FUSE file reads are cached in the page cache, but symlink reads are
not. This patch enables FUSE READLINK operations to be cached which
can improve performance of some FUSE workloads.

In particular, I'm working on a FUSE filesystem for access to source
code and discovered that about a 10% improvement to build times is
achieved with this patch (there are a lot of symlinks in the source
tree).
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>

After sending a synchronous READ request from __fuse_direct_read() we only
need to invalidate atime; none of the other attributes should be changed by
a read().
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>

If 'auto_inval_data' mode is active, then fuse_file_read_iter() will call
fuse_update_attributes(), which will check the attribute validity and send
a GETATTR request if some of the attributes are no longer valid.  The page
cache is then invalidated if the size or mtime have changed.

Then, if a READ request was sent and reply received (which is the case if
the data wasn't cached yet, or if the file is opened for O_DIRECT), the
atime attribute is invalidated.

This will result in the next read() also triggering a GETATTR, ...

This can be fixed by only sending GETATTR if the mode or size are invalid,
we don't need to do a refresh if only atime is invalid.

More generally, none of the callers of fuse_update_attributes() need an
up-to-date atime value, so for now just remove STATX_ATIME from the request
mask when attributes are updated for internal use.
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>

This patch adds the infrastructure for more fine grained attribute
invalidation.  Currently only 'atime' is invalidated separately.

The use of this infrastructure is extended to the statx(2) interface, which
for now means that if only 'atime' is invalid and STATX_ATIME is not
specified in the mask argument, then no GETATTR request will be generated.
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>

Unprotected naming of local variables within bit_clear_unless() can easily
lead to using the wrong scope.

Noticed this by code review after having hit this issue in set_mask_bits()
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
Fixes: 85ad1d13 ("md: set MD_CHANGE_PENDING in a atomic region")
Cc: Guoqing Jiang <gqjiang@suse.com>

Unprotected naming of local variables within the set_mask_bits() can easily
lead to using the wrong scope.

Noticed this when "set_mask_bits(&foo->bar, 0, mask)" behaved as no-op.
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
Fixes: 00a1a053 ("ext4: atomically set inode->i_flags in ext4_set_inode_flags()")
Cc: Theodore Ts'o <tytso@mit.edu>

Writeback caching currently allocates requests with the maximum number of
possible pages, while the actual number of pages per request depends on a
couple of factors that cannot be determined when the request is allocated
(whether page is already under writeback, whether page is contiguous with
previous pages already added to a request).

This patch allows such requests to start with no page allocation (all pages
inline) and grow the page array on demand.

If the max_pages tunable remains the default value, then this will mean
just one allocation that is the same size as before.  If the tunable is
larger, then this adds at most 3 additional memory allocations (which is
generously compensated by the improved performance from the larger
request).
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>

Replace FUSE_MAX_PAGES_PER_REQ with the configurable parameter max_pages to
improve performance.

Old RFC with detailed description of the problem and many fixes by Mitsuo
Hayasaka (mitsuo.hayasaka.hu@hitachi.com):
 - https://lkml.org/lkml/2012/7/5/136

We've encountered performance degradation and fixed it on a big and complex
virtual environment.

Environment to reproduce degradation and improvement:

1. Add lag to user mode FUSE
Add nanosleep(&(struct timespec){ 0, 1000 }, NULL); to xmp_write_buf in
passthrough_fh.c

2. patch UM fuse with configurable max_pages parameter. The patch will be
provided latter.

3. run test script and perform test on tmpfs
fuse_test()
{

       cd /tmp
       mkdir -p fusemnt
       passthrough_fh -o max_pages=$1 /tmp/fusemnt
       grep fuse /proc/self/mounts
       dd conv=fdatasync oflag=dsync if=/dev/zero of=fusemnt/tmp/tmp \
		count=1K bs=1M 2>&1 | grep -v records
       rm fusemnt/tmp/tmp
       killall passthrough_fh
}

Test results:

passthrough_fh /tmp/fusemnt fuse.passthrough_fh \
	rw,nosuid,nodev,relatime,user_id=0,group_id=0 0 0
1073741824 bytes (1.1 GB) copied, 1.73867 s, 618 MB/s

passthrough_fh /tmp/fusemnt fuse.passthrough_fh \
	rw,nosuid,nodev,relatime,user_id=0,group_id=0,max_pages=256 0 0
1073741824 bytes (1.1 GB) copied, 1.15643 s, 928 MB/s

Obviously with bigger lag the difference between 'before' and 'after'
will be more significant.

