nbl allocated in nfsd4_lock can be released by a several ways:
directly in nfsd4_lock(), via nfs4_laundromat(), via another nfs
command RELEASE_LOCKOWNER or via nfsd4_callback.
This structure should be refcounted to be used and released correctly
in all these cases.
Refcount is initialized to 1 during allocation and is incremented
when nbl is added into nbl_list/nbl_lru lists.
Usually nbl is linked into both lists together, so only one refcount
is used for both lists.
However nfsd4_lock() should keep in mind that nbl can be present
in one of lists only. This can happen if nbl was handled already
by nfs4_laundromat/nfsd4_callback/etc.
Refcount is decremented if vfs_lock_file() returns FILE_LOCK_DEFERRED,
because nbl can be handled already by nfs4_laundromat/nfsd4_callback/etc.
Refcount is not changed in find_blocked_lock() because of it reuses counter
released after removing nbl from lists.
Signed-off-by: Vasily Averin <vvs@virtuozzo.com> Reviewed-by: Jeff Layton <jlayton@kernel.org> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
NFSv4.1 supports an optional lock notification feature which notifies
the client when a lock comes available. (Normally NFSv4 clients just
poll for locks if necessary.) To make that work, we need to request a
blocking lock from the filesystem.
We turned that off for NFS in commit f657f8eef3ff ("nfs: don't atempt
blocking locks on nfs reexports") [sic] because it actually blocks the
nfsd thread while waiting for the lock.
Thanks to Vasily Averin for pointing out that NFS isn't the only
filesystem with that problem.
Any filesystem that leaves ->lock NULL will use posix_lock_file(), which
does the right thing. Simplest is just to assume that any filesystem
that defines its own ->lock is not safe to request a blocking lock from.
So, this patch mostly reverts commit f657f8eef3ff ("nfs: don't atempt
blocking locks on nfs reexports") [sic] and commit b840be2f00c0 ("lockd:
don't attempt blocking locks on nfs reexports"), and instead uses a
check of ->lock (Vasily's suggestion) to decide whether to support
blocking lock notifications on a given filesystem. Also add a little
documentation.
Perhaps someday we could add back an export flag later to allow
filesystems with "good" ->lock methods to support blocking lock
notifications.
Reported-by: Vasily Averin <vvs@virtuozzo.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com>
[ cel: Description rewritten to address checkpatch nits ]
[ cel: Fixed warning when SUNRPC debugging is disabled ]
[ cel: Fixed NULL check ] Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Reviewed-by: Vasily Averin <vvs@virtuozzo.com> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
The use of the bitmaps is confusing. Add a cross-reference to make it
easier to find the existing comment. Add an updated reference with URL
to make it quicker to look up. And a bit more editorializing about the
value of this.
Signed-off-by: J. Bruce Fields <bfields@redhat.com> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Clean up: The garbage_args and cant_encode tracepoints report the
same information as each other, so combine them into a single
tracepoint class to reduce code duplication and slightly reduce the
size of trace.o.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
We currently have a 'laundrette' for closing cached files - a different
work-item for each network-namespace.
These 'laundrettes' (aka struct nfsd_fcache_disposal) are currently on a
list, and are freed using rcu.
The list is not necessary as we have a per-namespace structure (struct
nfsd_net) which can hold a link to the nfsd_fcache_disposal.
The use of kfree_rcu is also unnecessary as the cache is cleaned of all
files associated with a given namespace, and no new files can be added,
before the nfsd_fcache_disposal is freed.
So add a '->fcache_disposal' link to nfsd_net, and discard the list
management and rcu usage.
Signed-off-by: NeilBrown <neilb@suse.de> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Commit 7142b98d9fd7 ("nfsd: Clean up drc cache in preparation for
global spinlock elimination"), billed as a clean-up, added
be32_to_cpu() to the DRC hash function without explanation. That
commit removed two comments that state that byte-swapping in the
hash function is unnecessary without explaining whether there was
a need for that change.
On some Intel CPUs, the swab32 instruction is known to cause a CPU
pipeline stall. be32_to_cpu() does not add extra randomness, since
the hash multiplication is done /before/ shifting to the high-order
bits of the result.
As a micro-optimization, remove the unnecessary transform from the
DRC hash function.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Now that thread management is consistent there is no need for
nfs-callback to use svc_create_pooled() as introduced in Commit df807fffaabd ("NFSv4.x/callback: Create the callback service through
svc_create_pooled"). So switch back to svc_create().
If service pools were configured, but the number of threads were left at
'1', nfs callback may not work reliably when svc_create_pooled() is used.
Signed-off-by: NeilBrown <neilb@suse.de> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
svc_set_num_threads() does everything that lockd_start_svc() does, except
set sv_maxconn. It also (when passed 0) finds the threads and
stops them with kthread_stop().
So move the setting for sv_maxconn, and use svc_set_num_thread()
We now don't need nlmsvc_task.
Now that we use svc_set_num_threads() it makes sense to set svo_module.
This request that the thread exists with module_put_and_exit().
Also fix the documentation for svo_module to make this explicit.
svc_prepare_thread is now only used where it is defined, so it can be
made static.
Signed-off-by: NeilBrown <neilb@suse.de>
[ cel: upstream, module_put_and_exit was replaced via a merge commit ] Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Currently 'pooled' services hold a reference on the pool_map, and
'unpooled' services do not.
svc_destroy() uses the presence of ->svo_function (via
svc_serv_is_pooled()) to determine if the reference should be dropped.
