Use PCID to avoid complete TLB shootdown when switching between user
and kernel mode with PTI enabled.
I use the model close to what I read about KAISER, user-mode PCID has
1:1 correspondence to the kernel-mode PCID, by setting bit 11 in PCID.
Full kernel-mode TLB shootdown is performed on context switches, since
KVA TLB invalidation only works in the current pmap. User-mode part of
TLB is flushed on the pmap activations as well.
Similarly, IPI TLB shootdowns must handle both kernel and user address
spaces for each address. Note that machines which implement PCID but
do not have INVPCID instructions, cause the usual complications in the
IPI handlers, due to the need to switch to the target PCID temporary.
This is racy, but because for PCID/no-INVPCID we disable the
interrupts in pmap_activate_sw(), IPI handler cannot see inconsistent
state of CPU PCID vs PCPU pmap/kcr3/ucr3 pointers.
On the other hand, on kernel/user switches, CR3_PCID_SAVE bit is set
and we do not clear TLB.
I can imagine alternative use of PCID, where there is only one PCID
allocated for the kernel pmap. Then, there is no need to shootdown
kernel TLB entries on context switch. But copyout(3) would need to
either use method similar to proc_rwmem() to access the userspace
data, or (in reverse) provide a temporal mapping for the kernel buffer
into user mode PCID and use trampoline for copy.
Reviewed by: markj (previous version)
Tested by: pho
Discussed with: alc (some aspects)
Sponsored by: The FreeBSD Foundation
MFC after: 3 weeks
Differential revision: https://reviews.freebsd.org/D13985
When PTI is enabled, empty IDT slots point to rsvd_pti.
Reported by: Dexuan-BSD Cui <dexuan.bsd@gmail.com>
Sponsored by: The FreeBSD Foundation
MFC after: 5 days
When allocating memory through malloc(9), we always expect the amount of
memory requested to be unsigned as a negative value would either stand for
an error or an overflow.
Unsign some values, found when considering the use of mallocarray(9), to
avoid unnecessary casting. Also consider that indexes should be of
at least the same size/type as the upper limit they pretend to index.
MFC after: 3 weeks
Uses of mallocarray(9).
The use of mallocarray(9) has rocketed the required swap to build FreeBSD.
This is likely caused by the allocation size attributes which put extra pressure
on the compiler.
Given that most of these checks are superfluous we have to choose better
where to use mallocarray(9). We still have more uses of mallocarray(9) but
hopefully this is enough to bring swap usage to a reasonable level.
Reported by: wosch
PR: 225197
Kernel Page Table Isolation (KPTI) was introduced in r328083 as a
mitigation for the 'Meltdown' vulnerability. AMD CPUs are not affected,
per https://www.amd.com/en/corporate/speculative-execution:
We believe AMD processors are not susceptible due to our use of
privilege level protections within paging architecture and no
mitigation is required.
Thus default KPTI to off for AMD CPUs, and to on for others. This may
be refined later as we obtain more specific information on the sets of
CPUs that are and are not affected.
Submitted by: Mitchell Horne
Reviewed by: cem
Relnotes: Yes
Security: CVE-2017-5754
Sponsored by: The FreeBSD Foundation
Differential Revision: https://reviews.freebsd.org/D13971
The implementation of the Kernel Page Table Isolation (KPTI) for
amd64, first version. It provides a workaround for the 'meltdown'
vulnerability. PTI is turned off by default for now, enable with the
loader tunable vm.pmap.pti=1.
The pmap page table is split into kernel-mode table and user-mode
table. Kernel-mode table is identical to the non-PTI table, while
usermode table is obtained from kernel table by leaving userspace
mappings intact, but only leaving the following parts of the kernel
mapped:
kernel text (but not modules text)
PCPU
GDT/IDT/user LDT/task structures
IST stacks for NMI and doublefault handlers.
Kernel switches to user page table before returning to usermode, and
restores full kernel page table on the entry. Initial kernel-mode
stack for PTI trampoline is allocated in PCPU, it is only 16
qwords. Kernel entry trampoline switches page tables. then the
hardware trap frame is copied to the normal kstack, and execution
continues.
IST stacks are kept mapped and no trampoline is needed for
NMI/doublefault, but of course page table switch is performed.
On return to usermode, the trampoline is used again, iret frame is
copied to the trampoline stack, page tables are switched and iretq is
executed. The case of iretq faulting due to the invalid usermode
context is tricky, since the frame for fault is appended to the
trampoline frame. Besides copying the fault frame and original
(corrupted) frame to kstack, the fault frame must be patched to make
it look as if the fault occured on the kstack, see the comment in
doret_iret detection code in trap().
Currently kernel pages which are mapped during trampoline operation
are identical for all pmaps. They are registered using
pmap_pti_add_kva(). Besides initial registrations done during boot,
LDT and non-common TSS segments are registered if user requested their
use. In principle, they can be installed into kernel page table per
pmap with some work. Similarly, PCPU can be hidden from userspace
mapping using trampoline PCPU page, but again I do not see much
benefits besides complexity.
PDPE pages for the kernel half of the user page tables are
pre-allocated during boot because we need to know pml4 entries which
are copied to the top-level paging structure page, in advance on a new
pmap creation. I enforce this to avoid iterating over the all
existing pmaps if a new PDPE page is needed for PTI kernel mappings.
The iteration is a known problematic operation on i386.
The need to flush hidden kernel translations on the switch to user
mode make global tables (PG_G) meaningless and even harming, so PG_G
use is disabled for PTI case. Our existing use of PCID is
incompatible with PTI and is automatically disabled if PTI is
enabled. PCID can be forced on only for developer's benefit.
MCE is known to be broken, it requires IST stack to operate completely
correctly even for non-PTI case, and absolutely needs dedicated IST
stack because MCE delivery while trampoline did not switched from PTI
stack is fatal. The fix is pending.
Reviewed by: markj (partially)
Tested by: pho (previous version)
Discussed with: jeff, jhb
Sponsored by: The FreeBSD Foundation
MFC after: 2 weeks
The static atrtc_set() function was called only from clock_settime(), so
just move its contents entirely into clock_settime() and delete atrtc_set().
Rename the struct bcd_clocktime variables from 'ct' to 'bct'. I had
originally wanted to emphasize how identical the clocktime and bcd_clocktime
structs were, but things evolved to the point where the structs are not at
all identical anymore, so now emphasizing the difference seems better.
related series of operations without doing a lock/unlock for each byte.
Use them when reading and writing the entire set of time registers.
The original rtcin() and writertc() functions which do lock/unlock on each
byte still exist, because they are public and called by outside code.
Focus on code where we are doing multiplications within malloc(9). None of
these ire likely to overflow, however the change is still useful as some
static checkers can benefit from the allocation attributes we use for
mallocarray.
This initial sweep only covers malloc(9) calls with M_NOWAIT. No good
reason but I started doing the changes before r327796 and at that time it
was convenient to make sure the sorrounding code could handle NULL values.
X-Differential revision: https://reviews.freebsd.org/D13837
New common routines were added to kern/subr_clock.c for converting between
calendrical time expressed in BCD and struct timespec. The new functions
return EINVAL on error, as expected when the clock hardware does not provide
valid time.
PR: 224813
Differential Revision: https://reviews.freebsd.org/D13731 (no reviewers)
allocated with a tag to come from the specified domain if it meets the
other constraints provided by the tag. Automatically create a tag at
the root of each bus specifying the domain local to that bus if
available.
Reviewed by: jhb, kib
Tested by: pho
Sponsored by: Netflix, Dell/EMC Isilon
Differential Revision: https://reviews.freebsd.org/D13545
userspace to control NUMA policy administratively and programmatically.
Implement domainset based iterators in the page layer.
Remove the now legacy numa_* syscalls.
Cleanup some header polution created by having seq.h in proc.h.
Reviewed by: markj, kib
Discussed with: alc
Tested by: pho
Sponsored by: Netflix, Dell/EMC Isilon
Differential Revision: https://reviews.freebsd.org/D13403
Add cpuctl(4) ioctl CPUCTL_EVAL_CPU_FEATURES which forces re-read of
cpu_features, cpu_features2, cpu_stdext_features, and
std_stdext_features2.
The intent is to allow the kernel to see the changes in the CPU
features after micocode update. Of course, the update is not atomic
across variables and not synchronized with readers. See the man page
warning as well.
