Pull performance event updates from Ingo Molnar:
- Add CPU-PMU support for Intel Sapphire Rapids CPUs
- Extend the perf ABI with PERF_SAMPLE_WEIGHT_STRUCT, to offer
two-parameter sampling event feedback. Not used yet, but is intended
for Golden Cove CPU-PMU, which can provide both the instruction
latency and the cache latency information for memory profiling
events.
- Remove experimental, default-disabled perfmon-v4 counter_freezing
support that could only be enabled via a boot option. The hardware is
hopelessly broken, we'd like to make sure nobody starts relying on
this, as it would only end in tears.
- Fix energy/power events on Intel SPR platforms
- Simplify the uprobes resume_execution() logic
- Misc smaller fixes.
* tag 'perf-core-2021-02-17' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
perf/x86/rapl: Fix psys-energy event on Intel SPR platform
perf/x86/rapl: Only check lower 32bits for RAPL energy counters
perf/x86/rapl: Add msr mask support
perf/x86/kvm: Add Cascade Lake Xeon steppings to isolation_ucodes[]
perf/x86/intel: Support CPUID 10.ECX to disable fixed counters
perf/x86/intel: Add perf core PMU support for Sapphire Rapids
perf/x86/intel: Filter unsupported Topdown metrics event
perf/x86/intel: Factor out intel_update_topdown_event()
perf/core: Add PERF_SAMPLE_WEIGHT_STRUCT
perf/intel: Remove Perfmon-v4 counter_freezing support
x86/perf: Use static_call for x86_pmu.guest_get_msrs
perf/x86/intel/uncore: With > 8 nodes, get pci bus die id from NUMA info
perf/x86/intel/uncore: Store the logical die id instead of the physical die id.
x86/kprobes: Do not decode opcode in resume_execution()
Pull scheduler updates from Ingo Molnar:
"Core scheduler updates:
- Add CONFIG_PREEMPT_DYNAMIC: this in its current form adds the
preempt=none/voluntary/full boot options (default: full), to allow
distros to build a PREEMPT kernel but fall back to close to
PREEMPT_VOLUNTARY (or PREEMPT_NONE) runtime scheduling behavior via
a boot time selection.
There's also the /debug/sched_debug switch to do this runtime.
This feature is implemented via runtime patching (a new variant of
static calls).
The scope of the runtime patching can be best reviewed by looking
at the sched_dynamic_update() function in kernel/sched/core.c.
( Note that the dynamic none/voluntary mode isn't 100% identical,
for example preempt-RCU is available in all cases, plus the
preempt count is maintained in all models, which has runtime
overhead even with the code patching. )
The PREEMPT_VOLUNTARY/PREEMPT_NONE models, used by the vast
majority of distributions, are supposed to be unaffected.
- Fix ignored rescheduling after rcu_eqs_enter(). This is a bug that
was found via rcutorture triggering a hang. The bug is that
rcu_idle_enter() may wake up a NOCB kthread, but this happens after
the last generic need_resched() check. Some cpuidle drivers fix it
by chance but many others don't.
In true 2020 fashion the original bug fix has grown into a 5-patch
scheduler/RCU fix series plus another 16 RCU patches to address the
underlying issue of missed preemption events. These are the initial
fixes that should fix current incarnations of the bug.
- Clean up rbtree usage in the scheduler, by providing & using the
following consistent set of rbtree APIs:
partial-order; less() based:
- rb_add(): add a new entry to the rbtree
- rb_add_cached(): like rb_add(), but for a rb_root_cached
total-order; cmp() based:
- rb_find(): find an entry in an rbtree
- rb_find_add(): find an entry, and add if not found
- rb_find_first(): find the first (leftmost) matching entry
- rb_next_match(): continue from rb_find_first()
- rb_for_each(): iterate a sub-tree using the previous two
- Improve the SMP/NUMA load-balancer: scan for an idle sibling in a
single pass. This is a 4-commit series where each commit improves
one aspect of the idle sibling scan logic.
- Improve the cpufreq cooling driver by getting the effective CPU
utilization metrics from the scheduler
- Improve the fair scheduler's active load-balancing logic by
reducing the number of active LB attempts & lengthen the
load-balancing interval. This improves stress-ng mmapfork
performance.