There is no direct correlation between being pooled and the use of
svo_function, though in practice, lockd is the only non-pooled service,
and the only one not to use svo_function.
This is untidy and would cause problems if we changed lockd to use
svc_set_num_threads(), which requires the use of ->svo_function.
So change the test for "is the service pooled" to "is sv_nrpools > 1".
This means that when svc_pool_map_get() returns 1, it must NOT take a
reference to the pool.
We discard svc_serv_is_pooled(), and test sv_nrpools directly.
Signed-off-by: NeilBrown <neilb@suse.de> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
These definitions are not used outside of svc.c, and there is no
evidence that they ever have been. So move them into svc.c
and make the declarations 'static'.
Signed-off-by: NeilBrown <neilb@suse.de> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
There is some cleanup that is duplicated in lockd_down() and the failure
path of lockd_up().
Factor these out into a new lockd_put() and call it from both places.
lockd_put() does *not* take the mutex - that must be held by the caller.
It decrements nlmsvc_users and if that reaches zero, it cleans up.
Signed-off-by: NeilBrown <neilb@suse.de> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
lockd_start_svc() only needs to be called once, just after the svc is
created. If the start fails, the svc is discarded too.
It thus makes sense to call lockd_start_svc() from lockd_create_svc().
This allows us to remove the test against nlmsvc_rqst at the start of
lockd_start_svc() - it must always be NULL.
lockd_up() only held an extra reference on the svc until a thread was
created - then it dropped it. The thread - and thus the extra reference
- will remain until kthread_stop() is called.
Now that the thread is created in lockd_create_svc(), the extra
reference can be dropped there. So the 'serv' variable is no longer
needed in lockd_up().
Signed-off-by: NeilBrown <neilb@suse.de> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Now that the network status notifiers use nlmsvc_serv rather then
nlmsvc_rqst the management can be simplified.
Notifier unregistration synchronises with any pending notifications so
providing we unregister before nlm_serv is freed no further interlock
is required.
So we move the unregister call to just before the thread is killed
(which destroys the service) and just before the service is destroyed in
the failure-path of lockd_up().
Then nlm_ntf_refcnt and nlm_ntf_wq can be removed.
Signed-off-by: NeilBrown <neilb@suse.de> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
lockd has two globals - nlmsvc_task and nlmsvc_rqst - but mostly it
wants the 'struct svc_serv', and when it doesn't want it exactly it can
get to what it wants from the serv.
This patch is a first step to removing nlmsvc_task and nlmsvc_rqst. It
introduces nlmsvc_serv to store the 'struct svc_serv*'. This is set as
soon as the serv is created, and cleared only when it is destroyed.
Signed-off-by: NeilBrown <neilb@suse.de> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
nfsd currently maintains an open-coded read/write semaphore (refcount
and wait queue) for each network namespace to ensure the nfs service
isn't shut down while the notifier is running.
This is excessive. As there is unlikely to be contention between
notifiers and they run without sleeping, a single spinlock is sufficient
to avoid problems.
Signed-off-by: NeilBrown <neilb@suse.de>
[ cel: ensure nfsd_notifier_lock is static ] Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
The ->svo_setup callback serves no purpose. It is always called from
within the same module that chooses which callback is needed. So
discard it and call the relevant function directly.
Now that svc_set_num_threads() is no longer used remove it and rename
svc_set_num_threads_sync() to remove the "_sync" suffix.
Signed-off-by: NeilBrown <neilb@suse.de> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
nfsd cannot currently use svc_set_num_threads_sync. It instead
uses svc_set_num_threads which does *not* wait for threads to all
exit, and has a separate mechanism (nfsd_shutdown_complete) to wait
for completion.
The reason that nfsd is unlike other services is that nfsd threads can
exit separately from svc_set_num_threads being called - they die on
receipt of SIGKILL. Also, when the last thread exits, the service must
be shut down (sockets closed).
For this, the nfsd_mutex needs to be taken, and as that mutex needs to
be held while svc_set_num_threads is called, the one cannot wait for
the other.
This patch changes the nfsd thread so that it can drop the ref on the
service without blocking on nfsd_mutex, so that svc_set_num_threads_sync
can be used:
- if it can drop a non-last reference, it does that. This does not
trigger shutdown and does not require a mutex. This will likely
happen for all but the last thread signalled, and for all threads
being shut down by nfsd_shutdown_threads()
- if it can get the mutex without blocking (trylock), it does that
and then drops the reference. This will likely happen for the
last thread killed by SIGKILL
- Otherwise there might be an unrelated task holding the mutex,
possibly in another network namespace, or nfsd_shutdown_threads()
might be just about to get a reference on the service, after which
we can drop ours safely.
We cannot conveniently get wakeup notifications on these events,
and we are unlikely to need to, so we sleep briefly and check again.
With this we can discard nfsd_shutdown_complete and
nfsd_complete_shutdown(), and switch to svc_set_num_threads_sync.
Signed-off-by: NeilBrown <neilb@suse.de> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
There is nothing happening in the start of nfsd() that requires
protection by the mutex, so don't take it until shutting down the thread
- which does still require protection - but only for nfsd_put().
Signed-off-by: NeilBrown <neilb@suse.de>
[ cel: address merge conflict with fd2468fa1301 ] Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Using sv_lock means we don't need to hold the service mutex over these
updates.
In particular, svc_exit_thread() no longer requires synchronisation, so
threads can exit asynchronously.
Note that we could use an atomic_t, but as there are many more read
sites than writes, that would add unnecessary noise to the code.
Some reads are already racy, and there is no need for them to not be.
