Issues were noted by Bruce Evans and are present on all architectures.
On i386, a counter fetch should use atomic read of 64bit value,
otherwise carry from the increment on other CPU could be lost for the
given fetch, making error of 2^32. If 64bit read (cmpxchg8b) is not
available on the machine, it cannot be SMP and it is enough to disable
preemption around read to avoid the split read.
On x86 the counter increment is not atomic on purpose, which makes it
possible for the store of the incremented result to override just
zeroed per-cpu slot. The effect would be a counter going off by
arbitrary value after zeroing. Perform the counter zeroing on the
same processor which does the increments, making the operations
mutually exclusive. On i386, same as for the fetching, if the
cmpxchg8b is not available, machine is not SMP and we disable
preemption for zeroing.
PowerPC64 is treated the same as amd64.
For other architectures, the changes made to allow the compilation to
succeed, without fixing the issues with zeroing or fetching. It
should be possible to handle them by using the 64bit loads and stores
atomic WRT preemption (assuming the architectures also converted from
using critical sections to proper asm). If architecture does not
provide the facility, using global (spin) mutex would be non-optimal
but working solution.
Noted by: bde
Sponsored by: The FreeBSD Foundation
o Relax locking assertions for pmap_enter_object() and add them also
to architectures that currently don't have any
o Introduce VM_OBJECT_LOCK_DOWNGRADE() which is basically a downgrade
operation on the per-object rwlock
o Use all the mechanisms above to make vm_map_pmap_enter() to work
mostl of the times only with readlocks.
Sponsored by: EMC / Isilon storage division
Reviewed by: alc
order to match the MAXCPU concept. The change should also be useful
for consolidation and consistency.
Sponsored by: EMC / Isilon storage division
Obtained from: jeff
Reviewed by: alc
and kern.cam.ctl.disable tunable; those were introduced as a workaround
to make it possible to boot GENERIC on low memory machines.
With ctl(4) being built as a module and automatically loaded by ctladm(8),
this makes CTL work out of the box.
Reviewed by: ken
Sponsored by: FreeBSD Foundation
Introduce counter(9) API, that implements fast and raceless counters,
provided (but not limited to) for gathering of statistical data.
See http://lists.freebsd.org/pipermail/freebsd-arch/2013-April/014204.html
for more details.
In collaboration with: kib
Reviewed by: luigi
Tested by: ae, ray
Sponsored by: Nginx, Inc.
most kernels before FreeBSD 9.0. Remove such modules and respective kernel
options: atadisk, ataraid, atapicd, atapifd, atapist, atapicam. Remove the
atacontrol utility and some man pages. Remove useless now options ATA_CAM.
No objections: current@, stable@
MFC after: never
do not map the b_pages pages into buffer_map KVA. The use of the
unmapped buffers eliminate the need to perform TLB shootdown for
mapping on the buffer creation and reuse, greatly reducing the amount
of IPIs for shootdown on big-SMP machines and eliminating up to 25-30%
of the system time on i/o intensive workloads.
The unmapped buffer should be explicitely requested by the GB_UNMAPPED
flag by the consumer. For unmapped buffer, no KVA reservation is
performed at all. The consumer might request unmapped buffer which
does have a KVA reserve, to manually map it without recursing into
buffer cache and blocking, with the GB_KVAALLOC flag.
When the mapped buffer is requested and unmapped buffer already
exists, the cache performs an upgrade, possibly reusing the KVA
reservation.
Unmapped buffer is translated into unmapped bio in g_vfs_strategy().
Unmapped bio carry a pointer to the vm_page_t array, offset and length
instead of the data pointer. The provider which processes the bio
should explicitely specify a readiness to accept unmapped bio,
otherwise g_down geom thread performs the transient upgrade of the bio
request by mapping the pages into the new bio_transient_map KVA
submap.
The bio_transient_map submap claims up to 10% of the buffer map, and
the total buffer_map + bio_transient_map KVA usage stays the
same. Still, it could be manually tuned by kern.bio_transient_maxcnt
tunable, in the units of the transient mappings. Eventually, the
bio_transient_map could be removed after all geom classes and drivers
can accept unmapped i/o requests.
Unmapped support can be turned off by the vfs.unmapped_buf_allowed
tunable, disabling which makes the buffer (or cluster) creation
requests to ignore GB_UNMAPPED and GB_KVAALLOC flags. Unmapped
buffers are only enabled by default on the architectures where
pmap_copy_page() was implemented and tested.
