When a DMA request using bounce pages completes, a swi is triggered to
schedule pending DMA requests using the just-freed bounce pages. For
a long time this bus_dma swi has been tied to a "virtual memory" swi
(swi_vm). However, all of the swi_vm implementations are the same and
consist of checking a flag (busdma_swi_pending) which is always true
and if set calling busdma_swi. I suspect this dates back to the
pre-SMPng days and that the intention was for swi_vm to serve as a
mux. However, in the current scheme there's no need for the mux.
Instead, remove swi_vm and vm_ih. Each bus_dma implementation that
uses bounce pages is responsible for creating its own swi (busdma_ih)
which it now schedules directly. This swi invokes busdma_swi directly
removing the need for busdma_swi_pending.
One consequence is that the swi now works on RISC-V which had previously
failed to invoke busdma_swi from swi_vm.
Reviewed by: imp, kib
Sponsored by: Netflix
Differential Revision: https://reviews.freebsd.org/D33447
The header exports the following:
- Definition of struct tcb.
- Helpers to get/set the tcb for the current thread.
- TLS_TCB_SIZE (size of TCB)
- TLS_TCB_ALIGN (alignment of TCB)
- TLS_VARIANT_I or TLS_VARIANT_II
- TLS_DTV_OFFSET (bias of pointers in dtv[])
- TLS_TP_OFFSET (bias of "thread pointer" relative to TCB)
Note that TLS_TP_OFFSET does not account for if the unbiased thread
pointer points to the start of the TCB (arm and x86) or the end of the
TCB (MIPS, PowerPC, and RISC-V).
Note also that for amd64, the struct tcb does not include the unused
tcb_spare field included in the current structure in libthr. libthr
does not use this field, and the existing calls in libc and rtld that
allocate a TCB for amd64 assume it is the size of 3 Elf_Addr's (and
thus do not allocate room for tcb_spare).
A <sys/_tls_variant_i.h> header is used by architectures using
Variant I TLS which uses a common struct tcb.
Reviewed by: kib (older version of x86/tls.h), jrtc27
Sponsored by: The University of Cambridge, Google Inc.
Differential Revision: https://reviews.freebsd.org/D33351
With various firmware files used by graphics and wireless drivers
we are exceeding the current 32 character module name (file path
in kldxref) length.
In order to overcome this issue bump it to the maximum path length
for the next version.
To be able to MFC provide backward compat support for another version
of the struct as the offsets for the second half change due to the
array size increase.
MAXMODNAME being defined to MAXPATHLEN needs param.h to be
included first. With only 7 modules (or LinuxKPI module.h) not
doing that adjust them rather than including param.h in module.h [1].
Reported by: Greg V (greg unrelenting.technology)
Sponsored by: The FreeBSD Foundation
Suggested by: imp [1]
MFC after: 10 days
Reviewed by: imp (and others to different level)
Differential Revision: https://reviews.freebsd.org/D32383
- Enable local MCEs on capable Intel CPUs. It delivers exceptions
only to the affected CPU instead of global broadcast, requiring a lot
of synchronization between CPUs. AMD always deliver MCEs locally.
- Make MCE handler process only uncorrected errors, while CMCI and
polling only corrected. It reduces synchronization problems between
them and is explicitly recommended by the documentation.
- Add minimal support for uncorrected software recoverable errors
on Intel CPUs. It allows to avoid kernel panics in case uncorrected
errors do not affect current operation, like ones found during scrub
or write. Such errors are only logged, postponing the panic until
the corrupted data will actually be needed (that may never happen).
- Reduce polling period from 1 hour to 5 minutes.
MFC after: 2 weeks
Previously it was not allowed on fast taskqueues. It was fixed in
4730a8972b. This should make no functional change, just a bit
cleaner and efficient code.
MFC after: 1 week
This ensures that LAPIC calibration is done using the correct tsc_freq
value, i.e., the one associated with the TSC timecounter. It does mean
though that TSC calibration cannot use sbinuptime() to read the
reference timecounter, as timehands are not yet set up.
Reviewed by: kib, jhb
MFC after: 2 weeks
Sponsored by: The FreeBSD Foundation
Differential Revision: https://reviews.freebsd.org/D33209
This ensures that we have a good reference timecounter for performing
calibration.
Change lapic_setup to avoid configuring the timer when booting, and move
calibration and initial configuration to a new lapic routine,
lapic_calibrate_timer. This calibration will be initiated from
cpu_initclocks(), before an eventtimer is selected.
Reviewed by: kib, jhb
MFC after: 2 weeks
Sponsored by: The FreeBSD Foundation
Differential Revision: https://reviews.freebsd.org/D33206
The headers were mostly identical on amd64 and i386.
No functional change intended.
Reviewed by: cperciva, mav, imp, kib, jhb
MFC after: 2 weeks
Sponsored by: The FreeBSD Foundation
Differential Revision: https://reviews.freebsd.org/D33205
It stopped being used in 3c256f5395, when trap() was reorganized to
have separate switch statements for user and kernel traps. Remove the
two leftover references and the flag itself.
Reviewed by: kib
MFC after: 3 days
Differential Revision: https://reviews.freebsd.org/D33253
The minidump code is written assuming that certain global state will not
change, and rightly so, since it executes from a kernel debugger
context. In order to support taking minidumps of a live system, we
should allow copies of relevant global state that is likely to change to
be passed as parameters to the minidumpsys() function.
This patch does the work of parameterizing this function, by adding a
struct minidumpstate argument. For now, this struct allows for copies of
the kernel message buffer, and the bitset that tracks which pages should
be dumped (vm_page_dump). Follow-up changes will actually make use of
these arguments.
Notably, dump_avail[] does not need a snapshot, since it is not expected
to change after system initialization.
The existing minidumpsys() definitions are renamed, and a thin MI
wrapper is added to kern_dump.c, which handles the construction of
the state struct. Thus, calling minidumpsys() remains as simple as
before.
Reviewed by: kib, markj, jhb
Sponsored by: Juniper Networks, Inc.
Sponsored by: Klara, Inc.
MFC after: 2 weeks
Differential Revision: https://reviews.freebsd.org/D31989
There is no universal way to find the TSC frequency. Newer Intel CPUs
may report it via CPUID leaves 0x15 and 0x16. Sometimes it can be
obtained from the PLATFORM_INFO MSR as well, though we never use that.
On older platforms we derive the frequency using a DELAY(1000000) call,
which uses the 8254 PIT. On some newer platforms the 8254 is apparently
non-functional, leading to bogus calibration results. On such platforms
the TSC frequency must be available from CPUID. It is also possible to
disable calibration with a tunable, in which case we try to parse the
brand string if the TSC freq is not available from CPUID.
CPUID 0x15 provides an authoritative TSC frequency value, but even that
is not always available on new Intel platforms. CPUID 0x16 provides the
specified processor base frequency, which is not the same as the TSC
frequency. Empirically, it is close enough for early boot, but too far
off for timekeeping: on a Comet Lake NUC, CPUID 0x16 yields 1600MHz but
the TSC frequency is rougly 1608MHz, leading to frequent clock stepping
when NTP is in use.
Thus we have a situation where we cannot calibrate using the PIT and
cannot obtain a precise frequency from CPUID (or MSRs). This change
seeks to address that by using the CPUID 0x16 value during early boot
and refining the calibration later once ACPI-based timecounters are
available. TSC frequency detection is thus split into two phases:
Early phase:
- On Intel platforms, query CPUID 0x15 and 0x16 and use that value
initially if available.
- Otherwise, get an estimate using the PIT, reducing the delay loop to
100ms from 1s.
- Continue to register the TSC as the CPU ticks provider early, even
though the frequency may be off. Otherwise any code executed during
boot that uses cpu_ticks() (e.g., context switching) gets tripped up
when the ticks provider changes.
