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
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
as CTASSERT in MI pcpu.h, stop including all possible mutually exclusive
PCPU_MD_FIELDS fields into LINT kernels, due to brekaing
aforementioned CTASSERT.
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.
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
implementation specific vs. the common architecture definition.
Bring PPC4XX defines (PSL, SPR, TLB). Note the new definitions under
BOOKE_PPC4XX are not used in the code yet.
This change set is not supposed to affect existing E500 support, it's just
another reorg step before bringing support for E500mc, E5500 and PPC465.
Obtained from: AppliedMicro, Freescale, Semihalf
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
exceptions early enough during boot that the kernel will do ithe same.
Use lwsync only when compiling for LP64 and revert to the more proven isync
when compiling for ILP32. Note that in the end (i.e. between revision 222198
and this change) ILP32 changed from using sync to using isync. As per Nathan
the isync is needed to make sure I/O accesses are properly serialized with
locks and isync tends to be more effecient than sync.
While here, undefine __ATOMIC_ACQ and __ATOMIC_REL at the end of the file
so as not to leak their definitions.
Discussed with: nwhitehorn
range operations like pmap_remove() and pmap_protect() as well as allowing
simple operations like pmap_extract() not to involve any global state.
This substantially reduces lock coverages for the global table lock and
improves concurrency.
- Use isync/lwsync unconditionally for acquire/release. Use of isync
guarantees a complete memory barrier, which is important for serialization
of bus space accesses with mutexes on multi-processor systems.
- Go back to using sync as the I/O memory barrier, which solves the same
problem as above with respect to mutex release using lwsync, while not
penalizing non-I/O operations like a return to sync on the atomic release
operations would.
- Place an acquisition barrier around thread lock acquisition in
cpu_switchin().
not provide general barriers, but only barriers in the context of the
atomic sequences here. As such, make them private and keep the global
*mb() routines using a variant of sync.
isync to implement read and write barriers, following Appendix B.2 of
Book II of the architecture manual. This provides a 25% speed increase
to fork() on the PowerPC G4.
of sync (lwsync is an alternate encoding of sync on systems that do not
support it, providing graceful fallback). This provides more than an order
of magnitude reduction in the time required to acquire or release a mutex.
MFC after: 2 months
sync performs a strict superset of the functions of eieio, so using both
is redundant. While here, expand bus barriers to all bus_space operations,
since many drivers do not correctly use bus_space_barrier().
In principle, we can also replace sync just with eieio, for a significant
performance increase, but it remains to be seen whether any poorly-written
drivers currently depend on the side effects of sync to properly function.
MFC after: 1 week
(slightly) different semantics and renaming it prevents a (harmless)
WITNESS warning during bootup for 32-bit kernels on 64-bit CPUs.
MFC after: 5 days
be less ambiguous and more clearly identify what it means. This
attribute is what Intel refers to as UC-, and it's only difference
relative to normal UC memory is that a WC MTRR will override a UC-
PAT entry causing the memory to be treated as WC, whereas a UC PAT
entry will always override the MTRR.
- Remove the VM_MEMATTR_UNCACHED alias from powerpc.
New kernel events can be added at various location for sampling or counting.
This will for example allow easy system profiling whatever the processor is
with known tools like pmcstat(8).
Simultaneous usage of software PMC and hardware PMC is possible, for example
looking at the lock acquire failure, page fault while sampling on
instructions.
Sponsored by: NETASQ
MFC after: 1 month
didn't already have them. This is because the ternary expression will
return int, due to the Usual Arithmetic Conversions. Such casts are not
needed for the 32 and 64 bit variants.
While here, add additional parentheses around the x86 variant, to
protect against unintended consequences.
MFC after: 2 weeks
Without this patch we were not able to see the assembly function.
Only the function descriptor was visible.
- Distinguish between user-land and kernel when creating the ENTRY() point of
assembly source.
- Make the ENTRY() macro more readable, replace the .align directive with the
gas platform independant .p2align directive.
- Create an END()macro for later use to provide traceback tables on powerpc64.
profiling and kernel profiling. To enable kernel profiling one has to build
kgmon(8). I will enable the build once I managed to build and test powerpc
(32-bit) kernels with profiling support.
- add a powerpc64 PROF_PROLOGUE for _mcount.
- add macros to avoid adding the PROF_PROLOGUE in certain assembly entries.
- apply these macros where needed.
- add size information to the MCOUNT function.
MFC after: 3 weeks, together with r230291
that the compiler promotes floats to double precision in computations, but
inspection of the output of a cross-compiler indicates that this isn't the
case on powerpc.
possible, and double faults within an SLB trap handler are not. The result
is that it possible to take an SLB fault at any time, on any address, for
any reason, at any point in the kernel.
This lets us do two important things. First, it removes the (soft) 16 GB RAM
ceiling on PPC64 as well as any architectural limitations on KVA space.
Second, it lets the kernel tolerate poorly designed hypervisors that
have a tendency to fail to restore the SLB properly after a hypervisor
context switch.
MFC after: 6 weeks
AIM systems to 4 GB on 32-bit systems and 2^64 bytes on 64-bit systems.
VM_MAXUSER_ADDRESS remains at 2 GB on pending Book-E, pending review of
an increase to 3 GB by those more familiar with Book-E.
pmap_remove() for large sparse requests. This can prevent pmap_remove()
operations on 64-bit process destruction or swapout that would take
several hundred times the lifetime of the universe to complete. This
behavior is largely indistinguishable from a hang.
implement a deprecated FPU control interface in addition to the
standard one. To make this clearer, further deprecate ieeefp.h
by not declaring the function prototypes except on architectures
that implement them already.
Currently i386 and amd64 implement the ieeefp.h interface for
compatibility, and for fp[gs]etprec(), which doesn't exist on
most other hardware. Powerpc, sparc64, and ia64 partially implement
it and probably shouldn't, and other architectures don't implement it
at all.
to VPO_UNMANAGED (and also making the flag protected by the vm object
lock, instead of vm page queue lock).
- Mark the fake pages with both PG_FICTITIOUS (as it is now) and
VPO_UNMANAGED. As a consequence, pmap code now can use use just
VPO_UNMANAGED to decide whether the page is unmanaged.
Reviewed by: alc
Tested by: pho (x86, previous version), marius (sparc64),
marcel (arm, ia64, powerpc), ray (mips)
Sponsored by: The FreeBSD Foundation
Approved by: re (bz)
This patch is going to help in cases like mips flavours where you
want a more granular support on MAXCPU.
No MFC is previewed for this patch.
Tested by: pluknet
Approved by: re (kib)
instead of a PCPU field for curthread. This averts a race on SMP systems
with a high interrupt rate where the thread looking up the value of
curthread could be preempted and migrated between obtaining the PCPU
pointer and reading the value of pc_curthread, resulting in curthread being
observed to be the current thread on the thread's original CPU. This played
merry havoc with the system, in particular with mutexes. Many thanks to
jhb for helping me work this one out.
Note that Book-E is in principle susceptible to the same problem, but has
not been modified yet due to lack of Book-E hardware.
MFC after: 2 weeks
Renovate and improve the AIM Open Firmware support:
- Add RTAS (Run-Time Abstraction Services) support, found on all IBM systems
and some Apple ones
- Improve support for 32-bit real mode Open Firmware systems
- Pull some more OF bits over from the AIM directory
- Fix memory detection on IBM LPARs and systems with more than one /memory
node (by andreast@)
o In bare_probe(), change the logic that determines the maximum
number of processors/cores into a switch statement and take
advantage of the fact that bit 3 of the SVR value indicates
whether we're running on a security enabled version. Since we
don't care about that here, mask the bit. All -E versions
are taken care of automatically.
Rewrite atomic operations for powerpc in order to achieve the following:
- Produce a type-clean implementation (in terms of functions arguments
and returned values) for the primitives.
