Fixes:

bcachefs (e7fdc10e-54a3-49d9-bd0c-390370889d84): disk usage increased 4294967296 more than 2823707312 sectors reserved)
transaction updates for __bchfs_fallocate journal seq 467859
  update: btree=extents cached=0 bch2_trans_update+0x4e8/0x540
    old u64s 5 type deleted 536925940:3559337304:4294967283 len 0 ver 0
    new u64s 6 type reservation 536925940:3559337304:4294967283 len 3559337304 ver 0: generation 0 replicas 2
  update: btree=inodes cached=1 bch2_extent_update_i_size_sectors+0x305/0x3b0
    old u64s 19 type inode_v3 0:536925940:4294967283 len 0 ver 0: mode 100600 flags 15300000 journal_seq 467859 bi_size 0 bi_sectors 0 bi_version 0 bi_atime 40905301656446 bi_ctime 40905301656446 bi_mtime 40905301656446 bi_otime 40905301656446 bi_uid 0 bi_gid 0 bi_nlink 0 bi_generation 0 bi_dev 0 bi_data_checksum 0 bi_compression 0 bi_project 0 bi_background_compression 0 bi_data_replicas 0 bi_promote_target 0 bi_foreground_target 0 bi_background_target 0 bi_erasure_code 0 bi_fields_set 0 bi_dir 1879048193 bi_dir_offset 3384856038735393365 bi_subvol 0 bi_parent_subvol 0 bi_nocow 0
    new u64s 19 type inode_v3 0:536925940:4294967283 len 0 ver 0: mode 100600 flags 15300000 journal_seq 467859 bi_size 0 bi_sectors 3559337304 bi_version 0 bi_atime 40905301656446 bi_ctime 40905301656446 bi_mtime 40905301656446 bi_otime 40905301656446 bi_uid 0 bi_gid 0 bi_nlink 0 bi_generation 0 bi_dev 0 bi_data_checksum 0 bi_compression 0 bi_project 0 bi_background_compression 0 bi_data_replicas 0 bi_promote_target 0 bi_foreground_target 0 bi_background_target 0 bi_erasure_code 0 bi_fields_set 0 bi_dir 1879048193 bi_dir_offset 3384856038735393365 bi_subvol 0 bi_parent_subvol 0 bi_nocow 0

Kernel panic - not syncing: bcachefs (e7fdc10e-54a3-49d9-bd0c-390370889d84): panic after error
CPU: 4 PID: 5154 Comm: rsync Not tainted 6.5.9-gateway-gca1614174cc0-dirty #1
Hardware name: To Be Filled By O.E.M. To Be Filled By O.E.M./X570 Phantom Gaming 4, BIOS P4.20 08/02/2021
Call Trace:
 <TASK>
 dump_stack_lvl+0x5a/0x90
 panic+0x105/0x300
 ? console_unlock+0xf1/0x130
 ? bch2_printbuf_exit+0x16/0x30
 ? srso_return_thunk+0x5/0x10
 bch2_inconsistent_error+0x6f/0x80
 bch2_trans_fs_usage_apply+0x279/0x3d0
 __bch2_trans_commit+0x112a/0x1df0
 ? bch2_extent_update+0x13a/0x1d0
 bch2_extent_update+0x13a/0x1d0
 bch2_extent_fallocate+0x58e/0x740
 bch2_fallocate_dispatch+0xb7c/0x1030
 ? do_filp_open+0xa0/0x140
 vfs_fallocate+0x18e/0x1d0
 __x64_sys_fallocate+0x46/0x70
 do_syscall_64+0x48/0xa0
 ? exit_to_user_mode_prepare+0x4d/0xa0
 entry_SYSCALL_64_after_hwframe+0x6e/0xd8
RIP: 0033:0x7fc85d91bbb3
Code: 64 89 02 b8 ff ff ff ff eb bd 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 00 80 3d 31 da 0d 00 00 49 89 ca 74 14 b8 1d 01 00 00 0f 05 <48> 3d 00 f0 ff ff 77 5d c3 0f 1f 40 00 48 83 ec 28 48 89 54 24 10
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>

