summaryrefslogtreecommitdiffstats
path: root/kernel/fs/ext4
diff options
context:
space:
mode:
authorYunhong Jiang <yunhong.jiang@linux.intel.com>2017-03-08 23:13:28 -0800
committerYunhong Jiang <yunhong.jiang@linux.intel.com>2017-03-08 23:36:15 -0800
commit52f993b8e89487ec9ee15a7fb4979e0f09a45b27 (patch)
treed65304486afe0bea4a311c783c0d72791c8c0aa2 /kernel/fs/ext4
parentc189ccac5702322ed843fe17057035b7222a59b6 (diff)
Upgrade to 4.4.50-rt62
The current kernel is based on rt kernel v4.4.6-rt14. We will upgrade it to 4.4.50-rt62. The command to achieve it is: a) Clone a git repo from git://git.kernel.org/pub/scm/linux/kernel/git/rt/linux-stable-rt.git b) Get the diff between this two changesets: git diff 640eca2901f3435e616157b11379d3223a44b391 705619beeea1b0b48219a683fd1a901a86fdaf5e where the two commits are: [yjiang5@jnakajim-build linux-stable-rt]$ git show --oneline --name-only 640eca2901f3435e616157b11379d3223a44b391 640eca2901f3 v4.4.6-rt14 localversion-rt [yjiang5@jnakajim-build linux-stable-rt]$ git show --oneline --name-only 705619beeea1b0b48219a683fd1a901a86fdaf5e 705619beeea1 Linux 4.4.50-rt62 localversion-rt c) One patch has been backported thus revert the patch before applying. filterdiff -p1 -x scripts/package/Makefile ~/tmp/v4.4.6-rt14-4.4.50-rt62.diff |patch -p1 --dry-run Upstream status: backport Change-Id: I244d57a32f6066e5a5b9915f9fbf99e7bbca6e01 Signed-off-by: Yunhong Jiang <yunhong.jiang@linux.intel.com>
Diffstat (limited to 'kernel/fs/ext4')
-rw-r--r--kernel/fs/ext4/acl.c12
-rw-r--r--kernel/fs/ext4/balloc.c3
-rw-r--r--kernel/fs/ext4/crypto_policy.c3
-rw-r--r--kernel/fs/ext4/ext4.h37
-rw-r--r--kernel/fs/ext4/ext4_jbd2.h14
-rw-r--r--kernel/fs/ext4/extents.c148
-rw-r--r--kernel/fs/ext4/file.c66
-rw-r--r--kernel/fs/ext4/ialloc.c59
-rw-r--r--kernel/fs/ext4/inline.c4
-rw-r--r--kernel/fs/ext4/inode.c170
-rw-r--r--kernel/fs/ext4/ioctl.c6
-rw-r--r--kernel/fs/ext4/mballoc.c78
-rw-r--r--kernel/fs/ext4/move_extent.c19
-rw-r--r--kernel/fs/ext4/namei.c25
-rw-r--r--kernel/fs/ext4/super.c196
-rw-r--r--kernel/fs/ext4/sysfs.c4
-rw-r--r--kernel/fs/ext4/truncate.h2
-rw-r--r--kernel/fs/ext4/xattr.c66
18 files changed, 619 insertions, 293 deletions
diff --git a/kernel/fs/ext4/acl.c b/kernel/fs/ext4/acl.c
index 69b1e7302..c3fe1e323 100644
--- a/kernel/fs/ext4/acl.c
+++ b/kernel/fs/ext4/acl.c
@@ -196,15 +196,11 @@ __ext4_set_acl(handle_t *handle, struct inode *inode, int type,
case ACL_TYPE_ACCESS:
name_index = EXT4_XATTR_INDEX_POSIX_ACL_ACCESS;
if (acl) {
- error = posix_acl_equiv_mode(acl, &inode->i_mode);
- if (error < 0)
+ error = posix_acl_update_mode(inode, &inode->i_mode, &acl);
+ if (error)
return error;
- else {
- inode->i_ctime = ext4_current_time(inode);
- ext4_mark_inode_dirty(handle, inode);
- if (error == 0)
- acl = NULL;
- }
+ inode->i_ctime = ext4_current_time(inode);
+ ext4_mark_inode_dirty(handle, inode);
}
break;
diff --git a/kernel/fs/ext4/balloc.c b/kernel/fs/ext4/balloc.c
index fe1f50fe7..f97110461 100644
--- a/kernel/fs/ext4/balloc.c
+++ b/kernel/fs/ext4/balloc.c
@@ -208,6 +208,9 @@ static int ext4_init_block_bitmap(struct super_block *sb,
memset(bh->b_data, 0, sb->s_blocksize);
bit_max = ext4_num_base_meta_clusters(sb, block_group);
+ if ((bit_max >> 3) >= bh->b_size)
+ return -EFSCORRUPTED;
+
for (bit = 0; bit < bit_max; bit++)
ext4_set_bit(bit, bh->b_data);
diff --git a/kernel/fs/ext4/crypto_policy.c b/kernel/fs/ext4/crypto_policy.c
index ad0506981..8a9feb341 100644
--- a/kernel/fs/ext4/crypto_policy.c
+++ b/kernel/fs/ext4/crypto_policy.c
@@ -102,6 +102,9 @@ static int ext4_create_encryption_context_from_policy(
int ext4_process_policy(const struct ext4_encryption_policy *policy,
struct inode *inode)
{
+ if (!inode_owner_or_capable(inode))
+ return -EACCES;
+
if (policy->version != 0)
return -EINVAL;
diff --git a/kernel/fs/ext4/ext4.h b/kernel/fs/ext4/ext4.h
index cc7ca4e87..cd5914495 100644
--- a/kernel/fs/ext4/ext4.h
+++ b/kernel/fs/ext4/ext4.h
@@ -221,6 +221,7 @@ struct ext4_io_submit {
#define EXT4_MAX_BLOCK_SIZE 65536
#define EXT4_MIN_BLOCK_LOG_SIZE 10
#define EXT4_MAX_BLOCK_LOG_SIZE 16
+#define EXT4_MAX_CLUSTER_LOG_SIZE 30
#ifdef __KERNEL__
# define EXT4_BLOCK_SIZE(s) ((s)->s_blocksize)
#else
@@ -850,6 +851,29 @@ do { \
#include "extents_status.h"
/*
+ * Lock subclasses for i_data_sem in the ext4_inode_info structure.
+ *
+ * These are needed to avoid lockdep false positives when we need to
+ * allocate blocks to the quota inode during ext4_map_blocks(), while
+ * holding i_data_sem for a normal (non-quota) inode. Since we don't
+ * do quota tracking for the quota inode, this avoids deadlock (as
+ * well as infinite recursion, since it isn't turtles all the way
+ * down...)
+ *
+ * I_DATA_SEM_NORMAL - Used for most inodes
+ * I_DATA_SEM_OTHER - Used by move_inode.c for the second normal inode
+ * where the second inode has larger inode number
+ * than the first
+ * I_DATA_SEM_QUOTA - Used for quota inodes only
+ */
+enum {
+ I_DATA_SEM_NORMAL = 0,
+ I_DATA_SEM_OTHER,
+ I_DATA_SEM_QUOTA,
+};
+
+
+/*
* fourth extended file system inode data in memory
*/
struct ext4_inode_info {
@@ -910,6 +934,15 @@ struct ext4_inode_info {
* by other means, so we have i_data_sem.
*/
struct rw_semaphore i_data_sem;
+ /*
+ * i_mmap_sem is for serializing page faults with truncate / punch hole
+ * operations. We have to make sure that new page cannot be faulted in
+ * a section of the inode that is being punched. We cannot easily use
+ * i_data_sem for this since we need protection for the whole punch
+ * operation and i_data_sem ranks below transaction start so we have
+ * to occasionally drop it.
+ */
+ struct rw_semaphore i_mmap_sem;
struct inode vfs_inode;
struct jbd2_inode *jinode;
@@ -2484,6 +2517,7 @@ extern int ext4_chunk_trans_blocks(struct inode *, int nrblocks);
extern int ext4_zero_partial_blocks(handle_t *handle, struct inode *inode,
loff_t lstart, loff_t lend);
extern int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf);
+extern int ext4_filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf);
extern qsize_t *ext4_get_reserved_space(struct inode *inode);
extern void ext4_da_update_reserve_space(struct inode *inode,
int used, int quota_claim);
@@ -2848,6 +2882,9 @@ static inline int ext4_update_inode_size(struct inode *inode, loff_t newsize)
return changed;
}
+int ext4_update_disksize_before_punch(struct inode *inode, loff_t offset,
+ loff_t len);
+
struct ext4_group_info {
unsigned long bb_state;
struct rb_root bb_free_root;
diff --git a/kernel/fs/ext4/ext4_jbd2.h b/kernel/fs/ext4/ext4_jbd2.h
index 5f5846211..f817ed58f 100644
--- a/kernel/fs/ext4/ext4_jbd2.h
+++ b/kernel/fs/ext4/ext4_jbd2.h
@@ -395,17 +395,19 @@ static inline int ext4_inode_journal_mode(struct inode *inode)
return EXT4_INODE_WRITEBACK_DATA_MODE; /* writeback */
/* We do not support data journalling with delayed allocation */
if (!S_ISREG(inode->i_mode) ||
- test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)
- return EXT4_INODE_JOURNAL_DATA_MODE; /* journal data */
- if (ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA) &&
- !test_opt(inode->i_sb, DELALLOC))
+ test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA ||
+ (ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA) &&
+ !test_opt(inode->i_sb, DELALLOC))) {
+ /* We do not support data journalling for encrypted data */
+ if (S_ISREG(inode->i_mode) && ext4_encrypted_inode(inode))
+ return EXT4_INODE_ORDERED_DATA_MODE; /* ordered */
return EXT4_INODE_JOURNAL_DATA_MODE; /* journal data */
+ }
if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA)
return EXT4_INODE_ORDERED_DATA_MODE; /* ordered */
if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)
return EXT4_INODE_WRITEBACK_DATA_MODE; /* writeback */
- else
- BUG();
+ BUG();
}
static inline int ext4_should_journal_data(struct inode *inode)
diff --git a/kernel/fs/ext4/extents.c b/kernel/fs/ext4/extents.c
index 551353b1b..9da42ace7 100644
--- a/kernel/fs/ext4/extents.c
+++ b/kernel/fs/ext4/extents.c
@@ -376,9 +376,13 @@ static int ext4_valid_extent(struct inode *inode, struct ext4_extent *ext)
ext4_fsblk_t block = ext4_ext_pblock(ext);
int len = ext4_ext_get_actual_len(ext);
ext4_lblk_t lblock = le32_to_cpu(ext->ee_block);
- ext4_lblk_t last = lblock + len - 1;
- if (len == 0 || lblock > last)
+ /*
+ * We allow neither:
+ * - zero length
+ * - overflow/wrap-around
+ */
+ if (lblock + len <= lblock)
return 0;
return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, len);
}
@@ -469,6 +473,10 @@ static int __ext4_ext_check(const char *function, unsigned int line,
error_msg = "invalid extent entries";
goto corrupted;
}
+ if (unlikely(depth > 32)) {
+ error_msg = "too large eh_depth";
+ goto corrupted;
+ }
/* Verify checksum on non-root extent tree nodes */
if (ext_depth(inode) != depth &&
!ext4_extent_block_csum_verify(inode, eh)) {
@@ -4685,10 +4693,6 @@ static int ext4_alloc_file_blocks(struct file *file, ext4_lblk_t offset,
if (len <= EXT_UNWRITTEN_MAX_LEN)
flags |= EXT4_GET_BLOCKS_NO_NORMALIZE;
- /* Wait all existing dio workers, newcomers will block on i_mutex */
- ext4_inode_block_unlocked_dio(inode);
- inode_dio_wait(inode);
-
/*
* credits to insert 1 extent into extent tree
*/
@@ -4752,8 +4756,6 @@ retry:
goto retry;
}
- ext4_inode_resume_unlocked_dio(inode);
-
return ret > 0 ? ret2 : ret;
}
@@ -4770,7 +4772,6 @@ static long ext4_zero_range(struct file *file, loff_t offset,
int partial_begin, partial_end;
loff_t start, end;
ext4_lblk_t lblk;
- struct address_space *mapping = inode->i_mapping;
unsigned int blkbits = inode->i_blkbits;
trace_ext4_zero_range(inode, offset, len, mode);
@@ -4786,17 +4787,6 @@ static long ext4_zero_range(struct file *file, loff_t offset,
}
/*
- * Write out all dirty pages to avoid race conditions
- * Then release them.
