The first 8 patches are unchanged from the series posted a week ago and
cleans up how we use the backing_dev_info structure in preparation for
fixing the life time rules for it. The most important change is to
split the unrelated nommu mmap flags from it, but it also remove a
backing_dev_info pointer from the address_space (and thus the inode)
and cleans up various other minor bits.
The remaining patches sort out the issues around bdi_unlink and now
let the bdi life until it's embedding structure is freed, which must
be equal or longer than the superblock using the bdi for writeback,
and thus gets rid of the whole mess around reassining inodes to new
bdis.
Changes since V1:
- various minor documentation updates based on Feedback from Tejun
hugetlbfs, kernfs and dlmfs can simply use noop_backing_dev_info instead
of creating a local duplicate.
Signed-off-by: Christoph Hellwig <[email protected]>
Acked-by: Tejun Heo <[email protected]>
---
fs/hugetlbfs/inode.c | 14 +-------------
fs/kernfs/inode.c | 14 +-------------
fs/kernfs/kernfs-internal.h | 1 -
fs/kernfs/mount.c | 1 -
fs/ocfs2/dlmfs/dlmfs.c | 16 ++--------------
5 files changed, 4 insertions(+), 42 deletions(-)
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 5eba47f..de7c95c 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -62,12 +62,6 @@ static inline struct hugetlbfs_inode_info *HUGETLBFS_I(struct inode *inode)
return container_of(inode, struct hugetlbfs_inode_info, vfs_inode);
}
-static struct backing_dev_info hugetlbfs_backing_dev_info = {
- .name = "hugetlbfs",
- .ra_pages = 0, /* No readahead */
- .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK,
-};
-
int sysctl_hugetlb_shm_group;
enum {
@@ -498,7 +492,7 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb,
lockdep_set_class(&inode->i_mapping->i_mmap_rwsem,
&hugetlbfs_i_mmap_rwsem_key);
inode->i_mapping->a_ops = &hugetlbfs_aops;
- inode->i_mapping->backing_dev_info =&hugetlbfs_backing_dev_info;
+ inode->i_mapping->backing_dev_info = &noop_backing_dev_info;
inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
inode->i_mapping->private_data = resv_map;
info = HUGETLBFS_I(inode);
@@ -1032,10 +1026,6 @@ static int __init init_hugetlbfs_fs(void)
return -ENOTSUPP;
}
- error = bdi_init(&hugetlbfs_backing_dev_info);
- if (error)
- return error;
-
error = -ENOMEM;
hugetlbfs_inode_cachep = kmem_cache_create("hugetlbfs_inode_cache",
sizeof(struct hugetlbfs_inode_info),
@@ -1071,7 +1061,6 @@ static int __init init_hugetlbfs_fs(void)
out:
kmem_cache_destroy(hugetlbfs_inode_cachep);
out2:
- bdi_destroy(&hugetlbfs_backing_dev_info);
return error;
}
@@ -1091,7 +1080,6 @@ static void __exit exit_hugetlbfs_fs(void)
for_each_hstate(h)
kern_unmount(hugetlbfs_vfsmount[i++]);
unregister_filesystem(&hugetlbfs_fs_type);
- bdi_destroy(&hugetlbfs_backing_dev_info);
}
module_init(init_hugetlbfs_fs)
diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c
index 9852176..06f0688 100644
--- a/fs/kernfs/inode.c
+++ b/fs/kernfs/inode.c
@@ -24,12 +24,6 @@ static const struct address_space_operations kernfs_aops = {
.write_end = simple_write_end,
};
-static struct backing_dev_info kernfs_bdi = {
- .name = "kernfs",
- .ra_pages = 0, /* No readahead */
- .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK,
-};
-
static const struct inode_operations kernfs_iops = {
.permission = kernfs_iop_permission,
.setattr = kernfs_iop_setattr,
@@ -40,12 +34,6 @@ static const struct inode_operations kernfs_iops = {
.listxattr = kernfs_iop_listxattr,
};
-void __init kernfs_inode_init(void)
-{
- if (bdi_init(&kernfs_bdi))
- panic("failed to init kernfs_bdi");
-}
-
static struct kernfs_iattrs *kernfs_iattrs(struct kernfs_node *kn)
{
static DEFINE_MUTEX(iattr_mutex);
@@ -298,7 +286,7 @@ static void kernfs_init_inode(struct kernfs_node *kn, struct inode *inode)
kernfs_get(kn);
inode->i_private = kn;
inode->i_mapping->a_ops = &kernfs_aops;
- inode->i_mapping->backing_dev_info = &kernfs_bdi;
+ inode->i_mapping->backing_dev_info = &noop_backing_dev_info;
inode->i_op = &kernfs_iops;
set_default_inode_attr(inode, kn->mode);
diff --git a/fs/kernfs/kernfs-internal.h b/fs/kernfs/kernfs-internal.h
index dc84a3e..af9fa74 100644
--- a/fs/kernfs/kernfs-internal.h
+++ b/fs/kernfs/kernfs-internal.h
@@ -88,7 +88,6 @@ int kernfs_iop_removexattr(struct dentry *dentry, const char *name);
ssize_t kernfs_iop_getxattr(struct dentry *dentry, const char *name, void *buf,
size_t size);
ssize_t kernfs_iop_listxattr(struct dentry *dentry, char *buf, size_t size);
-void kernfs_inode_init(void);
/*
* dir.c
diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c
index f973ae9..8eaf417 100644
--- a/fs/kernfs/mount.c
+++ b/fs/kernfs/mount.c
@@ -246,5 +246,4 @@ void __init kernfs_init(void)
kernfs_node_cache = kmem_cache_create("kernfs_node_cache",
sizeof(struct kernfs_node),
0, SLAB_PANIC, NULL);
- kernfs_inode_init();
}
diff --git a/fs/ocfs2/dlmfs/dlmfs.c b/fs/ocfs2/dlmfs/dlmfs.c
index 57c40e3..6000d30 100644
--- a/fs/ocfs2/dlmfs/dlmfs.c
+++ b/fs/ocfs2/dlmfs/dlmfs.c
@@ -390,12 +390,6 @@ clear_fields:
ip->ip_conn = NULL;
}
-static struct backing_dev_info dlmfs_backing_dev_info = {
- .name = "ocfs2-dlmfs",
- .ra_pages = 0, /* No readahead */
- .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK,
-};
-
static struct inode *dlmfs_get_root_inode(struct super_block *sb)
{
struct inode *inode = new_inode(sb);
@@ -404,7 +398,7 @@ static struct inode *dlmfs_get_root_inode(struct super_block *sb)
if (inode) {
inode->i_ino = get_next_ino();
inode_init_owner(inode, NULL, mode);
- inode->i_mapping->backing_dev_info = &dlmfs_backing_dev_info;
+ inode->i_mapping->backing_dev_info = &noop_backing_dev_info;
inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
inc_nlink(inode);
@@ -428,7 +422,7 @@ static struct inode *dlmfs_get_inode(struct inode *parent,
inode->i_ino = get_next_ino();
inode_init_owner(inode, parent, mode);
- inode->i_mapping->backing_dev_info = &dlmfs_backing_dev_info;
+ inode->i_mapping->backing_dev_info = &noop_backing_dev_info;
inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
ip = DLMFS_I(inode);
@@ -643,10 +637,6 @@ static int __init init_dlmfs_fs(void)
int status;
int cleanup_inode = 0, cleanup_worker = 0;
- status = bdi_init(&dlmfs_backing_dev_info);
- if (status)
- return status;
-
dlmfs_inode_cache = kmem_cache_create("dlmfs_inode_cache",
sizeof(struct dlmfs_inode_private),
0, (SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT|
@@ -673,7 +663,6 @@ bail:
kmem_cache_destroy(dlmfs_inode_cache);
if (cleanup_worker)
destroy_workqueue(user_dlm_worker);
- bdi_destroy(&dlmfs_backing_dev_info);
} else
printk("OCFS2 User DLM kernel interface loaded\n");
return status;
@@ -693,7 +682,6 @@ static void __exit exit_dlmfs_fs(void)
rcu_barrier();
kmem_cache_destroy(dlmfs_inode_cache);
- bdi_destroy(&dlmfs_backing_dev_info);
}
MODULE_AUTHOR("Oracle");
--
1.9.1
On Wed 14-01-15 10:42:30, Christoph Hellwig wrote:
> hugetlbfs, kernfs and dlmfs can simply use noop_backing_dev_info instead
> of creating a local duplicate.
Looks good.
Reviewed-by: Jan Kara <[email protected]>
Honza
>
> Signed-off-by: Christoph Hellwig <[email protected]>
> Acked-by: Tejun Heo <[email protected]>
> ---
> fs/hugetlbfs/inode.c | 14 +-------------
> fs/kernfs/inode.c | 14 +-------------
> fs/kernfs/kernfs-internal.h | 1 -
> fs/kernfs/mount.c | 1 -
> fs/ocfs2/dlmfs/dlmfs.c | 16 ++--------------
> 5 files changed, 4 insertions(+), 42 deletions(-)
>
> diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
> index 5eba47f..de7c95c 100644
> --- a/fs/hugetlbfs/inode.c
> +++ b/fs/hugetlbfs/inode.c
> @@ -62,12 +62,6 @@ static inline struct hugetlbfs_inode_info *HUGETLBFS_I(struct inode *inode)
> return container_of(inode, struct hugetlbfs_inode_info, vfs_inode);
> }
>
> -static struct backing_dev_info hugetlbfs_backing_dev_info = {
> - .name = "hugetlbfs",
> - .ra_pages = 0, /* No readahead */
> - .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK,
> -};
> -
> int sysctl_hugetlb_shm_group;
>
> enum {
> @@ -498,7 +492,7 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb,
> lockdep_set_class(&inode->i_mapping->i_mmap_rwsem,
> &hugetlbfs_i_mmap_rwsem_key);
> inode->i_mapping->a_ops = &hugetlbfs_aops;
> - inode->i_mapping->backing_dev_info =&hugetlbfs_backing_dev_info;
> + inode->i_mapping->backing_dev_info = &noop_backing_dev_info;
> inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
> inode->i_mapping->private_data = resv_map;
> info = HUGETLBFS_I(inode);
> @@ -1032,10 +1026,6 @@ static int __init init_hugetlbfs_fs(void)
> return -ENOTSUPP;
> }
>
> - error = bdi_init(&hugetlbfs_backing_dev_info);
> - if (error)
> - return error;
> -
> error = -ENOMEM;
> hugetlbfs_inode_cachep = kmem_cache_create("hugetlbfs_inode_cache",
> sizeof(struct hugetlbfs_inode_info),
> @@ -1071,7 +1061,6 @@ static int __init init_hugetlbfs_fs(void)
> out:
> kmem_cache_destroy(hugetlbfs_inode_cachep);
> out2:
> - bdi_destroy(&hugetlbfs_backing_dev_info);
> return error;
> }
>
> @@ -1091,7 +1080,6 @@ static void __exit exit_hugetlbfs_fs(void)
> for_each_hstate(h)
> kern_unmount(hugetlbfs_vfsmount[i++]);
> unregister_filesystem(&hugetlbfs_fs_type);
> - bdi_destroy(&hugetlbfs_backing_dev_info);
> }
>
> module_init(init_hugetlbfs_fs)
> diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c
> index 9852176..06f0688 100644
> --- a/fs/kernfs/inode.c
> +++ b/fs/kernfs/inode.c
> @@ -24,12 +24,6 @@ static const struct address_space_operations kernfs_aops = {
> .write_end = simple_write_end,
> };
>
> -static struct backing_dev_info kernfs_bdi = {
> - .name = "kernfs",
> - .ra_pages = 0, /* No readahead */
> - .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK,
> -};
> -
> static const struct inode_operations kernfs_iops = {
> .permission = kernfs_iop_permission,
> .setattr = kernfs_iop_setattr,
> @@ -40,12 +34,6 @@ static const struct inode_operations kernfs_iops = {
> .listxattr = kernfs_iop_listxattr,
> };
>
> -void __init kernfs_inode_init(void)
> -{
> - if (bdi_init(&kernfs_bdi))
> - panic("failed to init kernfs_bdi");
> -}
> -
> static struct kernfs_iattrs *kernfs_iattrs(struct kernfs_node *kn)
> {
> static DEFINE_MUTEX(iattr_mutex);
> @@ -298,7 +286,7 @@ static void kernfs_init_inode(struct kernfs_node *kn, struct inode *inode)
> kernfs_get(kn);
> inode->i_private = kn;
> inode->i_mapping->a_ops = &kernfs_aops;
> - inode->i_mapping->backing_dev_info = &kernfs_bdi;
> + inode->i_mapping->backing_dev_info = &noop_backing_dev_info;
> inode->i_op = &kernfs_iops;
>
> set_default_inode_attr(inode, kn->mode);
> diff --git a/fs/kernfs/kernfs-internal.h b/fs/kernfs/kernfs-internal.h
> index dc84a3e..af9fa74 100644
> --- a/fs/kernfs/kernfs-internal.h
> +++ b/fs/kernfs/kernfs-internal.h
> @@ -88,7 +88,6 @@ int kernfs_iop_removexattr(struct dentry *dentry, const char *name);
> ssize_t kernfs_iop_getxattr(struct dentry *dentry, const char *name, void *buf,
> size_t size);
> ssize_t kernfs_iop_listxattr(struct dentry *dentry, char *buf, size_t size);
> -void kernfs_inode_init(void);
>
> /*
> * dir.c
> diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c
> index f973ae9..8eaf417 100644
> --- a/fs/kernfs/mount.c
> +++ b/fs/kernfs/mount.c
> @@ -246,5 +246,4 @@ void __init kernfs_init(void)
> kernfs_node_cache = kmem_cache_create("kernfs_node_cache",
> sizeof(struct kernfs_node),
> 0, SLAB_PANIC, NULL);
> - kernfs_inode_init();
> }
> diff --git a/fs/ocfs2/dlmfs/dlmfs.c b/fs/ocfs2/dlmfs/dlmfs.c
> index 57c40e3..6000d30 100644
> --- a/fs/ocfs2/dlmfs/dlmfs.c
> +++ b/fs/ocfs2/dlmfs/dlmfs.c
> @@ -390,12 +390,6 @@ clear_fields:
> ip->ip_conn = NULL;
> }
>
> -static struct backing_dev_info dlmfs_backing_dev_info = {
> - .name = "ocfs2-dlmfs",
> - .ra_pages = 0, /* No readahead */
> - .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK,
> -};
> -
> static struct inode *dlmfs_get_root_inode(struct super_block *sb)
> {
> struct inode *inode = new_inode(sb);
> @@ -404,7 +398,7 @@ static struct inode *dlmfs_get_root_inode(struct super_block *sb)
> if (inode) {
> inode->i_ino = get_next_ino();
> inode_init_owner(inode, NULL, mode);
> - inode->i_mapping->backing_dev_info = &dlmfs_backing_dev_info;
> + inode->i_mapping->backing_dev_info = &noop_backing_dev_info;
> inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
> inc_nlink(inode);
>
> @@ -428,7 +422,7 @@ static struct inode *dlmfs_get_inode(struct inode *parent,
>
> inode->i_ino = get_next_ino();
> inode_init_owner(inode, parent, mode);
> - inode->i_mapping->backing_dev_info = &dlmfs_backing_dev_info;
> + inode->i_mapping->backing_dev_info = &noop_backing_dev_info;
> inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
>
> ip = DLMFS_I(inode);
> @@ -643,10 +637,6 @@ static int __init init_dlmfs_fs(void)
> int status;
> int cleanup_inode = 0, cleanup_worker = 0;
>
> - status = bdi_init(&dlmfs_backing_dev_info);
> - if (status)
> - return status;
> -
> dlmfs_inode_cache = kmem_cache_create("dlmfs_inode_cache",
> sizeof(struct dlmfs_inode_private),
> 0, (SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT|
> @@ -673,7 +663,6 @@ bail:
> kmem_cache_destroy(dlmfs_inode_cache);
> if (cleanup_worker)
> destroy_workqueue(user_dlm_worker);
> - bdi_destroy(&dlmfs_backing_dev_info);
> } else
> printk("OCFS2 User DLM kernel interface loaded\n");
> return status;
> @@ -693,7 +682,6 @@ static void __exit exit_dlmfs_fs(void)
> rcu_barrier();
> kmem_cache_destroy(dlmfs_inode_cache);
>
> - bdi_destroy(&dlmfs_backing_dev_info);
> }
>
> MODULE_AUTHOR("Oracle");
> --
> 1.9.1
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
> the body of a message to [email protected]
> More majordomo info at http://vger.kernel.org/majordomo-info.html
--
Jan Kara <[email protected]>
SUSE Labs, CR
This bdi flag isn't too useful - we can determine that a vma is backed by
either swap or shmem trivially in the caller.
This also allows removing the backing_dev_info instaces for swap and shmem
in favor of noop_backing_dev_info.
Signed-off-by: Christoph Hellwig <[email protected]>
Reviewed-by: Tejun Heo <[email protected]>
---
include/linux/backing-dev.h | 13 -------------
mm/madvise.c | 17 ++++++++++-------
mm/shmem.c | 25 +++++++------------------
mm/swap.c | 2 --
mm/swap_state.c | 7 +------
5 files changed, 18 insertions(+), 46 deletions(-)
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 5da6012..e936cea 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -238,8 +238,6 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio);
* BDI_CAP_WRITE_MAP: Can be mapped for writing
* BDI_CAP_EXEC_MAP: Can be mapped for execution
*
- * BDI_CAP_SWAP_BACKED: Count shmem/tmpfs objects as swap-backed.
- *
* BDI_CAP_STRICTLIMIT: Keep number of dirty pages below bdi threshold.
*/
#define BDI_CAP_NO_ACCT_DIRTY 0x00000001
@@ -250,7 +248,6 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio);
#define BDI_CAP_WRITE_MAP 0x00000020
#define BDI_CAP_EXEC_MAP 0x00000040
#define BDI_CAP_NO_ACCT_WB 0x00000080
-#define BDI_CAP_SWAP_BACKED 0x00000100
#define BDI_CAP_STABLE_WRITES 0x00000200
#define BDI_CAP_STRICTLIMIT 0x00000400
@@ -329,11 +326,6 @@ static inline bool bdi_cap_account_writeback(struct backing_dev_info *bdi)
BDI_CAP_NO_WRITEBACK));
}
-static inline bool bdi_cap_swap_backed(struct backing_dev_info *bdi)
-{
- return bdi->capabilities & BDI_CAP_SWAP_BACKED;
-}
-
static inline bool mapping_cap_writeback_dirty(struct address_space *mapping)
{
return bdi_cap_writeback_dirty(mapping->backing_dev_info);
@@ -344,11 +336,6 @@ static inline bool mapping_cap_account_dirty(struct address_space *mapping)
return bdi_cap_account_dirty(mapping->backing_dev_info);
}
-static inline bool mapping_cap_swap_backed(struct address_space *mapping)
-{
- return bdi_cap_swap_backed(mapping->backing_dev_info);
-}
-
static inline int bdi_sched_wait(void *word)
{
schedule();
diff --git a/mm/madvise.c b/mm/madvise.c
index a271adc..1383a89 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -222,19 +222,22 @@ static long madvise_willneed(struct vm_area_struct *vma,
struct file *file = vma->vm_file;
#ifdef CONFIG_SWAP
- if (!file || mapping_cap_swap_backed(file->f_mapping)) {
+ if (!file) {
*prev = vma;
- if (!file)
- force_swapin_readahead(vma, start, end);
- else
- force_shm_swapin_readahead(vma, start, end,
- file->f_mapping);
+ force_swapin_readahead(vma, start, end);
return 0;
}
-#endif
+ if (shmem_mapping(file->f_mapping)) {
+ *prev = vma;
+ force_shm_swapin_readahead(vma, start, end,
+ file->f_mapping);
+ return 0;
+ }
+#else
if (!file)
return -EBADF;
+#endif
if (file->f_mapping->a_ops->get_xip_mem) {
/* no bad return value, but ignore advice */
diff --git a/mm/shmem.c b/mm/shmem.c
index 73ba1df..1b77eaf 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -191,11 +191,6 @@ static const struct inode_operations shmem_dir_inode_operations;
static const struct inode_operations shmem_special_inode_operations;
static const struct vm_operations_struct shmem_vm_ops;
-static struct backing_dev_info shmem_backing_dev_info __read_mostly = {
- .ra_pages = 0, /* No readahead */
- .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK | BDI_CAP_SWAP_BACKED,
-};
-
static LIST_HEAD(shmem_swaplist);
static DEFINE_MUTEX(shmem_swaplist_mutex);
@@ -765,11 +760,11 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc)
goto redirty;
/*
- * shmem_backing_dev_info's capabilities prevent regular writeback or
- * sync from ever calling shmem_writepage; but a stacking filesystem
- * might use ->writepage of its underlying filesystem, in which case
- * tmpfs should write out to swap only in response to memory pressure,
- * and not for the writeback threads or sync.
+ * Our capabilities prevent regular writeback or sync from ever calling
+ * shmem_writepage; but a stacking filesystem might use ->writepage of
+ * its underlying filesystem, in which case tmpfs should write out to
+ * swap only in response to memory pressure, and not for the writeback
+ * threads or sync.
*/
if (!wbc->for_reclaim) {
WARN_ON_ONCE(1); /* Still happens? Tell us about it! */
@@ -1415,7 +1410,7 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode
inode->i_ino = get_next_ino();
inode_init_owner(inode, dir, mode);
inode->i_blocks = 0;
- inode->i_mapping->backing_dev_info = &shmem_backing_dev_info;
+ inode->i_mapping->backing_dev_info = &noop_backing_dev_info;
inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
inode->i_generation = get_seconds();
info = SHMEM_I(inode);
@@ -1461,7 +1456,7 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode
bool shmem_mapping(struct address_space *mapping)
{
- return mapping->backing_dev_info == &shmem_backing_dev_info;
+ return mapping->host->i_sb->s_op == &shmem_ops;
}
#ifdef CONFIG_TMPFS
@@ -3226,10 +3221,6 @@ int __init shmem_init(void)
if (shmem_inode_cachep)
return 0;
- error = bdi_init(&shmem_backing_dev_info);
- if (error)
- goto out4;
-
error = shmem_init_inodecache();
if (error)
goto out3;
@@ -3253,8 +3244,6 @@ out1:
out2:
shmem_destroy_inodecache();
out3:
- bdi_destroy(&shmem_backing_dev_info);
-out4:
shm_mnt = ERR_PTR(error);
return error;
}
diff --git a/mm/swap.c b/mm/swap.c
index 8a12b33..4e0109a 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -1138,8 +1138,6 @@ void __init swap_setup(void)
#ifdef CONFIG_SWAP
int i;
- if (bdi_init(swapper_spaces[0].backing_dev_info))
- panic("Failed to init swap bdi");
for (i = 0; i < MAX_SWAPFILES; i++) {
spin_lock_init(&swapper_spaces[i].tree_lock);
INIT_LIST_HEAD(&swapper_spaces[i].i_mmap_nonlinear);
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 9711342..1c137b6 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -32,17 +32,12 @@ static const struct address_space_operations swap_aops = {
#endif
};
-static struct backing_dev_info swap_backing_dev_info = {
- .name = "swap",
- .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK | BDI_CAP_SWAP_BACKED,
-};
-
struct address_space swapper_spaces[MAX_SWAPFILES] = {
[0 ... MAX_SWAPFILES - 1] = {
.page_tree = RADIX_TREE_INIT(GFP_ATOMIC|__GFP_NOWARN),
.i_mmap_writable = ATOMIC_INIT(0),
.a_ops = &swap_aops,
- .backing_dev_info = &swap_backing_dev_info,
+ .backing_dev_info = &noop_backing_dev_info,
}
};
--
1.9.1
On Wed 14-01-15 10:42:31, Christoph Hellwig wrote:
> This bdi flag isn't too useful - we can determine that a vma is backed by
> either swap or shmem trivially in the caller.
>
> This also allows removing the backing_dev_info instaces for swap and shmem
> in favor of noop_backing_dev_info.
>
> Signed-off-by: Christoph Hellwig <[email protected]>
> Reviewed-by: Tejun Heo <[email protected]>
Looks good to me. You can add:
Reviewed-by: Jan Kara <[email protected]>
Honza
> ---
> include/linux/backing-dev.h | 13 -------------
> mm/madvise.c | 17 ++++++++++-------
> mm/shmem.c | 25 +++++++------------------
> mm/swap.c | 2 --
> mm/swap_state.c | 7 +------
> 5 files changed, 18 insertions(+), 46 deletions(-)
>
> diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
> index 5da6012..e936cea 100644
> --- a/include/linux/backing-dev.h
> +++ b/include/linux/backing-dev.h
> @@ -238,8 +238,6 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio);
> * BDI_CAP_WRITE_MAP: Can be mapped for writing
> * BDI_CAP_EXEC_MAP: Can be mapped for execution
> *
> - * BDI_CAP_SWAP_BACKED: Count shmem/tmpfs objects as swap-backed.
> - *
> * BDI_CAP_STRICTLIMIT: Keep number of dirty pages below bdi threshold.
> */
> #define BDI_CAP_NO_ACCT_DIRTY 0x00000001
> @@ -250,7 +248,6 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio);
> #define BDI_CAP_WRITE_MAP 0x00000020
> #define BDI_CAP_EXEC_MAP 0x00000040
> #define BDI_CAP_NO_ACCT_WB 0x00000080
> -#define BDI_CAP_SWAP_BACKED 0x00000100
> #define BDI_CAP_STABLE_WRITES 0x00000200
> #define BDI_CAP_STRICTLIMIT 0x00000400
>
> @@ -329,11 +326,6 @@ static inline bool bdi_cap_account_writeback(struct backing_dev_info *bdi)
> BDI_CAP_NO_WRITEBACK));
> }
>
> -static inline bool bdi_cap_swap_backed(struct backing_dev_info *bdi)
> -{
> - return bdi->capabilities & BDI_CAP_SWAP_BACKED;
> -}
> -
> static inline bool mapping_cap_writeback_dirty(struct address_space *mapping)
> {
> return bdi_cap_writeback_dirty(mapping->backing_dev_info);
> @@ -344,11 +336,6 @@ static inline bool mapping_cap_account_dirty(struct address_space *mapping)
> return bdi_cap_account_dirty(mapping->backing_dev_info);
> }
>
> -static inline bool mapping_cap_swap_backed(struct address_space *mapping)
> -{
> - return bdi_cap_swap_backed(mapping->backing_dev_info);
> -}
> -
> static inline int bdi_sched_wait(void *word)
> {
> schedule();
> diff --git a/mm/madvise.c b/mm/madvise.c
> index a271adc..1383a89 100644
> --- a/mm/madvise.c
> +++ b/mm/madvise.c
> @@ -222,19 +222,22 @@ static long madvise_willneed(struct vm_area_struct *vma,
> struct file *file = vma->vm_file;
>
> #ifdef CONFIG_SWAP
> - if (!file || mapping_cap_swap_backed(file->f_mapping)) {
> + if (!file) {
> *prev = vma;
> - if (!file)
> - force_swapin_readahead(vma, start, end);
> - else
> - force_shm_swapin_readahead(vma, start, end,
> - file->f_mapping);
> + force_swapin_readahead(vma, start, end);
> return 0;
> }
> -#endif
>
> + if (shmem_mapping(file->f_mapping)) {
> + *prev = vma;
> + force_shm_swapin_readahead(vma, start, end,
> + file->f_mapping);
> + return 0;
> + }
> +#else
> if (!file)
> return -EBADF;
> +#endif
>
> if (file->f_mapping->a_ops->get_xip_mem) {
> /* no bad return value, but ignore advice */
> diff --git a/mm/shmem.c b/mm/shmem.c
> index 73ba1df..1b77eaf 100644
> --- a/mm/shmem.c
> +++ b/mm/shmem.c
> @@ -191,11 +191,6 @@ static const struct inode_operations shmem_dir_inode_operations;
> static const struct inode_operations shmem_special_inode_operations;
> static const struct vm_operations_struct shmem_vm_ops;
>
> -static struct backing_dev_info shmem_backing_dev_info __read_mostly = {
> - .ra_pages = 0, /* No readahead */
> - .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK | BDI_CAP_SWAP_BACKED,
> -};
> -
> static LIST_HEAD(shmem_swaplist);
> static DEFINE_MUTEX(shmem_swaplist_mutex);
>
> @@ -765,11 +760,11 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc)
> goto redirty;
>
> /*
> - * shmem_backing_dev_info's capabilities prevent regular writeback or
> - * sync from ever calling shmem_writepage; but a stacking filesystem
> - * might use ->writepage of its underlying filesystem, in which case
> - * tmpfs should write out to swap only in response to memory pressure,
> - * and not for the writeback threads or sync.
> + * Our capabilities prevent regular writeback or sync from ever calling
> + * shmem_writepage; but a stacking filesystem might use ->writepage of
> + * its underlying filesystem, in which case tmpfs should write out to
> + * swap only in response to memory pressure, and not for the writeback
> + * threads or sync.