In the rework, filesystem metadata is not the subject to maxbufspace
limit anymore. Since the metadata buffers are always mapped, the
buffers still have to fit into the buffer map, which provides a
reasonable (but practically unreachable) upper bound on it. The
non-metadata buffer allocations, both mapped and unmapped, is
accounted against maxbufspace, as before. Effectively, this means that
the maxbufspace is forced on mapped and unmapped buffers separately.
The pre-patch bufspace limiting code did not worked, because
buffer_map fragmentation does not allow the limit to be reached.
By Jeff Roberson request, the getnewbuf() function was split into
smaller single-purpose functions.
Sponsored by: The FreeBSD Foundation
Discussed with: jeff (previous version)
Tested by: pho, scottl (previous version), jhb, bf
MFC after: 2 weeks
pages around, taking array of vm_page_t both for source and
destination. Starting offsets and total transfer size are specified.
The function implements optimal algorithm for copying using the
platform-specific optimizations. For instance, on the architectures
were the direct map is available, no transient mappings are created,
for i386 the per-cpu ephemeral page frame is used. The code was
typically borrowed from the pmap_copy_page() for the same
architecture.
Only i386/amd64, powerpc aim and arm/arm-v6 implementations were
tested at the time of commit. High-level code, not committed yet to
the tree, ensures that the use of the function is only allowed after
explicit enablement.
For sparc64, the existing code has known issues and a stab is added
instead, to allow the kernel linking.
Sponsored by: The FreeBSD Foundation
Tested by: pho (i386, amd64), scottl (amd64), ian (arm and arm-v6)
MFC after: 2 weeks
future further optimizations where the vm_object lock will be held
in read mode most of the time the page cache resident pool of pages
are accessed for reading purposes.
The change is mostly mechanical but few notes are reported:
* The KPI changes as follow:
- VM_OBJECT_LOCK() -> VM_OBJECT_WLOCK()
- VM_OBJECT_TRYLOCK() -> VM_OBJECT_TRYWLOCK()
- VM_OBJECT_UNLOCK() -> VM_OBJECT_WUNLOCK()
- VM_OBJECT_LOCK_ASSERT(MA_OWNED) -> VM_OBJECT_ASSERT_WLOCKED()
(in order to avoid visibility of implementation details)
- The read-mode operations are added:
VM_OBJECT_RLOCK(), VM_OBJECT_TRYRLOCK(), VM_OBJECT_RUNLOCK(),
VM_OBJECT_ASSERT_RLOCKED(), VM_OBJECT_ASSERT_LOCKED()
* The vm/vm_pager.h namespace pollution avoidance (forcing requiring
sys/mutex.h in consumers directly to cater its inlining functions
using VM_OBJECT_LOCK()) imposes that all the vm/vm_pager.h
consumers now must include also sys/rwlock.h.
* zfs requires a quite convoluted fix to include FreeBSD rwlocks into
the compat layer because the name clash between FreeBSD and solaris
versions must be avoided.
At this purpose zfs redefines the vm_object locking functions
directly, isolating the FreeBSD components in specific compat stubs.
The KPI results heavilly broken by this commit. Thirdy part ports must
be updated accordingly (I can think off-hand of VirtualBox, for example).
Sponsored by: EMC / Isilon storage division
Reviewed by: jeff
Reviewed by: pjd (ZFS specific review)
Discussed with: alc
Tested by: pho
Switch eventtimers(9) from using struct bintime to sbintime_t.
Even before this not a single driver really supported full dynamic range of
struct bintime even in theory, not speaking about practical inexpediency.
This change legitimates the status quo and cleans up the code.
When CPU becomes idle, cpu_idleclock() calculates time to the next timer
event in order to reprogram hw timer. Return that time in sbintime_t to
the caller and pass it to acpi_cpu_idle(), where it can be used as one
more factor (quite precise) to extimate furter sleep time and choose
optimal sleep state. This is a preparatory change for further callout
improvements will be committed in the next days.
The commmit is not targeted for MFC.
introduction of the PBVM, this stopped being the case. Redefine the
VM parameters so that the PBVM is included in the kernel map. In
particular this introduces VM_INIT_KERNEL_ADDRESS to point to the base
of region 5 now that VM_MIN_KERNEL_ADDRESS points to the base of
region 4 to include the PBVM.
While here define KERNBASE to the actual link address of the kernel as
is intended.
PR: 169926
points to the TLS in user space and points to the PCPU structure in
the kernel. The race is the result of having the exception handler on
the one hand and the RPC system call entry on the other. The EPC
syscall path is non-atomic in that interrupts are enabled while the
two stacks are switched. The register stack is switched last as that
is the stack used to determine whether we're going back to user space
by the exception handler. If we go back to user space, we restore r13,
otherwise we leave r13 alone. The EPC syscall path however set r13 to
the PCPU structure *before* switching the register stack, which means
that there was a window in which the exception handler would restore
r13 when it was already pointing to the PCPU structure. This is fatal
when the exception happened on CPU x, but left from the exception on
anotehr CPU. In that case r13 would point to the PCPU of the CPU the
thread was running on. This immediately results in getting the wrong
value for curthread.