We should only be downgrading locks on success - otherwise, our
transaction restarts won't be getting the correct locks and we'll
livelock.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>

We were dropping a lock we hadn't taken when entering with an error.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>

This patch adds a superblock error counter for every distinct fsck
error; this means that when analyzing filesystems out in the wild we'll
be able to see what sorts of inconsistencies are being found and repair,
and hence what bugs to look for.

Errors validating bkeys are not yet considered distinct fsck errors, but
this patch adds a new helper, bkey_fsck_err(), in order to add distinct
error types for them as well.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>

Add a new superblock section to keep counts of errors seen since
filesystem creation: we'll be addingcounters for every distinct fsck
error.

The new superblock section has entries of the for [ id, count,
time_of_last_error ]; this is intended to let us see what errors are
occuring - and getting fixed - via show-super output.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>

We now track IO errors per device since filesystem creation.

IO error counts can be viewed in sysfs, or with the 'bcachefs
show-super' command.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>

This fixes a use after free - mi is dangling after the resize call.

Additionally, resizing the device's member info section was useless - we
were attempting to preallocate the space required before adding it to
the filesystem superblock, but there's other sections that we should
have been preallocating as well for that to work.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>

This fixes an incorrect memcpy() in the recent members_v2 code - a
members_v1 member is BCH_MEMBER_V1_BYTES, not sizeof(struct bch_member).
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>

This adds a new btree, rebalance_work, to eliminate scanning required
for finding extents that need work done on them in the background - i.e.
for the background_target and background_compression options.

rebalance_work is a bitset btree, where a KEY_TYPE_set corresponds to an
extent in the extents or reflink btree at the same pos.

A new extent field is added, bch_extent_rebalance, which indicates that
this extent has work that needs to be done in the background - and which
options to use. This allows per-inode options to be propagated to
indirect extents - at least in some circumstances. In this patch,
changing IO options on a file will not propagate the new options to
indirect extents pointed to by that file.

Updating (setting/clearing) the rebalance_work btree is done by the
extent trigger, which looks at the bch_extent_rebalance field.

Scanning is still requrired after changing IO path options - either just
for a given inode, or for the whole filesystem. We indicate that
scanning is required by adding a KEY_TYPE_cookie key to the
rebalance_work btree: the cookie counter is so that we can detect that
scanning is still required when an option has been flipped mid-way
through an existing scan.

Future possible work:
 - Propagate options to indirect extents when being changed
 - Add other IO path options - nr_replicas, ec, to rebalance_work so
   they can be applied in the background when they change
 - Add a counter, for bcachefs fs usage output, showing the pending
   amount of rebalance work: we'll probably want to do this after the
   disk space accounting rewrite (moving it to a new btree)
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>

New helper for new rebalance code
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>

data_progress_list is gone - it was redundant with moving_context_list

The upcoming rebalance rewrite is going to have it using two different
move_stats objects with the same moving_context, depending on whether
it's scanning or using the rebalance_work btree - this patch plumbs
stats around a bit differently so that will work.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>

btree_trans and moving_context are used together, and having the
moving_context owns the transaction object reduces some plumbing.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>

Prep work for the new rebalance code - we need a few helpers exported.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>

Since compression options now include compression level, proper
validation is a bit more involved.

This adds bch2_compression_opt_valid(), and plumbs it around
appropriately.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>

This fixes an infinite loop when there's a set bit at position >= 32.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>

We don't yet repair (split) them, just check.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>

The write path may (rarely) see an encoded (checksummed) extent that
exceeds encoded_extent_max - this can happen when we're moving an
existing extent that was not checksummed, but was given a checksum by
bch2_write_rechecksum().
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>

We're going to be using bch2_target_to_text() ->
bch2_disk_path_to_text() from bch2_bkey_ptrs_to_text() and
bch2_bkey_ptrs_invalid(), which can be called in any context.

