Skip to content

Commit

Permalink
Merge tag 'for-5.19-tag' of git://git.kernel.org/pub/scm/linux/kernel…
Browse files Browse the repository at this point in the history 
…/git/kdave/linux

Pull btrfs updates from David Sterba:
 "Features:

   - subpage:
      - support for PAGE_SIZE > 4K (previously only 64K)
      - make it work with raid56

   - repair super block num_devices automatically if it does not match
     the number of device items

   - defrag can convert inline extents to regular extents, up to now
     inline files were skipped but the setting of mount option
     max_inline could affect the decision logic

   - zoned:
      - minimal accepted zone size is explicitly set to 4MiB
      - make zone reclaim less aggressive and don't reclaim if there are
        enough free zones
      - add per-profile sysfs tunable of the reclaim threshold

   - allow automatic block group reclaim for non-zoned filesystems, with
     sysfs tunables

   - tree-checker: new check, compare extent buffer owner against owner
     rootid

  Performance:

   - avoid blocking on space reservation when doing nowait direct io
     writes (+7% throughput for reads and writes)

   - NOCOW write throughput improvement due to refined locking (+3%)

   - send: reduce pressure to page cache by dropping extent pages right
     after they're processed

  Core:

   - convert all radix trees to xarray

   - add iterators for b-tree node items

   - support printk message index

   - user bulk page allocation for extent buffers

   - switch to bio_alloc API, use on-stack bios where convenient, other
     bio cleanups

   - use rw lock for block groups to favor concurrent reads

   - simplify workques, don't allocate high priority threads for all
     normal queues as we need only one

   - refactor scrub, process chunks based on their constraints and
     similarity

   - allocate direct io structures on stack and pass around only
     pointers, avoids allocation and reduces potential error handling

  Fixes:

   - fix count of reserved transaction items for various inode
     operations

   - fix deadlock between concurrent dio writes when low on free data
     space

   - fix a few cases when zones need to be finished

  VFS, iomap:

   - add helper to check if sb write has started (usable for assertions)

   - new helper iomap_dio_alloc_bio, export iomap_dio_bio_end_io"

* tag 'for-5.19-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux: (173 commits)
  btrfs: zoned: introduce a minimal zone size 4M and reject mount
  btrfs: allow defrag to convert inline extents to regular extents
  btrfs: add "0x" prefix for unsupported optional features
  btrfs: do not account twice for inode ref when reserving metadata units
  btrfs: zoned: fix comparison of alloc_offset vs meta_write_pointer
  btrfs: send: avoid trashing the page cache
  btrfs: send: keep the current inode open while processing it
  btrfs: allocate the btrfs_dio_private as part of the iomap dio bio
  btrfs: move struct btrfs_dio_private to inode.c
  btrfs: remove the disk_bytenr in struct btrfs_dio_private
  btrfs: allocate dio_data on stack
  iomap: add per-iomap_iter private data
  iomap: allow the file system to provide a bio_set for direct I/O
  btrfs: add a btrfs_dio_rw wrapper
  btrfs: zoned: zone finish unused block group
  btrfs: zoned: properly finish block group on metadata write
  btrfs: zoned: finish block group when there are no more allocatable bytes left
  btrfs: zoned: consolidate zone finish functions
  btrfs: zoned: introduce btrfs_zoned_bg_is_full
  btrfs: improve error reporting in lookup_inline_extent_backref
  ...
  • Loading branch information
@torvalds
torvalds committed May 25, 2022
2 parents 3842007 + 0a05faf commit bd1b7c1
Show file tree
Hide file tree
Showing 67 changed files with 4,482 additions and 4,221 deletions.
39 changes: 3 additions & 36 deletions fs/btrfs/acl.c
View file
Original file line number Diff line number Diff line change
Expand Up @@ -55,9 +55,8 @@ struct posix_acl *btrfs_get_acl(struct inode *inode, int type, bool rcu)
return acl;
}