Mitsuo Hayasaka, in 2012 (https://lkml.org/lkml/2012/7/5/136),
observed improvement from 400-550 to 520-740.
Signed-off-by: Constantine Shulyupin <const@MakeLinux.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>

When allocating page array for a request the array for the page pointers
and the array for page descriptors are allocated by two separate kmalloc()
calls.  Merge these into one allocation.

Also instead of initializing the request and the page arrays with memset(),
use the zeroing allocation variants.

Reserved requests never carry pages (page array size is zero). Make that
explicit by initializing the page array pointers to NULL and make sure the
assumption remains true by adding a WARN_ON().
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>

Do this by grouping fields used for cached writes and putting them into a
union with fileds used for cached readdir (with obviously no overlap, since
we don't have hybrid objects).
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>

Use the internal iversion counter to make sure modifications of the
directory through this filesystem are not missed by the mtime check (due to
mtime granularity).
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>

Store the modification time of the directory in the cache, obtained before
starting to fill the cache.

When reading the cache, verify that the directory hasn't changed, by
checking if current modification time is the same as the one stored in the
cache.

This only needs to be done when the current file position is at the
beginning of the directory, as mandated by POSIX.
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>

Allow the cache to be invalidated when page(s) have gone missing.  In this
case increment the version of the cache and reset to an empty state.

Add a version number to the directory stream in struct fuse_file as well,
indicating the version of the cache it's supposed to be reading.  If the
cache version doesn't match the stream's version, then reset the stream to
the beginning of the cache.
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>

The cache is only used if it's completed, not while it's still being
filled; this constraint could be lifted later, if it turns out to be
useful.

Introduce state in struct fuse_file that indicates the position within the
cache.  After a seek, reset the position to the beginning of the cache and
search the cache for the current position.  If the current position is not
found in the cache, then fall back to uncached readdir.

It can also happen that page(s) disappear from the cache, in which case we
must also fall back to uncached readdir.
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>

This patch just adds the cache filling functions, which are invoked if
FOPEN_CACHE_DIR flag is set in the OPENDIR reply.

Cache reading and cache invalidation are added by subsequent patches.

The directory cache uses the page cache.  Directory entries are packed into
a page in the same format as in the READDIR reply.  A page only contains
whole entries, the space at the end of the page is cleared.  The page is
locked while being modified.

Multiple parallel readdirs on the same directory can fill the cache; the
only constraint is that continuity must be maintained (d_off of last entry
points to position of current entry).
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>

Prepare for cache filling by introducing a helper for emitting a single
directory entry.
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>

Add flag returned by OPENDIR request to allow kernel to cache directory
contents in page cache.  The effect of FOPEN_CACHE_DIR is twofold:

 a) if not already cached, it writes entries into the cache

 b) if already cached, it allows reading entries from the cache

The FOPEN_KEEP_CACHE has the same effect as on regular files: unless this
flag is given the cache is cleared upon completion of open.

So FOPEN_KEEP_CACHE and FOPEN_KEEP_CACHE flags should be used together to
make use of the directory caching facility introduced in the following
patches.

The FUSE_AUTO_INVAL_DATA flag returned in INIT reply also has the same
affect on the directory cache as it has on data cache for regular files.
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>

Directory reading code is about to grow larger, so split it out from dir.c
into a new source file.
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>

We noticed the performance bottleneck in FUSE running our Virtuozzo storage
over rdma. On some types of workload we observe 20% of times spent in
request_find() in profiler.  This function is iterating over long requests
list, and it scales bad.

The patch introduces hash table to reduce the number of iterations, we do
in this function. Hash generating algorithm is taken from hash_add()
function, while 256 lines table is used to store pending requests.  This
fixes problem and improves the performance.
Reported-by: Alexey Kuznetsov <kuznet@virtuozzo.com>
Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>

This field is not needed after the previous patch, since we can easily
convert request ID to interrupt request ID and vice versa.
Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>

Using of two unconnected IDs req->in.h.unique and req->intr_unique does not
allow to link requests to a hash table. We need can't use none of them as a
key to calculate hash.