- Fix CFS's estimated utilization (util_est) calculation bug that can
result in too high utilization values
Misc updates & fixes:
- Fix the HRTICK reprogramming & optimization feature
- Fix SCHED_SOFTIRQ raising race & warning in the CPU offlining code
- Reduce dl_add_task_root_domain() overhead
- Fix uprobes refcount bug
- Process pending softirqs in flush_smp_call_function_from_idle()
- Clean up task priority related defines, remove *USER_*PRIO and
USER_PRIO()
- Simplify the sched_init_numa() deduplication sort
- Documentation updates
- Fix EAS bug in update_misfit_status(), which degraded the quality
of energy-balancing
- Smaller cleanups"
* tag 'sched-core-2021-02-17' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (51 commits)
sched,x86: Allow !PREEMPT_DYNAMIC
entry/kvm: Explicitly flush pending rcuog wakeup before last rescheduling point
entry: Explicitly flush pending rcuog wakeup before last rescheduling point
rcu/nocb: Trigger self-IPI on late deferred wake up before user resume
rcu/nocb: Perform deferred wake up before last idle's need_resched() check
rcu: Pull deferred rcuog wake up to rcu_eqs_enter() callers
sched/features: Distinguish between NORMAL and DEADLINE hrtick
sched/features: Fix hrtick reprogramming
sched/deadline: Reduce rq lock contention in dl_add_task_root_domain()
uprobes: (Re)add missing get_uprobe() in __find_uprobe()
smp: Process pending softirqs in flush_smp_call_function_from_idle()
sched: Harden PREEMPT_DYNAMIC
static_call: Allow module use without exposing static_call_key
sched: Add /debug/sched_preempt
preempt/dynamic: Support dynamic preempt with preempt= boot option
preempt/dynamic: Provide irqentry_exit_cond_resched() static call
preempt/dynamic: Provide preempt_schedule[_notrace]() static calls
preempt/dynamic: Provide cond_resched() and might_resched() static calls
preempt: Introduce CONFIG_PREEMPT_DYNAMIC
static_call: Provide DEFINE_STATIC_CALL_RET0()
...
Pull tlb gather updates from Ingo Molnar:
"Theses fix MM (soft-)dirty bit management in the procfs code & clean
up the TLB gather API"
* tag 'core-mm-2021-02-17' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/ldt: Use tlb_gather_mmu_fullmm() when freeing LDT page-tables
tlb: arch: Remove empty __tlb_remove_tlb_entry() stubs
tlb: mmu_gather: Remove start/end arguments from tlb_gather_mmu()
tlb: mmu_gather: Introduce tlb_gather_mmu_fullmm()
tlb: mmu_gather: Remove unused start/end arguments from tlb_finish_mmu()
mm: proc: Invalidate TLB after clearing soft-dirty page state
Pull oprofile and dcookies removal from Viresh Kumar:
"Remove oprofile and dcookies support
The 'oprofile' user-space tools don't use the kernel OPROFILE support
any more, and haven't in a long time. User-space has been converted to
the perf interfaces.
The dcookies stuff is only used by the oprofile code. Now that
oprofile's support is getting removed from the kernel, there is no
need for dcookies as well.
Remove kernel's old oprofile and dcookies support"
* tag 'oprofile-removal-5.12' of git://git.kernel.org/pub/scm/linux/kernel/git/vireshk/linux:
fs: Remove dcookies support
drivers: Remove CONFIG_OPROFILE support
arch: xtensa: Remove CONFIG_OPROFILE support
arch: x86: Remove CONFIG_OPROFILE support
arch: sparc: Remove CONFIG_OPROFILE support
arch: sh: Remove CONFIG_OPROFILE support
arch: s390: Remove CONFIG_OPROFILE support
arch: powerpc: Remove oprofile
arch: powerpc: Stop building and using oprofile
arch: parisc: Remove CONFIG_OPROFILE support
arch: mips: Remove CONFIG_OPROFILE support
arch: microblaze: Remove CONFIG_OPROFILE support
arch: ia64: Remove rest of perfmon support
arch: ia64: Remove CONFIG_OPROFILE support
arch: hexagon: Don't select HAVE_OPROFILE
arch: arc: Remove CONFIG_OPROFILE support
arch: arm: Remove CONFIG_OPROFILE support
arch: alpha: Remove CONFIG_OPROFILE support
Pull ELF compat updates from Al Viro:
"Sanitizing ELF compat support, especially for triarch architectures:
- X32 handling cleaned up
- MIPS64 uses compat_binfmt_elf.c both for O32 and N32 now
- Kconfig side of things regularized
Eventually I hope to have compat_binfmt_elf.c killed, with both native
and compat built from fs/binfmt_elf.c, with -DELF_BITS={64,32} passed
by kbuild, but that's a separate story - not included here"
* 'work.elf-compat' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
get rid of COMPAT_ELF_EXEC_PAGESIZE
compat_binfmt_elf: don't bother with undef of ELF_ARCH
Kconfig: regularize selection of CONFIG_BINFMT_ELF
mips compat: switch to compat_binfmt_elf.c
mips: don't bother with ELF_CORE_EFLAGS
mips compat: don't bother with ELF_ET_DYN_BASE
mips: KVM_GUEST makes no sense for 64bit builds...
