r333273 and partially reverted with r333594.
Older CPUs implement addition of offsets into the page table by a
bitwise OR rather than actual addition, which only works if the table is
aligned at a multiple of its own size (they also require it to be aligned
at a multiple of 256KB). Newer ones do not have that requirement, but it
hardly matters to enforce it anyway.
The original code was failing on newer systems with huge amounts of RAM
(> 512 GB), in which the page table was 4 GB in size. Because the
bootstrap memory allocator took its alignment parameter as an int, this
turned into a 0, removing any alignment constraint at all and making
the MMU fail. The first round of this patch (r333273) fixed this case by
aligning it at 256 KB, which broke older CPUs. Fix this instead by widening
the alignment parameter.
The POWER9 MMU (PowerISA 3.0) is slightly different from current
configurations, using a partition table even for hypervisor mode, and
dropping the SDR1 register. Key off the newly early-enabled CPU features
flags for the new architecture, and configure the MMU appropriately.
The POWER9 MMU ignores the "PSIZ" field in the PTCR, and expects a 64kB
table. As we are enabled for powernv (hypervisor mode, no VMs), only
initialize partition table entry 0, and zero out the rest. The actual
contents of the register are identical to SDR1 from previous architectures.
Along with this, fix a bug in the page table allocation with very large
memory. The table can be allocated on any 256k boundary. The
bootstrap_alloc alignment argument is an int, and with large amounts of
memory passing the size of the table as the alignment will overflow an
integer. Hard-code the alignment at 256k as wider alignment is not
necessary.
Reviewed by: nwhitehorn
Tested by: Breno Leitao
Relnotes: Yes
region marked "available" by firmware is contained entirely in the kernel.
This had a tendency to happen with FDTs passed by loader, though could for
other reasons as well, and would result in the kernel slowly cannibalizing
itself for other purposes, eventually resulting in a crash.
A similar fix is needed for mmu_oea.c and should probably just be rolled
at that point into some generic code in platform.c for taking a mem_region
list and removing chunks.
PR: 226974
Submitted by: leandro.lupori@gmail.com
Reviewed by: jhibbits
Differential Revision: D15121
opt_compat.h is mentioned in nearly 180 files. In-progress network
driver compabibility improvements may add over 100 more so this is
closer to "just about everywhere" than "only some files" per the
guidance in sys/conf/options.
Keep COMPAT_LINUX32 in opt_compat.h as it is confined to a subset of
sys/compat/linux/*.c. A fake _COMPAT_LINUX option ensure opt_compat.h
is created on all architectures.
Move COMPAT_LINUXKPI to opt_dontuse.h as it is only used to control the
set of compiled files.
Reviewed by: kib, cem, jhb, jtl
Sponsored by: DARPA, AFRL
Differential Revision: https://reviews.freebsd.org/D14941
When the kernel can be in real mode in early boot, we can execute from
high addresses aliased to the kernel's physical memory. If that high
address has the first two bits set to 1 (0xc...), those addresses will
automatically become part of the direct map. This reduces page table
pressure from the kernel and it sets up the kernel to be used with
radix translation, for which it has to be up here.
This is accomplished by exploiting the fact that all PowerPC kernels are
built as position-independent executables and relocate themselves
on start. Before this patch, the kernel runs at 1:1 VA:PA, but that
VA/PA is random and set by the bootloader. Very early, it processes
its ELF relocations to operate wherever it happens to find itself.
This patch uses that mechanism to re-enter and re-relocate the kernel
a second time witha new base address set up in the early parts of
powerpc_init().
Reviewed by: jhibbits
Differential Revision: D14647
accomplishes a few things:
- Makes NULL an invalid address in the kernel, which is useful for catching
bugs.
- Lays groundwork for radix-tree translation on POWER9, which requires the
direct map be at high memory.
- Similarly lays groundwork for a direct map on 64-bit Book-E.
The new base address is chosen as the base of the fourth radix quadrant
(the minimum kernel address in this translation mode) and because all
supported CPUs ignore at least the first two bits of addresses in real
mode, allowing direct-map addresses to be used in real-mode handlers.
This is required by Linux and is part of the architecture standard
starting in POWER ISA 3, so can be relied upon.