Reviewed by: imp (previous version), jilles
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
Differential revision: https://reviews.freebsd.org/D13770
SDM editions 64 and below stated that it is enough to use MFENCe or
LFENCE to serialize x2APIC register writes. New edition 65 requires
either full serialization instruction or MFENCE;LFENCE sequence. Use
the later, FreeBSD needs serialization to ensure that writes done
before IPI request are visible to the target IPI CPU.
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
(now: Interrupt_Index[15]) and assigned the previously reserved bits
55:48 (Interrupt_Index[14:0] goes into 63:49 while Destination Field
used 63:56 and bit 48 now is Interrupt_Format) in the IO redirection
tables (see the VT-d specification, "5.1.5.1 I/OxAPIC Programming").
Thus, when not using interrupt remapping, ensure that all previously
reserved bits in the high part of the RTEs are zero instead of doing
a read-modify-write for their Destination Field bits only.
Otherwise, on machines based on Apollo Lake and its derivatives such
as Denverton, typically some of the previously preserved bits remain
set after boot when not employing interrupt remapping. The result is
that INTx interrupts are not getting delivered.
Note: With an AMD IOMMU, interrupt remapping apparently bypasses the
IO APIC altogether.
Submitted by: loos (modulo comment)
Reviewed by: jhb (modulo comment)
platform divergence.
Only architectures which pass arguments in registers (mips)
and platforms which use really weird compilers (any?) would
need to augment the contents of <sys/_stdarg.h>
Convert x86, arm and arm64 architectures to use <sys/_stdarg.h>
being removed from GENERIC in 12. Always print PNP info for ISA when
it exists: it doesn't depend on ISAPNP. Add PNP ID to orm and vga to
prevent us from warning about them since those devices aren't being
removed from GENERIC. PNP devices will be removed from GENERIC too,
but they will be automatically loaded, so need no warning. We don't
warn for non-GENERIC kernels because people running them are presumed
to know what they are doing.
MFC After: 2 weeks
restart_cpus() worked well enough by accident. Before this set of fixes,
resume_cpus() used the same cpuset (started_cpus, meaning CPUs directed to
restart) as restart_cpus(). resume_cpus() waited for the wrong cpuset
(stopped_cpus) to become empty, but since mixtures of stopped and suspended
CPUs are not close to working, stopped_cpus must be empty when resuming so
the wait is null -- restart_cpus just allows the other CPUs to restart and
returns without waiting.
Fix resume_cpus() to wait on a non-wrong cpuset for the ACPI case, and
add further kludges to try to keep it working for the XEN case. It
was only used for XEN. It waited on suspended_cpus. This works for
XEN. However, for ACPI, resuming is a 2-step process. ACPI has already
woken up the other CPUs and removed them from suspended_cpus. This
fix records the move by putting them in a new cpuset resuming_cpus.
Waiting on suspended_cpus would give the same null wait as waiting on
stopped_cpus. Wait on resuming_cpus instead.
Add a cpuset toresume_cpus to map the CPUs being told to resume to keep
this separate from the cpuset started_cpus for mapping the CPUs being told
to restart. Mixtures of stopped and suspended/resuming CPUs are still far
from working. Describe new and some old cpusets in comments.
Add further kludges to cpususpend_handler() to try to avoid breaking it
for XEN. XEN doesn't use resumectx(), so it doesn't use the second
return path for savectx(), and it goes from the suspended state directly
to the restarted state, while ACPI resume goes through the resuming state.
Enter the resuming state early for all cases so that resume_cpus can test
for being in this state and not have to worry about the intermediate
!suspended state for ACPI only.
Reviewed by: kib
it by a transient double mapping for the one instruction in ACPI wakeup
where it is needed (and for many surrounding instructions in ACPI resume).
Invalidate the TLB as soon as convenient after undoing the transient
mapping. ACPI resume already has the strict ordering needed for this.
This fixes the non-trapping of null pointers and other garbage pointers
below NBPDR (except transiently). NBPDR is quite large (4MB, or 2MB for
PAE).
This fixes spurious traps at the first instruction in VM86 bioscalls.
The traps are for transiently missing read permission in the first
VM86 page (physical page 0) which was just written to at KERNBASE in
the kernel. The mechanism is unknown (it is not simply PG_G).
locore uses a similar but larger transient double mapping and needs
it for 2 instructions instead of 1. Unmap the first PDE in it after
the 2 instructions to detect most garbage pointers while bootstrapping.
pmap_bootstrap() finishes the unmapping.
Remove the avoidance of the double mapping for a recently fixed special
case. ACPI resume could use this avoidance (made non-special) to avoid
any problems with the transient double mapping, but no such problems
are known.
Update comments in locore. Many were for old versions of FreeBSD which
tried to map low memory r/o except for special cases, or might have
allowed access to low memory via physical offsets. Now all kernel
maps are r/w, and removal of of the double map disallows use of physical
offsets again.
turn it off by default. It is very inefficient to verify current P-state of
each core, especially for CPUs with many cores. When multiple commands are
requested to the same power domain before completion of pending transitions,
the last command is executed according to the manual. Because requests are
serialized by the caller, all cores will receive the same command for each
call. Do not call sched_bind() and sched_unbind(). It is redundant because
the caller does it anyway.
Mainly focus on files that use BSD 2-Clause license, however the tool I
was using misidentified many licenses so this was mostly a manual - error
prone - task.
The Software Package Data Exchange (SPDX) group provides a specification
to make it easier for automated tools to detect and summarize well known
opensource licenses. We are gradually adopting the specification, noting
that the tags are considered only advisory and do not, in any way,
superceed or replace the license texts.
Mainly focus on files that use BSD 3-Clause license.
The Software Package Data Exchange (SPDX) group provides a specification
to make it easier for automated tools to detect and summarize well known
opensource licenses. We are gradually adopting the specification, noting
that the tags are considered only advisory and do not, in any way,
superceed or replace the license texts.
Special thanks to Wind River for providing access to "The Duke of
Highlander" tool: an older (2014) run over FreeBSD tree was useful as a
starting point.
The Software Package Data Exchange (SPDX) group provides a specification
to make it easier for automated tools to detect and summarize well known
opensource licenses. We are gradually adopting the specification, noting
that the tags are considered only advisory and do not, in any way,
superceed or replace the license texts.
Special thanks to Wind River for providing access to "The Duke of
Highlander" tool: an older (2014) run over FreeBSD tree was useful as a
starting point.
Initially, only tag files that use BSD 4-Clause "Original" license.
RelNotes: yes
Differential Revision: https://reviews.freebsd.org/D13133
It is for console presented at 2001 and featuring Pentium III
processor. Even if any of them are still alive and run FreeBSD, we do
not have any sign of life from their users. While removing another
dozens of #ifdefs from the i386 sources reduces the aversion from
looking at the code and improves the platform vitality.
Reviewed by: cem, pfg, rink (XBOX support author)
Sponsored by: The FreeBSD Foundation
Differential revision: https://reviews.freebsd.org/D13016
Also keep the calculated vm_page_alloc_contig() flags in the variable
to not re-evaluate it on the loop iteration.
Noted by: alc
Sponsored by: The FreeBSD Foundation
similar to the kernel memory allocator.
This simplifies NUMA allocation because the domain will be known at wait
time and races between failure and sleeping are eliminated. This also
reduces boilerplate code and simplifies callers.
A wait primitive is supplied for uma zones for similar reasons. This
eliminates some non-specific VM_WAIT calls in favor of more explicit
sleeps that may be satisfied without new pages.
Reviewed by: alc, kib, markj
Tested by: pho
Sponsored by: Netflix, Dell/EMC Isilon
- allocate value for new AT_HWCAP2 auxiliary vector on all platforms.
- expand 'struct sysentvec' by new 'u_long *sv_hwcap2', in exactly
same way as for AT_HWCAP.
MFC after: 1 month
Reviewed by: kib
Differential Revision: https://reviews.freebsd.org/D12699
When it was added in r314636, AMD Thresholding was hardcoded to only
bank 4 (Northbridge) for some reason. However, even on family 10h the
MCAx_MISC register Valid/Present bits determine whether thresholding is
supported on that bank.
Expand thresholding support to monitor all monitorable banks. This
simplifies some of the logic and makes it more consistent with our Intel
CMCI support.