> */
> if (!wbc->for_reclaim) {
> WARN_ON_ONCE(1); /* Still happens? Tell us about it! */
> @@ -1415,7 +1410,7 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode
> inode->i_ino = get_next_ino();
> inode_init_owner(inode, dir, mode);
> inode->i_blocks = 0;
> - inode->i_mapping->backing_dev_info = &shmem_backing_dev_info;
> + inode->i_mapping->backing_dev_info = &noop_backing_dev_info;
> inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
> inode->i_generation = get_seconds();
> info = SHMEM_I(inode);
> @@ -1461,7 +1456,7 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode
>
> bool shmem_mapping(struct address_space *mapping)
> {
> - return mapping->backing_dev_info == &shmem_backing_dev_info;
> + return mapping->host->i_sb->s_op == &shmem_ops;
> }
>
> #ifdef CONFIG_TMPFS
> @@ -3226,10 +3221,6 @@ int __init shmem_init(void)
> if (shmem_inode_cachep)
> return 0;
>
> - error = bdi_init(&shmem_backing_dev_info);
> - if (error)
> - goto out4;
> -
> error = shmem_init_inodecache();
> if (error)
> goto out3;
> @@ -3253,8 +3244,6 @@ out1:
> out2:
> shmem_destroy_inodecache();
> out3:
> - bdi_destroy(&shmem_backing_dev_info);
> -out4:
> shm_mnt = ERR_PTR(error);
> return error;
> }
> diff --git a/mm/swap.c b/mm/swap.c
> index 8a12b33..4e0109a 100644
> --- a/mm/swap.c
> +++ b/mm/swap.c
> @@ -1138,8 +1138,6 @@ void __init swap_setup(void)
> #ifdef CONFIG_SWAP
> int i;
>
> - if (bdi_init(swapper_spaces[0].backing_dev_info))
> - panic("Failed to init swap bdi");
> for (i = 0; i < MAX_SWAPFILES; i++) {
> spin_lock_init(&swapper_spaces[i].tree_lock);
> INIT_LIST_HEAD(&swapper_spaces[i].i_mmap_nonlinear);
> diff --git a/mm/swap_state.c b/mm/swap_state.c
> index 9711342..1c137b6 100644
> --- a/mm/swap_state.c
> +++ b/mm/swap_state.c
> @@ -32,17 +32,12 @@ static const struct address_space_operations swap_aops = {
> #endif
> };
>
> -static struct backing_dev_info swap_backing_dev_info = {
> - .name = "swap",
> - .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK | BDI_CAP_SWAP_BACKED,
> -};
> -
> struct address_space swapper_spaces[MAX_SWAPFILES] = {
> [0 ... MAX_SWAPFILES - 1] = {
> .page_tree = RADIX_TREE_INIT(GFP_ATOMIC|__GFP_NOWARN),
> .i_mmap_writable = ATOMIC_INIT(0),
> .a_ops = &swap_aops,
> - .backing_dev_info = &swap_backing_dev_info,
> + .backing_dev_info = &noop_backing_dev_info,
> }
> };
>
> --
> 1.9.1
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
> the body of a message to [email protected]
> More majordomo info at http://vger.kernel.org/majordomo-info.html
--
Jan Kara <[email protected]>
SUSE Labs, CR
Since "BDI: Provide backing device capability information [try #3]" the
backing_dev_info structure also provides flags for the kind of mmap
operation available in a nommu environment, which is entirely unrelated
to it's original purpose.
Introduce a new nommu-only file operation to provide this information to
the nommu mmap code instead. Splitting this from the backing_dev_info
structure allows to remove lots of backing_dev_info instance that aren't
otherwise needed, and entirely gets rid of the concept of providing a
backing_dev_info for a character device. It also removes the need for
the mtd_inodefs filesystem.
Signed-off-by: Christoph Hellwig <[email protected]>
Reviewed-by: Tejun Heo <[email protected]>
---
Documentation/nommu-mmap.txt | 8 +--
block/blk-core.c | 2 +-
drivers/char/mem.c | 64 ++++++++++----------
drivers/mtd/mtdchar.c | 72 ++++------------------
drivers/mtd/mtdconcat.c | 10 ----
drivers/mtd/mtdcore.c | 80 +++++++------------------
drivers/mtd/mtdpart.c | 1 -
drivers/staging/lustre/lustre/llite/llite_lib.c | 2 +-
fs/9p/v9fs.c | 2 +-
fs/afs/volume.c | 2 +-
fs/aio.c | 14 +----
fs/btrfs/disk-io.c | 3 +-
fs/char_dev.c | 24 --------
fs/cifs/connect.c | 2 +-
fs/coda/inode.c | 2 +-
fs/configfs/configfs_internal.h | 2 -
fs/configfs/inode.c | 18 +-----
fs/configfs/mount.c | 11 +---
fs/ecryptfs/main.c | 2 +-
fs/exofs/super.c | 2 +-
fs/ncpfs/inode.c | 2 +-
fs/ramfs/file-nommu.c | 7 +++
fs/ramfs/inode.c | 22 +------
fs/romfs/mmap-nommu.c | 10 ++++
fs/ubifs/super.c | 2 +-
include/linux/backing-dev.h | 33 ++--------
include/linux/cdev.h | 2 -
include/linux/fs.h | 23 +++++++
include/linux/mtd/mtd.h | 2 +
mm/backing-dev.c | 7 +--
mm/nommu.c | 69 ++++++++++-----------
security/security.c | 13 ++--
32 files changed, 169 insertions(+), 346 deletions(-)
diff --git a/Documentation/nommu-mmap.txt b/Documentation/nommu-mmap.txt
index 8e1ddec..ae57b9e 100644
--- a/Documentation/nommu-mmap.txt
+++ b/Documentation/nommu-mmap.txt
@@ -43,12 +43,12 @@ and it's also much more restricted in the latter case:
even if this was created by another process.
- If possible, the file mapping will be directly on the backing device
- if the backing device has the BDI_CAP_MAP_DIRECT capability and
+ if the backing device has the NOMMU_MAP_DIRECT capability and
appropriate mapping protection capabilities. Ramfs, romfs, cramfs
and mtd might all permit this.
- If the backing device device can't or won't permit direct sharing,
- but does have the BDI_CAP_MAP_COPY capability, then a copy of the
+ but does have the NOMMU_MAP_COPY capability, then a copy of the
appropriate bit of the file will be read into a contiguous bit of
memory and any extraneous space beyond the EOF will be cleared
@@ -220,7 +220,7 @@ directly (can't be copied).
The file->f_op->mmap() operation will be called to actually inaugurate the
mapping. It can be rejected at that point. Returning the ENOSYS error will
-cause the mapping to be copied instead if BDI_CAP_MAP_COPY is specified.
+cause the mapping to be copied instead if NOMMU_MAP_COPY is specified.
The vm_ops->close() routine will be invoked when the last mapping on a chardev
is removed. An existing mapping will be shared, partially or not, if possible
@@ -232,7 +232,7 @@ want to handle it, despite the fact it's got an operation. For instance, it
might try directing the call to a secondary driver which turns out not to
implement it. Such is the case for the framebuffer driver which attempts to
direct the call to the device-specific driver. Under such circumstances, the
-mapping request will be rejected if BDI_CAP_MAP_COPY is not specified, and a
+mapping request will be rejected if NOMMU_MAP_COPY is not specified, and a
copy mapped otherwise.
IMPORTANT NOTE:
diff --git a/block/blk-core.c b/block/blk-core.c
index 30f6153..56bc2b8 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -588,7 +588,7 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
q->backing_dev_info.ra_pages =
(VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE;
q->backing_dev_info.state = 0;
- q->backing_dev_info.capabilities = BDI_CAP_MAP_COPY;
+ q->backing_dev_info.capabilities = 0;
q->backing_dev_info.name = "block";
q->node = node_id;
diff --git a/drivers/char/mem.c b/drivers/char/mem.c
index 4c58333..9a6b637 100644
--- a/drivers/char/mem.c
+++ b/drivers/char/mem.c
@@ -287,13 +287,24 @@ static unsigned long get_unmapped_area_mem(struct file *file,
return pgoff << PAGE_SHIFT;
}
+/* permit direct mmap, for read, write or exec */
+static unsigned memory_mmap_capabilities(struct file *file)
+{
+ return NOMMU_MAP_DIRECT |
+ NOMMU_MAP_READ | NOMMU_MAP_WRITE | NOMMU_MAP_EXEC;
+}
+
+static unsigned zero_mmap_capabilities(struct file *file)
+{
+ return NOMMU_MAP_COPY;
+}
+
/* can't do an in-place private mapping if there's no MMU */
static inline int private_mapping_ok(struct vm_area_struct *vma)
{
return vma->vm_flags & VM_MAYSHARE;
}
#else
-#define get_unmapped_area_mem NULL
static inline int private_mapping_ok(struct vm_area_struct *vma)
{
@@ -721,7 +732,10 @@ static const struct file_operations mem_fops = {
.write = write_mem,
.mmap = mmap_mem,
.open = open_mem,
+#ifndef CONFIG_MMU
.get_unmapped_area = get_unmapped_area_mem,
+ .mmap_capabilities = memory_mmap_capabilities,
+#endif
};
#ifdef CONFIG_DEVKMEM
@@ -731,7 +745,10 @@ static const struct file_operations kmem_fops = {
.write = write_kmem,
.mmap = mmap_kmem,
.open = open_kmem,
+#ifndef CONFIG_MMU
.get_unmapped_area = get_unmapped_area_mem,
+ .mmap_capabilities = memory_mmap_capabilities,
+#endif
};
#endif
@@ -760,16 +777,9 @@ static const struct file_operations zero_fops = {
.read_iter = read_iter_zero,
.aio_write = aio_write_zero,
.mmap = mmap_zero,
-};
-
-/*
- * capabilities for /dev/zero
- * - permits private mappings, "copies" are taken of the source of zeros
- * - no writeback happens
- */
-static struct backing_dev_info zero_bdi = {
- .name = "char/mem",
- .capabilities = BDI_CAP_MAP_COPY | BDI_CAP_NO_ACCT_AND_WRITEBACK,
+#ifndef CONFIG_MMU
+ .mmap_capabilities = zero_mmap_capabilities,
+#endif
};
static const struct file_operations full_fops = {
@@ -783,22 +793,22 @@ static const struct memdev {
const char *name;
umode_t mode;
const struct file_operations *fops;
- struct backing_dev_info *dev_info;
+ fmode_t fmode;
} devlist[] = {
- [1] = { "mem", 0, &mem_fops, &directly_mappable_cdev_bdi },
+ [1] = { "mem", 0, &mem_fops, FMODE_UNSIGNED_OFFSET },
#ifdef CONFIG_DEVKMEM
- [2] = { "kmem", 0, &kmem_fops, &directly_mappable_cdev_bdi },
+ [2] = { "kmem", 0, &kmem_fops, FMODE_UNSIGNED_OFFSET },
#endif
- [3] = { "null", 0666, &null_fops, NULL },
+ [3] = { "null", 0666, &null_fops, 0 },
#ifdef CONFIG_DEVPORT
- [4] = { "port", 0, &port_fops, NULL },
+ [4] = { "port", 0, &port_fops, 0 },
#endif
- [5] = { "zero", 0666, &zero_fops, &zero_bdi },
- [7] = { "full", 0666, &full_fops, NULL },
- [8] = { "random", 0666, &random_fops, NULL },
- [9] = { "urandom", 0666, &urandom_fops, NULL },
+ [5] = { "zero", 0666, &zero_fops, 0 },
+ [7] = { "full", 0666, &full_fops, 0 },
+ [8] = { "random", 0666, &random_fops, 0 },
+ [9] = { "urandom", 0666, &urandom_fops, 0 },
#ifdef CONFIG_PRINTK
- [11] = { "kmsg", 0644, &kmsg_fops, NULL },
+ [11] = { "kmsg", 0644, &kmsg_fops, 0 },
#endif
};
@@ -816,12 +826,7 @@ static int memory_open(struct inode *inode, struct file *filp)
return -ENXIO;
filp->f_op = dev->fops;
- if (dev->dev_info)
- filp->f_mapping->backing_dev_info = dev->dev_info;
-
- /* Is /dev/mem or /dev/kmem ? */
- if (dev->dev_info == &directly_mappable_cdev_bdi)
- filp->f_mode |= FMODE_UNSIGNED_OFFSET;
+ filp->f_mode |= dev->fmode;
if (dev->fops->open)
return dev->fops->open(inode, filp);
@@ -846,11 +851,6 @@ static struct class *mem_class;
static int __init chr_dev_init(void)
{
int minor;
- int err;
-
- err = bdi_init(&zero_bdi);
- if (err)
- return err;
if (register_chrdev(MEM_MAJOR, "mem", &memory_fops))
printk("unable to get major %d for memory devs\n", MEM_MAJOR);
diff --git a/drivers/mtd/mtdchar.c b/drivers/mtd/mtdchar.c
index 5356395..55fa27e 100644
--- a/drivers/mtd/mtdchar.c
+++ b/drivers/mtd/mtdchar.c
@@ -49,7 +49,6 @@ static DEFINE_MUTEX(mtd_mutex);
*/
struct mtd_file_info {
struct mtd_info *mtd;
- struct inode *ino;
enum mtd_file_modes mode;
};
@@ -59,10 +58,6 @@ static loff_t mtdchar_lseek(struct file *file, loff_t offset, int orig)
return fixed_size_llseek(file, offset, orig, mfi->mtd->size);
}
-static int count;
-static struct vfsmount *mnt;
-static struct file_system_type mtd_inodefs_type;
-
static int mtdchar_open(struct inode *inode, struct file *file)
{
int minor = iminor(inode);
@@ -70,7 +65,6 @@ static int mtdchar_open(struct inode *inode, struct file *file)
int ret = 0;
struct mtd_info *mtd;
struct mtd_file_info *mfi;
- struct inode *mtd_ino;
pr_debug("MTD_open\n");
@@ -78,10 +72,6 @@ static int mtdchar_open(struct inode *inode, struct file *file)
if ((file->f_mode & FMODE_WRITE) && (minor & 1))
return -EACCES;
- ret = simple_pin_fs(&mtd_inodefs_type, &mnt, &count);
- if (ret)
- return ret;
-
mutex_lock(&mtd_mutex);
mtd = get_mtd_device(NULL, devnum);
@@ -95,43 +85,26 @@ static int mtdchar_open(struct inode *inode, struct file *file)
goto out1;
}
- mtd_ino = iget_locked(mnt->mnt_sb, devnum);
- if (!mtd_ino) {
- ret = -ENOMEM;
- goto out1;
- }
- if (mtd_ino->i_state & I_NEW) {
- mtd_ino->i_private = mtd;
- mtd_ino->i_mode = S_IFCHR;
- mtd_ino->i_data.backing_dev_info = mtd->backing_dev_info;
- unlock_new_inode(mtd_ino);
- }
- file->f_mapping = mtd_ino->i_mapping;
-
/* You can't open it RW if it's not a writeable device */
if ((file->f_mode & FMODE_WRITE) && !(mtd->flags & MTD_WRITEABLE)) {
ret = -EACCES;
- goto out2;
+ goto out1;
}
mfi = kzalloc(sizeof(*mfi), GFP_KERNEL);
if (!mfi) {
ret = -ENOMEM;
- goto out2;
+ goto out1;
}
- mfi->ino = mtd_ino;
mfi->mtd = mtd;
file->private_data = mfi;
mutex_unlock(&mtd_mutex);
return 0;
-out2:
- iput(mtd_ino);
out1:
put_mtd_device(mtd);
out:
mutex_unlock(&mtd_mutex);
- simple_release_fs(&mnt, &count);
return ret;
} /* mtdchar_open */
@@ -148,12 +121,9 @@ static int mtdchar_close(struct inode *inode, struct file *file)
if ((file->f_mode & FMODE_WRITE))
mtd_sync(mtd);
- iput(mfi->ino);
-
put_mtd_device(mtd);
file->private_data = NULL;
kfree(mfi);
- simple_release_fs(&mnt, &count);
return 0;
} /* mtdchar_close */
@@ -1117,6 +1087,13 @@ static unsigned long mtdchar_get_unmapped_area(struct file *file,
ret = mtd_get_unmapped_area(mtd, len, offset, flags);
return ret == -EOPNOTSUPP ? -ENODEV : ret;
}
+
+static unsigned mtdchar_mmap_capabilities(struct file *file)
+{
+ struct mtd_file_info *mfi = file->private_data;
+
+ return mtd_mmap_capabilities(mfi->mtd);
+}
#endif
/*
@@ -1160,27 +1137,10 @@ static const struct file_operations mtd_fops = {
.mmap = mtdchar_mmap,
#ifndef CONFIG_MMU
.get_unmapped_area = mtdchar_get_unmapped_area,
+ .mmap_capabilities = mtdchar_mmap_capabilities,
#endif
};
-static const struct super_operations mtd_ops = {
- .drop_inode = generic_delete_inode,
- .statfs = simple_statfs,
-};
-
-static struct dentry *mtd_inodefs_mount(struct file_system_type *fs_type,
- int flags, const char *dev_name, void *data)
-{
- return mount_pseudo(fs_type, "mtd_inode:", &mtd_ops, NULL, MTD_INODE_FS_MAGIC);
-}
-
-static struct file_system_type mtd_inodefs_type = {
- .name = "mtd_inodefs",
- .mount = mtd_inodefs_mount,
- .kill_sb = kill_anon_super,
-};
-MODULE_ALIAS_FS("mtd_inodefs");
-
int __init init_mtdchar(void)
{
int ret;
@@ -1193,23 +1153,11 @@ int __init init_mtdchar(void)
return ret;
}
- ret = register_filesystem(&mtd_inodefs_type);
- if (ret) {
- pr_err("Can't register mtd_inodefs filesystem, error %d\n",
- ret);
- goto err_unregister_chdev;
- }
-
- return ret;
-
-err_unregister_chdev:
- __unregister_chrdev(MTD_CHAR_MAJOR, 0, 1 << MINORBITS, "mtd");
return ret;
}
void __exit cleanup_mtdchar(void)
{
- unregister_filesystem(&mtd_inodefs_type);
__unregister_chrdev(MTD_CHAR_MAJOR, 0, 1 << MINORBITS, "mtd");
}
diff --git a/drivers/mtd/mtdconcat.c b/drivers/mtd/mtdconcat.c
index b900056..eacc3aa 100644
--- a/drivers/mtd/mtdconcat.c
+++ b/drivers/mtd/mtdconcat.c
@@ -732,8 +732,6 @@ struct mtd_info *mtd_concat_create(struct mtd_info *subdev[], /* subdevices to c
concat->mtd.ecc_stats.badblocks = subdev[0]->ecc_stats.badblocks;
- concat->mtd.backing_dev_info = subdev[0]->backing_dev_info;
-
concat->subdev[0] = subdev[0];
for (i = 1; i < num_devs; i++) {
@@ -761,14 +759,6 @@ struct mtd_info *mtd_concat_create(struct mtd_info *subdev[], /* subdevices to c
subdev[i]->flags & MTD_WRITEABLE;
}
- /* only permit direct mapping if the BDIs are all the same
- * - copy-mapping is still permitted
- */
- if (concat->mtd.backing_dev_info !=
- subdev[i]->backing_dev_info)
- concat->mtd.backing_dev_info =
- &default_backing_dev_info;
-
concat->mtd.size += subdev[i]->size;
concat->mtd.ecc_stats.badblocks +=
subdev[i]->ecc_stats.badblocks;
diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c
index 4c61187..ff38a1d 100644
--- a/drivers/mtd/mtdcore.c
+++ b/drivers/mtd/mtdcore.c
@@ -43,33 +43,7 @@
#include "mtdcore.h"
-/*
- * backing device capabilities for non-mappable devices (such as NAND flash)
- * - permits private mappings, copies are taken of the data
- */
-static struct backing_dev_info mtd_bdi_unmappable = {
- .capabilities = BDI_CAP_MAP_COPY,
-};
-
-/*
- * backing device capabilities for R/O mappable devices (such as ROM)
- * - permits private mappings, copies are taken of the data
- * - permits non-writable shared mappings
- */
-static struct backing_dev_info mtd_bdi_ro_mappable = {
- .capabilities = (BDI_CAP_MAP_COPY | BDI_CAP_MAP_DIRECT |
- BDI_CAP_EXEC_MAP | BDI_CAP_READ_MAP),
-};
-
-/*
- * backing device capabilities for writable mappable devices (such as RAM)
- * - permits private mappings, copies are taken of the data
- * - permits non-writable shared mappings
- */
-static struct backing_dev_info mtd_bdi_rw_mappable = {
- .capabilities = (BDI_CAP_MAP_COPY | BDI_CAP_MAP_DIRECT |
- BDI_CAP_EXEC_MAP | BDI_CAP_READ_MAP |
- BDI_CAP_WRITE_MAP),
+static struct backing_dev_info mtd_bdi = {
};
static int mtd_cls_suspend(struct device *dev, pm_message_t state);
@@ -365,6 +339,22 @@ static struct device_type mtd_devtype = {
.release = mtd_release,
};
+#ifndef CONFIG_MMU
+unsigned mtd_mmap_capabilities(struct mtd_info *mtd)
+{
+ switch (mtd->type) {
+ case MTD_RAM:
+ return NOMMU_MAP_COPY | NOMMU_MAP_DIRECT | NOMMU_MAP_EXEC |
+ NOMMU_MAP_READ | NOMMU_MAP_WRITE;
+ case MTD_ROM:
+ return NOMMU_MAP_COPY | NOMMU_MAP_DIRECT | NOMMU_MAP_EXEC |
+ NOMMU_MAP_READ;
+ default:
+ return NOMMU_MAP_COPY;
+ }
+}
+#endif
+
/**
* add_mtd_device - register an MTD device
* @mtd: pointer to new MTD device info structure
@@ -380,19 +370,7 @@ int add_mtd_device(struct mtd_info *mtd)
struct mtd_notifier *not;
int i, error;
- if (!mtd->backing_dev_info) {
- switch (mtd->type) {
- case MTD_RAM:
- mtd->backing_dev_info = &mtd_bdi_rw_mappable;
- break;
- case MTD_ROM:
- mtd->backing_dev_info = &mtd_bdi_ro_mappable;
- break;
- default:
- mtd->backing_dev_info = &mtd_bdi_unmappable;
- break;
- }
- }
+ mtd->backing_dev_info = &mtd_bdi;
BUG_ON(mtd->writesize == 0);
mutex_lock(&mtd_table_mutex);
@@ -1237,17 +1215,9 @@ static int __init init_mtd(void)
if (ret)
goto err_reg;
- ret = mtd_bdi_init(&mtd_bdi_unmappable, "mtd-unmap");
- if (ret)
- goto err_bdi1;
-
- ret = mtd_bdi_init(&mtd_bdi_ro_mappable, "mtd-romap");
- if (ret)
- goto err_bdi2;
-
- ret = mtd_bdi_init(&mtd_bdi_rw_mappable, "mtd-rwmap");
+ ret = mtd_bdi_init(&mtd_bdi, "mtd");
if (ret)
- goto err_bdi3;
+ goto err_bdi;
proc_mtd = proc_create("mtd", 0, NULL, &mtd_proc_ops);
@@ -1260,11 +1230,7 @@ static int __init init_mtd(void)
out_procfs:
if (proc_mtd)
remove_proc_entry("mtd", NULL);
-err_bdi3:
- bdi_destroy(&mtd_bdi_ro_mappable);
-err_bdi2:
- bdi_destroy(&mtd_bdi_unmappable);
-err_bdi1:
+err_bdi:
class_unregister(&mtd_class);
err_reg:
pr_err("Error registering mtd class or bdi: %d\n", ret);
@@ -1277,9 +1243,7 @@ static void __exit cleanup_mtd(void)
if (proc_mtd)
remove_proc_entry("mtd", NULL);
class_unregister(&mtd_class);
- bdi_destroy(&mtd_bdi_unmappable);
- bdi_destroy(&mtd_bdi_ro_mappable);
- bdi_destroy(&mtd_bdi_rw_mappable);
+ bdi_destroy(&mtd_bdi);
}
module_init(init_mtd);
diff --git a/drivers/mtd/mtdpart.c b/drivers/mtd/mtdpart.c
index a3e3a7d..e779de3 100644
--- a/drivers/mtd/mtdpart.c
+++ b/drivers/mtd/mtdpart.c
@@ -378,7 +378,6 @@ static struct mtd_part *allocate_partition(struct mtd_info *master,
slave->mtd.name = name;
slave->mtd.owner = master->owner;
- slave->mtd.backing_dev_info = master->backing_dev_info;
/* NOTE: we don't arrange MTDs as a tree; it'd be error-prone
* to have the same data be in two different partitions.
diff --git a/drivers/staging/lustre/lustre/llite/llite_lib.c b/drivers/staging/lustre/lustre/llite/llite_lib.c
index a3367bf..d5b149c 100644
--- a/drivers/staging/lustre/lustre/llite/llite_lib.c
+++ b/drivers/staging/lustre/lustre/llite/llite_lib.c
@@ -987,7 +987,7 @@ int ll_fill_super(struct super_block *sb, struct vfsmount *mnt)
if (err)
goto out_free;
lsi->lsi_flags |= LSI_BDI_INITIALIZED;
- lsi->lsi_bdi.capabilities = BDI_CAP_MAP_COPY;
+ lsi->lsi_bdi.capabilities = 0;
err = ll_bdi_register(&lsi->lsi_bdi);
if (err)
goto out_free;
diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c
index 6894b08..620d934 100644
--- a/fs/9p/v9fs.c
+++ b/fs/9p/v9fs.c
@@ -335,7 +335,7 @@ struct p9_fid *v9fs_session_init(struct v9fs_session_info *v9ses,
}
init_rwsem(&v9ses->rename_sem);
- rc = bdi_setup_and_register(&v9ses->bdi, "9p", BDI_CAP_MAP_COPY);
+ rc = bdi_setup_and_register(&v9ses->bdi, "9p");
if (rc) {
kfree(v9ses->aname);
kfree(v9ses->uname);
diff --git a/fs/afs/volume.c b/fs/afs/volume.c
index 2b60725..d142a24 100644
--- a/fs/afs/volume.c
+++ b/fs/afs/volume.c
@@ -106,7 +106,7 @@ struct afs_volume *afs_volume_lookup(struct afs_mount_params *params)
volume->cell = params->cell;
volume->vid = vlocation->vldb.vid[params->type];
- ret = bdi_setup_and_register(&volume->bdi, "afs", BDI_CAP_MAP_COPY);
+ ret = bdi_setup_and_register(&volume->bdi, "afs");
if (ret)
goto error_bdi;
diff --git a/fs/aio.c b/fs/aio.c
index 1b7893e..6f13d3f 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -165,15 +165,6 @@ static struct vfsmount *aio_mnt;
static const struct file_operations aio_ring_fops;
static const struct address_space_operations aio_ctx_aops;
-/* Backing dev info for aio fs.