Later phase:
- In SI_SUB_CLOCKS, once the timehands are initialized, load the current
TSC and timecounter (sbinuptime()) values at the beginning and end of
a 1s interval and use the timecounter frequency (typically from
kvmclock, HPET or the ACPI PM timer) to estimate the TSC frequency.
- Update the TSC timecounter, global tsc_freq and CPU ticker with the
new frequency and finally register the TSC as a timecounter.
Reviewed by: kib, jhb (previous version)
Discussed with: imp, cperciva
MFC after: 6 weeks
Sponsored by: The FreeBSD Foundation
Differential Revision: https://reviews.freebsd.org/D32512
We use pmap_invalidate_cpu_mask() to get the set of active CPUs. This
(32-byte) set is copied by value through multiple frames until we get to
smp_targeted_tlb_shootdown(), where it is copied yet again.
Avoid this copying by having smp_targeted_tlb_shootdown() make a local
copy of the active CPUs for the pmap, and drop the cpuset parameter,
simplifying callers. Also leverage the use of the non-destructive
CPU_FOREACH_ISSET to avoid unneeded copying within
smp_targeted_tlb_shootdown().
Reviewed by: alc, kib
Tested by: pho
MFC after: 1 month
Sponsored by: The FreeBSD Foundation
Differential Revision: https://reviews.freebsd.org/D32792
sched_throw() can no longer take a NULL thread, APs enter through
sched_ap_entry() instead. This completely removes branching in the
common case and cleans up both paths. No functional change intended.
Reviewed by: kib, markj
Differential Revision: https://reviews.freebsd.org/D32829
schedinit_ap() sets up an AP for a later call to sched_throw(NULL).
Currently, ULE sets up some pcpu bits and fixes the idlethread lock with
a call to sched_throw(NULL); this results in a window where curthread is
setup in platforms' init_secondary(), but it has the wrong td_lock.
Typical platform AP startup procedure looks something like:
- Setup curthread
- ... other stuff, including cpu_initclocks_ap()
- Signal smp_started
- sched_throw(NULL) to enter the scheduler
cpu_initclocks_ap() may have callouts to process (e.g., nvme) and
attempt to sched_add() for this AP, but this attempt fails because
of the noted violated assumption leading to locking heartburn in
sched_setpreempt().
Interrupts are still disabled until cpu_throw() so we're not really at
risk of being preempted -- just let the scheduler in on it a little
earlier as part of setting up curthread.
Reviewed by: alfredo, kib, markj
Triage help from: andrew, markj
Smoke-tested by: alfredo (ppc), kevans (arm64, x86), mhorne (arm)
Differential Revision: https://reviews.freebsd.org/D32797
Some BIOSes protect memory region they reside in by using DMAR to
prevent devices from doing any DMA transactions to that part of RAM.
AMI refers to this as "DMA Control Guarantee".
Disable the protection when address translation is enabled.
I stumbled upon this while investigation a failing coredump on a device
which has this feature enabled.
Sponsored by: Stormshield
Obtained from: Semihalf
Reviewed by: kib
Differential revision: https://reviews.freebsd.org/D32591
In some cases we might have to create DMAR context before the
corresponding device has been enumerated by the PCI bus.
In that case we get called with NULL dev, because of that trying
to reserve PCI regions causes a NULL pointer dereference in
pci_find_pcie_root_port.
Sponsored by: Stormshield
Obtained from: Semihalf
MFC after: 2 weeks
Reviewed by: kib, rlibby
Differential revision: https://reviews.freebsd.org/D32589
The last two drivers that required sppp are cp(4) and ce(4).
These devices are still produced and can be purchased
at Cronyx <http://cronyx.ru/hardware/wan.html>.
Since Roman Kurakin <rik@FreeBSD.org> has quit them, they no
longer support FreeBSD officially. Later they have dropped
support for Linux drivers to. As of mid-2020 they don't even
have a developer to maintain their Windows driver. However,
their support verbally told me that they could provide aid to
a FreeBSD developer with documentaion in case if there appears
a new customer for their devices.
These drivers have a feature to not use sppp(4) and create an
interface, but instead expose the device as netgraph(4) node.
Then, you can attach ng_ppp(4) with help of ports/net/mpd5 on
top of the node and get your synchronous PPP. Alternatively
you can attach ng_frame_relay(4) or ng_cisco(4) for HDLC.
Actually, last time I used cp(4) back in 2004, using netgraph(4)
instead of sppp(4) was already the right way to do.
Thus, remove the sppp(4) related part of the drivers and enable
by default the negraph(4) part. Further maintenance of these
drivers in the tree shouldn't be a big deal.
While doing that, remove some cruft and enable cp(4) compilation
on amd64. The ce(4) for some unknown reason marks its internal
DDK functions with __attribute__ fastcall, which most likely is
safe to remove, but without hardware I'm not going to do that, so
ce(4) remains i386-only.
Reviewed by: emaste, imp, donner
Differential Revision: https://reviews.freebsd.org/D32590
See also: https://reviews.freebsd.org/D23928
For some of them, used only when KTR or KMSAN are configured, apply
__unused attribute directly.
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
This implementation is faster and doesn't modify the cpuset, so it lets
us avoid some unnecessary copying as well. No functional change
intended.
This is a re-application of commit
9068f6ea69.
Reviewed by: cem, kib, jhb
MFC after: 2 weeks
Sponsored by: The FreeBSD Foundation
Differential Revision: https://reviews.freebsd.org/D32029
The default value for LAPIC registers page physical address
is usually right. Having this value available early makes
pmap_force_invalidate_cache_range(), used on non-self-snoop machines,
avoid flushing LAPIC range for early calls.
Reviewed by: alc, markj
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
Differential revision: https://reviews.freebsd.org/D32318
The implementation of the progress bar is simple, but duplicated for
most minidump implementations. Extract the common bits to kern_dump.c.
Ensure that the bar is reset with each subsequent dump; this was only
done on some platforms previously.
Reviewed by: markj
MFC after: 2 weeks
Sponsored by: Juniper Networks, Inc.
Sponsored by: Klara, Inc.
Differential Revision: https://reviews.freebsd.org/D31885
malloc_domainset_aligned() requires that alignment is less than
page size. Fall back to other allocation methods, most likely
kmem_alloc_contig(), when malloc_aligned() cannot fullfill the driver
request.
Reported by: Loic F <loic.f@hardenedbsd.org>
Reviewed by: markj
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
Differential revision: https://reviews.freebsd.org/D32127
Before this device unit number match was coincidental and broke if I
disabled some CPU device(s). Aside of cosmetics, for some drivers
(may be considered broken) it caused talking to wrong CPUs.
Depending on hardware, NUMA nodes may match last level caches, or
they may be above them (AMD Zen 2/3) or below (Intel Xeon w/ SNC).
This information is provided by ACPI instead of CPUID, and it is
provided for each CPU individually instead of mask widths, but
this code should be able to properly handle all the above cases.
This change should immediately allow idle stealing in sched_ule(4)
to prefer load from NUMA-local CPUs to remote ones when the node
does not match LLC. Later we may think of how to better handle it
on sched_pickcpu() side.
MFC after: 1 month
This reverts commit 0f6829488e.
Also it changes the type of md_usr_fpu_save struct mdthread member
to void *, which is what uncovered this trouble. Now the save area
is untyped, but since it is hidden behind accessors, it is not too
significant. Since apparently there are consumers affected outside
the tree, this hack is better than one from the reverted revision.
PR: 258678
Reported by: cy
Reviewed by: cy, kevans, markj
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
Differential revision: https://reviews.freebsd.org/D32060
when compiling in amd64 kernel environment with -m32. This is a temporal
workaround for some future proper (but unclear) fix.
Reviewed by: jhb, markj
Tested by: pho
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
Differential revision: https://reviews.freebsd.org/D31954
This implementation is faster and doesn't modify the cpuset, so it lets
us avoid some unnecessary copying as well. No functional change
intended.