Reviewed by: markj (earlier version)
Sponsored by: Dell EMC Isilon
Differential Revision: https://reviews.freebsd.org/D12321
A new 'u_long *sv_hwcap' field is added to 'struct sysentvec'. A
process ABI can set this field to point to a value holding a mask of
architecture-specific CPU feature flags. If an ABI does not wish to
supply AT_HWCAP to processes the field can be left as NULL.
The support code for AT_EHDRFLAGS was already present on all systems,
just the #define was not present. This is a step towards unifying the
AT_* constants across platforms.
Reviewed by: kib
MFC after: 1 month
Differential Revision: https://reviews.freebsd.org/D12290
On AMD, the MCG_CAP feature bit is reserved -- not explicitly zero. Do not
use it to determine CMCI support.
Reviewed by: avg, markj
Sponsored by: Dell EMC Isilon
Differential Revision: https://reviews.freebsd.org/D12320
Scan all buses for CSR bus, not stopping on the first failed
match. Scan all slots for function 0 on the found bus, for instance on
IvyBridge the slot 0 is not decoded at all. Since the scan is quite
unsafe, and access to the buses is mostly useful for developers,
enable the csr buses scan with the tunable.
Current qpi.c makes too many assumptions about the uncore
configuration buses location and about slots occupied. Also it
restricts itself only to Nehalem CPUs. It is needed on all Core-based
Xeons. On the 2600 v2 (IvyBridge) machine I have access to, the CSR
buses have numbers 31 (BSP socket) and 63 (second socket), and there
is no functions pci0.31.0.0 or pci0.63.0.0. According to the CPU
datasheet, all devices on the uncore bus occupy slots >= 8.
Practically, the attach to config buses is required for the intel-pcm
pcm-memory.x tool to work, for instance.
Reviewed by: jhb (previous version)
Sponsored by: Mellanox Technologies
MFC after: 1 week
Differential revision: https://reviews.freebsd.org/D12268
remapping.
VT-d specification requires use of PCI rid as source id for IOAPICs
enumerated by PCI bus. The values from the DMAR ACPI table should be
only used when IOAPIC is not on PCI.
Reviewed by: jhb
Sponsored by: The FreeBSD Foundation
Hardware provided by: Intel
MFC after: 2 weeks
Differential revision: https://reviews.freebsd.org/D12205
the interrupt messages from given IOAPIC, if the IOAPIC can be
enumerated on PCI bus.
If IOAPIC has PCI binding, match the PCI device against MADT
enumerated IOAPIC. Match is done first by registers window physical
address, then by IOAPIC ID as read from the APIC ID register.
PCI bsf address of the matched PCI device is the rid.
Reviewed by: jhb
Sponsored by: The FreeBSD Foundation
Hardware provided by: Intel
MFC after: 2 weeks
X-Differential revision: https://reviews.freebsd.org/D12205
17h supports MCA thresholding in the same way as 16h and earlier.
Supposedly a ScalableMca feature bit in CPUID 8000_0007:EBX must be set, but
that was not true for earlier models, so be careful about relying on it.
While here, document a missing bit in LS MCA MISC0.
Reviewed by: truckman
Sponsored by: Dell EMC Isilon
Differential Revision: https://reviews.freebsd.org/D12237
It doesn't seem necessary to busy the CPU while waiting to transition
into a different p-state.
PR: 221621 (related, but does not completely address)
Reviewed by: truckman
Sponsored by: Dell EMC Isilon
Differential Revision: https://reviews.freebsd.org/D12260
Fix from fallout introduced in r322348 that moved the cpus array to a
dynamic allocation without zeroing the area.
Reported by: mjg
MFC with: r322348
Reviewed by: mjg
Differential revision: https://reviews.freebsd.org/D12220
Not enabling FSGSBASE in %cr4 does not prevent reporting of the
feature by the CPUID instruction (blame Int*l). As result, kernels
which were run under monitors pretended that usermode cannot modify
TLS base without the syscall, while libc noted right combination of
capable CPU and the new kernel version, trying to use the WRFSBASE
instruction.
Really old hypervisors that cannot handle enablement of these features
in %cr4 would require the manual configuration, by setting the loader
tunable hw.cpu_stdext_disable=0x81
Reported by: lwhsu, mjoras
Sponsored by: The FreeBSD Foundation
MFC after: 18 days
Rather than repeatedly nesting loops, separate concerns with a single loop
per call stack level. Use a table to drive the recursive routine. Handle
missing topology layers more gracefully (infer a single unit).
Analyze some additional optional layers which may be present on e.g. AMD Zen
systems (groups, aka dies, per package; and cachegroups, aka CCXes, per
group).
Display that additional information in the boot-time topology information,
when it is relevent (non-one).
Reviewed by: markj@, mjoras@ (earlier version)
Sponsored by: Dell EMC Isilon
Differential Revision: https://reviews.freebsd.org/D12019
This information is normally available via acpi_perf, but in case it is not,
add support for fetching the information via MSRs on AMD family 17h (Zen)
processors. Zen uses a slightly different formula than previous generation
AMD CPUs.
This was inspired by, but does not fix, PR 221621.
Reported by: Sean P. R. <seanpr AT swbell.net>
Reviewed by: mjoras@
Sponsored by: Dell EMC Isilon
Differential Revision: https://reviews.freebsd.org/D12082
The Nodes per Processor topology information determines how many bits of the
APIC ID represent the Node (Zeppelin die, on Zen systems) ID. Documented in
Ryzen and Epyc Processor Programming Reference (PPR).
Correct topology information enables the scheduler to make better decisions
on this hardware.
Reviewed by: kib@
Tested by: jeff@ (earlier version)
Sponsored by: Dell EMC Isilon
Differential Revision: https://reviews.freebsd.org/D11801
Fallout from r322588. I'm not sure why !SMP is a knob we have, but, we have
it.
Reported by: Michael Butler <imb AT protected-networks.net>
Sponsored by: Dell EMC Isilon
Add an option to dynamically rebalance interrupts across cores
(hw.intrbalance); off by default.
The goal is to minimize preemption. By placing interrupt sources on distinct
CPUs, ithreads get preferentially scheduled on distinct CPUs. Overall
preemption is reduced and latency is reduced. In our workflow it reduced
"fighting" between two high-frequency interrupt sources. Reduced latency
was proven by, e.g., SPEC2008.
Submitted by: jeff@ (earlier version)
Reviewed by: kib@
Sponsored by: Dell EMC Isilon
Differential Revision: https://reviews.freebsd.org/D10435
removes the only reference to atrtc_set() from outside of atrtc.c, so make
it static.
The xen timer driver registers as a realtime clock with 1us resolution. In
the past that resulted in only the xen timer's clock_settime() getting
called, so it would call atrtc_set() to set the hardware clock as well. As
of r32090, the clock_settime() method of all registered realtime clocks gets
called, so the xen driver no longer needs to chain-call the lower-resolution
driver.
Thanks to royger@ for talking me through the xen stuff, and for testing.
Introduce a new define to take int account the xAPIC ID limit, for
systems where x2APIC is not available/reliable.
Also change some of the usages of the APIC ID to use an unsigned int
(which is the correct storage type to deal with x2APIC IDs as found in
x2APIC MADT entries).
This allows booting FreeBSD on a box with 256 CPUs and APIC IDs up to
295:
FreeBSD/SMP: Multiprocessor System Detected: 256 CPUs
FreeBSD/SMP: 1 package(s) x 64 core(s) x 4 hardware threads
Package HW ID = 0
Core HW ID = 0
CPU0 (BSP): APIC ID: 0
CPU1 (AP/HT): APIC ID: 1
CPU2 (AP/HT): APIC ID: 2
CPU3 (AP/HT): APIC ID: 3
[...]
Core HW ID = 73
CPU252 (AP): APIC ID: 292
CPU253 (AP/HT): APIC ID: 293
CPU254 (AP/HT): APIC ID: 294
CPU255 (AP/HT): APIC ID: 295
Submitted by: kib (previous version)
Relnotes: yes
MFC after: 1 month
Reviewed by: kib
Differential revision: https://reviews.freebsd.org/D11913
So that MAX_APIC_ID can be bumped without wasting memory.
Note that the usage of MAX_APIC_ID in the SRAT parsing forces the
parser to allocate memory directly from the phys_avail physical memory
array, which is not the best approach probably, but I haven't found
any other way to allocate memory so early in boot. This memory is not
returned to the system afterwards, but at least it's sized according
to the maximum APIC ID found in the MADT table.