- */
- if (mapping->nrpages && mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) {
- ret = filemap_write_and_wait_range(mapping, offset,
- offset + len - 1);
- if (ret)
- return ret;
- }
-
- /*
* Round up offset. This is not fallocate, we neet to zero out
* blocks, so convert interior block aligned part of the range to
* unwritten and possibly manually zero out unaligned parts of the
@@ -4839,6 +4829,10 @@ static long ext4_zero_range(struct file *file, loff_t offset,
if (mode & FALLOC_FL_KEEP_SIZE)
flags |= EXT4_GET_BLOCKS_KEEP_SIZE;
+ /* Wait all existing dio workers, newcomers will block on i_mutex */
+ ext4_inode_block_unlocked_dio(inode);
+ inode_dio_wait(inode);
+
/* Preallocate the range including the unaligned edges */
if (partial_begin || partial_end) {
ret = ext4_alloc_file_blocks(file,
@@ -4847,7 +4841,7 @@ static long ext4_zero_range(struct file *file, loff_t offset,
round_down(offset, 1 << blkbits)) >> blkbits,
new_size, flags, mode);
if (ret)
- goto out_mutex;
+ goto out_dio;
}
@@ -4856,16 +4850,23 @@ static long ext4_zero_range(struct file *file, loff_t offset,
flags |= (EXT4_GET_BLOCKS_CONVERT_UNWRITTEN |
EXT4_EX_NOCACHE);
- /* Now release the pages and zero block aligned part of pages*/
+ /*
+ * Prevent page faults from reinstantiating pages we have
+ * released from page cache.
+ */
+ down_write(&EXT4_I(inode)->i_mmap_sem);
+ ret = ext4_update_disksize_before_punch(inode, offset, len);
+ if (ret) {
+ up_write(&EXT4_I(inode)->i_mmap_sem);
+ goto out_dio;
+ }
+ /* Now release the pages and zero block aligned part of pages */
truncate_pagecache_range(inode, start, end - 1);
inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
- /* Wait all existing dio workers, newcomers will block on i_mutex */
- ext4_inode_block_unlocked_dio(inode);
- inode_dio_wait(inode);
-
ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size,
flags, mode);
+ up_write(&EXT4_I(inode)->i_mmap_sem);
if (ret)
goto out_dio;
}
@@ -4998,8 +4999,13 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
goto out;
}
+ /* Wait all existing dio workers, newcomers will block on i_mutex */
+ ext4_inode_block_unlocked_dio(inode);
+ inode_dio_wait(inode);
+
ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size,
flags, mode);
+ ext4_inode_resume_unlocked_dio(inode);
if (ret)
goto out;
@@ -5494,21 +5500,7 @@ int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
return ret;
}
- /*
- * Need to round down offset to be aligned with page size boundary
- * for page size > block size.
- */
- ioffset = round_down(offset, PAGE_SIZE);
-
- /* Write out all dirty pages */
- ret = filemap_write_and_wait_range(inode->i_mapping, ioffset,
- LLONG_MAX);
- if (ret)
- return ret;
-
- /* Take mutex lock */
mutex_lock(&inode->i_mutex);
-
/*
* There is no need to overlap collapse range with EOF, in which case
* it is effectively a truncate operation
@@ -5524,17 +5516,43 @@ int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
goto out_mutex;
}
- truncate_pagecache(inode, ioffset);
-
/* Wait for existing dio to complete */
ext4_inode_block_unlocked_dio(inode);
inode_dio_wait(inode);
+ /*
+ * Prevent page faults from reinstantiating pages we have released from
+ * page cache.
+ */
+ down_write(&EXT4_I(inode)->i_mmap_sem);
+ /*
+ * Need to round down offset to be aligned with page size boundary
+ * for page size > block size.
+ */
+ ioffset = round_down(offset, PAGE_SIZE);
+ /*
+ * Write tail of the last page before removed range since it will get
+ * removed from the page cache below.
+ */
+ ret = filemap_write_and_wait_range(inode->i_mapping, ioffset, offset);
+ if (ret)
+ goto out_mmap;
+ /*
+ * Write data that will be shifted to preserve them when discarding
+ * page cache below. We are also protected from pages becoming dirty
+ * by i_mmap_sem.
+ */
+ ret = filemap_write_and_wait_range(inode->i_mapping, offset + len,
+ LLONG_MAX);
+ if (ret)
+ goto out_mmap;
+ truncate_pagecache(inode, ioffset);
+
credits = ext4_writepage_trans_blocks(inode);
handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits);
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
- goto out_dio;
+ goto out_mmap;
}
down_write(&EXT4_I(inode)->i_data_sem);
@@ -5573,7 +5591,8 @@ int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
out_stop:
ext4_journal_stop(handle);
-out_dio:
+out_mmap:
+ up_write(&EXT4_I(inode)->i_mmap_sem);
ext4_inode_resume_unlocked_dio(inode);
out_mutex:
mutex_unlock(&inode->i_mutex);
@@ -5627,21 +5646,7 @@ int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len)
return ret;
}
- /*
- * Need to round down to align start offset to page size boundary
- * for page size > block size.
- */
- ioffset = round_down(offset, PAGE_SIZE);
-
- /* Write out all dirty pages */
- ret = filemap_write_and_wait_range(inode->i_mapping, ioffset,
- LLONG_MAX);
- if (ret)
- return ret;
-
- /* Take mutex lock */
mutex_lock(&inode->i_mutex);
-
/* Currently just for extent based files */
if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
ret = -EOPNOTSUPP;
@@ -5660,17 +5665,32 @@ int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len)
goto out_mutex;
}
- truncate_pagecache(inode, ioffset);
-
/* Wait for existing dio to complete */
ext4_inode_block_unlocked_dio(inode);
inode_dio_wait(inode);
+ /*
+ * Prevent page faults from reinstantiating pages we have released from
+ * page cache.
+ */
+ down_write(&EXT4_I(inode)->i_mmap_sem);
+ /*
+ * Need to round down to align start offset to page size boundary
+ * for page size > block size.
+ */
+ ioffset = round_down(offset, PAGE_SIZE);
+ /* Write out all dirty pages */
+ ret = filemap_write_and_wait_range(inode->i_mapping, ioffset,
+ LLONG_MAX);
+ if (ret)
+ goto out_mmap;
+ truncate_pagecache(inode, ioffset);
+
credits = ext4_writepage_trans_blocks(inode);
handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits);
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
- goto out_dio;
+ goto out_mmap;
}
/* Expand file to avoid data loss if there is error while shifting */
@@ -5718,6 +5738,9 @@ int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len)
up_write(&EXT4_I(inode)->i_data_sem);
goto out_stop;
}
+ } else {
+ ext4_ext_drop_refs(path);
+ kfree(path);
}
ret = ext4_es_remove_extent(inode, offset_lblk,
@@ -5741,7 +5764,8 @@ int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len)
out_stop:
ext4_journal_stop(handle);
-out_dio:
+out_mmap:
+ up_write(&EXT4_I(inode)->i_mmap_sem);
ext4_inode_resume_unlocked_dio(inode);
out_mutex:
mutex_unlock(&inode->i_mutex);
diff --git a/kernel/fs/ext4/file.c b/kernel/fs/ext4/file.c
index 113837e7b..0d24ebcd7 100644
--- a/kernel/fs/ext4/file.c
+++ b/kernel/fs/ext4/file.c
@@ -209,15 +209,18 @@ static int ext4_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
{
int result;
handle_t *handle = NULL;
- struct super_block *sb = file_inode(vma->vm_file)->i_sb;
+ struct inode *inode = file_inode(vma->vm_file);
+ struct super_block *sb = inode->i_sb;
bool write = vmf->flags & FAULT_FLAG_WRITE;
if (write) {
sb_start_pagefault(sb);
file_update_time(vma->vm_file);
+ down_read(&EXT4_I(inode)->i_mmap_sem);
handle = ext4_journal_start_sb(sb, EXT4_HT_WRITE_PAGE,
EXT4_DATA_TRANS_BLOCKS(sb));
- }
+ } else
+ down_read(&EXT4_I(inode)->i_mmap_sem);
if (IS_ERR(handle))
result = VM_FAULT_SIGBUS;
@@ -228,8 +231,10 @@ static int ext4_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
if (write) {
if (!IS_ERR(handle))
ext4_journal_stop(handle);
+ up_read(&EXT4_I(inode)->i_mmap_sem);
sb_end_pagefault(sb);
- }
+ } else
+ up_read(&EXT4_I(inode)->i_mmap_sem);
return result;
}
@@ -246,10 +251,12 @@ static int ext4_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
if (write) {
sb_start_pagefault(sb);
file_update_time(vma->vm_file);
+ down_read(&EXT4_I(inode)->i_mmap_sem);
handle = ext4_journal_start_sb(sb, EXT4_HT_WRITE_PAGE,
ext4_chunk_trans_blocks(inode,
PMD_SIZE / PAGE_SIZE));
- }
+ } else
+ down_read(&EXT4_I(inode)->i_mmap_sem);
if (IS_ERR(handle))
result = VM_FAULT_SIGBUS;
@@ -260,30 +267,71 @@ static int ext4_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
if (write) {
if (!IS_ERR(handle))
ext4_journal_stop(handle);
+ up_read(&EXT4_I(inode)->i_mmap_sem);
sb_end_pagefault(sb);
- }
+ } else
+ up_read(&EXT4_I(inode)->i_mmap_sem);
return result;
}
static int ext4_dax_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
{
- return dax_mkwrite(vma, vmf, ext4_get_block_dax,
- ext4_end_io_unwritten);
+ int err;
+ struct inode *inode = file_inode(vma->vm_file);
+
+ sb_start_pagefault(inode->i_sb);
+ file_update_time(vma->vm_file);
+ down_read(&EXT4_I(inode)->i_mmap_sem);
+ err = __dax_mkwrite(vma, vmf, ext4_get_block_dax,
+ ext4_end_io_unwritten);
+ up_read(&EXT4_I(inode)->i_mmap_sem);
+ sb_end_pagefault(inode->i_sb);
+
+ return err;
+}
+
+/*
+ * Handle write fault for VM_MIXEDMAP mappings. Similarly to ext4_dax_mkwrite()
+ * handler we check for races agaist truncate. Note that since we cycle through
+ * i_mmap_sem, we are sure that also any hole punching that began before we
+ * were called is finished by now and so if it included part of the file we
+ * are working on, our pte will get unmapped and the check for pte_same() in
+ * wp_pfn_shared() fails. Thus fault gets retried and things work out as
+ * desired.