Signed-off-by: NeilBrown <neilb@suse.de> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
The use of sv_nrthreads as a general refcount results in clumsy code, as
is seen by various comments needed to explain the situation.
This patch introduces a 'struct kref' and uses that for reference
counting, leaving sv_nrthreads to be a pure count of threads. The kref
is managed particularly in svc_get() and svc_put(), and also nfsd_put();
svc_destroy() now takes a pointer to the embedded kref, rather than to
the serv.
nfsd allows the svc_serv to exist with ->sv_nrhtreads being zero. This
happens when a transport is created before the first thread is started.
To support this, a 'keep_active' flag is introduced which holds a ref on
the svc_serv. This is set when any listening socket is successfully
added (unless there are running threads), and cleared when the number of
threads is set. So when the last thread exits, the nfs_serv will be
destroyed.
The use of 'keep_active' replaces previous code which checked if there
were any permanent sockets.
We no longer clear ->rq_server when nfsd() exits. This was done
to prevent svc_exit_thread() from calling svc_destroy().
Instead we take an extra reference to the svc_serv to prevent
svc_destroy() from being called.
Signed-off-by: NeilBrown <neilb@suse.de> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
svc_destroy() is poorly named - it doesn't necessarily destroy the svc,
it might just reduce the ref count.
nfsd_destroy() is poorly named for the same reason.
This patch:
- removes the refcount functionality from svc_destroy(), moving it to
a new svc_put(). Almost all previous callers of svc_destroy() now
call svc_put().
- renames nfsd_destroy() to nfsd_put() and improves the code, using
the new svc_destroy() rather than svc_put()
- removes a few comments that explain the important for balanced
get/put calls. This should be obvious.
The only non-trivial part of this is that svc_destroy() would call
svc_sock_update() on a non-final decrement. It can no longer do that,
and svc_put() isn't really a good place of it. This call is now made
from svc_exit_thread() which seems like a good place. This makes the
call *before* sv_nrthreads is decremented rather than after. This
is not particularly important as the call just sets a flag which
causes sv_nrthreads set be checked later. A subsequent patch will
improve the ordering.
Signed-off-by: NeilBrown <neilb@suse.de> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
It is common for 'get' functions to return the object that was 'got',
and there are a couple of places where users of svc_get() would be a
little simpler if svc_get() did that.
Make it so.
Signed-off-by: NeilBrown <neilb@suse.de> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
If write_ports_add() fails, we shouldn't destroy the serv, unless we had
only just created it. So if there are any permanent sockets already
attached, leave the serv in place.
Signed-off-by: NeilBrown <neilb@suse.de> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Update module_put_and_exit to call kthread_exit instead of do_exit.
Change the name to reflect this change in functionality. All of the
users of module_put_and_exit are causing the current kthread to exit
so this change makes it clear what is happening. There is no
functional change.
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
The way the per task_struct exit_code is used by kernel threads is not
quite compatible how it is used by userspace applications. The low
byte of the userspace exit_code value encodes the exit signal. While
kthreads just use the value as an int holding ordinary kernel function
exit status like -EPERM.
Add kthread_exit to clearly separate the two kinds of uses.
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Stable-dep-of: ca3574bd653a ("exit: Rename module_put_and_exit to module_put_and_kthread_exit") Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
FAN_RENAME is the successor of FAN_MOVED_FROM and FAN_MOVED_TO
and can be used to get the old and new parent+name information in
a single event.
FAN_MOVED_FROM and FAN_MOVED_TO are still supported for backward
compatibility, but it makes little sense to use them together with
FAN_RENAME in the same group.
FAN_RENAME uses special info type records to report the old and
new parent+name, so reporting only old and new parent id is less
useful and was not implemented.
Therefore, FAN_REANAME requires a group with flag FAN_REPORT_NAME.
In the special case of FAN_RENAME event, we report old or new or both
old and new parent+name.
A single info record will be reported if either the old or new dir
is watched and two records will be reported if both old and new dir
(or their filesystem) are watched.
The old and new parent+name are reported using new info record types
FAN_EVENT_INFO_TYPE_{OLD,NEW}_DFID_NAME, so if a single info record
is reported, it is clear to the application, to which dir entry the
fid+name info is referring to.
We do not want to report the dirfid+name of a directory whose
inode/sb are not watched, because watcher may not have permissions
to see the directory content.
Use an internal iter_info to indicate to fanotify_alloc_event()
which marks of this group are watching FAN_RENAME, so it can decide
if we need to record only the old parent+name, new parent+name or both.
Link: https://lore.kernel.org/r/20211129201537.1932819-10-amir73il@gmail.com Signed-off-by: Amir Goldstein <amir73il@gmail.com>
[JK: Modified code to pass around only mask of mark types matching
generated event] Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
fanotify_info buffer is parceled into variable sized records, so the
records must be written in order: dir_fh, file_fh, name.
Use helpers to assert that order and make fanotify_alloc_name_event()
a bit more generic to allow empty dir_fh record and to allow expanding
to more records (i.e. name2) soon.
The fanotify_info buffer contains up to two file handles and a name.
Use macros to simplify the code that access the different items within
the buffer.
Add assertions to verify that stored fh len and name len do not overflow
the u8 stored value in fanotify_info header.
The dnotify FS_DN_RENAME event is used to request notification about
a move within the same parent directory and was always coupled with
the FS_MOVED_FROM event.
Rename the FS_DN_RENAME event flag to FS_RENAME, decouple it from
FS_MOVED_FROM and report it with the moved dentry instead of the moved
inode, so it has the information about both old and new parent and name.