Sponsored by: Citrix Systems R&D
MFC after: 1 month
Reviewed by: kib
Differential revision: https://reviews.freebsd.org/D11912
Populate the lapics arrays and call cpu_add/lapic_create in the setup
phase instead. Also store the max APIC ID found in the newly
introduced max_apic_id global variable.
This is a requirement in order to make the static arrays currently
using MAX_LAPIC_ID dynamic.
Sponsored by: Citrix Systems R&D
MFC after: 1 month
Reviewed by: kib
Differential revision: https://reviews.freebsd.org/D11911
reduces diff between amd64 and i386. Also, it fixes a regression introduced
in r322076, i.e., identify_hypervisor() failed to identify some hypervisors.
This function assumes cpu_feature2 is already initialized.
Reported by: dexuan
Tested by: dexuan
but it was broken since r273800 (and r278522, its MFC to stable/10) because
identify_cpu() is called too late, i.e., after init_param1().
MFC after: 3 days
In this case we shouldn't assume that the thread has a valid frame pointer.
Reviewed by: kib
MFC after: 1 week
Differential Revision: https://reviews.freebsd.org/D11787
Pollution from counter.h made __pcpu visible in amd64/pmap.c. Delete
the existing extern decl of __pcpu in amd64/pmap.c and avoid referring
to that symbol, instead accessing the pcpu region via PCPU_SET macros.
Also delete an unused extern decl of __pcpu from mp_x86.c.
Reviewed by: kib
Approved by: markj (mentor)
Sponsored by: Dell EMC Isilon
Differential Revision: https://reviews.freebsd.org/D11666
The mutex protecting access to the registered realtime clock should not be
overloaded to protect access to the atrtc hardware, which might not even be
the registered rtc. More importantly, the resettodr mutex needs to be
eliminated to remove locking/sleeping restrictions on clock drivers, and
that can't happen if MD code for amd64 depends on it. This change moves the
protection into what's really being protected: access to the atrtc date and
time registers.
This change also adds protection when the clock is accessed from
xentimer_settime(), which bypasses the resettodr locking.
Differential Revision: https://reviews.freebsd.org/D11483
--Remove special-case handling of sparc64 bus_dmamap* functions.
Replace with a more generic mechanism that allows MD busdma
implementations to generate inline mapping functions by
defining WANT_INLINE_DMAMAP in <machine/bus_dma.h>. This
is currently useful for sparc64, x86, and arm64, which all
implement non-load dmamap operations as simple wrappers
around map objects which may be bus- or device-specific.
--Remove NULL-checked bus_dmamap macros. Implement the
equivalent NULL checks in the inlined x86 implementation.
For non-x86 platforms, these checks are a minor pessimization
as those platforms do not currently allow NULL maps. NULL
maps were originally allowed on arm64, which appears to have
been the motivation behind adding arm[64]-specific barriers
to bus_dma.h, but that support was removed in r299463.
--Simplify the internal interface used by the bus_dmamap_load*
variants and move it to bus_dma_internal.h
--Fix some drivers that directly include sys/bus_dma.h
despite the recommendations of bus_dma(9)
Reviewed by: kib (previous revision), marius
Differential Revision: https://reviews.freebsd.org/D10729
Do not queue dmar_map_entries with zeroed gseq to
dmar_qi_invalidate_locked(). Zero gseq stops the processing in the qi
task. Do not assign possibly uninitialized on-stack gseq to map
entries when requeuing them on unit tlb_flush queue. Random garbage
in gsec is interpreted as too high invalidation sequence number and
again stop the processing in the task.
Make the sequence numbers generation completely contained in
dmar_qi_invalidate_locked() and dmar_qi_emit_wait_seq(). Upper code
directly passes boolean requesting emiting wait command instead of
trying to provide hint to avoid it by passing NULL gseq pointer.
Microoptimize the requeueing to tlb_flush queue by doing it for the
whole queue.
Diagnosed and tested by: Brett Gutstein <bgutstein@rice.edu>
Discussed with: alc
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
All interrupts are routed to the sole CPU in that case implicitly.
This is a regression in EARLY_AP_STARTUP. Previously the 'assign_cpu'
variable was only set when a multi-CPU system finished booting, so
it's value both meant that interrupts could be assigned and that
there was more than one CPU.
PR: 219882
Reported by: ota@j.email.ne.jp
MFC after: 3 days
Do not try to set LMA bit while CPU is still in legacy mode.
Apparently Intel CPUs ignore non-id writes to LMA, while AMD's
(over-)react with #GP.
Reported and tested by: danfe
Sponsored by: The FreeBSD Foundation
MFC after: 3 days
An extra copy of the system call gate was added to the default LDT back
in 1996 (r18513 / r18514). However, the ability to run BSD/OS 2.1
i386 binaries under FreeBSD's native ABI is most likely no longer
needed.
Discussed with: kib
This patch improves the boundary checks in busdma to allow more cases
using the regular page based kernel memory allocator. Especially in
the case of having a non-zero boundary in the parent DMA tag. For
example AMD64 based platforms set the PCI DMA tag boundary to
PCI_DMA_BOUNDARY, 4GB, which before this patch caused contiguous
memory allocations to be preferred when allocating more than PAGE_SIZE
bytes. Even if the required alignment was less than PAGE_SIZE bytes.
This patch also fixes the nsegments check for using kmem_alloc_attr()
when the maximum segment size is less than PAGE_SIZE bytes.
Updated some comments describing the code in question.
Differential Revision: https://reviews.freebsd.org/D10645
Reviewed by: kib, jhb, gallatin, scottl
MFC after: 1 week
Sponsored by: Mellanox Technologies
operation after processor is configured to allow all required
features.
In particular, NX must be enabled in EFER, otherwise load of page
table element with nx bit set causes reserved bit page fault. Since
malloc uses direct mapping for small allocations, in particular for
the suspension pcbs, and DMAP is nx after r316767, this commit tripped
fault on resume path.
Restore complete state of EFER while wakeup code is still executing
with custom page table, before calling resumectx, instead of trying to
guess which features might be needed before resumectx restored EFER on
its own.
Bisected and tested by: trasz
Sponsored by: The FreeBSD Foundation
MFC after: 2 weeks
In exceptional circumstances, an MCA exception will trigger when the
freelist is exhausted. In such a case, no error will be logged on the list
and 'mca_count' will not be incremented.
Prior to this patch, all CPUs that received the exception would spin
forever.
With this change, the CPU that detects the error but finds the freelist
empty will proceed to panic the machine, ending the deadlock.
A follow-up to r260457.
Reported by: Ryan Libby <rlibby at gmail.com>
Reviewed by: jhb@
Sponsored by: Dell EMC Isilon
Differential Revision: https://reviews.freebsd.org/D10536
in place. To do per-cpu stats, convert all fields that previously were
maintained in the vmmeters that sit in pcpus to counter(9).
- Since some vmmeter stats may be touched at very early stages of boot,
before we have set up UMA and we can do counter_u64_alloc(), provide an
early counter mechanism:
o Leave one spare uint64_t in struct pcpu, named pc_early_dummy_counter.
o Point counter(9) fields of vmmeter to pcpu[0].pc_early_dummy_counter,
so that at early stages of boot, before counters are allocated we already
point to a counter that can be safely written to.
o For sparc64 that required a whole dummy pcpu[MAXCPU] array.
Further related changes:
- Don't include vmmeter.h into pcpu.h.
- vm.stats.vm.v_swappgsout and vm.stats.vm.v_swappgsin changed to 64-bit,
to match kernel representation.
- struct vmmeter hidden under _KERNEL, and only vmstat(1) is an exclusion.
This is based on benno@'s 4-year old patch:
https://lists.freebsd.org/pipermail/freebsd-arch/2013-July/014471.html
Reviewed by: kib, gallatin, marius, lidl
Differential Revision: https://reviews.freebsd.org/D10156
The MFC will include a compat definition of smp_no_rendevous_barrier()
that calls smp_no_rendezvous_barrier().
Reviewed by: gnn, kib
MFC after: 1 week
Differential Revision: https://reviews.freebsd.org/D10313
This is applicable only to the older processors that do not have the AMD
Topology extension.
