This can happen if a file is closed during unix socket GC. The same bug
was fixed for devfs descriptors in r228361.
PR: 242913
Reported and tested by: iz-rpi03@hs-karlsruhe.de
Reviewed by: hselasky, kib
MFC after: 1 week
Sponsored by: The FreeBSD Foundation
Differential Revision: https://reviews.freebsd.org/D23178
Filesystems which want to use it in limited capacity can employ the
VOP_UNLOCK_FLAGS macro.
Reviewed by: kib (previous version)
Differential Revision: https://reviews.freebsd.org/D21427
removed from objects including calls to free. Pages must not be xbusy
when freed and not on an object. Strengthen assertions to match these
expectations. In practice very little code had to change busy handling
to meet these rules but we can now make stronger guarantees to busy
holders and avoid conditionally dropping busy in free.
Refine vm_page_remove() and vm_page_replace() semantics now that we have
stronger guarantees about busy state. This removes redundant and
potentially problematic code that has proliferated.
Discussed with: markj
Reviewed by: kib
Differential Revision: https://reviews.freebsd.org/D22822
Don't hold the scheduler lock while doing context switches. Instead we
unlock after selecting the new thread and switch within a spinlock
section leaving interrupts and preemption disabled to prevent local
concurrency. This means that mi_switch() is entered with the thread
locked but returns without. This dramatically simplifies scheduler
locking because we will not hold the schedlock while spinning on
blocked lock in switch.
This change has not been made to 4BSD but in principle it would be
more straightforward.
Discussed with: markj
Reviewed by: kib
Tested by: pho
Differential Revision: https://reviews.freebsd.org/D22778
Eliminate recursion from most thread_lock consumers. Return from
sched_add() without the thread_lock held. This eliminates unnecessary
atomics and lock word loads as well as reducing the hold time for
scheduler locks. This will eventually allow for lockless remote adds.
Discussed with: kib
Reviewed by: jhb
Tested by: pho
Differential Revision: https://reviews.freebsd.org/D22626
The LinuxKPI linux_dma code calls PCTRIE_INSERT with a
mutex held, but does not set M_NOWAIT when allocating
nodes, leading to a potential panic. All of this code
can handle an allocation failure here, so prefer an
allocation failure to sleeping on memory.
Also fix a related case where NOWAIT/WAITOK was not
specified. In this case it's not clear whether sleeping
is allowed so be conservative and assume not. There are
a lot of other paths in this code that can fail due to
a lack of memory anyway.
Differential Revision: https://reviews.freebsd.org/D22127
Reviewed by: imp
Sponsored by: Dell EMC Isilon
MFC After: 1 week
Atomics are used for page busy and valid state when the shared busy is
held. The details of the locking protocol and valid and dirty
synchronization are in the updated vm_page.h comments.
Reviewed by: kib, markj
Tested by: pho
Sponsored by: Netflix, Intel
Differential Revision: https://reviews.freebsd.org/D21594
A work callback may restart itself. Loop in the drain function to see if the
work has been rescheduled and stop the subsequent reschedules, if any.
MFC after: 1 week
Sponsored by: Mellanox Technologies
- VM_ALLOC_NOCREAT will grab without creating a page.
- vm_page_grab_valid() will grab and page in if necessary.
- vm_page_busy_acquire() automates some busy acquire loops.
Discussed with: alc, kib, markj
Tested by: pho (part of larger branch)
Sponsored by: Netflix
Differential Revision: https://reviews.freebsd.org/D21546
There are several mechanisms by which a vm_page reference is held,
preventing the page from being freed back to the page allocator. In
particular, holding the page's object lock is sufficient to prevent the
page from being freed; holding the busy lock or a wiring is sufficent as
well. These references are protected by the page lock, which must
therefore be acquired for many per-page operations. This results in
false sharing since the page locks are external to the vm_page
structures themselves and each lock protects multiple structures.
Transition to using an atomically updated per-page reference counter.
The object's reference is counted using a flag bit in the counter. A
second flag bit is used to atomically block new references via
pmap_extract_and_hold() while removing managed mappings of a page.
Thus, the reference count of a page is guaranteed not to increase if the
page is unbusied, unmapped, and the object's write lock is held. As
a consequence of this, the page lock no longer protects a page's
identity; operations which move pages between objects are now
synchronized solely by the objects' locks.