- Fix errors with _long() atomics where they ended up with the wrong
arguments to be accepted.
- Follow the sys/type.h specifics that define the numbered types starting
from standard C types.
- Let _ptr() version to not auto-magically cast arguments, but leave
the burden on callers, as _ptr() atomic is intended to be used
relatively rarely.
Fix cfi in order to support the latest point.
In collabouration with: bde
Tested by: andreast, nwhitehorn, jceel
MFC after: 2 weeks
architectures (i386, for example) the virtual memory space may be
constrained enough that 2MB is a large chunk. Use 64K for arches
other than amd64 and ia64, with special handling for sparc64 due to
differing hardware.
Also commit the comment changes to kmem_init_zero_region() that I
missed due to not saving the file. (Darn the unfamiliar development
environment).
Arch maintainers, please feel free to adjust ZERO_REGION_SIZE as you
see fit.
Requested by: alc
MFC after: 1 week
MFC with: r221853
starting from base C types (int, long, etc).
That is also reflected when building atomic operations, as the
size-bounded types are built from the base C types.
However, powerpc does the inverse thing, leading to a serie of nasty
bugs.
Cleanup the atomic implementation by defining as base the base C type
version and depending on them, appropriately.
Tested by: jceel
already supported nested PICs, but was limited to having a nested
AT-PIC only. With G5 support the need for nested OpenPIC controllers
needed to be added. This was done the wrong way and broke the MPC8555
eval system in the process.
OFW, as well as FDT, describe the interrupt routing in terms of a
controller and an interrupt pin on it. This needs to be mapped to a
flat and global resource: the IRQ. The IRQ is the same as the PCI
intline and as such needs to be representable in 8 bits. Secondly,
ISA support pretty much dictates that IRQ 0-15 should be reserved
for ISA interrupts, because of the internal workins of south bridges.
Both were broken.
This change reverts revision 209298 for a big part and re-implements
it simpler. In particular:
o The id() method of the PIC I/F is removed again. It's not needed.
o The openpic_attach() function has been changed to take the OFW
or FDT phandle of the controller as a second argument. All bus
attachments that previously used openpic_attach() as the attach
method of the device I/F now implement as bus-specific method
and pass the phandle_t to the renamed openpic_attach().
o Change powerpc_register_pic() to take a few more arguments. In
particular:
- Pass the number of IPIs specificly. The number of IRQs carved
out for a PIC is the sum of the number of int. pins and IPIs.
- Pass a flag indicating whether the PIC is an AT-PIC or not.
This tells the interrupt framework whether to assign IRQ 0-15
or some other range.
o Until we implement proper multi-pass bus enumeration, we have to
handle the case where we need to map from PIC+pin to IRQ *before*
the PIC gets registered. This is done in a similar way as before,
but rather than carving out 256 IRQs per PIC, we carve out 128
IRQs (124 pins + 4 IPIs). This is supposed to handle the G5 case,
but should really be fixed properly using multiple passes.
o Have the interrupt framework set root_pic in most cases and not
put that burden in PIC drivers (for the most part).
o Remove powerpc_ign_lookup() and replace it with powerpc_get_irq().
Remove IGN_SHIFT, INTR_INTLINE and INTR_IGN.
Related to the above, fix the Freescale PCI controller driver, broken
by the FDT code. Besides not attaching properly, bus numbers were
assigned improperly and enumeration was broken in general. This
prevented the AT PIC from being discovered and interrupt routing to
work properly. Consequently, the ata(4) controller stopped functioning.
Fix the driver, and FDT PCI support, enough to get the MPC8555CDS
going again. The FDT PCI code needs a whole lot more work.
No breakages are expected, but lackiong G5 hardware, it's possible
that there are unpleasant side-effects. At least MPC85xx support is
back to where it was 7 months ago -- it's amazing how badly support
can be broken in just 7 months...
Sponsored by: Juniper Networks
Compile sys/dev/mem/memutil.c for all supported platforms and remove now
unnecessary dev_mem_md_init(). Consistently define mem_range_softc from
mem.c for all platforms. Add missing #include guards for machine/memdev.h
and sys/memrange.h. Clean up some nearby style(9) nits.
MFC after: 1 month
and pointers don't always have the same size, e.g. the __mips_n32 ABI
(ILP32) has 64 bit registers but 32 bit pointers.
On mips introduce PRIptr to fix the format specifier for (u)intptr_t.
Prefix PRI64 and PRIptr with underscores because macro names starting with
PRI[a-zX] are reserved for future use.
Approved by: kib (mentor)
architecture macros (__mips_n64, __powerpc64__) when 64 bit types (and
corresponding macros) are different from 32 bit. [1]
Correct the type of INT64_MIN, INT64_MAX and UINT64_MAX.
Define (U)INTMAX_C as an alias for (U)INT64_C matching the type definition
for (u)intmax_t. Do this on all architectures for consistency.
Suggested by: bde [1]
Approved by: kib (mentor)
of (unsigned) int __attribute__((__mode__(__DI__))). This aligns better
with macros such as (U)INT64_C, (U)INT64_MAX, etc. which assume (u)int64_t
has type (unsigned) long long.
The mode attribute was used because long long wasn't standardised until
C99. Nowadays compilers should support long long and use of the mode
attribute is discouraged according to GCC Internals documentation.
The type definition has to be marked with __extension__ to support
compilation with "-std=c89 -pedantic".
Discussed with: bde
Approved by: kib (mentor)
On some architectures UCHAR_MAX and USHRT_MAX had type unsigned int.
However, lacking integer suffixes for types smaller than int, their type
should correspond to that of an object of type unsigned char (or short)
when used in an expression with objects of type int. In that case unsigned
char (short) are promoted to int (i.e. signed) so the type of UCHAR_MAX and
USHRT_MAX should also be int.
Where MIN/MAX constants implicitly have the correct type the suffix has
been removed.
While here, correct some comments.
Reviewed by: bde
Approved by: kib (mentor)
It was used mainly to discover and fix some 64-bit portability problems
before 64-bit arches were widely available.
Discussed with: bde
Approved by: kib (mentor)
available on firmwares 3.15 and earlier.
Caveats: Support for the internal SATA controller is currently missing,
as is support for framebuffer resolutions other than 720x480. These
deficiencies will be remedied soon.
Special thanks to Peter Grehan for providing the hardware that made this
port possible, and thanks to Geoff Levand of Sony Computer Entertainment
for advice on the LV1 hypervisor.
logic to support modifying the page table through a hypervisor. This
uses KOBJ inheritance to provide subclasses of the base 64-bit AIM MMU
class with additional methods for page table manipulation.
Many thanks to Peter Grehan for suggesting this design and implementing
the MMU KOBJ inheritance mechanism.
Passing a count of zero on i386 and amd64 for [I386|AMD64]_BUS_SPACE_MEM
causes a crash/hang since the 'loop' instruction decrements the counter
before checking if it's zero.
PR: kern/80980
Discussed with: jhb
byte-swapped versions of compile-time constants. This allows use of
bswap() and htole*() in initializers, which is required to cross-build
btxld.
Obtained from: sparc64
hypervisor infrastructure support:
- Fix coexistence of multiple platform modules in the same kernel
- Allow platform modules to provide an SMP topology
- PowerPC hypervisors limit the amount of memory accessible in real mode.
Allow the platform modules to specify the maximum real-mode address,
and modify the bits of the kernel that need to allocate
real-mode-accessible buffers to respect this limits.
routines.
This unbreaks Book-E build after the recent machine/mutex.h removal.
While there move tlb_*lock() prototypes to machine/tlb.h.
Submitted by: jhb
contents of the ones that were not empty were stale and unused.
- Now that <machine/mutex.h> no longer exists, there is no need to allow it
to override various helper macros in <sys/mutex.h>.