Opteron 6100-series "Magny-Cours" processors had multiple nodes within a
package and didn't have the Topology extension. Without this change
FreeBSD would assume that those processors have a single L3 cache shared
by all cores while, in fact, each node has its own L3 cache.
Many thanks to Freddie Cash <fjwcash@gmail.com> for providing valuable
hardware information.
MFC after: 2 weeks
The change introduced a dependency between genassym.c and header files
generated from .m files, but that dependency is not specified in the
make files.
Also, the change could be not as useful as I thought it was.
Reported by: dchagin, Manfred Antar <null@pozo.com>, and many others
The change seems to be more in the nomenclature than in the way the
topology is advertised by the hardware.
Tested by: truckman (earlier version of the change)
MFC after: 2 weeks
Implement timeouts for register-based DMAR commands. Tunable/sysctl
hw.dmar.timeout specifies the timeout in nanoseconds, set it to zero
to allow infinite wait. Default is 1ms.
Runtime modification of the sysctl is not safe, it is allowed for
debugging.
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
Kernel environment variable hw.busdma.default can take values 'bounce'
and 'dmar' and selects corresponding busdma backend as default.
Per-device environment variable hw.busdma.pci<domain>.<bus>.<slot>.<func>
takes the same values and overrides hw.busdma.default for the given device.
Note that even with hw.busdma.default=bounce, DMA translation engines
are still started if DMARs are enabled, to disable them use
hw.dmar.dma tunable, as before.
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
The change is more intrusive than I would like because the feature
requires that a vector number is written to a special register.
Thus, now the vector number has to be provided to lapic_eoi().
It was readily available in the IO-APIC and MSI cases, but the IPI
handlers required more work.
Also, we now store the VMM IPI number in a global variable, so that it
is available to the justreturn handler for the same reason.
Reviewed by: kib
MFC after: 6 weeks
Differential Revision: https://reviews.freebsd.org/D9880
As noted in the comment, nothing special needs to be done to destroy
the unneeded context after the allocation race, but the context memory
itself still should to be freed.
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
It does not make sense since identity mapping already provides the
required mapping for RMRR ranges. More, since identity page tables do
not reflect content of map entries for id domains, creating RMRR
entries makes domain data inconsistent.
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
Ignore them like it's done in the MADT parser. This allows booting on a box
with SRAT and APIC IDs > 255.
Reported by: Wei Liu <wei.liu2@citrix.com>
Tested by: Wei Liu <wei.liu2@citrix.com>
Reviewed by: kib
MFC after: 2 weeks
Sponsored by: Citrix Systems R&D
1. There a was a typo in one place where the processor family is
checked (16 vs 0x16). Now the checks are consolidated in a single
function.
2. Instead of an array of struct amd_et_state objects the code allocated
an array of pointers. That was no problem on amd64 where the sizes
are the same, but could be a problem on i386.
Reported by: tuexen and others
Tested by: tuexen (earlier version of the fix)
Pointyhat to: avg
MFC after: 5 days
X-MFC with: r314636
Currently the feature is implemented only for a subset of errors
reported via Bank 4. The subset includes only DRAM-related errors.
The new code builds upon and reuses the Intel CMC (Correctable MCE
Counters) support code. However, the AMD feature is quite different
and, unfortunately, much less regular.
For references please see AMD BKDGs for models 10h - 16h.
Specifically, see MSR0000_0413 NB Machine Check Misc (Thresholding)
Register (MC4_MISC0).
http://developer.amd.com/resources/developer-guides-manuals/
Reviewed by: jhb
MFC after: 1 month
Differential Revision: https://reviews.freebsd.org/D9613
Renumber cluase 4 to 3, per what everybody else did when BSD granted
them permission to remove clause 3. My insistance on keeping the same
numbering for legal reasons is too pedantic, so give up on that point.
Submitted by: Jan Schaumann <jschauma@stevens.edu>
Pull Request: https://github.com/freebsd/freebsd/pull/96
The extended LVT entries can be used to configure interrupt delivery
for various events that are internal to a processor and can use this
feature.
All current processors that support the feature have four of such entries.
The entries are all masked upon the processor reset, but it's possible
that firmware may use some of them.
BIOS and Kernel Developer's Guides for some processor models do not assign
any particular names to the extended LVTs, while other BKDGs provide names
and suggested usage for them.
However, there is no fixed mapping between the LVTs and the processor
events in any processor model that supports the feature. Any entry can be
assigned to any event. The assignment is done by programming an offset
of an entry into configuration bits corresponding to an event.
This change does not expose the flexibility that the feature offers.
The change adds just a single method to configure a hardcoded extended LVT
entry to deliver APIC_CMC_INT. The method is designed to be used with
Machine Check Error Thresholding mechanism on supported processor models.
For references please see BKDGs for families 10h - 16h and specifically
descriptions of APIC30, APIC400, APIC[530:500] registers.
For a description of the Error Thresholding mechanism see, for example,
BKDG for family 10h, section 2.12.1.6.
http://developer.amd.com/resources/developer-guides-manuals/
Thanks to jhb and kib for their suggestions.
Reviewed by: kib
Discussed with: jhb
MFC after: 5 weeks
Relnotes: maybe
Differential Revision: https://reviews.freebsd.org/D9612
The fixed is used only to fix up buggy MPTable information and the
trigger mode is probably ignored for the relevant interrupt types
anyway. Still, it's better to be standards compliant and have the code
do what it says it does.
Discussed with: jhb
MFC after: 5 days
The ifdefs were '#if !defined(__i386__) || !defined(PC98)' previously,
so cpu_idle_acpi was enabled both i386 and amd64 except PC98.
I was obfuscated by '#if !defined(__i386__)' condition.
Submitted by: bde
Reported by: bde
Convert PCIe hot plug support over to asking the firmware, if any, for
permission to use the HotPlug hardware. Implement pci_request_feature
for ACPI. All other host pci connections to allowing all valid feature
requests.
Sponsored by: Netflix
We have an original panic. Then, instead of writing the core to the dump
device, the kernel has a second panic: "smp_targeted_tlb_shootdown:
interrupts disabled". This change is an attempt to fix that second panic.
When the other CPUs are stopped, we can't notify them of the TLB shootdown,
so we skip that operation. However, when the CPUs come back up, we
invalidate the TLB to ensure they correctly observe any changes to the
page mappings.
Reviewed by: kib
Sponsored by: Netflix
Differential Revision: https://reviews.freebsd.org/D9786
On Core2 and older Intel CPUs, where TSC stops in C2, system does not
allow C2 entrance if timecounter hardware is TSC. This is done by
tc_windup() which tests for TC_FLAGS_C2STOP flag of the new
timecounter and increases cpu_disable_c2_sleep if flag is set. Right
now init_TSC_tc() only sets the flag if cpu_deepest_sleep >= 2, but
TSC is initialized too early for this variable to be set by
acpi_cpu.c.
There is no reason to require that ACPI reported C2 and deeper states
to set TC_FLAGS_C2STOP, so remove cpu_deepest_sleep test from
init_TSC_tc() condition. And since this is the only use of the
variable, remove it at all.
Reported and submitted by: Jia-Shiun Li <jiashiun@gmail.com>
Suggested by: jhb
MFC after: 2 weeks
Use large enough type for calculation of mtrr physmask. Typical
cpu_maxphyaddr is 36 or larger.
Reported and tested by: sbruno
Sponsored by: The FreeBSD Foundation
MFC after: 13 days
and there is no reason to check cpu family or vendor.
Noted by: royger
Reviewed by: jhb
Sponsored by: The FreeBSD Foundation
MFC after: 2 weeks
Differential revision: https://reviews.freebsd.org/D9657
code. Also fix cast and remove unneeded XXX in comment.
Noted and reviewed by: jhb
Sponsored by: The FreeBSD Foundation
MFC after: 2 weeks
Differential revision: https://reviews.freebsd.org/D9657
compile options. Remove doxygen pointers to now deleted files. Remove
EISA and VME as examples in bus_space.9.
Retained EISA mode code for IO PIC and MPTABLES because that's not
EISA bus, per se, and some people have abused EISA to mean "EISA-like
behavior as opposed to ISA" rather than using it for EISA add-in
cards.
Relnotes: yes
machines, only a few 486 machines that used it, and those haven't had
enough memory to run FreeBSD for quite some time (often limited to
16MB).
Not to be confused with the Machine Check Architecture, which is still
very much alive and used (and untouched by this commit).