Reviewed by: cem, kib, jhb
MFC after: 2 weeks
Sponsored by: The FreeBSD Foundation
Differential Revision: https://reviews.freebsd.org/D32029
The file as is is the maze of #ifdef passages, all slightly different.
Divorcing i386 and amd64 version actually makes changing the code
easier, also no changes for i386 are planned.
Reviewed by: markj
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
Differential revision: https://reviews.freebsd.org/D31931
This is required since kernel text might be physically located
anywhere below 4G.
PR: 258432
Reported by: Taku YAMAMOTO <taku@tackymt.homeip.net>
Reviewed by: markj
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
Differential revision: https://reviews.freebsd.org/D31916
Do not use tab between type and variable name in local declarations.
Reviewed by: markj
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
Differential revision: https://reviews.freebsd.org/D31916
Move the common kernel function signatures from machine/reg.h to a new
sys/reg.h. This is in preperation for adding PT_GETREGSET to ptrace(2).
Reviewed by: imp, markj
Sponsored by: DARPA, AFRL (original work)
Sponsored by: The FreeBSD Foundation
Differential Revision: https://reviews.freebsd.org/D19830
Clang 13 produces the following warning for hammer_time_xen():
sys/x86/xen/pv.c:183:19: error: the pointer incremented by -2147483648 refers past the last possible element for an array in 64-bit address space containing 256-bit (32-byte) elements (max possible 576460752303423488 elements) [-Werror,-Warray-bounds]
(vm_paddr_t)start_info->modlist_paddr + KERNBASE;
^ ~~~~~~~~
sys/xen/interface/arch-x86/hvm/start_info.h:131:5: note: array 'modlist_paddr' declared here
uint64_t modlist_paddr; /* Physical address of an array of */
^
This is because the expression first casts start_info->modlist_paddr to
struct hvm_modlist_entry * (via vmpaddr_t), and *then* adds KERNBASE,
which is then interpreted as KERNBASE * sizeof(struct
hvm_modlist_entry).
Instead, parenthesize the addition to get the intended result, and cast
it to struct hvm_modlist_entry * afterwards. Also remove the cast to
vmpaddr_t since it is not necessary.
Reviewed by: royger
MFC after: 3 days
Differential Revision: https://reviews.freebsd.org/D31711
Add vDSO support for timekeeping devices that support the KVM/XEN
paravirtual clock API.
Also, expose, in the userspace-accessible '<machine/pvclock.h>',
definitions that will be needed by 'libc' to support
'VDSO_TH_ALGO_X86_PVCLK'.
Sponsored by: Juniper Networks, Inc.
Sponsored by: Klara, Inc.
Reviewed by: kib
Differential Revision: https://reviews.freebsd.org/D31418
Add support for the KVM paravirtual clock device.
Sponsored by: Juniper Networks, Inc.
Sponsored by: Klara, Inc.
Reviewed by: kib
Differential Revision: https://reviews.freebsd.org/D29733
Consolidate more hypervisor-agnostic functionality behind a new 'struct
pvclock' API.
This should also make it easier to subsequently add hypervisor-agnostic
vDSO timekeeping support.
Also, perform some clean-up:
- Remove 'pvclock_get_last_cycles()'; do not allow external access
to 'pvclock_last_systime' since this is not necessary.
- Consolidate/simplify wall and system time reading codepaths.
- Ensure correct ordering within wall and system time reading
codepaths via 'atomic(9)' and 'rdtsc_ordered()' rather than via
'rmb()'.
- Remove some extra newlines.
Sponsored by: Juniper Networks, Inc.
Sponsored by: Klara, Inc.
Reviewed by: kib
Differential Revision: https://reviews.freebsd.org/D31418
Add a variant of 'rdtsc()' that performs the ordered version of 'rdtsc'
appropriate for the invoking x86 variant.
Also, expose the 'lfence'-ed and 'mfence'-ed 'rdtsc()' variants needed
by 'rdtsc_ordered()' for general use.
Sponsored by: Juniper Networks, Inc.
Sponsored by: Klara, Inc.
Reviewed by: kib
Differential Revision: https://reviews.freebsd.org/D31416
At least Linux x86 ABI's does not use carry bit and expects that the dx register
is preserved. For this add a new sv_set_fork_retval hook and call it from cpu_fork().
Add a short comment about touching dx in x86_set_fork_retval(), for more details
see phab comments from kib@ and imp@.
Reviewed by: kib
Differential revision: https://reviews.freebsd.org/D31472
MFC after: 2 weeks
Sanitizer instrumentation of course cannot automatically update shadow
state when devices write to host memory. KMSAN thus hooks into busdma,
both to update shadow state after a device write, and to verify that the
kernel does not publish uninitalized bytes to devices.
To implement this, when KMSAN is configured, each dmamap embeds a memory
descriptor describing the region currently loaded into the map.
bus_dmamap_sync() uses the operation flags to determine whether to
validate the loaded region or to mark it as initialized in the shadow
map.
Note that in cases where the amount of data written is less than the
buffer size, the entire buffer is marked initialized even when it is
not. For example, if a NIC writes a 128B packet into a 2KB buffer, the
entire buffer will be marked initialized, but subsequent accesses past
the first 128 bytes are likely caused by bugs.
Reviewed by: kib
Sponsored by: The FreeBSD Foundation
Differential Revision: https://reviews.freebsd.org/D31338
Use this flag to indicate that busdma should allocate a map structure
even no bouncing is required to satisfy the tag's constraints. This
will be used for KMSAN.
Also fix a memory leak that can occur if the kernel fails to allocate
bounce pages in bounce_bus_dmamap_create().
Reviewed by: kib
Sponsored by: The FreeBSD Foundation
Differential Revision: https://reviews.freebsd.org/D31338
Interrupt and exception handlers must call kmsan_intr_enter() prior to
calling any C code. This is because the KMSAN runtime maintains some
TLS in order to track initialization state of function parameters and
return values across function calls. Then, to ensure that this state is
kept consistent in the face of asynchronous kernel-mode excpeptions, the
runtime uses a stack of TLS blocks, and kmsan_intr_enter() and
kmsan_intr_leave() push and pop that stack, respectively.
Use these functions in amd64 interrupt and exception handlers. Note
that handlers for user->kernel transitions need not be annotated.
Also ensure that trap frames pushed by the CPU and by handlers are
marked as initialized before they are used.
Reviewed by: kib
Sponsored by: The FreeBSD Foundation
Differential Revision: https://reviews.freebsd.org/D31467
These ones were unambiguous cases where the Foundation was the only
listed copyright holder (in the associated license block).
Sponsored by: The FreeBSD Foundation
KASAN and KCSAN implement interceptors for various primitive operations
that are not instrumented by the compiler. KMSAN requires them as well.
Rather than adding new cases for each sanitizer which requires
interceptors, implement the following protocol:
- When interceptor definitions are required, define
SAN_NEEDS_INTERCEPTORS and SANITIZER_INTERCEPTOR_PREFIX.
- In headers that declare functions which need to be intercepted by a
sanitizer runtime, use SANITIZER_INTERCEPTOR_PREFIX to provide
declarations.
- When SAN_RUNTIME is defined, do not redefine the names of intercepted
functions. This is typically the case in files which implement
sanitizer runtimes but is also needed in, for example, files which
define ifunc selectors for intercepted operations.
MFC after: 2 weeks
Sponsored by: The FreeBSD Foundation
There is no reason now why do we need to allocate trampoline page very
early in the boot process. The only requirement for the page is that
it is below 1M to be usable by the real mode during init. This can be
handled by vm_alloc_contig() when we do the startup.
Also assert that startup trampoline fits into single page. In principle
we can do multi-page allocation if needed, but it is not.
Move the alloc_ap_trampoline() function and the boot_address variable to
i386/mp_machdep.c. Keep existing mechanism of early alloc on i386.