- Rename various helper macros for low-level operations on mutexes to live
in the _mtx_* or __mtx_* namespaces. While here, change the names to more
closely match the real API functions they are backing.
- Drop support for including <sys/mutex.h> in assembly source files.
Suggested by: bde (1, 2)
concurrency bug. Since all SLB/SR entries were invalidated during an
exception, a decrementer exception could cause the user segment to be
invalidated during a copyin()/copyout() without a thread switch that
would cause it to be restored from the PCB, potentially causing the
operation to continue on invalid memory. This is now handled by explicit
restoration of segment 12 from the PCB on 32-bit systems and a check in
the Data Segment Exception handler on 64-bit.
While here, cause copyin()/copyout() to check whether the requested
user segment is already installed, saving some pipeline flushes, and
fix the synchronization primitives around the mtsr and slbmte
instructions to prevent accessing stale segments.
MFC after: 2 weeks
values to zero. A correct solution would involve emulating vector
operations on denormalized values, but this has little effect on accuracy
and is much less complicated for now.
MFC after: 2 weeks
Unlike actual MTRR, this only controls the mapping attributes for
subsequent mmap() of /dev/mem. Nonetheless, the support is sufficiently
MTRR-like that Xorg can use it, which translates into an enormous increase
in graphics performance on PowerPC.
MFC after: 2 weeks
which are similar to the previous ones, and one for user maps, which
are arrays of pointers into the SLB tree. This changes makes user SLB
updates atomic, closing a window for memory corruption. While here,
rearrange the allocation functions to make context switches faster.
hardware with a lockless sparse tree design. This marginally improves
the performance of PMAP and allows copyin()/copyout() to run without
acquiring locks when used on wired mappings.
Submitted by: mdf
include/mmuvar.h - Change the MMU_DEF macro to also create the class
definition as well as define the DATA_SET. Add a macro, MMU_DEF_INHERIT,
which has an extra parameter specifying the MMU class to inherit methods
from. Update the comments at the start of the header file to describe the
new macros.
booke/pmap.c
aim/mmu_oea.c
aim/mmu_oea64.c - Collapse mmu_def_t declaration into updated MMU_DEF macro
The MMU_DEF_INHERIT macro will be used in the PS3 MMU implementation to
allow it to inherit the stock powerpc64 MMU methods.
Reviewed by: nwhitehorn
The main goal of this is to generate timer interrupts only when there is
some work to do. When CPU is busy interrupts are generating at full rate
of hz + stathz to fullfill scheduler and timekeeping requirements. But
when CPU is idle, only minimum set of interrupts (down to 8 interrupts per
second per CPU now), needed to handle scheduled callouts is executed.
This allows significantly increase idle CPU sleep time, increasing effect
of static power-saving technologies. Also it should reduce host CPU load
on virtualized systems, when guest system is idle.
There is set of tunables, also available as writable sysctls, allowing to
control wanted event timer subsystem behavior:
kern.eventtimer.timer - allows to choose event timer hardware to use.
On x86 there is up to 4 different kinds of timers. Depending on whether
chosen timer is per-CPU, behavior of other options slightly differs.
kern.eventtimer.periodic - allows to choose periodic and one-shot
operation mode. In periodic mode, current timer hardware taken as the only
source of time for time events. This mode is quite alike to previous kernel
behavior. One-shot mode instead uses currently selected time counter
hardware to schedule all needed events one by one and program timer to
generate interrupt exactly in specified time. Default value depends of
chosen timer capabilities, but one-shot mode is preferred, until other is
forced by user or hardware.
kern.eventtimer.singlemul - in periodic mode specifies how much times
higher timer frequency should be, to not strictly alias hardclock() and
statclock() events. Default values are 2 and 4, but could be reduced to 1
if extra interrupts are unwanted.
kern.eventtimer.idletick - makes each CPU to receive every timer interrupt
independently of whether they busy or not. By default this options is
disabled. If chosen timer is per-CPU and runs in periodic mode, this option
has no effect - all interrupts are generating.
As soon as this patch modifies cpu_idle() on some platforms, I have also
refactored one on x86. Now it makes use of MONITOR/MWAIT instrunctions
(if supported) under high sleep/wakeup rate, as fast alternative to other
methods. It allows SMP scheduler to wake up sleeping CPUs much faster
without using IPI, significantly increasing performance on some highly
task-switching loads.
Tested by: many (on i386, amd64, sparc64 and powerc)
H/W donated by: Gheorghe Ardelean
Sponsored by: iXsystems, Inc.
A make buildkernel -j4 uses ~360% CPU.
- Bracket the AP spinup printf with a mutex to avoid garbled output.
- Enable SMP by default on powerpc64.
Reviewed by: nwhitehorn
the existing code was very platform specific, and broken for SMP systems
trying to reboot from KDB.
- Add a new PLATFORM_RESET() method to the platform KOBJ interface, and
migrate existing reset functions into platform modules.
- Modify the OF_reboot() routine to submit the request by hand to avoid
the IPIs involved in the regular openfirmware() routine. This fixes
reboot from KDB on SMP machines.
- Move non-KDB reset and poweroff functions on the Powermac platform
into the relevant power control drivers (cuda, pmu, smu), instead of
using them through the Open Firmware backdoor.
- Rename platform_chrp to platform_powermac since it has become
increasingly Powermac specific. When we gain support for IBM systems,
we will grow a new platform_chrp.
In particular, provide pagesize and pagesizes array, the canary value
for SSP use, number of host CPUs and osreldate.
Tested by: marius (sparc64)
MFC after: 1 month
IPI to a specific CPU by its cpuid. Replace calls to ipi_selected() that
constructed a mask for a single CPU with calls to ipi_cpu() instead. This
will matter more in the future when we transition from cpumask_t to
cpuset_t for CPU masks in which case building a CPU mask is more expensive.
Submitted by: peter, sbruno
Reviewed by: rookie
Obtained from: Yahoo! (x86)
MFC after: 1 month
now it uses a very dumb first-touch allocation policy. This will change in
the future.
- Each architecture indicates the maximum number of supported memory domains
via a new VM_NDOMAIN parameter in <machine/vmparam.h>.
- Each cpu now has a PCPU_GET(domain) member to indicate the memory domain
a CPU belongs to. Domain values are dense and numbered from 0.
- When a platform supports multiple domains, the default freelist
(VM_FREELIST_DEFAULT) is split up into N freelists, one for each domain.
The MD code is required to populate an array of mem_affinity structures.
Each entry in the array defines a range of memory (start and end) and a
domain for the range. Multiple entries may be present for a single
domain. The list is terminated by an entry where all fields are zero.
This array of structures is used to split up phys_avail[] regions that
fall in VM_FREELIST_DEFAULT into per-domain freelists.
- Each memory domain has a separate lookup-array of freelists that is
used when fulfulling a physical memory allocation. Right now the
per-domain freelists are listed in a round-robin order for each domain.
In the future a table such as the ACPI SLIT table may be used to order
the per-domain lookup lists based on the penalty for each memory domain
relative to a specific domain. The lookup lists may be examined via a
new vm.phys.lookup_lists sysctl.
- The first-touch policy is implemented by using PCPU_GET(domain) to
pick a lookup list when allocating memory.
Reviewed by: alc
name of 32bit sibling architecture instead of the host one. Do the
same for hw.machine on amd64.
Add a safety belt debug.adaptive_machine_arch sysctl, to turn the
substitution off.
Reviewed by: jhb, nwhitehorn
MFC after: 2 weeks
Kernel sources for 64-bit PowerPC, along with build-system changes to keep
32-bit kernels compiling (build system changes for 64-bit kernels are
coming later). Existing 32-bit PowerPC kernel configurations must be
updated after this change to specify their architecture.