No Objection From: arch@
This solves several problems.
First of all, cmc_throttle is specified in seconds and there was no
conversion between ticks and seconds when they were mixed together.
Second, we avoid potential problems with ticks wrapping around.
Resolution of time_uptime should be sufficient for the throttling
purposes.
Discussed with: jhb
MFC after: 12 days
Previously, if the threshold was changed, then MC_CTL2_CMCI_EN would get
cleared and the logic would switch to the polling only mode.
Discussed with: jhb
MFC after: 2 weeks
using the ACPI C1/mwait sleep method.
Previously, the mwait instruction would return when an interrupt was
pending; however, the idle loop did not actually enable interrupts when
this occurred. This led to a situation where the idle loop could quickly
spin through the C1/mwait sleep method a number of times when an interrupt
was pending. (Eventually, the situation corrected itself when something
other than an interrupt triggered the idle loop to either enable interrupts
or schedule another thread.)
Reviewed by: kib, imp (earlier version)
Input from: jhb
MFC after: 1 week
Sponsored by: Netflix
The types are for the byte offset and page index in vm object. They
are similar to off_t, which is defined as 64bit MI integer. Using MI
definitions will allow to provide consistent MD values of vm
object-related maximum sizes.
Reviewed by: alc
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
and device npx.
This means that FPU is always initialized and handled when available,
and SSE+ register file and exception are handled when available. This
makes the kernel FPU code much easier to maintain by the cost of
slight bloat for CPUs older than 25 years.
CPU_DISABLE_CMPXCHG outlived its usefulness, see the removed comment
explaining the original purpose.
Suggested by and discussed with: bde
Tested by: pho
Sponsored by: The FreeBSD Foundation
MFC after: 3 weeks
Replace archaic "busses" with modern form "buses."
Intentionally excluded:
* Old/random drivers I didn't recognize
* Old hardware in general
* Use of "busses" in code as identifiers
No functional change.
http://grammarist.com/spelling/buses-busses/
PR: 216099
Reported by: bltsrc at mail.ru
Sponsored by: Dell EMC Isilon
These are of the few cases where we use the GCC non-null attributes in
non-header code. As part of a review [1] of our use of such attributes we
are replacing such uses of the overly aggressive GCC attribute with clang's
_Nonnull attribute.
In this case the attributes serve little purpose as they just don't
enforce run time checks, If anything the attributes would cause NULL pointer
checks to be ignored but there are no such checks so only effect is
cosmetic.
The references appear to be left over from code development and likely
already fulfilled their purpose.
Reference [1]:
https://reviews.freebsd.org/D9004
Reviewed by: jhb
MFC after: 3 weeks
Current Xen IPI setup functions require that the caller provide a device in
order to obtain the name of the interrupt from it. With early AP startup this
device is no longer available at the point where IPIs are bound, and a KASSERT
would trigger:
panic: NULL pcpu device_t
cpuid = 0
KDB: stack backtrace:
db_trace_self_wrapper() at db_trace_self_wrapper+0x2b/frame 0xffffffff82233a20
vpanic() at vpanic+0x186/frame 0xffffffff82233aa0
kassert_panic() at kassert_panic+0x126/frame 0xffffffff82233b10
xen_setup_cpus() at xen_setup_cpus+0x5b/frame 0xffffffff82233b50
mi_startup() at mi_startup+0x118/frame 0xffffffff82233b70
btext() at btext+0x2c
Fix this by no longer requiring the presence of a device in order to bind IPIs,
and simply use the "cpuX" format where X is the CPU identifier in order to
describe the interrupt.
Reported by: sbruno, cperciva
Tested by: sbruno
X-MFC-With: r310177
Sponsored by: Citrix Systems R&D
This 6 times gettimeofday performance, as measured by
tools/tools/syscall_timing
Reviewed by: kib
MFC after: 1 week
Sponsored by: Microsoft
Differential Revision: https://reviews.freebsd.org/D8789
The MCA taskqueue is not initialized until some time after CMCIs are
enabled on the BSP.
Reviewed by: cem, jhb
MFC after: 1 week
Sponsored by: Dell EMC Isilon
Differential Revision: https://reviews.freebsd.org/D8783
stack_machdep.c is compiled if either of the DDB or STACK options is
specified, but stack_save_td_running() isn't useable from DDB. Moreover,
stack_save_td_running() works by raising an NMI on the CPU running the
target thread, and the corresponding handler is compiled only if STACK is
configured.
Reported by: kib
MFC after: 1 week
actual numbers would help debugging (also, `MSR' and `ACPI' are standard
abbreviations and thus should be properly capitalized)
- Rephrase unsupported AMD CPUs message and wrap as an overly long line:
`sorry' 1) is wrongly spelled after period (starts with a small letter)
and 2) carries emotional "tinge" that is unnecessary and even bogus in
debug message; `implemented' is not the best word as `supported' suits
better in this context
- Improve readability when reporting resulted P-state transition (debug)
Approved by: jhb
(APIC-Timer-always-running) is not implemented.
If machine has ncpus >= 8 and non-FSB interrupt routing from HPET,
default HPET eventtimer quality 450 is reduced by 100, i.e. it is
350. On the other hand, LAPIC default quality is 600 and it is reduced
by 200 if ARAT is not reported. We end up with HPET quality 350 <
LAPIC quality 400, despite ARAT is not set. Then, since deep Cx
states are active by default, eventtimer fail.
E.g., on Nehalem Core i7 CPU and X58 chipset, LAPIC only works in
C0/C1/C1E and HPET does not implement FSB mode, which otherwise
requires manual switch to HPET to get working system.
Set LAPIC eventtimer quality to 100 if no ARAT.
While there, do not ignore deadlint TSC mode for LAPIC timer if ARAT
is not implemented. If user manually selected LAPIC eventtimer on
such CPU, there is no reason to not use deadline if available and not
disabled administratively.
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
they shouldn't be.
I used this during driver bring-up to find that the Linux driver holds a
whole lot of locks whilst doing their equivalent of busdma operations.
If this works out well, it should be added to the other architecture busdma
implementations to aid in similar debugging.
Tested:
* bounce buffer and dmar busdma, Lenovo X230 laptop, all the internal
hardware
* ath(4) too
Discussed with: jhb
Add a reference count to xenisrc. This is required for implementation of
unmap-notifications in the grant table userspace device (gntdev). We need to
hold a reference to the event channel port, in case the user deallocates the
port before we send the notification.
Submitted by: jaggi
Reviewed by: royger
Differential review: https://reviews.freebsd.org/D7429
Use the same logic to calculate the nominal CPU frequency from the P-state
MSRs on family 0x12, 0x15, and 0x16 CPUs as is used for family 0x10.
Family 0x14 was included in the original patch in the PR but I left that
out as the BIOS writer's guide for family 0x14 CPUs show a different layout
for the relevant MSR and include a different formulate for calculating the
frequency.
While here, simplify a few expressions and print out the family of
unsupported CPUs in hex rather than decimal.
PR: 212020
Submitted by: Anthony Jenkins <Scoobi_doo@yahoo.com>
MFC after: 1 month
Differential Revision: https://reviews.freebsd.org/D7587
Reject attempts to read from or memory map offsets in /dev/mem that are
beyond the maximum-supported physical address of the current CPU.
Reviewed by: kib
MFC after: 1 month
Differential Revision: https://reviews.freebsd.org/D7408
- Make !KDB config buildable.
- Simplify interface to nmi_handle_intr() by evaluating panic_on_nmi
in one place, namely nmi_call_kdb(). This allows to remove do_panic
argument from the functions, and to remove i386/amd64 duplication of
the variable and sysctl definitions. Note that now NMI causes
panic(9) instead of trap_fatal() reporting and then panic(9),
consistently for NMIs delivered while CPU operated in ring 0 and 3.
Sponsored by: The FreeBSD Foundation
MFC after: 2 weeks
On several Intel chipsets, diagnostic NMIs sent from BMC or NMIs
reporting hardware errors are broadcasted to all CPUs.
When kernel is configured to enter kdb on NMI, the outcome is
problematic, because each CPU tries to enter kdb. All CPUs are
executing NMI handlers, which set the latches disabling the nested NMI
delivery; this means that stop_cpus_hard(), used by kdb_enter() to
stop other cpus by broadcasting IPI_STOP_HARD NMI, cannot work. One
indication of this is the harmless but annoying diagnostic "timeout
stopping cpus".