The vm_page_wire() and vm_page_unwire() KPIs are changed. The former
requires that either the object lock or the busy lock is held. The
latter no longer has a return value and may free the page if it releases
the last reference to that page. vm_page_unwire_noq() behaves the same
as before; the caller is responsible for checking its return value and
freeing or enqueuing the page as appropriate. vm_page_wire_mapped() is
introduced for use in pmap_extract_and_hold(). It fails if the page is
concurrently being unmapped, typically triggering a fallback to the
fault handler. vm_page_wire() no longer requires the page lock and
vm_page_unwire() now internally acquires the page lock when releasing
the last wiring of a page (since the page lock still protects a page's
queue state). In particular, synchronization details are no longer
leaked into the caller.
The change excises the page lock from several frequently executed code
paths. In particular, vm_object_terminate() no longer bounces between
page locks as it releases an object's pages, and direct I/O and
sendfile(SF_NOCACHE) completions no longer require the page lock. In
these latter cases we now get linear scalability in the common scenario
where different threads are operating on different files.
__FreeBSD_version is bumped. The DRM ports have been updated to
accomodate the KPI changes.
Reviewed by: jeff (earlier version)
Tested by: gallatin (earlier version), pho
Sponsored by: Netflix
Differential Revision: https://reviews.freebsd.org/D20486
PowerPC, and possibly other architectures, use different address ranges for
PCI space vs physical address space, which is only mapped at resource
activation time, when the BAR gets written. The DRM kernel modules do not
activate the rman resources, soas not to waste KVA, instead only mapping
parts of the PCI memory at a time. This introduces a
BUS_TRANSLATE_RESOURCE() method, implemented in the Open Firmware/FDT PCI
driver, to perform this necessary translation without activating the
resource.
In addition to system KPI changes, LinuxKPI is updated to handle a
big-endian host, by adding proper endian swaps to the I/O functions.
Submitted by: mmacy
Reported by: hselasky
Differential Revision: https://reviews.freebsd.org/D21096
The hold_count and wire_count fields of struct vm_page are separate
reference counters with similar semantics. The remaining essential
differences are that holds are not counted as a reference with respect
to LRU, and holds have an implicit free-on-last unhold semantic whereas
vm_page_unwire() callers must explicitly determine whether to free the
page once the last reference to the page is released.
This change removes the KPIs which directly manipulate hold_count.
Functions such as vm_fault_quick_hold_pages() now return wired pages
instead. Since r328977 the overhead of maintaining LRU for wired pages
is lower, and in many cases vm_fault_quick_hold_pages() callers would
swap holds for wirings on the returned pages anyway, so with this change
we remove a number of page lock acquisitions.
No functional change is intended. __FreeBSD_version is bumped.
Reviewed by: alc, kib
Discussed with: jeff
Discussed with: jhb, np (cxgbe)
Tested by: pho (previous version)
Sponsored by: Netflix
Differential Revision: https://reviews.freebsd.org/D19247
LINUXKPI_VERSION macro is not defined for any compiled LinuxKPI code
which basically means __GFP_NOTWIRED is never checked when allocating
pages. This should work fine with the existing external DRM code as
long as the page wiring and unwiring is balanced.
MFC after: 3 days
Sponsored by: Mellanox Technologies
These calls are not the same in general: the former will dequeue the
page if it is enqueued, while the latter will just leave it alone. But,
all existing uses of the former apply to unmanaged pages, which are
never enqueued in the first place. No functional change intended.
Reviewed by: kib
MFC after: 1 week
Sponsored by: Netflix
Differential Revision: https://reviews.freebsd.org/D20470
Previously it did this only on platforms without a direct map. This
also more closely matches Linux's semantics.
Since some DRM v5.0 code assumes the old behaviour, use a
LINUXKPI_VERSION guard to preserve that until the out-of-tree module
is updated.
Reviewed by: hselasky, kib (earlier versions), johalun
MFC after: 1 week
Sponsored by: Netflix
Differential Revision: https://reviews.freebsd.org/D20502
This was enumerated with exhaustive search for sys/eventhandler.h includes,
cross-referenced against EVENTHANDLER_* usage with the comm(1) utility. Manual
checking was performed to avoid redundant includes in some drivers where a
common os_bsd.h (for example) included sys/eventhandler.h indirectly, but it is
possible some of these are redundant with driver-specific headers in ways I
didn't notice.
(These CUs did not show up as missing eventhandler.h in tinderbox.)
X-MFC-With: r347984
DRM drivers expect tasklets to have a counter for enable/disable calls.
Also, add a few more tasklet locking functions.