(exec_setregs, etc.) in order to simplify the addition of 64-bit support,
and possible future extension of the Book-E code to handle hard floating
point and Altivec.
MFC after: 1 month
The following systems are affected:
- MPC8555CDS
- MPC8572DS
This overhaul covers the following major changes:
- All integrated peripherals drivers for Freescale MPC85XX SoC, which are
currently in the FreeBSD source tree are reworked and adjusted so they
derive config data out of the device tree blob (instead of hard coded /
tabelarized values).
- This includes: LBC, PCI / PCI-Express, I2C, DS1553, OpenPIC, TSEC, SEC,
QUICC, UART, CFI.
- Thanks to the common FDT infrastrucutre (fdtbus, simplebus) we retire
ocpbus(4) driver, which was based on hard-coded config data.
Note that world for these platforms has to be built WITH_FDT.
Reviewed by: imp
Sponsored by: The FreeBSD Foundation
CPUs by default, and provide a functional version of BUS_BIND_INTR().
While here, fix some potential concurrency problems in the interrupt
handling code.
o This is disabled by default for now, and can be enabled using WITH_FDT at
build time.
o Tested with ARM and PowerPC.
Reviewed by: imp
Sponsored by: The FreeBSD Foundation
Extend struct sysvec with three new elements:
sv_fetch_syscall_args - the method to fetch syscall arguments from
usermode into struct syscall_args. The structure is machine-depended
(this might be reconsidered after all architectures are converted).
sv_set_syscall_retval - the method to set a return value for usermode
from the syscall. It is a generalization of
cpu_set_syscall_retval(9) to allow ABIs to override the way to set a
return value.
sv_syscallnames - the table of syscall names.
Use sv_set_syscall_retval in kern_sigsuspend() instead of hardcoding
the call to cpu_set_syscall_retval().
The new functions syscallenter(9) and syscallret(9) are provided that
use sv_*syscall* pointers and contain the common repeated code from
the syscall() implementations for the architecture-specific syscall
trap handlers.
Syscallenter() fetches arguments, calls syscall implementation from
ABI sysent table, and set up return frame. The end of syscall
bookkeeping is done by syscallret().
Take advantage of single place for MI syscall handling code and
implement ptrace_lwpinfo pl_flags PL_FLAG_SCE, PL_FLAG_SCX and
PL_FLAG_EXEC. The SCE and SCX flags notify the debugger that the
thread is stopped at syscall entry or return point respectively. The
EXEC flag augments SCX and notifies debugger that the process address
space was changed by one of exec(2)-family syscalls.
The i386, amd64, sparc64, sun4v, powerpc and ia64 syscall()s are
changed to use syscallenter()/syscallret(). MIPS and arm are not
converted and use the mostly unchanged syscall() implementation.
Reviewed by: jhb, marcel, marius, nwhitehorn, stas
Tested by: marcel (ia64), marius (sparc64), nwhitehorn (powerpc),
stas (mips)
MFC after: 1 month
Powermac G5 systems. MSI and several other things are not presently
supported.
The U3/U4 internal device support portions of this change were contributed
by Andreas Tobler.
MFC after: 1 week
architecture from page queue lock to a hashed array of page locks
(based on a patch by Jeff Roberson), I've implemented page lock
support in the MI code and have only moved vm_page's hold_count
out from under page queue mutex to page lock. This changes
pmap_extract_and_hold on all pmaps.
Supported by: Bitgravity Inc.
Discussed with: alc, jeffr, and kib
physical address is changed, there is a brief window during which its PTE
is invalid. Since moea64_set_scratchpage_pa() does not and cannot hold
the page table lock, it was possible for another CPU to insert a new PTE
into the scratch page's PTEG slot during this interval, corrupting both
mappings.
Solve this by creating a new flag, LPTE_LOCKED, such that
moea64_pte_insert will avoid claiming locked PTEG slots even if they
are invalid. This change also incorporates some additional paranoia
added to solve things I thought might be this bug.
Reported by: linimon
UMA segments at their physical addresses instead of into KVA. This emulates
the direct mapping behavior of OEA32 in an ad-hoc way. To make this work
properly required sharing the entire kernel PMAP with Open Firmware, so
ofw_pmap is transformed into a stub on 64-bit CPUs.
Also implement some more tweaks to get more mileage out of our limited
amount of KVA, principally by extending KVA into segment 16 until the
beginning of the first OFW mapping.
Reported by: linimon
more. This provides three new sysctls to user space:
hw.cpu_features - A bitmask of available CPU features
hw.floatingpoint - Whether or not there is hardware FP support
hw.altivec - Whether or not Altivec is available
PR: powerpc/139154
MFC after: 10 days
at least on my Xserve, getting the decrementer and timebase on APs to tick
requires setting up a clock chip over I2C, which is not yet done.
While here, correct the 64-bit tlbie function to set the CPU to 64-bit
mode correctly.
Hardware donated by: grehan
the memory or D-cache, depending on the semantics of the platform.
vm_sync_icache() is basically a wrapper around pmap_sync_icache(),
that translates the vm_map_t argumument to pmap_t.
o Introduce pmap_sync_icache() to all PMAP implementation. For powerpc
it replaces the pmap_page_executable() function, added to solve
the I-cache problem in uiomove_fromphys().
o In proc_rwmem() call vm_sync_icache() when writing to a page that
has execute permissions. This assures that when breakpoints are
written, the I-cache will be coherent and the process will actually
hit the breakpoint.
o This also fixes the Book-E PMAP implementation that was missing
necessary locking while trying to deal with the I-cache coherency
in pmap_enter() (read: mmu_booke_enter_locked).
The key property of this change is that the I-cache is made coherent
*after* writes have been done. Doing it in the PMAP layer when adding
or changing a mapping means that the I-cache is made coherent *before*
any writes happen. The difference is key when the I-cache prefetches.
by looking at the bases used for non-relocatable executables by gnu ld(1),
and adjusting it slightly.
Discussed with: bz
Reviewed by: kan
Tested by: bz (i386, amd64), bsam (linux)
MFC after: some time
has proven to have a good effect when entering KDB by using a NMI,
but it completely violates all the good rules about interrupts
disabled while holding a spinlock in other occasions. This can be the
cause of deadlocks on events where a normal IPI_STOP is expected.
* Adds an new IPI called IPI_STOP_HARD on all the supported architectures.
This IPI is responsible for sending a stop message among CPUs using a
privileged channel when disponible. In other cases it just does match a
normal IPI_STOP.
Right now the IPI_STOP_HARD functionality uses a NMI on ia32 and amd64
architectures, while on the other has a normal IPI_STOP effect. It is
responsibility of maintainers to eventually implement an hard stop
when necessary and possible.
* Use the new IPI facility in order to implement a new userend SMP kernel
function called stop_cpus_hard(). That is specular to stop_cpu() but
it does use the privileged channel for the stopping facility.
* Let KDB use the newly introduced function stop_cpus_hard() and leave
stop_cpus() for all the other cases
* Disable interrupts on CPU0 when starting the process of APs suspension.
* Style cleanup and comments adding
This patch should fix the reboot/shutdown deadlocks many users are
constantly reporting on mailing lists.
Please don't forget to update your config file with the STOP_NMI
option removal
Reviewed by: jhb
Tested by: pho, bz, rink
Approved by: re (kib)
dependent memory attributes:
Rename vm_cache_mode_t to vm_memattr_t. The new name reflects the
fact that there are machine-dependent memory attributes that have
nothing to do with controlling the cache's behavior.
Introduce vm_object_set_memattr() for setting the default memory
attributes that will be given to an object's pages.
