avoid problems with some Pentium 4 cpus and some older PPro/Pentium2
cpus. There are several problems, some documented in Intel errata.
This patch:
1) moves the kernel to the second page in the PSE case. There is an
errata that says that you Must Not point a 4MB page at physical
address zero on older cpus. We avoided bugs here due to sheer luck.
2) sets up PSE page tables right from the start in locore, rather than
trying to switch from 4K to 4M (or 2M) pages part way through the boot
sequence at the same time that we're messing with PG_G.
For some reason, the pmap work over the last 18 months seems to tickle
the problems, and the PAE infrastructure changes disturb the cpu
bugs even more.
A couple of people have reported a problem with APM bios calls during
boot. I'll work with people to get this resolved.
Obtained from: bmilekic
Reimplement pmap_release() such that it uses the page table rather than
the pte object to locate the page table directory pages. (Temporarily,
retain an assertion on the emptiness of the pte object.)
systems where the data/stack/etc limits are too big for a 32 bit process.
Move the 5 or so identical instances of ELF_RTLD_ADDR() into imgact_elf.c.
Supply an ia32_fixlimits function. Export the clip/default values to
sysctl under the compat.ia32 heirarchy.
Have mmap(0, ...) respect the current p->p_limits[RLIMIT_DATA].rlim_max
value rather than the sysctl tweakable variable. This allows mmap to
place mappings at sensible locations when limits have been reduced.
Have the imgact_elf.c ld-elf.so.1 placement algorithm use the same
method as mmap(0, ...) now does.
Note that we cannot remove all references to the sysctl tweakable
maxdsiz etc variables because /etc/login.conf specifies a datasize
of 'unlimited'. And that causes exec etc to fail since it can no
longer find space to mmap things.
32 bit binary stuff. 32 bit binaries do not like it much when the kernel
tries hard to put things above the 8GB mark.
I have a work-in-progress to fix this properly, but I didn't want to burn
anybody with this yet.
initialize a TSC timecounter until we know if it is broke or not.
XXX I think there is a bug in the i386 code here. init_TSC_tc() comes
after:
if (statclock_disable)
return;
ie: if you turn off the statclock interrupt, you dont get the TSC either.
for breakpoint and trace traps from usermode. Although all the setidt
entries are interrupt gates on amd64, all but the trace and bpt trap
entry handlers reenable interrupts after the swapgs instruction in order
to simulate the trap/interrupt gate distinction. In other words, the
amd64 code behaves the same way that i386 does here.
for ddb input in some atkbd-based console drivers. ddb must not use any
normal locks but DELAY() normally calls getit() which needs clock_lock.
This also removes the need for recursion on clock_lock.
of "dumb" PCI-based serial/parallel boards get a hint how to enable
them.
I wasn't sure about the ia64, pc98, powerpc, and sparc64 archs whether
they'd support puc(4) or not.
pmap_remove_pte(), passed NULL instead of the required page table
page to pmap_unuse_pt(). Compute the necessary page table page
in pmap_remove_pte(). Also, remove some unreachable code from
pmap_remove_pte().
on data structures on the kernel stack which are guaranteed to be 16 byte
aligned by gcc, the amd64 ABI and __aligned(16).
Ensire the tss_rsp0 initial stack pointer is 16 byte aligned in case
sizeof(pcb) becomes odd at some point. This is convenient for the
interrupt handler case because the ring crossing pushes cause the
required odd alignment before the call to the C code.
Have fast_syscall add an additional 8 bytes to ensure that the trapframe
has the correct odd alignment for the call to C code. Note that there are
no checks to make sure that the trapframe size is appropriate for this.
This makes get/setfpcontext work properly (finally). You get a GPF in
kernel mode if any of this is botched without the alignment fixup code
that is apparently needed on i386.
atomically extracts and holds the physical page that is associated with the
given pmap and virtual address. Such a function is needed to make the
memory mapping optimizations used by, for example, pipes and raw disk I/O
MP-safe.