mips: kill unused definitions in binfmt_elf[on]32.c
mips binfmt_elf*32.c: use elfcore-compat.h
x32: make X32, !IA32_EMULATION setups able to execute x32 binaries
[amd64] clean PRSTATUS_SIZE/SET_PR_FPVALID up properly
elf_prstatus: collect the common part (everything before pr_reg) into a struct
binfmt_elf: partially sanitize PRSTATUS_SIZE and SET_PR_FPVALID
Pull x86 asm updates from Borislav Petkov:
"Annotate new MMIO-accessing insn wrappers' arguments with __iomem"
* tag 'x86_asm_for_v5.12' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/asm: Add a missing __iomem annotation in enqcmds()
x86/asm: Annotate movdir64b()'s dst argument with __iomem
Pull x86 resource control updates from Borislav Petkov:
"Avoid IPI-ing a task in certain cases and prevent load/store tearing
when accessing a task's resctrl fields concurrently"
* tag 'x86_cache_for_v5.12' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/resctrl: Apply READ_ONCE/WRITE_ONCE to task_struct.{rmid,closid}
x86/resctrl: Use task_curr() instead of task_struct->on_cpu to prevent unnecessary IPI
x86/resctrl: Add printf attribute to log function
Pull x86 CPUID cleanup from Borislav Petkov:
"Assign a dedicated feature word to a CPUID leaf which is widely used"
* tag 'x86_cpu_for_v5.12' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/cpufeatures: Assign dedicated feature word for CPUID_0x8000001F[EAX]
Pull x86 FPU updates from Borislav Petkov:
"x86 fpu usage optimization and cleanups:
- make 64-bit kernel code which uses 387 insns request a x87 init
(FNINIT) explicitly when using the FPU
- misc cleanups"
* tag 'x86_fpu_for_v5.12' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/fpu/xstate: Use sizeof() instead of a constant
x86/fpu/64: Don't FNINIT in kernel_fpu_begin()
x86/fpu: Make the EFI FPU calling convention explicit
Pull x86 microcode cleanup from Borislav Petkov:
"Make the driver init function static again"
* tag 'x86_microcode_for_v5.12' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/microcode: Make microcode_init() static
Pull x86 mm cleanups from Borislav Petkov:
- PTRACE_GETREGS/PTRACE_PUTREGS regset selection cleanup
- Another initial cleanup - more to follow - to the fault handling
code.
- Other minor cleanups and corrections.
* tag 'x86_mm_for_v5.12' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (23 commits)
x86/{fault,efi}: Fix and rename efi_recover_from_page_fault()
x86/fault: Don't run fixups for SMAP violations
x86/fault: Don't look for extable entries for SMEP violations
x86/fault: Rename no_context() to kernelmode_fixup_or_oops()
x86/fault: Bypass no_context() for implicit kernel faults from usermode
x86/fault: Split the OOPS code out from no_context()
x86/fault: Improve kernel-executing-user-memory handling
x86/fault: Correct a few user vs kernel checks wrt WRUSS
x86/fault: Document the locking in the fault_signal_pending() path
x86/fault/32: Move is_f00f_bug() to do_kern_addr_fault()
x86/fault: Fold mm_fault_error() into do_user_addr_fault()
x86/fault: Skip the AMD erratum #91 workaround on unaffected CPUs
x86/fault: Fix AMD erratum #91 errata fixup for user code
x86/Kconfig: Remove HPET_EMULATE_RTC depends on RTC
x86/asm: Fixup TASK_SIZE_MAX comment
x86/ptrace: Clean up PTRACE_GETREGS/PTRACE_PUTREGS regset selection
x86/vm86/32: Remove VM86_SCREEN_BITMAP support
x86: Remove definition of DEBUG
x86/entry: Remove now unused do_IRQ() declaration
x86/mm: Remove duplicate definition of _PAGE_PAT_LARGE
...