Reviewed by: jhibbits, Breno Leitao
Differential Revision: D14499
Make vm_wait() take the vm_object argument which specifies the domain
set to wait for the min condition pass. If there is no object
associated with the wait, use curthread' policy domainset. The
mechanics of the wait in vm_wait() and vm_wait_domain() is supplied by
the new helper vm_wait_doms(), which directly takes the bitmask of the
domains to wait for passing min condition.
Eliminate pagedaemon_wait(). vm_domain_clear() handles the same
operations.
Eliminate VM_WAIT and VM_WAITPFAULT macros, the direct functions calls
are enough.
Eliminate several control state variables from vm_domain, unneeded
after the vm_wait() conversion.
Scetched and reviewed by: jeff
Tested by: pho
Sponsored by: The FreeBSD Foundation, Mellanox Technologies
Differential revision: https://reviews.freebsd.org/D14384
This is part of a long-term goal of merging Book-E and AIM into a single GENERIC
kernel. As more work is done, the struct may be optimized further.
Reviewed by: nwhitehorn
used with hashed page tables on AIM and place it into a new, modular pmap
function called pmap_decode_kernel_ptr(). This function is the inverse
of pmap_map_user_ptr(). With POWER9 radix tables, which mapping to use
becomes more complex than just AIM/BOOKE and it is best to have it in
the same place as pmap_map_user_ptr().
Reviewed by: jhibbits
to which it is specific, rather than in the generic AIM startup code. This
will be required to support the radix-table-based MMU introduced with POWER9.
buffers into a new pmap-module function pmap_map_user_ptr() that can
be implemented by the respective modules. This is required to implement
non-segment-based AIM-ish MMU systems such as the radix-tree page tables
introduced by POWER ISA 3.0 and present on POWER9.
Reviewed by: jhibbits
using a new macro PHYS_TO_DMAP, which deliberately has the same name as the
equivalent macro on amd64. This also sets the stage for moving the direct
map to another base address.
domains can be done by the _domain() API variants. UMA also supports a
first-touch policy via the NUMA zone flag.
The slab layer is now segregated by VM domains and is precise. It handles
iteration for round-robin directly. The per-cpu cache layer remains
a mix of domains according to where memory is allocated and freed. Well
behaved clients can achieve perfect locality with no performance penalty.
The direct domain allocation functions have to visit the slab layer and
so require per-zone locks which come at some expense.
Reviewed by: Attilio (a slightly older version)
Tested by: pho
Sponsored by: Netflix, Dell/EMC Isilon
Mainly focus on files that use BSD 2-Clause license, however the tool I
was using misidentified many licenses so this was mostly a manual - error
prone - task.
The Software Package Data Exchange (SPDX) group provides a specification
to make it easier for automated tools to detect and summarize well known
opensource licenses. We are gradually adopting the specification, noting
that the tags are considered only advisory and do not, in any way,
superceed or replace the license texts.
similar to the kernel memory allocator.
This simplifies NUMA allocation because the domain will be known at wait
time and races between failure and sleeping are eliminated. This also
reduces boilerplate code and simplifies callers.
A wait primitive is supplied for uma zones for similar reasons. This
eliminates some non-specific VM_WAIT calls in favor of more explicit
sleeps that may be satisfied without new pages.
Reviewed by: alc, kib, markj
Tested by: pho
Sponsored by: Netflix, Dell/EMC Isilon
Idle page zeroing has been disabled by default on all architectures since
r170816 and has some bugs that make it seemingly unusable. Specifically,
the idle-priority pagezero thread exacerbates contention for the free page
lock, and yields the CPU without releasing it in non-preemptive kernels. The
pagezero thread also does not behave correctly when superpage reservations
are enabled: its target is a function of v_free_count, which includes
reserved-but-free pages, but it is only able to zero pages belonging to the
physical memory allocator.
Reviewed by: alc, imp, kib
Differential Revision: https://reviews.freebsd.org/D7714
rounddown2 tends to produce longer lines than the original code
and when the code has a high indentation level it was not really
advantageous to do the replacement.
This tries to strike a balance between readability using the macros
and flexibility of having the expressions, so not everything is
converted.
OF_getprop() to get encode-int encoded values from the OF tree. This is
a no-op at present, since all existing PowerPC ports are big-endian, but
it is a correctness improvement and will be required if we have a
little-endian kernel at some future point.