Much more harming behaviour is that because all CPUs try to enter kdb,
and if ddb is used as debugger, all CPUs issue prompt on console and
race for the input, not to mention the simultaneous use of the ddb
shared state.
Try to fix this by introducing a pseudo-lock for simultaneous attempts
to handle NMIs. If one core happens to enter NMI trap handler, other
cores see it and simulate reception of the IPI_STOP_HARD. More,
generic_stop_cpus() avoids sending IPI_STOP_HARD and avoids waiting
for the acknowledgement, relying on the nmi handler on other cores
suspending and then restarting the CPU.
Since it is impossible to detect at runtime whether some stray NMI is
broadcast or unicast, add a knob for administrator (really developer)
to configure debugging NMI handling mode.
The updated patch was debugged with the help from Andrey Gapon (avg)
and discussed with him.
Sponsored by: The FreeBSD Foundation
MFC after: 2 weeks
Differential revision: https://reviews.freebsd.org/D8249
All I/O APIC pins are masked when an I/O APIC is first probed. The
APIC enumerator (MP Table or MADT) then parses its associated tables to
configure individual pins to set custom delivery modes or alternate
routing (e.g. routing IRQ 0 to intpin 2). Pins for regular interrupt
pins are left masked until the first interrupt is assigned. However,
pins with unusual settings (e.g. NMI or SMI) are never assigned an
interrupt and thus never re-programmed. The I/O APIC code used to
reprogram all interrupt pins during registration but this was lost in
r151979.
In theory, this is mostly a no-op as the ACPI APIC table does not
include a way to enumerate NMI or SMI pins for the I/O APIC, so only
systems using an MP Table would be affected.
Reported by: avg
MFC after: 1 month
Reduce the cost of TLB invalidation on x86 by using per-CPU completion flags
Reduce contention during TLB invalidation operations by using a per-CPU
completion flag, rather than a single atomically-updated variable.
On a Westmere system (2 sockets x 4 cores x 1 threads), dtrace measurements
show that smp_tlb_shootdown is about 50% faster with this patch; observations
with VTune show that the percentage of time spent in invlrng_single_page on an
interrupt (actually doing invalidation, rather than synchronization) increases
from 31% with the old mechanism to 71% with the new one. (Running a basic file
server workload.)
Submitted by: Anton Rang <rang at acm.org>
Reviewed by: cem (earlier version)
Sponsored by: Dell EMC Isilon
Differential Revision: https://reviews.freebsd.org/D8041
Reduce contention during TLB invalidation operations by using a per-CPU
completion flag, rather than a single atomically-updated variable.
On a Westmere system (2 sockets x 4 cores x 1 threads), dtrace measurements
show that smp_tlb_shootdown is about 50% faster with this patch; observations
with VTune show that the percentage of time spent in invlrng_single_page on an
interrupt (actually doing invalidation, rather than synchronization) increases
from 31% with the old mechanism to 71% with the new one. (Running a basic file
server workload.)
Submitted by: Anton Rang <rang at acm.org>
Reviewed by: cem (earlier version), kib
Sponsored by: Dell EMC Isilon
Differential Revision: https://reviews.freebsd.org/D8041
On Hyper-V:
- Stick to the first cpu for all I/O APIC pins.
- And don't allow destination cpu changes.
Reviewed by: jhb
MFC after: 1 week
Sponsored by: Microsoft
Differential Revision: https://reviews.freebsd.org/D7949
If BIOS performed hand-off to OS with BSP LAPIC in the x2APIC mode,
system usually consumes such configuration without a notice, since
x2APIC is turned on by OS if possible (nop). But if BIOS
simultaneously requested OS to not use x2APIC, code assumption that
that xAPIC is active breaks.
In my opinion, we cannot safely turn off x2APIC if control is passed
in this mode. Make madt.c ignore user or BIOS requests to turn x2APIC
off, and do not check the x2APIC black list. Just trust the config
and try to continue, giving a warning in dmesg.
Reported and tested by: Slawa Olhovchenkov <slw@zxy.spb.ru> (previous version)
Diagnosed by and discussed with: avg
Sponsored by: The FreeBSD Foundation
MFC after: 2 weeks
i386-only section, and fix a comment about the amd64 kernel trapframe
not having stackregs.
tf_rsp doesn't need decoding on amd64, but had an old clone of i386
code to do this in 1 place, and since the amd64 kernel trapframe does
have stackregs, the result was an off-by-16 error for %rsp in an error
message.
The 'cpu' and 'cpu_class' variables were always set to the same value
on amd64 and are legacy holdovers from i386. Remove them entirely on
amd64.
Reviewed by: imp, kib (older version)
Differential Revision: https://reviews.freebsd.org/D7888
SEL_UPL and sometimes PSL_VM. This is just a style change on amd64,
but on i386 it fixes 1 unimportant place where the PSL_VM check was
missing and starts fixing 1 important place where the PSL_VM check
had a logic error.
Fix logic errors in treating vm86 bioscall mode as kernel mode. The
main place checked all the necessary flags, but put the necessary
parentheses for the PSL_VM and PCB_VM86CALL checks in the wrong
place. The broken case is only reached if a vm86 bioscall uses a
%cs which is nonzero mod 4, but that is unusual -- most bios calls
start with %cs = 0xc000 or 0xf000 and rarely change it. Another
place was missing the check for PCB_VM86CALL, but was only reachable
if there are bugs virtualizing PSL_I.
Add a macro TF_HAS_STACKREGS() and use this instead of converting
open-coded checks of SEL_UPL, etc. to TRAPF_USERMODE() when we only
care about whether the frame has stack registers. This fixes 3
places in my recent fix for register variables in vm86 mode where I
messed up the PSL_VM check and cleans up other places.
- Certain pic_assign_cpu, e.g. msi_assign_cpu can have quite a long
call chain. For msi_assign_cpu, mutex makes complex PCI bridge
drivers more tricky, e.g. sleep can note be called, etc, it will
be pretty tricky for upcoming Hyper-V PCI bridge driver for PCI
pass-through.
- It is not used on any hot code path nor non-sleepable context, so
sx should have the same effect as mutex.
PIC list is still protected by mutex to keep suspend/resume work.
Discussed with: jhb
Reviewed by: jhb
MFC after: 3 weeks
Sponsored by: Microsoft
Differential Revision: https://reviews.freebsd.org/D7784
Move msix_disable_migration under #ifdef SMP since it doesn't make sense
for !SMP kernels.
PR: 212014
Reported by: Glyn Grinstead <glyn@grinstead.org>
MFC after: 3 days
Right now, userspace (fast) gettimeofday(2) on x86 only works for
RDTSC. For older machines, like Core2, where RDTSC is not C2/C3
invariant, and which fall to HPET hardware, this means that the call
has both the penalty of the syscall and of the uncached hw behind the
QPI or PCIe connection to the sought bridge. Nothing can me done
against the access latency, but the syscall overhead can be removed.
System already provides mappable /dev/hpetX devices, which gives
straight access to the HPET registers page.
Add yet another algorithm to the x86 'vdso' timehands. Libc is updated
to handle both RDTSC and HPET. For HPET, the index of the hpet device
to mmap is passed from kernel to userspace, index might be changed and
libc invalidates its mapping as needed.
Remove cpu_fill_vdso_timehands() KPI, instead require that
timecounters which can be used from userspace, to provide
tc_fill_vdso_timehands{,32}() methods. Merge i386 and amd64
libc/<arch>/sys/__vdso_gettc.c into one source file in the new
libc/x86/sys location. __vdso_gettc() internal interface is changed
to move timecounter algorithm detection into the MD code.
Measurements show that RDTSC even with the syscall overhead is faster
than userspace HPET access. But still, userspace HPET is three-four
times faster than syscall HPET on several Core2 and SandyBridge
machines.
Tested by: Howard Su <howard0su@gmail.com>
Sponsored by: The FreeBSD Foundation
MFC after: 1 month
Differential revision: https://reviews.freebsd.org/D7473
Uses of commas instead of a semicolons can easily go undetected. The comma
can serve as a statement separator but this shouldn't be abused when
statements are meant to be standalone.
Detected with devel/coccinelle following a hint from DragonFlyBSD.
MFC after: 1 month
- Add constants for the fields in the root-entry table address register,
namely the root type type (RTT) and root table address (RTA) mask.