Pull x86 paravirt updates from Borislav Petkov:
"Part one of a major conversion of the paravirt infrastructure to our
kernel patching facilities and getting rid of the custom-grown ones"
* tag 'x86_paravirt_for_v5.12' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/pv: Rework arch_local_irq_restore() to not use popf
x86/xen: Drop USERGS_SYSRET64 paravirt call
x86/pv: Switch SWAPGS to ALTERNATIVE
x86/xen: Use specific Xen pv interrupt entry for DF
x86/xen: Use specific Xen pv interrupt entry for MCE
Pull EFI updates from Ard Biesheuvel via Borislav Petkov:
"A few cleanups left and right, some of which were part of a initrd
measured boot series that needs some more work, and so only the
cleanup patches have been included for this release"
* tag 'efi-next-for-v5.12' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
efi/arm64: Update debug prints to reflect other entropy sources
efi: x86: clean up previous struct mm switching
efi: x86: move mixed mode stack PA variable out of 'efi_scratch'
efi/libstub: move TPM related prototypes into efistub.h
efi/libstub: fix prototype of efi_tcg2_protocol::get_event_log()
efi/libstub: whitespace cleanup
efi: ia64: move IA64-only declarations to new asm/efi.h header
Pull RAS updates from Borislav Petkov:
- move therm_throt.c to the thermal framework, where it belongs.
- identify CPUs which miss to enter the broadcast handler, as an
additional debugging aid.
* tag 'ras_updates_for_v5.12' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
thermal: Move therm_throt there from x86/mce
x86/mce: Get rid of mcheck_intel_therm_init()
x86/mce: Make mce_timed_out() identify holdout CPUs
Use the new EXPORT_STATIC_CALL_TRAMP() / static_call_mod() to unexport
the static_call_key for the PREEMPT_DYNAMIC calls such that modules
can no longer update these calls.
Having modules change/hi-jack the preemption calls would be horrible.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
When exporting static_call_key; with EXPORT_STATIC_CALL*(), the module
can use static_call_update() to change the function called. This is
not desirable in general.
Not exporting static_call_key however also disallows usage of
static_call(), since objtool needs the key to construct the
static_call_site.
Solve this by allowing objtool to create the static_call_site using
the trampoline address when it builds a module and cannot find the
static_call_key symbol. The module loader will then try and map the
trampole back to a key before it constructs the normal sites list.
Doing this requires a trampoline -> key associsation, so add another
magic section that keeps those.
Originally-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lkml.kernel.org/r/20210127231837.ifddpn7rhwdaepiu@treble
Provide static calls to control preempt_schedule[_notrace]()
(called in CONFIG_PREEMPT) so that we can override their behaviour when
preempt= is overriden.
Since the default behaviour is full preemption, both their calls are
initialized to the arch provided wrapper, if any.
[fweisbec: only define static calls when PREEMPT_DYNAMIC, make it less
dependent on x86 with __preempt_schedule_func]
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lkml.kernel.org/r/20210118141223.123667-7-frederic@kernel.org
efi_recover_from_page_fault() doesn't recover -- it does a special EFI
mini-oops. Rename it to make it clear that it crashes.
While renaming it, I noticed a blatant bug: a page fault oops in a
different thread happening concurrently with an EFI runtime service call
would be misinterpreted as an EFI page fault. Fix that.
This isn't quite exact. The situation could be improved by using a
special CS for calls into EFI.
[ bp: Massage commit message and simplify in interrupt check. ]
Signed-off-by: Andy Lutomirski <luto@kernel.org>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/f43b1e80830dc78ed60ed8b0826f4f189254570c.1612924255.git.luto@kernel.org
POPF is a rather expensive operation, so don't use it for restoring
irq flags. Instead, test whether interrupts are enabled in the flags
parameter and enable interrupts via STI in that case.
This results in the restore_fl paravirt op to be no longer needed.