This patch adds the actual label to bch_disk_group_cpu so that it can be
used by bch2_disk_path_to_text, and splits out bch2_disk_path_to_text()
into two variants - like the previous patch, one for when we have a
running filesystem and another for when we only have a superblock.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>

Previously we just had bch2_opt_target_to_text() which could be passed
either a filesystem object or just a superblock - depending on if we
have a running filesystem or not.

Split these into two functions for clarity.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>

Upcoming rebalance_work btree will require extent triggers to be
BTREE_TRIGGER_WANTS_OLD_AND_NEW - so to reduce potential confusion,
let's just make all triggers BTREE_TRIGGER_WANTS_OLD_AND_NEW.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>

The data move path now correctly picks IO options when inodes in
different snapshots have different options applied.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>

We can't mark device superblocks or allocate journal on a device that
isn't online.

That means we may need to do this on every mount, because we may have
formatted a new filesystem and then done the first mount
(bch2_fs_initialize()) in degraded mode.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>

This code duplicated initialization already done in
bch2_fs_btree_iter_init().
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>

The ca->oldest_gen array needs to be the same size as the bucket_gens
array; ca->mi.nbuckets is updated with only state_lock held, not
gc_lock, so bch2_gc_gens() could race with device resize and allocate
too small of an oldest_gens array.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>

Shrinkers are now exported to debugfs, so the names can't have slashes
in them.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>

More forwards compatibility fixups: having BKEY_TYPE_btree at the end of
the enum conflicts with unnkown btree IDs, this shifts BKEY_TYPE_btree
to slot 0 and fixes things up accordingly.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>

Since we can run with unknown btree IDs, we can't directly index btree
IDs into fixed size arrays.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>

Be a bit more careful about when bch2_delete_dead_snapshots needs to
run: it only needs to run synchronously if we're running fsck, and it
only needs to run at all if we have snapshot nodes to delete or if fsck
has noticed that it needs to run.

Also:
  Rename BCH_FS_HAVE_DELETED_SNAPSHOTS -> BCH_FS_NEED_DELETE_DEAD_SNAPSHOTS

  Kill bch2_delete_dead_snapshots_hook(), move functionality to
  bch2_mark_snapshot()

  Factor out bch2_check_snapshot_needs_deletion(), to explicitly check
  if we need to be running snapshot deletion.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>

We must not hold btree locks while taking snapshot_create_lock - this
fixes a lockdep splat.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>

As pointed out by Linus, closure_sync() was racy; we could skip blocking
immediately after a get() and a put(), but then that would skip any
barrier corresponding to the other thread's put() barrier.

To fix this, always do the full __closure_sync() sequence whenever any
get() has happened and the closure might have been used by other
threads.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>

atomic_(dec|sub)_return_release() are a thing now - use them.

Also, delete the useless barrier in set_closure_fn(): it's redundant
with the memory barrier in closure_put(0.

Since closure_put() would now otherwise just have a release barrier, we
also need a new barrier when the ref hits 0 -
smp_acquire__after_ctrl_dep().
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>

Pull objtool updates from Ingo Molnar:
 "Misc fixes and cleanups:

   - Fix potential MAX_NAME_LEN limit related build failures

   - Fix scripts/faddr2line symbol filtering bug

   - Fix scripts/faddr2line on LLVM=1

   - Fix scripts/faddr2line to accept readelf output with mapping
     symbols

   - Minor cleanups"

* tag 'objtool-core-2023-10-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  scripts/faddr2line: Skip over mapping symbols in output from readelf
  scripts/faddr2line: Use LLVM addr2line and readelf if LLVM=1
  scripts/faddr2line: Don't filter out non-function symbols from readelf
  objtool: Remove max symbol name length limitation
  objtool: Propagate early errors
  objtool: Use 'the fallthrough' pseudo-keyword
  x86/speculation, objtool: Use absolute relocations for annotations
  x86/unwind/orc: Remove redundant initialization of 'mid' pointer in __orc_find()