Reviewed by: tegge
rl(4) driver and put it in a new re(4) driver. The re(4) driver shares
the if_rlreg.h file with rl(4) but is a separate module. (Ultimately
I may change this. For now, it's convenient.)
rl(4) has been modified so that it will never attach to an 8139C+
chip, leaving it to re(4) instead. Only re(4) has the PCI IDs to
match the 8169/8169S/8110S gigE chips. if_re.c contains the same
basic code that was originally bolted onto if_rl.c, with the
following updates:
- Added support for jumbo frames. Currently, there seems to be
a limit of approximately 6200 bytes for jumbo frames on transmit.
(This was determined via experimentation.) The 8169S/8110S chips
apparently are limited to 7.5K frames on transmit. This may require
some more work, though the framework to handle jumbo frames on RX
is in place: the re_rxeof() routine will gather up frames than span
multiple 2K clusters into a single mbuf list.
- Fixed bug in re_txeof(): if we reap some of the TX buffers,
but there are still some pending, re-arm the timer before exiting
re_txeof() so that another timeout interrupt will be generated, just
in case re_start() doesn't do it for us.
- Handle the 'link state changed' interrupt
- Fix a detach bug. If re(4) is loaded as a module, and you do
tcpdump -i re0, then you do 'kldunload if_re,' the system will
panic after a few seconds. This happens because ether_ifdetach()
ends up calling the BPF detach code, which notices the interface
is in promiscuous mode and tries to switch promisc mode off while
detaching the BPF listner. This ultimately results in a call
to re_ioctl() (due to SIOCSIFFLAGS), which in turn calls re_init()
to handle the IFF_PROMISC flag change. Unfortunately, calling re_init()
here turns the chip back on and restarts the 1-second timeout loop
that drives re_tick(). By the time the timeout fires, if_re.ko
has been unloaded, which results in a call to invalid code and
blows up the system.
To fix this, I cleared the IFF_UP flag before calling ether_ifdetach(),
which stops the ioctl routine from trying to reset the chip.
- Modified comments in re_rxeof() relating to the difference in
RX descriptor status bit layout between the 8139C+ and the gigE
chips. The layout is different because the frame length field
was expanded from 12 bits to 13, and they got rid of one of the
status bits to make room.
- Add diagnostic code (re_diag()) to test for the case where a user
has installed a broken 32-bit 8169 PCI NIC in a 64-bit slot. Some
NICs have the REQ64# and ACK64# lines connected even though the
board is 32-bit only (in this case, they should be pulled high).
This fools the chip into doing 64-bit DMA transfers even though
there is no 64-bit data path. To detect this, re_diag() puts the
chip into digital loopback mode and sets the receiver to promiscuous
mode, then initiates a single 64-byte packet transmission. The
frame is echoed back to the host, and if the frame contents are
intact, we know DMA is working correctly, otherwise we complain
loudly on the console and abort the device attach. (At the moment,
I don't know of any way to work around the problem other than
physically modifying the board, so until/unless I can think of a
software workaround, this will have do to.)
- Created re(4) man page
- Modified rlphy.c to allow re(4) to attach as well as rl(4).
Note that this code works for the sample 8169/Marvell 88E1000 NIC
that I have, but probably won't work for the 8169S/8110S chips.
RealTek has sent me some sample NICs, but they haven't arrived yet.
I will probably need to add an rlgphy driver to handle the on-board
PHY in the 8169S/8110S (it needs special DSP initialization).
sockets into machine-dependent files. The rationale for this
migration is illustrated by the modified amd64 allocator. It uses the
amd64's direct map to avoid emphemeral mappings in the kernel's
address space. On an SMP, the emphemeral mappings result in an IPI
for TLB shootdown for each transmitted page. Yuck.
Maintainers of other 64-bit platforms with direct maps should be able
to use the amd64 allocator as a reference implementation.
- Add a new PCIM_HDRTYPE constant for the field in PCIR_HDRTYPE that holds
the header type.
- Replace several magic numbers with appropriate constants for the header
type register and a couple of PCI_FUNCMAX.
- Merge to amd64 the fix to the i386 bridge code to skip devices with
unknown header types.
Requested by: imp (1, 2)
from the ia32 specific stuff. Some of this still needs to move to the MI
freebsd32 area, and some needs to move to the MD area. This is still
work-in-progress.
prototypes of cpu_halt(), cpu_reset() and swi_vm() from md_var.h to
cpu.h. This affects db_command.c and kern_shutdown.c.
ia64: move all MD prototypes from cpu.h to md_var.h. This affects
madt.c, interrupt.c and mp_machdep.c. Remove is_physical_memory().