Suggested-by: Andy Lutomirski <luto@kernel.org>
Signed-off-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20210120135555.32594-7-jgross@suse.com
USERGS_SYSRET64 is used to return from a syscall via SYSRET, but
a Xen PV guest will nevertheless use the IRET hypercall, as there
is no sysret PV hypercall defined.
So instead of testing all the prerequisites for doing a sysret and
then mangling the stack for Xen PV again for doing an iret just use
the iret exit from the beginning.
This can easily be done via an ALTERNATIVE like it is done for the
sysenter compat case already.
It should be noted that this drops the optimization in Xen for not
restoring a few registers when returning to user mode, but it seems
as if the saved instructions in the kernel more than compensate for
this drop (a kernel build in a Xen PV guest was slightly faster with
this patch applied).
While at it remove the stale sysret32 remnants.
Signed-off-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20210120135555.32594-6-jgross@suse.com
SWAPGS is used only for interrupts coming from user mode or for
returning to user mode. So there is no reason to use the PARAVIRT
framework, as it can easily be replaced by an ALTERNATIVE depending
on X86_FEATURE_XENPV.
There are several instances using the PV-aware SWAPGS macro in paths
which are never executed in a Xen PV guest. Replace those with the
plain swapgs instruction. For SWAPGS_UNSAFE_STACK the same applies.
Signed-off-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Andy Lutomirski <luto@kernel.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20210120135555.32594-5-jgross@suse.com
Pull syscall entry fixes from Borislav Petkov:
- For syscall user dispatch, separate prctl operation from syscall
redirection range specification before the API has been made official
in 5.11.
- Ensure tasks using the generic syscall code do trap after returning
from a syscall when single-stepping is requested.
* tag 'core_urgent_for_v5.11_rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
entry: Use different define for selector variable in SUD
entry: Ensure trap after single-step on system call return
Pull x86 fixes from Borislav Petkov:
"I hope this is the last batch of x86/urgent updates for this round:
- Remove superfluous EFI PGD range checks which lead to those
assertions failing with certain kernel configs and LLVM.
- Disable setting breakpoints on facilities involved in #DB exception
handling to avoid infinite loops.
- Add extra serialization to non-serializing MSRs (IA32_TSC_DEADLINE
and x2 APIC MSRs) to adhere to SDM's recommendation and avoid any
theoretical issues.
- Re-add the EPB MSR reading on turbostat so that it works on older
kernels which don't have the corresponding EPB sysfs file.
- Add Alder Lake to the list of CPUs which support split lock.
- Fix %dr6 register handling in order to be able to set watchpoints
with gdb again.
- Disable CET instrumentation in the kernel so that gcc doesn't add
ENDBR64 to kernel code and thus confuse tracing"
* tag 'x86_urgent_for_v5.11_rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/efi: Remove EFI PGD build time checks
x86/debug: Prevent data breakpoints on cpu_dr7
x86/debug: Prevent data breakpoints on __per_cpu_offset
x86/apic: Add extra serialization for non-serializing MSRs
tools/power/turbostat: Fallback to an MSR read for EPB
x86/split_lock: Enable the split lock feature on another Alder Lake CPU
x86/debug: Fix DR6 handling
x86/build: Disable CET instrumentation in the kernel
Commit 2991552447 ("entry: Drop usage of TIF flags in the generic syscall
code") introduced a bug on architectures using the generic syscall entry
code, in which processes stopped by PTRACE_SYSCALL do not trap on syscall
return after receiving a TIF_SINGLESTEP.
The reason is that the meaning of TIF_SINGLESTEP flag is overloaded to
cause the trap after a system call is executed, but since the above commit,
the syscall call handler only checks for the SYSCALL_WORK flags on the exit
work.
Split the meaning of TIF_SINGLESTEP such that it only means single-step
mode, and create a new type of SYSCALL_WORK to request a trap immediately
after a syscall in single-step mode. In the current implementation, the
SYSCALL_WORK flag shadows the TIF_SINGLESTEP flag for simplicity.
Update x86 to flip this bit when a tracer enables single stepping.