+ */
+static int ext4_dax_pfn_mkwrite(struct vm_area_struct *vma,
+ struct vm_fault *vmf)
+{
+ struct inode *inode = file_inode(vma->vm_file);
+ struct super_block *sb = inode->i_sb;
+ int ret = VM_FAULT_NOPAGE;
+ loff_t size;
+
+ sb_start_pagefault(sb);
+ file_update_time(vma->vm_file);
+ down_read(&EXT4_I(inode)->i_mmap_sem);
+ size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
+ if (vmf->pgoff >= size)
+ ret = VM_FAULT_SIGBUS;
+ up_read(&EXT4_I(inode)->i_mmap_sem);
+ sb_end_pagefault(sb);
+
+ return ret;
}
static const struct vm_operations_struct ext4_dax_vm_ops = {
.fault = ext4_dax_fault,
.pmd_fault = ext4_dax_pmd_fault,
.page_mkwrite = ext4_dax_mkwrite,
- .pfn_mkwrite = dax_pfn_mkwrite,
+ .pfn_mkwrite = ext4_dax_pfn_mkwrite,
};
#else
#define ext4_dax_vm_ops ext4_file_vm_ops
#endif
static const struct vm_operations_struct ext4_file_vm_ops = {
- .fault = filemap_fault,
+ .fault = ext4_filemap_fault,
.map_pages = filemap_map_pages,
.page_mkwrite = ext4_page_mkwrite,
};
diff --git a/kernel/fs/ext4/ialloc.c b/kernel/fs/ext4/ialloc.c
index 53f2b98a6..5388207d2 100644
--- a/kernel/fs/ext4/ialloc.c
+++ b/kernel/fs/ext4/ialloc.c
@@ -1143,25 +1143,20 @@ struct inode *ext4_orphan_get(struct super_block *sb, unsigned long ino)
unsigned long max_ino = le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count);
ext4_group_t block_group;
int bit;
- struct buffer_head *bitmap_bh;
+ struct buffer_head *bitmap_bh = NULL;
struct inode *inode = NULL;
- long err = -EIO;
+ int err = -EFSCORRUPTED;
- /* Error cases - e2fsck has already cleaned up for us */
- if (ino > max_ino) {
- ext4_warning(sb, "bad orphan ino %lu! e2fsck was run?", ino);
- err = -EFSCORRUPTED;
- goto error;
- }
+ if (ino < EXT4_FIRST_INO(sb) || ino > max_ino)
+ goto bad_orphan;
block_group = (ino - 1) / EXT4_INODES_PER_GROUP(sb);
bit = (ino - 1) % EXT4_INODES_PER_GROUP(sb);
bitmap_bh = ext4_read_inode_bitmap(sb, block_group);
if (IS_ERR(bitmap_bh)) {
- err = PTR_ERR(bitmap_bh);
- ext4_warning(sb, "inode bitmap error %ld for orphan %lu",
- ino, err);
- goto error;
+ ext4_error(sb, "inode bitmap error %ld for orphan %lu",
+ ino, PTR_ERR(bitmap_bh));
+ return (struct inode *) bitmap_bh;
}
/* Having the inode bit set should be a 100% indicator that this
@@ -1172,15 +1167,21 @@ struct inode *ext4_orphan_get(struct super_block *sb, unsigned long ino)
goto bad_orphan;
inode = ext4_iget(sb, ino);
- if (IS_ERR(inode))
- goto iget_failed;
+ if (IS_ERR(inode)) {
+ err = PTR_ERR(inode);
+ ext4_error(sb, "couldn't read orphan inode %lu (err %d)",
+ ino, err);
+ return inode;
+ }
/*
- * If the orphans has i_nlinks > 0 then it should be able to be
- * truncated, otherwise it won't be removed from the orphan list
- * during processing and an infinite loop will result.
+ * If the orphans has i_nlinks > 0 then it should be able to
+ * be truncated, otherwise it won't be removed from the orphan
+ * list during processing and an infinite loop will result.
+ * Similarly, it must not be a bad inode.
*/
- if (inode->i_nlink && !ext4_can_truncate(inode))
+ if ((inode->i_nlink && !ext4_can_truncate(inode)) ||
+ is_bad_inode(inode))
goto bad_orphan;
if (NEXT_ORPHAN(inode) > max_ino)
@@ -1188,29 +1189,25 @@ struct inode *ext4_orphan_get(struct super_block *sb, unsigned long ino)
brelse(bitmap_bh);
return inode;
-iget_failed:
- err = PTR_ERR(inode);
- inode = NULL;
bad_orphan:
- ext4_warning(sb, "bad orphan inode %lu! e2fsck was run?", ino);
- printk(KERN_WARNING "ext4_test_bit(bit=%d, block=%llu) = %d\n",
- bit, (unsigned long long)bitmap_bh->b_blocknr,
- ext4_test_bit(bit, bitmap_bh->b_data));
- printk(KERN_WARNING "inode=%p\n", inode);
+ ext4_error(sb, "bad orphan inode %lu", ino);
+ if (bitmap_bh)
+ printk(KERN_ERR "ext4_test_bit(bit=%d, block=%llu) = %d\n",
+ bit, (unsigned long long)bitmap_bh->b_blocknr,
+ ext4_test_bit(bit, bitmap_bh->b_data));
if (inode) {
- printk(KERN_WARNING "is_bad_inode(inode)=%d\n",
+ printk(KERN_ERR "is_bad_inode(inode)=%d\n",
is_bad_inode(inode));
- printk(KERN_WARNING "NEXT_ORPHAN(inode)=%u\n",
+ printk(KERN_ERR "NEXT_ORPHAN(inode)=%u\n",
NEXT_ORPHAN(inode));
- printk(KERN_WARNING "max_ino=%lu\n", max_ino);
- printk(KERN_WARNING "i_nlink=%u\n", inode->i_nlink);
+ printk(KERN_ERR "max_ino=%lu\n", max_ino);
+ printk(KERN_ERR "i_nlink=%u\n", inode->i_nlink);
/* Avoid freeing blocks if we got a bad deleted inode */
if (inode->i_nlink == 0)
inode->i_blocks = 0;
iput(inode);
}
brelse(bitmap_bh);
-error:
return ERR_PTR(err);
}
diff --git a/kernel/fs/ext4/inline.c b/kernel/fs/ext4/inline.c
index d884989cc..8968a93e2 100644
--- a/kernel/fs/ext4/inline.c
+++ b/kernel/fs/ext4/inline.c
@@ -336,8 +336,10 @@ static int ext4_update_inline_data(handle_t *handle, struct inode *inode,
len -= EXT4_MIN_INLINE_DATA_SIZE;
value = kzalloc(len, GFP_NOFS);
- if (!value)
+ if (!value) {
+ error = -ENOMEM;
goto out;
+ }
error = ext4_xattr_ibody_get(inode, i.name_index, i.name,
value, len);
diff --git a/kernel/fs/ext4/inode.c b/kernel/fs/ext4/inode.c
index 06bda0361..10690e5ba 100644
--- a/kernel/fs/ext4/inode.c
+++ b/kernel/fs/ext4/inode.c
@@ -51,25 +51,31 @@ static __u32 ext4_inode_csum(struct inode *inode, struct ext4_inode *raw,
struct ext4_inode_info *ei)
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
- __u16 csum_lo;
- __u16 csum_hi = 0;
__u32 csum;
+ __u16 dummy_csum = 0;
+ int offset = offsetof(struct ext4_inode, i_checksum_lo);
+ unsigned int csum_size = sizeof(dummy_csum);
- csum_lo = le16_to_cpu(raw->i_checksum_lo);
- raw->i_checksum_lo = 0;
- if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE &&
- EXT4_FITS_IN_INODE(raw, ei, i_checksum_hi)) {
- csum_hi = le16_to_cpu(raw->i_checksum_hi);
- raw->i_checksum_hi = 0;
- }
-
- csum = ext4_chksum(sbi, ei->i_csum_seed, (__u8 *)raw,
- EXT4_INODE_SIZE(inode->i_sb));
+ csum = ext4_chksum(sbi, ei->i_csum_seed, (__u8 *)raw, offset);
+ csum = ext4_chksum(sbi, csum, (__u8 *)&dummy_csum, csum_size);
+ offset += csum_size;
+ csum = ext4_chksum(sbi, csum, (__u8 *)raw + offset,
+ EXT4_GOOD_OLD_INODE_SIZE - offset);
- raw->i_checksum_lo = cpu_to_le16(csum_lo);
- if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE &&
- EXT4_FITS_IN_INODE(raw, ei, i_checksum_hi))
- raw->i_checksum_hi = cpu_to_le16(csum_hi);
+ if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) {
+ offset = offsetof(struct ext4_inode, i_checksum_hi);
+ csum = ext4_chksum(sbi, csum, (__u8 *)raw +
+ EXT4_GOOD_OLD_INODE_SIZE,
+ offset - EXT4_GOOD_OLD_INODE_SIZE);
+ if (EXT4_FITS_IN_INODE(raw, ei, i_checksum_hi)) {
+ csum = ext4_chksum(sbi, csum, (__u8 *)&dummy_csum,
+ csum_size);
+ offset += csum_size;
+ csum = ext4_chksum(sbi, csum, (__u8 *)raw + offset,
+ EXT4_INODE_SIZE(inode->i_sb) -
+ offset);
+ }
+ }
return csum;
}
@@ -205,9 +211,9 @@ void ext4_evict_inode(struct inode *inode)
* Note that directories do not have this problem because they
* don't use page cache.