Where it is totally impossible for the code ever to be used on a
little-endian system (much of powerpc/powermac, for instance), I have not
necessarily made the appropriate changes.
MFC after: 1 month
initial thread stack is not adjusted by the tunable, the stack is
allocated too early to get access to the kernel environment. See
TD0_KSTACK_PAGES for the thread0 stack sizing on i386.
The tunable was tested on x86 only. From the visual inspection, it
seems that it might work on arm and powerpc. The arm
USPACE_SVC_STACK_TOP and powerpc USPACE macros seems to be already
incorrect for the threads with non-default kstack size. I only
changed the macros to use variable instead of constant, since I cannot
test.
On arm64, mips and sparc64, some static data structures are sized by
KSTACK_PAGES, so the tunable is disabled.
Sponsored by: The FreeBSD Foundation
MFC after: 2 week
vm_offset_t pmap_quick_enter_page(vm_page_t m)
void pmap_quick_remove_page(vm_offset_t kva)
These will create and destroy a temporary, CPU-local KVA mapping of a specified page.
Guarantees:
--Will not sleep and will not fail.
--Safe to call under a non-sleepable lock or from an ithread
Restrictions:
--Not guaranteed to be safe to call from an interrupt filter or under a spin mutex on all platforms
--Current implementation does not guarantee more than one page of mapping space across all platforms. MI code should not make nested calls to pmap_quick_enter_page.
--MI code should not perform locking while holding onto a mapping created by pmap_quick_enter_page
The idea is to use this in busdma, for bounce buffer copies as well as virtually-indexed cache maintenance on mips and arm.
NOTE: the non-i386, non-amd64 implementations of these functions still need review and testing.
Reviewed by: kib
Approved by: kib (mentor)
Differential Revision: http://reviews.freebsd.org/D3013
On Book-E, physical addresses are actually 36-bits, not 32-bits. This is
currently worked around by ignoring the top bits. However, in some cases, the
boot loader configures CCSR to something above the 32-bit mark. This is stage 1
in updating the pmap to handle 36-bit physaddr.
Much of the code was common to begin with. There is one nit, which is likely
not an issue at all. With the old code, the AIM machdep would __syncicache()
the entire kernel core at setup. However, in the unified setup, that seems to
hang on the MPC7455, perhaps because it's running later than before. Removing
this allows it to boot just fine. Examining the code, the FreeBSD loader
already does syncicache of the full kernel, and each module loaded, so this
doesn't appear to be an actual problem.
Initial code by Nathan Whitehorn.
A couple of internal functions used by malloc(9) and uma truncated
a size_t down to an int. This could cause any number of issues
(e.g. indefinite sleeps, memory corruption) if any kernel
subsystem tried to allocate 2GB or more through malloc. zfs would
attempt such an allocation when run on a system with 2TB or more
of RAM.
Note to self: When this is MFCed, sparc64 needs the same fix.
Differential revision: https://reviews.freebsd.org/D2106
Reviewed by: kib
Reported by: Michael Fuckner <michael@fuckner.net>
Tested by: Michael Fuckner <michael@fuckner.net>
MFC after: 2 weeks
this change is to improve concurrency:
- Drop global state stored in the shadow overflow page table (and all other
global state)
- Remove all global locks
- Use per-PTE lock bits to allow parallel page insertion
- Reconstruct state when requested for evicted PTEs instead of buffering
it during overflow
This drops total wall time for make buildworld on a 32-thread POWER8 system
by a factor of two and system time by a factor of three, providing performance
20% better than similarly clocked Core i7 Xeons per-core. Performance on
smaller SMP systems, where PMAP lock contention was not as much of an issue,
is nearly unchanged.
Tested on: POWER8, POWER5+, G5 UP, G5 SMP (64-bit and 32-bit kernels)
Merged from: user/nwhitehorn/ppc64-pmap-rework
Looked over by: jhibbits, andreast
MFC after: 3 months
Relnotes: yes
Sponsored by: FreeBSD Foundation
PVO pool size. The default errs on the exceedingly large side, so absent
any intelligent automatic tuning, at least let the user set it to save
RAM on memory-constrained systems.