- * -no dirty page accounting or writeback happens
- */
-static struct backing_dev_info aio_fs_backing_dev_info = {
- .name = "aiofs",
- .state = 0,
- .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK | BDI_CAP_MAP_COPY,
-};
-
static struct file *aio_private_file(struct kioctx *ctx, loff_t nr_pages)
{
struct qstr this = QSTR_INIT("[aio]", 5);
@@ -185,7 +176,7 @@ static struct file *aio_private_file(struct kioctx *ctx, loff_t nr_pages)
inode->i_mapping->a_ops = &aio_ctx_aops;
inode->i_mapping->private_data = ctx;
- inode->i_mapping->backing_dev_info = &aio_fs_backing_dev_info;
+ inode->i_mapping->backing_dev_info = &noop_backing_dev_info;
inode->i_size = PAGE_SIZE * nr_pages;
path.dentry = d_alloc_pseudo(aio_mnt->mnt_sb, &this);
@@ -230,9 +221,6 @@ static int __init aio_setup(void)
if (IS_ERR(aio_mnt))
panic("Failed to create aio fs mount.");
- if (bdi_init(&aio_fs_backing_dev_info))
- panic("Failed to init aio fs backing dev info.");
-
kiocb_cachep = KMEM_CACHE(kiocb, SLAB_HWCACHE_ALIGN|SLAB_PANIC);
kioctx_cachep = KMEM_CACHE(kioctx,SLAB_HWCACHE_ALIGN|SLAB_PANIC);
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 8c63419..afc4092 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1715,8 +1715,7 @@ static int setup_bdi(struct btrfs_fs_info *info, struct backing_dev_info *bdi)
{
int err;
- bdi->capabilities = BDI_CAP_MAP_COPY;
- err = bdi_setup_and_register(bdi, "btrfs", BDI_CAP_MAP_COPY);
+ err = bdi_setup_and_register(bdi, "btrfs");
if (err)
return err;
diff --git a/fs/char_dev.c b/fs/char_dev.c
index 67b2007..ea06a3d 100644
--- a/fs/char_dev.c
+++ b/fs/char_dev.c
@@ -24,27 +24,6 @@
#include "internal.h"
-/*
- * capabilities for /dev/mem, /dev/kmem and similar directly mappable character
- * devices
- * - permits shared-mmap for read, write and/or exec
- * - does not permit private mmap in NOMMU mode (can't do COW)
- * - no readahead or I/O queue unplugging required
- */
-struct backing_dev_info directly_mappable_cdev_bdi = {
- .name = "char",
- .capabilities = (
-#ifdef CONFIG_MMU
- /* permit private copies of the data to be taken */
- BDI_CAP_MAP_COPY |
-#endif
- /* permit direct mmap, for read, write or exec */
- BDI_CAP_MAP_DIRECT |
- BDI_CAP_READ_MAP | BDI_CAP_WRITE_MAP | BDI_CAP_EXEC_MAP |
- /* no writeback happens */
- BDI_CAP_NO_ACCT_AND_WRITEBACK),
-};
-
static struct kobj_map *cdev_map;
static DEFINE_MUTEX(chrdevs_lock);
@@ -575,8 +554,6 @@ static struct kobject *base_probe(dev_t dev, int *part, void *data)
void __init chrdev_init(void)
{
cdev_map = kobj_map_init(base_probe, &chrdevs_lock);
- if (bdi_init(&directly_mappable_cdev_bdi))
- panic("Failed to init directly mappable cdev bdi");
}
@@ -590,4 +567,3 @@ EXPORT_SYMBOL(cdev_del);
EXPORT_SYMBOL(cdev_add);
EXPORT_SYMBOL(__register_chrdev);
EXPORT_SYMBOL(__unregister_chrdev);
-EXPORT_SYMBOL(directly_mappable_cdev_bdi);
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 2a772da..d3aa999 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -3446,7 +3446,7 @@ cifs_mount(struct cifs_sb_info *cifs_sb, struct smb_vol *volume_info)
int referral_walks_count = 0;
#endif
- rc = bdi_setup_and_register(&cifs_sb->bdi, "cifs", BDI_CAP_MAP_COPY);
+ rc = bdi_setup_and_register(&cifs_sb->bdi, "cifs");
if (rc)
return rc;
diff --git a/fs/coda/inode.c b/fs/coda/inode.c
index b945410..82ec68b 100644
--- a/fs/coda/inode.c
+++ b/fs/coda/inode.c
@@ -183,7 +183,7 @@ static int coda_fill_super(struct super_block *sb, void *data, int silent)
goto unlock_out;
}
- error = bdi_setup_and_register(&vc->bdi, "coda", BDI_CAP_MAP_COPY);
+ error = bdi_setup_and_register(&vc->bdi, "coda");
if (error)
goto unlock_out;
diff --git a/fs/configfs/configfs_internal.h b/fs/configfs/configfs_internal.h
index bd4a3c1..a315677 100644
--- a/fs/configfs/configfs_internal.h
+++ b/fs/configfs/configfs_internal.h
@@ -70,8 +70,6 @@ extern int configfs_is_root(struct config_item *item);
extern struct inode * configfs_new_inode(umode_t mode, struct configfs_dirent *, struct super_block *);
extern int configfs_create(struct dentry *, umode_t mode, int (*init)(struct inode *));
-extern int configfs_inode_init(void);
-extern void configfs_inode_exit(void);
extern int configfs_create_file(struct config_item *, const struct configfs_attribute *);
extern int configfs_make_dirent(struct configfs_dirent *,
diff --git a/fs/configfs/inode.c b/fs/configfs/inode.c
index 5946ad9..0ad6b4d 100644
--- a/fs/configfs/inode.c
+++ b/fs/configfs/inode.c
@@ -50,12 +50,6 @@ static const struct address_space_operations configfs_aops = {
.write_end = simple_write_end,
};
-static struct backing_dev_info configfs_backing_dev_info = {
- .name = "configfs",
- .ra_pages = 0, /* No readahead */
- .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK,
-};
-
static const struct inode_operations configfs_inode_operations ={
.setattr = configfs_setattr,
};
@@ -137,7 +131,7 @@ struct inode *configfs_new_inode(umode_t mode, struct configfs_dirent *sd,
if (inode) {
inode->i_ino = get_next_ino();
inode->i_mapping->a_ops = &configfs_aops;
- inode->i_mapping->backing_dev_info = &configfs_backing_dev_info;
+ inode->i_mapping->backing_dev_info = &noop_backing_dev_info;
inode->i_op = &configfs_inode_operations;
if (sd->s_iattr) {
@@ -283,13 +277,3 @@ void configfs_hash_and_remove(struct dentry * dir, const char * name)
}
mutex_unlock(&dir->d_inode->i_mutex);
}
-
-int __init configfs_inode_init(void)
-{
- return bdi_init(&configfs_backing_dev_info);
-}
-
-void configfs_inode_exit(void)
-{
- bdi_destroy(&configfs_backing_dev_info);
-}
diff --git a/fs/configfs/mount.c b/fs/configfs/mount.c
index f6c2858..da94e41 100644
--- a/fs/configfs/mount.c
+++ b/fs/configfs/mount.c
@@ -145,19 +145,13 @@ static int __init configfs_init(void)
if (!config_kobj)
goto out2;
- err = configfs_inode_init();
- if (err)
- goto out3;
-
err = register_filesystem(&configfs_fs_type);
if (err)
- goto out4;
+ goto out3;
return 0;
-out4:
- pr_err("Unable to register filesystem!\n");
- configfs_inode_exit();
out3:
+ pr_err("Unable to register filesystem!\n");
kobject_put(config_kobj);
out2:
kmem_cache_destroy(configfs_dir_cachep);
@@ -172,7 +166,6 @@ static void __exit configfs_exit(void)
kobject_put(config_kobj);
kmem_cache_destroy(configfs_dir_cachep);
configfs_dir_cachep = NULL;
- configfs_inode_exit();
}
MODULE_AUTHOR("Oracle");
diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c
index d9eb84b..1895d60 100644
--- a/fs/ecryptfs/main.c
+++ b/fs/ecryptfs/main.c
@@ -520,7 +520,7 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags
goto out;
}
- rc = bdi_setup_and_register(&sbi->bdi, "ecryptfs", BDI_CAP_MAP_COPY);
+ rc = bdi_setup_and_register(&sbi->bdi, "ecryptfs");
if (rc)
goto out1;
diff --git a/fs/exofs/super.c b/fs/exofs/super.c
index 9596550..fcc2e56 100644
--- a/fs/exofs/super.c
+++ b/fs/exofs/super.c
@@ -836,7 +836,7 @@ static int exofs_fill_super(struct super_block *sb, void *data, int silent)
goto free_sbi;
}
- ret = bdi_setup_and_register(&sbi->bdi, "exofs", BDI_CAP_MAP_COPY);
+ ret = bdi_setup_and_register(&sbi->bdi, "exofs");
if (ret) {
EXOFS_DBGMSG("Failed to bdi_setup_and_register\n");
dput(sb->s_root);
diff --git a/fs/ncpfs/inode.c b/fs/ncpfs/inode.c
index e31e589..a699a3f 100644
--- a/fs/ncpfs/inode.c
+++ b/fs/ncpfs/inode.c
@@ -560,7 +560,7 @@ static int ncp_fill_super(struct super_block *sb, void *raw_data, int silent)
server = NCP_SBP(sb);
memset(server, 0, sizeof(*server));
- error = bdi_setup_and_register(&server->bdi, "ncpfs", BDI_CAP_MAP_COPY);
+ error = bdi_setup_and_register(&server->bdi, "ncpfs");
if (error)
goto out_fput;
diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c
index bbafbde..f6ab41b 100644
--- a/fs/ramfs/file-nommu.c
+++ b/fs/ramfs/file-nommu.c
@@ -34,7 +34,14 @@ static unsigned long ramfs_nommu_get_unmapped_area(struct file *file,
unsigned long flags);
static int ramfs_nommu_mmap(struct file *file, struct vm_area_struct *vma);
+static unsigned ramfs_mmap_capabilities(struct file *file)
+{
+ return NOMMU_MAP_DIRECT | NOMMU_MAP_COPY | NOMMU_MAP_READ |
+ NOMMU_MAP_WRITE | NOMMU_MAP_EXEC;
+}
+
const struct file_operations ramfs_file_operations = {
+ .mmap_capabilities = ramfs_mmap_capabilities,
.mmap = ramfs_nommu_mmap,
.get_unmapped_area = ramfs_nommu_get_unmapped_area,
.read = new_sync_read,
diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c
index d365b1c..ad4d712 100644
--- a/fs/ramfs/inode.c
+++ b/fs/ramfs/inode.c
@@ -50,14 +50,6 @@ static const struct address_space_operations ramfs_aops = {
.set_page_dirty = __set_page_dirty_no_writeback,
};
-static struct backing_dev_info ramfs_backing_dev_info = {
- .name = "ramfs",
- .ra_pages = 0, /* No readahead */
- .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK |
- BDI_CAP_MAP_DIRECT | BDI_CAP_MAP_COPY |
- BDI_CAP_READ_MAP | BDI_CAP_WRITE_MAP | BDI_CAP_EXEC_MAP,
-};
-
struct inode *ramfs_get_inode(struct super_block *sb,
const struct inode *dir, umode_t mode, dev_t dev)
{
@@ -67,7 +59,7 @@ struct inode *ramfs_get_inode(struct super_block *sb,
inode->i_ino = get_next_ino();
inode_init_owner(inode, dir, mode);
inode->i_mapping->a_ops = &ramfs_aops;
- inode->i_mapping->backing_dev_info = &ramfs_backing_dev_info;
+ inode->i_mapping->backing_dev_info = &noop_backing_dev_info;
mapping_set_gfp_mask(inode->i_mapping, GFP_HIGHUSER);
mapping_set_unevictable(inode->i_mapping);
inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
@@ -267,19 +259,9 @@ static struct file_system_type ramfs_fs_type = {
int __init init_ramfs_fs(void)
{
static unsigned long once;
- int err;
if (test_and_set_bit(0, &once))
return 0;
-
- err = bdi_init(&ramfs_backing_dev_info);
- if (err)
- return err;
-
- err = register_filesystem(&ramfs_fs_type);
- if (err)
- bdi_destroy(&ramfs_backing_dev_info);
-
- return err;
+ return register_filesystem(&ramfs_fs_type);
}
fs_initcall(init_ramfs_fs);
diff --git a/fs/romfs/mmap-nommu.c b/fs/romfs/mmap-nommu.c
index ea06c75..7da9e21 100644
--- a/fs/romfs/mmap-nommu.c
+++ b/fs/romfs/mmap-nommu.c
@@ -70,6 +70,15 @@ static int romfs_mmap(struct file *file, struct vm_area_struct *vma)
return vma->vm_flags & (VM_SHARED | VM_MAYSHARE) ? 0 : -ENOSYS;
}
+static unsigned romfs_mmap_capabilities(struct file *file)
+{
+ struct mtd_info *mtd = file_inode(file)->i_sb->s_mtd;
+
+ if (!mtd)
+ return NOMMU_MAP_COPY;
+ return mtd_mmap_capabilities(mtd);
+}
+
const struct file_operations romfs_ro_fops = {
.llseek = generic_file_llseek,
.read = new_sync_read,
@@ -77,4 +86,5 @@ const struct file_operations romfs_ro_fops = {
.splice_read = generic_file_splice_read,
.mmap = romfs_mmap,
.get_unmapped_area = romfs_get_unmapped_area,
+ .mmap_capabilities = romfs_mmap_capabilities,
};
diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c
index 106bf20..ed93dc6 100644
--- a/fs/ubifs/super.c
+++ b/fs/ubifs/super.c
@@ -2017,7 +2017,7 @@ static int ubifs_fill_super(struct super_block *sb, void *data, int silent)
* Read-ahead will be disabled because @c->bdi.ra_pages is 0.
*/
c->bdi.name = "ubifs",
- c->bdi.capabilities = BDI_CAP_MAP_COPY;
+ c->bdi.capabilities = 0;
err = bdi_init(&c->bdi);
if (err)
goto out_close;
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index e936cea..478f95d 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -114,7 +114,7 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent,
const char *fmt, ...);
int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev);
void bdi_unregister(struct backing_dev_info *bdi);
-int __must_check bdi_setup_and_register(struct backing_dev_info *, char *, unsigned int);
+int __must_check bdi_setup_and_register(struct backing_dev_info *, char *);
void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages,
enum wb_reason reason);
void bdi_start_background_writeback(struct backing_dev_info *bdi);
@@ -228,42 +228,17 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio);
* BDI_CAP_NO_ACCT_DIRTY: Dirty pages shouldn't contribute to accounting
* BDI_CAP_NO_WRITEBACK: Don't write pages back
* BDI_CAP_NO_ACCT_WB: Don't automatically account writeback pages
- *
- * These flags let !MMU mmap() govern direct device mapping vs immediate
- * copying more easily for MAP_PRIVATE, especially for ROM filesystems.
- *
- * BDI_CAP_MAP_COPY: Copy can be mapped (MAP_PRIVATE)
- * BDI_CAP_MAP_DIRECT: Can be mapped directly (MAP_SHARED)
- * BDI_CAP_READ_MAP: Can be mapped for reading
- * BDI_CAP_WRITE_MAP: Can be mapped for writing
- * BDI_CAP_EXEC_MAP: Can be mapped for execution
- *
* BDI_CAP_STRICTLIMIT: Keep number of dirty pages below bdi threshold.
*/
#define BDI_CAP_NO_ACCT_DIRTY 0x00000001
#define BDI_CAP_NO_WRITEBACK 0x00000002
-#define BDI_CAP_MAP_COPY 0x00000004
-#define BDI_CAP_MAP_DIRECT 0x00000008
-#define BDI_CAP_READ_MAP 0x00000010
-#define BDI_CAP_WRITE_MAP 0x00000020
-#define BDI_CAP_EXEC_MAP 0x00000040
-#define BDI_CAP_NO_ACCT_WB 0x00000080
-#define BDI_CAP_STABLE_WRITES 0x00000200
-#define BDI_CAP_STRICTLIMIT 0x00000400
-
-#define BDI_CAP_VMFLAGS \
- (BDI_CAP_READ_MAP | BDI_CAP_WRITE_MAP | BDI_CAP_EXEC_MAP)
+#define BDI_CAP_NO_ACCT_WB 0x00000004
+#define BDI_CAP_STABLE_WRITES 0x00000008
+#define BDI_CAP_STRICTLIMIT 0x00000010
#define BDI_CAP_NO_ACCT_AND_WRITEBACK \
(BDI_CAP_NO_WRITEBACK | BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_ACCT_WB)
-#if defined(VM_MAYREAD) && \
- (BDI_CAP_READ_MAP != VM_MAYREAD || \
- BDI_CAP_WRITE_MAP != VM_MAYWRITE || \
- BDI_CAP_EXEC_MAP != VM_MAYEXEC)
-#error please change backing_dev_info::capabilities flags
-#endif
-
extern struct backing_dev_info default_backing_dev_info;
extern struct backing_dev_info noop_backing_dev_info;
diff --git a/include/linux/cdev.h b/include/linux/cdev.h
index fb45919..f876361 100644
--- a/include/linux/cdev.h
+++ b/include/linux/cdev.h
@@ -30,6 +30,4 @@ void cdev_del(struct cdev *);
void cd_forget(struct inode *);
-extern struct backing_dev_info directly_mappable_cdev_bdi;
-
#endif
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 42efe13..1dada39 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1502,6 +1502,26 @@ struct block_device_operations;
#define HAVE_COMPAT_IOCTL 1
#define HAVE_UNLOCKED_IOCTL 1
+/*
+ * These flags let !MMU mmap() govern direct device mapping vs immediate
+ * copying more easily for MAP_PRIVATE, especially for ROM filesystems.
+ *
+ * NOMMU_MAP_COPY: Copy can be mapped (MAP_PRIVATE)
+ * NOMMU_MAP_DIRECT: Can be mapped directly (MAP_SHARED)
+ * NOMMU_MAP_READ: Can be mapped for reading
+ * NOMMU_MAP_WRITE: Can be mapped for writing
+ * NOMMU_MAP_EXEC: Can be mapped for execution
+ */
+#define NOMMU_MAP_COPY 0x00000001
+#define NOMMU_MAP_DIRECT 0x00000008
+#define NOMMU_MAP_READ VM_MAYREAD
+#define NOMMU_MAP_WRITE VM_MAYWRITE
+#define NOMMU_MAP_EXEC VM_MAYEXEC
+
+#define NOMMU_VMFLAGS \
+ (NOMMU_MAP_READ | NOMMU_MAP_WRITE | NOMMU_MAP_EXEC)
+
+
struct iov_iter;
struct file_operations {
@@ -1536,6 +1556,9 @@ struct file_operations {
long (*fallocate)(struct file *file, int mode, loff_t offset,
loff_t len);
void (*show_fdinfo)(struct seq_file *m, struct file *f);
+#ifndef CONFIG_MMU
+ unsigned (*mmap_capabilities)(struct file *);
+#endif
};
struct inode_operations {
diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h
index 031ff3a..3301c4c 100644
--- a/include/linux/mtd/mtd.h
+++ b/include/linux/mtd/mtd.h
@@ -408,4 +408,6 @@ static inline int mtd_is_bitflip_or_eccerr(int err) {
return mtd_is_bitflip(err) || mtd_is_eccerr(err);
}
+unsigned mtd_mmap_capabilities(struct mtd_info *mtd);
+
#endif /* __MTD_MTD_H__ */
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 0ae0df5..16c6895 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -17,8 +17,6 @@ static atomic_long_t bdi_seq = ATOMIC_LONG_INIT(0);
struct backing_dev_info default_backing_dev_info = {
.name = "default",
.ra_pages = VM_MAX_READAHEAD * 1024 / PAGE_CACHE_SIZE,
- .state = 0,
- .capabilities = BDI_CAP_MAP_COPY,
};
EXPORT_SYMBOL_GPL(default_backing_dev_info);
@@ -513,13 +511,12 @@ EXPORT_SYMBOL(bdi_destroy);
* For use from filesystems to quickly init and register a bdi associated
* with dirty writeback
*/
-int bdi_setup_and_register(struct backing_dev_info *bdi, char *name,
- unsigned int cap)
+int bdi_setup_and_register(struct backing_dev_info *bdi, char *name)
{
int err;
bdi->name = name;
- bdi->capabilities = cap;
+ bdi->capabilities = 0;
err = bdi_init(bdi);
if (err)
return err;
diff --git a/mm/nommu.c b/mm/nommu.c
index b51eadf..13af96f3 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -946,9 +946,6 @@ static int validate_mmap_request(struct file *file,
return -EOVERFLOW;
if (file) {
- /* validate file mapping requests */
- struct address_space *mapping;
-
/* files must support mmap */
if (!file->f_op->mmap)
return -ENODEV;
@@ -957,28 +954,22 @@ static int validate_mmap_request(struct file *file,
* - we support chardevs that provide their own "memory"
* - we support files/blockdevs that are memory backed
*/
- mapping = file->f_mapping;
- if (!mapping)
- mapping = file_inode(file)->i_mapping;
-
- capabilities = 0;
- if (mapping && mapping->backing_dev_info)
- capabilities = mapping->backing_dev_info->capabilities;
-
- if (!capabilities) {
+ if (file->f_op->mmap_capabilities) {
+ capabilities = file->f_op->mmap_capabilities(file);
+ } else {
/* no explicit capabilities set, so assume some
* defaults */
switch (file_inode(file)->i_mode & S_IFMT) {
case S_IFREG:
case S_IFBLK:
- capabilities = BDI_CAP_MAP_COPY;
+ capabilities = NOMMU_MAP_COPY;
break;
case S_IFCHR:
capabilities =
- BDI_CAP_MAP_DIRECT |
- BDI_CAP_READ_MAP |
- BDI_CAP_WRITE_MAP;
+ NOMMU_MAP_DIRECT |
+ NOMMU_MAP_READ |
+ NOMMU_MAP_WRITE;
break;
default:
@@ -989,9 +980,9 @@ static int validate_mmap_request(struct file *file,
/* eliminate any capabilities that we can't support on this
* device */
if (!file->f_op->get_unmapped_area)
- capabilities &= ~BDI_CAP_MAP_DIRECT;
+ capabilities &= ~NOMMU_MAP_DIRECT;
if (!file->f_op->read)
- capabilities &= ~BDI_CAP_MAP_COPY;
+ capabilities &= ~NOMMU_MAP_COPY;
/* The file shall have been opened with read permission. */
if (!(file->f_mode & FMODE_READ))
@@ -1010,29 +1001,29 @@ static int validate_mmap_request(struct file *file,
if (locks_verify_locked(file))
return -EAGAIN;
- if (!(capabilities & BDI_CAP_MAP_DIRECT))
+ if (!(capabilities & NOMMU_MAP_DIRECT))
return -ENODEV;
/* we mustn't privatise shared mappings */
- capabilities &= ~BDI_CAP_MAP_COPY;
+ capabilities &= ~NOMMU_MAP_COPY;
} else {
/* we're going to read the file into private memory we
* allocate */
- if (!(capabilities & BDI_CAP_MAP_COPY))
+ if (!(capabilities & NOMMU_MAP_COPY))
return -ENODEV;
/* we don't permit a private writable mapping to be
* shared with the backing device */
if (prot & PROT_WRITE)
- capabilities &= ~BDI_CAP_MAP_DIRECT;
+ capabilities &= ~NOMMU_MAP_DIRECT;
}
- if (capabilities & BDI_CAP_MAP_DIRECT) {
- if (((prot & PROT_READ) && !(capabilities & BDI_CAP_READ_MAP)) ||
- ((prot & PROT_WRITE) && !(capabilities & BDI_CAP_WRITE_MAP)) ||
- ((prot & PROT_EXEC) && !(capabilities & BDI_CAP_EXEC_MAP))
+ if (capabilities & NOMMU_MAP_DIRECT) {
+ if (((prot & PROT_READ) && !(capabilities & NOMMU_MAP_READ)) ||
+ ((prot & PROT_WRITE) && !(capabilities & NOMMU_MAP_WRITE)) ||
+ ((prot & PROT_EXEC) && !(capabilities & NOMMU_MAP_EXEC))
) {
- capabilities &= ~BDI_CAP_MAP_DIRECT;
+ capabilities &= ~NOMMU_MAP_DIRECT;
if (flags & MAP_SHARED) {
printk(KERN_WARNING
"MAP_SHARED not completely supported on !MMU\n");
@@ -1049,21 +1040,21 @@ static int validate_mmap_request(struct file *file,
} else if ((prot & PROT_READ) && !(prot & PROT_EXEC)) {
/* handle implication of PROT_EXEC by PROT_READ */
if (current->personality & READ_IMPLIES_EXEC) {
- if (capabilities & BDI_CAP_EXEC_MAP)
+ if (capabilities & NOMMU_MAP_EXEC)
prot |= PROT_EXEC;
}
} else if ((prot & PROT_READ) &&
(prot & PROT_EXEC) &&
- !(capabilities & BDI_CAP_EXEC_MAP)
+ !(capabilities & NOMMU_MAP_EXEC)
) {
/* backing file is not executable, try to copy */
- capabilities &= ~BDI_CAP_MAP_DIRECT;
+ capabilities &= ~NOMMU_MAP_DIRECT;
}
} else {
/* anonymous mappings are always memory backed and can be
* privately mapped
*/
- capabilities = BDI_CAP_MAP_COPY;
+ capabilities = NOMMU_MAP_COPY;
/* handle PROT_EXEC implication by PROT_READ */
if ((prot & PROT_READ) &&
@@ -1095,7 +1086,7 @@ static unsigned long determine_vm_flags(struct file *file,
vm_flags = calc_vm_prot_bits(prot) | calc_vm_flag_bits(flags);
/* vm_flags |= mm->def_flags; */
- if (!(capabilities & BDI_CAP_MAP_DIRECT)) {
+ if (!(capabilities & NOMMU_MAP_DIRECT)) {
/* attempt to share read-only copies of mapped file chunks */
vm_flags |= VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC;
if (file && !(prot & PROT_WRITE))
@@ -1104,7 +1095,7 @@ static unsigned long determine_vm_flags(struct file *file,
/* overlay a shareable mapping on the backing device or inode
* if possible - used for chardevs, ramfs/tmpfs/shmfs and
* romfs/cramfs */
- vm_flags |= VM_MAYSHARE | (capabilities & BDI_CAP_VMFLAGS);
+ vm_flags |= VM_MAYSHARE | (capabilities & NOMMU_VMFLAGS);
if (flags & MAP_SHARED)
vm_flags |= VM_SHARED;
}
@@ -1157,7 +1148,7 @@ static int do_mmap_private(struct vm_area_struct *vma,
* shared mappings on devices or memory
* - VM_MAYSHARE will be set if it may attempt to share
*/
- if (capabilities & BDI_CAP_MAP_DIRECT) {
+ if (capabilities & NOMMU_MAP_DIRECT) {
ret = vma->vm_file->f_op->mmap(vma->vm_file, vma);
if (ret == 0) {
/* shouldn't return success if we're not sharing */
@@ -1346,7 +1337,7 @@ unsigned long do_mmap_pgoff(struct file *file,
if ((pregion->vm_pgoff != pgoff || rpglen != pglen) &&
!(pgoff >= pregion->vm_pgoff && pgend <= rpgend)) {
/* new mapping is not a subset of the region */
- if (!(capabilities & BDI_CAP_MAP_DIRECT))
+ if (!(capabilities & NOMMU_MAP_DIRECT))
goto sharing_violation;
continue;
}
@@ -1385,7 +1376,7 @@ unsigned long do_mmap_pgoff(struct file *file,
* - this is the hook for quasi-memory character devices to
* tell us the location of a shared mapping
*/
- if (capabilities & BDI_CAP_MAP_DIRECT) {
+ if (capabilities & NOMMU_MAP_DIRECT) {
addr = file->f_op->get_unmapped_area(file, addr, len,
pgoff, flags);
if (IS_ERR_VALUE(addr)) {
@@ -1397,10 +1388,10 @@ unsigned long do_mmap_pgoff(struct file *file,
* the mapping so we'll have to attempt to copy
* it */
ret = -ENODEV;
- if (!(capabilities & BDI_CAP_MAP_COPY))
+ if (!(capabilities & NOMMU_MAP_COPY))
goto error_just_free;
- capabilities &= ~BDI_CAP_MAP_DIRECT;
+ capabilities &= ~NOMMU_MAP_DIRECT;
} else {
vma->vm_start = region->vm_start = addr;
vma->vm_end = region->vm_end = addr + len;
@@ -1411,7 +1402,7 @@ unsigned long do_mmap_pgoff(struct file *file,
vma->vm_region = region;
/* set up the mapping
- * - the region is filled in if BDI_CAP_MAP_DIRECT is still set
+ * - the region is filled in if NOMMU_MAP_DIRECT is still set
*/
if (file && vma->vm_flags & VM_SHARED)
ret = do_mmap_shared_file(vma);
diff --git a/security/security.c b/security/security.c
index 18b35c6..a0442b2 100644
--- a/security/security.c
+++ b/security/security.c
@@ -726,16 +726,15 @@ static inline unsigned long mmap_prot(struct file *file, unsigned long prot)
return prot | PROT_EXEC;
/*
* ditto if it's not on noexec mount, except that on !MMU we need
- * BDI_CAP_EXEC_MMAP (== VM_MAYEXEC) in this case
+ * NOMMU_MAP_EXEC (== VM_MAYEXEC) in this case
*/
if (!(file->f_path.mnt->mnt_flags & MNT_NOEXEC)) {
#ifndef CONFIG_MMU
- unsigned long caps = 0;
- struct address_space *mapping = file->f_mapping;
- if (mapping && mapping->backing_dev_info)
- caps = mapping->backing_dev_info->capabilities;
- if (!(caps & BDI_CAP_EXEC_MAP))
- return prot;
+ if (file->f_op->mmap_capabilities) {
+ unsigned caps = file->f_op->mmap_capabilities(file);
+ if (!(caps & NOMMU_MAP_EXEC))
+ return prot;
+ }
#endif
return prot | PROT_EXEC;
}
--
1.9.1
+ dwmw2
On Wed, Jan 14, 2015 at 10:42:32AM +0100, Christoph Hellwig wrote:
> Since "BDI: Provide backing device capability information [try #3]" the
> backing_dev_info structure also provides flags for the kind of mmap
> operation available in a nommu environment, which is entirely unrelated
> to it's original purpose.
>
> Introduce a new nommu-only file operation to provide this information to
> the nommu mmap code instead. Splitting this from the backing_dev_info
> structure allows to remove lots of backing_dev_info instance that aren't
> otherwise needed, and entirely gets rid of the concept of providing a
> backing_dev_info for a character device. It also removes the need for
> the mtd_inodefs filesystem.
>
> Signed-off-by: Christoph Hellwig <[email protected]>
> Reviewed-by: Tejun Heo <[email protected]>
> ---
> Documentation/nommu-mmap.txt | 8 +--
> block/blk-core.c | 2 +-
> drivers/char/mem.c | 64 ++++++++++----------
> drivers/mtd/mtdchar.c | 72 ++++------------------
> drivers/mtd/mtdconcat.c | 10 ----
> drivers/mtd/mtdcore.c | 80 +++++++------------------
> drivers/mtd/mtdpart.c | 1 -
There's a small conflict in mtdcore.c with some stuff I have queued up
for MTD in linux-next. Should be trivial to resolve later.
I don't have a test platform for nommu, and I'll admit I'm not too
familiar with this code, but it looks OK to me. So FWIW, for the MTD
parts:
Acked-by: Brian Norris <[email protected]>
> drivers/staging/lustre/lustre/llite/llite_lib.c | 2 +-
> fs/9p/v9fs.c | 2 +-
> fs/afs/volume.c | 2 +-
> fs/aio.c | 14 +----
> fs/btrfs/disk-io.c | 3 +-
> fs/char_dev.c | 24 --------
> fs/cifs/connect.c | 2 +-
> fs/coda/inode.c | 2 +-
> fs/configfs/configfs_internal.h | 2 -
> fs/configfs/inode.c | 18 +-----
> fs/configfs/mount.c | 11 +---
> fs/ecryptfs/main.c | 2 +-
> fs/exofs/super.c | 2 +-
> fs/ncpfs/inode.c | 2 +-
> fs/ramfs/file-nommu.c | 7 +++
> fs/ramfs/inode.c | 22 +------
> fs/romfs/mmap-nommu.c | 10 ++++
> fs/ubifs/super.c | 2 +-
> include/linux/backing-dev.h | 33 ++--------
> include/linux/cdev.h | 2 -
> include/linux/fs.h | 23 +++++++
> include/linux/mtd/mtd.h | 2 +
> mm/backing-dev.c | 7 +--
> mm/nommu.c | 69 ++++++++++-----------
> security/security.c | 13 ++--
> 32 files changed, 169 insertions(+), 346 deletions(-)
[...]
Brian
Since 018a17bdc865 ("bdi: reimplement bdev_inode_switch_bdi()") the
block device code writes out all dirty data whenever switching the
backing_dev_info for a block device inode. But a block device inode can
only be dirtied when it is in use, which means we only have to write it
out on the final blkdev_put, but not when doing a blkdev_get.
Factoring out the write out from the bdi list switch prepares from
removing the list switch later in the series.
Signed-off-by: Christoph Hellwig <[email protected]>
Acked-by: Tejun Heo <[email protected]>
---
fs/block_dev.c | 31 +++++++++++++++++++------------
1 file changed, 19 insertions(+), 12 deletions(-)
diff --git a/fs/block_dev.c b/fs/block_dev.c
index b48c41b..026ca7b 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -49,6 +49,17 @@ inline struct block_device *I_BDEV(struct inode *inode)
}
EXPORT_SYMBOL(I_BDEV);
+static void bdev_write_inode(struct inode *inode)
+{
+ spin_lock(&inode->i_lock);
+ while (inode->i_state & I_DIRTY) {
+ spin_unlock(&inode->i_lock);
+ WARN_ON_ONCE(write_inode_now(inode, true));
+ spin_lock(&inode->i_lock);
+ }
+ spin_unlock(&inode->i_lock);
+}
+
/*
* Move the inode from its current bdi to a new bdi. Make sure the inode
* is clean before moving so that it doesn't linger on the old bdi.