*/
- if (ext4_should_journal_data(inode) &&
- (S_ISLNK(inode->i_mode) || S_ISREG(inode->i_mode)) &&
- inode->i_ino != EXT4_JOURNAL_INO) {
+ if (inode->i_ino != EXT4_JOURNAL_INO &&
+ ext4_should_journal_data(inode) &&
+ (S_ISLNK(inode->i_mode) || S_ISREG(inode->i_mode))) {
journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
tid_t commit_tid = EXT4_I(inode)->i_datasync_tid;
@@ -2589,13 +2595,36 @@ retry:
done = true;
}
}
- ext4_journal_stop(handle);
+ /*
+ * Caution: If the handle is synchronous,
+ * ext4_journal_stop() can wait for transaction commit
+ * to finish which may depend on writeback of pages to
+ * complete or on page lock to be released. In that
+ * case, we have to wait until after after we have
+ * submitted all the IO, released page locks we hold,
+ * and dropped io_end reference (for extent conversion
+ * to be able to complete) before stopping the handle.
+ */
+ if (!ext4_handle_valid(handle) || handle->h_sync == 0) {
+ ext4_journal_stop(handle);
+ handle = NULL;
+ }
/* Submit prepared bio */
ext4_io_submit(&mpd.io_submit);
/* Unlock pages we didn't use */
mpage_release_unused_pages(&mpd, give_up_on_write);
- /* Drop our io_end reference we got from init */
- ext4_put_io_end(mpd.io_submit.io_end);
+ /*
+ * Drop our io_end reference we got from init. We have
+ * to be careful and use deferred io_end finishing if
+ * we are still holding the transaction as we can
+ * release the last reference to io_end which may end
+ * up doing unwritten extent conversion.
+ */
+ if (handle) {
+ ext4_put_io_end_defer(mpd.io_submit.io_end);
+ ext4_journal_stop(handle);
+ } else
+ ext4_put_io_end(mpd.io_submit.io_end);
if (ret == -ENOSPC && sbi->s_journal) {
/*
@@ -3587,7 +3616,36 @@ int ext4_can_truncate(struct inode *inode)
}
/*
- * ext4_punch_hole: punches a hole in a file by releaseing the blocks
+ * We have to make sure i_disksize gets properly updated before we truncate
+ * page cache due to hole punching or zero range. Otherwise i_disksize update
+ * can get lost as it may have been postponed to submission of writeback but
+ * that will never happen after we truncate page cache.
+ */
+int ext4_update_disksize_before_punch(struct inode *inode, loff_t offset,
+ loff_t len)
+{
+ handle_t *handle;
+ loff_t size = i_size_read(inode);
+
+ WARN_ON(!mutex_is_locked(&inode->i_mutex));
+ if (offset > size || offset + len < size)
+ return 0;
+
+ if (EXT4_I(inode)->i_disksize >= size)
+ return 0;
+
+ handle = ext4_journal_start(inode, EXT4_HT_MISC, 1);
+ if (IS_ERR(handle))
+ return PTR_ERR(handle);
+ ext4_update_i_disksize(inode, size);
+ ext4_mark_inode_dirty(handle, inode);
+ ext4_journal_stop(handle);
+
+ return 0;
+}
+
+/*
+ * ext4_punch_hole: punches a hole in a file by releasing the blocks
* associated with the given offset and length
*
* @inode: File inode
@@ -3616,7 +3674,7 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
* Write out all dirty pages to avoid race conditions
* Then release them.
*/
- if (mapping->nrpages && mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) {
+ if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) {
ret = filemap_write_and_wait_range(mapping, offset,
offset + length - 1);
if (ret)
@@ -3651,17 +3709,26 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
}
+ /* Wait all existing dio workers, newcomers will block on i_mutex */
+ ext4_inode_block_unlocked_dio(inode);
+ inode_dio_wait(inode);
+
+ /*
+ * Prevent page faults from reinstantiating pages we have released from
+ * page cache.
+ */
+ down_write(&EXT4_I(inode)->i_mmap_sem);
first_block_offset = round_up(offset, sb->s_blocksize);
last_block_offset = round_down((offset + length), sb->s_blocksize) - 1;
/* Now release the pages and zero block aligned part of pages*/
- if (last_block_offset > first_block_offset)
+ if (last_block_offset > first_block_offset) {
+ ret = ext4_update_disksize_before_punch(inode, offset, length);
+ if (ret)
+ goto out_dio;
truncate_pagecache_range(inode, first_block_offset,
last_block_offset);
-
- /* Wait all existing dio workers, newcomers will block on i_mutex */
- ext4_inode_block_unlocked_dio(inode);
- inode_dio_wait(inode);
+ }
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
credits = ext4_writepage_trans_blocks(inode);
@@ -3708,16 +3775,12 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
if (IS_SYNC(inode))
ext4_handle_sync(handle);
- /* Now release the pages again to reduce race window */
- if (last_block_offset > first_block_offset)
- truncate_pagecache_range(inode, first_block_offset,
- last_block_offset);
-
inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
ext4_mark_inode_dirty(handle, inode);
out_stop:
ext4_journal_stop(handle);
out_dio:
+ up_write(&EXT4_I(inode)->i_mmap_sem);
ext4_inode_resume_unlocked_dio(inode);
out_mutex:
mutex_unlock(&inode->i_mutex);
@@ -4112,6 +4175,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
struct inode *inode;
journal_t *journal = EXT4_SB(sb)->s_journal;
long ret;
+ loff_t size;
int block;
uid_t i_uid;
gid_t i_gid;
@@ -4203,6 +4267,11 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
ei->i_file_acl |=
((__u64)le16_to_cpu(raw_inode->i_file_acl_high)) << 32;
inode->i_size = ext4_isize(raw_inode);
+ if ((size = i_size_read(inode)) < 0) {
+ EXT4_ERROR_INODE(inode, "bad i_size value: %lld", size);
+ ret = -EFSCORRUPTED;
+ goto bad_inode;
+ }
ei->i_disksize = inode->i_size;
#ifdef CONFIG_QUOTA
ei->i_reserved_quota = 0;
@@ -4486,14 +4555,14 @@ static int ext4_do_update_inode(handle_t *handle,
* Fix up interoperability with old kernels. Otherwise, old inodes get
* re-used with the upper 16 bits of the uid/gid intact
*/
- if (!ei->i_dtime) {
+ if (ei->i_dtime && list_empty(&ei->i_orphan)) {
+ raw_inode->i_uid_high = 0;
+ raw_inode->i_gid_high = 0;
+ } else {
raw_inode->i_uid_high =
cpu_to_le16(high_16_bits(i_uid));
raw_inode->i_gid_high =
cpu_to_le16(high_16_bits(i_gid));
- } else {
- raw_inode->i_uid_high = 0;
- raw_inode->i_gid_high = 0;
}
} else {
raw_inode->i_uid_low = cpu_to_le16(fs_high2lowuid(i_uid));
@@ -4851,6 +4920,7 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
} else
ext4_wait_for_tail_page_commit(inode);
}
+ down_write(&EXT4_I(inode)->i_mmap_sem);
/*
* Truncate pagecache after we've waited for commit
* in data=journal mode to make pages freeable.
@@ -4858,6 +4928,7 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
truncate_pagecache(inode, inode->i_size);
if (shrink)
ext4_truncate(inode);
+ up_write(&EXT4_I(inode)->i_mmap_sem);
}
if (!rc) {
@@ -5109,6 +5180,8 @@ int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode)
might_sleep();
trace_ext4_mark_inode_dirty(inode, _RET_IP_);
err = ext4_reserve_inode_write(handle, inode, &iloc);
+ if (err)
+ return err;
if (ext4_handle_valid(handle) &&
EXT4_I(inode)->i_extra_isize < sbi->s_want_extra_isize &&
!ext4_test_inode_state(inode, EXT4_STATE_NO_EXPAND)) {
@@ -5125,8 +5198,6 @@ int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode)
sbi->s_want_extra_isize,
iloc, handle);
if (ret) {
- ext4_set_inode_state(inode,
- EXT4_STATE_NO_EXPAND);
if (mnt_count !=
le16_to_cpu(sbi->s_es->s_mnt_count)) {
ext4_warning(inode->i_sb,
@@ -5139,9 +5210,7 @@ int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode)
}
}
}
- if (!err)
- err = ext4_mark_iloc_dirty(handle, inode, &iloc);
- return err;
+ return ext4_mark_iloc_dirty(handle, inode, &iloc);
}
/*
@@ -5306,6 +5375,8 @@ int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
sb_start_pagefault(inode->i_sb);
file_update_time(vma->vm_file);
+
+ down_read(&EXT4_I(inode)->i_mmap_sem);
/* Delalloc case is easy... */
if (test_opt(inode->i_sb, DELALLOC) &&
!ext4_should_journal_data(inode) &&
@@ -5375,6 +5446,19 @@ retry_alloc:
out_ret:
ret = block_page_mkwrite_return(ret);
out:
+ up_read(&EXT4_I(inode)->i_mmap_sem);
sb_end_pagefault(inode->i_sb);
return ret;
}
+
+int ext4_filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+ struct inode *inode = file_inode(vma->vm_file);
+ int err;
+
+ down_read(&EXT4_I(inode)->i_mmap_sem);
+ err = filemap_fault(vma, vmf);
+ up_read(&EXT4_I(inode)->i_mmap_sem);
+
+ return err;
+}
diff --git a/kernel/fs/ext4/ioctl.c b/kernel/fs/ext4/ioctl.c
index 5e872fd40..1fb12f9c9 100644
--- a/kernel/fs/ext4/ioctl.c
+++ b/kernel/fs/ext4/ioctl.c
@@ -629,7 +629,13 @@ resizefs_out:
goto encryption_policy_out;
}
+ err = mnt_want_write_file(filp);
+ if (err)
+ goto encryption_policy_out;
+
err = ext4_process_policy(&policy, inode);
+
+ mnt_drop_write_file(filp);
encryption_policy_out:
return err;
#else
diff --git a/kernel/fs/ext4/mballoc.c b/kernel/fs/ext4/mballoc.c
index 61eaf74dc..b7a3957a9 100644
--- a/kernel/fs/ext4/mballoc.c
+++ b/kernel/fs/ext4/mballoc.c
@@ -669,7 +669,7 @@ static void ext4_mb_mark_free_simple(struct super_block *sb,
ext4_grpblk_t min;
ext4_grpblk_t max;
ext4_grpblk_t chunk;
- unsigned short border;
+ unsigned int border;
BUG_ON(len > EXT4_CLUSTERS_PER_GROUP(sb));
@@ -815,7 +815,7 @@ static void mb_regenerate_buddy(struct ext4_buddy *e4b)
* for this page; do not hold this lock when calling this routine!