It's not used (vm_machdep.c).
alpha: the MD prototypes have been left in cpu.h with a comment
that they should be there. Moving them is left for later. It was
expected that the impact would be significant enough to be done in
a seperate commit.
powerpc: MD prototypes left in cpu.h. Comment added.
Suggested by: bde
Tested with: make universe (pc98 incomplete)
- Add a macro for the logical shift needed to extract an APIC ID from
either from the local APIC ICR Hi register or the APIC ID registers of
the local and IO APICs.
parameter. The new name better reflects what the function does and
how it is used. The last parameter was always FALSE.
Note: In theory, gcc would perform constant propagation and dead code
elimination to achieve the same effect as removing the last parameter,
which is always FALSE. In practice, recent versions do not. So, there
is little point in letting unused code pessimize execution.
they haven't been counted before. This test was ommitted when bus_dmamap_load()
was merged into this function, and results in the pagesneeded field growing
without bounds when multiple deferrals happen.
Thanks to Paul Saab for beating his head against this for a few hours =-)
set in cpu_critical_fork_exit() anymore.
- As far as I can tell, cpu_thread_link() has never been used, not even
when it was originally added, so remove it.
created not only with UMA_ZONE_VM but also with UMA_ZONE_NOFREE. In
the i386 case in particular, the pmap code would hook a special
page allocation routine that allocated from kernel_map and not kmem_map,
and so when/if the pageout daemon drained the zones, it could actually
push out slabs from the PV ENTRY zone but call UMA's default page_free,
which resulted in pages allocated from kernel_map being freed to
kmem_map; bad. kmem_free() ignores the return value of the
vm_map_delete and just returns. I'm not sure what the exact
repercussions could be, but it doesn't look good.
In the PAE case on i386, we also set-up a zone in pmap, so be
conservative for now and make that zone also ZONE_NOFREE and
ZONE_VM. Do this for the pmap zones for the other archs too,
although in some cases it may not be entirely necessarily. We'd
rather be safe than sorry at this point.
Perhaps all UMA_ZONE_VM zones should by default be also
UMA_ZONE_NOFREE?
May fix some of silby's crashes on the PV ENTRY zone.
memory in bus_dmamem_alloc(). This is possible now that
contigmalloc() supports the M_ZERO flag.
- Remove the locking of Giant around calls to contigmalloc() since
contigmalloc() now grabs Giant itself.
written as a template that when inlined is specialized for the caller
through constant value propagation and dead code elimination. Thus,
the specialized code that is generated for pmap_clear_reference() et
al. avoids several conditional branches inside of a loop.
fields in the low 32 bits of the local APIC ICR register. Use this macro
in place of APIC_RESV2_MASK when masking off existing bits from the ICR
when writing to it to send an IPI.
Tested by: scottl
AMD64, gcc (and the ABI) expects the x87 unit to be running in 80/64
mode (not 64/53) so that it can use it for 'long double' operations. It
takes the expected precision differences into account when generating
code.
the SSE mxcsr register as well. Since gcc will intermix SSE2 and x87
FP code, the fpsetround() etc mode had better be the same.
There are hooks to enable these inlines to be instantiated inside libc
for non-gcc or C++ callers. (g++ doesn't like the inlines that tried
to extract an integer and convert it to an enum).
on the implied sign extension. The single unified VADDR() macro was
not able to avoid sign extending the VM_MAXUSER_ADDRESS/USRSTACK values.
Be explicit about UVADDR() (positive address space) and KVADDR()
(kernel negative address space) to make mistakes show up more
spectacularly.
Increase user VM space from 1/2TB (512GB) to 128TB.
corresponding release code. This was preventing the use of more than
1/2TB of user VM. I also spent a week staring at this code only to
eventually find that I'd mistakenly typed a P as an R.
rather than a non-existing pte. There is code elsewhere in i386/amd64
pmap that neglects to handle the large page cases because it knows that
it will see PG_PS in the returned "pte".
order to avoid the overhead of later page faults. In general, it
implements two cases: one for vnode-backed objects and one for
device-backed objects. Only the device-backed case is really
machine-dependent, belonging in the pmap.