static int __btrfs_set_acl(struct btrfs_trans_handle *trans,
struct user_namespace *mnt_userns,
struct inode *inode, struct posix_acl *acl, int type)
int __btrfs_set_acl(struct btrfs_trans_handle *trans, struct inode *inode,
struct posix_acl *acl, int type)
{
int ret, size = 0;
const char *name;
Expand Down Expand Up @@ -123,40 +122,8 @@ int btrfs_set_acl(struct user_namespace *mnt_userns, struct inode *inode,
if (ret)
return ret;
}
ret = __btrfs_set_acl(NULL, mnt_userns, inode, acl, type);
ret = __btrfs_set_acl(NULL, inode, acl, type);
if (ret)
inode->i_mode = old_mode;
return ret;
}

int btrfs_init_acl(struct btrfs_trans_handle *trans,
struct inode *inode, struct inode *dir)
{
struct posix_acl *default_acl, *acl;
int ret = 0;

/* this happens with subvols */
if (!dir)
return 0;

ret = posix_acl_create(dir, &inode->i_mode, &default_acl, &acl);
if (ret)
return ret;

if (default_acl) {
ret = __btrfs_set_acl(trans, &init_user_ns, inode, default_acl,
ACL_TYPE_DEFAULT);
posix_acl_release(default_acl);
}

if (acl) {
if (!ret)
ret = __btrfs_set_acl(trans, &init_user_ns, inode, acl,
ACL_TYPE_ACCESS);
posix_acl_release(acl);
}

if (!default_acl && !acl)
cache_no_acl(inode);
return ret;
}
122 changes: 22 additions & 100 deletions fs/btrfs/async-thread.c
View file
Original file line number Diff line number Diff line change
Expand Up @@ -15,13 +15,12 @@
enum {
WORK_DONE_BIT,
WORK_ORDER_DONE_BIT,
WORK_HIGH_PRIO_BIT,
};

#define NO_THRESHOLD (-1)
#define DFT_THRESHOLD (32)

struct __btrfs_workqueue {
struct btrfs_workqueue {
struct workqueue_struct *normal_wq;

/* File system this workqueue services */
Expand All @@ -48,12 +47,7 @@ struct __btrfs_workqueue {
spinlock_t thres_lock;
};

struct btrfs_workqueue {
struct __btrfs_workqueue *normal;
struct __btrfs_workqueue *high;
};

struct btrfs_fs_info * __pure btrfs_workqueue_owner(const struct __btrfs_workqueue *wq)
struct btrfs_fs_info * __pure btrfs_workqueue_owner(const struct btrfs_workqueue *wq)
{
return wq->fs_info;
}
Expand All @@ -66,22 +60,22 @@ struct btrfs_fs_info * __pure btrfs_work_owner(const struct btrfs_work *work)
bool btrfs_workqueue_normal_congested(const struct btrfs_workqueue *wq)
{
/*
* We could compare wq->normal->pending with num_online_cpus()
* We could compare wq->pending with num_online_cpus()
* to support "thresh == NO_THRESHOLD" case, but it requires
* moving up atomic_inc/dec in thresh_queue/exec_hook. Let's
* postpone it until someone needs the support of that case.
*/
if (wq->normal->thresh == NO_THRESHOLD)
if (wq->thresh == NO_THRESHOLD)
return false;

return atomic_read(&wq->normal->pending) > wq->normal->thresh * 2;
return atomic_read(&wq->pending) > wq->thresh * 2;
}

static struct __btrfs_workqueue *
__btrfs_alloc_workqueue(struct btrfs_fs_info *fs_info, const char *name,
unsigned int flags, int limit_active, int thresh)
struct btrfs_workqueue *btrfs_alloc_workqueue(struct btrfs_fs_info *fs_info,
const char *name, unsigned int flags,
int limit_active, int thresh)
{
struct __btrfs_workqueue *ret = kzalloc(sizeof(*ret), GFP_KERNEL);
struct btrfs_workqueue *ret = kzalloc(sizeof(*ret), GFP_KERNEL);