Introduce and use pmap_page_{get,set}_memattr() for getting and
setting a page's machine-dependent memory attributes. Add full
support for these functions on amd64 and i386 and stubs for them on
the other architectures. The function pmap_page_set_memattr() is also
responsible for any other machine-dependent aspects of changing a
page's memory attributes, such as flushing the cache or updating the
direct map. The uses include kmem_alloc_contig(), vm_page_alloc(),
and the device pager:
kmem_alloc_contig() can now be used to allocate kernel memory with
non-default memory attributes on amd64 and i386.
vm_page_alloc() and the device pager will set the memory attributes
for the real or fictitious page according to the object's default
memory attributes.
Update the various pmap functions on amd64 and i386 that map pages to
incorporate each page's memory attributes in the mapping.
Notes: (1) Inherent to this design are safety features that prevent
the specification of inconsistent memory attributes by different
mappings on amd64 and i386. In addition, the device pager provides a
warning when a device driver creates a fictitious page with memory
attributes that are inconsistent with the real page that the
fictitious page is an alias for. (2) Storing the machine-dependent
memory attributes for amd64 and i386 as a dedicated "int" in "struct
md_page" represents a compromise between space efficiency and the ease
of MFCing these changes to RELENG_7.
In collaboration with: jhb
Approved by: re (kib)
o add to platforms where it was missing (arm, i386, powerpc, sparc64, sun4v)
o define as "1" on amd64 and i386 where there is no restriction
o make the type returned consistent with ALIGN
o remove _ALIGNED_POINTER
o make associated comments consistent
Reviewed by: bde, imp, marcel
Approved by: re (kensmith)
required by video card drivers. Specifically, this change introduces
vm_cache_mode_t with an appropriate VM_CACHE_DEFAULT definition on all
architectures. In addition, this changes adds a vm_cache_mode_t parameter
to kmem_alloc_contig() and vm_phys_alloc_contig(). These will be the
interfaces for allocating mapped kernel memory and physical memory,
respectively, with non-default cache modes.
In collaboration with: jhb
in Freescale system-on-chip devices.
The following algorithms and schemes are currently supported:
- 3DES, AES, DES
- MD5, SHA1, SHA256, SHA384, SHA512
Reviewed by: philip
Obtained from: Freescale, Semihalf
- make mftb() shared, rewrite in C, provide complementary mttb()
- adjust SMP startup per the above, additional comments, minor naming
changes
- eliminate redundant TB defines, other minor cosmetics
Reviewed by: marcel, nwhitehorn
Obtained from: Freescale, Semihalf
new platform module. These are probed in early boot, and have the
responsibility of determining the layout of physical memory, determining
the CPU timebase frequency, and handling the zoo of SMP mechanisms
found on PowerPC.
Reviewed by: marcel, raj
Book-E parts by: raj
controller in the VIA southbridge functional in the CDS
(Configurable Development System) for MPC85XX.
The embedded USB controllers look operational but the
interrupt steering is still wrong.
a fair number of static data structures, making this an unlikely
option to try to change without also changing source code. [1]
Change default cache line size on ia64, sparc64, and sun4v to 128
bytes, as this was what rtld-elf was already using on those
platforms. [2]
Suggested by: bde [1], jhb [2]
MFC after: 2 weeks
CACHE_LINE_SIZE constant. These constants are intended to
over-estimate the cache line size, and be used at compile-time
when a run-time tuning alternative isn't appropriate or
available.
Defaults for all architectures are 64 bytes, except powerpc
where it is 128 bytes (used on G5 systems).
MFC after: 2 weeks
Discussed on: arch@
replace magic numbers with constants to keep this from happening again.
Without this fix, some programs would occasionally get SIGTRAP instead
of SIGILL on an illegal instruction. This affected Altivec detection
in pixman, and possibly other software.
Reported by: Andreas Tobler
MFC after: 1 week
CPUs known to use 128 byte cache lines and defaulting to 32, use the dcbz
instruction to measure it. Also make dcbz behave the way you would
expect on PPC 970.
on a generic dumper that creates an ELF core file and
uses PMAP functions to scan and iterate over memory
chunks, as well as handle memory mappings used during
dumping.
the PMAP layer can choose to return physical memory
chunks or virtual memory chunks. For minidumps, the
chunks should be virtual.
The default MMU I/F implementation for the scan_md()
method returns NULL. Thus, when a PMAP implementation
does not implement the required methods, an empty
core file is created. Here, empty means having an ELF
header only.
Obtained from: Juniper Networks
provided, for example, on the PowerPC 970 (G5), as well as on related CPUs
like the POWER3 and POWER4.
This also adds support for various built-in hardware found on Apple G5
hardware (e.g. the IBM CPC925 northbridge).
Reviewed by: grehan
to the full path of the image that is being executed.
Increase AT_COUNT.
Remove no longer true comment about types used in Linux ELF binaries,
listed types contain FreeBSD-specific entries.
Reviewed by: kan
Previously, DBCR0 flags were set "globally", but this leads to problems
because Book-E fine grained debug settings work only in conjuction with the
debug master enable bit in MSR: in scenarios when the DBCR0 was set with
intention to debug one process, but another one with MSR[DE] set got
scheduled, the latter would immediately cause debug exceptions to occur upon
execution of its own code instructions (and not the one intended for
debugging).
To avoid such problems and properly handle debugging context, DBCR0 state
should be managed individually per process.
Submitted by: Grzegorz Bernacki gjb ! semihalf dot com
Reviewed by: marcel
o Eliminate tlb0[] (a s/w copy of TLB0)
- The table contents cannot be maintained reliably in multiple MMU
environments, where asynchronous events (invalidations from other cores)
can change our local TLB0 contents underneath.
- Simplify and optimize TLB flushing: system wide invalidations are
performed using tlbivax instruction (propagates to other cores), for
local MMU invalidations a new optimized routine (assembly) is introduced.
o Improve and simplify TID allocation and management.
- Let each core keep track of its TID allocations.
- Simplify TID recycling, eliminate dead code.
- Drop the now unused powerpc/booke/support.S file.
o Improve page tables management logic.
o Simplify TLB1 manipulation routines.
o Other improvements and polishing.
Obtained from: Freescale, Semihalf
of OFW access semantics, in order to allow future support for real-mode
OF access and flattened device frees. OF client interface modules are
implemented using KOBJ, in a similar way to the PPC PMAP modules.
Because we need Open Firmware to be available before mutexes can be used on
sparc64, changes are also included to allow KOBJ to be used very early in
the boot process by only using the mutex once we know it has been initialized.
Reviewed by: marius, grehan
the code for parsing interrupt maps) to PowerPC and reflect their new MI
status by moving them to the shared dev/ofw directory.
This commit also modifies the OFW PCI enumeration procedure on PowerPC to
allow the bus to find non-firmware-enumerated devices that Apple likes to add,
and adds some useful Open Firmware properties (compat and name) to the pnpinfo
string of children on OFW SBus, EBus, PCI, and MacIO links. Because of the
change to PCI enumeration on PowerPC, X has started working again on PPC
machines with Grackle hostbridges.
Reviewed by: marius
Obtained from: sparc64
and ifnet functions
- add memory barriers to <machine/atomic.h>
- update drivers to only conditionally define their own
- add lockless producer / consumer ring buffer
- remove ring buffer implementation from cxgb and update its callers
- add if_transmit(struct ifnet *ifp, struct mbuf *m) to ifnet to
allow drivers to efficiently manage multiple hardware queues
(i.e. not serialize all packets through one ifq)
- expose if_qflush to allow drivers to flush any driver managed queues
This work was supported by Bitgravity Inc. and Chelsio Inc.
simplifies certain device attachments (Kauai ATA, for instance), and makes
possible others on new hardware.
On G5 systems, there are several otherwise standard PCI devices
(Serverworks SATA) that will not allow their interrupt properties to be
written, so this information must be supplied directly from Open Firmware.
Obtained from: sparc64
all to date and the latter also is only used in ia64 and powerpc
code which no longer serves a real purpose after bring-up and just
can be removed as well. Note that architectures like sun4u also
provide no means of implementing IPI'ing a CPU itself natively
in the first place.