This commit moves the vnode-backed case into the (relatively) new
function vm_map_pmap_enter(). On amd64 and i386, this commit only
amounts to code rearrangement. On alpha and ia64, the new machine
independent (MI) implementation of the vnode case is smaller and more
efficient than their pmap-based implementations. (The MI
implementation takes advantage of the fact that objects in -CURRENT
are ordered collections of pages.) On sparc64, pmap_object_init_pt()
hadn't (yet) been implemented.
Add two new arguments to bus_dma_tag_create(): lockfunc and lockfuncarg.
Lockfunc allows a driver to provide a function for managing its locking
semantics while using busdma. At the moment, this is used for the
asynchronous busdma_swi and callback mechanism. Two lockfunc implementations
are provided: busdma_lock_mutex() performs standard mutex operations on the
mutex that is specified from lockfuncarg. dftl_lock() is a panic
implementation and is defaulted to when NULL, NULL are passed to
bus_dma_tag_create(). The only time that NULL, NULL should ever be used is
when the driver ensures that bus_dmamap_load() will not be deferred.
Drivers that do not provide their own locking can pass
busdma_lock_mutex,&Giant args in order to preserve the former behaviour.
sparc64 and powerpc do not provide real busdma_swi functions, so this is
largely a noop on those platforms. The busdma_swi on is64 is not properly
locked yet, so warnings will be emitted on this platform when busdma
callback deferrals happen.
If anyone gets panics or warnings from dflt_lock() being called, please
let me know right away.
Reviewed by: tmm, gibbs
implementation of a largely MI pmap_object_init_pt() for vnode-backed
objects. pmap_enter_quick() is implemented via pmap_enter() on sparc64
and powerpc.
- Correct a mismatch between pmap_object_init_pt()'s prototype and its
various implementations. (I plan to keep pmap_object_init_pt() as
the MD hook for device-backed objects on i386 and amd64.)
- Correct an error in ia64's pmap_enter_quick() and adjust its interface
to match the other versions. Discussed with: marcel
being requested is outside of the range of the direct map region. eg:
for pci windows. While here, increase the minimum size of the direct
map region to be 4GB instead of 1GB.
to the machine-independent parts of the VM. At the same time, this
introduces vm object locking for the non-i386 platforms.
Two details:
1. KSTACK_GUARD has been removed in favor of KSTACK_GUARD_PAGES. The
different machine-dependent implementations used various combinations
of KSTACK_GUARD and KSTACK_GUARD_PAGES. To disable guard page, set
KSTACK_GUARD_PAGES to 0.
2. Remove the (unnecessary) clearing of PG_ZERO in vm_thread_new. In
5.x, (but not 4.x,) PG_ZERO can only be set if VM_ALLOC_ZERO is passed
to vm_page_alloc() or vm_page_grab().
we were passing in a void* representing the PCB of the parent thread.
Now we pass a pointer to the parent thread itself.
The prime reason for this change is to allow cpu_set_upcall() to copy
(parts of) the trapframe instead of having it done in MI code in each
caller of cpu_set_upcall(). Copying the trapframe cannot always be
done with a simply bcopy() or may not always be optimal that way. On
ia64 specifically the trapframe contains information that is specific
to an entry into the kernel and can only be used by the corresponding
exit from the kernel. A trapframe copied verbatim from another frame
is in most cases useless without some additional normalization.
Note that this change removes the assignment to td->td_frame in some
implementations of cpu_set_upcall(). The assignment is redundant.
A previous call to cpu_thread_setup() already did the exact same
assignment. An added benefit of removing the redundant assignment is
that we can now change td_pcb without nasty side-effects.
This change officially marks the ability on ia64 for 1:1 threading.
Not tested on: amd64, powerpc
Compile & boot tested on: alpha, sparc64
Functionally tested on: i386, ia64
all the argument registers etc since we have almost certainly have trashed
them by now. Take particular car of %r10 since it held the original value
of %rcx (which we saved in tf_rcx on entry and doreti doesn't know this).
switch to it before calling mi_startup(). The bootstack is WAY too small
for running acpica during probe/attach. While here, pass modulep/physfree
to the startup routine, rather than writing to the global variables in
locore.S.