MFC after: 2 weeks
code in sys/kern/kern_dump.c. Most dumpsys() implementations are nearly
identical and simply redefine a number of constants and helper subroutines;
a generic implementation will make it easier to implement features around
kernel core dumps. This change does not alter any minidump code and should
have no functional impact.
PR: 193873
Differential Revision: https://reviews.freebsd.org/D904
Submitted by: Conrad Meyer <conrad.meyer@isilon.com>
Reviewed by: jhibbits (earlier version)
Sponsored by: EMC / Isilon Storage Division
the Open Firmware, as provided by petitboot, for example. Note that this is
not quite complete, since RTAS instantiation still depends on callable
firmware.
MFC after: 2 weeks
mapping size (currently unused). The flags includes the fault access
bits, wired flag as PMAP_ENTER_WIRED, and a new flag
PMAP_ENTER_NOSLEEP to indicate that pmap should not sleep.
For powerpc aim both 32 and 64 bit, fix implementation to ensure that
the requested mapping is created when PMAP_ENTER_NOSLEEP is not
specified, in particular, wait for the available memory required to
proceed.
In collaboration with: alc
Tested by: nwhitehorn (ppc aim32 and booke)
Sponsored by: The FreeBSD Foundation and EMC / Isilon Storage Division
MFC after: 2 weeks
We continue to use pmap_enter() for that. For unwiring virtual pages, we
now use pmap_unwire(), which unwires a range of virtual addresses instead
of a single virtual page.
Sponsored by: EMC / Isilon Storage Division
by the combination of r268591 and r269134: When we attempt to add the
wired attribute to an existing mapping, moea{,64}_pvo_enter() do nothing.
(They only set the wired attribute on newly created mappings.)
Tested by: andreast
pmap_unwire(), the call to MOEA64_PVO_TO_PTE() must be performed before
any changes are made to the PVO. Otherwise, MOEA64_PVO_TO_PTE() will
panic.
Reported by: andreast
The NetBSD Foundation states "Third parties are encouraged to change the
license on any files which have a 4-clause license contributed to the
NetBSD Foundation to a 2-clause license."
This change removes clauses 3 and 4 from copyright / license blocks that
list The NetBSD Foundation as the only copyright holder.
Sponsored by: The FreeBSD Foundation
pmap_clear_reference() has had exactly one caller in the kernel for
several years, more precisely, since FreeBSD 8. Now, that call no
longer exists.
Approved by: re (kib)
Sponsored by: EMC / Isilon Storage Division
chain. This repairs a panic observed during pageout on some 64-bit
PowerPC systems.
Submitted by: grehan
Approved by: re (kib)
MFC after: 2 weeks
Revisit after: 10.0
which is the part of struct vmspace, allocated from UMA_ZONE_NOFREE
zone. Initialize the pmap lock in the vmspace zone init function, and
remove pmap lock initialization and destruction from pmap_pinit() and
pmap_release().
Suggested and reviewed by: alc (previous version)
Tested by: pho
Sponsored by: The FreeBSD Foundation
Unify the 2 concept into a real, minimal, sxlock where the shared
acquisition represent the soft busy and the exclusive acquisition
represent the hard busy.
The old VPO_WANTED mechanism becames the hard-path for this new lock
and it becomes per-page rather than per-object.
The vm_object lock becames an interlock for this functionality:
it can be held in both read or write mode.
However, if the vm_object lock is held in read mode while acquiring
or releasing the busy state, the thread owner cannot make any
assumption on the busy state unless it is also busying it.
Also:
- Add a new flag to directly shared busy pages while vm_page_alloc
and vm_page_grab are being executed. This will be very helpful
once these functions happen under a read object lock.
- Move the swapping sleep into its own per-object flag
The KPI is heavilly changed this is why the version is bumped.
It is very likely that some VM ports users will need to change
their own code.
Sponsored by: EMC / Isilon storage division
Discussed with: alc
Reviewed by: jeff, kib
Tested by: gavin, bapt (older version)
Tested by: pho, scottl
transparent layering and better fragmentation.
- Normalize functions that allocate memory to use kmem_*
- Those that allocate address space are named kva_*
- Those that operate on maps are named kmap_*
- Implement recursive allocation handling for kmem_arena in vmem.
Reviewed by: alc
Tested by: pho
Sponsored by: EMC / Isilon Storage Division
