- req.pr_entry_nr = 0; /*
- * 0 says find free inode from beginning
- * of a group. dull code!!
- */
+ req.pr_entry_nr = NILFS_FIRST_INO(ifile->i_sb);
req.pr_entry_bh = NULL;
- ret = nilfs_palloc_prepare_alloc_entry(ifile, &req);
+ ret = nilfs_palloc_prepare_alloc_entry(ifile, &req, false);
if (!ret) {
ret = nilfs_palloc_get_entry_block(ifile, req.pr_entry_nr, 1,
&req.pr_entry_bh);
The patch below does not apply to the 6.6-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.6.y
git checkout FETCH_HEAD
git cherry-pick -x 6ef8eb5125722c241fd60d7b0c872d5c2e5dd4ca
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024070154-legged-throwaway-bd6a@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^..
Possible dependencies:
6ef8eb512572 ("cpu: Fix broken cmdline "nosmp" and "maxcpus=0"")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 6ef8eb5125722c241fd60d7b0c872d5c2e5dd4ca Mon Sep 17 00:00:00 2001
From: Huacai Chen <chenhuacai(a)kernel.org>
Date: Tue, 18 Jun 2024 16:13:36 +0800
Subject: [PATCH] cpu: Fix broken cmdline "nosmp" and "maxcpus=0"
After the rework of "Parallel CPU bringup", the cmdline "nosmp" and
"maxcpus=0" parameters are not working anymore. These parameters set
setup_max_cpus to zero and that's handed to bringup_nonboot_cpus().
The code there does a decrement before checking for zero, which brings it
into the negative space and brings up all CPUs.
Add a zero check at the beginning of the function to prevent this.
[ tglx: Massaged change log ]
Fixes: 18415f33e2ac4ab382 ("cpu/hotplug: Allow "parallel" bringup up to CPUHP_BP_KICK_AP_STATE")
Fixes: 06c6796e0304234da6 ("cpu/hotplug: Fix off by one in cpuhp_bringup_mask()")
Signed-off-by: Huacai Chen <chenhuacai(a)loongson.cn>
Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de>
Cc: stable(a)vger.kernel.org
Link: https://lore.kernel.org/r/20240618081336.3996825-1-chenhuacai@loongson.cn
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 74cfdb66a9bd..3d2bf1d50a0c 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -1859,6 +1859,9 @@ static inline bool cpuhp_bringup_cpus_parallel(unsigned int ncpus) { return fals
void __init bringup_nonboot_cpus(unsigned int max_cpus)
{
+ if (!max_cpus)
+ return;
+
/* Try parallel bringup optimization if enabled */
if (cpuhp_bringup_cpus_parallel(max_cpus))
return;
On Sun, Jul 07, 2024 at 10:55:51AM -0400, Sasha Levin wrote:
> This is a note to let you know that I've just added the patch titled
>
> wifi: cfg80211: restrict NL80211_ATTR_TXQ_QUANTUM values
>
> to the 6.6-stable tree which can be found at:
> http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
>
> The filename of the patch is:
> wifi-cfg80211-restrict-nl80211_attr_txq_quantum-valu.patch
> and it can be found in the queue-6.6 subdirectory.
>
> If you, or anyone else, feels it should not be added to the stable tree,
> please let <stable(a)vger.kernel.org> know about it.
>
>
>
> commit 0014eb2dd000fba5b30a3cb883b750bd344f050d
> Author: Eric Dumazet <edumazet(a)google.com>
> Date: Sat Jun 15 16:08:00 2024 +0000
>
> wifi: cfg80211: restrict NL80211_ATTR_TXQ_QUANTUM values
>
> [ Upstream commit d1cba2ea8121e7fdbe1328cea782876b1dd80993 ]
Breaks the build, so I've dropped it now.
On Fri, Jul 05, 2024 at 03:34:04PM -0400, Sasha Levin wrote:
> This is a note to let you know that I've just added the patch titled
>
> drm/amdgpu: fix the warning about the expression (int)size - len
>
> to the 6.1-stable tree which can be found at:
> http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
>
> The filename of the patch is:
> drm-amdgpu-fix-the-warning-about-the-expression-int-.patch
> and it can be found in the queue-6.1 subdirectory.
>
> If you, or anyone else, feels it should not be added to the stable tree,
> please let <stable(a)vger.kernel.org> know about it.
>
>
>
> commit c71e1d31c7d6735e32dcfd0043970d9fadb00b82
> Author: Jesse Zhang <jesse.zhang(a)amd.com>
> Date: Thu Apr 25 15:16:40 2024 +0800
>
> drm/amdgpu: fix the warning about the expression (int)size - len
>
> [ Upstream commit ea686fef5489ef7a2450a9fdbcc732b837fb46a8 ]
>
> Converting size from size_t to int may overflow.