@@ -56,16 +67,10 @@ EXPORT_SYMBOL(I_BDEV);
static void bdev_inode_switch_bdi(struct inode *inode,
struct backing_dev_info *dst)
{
- while (true) {
- spin_lock(&inode->i_lock);
- if (!(inode->i_state & I_DIRTY)) {
- inode->i_data.backing_dev_info = dst;
- spin_unlock(&inode->i_lock);
- return;
- }
- spin_unlock(&inode->i_lock);
- WARN_ON_ONCE(write_inode_now(inode, true));
- }
+ spin_lock(&inode->i_lock);
+ WARN_ON_ONCE(inode->i_state & I_DIRTY);
+ inode->i_data.backing_dev_info = dst;
+ spin_unlock(&inode->i_lock);
}
/* Kill _all_ buffers and pagecache , dirty or not.. */
@@ -1464,9 +1469,11 @@ static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part)
WARN_ON_ONCE(bdev->bd_holders);
sync_blockdev(bdev);
kill_bdev(bdev);
- /* ->release can cause the old bdi to disappear,
- * so must switch it out first
+ /*
+ * ->release can cause the queue to disappear, so flush all
+ * dirty data before.
*/
+ bdev_write_inode(bdev->bd_inode);
bdev_inode_switch_bdi(bdev->bd_inode,
&default_backing_dev_info);
}
--
1.9.1
On Wed 14-01-15 10:42:33, Christoph Hellwig wrote:
> Since 018a17bdc865 ("bdi: reimplement bdev_inode_switch_bdi()") the
> block device code writes out all dirty data whenever switching the
> backing_dev_info for a block device inode. But a block device inode can
> only be dirtied when it is in use, which means we only have to write it
> out on the final blkdev_put, but not when doing a blkdev_get.
>
> Factoring out the write out from the bdi list switch prepares from
> removing the list switch later in the series.
>
> Signed-off-by: Christoph Hellwig <[email protected]>
> Acked-by: Tejun Heo <[email protected]>
Looks good. You can add:
Reviewed-by: Jan Kara <[email protected]>
Honza
> ---
> fs/block_dev.c | 31 +++++++++++++++++++------------
> 1 file changed, 19 insertions(+), 12 deletions(-)
>
> diff --git a/fs/block_dev.c b/fs/block_dev.c
> index b48c41b..026ca7b 100644
> --- a/fs/block_dev.c
> +++ b/fs/block_dev.c
> @@ -49,6 +49,17 @@ inline struct block_device *I_BDEV(struct inode *inode)
> }
> EXPORT_SYMBOL(I_BDEV);
>
> +static void bdev_write_inode(struct inode *inode)
> +{
> + spin_lock(&inode->i_lock);
> + while (inode->i_state & I_DIRTY) {
> + spin_unlock(&inode->i_lock);
> + WARN_ON_ONCE(write_inode_now(inode, true));
> + spin_lock(&inode->i_lock);
> + }
> + spin_unlock(&inode->i_lock);
> +}
> +
> /*
> * Move the inode from its current bdi to a new bdi. Make sure the inode
> * is clean before moving so that it doesn't linger on the old bdi.
> @@ -56,16 +67,10 @@ EXPORT_SYMBOL(I_BDEV);
> static void bdev_inode_switch_bdi(struct inode *inode,
> struct backing_dev_info *dst)
> {
> - while (true) {
> - spin_lock(&inode->i_lock);
> - if (!(inode->i_state & I_DIRTY)) {
> - inode->i_data.backing_dev_info = dst;
> - spin_unlock(&inode->i_lock);
> - return;
> - }
> - spin_unlock(&inode->i_lock);
> - WARN_ON_ONCE(write_inode_now(inode, true));
> - }
> + spin_lock(&inode->i_lock);
> + WARN_ON_ONCE(inode->i_state & I_DIRTY);
> + inode->i_data.backing_dev_info = dst;
> + spin_unlock(&inode->i_lock);
> }
>
> /* Kill _all_ buffers and pagecache , dirty or not.. */
> @@ -1464,9 +1469,11 @@ static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part)
> WARN_ON_ONCE(bdev->bd_holders);
> sync_blockdev(bdev);
> kill_bdev(bdev);
> - /* ->release can cause the old bdi to disappear,
> - * so must switch it out first
> + /*
> + * ->release can cause the queue to disappear, so flush all
> + * dirty data before.
> */
> + bdev_write_inode(bdev->bd_inode);
> bdev_inode_switch_bdi(bdev->bd_inode,
> &default_backing_dev_info);
> }
> --
> 1.9.1
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
> the body of a message to [email protected]
> More majordomo info at http://vger.kernel.org/majordomo-info.html
--
Jan Kara <[email protected]>
SUSE Labs, CR
Directly grab the backing_dev_info from the request_queue instead of
detouring through the address_space.
Signed-off-by: Christoph Hellwig <[email protected]>
Reviewed-by: Tejun Heo <[email protected]>
---
fs/fs-writeback.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 2d609a5..e8116a4 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -69,10 +69,10 @@ EXPORT_SYMBOL(writeback_in_progress);
static inline struct backing_dev_info *inode_to_bdi(struct inode *inode)
{
struct super_block *sb = inode->i_sb;
-
+#ifdef CONFIG_BLOCK
if (sb_is_blkdev_sb(sb))
- return inode->i_mapping->backing_dev_info;
-
+ return blk_get_backing_dev_info(I_BDEV(inode));
+#endif
return sb->s_bdi;
}
--
1.9.1
On Wed 14-01-15 10:42:34, Christoph Hellwig wrote:
> Directly grab the backing_dev_info from the request_queue instead of
> detouring through the address_space.
>
> Signed-off-by: Christoph Hellwig <[email protected]>
> Reviewed-by: Tejun Heo <[email protected]>
Looks good. You can add:
Reviewed-by: Jan Kara <[email protected]>
Honza
> ---
> fs/fs-writeback.c | 6 +++---
> 1 file changed, 3 insertions(+), 3 deletions(-)
>
> diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
> index 2d609a5..e8116a4 100644
> --- a/fs/fs-writeback.c
> +++ b/fs/fs-writeback.c
> @@ -69,10 +69,10 @@ EXPORT_SYMBOL(writeback_in_progress);
> static inline struct backing_dev_info *inode_to_bdi(struct inode *inode)
> {
> struct super_block *sb = inode->i_sb;
> -
> +#ifdef CONFIG_BLOCK
> if (sb_is_blkdev_sb(sb))
> - return inode->i_mapping->backing_dev_info;
> -
> + return blk_get_backing_dev_info(I_BDEV(inode));
> +#endif
> return sb->s_bdi;
> }
>
> --
> 1.9.1
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
> the body of a message to [email protected]
> More majordomo info at http://vger.kernel.org/majordomo-info.html
--
Jan Kara <[email protected]>
SUSE Labs, CR
mapping->backing_dev_info will go away, so don't rely on it.
Signed-off-by: Christoph Hellwig <[email protected]>
Acked-by: Ryusuke Konishi <[email protected]>
Reviewed-by: Tejun Heo <[email protected]>
---
fs/nilfs2/super.c | 4 +---
1 file changed, 1 insertion(+), 3 deletions(-)
diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c
index 2e5b3ec..3d4bbac 100644
--- a/fs/nilfs2/super.c
+++ b/fs/nilfs2/super.c
@@ -1057,7 +1057,6 @@ nilfs_fill_super(struct super_block *sb, void *data, int silent)
{
struct the_nilfs *nilfs;
struct nilfs_root *fsroot;
- struct backing_dev_info *bdi;
__u64 cno;
int err;
@@ -1077,8 +1076,7 @@ nilfs_fill_super(struct super_block *sb, void *data, int silent)
sb->s_time_gran = 1;
sb->s_max_links = NILFS_LINK_MAX;
- bdi = sb->s_bdev->bd_inode->i_mapping->backing_dev_info;
- sb->s_bdi = bdi ? : &default_backing_dev_info;
+ sb->s_bdi = &bdev_get_queue(sb->s_bdev)->backing_dev_info;
err = load_nilfs(nilfs, sb);
if (err)
--
1.9.1
On Wed 14-01-15 10:42:35, Christoph Hellwig wrote:
> mapping->backing_dev_info will go away, so don't rely on it.
>
> Signed-off-by: Christoph Hellwig <[email protected]>
> Acked-by: Ryusuke Konishi <[email protected]>
> Reviewed-by: Tejun Heo <[email protected]>
> ---
> fs/nilfs2/super.c | 4 +---
> 1 file changed, 1 insertion(+), 3 deletions(-)
>
> diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c
> index 2e5b3ec..3d4bbac 100644
> --- a/fs/nilfs2/super.c
> +++ b/fs/nilfs2/super.c
> @@ -1077,8 +1076,7 @@ nilfs_fill_super(struct super_block *sb, void *data, int silent)
> sb->s_time_gran = 1;
> sb->s_max_links = NILFS_LINK_MAX;
>
> - bdi = sb->s_bdev->bd_inode->i_mapping->backing_dev_info;
> - sb->s_bdi = bdi ? : &default_backing_dev_info;
> + sb->s_bdi = &bdev_get_queue(sb->s_bdev)->backing_dev_info;
Why don't you use blk_get_backing_dev_info() here? Otherwise the patch
looks fine. So you can add:
Reviewed-by: Jan Kara <[email protected]>
Honza
--
Jan Kara <[email protected]>
SUSE Labs, CR
Now that we got rid of the bdi abuse on character devices we can always use
sb->s_bdi to get at the backing_dev_info for a file, except for the block
device special case. Export inode_to_bdi and replace uses of
mapping->backing_dev_info with it to prepare for the removal of
mapping->backing_dev_info.
Signed-off-by: Christoph Hellwig <[email protected]>
Reviewed-by: Tejun Heo <[email protected]>
---
fs/btrfs/file.c | 2 +-
fs/ceph/file.c | 2 +-
fs/ext2/ialloc.c | 2 +-
fs/ext4/super.c | 2 +-
fs/fs-writeback.c | 3 ++-
fs/fuse/file.c | 10 +++++-----
fs/gfs2/aops.c | 2 +-
fs/gfs2/super.c | 2 +-
fs/nfs/filelayout/filelayout.c | 2 +-
fs/nfs/write.c | 6 +++---
fs/ntfs/file.c | 3 ++-
fs/ocfs2/file.c | 2 +-
fs/xfs/xfs_file.c | 2 +-
include/linux/backing-dev.h | 6 ++++--
include/trace/events/writeback.h | 6 +++---
mm/fadvise.c | 4 ++--
mm/filemap.c | 4 ++--
mm/filemap_xip.c | 3 ++-
mm/page-writeback.c | 29 +++++++++++++----------------
mm/readahead.c | 4 ++--
mm/truncate.c | 2 +-
mm/vmscan.c | 4 ++--
22 files changed, 52 insertions(+), 50 deletions(-)
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index e409025..835c04a 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1746,7 +1746,7 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
mutex_lock(&inode->i_mutex);
- current->backing_dev_info = inode->i_mapping->backing_dev_info;
+ current->backing_dev_info = inode_to_bdi(inode);
err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode));
if (err) {
mutex_unlock(&inode->i_mutex);
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index ce74b39..905986d 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -945,7 +945,7 @@ static ssize_t ceph_write_iter(struct kiocb *iocb, struct iov_iter *from)
mutex_lock(&inode->i_mutex);
/* We can write back this queue in page reclaim */
- current->backing_dev_info = file->f_mapping->backing_dev_info;
+ current->backing_dev_info = inode_to_bdi(inode);
err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode));
if (err)
diff --git a/fs/ext2/ialloc.c b/fs/ext2/ialloc.c
index 7d66fb0..6c14bb8 100644
--- a/fs/ext2/ialloc.c
+++ b/fs/ext2/ialloc.c
@@ -170,7 +170,7 @@ static void ext2_preread_inode(struct inode *inode)
struct ext2_group_desc * gdp;
struct backing_dev_info *bdi;
- bdi = inode->i_mapping->backing_dev_info;
+ bdi = inode_to_bdi(inode);
if (bdi_read_congested(bdi))
return;
if (bdi_write_congested(bdi))
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 74c5f53..ad88e60 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -334,7 +334,7 @@ static void save_error_info(struct super_block *sb, const char *func,
static int block_device_ejected(struct super_block *sb)
{
struct inode *bd_inode = sb->s_bdev->bd_inode;
- struct backing_dev_info *bdi = bd_inode->i_mapping->backing_dev_info;
+ struct backing_dev_info *bdi = inode_to_bdi(bd_inode);
return bdi->dev == NULL;
}
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index e8116a4..a20b114 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -66,7 +66,7 @@ int writeback_in_progress(struct backing_dev_info *bdi)
}
EXPORT_SYMBOL(writeback_in_progress);
-static inline struct backing_dev_info *inode_to_bdi(struct inode *inode)
+struct backing_dev_info *inode_to_bdi(struct inode *inode)
{
struct super_block *sb = inode->i_sb;
#ifdef CONFIG_BLOCK
@@ -75,6 +75,7 @@ static inline struct backing_dev_info *inode_to_bdi(struct inode *inode)
#endif
return sb->s_bdi;
}
+EXPORT_SYMBOL_GPL(inode_to_bdi);
static inline struct inode *wb_inode(struct list_head *head)
{
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 760b2c5..19d80b8 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -1159,7 +1159,7 @@ static ssize_t fuse_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
mutex_lock(&inode->i_mutex);
/* We can write back this queue in page reclaim */
- current->backing_dev_info = mapping->backing_dev_info;
+ current->backing_dev_info = inode_to_bdi(inode);
err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode));
if (err)
@@ -1464,7 +1464,7 @@ static void fuse_writepage_finish(struct fuse_conn *fc, struct fuse_req *req)
{
struct inode *inode = req->inode;
struct fuse_inode *fi = get_fuse_inode(inode);
- struct backing_dev_info *bdi = inode->i_mapping->backing_dev_info;
+ struct backing_dev_info *bdi = inode_to_bdi(inode);
int i;
list_del(&req->writepages_entry);
@@ -1658,7 +1658,7 @@ static int fuse_writepage_locked(struct page *page)
req->end = fuse_writepage_end;
req->inode = inode;
- inc_bdi_stat(mapping->backing_dev_info, BDI_WRITEBACK);
+ inc_bdi_stat(inode_to_bdi(inode), BDI_WRITEBACK);
inc_zone_page_state(tmp_page, NR_WRITEBACK_TEMP);
spin_lock(&fc->lock);
@@ -1768,7 +1768,7 @@ static bool fuse_writepage_in_flight(struct fuse_req *new_req,
if (old_req->num_pages == 1 && (old_req->state == FUSE_REQ_INIT ||
old_req->state == FUSE_REQ_PENDING)) {
- struct backing_dev_info *bdi = page->mapping->backing_dev_info;
+ struct backing_dev_info *bdi = inode_to_bdi(page->mapping->host);
copy_highpage(old_req->pages[0], page);
spin_unlock(&fc->lock);
@@ -1872,7 +1872,7 @@ static int fuse_writepages_fill(struct page *page,
req->page_descs[req->num_pages].offset = 0;
req->page_descs[req->num_pages].length = PAGE_SIZE;
- inc_bdi_stat(page->mapping->backing_dev_info, BDI_WRITEBACK);
+ inc_bdi_stat(inode_to_bdi(inode), BDI_WRITEBACK);
inc_zone_page_state(tmp_page, NR_WRITEBACK_TEMP);
err = 0;
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index 805b37f..4ad4f94 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -289,7 +289,7 @@ continue_unlock:
if (!clear_page_dirty_for_io(page))
goto continue_unlock;
- trace_wbc_writepage(wbc, mapping->backing_dev_info);
+ trace_wbc_writepage(wbc, inode_to_bdi(inode));
ret = __gfs2_jdata_writepage(page, wbc);
if (unlikely(ret)) {
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index 5b327f8..1666382 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -743,7 +743,7 @@ static int gfs2_write_inode(struct inode *inode, struct writeback_control *wbc)
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_sbd *sdp = GFS2_SB(inode);
struct address_space *metamapping = gfs2_glock2aspace(ip->i_gl);
- struct backing_dev_info *bdi = metamapping->backing_dev_info;
+ struct backing_dev_info *bdi = inode_to_bdi(metamapping->host);
int ret = 0;
if (wbc->sync_mode == WB_SYNC_ALL)
diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c
index 7afb52f..51aa889 100644
--- a/fs/nfs/filelayout/filelayout.c
+++ b/fs/nfs/filelayout/filelayout.c
@@ -1081,7 +1081,7 @@ mds_commit:
spin_unlock(cinfo->lock);
if (!cinfo->dreq) {
inc_zone_page_state(req->wb_page, NR_UNSTABLE_NFS);
- inc_bdi_stat(page_file_mapping(req->wb_page)->backing_dev_info,
+ inc_bdi_stat(inode_to_bdi(page_file_mapping(req->wb_page)->host),
BDI_RECLAIMABLE);
__mark_inode_dirty(req->wb_context->dentry->d_inode,
I_DIRTY_DATASYNC);
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index af3af68..298abcc 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -786,7 +786,7 @@ nfs_request_add_commit_list(struct nfs_page *req, struct list_head *dst,
spin_unlock(cinfo->lock);
if (!cinfo->dreq) {
inc_zone_page_state(req->wb_page, NR_UNSTABLE_NFS);
- inc_bdi_stat(page_file_mapping(req->wb_page)->backing_dev_info,
+ inc_bdi_stat(inode_to_bdi(page_file_mapping(req->wb_page)->host),
BDI_RECLAIMABLE);
__mark_inode_dirty(req->wb_context->dentry->d_inode,
I_DIRTY_DATASYNC);
@@ -853,7 +853,7 @@ static void
nfs_clear_page_commit(struct page *page)
{
dec_zone_page_state(page, NR_UNSTABLE_NFS);
- dec_bdi_stat(page_file_mapping(page)->backing_dev_info, BDI_RECLAIMABLE);
+ dec_bdi_stat(inode_to_bdi(page_file_mapping(page)->host), BDI_RECLAIMABLE);
}
/* Called holding inode (/cinfo) lock */
@@ -1564,7 +1564,7 @@ void nfs_retry_commit(struct list_head *page_list,
nfs_mark_request_commit(req, lseg, cinfo);
if (!cinfo->dreq) {
dec_zone_page_state(req->wb_page, NR_UNSTABLE_NFS);
- dec_bdi_stat(page_file_mapping(req->wb_page)->backing_dev_info,
+ dec_bdi_stat(inode_to_bdi(page_file_mapping(req->wb_page)->host),
BDI_RECLAIMABLE);
}
nfs_unlock_and_release_request(req);
diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c
index 643faa4..1da9b2d 100644
--- a/fs/ntfs/file.c
+++ b/fs/ntfs/file.c
@@ -19,6 +19,7 @@
* Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*/
+#include <linux/backing-dev.h>
#include <linux/buffer_head.h>
#include <linux/gfp.h>
#include <linux/pagemap.h>
@@ -2091,7 +2092,7 @@ static ssize_t ntfs_file_aio_write_nolock(struct kiocb *iocb,
count = iov_length(iov, nr_segs);
pos = *ppos;
/* We can write back this queue in page reclaim. */
- current->backing_dev_info = mapping->backing_dev_info;
+ current->backing_dev_info = inode_to_bdi(inode);
written = 0;
err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode));
if (err)
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 3950693..abe7d98 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -2363,7 +2363,7 @@ relock:
goto out_dio;
}
} else {
- current->backing_dev_info = file->f_mapping->backing_dev_info;
+ current->backing_dev_info = inode_to_bdi(inode);
written = generic_perform_write(file, from, *ppos);
if (likely(written >= 0))
iocb->ki_pos = *ppos + written;
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 13e974e..5684ac3 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -699,7 +699,7 @@ xfs_file_buffered_aio_write(
iov_iter_truncate(from, count);
/* We can write back this queue in page reclaim */
- current->backing_dev_info = mapping->backing_dev_info;
+ current->backing_dev_info = inode_to_bdi(inode);
write_retry:
trace_xfs_file_buffered_write(ip, count, iocb->ki_pos, 0);
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 478f95d..ed59dee 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -106,6 +106,8 @@ struct backing_dev_info {
#endif
};
+struct backing_dev_info *inode_to_bdi(struct inode *inode);
+
int __must_check bdi_init(struct backing_dev_info *bdi);
void bdi_destroy(struct backing_dev_info *bdi);
@@ -303,12 +305,12 @@ static inline bool bdi_cap_account_writeback(struct backing_dev_info *bdi)
static inline bool mapping_cap_writeback_dirty(struct address_space *mapping)
{
- return bdi_cap_writeback_dirty(mapping->backing_dev_info);
+ return bdi_cap_writeback_dirty(inode_to_bdi(mapping->host));
}
static inline bool mapping_cap_account_dirty(struct address_space *mapping)
{
- return bdi_cap_account_dirty(mapping->backing_dev_info);
+ return bdi_cap_account_dirty(inode_to_bdi(mapping->host));
}
static inline int bdi_sched_wait(void *word)
diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h
index cee02d6..74f5207 100644
--- a/include/trace/events/writeback.h
+++ b/include/trace/events/writeback.h
@@ -47,7 +47,7 @@ TRACE_EVENT(writeback_dirty_page,
TP_fast_assign(
strncpy(__entry->name,
- mapping ? dev_name(mapping->backing_dev_info->dev) : "(unknown)", 32);
+ mapping ? dev_name(inode_to_bdi(mapping->host)->dev) : "(unknown)", 32);
__entry->ino = mapping ? mapping->host->i_ino : 0;
__entry->index = page->index;
),
@@ -72,7 +72,7 @@ DECLARE_EVENT_CLASS(writeback_dirty_inode_template,
),
TP_fast_assign(
- struct backing_dev_info *bdi = inode->i_mapping->backing_dev_info;
+ struct backing_dev_info *bdi = inode_to_bdi(inode);
/* may be called for files on pseudo FSes w/ unregistered bdi */
strncpy(__entry->name,
@@ -116,7 +116,7 @@ DECLARE_EVENT_CLASS(writeback_write_inode_template,
TP_fast_assign(
strncpy(__entry->name,
- dev_name(inode->i_mapping->backing_dev_info->dev), 32);
+ dev_name(inode_to_bdi(inode)->dev), 32);
__entry->ino = inode->i_ino;
__entry->sync_mode = wbc->sync_mode;
),
diff --git a/mm/fadvise.c b/mm/fadvise.c
index 2ad7adf..fac23ec 100644
--- a/mm/fadvise.c
+++ b/mm/fadvise.c
@@ -73,7 +73,7 @@ SYSCALL_DEFINE4(fadvise64_64, int, fd, loff_t, offset, loff_t, len, int, advice)
else
endbyte--; /* inclusive */
- bdi = mapping->backing_dev_info;
+ bdi = inode_to_bdi(mapping->host);
switch (advice) {
case POSIX_FADV_NORMAL:
@@ -113,7 +113,7 @@ SYSCALL_DEFINE4(fadvise64_64, int, fd, loff_t, offset, loff_t, len, int, advice)
case POSIX_FADV_NOREUSE:
break;
case POSIX_FADV_DONTNEED:
- if (!bdi_write_congested(mapping->backing_dev_info))
+ if (!bdi_write_congested(bdi))
__filemap_fdatawrite_range(mapping, offset, endbyte,
WB_SYNC_NONE);
diff --git a/mm/filemap.c b/mm/filemap.c
index 673e458..5d7c23c 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -211,7 +211,7 @@ void __delete_from_page_cache(struct page *page, void *shadow)
*/
if (PageDirty(page) && mapping_cap_account_dirty(mapping)) {
dec_zone_page_state(page, NR_FILE_DIRTY);
- dec_bdi_stat(mapping->backing_dev_info, BDI_RECLAIMABLE);
+ dec_bdi_stat(inode_to_bdi(mapping->host), BDI_RECLAIMABLE);
}
}
@@ -2565,7 +2565,7 @@ ssize_t __generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
size_t count = iov_iter_count(from);
/* We can write back this queue in page reclaim */
- current->backing_dev_info = mapping->backing_dev_info;
+ current->backing_dev_info = inode_to_bdi(inode);
err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode));
if (err)
goto out;
diff --git a/mm/filemap_xip.c b/mm/filemap_xip.c
index 0d105ae..26897fb 100644
--- a/mm/filemap_xip.c
+++ b/mm/filemap_xip.c
@@ -9,6 +9,7 @@
*/
#include <linux/fs.h>
+#include <linux/backing-dev.h>
#include <linux/pagemap.h>
#include <linux/export.h>
#include <linux/uio.h>
@@ -410,7 +411,7 @@ xip_file_write(struct file *filp, const char __user *buf, size_t len,
count = len;
/* We can write back this queue in page reclaim */
- current->backing_dev_info = mapping->backing_dev_info;
+ current->backing_dev_info = inode_to_bdi(inode);
ret = generic_write_checks(filp, &pos, &count, S_ISBLK(inode->i_mode));
if (ret)
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 6f43352..d4cbb4b 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -1351,7 +1351,7 @@ static void balance_dirty_pages(struct address_space *mapping,
unsigned long task_ratelimit;
unsigned long dirty_ratelimit;
unsigned long pos_ratio;
- struct backing_dev_info *bdi = mapping->backing_dev_info;
+ struct backing_dev_info *bdi = inode_to_bdi(mapping->host);
bool strictlimit = bdi->capabilities & BDI_CAP_STRICTLIMIT;
unsigned long start_time = jiffies;
@@ -1574,7 +1574,7 @@ DEFINE_PER_CPU(int, dirty_throttle_leaks) = 0;
*/
void balance_dirty_pages_ratelimited(struct address_space *mapping)
{
- struct backing_dev_info *bdi = mapping->backing_dev_info;
+ struct backing_dev_info *bdi = inode_to_bdi(mapping->host);
int ratelimit;
int *p;
@@ -1929,7 +1929,7 @@ continue_unlock:
if (!clear_page_dirty_for_io(page))
goto continue_unlock;
- trace_wbc_writepage(wbc, mapping->backing_dev_info);
+ trace_wbc_writepage(wbc, inode_to_bdi(mapping->host));
ret = (*writepage)(page, wbc, data);
if (unlikely(ret)) {
if (ret == AOP_WRITEPAGE_ACTIVATE) {
@@ -2094,10 +2094,12 @@ void account_page_dirtied(struct page *page, struct address_space *mapping)
trace_writeback_dirty_page(page, mapping);
if (mapping_cap_account_dirty(mapping)) {
+ struct backing_dev_info *bdi = inode_to_bdi(mapping->host);
+
__inc_zone_page_state(page, NR_FILE_DIRTY);
__inc_zone_page_state(page, NR_DIRTIED);
- __inc_bdi_stat(mapping->backing_dev_info, BDI_RECLAIMABLE);
- __inc_bdi_stat(mapping->backing_dev_info, BDI_DIRTIED);
+ __inc_bdi_stat(bdi, BDI_RECLAIMABLE);
+ __inc_bdi_stat(bdi, BDI_DIRTIED);
task_io_account_write(PAGE_CACHE_SIZE);
current->nr_dirtied++;
this_cpu_inc(bdp_ratelimits);
@@ -2156,7 +2158,7 @@ void account_page_redirty(struct page *page)
if (mapping && mapping_cap_account_dirty(mapping)) {
current->nr_dirtied--;
dec_zone_page_state(page, NR_DIRTIED);
- dec_bdi_stat(mapping->backing_dev_info, BDI_DIRTIED);
+ dec_bdi_stat(inode_to_bdi(mapping->host), BDI_DIRTIED);
}
}
EXPORT_SYMBOL(account_page_redirty);
@@ -2295,7 +2297,7 @@ int clear_page_dirty_for_io(struct page *page)
*/
if (TestClearPageDirty(page)) {
dec_zone_page_state(page, NR_FILE_DIRTY);
- dec_bdi_stat(mapping->backing_dev_info,
+ dec_bdi_stat(inode_to_bdi(mapping->host),
BDI_RECLAIMABLE);
return 1;
}
@@ -2315,7 +2317,7 @@ int test_clear_page_writeback(struct page *page)
memcg = mem_cgroup_begin_page_stat(page, &locked, &memcg_flags);
if (mapping) {
- struct backing_dev_info *bdi = mapping->backing_dev_info;
+ struct backing_dev_info *bdi = inode_to_bdi(mapping->host);
unsigned long flags;
spin_lock_irqsave(&mapping->tree_lock, flags);
@@ -2352,7 +2354,7 @@ int __test_set_page_writeback(struct page *page, bool keep_write)
memcg = mem_cgroup_begin_page_stat(page, &locked, &memcg_flags);
if (mapping) {
- struct backing_dev_info *bdi = mapping->backing_dev_info;
+ struct backing_dev_info *bdi = inode_to_bdi(mapping->host);
unsigned long flags;
spin_lock_irqsave(&mapping->tree_lock, flags);
@@ -2406,12 +2408,7 @@ EXPORT_SYMBOL(mapping_tagged);
*/
void wait_for_stable_page(struct page *page)
{
- struct address_space *mapping = page_mapping(page);
- struct backing_dev_info *bdi = mapping->backing_dev_info;
-
- if (!bdi_cap_stable_pages_required(bdi))
- return;
-
- wait_on_page_writeback(page);
+ if (bdi_cap_stable_pages_required(inode_to_bdi(page->mapping->host)))
+ wait_on_page_writeback(page);
}
EXPORT_SYMBOL_GPL(wait_for_stable_page);
diff --git a/mm/readahead.c b/mm/readahead.c
index 17b9172..9356758 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -27,7 +27,7 @@
void
file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping)
{
- ra->ra_pages = mapping->backing_dev_info->ra_pages;
+ ra->ra_pages = inode_to_bdi(mapping->host)->ra_pages;
ra->prev_pos = -1;
}
EXPORT_SYMBOL_GPL(file_ra_state_init);
@@ -541,7 +541,7 @@ page_cache_async_readahead(struct address_space *mapping,
/*
* Defer asynchronous read-ahead on IO congestion.