This patch changes the algorithm of allocation of IDs for a request. Plain
requests obtain even ID, while interrupt requests are encoded in the low
bit. So, in next patches we will be able to use the rest of ID bits to
calculate hash, and the hash will be the same for plain and interrupt
requests.
Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>

Currently, we take fc->lock there only to check for fc->connected.
But this flag is changed only on connection abort, which is very
rare operation.

So allow checking fc->connected under just fc->bg_lock and use this lock
(as well as fc->lock) when resetting fc->connected.
Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>

To reduce contention of fc->lock, this patch introduces bg_lock for
protection of fields related to background queue. These are:
max_background, congestion_threshold, num_background, active_background,
bg_queue and blocked.

This allows next patch to make async reads not requiring fc->lock, so async
reads and writes will have better performance executed in parallel.
Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>

Functions sequences like request_end()->flush_bg_queue() require that
max_background and congestion_threshold are constant during their
execution. Otherwise, checks like

	if (fc->num_background == fc->max_background)

made in different time may behave not like expected.
Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>

Since they are of unsigned int type, it's allowed to read them
unlocked during reporting to userspace. Let's underline this fact
with READ_ONCE() macroses.
Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>

This cleanup patch makes the function to use the primitive
instead of direct dereferencing.

Also, move fiq dereferencing out of cycle, since it's
always constant.
Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>

There are several FUSE filesystems that can implement server-side copy
or other efficient copy/duplication/clone methods. The copy_file_range()
syscall is the standard interface that users have access to while not
depending on external libraries that bypass FUSE.
Signed-off-by: Niels de Vos <ndevos@redhat.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>

Using waitqueue_active() is racy.  Make sure we issue a wake_up()
unconditionally after storing into fc->blocked.  After that it's okay to
optimize with waitqueue_active() since the first wake up provides the
necessary barrier for all waiters, not the just the woken one.
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
Fixes: 3c18ef81 ("fuse: optimize wake_up")
Cc: <stable@vger.kernel.org> # v3.10

Otherwise fuse_dev_do_write() could come in and finish off the request, and
the set_bit(FR_SENT, ...) could trigger the WARN_ON(test_bit(FR_SENT, ...))
in request_end().
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
Reported-by: syzbot+ef054c4d3f64cd7f7cec@syzkaller.appspotmai
Fixes: 46c34a34 ("fuse: no fc->lock for pqueue parts")
Cc: <stable@vger.kernel.org> # v4.2

After we found req in request_find() and released the lock,
everything may happen with the req in parallel:

cpu0                              cpu1
fuse_dev_do_write()               fuse_dev_do_write()
  req = request_find(fpq, ...)    ...
  spin_unlock(&fpq->lock)         ...
  ...                             req = request_find(fpq, oh.unique)
  ...                             spin_unlock(&fpq->lock)
  queue_interrupt(&fc->iq, req);   ...
  ...                              ...
  ...                              ...
  request_end(fc, req);
    fuse_put_request(fc, req);
  ...                              queue_interrupt(&fc->iq, req);
Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
Fixes: 46c34a34 ("fuse: no fc->lock for pqueue parts")
Cc: <stable@vger.kernel.org> # v4.2

We may pick freed req in this way:

[cpu0]                                  [cpu1]
fuse_dev_do_read()                      fuse_dev_do_write()
   list_move_tail(&req->list, ...);     ...
   spin_unlock(&fpq->lock);             ...
   ...                                  request_end(fc, req);
   ...                                    fuse_put_request(fc, req);
   if (test_bit(FR_INTERRUPTED, ...))
         queue_interrupt(fiq, req);

Fix that by keeping req alive until we finish all manipulations.

Reported-by: syzbot+4e975615ca01f2277bdd@syzkaller.appspotmail.com
Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
Fixes: 46c34a34 ("fuse: no fc->lock for pqueue parts")
Cc: <stable@vger.kernel.org> # v4.2

Lee writes:
  "MFD fixes for v4.19
   - Fix Dialog DA9063 regulator constraints issue causing failure in
     probe
   - Fix OMAP Device Tree compatible strings to match DT"

* tag 'mfd-fixes-4.19' of git://git.kernel.org/pub/scm/linux/kernel/git/lee/mfd:
  mfd: omap-usb-host: Fix dts probe of children
  mfd: da9063: Fix DT probing with constraints

Juergen writes:
  "xen:
   Two small fixes for xen drivers."