Fixes: 2991552447 ("entry: Drop usage of TIF flags in the generic syscall code")
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Kyle Huey <me@kylehuey.com>
Link: https://lore.kernel.org/r/87h7mtc9pr.fsf_-_@collabora.com
Comment says "by preventing anything executable" which is not true. Even
PROT_NONE mapping can't be installed at (1<<47 - 4096).
mmap(0x7ffffffff000, 4096, PROT_NONE, MAP_PRIVATE|MAP_FIXED|MAP_ANONYMOUS, -1, 0) = -1 ENOMEM
[ bp: Fixup to the moved location in page_64_types.h. ]
Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Andy Lutomirski <luto@kernel.org>
Link: https://lkml.kernel.org/r/20200305181719.GA5490@avx2
Jan Kiszka reported that the x2apic_wrmsr_fence() function uses a plain
MFENCE while the Intel SDM (10.12.3 MSR Access in x2APIC Mode) calls for
MFENCE; LFENCE.
Short summary: we have special MSRs that have weaker ordering than all
the rest. Add fencing consistent with current SDM recommendations.
This is not known to cause any issues in practice, only in theory.
Longer story below:
The reason the kernel uses a different semantic is that the SDM changed
(roughly in late 2017). The SDM changed because folks at Intel were
auditing all of the recommended fences in the SDM and realized that the
x2apic fences were insufficient.
Why was the pain MFENCE judged insufficient?
WRMSR itself is normally a serializing instruction. No fences are needed
because the instruction itself serializes everything.
But, there are explicit exceptions for this serializing behavior written
into the WRMSR instruction documentation for two classes of MSRs:
IA32_TSC_DEADLINE and the X2APIC MSRs.
Back to x2apic: WRMSR is *not* serializing in this specific case.
But why is MFENCE insufficient? MFENCE makes writes visible, but
only affects load/store instructions. WRMSR is unfortunately not a
load/store instruction and is unaffected by MFENCE. This means that a
non-serializing WRMSR could be reordered by the CPU to execute before
the writes made visible by the MFENCE have even occurred in the first
place.
This means that an x2apic IPI could theoretically be triggered before
there is any (visible) data to process.
Does this affect anything in practice? I honestly don't know. It seems
quite possible that by the time an interrupt gets to consume the (not
yet) MFENCE'd data, it has become visible, mostly by accident.
To be safe, add the SDM-recommended fences for all x2apic WRMSRs.
This also leaves open the question of the _other_ weakly-ordered WRMSR:
MSR_IA32_TSC_DEADLINE. While it has the same ordering architecture as
the x2APIC MSRs, it seems substantially less likely to be a problem in
practice. While writes to the in-memory Local Vector Table (LVT) might
theoretically be reordered with respect to a weakly-ordered WRMSR like
TSC_DEADLINE, the SDM has this to say:
In x2APIC mode, the WRMSR instruction is used to write to the LVT
entry. The processor ensures the ordering of this write and any
subsequent WRMSR to the deadline; no fencing is required.
But, that might still leave xAPIC exposed. The safest thing to do for
now is to add the extra, recommended LFENCE.
[ bp: Massage commit message, fix typos, drop accidentally added
newline to tools/arch/x86/include/asm/barrier.h. ]
Reported-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Cc: <stable@vger.kernel.org>
Link: https://lkml.kernel.org/r/20200305174708.F77040DD@viggo.jf.intel.com
Add perf core PMU support for the Intel Sapphire Rapids server, which is
the successor of the Intel Ice Lake server. The enabling code is based
on Ice Lake, but there are several new features introduced.
The event encoding is changed and simplified, e.g., the event codes
which are below 0x90 are restricted to counters 0-3. The event codes
which above 0x90 are likely to have no restrictions. The event
constraints, extra_regs(), and hardware cache events table are changed
accordingly.
A new Precise Distribution (PDist) facility is introduced, which
further minimizes the skid when a precise event is programmed on the GP
counter 0. Enable the Precise Distribution (PDist) facility with :ppp
event. For this facility to work, the period must be initialized with a
value larger than 127. Add spr_limit_period() to apply the limit for
:ppp event.
Two new data source fields, data block & address block, are added in the
PEBS Memory Info Record for the load latency event. To enable the
feature,
- An auxiliary event has to be enabled together with the load latency
event on Sapphire Rapids. A new flag PMU_FL_MEM_LOADS_AUX is
introduced to indicate the case. A new event, mem-loads-aux, is
exposed to sysfs for the user tool.
Add a check in hw_config(). If the auxiliary event is not detected,
return an unique error -ENODATA.