> v2: keep reverse xmas tree order (Christian)
>
> Signed-off-by: Jesse Zhang <jesse.zhang(a)amd.com>
> Reviewed-by: Alex Deucher <alexander.deucher(a)amd.com>
> Signed-off-by: Alex Deucher <alexander.deucher(a)amd.com>
> Signed-off-by: Sasha Levin <sashal(a)kernel.org>
Nope, this breaks the build on 6.1, which is kind of worse than fixing a
build warning :(
I'll go drop this now.
thanks,
greg k-h
From: Tvrtko Ursulin <tvrtko.ursulin(a)igalia.com>
Since balancing mode was added in
bda420b98505 ("numa balancing: migrate on fault among multiple bound nodes"),
it was possible to set this mode but it wouldn't be shown in
/proc/<pid>/numa_maps since there was no support for it in the
mpol_to_str() helper.
Furthermore, because the balancing mode sets the MPOL_F_MORON flag, it
would be displayed as 'default' due a workaround introduced a few years
earlier in
8790c71a18e5 ("mm/mempolicy.c: fix mempolicy printing in numa_maps").
To tidy this up we implement two changes:
Replace the MPOL_F_MORON check by pointer comparison against the
preferred_node_policy array. By doing this we generalise the current
special casing and replace the incorrect 'default' with the correct
'bind' for the mode.
Secondly, we add a string representation and corresponding handling for
the MPOL_F_NUMA_BALANCING flag.
With the two changes together we start showing the balancing flag when it
is set and therefore complete the fix.
Representation format chosen is to separate multiple flags with vertical
bars, following what existed long time ago in kernel 2.6.25. But as
between then and now there wasn't a way to display multiple flags, this
patch does not change the format in practice.
Some /proc/<pid>/numa_maps output examples:
555559580000 bind=balancing:0-1,3 file=...
555585800000 bind=balancing|static:0,2 file=...
555635240000 prefer=relative:0 file=
v2:
* Fully fix by introducing MPOL_F_KERNEL.
v3:
* Abandoned the MPOL_F_KERNEL approach in favour of pointer comparisons.
* Removed lookup generalisation for easier backporting.
* Replaced commas as separator with vertical bars.
* Added a few more words about the string format in the commit message.
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin(a)igalia.com>
Fixes: bda420b98505 ("numa balancing: migrate on fault among multiple bound nodes")
References: 8790c71a18e5 ("mm/mempolicy.c: fix mempolicy printing in numa_maps")
Cc: Huang Ying <ying.huang(a)intel.com>
Cc: Mel Gorman <mgorman(a)suse.de>
Cc: Peter Zijlstra <peterz(a)infradead.org>
Cc: Ingo Molnar <mingo(a)redhat.com>
Cc: Rik van Riel <riel(a)surriel.com>
Cc: Johannes Weiner <hannes(a)cmpxchg.org>
Cc: "Matthew Wilcox (Oracle)" <willy(a)infradead.org>
Cc: Dave Hansen <dave.hansen(a)intel.com>
Cc: Andi Kleen <ak(a)linux.intel.com>
Cc: Michal Hocko <mhocko(a)suse.com>
Cc: David Rientjes <rientjes(a)google.com>
Cc: <stable(a)vger.kernel.org> # v5.12+
---
mm/mempolicy.c | 18 ++++++++++++++----
1 file changed, 14 insertions(+), 4 deletions(-)
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index aec756ae5637..1bfb6c73a39c 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -3293,8 +3293,9 @@ int mpol_parse_str(char *str, struct mempolicy **mpol)
* @pol: pointer to mempolicy to be formatted
*
* Convert @pol into a string. If @buffer is too short, truncate the string.
- * Recommend a @maxlen of at least 32 for the longest mode, "interleave", the
- * longest flag, "relative", and to display at least a few node ids.
+ * Recommend a @maxlen of at least 42 for the longest mode, "weighted
+ * interleave", the longest flag, "balancing", and to display at least a few
+ * node ids.
*/
void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol)
{
@@ -3303,7 +3304,10 @@ void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol)
unsigned short mode = MPOL_DEFAULT;
unsigned short flags = 0;
- if (pol && pol != &default_policy && !(pol->flags & MPOL_F_MORON)) {
+ if (pol &&
+ pol != &default_policy &&
+ !(pol >= &preferred_node_policy[0] &&
+ pol <= &preferred_node_policy[MAX_NUMNODES - 1])) {
mode = pol->mode;
flags = pol->flags;
}
@@ -3331,12 +3335,18 @@ void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol)
p += snprintf(p, buffer + maxlen - p, "=");
/*
- * Currently, the only defined flags are mutually exclusive
+ * Static and relative are mutually exclusive.
*/
if (flags & MPOL_F_STATIC_NODES)
p += snprintf(p, buffer + maxlen - p, "static");
else if (flags & MPOL_F_RELATIVE_NODES)
p += snprintf(p, buffer + maxlen - p, "relative");
+
+ if (flags & MPOL_F_NUMA_BALANCING) {
+ if (hweight16(flags & MPOL_MODE_FLAGS) > 1)
+ p += snprintf(p, buffer + maxlen - p, "|");
+ p += snprintf(p, buffer + maxlen - p, "balancing");
+ }
}
if (!nodes_empty(nodes))
--
2.44.0