* tag 'for-linus-4.19d-rc5-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip:
  xen: issue warning message when out of grant maptrack entries
  xen/x86/vpmu: Zero struct pt_regs before calling into sample handling code

Jens writes:
  "Just a single fix in this pull request, fixing a regression in
  /proc/diskstats caused by the unification of timestamps."

* tag 'for-linus-20180922' of git://git.kernel.dk/linux-block:
  block: use nanosecond resolution for iostat

Thomas writes:
  "A set of fixes for x86:

   - Resolve the kvmclock regression on AMD systems with memory
     encryption enabled. The rework of the kvmclock memory allocation
     during early boot results in encrypted storage, which is not
     shareable with the hypervisor. Create a new section for this data
     which is mapped unencrypted and take care that the later
     allocations for shared kvmclock memory is unencrypted as well.

   - Fix the build regression in the paravirt code introduced by the
     recent spectre v2 updates.

   - Ensure that the initial static page tables cover the fixmap space
     correctly so early console always works. This worked so far by
     chance, but recent modifications to the fixmap layout can -
     depending on kernel configuration - move the relevant entries to a
     different place which is not covered by the initial static page
     tables.

   - Address the regressions and issues which got introduced with the
     recent extensions to the Intel Recource Director Technology code.

   - Update maintainer entries to document reality"

* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/mm: Expand static page table for fixmap space
  MAINTAINERS: Add X86 MM entry
  x86/intel_rdt: Add Reinette as co-maintainer for RDT
  MAINTAINERS: Add Borislav to the x86 maintainers
  x86/paravirt: Fix some warning messages
  x86/intel_rdt: Fix incorrect loop end condition
  x86/intel_rdt: Fix exclusive mode handling of MBA resource
  x86/intel_rdt: Fix incorrect loop end condition
  x86/intel_rdt: Do not allow pseudo-locking of MBA resource
  x86/intel_rdt: Fix unchecked MSR access
  x86/intel_rdt: Fix invalid mode warning when multiple resources are managed
  x86/intel_rdt: Global closid helper to support future fixes
  x86/intel_rdt: Fix size reporting of MBA resource
  x86/intel_rdt: Fix data type in parsing callbacks
  x86/kvm: Use __bss_decrypted attribute in shared variables
  x86/mm: Add .bss..decrypted section to hold shared variables

Thomas writes:
  "- Provide a strerror_r wrapper so lib/bpf can be built on systems
     without _GNU_SOURCE
   - Unbreak the man page generator when building out of tree"

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  perf Documentation: Fix out-of-tree asciidoctor man page generation
  tools lib bpf: Provide wrapper for strerror_r to build in !_GNU_SOURCE systems

Thomas writes:
  "Make the EFI arm stub device tree loader default on to unbreak
  existing EFI boot loaders which do not have DTB support."

* 'efi-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  efi/libstub/arm: default EFI_ARMSTUB_DTB_LOADER to y

Klaus Kusche reported that the I/O busy time in /proc/diskstats was not
updating properly on 4.18. This is because we started using ktime to
track elapsed time, and we convert nanoseconds to jiffies when we update
the partition counter. However, this gets rounded down, so any I/Os that
take less than a jiffy are not accounted for. Previously in this case,
the value of jiffies would sometimes increment while we were doing I/O,
so at least some I/Os were accounted for.

Let's convert the stats to use nanoseconds internally. We still report
milliseconds as before, now more accurately than ever. The value is
still truncated to 32 bits for backwards compatibility.

Fixes: 522a7775 ("block: consolidate struct request timestamp fields")
Cc: stable@vger.kernel.org
Reported-by: Klaus Kusche <klaus.kusche@computerix.info>
Signed-off-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

Linus writes:
  "Pin control fixes for v4.19:
   - Two fixes for the Intel pin controllers than cause
     problems on laptops."

* tag 'pinctrl-v4.19-3' of git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-pinctrl:
  pinctrl: intel: Do pin translation in other GPIO operations as well
  pinctrl: cannonlake: Fix gpio base for GPP-E