Pull scheduler updates from Ingo Molnar:
 "Fair scheduler (SCHED_OTHER) improvements:
   - Remove the old and now unused SIS_PROP code & option
   - Scan cluster before LLC in the wake-up path
   - Use candidate prev/recent_used CPU if scanning failed for cluster
     wakeup

  NUMA scheduling improvements:
   - Improve the VMA access-PID code to better skip/scan VMAs
   - Extend tracing to cover VMA-skipping decisions
   - Improve/fix the recently introduced sched_numa_find_nth_cpu() code
   - Generalize numa_map_to_online_node()

  Energy scheduling improvements:
   - Remove the EM_MAX_COMPLEXITY limit
   - Add tracepoints to track energy computation
   - Make the behavior of the 'sched_energy_aware' sysctl more
     consistent
   - Consolidate and clean up access to a CPU's max compute capacity
   - Fix uclamp code corner cases

  RT scheduling improvements:
   - Drive dl_rq->overloaded with dl_rq->pushable_dl_tasks updates
   - Drive the ->rto_mask with rt_rq->pushable_tasks updates

  Scheduler scalability improvements:
   - Rate-limit updates to tg->load_avg
   - On x86 disable IBRS when CPU is offline to improve single-threaded
     performance
   - Micro-optimize in_task() and in_interrupt()
   - Micro-optimize the PSI code
   - Avoid updating PSI triggers and ->rtpoll_total when there are no
     state changes

  Core scheduler infrastructure improvements:
   - Use saved_state to reduce some spurious freezer wakeups
   - Bring in a handful of fast-headers improvements to scheduler
     headers
   - Make the scheduler UAPI headers more widely usable by user-space
   - Simplify the control flow of scheduler syscalls by using lock
     guards
   - Fix sched_setaffinity() vs. CPU hotplug race

  Scheduler debuggability improvements:
   - Disallow writing invalid values to sched_rt_period_us
   - Fix a race in the rq-clock debugging code triggering warnings
   - Fix a warning in the bandwidth distribution code
   - Micro-optimize in_atomic_preempt_off() checks
   - Enforce that the tasklist_lock is held in for_each_thread()
   - Print the TGID in sched_show_task()
   - Remove the /proc/sys/kernel/sched_child_runs_first sysctl

  ... and misc cleanups & fixes"

* tag 'sched-core-2023-10-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (82 commits)
  sched/fair: Remove SIS_PROP
  sched/fair: Use candidate prev/recent_used CPU if scanning failed for cluster wakeup
  sched/fair: Scan cluster before scanning LLC in wake-up path
  sched: Add cpus_share_resources API
  sched/core: Fix RQCF_ACT_SKIP leak
  sched/fair: Remove unused 'curr' argument from pick_next_entity()
  sched/nohz: Update comments about NEWILB_KICK
  sched/fair: Remove duplicate #include
  sched/psi: Update poll => rtpoll in relevant comments
  sched: Make PELT acronym definition searchable
  sched: Fix stop_one_cpu_nowait() vs hotplug
  sched/psi: Bail out early from irq time accounting
  sched/topology: Rename 'DIE' domain to 'PKG'
  sched/psi: Delete the 'update_total' function parameter from update_triggers()
  sched/psi: Avoid updating PSI triggers and ->rtpoll_total when there are no state changes
  sched/headers: Remove comment referring to rq::cpu_load, since this has been removed
  sched/numa: Complete scanning of inactive VMAs when there is no alternative
  sched/numa: Complete scanning of partial VMAs regardless of PID activity
  sched/numa: Move up the access pid reset logic
  sched/numa: Trace decisions related to skipping VMAs
  ...