- The union perf_mem_data_src is extended to support the new fields.
- Ice Lake and earlier models do not support block information, but the
fields may be set by HW on some machines. Add pebs_no_block to
explicitly indicate the previous platforms which don't support the new
block fields. Accessing the new block fields are ignored on those
platforms.
A new store Latency facility is introduced, which leverages the PEBS
facility where it can provide additional information about sampled
stores. The additional information includes the data address, memory
auxiliary info (e.g. Data Source, STLB miss) and the latency of the
store access. To enable the facility, the new event (0x02cd) has to be
programed on the GP counter 0. A new flag PERF_X86_EVENT_PEBS_STLAT is
introduced to indicate the event. The store_latency_data() is introduced
to parse the memory auxiliary info.
The layout of access latency field of PEBS Memory Info Record has been
changed. Two latency, instruction latency (bit 15:0) and cache access
latency (bit 47:32) are recorded.
- The cache access latency is similar to previous memory access latency.
For loads, the latency starts by the actual cache access until the
data is returned by the memory subsystem.
For stores, the latency starts when the demand write accesses the L1
data cache and lasts until the cacheline write is completed in the
memory subsystem.
The cache access latency is stored in low 32bits of the sample type
PERF_SAMPLE_WEIGHT_STRUCT.
- The instruction latency starts by the dispatch of the load operation
for execution and lasts until completion of the instruction it belongs
to.
Add a new flag PMU_FL_INSTR_LATENCY to indicate the instruction
latency support. The instruction latency is stored in the bit 47:32
of the sample type PERF_SAMPLE_WEIGHT_STRUCT.
Extends the PERF_METRICS MSR to feature TMA method level 2 metrics. The
lower half of the register is the TMA level 1 metrics (legacy). The
upper half is also divided into four 8-bit fields for the new level 2
metrics. Expose all eight Topdown metrics events to user space.
The full description for the SPR features can be found at Intel
Architecture Instruction Set Extensions and Future Features
Programming Reference, 319433-041.
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/1611873611-156687-5-git-send-email-kan.liang@linux.intel.com
Intel Sapphire Rapids server will introduce 8 metrics events. Intel
Ice Lake only supports 4 metrics events. A perf tool user may mistakenly
use the unsupported events via RAW format on Ice Lake. The user can
still get a value from the unsupported Topdown metrics event once the
following Sapphire Rapids enabling patch is applied.
To enable the 8 metrics events on Intel Sapphire Rapids, the
INTEL_TD_METRIC_MAX has to be updated, which impacts the
is_metric_event(). The is_metric_event() is a generic function.
On Ice Lake, the newly added SPR metrics events will be mistakenly
accepted as metric events on creation. At runtime, the unsupported
Topdown metrics events will be updated.
Add a variable num_topdown_events in x86_pmu to indicate the available
number of the Topdown metrics event on the platform. Apply the number
into is_metric_event(). Only the supported Topdown metrics events
should be created as metrics events.
Apply the num_topdown_events in icl_update_topdown_event() as well. The
function can be reused by the following patch.
Suggested-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/1611873611-156687-4-git-send-email-kan.liang@linux.intel.com
EFI uses kernel_fpu_begin() to conform to the UEFI calling convention.
This specifically requires initializing FCW (FPU Control Word), whereas
no sane 64-bit kernel code should use legacy 387 operations that
reference FCW.
This should allow to safely change the default semantics of
kernel_fpu_begin() to stop initializing FCW on 64-bit kernels.
[ bp: Massage commit message a little. ]
Signed-off-by: Andy Lutomirski <luto@kernel.org>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/25d392fff64680e0f4bb8cf0b1003314dc29eafe.1611205691.git.luto@kernel.org
Pull xen fixes from Juergen Gross:
- A fix for a regression introduced in 5.11 resulting in Xen dom0
having problems to correctly initialize Xenstore.
- A fix for avoiding WARN splats when booting as Xen dom0 with
CONFIG_AMD_MEM_ENCRYPT enabled due to a missing trap handler for the
#VC exception (even if the handler should never be called).
- A fix for the Xen bklfront driver adapting to the correct but
unexpected behavior of new qemu.