*/
-static int ext4_mb_init_cache(struct page *page, char *incore)
+static int ext4_mb_init_cache(struct page *page, char *incore, gfp_t gfp)
{
ext4_group_t ngroups;
int blocksize;
@@ -848,7 +848,7 @@ static int ext4_mb_init_cache(struct page *page, char *incore)
/* allocate buffer_heads to read bitmaps */
if (groups_per_page > 1) {
i = sizeof(struct buffer_head *) * groups_per_page;
- bh = kzalloc(i, GFP_NOFS);
+ bh = kzalloc(i, gfp);
if (bh == NULL) {
err = -ENOMEM;
goto out;
@@ -983,7 +983,7 @@ out:
* are on the same page e4b->bd_buddy_page is NULL and return value is 0.
*/
static int ext4_mb_get_buddy_page_lock(struct super_block *sb,
- ext4_group_t group, struct ext4_buddy *e4b)
+ ext4_group_t group, struct ext4_buddy *e4b, gfp_t gfp)
{
struct inode *inode = EXT4_SB(sb)->s_buddy_cache;
int block, pnum, poff;
@@ -1002,7 +1002,7 @@ static int ext4_mb_get_buddy_page_lock(struct super_block *sb,
block = group * 2;
pnum = block / blocks_per_page;
poff = block % blocks_per_page;
- page = find_or_create_page(inode->i_mapping, pnum, GFP_NOFS);
+ page = find_or_create_page(inode->i_mapping, pnum, gfp);
if (!page)
return -ENOMEM;
BUG_ON(page->mapping != inode->i_mapping);
@@ -1016,7 +1016,7 @@ static int ext4_mb_get_buddy_page_lock(struct super_block *sb,
block++;
pnum = block / blocks_per_page;
- page = find_or_create_page(inode->i_mapping, pnum, GFP_NOFS);
+ page = find_or_create_page(inode->i_mapping, pnum, gfp);
if (!page)
return -ENOMEM;
BUG_ON(page->mapping != inode->i_mapping);
@@ -1042,7 +1042,7 @@ static void ext4_mb_put_buddy_page_lock(struct ext4_buddy *e4b)
* calling this routine!
*/
static noinline_for_stack
-int ext4_mb_init_group(struct super_block *sb, ext4_group_t group)
+int ext4_mb_init_group(struct super_block *sb, ext4_group_t group, gfp_t gfp)
{
struct ext4_group_info *this_grp;
@@ -1062,7 +1062,7 @@ int ext4_mb_init_group(struct super_block *sb, ext4_group_t group)
* The call to ext4_mb_get_buddy_page_lock will mark the
* page accessed.
*/
- ret = ext4_mb_get_buddy_page_lock(sb, group, &e4b);
+ ret = ext4_mb_get_buddy_page_lock(sb, group, &e4b, gfp);
if (ret || !EXT4_MB_GRP_NEED_INIT(this_grp)) {
/*
* somebody initialized the group
@@ -1072,7 +1072,7 @@ int ext4_mb_init_group(struct super_block *sb, ext4_group_t group)
}
page = e4b.bd_bitmap_page;
- ret = ext4_mb_init_cache(page, NULL);
+ ret = ext4_mb_init_cache(page, NULL, gfp);
if (ret)
goto err;
if (!PageUptodate(page)) {
@@ -1091,7 +1091,7 @@ int ext4_mb_init_group(struct super_block *sb, ext4_group_t group)
}
/* init buddy cache */
page = e4b.bd_buddy_page;
- ret = ext4_mb_init_cache(page, e4b.bd_bitmap);
+ ret = ext4_mb_init_cache(page, e4b.bd_bitmap, gfp);
if (ret)
goto err;
if (!PageUptodate(page)) {
@@ -1109,8 +1109,8 @@ err:
* calling this routine!
*/
static noinline_for_stack int
-ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group,
- struct ext4_buddy *e4b)
+ext4_mb_load_buddy_gfp(struct super_block *sb, ext4_group_t group,
+ struct ext4_buddy *e4b, gfp_t gfp)
{
int blocks_per_page;
int block;
@@ -1140,7 +1140,7 @@ ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group,
* we need full data about the group
* to make a good selection
*/
- ret = ext4_mb_init_group(sb, group);
+ ret = ext4_mb_init_group(sb, group, gfp);
if (ret)
return ret;
}
@@ -1168,11 +1168,11 @@ ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group,
* wait for it to initialize.
*/
page_cache_release(page);
- page = find_or_create_page(inode->i_mapping, pnum, GFP_NOFS);
+ page = find_or_create_page(inode->i_mapping, pnum, gfp);
if (page) {
BUG_ON(page->mapping != inode->i_mapping);
if (!PageUptodate(page)) {
- ret = ext4_mb_init_cache(page, NULL);
+ ret = ext4_mb_init_cache(page, NULL, gfp);
if (ret) {
unlock_page(page);
goto err;
@@ -1204,11 +1204,12 @@ ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group,
if (page == NULL || !PageUptodate(page)) {
if (page)
page_cache_release(page);
- page = find_or_create_page(inode->i_mapping, pnum, GFP_NOFS);
+ page = find_or_create_page(inode->i_mapping, pnum, gfp);
if (page) {
BUG_ON(page->mapping != inode->i_mapping);
if (!PageUptodate(page)) {
- ret = ext4_mb_init_cache(page, e4b->bd_bitmap);
+ ret = ext4_mb_init_cache(page, e4b->bd_bitmap,
+ gfp);
if (ret) {
unlock_page(page);
goto err;
@@ -1247,6 +1248,12 @@ err:
return ret;
}
+static int ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group,
+ struct ext4_buddy *e4b)
+{
+ return ext4_mb_load_buddy_gfp(sb, group, e4b, GFP_NOFS);
+}
+
static void ext4_mb_unload_buddy(struct ext4_buddy *e4b)
{
if (e4b->bd_bitmap_page)
@@ -1259,6 +1266,7 @@ static void ext4_mb_unload_buddy(struct ext4_buddy *e4b)
static int mb_find_order_for_block(struct ext4_buddy *e4b, int block)
{
int order = 1;
+ int bb_incr = 1 << (e4b->bd_blkbits - 1);
void *bb;
BUG_ON(e4b->bd_bitmap == e4b->bd_buddy);
@@ -1271,7 +1279,8 @@ static int mb_find_order_for_block(struct ext4_buddy *e4b, int block)
/* this block is part of buddy of order 'order' */
return order;
}
- bb += 1 << (e4b->bd_blkbits - order);
+ bb += bb_incr;
+ bb_incr >>= 1;
order++;
}
return 0;
@@ -2045,7 +2054,7 @@ static int ext4_mb_good_group(struct ext4_allocation_context *ac,
/* We only do this if the grp has never been initialized */
if (unlikely(EXT4_MB_GRP_NEED_INIT(grp))) {
- int ret = ext4_mb_init_group(ac->ac_sb, group);
+ int ret = ext4_mb_init_group(ac->ac_sb, group, GFP_NOFS);
if (ret)
return ret;
}
@@ -2278,7 +2287,7 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v)
struct ext4_group_info *grinfo;
struct sg {
struct ext4_group_info info;
- ext4_grpblk_t counters[16];
+ ext4_grpblk_t counters[EXT4_MAX_BLOCK_LOG_SIZE + 2];
} sg;
group--;
@@ -2576,7 +2585,7 @@ int ext4_mb_init(struct super_block *sb)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
unsigned i, j;
- unsigned offset;
+ unsigned offset, offset_incr;
unsigned max;
int ret;
@@ -2605,11 +2614,13 @@ int ext4_mb_init(struct super_block *sb)
i = 1;
offset = 0;
+ offset_incr = 1 << (sb->s_blocksize_bits - 1);
max = sb->s_blocksize << 2;
do {
sbi->s_mb_offsets[i] = offset;
sbi->s_mb_maxs[i] = max;
- offset += 1 << (sb->s_blocksize_bits - i);
+ offset += offset_incr;
+ offset_incr = offset_incr >> 1;
max = max >> 1;
i++;
} while (i <= sb->s_blocksize_bits + 1);
@@ -2928,7 +2939,7 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
ext4_error(sb, "Allocating blocks %llu-%llu which overlap "
"fs metadata", block, block+len);
/* File system mounted not to panic on error
- * Fix the bitmap and repeat the block allocation
+ * Fix the bitmap and return EFSCORRUPTED
* We leak some of the blocks here.