Reviewed by: markj
Sponsored by: The FreeBSD Foundation
MFC after: 2 weeks
Differential revision: https://reviews.freebsd.org/D31343
Before this change my dual-Xeon(R) Gold 6242R always reported 3 levels
or topology (root, package/L3 and core/L2). But with SMT disabled
core/L2 matches thread, so additional topology level only causes more
traversal work. With this change SMT case is reported same as before,
while non-SMT is reported with only 2 much more simple levels.
MFC after: 2 weeks
xen_vector_callback_enabled is x86 specific and availability of
per-cpu event channel delivery differs on other architectures.
Introduce a new helper to check if there's support for per-cpu event
channel injection.
Submitted by: Elliott Mitchell <ehem+freebsd@m5p.com>
Reviewed by: royger
Differential Revision: https://reviews.freebsd.org/D29402
While x86 only register PV shutdown handler for PV guests. ARM guests
are always using HVM and requires the PV shutdown handler.
Submitted by: Elliott Mitchell <ehem+freebsd@m5p.com>
Reviewed by: royger
Differential Revision: https://reviews.freebsd.org/D29406
ARM guest is considered as HVM in Freebsd but they only support PV disk
(no emulation available).
Submitted by: Elliott Mitchell <ehem+freebsd@m5p.com>
Reviewed by: royger
Differential Revision: https://reviews.freebsd.org/D29403
ARM guest is considered as HVM but it only supports PV nics (no
emulation available).
Submitted by: Elliott Mitchell <ehem+freebsd@m5p.com>
Reviewed by: royger
Differential Revision: https://reviews.freebsd.org/D29405
Several of x86 enable/disable functions depend upon the xen*domain()
functions. As such the xen*domain() functions need to be declared
before machine/xen-os.h.
Officially declare direct inclusion of machine/xen/xen-os.h verboten as
such will break these functions/macros. Remove one such soon to be
broken inclusion.
Reviewed by: royger
Differential Revision: https://reviews.freebsd.org/D29811
Functions tend to get renamed and unless the developer is careful
often debugging messages are missed. As such using func is far
superior. Replace several instances of hard-coded function names.
Reviewed by: royger
Differential revision: https://reviews.freebsd.org/D29499
Since xen_intr_handle_t is meant to be an opaque handle and the only
use is retrieving the associated struct xenisrc *, directly use it as
the opaque handler.
Also add a wrapper function for converting the other direction. If some
other value becomes appropriate in the future, these two functions will
be the only spots needing modification.
Reviewed by: mhorne, royger
Differential Revision: https://reviews.freebsd.org/D29500
The requirements for pages shared with Xen/other VMs may vary from
architecture to architecture. As such create a macro which various
architectures can use.
Remove a use of PAT_WRITE_BACK in xenstore.c. This is a x86-ism which
shouldn't have been present in a common area.
Original idea: Julien Grall <julien@xen.org>, 2014-01-14 06:44:08
Approach suggested by: royger
Reviewed by: royger, mhorne
Differential Revision: https://reviews.freebsd.org/D29351
Minor changes are necessary to make this processor-independent, but
moving the file out of x86 and into common is the first step (so
others don't add /more/ x86-isms).
Submitted by: Elliott Mitchell <ehem+freebsd@m5p.com>
Reviewed by: royger
Differential Revision: https://reviews.freebsd.org/D29042
Stop using temporal page table with 1:1 mapping of low 1G populated over
the whole VA. Use 1:1 mapping of low 4G temporarily installed in the
normal kernel page table.
The features are:
- now there is one less step for startup asm to perform
- the startup code still needs to be at lower 1G because CPU starts in
real mode. But everything else can be located anywhere in low 4G
because it is accessed by non-paged 32bit protected mode. Note that
kernel page table root page is at low 4G, as well as the kernel itself.
- the page table pages can be allocated by normal allocator, there is
no need to carve them from the phys_avail segments at very early time.
The allocation of the page for startup code still requires some magic.
Pages are freed after APs are ignited.
- la57 startup for APs is less tricky, we directly load the final page
table and do not need to tweak the paging mode.
Reviewed by: markj
Tested by: pho
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
Differential revision: https://reviews.freebsd.org/D31121
The vDSO (virtual dynamic shared object) is a small shared library that the
kernel maps R/O into the address space of all Linux processes on image
activation. The vDSO is a fully formed ELF image, shared by all processes
with the same ABI, has no process private data.
The primary purpose of the vDSO:
- non-executable stack, signal trampolines not copied to the stack;
- signal trampolines unwind, mandatory for the NPTL;
- to avoid contex-switch overhead frequently used system calls can be
implemented in the vDSO: for now gettimeofday, clock_gettime.
The first two have been implemented, so add the implementation of system
calls.
System calls implemenation based on a native timekeeping code with some
limitations:
- ifunc can't be used, as vDSO r/o mapped to the process VA and rtld
can't relocate symbols;
- reading HPET memory is not implemented for now (TODO).
In case on any error vDSO system calls fallback to the kernel system
calls. For unimplemented vDSO system calls added prototypes which call
corresponding kernel system call.
Tested by: trasz (arm64)
Differential revision: https://reviews.freebsd.org/D30900
MFC after: 2 weeks
Many of these typedefs are the same across all architectures or can
be set based on an architecture-independent compiler-provided macro
(e.g. __SIZEOF_SIZE_T__). These macros have been available since GCC 4.6
and Clang sometime before 3.0 (godbolt.org does not have any older clang
versions installed).
I originally considered using the compiler-provided `__FOO_TYPE__` directly.
However, in order to do so we have to check that those match the previous
typedef exactly (not just that they have the same size) since any change
would be an ABI break. For example, changing `long` to `long long` results
in different C++ name mangling. Additionally, Clang and GCC disagree on
the underlying type for some of (u)int*_fast_t types, so this change
only moves the definitions that are identical across all architectures
and does not touch those types.
This de-deduplication will allow us to have a smaller diff downstream in
CheriBSD: we only have to only change the (u)intptr_t definition in
sys/_types.h in CheriBSD instead of having to change machine/_types.h for
all CHERI-enabled architectures (currently RISC-V, AArch64 and MIPS).
Reviewed By: imp, kib
Differential Revision: https://reviews.freebsd.org/D29895
From the PR:
Almost always, my Samsung RF511 laptop could not boot with
x2APIC enabled in the kernel. It froze during SMP initialization,
shortly after "ACPI APIC Table: <SECCSD LH43STAR>" was printed
to the console. When the kernel is instructed not to use x2APIC,
the system boots correctly.
PR: 256389
Submitted by: David Sebek <dasebek@gmail.com>
Reviewed by: markj
MFC after: 1 week
Differential revision: https://reviews.freebsd.org/D30624
to prepare for one more addition
Reviewed by: markj
Tested by: David Sebek <dasebek@gmail.com>
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
Differential revision: https://reviews.freebsd.org/D30624
setidt_disp is the offset of the ISR trampoline relative to the address
of the routines in exception.s, so uintptr_t is not quite right.
Also remove a bogus declaration I added in commit 18f55c67f7, it is not
required after all.
Reported by: jrtc27
Reviewed by: jrtc27, kib
MFC after: 1 week
Sponsored by: The FreeBSD Foundation
Differential Revision: https://reviews.freebsd.org/D30590
The loop which checks to see if "dynamic" IDT entries are allocated
needs to compare with the trampoline address of the reserved ISR.
Otherwise it will never succeed.
Reported by: Harry Schmalzbauer <freebsd@omnilan.de>
Tested by: Harry Schmalzbauer <freebsd@omnilan.de>
Reviewed by: kib
MFC after: 1 week
Sponsored by: The FreeBSD Foundation
Differential Revision: https://reviews.freebsd.org/D30576
The AP startup extern variable declarations are not longer needed,
since PVHv2 uses the native AP startup path using the lapic. Remove
the declaration and make the variables static to mp_machdep.c
Sponsored by: Citrix Systems R&D
PVHv1 was officially removed from Xen in 4.9, so just axe the related
code from FreeBSD.