*/
- if (bdi_read_congested(mapping->backing_dev_info))
+ if (bdi_read_congested(inode_to_bdi(mapping->host)))
return;
/* do read-ahead */
diff --git a/mm/truncate.c b/mm/truncate.c
index f1e4d60..ddec5a5 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -112,7 +112,7 @@ void cancel_dirty_page(struct page *page, unsigned int account_size)
struct address_space *mapping = page->mapping;
if (mapping && mapping_cap_account_dirty(mapping)) {
dec_zone_page_state(page, NR_FILE_DIRTY);
- dec_bdi_stat(mapping->backing_dev_info,
+ dec_bdi_stat(inode_to_bdi(mapping->host),
BDI_RECLAIMABLE);
if (account_size)
task_io_account_cancelled_write(account_size);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index ab2505c..e00a163 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -497,7 +497,7 @@ static pageout_t pageout(struct page *page, struct address_space *mapping,
}
if (mapping->a_ops->writepage == NULL)
return PAGE_ACTIVATE;
- if (!may_write_to_queue(mapping->backing_dev_info, sc))
+ if (!may_write_to_queue(inode_to_bdi(mapping->host), sc))
return PAGE_KEEP;
if (clear_page_dirty_for_io(page)) {
@@ -876,7 +876,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
*/
mapping = page_mapping(page);
if (((dirty || writeback) && mapping &&
- bdi_write_congested(mapping->backing_dev_info)) ||
+ bdi_write_congested(inode_to_bdi(mapping->host))) ||
(writeback && PageReclaim(page)))
nr_congested++;
--
1.9.1
On Wed 14-01-15 10:42:36, Christoph Hellwig wrote:
> Now that we got rid of the bdi abuse on character devices we can always use
> sb->s_bdi to get at the backing_dev_info for a file, except for the block
> device special case. Export inode_to_bdi and replace uses of
> mapping->backing_dev_info with it to prepare for the removal of
> mapping->backing_dev_info.
>
> Signed-off-by: Christoph Hellwig <[email protected]>
> Reviewed-by: Tejun Heo <[email protected]>
Looks good. You can add:
Reviewed-by: Jan Kara <[email protected]>
Honza
> ---
> fs/btrfs/file.c | 2 +-
> fs/ceph/file.c | 2 +-
> fs/ext2/ialloc.c | 2 +-
> fs/ext4/super.c | 2 +-
> fs/fs-writeback.c | 3 ++-
> fs/fuse/file.c | 10 +++++-----
> fs/gfs2/aops.c | 2 +-
> fs/gfs2/super.c | 2 +-
> fs/nfs/filelayout/filelayout.c | 2 +-
> fs/nfs/write.c | 6 +++---
> fs/ntfs/file.c | 3 ++-
> fs/ocfs2/file.c | 2 +-
> fs/xfs/xfs_file.c | 2 +-
> include/linux/backing-dev.h | 6 ++++--
> include/trace/events/writeback.h | 6 +++---
> mm/fadvise.c | 4 ++--
> mm/filemap.c | 4 ++--
> mm/filemap_xip.c | 3 ++-
> mm/page-writeback.c | 29 +++++++++++++----------------
> mm/readahead.c | 4 ++--
> mm/truncate.c | 2 +-
> mm/vmscan.c | 4 ++--
> 22 files changed, 52 insertions(+), 50 deletions(-)
>
> diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
> index e409025..835c04a 100644
> --- a/fs/btrfs/file.c
> +++ b/fs/btrfs/file.c
> @@ -1746,7 +1746,7 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
>
> mutex_lock(&inode->i_mutex);
>
> - current->backing_dev_info = inode->i_mapping->backing_dev_info;
> + current->backing_dev_info = inode_to_bdi(inode);
> err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode));
> if (err) {
> mutex_unlock(&inode->i_mutex);
> diff --git a/fs/ceph/file.c b/fs/ceph/file.c
> index ce74b39..905986d 100644
> --- a/fs/ceph/file.c
> +++ b/fs/ceph/file.c
> @@ -945,7 +945,7 @@ static ssize_t ceph_write_iter(struct kiocb *iocb, struct iov_iter *from)
> mutex_lock(&inode->i_mutex);
>
> /* We can write back this queue in page reclaim */
> - current->backing_dev_info = file->f_mapping->backing_dev_info;
> + current->backing_dev_info = inode_to_bdi(inode);
>
> err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode));
> if (err)
> diff --git a/fs/ext2/ialloc.c b/fs/ext2/ialloc.c
> index 7d66fb0..6c14bb8 100644
> --- a/fs/ext2/ialloc.c
> +++ b/fs/ext2/ialloc.c
> @@ -170,7 +170,7 @@ static void ext2_preread_inode(struct inode *inode)
> struct ext2_group_desc * gdp;
> struct backing_dev_info *bdi;
>
> - bdi = inode->i_mapping->backing_dev_info;
> + bdi = inode_to_bdi(inode);
> if (bdi_read_congested(bdi))
> return;
> if (bdi_write_congested(bdi))
> diff --git a/fs/ext4/super.c b/fs/ext4/super.c
> index 74c5f53..ad88e60 100644
> --- a/fs/ext4/super.c
> +++ b/fs/ext4/super.c
> @@ -334,7 +334,7 @@ static void save_error_info(struct super_block *sb, const char *func,
> static int block_device_ejected(struct super_block *sb)
> {
> struct inode *bd_inode = sb->s_bdev->bd_inode;
> - struct backing_dev_info *bdi = bd_inode->i_mapping->backing_dev_info;
> + struct backing_dev_info *bdi = inode_to_bdi(bd_inode);
>
> return bdi->dev == NULL;
> }
> diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
> index e8116a4..a20b114 100644
> --- a/fs/fs-writeback.c
> +++ b/fs/fs-writeback.c
> @@ -66,7 +66,7 @@ int writeback_in_progress(struct backing_dev_info *bdi)
> }
> EXPORT_SYMBOL(writeback_in_progress);
>
> -static inline struct backing_dev_info *inode_to_bdi(struct inode *inode)
> +struct backing_dev_info *inode_to_bdi(struct inode *inode)
> {
> struct super_block *sb = inode->i_sb;
> #ifdef CONFIG_BLOCK
> @@ -75,6 +75,7 @@ static inline struct backing_dev_info *inode_to_bdi(struct inode *inode)
> #endif
> return sb->s_bdi;
> }
> +EXPORT_SYMBOL_GPL(inode_to_bdi);
>
> static inline struct inode *wb_inode(struct list_head *head)
> {
> diff --git a/fs/fuse/file.c b/fs/fuse/file.c
> index 760b2c5..19d80b8 100644
> --- a/fs/fuse/file.c
> +++ b/fs/fuse/file.c
> @@ -1159,7 +1159,7 @@ static ssize_t fuse_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
> mutex_lock(&inode->i_mutex);
>
> /* We can write back this queue in page reclaim */
> - current->backing_dev_info = mapping->backing_dev_info;
> + current->backing_dev_info = inode_to_bdi(inode);
>
> err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode));
> if (err)
> @@ -1464,7 +1464,7 @@ static void fuse_writepage_finish(struct fuse_conn *fc, struct fuse_req *req)
> {
> struct inode *inode = req->inode;
> struct fuse_inode *fi = get_fuse_inode(inode);
> - struct backing_dev_info *bdi = inode->i_mapping->backing_dev_info;
> + struct backing_dev_info *bdi = inode_to_bdi(inode);
> int i;
>
> list_del(&req->writepages_entry);
> @@ -1658,7 +1658,7 @@ static int fuse_writepage_locked(struct page *page)
> req->end = fuse_writepage_end;
> req->inode = inode;
>
> - inc_bdi_stat(mapping->backing_dev_info, BDI_WRITEBACK);
> + inc_bdi_stat(inode_to_bdi(inode), BDI_WRITEBACK);
> inc_zone_page_state(tmp_page, NR_WRITEBACK_TEMP);
>
> spin_lock(&fc->lock);
> @@ -1768,7 +1768,7 @@ static bool fuse_writepage_in_flight(struct fuse_req *new_req,
>
> if (old_req->num_pages == 1 && (old_req->state == FUSE_REQ_INIT ||
> old_req->state == FUSE_REQ_PENDING)) {
> - struct backing_dev_info *bdi = page->mapping->backing_dev_info;
> + struct backing_dev_info *bdi = inode_to_bdi(page->mapping->host);
>
> copy_highpage(old_req->pages[0], page);
> spin_unlock(&fc->lock);
> @@ -1872,7 +1872,7 @@ static int fuse_writepages_fill(struct page *page,
> req->page_descs[req->num_pages].offset = 0;
> req->page_descs[req->num_pages].length = PAGE_SIZE;
>
> - inc_bdi_stat(page->mapping->backing_dev_info, BDI_WRITEBACK);
> + inc_bdi_stat(inode_to_bdi(inode), BDI_WRITEBACK);
> inc_zone_page_state(tmp_page, NR_WRITEBACK_TEMP);
>
> err = 0;
> diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
> index 805b37f..4ad4f94 100644
> --- a/fs/gfs2/aops.c
> +++ b/fs/gfs2/aops.c
> @@ -289,7 +289,7 @@ continue_unlock:
> if (!clear_page_dirty_for_io(page))
> goto continue_unlock;
>
> - trace_wbc_writepage(wbc, mapping->backing_dev_info);
> + trace_wbc_writepage(wbc, inode_to_bdi(inode));
>
> ret = __gfs2_jdata_writepage(page, wbc);
> if (unlikely(ret)) {
> diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
> index 5b327f8..1666382 100644
> --- a/fs/gfs2/super.c
> +++ b/fs/gfs2/super.c
> @@ -743,7 +743,7 @@ static int gfs2_write_inode(struct inode *inode, struct writeback_control *wbc)
> struct gfs2_inode *ip = GFS2_I(inode);
> struct gfs2_sbd *sdp = GFS2_SB(inode);
> struct address_space *metamapping = gfs2_glock2aspace(ip->i_gl);
> - struct backing_dev_info *bdi = metamapping->backing_dev_info;
> + struct backing_dev_info *bdi = inode_to_bdi(metamapping->host);
> int ret = 0;
>
> if (wbc->sync_mode == WB_SYNC_ALL)
> diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c
> index 7afb52f..51aa889 100644
> --- a/fs/nfs/filelayout/filelayout.c
> +++ b/fs/nfs/filelayout/filelayout.c
> @@ -1081,7 +1081,7 @@ mds_commit:
> spin_unlock(cinfo->lock);
> if (!cinfo->dreq) {
> inc_zone_page_state(req->wb_page, NR_UNSTABLE_NFS);
> - inc_bdi_stat(page_file_mapping(req->wb_page)->backing_dev_info,
> + inc_bdi_stat(inode_to_bdi(page_file_mapping(req->wb_page)->host),
> BDI_RECLAIMABLE);
> __mark_inode_dirty(req->wb_context->dentry->d_inode,
> I_DIRTY_DATASYNC);
> diff --git a/fs/nfs/write.c b/fs/nfs/write.c
> index af3af68..298abcc 100644
> --- a/fs/nfs/write.c
> +++ b/fs/nfs/write.c
> @@ -786,7 +786,7 @@ nfs_request_add_commit_list(struct nfs_page *req, struct list_head *dst,
> spin_unlock(cinfo->lock);
> if (!cinfo->dreq) {
> inc_zone_page_state(req->wb_page, NR_UNSTABLE_NFS);
> - inc_bdi_stat(page_file_mapping(req->wb_page)->backing_dev_info,
> + inc_bdi_stat(inode_to_bdi(page_file_mapping(req->wb_page)->host),
> BDI_RECLAIMABLE);
> __mark_inode_dirty(req->wb_context->dentry->d_inode,
> I_DIRTY_DATASYNC);
> @@ -853,7 +853,7 @@ static void
> nfs_clear_page_commit(struct page *page)
> {
> dec_zone_page_state(page, NR_UNSTABLE_NFS);
> - dec_bdi_stat(page_file_mapping(page)->backing_dev_info, BDI_RECLAIMABLE);
> + dec_bdi_stat(inode_to_bdi(page_file_mapping(page)->host), BDI_RECLAIMABLE);
> }
>
> /* Called holding inode (/cinfo) lock */
> @@ -1564,7 +1564,7 @@ void nfs_retry_commit(struct list_head *page_list,
> nfs_mark_request_commit(req, lseg, cinfo);
> if (!cinfo->dreq) {
> dec_zone_page_state(req->wb_page, NR_UNSTABLE_NFS);
> - dec_bdi_stat(page_file_mapping(req->wb_page)->backing_dev_info,
> + dec_bdi_stat(inode_to_bdi(page_file_mapping(req->wb_page)->host),
> BDI_RECLAIMABLE);
> }
> nfs_unlock_and_release_request(req);
> diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c
> index 643faa4..1da9b2d 100644
> --- a/fs/ntfs/file.c
> +++ b/fs/ntfs/file.c
> @@ -19,6 +19,7 @@
> * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
> */
>
> +#include <linux/backing-dev.h>
> #include <linux/buffer_head.h>
> #include <linux/gfp.h>
> #include <linux/pagemap.h>
> @@ -2091,7 +2092,7 @@ static ssize_t ntfs_file_aio_write_nolock(struct kiocb *iocb,
> count = iov_length(iov, nr_segs);
> pos = *ppos;
> /* We can write back this queue in page reclaim. */
> - current->backing_dev_info = mapping->backing_dev_info;
> + current->backing_dev_info = inode_to_bdi(inode);
> written = 0;
> err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode));
> if (err)
> diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
> index 3950693..abe7d98 100644
> --- a/fs/ocfs2/file.c
> +++ b/fs/ocfs2/file.c
> @@ -2363,7 +2363,7 @@ relock:
> goto out_dio;
> }
> } else {
> - current->backing_dev_info = file->f_mapping->backing_dev_info;
> + current->backing_dev_info = inode_to_bdi(inode);
> written = generic_perform_write(file, from, *ppos);
> if (likely(written >= 0))
> iocb->ki_pos = *ppos + written;
> diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
> index 13e974e..5684ac3 100644
> --- a/fs/xfs/xfs_file.c
> +++ b/fs/xfs/xfs_file.c
> @@ -699,7 +699,7 @@ xfs_file_buffered_aio_write(
>
> iov_iter_truncate(from, count);
> /* We can write back this queue in page reclaim */
> - current->backing_dev_info = mapping->backing_dev_info;
> + current->backing_dev_info = inode_to_bdi(inode);
>
> write_retry:
> trace_xfs_file_buffered_write(ip, count, iocb->ki_pos, 0);
> diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
> index 478f95d..ed59dee 100644
> --- a/include/linux/backing-dev.h
> +++ b/include/linux/backing-dev.h
> @@ -106,6 +106,8 @@ struct backing_dev_info {
> #endif
> };
>
> +struct backing_dev_info *inode_to_bdi(struct inode *inode);
> +
> int __must_check bdi_init(struct backing_dev_info *bdi);
> void bdi_destroy(struct backing_dev_info *bdi);
>
> @@ -303,12 +305,12 @@ static inline bool bdi_cap_account_writeback(struct backing_dev_info *bdi)
>
> static inline bool mapping_cap_writeback_dirty(struct address_space *mapping)
> {
> - return bdi_cap_writeback_dirty(mapping->backing_dev_info);
> + return bdi_cap_writeback_dirty(inode_to_bdi(mapping->host));
> }
>
> static inline bool mapping_cap_account_dirty(struct address_space *mapping)
> {
> - return bdi_cap_account_dirty(mapping->backing_dev_info);
> + return bdi_cap_account_dirty(inode_to_bdi(mapping->host));
> }
>
> static inline int bdi_sched_wait(void *word)
> diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h
> index cee02d6..74f5207 100644
> --- a/include/trace/events/writeback.h
> +++ b/include/trace/events/writeback.h
> @@ -47,7 +47,7 @@ TRACE_EVENT(writeback_dirty_page,
>
> TP_fast_assign(
> strncpy(__entry->name,
> - mapping ? dev_name(mapping->backing_dev_info->dev) : "(unknown)", 32);
> + mapping ? dev_name(inode_to_bdi(mapping->host)->dev) : "(unknown)", 32);
> __entry->ino = mapping ? mapping->host->i_ino : 0;
> __entry->index = page->index;
> ),
> @@ -72,7 +72,7 @@ DECLARE_EVENT_CLASS(writeback_dirty_inode_template,
> ),
>
> TP_fast_assign(
> - struct backing_dev_info *bdi = inode->i_mapping->backing_dev_info;
> + struct backing_dev_info *bdi = inode_to_bdi(inode);
>
> /* may be called for files on pseudo FSes w/ unregistered bdi */
> strncpy(__entry->name,
> @@ -116,7 +116,7 @@ DECLARE_EVENT_CLASS(writeback_write_inode_template,
>
> TP_fast_assign(
> strncpy(__entry->name,
> - dev_name(inode->i_mapping->backing_dev_info->dev), 32);
> + dev_name(inode_to_bdi(inode)->dev), 32);
> __entry->ino = inode->i_ino;
> __entry->sync_mode = wbc->sync_mode;
> ),
> diff --git a/mm/fadvise.c b/mm/fadvise.c
> index 2ad7adf..fac23ec 100644
> --- a/mm/fadvise.c
> +++ b/mm/fadvise.c
> @@ -73,7 +73,7 @@ SYSCALL_DEFINE4(fadvise64_64, int, fd, loff_t, offset, loff_t, len, int, advice)
> else
> endbyte--; /* inclusive */
>
> - bdi = mapping->backing_dev_info;
> + bdi = inode_to_bdi(mapping->host);
>
> switch (advice) {
> case POSIX_FADV_NORMAL:
> @@ -113,7 +113,7 @@ SYSCALL_DEFINE4(fadvise64_64, int, fd, loff_t, offset, loff_t, len, int, advice)
> case POSIX_FADV_NOREUSE:
> break;
> case POSIX_FADV_DONTNEED:
> - if (!bdi_write_congested(mapping->backing_dev_info))
> + if (!bdi_write_congested(bdi))
> __filemap_fdatawrite_range(mapping, offset, endbyte,
> WB_SYNC_NONE);
>
> diff --git a/mm/filemap.c b/mm/filemap.c
> index 673e458..5d7c23c 100644
> --- a/mm/filemap.c
> +++ b/mm/filemap.c
> @@ -211,7 +211,7 @@ void __delete_from_page_cache(struct page *page, void *shadow)
> */
> if (PageDirty(page) && mapping_cap_account_dirty(mapping)) {
> dec_zone_page_state(page, NR_FILE_DIRTY);
> - dec_bdi_stat(mapping->backing_dev_info, BDI_RECLAIMABLE);
> + dec_bdi_stat(inode_to_bdi(mapping->host), BDI_RECLAIMABLE);
> }
> }
>
> @@ -2565,7 +2565,7 @@ ssize_t __generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
> size_t count = iov_iter_count(from);
>
> /* We can write back this queue in page reclaim */
> - current->backing_dev_info = mapping->backing_dev_info;
> + current->backing_dev_info = inode_to_bdi(inode);
> err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode));
> if (err)
> goto out;
> diff --git a/mm/filemap_xip.c b/mm/filemap_xip.c
> index 0d105ae..26897fb 100644
> --- a/mm/filemap_xip.c
> +++ b/mm/filemap_xip.c
> @@ -9,6 +9,7 @@
> */
>
> #include <linux/fs.h>
> +#include <linux/backing-dev.h>
> #include <linux/pagemap.h>
> #include <linux/export.h>
> #include <linux/uio.h>
> @@ -410,7 +411,7 @@ xip_file_write(struct file *filp, const char __user *buf, size_t len,
> count = len;
>
> /* We can write back this queue in page reclaim */
> - current->backing_dev_info = mapping->backing_dev_info;
> + current->backing_dev_info = inode_to_bdi(inode);
>
> ret = generic_write_checks(filp, &pos, &count, S_ISBLK(inode->i_mode));
> if (ret)
> diff --git a/mm/page-writeback.c b/mm/page-writeback.c
> index 6f43352..d4cbb4b 100644
> --- a/mm/page-writeback.c
> +++ b/mm/page-writeback.c
> @@ -1351,7 +1351,7 @@ static void balance_dirty_pages(struct address_space *mapping,
> unsigned long task_ratelimit;
> unsigned long dirty_ratelimit;
> unsigned long pos_ratio;
> - struct backing_dev_info *bdi = mapping->backing_dev_info;
> + struct backing_dev_info *bdi = inode_to_bdi(mapping->host);
> bool strictlimit = bdi->capabilities & BDI_CAP_STRICTLIMIT;
> unsigned long start_time = jiffies;
>
> @@ -1574,7 +1574,7 @@ DEFINE_PER_CPU(int, dirty_throttle_leaks) = 0;
> */
> void balance_dirty_pages_ratelimited(struct address_space *mapping)
> {
> - struct backing_dev_info *bdi = mapping->backing_dev_info;
> + struct backing_dev_info *bdi = inode_to_bdi(mapping->host);
> int ratelimit;
> int *p;
>
> @@ -1929,7 +1929,7 @@ continue_unlock:
> if (!clear_page_dirty_for_io(page))
> goto continue_unlock;
>
> - trace_wbc_writepage(wbc, mapping->backing_dev_info);
> + trace_wbc_writepage(wbc, inode_to_bdi(mapping->host));
> ret = (*writepage)(page, wbc, data);
> if (unlikely(ret)) {
> if (ret == AOP_WRITEPAGE_ACTIVATE) {
> @@ -2094,10 +2094,12 @@ void account_page_dirtied(struct page *page, struct address_space *mapping)
> trace_writeback_dirty_page(page, mapping);
>
> if (mapping_cap_account_dirty(mapping)) {
> + struct backing_dev_info *bdi = inode_to_bdi(mapping->host);
> +
> __inc_zone_page_state(page, NR_FILE_DIRTY);
> __inc_zone_page_state(page, NR_DIRTIED);
> - __inc_bdi_stat(mapping->backing_dev_info, BDI_RECLAIMABLE);
> - __inc_bdi_stat(mapping->backing_dev_info, BDI_DIRTIED);
> + __inc_bdi_stat(bdi, BDI_RECLAIMABLE);
> + __inc_bdi_stat(bdi, BDI_DIRTIED);
> task_io_account_write(PAGE_CACHE_SIZE);
> current->nr_dirtied++;
> this_cpu_inc(bdp_ratelimits);
> @@ -2156,7 +2158,7 @@ void account_page_redirty(struct page *page)
> if (mapping && mapping_cap_account_dirty(mapping)) {
> current->nr_dirtied--;
> dec_zone_page_state(page, NR_DIRTIED);
> - dec_bdi_stat(mapping->backing_dev_info, BDI_DIRTIED);
> + dec_bdi_stat(inode_to_bdi(mapping->host), BDI_DIRTIED);
> }
> }
> EXPORT_SYMBOL(account_page_redirty);
> @@ -2295,7 +2297,7 @@ int clear_page_dirty_for_io(struct page *page)
> */
> if (TestClearPageDirty(page)) {
> dec_zone_page_state(page, NR_FILE_DIRTY);
> - dec_bdi_stat(mapping->backing_dev_info,
> + dec_bdi_stat(inode_to_bdi(mapping->host),
> BDI_RECLAIMABLE);
> return 1;
> }
> @@ -2315,7 +2317,7 @@ int test_clear_page_writeback(struct page *page)
>
> memcg = mem_cgroup_begin_page_stat(page, &locked, &memcg_flags);
> if (mapping) {
> - struct backing_dev_info *bdi = mapping->backing_dev_info;
> + struct backing_dev_info *bdi = inode_to_bdi(mapping->host);
> unsigned long flags;
>
> spin_lock_irqsave(&mapping->tree_lock, flags);
> @@ -2352,7 +2354,7 @@ int __test_set_page_writeback(struct page *page, bool keep_write)
>
> memcg = mem_cgroup_begin_page_stat(page, &locked, &memcg_flags);
> if (mapping) {
> - struct backing_dev_info *bdi = mapping->backing_dev_info;
> + struct backing_dev_info *bdi = inode_to_bdi(mapping->host);
> unsigned long flags;
>
> spin_lock_irqsave(&mapping->tree_lock, flags);
> @@ -2406,12 +2408,7 @@ EXPORT_SYMBOL(mapping_tagged);
> */
> void wait_for_stable_page(struct page *page)
> {
> - struct address_space *mapping = page_mapping(page);
> - struct backing_dev_info *bdi = mapping->backing_dev_info;
> -
> - if (!bdi_cap_stable_pages_required(bdi))
> - return;
> -
> - wait_on_page_writeback(page);
> + if (bdi_cap_stable_pages_required(inode_to_bdi(page->mapping->host)))
> + wait_on_page_writeback(page);
> }
> EXPORT_SYMBOL_GPL(wait_for_stable_page);
> diff --git a/mm/readahead.c b/mm/readahead.c
> index 17b9172..9356758 100644
> --- a/mm/readahead.c
> +++ b/mm/readahead.c
> @@ -27,7 +27,7 @@
> void
> file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping)
> {
> - ra->ra_pages = mapping->backing_dev_info->ra_pages;
> + ra->ra_pages = inode_to_bdi(mapping->host)->ra_pages;
> ra->prev_pos = -1;
> }
> EXPORT_SYMBOL_GPL(file_ra_state_init);
> @@ -541,7 +541,7 @@ page_cache_async_readahead(struct address_space *mapping,
> /*
> * Defer asynchronous read-ahead on IO congestion.
> */
> - if (bdi_read_congested(mapping->backing_dev_info))
> + if (bdi_read_congested(inode_to_bdi(mapping->host)))
> return;
>
> /* do read-ahead */
> diff --git a/mm/truncate.c b/mm/truncate.c
> index f1e4d60..ddec5a5 100644
> --- a/mm/truncate.c
> +++ b/mm/truncate.c
> @@ -112,7 +112,7 @@ void cancel_dirty_page(struct page *page, unsigned int account_size)
> struct address_space *mapping = page->mapping;
> if (mapping && mapping_cap_account_dirty(mapping)) {
> dec_zone_page_state(page, NR_FILE_DIRTY);
> - dec_bdi_stat(mapping->backing_dev_info,
> + dec_bdi_stat(inode_to_bdi(mapping->host),
> BDI_RECLAIMABLE);
> if (account_size)
> task_io_account_cancelled_write(account_size);
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index ab2505c..e00a163 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -497,7 +497,7 @@ static pageout_t pageout(struct page *page, struct address_space *mapping,
> }
> if (mapping->a_ops->writepage == NULL)
> return PAGE_ACTIVATE;
> - if (!may_write_to_queue(mapping->backing_dev_info, sc))
> + if (!may_write_to_queue(inode_to_bdi(mapping->host), sc))
> return PAGE_KEEP;
>
> if (clear_page_dirty_for_io(page)) {
> @@ -876,7 +876,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
> */
> mapping = page_mapping(page);
> if (((dirty || writeback) && mapping &&
> - bdi_write_congested(mapping->backing_dev_info)) ||
> + bdi_write_congested(inode_to_bdi(mapping->host))) ||
> (writeback && PageReclaim(page)))
> nr_congested++;
>
> --
> 1.9.1
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
> the body of a message to [email protected]
> More majordomo info at http://vger.kernel.org/majordomo-info.html
--
Jan Kara <[email protected]>
SUSE Labs, CR
Now that we never use the backing_dev_info pointer in struct address_space
we can simply remove it and save 4 to 8 bytes in every inode.
Signed-off-by: Christoph Hellwig <[email protected]>
Acked-by: Ryusuke Konishi <[email protected]>
Reviewed-by: Tejun Heo <[email protected]>
---
drivers/char/raw.c | 4 +---
fs/aio.c | 1 -
fs/block_dev.c | 26 +-------------------------
fs/btrfs/disk-io.c | 1 -
fs/btrfs/inode.c | 6 ------
fs/ceph/inode.c | 2 --
fs/cifs/inode.c | 2 --
fs/configfs/inode.c | 1 -
fs/ecryptfs/inode.c | 1 -
fs/exofs/inode.c | 2 --
fs/fuse/inode.c | 1 -
fs/gfs2/glock.c | 1 -
fs/gfs2/ops_fstype.c | 1 -
fs/hugetlbfs/inode.c | 1 -
fs/inode.c | 13 -------------
fs/kernfs/inode.c | 1 -
fs/ncpfs/inode.c | 1 -
fs/nfs/inode.c | 1 -
fs/nilfs2/gcinode.c | 1 -
fs/nilfs2/mdt.c | 6 ++----
fs/nilfs2/page.c | 4 +---
fs/nilfs2/page.h | 3 +--
fs/nilfs2/super.c | 2 +-
fs/ocfs2/dlmfs/dlmfs.c | 2 --
fs/ramfs/inode.c | 1 -
fs/romfs/super.c | 3 ---
fs/ubifs/dir.c | 2 --
fs/ubifs/super.c | 3 ---
include/linux/fs.h | 3 +--
mm/backing-dev.c | 1 -
mm/shmem.c | 1 -
mm/swap_state.c | 1 -
32 files changed, 8 insertions(+), 91 deletions(-)
diff --git a/drivers/char/raw.c b/drivers/char/raw.c
index a24891b..6e29bf2 100644
--- a/drivers/char/raw.c
+++ b/drivers/char/raw.c
@@ -104,11 +104,9 @@ static int raw_release(struct inode *inode, struct file *filp)
mutex_lock(&raw_mutex);
bdev = raw_devices[minor].binding;
- if (--raw_devices[minor].inuse == 0) {
+ if (--raw_devices[minor].inuse == 0)
/* Here inode->i_mapping == bdev->bd_inode->i_mapping */
inode->i_mapping = &inode->i_data;
- inode->i_mapping->backing_dev_info = &default_backing_dev_info;
- }
mutex_unlock(&raw_mutex);
blkdev_put(bdev, filp->f_mode | FMODE_EXCL);
diff --git a/fs/aio.c b/fs/aio.c
index 6f13d3f..3bf8b1d 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -176,7 +176,6 @@ static struct file *aio_private_file(struct kioctx *ctx, loff_t nr_pages)
inode->i_mapping->a_ops = &aio_ctx_aops;
inode->i_mapping->private_data = ctx;
- inode->i_mapping->backing_dev_info = &noop_backing_dev_info;
inode->i_size = PAGE_SIZE * nr_pages;
path.dentry = d_alloc_pseudo(aio_mnt->mnt_sb, &this);
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 026ca7b..a9f9279 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -60,19 +60,6 @@ static void bdev_write_inode(struct inode *inode)
spin_unlock(&inode->i_lock);
}
-/*
- * Move the inode from its current bdi to a new bdi. Make sure the inode
- * is clean before moving so that it doesn't linger on the old bdi.