Suggested by: jhb
Reviewed by: arch, grehan, jhb
volatile so that the compiler won't perform CSE. For SMP,
this may result in us accessing the wrong PCPU and as such
results in a bogus curthread value.
Note that getting curthread is not quite MP-safe in the sense
that it requires two instructions that aren't performed
atomically. The first instruction gets the address of the PCPU
structure and the second instruction dereferences that pointer
to get curthread. If a thread is switched-out in between these
instructions and switched-in on a different CPU, we still get
the wrong curthread.
Now that st_rdev is being automatically generated by the kernel, there
is no need to define static major/minor numbers for the iodev and
memdev. We still need the minor numbers for the memdev, however, to
distinguish between /dev/mem and /dev/kmem.
Approved by: philip (mentor)
o The function is defined unconditionally but depends on SPR_SVR,
which is defined conditionally.
o spr.h defines mfspr() and mtspr(), which is no worse to use.
- detect number of LAWs in run time and initalize accordingly
- introduce decode windows target IDs used in MPC8572
- other minor updates
Obtained from: Freescale, Semihalf
so that all implemented variants have proper prototypes. The 8-bit,
16-bit and 64-bit variants are not implemented.
This really fixes the current build breakages caused by type casting
and struct aliasing rules.
these days, so de-generalize the acquire_timer/release_timer api
to just deal with speakers.
The new (optional) MD functions are:
timer_spkr_acquire()
timer_spkr_release()
and
timer_spkr_setfreq()
the last of which configures the timer to generate a tone of a given
frequency, in Hz instead of 1/1193182th of seconds.
Drop entirely timer2 on pc98, it is not used anywhere at all.
Move sysbeep() to kern/tty_cons.c and use the timer_spkr*() if
they exist, and do nothing otherwise.
Remove prototypes and empty acquire-/release-timer() and sysbeep()
functions from the non-beeping archs.
This eliminate the need for the speaker driver to know about
i8254frequency at all. In theory this makes the speaker driver MI,
contingent on the timer_spkr_*() functions existing but the driver
does not know this yet and still attaches to the ISA bus.
Syscons is more tricky, in one function, sc_tone(), it knows the hz
and things are just fine.
In the other function, sc_bell() it seems to get the period from
the KDMKTONE ioctl in terms if 1/1193182th second, so we hardcode
the 1193182 and leave it at that. It's probably not important.
Change a few other sysbeep() uses which obviously knew that the
argument was in terms of i8254 frequency, and leave alone those
that look like people thought sysbeep() took frequency in hertz.
This eliminates the knowledge of i8254_freq from all but the actual
clock.c code and the prof_machdep.c on amd64 and i386, where I think
it would be smart to ask for help from the timecounters anyway [TBD].
will have a special section, named .PPC.EMB.apuinfo, which will
tell GDB that a BookE processor is targeted and which will
result in GDB using a different register definition. In order
to support remote GDB for BookE, we need the GDB stub in the
kernel look for that section and use the BookE definitions.
might be currently programmed into the registers.
Underlying firmware (U-Boot) would typically program MAC address into the
first unit only, and others are left uninitialized. It is now possible to
retrieve and program MAC address for all units properly, provided they were
passed on in the bootinfo metadata.
Reviewed by: imp, marcel
Approved by: cognet (mentor)
variable is set. On my Mac Mini this puts the CPU in NAP mode when
the kernel is idle and, any technical or environmental reasons
aside, avoids that I have to listen to the fan all day :-)
used in the kernel only (by virtue of checking for _KERNEL),
ports like lsof (part of gtop) cheat. It sets _KERNEL, but does
not set either AIM or E500. As such, PCPU_MD_FIELDS didn't get
defined and the build broke.
The catch-all is to define PCPU_MD_FIELDS with a dummy integer
when at the end of line we ended up without a definition for it.
The PQ3 is a high performance integrated communications processing system
based on the e500 core, which is an embedded RISC processor that implements
the 32-bit Book E definition of the PowerPC architecture. For details refer
to: http://www.freescale.com/webapp/sps/site/prod_summary.jsp?code=MPC8555E
This port was tested and successfully run on the following members of the PQ3
family: MPC8533, MPC8541, MPC8548, MPC8555.
The following major integrated peripherals are supported:
* On-chip peripherals bus
* OpenPIC interrupt controller
* UART
* Ethernet (TSEC)
* Host/PCI bridge
* QUICC engine (SCC functionality)
This commit brings the main functionality and will be followed by individual
drivers that are logically separate from this base.
Approved by: cognet (mentor)
Obtained from: Juniper, Semihalf
MFp4: e500
Rework of this area is a pre-requirement for importing e500 support (and
other PowerPC core variations in the future). Mainly the following
headers are refactored so that we can cover for low-level differences between
various machines within PowerPC architecture:
<machine/pcpu.h>
<machine/pcb.h>
<machine/kdb.h>
<machine/hid.h>
<machine/frame.h>
Areas which use the above are adjusted and cleaned up.
Credits for this rework go to marcel@
Approved by: cognet (mentor)
MFp4: e500
variations (e500 currently), this provides a gcc-level FPU emulation and is an
alternative approach to the recently introduced kernel-level emulation
(FPU_EMU).
Approved by: cognet (mentor)
MFp4: e500
the PIC also informs the platform at which IRQ level it can start
assigning IPIs, since this can depend on the number of IRQs
supported for external interrupts.
a pointer to struct bus_space. The structure contains function
pointers that do the actual bus space access.
The reason for this change is that previously all bus space
accesses were little endian (i.e. had an explicit byte-swap
for multi-byte accesses), because all busses on Macs are little
endian.
The upcoming support for Book E, and in particular the E500
core, requires support for big-endian busses because all
embedded peripherals are in the native byte-order.
With this change, there's no distinction between I/O port
space and memory mapped I/O. PowerPC doesn't have I/O port
space. Busses assign tags based on the byte-order only.
For that purpose, two global structures exist (bs_be_tag and
bs_le_tag), of which the address can be taken to get a valid
tag.
Obtained from: Juniper, Semihalf
processors (it's the PowerPC Operating Environment Architecture).
AIM designates the processors made by the Apple-IBM-Motorola
alliance and those we typically support.
While here, remove the NetBSD option IPKDB. It's not an option
used by us. Also, PPC_HAVE_FPU is not used by us either. Remove
that too.
Obtained from: Juniper, Semihalf
- Introduce per-architecture stack_machdep.c to hold stack_save(9).
- Introduce per-architecture machine/stack.h to capture any common
definitions required between db_trace.c and stack_machdep.c.
- Add new kernel option "options STACK"; we will build in stack(9) if it is
defined, or also if "options DDB" is defined to provide compatibility
with existing users of stack(9).
Add new stack_save_td(9) function, which allows the capture of a stacktrace
of another thread rather than the current thread, which the existing
stack_save(9) was limited to. It requires that the thread be neither
swapped out nor running, which is the responsibility of the consumer to
enforce.
Update stack(9) man page.
Build tested: amd64, arm, i386, ia64, powerpc, sparc64, sun4v
Runtime tested: amd64 (rwatson), arm (cognet), i386 (rwatson)
cast as uint32_t which is defined as unsigned int. gcc doesn't want to
consider that there might not be much difference between an int and
a long on a 32 bit architecture.
frequency from OpenFirmware moved out and into a routine that is called
from cpu_startup().
This allows correct reporting of the CPU clockspeed when printing out
CPU information at boot time.
Reported by: numerous
Reviewed by: marcel
MFC after: 1 day
ways:
(1) Cached pages are no longer kept in the object's resident page
splay tree and memq. Instead, they are kept in a separate per-object
splay tree of cached pages. However, access to this new per-object
splay tree is synchronized by the _free_ page queues lock, not to be
confused with the heavily contended page queues lock. Consequently, a
cached page can be reclaimed by vm_page_alloc(9) without acquiring the
object's lock or the page queues lock.