Note FreeBSD supports PVHv2, which is the replacement for PVHv1.
Sponsored by: Citrix Systems R&D
Reviewed by: kib, Elliott Mitchell
Differential Revision: https://reviews.freebsd.org/D30228
When unwinding the stack, we may encounter a stack frame in a poisoned
region of the stack, triggering a false positive.
Reviewed by: andrew, kib
Sponsored by: The FreeBSD Foundation
Differential Revision: https://reviews.freebsd.org/D30126
When sending an IPI, if a previous IPI is still pending delivery,
native_lapic_ipi_vectored() waits for the previous IPI to be sent.
We've seen a few inexplicable panics with the current timeout of 50 ms.
Increase the timeout to 1 second and make it tunable.
No hardware specification mentions a timeout in this case; I checked
the Intel SDM, Intel MP spec, and Intel x2APIC spec. Linux and illumos
wait forever. In Linux, see __default_send_IPI_shortcut() in
arch/x86/kernel/apic/ipi.c. In illumos, see apic_send_ipi() in
usr/src/uts/i86pc/io/pcplusmp/apic_common.c. However, misbehaving hardware
could hang the system if we wait forever.
Reviewed by: mav kib
MFC after: 1 week
Sponsored by: Dell EMC Isilon
Differential Revision: https://reviews.freebsd.org/D29942
- Initialize KASAN before executing SYSINITs.
- Add a GENERIC-KASAN kernel config, akin to GENERIC-KCSAN.
- Increase the kernel stack size if KASAN is enabled. Some of the
ASAN instrumentation increases stack usage and it's enough to
trigger stack overflows in ZFS.
- Mark the trapframe as valid in interrupt handlers if it is
assigned to td_intr_frame. Otherwise, an interrupt in a function
which creates a poisoned alloca region can trigger false positives.
MFC after: 2 weeks
Sponsored by: The FreeBSD Foundation
Differential Revision: https://reviews.freebsd.org/D29455
Move the code from exec_setregs() to reset debug registers state on exec,
to the x86_clear_dbregs() helper
Reviewed by: jhb
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
Differential revision: https://reviews.freebsd.org/D29687
Handle the 'z' and 'Z' remote packets for manipulating hardware
watchpoints.
This could be expanded quite easily to support hardware or software
breakpoints as well.
https://sourceware.org/gdb/onlinedocs/gdb/Packets.html
Reviewed by: cem, markj
MFC after: 3 weeks
Sponsored by: NetApp, Inc.
Sponsored by: Klara, Inc.
NetApp PR: 51
Differential Revision: https://reviews.freebsd.org/D29173
Add wrappers around the dbreg interface that can be consumed by MI
kernel debugger code. The dbreg functions themselves are updated to
return error codes, not just -1. dbreg_set_watchpoint() is extended to
accept access bits as an argument.
Reviewed by: jhb, kib, markj
MFC after: 3 weeks
Sponsored by: NetApp, Inc.
Sponsored by: Klara, Inc.
Differential Revision: https://reviews.freebsd.org/D29155
This change serves two purposes.
First, we take advantage of the compiler provided endian definitions to
eliminate some long-standing duplication between the different versions
of this header. __BYTE_ORDER__ has been defined since GCC 4.6, so there
is no need to rely on platform defaults or e.g. __MIPSEB__ to determine
endianness. A new common sub-header is added, but there should be no
changes to the visibility of these definitions.
Second, this eliminates the hand-rolled __bswapNN() routines, again in
favor of the compiler builtins. This was done already for x86 in
e6ff6154d2. The benefit here is that we no longer have to maintain our
own implementations on each arch, and can instead rely on the compiler
to emit appropriate instructions or libcalls, as available. This should
result in equivalent or better code generation. Notably 32-bit arm will
start using the `rev` instruction for these routines, which is available
on armv6+.
PR: 236920
Reviewed by: arichardson, imp
Tested by: bdragon (BE powerpc)
MFC after: 3 weeks
Differential Revision: https://reviews.freebsd.org/D29012
Make it easy to define interceptors for new sanitizer runtimes, rather
than assuming KCSAN. Lay a bit of groundwork for KASAN and KMSAN.
When a sanitizer is compiled in, atomic(9) and bus_space(9) definitions
in atomic_san.h are used by default instead of the inline
implementations in the platform's atomic.h. These definitions are
implemented in the sanitizer runtime, which includes
machine/{atomic,bus}.h with SAN_RUNTIME defined to pull in the actual
implementations.
No functional change intended.
MFC after: 1 month
Sponsored by: The FreeBSD Foundation
This is a prerequisite to using these functions outside of ddb, but also
provides some cleanup and minor refactoring. This code is almost
entirely duplicated between the two implementations, the only
significant difference being the lack of dbreg synchronization on i386.
Cleanups are:
- demote some internal functions to static
- use the constant NDBREGS instead of a '4' literal
- remove K&R definitions
- some added comments
Reviewed by: kib, jhb
Sponsored by: NetApp, Inc.
Sponsored by: Klara, Inc.
MFC after: 1 week
Differential Revision: https://reviews.freebsd.org/D29153
This is x86-only and so should not be in the common area.
Submitted by: Elliott Mitchell <ehem+freebsd@m5p.com>
Reviewed by: royger
Differential revision: https://reviews.freebsd.org/D29040
Misbehavior has been observed with TSC under VirtualBox, where threads
doing small sleeps (~1 second) may miss their wake up and hang around
in a sleep state indefinitely. Switching back to ACPI-fast decidedly
fixes it, so stop using TSC on VirtualBox at least for the time being.
This partially reverts 84eaf2ccc6, applying it only to VirtualBox and
increasing the quality to 0. Negative qualities can never be chosen and
cannot be chosen with the tunable recently added. If we do not have a
timecounter with a higher quality than 0, then TSC does at least leave
the system mostly usable.
PR: 253087
Reviewed by: emaste, kib
MFC after: 3 days
Differential Revision: https://reviews.freebsd.org/D29132
Other kernel sanitizers (KMSAN, KASAN) require interceptors as well, so
put these in a more generic place as a step towards importing the other
sanitizers.
No functional change intended.
MFC after: 1 week
Sponsored by: The FreeBSD Foundation
Differential Revision: https://reviews.freebsd.org/D29103
Add it to the x86 GENERIC and MINIMAL kernels
Sponsored by: Ampere Computing LLC
Submitted by: Klara Inc.
Reviewed by: rpokala
Differential Revision: https://reviews.freebsd.org/D28738
Allow setting the bootmethod variable from the Xen PVH entry point, in
order to be able to correctly set the underlying firmware mode when
booted as a dom0.
Move the bootmethod variable to be defined in x86/cpu_machdep.c
instead so it can be shared by both i386 and amd64.
Sponsored by: Citrix Systems R&D
Reviewed by: kib
Differential revision: https://reviews.freebsd.org/D28619
A BIOS bug may apparently cause the BSP to report that it does not
implement CMCI, with some APs reporting that they do. In this scenario,
avoid a NULL pointer dereference that occurs in cmci_monitor() because
cmc_state was not allocated by the BSP.
PR: 253272
Reported by: asomers, mmacy
Reviewed by: kib (previous version)
MFC after: 1 week
There's a currently ad-hoc protocol to hand off the FreeBSD kernel
payload between the loader and the kernel itself when Xen is in the
middle of the picture. Such protocol wasn't very resilient to changes
to the loader itself, because it relied on moving metadata around to
package it using a certain layout. This has proven to be fragile, so
replace it with a more robust version.
The new protocol requires using a xen_header structure that will be
used to pass data between the FreeBSD loader and the FreeBSD kernel
when booting in dom0 mode. At the moment the only data conveyed is the
offset of the start of the module metadata relative to the start of the
module itself.