Generate the FS_RENAME event regardless of same parent dir and apply
the "same parent" rule in the generic fsnotify_handle_event() helper
that is used to call backends with ->handle_inode_event() method
(i.e. dnotify). The ->handle_inode_event() method is not rich enough to
report both old and new parent and name anyway.
The enriched event is reported to fanotify over the ->handle_event()
method with the old and new dir inode marks in marks array slots for
ITER_TYPE_INODE and a new iter type slot ITER_TYPE_INODE2.
The enriched event will be used for reporting old and new parent+name to
fanotify groups with FAN_RENAME events.
FAN_REPORT_FID is ambiguous in that it reports the fid of the child for
some events and the fid of the parent for create/delete/move events.
The new FAN_REPORT_TARGET_FID flag is an implicit request to report
the fid of the target object of the operation (a.k.a the child inode)
also in create/delete/move events in addition to the fid of the parent
and the name of the child.
To reduce the test matrix for uninteresting use cases, the new
FAN_REPORT_TARGET_FID flag requires both FAN_REPORT_NAME and
FAN_REPORT_FID. The convenience macro FAN_REPORT_DFID_NAME_TARGET
combines FAN_REPORT_TARGET_FID with all the required flags.
In preparation for separating object type from iterator type, rename
some 'type' arguments in functions to 'obj_type' and remove the unused
interface to clear marks by object type mask.
ext4_abort will eventually call ext4_errno_to_code, which translates the
errno to an EXT4_ERR specific error. This means that ext4_abort expects
an errno. By using EXT4_ERR_ here, it gets misinterpreted (as an errno),
and ends up saving EXT4_ERR_EBUSY on the superblock during an abort,
which makes no sense.
ESHUTDOWN will get properly translated to EXT4_ERR_SHUTDOWN, so use that
instead.
./fs/nfsd/nfssvc.c: 1072: 8-9: :WARNING return of 0/1 in function
'nfssvc_decode_voidarg' with return type bool
Return statements in functions returning bool should use true/false
instead of 1/0.
Reported-by: Zeal Robot <zealci@zte.com.cn> Signed-off-by: Changcheng Deng <deng.changcheng@zte.com.cn> Signed-off-by: J. Bruce Fields <bfields@redhat.com> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
I don't know if that Solaris behavior matters any more or if it's still
possible to look up that bug ID any more. The XFS behavior's definitely
still relevant, though; any but the most recent XFS filesystems will
lose the top bits.
Reported-by: Frank S. Filz <ffilzlnx@mindspring.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Returning an undecorated integer is an age-old trope, but it's
not clear (even to previous experts in this code) that the only
valid return values are 1 and 0. These functions do not return
a negative errno, rpc_stat value, or a positive length.
Document there are only two valid return values by having
.pc_encode return only true or false.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
The passed-in value of the "__be32 *p" parameter is now unused in
every server-side XDR encoder, and can be removed.
Note also that there is a line in each encoder that sets up a local
pointer to a struct xdr_stream. Passing that pointer from the
dispatcher instead saves one line per encoder function.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Refactor: Currently nfs4svc_encode_compoundres() relies on the NFS
dispatcher to pass in the buffer location of the COMPOUND status.
Instead, save that buffer location in struct nfsd4_compoundres.
The compound tag follows immediately after.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Returning an undecorated integer is an age-old trope, but it's
not clear (even to previous experts in this code) that the only
valid return values are 1 and 0. These functions do not return
a negative errno, rpc_stat value, or a positive length.
Document there are only two valid return values by having
.pc_decode return only true or false.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
The passed-in value of the "__be32 *p" parameter is now unused in
every server-side XDR decoder, and can be removed.
Note also that there is a line in each decoder that sets up a local
pointer to a struct xdr_stream. Passing that pointer from the
dispatcher instead saves one line per decoder function.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Pointer ni is being initialized with plain integer zero. Fix
this by initializing with NULL.
Signed-off-by: Colin Ian King <colin.king@canonical.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Most of the fields in 'struct knfsd_fh' are 2 levels deep (a union and a
struct) and are accessed using macros like:
#define fh_FOO fh_base.fh_new.fb_FOO
This patch makes the union and struct anonymous, so that "fh_FOO" can be
a name directly within 'struct knfsd_fh' and the #defines aren't needed.
The file handle as a whole is sometimes accessed as "fh_base" or
"fh_base.fh_pad", neither of which are particularly helpful names.
As the struct holding the filehandle is now anonymous, we
cannot use the name of that, so we union it with 'fh_raw' and use that
where the raw filehandle is needed. fh_raw also ensure the structure is
large enough for the largest possible filehandle.
fh_raw is a 'char' array, removing any need to cast it for memcpy etc.
SVCFH_fmt() is simplified using the "%ph" printk format. This
changes the appearance of filehandles in dprintk() debugging, making
them a little more precise.
Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: NeilBrown <neilb@suse.de> Signed-off-by: J. Bruce Fields <bfields@redhat.com> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Filehandles not in the "new" or "version 1" format have not been handed
out for new mounts since Linux 2.4 which was released 20 years ago.
I think it is safe to say that no such file handles are still in use,
and that we can drop support for them.
Signed-off-by: NeilBrown <neilb@suse.de> Signed-off-by: J. Bruce Fields <bfields@redhat.com> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
A small part of the declaration concerning filehandle format are
currently in the "uapi" include directory:
include/uapi/linux/nfsd/nfsfh.h
There is a lot more to the filehandle format, including "enum fid_type"
and "enum nfsd_fsid" which are not exported via "uapi".