This solves a problem independently reported by tegge@ and Isilon.
Specifically, they observed the page daemon consuming a great deal of
CPU time because of pages bouncing back and forth between the cache
queue (PQ_CACHE) and the inactive queue (PQ_INACTIVE). The source of
this problem turned out to be a deadlock avoidance strategy employed
when selecting a cached page to reclaim in vm_page_select_cache().
However, the root cause was really that reclaiming a cached page
required the acquisition of an object lock while the page queues lock
was already held. Thus, this change addresses the problem at its
root, by eliminating the need to acquire the object's lock.
Moreover, keeping cached pages in the object's primary splay tree and
memq was, in effect, optimizing for the uncommon case. Cached pages
are reclaimed far, far more often than they are reactivated. Instead,
this change makes reclamation cheaper, especially in terms of
synchronization overhead, and reactivation more expensive, because
reactivated pages will have to be reentered into the object's primary
splay tree and memq.
(2) Cached pages are now stored alongside free pages in the physical
memory allocator's buddy queues, increasing the likelihood that large
allocations of contiguous physical memory (i.e., superpages) will
succeed.
Finally, as a result of this change long-standing restrictions on when
and where a cached page can be reclaimed and returned by
vm_page_alloc(9) are eliminated. Specifically, calls to
vm_page_alloc(9) specifying VM_ALLOC_INTERRUPT can now reclaim and
return a formerly cached page. Consequently, a call to malloc(9)
specifying M_NOWAIT is less likely to fail.
Discussed with: many over the course of the summer, including jeff@,
Justin Husted @ Isilon, peter@, tegge@
Tested by: an earlier version by kris@
Approved by: re (kensmith)
o Revamp the PIC I/F to only abstract the PIC hardware. The
resource handling has been moved to nexus, where it belongs.
o Include EOI and MASK+EOI methods to the PIC I/F in support of
INTR_FILTER.
o With the allocation of interrupt resources and setup of
interrupt handlers in the common platform code we can delay
talking to the PIC hardware after enumeration of all devices.
Introduce a call to powerpc_intr_enable() in configure_final()
to achieve that and have powerpc_setup_intr() only program the
PIC when !cold.
o As a consequence of the above, remove all early_attach() glue
from the OpenPIC and Heathrow PIC drivers and have them
register themselves when they're found during enumeration.
o Decouple the interrupt vector from the interrupt request line.
Allocate vectors increasingly so that they can be used for
the intrcnt index as well. Extend the Heathrow PIC driver to
translate between IRQ and vector. The OpenPIC driver already
has the support for vectors in hardware.
Approved by: re (blanket)
This allocator uses a binary buddy system with a twist. First and
foremost, this allocator is required to support the implementation of
superpages. As a side effect, it enables a more robust implementation
of contigmalloc(9). Moreover, this reimplementation of
contigmalloc(9) eliminates the acquisition of Giant by
contigmalloc(..., M_NOWAIT, ...).
The twist is that this allocator tries to reduce the number of TLB
misses incurred by accesses through a direct map to small, UMA-managed
objects and page table pages. Roughly speaking, the physical pages
that are allocated for such purposes are clustered together in the
physical address space. The performance benefits vary. In the most
extreme case, a uniprocessor kernel running on an Opteron, I measured
an 18% reduction in system time during a buildworld.
This allocator does not implement page coloring. The reason is that
superpages have much the same effect. The contiguous physical memory
allocation necessary for a superpage is inherently colored.
Finally, the one caveat is that this allocator does not effectively
support prezeroed pages. I hope this is temporary. On i386, this is
a slight pessimization. However, on amd64, the beneficial effects of
the direct-map optimization outweigh the ill effects. I speculate
that this is true in general of machines with a direct map.
Approved by: re
caches with data caches after writing to memory. This typically
is required to make breakpoints work on ia64 and powerpc. For
those architectures the function is implemented.
- Rename PCPU_LAZY_INC into PCPU_INC
- Add the PCPU_ADD interface which just does an add on the pcpu member
given a specific value.
Note that for most architectures PCPU_INC and PCPU_ADD are not safe.
This is a point that needs some discussions/work in the next days.
Reviewed by: alc, bde
Approved by: jeff (mentor)
VM_PHYSSEG_SPARSE depending on whether the physical address space is
densely or sparsely populated with memory. The effect of this
definition is to determine which of two implementations of
vm_page_array and PHYS_TO_VM_PAGE() is used. The legacy
implementation is obtained by defining VM_PHYSSEG_DENSE, and a new
implementation that trades off time for space is obtained by defining
VM_PHYSSEG_SPARSE. For now, all architectures except for ia64 and
sparc64 define VM_PHYSSEG_DENSE. Defining VM_PHYSSEG_SPARSE on ia64
allows the entirety of my Itanium 2's memory to be used. Previously,
only the first 1 GB could be used. Defining VM_PHYSSEG_SPARSE on
sparc64 allows USIIIi-based systems to boot without crashing.
This change is a combination of Nathan Whitehorn's patch and my own
work in perforce.
Discussed with: kmacy, marius, Nathan Whitehorn
PR: 112194
was written into a user's address space. The fix is to modify uiomove_fromphys
to sync the icache when an executable user-space page is written into.
Alan Cox suggested that there should probably be a higher-level interface
to this in the ptrace code, but agreed that this is an OK short-term solution.
Files changed:
pmap.h - declaration of pmap_page_executable()
pmap_dispatch.c - pass through the page_executable call to the mmu object
mmu_oea.c - implement the page_executable method by examining the PTE_EXEC
field in the vm_page_t
uio_machdep.c - in uiomove_fromphys(), if the op was a UIO_WRITE to user-space,
and if the page is executable, sync the icache since this is at the least
a breakpoint-write from gdb.
Reported by: marcel
Tested by: marcel, grehan on g3+g4
Discussed with: alc
MFC after: 2 weeks
Submitted by:
Reviewed by:
Approved by:
Obtained from:
MFC after:
Security:
Move the relocation definitions to the common elf header so that DTrace
can use them on one architecture targeted to a different one.
Add the additional ELF types defines in Sun's "Linker and Libraries"
manual.
This avoids that mem.c has to include ofw_machdep.h, including
all OFW related headers.
o Provide a stub for OF_decode_addr(), which is used by low-level
console drivers to obtain a tag and handle given a OFW phandle.
This is different from sparc64, where a fake bus tag needs to be
created explicitly.
passing a pointer to an opaque clockframe structure and requiring the
MD code to supply CLKF_FOO() macros to extract needed values out of the
opaque structure, just pass the needed values directly. In practice this
means passing the pair (usermode, pc) to hardclock() and profclock() and
passing the boolean (usermode) to hardclock_cpu() and hardclock_process().
Other details:
- Axe clockframe and CLKF_FOO() macros on all architectures. Basically,
all the archs were taking a trapframe and converting it into a clockframe
one way or another. Now they can just extract the PC and usermode values
directly out of the trapframe and pass it to fooclock().
- Renamed hardclock_process() to hardclock_cpu() as the latter is more
accurate.
- On Alpha, we now run profclock() at hz (profhz == hz) rather than at
the slower stathz.
- On Alpha, for the TurboLaser machines that don't have an 8254
timecounter, call hardclock() directly. This removes an extra
conditional check from every clock interrupt on Alpha on the BSP.
There is probably room for even further pruning here by changing Alpha
to use the simplified timecounter we use on x86 with the lapic timer
since we don't get interrupts from the 8254 on Alpha anyway.
- On x86, clkintr() shouldn't ever be called now unless using_lapic_timer
is false, so add a KASSERT() to that affect and remove a condition
to slightly optimize the non-lapic case.