Approved by: re (amd64/*)
The current name is confusing, because it indicates to
the client that a bus_dmamap_sync() operation is not
necessary when the flag is specified, which is wrong.
The main purpose of this flag is to hint the underlying
architecture that DMA memory should be mapped in a coherent
way, but the architecture can ignore it. But if the
architecture does supports coherent mapping of memory, then
it makes bus_dmamap_sync() calls cheap.
This flag is the same as the one in NetBSD's Bus DMA.
Reviewed by: gibbs, scottl, des (implicitly)
Approved by: re@ (jhb)
disassembler has not been updated yet, and will do some very strange
things. It does tracebacks (without function arguments due to regparm
calling conventions) if -fno-omit-frame-pointer is used (to come later).
This achieves basic functionality.
Approved by: re (amd64/* blanket)
BUS_DMASYNC_ definitions remain as before. The does not change the ABI,
and reverts the API to be a bit more compatible and flexible. This has
survived a full 'make universe'.
Approved by: re (bmah)
having their stack at the 512GB mark. Give 4GB of user VM space for 32
bit apps. Note that this is significantly more than on i386 which gives
only about 2.9GB of user VM to a process (1GB for kernel, plus page
table pages which eat user VM space).
Approved by: re (blanket)
systems. Of note:
- Implement a direct mapped region using 2MB pages. This eliminates the
need for temporary mappings when getting ptes. This supports up to
512GB of physical memory for now. This should be enough for a while.
- Implement a 4-tier page table system. Most of the infrastructure is
there for 128TB of userland virtual address space, but only 512GB is
presently enabled due to a mystery bug somewhere. The design of this
was heavily inspired by the alpha pmap.c.
- The kernel is moved into the negative address space(!).
- The kernel has 2GB of KVM available.
- Provide a uma memory allocator to use the direct map region to take
advantage of the 2MB TLBs.
- Fixed some assumptions in the bus_space macros about the ability
to fit virtual addresses in an 'int'.
Notable missing things:
- pmap_growkernel() should be able to grow to 512GB of KVM by expanding
downwards below kernbase. The kernel must be at the top 2GB of the
negative address space because of gcc code generation strategies.
- need to fix the >512GB user vm code.
Approved by: re (blanket)
- Fix visibilty test for LONG_BIT and WORD_BIT. `#if defined(__FOO_VISIBLE)'
is alays wrong because __FOO_VISIBLE is always defined (to 0 for
invisibility).
sys/<arch>/include/limits.h
sys/<arch>/include/_limits.h:
- Style fixes.
Submitted by: bde
Reviewed by: bsdmike
Approved by: re (scottl)
load_gs() calls into a single place that is less likely to go wrong.
Eliminate the per-process context switching of MSR_GSBASE, because it
should be constant for a single cpu. Instead, save/restore it during
the loading of the new %gs selector for the new process.
Approved by: re (amd64/* blanket)
stolen from the ia64/ia32 code (indeed there was a repocopy), but I've
redone the MD parts and added and fixed a few essential syscalls. It
is sufficient to run i386 binaries like /bin/ls, /usr/bin/id (dynamic)
and p4. The ia64 code has not implemented signal delivery, so I had
to do that.
Before you say it, yes, this does need to go in a common place. But
we're in a freeze at the moment and I didn't want to risk breaking ia64.
I will sort this out after the freeze so that the common code is in a
common place.
On the AMD64 side, this required adding segment selector context switch
support and some other support infrastructure. The %fs/%gs etc code
is hairy because loading %gs will clobber the kernel's current MSR_GSBASE
setting. The segment selectors are not used by the kernel, so they're only
changed at context switch time or when changing modes. This still needs
to be optimized.
Approved by: re (amd64/* blanket)
- Move struct sigacts out of the u-area and malloc() it using the
M_SUBPROC malloc bucket.
- Add a small sigacts_*() API for managing sigacts structures: sigacts_alloc(),
sigacts_free(), sigacts_copy(), sigacts_share(), and sigacts_shared().
- Remove the p_sigignore, p_sigacts, and p_sigcatch macros.