This small part of the filehandle definition is of minimal use outside
of the kernel, and I can find no evidence that an other code is using
it. Certainly nfs-utils and wireshark (The most likely candidates) do not
use these declarations.
So move it out of "uapi" by copying the content from
include/uapi/linux/nfsd/nfsfh.h
into
fs/nfsd/nfsfh.h
A few unnecessary "#include" directives are not copied, and neither is
the #define of fh_auth, which is annotated as being for userspace only.
The copyright claims in the uapi file are identical to those in the nfsd
file, so there is no need to copy those.
The "__u32" style integer types are only needed in "uapi". In
kernel-only code we can use the more familiar "u32" style.
Signed-off-by: NeilBrown <neilb@suse.de> Signed-off-by: J. Bruce Fields <bfields@redhat.com> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
DRC bucket pruning is done by nfsd_cache_lookup(), which is part of
every NFSv2 and NFSv3 dispatch (ie, it's done while the client is
waiting).
I added a trace_printk() in prune_bucket() to see just how long
it takes to prune. Here are two ends of the spectrum:
prune_bucket: Scanned 1 and freed 0 in 90 ns, 62 entries remaining
prune_bucket: Scanned 2 and freed 1 in 716 ns, 63 entries remaining
...
prune_bucket: Scanned 75 and freed 74 in 34149 ns, 1 entries remaining
Pruning latency is noticeable on fast transports with fast storage.
By noticeable, I mean that the latency measured here in the worst
case is the same order of magnitude as the round trip time for
cached server operations.
We could do something like moving expired entries to an expired list
and then free them later instead of freeing them right in
prune_bucket(). But simply limiting the number of entries that can
be pruned by a lookup is simple and retains more entries in the
cache, making the DRC somewhat more effective.
Comparison with a 70/30 fio 8KB 12 thread direct I/O test:
Before:
write: IOPS=61.6k, BW=481MiB/s (505MB/s)(14.1GiB/30001msec); 0 zone resets
WRITE: 1848726 ops (30%)
avg bytes sent per op: 8340 avg bytes received per op: 136
backlog wait: 0.635158 RTT: 0.128525 total execute time: 0.827242 (milliseconds)
After:
write: IOPS=63.0k, BW=492MiB/s (516MB/s)(14.4GiB/30001msec); 0 zone resets
WRITE: 1891144 ops (30%)
avg bytes sent per op: 8340 avg bytes received per op: 136
backlog wait: 0.616114 RTT: 0.126842 total execute time: 0.805348 (milliseconds)
Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Refactor: surface useful show_ macros so they can be shared between
the client and server trace code.
Additional clean up:
- Housekeeping: ensure the correct #include files are pulled in
and add proper TRACE_DEFINE_ENUM where they are missing
- Use a consistent naming scheme for the helpers
- Store values to be displayed symbolically as unsigned long, as
that is the type that the __print_yada() functions take
Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
For certain special cases, RPC-related tracepoints record a -1 as
the task ID or the client ID. It's ugly for a trace event to display
4 billion in these cases.
To help keep SUNRPC tracepoints consistent, create a macro that
defines the print format specifiers for tk_pid and cl_clid. At some
point in the future we might try tk_pid with a wider range of values
than 0..64K so this makes it easier to make that change.
Document the FAN_FS_ERROR event for user administrators and user space
developers.
Link: https://lore.kernel.org/r/20211025192746.66445-32-krisman@collabora.com Reviewed-by: Amir Goldstein <amir73il@gmail.com> Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com> Reviewed-by: Jan Kara <jack@suse.cz> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Send a FS_ERROR message via fsnotify to a userspace monitoring tool
whenever a ext4 error condition is triggered. This follows the existing
error conditions in ext4, so it is hooked to the ext4_error* functions.
Link: https://lore.kernel.org/r/20211025192746.66445-30-krisman@collabora.com Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com> Acked-by: Theodore Ts'o <tytso@mit.edu> Reviewed-by: Amir Goldstein <amir73il@gmail.com> Reviewed-by: Jan Kara <jack@suse.cz> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Wire up the FAN_FS_ERROR event in the fanotify_mark syscall, allowing
user space to request the monitoring of FAN_FS_ERROR events.
These events are limited to filesystem marks, so check it is the
case in the syscall handler.
Link: https://lore.kernel.org/r/20211025192746.66445-29-krisman@collabora.com Reviewed-by: Amir Goldstein <amir73il@gmail.com> Reviewed-by: Jan Kara <jack@suse.cz> Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
The error info is a record sent to users on FAN_FS_ERROR events
documenting the type of error. It also carries an error count,
documenting how many errors were observed since the last reporting.
Link: https://lore.kernel.org/r/20211025192746.66445-28-krisman@collabora.com Reviewed-by: Amir Goldstein <amir73il@gmail.com> Reviewed-by: Jan Kara <jack@suse.cz> Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Plumb the pieces to add a FID report to error records. Since all error
event memory must be pre-allocated, we pre-allocate the maximum file
handle size possible, such that it should always fit.
For errors that don't expose a file handle, report it with an invalid
FID. Internally we use zero-length FILEID_ROOT file handle for passing
the information (which we report as zero-length FILEID_INVALID file
handle to userspace) so we update the handle reporting code to deal with
this case correctly.
struct fanotify_error_event, at least, is preallocated and isn't able to
to handle arbitrarily large file handles. Future-proof the code by
complaining loudly if a handle larger than MAX_HANDLE_SZ is ever found.
