It is applied before it is possible for idle threads to execute on any
CPU, allowing to work around against some bugs.
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
Otherwise, under bootverbose, the lapic_enable_cmc() banner 'lapicX:
CMCI unmasked' is printed by several CPUs in parallel, causing garbled
output for the LAPIC dumps.
Reported by: royger
Reviewed by: jhb
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
Differential revision: https://reviews.freebsd.org/D15157
machine check banks must be only monitored by single CPU.
Noted and reviewed by: jhb
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
Differential revision: https://reviews.freebsd.org/D15157
We must ensure that accesses occur, they do not have any other
compiler-visible effects. Bruce found some situations where
optimization could remove an access, and provided a patch to use
volatile qualifier for the state variables. Since volatile behaviour
there is the compiler-specific interpretation of the keyword, use
relaxed atomics instead, which gives exactly the desired semantic.
Noted by and discussed with: bde
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
This sysctl allows a deeper dive into the sleep abyss comparing to
debug.acpi.suspend_bounce. When the new sysctl is set the system will
execute the suspend sequence up to the call to AcpiEnterSleepState().
That includes saving processor contexts and parking APs. Then, instead
of actually entering the sleep state, the BSP will call resumectx() to
emulate the wakeup. The APs should get restarted by the sequence of
Init and Startup IPIs that BSP sends to them.
MFC after: 8 days
x86 enforces an (arbitray) limit on the number of available MSI and
MSI-X interrupts to simplify code (in particular, interrupt_source[]
is statically sized). This means that an attempt to allocate an MSI
vector needs to fail if it would go beyond the limit, but the checks
for exceeding the limit had an off-by-one error. In the case of MSI-X
which allocates interrupts one at a time this meant that IRQ 768 kept
getting handed out multiple times for msix_alloc() instead of failing
because all MSI IRQs were in use.
Tested by: lidl
MFC after: 1 week
The change makes the user and kernel address spaces on i386
independent, giving each almost the full 4G of usable virtual addresses
except for one PDE at top used for trampoline and per-CPU trampoline
stacks, and system structures that must be always mapped, namely IDT,
GDT, common TSS and LDT, and process-private TSS and LDT if allocated.
By using 1:1 mapping for the kernel text and data, it appeared
possible to eliminate assembler part of the locore.S which bootstraps
initial page table and KPTmap. The code is rewritten in C and moved
into the pmap_cold(). The comment in vmparam.h explains the KVA
layout.
There is no PCID mechanism available in protected mode, so each
kernel/user switch forth and back completely flushes the TLB, except
for the trampoline PTD region. The TLB invalidations for userspace
becomes trivial, because IPI handlers switch page tables. On the other
hand, context switches no longer need to reload %cr3.
copyout(9) was rewritten to use vm_fault_quick_hold(). An issue for
new copyout(9) is compatibility with wiring user buffers around sysctl
handlers. This explains two kind of locks for copyout ptes and
accounting of the vslock() calls. The vm_fault_quick_hold() AKA slow
path, is only tried after the 'fast path' failed, which temporary
changes mapping to the userspace and copies the data to/from small
per-cpu buffer in the trampoline. If a page fault occurs during the
copy, it is short-circuit by exception.s to not even reach C code.
The change was motivated by the need to implement the Meltdown
mitigation, but instead of KPTI the full split is done. The i386
architecture already shows the sizing problems, in particular, it is
impossible to link clang and lld with debugging. I expect that the
issues due to the virtual address space limits would only exaggerate
and the split gives more liveness to the platform.
Tested by: pho
Discussed with: bde
Sponsored by: The FreeBSD Foundation
MFC after: 1 month
Differential revision: https://reviews.freebsd.org/D14633
opt_compat.h is mentioned in nearly 180 files. In-progress network
driver compabibility improvements may add over 100 more so this is
closer to "just about everywhere" than "only some files" per the
guidance in sys/conf/options.
Keep COMPAT_LINUX32 in opt_compat.h as it is confined to a subset of
sys/compat/linux/*.c. A fake _COMPAT_LINUX option ensure opt_compat.h
is created on all architectures.
Move COMPAT_LINUXKPI to opt_dontuse.h as it is only used to control the
set of compiled files.
Reviewed by: kib, cem, jhb, jtl
Sponsored by: DARPA, AFRL
Differential Revision: https://reviews.freebsd.org/D14941
Add the missing breaks in the for loops, in order to exit the loop
when a suitable entry is found.
Also switch amd64 native_start_all_aps to use PHYS_TO_DMAP in order to
find the virtual address of the boot_trampoline and the initial page
tables.