*/
ext4_lock_group(sb, ac->ac_b_ex.fe_group);
@@ -2937,7 +2948,7 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
ext4_unlock_group(sb, ac->ac_b_ex.fe_group);
err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);
if (!err)
- err = -EAGAIN;
+ err = -EFSCORRUPTED;
goto out_err;
}
@@ -4502,18 +4513,7 @@ repeat:
}
if (likely(ac->ac_status == AC_STATUS_FOUND)) {
*errp = ext4_mb_mark_diskspace_used(ac, handle, reserv_clstrs);
- if (*errp == -EAGAIN) {
- /*
- * drop the reference that we took
- * in ext4_mb_use_best_found
- */
- ext4_mb_release_context(ac);
- ac->ac_b_ex.fe_group = 0;
- ac->ac_b_ex.fe_start = 0;
- ac->ac_b_ex.fe_len = 0;
- ac->ac_status = AC_STATUS_CONTINUE;
- goto repeat;
- } else if (*errp) {
+ if (*errp) {
ext4_discard_allocated_blocks(ac);
goto errout;
} else {
@@ -4815,7 +4815,9 @@ do_more:
#endif
trace_ext4_mballoc_free(sb, inode, block_group, bit, count_clusters);
- err = ext4_mb_load_buddy(sb, block_group, &e4b);
+ /* __GFP_NOFAIL: retry infinitely, ignore TIF_MEMDIE and memcg limit. */
+ err = ext4_mb_load_buddy_gfp(sb, block_group, &e4b,
+ GFP_NOFS|__GFP_NOFAIL);
if (err)
goto error_return;
@@ -5217,7 +5219,7 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
grp = ext4_get_group_info(sb, group);
/* We only do this if the grp has never been initialized */
if (unlikely(EXT4_MB_GRP_NEED_INIT(grp))) {
- ret = ext4_mb_init_group(sb, group);
+ ret = ext4_mb_init_group(sb, group, GFP_NOFS);
if (ret)
break;
}
diff --git a/kernel/fs/ext4/move_extent.c b/kernel/fs/ext4/move_extent.c
index e032a0423..7861d801b 100644
--- a/kernel/fs/ext4/move_extent.c
+++ b/kernel/fs/ext4/move_extent.c
@@ -60,10 +60,10 @@ ext4_double_down_write_data_sem(struct inode *first, struct inode *second)
{
if (first < second) {
down_write(&EXT4_I(first)->i_data_sem);
- down_write_nested(&EXT4_I(second)->i_data_sem, SINGLE_DEPTH_NESTING);
+ down_write_nested(&EXT4_I(second)->i_data_sem, I_DATA_SEM_OTHER);
} else {
down_write(&EXT4_I(second)->i_data_sem);
- down_write_nested(&EXT4_I(first)->i_data_sem, SINGLE_DEPTH_NESTING);
+ down_write_nested(&EXT4_I(first)->i_data_sem, I_DATA_SEM_OTHER);
}
}
@@ -390,6 +390,7 @@ data_copy:
*err = ext4_get_block(orig_inode, orig_blk_offset + i, bh, 0);
if (*err < 0)
break;
+ bh = bh->b_this_page;
}
if (!*err)
*err = block_commit_write(pagep[0], from, from + replaced_size);
@@ -483,6 +484,13 @@ mext_check_arguments(struct inode *orig_inode,
return -EBUSY;
}
+ if (IS_NOQUOTA(orig_inode) || IS_NOQUOTA(donor_inode)) {
+ ext4_debug("ext4 move extent: The argument files should "
+ "not be quota files [ino:orig %lu, donor %lu]\n",
+ orig_inode->i_ino, donor_inode->i_ino);
+ return -EBUSY;
+ }
+
/* Ext4 move extent supports only extent based file */
if (!(ext4_test_inode_flag(orig_inode, EXT4_INODE_EXTENTS))) {
ext4_debug("ext4 move extent: orig file is not extents "
@@ -590,6 +598,13 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 orig_blk,
return -EOPNOTSUPP;
}
+ if (ext4_encrypted_inode(orig_inode) ||
+ ext4_encrypted_inode(donor_inode)) {
+ ext4_msg(orig_inode->i_sb, KERN_ERR,
+ "Online defrag not supported for encrypted files");
+ return -EOPNOTSUPP;
+ }
+
/* Protect orig and donor inodes against a truncate */
lock_two_nondirectories(orig_inode, donor_inode);
diff --git a/kernel/fs/ext4/namei.c b/kernel/fs/ext4/namei.c
index a969ab39f..573b4cbb0 100644
--- a/kernel/fs/ext4/namei.c
+++ b/kernel/fs/ext4/namei.c
@@ -420,15 +420,14 @@ static __le32 ext4_dx_csum(struct inode *inode, struct ext4_dir_entry *dirent,
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
struct ext4_inode_info *ei = EXT4_I(inode);
__u32 csum;
- __le32 save_csum;
int size;
+ __u32 dummy_csum = 0;
+ int offset = offsetof(struct dx_tail, dt_checksum);
size = count_offset + (count * sizeof(struct dx_entry));
- save_csum = t->dt_checksum;
- t->dt_checksum = 0;
csum = ext4_chksum(sbi, ei->i_csum_seed, (__u8 *)dirent, size);
- csum = ext4_chksum(sbi, csum, (__u8 *)t, sizeof(struct dx_tail));
- t->dt_checksum = save_csum;
+ csum = ext4_chksum(sbi, csum, (__u8 *)t, offset);
+ csum = ext4_chksum(sbi, csum, (__u8 *)&dummy_csum, sizeof(dummy_csum));
return cpu_to_le32(csum);
}
@@ -2018,33 +2017,31 @@ static int make_indexed_dir(handle_t *handle, struct ext4_filename *fname,
frame->entries = entries;
frame->at = entries;
frame->bh = bh;
- bh = bh2;
retval = ext4_handle_dirty_dx_node(handle, dir, frame->bh);
if (retval)
goto out_frames;
- retval = ext4_handle_dirty_dirent_node(handle, dir, bh);
+ retval = ext4_handle_dirty_dirent_node(handle, dir, bh2);
if (retval)
goto out_frames;
- de = do_split(handle,dir, &bh, frame, &fname->hinfo);
+ de = do_split(handle,dir, &bh2, frame, &fname->hinfo);
if (IS_ERR(de)) {
retval = PTR_ERR(de);
goto out_frames;
}
- dx_release(frames);
- retval = add_dirent_to_buf(handle, fname, dir, inode, de, bh);
- brelse(bh);
- return retval;
+ retval = add_dirent_to_buf(handle, fname, dir, inode, de, bh2);
out_frames:
/*
* Even if the block split failed, we have to properly write
* out all the changes we did so far. Otherwise we can end up
* with corrupted filesystem.
*/
- ext4_mark_inode_dirty(handle, dir);
+ if (retval)
+ ext4_mark_inode_dirty(handle, dir);
dx_release(frames);
+ brelse(bh2);
return retval;
}
@@ -2809,7 +2806,7 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode)
* list entries can cause panics at unmount time.
*/
mutex_lock(&sbi->s_orphan_lock);
- list_del(&EXT4_I(inode)->i_orphan);
+ list_del_init(&EXT4_I(inode)->i_orphan);
mutex_unlock(&sbi->s_orphan_lock);
}
}
diff --git a/kernel/fs/ext4/super.c b/kernel/fs/ext4/super.c
index c9ab67da6..b405a7b74 100644
--- a/kernel/fs/ext4/super.c
+++ b/kernel/fs/ext4/super.c
@@ -958,6 +958,7 @@ static void init_once(void *foo)
INIT_LIST_HEAD(&ei->i_orphan);
init_rwsem(&ei->xattr_sem);
init_rwsem(&ei->i_data_sem);
+ init_rwsem(&ei->i_mmap_sem);
inode_init_once(&ei->vfs_inode);
}
@@ -1292,9 +1293,9 @@ static int set_qf_name(struct super_block *sb, int qtype, substring_t *args)
return -1;
}
if (ext4_has_feature_quota(sb)) {
- ext4_msg(sb, KERN_ERR, "Cannot set journaled quota options "
- "when QUOTA feature is enabled");
- return -1;
+ ext4_msg(sb, KERN_INFO, "Journaled quota options "
+ "ignored when QUOTA feature is enabled");
+ return 1;
}
qname = match_strdup(args);
if (!qname) {
@@ -1657,10 +1658,10 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token,
return -1;
}
if (ext4_has_feature_quota(sb)) {
- ext4_msg(sb, KERN_ERR,
- "Cannot set journaled quota options "
+ ext4_msg(sb, KERN_INFO,
+ "Quota format mount options ignored "
"when QUOTA feature is enabled");
- return -1;
+ return 1;
}
sbi->s_jquota_fmt = m->mount_opt;
#endif
@@ -1721,11 +1722,11 @@ static int parse_options(char *options, struct super_block *sb,
#ifdef CONFIG_QUOTA
if (ext4_has_feature_quota(sb) &&
(test_opt(sb, USRQUOTA) || test_opt(sb, GRPQUOTA))) {
- ext4_msg(sb, KERN_ERR, "Cannot set quota options when QUOTA "
- "feature is enabled");
- return 0;
- }
- if (sbi->s_qf_names[USRQUOTA] || sbi->s_qf_names[GRPQUOTA]) {
+ ext4_msg(sb, KERN_INFO, "Quota feature enabled, usrquota and grpquota "
+ "mount options ignored.");
+ clear_opt(sb, USRQUOTA);
+ clear_opt(sb, GRPQUOTA);
+ } else if (sbi->s_qf_names[USRQUOTA] || sbi->s_qf_names[GRPQUOTA]) {
if (test_opt(sb, USRQUOTA) && sbi->s_qf_names[USRQUOTA])
clear_opt(sb, USRQUOTA);
@@ -2029,23 +2030,25 @@ failed:
static __le16 ext4_group_desc_csum(struct super_block *sb, __u32 block_group,
struct ext4_group_desc *gdp)
{
- int offset;
+ int offset = offsetof(struct ext4_group_desc, bg_checksum);
__u16 crc = 0;
__le32 le_group = cpu_to_le32(block_group);
struct ext4_sb_info *sbi = EXT4_SB(sb);
if (ext4_has_metadata_csum(sbi->s_sb)) {
/* Use new metadata_csum algorithm */
- __le16 save_csum;
__u32 csum32;
+ __u16 dummy_csum = 0;
- save_csum = gdp->bg_checksum;
- gdp->bg_checksum = 0;
csum32 = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)&le_group,
sizeof(le_group));
- csum32 = ext4_chksum(sbi, csum32, (__u8 *)gdp,
- sbi->s_desc_size);
- gdp->bg_checksum = save_csum;
+ csum32 = ext4_chksum(sbi, csum32, (__u8 *)gdp, offset);
+ csum32 = ext4_chksum(sbi, csum32, (__u8 *)&dummy_csum,
+ sizeof(dummy_csum));
+ offset += sizeof(dummy_csum);
+ if (offset < sbi->s_desc_size)
+ csum32 = ext4_chksum(sbi, csum32, (__u8 *)gdp + offset,
+ sbi->s_desc_size - offset);
crc = csum32 & 0xFFFF;
goto out;
@@ -2055,8 +2058,6 @@ static __le16 ext4_group_desc_csum(struct super_block *sb, __u32 block_group,
if (!ext4_has_feature_gdt_csum(sb))
return 0;
- offset = offsetof(struct ext4_group_desc, bg_checksum);
-
crc = crc16(~0, sbi->s_es->s_uuid, sizeof(sbi->s_es->s_uuid));
crc = crc16(crc, (__u8 *)&le_group, sizeof(le_group));
crc = crc16(crc, (__u8 *)gdp, offset);
@@ -2092,6 +2093,7 @@ void ext4_group_desc_csum_set(struct super_block *sb, __u32 block_group,
/* Called at mount-time, super-block is locked */
static int ext4_check_descriptors(struct super_block *sb,
+ ext4_fsblk_t sb_block,
ext4_group_t *first_not_zeroed)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
@@ -2122,6 +2124,11 @@ static int ext4_check_descriptors(struct super_block *sb,
grp = i;
block_bitmap = ext4_block_bitmap(sb, gdp);
+ if (block_bitmap == sb_block) {
+ ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
+ "Block bitmap for group %u overlaps "
+ "superblock", i);
+ }
if (block_bitmap < first_block || block_bitmap > last_block) {
ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
"Block bitmap for group %u not in group "
@@ -2129,6 +2136,11 @@ static int ext4_check_descriptors(struct super_block *sb,
return 0;
}
inode_bitmap = ext4_inode_bitmap(sb, gdp);
+ if (inode_bitmap == sb_block) {
+ ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
+ "Inode bitmap for group %u overlaps "
+ "superblock", i);
+ }
if (inode_bitmap < first_block || inode_bitmap > last_block) {
ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
"Inode bitmap for group %u not in group "
@@ -2136,6 +2148,11 @@ static int ext4_check_descriptors(struct super_block *sb,
return 0;
}
inode_table = ext4_inode_table(sb, gdp);
+ if (inode_table == sb_block) {
+ ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
+ "Inode table for group %u overlaps "
+ "superblock", i);
+ }
if (inode_table < first_block ||
inode_table + sbi->s_itb_per_group - 1 > last_block) {
ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
@@ -2239,6 +2256,16 @@ static void ext4_orphan_cleanup(struct super_block *sb,
while (es->s_last_orphan) {
struct inode *inode;
+ /*
+ * We may have encountered an error during cleanup; if
+ * so, skip the rest.