- Change prototypeof arm_handler_execute() so that it's first arg is a
trapframe pointer rather than a void pointer for clarity.
- Use KCOUNT macro in profclock() to lookup the kernel profiling bucket.
Tested on: alpha, amd64, arm, i386, ia64, sparc64
Reviewed by: bde (mostly)
- Move vtophys() macros next to vtopte() where vtopte() exists to match
comments above vtopte().
- Remove references to the alternate address space in the comment above
vtopte(). amd64 never had the alternate address space, and i386 lost it
prior to PAE support being added.
- s/entires/entries/ in comments.
Reviewed by: alc
MACHINE_ARCH and MACHINE). Their purpose was to be able to test
in cpp(1), but cpp(1) only understands integer type expressions.
Using such unsupported expressions introduced a number of subtle
bugs, which were discovered by compiling with -Wundef.
the interface. This allows run-time selection of MMU code, based
on CPU-type detection, or tunable-overrides when testing new code.
Pre-requisite for G5 support.
conf/files.powerpc
- remove pmap.c
- add mmu_if.h, mmu_oea.c, pmap_dispatch.c
powerpc/include/mmuvar.h
- definitions for MMU implementations
powerpc/include/pmap.h
- remove pmap_pte_spill declaration
- add pmap_mmu_install declaration
- size the phys_avail array
- pmap_bootstrapped is now global-scope
powerpc/powerpc/machdep.c
- call kobj_machdep_init early in the boot sequence to allow
kobj usage prior to SI_SUB_LOCK
- install the OEA pmap code. This will be moved to CPU-specific
init code in the future.
powerpc/powerpc/mmu_if.m
- Kobj MMU interface definitions
powerpc/powerpc/pmap_dispatch.c
- central dispatch for pmap calls
- contains the global mmu kobj and the routine to locate the
the mmu implementation and init the kobj
and increase flexibility to allow various different approaches to be tried
in the future.
- Split struct ithd up into two pieces. struct intr_event holds the list
of interrupt handlers associated with interrupt sources.
struct intr_thread contains the data relative to an interrupt thread.
Currently we still provide a 1:1 relationship of events to threads
with the exception that events only have an associated thread if there
is at least one threaded interrupt handler attached to the event. This
means that on x86 we no longer have 4 bazillion interrupt threads with
no handlers. It also means that interrupt events with only INTR_FAST
handlers no longer have an associated thread either.
- Renamed struct intrhand to struct intr_handler to follow the struct
intr_foo naming convention. This did require renaming the powerpc
MD struct intr_handler to struct ppc_intr_handler.
- INTR_FAST no longer implies INTR_EXCL on all architectures except for
powerpc. This means that multiple INTR_FAST handlers can attach to the
same interrupt and that INTR_FAST and non-INTR_FAST handlers can attach
to the same interrupt. Sharing INTR_FAST handlers may not always be
desirable, but having sio(4) and uhci(4) fight over an IRQ isn't fun
either. Drivers can always still use INTR_EXCL to ask for an interrupt
exclusively. The way this sharing works is that when an interrupt
comes in, all the INTR_FAST handlers are executed first, and if any
threaded handlers exist, the interrupt thread is scheduled afterwards.
This type of layout also makes it possible to investigate using interrupt
filters ala OS X where the filter determines whether or not its companion
threaded handler should run.
- Aside from the INTR_FAST changes above, the impact on MD interrupt code
is mostly just 's/ithread/intr_event/'.
- A new MI ddb command 'show intrs' walks the list of interrupt events
dumping their state. It also has a '/v' verbose switch which dumps
info about all of the handlers attached to each event.
- We currently don't destroy an interrupt thread when the last threaded
handler is removed because it would suck for things like ppbus(8)'s
braindead behavior. The code is present, though, it is just under
#if 0 for now.
- Move the code to actually execute the threaded handlers for an interrrupt
event into a separate function so that ithread_loop() becomes more
readable. Previously this code was all in the middle of ithread_loop()
and indented halfway across the screen.
- Made struct intr_thread private to kern_intr.c and replaced td_ithd
with a thread private flag TDP_ITHREAD.
- In statclock, check curthread against idlethread directly rather than
curthread's proc against idlethread's proc. (Not really related to intr
changes)
Tested on: alpha, amd64, i386, sparc64
Tested on: arm, ia64 (older version of patch by cognet and marcel)
variable and returns the previous value of the variable.
Tested on: i386, alpha, sparc64, arm (cognet)
Reviewed by: arch@
Submitted by: cognet (arm)
MFC after: 1 week
constraint is actually only allowed for register operands. Instead, use
separate input and output memory constraints.
Education from: alc
Reviewed by: alc
Tested on: i386, alpha
MFC after: 1 week
it to __MINSIGSTKSZ. Define MINSIGSTKSZ in <sys/signal.h>.
This is done in order to use MINSIGSTKSZ for the macro PTHREAD_STACK_MIN
in <pthread.h> (soon <limits.h>) without having to include the whole
<sys/signal.h> header.
Discussed with: bde
variables rather than void * variables. This makes it easier and simpler
to get asm constraints and volatile keywords correct.
MFC after: 3 days
Tested on: i386, alpha, sparc64
Compiled on: ia64, powerpc, amd64
Kernel toolchain busted on: arm
- Implement sampling modes and logging support in hwpmc(4).
- Separate MI and MD parts of hwpmc(4) and allow sharing of
PMC implementations across different architectures.
Add support for P4 (EMT64) style PMCs to the amd64 code.
- New pmcstat(8) options: -E (exit time counts) -W (counts
every context switch), -R (print log file).
- pmc(3) API changes, improve our ability to keep ABI compatibility
in the future. Add more 'alias' names for commonly used events.
- bug fixes & documentation.
into _bus.h to help with name space polution from including all of bus.h.
In a few days, I'll commit changes to the MI code to take advantage of thse
sepration (after I've made sure that these changes don't break anything in
the main tree, I've tested in my trees, but you never know...).
Suggested by: bde (in 2002 or 2003 I think)
Reviewed in principle by: jhb
critical_enter() and critical_exit() are now solely a mechanism for
deferring kernel preemptions. They no longer have any affect on
interrupts. This means that standalone critical sections are now very
cheap as they are simply unlocked integer increments and decrements for the
common case.
Spin mutexes now use a separate KPI implemented in MD code: spinlock_enter()
and spinlock_exit(). This KPI is responsible for providing whatever MD
guarantees are needed to ensure that a thread holding a spin lock won't
be preempted by any other code that will try to lock the same lock. For
now all archs continue to block interrupts in a "spinlock section" as they
did formerly in all critical sections. Note that I've also taken this
opportunity to push a few things into MD code rather than MI. For example,
critical_fork_exit() no longer exists. Instead, MD code ensures that new
threads have the correct state when they are created. Also, we no longer
try to fixup the idlethreads for APs in MI code. Instead, each arch sets
the initial curthread and adjusts the state of the idle thread it borrows
in order to perform the initial context switch.
This change is largely a big NOP, but the cleaner separation it provides
will allow for more efficient alternative locking schemes in other parts
of the kernel (bare critical sections rather than per-CPU spin mutexes
for per-CPU data for example).
Reviewed by: grehan, cognet, arch@, others
Tested on: i386, alpha, sparc64, powerpc, arm, possibly more
sys/bus_dma.h instead of being copied in every single arch. This slightly
reorders a flag that was specific to AXP and thus changes the ABI there.
The interface still relies on bus_space definitions found in <machine/bus.h>
so it cannot be included on its own yet, but that will be fixed at a later
date. Add an MD <machine/bus_dma.h> for ever arch for consistency and to
allow for future MD augmentation of the API. sparc64 makes heavy use of
this right now due to its different bus_dma implemenation.