* tag 'for-linus-5.11-rc6-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip:
x86/xen: avoid warning in Xen pv guest with CONFIG_AMD_MEM_ENCRYPT enabled
xen: Fix XenStore initialisation for XS_LOCAL
xen-blkfront: allow discard-* nodes to be optional
Collect the scattered SME/SEV related feature flags into a dedicated
word. There are now five recognized features in CPUID.0x8000001F.EAX,
with at least one more on the horizon (SEV-SNP). Using a dedicated word
allows KVM to use its automagic CPUID adjustment logic when reporting
the set of supported features to userspace.
No functional change intended.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Brijesh Singh <brijesh.singh@amd.com>
Link: https://lkml.kernel.org/r/20210122204047.2860075-2-seanjc@google.com
Pull x86 fixes from Borislav Petkov:
- Add a new Intel model number for Alder Lake
- Differentiate which aspects of the FPU state get saved/restored when
the FPU is used in-kernel and fix a boot crash on K7 due to early
MXCSR access before CR4.OSFXSR is even set.
- A couple of noinstr annotation fixes
- Correct die ID setting on AMD for users of topology information which
need the correct die ID
- A SEV-ES fix to handle string port IO to/from kernel memory properly
* tag 'x86_urgent_for_v5.11_rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/cpu: Add another Alder Lake CPU to the Intel family
x86/mmx: Use KFPU_387 for MMX string operations
x86/fpu: Add kernel_fpu_begin_mask() to selectively initialize state
x86/topology: Make __max_die_per_package available unconditionally
x86: __always_inline __{rd,wr}msr()
x86/mce: Remove explicit/superfluous tracing
locking/lockdep: Avoid noinstr warning for DEBUG_LOCKDEP
locking/lockdep: Cure noinstr fail
x86/sev: Fix nonistr violation
x86/entry: Fix noinstr fail
x86/cpu/amd: Set __max_die_per_package on AMD
x86/sev-es: Handle string port IO to kernel memory properly
The implementation was rather buggy. It unconditionally marked PTEs
read-only, even for VM_SHARED mappings. I'm not sure whether this is
actually a problem, but it certainly seems unwise. More importantly, it
released the mmap lock before flushing the TLB, which could allow a racing
CoW operation to falsely believe that the underlying memory was not
writable.
I can't find any users at all of this mechanism, so just remove it.
Signed-off-by: Andy Lutomirski <luto@kernel.org>
Signed-off-by: Borislav Petkov <bp@suse.de>
Acked-by: Stas Sergeev <stsp2@yandex.ru>
Link: https://lkml.kernel.org/r/f3086de0babcab36f69949b5780bde851f719bc8.1611078018.git.luto@kernel.org
Currently, requesting kernel FPU access doesn't distinguish which parts of
the extended ("FPU") state are needed. This is nice for simplicity, but
there are a few cases in which it's suboptimal:
- The vast majority of in-kernel FPU users want XMM/YMM/ZMM state but do
not use legacy 387 state. These users want MXCSR initialized but don't
care about the FPU control word. Skipping FNINIT would save time.
(Empirically, FNINIT is several times slower than LDMXCSR.)
- Code that wants MMX doesn't want or need MXCSR initialized.
_mmx_memcpy(), for example, can run before CR4.OSFXSR gets set, and
initializing MXCSR will fail because LDMXCSR generates an #UD when the
aforementioned CR4 bit is not set.
- Any future in-kernel users of XFD (eXtended Feature Disable)-capable
dynamic states will need special handling.
Add a more specific API that allows callers to specify exactly what they
want.
Signed-off-by: Andy Lutomirski <luto@kernel.org>
Signed-off-by: Borislav Petkov <bp@suse.de>
Tested-by: Krzysztof Piotr Olędzki <ole@ans.pl>
Link: https://lkml.kernel.org/r/aff1cac8b8fc7ee900cf73e8f2369966621b053f.1611205691.git.luto@kernel.org
EFI on x86_64 keeps track of the process's MM pointer by storing it
in a global struct called 'efi_scratch', which also used to contain
the mixed mode stack pointer. Let's clean this up a little bit, by
getting rid of the struct, and pushing the mm handling into the
callees entirely.
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
As a first step to removing the awkward 'struct efi_scratch' definition
that conveniently combines the storage of the mixed mode stack pointer
with the MM pointer variable that records the task's MM pointer while it
is being replaced with the EFI MM one, move the mixed mode stack pointer
into a separate variable.
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