Link: https://lore.kernel.org/r/20211025192746.66445-26-krisman@collabora.com Reviewed-by: Amir Goldstein <amir73il@gmail.com> Reviewed-by: Jan Kara <jack@suse.cz> Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Now that there is an event that reports FID records even for a zeroed
file handle, wrap the logic that deides whether to issue the records
into helper functions. This shouldn't have any impact on the code, but
simplifies further patches.
Link: https://lore.kernel.org/r/20211025192746.66445-24-krisman@collabora.com Reviewed-by: Jan Kara <jack@suse.cz> Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com> Reviewed-by: Amir Goldstein <amir73il@gmail.com> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
fanotify_error_event would duplicate this sequence of declarations that
already exist elsewhere with a slight different size. Create a helper
macro to avoid code duplication.
Link: https://lore.kernel.org/r/20211025192746.66445-23-krisman@collabora.com Suggested-by: Jan Kara <jack@suse.cz> Reviewed-by: Amir Goldstein <amir73il@gmail.com> Reviewed-by: Jan Kara <jack@suse.cz> Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Error events (FAN_FS_ERROR) against the same file system can be merged
by simply iterating the error count. The hash is taken from the fsid,
without considering the FH. This means that only the first error object
is reported.
Link: https://lore.kernel.org/r/20211025192746.66445-22-krisman@collabora.com Reviewed-by: Amir Goldstein <amir73il@gmail.com> Reviewed-by: Jan Kara <jack@suse.cz> Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Once an error event is triggered, enqueue it in the notification group,
similarly to what is done for other events. FAN_FS_ERROR is not
handled specially, since the memory is now handled by a preallocated
mempool.
For now, make the event unhashed. A future patch implements merging of
this kind of event.
Link: https://lore.kernel.org/r/20211025192746.66445-21-krisman@collabora.com Reviewed-by: Jan Kara <jack@suse.cz> Reviewed-by: Amir Goldstein <amir73il@gmail.com> Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Pre-allocate slots for file system errors to have greater chances of
succeeding, since error events can happen in GFP_NOFS context. This
patch introduces a group-wide mempool of error events, shared by all
FAN_FS_ERROR marks in this group.
Link: https://lore.kernel.org/r/20211025192746.66445-20-krisman@collabora.com Reviewed-by: Amir Goldstein <amir73il@gmail.com> Reviewed-by: Jan Kara <jack@suse.cz> Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
FAN_FS_ERROR allows reporting of event type FS_ERROR to userspace, which
is a mechanism to report file system wide problems via fanotify. This
commit preallocate userspace visible bits to match the FS_ERROR event.
Link: https://lore.kernel.org/r/20211025192746.66445-19-krisman@collabora.com Reviewed-by: Jan Kara <jack@suse.cz> Reviewed-by: Amir Goldstein <amir73il@gmail.com> Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Expose a new type of fsnotify event for filesystems to report errors for
userspace monitoring tools. fanotify will send this type of
notification for FAN_FS_ERROR events. This also introduce a helper for
generating the new event.
Link: https://lore.kernel.org/r/20211025192746.66445-18-krisman@collabora.com Reviewed-by: Amir Goldstein <amir73il@gmail.com> Reviewed-by: Jan Kara <jack@suse.cz> Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Like inode events, FAN_FS_ERROR will require fid mode. Therefore,
convert the verification during fanotify_mark(2) to require fid for any
non-fd event. This means fid_mode will not only be required for inode
events, but for any event that doesn't provide a descriptor.
Link: https://lore.kernel.org/r/20211025192746.66445-17-krisman@collabora.com Suggested-by: Amir Goldstein <amir73il@gmail.com> Reviewed-by: Jan Kara <jack@suse.cz> Reviewed-by: Amir Goldstein <amir73il@gmail.com> Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Instead of failing, encode an invalid file handle in fanotify_encode_fh
if no inode is provided. This bogus file handle will be reported by
FAN_FS_ERROR for non-inode errors.
Link: https://lore.kernel.org/r/20211025192746.66445-16-krisman@collabora.com Reviewed-by: Amir Goldstein <amir73il@gmail.com> Reviewed-by: Jan Kara <jack@suse.cz> Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Allow passing a NULL hash to fanotify_encode_fh and avoid calculating
the hash if not needed.
Link: https://lore.kernel.org/r/20211025192746.66445-15-krisman@collabora.com Reviewed-by: Jan Kara <jack@suse.cz> Reviewed-by: Amir Goldstein <amir73il@gmail.com> Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
FAN_FS_ERROR doesn't support DFID, but this function is still called for
every event. The problem is that it is not capable of handling null
inodes, which now can happen in case of superblock error events. For
this case, just returning dir will be enough.
Link: https://lore.kernel.org/r/20211025192746.66445-14-krisman@collabora.com Reviewed-by: Amir Goldstein <amir73il@gmail.com> Reviewed-by: Jan Kara <jack@suse.cz> Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
For group-wide mempool backed events, like FS_ERROR, the free_event
callback will need to reference the group's mempool to free the memory.
Wire that argument into the current callers.
Link: https://lore.kernel.org/r/20211025192746.66445-13-krisman@collabora.com Reviewed-by: Jan Kara <jack@suse.cz> Reviewed-by: Amir Goldstein <amir73il@gmail.com> Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
FAN_FS_ERROR allows events without inodes - i.e. for file system-wide
errors. Even though fsnotify_handle_inode_event is not currently used
by fanotify, this patch protects other backends from cases where neither
inode or dir are provided. Also document the constraints of the
interface (inode and dir cannot be both NULL).