This patch is part of D19565
Reviewed by: hps
Approved by: imp (mentor), hps
MFC after: 1 week
Assign self as group leader at creation to act as the only member of a
new process group.
This patch is part of D19565
Reviewed by: hps
Approved by: imp (mentor), hps
MFC after: 1 week
Check LINUXKPI_VERSION macro for backwards compatibility.
It's recommended to update any drivers that depend on the older KPI
so we can deprecate < 5.0 code as we update to newer Linux version.
This patch is part of D19565
Reviewed by: hps
Approved by: imp (mentor), hps
MFC after: 1 week
Turning on pr_debug at compile time make it non-optional at runtime.
This often means that the amount of the debugging is unbearable.
Allow developer to turn on pr_debug output only when needed.
Build tested drm-current-kmod prior to commit.
MFC after: 1 week
Submitted by: kib@
Sponsored by: Mellanox Technologies
The S/G list must be mapped AS-IS without any optimisations.
This also implies that sg_dma_len() must be equal to sg->length.
Many Linux drivers assume this and this fixes some DRM issues.
Put the BUS DMA map pointer into the scatter-gather list to
allow multiple mappings on the same physical memory address.
The FreeBSD version has been bumped to force recompilation of
external kernel modules.
Sponsored by: Mellanox Technologies
Make function macro wrappers for locking and unlocking to ease readability.
No functional change.
Discussed with: kib@, tychon@ and zeising@
Sponsored by: Mellanox Technologies
The <sys/pctrie.h> APIs expect a 64-bit DMA key.
This is fine as long as the DMA is less than or equal to 64 bits, which
is currently the case.
Sponsored by: Mellanox Technologies
Some consumers may be loosely coupled with the lkpi.
This allows them to call linux_alloc_current without
having a static dependency.
Reviewed by: hps@
MFC after: 1 week
Sponsored by: iX Systems
Differential Revision: https://reviews.freebsd.org/D19257
So far, intr_{g,s}etaffinity(9) take a single int for identifying
a device interrupt. This approach doesn't work on all architectures
supported, as a single int isn't sufficient to globally specify a
device interrupt. In particular, with multiple interrupt controllers
in one system as found on e. g. arm and arm64 machines, an interrupt
number as returned by rman_get_start(9) may be only unique relative
to the bus and, thus, interrupt controller, a certain device hangs
off from.
In turn, this makes taskqgroup_attach{,_cpu}(9) and - internal to
the gtaskqueue implementation - taskqgroup_attach_deferred{,_cpu}()
not work across architectures. Yet in turn, iflib(4) as gtaskqueue
consumer so far doesn't fit architectures where interrupt numbers
aren't globally unique.
However, at least for intr_setaffinity(..., CPU_WHICH_IRQ, ...) as
employed by the gtaskqueue implementation to bind an interrupt to a
particular CPU, using bus_bind_intr(9) instead is equivalent from
a functional point of view, with bus_bind_intr(9) taking the device
and interrupt resource arguments required for uniquely specifying a
device interrupt.
Thus, change the gtaskqueue implementation to employ bus_bind_intr(9)
instead and intr_{g,s}etaffinity(9) to take the device and interrupt
resource arguments required respectively. This change also moves
struct grouptask from <sys/_task.h> to <sys/gtaskqueue.h> and wraps
struct gtask along with the gtask_fn_t typedef into #ifdef _KERNEL
as userland likes to include <sys/_task.h> or indirectly drags it
in - for better or worse also with _KERNEL defined -, which with
device_t and struct resource dependencies otherwise is no longer
as easily possible now.
The userland inclusion problem probably can be improved a bit by
introducing a _WANT_TASK (as well as a _WANT_MOUNT) akin to the
existing _WANT_PRISON etc., which is orthogonal to this change,
though, and likely needs an exp-run.
While at it:
- Change the gt_cpu member in the grouptask structure to be of type
int as used elswhere for specifying CPUs (an int16_t may be too
narrow sooner or later),
- move the gtaskqueue_enqueue_fn typedef from <sys/gtaskqueue.h> to
the gtaskqueue implementation as it's only used and needed there,
- change the GTASK_INIT macro to use "gtask" rather than "task" as
argument given that it actually operates on a struct gtask rather
than a struct task, and
- let subr_gtaskqueue.c consistently use __func__ to print functions
names.
Reported by: mmel
Reviewed by: mmel
Differential Revision: https://reviews.freebsd.org/D19139