The fix is to make sure we assign r13 *after* we set ar.bspstore to
point to the kernel register stack for the thread.
thread structure pointer atomically from r13 (the pcpu pointer)
for the current CPU/core.
Add a CTASSERT in machdep.c to make sure that pc_curthread is in
fact the first field in struct pcpu.
The only non-atomic operations left were those related to process-
space operations, such as casuword, subyte, suword16, fubyte,
fuword16, copyin, copyout and their variations.
The casuword function has been re-structured more complete than
the others. This way we have an example of a better bundling
without introducing a lot of risk when we get it wrong. The
other functions can be rebundled in separate commits and with
the appropriate testing.
every architecture's busdma_machdep.c. It is done by unifying the
bus_dmamap_load_buffer() routines so that they may be called from MI
code. The MD busdma is then given a chance to do any final processing
in the complete() callback.
The cam changes unify the bus_dmamap_load* handling in cam drivers.
The arm and mips implementations are updated to track virtual
addresses for sync(). Previously this was done in a type specific
way. Now it is done in a generic way by recording the list of
virtuals in the map.
Submitted by: jeff (sponsored by EMC/Isilon)
Reviewed by: kan (previous version), scottl,
mjacob (isp(4), no objections for target mode changes)
Discussed with: ian (arm changes)
Tested by: marius (sparc64), mips (jmallet), isci(4) on x86 (jharris),
amd64 (Fabian Keil <freebsd-listen@fabiankeil.de>)
sleep, and perform the page allocations with VM_ALLOC_SYSTEM
class. Previously, the allocation was also allowed to completely drain
the reserve of the free pages, being translated to VM_ALLOC_INTERRUPT
request class for vm_page_alloc() and similar functions.
Allow the caller of malloc* to request the 'deep drain' semantic by
providing M_USE_RESERVE flag, now translated to VM_ALLOC_INTERRUPT
class. Previously, it resulted in less aggressive VM_ALLOC_SYSTEM
allocation class.
Centralize the translation of the M_* malloc(9) flags in the single
inline function malloc2vm_flags().
Discussion started by: "Sears, Steven" <Steven.Sears@netapp.com>
Reviewed by: alc, mdf (previous version)
Tested by: pho (previous version)
MFC after: 2 weeks
advantages. First, PV entries are roughly half the size. Second, this
allocator doesn't access the paging queues, and thus it allows for the
removal of the page queues lock from this pmap.
Replace all uses of the page queues lock by a R/W lock that is private
to this pmap.
Tested by: marcel
used, serves very little value given that FreeBSD runs on real H/W
for a long time.
Note that SKI is open-source (see http://ski.sourceforge.net), so
if there's interest and value again, then this code can be revived.
Discussed with: jhb
makes calls out to the emulator, the locking is fairly simple. A global
mutex protects the list of ssc disks, and each ssc disk has a mutex
to protect it's bioq.
Approved by: marcel
to pull vm_param.h was removed. Other big dependency of vm_page.h on
vm_param.h are PA_LOCK* definitions, which are only needed for
in-kernel code, because modules use KBI-safe functions to lock the
pages.
Stop including vm_param.h into vm_page.h. Include vm_param.h
explicitely for the kernel code which needs it.
Suggested and reviewed by: alc
MFC after: 2 weeks
up and running to service interrupts. This is especially important
when the firmware has bound interrupts to CPUs, like for the SGI
Altix 350. We wake up APs at SI_SUB_CPU time and they sit and spin
until we unleash them, so there's nothing fundamentally different
from a MD perspective.
before VM has been initialized. This includes:
1. Replacing pmap_steal_memory(),
2. Replace the handcrafted logic to allocate a naturally aligned VHPT,
3. Properly allocate the DPCPU for the BSP.
Ad 3: Appending the DPCPU to kernend worked as long as we wouldn't
cross into the next PBVM page. If we were to cross into the next
page, then there wouldn't be a PTE entry on the page table for it
and we would end up with a MCA following a page fault. As such,
this commit fixes MCAs occasionally seen.
correctly. We now iterate the EFI memory descriptors once and collect all
the information in a single pass. This includes:
1. The I/O port base address,
2. The PAL memory region. Have the physmem API track this.
3. Memory descriptors of memory we can't use, like bad memory, runtime
services code & data, etc. Have the physmem API track these.