- */
-static void bdev_inode_switch_bdi(struct inode *inode,
- struct backing_dev_info *dst)
-{
- spin_lock(&inode->i_lock);
- WARN_ON_ONCE(inode->i_state & I_DIRTY);
- inode->i_data.backing_dev_info = dst;
- spin_unlock(&inode->i_lock);
-}
-
/* Kill _all_ buffers and pagecache , dirty or not.. */
void kill_bdev(struct block_device *bdev)
{
@@ -589,7 +576,6 @@ struct block_device *bdget(dev_t dev)
inode->i_bdev = bdev;
inode->i_data.a_ops = &def_blk_aops;
mapping_set_gfp_mask(&inode->i_data, GFP_USER);
- inode->i_data.backing_dev_info = &default_backing_dev_info;
spin_lock(&bdev_lock);
list_add(&bdev->bd_list, &all_bdevs);
spin_unlock(&bdev_lock);
@@ -1150,8 +1136,6 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
bdev->bd_queue = disk->queue;
bdev->bd_contains = bdev;
if (!partno) {
- struct backing_dev_info *bdi;
-
ret = -ENXIO;
bdev->bd_part = disk_get_part(disk, partno);
if (!bdev->bd_part)
@@ -1177,11 +1161,8 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
}
}
- if (!ret) {
+ if (!ret)
bd_set_size(bdev,(loff_t)get_capacity(disk)<<9);
- bdi = blk_get_backing_dev_info(bdev);
- bdev_inode_switch_bdi(bdev->bd_inode, bdi);
- }
/*
* If the device is invalidated, rescan partition
@@ -1208,8 +1189,6 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
if (ret)
goto out_clear;
bdev->bd_contains = whole;
- bdev_inode_switch_bdi(bdev->bd_inode,
- whole->bd_inode->i_data.backing_dev_info);
bdev->bd_part = disk_get_part(disk, partno);
if (!(disk->flags & GENHD_FL_UP) ||
!bdev->bd_part || !bdev->bd_part->nr_sects) {
@@ -1249,7 +1228,6 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
bdev->bd_disk = NULL;
bdev->bd_part = NULL;
bdev->bd_queue = NULL;
- bdev_inode_switch_bdi(bdev->bd_inode, &default_backing_dev_info);
if (bdev != bdev->bd_contains)
__blkdev_put(bdev->bd_contains, mode, 1);
bdev->bd_contains = NULL;
@@ -1474,8 +1452,6 @@ static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part)
* dirty data before.
*/
bdev_write_inode(bdev->bd_inode);
- bdev_inode_switch_bdi(bdev->bd_inode,
- &default_backing_dev_info);
}
if (bdev->bd_contains == bdev) {
if (disk->fops->release)
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index afc4092..1ec872e 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -2318,7 +2318,6 @@ int open_ctree(struct super_block *sb,
*/
fs_info->btree_inode->i_size = OFFSET_MAX;
fs_info->btree_inode->i_mapping->a_ops = &btree_aops;
- fs_info->btree_inode->i_mapping->backing_dev_info = &fs_info->bdi;
RB_CLEAR_NODE(&BTRFS_I(fs_info->btree_inode)->rb_node);
extent_io_tree_init(&BTRFS_I(fs_info->btree_inode)->io_tree,
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 8bf326a..54bcf63 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -3608,7 +3608,6 @@ cache_acl:
switch (inode->i_mode & S_IFMT) {
case S_IFREG:
inode->i_mapping->a_ops = &btrfs_aops;
- inode->i_mapping->backing_dev_info = &root->fs_info->bdi;
BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
inode->i_fop = &btrfs_file_operations;
inode->i_op = &btrfs_file_inode_operations;
@@ -3623,7 +3622,6 @@ cache_acl:
case S_IFLNK:
inode->i_op = &btrfs_symlink_inode_operations;
inode->i_mapping->a_ops = &btrfs_symlink_aops;
- inode->i_mapping->backing_dev_info = &root->fs_info->bdi;
break;
default:
inode->i_op = &btrfs_special_inode_operations;
@@ -6088,7 +6086,6 @@ static int btrfs_create(struct inode *dir, struct dentry *dentry,
inode->i_fop = &btrfs_file_operations;
inode->i_op = &btrfs_file_inode_operations;
inode->i_mapping->a_ops = &btrfs_aops;
- inode->i_mapping->backing_dev_info = &root->fs_info->bdi;
err = btrfs_init_inode_security(trans, inode, dir, &dentry->d_name);
if (err)
@@ -9203,7 +9200,6 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
inode->i_fop = &btrfs_file_operations;
inode->i_op = &btrfs_file_inode_operations;
inode->i_mapping->a_ops = &btrfs_aops;
- inode->i_mapping->backing_dev_info = &root->fs_info->bdi;
BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
err = btrfs_init_inode_security(trans, inode, dir, &dentry->d_name);
@@ -9247,7 +9243,6 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
inode->i_op = &btrfs_symlink_inode_operations;
inode->i_mapping->a_ops = &btrfs_symlink_aops;
- inode->i_mapping->backing_dev_info = &root->fs_info->bdi;
inode_set_bytes(inode, name_len);
btrfs_i_size_write(inode, name_len);
err = btrfs_update_inode(trans, root, inode);
@@ -9459,7 +9454,6 @@ static int btrfs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
inode->i_op = &btrfs_file_inode_operations;
inode->i_mapping->a_ops = &btrfs_aops;
- inode->i_mapping->backing_dev_info = &root->fs_info->bdi;
BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
ret = btrfs_init_inode_security(trans, inode, dir, NULL);
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index f61a741..6b51736 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -783,8 +783,6 @@ static int fill_inode(struct inode *inode, struct page *locked_page,
}
inode->i_mapping->a_ops = &ceph_aops;
- inode->i_mapping->backing_dev_info =
- &ceph_sb_to_client(inode->i_sb)->backing_dev_info;
switch (inode->i_mode & S_IFMT) {
case S_IFIFO:
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 0c3ce464..2d4f372 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -937,8 +937,6 @@ retry_iget5_locked:
inode->i_flags |= S_NOATIME | S_NOCMTIME;
if (inode->i_state & I_NEW) {
inode->i_ino = hash;
- if (S_ISREG(inode->i_mode))
- inode->i_data.backing_dev_info = sb->s_bdi;
#ifdef CONFIG_CIFS_FSCACHE
/* initialize per-inode cache cookie pointer */
CIFS_I(inode)->fscache = NULL;
diff --git a/fs/configfs/inode.c b/fs/configfs/inode.c
index 0ad6b4d..65af861 100644
--- a/fs/configfs/inode.c
+++ b/fs/configfs/inode.c
@@ -131,7 +131,6 @@ struct inode *configfs_new_inode(umode_t mode, struct configfs_dirent *sd,
if (inode) {
inode->i_ino = get_next_ino();
inode->i_mapping->a_ops = &configfs_aops;
- inode->i_mapping->backing_dev_info = &noop_backing_dev_info;
inode->i_op = &configfs_inode_operations;
if (sd->s_iattr) {
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index 1686dc2..34b36a5 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -67,7 +67,6 @@ static int ecryptfs_inode_set(struct inode *inode, void *opaque)
inode->i_ino = lower_inode->i_ino;
inode->i_version++;
inode->i_mapping->a_ops = &ecryptfs_aops;
- inode->i_mapping->backing_dev_info = inode->i_sb->s_bdi;
if (S_ISLNK(inode->i_mode))
inode->i_op = &ecryptfs_symlink_iops;
diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c
index f1d3d4e..6fc91df 100644
--- a/fs/exofs/inode.c
+++ b/fs/exofs/inode.c
@@ -1214,7 +1214,6 @@ struct inode *exofs_iget(struct super_block *sb, unsigned long ino)
memcpy(oi->i_data, fcb.i_data, sizeof(fcb.i_data));
}
- inode->i_mapping->backing_dev_info = sb->s_bdi;
if (S_ISREG(inode->i_mode)) {
inode->i_op = &exofs_file_inode_operations;
inode->i_fop = &exofs_file_operations;
@@ -1314,7 +1313,6 @@ struct inode *exofs_new_inode(struct inode *dir, umode_t mode)
set_obj_2bcreated(oi);
- inode->i_mapping->backing_dev_info = sb->s_bdi;
inode_init_owner(inode, dir, mode);
inode->i_ino = sbi->s_nextid++;
inode->i_blkbits = EXOFS_BLKSHIFT;
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 6749109..ea0aacd 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -308,7 +308,6 @@ struct inode *fuse_iget(struct super_block *sb, u64 nodeid,
if (!fc->writeback_cache || !S_ISREG(attr->mode))
inode->i_flags |= S_NOCMTIME;
inode->i_generation = generation;
- inode->i_data.backing_dev_info = &fc->bdi;
fuse_init_inode(inode, attr);
unlock_new_inode(inode);
} else if ((inode->i_mode ^ attr->mode) & S_IFMT) {
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index a23524a..08ea717 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -775,7 +775,6 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number,
mapping->flags = 0;
mapping_set_gfp_mask(mapping, GFP_NOFS);
mapping->private_data = NULL;
- mapping->backing_dev_info = s->s_bdi;
mapping->writeback_index = 0;
}
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index 8633ad3..efc8e25 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -112,7 +112,6 @@ static struct gfs2_sbd *init_sbd(struct super_block *sb)
mapping->flags = 0;
mapping_set_gfp_mask(mapping, GFP_NOFS);
mapping->private_data = NULL;
- mapping->backing_dev_info = sb->s_bdi;
mapping->writeback_index = 0;
spin_lock_init(&sdp->sd_log_lock);
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index de7c95c..c274aca 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -492,7 +492,6 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb,
lockdep_set_class(&inode->i_mapping->i_mmap_rwsem,
&hugetlbfs_i_mmap_rwsem_key);
inode->i_mapping->a_ops = &hugetlbfs_aops;
- inode->i_mapping->backing_dev_info = &noop_backing_dev_info;
inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
inode->i_mapping->private_data = resv_map;
info = HUGETLBFS_I(inode);
diff --git a/fs/inode.c b/fs/inode.c
index aa149e7..e4e8caa 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -170,20 +170,7 @@ int inode_init_always(struct super_block *sb, struct inode *inode)
atomic_set(&mapping->i_mmap_writable, 0);
mapping_set_gfp_mask(mapping, GFP_HIGHUSER_MOVABLE);
mapping->private_data = NULL;
- mapping->backing_dev_info = &default_backing_dev_info;
mapping->writeback_index = 0;
-
- /*
- * If the block_device provides a backing_dev_info for client
- * inodes then use that. Otherwise the inode share the bdev's
- * backing_dev_info.
- */
- if (sb->s_bdev) {
- struct backing_dev_info *bdi;
-
- bdi = sb->s_bdev->bd_inode->i_mapping->backing_dev_info;
- mapping->backing_dev_info = bdi;
- }
inode->i_private = NULL;
inode->i_mapping = mapping;
INIT_HLIST_HEAD(&inode->i_dentry); /* buggered by rcu freeing */
diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c
index 06f0688..9000874 100644
--- a/fs/kernfs/inode.c
+++ b/fs/kernfs/inode.c
@@ -286,7 +286,6 @@ static void kernfs_init_inode(struct kernfs_node *kn, struct inode *inode)
kernfs_get(kn);
inode->i_private = kn;
inode->i_mapping->a_ops = &kernfs_aops;
- inode->i_mapping->backing_dev_info = &noop_backing_dev_info;
inode->i_op = &kernfs_iops;
set_default_inode_attr(inode, kn->mode);
diff --git a/fs/ncpfs/inode.c b/fs/ncpfs/inode.c
index a699a3f..01a9e16 100644
--- a/fs/ncpfs/inode.c
+++ b/fs/ncpfs/inode.c
@@ -267,7 +267,6 @@ ncp_iget(struct super_block *sb, struct ncp_entry_info *info)
if (inode) {
atomic_set(&NCP_FINFO(inode)->opened, info->opened);
- inode->i_mapping->backing_dev_info = sb->s_bdi;
inode->i_ino = info->ino;
ncp_set_attr(inode, info);
if (S_ISREG(inode->i_mode)) {
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 4bffe63..24aac72 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -387,7 +387,6 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, st
if (S_ISREG(inode->i_mode)) {
inode->i_fop = NFS_SB(sb)->nfs_client->rpc_ops->file_ops;
inode->i_data.a_ops = &nfs_file_aops;
- inode->i_data.backing_dev_info = &NFS_SB(sb)->backing_dev_info;
} else if (S_ISDIR(inode->i_mode)) {
inode->i_op = NFS_SB(sb)->nfs_client->rpc_ops->dir_inode_ops;
inode->i_fop = &nfs_dir_operations;
diff --git a/fs/nilfs2/gcinode.c b/fs/nilfs2/gcinode.c
index 57ceaf3..748ca23 100644
--- a/fs/nilfs2/gcinode.c
+++ b/fs/nilfs2/gcinode.c
@@ -172,7 +172,6 @@ int nilfs_init_gcinode(struct inode *inode)
inode->i_mode = S_IFREG;
mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS);
inode->i_mapping->a_ops = &empty_aops;
- inode->i_mapping->backing_dev_info = inode->i_sb->s_bdi;
ii->i_flags = 0;
nilfs_bmap_init_gc(ii->i_bmap);
diff --git a/fs/nilfs2/mdt.c b/fs/nilfs2/mdt.c
index c4dcd1d..892cf5f 100644
--- a/fs/nilfs2/mdt.c
+++ b/fs/nilfs2/mdt.c
@@ -429,7 +429,6 @@ int nilfs_mdt_init(struct inode *inode, gfp_t gfp_mask, size_t objsz)
inode->i_mode = S_IFREG;
mapping_set_gfp_mask(inode->i_mapping, gfp_mask);
- inode->i_mapping->backing_dev_info = inode->i_sb->s_bdi;
inode->i_op = &def_mdt_iops;
inode->i_fop = &def_mdt_fops;
@@ -457,13 +456,12 @@ int nilfs_mdt_setup_shadow_map(struct inode *inode,
struct nilfs_shadow_map *shadow)
{
struct nilfs_mdt_info *mi = NILFS_MDT(inode);
- struct backing_dev_info *bdi = inode->i_sb->s_bdi;
INIT_LIST_HEAD(&shadow->frozen_buffers);
address_space_init_once(&shadow->frozen_data);
- nilfs_mapping_init(&shadow->frozen_data, inode, bdi);
+ nilfs_mapping_init(&shadow->frozen_data, inode);
address_space_init_once(&shadow->frozen_btnodes);
- nilfs_mapping_init(&shadow->frozen_btnodes, inode, bdi);
+ nilfs_mapping_init(&shadow->frozen_btnodes, inode);
mi->mi_shadow = shadow;
return 0;
}
diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c
index da27664..700ecbc 100644
--- a/fs/nilfs2/page.c
+++ b/fs/nilfs2/page.c
@@ -461,14 +461,12 @@ unsigned nilfs_page_count_clean_buffers(struct page *page,
return nc;
}
-void nilfs_mapping_init(struct address_space *mapping, struct inode *inode,
- struct backing_dev_info *bdi)
+void nilfs_mapping_init(struct address_space *mapping, struct inode *inode)
{
mapping->host = inode;
mapping->flags = 0;
mapping_set_gfp_mask(mapping, GFP_NOFS);
mapping->private_data = NULL;
- mapping->backing_dev_info = bdi;
mapping->a_ops = &empty_aops;
}
diff --git a/fs/nilfs2/page.h b/fs/nilfs2/page.h
index ef30c5c..a43b828 100644
--- a/fs/nilfs2/page.h
+++ b/fs/nilfs2/page.h
@@ -57,8 +57,7 @@ int nilfs_copy_dirty_pages(struct address_space *, struct address_space *);
void nilfs_copy_back_pages(struct address_space *, struct address_space *);
void nilfs_clear_dirty_page(struct page *, bool);
void nilfs_clear_dirty_pages(struct address_space *, bool);
-void nilfs_mapping_init(struct address_space *mapping, struct inode *inode,
- struct backing_dev_info *bdi);
+void nilfs_mapping_init(struct address_space *mapping, struct inode *inode);
unsigned nilfs_page_count_clean_buffers(struct page *, unsigned, unsigned);
unsigned long nilfs_find_uncommitted_extent(struct inode *inode,
sector_t start_blk,
diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c
index 3d4bbac..5bc2a1c 100644
--- a/fs/nilfs2/super.c
+++ b/fs/nilfs2/super.c
@@ -166,7 +166,7 @@ struct inode *nilfs_alloc_inode(struct super_block *sb)
ii->i_state = 0;
ii->i_cno = 0;
ii->vfs_inode.i_version = 1;
- nilfs_mapping_init(&ii->i_btnode_cache, &ii->vfs_inode, sb->s_bdi);
+ nilfs_mapping_init(&ii->i_btnode_cache, &ii->vfs_inode);
return &ii->vfs_inode;
}
diff --git a/fs/ocfs2/dlmfs/dlmfs.c b/fs/ocfs2/dlmfs/dlmfs.c
index 6000d30..061ba6a 100644
--- a/fs/ocfs2/dlmfs/dlmfs.c
+++ b/fs/ocfs2/dlmfs/dlmfs.c
@@ -398,7 +398,6 @@ static struct inode *dlmfs_get_root_inode(struct super_block *sb)
if (inode) {
inode->i_ino = get_next_ino();
inode_init_owner(inode, NULL, mode);
- inode->i_mapping->backing_dev_info = &noop_backing_dev_info;
inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
inc_nlink(inode);
@@ -422,7 +421,6 @@ static struct inode *dlmfs_get_inode(struct inode *parent,
inode->i_ino = get_next_ino();
inode_init_owner(inode, parent, mode);
- inode->i_mapping->backing_dev_info = &noop_backing_dev_info;
inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
ip = DLMFS_I(inode);
diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c
index ad4d712..889d558 100644
--- a/fs/ramfs/inode.c
+++ b/fs/ramfs/inode.c
@@ -59,7 +59,6 @@ struct inode *ramfs_get_inode(struct super_block *sb,
inode->i_ino = get_next_ino();
inode_init_owner(inode, dir, mode);
inode->i_mapping->a_ops = &ramfs_aops;
- inode->i_mapping->backing_dev_info = &noop_backing_dev_info;
mapping_set_gfp_mask(inode->i_mapping, GFP_HIGHUSER);
mapping_set_unevictable(inode->i_mapping);
inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
diff --git a/fs/romfs/super.c b/fs/romfs/super.c
index e98dd88..268733c 100644
--- a/fs/romfs/super.c
+++ b/fs/romfs/super.c
@@ -355,9 +355,6 @@ static struct inode *romfs_iget(struct super_block *sb, unsigned long pos)
case ROMFH_REG:
i->i_fop = &romfs_ro_fops;
i->i_data.a_ops = &romfs_aops;
- if (i->i_sb->s_mtd)
- i->i_data.backing_dev_info =
- i->i_sb->s_mtd->backing_dev_info;
if (nextfh & ROMFH_EXEC)
mode |= S_IXUGO;
break;
diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c
index ea41649..c49b198 100644
--- a/fs/ubifs/dir.c
+++ b/fs/ubifs/dir.c
@@ -108,8 +108,6 @@ struct inode *ubifs_new_inode(struct ubifs_info *c, const struct inode *dir,
inode->i_mtime = inode->i_atime = inode->i_ctime =
ubifs_current_time(inode);
inode->i_mapping->nrpages = 0;
- /* Disable readahead */
- inode->i_mapping->backing_dev_info = &c->bdi;
switch (mode & S_IFMT) {
case S_IFREG:
diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c
index ed93dc6..6197154 100644
--- a/fs/ubifs/super.c
+++ b/fs/ubifs/super.c
@@ -156,9 +156,6 @@ struct inode *ubifs_iget(struct super_block *sb, unsigned long inum)
if (err)
goto out_invalid;
- /* Disable read-ahead */
- inode->i_mapping->backing_dev_info = &c->bdi;
-
switch (inode->i_mode & S_IFMT) {
case S_IFREG:
inode->i_mapping->a_ops = &ubifs_file_address_operations;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 1dada39..65d02de 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -34,6 +34,7 @@
#include <asm/byteorder.h>
#include <uapi/linux/fs.h>
+struct backing_dev_info;
struct export_operations;
struct hd_geometry;
struct iovec;
@@ -394,7 +395,6 @@ int pagecache_write_end(struct file *, struct address_space *mapping,
loff_t pos, unsigned len, unsigned copied,
struct page *page, void *fsdata);
-struct backing_dev_info;
struct address_space {
struct inode *host; /* owner: inode, block_device */
struct radix_tree_root page_tree; /* radix tree of all pages */
@@ -409,7 +409,6 @@ struct address_space {
pgoff_t writeback_index;/* writeback starts here */
const struct address_space_operations *a_ops; /* methods */
unsigned long flags; /* error bits/gfp mask */
- struct backing_dev_info *backing_dev_info; /* device readahead, etc */
spinlock_t private_lock; /* for use by the address_space */
struct list_head private_list; /* ditto */
void *private_data; /* ditto */
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 16c6895..52e0c76 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -24,7 +24,6 @@ struct backing_dev_info noop_backing_dev_info = {
.name = "noop",
.capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK,
};
-EXPORT_SYMBOL_GPL(noop_backing_dev_info);
static struct class *bdi_class;
diff --git a/mm/shmem.c b/mm/shmem.c
index 1b77eaf..4c61d3d 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1410,7 +1410,6 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode
inode->i_ino = get_next_ino();
inode_init_owner(inode, dir, mode);
inode->i_blocks = 0;
- inode->i_mapping->backing_dev_info = &noop_backing_dev_info;
inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
inode->i_generation = get_seconds();
info = SHMEM_I(inode);
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 1c137b6..405923f 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -37,7 +37,6 @@ struct address_space swapper_spaces[MAX_SWAPFILES] = {
.page_tree = RADIX_TREE_INIT(GFP_ATOMIC|__GFP_NOWARN),
.i_mmap_writable = ATOMIC_INIT(0),
.a_ops = &swap_aops,
- .backing_dev_info = &noop_backing_dev_info,
}
};
--
1.9.1
On Wed 14-01-15 10:42:37, Christoph Hellwig wrote:
> Now that we never use the backing_dev_info pointer in struct address_space
> we can simply remove it and save 4 to 8 bytes in every inode.
I was thinking whether we don't increase an overhead of some operations
by having to fetch bdi via mapping->host->i_sb->s_bdi (instead of simple
mapping->backing_dev_info). But in the end I didn't find an operation
which would be sufficiently hot that the additional overhead would matter.
So you can add:
Reviewed-by: Jan Kara <[email protected]>
Honza
>
> Signed-off-by: Christoph Hellwig <[email protected]>
> Acked-by: Ryusuke Konishi <[email protected]>
> Reviewed-by: Tejun Heo <[email protected]>
> ---
> drivers/char/raw.c | 4 +---
> fs/aio.c | 1 -
> fs/block_dev.c | 26 +-------------------------
> fs/btrfs/disk-io.c | 1 -
> fs/btrfs/inode.c | 6 ------
> fs/ceph/inode.c | 2 --
> fs/cifs/inode.c | 2 --
> fs/configfs/inode.c | 1 -
> fs/ecryptfs/inode.c | 1 -
> fs/exofs/inode.c | 2 --
> fs/fuse/inode.c | 1 -
> fs/gfs2/glock.c | 1 -
> fs/gfs2/ops_fstype.c | 1 -
> fs/hugetlbfs/inode.c | 1 -
> fs/inode.c | 13 -------------
> fs/kernfs/inode.c | 1 -
> fs/ncpfs/inode.c | 1 -
> fs/nfs/inode.c | 1 -
> fs/nilfs2/gcinode.c | 1 -
> fs/nilfs2/mdt.c | 6 ++----
> fs/nilfs2/page.c | 4 +---
> fs/nilfs2/page.h | 3 +--
> fs/nilfs2/super.c | 2 +-
> fs/ocfs2/dlmfs/dlmfs.c | 2 --
> fs/ramfs/inode.c | 1 -
> fs/romfs/super.c | 3 ---
> fs/ubifs/dir.c | 2 --
> fs/ubifs/super.c | 3 ---
> include/linux/fs.h | 3 +--
> mm/backing-dev.c | 1 -
> mm/shmem.c | 1 -
> mm/swap_state.c | 1 -
> 32 files changed, 8 insertions(+), 91 deletions(-)
>
> diff --git a/drivers/char/raw.c b/drivers/char/raw.c
> index a24891b..6e29bf2 100644
> --- a/drivers/char/raw.c
> +++ b/drivers/char/raw.c
> @@ -104,11 +104,9 @@ static int raw_release(struct inode *inode, struct file *filp)
>
> mutex_lock(&raw_mutex);
> bdev = raw_devices[minor].binding;
> - if (--raw_devices[minor].inuse == 0) {
> + if (--raw_devices[minor].inuse == 0)
> /* Here inode->i_mapping == bdev->bd_inode->i_mapping */
> inode->i_mapping = &inode->i_data;
> - inode->i_mapping->backing_dev_info = &default_backing_dev_info;
> - }
> mutex_unlock(&raw_mutex);
>
> blkdev_put(bdev, filp->f_mode | FMODE_EXCL);
> diff --git a/fs/aio.c b/fs/aio.c
> index 6f13d3f..3bf8b1d 100644
> --- a/fs/aio.c
> +++ b/fs/aio.c
> @@ -176,7 +176,6 @@ static struct file *aio_private_file(struct kioctx *ctx, loff_t nr_pages)
>
> inode->i_mapping->a_ops = &aio_ctx_aops;
> inode->i_mapping->private_data = ctx;
> - inode->i_mapping->backing_dev_info = &noop_backing_dev_info;
> inode->i_size = PAGE_SIZE * nr_pages;
>
> path.dentry = d_alloc_pseudo(aio_mnt->mnt_sb, &this);
> diff --git a/fs/block_dev.c b/fs/block_dev.c
> index 026ca7b..a9f9279 100644
> --- a/fs/block_dev.c
> +++ b/fs/block_dev.c
> @@ -60,19 +60,6 @@ static void bdev_write_inode(struct inode *inode)
> spin_unlock(&inode->i_lock);
> }
>
> -/*
> - * Move the inode from its current bdi to a new bdi. Make sure the inode
> - * is clean before moving so that it doesn't linger on the old bdi.
> - */
> -static void bdev_inode_switch_bdi(struct inode *inode,
> - struct backing_dev_info *dst)
> -{
> - spin_lock(&inode->i_lock);
> - WARN_ON_ONCE(inode->i_state & I_DIRTY);
> - inode->i_data.backing_dev_info = dst;
> - spin_unlock(&inode->i_lock);
> -}
> -
> /* Kill _all_ buffers and pagecache , dirty or not.. */
> void kill_bdev(struct block_device *bdev)
> {
> @@ -589,7 +576,6 @@ struct block_device *bdget(dev_t dev)
> inode->i_bdev = bdev;
> inode->i_data.a_ops = &def_blk_aops;
> mapping_set_gfp_mask(&inode->i_data, GFP_USER);
> - inode->i_data.backing_dev_info = &default_backing_dev_info;
> spin_lock(&bdev_lock);
> list_add(&bdev->bd_list, &all_bdevs);
> spin_unlock(&bdev_lock);
> @@ -1150,8 +1136,6 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
> bdev->bd_queue = disk->queue;
> bdev->bd_contains = bdev;
> if (!partno) {
> - struct backing_dev_info *bdi;
> -
> ret = -ENXIO;
> bdev->bd_part = disk_get_part(disk, partno);
> if (!bdev->bd_part)
> @@ -1177,11 +1161,8 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
> }
> }
>
> - if (!ret) {
> + if (!ret)
> bd_set_size(bdev,(loff_t)get_capacity(disk)<<9);
> - bdi = blk_get_backing_dev_info(bdev);
> - bdev_inode_switch_bdi(bdev->bd_inode, bdi);
> - }
>
> /*
> * If the device is invalidated, rescan partition
> @@ -1208,8 +1189,6 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
> if (ret)
> goto out_clear;
> bdev->bd_contains = whole;
> - bdev_inode_switch_bdi(bdev->bd_inode,
> - whole->bd_inode->i_data.backing_dev_info);
> bdev->bd_part = disk_get_part(disk, partno);
> if (!(disk->flags & GENHD_FL_UP) ||
> !bdev->bd_part || !bdev->bd_part->nr_sects) {
> @@ -1249,7 +1228,6 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
> bdev->bd_disk = NULL;
> bdev->bd_part = NULL;
> bdev->bd_queue = NULL;
> - bdev_inode_switch_bdi(bdev->bd_inode, &default_backing_dev_info);
> if (bdev != bdev->bd_contains)
> __blkdev_put(bdev->bd_contains, mode, 1);
> bdev->bd_contains = NULL;
> @@ -1474,8 +1452,6 @@ static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part)
> * dirty data before.