Reported and tested by: pho
Sponsored by: Citrix Systems R&D
So that it doesn't rely on physmap[1] containing an address below
1MiB. Instead scan the full physmap and search for a suitable address
to place the trampoline code (below 1MiB) and the initial memory pages
(below 4GiB).
Sponsored by: Citrix Systems R&D
Reviewed by: kib
Differential Revision: https://reviews.freebsd.org/D14878
x86/cpu_machdep.c now needs to include elan_mmcr.h when CPU_ELAN is set.
While here, also remove the now unneeded inclusion of isareg.h in i386
and amd64 vm_machdep.c.
Reported by: lwhsu
MFC after: 14 days
X-MFC with: r331878
When I moved these functions from i386 and amd64 to x86 I dropped their
prototype declarations (that were correct) and left only their definitions
that became incorrect.
Reported by: bde
MFC after: 15 days
X-MFC with: r331878
Because I didn't see any reason not too.
I've been making some changes to the code and couldn't help but notice
that the i386 and am64 code was nearly identical.
MFC after: 17 days
platforms. Original commit message as follows:
Only use CPUs in the domain the device is attached to for default
assignment. Device drivers are able to override the default assignment
if they bind directly. There are severe performance penalties for
handling interrupts on remote CPUs and this should only be done in
very controlled circumstances.
Reviewed by: jhb, kib
Tested by: pho
Sponsored by: Netflix, Dell/EMC Isilon
Differential Revision: https://reviews.freebsd.org/D14838
These have been supplanted by the MI signal information codes in
<sys/signal.h> since 7.0. The FPE_*_TRAP ones were deprecated even
earlier in 1999.
PR: 226579 (exp-run)
Reviewed by: kib
Differential Revision: https://reviews.freebsd.org/D14637
assignment. Device drivers are able to override the default assignment
if they bind directly. There are severe performance penalties for
handling interrupts on remote CPUs and this should only be done in
very controlled circumstances.
Reviewed by: jhb, kib
Tested by: pho (earlier version)
Sponsored by: Netflix, Dell/EMC Isilon
Differential Revision: https://reviews.freebsd.org/D14838
Originally KVM set %eax to 0 in the cpuid leaf 0x4000000 rather than
to the highest supported leaf in the hypervisor "branch". Detect this
case and fixup the %eax value so that the hypervisor is still
detected.
Reported by: jpaetzel
Reviewed by: kib
MFC after: 1 week
Differential Revision: https://reviews.freebsd.org/D14810
Or else disable the device. Note that the detection can be bypassed by
setting the hw.atrtc.enable option in the loader configuration file.
More information can be found on atrtc(4).
Sponsored by: Citrix Systems R&D
Reviewed by: ian
Differential revision: https://reviews.freebsd.org/D14399
from the i8254 driver when I created separate mutexes for each. The i8254
driver could be the active timecounter, leading to recursion during mutex
profiling, but the atrtc driver cannot be a timecounter, so it isn't needed.
un-function-like RTC_LOCK/UNLOCK macro usage into normal function calls.
Since there is no longer any need to handle register access from a debugger
context, those function calls can just be regular mutex lock/unlock calls.
Requested by: bde
command handler which provided much the same information. Removing the
possibility of accessing the hardware regs from the debugger context
paves the way for simplifying the locking code in the driver.
We don't support float in the boot loaders, so don't include
interfaces for float or double in systems headers. In addition, take
the unusual step of spiking double and float to prevent any more
accidental seepage.
Such items may be allocated in the I/O path used by the dumper,
potentially causing the dump to fail. Since there is some precedent
in the DMAR driver for avoiding this problem using _NODUMP, apply
this workaround to the zone as well.
Reported and tested by: mmacy
Reviewed by: kib
MFC after: 1 week
Differential Revision: https://reviews.freebsd.org/D14422
Do not use C constant suffixes. Bit values are small enough to not
require typing, despite they are used for 64bit MSR writes. The added
cast in hw_ibrs_recalculate() is redundand but I prefer to add it for
clarity.
Reported by: bde
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
It is coded according to the Intel document 336996-001, reading of the
patches posted on lkml, and some additional consultations with Intel.
For existing processors, you need a microcode update which adds IBRS
CPU features, and to manually enable it by setting the tunable/sysctl
hw.ibrs_disable to 0. Current status can be checked in sysctl
hw.ibrs_active. The mitigation might be inactive if the CPU feature
is not patched in, or if CPU reports that IBRS use is not required, by
IA32_ARCH_CAP_IBRS_ALL bit.
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
Differential revision: https://reviews.freebsd.org/D14029
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