This is a slightly disruptive change since it also requires a change
to the kernel which is contained in this patch. In order to update
with this change the kernel must be updated before updating the
loader, as described in the handbook. Note this is only required when
booting a FreeBSD/Xen dom0. This change doesn't affect the normal
FreeBSD boot protocol.
This fixes booting FreeBSD/Xen in dom0 mode after
3630506b9d.
Sponsored by: Citrix Systems R&D
MFC after: 3 days
Reviewed by: tsoome
Differential Revision: https://reviews.freebsd.org/D28411
This stops busdma bounce making assumptions about alignment of malloc(9)
results, which are no longer true.
Also add assert that the result of malloc_aligned() fits into single
page, which is the assumption of the code.
Reported by: dim
Reviewed by: andrew, jah, markj
Tested by: pho
MFC after: 1 week
Sponsored by: The FreeBSD Foundation
Differential Revision: https://reviews.freebsd.org/D28147
This reverts commit 8f54940f01.
The free needs to be called on the address returned by malloc,
not the realigned address.
Noted by: andrew
Sponsored by: The FreeBSD Foundation
i386 codegen insists on preloading tc_priv into register on i386, and
this register cannot be %eax because RDTSCP instruction clobbers it
before it is used.
Reported and tested by: dim
MFC after: 6 days
Sponsored by: The FreeBSD Foundation
Use it in preference of Xfenced RDTSC if RDTSCP is supported. It is
recommended by both Intel and AMD. But, on AMD Zens and newer use
LFENCE, as recommended by AMD [*]. In particular, this means that now
AMD CPUs use more appropriate fence instead of too harsh MFENCe.
Add comment explaining the intent of the selection logic.
Reported by: gallatin [*]
Reviewed by: gallatin, markj
Tested by: gallatin, pho
MFC after: 1 week
Sponsored by: The FreeBSD Foundation
Differential Revision: https://reviews.freebsd.org/D27986
I suspect that virtualization techniques improved from the time when we
have to effectively disable TSC use in VM. For instance, it was reported
(complained) in https://github.com/JuliaLang/julia/issues/38877 that
FreeBSD is groundlessly slow on AWS with some loads.
Remove the check and start watching for complaints.
Reviewed by: emaste, grehan
Discussed with: cperciva
Sponsored by: The FreeBSD Foundation
Differential Revision: https://reviews.freebsd.org/D27629
PCI memory address space is shared between memory-mapped devices (MMIO)
and host memory (which may be remapped by an IOMMU). Device accesses to
an address within a memory aperture in a PCIe root port will be treated
as peer-to-peer and not forwarded to an IOMMU. To avoid this, reserve
the address space of the root port's memory apertures in the address
space used by the IOMMU for remapping.
Reviewed by: kib, tychon
Discussed with: Anton Rang <rang@acm.org>
Tested by: tychon
Sponsored by: Dell EMC Isilon
Differential Revision: https://reviews.freebsd.org/D27503
Add an explicit thread fence release before returning from
bus_dmamap_sync. This should be a no-op in practice, but makes
explicit that all ordinary stores will be completed before subsequent
reads/writes to ordinary device memory. On x86, normal memory ordering
is strong enough to generally guarantee this. The fence keeps the
optimizer (likely LTO) from reordering other calls around this.
The other architectures already have calls, as appropriate, that
are equivalent.
Note: On x86, there is one exception to this rule. If you've mapped
memory as write combining, then you will need to add a sfence or
similar. Normally, though, busdma doesn't operate on such memory, and
drivers that do already cope appropriately.
Reviewed by: kib@, gallatin@, chuck@, mav@
Differential Revision: https://reviews.freebsd.org/D27448
This is useful for stack unwinders which need to avoid out-of-bounds
reads of a kernel stack which can trigger kernel faults.
Reviewed by: kib, markj
Obtained from: CheriBSD
Sponsored by: DARPA
Differential Revision: https://reviews.freebsd.org/D27356
Implement vt_vbefb to support Vesa Bios Extensions (VBE) framebuffer with VT.
vt_vbefb is built based on vt_efifb and is assuming similar data for
initialization, use MODINFOMD_VBE_FB to identify the structure vbe_fb
in kernel metadata.
struct vbe_fb, is populated by boot loader, and is passed to kernel via
metadata payload.
Differential Revision: https://reviews.freebsd.org/D27373
Actually check the wrmsr_safe() return value when setting autonomous
HWP for package.
PR: 245582
Differential Revision: https://reviews.freebsd.org/D24744
This is needed on arm64 for the interface between iommu framework
and iommu controller drivers.
Reviewed by: kib
Sponsored by: Innovate DSbD
Differential Revision: https://reviews.freebsd.org/D27229
platforms.
This allows to not depend on the IOMMU macro in AHCI driver.
Requested by: kib
Suggested by: andrew
Reviewed by: kib
Sponsored by: Innovate DSbD
Differential Revision: https://reviews.freebsd.org/D26887
From Linux sources and several datasheets I looked at, it seems that
the workaround is only needed on families 0xf and 0x10. For instance,
Ryzens do not implement the accessed MSR at all, it is documented as
reserved. Also, hypervisors should not allow guest to put CPU into
idle state, so activate workaround only when on bare hardware.
While there, style the code:
move MSR defines to specialreg.h
move identification to initcpu.c
Reported by: whu
Reviewed by: avg
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
Differential revision: https://reviews.freebsd.org/D26470
Move dump_avail[] extern declaration and inlines into a new header
vm/vm_dumpset.h. This fixes default gcc build for mips.
Reviewed by: alc, scottph
Tested by: kevans (previous version)
Sponsored by: The FreeBSD Foundation
Differential revision: https://reviews.freebsd.org/D26741
The prototype was added with the creation of kern_shutdown.c in r17658,
but it appears to have never been implemented. Remove it now.
Reviewed by: cem, kib
Differential Revision: https://reviews.freebsd.org/D26702
Dynamically created OIDs automatically get this flag set.
Reviewed by: jhb
MFC after: 1 week
Sponsored by: iXsystems, Inc.
Differential Revision: https://reviews.freebsd.org/D26561
This is mostly needed for a common arm64/amd64 iommu code.
Reviewed by: kib
Sponsored by: DARPA, AFRL
Differential Revision: https://reviews.freebsd.org/D26587
The NOTES files have a bunch of hint lines that are removed when
generating LINT. However, we can achieve the same effect by prepending
each of the lines with 'envvar' so the NOTES files become standard
config(8) files. No functional changes as the sed script to generate
the LINT files filters these either way.
Suggested by: kevans
These definitions were repeated by all architectures, with small
variations. Consolidate the common definitons in machine
independent code and use bitset(9) macros for manipulation. Many
opportunities for deduplication remain in the machine dependent
minidump logic. The only intended functional change is increasing
the bit index type to vm_pindex_t, allowing the indexing of pages
with address of 8 TiB and greater.
Reviewed by: kib, markj
Approved by: scottl (implicit)
MFC after: 1 week
Sponsored by: Ampere Computing, Inc.
Differential Revision: https://reviews.freebsd.org/D26129
One problem with the bus_space_read_N() and bus_space_write_N() family of
functions is that they provide no protection against exceptions which can
occur when no physical hardware or device responds to the read or write
cycles. In such a situation, the system typically would panic due to a
kernel-mode bus error. The bus_space_peek_N() and bus_space_poke_N() family
of functions provide a mechanism to handle these exceptions gracefully
without the risk of crashing the system.
Typical example is access to PCI(e) configuration space in bus enumeration
function on badly implemented PCI(e) root complexes (RK3399 or Neoverse
N1 N1SDP and/or access to PCI(e) register when device is in deep sleep state.