> */
> bdev_write_inode(bdev->bd_inode);
> - bdev_inode_switch_bdi(bdev->bd_inode,
> - &default_backing_dev_info);
> }
> if (bdev->bd_contains == bdev) {
> if (disk->fops->release)
> diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
> index afc4092..1ec872e 100644
> --- a/fs/btrfs/disk-io.c
> +++ b/fs/btrfs/disk-io.c
> @@ -2318,7 +2318,6 @@ int open_ctree(struct super_block *sb,
> */
> fs_info->btree_inode->i_size = OFFSET_MAX;
> fs_info->btree_inode->i_mapping->a_ops = &btree_aops;
> - fs_info->btree_inode->i_mapping->backing_dev_info = &fs_info->bdi;
>
> RB_CLEAR_NODE(&BTRFS_I(fs_info->btree_inode)->rb_node);
> extent_io_tree_init(&BTRFS_I(fs_info->btree_inode)->io_tree,
> diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
> index 8bf326a..54bcf63 100644
> --- a/fs/btrfs/inode.c
> +++ b/fs/btrfs/inode.c
> @@ -3608,7 +3608,6 @@ cache_acl:
> switch (inode->i_mode & S_IFMT) {
> case S_IFREG:
> inode->i_mapping->a_ops = &btrfs_aops;
> - inode->i_mapping->backing_dev_info = &root->fs_info->bdi;
> BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
> inode->i_fop = &btrfs_file_operations;
> inode->i_op = &btrfs_file_inode_operations;
> @@ -3623,7 +3622,6 @@ cache_acl:
> case S_IFLNK:
> inode->i_op = &btrfs_symlink_inode_operations;
> inode->i_mapping->a_ops = &btrfs_symlink_aops;
> - inode->i_mapping->backing_dev_info = &root->fs_info->bdi;
> break;
> default:
> inode->i_op = &btrfs_special_inode_operations;
> @@ -6088,7 +6086,6 @@ static int btrfs_create(struct inode *dir, struct dentry *dentry,
> inode->i_fop = &btrfs_file_operations;
> inode->i_op = &btrfs_file_inode_operations;
> inode->i_mapping->a_ops = &btrfs_aops;
> - inode->i_mapping->backing_dev_info = &root->fs_info->bdi;
>
> err = btrfs_init_inode_security(trans, inode, dir, &dentry->d_name);
> if (err)
> @@ -9203,7 +9200,6 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
> inode->i_fop = &btrfs_file_operations;
> inode->i_op = &btrfs_file_inode_operations;
> inode->i_mapping->a_ops = &btrfs_aops;
> - inode->i_mapping->backing_dev_info = &root->fs_info->bdi;
> BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
>
> err = btrfs_init_inode_security(trans, inode, dir, &dentry->d_name);
> @@ -9247,7 +9243,6 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
>
> inode->i_op = &btrfs_symlink_inode_operations;
> inode->i_mapping->a_ops = &btrfs_symlink_aops;
> - inode->i_mapping->backing_dev_info = &root->fs_info->bdi;
> inode_set_bytes(inode, name_len);
> btrfs_i_size_write(inode, name_len);
> err = btrfs_update_inode(trans, root, inode);
> @@ -9459,7 +9454,6 @@ static int btrfs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
> inode->i_op = &btrfs_file_inode_operations;
>
> inode->i_mapping->a_ops = &btrfs_aops;
> - inode->i_mapping->backing_dev_info = &root->fs_info->bdi;
> BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
>
> ret = btrfs_init_inode_security(trans, inode, dir, NULL);
> diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
> index f61a741..6b51736 100644
> --- a/fs/ceph/inode.c
> +++ b/fs/ceph/inode.c
> @@ -783,8 +783,6 @@ static int fill_inode(struct inode *inode, struct page *locked_page,
> }
>
> inode->i_mapping->a_ops = &ceph_aops;
> - inode->i_mapping->backing_dev_info =
> - &ceph_sb_to_client(inode->i_sb)->backing_dev_info;
>
> switch (inode->i_mode & S_IFMT) {
> case S_IFIFO:
> diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
> index 0c3ce464..2d4f372 100644
> --- a/fs/cifs/inode.c
> +++ b/fs/cifs/inode.c
> @@ -937,8 +937,6 @@ retry_iget5_locked:
> inode->i_flags |= S_NOATIME | S_NOCMTIME;
> if (inode->i_state & I_NEW) {
> inode->i_ino = hash;
> - if (S_ISREG(inode->i_mode))
> - inode->i_data.backing_dev_info = sb->s_bdi;
> #ifdef CONFIG_CIFS_FSCACHE
> /* initialize per-inode cache cookie pointer */
> CIFS_I(inode)->fscache = NULL;
> diff --git a/fs/configfs/inode.c b/fs/configfs/inode.c
> index 0ad6b4d..65af861 100644
> --- a/fs/configfs/inode.c
> +++ b/fs/configfs/inode.c
> @@ -131,7 +131,6 @@ struct inode *configfs_new_inode(umode_t mode, struct configfs_dirent *sd,
> if (inode) {
> inode->i_ino = get_next_ino();
> inode->i_mapping->a_ops = &configfs_aops;
> - inode->i_mapping->backing_dev_info = &noop_backing_dev_info;
> inode->i_op = &configfs_inode_operations;
>
> if (sd->s_iattr) {
> diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
> index 1686dc2..34b36a5 100644
> --- a/fs/ecryptfs/inode.c
> +++ b/fs/ecryptfs/inode.c
> @@ -67,7 +67,6 @@ static int ecryptfs_inode_set(struct inode *inode, void *opaque)
> inode->i_ino = lower_inode->i_ino;
> inode->i_version++;
> inode->i_mapping->a_ops = &ecryptfs_aops;
> - inode->i_mapping->backing_dev_info = inode->i_sb->s_bdi;
>
> if (S_ISLNK(inode->i_mode))
> inode->i_op = &ecryptfs_symlink_iops;
> diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c
> index f1d3d4e..6fc91df 100644
> --- a/fs/exofs/inode.c
> +++ b/fs/exofs/inode.c
> @@ -1214,7 +1214,6 @@ struct inode *exofs_iget(struct super_block *sb, unsigned long ino)
> memcpy(oi->i_data, fcb.i_data, sizeof(fcb.i_data));
> }
>
> - inode->i_mapping->backing_dev_info = sb->s_bdi;
> if (S_ISREG(inode->i_mode)) {
> inode->i_op = &exofs_file_inode_operations;
> inode->i_fop = &exofs_file_operations;
> @@ -1314,7 +1313,6 @@ struct inode *exofs_new_inode(struct inode *dir, umode_t mode)
>
> set_obj_2bcreated(oi);
>
> - inode->i_mapping->backing_dev_info = sb->s_bdi;
> inode_init_owner(inode, dir, mode);
> inode->i_ino = sbi->s_nextid++;
> inode->i_blkbits = EXOFS_BLKSHIFT;
> diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
> index 6749109..ea0aacd 100644
> --- a/fs/fuse/inode.c
> +++ b/fs/fuse/inode.c
> @@ -308,7 +308,6 @@ struct inode *fuse_iget(struct super_block *sb, u64 nodeid,
> if (!fc->writeback_cache || !S_ISREG(attr->mode))
> inode->i_flags |= S_NOCMTIME;
> inode->i_generation = generation;
> - inode->i_data.backing_dev_info = &fc->bdi;
> fuse_init_inode(inode, attr);
> unlock_new_inode(inode);
> } else if ((inode->i_mode ^ attr->mode) & S_IFMT) {
> diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
> index a23524a..08ea717 100644
> --- a/fs/gfs2/glock.c
> +++ b/fs/gfs2/glock.c
> @@ -775,7 +775,6 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number,
> mapping->flags = 0;
> mapping_set_gfp_mask(mapping, GFP_NOFS);
> mapping->private_data = NULL;
> - mapping->backing_dev_info = s->s_bdi;
> mapping->writeback_index = 0;
> }
>
> diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
> index 8633ad3..efc8e25 100644
> --- a/fs/gfs2/ops_fstype.c
> +++ b/fs/gfs2/ops_fstype.c
> @@ -112,7 +112,6 @@ static struct gfs2_sbd *init_sbd(struct super_block *sb)
> mapping->flags = 0;
> mapping_set_gfp_mask(mapping, GFP_NOFS);
> mapping->private_data = NULL;
> - mapping->backing_dev_info = sb->s_bdi;
> mapping->writeback_index = 0;
>
> spin_lock_init(&sdp->sd_log_lock);
> diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
> index de7c95c..c274aca 100644
> --- a/fs/hugetlbfs/inode.c
> +++ b/fs/hugetlbfs/inode.c
> @@ -492,7 +492,6 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb,
> lockdep_set_class(&inode->i_mapping->i_mmap_rwsem,
> &hugetlbfs_i_mmap_rwsem_key);
> inode->i_mapping->a_ops = &hugetlbfs_aops;
> - inode->i_mapping->backing_dev_info = &noop_backing_dev_info;
> inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
> inode->i_mapping->private_data = resv_map;
> info = HUGETLBFS_I(inode);
> diff --git a/fs/inode.c b/fs/inode.c
> index aa149e7..e4e8caa 100644
> --- a/fs/inode.c
> +++ b/fs/inode.c
> @@ -170,20 +170,7 @@ int inode_init_always(struct super_block *sb, struct inode *inode)
> atomic_set(&mapping->i_mmap_writable, 0);
> mapping_set_gfp_mask(mapping, GFP_HIGHUSER_MOVABLE);
> mapping->private_data = NULL;
> - mapping->backing_dev_info = &default_backing_dev_info;
> mapping->writeback_index = 0;
> -
> - /*
> - * If the block_device provides a backing_dev_info for client
> - * inodes then use that. Otherwise the inode share the bdev's
> - * backing_dev_info.
> - */
> - if (sb->s_bdev) {
> - struct backing_dev_info *bdi;
> -
> - bdi = sb->s_bdev->bd_inode->i_mapping->backing_dev_info;
> - mapping->backing_dev_info = bdi;
> - }
> inode->i_private = NULL;
> inode->i_mapping = mapping;
> INIT_HLIST_HEAD(&inode->i_dentry); /* buggered by rcu freeing */
> diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c
> index 06f0688..9000874 100644
> --- a/fs/kernfs/inode.c
> +++ b/fs/kernfs/inode.c
> @@ -286,7 +286,6 @@ static void kernfs_init_inode(struct kernfs_node *kn, struct inode *inode)
> kernfs_get(kn);
> inode->i_private = kn;
> inode->i_mapping->a_ops = &kernfs_aops;
> - inode->i_mapping->backing_dev_info = &noop_backing_dev_info;
> inode->i_op = &kernfs_iops;
>
> set_default_inode_attr(inode, kn->mode);
> diff --git a/fs/ncpfs/inode.c b/fs/ncpfs/inode.c
> index a699a3f..01a9e16 100644
> --- a/fs/ncpfs/inode.c
> +++ b/fs/ncpfs/inode.c
> @@ -267,7 +267,6 @@ ncp_iget(struct super_block *sb, struct ncp_entry_info *info)
> if (inode) {
> atomic_set(&NCP_FINFO(inode)->opened, info->opened);
>
> - inode->i_mapping->backing_dev_info = sb->s_bdi;
> inode->i_ino = info->ino;
> ncp_set_attr(inode, info);
> if (S_ISREG(inode->i_mode)) {
> diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
> index 4bffe63..24aac72 100644
> --- a/fs/nfs/inode.c
> +++ b/fs/nfs/inode.c
> @@ -387,7 +387,6 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, st
> if (S_ISREG(inode->i_mode)) {
> inode->i_fop = NFS_SB(sb)->nfs_client->rpc_ops->file_ops;
> inode->i_data.a_ops = &nfs_file_aops;
> - inode->i_data.backing_dev_info = &NFS_SB(sb)->backing_dev_info;
> } else if (S_ISDIR(inode->i_mode)) {
> inode->i_op = NFS_SB(sb)->nfs_client->rpc_ops->dir_inode_ops;
> inode->i_fop = &nfs_dir_operations;
> diff --git a/fs/nilfs2/gcinode.c b/fs/nilfs2/gcinode.c
> index 57ceaf3..748ca23 100644
> --- a/fs/nilfs2/gcinode.c
> +++ b/fs/nilfs2/gcinode.c
> @@ -172,7 +172,6 @@ int nilfs_init_gcinode(struct inode *inode)
> inode->i_mode = S_IFREG;
> mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS);
> inode->i_mapping->a_ops = &empty_aops;
> - inode->i_mapping->backing_dev_info = inode->i_sb->s_bdi;
>
> ii->i_flags = 0;
> nilfs_bmap_init_gc(ii->i_bmap);
> diff --git a/fs/nilfs2/mdt.c b/fs/nilfs2/mdt.c
> index c4dcd1d..892cf5f 100644
> --- a/fs/nilfs2/mdt.c
> +++ b/fs/nilfs2/mdt.c
> @@ -429,7 +429,6 @@ int nilfs_mdt_init(struct inode *inode, gfp_t gfp_mask, size_t objsz)
>
> inode->i_mode = S_IFREG;
> mapping_set_gfp_mask(inode->i_mapping, gfp_mask);
> - inode->i_mapping->backing_dev_info = inode->i_sb->s_bdi;
>
> inode->i_op = &def_mdt_iops;
> inode->i_fop = &def_mdt_fops;
> @@ -457,13 +456,12 @@ int nilfs_mdt_setup_shadow_map(struct inode *inode,
> struct nilfs_shadow_map *shadow)
> {
> struct nilfs_mdt_info *mi = NILFS_MDT(inode);
> - struct backing_dev_info *bdi = inode->i_sb->s_bdi;
>
> INIT_LIST_HEAD(&shadow->frozen_buffers);
> address_space_init_once(&shadow->frozen_data);
> - nilfs_mapping_init(&shadow->frozen_data, inode, bdi);
> + nilfs_mapping_init(&shadow->frozen_data, inode);
> address_space_init_once(&shadow->frozen_btnodes);
> - nilfs_mapping_init(&shadow->frozen_btnodes, inode, bdi);
> + nilfs_mapping_init(&shadow->frozen_btnodes, inode);
> mi->mi_shadow = shadow;
> return 0;
> }
> diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c
> index da27664..700ecbc 100644
> --- a/fs/nilfs2/page.c
> +++ b/fs/nilfs2/page.c
> @@ -461,14 +461,12 @@ unsigned nilfs_page_count_clean_buffers(struct page *page,
> return nc;
> }
>
> -void nilfs_mapping_init(struct address_space *mapping, struct inode *inode,
> - struct backing_dev_info *bdi)
> +void nilfs_mapping_init(struct address_space *mapping, struct inode *inode)
> {
> mapping->host = inode;
> mapping->flags = 0;
> mapping_set_gfp_mask(mapping, GFP_NOFS);
> mapping->private_data = NULL;
> - mapping->backing_dev_info = bdi;
> mapping->a_ops = &empty_aops;
> }
>
> diff --git a/fs/nilfs2/page.h b/fs/nilfs2/page.h
> index ef30c5c..a43b828 100644
> --- a/fs/nilfs2/page.h
> +++ b/fs/nilfs2/page.h
> @@ -57,8 +57,7 @@ int nilfs_copy_dirty_pages(struct address_space *, struct address_space *);
> void nilfs_copy_back_pages(struct address_space *, struct address_space *);
> void nilfs_clear_dirty_page(struct page *, bool);
> void nilfs_clear_dirty_pages(struct address_space *, bool);
> -void nilfs_mapping_init(struct address_space *mapping, struct inode *inode,
> - struct backing_dev_info *bdi);
> +void nilfs_mapping_init(struct address_space *mapping, struct inode *inode);
> unsigned nilfs_page_count_clean_buffers(struct page *, unsigned, unsigned);
> unsigned long nilfs_find_uncommitted_extent(struct inode *inode,
> sector_t start_blk,
> diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c
> index 3d4bbac..5bc2a1c 100644
> --- a/fs/nilfs2/super.c
> +++ b/fs/nilfs2/super.c
> @@ -166,7 +166,7 @@ struct inode *nilfs_alloc_inode(struct super_block *sb)
> ii->i_state = 0;
> ii->i_cno = 0;
> ii->vfs_inode.i_version = 1;
> - nilfs_mapping_init(&ii->i_btnode_cache, &ii->vfs_inode, sb->s_bdi);
> + nilfs_mapping_init(&ii->i_btnode_cache, &ii->vfs_inode);
> return &ii->vfs_inode;
> }
>
> diff --git a/fs/ocfs2/dlmfs/dlmfs.c b/fs/ocfs2/dlmfs/dlmfs.c
> index 6000d30..061ba6a 100644
> --- a/fs/ocfs2/dlmfs/dlmfs.c
> +++ b/fs/ocfs2/dlmfs/dlmfs.c
> @@ -398,7 +398,6 @@ static struct inode *dlmfs_get_root_inode(struct super_block *sb)
> if (inode) {
> inode->i_ino = get_next_ino();
> inode_init_owner(inode, NULL, mode);
> - inode->i_mapping->backing_dev_info = &noop_backing_dev_info;
> inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
> inc_nlink(inode);
>
> @@ -422,7 +421,6 @@ static struct inode *dlmfs_get_inode(struct inode *parent,
>
> inode->i_ino = get_next_ino();
> inode_init_owner(inode, parent, mode);
> - inode->i_mapping->backing_dev_info = &noop_backing_dev_info;
> inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
>
> ip = DLMFS_I(inode);
> diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c
> index ad4d712..889d558 100644
> --- a/fs/ramfs/inode.c
> +++ b/fs/ramfs/inode.c
> @@ -59,7 +59,6 @@ struct inode *ramfs_get_inode(struct super_block *sb,
> inode->i_ino = get_next_ino();
> inode_init_owner(inode, dir, mode);
> inode->i_mapping->a_ops = &ramfs_aops;
> - inode->i_mapping->backing_dev_info = &noop_backing_dev_info;
> mapping_set_gfp_mask(inode->i_mapping, GFP_HIGHUSER);
> mapping_set_unevictable(inode->i_mapping);
> inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
> diff --git a/fs/romfs/super.c b/fs/romfs/super.c
> index e98dd88..268733c 100644
> --- a/fs/romfs/super.c
> +++ b/fs/romfs/super.c
> @@ -355,9 +355,6 @@ static struct inode *romfs_iget(struct super_block *sb, unsigned long pos)
> case ROMFH_REG:
> i->i_fop = &romfs_ro_fops;
> i->i_data.a_ops = &romfs_aops;
> - if (i->i_sb->s_mtd)
> - i->i_data.backing_dev_info =
> - i->i_sb->s_mtd->backing_dev_info;
> if (nextfh & ROMFH_EXEC)
> mode |= S_IXUGO;
> break;
> diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c
> index ea41649..c49b198 100644
> --- a/fs/ubifs/dir.c
> +++ b/fs/ubifs/dir.c
> @@ -108,8 +108,6 @@ struct inode *ubifs_new_inode(struct ubifs_info *c, const struct inode *dir,
> inode->i_mtime = inode->i_atime = inode->i_ctime =
> ubifs_current_time(inode);
> inode->i_mapping->nrpages = 0;
> - /* Disable readahead */
> - inode->i_mapping->backing_dev_info = &c->bdi;
>
> switch (mode & S_IFMT) {
> case S_IFREG:
> diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c
> index ed93dc6..6197154 100644
> --- a/fs/ubifs/super.c
> +++ b/fs/ubifs/super.c
> @@ -156,9 +156,6 @@ struct inode *ubifs_iget(struct super_block *sb, unsigned long inum)
> if (err)
> goto out_invalid;
>
> - /* Disable read-ahead */
> - inode->i_mapping->backing_dev_info = &c->bdi;
> -
> switch (inode->i_mode & S_IFMT) {
> case S_IFREG:
> inode->i_mapping->a_ops = &ubifs_file_address_operations;
> diff --git a/include/linux/fs.h b/include/linux/fs.h
> index 1dada39..65d02de 100644
> --- a/include/linux/fs.h
> +++ b/include/linux/fs.h
> @@ -34,6 +34,7 @@
> #include <asm/byteorder.h>
> #include <uapi/linux/fs.h>
>
> +struct backing_dev_info;
> struct export_operations;
> struct hd_geometry;
> struct iovec;
> @@ -394,7 +395,6 @@ int pagecache_write_end(struct file *, struct address_space *mapping,
> loff_t pos, unsigned len, unsigned copied,
> struct page *page, void *fsdata);
>
> -struct backing_dev_info;
> struct address_space {
> struct inode *host; /* owner: inode, block_device */
> struct radix_tree_root page_tree; /* radix tree of all pages */
> @@ -409,7 +409,6 @@ struct address_space {
> pgoff_t writeback_index;/* writeback starts here */
> const struct address_space_operations *a_ops; /* methods */
> unsigned long flags; /* error bits/gfp mask */
> - struct backing_dev_info *backing_dev_info; /* device readahead, etc */
> spinlock_t private_lock; /* for use by the address_space */
> struct list_head private_list; /* ditto */
> void *private_data; /* ditto */
> diff --git a/mm/backing-dev.c b/mm/backing-dev.c
> index 16c6895..52e0c76 100644
> --- a/mm/backing-dev.c
> +++ b/mm/backing-dev.c
> @@ -24,7 +24,6 @@ struct backing_dev_info noop_backing_dev_info = {
> .name = "noop",
> .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK,
> };
> -EXPORT_SYMBOL_GPL(noop_backing_dev_info);
>
> static struct class *bdi_class;
>
> diff --git a/mm/shmem.c b/mm/shmem.c
> index 1b77eaf..4c61d3d 100644
> --- a/mm/shmem.c
> +++ b/mm/shmem.c
> @@ -1410,7 +1410,6 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode
> inode->i_ino = get_next_ino();
> inode_init_owner(inode, dir, mode);
> inode->i_blocks = 0;
> - inode->i_mapping->backing_dev_info = &noop_backing_dev_info;
> inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
> inode->i_generation = get_seconds();
> info = SHMEM_I(inode);
> diff --git a/mm/swap_state.c b/mm/swap_state.c
> index 1c137b6..405923f 100644
> --- a/mm/swap_state.c
> +++ b/mm/swap_state.c
> @@ -37,7 +37,6 @@ struct address_space swapper_spaces[MAX_SWAPFILES] = {
> .page_tree = RADIX_TREE_INIT(GFP_ATOMIC|__GFP_NOWARN),
> .i_mmap_writable = ATOMIC_INIT(0),
> .a_ops = &swap_aops,
> - .backing_dev_info = &noop_backing_dev_info,
> }
> };
>
> --
> 1.9.1
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
> the body of a message to [email protected]
> More majordomo info at http://vger.kernel.org/majordomo-info.html
--
Jan Kara <[email protected]>
SUSE Labs, CR
bdi_destroy already does all the work, and if we delay freeing the
anon bdev we can get away with just that single call.
Signed-off-by: Christoph Hellwig <[email protected]>
---
fs/ceph/super.c | 18 ++++++------------
1 file changed, 6 insertions(+), 12 deletions(-)
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index 50f06cd..e350cc1 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -40,17 +40,6 @@ static void ceph_put_super(struct super_block *s)
dout("put_super\n");
ceph_mdsc_close_sessions(fsc->mdsc);
-
- /*
- * ensure we release the bdi before put_anon_super releases
- * the device name.
- */
- if (s->s_bdi == &fsc->backing_dev_info) {
- bdi_unregister(&fsc->backing_dev_info);
- s->s_bdi = NULL;
- }
-
- return;
}
static int ceph_statfs(struct dentry *dentry, struct kstatfs *buf)
@@ -1002,11 +991,16 @@ out_final:
static void ceph_kill_sb(struct super_block *s)
{
struct ceph_fs_client *fsc = ceph_sb_to_client(s);
+ dev_t dev = s->s_dev;
+
dout("kill_sb %p\n", s);
+
ceph_mdsc_pre_umount(fsc->mdsc);
- kill_anon_super(s); /* will call put_super after sb is r/o */
+ generic_shutdown_super(s);
ceph_mdsc_destroy(fsc);
+
destroy_fs_client(fsc);
+ free_anon_bdev(dev);
}
static struct file_system_type ceph_fs_type = {
--
1.9.1
On Wed 14-01-15 10:42:38, Christoph Hellwig wrote:
> bdi_destroy already does all the work, and if we delay freeing the
> anon bdev we can get away with just that single call.
Looks good. You can add:
Reviewed-by: Jan Kara <[email protected]>
Honza
>
> Signed-off-by: Christoph Hellwig <[email protected]>
> ---
> fs/ceph/super.c | 18 ++++++------------
> 1 file changed, 6 insertions(+), 12 deletions(-)
>
> diff --git a/fs/ceph/super.c b/fs/ceph/super.c
> index 50f06cd..e350cc1 100644
> --- a/fs/ceph/super.c
> +++ b/fs/ceph/super.c
> @@ -40,17 +40,6 @@ static void ceph_put_super(struct super_block *s)
>
> dout("put_super\n");
> ceph_mdsc_close_sessions(fsc->mdsc);
> -
> - /*
> - * ensure we release the bdi before put_anon_super releases
> - * the device name.
> - */
> - if (s->s_bdi == &fsc->backing_dev_info) {
> - bdi_unregister(&fsc->backing_dev_info);
> - s->s_bdi = NULL;
> - }
> -
> - return;
> }
>
> static int ceph_statfs(struct dentry *dentry, struct kstatfs *buf)
> @@ -1002,11 +991,16 @@ out_final:
> static void ceph_kill_sb(struct super_block *s)
> {
> struct ceph_fs_client *fsc = ceph_sb_to_client(s);
> + dev_t dev = s->s_dev;
> +
> dout("kill_sb %p\n", s);
> +
> ceph_mdsc_pre_umount(fsc->mdsc);
> - kill_anon_super(s); /* will call put_super after sb is r/o */
> + generic_shutdown_super(s);
> ceph_mdsc_destroy(fsc);
> +
> destroy_fs_client(fsc);
> + free_anon_bdev(dev);
> }
>
> static struct file_system_type ceph_fs_type = {
> --
> 1.9.1
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
> the body of a message to [email protected]
> More majordomo info at http://vger.kernel.org/majordomo-info.html
--
Jan Kara <[email protected]>
SUSE Labs, CR
bdi_destroy already does all the work, and if we delay freeing the
anon bdev we can get away with just that single call.
Addintionally remove the call during mount failure, as
deactivate_super_locked will already call ->kill_sb and clean up
the bdi for us.
Signed-off-by: Christoph Hellwig <[email protected]>
---
fs/nfs/internal.h | 1 -
fs/nfs/nfs4super.c | 1 -
fs/nfs/super.c | 24 ++++++------------------
3 files changed, 6 insertions(+), 20 deletions(-)
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index efaa31c..f519d41 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -416,7 +416,6 @@ int nfs_show_options(struct seq_file *, struct dentry *);
int nfs_show_devname(struct seq_file *, struct dentry *);
int nfs_show_path(struct seq_file *, struct dentry *);
int nfs_show_stats(struct seq_file *, struct dentry *);
-void nfs_put_super(struct super_block *);
int nfs_remount(struct super_block *sb, int *flags, char *raw_data);
/* write.c */
diff --git a/fs/nfs/nfs4super.c b/fs/nfs/nfs4super.c
index 6f340f0..ab30a3a 100644
--- a/fs/nfs/nfs4super.c
+++ b/fs/nfs/nfs4super.c
@@ -53,7 +53,6 @@ static const struct super_operations nfs4_sops = {
.destroy_inode = nfs_destroy_inode,
.write_inode = nfs4_write_inode,
.drop_inode = nfs_drop_inode,
- .put_super = nfs_put_super,
.statfs = nfs_statfs,
.evict_inode = nfs4_evict_inode,
.umount_begin = nfs_umount_begin,
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 31a11b0..6ec4fe2 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -311,7 +311,6 @@ const struct super_operations nfs_sops = {
.destroy_inode = nfs_destroy_inode,
.write_inode = nfs_write_inode,
.drop_inode = nfs_drop_inode,
- .put_super = nfs_put_super,
.statfs = nfs_statfs,
.evict_inode = nfs_evict_inode,
.umount_begin = nfs_umount_begin,
@@ -2569,7 +2568,7 @@ struct dentry *nfs_fs_mount_common(struct nfs_server *server,
error = nfs_bdi_register(server);
if (error) {
mntroot = ERR_PTR(error);
- goto error_splat_bdi;
+ goto error_splat_super;
}
server->super = s;
}
@@ -2601,9 +2600,6 @@ error_splat_root:
dput(mntroot);
mntroot = ERR_PTR(error);
error_splat_super:
- if (server && !s->s_root)
- bdi_unregister(&server->backing_dev_info);
-error_splat_bdi:
deactivate_locked_super(s);
goto out;
}
@@ -2651,27 +2647,19 @@ out:
EXPORT_SYMBOL_GPL(nfs_fs_mount);
/*
- * Ensure that we unregister the bdi before kill_anon_super
- * releases the device name
- */
-void nfs_put_super(struct super_block *s)
-{
- struct nfs_server *server = NFS_SB(s);
-
- bdi_unregister(&server->backing_dev_info);
-}
-EXPORT_SYMBOL_GPL(nfs_put_super);
-
-/*
* Destroy an NFS2/3 superblock
*/
void nfs_kill_super(struct super_block *s)
{
struct nfs_server *server = NFS_SB(s);
+ dev_t dev = s->s_dev;
+
+ generic_shutdown_super(s);
- kill_anon_super(s);
nfs_fscache_release_super_cookie(s);
+
nfs_free_server(server);
+ free_anon_bdev(dev);
}
EXPORT_SYMBOL_GPL(nfs_kill_super);
--
1.9.1
On Wed 14-01-15 10:42:39, Christoph Hellwig wrote:
> bdi_destroy already does all the work, and if we delay freeing the
> anon bdev we can get away with just that single call.
>
> Addintionally remove the call during mount failure, as
> deactivate_super_locked will already call ->kill_sb and clean up
> the bdi for us.