Link: https://lore.kernel.org/r/20211025192746.66445-12-krisman@collabora.com Suggested-by: Amir Goldstein <amir73il@gmail.com> Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com> Reviewed-by: Amir Goldstein <amir73il@gmail.com> Reviewed-by: Jan Kara <jack@suse.cz> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Some file system events (i.e. FS_ERROR) might not be associated with an
inode or directory. For these, we can retrieve the super block from the
data field. But, since the super_block is available in the data field
on every event type, simplify the code to always retrieve it from there,
through a new helper.
Link: https://lore.kernel.org/r/20211025192746.66445-11-krisman@collabora.com Suggested-by: Jan Kara <jack@suse.cz> Reviewed-by: Amir Goldstein <amir73il@gmail.com> Reviewed-by: Jan Kara <jack@suse.cz> Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
fsnotify_add_event is growing in number of parameters, which in most
case are just passed a NULL pointer. So, split out a new
fsnotify_insert_event function to clean things up for users who don't
need an insert hook.
Link: https://lore.kernel.org/r/20211025192746.66445-10-krisman@collabora.com Suggested-by: Amir Goldstein <amir73il@gmail.com> Reviewed-by: Amir Goldstein <amir73il@gmail.com> Reviewed-by: Jan Kara <jack@suse.cz> Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Similarly to fanotify_is_perm_event and friends, provide a helper
predicate to say whether a mask is of an overflow event.
Link: https://lore.kernel.org/r/20211025192746.66445-9-krisman@collabora.com Suggested-by: Amir Goldstein <amir73il@gmail.com> Reviewed-by: Amir Goldstein <amir73il@gmail.com> Reviewed-by: Jan Kara <jack@suse.cz> Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
"FS_IN_IGNORED is completely internal to inotify and there is no need
to set it in i_fsnotify_mask at all, so if we remove the bit from the
output of inotify_arg_to_mask() no functionality will change and we will
be able to overload the event bit for FS_ERROR."
This is done in preparation to overload FS_ERROR with the notification
mechanism in fanotify.
Link: https://lore.kernel.org/r/20211025192746.66445-8-krisman@collabora.com Suggested-by: Amir Goldstein <amir73il@gmail.com> Reviewed-by: Amir Goldstein <amir73il@gmail.com> Reviewed-by: Jan Kara <jack@suse.cz> Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
FAN_FS_ERROR will require fsid, but not necessarily require the
filesystem to expose a file handle. Split those checks into different
functions, so they can be used separately when setting up an event.
While there, update a comment about tmpfs having 0 fsid, which is no
longer true.
Link: https://lore.kernel.org/r/20211025192746.66445-7-krisman@collabora.com Reviewed-by: Amir Goldstein <amir73il@gmail.com> Reviewed-by: Jan Kara <jack@suse.cz> Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Every time this function is invoked, it is immediately added to
FAN_EVENT_METADATA_LEN, since there is no need to just calculate the
length of info records. This minor clean up folds the rest of the
calculation into the function, which now operates in terms of events,
returning the size of the entire event, including metadata.
Link: https://lore.kernel.org/r/20211025192746.66445-6-krisman@collabora.com Reviewed-by: Amir Goldstein <amir73il@gmail.com> Reviewed-by: Jan Kara <jack@suse.cz> Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Some events, like the overflow event, are not mergeable, so they are not
hashed. But, when failing inside fsnotify_add_event for lack of space,
fsnotify_add_event() still calls the insert hook, which adds the
overflow event to the merge list. Add a check to prevent any kind of
unmergeable event to be inserted in the hashtable.
Fixes: 94e00d28a680 ("fsnotify: use hash table for faster events merge") Link: https://lore.kernel.org/r/20211025192746.66445-5-krisman@collabora.com Reviewed-by: Amir Goldstein <amir73il@gmail.com> Reviewed-by: Jan Kara <jack@suse.cz> Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Clarify argument names and contract for fsnotify_create() and
fsnotify_mkdir() to reflect the anomaly of kernfs, which leaves dentries
negavite after mkdir/create.
Remove the WARN_ON(!inode) in audit code that were added by the Fixes
commit under the wrong assumption that dentries cannot be negative after
mkdir/create.
Define a new data type to pass for event - FSNOTIFY_EVENT_DENTRY.
Use it to pass the dentry instead of it's ->d_inode where available.
This is needed in preparation to the refactor to retrieve the super
block from the data field. In some cases (i.e. mkdir in kernfs), the
data inode comes from a negative dentry, such that no super block
information would be available. By receiving the dentry itself, instead
of the inode, fsnotify can derive the super block even on these cases.
Link: https://lore.kernel.org/r/20211025192746.66445-3-krisman@collabora.com Reviewed-by: Jan Kara <jack@suse.cz> Signed-off-by: Amir Goldstein <amir73il@gmail.com>
[Expand explanation in commit message] Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Align the arguments of fsnotify_name() to those of fsnotify().
Link: https://lore.kernel.org/r/20211025192746.66445-2-krisman@collabora.com Reviewed-by: Jan Kara <jack@suse.cz> Signed-off-by: Amir Goldstein <amir73il@gmail.com> Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Where 0x35d is a static call site that's turned into a conditional
tail-call using the Jcc class of instructions.
Teach the in-line static call text patching about this.
Notably, since there is no conditional-ret, in that case patch the Jcc
to point at an empty stub function that does the ret -- or the return
thunk when needed.