- Add a mutex to struct sigacts that protects all the members of the struct.
- Add sigacts locking.
- Remove Giant from nosys(), kill(), killpg(), and kern_sigaction() now
that sigacts is locked.
- Several in-kernel functions such as psignal(), tdsignal(), trapsignal(),
and thread_stopped() are now MP safe.
Reviewed by: arch@
Approved by: re (rwatson)
we do not have to run so long with interrupts disabled. This involved
creating tf_addr in the trapframe. Reorganize the trap stubs so that
they consistently reserve the stack space and initialize any missing
bits.
Approved by: re (amd64 stuff)
bus_dma MD code for AMD64. (And a trivial ifdef update in dev/kbd because
of this). More updates are needed here to take advantage of the 64 bit
instructions.
Approved by: re (blanket amd64/*)
value on entry and exit. This isn't as easy as it sounds because when
we recursively trap or interrupt, we have to avoid duplicating the
swapgs instruction or we end up back with the userland %gs. I implemented
this by testing TF_CS to see if we're coming from supervisor mode
already, and check for returning to supervisor. To avoid a race with
interrupts in the brief period after beginning executing the handler and
before the swapgs, convert all trap gates to interrupt gates, and reenable
interrupts immediately after the swapgs. I am not happy with this.
There are other possible ways to do this that should be investigated.
(eg: storing the GS.base MSR value in the trapframe)
Add some sysarch functions to let the userland code get to this.
Approved by: re (blanket amd64/*)
could use different versions of the math code depending on whether there
was real floating point hardware or math emulation. Since the fpu is
part of the core specification on amd64, there is no need for this here.
Approved by: re (blanket amd64/*)
should really be renamed to fpu.h and npx.c to fpu.c since its part of
the core architecture on amd64 systems, not an isa 'numeric processor
extension'.
that interrupts be disabled and remain disabled until %cr2 is read.
Otherwise we can preempt and another process can fault, and by the
time we read %cr2, we see a different processes fault address. This
Greatly Confuses vm_fault() (to say the least). The i386 port has
got this marked as a bug workaround for a Cyrix CPU, which is what
lead me astray. Its actually necessary for preemption, regardless
of whether Cyrix cpus had a bug or not.
call handler before it was safe. It was possible for to lose context
and for something else to clobber the PCPU scratch variable. This
moves the interrupt enable *way* too late, but its better safe than
sorry for the moment.
Remove DBL_DIG, DBL_MIN, DBL_MAX and their FLT_ counterparts, they
were marked for deprecation ever since SUSv1 at least.
Only define ULLONG_MIN/MAX and LLONG_MAX if long long type is
supported.
Restore a lost comment in MI _limits.h file and remove it from
sys/limits.h where it does not belong.
that were added to sparc64 and later powerpc, really should have been in
the MI area. But changing that now with insufficient preperation will
just cause too much pain.
Move MD_FETCH() to the MI sys/linker.h file to avoid another two copies
of it.
a heavily stripped down FreeBSD/i386 (brutally stripped down actually) to
attempt to get a stable base to start from. There is a lot missing still.
Worth noting:
- The kernel runs at 1GB in order to cheat with the pmap code. pmap uses
a variation of the PAE code in order to avoid having to worry about 4
levels of page tables yet.
- It boots in 64 bit "long mode" with a tiny trampoline embedded in the
i386 loader. This simplifies locore.s greatly.
- There are still quite a few fragments of i386-specific code that have
not been translated yet, and some that I cheated and wrote dumb C
versions of (bcopy etc).
- It has both int 0x80 for syscalls (but using registers for argument
passing, as is native on the amd64 ABI), and the 'syscall' instruction
for syscalls. int 0x80 preserves all registers, 'syscall' does not.
- I have tried to minimize looking at the NetBSD code, except in a couple
of places (eg: to find which register they use to replace the trashed
%rcx register in the syscall instruction). As a result, there is not a
lot of similarity. I did look at NetBSD a few times while debugging to
get some ideas about what I might have done wrong in my first attempt.
Rename visible x86_64 references to amd64.
Kill MID_MACHINE, its a.out specific, the only platform that supports it
is i386. All of the other platforms should remove it too.