Looks good. You can add:
Reviewed-by: Jan Kara <[email protected]>
Honza
>
> Signed-off-by: Christoph Hellwig <[email protected]>
> ---
> fs/nfs/internal.h | 1 -
> fs/nfs/nfs4super.c | 1 -
> fs/nfs/super.c | 24 ++++++------------------
> 3 files changed, 6 insertions(+), 20 deletions(-)
>
> diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
> index efaa31c..f519d41 100644
> --- a/fs/nfs/internal.h
> +++ b/fs/nfs/internal.h
> @@ -416,7 +416,6 @@ int nfs_show_options(struct seq_file *, struct dentry *);
> int nfs_show_devname(struct seq_file *, struct dentry *);
> int nfs_show_path(struct seq_file *, struct dentry *);
> int nfs_show_stats(struct seq_file *, struct dentry *);
> -void nfs_put_super(struct super_block *);
> int nfs_remount(struct super_block *sb, int *flags, char *raw_data);
>
> /* write.c */
> diff --git a/fs/nfs/nfs4super.c b/fs/nfs/nfs4super.c
> index 6f340f0..ab30a3a 100644
> --- a/fs/nfs/nfs4super.c
> +++ b/fs/nfs/nfs4super.c
> @@ -53,7 +53,6 @@ static const struct super_operations nfs4_sops = {
> .destroy_inode = nfs_destroy_inode,
> .write_inode = nfs4_write_inode,
> .drop_inode = nfs_drop_inode,
> - .put_super = nfs_put_super,
> .statfs = nfs_statfs,
> .evict_inode = nfs4_evict_inode,
> .umount_begin = nfs_umount_begin,
> diff --git a/fs/nfs/super.c b/fs/nfs/super.c
> index 31a11b0..6ec4fe2 100644
> --- a/fs/nfs/super.c
> +++ b/fs/nfs/super.c
> @@ -311,7 +311,6 @@ const struct super_operations nfs_sops = {
> .destroy_inode = nfs_destroy_inode,
> .write_inode = nfs_write_inode,
> .drop_inode = nfs_drop_inode,
> - .put_super = nfs_put_super,
> .statfs = nfs_statfs,
> .evict_inode = nfs_evict_inode,
> .umount_begin = nfs_umount_begin,
> @@ -2569,7 +2568,7 @@ struct dentry *nfs_fs_mount_common(struct nfs_server *server,
> error = nfs_bdi_register(server);
> if (error) {
> mntroot = ERR_PTR(error);
> - goto error_splat_bdi;
> + goto error_splat_super;
> }
> server->super = s;
> }
> @@ -2601,9 +2600,6 @@ error_splat_root:
> dput(mntroot);
> mntroot = ERR_PTR(error);
> error_splat_super:
> - if (server && !s->s_root)
> - bdi_unregister(&server->backing_dev_info);
> -error_splat_bdi:
> deactivate_locked_super(s);
> goto out;
> }
> @@ -2651,27 +2647,19 @@ out:
> EXPORT_SYMBOL_GPL(nfs_fs_mount);
>
> /*
> - * Ensure that we unregister the bdi before kill_anon_super
> - * releases the device name
> - */
> -void nfs_put_super(struct super_block *s)
> -{
> - struct nfs_server *server = NFS_SB(s);
> -
> - bdi_unregister(&server->backing_dev_info);
> -}
> -EXPORT_SYMBOL_GPL(nfs_put_super);
> -
> -/*
> * Destroy an NFS2/3 superblock
> */
> void nfs_kill_super(struct super_block *s)
> {
> struct nfs_server *server = NFS_SB(s);
> + dev_t dev = s->s_dev;
> +
> + generic_shutdown_super(s);
>
> - kill_anon_super(s);
> nfs_fscache_release_super_cookie(s);
> +
> nfs_free_server(server);
> + free_anon_bdev(dev);
> }
> EXPORT_SYMBOL_GPL(nfs_kill_super);
>
> --
> 1.9.1
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
> the body of a message to [email protected]
> More majordomo info at http://vger.kernel.org/majordomo-info.html
--
Jan Kara <[email protected]>
SUSE Labs, CR
If we have dirty inodes we need to call the filesystem for it, even if the
device has been removed and the filesystem will error out early. The
current code does that by reassining all dirty inodes to the default
backing_dev_info when a bdi is unlinked, but that's pretty pointless given
that the bdi must always outlive the super block.
Instead of stopping writeback at unregister time and moving inodes to the
default bdi just keep the current bdi alive until it is destroyed. The
containing objects of the bdi ensure this doesn't happen until all
writeback has finished by erroring out.
Signed-off-by: Christoph Hellwig <[email protected]>
Reviewed-by: Tejun Heo <[email protected]>
---
mm/backing-dev.c | 91 +++++++++++++++-----------------------------------------
1 file changed, 24 insertions(+), 67 deletions(-)
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 52e0c76..3ebba25 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -37,17 +37,6 @@ LIST_HEAD(bdi_list);
/* bdi_wq serves all asynchronous writeback tasks */
struct workqueue_struct *bdi_wq;
-static void bdi_lock_two(struct bdi_writeback *wb1, struct bdi_writeback *wb2)
-{
- if (wb1 < wb2) {
- spin_lock(&wb1->list_lock);
- spin_lock_nested(&wb2->list_lock, 1);
- } else {
- spin_lock(&wb2->list_lock);
- spin_lock_nested(&wb1->list_lock, 1);
- }
-}
-
#ifdef CONFIG_DEBUG_FS
#include <linux/debugfs.h>
#include <linux/seq_file.h>
@@ -352,19 +341,19 @@ EXPORT_SYMBOL(bdi_register_dev);
*/
static void bdi_wb_shutdown(struct backing_dev_info *bdi)
{
- if (!bdi_cap_writeback_dirty(bdi))
+ /* Make sure nobody queues further work */
+ spin_lock_bh(&bdi->wb_lock);
+ if (!test_and_clear_bit(BDI_registered, &bdi->state)) {
+ spin_unlock_bh(&bdi->wb_lock);
return;
+ }
+ spin_unlock_bh(&bdi->wb_lock);
/*
* Make sure nobody finds us on the bdi_list anymore
*/
bdi_remove_from_list(bdi);
- /* Make sure nobody queues further work */
- spin_lock_bh(&bdi->wb_lock);
- clear_bit(BDI_registered, &bdi->state);
- spin_unlock_bh(&bdi->wb_lock);
-
/*
* Drain work list and shutdown the delayed_work. At this point,
* @bdi->bdi_list is empty telling bdi_Writeback_workfn() that @bdi
@@ -372,37 +361,22 @@ static void bdi_wb_shutdown(struct backing_dev_info *bdi)
*/
mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0);
flush_delayed_work(&bdi->wb.dwork);
- WARN_ON(!list_empty(&bdi->work_list));
- WARN_ON(delayed_work_pending(&bdi->wb.dwork));
}
/*
- * This bdi is going away now, make sure that no super_blocks point to it
+ * Called when the device behind @bdi has been removed or ejected.
+ *
+ * We can't really do much here except for reducing the dirty ratio at
+ * the moment. In the future we should be able to set a flag so that
+ * the filesystem can handle errors at mark_inode_dirty time instead
+ * of only at writeback time.
*/
-static void bdi_prune_sb(struct backing_dev_info *bdi)
-{
- struct super_block *sb;
-
- spin_lock(&sb_lock);
- list_for_each_entry(sb, &super_blocks, s_list) {
- if (sb->s_bdi == bdi)
- sb->s_bdi = &default_backing_dev_info;
- }
- spin_unlock(&sb_lock);
-}
-
void bdi_unregister(struct backing_dev_info *bdi)
{
- if (bdi->dev) {
- bdi_set_min_ratio(bdi, 0);
- trace_writeback_bdi_unregister(bdi);
- bdi_prune_sb(bdi);
+ if (WARN_ON_ONCE(!bdi->dev))
+ return;
- bdi_wb_shutdown(bdi);
- bdi_debug_unregister(bdi);
- device_unregister(bdi->dev);
- bdi->dev = NULL;
- }
+ bdi_set_min_ratio(bdi, 0);
}
EXPORT_SYMBOL(bdi_unregister);
@@ -471,37 +445,20 @@ void bdi_destroy(struct backing_dev_info *bdi)
{
int i;
- /*
- * Splice our entries to the default_backing_dev_info. This
- * condition shouldn't happen. @wb must be empty at this point and
- * dirty inodes on it might cause other issues. This workaround is
- * added by ce5f8e779519 ("writeback: splice dirty inode entries to
- * default bdi on bdi_destroy()") without root-causing the issue.
- *
- * http://lkml.kernel.org/g/[email protected]
- * http://thread.gmane.org/gmane.linux.file-systems/35341/focus=35350
- *
- * We should probably add WARN_ON() to find out whether it still
- * happens and track it down if so.
- */
- if (bdi_has_dirty_io(bdi)) {
- struct bdi_writeback *dst = &default_backing_dev_info.wb;
-
- bdi_lock_two(&bdi->wb, dst);
- list_splice(&bdi->wb.b_dirty, &dst->b_dirty);
- list_splice(&bdi->wb.b_io, &dst->b_io);
- list_splice(&bdi->wb.b_more_io, &dst->b_more_io);
- spin_unlock(&bdi->wb.list_lock);
- spin_unlock(&dst->list_lock);
- }
-
- bdi_unregister(bdi);
+ bdi_wb_shutdown(bdi);
+ WARN_ON(!list_empty(&bdi->work_list));
+ WARN_ON(delayed_work_pending(&bdi->wb.dwork));
WARN_ON(delayed_work_pending(&bdi->wb.dwork));
+ if (bdi->dev) {
+ bdi_debug_unregister(bdi);
+ device_unregister(bdi->dev);
+ bdi->dev = NULL;
+ }
+
for (i = 0; i < NR_BDI_STAT_ITEMS; i++)
percpu_counter_destroy(&bdi->bdi_stat[i]);
-
fprop_local_destroy_percpu(&bdi->completions);
}
EXPORT_SYMBOL(bdi_destroy);
--
1.9.1
On Wed 14-01-15 10:42:40, Christoph Hellwig wrote:
> If we have dirty inodes we need to call the filesystem for it, even if the
> device has been removed and the filesystem will error out early. The
> current code does that by reassining all dirty inodes to the default
> backing_dev_info when a bdi is unlinked, but that's pretty pointless given
> that the bdi must always outlive the super block.
>
> Instead of stopping writeback at unregister time and moving inodes to the
> default bdi just keep the current bdi alive until it is destroyed. The
> containing objects of the bdi ensure this doesn't happen until all
> writeback has finished by erroring out.
>
> Signed-off-by: Christoph Hellwig <[email protected]>
> Reviewed-by: Tejun Heo <[email protected]>
Looks good. You can add:
Reviewed-by: Jan Kara <[email protected]>
One nit below:
> ---
> mm/backing-dev.c | 91 +++++++++++++++-----------------------------------------
> 1 file changed, 24 insertions(+), 67 deletions(-)
>
> diff --git a/mm/backing-dev.c b/mm/backing-dev.c
> index 52e0c76..3ebba25 100644
> --- a/mm/backing-dev.c
> +++ b/mm/backing-dev.c
...
> @@ -471,37 +445,20 @@ void bdi_destroy(struct backing_dev_info *bdi)
> {
> int i;
>
> - /*
> - * Splice our entries to the default_backing_dev_info. This
> - * condition shouldn't happen. @wb must be empty at this point and
> - * dirty inodes on it might cause other issues. This workaround is
> - * added by ce5f8e779519 ("writeback: splice dirty inode entries to
> - * default bdi on bdi_destroy()") without root-causing the issue.
> - *
> - * http://lkml.kernel.org/g/[email protected]
> - * http://thread.gmane.org/gmane.linux.file-systems/35341/focus=35350
> - *
> - * We should probably add WARN_ON() to find out whether it still
> - * happens and track it down if so.
> - */
> - if (bdi_has_dirty_io(bdi)) {
> - struct bdi_writeback *dst = &default_backing_dev_info.wb;
> -
> - bdi_lock_two(&bdi->wb, dst);
> - list_splice(&bdi->wb.b_dirty, &dst->b_dirty);
> - list_splice(&bdi->wb.b_io, &dst->b_io);
> - list_splice(&bdi->wb.b_more_io, &dst->b_more_io);
> - spin_unlock(&bdi->wb.list_lock);
> - spin_unlock(&dst->list_lock);
> - }
> -
> - bdi_unregister(bdi);
> + bdi_wb_shutdown(bdi);
>
> + WARN_ON(!list_empty(&bdi->work_list));
> + WARN_ON(delayed_work_pending(&bdi->wb.dwork));
> WARN_ON(delayed_work_pending(&bdi->wb.dwork));
You have the warning twice here...
Honza
--
Jan Kara <[email protected]>
SUSE Labs, CR
Now that default_backing_dev_info is not used for writeback purposes we can
git rid of it easily:
- instead of using it's name for tracing unregistered bdi we just use
"unknown"
- btrfs and ceph can just assign the default read ahead window themselves
like several other filesystems already do.
- we can assign noop_backing_dev_info as the default one in alloc_super.
All filesystems already either assigned their own or
noop_backing_dev_info.
Signed-off-by: Christoph Hellwig <[email protected]>
Reviewed-by: Tejun Heo <[email protected]>
---
fs/btrfs/disk-io.c | 2 +-
fs/ceph/super.c | 2 +-
fs/super.c | 8 ++------
include/linux/backing-dev.h | 1 -
include/trace/events/writeback.h | 6 ++----
mm/backing-dev.c | 9 ---------
6 files changed, 6 insertions(+), 22 deletions(-)
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 1ec872e..1afb182 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1719,7 +1719,7 @@ static int setup_bdi(struct btrfs_fs_info *info, struct backing_dev_info *bdi)
if (err)
return err;
- bdi->ra_pages = default_backing_dev_info.ra_pages;
+ bdi->ra_pages = VM_MAX_READAHEAD * 1024 / PAGE_CACHE_SIZE;
bdi->congested_fn = btrfs_congested_fn;
bdi->congested_data = info;
return 0;
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index e350cc1..5ae6258 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -899,7 +899,7 @@ static int ceph_register_bdi(struct super_block *sb,
>> PAGE_SHIFT;
else
fsc->backing_dev_info.ra_pages =
- default_backing_dev_info.ra_pages;
+ VM_MAX_READAHEAD * 1024 / PAGE_CACHE_SIZE;
err = bdi_register(&fsc->backing_dev_info, NULL, "ceph-%ld",
atomic_long_inc_return(&bdi_seq));
diff --git a/fs/super.c b/fs/super.c
index eae088f..3b4dada 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -185,8 +185,8 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags)
}
init_waitqueue_head(&s->s_writers.wait);
init_waitqueue_head(&s->s_writers.wait_unfrozen);
+ s->s_bdi = &noop_backing_dev_info;
s->s_flags = flags;
- s->s_bdi = &default_backing_dev_info;
INIT_HLIST_NODE(&s->s_instances);
INIT_HLIST_BL_HEAD(&s->s_anon);
INIT_LIST_HEAD(&s->s_inodes);
@@ -863,10 +863,7 @@ EXPORT_SYMBOL(free_anon_bdev);
int set_anon_super(struct super_block *s, void *data)
{
- int error = get_anon_bdev(&s->s_dev);
- if (!error)
- s->s_bdi = &noop_backing_dev_info;
- return error;
+ return get_anon_bdev(&s->s_dev);
}
EXPORT_SYMBOL(set_anon_super);
@@ -1111,7 +1108,6 @@ mount_fs(struct file_system_type *type, int flags, const char *name, void *data)
sb = root->d_sb;
BUG_ON(!sb);
WARN_ON(!sb->s_bdi);
- WARN_ON(sb->s_bdi == &default_backing_dev_info);
sb->s_flags |= MS_BORN;
error = security_sb_kern_mount(sb, flags, secdata);
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index ed59dee..d94077f 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -241,7 +241,6 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio);
#define BDI_CAP_NO_ACCT_AND_WRITEBACK \
(BDI_CAP_NO_WRITEBACK | BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_ACCT_WB)
-extern struct backing_dev_info default_backing_dev_info;
extern struct backing_dev_info noop_backing_dev_info;
int writeback_in_progress(struct backing_dev_info *bdi);
diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h
index 74f5207..0e93109 100644
--- a/include/trace/events/writeback.h
+++ b/include/trace/events/writeback.h
@@ -156,10 +156,8 @@ DECLARE_EVENT_CLASS(writeback_work_class,
__field(int, reason)
),
TP_fast_assign(
- struct device *dev = bdi->dev;
- if (!dev)
- dev = default_backing_dev_info.dev;
- strncpy(__entry->name, dev_name(dev), 32);
+ strncpy(__entry->name,
+ bdi->dev ? dev_name(bdi->dev) : "(unknown)", 32);
__entry->nr_pages = work->nr_pages;
__entry->sb_dev = work->sb ? work->sb->s_dev : 0;
__entry->sync_mode = work->sync_mode;
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 3ebba25..c49026d 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -14,12 +14,6 @@
static atomic_long_t bdi_seq = ATOMIC_LONG_INIT(0);
-struct backing_dev_info default_backing_dev_info = {
- .name = "default",
- .ra_pages = VM_MAX_READAHEAD * 1024 / PAGE_CACHE_SIZE,
-};
-EXPORT_SYMBOL_GPL(default_backing_dev_info);
-
struct backing_dev_info noop_backing_dev_info = {
.name = "noop",
.capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK,
@@ -250,9 +244,6 @@ static int __init default_bdi_init(void)
if (!bdi_wq)
return -ENOMEM;
- err = bdi_init(&default_backing_dev_info);
- if (!err)
- bdi_register(&default_backing_dev_info, NULL, "default");
err = bdi_init(&noop_backing_dev_info);
return err;
--
1.9.1
On Wed 14-01-15 10:42:41, Christoph Hellwig wrote:
> Now that default_backing_dev_info is not used for writeback purposes we can
> git rid of it easily:
>
> - instead of using it's name for tracing unregistered bdi we just use
> "unknown"
> - btrfs and ceph can just assign the default read ahead window themselves
> like several other filesystems already do.
> - we can assign noop_backing_dev_info as the default one in alloc_super.
> All filesystems already either assigned their own or
> noop_backing_dev_info.
>
> Signed-off-by: Christoph Hellwig <[email protected]>
> Reviewed-by: Tejun Heo <[email protected]>
Looks good. You can add:
Reviewed-by: Jan Kara <[email protected]>
Honza
> ---
> fs/btrfs/disk-io.c | 2 +-
> fs/ceph/super.c | 2 +-
> fs/super.c | 8 ++------
> include/linux/backing-dev.h | 1 -
> include/trace/events/writeback.h | 6 ++----
> mm/backing-dev.c | 9 ---------
> 6 files changed, 6 insertions(+), 22 deletions(-)
>
> diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
> index 1ec872e..1afb182 100644
> --- a/fs/btrfs/disk-io.c
> +++ b/fs/btrfs/disk-io.c
> @@ -1719,7 +1719,7 @@ static int setup_bdi(struct btrfs_fs_info *info, struct backing_dev_info *bdi)
> if (err)
> return err;
>
> - bdi->ra_pages = default_backing_dev_info.ra_pages;
> + bdi->ra_pages = VM_MAX_READAHEAD * 1024 / PAGE_CACHE_SIZE;
> bdi->congested_fn = btrfs_congested_fn;
> bdi->congested_data = info;
> return 0;
> diff --git a/fs/ceph/super.c b/fs/ceph/super.c
> index e350cc1..5ae6258 100644
> --- a/fs/ceph/super.c
> +++ b/fs/ceph/super.c
> @@ -899,7 +899,7 @@ static int ceph_register_bdi(struct super_block *sb,
> >> PAGE_SHIFT;
> else
> fsc->backing_dev_info.ra_pages =
> - default_backing_dev_info.ra_pages;
> + VM_MAX_READAHEAD * 1024 / PAGE_CACHE_SIZE;
>
> err = bdi_register(&fsc->backing_dev_info, NULL, "ceph-%ld",
> atomic_long_inc_return(&bdi_seq));
> diff --git a/fs/super.c b/fs/super.c
> index eae088f..3b4dada 100644
> --- a/fs/super.c
> +++ b/fs/super.c
> @@ -185,8 +185,8 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags)
> }
> init_waitqueue_head(&s->s_writers.wait);
> init_waitqueue_head(&s->s_writers.wait_unfrozen);
> + s->s_bdi = &noop_backing_dev_info;
> s->s_flags = flags;
> - s->s_bdi = &default_backing_dev_info;
> INIT_HLIST_NODE(&s->s_instances);
> INIT_HLIST_BL_HEAD(&s->s_anon);
> INIT_LIST_HEAD(&s->s_inodes);
> @@ -863,10 +863,7 @@ EXPORT_SYMBOL(free_anon_bdev);
>
> int set_anon_super(struct super_block *s, void *data)
> {
> - int error = get_anon_bdev(&s->s_dev);
> - if (!error)
> - s->s_bdi = &noop_backing_dev_info;
> - return error;
> + return get_anon_bdev(&s->s_dev);
> }
>
> EXPORT_SYMBOL(set_anon_super);
> @@ -1111,7 +1108,6 @@ mount_fs(struct file_system_type *type, int flags, const char *name, void *data)
> sb = root->d_sb;
> BUG_ON(!sb);
> WARN_ON(!sb->s_bdi);
> - WARN_ON(sb->s_bdi == &default_backing_dev_info);
> sb->s_flags |= MS_BORN;
>
> error = security_sb_kern_mount(sb, flags, secdata);
> diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
> index ed59dee..d94077f 100644
> --- a/include/linux/backing-dev.h
> +++ b/include/linux/backing-dev.h
> @@ -241,7 +241,6 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio);
> #define BDI_CAP_NO_ACCT_AND_WRITEBACK \
> (BDI_CAP_NO_WRITEBACK | BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_ACCT_WB)
>
> -extern struct backing_dev_info default_backing_dev_info;
> extern struct backing_dev_info noop_backing_dev_info;
>
> int writeback_in_progress(struct backing_dev_info *bdi);
> diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h
> index 74f5207..0e93109 100644
> --- a/include/trace/events/writeback.h
> +++ b/include/trace/events/writeback.h
> @@ -156,10 +156,8 @@ DECLARE_EVENT_CLASS(writeback_work_class,
> __field(int, reason)
> ),
> TP_fast_assign(
> - struct device *dev = bdi->dev;
> - if (!dev)
> - dev = default_backing_dev_info.dev;
> - strncpy(__entry->name, dev_name(dev), 32);
> + strncpy(__entry->name,
> + bdi->dev ? dev_name(bdi->dev) : "(unknown)", 32);
> __entry->nr_pages = work->nr_pages;
> __entry->sb_dev = work->sb ? work->sb->s_dev : 0;
> __entry->sync_mode = work->sync_mode;
> diff --git a/mm/backing-dev.c b/mm/backing-dev.c
> index 3ebba25..c49026d 100644
> --- a/mm/backing-dev.c
> +++ b/mm/backing-dev.c
> @@ -14,12 +14,6 @@
>
> static atomic_long_t bdi_seq = ATOMIC_LONG_INIT(0);
>
> -struct backing_dev_info default_backing_dev_info = {
> - .name = "default",
> - .ra_pages = VM_MAX_READAHEAD * 1024 / PAGE_CACHE_SIZE,
> -};
> -EXPORT_SYMBOL_GPL(default_backing_dev_info);
> -
> struct backing_dev_info noop_backing_dev_info = {
> .name = "noop",
> .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK,
> @@ -250,9 +244,6 @@ static int __init default_bdi_init(void)
> if (!bdi_wq)
> return -ENOMEM;
>
> - err = bdi_init(&default_backing_dev_info);
> - if (!err)
> - bdi_register(&default_backing_dev_info, NULL, "default");
> err = bdi_init(&noop_backing_dev_info);
>
> return err;
> --
> 1.9.1
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
> the body of a message to [email protected]
> More majordomo info at http://vger.kernel.org/majordomo-info.html
--
Jan Kara <[email protected]>
SUSE Labs, CR
On 01/14/2015 02:42 AM, Christoph Hellwig wrote:
> The first 8 patches are unchanged from the series posted a week ago and
> cleans up how we use the backing_dev_info structure in preparation for
> fixing the life time rules for it. The most important change is to
> split the unrelated nommu mmap flags from it, but it also remove a
> backing_dev_info pointer from the address_space (and thus the inode)
> and cleans up various other minor bits.
>
> The remaining patches sort out the issues around bdi_unlink and now
> let the bdi life until it's embedding structure is freed, which must
> be equal or longer than the superblock using the bdi for writeback,
> and thus gets rid of the whole mess around reassining inodes to new
> bdis.
>
> Changes since V1:
> - various minor documentation updates based on Feedback from Tejun
I applied this to for-3.20/bdi, only making the change (noticed by Jan)
to kill the extra WARN_ON() in patch #11.
--
Jens Axboe
On Tue, Jan 20, 2015 at 02:08:18PM -0700, Jens Axboe wrote:
> On 01/14/2015 02:42 AM, Christoph Hellwig wrote:
> >The first 8 patches are unchanged from the series posted a week ago and
> >cleans up how we use the backing_dev_info structure in preparation for
> >fixing the life time rules for it. The most important change is to
> >split the unrelated nommu mmap flags from it, but it also remove a
> >backing_dev_info pointer from the address_space (and thus the inode)
> >and cleans up various other minor bits.
> >
> >The remaining patches sort out the issues around bdi_unlink and now
> >let the bdi life until it's embedding structure is freed, which must
> >be equal or longer than the superblock using the bdi for writeback,
> >and thus gets rid of the whole mess around reassining inodes to new
> >bdis.
> >
> >Changes since V1:
> > - various minor documentation updates based on Feedback from Tejun
>
> I applied this to for-3.20/bdi, only making the change (noticed by
> Jan) to kill the extra WARN_ON() in patch #11.
And at that point we finally can make sb_lock and super_blocks static in
fs/super.c. Do you want that in your tree, or would you rather have it
done via vfs.git during the merge window after your tree goes in? It's
as trivial as this:
Make super_blocks and sb_lock static
The only user outside of fs/super.c is gone now
Signed-off-by: Al Viro <[email protected]>
---
diff --git a/fs/super.c b/fs/super.c
index eae088f..91badbb 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -36,8 +36,8 @@
#include "internal.h"
-LIST_HEAD(super_blocks);
-DEFINE_SPINLOCK(sb_lock);
+static LIST_HEAD(super_blocks);
+static DEFINE_SPINLOCK(sb_lock);
static char *sb_writers_name[SB_FREEZE_LEVELS] = {
"sb_writers",
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 1f3c439..efc384e 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1184,8 +1184,6 @@ struct mm_struct;
#define UMOUNT_NOFOLLOW 0x00000008 /* Don't follow symlink on umount */
#define UMOUNT_UNUSED 0x80000000 /* Flag guaranteed to be unused */
-extern struct list_head super_blocks;
-extern spinlock_t sb_lock;
/* Possible states of 'frozen' field */
enum {
On Sun, Feb 01, 2015 at 06:31:16AM +0000, Al Viro wrote:
> And at that point we finally can make sb_lock and super_blocks static in
> fs/super.c. Do you want that in your tree, or would you rather have it
> done via vfs.git during the merge window after your tree goes in? It's
> as trivial as this:
>
> Make super_blocks and sb_lock static
>
> The only user outside of fs/super.c is gone now
>
> Signed-off-by: Al Viro <[email protected]>
I'd say merge it through the block tree..
Acked-by: Christoph Hellwig <[email protected]>
On 02/02/2015 01:06 AM, Christoph Hellwig wrote:
> On Sun, Feb 01, 2015 at 06:31:16AM +0000, Al Viro wrote:
>> And at that point we finally can make sb_lock and super_blocks static in
>> fs/super.c. Do you want that in your tree, or would you rather have it
>> done via vfs.git during the merge window after your tree goes in? It's
>> as trivial as this:
>>
>> Make super_blocks and sb_lock static
>>
>> The only user outside of fs/super.c is gone now
>>
>> Signed-off-by: Al Viro <[email protected]>
>
> I'd say merge it through the block tree..
>
> Acked-by: Christoph Hellwig <[email protected]>
Added to for-3.20/bdi
--
Jens Axboe
On Wed, Jan 14, 2015 at 4:42 AM, Christoph Hellwig <[email protected]> wrote:
> If we have dirty inodes we need to call the filesystem for it, even if the
> device has been removed and the filesystem will error out early. The
> current code does that by reassining all dirty inodes to the default
> backing_dev_info when a bdi is unlinked, but that's pretty pointless given
> that the bdi must always outlive the super block.
>
> Instead of stopping writeback at unregister time and moving inodes to the
> default bdi just keep the current bdi alive until it is destroyed. The
> containing objects of the bdi ensure this doesn't happen until all
> writeback has finished by erroring out.
>
> Signed-off-by: Christoph Hellwig <[email protected]>
> Reviewed-by: Tejun Heo <[email protected]>
> ---
> mm/backing-dev.c | 91 +++++++++++++++-----------------------------------------
> 1 file changed, 24 insertions(+), 67 deletions(-)
Hey Christoph,
Just a heads up: your commit c4db59d31e39ea067c32163ac961e9c80198fd37
is suspected as the first bad commit in a bisect performed to track
down the cause of DM crashes reported in this BZ:
https://bugzilla.redhat.com/show_bug.cgi?id=1202449
I've yet to look closely at _why_ this commit but figured I'd share
since this appears to be a 4.0-rcX regression.
Mike
On Sat, Mar 21 2015 at 11:11am -0400,
Mike Snitzer <[email protected]> wrote:
> On Wed, Jan 14, 2015 at 4:42 AM, Christoph Hellwig <[email protected]> wrote:
> > If we have dirty inodes we need to call the filesystem for it, even if the
> > device has been removed and the filesystem will error out early. The
> > current code does that by reassining all dirty inodes to the default
> > backing_dev_info when a bdi is unlinked, but that's pretty pointless given
> > that the bdi must always outlive the super block.
> >
> > Instead of stopping writeback at unregister time and moving inodes to the
> > default bdi just keep the current bdi alive until it is destroyed. The
> > containing objects of the bdi ensure this doesn't happen until all
> > writeback has finished by erroring out.
> >
> > Signed-off-by: Christoph Hellwig <[email protected]>
> > Reviewed-by: Tejun Heo <[email protected]>
> > ---
> > mm/backing-dev.c | 91 +++++++++++++++-----------------------------------------
> > 1 file changed, 24 insertions(+), 67 deletions(-)
>
> Hey Christoph,
>
> Just a heads up: your commit c4db59d31e39ea067c32163ac961e9c80198fd37
> is suspected as the first bad commit in a bisect performed to track
> down the cause of DM crashes reported in this BZ:
> https://bugzilla.redhat.com/show_bug.cgi?id=1202449
>
> I've yet to look closely at _why_ this commit but figured I'd share
> since this appears to be a 4.0-rcX regression.
FYI, here is the DM fix I've staged for 4.0-rc6. I'll continue testing
the various DM targets before requesting Linus to pull.
On Mon, Mar 23, 2015 at 06:40:13PM -0400, Mike Snitzer wrote:
> FYI, here is the DM fix I've staged for 4.0-rc6. I'll continue testing
> the various DM targets before requesting Linus to pull.
Yeah, from looking at the bugzilla it seemed like dm was releasing the
dev_t before the queue has been freed.
I don't know this code to well, so this isn't a full review, but it looks like
the right fix to me.