This commit adds a real implementation for arm64 only. The remaining
architectures have bus_space_peek()/bus_space_poke() emulated by using
bus_space_read()/bus_space_write() (without exception handling).
MFC after: 1 month
Reviewed by: kib
Differential Revision: https://reviews.freebsd.org/D25371
that can be extended, but also ensure compile-time type checking. Refactor
common code out of arch-specific implementations. Move the mpr and mps
drivers to this new API. The template type remains visible to the consumer
so that it can be allocated on the stack, but should be considered opaque.
For configurations without x2APIC support (guests, older hardware), the global
LAPIC MMIO mapping will trigger false-positive KCSan reports as it will appear
that multiple CPUs are concurrently reading and writing the same address.
This isn't actually true, as the underlying physical access will be performed
on the local CPU's APIC. Additionally, because LAPIC access can happen during
event timer configuration, the resulting KCSan printf can produce a panic due
to attempted recursion on event timer resources.
Add a __nosanitizethread preprocessor define to prevent the compiler from
inserting TSan hooks, and apply it to the x86 LAPIC accessors.
PR: 249149
Reported by: gbe
Reviewed by: andrew, kib
Tested by: gbe
Differential Revision: https://reviews.freebsd.org/D26354
It could be used in various IOMMU platforms, not only DMAR.
Reviewed by: kib
Sponsored by: DARPA, AFRL
Differential Revision: https://reviews.freebsd.org/D26373
We can switch into long mode directly with LA57 enabled.
Sponsored by: The FreeBSD Foundation
Differential revision: https://reviews.freebsd.org/D25273
so we don't ifdef for every arch in busdma_iommu.c;
o No need to include specialreg.h for x86, remove it.
Requested by: andrew
Reviewed by: kib
Sponsored by: DARPA/AFRL
Differential Revision: https://reviews.freebsd.org/D25957
These functions were introduced before UMA started ensuring that freed
memory gets placed in domain-local caches. They no longer serve any
purpose since UMA now provides their functionality by default. Remove
them to simplyify the kernel memory allocator interfaces a bit.
Reviewed by: cem, kib
Sponsored by: The FreeBSD Foundation
Differential Revision: https://reviews.freebsd.org/D25937
so x86 can support Intel DMAR and AMD IOMMU simultaneously.
Reviewed by: kib
Sponsored by: DARPA/AFRL
Differential Revision: https://reviews.freebsd.org/D25894
APEI allows platform to report different kinds of errors to OS in several
ways. We've found that Supermicro X10/X11 motherboards report PCIe errors
appearing on hot-unplug via this interface using NMI. Without respective
driver it ended up in kernel panic without any additional information.
This driver introduces support for the APEI Generic Hardware Error Source
reporting via NMI, SCI or polling. It decodes the reported errors and
either pass them to pci(4) for processing or just logs otherwise. Errors
marked as fatal still end up in kernel panic, but some more informative.
When somebody get to native PCIe AER support implementation both of the
reporting mechanisms should get common error recovery code. Since in our
case errors happen when the device is already gone, there is nothing to
recover, so the code just clears the error statuses, practically ignoring
the otherwise destructive NMIs in nicer way.
MFC after: 2 weeks
Relnotes: yes
Sponsored by: iXsystems, Inc.
For purposes of handling hardware error reported via NMIs I need a way to
escape NMI context, being too restrictive to do something significant.
To do it this change introduces new swi_sched() flag SWI_FROMNMI, making
it careful about used KPIs. On platforms allowing IPI sending from NMI
context (x86 for now) it immediately wakes clk_intr_event via new IPI_SWI,
otherwise it works just like SWI_DELAY. To handle the delayed SWIs this
patch calls clk_intr_event on every hardclock() tick.
MFC after: 2 weeks
Sponsored by: iXsystems, Inc.
Differential Revision: https://reviews.freebsd.org/D25754
from Intel DMAR support, so it can be used on other IOMMU systems.
Reviewed by: kib
Sponsored by: DARPA/AFRL
Differential Revision: https://reviews.freebsd.org/D25743
It allows safe IPI sending to current CPU from NMI context.
Unlike other ipi_*() functions this waits for delivery to leave LAPIC in
a state safe for interrupted code.
MFC after: 2 weeks
Sponsored by: iXsystems, Inc.
Sending IPI to self or all CPUs does not require write into upper part of
the ICR, prone to races. Previously the code disabled interrupts, but it
was not enough for NMIs. Instead of that when possible write only lower
part of the register, or use special SELF IPI register in x2APIC mode.
This also removes ICR reads used to preserve reserved bits on write.
It was there from the beginning, but I failed to find explanation why,
neither I see Linux doing it. Specification even tells that ICR content
may be lost in deep C-states, so if hardware does not bother to preserve
it, why should we?
MFC after: 2 weeks
Sponsored by: iXsystems, Inc.
pmc_cpuid was uninitialized for most AMD processor families. We can still
populate this string for unimplemented families.
Also added a CPUID_TO_STEPPING macro and converted existing code to use it.
Reviewed by: mav
MFC after: 2 weeks
Sponsored by: iXsystems, Inc.
Differential Revision: https://reviews.freebsd.org/D25673
Stop using smp_ipi_mtx to protect global shootdown state, and
move/multiply the global state into pcpu. Now each CPU can initiate
shootdown IPI independently from other CPUs. Initiator enters
critical section, then fills its local PCPU shootdown info
(pc_smp_tlb_XXX), then clears scoreboard generation at location (cpu,
my_cpuid) for each target cpu. After that IPI is sent to all targets
which scan for zeroed scoreboard generation words. Upon finding such
word the shootdown data is read from corresponding cpu' pcpu, and
generation is set. Meantime initiator loops waiting for all zeroed
generations in scoreboard to update.
Initiator does not disable interrupts, which should allow
non-invalidation IPIs from deadlocking, it only needs to disable
preemption to pin itself to the instance of the pcpu smp_tlb data.
The generation is set before the actual invalidation is performed in
handler. It is safe because target CPU cannot return to userspace
before handler finishes. In principle only NMI can preempt the
handler, but NMI would see the kernel handler frame and not touch
not-invalidated user page table.
Handlers loop until they do not see zeroed scoreboard generations.
This, together with hardware keeping one pending IPI in LAPIC IRR
should prevent lost shootdowns.
Notes.
1. The code does protect writes to LAPIC ICR with exclusion. I believe
this is fine because we in fact do not send IPIs from interrupt
handlers. More for !x2APIC mode where ICR access for write requires
two registers write, we disable interrupts around it. If considered
incorrect, I can add per-cpu spinlock around ipi_send().
2. Scoreboard lines owned by given target CPU can be padded to the
cache line, to reduce ping-pong.
Reviewed by: markj (previous version)
Discussed with: alc
Tested by: pho
Sponsored by: The FreeBSD Foundation
MFC after: 3 weeks
Differential revision: https://reviews.freebsd.org/D25510
so it can be used on other IOMMU systems.
Provide MI iommu_unit, iommu_domain and iommu_ctx structs in sys/iommu.h;
use them as a first member of MD dmar_unit, dmar_domain and dmar_ctx.
Change the namespace in DMAR backend: use iommu_ prefix instead of dmar_.
Move some macroses and function prototypes to sys/iommu.h.
Reviewed by: kib
Sponsored by: DARPA, AFRL
Differential Revision: https://reviews.freebsd.org/D25574
when it has passed the synchronization test.
"Processor Programming Reference (PPR) for AMD Family 17h" states that
the TSC uses a common reference for all sockets, cores and threads.
MFC after: 1 month
Given that 64c/128t CPUs are currently available, and that many
devices (nvme, many NICs) desire to map 1 MSI-X vector per core,
or even 1 per-thread, it is becoming far easier to see MSI-X interrupt
setup fail due to msi vector exhaustion, and devices fail to attach at
boot on large system.
This bump costs 12KB on amd64 (and 6KB on i386), which seems
worth the trade off for a better out of the box experience on
high end hardware.