- Add macros for the bitmask of the domain ID field in the second word
of context table entries as well as a helper macro (DMAR_CTX2_GET_DID)
to extract the domain ID from a context table entry.
Reviewed by: kib
MFC after: 1 month
Sponsored by: Chelsio Communications
difference between files.
For pc98, put x86/mp_x86.c into the same place as used by i386 file list.
Fix typo in comment.
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
This was only needed for Xen, and a better way to deal with this issue has
been found, so this commit can be reverted.
Sponsored by: Citrix Systems R&D
MFC after: 5 days
Reviewed by: kib
Differential revision: https://reviews.freebsd.org/D7363
Event channel handlers cannot be removed during resume because there might
be an interrupt thread running on a CPU currently blocked in the
cpususpend_handler, which prevents the call to intr_remove_handler from
finishing and completely freezes the system during resume. r291022 tried to
fix this by allowing recursion in intr_remove_handler, but that's clearly
not enough.
Instead don't remove the handlers at the interrupt resume phase, and let
each driver remove the handler by itself during resume. In order to do this,
change the opaque event channel handler cookie to use the global interrupt
vector instead of the event channel port. The event channel port cannot be
used because after resume all event channels are reset, and the port numbers
can change.
Sponsored by: Citrix Systems R&D
MFC after: 5 days
Since these pages are allocated from a narrow range of memory, this makes
the allocation more likely to succeed.
Suggested by: kib
Reviewed by: jkim, kib
MFC after: 2 months
Differential Revision: https://reviews.freebsd.org/D7154
Set vm_guest to a new enum value (VM_GUEST_KVM) when kvm is detected and use
vm_guest in conditionals testing for KVM.
Also, fix a conditional checking if we're running in a VM which caught only
the generic VM case, but not more specific VMs (KVM, VMWare, etc.). (Spotted
by: vangyzen).
Differential revision: https://reviews.freebsd.org/D7172
Sponsored by: Dell Inc.
Approved by: kib (mentor), vangyzen (mentor)
Reviewed by: alc
MFC after: 4 weeks
If the hypervisor version is smaller than 4.6.0. Xen commits 74fd00 and
70a3cb are required on the hypervisor side for this to be fixed, and those
are only included in 4.6.0, so stay on the safe side and disable MSI-X
interrupt migration on anything older than 4.6.0.
It should not cause major performance degradation unless a lot of MSI-X
interrupts are allocated.
Sponsored by: Citrix Systems R&D
MFC after: 3 days
Reviewed by: jhb
Differential revision: https://reviews.freebsd.org/D7148
The new 'machdep.disable_msix_migration' tunable can be set to 1 to
disable migration of MSI-X interrupts.
Xen versions prior to 4.6.0 do not properly handle updates to MSI-X
table entries after the initial write. In particular, the operation
to unmask a table entry after updating it during migration is not
propagated to the "real" table for passthrough devices causing the
interrupt to remain masked. At least some systems in EC2 are
affected by this bug when using SRIOV. The tunable can be set in
loader.conf as a workaround.
Submitted by: Jeremiah Lott <jlott@averesystems.com> (original patch)
Approved by: re (marius)
MFC after: 2 weeks
Differential Revision: https://reviews.freebsd.org/D6947
If the allocation attempt fails, we may otherwise VM_WAIT after a failed
attempt to reclaim contiguous memory in the requested range. After r297466,
this results in the thread going to sleep, causing a hang during boot.
Reviewed by: jkim, kib
Approved by: re (gjb)
Sponsored by: EMC / Isilon Storage Division
Differential Revision: https://reviews.freebsd.org/D6945
Reduce number of iterations used for calibrating ICR read loop. The
new number of iteration still gives the same ICR latency as before,
tested on Intel SandyBridge and Haswell machines, and on AMD. But it
significantly reduces the unneeded pause on boot in some VMs, from ~10
secs to less then 1 sec. It was reported to occur in bhyve on AMD
host.
Reported and tested by: avg
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
The existing version depends on register_t and uintptr_t, which are only
available when including headers such as <sys/types.h>. As this macro is
used by <sys/socket.h>, for example, it should be written in such a way
that it doesn't depend on those types.
In r227474, this header file was changed to define SIG_ATOMIC_{MIN,MAX}
in terms of LONG_{MIN,MAX}. Unlike all of the definitions in this header
file, LONG_{MIN,MAX} is provided by <limits.h>. Remove the dependency on
<limits.h> by using __LONG_{MIN,MAX} instead and including
<machine/_limits.h>.
This change is needed to make SIG_ATOMIC_{MIN,MAX} work without
including any other header files.
This header uses __INT_MIN and __INT_MAX, which is provided by
<machine/_limits.h>. This is needed to make <stdint.h>'s WCHAR_MIN and
WCHAR_MAX work without including other headers as well.
switching between LAPIC modes is not supported, and there is no need
to wait for IPI ack in x2APIC mode. So the calibrated delay is only
needed for !x2APIC.
This saves around a second of boot time on the real hardware for
x2APIC.
Sponsored by: The FreeBSD Foundation
Add implementations of bus_map/unmap_resource to the x86 nexus driver.
Change bus_activate/deactivate_resource to honor RF_UNMAPPED and to
use bus_map/unmap_resource to create/destroy the implicit mapping when
RF_UNMAPPED is not set.
Reviewed by: cem
Differential Revision: https://reviews.freebsd.org/D5237
Currently, Application Processors (non-boot CPUs) are started by
MD code at SI_SUB_CPU, but they are kept waiting in a "pen" until
SI_SUB_SMP at which point they are released to run kernel threads.
SI_SUB_SMP is one of the last SYSINIT levels, so APs don't enter
the scheduler and start running threads until fairly late in the
boot.
This change moves SI_SUB_SMP up to just before software interrupt
threads are created allowing the APs to start executing kernel
threads much sooner (before any devices are probed). This allows
several initialization routines that need to perform initialization
on all CPUs to now perform that initialization in one step rather
than having to defer the AP initialization to a second SYSINIT run
at SI_SUB_SMP. It also permits all CPUs to be available for
handling interrupts before any devices are probed.
This last feature fixes a problem on with interrupt vector exhaustion.
Specifically, in the old model all device interrupts were routed
onto the boot CPU during boot. Later after the APs were released at
SI_SUB_SMP, interrupts were redistributed across all CPUs.
However, several drivers for multiqueue hardware allocate N interrupts
per CPU in the system. In a system with many CPUs, just a few drivers
doing this could exhaust the available pool of interrupt vectors on
the boot CPU as each driver was allocating N * mp_ncpu vectors on the
boot CPU. Now, drivers will allocate interrupts on their desired CPUs
during boot meaning that only N interrupts are allocated from the boot
CPU instead of N * mp_ncpu.
Some other bits of code can also be simplified as smp_started is
now true much earlier and will now always be true for these bits of
code. This removes the need to treat the single-CPU boot environment
as a special case.
As a transition aid, the new behavior is available under a new kernel
option (EARLY_AP_STARTUP). This will allow the option to be turned off
if need be during initial testing. I plan to enable this on x86 by
default in a followup commit in the next few days and to have all
platforms moved over before 11.0. Once the transition is complete,
the option will be removed along with the !EARLY_AP_STARTUP code.
These changes have only been tested on x86. Other platform maintainers
are encouraged to port their architectures over as well. The main
things to check for are any uses of smp_started in MD code that can be
simplified and SI_SUB_SMP SYSINITs in MD code that can be removed in
the EARLY_AP_STARTUP case (e.g. the interrupt shuffling).
PR: kern/199321
Reviewed by: markj, gnn, kib
Sponsored by: Netflix
if specific CPU features are not present.
Some simulation environments, e.g. gem5, have been found to require more
TLB management from the kernel in certain setups. It is currently unclear why.
Turning on the workaround_erratum383 seems to help and make problems (panics)
go away.
Given this is a fairly uncommon environment so far, allowing the workaround
to be manually enabled from loader in order to make debugging and comparing
traces easier, but also to allow gem5 run FreeBSD in X86 timing mode, seems
to be the least intrusive option for now until the issue if fully understood.
Sponsored by: DARPA/AFRL
Reviewed by: kib, alc (earlier)
MFC after: 2 weeks
Differential Revision: https://reviews.freebsd.org/D6206