4. memory descriptors of memory we can use or re-use, such as free
memory, boot time services code & data, loader code & data, etc.
These are added by the physmem API.
Since the PBVM page table and pages are in memory described as loader
data, inform the physmem API of chunks that need to be delated from the
available physical memory.
While here, remove Maxmem and replace it with the better named paddr_max.
Maxmem was defined as physmem, which is generally wrong. Now, paddr_max
is properly defined as the largesty physical address.
The upshot of all this is that:
1. We properly determine realmem.
2. We maximize physmem by re-using memory where possible.
3. We remove complexity from ia64_init() in machdep.c.
4. Remove confusion about realmem, physmem & Maxmem.
The new ia64_physmem_alloc() is to replace pmap_steal_memory() in pmap.c,
as well as replace the handcrafted allocation of the VHPT for the BSP in
pmap_bootstrap() in pmap.c. This is step 2 and addresses the manipulation
of phys_avail after it is being created.
This is required for ARM EABI. Section 7.1.1 of the Procedure Call for the
ARM Architecture (AAPCS) defines wchar_t as either an unsigned int or an
unsigned short with the former preferred.
Because of this requirement we need to move the definition of __wchar_t to
a machine dependent header. It also cleans up the macros defining the limits
of wchar_t by defining __WCHAR_MIN and __WCHAR_MAX in the same machine
dependent header then using them to define WCHAR_MIN and WCHAR_MAX
respectively.
Discussed with: bde
usermode, using shared page. The structures and functions have vdso
prefix, to indicate the intended location of the code in some future.
The versioned per-algorithm data is exported in the format of struct
vdso_timehands, which mostly repeats the content of in-kernel struct
timehands. Usermode reading of the structure can be lockless.
Compatibility export for 32bit processes on 64bit host is also
provided. Kernel also provides usermode with indication about
currently used timecounter, so that libc can fall back to syscall if
configured timecounter is unknown to usermode code.
The shared data updates are initiated both from the tc_windup(), where
a fast task is queued to do the update, and from sysctl handlers which
change timecounter. A manual override switch
kern.timecounter.fast_gettime allows to turn off the mechanism.
Only x86 architectures export the real algorithm data, and there, only
for tsc timecounter. HPET counters page could be exported as well, but
I prefer to not further glue the kernel and libc ABI there until
proper vdso-based solution is developed.
Minimal stubs neccessary for non-x86 architectures to still compile
are provided.
Discussed with: bde
Reviewed by: jhb
Tested by: flo
MFC after: 1 month
layer, but it is read directly by the MI VM layer. This change introduces
pmap_page_is_write_mapped() in order to completely encapsulate all direct
access to PGA_WRITEABLE in the pmap layer.
Aesthetics aside, I am making this change because amd64 will likely begin
using an alternative method to track write mappings, and having
pmap_page_is_write_mapped() in place allows me to make such a change
without further modification to the MI VM layer.
As an added bonus, tidy up some nearby comments concerning page flags.
Reviewed by: kib
MFC after: 6 weeks
(described in ACPICA source code).
- Move intr_disable() and intr_restore() from acpi_wakeup.c to acpi.c
and call AcpiLeaveSleepStatePrep() in interrupt disabled context.
- Add acpi_wakeup_machdep() to execute wakeup MD procedures and call
it twice in interrupt disabled/enabled context (ia64 version is
just dummy).
- Rename wakeup_cpus variable in acpi_sleep_machdep() to suspcpus in
order to be shared by acpi_sleep_machdep() and acpi_wakeup_machdep().
- Move identity mapping related code to acpi_install_wakeup_handler()
(i386 version) for preparation of x86/acpica/acpi_wakeup.c
(MFC candidate).
Reviewed by: jkim@
MFC after: 2 days
in_cksum.h required ip.h to be included for struct ip. To be
able to use some general checksum functions like in_addword()
in a non-IPv4 context, limit the (also exported to user space)
IPv4 specific functions to the times, when the ip.h header is
present and IPVERSION is defined (to 4).
We should consider more general checksum (updating) functions
to also allow easier incremental checksum updates in the L3/4
stack and firewalls, as well as ponder further requirements by
certain NIC drivers needing slightly different pseudo values
in offloading cases. Thinking in terms of a better "library".
Sponsored by: The FreeBSD Foundation
Sponsored by: iXsystems
Reviewed by: gnn (as part of the whole)
MFC After: 3 days
I/O port addresses. Even if we do, this is hardly the place to mask
interrupts. It's not clear that this was at all needed. The code came
with CVS revision 1.2 of nexus.c when interrupt support was first added.
What is known is that ia64 has always been designed around the IOSAPIC,
and that doing I/O like this prevents Altix from booting.