+ */
+ if (EXT4_SB(sb)->s_mount_state & EXT4_ERROR_FS) {
+ jbd_debug(1, "Skipping orphan recovery on fs with errors.\n");
+ es->s_last_orphan = 0;
+ break;
+ }
+
inode = ext4_orphan_get(sb, le32_to_cpu(es->s_last_orphan));
if (IS_ERR(inode)) {
es->s_last_orphan = 0;
@@ -3010,10 +3037,15 @@ static int count_overhead(struct super_block *sb, ext4_group_t grp,
ext4_set_bit(s++, buf);
count++;
}
- for (j = ext4_bg_num_gdb(sb, grp); j > 0; j--) {
- ext4_set_bit(EXT4_B2C(sbi, s++), buf);
- count++;
+ j = ext4_bg_num_gdb(sb, grp);
+ if (s + j > EXT4_BLOCKS_PER_GROUP(sb)) {
+ ext4_error(sb, "Invalid number of block group "
+ "descriptor blocks: %d", j);
+ j = EXT4_BLOCKS_PER_GROUP(sb) - s;
}
+ count += j;
+ for (; j > 0; j--)
+ ext4_set_bit(EXT4_B2C(sbi, s++), buf);
}
if (!count)
return 0;
@@ -3103,7 +3135,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
char *orig_data = kstrdup(data, GFP_KERNEL);
struct buffer_head *bh;
struct ext4_super_block *es = NULL;
- struct ext4_sb_info *sbi;
+ struct ext4_sb_info *sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
ext4_fsblk_t block;
ext4_fsblk_t sb_block = get_sb_block(&data);
ext4_fsblk_t logical_sb_block;
@@ -3122,16 +3154,14 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
unsigned int journal_ioprio = DEFAULT_JOURNAL_IOPRIO;
ext4_group_t first_not_zeroed;
- sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
- if (!sbi)
- goto out_free_orig;
+ if ((data && !orig_data) || !sbi)
+ goto out_free_base;
sbi->s_blockgroup_lock =
kzalloc(sizeof(struct blockgroup_lock), GFP_KERNEL);
- if (!sbi->s_blockgroup_lock) {
- kfree(sbi);
- goto out_free_orig;
- }
+ if (!sbi->s_blockgroup_lock)
+ goto out_free_base;
+
sb->s_fs_info = sbi;
sbi->s_sb = sb;
sbi->s_inode_readahead_blks = EXT4_DEF_INODE_READAHEAD_BLKS;
@@ -3277,11 +3307,19 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
*/
sbi->s_li_wait_mult = EXT4_DEF_LI_WAIT_MULT;
- if (!parse_options((char *) sbi->s_es->s_mount_opts, sb,
- &journal_devnum, &journal_ioprio, 0)) {
- ext4_msg(sb, KERN_WARNING,
- "failed to parse options in superblock: %s",
- sbi->s_es->s_mount_opts);
+ if (sbi->s_es->s_mount_opts[0]) {
+ char *s_mount_opts = kstrndup(sbi->s_es->s_mount_opts,
+ sizeof(sbi->s_es->s_mount_opts),
+ GFP_KERNEL);
+ if (!s_mount_opts)
+ goto failed_mount;
+ if (!parse_options(s_mount_opts, sb, &journal_devnum,
+ &journal_ioprio, 0)) {
+ ext4_msg(sb, KERN_WARNING,
+ "failed to parse options in superblock: %s",
+ s_mount_opts);
+ }
+ kfree(s_mount_opts);
}
sbi->s_def_mount_opt = sbi->s_mount_opt;
if (!parse_options((char *) data, sb, &journal_devnum,
@@ -3307,6 +3345,11 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
"both data=journal and dax");
goto failed_mount;
}
+ if (ext4_has_feature_encrypt(sb)) {
+ ext4_msg(sb, KERN_WARNING,
+ "encrypted files will use data=ordered "
+ "instead of data journaling mode");
+ }
if (test_opt(sb, DELALLOC))
clear_opt(sb, DELALLOC);
} else {
@@ -3367,7 +3410,22 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
if (blocksize < EXT4_MIN_BLOCK_SIZE ||
blocksize > EXT4_MAX_BLOCK_SIZE) {
ext4_msg(sb, KERN_ERR,
- "Unsupported filesystem blocksize %d", blocksize);
+ "Unsupported filesystem blocksize %d (%d log_block_size)",
+ blocksize, le32_to_cpu(es->s_log_block_size));
+ goto failed_mount;
+ }
+ if (le32_to_cpu(es->s_log_block_size) >
+ (EXT4_MAX_BLOCK_LOG_SIZE - EXT4_MIN_BLOCK_LOG_SIZE)) {
+ ext4_msg(sb, KERN_ERR,
+ "Invalid log block size: %u",
+ le32_to_cpu(es->s_log_block_size));
+ goto failed_mount;
+ }
+
+ if (le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks) > (blocksize / 4)) {
+ ext4_msg(sb, KERN_ERR,
+ "Number of reserved GDT blocks insanely large: %d",
+ le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks));
goto failed_mount;
}
@@ -3454,12 +3512,16 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
sbi->s_blocks_per_group = le32_to_cpu(es->s_blocks_per_group);
sbi->s_inodes_per_group = le32_to_cpu(es->s_inodes_per_group);
- if (EXT4_INODE_SIZE(sb) == 0 || EXT4_INODES_PER_GROUP(sb) == 0)
- goto cantfind_ext4;
sbi->s_inodes_per_block = blocksize / EXT4_INODE_SIZE(sb);
if (sbi->s_inodes_per_block == 0)
goto cantfind_ext4;
+ if (sbi->s_inodes_per_group < sbi->s_inodes_per_block ||
+ sbi->s_inodes_per_group > blocksize * 8) {
+ ext4_msg(sb, KERN_ERR, "invalid inodes per group: %lu\n",
+ sbi->s_blocks_per_group);
+ goto failed_mount;
+ }
sbi->s_itb_per_group = sbi->s_inodes_per_group /
sbi->s_inodes_per_block;
sbi->s_desc_per_block = blocksize / EXT4_DESC_SIZE(sb);
@@ -3499,6 +3561,13 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
"block size (%d)", clustersize, blocksize);
goto failed_mount;
}
+ if (le32_to_cpu(es->s_log_cluster_size) >
+ (EXT4_MAX_CLUSTER_LOG_SIZE - EXT4_MIN_BLOCK_LOG_SIZE)) {
+ ext4_msg(sb, KERN_ERR,
+ "Invalid log cluster size: %u",
+ le32_to_cpu(es->s_log_cluster_size));
+ goto failed_mount;
+ }
sbi->s_cluster_bits = le32_to_cpu(es->s_log_cluster_size) -
le32_to_cpu(es->s_log_block_size);
sbi->s_clusters_per_group =
@@ -3535,13 +3604,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
}
sbi->s_cluster_ratio = clustersize / blocksize;
- if (sbi->s_inodes_per_group > blocksize * 8) {
- ext4_msg(sb, KERN_ERR,
- "#inodes per group too big: %lu",
- sbi->s_inodes_per_group);
- goto failed_mount;
- }
-
/* Do we have standard group size of clustersize * 8 blocks ? */
if (sbi->s_blocks_per_group == clustersize << 3)
set_opt2(sb, STD_GROUP_SIZE);
@@ -3601,6 +3663,15 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
(EXT4_MAX_BLOCK_FILE_PHYS / EXT4_BLOCKS_PER_GROUP(sb)));
db_count = (sbi->s_groups_count + EXT4_DESC_PER_BLOCK(sb) - 1) /
EXT4_DESC_PER_BLOCK(sb);
+ if (ext4_has_feature_meta_bg(sb)) {
+ if (le32_to_cpu(es->s_first_meta_bg) >= db_count) {
+ ext4_msg(sb, KERN_WARNING,
+ "first meta block group too large: %u "
+ "(group descriptor block count %u)",
+ le32_to_cpu(es->s_first_meta_bg), db_count);
+ goto failed_mount;
+ }
+ }
sbi->s_group_desc = ext4_kvmalloc(db_count *
sizeof(struct buffer_head *),
GFP_KERNEL);
@@ -3622,7 +3693,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
goto failed_mount2;
}
}
- if (!ext4_check_descriptors(sb, &first_not_zeroed)) {
+ if (!ext4_check_descriptors(sb, logical_sb_block, &first_not_zeroed)) {
ext4_msg(sb, KERN_ERR, "group descriptors corrupted!");
ret = -EFSCORRUPTED;
goto failed_mount2;
@@ -3945,7 +4016,9 @@ no_journal:
if (___ratelimit(&ext4_mount_msg_ratelimit, "EXT4-fs mount"))
ext4_msg(sb, KERN_INFO, "mounted filesystem with%s. "
- "Opts: %s%s%s", descr, sbi->s_es->s_mount_opts,
+ "Opts: %.*s%s%s", descr,
+ (int) sizeof(sbi->s_es->s_mount_opts),
+ sbi->s_es->s_mount_opts,
*sbi->s_es->s_mount_opts ? "; " : "", orig_data);
if (es->s_error_count)
@@ -4015,8 +4088,8 @@ failed_mount:
out_fail:
sb->s_fs_info = NULL;
kfree(sbi->s_blockgroup_lock);
+out_free_base:
kfree(sbi);
-out_free_orig:
kfree(orig_data);
return err ? err : ret;
}
@@ -4936,6 +5009,20 @@ static int ext4_quota_on_mount(struct super_block *sb, int type)
EXT4_SB(sb)->s_jquota_fmt, type);
}
+static void lockdep_set_quota_inode(struct inode *inode, int subclass)
+{
+ struct ext4_inode_info *ei = EXT4_I(inode);
+
+ /* The first argument of lockdep_set_subclass has to be
+ * *exactly* the same as the argument to init_rwsem() --- in
+ * this case, in init_once() --- or lockdep gets unhappy
+ * because the name of the lock is set using the
+ * stringification of the argument to init_rwsem().