if (!ret)
return NULL;
Expand All @@ -105,12 +99,8 @@ __btrfs_alloc_workqueue(struct btrfs_fs_info *fs_info, const char *name,
ret->thresh = thresh;
}

if (flags & WQ_HIGHPRI)
ret->normal_wq = alloc_workqueue("btrfs-%s-high", flags,
ret->current_active, name);
else
ret->normal_wq = alloc_workqueue("btrfs-%s", flags,
ret->current_active, name);
ret->normal_wq = alloc_workqueue("btrfs-%s", flags, ret->current_active,
name);
if (!ret->normal_wq) {
kfree(ret);
return NULL;
Expand All @@ -119,41 +109,7 @@ __btrfs_alloc_workqueue(struct btrfs_fs_info *fs_info, const char *name,
INIT_LIST_HEAD(&ret->ordered_list);
spin_lock_init(&ret->list_lock);
spin_lock_init(&ret->thres_lock);
trace_btrfs_workqueue_alloc(ret, name, flags & WQ_HIGHPRI);
return ret;
}

static inline void
__btrfs_destroy_workqueue(struct __btrfs_workqueue *wq);

struct btrfs_workqueue *btrfs_alloc_workqueue(struct btrfs_fs_info *fs_info,
const char *name,
unsigned int flags,
int limit_active,
int thresh)
{
struct btrfs_workqueue *ret = kzalloc(sizeof(*ret), GFP_KERNEL);

if (!ret)
return NULL;

ret->normal = __btrfs_alloc_workqueue(fs_info, name,
flags & ~WQ_HIGHPRI,
limit_active, thresh);
if (!ret->normal) {
kfree(ret);
return NULL;
}

if (flags & WQ_HIGHPRI) {
ret->high = __btrfs_alloc_workqueue(fs_info, name, flags,
limit_active, thresh);
if (!ret->high) {
__btrfs_destroy_workqueue(ret->normal);
kfree(ret);
return NULL;
}
}
trace_btrfs_workqueue_alloc(ret, name);
return ret;
}

Expand All @@ -162,7 +118,7 @@ struct btrfs_workqueue *btrfs_alloc_workqueue(struct btrfs_fs_info *fs_info,
* This hook WILL be called in IRQ handler context,
* so workqueue_set_max_active MUST NOT be called in this hook
*/
static inline void thresh_queue_hook(struct __btrfs_workqueue *wq)
static inline void thresh_queue_hook(struct btrfs_workqueue *wq)
{
if (wq->thresh == NO_THRESHOLD)
return;
Expand All @@ -174,7 +130,7 @@ static inline void thresh_queue_hook(struct __btrfs_workqueue *wq)
* This hook is called in kthread content.
* So workqueue_set_max_active is called here.
*/
static inline void thresh_exec_hook(struct __btrfs_workqueue *wq)
static inline void thresh_exec_hook(struct btrfs_workqueue *wq)
{
int new_current_active;
long pending;
Expand Down Expand Up @@ -217,7 +173,7 @@ static inline void thresh_exec_hook(struct __btrfs_workqueue *wq)
}
}

static void run_ordered_work(struct __btrfs_workqueue *wq,
static void run_ordered_work(struct btrfs_workqueue *wq,
struct btrfs_work *self)
{
struct list_head *list = &wq->ordered_list;
Expand Down Expand Up @@ -305,7 +261,7 @@ static void btrfs_work_helper(struct work_struct *normal_work)
{
struct btrfs_work *work = container_of(normal_work, struct btrfs_work,
normal_work);
struct __btrfs_workqueue *wq;
struct btrfs_workqueue *wq = work->wq;
int need_order = 0;