Reported-by: "Erhard F." <erhard_f@mailbox.org>
Change-Id: I99c8fc3f721e5d1c74f06710b38d4bac5230303a Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Signed-off-by: Ingo Molnar <mingo@kernel.org> Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org> Link: https://lore.kernel.org/r/Y9Kdg9QjHkr9G5b5@hirez.programming.kicks-ass.net
[cascardo: __static_call_validate didn't have the bool tramp argument] Signed-off-by: Thadeu Lima de Souza Cascardo <cascardo@igalia.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
In order to re-write Jcc.d32 instructions text_poke_bp() needs to be
taught about them.
The biggest hurdle is that the whole machinery is currently made for 5
byte instructions and extending this would grow struct text_poke_loc
which is currently a nice 16 bytes and used in an array.
However, since text_poke_loc contains a full copy of the (s32)
displacement, it is possible to map the Jcc.d32 2 byte opcodes to
Jcc.d8 1 byte opcode for the int3 emulation.
This then leaves the replacement bytes; fudge that by only storing the
last 5 bytes and adding the rule that 'length == 6' instruction will
be prefixed with a 0x0f byte.
Change-Id: Ie3f72c6b92f865d287c8940e5a87e59d41cfaa27 Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Signed-off-by: Ingo Molnar <mingo@kernel.org> Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org> Link: https://lore.kernel.org/r/20230123210607.115718513@infradead.org
[cascardo: there is no emit_call_track_retpoline] Signed-off-by: Thadeu Lima de Souza Cascardo <cascardo@igalia.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Mitigation for RFDS requires RFDS_CLEAR capability which is enumerated
by MSR_IA32_ARCH_CAPABILITIES bit 27. If the host has it set, export it
to guests so that they can deploy the mitigation.
RFDS_NO indicates that the system is not vulnerable to RFDS, export it
to guests so that they don't deploy the mitigation unnecessarily. When
the host is not affected by X86_BUG_RFDS, but has RFDS_NO=0, synthesize
RFDS_NO to the guest.
Signed-off-by: Pawan Gupta <pawan.kumar.gupta@linux.intel.com> Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Josh Poimboeuf <jpoimboe@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
RFDS is a CPU vulnerability that may allow userspace to infer kernel
stale data previously used in floating point registers, vector registers
and integer registers. RFDS only affects certain Intel Atom processors.
Intel released a microcode update that uses VERW instruction to clear
the affected CPU buffers. Unlike MDS, none of the affected cores support
SMT.
Add RFDS bug infrastructure and enable the VERW based mitigation by
default, that clears the affected buffers just before exiting to
userspace. Also add sysfs reporting and cmdline parameter
"reg_file_data_sampling" to control the mitigation.
For details see:
Documentation/admin-guide/hw-vuln/reg-file-data-sampling.rst
[ pawan: - Resolved conflicts in sysfs reporting.
- s/ATOM_GRACEMONT/ALDERLAKE_N/ATOM_GRACEMONT is called
ALDERLAKE_N in 6.6. ]
Signed-off-by: Pawan Gupta <pawan.kumar.gupta@linux.intel.com> Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Josh Poimboeuf <jpoimboe@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Currently MMIO Stale Data mitigation for CPUs not affected by MDS/TAA is
to only deploy VERW at VMentry by enabling mmio_stale_data_clear static
branch. No mitigation is needed for kernel->user transitions. If such
CPUs are also affected by RFDS, its mitigation may set
X86_FEATURE_CLEAR_CPU_BUF to deploy VERW at kernel->user and VMentry.
This could result in duplicate VERW at VMentry.
Fix this by disabling mmio_stale_data_clear static branch when
X86_FEATURE_CLEAR_CPU_BUF is enabled.
Signed-off-by: Pawan Gupta <pawan.kumar.gupta@linux.intel.com> Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com> Reviewed-by: Dave Hansen <dave.hansen@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
During VMentry VERW is executed to mitigate MDS. After VERW, any memory
access like register push onto stack may put host data in MDS affected
CPU buffers. A guest can then use MDS to sample host data.
Although likelihood of secrets surviving in registers at current VERW
callsite is less, but it can't be ruled out. Harden the MDS mitigation
by moving the VERW mitigation late in VMentry path.
Note that VERW for MMIO Stale Data mitigation is unchanged because of
the complexity of per-guest conditional VERW which is not easy to handle
that late in asm with no GPRs available. If the CPU is also affected by
MDS, VERW is unconditionally executed late in asm regardless of guest
having MMIO access.
Use EFLAGS.CF instead of EFLAGS.ZF to track whether to use VMRESUME versus
VMLAUNCH. Freeing up EFLAGS.ZF will allow doing VERW, which clobbers ZF,
for MDS mitigations as late as possible without needing to duplicate VERW
for both paths.
[ pawan: resolved merge conflict in __vmx_vcpu_run in backport. ]
Signed-off-by: Sean Christopherson <seanjc@google.com> Signed-off-by: Pawan Gupta <pawan.kumar.gupta@linux.intel.com> Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com> Reviewed-by: Nikolay Borisov <nik.borisov@suse.com> Link: https://lore.kernel.org/all/20240213-delay-verw-v8-5-a6216d83edb7%40linux.intel.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
The VERW mitigation at exit-to-user is enabled via a static branch
mds_user_clear. This static branch is never toggled after boot, and can
be safely replaced with an ALTERNATIVE() which is convenient to use in
asm.
Switch to ALTERNATIVE() to use the VERW mitigation late in exit-to-user
path. Also remove the now redundant VERW in exc_nmi() and
arch_exit_to_user_mode().
projects / users / dwmw2 / linux.git / log