+ */
+ (void) ei; /* shut up clang warning if !CONFIG_LOCKDEP */
+ lockdep_set_subclass(&ei->i_data_sem, subclass);
+}
+
/*
* Standard function to be called on quota_on
*/
@@ -4975,8 +5062,12 @@ static int ext4_quota_on(struct super_block *sb, int type, int format_id,
if (err)
return err;
}
-
- return dquot_quota_on(sb, type, format_id, path);
+ lockdep_set_quota_inode(path->dentry->d_inode, I_DATA_SEM_QUOTA);
+ err = dquot_quota_on(sb, type, format_id, path);
+ if (err)
+ lockdep_set_quota_inode(path->dentry->d_inode,
+ I_DATA_SEM_NORMAL);
+ return err;
}
static int ext4_quota_enable(struct super_block *sb, int type, int format_id,
@@ -5002,8 +5093,11 @@ static int ext4_quota_enable(struct super_block *sb, int type, int format_id,
/* Don't account quota for quota files to avoid recursion */
qf_inode->i_flags |= S_NOQUOTA;
+ lockdep_set_quota_inode(qf_inode, I_DATA_SEM_QUOTA);
err = dquot_enable(qf_inode, type, format_id, flags);
iput(qf_inode);
+ if (err)
+ lockdep_set_quota_inode(qf_inode, I_DATA_SEM_NORMAL);
return err;
}
diff --git a/kernel/fs/ext4/sysfs.c b/kernel/fs/ext4/sysfs.c
index 1420a3c61..5d09ea585 100644
--- a/kernel/fs/ext4/sysfs.c
+++ b/kernel/fs/ext4/sysfs.c
@@ -223,14 +223,18 @@ static struct attribute *ext4_attrs[] = {
EXT4_ATTR_FEATURE(lazy_itable_init);
EXT4_ATTR_FEATURE(batched_discard);
EXT4_ATTR_FEATURE(meta_bg_resize);
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
EXT4_ATTR_FEATURE(encryption);
+#endif
EXT4_ATTR_FEATURE(metadata_csum_seed);
static struct attribute *ext4_feat_attrs[] = {
ATTR_LIST(lazy_itable_init),
ATTR_LIST(batched_discard),
ATTR_LIST(meta_bg_resize),
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
ATTR_LIST(encryption),
+#endif
ATTR_LIST(metadata_csum_seed),
NULL,
};
diff --git a/kernel/fs/ext4/truncate.h b/kernel/fs/ext4/truncate.h
index 011ba6670..c70d06a38 100644
--- a/kernel/fs/ext4/truncate.h
+++ b/kernel/fs/ext4/truncate.h
@@ -10,8 +10,10 @@
*/
static inline void ext4_truncate_failed_write(struct inode *inode)
{
+ down_write(&EXT4_I(inode)->i_mmap_sem);
truncate_inode_pages(inode->i_mapping, inode->i_size);
ext4_truncate(inode);
+ up_write(&EXT4_I(inode)->i_mmap_sem);
}
/*
diff --git a/kernel/fs/ext4/xattr.c b/kernel/fs/ext4/xattr.c
index 6b6b3e751..263002f03 100644
--- a/kernel/fs/ext4/xattr.c
+++ b/kernel/fs/ext4/xattr.c
@@ -123,17 +123,18 @@ static __le32 ext4_xattr_block_csum(struct inode *inode,
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
__u32 csum;
- __le32 save_csum;
__le64 dsk_block_nr = cpu_to_le64(block_nr);
+ __u32 dummy_csum = 0;
+ int offset = offsetof(struct ext4_xattr_header, h_checksum);
- save_csum = hdr->h_checksum;
- hdr->h_checksum = 0;
csum = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)&dsk_block_nr,
sizeof(dsk_block_nr));
- csum = ext4_chksum(sbi, csum, (__u8 *)hdr,
- EXT4_BLOCK_SIZE(inode->i_sb));
+ csum = ext4_chksum(sbi, csum, (__u8 *)hdr, offset);
+ csum = ext4_chksum(sbi, csum, (__u8 *)&dummy_csum, sizeof(dummy_csum));
+ offset += sizeof(dummy_csum);
+ csum = ext4_chksum(sbi, csum, (__u8 *)hdr + offset,
+ EXT4_BLOCK_SIZE(inode->i_sb) - offset);
- hdr->h_checksum = save_csum;
return cpu_to_le32(csum);
}
@@ -1264,15 +1265,19 @@ int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize,
size_t min_offs, free;
int total_ino;
void *base, *start, *end;
- int extra_isize = 0, error = 0, tried_min_extra_isize = 0;
+ int error = 0, tried_min_extra_isize = 0;
int s_min_extra_isize = le16_to_cpu(EXT4_SB(inode->i_sb)->s_es->s_min_extra_isize);
+ int isize_diff; /* How much do we need to grow i_extra_isize */
down_write(&EXT4_I(inode)->xattr_sem);
+ /*
+ * Set EXT4_STATE_NO_EXPAND to avoid recursion when marking inode dirty
+ */
+ ext4_set_inode_state(inode, EXT4_STATE_NO_EXPAND);
retry:
- if (EXT4_I(inode)->i_extra_isize >= new_extra_isize) {
- up_write(&EXT4_I(inode)->xattr_sem);
- return 0;
- }
+ isize_diff = new_extra_isize - EXT4_I(inode)->i_extra_isize;
+ if (EXT4_I(inode)->i_extra_isize >= new_extra_isize)
+ goto out;
header = IHDR(inode, raw_inode);
entry = IFIRST(header);
@@ -1289,7 +1294,7 @@ retry:
total_ino = sizeof(struct ext4_xattr_ibody_header);
free = ext4_xattr_free_space(last, &min_offs, base, &total_ino);
- if (free >= new_extra_isize) {
+ if (free >= isize_diff) {
entry = IFIRST(header);
ext4_xattr_shift_entries(entry, EXT4_I(inode)->i_extra_isize
- new_extra_isize, (void *)raw_inode +
@@ -1297,8 +1302,7 @@ retry:
(void *)header, total_ino,
inode->i_sb->s_blocksize);
EXT4_I(inode)->i_extra_isize = new_extra_isize;
- error = 0;
- goto cleanup;
+ goto out;
}
/*
@@ -1321,7 +1325,7 @@ retry:
end = bh->b_data + bh->b_size;
min_offs = end - base;
free = ext4_xattr_free_space(first, &min_offs, base, NULL);
- if (free < new_extra_isize) {
+ if (free < isize_diff) {
if (!tried_min_extra_isize && s_min_extra_isize) {
tried_min_extra_isize++;
new_extra_isize = s_min_extra_isize;
@@ -1335,7 +1339,7 @@ retry:
free = inode->i_sb->s_blocksize;
}
- while (new_extra_isize > 0) {
+ while (isize_diff > 0) {
size_t offs, size, entry_size;
struct ext4_xattr_entry *small_entry = NULL;
struct ext4_xattr_info i = {
@@ -1366,7 +1370,7 @@ retry:
EXT4_XATTR_SIZE(le32_to_cpu(last->e_value_size)) +
EXT4_XATTR_LEN(last->e_name_len);
if (total_size <= free && total_size < min_total_size) {
- if (total_size < new_extra_isize) {
+ if (total_size < isize_diff) {
small_entry = last;
} else {
entry = last;
@@ -1421,22 +1425,22 @@ retry:
error = ext4_xattr_ibody_set(handle, inode, &i, is);
if (error)
goto cleanup;
+ total_ino -= entry_size;
entry = IFIRST(header);
- if (entry_size + EXT4_XATTR_SIZE(size) >= new_extra_isize)
- shift_bytes = new_extra_isize;
+ if (entry_size + EXT4_XATTR_SIZE(size) >= isize_diff)
+ shift_bytes = isize_diff;
else
- shift_bytes = entry_size + size;
+ shift_bytes = entry_size + EXT4_XATTR_SIZE(size);
/* Adjust the offsets and shift the remaining entries ahead */
- ext4_xattr_shift_entries(entry, EXT4_I(inode)->i_extra_isize -
- shift_bytes, (void *)raw_inode +
- EXT4_GOOD_OLD_INODE_SIZE + extra_isize + shift_bytes,
- (void *)header, total_ino - entry_size,
- inode->i_sb->s_blocksize);
+ ext4_xattr_shift_entries(entry, -shift_bytes,
+ (void *)raw_inode + EXT4_GOOD_OLD_INODE_SIZE +
+ EXT4_I(inode)->i_extra_isize + shift_bytes,
+ (void *)header, total_ino, inode->i_sb->s_blocksize);
- extra_isize += shift_bytes;
- new_extra_isize -= shift_bytes;
- EXT4_I(inode)->i_extra_isize = extra_isize;
+ isize_diff -= shift_bytes;
+ EXT4_I(inode)->i_extra_isize += shift_bytes;
+ header = IHDR(inode, raw_inode);
i.name = b_entry_name;
i.value = buffer;
@@ -1458,6 +1462,8 @@ retry:
kfree(bs);
}
brelse(bh);
+out:
+ ext4_clear_inode_state(inode, EXT4_STATE_NO_EXPAND);
up_write(&EXT4_I(inode)->xattr_sem);
return 0;
@@ -1469,6 +1475,10 @@ cleanup:
kfree(is);
kfree(bs);
brelse(bh);
+ /*
+ * We deliberately leave EXT4_STATE_NO_EXPAND set here since inode
+ * size expansion failed.
+ */
up_write(&EXT4_I(inode)->xattr_sem);
return error;
}