/*
Expand All @@ -318,7 +274,6 @@ static void btrfs_work_helper(struct work_struct *normal_work)
*/
if (work->ordered_func)
need_order = 1;
wq = work->wq;

trace_btrfs_work_sched(work);
thresh_exec_hook(wq);
Expand Down Expand Up @@ -350,8 +305,7 @@ void btrfs_init_work(struct btrfs_work *work, btrfs_func_t func,
work->flags = 0;
}

static inline void __btrfs_queue_work(struct __btrfs_workqueue *wq,
struct btrfs_work *work)
void btrfs_queue_work(struct btrfs_workqueue *wq, struct btrfs_work *work)
{
unsigned long flags;

Expand All @@ -366,54 +320,22 @@ static inline void __btrfs_queue_work(struct __btrfs_workqueue *wq,
queue_work(wq->normal_wq, &work->normal_work);
}

void btrfs_queue_work(struct btrfs_workqueue *wq,
struct btrfs_work *work)
{
struct __btrfs_workqueue *dest_wq;

if (test_bit(WORK_HIGH_PRIO_BIT, &work->flags) && wq->high)
dest_wq = wq->high;
else
dest_wq = wq->normal;
__btrfs_queue_work(dest_wq, work);
}

static inline void
__btrfs_destroy_workqueue(struct __btrfs_workqueue *wq)
{
destroy_workqueue(wq->normal_wq);
trace_btrfs_workqueue_destroy(wq);
kfree(wq);
}

void btrfs_destroy_workqueue(struct btrfs_workqueue *wq)
{
if (!wq)
return;
if (wq->high)
__btrfs_destroy_workqueue(wq->high);
__btrfs_destroy_workqueue(wq->normal);
destroy_workqueue(wq->normal_wq);
trace_btrfs_workqueue_destroy(wq);
kfree(wq);
}

void btrfs_workqueue_set_max(struct btrfs_workqueue *wq, int limit_active)
{
if (!wq)
return;
wq->normal->limit_active = limit_active;
if (wq->high)
wq->high->limit_active = limit_active;
}

void btrfs_set_work_high_priority(struct btrfs_work *work)
{
set_bit(WORK_HIGH_PRIO_BIT, &work->flags);
if (wq)
wq->limit_active = limit_active;
}

void btrfs_flush_workqueue(struct btrfs_workqueue *wq)
{
if (wq->high)
flush_workqueue(wq->high->normal_wq);

flush_workqueue(wq->normal->normal_wq);
flush_workqueue(wq->normal_wq);
}
7 changes: 2 additions & 5 deletions fs/btrfs/async-thread.h
View file
Original file line number Diff line number Diff line change
Expand Up @@ -11,8 +11,6 @@

struct btrfs_fs_info;
struct btrfs_workqueue;
/* Internal use only */
struct __btrfs_workqueue;
struct btrfs_work;
typedef void (*btrfs_func_t)(struct btrfs_work *arg);
typedef void (*btrfs_work_func_t)(struct work_struct *arg);
Expand All @@ -25,7 +23,7 @@ struct btrfs_work {
/* Don't touch things below */
struct work_struct normal_work;
struct list_head ordered_list;
struct __btrfs_workqueue *wq;
struct btrfs_workqueue *wq;
unsigned long flags;
};

Expand All @@ -40,9 +38,8 @@ void btrfs_queue_work(struct btrfs_workqueue *wq,
struct btrfs_work *work);
void btrfs_destroy_workqueue(struct btrfs_workqueue *wq);
void btrfs_workqueue_set_max(struct btrfs_workqueue *wq, int max);
void btrfs_set_work_high_priority(struct btrfs_work *work);
struct btrfs_fs_info * __pure btrfs_work_owner(const struct btrfs_work *work);
struct btrfs_fs_info * __pure btrfs_workqueue_owner(const struct __btrfs_workqueue *wq);
struct btrfs_fs_info * __pure btrfs_workqueue_owner(const struct btrfs_workqueue *wq);
bool btrfs_workqueue_normal_congested(const struct btrfs_workqueue *wq);
void btrfs_flush_workqueue(struct btrfs_workqueue *wq);

Expand Down
Loading

0 comments on commit bd1b7c1

Please sign in to comment.