Reviewed by: jhb
MFC after: 21 days
Sponsored by: Netflix
In particular, invalidation of the preloaded modules text to allow
execution from it was broken after D25188/r362031.
Reviewed by: markj
Reported by: delphij, dhw
Sponsored by: The FreeBSD Foundation
MFC after: 13 days
Right now code first flushes all local TLB entries that needs to be
flushed, then signals IPI to remote cores, and then waits for
acknowledgements while spinning idle. In the VMWare article 'Don’t
shoot down TLB shootdowns!' it was noted that the time spent spinning
is lost, and can be more usefully used doing local TLB invalidation.
We could use the same invalidation handler for local TLB as for
remote, but typically for pmap == curpmap we can use INVLPG for locals
instead of INVPCID on remotes, since we cannot control context
switches on them. Due to that, keep the local code and provide the
callbacks to be called from smp_targeted_tlb_shootdown() after IPIs
are fired but before spin wait starts.
Reviewed by: alc, cem, markj, Anton Rang <rang at acm.org>
Tested by: pho
Sponsored by: The FreeBSD Foundation
MFC after: 2 weeks
Differential revision: https://reviews.freebsd.org/D25188
When I did some bus_dma cleanup in r320528, I brought forward some sketchy
WITNESS checks from the prior x86 busdma wrappers, instead of recognizing
them as technical debt and just dropping them. Two of these were removed in
r346351 and r346851, but one remains in bounce_bus_dmamem_alloc(). This check
could be constrained to only apply in the BUS_DMA_NOWAIT case, but it's cleaner
to simply remove it and rely on the checks already present in the sleepable
allocation paths used by this function.
While here, remove another unnecessary witness check in bus_dma_tag_create
(the tag is always allocated with M_NOWAIT), and fix a couple of typos.
Reported by: cem
Reviewed by: kib, cem
MFC after: 1 week
Differential Revision: https://reviews.freebsd.org/D25107
On amd64 we already avoid using memory below 4GB in order to prevent
clashes with MMIO regions, but i386 was allowed to use any hole in
the physical memory map in order to map Xen pages.
Limit this to memory above the 1MB boundary on i386 in order to avoid
clashes with the MMIO holes in that area.
Sponsored by: Citrix Systems R&D
MFC after: 1 week
The flush is needed to prevent cross-process ret2spec, which is not handled
on kernel entry if IBPB is enabled but SMEP is present.
While there, add i386 RSB flush.
Reported by: Anthony Steinhauser <asteinhauser@google.com>
Reviewed by: markj, Anthony Steinhauser
Discussed with: philip
admbugs: 961
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
This function is responsible for setting pc_domain in each pcpu
structure. Call it from the main function that starts APs, rather than
a separate SYSINIT. This makes it easier to close the window where
UMA's per-CPU slab allocator may be called while pc_domain is
uninitialized. In particular, the allocator uses pc_domain to allocate
domain-local pages, so allocations before this point end up using domain
0 for everything.
Reviewed by: kib
MFC after: 1 week
Sponsored by: The FreeBSD Foundation
Differential Revision: https://reviews.freebsd.org/D24757
Release kernels have no KDB backends enabled, so they discard an NMI
if it is not due to a hardware failure. This includes NMIs from
IPMI BMCs and hypervisors.
Furthermore, the interaction of panic_on_nmi, kdb_on_nmi, and
debugger_on_panic is confusing.
Respond to all NMIs according to panic_on_nmi and debugger_on_panic.
Remove kdb_on_nmi. Expand the meaning of panic_on_nmi by making
it a bitfield. There are currently two bits: one for NMIs due to
hardware failure, and one for all others. Leave room for more.
If panic_on_nmi and debugger_on_panic are both true, don't actually panic,
but directly enter the debugger, to allow someone to leave the debugger
and [hopefully] resume normal execution.
Reviewed by: kib
MFC after: 2 weeks
Relnotes: yes: machdep.kdb_on_nmi is gone; machdep.panic_on_nmi changed
Sponsored by: Dell EMC Isilon
Differential Revision: https://reviews.freebsd.org/D24558
Stop attempting to use FADT legacy hardware flag, it is almost always
a lie.
Instead, unless user explicitly disabled the calibration, calibrate
against 8254 ISA clock. Then, obtain the rough value of the expected
TSC frequency from CPUID leafs 0x15/0x16 or even from the CPU
marketing name string. If calibration results look unbelievably bogus
comparing with CPUID leafs report, use CPUID one.
Intel does not recommend to use CPUID leaf 0x16 for the value of the
system time frequency, indeed the error there might be up to 1% which
e.g. makes ntpd give up. If ISA clock is present, we win, if not, we
get some frequency that allows the machine to boot without enormous
delay.
Next improvement would be to use HPET for re-calibration if we decided
that ISA clock gives bogus results, after HPETs are enumerated. This
is a much bigger change since we probably would need to re-evaluate
some constants depending on TSC frequency.
Reviewed by: emaste, jhb, scottl
Tested by: scottl
Sponsored by: The FreeBSD Foundation
MFC after: 2 weeks
Differential revision: https://reviews.freebsd.org/D24426
If EOI suppression is supported but reported ioapic version is so old
that it does not has EOI register (weird virtualization setup), fix
Intel trick of eoi-ing by flipping pin type (edge/level) to account
for the disabled pin.
Reported by: Juniper
Reviewed by: jhb
Sponsored by: The FreeBSD Foundation
MFC after: 2 weeks
Differential revision: https://reviews.freebsd.org/D23965
It does not serve any purpose now, the io apic id is not seen by
software, and some Intel documents claim that the register is
implemented for FUD reasons. More, renumbering seems to not work on
new Intel machines which actually have mismatched MADT and hw IDs.
On older machines where separate APIC bus existed, unique numbering of
all APICs was required for bus arbitration to work, but it is no
longer true (that machines were SMP from pre-Pentium IV era).
When matching PCIe IOAPIC device against MADT-enumerated IOAPICs,
compare io_apic_id from BAR against io_apic_id read from the
MADT-pointed register page.
Reviewed by: jhb
Tested by: flo (previous version), pho
MFC after: 2 weeks
Differential revision: https://reviews.freebsd.org/D23965
It seems that the newer Intel chipset did that, and Linux reads 8
bits. The only detail is that all seen datasheets, even under NDA,
claim that io apic id is 4 bits.
Submitted by: jeff
Reviewed by: jhb
Tested by: flo, pho
MFC after: 2 weeks
Differential revision: https://reviews.freebsd.org/D23965
r357614 added CTLFLAG_NEEDGIANT to make it easier to find nodes that are
still not MPSAFE (or already are but aren’t properly marked).
Use it in preparation for a general review of all nodes.
This is non-functional change that adds annotations to SYSCTL_NODE and
SYSCTL_PROC nodes using one of the soon-to-be-required flags.
Mark all obvious cases as MPSAFE. All entries that haven't been marked
as MPSAFE before are by default marked as NEEDGIANT
Approved by: kib (mentor, blanket)
Commented by: kib, gallatin, melifaro
Differential Revision: https://reviews.freebsd.org/D23718
When turning IBRS mitigation using sysctl, as opposed to loader tunable,
send IPI to tweak MSR on all cores. Right now code only performed MSR write
onr the CPU where sysctl was run.
Properly report hw.ibrs_active for IBRS_ALL. Split hw_ibrs_ibpb_active out
from ibrs_active, to keep the current semantic of guiding kernel entry and
exit handlers.
Reported and tested by: mav
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
This is SVM features word, the bit is defined in "PPR for AMD Family
17h Model 31h B0", document 55803 Rev 0.54.
N.B. GuesSpecCtl (no 't') is the spelling from the document.
Submitted by: Dmitry Luhtionov <dmitryluhtionov@gmail.com>
MFC after: 3 days